724 files changed, 57311 insertions, 19296 deletions

diff --git a/drivers/net/ethernet/3com/3c509.c b/drivers/net/ethernet/3com/3c509.c
index b223769d6a5e..3da97996bdf3 100644
--- a/drivers/net/ethernet/3com/3c509.c
+++ b/drivers/net/ethernet/3com/3c509.c
@@ -1266,12 +1266,14 @@ el3_up(struct net_device *dev)
 					pr_cont("Forcing 3c5x9b full-duplex mode");
 					break;
 				}
+				/* fall through */
 			case 8:
 				/* set full-duplex mode based on eeprom config setting */
 				if ((sw_info & 0x000f) && (sw_info & 0x8000)) {
 					pr_cont("Setting 3c5x9b full-duplex mode (from EEPROM configuration bit)");
 					break;
 				}
+				/* fall through */
 			default:
 				/* xcvr=(0 || 4) OR user has an old 3c5x9 non "B" model */
 				pr_cont("Setting 3c5x9/3c5x9B half-duplex mode");
diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c
index b648e3f95c01..b15752267c8d 100644
--- a/drivers/net/ethernet/3com/3c515.c
+++ b/drivers/net/ethernet/3com/3c515.c
@@ -1177,7 +1177,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id)
 				if (inl(ioaddr + DownListPtr) == isa_virt_to_bus(&lp->tx_ring[entry]))
 					break;	/* It still hasn't been processed. */
 				if (lp->tx_skbuff[entry]) {
-					dev_kfree_skb_irq(lp->tx_skbuff[entry]);
+					dev_consume_skb_irq(lp->tx_skbuff[entry]);
 					lp->tx_skbuff[entry] = NULL;
 				}
 				dirty_tx++;
@@ -1192,7 +1192,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id)
 #ifdef VORTEX_BUS_MASTER
 		if (status & DMADone) {
 			outw(0x1000, ioaddr + Wn7_MasterStatus);	/* Ack the event. */
-			dev_kfree_skb_irq(lp->tx_skb);	/* Release the transferred buffer */
+			dev_consume_skb_irq(lp->tx_skb);	/* Release the transferred buffer */
 			netif_wake_queue(dev);
 		}
 #endif
@@ -1521,7 +1521,7 @@ static void update_stats(int ioaddr, struct net_device *dev)
 static void set_rx_mode(struct net_device *dev)
 {
 	int ioaddr = dev->base_addr;
-	short new_mode;
+	unsigned short new_mode;
 
 	if (dev->flags & IFF_PROMISC) {
 		if (corkscrew_debug > 3)
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 5bc168314ea2..147051404194 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1151,7 +1151,7 @@ static int vortex_probe1(struct device *gendev, void __iomem *ioaddr, int irq,
 
 	print_info = (vortex_debug > 1);
 	if (print_info)
-		pr_info("See Documentation/networking/vortex.txt\n");
+		pr_info("See Documentation/networking/device_drivers/3com/vortex.txt\n");
 
 	pr_info("%s: 3Com %s %s at %p.\n",
 	       print_name,
@@ -1956,7 +1956,7 @@ vortex_error(struct net_device *dev, int status)
 				   dev->name, tx_status);
 			if (tx_status == 0x82) {
 				pr_err("Probably a duplex mismatch.  See "
-						"Documentation/networking/vortex.txt\n");
+						"Documentation/networking/device_drivers/3com/vortex.txt\n");
 			}
 			dump_tx_ring(dev);
 		}
@@ -2307,7 +2307,7 @@ _vortex_interrupt(int irq, struct net_device *dev)
 				dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE);
 				pkts_compl++;
 				bytes_compl += vp->tx_skb->len;
-				dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */
+				dev_consume_skb_irq(vp->tx_skb); /* Release the transferred buffer */
 				if (ioread16(ioaddr + TxFree) > 1536) {
 					/*
 					 * AKPM: FIXME: I don't think we need this.  If the queue was stopped due to
@@ -2449,7 +2449,7 @@ _boomerang_interrupt(int irq, struct net_device *dev)
 #endif
 					pkts_compl++;
 					bytes_compl += skb->len;
-					dev_kfree_skb_irq(skb);
+					dev_consume_skb_irq(skb);
 					vp->tx_skbuff[entry] = NULL;
 				} else {
 					pr_debug("boomerang_interrupt: no skb!\n");
diff --git a/drivers/net/ethernet/3com/Kconfig b/drivers/net/ethernet/3com/Kconfig
index 5c3ef9fc8207..0ac44ef1f7a9 100644
--- a/drivers/net/ethernet/3com/Kconfig
+++ b/drivers/net/ethernet/3com/Kconfig
@@ -75,8 +75,9 @@ config VORTEX
 	  "Hurricane" (3c555/3cSOHO)                           PCI
 
 	  If you have such a card, say Y here.  More specific information is in
-	  <file:Documentation/networking/vortex.txt> and in the comments at
-	  the beginning of <file:drivers/net/ethernet/3com/3c59x.c>.
+	  <file:Documentation/networking/device_drivers/3com/vortex.txt> and
+	  in the comments at the beginning of
+	  <file:drivers/net/ethernet/3com/3c59x.c>.
 
 	  To compile this support as a module, choose M here.
 
diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index 342ae08ec3c2..d60a86aa8aa8 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,8 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
-
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
 static void slow_sane_get_8390_hdr(struct net_device *dev,
 				   struct e8390_pkt_hdr *hdr, int ring_page);
@@ -233,19 +231,26 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres)
 
 static enum mac8390_access mac8390_testio(unsigned long membase)
 {
-	unsigned long outdata = 0xA5A0B5B0;
-	unsigned long indata =  0x00000000;
+	u32 outdata = 0xA5A0B5B0;
+	u32 indata = 0;
+
 	/* Try writing 32 bits */
-	memcpy_toio((void __iomem *)membase, &outdata, 4);
-	/* Now compare them */
-	if (memcmp_withio(&outdata, membase, 4) == 0)
+	nubus_writel(outdata, membase);
+	/* Now read it back */
+	indata = nubus_readl(membase);
+	if (outdata == indata)
 		return ACCESS_32;
+
+	outdata = 0xC5C0D5D0;
+	indata = 0;
+
 	/* Write 16 bit output */
 	word_memcpy_tocard(membase, &outdata, 4);
 	/* Now read it back */
 	word_memcpy_fromcard(&indata, membase, 4);
 	if (outdata == indata)
 		return ACCESS_16;
+
 	return ACCESS_UNKNOWN;
 }
 
diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c
index 61e43802b9a5..645efac6310d 100644
--- a/drivers/net/ethernet/8390/pcnet_cs.c
+++ b/drivers/net/ethernet/8390/pcnet_cs.c
@@ -289,6 +289,11 @@ static struct hw_info *get_hwinfo(struct pcmcia_device *link)
 
     virt = ioremap(link->resource[2]->start,
 	    resource_size(link->resource[2]));
+    if (unlikely(!virt)) {
+	    pcmcia_release_window(link, link->resource[2]);
+	    return NULL;
+    }
+
     for (i = 0; i < NR_INFO; i++) {
 	pcmcia_map_mem_page(link, link->resource[2],
 		hw_info[i].offset & ~(resource_size(link->resource[2])-1));
@@ -1423,6 +1428,11 @@ static int setup_shmem_window(struct pcmcia_device *link, int start_pg,
     /* Try scribbling on the buffer */
     info->base = ioremap(link->resource[3]->start,
 			resource_size(link->resource[3]));
+    if (unlikely(!info->base)) {
+	    ret = -ENOMEM;
+	    goto failed;
+    }
+
     for (i = 0; i < (TX_PAGES<<8); i += 2)
 	__raw_writew((i>>1), info->base+offset+i);
     udelay(100);
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 097467f44b0d..816540e6beac 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -1390,7 +1390,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 					}
 				}
 
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 			}
 			np->tx_done_q[np->tx_done].status = 0;
 			np->tx_done = (np->tx_done + 1) % DONE_Q_SIZE;
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 7c9348a26cbb..47e5984f16fb 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1283,7 +1283,7 @@ static int greth_mdio_probe(struct net_device *dev)
 	else
 		phy_set_max_speed(phy, SPEED_100);
 
-	phy->advertising = phy->supported;
+	linkmode_copy(phy->advertising, phy->supported);
 
 	greth->link = 0;
 	greth->speed = 0;
@@ -1433,18 +1433,18 @@ static int greth_of_probe(struct platform_device *ofdev)
 	}
 
 	/* Allocate TX descriptor ring in coherent memory */
-	greth->tx_bd_base = dma_zalloc_coherent(greth->dev, 1024,
-						&greth->tx_bd_base_phys,
-						GFP_KERNEL);
+	greth->tx_bd_base = dma_alloc_coherent(greth->dev, 1024,
+					       &greth->tx_bd_base_phys,
+					       GFP_KERNEL);
 	if (!greth->tx_bd_base) {
 		err = -ENOMEM;
 		goto error3;
 	}
 
 	/* Allocate RX descriptor ring in coherent memory */
-	greth->rx_bd_base = dma_zalloc_coherent(greth->dev, 1024,
-						&greth->rx_bd_base_phys,
-						GFP_KERNEL);
+	greth->rx_bd_base = dma_alloc_coherent(greth->dev, 1024,
+					       &greth->rx_bd_base_phys,
+					       GFP_KERNEL);
 	if (!greth->rx_bd_base) {
 		err = -ENOMEM;
 		goto error4;
diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c
index 0b60921c392f..16477aa6d61f 100644
--- a/drivers/net/ethernet/alacritech/slicoss.c
+++ b/drivers/net/ethernet/alacritech/slicoss.c
@@ -795,8 +795,8 @@ static int slic_init_stat_queue(struct slic_device *sdev)
 	size = stq->len * sizeof(*descs) + DESC_ALIGN_MASK;
 
 	for (i = 0; i < SLIC_NUM_STAT_DESC_ARRAYS; i++) {
-		descs = dma_zalloc_coherent(&sdev->pdev->dev, size, &paddr,
-					    GFP_KERNEL);
+		descs = dma_alloc_coherent(&sdev->pdev->dev, size, &paddr,
+					   GFP_KERNEL);
 		if (!descs) {
 			netdev_err(sdev->netdev,
 				   "failed to allocate status descriptors\n");
@@ -1240,8 +1240,8 @@ static int slic_init_shmem(struct slic_device *sdev)
 	struct slic_shmem_data *sm_data;
 	dma_addr_t paddr;
 
-	sm_data = dma_zalloc_coherent(&sdev->pdev->dev, sizeof(*sm_data),
-				      &paddr, GFP_KERNEL);
+	sm_data = dma_alloc_coherent(&sdev->pdev->dev, sizeof(*sm_data),
+				     &paddr, GFP_KERNEL);
 	if (!sm_data) {
 		dev_err(&sdev->pdev->dev, "failed to allocate shared memory\n");
 		return -ENOMEM;
@@ -1621,8 +1621,8 @@ static int slic_read_eeprom(struct slic_device *sdev)
 	int err = 0;
 	u8 *mac[2];
 
-	eeprom = dma_zalloc_coherent(&sdev->pdev->dev, SLIC_EEPROM_SIZE,
-				     &paddr, GFP_KERNEL);
+	eeprom = dma_alloc_coherent(&sdev->pdev->dev, SLIC_EEPROM_SIZE,
+				    &paddr, GFP_KERNEL);
 	if (!eeprom)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 4f11f98347ed..1827ef1f6d55 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -2059,7 +2059,7 @@ static inline void ace_tx_int(struct net_device *dev,
 		if (skb) {
 			dev->stats.tx_packets++;
 			dev->stats.tx_bytes += skb->len;
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			info->skb = NULL;
 		}
 
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 0fb986ba3290..0ae723f75341 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
 			& 0xffff;
 
 	if (inuse) { /* Tx FIFO is not empty */
-		ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+		ready = max_t(int,
+			      priv->tx_prod - priv->tx_cons - inuse - 1, 0);
 	} else {
 		/* Check for buffered last packet */
 		status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c
index 02921d877c08..aa1d1f5339d2 100644
--- a/drivers/net/ethernet/altera/altera_tse_main.c
+++ b/drivers/net/ethernet/altera/altera_tse_main.c
@@ -714,8 +714,10 @@ static struct phy_device *connect_local_phy(struct net_device *dev)
 
 		phydev = phy_connect(dev, phy_id_fmt, &altera_tse_adjust_link,
 				     priv->phy_iface);
-		if (IS_ERR(phydev))
+		if (IS_ERR(phydev)) {
 			netdev_err(dev, "Could not attach to PHY\n");
+			phydev = NULL;
+		}
 
 	} else {
 		int ret;
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 420cede41ca4..b17d435de09f 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -111,8 +111,8 @@ static int ena_com_admin_init_sq(struct ena_com_admin_queue *queue)
 	struct ena_com_admin_sq *sq = &queue->sq;
 	u16 size = ADMIN_SQ_SIZE(queue->q_depth);
 
-	sq->entries = dma_zalloc_coherent(queue->q_dmadev, size, &sq->dma_addr,
-					  GFP_KERNEL);
+	sq->entries = dma_alloc_coherent(queue->q_dmadev, size, &sq->dma_addr,
+					 GFP_KERNEL);
 
 	if (!sq->entries) {
 		pr_err("memory allocation failed");
@@ -133,8 +133,8 @@ static int ena_com_admin_init_cq(struct ena_com_admin_queue *queue)
 	struct ena_com_admin_cq *cq = &queue->cq;
 	u16 size = ADMIN_CQ_SIZE(queue->q_depth);
 
-	cq->entries = dma_zalloc_coherent(queue->q_dmadev, size, &cq->dma_addr,
-					  GFP_KERNEL);
+	cq->entries = dma_alloc_coherent(queue->q_dmadev, size, &cq->dma_addr,
+					 GFP_KERNEL);
 
 	if (!cq->entries) {
 		pr_err("memory allocation failed");
@@ -156,8 +156,8 @@ static int ena_com_admin_init_aenq(struct ena_com_dev *dev,
 
 	dev->aenq.q_depth = ENA_ASYNC_QUEUE_DEPTH;
 	size = ADMIN_AENQ_SIZE(ENA_ASYNC_QUEUE_DEPTH);
-	aenq->entries = dma_zalloc_coherent(dev->dmadev, size, &aenq->dma_addr,
-					    GFP_KERNEL);
+	aenq->entries = dma_alloc_coherent(dev->dmadev, size, &aenq->dma_addr,
+					   GFP_KERNEL);
 
 	if (!aenq->entries) {
 		pr_err("memory allocation failed");
@@ -344,15 +344,15 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 		dev_node = dev_to_node(ena_dev->dmadev);
 		set_dev_node(ena_dev->dmadev, ctx->numa_node);
 		io_sq->desc_addr.virt_addr =
-			dma_zalloc_coherent(ena_dev->dmadev, size,
-					    &io_sq->desc_addr.phys_addr,
-					    GFP_KERNEL);
+			dma_alloc_coherent(ena_dev->dmadev, size,
+					   &io_sq->desc_addr.phys_addr,
+					   GFP_KERNEL);
 		set_dev_node(ena_dev->dmadev, dev_node);
 		if (!io_sq->desc_addr.virt_addr) {
 			io_sq->desc_addr.virt_addr =
-				dma_zalloc_coherent(ena_dev->dmadev, size,
-						    &io_sq->desc_addr.phys_addr,
-						    GFP_KERNEL);
+				dma_alloc_coherent(ena_dev->dmadev, size,
+						   &io_sq->desc_addr.phys_addr,
+						   GFP_KERNEL);
 		}
 
 		if (!io_sq->desc_addr.virt_addr) {
@@ -425,14 +425,14 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev,
 	prev_node = dev_to_node(ena_dev->dmadev);
 	set_dev_node(ena_dev->dmadev, ctx->numa_node);
 	io_cq->cdesc_addr.virt_addr =
-		dma_zalloc_coherent(ena_dev->dmadev, size,
-				    &io_cq->cdesc_addr.phys_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev, size,
+				   &io_cq->cdesc_addr.phys_addr, GFP_KERNEL);
 	set_dev_node(ena_dev->dmadev, prev_node);
 	if (!io_cq->cdesc_addr.virt_addr) {
 		io_cq->cdesc_addr.virt_addr =
-			dma_zalloc_coherent(ena_dev->dmadev, size,
-					    &io_cq->cdesc_addr.phys_addr,
-					    GFP_KERNEL);
+			dma_alloc_coherent(ena_dev->dmadev, size,
+					   &io_cq->cdesc_addr.phys_addr,
+					   GFP_KERNEL);
 	}
 
 	if (!io_cq->cdesc_addr.virt_addr) {
@@ -1026,8 +1026,8 @@ static int ena_com_hash_key_allocate(struct ena_com_dev *ena_dev)
 	struct ena_rss *rss = &ena_dev->rss;
 
 	rss->hash_key =
-		dma_zalloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key),
-				    &rss->hash_key_dma_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_key),
+				   &rss->hash_key_dma_addr, GFP_KERNEL);
 
 	if (unlikely(!rss->hash_key))
 		return -ENOMEM;
@@ -1050,8 +1050,8 @@ static int ena_com_hash_ctrl_init(struct ena_com_dev *ena_dev)
 	struct ena_rss *rss = &ena_dev->rss;
 
 	rss->hash_ctrl =
-		dma_zalloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_ctrl),
-				    &rss->hash_ctrl_dma_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev, sizeof(*rss->hash_ctrl),
+				   &rss->hash_ctrl_dma_addr, GFP_KERNEL);
 
 	if (unlikely(!rss->hash_ctrl))
 		return -ENOMEM;
@@ -1094,8 +1094,8 @@ static int ena_com_indirect_table_allocate(struct ena_com_dev *ena_dev,
 		sizeof(struct ena_admin_rss_ind_table_entry);
 
 	rss->rss_ind_tbl =
-		dma_zalloc_coherent(ena_dev->dmadev, tbl_size,
-				    &rss->rss_ind_tbl_dma_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev, tbl_size,
+				   &rss->rss_ind_tbl_dma_addr, GFP_KERNEL);
 	if (unlikely(!rss->rss_ind_tbl))
 		goto mem_err1;
 
@@ -1649,9 +1649,9 @@ int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev)
 
 	spin_lock_init(&mmio_read->lock);
 	mmio_read->read_resp =
-		dma_zalloc_coherent(ena_dev->dmadev,
-				    sizeof(*mmio_read->read_resp),
-				    &mmio_read->read_resp_dma_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev,
+				   sizeof(*mmio_read->read_resp),
+				   &mmio_read->read_resp_dma_addr, GFP_KERNEL);
 	if (unlikely(!mmio_read->read_resp))
 		goto err;
 
@@ -2623,8 +2623,8 @@ int ena_com_allocate_host_info(struct ena_com_dev *ena_dev)
 	struct ena_host_attribute *host_attr = &ena_dev->host_attr;
 
 	host_attr->host_info =
-		dma_zalloc_coherent(ena_dev->dmadev, SZ_4K,
-				    &host_attr->host_info_dma_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev, SZ_4K,
+				   &host_attr->host_info_dma_addr, GFP_KERNEL);
 	if (unlikely(!host_attr->host_info))
 		return -ENOMEM;
 
@@ -2641,8 +2641,9 @@ int ena_com_allocate_debug_area(struct ena_com_dev *ena_dev,
 	struct ena_host_attribute *host_attr = &ena_dev->host_attr;
 
 	host_attr->debug_area_virt_addr =
-		dma_zalloc_coherent(ena_dev->dmadev, debug_area_size,
-				    &host_attr->debug_area_dma_addr, GFP_KERNEL);
+		dma_alloc_coherent(ena_dev->dmadev, debug_area_size,
+				   &host_attr->debug_area_dma_addr,
+				   GFP_KERNEL);
 	if (unlikely(!host_attr->debug_area_virt_addr)) {
 		host_attr->debug_area_size = 0;
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index a70bb1bb90e7..a6eacf2099c3 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter)
 		goto err_device_destroy;
 	}
 
-	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
-	/* Make sure we don't have a race with AENQ Links state handler */
-	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
-		netif_carrier_on(adapter->netdev);
-
 	rc = ena_enable_msix_and_set_admin_interrupts(adapter,
 						      adapter->num_queues);
 	if (rc) {
@@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter)
 	}
 
 	set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags);
+
+	clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags);
+	if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags))
+		netif_carrier_on(adapter->netdev);
+
 	mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ));
 	dev_err(&pdev->dev,
 		"Device reset completed successfully, Driver info: %s\n",
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h
index dc8b6173d8d8..63870072cbbd 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.h
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h
@@ -45,7 +45,7 @@
 
 #define DRV_MODULE_VER_MAJOR	2
 #define DRV_MODULE_VER_MINOR	0
-#define DRV_MODULE_VER_SUBMINOR 2
+#define DRV_MODULE_VER_SUBMINOR 3
 
 #define DRV_MODULE_NAME		"ena"
 #ifndef DRV_MODULE_VERSION
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index a90080f12e67..145fe71fd155 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -435,7 +435,7 @@ static int amd8111e_restart(struct net_device *dev)
 	int i,reg_val;
 
 	/* stop the chip */
-	 writel(RUN, mmio + CMD0);
+	writel(RUN, mmio + CMD0);
 
 	if(amd8111e_init_ring(dev))
 		return -ENOMEM;
@@ -666,7 +666,7 @@ static int amd8111e_tx(struct net_device *dev)
 			pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[tx_index],
 				  	lp->tx_skbuff[tx_index]->len,
 					PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq (lp->tx_skbuff[tx_index]);
+			dev_consume_skb_irq(lp->tx_skbuff[tx_index]);
 			lp->tx_skbuff[tx_index] = NULL;
 			lp->tx_dma_addr[tx_index] = 0;
 		}
@@ -1720,7 +1720,7 @@ static void amd8111e_config_ipg(struct timer_list *t)
 		writew((u32)tmp_ipg, mmio + IPG);
 		writew((u32)(tmp_ipg - IFS1_DELTA), mmio + IFS1);
 	}
-	 mod_timer(&lp->ipg_data.ipg_timer, jiffies + IPG_CONVERGE_JIFFIES);
+	mod_timer(&lp->ipg_data.ipg_timer, jiffies + IPG_CONVERGE_JIFFIES);
 	return;
 
 }
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 7c1eb304c27e..e5073aeea06a 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -940,11 +940,8 @@ static int au1000_open(struct net_device *dev)
 		return retval;
 	}
 
-	if (dev->phydev) {
-		/* cause the PHY state machine to schedule a link state check */
-		dev->phydev->state = PHY_CHANGELINK;
+	if (dev->phydev)
 		phy_start(dev->phydev);
-	}
 
 	netif_start_queue(dev);
 
@@ -1170,7 +1167,7 @@ static int au1000_probe(struct platform_device *pdev)
 	/* Allocate the data buffers
 	 * Snooping works fine with eth on all au1xxx
 	 */
-	aup->vaddr = (u32)dma_alloc_attrs(NULL, MAX_BUF_SIZE *
+	aup->vaddr = (u32)dma_alloc_attrs(&pdev->dev, MAX_BUF_SIZE *
 					  (NUM_TX_BUFFS + NUM_RX_BUFFS),
 					  &aup->dma_addr, 0,
 					  DMA_ATTR_NON_CONSISTENT);
@@ -1352,7 +1349,7 @@ err_remap3:
 err_remap2:
 	iounmap(aup->mac);
 err_remap1:
-	dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
+	dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
 			(void *)aup->vaddr, aup->dma_addr,
 			DMA_ATTR_NON_CONSISTENT);
 err_vaddr:
@@ -1386,7 +1383,7 @@ static int au1000_remove(struct platform_device *pdev)
 		if (aup->tx_db_inuse[i])
 			au1000_ReleaseDB(aup, aup->tx_db_inuse[i]);
 
-	dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
+	dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS),
 			(void *)aup->vaddr, aup->dma_addr,
 			DMA_ATTR_NON_CONSISTENT);
 
diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c
index b56d84c7df46..f90b454b1642 100644
--- a/drivers/net/ethernet/amd/lance.c
+++ b/drivers/net/ethernet/amd/lance.c
@@ -1084,7 +1084,7 @@ static irqreturn_t lance_interrupt(int irq, void *dev_id)
 				/* We must free the original skb if it's not a data-only copy
 				   in the bounce buffer. */
 				if (lp->tx_skbuff[entry]) {
-					dev_kfree_skb_irq(lp->tx_skbuff[entry]);
+					dev_consume_skb_irq(lp->tx_skbuff[entry]);
 					lp->tx_skbuff[entry] = NULL;
 				}
 				dirty_tx++;
diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c
index 8931ce6bab7b..87ff5d6d1b22 100644
--- a/drivers/net/ethernet/amd/ni65.c
+++ b/drivers/net/ethernet/amd/ni65.c
@@ -1028,7 +1028,7 @@ static void ni65_xmit_intr(struct net_device *dev,int csr0)
 
 #ifdef XMT_VIA_SKB
 		if(p->tmd_skb[p->tmdlast]) {
-			 dev_kfree_skb_irq(p->tmd_skb[p->tmdlast]);
+			 dev_consume_skb_irq(p->tmd_skb[p->tmdlast]);
 			 p->tmd_skb[p->tmdlast] = NULL;
 		}
 #endif
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 9d4899826823..bd6589de93d9 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -1488,9 +1488,9 @@ static int sunlance_sbus_probe(struct platform_device *op)
 	struct device_node *parent_dp = parent->dev.of_node;
 	int err;
 
-	if (!strcmp(parent_dp->name, "ledma")) {
+	if (of_node_name_eq(parent_dp, "ledma")) {
 		err = sparc_lance_probe_one(op, parent, NULL);
-	} else if (!strcmp(parent_dp->name, "lebuffer")) {
+	} else if (of_node_name_eq(parent_dp, "lebuffer")) {
 		err = sparc_lance_probe_one(op, NULL, parent);
 	} else
 		err = sparc_lance_probe_one(op, NULL, NULL);
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-common.h b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
index d272dc6984ac..b40d4377cc71 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-common.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-common.h
@@ -431,8 +431,6 @@
 #define MAC_MDIOSCAR_PA_WIDTH		5
 #define MAC_MDIOSCAR_RA_INDEX		0
 #define MAC_MDIOSCAR_RA_WIDTH		16
-#define MAC_MDIOSCAR_REG_INDEX		0
-#define MAC_MDIOSCAR_REG_WIDTH		21
 #define MAC_MDIOSCCDR_BUSY_INDEX	22
 #define MAC_MDIOSCCDR_BUSY_WIDTH	1
 #define MAC_MDIOSCCDR_CMD_INDEX		16
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 1e929a1e4ca7..4666084eda16 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1284,6 +1284,20 @@ static void xgbe_write_mmd_regs(struct xgbe_prv_data *pdata, int prtad,
 	}
 }
 
+static unsigned int xgbe_create_mdio_sca(int port, int reg)
+{
+	unsigned int mdio_sca, da;
+
+	da = (reg & MII_ADDR_C45) ? reg >> 16 : 0;
+
+	mdio_sca = 0;
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, RA, reg);
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, PA, port);
+	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, da);
+
+	return mdio_sca;
+}
+
 static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 				   int reg, u16 val)
 {
@@ -1291,9 +1305,7 @@ static int xgbe_write_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 
 	reinit_completion(&pdata->mdio_complete);
 
-	mdio_sca = 0;
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+	mdio_sca = xgbe_create_mdio_sca(addr, reg);
 	XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
 
 	mdio_sccd = 0;
@@ -1317,9 +1329,7 @@ static int xgbe_read_ext_mii_regs(struct xgbe_prv_data *pdata, int addr,
 
 	reinit_completion(&pdata->mdio_complete);
 
-	mdio_sca = 0;
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, REG, reg);
-	XGMAC_SET_BITS(mdio_sca, MAC_MDIOSCAR, DA, addr);
+	mdio_sca = xgbe_create_mdio_sca(addr, reg);
 	XGMAC_IOWRITE(pdata, MAC_MDIOSCAR, mdio_sca);
 
 	mdio_sccd = 0;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
index 151bdb629e8a..128cd648ba99 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c
@@ -857,6 +857,7 @@ static void xgbe_phy_free_phy_device(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	unsigned int phy_id = phy_data->phydev->phy_id;
 
@@ -878,9 +879,15 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 	phy_write(phy_data->phydev, 0x04, 0x0d01);
 	phy_write(phy_data->phydev, 0x00, 0x9140);
 
-	phy_data->phydev->supported = PHY_10BT_FEATURES |
-				      PHY_100BT_FEATURES |
-				      PHY_1000BT_FEATURES;
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       supported);
+	linkmode_set_bit_array(phy_gbit_features_array,
+			       ARRAY_SIZE(phy_gbit_features_array),
+			       supported);
+
+	linkmode_copy(phy_data->phydev->supported, supported);
+
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,
@@ -891,6 +898,7 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata)
 
 static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct xgbe_sfp_eeprom *sfp_eeprom = &phy_data->sfp_eeprom;
 	unsigned int phy_id = phy_data->phydev->phy_id;
@@ -951,9 +959,13 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata)
 	reg = phy_read(phy_data->phydev, 0x00);
 	phy_write(phy_data->phydev, 0x00, reg & ~0x00800);
 
-	phy_data->phydev->supported = (PHY_10BT_FEATURES |
-				       PHY_100BT_FEATURES |
-				       PHY_1000BT_FEATURES);
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       supported);
+	linkmode_set_bit_array(phy_gbit_features_array,
+			       ARRAY_SIZE(phy_gbit_features_array),
+			       supported);
+	linkmode_copy(phy_data->phydev->supported, supported);
 	phy_support_asym_pause(phy_data->phydev);
 
 	netif_dbg(pdata, drv, pdata->netdev,
@@ -976,7 +988,6 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 	struct ethtool_link_ksettings *lks = &pdata->phy.lks;
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
 	struct phy_device *phydev;
-	u32 advertising;
 	int ret;
 
 	/* If we already have a PHY, just return */
@@ -1036,9 +1047,8 @@ static int xgbe_phy_find_phy_device(struct xgbe_prv_data *pdata)
 
 	xgbe_phy_external_phy_quirks(pdata);
 
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						lks->link_modes.advertising);
-	phydev->advertising &= advertising;
+	linkmode_and(phydev->advertising, phydev->advertising,
+		     lks->link_modes.advertising);
 
 	phy_start_aneg(phy_data->phydev);
 
@@ -1497,7 +1507,7 @@ static void xgbe_phy_phydev_flowctrl(struct xgbe_prv_data *pdata)
 	if (!phy_data->phydev)
 		return;
 
-	lcl_adv = ethtool_adv_to_lcl_adv_t(phy_data->phydev->advertising);
+	lcl_adv = linkmode_adv_to_lcl_adv_t(phy_data->phydev->advertising);
 
 	if (phy_data->phydev->pause) {
 		XGBE_SET_LP_ADV(lks, Pause);
@@ -1815,7 +1825,6 @@ static int xgbe_phy_an_config(struct xgbe_prv_data *pdata)
 {
 	struct ethtool_link_ksettings *lks = &pdata->phy.lks;
 	struct xgbe_phy_data *phy_data = pdata->phy_data;
-	u32 advertising;
 	int ret;
 
 	ret = xgbe_phy_find_phy_device(pdata);
@@ -1825,12 +1834,10 @@ static int xgbe_phy_an_config(struct xgbe_prv_data *pdata)
 	if (!phy_data->phydev)
 		return 0;
 
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						lks->link_modes.advertising);
-
 	phy_data->phydev->autoneg = pdata->phy.autoneg;
-	phy_data->phydev->advertising = phy_data->phydev->supported &
-					advertising;
+	linkmode_and(phy_data->phydev->advertising,
+		     phy_data->phydev->supported,
+		     lks->link_modes.advertising);
 
 	if (pdata->phy.autoneg != AUTONEG_ENABLE) {
 		phy_data->phydev->speed = pdata->phy.speed;
diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
index 0f2ad50f3bd7..87b142a312e0 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.c
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -206,8 +206,8 @@ static netdev_tx_t xge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	}
 
 	/* Packet buffers should be 64B aligned */
-	pkt_buf = dma_zalloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr,
-				      GFP_ATOMIC);
+	pkt_buf = dma_alloc_coherent(dev, XGENE_ENET_STD_MTU, &dma_addr,
+				     GFP_ATOMIC);
 	if (unlikely(!pkt_buf)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -428,8 +428,8 @@ static struct xge_desc_ring *xge_create_desc_ring(struct net_device *ndev)
 	ring->ndev = ndev;
 
 	size = XGENE_ENET_DESC_SIZE * XGENE_ENET_NUM_DESC;
-	ring->desc_addr = dma_zalloc_coherent(dev, size, &ring->dma_addr,
-					      GFP_KERNEL);
+	ring->desc_addr = dma_alloc_coherent(dev, size, &ring->dma_addr,
+					     GFP_KERNEL);
 	if (!ring->desc_addr)
 		goto err;
 
diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
index f5fe3bb2e59d..53529cd85162 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mdio.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -109,6 +109,7 @@ void xge_mdio_remove(struct net_device *ndev)
 
 int xge_mdio_config(struct net_device *ndev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct xge_pdata *pdata = netdev_priv(ndev);
 	struct device *dev = &pdata->pdev->dev;
 	struct mii_bus *mdio_bus;
@@ -148,16 +149,17 @@ int xge_mdio_config(struct net_device *ndev)
 		goto err;
 	}
 
-	phydev->supported &= ~(SUPPORTED_10baseT_Half |
-			       SUPPORTED_10baseT_Full |
-			       SUPPORTED_100baseT_Half |
-			       SUPPORTED_100baseT_Full |
-			       SUPPORTED_1000baseT_Half |
-			       SUPPORTED_AUI |
-			       SUPPORTED_MII |
-			       SUPPORTED_FIBRE |
-			       SUPPORTED_BNC);
-	phydev->advertising = phydev->supported;
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_AUI_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_BNC_BIT, mask);
+
+	linkmode_andnot(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return 0;
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 6a8e2567f2bd..4d3855ceb500 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -777,7 +777,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id)
 
 		if (bp->tx_bufs[bp->tx_empty]) {
 			++dev->stats.tx_packets;
-			dev_kfree_skb_irq(bp->tx_bufs[bp->tx_empty]);
+			dev_consume_skb_irq(bp->tx_bufs[bp->tx_empty]);
 		}
 		bp->tx_bufs[bp->tx_empty] = NULL;
 		bp->tx_fullup = 0;
diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c
index 68b9ee489489..4d9819d2894d 100644
--- a/drivers/net/ethernet/apple/mace.c
+++ b/drivers/net/ethernet/apple/mace.c
@@ -764,7 +764,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id)
 	    dev->stats.tx_bytes += mp->tx_bufs[i]->len;
 	    ++dev->stats.tx_packets;
 	}
-	dev_kfree_skb_irq(mp->tx_bufs[i]);
+	dev_consume_skb_irq(mp->tx_bufs[i]);
 	--mp->tx_active;
 	if (++i >= N_TX_RING)
 	    i = 0;
diff --git a/drivers/net/ethernet/aquantia/atlantic/Makefile b/drivers/net/ethernet/aquantia/atlantic/Makefile
index 686f6d8c9e79..4556630ee286 100644
--- a/drivers/net/ethernet/aquantia/atlantic/Makefile
+++ b/drivers/net/ethernet/aquantia/atlantic/Makefile
@@ -36,6 +36,7 @@ atlantic-objs := aq_main.o \
 	aq_ring.o \
 	aq_hw_utils.o \
 	aq_ethtool.o \
+	aq_filters.o \
 	hw_atl/hw_atl_a0.o \
 	hw_atl/hw_atl_b0.o \
 	hw_atl/hw_atl_utils.o \
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
index 91eb8910b1c9..3944ce7f0870 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_cfg.h
@@ -12,7 +12,7 @@
 #ifndef AQ_CFG_H
 #define AQ_CFG_H
 
-#define AQ_CFG_VECS_DEF   4U
+#define AQ_CFG_VECS_DEF   8U
 #define AQ_CFG_TCS_DEF    1U
 
 #define AQ_CFG_TXDS_DEF    4096U
@@ -42,8 +42,8 @@
 #define AQ_CFG_IS_LRO_DEF           1U
 
 /* RSS */
-#define AQ_CFG_RSS_INDIRECTION_TABLE_MAX  128U
-#define AQ_CFG_RSS_HASHKEY_SIZE           320U
+#define AQ_CFG_RSS_INDIRECTION_TABLE_MAX  64U
+#define AQ_CFG_RSS_HASHKEY_SIZE           40U
 
 #define AQ_CFG_IS_RSS_DEF           1U
 #define AQ_CFG_NUM_RSS_QUEUES_DEF   AQ_CFG_VECS_DEF
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
index becb578211ed..6b6d1724676e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h
@@ -14,7 +14,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
-
+#include <linux/if_vlan.h>
 #include "ver.h"
 #include "aq_cfg.h"
 #include "aq_utils.h"
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 99ef1daaa4d8..a718d7a1f76c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -12,6 +12,7 @@
 #include "aq_ethtool.h"
 #include "aq_nic.h"
 #include "aq_vec.h"
+#include "aq_filters.h"
 
 static void aq_ethtool_get_regs(struct net_device *ndev,
 				struct ethtool_regs *regs, void *p)
@@ -137,7 +138,7 @@ static void aq_ethtool_get_strings(struct net_device *ndev,
 	u8 *p = data;
 
 	if (stringset == ETH_SS_STATS) {
-		memcpy(p, *aq_ethtool_stat_names,
+		memcpy(p, aq_ethtool_stat_names,
 		       sizeof(aq_ethtool_stat_names));
 		p = p + sizeof(aq_ethtool_stat_names);
 		for (i = 0; i < cfg->vecs; i++) {
@@ -201,6 +202,41 @@ static int aq_ethtool_get_rss(struct net_device *ndev, u32 *indir, u8 *key,
 	return 0;
 }
 
+static int aq_ethtool_set_rss(struct net_device *netdev, const u32 *indir,
+			      const u8 *key, const u8 hfunc)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(netdev);
+	struct aq_nic_cfg_s *cfg;
+	unsigned int i = 0U;
+	u32 rss_entries;
+	int err = 0;
+
+	cfg = aq_nic_get_cfg(aq_nic);
+	rss_entries = cfg->aq_rss.indirection_table_size;
+
+	/* We do not allow change in unsupported parameters */
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+	/* Fill out the redirection table */
+	if (indir)
+		for (i = 0; i < rss_entries; i++)
+			cfg->aq_rss.indirection_table[i] = indir[i];
+
+	/* Fill out the rss hash key */
+	if (key) {
+		memcpy(cfg->aq_rss.hash_secret_key, key,
+		       sizeof(cfg->aq_rss.hash_secret_key));
+		err = aq_nic->aq_hw_ops->hw_rss_hash_set(aq_nic->aq_hw,
+			&cfg->aq_rss);
+		if (err)
+			return err;
+	}
+
+	err = aq_nic->aq_hw_ops->hw_rss_set(aq_nic->aq_hw, &cfg->aq_rss);
+
+	return err;
+}
+
 static int aq_ethtool_get_rxnfc(struct net_device *ndev,
 				struct ethtool_rxnfc *cmd,
 				u32 *rule_locs)
@@ -213,7 +249,36 @@ static int aq_ethtool_get_rxnfc(struct net_device *ndev,
 	case ETHTOOL_GRXRINGS:
 		cmd->data = cfg->vecs;
 		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		cmd->rule_cnt = aq_get_rxnfc_count_all_rules(aq_nic);
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = aq_get_rxnfc_rule(aq_nic, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		err = aq_get_rxnfc_all_rules(aq_nic, cmd, rule_locs);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static int aq_ethtool_set_rxnfc(struct net_device *ndev,
+				struct ethtool_rxnfc *cmd)
+{
+	int err = 0;
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
 
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = aq_add_rxnfc_rule(aq_nic, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = aq_del_rxnfc_rule(aq_nic, cmd);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -495,7 +560,7 @@ static int aq_set_ringparam(struct net_device *ndev,
 		}
 	}
 	if (ndev_running)
-		err = dev_open(ndev);
+		err = dev_open(ndev, NULL);
 
 err_exit:
 	return err;
@@ -519,7 +584,9 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.set_pauseparam      = aq_ethtool_set_pauseparam,
 	.get_rxfh_key_size   = aq_ethtool_get_rss_key_size,
 	.get_rxfh            = aq_ethtool_get_rss,
+	.set_rxfh            = aq_ethtool_set_rss,
 	.get_rxnfc           = aq_ethtool_get_rxnfc,
+	.set_rxnfc           = aq_ethtool_set_rxnfc,
 	.get_sset_count      = aq_ethtool_get_sset_count,
 	.get_ethtool_stats   = aq_ethtool_stats,
 	.get_link_ksettings  = aq_ethtool_get_link_ksettings,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
new file mode 100644
index 000000000000..18bc035da850
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c
@@ -0,0 +1,876 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Copyright (C) 2014-2017 aQuantia Corporation. */
+
+/* File aq_filters.c: RX filters related functions. */
+
+#include "aq_filters.h"
+
+static bool __must_check
+aq_rule_is_approve(struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->flow_type & FLOW_MAC_EXT)
+		return false;
+
+	switch (fsp->flow_type & ~FLOW_EXT) {
+	case ETHER_FLOW:
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case SCTP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+	case SCTP_V6_FLOW:
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		return true;
+	case IP_USER_FLOW:
+		switch (fsp->h_u.usr_ip4_spec.proto) {
+		case IPPROTO_TCP:
+		case IPPROTO_UDP:
+		case IPPROTO_SCTP:
+		case IPPROTO_IP:
+			return true;
+		default:
+			return false;
+			}
+	case IPV6_USER_FLOW:
+		switch (fsp->h_u.usr_ip6_spec.l4_proto) {
+		case IPPROTO_TCP:
+		case IPPROTO_UDP:
+		case IPPROTO_SCTP:
+		case IPPROTO_IP:
+			return true;
+		default:
+			return false;
+			}
+	default:
+		return false;
+	}
+
+	return false;
+}
+
+static bool __must_check
+aq_match_filter(struct ethtool_rx_flow_spec *fsp1,
+		struct ethtool_rx_flow_spec *fsp2)
+{
+	if (fsp1->flow_type != fsp2->flow_type ||
+	    memcmp(&fsp1->h_u, &fsp2->h_u, sizeof(fsp2->h_u)) ||
+	    memcmp(&fsp1->h_ext, &fsp2->h_ext, sizeof(fsp2->h_ext)) ||
+	    memcmp(&fsp1->m_u, &fsp2->m_u, sizeof(fsp2->m_u)) ||
+	    memcmp(&fsp1->m_ext, &fsp2->m_ext, sizeof(fsp2->m_ext)))
+		return false;
+
+	return true;
+}
+
+static bool __must_check
+aq_rule_already_exists(struct aq_nic_s *aq_nic,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	struct aq_rx_filter *rule;
+	struct hlist_node *aq_node2;
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (rule->aq_fsp.location == fsp->location)
+			continue;
+		if (aq_match_filter(&rule->aq_fsp, fsp)) {
+			netdev_err(aq_nic->ndev,
+				   "ethtool: This filter is already set\n");
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static int aq_check_approve_fl3l4(struct aq_nic_s *aq_nic,
+				  struct aq_hw_rx_fltrs_s *rx_fltrs,
+				  struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->location < AQ_RX_FIRST_LOC_FL3L4 ||
+	    fsp->location > AQ_RX_LAST_LOC_FL3L4) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: location must be in range [%d, %d]",
+			   AQ_RX_FIRST_LOC_FL3L4,
+			   AQ_RX_LAST_LOC_FL3L4);
+		return -EINVAL;
+	}
+	if (rx_fltrs->fl3l4.is_ipv6 && rx_fltrs->fl3l4.active_ipv4) {
+		rx_fltrs->fl3l4.is_ipv6 = false;
+		netdev_err(aq_nic->ndev,
+			   "ethtool: mixing ipv4 and ipv6 is not allowed");
+		return -EINVAL;
+	} else if (!rx_fltrs->fl3l4.is_ipv6 && rx_fltrs->fl3l4.active_ipv6) {
+		rx_fltrs->fl3l4.is_ipv6 = true;
+		netdev_err(aq_nic->ndev,
+			   "ethtool: mixing ipv4 and ipv6 is not allowed");
+		return -EINVAL;
+	} else if (rx_fltrs->fl3l4.is_ipv6		      &&
+		   fsp->location != AQ_RX_FIRST_LOC_FL3L4 + 4 &&
+		   fsp->location != AQ_RX_FIRST_LOC_FL3L4) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified location for ipv6 must be %d or %d",
+			   AQ_RX_FIRST_LOC_FL3L4, AQ_RX_FIRST_LOC_FL3L4 + 4);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __must_check
+aq_check_approve_fl2(struct aq_nic_s *aq_nic,
+		     struct aq_hw_rx_fltrs_s *rx_fltrs,
+		     struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->location < AQ_RX_FIRST_LOC_FETHERT ||
+	    fsp->location > AQ_RX_LAST_LOC_FETHERT) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: location must be in range [%d, %d]",
+			   AQ_RX_FIRST_LOC_FETHERT,
+			   AQ_RX_LAST_LOC_FETHERT);
+		return -EINVAL;
+	}
+
+	if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_PRIO_MASK &&
+	    fsp->m_u.ether_spec.h_proto == 0U) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: proto (ether_type) parameter must be specified");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int __must_check
+aq_check_approve_fvlan(struct aq_nic_s *aq_nic,
+		       struct aq_hw_rx_fltrs_s *rx_fltrs,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	if (fsp->location < AQ_RX_FIRST_LOC_FVLANID ||
+	    fsp->location > AQ_RX_LAST_LOC_FVLANID) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: location must be in range [%d, %d]",
+			   AQ_RX_FIRST_LOC_FVLANID,
+			   AQ_RX_LAST_LOC_FVLANID);
+		return -EINVAL;
+	}
+
+	if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) &&
+	    (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci),
+		       aq_nic->active_vlans))) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: unknown vlan-id specified");
+		return -EINVAL;
+	}
+
+	if (fsp->ring_cookie > aq_nic->aq_nic_cfg.num_rss_queues) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: queue number must be in range [0, %d]",
+			   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int __must_check
+aq_check_filter(struct aq_nic_s *aq_nic,
+		struct ethtool_rx_flow_spec *fsp)
+{
+	int err = 0;
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+
+	if (fsp->flow_type & FLOW_EXT) {
+		if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_VID_MASK) {
+			err = aq_check_approve_fvlan(aq_nic, rx_fltrs, fsp);
+		} else if (be16_to_cpu(fsp->m_ext.vlan_tci) == VLAN_PRIO_MASK) {
+			err = aq_check_approve_fl2(aq_nic, rx_fltrs, fsp);
+		} else {
+			netdev_err(aq_nic->ndev,
+				   "ethtool: invalid vlan mask 0x%x specified",
+				   be16_to_cpu(fsp->m_ext.vlan_tci));
+			err = -EINVAL;
+		}
+	} else {
+		switch (fsp->flow_type & ~FLOW_EXT) {
+		case ETHER_FLOW:
+			err = aq_check_approve_fl2(aq_nic, rx_fltrs, fsp);
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+		case SCTP_V4_FLOW:
+		case IPV4_FLOW:
+		case IP_USER_FLOW:
+			rx_fltrs->fl3l4.is_ipv6 = false;
+			err = aq_check_approve_fl3l4(aq_nic, rx_fltrs, fsp);
+			break;
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+		case SCTP_V6_FLOW:
+		case IPV6_FLOW:
+		case IPV6_USER_FLOW:
+			rx_fltrs->fl3l4.is_ipv6 = true;
+			err = aq_check_approve_fl3l4(aq_nic, rx_fltrs, fsp);
+			break;
+		default:
+			netdev_err(aq_nic->ndev,
+				   "ethtool: unknown flow-type specified");
+			err = -EINVAL;
+		}
+	}
+
+	return err;
+}
+
+static bool __must_check
+aq_rule_is_not_support(struct aq_nic_s *aq_nic,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	bool rule_is_not_support = false;
+
+	if (!(aq_nic->ndev->features & NETIF_F_NTUPLE)) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: Please, to enable the RX flow control:\n"
+			   "ethtool -K %s ntuple on\n", aq_nic->ndev->name);
+		rule_is_not_support = true;
+	} else if (!aq_rule_is_approve(fsp)) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified flow type is not supported\n");
+		rule_is_not_support = true;
+	} else if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW &&
+		   (fsp->h_u.tcp_ip4_spec.tos ||
+		    fsp->h_u.tcp_ip6_spec.tclass)) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified tos tclass are not supported\n");
+		rule_is_not_support = true;
+	} else if (fsp->flow_type & FLOW_MAC_EXT) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: MAC_EXT is not supported");
+		rule_is_not_support = true;
+	}
+
+	return rule_is_not_support;
+}
+
+static bool __must_check
+aq_rule_is_not_correct(struct aq_nic_s *aq_nic,
+		       struct ethtool_rx_flow_spec *fsp)
+{
+	bool rule_is_not_correct = false;
+
+	if (!aq_nic) {
+		rule_is_not_correct = true;
+	} else if (fsp->location > AQ_RX_MAX_RXNFC_LOC) {
+		netdev_err(aq_nic->ndev,
+			   "ethtool: The specified number %u rule is invalid\n",
+			   fsp->location);
+		rule_is_not_correct = true;
+	} else if (aq_check_filter(aq_nic, fsp)) {
+		rule_is_not_correct = true;
+	} else if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
+		if (fsp->ring_cookie >= aq_nic->aq_nic_cfg.num_rss_queues) {
+			netdev_err(aq_nic->ndev,
+				   "ethtool: The specified action is invalid.\n"
+				   "Maximum allowable value action is %u.\n",
+				   aq_nic->aq_nic_cfg.num_rss_queues - 1);
+			rule_is_not_correct = true;
+		}
+	}
+
+	return rule_is_not_correct;
+}
+
+static int __must_check
+aq_check_rule(struct aq_nic_s *aq_nic,
+	      struct ethtool_rx_flow_spec *fsp)
+{
+	int err = 0;
+
+	if (aq_rule_is_not_correct(aq_nic, fsp))
+		err = -EINVAL;
+	else if (aq_rule_is_not_support(aq_nic, fsp))
+		err = -EOPNOTSUPP;
+	else if (aq_rule_already_exists(aq_nic, fsp))
+		err = -EEXIST;
+
+	return err;
+}
+
+static void aq_set_data_fl2(struct aq_nic_s *aq_nic,
+			    struct aq_rx_filter *aq_rx_fltr,
+			    struct aq_rx_filter_l2 *data, bool add)
+{
+	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
+
+	memset(data, 0, sizeof(*data));
+
+	data->location = fsp->location - AQ_RX_FIRST_LOC_FETHERT;
+
+	if (fsp->ring_cookie != RX_CLS_FLOW_DISC)
+		data->queue = fsp->ring_cookie;
+	else
+		data->queue = -1;
+
+	data->ethertype = be16_to_cpu(fsp->h_u.ether_spec.h_proto);
+	data->user_priority_en = be16_to_cpu(fsp->m_ext.vlan_tci)
+				 == VLAN_PRIO_MASK;
+	data->user_priority = (be16_to_cpu(fsp->h_ext.vlan_tci)
+			       & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+}
+
+static int aq_add_del_fether(struct aq_nic_s *aq_nic,
+			     struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	struct aq_rx_filter_l2 data;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+
+	aq_set_data_fl2(aq_nic, aq_rx_fltr, &data, add);
+
+	if (unlikely(!aq_hw_ops->hw_filter_l2_set))
+		return -EOPNOTSUPP;
+	if (unlikely(!aq_hw_ops->hw_filter_l2_clear))
+		return -EOPNOTSUPP;
+
+	if (add)
+		return aq_hw_ops->hw_filter_l2_set(aq_hw, &data);
+	else
+		return aq_hw_ops->hw_filter_l2_clear(aq_hw, &data);
+}
+
+static bool aq_fvlan_is_busy(struct aq_rx_filter_vlan *aq_vlans, int vlan)
+{
+	int i;
+
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; ++i) {
+		if (aq_vlans[i].enable &&
+		    aq_vlans[i].queue != AQ_RX_QUEUE_NOT_ASSIGNED &&
+		    aq_vlans[i].vlan_id == vlan) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+/* Function rebuilds array of vlan filters so that filters with assigned
+ * queue have a precedence over just vlans on the interface.
+ */
+static void aq_fvlan_rebuild(struct aq_nic_s *aq_nic,
+			     unsigned long *active_vlans,
+			     struct aq_rx_filter_vlan *aq_vlans)
+{
+	bool vlan_busy = false;
+	int vlan = -1;
+	int i;
+
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; ++i) {
+		if (aq_vlans[i].enable &&
+		    aq_vlans[i].queue != AQ_RX_QUEUE_NOT_ASSIGNED)
+			continue;
+		do {
+			vlan = find_next_bit(active_vlans,
+					     VLAN_N_VID,
+					     vlan + 1);
+			if (vlan == VLAN_N_VID) {
+				aq_vlans[i].enable = 0U;
+				aq_vlans[i].queue = AQ_RX_QUEUE_NOT_ASSIGNED;
+				aq_vlans[i].vlan_id = 0;
+				continue;
+			}
+
+			vlan_busy = aq_fvlan_is_busy(aq_vlans, vlan);
+			if (!vlan_busy) {
+				aq_vlans[i].enable = 1U;
+				aq_vlans[i].queue = AQ_RX_QUEUE_NOT_ASSIGNED;
+				aq_vlans[i].vlan_id = vlan;
+			}
+		} while (vlan_busy && vlan != VLAN_N_VID);
+	}
+}
+
+static int aq_set_data_fvlan(struct aq_nic_s *aq_nic,
+			     struct aq_rx_filter *aq_rx_fltr,
+			     struct aq_rx_filter_vlan *aq_vlans, bool add)
+{
+	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
+	int location = fsp->location - AQ_RX_FIRST_LOC_FVLANID;
+	int i;
+
+	memset(&aq_vlans[location], 0, sizeof(aq_vlans[location]));
+
+	if (!add)
+		return 0;
+
+	/* remove vlan if it was in table without queue assignment */
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; ++i) {
+		if (aq_vlans[i].vlan_id ==
+		   (be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK)) {
+			aq_vlans[i].enable = false;
+		}
+	}
+
+	aq_vlans[location].location = location;
+	aq_vlans[location].vlan_id = be16_to_cpu(fsp->h_ext.vlan_tci)
+				     & VLAN_VID_MASK;
+	aq_vlans[location].queue = fsp->ring_cookie & 0x1FU;
+	aq_vlans[location].enable = 1U;
+
+	return 0;
+}
+
+int aq_del_fvlan_by_vlan(struct aq_nic_s *aq_nic, u16 vlan_id)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct aq_rx_filter *rule = NULL;
+	struct hlist_node *aq_node2;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id)
+			break;
+	}
+	if (rule && be16_to_cpu(rule->aq_fsp.h_ext.vlan_tci) == vlan_id) {
+		struct ethtool_rxnfc cmd;
+
+		cmd.fs.location = rule->aq_fsp.location;
+		return aq_del_rxnfc_rule(aq_nic, &cmd);
+	}
+
+	return -ENOENT;
+}
+
+static int aq_add_del_fvlan(struct aq_nic_s *aq_nic,
+			    struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
+		return -EOPNOTSUPP;
+
+	aq_set_data_fvlan(aq_nic,
+			  aq_rx_fltr,
+			  aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans,
+			  add);
+
+	return aq_filters_vlans_update(aq_nic);
+}
+
+static int aq_set_data_fl3l4(struct aq_nic_s *aq_nic,
+			     struct aq_rx_filter *aq_rx_fltr,
+			     struct aq_rx_filter_l3l4 *data, bool add)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	const struct ethtool_rx_flow_spec *fsp = &aq_rx_fltr->aq_fsp;
+
+	memset(data, 0, sizeof(*data));
+
+	data->is_ipv6 = rx_fltrs->fl3l4.is_ipv6;
+	data->location = HW_ATL_GET_REG_LOCATION_FL3L4(fsp->location);
+
+	if (!add) {
+		if (!data->is_ipv6)
+			rx_fltrs->fl3l4.active_ipv4 &= ~BIT(data->location);
+		else
+			rx_fltrs->fl3l4.active_ipv6 &=
+				~BIT((data->location) / 4);
+
+		return 0;
+	}
+
+	data->cmd |= HW_ATL_RX_ENABLE_FLTR_L3L4;
+
+	switch (fsp->flow_type) {
+	case TCP_V4_FLOW:
+	case TCP_V6_FLOW:
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_PROT_L4;
+		break;
+	case UDP_V4_FLOW:
+	case UDP_V6_FLOW:
+		data->cmd |= HW_ATL_RX_UDP;
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_PROT_L4;
+		break;
+	case SCTP_V4_FLOW:
+	case SCTP_V6_FLOW:
+		data->cmd |= HW_ATL_RX_SCTP;
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_PROT_L4;
+		break;
+	default:
+		break;
+	}
+
+	if (!data->is_ipv6) {
+		data->ip_src[0] =
+			ntohl(fsp->h_u.tcp_ip4_spec.ip4src);
+		data->ip_dst[0] =
+			ntohl(fsp->h_u.tcp_ip4_spec.ip4dst);
+		rx_fltrs->fl3l4.active_ipv4 |= BIT(data->location);
+	} else {
+		int i;
+
+		rx_fltrs->fl3l4.active_ipv6 |= BIT((data->location) / 4);
+		for (i = 0; i < HW_ATL_RX_CNT_REG_ADDR_IPV6; ++i) {
+			data->ip_dst[i] =
+				ntohl(fsp->h_u.tcp_ip6_spec.ip6dst[i]);
+			data->ip_src[i] =
+				ntohl(fsp->h_u.tcp_ip6_spec.ip6src[i]);
+		}
+		data->cmd |= HW_ATL_RX_ENABLE_L3_IPV6;
+	}
+	if (fsp->flow_type != IP_USER_FLOW &&
+	    fsp->flow_type != IPV6_USER_FLOW) {
+		if (!data->is_ipv6) {
+			data->p_dst =
+				ntohs(fsp->h_u.tcp_ip4_spec.pdst);
+			data->p_src =
+				ntohs(fsp->h_u.tcp_ip4_spec.psrc);
+		} else {
+			data->p_dst =
+				ntohs(fsp->h_u.tcp_ip6_spec.pdst);
+			data->p_src =
+				ntohs(fsp->h_u.tcp_ip6_spec.psrc);
+		}
+	}
+	if (data->ip_src[0] && !data->is_ipv6)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_SRC_ADDR_L3;
+	if (data->ip_dst[0] && !data->is_ipv6)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_DEST_ADDR_L3;
+	if (data->p_dst)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_DEST_PORT_L4;
+	if (data->p_src)
+		data->cmd |= HW_ATL_RX_ENABLE_CMP_SRC_PORT_L4;
+	if (fsp->ring_cookie != RX_CLS_FLOW_DISC) {
+		data->cmd |= HW_ATL_RX_HOST << HW_ATL_RX_ACTION_FL3F4_SHIFT;
+		data->cmd |= fsp->ring_cookie << HW_ATL_RX_QUEUE_FL3L4_SHIFT;
+		data->cmd |= HW_ATL_RX_ENABLE_QUEUE_L3L4;
+	} else {
+		data->cmd |= HW_ATL_RX_DISCARD << HW_ATL_RX_ACTION_FL3F4_SHIFT;
+	}
+
+	return 0;
+}
+
+static int aq_set_fl3l4(struct aq_hw_s *aq_hw,
+			const struct aq_hw_ops *aq_hw_ops,
+			struct aq_rx_filter_l3l4 *data)
+{
+	if (unlikely(!aq_hw_ops->hw_filter_l3l4_set))
+		return -EOPNOTSUPP;
+
+	return aq_hw_ops->hw_filter_l3l4_set(aq_hw, data);
+}
+
+static int aq_add_del_fl3l4(struct aq_nic_s *aq_nic,
+			    struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	struct aq_rx_filter_l3l4 data;
+
+	if (unlikely(aq_rx_fltr->aq_fsp.location < AQ_RX_FIRST_LOC_FL3L4 ||
+		     aq_rx_fltr->aq_fsp.location > AQ_RX_LAST_LOC_FL3L4  ||
+		     aq_set_data_fl3l4(aq_nic, aq_rx_fltr, &data, add)))
+		return -EINVAL;
+
+	return aq_set_fl3l4(aq_hw, aq_hw_ops, &data);
+}
+
+static int aq_add_del_rule(struct aq_nic_s *aq_nic,
+			   struct aq_rx_filter *aq_rx_fltr, bool add)
+{
+	int err = -EINVAL;
+
+	if (aq_rx_fltr->aq_fsp.flow_type & FLOW_EXT) {
+		if (be16_to_cpu(aq_rx_fltr->aq_fsp.m_ext.vlan_tci)
+		    == VLAN_VID_MASK) {
+			aq_rx_fltr->type = aq_rx_filter_vlan;
+			err = aq_add_del_fvlan(aq_nic, aq_rx_fltr, add);
+		} else if (be16_to_cpu(aq_rx_fltr->aq_fsp.m_ext.vlan_tci)
+			== VLAN_PRIO_MASK) {
+			aq_rx_fltr->type = aq_rx_filter_ethertype;
+			err = aq_add_del_fether(aq_nic, aq_rx_fltr, add);
+		}
+	} else {
+		switch (aq_rx_fltr->aq_fsp.flow_type & ~FLOW_EXT) {
+		case ETHER_FLOW:
+			aq_rx_fltr->type = aq_rx_filter_ethertype;
+			err = aq_add_del_fether(aq_nic, aq_rx_fltr, add);
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+		case SCTP_V4_FLOW:
+		case IP_USER_FLOW:
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+		case SCTP_V6_FLOW:
+		case IPV6_USER_FLOW:
+			aq_rx_fltr->type = aq_rx_filter_l3l4;
+			err = aq_add_del_fl3l4(aq_nic, aq_rx_fltr, add);
+			break;
+		default:
+			err = -EINVAL;
+			break;
+		}
+	}
+
+	return err;
+}
+
+static int aq_update_table_filters(struct aq_nic_s *aq_nic,
+				   struct aq_rx_filter *aq_rx_fltr, u16 index,
+				   struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct aq_rx_filter *rule = NULL, *parent = NULL;
+	struct hlist_node *aq_node2;
+	int err = -EINVAL;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (rule->aq_fsp.location >= index)
+			break;
+		parent = rule;
+	}
+
+	if (rule && rule->aq_fsp.location == index) {
+		err = aq_add_del_rule(aq_nic, rule, false);
+		hlist_del(&rule->aq_node);
+		kfree(rule);
+		--rx_fltrs->active_filters;
+	}
+
+	if (unlikely(!aq_rx_fltr))
+		return err;
+
+	INIT_HLIST_NODE(&aq_rx_fltr->aq_node);
+
+	if (parent)
+		hlist_add_behind(&aq_rx_fltr->aq_node, &parent->aq_node);
+	else
+		hlist_add_head(&aq_rx_fltr->aq_node, &rx_fltrs->filter_list);
+
+	++rx_fltrs->active_filters;
+
+	return 0;
+}
+
+u16 aq_get_rxnfc_count_all_rules(struct aq_nic_s *aq_nic)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+
+	return rx_fltrs->active_filters;
+}
+
+struct aq_hw_rx_fltrs_s *aq_get_hw_rx_fltrs(struct aq_nic_s *aq_nic)
+{
+	return &aq_nic->aq_hw_rx_fltrs;
+}
+
+int aq_add_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct ethtool_rx_flow_spec *fsp =
+		(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct aq_rx_filter *aq_rx_fltr;
+	int err = 0;
+
+	err = aq_check_rule(aq_nic, fsp);
+	if (err)
+		goto err_exit;
+
+	aq_rx_fltr = kzalloc(sizeof(*aq_rx_fltr), GFP_KERNEL);
+	if (unlikely(!aq_rx_fltr)) {
+		err = -ENOMEM;
+		goto err_exit;
+	}
+
+	memcpy(&aq_rx_fltr->aq_fsp, fsp, sizeof(*fsp));
+
+	err = aq_update_table_filters(aq_nic, aq_rx_fltr, fsp->location, NULL);
+	if (unlikely(err))
+		goto err_free;
+
+	err = aq_add_del_rule(aq_nic, aq_rx_fltr, true);
+	if (unlikely(err)) {
+		hlist_del(&aq_rx_fltr->aq_node);
+		--rx_fltrs->active_filters;
+		goto err_free;
+	}
+
+	return 0;
+
+err_free:
+	kfree(aq_rx_fltr);
+err_exit:
+	return err;
+}
+
+int aq_del_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct aq_rx_filter *rule = NULL;
+	struct hlist_node *aq_node2;
+	int err = -EINVAL;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (rule->aq_fsp.location == cmd->fs.location)
+			break;
+	}
+
+	if (rule && rule->aq_fsp.location == cmd->fs.location) {
+		err = aq_add_del_rule(aq_nic, rule, false);
+		hlist_del(&rule->aq_node);
+		kfree(rule);
+		--rx_fltrs->active_filters;
+	}
+	return err;
+}
+
+int aq_get_rxnfc_rule(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct ethtool_rx_flow_spec *fsp =
+			(struct ethtool_rx_flow_spec *)&cmd->fs;
+	struct aq_rx_filter *rule = NULL;
+	struct hlist_node *aq_node2;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node)
+		if (fsp->location <= rule->aq_fsp.location)
+			break;
+
+	if (unlikely(!rule || fsp->location != rule->aq_fsp.location))
+		return -EINVAL;
+
+	memcpy(fsp, &rule->aq_fsp, sizeof(*fsp));
+
+	return 0;
+}
+
+int aq_get_rxnfc_all_rules(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd,
+			   u32 *rule_locs)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct hlist_node *aq_node2;
+	struct aq_rx_filter *rule;
+	int count = 0;
+
+	cmd->data = aq_get_rxnfc_count_all_rules(aq_nic);
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		if (unlikely(count == cmd->rule_cnt))
+			return -EMSGSIZE;
+
+		rule_locs[count++] = rule->aq_fsp.location;
+	}
+
+	cmd->rule_cnt = count;
+
+	return 0;
+}
+
+int aq_clear_rxnfc_all_rules(struct aq_nic_s *aq_nic)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct hlist_node *aq_node2;
+	struct aq_rx_filter *rule;
+	int err = 0;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		err = aq_add_del_rule(aq_nic, rule, false);
+		if (err)
+			goto err_exit;
+		hlist_del(&rule->aq_node);
+		kfree(rule);
+		--rx_fltrs->active_filters;
+	}
+
+err_exit:
+	return err;
+}
+
+int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic)
+{
+	struct aq_hw_rx_fltrs_s *rx_fltrs = aq_get_hw_rx_fltrs(aq_nic);
+	struct hlist_node *aq_node2;
+	struct aq_rx_filter *rule;
+	int err = 0;
+
+	hlist_for_each_entry_safe(rule, aq_node2,
+				  &rx_fltrs->filter_list, aq_node) {
+		err = aq_add_del_rule(aq_nic, rule, true);
+		if (err)
+			goto err_exit;
+	}
+
+err_exit:
+	return err;
+}
+
+int aq_filters_vlans_update(struct aq_nic_s *aq_nic)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	int hweight = 0;
+	int err = 0;
+	int i;
+
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
+		return -EOPNOTSUPP;
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl))
+		return -EOPNOTSUPP;
+
+	aq_fvlan_rebuild(aq_nic, aq_nic->active_vlans,
+			 aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans);
+
+	if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		for (i = 0; i < BITS_TO_LONGS(VLAN_N_VID); i++)
+			hweight += hweight_long(aq_nic->active_vlans[i]);
+
+		err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false);
+		if (err)
+			return err;
+	}
+
+	err = aq_hw_ops->hw_filter_vlan_set(aq_hw,
+					    aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans
+					   );
+	if (err)
+		return err;
+
+	if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+		if (hweight < AQ_VLAN_MAX_FILTERS)
+			err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, true);
+		/* otherwise left in promiscue mode */
+	}
+
+	return err;
+}
+
+int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic)
+{
+	const struct aq_hw_ops *aq_hw_ops = aq_nic->aq_hw_ops;
+	struct aq_hw_s *aq_hw = aq_nic->aq_hw;
+	int err = 0;
+
+	memset(aq_nic->active_vlans, 0, sizeof(aq_nic->active_vlans));
+	aq_fvlan_rebuild(aq_nic, aq_nic->active_vlans,
+			 aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans);
+
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_set))
+		return -EOPNOTSUPP;
+	if (unlikely(!aq_hw_ops->hw_filter_vlan_ctrl))
+		return -EOPNOTSUPP;
+
+	err = aq_hw_ops->hw_filter_vlan_ctrl(aq_hw, false);
+	if (err)
+		return err;
+	err = aq_hw_ops->hw_filter_vlan_set(aq_hw,
+					    aq_nic->aq_hw_rx_fltrs.fl2.aq_vlans
+					   );
+	return err;
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.h b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
new file mode 100644
index 000000000000..c6a08c6585d5
--- /dev/null
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (C) 2014-2017 aQuantia Corporation. */
+
+/* File aq_filters.h: RX filters related functions. */
+
+#ifndef AQ_FILTERS_H
+#define AQ_FILTERS_H
+
+#include "aq_nic.h"
+
+enum aq_rx_filter_type {
+	aq_rx_filter_ethertype,
+	aq_rx_filter_vlan,
+	aq_rx_filter_l3l4
+};
+
+struct aq_rx_filter {
+	struct hlist_node aq_node;
+	enum aq_rx_filter_type type;
+	struct ethtool_rx_flow_spec aq_fsp;
+};
+
+u16 aq_get_rxnfc_count_all_rules(struct aq_nic_s *aq_nic);
+struct aq_hw_rx_fltrs_s *aq_get_hw_rx_fltrs(struct aq_nic_s *aq_nic);
+int aq_add_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd);
+int aq_del_rxnfc_rule(struct aq_nic_s *aq_nic, const struct ethtool_rxnfc *cmd);
+int aq_get_rxnfc_rule(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd);
+int aq_get_rxnfc_all_rules(struct aq_nic_s *aq_nic, struct ethtool_rxnfc *cmd,
+			   u32 *rule_locs);
+int aq_del_fvlan_by_vlan(struct aq_nic_s *aq_nic, u16 vlan_id);
+int aq_clear_rxnfc_all_rules(struct aq_nic_s *aq_nic);
+int aq_reapply_rxnfc_all_rules(struct aq_nic_s *aq_nic);
+int aq_filters_vlans_update(struct aq_nic_s *aq_nic);
+int aq_filters_vlan_offload_off(struct aq_nic_s *aq_nic);
+
+#endif /* AQ_FILTERS_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index a1e70da358ca..81aab73dc22f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -18,6 +18,17 @@
 #include "aq_rss.h"
 #include "hw_atl/hw_atl_utils.h"
 
+#define AQ_RX_FIRST_LOC_FVLANID     0U
+#define AQ_RX_LAST_LOC_FVLANID	   15U
+#define AQ_RX_FIRST_LOC_FETHERT    16U
+#define AQ_RX_LAST_LOC_FETHERT	   31U
+#define AQ_RX_FIRST_LOC_FL3L4	   32U
+#define AQ_RX_LAST_LOC_FL3L4	   39U
+#define AQ_RX_MAX_RXNFC_LOC	   AQ_RX_LAST_LOC_FL3L4
+#define AQ_VLAN_MAX_FILTERS   \
+			(AQ_RX_LAST_LOC_FVLANID - AQ_RX_FIRST_LOC_FVLANID + 1U)
+#define AQ_RX_QUEUE_NOT_ASSIGNED   0xFFU
+
 /* NIC H/W capabilities */
 struct aq_hw_caps_s {
 	u64 hw_features;
@@ -130,6 +141,7 @@ struct aq_hw_s {
 struct aq_ring_s;
 struct aq_ring_param_s;
 struct sk_buff;
+struct aq_rx_filter_l3l4;
 
 struct aq_hw_ops {
 
@@ -183,6 +195,23 @@ struct aq_hw_ops {
 	int (*hw_packet_filter_set)(struct aq_hw_s *self,
 				    unsigned int packet_filter);
 
+	int (*hw_filter_l3l4_set)(struct aq_hw_s *self,
+				  struct aq_rx_filter_l3l4 *data);
+
+	int (*hw_filter_l3l4_clear)(struct aq_hw_s *self,
+				    struct aq_rx_filter_l3l4 *data);
+
+	int (*hw_filter_l2_set)(struct aq_hw_s *self,
+				struct aq_rx_filter_l2 *data);
+
+	int (*hw_filter_l2_clear)(struct aq_hw_s *self,
+				  struct aq_rx_filter_l2 *data);
+
+	int (*hw_filter_vlan_set)(struct aq_hw_s *self,
+				  struct aq_rx_filter_vlan *aq_vlans);
+
+	int (*hw_filter_vlan_ctrl)(struct aq_hw_s *self, bool enable);
+
 	int (*hw_multicast_list_set)(struct aq_hw_s *self,
 				     u8 ar_mac[AQ_HW_MULTICAST_ADDRESS_MAX]
 				     [ETH_ALEN],
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
index dc88a1221f1d..bc711238ca0c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw_utils.h
@@ -14,6 +14,8 @@
 #ifndef AQ_HW_UTILS_H
 #define AQ_HW_UTILS_H
 
+#include <linux/iopoll.h>
+
 #include "aq_common.h"
 
 #ifndef HIDWORD
@@ -23,18 +25,6 @@
 
 #define AQ_HW_SLEEP(_US_) mdelay(_US_)
 
-#define AQ_HW_WAIT_FOR(_B_, _US_, _N_) \
-do { \
-	unsigned int AQ_HW_WAIT_FOR_i; \
-	for (AQ_HW_WAIT_FOR_i = _N_; (!(_B_)) && (AQ_HW_WAIT_FOR_i);\
-	--AQ_HW_WAIT_FOR_i) {\
-		udelay(_US_); \
-	} \
-	if (!AQ_HW_WAIT_FOR_i) {\
-		err = -ETIME; \
-	} \
-} while (0)
-
 #define aq_pr_err(...) pr_err(AQ_CFG_DRV_NAME ": " __VA_ARGS__)
 #define aq_pr_trace(...) pr_info(AQ_CFG_DRV_NAME ": " __VA_ARGS__)
 
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
index 7c07eef275eb..2a11c1eefd8f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c
@@ -13,6 +13,7 @@
 #include "aq_nic.h"
 #include "aq_pci_func.h"
 #include "aq_ethtool.h"
+#include "aq_filters.h"
 
 #include <linux/netdevice.h>
 #include <linux/module.h>
@@ -49,6 +50,11 @@ static int aq_ndev_open(struct net_device *ndev)
 	err = aq_nic_init(aq_nic);
 	if (err < 0)
 		goto err_exit;
+
+	err = aq_reapply_rxnfc_all_rules(aq_nic);
+	if (err < 0)
+		goto err_exit;
+
 	err = aq_nic_start(aq_nic);
 	if (err < 0)
 		goto err_exit;
@@ -101,6 +107,21 @@ static int aq_ndev_set_features(struct net_device *ndev,
 	bool is_lro = false;
 	int err = 0;
 
+	if (!(features & NETIF_F_NTUPLE)) {
+		if (aq_nic->ndev->features & NETIF_F_NTUPLE) {
+			err = aq_clear_rxnfc_all_rules(aq_nic);
+			if (unlikely(err))
+				goto err_exit;
+		}
+	}
+	if (!(features & NETIF_F_HW_VLAN_CTAG_FILTER)) {
+		if (aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) {
+			err = aq_filters_vlan_offload_off(aq_nic);
+			if (unlikely(err))
+				goto err_exit;
+		}
+	}
+
 	aq_cfg->features = features;
 
 	if (aq_cfg->aq_hw_caps->hw_features & NETIF_F_LRO) {
@@ -119,6 +140,7 @@ static int aq_ndev_set_features(struct net_device *ndev,
 		err = aq_nic->aq_hw_ops->hw_set_offload(aq_nic->aq_hw,
 							aq_cfg);
 
+err_exit:
 	return err;
 }
 
@@ -147,6 +169,35 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev)
 	aq_nic_set_multicast_list(aq_nic, ndev);
 }
 
+static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto,
+				  u16 vid)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	if (!aq_nic->aq_hw_ops->hw_filter_vlan_set)
+		return -EOPNOTSUPP;
+
+	set_bit(vid, aq_nic->active_vlans);
+
+	return aq_filters_vlans_update(aq_nic);
+}
+
+static int aq_ndo_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto,
+				   u16 vid)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	if (!aq_nic->aq_hw_ops->hw_filter_vlan_set)
+		return -EOPNOTSUPP;
+
+	clear_bit(vid, aq_nic->active_vlans);
+
+	if (-ENOENT == aq_del_fvlan_by_vlan(aq_nic, vid))
+		return aq_filters_vlans_update(aq_nic);
+
+	return 0;
+}
+
 static const struct net_device_ops aq_ndev_ops = {
 	.ndo_open = aq_ndev_open,
 	.ndo_stop = aq_ndev_close,
@@ -154,5 +205,7 @@ static const struct net_device_ops aq_ndev_ops = {
 	.ndo_set_rx_mode = aq_ndev_set_multicast_settings,
 	.ndo_change_mtu = aq_ndev_change_mtu,
 	.ndo_set_mac_address = aq_ndev_set_mac_address,
-	.ndo_set_features = aq_ndev_set_features
+	.ndo_set_features = aq_ndev_set_features,
+	.ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 7abdc0952425..ff83667410bd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -44,7 +44,7 @@ static void aq_nic_rss_init(struct aq_nic_s *self, unsigned int num_rss_queues)
 	struct aq_rss_parameters *rss_params = &cfg->aq_rss;
 	int i = 0;
 
-	static u8 rss_key[40] = {
+	static u8 rss_key[AQ_CFG_RSS_HASHKEY_SIZE] = {
 		0x1e, 0xad, 0x71, 0x87, 0x65, 0xfc, 0x26, 0x7d,
 		0x0d, 0x45, 0x67, 0x74, 0xcd, 0x06, 0x1a, 0x18,
 		0xb6, 0xc1, 0xf0, 0xc7, 0xbb, 0x18, 0xbe, 0xf8,
@@ -84,10 +84,6 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->is_lro = AQ_CFG_IS_LRO_DEF;
 
-	cfg->vlan_id = 0U;
-
-	aq_nic_rss_init(self, cfg->num_rss_queues);
-
 	/*descriptors */
 	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
 	cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
@@ -108,6 +104,8 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 
 	cfg->num_rss_queues = min(cfg->vecs, AQ_CFG_NUM_RSS_QUEUES_DEF);
 
+	aq_nic_rss_init(self, cfg->num_rss_queues);
+
 	cfg->irq_type = aq_pci_func_get_irq_type(self);
 
 	if ((cfg->irq_type == AQ_HW_IRQ_LEGACY) ||
@@ -988,4 +986,4 @@ void aq_nic_shutdown(struct aq_nic_s *self)
 
 err_exit:
 	rtnl_unlock();
-}
\ No newline at end of file
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
index 44ec47a3d60a..8e34c1e49bf2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h
@@ -35,7 +35,6 @@ struct aq_nic_cfg_s {
 	u32 mtu;
 	u32 flow_control;
 	u32 link_speed_msk;
-	u32 vlan_id;
 	u32 wol;
 	u16 is_mc_list_enabled;
 	u16 mc_list_count;
@@ -61,6 +60,23 @@ struct aq_nic_cfg_s {
 #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \
 	((_TC_) * AQ_CFG_TCS_MAX + (_VEC_))
 
+struct aq_hw_rx_fl2 {
+	struct aq_rx_filter_vlan aq_vlans[AQ_VLAN_MAX_FILTERS];
+};
+
+struct aq_hw_rx_fl3l4 {
+	u8   active_ipv4;
+	u8   active_ipv6:2;
+	u8 is_ipv6;
+};
+
+struct aq_hw_rx_fltrs_s {
+	struct hlist_head     filter_list;
+	u16                   active_filters;
+	struct aq_hw_rx_fl2   fl2;
+	struct aq_hw_rx_fl3l4 fl3l4;
+};
+
 struct aq_nic_s {
 	atomic_t flags;
 	struct aq_vec_s *aq_vec[AQ_CFG_VECS_MAX];
@@ -81,10 +97,13 @@ struct aq_nic_s {
 		u32 count;
 		u8 ar[AQ_HW_MULTICAST_ADDRESS_MAX][ETH_ALEN];
 	} mc_list;
+	/* Bitmask of currently assigned vlans from linux */
+	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 
 	struct pci_dev *pdev;
 	unsigned int msix_entry_mask;
 	u32 irqvecs;
+	struct aq_hw_rx_fltrs_s aq_hw_rx_fltrs;
 };
 
 static inline struct device *aq_nic_get_dev(struct aq_nic_s *self)
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
index 1d5d6b8df855..0217ff4669a4 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c
@@ -19,6 +19,7 @@
 #include "aq_pci_func.h"
 #include "hw_atl/hw_atl_a0.h"
 #include "hw_atl/hw_atl_b0.h"
+#include "aq_filters.h"
 
 static const struct pci_device_id aq_pci_tbl[] = {
 	{ PCI_VDEVICE(AQUANTIA, AQ_DEVICE_ID_0001), },
@@ -169,6 +170,8 @@ void aq_pci_func_free_irqs(struct aq_nic_s *self)
 	for (i = 32U; i--;) {
 		if (!((1U << i) & self->msix_entry_mask))
 			continue;
+		if (i >= AQ_CFG_VECS_MAX)
+			continue;
 
 		if (pdev->msix_enabled)
 			irq_set_affinity_hint(pci_irq_vector(pdev, i), NULL);
@@ -309,6 +312,7 @@ static void aq_pci_remove(struct pci_dev *pdev)
 	struct aq_nic_s *self = pci_get_drvdata(pdev);
 
 	if (self->ndev) {
+		aq_clear_rxnfc_all_rules(self);
 		if (self->ndev->reg_state == NETREG_REGISTERED)
 			unregister_netdev(self->ndev);
 		aq_nic_free_vectors(self);
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 74550ccc7a20..e2ffb159cbe2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -186,11 +186,12 @@ static void aq_rx_checksum(struct aq_ring_s *self,
 	}
 	if (buff->is_ip_cso) {
 		__skb_incr_checksum_unnecessary(skb);
-		if (buff->is_udp_cso || buff->is_tcp_cso)
-			__skb_incr_checksum_unnecessary(skb);
 	} else {
 		skb->ip_summed = CHECKSUM_NONE;
 	}
+
+	if (buff->is_udp_cso || buff->is_tcp_cso)
+		__skb_incr_checksum_unnecessary(skb);
 }
 
 #define AQ_SKB_ALIGN SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 2469ed4d86b9..f6f8338153a2 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -85,6 +85,7 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc109 = {
 static int hw_atl_a0_hw_reset(struct aq_hw_s *self)
 {
 	int err = 0;
+	u32 val;
 
 	hw_atl_glb_glb_reg_res_dis_set(self, 1U);
 	hw_atl_pci_pci_reg_res_dis_set(self, 0U);
@@ -95,7 +96,9 @@ static int hw_atl_a0_hw_reset(struct aq_hw_s *self)
 	hw_atl_glb_soft_res_set(self, 1);
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(hw_atl_glb_soft_res_get(self) == 0, 1000U, 10U);
+	err = readx_poll_timeout_atomic(hw_atl_glb_soft_res_get,
+					self, val, val == 0,
+					1000U, 10000U);
 	if (err < 0)
 		goto err_exit;
 
@@ -103,7 +106,9 @@ static int hw_atl_a0_hw_reset(struct aq_hw_s *self)
 	hw_atl_itr_res_irq_set(self, 1U);
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(hw_atl_itr_res_irq_get(self) == 0, 1000U, 10U);
+	err = readx_poll_timeout_atomic(hw_atl_itr_res_irq_get,
+					self, val, val == 0,
+					1000U, 10000U);
 	if (err < 0)
 		goto err_exit;
 
@@ -181,6 +186,7 @@ static int hw_atl_a0_hw_rss_hash_set(struct aq_hw_s *self,
 	int err = 0;
 	unsigned int i = 0U;
 	unsigned int addr = 0U;
+	u32 val;
 
 	for (i = 10, addr = 0U; i--; ++addr) {
 		u32 key_data = cfg->is_rss ?
@@ -188,8 +194,9 @@ static int hw_atl_a0_hw_rss_hash_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_key_wr_data_set(self, key_data);
 		hw_atl_rpf_rss_key_addr_set(self, addr);
 		hw_atl_rpf_rss_key_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_key_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_key_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -207,8 +214,9 @@ static int hw_atl_a0_hw_rss_set(struct aq_hw_s *self,
 	u32 i = 0U;
 	u32 num_rss_queues = max(1U, self->aq_nic_cfg->num_rss_queues);
 	int err = 0;
-	u16 bitary[(HW_ATL_A0_RSS_REDIRECTION_MAX *
-					HW_ATL_A0_RSS_REDIRECTION_BITS / 16U)];
+	u16 bitary[1 + (HW_ATL_A0_RSS_REDIRECTION_MAX *
+		   HW_ATL_A0_RSS_REDIRECTION_BITS / 16U)];
+	u32 val;
 
 	memset(bitary, 0, sizeof(bitary));
 
@@ -222,8 +230,9 @@ static int hw_atl_a0_hw_rss_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_redir_tbl_wr_data_set(self, bitary[i]);
 		hw_atl_rpf_rss_redir_tbl_addr_set(self, i);
 		hw_atl_rpf_rss_redir_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_redir_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_redir_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index a7e853fa43c2..b31dba1b1a55 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -21,7 +21,7 @@
 
 #define DEFAULT_B0_BOARD_BASIC_CAPABILITIES \
 	.is_64_dma = true,		  \
-	.msix_irqs = 4U,		  \
+	.msix_irqs = 8U,		  \
 	.irq_mask = ~0U,		  \
 	.vecs = HW_ATL_B0_RSS_MAX,	  \
 	.tcs = HW_ATL_B0_TC_MAX,	  \
@@ -41,7 +41,9 @@
 			NETIF_F_RXHASH |  \
 			NETIF_F_SG |      \
 			NETIF_F_TSO |     \
-			NETIF_F_LRO,      \
+			NETIF_F_LRO |     \
+			NETIF_F_NTUPLE |  \
+			NETIF_F_HW_VLAN_CTAG_FILTER, \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
 	.flow_control = true,		  \
 	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
@@ -171,6 +173,7 @@ static int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
 	int err = 0;
 	unsigned int i = 0U;
 	unsigned int addr = 0U;
+	u32 val;
 
 	for (i = 10, addr = 0U; i--; ++addr) {
 		u32 key_data = cfg->is_rss ?
@@ -178,8 +181,9 @@ static int hw_atl_b0_hw_rss_hash_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_key_wr_data_set(self, key_data);
 		hw_atl_rpf_rss_key_addr_set(self, addr);
 		hw_atl_rpf_rss_key_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_key_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_key_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -197,8 +201,9 @@ static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
 	u32 i = 0U;
 	u32 num_rss_queues = max(1U, self->aq_nic_cfg->num_rss_queues);
 	int err = 0;
-	u16 bitary[(HW_ATL_B0_RSS_REDIRECTION_MAX *
-					HW_ATL_B0_RSS_REDIRECTION_BITS / 16U)];
+	u16 bitary[1 + (HW_ATL_B0_RSS_REDIRECTION_MAX *
+		   HW_ATL_B0_RSS_REDIRECTION_BITS / 16U)];
+	u32 val;
 
 	memset(bitary, 0, sizeof(bitary));
 
@@ -212,8 +217,9 @@ static int hw_atl_b0_hw_rss_set(struct aq_hw_s *self,
 		hw_atl_rpf_rss_redir_tbl_wr_data_set(self, bitary[i]);
 		hw_atl_rpf_rss_redir_tbl_addr_set(self, i);
 		hw_atl_rpf_rss_redir_wr_en_set(self, 1U);
-		AQ_HW_WAIT_FOR(hw_atl_rpf_rss_redir_wr_en_get(self) == 0,
-			       1000U, 10U);
+		err = readx_poll_timeout_atomic(hw_atl_rpf_rss_redir_wr_en_get,
+						self, val, val == 0,
+						1000U, 10000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -273,6 +279,9 @@ static int hw_atl_b0_hw_offload_set(struct aq_hw_s *self,
 
 static int hw_atl_b0_hw_init_tx_path(struct aq_hw_s *self)
 {
+	/* Tx TC/Queue number config */
+	hw_atl_rpb_tps_tx_tc_mode_set(self, 1U);
+
 	hw_atl_thm_lso_tcp_flag_of_first_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(self, 0x0FF6U);
 	hw_atl_thm_lso_tcp_flag_of_last_pkt_set(self, 0x0F7FU);
@@ -319,20 +328,11 @@ static int hw_atl_b0_hw_init_rx_path(struct aq_hw_s *self)
 	hw_atl_rpf_vlan_outer_etht_set(self, 0x88A8U);
 	hw_atl_rpf_vlan_inner_etht_set(self, 0x8100U);
 
-	if (cfg->vlan_id) {
-		hw_atl_rpf_vlan_flr_act_set(self, 1U, 0U);
-		hw_atl_rpf_vlan_id_flr_set(self, 0U, 0U);
-		hw_atl_rpf_vlan_flr_en_set(self, 0U, 0U);
+	hw_atl_rpf_vlan_prom_mode_en_set(self, 1);
 
-		hw_atl_rpf_vlan_accept_untagged_packets_set(self, 1U);
-		hw_atl_rpf_vlan_untagged_act_set(self, 1U);
-
-		hw_atl_rpf_vlan_flr_act_set(self, 1U, 1U);
-		hw_atl_rpf_vlan_id_flr_set(self, cfg->vlan_id, 0U);
-		hw_atl_rpf_vlan_flr_en_set(self, 1U, 1U);
-	} else {
-		hw_atl_rpf_vlan_prom_mode_en_set(self, 1);
-	}
+	// Always accept untagged packets
+	hw_atl_rpf_vlan_accept_untagged_packets_set(self, 1U);
+	hw_atl_rpf_vlan_untagged_act_set(self, 1U);
 
 	/* Rx Interrupts */
 	hw_atl_rdm_rx_desc_wr_wb_irq_en_set(self, 1U);
@@ -945,6 +945,142 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self,
 	return aq_hw_err_from_flags(self);
 }
 
+static int hw_atl_b0_hw_fl3l4_clear(struct aq_hw_s *self,
+				    struct aq_rx_filter_l3l4 *data)
+{
+	u8 location = data->location;
+
+	if (!data->is_ipv6) {
+		hw_atl_rpfl3l4_cmd_clear(self, location);
+		hw_atl_rpf_l4_spd_set(self, 0U, location);
+		hw_atl_rpf_l4_dpd_set(self, 0U, location);
+		hw_atl_rpfl3l4_ipv4_src_addr_clear(self, location);
+		hw_atl_rpfl3l4_ipv4_dest_addr_clear(self, location);
+	} else {
+		int i;
+
+		for (i = 0; i < HW_ATL_RX_CNT_REG_ADDR_IPV6; ++i) {
+			hw_atl_rpfl3l4_cmd_clear(self, location + i);
+			hw_atl_rpf_l4_spd_set(self, 0U, location + i);
+			hw_atl_rpf_l4_dpd_set(self, 0U, location + i);
+		}
+		hw_atl_rpfl3l4_ipv6_src_addr_clear(self, location);
+		hw_atl_rpfl3l4_ipv6_dest_addr_clear(self, location);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl_b0_hw_fl3l4_set(struct aq_hw_s *self,
+				  struct aq_rx_filter_l3l4 *data)
+{
+	u8 location = data->location;
+
+	hw_atl_b0_hw_fl3l4_clear(self, data);
+
+	if (data->cmd) {
+		if (!data->is_ipv6) {
+			hw_atl_rpfl3l4_ipv4_dest_addr_set(self,
+							  location,
+							  data->ip_dst[0]);
+			hw_atl_rpfl3l4_ipv4_src_addr_set(self,
+							 location,
+							 data->ip_src[0]);
+		} else {
+			hw_atl_rpfl3l4_ipv6_dest_addr_set(self,
+							  location,
+							  data->ip_dst);
+			hw_atl_rpfl3l4_ipv6_src_addr_set(self,
+							 location,
+							 data->ip_src);
+		}
+	}
+	hw_atl_rpf_l4_dpd_set(self, data->p_dst, location);
+	hw_atl_rpf_l4_spd_set(self, data->p_src, location);
+	hw_atl_rpfl3l4_cmd_set(self, location, data->cmd);
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl_b0_hw_fl2_set(struct aq_hw_s *self,
+				struct aq_rx_filter_l2 *data)
+{
+	hw_atl_rpf_etht_flr_en_set(self, 1U, data->location);
+	hw_atl_rpf_etht_flr_set(self, data->ethertype, data->location);
+	hw_atl_rpf_etht_user_priority_en_set(self,
+					     !!data->user_priority_en,
+					     data->location);
+	if (data->user_priority_en)
+		hw_atl_rpf_etht_user_priority_set(self,
+						  data->user_priority,
+						  data->location);
+
+	if (data->queue < 0) {
+		hw_atl_rpf_etht_flr_act_set(self, 0U, data->location);
+		hw_atl_rpf_etht_rx_queue_en_set(self, 0U, data->location);
+	} else {
+		hw_atl_rpf_etht_flr_act_set(self, 1U, data->location);
+		hw_atl_rpf_etht_rx_queue_en_set(self, 1U, data->location);
+		hw_atl_rpf_etht_rx_queue_set(self, data->queue, data->location);
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl_b0_hw_fl2_clear(struct aq_hw_s *self,
+				  struct aq_rx_filter_l2 *data)
+{
+	hw_atl_rpf_etht_flr_en_set(self, 0U, data->location);
+	hw_atl_rpf_etht_flr_set(self, 0U, data->location);
+	hw_atl_rpf_etht_user_priority_en_set(self, 0U, data->location);
+
+	return aq_hw_err_from_flags(self);
+}
+
+/**
+ * @brief Set VLAN filter table
+ * @details Configure VLAN filter table to accept (and assign the queue) traffic
+ *  for the particular vlan ids.
+ * Note: use this function under vlan promisc mode not to lost the traffic
+ *
+ * @param aq_hw_s
+ * @param aq_rx_filter_vlan VLAN filter configuration
+ * @return 0 - OK, <0 - error
+ */
+static int hw_atl_b0_hw_vlan_set(struct aq_hw_s *self,
+				 struct aq_rx_filter_vlan *aq_vlans)
+{
+	int i;
+
+	for (i = 0; i < AQ_VLAN_MAX_FILTERS; i++) {
+		hw_atl_rpf_vlan_flr_en_set(self, 0U, i);
+		hw_atl_rpf_vlan_rxq_en_flr_set(self, 0U, i);
+		if (aq_vlans[i].enable) {
+			hw_atl_rpf_vlan_id_flr_set(self,
+						   aq_vlans[i].vlan_id,
+						   i);
+			hw_atl_rpf_vlan_flr_act_set(self, 1U, i);
+			hw_atl_rpf_vlan_flr_en_set(self, 1U, i);
+			if (aq_vlans[i].queue != 0xFF) {
+				hw_atl_rpf_vlan_rxq_flr_set(self,
+							    aq_vlans[i].queue,
+							    i);
+				hw_atl_rpf_vlan_rxq_en_flr_set(self, 1U, i);
+			}
+		}
+	}
+
+	return aq_hw_err_from_flags(self);
+}
+
+static int hw_atl_b0_hw_vlan_ctrl(struct aq_hw_s *self, bool enable)
+{
+	/* set promisc in case of disabing the vland filter */
+	hw_atl_rpf_vlan_prom_mode_en_set(self, !!!enable);
+
+	return aq_hw_err_from_flags(self);
+}
+
 const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
@@ -969,6 +1105,11 @@ const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_ring_rx_init             = hw_atl_b0_hw_ring_rx_init,
 	.hw_ring_tx_init             = hw_atl_b0_hw_ring_tx_init,
 	.hw_packet_filter_set        = hw_atl_b0_hw_packet_filter_set,
+	.hw_filter_l2_set            = hw_atl_b0_hw_fl2_set,
+	.hw_filter_l2_clear          = hw_atl_b0_hw_fl2_clear,
+	.hw_filter_l3l4_set          = hw_atl_b0_hw_fl3l4_set,
+	.hw_filter_vlan_set          = hw_atl_b0_hw_vlan_set,
+	.hw_filter_vlan_ctrl         = hw_atl_b0_hw_vlan_ctrl,
 	.hw_multicast_list_set       = hw_atl_b0_hw_multicast_list_set,
 	.hw_interrupt_moderation_set = hw_atl_b0_hw_interrupt_moderation_set,
 	.hw_rss_set                  = hw_atl_b0_hw_rss_set,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
index 5502ec5f0f69..0722b8e01964 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c
@@ -898,6 +898,24 @@ void hw_atl_rpf_vlan_id_flr_set(struct aq_hw_s *aq_hw, u32 vlan_id_flr,
 			    vlan_id_flr);
 }
 
+void hw_atl_rpf_vlan_rxq_en_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq_en,
+				    u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_VL_RXQ_EN_F_ADR(filter),
+			    HW_ATL_RPF_VL_RXQ_EN_F_MSK,
+			    HW_ATL_RPF_VL_RXQ_EN_F_SHIFT,
+			    vlan_rxq_en);
+}
+
+void hw_atl_rpf_vlan_rxq_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq,
+				 u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_VL_RXQ_F_ADR(filter),
+			    HW_ATL_RPF_VL_RXQ_F_MSK,
+			    HW_ATL_RPF_VL_RXQ_F_SHIFT,
+			    vlan_rxq);
+};
+
 void hw_atl_rpf_etht_flr_en_set(struct aq_hw_s *aq_hw, u32 etht_flr_en,
 				u32 filter)
 {
@@ -965,6 +983,20 @@ void hw_atl_rpf_etht_flr_set(struct aq_hw_s *aq_hw, u32 etht_flr, u32 filter)
 			    HW_ATL_RPF_ET_VALF_SHIFT, etht_flr);
 }
 
+void hw_atl_rpf_l4_spd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_L4_SPD_ADR(filter),
+			    HW_ATL_RPF_L4_SPD_MSK,
+			    HW_ATL_RPF_L4_SPD_SHIFT, val);
+}
+
+void hw_atl_rpf_l4_dpd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_RPF_L4_DPD_ADR(filter),
+			    HW_ATL_RPF_L4_DPD_MSK,
+			    HW_ATL_RPF_L4_DPD_SHIFT, val);
+}
+
 /* RPO: rx packet offload */
 void hw_atl_rpo_ipv4header_crc_offload_en_set(struct aq_hw_s *aq_hw,
 					      u32 ipv4header_crc_offload_en)
@@ -1242,6 +1274,15 @@ void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en)
 			    HW_ATL_TPB_TX_BUF_EN_SHIFT, tx_buff_en);
 }
 
+void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
+				   u32 tx_traf_class_mode)
+{
+	aq_hw_write_reg_bit(aq_hw, HW_ATL_TPB_TX_TC_MODE_ADDR,
+			HW_ATL_TPB_TX_TC_MODE_MSK,
+			HW_ATL_TPB_TX_TC_MODE_SHIFT,
+			tx_traf_class_mode);
+}
+
 void hw_atl_tpb_tx_buff_hi_threshold_per_tc_set(struct aq_hw_s *aq_hw,
 						u32 tx_buff_hi_threshold_per_tc,
 					 u32 buffer)
@@ -1476,3 +1517,101 @@ void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr)
 			    HW_ATL_MCP_UP_FORCE_INTERRUPT_SHIFT,
 			    up_force_intr);
 }
+
+void hw_atl_rpfl3l4_ipv4_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_DSTA_ADR(location), 0U);
+}
+
+void hw_atl_rpfl3l4_ipv4_src_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_SRCA_ADR(location), 0U);
+}
+
+void hw_atl_rpfl3l4_cmd_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_REG_CTRL_ADR(location), 0U);
+}
+
+void hw_atl_rpfl3l4_ipv6_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_DSTA_ADR(location + i),
+				0U);
+}
+
+void hw_atl_rpfl3l4_ipv6_src_addr_clear(struct aq_hw_s *aq_hw, u8 location)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_SRCA_ADR(location + i),
+				0U);
+}
+
+void hw_atl_rpfl3l4_ipv4_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 ipv4_dest)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_DSTA_ADR(location),
+			ipv4_dest);
+}
+
+void hw_atl_rpfl3l4_ipv4_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 ipv4_src)
+{
+	aq_hw_write_reg(aq_hw,
+			HW_ATL_RPF_L3_SRCA_ADR(location),
+			ipv4_src);
+}
+
+void hw_atl_rpfl3l4_cmd_set(struct aq_hw_s *aq_hw, u8 location, u32 cmd)
+{
+	aq_hw_write_reg(aq_hw, HW_ATL_RPF_L3_REG_CTRL_ADR(location), cmd);
+}
+
+void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 *ipv6_src)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_SRCA_ADR(location + i),
+				ipv6_src[i]);
+}
+
+void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 *ipv6_dest)
+{
+	int i;
+
+	for (i = 0; i < 4; ++i)
+		aq_hw_write_reg(aq_hw,
+				HW_ATL_RPF_L3_DSTA_ADR(location + i),
+				ipv6_dest[i]);
+}
+
+u32 hw_atl_sem_ram_get(struct aq_hw_s *self)
+{
+	return hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM);
+}
+
+u32 hw_atl_scrpad_get(struct aq_hw_s *aq_hw, u32 scratch_scp)
+{
+	return aq_hw_read_reg(aq_hw,
+			      HW_ATL_GLB_CPU_SCRATCH_SCP_ADR(scratch_scp));
+}
+
+u32 hw_atl_scrpad12_get(struct aq_hw_s *self)
+{
+	return  hw_atl_scrpad_get(self, 0xB);
+}
+
+u32 hw_atl_scrpad25_get(struct aq_hw_s *self)
+{
+	return hw_atl_scrpad_get(self, 0x18);
+}
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
index 41f239928c15..d46351890b16 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h
@@ -441,6 +441,14 @@ void hw_atl_rpf_vlan_flr_act_set(struct aq_hw_s *aq_hw, u32 vlan_filter_act,
 void hw_atl_rpf_vlan_id_flr_set(struct aq_hw_s *aq_hw, u32 vlan_id_flr,
 				u32 filter);
 
+/* Set VLAN RX queue assignment enable */
+void hw_atl_rpf_vlan_rxq_en_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq_en,
+				    u32 filter);
+
+/* Set VLAN RX queue */
+void hw_atl_rpf_vlan_rxq_flr_set(struct aq_hw_s *aq_hw, u32 vlan_rxq,
+				 u32 filter);
+
 /* set ethertype filter enable */
 void hw_atl_rpf_etht_flr_en_set(struct aq_hw_s *aq_hw, u32 etht_flr_en,
 				u32 filter);
@@ -475,6 +483,12 @@ void hw_atl_rpf_etht_flr_act_set(struct aq_hw_s *aq_hw, u32 etht_flr_act,
 /* set ethertype filter */
 void hw_atl_rpf_etht_flr_set(struct aq_hw_s *aq_hw, u32 etht_flr, u32 filter);
 
+/* set L4 source port */
+void hw_atl_rpf_l4_spd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter);
+
+/* set L4 destination port */
+void hw_atl_rpf_l4_dpd_set(struct aq_hw_s *aq_hw, u32 val, u32 filter);
+
 /* rpo */
 
 /* set ipv4 header checksum offload enable */
@@ -591,6 +605,10 @@ void hw_atl_thm_lso_tcp_flag_of_middle_pkt_set(struct aq_hw_s *aq_hw,
 
 /* tpb */
 
+/* set TX Traffic Class Mode */
+void hw_atl_rpb_tps_tx_tc_mode_set(struct aq_hw_s *aq_hw,
+				   u32 tx_traf_class_mode);
+
 /* set tx buffer enable */
 void hw_atl_tpb_tx_buff_en_set(struct aq_hw_s *aq_hw, u32 tx_buff_en);
 
@@ -704,4 +722,50 @@ void hw_atl_pci_pci_reg_res_dis_set(struct aq_hw_s *aq_hw, u32 pci_reg_res_dis);
 /* set uP Force Interrupt */
 void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr);
 
+/* clear ipv4 filter destination address */
+void hw_atl_rpfl3l4_ipv4_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear ipv4 filter source address */
+void hw_atl_rpfl3l4_ipv4_src_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear command for filter l3-l4 */
+void hw_atl_rpfl3l4_cmd_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear ipv6 filter destination address */
+void hw_atl_rpfl3l4_ipv6_dest_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* clear ipv6 filter source address */
+void hw_atl_rpfl3l4_ipv6_src_addr_clear(struct aq_hw_s *aq_hw, u8 location);
+
+/* set ipv4 filter destination address */
+void hw_atl_rpfl3l4_ipv4_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 ipv4_dest);
+
+/* set ipv4 filter source address */
+void hw_atl_rpfl3l4_ipv4_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 ipv4_src);
+
+/* set command for filter l3-l4 */
+void hw_atl_rpfl3l4_cmd_set(struct aq_hw_s *aq_hw, u8 location, u32 cmd);
+
+/* set ipv6 filter source address */
+void hw_atl_rpfl3l4_ipv6_src_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				      u32 *ipv6_src);
+
+/* set ipv6 filter destination address */
+void hw_atl_rpfl3l4_ipv6_dest_addr_set(struct aq_hw_s *aq_hw, u8 location,
+				       u32 *ipv6_dest);
+
+/* get global microprocessor ram semaphore */
+u32 hw_atl_sem_ram_get(struct aq_hw_s *self);
+
+/* get global microprocessor scratch pad register */
+u32 hw_atl_scrpad_get(struct aq_hw_s *aq_hw, u32 scratch_scp);
+
+/* get global microprocessor scratch pad 12 register */
+u32 hw_atl_scrpad12_get(struct aq_hw_s *self);
+
+/* get global microprocessor scratch pad 25 register */
+u32 hw_atl_scrpad25_get(struct aq_hw_s *self);
+
 #endif /* HW_ATL_LLH_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
index a715fa317b1c..fb45bc2d99cf 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h
@@ -1092,24 +1092,43 @@
 /* Default value of bitfield vl_id{F}[B:0] */
 #define HW_ATL_RPF_VL_ID_F_DEFAULT 0x0
 
-/* RX et_en{F} Bitfield Definitions
- * Preprocessor definitions for the bitfield "et_en{F}".
+/* RX vl_rxq_en{F} Bitfield Definitions
+ * Preprocessor definitions for the bitfield "vl_rxq{F}".
  * Parameter: filter {F} | stride size 0x4 | range [0, 15]
- * PORT="pif_rpf_et_en_i[0]"
- */
-
-/* Register address for bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_ADR(filter) (0x00005300 + (filter) * 0x4)
-/* Bitmask for bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_MSK 0x80000000
-/* Inverted bitmask for bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_MSKN 0x7FFFFFFF
-/* Lower bit position of bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_SHIFT 31
-/* Width of bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_WIDTH 1
-/* Default value of bitfield et_en{F} */
-#define HW_ATL_RPF_ET_EN_F_DEFAULT 0x0
+ * PORT="pif_rpf_vl_rxq_en_i"
+ */
+
+/* Register address for bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_ADR(filter) (0x00005290 + (filter) * 0x4)
+/* Bitmask for bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_MSK 0x10000000
+/* Inverted bitmask for bitfield vl_rxq_en{F}[ */
+#define HW_ATL_RPF_VL_RXQ_EN_F_MSKN 0xEFFFFFFF
+/* Lower bit position of bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_SHIFT 28
+/* Width of bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_WIDTH 1
+/* Default value of bitfield vl_rxq_en{F} */
+#define HW_ATL_RPF_VL_RXQ_EN_F_DEFAULT 0x0
+
+/* RX vl_rxq{F}[4:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "vl_rxq{F}[4:0]".
+ * Parameter: filter {F} | stride size 0x4 | range [0, 15]
+ * PORT="pif_rpf_vl_rxq0_i[4:0]"
+ */
+
+/* Register address for bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_ADR(filter) (0x00005290 + (filter) * 0x4)
+/* Bitmask for bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_MSK 0x01F00000
+/* Inverted bitmask for bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_MSKN 0xFE0FFFFF
+/* Lower bit position of bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_SHIFT 20
+/* Width of bitfield vl_rxw{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_WIDTH 5
+/* Default value of bitfield vl_rxq{F}[4:0] */
+#define HW_ATL_RPF_VL_RXQ_F_DEFAULT 0x0
 
 /* rx et_en{f} bitfield definitions
  * preprocessor definitions for the bitfield "et_en{f}".
@@ -1263,6 +1282,44 @@
 /* default value of bitfield et_val{f}[f:0] */
 #define HW_ATL_RPF_ET_VALF_DEFAULT 0x0
 
+/* RX l4_sp{D}[F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l4_sp{D}[F:0]".
+ * Parameter: srcport {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l4_sp0_i[15:0]"
+ */
+
+/* Register address for bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_ADR(srcport) (0x00005400u + (srcport) * 0x4)
+/* Bitmask for bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_MSK 0x0000FFFFu
+/* Inverted bitmask for bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_MSKN 0xFFFF0000u
+/* Lower bit position of bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_SHIFT 0
+/* Width of bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_WIDTH 16
+/* Default value of bitfield l4_sp{D}[F:0] */
+#define HW_ATL_RPF_L4_SPD_DEFAULT 0x0
+
+/* RX l4_dp{D}[F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l4_dp{D}[F:0]".
+ * Parameter: destport {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l4_dp0_i[15:0]"
+ */
+
+/* Register address for bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_ADR(destport) (0x00005420u + (destport) * 0x4)
+/* Bitmask for bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_MSK 0x0000FFFFu
+/* Inverted bitmask for bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_MSKN 0xFFFF0000u
+/* Lower bit position of bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_SHIFT 0
+/* Width of bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_WIDTH 16
+/* Default value of bitfield l4_dp{D}[F:0] */
+#define HW_ATL_RPF_L4_DPD_DEFAULT 0x0
+
 /* rx ipv4_chk_en bitfield definitions
  * preprocessor definitions for the bitfield "ipv4_chk_en".
  * port="pif_rpo_ipv4_chk_en_i"
@@ -1891,6 +1948,19 @@
 /* default value of bitfield tx_buf_en */
 #define HW_ATL_TPB_TX_BUF_EN_DEFAULT 0x0
 
+/* register address for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_ADDR 0x00007900
+/* bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSK 0x00000100
+/* inverted bitmask for bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_MSKN 0xFFFFFEFF
+/* lower bit position of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_SHIFT 8
+/* width of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_WIDTH 1
+/* default value of bitfield tx_tc_mode */
+#define HW_ATL_TPB_TX_TC_MODE_DEFAULT 0x0
+
 /* tx tx{b}_hi_thresh[c:0] bitfield definitions
  * preprocessor definitions for the bitfield "tx{b}_hi_thresh[c:0]".
  * parameter: buffer {b} | stride size 0x10 | range [0, 7]
@@ -2418,4 +2488,50 @@
 /* default value of bitfield uP Force Interrupt */
 #define HW_ATL_MCP_UP_FORCE_INTERRUPT_DEFAULT 0x0
 
+#define HW_ATL_RX_CTRL_ADDR_BEGIN_FL3L4   0x00005380
+#define HW_ATL_RX_SRCA_ADDR_BEGIN_FL3L4   0x000053B0
+#define HW_ATL_RX_DESTA_ADDR_BEGIN_FL3L4  0x000053D0
+
+#define HW_ATL_RPF_L3_REG_CTRL_ADR(location) (0x00005380 + (location) * 0x4)
+
+/* RX rpf_l3_sa{D}[1F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l3_sa{D}[1F:0]".
+ * Parameter: location {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l3_sa0_i[31:0]"
+ */
+
+/* Register address for bitfield pif_rpf_l3_sa0_i[31:0] */
+#define HW_ATL_RPF_L3_SRCA_ADR(location) (0x000053B0 + (location) * 0x4)
+/* Bitmask for bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_MSK 0xFFFFFFFFu
+/* Inverted bitmask for bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_MSKN 0xFFFFFFFFu
+/* Lower bit position of bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_SHIFT 0
+/* Width of bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_WIDTH 32
+/* Default value of bitfield l3_sa0[1F:0] */
+#define HW_ATL_RPF_L3_SRCA_DEFAULT 0x0
+
+/* RX rpf_l3_da{D}[1F:0] Bitfield Definitions
+ * Preprocessor definitions for the bitfield "l3_da{D}[1F:0]".
+ * Parameter: location {D} | stride size 0x4 | range [0, 7]
+ * PORT="pif_rpf_l3_da0_i[31:0]"
+ */
+
+ /* Register address for bitfield pif_rpf_l3_da0_i[31:0] */
+#define HW_ATL_RPF_L3_DSTA_ADR(location) (0x000053B0 + (location) * 0x4)
+/* Bitmask for bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_MSK 0xFFFFFFFFu
+/* Inverted bitmask for bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_MSKN 0xFFFFFFFFu
+/* Lower bit position of bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_SHIFT 0
+/* Width of bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_WIDTH 32
+/* Default value of bitfield l3_da0[1F:0] */
+#define HW_ATL_RPF_L3_DSTA_DEFAULT 0x0
+
+#define HW_ATL_FW_SM_RAM        0x2U
+
 #endif /* HW_ATL_LLH_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 7def1cb8ab9d..eb4b99d56081 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -25,7 +25,9 @@
 #define HW_ATL_MIF_ADDR         0x0208U
 #define HW_ATL_MIF_VAL          0x020CU
 
-#define HW_ATL_FW_SM_RAM        0x2U
+#define HW_ATL_RPC_CONTROL_ADR  0x0338U
+#define HW_ATL_RPC_STATE_ADR    0x033CU
+
 #define HW_ATL_MPI_FW_VERSION	0x18
 #define HW_ATL_MPI_CONTROL_ADR  0x0368U
 #define HW_ATL_MPI_STATE_ADR    0x036CU
@@ -53,6 +55,12 @@ static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual);
 static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 				      enum hal_atl_utils_fw_state_e state);
 
+static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self);
+static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self);
+static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self);
+static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self);
+static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self);
+
 int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops)
 {
 	int err = 0;
@@ -234,6 +242,7 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
 {
 	int k;
 	u32 boot_exit_code = 0;
+	u32 val;
 
 	for (k = 0; k < 1000; ++k) {
 		u32 flb_status = aq_hw_read_reg(self,
@@ -260,9 +269,13 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self)
 		int err = 0;
 
 		hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
-		AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) &
-				HW_ATL_MPI_STATE_MSK) == MPI_DEINIT,
-			       10, 1000U);
+		err = readx_poll_timeout_atomic(hw_atl_utils_mpi_get_state,
+						self, val,
+						(val & HW_ATL_MPI_STATE_MSK) ==
+						 MPI_DEINIT,
+						10, 10000U);
+		if (err)
+			return err;
 	}
 
 	if (self->rbl_enabled)
@@ -275,16 +288,17 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a,
 				  u32 *p, u32 cnt)
 {
 	int err = 0;
+	u32 val;
 
-	AQ_HW_WAIT_FOR(hw_atl_reg_glb_cpu_sem_get(self,
-						  HW_ATL_FW_SM_RAM) == 1U,
-		       1U, 10000U);
+	err = readx_poll_timeout_atomic(hw_atl_sem_ram_get,
+					self, val, val == 1U,
+					1U, 10000U);
 
 	if (err < 0) {
 		bool is_locked;
 
 		hw_atl_reg_glb_cpu_sem_set(self, 1U, HW_ATL_FW_SM_RAM);
-		is_locked = hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM);
+		is_locked = hw_atl_sem_ram_get(self);
 		if (!is_locked) {
 			err = -ETIME;
 			goto err_exit;
@@ -297,13 +311,14 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a,
 		aq_hw_write_reg(self, HW_ATL_MIF_CMD, 0x00008000U);
 
 		if (IS_CHIP_FEATURE(REVISION_B1))
-			AQ_HW_WAIT_FOR(a != aq_hw_read_reg(self,
-							   HW_ATL_MIF_ADDR),
-				       1, 1000U);
+			err = readx_poll_timeout_atomic(hw_atl_utils_mif_addr_get,
+							self, val, val != a,
+							1U, 1000U);
 		else
-			AQ_HW_WAIT_FOR(!(0x100 & aq_hw_read_reg(self,
-							   HW_ATL_MIF_CMD)),
-				       1, 1000U);
+			err = readx_poll_timeout_atomic(hw_atl_utils_mif_cmd_get,
+							self, val,
+							!(val & 0x100),
+							1U, 1000U);
 
 		*(p++) = aq_hw_read_reg(self, HW_ATL_MIF_VAL);
 		a += 4;
@@ -318,10 +333,11 @@ err_exit:
 static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 					 u32 cnt)
 {
+	u32 val;
 	int err = 0;
 	bool is_locked;
 
-	is_locked = hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM);
+	is_locked = hw_atl_sem_ram_get(self);
 	if (!is_locked) {
 		err = -ETIME;
 		goto err_exit;
@@ -335,10 +351,11 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 					(0x80000000 | (0xFFFF & (offset * 4))));
 			hw_atl_mcp_up_force_intr_set(self, 1);
 			/* 1000 times by 10us = 10ms */
-			AQ_HW_WAIT_FOR((aq_hw_read_reg(self,
-						       0x32C) & 0xF0000000) !=
-				       0x80000000,
-				       10, 1000);
+			err = readx_poll_timeout_atomic(hw_atl_scrpad12_get,
+							self, val,
+							(val & 0xF0000000) ==
+							 0x80000000,
+							10U, 10000U);
 		}
 	} else {
 		u32 offset = 0;
@@ -349,8 +366,10 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p,
 			aq_hw_write_reg(self, 0x20C, p[offset]);
 			aq_hw_write_reg(self, 0x200, 0xC000);
 
-			AQ_HW_WAIT_FOR((aq_hw_read_reg(self, 0x200U) &
-					0x100) == 0, 10, 1000);
+			err = readx_poll_timeout_atomic(hw_atl_utils_mif_cmd_get,
+							self, val,
+							(val & 0x100) == 0,
+							1000U, 10000U);
 		}
 	}
 
@@ -393,15 +412,14 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self,
 	hw_atl_reg_glb_cpu_scratch_scp_set(self, 0x00000000U, 25U);
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(0U != (self->mbox_addr =
-			      aq_hw_read_reg(self, 0x360U)), 1000U, 10U);
+	err = readx_poll_timeout_atomic(hw_atl_scrpad25_get,
+					self, self->mbox_addr,
+					self->mbox_addr != 0U,
+					1000U, 10000U);
 
 	return err;
 }
 
-#define HW_ATL_RPC_CONTROL_ADR 0x0338U
-#define HW_ATL_RPC_STATE_ADR   0x033CU
-
 struct aq_hw_atl_utils_fw_rpc_tid_s {
 	union {
 		u32 val;
@@ -450,12 +468,10 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 
 		self->rpc_tid = sw.tid;
 
-		AQ_HW_WAIT_FOR(sw.tid ==
-			       (fw.val =
-				aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR),
-				fw.tid), 1000U, 100U);
-		if (err < 0)
-			goto err_exit;
+		err = readx_poll_timeout_atomic(hw_atl_utils_rpc_state_get,
+						self, fw.val,
+						sw.tid == fw.tid,
+						1000U, 100000U);
 
 		if (fw.len == 0xFFFFU) {
 			err = hw_atl_utils_fw_rpc_call(self, sw.len);
@@ -463,8 +479,6 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self,
 				goto err_exit;
 		}
 	} while (sw.tid != fw.tid || 0xFFFFU == fw.len);
-	if (err < 0)
-		goto err_exit;
 
 	if (rpc) {
 		if (fw.len) {
@@ -561,10 +575,11 @@ static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
 
 		transaction_id = mbox.transaction_id;
 
-		AQ_HW_WAIT_FOR(transaction_id !=
-			       (hw_atl_utils_mpi_read_mbox(self, &mbox),
-				mbox.transaction_id),
-			       1000U, 100U);
+		err = readx_poll_timeout_atomic(hw_atl_utils_get_mpi_mbox_tid,
+						self, mbox.transaction_id,
+						transaction_id !=
+						mbox.transaction_id,
+						1000U, 100000U);
 		if (err < 0)
 			goto err_exit;
 	}
@@ -587,7 +602,7 @@ err_exit:
 
 int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
 {
-	u32 cp0x036C = aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR);
+	u32 cp0x036C = hw_atl_utils_mpi_get_state(self);
 	u32 link_speed_mask = cp0x036C >> HW_ATL_MPI_SPEED_SHIFT;
 	struct aq_hw_link_status_s *link_status = &self->aq_link_status;
 
@@ -907,6 +922,35 @@ err_exit:
 	return err;
 }
 
+static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self)
+{
+	struct hw_atl_utils_mbox_header mbox;
+
+	hw_atl_utils_mpi_read_mbox(self, &mbox);
+
+	return mbox.transaction_id;
+}
+
+static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR);
+}
+
+static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MIF_CMD);
+}
+
+static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_MIF_ADDR);
+}
+
+static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR);
+}
+
 const struct aq_fw_ops aq_fw_1x_ops = {
 	.init = hw_atl_utils_mpi_create,
 	.deinit = hw_atl_fw1x_deinit,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index 3613fca64b58..48278e333462 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -240,6 +240,64 @@ struct __packed offload_info {
 	u8 buf[0];
 };
 
+enum hw_atl_rx_action_with_traffic {
+	HW_ATL_RX_DISCARD,
+	HW_ATL_RX_HOST,
+};
+
+struct aq_rx_filter_vlan {
+	u8 enable;
+	u8 location;
+	u16 vlan_id;
+	u8 queue;
+};
+
+struct aq_rx_filter_l2 {
+	s8 queue;
+	u8 location;
+	u8 user_priority_en;
+	u8 user_priority;
+	u16 ethertype;
+};
+
+struct aq_rx_filter_l3l4 {
+	u32 cmd;
+	u8 location;
+	u32 ip_dst[4];
+	u32 ip_src[4];
+	u16 p_dst;
+	u16 p_src;
+	u8 is_ipv6;
+};
+
+enum hw_atl_rx_protocol_value_l3l4 {
+	HW_ATL_RX_TCP,
+	HW_ATL_RX_UDP,
+	HW_ATL_RX_SCTP,
+	HW_ATL_RX_ICMP
+};
+
+enum hw_atl_rx_ctrl_registers_l3l4 {
+	HW_ATL_RX_ENABLE_MNGMNT_QUEUE_L3L4 = BIT(22),
+	HW_ATL_RX_ENABLE_QUEUE_L3L4        = BIT(23),
+	HW_ATL_RX_ENABLE_ARP_FLTR_L3       = BIT(24),
+	HW_ATL_RX_ENABLE_CMP_PROT_L4       = BIT(25),
+	HW_ATL_RX_ENABLE_CMP_DEST_PORT_L4  = BIT(26),
+	HW_ATL_RX_ENABLE_CMP_SRC_PORT_L4   = BIT(27),
+	HW_ATL_RX_ENABLE_CMP_DEST_ADDR_L3  = BIT(28),
+	HW_ATL_RX_ENABLE_CMP_SRC_ADDR_L3   = BIT(29),
+	HW_ATL_RX_ENABLE_L3_IPV6           = BIT(30),
+	HW_ATL_RX_ENABLE_FLTR_L3L4         = BIT(31)
+};
+
+#define HW_ATL_RX_QUEUE_FL3L4_SHIFT       8U
+#define HW_ATL_RX_ACTION_FL3F4_SHIFT      16U
+
+#define HW_ATL_RX_CNT_REG_ADDR_IPV6       4U
+
+#define HW_ATL_GET_REG_LOCATION_FL3L4(location) \
+	((location) - AQ_RX_FIRST_LOC_FL3L4)
+
 #define HAL_ATLANTIC_UTILS_CHIP_MIPS         0x00000001U
 #define HAL_ATLANTIC_UTILS_CHIP_TPO2         0x00000002U
 #define HAL_ATLANTIC_UTILS_CHIP_RPF2         0x00000004U
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 7de3220d9cab..fe6c5658e016 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -20,15 +20,14 @@
 #include "hw_atl_utils.h"
 #include "hw_atl_llh.h"
 
-#define HW_ATL_FW2X_MPI_EFUSE_ADDR	0x364
-#define HW_ATL_FW2X_MPI_MBOX_ADDR	0x360
 #define HW_ATL_FW2X_MPI_RPC_ADDR        0x334
 
+#define HW_ATL_FW2X_MPI_MBOX_ADDR       0x360
+#define HW_ATL_FW2X_MPI_EFUSE_ADDR	0x364
 #define HW_ATL_FW2X_MPI_CONTROL_ADDR	0x368
 #define HW_ATL_FW2X_MPI_CONTROL2_ADDR	0x36C
-
 #define HW_ATL_FW2X_MPI_STATE_ADDR	0x370
-#define HW_ATL_FW2X_MPI_STATE2_ADDR	0x374
+#define HW_ATL_FW2X_MPI_STATE2_ADDR     0x374
 
 #define HW_ATL_FW2X_CAP_PAUSE            BIT(CAPS_HI_PAUSE)
 #define HW_ATL_FW2X_CAP_ASYM_PAUSE       BIT(CAPS_HI_ASYMMETRIC_PAUSE)
@@ -72,17 +71,24 @@ static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed);
 static int aq_fw2x_set_state(struct aq_hw_s *self,
 			     enum hal_atl_utils_fw_state_e state);
 
+static u32 aq_fw2x_mbox_get(struct aq_hw_s *self);
+static u32 aq_fw2x_rpc_get(struct aq_hw_s *self);
+static u32 aq_fw2x_state2_get(struct aq_hw_s *self);
+
 static int aq_fw2x_init(struct aq_hw_s *self)
 {
 	int err = 0;
 
 	/* check 10 times by 1ms */
-	AQ_HW_WAIT_FOR(0U != (self->mbox_addr =
-		       aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR)),
-		       1000U, 10U);
-	AQ_HW_WAIT_FOR(0U != (self->rpc_addr =
-		       aq_hw_read_reg(self, HW_ATL_FW2X_MPI_RPC_ADDR)),
-		       1000U, 100U);
+	err = readx_poll_timeout_atomic(aq_fw2x_mbox_get,
+					self, self->mbox_addr,
+					self->mbox_addr != 0U,
+					1000U, 10000U);
+
+	err = readx_poll_timeout_atomic(aq_fw2x_rpc_get,
+					self, self->rpc_addr,
+					self->rpc_addr != 0U,
+					1000U, 100000U);
 
 	return err;
 }
@@ -286,16 +292,18 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self)
 	int err = 0;
 	u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
 	u32 orig_stats_val = mpi_opts & BIT(CAPS_HI_STATISTICS);
+	u32 stats_val;
 
 	/* Toggle statistics bit for FW to update */
 	mpi_opts = mpi_opts ^ BIT(CAPS_HI_STATISTICS);
 	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
 
 	/* Wait FW to report back */
-	AQ_HW_WAIT_FOR(orig_stats_val !=
-		       (aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) &
-			BIT(CAPS_HI_STATISTICS)),
-		       1U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
+					self, stats_val,
+					orig_stats_val != (stats_val &
+					BIT(CAPS_HI_STATISTICS)),
+					1U, 10000U);
 	if (err)
 		return err;
 
@@ -309,6 +317,7 @@ static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac)
 	unsigned int rpc_size = 0U;
 	u32 mpi_opts;
 	int err = 0;
+	u32 val;
 
 	rpc_size = sizeof(rpc->msg_id) + sizeof(*cfg);
 
@@ -337,8 +346,10 @@ static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac)
 	mpi_opts |= HW_ATL_FW2X_CTRL_SLEEP_PROXY;
 	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
 
-	AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) &
-			HW_ATL_FW2X_CTRL_SLEEP_PROXY), 1U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
+					self, val,
+					val & HW_ATL_FW2X_CTRL_SLEEP_PROXY,
+					1U, 10000U);
 
 err_exit:
 	return err;
@@ -350,6 +361,7 @@ static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac)
 	struct fw2x_msg_wol *msg = NULL;
 	u32 mpi_opts;
 	int err = 0;
+	u32 val;
 
 	err = hw_atl_utils_fw_rpc_wait(self, &rpc);
 	if (err < 0)
@@ -374,8 +386,9 @@ static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac)
 	mpi_opts |= HW_ATL_FW2X_CTRL_WOL;
 	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
 
-	AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) &
-			HW_ATL_FW2X_CTRL_WOL), 1U, 10000U);
+	err = readx_poll_timeout_atomic(aq_fw2x_state2_get,
+					self, val, val & HW_ATL_FW2X_CTRL_WOL,
+					1U, 10000U);
 
 err_exit:
 	return err;
@@ -425,7 +438,7 @@ static int aq_fw2x_get_eee_rate(struct aq_hw_s *self, u32 *rate,
 
 	*supported_rates = fw2x_to_eee_mask(caps_hi);
 
-	mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR);
+	mpi_state = aq_fw2x_state2_get(self);
 	*rate = fw2x_to_eee_mask(mpi_state);
 
 	return err;
@@ -455,7 +468,7 @@ static int aq_fw2x_set_flow_control(struct aq_hw_s *self)
 
 static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode)
 {
-	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR);
+	u32 mpi_state = aq_fw2x_state2_get(self);
 
 	if (mpi_state & HW_ATL_FW2X_CAP_PAUSE)
 		if (mpi_state & HW_ATL_FW2X_CAP_ASYM_PAUSE)
@@ -471,6 +484,21 @@ static u32 aq_fw2x_get_flow_control(struct aq_hw_s *self, u32 *fcmode)
 	return 0;
 }
 
+static u32 aq_fw2x_mbox_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR);
+}
+
+static u32 aq_fw2x_rpc_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_FW2X_MPI_RPC_ADDR);
+}
+
+static u32 aq_fw2x_state2_get(struct aq_hw_s *self)
+{
+	return aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR);
+}
+
 const struct aq_fw_ops aq_fw_2x_ops = {
 	.init = aq_fw2x_init,
 	.deinit = aq_fw2x_deinit,
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index bd277b0dc615..ff3d68532f5f 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -148,7 +148,7 @@ static void arc_emac_tx_clean(struct net_device *ndev)
 				 dma_unmap_len(tx_buff, len), DMA_TO_DEVICE);
 
 		/* return the sk_buff to system */
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 
 		txbd->data = 0;
 		txbd->info = 0;
@@ -432,7 +432,8 @@ static int arc_emac_open(struct net_device *ndev)
 	phy_dev->autoneg = AUTONEG_ENABLE;
 	phy_dev->speed = 0;
 	phy_dev->duplex = 0;
-	phy_dev->advertising &= phy_dev->supported;
+	linkmode_and(phy_dev->advertising, phy_dev->advertising,
+		     phy_dev->supported);
 
 	priv->last_rx_bd = 0;
 
diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index c131cfc1b79d..e3538ba7d0e7 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -660,10 +660,9 @@ static int alx_alloc_rings(struct alx_priv *alx)
 			    alx->num_txq +
 			    sizeof(struct alx_rrd) * alx->rx_ringsz +
 			    sizeof(struct alx_rfd) * alx->rx_ringsz;
-	alx->descmem.virt = dma_zalloc_coherent(&alx->hw.pdev->dev,
-						alx->descmem.size,
-						&alx->descmem.dma,
-						GFP_KERNEL);
+	alx->descmem.virt = dma_alloc_coherent(&alx->hw.pdev->dev,
+					       alx->descmem.size,
+					       &alx->descmem.dma, GFP_KERNEL);
 	if (!alx->descmem.virt)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 7087b88550db..0f1eb1981469 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -1019,8 +1019,8 @@ static int atl1c_setup_ring_resources(struct atl1c_adapter *adapter)
 		sizeof(struct atl1c_recv_ret_status) * rx_desc_count +
 		8 * 4;
 
-	ring_header->desc = dma_zalloc_coherent(&pdev->dev, ring_header->size,
-						&ring_header->dma, GFP_KERNEL);
+	ring_header->desc = dma_alloc_coherent(&pdev->dev, ring_header->size,
+					       &ring_header->dma, GFP_KERNEL);
 	if (unlikely(!ring_header->desc)) {
 		dev_err(&pdev->dev, "could not get memory for DMA buffer\n");
 		goto err_nomem;
@@ -1833,10 +1833,10 @@ rrs_checked:
 		atl1c_clean_rrd(rrd_ring, rrs, rfd_num);
 		if (rrs->word3 & (RRS_RX_ERR_SUM | RRS_802_3_LEN_ERR)) {
 			atl1c_clean_rfd(rfd_ring, rrs, rfd_num);
-				if (netif_msg_rx_err(adapter))
-					dev_warn(&pdev->dev,
-						"wrong packet! rrs word3 is %x\n",
-						rrs->word3);
+			if (netif_msg_rx_err(adapter))
+				dev_warn(&pdev->dev,
+					 "wrong packet! rrs word3 is %x\n",
+					 rrs->word3);
 			continue;
 		}
 
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 9dc6da039a6d..9dfe6a9431e6 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -473,7 +473,9 @@ static void atl1e_mdio_write(struct net_device *netdev, int phy_id,
 {
 	struct atl1e_adapter *adapter = netdev_priv(netdev);
 
-	atl1e_write_phy_reg(&adapter->hw, reg_num & MDIO_REG_ADDR_MASK, val);
+	if (atl1e_write_phy_reg(&adapter->hw,
+				reg_num & MDIO_REG_ADDR_MASK, val))
+		netdev_err(netdev, "write phy register failed\n");
 }
 
 static int atl1e_mii_ioctl(struct net_device *netdev,
@@ -1257,7 +1259,7 @@ static bool atl1e_clean_tx_irq(struct atl1e_adapter *adapter)
 		}
 
 		if (tx_buffer->skb) {
-			dev_kfree_skb_irq(tx_buffer->skb);
+			dev_consume_skb_irq(tx_buffer->skb);
 			tx_buffer->skb = NULL;
 		}
 
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 63edc5706c09..156fbc5601ca 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -1721,7 +1721,7 @@ static void atl1_inc_smb(struct atl1_adapter *adapter)
 	adapter->soft_stats.scc += smb->tx_1_col;
 	adapter->soft_stats.mcc += smb->tx_2_col;
 	adapter->soft_stats.latecol += smb->tx_late_col;
-	adapter->soft_stats.tx_underun += smb->tx_underrun;
+	adapter->soft_stats.tx_underrun += smb->tx_underrun;
 	adapter->soft_stats.tx_trunc += smb->tx_trunc;
 	adapter->soft_stats.tx_pause += smb->tx_pause;
 
@@ -2088,7 +2088,7 @@ static int atl1_intr_tx(struct atl1_adapter *adapter)
 		}
 
 		if (buffer_info->skb) {
-			dev_kfree_skb_irq(buffer_info->skb);
+			dev_consume_skb_irq(buffer_info->skb);
 			buffer_info->skb = NULL;
 		}
 
@@ -3179,7 +3179,7 @@ static struct atl1_stats atl1_gstrings_stats[] = {
 	{"tx_deferred_ok", ATL1_STAT(soft_stats.deffer)},
 	{"tx_single_coll_ok", ATL1_STAT(soft_stats.scc)},
 	{"tx_multi_coll_ok", ATL1_STAT(soft_stats.mcc)},
-	{"tx_underun", ATL1_STAT(soft_stats.tx_underun)},
+	{"tx_underrun", ATL1_STAT(soft_stats.tx_underrun)},
 	{"tx_trunc", ATL1_STAT(soft_stats.tx_trunc)},
 	{"tx_pause", ATL1_STAT(soft_stats.tx_pause)},
 	{"rx_pause", ATL1_STAT(soft_stats.rx_pause)},
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.h b/drivers/net/ethernet/atheros/atlx/atl1.h
index 34a58cd846a0..eacff19ea05b 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.h
+++ b/drivers/net/ethernet/atheros/atlx/atl1.h
@@ -681,7 +681,7 @@ struct atl1_sft_stats {
 	u64 scc;		/* packets TX after a single collision */
 	u64 mcc;		/* packets TX after multiple collisions */
 	u64 latecol;		/* TX packets w/ late collisions */
-	u64 tx_underun;		/* TX packets aborted due to TX FIFO underrun
+	u64 tx_underrun;	/* TX packets aborted due to TX FIFO underrun
 				 * or TRD FIFO underrun */
 	u64 tx_trunc;		/* TX packets truncated due to size > MTU */
 	u64 rx_pause;		/* num Pause packets received. */
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index bb41becb6609..98da0fa27192 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -553,7 +553,7 @@ static void atl2_intr_tx(struct atl2_adapter *adapter)
 			netdev->stats.tx_aborted_errors++;
 		if (txs->late_col)
 			netdev->stats.tx_window_errors++;
-		if (txs->underun)
+		if (txs->underrun)
 			netdev->stats.tx_fifo_errors++;
 	} while (1);
 
@@ -909,7 +909,7 @@ static netdev_tx_t atl2_xmit_frame(struct sk_buff *skb,
 		(adapter->txd_write_ptr >> 2));
 
 	mmiowb();
-	dev_kfree_skb_any(skb);
+	dev_consume_skb_any(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -1335,13 +1335,11 @@ static int atl2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *netdev;
 	struct atl2_adapter *adapter;
-	static int cards_found;
+	static int cards_found = 0;
 	unsigned long mmio_start;
 	int mmio_len;
 	int err;
 
-	cards_found = 0;
-
 	err = pci_enable_device(pdev);
 	if (err)
 		return err;
@@ -2946,7 +2944,7 @@ static int atl2_validate_option(int *value, struct atl2_option *opt)
 			if (*value == ent->i) {
 				if (ent->str[0] != '\0')
 					printk(KERN_INFO "%s\n", ent->str);
-			return 0;
+				return 0;
 			}
 		}
 		break;
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.h b/drivers/net/ethernet/atheros/atlx/atl2.h
index c64a6bdfa7ae..25ec84cb4853 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.h
+++ b/drivers/net/ethernet/atheros/atlx/atl2.h
@@ -260,7 +260,7 @@ struct tx_pkt_status {
 	unsigned multi_col:1;
 	unsigned late_col:1;
 	unsigned abort_col:1;
-	unsigned underun:1;	/* current packet is aborted
+	unsigned underrun:1;	/* current packet is aborted
 				 * due to txram underrun */
 	unsigned:3;		/* reserved */
 	unsigned update:1;	/* always 1'b1 in tx_status_buf */
diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index c1d3ee9baf7e..716bfbba59cf 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -194,7 +194,6 @@ config SYSTEMPORT
 config BNXT
 	tristate "Broadcom NetXtreme-C/E support"
 	depends on PCI
-	depends on MAY_USE_DEVLINK
 	select FW_LOADER
 	select LIBCRC32C
 	---help---
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index e445ab724827..97ab0dd25552 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -638,7 +638,7 @@ static void b44_tx(struct b44 *bp)
 		bytes_compl += skb->len;
 		pkts_compl++;
 
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 
 	netdev_completed_queue(bp->dev, pkts_compl, bytes_compl);
@@ -1012,7 +1012,7 @@ static netdev_tx_t b44_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 
 		skb_copy_from_linear_data(skb, skb_put(bounce_skb, len), len);
-		dev_kfree_skb_any(skb);
+		dev_consume_skb_any(skb);
 		skb = bounce_skb;
 	}
 
@@ -2248,6 +2248,7 @@ static void b44_adjust_link(struct net_device *dev)
 
 static int b44_register_phy_one(struct b44 *bp)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct mii_bus *mii_bus;
 	struct ssb_device *sdev = bp->sdev;
 	struct phy_device *phydev;
@@ -2303,11 +2304,12 @@ static int b44_register_phy_one(struct b44 *bp)
 	}
 
 	/* mask with MAC supported features */
-	phydev->supported &= (SUPPORTED_100baseT_Half |
-			      SUPPORTED_100baseT_Full |
-			      SUPPORTED_Autoneg |
-			      SUPPORTED_MII);
-	phydev->advertising = phydev->supported;
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	bp->old_link = 0;
 	bp->phy_addr = phydev->mdio.addr;
diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
index 6bae973d4dce..09cd188826b1 100644
--- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c
+++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c
@@ -936,7 +936,7 @@ static int bcm_enet_open(struct net_device *dev)
 
 	/* allocate rx dma ring */
 	size = priv->rx_ring_size * sizeof(struct bcm_enet_desc);
-	p = dma_zalloc_coherent(kdev, size, &priv->rx_desc_dma, GFP_KERNEL);
+	p = dma_alloc_coherent(kdev, size, &priv->rx_desc_dma, GFP_KERNEL);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out_freeirq_tx;
@@ -947,7 +947,7 @@ static int bcm_enet_open(struct net_device *dev)
 
 	/* allocate tx dma ring */
 	size = priv->tx_ring_size * sizeof(struct bcm_enet_desc);
-	p = dma_zalloc_coherent(kdev, size, &priv->tx_desc_dma, GFP_KERNEL);
+	p = dma_alloc_coherent(kdev, size, &priv->tx_desc_dma, GFP_KERNEL);
 	if (!p) {
 		ret = -ENOMEM;
 		goto out_free_rx_ring;
@@ -2120,7 +2120,7 @@ static int bcm_enetsw_open(struct net_device *dev)
 
 	/* allocate rx dma ring */
 	size = priv->rx_ring_size * sizeof(struct bcm_enet_desc);
-	p = dma_zalloc_coherent(kdev, size, &priv->rx_desc_dma, GFP_KERNEL);
+	p = dma_alloc_coherent(kdev, size, &priv->rx_desc_dma, GFP_KERNEL);
 	if (!p) {
 		dev_err(kdev, "cannot allocate rx ring %u\n", size);
 		ret = -ENOMEM;
@@ -2132,7 +2132,7 @@ static int bcm_enetsw_open(struct net_device *dev)
 
 	/* allocate tx dma ring */
 	size = priv->tx_ring_size * sizeof(struct bcm_enet_desc);
-	p = dma_zalloc_coherent(kdev, size, &priv->tx_desc_dma, GFP_KERNEL);
+	p = dma_alloc_coherent(kdev, size, &priv->tx_desc_dma, GFP_KERNEL);
 	if (!p) {
 		dev_err(kdev, "cannot allocate tx ring\n");
 		ret = -ENOMEM;
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 0e2d99c737e3..bc3ac369cbe3 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -134,6 +134,10 @@ static void bcm_sysport_set_rx_csum(struct net_device *dev,
 
 	priv->rx_chk_en = !!(wanted & NETIF_F_RXCSUM);
 	reg = rxchk_readl(priv, RXCHK_CONTROL);
+	/* Clear L2 header checks, which would prevent BPDUs
+	 * from being received.
+	 */
+	reg &= ~RXCHK_L2_HDR_DIS;
 	if (priv->rx_chk_en)
 		reg |= RXCHK_EN;
 	else
@@ -520,7 +524,6 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 				struct ethtool_wolinfo *wol)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
-	u32 reg;
 
 	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
@@ -528,11 +531,7 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 	if (!(priv->wolopts & WAKE_MAGICSECURE))
 		return;
 
-	/* Return the programmed SecureOn password */
-	reg = umac_readl(priv, UMAC_PSW_MS);
-	put_unaligned_be16(reg, &wol->sopass[0]);
-	reg = umac_readl(priv, UMAC_PSW_LS);
-	put_unaligned_be32(reg, &wol->sopass[2]);
+	memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass));
 }
 
 static int bcm_sysport_set_wol(struct net_device *dev,
@@ -548,13 +547,8 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 	if (wol->wolopts & ~supported)
 		return -EINVAL;
 
-	/* Program the SecureOn password */
-	if (wol->wolopts & WAKE_MAGICSECURE) {
-		umac_writel(priv, get_unaligned_be16(&wol->sopass[0]),
-			    UMAC_PSW_MS);
-		umac_writel(priv, get_unaligned_be32(&wol->sopass[2]),
-			    UMAC_PSW_LS);
-	}
+	if (wol->wolopts & WAKE_MAGICSECURE)
+		memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass));
 
 	/* Flag the device and relevant IRQ as wakeup capable */
 	if (wol->wolopts) {
@@ -1068,6 +1062,7 @@ static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
 
 static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 {
+	unsigned int index;
 	u32 reg;
 
 	/* Disable RXCHK, active filters and Broadcom tag matching */
@@ -1076,6 +1071,15 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 		 RXCHK_BRCM_TAG_MATCH_SHIFT | RXCHK_EN | RXCHK_BRCM_TAG_EN);
 	rxchk_writel(priv, reg, RXCHK_CONTROL);
 
+	/* Make sure we restore correct CID index in case HW lost
+	 * its context during deep idle state
+	 */
+	for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+		rxchk_writel(priv, priv->filters_loc[index] <<
+			     RXCHK_BRCM_TAG_CID_SHIFT, RXCHK_BRCM_TAG(index));
+		rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
+	}
+
 	/* Clear the MagicPacket detection logic */
 	mpd_enable_set(priv, false);
 
@@ -1496,8 +1500,8 @@ static int bcm_sysport_init_tx_ring(struct bcm_sysport_priv *priv,
 	/* We just need one DMA descriptor which is DMA-able, since writing to
 	 * the port will allocate a new descriptor in its internal linked-list
 	 */
-	p = dma_zalloc_coherent(kdev, sizeof(struct dma_desc), &ring->desc_dma,
-				GFP_KERNEL);
+	p = dma_alloc_coherent(kdev, sizeof(struct dma_desc), &ring->desc_dma,
+			       GFP_KERNEL);
 	if (!p) {
 		netif_err(priv, hw, priv->netdev, "DMA alloc failed\n");
 		return -ENOMEM;
@@ -2189,6 +2193,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 	rxchk_writel(priv, reg, RXCHK_BRCM_TAG(index));
 	rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
 
+	priv->filters_loc[index] = nfc->fs.location;
 	set_bit(index, priv->filters);
 
 	return 0;
@@ -2208,6 +2213,7 @@ static int bcm_sysport_rule_del(struct bcm_sysport_priv *priv,
 	 * be taken care of during suspend time by bcm_sysport_suspend_to_wol
 	 */
 	clear_bit(index, priv->filters);
+	priv->filters_loc[index] = 0;
 
 	return 0;
 }
@@ -2312,7 +2318,7 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 	struct bcm_sysport_priv *priv;
 	struct net_device *slave_dev;
 	unsigned int num_tx_queues;
-	unsigned int q, start, port;
+	unsigned int q, qp, port;
 	struct net_device *dev;
 
 	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
@@ -2351,20 +2357,61 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 
 	priv->per_port_num_tx_queues = num_tx_queues;
 
-	start = find_first_zero_bit(&priv->queue_bitmap, dev->num_tx_queues);
-	for (q = 0; q < num_tx_queues; q++) {
-		ring = &priv->tx_rings[q + start];
+	for (q = 0, qp = 0; q < dev->num_tx_queues && qp < num_tx_queues;
+	     q++) {
+		ring = &priv->tx_rings[q];
+
+		if (ring->inspect)
+			continue;
 
 		/* Just remember the mapping actual programming done
 		 * during bcm_sysport_init_tx_ring
 		 */
-		ring->switch_queue = q;
+		ring->switch_queue = qp;
 		ring->switch_port = port;
 		ring->inspect = true;
 		priv->ring_map[q + port * num_tx_queues] = ring;
+		qp++;
+	}
+
+	return 0;
+}
 
-		/* Set all queues as being used now */
-		set_bit(q + start, &priv->queue_bitmap);
+static int bcm_sysport_unmap_queues(struct notifier_block *nb,
+				    struct dsa_notifier_register_info *info)
+{
+	struct bcm_sysport_tx_ring *ring;
+	struct bcm_sysport_priv *priv;
+	struct net_device *slave_dev;
+	unsigned int num_tx_queues;
+	struct net_device *dev;
+	unsigned int q, port;
+
+	priv = container_of(nb, struct bcm_sysport_priv, dsa_notifier);
+	if (priv->netdev != info->master)
+		return 0;
+
+	dev = info->master;
+
+	if (dev->netdev_ops != &bcm_sysport_netdev_ops)
+		return 0;
+
+	port = info->port_number;
+	slave_dev = info->info.dev;
+
+	num_tx_queues = slave_dev->real_num_tx_queues;
+
+	for (q = 0; q < dev->num_tx_queues; q++) {
+		ring = &priv->tx_rings[q];
+
+		if (ring->switch_port != port)
+			continue;
+
+		if (!ring->inspect)
+			continue;
+
+		ring->inspect = false;
+		priv->ring_map[q + port * num_tx_queues] = NULL;
 	}
 
 	return 0;
@@ -2373,14 +2420,18 @@ static int bcm_sysport_map_queues(struct notifier_block *nb,
 static int bcm_sysport_dsa_notifier(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
-	struct dsa_notifier_register_info *info;
-
-	if (event != DSA_PORT_REGISTER)
-		return NOTIFY_DONE;
+	int ret = NOTIFY_DONE;
 
-	info = ptr;
+	switch (event) {
+	case DSA_PORT_REGISTER:
+		ret = bcm_sysport_map_queues(nb, ptr);
+		break;
+	case DSA_PORT_UNREGISTER:
+		ret = bcm_sysport_unmap_queues(nb, ptr);
+		break;
+	}
 
-	return notifier_from_errno(bcm_sysport_map_queues(nb, info));
+	return notifier_from_errno(ret);
 }
 
 #define REV_FMT	"v%2x.%02x"
@@ -2592,13 +2643,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	unsigned int index, i = 0;
 	u32 reg;
 
-	/* Password has already been programmed */
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
 		reg |= MPD_EN;
 	reg &= ~PSW_EN;
-	if (priv->wolopts & WAKE_MAGICSECURE)
+	if (priv->wolopts & WAKE_MAGICSECURE) {
+		/* Program the SecureOn password */
+		umac_writel(priv, get_unaligned_be16(&priv->sopass[0]),
+			    UMAC_PSW_MS);
+		umac_writel(priv, get_unaligned_be32(&priv->sopass[2]),
+			    UMAC_PSW_LS);
 		reg |= PSW_EN;
+	}
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
 
 	if (priv->wolopts & WAKE_FILTER) {
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index a7a230884a87..0b192fea9c5d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -12,6 +12,7 @@
 #define __BCM_SYSPORT_H
 
 #include <linux/bitmap.h>
+#include <linux/ethtool.h>
 #include <linux/if_vlan.h>
 #include <linux/net_dim.h>
 
@@ -778,6 +779,7 @@ struct bcm_sysport_priv {
 	unsigned int		crc_fwd:1;
 	u16			rev;
 	u32			wolopts;
+	u8			sopass[SOPASS_MAX];
 	unsigned int		wol_irq_disabled:1;
 
 	/* MIB related fields */
@@ -786,6 +788,7 @@ struct bcm_sysport_priv {
 	/* Ethtool */
 	u32			msg_enable;
 	DECLARE_BITMAP(filters, RXCHK_BRCM_TAG_MAX);
+	u32			filters_loc[RXCHK_BRCM_TAG_MAX];
 
 	struct bcm_sysport_stats64	stats64;
 
@@ -795,7 +798,6 @@ struct bcm_sysport_priv {
 	/* map information between switch port queues and local queues */
 	struct notifier_block	dsa_notifier;
 	unsigned int		per_port_num_tx_queues;
-	unsigned long		queue_bitmap;
 	struct bcm_sysport_tx_ring *ring_map[DSA_MAX_PORTS * 8];
 
 };
diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index cabc8e49ad24..4632dd5dbad1 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -634,9 +634,9 @@ static int bgmac_dma_alloc(struct bgmac *bgmac)
 
 		/* Alloc ring of descriptors */
 		size = BGMAC_TX_RING_SLOTS * sizeof(struct bgmac_dma_desc);
-		ring->cpu_base = dma_zalloc_coherent(dma_dev, size,
-						     &ring->dma_base,
-						     GFP_KERNEL);
+		ring->cpu_base = dma_alloc_coherent(dma_dev, size,
+						    &ring->dma_base,
+						    GFP_KERNEL);
 		if (!ring->cpu_base) {
 			dev_err(bgmac->dev, "Allocation of TX ring 0x%X failed\n",
 				ring->mmio_base);
@@ -659,9 +659,9 @@ static int bgmac_dma_alloc(struct bgmac *bgmac)
 
 		/* Alloc ring of descriptors */
 		size = BGMAC_RX_RING_SLOTS * sizeof(struct bgmac_dma_desc);
-		ring->cpu_base = dma_zalloc_coherent(dma_dev, size,
-						     &ring->dma_base,
-						     GFP_KERNEL);
+		ring->cpu_base = dma_alloc_coherent(dma_dev, size,
+						    &ring->dma_base,
+						    GFP_KERNEL);
 		if (!ring->cpu_base) {
 			dev_err(bgmac->dev, "Allocation of RX ring 0x%X failed\n",
 				ring->mmio_base);
@@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac)
 	struct phy_device *phy_dev;
 	int err;
 
-	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL);
+	phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 	if (!phy_dev || IS_ERR(phy_dev)) {
 		dev_err(bgmac->dev, "Failed to register fixed PHY device\n");
 		return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index bbb247116045..d63371d70bce 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -844,8 +844,8 @@ bnx2_alloc_stats_blk(struct net_device *dev)
 						 BNX2_SBLK_MSIX_ALIGN_SIZE);
 	bp->status_stats_size = status_blk_size +
 				sizeof(struct statistics_block);
-	status_blk = dma_zalloc_coherent(&bp->pdev->dev, bp->status_stats_size,
-					 &bp->status_blk_mapping, GFP_KERNEL);
+	status_blk = dma_alloc_coherent(&bp->pdev->dev, bp->status_stats_size,
+					&bp->status_blk_mapping, GFP_KERNEL);
 	if (!status_blk)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index 5cd3135dfe30..6026b53137aa 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -32,7 +32,7 @@
  * (you will need to reboot afterwards) */
 /* #define BNX2X_STOP_ON_ERROR */
 
-#define DRV_MODULE_VERSION      "1.712.30-0"
+#define DRV_MODULE_VERSION      "1.713.36-0"
 #define DRV_MODULE_RELDATE      "2014/02/10"
 #define BNX2X_BC_VER            0x040200
 
@@ -2081,7 +2081,7 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id,
 			    bool is_pf);
 
 #define BNX2X_ILT_ZALLOC(x, y, size)					\
-	x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL)
+	x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL)
 
 #define BNX2X_ILT_FREE(x, y, size) \
 	do { \
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 142bc11b9fbb..2462e7aa0c5d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -52,7 +52,7 @@ extern int bnx2x_num_queues;
 
 #define BNX2X_PCI_ALLOC(y, size)					\
 ({									\
-	void *x = dma_zalloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
+	void *x = dma_alloc_coherent(&bp->pdev->dev, size, y, GFP_KERNEL); \
 	if (x)								\
 		DP(NETIF_MSG_HW,					\
 		   "BNX2X_PCI_ALLOC: Physical %Lx Virtual %p\n",	\
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index a4a90b6cdb46..749d0ef44371 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1105,11 +1105,39 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 			      struct ethtool_drvinfo *info)
 {
 	struct bnx2x *bp = netdev_priv(dev);
+	char version[ETHTOOL_FWVERS_LEN];
+	int ext_dev_info_offset;
+	u32 mbi;
 
 	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 
-	bnx2x_fill_fw_str(bp, info->fw_version, sizeof(info->fw_version));
+	memset(version, 0, sizeof(version));
+	snprintf(version, ETHTOOL_FWVERS_LEN, " storm %d.%d.%d.%d",
+		 BCM_5710_FW_MAJOR_VERSION, BCM_5710_FW_MINOR_VERSION,
+		 BCM_5710_FW_REVISION_VERSION, BCM_5710_FW_ENGINEERING_VERSION);
+	strlcat(info->version, version, sizeof(info->version));
+
+	if (SHMEM2_HAS(bp, extended_dev_info_shared_addr)) {
+		ext_dev_info_offset = SHMEM2_RD(bp,
+						extended_dev_info_shared_addr);
+		mbi = REG_RD(bp, ext_dev_info_offset +
+			     offsetof(struct extended_dev_info_shared_cfg,
+				      mbi_version));
+		if (mbi) {
+			memset(version, 0, sizeof(version));
+			snprintf(version, ETHTOOL_FWVERS_LEN, "mbi %d.%d.%d ",
+				 (mbi & 0xff000000) >> 24,
+				 (mbi & 0x00ff0000) >> 16,
+				 (mbi & 0x0000ff00) >> 8);
+			strlcpy(info->fw_version, version,
+				sizeof(info->fw_version));
+		}
+	}
+
+	memset(version, 0, sizeof(version));
+	bnx2x_fill_fw_str(bp, version, ETHTOOL_FWVERS_LEN);
+	strlcat(info->fw_version, version, sizeof(info->fw_version));
 
 	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index f8b810313094..d9057c8bbeef 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -1140,6 +1140,11 @@ struct shm_dev_info {				/* size */
 
 };
 
+struct extended_dev_info_shared_cfg {
+	u32 reserved[18];
+	u32 mbi_version;
+	u32 mbi_date;
+};
 
 #if !defined(__LITTLE_ENDIAN) && !defined(__BIG_ENDIAN)
 	#error "Missing either LITTLE_ENDIAN or BIG_ENDIAN definition."
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
index 46ee2c01f4c5..066765fbef06 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_init.h
@@ -449,7 +449,7 @@ static inline void bnx2x_init_fw_wrr(const struct cmng_init_input *input_data,
 				ccd[cos] =
 				    (u32)input_data->cos_min_rate[cos] * 100 *
 				    (T_FAIR_COEF / (8 * 100 * cosWeightSum));
-				 if (ccd[cos] < pdata->fair_vars.fair_threshold
+				if (ccd[cos] < pdata->fair_vars.fair_threshold
 						+ MIN_ABOVE_THRESH) {
 					ccd[cos] =
 					    pdata->fair_vars.fair_threshold +
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 98d4c5a3ff21..d581d0ae6584 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -837,49 +837,45 @@ static int bnx2x_ets_e3b0_set_cos_bw(struct bnx2x *bp,
 
 	switch (cos_entry) {
 	case 0:
-	    nig_reg_adress_crd_weight =
-		 (port) ? NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_0 :
-		     NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_0;
-	     pbf_reg_adress_crd_weight = (port) ?
-		 PBF_REG_COS0_WEIGHT_P1 : PBF_REG_COS0_WEIGHT_P0;
-	     break;
+		nig_reg_adress_crd_weight =
+			(port) ? NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_0 :
+			NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_0;
+		pbf_reg_adress_crd_weight = (port) ?
+		    PBF_REG_COS0_WEIGHT_P1 : PBF_REG_COS0_WEIGHT_P0;
+		break;
 	case 1:
-	     nig_reg_adress_crd_weight = (port) ?
-		 NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_1 :
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_1;
-	     pbf_reg_adress_crd_weight = (port) ?
-		 PBF_REG_COS1_WEIGHT_P1 : PBF_REG_COS1_WEIGHT_P0;
-	     break;
+		nig_reg_adress_crd_weight = (port) ?
+			NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_1 :
+			NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_1;
+		pbf_reg_adress_crd_weight = (port) ?
+			PBF_REG_COS1_WEIGHT_P1 : PBF_REG_COS1_WEIGHT_P0;
+		break;
 	case 2:
-	     nig_reg_adress_crd_weight = (port) ?
-		 NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_2 :
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_2;
+		nig_reg_adress_crd_weight = (port) ?
+			NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_2 :
+			NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_2;
 
-		 pbf_reg_adress_crd_weight = (port) ?
-		     PBF_REG_COS2_WEIGHT_P1 : PBF_REG_COS2_WEIGHT_P0;
-	     break;
+		pbf_reg_adress_crd_weight = (port) ?
+			PBF_REG_COS2_WEIGHT_P1 : PBF_REG_COS2_WEIGHT_P0;
+		break;
 	case 3:
-	    if (port)
+		if (port)
 			return -EINVAL;
-	     nig_reg_adress_crd_weight =
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_3;
-	     pbf_reg_adress_crd_weight =
-		 PBF_REG_COS3_WEIGHT_P0;
-	     break;
+		nig_reg_adress_crd_weight = NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_3;
+		pbf_reg_adress_crd_weight = PBF_REG_COS3_WEIGHT_P0;
+		break;
 	case 4:
-	    if (port)
-		return -EINVAL;
-	     nig_reg_adress_crd_weight =
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_4;
-	     pbf_reg_adress_crd_weight = PBF_REG_COS4_WEIGHT_P0;
-	     break;
+		if (port)
+			return -EINVAL;
+		nig_reg_adress_crd_weight = NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_4;
+		pbf_reg_adress_crd_weight = PBF_REG_COS4_WEIGHT_P0;
+		break;
 	case 5:
-	    if (port)
-		return -EINVAL;
-	     nig_reg_adress_crd_weight =
-		 NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_5;
-	     pbf_reg_adress_crd_weight = PBF_REG_COS5_WEIGHT_P0;
-	     break;
+		if (port)
+			return -EINVAL;
+		nig_reg_adress_crd_weight = NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_5;
+		pbf_reg_adress_crd_weight = PBF_REG_COS5_WEIGHT_P0;
+		break;
 	}
 
 	REG_WR(bp, nig_reg_adress_crd_weight, cos_bw_nig);
@@ -966,7 +962,7 @@ static int bnx2x_ets_e3b0_sp_pri_to_cos_set(const struct link_params *params,
 	if (pri >= max_num_of_cos) {
 		DP(NETIF_MSG_LINK, "bnx2x_ets_e3b0_sp_pri_to_cos_set invalid "
 		   "parameter Illegal strict priority\n");
-	    return -EINVAL;
+		return -EINVAL;
 	}
 
 	if (sp_pri_to_cos[pri] != DCBX_INVALID_COS) {
@@ -1845,28 +1841,28 @@ static int bnx2x_emac_enable(struct link_params *params,
 	bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE,
 		      EMAC_TX_MODE_RESET);
 
-		/* pause enable/disable */
-		bnx2x_bits_dis(bp, emac_base + EMAC_REG_EMAC_RX_MODE,
-			       EMAC_RX_MODE_FLOW_EN);
+	/* pause enable/disable */
+	bnx2x_bits_dis(bp, emac_base + EMAC_REG_EMAC_RX_MODE,
+		       EMAC_RX_MODE_FLOW_EN);
 
-		bnx2x_bits_dis(bp,  emac_base + EMAC_REG_EMAC_TX_MODE,
-			       (EMAC_TX_MODE_EXT_PAUSE_EN |
-				EMAC_TX_MODE_FLOW_EN));
-		if (!(params->feature_config_flags &
-		      FEATURE_CONFIG_PFC_ENABLED)) {
-			if (vars->flow_ctrl & BNX2X_FLOW_CTRL_RX)
-				bnx2x_bits_en(bp, emac_base +
-					      EMAC_REG_EMAC_RX_MODE,
-					      EMAC_RX_MODE_FLOW_EN);
-
-			if (vars->flow_ctrl & BNX2X_FLOW_CTRL_TX)
-				bnx2x_bits_en(bp, emac_base +
-					      EMAC_REG_EMAC_TX_MODE,
-					      (EMAC_TX_MODE_EXT_PAUSE_EN |
-					       EMAC_TX_MODE_FLOW_EN));
-		} else
-			bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE,
-				      EMAC_TX_MODE_FLOW_EN);
+	bnx2x_bits_dis(bp,  emac_base + EMAC_REG_EMAC_TX_MODE,
+		       (EMAC_TX_MODE_EXT_PAUSE_EN |
+			EMAC_TX_MODE_FLOW_EN));
+	if (!(params->feature_config_flags &
+	      FEATURE_CONFIG_PFC_ENABLED)) {
+		if (vars->flow_ctrl & BNX2X_FLOW_CTRL_RX)
+			bnx2x_bits_en(bp, emac_base +
+				      EMAC_REG_EMAC_RX_MODE,
+				      EMAC_RX_MODE_FLOW_EN);
+
+		if (vars->flow_ctrl & BNX2X_FLOW_CTRL_TX)
+			bnx2x_bits_en(bp, emac_base +
+				      EMAC_REG_EMAC_TX_MODE,
+				      (EMAC_TX_MODE_EXT_PAUSE_EN |
+				       EMAC_TX_MODE_FLOW_EN));
+	} else
+		bnx2x_bits_en(bp, emac_base + EMAC_REG_EMAC_TX_MODE,
+			      EMAC_TX_MODE_FLOW_EN);
 
 	/* KEEP_VLAN_TAG, promiscuous */
 	val = REG_RD(bp, emac_base + EMAC_REG_EMAC_RX_MODE);
@@ -6339,7 +6335,7 @@ int bnx2x_set_led(struct link_params *params,
 		 */
 		if (!vars->link_up)
 			break;
-		/* else: fall through */
+		/* fall through */
 	case LED_MODE_ON:
 		if (((params->phy[EXT_PHY1].type ==
 			  PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) ||
@@ -6478,9 +6474,9 @@ int bnx2x_test_link(struct link_params *params, struct link_vars *vars,
 			  MDIO_REG_BANK_GP_STATUS,
 			  MDIO_GP_STATUS_TOP_AN_STATUS1,
 			  &gp_status);
-	/* Link is up only if both local phy and external phy are up */
-	if (!(gp_status & MDIO_GP_STATUS_TOP_AN_STATUS1_LINK_STATUS))
-		return -ESRCH;
+		/* Link is up only if both local phy and external phy are up */
+		if (!(gp_status & MDIO_GP_STATUS_TOP_AN_STATUS1_LINK_STATUS))
+			return -ESRCH;
 	}
 	/* In XGXS loopback mode, do not check external PHY */
 	if (params->loopback_mode == LOOPBACK_XGXS)
@@ -7293,8 +7289,8 @@ static int bnx2x_8073_xaui_wa(struct bnx2x *bp, struct bnx2x_phy *phy)
 					DP(NETIF_MSG_LINK,
 					  "XAUI workaround has completed\n");
 					return 0;
-				 }
-				 usleep_range(3000, 6000);
+				}
+				usleep_range(3000, 6000);
 			}
 			break;
 		}
@@ -12675,39 +12671,39 @@ static void bnx2x_init_bmac_loopback(struct link_params *params,
 				     struct link_vars *vars)
 {
 	struct bnx2x *bp = params->bp;
-		vars->link_up = 1;
-		vars->line_speed = SPEED_10000;
-		vars->duplex = DUPLEX_FULL;
-		vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
-		vars->mac_type = MAC_TYPE_BMAC;
+	vars->link_up = 1;
+	vars->line_speed = SPEED_10000;
+	vars->duplex = DUPLEX_FULL;
+	vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
+	vars->mac_type = MAC_TYPE_BMAC;
 
-		vars->phy_flags = PHY_XGXS_FLAG;
+	vars->phy_flags = PHY_XGXS_FLAG;
 
-		bnx2x_xgxs_deassert(params);
+	bnx2x_xgxs_deassert(params);
 
-		/* Set bmac loopback */
-		bnx2x_bmac_enable(params, vars, 1, 1);
+	/* Set bmac loopback */
+	bnx2x_bmac_enable(params, vars, 1, 1);
 
-		REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port * 4, 0);
 }
 
 static void bnx2x_init_emac_loopback(struct link_params *params,
 				     struct link_vars *vars)
 {
 	struct bnx2x *bp = params->bp;
-		vars->link_up = 1;
-		vars->line_speed = SPEED_1000;
-		vars->duplex = DUPLEX_FULL;
-		vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
-		vars->mac_type = MAC_TYPE_EMAC;
+	vars->link_up = 1;
+	vars->line_speed = SPEED_1000;
+	vars->duplex = DUPLEX_FULL;
+	vars->flow_ctrl = BNX2X_FLOW_CTRL_NONE;
+	vars->mac_type = MAC_TYPE_EMAC;
 
-		vars->phy_flags = PHY_XGXS_FLAG;
+	vars->phy_flags = PHY_XGXS_FLAG;
 
-		bnx2x_xgxs_deassert(params);
-		/* Set bmac loopback */
-		bnx2x_emac_enable(params, vars, 1);
-		bnx2x_emac_program(params, vars);
-		REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port*4, 0);
+	bnx2x_xgxs_deassert(params);
+	/* Set bmac loopback */
+	bnx2x_emac_enable(params, vars, 1);
+	bnx2x_emac_program(params, vars);
+	REG_WR(bp, NIG_REG_EGRESS_DRAIN0_MODE + params->port * 4, 0);
 }
 
 static void bnx2x_init_xmac_loopback(struct link_params *params,
@@ -13073,12 +13069,12 @@ int bnx2x_link_reset(struct link_params *params, struct link_vars *vars,
 		REG_WR(bp, NIG_REG_EGRESS_EMAC0_OUT_EN + port*4, 0);
 	}
 
-		if (!CHIP_IS_E3(bp)) {
-			bnx2x_set_bmac_rx(bp, params->chip_id, port, 0);
-		} else {
-			bnx2x_set_xmac_rxtx(params, 0);
-			bnx2x_set_umac_rxtx(params, 0);
-		}
+	if (!CHIP_IS_E3(bp)) {
+		bnx2x_set_bmac_rx(bp, params->chip_id, port, 0);
+	} else {
+		bnx2x_set_xmac_rxtx(params, 0);
+		bnx2x_set_umac_rxtx(params, 0);
+	}
 	/* Disable emac */
 	if (!CHIP_IS_E3(bp))
 		REG_WR(bp, NIG_REG_NIG_EMAC0_EN + port*4, 0);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index b164f705709d..626b491f7674 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -9360,10 +9360,16 @@ void bnx2x_chip_cleanup(struct bnx2x *bp, int unload_mode, bool keep_link)
 		BNX2X_ERR("Failed to schedule DEL commands for UC MACs list: %d\n",
 			  rc);
 
-	/* Remove all currently configured VLANs */
-	rc = bnx2x_del_all_vlans(bp);
-	if (rc < 0)
-		BNX2X_ERR("Failed to delete all VLANs\n");
+	/* The whole *vlan_obj structure may be not initialized if VLAN
+	 * filtering offload is not supported by hardware. Currently this is
+	 * true for all hardware covered by CHIP_IS_E1x().
+	 */
+	if (!CHIP_IS_E1x(bp)) {
+		/* Remove all currently configured VLANs */
+		rc = bnx2x_del_all_vlans(bp);
+		if (rc < 0)
+			BNX2X_ERR("Failed to delete all VLANs\n");
+	}
 
 	/* Disable LLH */
 	if (!CHIP_IS_E1(bp))
@@ -11292,7 +11298,7 @@ static void bnx2x_link_settings_supported(struct bnx2x *bp, u32 switch_cfg)
 			   dev_info.port_hw_config[port].external_phy_config),
 			   SHMEM_RD(bp,
 			   dev_info.port_hw_config[port].external_phy_config2));
-			return;
+		return;
 	}
 
 	if (CHIP_IS_E3(bp))
@@ -11992,7 +11998,7 @@ static void validate_set_si_mode(struct bnx2x *bp)
 static int bnx2x_get_hwinfo(struct bnx2x *bp)
 {
 	int /*abs*/func = BP_ABS_FUNC(bp);
-	int vn, mfw_vn;
+	int vn;
 	u32 val = 0, val2 = 0;
 	int rc = 0;
 
@@ -12077,12 +12083,10 @@ static int bnx2x_get_hwinfo(struct bnx2x *bp)
 	/*
 	 * Initialize MF configuration
 	 */
-
 	bp->mf_ov = 0;
 	bp->mf_mode = 0;
 	bp->mf_sub_mode = 0;
 	vn = BP_VN(bp);
-	mfw_vn = BP_FW_MB_IDX(bp);
 
 	if (!CHIP_IS_E1(bp) && !BP_NOMCP(bp)) {
 		BNX2X_DEV_INFO("shmem2base 0x%x, size %d, mfcfg offset %d\n",
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index a9eaaf3e73a4..7b22a6d8514c 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -2977,8 +2977,8 @@ static inline void bnx2x_mcast_hdl_pending_del_e2(struct bnx2x *bp,
 
 		cmd_pos->data.macs_num--;
 
-		  DP(BNX2X_MSG_SP, "Deleting MAC. %d left,cnt is %d\n",
-				   cmd_pos->data.macs_num, cnt);
+		DP(BNX2X_MSG_SP, "Deleting MAC. %d left,cnt is %d\n",
+		   cmd_pos->data.macs_num, cnt);
 
 		/* Break if we reached the maximum
 		 * number of rules.
@@ -3597,8 +3597,8 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp,
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
 		p->mcast_list_len = reg_sz;
-		  DP(BNX2X_MSG_SP, "Command %d, p->mcast_list_len=%d\n",
-				   cmd, p->mcast_list_len);
+		DP(BNX2X_MSG_SP, "Command %d, p->mcast_list_len=%d\n",
+		   cmd, p->mcast_list_len);
 		break;
 
 	case BNX2X_MCAST_CMD_ADD:
@@ -3735,8 +3735,8 @@ static inline int bnx2x_mcast_handle_restore_cmd_e1(
 
 		i++;
 
-		  DP(BNX2X_MSG_SP, "About to configure %pM mcast MAC\n",
-		     cfg_data.mac);
+		DP(BNX2X_MSG_SP, "About to configure %pM mcast MAC\n",
+		   cfg_data.mac);
 	}
 
 	*rdata_idx = i;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index c835f6c7ecd0..c97b642e6537 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -2230,7 +2230,7 @@ int bnx2x_vf_free(struct bnx2x *bp, struct bnx2x_virtf *vf)
 		rc = bnx2x_vf_close(bp, vf);
 		if (rc)
 			goto op_err;
-		/* Fallthrough to release resources */
+		/* Fall through - to release resources */
 	case VF_ACQUIRED:
 		DP(BNX2X_MSG_IOV, "about to free resources\n");
 		bnx2x_vf_free_resc(bp, vf);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
index 8e0a317b31f7..10ff37d6dc78 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c
@@ -957,7 +957,7 @@ int bnx2x_vfpf_update_vlan(struct bnx2x *bp, u16 vid, u8 vf_qid, bool add)
 	bnx2x_sample_bulletin(bp);
 
 	if (bp->shadow_bulletin.content.valid_bitmap & 1 << VLAN_VALID) {
-		BNX2X_ERR("Hypervisor will dicline the request, avoiding\n");
+		BNX2X_ERR("Hypervisor will decline the request, avoiding\n");
 		rc = -EINVAL;
 		goto out;
 	}
@@ -1654,13 +1654,9 @@ static int bnx2x_vf_mbx_macvlan_list(struct bnx2x *bp,
 {
 	int i, j;
 	struct bnx2x_vf_mac_vlan_filters *fl = NULL;
-	size_t fsz;
 
-	fsz = tlv->n_mac_vlan_filters *
-	      sizeof(struct bnx2x_vf_mac_vlan_filter) +
-	      sizeof(struct bnx2x_vf_mac_vlan_filters);
-
-	fl = kzalloc(fsz, GFP_KERNEL);
+	fl = kzalloc(struct_size(fl, filters, tlv->n_mac_vlan_filters),
+		     GFP_KERNEL);
 	if (!fl)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5d21c14853ac..52ade133b57c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1,7 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
- * Copyright (c) 2016-2018 Broadcom Limited
+ * Copyright (c) 2016-2019 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -31,6 +31,7 @@
 #include <asm/page.h>
 #include <linux/time.h>
 #include <linux/mii.h>
+#include <linux/mdio.h>
 #include <linux/if.h>
 #include <linux/if_vlan.h>
 #include <linux/if_bridge.h>
@@ -112,12 +113,14 @@ enum board_idx {
 	BCM57454,
 	BCM5745x_NPAR,
 	BCM57508,
+	BCM57504,
 	BCM58802,
 	BCM58804,
 	BCM58808,
 	NETXTREME_E_VF,
 	NETXTREME_C_VF,
 	NETXTREME_S_VF,
+	NETXTREME_E_P5_VF,
 };
 
 /* indexed by enum above */
@@ -154,12 +157,14 @@ static const struct {
 	[BCM57454] = { "Broadcom BCM57454 NetXtreme-E 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[BCM5745x_NPAR] = { "Broadcom BCM5745x NetXtreme-E Ethernet Partition" },
 	[BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
+	[BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" },
 	[BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" },
 	[BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" },
 	[NETXTREME_E_VF] = { "Broadcom NetXtreme-E Ethernet Virtual Function" },
 	[NETXTREME_C_VF] = { "Broadcom NetXtreme-C Ethernet Virtual Function" },
 	[NETXTREME_S_VF] = { "Broadcom NetXtreme-S Ethernet Virtual Function" },
+	[NETXTREME_E_P5_VF] = { "Broadcom BCM5750X NetXtreme-E Ethernet Virtual Function" },
 };
 
 static const struct pci_device_id bnxt_pci_tbl[] = {
@@ -199,6 +204,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16f0), .driver_data = BCM58808 },
 	{ PCI_VDEVICE(BROADCOM, 0x16f1), .driver_data = BCM57452 },
 	{ PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 },
+	{ PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 },
 	{ PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 },
 	{ PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 },
 #ifdef CONFIG_BNXT_SRIOV
@@ -210,6 +216,7 @@ static const struct pci_device_id bnxt_pci_tbl[] = {
 	{ PCI_VDEVICE(BROADCOM, 0x16dc), .driver_data = NETXTREME_E_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e1), .driver_data = NETXTREME_C_VF },
 	{ PCI_VDEVICE(BROADCOM, 0x16e5), .driver_data = NETXTREME_C_VF },
+	{ PCI_VDEVICE(BROADCOM, 0x1807), .driver_data = NETXTREME_E_P5_VF },
 	{ PCI_VDEVICE(BROADCOM, 0xd800), .driver_data = NETXTREME_S_VF },
 #endif
 	{ 0 }
@@ -237,7 +244,7 @@ static struct workqueue_struct *bnxt_pf_wq;
 static bool bnxt_vf_pciid(enum board_idx idx)
 {
 	return (idx == NETXTREME_C_VF || idx == NETXTREME_E_VF ||
-		idx == NETXTREME_S_VF);
+		idx == NETXTREME_S_VF || idx == NETXTREME_E_P5_VF);
 }
 
 #define DB_CP_REARM_FLAGS	(DB_KEY_CP | DB_IDX_VALID)
@@ -497,6 +504,12 @@ normal_tx:
 	}
 
 	length >>= 9;
+	if (unlikely(length >= ARRAY_SIZE(bnxt_lhint_arr))) {
+		dev_warn_ratelimited(&pdev->dev, "Dropped oversize %d bytes TX packet.\n",
+				     skb->len);
+		i = 0;
+		goto tx_dma_error;
+	}
 	flags |= bnxt_lhint_arr[length];
 	txbd->tx_bd_len_flags_type = cpu_to_le32(flags);
 
@@ -1120,6 +1133,8 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	tpa_info = &rxr->rx_tpa[agg_id];
 
 	if (unlikely(cons != rxr->rx_next_cons)) {
+		netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return;
 	}
@@ -1572,15 +1587,17 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	}
 
 	cons = rxcmp->rx_cmp_opaque;
-	rx_buf = &rxr->rx_buf_ring[cons];
-	data = rx_buf->data;
-	data_ptr = rx_buf->data_ptr;
 	if (unlikely(cons != rxr->rx_next_cons)) {
 		int rc1 = bnxt_discard_rx(bp, cpr, raw_cons, rxcmp);
 
+		netdev_warn(bp->dev, "RX cons %x != expected cons %x\n",
+			    cons, rxr->rx_next_cons);
 		bnxt_sched_reset(bp, rxr);
 		return rc1;
 	}
+	rx_buf = &rxr->rx_buf_ring[cons];
+	data = rx_buf->data;
+	data_ptr = rx_buf->data_ptr;
 	prefetch(data_ptr);
 
 	misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1);
@@ -1597,12 +1614,18 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 
 	rx_buf->data = NULL;
 	if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) {
+		u32 rx_err = le32_to_cpu(rxcmp1->rx_cmp_cfa_code_errors_v2);
+
 		bnxt_reuse_rx_data(rxr, cons, data);
 		if (agg_bufs)
 			bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs);
 
 		rc = -EIO;
-		goto next_rx;
+		if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) {
+			netdev_warn(bp->dev, "RX buffer error %x\n", rx_err);
+			bnxt_sched_reset(bp, rxr);
+		}
+		goto next_rx_no_len;
 	}
 
 	len = le32_to_cpu(rxcmp->rx_cmp_len_flags_type) >> RX_CMP_LEN_SHIFT;
@@ -1683,12 +1706,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	rc = 1;
 
 next_rx:
-	rxr->rx_prod = NEXT_RX(prod);
-	rxr->rx_next_cons = NEXT_RX(cons);
-
 	cpr->rx_packets += 1;
 	cpr->rx_bytes += len;
 
+next_rx_no_len:
+	rxr->rx_prod = NEXT_RX(prod);
+	rxr->rx_next_cons = NEXT_RX(cons);
+
 next_rx_no_prod_no_len:
 	*raw_cons = tmp_raw_cons;
 
@@ -1809,7 +1833,7 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 	case CMPL_BASE_TYPE_HWRM_DONE:
 		seq_id = le16_to_cpu(h_cmpl->sequence_id);
 		if (seq_id == bp->hwrm_intr_seq_id)
-			bp->hwrm_intr_seq_id = HWRM_SEQ_ID_INVALID;
+			bp->hwrm_intr_seq_id = (u16)~bp->hwrm_intr_seq_id;
 		else
 			netdev_err(bp->dev, "Invalid hwrm seq id %d\n", seq_id);
 		break;
@@ -2372,7 +2396,11 @@ static void bnxt_free_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		rmem->pg_arr[i] = NULL;
 	}
 	if (rmem->pg_tbl) {
-		dma_free_coherent(&pdev->dev, rmem->nr_pages * 8,
+		size_t pg_tbl_size = rmem->nr_pages * 8;
+
+		if (rmem->flags & BNXT_RMEM_USE_FULL_PAGE_FLAG)
+			pg_tbl_size = rmem->page_size;
+		dma_free_coherent(&pdev->dev, pg_tbl_size,
 				  rmem->pg_tbl, rmem->pg_tbl_map);
 		rmem->pg_tbl = NULL;
 	}
@@ -2390,9 +2418,12 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 
 	if (rmem->flags & (BNXT_RMEM_VALID_PTE_FLAG | BNXT_RMEM_RING_PTE_FLAG))
 		valid_bit = PTU_PTE_VALID;
-	if (rmem->nr_pages > 1) {
-		rmem->pg_tbl = dma_alloc_coherent(&pdev->dev,
-						  rmem->nr_pages * 8,
+	if ((rmem->nr_pages > 1 || rmem->depth > 0) && !rmem->pg_tbl) {
+		size_t pg_tbl_size = rmem->nr_pages * 8;
+
+		if (rmem->flags & BNXT_RMEM_USE_FULL_PAGE_FLAG)
+			pg_tbl_size = rmem->page_size;
+		rmem->pg_tbl = dma_alloc_coherent(&pdev->dev, pg_tbl_size,
 						  &rmem->pg_tbl_map,
 						  GFP_KERNEL);
 		if (!rmem->pg_tbl)
@@ -2409,7 +2440,7 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem)
 		if (!rmem->pg_arr[i])
 			return -ENOMEM;
 
-		if (rmem->nr_pages > 1) {
+		if (rmem->nr_pages > 1 || rmem->depth > 0) {
 			if (i == rmem->nr_pages - 2 &&
 			    (rmem->flags & BNXT_RMEM_RING_PTE_FLAG))
 				extra_bits |= PTU_PTE_NEXT_TO_LAST;
@@ -3276,6 +3307,27 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp)
 				  bp->hwrm_cmd_resp_dma_addr);
 		bp->hwrm_cmd_resp_addr = NULL;
 	}
+
+	if (bp->hwrm_cmd_kong_resp_addr) {
+		dma_free_coherent(&pdev->dev, PAGE_SIZE,
+				  bp->hwrm_cmd_kong_resp_addr,
+				  bp->hwrm_cmd_kong_resp_dma_addr);
+		bp->hwrm_cmd_kong_resp_addr = NULL;
+	}
+}
+
+static int bnxt_alloc_kong_hwrm_resources(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+
+	bp->hwrm_cmd_kong_resp_addr =
+		dma_alloc_coherent(&pdev->dev, PAGE_SIZE,
+				   &bp->hwrm_cmd_kong_resp_dma_addr,
+				   GFP_KERNEL);
+	if (!bp->hwrm_cmd_kong_resp_addr)
+		return -ENOMEM;
+
+	return 0;
 }
 
 static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
@@ -3317,9 +3369,8 @@ static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp)
 	return 0;
 }
 
-static void bnxt_free_stats(struct bnxt *bp)
+static void bnxt_free_port_stats(struct bnxt *bp)
 {
-	u32 size, i;
 	struct pci_dev *pdev = bp->pdev;
 
 	bp->flags &= ~BNXT_FLAG_PORT_STATS;
@@ -3345,6 +3396,12 @@ static void bnxt_free_stats(struct bnxt *bp)
 				  bp->hw_rx_port_stats_ext_map);
 		bp->hw_rx_port_stats_ext = NULL;
 	}
+}
+
+static void bnxt_free_ring_stats(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+	int size, i;
 
 	if (!bp->bnapi)
 		return;
@@ -3384,6 +3441,9 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 	}
 
 	if (BNXT_PF(bp) && bp->chip_num != CHIP_NUM_58700) {
+		if (bp->hw_rx_port_stats)
+			goto alloc_ext_stats;
+
 		bp->hw_port_stats_size = sizeof(struct rx_port_stats) +
 					 sizeof(struct tx_port_stats) + 1024;
 
@@ -3400,25 +3460,33 @@ static int bnxt_alloc_stats(struct bnxt *bp)
 					   sizeof(struct rx_port_stats) + 512;
 		bp->flags |= BNXT_FLAG_PORT_STATS;
 
+alloc_ext_stats:
 		/* Display extended statistics only if FW supports it */
 		if (bp->hwrm_spec_code < 0x10804 ||
 		    bp->hwrm_spec_code == 0x10900)
 			return 0;
 
+		if (bp->hw_rx_port_stats_ext)
+			goto alloc_tx_ext_stats;
+
 		bp->hw_rx_port_stats_ext =
-			dma_zalloc_coherent(&pdev->dev,
-					    sizeof(struct rx_port_stats_ext),
-					    &bp->hw_rx_port_stats_ext_map,
-					    GFP_KERNEL);
+			dma_alloc_coherent(&pdev->dev,
+					   sizeof(struct rx_port_stats_ext),
+					   &bp->hw_rx_port_stats_ext_map,
+					   GFP_KERNEL);
 		if (!bp->hw_rx_port_stats_ext)
 			return 0;
 
+alloc_tx_ext_stats:
+		if (bp->hw_tx_port_stats_ext)
+			return 0;
+
 		if (bp->hwrm_spec_code >= 0x10902) {
 			bp->hw_tx_port_stats_ext =
-				dma_zalloc_coherent(&pdev->dev,
-					    sizeof(struct tx_port_stats_ext),
-					    &bp->hw_tx_port_stats_ext_map,
-					    GFP_KERNEL);
+				dma_alloc_coherent(&pdev->dev,
+						   sizeof(struct tx_port_stats_ext),
+						   &bp->hw_tx_port_stats_ext_map,
+						   GFP_KERNEL);
 		}
 		bp->flags |= BNXT_FLAG_PORT_STATS_EXT;
 	}
@@ -3520,7 +3588,7 @@ static void bnxt_free_mem(struct bnxt *bp, bool irq_re_init)
 	bnxt_free_cp_rings(bp);
 	bnxt_free_ntp_fltrs(bp, irq_re_init);
 	if (irq_re_init) {
-		bnxt_free_stats(bp);
+		bnxt_free_ring_stats(bp);
 		bnxt_free_ring_grps(bp);
 		bnxt_free_vnics(bp);
 		kfree(bp->tx_ring_map);
@@ -3721,7 +3789,10 @@ void bnxt_hwrm_cmd_hdr_init(struct bnxt *bp, void *request, u16 req_type,
 	req->req_type = cpu_to_le16(req_type);
 	req->cmpl_ring = cpu_to_le16(cmpl_ring);
 	req->target_id = cpu_to_le16(target_id);
-	req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
+	if (bnxt_kong_hwrm_message(bp, req))
+		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr);
+	else
+		req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr);
 }
 
 static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
@@ -3736,11 +3807,10 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	struct hwrm_err_output *resp = bp->hwrm_cmd_resp_addr;
 	u16 max_req_len = BNXT_HWRM_MAX_REQ_LEN;
 	struct hwrm_short_input short_input = {0};
-
-	req->seq_id = cpu_to_le16(bp->hwrm_cmd_seq++);
-	memset(resp, 0, PAGE_SIZE);
-	cp_ring_id = le16_to_cpu(req->cmpl_ring);
-	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
+	u32 doorbell_offset = BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER;
+	u8 *resp_addr = (u8 *)bp->hwrm_cmd_resp_addr;
+	u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM;
+	u16 dst = BNXT_HWRM_CHNL_CHIMP;
 
 	if (msg_len > BNXT_HWRM_MAX_REQ_LEN) {
 		if (msg_len > bp->hwrm_max_ext_req_len ||
@@ -3748,6 +3818,23 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			return -EINVAL;
 	}
 
+	if (bnxt_hwrm_kong_chnl(bp, req)) {
+		dst = BNXT_HWRM_CHNL_KONG;
+		bar_offset = BNXT_GRCPF_REG_KONG_COMM;
+		doorbell_offset = BNXT_GRCPF_REG_KONG_COMM_TRIGGER;
+		resp = bp->hwrm_cmd_kong_resp_addr;
+		resp_addr = (u8 *)bp->hwrm_cmd_kong_resp_addr;
+	}
+
+	memset(resp, 0, PAGE_SIZE);
+	cp_ring_id = le16_to_cpu(req->cmpl_ring);
+	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
+
+	req->seq_id = cpu_to_le16(bnxt_get_hwrm_seq_id(bp, dst));
+	/* currently supports only one outstanding message */
+	if (intr_process)
+		bp->hwrm_intr_seq_id = le16_to_cpu(req->seq_id);
+
 	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
 	    msg_len > BNXT_HWRM_MAX_REQ_LEN) {
 		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
@@ -3781,17 +3868,13 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	}
 
 	/* Write request msg to hwrm channel */
-	__iowrite32_copy(bp->bar0, data, msg_len / 4);
+	__iowrite32_copy(bp->bar0 + bar_offset, data, msg_len / 4);
 
 	for (i = msg_len; i < max_req_len; i += 4)
-		writel(0, bp->bar0 + i);
-
-	/* currently supports only one outstanding message */
-	if (intr_process)
-		bp->hwrm_intr_seq_id = le16_to_cpu(req->seq_id);
+		writel(0, bp->bar0 + bar_offset + i);
 
 	/* Ring channel doorbell */
-	writel(1, bp->bar0 + 0x100);
+	writel(1, bp->bar0 + doorbell_offset);
 
 	if (!timeout)
 		timeout = DFLT_HWRM_CMD_TIMEOUT;
@@ -3806,10 +3889,13 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	tmo_count = HWRM_SHORT_TIMEOUT_COUNTER;
 	timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER;
 	tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT);
-	resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET;
+	resp_len = (__le32 *)(resp_addr + HWRM_RESP_LEN_OFFSET);
+
 	if (intr_process) {
+		u16 seq_id = bp->hwrm_intr_seq_id;
+
 		/* Wait until hwrm response cmpl interrupt is processed */
-		while (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID &&
+		while (bp->hwrm_intr_seq_id != (u16)~seq_id &&
 		       i++ < tmo_count) {
 			/* on first few passes, just barely sleep */
 			if (i < HWRM_SHORT_TIMEOUT_COUNTER)
@@ -3820,14 +3906,14 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 					     HWRM_MAX_TIMEOUT);
 		}
 
-		if (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID) {
+		if (bp->hwrm_intr_seq_id != (u16)~seq_id) {
 			netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n",
 				   le16_to_cpu(req->req_type));
 			return -1;
 		}
 		len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >>
 		      HWRM_RESP_LEN_SFT;
-		valid = bp->hwrm_cmd_resp_addr + len - 1;
+		valid = resp_addr + len - 1;
 	} else {
 		int j;
 
@@ -3838,7 +3924,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 			if (len)
 				break;
 			/* on first few passes, just barely sleep */
-			if (i < DFLT_HWRM_CMD_TIMEOUT)
+			if (i < HWRM_SHORT_TIMEOUT_COUNTER)
 				usleep_range(HWRM_SHORT_MIN_TIMEOUT,
 					     HWRM_SHORT_MAX_TIMEOUT);
 			else
@@ -3855,13 +3941,13 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 		}
 
 		/* Last byte of resp contains valid bit */
-		valid = bp->hwrm_cmd_resp_addr + len - 1;
+		valid = resp_addr + len - 1;
 		for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) {
 			/* make sure we read from updated DMA memory */
 			dma_rmb();
 			if (*valid)
 				break;
-			udelay(1);
+			usleep_range(1, 5);
 		}
 
 		if (j >= HWRM_VALID_BIT_DELAY_USEC) {
@@ -3990,6 +4076,10 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD);
 	}
 
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+		req.flags |= cpu_to_le32(
+			FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE);
+
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
@@ -4118,12 +4208,11 @@ static int bnxt_hwrm_cfa_ntuple_filter_free(struct bnxt *bp,
 static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 					     struct bnxt_ntuple_filter *fltr)
 {
-	int rc = 0;
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[fltr->rxq + 1];
 	struct hwrm_cfa_ntuple_filter_alloc_input req = {0};
-	struct hwrm_cfa_ntuple_filter_alloc_output *resp =
-		bp->hwrm_cmd_resp_addr;
+	struct hwrm_cfa_ntuple_filter_alloc_output *resp;
 	struct flow_keys *keys = &fltr->fkeys;
-	struct bnxt_vnic_info *vnic = &bp->vnic_info[fltr->rxq + 1];
+	int rc = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_NTUPLE_FILTER_ALLOC, -1, -1);
 	req.l2_filter_id = bp->vnic_info[0].fw_l2_filter_id[fltr->l2_fltr_idx];
@@ -4169,8 +4258,10 @@ static int bnxt_hwrm_cfa_ntuple_filter_alloc(struct bnxt *bp,
 	req.dst_id = cpu_to_le16(vnic->fw_vnic_id);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		fltr->filter_id = resp->ntuple_filter_id;
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
@@ -4903,12 +4994,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
 		struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
 		u32 map_idx = ring->map_idx;
+		unsigned int vector;
 
+		vector = bp->irq_tbl[map_idx].vector;
+		disable_irq_nosync(vector);
 		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
-		if (rc)
+		if (rc) {
+			enable_irq(vector);
 			goto err_out;
+		}
 		bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
 		bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+		enable_irq(vector);
 		bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id;
 
 		if (!i) {
@@ -5039,10 +5136,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
 		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_TX,
 						close_path ? cmpl_ring_id :
@@ -5055,10 +5152,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring,
 						RING_FREE_REQ_RING_TYPE_RX,
 						close_path ? cmpl_ring_id :
@@ -5077,10 +5174,10 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
 		struct bnxt_ring_struct *ring = &rxr->rx_agg_ring_struct;
 		u32 grp_idx = rxr->bnapi->index;
-		u32 cmpl_ring_id;
 
-		cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
+			u32 cmpl_ring_id = bnxt_cp_ring_for_rx(bp, rxr);
+
 			hwrm_ring_free_send_msg(bp, ring, type,
 						close_path ? cmpl_ring_id :
 						INVALID_HW_RING_ID);
@@ -5161,7 +5258,6 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 		hw_resc->resv_vnics = le16_to_cpu(resp->alloc_vnics);
 		cp = le16_to_cpu(resp->alloc_cmpl_rings);
 		stats = le16_to_cpu(resp->alloc_stat_ctx);
-		cp = min_t(u16, cp, stats);
 		hw_resc->resv_irqs = cp;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			int rx = hw_resc->resv_rx_rings;
@@ -5180,6 +5276,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 			hw_resc->resv_hw_ring_grps = rx;
 		}
 		hw_resc->resv_cp_rings = cp;
+		hw_resc->resv_stat_ctxs = stats;
 	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return 0;
@@ -5209,7 +5306,7 @@ static bool bnxt_rfs_supported(struct bnxt *bp);
 static void
 __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 			     int tx_rings, int rx_rings, int ring_grps,
-			     int cp_rings, int vnics)
+			     int cp_rings, int stats, int vnics)
 {
 	u32 enables = 0;
 
@@ -5219,17 +5316,16 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->num_tx_rings = cpu_to_le16(tx_rings);
 	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
+		enables |= stats ? FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 		if (bp->flags & BNXT_FLAG_CHIP_P5) {
 			enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_MSIX : 0;
 			enables |= tx_rings + ring_grps ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= rx_rings ?
 				FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
 		} else {
 			enables |= cp_rings ?
-				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-				   FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+				   FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 			enables |= ring_grps ?
 				   FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS |
 				   FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
@@ -5251,7 +5347,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 				req->num_rsscos_ctxs =
 					cpu_to_le16(ring_grps + 1);
 		}
-		req->num_stat_ctxs = req->num_cmpl_rings;
+		req->num_stat_ctxs = cpu_to_le16(stats);
 		req->num_vnics = cpu_to_le16(vnics);
 	}
 	req->enables = cpu_to_le32(enables);
@@ -5261,7 +5357,7 @@ static void
 __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 			     struct hwrm_func_vf_cfg_input *req, int tx_rings,
 			     int rx_rings, int ring_grps, int cp_rings,
-			     int vnics)
+			     int stats, int vnics)
 {
 	u32 enables = 0;
 
@@ -5269,14 +5365,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 	enables |= tx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	enables |= rx_rings ? FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS |
 			      FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS : 0;
+	enables |= stats ? FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		enables |= tx_rings + ring_grps ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 	} else {
 		enables |= cp_rings ?
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
-			   FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
+			   FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS : 0;
 		enables |= ring_grps ?
 			   FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS : 0;
 	}
@@ -5294,7 +5389,7 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 		req->num_hw_ring_grps = cpu_to_le16(ring_grps);
 		req->num_rsscos_ctxs = cpu_to_le16(BNXT_VF_MAX_RSS_CTX);
 	}
-	req->num_stat_ctxs = req->num_cmpl_rings;
+	req->num_stat_ctxs = cpu_to_le16(stats);
 	req->num_vnics = cpu_to_le16(vnics);
 
 	req->enables = cpu_to_le32(enables);
@@ -5302,13 +5397,13 @@ __bnxt_hwrm_reserve_vf_rings(struct bnxt *bp,
 
 static int
 bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-			   int ring_grps, int cp_rings, int vnics)
+			   int ring_grps, int cp_rings, int stats, int vnics)
 {
 	struct hwrm_func_cfg_input req = {0};
 	int rc;
 
 	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	if (!req.enables)
 		return 0;
 
@@ -5325,7 +5420,7 @@ bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 
 static int
 bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-			   int ring_grps, int cp_rings, int vnics)
+			   int ring_grps, int cp_rings, int stats, int vnics)
 {
 	struct hwrm_func_vf_cfg_input req = {0};
 	int rc;
@@ -5336,7 +5431,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	}
 
 	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
 		return -ENOMEM;
@@ -5346,15 +5441,17 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 }
 
 static int bnxt_hwrm_reserve_rings(struct bnxt *bp, int tx, int rx, int grp,
-				   int cp, int vnic)
+				   int cp, int stat, int vnic)
 {
 	if (BNXT_PF(bp))
-		return bnxt_hwrm_reserve_pf_rings(bp, tx, rx, grp, cp, vnic);
+		return bnxt_hwrm_reserve_pf_rings(bp, tx, rx, grp, cp, stat,
+						  vnic);
 	else
-		return bnxt_hwrm_reserve_vf_rings(bp, tx, rx, grp, cp, vnic);
+		return bnxt_hwrm_reserve_vf_rings(bp, tx, rx, grp, cp, stat,
+						  vnic);
 }
 
-static int bnxt_nq_rings_in_use(struct bnxt *bp)
+int bnxt_nq_rings_in_use(struct bnxt *bp)
 {
 	int cp = bp->cp_nr_rings;
 	int ulp_msix, ulp_base;
@@ -5380,12 +5477,17 @@ static int bnxt_cp_rings_in_use(struct bnxt *bp)
 	return cp;
 }
 
+static int bnxt_get_func_stat_ctxs(struct bnxt *bp)
+{
+	return bp->cp_nr_rings + bnxt_get_ulp_stat_ctxs(bp);
+}
+
 static bool bnxt_need_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 	int cp = bnxt_cp_rings_in_use(bp);
 	int nq = bnxt_nq_rings_in_use(bp);
-	int rx = bp->rx_nr_rings;
+	int rx = bp->rx_nr_rings, stat;
 	int vnic = 1, grp = rx;
 
 	if (bp->hwrm_spec_code < 0x10601)
@@ -5398,9 +5500,11 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
+	stat = bnxt_get_func_stat_ctxs(bp);
 	if (BNXT_NEW_RM(bp) &&
 	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
 	     hw_resc->resv_irqs < nq || hw_resc->resv_vnics != vnic ||
+	     hw_resc->resv_stat_ctxs != stat ||
 	     (hw_resc->resv_hw_ring_grps != grp &&
 	      !(bp->flags & BNXT_FLAG_CHIP_P5))))
 		return true;
@@ -5414,8 +5518,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	int tx = bp->tx_nr_rings;
 	int rx = bp->rx_nr_rings;
 	int grp, rx_rings, rc;
+	int vnic = 1, stat;
 	bool sh = false;
-	int vnic = 1;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
@@ -5427,8 +5531,9 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
 	grp = bp->rx_nr_rings;
+	stat = bnxt_get_func_stat_ctxs(bp);
 
-	rc = bnxt_hwrm_reserve_rings(bp, tx, rx, grp, cp, vnic);
+	rc = bnxt_hwrm_reserve_rings(bp, tx, rx, grp, cp, stat, vnic);
 	if (rc)
 		return rc;
 
@@ -5438,6 +5543,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		cp = hw_resc->resv_irqs;
 		grp = hw_resc->resv_hw_ring_grps;
 		vnic = hw_resc->resv_vnics;
+		stat = hw_resc->resv_stat_ctxs;
 	}
 
 	rx_rings = rx;
@@ -5456,6 +5562,10 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		}
 	}
 	rx_rings = min_t(int, rx_rings, grp);
+	cp = min_t(int, cp, bp->cp_nr_rings);
+	if (stat > bnxt_get_ulp_stat_ctxs(bp))
+		stat -= bnxt_get_ulp_stat_ctxs(bp);
+	cp = min_t(int, cp, stat);
 	rc = bnxt_trim_rings(bp, &rx_rings, &tx, cp, sh);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx = rx_rings << 1;
@@ -5464,14 +5574,15 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	bp->rx_nr_rings = rx_rings;
 	bp->cp_nr_rings = cp;
 
-	if (!tx || !rx || !cp || !grp || !vnic)
+	if (!tx || !rx || !cp || !grp || !vnic || !stat)
 		return -ENOMEM;
 
 	return rc;
 }
 
 static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-				    int ring_grps, int cp_rings, int vnics)
+				    int ring_grps, int cp_rings, int stats,
+				    int vnics)
 {
 	struct hwrm_func_vf_cfg_input req = {0};
 	u32 flags;
@@ -5481,7 +5592,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 		return 0;
 
 	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	flags = FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST |
 		FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
@@ -5499,14 +5610,15 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 }
 
 static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-				    int ring_grps, int cp_rings, int vnics)
+				    int ring_grps, int cp_rings, int stats,
+				    int vnics)
 {
 	struct hwrm_func_cfg_input req = {0};
 	u32 flags;
 	int rc;
 
 	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
-				     cp_rings, vnics);
+				     cp_rings, stats, vnics);
 	flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST;
 	if (BNXT_NEW_RM(bp)) {
 		flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST |
@@ -5514,7 +5626,8 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 			 FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST;
 		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			flags |= FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST;
+			flags |= FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST |
+				 FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST;
 		else
 			flags |= FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST;
 	}
@@ -5527,17 +5640,19 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 }
 
 static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings,
-				 int ring_grps, int cp_rings, int vnics)
+				 int ring_grps, int cp_rings, int stats,
+				 int vnics)
 {
 	if (bp->hwrm_spec_code < 0x10801)
 		return 0;
 
 	if (BNXT_PF(bp))
 		return bnxt_hwrm_check_pf_rings(bp, tx_rings, rx_rings,
-						ring_grps, cp_rings, vnics);
+						ring_grps, cp_rings, stats,
+						vnics);
 
 	return bnxt_hwrm_check_vf_rings(bp, tx_rings, rx_rings, ring_grps,
-					cp_rings, vnics);
+					cp_rings, stats, vnics);
 }
 
 static void bnxt_hwrm_coal_params_qcaps(struct bnxt *bp)
@@ -5962,8 +6077,11 @@ static void bnxt_hwrm_set_pg_attr(struct bnxt_ring_mem_info *rmem, u8 *pg_attr,
 		pg_size = 2 << 4;
 
 	*pg_attr = pg_size;
-	if (rmem->nr_pages > 1) {
-		*pg_attr |= 1;
+	if (rmem->depth >= 1) {
+		if (rmem->depth == 2)
+			*pg_attr |= 2;
+		else
+			*pg_attr |= 1;
 		*pg_dir = cpu_to_le64(rmem->pg_tbl_map);
 	} else {
 		*pg_dir = cpu_to_le64(rmem->dma_arr[0]);
@@ -6040,6 +6158,22 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 				      &req.stat_pg_size_stat_lvl,
 				      &req.stat_page_dir);
 	}
+	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV) {
+		ctx_pg = &ctx->mrav_mem;
+		req.mrav_num_entries = cpu_to_le32(ctx_pg->entries);
+		req.mrav_entry_size = cpu_to_le16(ctx->mrav_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.mrav_pg_size_mrav_lvl,
+				      &req.mrav_page_dir);
+	}
+	if (enables & FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM) {
+		ctx_pg = &ctx->tim_mem;
+		req.tim_num_entries = cpu_to_le32(ctx_pg->entries);
+		req.tim_entry_size = cpu_to_le16(ctx->tim_entry_size);
+		bnxt_hwrm_set_pg_attr(&ctx_pg->ring_mem,
+				      &req.tim_pg_size_tim_lvl,
+				      &req.tim_page_dir);
+	}
 	for (i = 0, num_entries = &req.tqm_sp_num_entries,
 	     pg_attr = &req.tqm_sp_pg_size_tqm_sp_lvl,
 	     pg_dir = &req.tqm_sp_page_dir,
@@ -6060,25 +6194,107 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables)
 }
 
 static int bnxt_alloc_ctx_mem_blk(struct bnxt *bp,
-				  struct bnxt_ctx_pg_info *ctx_pg, u32 mem_size)
+				  struct bnxt_ctx_pg_info *ctx_pg)
 {
 	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
 
-	if (!mem_size)
-		return 0;
-
-	rmem->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
-	if (rmem->nr_pages > MAX_CTX_PAGES) {
-		rmem->nr_pages = 0;
-		return -EINVAL;
-	}
 	rmem->page_size = BNXT_PAGE_SIZE;
 	rmem->pg_arr = ctx_pg->ctx_pg_arr;
 	rmem->dma_arr = ctx_pg->ctx_dma_arr;
 	rmem->flags = BNXT_RMEM_VALID_PTE_FLAG;
+	if (rmem->depth >= 1)
+		rmem->flags |= BNXT_RMEM_USE_FULL_PAGE_FLAG;
 	return bnxt_alloc_ring(bp, rmem);
 }
 
+static int bnxt_alloc_ctx_pg_tbls(struct bnxt *bp,
+				  struct bnxt_ctx_pg_info *ctx_pg, u32 mem_size,
+				  u8 depth)
+{
+	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
+	int rc;
+
+	if (!mem_size)
+		return 0;
+
+	ctx_pg->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
+	if (ctx_pg->nr_pages > MAX_CTX_TOTAL_PAGES) {
+		ctx_pg->nr_pages = 0;
+		return -EINVAL;
+	}
+	if (ctx_pg->nr_pages > MAX_CTX_PAGES || depth > 1) {
+		int nr_tbls, i;
+
+		rmem->depth = 2;
+		ctx_pg->ctx_pg_tbl = kcalloc(MAX_CTX_PAGES, sizeof(ctx_pg),
+					     GFP_KERNEL);
+		if (!ctx_pg->ctx_pg_tbl)
+			return -ENOMEM;
+		nr_tbls = DIV_ROUND_UP(ctx_pg->nr_pages, MAX_CTX_PAGES);
+		rmem->nr_pages = nr_tbls;
+		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg);
+		if (rc)
+			return rc;
+		for (i = 0; i < nr_tbls; i++) {
+			struct bnxt_ctx_pg_info *pg_tbl;
+
+			pg_tbl = kzalloc(sizeof(*pg_tbl), GFP_KERNEL);
+			if (!pg_tbl)
+				return -ENOMEM;
+			ctx_pg->ctx_pg_tbl[i] = pg_tbl;
+			rmem = &pg_tbl->ring_mem;
+			rmem->pg_tbl = ctx_pg->ctx_pg_arr[i];
+			rmem->pg_tbl_map = ctx_pg->ctx_dma_arr[i];
+			rmem->depth = 1;
+			rmem->nr_pages = MAX_CTX_PAGES;
+			if (i == (nr_tbls - 1)) {
+				int rem = ctx_pg->nr_pages % MAX_CTX_PAGES;
+
+				if (rem)
+					rmem->nr_pages = rem;
+			}
+			rc = bnxt_alloc_ctx_mem_blk(bp, pg_tbl);
+			if (rc)
+				break;
+		}
+	} else {
+		rmem->nr_pages = DIV_ROUND_UP(mem_size, BNXT_PAGE_SIZE);
+		if (rmem->nr_pages > 1 || depth)
+			rmem->depth = 1;
+		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg);
+	}
+	return rc;
+}
+
+static void bnxt_free_ctx_pg_tbls(struct bnxt *bp,
+				  struct bnxt_ctx_pg_info *ctx_pg)
+{
+	struct bnxt_ring_mem_info *rmem = &ctx_pg->ring_mem;
+
+	if (rmem->depth > 1 || ctx_pg->nr_pages > MAX_CTX_PAGES ||
+	    ctx_pg->ctx_pg_tbl) {
+		int i, nr_tbls = rmem->nr_pages;
+
+		for (i = 0; i < nr_tbls; i++) {
+			struct bnxt_ctx_pg_info *pg_tbl;
+			struct bnxt_ring_mem_info *rmem2;
+
+			pg_tbl = ctx_pg->ctx_pg_tbl[i];
+			if (!pg_tbl)
+				continue;
+			rmem2 = &pg_tbl->ring_mem;
+			bnxt_free_ring(bp, rmem2);
+			ctx_pg->ctx_pg_arr[i] = NULL;
+			kfree(pg_tbl);
+			ctx_pg->ctx_pg_tbl[i] = NULL;
+		}
+		kfree(ctx_pg->ctx_pg_tbl);
+		ctx_pg->ctx_pg_tbl = NULL;
+	}
+	bnxt_free_ring(bp, rmem);
+	ctx_pg->nr_pages = 0;
+}
+
 static void bnxt_free_ctx_mem(struct bnxt *bp)
 {
 	struct bnxt_ctx_mem_info *ctx = bp->ctx;
@@ -6089,16 +6305,18 @@ static void bnxt_free_ctx_mem(struct bnxt *bp)
 
 	if (ctx->tqm_mem[0]) {
 		for (i = 0; i < bp->max_q + 1; i++)
-			bnxt_free_ring(bp, &ctx->tqm_mem[i]->ring_mem);
+			bnxt_free_ctx_pg_tbls(bp, ctx->tqm_mem[i]);
 		kfree(ctx->tqm_mem[0]);
 		ctx->tqm_mem[0] = NULL;
 	}
 
-	bnxt_free_ring(bp, &ctx->stat_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->vnic_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->cq_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->srq_mem.ring_mem);
-	bnxt_free_ring(bp, &ctx->qp_mem.ring_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->tim_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->mrav_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->stat_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->vnic_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->cq_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->srq_mem);
+	bnxt_free_ctx_pg_tbls(bp, &ctx->qp_mem);
 	ctx->flags &= ~BNXT_CTX_FLAG_INITED;
 }
 
@@ -6107,6 +6325,9 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	struct bnxt_ctx_pg_info *ctx_pg;
 	struct bnxt_ctx_mem_info *ctx;
 	u32 mem_size, ena, entries;
+	u32 extra_srqs = 0;
+	u32 extra_qps = 0;
+	u8 pg_lvl = 1;
 	int i, rc;
 
 	rc = bnxt_hwrm_func_backing_store_qcaps(bp);
@@ -6119,24 +6340,31 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	if (!ctx || (ctx->flags & BNXT_CTX_FLAG_INITED))
 		return 0;
 
+	if (bp->flags & BNXT_FLAG_ROCE_CAP) {
+		pg_lvl = 2;
+		extra_qps = 65536;
+		extra_srqs = 8192;
+	}
+
 	ctx_pg = &ctx->qp_mem;
-	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries;
+	ctx_pg->entries = ctx->qp_min_qp1_entries + ctx->qp_max_l2_entries +
+			  extra_qps;
 	mem_size = ctx->qp_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->srq_mem;
-	ctx_pg->entries = ctx->srq_max_l2_entries;
+	ctx_pg->entries = ctx->srq_max_l2_entries + extra_srqs;
 	mem_size = ctx->srq_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->cq_mem;
-	ctx_pg->entries = ctx->cq_max_l2_entries;
+	ctx_pg->entries = ctx->cq_max_l2_entries + extra_qps * 2;
 	mem_size = ctx->cq_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, pg_lvl);
 	if (rc)
 		return rc;
 
@@ -6144,26 +6372,47 @@ static int bnxt_alloc_ctx_mem(struct bnxt *bp)
 	ctx_pg->entries = ctx->vnic_max_vnic_entries +
 			  ctx->vnic_max_ring_table_entries;
 	mem_size = ctx->vnic_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 	if (rc)
 		return rc;
 
 	ctx_pg = &ctx->stat_mem;
 	ctx_pg->entries = ctx->stat_max_entries;
 	mem_size = ctx->stat_entry_size * ctx_pg->entries;
-	rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
+	if (rc)
+		return rc;
+
+	ena = 0;
+	if (!(bp->flags & BNXT_FLAG_ROCE_CAP))
+		goto skip_rdma;
+
+	ctx_pg = &ctx->mrav_mem;
+	ctx_pg->entries = extra_qps * 4;
+	mem_size = ctx->mrav_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 2);
 	if (rc)
 		return rc;
+	ena = FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV;
 
-	entries = ctx->qp_max_l2_entries;
+	ctx_pg = &ctx->tim_mem;
+	ctx_pg->entries = ctx->qp_mem.entries;
+	mem_size = ctx->tim_entry_size * ctx_pg->entries;
+	rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
+	if (rc)
+		return rc;
+	ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM;
+
+skip_rdma:
+	entries = ctx->qp_max_l2_entries + extra_qps;
 	entries = roundup(entries, ctx->tqm_entries_multiple);
 	entries = clamp_t(u32, entries, ctx->tqm_min_entries_per_ring,
 			  ctx->tqm_max_entries_per_ring);
-	for (i = 0, ena = 0; i < bp->max_q + 1; i++) {
+	for (i = 0; i < bp->max_q + 1; i++) {
 		ctx_pg = ctx->tqm_mem[i];
 		ctx_pg->entries = entries;
 		mem_size = ctx->tqm_entry_size * entries;
-		rc = bnxt_alloc_ctx_mem_blk(bp, ctx_pg, mem_size);
+		rc = bnxt_alloc_ctx_pg_tbls(bp, ctx_pg, mem_size, 1);
 		if (rc)
 			return rc;
 		ena |= FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP << i;
@@ -6190,7 +6439,8 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	req.fid = cpu_to_le16(0xffff);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = _hwrm_send_message_silent(bp, &req, sizeof(req),
+				       HWRM_CMD_TIMEOUT);
 	if (rc) {
 		rc = -EIO;
 		goto hwrm_func_resc_qcaps_exit;
@@ -6220,7 +6470,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 	if (bp->flags & BNXT_FLAG_CHIP_P5) {
 		u16 max_msix = le16_to_cpu(resp->max_msix);
 
-		hw_resc->max_irqs = min_t(u16, hw_resc->max_irqs, max_msix);
+		hw_resc->max_nqs = max_msix;
 		hw_resc->max_hw_ring_grps = hw_resc->max_rx_rings;
 	}
 
@@ -6442,6 +6692,17 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	    (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED))
 		bp->fw_cap |= BNXT_FW_CAP_SHORT_CMD;
 
+	if (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_KONG_MB_CHNL;
+
+	if (dev_caps_cfg &
+	    VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_OVS_64BIT_HANDLE;
+
+	if (dev_caps_cfg &
+	    VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_TRUSTED_VF;
+
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
@@ -6488,8 +6749,10 @@ static int bnxt_hwrm_port_qstats(struct bnxt *bp)
 static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 {
 	struct hwrm_port_qstats_ext_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_queue_pri2cos_qcfg_input req2 = {0};
 	struct hwrm_port_qstats_ext_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
+	u32 tx_stat_size;
 	int rc;
 
 	if (!(bp->flags & BNXT_FLAG_PORT_STATS_EXT))
@@ -6499,17 +6762,48 @@ static int bnxt_hwrm_port_qstats_ext(struct bnxt *bp)
 	req.port_id = cpu_to_le16(pf->port_id);
 	req.rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext));
 	req.rx_stat_host_addr = cpu_to_le64(bp->hw_rx_port_stats_ext_map);
-	req.tx_stat_size = cpu_to_le16(sizeof(struct tx_port_stats_ext));
+	tx_stat_size = bp->hw_tx_port_stats_ext ?
+		       sizeof(*bp->hw_tx_port_stats_ext) : 0;
+	req.tx_stat_size = cpu_to_le16(tx_stat_size);
 	req.tx_stat_host_addr = cpu_to_le64(bp->hw_tx_port_stats_ext_map);
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
 		bp->fw_rx_stats_ext_size = le16_to_cpu(resp->rx_stat_size) / 8;
-		bp->fw_tx_stats_ext_size = le16_to_cpu(resp->tx_stat_size) / 8;
+		bp->fw_tx_stats_ext_size = tx_stat_size ?
+			le16_to_cpu(resp->tx_stat_size) / 8 : 0;
 	} else {
 		bp->fw_rx_stats_ext_size = 0;
 		bp->fw_tx_stats_ext_size = 0;
 	}
+	if (bp->fw_tx_stats_ext_size <=
+	    offsetof(struct tx_port_stats_ext, pfc_pri0_tx_duration_us) / 8) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
+		bp->pri2cos_valid = 0;
+		return rc;
+	}
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req2, HWRM_QUEUE_PRI2COS_QCFG, -1, -1);
+	req2.flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN);
+
+	rc = _hwrm_send_message(bp, &req2, sizeof(req2), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		struct hwrm_queue_pri2cos_qcfg_output *resp2;
+		u8 *pri2cos;
+		int i, j;
+
+		resp2 = bp->hwrm_cmd_resp_addr;
+		pri2cos = &resp2->pri0_cos_queue_id;
+		for (i = 0; i < 8; i++) {
+			u8 queue_id = pri2cos[i];
+
+			for (j = 0; j < bp->max_q; j++) {
+				if (bp->q_ids[j] == queue_id)
+					bp->pri2cos[i] = j;
+			}
+		}
+		bp->pri2cos_valid = 1;
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
 }
@@ -7034,17 +7328,12 @@ unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp)
 	return bp->hw_resc.max_stat_ctxs;
 }
 
-void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max)
-{
-	bp->hw_resc.max_stat_ctxs = max;
-}
-
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp)
 {
 	return bp->hw_resc.max_cp_rings;
 }
 
-unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
+static unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp)
 {
 	unsigned int cp = bp->hw_resc.max_cp_rings;
 
@@ -7058,6 +7347,9 @@ static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp)
 {
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_nqs);
+
 	return min_t(unsigned int, hw_resc->max_irqs, hw_resc->max_cp_rings);
 }
 
@@ -7066,6 +7358,26 @@ static void bnxt_set_max_func_irqs(struct bnxt *bp, unsigned int max_irqs)
 	bp->hw_resc.max_irqs = max_irqs;
 }
 
+unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp)
+{
+	unsigned int cp;
+
+	cp = bnxt_get_max_func_cp_rings_for_en(bp);
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		return cp - bp->rx_nr_rings - bp->tx_nr_rings;
+	else
+		return cp - bp->cp_nr_rings;
+}
+
+unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp)
+{
+	unsigned int stat;
+
+	stat = bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_ulp_stat_ctxs(bp);
+	stat -= bp->cp_nr_rings;
+	return stat;
+}
+
 int bnxt_get_avail_msix(struct bnxt *bp, int num)
 {
 	int max_cp = bnxt_get_max_func_cp_rings(bp);
@@ -7203,23 +7515,26 @@ static void bnxt_clear_int_mode(struct bnxt *bp)
 int bnxt_reserve_rings(struct bnxt *bp)
 {
 	int tcs = netdev_get_num_tc(bp->dev);
+	bool reinit_irq = false;
 	int rc;
 
 	if (!bnxt_need_reserve_rings(bp))
 		return 0;
 
-	rc = __bnxt_reserve_rings(bp);
-	if (rc) {
-		netdev_err(bp->dev, "ring reservation failure rc: %d\n", rc);
-		return rc;
-	}
 	if (BNXT_NEW_RM(bp) && (bnxt_get_num_msix(bp) != bp->total_irqs)) {
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
-		rc = bnxt_init_int_mode(bp);
+		reinit_irq = true;
+	}
+	rc = __bnxt_reserve_rings(bp);
+	if (reinit_irq) {
+		if (!rc)
+			rc = bnxt_init_int_mode(bp);
 		bnxt_ulp_irq_restart(bp, rc);
-		if (rc)
-			return rc;
+	}
+	if (rc) {
+		netdev_err(bp->dev, "ring reservation/IRQ init failure rc: %d\n", rc);
+		return rc;
 	}
 	if (tcs && (bp->tx_nr_rings_per_tc * tcs != bp->tx_nr_rings)) {
 		netdev_err(bp->dev, "tx ring reservation failure\n");
@@ -7227,7 +7542,6 @@ int bnxt_reserve_rings(struct bnxt *bp)
 		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 		return -ENOMEM;
 	}
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 	return 0;
 }
 
@@ -7821,6 +8135,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 
 		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
 		hw_resc->resv_cp_rings = 0;
+		hw_resc->resv_stat_ctxs = 0;
 		hw_resc->resv_irqs = 0;
 		hw_resc->resv_tx_rings = 0;
 		hw_resc->resv_rx_rings = 0;
@@ -8260,6 +8575,9 @@ static bool bnxt_drv_busy(struct bnxt *bp)
 		test_bit(BNXT_STATE_READ_STATS, &bp->state));
 }
 
+static void bnxt_get_ring_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats);
+
 static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 			     bool link_re_init)
 {
@@ -8285,6 +8603,9 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init,
 	del_timer_sync(&bp->timer);
 	bnxt_free_skbs(bp);
 
+	/* Save ring stats before shutdown */
+	if (bp->bnapi)
+		bnxt_get_ring_stats(bp, &bp->net_stats_prev);
 	if (irq_re_init) {
 		bnxt_free_irq(bp);
 		bnxt_del_napi(bp);
@@ -8320,24 +8641,88 @@ static int bnxt_close(struct net_device *dev)
 	return 0;
 }
 
+static int bnxt_hwrm_port_phy_read(struct bnxt *bp, u16 phy_addr, u16 reg,
+				   u16 *val)
+{
+	struct hwrm_port_phy_mdio_read_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_mdio_read_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10a00)
+		return -EOPNOTSUPP;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_READ, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.phy_addr = phy_addr;
+	req.reg_addr = cpu_to_le16(reg & 0x1f);
+	if (bp->link_info.support_speeds & BNXT_LINK_SPEED_MSK_10GB) {
+		req.cl45_mdio = 1;
+		req.phy_addr = mdio_phy_id_prtad(phy_addr);
+		req.dev_addr = mdio_phy_id_devad(phy_addr);
+		req.reg_addr = cpu_to_le16(reg);
+	}
+
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*val = le16_to_cpu(resp->reg_data);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg,
+				    u16 val)
+{
+	struct hwrm_port_phy_mdio_write_input req = {0};
+
+	if (bp->hwrm_spec_code < 0x10a00)
+		return -EOPNOTSUPP;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_MDIO_WRITE, -1, -1);
+	req.port_id = cpu_to_le16(bp->pf.port_id);
+	req.phy_addr = phy_addr;
+	req.reg_addr = cpu_to_le16(reg & 0x1f);
+	if (bp->link_info.support_speeds & BNXT_LINK_SPEED_MSK_10GB) {
+		req.cl45_mdio = 1;
+		req.phy_addr = mdio_phy_id_prtad(phy_addr);
+		req.dev_addr = mdio_phy_id_devad(phy_addr);
+		req.reg_addr = cpu_to_le16(reg);
+	}
+	req.reg_data = cpu_to_le16(val);
+
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
 /* rtnl_lock held */
 static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	struct mii_ioctl_data *mdio = if_mii(ifr);
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
 	switch (cmd) {
 	case SIOCGMIIPHY:
+		mdio->phy_id = bp->link_info.phy_addr;
+
 		/* fallthru */
 	case SIOCGMIIREG: {
+		u16 mii_regval = 0;
+
 		if (!netif_running(dev))
 			return -EAGAIN;
 
-		return 0;
+		rc = bnxt_hwrm_port_phy_read(bp, mdio->phy_id, mdio->reg_num,
+					     &mii_regval);
+		mdio->val_out = mii_regval;
+		return rc;
 	}
 
 	case SIOCSMIIREG:
 		if (!netif_running(dev))
 			return -EAGAIN;
 
-		return 0;
+		return bnxt_hwrm_port_phy_write(bp, mdio->phy_id, mdio->reg_num,
+						mdio->val_in);
 
 	default:
 		/* do nothing */
@@ -8346,23 +8731,12 @@ static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return -EOPNOTSUPP;
 }
 
-static void
-bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+static void bnxt_get_ring_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats)
 {
-	u32 i;
-	struct bnxt *bp = netdev_priv(dev);
+	int i;
 
-	set_bit(BNXT_STATE_READ_STATS, &bp->state);
-	/* Make sure bnxt_close_nic() sees that we are reading stats before
-	 * we check the BNXT_STATE_OPEN flag.
-	 */
-	smp_mb__after_atomic();
-	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		clear_bit(BNXT_STATE_READ_STATS, &bp->state);
-		return;
-	}
 
-	/* TODO check if we need to synchronize with bnxt_close path */
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 		struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring;
@@ -8391,6 +8765,40 @@ bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 
 		stats->tx_dropped += le64_to_cpu(hw_stats->tx_drop_pkts);
 	}
+}
+
+static void bnxt_add_prev_stats(struct bnxt *bp,
+				struct rtnl_link_stats64 *stats)
+{
+	struct rtnl_link_stats64 *prev_stats = &bp->net_stats_prev;
+
+	stats->rx_packets += prev_stats->rx_packets;
+	stats->tx_packets += prev_stats->tx_packets;
+	stats->rx_bytes += prev_stats->rx_bytes;
+	stats->tx_bytes += prev_stats->tx_bytes;
+	stats->rx_missed_errors += prev_stats->rx_missed_errors;
+	stats->multicast += prev_stats->multicast;
+	stats->tx_dropped += prev_stats->tx_dropped;
+}
+
+static void
+bnxt_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	set_bit(BNXT_STATE_READ_STATS, &bp->state);
+	/* Make sure bnxt_close_nic() sees that we are reading stats before
+	 * we check the BNXT_STATE_OPEN flag.
+	 */
+	smp_mb__after_atomic();
+	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
+		clear_bit(BNXT_STATE_READ_STATS, &bp->state);
+		*stats = bp->net_stats_prev;
+		return;
+	}
+
+	bnxt_get_ring_stats(bp, stats);
+	bnxt_add_prev_stats(bp, stats);
 
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		struct rx_port_stats *rx = bp->hw_rx_port_stats;
@@ -8556,8 +8964,15 @@ static int bnxt_cfg_rx_mode(struct bnxt *bp)
 
 skip_uc:
 	rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	if (rc && vnic->mc_list_count) {
+		netdev_info(bp->dev, "Failed setting MC filters rc: %d, turning on ALL_MCAST mode\n",
+			    rc);
+		vnic->rx_mask |= CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST;
+		vnic->mc_list_count = 0;
+		rc = bnxt_hwrm_cfa_l2_set_rx_mask(bp, 0);
+	}
 	if (rc)
-		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %x\n",
+		netdev_err(bp->dev, "HWRM cfa l2 rx mask failure rc: %d\n",
 			   rc);
 
 	return rc;
@@ -8626,12 +9041,12 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 	if (vnics == bp->hw_resc.resv_vnics)
 		return true;
 
-	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, vnics);
+	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, vnics);
 	if (vnics <= bp->hw_resc.resv_vnics)
 		return true;
 
 	netdev_warn(bp->dev, "Unable to reserve resources to support NTUPLE filters.\n");
-	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 1);
+	bnxt_hwrm_reserve_rings(bp, 0, 0, 0, 0, 0, 1);
 	return false;
 #else
 	return false;
@@ -9042,7 +9457,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
 	int max_rx, max_tx, tx_sets = 1;
-	int tx_rings_needed;
+	int tx_rings_needed, stats;
 	int rx_rings = rx;
 	int cp, vnics, rc;
 
@@ -9067,10 +9482,13 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx_rings <<= 1;
 	cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx;
-	if (BNXT_NEW_RM(bp))
+	stats = cp;
+	if (BNXT_NEW_RM(bp)) {
 		cp += bnxt_get_ulp_msix_num(bp);
+		stats += bnxt_get_ulp_stat_ctxs(bp);
+	}
 	return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp,
-				     vnics);
+				     stats, vnics);
 }
 
 static void bnxt_unmap_bars(struct bnxt *bp, struct pci_dev *pdev)
@@ -9106,7 +9524,7 @@ static void bnxt_init_dflt_coal(struct bnxt *bp)
 	 * 1 coal_buf x bufs_per_record = 1 completion record.
 	 */
 	coal = &bp->rx_coal;
-	coal->coal_ticks = 14;
+	coal->coal_ticks = 10;
 	coal->coal_bufs = 30;
 	coal->coal_ticks_irq = 1;
 	coal->coal_bufs_irq = 2;
@@ -9294,7 +9712,6 @@ int bnxt_setup_mq_tc(struct net_device *dev, u8 tc)
 	bp->tx_nr_rings += bp->tx_nr_rings_xdp;
 	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
 			       bp->tx_nr_rings + bp->rx_nr_rings;
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 
 	if (netif_running(bp->dev))
 		return bnxt_open_nic(bp, true, false);
@@ -9617,7 +10034,7 @@ static int bnxt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 }
 
 static int bnxt_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-			       u16 flags)
+			       u16 flags, struct netlink_ext_ack *extack)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
@@ -9668,8 +10085,11 @@ static int bnxt_get_phys_port_name(struct net_device *dev, char *buf,
 	return 0;
 }
 
-int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr)
+int bnxt_get_port_parent_id(struct net_device *dev,
+			    struct netdev_phys_item_id *ppid)
 {
+	struct bnxt *bp = netdev_priv(dev);
+
 	if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
 		return -EOPNOTSUPP;
 
@@ -9677,27 +10097,12 @@ int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr)
 	if (!BNXT_PF(bp))
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(bp->switch_id);
-		memcpy(attr->u.ppid.id, bp->switch_id, attr->u.ppid.id_len);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-	return 0;
-}
+	ppid->id_len = sizeof(bp->switch_id);
+	memcpy(ppid->id, bp->switch_id, ppid->id_len);
 
-static int bnxt_swdev_port_attr_get(struct net_device *dev,
-				    struct switchdev_attr *attr)
-{
-	return bnxt_port_attr_get(netdev_priv(dev), attr);
+	return 0;
 }
 
-static const struct switchdev_ops bnxt_switchdev_ops = {
-	.switchdev_port_attr_get	= bnxt_swdev_port_attr_get
-};
-
 static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_open		= bnxt_open,
 	.ndo_start_xmit		= bnxt_start_xmit,
@@ -9729,6 +10134,7 @@ static const struct net_device_ops bnxt_netdev_ops = {
 	.ndo_bpf		= bnxt_xdp,
 	.ndo_bridge_getlink	= bnxt_bridge_getlink,
 	.ndo_bridge_setlink	= bnxt_bridge_setlink,
+	.ndo_get_port_parent_id	= bnxt_get_port_parent_id,
 	.ndo_get_phys_port_name = bnxt_get_phys_port_name
 };
 
@@ -9760,6 +10166,7 @@ static void bnxt_remove_one(struct pci_dev *pdev)
 	kfree(bp->ctx);
 	bp->ctx = NULL;
 	bnxt_cleanup_pci(bp);
+	bnxt_free_port_stats(bp);
 	free_netdev(dev);
 }
 
@@ -9834,7 +10241,7 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 	*max_cp = bnxt_get_max_func_cp_rings_for_en(bp);
 	max_irq = min_t(int, bnxt_get_max_func_irqs(bp) -
 			bnxt_get_ulp_msix_num(bp),
-			bnxt_get_max_func_stat_ctxs(bp));
+			hw_resc->max_stat_ctxs - bnxt_get_ulp_stat_ctxs(bp));
 	if (!(bp->flags & BNXT_FLAG_CHIP_P5))
 		*max_cp = min_t(int, *max_cp, max_irq);
 	max_ring_grps = hw_resc->max_hw_ring_grps;
@@ -9965,7 +10372,6 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh)
 			netdev_warn(bp->dev, "2nd rings reservation failed.\n");
 		bp->tx_nr_rings_per_tc = bp->tx_nr_rings;
 	}
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bp->rx_nr_rings++;
 		bp->cp_nr_rings++;
@@ -10087,7 +10493,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->netdev_ops = &bnxt_netdev_ops;
 	dev->watchdog_timeo = BNXT_TX_TIMEOUT;
 	dev->ethtool_ops = &bnxt_ethtool_ops;
-	SWITCHDEV_SET_OPS(dev, &bnxt_switchdev_ops);
 	pci_set_drvdata(pdev, dev);
 
 	rc = bnxt_alloc_hwrm_resources(bp);
@@ -10099,6 +10504,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
+	if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) {
+		rc = bnxt_alloc_kong_hwrm_resources(bp);
+		if (rc)
+			bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL;
+	}
+
 	if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) ||
 	    bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) {
 		rc = bnxt_alloc_hwrm_short_cmd_req(bp);
@@ -10284,6 +10695,7 @@ init_err_cleanup_tc:
 	bnxt_clear_int_mode(bp);
 
 init_err_pci_clean:
+	bnxt_free_hwrm_short_cmd_req(bp);
 	bnxt_free_hwrm_resources(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3030931ccaf8..cf81ace7a6e6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -22,7 +22,6 @@
 #include <linux/rhashtable.h>
 #include <net/devlink.h>
 #include <net/dst_metadata.h>
-#include <net/switchdev.h>
 #include <net/xdp.h>
 #include <linux/net_dim.h>
 
@@ -567,7 +566,6 @@ struct nqe_cn {
 #define HWRM_RESP_LEN_MASK		0xffff0000
 #define HWRM_RESP_LEN_SFT		16
 #define HWRM_RESP_VALID_MASK		0xff000000
-#define HWRM_SEQ_ID_INVALID		-1
 #define BNXT_HWRM_REQ_MAX_SIZE		128
 #define BNXT_HWRM_REQS_PER_PAGE		(BNXT_PAGE_SIZE /	\
 					 BNXT_HWRM_REQ_MAX_SIZE)
@@ -583,7 +581,10 @@ struct nqe_cn {
 	(HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT +		\
 	 ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT))
 
-#define HWRM_VALID_BIT_DELAY_USEC	20
+#define HWRM_VALID_BIT_DELAY_USEC	150
+
+#define BNXT_HWRM_CHNL_CHIMP	0
+#define BNXT_HWRM_CHNL_KONG	1
 
 #define BNXT_RX_EVENT	1
 #define BNXT_AGG_EVENT	2
@@ -615,9 +616,12 @@ struct bnxt_sw_rx_agg_bd {
 struct bnxt_ring_mem_info {
 	int			nr_pages;
 	int			page_size;
-	u32			flags;
+	u16			flags;
 #define BNXT_RMEM_VALID_PTE_FLAG	1
 #define BNXT_RMEM_RING_PTE_FLAG		2
+#define BNXT_RMEM_USE_FULL_PAGE_FLAG	4
+
+	u16			depth;
 
 	void			**pg_arr;
 	dma_addr_t		*dma_arr;
@@ -927,6 +931,8 @@ struct bnxt_hw_resc {
 	u16	resv_vnics;
 	u16	min_stat_ctxs;
 	u16	max_stat_ctxs;
+	u16	resv_stat_ctxs;
+	u16	max_nqs;
 	u16	max_irqs;
 	u16	resv_irqs;
 };
@@ -939,6 +945,7 @@ struct bnxt_vf_info {
 					 * stored by PF.
 					 */
 	u16	vlan;
+	u16	func_qcfg_flags;
 	u32	flags;
 #define BNXT_VF_QOS		0x1
 #define BNXT_VF_SPOOFCHK	0x2
@@ -1111,9 +1118,14 @@ struct bnxt_test_info {
 	char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
 };
 
-#define BNXT_GRCPF_REG_WINDOW_BASE_OUT	0x400
-#define BNXT_CAG_REG_LEGACY_INT_STATUS	0x4014
-#define BNXT_CAG_REG_BASE		0x300000
+#define BNXT_GRCPF_REG_CHIMP_COMM		0x0
+#define BNXT_GRCPF_REG_CHIMP_COMM_TRIGGER	0x100
+#define BNXT_GRCPF_REG_WINDOW_BASE_OUT		0x400
+#define BNXT_CAG_REG_LEGACY_INT_STATUS		0x4014
+#define BNXT_CAG_REG_BASE			0x300000
+
+#define BNXT_GRCPF_REG_KONG_COMM		0xA00
+#define BNXT_GRCPF_REG_KONG_COMM_TRIGGER	0xB00
 
 struct bnxt_tc_flow_stats {
 	u64		packets;
@@ -1181,12 +1193,15 @@ struct bnxt_vf_rep {
 #define PTU_PTE_NEXT_TO_LAST      0x4UL
 
 #define MAX_CTX_PAGES	(BNXT_PAGE_SIZE / 8)
+#define MAX_CTX_TOTAL_PAGES	(MAX_CTX_PAGES * MAX_CTX_PAGES)
 
 struct bnxt_ctx_pg_info {
 	u32		entries;
+	u32		nr_pages;
 	void		*ctx_pg_arr[MAX_CTX_PAGES];
 	dma_addr_t	ctx_dma_arr[MAX_CTX_PAGES];
 	struct bnxt_ring_mem_info ring_mem;
+	struct bnxt_ctx_pg_info **ctx_pg_tbl;
 };
 
 struct bnxt_ctx_mem_info {
@@ -1222,6 +1237,8 @@ struct bnxt_ctx_mem_info {
 	struct bnxt_ctx_pg_info cq_mem;
 	struct bnxt_ctx_pg_info vnic_mem;
 	struct bnxt_ctx_pg_info stat_mem;
+	struct bnxt_ctx_pg_info mrav_mem;
+	struct bnxt_ctx_pg_info tim_mem;
 	struct bnxt_ctx_pg_info *tqm_mem[9];
 };
 
@@ -1416,8 +1433,6 @@ struct bnxt {
 	int			cp_nr_pages;
 	int			cp_nr_rings;
 
-	int			num_stat_ctxs;
-
 	/* grp_info indexed by completion ring index */
 	struct bnxt_ring_grp_info	*grp_info;
 	struct bnxt_vnic_info	*vnic_info;
@@ -1457,21 +1472,28 @@ struct bnxt {
 	u32			msg_enable;
 
 	u32			fw_cap;
-	#define BNXT_FW_CAP_SHORT_CMD	0x00000001
-	#define BNXT_FW_CAP_LLDP_AGENT	0x00000002
-	#define BNXT_FW_CAP_DCBX_AGENT	0x00000004
-	#define BNXT_FW_CAP_NEW_RM	0x00000008
-	#define BNXT_FW_CAP_IF_CHANGE	0x00000010
+	#define BNXT_FW_CAP_SHORT_CMD			0x00000001
+	#define BNXT_FW_CAP_LLDP_AGENT			0x00000002
+	#define BNXT_FW_CAP_DCBX_AGENT			0x00000004
+	#define BNXT_FW_CAP_NEW_RM			0x00000008
+	#define BNXT_FW_CAP_IF_CHANGE			0x00000010
+	#define BNXT_FW_CAP_KONG_MB_CHNL		0x00000080
+	#define BNXT_FW_CAP_OVS_64BIT_HANDLE		0x00000400
+	#define BNXT_FW_CAP_TRUSTED_VF			0x00000800
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
-	u32			hwrm_intr_seq_id;
+	u16                     hwrm_cmd_kong_seq;
+	u16			hwrm_intr_seq_id;
 	void			*hwrm_short_cmd_req_addr;
 	dma_addr_t		hwrm_short_cmd_req_dma_addr;
 	void			*hwrm_cmd_resp_addr;
 	dma_addr_t		hwrm_cmd_resp_dma_addr;
+	void			*hwrm_cmd_kong_resp_addr;
+	dma_addr_t		hwrm_cmd_kong_resp_dma_addr;
 
+	struct rtnl_link_stats64	net_stats_prev;
 	struct rx_port_stats	*hw_rx_port_stats;
 	struct tx_port_stats	*hw_tx_port_stats;
 	struct rx_port_stats_ext	*hw_rx_port_stats_ext;
@@ -1483,6 +1505,8 @@ struct bnxt {
 	int			hw_port_stats_size;
 	u16			fw_rx_stats_ext_size;
 	u16			fw_tx_stats_ext_size;
+	u8			pri2cos[8];
+	u8			pri2cos_valid;
 
 	u16			hwrm_max_req_len;
 	u16			hwrm_max_ext_req_len;
@@ -1586,6 +1610,7 @@ struct bnxt {
 
 	/* devlink interface and vf-rep structs */
 	struct devlink		*dl;
+	struct devlink_port	dl_port;
 	enum devlink_eswitch_mode eswitch_mode;
 	struct bnxt_vf_rep	**vf_reps; /* array of vf-rep ptrs */
 	u16			*cfa_code_map; /* cfa_code -> vf_idx map */
@@ -1669,6 +1694,66 @@ static inline void bnxt_db_write(struct bnxt *bp, struct bnxt_db_info *db,
 	}
 }
 
+static inline bool bnxt_cfa_hwrm_message(u16 req_type)
+{
+	switch (req_type) {
+	case HWRM_CFA_ENCAP_RECORD_ALLOC:
+	case HWRM_CFA_ENCAP_RECORD_FREE:
+	case HWRM_CFA_DECAP_FILTER_ALLOC:
+	case HWRM_CFA_DECAP_FILTER_FREE:
+	case HWRM_CFA_NTUPLE_FILTER_ALLOC:
+	case HWRM_CFA_NTUPLE_FILTER_FREE:
+	case HWRM_CFA_NTUPLE_FILTER_CFG:
+	case HWRM_CFA_EM_FLOW_ALLOC:
+	case HWRM_CFA_EM_FLOW_FREE:
+	case HWRM_CFA_EM_FLOW_CFG:
+	case HWRM_CFA_FLOW_ALLOC:
+	case HWRM_CFA_FLOW_FREE:
+	case HWRM_CFA_FLOW_INFO:
+	case HWRM_CFA_FLOW_FLUSH:
+	case HWRM_CFA_FLOW_STATS:
+	case HWRM_CFA_METER_PROFILE_ALLOC:
+	case HWRM_CFA_METER_PROFILE_FREE:
+	case HWRM_CFA_METER_PROFILE_CFG:
+	case HWRM_CFA_METER_INSTANCE_ALLOC:
+	case HWRM_CFA_METER_INSTANCE_FREE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline bool bnxt_kong_hwrm_message(struct bnxt *bp, struct input *req)
+{
+	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
+		bnxt_cfa_hwrm_message(le16_to_cpu(req->req_type)));
+}
+
+static inline bool bnxt_hwrm_kong_chnl(struct bnxt *bp, struct input *req)
+{
+	return (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL &&
+		req->resp_addr == cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr));
+}
+
+static inline void *bnxt_get_hwrm_resp_addr(struct bnxt *bp, void *req)
+{
+	if (bnxt_hwrm_kong_chnl(bp, (struct input *)req))
+		return bp->hwrm_cmd_kong_resp_addr;
+	else
+		return bp->hwrm_cmd_resp_addr;
+}
+
+static inline u16 bnxt_get_hwrm_seq_id(struct bnxt *bp, u16 dst)
+{
+	u16 seq_id;
+
+	if (dst == BNXT_HWRM_CHNL_CHIMP)
+		seq_id = bp->hwrm_cmd_seq++;
+	else
+		seq_id = bp->hwrm_cmd_kong_seq++;
+	return seq_id;
+}
+
 extern const u16 bnxt_lhint_arr[];
 
 int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
@@ -1686,11 +1771,12 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 				     int bmap_size);
 int bnxt_hwrm_vnic_cfg(struct bnxt *bp, u16 vnic_id);
 int __bnxt_hwrm_get_tx_rings(struct bnxt *bp, u16 fid, int *tx_rings);
+int bnxt_nq_rings_in_use(struct bnxt *bp);
 int bnxt_hwrm_set_coal(struct bnxt *);
 unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp);
-void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max);
+unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp);
 unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp);
-unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp);
+unsigned int bnxt_get_avail_cp_rings_for_en(struct bnxt *bp);
 int bnxt_get_avail_msix(struct bnxt *bp, int num);
 int bnxt_reserve_rings(struct bnxt *bp);
 void bnxt_tx_disable(struct bnxt *bp);
@@ -1710,7 +1796,8 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 int bnxt_setup_mq_tc(struct net_device *dev, u8 tc);
 int bnxt_get_max_rings(struct bnxt *, int *, int *, bool);
 int bnxt_restore_pf_fw_resources(struct bnxt *bp);
-int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr);
+int bnxt_get_port_parent_id(struct net_device *dev,
+			    struct netdev_phys_item_id *ppid);
 void bnxt_dim_work(struct work_struct *work);
 int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index a85d2be986af..70775158c8c4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -316,8 +316,8 @@ static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app,
 
 	n = IEEE_8021QAZ_MAX_TCS;
 	data_len = sizeof(*data) + sizeof(*fw_app) * n;
-	data = dma_zalloc_coherent(&bp->pdev->dev, data_len, &mapping,
-				   GFP_KERNEL);
+	data = dma_alloc_coherent(&bp->pdev->dev, data_len, &mapping,
+				  GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
@@ -471,7 +471,10 @@ static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 	if (total_ets_bw > 100)
 		return -EINVAL;
 
-	*tc = max_tc + 1;
+	if (max_tc >= bp->max_tc)
+		*tc = bp->max_tc;
+	else
+		*tc = max_tc + 1;
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 140dbd62106d..e1feb97bcd81 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -85,8 +85,8 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 		return -EFAULT;
 	}
 
-	data_addr = dma_zalloc_coherent(&bp->pdev->dev, bytesize,
-					&data_dma_addr, GFP_KERNEL);
+	data_addr = dma_alloc_coherent(&bp->pdev->dev, bytesize,
+				       &data_dma_addr, GFP_KERNEL);
 	if (!data_addr)
 		return -ENOMEM;
 
@@ -188,6 +188,9 @@ static const struct devlink_param bnxt_dl_params[] = {
 			     NULL),
 };
 
+static const struct devlink_param bnxt_dl_port_params[] = {
+};
+
 int bnxt_dl_register(struct bnxt *bp)
 {
 	struct devlink *dl;
@@ -225,8 +228,29 @@ int bnxt_dl_register(struct bnxt *bp)
 		goto err_dl_unreg;
 	}
 
+	rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id);
+	if (rc) {
+		netdev_err(bp->dev, "devlink_port_register failed");
+		goto err_dl_param_unreg;
+	}
+	devlink_port_type_eth_set(&bp->dl_port, bp->dev);
+
+	rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params,
+					  ARRAY_SIZE(bnxt_dl_port_params));
+	if (rc) {
+		netdev_err(bp->dev, "devlink_port_params_register failed");
+		goto err_dl_port_unreg;
+	}
+
+	devlink_params_publish(dl);
+
 	return 0;
 
+err_dl_port_unreg:
+	devlink_port_unregister(&bp->dl_port);
+err_dl_param_unreg:
+	devlink_params_unregister(dl, bnxt_dl_params,
+				  ARRAY_SIZE(bnxt_dl_params));
 err_dl_unreg:
 	devlink_unregister(dl);
 err_dl_free:
@@ -242,6 +266,9 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
+	devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params,
+				       ARRAY_SIZE(bnxt_dl_port_params));
+	devlink_port_unregister(&bp->dl_port);
 	devlink_params_unregister(dl, bnxt_dl_params,
 				  ARRAY_SIZE(bnxt_dl_params));
 	devlink_unregister(dl);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 6b51f4de6017..adabbe94a259 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -207,6 +207,34 @@ reset_coalesce:
 	BNXT_TX_STATS_EXT_COS_ENTRY(6),				\
 	BNXT_TX_STATS_EXT_COS_ENTRY(7)				\
 
+#define BNXT_RX_STATS_PRI_ENTRY(counter, n)		\
+	{ BNXT_RX_STATS_EXT_OFFSET(counter##_cos0),	\
+	  __stringify(counter##_pri##n) }
+
+#define BNXT_TX_STATS_PRI_ENTRY(counter, n)		\
+	{ BNXT_TX_STATS_EXT_OFFSET(counter##_cos0),	\
+	  __stringify(counter##_pri##n) }
+
+#define BNXT_RX_STATS_PRI_ENTRIES(counter)		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 0),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 1),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 2),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 3),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 4),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 5),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 6),		\
+	BNXT_RX_STATS_PRI_ENTRY(counter, 7)
+
+#define BNXT_TX_STATS_PRI_ENTRIES(counter)		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 0),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 1),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 2),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 3),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 4),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 5),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 6),		\
+	BNXT_TX_STATS_PRI_ENTRY(counter, 7)
+
 enum {
 	RX_TOTAL_DISCARDS,
 	TX_TOTAL_DISCARDS,
@@ -327,8 +355,41 @@ static const struct {
 	BNXT_TX_STATS_EXT_PFC_ENTRIES,
 };
 
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_rx_bytes_pri_arr[] = {
+	BNXT_RX_STATS_PRI_ENTRIES(rx_bytes),
+};
+
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_rx_pkts_pri_arr[] = {
+	BNXT_RX_STATS_PRI_ENTRIES(rx_packets),
+};
+
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_tx_bytes_pri_arr[] = {
+	BNXT_TX_STATS_PRI_ENTRIES(tx_bytes),
+};
+
+static const struct {
+	long base_off;
+	char string[ETH_GSTRING_LEN];
+} bnxt_tx_pkts_pri_arr[] = {
+	BNXT_TX_STATS_PRI_ENTRIES(tx_packets),
+};
+
 #define BNXT_NUM_SW_FUNC_STATS	ARRAY_SIZE(bnxt_sw_func_stats)
 #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr)
+#define BNXT_NUM_STATS_PRI			\
+	(ARRAY_SIZE(bnxt_rx_bytes_pri_arr) +	\
+	 ARRAY_SIZE(bnxt_rx_pkts_pri_arr) +	\
+	 ARRAY_SIZE(bnxt_tx_bytes_pri_arr) +	\
+	 ARRAY_SIZE(bnxt_tx_pkts_pri_arr))
 
 static int bnxt_get_num_stats(struct bnxt *bp)
 {
@@ -339,9 +400,12 @@ static int bnxt_get_num_stats(struct bnxt *bp)
 	if (bp->flags & BNXT_FLAG_PORT_STATS)
 		num_stats += BNXT_NUM_PORT_STATS;
 
-	if (bp->flags & BNXT_FLAG_PORT_STATS_EXT)
+	if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) {
 		num_stats += bp->fw_rx_stats_ext_size +
 			     bp->fw_tx_stats_ext_size;
+		if (bp->pri2cos_valid)
+			num_stats += BNXT_NUM_STATS_PRI;
+	}
 
 	return num_stats;
 }
@@ -369,8 +433,10 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 	struct bnxt *bp = netdev_priv(dev);
 	u32 stat_fields = sizeof(struct ctx_hw_stats) / 8;
 
-	if (!bp->bnapi)
-		return;
+	if (!bp->bnapi) {
+		j += BNXT_NUM_STATS * bp->cp_nr_rings + BNXT_NUM_SW_FUNC_STATS;
+		goto skip_ring_stats;
+	}
 
 	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++)
 		bnxt_sw_func_stats[i].counter = 0;
@@ -395,6 +461,7 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++)
 		buf[j] = bnxt_sw_func_stats[i].counter;
 
+skip_ring_stats:
 	if (bp->flags & BNXT_FLAG_PORT_STATS) {
 		__le64 *port_stats = (__le64 *)bp->hw_rx_port_stats;
 
@@ -415,6 +482,32 @@ static void bnxt_get_ethtool_stats(struct net_device *dev,
 			buf[j] = le64_to_cpu(*(tx_port_stats_ext +
 					bnxt_tx_port_stats_ext_arr[i].offset));
 		}
+		if (bp->pri2cos_valid) {
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_rx_bytes_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
+			}
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_rx_pkts_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(rx_port_stats_ext + n));
+			}
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_tx_bytes_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
+			}
+			for (i = 0; i < 8; i++, j++) {
+				long n = bnxt_tx_pkts_pri_arr[i].base_off +
+					 bp->pri2cos[i];
+
+				buf[j] = le64_to_cpu(*(tx_port_stats_ext + n));
+			}
+		}
 	}
 }
 
@@ -493,6 +586,28 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
 				       bnxt_tx_port_stats_ext_arr[i].string);
 				buf += ETH_GSTRING_LEN;
 			}
+			if (bp->pri2cos_valid) {
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_rx_bytes_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_rx_pkts_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_tx_bytes_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+				for (i = 0; i < 8; i++) {
+					strcpy(buf,
+					       bnxt_tx_pkts_pri_arr[i].string);
+					buf += ETH_GSTRING_LEN;
+				}
+			}
 		}
 		break;
 	case ETH_SS_TEST:
@@ -663,8 +778,6 @@ static int bnxt_set_channels(struct net_device *dev,
 	bp->cp_nr_rings = sh ? max_t(int, bp->tx_nr_rings, bp->rx_nr_rings) :
 			       bp->tx_nr_rings + bp->rx_nr_rings;
 
-	bp->num_stat_ctxs = bp->cp_nr_rings;
-
 	/* After changing number of rx channels, update NTUPLE feature. */
 	netdev_update_features(dev);
 	if (netif_running(dev)) {
@@ -1526,14 +1639,22 @@ static int bnxt_flash_nvram(struct net_device *dev,
 	rc = hwrm_send_message(bp, &req, sizeof(req), FLASH_NVRAM_TIMEOUT);
 	dma_free_coherent(&bp->pdev->dev, data_len, kmem, dma_handle);
 
+	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to flash the device\n");
+		rc = -EACCES;
+	} else if (rc) {
+		rc = -EIO;
+	}
 	return rc;
 }
 
 static int bnxt_firmware_reset(struct net_device *dev,
 			       u16 dir_type)
 {
-	struct bnxt *bp = netdev_priv(dev);
 	struct hwrm_fw_reset_input req = {0};
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1);
 
@@ -1573,7 +1694,15 @@ static int bnxt_firmware_reset(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to reset the device\n");
+		rc = -EACCES;
+	} else if (rc) {
+		rc = -EIO;
+	}
+	return rc;
 }
 
 static int bnxt_flash_firmware(struct net_device *dev,
@@ -1780,9 +1909,9 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	struct hwrm_nvm_install_update_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_nvm_install_update_input install = {0};
 	const struct firmware *fw;
+	int rc, hwrm_err = 0;
 	u32 item_len;
 	u16 index;
-	int rc;
 
 	bnxt_hwrm_fw_set_time(bp);
 
@@ -1825,15 +1954,16 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 			memcpy(kmem, fw->data, fw->size);
 			modify.host_src_addr = cpu_to_le64(dma_handle);
 
-			rc = hwrm_send_message(bp, &modify, sizeof(modify),
-					       FLASH_PACKAGE_TIMEOUT);
+			hwrm_err = hwrm_send_message(bp, &modify,
+						     sizeof(modify),
+						     FLASH_PACKAGE_TIMEOUT);
 			dma_free_coherent(&bp->pdev->dev, fw->size, kmem,
 					  dma_handle);
 		}
 	}
 	release_firmware(fw);
-	if (rc)
-		return rc;
+	if (rc || hwrm_err)
+		goto err_exit;
 
 	if ((install_type & 0xffff) == 0)
 		install_type >>= 16;
@@ -1841,12 +1971,10 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	install.install_type = cpu_to_le32(install_type);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
-	rc = _hwrm_send_message(bp, &install, sizeof(install),
-				INSTALL_PACKAGE_TIMEOUT);
-	if (rc) {
-		rc = -EOPNOTSUPP;
+	hwrm_err = _hwrm_send_message(bp, &install, sizeof(install),
+				      INSTALL_PACKAGE_TIMEOUT);
+	if (hwrm_err)
 		goto flash_pkg_exit;
-	}
 
 	if (resp->error_code) {
 		u8 error_code = ((struct hwrm_err_output *)resp)->cmd_err;
@@ -1854,12 +1982,11 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 		if (error_code == NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR) {
 			install.flags |= cpu_to_le16(
 			       NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG);
-			rc = _hwrm_send_message(bp, &install, sizeof(install),
-						INSTALL_PACKAGE_TIMEOUT);
-			if (rc) {
-				rc = -EOPNOTSUPP;
+			hwrm_err = _hwrm_send_message(bp, &install,
+						      sizeof(install),
+						      INSTALL_PACKAGE_TIMEOUT);
+			if (hwrm_err)
 				goto flash_pkg_exit;
-			}
 		}
 	}
 
@@ -1870,6 +1997,14 @@ static int bnxt_flash_package_from_file(struct net_device *dev,
 	}
 flash_pkg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
+err_exit:
+	if (hwrm_err == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) {
+		netdev_info(dev,
+			    "PF does not have admin privileges to flash the device\n");
+		rc = -EACCES;
+	} else if (hwrm_err) {
+		rc = -EOPNOTSUPP;
+	}
 	return rc;
 }
 
@@ -2450,17 +2585,37 @@ static int bnxt_hwrm_mac_loopback(struct bnxt *bp, bool enable)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+static int bnxt_query_force_speeds(struct bnxt *bp, u16 *force_speeds)
+{
+	struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_port_phy_qcaps_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_QCAPS, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc)
+		*force_speeds = le16_to_cpu(resp->supported_speeds_force_mode);
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
 static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 				    struct hwrm_port_phy_cfg_input *req)
 {
 	struct bnxt_link_info *link_info = &bp->link_info;
-	u16 fw_advertising = link_info->advertising;
+	u16 fw_advertising;
 	u16 fw_speed;
 	int rc;
 
 	if (!link_info->autoneg)
 		return 0;
 
+	rc = bnxt_query_force_speeds(bp, &fw_advertising);
+	if (rc)
+		return rc;
+
 	fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB;
 	if (netif_carrier_ok(bp->dev))
 		fw_speed = bp->link_info.link_speed;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 5dd086059568..b6c610339501 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -1,7 +1,7 @@
 /* Broadcom NetXtreme-C/E network driver.
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
- * Copyright (c) 2016-2018 Broadcom Limited
+ * Copyright (c) 2016-2019 Broadcom Limited
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -98,6 +98,7 @@ struct hwrm_short_input {
 struct cmd_nums {
 	__le16	req_type;
 	#define HWRM_VER_GET                              0x0UL
+	#define HWRM_ERROR_RECOVERY_QCFG                  0xcUL
 	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
 	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
 	#define HWRM_FUNC_VF_CFG                          0xfUL
@@ -194,6 +195,8 @@ struct cmd_nums {
 	#define HWRM_STAT_CTX_QUERY                       0xb2UL
 	#define HWRM_STAT_CTX_CLR_STATS                   0xb3UL
 	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
+	#define HWRM_PORT_PHY_MDIO_WRITE                  0xb5UL
+	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
 	#define HWRM_FW_RESET                             0xc0UL
 	#define HWRM_FW_QSTATUS                           0xc1UL
 	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
@@ -213,11 +216,13 @@ struct cmd_nums {
 	#define HWRM_WOL_FILTER_FREE                      0xf1UL
 	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
 	#define HWRM_WOL_REASON_QCFG                      0xf3UL
+	#define HWRM_CFA_METER_QCAPS                      0xf4UL
 	#define HWRM_CFA_METER_PROFILE_ALLOC              0xf5UL
 	#define HWRM_CFA_METER_PROFILE_FREE               0xf6UL
 	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
 	#define HWRM_CFA_METER_INSTANCE_ALLOC             0xf8UL
 	#define HWRM_CFA_METER_INSTANCE_FREE              0xf9UL
+	#define HWRM_CFA_METER_INSTANCE_CFG               0xfaUL
 	#define HWRM_CFA_VFR_ALLOC                        0xfdUL
 	#define HWRM_CFA_VFR_FREE                         0xfeUL
 	#define HWRM_CFA_VF_PAIR_ALLOC                    0x100UL
@@ -239,6 +244,24 @@ struct cmd_nums {
 	#define HWRM_FW_IPC_MSG                           0x110UL
 	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_INFO        0x111UL
 	#define HWRM_CFA_REDIRECT_QUERY_TUNNEL_TYPE       0x112UL
+	#define HWRM_CFA_FLOW_AGING_TIMER_RESET           0x113UL
+	#define HWRM_CFA_FLOW_AGING_CFG                   0x114UL
+	#define HWRM_CFA_FLOW_AGING_QCFG                  0x115UL
+	#define HWRM_CFA_FLOW_AGING_QCAPS                 0x116UL
+	#define HWRM_CFA_CTX_MEM_RGTR                     0x117UL
+	#define HWRM_CFA_CTX_MEM_UNRGTR                   0x118UL
+	#define HWRM_CFA_CTX_MEM_QCTX                     0x119UL
+	#define HWRM_CFA_CTX_MEM_QCAPS                    0x11aUL
+	#define HWRM_CFA_COUNTER_QCAPS                    0x11bUL
+	#define HWRM_CFA_COUNTER_CFG                      0x11cUL
+	#define HWRM_CFA_COUNTER_QCFG                     0x11dUL
+	#define HWRM_CFA_COUNTER_QSTATS                   0x11eUL
+	#define HWRM_CFA_TCP_FLAG_PROCESS_QCFG            0x11fUL
+	#define HWRM_CFA_EEM_QCAPS                        0x120UL
+	#define HWRM_CFA_EEM_CFG                          0x121UL
+	#define HWRM_CFA_EEM_QCFG                         0x122UL
+	#define HWRM_CFA_EEM_OP                           0x123UL
+	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
 	#define HWRM_ENGINE_CKV_HELLO                     0x12dUL
 	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
 	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
@@ -248,6 +271,7 @@ struct cmd_nums {
 	#define HWRM_ENGINE_CKV_FLUSH                     0x133UL
 	#define HWRM_ENGINE_CKV_RNG_GET                   0x134UL
 	#define HWRM_ENGINE_CKV_KEY_GEN                   0x135UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_CFG             0x136UL
 	#define HWRM_ENGINE_QG_CONFIG_QUERY               0x13cUL
 	#define HWRM_ENGINE_QG_QUERY                      0x13dUL
 	#define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL
@@ -275,6 +299,7 @@ struct cmd_nums {
 	#define HWRM_ENGINE_NQ_ALLOC                      0x162UL
 	#define HWRM_ENGINE_NQ_FREE                       0x163UL
 	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
+	#define HWRM_ENGINE_FUNC_QCFG                     0x165UL
 	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
 	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
 	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
@@ -335,6 +360,8 @@ struct ret_codes {
 	#define HWRM_ERR_CODE_UNSUPPORTED_TLV           0x7UL
 	#define HWRM_ERR_CODE_NO_BUFFER                 0x8UL
 	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR    0x9UL
+	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS        0xaUL
+	#define HWRM_ERR_CODE_HOT_RESET_FAIL            0xbUL
 	#define HWRM_ERR_CODE_HWRM_ERROR                0xfUL
 	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE 0x8000UL
 	#define HWRM_ERR_CODE_UNKNOWN_ERR               0xfffeUL
@@ -356,15 +383,15 @@ struct hwrm_err_output {
 };
 #define HWRM_NA_SIGNATURE ((__le32)(-1))
 #define HWRM_MAX_REQ_LEN 128
-#define HWRM_MAX_RESP_LEN 280
+#define HWRM_MAX_RESP_LEN 704
 #define HW_HASH_INDEX_SIZE 0x80
 #define HW_HASH_KEY_SIZE 40
 #define HWRM_RESP_VALID_KEY 1
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 0
-#define HWRM_VERSION_RSVD 3
-#define HWRM_VERSION_STR "1.10.0.3"
+#define HWRM_VERSION_RSVD 47
+#define HWRM_VERSION_STR "1.10.0.47"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -411,6 +438,10 @@ struct hwrm_ver_get_output {
 	#define VER_GET_RESP_DEV_CAPS_CFG_L2_FILTER_TYPES_ROCE_OR_L2_SUPPORTED     0x40UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_VIRTIO_VSWITCH_OFFLOAD_SUPPORTED         0x80UL
 	#define VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED                     0x100UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_AGING_SUPPORTED                     0x200UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
 	u8	roce_fw_maj_8b;
 	u8	roce_fw_min_8b;
 	u8	roce_fw_bld_8b;
@@ -465,14 +496,27 @@ struct hwrm_ver_get_output {
 /* eject_cmpl (size:128b/16B) */
 struct eject_cmpl {
 	__le16	type;
-	#define EJECT_CMPL_TYPE_MASK      0x3fUL
-	#define EJECT_CMPL_TYPE_SFT       0
-	#define EJECT_CMPL_TYPE_STAT_EJECT  0x1aUL
-	#define EJECT_CMPL_TYPE_LAST       EJECT_CMPL_TYPE_STAT_EJECT
+	#define EJECT_CMPL_TYPE_MASK       0x3fUL
+	#define EJECT_CMPL_TYPE_SFT        0
+	#define EJECT_CMPL_TYPE_STAT_EJECT   0x1aUL
+	#define EJECT_CMPL_TYPE_LAST        EJECT_CMPL_TYPE_STAT_EJECT
+	#define EJECT_CMPL_FLAGS_MASK      0xffc0UL
+	#define EJECT_CMPL_FLAGS_SFT       6
+	#define EJECT_CMPL_FLAGS_ERROR      0x40UL
 	__le16	len;
 	__le32	opaque;
-	__le32	v;
-	#define EJECT_CMPL_V     0x1UL
+	__le16	v;
+	#define EJECT_CMPL_V                              0x1UL
+	#define EJECT_CMPL_ERRORS_MASK                    0xfffeUL
+	#define EJECT_CMPL_ERRORS_SFT                     1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_MASK        0xeUL
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_SFT         1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER     (0x0UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT   (0x1UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT    (0x3UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH         (0x5UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_LAST         EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH
+	__le16	reserved16;
 	__le32	unused_2;
 };
 
@@ -540,6 +584,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE      0x6UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE        0x7UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY               0x8UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY             0x9UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD           0x10UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD             0x11UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT        0x12UL
@@ -552,6 +597,13 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE            0x34UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE        0x35UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_FLOW_AGED               0x36UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION         0x37UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ        0x38UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE       0x39UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE     0x3aUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE            0x3bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE             0x3cUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG               0xfeUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                 0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                      ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
 	__le32	event_data2;
@@ -647,6 +699,63 @@ struct hwrm_async_event_cmpl_link_speed_cfg_change {
 	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_ILLEGAL_LINK_SPEED_CFG           0x20000UL
 };
 
+/* hwrm_async_event_cmpl_reset_notify (size:128b/16B) */
+struct hwrm_async_event_cmpl_reset_notify {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_LAST             ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY 0x8UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_LAST        ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_MASK                  0xffUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_SFT                   0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_STOP_TX_QUEUE    0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN           0x2UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_LAST                   ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK                    0xff00UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_SFT                     8
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MANAGEMENT_RESET_REQUEST  (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL        (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL    (0x3UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST                     ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK           0xffff0000UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
+};
+
+/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_recovery {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST          ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK                 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT                  0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC           0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
+};
+
 /* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
 struct hwrm_async_event_cmpl_vf_cfg_change {
 	__le16	type;
@@ -672,6 +781,74 @@ struct hwrm_async_event_cmpl_vf_cfg_change {
 	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE     0x10UL
 };
 
+/* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */
+struct hwrm_async_event_cmpl_hw_flow_aged {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_LAST             ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED 0x36UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_MASK       0x7fffffffUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_SFT        0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION     0x80000000UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_RX    (0x0UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX    (0x1UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_LAST ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_req (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_req {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_LAST               ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_done (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_done {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_LAST                ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
+};
+
 /* hwrm_func_reset_input (size:192b/24B) */
 struct hwrm_func_reset_input {
 	__le16	req_type;
@@ -867,6 +1044,9 @@ struct hwrm_func_qcaps_output {
 	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED              0x40000UL
 	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED     0x80000UL
 	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                   0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC           0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE               0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE          0x800000UL
 	u8	mac_address[6];
 	__le16	max_rsscos_ctx;
 	__le16	max_cmpl_rings;
@@ -902,7 +1082,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:640b/80B) */
+/* hwrm_func_qcfg_output (size:704b/88B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -919,6 +1099,7 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED        0x10UL
 	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST                   0x20UL
 	#define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF                   0x40UL
+	#define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED          0x80UL
 	u8	mac_address[6];
 	__le16	pci_id;
 	__le16	alloc_rsscos_ctx;
@@ -1000,7 +1181,11 @@ struct hwrm_func_qcfg_output {
 	__le16	alloc_sp_tx_rings;
 	__le16	alloc_stat_ctx;
 	__le16	alloc_msix;
-	u8	unused_2[5];
+	__le16	registered_vfs;
+	u8	unused_1[3];
+	u8	always_1;
+	__le32	reset_addr_poll;
+	u8	unused_2[3];
 	u8	valid;
 };
 
@@ -1031,6 +1216,9 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST               0x80000UL
 	#define FUNC_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST             0x100000UL
 	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
+	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
+	#define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST                 0x800000UL
+	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE             0x1000000UL
 	__le32	enables;
 	#define FUNC_CFG_REQ_ENABLES_MTU                     0x1UL
 	#define FUNC_CFG_REQ_ENABLES_MRU                     0x2UL
@@ -1235,6 +1423,8 @@ struct hwrm_func_drv_rgtr_input {
 	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE              0x2UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE             0x4UL
 	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE     0x8UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT          0x10UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT     0x20UL
 	__le32	enables;
 	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
 	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
@@ -1869,6 +2059,89 @@ struct hwrm_func_backing_store_cfg_output {
 	u8	valid;
 };
 
+/* hwrm_error_recovery_qcfg_input (size:192b/24B) */
+struct hwrm_error_recovery_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */
+struct hwrm_error_recovery_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU     0x2UL
+	__le32	driver_polling_freq;
+	__le32	master_func_wait_period;
+	__le32	normal_func_wait_period;
+	__le32	master_func_wait_period_after_reset;
+	__le32	max_bailout_time_after_reset;
+	__le32	fw_health_status_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT           2
+	__le32	fw_heartbeat_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT           2
+	__le32	fw_reset_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg_mask;
+	u8	unused_0[3];
+	u8	reg_array_cnt;
+	__le32	reset_reg[16];
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
+	__le32	reset_reg_val[16];
+	u8	delay_after_reset[16];
+	u8	unused_1[7];
+	u8	valid;
+};
+
 /* hwrm_func_drv_if_change_input (size:192b/24B) */
 struct hwrm_func_drv_if_change_input {
 	__le16	req_type;
@@ -1888,7 +2161,8 @@ struct hwrm_func_drv_if_change_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	__le32	flags;
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE     0x1UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
 	u8	unused_0[3];
 	u8	valid;
 };
@@ -2799,6 +3073,7 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB       0x800UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD      0x1000UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB        0x2000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_200GB       0x4000UL
 	__le16	supported_speeds_auto_mode;
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD     0x1UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB       0x2UL
@@ -2814,6 +3089,7 @@ struct hwrm_port_phy_qcaps_output {
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB       0x800UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD      0x1000UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB        0x2000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_200GB       0x4000UL
 	__le16	supported_speeds_eee_mode;
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1     0x1UL
 	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB     0x2UL
@@ -2864,6 +3140,60 @@ struct hwrm_port_phy_i2c_read_output {
 	u8	valid;
 };
 
+/* hwrm_port_phy_mdio_write_input (size:320b/40B) */
+struct hwrm_port_phy_mdio_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	__le16	reg_data;
+	u8	cl45_mdio;
+	u8	unused_1[7];
+};
+
+/* hwrm_port_phy_mdio_write_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_mdio_read_input (size:256b/32B) */
+struct hwrm_port_phy_mdio_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	u8	cl45_mdio;
+	u8	unused_1;
+};
+
+/* hwrm_port_phy_mdio_read_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	reg_data;
+	u8	unused_0[5];
+	u8	valid;
+};
+
 /* hwrm_port_led_cfg_input (size:512b/64B) */
 struct hwrm_port_led_cfg_input {
 	__le16	req_type;
@@ -4709,6 +5039,35 @@ struct hwrm_ring_free_output {
 	u8	valid;
 };
 
+/* hwrm_ring_reset_input (size:192b/24B) */
+struct hwrm_ring_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define RING_RESET_REQ_RING_TYPE_L2_CMPL   0x0UL
+	#define RING_RESET_REQ_RING_TYPE_TX        0x1UL
+	#define RING_RESET_REQ_RING_TYPE_RX        0x2UL
+	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL 0x3UL
+	#define RING_RESET_REQ_RING_TYPE_LAST     RING_RESET_REQ_RING_TYPE_ROCE_CMPL
+	u8	unused_0;
+	__le16	ring_id;
+	u8	unused_1[4];
+};
+
+/* hwrm_ring_reset_output (size:128b/16B) */
+struct hwrm_ring_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[4];
+	u8	consumer_idx[3];
+	u8	valid;
+};
+
 /* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
 struct hwrm_ring_aggint_qcaps_input {
 	__le16	req_type;
@@ -4869,6 +5228,10 @@ struct hwrm_ring_grp_free_output {
 	u8	unused_0[7];
 	u8	valid;
 };
+#define DEFAULT_FLOW_ID 0xFFFFFFFFUL
+#define ROCEV1_FLOW_ID 0xFFFFFFFEUL
+#define ROCEV2_FLOW_ID 0xFFFFFFFDUL
+#define ROCEV2_CNP_FLOW_ID 0xFFFFFFFCUL
 
 /* hwrm_cfa_l2_filter_alloc_input (size:768b/96B) */
 struct hwrm_cfa_l2_filter_alloc_input {
@@ -4937,20 +5300,21 @@ struct hwrm_cfa_l2_filter_alloc_input {
 	u8	unused_3;
 	__le32	src_id;
 	u8	tunnel_type;
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	unused_4;
 	__le16	dst_id;
 	__le16	mirror_vnic_id;
@@ -5108,20 +5472,21 @@ struct hwrm_cfa_tunnel_filter_alloc_input {
 	u8	l3_addr_type;
 	u8	t_l3_addr_type;
 	u8	tunnel_type;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	tunnel_flags;
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_OAM_CHECKSUM_EXPLHDR     0x1UL
 	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_CRITICAL_OPT_S1          0x2UL
@@ -5230,19 +5595,21 @@ struct hwrm_cfa_encap_record_alloc_input {
 	__le64	resp_addr;
 	__le32	flags;
 	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL     0x2UL
 	u8	encap_type;
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN    0x1UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE    0x2UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE    0x3UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP     0x4UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE   0x5UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS     0x6UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN     0x7UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE    0x8UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4 0x9UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1 0xaUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE 0xbUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST    CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN        0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE        0x2UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE        0x3UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP         0x4UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE       0x5UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS         0x6UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN         0x7UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE        0x8UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4     0x9UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1     0xaUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE     0xbUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST        CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6
 	u8	unused_0[3];
 	__le32	encap_data[20];
 };
@@ -5290,6 +5657,7 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP         0x2UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER        0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID     0x8UL
 	__le32	enables;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID         0x1UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE            0x2UL
@@ -5326,20 +5694,21 @@ struct hwrm_cfa_ntuple_filter_alloc_input {
 	__le16	dst_id;
 	__le16	mirror_vnic_id;
 	u8	tunnel_type;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	pri_hint;
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER 0x0UL
 	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE     0x1UL
@@ -5410,7 +5779,8 @@ struct hwrm_cfa_ntuple_filter_cfg_input {
 	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID                0x1UL
 	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID        0x2UL
 	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID     0x4UL
-	u8	unused_0[4];
+	__le32	flags;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID     0x1UL
 	__le64	ntuple_filter_id;
 	__le32	new_dst_id;
 	__le32	new_mirror_vnic_id;
@@ -5459,20 +5829,21 @@ struct hwrm_cfa_decap_filter_alloc_input {
 	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x10000UL
 	__be32	tunnel_id;
 	u8	tunnel_type;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 	u8	unused_0;
 	__le16	unused_1;
 	u8	src_macaddr[6];
@@ -5559,20 +5930,23 @@ struct hwrm_cfa_flow_alloc_input {
 	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_TX                0x40UL
 	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_RX                0x80UL
 	#define CFA_FLOW_ALLOC_REQ_FLAGS_MATCH_VXLAN_IP_VNI     0x100UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_VHOST_ID_USE_VLAN      0x200UL
 	__le16	src_fid;
 	__le32	tunnel_handle;
 	__le16	action_flags;
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                   0x1UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE               0x2UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                  0x4UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                 0x8UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                0x10UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC               0x20UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST              0x40UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS      0x80UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE     0x100UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT         0x200UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP             0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                    0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                   0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                  0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                 0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST               0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS       0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE      0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT          0x200UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP              0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED     0x800UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT               0x1000UL
 	__le16	dst_fid;
 	__be16	l2_rewrite_vlan_tpid;
 	__be16	l2_rewrite_vlan_tci;
@@ -5597,20 +5971,21 @@ struct hwrm_cfa_flow_alloc_input {
 	__be16	l2_rewrite_smac[3];
 	u8	ip_proto;
 	u8	tunnel_type;
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL 0x0UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN     0x1UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE     0x2UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE     0x3UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP      0x4UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE    0x5UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS      0x6UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT       0x7UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE     0x8UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4  0x9UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1  0xaUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE  0xbUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL 0xffUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST     CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
 };
 
 /* hwrm_cfa_flow_alloc_output (size:256b/32B) */
@@ -5623,7 +5998,8 @@ struct hwrm_cfa_flow_alloc_output {
 	u8	unused_0[2];
 	__le32	flow_id;
 	__le64	ext_flow_handle;
-	u8	unused_1[7];
+	__le32	flow_counter_id;
+	u8	unused_1[3];
 	u8	valid;
 };
 
@@ -5651,6 +6027,51 @@ struct hwrm_cfa_flow_free_output {
 	u8	valid;
 };
 
+/* hwrm_cfa_flow_info_input (size:256b/32B) */
+struct hwrm_cfa_flow_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flow_handle;
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK       0xfffUL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_SFT        0
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT        0x1000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT     0x2000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT     0x4000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX         0x8000UL
+	u8	unused_0[6];
+	__le64	ext_flow_handle;
+};
+
+/* hwrm_cfa_flow_info_output (size:5632b/704B) */
+struct hwrm_cfa_flow_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX     0x1UL
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX     0x2UL
+	u8	profile;
+	__le16	src_fid;
+	__le16	dst_fid;
+	__le16	l2_ctxt_id;
+	__le64	em_info;
+	__le64	tcam_info;
+	__le64	vfp_tcam_info;
+	__le16	ar_id;
+	__le16	flow_handle;
+	__le32	tunnel_handle;
+	__le16	flow_timer;
+	u8	unused_0[6];
+	__le32	flow_key_data[130];
+	__le32	flow_action_info[30];
+	u8	unused_1[7];
+	u8	valid;
+};
+
 /* hwrm_cfa_flow_stats_input (size:640b/80B) */
 struct hwrm_cfa_flow_stats_input {
 	__le16	req_type;
@@ -5757,6 +6178,128 @@ struct hwrm_cfa_vfr_free_output {
 	u8	valid;
 };
 
+/* hwrm_cfa_eem_qcaps_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcaps_output (size:256b/32B) */
+struct hwrm_cfa_eem_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX     0x2UL
+	__le32	unused_0;
+	__le32	supported;
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE                       0x2UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE            0x4UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE     0x8UL
+	__le32	max_entries_supported;
+	__le16	key_entry_size;
+	__le16	record_entry_size;
+	__le16	efc_entry_size;
+	u8	unused_1;
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_cfg_input (size:320b/40B) */
+struct hwrm_cfa_eem_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	unused_0;
+	__le32	num_entries;
+	__le32	unused_1;
+	__le16	key0_ctx_id;
+	__le16	key1_ctx_id;
+	__le16	record_ctx_id;
+	__le16	efc_ctx_id;
+};
+
+/* hwrm_cfa_eem_cfg_output (size:128b/16B) */
+struct hwrm_cfa_eem_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_qcfg_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_RX     0x2UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcfg_output (size:128b/16B) */
+struct hwrm_cfa_eem_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	num_entries;
+};
+
+/* hwrm_cfa_eem_op_input (size:192b/24B) */
+struct hwrm_cfa_eem_op_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_RX     0x2UL
+	__le16	unused_0;
+	__le16	op;
+	#define CFA_EEM_OP_REQ_OP_RESERVED    0x0UL
+	#define CFA_EEM_OP_REQ_OP_EEM_DISABLE 0x1UL
+	#define CFA_EEM_OP_REQ_OP_EEM_ENABLE  0x2UL
+	#define CFA_EEM_OP_REQ_OP_EEM_CLEANUP 0x3UL
+	#define CFA_EEM_OP_REQ_OP_LAST       CFA_EEM_OP_REQ_OP_EEM_CLEANUP
+};
+
+/* hwrm_cfa_eem_op_output (size:128b/16B) */
+struct hwrm_cfa_eem_op_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
 /* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
 struct hwrm_tunnel_dst_port_query_input {
 	__le16	req_type;
@@ -5765,12 +6308,13 @@ struct hwrm_tunnel_dst_port_query_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN    0x1UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE   0x5UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6
 	u8	unused_0[7];
 };
 
@@ -5794,12 +6338,13 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN    0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE   0x5UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6
 	u8	unused_0;
 	__be16	tunnel_dst_port_val;
 	u8	unused_1[4];
@@ -5824,12 +6369,13 @@ struct hwrm_tunnel_dst_port_free_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN    0x1UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE   0x5UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE 0xbUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST        TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6
 	u8	unused_0;
 	__le16	tunnel_dst_port_id;
 	u8	unused_1[4];
@@ -6040,7 +6586,9 @@ struct hwrm_fw_reset_input {
 	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
 	#define FW_RESET_REQ_SELFRST_STATUS_LAST            FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE
 	u8	host_idx;
-	u8	unused_0[5];
+	u8	flags;
+	#define FW_RESET_REQ_FLAGS_RESET_GRACEFUL     0x1UL
+	u8	unused_0[4];
 };
 
 /* hwrm_fw_reset_output (size:128b/16B) */
@@ -6137,6 +6685,7 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE 0x422UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC       0x424UL
 	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE        0x426UL
+	#define STRUCT_HDR_STRUCT_ID_POWER_BKUP         0x427UL
 	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE         0x1UL
 	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION   0xaUL
 	#define STRUCT_HDR_STRUCT_ID_RSS_V2             0x64UL
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 3962f6fd543c..2b90a2bb1a1d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -121,6 +121,54 @@ int bnxt_set_vf_spoofchk(struct net_device *dev, int vf_id, bool setting)
 	return rc;
 }
 
+static int bnxt_hwrm_func_qcfg_flags(struct bnxt *bp, struct bnxt_vf_info *vf)
+{
+	struct hwrm_func_qcfg_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_qcfg_input req = {0};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_QCFG, -1, -1);
+	req.fid = cpu_to_le16(vf->fw_fid);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc) {
+		mutex_unlock(&bp->hwrm_cmd_lock);
+		return -EIO;
+	}
+	vf->func_qcfg_flags = le16_to_cpu(resp->flags);
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return 0;
+}
+
+static bool bnxt_is_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
+{
+	if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF))
+		return !!(vf->flags & BNXT_VF_TRUST);
+
+	bnxt_hwrm_func_qcfg_flags(bp, vf);
+	return !!(vf->func_qcfg_flags & FUNC_QCFG_RESP_FLAGS_TRUSTED_VF);
+}
+
+static int bnxt_hwrm_set_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf)
+{
+	struct hwrm_func_cfg_input req = {0};
+	int rc;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_TRUSTED_VF))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
+	req.fid = cpu_to_le16(vf->fw_fid);
+	if (vf->flags & BNXT_VF_TRUST)
+		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE);
+	else
+		req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		return -EIO;
+	return 0;
+}
+
 int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted)
 {
 	struct bnxt *bp = netdev_priv(dev);
@@ -135,6 +183,7 @@ int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted)
 	else
 		vf->flags &= ~BNXT_VF_TRUST;
 
+	bnxt_hwrm_set_trusted_vf(bp, vf);
 	return 0;
 }
 
@@ -164,7 +213,7 @@ int bnxt_get_vf_config(struct net_device *dev, int vf_id,
 	else
 		ivi->qos = 0;
 	ivi->spoofchk = !!(vf->flags & BNXT_VF_SPOOFCHK);
-	ivi->trusted = !!(vf->flags & BNXT_VF_TRUST);
+	ivi->trusted = bnxt_is_trusted_vf(bp, vf);
 	if (!(vf->flags & BNXT_VF_LINK_FORCED))
 		ivi->linkstate = IFLA_VF_LINK_STATE_AUTO;
 	else if (vf->flags & BNXT_VF_LINK_UP)
@@ -448,16 +497,22 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	u16 vf_stat_ctx, vf_vnics, vf_ring_grps;
 	struct bnxt_pf_info *pf = &bp->pf;
 	int i, rc = 0, min = 1;
+	u16 vf_msix = 0;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
-	vf_cp_rings = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
-	vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
+	if (bp->flags & BNXT_FLAG_CHIP_P5) {
+		vf_msix = hw_resc->max_nqs - bnxt_nq_rings_in_use(bp);
+		vf_ring_grps = 0;
+	} else {
+		vf_ring_grps = hw_resc->max_hw_ring_grps - bp->rx_nr_rings;
+	}
+	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp);
+	vf_stat_ctx = bnxt_get_avail_stat_ctxs_for_en(bp);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2;
 	else
 		vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings;
-	vf_ring_grps = hw_resc->max_hw_ring_grps - bp->rx_nr_rings;
 	vf_tx_rings = hw_resc->max_tx_rings - bp->tx_nr_rings;
 	vf_vnics = hw_resc->max_vnics - bp->nr_vnics;
 	vf_vnics = min_t(u16, vf_vnics, vf_rx_rings);
@@ -476,7 +531,8 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 		req.min_l2_ctxs = cpu_to_le16(min);
 		req.min_vnics = cpu_to_le16(min);
 		req.min_stat_ctx = cpu_to_le16(min);
-		req.min_hw_ring_grps = cpu_to_le16(min);
+		if (!(bp->flags & BNXT_FLAG_CHIP_P5))
+			req.min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
 		vf_tx_rings /= num_vfs;
@@ -500,6 +556,8 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	req.max_vnics = cpu_to_le16(vf_vnics);
 	req.max_stat_ctx = cpu_to_le16(vf_stat_ctx);
 	req.max_hw_ring_grps = cpu_to_le16(vf_ring_grps);
+	if (bp->flags & BNXT_FLAG_CHIP_P5)
+		req.max_msix = cpu_to_le16(vf_msix / num_vfs);
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	for (i = 0; i < num_vfs; i++) {
@@ -525,6 +583,8 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 		hw_resc->max_rsscos_ctxs -= pf->active_vfs;
 		hw_resc->max_stat_ctxs -= le16_to_cpu(req.min_stat_ctx) * n;
 		hw_resc->max_vnics -= le16_to_cpu(req.min_vnics) * n;
+		if (bp->flags & BNXT_FLAG_CHIP_P5)
+			hw_resc->max_irqs -= vf_msix * n;
 
 		rc = pf->active_vfs;
 	}
@@ -539,19 +599,16 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 	u32 rc = 0, mtu, i;
 	u16 vf_tx_rings, vf_rx_rings, vf_cp_rings, vf_stat_ctx, vf_vnics;
 	struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
-	u16 vf_ring_grps, max_stat_ctxs;
 	struct hwrm_func_cfg_input req = {0};
 	struct bnxt_pf_info *pf = &bp->pf;
 	int total_vf_tx_rings = 0;
+	u16 vf_ring_grps;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1);
 
-	max_stat_ctxs = hw_resc->max_stat_ctxs;
-
 	/* Remaining rings are distributed equally amongs VF's for now */
-	vf_cp_rings = (bnxt_get_max_func_cp_rings_for_en(bp) -
-		       bp->cp_nr_rings) / num_vfs;
-	vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs;
+	vf_cp_rings = bnxt_get_avail_cp_rings_for_en(bp) / num_vfs;
+	vf_stat_ctx = bnxt_get_avail_stat_ctxs_for_en(bp) / num_vfs;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) /
 			      num_vfs;
@@ -644,8 +701,8 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs)
 	 */
 	vfs_supported = *num_vfs;
 
-	avail_cp = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings;
-	avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs;
+	avail_cp = bnxt_get_avail_cp_rings_for_en(bp);
+	avail_stat = bnxt_get_avail_stat_ctxs_for_en(bp);
 	avail_cp = min_t(int, avail_cp, avail_stat);
 
 	while (vfs_supported) {
@@ -927,9 +984,10 @@ static int bnxt_vf_configure_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 	 * if the PF assigned MAC address is zero
 	 */
 	if (req->enables & cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR)) {
+		bool trust = bnxt_is_trusted_vf(bp, vf);
+
 		if (is_valid_ether_addr(req->dflt_mac_addr) &&
-		    ((vf->flags & BNXT_VF_TRUST) ||
-		     !is_valid_ether_addr(vf->mac_addr) ||
+		    (trust || !is_valid_ether_addr(vf->mac_addr) ||
 		     ether_addr_equal(req->dflt_mac_addr, vf->mac_addr))) {
 			ether_addr_copy(vf->vf_mac_addr, req->dflt_mac_addr);
 			return bnxt_hwrm_exec_fwd_resp(bp, vf, msg_size);
@@ -954,7 +1012,7 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 	 * Otherwise, it must match the VF MAC address if firmware spec >=
 	 * 1.2.2
 	 */
-	if (vf->flags & BNXT_VF_TRUST) {
+	if (bnxt_is_trusted_vf(bp, vf)) {
 		mac_ok = true;
 	} else if (is_valid_ether_addr(vf->mac_addr)) {
 		if (ether_addr_equal((const u8 *)req->l2_addr, vf->mac_addr))
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 749f63beddd8..44d6c5743fb9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -45,7 +45,7 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
 	struct bnxt *bp;
 
 	/* check if dev belongs to the same switch */
-	if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) {
+	if (!netdev_port_same_parent_id(pf_bp->dev, dev)) {
 		netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch",
 			    dev->ifindex);
 		return BNXT_FID_INVALID;
@@ -61,9 +61,9 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev)
 
 static int bnxt_tc_parse_redir(struct bnxt *bp,
 			       struct bnxt_tc_actions *actions,
-			       const struct tc_action *tc_act)
+			       const struct flow_action_entry *act)
 {
-	struct net_device *dev = tcf_mirred_dev(tc_act);
+	struct net_device *dev = act->dev;
 
 	if (!dev) {
 		netdev_info(bp->dev, "no dev in mirred action");
@@ -77,16 +77,16 @@ static int bnxt_tc_parse_redir(struct bnxt *bp,
 
 static int bnxt_tc_parse_vlan(struct bnxt *bp,
 			      struct bnxt_tc_actions *actions,
-			      const struct tc_action *tc_act)
+			      const struct flow_action_entry *act)
 {
-	switch (tcf_vlan_action(tc_act)) {
-	case TCA_VLAN_ACT_POP:
+	switch (act->id) {
+	case FLOW_ACTION_VLAN_POP:
 		actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN;
 		break;
-	case TCA_VLAN_ACT_PUSH:
+	case FLOW_ACTION_VLAN_PUSH:
 		actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN;
-		actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act));
-		actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act);
+		actions->push_vlan_tci = htons(act->vlan.vid);
+		actions->push_vlan_tpid = act->vlan.proto;
 		break;
 	default:
 		return -EOPNOTSUPP;
@@ -96,10 +96,10 @@ static int bnxt_tc_parse_vlan(struct bnxt *bp,
 
 static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
 				    struct bnxt_tc_actions *actions,
-				    const struct tc_action *tc_act)
+				    const struct flow_action_entry *act)
 {
-	struct ip_tunnel_info *tun_info = tcf_tunnel_info(tc_act);
-	struct ip_tunnel_key *tun_key = &tun_info->key;
+	const struct ip_tunnel_info *tun_info = act->tunnel;
+	const struct ip_tunnel_key *tun_key = &tun_info->key;
 
 	if (ip_tunnel_info_af(tun_info) != AF_INET) {
 		netdev_info(bp->dev, "only IPv4 tunnel-encap is supported");
@@ -113,51 +113,43 @@ static int bnxt_tc_parse_tunnel_set(struct bnxt *bp,
 
 static int bnxt_tc_parse_actions(struct bnxt *bp,
 				 struct bnxt_tc_actions *actions,
-				 struct tcf_exts *tc_exts)
+				 struct flow_action *flow_action)
 {
-	const struct tc_action *tc_act;
+	struct flow_action_entry *act;
 	int i, rc;
 
-	if (!tcf_exts_has_actions(tc_exts)) {
+	if (!flow_action_has_entries(flow_action)) {
 		netdev_info(bp->dev, "no actions");
 		return -EINVAL;
 	}
 
-	tcf_exts_for_each_action(i, tc_act, tc_exts) {
-		/* Drop action */
-		if (is_tcf_gact_shot(tc_act)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
 			actions->flags |= BNXT_TC_ACTION_FLAG_DROP;
 			return 0; /* don't bother with other actions */
-		}
-
-		/* Redirect action */
-		if (is_tcf_mirred_egress_redirect(tc_act)) {
-			rc = bnxt_tc_parse_redir(bp, actions, tc_act);
+		case FLOW_ACTION_REDIRECT:
+			rc = bnxt_tc_parse_redir(bp, actions, act);
 			if (rc)
 				return rc;
-			continue;
-		}
-
-		/* Push/pop VLAN */
-		if (is_tcf_vlan(tc_act)) {
-			rc = bnxt_tc_parse_vlan(bp, actions, tc_act);
+			break;
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_MANGLE:
+			rc = bnxt_tc_parse_vlan(bp, actions, act);
 			if (rc)
 				return rc;
-			continue;
-		}
-
-		/* Tunnel encap */
-		if (is_tcf_tunnel_set(tc_act)) {
-			rc = bnxt_tc_parse_tunnel_set(bp, actions, tc_act);
+			break;
+		case FLOW_ACTION_TUNNEL_ENCAP:
+			rc = bnxt_tc_parse_tunnel_set(bp, actions, act);
 			if (rc)
 				return rc;
-			continue;
-		}
-
-		/* Tunnel decap */
-		if (is_tcf_tunnel_release(tc_act)) {
+			break;
+		case FLOW_ACTION_TUNNEL_DECAP:
 			actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_DECAP;
-			continue;
+			break;
+		default:
+			break;
 		}
 	}
 
@@ -177,18 +169,12 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 	return 0;
 }
 
-#define GET_KEY(flow_cmd, key_type)					\
-		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
-					  (flow_cmd)->key)
-#define GET_MASK(flow_cmd, key_type)					\
-		skb_flow_dissector_target((flow_cmd)->dissector, key_type,\
-					  (flow_cmd)->mask)
-
 static int bnxt_tc_parse_flow(struct bnxt *bp,
 			      struct tc_cls_flower_offload *tc_flow_cmd,
 			      struct bnxt_tc_flow *flow)
 {
-	struct flow_dissector *dissector = tc_flow_cmd->dissector;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(tc_flow_cmd);
+	struct flow_dissector *dissector = rule->match.dissector;
 
 	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
 	if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 ||
@@ -198,157 +184,140 @@ static int bnxt_tc_parse_flow(struct bnxt *bp,
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
-		struct flow_dissector_key_basic *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		flow->l2_key.ether_type = key->n_proto;
-		flow->l2_mask.ether_type = mask->n_proto;
+		flow_rule_match_basic(rule, &match);
+		flow->l2_key.ether_type = match.key->n_proto;
+		flow->l2_mask.ether_type = match.mask->n_proto;
 
-		if (key->n_proto == htons(ETH_P_IP) ||
-		    key->n_proto == htons(ETH_P_IPV6)) {
-			flow->l4_key.ip_proto = key->ip_proto;
-			flow->l4_mask.ip_proto = mask->ip_proto;
+		if (match.key->n_proto == htons(ETH_P_IP) ||
+		    match.key->n_proto == htons(ETH_P_IPV6)) {
+			flow->l4_key.ip_proto = match.key->ip_proto;
+			flow->l4_mask.ip_proto = match.mask->ip_proto;
 		}
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
-		struct flow_dissector_key_eth_addrs *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
+		flow_rule_match_eth_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS;
-		ether_addr_copy(flow->l2_key.dmac, key->dst);
-		ether_addr_copy(flow->l2_mask.dmac, mask->dst);
-		ether_addr_copy(flow->l2_key.smac, key->src);
-		ether_addr_copy(flow->l2_mask.smac, mask->src);
+		ether_addr_copy(flow->l2_key.dmac, match.key->dst);
+		ether_addr_copy(flow->l2_mask.dmac, match.mask->dst);
+		ether_addr_copy(flow->l2_key.smac, match.key->src);
+		ether_addr_copy(flow->l2_mask.smac, match.mask->src);
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
-		struct flow_dissector_key_vlan *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
+		flow_rule_match_vlan(rule, &match);
 		flow->l2_key.inner_vlan_tci =
-		   cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority));
+			cpu_to_be16(VLAN_TCI(match.key->vlan_id,
+					     match.key->vlan_priority));
 		flow->l2_mask.inner_vlan_tci =
-		   cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority)));
+			cpu_to_be16((VLAN_TCI(match.mask->vlan_id,
+					      match.mask->vlan_priority)));
 		flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q);
 		flow->l2_mask.inner_vlan_tpid = htons(0xffff);
 		flow->l2_key.num_vlans = 1;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
+		flow_rule_match_ipv4_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS;
-		flow->l3_key.ipv4.daddr.s_addr = key->dst;
-		flow->l3_mask.ipv4.daddr.s_addr = mask->dst;
-		flow->l3_key.ipv4.saddr.s_addr = key->src;
-		flow->l3_mask.ipv4.saddr.s_addr = mask->src;
-	} else if (dissector_uses_key(dissector,
-				      FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
-
+		flow->l3_key.ipv4.daddr.s_addr = match.key->dst;
+		flow->l3_mask.ipv4.daddr.s_addr = match.mask->dst;
+		flow->l3_key.ipv4.saddr.s_addr = match.key->src;
+		flow->l3_mask.ipv4.saddr.s_addr = match.mask->src;
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS;
-		flow->l3_key.ipv6.daddr = key->dst;
-		flow->l3_mask.ipv6.daddr = mask->dst;
-		flow->l3_key.ipv6.saddr = key->src;
-		flow->l3_mask.ipv6.saddr = mask->src;
+		flow->l3_key.ipv6.daddr = match.key->dst;
+		flow->l3_mask.ipv6.daddr = match.mask->dst;
+		flow->l3_key.ipv6.saddr = match.key->src;
+		flow->l3_mask.ipv6.saddr = match.mask->src;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
-		struct flow_dissector_key_ports *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
+		flow_rule_match_ports(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS;
-		flow->l4_key.ports.dport = key->dst;
-		flow->l4_mask.ports.dport = mask->dst;
-		flow->l4_key.ports.sport = key->src;
-		flow->l4_mask.ports.sport = mask->src;
+		flow->l4_key.ports.dport = match.key->dst;
+		flow->l4_mask.ports.dport = match.mask->dst;
+		flow->l4_key.ports.sport = match.key->src;
+		flow->l4_mask.ports.sport = match.mask->src;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) {
-		struct flow_dissector_key_icmp *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
-		struct flow_dissector_key_icmp *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP)) {
+		struct flow_match_icmp match;
 
+		flow_rule_match_icmp(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP;
-		flow->l4_key.icmp.type = key->type;
-		flow->l4_key.icmp.code = key->code;
-		flow->l4_mask.icmp.type = mask->type;
-		flow->l4_mask.icmp.code = mask->code;
+		flow->l4_key.icmp.type = match.key->type;
+		flow->l4_key.icmp.code = match.key->code;
+		flow->l4_mask.icmp.type = match.mask->type;
+		flow->l4_mask.icmp.code = match.mask->code;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
-		struct flow_dissector_key_ipv4_addrs *mask =
-				GET_MASK(tc_flow_cmd,
-					 FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
+		flow_rule_match_enc_ipv4_addrs(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS;
-		flow->tun_key.u.ipv4.dst = key->dst;
-		flow->tun_mask.u.ipv4.dst = mask->dst;
-		flow->tun_key.u.ipv4.src = key->src;
-		flow->tun_mask.u.ipv4.src = mask->src;
-	} else if (dissector_uses_key(dissector,
+		flow->tun_key.u.ipv4.dst = match.key->dst;
+		flow->tun_mask.u.ipv4.dst = match.mask->dst;
+		flow->tun_key.u.ipv4.src = match.key->src;
+		flow->tun_mask.u.ipv4.src = match.mask->src;
+	} else if (flow_rule_match_key(rule,
 				      FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) {
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
-		struct flow_dissector_key_keyid *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 
+		flow_rule_match_enc_keyid(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ID;
-		flow->tun_key.tun_id = key32_to_tunnel_id(key->keyid);
-		flow->tun_mask.tun_id = key32_to_tunnel_id(mask->keyid);
+		flow->tun_key.tun_id = key32_to_tunnel_id(match.key->keyid);
+		flow->tun_mask.tun_id = key32_to_tunnel_id(match.mask->keyid);
 	}
 
-	if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
-		struct flow_dissector_key_ports *mask =
-			GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
+		struct flow_match_ports match;
 
+		flow_rule_match_enc_ports(rule, &match);
 		flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_PORTS;
-		flow->tun_key.tp_dst = key->dst;
-		flow->tun_mask.tp_dst = mask->dst;
-		flow->tun_key.tp_src = key->src;
-		flow->tun_mask.tp_src = mask->src;
+		flow->tun_key.tp_dst = match.key->dst;
+		flow->tun_mask.tp_dst = match.mask->dst;
+		flow->tun_key.tp_src = match.key->src;
+		flow->tun_mask.tp_src = match.mask->src;
 	}
 
-	return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts);
+	return bnxt_tc_parse_actions(bp, &flow->actions, &rule->action);
 }
 
-static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, __le16 flow_handle)
+static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp,
+				   struct bnxt_tc_flow_node *flow_node)
 {
 	struct hwrm_cfa_flow_free_input req = { 0 };
 	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_FREE, -1, -1);
-	req.flow_handle = flow_handle;
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+		req.ext_flow_handle = flow_node->ext_flow_handle;
+	else
+		req.flow_handle = flow_node->flow_handle;
 
 	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
-		netdev_info(bp->dev, "Error: %s: flow_handle=0x%x rc=%d",
-			    __func__, flow_handle, rc);
+		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
 
 	if (rc)
 		rc = -EIO;
@@ -418,13 +387,14 @@ static bool bits_set(void *key, int len)
 
 static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				    __le16 ref_flow_handle,
-				    __le32 tunnel_handle, __le16 *flow_handle)
+				    __le32 tunnel_handle,
+				    struct bnxt_tc_flow_node *flow_node)
 {
-	struct hwrm_cfa_flow_alloc_output *resp = bp->hwrm_cmd_resp_addr;
 	struct bnxt_tc_actions *actions = &flow->actions;
 	struct bnxt_tc_l3_key *l3_mask = &flow->l3_mask;
 	struct bnxt_tc_l3_key *l3_key = &flow->l3_key;
 	struct hwrm_cfa_flow_alloc_input req = { 0 };
+	struct hwrm_cfa_flow_alloc_output *resp;
 	u16 flow_flags = 0, action_flags = 0;
 	int rc;
 
@@ -527,8 +497,23 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow,
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
-		*flow_handle = resp->flow_handle;
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
+		/* CFA_FLOW_ALLOC response interpretation:
+		 *		    fw with	     fw with
+		 *		    16-bit	     64-bit
+		 *		    flow handle      flow handle
+		 *		    ===========	     ===========
+		 * flow_handle      flow handle      flow context id
+		 * ext_flow_handle  INVALID	     flow handle
+		 * flow_id	    INVALID	     flow counter id
+		 */
+		flow_node->flow_handle = resp->flow_handle;
+		if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE) {
+			flow_node->ext_flow_handle = resp->ext_flow_handle;
+			flow_node->flow_id = resp->flow_id;
+		}
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	if (rc == HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR)
@@ -544,9 +529,8 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 				       __le32 ref_decap_handle,
 				       __le32 *decap_filter_handle)
 {
-	struct hwrm_cfa_decap_filter_alloc_output *resp =
-						bp->hwrm_cmd_resp_addr;
 	struct hwrm_cfa_decap_filter_alloc_input req = { 0 };
+	struct hwrm_cfa_decap_filter_alloc_output *resp;
 	struct ip_tunnel_key *tun_key = &flow->tun_key;
 	u32 enables = 0;
 	int rc;
@@ -599,10 +583,12 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp,
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		*decap_filter_handle = resp->decap_filter_id;
-	else
+	} else {
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	if (rc)
@@ -633,9 +619,8 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 				       struct bnxt_tc_l2_key *l2_info,
 				       __le32 *encap_record_handle)
 {
-	struct hwrm_cfa_encap_record_alloc_output *resp =
-						bp->hwrm_cmd_resp_addr;
 	struct hwrm_cfa_encap_record_alloc_input req = { 0 };
+	struct hwrm_cfa_encap_record_alloc_output *resp;
 	struct hwrm_cfa_encap_data_vxlan *encap =
 			(struct hwrm_cfa_encap_data_vxlan *)&req.encap_data;
 	struct hwrm_vxlan_ipv4_hdr *encap_ipv4 =
@@ -667,10 +652,12 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp,
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
-	if (!rc)
+	if (!rc) {
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
 		*encap_record_handle = resp->encap_record_id;
-	else
+	} else {
 		netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc);
+	}
 	mutex_unlock(&bp->hwrm_cmd_lock);
 
 	if (rc)
@@ -1224,7 +1211,7 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 	int rc;
 
 	/* send HWRM cmd to free the flow-id */
-	bnxt_hwrm_cfa_flow_free(bp, flow_node->flow_handle);
+	bnxt_hwrm_cfa_flow_free(bp, flow_node);
 
 	mutex_lock(&tc_info->lock);
 
@@ -1246,6 +1233,12 @@ static int __bnxt_tc_del_flow(struct bnxt *bp,
 	return 0;
 }
 
+static void bnxt_tc_set_flow_dir(struct bnxt *bp, struct bnxt_tc_flow *flow,
+				 u16 src_fid)
+{
+	flow->dir = (bp->pf.fw_fid == src_fid) ? BNXT_DIR_RX : BNXT_DIR_TX;
+}
+
 static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
 				u16 src_fid)
 {
@@ -1293,8 +1286,11 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 
 	bnxt_tc_set_src_fid(bp, flow, src_fid);
 
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE)
+		bnxt_tc_set_flow_dir(bp, flow, src_fid);
+
 	if (!bnxt_tc_can_offload(bp, flow)) {
-		rc = -ENOSPC;
+		rc = -EOPNOTSUPP;
 		goto free_node;
 	}
 
@@ -1320,7 +1316,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 
 	/* send HWRM cmd to alloc the flow */
 	rc = bnxt_hwrm_cfa_flow_alloc(bp, flow, ref_flow_handle,
-				      tunnel_handle, &new_node->flow_handle);
+				      tunnel_handle, new_node);
 	if (rc)
 		goto put_tunnel;
 
@@ -1336,7 +1332,7 @@ static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
 	return 0;
 
 hwrm_flow_free:
-	bnxt_hwrm_cfa_flow_free(bp, new_node->flow_handle);
+	bnxt_hwrm_cfa_flow_free(bp, new_node);
 put_tunnel:
 	bnxt_tc_put_tunnel_handle(bp, flow, new_node);
 put_l2:
@@ -1392,18 +1388,45 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp,
 	lastused = flow->lastused;
 	spin_unlock(&flow->stats_lock);
 
-	tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets,
-			      lastused);
+	flow_stats_update(&tc_flow_cmd->stats, stats.bytes, stats.packets,
+			  lastused);
 	return 0;
 }
 
+static void bnxt_fill_cfa_stats_req(struct bnxt *bp,
+				    struct bnxt_tc_flow_node *flow_node,
+				    __le16 *flow_handle, __le32 *flow_id)
+{
+	u16 handle;
+
+	if (bp->fw_cap & BNXT_FW_CAP_OVS_64BIT_HANDLE) {
+		*flow_id = flow_node->flow_id;
+
+		/* If flow_id is used to fetch flow stats then:
+		 * 1. lower 12 bits of flow_handle must be set to all 1s.
+		 * 2. 15th bit of flow_handle must specify the flow
+		 *    direction (TX/RX).
+		 */
+		if (flow_node->flow.dir == BNXT_DIR_RX)
+			handle = CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX |
+				 CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK;
+		else
+			handle = CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK;
+
+		*flow_handle = cpu_to_le16(handle);
+	} else {
+		*flow_handle = flow_node->flow_handle;
+	}
+}
+
 static int
 bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 			     struct bnxt_tc_stats_batch stats_batch[])
 {
-	struct hwrm_cfa_flow_stats_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_cfa_flow_stats_input req = { 0 };
+	struct hwrm_cfa_flow_stats_output *resp;
 	__le16 *req_flow_handles = &req.flow_handle_0;
+	__le32 *req_flow_ids = &req.flow_id_0;
 	int rc, i;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_CFA_FLOW_STATS, -1, -1);
@@ -1411,14 +1434,19 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows,
 	for (i = 0; i < num_flows; i++) {
 		struct bnxt_tc_flow_node *flow_node = stats_batch[i].flow_node;
 
-		req_flow_handles[i] = flow_node->flow_handle;
+		bnxt_fill_cfa_stats_req(bp, flow_node,
+					&req_flow_handles[i], &req_flow_ids[i]);
 	}
 
 	mutex_lock(&bp->hwrm_cmd_lock);
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (!rc) {
-		__le64 *resp_packets = &resp->packet_0;
-		__le64 *resp_bytes = &resp->byte_0;
+		__le64 *resp_packets;
+		__le64 *resp_bytes;
+
+		resp = bnxt_get_hwrm_resp_addr(bp, &req);
+		resp_packets = &resp->packet_0;
+		resp_bytes = &resp->byte_0;
 
 		for (i = 0; i < num_flows; i++) {
 			stats_batch[i].hw_stats.packets =
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
index 97e09a880693..8a0968967bc5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -98,6 +98,9 @@ struct bnxt_tc_flow {
 
 	/* flow applicable to pkts ingressing on this fid */
 	u16				src_fid;
+	u8				dir;
+#define BNXT_DIR_RX	1
+#define BNXT_DIR_TX	0
 	struct bnxt_tc_l2_key		l2_key;
 	struct bnxt_tc_l2_key		l2_mask;
 	struct bnxt_tc_l3_key		l3_key;
@@ -170,7 +173,9 @@ struct bnxt_tc_flow_node {
 
 	struct bnxt_tc_flow		flow;
 
+	__le64				ext_flow_handle;
 	__le16				flow_handle;
+	__le32				flow_id;
 
 	/* L2 node in l2 hashtable that shares flow's l2 key */
 	struct bnxt_tc_l2_node		*l2_node;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 0a3097baafde..cf475873ce81 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -43,15 +43,10 @@ static int bnxt_register_dev(struct bnxt_en_dev *edev, int ulp_id,
 	if (ulp_id == BNXT_ROCE_ULP) {
 		unsigned int max_stat_ctxs;
 
-		if (bp->flags & BNXT_FLAG_CHIP_P5)
-			return -EOPNOTSUPP;
-
 		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
 		if (max_stat_ctxs <= BNXT_MIN_ROCE_STAT_CTXS ||
-		    bp->num_stat_ctxs == max_stat_ctxs)
+		    bp->cp_nr_rings == max_stat_ctxs)
 			return -ENOMEM;
-		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs -
-					    BNXT_MIN_ROCE_STAT_CTXS);
 	}
 
 	atomic_set(&ulp->ref_count, 0);
@@ -82,14 +77,9 @@ static int bnxt_unregister_dev(struct bnxt_en_dev *edev, int ulp_id)
 		netdev_err(bp->dev, "ulp id %d not registered\n", ulp_id);
 		return -EINVAL;
 	}
-	if (ulp_id == BNXT_ROCE_ULP) {
-		unsigned int max_stat_ctxs;
+	if (ulp_id == BNXT_ROCE_ULP && ulp->msix_requested)
+		edev->en_ops->bnxt_free_msix(edev, ulp_id);
 
-		max_stat_ctxs = bnxt_get_max_func_stat_ctxs(bp);
-		bnxt_set_max_func_stat_ctxs(bp, max_stat_ctxs + 1);
-		if (ulp->msix_requested)
-			edev->en_ops->bnxt_free_msix(edev, ulp_id);
-	}
 	if (ulp->max_async_event_id)
 		bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0);
 
@@ -218,6 +208,14 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp)
 	return 0;
 }
 
+int bnxt_get_ulp_stat_ctxs(struct bnxt *bp)
+{
+	if (bnxt_ulp_registered(bp->edev, BNXT_ROCE_ULP))
+		return BNXT_MIN_ROCE_STAT_CTXS;
+
+	return 0;
+}
+
 static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id,
 			 struct bnxt_fw_msg *fw_msg)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
index d9bea37cd211..cd78453d0bf0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h
@@ -90,6 +90,7 @@ static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id)
 
 int bnxt_get_ulp_msix_num(struct bnxt *bp);
 int bnxt_get_ulp_msix_base(struct bnxt *bp);
+int bnxt_get_ulp_stat_ctxs(struct bnxt *bp);
 void bnxt_ulp_stop(struct bnxt *bp);
 void bnxt_ulp_start(struct bnxt *bp);
 void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 9a25c05aa571..2bdd2da9aac7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -237,21 +237,17 @@ static void bnxt_vf_rep_get_drvinfo(struct net_device *dev,
 	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 }
 
-static int bnxt_vf_rep_port_attr_get(struct net_device *dev,
-				     struct switchdev_attr *attr)
+static int bnxt_vf_rep_get_port_parent_id(struct net_device *dev,
+					  struct netdev_phys_item_id *ppid)
 {
 	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
 
 	/* as only PORT_PARENT_ID is supported currently use common code
 	 * between PF and VF-rep for now.
 	 */
-	return bnxt_port_attr_get(vf_rep->bp, attr);
+	return bnxt_get_port_parent_id(vf_rep->bp->dev, ppid);
 }
 
-static const struct switchdev_ops bnxt_vf_rep_switchdev_ops = {
-	.switchdev_port_attr_get	= bnxt_vf_rep_port_attr_get
-};
-
 static const struct ethtool_ops bnxt_vf_rep_ethtool_ops = {
 	.get_drvinfo		= bnxt_vf_rep_get_drvinfo
 };
@@ -262,6 +258,7 @@ static const struct net_device_ops bnxt_vf_rep_netdev_ops = {
 	.ndo_start_xmit		= bnxt_vf_rep_xmit,
 	.ndo_get_stats64	= bnxt_vf_rep_get_stats64,
 	.ndo_setup_tc		= bnxt_vf_rep_setup_tc,
+	.ndo_get_port_parent_id	= bnxt_vf_rep_get_port_parent_id,
 	.ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name
 };
 
@@ -392,7 +389,6 @@ static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 
 	dev->netdev_ops = &bnxt_vf_rep_netdev_ops;
 	dev->ethtool_ops = &bnxt_vf_rep_ethtool_ops;
-	SWITCHDEV_SET_OPS(dev, &bnxt_vf_rep_switchdev_ops);
 	/* Just inherit all the featues of the parent PF as the VF-R
 	 * uses the RX/TX rings of the parent PF
 	 */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index bf6de02be396..0184ef6f05a7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -199,7 +199,6 @@ static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 	bp->tx_nr_rings_xdp = tx_xdp;
 	bp->tx_nr_rings = bp->tx_nr_rings_per_tc * tc + tx_xdp;
 	bp->cp_nr_rings = max_t(int, bp->tx_nr_rings, bp->rx_nr_rings);
-	bp->num_stat_ctxs = bp->cp_nr_rings;
 	bnxt_set_tpa_flags(bp);
 	bnxt_set_ring_params(bp);
 
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index d83233ae4a15..510dfc1c236b 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -5731,7 +5731,7 @@ static int cnic_netdev_event(struct notifier_block *this, unsigned long event,
 		if (realdev) {
 			dev = cnic_from_netdev(realdev);
 			if (dev) {
-				vid |= VLAN_TAG_PRESENT;
+				vid |= VLAN_CFI_MASK;	/* make non-zero */
 				cnic_rcv_netevent(dev->cnic_priv, event, vid);
 				cnic_put(dev);
 			}
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 2d6f090bf644..983245c0867c 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1169,7 +1169,7 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static void bcmgenet_power_up(struct bcmgenet_priv *priv,
@@ -3612,36 +3612,6 @@ static int bcmgenet_remove(struct platform_device *pdev)
 }
 
 #ifdef CONFIG_PM_SLEEP
-static int bcmgenet_suspend(struct device *d)
-{
-	struct net_device *dev = dev_get_drvdata(d);
-	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int ret = 0;
-
-	if (!netif_running(dev))
-		return 0;
-
-	netif_device_detach(dev);
-
-	bcmgenet_netif_stop(dev);
-
-	if (!device_may_wakeup(d))
-		phy_suspend(dev->phydev);
-
-	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
-	if (device_may_wakeup(d) && priv->wolopts) {
-		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
-		clk_prepare_enable(priv->clk_wol);
-	} else if (priv->internal_phy) {
-		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
-	}
-
-	/* Turn off the clocks */
-	clk_disable_unprepare(priv->clk);
-
-	return ret;
-}
-
 static int bcmgenet_resume(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
@@ -3719,6 +3689,39 @@ out_clk_disable:
 	clk_disable_unprepare(priv->clk);
 	return ret;
 }
+
+static int bcmgenet_suspend(struct device *d)
+{
+	struct net_device *dev = dev_get_drvdata(d);
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	int ret = 0;
+
+	if (!netif_running(dev))
+		return 0;
+
+	netif_device_detach(dev);
+
+	bcmgenet_netif_stop(dev);
+
+	if (!device_may_wakeup(d))
+		phy_suspend(dev->phydev);
+
+	/* Prepare the device for Wake-on-LAN and switch to the slow clock */
+	if (device_may_wakeup(d) && priv->wolopts) {
+		ret = bcmgenet_power_down(priv, GENET_POWER_WOL_MAGIC);
+		clk_prepare_enable(priv->clk_wol);
+	} else if (priv->internal_phy) {
+		ret = bcmgenet_power_down(priv, GENET_POWER_PASSIVE);
+	}
+
+	/* Turn off the clocks */
+	clk_disable_unprepare(priv->clk);
+
+	if (ret)
+		bcmgenet_resume(d);
+
+	return ret;
+}
 #endif /* CONFIG_PM_SLEEP */
 
 static SIMPLE_DEV_PM_OPS(bcmgenet_pm_ops, bcmgenet_suspend, bcmgenet_resume);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 2fbd027f0148..57582efa362d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -186,6 +186,8 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	}
 
 	reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
+	if (!(reg & MPD_EN))
+		return;	/* already powered up so skip the rest */
 	reg &= ~MPD_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index a6cbaca37e94..51880d83131a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -226,7 +226,8 @@ int bcmgenet_mii_config(struct net_device *dev, bool init)
 		 * capabilities, use that knowledge to also configure the
 		 * Reverse MII interface correctly.
 		 */
-		if (dev->phydev->supported & PHY_1000BT_FEATURES)
+		if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				      dev->phydev->supported))
 			port_ctrl = PORT_MODE_EXT_RVMII_50;
 		else
 			port_ctrl = PORT_MODE_EXT_RVMII_25;
@@ -317,7 +318,7 @@ int bcmgenet_mii_probe(struct net_device *dev)
 		return ret;
 	}
 
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	/* The internal PHY has its link interrupts routed to the
 	 * Ethernet MAC ISRs. On GENETv5 there is a hardware issue
@@ -524,7 +525,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv)
 			.asym_pause = 0,
 		};
 
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL);
+		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 		if (!phydev || IS_ERR(phydev)) {
 			dev_err(kdev, "failed to register fixed PHY device\n");
 			return -ENODEV;
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 5db9f4158e62..134ae2862efa 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -1288,7 +1288,7 @@ static void sbdma_tx_process(struct sbmac_softc *sc, struct sbmacdma *d,
 		 * for transmits, we just free buffers.
 		 */
 
-		dev_kfree_skb_irq(sb);
+		dev_consume_skb_irq(sb);
 
 		/*
 		 * .. and advance to the next buffer.
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 432c3b867084..060a6f386104 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -66,11 +66,6 @@
 #include <uapi/linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
 
-#ifdef CONFIG_SPARC
-#include <asm/idprom.h>
-#include <asm/prom.h>
-#endif
-
 #define BAR_0	0
 #define BAR_2	2
 
@@ -726,7 +721,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return 0;
-		/* else: fall through */
+		/* fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -787,7 +782,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return;
-		/* else: fall through */
+		/* fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -2157,7 +2152,8 @@ static void tg3_phy_start(struct tg3 *tp)
 		phydev->speed = tp->link_config.speed;
 		phydev->duplex = tp->link_config.duplex;
 		phydev->autoneg = tp->link_config.autoneg;
-		phydev->advertising = tp->link_config.advertising;
+		ethtool_convert_legacy_u32_to_link_mode(
+			phydev->advertising, tp->link_config.advertising);
 	}
 
 	phy_start(phydev);
@@ -4057,8 +4053,9 @@ static int tg3_power_down_prepare(struct tg3 *tp)
 		do_low_power = false;
 		if ((tp->phy_flags & TG3_PHYFLG_IS_CONNECTED) &&
 		    !(tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER)) {
+			__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising) = { 0, };
 			struct phy_device *phydev;
-			u32 phyid, advertising;
+			u32 phyid;
 
 			phydev = mdiobus_get_phy(tp->mdio_bus, tp->phy_addr);
 
@@ -4067,25 +4064,33 @@ static int tg3_power_down_prepare(struct tg3 *tp)
 			tp->link_config.speed = phydev->speed;
 			tp->link_config.duplex = phydev->duplex;
 			tp->link_config.autoneg = phydev->autoneg;
-			tp->link_config.advertising = phydev->advertising;
-
-			advertising = ADVERTISED_TP |
-				      ADVERTISED_Pause |
-				      ADVERTISED_Autoneg |
-				      ADVERTISED_10baseT_Half;
+			ethtool_convert_link_mode_to_legacy_u32(
+				&tp->link_config.advertising,
+				phydev->advertising);
+
+			linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, advertising);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+					 advertising);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+					 advertising);
+			linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT,
+					 advertising);
 
 			if (tg3_flag(tp, ENABLE_ASF) || device_should_wake) {
-				if (tg3_flag(tp, WOL_SPEED_100MB))
-					advertising |=
-						ADVERTISED_100baseT_Half |
-						ADVERTISED_100baseT_Full |
-						ADVERTISED_10baseT_Full;
-				else
-					advertising |= ADVERTISED_10baseT_Full;
+				if (tg3_flag(tp, WOL_SPEED_100MB)) {
+					linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+							 advertising);
+					linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+							 advertising);
+					linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+							 advertising);
+				} else {
+					linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT,
+							 advertising);
+				}
 			}
 
-			phydev->advertising = advertising;
-
+			linkmode_copy(phydev->advertising, advertising);
 			phy_start_aneg(phydev);
 
 			phyid = phydev->drv->phy_id & phydev->drv->phy_id_mask;
@@ -4278,7 +4283,7 @@ static void tg3_power_down(struct tg3 *tp)
 	pci_set_power_state(tp->pdev, PCI_D3hot);
 }
 
-static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u16 *speed, u8 *duplex)
+static void tg3_aux_stat_to_speed_duplex(struct tg3 *tp, u32 val, u32 *speed, u8 *duplex)
 {
 	switch (val & MII_TG3_AUX_STAT_SPDMASK) {
 	case MII_TG3_AUX_STAT_10HALF:
@@ -4782,7 +4787,7 @@ static int tg3_setup_copper_phy(struct tg3 *tp, bool force_reset)
 	bool current_link_up;
 	u32 bmsr, val;
 	u32 lcl_adv, rmt_adv;
-	u16 current_speed;
+	u32 current_speed;
 	u8 current_duplex;
 	int i, err;
 
@@ -5714,7 +5719,7 @@ out:
 static int tg3_setup_fiber_phy(struct tg3 *tp, bool force_reset)
 {
 	u32 orig_pause_cfg;
-	u16 orig_active_speed;
+	u32 orig_active_speed;
 	u8 orig_active_duplex;
 	u32 mac_status;
 	bool current_link_up;
@@ -5818,7 +5823,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, bool force_reset)
 {
 	int err = 0;
 	u32 bmsr, bmcr;
-	u16 current_speed = SPEED_UNKNOWN;
+	u32 current_speed = SPEED_UNKNOWN;
 	u8 current_duplex = DUPLEX_UNKNOWN;
 	bool current_link_up = false;
 	u32 local_adv, remote_adv, sgsr;
@@ -6135,10 +6140,16 @@ static int tg3_setup_phy(struct tg3 *tp, bool force_reset)
 }
 
 /* tp->lock must be held */
-static u64 tg3_refclk_read(struct tg3 *tp)
+static u64 tg3_refclk_read(struct tg3 *tp, struct ptp_system_timestamp *sts)
 {
-	u64 stamp = tr32(TG3_EAV_REF_CLCK_LSB);
-	return stamp | (u64)tr32(TG3_EAV_REF_CLCK_MSB) << 32;
+	u64 stamp;
+
+	ptp_read_system_prets(sts);
+	stamp = tr32(TG3_EAV_REF_CLCK_LSB);
+	ptp_read_system_postts(sts);
+	stamp |= (u64)tr32(TG3_EAV_REF_CLCK_MSB) << 32;
+
+	return stamp;
 }
 
 /* tp->lock must be held */
@@ -6229,13 +6240,14 @@ static int tg3_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-static int tg3_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int tg3_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			    struct ptp_system_timestamp *sts)
 {
 	u64 ns;
 	struct tg3 *tp = container_of(ptp, struct tg3, ptp_info);
 
 	tg3_full_lock(tp, 0);
-	ns = tg3_refclk_read(tp);
+	ns = tg3_refclk_read(tp, sts);
 	ns += tp->ptp_adjust;
 	tg3_full_unlock(tp);
 
@@ -6330,7 +6342,7 @@ static const struct ptp_clock_info tg3_ptp_caps = {
 	.pps		= 0,
 	.adjfreq	= tg3_ptp_adjfreq,
 	.adjtime	= tg3_ptp_adjtime,
-	.gettime64	= tg3_ptp_gettime,
+	.gettimex64	= tg3_ptp_gettimex,
 	.settime64	= tg3_ptp_settime,
 	.enable		= tg3_ptp_enable,
 };
@@ -8700,10 +8712,10 @@ static int tg3_mem_rx_acquire(struct tg3 *tp)
 		if (!i && tg3_flag(tp, ENABLE_RSS))
 			continue;
 
-		tnapi->rx_rcb = dma_zalloc_coherent(&tp->pdev->dev,
-						    TG3_RX_RCB_RING_BYTES(tp),
-						    &tnapi->rx_rcb_mapping,
-						    GFP_KERNEL);
+		tnapi->rx_rcb = dma_alloc_coherent(&tp->pdev->dev,
+						   TG3_RX_RCB_RING_BYTES(tp),
+						   &tnapi->rx_rcb_mapping,
+						   GFP_KERNEL);
 		if (!tnapi->rx_rcb)
 			goto err_out;
 	}
@@ -8756,9 +8768,9 @@ static int tg3_alloc_consistent(struct tg3 *tp)
 {
 	int i;
 
-	tp->hw_stats = dma_zalloc_coherent(&tp->pdev->dev,
-					   sizeof(struct tg3_hw_stats),
-					   &tp->stats_mapping, GFP_KERNEL);
+	tp->hw_stats = dma_alloc_coherent(&tp->pdev->dev,
+					  sizeof(struct tg3_hw_stats),
+					  &tp->stats_mapping, GFP_KERNEL);
 	if (!tp->hw_stats)
 		goto err_out;
 
@@ -8766,10 +8778,10 @@ static int tg3_alloc_consistent(struct tg3 *tp)
 		struct tg3_napi *tnapi = &tp->napi[i];
 		struct tg3_hw_status *sblk;
 
-		tnapi->hw_status = dma_zalloc_coherent(&tp->pdev->dev,
-						       TG3_HW_STATUS_SIZE,
-						       &tnapi->status_mapping,
-						       GFP_KERNEL);
+		tnapi->hw_status = dma_alloc_coherent(&tp->pdev->dev,
+						      TG3_HW_STATUS_SIZE,
+						      &tnapi->status_mapping,
+						      GFP_KERNEL);
 		if (!tnapi->hw_status)
 			goto err_out;
 
@@ -16973,32 +16985,6 @@ static int tg3_get_invariants(struct tg3 *tp, const struct pci_device_id *ent)
 	return err;
 }
 
-#ifdef CONFIG_SPARC
-static int tg3_get_macaddr_sparc(struct tg3 *tp)
-{
-	struct net_device *dev = tp->dev;
-	struct pci_dev *pdev = tp->pdev;
-	struct device_node *dp = pci_device_to_OF_node(pdev);
-	const unsigned char *addr;
-	int len;
-
-	addr = of_get_property(dp, "local-mac-address", &len);
-	if (addr && len == ETH_ALEN) {
-		memcpy(dev->dev_addr, addr, ETH_ALEN);
-		return 0;
-	}
-	return -ENODEV;
-}
-
-static int tg3_get_default_macaddr_sparc(struct tg3 *tp)
-{
-	struct net_device *dev = tp->dev;
-
-	memcpy(dev->dev_addr, idprom->id_ethaddr, ETH_ALEN);
-	return 0;
-}
-#endif
-
 static int tg3_get_device_address(struct tg3 *tp)
 {
 	struct net_device *dev = tp->dev;
@@ -17006,10 +16992,8 @@ static int tg3_get_device_address(struct tg3 *tp)
 	int addr_ok = 0;
 	int err;
 
-#ifdef CONFIG_SPARC
-	if (!tg3_get_macaddr_sparc(tp))
+	if (!eth_platform_get_mac_address(&tp->pdev->dev, dev->dev_addr))
 		return 0;
-#endif
 
 	if (tg3_flag(tp, IS_SSB_CORE)) {
 		err = ssb_gige_get_macaddr(tp->pdev, &dev->dev_addr[0]);
@@ -17071,13 +17055,8 @@ static int tg3_get_device_address(struct tg3 *tp)
 		}
 	}
 
-	if (!is_valid_ether_addr(&dev->dev_addr[0])) {
-#ifdef CONFIG_SPARC
-		if (!tg3_get_default_macaddr_sparc(tp))
-			return 0;
-#endif
+	if (!is_valid_ether_addr(&dev->dev_addr[0]))
 		return -EINVAL;
-	}
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index a772a33b685c..6953d0546acb 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -2873,7 +2873,7 @@ struct tg3_tx_ring_info {
 struct tg3_link_config {
 	/* Describes what we're trying to get. */
 	u32				advertising;
-	u16				speed;
+	u32				speed;
 	u8				duplex;
 	u8				autoneg;
 	u8				flowctrl;
@@ -2882,7 +2882,7 @@ struct tg3_link_config {
 	u8				active_flowctrl;
 
 	u8				active_duplex;
-	u16				active_speed;
+	u32				active_speed;
 	u32				rmt_adv;
 };
 
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index a36e38676640..84741d288ffa 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -743,7 +743,7 @@ bfa_iocpf_sm_hwinit(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_TIMEOUT:
 		bfa_nw_ioc_hw_sem_release(ioc);
-			bfa_ioc_pf_failed(ioc);
+		bfa_ioc_pf_failed(ioc);
 		bfa_fsm_set_state(iocpf, bfa_iocpf_sm_initfail_sync);
 		break;
 
@@ -788,9 +788,8 @@ bfa_iocpf_sm_enabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_INITFAIL:
 		del_timer(&ioc->iocpf_timer);
-		/*
-		 * !!! fall through !!!
-		 */
+		/* fall through */
+
 	case IOCPF_E_TIMEOUT:
 		bfa_nw_ioc_hw_sem_release(ioc);
 		if (event == IOCPF_E_TIMEOUT)
@@ -858,9 +857,7 @@ bfa_iocpf_sm_disabling(struct bfa_iocpf *iocpf, enum iocpf_event event)
 
 	case IOCPF_E_FAIL:
 		del_timer(&ioc->iocpf_timer);
-		/*
-		 * !!! fall through !!!
-		 */
+		/* fall through*/
 
 	case IOCPF_E_TIMEOUT:
 		bfa_ioc_set_cur_ioc_fwstate(ioc, BFI_IOC_FAIL);
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 3d45f4c92cf6..acc66a7e7b95 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -643,6 +643,7 @@
 #define MACB_CAPS_JUMBO				0x00000020
 #define MACB_CAPS_GEM_HAS_PTP			0x00000040
 #define MACB_CAPS_BD_RD_PREFETCH		0x00000080
+#define MACB_CAPS_NEEDS_RSTONUBR		0x00000100
 #define MACB_CAPS_FIFO_MODE			0x10000000
 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE	0x20000000
 #define MACB_CAPS_SG_DISABLED			0x40000000
@@ -714,6 +715,8 @@
 		__v; \
 	})
 
+#define MACB_READ_NSR(bp)	macb_readl(bp, NSR)
+
 /* struct macb_dma_desc - Hardware DMA descriptor
  * @addr: DMA address of data buffer
  * @ctrl: Control and status bits
@@ -1082,7 +1085,7 @@ struct macb_config {
 	unsigned int		dma_burst_length;
 	int	(*clk_init)(struct platform_device *pdev, struct clk **pclk,
 			    struct clk **hclk, struct clk **tx_clk,
-			    struct clk **rx_clk);
+			    struct clk **rx_clk, struct clk **tsu_clk);
 	int	(*init)(struct platform_device *pdev);
 	int	jumbo_max_len;
 };
@@ -1162,6 +1165,7 @@ struct macb {
 	struct clk		*hclk;
 	struct clk		*tx_clk;
 	struct clk		*rx_clk;
+	struct clk		*tsu_clk;
 	struct net_device	*dev;
 	union {
 		struct macb_stats	macb;
@@ -1214,6 +1218,8 @@ struct macb {
 
 	int	rx_bd_rd_prefetch;
 	int	tx_bd_rd_prefetch;
+
+	u32	rx_intr_mask;
 };
 
 #ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4c816e5a841f..3da2795e2486 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -36,6 +36,8 @@
 #include <linux/ip.h>
 #include <linux/udp.h>
 #include <linux/tcp.h>
+#include <linux/iopoll.h>
+#include <linux/pm_runtime.h>
 #include "macb.h"
 
 #define MACB_RX_BUFFER_SIZE	128
@@ -56,8 +58,7 @@
 /* level of occupied TX descriptors under which we wake up TX process */
 #define MACB_TX_WAKEUP_THRESH(bp)	(3 * (bp)->tx_ring_size / 4)
 
-#define MACB_RX_INT_FLAGS	(MACB_BIT(RCOMP) | MACB_BIT(RXUBR)	\
-				 | MACB_BIT(ISR_ROVR))
+#define MACB_RX_INT_FLAGS	(MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR))
 #define MACB_TX_ERR_FLAGS	(MACB_BIT(ISR_TUND)			\
 					| MACB_BIT(ISR_RLE)		\
 					| MACB_BIT(TXERR))
@@ -80,6 +81,10 @@
  */
 #define MACB_HALT_TIMEOUT	1230
 
+#define MACB_PM_TIMEOUT  100 /* ms */
+
+#define MACB_MDIO_TIMEOUT	1000000 /* in usecs */
+
 /* DMA buffer descriptor might be different size
  * depends on hardware configuration:
  *
@@ -319,10 +324,26 @@ static void macb_get_hwaddr(struct macb *bp)
 	eth_hw_addr_random(bp->dev);
 }
 
+static int macb_mdio_wait_for_idle(struct macb *bp)
+{
+	u32 val;
+
+	return readx_poll_timeout(MACB_READ_NSR, bp, val, val & MACB_BIT(IDLE),
+				  1, MACB_MDIO_TIMEOUT);
+}
+
 static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct macb *bp = bus->priv;
-	int value;
+	int status;
+
+	status = pm_runtime_get_sync(&bp->pdev->dev);
+	if (status < 0)
+		goto mdio_pm_exit;
+
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_read_exit;
 
 	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_SOF)
 			      | MACB_BF(RW, MACB_MAN_READ)
@@ -330,19 +351,32 @@ static int macb_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 			      | MACB_BF(REGA, regnum)
 			      | MACB_BF(CODE, MACB_MAN_CODE)));
 
-	/* wait for end of transfer */
-	while (!MACB_BFEXT(IDLE, macb_readl(bp, NSR)))
-		cpu_relax();
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_read_exit;
 
-	value = MACB_BFEXT(DATA, macb_readl(bp, MAN));
+	status = MACB_BFEXT(DATA, macb_readl(bp, MAN));
 
-	return value;
+mdio_read_exit:
+	pm_runtime_mark_last_busy(&bp->pdev->dev);
+	pm_runtime_put_autosuspend(&bp->pdev->dev);
+mdio_pm_exit:
+	return status;
 }
 
 static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			   u16 value)
 {
 	struct macb *bp = bus->priv;
+	int status;
+
+	status = pm_runtime_get_sync(&bp->pdev->dev);
+	if (status < 0)
+		goto mdio_pm_exit;
+
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_write_exit;
 
 	macb_writel(bp, MAN, (MACB_BF(SOF, MACB_MAN_SOF)
 			      | MACB_BF(RW, MACB_MAN_WRITE)
@@ -351,11 +385,15 @@ static int macb_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			      | MACB_BF(CODE, MACB_MAN_CODE)
 			      | MACB_BF(DATA, value)));
 
-	/* wait for end of transfer */
-	while (!MACB_BFEXT(IDLE, macb_readl(bp, NSR)))
-		cpu_relax();
+	status = macb_mdio_wait_for_idle(bp);
+	if (status < 0)
+		goto mdio_write_exit;
 
-	return 0;
+mdio_write_exit:
+	pm_runtime_mark_last_busy(&bp->pdev->dev);
+	pm_runtime_put_autosuspend(&bp->pdev->dev);
+mdio_pm_exit:
+	return status;
 }
 
 /**
@@ -860,7 +898,9 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 
 			/* First, update TX stats if needed */
 			if (skb) {
-				if (gem_ptp_do_txstamp(queue, skb, desc) == 0) {
+				if (unlikely(skb_shinfo(skb)->tx_flags &
+					     SKBTX_HW_TSTAMP) &&
+				    gem_ptp_do_txstamp(queue, skb, desc) == 0) {
 					/* skb now belongs to timestamp buffer
 					 * and will be removed later
 					 */
@@ -1270,7 +1310,7 @@ static int macb_poll(struct napi_struct *napi, int budget)
 				queue_writel(queue, ISR, MACB_BIT(RCOMP));
 			napi_reschedule(napi);
 		} else {
-			queue_writel(queue, IER, MACB_RX_INT_FLAGS);
+			queue_writel(queue, IER, bp->rx_intr_mask);
 		}
 	}
 
@@ -1288,7 +1328,7 @@ static void macb_hresp_error_task(unsigned long data)
 	u32 ctrl;
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		queue_writel(queue, IDR, MACB_RX_INT_FLAGS |
+		queue_writel(queue, IDR, bp->rx_intr_mask |
 					 MACB_TX_INT_FLAGS |
 					 MACB_BIT(HRESP));
 	}
@@ -1318,7 +1358,7 @@ static void macb_hresp_error_task(unsigned long data)
 
 		/* Enable interrupts */
 		queue_writel(queue, IER,
-			     MACB_RX_INT_FLAGS |
+			     bp->rx_intr_mask |
 			     MACB_TX_INT_FLAGS |
 			     MACB_BIT(HRESP));
 	}
@@ -1372,14 +1412,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 			    (unsigned int)(queue - bp->queues),
 			    (unsigned long)status);
 
-		if (status & MACB_RX_INT_FLAGS) {
+		if (status & bp->rx_intr_mask) {
 			/* There's no point taking any more interrupts
 			 * until we have processed the buffers. The
 			 * scheduling call may fail if the poll routine
 			 * is already scheduled, so disable interrupts
 			 * now.
 			 */
-			queue_writel(queue, IDR, MACB_RX_INT_FLAGS);
+			queue_writel(queue, IDR, bp->rx_intr_mask);
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 				queue_writel(queue, ISR, MACB_BIT(RCOMP));
 
@@ -1412,8 +1452,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 		/* There is a hardware issue under heavy load where DMA can
 		 * stop, this causes endless "used buffer descriptor read"
 		 * interrupts but it can be cleared by re-enabling RX. See
-		 * the at91 manual, section 41.3.1 or the Zynq manual
-		 * section 16.7.4 for details.
+		 * the at91rm9200 manual, section 41.3.1 or the Zynq manual
+		 * section 16.7.4 for details. RXUBR is only enabled for
+		 * these two versions.
 		 */
 		if (status & MACB_BIT(RXUBR)) {
 			ctrl = macb_readl(bp, NCR);
@@ -1734,16 +1775,12 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
 		if (!nskb)
 			return -ENOMEM;
 
-		dev_kfree_skb_any(*skb);
+		dev_consume_skb_any(*skb);
 		*skb = nskb;
 	}
 
-	if (padlen) {
-		if (padlen >= ETH_FCS_LEN)
-			skb_put_zero(*skb, padlen - ETH_FCS_LEN);
-		else
-			skb_trim(*skb, ETH_FCS_LEN - padlen);
-	}
+	if (padlen > ETH_FCS_LEN)
+		skb_put_zero(*skb, padlen - ETH_FCS_LEN);
 
 add_fcs:
 	/* set FCS to packet */
@@ -2263,7 +2300,7 @@ static void macb_init_hw(struct macb *bp)
 
 		/* Enable interrupts */
 		queue_writel(queue, IER,
-			     MACB_RX_INT_FLAGS |
+			     bp->rx_intr_mask |
 			     MACB_TX_INT_FLAGS |
 			     MACB_BIT(HRESP));
 	}
@@ -2401,12 +2438,18 @@ static int macb_open(struct net_device *dev)
 
 	netdev_dbg(bp->dev, "open\n");
 
+	err = pm_runtime_get_sync(&bp->pdev->dev);
+	if (err < 0)
+		goto pm_exit;
+
 	/* carrier starts down */
 	netif_carrier_off(dev);
 
 	/* if the phy is not yet register, retry later*/
-	if (!dev->phydev)
-		return -EAGAIN;
+	if (!dev->phydev) {
+		err = -EAGAIN;
+		goto pm_exit;
+	}
 
 	/* RX buffers initialization */
 	macb_init_rx_buffer_size(bp, bufsz);
@@ -2415,7 +2458,7 @@ static int macb_open(struct net_device *dev)
 	if (err) {
 		netdev_err(dev, "Unable to allocate DMA memory (error %d)\n",
 			   err);
-		return err;
+		goto pm_exit;
 	}
 
 	bp->macbgem_ops.mog_init_rings(bp);
@@ -2432,6 +2475,11 @@ static int macb_open(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_init(dev);
 
+pm_exit:
+	if (err) {
+		pm_runtime_put_sync(&bp->pdev->dev);
+		return err;
+	}
 	return 0;
 }
 
@@ -2460,6 +2508,8 @@ static int macb_close(struct net_device *dev)
 	if (bp->ptp_info)
 		bp->ptp_info->ptp_remove(dev);
 
+	pm_runtime_put(&bp->pdev->dev);
+
 	return 0;
 }
 
@@ -3308,7 +3358,7 @@ static void macb_probe_queues(void __iomem *mem,
 
 static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 			 struct clk **hclk, struct clk **tx_clk,
-			 struct clk **rx_clk)
+			 struct clk **rx_clk, struct clk **tsu_clk)
 {
 	struct macb_platform_data *pdata;
 	int err;
@@ -3322,14 +3372,20 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 		*hclk = devm_clk_get(&pdev->dev, "hclk");
 	}
 
-	if (IS_ERR(*pclk)) {
+	if (IS_ERR_OR_NULL(*pclk)) {
 		err = PTR_ERR(*pclk);
+		if (!err)
+			err = -ENODEV;
+
 		dev_err(&pdev->dev, "failed to get macb_clk (%u)\n", err);
 		return err;
 	}
 
-	if (IS_ERR(*hclk)) {
+	if (IS_ERR_OR_NULL(*hclk)) {
 		err = PTR_ERR(*hclk);
+		if (!err)
+			err = -ENODEV;
+
 		dev_err(&pdev->dev, "failed to get hclk (%u)\n", err);
 		return err;
 	}
@@ -3342,6 +3398,10 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 	if (IS_ERR(*rx_clk))
 		*rx_clk = NULL;
 
+	*tsu_clk = devm_clk_get(&pdev->dev, "tsu_clk");
+	if (IS_ERR(*tsu_clk))
+		*tsu_clk = NULL;
+
 	err = clk_prepare_enable(*pclk);
 	if (err) {
 		dev_err(&pdev->dev, "failed to enable pclk (%u)\n", err);
@@ -3366,8 +3426,17 @@ static int macb_clk_init(struct platform_device *pdev, struct clk **pclk,
 		goto err_disable_txclk;
 	}
 
+	err = clk_prepare_enable(*tsu_clk);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable tsu_clk (%u)\n", err);
+		goto err_disable_rxclk;
+	}
+
 	return 0;
 
+err_disable_rxclk:
+	clk_disable_unprepare(*rx_clk);
+
 err_disable_txclk:
 	clk_disable_unprepare(*tx_clk);
 
@@ -3677,9 +3746,9 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb,
 		/* Store packet information (to free when Tx completed) */
 		lp->skb = skb;
 		lp->skb_length = skb->len;
-		lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len,
-							DMA_TO_DEVICE);
-		if (dma_mapping_error(NULL, lp->skb_physaddr)) {
+		lp->skb_physaddr = dma_map_single(&lp->pdev->dev, skb->data,
+						  skb->len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&lp->pdev->dev, lp->skb_physaddr)) {
 			dev_kfree_skb_any(skb);
 			dev->stats.tx_dropped++;
 			netdev_err(dev, "%s: DMA mapping error\n", __func__);
@@ -3767,9 +3836,9 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id)
 			dev->stats.tx_errors++;
 
 		if (lp->skb) {
-			dev_kfree_skb_irq(lp->skb);
+			dev_consume_skb_irq(lp->skb);
 			lp->skb = NULL;
-			dma_unmap_single(NULL, lp->skb_physaddr,
+			dma_unmap_single(&lp->pdev->dev, lp->skb_physaddr,
 					 lp->skb_length, DMA_TO_DEVICE);
 			dev->stats.tx_packets++;
 			dev->stats.tx_bytes += lp->skb_length;
@@ -3818,13 +3887,14 @@ static const struct net_device_ops at91ether_netdev_ops = {
 
 static int at91ether_clk_init(struct platform_device *pdev, struct clk **pclk,
 			      struct clk **hclk, struct clk **tx_clk,
-			      struct clk **rx_clk)
+			      struct clk **rx_clk, struct clk **tsu_clk)
 {
 	int err;
 
 	*hclk = NULL;
 	*tx_clk = NULL;
 	*rx_clk = NULL;
+	*tsu_clk = NULL;
 
 	*pclk = devm_clk_get(&pdev->dev, "ether_clk");
 	if (IS_ERR(*pclk))
@@ -3911,6 +3981,7 @@ static const struct macb_config sama5d4_config = {
 };
 
 static const struct macb_config emac_config = {
+	.caps = MACB_CAPS_NEEDS_RSTONUBR,
 	.clk_init = at91ether_clk_init,
 	.init = at91ether_init,
 };
@@ -3932,7 +4003,8 @@ static const struct macb_config zynqmp_config = {
 };
 
 static const struct macb_config zynq_config = {
-	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF,
+	.caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF |
+		MACB_CAPS_NEEDS_RSTONUBR,
 	.dma_burst_length = 16,
 	.clk_init = macb_clk_init,
 	.init = macb_init,
@@ -3945,6 +4017,7 @@ static const struct of_device_id macb_dt_ids[] = {
 	{ .compatible = "cdns,np4-macb", .data = &np4_config },
 	{ .compatible = "cdns,pc302-gem", .data = &pc302gem_config },
 	{ .compatible = "cdns,gem", .data = &pc302gem_config },
+	{ .compatible = "cdns,sam9x60-macb", .data = &at91sam9260_config },
 	{ .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config },
 	{ .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config },
 	{ .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config },
@@ -3972,11 +4045,12 @@ static int macb_probe(struct platform_device *pdev)
 {
 	const struct macb_config *macb_config = &default_gem_config;
 	int (*clk_init)(struct platform_device *, struct clk **,
-			struct clk **, struct clk **,  struct clk **)
-					      = macb_config->clk_init;
+			struct clk **, struct clk **,  struct clk **,
+			struct clk **) = macb_config->clk_init;
 	int (*init)(struct platform_device *) = macb_config->init;
 	struct device_node *np = pdev->dev.of_node;
 	struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL;
+	struct clk *tsu_clk = NULL;
 	unsigned int queue_mask, num_queues;
 	struct macb_platform_data *pdata;
 	bool native_io;
@@ -4004,10 +4078,15 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 
-	err = clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk);
+	err = clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk);
 	if (err)
 		return err;
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, MACB_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
 	native_io = hw_is_native_io(mem);
 
 	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
@@ -4041,6 +4120,7 @@ static int macb_probe(struct platform_device *pdev)
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
 	bp->rx_clk = rx_clk;
+	bp->tsu_clk = tsu_clk;
 	if (macb_config)
 		bp->jumbo_max_len = macb_config->jumbo_max_len;
 
@@ -4087,11 +4167,15 @@ static int macb_probe(struct platform_device *pdev)
 						macb_dma_desc_get_size(bp);
 	}
 
+	bp->rx_intr_mask = MACB_RX_INT_FLAGS;
+	if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR)
+		bp->rx_intr_mask |= MACB_BIT(RXUBR);
+
 	mac = of_get_mac_address(np);
 	if (mac) {
 		ether_addr_copy(bp->dev->dev_addr, mac);
 	} else {
-		err = of_get_nvmem_mac_address(np, bp->dev->dev_addr);
+		err = nvmem_get_mac_address(&pdev->dev, bp->dev->dev_addr);
 		if (err) {
 			if (err == -EPROBE_DEFER)
 				goto err_out_free_netdev;
@@ -4138,6 +4222,9 @@ static int macb_probe(struct platform_device *pdev)
 		    macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID),
 		    dev->base_addr, dev->irq, dev->dev_addr);
 
+	pm_runtime_mark_last_busy(&bp->pdev->dev);
+	pm_runtime_put_autosuspend(&bp->pdev->dev);
+
 	return 0;
 
 err_out_unregister_mdio:
@@ -4156,6 +4243,10 @@ err_disable_clocks:
 	clk_disable_unprepare(hclk);
 	clk_disable_unprepare(pclk);
 	clk_disable_unprepare(rx_clk);
+	clk_disable_unprepare(tsu_clk);
+	pm_runtime_disable(&pdev->dev);
+	pm_runtime_set_suspended(&pdev->dev);
+	pm_runtime_dont_use_autosuspend(&pdev->dev);
 
 	return err;
 }
@@ -4179,10 +4270,16 @@ static int macb_remove(struct platform_device *pdev)
 		mdiobus_free(bp->mii_bus);
 
 		unregister_netdev(dev);
-		clk_disable_unprepare(bp->tx_clk);
-		clk_disable_unprepare(bp->hclk);
-		clk_disable_unprepare(bp->pclk);
-		clk_disable_unprepare(bp->rx_clk);
+		pm_runtime_disable(&pdev->dev);
+		pm_runtime_dont_use_autosuspend(&pdev->dev);
+		if (!pm_runtime_suspended(&pdev->dev)) {
+			clk_disable_unprepare(bp->tx_clk);
+			clk_disable_unprepare(bp->hclk);
+			clk_disable_unprepare(bp->pclk);
+			clk_disable_unprepare(bp->rx_clk);
+			clk_disable_unprepare(bp->tsu_clk);
+			pm_runtime_set_suspended(&pdev->dev);
+		}
 		of_node_put(bp->phy_node);
 		free_netdev(dev);
 	}
@@ -4194,21 +4291,36 @@ static int __maybe_unused macb_suspend(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct macb *bp = netdev_priv(netdev);
+	struct macb_queue *queue = bp->queues;
+	unsigned long flags;
+	unsigned int q;
+
+	if (!netif_running(netdev))
+		return 0;
 
-	netif_carrier_off(netdev);
-	netif_device_detach(netdev);
 
 	if (bp->wol & MACB_WOL_ENABLED) {
 		macb_writel(bp, IER, MACB_BIT(WOL));
 		macb_writel(bp, WOL, MACB_BIT(MAG));
 		enable_irq_wake(bp->queues[0].irq);
+		netif_device_detach(netdev);
 	} else {
-		clk_disable_unprepare(bp->tx_clk);
-		clk_disable_unprepare(bp->hclk);
-		clk_disable_unprepare(bp->pclk);
-		clk_disable_unprepare(bp->rx_clk);
+		netif_device_detach(netdev);
+		for (q = 0, queue = bp->queues; q < bp->num_queues;
+		     ++q, ++queue)
+			napi_disable(&queue->napi);
+		phy_stop(netdev->phydev);
+		phy_suspend(netdev->phydev);
+		spin_lock_irqsave(&bp->lock, flags);
+		macb_reset_hw(bp);
+		spin_unlock_irqrestore(&bp->lock, flags);
 	}
 
+	netif_carrier_off(netdev);
+	if (bp->ptp_info)
+		bp->ptp_info->ptp_remove(netdev);
+	pm_runtime_force_suspend(dev);
+
 	return 0;
 }
 
@@ -4216,24 +4328,76 @@ static int __maybe_unused macb_resume(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
 	struct macb *bp = netdev_priv(netdev);
+	struct macb_queue *queue = bp->queues;
+	unsigned int q;
+
+	if (!netif_running(netdev))
+		return 0;
+
+	pm_runtime_force_resume(dev);
 
 	if (bp->wol & MACB_WOL_ENABLED) {
 		macb_writel(bp, IDR, MACB_BIT(WOL));
 		macb_writel(bp, WOL, 0);
 		disable_irq_wake(bp->queues[0].irq);
 	} else {
+		macb_writel(bp, NCR, MACB_BIT(MPE));
+		for (q = 0, queue = bp->queues; q < bp->num_queues;
+		     ++q, ++queue)
+			napi_enable(&queue->napi);
+		phy_resume(netdev->phydev);
+		phy_init_hw(netdev->phydev);
+		phy_start(netdev->phydev);
+	}
+
+	bp->macbgem_ops.mog_init_rings(bp);
+	macb_init_hw(bp);
+	macb_set_rx_mode(netdev);
+	netif_device_attach(netdev);
+	if (bp->ptp_info)
+		bp->ptp_info->ptp_init(netdev);
+
+	return 0;
+}
+
+static int __maybe_unused macb_runtime_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct net_device *netdev = platform_get_drvdata(pdev);
+	struct macb *bp = netdev_priv(netdev);
+
+	if (!(device_may_wakeup(&bp->dev->dev))) {
+		clk_disable_unprepare(bp->tx_clk);
+		clk_disable_unprepare(bp->hclk);
+		clk_disable_unprepare(bp->pclk);
+		clk_disable_unprepare(bp->rx_clk);
+	}
+	clk_disable_unprepare(bp->tsu_clk);
+
+	return 0;
+}
+
+static int __maybe_unused macb_runtime_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct net_device *netdev = platform_get_drvdata(pdev);
+	struct macb *bp = netdev_priv(netdev);
+
+	if (!(device_may_wakeup(&bp->dev->dev))) {
 		clk_prepare_enable(bp->pclk);
 		clk_prepare_enable(bp->hclk);
 		clk_prepare_enable(bp->tx_clk);
 		clk_prepare_enable(bp->rx_clk);
 	}
-
-	netif_device_attach(netdev);
+	clk_prepare_enable(bp->tsu_clk);
 
 	return 0;
 }
 
-static SIMPLE_DEV_PM_OPS(macb_pm_ops, macb_suspend, macb_resume);
+static const struct dev_pm_ops macb_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(macb_suspend, macb_resume)
+	SET_RUNTIME_PM_OPS(macb_runtime_suspend, macb_runtime_resume, NULL)
+};
 
 static struct platform_driver macb_driver = {
 	.probe		= macb_probe,
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 5f03199a3acf..6650e2a5f171 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -54,7 +54,6 @@ config CAVIUM_PTP
 	tristate "Cavium PTP coprocessor as PTP clock"
 	depends on 64BIT && PCI
 	imply PTP_1588_CLOCK
-	default y
 	---help---
 	  This driver adds support for the Precision Time Protocol Clocks and
 	  Timestamping coprocessor (PTP) found on Cavium processors.
@@ -65,7 +64,6 @@ config CAVIUM_PTP
 config LIQUIDIO
 	tristate "Cavium LiquidIO support"
 	depends on 64BIT && PCI
-	depends on MAY_USE_DEVLINK
 	depends on PCI
 	imply PTP_1588_CLOCK
 	select FW_LOADER
diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c
index 6aeb1045c302..73632b843749 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.c
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c
@@ -277,10 +277,6 @@ static int cavium_ptp_probe(struct pci_dev *pdev,
 	writeq(clock_comp, clock->reg_base + PTP_CLOCK_COMP);
 
 	clock->ptp_clock = ptp_clock_register(&clock->ptp_info, dev);
-	if (!clock->ptp_clock) {
-		err = -ENODEV;
-		goto error_stop;
-	}
 	if (IS_ERR(clock->ptp_clock)) {
 		err = PTR_ERR(clock->ptp_clock);
 		goto error_stop;
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 9f4f3c1d5043..43d11c38b38a 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1450,7 +1450,7 @@ void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx,
 		mbox_cmd.recv_len = 0;
 		mbox_cmd.recv_status = 0;
 		mbox_cmd.fn = NULL;
-		mbox_cmd.fn_arg = 0;
+		mbox_cmd.fn_arg = NULL;
 		ether_addr_copy(mbox_cmd.msg.s.params, mac);
 		mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf;
 		octeon_mbox_write(oct, &mbox_cmd);
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 825a28e5b544..1c50c10b5a16 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -661,7 +661,8 @@ liquidio_push_packet(u32 octeon_id __attribute__((unused)),
 		    (((rh->r_dh.encap_on) &&
 		      (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) ||
 		     (!(rh->r_dh.encap_on) &&
-		      (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED))))
+		      ((rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED) ==
+			CNNIC_CSUM_VERIFIED))))
 			/* checksum has already been verified */
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		else
@@ -1210,6 +1211,11 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
 
 	sc = (struct octeon_soft_command *)
 		octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, 16, 0);
+	if (!sc) {
+		netif_info(lio, rx_err, lio->netdev,
+			   "Failed to allocate soft command\n");
+		return -ENOMEM;
+	}
 
 	ncmd = (union octnet_cmd *)sc->virtdptr;
 
@@ -1683,6 +1689,11 @@ int liquidio_set_fec(struct lio *lio, int on_off)
 
 	sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
 				       sizeof(struct oct_nic_seapi_resp), 0);
+	if (!sc) {
+		dev_err(&oct->pci_dev->dev,
+			"Failed to allocate soft command\n");
+		return -ENOMEM;
+	}
 
 	ncmd = sc->virtdptr;
 	resp = sc->virtrptr;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 3d24133e5e49..fb6f813cff65 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -21,7 +21,6 @@
 #include <linux/firmware.h>
 #include <net/vxlan.h>
 #include <linux/kthread.h>
-#include <net/switchdev.h>
 #include "liquidio_common.h"
 #include "octeon_droq.h"
 #include "octeon_iq.h"
@@ -1193,6 +1192,11 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
 	sc = (struct octeon_soft_command *)
 		octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
 					  16, 0);
+	if (!sc) {
+		netif_info(lio, rx_err, lio->netdev,
+			   "Failed to allocate octeon_soft_command\n");
+		return;
+	}
 
 	ncmd = (union octnet_cmd *)sc->virtdptr;
 
@@ -2908,7 +2912,7 @@ static int liquidio_set_vf_spoofchk(struct net_device *netdev, int vfidx,
 	nctrl.ncmd.s.param2 = enable;
 	nctrl.ncmd.s.more = 0;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.cb_fn = NULL;
 
 	retval = octnet_send_nic_ctrl_pkt(oct, &nctrl);
 
@@ -3184,7 +3188,8 @@ static const struct devlink_ops liquidio_devlink_ops = {
 };
 
 static int
-lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+liquidio_get_port_parent_id(struct net_device *dev,
+			    struct netdev_phys_item_id *ppid)
 {
 	struct lio *lio = GET_LIO(dev);
 	struct octeon_device *oct = lio->oct_dev;
@@ -3192,24 +3197,12 @@ lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 	if (oct->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV)
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = ETH_ALEN;
-		ether_addr_copy(attr->u.ppid.id,
-				(void *)&lio->linfo.hw_addr + 2);
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = ETH_ALEN;
+	ether_addr_copy(ppid->id, (void *)&lio->linfo.hw_addr + 2);
 
 	return 0;
 }
 
-static const struct switchdev_ops lio_pf_switchdev_ops = {
-	.switchdev_port_attr_get = lio_pf_switchdev_attr_get,
-};
-
 static int liquidio_get_vf_stats(struct net_device *netdev, int vfidx,
 				 struct ifla_vf_stats *vf_stats)
 {
@@ -3259,6 +3252,7 @@ static const struct net_device_ops lionetdevops = {
 	.ndo_set_vf_trust	= liquidio_set_vf_trust,
 	.ndo_set_vf_link_state  = liquidio_set_vf_link_state,
 	.ndo_get_vf_stats	= liquidio_get_vf_stats,
+	.ndo_get_port_parent_id	= liquidio_get_port_parent_id,
 };
 
 /** \brief Entry point for the liquidio module
@@ -3534,7 +3528,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		 * netdev tasks.
 		 */
 		netdev->netdev_ops = &lionetdevops;
-		SWITCHDEV_SET_OPS(netdev, &lio_pf_switchdev_ops);
 
 		retval = netif_set_real_num_rx_queues(netdev, num_oqueues);
 		if (retval) {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
index de61060721c4..f3f2e71431ac 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -25,7 +25,6 @@
 #include "octeon_nic.h"
 #include "octeon_main.h"
 #include "octeon_network.h"
-#include <net/switchdev.h>
 #include "lio_vf_rep.h"
 
 static int lio_vf_rep_open(struct net_device *ndev);
@@ -38,6 +37,8 @@ static int lio_vf_rep_phys_port_name(struct net_device *dev,
 static void lio_vf_rep_get_stats64(struct net_device *dev,
 				   struct rtnl_link_stats64 *stats64);
 static int lio_vf_rep_change_mtu(struct net_device *ndev, int new_mtu);
+static int lio_vf_get_port_parent_id(struct net_device *dev,
+				     struct netdev_phys_item_id *ppid);
 
 static const struct net_device_ops lio_vf_rep_ndev_ops = {
 	.ndo_open = lio_vf_rep_open,
@@ -47,6 +48,7 @@ static const struct net_device_ops lio_vf_rep_ndev_ops = {
 	.ndo_get_phys_port_name = lio_vf_rep_phys_port_name,
 	.ndo_get_stats64 = lio_vf_rep_get_stats64,
 	.ndo_change_mtu = lio_vf_rep_change_mtu,
+	.ndo_get_port_parent_id = lio_vf_get_port_parent_id,
 };
 
 static int
@@ -443,31 +445,19 @@ xmit_failed:
 	return NETDEV_TX_OK;
 }
 
-static int
-lio_vf_rep_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static int lio_vf_get_port_parent_id(struct net_device *dev,
+				     struct netdev_phys_item_id *ppid)
 {
 	struct lio_vf_rep_desc *vf_rep = netdev_priv(dev);
 	struct net_device *parent_ndev = vf_rep->parent_ndev;
 	struct lio *lio = GET_LIO(parent_ndev);
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = ETH_ALEN;
-		ether_addr_copy(attr->u.ppid.id,
-				(void *)&lio->linfo.hw_addr + 2);
-		break;
-
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = ETH_ALEN;
+	ether_addr_copy(ppid->id, (void *)&lio->linfo.hw_addr + 2);
 
 	return 0;
 }
 
-static const struct switchdev_ops lio_vf_rep_switchdev_ops = {
-	.switchdev_port_attr_get        = lio_vf_rep_attr_get,
-};
-
 static void
 lio_vf_rep_fetch_stats(struct work_struct *work)
 {
@@ -524,7 +514,6 @@ lio_vf_rep_create(struct octeon_device *oct)
 		ndev->min_mtu = LIO_MIN_MTU_SIZE;
 		ndev->max_mtu = LIO_MAX_MTU_SIZE;
 		ndev->netdev_ops = &lio_vf_rep_ndev_ops;
-		SWITCHDEV_SET_OPS(ndev, &lio_vf_rep_switchdev_ops);
 
 		vf_rep = netdev_priv(ndev);
 		memset(vf_rep, 0, sizeof(*vf_rep));
diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
index 4b3aecf98f2a..5359c1021f42 100644
--- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
+++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c
@@ -1080,8 +1080,11 @@ static int octeon_mgmt_open(struct net_device *netdev)
 	/* Set the mode of the interface, RGMII/MII. */
 	if (OCTEON_IS_MODEL(OCTEON_CN6XXX) && netdev->phydev) {
 		union cvmx_agl_prtx_ctl agl_prtx_ctl;
-		int rgmii_mode = (netdev->phydev->supported &
-				  (SUPPORTED_1000baseT_Half | SUPPORTED_1000baseT_Full)) != 0;
+		int rgmii_mode =
+			(linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+					   netdev->phydev->supported) |
+			 linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+					   netdev->phydev->supported)) != 0;
 
 		agl_prtx_ctl.u64 = cvmx_read_csr(p->agl_prt_ctl);
 		agl_prtx_ctl.s.mode = rgmii_mode ? 0 : 1;
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index f4d81765221e..62636c1ed141 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -271,7 +271,7 @@ struct xcast_addr_list {
 };
 
 struct nicvf_work {
-	struct delayed_work    work;
+	struct work_struct     work;
 	u8                     mode;
 	struct xcast_addr_list *mc;
 };
@@ -327,7 +327,11 @@ struct nicvf {
 	struct nicvf_work       rx_mode_work;
 	/* spinlock to protect workqueue arguments from concurrent access */
 	spinlock_t              rx_mode_wq_lock;
-
+	/* workqueue for handling kernel ndo_set_rx_mode() calls */
+	struct workqueue_struct *nicvf_rx_mode_wq;
+	/* mutex to protect VF's mailbox contents from concurrent access */
+	struct mutex            rx_mode_mtx;
+	struct delayed_work	link_change_work;
 	/* PTP timestamp */
 	struct cavium_ptp	*ptp_clock;
 	/* Inbound timestamping is on */
@@ -575,10 +579,8 @@ struct set_ptp {
 
 struct xcast {
 	u8    msg;
-	union {
-		u8    mode;
-		u64   mac;
-	} data;
+	u8    mode;
+	u64   mac:48;
 };
 
 /* 128 bit shared memory between PF and each VF */
diff --git a/drivers/net/ethernet/cavium/thunder/nic_main.c b/drivers/net/ethernet/cavium/thunder/nic_main.c
index 6c8dcb65ff03..c90252829ed3 100644
--- a/drivers/net/ethernet/cavium/thunder/nic_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nic_main.c
@@ -57,14 +57,8 @@ struct nicpf {
 #define	NIC_GET_BGX_FROM_VF_LMAC_MAP(map)	((map >> 4) & 0xF)
 #define	NIC_GET_LMAC_FROM_VF_LMAC_MAP(map)	(map & 0xF)
 	u8			*vf_lmac_map;
-	struct delayed_work     dwork;
-	struct workqueue_struct *check_link;
-	u8			*link;
-	u8			*duplex;
-	u32			*speed;
 	u16			cpi_base[MAX_NUM_VFS_SUPPORTED];
 	u16			rssi_base[MAX_NUM_VFS_SUPPORTED];
-	bool			mbx_lock[MAX_NUM_VFS_SUPPORTED];
 
 	/* MSI-X */
 	u8			num_vec;
@@ -929,6 +923,35 @@ static void nic_config_timestamp(struct nicpf *nic, int vf, struct set_ptp *ptp)
 	nic_reg_write(nic, NIC_PF_PKIND_0_15_CFG | (pkind_idx << 3), pkind_val);
 }
 
+/* Get BGX LMAC link status and update corresponding VF
+ * if there is a change, valid only if internal L2 switch
+ * is not present otherwise VF link is always treated as up
+ */
+static void nic_link_status_get(struct nicpf *nic, u8 vf)
+{
+	union nic_mbx mbx = {};
+	struct bgx_link_status link;
+	u8 bgx, lmac;
+
+	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+
+	/* Get BGX, LMAC indices for the VF */
+	bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+	lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
+
+	/* Get interface link status */
+	bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
+
+	/* Send a mbox message to VF with current link status */
+	mbx.link_status.link_up = link.link_up;
+	mbx.link_status.duplex = link.duplex;
+	mbx.link_status.speed = link.speed;
+	mbx.link_status.mac_type = link.mac_type;
+
+	/* reply with link status */
+	nic_send_msg_to_vf(nic, vf, &mbx);
+}
+
 /* Interrupt handler to handle mailbox messages from VFs */
 static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 {
@@ -941,8 +964,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	int i;
 	int ret = 0;
 
-	nic->mbx_lock[vf] = true;
-
 	mbx_addr = nic_get_mbx_addr(vf);
 	mbx_data = (u64 *)&mbx;
 
@@ -957,12 +978,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	switch (mbx.msg.msg) {
 	case NIC_MBOX_MSG_READY:
 		nic_mbx_send_ready(nic, vf);
-		if (vf < nic->num_vf_en) {
-			nic->link[vf] = 0;
-			nic->duplex[vf] = 0;
-			nic->speed[vf] = 0;
-		}
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_QS_CFG:
 		reg_addr = NIC_PF_QSET_0_127_CFG |
 			   (mbx.qs.num << NIC_QS_ID_SHIFT);
@@ -1031,7 +1047,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_RSS_SIZE:
 		nic_send_rss_size(nic, vf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_RSS_CFG:
 	case NIC_MBOX_MSG_RSS_CFG_CONT:
 		nic_config_rss(nic, &mbx.rss_cfg);
@@ -1039,7 +1055,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 	case NIC_MBOX_MSG_CFG_DONE:
 		/* Last message of VF config msg sequence */
 		nic_enable_vf(nic, vf, true);
-		goto unlock;
+		break;
 	case NIC_MBOX_MSG_SHUTDOWN:
 		/* First msg in VF teardown sequence */
 		if (vf >= nic->num_vf_en)
@@ -1049,19 +1065,19 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
 		nic_alloc_sqs(nic, &mbx.sqs_alloc);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_NICVF_PTR:
 		nic->nicvf[vf] = mbx.nicvf.nicvf;
 		break;
 	case NIC_MBOX_MSG_PNICVF_PTR:
 		nic_send_pnicvf(nic, vf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_SNICVF_PTR:
 		nic_send_snicvf(nic, &mbx.nicvf);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_BGX_STATS:
 		nic_get_bgx_stats(nic, &mbx.bgx_stats);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_LOOPBACK:
 		ret = nic_config_loopback(nic, &mbx.lbk);
 		break;
@@ -1070,7 +1086,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		break;
 	case NIC_MBOX_MSG_PFC:
 		nic_pause_frame(nic, vf, &mbx.pfc);
-		goto unlock;
+		return;
 	case NIC_MBOX_MSG_PTP_CFG:
 		nic_config_timestamp(nic, vf, &mbx.ptp);
 		break;
@@ -1094,7 +1110,7 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		bgx_set_dmac_cam_filter(nic->node, bgx, lmac,
-					mbx.xcast.data.mac,
+					mbx.xcast.mac,
 					vf < NIC_VF_PER_MBX_REG ? vf :
 					vf - NIC_VF_PER_MBX_REG);
 		break;
@@ -1106,8 +1122,15 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 		}
 		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
 		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.data.mode);
+		bgx_set_xcast_mode(nic->node, bgx, lmac, mbx.xcast.mode);
 		break;
+	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
+		if (vf >= nic->num_vf_en) {
+			ret = -1; /* NACK */
+			break;
+		}
+		nic_link_status_get(nic, vf);
+		return;
 	default:
 		dev_err(&nic->pdev->dev,
 			"Invalid msg from VF%d, msg 0x%x\n", vf, mbx.msg.msg);
@@ -1121,8 +1144,6 @@ static void nic_handle_mbx_intr(struct nicpf *nic, int vf)
 			mbx.msg.msg, vf);
 		nic_mbx_send_nack(nic, vf);
 	}
-unlock:
-	nic->mbx_lock[vf] = false;
 }
 
 static irqreturn_t nic_mbx_intr_handler(int irq, void *nic_irq)
@@ -1270,52 +1291,6 @@ static int nic_sriov_init(struct pci_dev *pdev, struct nicpf *nic)
 	return 0;
 }
 
-/* Poll for BGX LMAC link status and update corresponding VF
- * if there is a change, valid only if internal L2 switch
- * is not present otherwise VF link is always treated as up
- */
-static void nic_poll_for_link(struct work_struct *work)
-{
-	union nic_mbx mbx = {};
-	struct nicpf *nic;
-	struct bgx_link_status link;
-	u8 vf, bgx, lmac;
-
-	nic = container_of(work, struct nicpf, dwork.work);
-
-	mbx.link_status.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
-
-	for (vf = 0; vf < nic->num_vf_en; vf++) {
-		/* Poll only if VF is UP */
-		if (!nic->vf_enabled[vf])
-			continue;
-
-		/* Get BGX, LMAC indices for the VF */
-		bgx = NIC_GET_BGX_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		lmac = NIC_GET_LMAC_FROM_VF_LMAC_MAP(nic->vf_lmac_map[vf]);
-		/* Get interface link status */
-		bgx_get_lmac_link_state(nic->node, bgx, lmac, &link);
-
-		/* Inform VF only if link status changed */
-		if (nic->link[vf] == link.link_up)
-			continue;
-
-		if (!nic->mbx_lock[vf]) {
-			nic->link[vf] = link.link_up;
-			nic->duplex[vf] = link.duplex;
-			nic->speed[vf] = link.speed;
-
-			/* Send a mbox message to VF with current link status */
-			mbx.link_status.link_up = link.link_up;
-			mbx.link_status.duplex = link.duplex;
-			mbx.link_status.speed = link.speed;
-			mbx.link_status.mac_type = link.mac_type;
-			nic_send_msg_to_vf(nic, vf, &mbx);
-		}
-	}
-	queue_delayed_work(nic->check_link, &nic->dwork, HZ * 2);
-}
-
 static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct device *dev = &pdev->dev;
@@ -1384,18 +1359,6 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!nic->vf_lmac_map)
 		goto err_release_regions;
 
-	nic->link = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL);
-	if (!nic->link)
-		goto err_release_regions;
-
-	nic->duplex = devm_kmalloc_array(dev, max_lmac, sizeof(u8), GFP_KERNEL);
-	if (!nic->duplex)
-		goto err_release_regions;
-
-	nic->speed = devm_kmalloc_array(dev, max_lmac, sizeof(u32), GFP_KERNEL);
-	if (!nic->speed)
-		goto err_release_regions;
-
 	/* Initialize hardware */
 	nic_init_hw(nic);
 
@@ -1411,22 +1374,8 @@ static int nic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_unregister_interrupts;
 
-	/* Register a physical link status poll fn() */
-	nic->check_link = alloc_workqueue("check_link_status",
-					  WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
-	if (!nic->check_link) {
-		err = -ENOMEM;
-		goto err_disable_sriov;
-	}
-
-	INIT_DELAYED_WORK(&nic->dwork, nic_poll_for_link);
-	queue_delayed_work(nic->check_link, &nic->dwork, 0);
-
 	return 0;
 
-err_disable_sriov:
-	if (nic->flags & NIC_SRIOV_ENABLED)
-		pci_disable_sriov(pdev);
 err_unregister_interrupts:
 	nic_unregister_interrupts(nic);
 err_release_regions:
@@ -1447,12 +1396,6 @@ static void nic_remove(struct pci_dev *pdev)
 	if (nic->flags & NIC_SRIOV_ENABLED)
 		pci_disable_sriov(pdev);
 
-	if (nic->check_link) {
-		/* Destroy work Queue */
-		cancel_delayed_work_sync(&nic->dwork);
-		destroy_workqueue(nic->check_link);
-	}
-
 	nic_unregister_interrupts(nic);
 	pci_release_regions(pdev);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 88f8a8fa93cd..c032bef1b776 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -32,6 +32,13 @@
 #define DRV_NAME	"nicvf"
 #define DRV_VERSION	"1.0"
 
+/* NOTE: Packets bigger than 1530 are split across multiple pages and XDP needs
+ * the buffer to be contiguous. Allow XDP to be set up only if we don't exceed
+ * this value, keeping headroom for the 14 byte Ethernet header and two
+ * VLAN tags (for QinQ)
+ */
+#define MAX_XDP_MTU	(1530 - ETH_HLEN - VLAN_HLEN * 2)
+
 /* Supported devices */
 static const struct pci_device_id nicvf_id_table[] = {
 	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM,
@@ -68,9 +75,6 @@ module_param(cpi_alg, int, 0444);
 MODULE_PARM_DESC(cpi_alg,
 		 "PFC algorithm (0=none, 1=VLAN, 2=VLAN16, 3=IP Diffserv)");
 
-/* workqueue for handling kernel ndo_set_rx_mode() calls */
-static struct workqueue_struct *nicvf_rx_mode_wq;
-
 static inline u8 nicvf_netdev_qidx(struct nicvf *nic, u8 qidx)
 {
 	if (nic->sqs_mode)
@@ -127,6 +131,9 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 {
 	int timeout = NIC_MBOX_MSG_TIMEOUT;
 	int sleep = 10;
+	int ret = 0;
+
+	mutex_lock(&nic->rx_mode_mtx);
 
 	nic->pf_acked = false;
 	nic->pf_nacked = false;
@@ -139,7 +146,8 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF NACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EINVAL;
+			ret = -EINVAL;
+			break;
 		}
 		msleep(sleep);
 		if (nic->pf_acked)
@@ -149,10 +157,12 @@ int nicvf_send_msg_to_pf(struct nicvf *nic, union nic_mbx *mbx)
 			netdev_err(nic->netdev,
 				   "PF didn't ACK to mbox msg 0x%02x from VF%d\n",
 				   (mbx->msg.msg & 0xFF), nic->vf_id);
-			return -EBUSY;
+			ret = -EBUSY;
+			break;
 		}
 	}
-	return 0;
+	mutex_unlock(&nic->rx_mode_mtx);
+	return ret;
 }
 
 /* Checks if VF is able to comminicate with PF
@@ -172,6 +182,17 @@ static int nicvf_check_pf_ready(struct nicvf *nic)
 	return 1;
 }
 
+static void nicvf_send_cfg_done(struct nicvf *nic)
+{
+	union nic_mbx mbx = {};
+
+	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
+	if (nicvf_send_msg_to_pf(nic, &mbx)) {
+		netdev_err(nic->netdev,
+			   "PF didn't respond to CFG DONE msg\n");
+	}
+}
+
 static void nicvf_read_bgx_stats(struct nicvf *nic, struct bgx_stats_msg *bgx)
 {
 	if (bgx->rx)
@@ -228,21 +249,24 @@ static void  nicvf_handle_mbx_intr(struct nicvf *nic)
 		break;
 	case NIC_MBOX_MSG_BGX_LINK_CHANGE:
 		nic->pf_acked = true;
-		nic->link_up = mbx.link_status.link_up;
-		nic->duplex = mbx.link_status.duplex;
-		nic->speed = mbx.link_status.speed;
-		nic->mac_type = mbx.link_status.mac_type;
-		if (nic->link_up) {
-			netdev_info(nic->netdev, "Link is Up %d Mbps %s duplex\n",
-				    nic->speed,
-				    nic->duplex == DUPLEX_FULL ?
-				    "Full" : "Half");
-			netif_carrier_on(nic->netdev);
-			netif_tx_start_all_queues(nic->netdev);
-		} else {
-			netdev_info(nic->netdev, "Link is Down\n");
-			netif_carrier_off(nic->netdev);
-			netif_tx_stop_all_queues(nic->netdev);
+		if (nic->link_up != mbx.link_status.link_up) {
+			nic->link_up = mbx.link_status.link_up;
+			nic->duplex = mbx.link_status.duplex;
+			nic->speed = mbx.link_status.speed;
+			nic->mac_type = mbx.link_status.mac_type;
+			if (nic->link_up) {
+				netdev_info(nic->netdev,
+					    "Link is Up %d Mbps %s duplex\n",
+					    nic->speed,
+					    nic->duplex == DUPLEX_FULL ?
+					    "Full" : "Half");
+				netif_carrier_on(nic->netdev);
+				netif_tx_start_all_queues(nic->netdev);
+			} else {
+				netdev_info(nic->netdev, "Link is Down\n");
+				netif_carrier_off(nic->netdev);
+				netif_tx_stop_all_queues(nic->netdev);
+			}
 		}
 		break;
 	case NIC_MBOX_MSG_ALLOC_SQS:
@@ -1311,6 +1335,12 @@ int nicvf_stop(struct net_device *netdev)
 	struct nicvf_cq_poll *cq_poll = NULL;
 	union nic_mbx mbx = {};
 
+	/* wait till all queued set_rx_mode tasks completes */
+	if (nic->nicvf_rx_mode_wq) {
+		cancel_delayed_work_sync(&nic->link_change_work);
+		drain_workqueue(nic->nicvf_rx_mode_wq);
+	}
+
 	mbx.msg.msg = NIC_MBOX_MSG_SHUTDOWN;
 	nicvf_send_msg_to_pf(nic, &mbx);
 
@@ -1410,13 +1440,28 @@ static int nicvf_update_hw_max_frs(struct nicvf *nic, int mtu)
 	return nicvf_send_msg_to_pf(nic, &mbx);
 }
 
+static void nicvf_link_status_check_task(struct work_struct *work_arg)
+{
+	struct nicvf *nic = container_of(work_arg,
+					 struct nicvf,
+					 link_change_work.work);
+	union nic_mbx mbx = {};
+	mbx.msg.msg = NIC_MBOX_MSG_BGX_LINK_CHANGE;
+	nicvf_send_msg_to_pf(nic, &mbx);
+	queue_delayed_work(nic->nicvf_rx_mode_wq,
+			   &nic->link_change_work, 2 * HZ);
+}
+
 int nicvf_open(struct net_device *netdev)
 {
 	int cpu, err, qidx;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct nicvf_cq_poll *cq_poll = NULL;
-	union nic_mbx mbx = {};
+
+	/* wait till all queued set_rx_mode tasks completes if any */
+	if (nic->nicvf_rx_mode_wq)
+		drain_workqueue(nic->nicvf_rx_mode_wq);
 
 	netif_carrier_off(netdev);
 
@@ -1512,8 +1557,14 @@ int nicvf_open(struct net_device *netdev)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
 	/* Send VF config done msg to PF */
-	mbx.msg.msg = NIC_MBOX_MSG_CFG_DONE;
-	nicvf_write_to_mbx(nic, &mbx);
+	nicvf_send_cfg_done(nic);
+
+	if (nic->nicvf_rx_mode_wq) {
+		INIT_DELAYED_WORK(&nic->link_change_work,
+				  nicvf_link_status_check_task);
+		queue_delayed_work(nic->nicvf_rx_mode_wq,
+				   &nic->link_change_work, 0);
+	}
 
 	return 0;
 cleanup:
@@ -1538,6 +1589,15 @@ static int nicvf_change_mtu(struct net_device *netdev, int new_mtu)
 	struct nicvf *nic = netdev_priv(netdev);
 	int orig_mtu = netdev->mtu;
 
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (nic->xdp_prog && new_mtu > MAX_XDP_MTU) {
+		netdev_warn(netdev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
+			    netdev->mtu);
+		return -EINVAL;
+	}
+
 	netdev->mtu = new_mtu;
 
 	if (!netif_running(netdev))
@@ -1786,8 +1846,10 @@ static int nicvf_xdp_setup(struct nicvf *nic, struct bpf_prog *prog)
 	bool bpf_attached = false;
 	int ret = 0;
 
-	/* For now just support only the usual MTU sized frames */
-	if (prog && (dev->mtu > 1500)) {
+	/* For now just support only the usual MTU sized frames,
+	 * plus some headroom for VLAN, QinQ.
+	 */
+	if (prog && dev->mtu > MAX_XDP_MTU) {
 		netdev_warn(dev, "Jumbo frames not yet supported with XDP, current MTU %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
@@ -1941,15 +2003,17 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 
 	/* flush DMAC filters and reset RX mode */
 	mbx.xcast.msg = NIC_MBOX_MSG_RESET_XCAST;
-	nicvf_send_msg_to_pf(nic, &mbx);
+	if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+		goto free_mc;
 
 	if (mode & BGX_XCAST_MCAST_FILTER) {
 		/* once enabling filtering, we need to signal to PF to add
 		 * its' own LMAC to the filter to accept packets for it.
 		 */
 		mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-		mbx.xcast.data.mac = 0;
-		nicvf_send_msg_to_pf(nic, &mbx);
+		mbx.xcast.mac = 0;
+		if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+			goto free_mc;
 	}
 
 	/* check if we have any specific MACs to be added to PF DMAC filter */
@@ -1957,23 +2021,25 @@ static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs,
 		/* now go through kernel list of MACs and add them one by one */
 		for (idx = 0; idx < mc_addrs->count; idx++) {
 			mbx.xcast.msg = NIC_MBOX_MSG_ADD_MCAST;
-			mbx.xcast.data.mac = mc_addrs->mc[idx];
-			nicvf_send_msg_to_pf(nic, &mbx);
+			mbx.xcast.mac = mc_addrs->mc[idx];
+			if (nicvf_send_msg_to_pf(nic, &mbx) < 0)
+				goto free_mc;
 		}
-		kfree(mc_addrs);
 	}
 
 	/* and finally set rx mode for PF accordingly */
 	mbx.xcast.msg = NIC_MBOX_MSG_SET_XCAST;
-	mbx.xcast.data.mode = mode;
+	mbx.xcast.mode = mode;
 
 	nicvf_send_msg_to_pf(nic, &mbx);
+free_mc:
+	kfree(mc_addrs);
 }
 
 static void nicvf_set_rx_mode_task(struct work_struct *work_arg)
 {
 	struct nicvf_work *vf_work = container_of(work_arg, struct nicvf_work,
-						  work.work);
+						  work);
 	struct nicvf *nic = container_of(vf_work, struct nicvf, rx_mode_work);
 	u8 mode;
 	struct xcast_addr_list *mc;
@@ -2030,7 +2096,7 @@ static void nicvf_set_rx_mode(struct net_device *netdev)
 	kfree(nic->rx_mode_work.mc);
 	nic->rx_mode_work.mc = mc_list;
 	nic->rx_mode_work.mode = mode;
-	queue_delayed_work(nicvf_rx_mode_wq, &nic->rx_mode_work.work, 0);
+	queue_work(nic->nicvf_rx_mode_wq, &nic->rx_mode_work.work);
 	spin_unlock(&nic->rx_mode_wq_lock);
 }
 
@@ -2187,8 +2253,18 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
-	INIT_DELAYED_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
+	nic->nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_rx_mode_wq_VF%d",
+							WQ_MEM_RECLAIM,
+							nic->vf_id);
+	if (!nic->nicvf_rx_mode_wq) {
+		err = -ENOMEM;
+		dev_err(dev, "Failed to allocate work queue\n");
+		goto err_unregister_interrupts;
+	}
+
+	INIT_WORK(&nic->rx_mode_work.work, nicvf_set_rx_mode_task);
 	spin_lock_init(&nic->rx_mode_wq_lock);
+	mutex_init(&nic->rx_mode_mtx);
 
 	err = register_netdev(netdev);
 	if (err) {
@@ -2228,13 +2304,15 @@ static void nicvf_remove(struct pci_dev *pdev)
 	nic = netdev_priv(netdev);
 	pnetdev = nic->pnicvf->netdev;
 
-	cancel_delayed_work_sync(&nic->rx_mode_work.work);
-
 	/* Check if this Qset is assigned to different VF.
 	 * If yes, clean primary and all secondary Qsets.
 	 */
 	if (pnetdev && (pnetdev->reg_state == NETREG_REGISTERED))
 		unregister_netdev(pnetdev);
+	if (nic->nicvf_rx_mode_wq) {
+		destroy_workqueue(nic->nicvf_rx_mode_wq);
+		nic->nicvf_rx_mode_wq = NULL;
+	}
 	nicvf_unregister_interrupts(nic);
 	pci_set_drvdata(pdev, NULL);
 	if (nic->drv_stats)
@@ -2261,17 +2339,11 @@ static struct pci_driver nicvf_driver = {
 static int __init nicvf_init_module(void)
 {
 	pr_info("%s, ver %s\n", DRV_NAME, DRV_VERSION);
-	nicvf_rx_mode_wq = alloc_ordered_workqueue("nicvf_generic",
-						   WQ_MEM_RECLAIM);
 	return pci_register_driver(&nicvf_driver);
 }
 
 static void __exit nicvf_cleanup_module(void)
 {
-	if (nicvf_rx_mode_wq) {
-		destroy_workqueue(nicvf_rx_mode_wq);
-		nicvf_rx_mode_wq = NULL;
-	}
 	pci_unregister_driver(&nicvf_driver);
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index fcaf18fa3904..e246f9733bb8 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -59,7 +59,7 @@ static int nicvf_alloc_q_desc_mem(struct nicvf *nic, struct q_desc_mem *dmem,
 	dmem->q_len = q_len;
 	dmem->size = (desc_size * q_len) + align_bytes;
 	/* Save address, need it while freeing */
-	dmem->unalign_base = dma_zalloc_coherent(&nic->pdev->dev, dmem->size,
+	dmem->unalign_base = dma_alloc_coherent(&nic->pdev->dev, dmem->size,
 						&dmem->dma, GFP_KERNEL);
 	if (!dmem->unalign_base)
 		return -ENOMEM;
@@ -105,20 +105,19 @@ static inline struct pgcache *nicvf_alloc_page(struct nicvf *nic,
 	/* Check if page can be recycled */
 	if (page) {
 		ref_count = page_ref_count(page);
-		/* Check if this page has been used once i.e 'put_page'
-		 * called after packet transmission i.e internal ref_count
-		 * and page's ref_count are equal i.e page can be recycled.
+		/* This page can be recycled if internal ref_count and page's
+		 * ref_count are equal, indicating that the page has been used
+		 * once for packet transmission. For non-XDP mode, internal
+		 * ref_count is always '1'.
 		 */
-		if (rbdr->is_xdp && (ref_count == pgcache->ref_count))
-			pgcache->ref_count--;
-		else
-			page = NULL;
-
-		/* In non-XDP mode, page's ref_count needs to be '1' for it
-		 * to be recycled.
-		 */
-		if (!rbdr->is_xdp && (ref_count != 1))
+		if (rbdr->is_xdp) {
+			if (ref_count == pgcache->ref_count)
+				pgcache->ref_count--;
+			else
+				page = NULL;
+		} else if (ref_count != 1) {
 			page = NULL;
+		}
 	}
 
 	if (!page) {
@@ -365,11 +364,10 @@ static void nicvf_free_rbdr(struct nicvf *nic, struct rbdr *rbdr)
 	while (head < rbdr->pgcnt) {
 		pgcache = &rbdr->pgcache[head];
 		if (pgcache->page && page_ref_count(pgcache->page) != 0) {
-			if (!rbdr->is_xdp) {
-				put_page(pgcache->page);
-				continue;
+			if (rbdr->is_xdp) {
+				page_ref_sub(pgcache->page,
+					     pgcache->ref_count - 1);
 			}
-			page_ref_sub(pgcache->page, pgcache->ref_count - 1);
 			put_page(pgcache->page);
 		}
 		head++;
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index e337da6ba2a4..673c57b8023f 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -1217,7 +1217,7 @@ static void bgx_init_hw(struct bgx *bgx)
 
 	/* Disable MAC steering (NCSI traffic) */
 	for (i = 0; i < RX_TRAFFIC_STEER_RULE_COUNT; i++)
-		bgx_reg_write(bgx, 0, BGX_CMR_RX_STREERING + (i * 8), 0x00);
+		bgx_reg_write(bgx, 0, BGX_CMR_RX_STEERING + (i * 8), 0x00);
 }
 
 static u8 bgx_get_lane2sds_cfg(struct bgx *bgx, struct lmac *lmac)
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
index cbdd20b9ee6f..5cbc54e9eb19 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h
@@ -60,7 +60,7 @@
 #define  RX_DMACX_CAM_EN			BIT_ULL(48)
 #define  RX_DMACX_CAM_LMACID(x)			(((u64)x) << 49)
 #define  RX_DMAC_COUNT				32
-#define BGX_CMR_RX_STREERING		0x300
+#define BGX_CMR_RX_STEERING		0x300
 #define  RX_TRAFFIC_STEER_RULE_COUNT		8
 #define BGX_CMR_CHAN_MSK_AND		0x450
 #define BGX_CMR_BIST_STATUS		0x460
diff --git a/drivers/net/ethernet/chelsio/Kconfig b/drivers/net/ethernet/chelsio/Kconfig
index e2cdfa75673f..e8001e974411 100644
--- a/drivers/net/ethernet/chelsio/Kconfig
+++ b/drivers/net/ethernet/chelsio/Kconfig
@@ -24,7 +24,8 @@ config CHELSIO_T1
 	---help---
 	  This driver supports Chelsio gigabit and 10-gigabit
 	  Ethernet cards. More information about adapter features and
-	  performance tuning is in <file:Documentation/networking/cxgb.txt>.
+	  performance tuning is in
+	  <file:Documentation/networking/device_drivers/chelsio/cxgb.txt>.
 
 	  For general information about Chelsio and our products, visit
 	  our website at <http://www.chelsio.com>.
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 30de26ef3da4..47b5c8e2104b 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -585,8 +585,7 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p)
 		sizeof(struct cpl_rx_data) +
 		sge->freelQ[!sge->jumbo_fl].dma_offset;
 
-		size = (16 * 1024) -
-		    SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	size = (16 * 1024) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	sge->freelQ[sge->jumbo_fl].rx_buffer_size = size;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c
index 20b6e1b3f5e3..89db739b7819 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -620,7 +620,7 @@ static void *alloc_ring(struct pci_dev *pdev, size_t nelem, size_t elem_size,
 {
 	size_t len = nelem * elem_size;
 	void *s = NULL;
-	void *p = dma_zalloc_coherent(&pdev->dev, len, phys, GFP_KERNEL);
+	void *p = dma_alloc_coherent(&pdev->dev, len, phys, GFP_KERNEL);
 
 	if (!p)
 		return NULL;
@@ -2381,7 +2381,7 @@ no_mem:
 					lro_add_page(adap, qs, fl,
 						     G_RSPD_LEN(len),
 						     flags & F_RSPD_EOP);
-					 goto next_fl;
+					goto next_fl;
 				}
 
 				skb = get_packet_pg(adap, fl, q,
@@ -3214,11 +3214,13 @@ void t3_start_sge_timers(struct adapter *adap)
 	for (i = 0; i < SGE_QSETS; ++i) {
 		struct sge_qset *q = &adap->sge.qs[i];
 
-	if (q->tx_reclaim_timer.function)
-		mod_timer(&q->tx_reclaim_timer, jiffies + TX_RECLAIM_PERIOD);
+		if (q->tx_reclaim_timer.function)
+			mod_timer(&q->tx_reclaim_timer,
+				  jiffies + TX_RECLAIM_PERIOD);
 
-	if (q->rx_reclaim_timer.function)
-		mod_timer(&q->rx_reclaim_timer, jiffies + RX_RECLAIM_PERIOD);
+		if (q->rx_reclaim_timer.function)
+			mod_timer(&q->rx_reclaim_timer,
+				  jiffies + RX_RECLAIM_PERIOD);
 	}
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
index 080918af773c..0a9f2c596624 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c
@@ -1082,7 +1082,7 @@ int t3_check_fw_version(struct adapter *adapter)
 		CH_WARN(adapter, "found newer FW version(%u.%u), "
 		        "driver compiled for version %u.%u\n", major, minor,
 			FW_VERSION_MAJOR, FW_VERSION_MINOR);
-			return 0;
+		return 0;
 	}
 	return -EINVAL;
 }
@@ -3619,7 +3619,7 @@ int t3_reset_adapter(struct adapter *adapter)
 
 static int init_parity(struct adapter *adap)
 {
-		int i, err, addr;
+	int i, err, addr;
 
 	if (t3_read_reg(adap, A_SG_CONTEXT_CMD) & F_CONTEXT_CMD_BUSY)
 		return -EBUSY;
@@ -3806,6 +3806,6 @@ int t3_replay_prep_adapter(struct adapter *adapter)
 		p->phy.ops->power_down(&p->phy, 1);
 	}
 
-return 0;
+	return 0;
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
index 5701272aa7f7..ce28820c57c9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c
@@ -289,8 +289,7 @@ struct clip_tbl *t4_init_clip_tbl(unsigned int clipt_start,
 	if (clipt_size < CLIPT_MIN_HASH_BUCKETS)
 		return NULL;
 
-	ctbl = kvzalloc(sizeof(*ctbl) +
-			    clipt_size*sizeof(struct list_head), GFP_KERNEL);
+	ctbl = kvzalloc(struct_size(ctbl, hash_list, clipt_size), GFP_KERNEL);
 	if (!ctbl)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 7c49681407ad..7c5bfc931128 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -81,7 +81,7 @@ static int is_fw_attached(struct cudbg_init *pdbg_init)
 {
 	struct adapter *padap = pdbg_init->adap;
 
-	if (!(padap->flags & FW_OK) || padap->use_bd)
+	if (!(padap->flags & CXGB4_FW_OK) || padap->use_bd)
 		return 0;
 
 	return 1;
@@ -1229,6 +1229,10 @@ int cudbg_collect_hw_sched(struct cudbg_init *pdbg_init,
 
 	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_hw_sched),
 			    &temp_buff);
+
+	if (rc)
+		return rc;
+
 	hw_sched_buff = (struct cudbg_hw_sched *)temp_buff.data;
 	hw_sched_buff->map = t4_read_reg(padap, TP_TX_MOD_QUEUE_REQ_MAP_A);
 	hw_sched_buff->mode = TIMERMODE_G(t4_read_reg(padap, TP_MOD_CONFIG_A));
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index b16f4b3ef4c5..956219c178e1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -404,6 +404,7 @@ struct adapter_params {
 	bool fr_nsmr_tpte_wr_support;	  /* FW support for FR_NSMR_TPTE_WR */
 	u8 fw_caps_support;		/* 32-bit Port Capabilities */
 	bool filter2_wr_support;	/* FW support for FILTER2_WR */
+	unsigned int viid_smt_extn_support:1; /* FW returns vin and smt index */
 
 	/* MPS Buffer Group Map[per Port].  Bit i is set if buffer group i is
 	 * used by the Port
@@ -567,7 +568,7 @@ struct sge_rspq;
 struct port_info {
 	struct adapter *adapter;
 	u16    viid;
-	s16    xact_addr_filt;        /* index of exact MAC address filter */
+	int    xact_addr_filt;        /* index of exact MAC address filter */
 	u16    rss_size;              /* size of VI's RSS table slice */
 	s8     mdio_addr;
 	enum fw_port_type port_type;
@@ -592,23 +593,31 @@ struct port_info {
 	bool ptp_enable;
 	struct sched_table *sched_tbl;
 	u32 eth_flags;
+
+	/* viid and smt fields either returned by fw
+	 * or decoded by parsing viid by driver.
+	 */
+	u8 vin;
+	u8 vivld;
+	u8 smt_idx;
 };
 
 struct dentry;
 struct work_struct;
 
 enum {                                 /* adapter flags */
-	FULL_INIT_DONE     = (1 << 0),
-	DEV_ENABLED        = (1 << 1),
-	USING_MSI          = (1 << 2),
-	USING_MSIX         = (1 << 3),
-	FW_OK              = (1 << 4),
-	RSS_TNLALLLOOKUP   = (1 << 5),
-	USING_SOFT_PARAMS  = (1 << 6),
-	MASTER_PF          = (1 << 7),
-	FW_OFLD_CONN       = (1 << 9),
-	ROOT_NO_RELAXED_ORDERING = (1 << 10),
-	SHUTTING_DOWN	   = (1 << 11),
+	CXGB4_FULL_INIT_DONE		= (1 << 0),
+	CXGB4_DEV_ENABLED		= (1 << 1),
+	CXGB4_USING_MSI			= (1 << 2),
+	CXGB4_USING_MSIX		= (1 << 3),
+	CXGB4_FW_OK			= (1 << 4),
+	CXGB4_RSS_TNLALLLOOKUP		= (1 << 5),
+	CXGB4_USING_SOFT_PARAMS		= (1 << 6),
+	CXGB4_MASTER_PF			= (1 << 7),
+	CXGB4_FW_OFLD_CONN		= (1 << 9),
+	CXGB4_ROOT_NO_RELAXED_ORDERING	= (1 << 10),
+	CXGB4_SHUTTING_DOWN		= (1 << 11),
+	CXGB4_SGE_DBQ_TIMER		= (1 << 12),
 };
 
 enum {
@@ -748,6 +757,8 @@ struct sge_eth_txq {                /* state for an SGE Ethernet Tx queue */
 #ifdef CONFIG_CHELSIO_T4_DCB
 	u8 dcb_prio;		    /* DCB Priority bound to queue */
 #endif
+	u8 dbqt;                    /* SGE Doorbell Queue Timer in use */
+	unsigned int dbqtimerix;    /* SGE Doorbell Queue Timer Index */
 	unsigned long tso;          /* # of TSO requests */
 	unsigned long tx_cso;       /* # of Tx checksum offloads */
 	unsigned long vlan_ins;     /* # of Tx VLAN insertions */
@@ -808,6 +819,8 @@ struct sge {
 	u16 nqs_per_uld;	    /* # of Rx queues per ULD */
 	u16 timer_val[SGE_NTIMERS];
 	u8 counter_val[SGE_NCOUNTERS];
+	u16 dbqtimer_tick;
+	u16 dbqtimer_val[SGE_NDBQTIMERS];
 	u32 fl_pg_order;            /* large page allocation size */
 	u32 stat_len;               /* length of status page at ring end */
 	u32 pktshift;               /* padding between CPL & packet data */
@@ -852,6 +865,7 @@ struct doorbell_stats {
 struct hash_mac_addr {
 	struct list_head list;
 	u8 addr[ETH_ALEN];
+	unsigned int iface_mac;
 };
 
 struct uld_msix_bmap {
@@ -871,6 +885,7 @@ struct vf_info {
 	unsigned int tx_rate;
 	bool pf_set_mac;
 	u16 vlan;
+	int link_state;
 };
 
 enum {
@@ -1393,7 +1408,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		     rspq_flush_handler_t flush_handler, int cong);
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
-			 unsigned int iqid);
+			 unsigned int iqid, u8 dbqt);
 int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 			  struct net_device *dev, unsigned int iqid,
 			  unsigned int cmplqid);
@@ -1406,6 +1421,8 @@ irqreturn_t t4_sge_intr_msix(int irq, void *cookie);
 int t4_sge_init(struct adapter *adap);
 void t4_sge_start(struct adapter *adap);
 void t4_sge_stop(struct adapter *adap);
+int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *q,
+				 int maxreclaim);
 void cxgb4_set_ethtool_ops(struct net_device *netdev);
 int cxgb4_write_rss(const struct port_info *pi, const u16 *queues);
 enum cpl_tx_tnl_lso_type cxgb_encap_offload_supported(struct sk_buff *skb);
@@ -1757,7 +1774,7 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		unsigned int nexact, unsigned int rcaps, unsigned int wxcaps);
 int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		unsigned int pf, unsigned int vf, unsigned int nmac, u8 *mac,
-		unsigned int *rss_size);
+		unsigned int *rss_size, u8 *vivld, u8 *vin);
 int t4_free_vi(struct adapter *adap, unsigned int mbox,
 	       unsigned int pf, unsigned int vf,
 	       unsigned int viid);
@@ -1783,7 +1800,7 @@ int t4_free_mac_filt(struct adapter *adap, unsigned int mbox,
 		     unsigned int viid, unsigned int naddr,
 		     const u8 **addr, bool sleep_ok);
 int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
-		  int idx, const u8 *addr, bool persist, bool add_smt);
+		  int idx, const u8 *addr, bool persist, u8 *smt_idx);
 int t4_set_addr_hash(struct adapter *adap, unsigned int mbox, unsigned int viid,
 		     bool ucast, u64 vec, bool sleep_ok);
 int t4_enable_vi_params(struct adapter *adap, unsigned int mbox,
@@ -1812,6 +1829,8 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf,
 		    unsigned int vf, unsigned int eqid);
 int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type);
+int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers,
+			  u16 *dbqtimers);
 void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl);
 int t4_update_port_info(struct port_info *pi);
 int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index cab492ec8f59..02959035ed3f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -378,19 +378,7 @@ static int cim_qcfg_show(struct seq_file *seq, void *v)
 			   QUEREMFLITS_G(p[2]) * 16);
 	return 0;
 }
-
-static int cim_qcfg_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, cim_qcfg_show, inode->i_private);
-}
-
-static const struct file_operations cim_qcfg_fops = {
-	.owner   = THIS_MODULE,
-	.open    = cim_qcfg_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(cim_qcfg);
 
 static int cimq_show(struct seq_file *seq, void *v, int idx)
 {
@@ -860,8 +848,7 @@ static int tx_rate_show(struct seq_file *seq, void *v)
 	}
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(tx_rate);
+DEFINE_SHOW_ATTRIBUTE(tx_rate);
 
 static int cctrl_tbl_show(struct seq_file *seq, void *v)
 {
@@ -893,8 +880,7 @@ static int cctrl_tbl_show(struct seq_file *seq, void *v)
 	kfree(incr);
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(cctrl_tbl);
+DEFINE_SHOW_ATTRIBUTE(cctrl_tbl);
 
 /* Format a value in a unit that differs from the value's native unit by the
  * given factor.
@@ -955,8 +941,7 @@ static int clk_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(clk);
+DEFINE_SHOW_ATTRIBUTE(clk);
 
 /* Firmware Device Log dump. */
 static const char * const devlog_level_strings[] = {
@@ -1990,22 +1975,10 @@ static int sensors_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(sensors);
+DEFINE_SHOW_ATTRIBUTE(sensors);
 
 #if IS_ENABLED(CONFIG_IPV6)
-static int clip_tbl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, clip_tbl_show, inode->i_private);
-}
-
-static const struct file_operations clip_tbl_debugfs_fops = {
-	.owner   = THIS_MODULE,
-	.open    = clip_tbl_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release
-};
+DEFINE_SHOW_ATTRIBUTE(clip_tbl);
 #endif
 
 /*RSS Table.
@@ -2208,8 +2181,7 @@ static int rss_config_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(rss_config);
+DEFINE_SHOW_ATTRIBUTE(rss_config);
 
 /* RSS Secret Key.
  */
@@ -2628,19 +2600,7 @@ static int resources_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int resources_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, resources_show, inode->i_private);
-}
-
-static const struct file_operations resources_debugfs_fops = {
-	.owner   = THIS_MODULE,
-	.open    = resources_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = seq_release,
-};
+DEFINE_SHOW_ATTRIBUTE(resources);
 
 /**
  * ethqset2pinfo - return port_info of an Ethernet Queue Set
@@ -2660,7 +2620,7 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset)
 	}
 
 	/* should never happen! */
-	BUG_ON(1);
+	BUG();
 	return NULL;
 }
 
@@ -3183,7 +3143,7 @@ static int tid_info_show(struct seq_file *seq, void *v)
 			seq_printf(seq, ", in use: %u/%u\n",
 				   atomic_read(&t->tids_in_use),
 				   atomic_read(&t->hash_tids_in_use));
-		} else if (adap->flags & FW_OFLD_CONN) {
+		} else if (adap->flags & CXGB4_FW_OFLD_CONN) {
 			seq_printf(seq, "TID range: %u..%u/%u..%u",
 				   t->aftid_base,
 				   t->aftid_end,
@@ -3233,8 +3193,7 @@ static int tid_info_show(struct seq_file *seq, void *v)
 			   t4_read_reg(adap, LE_DB_ACT_CNT_IPV6_A));
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(tid_info);
+DEFINE_SHOW_ATTRIBUTE(tid_info);
 
 static void add_debugfs_mem(struct adapter *adap, const char *name,
 			    unsigned int idx, unsigned int size_mb)
@@ -3364,21 +3323,9 @@ static int meminfo_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(meminfo);
 
-static int meminfo_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, meminfo_show, inode->i_private);
-}
-
-static const struct file_operations meminfo_fops = {
-	.owner   = THIS_MODULE,
-	.open    = meminfo_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
-
-static int chcr_show(struct seq_file *seq, void *v)
+static int chcr_stats_show(struct seq_file *seq, void *v)
 {
 	struct adapter *adap = seq->private;
 
@@ -3399,20 +3346,7 @@ static int chcr_show(struct seq_file *seq, void *v)
 		   atomic_read(&adap->chcr_stats.ipsec_cnt));
 	return 0;
 }
-
-
-static int chcr_stats_open(struct inode *inode, struct file *file)
-{
-        return single_open(file, chcr_show, inode->i_private);
-}
-
-static const struct file_operations chcr_stats_debugfs_fops = {
-        .owner   = THIS_MODULE,
-        .open    = chcr_stats_open,
-        .read    = seq_read,
-        .llseek  = seq_lseek,
-        .release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(chcr_stats);
 
 #define PRINT_ADAP_STATS(string, value) \
 	seq_printf(seq, "%-25s %-20llu\n", (string), \
@@ -3573,8 +3507,7 @@ static int tp_stats_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-DEFINE_SIMPLE_DEBUGFS_FILE(tp_stats);
+DEFINE_SHOW_ATTRIBUTE(tp_stats);
 
 /* Add an array of Debug FS files.
  */
@@ -3603,7 +3536,7 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "cim_pif_la", &cim_pif_la_fops, 0400, 0 },
 		{ "cim_ma_la", &cim_ma_la_fops, 0400, 0 },
 		{ "cim_qcfg", &cim_qcfg_fops, 0400, 0 },
-		{ "clk", &clk_debugfs_fops, 0400, 0 },
+		{ "clk", &clk_fops, 0400, 0 },
 		{ "devlog", &devlog_fops, 0400, 0 },
 		{ "mboxlog", &mboxlog_fops, 0400, 0 },
 		{ "mbox0", &mbox_debugfs_fops, 0600, 0 },
@@ -3621,11 +3554,11 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "l2t", &t4_l2t_fops, 0400, 0},
 		{ "mps_tcam", &mps_tcam_debugfs_fops, 0400, 0 },
 		{ "rss", &rss_debugfs_fops, 0400, 0 },
-		{ "rss_config", &rss_config_debugfs_fops, 0400, 0 },
+		{ "rss_config", &rss_config_fops, 0400, 0 },
 		{ "rss_key", &rss_key_debugfs_fops, 0400, 0 },
 		{ "rss_pf_config", &rss_pf_config_debugfs_fops, 0400, 0 },
 		{ "rss_vf_config", &rss_vf_config_debugfs_fops, 0400, 0 },
-		{ "resources", &resources_debugfs_fops, 0400, 0 },
+		{ "resources", &resources_fops, 0400, 0 },
 #ifdef CONFIG_CHELSIO_T4_DCB
 		{ "dcb_info", &dcb_info_debugfs_fops, 0400, 0 },
 #endif
@@ -3644,18 +3577,18 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "obq_ncsi", &cim_obq_fops, 0400, 5 },
 		{ "tp_la", &tp_la_fops, 0400, 0 },
 		{ "ulprx_la", &ulprx_la_fops, 0400, 0 },
-		{ "sensors", &sensors_debugfs_fops, 0400, 0 },
+		{ "sensors", &sensors_fops, 0400, 0 },
 		{ "pm_stats", &pm_stats_debugfs_fops, 0400, 0 },
-		{ "tx_rate", &tx_rate_debugfs_fops, 0400, 0 },
-		{ "cctrl", &cctrl_tbl_debugfs_fops, 0400, 0 },
+		{ "tx_rate", &tx_rate_fops, 0400, 0 },
+		{ "cctrl", &cctrl_tbl_fops, 0400, 0 },
 #if IS_ENABLED(CONFIG_IPV6)
-		{ "clip_tbl", &clip_tbl_debugfs_fops, 0400, 0 },
+		{ "clip_tbl", &clip_tbl_fops, 0400, 0 },
 #endif
-		{ "tids", &tid_info_debugfs_fops, 0400, 0},
+		{ "tids", &tid_info_fops, 0400, 0},
 		{ "blocked_fl", &blocked_fl_fops, 0600, 0 },
 		{ "meminfo", &meminfo_fops, 0400, 0 },
-		{ "crypto", &chcr_stats_debugfs_fops, 0400, 0 },
-		{ "tp_stats", &tp_stats_debugfs_fops, 0400, 0 },
+		{ "crypto", &chcr_stats_fops, 0400, 0 },
+		{ "tp_stats", &tp_stats_fops, 0400, 0 },
 	};
 
 	/* Debug FS nodes common to all T5 and later adapters.
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h
index 23f43a0f8950..ba95e13d52da 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.h
@@ -37,19 +37,6 @@
 
 #include <linux/export.h>
 
-#define DEFINE_SIMPLE_DEBUGFS_FILE(name) \
-static int name##_open(struct inode *inode, struct file *file) \
-{ \
-	return single_open(file, name##_show, inode->i_private); \
-} \
-static const struct file_operations name##_debugfs_fops = { \
-	.owner   = THIS_MODULE, \
-	.open    = name##_open, \
-	.read    = seq_read, \
-	.llseek  = seq_lseek, \
-	.release = single_release \
-}
-
 struct t4_debugfs_entry {
 	const char *name;
 	const struct file_operations *ops;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index d07230c892a5..bec4711005cc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -446,8 +446,10 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 			   unsigned long *link_mode_mask)
 {
 	#define SET_LMM(__lmm_name) \
-		__set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \
-			  link_mode_mask)
+		do { \
+			__set_bit(ETHTOOL_LINK_MODE_ ## __lmm_name ## _BIT, \
+				  link_mode_mask); \
+		} while (0)
 
 	#define FW_CAPS_TO_LMM(__fw_name, __lmm_name) \
 		do { \
@@ -541,7 +543,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 	case FW_PORT_TYPE_CR4_QSFP:
 		SET_LMM(FIBRE);
 		FW_CAPS_TO_LMM(SPEED_1G,  1000baseT_Full);
-		FW_CAPS_TO_LMM(SPEED_10G, 10000baseSR_Full);
+		FW_CAPS_TO_LMM(SPEED_10G, 10000baseKR_Full);
 		FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full);
 		FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full);
 		FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full);
@@ -552,6 +554,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 		break;
 	}
 
+	if (fw_caps & FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M)) {
+		FW_CAPS_TO_LMM(FEC_RS, FEC_RS);
+		FW_CAPS_TO_LMM(FEC_BASER_RS, FEC_BASER);
+	} else {
+		SET_LMM(FEC_NONE);
+	}
+
 	FW_CAPS_TO_LMM(ANEG, Autoneg);
 	FW_CAPS_TO_LMM(802_3_PAUSE, Pause);
 	FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause);
@@ -679,18 +688,15 @@ static int set_link_ksettings(struct net_device *dev,
 	    base->autoneg == AUTONEG_DISABLE) {
 		fw_caps = speed_to_fw_caps(base->speed);
 
-		/* Must only specify a single speed which must be supported
-		 * as part of the Physical Port Capabilities.
-		 */
-		if ((fw_caps & (fw_caps - 1)) != 0 ||
-		    !(lc->pcaps & fw_caps))
+		/* Speed must be supported by Physical Port Capabilities. */
+		if (!(lc->pcaps & fw_caps))
 			return -EINVAL;
 
 		lc->speed_caps = fw_caps;
 		lc->acaps = fw_caps;
 	} else {
 		fw_caps =
-			 lmm_to_fw_caps(link_ksettings->link_modes.advertising);
+			lmm_to_fw_caps(link_ksettings->link_modes.advertising);
 		if (!(lc->pcaps & fw_caps))
 			return -EINVAL;
 		lc->speed_caps = 0;
@@ -869,7 +875,7 @@ static int set_sge_param(struct net_device *dev, struct ethtool_ringparam *e)
 	    e->rx_pending < MIN_FL_ENTRIES || e->tx_pending < MIN_TXQ_ENTRIES)
 		return -EINVAL;
 
-	if (adapter->flags & FULL_INIT_DONE)
+	if (adapter->flags & CXGB4_FULL_INIT_DONE)
 		return -EBUSY;
 
 	for (i = 0; i < pi->nqsets; ++i) {
@@ -926,11 +932,190 @@ static int get_adaptive_rx_setting(struct net_device *dev)
 	return q->rspq.adaptive_rx;
 }
 
-static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
+/* Return the current global Adapter SGE Doorbell Queue Timer Tick for all
+ * Ethernet TX Queues.
+ */
+static int get_dbqtimer_tick(struct net_device *dev)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	return adap->sge.dbqtimer_tick;
+}
+
+/* Return the SGE Doorbell Queue Timer Value for the Ethernet TX Queues
+ * associated with a Network Device.
+ */
+static int get_dbqtimer(struct net_device *dev)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	struct sge_eth_txq *txq;
+
+	txq = &adap->sge.ethtxq[pi->first_qset];
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	/* all of the TX Queues use the same Timer Index */
+	return adap->sge.dbqtimer_val[txq->dbqtimerix];
+}
+
+/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX
+ * Queues.  This is the fundamental "Tick" that sets the scale of values which
+ * can be used.  Individual Ethernet TX Queues index into a relatively small
+ * array of Tick Multipliers.  Changing the base Tick will thus change all of
+ * the resulting Timer Values associated with those multipliers for all
+ * Ethernet TX Queues.
+ */
+static int set_dbqtimer_tick(struct net_device *dev, int usecs)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	struct sge *s = &adap->sge;
+	u32 param, val;
+	int ret;
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	/* return early if it's the same Timer Tick we're already using */
+	if (s->dbqtimer_tick == usecs)
+		return 0;
+
+	/* attempt to set the new Timer Tick value */
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK));
+	val = usecs;
+	ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, &param, &val);
+	if (ret)
+		return ret;
+	s->dbqtimer_tick = usecs;
+
+	/* if successful, reread resulting dependent Timer values */
+	ret = t4_read_sge_dbqtimers(adap, ARRAY_SIZE(s->dbqtimer_val),
+				    s->dbqtimer_val);
+	return ret;
+}
+
+/* Set the SGE Doorbell Queue Timer Value for the Ethernet TX Queues
+ * associated with a Network Device.  There is a relatively small array of
+ * possible Timer Values so we need to pick the closest value available.
+ */
+static int set_dbqtimer(struct net_device *dev, int usecs)
+{
+	int qix, timerix, min_timerix, delta, min_delta;
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	struct sge *s = &adap->sge;
+	struct sge_eth_txq *txq;
+	u32 param, val;
+	int ret;
+
+	if (!(adap->flags & CXGB4_SGE_DBQ_TIMER))
+		return 0;
+
+	/* Find the SGE Doorbell Timer Value that's closest to the requested
+	 * value.
+	 */
+	min_delta = INT_MAX;
+	min_timerix = 0;
+	for (timerix = 0; timerix < ARRAY_SIZE(s->dbqtimer_val); timerix++) {
+		delta = s->dbqtimer_val[timerix] - usecs;
+		if (delta < 0)
+			delta = -delta;
+		if (delta < min_delta) {
+			min_delta = delta;
+			min_timerix = timerix;
+		}
+	}
+
+	/* Return early if it's the same Timer Index we're already using.
+	 * We use the same Timer Index for all of the TX Queues for an
+	 * interface so it's only necessary to check the first one.
+	 */
+	txq = &s->ethtxq[pi->first_qset];
+	if (txq->dbqtimerix == min_timerix)
+		return 0;
+
+	for (qix = 0; qix < pi->nqsets; qix++, txq++) {
+		if (adap->flags & CXGB4_FULL_INIT_DONE) {
+			param =
+			 (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) |
+			  FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX) |
+			  FW_PARAMS_PARAM_YZ_V(txq->q.cntxt_id));
+			val = min_timerix;
+			ret = t4_set_params(adap, adap->mbox, adap->pf, 0,
+					    1, &param, &val);
+			if (ret)
+				return ret;
+		}
+		txq->dbqtimerix = min_timerix;
+	}
+	return 0;
+}
+
+/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX
+ * Queues and the Timer Value for the Ethernet TX Queues associated with a
+ * Network Device.  Since changing the global Tick changes all of the
+ * available Timer Values, we need to do this first before selecting the
+ * resulting closest Timer Value.  Moreover, since the Tick is global,
+ * changing it affects the Timer Values for all Network Devices on the
+ * adapter.  So, before changing the Tick, we grab all of the current Timer
+ * Values for other Network Devices on this Adapter and then attempt to select
+ * new Timer Values which are close to the old values ...
+ */
+static int set_dbqtimer_tickval(struct net_device *dev,
+				int tick_usecs, int timer_usecs)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	int timer[MAX_NPORTS];
+	unsigned int port;
+	int ret;
+
+	/* Grab the other adapter Network Interface current timers and fill in
+	 * the new one for this Network Interface.
+	 */
+	for_each_port(adap, port)
+		if (port == pi->port_id)
+			timer[port] = timer_usecs;
+		else
+			timer[port] = get_dbqtimer(adap->port[port]);
+
+	/* Change the global Tick first ... */
+	ret = set_dbqtimer_tick(dev, tick_usecs);
+	if (ret)
+		return ret;
+
+	/* ... and then set all of the Network Interface Timer Values ... */
+	for_each_port(adap, port) {
+		ret = set_dbqtimer(adap->port[port], timer[port]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int set_coalesce(struct net_device *dev,
+			struct ethtool_coalesce *coalesce)
 {
-	set_adaptive_rx_setting(dev, c->use_adaptive_rx_coalesce);
-	return set_rx_intr_params(dev, c->rx_coalesce_usecs,
-				  c->rx_max_coalesced_frames);
+	int ret;
+
+	set_adaptive_rx_setting(dev, coalesce->use_adaptive_rx_coalesce);
+
+	ret = set_rx_intr_params(dev, coalesce->rx_coalesce_usecs,
+				 coalesce->rx_max_coalesced_frames);
+	if (ret)
+		return ret;
+
+	return set_dbqtimer_tickval(dev,
+				    coalesce->tx_coalesce_usecs_irq,
+				    coalesce->tx_coalesce_usecs);
 }
 
 static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
@@ -943,6 +1128,8 @@ static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c)
 	c->rx_max_coalesced_frames = (rq->intr_params & QINTR_CNT_EN_F) ?
 		adap->sge.counter_val[rq->pktcnt_idx] : 0;
 	c->use_adaptive_rx_coalesce = get_adaptive_rx_setting(dev);
+	c->tx_coalesce_usecs_irq = get_dbqtimer_tick(dev);
+	c->tx_coalesce_usecs = get_dbqtimer(dev);
 	return 0;
 }
 
@@ -1076,7 +1263,7 @@ static int set_flash(struct net_device *netdev, struct ethtool_flash *ef)
 	 * firmware image otherwise we'll try to do the entire job from the
 	 * host ... and we always "force" the operation in this path.
 	 */
-	if (adap->flags & FULL_INIT_DONE)
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		mbox = adap->mbox;
 
 	ret = t4_fw_upgrade(adap, mbox, fw->data, fw->size, 1);
@@ -1155,7 +1342,7 @@ static int set_rss_table(struct net_device *dev, const u32 *p, const u8 *key,
 		return 0;
 
 	/* Interface must be brought up atleast once */
-	if (pi->adapter->flags & FULL_INIT_DONE) {
+	if (pi->adapter->flags & CXGB4_FULL_INIT_DONE) {
 		for (i = 0; i < pi->rss_size; i++)
 			pi->rss[i] = p[i];
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
index 6c8a62eefe51..33b2c0c45509 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_fcoe.c
@@ -74,7 +74,7 @@ int cxgb_fcoe_enable(struct net_device *netdev)
 	if (is_t4(adap->params.chip))
 		return -EINVAL;
 
-	if (!(adap->flags & FULL_INIT_DONE))
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE))
 		return -EINVAL;
 
 	dev_info(adap->pdev_dev, "Enabling FCoE offload features\n");
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 7dddb9e748b8..5afb43000049 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -524,7 +524,7 @@ static int del_filter_wr(struct adapter *adapter, int fidx)
 		return -ENOMEM;
 
 	fwr = __skb_put(skb, len);
-	t4_mk_filtdelwr(f->tid, fwr, (adapter->flags & SHUTTING_DOWN) ? -1
+	t4_mk_filtdelwr(f->tid, fwr, (adapter->flags & CXGB4_SHUTTING_DOWN) ? -1
 			: adapter->sge.fw_evtq.abs_id);
 
 	/* Mark the filter as "pending" and ship off the Filter Work Request.
@@ -1569,7 +1569,7 @@ int cxgb4_del_filter(struct net_device *dev, int filter_id,
 	int ret;
 
 	/* If we are shutting down the adapter do not wait for completion */
-	if (netdev2adap(dev)->flags & SHUTTING_DOWN)
+	if (netdev2adap(dev)->flags & CXGB4_SHUTTING_DOWN)
 		return __cxgb4_del_filter(dev, filter_id, fs, NULL);
 
 	init_completion(&ctx.completion);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index d49db46254cd..89179e316687 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -433,6 +433,60 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok)
 }
 
 /**
+ *	cxgb4_change_mac - Update match filter for a MAC address.
+ *	@pi: the port_info
+ *	@viid: the VI id
+ *	@tcam_idx: TCAM index of existing filter for old value of MAC address,
+ *		   or -1
+ *	@addr: the new MAC address value
+ *	@persist: whether a new MAC allocation should be persistent
+ *	@add_smt: if true also add the address to the HW SMT
+ *
+ *	Modifies an MPS filter and sets it to the new MAC address if
+ *	@tcam_idx >= 0, or adds the MAC address to a new filter if
+ *	@tcam_idx < 0. In the latter case the address is added persistently
+ *	if @persist is %true.
+ *	Addresses are programmed to hash region, if tcam runs out of entries.
+ *
+ */
+static int cxgb4_change_mac(struct port_info *pi, unsigned int viid,
+			    int *tcam_idx, const u8 *addr, bool persist,
+			    u8 *smt_idx)
+{
+	struct adapter *adapter = pi->adapter;
+	struct hash_mac_addr *entry, *new_entry;
+	int ret;
+
+	ret = t4_change_mac(adapter, adapter->mbox, viid,
+			    *tcam_idx, addr, persist, smt_idx);
+	/* We ran out of TCAM entries. try programming hash region. */
+	if (ret == -ENOMEM) {
+		/* If the MAC address to be updated is in the hash addr
+		 * list, update it from the list
+		 */
+		list_for_each_entry(entry, &adapter->mac_hlist, list) {
+			if (entry->iface_mac) {
+				ether_addr_copy(entry->addr, addr);
+				goto set_hash;
+			}
+		}
+		new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		ether_addr_copy(new_entry->addr, addr);
+		new_entry->iface_mac = true;
+		list_add_tail(&new_entry->list, &adapter->mac_hlist);
+set_hash:
+		ret = cxgb4_set_addr_hash(pi);
+	} else if (ret >= 0) {
+		*tcam_idx = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+/*
  *	link_start - enable a port
  *	@dev: the port to enable
  *
@@ -450,15 +504,9 @@ static int link_start(struct net_device *dev)
 	 */
 	ret = t4_set_rxmode(pi->adapter, mb, pi->viid, dev->mtu, -1, -1, -1,
 			    !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true);
-	if (ret == 0) {
-		ret = t4_change_mac(pi->adapter, mb, pi->viid,
-				    pi->xact_addr_filt, dev->dev_addr, true,
-				    true);
-		if (ret >= 0) {
-			pi->xact_addr_filt = ret;
-			ret = 0;
-		}
-	}
+	if (ret == 0)
+		ret = cxgb4_change_mac(pi, pi->viid, &pi->xact_addr_filt,
+				       dev->dev_addr, true, &pi->smt_idx);
 	if (ret == 0)
 		ret = t4_link_l1cfg(pi->adapter, mb, pi->tx_chan,
 				    &pi->link_cfg);
@@ -527,7 +575,7 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 			struct sge_eth_txq *eq;
 
 			eq = container_of(txq, struct sge_eth_txq, q);
-			netif_tx_wake_queue(eq->txq);
+			t4_sge_eth_txq_egress_update(q->adap, eq, -1);
 		} else {
 			struct sge_uld_txq *oq;
 
@@ -603,12 +651,12 @@ out:
 
 static void disable_msi(struct adapter *adapter)
 {
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4_USING_MSIX) {
 		pci_disable_msix(adapter->pdev);
-		adapter->flags &= ~USING_MSIX;
-	} else if (adapter->flags & USING_MSI) {
+		adapter->flags &= ~CXGB4_USING_MSIX;
+	} else if (adapter->flags & CXGB4_USING_MSI) {
 		pci_disable_msi(adapter->pdev);
-		adapter->flags &= ~USING_MSI;
+		adapter->flags &= ~CXGB4_USING_MSI;
 	}
 }
 
@@ -624,7 +672,7 @@ static irqreturn_t t4_nondata_intr(int irq, void *cookie)
 		adap->swintr = 1;
 		t4_write_reg(adap, MYPF_REG(PL_PF_INT_CAUSE_A), v);
 	}
-	if (adap->flags & MASTER_PF)
+	if (adap->flags & CXGB4_MASTER_PF)
 		t4_slow_intr_handler(adap);
 	return IRQ_HANDLED;
 }
@@ -789,9 +837,9 @@ static void quiesce_rx(struct adapter *adap)
 /* Disable interrupt and napi handler */
 static void disable_interrupts(struct adapter *adap)
 {
-	if (adap->flags & FULL_INIT_DONE) {
+	if (adap->flags & CXGB4_FULL_INIT_DONE) {
 		t4_intr_disable(adap);
-		if (adap->flags & USING_MSIX) {
+		if (adap->flags & CXGB4_USING_MSIX) {
 			free_msix_queue_irqs(adap);
 			free_irq(adap->msix_info[0].vec, adap);
 		} else {
@@ -832,7 +880,7 @@ static int setup_fw_sge_queues(struct adapter *adap)
 	bitmap_zero(s->starving_fl, s->egr_sz);
 	bitmap_zero(s->txq_maperr, s->egr_sz);
 
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		adap->msi_idx = 1;         /* vector 0 is for non-queue interrupts */
 	else {
 		err = t4_sge_alloc_rxq(adap, &s->intrq, false, adap->port[0], 0,
@@ -885,10 +933,13 @@ static int setup_sge_queues(struct adapter *adap)
 			q->rspq.idx = j;
 			memset(&q->stats, 0, sizeof(q->stats));
 		}
-		for (j = 0; j < pi->nqsets; j++, t++) {
+
+		q = &s->ethrxq[pi->first_qset];
+		for (j = 0; j < pi->nqsets; j++, t++, q++) {
 			err = t4_sge_alloc_eth_txq(adap, t, dev,
 					netdev_get_tx_queue(dev, j),
-					s->fw_evtq.cntxt_id);
+					q->rspq.cntxt_id,
+					!!(adap->flags & CXGB4_SGE_DBQ_TIMER));
 			if (err)
 				goto freeout;
 		}
@@ -910,7 +961,7 @@ static int setup_sge_queues(struct adapter *adap)
 	if (!is_t4(adap->params.chip)) {
 		err = t4_sge_alloc_eth_txq(adap, &s->ptptxq, adap->port[0],
 					   netdev_get_tx_queue(adap->port[0], 0)
-					   , s->fw_evtq.cntxt_id);
+					   , s->fw_evtq.cntxt_id, false);
 		if (err)
 			goto freeout;
 	}
@@ -1585,28 +1636,6 @@ unsigned int cxgb4_best_aligned_mtu(const unsigned short *mtus,
 EXPORT_SYMBOL(cxgb4_best_aligned_mtu);
 
 /**
- *	cxgb4_tp_smt_idx - Get the Source Mac Table index for this VI
- *	@chip: chip type
- *	@viid: VI id of the given port
- *
- *	Return the SMT index for this VI.
- */
-unsigned int cxgb4_tp_smt_idx(enum chip_type chip, unsigned int viid)
-{
-	/* In T4/T5, SMT contains 256 SMAC entries organized in
-	 * 128 rows of 2 entries each.
-	 * In T6, SMT contains 256 SMAC entries in 256 rows.
-	 * TODO: The below code needs to be updated when we add support
-	 * for 256 VFs.
-	 */
-	if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5)
-		return ((viid & 0x7f) << 1);
-	else
-		return (viid & 0x7f);
-}
-EXPORT_SYMBOL(cxgb4_tp_smt_idx);
-
-/**
  *	cxgb4_port_chan - get the HW channel of a port
  *	@dev: the net device for the port
  *
@@ -2251,7 +2280,7 @@ static int cxgb_up(struct adapter *adap)
 	if (err)
 		goto freeq;
 
-	if (adap->flags & USING_MSIX) {
+	if (adap->flags & CXGB4_USING_MSIX) {
 		name_msix_vecs(adap);
 		err = request_irq(adap->msix_info[0].vec, t4_nondata_intr, 0,
 				  adap->msix_info[0].desc, adap);
@@ -2264,7 +2293,8 @@ static int cxgb_up(struct adapter *adap)
 		}
 	} else {
 		err = request_irq(adap->pdev->irq, t4_intr_handler(adap),
-				  (adap->flags & USING_MSI) ? 0 : IRQF_SHARED,
+				  (adap->flags & CXGB4_USING_MSI) ? 0
+								  : IRQF_SHARED,
 				  adap->port[0]->name, adap);
 		if (err)
 			goto irq_err;
@@ -2273,15 +2303,13 @@ static int cxgb_up(struct adapter *adap)
 	enable_rx(adap);
 	t4_sge_start(adap);
 	t4_intr_enable(adap);
-	adap->flags |= FULL_INIT_DONE;
+	adap->flags |= CXGB4_FULL_INIT_DONE;
 	mutex_unlock(&uld_mutex);
 
 	notify_ulds(adap, CXGB4_STATE_UP);
 #if IS_ENABLED(CONFIG_IPV6)
 	update_clip(adap);
 #endif
-	/* Initialize hash mac addr list*/
-	INIT_LIST_HEAD(&adap->mac_hlist);
 	return err;
 
  irq_err:
@@ -2303,7 +2331,8 @@ static void cxgb_down(struct adapter *adapter)
 
 	t4_sge_stop(adapter);
 	t4_free_sge_resources(adapter);
-	adapter->flags &= ~FULL_INIT_DONE;
+
+	adapter->flags &= ~CXGB4_FULL_INIT_DONE;
 }
 
 /*
@@ -2317,7 +2346,7 @@ static int cxgb_open(struct net_device *dev)
 
 	netif_carrier_off(dev);
 
-	if (!(adapter->flags & FULL_INIT_DONE)) {
+	if (!(adapter->flags & CXGB4_FULL_INIT_DONE)) {
 		err = cxgb_up(adapter);
 		if (err < 0)
 			return err;
@@ -2669,7 +2698,7 @@ static void cxgb4_mgmt_fill_vf_station_mac_addr(struct adapter *adap)
 
 	for (vf = 0, nvfs = pci_sriov_get_totalvfs(adap->pdev);
 		vf < nvfs; vf++) {
-		macaddr[5] = adap->pf * 16 + vf;
+		macaddr[5] = adap->pf * nvfs + vf;
 		ether_addr_copy(adap->vfinfo[vf].vf_mac_addr, macaddr);
 	}
 }
@@ -2712,6 +2741,7 @@ static int cxgb4_mgmt_get_vf_config(struct net_device *dev,
 	ivi->min_tx_rate = 0;
 	ether_addr_copy(ivi->mac, vfinfo->vf_mac_addr);
 	ivi->vlan = vfinfo->vlan;
+	ivi->linkstate = vfinfo->link_state;
 	return 0;
 }
 
@@ -2851,6 +2881,49 @@ static int cxgb4_mgmt_set_vf_vlan(struct net_device *dev, int vf,
 		ret, (vlan ? "setting" : "clearing"), adap->pf, vf);
 	return ret;
 }
+
+static int cxgb4_mgmt_set_vf_link_state(struct net_device *dev, int vf,
+					int link)
+{
+	struct port_info *pi = netdev_priv(dev);
+	struct adapter *adap = pi->adapter;
+	u32 param, val;
+	int ret = 0;
+
+	if (vf >= adap->num_vfs)
+		return -EINVAL;
+
+	switch (link) {
+	case IFLA_VF_LINK_STATE_AUTO:
+		val = FW_VF_LINK_STATE_AUTO;
+		break;
+
+	case IFLA_VF_LINK_STATE_ENABLE:
+		val = FW_VF_LINK_STATE_ENABLE;
+		break;
+
+	case IFLA_VF_LINK_STATE_DISABLE:
+		val = FW_VF_LINK_STATE_DISABLE;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) |
+		 FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_LINK_STATE));
+	ret = t4_set_params(adap, adap->mbox, adap->pf, vf + 1, 1,
+			    &param, &val);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Error %d in setting PF %d VF %d link state\n",
+			ret, adap->pf, vf);
+		return -EINVAL;
+	}
+
+	adap->vfinfo[vf].link_state = link;
+	return ret;
+}
 #endif /* CONFIG_PCI_IOV */
 
 static int cxgb_set_mac_addr(struct net_device *dev, void *p)
@@ -2862,8 +2935,8 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid,
-			    pi->xact_addr_filt, addr->sa_data, true, true);
+	ret = cxgb4_change_mac(pi, pi->viid, &pi->xact_addr_filt,
+			       addr->sa_data, true, &pi->smt_idx);
 	if (ret < 0)
 		return ret;
 
@@ -2878,7 +2951,7 @@ static void cxgb_netpoll(struct net_device *dev)
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adap = pi->adapter;
 
-	if (adap->flags & USING_MSIX) {
+	if (adap->flags & CXGB4_USING_MSIX) {
 		int i;
 		struct sge_eth_rxq *rx = &adap->sge.ethrxq[pi->first_qset];
 
@@ -2905,7 +2978,7 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	if (index < 0 || index > pi->nqsets - 1)
 		return -EINVAL;
 
-	if (!(adap->flags & FULL_INIT_DONE)) {
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
 		dev_err(adap->pdev_dev,
 			"Failed to rate limit on queue %d. Link Down?\n",
 			index);
@@ -3006,7 +3079,7 @@ static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	struct port_info *pi = netdev2pinfo(dev);
 	struct adapter *adap = netdev2adap(dev);
 
-	if (!(adap->flags & FULL_INIT_DONE)) {
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE)) {
 		dev_err(adap->pdev_dev,
 			"Failed to setup tc on port %d. Link Down?\n",
 			pi->port_id);
@@ -3266,12 +3339,13 @@ static const struct net_device_ops cxgb4_netdev_ops = {
 
 #ifdef CONFIG_PCI_IOV
 static const struct net_device_ops cxgb4_mgmt_netdev_ops = {
-	.ndo_open             = cxgb4_mgmt_open,
-	.ndo_set_vf_mac       = cxgb4_mgmt_set_vf_mac,
-	.ndo_get_vf_config    = cxgb4_mgmt_get_vf_config,
-	.ndo_set_vf_rate      = cxgb4_mgmt_set_vf_rate,
-	.ndo_get_phys_port_id = cxgb4_mgmt_get_phys_port_id,
-	.ndo_set_vf_vlan      = cxgb4_mgmt_set_vf_vlan,
+	.ndo_open               = cxgb4_mgmt_open,
+	.ndo_set_vf_mac         = cxgb4_mgmt_set_vf_mac,
+	.ndo_get_vf_config      = cxgb4_mgmt_get_vf_config,
+	.ndo_set_vf_rate        = cxgb4_mgmt_set_vf_rate,
+	.ndo_get_phys_port_id   = cxgb4_mgmt_get_phys_port_id,
+	.ndo_set_vf_vlan        = cxgb4_mgmt_set_vf_vlan,
+	.ndo_set_vf_link_state	= cxgb4_mgmt_set_vf_link_state,
 };
 #endif
 
@@ -4137,7 +4211,7 @@ static int adap_init0(struct adapter *adap)
 		return ret;
 	}
 	if (ret == adap->mbox)
-		adap->flags |= MASTER_PF;
+		adap->flags |= CXGB4_MASTER_PF;
 
 	/*
 	 * If we're the Master PF Driver and the device is uninitialized,
@@ -4152,7 +4226,7 @@ static int adap_init0(struct adapter *adap)
 	/* If firmware is too old (not supported by driver) force an update. */
 	if (ret)
 		state = DEV_STATE_UNINIT;
-	if ((adap->flags & MASTER_PF) && state != DEV_STATE_INIT) {
+	if ((adap->flags & CXGB4_MASTER_PF) && state != DEV_STATE_INIT) {
 		struct fw_info *fw_info;
 		struct fw_hdr *card_fw;
 		const struct firmware *fw;
@@ -4214,7 +4288,7 @@ static int adap_init0(struct adapter *adap)
 				ret);
 		dev_info(adap->pdev_dev, "Coming up as %s: "\
 			 "Adapter already initialized\n",
-			 adap->flags & MASTER_PF ? "MASTER" : "SLAVE");
+			 adap->flags & CXGB4_MASTER_PF ? "MASTER" : "SLAVE");
 	} else {
 		dev_info(adap->pdev_dev, "Coming up as MASTER: "\
 			 "Initializing adapter\n");
@@ -4300,6 +4374,24 @@ static int adap_init0(struct adapter *adap)
 	if (ret < 0)
 		goto bye;
 
+	/* Grab the SGE Doorbell Queue Timer values.  If successful, that
+	 * indicates that the Firmware and Hardware support this.
+	 */
+	params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+		    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK));
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+			      1, params, val);
+
+	if (!ret) {
+		adap->sge.dbqtimer_tick = val[0];
+		ret = t4_read_sge_dbqtimers(adap,
+					    ARRAY_SIZE(adap->sge.dbqtimer_val),
+					    adap->sge.dbqtimer_val);
+	}
+
+	if (!ret)
+		adap->flags |= CXGB4_SGE_DBQ_TIMER;
+
 	if (is_bypass_device(adap->pdev->device))
 		adap->params.bypass = 1;
 
@@ -4422,7 +4514,7 @@ static int adap_init0(struct adapter *adap)
 	 * offload connection through firmware work request
 	 */
 	if ((val[0] != val[1]) && (ret >= 0)) {
-		adap->flags |= FW_OFLD_CONN;
+		adap->flags |= CXGB4_FW_OFLD_CONN;
 		adap->tids.aftid_base = val[0];
 		adap->tids.aftid_end = val[1];
 	}
@@ -4467,6 +4559,15 @@ static int adap_init0(struct adapter *adap)
 		adap->params.filter2_wr_support = (ret == 0 && val[0] != 0);
 	}
 
+	/* Check if FW supports returning vin and smt index.
+	 * If this is not supported, driver will interpret
+	 * these values from viid.
+	 */
+	params[0] = FW_PARAM_DEV(OPAQUE_VIID_SMT_EXTN);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+			      1, params, val);
+	adap->params.viid_smt_extn_support = (ret == 0 && val[0] != 0);
+
 	/*
 	 * Get device capabilities so we can determine what resources we need
 	 * to manage.
@@ -4506,7 +4607,7 @@ static int adap_init0(struct adapter *adap)
 		 * 2. Server filter: This are special filters which are used
 		 * to redirect SYN packets to offload queue.
 		 */
-		if (adap->flags & FW_OFLD_CONN && !is_bypass(adap)) {
+		if (adap->flags & CXGB4_FW_OFLD_CONN && !is_bypass(adap)) {
 			adap->tids.sftid_base = adap->tids.ftid_base +
 					DIV_ROUND_UP(adap->tids.nftids, 3);
 			adap->tids.nsftids = adap->tids.nftids -
@@ -4685,7 +4786,7 @@ static int adap_init0(struct adapter *adap)
 			     adap->params.b_wnd);
 	}
 	t4_init_sge_params(adap);
-	adap->flags |= FW_OK;
+	adap->flags |= CXGB4_FW_OK;
 	t4_init_tp_params(adap, true);
 	return 0;
 
@@ -4720,7 +4821,7 @@ static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
 		goto out;
 
 	rtnl_lock();
-	adap->flags &= ~FW_OK;
+	adap->flags &= ~CXGB4_FW_OK;
 	notify_ulds(adap, CXGB4_STATE_START_RECOVERY);
 	spin_lock(&adap->stats_lock);
 	for_each_port(adap, i) {
@@ -4732,12 +4833,12 @@ static pci_ers_result_t eeh_err_detected(struct pci_dev *pdev,
 	}
 	spin_unlock(&adap->stats_lock);
 	disable_interrupts(adap);
-	if (adap->flags & FULL_INIT_DONE)
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		cxgb_down(adap);
 	rtnl_unlock();
-	if ((adap->flags & DEV_ENABLED)) {
+	if ((adap->flags & CXGB4_DEV_ENABLED)) {
 		pci_disable_device(pdev);
-		adap->flags &= ~DEV_ENABLED;
+		adap->flags &= ~CXGB4_DEV_ENABLED;
 	}
 out:	return state == pci_channel_io_perm_failure ?
 		PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET;
@@ -4755,13 +4856,13 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_RECOVERED;
 	}
 
-	if (!(adap->flags & DEV_ENABLED)) {
+	if (!(adap->flags & CXGB4_DEV_ENABLED)) {
 		if (pci_enable_device(pdev)) {
 			dev_err(&pdev->dev, "Cannot reenable PCI "
 					    "device after reset\n");
 			return PCI_ERS_RESULT_DISCONNECT;
 		}
-		adap->flags |= DEV_ENABLED;
+		adap->flags |= CXGB4_DEV_ENABLED;
 	}
 
 	pci_set_master(pdev);
@@ -4772,19 +4873,31 @@ static pci_ers_result_t eeh_slot_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_DISCONNECT;
 	if (t4_fw_hello(adap, adap->mbox, adap->pf, MASTER_MUST, NULL) < 0)
 		return PCI_ERS_RESULT_DISCONNECT;
-	adap->flags |= FW_OK;
+	adap->flags |= CXGB4_FW_OK;
 	if (adap_init1(adap, &c))
 		return PCI_ERS_RESULT_DISCONNECT;
 
 	for_each_port(adap, i) {
-		struct port_info *p = adap2pinfo(adap, i);
+		struct port_info *pi = adap2pinfo(adap, i);
+		u8 vivld = 0, vin = 0;
 
-		ret = t4_alloc_vi(adap, adap->mbox, p->tx_chan, adap->pf, 0, 1,
-				  NULL, NULL);
+		ret = t4_alloc_vi(adap, adap->mbox, pi->tx_chan, adap->pf, 0, 1,
+				  NULL, NULL, &vivld, &vin);
 		if (ret < 0)
 			return PCI_ERS_RESULT_DISCONNECT;
-		p->viid = ret;
-		p->xact_addr_filt = -1;
+		pi->viid = ret;
+		pi->xact_addr_filt = -1;
+		/* If fw supports returning the VIN as part of FW_VI_CMD,
+		 * save the returned values.
+		 */
+		if (adap->params.viid_smt_extn_support) {
+			pi->vivld = vivld;
+			pi->vin = vin;
+		} else {
+			/* Retrieve the values from VIID */
+			pi->vivld = FW_VIID_VIVLD_G(pi->viid);
+			pi->vin = FW_VIID_VIN_G(pi->viid);
+		}
 	}
 
 	t4_load_mtus(adap, adap->params.mtus, adap->params.a_wnd,
@@ -4872,7 +4985,7 @@ static int cfg_queues(struct adapter *adap)
 	 * at all is problematic ...
 	 */
 	niqflint = adap->params.pfres.niqflint - 1;
-	if (!(adap->flags & USING_MSIX))
+	if (!(adap->flags & CXGB4_USING_MSIX))
 		niqflint--;
 	neq = adap->params.pfres.neq / 2;
 	avail_eth_qsets = min(niqflint, neq);
@@ -5154,8 +5267,8 @@ static void print_adapter_info(struct adapter *adapter)
 	/* Software/Hardware configuration */
 	dev_info(adapter->pdev_dev, "Configuration: %sNIC %s, %s capable\n",
 		 is_offload(adapter) ? "R" : "",
-		 ((adapter->flags & USING_MSIX) ? "MSI-X" :
-		  (adapter->flags & USING_MSI) ? "MSI" : ""),
+		 ((adapter->flags & CXGB4_USING_MSIX) ? "MSI-X" :
+		  (adapter->flags & CXGB4_USING_MSI) ? "MSI" : ""),
 		 is_offload(adapter) ? "Offload" : "non-Offload");
 }
 
@@ -5230,13 +5343,13 @@ static void free_some_resources(struct adapter *adapter)
 			kfree(adap2pinfo(adapter, i)->rss);
 			free_netdev(adapter->port[i]);
 		}
-	if (adapter->flags & FW_OK)
+	if (adapter->flags & CXGB4_FW_OK)
 		t4_fw_bye(adapter, adapter->pf);
 }
 
 #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
 #define VLAN_FEAT (NETIF_F_SG | NETIF_F_IP_CSUM | TSO_FLAGS | \
-		   NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
+		   NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
 #define SEGMENT_SIZE 128
 
 static int t4_get_chip_type(struct adapter *adap, int ver)
@@ -5534,7 +5647,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 	/* PCI device has been enabled */
-	adapter->flags |= DEV_ENABLED;
+	adapter->flags |= CXGB4_DEV_ENABLED;
 	memset(adapter->chan_map, 0xff, sizeof(adapter->chan_map));
 
 	/* If possible, we use PCIe Relaxed Ordering Attribute to deliver
@@ -5552,7 +5665,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * using Relaxed Ordering.
 	 */
 	if (!pcie_relaxed_ordering_enabled(pdev))
-		adapter->flags |= ROOT_NO_RELAXED_ORDERING;
+		adapter->flags |= CXGB4_ROOT_NO_RELAXED_ORDERING;
 
 	spin_lock_init(&adapter->stats_lock);
 	spin_lock_init(&adapter->tid_release_lock);
@@ -5621,6 +5734,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 			     (is_t5(adapter->params.chip) ? STATMODE_V(0) :
 			      T6_STATMODE_V(0)));
 
+	/* Initialize hash mac addr list */
+	INIT_LIST_HEAD(&adapter->mac_hlist);
+
 	for_each_port(adapter, i) {
 		netdev = alloc_etherdev_mq(sizeof(struct port_info),
 					   MAX_ETH_QSETS);
@@ -5640,7 +5756,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 		netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
 			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			NETIF_F_RXCSUM | NETIF_F_RXHASH |
+			NETIF_F_RXCSUM | NETIF_F_RXHASH | NETIF_F_GRO |
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
 			NETIF_F_HW_TC;
 
@@ -5649,9 +5765,12 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 						   NETIF_F_IPV6_CSUM |
 						   NETIF_F_RXCSUM |
 						   NETIF_F_GSO_UDP_TUNNEL |
+						   NETIF_F_GSO_UDP_TUNNEL_CSUM |
 						   NETIF_F_TSO | NETIF_F_TSO6;
 
-			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL |
+					       NETIF_F_GSO_UDP_TUNNEL_CSUM |
+					       NETIF_F_HW_TLS_RECORD;
 		}
 
 		if (highdma)
@@ -5678,7 +5797,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, adapter);
 
-	if (adapter->flags & FW_OK) {
+	if (adapter->flags & CXGB4_FW_OK) {
 		err = t4_port_init(adapter, func, func, 0);
 		if (err)
 			goto out_free_dev;
@@ -5700,7 +5819,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
-	if (!(adapter->flags & FW_OK))
+	if (!(adapter->flags & CXGB4_FW_OK))
 		goto fw_attach_fail;
 
 	/* Configure queues and allocate tables now, they can be needed as
@@ -5794,9 +5913,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* See what interrupts we'll be using */
 	if (msi > 1 && enable_msix(adapter) == 0)
-		adapter->flags |= USING_MSIX;
+		adapter->flags |= CXGB4_USING_MSIX;
 	else if (msi > 0 && pci_enable_msi(pdev) == 0) {
-		adapter->flags |= USING_MSI;
+		adapter->flags |= CXGB4_USING_MSI;
 		if (msi > 1)
 			free_msix_info(adapter);
 	}
@@ -5864,7 +5983,7 @@ fw_attach_fail:
 		cxgb4_ptp_init(adapter);
 
 	if (IS_REACHABLE(CONFIG_THERMAL) &&
-	    !is_t4(adapter->params.chip) && (adapter->flags & FW_OK))
+	    !is_t4(adapter->params.chip) && (adapter->flags & CXGB4_FW_OK))
 		cxgb4_thermal_init(adapter);
 
 	print_adapter_info(adapter);
@@ -5873,7 +5992,7 @@ fw_attach_fail:
  out_free_dev:
 	t4_free_sge_resources(adapter);
 	free_some_resources(adapter);
-	if (adapter->flags & USING_MSIX)
+	if (adapter->flags & CXGB4_USING_MSIX)
 		free_msix_info(adapter);
 	if (adapter->num_uld || adapter->num_ofld_uld)
 		t4_uld_mem_free(adapter);
@@ -5899,13 +6018,14 @@ fw_attach_fail:
 static void remove_one(struct pci_dev *pdev)
 {
 	struct adapter *adapter = pci_get_drvdata(pdev);
+	struct hash_mac_addr *entry, *tmp;
 
 	if (!adapter) {
 		pci_release_regions(pdev);
 		return;
 	}
 
-	adapter->flags |= SHUTTING_DOWN;
+	adapter->flags |= CXGB4_SHUTTING_DOWN;
 
 	if (adapter->pf == 4) {
 		int i;
@@ -5940,14 +6060,20 @@ static void remove_one(struct pci_dev *pdev)
 		 */
 		clear_all_filters(adapter);
 
-		if (adapter->flags & FULL_INIT_DONE)
+		if (adapter->flags & CXGB4_FULL_INIT_DONE)
 			cxgb_down(adapter);
 
-		if (adapter->flags & USING_MSIX)
+		if (adapter->flags & CXGB4_USING_MSIX)
 			free_msix_info(adapter);
 		if (adapter->num_uld || adapter->num_ofld_uld)
 			t4_uld_mem_free(adapter);
 		free_some_resources(adapter);
+		list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist,
+					 list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
+
 #if IS_ENABLED(CONFIG_IPV6)
 		t4_cleanup_clip_tbl(adapter);
 #endif
@@ -5961,9 +6087,9 @@ static void remove_one(struct pci_dev *pdev)
 #endif
 	iounmap(adapter->regs);
 	pci_disable_pcie_error_reporting(pdev);
-	if ((adapter->flags & DEV_ENABLED)) {
+	if ((adapter->flags & CXGB4_DEV_ENABLED)) {
 		pci_disable_device(pdev);
-		adapter->flags &= ~DEV_ENABLED;
+		adapter->flags &= ~CXGB4_DEV_ENABLED;
 	}
 	pci_release_regions(pdev);
 	kfree(adapter->mbox_log);
@@ -5989,7 +6115,7 @@ static void shutdown_one(struct pci_dev *pdev)
 		return;
 	}
 
-	adapter->flags |= SHUTTING_DOWN;
+	adapter->flags |= CXGB4_SHUTTING_DOWN;
 
 	if (adapter->pf == 4) {
 		int i;
@@ -6007,7 +6133,7 @@ static void shutdown_one(struct pci_dev *pdev)
 		disable_msi(adapter);
 
 		t4_sge_stop(adapter);
-		if (adapter->flags & FW_OK)
+		if (adapter->flags & CXGB4_FW_OK)
 			t4_fw_bye(adapter, adapter->mbox);
 	}
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
index 9f9d6cae39d5..58a039c3224a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ptp.c
@@ -378,10 +378,10 @@ static void cxgb4_init_ptp_timer(struct adapter *adapter)
 	int err;
 
 	memset(&c, 0, sizeof(c));
-		c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
-					     FW_CMD_REQUEST_F |
-					     FW_CMD_WRITE_F |
-					     FW_PTP_CMD_PORTID_V(0));
+	c.op_to_portid = cpu_to_be32(FW_CMD_OP_V(FW_PTP_CMD) |
+				     FW_CMD_REQUEST_F |
+				     FW_CMD_WRITE_F |
+				     FW_PTP_CMD_PORTID_V(0));
 	c.retval_len16 = cpu_to_be32(FW_CMD_LEN16_V(sizeof(c) / 16));
 	c.u.scmd.sc = FW_PTP_SC_INIT_TIMER;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index c116f96956fe..82a8d1970060 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -83,28 +83,23 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 				     struct tc_cls_flower_offload *cls,
 				     struct ch_filter_specification *fs)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
 	u16 addr_type = 0;
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  cls->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->mask);
-		u16 ethtype_key = ntohs(key->n_proto);
-		u16 ethtype_mask = ntohs(mask->n_proto);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+		u16 ethtype_key, ethtype_mask;
+
+		flow_rule_match_basic(rule, &match);
+		ethtype_key = ntohs(match.key->n_proto);
+		ethtype_mask = ntohs(match.mask->n_proto);
 
 		if (ethtype_key == ETH_P_ALL) {
 			ethtype_key = 0;
@@ -116,115 +111,89 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 
 		fs->val.ethtype = ethtype_key;
 		fs->mask.ethtype = ethtype_mask;
-		fs->val.proto = key->ip_proto;
-		fs->mask.proto = mask->ip_proto;
+		fs->val.proto = match.key->ip_proto;
+		fs->mask.proto = match.mask->ip_proto;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  cls->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  cls->mask);
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
 		fs->type = 0;
-		memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst));
-		memcpy(&fs->val.fip[0], &key->src, sizeof(key->src));
-		memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst));
-		memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src));
+		memcpy(&fs->val.lip[0], &match.key->dst, sizeof(match.key->dst));
+		memcpy(&fs->val.fip[0], &match.key->src, sizeof(match.key->src));
+		memcpy(&fs->mask.lip[0], &match.mask->dst, sizeof(match.mask->dst));
+		memcpy(&fs->mask.fip[0], &match.mask->src, sizeof(match.mask->src));
 
 		/* also initialize nat_lip/fip to same values */
-		memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst));
-		memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src));
-
+		memcpy(&fs->nat_lip[0], &match.key->dst, sizeof(match.key->dst));
+		memcpy(&fs->nat_fip[0], &match.key->src, sizeof(match.key->src));
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  cls->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  cls->mask);
+		struct flow_match_ipv6_addrs match;
 
+		flow_rule_match_ipv6_addrs(rule, &match);
 		fs->type = 1;
-		memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst));
-		memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src));
-		memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst));
-		memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src));
+		memcpy(&fs->val.lip[0], match.key->dst.s6_addr,
+		       sizeof(match.key->dst));
+		memcpy(&fs->val.fip[0], match.key->src.s6_addr,
+		       sizeof(match.key->src));
+		memcpy(&fs->mask.lip[0], match.mask->dst.s6_addr,
+		       sizeof(match.mask->dst));
+		memcpy(&fs->mask.fip[0], match.mask->src.s6_addr,
+		       sizeof(match.mask->src));
 
 		/* also initialize nat_lip/fip to same values */
-		memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst));
-		memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src));
+		memcpy(&fs->nat_lip[0], match.key->dst.s6_addr,
+		       sizeof(match.key->dst));
+		memcpy(&fs->nat_fip[0], match.key->src.s6_addr,
+		       sizeof(match.key->src));
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key, *mask;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_PORTS,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_PORTS,
-						 cls->mask);
-		fs->val.lport = cpu_to_be16(key->dst);
-		fs->mask.lport = cpu_to_be16(mask->dst);
-		fs->val.fport = cpu_to_be16(key->src);
-		fs->mask.fport = cpu_to_be16(mask->src);
+		flow_rule_match_ports(rule, &match);
+		fs->val.lport = cpu_to_be16(match.key->dst);
+		fs->mask.lport = cpu_to_be16(match.mask->dst);
+		fs->val.fport = cpu_to_be16(match.key->src);
+		fs->mask.fport = cpu_to_be16(match.mask->src);
 
 		/* also initialize nat_lport/fport to same values */
-		fs->nat_lport = cpu_to_be16(key->dst);
-		fs->nat_fport = cpu_to_be16(key->src);
+		fs->nat_lport = cpu_to_be16(match.key->dst);
+		fs->nat_fport = cpu_to_be16(match.key->src);
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
-		struct flow_dissector_key_ip *key, *mask;
-
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_IP,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_IP,
-						 cls->mask);
-		fs->val.tos = key->tos;
-		fs->mask.tos = mask->tos;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match;
+
+		flow_rule_match_ip(rule, &match);
+		fs->val.tos = match.key->tos;
+		fs->mask.tos = match.mask->tos;
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key, *mask;
-
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_ENC_KEYID,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_ENC_KEYID,
-						 cls->mask);
-		fs->val.vni = be32_to_cpu(key->keyid);
-		fs->mask.vni = be32_to_cpu(mask->keyid);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
+
+		flow_rule_match_enc_keyid(rule, &match);
+		fs->val.vni = be32_to_cpu(match.key->keyid);
+		fs->mask.vni = be32_to_cpu(match.mask->keyid);
 		if (fs->mask.vni) {
 			fs->val.encap_vld = 1;
 			fs->mask.encap_vld = 1;
 		}
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key, *mask;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 		u16 vlan_tci, vlan_tci_mask;
 
-		key = skb_flow_dissector_target(cls->dissector,
-						FLOW_DISSECTOR_KEY_VLAN,
-						cls->key);
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_VLAN,
-						 cls->mask);
-		vlan_tci = key->vlan_id | (key->vlan_priority <<
-					   VLAN_PRIO_SHIFT);
-		vlan_tci_mask = mask->vlan_id | (mask->vlan_priority <<
-						 VLAN_PRIO_SHIFT);
+		flow_rule_match_vlan(rule, &match);
+		vlan_tci = match.key->vlan_id | (match.key->vlan_priority <<
+					       VLAN_PRIO_SHIFT);
+		vlan_tci_mask = match.mask->vlan_id | (match.mask->vlan_priority <<
+						     VLAN_PRIO_SHIFT);
 		fs->val.ivlan = vlan_tci;
 		fs->mask.ivlan = vlan_tci_mask;
 
@@ -255,10 +224,12 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 static int cxgb4_validate_flow_match(struct net_device *dev,
 				     struct tc_cls_flower_offload *cls)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 ethtype_mask = 0;
 	u16 ethtype_key = 0;
 
-	if (cls->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
@@ -268,36 +239,29 @@ static int cxgb4_validate_flow_match(struct net_device *dev,
 	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
 	      BIT(FLOW_DISSECTOR_KEY_IP))) {
 		netdev_warn(dev, "Unsupported key used: 0x%x\n",
-			    cls->dissector->used_keys);
+			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(cls->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  cls->mask);
-		ethtype_key = ntohs(key->n_proto);
-		ethtype_mask = ntohs(mask->n_proto);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		ethtype_key = ntohs(match.key->n_proto);
+		ethtype_mask = ntohs(match.mask->n_proto);
 	}
 
-	if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
 		u16 eth_ip_type = ethtype_key & ethtype_mask;
-		struct flow_dissector_key_ip *mask;
+		struct flow_match_ip match;
 
 		if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) {
 			netdev_err(dev, "IP Key supported only with IPv4/v6");
 			return -EINVAL;
 		}
 
-		mask = skb_flow_dissector_target(cls->dissector,
-						 FLOW_DISSECTOR_KEY_IP,
-						 cls->mask);
-		if (mask->ttl) {
+		flow_rule_match_ip(rule, &match);
+		if (match.mask->ttl) {
 			netdev_warn(dev, "ttl match unsupported for offload");
 			return -EOPNOTSUPP;
 		}
@@ -328,7 +292,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 				u32 mask, u32 offset, u8 htype)
 {
 	switch (htype) {
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
 		switch (offset) {
 		case PEDIT_ETH_DMAC_31_0:
 			fs->newdmac = 1;
@@ -346,7 +310,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 			offload_pedit(fs, val, mask, ETH_SMAC_47_16);
 		}
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
 		switch (offset) {
 		case PEDIT_IP4_SRC:
 			offload_pedit(fs, val, mask, IP4_SRC);
@@ -356,7 +320,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
 		switch (offset) {
 		case PEDIT_IP6_SRC_31_0:
 			offload_pedit(fs, val, mask, IP6_SRC_31_0);
@@ -384,7 +348,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
 		switch (offset) {
 		case PEDIT_TCP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
@@ -397,7 +361,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 		}
 		fs->nat_mode = NAT_MODE_ALL;
 		break;
-	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
 		switch (offset) {
 		case PEDIT_UDP_SPORT_DPORT:
 			if (~mask & PEDIT_TCP_UDP_SPORT_MASK)
@@ -416,56 +380,63 @@ static void cxgb4_process_flow_actions(struct net_device *in,
 				       struct tc_cls_flower_offload *cls,
 				       struct ch_filter_specification *fs)
 {
-	const struct tc_action *a;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_action_entry *act;
 	int i;
 
-	tcf_exts_for_each_action(i, a, cls->exts) {
-		if (is_tcf_gact_ok(a)) {
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
 			fs->action = FILTER_PASS;
-		} else if (is_tcf_gact_shot(a)) {
+			break;
+		case FLOW_ACTION_DROP:
 			fs->action = FILTER_DROP;
-		} else if (is_tcf_mirred_egress_redirect(a)) {
-			struct net_device *out = tcf_mirred_dev(a);
+			break;
+		case FLOW_ACTION_REDIRECT: {
+			struct net_device *out = act->dev;
 			struct port_info *pi = netdev_priv(out);
 
 			fs->action = FILTER_SWITCH;
 			fs->eport = pi->port_id;
-		} else if (is_tcf_vlan(a)) {
-			u32 vlan_action = tcf_vlan_action(a);
-			u8 prio = tcf_vlan_push_prio(a);
-			u16 vid = tcf_vlan_push_vid(a);
+			}
+			break;
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_MANGLE: {
+			u8 prio = act->vlan.prio;
+			u16 vid = act->vlan.vid;
 			u16 vlan_tci = (prio << VLAN_PRIO_SHIFT) | vid;
-
-			switch (vlan_action) {
-			case TCA_VLAN_ACT_POP:
+			switch (act->id) {
+			case FLOW_ACTION_VLAN_POP:
 				fs->newvlan |= VLAN_REMOVE;
 				break;
-			case TCA_VLAN_ACT_PUSH:
+			case FLOW_ACTION_VLAN_PUSH:
 				fs->newvlan |= VLAN_INSERT;
 				fs->vlan = vlan_tci;
 				break;
-			case TCA_VLAN_ACT_MODIFY:
+			case FLOW_ACTION_VLAN_MANGLE:
 				fs->newvlan |= VLAN_REWRITE;
 				fs->vlan = vlan_tci;
 				break;
 			default:
 				break;
 			}
-		} else if (is_tcf_pedit(a)) {
+			}
+			break;
+		case FLOW_ACTION_MANGLE: {
 			u32 mask, val, offset;
-			int nkeys, i;
 			u8 htype;
 
-			nkeys = tcf_pedit_nkeys(a);
-			for (i = 0; i < nkeys; i++) {
-				htype = tcf_pedit_htype(a, i);
-				mask = tcf_pedit_mask(a, i);
-				val = tcf_pedit_val(a, i);
-				offset = tcf_pedit_offset(a, i);
+			htype = act->mangle.htype;
+			mask = act->mangle.mask;
+			val = act->mangle.val;
+			offset = act->mangle.offset;
 
-				process_pedit_field(fs, val, mask, offset,
-						    htype);
+			process_pedit_field(fs, val, mask, offset, htype);
 			}
+			break;
+		default:
+			break;
 		}
 	}
 }
@@ -484,101 +455,89 @@ static bool valid_l4_mask(u32 mask)
 }
 
 static bool valid_pedit_action(struct net_device *dev,
-			       const struct tc_action *a)
+			       const struct flow_action_entry *act)
 {
 	u32 mask, offset;
-	u8 cmd, htype;
-	int nkeys, i;
-
-	nkeys = tcf_pedit_nkeys(a);
-	for (i = 0; i < nkeys; i++) {
-		htype = tcf_pedit_htype(a, i);
-		cmd = tcf_pedit_cmd(a, i);
-		mask = tcf_pedit_mask(a, i);
-		offset = tcf_pedit_offset(a, i);
-
-		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) {
-			netdev_err(dev, "%s: Unsupported pedit cmd\n",
+	u8 htype;
+
+	htype = act->mangle.htype;
+	mask = act->mangle.mask;
+	offset = act->mangle.offset;
+
+	switch (htype) {
+	case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+		switch (offset) {
+		case PEDIT_ETH_DMAC_31_0:
+		case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
+		case PEDIT_ETH_SMAC_47_16:
+			break;
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
 				   __func__);
 			return false;
 		}
-
-		switch (htype) {
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
-			switch (offset) {
-			case PEDIT_ETH_DMAC_31_0:
-			case PEDIT_ETH_DMAC_47_32_SMAC_15_0:
-			case PEDIT_ETH_SMAC_47_16:
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
-					   __func__);
-				return false;
-			}
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
-			switch (offset) {
-			case PEDIT_IP4_SRC:
-			case PEDIT_IP4_DST:
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
-					   __func__);
-				return false;
-			}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+		switch (offset) {
+		case PEDIT_IP4_SRC:
+		case PEDIT_IP4_DST:
 			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
-			switch (offset) {
-			case PEDIT_IP6_SRC_31_0:
-			case PEDIT_IP6_SRC_63_32:
-			case PEDIT_IP6_SRC_95_64:
-			case PEDIT_IP6_SRC_127_96:
-			case PEDIT_IP6_DST_31_0:
-			case PEDIT_IP6_DST_63_32:
-			case PEDIT_IP6_DST_95_64:
-			case PEDIT_IP6_DST_127_96:
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
-					   __func__);
-				return false;
-			}
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
+				   __func__);
+			return false;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_IP6:
+		switch (offset) {
+		case PEDIT_IP6_SRC_31_0:
+		case PEDIT_IP6_SRC_63_32:
+		case PEDIT_IP6_SRC_95_64:
+		case PEDIT_IP6_SRC_127_96:
+		case PEDIT_IP6_DST_31_0:
+		case PEDIT_IP6_DST_63_32:
+		case PEDIT_IP6_DST_95_64:
+		case PEDIT_IP6_DST_127_96:
 			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
-			switch (offset) {
-			case PEDIT_TCP_SPORT_DPORT:
-				if (!valid_l4_mask(~mask)) {
-					netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
-						   __func__);
-					return false;
-				}
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
+				   __func__);
+			return false;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+		switch (offset) {
+		case PEDIT_TCP_SPORT_DPORT:
+			if (!valid_l4_mask(~mask)) {
+				netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n",
 					   __func__);
 				return false;
 			}
 			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
-			switch (offset) {
-			case PEDIT_UDP_SPORT_DPORT:
-				if (!valid_l4_mask(~mask)) {
-					netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
-						   __func__);
-					return false;
-				}
-				break;
-			default:
-				netdev_err(dev, "%s: Unsupported pedit field\n",
+		default:
+			netdev_err(dev, "%s: Unsupported pedit field\n",
+				   __func__);
+			return false;
+		}
+		break;
+	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+		switch (offset) {
+		case PEDIT_UDP_SPORT_DPORT:
+			if (!valid_l4_mask(~mask)) {
+				netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n",
 					   __func__);
 				return false;
 			}
 			break;
 		default:
-			netdev_err(dev, "%s: Unsupported pedit type\n",
+			netdev_err(dev, "%s: Unsupported pedit field\n",
 				   __func__);
 			return false;
 		}
+		break;
+	default:
+		netdev_err(dev, "%s: Unsupported pedit type\n", __func__);
+		return false;
 	}
 	return true;
 }
@@ -586,24 +545,26 @@ static bool valid_pedit_action(struct net_device *dev,
 static int cxgb4_validate_flow_actions(struct net_device *dev,
 				       struct tc_cls_flower_offload *cls)
 {
-	const struct tc_action *a;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_action_entry *act;
 	bool act_redir = false;
 	bool act_pedit = false;
 	bool act_vlan = false;
 	int i;
 
-	tcf_exts_for_each_action(i, a, cls->exts) {
-		if (is_tcf_gact_ok(a)) {
-			/* Do nothing */
-		} else if (is_tcf_gact_shot(a)) {
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
+		case FLOW_ACTION_DROP:
 			/* Do nothing */
-		} else if (is_tcf_mirred_egress_redirect(a)) {
+			break;
+		case FLOW_ACTION_REDIRECT: {
 			struct adapter *adap = netdev2adap(dev);
 			struct net_device *n_dev, *target_dev;
 			unsigned int i;
 			bool found = false;
 
-			target_dev = tcf_mirred_dev(a);
+			target_dev = act->dev;
 			for_each_port(adap, i) {
 				n_dev = adap->port[i];
 				if (target_dev == n_dev) {
@@ -621,15 +582,18 @@ static int cxgb4_validate_flow_actions(struct net_device *dev,
 				return -EINVAL;
 			}
 			act_redir = true;
-		} else if (is_tcf_vlan(a)) {
-			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
-			u32 vlan_action = tcf_vlan_action(a);
+			}
+			break;
+		case FLOW_ACTION_VLAN_POP:
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_MANGLE: {
+			u16 proto = be16_to_cpu(act->vlan.proto);
 
-			switch (vlan_action) {
-			case TCA_VLAN_ACT_POP:
+			switch (act->id) {
+			case FLOW_ACTION_VLAN_POP:
 				break;
-			case TCA_VLAN_ACT_PUSH:
-			case TCA_VLAN_ACT_MODIFY:
+			case FLOW_ACTION_VLAN_PUSH:
+			case FLOW_ACTION_VLAN_MANGLE:
 				if (proto != ETH_P_8021Q) {
 					netdev_err(dev, "%s: Unsupported vlan proto\n",
 						   __func__);
@@ -642,13 +606,17 @@ static int cxgb4_validate_flow_actions(struct net_device *dev,
 				return -EOPNOTSUPP;
 			}
 			act_vlan = true;
-		} else if (is_tcf_pedit(a)) {
-			bool pedit_valid = valid_pedit_action(dev, a);
+			}
+			break;
+		case FLOW_ACTION_MANGLE: {
+			bool pedit_valid = valid_pedit_action(dev, act);
 
 			if (!pedit_valid)
 				return -EOPNOTSUPP;
 			act_pedit = true;
-		} else {
+			}
+			break;
+		default:
 			netdev_err(dev, "%s: Unsupported action\n", __func__);
 			return -EOPNOTSUPP;
 		}
@@ -843,9 +811,9 @@ int cxgb4_tc_flower_stats(struct net_device *dev,
 	if (ofld_stats->packet_count != packets) {
 		if (ofld_stats->prev_packet_count != packets)
 			ofld_stats->last_used = jiffies;
-		tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count,
-				      packets - ofld_stats->packet_count,
-				      ofld_stats->last_used);
+		flow_stats_update(&cls->stats, bytes - ofld_stats->byte_count,
+				  packets - ofld_stats->packet_count,
+				  ofld_stats->last_used);
 
 		ofld_stats->packet_count = packets;
 		ofld_stats->byte_count = bytes;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
index c7d2b4dc7568..02fc63fa7f25 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c
@@ -444,8 +444,7 @@ struct cxgb4_tc_u32_table *cxgb4_init_tc_u32(struct adapter *adap)
 	if (!max_tids)
 		return NULL;
 
-	t = kvzalloc(sizeof(*t) +
-			 (max_tids * sizeof(struct cxgb4_link)), GFP_KERNEL);
+	t = kvzalloc(struct_size(t, table, max_tids), GFP_KERNEL);
 	if (!t)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
index 9a6065a3fa46..6c685b920713 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.c
@@ -78,7 +78,7 @@ static void free_msix_idx_in_bmap(struct adapter *adap, unsigned int msix_idx)
 	unsigned long flags;
 
 	spin_lock_irqsave(&bmap->lock, flags);
-	 __clear_bit(msix_idx, bmap->msix_bmap);
+	__clear_bit(msix_idx, bmap->msix_bmap);
 	spin_unlock_irqrestore(&bmap->lock, flags);
 }
 
@@ -147,7 +147,7 @@ static int alloc_uld_rxqs(struct adapter *adap,
 
 	per_chan = rxq_info->nrxq / adap->params.nports;
 
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		msi_idx = 1;
 	else
 		msi_idx = -((int)s->intrq.abs_id + 1);
@@ -195,7 +195,7 @@ setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
 	int i, ret = 0;
 
-	if (adap->flags & USING_MSIX) {
+	if (adap->flags & CXGB4_USING_MSIX) {
 		rxq_info->msix_tbl = kcalloc((rxq_info->nrxq + rxq_info->nciq),
 					     sizeof(unsigned short),
 					     GFP_KERNEL);
@@ -206,7 +206,7 @@ setup_sge_queues_uld(struct adapter *adap, unsigned int uld_type, bool lro)
 	ret = !(!alloc_uld_rxqs(adap, rxq_info, lro));
 
 	/* Tell uP to route control queue completions to rdma rspq */
-	if (adap->flags & FULL_INIT_DONE &&
+	if (adap->flags & CXGB4_FULL_INIT_DONE &&
 	    !ret && uld_type == CXGB4_ULD_RDMA) {
 		struct sge *s = &adap->sge;
 		unsigned int cmplqid;
@@ -239,7 +239,7 @@ static void free_sge_queues_uld(struct adapter *adap, unsigned int uld_type)
 {
 	struct sge_uld_rxq_info *rxq_info = adap->sge.uld_rxq_info[uld_type];
 
-	if (adap->flags & FULL_INIT_DONE && uld_type == CXGB4_ULD_RDMA) {
+	if (adap->flags & CXGB4_FULL_INIT_DONE && uld_type == CXGB4_ULD_RDMA) {
 		struct sge *s = &adap->sge;
 		u32 param, cmdop, cmplqid = 0;
 		int i;
@@ -258,7 +258,7 @@ static void free_sge_queues_uld(struct adapter *adap, unsigned int uld_type)
 		t4_free_uld_rxqs(adap, rxq_info->nciq,
 				 rxq_info->uldrxq + rxq_info->nrxq);
 	t4_free_uld_rxqs(adap, rxq_info->nrxq, rxq_info->uldrxq);
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		kfree(rxq_info->msix_tbl);
 }
 
@@ -273,7 +273,7 @@ static int cfg_queues_uld(struct adapter *adap, unsigned int uld_type,
 	if (!rxq_info)
 		return -ENOMEM;
 
-	if (adap->flags & USING_MSIX && uld_info->nrxq > s->nqs_per_uld) {
+	if (adap->flags & CXGB4_USING_MSIX && uld_info->nrxq > s->nqs_per_uld) {
 		i = s->nqs_per_uld;
 		rxq_info->nrxq = roundup(i, adap->params.nports);
 	} else {
@@ -284,7 +284,7 @@ static int cfg_queues_uld(struct adapter *adap, unsigned int uld_type,
 	if (!uld_info->ciq) {
 		rxq_info->nciq = 0;
 	} else  {
-		if (adap->flags & USING_MSIX)
+		if (adap->flags & CXGB4_USING_MSIX)
 			rxq_info->nciq = min_t(int, s->nqs_per_uld,
 					       num_online_cpus());
 		else
@@ -611,10 +611,10 @@ static void cxgb4_shutdown_uld_adapter(struct adapter *adap, enum cxgb4_uld type
 		adap->uld[type].add = NULL;
 		release_sge_txq_uld(adap, type);
 
-		if (adap->flags & FULL_INIT_DONE)
+		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			quiesce_rx_uld(adap, type);
 
-		if (adap->flags & USING_MSIX)
+		if (adap->flags & CXGB4_USING_MSIX)
 			free_msix_queue_irqs_uld(adap, type);
 
 		free_sge_queues_uld(adap, type);
@@ -660,6 +660,7 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->cclk_ps = 1000000000 / adap->params.vpd.cclk;
 	lld->udb_density = 1 << adap->params.sge.eq_qpp;
 	lld->ucq_density = 1 << adap->params.sge.iq_qpp;
+	lld->sge_host_page_size = 1 << (adap->params.sge.hps + 10);
 	lld->filt_mode = adap->params.tp.vlan_pri_map;
 	/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
 	for (i = 0; i < NCHAN; i++)
@@ -672,7 +673,7 @@ static void uld_init(struct adapter *adap, struct cxgb4_lld_info *lld)
 	lld->sge_egrstatuspagesize = adap->sge.stat_len;
 	lld->sge_pktshift = adap->sge.pktshift;
 	lld->ulp_crypto = adap->params.crypto;
-	lld->enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
+	lld->enable_fw_ofld_conn = adap->flags & CXGB4_FW_OFLD_CONN;
 	lld->max_ordird_qp = adap->params.max_ordird_qp;
 	lld->max_ird_adapter = adap->params.max_ird_adapter;
 	lld->ulptx_memwrite_dsgl = adap->params.ulptx_memwrite_dsgl;
@@ -701,7 +702,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 	adap->uld[uld].handle = handle;
 	t4_register_netevent_notifier();
 
-	if (adap->flags & FULL_INIT_DONE)
+	if (adap->flags & CXGB4_FULL_INIT_DONE)
 		adap->uld[uld].state_change(handle, CXGB4_STATE_UP);
 }
 
@@ -736,13 +737,13 @@ void cxgb4_register_uld(enum cxgb4_uld type,
 		ret = setup_sge_queues_uld(adap, type, p->lro);
 		if (ret)
 			goto free_queues;
-		if (adap->flags & USING_MSIX) {
+		if (adap->flags & CXGB4_USING_MSIX) {
 			name_msix_vecs_uld(adap, type);
 			ret = request_msix_queue_irqs_uld(adap, type);
 			if (ret)
 				goto free_rxq;
 		}
-		if (adap->flags & FULL_INIT_DONE)
+		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			enable_rx_uld(adap, type);
 		if (adap->uld[type].add)
 			goto free_irq;
@@ -753,9 +754,9 @@ void cxgb4_register_uld(enum cxgb4_uld type,
 		uld_attach(adap, type);
 		continue;
 free_irq:
-		if (adap->flags & FULL_INIT_DONE)
+		if (adap->flags & CXGB4_FULL_INIT_DONE)
 			quiesce_rx_uld(adap, type);
-		if (adap->flags & USING_MSIX)
+		if (adap->flags & CXGB4_USING_MSIX)
 			free_msix_queue_irqs_uld(adap, type);
 free_rxq:
 		free_sge_queues_uld(adap, type);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 5fa9a2d5fc4b..21da34a4ca24 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -336,6 +336,7 @@ struct cxgb4_lld_info {
 	unsigned int cclk_ps;                /* Core clock period in psec */
 	unsigned short udb_density;          /* # of user DB/page */
 	unsigned short ucq_density;          /* # of user CQs/page */
+	unsigned int sge_host_page_size;     /* SGE host page size */
 	unsigned short filt_mode;            /* filter optional components */
 	unsigned short tx_modq[NCHAN];       /* maps each tx channel to a */
 					     /* scheduler queue */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 99022c0898b5..1a407d3c1d67 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -495,14 +495,11 @@ u64 cxgb4_select_ntuple(struct net_device *dev,
 		ntuple |= (u64)IPPROTO_TCP << tp->protocol_shift;
 
 	if (tp->vnic_shift >= 0 && (tp->ingress_config & VNIC_F)) {
-		u32 viid = cxgb4_port_viid(dev);
-		u32 vf = FW_VIID_VIN_G(viid);
-		u32 pf = FW_VIID_PFN_G(viid);
-		u32 vld = FW_VIID_VIVLD_G(viid);
-
-		ntuple |= (u64)(FT_VNID_ID_VF_V(vf) |
-				FT_VNID_ID_PF_V(pf) |
-				FT_VNID_ID_VLD_V(vld)) << tp->vnic_shift;
+		struct port_info *pi = (struct port_info *)netdev_priv(dev);
+
+		ntuple |= (u64)(FT_VNID_ID_VF_V(pi->vin) |
+				FT_VNID_ID_PF_V(adap->pf) |
+				FT_VNID_ID_VLD_V(pi->vivld)) << tp->vnic_shift;
 	}
 
 	return ntuple;
@@ -649,7 +646,7 @@ struct l2t_data *t4_init_l2t(unsigned int l2t_start, unsigned int l2t_end)
 	if (l2t_size < L2T_MIN_HASH_BUCKETS)
 		return NULL;
 
-	d = kvzalloc(sizeof(*d) + l2t_size * sizeof(struct l2t_entry), GFP_KERNEL);
+	d = kvzalloc(struct_size(d, l2tab, l2t_size), GFP_KERNEL);
 	if (!d)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 52edb688942b..ba6c153ee45c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -478,7 +478,7 @@ struct sched_table *t4_init_sched(unsigned int sched_size)
 	struct sched_table *s;
 	unsigned int i;
 
-	s = kvzalloc(sizeof(*s) + sched_size * sizeof(struct sched_class), GFP_KERNEL);
+	s = kvzalloc(struct_size(s, tab, sched_size), GFP_KERNEL);
 	if (!s)
 		return NULL;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index b90188401d4a..b3da81e90132 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -80,9 +80,10 @@
  * Max number of Tx descriptors we clean up at a time.  Should be modest as
  * freeing skbs isn't cheap and it happens while holding locks.  We just need
  * to free packets faster than they arrive, we eventually catch up and keep
- * the amortized cost reasonable.  Must be >= 2 * TXQ_STOP_THRES.
+ * the amortized cost reasonable.  Must be >= 2 * TXQ_STOP_THRES.  It should
+ * also match the CIDX Flush Threshold.
  */
-#define MAX_TX_RECLAIM 16
+#define MAX_TX_RECLAIM 32
 
 /*
  * Max number of Rx buffers we replenish at a time.  Again keep this modest,
@@ -401,31 +402,52 @@ static inline int reclaimable(const struct sge_txq *q)
 }
 
 /**
- *	cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors
+ *	reclaim_completed_tx - reclaims completed TX Descriptors
  *	@adap: the adapter
  *	@q: the Tx queue to reclaim completed descriptors from
+ *	@maxreclaim: the maximum number of TX Descriptors to reclaim or -1
  *	@unmap: whether the buffers should be unmapped for DMA
  *
- *	Reclaims Tx descriptors that the SGE has indicated it has processed,
- *	and frees the associated buffers if possible.  Called with the Tx
- *	queue locked.
+ *	Reclaims Tx Descriptors that the SGE has indicated it has processed,
+ *	and frees the associated buffers if possible.  If @max == -1, then
+ *	we'll use a defaiult maximum.  Called with the TX Queue locked.
  */
-inline void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
-					bool unmap)
+static inline int reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
+				       int maxreclaim, bool unmap)
 {
-	int avail = reclaimable(q);
+	int reclaim = reclaimable(q);
 
-	if (avail) {
+	if (reclaim) {
 		/*
 		 * Limit the amount of clean up work we do at a time to keep
 		 * the Tx lock hold time O(1).
 		 */
-		if (avail > MAX_TX_RECLAIM)
-			avail = MAX_TX_RECLAIM;
+		if (maxreclaim < 0)
+			maxreclaim = MAX_TX_RECLAIM;
+		if (reclaim > maxreclaim)
+			reclaim = maxreclaim;
 
-		free_tx_desc(adap, q, avail, unmap);
-		q->in_use -= avail;
+		free_tx_desc(adap, q, reclaim, unmap);
+		q->in_use -= reclaim;
 	}
+
+	return reclaim;
+}
+
+/**
+ *	cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors
+ *	@adap: the adapter
+ *	@q: the Tx queue to reclaim completed descriptors from
+ *	@unmap: whether the buffers should be unmapped for DMA
+ *
+ *	Reclaims Tx descriptors that the SGE has indicated it has processed,
+ *	and frees the associated buffers if possible.  Called with the Tx
+ *	queue locked.
+ */
+void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q,
+				bool unmap)
+{
+	(void)reclaim_completed_tx(adap, q, -1, unmap);
 }
 EXPORT_SYMBOL(cxgb4_reclaim_completed_tx);
 
@@ -454,7 +476,7 @@ static inline int get_buf_size(struct adapter *adapter,
 		break;
 
 	default:
-		BUG_ON(1);
+		BUG();
 	}
 
 	return buf_size;
@@ -694,7 +716,7 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t elem_size,
 {
 	size_t len = nelem * elem_size + stat_size;
 	void *s = NULL;
-	void *p = dma_zalloc_coherent(dev, len, phys, GFP_KERNEL);
+	void *p = dma_alloc_coherent(dev, len, phys, GFP_KERNEL);
 
 	if (!p)
 		return NULL;
@@ -1288,6 +1310,44 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb,
 }
 
 /**
+ *	t4_sge_eth_txq_egress_update - handle Ethernet TX Queue update
+ *	@adap: the adapter
+ *	@eq: the Ethernet TX Queue
+ *	@maxreclaim: the maximum number of TX Descriptors to reclaim or -1
+ *
+ *	We're typically called here to update the state of an Ethernet TX
+ *	Queue with respect to the hardware's progress in consuming the TX
+ *	Work Requests that we've put on that Egress Queue.  This happens
+ *	when we get Egress Queue Update messages and also prophylactically
+ *	in regular timer-based Ethernet TX Queue maintenance.
+ */
+int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq,
+				 int maxreclaim)
+{
+	struct sge_txq *q = &eq->q;
+	unsigned int reclaimed;
+
+	if (!q->in_use || !__netif_tx_trylock(eq->txq))
+		return 0;
+
+	/* Reclaim pending completed TX Descriptors. */
+	reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true);
+
+	/* If the TX Queue is currently stopped and there's now more than half
+	 * the queue available, restart it.  Otherwise bail out since the rest
+	 * of what we want do here is with the possibility of shipping any
+	 * currently buffered Coalesced TX Work Request.
+	 */
+	if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) {
+		netif_tx_wake_queue(eq->txq);
+		eq->q.restarts++;
+	}
+
+	__netif_tx_unlock(eq->txq);
+	return reclaimed;
+}
+
+/**
  *	cxgb4_eth_xmit - add a packet to an Ethernet Tx queue
  *	@skb: the packet
  *	@dev: the egress net device
@@ -1357,7 +1417,7 @@ out_free:	dev_kfree_skb_any(skb);
 	}
 	skb_tx_timestamp(skb);
 
-	cxgb4_reclaim_completed_tx(adap, &q->q, true);
+	reclaim_completed_tx(adap, &q->q, -1, true);
 	cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
 
 #ifdef CONFIG_CHELSIO_T4_FCOE
@@ -1400,8 +1460,25 @@ out_free:	dev_kfree_skb_any(skb);
 
 	wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2));
 	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		/* After we're done injecting the Work Request for this
+		 * packet, we'll be below our "stop threshold" so stop the TX
+		 * Queue now and schedule a request for an SGE Egress Queue
+		 * Update message. The queue will get started later on when
+		 * the firmware processes this Work Request and sends us an
+		 * Egress Queue Status Update message indicating that space
+		 * has opened up.
+		 */
 		eth_txq_stop(q);
-		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+
+		/* If we're using the SGE Doorbell Queue Timer facility, we
+		 * don't need to ask the Firmware to send us Egress Queue CIDX
+		 * Updates: the Hardware will do this automatically.  And
+		 * since we send the Ingress Queue CIDX Updates to the
+		 * corresponding Ethernet Response Queue, we'll get them very
+		 * quickly.
+		 */
+		if (!q->dbqt)
+			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	wr = (void *)&q->q.desc[q->q.pidx];
@@ -1671,7 +1748,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 	/* Take this opportunity to reclaim any TX Descriptors whose DMA
 	 * transfers have completed.
 	 */
-	cxgb4_reclaim_completed_tx(adapter, &txq->q, true);
+	reclaim_completed_tx(adapter, &txq->q, -1, true);
 
 	/* Calculate the number of flits and TX Descriptors we're going to
 	 * need along with how many TX Descriptors will be left over after
@@ -1715,7 +1792,16 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
 		 * has opened up.
 		 */
 		eth_txq_stop(txq);
-		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+
+		/* If we're using the SGE Doorbell Queue Timer facility, we
+		 * don't need to ask the Firmware to send us Egress Queue CIDX
+		 * Updates: the Hardware will do this automatically.  And
+		 * since we send the Ingress Queue CIDX Updates to the
+		 * corresponding Ethernet Response Queue, we'll get them very
+		 * quickly.
+		 */
+		if (!txq->dbqt)
+			wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
 	}
 
 	/* Start filling in our Work Request.  Note that we do _not_ handle
@@ -2794,6 +2880,74 @@ static int t4_tx_hststamp(struct adapter *adapter, struct sk_buff *skb,
 }
 
 /**
+ *	t4_tx_completion_handler - handle CPL_SGE_EGR_UPDATE messages
+ *	@rspq: Ethernet RX Response Queue associated with Ethernet TX Queue
+ *	@rsp: Response Entry pointer into Response Queue
+ *	@gl: Gather List pointer
+ *
+ *	For adapters which support the SGE Doorbell Queue Timer facility,
+ *	we configure the Ethernet TX Queues to send CIDX Updates to the
+ *	Associated Ethernet RX Response Queue with CPL_SGE_EGR_UPDATE
+ *	messages.  This adds a small load to PCIe Link RX bandwidth and,
+ *	potentially, higher CPU Interrupt load, but allows us to respond
+ *	much more quickly to the CIDX Updates.  This is important for
+ *	Upper Layer Software which isn't willing to have a large amount
+ *	of TX Data outstanding before receiving DMA Completions.
+ */
+static void t4_tx_completion_handler(struct sge_rspq *rspq,
+				     const __be64 *rsp,
+				     const struct pkt_gl *gl)
+{
+	u8 opcode = ((const struct rss_header *)rsp)->opcode;
+	struct port_info *pi = netdev_priv(rspq->netdev);
+	struct adapter *adapter = rspq->adap;
+	struct sge *s = &adapter->sge;
+	struct sge_eth_txq *txq;
+
+	/* skip RSS header */
+	rsp++;
+
+	/* FW can send EGR_UPDATEs encapsulated in a CPL_FW4_MSG.
+	 */
+	if (unlikely(opcode == CPL_FW4_MSG &&
+		     ((const struct cpl_fw4_msg *)rsp)->type ==
+							FW_TYPE_RSSCPL)) {
+		rsp++;
+		opcode = ((const struct rss_header *)rsp)->opcode;
+		rsp++;
+	}
+
+	if (unlikely(opcode != CPL_SGE_EGR_UPDATE)) {
+		pr_info("%s: unexpected FW4/CPL %#x on Rx queue\n",
+			__func__, opcode);
+		return;
+	}
+
+	txq = &s->ethtxq[pi->first_qset + rspq->idx];
+
+	/* We've got the Hardware Consumer Index Update in the Egress Update
+	 * message.  If we're using the SGE Doorbell Queue Timer mechanism,
+	 * these Egress Update messages will be our sole CIDX Updates we get
+	 * since we don't want to chew up PCIe bandwidth for both Ingress
+	 * Messages and Status Page writes.  However, The code which manages
+	 * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value
+	 * stored in the Status Page at the end of the TX Queue.  It's easiest
+	 * to simply copy the CIDX Update value from the Egress Update message
+	 * to the Status Page.  Also note that no Endian issues need to be
+	 * considered here since both are Big Endian and we're just copying
+	 * bytes consistently ...
+	 */
+	if (txq->dbqt) {
+		struct cpl_sge_egr_update *egr;
+
+		egr = (struct cpl_sge_egr_update *)rsp;
+		WRITE_ONCE(txq->q.stat->cidx, egr->cidx);
+	}
+
+	t4_sge_eth_txq_egress_update(adapter, txq, -1);
+}
+
+/**
  *	t4_ethrx_handler - process an ingress ethernet packet
  *	@q: the response queue that received the packet
  *	@rsp: the response queue descriptor holding the RX_PKT message
@@ -2816,6 +2970,15 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 	struct port_info *pi;
 	int ret = 0;
 
+	/* If we're looking at TX Queue CIDX Update, handle that separately
+	 * and return.
+	 */
+	if (unlikely((*(u8 *)rsp == CPL_FW4_MSG) ||
+		     (*(u8 *)rsp == CPL_SGE_EGR_UPDATE))) {
+		t4_tx_completion_handler(q, rsp, si);
+		return 0;
+	}
+
 	if (unlikely(*(u8 *)rsp == cpl_trace_pkt))
 		return handle_trace_pkt(q->adap, si);
 
@@ -3212,7 +3375,7 @@ static irqreturn_t t4_intr_msi(int irq, void *cookie)
 {
 	struct adapter *adap = cookie;
 
-	if (adap->flags & MASTER_PF)
+	if (adap->flags & CXGB4_MASTER_PF)
 		t4_slow_intr_handler(adap);
 	process_intrq(adap);
 	return IRQ_HANDLED;
@@ -3228,7 +3391,7 @@ static irqreturn_t t4_intr_intx(int irq, void *cookie)
 	struct adapter *adap = cookie;
 
 	t4_write_reg(adap, MYPF_REG(PCIE_PF_CLI_A), 0);
-	if (((adap->flags & MASTER_PF) && t4_slow_intr_handler(adap)) |
+	if (((adap->flags & CXGB4_MASTER_PF) && t4_slow_intr_handler(adap)) |
 	    process_intrq(adap))
 		return IRQ_HANDLED;
 	return IRQ_NONE;             /* probably shared interrupt */
@@ -3243,9 +3406,9 @@ static irqreturn_t t4_intr_intx(int irq, void *cookie)
  */
 irq_handler_t t4_intr_handler(struct adapter *adap)
 {
-	if (adap->flags & USING_MSIX)
+	if (adap->flags & CXGB4_USING_MSIX)
 		return t4_sge_intr_msix;
-	if (adap->flags & USING_MSI)
+	if (adap->flags & CXGB4_USING_MSI)
 		return t4_intr_msi;
 	return t4_intr_intx;
 }
@@ -3278,7 +3441,7 @@ static void sge_rx_timer_cb(struct timer_list *t)
 	 * global Master PF activities like checking for chip ingress stalls,
 	 * etc.
 	 */
-	if (!(adap->flags & MASTER_PF))
+	if (!(adap->flags & CXGB4_MASTER_PF))
 		goto done;
 
 	t4_idma_monitor(adap, &s->idma_monitor, HZ, RX_QCHECK_PERIOD);
@@ -3289,10 +3452,10 @@ done:
 
 static void sge_tx_timer_cb(struct timer_list *t)
 {
-	unsigned long m;
-	unsigned int i, budget;
 	struct adapter *adap = from_timer(adap, t, sge.tx_timer);
 	struct sge *s = &adap->sge;
+	unsigned long m, period;
+	unsigned int i, budget;
 
 	for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++)
 		for (m = s->txq_maperr[i]; m; m &= m - 1) {
@@ -3320,29 +3483,29 @@ static void sge_tx_timer_cb(struct timer_list *t)
 	budget = MAX_TIMER_TX_RECLAIM;
 	i = s->ethtxq_rover;
 	do {
-		struct sge_eth_txq *q = &s->ethtxq[i];
-
-		if (q->q.in_use &&
-		    time_after_eq(jiffies, q->txq->trans_start + HZ / 100) &&
-		    __netif_tx_trylock(q->txq)) {
-			int avail = reclaimable(&q->q);
-
-			if (avail) {
-				if (avail > budget)
-					avail = budget;
-
-				free_tx_desc(adap, &q->q, avail, true);
-				q->q.in_use -= avail;
-				budget -= avail;
-			}
-			__netif_tx_unlock(q->txq);
-		}
+		budget -= t4_sge_eth_txq_egress_update(adap, &s->ethtxq[i],
+						       budget);
+		if (!budget)
+			break;
 
 		if (++i >= s->ethqsets)
 			i = 0;
-	} while (budget && i != s->ethtxq_rover);
+	} while (i != s->ethtxq_rover);
 	s->ethtxq_rover = i;
-	mod_timer(&s->tx_timer, jiffies + (budget ? TX_QCHECK_PERIOD : 2));
+
+	if (budget == 0) {
+		/* If we found too many reclaimable packets schedule a timer
+		 * in the near future to continue where we left off.
+		 */
+		period = 2;
+	} else {
+		/* We reclaimed all reclaimable TX Descriptors, so reschedule
+		 * at the normal period.
+		 */
+		period = TX_QCHECK_PERIOD;
+	}
+
+	mod_timer(&s->tx_timer, jiffies + period);
 }
 
 /**
@@ -3386,7 +3549,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	struct fw_iq_cmd c;
 	struct sge *s = &adap->sge;
 	struct port_info *pi = netdev_priv(dev);
-	int relaxed = !(adap->flags & ROOT_NO_RELAXED_ORDERING);
+	int relaxed = !(adap->flags & CXGB4_ROOT_NO_RELAXED_ORDERING);
 
 	/* Size needs to be multiple of 16, including status entry. */
 	iq->size = roundup(iq->size, 16);
@@ -3421,7 +3584,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 							:  FW_IQ_IQTYPE_OFLD));
 
 	if (fl) {
-		enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
+		unsigned int chip_ver =
+			CHELSIO_CHIP_VERSION(adap->params.chip);
 
 		/* Allocate the ring for the hardware free list (with space
 		 * for its status page) along with the associated software
@@ -3459,10 +3623,10 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		 * the smaller 64-byte value there).
 		 */
 		c.fl0dcaen_to_fl0cidxfthresh =
-			htons(FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ?
+			htons(FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5 ?
 						   FETCHBURSTMIN_128B_X :
-						   FETCHBURSTMIN_64B_X) |
-			      FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ?
+						   FETCHBURSTMIN_64B_T6_X) |
+			      FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ?
 						   FETCHBURSTMAX_512B_X :
 						   FETCHBURSTMAX_256B_X));
 		c.fl0size = htons(flsz);
@@ -3584,14 +3748,24 @@ static void init_txq(struct adapter *adap, struct sge_txq *q, unsigned int id)
 	adap->sge.egr_map[id - adap->sge.egr_start] = q;
 }
 
+/**
+ *	t4_sge_alloc_eth_txq - allocate an Ethernet TX Queue
+ *	@adap: the adapter
+ *	@txq: the SGE Ethernet TX Queue to initialize
+ *	@dev: the Linux Network Device
+ *	@netdevq: the corresponding Linux TX Queue
+ *	@iqid: the Ingress Queue to which to deliver CIDX Update messages
+ *	@dbqt: whether this TX Queue will use the SGE Doorbell Queue Timers
+ */
 int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			 struct net_device *dev, struct netdev_queue *netdevq,
-			 unsigned int iqid)
+			 unsigned int iqid, u8 dbqt)
 {
-	int ret, nentries;
-	struct fw_eq_eth_cmd c;
-	struct sge *s = &adap->sge;
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
 	struct port_info *pi = netdev_priv(dev);
+	struct sge *s = &adap->sge;
+	struct fw_eq_eth_cmd c;
+	int ret, nentries;
 
 	/* Add status entries */
 	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
@@ -3610,19 +3784,47 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 			    FW_EQ_ETH_CMD_VFN_V(0));
 	c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_ALLOC_F |
 				 FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(c));
-	c.viid_pkd = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
-			   FW_EQ_ETH_CMD_VIID_V(pi->viid));
+
+	/* For TX Ethernet Queues using the SGE Doorbell Queue Timer
+	 * mechanism, we use Ingress Queue messages for Hardware Consumer
+	 * Index Updates on the TX Queue.  Otherwise we have the Hardware
+	 * write the CIDX Updates into the Status Page at the end of the
+	 * TX Queue.
+	 */
+	c.autoequiqe_to_viid = htonl((dbqt
+				      ? FW_EQ_ETH_CMD_AUTOEQUIQE_F
+				      : FW_EQ_ETH_CMD_AUTOEQUEQE_F) |
+				     FW_EQ_ETH_CMD_VIID_V(pi->viid));
+
 	c.fetchszm_to_iqid =
-		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) |
+		htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt
+						 ? HOSTFCMODE_INGRESS_QUEUE_X
+						 : HOSTFCMODE_STATUS_PAGE_X) |
 		      FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid));
+
+	/* Note that the CIDX Flush Threshold should match MAX_TX_RECLAIM. */
 	c.dcaen_to_eqsize =
-		htonl(FW_EQ_ETH_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		htonl(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+					    ? FETCHBURSTMIN_64B_X
+					    : FETCHBURSTMIN_64B_T6_X) |
 		      FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 		      FW_EQ_ETH_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
 		      FW_EQ_ETH_CMD_EQSIZE_V(nentries));
+
 	c.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
+	/* If we're using the SGE Doorbell Queue Timer mechanism, pass in the
+	 * currently configured Timer Index.  THis can be changed later via an
+	 * ethtool -C tx-usecs {Timer Val} command.  Note that the SGE
+	 * Doorbell Queue mode is currently automatically enabled in the
+	 * Firmware by setting either AUTOEQUEQE or AUTOEQUIQE ...
+	 */
+	if (dbqt)
+		c.timeren_timerix =
+			cpu_to_be32(FW_EQ_ETH_CMD_TIMEREN_F |
+				    FW_EQ_ETH_CMD_TIMERIX_V(txq->dbqtimerix));
+
 	ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c);
 	if (ret) {
 		kfree(txq->q.sdesc);
@@ -3639,6 +3841,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq,
 	txq->txq = netdevq;
 	txq->tso = txq->tx_cso = txq->vlan_ins = 0;
 	txq->mapping_err = 0;
+	txq->dbqt = dbqt;
+
 	return 0;
 }
 
@@ -3646,10 +3850,11 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 			  struct net_device *dev, unsigned int iqid,
 			  unsigned int cmplqid)
 {
-	int ret, nentries;
-	struct fw_eq_ctrl_cmd c;
-	struct sge *s = &adap->sge;
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
 	struct port_info *pi = netdev_priv(dev);
+	struct sge *s = &adap->sge;
+	struct fw_eq_ctrl_cmd c;
+	int ret, nentries;
 
 	/* Add status entries */
 	nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc);
@@ -3673,7 +3878,9 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq,
 		      FW_EQ_CTRL_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_CTRL_CMD_FETCHRO_F | FW_EQ_CTRL_CMD_IQID_V(iqid));
 	c.dcaen_to_eqsize =
-		htonl(FW_EQ_CTRL_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		htonl(FW_EQ_CTRL_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+					     ? FETCHBURSTMIN_64B_X
+					     : FETCHBURSTMIN_64B_T6_X) |
 		      FW_EQ_CTRL_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 		      FW_EQ_CTRL_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
 		      FW_EQ_CTRL_CMD_EQSIZE_V(nentries));
@@ -3713,6 +3920,7 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq,
 			 struct net_device *dev, unsigned int iqid,
 			 unsigned int uld_type)
 {
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip);
 	int ret, nentries;
 	struct fw_eq_ofld_cmd c;
 	struct sge *s = &adap->sge;
@@ -3743,7 +3951,9 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq,
 		      FW_EQ_OFLD_CMD_PCIECHN_V(pi->tx_chan) |
 		      FW_EQ_OFLD_CMD_FETCHRO_F | FW_EQ_OFLD_CMD_IQID_V(iqid));
 	c.dcaen_to_eqsize =
-		htonl(FW_EQ_OFLD_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) |
+		htonl(FW_EQ_OFLD_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+					     ? FETCHBURSTMIN_64B_X
+					     : FETCHBURSTMIN_64B_T6_X) |
 		      FW_EQ_OFLD_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 		      FW_EQ_OFLD_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) |
 		      FW_EQ_OFLD_CMD_EQSIZE_V(nentries));
diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c
index 7b2207a2a130..eaf1fb74689c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/smt.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c
@@ -47,8 +47,7 @@ struct smt_data *t4_init_smt(void)
 
 	smt_size = SMT_SIZE;
 
-	s = kvzalloc(sizeof(*s) + smt_size * sizeof(struct smt_entry),
-		     GFP_KERNEL);
+	s = kvzalloc(struct_size(s, smtab, smt_size), GFP_KERNEL);
 	if (!s)
 		return NULL;
 	s->smt_size = smt_size;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/srq.c b/drivers/net/ethernet/chelsio/cxgb4/srq.c
index 82b70a565e24..9a54302bb046 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/srq.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/srq.c
@@ -77,7 +77,7 @@ int cxgb4_get_srq_entry(struct net_device *dev,
 	adap = netdev2adap(dev);
 	s = adap->srq;
 
-	if (!(adap->flags & FULL_INIT_DONE) || !s)
+	if (!(adap->flags & CXGB4_FULL_INIT_DONE) || !s)
 		goto out;
 
 	skb = alloc_skb(sizeof(*req), GFP_KERNEL);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index cb523949c812..a3544041ad32 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -198,7 +198,7 @@ static void t4_report_fw_error(struct adapter *adap)
 	if (pcie_fw & PCIE_FW_ERR_F) {
 		dev_err(adap->pdev_dev, "Firmware reports adapter error: %s\n",
 			reason[PCIE_FW_EVAL_G(pcie_fw)]);
-		adap->flags &= ~FW_OK;
+		adap->flags &= ~CXGB4_FW_OK;
 	}
 }
 
@@ -3794,7 +3794,7 @@ int t4_load_phy_fw(struct adapter *adap,
 	/* If we have version number support, then check to see if the adapter
 	 * already has up-to-date PHY firmware loaded.
 	 */
-	 if (phy_fw_version) {
+	if (phy_fw_version) {
 		new_phy_fw_vers = phy_fw_version(phy_fw_data, phy_fw_size);
 		ret = t4_phy_fw_ver(adap, &cur_phy_fw_ver);
 		if (ret < 0)
@@ -4105,6 +4105,9 @@ static inline fw_port_cap32_t cc_to_fwcap_fec(enum cc_fec cc_fec)
  *	@mbox: the Firmware Mailbox to use
  *	@port: the Port ID
  *	@lc: the Port's Link Configuration
+ *	@sleep_ok: if true we may sleep while awaiting command completion
+ *	@timeout: time to wait for command to finish before timing out
+ *		(negative implies @sleep_ok=false)
  *
  *	Set up a port's MAC and PHY according to a desired link configuration.
  *	- If the PHY can auto-negotiate first decide what to advertise, then
@@ -4124,6 +4127,7 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
 	int ret;
 
 	fw_mdi = (FW_PORT_CAP32_MDI_V(FW_PORT_CAP32_MDI_AUTO) & lc->pcaps);
+
 	/* Convert driver coding of Pause Frame Flow Control settings into the
 	 * Firmware's API.
 	 */
@@ -4143,8 +4147,13 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
 	fw_fec = cc_to_fwcap_fec(cc_fec);
 
 	/* Figure out what our Requested Port Capabilities are going to be.
+	 * Note parallel structure in t4_handle_get_port_info() and
+	 * init_link_config().
 	 */
 	if (!(lc->pcaps & FW_PORT_CAP32_ANEG)) {
+		if (lc->autoneg == AUTONEG_ENABLE)
+			return -EINVAL;
+
 		rcap = lc->acaps | fw_fc | fw_fec;
 		lc->fc = lc->requested_fc & ~PAUSE_AUTONEG;
 		lc->fec = cc_fec;
@@ -4156,7 +4165,11 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
 		rcap = lc->acaps | fw_fc | fw_fec | fw_mdi;
 	}
 
-	/* Note that older Firmware doesn't have FW_PORT_CAP32_FORCE_PAUSE, so
+	/* Some Requested Port Capabilities are trivially wrong if they exceed
+	 * the Physical Port Capabilities.  We can check that here and provide
+	 * moderately useful feedback in the system log.
+	 *
+	 * Note that older Firmware doesn't have FW_PORT_CAP32_FORCE_PAUSE, so
 	 * we need to exclude this from this check in order to maintain
 	 * compatibility ...
 	 */
@@ -4185,6 +4198,13 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox,
 
 	ret = t4_wr_mbox_meat_timeout(adapter, mbox, &cmd, sizeof(cmd), NULL,
 				      sleep_ok, timeout);
+
+	/* Unfortunately, even if the Requested Port Capabilities "fit" within
+	 * the Physical Port Capabilities, some combinations of features may
+	 * still not be leagal.  For example, 40Gb/s and Reed-Solomon Forward
+	 * Error Correction.  So if the Firmware rejects the L1 Configure
+	 * request, flag that here.
+	 */
 	if (ret) {
 		dev_err(adapter->pdev_dev,
 			"Requested Port Capabilities %#x rejected, error %d\n",
@@ -4942,7 +4962,13 @@ static void pl_intr_handler(struct adapter *adap)
  */
 int t4_slow_intr_handler(struct adapter *adapter)
 {
-	u32 cause = t4_read_reg(adapter, PL_INT_CAUSE_A);
+	/* There are rare cases where a PL_INT_CAUSE bit may end up getting
+	 * set when the corresponding PL_INT_ENABLE bit isn't set.  It's
+	 * easiest just to mask that case here.
+	 */
+	u32 raw_cause = t4_read_reg(adapter, PL_INT_CAUSE_A);
+	u32 enable = t4_read_reg(adapter, PL_INT_ENABLE_A);
+	u32 cause = raw_cause & enable;
 
 	if (!(cause & GLBL_INTR_MASK))
 		return 0;
@@ -4994,7 +5020,7 @@ int t4_slow_intr_handler(struct adapter *adapter)
 		ulptx_intr_handler(adapter);
 
 	/* Clear the interrupts just processed for which we are the master. */
-	t4_write_reg(adapter, PL_INT_CAUSE_A, cause & GLBL_INTR_MASK);
+	t4_write_reg(adapter, PL_INT_CAUSE_A, raw_cause & GLBL_INTR_MASK);
 	(void)t4_read_reg(adapter, PL_INT_CAUSE_A); /* flush */
 	return 1;
 }
@@ -5217,7 +5243,7 @@ int t4_read_rss(struct adapter *adapter, u16 *map)
 
 static unsigned int t4_use_ldst(struct adapter *adap)
 {
-	return (adap->flags & FW_OK) && !adap->use_bd;
+	return (adap->flags & CXGB4_FW_OK) && !adap->use_bd;
 }
 
 /**
@@ -5880,7 +5906,6 @@ int t4_set_trace_filter(struct adapter *adap, const struct trace_params *tp,
 {
 	int i, ofst = idx * 4;
 	u32 data_reg, mask_reg, cfg;
-	u32 multitrc = TRCMULTIFILTER_F;
 
 	if (!enable) {
 		t4_write_reg(adap, MPS_TRC_FILTER_MATCH_CTL_A_A + ofst, 0);
@@ -5900,7 +5925,6 @@ int t4_set_trace_filter(struct adapter *adap, const struct trace_params *tp,
 		 * maximum packet capture size of 9600 bytes is recommended.
 		 * Also in this mode, only trace0 can be enabled and running.
 		 */
-		multitrc = 0;
 		if (tp->snap_len > 9600 || idx)
 			return -EINVAL;
 	}
@@ -6108,7 +6132,7 @@ unsigned int t4_get_mps_bg_map(struct adapter *adapter, int pidx)
 	 *        ( MPSBGMAP[Port 1] <<  8 ) |
 	 *        ( MPSBGMAP[Port 0] <<  0 ))
 	 */
-	if (adapter->flags & FW_OK) {
+	if (adapter->flags & CXGB4_FW_OK) {
 		u32 param, val;
 		int ret;
 
@@ -6695,6 +6719,47 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type)
 }
 
 /**
+ *	t4_read_sge_dbqtimers - reag SGE Doorbell Queue Timer values
+ *	@adap - the adapter
+ *	@ndbqtimers: size of the provided SGE Doorbell Queue Timer table
+ *	@dbqtimers: SGE Doorbell Queue Timer table
+ *
+ *	Reads the SGE Doorbell Queue Timer values into the provided table.
+ *	Returns 0 on success (Firmware and Hardware support this feature),
+ *	an error on failure.
+ */
+int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers,
+			  u16 *dbqtimers)
+{
+	int ret, dbqtimerix;
+
+	ret = 0;
+	dbqtimerix = 0;
+	while (dbqtimerix < ndbqtimers) {
+		int nparams, param;
+		u32 params[7], vals[7];
+
+		nparams = ndbqtimers - dbqtimerix;
+		if (nparams > ARRAY_SIZE(params))
+			nparams = ARRAY_SIZE(params);
+
+		for (param = 0; param < nparams; param++)
+			params[param] =
+			  (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+			   FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMER) |
+			   FW_PARAMS_PARAM_Y_V(dbqtimerix + param));
+		ret = t4_query_params(adap, adap->mbox, adap->pf, 0,
+				      nparams, params, vals);
+		if (ret)
+			break;
+
+		for (param = 0; param < nparams; param++)
+			dbqtimers[dbqtimerix++] = vals[param];
+	}
+	return ret;
+}
+
+/**
  *      t4_fw_hello - establish communication with FW
  *      @adap: the adapter
  *      @mbox: mailbox to use for the FW command
@@ -7028,10 +7093,10 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 	if (!t4_fw_matches_chip(adap, fw_hdr))
 		return -EINVAL;
 
-	/* Disable FW_OK flag so that mbox commands with FW_OK flag set
-	 * wont be sent when we are flashing FW.
+	/* Disable CXGB4_FW_OK flag so that mbox commands with CXGB4_FW_OK flag
+	 * set wont be sent when we are flashing FW.
 	 */
-	adap->flags &= ~FW_OK;
+	adap->flags &= ~CXGB4_FW_OK;
 
 	ret = t4_fw_halt(adap, mbox, force);
 	if (ret < 0 && !force)
@@ -7070,7 +7135,7 @@ int t4_fw_upgrade(struct adapter *adap, unsigned int mbox,
 	 */
 	(void)t4_init_devlog_params(adap);
 out:
-	adap->flags |= FW_OK;
+	adap->flags |= CXGB4_FW_OK;
 	return ret;
 }
 
@@ -7141,21 +7206,10 @@ int t4_fixup_host_params(struct adapter *adap, unsigned int page_size,
 			 unsigned int cache_line_size)
 {
 	unsigned int page_shift = fls(page_size) - 1;
-	unsigned int sge_hps = page_shift - 10;
 	unsigned int stat_len = cache_line_size > 64 ? 128 : 64;
 	unsigned int fl_align = cache_line_size < 32 ? 32 : cache_line_size;
 	unsigned int fl_align_log = fls(fl_align) - 1;
 
-	t4_write_reg(adap, SGE_HOST_PAGE_SIZE_A,
-		     HOSTPAGESIZEPF0_V(sge_hps) |
-		     HOSTPAGESIZEPF1_V(sge_hps) |
-		     HOSTPAGESIZEPF2_V(sge_hps) |
-		     HOSTPAGESIZEPF3_V(sge_hps) |
-		     HOSTPAGESIZEPF4_V(sge_hps) |
-		     HOSTPAGESIZEPF5_V(sge_hps) |
-		     HOSTPAGESIZEPF6_V(sge_hps) |
-		     HOSTPAGESIZEPF7_V(sge_hps));
-
 	if (is_t4(adap->params.chip)) {
 		t4_set_reg_field(adap, SGE_CONTROL_A,
 				 INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
@@ -7488,7 +7542,7 @@ int t4_cfg_pfvf(struct adapter *adap, unsigned int mbox, unsigned int pf,
  */
 int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		unsigned int pf, unsigned int vf, unsigned int nmac, u8 *mac,
-		unsigned int *rss_size)
+		unsigned int *rss_size, u8 *vivld, u8 *vin)
 {
 	int ret;
 	struct fw_vi_cmd c;
@@ -7523,6 +7577,13 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 	}
 	if (rss_size)
 		*rss_size = FW_VI_CMD_RSSSIZE_G(be16_to_cpu(c.rsssize_pkd));
+
+	if (vivld)
+		*vivld = FW_VI_CMD_VFVLD_G(be32_to_cpu(c.alloc_to_len16));
+
+	if (vin)
+		*vin = FW_VI_CMD_VIN_G(be32_to_cpu(c.alloc_to_len16));
+
 	return FW_VI_CMD_VIID_G(be16_to_cpu(c.type_viid));
 }
 
@@ -7980,7 +8041,7 @@ int t4_free_mac_filt(struct adapter *adap, unsigned int mbox,
  *	MAC value.
  */
 int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
-		  int idx, const u8 *addr, bool persist, bool add_smt)
+		  int idx, const u8 *addr, bool persist, u8 *smt_idx)
 {
 	int ret, mode;
 	struct fw_vi_mac_cmd c;
@@ -7989,7 +8050,7 @@ int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
 
 	if (idx < 0)                             /* new allocation */
 		idx = persist ? FW_VI_MAC_ADD_PERSIST_MAC : FW_VI_MAC_ADD_MAC;
-	mode = add_smt ? FW_VI_MAC_SMT_AND_MPSTCAM : FW_VI_MAC_MPS_TCAM_ENTRY;
+	mode = smt_idx ? FW_VI_MAC_SMT_AND_MPSTCAM : FW_VI_MAC_MPS_TCAM_ENTRY;
 
 	memset(&c, 0, sizeof(c));
 	c.op_to_viid = cpu_to_be32(FW_CMD_OP_V(FW_VI_MAC_CMD) |
@@ -8006,6 +8067,23 @@ int t4_change_mac(struct adapter *adap, unsigned int mbox, unsigned int viid,
 		ret = FW_VI_MAC_CMD_IDX_G(be16_to_cpu(p->valid_to_idx));
 		if (ret >= max_mac_addr)
 			ret = -ENOMEM;
+		if (smt_idx) {
+			if (adap->params.viid_smt_extn_support) {
+				*smt_idx = FW_VI_MAC_CMD_SMTID_G
+						    (be32_to_cpu(c.op_to_viid));
+			} else {
+				/* In T4/T5, SMT contains 256 SMAC entries
+				 * organized in 128 rows of 2 entries each.
+				 * In T6, SMT contains 256 SMAC entries in
+				 * 256 rows.
+				 */
+				if (CHELSIO_CHIP_VERSION(adap->params.chip) <=
+								     CHELSIO_T5)
+					*smt_idx = (viid & FW_VIID_VIN_M) << 1;
+				else
+					*smt_idx = (viid & FW_VIID_VIN_M);
+			}
+		}
 	}
 	return ret;
 }
@@ -8450,6 +8528,10 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 	fc = fwcap_to_cc_pause(linkattr);
 	speed = fwcap_to_speed(linkattr);
 
+	/* Reset state for communicating new Transceiver Module status and
+	 * whether the OS-dependent layer wants us to redo the current
+	 * "sticky" L1 Configure Link Parameters.
+	 */
 	lc->new_module = false;
 	lc->redo_l1cfg = false;
 
@@ -8486,9 +8568,15 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		 */
 		pi->port_type = port_type;
 
+		/* Record new Module Type information.
+		 */
 		pi->mod_type = mod_type;
 
+		/* Let the OS-dependent layer know if we have a new
+		 * Transceiver Module inserted.
+		 */
 		lc->new_module = t4_is_inserted_mod_type(mod_type);
+
 		t4_os_portmod_changed(adapter, pi->port_id);
 	}
 
@@ -8496,8 +8584,10 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 	    fc != lc->fc || fec != lc->fec) {	/* something changed */
 		if (!link_ok && lc->link_ok) {
 			lc->link_down_rc = linkdnrc;
-			dev_warn(adapter->pdev_dev, "Port %d link down, reason: %s\n",
-				 pi->tx_chan, t4_link_down_rc_str(linkdnrc));
+			dev_warn_ratelimited(adapter->pdev_dev,
+					     "Port %d link down, reason: %s\n",
+					     pi->tx_chan,
+					     t4_link_down_rc_str(linkdnrc));
 		}
 		lc->link_ok = link_ok;
 		lc->speed = speed;
@@ -8507,6 +8597,11 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		lc->lpacaps = lpacaps;
 		lc->acaps = acaps & ADVERT_MASK;
 
+		/* If we're not physically capable of Auto-Negotiation, note
+		 * this as Auto-Negotiation disabled.  Otherwise, we track
+		 * what Auto-Negotiation settings we have.  Note parallel
+		 * structure in t4_link_l1cfg_core() and init_link_config().
+		 */
 		if (!(lc->acaps & FW_PORT_CAP32_ANEG)) {
 			lc->autoneg = AUTONEG_DISABLE;
 		} else if (lc->acaps & FW_PORT_CAP32_ANEG) {
@@ -8524,6 +8619,10 @@ void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl)
 		t4_os_link_changed(adapter, pi->port_id, link_ok);
 	}
 
+	/* If we have a new Transceiver Module and the OS-dependent code has
+	 * told us that it wants us to redo whatever "sticky" L1 Configuration
+	 * Link Parameters are set, do that now.
+	 */
 	if (lc->new_module && lc->redo_l1cfg) {
 		struct link_config old_lc;
 		int ret;
@@ -8593,7 +8692,7 @@ int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,
 {
 	unsigned int fw_caps = pi->adapter->params.fw_caps_support;
 	struct fw_port_cmd port_cmd;
-	unsigned int action, link_ok, speed, mtu;
+	unsigned int action, link_ok, mtu;
 	fw_port_cap32_t linkattr;
 	int ret;
 
@@ -8627,7 +8726,6 @@ int t4_get_link_params(struct port_info *pi, unsigned int *link_okp,
 		mtu = FW_PORT_CMD_MTU32_G(
 			be32_to_cpu(port_cmd.u.info32.auxlinfo32_mtu32));
 	}
-	speed = fwcap_to_speed(linkattr);
 
 	*link_okp = link_ok;
 	*speedp = fwcap_to_speed(linkattr);
@@ -9374,6 +9472,7 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 	enum fw_port_type port_type;
 	int mdio_addr;
 	fw_port_cap32_t pcaps, acaps;
+	u8 vivld = 0, vin = 0;
 	int ret;
 
 	/* If we haven't yet determined whether we're talking to Firmware
@@ -9428,7 +9527,8 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 		acaps = be32_to_cpu(cmd.u.info32.acaps32);
 	}
 
-	ret = t4_alloc_vi(pi->adapter, mbox, port, pf, vf, 1, mac, &rss_size);
+	ret = t4_alloc_vi(pi->adapter, mbox, port, pf, vf, 1, mac, &rss_size,
+			  &vivld, &vin);
 	if (ret < 0)
 		return ret;
 
@@ -9437,6 +9537,18 @@ int t4_init_portinfo(struct port_info *pi, int mbox,
 	pi->lport = port;
 	pi->rss_size = rss_size;
 
+	/* If fw supports returning the VIN as part of FW_VI_CMD,
+	 * save the returned values.
+	 */
+	if (adapter->params.viid_smt_extn_support) {
+		pi->vivld = vivld;
+		pi->vin = vin;
+	} else {
+		/* Retrieve the values from VIID */
+		pi->vivld = FW_VIID_VIVLD_G(pi->viid);
+		pi->vin =  FW_VIID_VIN_G(pi->viid);
+	}
+
 	pi->port_type = port_type;
 	pi->mdio_addr = mdio_addr;
 	pi->mod_type = FW_PORT_MOD_TYPE_NA;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
index 361d5032c288..002fc62ea726 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h
@@ -91,6 +91,7 @@ enum {
 	SGE_CTXT_SIZE = 24,       /* size of SGE context */
 	SGE_NTIMERS = 6,          /* # of interrupt holdoff timer values */
 	SGE_NCOUNTERS = 4,        /* # of interrupt packet counter values */
+	SGE_NDBQTIMERS = 8,       /* # of Doorbell Queue Timer values */
 	SGE_MAX_IQ_SIZE = 65520,
 
 	SGE_TIMER_RSTRT_CNTR = 6, /* restart RX packet threshold counter */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index c62a0c830705..38dd41eb959e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -56,6 +56,7 @@ enum {
 	CPL_TX_DATA_ISO	      = 0x1F,
 
 	CPL_CLOSE_LISTSRV_RPL = 0x20,
+	CPL_GET_TCB_RPL       = 0x22,
 	CPL_L2T_WRITE_RPL     = 0x23,
 	CPL_PASS_OPEN_RPL     = 0x24,
 	CPL_ACT_OPEN_RPL      = 0x25,
@@ -688,6 +689,13 @@ struct cpl_get_tcb {
 #define NO_REPLY_V(x) ((x) << NO_REPLY_S)
 #define NO_REPLY_F    NO_REPLY_V(1U)
 
+struct cpl_get_tcb_rpl {
+	union opcode_tid ot;
+	__u8 cookie;
+	__u8 status;
+	__be16 len;
+};
+
 struct cpl_set_tcb_field {
 	WR_HDR;
 	union opcode_tid ot;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index 60df66f4d21c..0c5373462ced 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -217,6 +217,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x6087), /* Custom T6225-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x6088), /* Custom T62100-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x6089), /* Custom T62100-KR */
+	CH_PCI_ID_TABLE_FENTRY(0x608a), /* Custom T62100-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x608b), /* Custom T6225-CR */
 CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
 
 #endif /* __T4_PCI_ID_TBL_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
index 3297ce025e8b..1b9afb192f7f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_tcb.h
@@ -41,6 +41,14 @@
 #define TCB_SMAC_SEL_V(x)	((x) << TCB_SMAC_SEL_S)
 
 #define TCB_T_FLAGS_W		1
+#define TCB_T_FLAGS_S		0
+#define TCB_T_FLAGS_M		0xffffffffffffffffULL
+#define TCB_T_FLAGS_V(x)	((__u64)(x) << TCB_T_FLAGS_S)
+
+#define TCB_RQ_START_W		30
+#define TCB_RQ_START_S		0
+#define TCB_RQ_START_M		0x3ffffffULL
+#define TCB_RQ_START_V(x)	((x) << TCB_RQ_START_S)
 
 #define TF_CCTRL_ECE_S		60
 #define TF_CCTRL_CWR_S		61
@@ -66,4 +74,8 @@
 #define TCB_RX_FRAG3_LEN_RAW_W	29
 #define TCB_RX_FRAG3_START_IDX_OFFSET_RAW_W	30
 #define TCB_PDU_HDR_LEN_W	31
+
+#define TF_RX_PDU_OUT_S		49
+#define TF_RX_PDU_OUT_V(x)	((__u64)(x) << TF_RX_PDU_OUT_S)
+
 #endif /* __T4_TCB_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
index f6558cbfc54e..eb1aa82149db 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h
@@ -71,12 +71,18 @@
 #define FETCHBURSTMIN_64B_X		2
 #define FETCHBURSTMIN_128B_X		3
 
+/* T6 and later use a single-bit encoding for FetchBurstMin */
+#define FETCHBURSTMIN_64B_T6_X		0
+#define FETCHBURSTMIN_128B_T6_X		1
+
 #define FETCHBURSTMAX_256B_X		2
 #define FETCHBURSTMAX_512B_X		3
 
+#define HOSTFCMODE_INGRESS_QUEUE_X	1
 #define HOSTFCMODE_STATUS_PAGE_X	2
 
 #define CIDXFLUSHTHRESH_32_X		5
+#define CIDXFLUSHTHRESH_128_X		7
 
 #define UPDATEDELIVERY_INTERRUPT_X	1
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index 57584ab32043..b2a618e72fcf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1253,6 +1253,9 @@ enum fw_params_param_dev {
 	FW_PARAMS_PARAM_DEV_HMA_SIZE	= 0x20,
 	FW_PARAMS_PARAM_DEV_RDMA_WRITE_WITH_IMM = 0x21,
 	FW_PARAMS_PARAM_DEV_RI_WRITE_CMPL_WR    = 0x24,
+	FW_PARAMS_PARAM_DEV_OPAQUE_VIID_SMT_EXTN = 0x27,
+	FW_PARAMS_PARAM_DEV_DBQ_TIMER	= 0x29,
+	FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK = 0x2A,
 };
 
 /*
@@ -1309,6 +1312,14 @@ enum fw_params_param_pfvf {
 	FW_PARAMS_PARAM_PFVF_RAWF_END = 0x37,
 	FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x39,
 	FW_PARAMS_PARAM_PFVF_PORT_CAPS32 = 0x3A,
+	FW_PARAMS_PARAM_PFVF_LINK_STATE = 0x40,
+};
+
+/* Virtual link state as seen by the specified VF */
+enum vf_link_states {
+	FW_VF_LINK_STATE_AUTO		= 0x00,
+	FW_VF_LINK_STATE_ENABLE		= 0x01,
+	FW_VF_LINK_STATE_DISABLE	= 0x02,
 };
 
 /*
@@ -1321,6 +1332,7 @@ enum fw_params_param_dmaq {
 	FW_PARAMS_PARAM_DMAQ_EQ_CMPLIQID_CTRL = 0x11,
 	FW_PARAMS_PARAM_DMAQ_EQ_SCHEDCLASS_ETH = 0x12,
 	FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH = 0x13,
+	FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX	= 0x15,
 	FW_PARAMS_PARAM_DMAQ_CONM_CTXT = 0x20,
 };
 
@@ -1750,8 +1762,8 @@ struct fw_eq_eth_cmd {
 	__be32 fetchszm_to_iqid;
 	__be32 dcaen_to_eqsize;
 	__be64 eqaddr;
-	__be32 viid_pkd;
-	__be32 r8_lo;
+	__be32 autoequiqe_to_viid;
+	__be32 timeren_timerix;
 	__be64 r9;
 };
 
@@ -1846,6 +1858,10 @@ struct fw_eq_eth_cmd {
 #define FW_EQ_ETH_CMD_EQSIZE_S		0
 #define FW_EQ_ETH_CMD_EQSIZE_V(x)	((x) << FW_EQ_ETH_CMD_EQSIZE_S)
 
+#define FW_EQ_ETH_CMD_AUTOEQUIQE_S	31
+#define FW_EQ_ETH_CMD_AUTOEQUIQE_V(x)	((x) << FW_EQ_ETH_CMD_AUTOEQUIQE_S)
+#define FW_EQ_ETH_CMD_AUTOEQUIQE_F	FW_EQ_ETH_CMD_AUTOEQUIQE_V(1U)
+
 #define FW_EQ_ETH_CMD_AUTOEQUEQE_S	30
 #define FW_EQ_ETH_CMD_AUTOEQUEQE_V(x)	((x) << FW_EQ_ETH_CMD_AUTOEQUEQE_S)
 #define FW_EQ_ETH_CMD_AUTOEQUEQE_F	FW_EQ_ETH_CMD_AUTOEQUEQE_V(1U)
@@ -1853,6 +1869,19 @@ struct fw_eq_eth_cmd {
 #define FW_EQ_ETH_CMD_VIID_S	16
 #define FW_EQ_ETH_CMD_VIID_V(x)	((x) << FW_EQ_ETH_CMD_VIID_S)
 
+#define FW_EQ_ETH_CMD_TIMEREN_S		3
+#define FW_EQ_ETH_CMD_TIMEREN_M		0x1
+#define FW_EQ_ETH_CMD_TIMEREN_V(x)	((x) << FW_EQ_ETH_CMD_TIMEREN_S)
+#define FW_EQ_ETH_CMD_TIMEREN_G(x)	\
+    (((x) >> FW_EQ_ETH_CMD_TIMEREN_S) & FW_EQ_ETH_CMD_TIMEREN_M)
+#define FW_EQ_ETH_CMD_TIMEREN_F	FW_EQ_ETH_CMD_TIMEREN_V(1U)
+
+#define FW_EQ_ETH_CMD_TIMERIX_S		0
+#define FW_EQ_ETH_CMD_TIMERIX_M		0x7
+#define FW_EQ_ETH_CMD_TIMERIX_V(x)	((x) << FW_EQ_ETH_CMD_TIMERIX_S)
+#define FW_EQ_ETH_CMD_TIMERIX_G(x)	\
+    (((x) >> FW_EQ_ETH_CMD_TIMERIX_S) & FW_EQ_ETH_CMD_TIMERIX_M)
+
 struct fw_eq_ctrl_cmd {
 	__be32 op_to_vfn;
 	__be32 alloc_to_len16;
@@ -2109,6 +2138,19 @@ struct fw_vi_cmd {
 #define FW_VI_CMD_FREE_V(x)	((x) << FW_VI_CMD_FREE_S)
 #define FW_VI_CMD_FREE_F	FW_VI_CMD_FREE_V(1U)
 
+#define FW_VI_CMD_VFVLD_S	24
+#define FW_VI_CMD_VFVLD_M	0x1
+#define FW_VI_CMD_VFVLD_V(x)	((x) << FW_VI_CMD_VFVLD_S)
+#define FW_VI_CMD_VFVLD_G(x)	\
+	(((x) >> FW_VI_CMD_VFVLD_S) & FW_VI_CMD_VFVLD_M)
+#define FW_VI_CMD_VFVLD_F	FW_VI_CMD_VFVLD_V(1U)
+
+#define FW_VI_CMD_VIN_S		16
+#define FW_VI_CMD_VIN_M		0xff
+#define FW_VI_CMD_VIN_V(x)	((x) << FW_VI_CMD_VIN_S)
+#define FW_VI_CMD_VIN_G(x)	\
+	(((x) >> FW_VI_CMD_VIN_S) & FW_VI_CMD_VIN_M)
+
 #define FW_VI_CMD_VIID_S	0
 #define FW_VI_CMD_VIID_M	0xfff
 #define FW_VI_CMD_VIID_V(x)	((x) << FW_VI_CMD_VIID_S)
@@ -2182,6 +2224,12 @@ struct fw_vi_mac_cmd {
 	} u;
 };
 
+#define FW_VI_MAC_CMD_SMTID_S		12
+#define FW_VI_MAC_CMD_SMTID_M		0xff
+#define FW_VI_MAC_CMD_SMTID_V(x)	((x) << FW_VI_MAC_CMD_SMTID_S)
+#define FW_VI_MAC_CMD_SMTID_G(x)	\
+	(((x) >> FW_VI_MAC_CMD_SMTID_S) & FW_VI_MAC_CMD_SMTID_M)
+
 #define FW_VI_MAC_CMD_VIID_S	0
 #define FW_VI_MAC_CMD_VIID_V(x)	((x) << FW_VI_MAC_CMD_VIID_S)
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index a844296135b4..9125ddd89dd1 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 0x14
-#define T4FW_VERSION_MICRO 0x08
+#define T4FW_VERSION_MINOR 0x16
+#define T4FW_VERSION_MICRO 0x09
 #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 0x14
-#define T5FW_VERSION_MICRO 0x08
+#define T5FW_VERSION_MINOR 0x16
+#define T5FW_VERSION_MICRO 0x09
 #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 0x14
-#define T6FW_VERSION_MICRO 0x08
+#define T6FW_VERSION_MINOR 0x16
+#define T6FW_VERSION_MICRO 0x09
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
index 5883f09e3804..3782e48dada2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h
@@ -94,7 +94,7 @@ struct port_info {
 	struct adapter *adapter;	/* our adapter */
 	u32 vlan_id;			/* vlan id for VST */
 	u16 viid;			/* virtual interface ID */
-	s16 xact_addr_filt;		/* index of our MAC address filter */
+	int xact_addr_filt;		/* index of our MAC address filter */
 	u16 rss_size;			/* size of VI's RSS table slice */
 	u8 pidx;			/* index into adapter port[] */
 	s8 mdio_addr;
@@ -352,6 +352,7 @@ struct sge {
 struct hash_mac_addr {
 	struct list_head list;
 	u8 addr[ETH_ALEN];
+	unsigned int iface_mac;
 };
 
 struct mbox_list {
@@ -405,11 +406,12 @@ struct adapter {
 };
 
 enum { /* adapter flags */
-	FULL_INIT_DONE     = (1UL << 0),
-	USING_MSI          = (1UL << 1),
-	USING_MSIX         = (1UL << 2),
-	QUEUES_BOUND       = (1UL << 3),
-	ROOT_NO_RELAXED_ORDERING = (1UL << 4),
+	CXGB4VF_FULL_INIT_DONE			= (1UL << 0),
+	CXGB4VF_USING_MSI			= (1UL << 1),
+	CXGB4VF_USING_MSIX			= (1UL << 2),
+	CXGB4VF_QUEUES_BOUND			= (1UL << 3),
+	CXGB4VF_ROOT_NO_RELAXED_ORDERING	= (1UL << 4),
+	CXGB4VF_FW_OK				= (1UL << 5),
 };
 
 /*
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index ff84791a0ff8..adc4d481815b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -155,6 +155,8 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok)
 		const char *fc;
 		const struct port_info *pi = netdev_priv(dev);
 
+		netif_carrier_on(dev);
+
 		switch (pi->link_cfg.speed) {
 		case 100:
 			s = "100Mbps";
@@ -200,6 +202,7 @@ void t4vf_os_link_changed(struct adapter *adapter, int pidx, int link_ok)
 
 		netdev_info(dev, "link up, %s, full-duplex, %s PAUSE\n", s, fc);
 	} else {
+		netif_carrier_off(dev);
 		netdev_info(dev, "link down\n");
 	}
 }
@@ -236,6 +239,73 @@ void t4vf_os_portmod_changed(struct adapter *adapter, int pidx)
 			 "inserted\n", dev->name, pi->mod_type);
 }
 
+static int cxgb4vf_set_addr_hash(struct port_info *pi)
+{
+	struct adapter *adapter = pi->adapter;
+	u64 vec = 0;
+	bool ucast = false;
+	struct hash_mac_addr *entry;
+
+	/* Calculate the hash vector for the updated list and program it */
+	list_for_each_entry(entry, &adapter->mac_hlist, list) {
+		ucast |= is_unicast_ether_addr(entry->addr);
+		vec |= (1ULL << hash_mac_addr(entry->addr));
+	}
+	return t4vf_set_addr_hash(adapter, pi->viid, ucast, vec, false);
+}
+
+/**
+ *	cxgb4vf_change_mac - Update match filter for a MAC address.
+ *	@pi: the port_info
+ *	@viid: the VI id
+ *	@tcam_idx: TCAM index of existing filter for old value of MAC address,
+ *		   or -1
+ *	@addr: the new MAC address value
+ *	@persist: whether a new MAC allocation should be persistent
+ *	@add_smt: if true also add the address to the HW SMT
+ *
+ *	Modifies an MPS filter and sets it to the new MAC address if
+ *	@tcam_idx >= 0, or adds the MAC address to a new filter if
+ *	@tcam_idx < 0. In the latter case the address is added persistently
+ *	if @persist is %true.
+ *	Addresses are programmed to hash region, if tcam runs out of entries.
+ *
+ */
+static int cxgb4vf_change_mac(struct port_info *pi, unsigned int viid,
+			      int *tcam_idx, const u8 *addr, bool persistent)
+{
+	struct hash_mac_addr *new_entry, *entry;
+	struct adapter *adapter = pi->adapter;
+	int ret;
+
+	ret = t4vf_change_mac(adapter, viid, *tcam_idx, addr, persistent);
+	/* We ran out of TCAM entries. try programming hash region. */
+	if (ret == -ENOMEM) {
+		/* If the MAC address to be updated is in the hash addr
+		 * list, update it from the list
+		 */
+		list_for_each_entry(entry, &adapter->mac_hlist, list) {
+			if (entry->iface_mac) {
+				ether_addr_copy(entry->addr, addr);
+				goto set_hash;
+			}
+		}
+		new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL);
+		if (!new_entry)
+			return -ENOMEM;
+		ether_addr_copy(new_entry->addr, addr);
+		new_entry->iface_mac = true;
+		list_add_tail(&new_entry->list, &adapter->mac_hlist);
+set_hash:
+		ret = cxgb4vf_set_addr_hash(pi);
+	} else if (ret >= 0) {
+		*tcam_idx = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
 /*
  * Net device operations.
  * ======================
@@ -259,14 +329,10 @@ static int link_start(struct net_device *dev)
 	 */
 	ret = t4vf_set_rxmode(pi->adapter, pi->viid, dev->mtu, -1, -1, -1, 1,
 			      true);
-	if (ret == 0) {
-		ret = t4vf_change_mac(pi->adapter, pi->viid,
-				      pi->xact_addr_filt, dev->dev_addr, true);
-		if (ret >= 0) {
-			pi->xact_addr_filt = ret;
-			ret = 0;
-		}
-	}
+	if (ret == 0)
+		ret = cxgb4vf_change_mac(pi, pi->viid,
+					 &pi->xact_addr_filt,
+					 dev->dev_addr, true);
 
 	/*
 	 * We don't need to actually "start the link" itself since the
@@ -276,16 +342,6 @@ static int link_start(struct net_device *dev)
 	if (ret == 0)
 		ret = t4vf_enable_pi(pi->adapter, pi, true, true);
 
-	/* The Virtual Interfaces are connected to an internal switch on the
-	 * chip which allows VIs attached to the same port to talk to each
-	 * other even when the port link is down.  As a result, we generally
-	 * want to always report a VI's link as being "up", provided there are
-	 * no errors in enabling vi.
-	 */
-
-	if (ret == 0)
-		netif_carrier_on(dev);
-
 	return ret;
 }
 
@@ -406,7 +462,7 @@ static void enable_rx(struct adapter *adapter)
 	 * The interrupt queue doesn't use NAPI so we do the 0-increment of
 	 * its Going To Sleep register here to get it started.
 	 */
-	if (adapter->flags & USING_MSI)
+	if (adapter->flags & CXGB4VF_USING_MSI)
 		t4_write_reg(adapter, T4VF_SGE_BASE_ADDR + SGE_VF_GTS,
 			     CIDXINC_V(0) |
 			     SEINTARM_V(s->intrq.intr_params) |
@@ -550,7 +606,7 @@ static int setup_sge_queues(struct adapter *adapter)
 	 * the intrq's queue ID as the interrupt forwarding queue for the
 	 * subsequent calls ...
 	 */
-	if (adapter->flags & USING_MSI) {
+	if (adapter->flags & CXGB4VF_USING_MSI) {
 		err = t4vf_sge_alloc_rxq(adapter, &s->intrq, false,
 					 adapter->port[0], 0, NULL, NULL);
 		if (err)
@@ -710,7 +766,7 @@ static int adapter_up(struct adapter *adapter)
 	 * adapter setup.  Once we've done this, many of our adapter
 	 * parameters can no longer be changed ...
 	 */
-	if ((adapter->flags & FULL_INIT_DONE) == 0) {
+	if ((adapter->flags & CXGB4VF_FULL_INIT_DONE) == 0) {
 		err = setup_sge_queues(adapter);
 		if (err)
 			return err;
@@ -720,16 +776,18 @@ static int adapter_up(struct adapter *adapter)
 			return err;
 		}
 
-		if (adapter->flags & USING_MSIX)
+		if (adapter->flags & CXGB4VF_USING_MSIX)
 			name_msix_vecs(adapter);
-		adapter->flags |= FULL_INIT_DONE;
+
+		adapter->flags |= CXGB4VF_FULL_INIT_DONE;
 	}
 
 	/*
 	 * Acquire our interrupt resources.  We only support MSI-X and MSI.
 	 */
-	BUG_ON((adapter->flags & (USING_MSIX|USING_MSI)) == 0);
-	if (adapter->flags & USING_MSIX)
+	BUG_ON((adapter->flags &
+	       (CXGB4VF_USING_MSIX | CXGB4VF_USING_MSI)) == 0);
+	if (adapter->flags & CXGB4VF_USING_MSIX)
 		err = request_msix_queue_irqs(adapter);
 	else
 		err = request_irq(adapter->pdev->irq,
@@ -747,8 +805,6 @@ static int adapter_up(struct adapter *adapter)
 	enable_rx(adapter);
 	t4vf_sge_start(adapter);
 
-	/* Initialize hash mac addr list*/
-	INIT_LIST_HEAD(&adapter->mac_hlist);
 	return 0;
 }
 
@@ -762,7 +818,7 @@ static void adapter_down(struct adapter *adapter)
 	/*
 	 * Free interrupt resources.
 	 */
-	if (adapter->flags & USING_MSIX)
+	if (adapter->flags & CXGB4VF_USING_MSIX)
 		free_msix_queue_irqs(adapter);
 	else
 		free_irq(adapter->pdev->irq, adapter);
@@ -783,6 +839,13 @@ static int cxgb4vf_open(struct net_device *dev)
 	struct adapter *adapter = pi->adapter;
 
 	/*
+	 * If we don't have a connection to the firmware there's nothing we
+	 * can do.
+	 */
+	if (!(adapter->flags & CXGB4VF_FW_OK))
+		return -ENXIO;
+
+	/*
 	 * If this is the first interface that we're opening on the "adapter",
 	 * bring the "adapter" up now.
 	 */
@@ -792,6 +855,13 @@ static int cxgb4vf_open(struct net_device *dev)
 			return err;
 	}
 
+	/* It's possible that the basic port information could have
+	 * changed since we first read it.
+	 */
+	err = t4vf_update_port_info(pi);
+	if (err < 0)
+		return err;
+
 	/*
 	 * Note that this interface is up and start everything up ...
 	 */
@@ -864,21 +934,6 @@ static struct net_device_stats *cxgb4vf_get_stats(struct net_device *dev)
 	return ns;
 }
 
-static inline int cxgb4vf_set_addr_hash(struct port_info *pi)
-{
-	struct adapter *adapter = pi->adapter;
-	u64 vec = 0;
-	bool ucast = false;
-	struct hash_mac_addr *entry;
-
-	/* Calculate the hash vector for the updated list and program it */
-	list_for_each_entry(entry, &adapter->mac_hlist, list) {
-		ucast |= is_unicast_ether_addr(entry->addr);
-		vec |= (1ULL << hash_mac_addr(entry->addr));
-	}
-	return t4vf_set_addr_hash(adapter, pi->viid, ucast, vec, false);
-}
-
 static int cxgb4vf_mac_sync(struct net_device *netdev, const u8 *mac_addr)
 {
 	struct port_info *pi = netdev_priv(netdev);
@@ -1160,13 +1215,12 @@ static int cxgb4vf_set_mac_addr(struct net_device *dev, void *_addr)
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
-	ret = t4vf_change_mac(pi->adapter, pi->viid, pi->xact_addr_filt,
-			      addr->sa_data, true);
+	ret = cxgb4vf_change_mac(pi, pi->viid, &pi->xact_addr_filt,
+				 addr->sa_data, true);
 	if (ret < 0)
 		return ret;
 
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
-	pi->xact_addr_filt = ret;
 	return 0;
 }
 
@@ -1180,7 +1234,7 @@ static void cxgb4vf_poll_controller(struct net_device *dev)
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
 
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4VF_USING_MSIX) {
 		struct sge_eth_rxq *rxq;
 		int nqsets;
 
@@ -1355,7 +1409,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 	case FW_PORT_TYPE_CR4_QSFP:
 		SET_LMM(FIBRE);
 		FW_CAPS_TO_LMM(SPEED_1G,  1000baseT_Full);
-		FW_CAPS_TO_LMM(SPEED_10G, 10000baseSR_Full);
+		FW_CAPS_TO_LMM(SPEED_10G, 10000baseKR_Full);
 		FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full);
 		FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full);
 		FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full);
@@ -1366,6 +1420,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type,
 		break;
 	}
 
+	if (fw_caps & FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M)) {
+		FW_CAPS_TO_LMM(FEC_RS, FEC_RS);
+		FW_CAPS_TO_LMM(FEC_BASER_RS, FEC_BASER);
+	} else {
+		SET_LMM(FEC_NONE);
+	}
+
 	FW_CAPS_TO_LMM(ANEG, Autoneg);
 	FW_CAPS_TO_LMM(802_3_PAUSE, Pause);
 	FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause);
@@ -1588,7 +1649,7 @@ static int cxgb4vf_set_ringparam(struct net_device *dev,
 	    rp->tx_pending < MIN_TXQ_ENTRIES)
 		return -EINVAL;
 
-	if (adapter->flags & FULL_INIT_DONE)
+	if (adapter->flags & CXGB4VF_FULL_INIT_DONE)
 		return -EBUSY;
 
 	for (qs = pi->first_qset; qs < pi->first_qset + pi->nqsets; qs++) {
@@ -1872,6 +1933,8 @@ static void cxgb4vf_get_wol(struct net_device *dev,
  * TCP Segmentation Offload flags which we support.
  */
 #define TSO_FLAGS (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+#define VLAN_FEAT (NETIF_F_SG | NETIF_F_IP_CSUM | TSO_FLAGS | \
+		   NETIF_F_GRO | NETIF_F_IPV6_CSUM | NETIF_F_HIGHDMA)
 
 static const struct ethtool_ops cxgb4vf_ethtool_ops = {
 	.get_link_ksettings	= cxgb4vf_get_link_ksettings,
@@ -2103,7 +2166,7 @@ static int sge_qinfo_show(struct seq_file *seq, void *v)
 static int sge_queue_entries(const struct adapter *adapter)
 {
 	return DIV_ROUND_UP(adapter->sge.ethqsets, QPL) + 1 +
-		((adapter->flags & USING_MSI) != 0);
+		((adapter->flags & CXGB4VF_USING_MSI) != 0);
 }
 
 static void *sge_queue_start(struct seq_file *seq, loff_t *pos)
@@ -2249,7 +2312,7 @@ static int sge_qstats_show(struct seq_file *seq, void *v)
 static int sge_qstats_entries(const struct adapter *adapter)
 {
 	return DIV_ROUND_UP(adapter->sge.ethqsets, QPL) + 1 +
-		((adapter->flags & USING_MSI) != 0);
+		((adapter->flags & CXGB4VF_USING_MSI) != 0);
 }
 
 static void *sge_qstats_start(struct seq_file *seq, loff_t *pos)
@@ -2324,19 +2387,7 @@ static int resources_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int resources_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, resources_show, inode->i_private);
-}
-
-static const struct file_operations resources_proc_fops = {
-	.owner   = THIS_MODULE,
-	.open    = resources_open,
-	.read    = seq_read,
-	.llseek  = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(resources);
 
 /*
  * Show Virtual Interfaces.
@@ -2420,7 +2471,7 @@ static struct cxgb4vf_debugfs_entry debugfs_files[] = {
 	{ "mboxlog",    0444, &mboxlog_fops },
 	{ "sge_qinfo",  0444, &sge_qinfo_debugfs_fops },
 	{ "sge_qstats", 0444, &sge_qstats_proc_fops },
-	{ "resources",  0444, &resources_proc_fops },
+	{ "resources",  0444, &resources_fops },
 	{ "interfaces", 0444, &interfaces_proc_fops },
 };
 
@@ -2670,6 +2721,7 @@ static int adap_init0(struct adapter *adapter)
 	 */
 	size_nports_qsets(adapter);
 
+	adapter->flags |= CXGB4VF_FW_OK;
 	return 0;
 }
 
@@ -2704,7 +2756,8 @@ static void cfg_queues(struct adapter *adapter)
 	 * support.  In particular, this means that we need to know what kind
 	 * of interrupts we'll be using ...
 	 */
-	BUG_ON((adapter->flags & (USING_MSIX|USING_MSI)) == 0);
+	BUG_ON((adapter->flags &
+	       (CXGB4VF_USING_MSIX | CXGB4VF_USING_MSI)) == 0);
 
 	/*
 	 * Count the number of 10GbE Virtual Interfaces that we have.
@@ -3030,11 +3083,16 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * using Relaxed Ordering.
 	 */
 	if (!pcie_relaxed_ordering_enabled(pdev))
-		adapter->flags |= ROOT_NO_RELAXED_ORDERING;
+		adapter->flags |= CXGB4VF_ROOT_NO_RELAXED_ORDERING;
 
 	err = adap_init0(adapter);
 	if (err)
-		goto err_unmap_bar;
+		dev_err(&pdev->dev,
+			"Adapter initialization failed, error %d. Continuing in debug mode\n",
+			err);
+
+	/* Initialize hash mac addr list */
+	INIT_LIST_HEAD(&adapter->mac_hlist);
 
 	/*
 	 * Allocate our "adapter ports" and stitch everything together.
@@ -3056,13 +3114,6 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 			break;
 		port_id = ffs(pmask) - 1;
 		pmask &= ~(1 << port_id);
-		viid = t4vf_alloc_vi(adapter, port_id);
-		if (viid < 0) {
-			dev_err(&pdev->dev, "cannot allocate VI for port %d:"
-				" err=%d\n", port_id, viid);
-			err = viid;
-			goto err_free_dev;
-		}
 
 		/*
 		 * Allocate our network device and stitch things together.
@@ -3070,7 +3121,6 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netdev = alloc_etherdev_mq(sizeof(struct port_info),
 					   MAX_PORT_QSETS);
 		if (netdev == NULL) {
-			t4vf_free_vi(adapter, viid);
 			err = -ENOMEM;
 			goto err_free_dev;
 		}
@@ -3080,26 +3130,21 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		pi->adapter = adapter;
 		pi->pidx = pidx;
 		pi->port_id = port_id;
-		pi->viid = viid;
 
 		/*
 		 * Initialize the starting state of our "port" and register
 		 * it.
 		 */
 		pi->xact_addr_filt = -1;
-		netif_carrier_off(netdev);
 		netdev->irq = pdev->irq;
 
-		netdev->hw_features = NETIF_F_SG | TSO_FLAGS |
-			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_RXCSUM;
-		netdev->vlan_features = NETIF_F_SG | TSO_FLAGS |
-			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-			NETIF_F_HIGHDMA;
-		netdev->features = netdev->hw_features |
-				   NETIF_F_HW_VLAN_CTAG_TX;
+		netdev->hw_features = NETIF_F_SG | TSO_FLAGS | NETIF_F_GRO |
+			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM |
+			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
+		netdev->features = netdev->hw_features;
 		if (pci_using_dac)
 			netdev->features |= NETIF_F_HIGHDMA;
+		netdev->vlan_features = netdev->features & VLAN_FEAT;
 
 		netdev->priv_flags |= IFF_UNICAST_FLT;
 		netdev->min_mtu = 81;
@@ -3110,6 +3155,23 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 		netdev->dev_port = pi->port_id;
 
 		/*
+		 * If we haven't been able to contact the firmware, there's
+		 * nothing else we can do for this "port" ...
+		 */
+		if (!(adapter->flags & CXGB4VF_FW_OK))
+			continue;
+
+		viid = t4vf_alloc_vi(adapter, port_id);
+		if (viid < 0) {
+			dev_err(&pdev->dev,
+				"cannot allocate VI for port %d: err=%d\n",
+				port_id, viid);
+			err = viid;
+			goto err_free_dev;
+		}
+		pi->viid = viid;
+
+		/*
 		 * Initialize the hardware/software state for the port.
 		 */
 		err = t4vf_port_init(adapter, pidx);
@@ -3146,7 +3208,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * get MSI interrupts we bail with the error.
 	 */
 	if (msi == MSI_MSIX && enable_msix(adapter) == 0)
-		adapter->flags |= USING_MSIX;
+		adapter->flags |= CXGB4VF_USING_MSIX;
 	else {
 		if (msi == MSI_MSIX) {
 			dev_info(adapter->pdev_dev,
@@ -3166,7 +3228,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 				" err=%d\n", err);
 			goto err_free_dev;
 		}
-		adapter->flags |= USING_MSI;
+		adapter->flags |= CXGB4VF_USING_MSI;
 	}
 
 	/* Now that we know how many "ports" we have and what interrupt
@@ -3196,6 +3258,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 			continue;
 		}
 
+		netif_carrier_off(netdev);
 		set_bit(pidx, &adapter->registered_device_map);
 	}
 	if (adapter->registered_device_map == 0) {
@@ -3224,8 +3287,8 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	for_each_port(adapter, pidx) {
 		dev_info(adapter->pdev_dev, "%s: Chelsio VF NIC PCIe %s\n",
 			 adapter->port[pidx]->name,
-			 (adapter->flags & USING_MSIX) ? "MSI-X" :
-			 (adapter->flags & USING_MSI)  ? "MSI" : "");
+			 (adapter->flags & CXGB4VF_USING_MSIX) ? "MSI-X" :
+			 (adapter->flags & CXGB4VF_USING_MSI)  ? "MSI" : "");
 	}
 
 	/*
@@ -3238,12 +3301,12 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev,
 	 * so far and return the error.
 	 */
 err_disable_interrupts:
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4VF_USING_MSIX) {
 		pci_disable_msix(adapter->pdev);
-		adapter->flags &= ~USING_MSIX;
-	} else if (adapter->flags & USING_MSI) {
+		adapter->flags &= ~CXGB4VF_USING_MSIX;
+	} else if (adapter->flags & CXGB4VF_USING_MSI) {
 		pci_disable_msi(adapter->pdev);
-		adapter->flags &= ~USING_MSI;
+		adapter->flags &= ~CXGB4VF_USING_MSI;
 	}
 
 err_free_dev:
@@ -3252,13 +3315,13 @@ err_free_dev:
 		if (netdev == NULL)
 			continue;
 		pi = netdev_priv(netdev);
-		t4vf_free_vi(adapter, pi->viid);
+		if (pi->viid)
+			t4vf_free_vi(adapter, pi->viid);
 		if (test_bit(pidx, &adapter->registered_device_map))
 			unregister_netdev(netdev);
 		free_netdev(netdev);
 	}
 
-err_unmap_bar:
 	if (!is_t4(adapter->params.chip))
 		iounmap(adapter->bar2);
 
@@ -3287,6 +3350,7 @@ err_disable_device:
 static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 {
 	struct adapter *adapter = pci_get_drvdata(pdev);
+	struct hash_mac_addr *entry, *tmp;
 
 	/*
 	 * Tear down driver state associated with device.
@@ -3302,12 +3366,12 @@ static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 			if (test_bit(pidx, &adapter->registered_device_map))
 				unregister_netdev(adapter->port[pidx]);
 		t4vf_sge_stop(adapter);
-		if (adapter->flags & USING_MSIX) {
+		if (adapter->flags & CXGB4VF_USING_MSIX) {
 			pci_disable_msix(adapter->pdev);
-			adapter->flags &= ~USING_MSIX;
-		} else if (adapter->flags & USING_MSI) {
+			adapter->flags &= ~CXGB4VF_USING_MSIX;
+		} else if (adapter->flags & CXGB4VF_USING_MSI) {
 			pci_disable_msi(adapter->pdev);
-			adapter->flags &= ~USING_MSI;
+			adapter->flags &= ~CXGB4VF_USING_MSI;
 		}
 
 		/*
@@ -3330,13 +3394,19 @@ static void cxgb4vf_pci_remove(struct pci_dev *pdev)
 				continue;
 
 			pi = netdev_priv(netdev);
-			t4vf_free_vi(adapter, pi->viid);
+			if (pi->viid)
+				t4vf_free_vi(adapter, pi->viid);
 			free_netdev(netdev);
 		}
 		iounmap(adapter->regs);
 		if (!is_t4(adapter->params.chip))
 			iounmap(adapter->bar2);
 		kfree(adapter->mbox_log);
+		list_for_each_entry_safe(entry, tmp, &adapter->mac_hlist,
+					 list) {
+			list_del(&entry->list);
+			kfree(entry);
+		}
 		kfree(adapter);
 	}
 
@@ -3373,12 +3443,12 @@ static void cxgb4vf_pci_shutdown(struct pci_dev *pdev)
 	 * Interrupts allowing various internal pathways to drain.
 	 */
 	t4vf_sge_stop(adapter);
-	if (adapter->flags & USING_MSIX) {
+	if (adapter->flags & CXGB4VF_USING_MSIX) {
 		pci_disable_msix(adapter->pdev);
-		adapter->flags &= ~USING_MSIX;
-	} else if (adapter->flags & USING_MSI) {
+		adapter->flags &= ~CXGB4VF_USING_MSIX;
+	} else if (adapter->flags & CXGB4VF_USING_MSI) {
 		pci_disable_msi(adapter->pdev);
-		adapter->flags &= ~USING_MSI;
+		adapter->flags &= ~CXGB4VF_USING_MSI;
 	}
 
 	/*
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 3007e1ac1e61..f71c973398ec 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -756,7 +756,7 @@ static void *alloc_ring(struct device *dev, size_t nelem, size_t hwsize,
 	 * Allocate the hardware ring and PCI DMA bus address space for said.
 	 */
 	size_t hwlen = nelem * hwsize + stat_size;
-	void *hwring = dma_zalloc_coherent(dev, hwlen, busaddrp, GFP_KERNEL);
+	void *hwring = dma_alloc_coherent(dev, hwlen, busaddrp, GFP_KERNEL);
 
 	if (!hwring)
 		return NULL;
@@ -2044,8 +2044,9 @@ static irqreturn_t t4vf_intr_msi(int irq, void *cookie)
  */
 irq_handler_t t4vf_intr_handler(struct adapter *adapter)
 {
-	BUG_ON((adapter->flags & (USING_MSIX|USING_MSI)) == 0);
-	if (adapter->flags & USING_MSIX)
+	BUG_ON((adapter->flags &
+	       (CXGB4VF_USING_MSIX | CXGB4VF_USING_MSI)) == 0);
+	if (adapter->flags & CXGB4VF_USING_MSIX)
 		return t4vf_sge_intr_msix;
 	else
 		return t4vf_intr_msi;
@@ -2209,7 +2210,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	struct port_info *pi = netdev_priv(dev);
 	struct fw_iq_cmd cmd, rpl;
 	int ret, iqandst, flsz = 0;
-	int relaxed = !(adapter->flags & ROOT_NO_RELAXED_ORDERING);
+	int relaxed = !(adapter->flags & CXGB4VF_ROOT_NO_RELAXED_ORDERING);
 
 	/*
 	 * If we're using MSI interrupts and we're not initializing the
@@ -2218,7 +2219,8 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	 * the Forwarded Interrupt Queue must be set up before any other
 	 * ingress queue ...
 	 */
-	if ((adapter->flags & USING_MSI) && rspq != &adapter->sge.intrq) {
+	if ((adapter->flags & CXGB4VF_USING_MSI) &&
+	    rspq != &adapter->sge.intrq) {
 		iqandst = SGE_INTRDST_IQ;
 		intr_dest = adapter->sge.intrq.abs_id;
 	} else
@@ -2268,7 +2270,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 	cmd.iqaddr = cpu_to_be64(rspq->phys_addr);
 
 	if (fl) {
-		enum chip_type chip =
+		unsigned int chip_ver =
 			CHELSIO_CHIP_VERSION(adapter->params.chip);
 		/*
 		 * Allocate the ring for the hardware free list (with space
@@ -2319,10 +2321,10 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq,
 		 */
 		cmd.fl0dcaen_to_fl0cidxfthresh =
 			cpu_to_be16(
-				FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ?
-						     FETCHBURSTMIN_128B_X :
-						     FETCHBURSTMIN_64B_X) |
-				FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ?
+				FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5
+						     ? FETCHBURSTMIN_128B_X
+						     : FETCHBURSTMIN_64B_T6_X) |
+				FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ?
 						     FETCHBURSTMAX_512B_X :
 						     FETCHBURSTMAX_256B_X));
 		cmd.fl0size = cpu_to_be16(flsz);
@@ -2411,10 +2413,11 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq,
 			   struct net_device *dev, struct netdev_queue *devq,
 			   unsigned int iqid)
 {
+	unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip);
+	struct port_info *pi = netdev_priv(dev);
+	struct fw_eq_eth_cmd cmd, rpl;
 	struct sge *s = &adapter->sge;
 	int ret, nentries;
-	struct fw_eq_eth_cmd cmd, rpl;
-	struct port_info *pi = netdev_priv(dev);
 
 	/*
 	 * Calculate the size of the hardware TX Queue (including the Status
@@ -2448,17 +2451,19 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq,
 	cmd.alloc_to_len16 = cpu_to_be32(FW_EQ_ETH_CMD_ALLOC_F |
 					 FW_EQ_ETH_CMD_EQSTART_F |
 					 FW_LEN16(cmd));
-	cmd.viid_pkd = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
-				   FW_EQ_ETH_CMD_VIID_V(pi->viid));
+	cmd.autoequiqe_to_viid = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F |
+					     FW_EQ_ETH_CMD_VIID_V(pi->viid));
 	cmd.fetchszm_to_iqid =
 		cpu_to_be32(FW_EQ_ETH_CMD_HOSTFCMODE_V(SGE_HOSTFCMODE_STPG) |
 			    FW_EQ_ETH_CMD_PCIECHN_V(pi->port_id) |
 			    FW_EQ_ETH_CMD_IQID_V(iqid));
 	cmd.dcaen_to_eqsize =
-		cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(SGE_FETCHBURSTMIN_64B) |
-			    FW_EQ_ETH_CMD_FBMAX_V(SGE_FETCHBURSTMAX_512B) |
+		cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5
+						  ? FETCHBURSTMIN_64B_X
+						  : FETCHBURSTMIN_64B_T6_X) |
+			    FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) |
 			    FW_EQ_ETH_CMD_CIDXFTHRESH_V(
-						SGE_CIDXFLUSHTHRESH_32) |
+						CIDXFLUSHTHRESH_32_X) |
 			    FW_EQ_ETH_CMD_EQSIZE_V(nentries));
 	cmd.eqaddr = cpu_to_be64(txq->q.phys_addr);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
index 5b8c08cf523f..84dff74ca9cd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/t4vf_hw.c
@@ -2005,8 +2005,10 @@ static void t4vf_handle_get_port_info(struct port_info *pi,
 	    fc != lc->fc || fec != lc->fec) {	/* something changed */
 		if (!link_ok && lc->link_ok) {
 			lc->link_down_rc = linkdnrc;
-			dev_warn(adapter->pdev_dev, "Port %d link down, reason: %s\n",
-				 pi->port_id, t4vf_link_down_rc_str(linkdnrc));
+			dev_warn_ratelimited(adapter->pdev_dev,
+					     "Port %d link down, reason: %s\n",
+					     pi->port_id,
+					     t4vf_link_down_rc_str(linkdnrc));
 		}
 		lc->link_ok = link_ok;
 		lc->speed = speed;
diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
index 74849be5f004..e2919005ead3 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
@@ -354,7 +354,10 @@ static struct cxgbi_ppm_pool *ppm_alloc_cpu_pool(unsigned int *total,
 		ppmax = max;
 
 	/* pool size must be multiple of unsigned long */
-	bmap = BITS_TO_LONGS(ppmax);
+	bmap = ppmax / BITS_PER_TYPE(unsigned long);
+	if (!bmap)
+		return NULL;
+
 	ppmax = (bmap * sizeof(unsigned long)) << 3;
 
 	alloc_sz = sizeof(*pools) + sizeof(unsigned long) * bmap;
@@ -402,6 +405,10 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 	if (reserve_factor) {
 		ppmax_pool = ppmax / reserve_factor;
 		pool = ppm_alloc_cpu_pool(&ppmax_pool, &pool_index_max);
+		if (!pool) {
+			ppmax_pool = 0;
+			reserve_factor = 0;
+		}
 
 		pr_debug("%s: ppmax %u, cpu total %u, per cpu %u.\n",
 			 ndev->name, ppmax, ppmax_pool, pool_index_max);
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index ec0b545197e2..e9a0213b08c4 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -23,7 +23,7 @@ config CS89x0
 	---help---
 	  Support for CS89x0 chipset based Ethernet cards. If you have a
 	  network (Ethernet) card of this type, say Y and read the file
-	  <file:Documentation/networking/cs89x0.txt>.
+	  <file:Documentation/networking/device_drivers/cirrus/cs89x0.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called cs89x0.
diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c
index 99038dfc7fbe..9900993b6aea 100644
--- a/drivers/net/ethernet/cisco/enic/enic_clsf.c
+++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c
@@ -32,7 +32,8 @@ int enic_addfltr_5t(struct enic *enic, struct flow_keys *keys, u16 rq)
 		break;
 	default:
 		return -EPROTONOSUPPORT;
-	};
+	}
+
 	data.type = FILTER_IPV4_5TUPLE;
 	data.u.ipv4.src_addr = ntohl(keys->addrs.v4addrs.src);
 	data.u.ipv4.dst_addr = ntohl(keys->addrs.v4addrs.dst);
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index f42f7a6e1559..ebd5c2cf1efe 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -241,7 +241,7 @@ static int enic_set_ringparam(struct net_device *netdev,
 	}
 	enic_init_vnic_resources(enic);
 	if (running) {
-		err = dev_open(netdev);
+		err = dev_open(netdev, NULL);
 		if (err)
 			goto err_out;
 	}
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 60641e202534..733d9172425b 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -119,7 +119,7 @@ static void enic_init_affinity_hint(struct enic *enic)
 
 	for (i = 0; i < enic->intr_count; i++) {
 		if (enic_is_err_intr(enic, i) || enic_is_notify_intr(enic, i) ||
-		    (enic->msix[i].affinity_mask &&
+		    (cpumask_available(enic->msix[i].affinity_mask) &&
 		     !cpumask_empty(enic->msix[i].affinity_mask)))
 			continue;
 		if (zalloc_cpumask_var(&enic->msix[i].affinity_mask,
@@ -148,7 +148,7 @@ static void enic_set_affinity_hint(struct enic *enic)
 	for (i = 0; i < enic->intr_count; i++) {
 		if (enic_is_err_intr(enic, i)		||
 		    enic_is_notify_intr(enic, i)	||
-		    !enic->msix[i].affinity_mask	||
+		    !cpumask_available(enic->msix[i].affinity_mask) ||
 		    cpumask_empty(enic->msix[i].affinity_mask))
 			continue;
 		err = irq_set_affinity_hint(enic->msix_entry[i].vector,
@@ -161,7 +161,7 @@ static void enic_set_affinity_hint(struct enic *enic)
 	for (i = 0; i < enic->wq_count; i++) {
 		int wq_intr = enic_msix_wq_intr(enic, i);
 
-		if (enic->msix[wq_intr].affinity_mask &&
+		if (cpumask_available(enic->msix[wq_intr].affinity_mask) &&
 		    !cpumask_empty(enic->msix[wq_intr].affinity_mask))
 			netif_set_xps_queue(enic->netdev,
 					    enic->msix[wq_intr].affinity_mask,
@@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq,
 		 * csum is correct or is zero.
 		 */
 		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) {
+		    tcp_udp_csum_ok && outer_csum_ok &&
+		    (ipv4_csum_ok || ipv6)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 			skb->csum_level = encap;
 		}
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 0a82fcf16d35..c2586f44c29d 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -395,6 +395,7 @@ static void dm9000_set_io(struct board_info *db, int byte_width)
 
 	case 3:
 		dev_dbg(db->dev, ": 3 byte IO, falling back to 16bit\n");
+		/* fall through */
 	case 2:
 		db->dumpblk = dm9000_dumpblk_16bit;
 		db->outblk  = dm9000_outblk_16bit;
diff --git a/drivers/net/ethernet/dec/tulip/Kconfig b/drivers/net/ethernet/dec/tulip/Kconfig
index 1003201b5d80..264e9b413e94 100644
--- a/drivers/net/ethernet/dec/tulip/Kconfig
+++ b/drivers/net/ethernet/dec/tulip/Kconfig
@@ -113,7 +113,7 @@ config DE4X5
 	  These include the DE425, DE434, DE435, DE450 and DE500 models.  If
 	  you have a network card of this type, say Y.  More specific
 	  information is contained in
-	  <file:Documentation/networking/de4x5.txt>.
+	  <file:Documentation/networking/device_drivers/dec/de4x5.txt>.
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called de4x5.
@@ -137,7 +137,7 @@ config DM9102
 	  This driver is for DM9102(A)/DM9132/DM9801 compatible PCI cards from
 	  Davicom (<http://www.davicom.com.tw/>).  If you have such a network
 	  (Ethernet) card, say Y.  Some information is contained in the file
-	  <file:Documentation/networking/dmfe.txt>.
+	  <file:Documentation/networking/device_drivers/dec/dmfe.txt>.
 
 	  To compile this driver as a module, choose M here. The module will
 	  be called dmfe.
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 13430f75496c..f1a2da15dd0a 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -585,7 +585,7 @@ static void de_tx (struct de_private *de)
 				netif_dbg(de, tx_done, de->dev,
 					  "tx done, slot %d\n", tx_tail);
 			}
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 		}
 
 next:
diff --git a/drivers/net/ethernet/dec/tulip/eeprom.c b/drivers/net/ethernet/dec/tulip/eeprom.c
index 1812f4916917..ba0a69b363f8 100644
--- a/drivers/net/ethernet/dec/tulip/eeprom.c
+++ b/drivers/net/ethernet/dec/tulip/eeprom.c
@@ -224,9 +224,7 @@ subsequent_board:
 		        return;
 		}
 
-		mtable = kmalloc(sizeof(struct mediatable) +
-				 count * sizeof(struct medialeaf),
-				 GFP_KERNEL);
+		mtable = kmalloc(struct_size(mtable, mleaf, count), GFP_KERNEL);
 		if (mtable == NULL)
 			return;				/* Horrible, impossible failure. */
 		last_mediatable = tp->mtable = mtable;
diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index f0536b16b3c3..cfcdfee718b0 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -843,9 +843,9 @@ rio_free_tx (struct net_device *dev, int irq)
 				  desc_to_dma(&np->tx_ring[entry]),
 				  skb->len, PCI_DMA_TODEVICE);
 		if (irq)
-			dev_kfree_skb_irq (skb);
+			dev_consume_skb_irq(skb);
 		else
-			dev_kfree_skb (skb);
+			dev_kfree_skb(skb);
 
 		np->tx_skbuff[entry] = NULL;
 		entry = (entry + 1) % TX_RING_SIZE;
@@ -1881,7 +1881,7 @@ Compile command:
 
 gcc -D__KERNEL__ -DMODULE -I/usr/src/linux/include -Wall -Wstrict-prototypes -O2 -c dl2k.c
 
-Read Documentation/networking/dl2k.txt for details.
+Read Documentation/networking/device_drivers/dlink/dl2k.txt for details.
 
 */
 
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index 1a27176381fb..4a37a69764ce 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -1193,7 +1193,6 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 	int handled = 0;
 	int i;
 
-
 	do {
 		int intr_status = ioread16(ioaddr + IntrStatus);
 		iowrite16(intr_status, ioaddr + IntrStatus);
@@ -1286,7 +1285,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 				dma_unmap_single(&np->pci_dev->dev,
 					le32_to_cpu(np->tx_ring[entry].frag[0].addr),
 					skb->len, DMA_TO_DEVICE);
-				dev_kfree_skb_irq (np->tx_skbuff[entry]);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
 				np->tx_skbuff[entry] = NULL;
 				np->tx_ring[entry].frag[0].addr = 0;
 				np->tx_ring[entry].frag[0].length = 0;
@@ -1305,7 +1304,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 				dma_unmap_single(&np->pci_dev->dev,
 					le32_to_cpu(np->tx_ring[entry].frag[0].addr),
 					skb->len, DMA_TO_DEVICE);
-				dev_kfree_skb_irq (np->tx_skbuff[entry]);
+				dev_consume_skb_irq(np->tx_skbuff[entry]);
 				np->tx_skbuff[entry] = NULL;
 				np->tx_ring[entry].frag[0].addr = 0;
 				np->tx_ring[entry].frag[0].length = 0;
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 1e9d882c04ef..59a7f0b99069 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -1808,9 +1808,9 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 	total_size = buf_len;
 
 	get_fat_cmd.size = sizeof(struct be_cmd_req_get_fat) + 60*1024;
-	get_fat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-					     get_fat_cmd.size,
-					     &get_fat_cmd.dma, GFP_ATOMIC);
+	get_fat_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+					    get_fat_cmd.size,
+					    &get_fat_cmd.dma, GFP_ATOMIC);
 	if (!get_fat_cmd.va)
 		return -ENOMEM;
 
@@ -2302,8 +2302,8 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -EINVAL;
 
 	cmd.size = sizeof(struct be_cmd_resp_port_type);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_ATOMIC);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failed\n");
 		return -ENOMEM;
@@ -3066,8 +3066,8 @@ int lancer_fw_download(struct be_adapter *adapter,
 
 	flash_cmd.size = sizeof(struct lancer_cmd_req_write_object)
 				+ LANCER_FW_DOWNLOAD_CHUNK;
-	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size,
-					   &flash_cmd.dma, GFP_KERNEL);
+	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
+					  GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -3184,8 +3184,8 @@ int be_fw_download(struct be_adapter *adapter, const struct firmware *fw)
 	}
 
 	flash_cmd.size = sizeof(struct be_cmd_write_flashrom);
-	flash_cmd.va = dma_zalloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
-					   GFP_KERNEL);
+	flash_cmd.va = dma_alloc_coherent(dev, flash_cmd.size, &flash_cmd.dma,
+					  GFP_KERNEL);
 	if (!flash_cmd.va)
 		return -ENOMEM;
 
@@ -3435,8 +3435,8 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 		goto err;
 	}
 	cmd.size = sizeof(struct be_cmd_req_get_phy_info);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_ATOMIC);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -3522,9 +3522,9 @@ int be_cmd_get_cntl_attributes(struct be_adapter *adapter)
 
 	memset(&attribs_cmd, 0, sizeof(struct be_dma_mem));
 	attribs_cmd.size = sizeof(struct be_cmd_resp_cntl_attribs);
-	attribs_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-					     attribs_cmd.size,
-					     &attribs_cmd.dma, GFP_ATOMIC);
+	attribs_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+					    attribs_cmd.size,
+					    &attribs_cmd.dma, GFP_ATOMIC);
 	if (!attribs_cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -3699,10 +3699,10 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 
 	memset(&get_mac_list_cmd, 0, sizeof(struct be_dma_mem));
 	get_mac_list_cmd.size = sizeof(struct be_cmd_resp_get_mac_list);
-	get_mac_list_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-						  get_mac_list_cmd.size,
-						  &get_mac_list_cmd.dma,
-						  GFP_ATOMIC);
+	get_mac_list_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+						 get_mac_list_cmd.size,
+						 &get_mac_list_cmd.dma,
+						 GFP_ATOMIC);
 
 	if (!get_mac_list_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -3829,8 +3829,8 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_KERNEL);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -4035,8 +4035,8 @@ int be_cmd_get_acpi_wol_cap(struct be_adapter *adapter)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_acpi_wol_magic_config_v1);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_ATOMIC);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory allocation failure\n");
 		status = -ENOMEM;
@@ -4089,9 +4089,9 @@ int be_cmd_set_fw_log_level(struct be_adapter *adapter, u32 level)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-					    extfat_cmd.size, &extfat_cmd.dma,
-					    GFP_ATOMIC);
+	extfat_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+					   extfat_cmd.size, &extfat_cmd.dma,
+					   GFP_ATOMIC);
 	if (!extfat_cmd.va)
 		return -ENOMEM;
 
@@ -4127,9 +4127,9 @@ int be_cmd_get_fw_log_level(struct be_adapter *adapter)
 
 	memset(&extfat_cmd, 0, sizeof(struct be_dma_mem));
 	extfat_cmd.size = sizeof(struct be_cmd_resp_get_ext_fat_caps);
-	extfat_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-					    extfat_cmd.size, &extfat_cmd.dma,
-					    GFP_ATOMIC);
+	extfat_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+					   extfat_cmd.size, &extfat_cmd.dma,
+					   GFP_ATOMIC);
 
 	if (!extfat_cmd.va) {
 		dev_err(&adapter->pdev->dev, "%s: Memory allocation failure\n",
@@ -4354,8 +4354,8 @@ int be_cmd_get_func_config(struct be_adapter *adapter, struct be_resources *res)
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_func_config);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_ATOMIC);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_ATOMIC);
 	if (!cmd.va) {
 		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
 		status = -ENOMEM;
@@ -4452,8 +4452,8 @@ int be_cmd_get_profile_config(struct be_adapter *adapter,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_resp_get_profile_config);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_ATOMIC);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -4539,8 +4539,8 @@ static int be_cmd_set_profile_config(struct be_adapter *adapter, void *desc,
 
 	memset(&cmd, 0, sizeof(struct be_dma_mem));
 	cmd.size = sizeof(struct be_cmd_req_set_profile_config);
-	cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
-				     GFP_ATOMIC);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size, &cmd.dma,
+				    GFP_ATOMIC);
 	if (!cmd.va)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 3f6749fc889f..4c218341c51b 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -274,8 +274,8 @@ static int lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
 	int status = 0;
 
 	read_cmd.size = LANCER_READ_FILE_CHUNK;
-	read_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev, read_cmd.size,
-					  &read_cmd.dma, GFP_ATOMIC);
+	read_cmd.va = dma_alloc_coherent(&adapter->pdev->dev, read_cmd.size,
+					 &read_cmd.dma, GFP_ATOMIC);
 
 	if (!read_cmd.va) {
 		dev_err(&adapter->pdev->dev,
@@ -815,7 +815,7 @@ static int be_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	}
 
 	cmd.size = sizeof(struct be_cmd_req_acpi_wol_magic_config);
-	cmd.va = dma_zalloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL);
+	cmd.va = dma_alloc_coherent(dev, cmd.size, &cmd.dma, GFP_KERNEL);
 	if (!cmd.va)
 		return -ENOMEM;
 
@@ -851,9 +851,9 @@ static int be_test_ddr_dma(struct be_adapter *adapter)
 	};
 
 	ddrdma_cmd.size = sizeof(struct be_cmd_req_ddrdma_test);
-	ddrdma_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-					    ddrdma_cmd.size, &ddrdma_cmd.dma,
-					    GFP_KERNEL);
+	ddrdma_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+					   ddrdma_cmd.size, &ddrdma_cmd.dma,
+					   GFP_KERNEL);
 	if (!ddrdma_cmd.va)
 		return -ENOMEM;
 
@@ -1014,9 +1014,9 @@ static int be_read_eeprom(struct net_device *netdev,
 
 	memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
 	eeprom_cmd.size = sizeof(struct be_cmd_req_seeprom_read);
-	eeprom_cmd.va = dma_zalloc_coherent(&adapter->pdev->dev,
-					    eeprom_cmd.size, &eeprom_cmd.dma,
-					    GFP_KERNEL);
+	eeprom_cmd.va = dma_alloc_coherent(&adapter->pdev->dev,
+					   eeprom_cmd.size, &eeprom_cmd.dma,
+					   GFP_KERNEL);
 
 	if (!eeprom_cmd.va)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index c5ad7a4f4d83..3c7c04406a2b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -167,8 +167,8 @@ static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q,
 	q->len = len;
 	q->entry_size = entry_size;
 	mem->size = len * entry_size;
-	mem->va = dma_zalloc_coherent(&adapter->pdev->dev, mem->size, &mem->dma,
-				      GFP_KERNEL);
+	mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size,
+				     &mem->dma, GFP_KERNEL);
 	if (!mem->va)
 		return -ENOMEM;
 	return 0;
@@ -796,7 +796,7 @@ static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
 	u16 vlan_tag;
 
 	vlan_tag = skb_vlan_tag_get(skb);
-	vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	vlan_prio = skb_vlan_tag_get_prio(skb);
 	/* If vlan priority provided by OS is NOT in available bmap */
 	if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
 		vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
@@ -1049,30 +1049,35 @@ static struct sk_buff *be_insert_vlan_in_pkt(struct be_adapter *adapter,
 					     struct be_wrb_params
 					     *wrb_params)
 {
+	bool insert_vlan = false;
 	u16 vlan_tag = 0;
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
 		return skb;
 
-	if (skb_vlan_tag_present(skb))
+	if (skb_vlan_tag_present(skb)) {
 		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
+		insert_vlan = true;
+	}
 
 	if (qnq_async_evt_rcvd(adapter) && adapter->pvid) {
-		if (!vlan_tag)
+		if (!insert_vlan) {
 			vlan_tag = adapter->pvid;
+			insert_vlan = true;
+		}
 		/* f/w workaround to set skip_hw_vlan = 1, informs the F/W to
 		 * skip VLAN insertion
 		 */
 		BE_WRB_F_SET(wrb_params->features, VLAN_SKIP_HW, 1);
 	}
 
-	if (vlan_tag) {
+	if (insert_vlan) {
 		skb = vlan_insert_tag_set_proto(skb, htons(ETH_P_8021Q),
 						vlan_tag);
 		if (unlikely(!skb))
 			return skb;
-		skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(skb);
 	}
 
 	/* Insert the outer VLAN, if any */
@@ -1265,10 +1270,6 @@ static void be_xmit_flush(struct be_adapter *adapter, struct be_tx_obj *txo)
 #define is_arp_allowed_on_bmc(adapter, skb)	\
 	(is_arp(skb) && is_arp_filt_enabled(adapter))
 
-#define is_broadcast_packet(eh, adapter)	\
-		(is_multicast_ether_addr(eh->h_dest) && \
-		!compare_ether_addr(eh->h_dest, adapter->netdev->broadcast))
-
 #define is_arp(skb)	(skb->protocol == htons(ETH_P_ARP))
 
 #define is_arp_filt_enabled(adapter)	\
@@ -4950,7 +4951,7 @@ fw_exit:
 }
 
 static int be_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-				 u16 flags)
+				 u16 flags, struct netlink_ext_ack *extack)
 {
 	struct be_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
@@ -5761,9 +5762,9 @@ static int be_drv_init(struct be_adapter *adapter)
 	int status = 0;
 
 	mbox_mem_alloc->size = sizeof(struct be_mcc_mailbox) + 16;
-	mbox_mem_alloc->va = dma_zalloc_coherent(dev, mbox_mem_alloc->size,
-						 &mbox_mem_alloc->dma,
-						 GFP_KERNEL);
+	mbox_mem_alloc->va = dma_alloc_coherent(dev, mbox_mem_alloc->size,
+						&mbox_mem_alloc->dma,
+						GFP_KERNEL);
 	if (!mbox_mem_alloc->va)
 		return -ENOMEM;
 
@@ -5772,8 +5773,8 @@ static int be_drv_init(struct be_adapter *adapter)
 	mbox_mem_align->dma = PTR_ALIGN(mbox_mem_alloc->dma, 16);
 
 	rx_filter->size = sizeof(struct be_cmd_req_rx_filter);
-	rx_filter->va = dma_zalloc_coherent(dev, rx_filter->size,
-					    &rx_filter->dma, GFP_KERNEL);
+	rx_filter->va = dma_alloc_coherent(dev, rx_filter->size,
+					   &rx_filter->dma, GFP_KERNEL);
 	if (!rx_filter->va) {
 		status = -ENOMEM;
 		goto free_mbox;
@@ -5787,8 +5788,8 @@ static int be_drv_init(struct be_adapter *adapter)
 		stats_cmd->size = sizeof(struct be_cmd_req_get_stats_v1);
 	else
 		stats_cmd->size = sizeof(struct be_cmd_req_get_stats_v2);
-	stats_cmd->va = dma_zalloc_coherent(dev, stats_cmd->size,
-					    &stats_cmd->dma, GFP_KERNEL);
+	stats_cmd->va = dma_alloc_coherent(dev, stats_cmd->size,
+					   &stats_cmd->dma, GFP_KERNEL);
 	if (!stats_cmd->va) {
 		status = -ENOMEM;
 		goto free_rx_filter;
diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
index 4d673225ed3e..b17b79e612a3 100644
--- a/drivers/net/ethernet/faraday/ftgmac100.c
+++ b/drivers/net/ethernet/faraday/ftgmac100.c
@@ -935,16 +935,14 @@ static int ftgmac100_alloc_rings(struct ftgmac100 *priv)
 		return -ENOMEM;
 
 	/* Allocate descriptors */
-	priv->rxdes = dma_zalloc_coherent(priv->dev,
-					  MAX_RX_QUEUE_ENTRIES *
-					  sizeof(struct ftgmac100_rxdes),
-					  &priv->rxdes_dma, GFP_KERNEL);
+	priv->rxdes = dma_alloc_coherent(priv->dev,
+					 MAX_RX_QUEUE_ENTRIES * sizeof(struct ftgmac100_rxdes),
+					 &priv->rxdes_dma, GFP_KERNEL);
 	if (!priv->rxdes)
 		return -ENOMEM;
-	priv->txdes = dma_zalloc_coherent(priv->dev,
-					  MAX_TX_QUEUE_ENTRIES *
-					  sizeof(struct ftgmac100_txdes),
-					  &priv->txdes_dma, GFP_KERNEL);
+	priv->txdes = dma_alloc_coherent(priv->dev,
+					 MAX_TX_QUEUE_ENTRIES * sizeof(struct ftgmac100_txdes),
+					 &priv->txdes_dma, GFP_KERNEL);
 	if (!priv->txdes)
 		return -ENOMEM;
 
@@ -1639,7 +1637,7 @@ static int ftgmac100_setup_mdio(struct net_device *netdev)
 		reg = ioread32(priv->base + FTGMAC100_OFFSET_REVR);
 		reg &= ~FTGMAC100_REVR_NEW_MDIO_INTERFACE;
 		iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR);
-	};
+	}
 
 	/* Get PHY mode from device-tree */
 	if (np) {
diff --git a/drivers/net/ethernet/faraday/ftmac100.c b/drivers/net/ethernet/faraday/ftmac100.c
index 084f24daf2b5..2a0e820526dc 100644
--- a/drivers/net/ethernet/faraday/ftmac100.c
+++ b/drivers/net/ethernet/faraday/ftmac100.c
@@ -734,10 +734,9 @@ static int ftmac100_alloc_buffers(struct ftmac100 *priv)
 {
 	int i;
 
-	priv->descs = dma_zalloc_coherent(priv->dev,
-					  sizeof(struct ftmac100_descs),
-					  &priv->descs_dma_addr,
-					  GFP_KERNEL);
+	priv->descs = dma_alloc_coherent(priv->dev,
+					 sizeof(struct ftmac100_descs),
+					 &priv->descs_dma_addr, GFP_KERNEL);
 	if (!priv->descs)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index ae55da60ed0e..c24fd56a2c71 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -1531,7 +1531,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance)
 			/* Free the original skb. */
 			pci_unmap_single(np->pci_dev, np->cur_tx->buffer,
 				np->cur_tx->skbuff->len, PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq(np->cur_tx->skbuff);
+			dev_consume_skb_irq(np->cur_tx->skbuff);
 			np->cur_tx->skbuff = NULL;
 			--np->really_tx_count;
 			if (np->cur_tx->control & TXLD) {
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index d3a62bc1f1c6..71793e03c3c8 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -97,5 +97,6 @@ config GIANFAR
 
 source "drivers/net/ethernet/freescale/dpaa/Kconfig"
 source "drivers/net/ethernet/freescale/dpaa2/Kconfig"
+source "drivers/net/ethernet/freescale/enetc/Kconfig"
 
 endif # NET_VENDOR_FREESCALE
diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile
index 3b4ff08e3841..6a93293d31e0 100644
--- a/drivers/net/ethernet/freescale/Makefile
+++ b/drivers/net/ethernet/freescale/Makefile
@@ -23,3 +23,6 @@ obj-$(CONFIG_FSL_FMAN) += fman/
 obj-$(CONFIG_FSL_DPAA_ETH) += dpaa/
 
 obj-$(CONFIG_FSL_DPAA2_ETH) += dpaa2/
+
+obj-$(CONFIG_FSL_ENETC) += enetc/
+obj-$(CONFIG_FSL_ENETC_VF) += enetc/
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 6e0f47f2c8a3..dfebc30c4841 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -51,9 +51,9 @@
 #include <linux/percpu.h>
 #include <linux/dma-mapping.h>
 #include <linux/sort.h>
+#include <linux/phy_fixed.h>
 #include <soc/fsl/bman.h>
 #include <soc/fsl/qman.h>
-
 #include "fman.h"
 #include "fman_port.h"
 #include "mac.h"
@@ -2051,6 +2051,7 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	bool nonlinear = skb_is_nonlinear(skb);
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa_percpu_priv *percpu_priv;
+	struct netdev_queue *txq;
 	struct dpaa_priv *priv;
 	struct qm_fd fd;
 	int offset = 0;
@@ -2100,6 +2101,11 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0))
 		goto skb_to_fd_failed;
 
+	txq = netdev_get_tx_queue(net_dev, queue_mapping);
+
+	/* LLTX requires to do our own update of trans_start */
+	txq->trans_start = jiffies;
+
 	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
 		fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD);
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
@@ -2475,6 +2481,7 @@ static void dpaa_adjust_link(struct net_device *net_dev)
 
 static int dpaa_phy_init(struct net_device *net_dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct mac_device *mac_dev;
 	struct phy_device *phy_dev;
 	struct dpaa_priv *priv;
@@ -2491,7 +2498,9 @@ static int dpaa_phy_init(struct net_device *net_dev)
 	}
 
 	/* Remove any features not supported by the controller */
-	phy_dev->supported &= mac_dev->if_support;
+	ethtool_convert_legacy_u32_to_link_mode(mask, mac_dev->if_support);
+	linkmode_and(phy_dev->supported, phy_dev->supported, mask);
+
 	phy_support_asym_pause(phy_dev);
 
 	mac_dev->phy_dev = phy_dev;
@@ -2613,6 +2622,7 @@ static const struct net_device_ops dpaa_ops = {
 	.ndo_stop = dpaa_eth_stop,
 	.ndo_tx_timeout = dpaa_tx_timeout,
 	.ndo_get_stats64 = dpaa_get_stats64,
+	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = dpaa_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = dpaa_set_rx_mode,
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 13d6e2272ece..bdee441bc3b7 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -501,7 +501,7 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 	struct device_node *mac_node = dev->of_node;
 	struct device_node *fman_node = NULL, *ptp_node = NULL;
 	struct platform_device *ptp_dev = NULL;
-	struct qoriq_ptp *ptp = NULL;
+	struct ptp_qoriq *ptp = NULL;
 
 	info->phc_index = -1;
 
@@ -529,6 +529,75 @@ static int dpaa_get_ts_info(struct net_device *net_dev,
 	return 0;
 }
 
+static int dpaa_get_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *c)
+{
+	struct qman_portal *portal;
+	u32 period;
+	u8 thresh;
+
+	portal = qman_get_affine_portal(smp_processor_id());
+	qman_portal_get_iperiod(portal, &period);
+	qman_dqrr_get_ithresh(portal, &thresh);
+
+	c->rx_coalesce_usecs = period;
+	c->rx_max_coalesced_frames = thresh;
+	c->use_adaptive_rx_coalesce = false;
+
+	return 0;
+}
+
+static int dpaa_set_coalesce(struct net_device *dev,
+			     struct ethtool_coalesce *c)
+{
+	const cpumask_t *cpus = qman_affine_cpus();
+	bool needs_revert[NR_CPUS] = {false};
+	struct qman_portal *portal;
+	u32 period, prev_period;
+	u8 thresh, prev_thresh;
+	int cpu, res;
+
+	if (c->use_adaptive_rx_coalesce)
+		return -EINVAL;
+
+	period = c->rx_coalesce_usecs;
+	thresh = c->rx_max_coalesced_frames;
+
+	/* save previous values */
+	portal = qman_get_affine_portal(smp_processor_id());
+	qman_portal_get_iperiod(portal, &prev_period);
+	qman_dqrr_get_ithresh(portal, &prev_thresh);
+
+	/* set new values */
+	for_each_cpu(cpu, cpus) {
+		portal = qman_get_affine_portal(cpu);
+		res = qman_portal_set_iperiod(portal, period);
+		if (res)
+			goto revert_values;
+		res = qman_dqrr_set_ithresh(portal, thresh);
+		if (res) {
+			qman_portal_set_iperiod(portal, prev_period);
+			goto revert_values;
+		}
+		needs_revert[cpu] = true;
+	}
+
+	return 0;
+
+revert_values:
+	/* restore previous values */
+	for_each_cpu(cpu, cpus) {
+		if (!needs_revert[cpu])
+			continue;
+		portal = qman_get_affine_portal(cpu);
+		/* previous values will not fail, ignore return value */
+		qman_portal_set_iperiod(portal, prev_period);
+		qman_dqrr_set_ithresh(portal, prev_thresh);
+	}
+
+	return res;
+}
+
 const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_drvinfo = dpaa_get_drvinfo,
 	.get_msglevel = dpaa_get_msglevel,
@@ -545,4 +614,6 @@ const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_rxnfc = dpaa_get_rxnfc,
 	.set_rxnfc = dpaa_set_rxnfc,
 	.get_ts_info = dpaa_get_ts_info,
+	.get_coalesce = dpaa_get_coalesce,
+	.set_coalesce = dpaa_set_coalesce,
 };
diff --git a/drivers/net/ethernet/freescale/dpaa2/Kconfig b/drivers/net/ethernet/freescale/dpaa2/Kconfig
index 809a155eb193..f6d244c663fd 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Kconfig
+++ b/drivers/net/ethernet/freescale/dpaa2/Kconfig
@@ -9,8 +9,9 @@ config FSL_DPAA2_ETH
 
 config FSL_DPAA2_PTP_CLOCK
 	tristate "Freescale DPAA2 PTP Clock"
-	depends on FSL_DPAA2_ETH && POSIX_TIMERS
-	select PTP_1588_CLOCK
+	depends on FSL_DPAA2_ETH
+	imply PTP_1588_CLOCK
+	default y
 	help
 	  This driver adds support for using the DPAA2 1588 timer module
 	  as a PTP clock.
diff --git a/drivers/net/ethernet/freescale/dpaa2/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile
index 2f424e0a8225..d1e78cdd512f 100644
--- a/drivers/net/ethernet/freescale/dpaa2/Makefile
+++ b/drivers/net/ethernet/freescale/dpaa2/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_FSL_DPAA2_ETH)		+= fsl-dpaa2-eth.o
 obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK)	+= fsl-dpaa2-ptp.o
 
 fsl-dpaa2-eth-objs	:= dpaa2-eth.o dpaa2-ethtool.o dpni.o
+fsl-dpaa2-eth-${CONFIG_DEBUG_FS} += dpaa2-eth-debugfs.o
 fsl-dpaa2-ptp-objs	:= dpaa2-ptp.o dprtc.o
 
 # Needed by the tracing framework
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
new file mode 100644
index 000000000000..a027f4a9d0cc
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c
@@ -0,0 +1,237 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2015 Freescale Semiconductor Inc.
+ * Copyright 2018-2019 NXP
+ */
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include "dpaa2-eth.h"
+#include "dpaa2-eth-debugfs.h"
+
+#define DPAA2_ETH_DBG_ROOT "dpaa2-eth"
+
+static struct dentry *dpaa2_dbg_root;
+
+static int dpaa2_dbg_cpu_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	struct rtnl_link_stats64 *stats;
+	struct dpaa2_eth_drv_stats *extras;
+	int i;
+
+	seq_printf(file, "Per-CPU stats for %s\n", priv->net_dev->name);
+	seq_printf(file, "%s%16s%16s%16s%16s%16s%16s%16s%16s%16s\n",
+		   "CPU", "Rx", "Rx Err", "Rx SG", "Tx", "Tx Err", "Tx conf",
+		   "Tx SG", "Tx realloc", "Enq busy");
+
+	for_each_online_cpu(i) {
+		stats = per_cpu_ptr(priv->percpu_stats, i);
+		extras = per_cpu_ptr(priv->percpu_extras, i);
+		seq_printf(file, "%3d%16llu%16llu%16llu%16llu%16llu%16llu%16llu%16llu%16llu\n",
+			   i,
+			   stats->rx_packets,
+			   stats->rx_errors,
+			   extras->rx_sg_frames,
+			   stats->tx_packets,
+			   stats->tx_errors,
+			   extras->tx_conf_frames,
+			   extras->tx_sg_frames,
+			   extras->tx_reallocs,
+			   extras->tx_portal_busy);
+	}
+
+	return 0;
+}
+
+static int dpaa2_dbg_cpu_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)inode->i_private;
+
+	err = single_open(file, dpaa2_dbg_cpu_show, priv);
+	if (err < 0)
+		netdev_err(priv->net_dev, "single_open() failed\n");
+
+	return err;
+}
+
+static const struct file_operations dpaa2_dbg_cpu_ops = {
+	.open = dpaa2_dbg_cpu_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static char *fq_type_to_str(struct dpaa2_eth_fq *fq)
+{
+	switch (fq->type) {
+	case DPAA2_RX_FQ:
+		return "Rx";
+	case DPAA2_TX_CONF_FQ:
+		return "Tx conf";
+	default:
+		return "N/A";
+	}
+}
+
+static int dpaa2_dbg_fqs_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	struct dpaa2_eth_fq *fq;
+	u32 fcnt, bcnt;
+	int i, err;
+
+	seq_printf(file, "FQ stats for %s:\n", priv->net_dev->name);
+	seq_printf(file, "%s%16s%16s%16s%16s\n",
+		   "VFQID", "CPU", "Type", "Frames", "Pending frames");
+
+	for (i = 0; i <  priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+		err = dpaa2_io_query_fq_count(NULL, fq->fqid, &fcnt, &bcnt);
+		if (err)
+			fcnt = 0;
+
+		seq_printf(file, "%5d%16d%16s%16llu%16u\n",
+			   fq->fqid,
+			   fq->target_cpu,
+			   fq_type_to_str(fq),
+			   fq->stats.frames,
+			   fcnt);
+	}
+
+	return 0;
+}
+
+static int dpaa2_dbg_fqs_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)inode->i_private;
+
+	err = single_open(file, dpaa2_dbg_fqs_show, priv);
+	if (err < 0)
+		netdev_err(priv->net_dev, "single_open() failed\n");
+
+	return err;
+}
+
+static const struct file_operations dpaa2_dbg_fq_ops = {
+	.open = dpaa2_dbg_fqs_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int dpaa2_dbg_ch_show(struct seq_file *file, void *offset)
+{
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)file->private;
+	struct dpaa2_eth_channel *ch;
+	int i;
+
+	seq_printf(file, "Channel stats for %s:\n", priv->net_dev->name);
+	seq_printf(file, "%s%16s%16s%16s%16s\n",
+		   "CHID", "CPU", "Deq busy", "CDANs", "Buf count");
+
+	for (i = 0; i < priv->num_channels; i++) {
+		ch = priv->channel[i];
+		seq_printf(file, "%4d%16d%16llu%16llu%16d\n",
+			   ch->ch_id,
+			   ch->nctx.desired_cpu,
+			   ch->stats.dequeue_portal_busy,
+			   ch->stats.cdan,
+			   ch->buf_count);
+	}
+
+	return 0;
+}
+
+static int dpaa2_dbg_ch_open(struct inode *inode, struct file *file)
+{
+	int err;
+	struct dpaa2_eth_priv *priv = (struct dpaa2_eth_priv *)inode->i_private;
+
+	err = single_open(file, dpaa2_dbg_ch_show, priv);
+	if (err < 0)
+		netdev_err(priv->net_dev, "single_open() failed\n");
+
+	return err;
+}
+
+static const struct file_operations dpaa2_dbg_ch_ops = {
+	.open = dpaa2_dbg_ch_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void dpaa2_dbg_add(struct dpaa2_eth_priv *priv)
+{
+	if (!dpaa2_dbg_root)
+		return;
+
+	/* Create a directory for the interface */
+	priv->dbg.dir = debugfs_create_dir(priv->net_dev->name,
+					   dpaa2_dbg_root);
+	if (!priv->dbg.dir) {
+		netdev_err(priv->net_dev, "debugfs_create_dir() failed\n");
+		return;
+	}
+
+	/* per-cpu stats file */
+	priv->dbg.cpu_stats = debugfs_create_file("cpu_stats", 0444,
+						  priv->dbg.dir, priv,
+						  &dpaa2_dbg_cpu_ops);
+	if (!priv->dbg.cpu_stats) {
+		netdev_err(priv->net_dev, "debugfs_create_file() failed\n");
+		goto err_cpu_stats;
+	}
+
+	/* per-fq stats file */
+	priv->dbg.fq_stats = debugfs_create_file("fq_stats", 0444,
+						 priv->dbg.dir, priv,
+						 &dpaa2_dbg_fq_ops);
+	if (!priv->dbg.fq_stats) {
+		netdev_err(priv->net_dev, "debugfs_create_file() failed\n");
+		goto err_fq_stats;
+	}
+
+	/* per-fq stats file */
+	priv->dbg.ch_stats = debugfs_create_file("ch_stats", 0444,
+						 priv->dbg.dir, priv,
+						 &dpaa2_dbg_ch_ops);
+	if (!priv->dbg.fq_stats) {
+		netdev_err(priv->net_dev, "debugfs_create_file() failed\n");
+		goto err_ch_stats;
+	}
+
+	return;
+
+err_ch_stats:
+	debugfs_remove(priv->dbg.fq_stats);
+err_fq_stats:
+	debugfs_remove(priv->dbg.cpu_stats);
+err_cpu_stats:
+	debugfs_remove(priv->dbg.dir);
+}
+
+void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv)
+{
+	debugfs_remove(priv->dbg.fq_stats);
+	debugfs_remove(priv->dbg.ch_stats);
+	debugfs_remove(priv->dbg.cpu_stats);
+	debugfs_remove(priv->dbg.dir);
+}
+
+void dpaa2_eth_dbg_init(void)
+{
+	dpaa2_dbg_root = debugfs_create_dir(DPAA2_ETH_DBG_ROOT, NULL);
+	if (!dpaa2_dbg_root) {
+		pr_err("DPAA2-ETH: debugfs create failed\n");
+		return;
+	}
+
+	pr_debug("DPAA2-ETH: debugfs created\n");
+}
+
+void dpaa2_eth_dbg_exit(void)
+{
+	debugfs_remove(dpaa2_dbg_root);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h
new file mode 100644
index 000000000000..4f63de997a26
--- /dev/null
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2015 Freescale Semiconductor Inc.
+ * Copyright 2018-2019 NXP
+ */
+#ifndef DPAA2_ETH_DEBUGFS_H
+#define DPAA2_ETH_DEBUGFS_H
+
+#include <linux/dcache.h>
+
+struct dpaa2_eth_priv;
+
+struct dpaa2_debugfs {
+	struct dentry *dir;
+	struct dentry *fq_stats;
+	struct dentry *ch_stats;
+	struct dentry *cpu_stats;
+};
+
+#ifdef CONFIG_DEBUG_FS
+void dpaa2_eth_dbg_init(void);
+void dpaa2_eth_dbg_exit(void);
+void dpaa2_dbg_add(struct dpaa2_eth_priv *priv);
+void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv);
+#else
+static inline void dpaa2_eth_dbg_init(void) {}
+static inline void dpaa2_eth_dbg_exit(void) {}
+static inline void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) {}
+static inline void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv) {}
+#endif /* CONFIG_DEBUG_FS */
+
+#endif /* DPAA2_ETH_DEBUGFS_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
index 88f7acce38dc..dc339dc1adb2 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c
@@ -13,7 +13,8 @@
 #include <linux/iommu.h>
 #include <linux/net_tstamp.h>
 #include <linux/fsl/mc.h>
-
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <net/sock.h>
 
 #include "dpaa2-eth.h"
@@ -85,16 +86,16 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv,
 	for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) {
 		addr = dpaa2_sg_get_addr(&sgt[i]);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-		dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 
-		skb_free_frag(sg_vaddr);
+		free_pages((unsigned long)sg_vaddr, 0);
 		if (dpaa2_sg_is_final(&sgt[i]))
 			break;
 	}
 
 free_buf:
-	skb_free_frag(vaddr);
+	free_pages((unsigned long)vaddr, 0);
 }
 
 /* Build a linear skb based on a single-buffer frame descriptor */
@@ -108,7 +109,7 @@ static struct sk_buff *build_linear_skb(struct dpaa2_eth_channel *ch,
 
 	ch->buf_count--;
 
-	skb = build_skb(fd_vaddr, DPAA2_ETH_SKB_SIZE);
+	skb = build_skb(fd_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -143,19 +144,19 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 		/* Get the address and length from the S/G entry */
 		sg_addr = dpaa2_sg_get_addr(sge);
 		sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr);
-		dma_unmap_single(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+		dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 
 		sg_length = dpaa2_sg_get_len(sge);
 
 		if (i == 0) {
 			/* We build the skb around the first data buffer */
-			skb = build_skb(sg_vaddr, DPAA2_ETH_SKB_SIZE);
+			skb = build_skb(sg_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE);
 			if (unlikely(!skb)) {
 				/* Free the first SG entry now, since we already
 				 * unmapped it and obtained the virtual address
 				 */
-				skb_free_frag(sg_vaddr);
+				free_pages((unsigned long)sg_vaddr, 0);
 
 				/* We still need to subtract the buffers used
 				 * by this FD from our software counter
@@ -199,12 +200,159 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv,
 	return skb;
 }
 
+/* Free buffers acquired from the buffer pool or which were meant to
+ * be released in the pool
+ */
+static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
+{
+	struct device *dev = priv->net_dev->dev.parent;
+	void *vaddr;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
+		dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
+		free_pages((unsigned long)vaddr, 0);
+	}
+}
+
+static void xdp_release_buf(struct dpaa2_eth_priv *priv,
+			    struct dpaa2_eth_channel *ch,
+			    dma_addr_t addr)
+{
+	int err;
+
+	ch->xdp.drop_bufs[ch->xdp.drop_cnt++] = addr;
+	if (ch->xdp.drop_cnt < DPAA2_ETH_BUFS_PER_CMD)
+		return;
+
+	while ((err = dpaa2_io_service_release(ch->dpio, priv->bpid,
+					       ch->xdp.drop_bufs,
+					       ch->xdp.drop_cnt)) == -EBUSY)
+		cpu_relax();
+
+	if (err) {
+		free_bufs(priv, ch->xdp.drop_bufs, ch->xdp.drop_cnt);
+		ch->buf_count -= ch->xdp.drop_cnt;
+	}
+
+	ch->xdp.drop_cnt = 0;
+}
+
+static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd,
+		       void *buf_start, u16 queue_id)
+{
+	struct dpaa2_eth_fq *fq;
+	struct dpaa2_faead *faead;
+	u32 ctrl, frc;
+	int i, err;
+
+	/* Mark the egress frame hardware annotation area as valid */
+	frc = dpaa2_fd_get_frc(fd);
+	dpaa2_fd_set_frc(fd, frc | DPAA2_FD_FRC_FAEADV);
+	dpaa2_fd_set_ctrl(fd, DPAA2_FD_CTRL_ASAL);
+
+	/* Instruct hardware to release the FD buffer directly into
+	 * the buffer pool once transmission is completed, instead of
+	 * sending a Tx confirmation frame to us
+	 */
+	ctrl = DPAA2_FAEAD_A4V | DPAA2_FAEAD_A2V | DPAA2_FAEAD_EBDDV;
+	faead = dpaa2_get_faead(buf_start, false);
+	faead->ctrl = cpu_to_le32(ctrl);
+	faead->conf_fqid = 0;
+
+	fq = &priv->fq[queue_id];
+	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
+		err = priv->enqueue(priv, fq, fd, 0);
+		if (err != -EBUSY)
+			break;
+	}
+
+	return err;
+}
+
+static u32 run_xdp(struct dpaa2_eth_priv *priv,
+		   struct dpaa2_eth_channel *ch,
+		   struct dpaa2_eth_fq *rx_fq,
+		   struct dpaa2_fd *fd, void *vaddr)
+{
+	dma_addr_t addr = dpaa2_fd_get_addr(fd);
+	struct rtnl_link_stats64 *percpu_stats;
+	struct bpf_prog *xdp_prog;
+	struct xdp_buff xdp;
+	u32 xdp_act = XDP_PASS;
+	int err;
+
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+
+	rcu_read_lock();
+
+	xdp_prog = READ_ONCE(ch->xdp.prog);
+	if (!xdp_prog)
+		goto out;
+
+	xdp.data = vaddr + dpaa2_fd_get_offset(fd);
+	xdp.data_end = xdp.data + dpaa2_fd_get_len(fd);
+	xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM;
+	xdp_set_data_meta_invalid(&xdp);
+	xdp.rxq = &ch->xdp_rxq;
+
+	xdp_act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	/* xdp.data pointer may have changed */
+	dpaa2_fd_set_offset(fd, xdp.data - vaddr);
+	dpaa2_fd_set_len(fd, xdp.data_end - xdp.data);
+
+	switch (xdp_act) {
+	case XDP_PASS:
+		break;
+	case XDP_TX:
+		err = xdp_enqueue(priv, fd, vaddr, rx_fq->flowid);
+		if (err) {
+			xdp_release_buf(priv, ch, addr);
+			percpu_stats->tx_errors++;
+			ch->stats.xdp_tx_err++;
+		} else {
+			percpu_stats->tx_packets++;
+			percpu_stats->tx_bytes += dpaa2_fd_get_len(fd);
+			ch->stats.xdp_tx++;
+		}
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(xdp_act);
+		/* fall through */
+	case XDP_ABORTED:
+		trace_xdp_exception(priv->net_dev, xdp_prog, xdp_act);
+		/* fall through */
+	case XDP_DROP:
+		xdp_release_buf(priv, ch, addr);
+		ch->stats.xdp_drop++;
+		break;
+	case XDP_REDIRECT:
+		dma_unmap_page(priv->net_dev->dev.parent, addr,
+			       DPAA2_ETH_RX_BUF_SIZE, DMA_BIDIRECTIONAL);
+		ch->buf_count--;
+		xdp.data_hard_start = vaddr;
+		err = xdp_do_redirect(priv->net_dev, &xdp, xdp_prog);
+		if (unlikely(err))
+			ch->stats.xdp_drop++;
+		else
+			ch->stats.xdp_redirect++;
+		break;
+	}
+
+	ch->xdp.res |= xdp_act;
+out:
+	rcu_read_unlock();
+	return xdp_act;
+}
+
 /* Main Rx frame processing routine */
 static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 			 struct dpaa2_eth_channel *ch,
 			 const struct dpaa2_fd *fd,
-			 struct napi_struct *napi,
-			 u16 queue_id)
+			 struct dpaa2_eth_fq *fq)
 {
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
 	u8 fd_format = dpaa2_fd_get_format(fd);
@@ -216,12 +364,14 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	struct dpaa2_fas *fas;
 	void *buf_data;
 	u32 status = 0;
+	u32 xdp_act;
 
 	/* Tracing point */
 	trace_dpaa2_rx_fd(priv->net_dev, fd);
 
 	vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr);
-	dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE, DMA_FROM_DEVICE);
+	dma_sync_single_for_cpu(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+				DMA_BIDIRECTIONAL);
 
 	fas = dpaa2_get_fas(vaddr, false);
 	prefetch(fas);
@@ -232,10 +382,23 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 
 	if (fd_format == dpaa2_fd_single) {
+		xdp_act = run_xdp(priv, ch, fq, (struct dpaa2_fd *)fd, vaddr);
+		if (xdp_act != XDP_PASS) {
+			percpu_stats->rx_packets++;
+			percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
+			return;
+		}
+
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 		skb = build_linear_skb(ch, fd, vaddr);
 	} else if (fd_format == dpaa2_fd_sg) {
+		WARN_ON(priv->xdp_prog);
+
+		dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE,
+			       DMA_BIDIRECTIONAL);
 		skb = build_frag_skb(priv, ch, buf_data);
-		skb_free_frag(vaddr);
+		free_pages((unsigned long)vaddr, 0);
 		percpu_extras->rx_sg_frames++;
 		percpu_extras->rx_sg_bytes += dpaa2_fd_get_len(fd);
 	} else {
@@ -267,12 +430,12 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv,
 	}
 
 	skb->protocol = eth_type_trans(skb, priv->net_dev);
-	skb_record_rx_queue(skb, queue_id);
+	skb_record_rx_queue(skb, fq->flowid);
 
 	percpu_stats->rx_packets++;
 	percpu_stats->rx_bytes += dpaa2_fd_get_len(fd);
 
-	napi_gro_receive(napi, skb);
+	napi_gro_receive(&ch->napi, skb);
 
 	return;
 
@@ -289,7 +452,7 @@ err_frame_format:
  * Observance of NAPI budget is not our concern, leaving that to the caller.
  */
 static int consume_frames(struct dpaa2_eth_channel *ch,
-			  enum dpaa2_eth_fq_type *type)
+			  struct dpaa2_eth_fq **src)
 {
 	struct dpaa2_eth_priv *priv = ch->priv;
 	struct dpaa2_eth_fq *fq = NULL;
@@ -312,7 +475,7 @@ static int consume_frames(struct dpaa2_eth_channel *ch,
 		fd = dpaa2_dq_fd(dq);
 		fq = (struct dpaa2_eth_fq *)(uintptr_t)dpaa2_dq_fqd_ctx(dq);
 
-		fq->consume(priv, ch, fd, &ch->napi, fq->flowid);
+		fq->consume(priv, ch, fd, fq);
 		cleaned++;
 	} while (!is_last);
 
@@ -320,13 +483,12 @@ static int consume_frames(struct dpaa2_eth_channel *ch,
 		return 0;
 
 	fq->stats.frames += cleaned;
-	ch->stats.frames += cleaned;
 
 	/* A dequeue operation only pulls frames from a single queue
-	 * into the store. Return the frame queue type as an out param.
+	 * into the store. Return the frame queue as an out param.
 	 */
-	if (type)
-		*type = fq->type;
+	if (src)
+		*src = fq;
 
 	return cleaned;
 }
@@ -422,10 +584,11 @@ static int build_sg_fd(struct dpaa2_eth_priv *priv,
 	 * all of them on Tx Conf.
 	 */
 	swa = (struct dpaa2_eth_swa *)sgt_buf;
-	swa->skb = skb;
-	swa->scl = scl;
-	swa->num_sg = num_sg;
-	swa->sgt_size = sgt_buf_size;
+	swa->type = DPAA2_ETH_SWA_SG;
+	swa->sg.skb = skb;
+	swa->sg.scl = scl;
+	swa->sg.num_sg = num_sg;
+	swa->sg.sgt_size = sgt_buf_size;
 
 	/* Separately map the SGT buffer */
 	addr = dma_map_single(dev, sgt_buf, sgt_buf_size, DMA_BIDIRECTIONAL);
@@ -460,7 +623,7 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	u8 *buffer_start, *aligned_start;
-	struct sk_buff **skbh;
+	struct dpaa2_eth_swa *swa;
 	dma_addr_t addr;
 
 	buffer_start = skb->data - dpaa2_eth_needed_headroom(priv, skb);
@@ -477,8 +640,9 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
 	 * (in the private data area) such that we can release it
 	 * on Tx confirm
 	 */
-	skbh = (struct sk_buff **)buffer_start;
-	*skbh = skb;
+	swa = (struct dpaa2_eth_swa *)buffer_start;
+	swa->type = DPAA2_ETH_SWA_SINGLE;
+	swa->single.skb = skb;
 
 	addr = dma_map_single(dev, buffer_start,
 			      skb_tail_pointer(skb) - buffer_start,
@@ -506,47 +670,65 @@ static int build_single_fd(struct dpaa2_eth_priv *priv,
  * dpaa2_eth_tx().
  */
 static void free_tx_fd(const struct dpaa2_eth_priv *priv,
-		       const struct dpaa2_fd *fd)
+		       struct dpaa2_eth_fq *fq,
+		       const struct dpaa2_fd *fd, bool in_napi)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	dma_addr_t fd_addr;
-	struct sk_buff **skbh, *skb;
+	struct sk_buff *skb = NULL;
 	unsigned char *buffer_start;
 	struct dpaa2_eth_swa *swa;
 	u8 fd_format = dpaa2_fd_get_format(fd);
+	u32 fd_len = dpaa2_fd_get_len(fd);
 
 	fd_addr = dpaa2_fd_get_addr(fd);
-	skbh = dpaa2_iova_to_virt(priv->iommu_domain, fd_addr);
+	buffer_start = dpaa2_iova_to_virt(priv->iommu_domain, fd_addr);
+	swa = (struct dpaa2_eth_swa *)buffer_start;
 
 	if (fd_format == dpaa2_fd_single) {
-		skb = *skbh;
-		buffer_start = (unsigned char *)skbh;
-		/* Accessing the skb buffer is safe before dma unmap, because
-		 * we didn't map the actual skb shell.
-		 */
-		dma_unmap_single(dev, fd_addr,
-				 skb_tail_pointer(skb) - buffer_start,
-				 DMA_BIDIRECTIONAL);
+		if (swa->type == DPAA2_ETH_SWA_SINGLE) {
+			skb = swa->single.skb;
+			/* Accessing the skb buffer is safe before dma unmap,
+			 * because we didn't map the actual skb shell.
+			 */
+			dma_unmap_single(dev, fd_addr,
+					 skb_tail_pointer(skb) - buffer_start,
+					 DMA_BIDIRECTIONAL);
+		} else {
+			WARN_ONCE(swa->type != DPAA2_ETH_SWA_XDP, "Wrong SWA type");
+			dma_unmap_single(dev, fd_addr, swa->xdp.dma_size,
+					 DMA_BIDIRECTIONAL);
+		}
 	} else if (fd_format == dpaa2_fd_sg) {
-		swa = (struct dpaa2_eth_swa *)skbh;
-		skb = swa->skb;
+		skb = swa->sg.skb;
 
 		/* Unmap the scatterlist */
-		dma_unmap_sg(dev, swa->scl, swa->num_sg, DMA_BIDIRECTIONAL);
-		kfree(swa->scl);
+		dma_unmap_sg(dev, swa->sg.scl, swa->sg.num_sg,
+			     DMA_BIDIRECTIONAL);
+		kfree(swa->sg.scl);
 
 		/* Unmap the SGT buffer */
-		dma_unmap_single(dev, fd_addr, swa->sgt_size,
+		dma_unmap_single(dev, fd_addr, swa->sg.sgt_size,
 				 DMA_BIDIRECTIONAL);
 	} else {
 		netdev_dbg(priv->net_dev, "Invalid FD format\n");
 		return;
 	}
 
+	if (swa->type != DPAA2_ETH_SWA_XDP && in_napi) {
+		fq->dq_frames++;
+		fq->dq_bytes += fd_len;
+	}
+
+	if (swa->type == DPAA2_ETH_SWA_XDP) {
+		xdp_return_frame(swa->xdp.xdpf);
+		return;
+	}
+
 	/* Get the timestamp value */
 	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
 		struct skb_shared_hwtstamps shhwtstamps;
-		__le64 *ts = dpaa2_get_ts(skbh, true);
+		__le64 *ts = dpaa2_get_ts(buffer_start, true);
 		u64 ns;
 
 		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
@@ -558,10 +740,10 @@ static void free_tx_fd(const struct dpaa2_eth_priv *priv,
 
 	/* Free SGT buffer allocated on tx */
 	if (fd_format != dpaa2_fd_single)
-		skb_free_frag(skbh);
+		skb_free_frag(buffer_start);
 
 	/* Move on with skb release */
-	dev_kfree_skb(skb);
+	napi_consume_skb(skb, in_napi);
 }
 
 static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
@@ -571,8 +753,10 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
 	struct dpaa2_eth_fq *fq;
+	struct netdev_queue *nq;
 	u16 queue_mapping;
 	unsigned int needed_headroom;
+	u32 fd_len;
 	int err, i;
 
 	percpu_stats = this_cpu_ptr(priv->percpu_stats);
@@ -631,10 +815,16 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	 */
 	queue_mapping = skb_get_queue_mapping(skb);
 	fq = &priv->fq[queue_mapping];
+
+	fd_len = dpaa2_fd_get_len(&fd);
+	nq = netdev_get_tx_queue(net_dev, queue_mapping);
+	netdev_tx_sent_queue(nq, fd_len);
+
+	/* Everything that happens after this enqueues might race with
+	 * the Tx confirmation callback for this frame
+	 */
 	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
-		err = dpaa2_io_service_enqueue_qd(fq->channel->dpio,
-						  priv->tx_qdid, 0,
-						  fq->tx_qdbin, &fd);
+		err = priv->enqueue(priv, fq, &fd, 0);
 		if (err != -EBUSY)
 			break;
 	}
@@ -642,10 +832,11 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0)) {
 		percpu_stats->tx_errors++;
 		/* Clean up everything, including freeing the skb */
-		free_tx_fd(priv, &fd);
+		free_tx_fd(priv, fq, &fd, false);
+		netdev_tx_completed_queue(nq, 1, fd_len);
 	} else {
 		percpu_stats->tx_packets++;
-		percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
+		percpu_stats->tx_bytes += fd_len;
 	}
 
 	return NETDEV_TX_OK;
@@ -661,11 +852,11 @@ err_alloc_headroom:
 static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 			      struct dpaa2_eth_channel *ch __always_unused,
 			      const struct dpaa2_fd *fd,
-			      struct napi_struct *napi __always_unused,
-			      u16 queue_id __always_unused)
+			      struct dpaa2_eth_fq *fq)
 {
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa2_eth_drv_stats *percpu_extras;
+	u32 fd_len = dpaa2_fd_get_len(fd);
 	u32 fd_errors;
 
 	/* Tracing point */
@@ -673,11 +864,11 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv,
 
 	percpu_extras = this_cpu_ptr(priv->percpu_extras);
 	percpu_extras->tx_conf_frames++;
-	percpu_extras->tx_conf_bytes += dpaa2_fd_get_len(fd);
+	percpu_extras->tx_conf_bytes += fd_len;
 
 	/* Check frame errors in the FD field */
 	fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK;
-	free_tx_fd(priv, fd);
+	free_tx_fd(priv, fq, fd, true);
 
 	if (likely(!fd_errors))
 		return;
@@ -735,23 +926,6 @@ static int set_tx_csum(struct dpaa2_eth_priv *priv, bool enable)
 	return 0;
 }
 
-/* Free buffers acquired from the buffer pool or which were meant to
- * be released in the pool
- */
-static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count)
-{
-	struct device *dev = priv->net_dev->dev.parent;
-	void *vaddr;
-	int i;
-
-	for (i = 0; i < count; i++) {
-		vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]);
-		dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
-		skb_free_frag(vaddr);
-	}
-}
-
 /* Perform a single release command to add buffers
  * to the specified buffer pool
  */
@@ -760,7 +934,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	u64 buf_array[DPAA2_ETH_BUFS_PER_CMD];
-	void *buf;
+	struct page *page;
 	dma_addr_t addr;
 	int i, err;
 
@@ -768,14 +942,16 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 		/* Allocate buffer visible to WRIOP + skb shared info +
 		 * alignment padding
 		 */
-		buf = napi_alloc_frag(dpaa2_eth_buf_raw_size(priv));
-		if (unlikely(!buf))
+		/* allocate one page for each Rx buffer. WRIOP sees
+		 * the entire page except for a tailroom reserved for
+		 * skb shared info
+		 */
+		page = dev_alloc_pages(0);
+		if (!page)
 			goto err_alloc;
 
-		buf = PTR_ALIGN(buf, priv->rx_buf_align);
-
-		addr = dma_map_single(dev, buf, DPAA2_ETH_RX_BUF_SIZE,
-				      DMA_FROM_DEVICE);
+		addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE,
+				    DMA_BIDIRECTIONAL);
 		if (unlikely(dma_mapping_error(dev, addr)))
 			goto err_map;
 
@@ -783,7 +959,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv,
 
 		/* tracing point */
 		trace_dpaa2_eth_buf_seed(priv->net_dev,
-					 buf, dpaa2_eth_buf_raw_size(priv),
+					 page, DPAA2_ETH_RX_BUF_RAW_SIZE,
 					 addr, DPAA2_ETH_RX_BUF_SIZE,
 					 bpid);
 	}
@@ -805,7 +981,7 @@ release_bufs:
 	return i;
 
 err_map:
-	skb_free_frag(buf);
+	__free_pages(page, 0);
 err_alloc:
 	/* If we managed to allocate at least some buffers,
 	 * release them to hardware
@@ -934,11 +1110,13 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	struct dpaa2_eth_channel *ch;
 	struct dpaa2_eth_priv *priv;
 	int rx_cleaned = 0, txconf_cleaned = 0;
-	enum dpaa2_eth_fq_type type = 0;
-	int store_cleaned;
+	struct dpaa2_eth_fq *fq, *txc_fq = NULL;
+	struct netdev_queue *nq;
+	int store_cleaned, work_done;
 	int err;
 
 	ch = container_of(napi, struct dpaa2_eth_channel, napi);
+	ch->xdp.res = 0;
 	priv = ch->priv;
 
 	do {
@@ -949,18 +1127,25 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 		/* Refill pool if appropriate */
 		refill_pool(priv, ch, priv->bpid);
 
-		store_cleaned = consume_frames(ch, &type);
-		if (type == DPAA2_RX_FQ)
+		store_cleaned = consume_frames(ch, &fq);
+		if (!store_cleaned)
+			break;
+		if (fq->type == DPAA2_RX_FQ) {
 			rx_cleaned += store_cleaned;
-		else
+		} else {
 			txconf_cleaned += store_cleaned;
+			/* We have a single Tx conf FQ on this channel */
+			txc_fq = fq;
+		}
 
 		/* If we either consumed the whole NAPI budget with Rx frames
 		 * or we reached the Tx confirmations threshold, we're done.
 		 */
 		if (rx_cleaned >= budget ||
-		    txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI)
-			return budget;
+		    txconf_cleaned >= DPAA2_ETH_TXCONF_PER_NAPI) {
+			work_done = budget;
+			goto out;
+		}
 	} while (store_cleaned);
 
 	/* We didn't consume the entire budget, so finish napi and
@@ -974,7 +1159,21 @@ static int dpaa2_eth_poll(struct napi_struct *napi, int budget)
 	WARN_ONCE(err, "CDAN notifications rearm failed on core %d",
 		  ch->nctx.desired_cpu);
 
-	return max(rx_cleaned, 1);
+	work_done = max(rx_cleaned, 1);
+
+out:
+	if (txc_fq && txc_fq->dq_frames) {
+		nq = netdev_get_tx_queue(priv->net_dev, txc_fq->flowid);
+		netdev_tx_completed_queue(nq, txc_fq->dq_frames,
+					  txc_fq->dq_bytes);
+		txc_fq->dq_frames = 0;
+		txc_fq->dq_bytes = 0;
+	}
+
+	if (ch->xdp.res & XDP_REDIRECT)
+		xdp_do_flush_map();
+
+	return work_done;
 }
 
 static void enable_ch_napi(struct dpaa2_eth_priv *priv)
@@ -1081,34 +1280,36 @@ enable_err:
 	return err;
 }
 
-/* The DPIO store must be empty when we call this,
- * at the end of every NAPI cycle.
- */
-static u32 drain_channel(struct dpaa2_eth_channel *ch)
+/* Total number of in-flight frames on ingress queues */
+static u32 ingress_fq_count(struct dpaa2_eth_priv *priv)
 {
-	u32 drained = 0, total = 0;
+	struct dpaa2_eth_fq *fq;
+	u32 fcnt = 0, bcnt = 0, total = 0;
+	int i, err;
 
-	do {
-		pull_channel(ch);
-		drained = consume_frames(ch, NULL);
-		total += drained;
-	} while (drained);
+	for (i = 0; i < priv->num_fqs; i++) {
+		fq = &priv->fq[i];
+		err = dpaa2_io_query_fq_count(NULL, fq->fqid, &fcnt, &bcnt);
+		if (err) {
+			netdev_warn(priv->net_dev, "query_fq_count failed");
+			break;
+		}
+		total += fcnt;
+	}
 
 	return total;
 }
 
-static u32 drain_ingress_frames(struct dpaa2_eth_priv *priv)
+static void wait_for_fq_empty(struct dpaa2_eth_priv *priv)
 {
-	struct dpaa2_eth_channel *ch;
-	int i;
-	u32 drained = 0;
-
-	for (i = 0; i < priv->num_channels; i++) {
-		ch = priv->channel[i];
-		drained += drain_channel(ch);
-	}
+	int retries = 10;
+	u32 pending;
 
-	return drained;
+	do {
+		pending = ingress_fq_count(priv);
+		if (pending)
+			msleep(100);
+	} while (pending && --retries);
 }
 
 static int dpaa2_eth_stop(struct net_device *net_dev)
@@ -1116,14 +1317,22 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	int dpni_enabled = 0;
 	int retries = 10;
-	u32 drained;
 
 	netif_tx_stop_all_queues(net_dev);
 	netif_carrier_off(net_dev);
 
-	/* Loop while dpni_disable() attempts to drain the egress FQs
-	 * and confirm them back to us.
+	/* On dpni_disable(), the MC firmware will:
+	 * - stop MAC Rx and wait for all Rx frames to be enqueued to software
+	 * - cut off WRIOP dequeues from egress FQs and wait until transmission
+	 * of all in flight Tx frames is finished (and corresponding Tx conf
+	 * frames are enqueued back to software)
+	 *
+	 * Before calling dpni_disable(), we wait for all Tx frames to arrive
+	 * on WRIOP. After it finishes, wait until all remaining frames on Rx
+	 * and Tx conf queues are consumed on NAPI poll.
 	 */
+	msleep(500);
+
 	do {
 		dpni_disable(priv->mc_io, 0, priv->mc_token);
 		dpni_is_enabled(priv->mc_io, 0, priv->mc_token, &dpni_enabled);
@@ -1138,19 +1347,9 @@ static int dpaa2_eth_stop(struct net_device *net_dev)
 		 */
 	}
 
-	/* Wait for NAPI to complete on every core and disable it.
-	 * In particular, this will also prevent NAPI from being rescheduled if
-	 * a new CDAN is serviced, effectively discarding the CDAN. We therefore
-	 * don't even need to disarm the channels, except perhaps for the case
-	 * of a huge coalescing value.
-	 */
+	wait_for_fq_empty(priv);
 	disable_ch_napi(priv);
 
-	 /* Manually drain the Rx and TxConf queues */
-	drained = drain_ingress_frames(priv);
-	if (drained)
-		netdev_dbg(net_dev, "Drained %d frames.\n", drained);
-
 	/* Empty the buffer pool */
 	drain_pool(priv);
 
@@ -1400,6 +1599,273 @@ static int dpaa2_eth_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	return -EINVAL;
 }
 
+static bool xdp_mtu_valid(struct dpaa2_eth_priv *priv, int mtu)
+{
+	int mfl, linear_mfl;
+
+	mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
+	linear_mfl = DPAA2_ETH_RX_BUF_SIZE - DPAA2_ETH_RX_HWA_SIZE -
+		     dpaa2_eth_rx_head_room(priv) - XDP_PACKET_HEADROOM;
+
+	if (mfl > linear_mfl) {
+		netdev_warn(priv->net_dev, "Maximum MTU for XDP is %d\n",
+			    linear_mfl - VLAN_ETH_HLEN);
+		return false;
+	}
+
+	return true;
+}
+
+static int set_rx_mfl(struct dpaa2_eth_priv *priv, int mtu, bool has_xdp)
+{
+	int mfl, err;
+
+	/* We enforce a maximum Rx frame length based on MTU only if we have
+	 * an XDP program attached (in order to avoid Rx S/G frames).
+	 * Otherwise, we accept all incoming frames as long as they are not
+	 * larger than maximum size supported in hardware
+	 */
+	if (has_xdp)
+		mfl = DPAA2_ETH_L2_MAX_FRM(mtu);
+	else
+		mfl = DPAA2_ETH_MFL;
+
+	err = dpni_set_max_frame_length(priv->mc_io, 0, priv->mc_token, mfl);
+	if (err) {
+		netdev_err(priv->net_dev, "dpni_set_max_frame_length failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int dpaa2_eth_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	int err;
+
+	if (!priv->xdp_prog)
+		goto out;
+
+	if (!xdp_mtu_valid(priv, new_mtu))
+		return -EINVAL;
+
+	err = set_rx_mfl(priv, new_mtu, true);
+	if (err)
+		return err;
+
+out:
+	dev->mtu = new_mtu;
+	return 0;
+}
+
+static int update_rx_buffer_headroom(struct dpaa2_eth_priv *priv, bool has_xdp)
+{
+	struct dpni_buffer_layout buf_layout = {0};
+	int err;
+
+	err = dpni_get_buffer_layout(priv->mc_io, 0, priv->mc_token,
+				     DPNI_QUEUE_RX, &buf_layout);
+	if (err) {
+		netdev_err(priv->net_dev, "dpni_get_buffer_layout failed\n");
+		return err;
+	}
+
+	/* Reserve extra headroom for XDP header size changes */
+	buf_layout.data_head_room = dpaa2_eth_rx_head_room(priv) +
+				    (has_xdp ? XDP_PACKET_HEADROOM : 0);
+	buf_layout.options = DPNI_BUF_LAYOUT_OPT_DATA_HEAD_ROOM;
+	err = dpni_set_buffer_layout(priv->mc_io, 0, priv->mc_token,
+				     DPNI_QUEUE_RX, &buf_layout);
+	if (err) {
+		netdev_err(priv->net_dev, "dpni_set_buffer_layout failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int setup_xdp(struct net_device *dev, struct bpf_prog *prog)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+	struct dpaa2_eth_channel *ch;
+	struct bpf_prog *old;
+	bool up, need_update;
+	int i, err;
+
+	if (prog && !xdp_mtu_valid(priv, dev->mtu))
+		return -EINVAL;
+
+	if (prog) {
+		prog = bpf_prog_add(prog, priv->num_channels);
+		if (IS_ERR(prog))
+			return PTR_ERR(prog);
+	}
+
+	up = netif_running(dev);
+	need_update = (!!priv->xdp_prog != !!prog);
+
+	if (up)
+		dpaa2_eth_stop(dev);
+
+	/* While in xdp mode, enforce a maximum Rx frame size based on MTU.
+	 * Also, when switching between xdp/non-xdp modes we need to reconfigure
+	 * our Rx buffer layout. Buffer pool was drained on dpaa2_eth_stop,
+	 * so we are sure no old format buffers will be used from now on.
+	 */
+	if (need_update) {
+		err = set_rx_mfl(priv, dev->mtu, !!prog);
+		if (err)
+			goto out_err;
+		err = update_rx_buffer_headroom(priv, !!prog);
+		if (err)
+			goto out_err;
+	}
+
+	old = xchg(&priv->xdp_prog, prog);
+	if (old)
+		bpf_prog_put(old);
+
+	for (i = 0; i < priv->num_channels; i++) {
+		ch = priv->channel[i];
+		old = xchg(&ch->xdp.prog, prog);
+		if (old)
+			bpf_prog_put(old);
+	}
+
+	if (up) {
+		err = dpaa2_eth_open(dev);
+		if (err)
+			return err;
+	}
+
+	return 0;
+
+out_err:
+	if (prog)
+		bpf_prog_sub(prog, priv->num_channels);
+	if (up)
+		dpaa2_eth_open(dev);
+
+	return err;
+}
+
+static int dpaa2_eth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(dev);
+
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return setup_xdp(dev, xdp->prog);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = priv->xdp_prog ? priv->xdp_prog->aux->id : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dpaa2_eth_xdp_xmit_frame(struct net_device *net_dev,
+				    struct xdp_frame *xdpf)
+{
+	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
+	struct device *dev = net_dev->dev.parent;
+	struct rtnl_link_stats64 *percpu_stats;
+	struct dpaa2_eth_drv_stats *percpu_extras;
+	unsigned int needed_headroom;
+	struct dpaa2_eth_swa *swa;
+	struct dpaa2_eth_fq *fq;
+	struct dpaa2_fd fd;
+	void *buffer_start, *aligned_start;
+	dma_addr_t addr;
+	int err, i;
+
+	/* We require a minimum headroom to be able to transmit the frame.
+	 * Otherwise return an error and let the original net_device handle it
+	 */
+	needed_headroom = dpaa2_eth_needed_headroom(priv, NULL);
+	if (xdpf->headroom < needed_headroom)
+		return -EINVAL;
+
+	percpu_stats = this_cpu_ptr(priv->percpu_stats);
+	percpu_extras = this_cpu_ptr(priv->percpu_extras);
+
+	/* Setup the FD fields */
+	memset(&fd, 0, sizeof(fd));
+
+	/* Align FD address, if possible */
+	buffer_start = xdpf->data - needed_headroom;
+	aligned_start = PTR_ALIGN(buffer_start - DPAA2_ETH_TX_BUF_ALIGN,
+				  DPAA2_ETH_TX_BUF_ALIGN);
+	if (aligned_start >= xdpf->data - xdpf->headroom)
+		buffer_start = aligned_start;
+
+	swa = (struct dpaa2_eth_swa *)buffer_start;
+	/* fill in necessary fields here */
+	swa->type = DPAA2_ETH_SWA_XDP;
+	swa->xdp.dma_size = xdpf->data + xdpf->len - buffer_start;
+	swa->xdp.xdpf = xdpf;
+
+	addr = dma_map_single(dev, buffer_start,
+			      swa->xdp.dma_size,
+			      DMA_BIDIRECTIONAL);
+	if (unlikely(dma_mapping_error(dev, addr))) {
+		percpu_stats->tx_dropped++;
+		return -ENOMEM;
+	}
+
+	dpaa2_fd_set_addr(&fd, addr);
+	dpaa2_fd_set_offset(&fd, xdpf->data - buffer_start);
+	dpaa2_fd_set_len(&fd, xdpf->len);
+	dpaa2_fd_set_format(&fd, dpaa2_fd_single);
+	dpaa2_fd_set_ctrl(&fd, FD_CTRL_PTA);
+
+	fq = &priv->fq[smp_processor_id() % dpaa2_eth_queue_count(priv)];
+	for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) {
+		err = priv->enqueue(priv, fq, &fd, 0);
+		if (err != -EBUSY)
+			break;
+	}
+	percpu_extras->tx_portal_busy += i;
+	if (unlikely(err < 0)) {
+		percpu_stats->tx_errors++;
+		/* let the Rx device handle the cleanup */
+		return err;
+	}
+
+	percpu_stats->tx_packets++;
+	percpu_stats->tx_bytes += dpaa2_fd_get_len(&fd);
+
+	return 0;
+}
+
+static int dpaa2_eth_xdp_xmit(struct net_device *net_dev, int n,
+			      struct xdp_frame **frames, u32 flags)
+{
+	int drops = 0;
+	int i, err;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	if (!netif_running(net_dev))
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+
+		err = dpaa2_eth_xdp_xmit_frame(net_dev, xdpf);
+		if (err) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	return n - drops;
+}
+
 static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_open = dpaa2_eth_open,
 	.ndo_start_xmit = dpaa2_eth_tx,
@@ -1409,6 +1875,9 @@ static const struct net_device_ops dpaa2_eth_ops = {
 	.ndo_set_rx_mode = dpaa2_eth_set_rx_mode,
 	.ndo_set_features = dpaa2_eth_set_features,
 	.ndo_do_ioctl = dpaa2_eth_ioctl,
+	.ndo_change_mtu = dpaa2_eth_change_mtu,
+	.ndo_bpf = dpaa2_eth_xdp,
+	.ndo_xdp_xmit = dpaa2_eth_xdp_xmit,
 };
 
 static void cdan_cb(struct dpaa2_io_notification_ctx *ctx)
@@ -1434,8 +1903,11 @@ static struct fsl_mc_device *setup_dpcon(struct dpaa2_eth_priv *priv)
 	err = fsl_mc_object_allocate(to_fsl_mc_device(dev),
 				     FSL_MC_POOL_DPCON, &dpcon);
 	if (err) {
-		dev_info(dev, "Not enough DPCONs, will go on as-is\n");
-		return NULL;
+		if (err == -ENXIO)
+			err = -EPROBE_DEFER;
+		else
+			dev_info(dev, "Not enough DPCONs, will go on as-is\n");
+		return ERR_PTR(err);
 	}
 
 	err = dpcon_open(priv->mc_io, 0, dpcon->obj_desc.id, &dpcon->mc_handle);
@@ -1493,8 +1965,10 @@ alloc_channel(struct dpaa2_eth_priv *priv)
 		return NULL;
 
 	channel->dpcon = setup_dpcon(priv);
-	if (!channel->dpcon)
+	if (IS_ERR_OR_NULL(channel->dpcon)) {
+		err = PTR_ERR(channel->dpcon);
 		goto err_setup;
+	}
 
 	err = dpcon_get_attributes(priv->mc_io, 0, channel->dpcon->mc_handle,
 				   &attr);
@@ -1513,7 +1987,7 @@ err_get_attr:
 	free_dpcon(priv, channel->dpcon);
 err_setup:
 	kfree(channel);
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static void free_channel(struct dpaa2_eth_priv *priv,
@@ -1547,10 +2021,11 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 	for_each_online_cpu(i) {
 		/* Try to allocate a channel */
 		channel = alloc_channel(priv);
-		if (!channel) {
-			dev_info(dev,
-				 "No affine channel for cpu %d and above\n", i);
-			err = -ENODEV;
+		if (IS_ERR_OR_NULL(channel)) {
+			err = PTR_ERR(channel);
+			if (err != -EPROBE_DEFER)
+				dev_info(dev,
+					 "No affine channel for cpu %d and above\n", i);
 			goto err_alloc_ch;
 		}
 
@@ -1564,7 +2039,7 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 
 		/* Register the new context */
 		channel->dpio = dpaa2_io_service_select(i);
-		err = dpaa2_io_service_register(channel->dpio, nctx);
+		err = dpaa2_io_service_register(channel->dpio, nctx, dev);
 		if (err) {
 			dev_dbg(dev, "No affine DPIO for cpu %d\n", i);
 			/* If no affine DPIO for this core, there's probably
@@ -1597,20 +2072,23 @@ static int setup_dpio(struct dpaa2_eth_priv *priv)
 		/* Stop if we already have enough channels to accommodate all
 		 * RX and TX conf queues
 		 */
-		if (priv->num_channels == dpaa2_eth_queue_count(priv))
+		if (priv->num_channels == priv->dpni_attrs.num_queues)
 			break;
 	}
 
 	return 0;
 
 err_set_cdan:
-	dpaa2_io_service_deregister(channel->dpio, nctx);
+	dpaa2_io_service_deregister(channel->dpio, nctx, dev);
 err_service_reg:
 	free_channel(priv, channel);
 err_alloc_ch:
+	if (err == -EPROBE_DEFER)
+		return err;
+
 	if (cpumask_empty(&priv->dpio_cpumask)) {
 		dev_err(dev, "No cpu with an affine DPIO/DPCON\n");
-		return err;
+		return -ENODEV;
 	}
 
 	dev_info(dev, "Cores %*pbl available for processing ingress traffic\n",
@@ -1621,13 +2099,14 @@ err_alloc_ch:
 
 static void free_dpio(struct dpaa2_eth_priv *priv)
 {
-	int i;
+	struct device *dev = priv->net_dev->dev.parent;
 	struct dpaa2_eth_channel *ch;
+	int i;
 
 	/* deregister CDAN notifications and free channels */
 	for (i = 0; i < priv->num_channels; i++) {
 		ch = priv->channel[i];
-		dpaa2_io_service_deregister(ch->dpio, &ch->nctx);
+		dpaa2_io_service_deregister(ch->dpio, &ch->nctx, dev);
 		free_channel(priv, ch);
 	}
 }
@@ -1732,7 +2211,10 @@ static int setup_dpbp(struct dpaa2_eth_priv *priv)
 	err = fsl_mc_object_allocate(to_fsl_mc_device(dev), FSL_MC_POOL_DPBP,
 				     &dpbp_dev);
 	if (err) {
-		dev_err(dev, "DPBP device allocation failed\n");
+		if (err == -ENXIO)
+			err = -EPROBE_DEFER;
+		else
+			dev_err(dev, "DPBP device allocation failed\n");
 		return err;
 	}
 
@@ -1790,6 +2272,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 {
 	struct device *dev = priv->net_dev->dev.parent;
 	struct dpni_buffer_layout buf_layout = {0};
+	u16 rx_buf_align;
 	int err;
 
 	/* We need to check for WRIOP version 1.0.0, but depending on the MC
@@ -1798,9 +2281,9 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	 */
 	if (priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(0, 0, 0) ||
 	    priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(1, 0, 0))
-		priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1;
+		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1;
 	else
-		priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
+		rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN;
 
 	/* tx buffer */
 	buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE;
@@ -1840,7 +2323,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	/* rx buffer */
 	buf_layout.pass_frame_status = true;
 	buf_layout.pass_parser_result = true;
-	buf_layout.data_align = priv->rx_buf_align;
+	buf_layout.data_align = rx_buf_align;
 	buf_layout.data_head_room = dpaa2_eth_rx_head_room(priv);
 	buf_layout.private_data_size = 0;
 	buf_layout.options = DPNI_BUF_LAYOUT_OPT_PARSER_RESULT |
@@ -1858,6 +2341,36 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv)
 	return 0;
 }
 
+#define DPNI_ENQUEUE_FQID_VER_MAJOR	7
+#define DPNI_ENQUEUE_FQID_VER_MINOR	9
+
+static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv,
+				       struct dpaa2_eth_fq *fq,
+				       struct dpaa2_fd *fd, u8 prio)
+{
+	return dpaa2_io_service_enqueue_qd(fq->channel->dpio,
+					   priv->tx_qdid, prio,
+					   fq->tx_qdbin, fd);
+}
+
+static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv,
+				       struct dpaa2_eth_fq *fq,
+				       struct dpaa2_fd *fd,
+				       u8 prio __always_unused)
+{
+	return dpaa2_io_service_enqueue_fq(fq->channel->dpio,
+					   fq->tx_fqid, fd);
+}
+
+static void set_enqueue_mode(struct dpaa2_eth_priv *priv)
+{
+	if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR,
+				   DPNI_ENQUEUE_FQID_VER_MINOR) < 0)
+		priv->enqueue = dpaa2_eth_enqueue_qd;
+	else
+		priv->enqueue = dpaa2_eth_enqueue_fq;
+}
+
 /* Configure the DPNI object this interface is associated with */
 static int setup_dpni(struct fsl_mc_device *ls_dev)
 {
@@ -1911,6 +2424,8 @@ static int setup_dpni(struct fsl_mc_device *ls_dev)
 	if (err)
 		goto close;
 
+	set_enqueue_mode(priv);
+
 	priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) *
 				       dpaa2_eth_fs_count(priv), GFP_KERNEL);
 	if (!priv->cls_rules)
@@ -1958,9 +2473,14 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 	queue.destination.type = DPNI_DEST_DPCON;
 	queue.destination.priority = 1;
 	queue.user_context = (u64)(uintptr_t)fq;
+	queue.flc.stash_control = 1;
+	queue.flc.value &= 0xFFFFFFFFFFFFFFC0;
+	/* 01 01 00 - data, annotation, flow context */
+	queue.flc.value |= 0x14;
 	err = dpni_set_queue(priv->mc_io, 0, priv->mc_token,
 			     DPNI_QUEUE_RX, 0, fq->flowid,
-			     DPNI_QUEUE_OPT_USER_CTX | DPNI_QUEUE_OPT_DEST,
+			     DPNI_QUEUE_OPT_USER_CTX | DPNI_QUEUE_OPT_DEST |
+			     DPNI_QUEUE_OPT_FLC,
 			     &queue);
 	if (err) {
 		dev_err(dev, "dpni_set_queue(RX) failed\n");
@@ -1976,6 +2496,21 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv,
 		return err;
 	}
 
+	/* xdp_rxq setup */
+	err = xdp_rxq_info_reg(&fq->channel->xdp_rxq, priv->net_dev,
+			       fq->flowid);
+	if (err) {
+		dev_err(dev, "xdp_rxq_info_reg failed\n");
+		return err;
+	}
+
+	err = xdp_rxq_info_reg_mem_model(&fq->channel->xdp_rxq,
+					 MEM_TYPE_PAGE_ORDER0, NULL);
+	if (err) {
+		dev_err(dev, "xdp_rxq_info_reg_mem_model failed\n");
+		return err;
+	}
+
 	return 0;
 }
 
@@ -1995,6 +2530,7 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv,
 	}
 
 	fq->tx_qdbin = qid.qdbin;
+	fq->tx_fqid = qid.fqid;
 
 	err = dpni_get_queue(priv->mc_io, 0, priv->mc_token,
 			     DPNI_QUEUE_TX_CONFIRM, 0, fq->flowid,
@@ -2739,6 +3275,10 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev)
 		goto err_netdev_reg;
 	}
 
+#ifdef CONFIG_DEBUG_FS
+	dpaa2_dbg_add(priv);
+#endif
+
 	dev_info(dev, "Probed interface %s\n", net_dev->name);
 	return 0;
 
@@ -2782,6 +3322,9 @@ static int dpaa2_eth_remove(struct fsl_mc_device *ls_dev)
 	net_dev = dev_get_drvdata(dev);
 	priv = netdev_priv(net_dev);
 
+#ifdef CONFIG_DEBUG_FS
+	dpaa2_dbg_remove(priv);
+#endif
 	unregister_netdev(net_dev);
 
 	if (priv->do_link_poll)
@@ -2826,4 +3369,25 @@ static struct fsl_mc_driver dpaa2_eth_driver = {
 	.match_id_table = dpaa2_eth_match_id_table
 };
 
-module_fsl_mc_driver(dpaa2_eth_driver);
+static int __init dpaa2_eth_driver_init(void)
+{
+	int err;
+
+	dpaa2_eth_dbg_init();
+	err = fsl_mc_driver_register(&dpaa2_eth_driver);
+	if (err) {
+		dpaa2_eth_dbg_exit();
+		return err;
+	}
+
+	return 0;
+}
+
+static void __exit dpaa2_eth_driver_exit(void)
+{
+	dpaa2_eth_dbg_exit();
+	fsl_mc_driver_unregister(&dpaa2_eth_driver);
+}
+
+module_init(dpaa2_eth_driver_init);
+module_exit(dpaa2_eth_driver_exit);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
index 452a8e9c4f0e..7879622aa3e6 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h
@@ -16,6 +16,7 @@
 #include "dpni-cmd.h"
 
 #include "dpaa2-eth-trace.h"
+#include "dpaa2-eth-debugfs.h"
 
 #define DPAA2_WRIOP_VERSION(x, y, z) ((x) << 10 | (y) << 5 | (z) << 0)
 
@@ -52,7 +53,8 @@
  */
 #define DPAA2_ETH_MAX_FRAMES_PER_QUEUE	(DPAA2_ETH_TAILDROP_THRESH / 64)
 #define DPAA2_ETH_NUM_BUFS		(DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256)
-#define DPAA2_ETH_REFILL_THRESH		DPAA2_ETH_MAX_FRAMES_PER_QUEUE
+#define DPAA2_ETH_REFILL_THRESH \
+	(DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD)
 
 /* Maximum number of buffers that can be acquired/released through a single
  * QBMan command
@@ -62,9 +64,11 @@
 /* Hardware requires alignment for ingress/egress buffer addresses */
 #define DPAA2_ETH_TX_BUF_ALIGN		64
 
-#define DPAA2_ETH_RX_BUF_SIZE		2048
-#define DPAA2_ETH_SKB_SIZE \
-	(DPAA2_ETH_RX_BUF_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define DPAA2_ETH_RX_BUF_RAW_SIZE	PAGE_SIZE
+#define DPAA2_ETH_RX_BUF_TAILROOM \
+	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))
+#define DPAA2_ETH_RX_BUF_SIZE \
+	(DPAA2_ETH_RX_BUF_RAW_SIZE - DPAA2_ETH_RX_BUF_TAILROOM)
 
 /* Hardware annotation area in RX/TX buffers */
 #define DPAA2_ETH_RX_HWA_SIZE		64
@@ -85,12 +89,33 @@
  */
 #define DPAA2_ETH_SWA_SIZE		64
 
+/* We store different information in the software annotation area of a Tx frame
+ * based on what type of frame it is
+ */
+enum dpaa2_eth_swa_type {
+	DPAA2_ETH_SWA_SINGLE,
+	DPAA2_ETH_SWA_SG,
+	DPAA2_ETH_SWA_XDP,
+};
+
 /* Must keep this struct smaller than DPAA2_ETH_SWA_SIZE */
 struct dpaa2_eth_swa {
-	struct sk_buff *skb;
-	struct scatterlist *scl;
-	int num_sg;
-	int sgt_size;
+	enum dpaa2_eth_swa_type type;
+	union {
+		struct {
+			struct sk_buff *skb;
+		} single;
+		struct {
+			struct sk_buff *skb;
+			struct scatterlist *scl;
+			int num_sg;
+			int sgt_size;
+		} sg;
+		struct {
+			int dma_size;
+			struct xdp_frame *xdpf;
+		} xdp;
+	};
 };
 
 /* Annotation valid bits in FD FRC */
@@ -139,7 +164,9 @@ struct dpaa2_faead {
 };
 
 #define DPAA2_FAEAD_A2V			0x20000000
+#define DPAA2_FAEAD_A4V			0x08000000
 #define DPAA2_FAEAD_UPDV		0x00001000
+#define DPAA2_FAEAD_EBDDV		0x00002000
 #define DPAA2_FAEAD_UPD			0x00000010
 
 /* Accessors for the hardware annotation fields that we use */
@@ -243,12 +270,15 @@ struct dpaa2_eth_fq_stats {
 struct dpaa2_eth_ch_stats {
 	/* Volatile dequeues retried due to portal busy */
 	__u64 dequeue_portal_busy;
-	/* Number of CDANs; useful to estimate avg NAPI len */
-	__u64 cdan;
-	/* Number of frames received on queues from this channel */
-	__u64 frames;
 	/* Pull errors */
 	__u64 pull_err;
+	/* Number of CDANs; useful to estimate avg NAPI len */
+	__u64 cdan;
+	/* XDP counters */
+	__u64 xdp_drop;
+	__u64 xdp_tx;
+	__u64 xdp_tx_err;
+	__u64 xdp_redirect;
 };
 
 /* Maximum number of queues associated with a DPNI */
@@ -269,19 +299,28 @@ struct dpaa2_eth_priv;
 struct dpaa2_eth_fq {
 	u32 fqid;
 	u32 tx_qdbin;
+	u32 tx_fqid;
 	u16 flowid;
 	int target_cpu;
+	u32 dq_frames;
+	u32 dq_bytes;
 	struct dpaa2_eth_channel *channel;
 	enum dpaa2_eth_fq_type type;
 
 	void (*consume)(struct dpaa2_eth_priv *priv,
 			struct dpaa2_eth_channel *ch,
 			const struct dpaa2_fd *fd,
-			struct napi_struct *napi,
-			u16 queue_id);
+			struct dpaa2_eth_fq *fq);
 	struct dpaa2_eth_fq_stats stats;
 };
 
+struct dpaa2_eth_ch_xdp {
+	struct bpf_prog *prog;
+	u64 drop_bufs[DPAA2_ETH_BUFS_PER_CMD];
+	int drop_cnt;
+	unsigned int res;
+};
+
 struct dpaa2_eth_channel {
 	struct dpaa2_io_notification_ctx nctx;
 	struct fsl_mc_device *dpcon;
@@ -293,6 +332,8 @@ struct dpaa2_eth_channel {
 	struct dpaa2_eth_priv *priv;
 	int buf_count;
 	struct dpaa2_eth_ch_stats stats;
+	struct dpaa2_eth_ch_xdp xdp;
+	struct xdp_rxq_info xdp_rxq;
 };
 
 struct dpaa2_eth_dist_fields {
@@ -313,6 +354,9 @@ struct dpaa2_eth_priv {
 
 	u8 num_fqs;
 	struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES];
+	int (*enqueue)(struct dpaa2_eth_priv *priv,
+		       struct dpaa2_eth_fq *fq,
+		       struct dpaa2_fd *fd, u8 prio);
 
 	u8 num_channels;
 	struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS];
@@ -330,7 +374,6 @@ struct dpaa2_eth_priv {
 	bool rx_tstamp; /* Rx timestamping enabled */
 
 	u16 tx_qdid;
-	u16 rx_buf_align;
 	struct fsl_mc_io *mc_io;
 	/* Cores which have an affine DPIO/DPCON.
 	 * This is the cpu set on which Rx and Tx conf frames are processed
@@ -352,6 +395,10 @@ struct dpaa2_eth_priv {
 	u64 rx_hash_fields;
 	struct dpaa2_eth_cls_rule *cls_rules;
 	u8 rx_cls_enabled;
+	struct bpf_prog *xdp_prog;
+#ifdef CONFIG_DEBUG_FS
+	struct dpaa2_debugfs dbg;
+#endif
 };
 
 #define DPAA2_RXH_SUPPORTED	(RXH_L2DA | RXH_VLAN | RXH_L3_PROTO \
@@ -392,26 +439,27 @@ static inline int dpaa2_eth_cmp_dpni_ver(struct dpaa2_eth_priv *priv,
 #define dpaa2_eth_fs_count(priv)        \
 	((priv)->dpni_attrs.fs_entries)
 
+/* We have exactly one {Rx, Tx conf} queue per channel */
+#define dpaa2_eth_queue_count(priv)     \
+	((priv)->num_channels)
+
 enum dpaa2_eth_rx_dist {
 	DPAA2_ETH_RX_DIST_HASH,
 	DPAA2_ETH_RX_DIST_CLS
 };
 
-/* Hardware only sees DPAA2_ETH_RX_BUF_SIZE, but the skb built around
- * the buffer also needs space for its shared info struct, and we need
- * to allocate enough to accommodate hardware alignment restrictions
- */
-static inline unsigned int dpaa2_eth_buf_raw_size(struct dpaa2_eth_priv *priv)
-{
-	return DPAA2_ETH_SKB_SIZE + priv->rx_buf_align;
-}
-
 static inline
 unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
 				       struct sk_buff *skb)
 {
 	unsigned int headroom = DPAA2_ETH_SWA_SIZE;
 
+	/* If we don't have an skb (e.g. XDP buffer), we only need space for
+	 * the software annotation area
+	 */
+	if (!skb)
+		return headroom;
+
 	/* For non-linear skbs we have no headroom requirement, as we build a
 	 * SG frame with a newly allocated SGT buffer
 	 */
@@ -430,13 +478,7 @@ unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv,
  */
 static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv)
 {
-	return priv->tx_data_offset + DPAA2_ETH_TX_BUF_ALIGN -
-	       DPAA2_ETH_RX_HWA_SIZE;
-}
-
-static int dpaa2_eth_queue_count(struct dpaa2_eth_priv *priv)
-{
-	return priv->dpni_attrs.num_queues;
+	return priv->tx_data_offset - DPAA2_ETH_RX_HWA_SIZE;
 }
 
 int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
index 26bd5a2bd8ed..591dfcf76adb 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c
@@ -45,6 +45,16 @@ static char dpaa2_ethtool_extras[][ETH_GSTRING_LEN] = {
 	"[drv] dequeue portal busy",
 	"[drv] channel pull errors",
 	"[drv] cdan",
+	"[drv] xdp drop",
+	"[drv] xdp tx",
+	"[drv] xdp tx errors",
+	"[drv] xdp redirect",
+	/* FQ stats */
+	"[qbman] rx pending frames",
+	"[qbman] rx pending bytes",
+	"[qbman] tx conf pending frames",
+	"[qbman] tx conf pending bytes",
+	"[qbman] buffer count",
 };
 
 #define DPAA2_ETH_NUM_EXTRA_STATS	ARRAY_SIZE(dpaa2_ethtool_extras)
@@ -174,8 +184,10 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	int j, k, err;
 	int num_cnt;
 	union dpni_statistics dpni_stats;
-	u64 cdan = 0;
-	u64 portal_busy = 0, pull_err = 0;
+	u32 fcnt, bcnt;
+	u32 fcnt_rx_total = 0, fcnt_tx_total = 0;
+	u32 bcnt_rx_total = 0, bcnt_tx_total = 0;
+	u32 buf_cnt;
 	struct dpaa2_eth_priv *priv = netdev_priv(net_dev);
 	struct dpaa2_eth_drv_stats *extras;
 	struct dpaa2_eth_ch_stats *ch_stats;
@@ -212,16 +224,43 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev,
 	}
 	i += j;
 
-	for (j = 0; j < priv->num_channels; j++) {
-		ch_stats = &priv->channel[j]->stats;
-		cdan += ch_stats->cdan;
-		portal_busy += ch_stats->dequeue_portal_busy;
-		pull_err += ch_stats->pull_err;
+	/* Per-channel stats */
+	for (k = 0; k < priv->num_channels; k++) {
+		ch_stats = &priv->channel[k]->stats;
+		for (j = 0; j < sizeof(*ch_stats) / sizeof(__u64); j++)
+			*((__u64 *)data + i + j) += *((__u64 *)ch_stats + j);
 	}
+	i += j;
+
+	for (j = 0; j < priv->num_fqs; j++) {
+		/* Print FQ instantaneous counts */
+		err = dpaa2_io_query_fq_count(NULL, priv->fq[j].fqid,
+					      &fcnt, &bcnt);
+		if (err) {
+			netdev_warn(net_dev, "FQ query error %d", err);
+			return;
+		}
 
-	*(data + i++) = portal_busy;
-	*(data + i++) = pull_err;
-	*(data + i++) = cdan;
+		if (priv->fq[j].type == DPAA2_TX_CONF_FQ) {
+			fcnt_tx_total += fcnt;
+			bcnt_tx_total += bcnt;
+		} else {
+			fcnt_rx_total += fcnt;
+			bcnt_rx_total += bcnt;
+		}
+	}
+
+	*(data + i++) = fcnt_rx_total;
+	*(data + i++) = bcnt_rx_total;
+	*(data + i++) = fcnt_tx_total;
+	*(data + i++) = bcnt_tx_total;
+
+	err = dpaa2_io_query_bp_count(NULL, priv->bpid, &buf_cnt);
+	if (err) {
+		netdev_warn(net_dev, "Buffer count query error %d\n", err);
+		return;
+	}
+	*(data + i++) = buf_cnt;
 }
 
 static int prep_eth_rule(struct ethhdr *eth_value, struct ethhdr *eth_mask,
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
index 84b942b1eccc..9b150db3b510 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c
@@ -140,7 +140,10 @@ static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 
 	err = fsl_mc_portal_allocate(mc_dev, 0, &mc_dev->mc_io);
 	if (err) {
-		dev_err(dev, "fsl_mc_portal_allocate err %d\n", err);
+		if (err == -ENXIO)
+			err = -EPROBE_DEFER;
+		else
+			dev_err(dev, "fsl_mc_portal_allocate err %d\n", err);
 		goto err_exit;
 	}
 
diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig
new file mode 100644
index 000000000000..8429f5c1d810
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/Kconfig
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+config FSL_ENETC
+	tristate "ENETC PF driver"
+	depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+	help
+	  This driver supports NXP ENETC gigabit ethernet controller PCIe
+	  physical function (PF) devices, managing ENETC Ports at a privileged
+	  level.
+
+	  If compiled as module (M), the module name is fsl-enetc.
+
+config FSL_ENETC_VF
+	tristate "ENETC VF driver"
+	depends on PCI && PCI_MSI && (ARCH_LAYERSCAPE || COMPILE_TEST)
+	help
+	  This driver supports NXP ENETC gigabit ethernet controller PCIe
+	  virtual function (VF) devices enabled by the ENETC PF driver.
+
+	  If compiled as module (M), the module name is fsl-enetc-vf.
+
+config FSL_ENETC_PTP_CLOCK
+	tristate "ENETC PTP clock driver"
+	depends on PTP_1588_CLOCK_QORIQ && (FSL_ENETC || FSL_ENETC_VF)
+	default y
+	help
+	  This driver adds support for using the ENETC 1588 timer
+	  as a PTP clock. This clock is only useful if your PTP
+	  programs are getting hardware time stamps on the PTP Ethernet
+	  packets using the SO_TIMESTAMPING API.
+
+	  If compiled as module (M), the module name is fsl-enetc-ptp.
diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile
new file mode 100644
index 000000000000..7139e414dccf
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/Makefile
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o
+fsl-enetc-$(CONFIG_FSL_ENETC) += enetc.o enetc_cbdr.o enetc_ethtool.o \
+				 enetc_mdio.o
+fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o
+fsl-enetc-objs := enetc_pf.o $(fsl-enetc-y)
+
+obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o
+
+ifeq ($(CONFIG_FSL_ENETC)$(CONFIG_FSL_ENETC_VF), yy)
+fsl-enetc-vf-objs := enetc_vf.o
+else
+fsl-enetc-vf-$(CONFIG_FSL_ENETC_VF) += enetc.o enetc_cbdr.o \
+				       enetc_ethtool.o
+fsl-enetc-vf-objs := enetc_vf.o $(fsl-enetc-vf-y)
+endif
+
+obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o
+fsl-enetc-ptp-$(CONFIG_FSL_ENETC_PTP_CLOCK) += enetc_ptp.o
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
new file mode 100644
index 000000000000..5bb9eb35d76d
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -0,0 +1,1604 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include "enetc.h"
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/of_mdio.h>
+#include <linux/vmalloc.h>
+
+/* ENETC overhead: optional extension BD + 1 BD gap */
+#define ENETC_TXBDS_NEEDED(val)	((val) + 2)
+/* max # of chained Tx BDs is 15, including head and extension BD */
+#define ENETC_MAX_SKB_FRAGS	13
+#define ENETC_TXBDS_MAX_NEEDED	ENETC_TXBDS_NEEDED(ENETC_MAX_SKB_FRAGS + 1)
+
+static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb);
+
+netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_bdr *tx_ring;
+	int count;
+
+	tx_ring = priv->tx_ring[skb->queue_mapping];
+
+	if (unlikely(skb_shinfo(skb)->nr_frags > ENETC_MAX_SKB_FRAGS))
+		if (unlikely(skb_linearize(skb)))
+			goto drop_packet_err;
+
+	count = skb_shinfo(skb)->nr_frags + 1; /* fragments + head */
+	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_NEEDED(count)) {
+		netif_stop_subqueue(ndev, tx_ring->index);
+		return NETDEV_TX_BUSY;
+	}
+
+	count = enetc_map_tx_buffs(tx_ring, skb);
+	if (unlikely(!count))
+		goto drop_packet_err;
+
+	if (enetc_bd_unused(tx_ring) < ENETC_TXBDS_MAX_NEEDED)
+		netif_stop_subqueue(ndev, tx_ring->index);
+
+	return NETDEV_TX_OK;
+
+drop_packet_err:
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool enetc_tx_csum(struct sk_buff *skb, union enetc_tx_bd *txbd)
+{
+	int l3_start, l3_hsize;
+	u16 l3_flags, l4_flags;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return false;
+
+	switch (skb->csum_offset) {
+	case offsetof(struct tcphdr, check):
+		l4_flags = ENETC_TXBD_L4_TCP;
+		break;
+	case offsetof(struct udphdr, check):
+		l4_flags = ENETC_TXBD_L4_UDP;
+		break;
+	default:
+		skb_checksum_help(skb);
+		return false;
+	}
+
+	l3_start = skb_network_offset(skb);
+	l3_hsize = skb_network_header_len(skb);
+
+	l3_flags = 0;
+	if (skb->protocol == htons(ETH_P_IPV6))
+		l3_flags = ENETC_TXBD_L3_IPV6;
+
+	/* write BD fields */
+	txbd->l3_csoff = enetc_txbd_l3_csoff(l3_start, l3_hsize, l3_flags);
+	txbd->l4_csoff = l4_flags;
+
+	return true;
+}
+
+static void enetc_unmap_tx_buff(struct enetc_bdr *tx_ring,
+				struct enetc_tx_swbd *tx_swbd)
+{
+	if (tx_swbd->is_dma_page)
+		dma_unmap_page(tx_ring->dev, tx_swbd->dma,
+			       tx_swbd->len, DMA_TO_DEVICE);
+	else
+		dma_unmap_single(tx_ring->dev, tx_swbd->dma,
+				 tx_swbd->len, DMA_TO_DEVICE);
+	tx_swbd->dma = 0;
+}
+
+static void enetc_free_tx_skb(struct enetc_bdr *tx_ring,
+			      struct enetc_tx_swbd *tx_swbd)
+{
+	if (tx_swbd->dma)
+		enetc_unmap_tx_buff(tx_ring, tx_swbd);
+
+	if (tx_swbd->skb) {
+		dev_kfree_skb_any(tx_swbd->skb);
+		tx_swbd->skb = NULL;
+	}
+}
+
+static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
+{
+	struct enetc_tx_swbd *tx_swbd;
+	struct skb_frag_struct *frag;
+	int len = skb_headlen(skb);
+	union enetc_tx_bd temp_bd;
+	union enetc_tx_bd *txbd;
+	bool do_vlan, do_tstamp;
+	int i, count = 0;
+	unsigned int f;
+	dma_addr_t dma;
+	u8 flags = 0;
+
+	i = tx_ring->next_to_use;
+	txbd = ENETC_TXBD(*tx_ring, i);
+	prefetchw(txbd);
+
+	dma = dma_map_single(tx_ring->dev, skb->data, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(tx_ring->dev, dma)))
+		goto dma_err;
+
+	temp_bd.addr = cpu_to_le64(dma);
+	temp_bd.buf_len = cpu_to_le16(len);
+	temp_bd.lstatus = 0;
+
+	tx_swbd = &tx_ring->tx_swbd[i];
+	tx_swbd->dma = dma;
+	tx_swbd->len = len;
+	tx_swbd->is_dma_page = 0;
+	count++;
+
+	do_vlan = skb_vlan_tag_present(skb);
+	do_tstamp = skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP;
+
+	if (do_vlan || do_tstamp)
+		flags |= ENETC_TXBD_FLAGS_EX;
+
+	if (enetc_tx_csum(skb, &temp_bd))
+		flags |= ENETC_TXBD_FLAGS_CSUM | ENETC_TXBD_FLAGS_L4CS;
+
+	/* first BD needs frm_len and offload flags set */
+	temp_bd.frm_len = cpu_to_le16(skb->len);
+	temp_bd.flags = flags;
+
+	if (flags & ENETC_TXBD_FLAGS_EX) {
+		u8 e_flags = 0;
+		*txbd = temp_bd;
+		enetc_clear_tx_bd(&temp_bd);
+
+		/* add extension BD for VLAN and/or timestamping */
+		flags = 0;
+		tx_swbd++;
+		txbd++;
+		i++;
+		if (unlikely(i == tx_ring->bd_count)) {
+			i = 0;
+			tx_swbd = tx_ring->tx_swbd;
+			txbd = ENETC_TXBD(*tx_ring, 0);
+		}
+		prefetchw(txbd);
+
+		if (do_vlan) {
+			temp_bd.ext.vid = cpu_to_le16(skb_vlan_tag_get(skb));
+			temp_bd.ext.tpid = 0; /* < C-TAG */
+			e_flags |= ENETC_TXBD_E_FLAGS_VLAN_INS;
+		}
+
+		if (do_tstamp) {
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+			e_flags |= ENETC_TXBD_E_FLAGS_TWO_STEP_PTP;
+		}
+
+		temp_bd.ext.e_flags = e_flags;
+		count++;
+	}
+
+	frag = &skb_shinfo(skb)->frags[0];
+	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++, frag++) {
+		len = skb_frag_size(frag);
+		dma = skb_frag_dma_map(tx_ring->dev, frag, 0, len,
+				       DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_ring->dev, dma))
+			goto dma_err;
+
+		*txbd = temp_bd;
+		enetc_clear_tx_bd(&temp_bd);
+
+		flags = 0;
+		tx_swbd++;
+		txbd++;
+		i++;
+		if (unlikely(i == tx_ring->bd_count)) {
+			i = 0;
+			tx_swbd = tx_ring->tx_swbd;
+			txbd = ENETC_TXBD(*tx_ring, 0);
+		}
+		prefetchw(txbd);
+
+		temp_bd.addr = cpu_to_le64(dma);
+		temp_bd.buf_len = cpu_to_le16(len);
+
+		tx_swbd->dma = dma;
+		tx_swbd->len = len;
+		tx_swbd->is_dma_page = 1;
+		count++;
+	}
+
+	/* last BD needs 'F' bit set */
+	flags |= ENETC_TXBD_FLAGS_F;
+	temp_bd.flags = flags;
+	*txbd = temp_bd;
+
+	tx_ring->tx_swbd[i].skb = skb;
+
+	enetc_bdr_idx_inc(tx_ring, &i);
+	tx_ring->next_to_use = i;
+
+	/* let H/W know BD ring has been updated */
+	enetc_wr_reg(tx_ring->tpir, i); /* includes wmb() */
+
+	return count;
+
+dma_err:
+	dev_err(tx_ring->dev, "DMA map error");
+
+	do {
+		tx_swbd = &tx_ring->tx_swbd[i];
+		enetc_free_tx_skb(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	} while (count--);
+
+	return 0;
+}
+
+static irqreturn_t enetc_msix(int irq, void *data)
+{
+	struct enetc_int_vector	*v = data;
+	int i;
+
+	/* disable interrupts */
+	enetc_wr_reg(v->rbier, 0);
+
+	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i), 0);
+
+	napi_schedule_irqoff(&v->napi);
+
+	return IRQ_HANDLED;
+}
+
+static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget);
+static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
+			       struct napi_struct *napi, int work_limit);
+
+static int enetc_poll(struct napi_struct *napi, int budget)
+{
+	struct enetc_int_vector
+		*v = container_of(napi, struct enetc_int_vector, napi);
+	bool complete = true;
+	int work_done;
+	int i;
+
+	for (i = 0; i < v->count_tx_rings; i++)
+		if (!enetc_clean_tx_ring(&v->tx_ring[i], budget))
+			complete = false;
+
+	work_done = enetc_clean_rx_ring(&v->rx_ring, napi, budget);
+	if (work_done == budget)
+		complete = false;
+
+	if (!complete)
+		return budget;
+
+	napi_complete_done(napi, work_done);
+
+	/* enable interrupts */
+	enetc_wr_reg(v->rbier, ENETC_RBIER_RXTIE);
+
+	for_each_set_bit(i, &v->tx_rings_map, v->count_tx_rings)
+		enetc_wr_reg(v->tbier_base + ENETC_BDR_OFF(i),
+			     ENETC_TBIER_TXTIE);
+
+	return work_done;
+}
+
+static int enetc_bd_ready_count(struct enetc_bdr *tx_ring, int ci)
+{
+	int pi = enetc_rd_reg(tx_ring->tcir) & ENETC_TBCIR_IDX_MASK;
+
+	return pi >= ci ? pi - ci : tx_ring->bd_count - ci + pi;
+}
+
+static bool enetc_clean_tx_ring(struct enetc_bdr *tx_ring, int napi_budget)
+{
+	struct net_device *ndev = tx_ring->ndev;
+	int tx_frm_cnt = 0, tx_byte_cnt = 0;
+	struct enetc_tx_swbd *tx_swbd;
+	int i, bds_to_clean;
+
+	i = tx_ring->next_to_clean;
+	tx_swbd = &tx_ring->tx_swbd[i];
+	bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+
+	while (bds_to_clean && tx_frm_cnt < ENETC_DEFAULT_TX_WORK) {
+		bool is_eof = !!tx_swbd->skb;
+
+		enetc_unmap_tx_buff(tx_ring, tx_swbd);
+		if (is_eof) {
+			napi_consume_skb(tx_swbd->skb, napi_budget);
+			tx_swbd->skb = NULL;
+		}
+
+		tx_byte_cnt += tx_swbd->len;
+
+		bds_to_clean--;
+		tx_swbd++;
+		i++;
+		if (unlikely(i == tx_ring->bd_count)) {
+			i = 0;
+			tx_swbd = tx_ring->tx_swbd;
+		}
+
+		/* BD iteration loop end */
+		if (is_eof) {
+			tx_frm_cnt++;
+			/* re-arm interrupt source */
+			enetc_wr_reg(tx_ring->idr, BIT(tx_ring->index) |
+				     BIT(16 + tx_ring->index));
+		}
+
+		if (unlikely(!bds_to_clean))
+			bds_to_clean = enetc_bd_ready_count(tx_ring, i);
+	}
+
+	tx_ring->next_to_clean = i;
+	tx_ring->stats.packets += tx_frm_cnt;
+	tx_ring->stats.bytes += tx_byte_cnt;
+
+	if (unlikely(tx_frm_cnt && netif_carrier_ok(ndev) &&
+		     __netif_subqueue_stopped(ndev, tx_ring->index) &&
+		     (enetc_bd_unused(tx_ring) >= ENETC_TXBDS_MAX_NEEDED))) {
+		netif_wake_subqueue(ndev, tx_ring->index);
+	}
+
+	return tx_frm_cnt != ENETC_DEFAULT_TX_WORK;
+}
+
+static bool enetc_new_page(struct enetc_bdr *rx_ring,
+			   struct enetc_rx_swbd *rx_swbd)
+{
+	struct page *page;
+	dma_addr_t addr;
+
+	page = dev_alloc_page();
+	if (unlikely(!page))
+		return false;
+
+	addr = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(rx_ring->dev, addr))) {
+		__free_page(page);
+
+		return false;
+	}
+
+	rx_swbd->dma = addr;
+	rx_swbd->page = page;
+	rx_swbd->page_offset = ENETC_RXB_PAD;
+
+	return true;
+}
+
+static int enetc_refill_rx_ring(struct enetc_bdr *rx_ring, const int buff_cnt)
+{
+	struct enetc_rx_swbd *rx_swbd;
+	union enetc_rx_bd *rxbd;
+	int i, j;
+
+	i = rx_ring->next_to_use;
+	rx_swbd = &rx_ring->rx_swbd[i];
+	rxbd = ENETC_RXBD(*rx_ring, i);
+
+	for (j = 0; j < buff_cnt; j++) {
+		/* try reuse page */
+		if (unlikely(!rx_swbd->page)) {
+			if (unlikely(!enetc_new_page(rx_ring, rx_swbd))) {
+				rx_ring->stats.rx_alloc_errs++;
+				break;
+			}
+		}
+
+		/* update RxBD */
+		rxbd->w.addr = cpu_to_le64(rx_swbd->dma +
+					   rx_swbd->page_offset);
+		/* clear 'R" as well */
+		rxbd->r.lstatus = 0;
+
+		rx_swbd++;
+		rxbd++;
+		i++;
+		if (unlikely(i == rx_ring->bd_count)) {
+			i = 0;
+			rx_swbd = rx_ring->rx_swbd;
+			rxbd = ENETC_RXBD(*rx_ring, 0);
+		}
+	}
+
+	if (likely(j)) {
+		rx_ring->next_to_alloc = i; /* keep track from page reuse */
+		rx_ring->next_to_use = i;
+		/* update ENETC's consumer index */
+		enetc_wr_reg(rx_ring->rcir, i);
+	}
+
+	return j;
+}
+
+static void enetc_get_offloads(struct enetc_bdr *rx_ring,
+			       union enetc_rx_bd *rxbd, struct sk_buff *skb)
+{
+	/* TODO: add tstamp, hashing */
+	if (rx_ring->ndev->features & NETIF_F_RXCSUM) {
+		u16 inet_csum = le16_to_cpu(rxbd->r.inet_csum);
+
+		skb->csum = csum_unfold((__force __sum16)~htons(inet_csum));
+		skb->ip_summed = CHECKSUM_COMPLETE;
+	}
+
+	/* copy VLAN to skb, if one is extracted, for now we assume it's a
+	 * standard TPID, but HW also supports custom values
+	 */
+	if (le16_to_cpu(rxbd->r.flags) & ENETC_RXBD_FLAG_VLAN)
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
+				       le16_to_cpu(rxbd->r.vlan_opt));
+}
+
+static void enetc_process_skb(struct enetc_bdr *rx_ring,
+			      struct sk_buff *skb)
+{
+	skb_record_rx_queue(skb, rx_ring->index);
+	skb->protocol = eth_type_trans(skb, rx_ring->ndev);
+}
+
+static bool enetc_page_reusable(struct page *page)
+{
+	return (!page_is_pfmemalloc(page) && page_ref_count(page) == 1);
+}
+
+static void enetc_reuse_page(struct enetc_bdr *rx_ring,
+			     struct enetc_rx_swbd *old)
+{
+	struct enetc_rx_swbd *new;
+
+	new = &rx_ring->rx_swbd[rx_ring->next_to_alloc];
+
+	/* next buf that may reuse a page */
+	enetc_bdr_idx_inc(rx_ring, &rx_ring->next_to_alloc);
+
+	/* copy page reference */
+	*new = *old;
+}
+
+static struct enetc_rx_swbd *enetc_get_rx_buff(struct enetc_bdr *rx_ring,
+					       int i, u16 size)
+{
+	struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[i];
+
+	dma_sync_single_range_for_cpu(rx_ring->dev, rx_swbd->dma,
+				      rx_swbd->page_offset,
+				      size, DMA_FROM_DEVICE);
+	return rx_swbd;
+}
+
+static void enetc_put_rx_buff(struct enetc_bdr *rx_ring,
+			      struct enetc_rx_swbd *rx_swbd)
+{
+	if (likely(enetc_page_reusable(rx_swbd->page))) {
+		rx_swbd->page_offset ^= ENETC_RXB_TRUESIZE;
+		page_ref_inc(rx_swbd->page);
+
+		enetc_reuse_page(rx_ring, rx_swbd);
+
+		/* sync for use by the device */
+		dma_sync_single_range_for_device(rx_ring->dev, rx_swbd->dma,
+						 rx_swbd->page_offset,
+						 ENETC_RXB_DMA_SIZE,
+						 DMA_FROM_DEVICE);
+	} else {
+		dma_unmap_page(rx_ring->dev, rx_swbd->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+	}
+
+	rx_swbd->page = NULL;
+}
+
+static struct sk_buff *enetc_map_rx_buff_to_skb(struct enetc_bdr *rx_ring,
+						int i, u16 size)
+{
+	struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size);
+	struct sk_buff *skb;
+	void *ba;
+
+	ba = page_address(rx_swbd->page) + rx_swbd->page_offset;
+	skb = build_skb(ba - ENETC_RXB_PAD, ENETC_RXB_TRUESIZE);
+	if (unlikely(!skb)) {
+		rx_ring->stats.rx_alloc_errs++;
+		return NULL;
+	}
+
+	skb_reserve(skb, ENETC_RXB_PAD);
+	__skb_put(skb, size);
+
+	enetc_put_rx_buff(rx_ring, rx_swbd);
+
+	return skb;
+}
+
+static void enetc_add_rx_buff_to_skb(struct enetc_bdr *rx_ring, int i,
+				     u16 size, struct sk_buff *skb)
+{
+	struct enetc_rx_swbd *rx_swbd = enetc_get_rx_buff(rx_ring, i, size);
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_swbd->page,
+			rx_swbd->page_offset, size, ENETC_RXB_TRUESIZE);
+
+	enetc_put_rx_buff(rx_ring, rx_swbd);
+}
+
+#define ENETC_RXBD_BUNDLE 16 /* # of BDs to update at once */
+
+static int enetc_clean_rx_ring(struct enetc_bdr *rx_ring,
+			       struct napi_struct *napi, int work_limit)
+{
+	int rx_frm_cnt = 0, rx_byte_cnt = 0;
+	int cleaned_cnt, i;
+
+	cleaned_cnt = enetc_bd_unused(rx_ring);
+	/* next descriptor to process */
+	i = rx_ring->next_to_clean;
+
+	while (likely(rx_frm_cnt < work_limit)) {
+		union enetc_rx_bd *rxbd;
+		struct sk_buff *skb;
+		u32 bd_status;
+		u16 size;
+
+		if (cleaned_cnt >= ENETC_RXBD_BUNDLE) {
+			int count = enetc_refill_rx_ring(rx_ring, cleaned_cnt);
+
+			cleaned_cnt -= count;
+		}
+
+		rxbd = ENETC_RXBD(*rx_ring, i);
+		bd_status = le32_to_cpu(rxbd->r.lstatus);
+		if (!bd_status)
+			break;
+
+		enetc_wr_reg(rx_ring->idr, BIT(rx_ring->index));
+		dma_rmb(); /* for reading other rxbd fields */
+		size = le16_to_cpu(rxbd->r.buf_len);
+		skb = enetc_map_rx_buff_to_skb(rx_ring, i, size);
+		if (!skb)
+			break;
+
+		enetc_get_offloads(rx_ring, rxbd, skb);
+
+		cleaned_cnt++;
+		rxbd++;
+		i++;
+		if (unlikely(i == rx_ring->bd_count)) {
+			i = 0;
+			rxbd = ENETC_RXBD(*rx_ring, 0);
+		}
+
+		if (unlikely(bd_status &
+			     ENETC_RXBD_LSTATUS(ENETC_RXBD_ERR_MASK))) {
+			dev_kfree_skb(skb);
+			while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
+				dma_rmb();
+				bd_status = le32_to_cpu(rxbd->r.lstatus);
+				rxbd++;
+				i++;
+				if (unlikely(i == rx_ring->bd_count)) {
+					i = 0;
+					rxbd = ENETC_RXBD(*rx_ring, 0);
+				}
+			}
+
+			rx_ring->ndev->stats.rx_dropped++;
+			rx_ring->ndev->stats.rx_errors++;
+
+			break;
+		}
+
+		/* not last BD in frame? */
+		while (!(bd_status & ENETC_RXBD_LSTATUS_F)) {
+			bd_status = le32_to_cpu(rxbd->r.lstatus);
+			size = ENETC_RXB_DMA_SIZE;
+
+			if (bd_status & ENETC_RXBD_LSTATUS_F) {
+				dma_rmb();
+				size = le16_to_cpu(rxbd->r.buf_len);
+			}
+
+			enetc_add_rx_buff_to_skb(rx_ring, i, size, skb);
+
+			cleaned_cnt++;
+			rxbd++;
+			i++;
+			if (unlikely(i == rx_ring->bd_count)) {
+				i = 0;
+				rxbd = ENETC_RXBD(*rx_ring, 0);
+			}
+		}
+
+		rx_byte_cnt += skb->len;
+
+		enetc_process_skb(rx_ring, skb);
+
+		napi_gro_receive(napi, skb);
+
+		rx_frm_cnt++;
+	}
+
+	rx_ring->next_to_clean = i;
+
+	rx_ring->stats.packets += rx_frm_cnt;
+	rx_ring->stats.bytes += rx_byte_cnt;
+
+	return rx_frm_cnt;
+}
+
+/* Probing and Init */
+#define ENETC_MAX_RFS_SIZE 64
+void enetc_get_si_caps(struct enetc_si *si)
+{
+	struct enetc_hw *hw = &si->hw;
+	u32 val;
+
+	/* find out how many of various resources we have to work with */
+	val = enetc_rd(hw, ENETC_SICAPR0);
+	si->num_rx_rings = (val >> 16) & 0xff;
+	si->num_tx_rings = val & 0xff;
+
+	val = enetc_rd(hw, ENETC_SIRFSCAPR);
+	si->num_fs_entries = ENETC_SIRFSCAPR_GET_NUM_RFS(val);
+	si->num_fs_entries = min(si->num_fs_entries, ENETC_MAX_RFS_SIZE);
+
+	si->num_rss = 0;
+	val = enetc_rd(hw, ENETC_SIPCAPR0);
+	if (val & ENETC_SIPCAPR0_RSS) {
+		val = enetc_rd(hw, ENETC_SIRSSCAPR);
+		si->num_rss = ENETC_SIRSSCAPR_GET_NUM_RSS(val);
+	}
+}
+
+static int enetc_dma_alloc_bdr(struct enetc_bdr *r, size_t bd_size)
+{
+	r->bd_base = dma_alloc_coherent(r->dev, r->bd_count * bd_size,
+					&r->bd_dma_base, GFP_KERNEL);
+	if (!r->bd_base)
+		return -ENOMEM;
+
+	/* h/w requires 128B alignment */
+	if (!IS_ALIGNED(r->bd_dma_base, 128)) {
+		dma_free_coherent(r->dev, r->bd_count * bd_size, r->bd_base,
+				  r->bd_dma_base);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int enetc_alloc_txbdr(struct enetc_bdr *txr)
+{
+	int err;
+
+	txr->tx_swbd = vzalloc(txr->bd_count * sizeof(struct enetc_tx_swbd));
+	if (!txr->tx_swbd)
+		return -ENOMEM;
+
+	err = enetc_dma_alloc_bdr(txr, sizeof(union enetc_tx_bd));
+	if (err) {
+		vfree(txr->tx_swbd);
+		return err;
+	}
+
+	txr->next_to_clean = 0;
+	txr->next_to_use = 0;
+
+	return 0;
+}
+
+static void enetc_free_txbdr(struct enetc_bdr *txr)
+{
+	int size, i;
+
+	for (i = 0; i < txr->bd_count; i++)
+		enetc_free_tx_skb(txr, &txr->tx_swbd[i]);
+
+	size = txr->bd_count * sizeof(union enetc_tx_bd);
+
+	dma_free_coherent(txr->dev, size, txr->bd_base, txr->bd_dma_base);
+	txr->bd_base = NULL;
+
+	vfree(txr->tx_swbd);
+	txr->tx_swbd = NULL;
+}
+
+static int enetc_alloc_tx_resources(struct enetc_ndev_priv *priv)
+{
+	int i, err;
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		err = enetc_alloc_txbdr(priv->tx_ring[i]);
+
+		if (err)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	while (i-- > 0)
+		enetc_free_txbdr(priv->tx_ring[i]);
+
+	return err;
+}
+
+static void enetc_free_tx_resources(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_free_txbdr(priv->tx_ring[i]);
+}
+
+static int enetc_alloc_rxbdr(struct enetc_bdr *rxr)
+{
+	int err;
+
+	rxr->rx_swbd = vzalloc(rxr->bd_count * sizeof(struct enetc_rx_swbd));
+	if (!rxr->rx_swbd)
+		return -ENOMEM;
+
+	err = enetc_dma_alloc_bdr(rxr, sizeof(union enetc_rx_bd));
+	if (err) {
+		vfree(rxr->rx_swbd);
+		return err;
+	}
+
+	rxr->next_to_clean = 0;
+	rxr->next_to_use = 0;
+	rxr->next_to_alloc = 0;
+
+	return 0;
+}
+
+static void enetc_free_rxbdr(struct enetc_bdr *rxr)
+{
+	int size;
+
+	size = rxr->bd_count * sizeof(union enetc_rx_bd);
+
+	dma_free_coherent(rxr->dev, size, rxr->bd_base, rxr->bd_dma_base);
+	rxr->bd_base = NULL;
+
+	vfree(rxr->rx_swbd);
+	rxr->rx_swbd = NULL;
+}
+
+static int enetc_alloc_rx_resources(struct enetc_ndev_priv *priv)
+{
+	int i, err;
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		err = enetc_alloc_rxbdr(priv->rx_ring[i]);
+
+		if (err)
+			goto fail;
+	}
+
+	return 0;
+
+fail:
+	while (i-- > 0)
+		enetc_free_rxbdr(priv->rx_ring[i]);
+
+	return err;
+}
+
+static void enetc_free_rx_resources(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_free_rxbdr(priv->rx_ring[i]);
+}
+
+static void enetc_free_tx_ring(struct enetc_bdr *tx_ring)
+{
+	int i;
+
+	if (!tx_ring->tx_swbd)
+		return;
+
+	for (i = 0; i < tx_ring->bd_count; i++) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_skb(tx_ring, tx_swbd);
+	}
+
+	tx_ring->next_to_clean = 0;
+	tx_ring->next_to_use = 0;
+}
+
+static void enetc_free_rx_ring(struct enetc_bdr *rx_ring)
+{
+	int i;
+
+	if (!rx_ring->rx_swbd)
+		return;
+
+	for (i = 0; i < rx_ring->bd_count; i++) {
+		struct enetc_rx_swbd *rx_swbd = &rx_ring->rx_swbd[i];
+
+		if (!rx_swbd->page)
+			continue;
+
+		dma_unmap_page(rx_ring->dev, rx_swbd->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+		__free_page(rx_swbd->page);
+		rx_swbd->page = NULL;
+	}
+
+	rx_ring->next_to_clean = 0;
+	rx_ring->next_to_use = 0;
+	rx_ring->next_to_alloc = 0;
+}
+
+static void enetc_free_rxtx_rings(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_free_rx_ring(priv->rx_ring[i]);
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_free_tx_ring(priv->tx_ring[i]);
+}
+
+static int enetc_alloc_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+{
+	int size = cbdr->bd_count * sizeof(struct enetc_cbd);
+
+	cbdr->bd_base = dma_alloc_coherent(dev, size, &cbdr->bd_dma_base,
+					   GFP_KERNEL);
+	if (!cbdr->bd_base)
+		return -ENOMEM;
+
+	/* h/w requires 128B alignment */
+	if (!IS_ALIGNED(cbdr->bd_dma_base, 128)) {
+		dma_free_coherent(dev, size, cbdr->bd_base, cbdr->bd_dma_base);
+		return -EINVAL;
+	}
+
+	cbdr->next_to_clean = 0;
+	cbdr->next_to_use = 0;
+
+	return 0;
+}
+
+static void enetc_free_cbdr(struct device *dev, struct enetc_cbdr *cbdr)
+{
+	int size = cbdr->bd_count * sizeof(struct enetc_cbd);
+
+	dma_free_coherent(dev, size, cbdr->bd_base, cbdr->bd_dma_base);
+	cbdr->bd_base = NULL;
+}
+
+static void enetc_setup_cbdr(struct enetc_hw *hw, struct enetc_cbdr *cbdr)
+{
+	/* set CBDR cache attributes */
+	enetc_wr(hw, ENETC_SICAR2,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+
+	enetc_wr(hw, ENETC_SICBDRBAR0, lower_32_bits(cbdr->bd_dma_base));
+	enetc_wr(hw, ENETC_SICBDRBAR1, upper_32_bits(cbdr->bd_dma_base));
+	enetc_wr(hw, ENETC_SICBDRLENR, ENETC_RTBLENR_LEN(cbdr->bd_count));
+
+	enetc_wr(hw, ENETC_SICBDRPIR, 0);
+	enetc_wr(hw, ENETC_SICBDRCIR, 0);
+
+	/* enable ring */
+	enetc_wr(hw, ENETC_SICBDRMR, BIT(31));
+
+	cbdr->pir = hw->reg + ENETC_SICBDRPIR;
+	cbdr->cir = hw->reg + ENETC_SICBDRCIR;
+}
+
+static void enetc_clear_cbdr(struct enetc_hw *hw)
+{
+	enetc_wr(hw, ENETC_SICBDRMR, 0);
+}
+
+static int enetc_setup_default_rss_table(struct enetc_si *si, int num_groups)
+{
+	int *rss_table;
+	int i;
+
+	rss_table = kmalloc_array(si->num_rss, sizeof(*rss_table), GFP_KERNEL);
+	if (!rss_table)
+		return -ENOMEM;
+
+	/* Set up RSS table defaults */
+	for (i = 0; i < si->num_rss; i++)
+		rss_table[i] = i % num_groups;
+
+	enetc_set_rss_table(si, rss_table, si->num_rss);
+
+	kfree(rss_table);
+
+	return 0;
+}
+
+static int enetc_configure_si(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+	struct enetc_hw *hw = &si->hw;
+	int err;
+
+	enetc_setup_cbdr(hw, &si->cbd_ring);
+	/* set SI cache attributes */
+	enetc_wr(hw, ENETC_SICAR0,
+		 ENETC_SICAR_RD_COHERENT | ENETC_SICAR_WR_COHERENT);
+	enetc_wr(hw, ENETC_SICAR1, ENETC_SICAR_MSI);
+	/* enable SI */
+	enetc_wr(hw, ENETC_SIMR, ENETC_SIMR_EN);
+
+	if (si->num_rss) {
+		err = enetc_setup_default_rss_table(si, priv->num_rx_rings);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void enetc_init_si_rings_params(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+	int cpus = num_online_cpus();
+
+	priv->tx_bd_count = ENETC_BDR_DEFAULT_SIZE;
+	priv->rx_bd_count = ENETC_BDR_DEFAULT_SIZE;
+
+	/* Enable all available TX rings in order to configure as many
+	 * priorities as possible, when needed.
+	 * TODO: Make # of TX rings run-time configurable
+	 */
+	priv->num_rx_rings = min_t(int, cpus, si->num_rx_rings);
+	priv->num_tx_rings = si->num_tx_rings;
+	priv->bdr_int_num = cpus;
+
+	/* SI specific */
+	si->cbd_ring.bd_count = ENETC_CBDR_DEFAULT_SIZE;
+}
+
+int enetc_alloc_si_resources(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+	int err;
+
+	err = enetc_alloc_cbdr(priv->dev, &si->cbd_ring);
+	if (err)
+		return err;
+
+	priv->cls_rules = kcalloc(si->num_fs_entries, sizeof(*priv->cls_rules),
+				  GFP_KERNEL);
+	if (!priv->cls_rules) {
+		err = -ENOMEM;
+		goto err_alloc_cls;
+	}
+
+	err = enetc_configure_si(priv);
+	if (err)
+		goto err_config_si;
+
+	return 0;
+
+err_config_si:
+	kfree(priv->cls_rules);
+err_alloc_cls:
+	enetc_clear_cbdr(&si->hw);
+	enetc_free_cbdr(priv->dev, &si->cbd_ring);
+
+	return err;
+}
+
+void enetc_free_si_resources(struct enetc_ndev_priv *priv)
+{
+	struct enetc_si *si = priv->si;
+
+	enetc_clear_cbdr(&si->hw);
+	enetc_free_cbdr(priv->dev, &si->cbd_ring);
+
+	kfree(priv->cls_rules);
+}
+
+static void enetc_setup_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
+{
+	int idx = tx_ring->index;
+	u32 tbmr;
+
+	enetc_txbdr_wr(hw, idx, ENETC_TBBAR0,
+		       lower_32_bits(tx_ring->bd_dma_base));
+
+	enetc_txbdr_wr(hw, idx, ENETC_TBBAR1,
+		       upper_32_bits(tx_ring->bd_dma_base));
+
+	WARN_ON(!IS_ALIGNED(tx_ring->bd_count, 64)); /* multiple of 64 */
+	enetc_txbdr_wr(hw, idx, ENETC_TBLENR,
+		       ENETC_RTBLENR_LEN(tx_ring->bd_count));
+
+	/* clearing PI/CI registers for Tx not supported, adjust sw indexes */
+	tx_ring->next_to_use = enetc_txbdr_rd(hw, idx, ENETC_TBPIR);
+	tx_ring->next_to_clean = enetc_txbdr_rd(hw, idx, ENETC_TBCIR);
+
+	/* enable Tx ints by setting pkt thr to 1 */
+	enetc_txbdr_wr(hw, idx, ENETC_TBICIR0, ENETC_TBICIR0_ICEN | 0x1);
+
+	tbmr = ENETC_TBMR_EN;
+	if (tx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_TX)
+		tbmr |= ENETC_TBMR_VIH;
+
+	/* enable ring */
+	enetc_txbdr_wr(hw, idx, ENETC_TBMR, tbmr);
+
+	tx_ring->tpir = hw->reg + ENETC_BDR(TX, idx, ENETC_TBPIR);
+	tx_ring->tcir = hw->reg + ENETC_BDR(TX, idx, ENETC_TBCIR);
+	tx_ring->idr = hw->reg + ENETC_SITXIDR;
+}
+
+static void enetc_setup_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
+{
+	int idx = rx_ring->index;
+	u32 rbmr;
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBBAR0,
+		       lower_32_bits(rx_ring->bd_dma_base));
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBBAR1,
+		       upper_32_bits(rx_ring->bd_dma_base));
+
+	WARN_ON(!IS_ALIGNED(rx_ring->bd_count, 64)); /* multiple of 64 */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBLENR,
+		       ENETC_RTBLENR_LEN(rx_ring->bd_count));
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBBSR, ENETC_RXB_DMA_SIZE);
+
+	enetc_rxbdr_wr(hw, idx, ENETC_RBPIR, 0);
+
+	/* enable Rx ints by setting pkt thr to 1 */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBICIR0, ENETC_RBICIR0_ICEN | 0x1);
+
+	rbmr = ENETC_RBMR_EN;
+	if (rx_ring->ndev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		rbmr |= ENETC_RBMR_VTE;
+
+	rx_ring->rcir = hw->reg + ENETC_BDR(RX, idx, ENETC_RBCIR);
+	rx_ring->idr = hw->reg + ENETC_SIRXIDR;
+
+	enetc_refill_rx_ring(rx_ring, enetc_bd_unused(rx_ring));
+
+	/* enable ring */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, rbmr);
+}
+
+static void enetc_setup_bdrs(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_setup_txbdr(&priv->si->hw, priv->tx_ring[i]);
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_setup_rxbdr(&priv->si->hw, priv->rx_ring[i]);
+}
+
+static void enetc_clear_rxbdr(struct enetc_hw *hw, struct enetc_bdr *rx_ring)
+{
+	int idx = rx_ring->index;
+
+	/* disable EN bit on ring */
+	enetc_rxbdr_wr(hw, idx, ENETC_RBMR, 0);
+}
+
+static void enetc_clear_txbdr(struct enetc_hw *hw, struct enetc_bdr *tx_ring)
+{
+	int delay = 8, timeout = 100;
+	int idx = tx_ring->index;
+
+	/* disable EN bit on ring */
+	enetc_txbdr_wr(hw, idx, ENETC_TBMR, 0);
+
+	/* wait for busy to clear */
+	while (delay < timeout &&
+	       enetc_txbdr_rd(hw, idx, ENETC_TBSR) & ENETC_TBSR_BUSY) {
+		msleep(delay);
+		delay *= 2;
+	}
+
+	if (delay >= timeout)
+		netdev_warn(tx_ring->ndev, "timeout for tx ring #%d clear\n",
+			    idx);
+}
+
+static void enetc_clear_bdrs(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_clear_txbdr(&priv->si->hw, priv->tx_ring[i]);
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_clear_rxbdr(&priv->si->hw, priv->rx_ring[i]);
+
+	udelay(1);
+}
+
+static int enetc_setup_irqs(struct enetc_ndev_priv *priv)
+{
+	struct pci_dev *pdev = priv->si->pdev;
+	cpumask_t cpu_mask;
+	int i, j, err;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i);
+		struct enetc_int_vector *v = priv->int_vector[i];
+		int entry = ENETC_BDR_INT_BASE_IDX + i;
+		struct enetc_hw *hw = &priv->si->hw;
+
+		snprintf(v->name, sizeof(v->name), "%s-rxtx%d",
+			 priv->ndev->name, i);
+		err = request_irq(irq, enetc_msix, 0, v->name, v);
+		if (err) {
+			dev_err(priv->dev, "request_irq() failed!\n");
+			goto irq_err;
+		}
+
+		v->tbier_base = hw->reg + ENETC_BDR(TX, 0, ENETC_TBIER);
+		v->rbier = hw->reg + ENETC_BDR(RX, i, ENETC_RBIER);
+
+		enetc_wr(hw, ENETC_SIMSIRRV(i), entry);
+
+		for (j = 0; j < v->count_tx_rings; j++) {
+			int idx = v->tx_ring[j].index;
+
+			enetc_wr(hw, ENETC_SIMSITRV(idx), entry);
+		}
+		cpumask_clear(&cpu_mask);
+		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
+		irq_set_affinity_hint(irq, &cpu_mask);
+	}
+
+	return 0;
+
+irq_err:
+	while (i--) {
+		int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i);
+
+		irq_set_affinity_hint(irq, NULL);
+		free_irq(irq, priv->int_vector[i]);
+	}
+
+	return err;
+}
+
+static void enetc_free_irqs(struct enetc_ndev_priv *priv)
+{
+	struct pci_dev *pdev = priv->si->pdev;
+	int i;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		int irq = pci_irq_vector(pdev, ENETC_BDR_INT_BASE_IDX + i);
+
+		irq_set_affinity_hint(irq, NULL);
+		free_irq(irq, priv->int_vector[i]);
+	}
+}
+
+static void enetc_enable_interrupts(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	/* enable Tx & Rx event indication */
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		enetc_rxbdr_wr(&priv->si->hw, i,
+			       ENETC_RBIER, ENETC_RBIER_RXTIE);
+	}
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		enetc_txbdr_wr(&priv->si->hw, i,
+			       ENETC_TBIER, ENETC_TBIER_TXTIE);
+	}
+}
+
+static void enetc_disable_interrupts(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		enetc_txbdr_wr(&priv->si->hw, i, ENETC_TBIER, 0);
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		enetc_rxbdr_wr(&priv->si->hw, i, ENETC_RBIER, 0);
+}
+
+static void adjust_link(struct net_device *ndev)
+{
+	struct phy_device *phydev = ndev->phydev;
+
+	phy_print_status(phydev);
+}
+
+static int enetc_phy_connect(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct phy_device *phydev;
+
+	if (!priv->phy_node)
+		return 0; /* phy-less mode */
+
+	phydev = of_phy_connect(ndev, priv->phy_node, &adjust_link,
+				0, priv->if_mode);
+	if (!phydev) {
+		dev_err(&ndev->dev, "could not attach to PHY\n");
+		return -ENODEV;
+	}
+
+	phy_attached_info(phydev);
+
+	return 0;
+}
+
+int enetc_open(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i, err;
+
+	err = enetc_setup_irqs(priv);
+	if (err)
+		return err;
+
+	err = enetc_phy_connect(ndev);
+	if (err)
+		goto err_phy_connect;
+
+	err = enetc_alloc_tx_resources(priv);
+	if (err)
+		goto err_alloc_tx;
+
+	err = enetc_alloc_rx_resources(priv);
+	if (err)
+		goto err_alloc_rx;
+
+	enetc_setup_bdrs(priv);
+
+	err = netif_set_real_num_tx_queues(ndev, priv->num_tx_rings);
+	if (err)
+		goto err_set_queues;
+
+	err = netif_set_real_num_rx_queues(ndev, priv->num_rx_rings);
+	if (err)
+		goto err_set_queues;
+
+	for (i = 0; i < priv->bdr_int_num; i++)
+		napi_enable(&priv->int_vector[i]->napi);
+
+	enetc_enable_interrupts(priv);
+
+	if (ndev->phydev)
+		phy_start(ndev->phydev);
+	else
+		netif_carrier_on(ndev);
+
+	netif_tx_start_all_queues(ndev);
+
+	return 0;
+
+err_set_queues:
+	enetc_free_rx_resources(priv);
+err_alloc_rx:
+	enetc_free_tx_resources(priv);
+err_alloc_tx:
+	if (ndev->phydev)
+		phy_disconnect(ndev->phydev);
+err_phy_connect:
+	enetc_free_irqs(priv);
+
+	return err;
+}
+
+int enetc_close(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i;
+
+	netif_tx_stop_all_queues(ndev);
+
+	if (ndev->phydev) {
+		phy_stop(ndev->phydev);
+		phy_disconnect(ndev->phydev);
+	} else {
+		netif_carrier_off(ndev);
+	}
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		napi_synchronize(&priv->int_vector[i]->napi);
+		napi_disable(&priv->int_vector[i]->napi);
+	}
+
+	enetc_disable_interrupts(priv);
+	enetc_clear_bdrs(priv);
+
+	enetc_free_rxtx_rings(priv);
+	enetc_free_rx_resources(priv);
+	enetc_free_tx_resources(priv);
+	enetc_free_irqs(priv);
+
+	return 0;
+}
+
+struct net_device_stats *enetc_get_stats(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
+	unsigned long packets = 0, bytes = 0;
+	int i;
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		packets += priv->rx_ring[i]->stats.packets;
+		bytes	+= priv->rx_ring[i]->stats.bytes;
+	}
+
+	stats->rx_packets = packets;
+	stats->rx_bytes = bytes;
+	bytes = 0;
+	packets = 0;
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		packets += priv->tx_ring[i]->stats.packets;
+		bytes	+= priv->tx_ring[i]->stats.bytes;
+	}
+
+	stats->tx_packets = packets;
+	stats->tx_bytes = bytes;
+
+	return stats;
+}
+
+static int enetc_set_rss(struct net_device *ndev, int en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	enetc_wr(hw, ENETC_SIRBGCR, priv->num_rx_rings);
+
+	reg = enetc_rd(hw, ENETC_SIMR);
+	reg &= ~ENETC_SIMR_RSSE;
+	reg |= (en) ? ENETC_SIMR_RSSE : 0;
+	enetc_wr(hw, ENETC_SIMR, reg);
+
+	return 0;
+}
+
+int enetc_set_features(struct net_device *ndev,
+		       netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+
+	if (changed & NETIF_F_RXHASH)
+		enetc_set_rss(ndev, !!(features & NETIF_F_RXHASH));
+
+	return 0;
+}
+
+int enetc_alloc_msix(struct enetc_ndev_priv *priv)
+{
+	struct pci_dev *pdev = priv->si->pdev;
+	int size, v_tx_rings;
+	int i, n, err, nvec;
+
+	nvec = ENETC_BDR_INT_BASE_IDX + priv->bdr_int_num;
+	/* allocate MSIX for both messaging and Rx/Tx interrupts */
+	n = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX);
+
+	if (n < 0)
+		return n;
+
+	if (n != nvec)
+		return -EPERM;
+
+	/* # of tx rings per int vector */
+	v_tx_rings = priv->num_tx_rings / priv->bdr_int_num;
+	size = sizeof(struct enetc_int_vector) +
+	       sizeof(struct enetc_bdr) * v_tx_rings;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		struct enetc_int_vector *v;
+		struct enetc_bdr *bdr;
+		int j;
+
+		v = kzalloc(size, GFP_KERNEL);
+		if (!v) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		priv->int_vector[i] = v;
+
+		netif_napi_add(priv->ndev, &v->napi, enetc_poll,
+			       NAPI_POLL_WEIGHT);
+		v->count_tx_rings = v_tx_rings;
+
+		for (j = 0; j < v_tx_rings; j++) {
+			int idx;
+
+			/* default tx ring mapping policy */
+			if (priv->bdr_int_num == ENETC_MAX_BDR_INT)
+				idx = 2 * j + i; /* 2 CPUs */
+			else
+				idx = j + i * v_tx_rings; /* default */
+
+			__set_bit(idx, &v->tx_rings_map);
+			bdr = &v->tx_ring[j];
+			bdr->index = idx;
+			bdr->ndev = priv->ndev;
+			bdr->dev = priv->dev;
+			bdr->bd_count = priv->tx_bd_count;
+			priv->tx_ring[idx] = bdr;
+		}
+
+		bdr = &v->rx_ring;
+		bdr->index = i;
+		bdr->ndev = priv->ndev;
+		bdr->dev = priv->dev;
+		bdr->bd_count = priv->rx_bd_count;
+		priv->rx_ring[i] = bdr;
+	}
+
+	return 0;
+
+fail:
+	while (i--) {
+		netif_napi_del(&priv->int_vector[i]->napi);
+		kfree(priv->int_vector[i]);
+	}
+
+	pci_free_irq_vectors(pdev);
+
+	return err;
+}
+
+void enetc_free_msix(struct enetc_ndev_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		struct enetc_int_vector *v = priv->int_vector[i];
+
+		netif_napi_del(&v->napi);
+	}
+
+	for (i = 0; i < priv->num_rx_rings; i++)
+		priv->rx_ring[i] = NULL;
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		priv->tx_ring[i] = NULL;
+
+	for (i = 0; i < priv->bdr_int_num; i++) {
+		kfree(priv->int_vector[i]);
+		priv->int_vector[i] = NULL;
+	}
+
+	/* disable all MSIX for this device */
+	pci_free_irq_vectors(priv->si->pdev);
+}
+
+static void enetc_kfree_si(struct enetc_si *si)
+{
+	char *p = (char *)si - si->pad;
+
+	kfree(p);
+}
+
+static void enetc_detect_errata(struct enetc_si *si)
+{
+	if (si->pdev->revision == ENETC_REV1)
+		si->errata = ENETC_ERR_TXCSUM | ENETC_ERR_VLAN_ISOL |
+			     ENETC_ERR_UCMCSWP;
+}
+
+int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv)
+{
+	struct enetc_si *si, *p;
+	struct enetc_hw *hw;
+	size_t alloc_size;
+	int err, len;
+
+	pcie_flr(pdev);
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "device enable failed\n");
+		return err;
+	}
+
+	/* set up for high or low dma */
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev,
+				"DMA configuration failed: 0x%x\n", err);
+			goto err_dma;
+		}
+	}
+
+	err = pci_request_mem_regions(pdev, name);
+	if (err) {
+		dev_err(&pdev->dev, "pci_request_regions failed err=%d\n", err);
+		goto err_pci_mem_reg;
+	}
+
+	pci_set_master(pdev);
+
+	alloc_size = sizeof(struct enetc_si);
+	if (sizeof_priv) {
+		/* align priv to 32B */
+		alloc_size = ALIGN(alloc_size, ENETC_SI_ALIGN);
+		alloc_size += sizeof_priv;
+	}
+	/* force 32B alignment for enetc_si */
+	alloc_size += ENETC_SI_ALIGN - 1;
+
+	p = kzalloc(alloc_size, GFP_KERNEL);
+	if (!p) {
+		err = -ENOMEM;
+		goto err_alloc_si;
+	}
+
+	si = PTR_ALIGN(p, ENETC_SI_ALIGN);
+	si->pad = (char *)si - (char *)p;
+
+	pci_set_drvdata(pdev, si);
+	si->pdev = pdev;
+	hw = &si->hw;
+
+	len = pci_resource_len(pdev, ENETC_BAR_REGS);
+	hw->reg = ioremap(pci_resource_start(pdev, ENETC_BAR_REGS), len);
+	if (!hw->reg) {
+		err = -ENXIO;
+		dev_err(&pdev->dev, "ioremap() failed\n");
+		goto err_ioremap;
+	}
+	if (len > ENETC_PORT_BASE)
+		hw->port = hw->reg + ENETC_PORT_BASE;
+	if (len > ENETC_GLOBAL_BASE)
+		hw->global = hw->reg + ENETC_GLOBAL_BASE;
+
+	enetc_detect_errata(si);
+
+	return 0;
+
+err_ioremap:
+	enetc_kfree_si(si);
+err_alloc_si:
+	pci_release_mem_regions(pdev);
+err_pci_mem_reg:
+err_dma:
+	pci_disable_device(pdev);
+
+	return err;
+}
+
+void enetc_pci_remove(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_hw *hw = &si->hw;
+
+	iounmap(hw->reg);
+	enetc_kfree_si(si);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h
new file mode 100644
index 000000000000..b274135c5103
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc.h
@@ -0,0 +1,230 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2017-2019 NXP */
+
+#include <linux/timer.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/dma-mapping.h>
+#include <linux/skbuff.h>
+#include <linux/ethtool.h>
+#include <linux/if_vlan.h>
+#include <linux/phy.h>
+
+#include "enetc_hw.h"
+
+#define ENETC_MAC_MAXFRM_SIZE	9600
+#define ENETC_MAX_MTU		(ENETC_MAC_MAXFRM_SIZE - \
+				(ETH_FCS_LEN + ETH_HLEN + VLAN_HLEN))
+
+struct enetc_tx_swbd {
+	struct sk_buff *skb;
+	dma_addr_t dma;
+	u16 len;
+	u16 is_dma_page;
+};
+
+#define ENETC_RX_MAXFRM_SIZE	ENETC_MAC_MAXFRM_SIZE
+#define ENETC_RXB_TRUESIZE	2048 /* PAGE_SIZE >> 1 */
+#define ENETC_RXB_PAD		NET_SKB_PAD /* add extra space if needed */
+#define ENETC_RXB_DMA_SIZE	\
+	(SKB_WITH_OVERHEAD(ENETC_RXB_TRUESIZE) - ENETC_RXB_PAD)
+
+struct enetc_rx_swbd {
+	dma_addr_t dma;
+	struct page *page;
+	u16 page_offset;
+};
+
+struct enetc_ring_stats {
+	unsigned int packets;
+	unsigned int bytes;
+	unsigned int rx_alloc_errs;
+};
+
+#define ENETC_BDR_DEFAULT_SIZE	1024
+#define ENETC_DEFAULT_TX_WORK	256
+
+struct enetc_bdr {
+	struct device *dev; /* for DMA mapping */
+	struct net_device *ndev;
+	void *bd_base; /* points to Rx or Tx BD ring */
+	union {
+		void __iomem *tpir;
+		void __iomem *rcir;
+	};
+	u16 index;
+	int bd_count; /* # of BDs */
+	int next_to_use;
+	int next_to_clean;
+	union {
+		struct enetc_tx_swbd *tx_swbd;
+		struct enetc_rx_swbd *rx_swbd;
+	};
+	union {
+		void __iomem *tcir; /* Tx */
+		int next_to_alloc; /* Rx */
+	};
+	void __iomem *idr; /* Interrupt Detect Register pointer */
+
+	struct enetc_ring_stats stats;
+
+	dma_addr_t bd_dma_base;
+} ____cacheline_aligned_in_smp;
+
+static inline void enetc_bdr_idx_inc(struct enetc_bdr *bdr, int *i)
+{
+	if (unlikely(++*i == bdr->bd_count))
+		*i = 0;
+}
+
+static inline int enetc_bd_unused(struct enetc_bdr *bdr)
+{
+	if (bdr->next_to_clean > bdr->next_to_use)
+		return bdr->next_to_clean - bdr->next_to_use - 1;
+
+	return bdr->bd_count + bdr->next_to_clean - bdr->next_to_use - 1;
+}
+
+/* Control BD ring */
+#define ENETC_CBDR_DEFAULT_SIZE	64
+struct enetc_cbdr {
+	void *bd_base; /* points to Rx or Tx BD ring */
+	void __iomem *pir;
+	void __iomem *cir;
+
+	int bd_count; /* # of BDs */
+	int next_to_use;
+	int next_to_clean;
+
+	dma_addr_t bd_dma_base;
+};
+
+#define ENETC_TXBD(BDR, i) (&(((union enetc_tx_bd *)((BDR).bd_base))[i]))
+#define ENETC_RXBD(BDR, i) (&(((union enetc_rx_bd *)((BDR).bd_base))[i]))
+
+struct enetc_msg_swbd {
+	void *vaddr;
+	dma_addr_t dma;
+	int size;
+};
+
+#define ENETC_REV1	0x1
+enum enetc_errata {
+	ENETC_ERR_TXCSUM	= BIT(0),
+	ENETC_ERR_VLAN_ISOL	= BIT(1),
+	ENETC_ERR_UCMCSWP	= BIT(2),
+};
+
+/* PCI IEP device data */
+struct enetc_si {
+	struct pci_dev *pdev;
+	struct enetc_hw hw;
+	enum enetc_errata errata;
+
+	struct net_device *ndev; /* back ref. */
+
+	struct enetc_cbdr cbd_ring;
+
+	int num_rx_rings; /* how many rings are available in the SI */
+	int num_tx_rings;
+	int num_fs_entries;
+	int num_rss; /* number of RSS buckets */
+	unsigned short pad;
+};
+
+#define ENETC_SI_ALIGN	32
+
+static inline void *enetc_si_priv(const struct enetc_si *si)
+{
+	return (char *)si + ALIGN(sizeof(struct enetc_si), ENETC_SI_ALIGN);
+}
+
+static inline bool enetc_si_is_pf(struct enetc_si *si)
+{
+	return !!(si->hw.port);
+}
+
+#define ENETC_MAX_NUM_TXQS	8
+#define ENETC_INT_NAME_MAX	(IFNAMSIZ + 8)
+
+struct enetc_int_vector {
+	void __iomem *rbier;
+	void __iomem *tbier_base;
+	unsigned long tx_rings_map;
+	int count_tx_rings;
+	struct napi_struct napi;
+	char name[ENETC_INT_NAME_MAX];
+
+	struct enetc_bdr rx_ring ____cacheline_aligned_in_smp;
+	struct enetc_bdr tx_ring[0];
+};
+
+struct enetc_cls_rule {
+	struct ethtool_rx_flow_spec fs;
+	int used;
+};
+
+#define ENETC_MAX_BDR_INT	2 /* fixed to max # of available cpus */
+
+struct enetc_ndev_priv {
+	struct net_device *ndev;
+	struct device *dev; /* dma-mapping device */
+	struct enetc_si *si;
+
+	int bdr_int_num; /* number of Rx/Tx ring interrupts */
+	struct enetc_int_vector *int_vector[ENETC_MAX_BDR_INT];
+	u16 num_rx_rings, num_tx_rings;
+	u16 rx_bd_count, tx_bd_count;
+
+	u16 msg_enable;
+
+	struct enetc_bdr *tx_ring[16];
+	struct enetc_bdr *rx_ring[16];
+
+	struct enetc_cls_rule *cls_rules;
+
+	struct device_node *phy_node;
+	phy_interface_t if_mode;
+};
+
+/* Messaging */
+
+/* VF-PF set primary MAC address message format */
+struct enetc_msg_cmd_set_primary_mac {
+	struct enetc_msg_cmd_header header;
+	struct sockaddr mac;
+};
+
+#define ENETC_CBD(R, i)	(&(((struct enetc_cbd *)((R).bd_base))[i]))
+
+#define ENETC_CBDR_TIMEOUT	1000 /* usecs */
+
+/* SI common */
+int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv);
+void enetc_pci_remove(struct pci_dev *pdev);
+int enetc_alloc_msix(struct enetc_ndev_priv *priv);
+void enetc_free_msix(struct enetc_ndev_priv *priv);
+void enetc_get_si_caps(struct enetc_si *si);
+void enetc_init_si_rings_params(struct enetc_ndev_priv *priv);
+int enetc_alloc_si_resources(struct enetc_ndev_priv *priv);
+void enetc_free_si_resources(struct enetc_ndev_priv *priv);
+
+int enetc_open(struct net_device *ndev);
+int enetc_close(struct net_device *ndev);
+netdev_tx_t enetc_xmit(struct sk_buff *skb, struct net_device *ndev);
+struct net_device_stats *enetc_get_stats(struct net_device *ndev);
+int enetc_set_features(struct net_device *ndev,
+		       netdev_features_t features);
+/* ethtool */
+void enetc_set_ethtool_ops(struct net_device *ndev);
+
+/* control buffer descriptor ring (CBDR) */
+int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
+			    char *mac_addr, int si_map);
+int enetc_clear_mac_flt_entry(struct enetc_si *si, int index);
+int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
+		       int index);
+void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes);
+int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count);
+int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
new file mode 100644
index 000000000000..de466b71bf8f
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_cbdr.c
@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include "enetc.h"
+
+static void enetc_clean_cbdr(struct enetc_si *si)
+{
+	struct enetc_cbdr *ring = &si->cbd_ring;
+	struct enetc_cbd *dest_cbd;
+	int i, status;
+
+	i = ring->next_to_clean;
+
+	while (enetc_rd_reg(ring->cir) != i) {
+		dest_cbd = ENETC_CBD(*ring, i);
+		status = dest_cbd->status_flags & ENETC_CBD_STATUS_MASK;
+		if (status)
+			dev_warn(&si->pdev->dev, "CMD err %04x for cmd %04x\n",
+				 status, dest_cbd->cmd);
+
+		memset(dest_cbd, 0, sizeof(*dest_cbd));
+
+		i = (i + 1) % ring->bd_count;
+	}
+
+	ring->next_to_clean = i;
+}
+
+static int enetc_cbd_unused(struct enetc_cbdr *r)
+{
+	return (r->next_to_clean - r->next_to_use - 1 + r->bd_count) %
+		r->bd_count;
+}
+
+static int enetc_send_cmd(struct enetc_si *si, struct enetc_cbd *cbd)
+{
+	struct enetc_cbdr *ring = &si->cbd_ring;
+	int timeout = ENETC_CBDR_TIMEOUT;
+	struct enetc_cbd *dest_cbd;
+	int i;
+
+	if (unlikely(!ring->bd_base))
+		return -EIO;
+
+	if (unlikely(!enetc_cbd_unused(ring)))
+		enetc_clean_cbdr(si);
+
+	i = ring->next_to_use;
+	dest_cbd = ENETC_CBD(*ring, i);
+
+	/* copy command to the ring */
+	*dest_cbd = *cbd;
+	i = (i + 1) % ring->bd_count;
+
+	ring->next_to_use = i;
+	/* let H/W know BD ring has been updated */
+	enetc_wr_reg(ring->pir, i);
+
+	do {
+		if (enetc_rd_reg(ring->cir) == i)
+			break;
+		udelay(10); /* cannot sleep, rtnl_lock() */
+		timeout -= 10;
+	} while (timeout);
+
+	if (!timeout)
+		return -EBUSY;
+
+	enetc_clean_cbdr(si);
+
+	return 0;
+}
+
+int enetc_clear_mac_flt_entry(struct enetc_si *si, int index)
+{
+	struct enetc_cbd cbd;
+
+	memset(&cbd, 0, sizeof(cbd));
+
+	cbd.cls = 1;
+	cbd.status_flags = ENETC_CBD_FLAGS_SF;
+	cbd.index = cpu_to_le16(index);
+
+	return enetc_send_cmd(si, &cbd);
+}
+
+int enetc_set_mac_flt_entry(struct enetc_si *si, int index,
+			    char *mac_addr, int si_map)
+{
+	struct enetc_cbd cbd;
+	u32 upper;
+	u16 lower;
+
+	memset(&cbd, 0, sizeof(cbd));
+
+	/* fill up the "set" descriptor */
+	cbd.cls = 1;
+	cbd.status_flags = ENETC_CBD_FLAGS_SF;
+	cbd.index = cpu_to_le16(index);
+	cbd.opt[3] = cpu_to_le32(si_map);
+	/* enable entry */
+	cbd.opt[0] = cpu_to_le32(BIT(31));
+
+	upper = *(const u32 *)mac_addr;
+	lower = *(const u16 *)(mac_addr + 4);
+	cbd.addr[0] = cpu_to_le32(upper);
+	cbd.addr[1] = cpu_to_le32(lower);
+
+	return enetc_send_cmd(si, &cbd);
+}
+
+#define RFSE_ALIGN	64
+/* Set entry in RFS table */
+int enetc_set_fs_entry(struct enetc_si *si, struct enetc_cmd_rfse *rfse,
+		       int index)
+{
+	struct enetc_cbd cbd = {.cmd = 0};
+	dma_addr_t dma, dma_align;
+	void *tmp, *tmp_align;
+	int err;
+
+	/* fill up the "set" descriptor */
+	cbd.cmd = 0;
+	cbd.cls = 4;
+	cbd.index = cpu_to_le16(index);
+	cbd.length = cpu_to_le16(sizeof(*rfse));
+	cbd.opt[3] = cpu_to_le32(0); /* SI */
+
+	tmp = dma_alloc_coherent(&si->pdev->dev, sizeof(*rfse) + RFSE_ALIGN,
+				 &dma, GFP_KERNEL);
+	if (!tmp) {
+		dev_err(&si->pdev->dev, "DMA mapping of RFS entry failed!\n");
+		return -ENOMEM;
+	}
+
+	dma_align = ALIGN(dma, RFSE_ALIGN);
+	tmp_align = PTR_ALIGN(tmp, RFSE_ALIGN);
+	memcpy(tmp_align, rfse, sizeof(*rfse));
+
+	cbd.addr[0] = cpu_to_le32(lower_32_bits(dma_align));
+	cbd.addr[1] = cpu_to_le32(upper_32_bits(dma_align));
+
+	err = enetc_send_cmd(si, &cbd);
+	if (err)
+		dev_err(&si->pdev->dev, "FS entry add failed (%d)!", err);
+
+	dma_free_coherent(&si->pdev->dev, sizeof(*rfse) + RFSE_ALIGN,
+			  tmp, dma);
+
+	return err;
+}
+
+#define RSSE_ALIGN	64
+static int enetc_cmd_rss_table(struct enetc_si *si, u32 *table, int count,
+			       bool read)
+{
+	struct enetc_cbd cbd = {.cmd = 0};
+	dma_addr_t dma, dma_align;
+	u8 *tmp, *tmp_align;
+	int err, i;
+
+	if (count < RSSE_ALIGN)
+		/* HW only takes in a full 64 entry table */
+		return -EINVAL;
+
+	tmp = dma_alloc_coherent(&si->pdev->dev, count + RSSE_ALIGN,
+				 &dma, GFP_KERNEL);
+	if (!tmp) {
+		dev_err(&si->pdev->dev, "DMA mapping of RSS table failed!\n");
+		return -ENOMEM;
+	}
+	dma_align = ALIGN(dma, RSSE_ALIGN);
+	tmp_align = PTR_ALIGN(tmp, RSSE_ALIGN);
+
+	if (!read)
+		for (i = 0; i < count; i++)
+			tmp_align[i] = (u8)(table[i]);
+
+	/* fill up the descriptor */
+	cbd.cmd = read ? 2 : 1;
+	cbd.cls = 3;
+	cbd.length = cpu_to_le16(count);
+
+	cbd.addr[0] = cpu_to_le32(lower_32_bits(dma_align));
+	cbd.addr[1] = cpu_to_le32(upper_32_bits(dma_align));
+
+	err = enetc_send_cmd(si, &cbd);
+	if (err)
+		dev_err(&si->pdev->dev, "RSS cmd failed (%d)!", err);
+
+	if (read)
+		for (i = 0; i < count; i++)
+			table[i] = tmp_align[i];
+
+	dma_free_coherent(&si->pdev->dev, count + RSSE_ALIGN, tmp, dma);
+
+	return err;
+}
+
+/* Get RSS table */
+int enetc_get_rss_table(struct enetc_si *si, u32 *table, int count)
+{
+	return enetc_cmd_rss_table(si, table, count, true);
+}
+
+/* Set RSS table */
+int enetc_set_rss_table(struct enetc_si *si, const u32 *table, int count)
+{
+	return enetc_cmd_rss_table(si, (u32 *)table, count, false);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
new file mode 100644
index 000000000000..1ecad9ffabae
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -0,0 +1,597 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include <linux/net_tstamp.h>
+#include <linux/module.h>
+#include "enetc.h"
+
+static const u32 enetc_si_regs[] = {
+	ENETC_SIMR, ENETC_SIPMAR0, ENETC_SIPMAR1, ENETC_SICBDRMR,
+	ENETC_SICBDRSR,	ENETC_SICBDRBAR0, ENETC_SICBDRBAR1, ENETC_SICBDRPIR,
+	ENETC_SICBDRCIR, ENETC_SICBDRLENR, ENETC_SICAPR0, ENETC_SICAPR1,
+	ENETC_SIUEFDCR
+};
+
+static const u32 enetc_txbdr_regs[] = {
+	ENETC_TBMR, ENETC_TBSR, ENETC_TBBAR0, ENETC_TBBAR1,
+	ENETC_TBPIR, ENETC_TBCIR, ENETC_TBLENR, ENETC_TBIER
+};
+
+static const u32 enetc_rxbdr_regs[] = {
+	ENETC_RBMR, ENETC_RBSR, ENETC_RBBSR, ENETC_RBCIR, ENETC_RBBAR0,
+	ENETC_RBBAR1, ENETC_RBPIR, ENETC_RBLENR, ENETC_RBICIR0, ENETC_RBIER
+};
+
+static const u32 enetc_port_regs[] = {
+	ENETC_PMR, ENETC_PSR, ENETC_PSIPMR, ENETC_PSIPMAR0(0),
+	ENETC_PSIPMAR1(0), ENETC_PTXMBAR, ENETC_PCAPR0, ENETC_PCAPR1,
+	ENETC_PSICFGR0(0), ENETC_PRFSCAPR, ENETC_PTCMSDUR(0),
+	ENETC_PM0_CMD_CFG, ENETC_PM0_MAXFRM, ENETC_PM0_IF_MODE
+};
+
+static int enetc_get_reglen(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int len;
+
+	len = ARRAY_SIZE(enetc_si_regs);
+	len += ARRAY_SIZE(enetc_txbdr_regs) * priv->num_tx_rings;
+	len += ARRAY_SIZE(enetc_rxbdr_regs) * priv->num_rx_rings;
+
+	if (hw->port)
+		len += ARRAY_SIZE(enetc_port_regs);
+
+	len *= sizeof(u32) * 2; /* store 2 entries per reg: addr and value */
+
+	return len;
+}
+
+static void enetc_get_regs(struct net_device *ndev, struct ethtool_regs *regs,
+			   void *regbuf)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 *buf = (u32 *)regbuf;
+	int i, j;
+	u32 addr;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_si_regs); i++) {
+		*buf++ = enetc_si_regs[i];
+		*buf++ = enetc_rd(hw, enetc_si_regs[i]);
+	}
+
+	for (i = 0; i < priv->num_tx_rings; i++) {
+		for (j = 0; j < ARRAY_SIZE(enetc_txbdr_regs); j++) {
+			addr = ENETC_BDR(TX, i, enetc_txbdr_regs[j]);
+
+			*buf++ = addr;
+			*buf++ = enetc_rd(hw, addr);
+		}
+	}
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		for (j = 0; j < ARRAY_SIZE(enetc_rxbdr_regs); j++) {
+			addr = ENETC_BDR(RX, i, enetc_rxbdr_regs[j]);
+
+			*buf++ = addr;
+			*buf++ = enetc_rd(hw, addr);
+		}
+	}
+
+	if (!hw->port)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_port_regs); i++) {
+		addr = ENETC_PORT_BASE + enetc_port_regs[i];
+		*buf++ = addr;
+		*buf++ = enetc_rd(hw, addr);
+	}
+}
+
+static const struct {
+	int reg;
+	char name[ETH_GSTRING_LEN];
+} enetc_si_counters[] =  {
+	{ ENETC_SIROCT, "SI rx octets" },
+	{ ENETC_SIRFRM, "SI rx frames" },
+	{ ENETC_SIRUCA, "SI rx u-cast frames" },
+	{ ENETC_SIRMCA, "SI rx m-cast frames" },
+	{ ENETC_SITOCT, "SI tx octets" },
+	{ ENETC_SITFRM, "SI tx frames" },
+	{ ENETC_SITUCA, "SI tx u-cast frames" },
+	{ ENETC_SITMCA, "SI tx m-cast frames" },
+	{ ENETC_RBDCR(0), "Rx ring  0 discarded frames" },
+	{ ENETC_RBDCR(1), "Rx ring  1 discarded frames" },
+	{ ENETC_RBDCR(2), "Rx ring  2 discarded frames" },
+	{ ENETC_RBDCR(3), "Rx ring  3 discarded frames" },
+	{ ENETC_RBDCR(4), "Rx ring  4 discarded frames" },
+	{ ENETC_RBDCR(5), "Rx ring  5 discarded frames" },
+	{ ENETC_RBDCR(6), "Rx ring  6 discarded frames" },
+	{ ENETC_RBDCR(7), "Rx ring  7 discarded frames" },
+	{ ENETC_RBDCR(8), "Rx ring  8 discarded frames" },
+	{ ENETC_RBDCR(9), "Rx ring  9 discarded frames" },
+	{ ENETC_RBDCR(10), "Rx ring 10 discarded frames" },
+	{ ENETC_RBDCR(11), "Rx ring 11 discarded frames" },
+	{ ENETC_RBDCR(12), "Rx ring 12 discarded frames" },
+	{ ENETC_RBDCR(13), "Rx ring 13 discarded frames" },
+	{ ENETC_RBDCR(14), "Rx ring 14 discarded frames" },
+	{ ENETC_RBDCR(15), "Rx ring 15 discarded frames" },
+};
+
+static const struct {
+	int reg;
+	char name[ETH_GSTRING_LEN];
+} enetc_port_counters[] = {
+	{ ENETC_PM0_REOCT,  "MAC rx ethernet octets" },
+	{ ENETC_PM0_RALN,   "MAC rx alignment errors" },
+	{ ENETC_PM0_RXPF,   "MAC rx valid pause frames" },
+	{ ENETC_PM0_RFRM,   "MAC rx valid frames" },
+	{ ENETC_PM0_RFCS,   "MAC rx fcs errors" },
+	{ ENETC_PM0_RVLAN,  "MAC rx VLAN frames" },
+	{ ENETC_PM0_RERR,   "MAC rx frame errors" },
+	{ ENETC_PM0_RUCA,   "MAC rx unicast frames" },
+	{ ENETC_PM0_RMCA,   "MAC rx multicast frames" },
+	{ ENETC_PM0_RBCA,   "MAC rx broadcast frames" },
+	{ ENETC_PM0_RDRP,   "MAC rx dropped packets" },
+	{ ENETC_PM0_RPKT,   "MAC rx packets" },
+	{ ENETC_PM0_RUND,   "MAC rx undersized packets" },
+	{ ENETC_PM0_R64,    "MAC rx 64 byte packets" },
+	{ ENETC_PM0_R127,   "MAC rx 65-127 byte packets" },
+	{ ENETC_PM0_R255,   "MAC rx 128-255 byte packets" },
+	{ ENETC_PM0_R511,   "MAC rx 256-511 byte packets" },
+	{ ENETC_PM0_R1023,  "MAC rx 512-1023 byte packets" },
+	{ ENETC_PM0_R1518,  "MAC rx 1024-1518 byte packets" },
+	{ ENETC_PM0_R1519X, "MAC rx 1519 to max-octet packets" },
+	{ ENETC_PM0_ROVR,   "MAC rx oversized packets" },
+	{ ENETC_PM0_RJBR,   "MAC rx jabber packets" },
+	{ ENETC_PM0_RFRG,   "MAC rx fragment packets" },
+	{ ENETC_PM0_RCNP,   "MAC rx control packets" },
+	{ ENETC_PM0_RDRNTP, "MAC rx fifo drop" },
+	{ ENETC_PM0_TEOCT,  "MAC tx ethernet octets" },
+	{ ENETC_PM0_TOCT,   "MAC tx octets" },
+	{ ENETC_PM0_TCRSE,  "MAC tx carrier sense errors" },
+	{ ENETC_PM0_TXPF,   "MAC tx valid pause frames" },
+	{ ENETC_PM0_TFRM,   "MAC tx frames" },
+	{ ENETC_PM0_TFCS,   "MAC tx fcs errors" },
+	{ ENETC_PM0_TVLAN,  "MAC tx VLAN frames" },
+	{ ENETC_PM0_TERR,   "MAC tx frames" },
+	{ ENETC_PM0_TUCA,   "MAC tx unicast frames" },
+	{ ENETC_PM0_TMCA,   "MAC tx multicast frames" },
+	{ ENETC_PM0_TBCA,   "MAC tx broadcast frames" },
+	{ ENETC_PM0_TPKT,   "MAC tx packets" },
+	{ ENETC_PM0_TUND,   "MAC tx undersized packets" },
+	{ ENETC_PM0_T127,   "MAC tx 65-127 byte packets" },
+	{ ENETC_PM0_T1023,  "MAC tx 512-1023 byte packets" },
+	{ ENETC_PM0_T1518,  "MAC tx 1024-1518 byte packets" },
+	{ ENETC_PM0_TCNP,   "MAC tx control packets" },
+	{ ENETC_PM0_TDFR,   "MAC tx deferred packets" },
+	{ ENETC_PM0_TMCOL,  "MAC tx multiple collisions" },
+	{ ENETC_PM0_TSCOL,  "MAC tx single collisions" },
+	{ ENETC_PM0_TLCOL,  "MAC tx late collisions" },
+	{ ENETC_PM0_TECOL,  "MAC tx excessive collisions" },
+	{ ENETC_UFDMF,      "SI MAC nomatch u-cast discards" },
+	{ ENETC_MFDMF,      "SI MAC nomatch m-cast discards" },
+	{ ENETC_PBFDSIR,    "SI MAC nomatch b-cast discards" },
+	{ ENETC_PUFDVFR,    "SI VLAN nomatch u-cast discards" },
+	{ ENETC_PMFDVFR,    "SI VLAN nomatch m-cast discards" },
+	{ ENETC_PBFDVFR,    "SI VLAN nomatch b-cast discards" },
+	{ ENETC_PFDMSAPR,   "SI pruning discarded frames" },
+	{ ENETC_PICDR(0),   "ICM DR0 discarded frames" },
+	{ ENETC_PICDR(1),   "ICM DR1 discarded frames" },
+	{ ENETC_PICDR(2),   "ICM DR2 discarded frames" },
+	{ ENETC_PICDR(3),   "ICM DR3 discarded frames" },
+};
+
+static const char rx_ring_stats[][ETH_GSTRING_LEN] = {
+	"Rx ring %2d frames",
+	"Rx ring %2d alloc errors",
+};
+
+static const char tx_ring_stats[][ETH_GSTRING_LEN] = {
+	"Tx ring %2d frames",
+};
+
+static int enetc_get_sset_count(struct net_device *ndev, int sset)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (sset == ETH_SS_STATS)
+		return ARRAY_SIZE(enetc_si_counters) +
+			ARRAY_SIZE(tx_ring_stats) * priv->num_tx_rings +
+			ARRAY_SIZE(rx_ring_stats) * priv->num_rx_rings +
+			(enetc_si_is_pf(priv->si) ?
+			ARRAY_SIZE(enetc_port_counters) : 0);
+
+	return -EOPNOTSUPP;
+}
+
+static void enetc_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	u8 *p = data;
+	int i, j;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < ARRAY_SIZE(enetc_si_counters); i++) {
+			strlcpy(p, enetc_si_counters[i].name, ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		for (i = 0; i < priv->num_tx_rings; i++) {
+			for (j = 0; j < ARRAY_SIZE(tx_ring_stats); j++) {
+				snprintf(p, ETH_GSTRING_LEN, tx_ring_stats[j],
+					 i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+		for (i = 0; i < priv->num_rx_rings; i++) {
+			for (j = 0; j < ARRAY_SIZE(rx_ring_stats); j++) {
+				snprintf(p, ETH_GSTRING_LEN, rx_ring_stats[j],
+					 i);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
+		if (!enetc_si_is_pf(priv->si))
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++) {
+			strlcpy(p, enetc_port_counters[i].name,
+				ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	}
+}
+
+static void enetc_get_ethtool_stats(struct net_device *ndev,
+				    struct ethtool_stats *stats, u64 *data)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int i, o = 0;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_si_counters); i++)
+		data[o++] = enetc_rd64(hw, enetc_si_counters[i].reg);
+
+	for (i = 0; i < priv->num_tx_rings; i++)
+		data[o++] = priv->tx_ring[i]->stats.packets;
+
+	for (i = 0; i < priv->num_rx_rings; i++) {
+		data[o++] = priv->rx_ring[i]->stats.packets;
+		data[o++] = priv->rx_ring[i]->stats.rx_alloc_errs;
+	}
+
+	if (!enetc_si_is_pf(priv->si))
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(enetc_port_counters); i++)
+		data[o++] = enetc_port_rd(hw, enetc_port_counters[i].reg);
+}
+
+#define ENETC_RSSHASH_L3 (RXH_L2DA | RXH_VLAN | RXH_L3_PROTO | RXH_IP_SRC | \
+			  RXH_IP_DST)
+#define ENETC_RSSHASH_L4 (ENETC_RSSHASH_L3 | RXH_L4_B_0_1 | RXH_L4_B_2_3)
+static int enetc_get_rsshash(struct ethtool_rxnfc *rxnfc)
+{
+	static const u32 rsshash[] = {
+			[TCP_V4_FLOW]    = ENETC_RSSHASH_L4,
+			[UDP_V4_FLOW]    = ENETC_RSSHASH_L4,
+			[SCTP_V4_FLOW]   = ENETC_RSSHASH_L4,
+			[AH_ESP_V4_FLOW] = ENETC_RSSHASH_L3,
+			[IPV4_FLOW]      = ENETC_RSSHASH_L3,
+			[TCP_V6_FLOW]    = ENETC_RSSHASH_L4,
+			[UDP_V6_FLOW]    = ENETC_RSSHASH_L4,
+			[SCTP_V6_FLOW]   = ENETC_RSSHASH_L4,
+			[AH_ESP_V6_FLOW] = ENETC_RSSHASH_L3,
+			[IPV6_FLOW]      = ENETC_RSSHASH_L3,
+			[ETHER_FLOW]     = 0,
+	};
+
+	if (rxnfc->flow_type >= ARRAY_SIZE(rsshash))
+		return -EINVAL;
+
+	rxnfc->data = rsshash[rxnfc->flow_type];
+
+	return 0;
+}
+
+/* current HW spec does byte reversal on everything including MAC addresses */
+static void ether_addr_copy_swap(u8 *dst, const u8 *src)
+{
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dst[i] = src[ETH_ALEN - i - 1];
+}
+
+static int enetc_set_cls_entry(struct enetc_si *si,
+			       struct ethtool_rx_flow_spec *fs, bool en)
+{
+	struct ethtool_tcpip4_spec *l4ip4_h, *l4ip4_m;
+	struct ethtool_usrip4_spec *l3ip4_h, *l3ip4_m;
+	struct ethhdr *eth_h, *eth_m;
+	struct enetc_cmd_rfse rfse = { {0} };
+
+	if (!en)
+		goto done;
+
+	switch (fs->flow_type & 0xff) {
+	case TCP_V4_FLOW:
+		l4ip4_h = &fs->h_u.tcp_ip4_spec;
+		l4ip4_m = &fs->m_u.tcp_ip4_spec;
+		goto l4ip4;
+	case UDP_V4_FLOW:
+		l4ip4_h = &fs->h_u.udp_ip4_spec;
+		l4ip4_m = &fs->m_u.udp_ip4_spec;
+		goto l4ip4;
+	case SCTP_V4_FLOW:
+		l4ip4_h = &fs->h_u.sctp_ip4_spec;
+		l4ip4_m = &fs->m_u.sctp_ip4_spec;
+l4ip4:
+		rfse.sip_h[0] = l4ip4_h->ip4src;
+		rfse.sip_m[0] = l4ip4_m->ip4src;
+		rfse.dip_h[0] = l4ip4_h->ip4dst;
+		rfse.dip_m[0] = l4ip4_m->ip4dst;
+		rfse.sport_h = ntohs(l4ip4_h->psrc);
+		rfse.sport_m = ntohs(l4ip4_m->psrc);
+		rfse.dport_h = ntohs(l4ip4_h->pdst);
+		rfse.dport_m = ntohs(l4ip4_m->pdst);
+		if (l4ip4_m->tos)
+			netdev_warn(si->ndev, "ToS field is not supported and was ignored\n");
+		rfse.ethtype_h = ETH_P_IP; /* IPv4 */
+		rfse.ethtype_m = 0xffff;
+		break;
+	case IP_USER_FLOW:
+		l3ip4_h = &fs->h_u.usr_ip4_spec;
+		l3ip4_m = &fs->m_u.usr_ip4_spec;
+
+		rfse.sip_h[0] = l3ip4_h->ip4src;
+		rfse.sip_m[0] = l3ip4_m->ip4src;
+		rfse.dip_h[0] = l3ip4_h->ip4dst;
+		rfse.dip_m[0] = l3ip4_m->ip4dst;
+		if (l3ip4_m->tos)
+			netdev_warn(si->ndev, "ToS field is not supported and was ignored\n");
+		rfse.ethtype_h = ETH_P_IP; /* IPv4 */
+		rfse.ethtype_m = 0xffff;
+		break;
+	case ETHER_FLOW:
+		eth_h = &fs->h_u.ether_spec;
+		eth_m = &fs->m_u.ether_spec;
+
+		ether_addr_copy_swap(rfse.smac_h, eth_h->h_source);
+		ether_addr_copy_swap(rfse.smac_m, eth_m->h_source);
+		ether_addr_copy_swap(rfse.dmac_h, eth_h->h_dest);
+		ether_addr_copy_swap(rfse.dmac_m, eth_m->h_dest);
+		rfse.ethtype_h = ntohs(eth_h->h_proto);
+		rfse.ethtype_m = ntohs(eth_m->h_proto);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	rfse.mode |= ENETC_RFSE_EN;
+	if (fs->ring_cookie != RX_CLS_FLOW_DISC) {
+		rfse.mode |= ENETC_RFSE_MODE_BD;
+		rfse.result = fs->ring_cookie;
+	}
+done:
+	return enetc_set_fs_entry(si, &rfse, fs->location);
+}
+
+static int enetc_get_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc,
+			   u32 *rule_locs)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int i, j;
+
+	switch (rxnfc->cmd) {
+	case ETHTOOL_GRXRINGS:
+		rxnfc->data = priv->num_rx_rings;
+		break;
+	case ETHTOOL_GRXFH:
+		/* get RSS hash config */
+		return enetc_get_rsshash(rxnfc);
+	case ETHTOOL_GRXCLSRLCNT:
+		/* total number of entries */
+		rxnfc->data = priv->si->num_fs_entries;
+		/* number of entries in use */
+		rxnfc->rule_cnt = 0;
+		for (i = 0; i < priv->si->num_fs_entries; i++)
+			if (priv->cls_rules[i].used)
+				rxnfc->rule_cnt++;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		if (rxnfc->fs.location >= priv->si->num_fs_entries)
+			return -EINVAL;
+
+		/* get entry x */
+		rxnfc->fs = priv->cls_rules[rxnfc->fs.location].fs;
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		/* total number of entries */
+		rxnfc->data = priv->si->num_fs_entries;
+		/* array of indexes of used entries */
+		j = 0;
+		for (i = 0; i < priv->si->num_fs_entries; i++) {
+			if (!priv->cls_rules[i].used)
+				continue;
+			if (j == rxnfc->rule_cnt)
+				return -EMSGSIZE;
+			rule_locs[j++] = i;
+		}
+		/* number of entries in use */
+		rxnfc->rule_cnt = j;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int enetc_set_rxnfc(struct net_device *ndev, struct ethtool_rxnfc *rxnfc)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	int err;
+
+	switch (rxnfc->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		if (rxnfc->fs.location >= priv->si->num_fs_entries)
+			return -EINVAL;
+
+		if (rxnfc->fs.ring_cookie >= priv->num_rx_rings &&
+		    rxnfc->fs.ring_cookie != RX_CLS_FLOW_DISC)
+			return -EINVAL;
+
+		err = enetc_set_cls_entry(priv->si, &rxnfc->fs, true);
+		if (err)
+			return err;
+		priv->cls_rules[rxnfc->fs.location].fs = rxnfc->fs;
+		priv->cls_rules[rxnfc->fs.location].used = 1;
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		if (rxnfc->fs.location >= priv->si->num_fs_entries)
+			return -EINVAL;
+
+		err = enetc_set_cls_entry(priv->si, &rxnfc->fs, false);
+		if (err)
+			return err;
+		priv->cls_rules[rxnfc->fs.location].used = 0;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static u32 enetc_get_rxfh_key_size(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	/* return the size of the RX flow hash key.  PF only */
+	return (priv->si->hw.port) ? ENETC_RSSHASH_KEY_SIZE : 0;
+}
+
+static u32 enetc_get_rxfh_indir_size(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	/* return the size of the RX flow hash indirection table */
+	return priv->si->num_rss;
+}
+
+static int enetc_get_rxfh(struct net_device *ndev, u32 *indir, u8 *key,
+			  u8 *hfunc)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int err = 0, i;
+
+	/* return hash function */
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+
+	/* return hash key */
+	if (key && hw->port)
+		for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+			((u32 *)key)[i] = enetc_port_rd(hw, ENETC_PRSSK(i));
+
+	/* return RSS table */
+	if (indir)
+		err = enetc_get_rss_table(priv->si, indir, priv->si->num_rss);
+
+	return err;
+}
+
+void enetc_set_rss_key(struct enetc_hw *hw, const u8 *bytes)
+{
+	int i;
+
+	for (i = 0; i < ENETC_RSSHASH_KEY_SIZE / 4; i++)
+		enetc_port_wr(hw, ENETC_PRSSK(i), ((u32 *)bytes)[i]);
+}
+
+static int enetc_set_rxfh(struct net_device *ndev, const u32 *indir,
+			  const u8 *key, const u8 hfunc)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	int err = 0;
+
+	/* set hash key, if PF */
+	if (key && hw->port)
+		enetc_set_rss_key(hw, key);
+
+	/* set RSS table */
+	if (indir)
+		err = enetc_set_rss_table(priv->si, indir, priv->si->num_rss);
+
+	return err;
+}
+
+static void enetc_get_ringparam(struct net_device *ndev,
+				struct ethtool_ringparam *ring)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	ring->rx_pending = priv->rx_bd_count;
+	ring->tx_pending = priv->tx_bd_count;
+
+	/* do some h/w sanity checks for BDR length */
+	if (netif_running(ndev)) {
+		struct enetc_hw *hw = &priv->si->hw;
+		u32 val = enetc_rxbdr_rd(hw, 0, ENETC_RBLENR);
+
+		if (val != priv->rx_bd_count)
+			netif_err(priv, hw, ndev, "RxBDR[RBLENR] = %d!\n", val);
+
+		val = enetc_txbdr_rd(hw, 0, ENETC_TBLENR);
+
+		if (val != priv->tx_bd_count)
+			netif_err(priv, hw, ndev, "TxBDR[TBLENR] = %d!\n", val);
+	}
+}
+
+static const struct ethtool_ops enetc_pf_ethtool_ops = {
+	.get_regs_len = enetc_get_reglen,
+	.get_regs = enetc_get_regs,
+	.get_sset_count = enetc_get_sset_count,
+	.get_strings = enetc_get_strings,
+	.get_ethtool_stats = enetc_get_ethtool_stats,
+	.get_rxnfc = enetc_get_rxnfc,
+	.set_rxnfc = enetc_set_rxnfc,
+	.get_rxfh_key_size = enetc_get_rxfh_key_size,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
+	.get_ringparam = enetc_get_ringparam,
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+};
+
+static const struct ethtool_ops enetc_vf_ethtool_ops = {
+	.get_regs_len = enetc_get_reglen,
+	.get_regs = enetc_get_regs,
+	.get_sset_count = enetc_get_sset_count,
+	.get_strings = enetc_get_strings,
+	.get_ethtool_stats = enetc_get_ethtool_stats,
+	.get_rxnfc = enetc_get_rxnfc,
+	.set_rxnfc = enetc_set_rxnfc,
+	.get_rxfh_indir_size = enetc_get_rxfh_indir_size,
+	.get_rxfh = enetc_get_rxfh,
+	.set_rxfh = enetc_set_rxfh,
+	.get_ringparam = enetc_get_ringparam,
+};
+
+void enetc_set_ethtool_ops(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (enetc_si_is_pf(priv->si))
+		ndev->ethtool_ops = &enetc_pf_ethtool_ops;
+	else
+		ndev->ethtool_ops = &enetc_vf_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
new file mode 100644
index 000000000000..df8eb8882d92
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h
@@ -0,0 +1,533 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2017-2019 NXP */
+
+#include <linux/bitops.h>
+
+/* ENETC device IDs */
+#define ENETC_DEV_ID_PF		0xe100
+#define ENETC_DEV_ID_VF		0xef00
+#define ENETC_DEV_ID_PTP	0xee02
+
+/* ENETC register block BAR */
+#define ENETC_BAR_REGS	0
+
+/** SI regs, offset: 0h */
+#define ENETC_SIMR	0
+#define ENETC_SIMR_EN	BIT(31)
+#define ENETC_SIMR_RSSE	BIT(0)
+#define ENETC_SICTR0	0x18
+#define ENETC_SICTR1	0x1c
+#define ENETC_SIPCAPR0	0x20
+#define ENETC_SIPCAPR0_RSS	BIT(8)
+#define ENETC_SIPCAPR1	0x24
+#define ENETC_SITGTGR	0x30
+#define ENETC_SIRBGCR	0x38
+/* cache attribute registers for transactions initiated by ENETC */
+#define ENETC_SICAR0	0x40
+#define ENETC_SICAR1	0x44
+#define ENETC_SICAR2	0x48
+/* rd snoop, no alloc
+ * wr snoop, no alloc, partial cache line update for BDs and full cache line
+ * update for data
+ */
+#define ENETC_SICAR_RD_COHERENT	0x2b2b0000
+#define ENETC_SICAR_WR_COHERENT	0x00006727
+#define ENETC_SICAR_MSI	0x00300030 /* rd/wr device, no snoop, no alloc */
+
+#define ENETC_SIPMAR0	0x80
+#define ENETC_SIPMAR1	0x84
+
+/* VF-PF Message passing */
+#define ENETC_DEFAULT_MSG_SIZE	1024	/* and max size */
+/* msg size encoding: default and max msg value of 1024B encoded as 0 */
+static inline u32 enetc_vsi_set_msize(u32 size)
+{
+	return size < ENETC_DEFAULT_MSG_SIZE ? size >> 5 : 0;
+}
+
+#define ENETC_PSIMSGRR	0x204
+#define ENETC_PSIMSGRR_MR_MASK	GENMASK(2, 1)
+#define ENETC_PSIMSGRR_MR(n) BIT((n) + 1) /* n = VSI index */
+#define ENETC_PSIVMSGRCVAR0(n)	(0x210 + (n) * 0x8) /* n = VSI index */
+#define ENETC_PSIVMSGRCVAR1(n)	(0x214 + (n) * 0x8)
+
+#define ENETC_VSIMSGSR	0x204	/* RO */
+#define ENETC_VSIMSGSR_MB	BIT(0)
+#define ENETC_VSIMSGSR_MS	BIT(1)
+#define ENETC_VSIMSGSNDAR0	0x210
+#define ENETC_VSIMSGSNDAR1	0x214
+
+#define ENETC_SIMSGSR_SET_MC(val) ((val) << 16)
+#define ENETC_SIMSGSR_GET_MC(val) ((val) >> 16)
+
+/* SI statistics */
+#define ENETC_SIROCT	0x300
+#define ENETC_SIRFRM	0x308
+#define ENETC_SIRUCA	0x310
+#define ENETC_SIRMCA	0x318
+#define ENETC_SITOCT	0x320
+#define ENETC_SITFRM	0x328
+#define ENETC_SITUCA	0x330
+#define ENETC_SITMCA	0x338
+#define ENETC_RBDCR(n)	(0x8180 + (n) * 0x200)
+
+/* Control BDR regs */
+#define ENETC_SICBDRMR		0x800
+#define ENETC_SICBDRSR		0x804	/* RO */
+#define ENETC_SICBDRBAR0	0x810
+#define ENETC_SICBDRBAR1	0x814
+#define ENETC_SICBDRPIR		0x818
+#define ENETC_SICBDRCIR		0x81c
+#define ENETC_SICBDRLENR	0x820
+
+#define ENETC_SICAPR0	0x900
+#define ENETC_SICAPR1	0x904
+
+#define ENETC_PSIIER	0xa00
+#define ENETC_PSIIER_MR_MASK	GENMASK(2, 1)
+#define ENETC_PSIIDR	0xa08
+#define ENETC_SITXIDR	0xa18
+#define ENETC_SIRXIDR	0xa28
+#define ENETC_SIMSIVR	0xa30
+
+#define ENETC_SIMSITRV(n) (0xB00 + (n) * 0x4)
+#define ENETC_SIMSIRRV(n) (0xB80 + (n) * 0x4)
+
+#define ENETC_SIUEFDCR	0xe28
+
+#define ENETC_SIRFSCAPR	0x1200
+#define ENETC_SIRFSCAPR_GET_NUM_RFS(val) ((val) & 0x7f)
+#define ENETC_SIRSSCAPR	0x1600
+#define ENETC_SIRSSCAPR_GET_NUM_RSS(val) (BIT((val) & 0xf) * 32)
+
+/** SI BDR sub-blocks, n = 0..7 */
+enum enetc_bdr_type {TX, RX};
+#define ENETC_BDR_OFF(i)	((i) * 0x200)
+#define ENETC_BDR(t, i, r)	(0x8000 + (t) * 0x100 + ENETC_BDR_OFF(i) + (r))
+/* RX BDR reg offsets */
+#define ENETC_RBMR	0
+#define ENETC_RBMR_BDS	BIT(2)
+#define ENETC_RBMR_VTE	BIT(5)
+#define ENETC_RBMR_EN	BIT(31)
+#define ENETC_RBSR	0x4
+#define ENETC_RBBSR	0x8
+#define ENETC_RBCIR	0xc
+#define ENETC_RBBAR0	0x10
+#define ENETC_RBBAR1	0x14
+#define ENETC_RBPIR	0x18
+#define ENETC_RBLENR	0x20
+#define ENETC_RBIER	0xa0
+#define ENETC_RBIER_RXTIE	BIT(0)
+#define ENETC_RBIDR	0xa4
+#define ENETC_RBICIR0	0xa8
+#define ENETC_RBICIR0_ICEN	BIT(31)
+
+/* TX BDR reg offsets */
+#define ENETC_TBMR	0
+#define ENETC_TBSR_BUSY	BIT(0)
+#define ENETC_TBMR_VIH	BIT(9)
+#define ENETC_TBMR_PRIO_MASK		GENMASK(2, 0)
+#define ENETC_TBMR_PRIO_SET(val)	val
+#define ENETC_TBMR_EN	BIT(31)
+#define ENETC_TBSR	0x4
+#define ENETC_TBBAR0	0x10
+#define ENETC_TBBAR1	0x14
+#define ENETC_TBPIR	0x18
+#define ENETC_TBCIR	0x1c
+#define ENETC_TBCIR_IDX_MASK	0xffff
+#define ENETC_TBLENR	0x20
+#define ENETC_TBIER	0xa0
+#define ENETC_TBIER_TXTIE	BIT(0)
+#define ENETC_TBIDR	0xa4
+#define ENETC_TBICIR0	0xa8
+#define ENETC_TBICIR0_ICEN	BIT(31)
+
+#define ENETC_RTBLENR_LEN(n)	((n) & ~0x7)
+
+/* Port regs, offset: 1_0000h */
+#define ENETC_PORT_BASE		0x10000
+#define ENETC_PMR		0x0000
+#define ENETC_PMR_EN	GENMASK(18, 16)
+#define ENETC_PSR		0x0004 /* RO */
+#define ENETC_PSIPMR		0x0018
+#define ENETC_PSIPMR_SET_UP(n)	BIT(n) /* n = SI index */
+#define ENETC_PSIPMR_SET_MP(n)	BIT((n) + 16)
+#define ENETC_PSIPVMR		0x001c
+#define ENETC_VLAN_PROMISC_MAP_ALL	0x7
+#define ENETC_PSIPVMR_SET_VP(simap)	((simap) & 0x7)
+#define ENETC_PSIPVMR_SET_VUTA(simap)	(((simap) & 0x7) << 16)
+#define ENETC_PSIPMAR0(n)	(0x0100 + (n) * 0x8) /* n = SI index */
+#define ENETC_PSIPMAR1(n)	(0x0104 + (n) * 0x8)
+#define ENETC_PVCLCTR		0x0208
+#define ENETC_VLAN_TYPE_C	BIT(0)
+#define ENETC_VLAN_TYPE_S	BIT(1)
+#define ENETC_PVCLCTR_OVTPIDL(bmp)	((bmp) & 0xff) /* VLAN_TYPE */
+#define ENETC_PSIVLANR(n)	(0x0240 + (n) * 4) /* n = SI index */
+#define ENETC_PSIVLAN_EN	BIT(31)
+#define ENETC_PSIVLAN_SET_QOS(val)	((u32)(val) << 12)
+#define ENETC_PTXMBAR		0x0608
+#define ENETC_PCAPR0		0x0900
+#define ENETC_PCAPR0_RXBDR(val)	((val) >> 24)
+#define ENETC_PCAPR0_TXBDR(val)	(((val) >> 16) & 0xff)
+#define ENETC_PCAPR1		0x0904
+#define ENETC_PSICFGR0(n)	(0x0940 + (n) * 0xc)  /* n = SI index */
+#define ENETC_PSICFGR0_SET_TXBDR(val)	((val) & 0xff)
+#define ENETC_PSICFGR0_SET_RXBDR(val)	(((val) & 0xff) << 16)
+#define ENETC_PSICFGR0_VTE	BIT(12)
+#define ENETC_PSICFGR0_SIVIE	BIT(14)
+#define ENETC_PSICFGR0_ASE	BIT(15)
+#define ENETC_PSICFGR0_SIVC(bmp)	(((bmp) & 0xff) << 24) /* VLAN_TYPE */
+
+#define ENETC_PTCCBSR0(n)	(0x1110 + (n) * 8) /* n = 0 to 7*/
+#define ENETC_PTCCBSR1(n)	(0x1114 + (n) * 8) /* n = 0 to 7*/
+#define ENETC_RSSHASH_KEY_SIZE	40
+#define ENETC_PRSSK(n)		(0x1410 + (n) * 4) /* n = [0..9] */
+#define ENETC_PSIVLANFMR	0x1700
+#define ENETC_PSIVLANFMR_VS	BIT(0)
+#define ENETC_PRFSMR		0x1800
+#define ENETC_PRFSMR_RFSE	BIT(31)
+#define ENETC_PRFSCAPR		0x1804
+#define ENETC_PRFSCAPR_GET_NUM_RFS(val)	((((val) & 0xf) + 1) * 16)
+#define ENETC_PSIRFSCFGR(n)	(0x1814 + (n) * 4) /* n = SI index */
+#define ENETC_PFPMR		0x1900
+#define ENETC_PFPMR_PMACE	BIT(1)
+#define ENETC_PFPMR_MWLM	BIT(0)
+#define ENETC_PSIUMHFR0(n, err)	(((err) ? 0x1d08 : 0x1d00) + (n) * 0x10)
+#define ENETC_PSIUMHFR1(n)	(0x1d04 + (n) * 0x10)
+#define ENETC_PSIMMHFR0(n, err)	(((err) ? 0x1d00 : 0x1d08) + (n) * 0x10)
+#define ENETC_PSIMMHFR1(n)	(0x1d0c + (n) * 0x10)
+#define ENETC_PSIVHFR0(n)	(0x1e00 + (n) * 8) /* n = SI index */
+#define ENETC_PSIVHFR1(n)	(0x1e04 + (n) * 8) /* n = SI index */
+#define ENETC_MMCSR		0x1f00
+#define ENETC_MMCSR_ME		BIT(16)
+#define ENETC_PTCMSDUR(n)	(0x2020 + (n) * 4) /* n = TC index [0..7] */
+
+#define ENETC_PM0_CMD_CFG	0x8008
+#define ENETC_PM1_CMD_CFG	0x9008
+#define ENETC_PM0_TX_EN		BIT(0)
+#define ENETC_PM0_RX_EN		BIT(1)
+#define ENETC_PM0_PROMISC	BIT(4)
+#define ENETC_PM0_CMD_XGLP	BIT(10)
+#define ENETC_PM0_CMD_TXP	BIT(11)
+#define ENETC_PM0_CMD_PHY_TX_EN	BIT(15)
+#define ENETC_PM0_CMD_SFD	BIT(21)
+#define ENETC_PM0_MAXFRM	0x8014
+#define ENETC_SET_TX_MTU(val)	((val) << 16)
+#define ENETC_SET_MAXFRM(val)	((val) & 0xffff)
+#define ENETC_PM0_IF_MODE	0x8300
+#define ENETC_PMO_IFM_RG	BIT(2)
+#define ENETC_PM0_IFM_RLP	(BIT(5) | BIT(11))
+#define ENETC_PM0_IFM_RGAUTO	(BIT(15) | ENETC_PMO_IFM_RG | BIT(1))
+#define ENETC_PM0_IFM_XGMII	BIT(12)
+
+/* MAC counters */
+#define ENETC_PM0_REOCT		0x8100
+#define ENETC_PM0_RALN		0x8110
+#define ENETC_PM0_RXPF		0x8118
+#define ENETC_PM0_RFRM		0x8120
+#define ENETC_PM0_RFCS		0x8128
+#define ENETC_PM0_RVLAN		0x8130
+#define ENETC_PM0_RERR		0x8138
+#define ENETC_PM0_RUCA		0x8140
+#define ENETC_PM0_RMCA		0x8148
+#define ENETC_PM0_RBCA		0x8150
+#define ENETC_PM0_RDRP		0x8158
+#define ENETC_PM0_RPKT		0x8160
+#define ENETC_PM0_RUND		0x8168
+#define ENETC_PM0_R64		0x8170
+#define ENETC_PM0_R127		0x8178
+#define ENETC_PM0_R255		0x8180
+#define ENETC_PM0_R511		0x8188
+#define ENETC_PM0_R1023		0x8190
+#define ENETC_PM0_R1518		0x8198
+#define ENETC_PM0_R1519X	0x81A0
+#define ENETC_PM0_ROVR		0x81A8
+#define ENETC_PM0_RJBR		0x81B0
+#define ENETC_PM0_RFRG		0x81B8
+#define ENETC_PM0_RCNP		0x81C0
+#define ENETC_PM0_RDRNTP	0x81C8
+#define ENETC_PM0_TEOCT		0x8200
+#define ENETC_PM0_TOCT		0x8208
+#define ENETC_PM0_TCRSE		0x8210
+#define ENETC_PM0_TXPF		0x8218
+#define ENETC_PM0_TFRM		0x8220
+#define ENETC_PM0_TFCS		0x8228
+#define ENETC_PM0_TVLAN		0x8230
+#define ENETC_PM0_TERR		0x8238
+#define ENETC_PM0_TUCA		0x8240
+#define ENETC_PM0_TMCA		0x8248
+#define ENETC_PM0_TBCA		0x8250
+#define ENETC_PM0_TPKT		0x8260
+#define ENETC_PM0_TUND		0x8268
+#define ENETC_PM0_T127		0x8278
+#define ENETC_PM0_T1023		0x8290
+#define ENETC_PM0_T1518		0x8298
+#define ENETC_PM0_TCNP		0x82C0
+#define ENETC_PM0_TDFR		0x82D0
+#define ENETC_PM0_TMCOL		0x82D8
+#define ENETC_PM0_TSCOL		0x82E0
+#define ENETC_PM0_TLCOL		0x82E8
+#define ENETC_PM0_TECOL		0x82F0
+
+/* Port counters */
+#define ENETC_PICDR(n)		(0x0700 + (n) * 8) /* n = [0..3] */
+#define ENETC_PBFDSIR		0x0810
+#define ENETC_PFDMSAPR		0x0814
+#define ENETC_UFDMF		0x1680
+#define ENETC_MFDMF		0x1684
+#define ENETC_PUFDVFR		0x1780
+#define ENETC_PMFDVFR		0x1784
+#define ENETC_PBFDVFR		0x1788
+
+/** Global regs, offset: 2_0000h */
+#define ENETC_GLOBAL_BASE	0x20000
+#define ENETC_G_EIPBRR0		0x0bf8
+#define ENETC_G_EIPBRR1		0x0bfc
+#define ENETC_G_EPFBLPR(n)	(0xd00 + 4 * (n))
+#define ENETC_G_EPFBLPR1_XGMII	0x80000000
+
+/* PCI device info */
+struct enetc_hw {
+	/* SI registers, used by all PCI functions */
+	void __iomem *reg;
+	/* Port registers, PF only */
+	void __iomem *port;
+	/* IP global registers, PF only */
+	void __iomem *global;
+};
+
+/* general register accessors */
+#define enetc_rd_reg(reg)	ioread32((reg))
+#define enetc_wr_reg(reg, val)	iowrite32((val), (reg))
+#ifdef ioread64
+#define enetc_rd_reg64(reg)	ioread64((reg))
+#else
+/* using this to read out stats on 32b systems */
+static inline u64 enetc_rd_reg64(void __iomem *reg)
+{
+	u32 low, high, tmp;
+
+	do {
+		high = ioread32(reg + 4);
+		low = ioread32(reg);
+		tmp = ioread32(reg + 4);
+	} while (high != tmp);
+
+	return le64_to_cpu((__le64)high << 32 | low);
+}
+#endif
+
+#define enetc_rd(hw, off)		enetc_rd_reg((hw)->reg + (off))
+#define enetc_wr(hw, off, val)		enetc_wr_reg((hw)->reg + (off), val)
+#define enetc_rd64(hw, off)		enetc_rd_reg64((hw)->reg + (off))
+/* port register accessors - PF only */
+#define enetc_port_rd(hw, off)		enetc_rd_reg((hw)->port + (off))
+#define enetc_port_wr(hw, off, val)	enetc_wr_reg((hw)->port + (off), val)
+/* global register accessors - PF only */
+#define enetc_global_rd(hw, off)	enetc_rd_reg((hw)->global + (off))
+#define enetc_global_wr(hw, off, val)	enetc_wr_reg((hw)->global + (off), val)
+/* BDR register accessors, see ENETC_BDR() */
+#define enetc_bdr_rd(hw, t, n, off) \
+				enetc_rd(hw, ENETC_BDR(t, n, off))
+#define enetc_bdr_wr(hw, t, n, off, val) \
+				enetc_wr(hw, ENETC_BDR(t, n, off), val)
+#define enetc_txbdr_rd(hw, n, off) enetc_bdr_rd(hw, TX, n, off)
+#define enetc_rxbdr_rd(hw, n, off) enetc_bdr_rd(hw, RX, n, off)
+#define enetc_txbdr_wr(hw, n, off, val) \
+				enetc_bdr_wr(hw, TX, n, off, val)
+#define enetc_rxbdr_wr(hw, n, off, val) \
+				enetc_bdr_wr(hw, RX, n, off, val)
+
+/* Buffer Descriptors (BD) */
+union enetc_tx_bd {
+	struct {
+		__le64 addr;
+		__le16 buf_len;
+		__le16 frm_len;
+		union {
+			struct {
+				__le16 l3_csoff;
+				u8 l4_csoff;
+				u8 flags;
+			}; /* default layout */
+			__le32 lstatus;
+		};
+	};
+	struct {
+		__le32 tstamp;
+		__le16 tpid;
+		__le16 vid;
+		u8 reserved[6];
+		u8 e_flags;
+		u8 flags;
+	} ext; /* Tx BD extension */
+};
+
+#define ENETC_TXBD_FLAGS_L4CS	BIT(0)
+#define ENETC_TXBD_FLAGS_W	BIT(2)
+#define ENETC_TXBD_FLAGS_CSUM	BIT(3)
+#define ENETC_TXBD_FLAGS_EX	BIT(6)
+#define ENETC_TXBD_FLAGS_F	BIT(7)
+
+static inline void enetc_clear_tx_bd(union enetc_tx_bd *txbd)
+{
+	memset(txbd, 0, sizeof(*txbd));
+}
+
+/* L3 csum flags */
+#define ENETC_TXBD_L3_IPCS	BIT(7)
+#define ENETC_TXBD_L3_IPV6	BIT(15)
+
+#define ENETC_TXBD_L3_START_MASK	GENMASK(6, 0)
+#define ENETC_TXBD_L3_SET_HSIZE(val)	((((val) >> 2) & 0x7f) << 8)
+
+/* Extension flags */
+#define ENETC_TXBD_E_FLAGS_VLAN_INS	BIT(0)
+#define ENETC_TXBD_E_FLAGS_TWO_STEP_PTP	BIT(2)
+
+static inline __le16 enetc_txbd_l3_csoff(int start, int hdr_sz, u16 l3_flags)
+{
+	return cpu_to_le16(l3_flags | ENETC_TXBD_L3_SET_HSIZE(hdr_sz) |
+			   (start & ENETC_TXBD_L3_START_MASK));
+}
+
+/* L4 csum flags */
+#define ENETC_TXBD_L4_UDP	BIT(5)
+#define ENETC_TXBD_L4_TCP	BIT(6)
+
+union enetc_rx_bd {
+	struct {
+		__le64 addr;
+		u8 reserved[8];
+	} w;
+	struct {
+		__le16 inet_csum;
+		__le16 parse_summary;
+		__le32 rss_hash;
+		__le16 buf_len;
+		__le16 vlan_opt;
+		union {
+			struct {
+				__le16 flags;
+				__le16 error;
+			};
+			__le32 lstatus;
+		};
+	} r;
+};
+
+#define ENETC_RXBD_LSTATUS_R	BIT(30)
+#define ENETC_RXBD_LSTATUS_F	BIT(31)
+#define ENETC_RXBD_ERR_MASK	0xff
+#define ENETC_RXBD_LSTATUS(flags)	((flags) << 16)
+#define ENETC_RXBD_FLAG_VLAN	BIT(9)
+#define ENETC_RXBD_FLAG_TSTMP	BIT(10)
+
+#define ENETC_MAC_ADDR_FILT_CNT	8 /* # of supported entries per port */
+#define EMETC_MAC_ADDR_FILT_RES	3 /* # of reserved entries at the beginning */
+#define ENETC_MAX_NUM_VFS	2
+
+struct enetc_cbd {
+	union {
+		struct {
+			__le32 addr[2];
+			__le32 opt[4];
+		};
+		__le32 data[6];
+	};
+	__le16 index;
+	__le16 length;
+	u8 cmd;
+	u8 cls;
+	u8 _res;
+	u8 status_flags;
+};
+
+#define ENETC_CBD_FLAGS_SF	BIT(7) /* short format */
+#define ENETC_CBD_STATUS_MASK	0xf
+
+struct enetc_cmd_rfse {
+	u8 smac_h[6];
+	u8 smac_m[6];
+	u8 dmac_h[6];
+	u8 dmac_m[6];
+	u32 sip_h[4];
+	u32 sip_m[4];
+	u32 dip_h[4];
+	u32 dip_m[4];
+	u16 ethtype_h;
+	u16 ethtype_m;
+	u16 ethtype4_h;
+	u16 ethtype4_m;
+	u16 sport_h;
+	u16 sport_m;
+	u16 dport_h;
+	u16 dport_m;
+	u16 vlan_h;
+	u16 vlan_m;
+	u8 proto_h;
+	u8 proto_m;
+	u16 flags;
+	u16 result;
+	u16 mode;
+};
+
+#define ENETC_RFSE_EN	BIT(15)
+#define ENETC_RFSE_MODE_BD	2
+
+static inline void enetc_get_primary_mac_addr(struct enetc_hw *hw, u8 *addr)
+{
+	*(u32 *)addr = __raw_readl(hw->reg + ENETC_SIPMAR0);
+	*(u16 *)(addr + 4) = __raw_readw(hw->reg + ENETC_SIPMAR1);
+}
+
+#define ENETC_SI_INT_IDX	0
+/* base index for Rx/Tx interrupts */
+#define ENETC_BDR_INT_BASE_IDX	1
+
+/* Messaging */
+
+/* Command completion status */
+enum enetc_msg_cmd_status {
+	ENETC_MSG_CMD_STATUS_OK,
+	ENETC_MSG_CMD_STATUS_FAIL
+};
+
+/* VSI-PSI command message types */
+enum enetc_msg_cmd_type {
+	ENETC_MSG_CMD_MNG_MAC = 1, /* manage MAC address */
+	ENETC_MSG_CMD_MNG_RX_MAC_FILTER,/* manage RX MAC table */
+	ENETC_MSG_CMD_MNG_RX_VLAN_FILTER /* manage RX VLAN table */
+};
+
+/* VSI-PSI command action types */
+enum enetc_msg_cmd_action_type {
+	ENETC_MSG_CMD_MNG_ADD = 1,
+	ENETC_MSG_CMD_MNG_REMOVE
+};
+
+/* PSI-VSI command header format */
+struct enetc_msg_cmd_header {
+	u16 type;	/* command class type */
+	u16 id;		/* denotes the specific required action */
+};
+
+/* Common H/W utility functions */
+
+static inline void enetc_enable_rxvlan(struct enetc_hw *hw, int si_idx,
+				       bool en)
+{
+	u32 val = enetc_rxbdr_rd(hw, si_idx, ENETC_RBMR);
+
+	val = (val & ~ENETC_RBMR_VTE) | (en ? ENETC_RBMR_VTE : 0);
+	enetc_rxbdr_wr(hw, si_idx, ENETC_RBMR, val);
+}
+
+static inline void enetc_enable_txvlan(struct enetc_hw *hw, int si_idx,
+				       bool en)
+{
+	u32 val = enetc_txbdr_rd(hw, si_idx, ENETC_TBMR);
+
+	val = (val & ~ENETC_TBMR_VIH) | (en ? ENETC_TBMR_VIH : 0);
+	enetc_txbdr_wr(hw, si_idx, ENETC_TBMR, val);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
new file mode 100644
index 000000000000..77b9cd10ba2b
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2019 NXP */
+
+#include <linux/mdio.h>
+#include <linux/of_mdio.h>
+#include <linux/iopoll.h>
+#include <linux/of.h>
+
+#include "enetc_pf.h"
+
+struct enetc_mdio_regs {
+	u32	mdio_cfg;	/* MDIO configuration and status */
+	u32	mdio_ctl;	/* MDIO control */
+	u32	mdio_data;	/* MDIO data */
+	u32	mdio_addr;	/* MDIO address */
+};
+
+#define bus_to_enetc_regs(bus)	(struct enetc_mdio_regs __iomem *)((bus)->priv)
+
+#define ENETC_MDIO_REG_OFFSET	0x1c00
+#define ENETC_MDC_DIV		258
+
+#define MDIO_CFG_CLKDIV(x)	((((x) >> 1) & 0xff) << 8)
+#define MDIO_CFG_BSY		BIT(0)
+#define MDIO_CFG_RD_ER		BIT(1)
+#define MDIO_CFG_ENC45		BIT(6)
+ /* external MDIO only - driven on neg MDC edge */
+#define MDIO_CFG_NEG		BIT(23)
+
+#define MDIO_CTL_DEV_ADDR(x)	((x) & 0x1f)
+#define MDIO_CTL_PORT_ADDR(x)	(((x) & 0x1f) << 5)
+#define MDIO_CTL_READ		BIT(15)
+#define MDIO_DATA(x)		((x) & 0xffff)
+
+#define TIMEOUT	1000
+static int enetc_mdio_wait_complete(struct enetc_mdio_regs __iomem *regs)
+{
+	u32 val;
+
+	return readx_poll_timeout(enetc_rd_reg, &regs->mdio_cfg, val,
+				  !(val & MDIO_CFG_BSY), 10, 10 * TIMEOUT);
+}
+
+static int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum,
+			    u16 value)
+{
+	struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus);
+	u32 mdio_ctl, mdio_cfg;
+	u16 dev_addr;
+	int ret;
+
+	mdio_cfg = MDIO_CFG_CLKDIV(ENETC_MDC_DIV) | MDIO_CFG_NEG;
+	if (regnum & MII_ADDR_C45) {
+		dev_addr = (regnum >> 16) & 0x1f;
+		mdio_cfg |= MDIO_CFG_ENC45;
+	} else {
+		/* clause 22 (ie 1G) */
+		dev_addr = regnum & 0x1f;
+		mdio_cfg &= ~MDIO_CFG_ENC45;
+	}
+
+	enetc_wr_reg(&regs->mdio_cfg, mdio_cfg);
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	/* set port and dev addr */
+	mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
+	enetc_wr_reg(&regs->mdio_ctl, mdio_ctl);
+
+	/* set the register address */
+	if (regnum & MII_ADDR_C45) {
+		enetc_wr_reg(&regs->mdio_addr, regnum & 0xffff);
+
+		ret = enetc_mdio_wait_complete(regs);
+		if (ret)
+			return ret;
+	}
+
+	/* write the value */
+	enetc_wr_reg(&regs->mdio_data, MDIO_DATA(value));
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
+{
+	struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus);
+	u32 mdio_ctl, mdio_cfg;
+	u16 dev_addr, value;
+	int ret;
+
+	mdio_cfg = MDIO_CFG_CLKDIV(ENETC_MDC_DIV) | MDIO_CFG_NEG;
+	if (regnum & MII_ADDR_C45) {
+		dev_addr = (regnum >> 16) & 0x1f;
+		mdio_cfg |= MDIO_CFG_ENC45;
+	} else {
+		dev_addr = regnum & 0x1f;
+		mdio_cfg &= ~MDIO_CFG_ENC45;
+	}
+
+	enetc_wr_reg(&regs->mdio_cfg, mdio_cfg);
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	/* set port and device addr */
+	mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr);
+	enetc_wr_reg(&regs->mdio_ctl, mdio_ctl);
+
+	/* set the register address */
+	if (regnum & MII_ADDR_C45) {
+		enetc_wr_reg(&regs->mdio_addr, regnum & 0xffff);
+
+		ret = enetc_mdio_wait_complete(regs);
+		if (ret)
+			return ret;
+	}
+
+	/* initiate the read */
+	enetc_wr_reg(&regs->mdio_ctl, mdio_ctl | MDIO_CTL_READ);
+
+	ret = enetc_mdio_wait_complete(regs);
+	if (ret)
+		return ret;
+
+	/* return all Fs if nothing was there */
+	if (enetc_rd_reg(&regs->mdio_cfg) & MDIO_CFG_RD_ER) {
+		dev_dbg(&bus->dev,
+			"Error while reading PHY%d reg at %d.%hhu\n",
+			phy_id, dev_addr, regnum);
+		return 0xffff;
+	}
+
+	value = enetc_rd_reg(&regs->mdio_data) & 0xffff;
+
+	return value;
+}
+
+int enetc_mdio_probe(struct enetc_pf *pf)
+{
+	struct device *dev = &pf->si->pdev->dev;
+	struct enetc_mdio_regs __iomem *regs;
+	struct device_node *np;
+	struct mii_bus *bus;
+	int ret;
+
+	bus = mdiobus_alloc_size(sizeof(regs));
+	if (!bus)
+		return -ENOMEM;
+
+	bus->name = "Freescale ENETC MDIO Bus";
+	bus->read = enetc_mdio_read;
+	bus->write = enetc_mdio_write;
+	bus->parent = dev;
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev));
+
+	/* store the enetc mdio base address for this bus */
+	regs = pf->si->hw.port + ENETC_MDIO_REG_OFFSET;
+	bus->priv = regs;
+
+	np = of_get_child_by_name(dev->of_node, "mdio");
+	if (!np) {
+		dev_err(dev, "MDIO node missing\n");
+		ret = -EINVAL;
+		goto err_registration;
+	}
+
+	ret = of_mdiobus_register(bus, np);
+	if (ret) {
+		of_node_put(np);
+		dev_err(dev, "cannot register MDIO bus\n");
+		goto err_registration;
+	}
+
+	of_node_put(np);
+	pf->mdio = bus;
+
+	return 0;
+
+err_registration:
+	mdiobus_free(bus);
+
+	return ret;
+}
+
+void enetc_mdio_remove(struct enetc_pf *pf)
+{
+	if (pf->mdio) {
+		mdiobus_unregister(pf->mdio);
+		mdiobus_free(pf->mdio);
+	}
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_msg.c b/drivers/net/ethernet/freescale/enetc/enetc_msg.c
new file mode 100644
index 000000000000..40d22ebe9224
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_msg.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include "enetc_pf.h"
+
+static void enetc_msg_disable_mr_int(struct enetc_hw *hw)
+{
+	u32 psiier = enetc_rd(hw, ENETC_PSIIER);
+	/* disable MR int source(s) */
+	enetc_wr(hw, ENETC_PSIIER, psiier & ~ENETC_PSIIER_MR_MASK);
+}
+
+static void enetc_msg_enable_mr_int(struct enetc_hw *hw)
+{
+	u32 psiier = enetc_rd(hw, ENETC_PSIIER);
+
+	enetc_wr(hw, ENETC_PSIIER, psiier | ENETC_PSIIER_MR_MASK);
+}
+
+static irqreturn_t enetc_msg_psi_msix(int irq, void *data)
+{
+	struct enetc_si *si = (struct enetc_si *)data;
+	struct enetc_pf *pf = enetc_si_priv(si);
+
+	enetc_msg_disable_mr_int(&si->hw);
+	schedule_work(&pf->msg_task);
+
+	return IRQ_HANDLED;
+}
+
+static void enetc_msg_task(struct work_struct *work)
+{
+	struct enetc_pf *pf = container_of(work, struct enetc_pf, msg_task);
+	struct enetc_hw *hw = &pf->si->hw;
+	unsigned long mr_mask;
+	int i;
+
+	for (;;) {
+		mr_mask = enetc_rd(hw, ENETC_PSIMSGRR) & ENETC_PSIMSGRR_MR_MASK;
+		if (!mr_mask) {
+			/* re-arm MR interrupts, w1c the IDR reg */
+			enetc_wr(hw, ENETC_PSIIDR, ENETC_PSIIER_MR_MASK);
+			enetc_msg_enable_mr_int(hw);
+			return;
+		}
+
+		for (i = 0; i < pf->num_vfs; i++) {
+			u32 psimsgrr;
+			u16 msg_code;
+
+			if (!(ENETC_PSIMSGRR_MR(i) & mr_mask))
+				continue;
+
+			enetc_msg_handle_rxmsg(pf, i, &msg_code);
+
+			psimsgrr = ENETC_SIMSGSR_SET_MC(msg_code);
+			psimsgrr |= ENETC_PSIMSGRR_MR(i); /* w1c */
+			enetc_wr(hw, ENETC_PSIMSGRR, psimsgrr);
+		}
+	}
+}
+
+/* Init */
+static int enetc_msg_alloc_mbx(struct enetc_si *si, int idx)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct device *dev = &si->pdev->dev;
+	struct enetc_hw *hw = &si->hw;
+	struct enetc_msg_swbd *msg;
+	u32 val;
+
+	msg = &pf->rxmsg[idx];
+	/* allocate and set receive buffer */
+	msg->size = ENETC_DEFAULT_MSG_SIZE;
+
+	msg->vaddr = dma_alloc_coherent(dev, msg->size, &msg->dma,
+					GFP_KERNEL);
+	if (!msg->vaddr) {
+		dev_err(dev, "msg: fail to alloc dma buffer of size: %d\n",
+			msg->size);
+		return -ENOMEM;
+	}
+
+	/* set multiple of 32 bytes */
+	val = lower_32_bits(msg->dma);
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR0(idx), val);
+	val = upper_32_bits(msg->dma);
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR1(idx), val);
+
+	return 0;
+}
+
+static void enetc_msg_free_mbx(struct enetc_si *si, int idx)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	struct enetc_msg_swbd *msg;
+
+	msg = &pf->rxmsg[idx];
+	dma_free_coherent(&si->pdev->dev, msg->size, msg->vaddr, msg->dma);
+	memset(msg, 0, sizeof(*msg));
+
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR0(idx), 0);
+	enetc_wr(hw, ENETC_PSIVMSGRCVAR1(idx), 0);
+}
+
+int enetc_msg_psi_init(struct enetc_pf *pf)
+{
+	struct enetc_si *si = pf->si;
+	int vector, i, err;
+
+	/* register message passing interrupt handler */
+	snprintf(pf->msg_int_name, sizeof(pf->msg_int_name), "%s-vfmsg",
+		 si->ndev->name);
+	vector = pci_irq_vector(si->pdev, ENETC_SI_INT_IDX);
+	err = request_irq(vector, enetc_msg_psi_msix, 0, pf->msg_int_name, si);
+	if (err) {
+		dev_err(&si->pdev->dev,
+			"PSI messaging: request_irq() failed!\n");
+		return err;
+	}
+
+	/* set one IRQ entry for PSI message receive notification (SI int) */
+	enetc_wr(&si->hw, ENETC_SIMSIVR, ENETC_SI_INT_IDX);
+
+	/* initialize PSI mailbox */
+	INIT_WORK(&pf->msg_task, enetc_msg_task);
+
+	for (i = 0; i < pf->num_vfs; i++) {
+		err = enetc_msg_alloc_mbx(si, i);
+		if (err)
+			goto err_init_mbx;
+	}
+
+	/* enable MR interrupts */
+	enetc_msg_enable_mr_int(&si->hw);
+
+	return 0;
+
+err_init_mbx:
+	for (i--; i >= 0; i--)
+		enetc_msg_free_mbx(si, i);
+
+	free_irq(vector, si);
+
+	return err;
+}
+
+void enetc_msg_psi_free(struct enetc_pf *pf)
+{
+	struct enetc_si *si = pf->si;
+	int i;
+
+	cancel_work_sync(&pf->msg_task);
+
+	/* disable MR interrupts */
+	enetc_msg_disable_mr_int(&si->hw);
+
+	for (i = 0; i < pf->num_vfs; i++)
+		enetc_msg_free_mbx(si, i);
+
+	/* de-register message passing interrupt handler */
+	free_irq(pci_irq_vector(si->pdev, ENETC_SI_INT_IDX), si);
+}
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
new file mode 100644
index 000000000000..15876a6e7598
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c
@@ -0,0 +1,943 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include <linux/module.h>
+#include <linux/of_mdio.h>
+#include <linux/of_net.h>
+#include "enetc_pf.h"
+
+#define ENETC_DRV_VER_MAJ 1
+#define ENETC_DRV_VER_MIN 0
+
+#define ENETC_DRV_VER_STR __stringify(ENETC_DRV_VER_MAJ) "." \
+			  __stringify(ENETC_DRV_VER_MIN)
+static const char enetc_drv_ver[] = ENETC_DRV_VER_STR;
+#define ENETC_DRV_NAME_STR "ENETC PF driver"
+static const char enetc_drv_name[] = ENETC_DRV_NAME_STR;
+
+static void enetc_pf_get_primary_mac_addr(struct enetc_hw *hw, int si, u8 *addr)
+{
+	u32 upper = __raw_readl(hw->port + ENETC_PSIPMAR0(si));
+	u16 lower = __raw_readw(hw->port + ENETC_PSIPMAR1(si));
+
+	*(u32 *)addr = upper;
+	*(u16 *)(addr + 4) = lower;
+}
+
+static void enetc_pf_set_primary_mac_addr(struct enetc_hw *hw, int si,
+					  const u8 *addr)
+{
+	u32 upper = *(const u32 *)addr;
+	u16 lower = *(const u16 *)(addr + 4);
+
+	__raw_writel(upper, hw->port + ENETC_PSIPMAR0(si));
+	__raw_writew(lower, hw->port + ENETC_PSIPMAR1(si));
+}
+
+static int enetc_pf_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(ndev->dev_addr, saddr->sa_data, ndev->addr_len);
+	enetc_pf_set_primary_mac_addr(&priv->si->hw, 0, saddr->sa_data);
+
+	return 0;
+}
+
+static void enetc_set_vlan_promisc(struct enetc_hw *hw, char si_map)
+{
+	u32 val = enetc_port_rd(hw, ENETC_PSIPVMR);
+
+	val &= ~ENETC_PSIPVMR_SET_VP(ENETC_VLAN_PROMISC_MAP_ALL);
+	enetc_port_wr(hw, ENETC_PSIPVMR, ENETC_PSIPVMR_SET_VP(si_map) | val);
+}
+
+static bool enetc_si_vlan_promisc_is_on(struct enetc_pf *pf, int si_idx)
+{
+	return pf->vlan_promisc_simap & BIT(si_idx);
+}
+
+static bool enetc_vlan_filter_is_on(struct enetc_pf *pf)
+{
+	int i;
+
+	for_each_set_bit(i, pf->active_vlans, VLAN_N_VID)
+		return true;
+
+	return false;
+}
+
+static void enetc_enable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
+{
+	pf->vlan_promisc_simap |= BIT(si_idx);
+	enetc_set_vlan_promisc(&pf->si->hw, pf->vlan_promisc_simap);
+}
+
+static void enetc_disable_si_vlan_promisc(struct enetc_pf *pf, int si_idx)
+{
+	pf->vlan_promisc_simap &= ~BIT(si_idx);
+	enetc_set_vlan_promisc(&pf->si->hw, pf->vlan_promisc_simap);
+}
+
+static void enetc_set_isol_vlan(struct enetc_hw *hw, int si, u16 vlan, u8 qos)
+{
+	u32 val = 0;
+
+	if (vlan)
+		val = ENETC_PSIVLAN_EN | ENETC_PSIVLAN_SET_QOS(qos) | vlan;
+
+	enetc_port_wr(hw, ENETC_PSIVLANR(si), val);
+}
+
+static int enetc_mac_addr_hash_idx(const u8 *addr)
+{
+	u64 fold = __swab64(ether_addr_to_u64(addr)) >> 16;
+	u64 mask = 0;
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 8; i++)
+		mask |= BIT_ULL(i * 6);
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight64(fold & (mask << i)) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_reset_mac_addr_filter(struct enetc_mac_filter *filter)
+{
+	filter->mac_addr_cnt = 0;
+
+	bitmap_zero(filter->mac_hash_table,
+		    ENETC_MADDR_HASH_TBL_SZ);
+}
+
+static void enetc_add_mac_addr_em_filter(struct enetc_mac_filter *filter,
+					 const unsigned char *addr)
+{
+	/* add exact match addr */
+	ether_addr_copy(filter->mac_addr, addr);
+	filter->mac_addr_cnt++;
+}
+
+static void enetc_add_mac_addr_ht_filter(struct enetc_mac_filter *filter,
+					 const unsigned char *addr)
+{
+	int idx = enetc_mac_addr_hash_idx(addr);
+
+	/* add hash table entry */
+	__set_bit(idx, filter->mac_hash_table);
+	filter->mac_addr_cnt++;
+}
+
+static void enetc_clear_mac_ht_flt(struct enetc_si *si, int si_idx, int type)
+{
+	bool err = si->errata & ENETC_ERR_UCMCSWP;
+
+	if (type == UC) {
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR0(si_idx, err), 0);
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR1(si_idx), 0);
+	} else { /* MC */
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR0(si_idx, err), 0);
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR1(si_idx), 0);
+	}
+}
+
+static void enetc_set_mac_ht_flt(struct enetc_si *si, int si_idx, int type,
+				 u32 *hash)
+{
+	bool err = si->errata & ENETC_ERR_UCMCSWP;
+
+	if (type == UC) {
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR0(si_idx, err), *hash);
+		enetc_port_wr(&si->hw, ENETC_PSIUMHFR1(si_idx), *(hash + 1));
+	} else { /* MC */
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR0(si_idx, err), *hash);
+		enetc_port_wr(&si->hw, ENETC_PSIMMHFR1(si_idx), *(hash + 1));
+	}
+}
+
+static void enetc_sync_mac_filters(struct enetc_pf *pf)
+{
+	struct enetc_mac_filter *f = pf->mac_filter;
+	struct enetc_si *si = pf->si;
+	int i, pos;
+
+	pos = EMETC_MAC_ADDR_FILT_RES;
+
+	for (i = 0; i < MADDR_TYPE; i++, f++) {
+		bool em = (f->mac_addr_cnt == 1) && (i == UC);
+		bool clear = !f->mac_addr_cnt;
+
+		if (clear) {
+			if (i == UC)
+				enetc_clear_mac_flt_entry(si, pos);
+
+			enetc_clear_mac_ht_flt(si, 0, i);
+			continue;
+		}
+
+		/* exact match filter */
+		if (em) {
+			int err;
+
+			enetc_clear_mac_ht_flt(si, 0, UC);
+
+			err = enetc_set_mac_flt_entry(si, pos, f->mac_addr,
+						      BIT(0));
+			if (!err)
+				continue;
+
+			/* fallback to HT filtering */
+			dev_warn(&si->pdev->dev, "fallback to HT filt (%d)\n",
+				 err);
+		}
+
+		/* hash table filter, clear EM filter for UC entries */
+		if (i == UC)
+			enetc_clear_mac_flt_entry(si, pos);
+
+		enetc_set_mac_ht_flt(si, 0, i, (u32 *)f->mac_hash_table);
+	}
+}
+
+static void enetc_pf_set_rx_mode(struct net_device *ndev)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	struct enetc_hw *hw = &priv->si->hw;
+	bool uprom = false, mprom = false;
+	struct enetc_mac_filter *filter;
+	struct netdev_hw_addr *ha;
+	u32 psipmr = 0;
+	bool em;
+
+	if (ndev->flags & IFF_PROMISC) {
+		/* enable promisc mode for SI0 (PF) */
+		psipmr = ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0);
+		uprom = true;
+		mprom = true;
+		/* enable VLAN promisc mode for SI0 */
+		if (!enetc_si_vlan_promisc_is_on(pf, 0))
+			enetc_enable_si_vlan_promisc(pf, 0);
+
+	} else if (ndev->flags & IFF_ALLMULTI) {
+		/* enable multi cast promisc mode for SI0 (PF) */
+		psipmr = ENETC_PSIPMR_SET_MP(0);
+		mprom = true;
+	}
+
+	/* first 2 filter entries belong to PF */
+	if (!uprom) {
+		/* Update unicast filters */
+		filter = &pf->mac_filter[UC];
+		enetc_reset_mac_addr_filter(filter);
+
+		em = (netdev_uc_count(ndev) == 1);
+		netdev_for_each_uc_addr(ha, ndev) {
+			if (em) {
+				enetc_add_mac_addr_em_filter(filter, ha->addr);
+				break;
+			}
+
+			enetc_add_mac_addr_ht_filter(filter, ha->addr);
+		}
+	}
+
+	if (!mprom) {
+		/* Update multicast filters */
+		filter = &pf->mac_filter[MC];
+		enetc_reset_mac_addr_filter(filter);
+
+		netdev_for_each_mc_addr(ha, ndev) {
+			if (!is_multicast_ether_addr(ha->addr))
+				continue;
+
+			enetc_add_mac_addr_ht_filter(filter, ha->addr);
+		}
+	}
+
+	if (!uprom || !mprom)
+		/* update PF entries */
+		enetc_sync_mac_filters(pf);
+
+	psipmr |= enetc_port_rd(hw, ENETC_PSIPMR) &
+		  ~(ENETC_PSIPMR_SET_UP(0) | ENETC_PSIPMR_SET_MP(0));
+	enetc_port_wr(hw, ENETC_PSIPMR, psipmr);
+}
+
+static void enetc_set_vlan_ht_filter(struct enetc_hw *hw, int si_idx,
+				     u32 *hash)
+{
+	enetc_port_wr(hw, ENETC_PSIVHFR0(si_idx), *hash);
+	enetc_port_wr(hw, ENETC_PSIVHFR1(si_idx), *(hash + 1));
+}
+
+static int enetc_vid_hash_idx(unsigned int vid)
+{
+	int res = 0;
+	int i;
+
+	for (i = 0; i < 6; i++)
+		res |= (hweight8(vid & (BIT(i) | BIT(i + 6))) & 0x1) << i;
+
+	return res;
+}
+
+static void enetc_sync_vlan_ht_filter(struct enetc_pf *pf, bool rehash)
+{
+	int i;
+
+	if (rehash) {
+		bitmap_zero(pf->vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+
+		for_each_set_bit(i, pf->active_vlans, VLAN_N_VID) {
+			int hidx = enetc_vid_hash_idx(i);
+
+			__set_bit(hidx, pf->vlan_ht_filter);
+		}
+	}
+
+	enetc_set_vlan_ht_filter(&pf->si->hw, 0, (u32 *)pf->vlan_ht_filter);
+}
+
+static int enetc_vlan_rx_add_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	int idx;
+
+	if (enetc_si_vlan_promisc_is_on(pf, 0))
+		enetc_disable_si_vlan_promisc(pf, 0);
+
+	__set_bit(vid, pf->active_vlans);
+
+	idx = enetc_vid_hash_idx(vid);
+	if (!__test_and_set_bit(idx, pf->vlan_ht_filter))
+		enetc_sync_vlan_ht_filter(pf, false);
+
+	return 0;
+}
+
+static int enetc_vlan_rx_del_vid(struct net_device *ndev, __be16 prot, u16 vid)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	__clear_bit(vid, pf->active_vlans);
+	enetc_sync_vlan_ht_filter(pf, true);
+
+	if (!enetc_vlan_filter_is_on(pf))
+		enetc_enable_si_vlan_promisc(pf, 0);
+
+	return 0;
+}
+
+static void enetc_set_loopback(struct net_device *ndev, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_hw *hw = &priv->si->hw;
+	u32 reg;
+
+	reg = enetc_port_rd(hw, ENETC_PM0_IF_MODE);
+	if (reg & ENETC_PMO_IFM_RG) {
+		/* RGMII mode */
+		reg = (reg & ~ENETC_PM0_IFM_RLP) |
+		      (en ? ENETC_PM0_IFM_RLP : 0);
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, reg);
+	} else {
+		/* assume SGMII mode */
+		reg = enetc_port_rd(hw, ENETC_PM0_CMD_CFG);
+		reg = (reg & ~ENETC_PM0_CMD_XGLP) |
+		      (en ? ENETC_PM0_CMD_XGLP : 0);
+		reg = (reg & ~ENETC_PM0_CMD_PHY_TX_EN) |
+		      (en ? ENETC_PM0_CMD_PHY_TX_EN : 0);
+		enetc_port_wr(hw, ENETC_PM0_CMD_CFG, reg);
+		enetc_port_wr(hw, ENETC_PM1_CMD_CFG, reg);
+	}
+}
+
+static int enetc_pf_set_vf_mac(struct net_device *ndev, int vf, u8 *mac)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	struct enetc_vf_state *vf_state;
+
+	if (vf >= pf->total_vfs)
+		return -EINVAL;
+
+	if (!is_valid_ether_addr(mac))
+		return -EADDRNOTAVAIL;
+
+	vf_state = &pf->vf_state[vf];
+	vf_state->flags |= ENETC_VF_FLAG_PF_SET_MAC;
+	enetc_pf_set_primary_mac_addr(&priv->si->hw, vf + 1, mac);
+	return 0;
+}
+
+static int enetc_pf_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan,
+				u8 qos, __be16 proto)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+
+	if (priv->si->errata & ENETC_ERR_VLAN_ISOL)
+		return -EOPNOTSUPP;
+
+	if (vf >= pf->total_vfs)
+		return -EINVAL;
+
+	if (proto != htons(ETH_P_8021Q))
+		/* only C-tags supported for now */
+		return -EPROTONOSUPPORT;
+
+	enetc_set_isol_vlan(&priv->si->hw, vf + 1, vlan, qos);
+	return 0;
+}
+
+static int enetc_pf_set_vf_spoofchk(struct net_device *ndev, int vf, bool en)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	u32 cfgr;
+
+	if (vf >= pf->total_vfs)
+		return -EINVAL;
+
+	cfgr = enetc_port_rd(&priv->si->hw, ENETC_PSICFGR0(vf + 1));
+	cfgr = (cfgr & ~ENETC_PSICFGR0_ASE) | (en ? ENETC_PSICFGR0_ASE : 0);
+	enetc_port_wr(&priv->si->hw, ENETC_PSICFGR0(vf + 1), cfgr);
+
+	return 0;
+}
+
+static void enetc_port_setup_primary_mac_address(struct enetc_si *si)
+{
+	unsigned char mac_addr[MAX_ADDR_LEN];
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	int i;
+
+	/* check MAC addresses for PF and all VFs, if any is 0 set it ro rand */
+	for (i = 0; i < pf->total_vfs + 1; i++) {
+		enetc_pf_get_primary_mac_addr(hw, i, mac_addr);
+		if (!is_zero_ether_addr(mac_addr))
+			continue;
+		eth_random_addr(mac_addr);
+		dev_info(&si->pdev->dev, "no MAC address specified for SI%d, using %pM\n",
+			 i, mac_addr);
+		enetc_pf_set_primary_mac_addr(hw, i, mac_addr);
+	}
+}
+
+static void enetc_port_assign_rfs_entries(struct enetc_si *si)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	int num_entries, vf_entries, i;
+	u32 val;
+
+	/* split RFS entries between functions */
+	val = enetc_port_rd(hw, ENETC_PRFSCAPR);
+	num_entries = ENETC_PRFSCAPR_GET_NUM_RFS(val);
+	vf_entries = num_entries / (pf->total_vfs + 1);
+
+	for (i = 0; i < pf->total_vfs; i++)
+		enetc_port_wr(hw, ENETC_PSIRFSCFGR(i + 1), vf_entries);
+	enetc_port_wr(hw, ENETC_PSIRFSCFGR(0),
+		      num_entries - vf_entries * pf->total_vfs);
+
+	/* enable RFS on port */
+	enetc_port_wr(hw, ENETC_PRFSMR, ENETC_PRFSMR_RFSE);
+}
+
+static void enetc_port_si_configure(struct enetc_si *si)
+{
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_hw *hw = &si->hw;
+	int num_rings, i;
+	u32 val;
+
+	val = enetc_port_rd(hw, ENETC_PCAPR0);
+	num_rings = min(ENETC_PCAPR0_RXBDR(val), ENETC_PCAPR0_TXBDR(val));
+
+	val = ENETC_PSICFGR0_SET_TXBDR(ENETC_PF_NUM_RINGS);
+	val |= ENETC_PSICFGR0_SET_RXBDR(ENETC_PF_NUM_RINGS);
+
+	if (unlikely(num_rings < ENETC_PF_NUM_RINGS)) {
+		val = ENETC_PSICFGR0_SET_TXBDR(num_rings);
+		val |= ENETC_PSICFGR0_SET_RXBDR(num_rings);
+
+		dev_warn(&si->pdev->dev, "Found %d rings, expected %d!\n",
+			 num_rings, ENETC_PF_NUM_RINGS);
+
+		num_rings = 0;
+	}
+
+	/* Add default one-time settings for SI0 (PF) */
+	val |= ENETC_PSICFGR0_SIVC(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S);
+
+	enetc_port_wr(hw, ENETC_PSICFGR0(0), val);
+
+	if (num_rings)
+		num_rings -= ENETC_PF_NUM_RINGS;
+
+	/* Configure the SIs for each available VF */
+	val = ENETC_PSICFGR0_SIVC(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S);
+	val |= ENETC_PSICFGR0_VTE | ENETC_PSICFGR0_SIVIE;
+
+	if (num_rings) {
+		num_rings /= pf->total_vfs;
+		val |= ENETC_PSICFGR0_SET_TXBDR(num_rings);
+		val |= ENETC_PSICFGR0_SET_RXBDR(num_rings);
+	}
+
+	for (i = 0; i < pf->total_vfs; i++)
+		enetc_port_wr(hw, ENETC_PSICFGR0(i + 1), val);
+
+	/* Port level VLAN settings */
+	val = ENETC_PVCLCTR_OVTPIDL(ENETC_VLAN_TYPE_C | ENETC_VLAN_TYPE_S);
+	enetc_port_wr(hw, ENETC_PVCLCTR, val);
+	/* use outer tag for VLAN filtering */
+	enetc_port_wr(hw, ENETC_PSIVLANFMR, ENETC_PSIVLANFMR_VS);
+}
+
+static void enetc_configure_port_mac(struct enetc_hw *hw)
+{
+	enetc_port_wr(hw, ENETC_PM0_MAXFRM,
+		      ENETC_SET_MAXFRM(ENETC_RX_MAXFRM_SIZE));
+
+	enetc_port_wr(hw, ENETC_PTCMSDUR(0), ENETC_MAC_MAXFRM_SIZE);
+	enetc_port_wr(hw, ENETC_PTXMBAR, 2 * ENETC_MAC_MAXFRM_SIZE);
+
+	enetc_port_wr(hw, ENETC_PM0_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
+		      ENETC_PM0_CMD_TXP	| ENETC_PM0_PROMISC |
+		      ENETC_PM0_TX_EN | ENETC_PM0_RX_EN);
+
+	enetc_port_wr(hw, ENETC_PM1_CMD_CFG, ENETC_PM0_CMD_PHY_TX_EN |
+		      ENETC_PM0_CMD_TXP	| ENETC_PM0_PROMISC |
+		      ENETC_PM0_TX_EN | ENETC_PM0_RX_EN);
+	/* set auto-speed for RGMII */
+	if (enetc_port_rd(hw, ENETC_PM0_IF_MODE) & ENETC_PMO_IFM_RG)
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_RGAUTO);
+	if (enetc_global_rd(hw, ENETC_G_EPFBLPR(1)) == ENETC_G_EPFBLPR1_XGMII)
+		enetc_port_wr(hw, ENETC_PM0_IF_MODE, ENETC_PM0_IFM_XGMII);
+}
+
+static void enetc_configure_port_pmac(struct enetc_hw *hw)
+{
+	u32 temp;
+
+	/* Set pMAC step lock */
+	temp = enetc_port_rd(hw, ENETC_PFPMR);
+	enetc_port_wr(hw, ENETC_PFPMR,
+		      temp | ENETC_PFPMR_PMACE | ENETC_PFPMR_MWLM);
+
+	temp = enetc_port_rd(hw, ENETC_MMCSR);
+	enetc_port_wr(hw, ENETC_MMCSR, temp | ENETC_MMCSR_ME);
+}
+
+static void enetc_configure_port(struct enetc_pf *pf)
+{
+	u8 hash_key[ENETC_RSSHASH_KEY_SIZE];
+	struct enetc_hw *hw = &pf->si->hw;
+
+	enetc_configure_port_pmac(hw);
+
+	enetc_configure_port_mac(hw);
+
+	enetc_port_si_configure(pf->si);
+
+	/* set up hash key */
+	get_random_bytes(hash_key, ENETC_RSSHASH_KEY_SIZE);
+	enetc_set_rss_key(hw, hash_key);
+
+	/* split up RFS entries */
+	enetc_port_assign_rfs_entries(pf->si);
+
+	/* fix-up primary MAC addresses, if not set already */
+	enetc_port_setup_primary_mac_address(pf->si);
+
+	/* enforce VLAN promisc mode for all SIs */
+	pf->vlan_promisc_simap = ENETC_VLAN_PROMISC_MAP_ALL;
+	enetc_set_vlan_promisc(hw, pf->vlan_promisc_simap);
+
+	enetc_port_wr(hw, ENETC_PSIPMR, 0);
+
+	/* enable port */
+	enetc_port_wr(hw, ENETC_PMR, ENETC_PMR_EN);
+}
+
+/* Messaging */
+static u16 enetc_msg_pf_set_vf_primary_mac_addr(struct enetc_pf *pf,
+						int vf_id)
+{
+	struct enetc_vf_state *vf_state = &pf->vf_state[vf_id];
+	struct enetc_msg_swbd *msg = &pf->rxmsg[vf_id];
+	struct enetc_msg_cmd_set_primary_mac *cmd;
+	struct device *dev = &pf->si->pdev->dev;
+	u16 cmd_id;
+	char *addr;
+
+	cmd = (struct enetc_msg_cmd_set_primary_mac *)msg->vaddr;
+	cmd_id = cmd->header.id;
+	if (cmd_id != ENETC_MSG_CMD_MNG_ADD)
+		return ENETC_MSG_CMD_STATUS_FAIL;
+
+	addr = cmd->mac.sa_data;
+	if (vf_state->flags & ENETC_VF_FLAG_PF_SET_MAC)
+		dev_warn(dev, "Attempt to override PF set mac addr for VF%d\n",
+			 vf_id);
+	else
+		enetc_pf_set_primary_mac_addr(&pf->si->hw, vf_id + 1, addr);
+
+	return ENETC_MSG_CMD_STATUS_OK;
+}
+
+void enetc_msg_handle_rxmsg(struct enetc_pf *pf, int vf_id, u16 *status)
+{
+	struct enetc_msg_swbd *msg = &pf->rxmsg[vf_id];
+	struct device *dev = &pf->si->pdev->dev;
+	struct enetc_msg_cmd_header *cmd_hdr;
+	u16 cmd_type;
+
+	*status = ENETC_MSG_CMD_STATUS_OK;
+	cmd_hdr = (struct enetc_msg_cmd_header *)msg->vaddr;
+	cmd_type = cmd_hdr->type;
+
+	switch (cmd_type) {
+	case ENETC_MSG_CMD_MNG_MAC:
+		*status = enetc_msg_pf_set_vf_primary_mac_addr(pf, vf_id);
+		break;
+	default:
+		dev_err(dev, "command not supported (cmd_type: 0x%x)\n",
+			cmd_type);
+	}
+}
+
+#ifdef CONFIG_PCI_IOV
+static int enetc_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	int err;
+
+	if (!num_vfs) {
+		enetc_msg_psi_free(pf);
+		kfree(pf->vf_state);
+		pf->num_vfs = 0;
+		pci_disable_sriov(pdev);
+	} else {
+		pf->num_vfs = num_vfs;
+
+		pf->vf_state = kcalloc(num_vfs, sizeof(struct enetc_vf_state),
+				       GFP_KERNEL);
+		if (!pf->vf_state) {
+			pf->num_vfs = 0;
+			return -ENOMEM;
+		}
+
+		err = enetc_msg_psi_init(pf);
+		if (err) {
+			dev_err(&pdev->dev, "enetc_msg_psi_init (%d)\n", err);
+			goto err_msg_psi;
+		}
+
+		err = pci_enable_sriov(pdev, num_vfs);
+		if (err) {
+			dev_err(&pdev->dev, "pci_enable_sriov err %d\n", err);
+			goto err_en_sriov;
+		}
+	}
+
+	return num_vfs;
+
+err_en_sriov:
+	enetc_msg_psi_free(pf);
+err_msg_psi:
+	kfree(pf->vf_state);
+	pf->num_vfs = 0;
+
+	return err;
+}
+#else
+#define enetc_sriov_configure(pdev, num_vfs)	(void)0
+#endif
+
+static int enetc_pf_set_features(struct net_device *ndev,
+				 netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX)
+		enetc_enable_rxvlan(&priv->si->hw, 0,
+				    !!(features & NETIF_F_HW_VLAN_CTAG_RX));
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_TX)
+		enetc_enable_txvlan(&priv->si->hw, 0,
+				    !!(features & NETIF_F_HW_VLAN_CTAG_TX));
+
+	if (changed & NETIF_F_LOOPBACK)
+		enetc_set_loopback(ndev, !!(features & NETIF_F_LOOPBACK));
+
+	return enetc_set_features(ndev, features);
+}
+
+static const struct net_device_ops enetc_ndev_ops = {
+	.ndo_open		= enetc_open,
+	.ndo_stop		= enetc_close,
+	.ndo_start_xmit		= enetc_xmit,
+	.ndo_get_stats		= enetc_get_stats,
+	.ndo_set_mac_address	= enetc_pf_set_mac_addr,
+	.ndo_set_rx_mode	= enetc_pf_set_rx_mode,
+	.ndo_vlan_rx_add_vid	= enetc_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= enetc_vlan_rx_del_vid,
+	.ndo_set_vf_mac		= enetc_pf_set_vf_mac,
+	.ndo_set_vf_vlan	= enetc_pf_set_vf_vlan,
+	.ndo_set_vf_spoofchk	= enetc_pf_set_vf_spoofchk,
+	.ndo_set_features	= enetc_pf_set_features,
+};
+
+static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
+				  const struct net_device_ops *ndev_ops)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	SET_NETDEV_DEV(ndev, &si->pdev->dev);
+	priv->ndev = ndev;
+	priv->si = si;
+	priv->dev = &si->pdev->dev;
+	si->ndev = ndev;
+
+	priv->msg_enable = (NETIF_MSG_WOL << 1) - 1;
+	ndev->netdev_ops = ndev_ops;
+	enetc_set_ethtool_ops(ndev);
+	ndev->watchdog_timeo = 5 * HZ;
+	ndev->max_mtu = ENETC_MAX_MTU;
+
+	ndev->hw_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			    NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX |
+			    NETIF_F_LOOPBACK;
+	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
+			 NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			 NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX |
+			 NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	if (si->num_rss)
+		ndev->hw_features |= NETIF_F_RXHASH;
+
+	if (si->errata & ENETC_ERR_TXCSUM) {
+		ndev->hw_features &= ~NETIF_F_HW_CSUM;
+		ndev->features &= ~NETIF_F_HW_CSUM;
+	}
+
+	ndev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* pick up primary MAC address from SI */
+	enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
+}
+
+static int enetc_of_get_phy(struct enetc_ndev_priv *priv)
+{
+	struct enetc_pf *pf = enetc_si_priv(priv->si);
+	struct device_node *np = priv->dev->of_node;
+	int err;
+
+	if (!np) {
+		dev_err(priv->dev, "missing ENETC port node\n");
+		return -ENODEV;
+	}
+
+	priv->phy_node = of_parse_phandle(np, "phy-handle", 0);
+	if (!priv->phy_node) {
+		if (!of_phy_is_fixed_link(np)) {
+			dev_err(priv->dev, "PHY not specified\n");
+			return -ENODEV;
+		}
+
+		err = of_phy_register_fixed_link(np);
+		if (err < 0) {
+			dev_err(priv->dev, "fixed link registration failed\n");
+			return err;
+		}
+
+		priv->phy_node = of_node_get(np);
+	}
+
+	if (!of_phy_is_fixed_link(np)) {
+		err = enetc_mdio_probe(pf);
+		if (err) {
+			of_node_put(priv->phy_node);
+			return err;
+		}
+	}
+
+	priv->if_mode = of_get_phy_mode(np);
+	if (priv->if_mode < 0) {
+		dev_err(priv->dev, "missing phy type\n");
+		of_node_put(priv->phy_node);
+		if (of_phy_is_fixed_link(np))
+			of_phy_deregister_fixed_link(np);
+		else
+			enetc_mdio_remove(pf);
+
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void enetc_of_put_phy(struct enetc_ndev_priv *priv)
+{
+	struct device_node *np = priv->dev->of_node;
+
+	if (np && of_phy_is_fixed_link(np))
+		of_phy_deregister_fixed_link(np);
+	if (priv->phy_node)
+		of_node_put(priv->phy_node);
+}
+
+static int enetc_pf_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *ent)
+{
+	struct enetc_ndev_priv *priv;
+	struct net_device *ndev;
+	struct enetc_si *si;
+	struct enetc_pf *pf;
+	int err;
+
+	if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) {
+		dev_info(&pdev->dev, "device is disabled, skipping\n");
+		return -ENODEV;
+	}
+
+	err = enetc_pci_probe(pdev, KBUILD_MODNAME, sizeof(*pf));
+	if (err) {
+		dev_err(&pdev->dev, "PCI probing failed\n");
+		return err;
+	}
+
+	si = pci_get_drvdata(pdev);
+	if (!si->hw.port || !si->hw.global) {
+		err = -ENODEV;
+		dev_err(&pdev->dev, "could not map PF space, probing a VF?\n");
+		goto err_map_pf_space;
+	}
+
+	pf = enetc_si_priv(si);
+	pf->si = si;
+	pf->total_vfs = pci_sriov_get_totalvfs(pdev);
+
+	enetc_configure_port(pf);
+
+	enetc_get_si_caps(si);
+
+	ndev = alloc_etherdev_mq(sizeof(*priv), ENETC_MAX_NUM_TXQS);
+	if (!ndev) {
+		err = -ENOMEM;
+		dev_err(&pdev->dev, "netdev creation failed\n");
+		goto err_alloc_netdev;
+	}
+
+	enetc_pf_netdev_setup(si, ndev, &enetc_ndev_ops);
+
+	priv = netdev_priv(ndev);
+
+	enetc_init_si_rings_params(priv);
+
+	err = enetc_alloc_si_resources(priv);
+	if (err) {
+		dev_err(&pdev->dev, "SI resource alloc failed\n");
+		goto err_alloc_si_res;
+	}
+
+	err = enetc_alloc_msix(priv);
+	if (err) {
+		dev_err(&pdev->dev, "MSIX alloc failed\n");
+		goto err_alloc_msix;
+	}
+
+	err = enetc_of_get_phy(priv);
+	if (err)
+		dev_warn(&pdev->dev, "Fallback to PHY-less operation\n");
+
+	err = register_netdev(ndev);
+	if (err)
+		goto err_reg_netdev;
+
+	netif_carrier_off(ndev);
+
+	netif_info(priv, probe, ndev, "%s v%s\n",
+		   enetc_drv_name, enetc_drv_ver);
+
+	return 0;
+
+err_reg_netdev:
+	enetc_of_put_phy(priv);
+	enetc_free_msix(priv);
+err_alloc_msix:
+	enetc_free_si_resources(priv);
+err_alloc_si_res:
+	si->ndev = NULL;
+	free_netdev(ndev);
+err_alloc_netdev:
+err_map_pf_space:
+	enetc_pci_remove(pdev);
+
+	return err;
+}
+
+static void enetc_pf_remove(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_pf *pf = enetc_si_priv(si);
+	struct enetc_ndev_priv *priv;
+
+	if (pf->num_vfs)
+		enetc_sriov_configure(pdev, 0);
+
+	priv = netdev_priv(si->ndev);
+	netif_info(priv, drv, si->ndev, "%s v%s remove\n",
+		   enetc_drv_name, enetc_drv_ver);
+
+	unregister_netdev(si->ndev);
+
+	enetc_mdio_remove(pf);
+	enetc_of_put_phy(priv);
+
+	enetc_free_msix(priv);
+
+	enetc_free_si_resources(priv);
+
+	free_netdev(si->ndev);
+
+	enetc_pci_remove(pdev);
+}
+
+static const struct pci_device_id enetc_pf_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PF) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, enetc_pf_id_table);
+
+static struct pci_driver enetc_pf_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = enetc_pf_id_table,
+	.probe = enetc_pf_probe,
+	.remove = enetc_pf_remove,
+#ifdef CONFIG_PCI_IOV
+	.sriov_configure = enetc_sriov_configure,
+#endif
+};
+module_pci_driver(enetc_pf_driver);
+
+MODULE_DESCRIPTION(ENETC_DRV_NAME_STR);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(ENETC_DRV_VER_STR);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.h b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
new file mode 100644
index 000000000000..10dd1b53bb08
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2017-2019 NXP */
+
+#include "enetc.h"
+
+#define ENETC_PF_NUM_RINGS	8
+
+enum enetc_mac_addr_type {UC, MC, MADDR_TYPE};
+#define ENETC_MAX_NUM_MAC_FLT	((ENETC_MAX_NUM_VFS + 1) * MADDR_TYPE)
+
+#define ENETC_MADDR_HASH_TBL_SZ	64
+struct enetc_mac_filter {
+	union {
+		char mac_addr[ETH_ALEN];
+		DECLARE_BITMAP(mac_hash_table, ENETC_MADDR_HASH_TBL_SZ);
+	};
+	int mac_addr_cnt;
+};
+
+#define ENETC_VLAN_HT_SIZE	64
+
+enum enetc_vf_flags {
+	ENETC_VF_FLAG_PF_SET_MAC	= BIT(0),
+};
+
+struct enetc_vf_state {
+	enum enetc_vf_flags flags;
+};
+
+struct enetc_pf {
+	struct enetc_si *si;
+	int num_vfs; /* number of active VFs, after sriov_init */
+	int total_vfs; /* max number of VFs, set for PF at probe */
+	struct enetc_vf_state *vf_state;
+
+	struct enetc_mac_filter mac_filter[ENETC_MAX_NUM_MAC_FLT];
+
+	struct enetc_msg_swbd rxmsg[ENETC_MAX_NUM_VFS];
+	struct work_struct msg_task;
+	char msg_int_name[ENETC_INT_NAME_MAX];
+
+	char vlan_promisc_simap; /* bitmap of SIs in VLAN promisc mode */
+	DECLARE_BITMAP(vlan_ht_filter, ENETC_VLAN_HT_SIZE);
+	DECLARE_BITMAP(active_vlans, VLAN_N_VID);
+
+	struct mii_bus *mdio; /* saved for cleanup */
+};
+
+int enetc_msg_psi_init(struct enetc_pf *pf);
+void enetc_msg_psi_free(struct enetc_pf *pf);
+void enetc_msg_handle_rxmsg(struct enetc_pf *pf, int mbox_id, u16 *status);
+
+/* MDIO */
+int enetc_mdio_probe(struct enetc_pf *pf);
+void enetc_mdio_remove(struct enetc_pf *pf);
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
new file mode 100644
index 000000000000..8c1497e7d9c5
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2019 NXP */
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/fsl/ptp_qoriq.h>
+
+#include "enetc.h"
+
+static struct ptp_clock_info enetc_ptp_caps = {
+	.owner		= THIS_MODULE,
+	.name		= "ENETC PTP clock",
+	.max_adj	= 512000,
+	.n_alarm	= 0,
+	.n_ext_ts	= 2,
+	.n_per_out	= 0,
+	.n_pins		= 0,
+	.pps		= 1,
+	.adjfine	= ptp_qoriq_adjfine,
+	.adjtime	= ptp_qoriq_adjtime,
+	.gettime64	= ptp_qoriq_gettime,
+	.settime64	= ptp_qoriq_settime,
+	.enable		= ptp_qoriq_enable,
+};
+
+static int enetc_ptp_probe(struct pci_dev *pdev,
+			   const struct pci_device_id *ent)
+{
+	struct ptp_qoriq *ptp_qoriq;
+	void __iomem *base;
+	int err, len, n;
+
+	if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) {
+		dev_info(&pdev->dev, "device is disabled, skipping\n");
+		return -ENODEV;
+	}
+
+	err = pci_enable_device_mem(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "device enable failed\n");
+		return err;
+	}
+
+	/* set up for high or low dma */
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev,
+				"DMA configuration failed: 0x%x\n", err);
+			goto err_dma;
+		}
+	}
+
+	err = pci_request_mem_regions(pdev, KBUILD_MODNAME);
+	if (err) {
+		dev_err(&pdev->dev, "pci_request_regions failed err=%d\n", err);
+		goto err_pci_mem_reg;
+	}
+
+	pci_set_master(pdev);
+
+	ptp_qoriq = kzalloc(sizeof(*ptp_qoriq), GFP_KERNEL);
+	if (!ptp_qoriq) {
+		err = -ENOMEM;
+		goto err_alloc_ptp;
+	}
+
+	len = pci_resource_len(pdev, ENETC_BAR_REGS);
+
+	base = ioremap(pci_resource_start(pdev, ENETC_BAR_REGS), len);
+	if (!base) {
+		err = -ENXIO;
+		dev_err(&pdev->dev, "ioremap() failed\n");
+		goto err_ioremap;
+	}
+
+	/* Allocate 1 interrupt */
+	n = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX);
+	if (n != 1) {
+		err = -EPERM;
+		goto err_irq;
+	}
+
+	ptp_qoriq->irq = pci_irq_vector(pdev, 0);
+
+	err = request_irq(ptp_qoriq->irq, ptp_qoriq_isr, 0, DRIVER, ptp_qoriq);
+	if (err) {
+		dev_err(&pdev->dev, "request_irq() failed!\n");
+		goto err_irq;
+	}
+
+	ptp_qoriq->dev = &pdev->dev;
+
+	err = ptp_qoriq_init(ptp_qoriq, base, &enetc_ptp_caps);
+	if (err)
+		goto err_no_clock;
+
+	pci_set_drvdata(pdev, ptp_qoriq);
+
+	return 0;
+
+err_no_clock:
+	free_irq(ptp_qoriq->irq, ptp_qoriq);
+err_irq:
+	iounmap(base);
+err_ioremap:
+	kfree(ptp_qoriq);
+err_alloc_ptp:
+	pci_release_mem_regions(pdev);
+err_pci_mem_reg:
+err_dma:
+	pci_disable_device(pdev);
+
+	return err;
+}
+
+static void enetc_ptp_remove(struct pci_dev *pdev)
+{
+	struct ptp_qoriq *ptp_qoriq = pci_get_drvdata(pdev);
+
+	ptp_qoriq_free(ptp_qoriq);
+	kfree(ptp_qoriq);
+
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+}
+
+static const struct pci_device_id enetc_ptp_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PTP) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, enetc_ptp_id_table);
+
+static struct pci_driver enetc_ptp_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = enetc_ptp_id_table,
+	.probe = enetc_ptp_probe,
+	.remove = enetc_ptp_remove,
+};
+module_pci_driver(enetc_ptp_driver);
+
+MODULE_DESCRIPTION("ENETC PTP clock driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
new file mode 100644
index 000000000000..64bebee9f52a
--- /dev/null
+++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause)
+/* Copyright 2017-2019 NXP */
+
+#include <linux/module.h>
+#include "enetc.h"
+
+#define ENETC_DRV_VER_MAJ 1
+#define ENETC_DRV_VER_MIN 0
+
+#define ENETC_DRV_VER_STR __stringify(ENETC_DRV_VER_MAJ) "." \
+			  __stringify(ENETC_DRV_VER_MIN)
+static const char enetc_drv_ver[] = ENETC_DRV_VER_STR;
+#define ENETC_DRV_NAME_STR "ENETC VF driver"
+static const char enetc_drv_name[] = ENETC_DRV_NAME_STR;
+
+/* Messaging */
+static void enetc_msg_vsi_write_msg(struct enetc_hw *hw,
+				    struct enetc_msg_swbd *msg)
+{
+	u32 val;
+
+	val = enetc_vsi_set_msize(msg->size) | lower_32_bits(msg->dma);
+	enetc_wr(hw, ENETC_VSIMSGSNDAR1, upper_32_bits(msg->dma));
+	enetc_wr(hw, ENETC_VSIMSGSNDAR0, val);
+}
+
+static int enetc_msg_vsi_send(struct enetc_si *si, struct enetc_msg_swbd *msg)
+{
+	int timeout = 100;
+	u32 vsimsgsr;
+
+	enetc_msg_vsi_write_msg(&si->hw, msg);
+
+	do {
+		vsimsgsr = enetc_rd(&si->hw, ENETC_VSIMSGSR);
+		if (!(vsimsgsr & ENETC_VSIMSGSR_MB))
+			break;
+
+		usleep_range(1000, 2000);
+	} while (--timeout);
+
+	if (!timeout)
+		return -ETIMEDOUT;
+
+	/* check for message delivery error */
+	if (vsimsgsr & ENETC_VSIMSGSR_MS) {
+		dev_err(&si->pdev->dev, "VSI command execute error: %d\n",
+			ENETC_SIMSGSR_GET_MC(vsimsgsr));
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int enetc_msg_vsi_set_primary_mac_addr(struct enetc_ndev_priv *priv,
+					      struct sockaddr *saddr)
+{
+	struct enetc_msg_cmd_set_primary_mac *cmd;
+	struct enetc_msg_swbd msg;
+	int err;
+
+	msg.size = ALIGN(sizeof(struct enetc_msg_cmd_set_primary_mac), 64);
+	msg.vaddr = dma_alloc_coherent(priv->dev, msg.size, &msg.dma,
+				       GFP_KERNEL);
+	if (!msg.vaddr) {
+		dev_err(priv->dev, "Failed to alloc Tx msg (size: %d)\n",
+			msg.size);
+		return -ENOMEM;
+	}
+
+	cmd = (struct enetc_msg_cmd_set_primary_mac *)msg.vaddr;
+	cmd->header.type = ENETC_MSG_CMD_MNG_MAC;
+	cmd->header.id = ENETC_MSG_CMD_MNG_ADD;
+	memcpy(&cmd->mac, saddr, sizeof(struct sockaddr));
+
+	/* send the command and wait */
+	err = enetc_msg_vsi_send(priv->si, &msg);
+
+	dma_free_coherent(priv->dev, msg.size, msg.vaddr, msg.dma);
+
+	return err;
+}
+
+static int enetc_vf_set_mac_addr(struct net_device *ndev, void *addr)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+	struct sockaddr *saddr = addr;
+	int err;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	err = enetc_msg_vsi_set_primary_mac_addr(priv, saddr);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int enetc_vf_set_features(struct net_device *ndev,
+				 netdev_features_t features)
+{
+	return enetc_set_features(ndev, features);
+}
+
+/* Probing/ Init */
+static const struct net_device_ops enetc_ndev_ops = {
+	.ndo_open		= enetc_open,
+	.ndo_stop		= enetc_close,
+	.ndo_start_xmit		= enetc_xmit,
+	.ndo_get_stats		= enetc_get_stats,
+	.ndo_set_mac_address	= enetc_vf_set_mac_addr,
+	.ndo_set_features	= enetc_vf_set_features,
+};
+
+static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev,
+				  const struct net_device_ops *ndev_ops)
+{
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
+
+	SET_NETDEV_DEV(ndev, &si->pdev->dev);
+	priv->ndev = ndev;
+	priv->si = si;
+	priv->dev = &si->pdev->dev;
+	si->ndev = ndev;
+
+	priv->msg_enable = (NETIF_MSG_IFUP << 1) - 1;
+	ndev->netdev_ops = ndev_ops;
+	enetc_set_ethtool_ops(ndev);
+	ndev->watchdog_timeo = 5 * HZ;
+	ndev->max_mtu = ENETC_MAX_MTU;
+
+	ndev->hw_features = NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			    NETIF_F_HW_VLAN_CTAG_TX |
+			    NETIF_F_HW_VLAN_CTAG_RX;
+	ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG |
+			 NETIF_F_RXCSUM | NETIF_F_HW_CSUM |
+			 NETIF_F_HW_VLAN_CTAG_TX |
+			 NETIF_F_HW_VLAN_CTAG_RX;
+
+	if (si->num_rss)
+		ndev->hw_features |= NETIF_F_RXHASH;
+
+	if (si->errata & ENETC_ERR_TXCSUM) {
+		ndev->hw_features &= ~NETIF_F_HW_CSUM;
+		ndev->features &= ~NETIF_F_HW_CSUM;
+	}
+
+	/* pick up primary MAC address from SI */
+	enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr);
+}
+
+static int enetc_vf_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *ent)
+{
+	struct enetc_ndev_priv *priv;
+	struct net_device *ndev;
+	struct enetc_si *si;
+	int err;
+
+	err = enetc_pci_probe(pdev, KBUILD_MODNAME, 0);
+	if (err) {
+		dev_err(&pdev->dev, "PCI probing failed\n");
+		return err;
+	}
+
+	si = pci_get_drvdata(pdev);
+
+	enetc_get_si_caps(si);
+
+	ndev = alloc_etherdev_mq(sizeof(*priv), ENETC_MAX_NUM_TXQS);
+	if (!ndev) {
+		err = -ENOMEM;
+		dev_err(&pdev->dev, "netdev creation failed\n");
+		goto err_alloc_netdev;
+	}
+
+	enetc_vf_netdev_setup(si, ndev, &enetc_ndev_ops);
+
+	priv = netdev_priv(ndev);
+
+	enetc_init_si_rings_params(priv);
+
+	err = enetc_alloc_si_resources(priv);
+	if (err) {
+		dev_err(&pdev->dev, "SI resource alloc failed\n");
+		goto err_alloc_si_res;
+	}
+
+	err = enetc_alloc_msix(priv);
+	if (err) {
+		dev_err(&pdev->dev, "MSIX alloc failed\n");
+		goto err_alloc_msix;
+	}
+
+	err = register_netdev(ndev);
+	if (err)
+		goto err_reg_netdev;
+
+	netif_carrier_off(ndev);
+
+	netif_info(priv, probe, ndev, "%s v%s\n",
+		   enetc_drv_name, enetc_drv_ver);
+
+	return 0;
+
+err_reg_netdev:
+	enetc_free_msix(priv);
+err_alloc_msix:
+	enetc_free_si_resources(priv);
+err_alloc_si_res:
+	si->ndev = NULL;
+	free_netdev(ndev);
+err_alloc_netdev:
+	enetc_pci_remove(pdev);
+
+	return err;
+}
+
+static void enetc_vf_remove(struct pci_dev *pdev)
+{
+	struct enetc_si *si = pci_get_drvdata(pdev);
+	struct enetc_ndev_priv *priv;
+
+	priv = netdev_priv(si->ndev);
+	netif_info(priv, drv, si->ndev, "%s v%s remove\n",
+		   enetc_drv_name, enetc_drv_ver);
+	unregister_netdev(si->ndev);
+
+	enetc_free_msix(priv);
+
+	enetc_free_si_resources(priv);
+
+	free_netdev(si->ndev);
+
+	enetc_pci_remove(pdev);
+}
+
+static const struct pci_device_id enetc_vf_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_VF) },
+	{ 0, } /* End of table. */
+};
+MODULE_DEVICE_TABLE(pci, enetc_vf_id_table);
+
+static struct pci_driver enetc_vf_driver = {
+	.name = KBUILD_MODNAME,
+	.id_table = enetc_vf_id_table,
+	.probe = enetc_vf_probe,
+	.remove = enetc_vf_remove,
+};
+module_pci_driver(enetc_vf_driver);
+
+MODULE_DESCRIPTION(ENETC_DRV_NAME_STR);
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(ENETC_DRV_VER_STR);
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index bf80855dd0dd..f79e57f735b3 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -531,7 +531,6 @@ struct fec_enet_private {
 
 	/* Phylib and MDIO interface */
 	struct	mii_bus *mii_bus;
-	int	mii_timeout;
 	uint	phy_speed;
 	phy_interface_t	phy_interface;
 	struct device_node *phy_node;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 6db69ba30dcd..a96ad20ee484 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1714,12 +1714,6 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 	struct phy_device *phy_dev = ndev->phydev;
 	int status_change = 0;
 
-	/* Prevent a state halted on mii error */
-	if (fep->mii_timeout && phy_dev->state == PHY_HALTED) {
-		phy_dev->state = PHY_RESUMING;
-		return;
-	}
-
 	/*
 	 * If the netdev is down, or is going down, we're not interested
 	 * in link state events, so just mark our idea of the link as down
@@ -1779,7 +1773,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (ret < 0)
 		return ret;
 
-	fep->mii_timeout = 0;
 	reinit_completion(&fep->mdio_done);
 
 	/* start a read op */
@@ -1791,7 +1784,6 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	time_left = wait_for_completion_timeout(&fep->mdio_done,
 			usecs_to_jiffies(FEC_MII_TIMEOUT));
 	if (time_left == 0) {
-		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO read timeout\n");
 		ret = -ETIMEDOUT;
 		goto out;
@@ -1820,7 +1812,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	else
 		ret = 0;
 
-	fep->mii_timeout = 0;
 	reinit_completion(&fep->mdio_done);
 
 	/* start a write op */
@@ -1833,7 +1824,6 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	time_left = wait_for_completion_timeout(&fep->mdio_done,
 			usecs_to_jiffies(FEC_MII_TIMEOUT));
 	if (time_left == 0) {
-		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO write timeout\n");
 		ret  = -ETIMEDOUT;
 	}
@@ -1850,13 +1840,9 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 	int ret;
 
 	if (enable) {
-		ret = clk_prepare_enable(fep->clk_ahb);
-		if (ret)
-			return ret;
-
 		ret = clk_prepare_enable(fep->clk_enet_out);
 		if (ret)
-			goto failed_clk_enet_out;
+			return ret;
 
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1876,7 +1862,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 
 		phy_reset_after_clk_enable(ndev->phydev);
 	} else {
-		clk_disable_unprepare(fep->clk_ahb);
 		clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
 			mutex_lock(&fep->ptp_clk_mutex);
@@ -1895,8 +1880,6 @@ failed_clk_ref:
 failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
-failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
 }
@@ -2001,8 +1984,6 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 		return -ENOENT;
 	}
 
-	fep->mii_timeout = 0;
-
 	/*
 	 * Set MII speed to 2.5 MHz (= clk_get_rate() / 2 * phy_speed)
 	 *
@@ -2110,6 +2091,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev)
 #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
 	defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \
 	defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST)
+static __u32 fec_enet_register_version = 2;
 static u32 fec_enet_register_offset[] = {
 	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
 	FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
@@ -2140,6 +2122,7 @@ static u32 fec_enet_register_offset[] = {
 	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
 };
 #else
+static __u32 fec_enet_register_version = 1;
 static u32 fec_enet_register_offset[] = {
 	FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0,
 	FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0,
@@ -2161,6 +2144,8 @@ static void fec_enet_get_regs(struct net_device *ndev,
 	u32 *buf = (u32 *)regbuf;
 	u32 i, off;
 
+	regs->version = fec_enet_register_version;
+
 	memset(buf, 0, regs->len);
 
 	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
@@ -3478,8 +3463,11 @@ fec_probe(struct platform_device *pdev)
 	ret = clk_prepare_enable(fep->clk_ipg);
 	if (ret)
 		goto failed_clk_ipg;
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		goto failed_clk_ahb;
 
-	fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
+	fep->reg_phy = devm_regulator_get_optional(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
 		ret = regulator_enable(fep->reg_phy);
 		if (ret) {
@@ -3571,6 +3559,9 @@ failed_reset:
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ahb);
+failed_clk_ahb:
+	clk_disable_unprepare(fep->clk_ipg);
 failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
@@ -3694,6 +3685,7 @@ static int __maybe_unused fec_runtime_suspend(struct device *dev)
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
+	clk_disable_unprepare(fep->clk_ahb);
 	clk_disable_unprepare(fep->clk_ipg);
 
 	return 0;
@@ -3703,8 +3695,20 @@ static int __maybe_unused fec_runtime_resume(struct device *dev)
 {
 	struct net_device *ndev = dev_get_drvdata(dev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
+	int ret;
 
-	return clk_prepare_enable(fep->clk_ipg);
+	ret = clk_prepare_enable(fep->clk_ahb);
+	if (ret)
+		return ret;
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
+	return 0;
+
+failed_clk_ipg:
+	clk_disable_unprepare(fep->clk_ahb);
+	return ret;
 }
 
 static const struct dev_pm_ops fec_pm_ops = {
diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c
index b90bab72efdb..c1968b3ecec8 100644
--- a/drivers/net/ethernet/freescale/fec_mpc52xx.c
+++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c
@@ -369,7 +369,7 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id)
 		dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len,
 				 DMA_TO_DEVICE);
 
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 	spin_unlock(&priv->lock);
 
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index bc6eb30aa20f..41c6fa200e74 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -928,7 +928,7 @@ int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
 	hash = get_mac_addr_hash_code(addr) & HASH_CTRL_ADDR_MASK;
 
 	/* Create element to be added to the driver hash table */
-	hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL);
+	hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC);
 	if (!hash_entry)
 		return -ENOMEM;
 	hash_entry->addr = addr;
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c
index 40705938eecc..f75b9c11b2d2 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c
@@ -553,7 +553,7 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
 	hash = (crc >> TGEC_HASH_MCAST_SHIFT) & TGEC_HASH_ADR_MSK;
 
 	/* Create element to be added to the driver hash table */
-	hash_entry = kmalloc(sizeof(*hash_entry), GFP_KERNEL);
+	hash_entry = kmalloc(sizeof(*hash_entry), GFP_ATOMIC);
 	if (!hash_entry)
 		return -ENOMEM;
 	hash_entry->addr = addr;
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index d79e4e009d63..3c21486c6c84 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -393,7 +393,7 @@ void fman_get_pause_cfg(struct mac_device *mac_dev, bool *rx_pause,
 	 */
 
 	/* get local capabilities */
-	lcl_adv = ethtool_adv_to_lcl_adv_t(phy_dev->advertising);
+	lcl_adv = linkmode_adv_to_lcl_adv_t(phy_dev->advertising);
 
 	/* get link partner capabilities */
 	rmt_adv = 0;
@@ -855,9 +855,7 @@ static int mac_probe(struct platform_device *_of_dev)
 	if (err < 0)
 		dev_err(dev, "fman_set_mac_active_pause() = %d\n", err);
 
-	dev_info(dev, "FMan MAC address: %02hx:%02hx:%02hx:%02hx:%02hx:%02hx\n",
-		 mac_dev->addr[0], mac_dev->addr[1], mac_dev->addr[2],
-		 mac_dev->addr[3], mac_dev->addr[4], mac_dev->addr[5]);
+	dev_info(dev, "FMan MAC address: %pM\n", mac_dev->addr);
 
 	priv->eth_dev = dpaa_eth_add_device(fman_id, mac_dev);
 	if (IS_ERR(priv->eth_dev)) {
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 82722d05fedb..88a396fd242f 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -473,7 +473,7 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev)
 
 	if (data->get_tbipa) {
 		for_each_child_of_node(np, tbi) {
-			if (strcmp(tbi->type, "tbi-phy") == 0) {
+			if (of_node_is_type(tbi, "tbi-phy")) {
 				dev_dbg(&pdev->dev, "found TBI PHY node %pOFP\n",
 					tbi);
 				break;
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 3c8da1a18ba0..45fcc96be90e 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -500,6 +500,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_tx_timeout = gfar_timeout,
 	.ndo_do_ioctl = gfar_ioctl,
 	.ndo_get_stats = gfar_get_stats,
+	.ndo_change_carrier = fixed_phy_change_carrier,
 	.ndo_set_mac_address = gfar_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -720,7 +721,7 @@ static int gfar_of_group_count(struct device_node *np)
 	int num = 0;
 
 	for_each_available_child_of_node(np, child)
-		if (!of_node_cmp(child->name, "queue-group"))
+		if (of_node_name_eq(child, "queue-group"))
 			num++;
 
 	return num;
@@ -838,7 +839,7 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 	/* Parse and initialize group specific information */
 	if (priv->mode == MQ_MG_MODE) {
 		for_each_available_child_of_node(np, child) {
-			if (of_node_cmp(child->name, "queue-group"))
+			if (!of_node_name_eq(child, "queue-group"))
 				continue;
 
 			err = gfar_parse_group(child, priv, model);
@@ -1784,14 +1785,20 @@ static phy_interface_t gfar_get_interface(struct net_device *dev)
  */
 static int init_phy(struct net_device *dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct gfar_private *priv = netdev_priv(dev);
-	uint gigabit_support =
-		priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT ?
-		GFAR_SUPPORTED_GBIT : 0;
 	phy_interface_t interface;
 	struct phy_device *phydev;
 	struct ethtool_eee edata;
 
+	linkmode_set_bit_array(phy_10_100_features_array,
+			       ARRAY_SIZE(phy_10_100_features_array),
+			       mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
+	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask);
+
 	priv->oldlink = 0;
 	priv->oldspeed = 0;
 	priv->oldduplex = -1;
@@ -1809,8 +1816,8 @@ static int init_phy(struct net_device *dev)
 		gfar_configure_serdes(dev);
 
 	/* Remove any features not supported by the controller */
-	phydev->supported &= (GFAR_SUPPORTED | gigabit_support);
-	phydev->advertising = phydev->supported;
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	/* Add support for flow control */
 	phy_support_asym_pause(phydev);
@@ -3656,7 +3663,7 @@ static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv)
 		if (phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+		lcl_adv = linkmode_adv_to_lcl_adv_t(phydev->advertising);
 		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 		if (flowctrl & FLOW_CTRL_TX)
 			val |= MACCFG1_TX_FLOW;
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 0d76e15cd6dd..27ed995f439a 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1134,11 +1134,9 @@ static int gfar_convert_to_filer(struct ethtool_rx_flow_spec *rule,
 		prio = vlan_tci_prio(rule);
 		prio_mask = vlan_tci_priom(rule);
 
-		if (cfi == VLAN_TAG_PRESENT && cfi_mask == VLAN_TAG_PRESENT) {
-			vlan |= RQFPR_CFI;
-			vlan_mask |= RQFPR_CFI;
-		} else if (cfi != VLAN_TAG_PRESENT &&
-			   cfi_mask == VLAN_TAG_PRESENT) {
+		if (cfi_mask) {
+			if (cfi)
+				vlan |= RQFPR_CFI;
 			vlan_mask |= RQFPR_CFI;
 		}
 	}
@@ -1494,7 +1492,7 @@ static int gfar_get_ts_info(struct net_device *dev,
 	struct gfar_private *priv = netdev_priv(dev);
 	struct platform_device *ptp_dev;
 	struct device_node *ptp_node;
-	struct qoriq_ptp *ptp = NULL;
+	struct ptp_qoriq *ptp = NULL;
 
 	info->phc_index = -1;
 
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 32e02700feaa..eb3e65e8868f 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -30,6 +30,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
+#include <linux/phy_fixed.h>
 #include <linux/workqueue.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -1742,12 +1743,7 @@ static int init_phy(struct net_device *dev)
 	if (priv->phy_interface == PHY_INTERFACE_MODE_SGMII)
 		uec_configure_serdes(dev);
 
-	phy_set_max_speed(phydev, SPEED_100);
-
-	if (priv->max_speed == SPEED_1000)
-		phydev->supported |= ADVERTISED_1000baseT_Full;
-
-	phydev->advertising = phydev->supported;
+	phy_set_max_speed(phydev, priv->max_speed);
 
 	priv->phydev = phydev;
 
@@ -1883,6 +1879,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth)
 	u16 i, j;
 	u8 __iomem *bd;
 
+	netdev_reset_queue(ugeth->ndev);
+
 	ug_info = ugeth->ug_info;
 	uf_info = &ug_info->uf_info;
 
@@ -3681,6 +3679,7 @@ static const struct net_device_ops ucc_geth_netdev_ops = {
 	.ndo_stop		= ucc_geth_close,
 	.ndo_start_xmit		= ucc_geth_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_change_carrier     = fixed_phy_change_carrier,
 	.ndo_set_mac_address	= ucc_geth_set_mac_addr,
 	.ndo_set_rx_mode	= ucc_geth_set_multi,
 	.ndo_tx_timeout		= ucc_geth_timeout,
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index a69cd19a55ae..1eca0fdb9933 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -547,6 +547,11 @@ static int fmvj18x_get_hwinfo(struct pcmcia_device *link, u_char *node_id)
 	return -1;
 
     base = ioremap(link->resource[2]->start, resource_size(link->resource[2]));
+    if (!base) {
+	    pcmcia_release_window(link, link->resource[2]);
+	    return -ENOMEM;
+    }
+
     pcmcia_map_mem_page(link, link->resource[2], 0);
 
     /*
diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index 25152715396b..fee4664c9189 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -118,6 +118,7 @@ config HNS3_ENET
 	tristate "Hisilicon HNS3 Ethernet Device Support"
 	default m
 	depends on 64BIT && PCI
+	depends on INET
 	---help---
 	  This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08
 	  family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index 471805ea363b..e5d853b7b454 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1006,8 +1006,8 @@ static int hix5hd2_init_hw_desc_queue(struct hix5hd2_priv *priv)
 
 	for (i = 0; i < QUEUE_NUMS; i++) {
 		size = priv->pool[i].count * sizeof(struct hix5hd2_desc);
-		virt_addr = dma_zalloc_coherent(dev, size, &phys_addr,
-						GFP_KERNEL);
+		virt_addr = dma_alloc_coherent(dev, size, &phys_addr,
+					       GFP_KERNEL);
 		if (virt_addr == NULL)
 			goto error_free_pool;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c
index 79d03f8ee7b1..c7fa97a7e1f4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.c
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.c
@@ -150,7 +150,6 @@ out_buffer_fail:
 /* free desc along with its attached buffer */
 static void hnae_free_desc(struct hnae_ring *ring)
 {
-	hnae_free_buffers(ring);
 	dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
 			 ring->desc_num * sizeof(ring->desc[0]),
 			 ring_to_dma_dir(ring));
@@ -183,6 +182,9 @@ static int hnae_alloc_desc(struct hnae_ring *ring)
 /* fini ring, also free the buffer for the ring */
 static void hnae_fini_ring(struct hnae_ring *ring)
 {
+	if (is_rx_ring(ring))
+		hnae_free_buffers(ring);
+
 	hnae_free_desc(ring);
 	kfree(ring->desc_cb);
 	ring->desc_cb = NULL;
diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h
index 08a750fb60c4..d6fb83437230 100644
--- a/drivers/net/ethernet/hisilicon/hns/hnae.h
+++ b/drivers/net/ethernet/hisilicon/hns/hnae.h
@@ -357,7 +357,7 @@ struct hnae_buf_ops {
 };
 
 struct hnae_queue {
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	phys_addr_t phy_base;
 	struct hnae_ae_dev *dev;	/* the device who use this queue */
 	struct hnae_ring rx_ring ____cacheline_internodealigned_in_smp;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index ad1779fc410e..a78bfafd212c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -147,12 +147,10 @@ static void hns_ae_put_handle(struct hnae_handle *handle)
 	struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle);
 	int i;
 
-	vf_cb->mac_cb	 = NULL;
-
-	kfree(vf_cb);
-
 	for (i = 0; i < handle->q_num; i++)
 		hns_ae_get_ring_pair(handle->qs[i])->used_by_vf = 0;
+
+	kfree(vf_cb);
 }
 
 static int hns_ae_wait_flow_down(struct hnae_handle *handle)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index a97228c93831..6c0507921623 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -370,7 +370,7 @@ int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn)
 static void hns_mac_param_get(struct mac_params *param,
 			      struct hns_mac_cb *mac_cb)
 {
-	param->vaddr = (void *)mac_cb->vaddr;
+	param->vaddr = mac_cb->vaddr;
 	param->mac_mode = hns_get_enet_interface(mac_cb);
 	ether_addr_copy(param->addr, mac_cb->addr_entry_idx[0].addr);
 	param->mac_id = mac_cb->mac_id;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
index fbc75341bef7..22589799f1a5 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h
@@ -187,7 +187,7 @@ struct mac_statistics {
 /*mac para struct ,mac get param from nic or dsaf when initialize*/
 struct mac_params {
 	char addr[ETH_ALEN];
-	void *vaddr; /*virtual address*/
+	u8 __iomem *vaddr; /*virtual address*/
 	struct device *dev;
 	u8 mac_id;
 	/**< Ethernet operation mode (MAC-PHY interface and speed) */
@@ -402,7 +402,7 @@ struct mac_driver {
 	enum mac_mode mac_mode;
 	u8 mac_id;
 	struct hns_mac_cb *mac_cb;
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	unsigned int mac_en_flg;/*you'd better don't enable mac twice*/
 	unsigned int virt_dev_num;
 	struct device *dev;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 3b9e74be5fbd..61eea6ac846f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -1602,8 +1602,6 @@ static void hns_dsaf_set_mac_key(
 		       DSAF_TBL_TCAM_KEY_VLAN_S, vlan_id);
 	dsaf_set_field(mac_key->low.bits.port_vlan, DSAF_TBL_TCAM_KEY_PORT_M,
 		       DSAF_TBL_TCAM_KEY_PORT_S, port);
-
-	mac_key->low.bits.port_vlan = le16_to_cpu(mac_key->low.bits.port_vlan);
 }
 
 /**
@@ -1663,8 +1661,8 @@ int hns_dsaf_set_mac_uc_entry(
 	/* default config dvc to 0 */
 	mac_data.tbl_ucast_dvc = 0;
 	mac_data.tbl_ucast_out_port = mac_entry->port_num;
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+	tcam_data.tbl_tcam_data_high = mac_key.high.val;
+	tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 	hns_dsaf_tcam_uc_cfg(dsaf_dev, entry_index, &tcam_data, &mac_data);
 
@@ -1786,9 +1784,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 				     0xff,
 				     mc_mask);
 
-		mask_key.high.val = le32_to_cpu(mask_key.high.val);
-		mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
 		pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
 	}
 
@@ -1840,8 +1835,8 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 		dsaf_dev->ae_dev.name, mac_key.high.val,
 		mac_key.low.val, entry_index);
 
-	tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-	tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+	tcam_data.tbl_tcam_data_high = mac_key.high.val;
+	tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 	/* config mc entry with mask */
 	hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index, &tcam_data,
@@ -1956,9 +1951,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 		/* config key mask */
 		hns_dsaf_set_mac_key(dsaf_dev, &mask_key, 0x00, 0xff, mc_mask);
 
-		mask_key.high.val = le32_to_cpu(mask_key.high.val);
-		mask_key.low.val = le32_to_cpu(mask_key.low.val);
-
 		pmask_key = (struct dsaf_tbl_tcam_data *)(&mask_key);
 	}
 
@@ -2012,8 +2004,8 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 		soft_mac_entry += entry_index;
 		soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX;
 	} else { /* not zero, just del port, update */
-		tcam_data.tbl_tcam_data_high = cpu_to_le32(mac_key.high.val);
-		tcam_data.tbl_tcam_data_low = cpu_to_le32(mac_key.low.val);
+		tcam_data.tbl_tcam_data_high = mac_key.high.val;
+		tcam_data.tbl_tcam_data_low = mac_key.low.val;
 
 		hns_dsaf_tcam_mc_cfg(dsaf_dev, entry_index,
 				     &tcam_data,
@@ -2750,6 +2742,17 @@ int hns_dsaf_get_regs_count(void)
 	return DSAF_DUMP_REGS_NUM;
 }
 
+static int hns_dsaf_get_port_id(u8 port)
+{
+	if (port < DSAF_SERVICE_NW_NUM)
+		return port;
+
+	if (port >= DSAF_BASE_INNER_PORT_NUM)
+		return port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
+
+	return -EINVAL;
+}
+
 static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 {
 	struct dsaf_tbl_tcam_ucast_cfg tbl_tcam_ucast = {0, 1, 0, 0, 0x80};
@@ -2815,23 +2818,33 @@ static void set_promisc_tcam_enable(struct dsaf_device *dsaf_dev, u32 port)
 	memset(&temp_key, 0x0, sizeof(temp_key));
 	mask_entry.addr[0] = 0x01;
 	hns_dsaf_set_mac_key(dsaf_dev, &mask_key, mask_entry.in_vlan_id,
-			     port, mask_entry.addr);
+			     0xf, mask_entry.addr);
 	tbl_tcam_mcast.tbl_mcast_item_vld = 1;
 	tbl_tcam_mcast.tbl_mcast_old_en = 0;
 
-	if (port < DSAF_SERVICE_NW_NUM) {
-		mskid = port;
-	} else if (port >= DSAF_BASE_INNER_PORT_NUM) {
-		mskid = port - DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM;
-	} else {
+	/* set MAC port to handle multicast */
+	mskid = hns_dsaf_get_port_id(port);
+	if (mskid == -EINVAL) {
 		dev_err(dsaf_dev->dev, "%s,pnum(%d)error,key(%#x:%#x)\n",
 			dsaf_dev->ae_dev.name, port,
 			mask_key.high.val, mask_key.low.val);
 		return;
 	}
+	dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
+		     mskid % 32, 1);
 
+	/* set pool bit map to handle multicast */
+	mskid = hns_dsaf_get_port_id(port_num);
+	if (mskid == -EINVAL) {
+		dev_err(dsaf_dev->dev,
+			"%s, pool bit map pnum(%d)error,key(%#x:%#x)\n",
+			dsaf_dev->ae_dev.name, port_num,
+			mask_key.high.val, mask_key.low.val);
+		return;
+	}
 	dsaf_set_bit(tbl_tcam_mcast.tbl_mcast_port_msk[mskid / 32],
 		     mskid % 32, 1);
+
 	memcpy(&temp_key, &mask_key, sizeof(mask_key));
 	hns_dsaf_tcam_mc_cfg_vague(dsaf_dev, entry_index, &tbl_tcam_data_mc,
 				   (struct dsaf_tbl_tcam_data *)(&mask_key),
@@ -3081,6 +3094,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 	dsaf_dev = dev_get_drvdata(&pdev->dev);
 	if (!dsaf_dev) {
 		dev_err(&pdev->dev, "dsaf_dev is NULL\n");
+		put_device(&pdev->dev);
 		return -ENODEV;
 	}
 
@@ -3088,6 +3102,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 	if (AE_IS_VER1(dsaf_dev->dsaf_ver)) {
 		dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n",
 			dsaf_dev->ae_dev.name);
+		put_device(&pdev->dev);
 		return -ENODEV;
 	}
 
@@ -3126,6 +3141,9 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 		dsaf_set_bit(credit, DSAF_SBM_ROCEE_CFG_CRD_EN_B, 1);
 		dsaf_write_dev(dsaf_dev, DSAF_SBM_ROCEE_CFG_REG_REG, credit);
 	}
+
+	put_device(&pdev->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL(hns_dsaf_roce_reset);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
index 0e1cd99831a6..76cc8887e1a8 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h
@@ -467,4 +467,6 @@ int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev,
 			     u8 mac_id, u8 port_num);
 int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port);
 
+int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset);
+
 #endif /* __HNS_DSAF_MAIN_H__ */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index 16294cd3c954..19b94879691f 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -670,7 +670,7 @@ static int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, bool en)
 		dsaf_set_field(origin, 1ull << 10, 10, en);
 		dsaf_write_syscon(mac_cb->serdes_ctrl, reg_offset, origin);
 	} else {
-		u8 *base_addr = (u8 *)mac_cb->serdes_vaddr +
+		u8 __iomem *base_addr = mac_cb->serdes_vaddr +
 				(mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000);
 		dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, en);
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 0942e4916d9d..17c019106e6e 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -61,7 +61,7 @@ void hns_ppe_set_indir_table(struct hns_ppe_cb *ppe_cb,
 	}
 }
 
-static void __iomem *
+static u8 __iomem *
 hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
 {
 	return ppe_common->dsaf_dev->ppe_base + PPE_COMMON_REG_OFFSET;
@@ -83,8 +83,9 @@ static int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 	else
 		ppe_num = HNS_PPE_DEBUG_NW_ENGINE_NUM;
 
-	ppe_common = devm_kzalloc(dsaf_dev->dev, sizeof(*ppe_common) +
-		ppe_num * sizeof(struct hns_ppe_cb), GFP_KERNEL);
+	ppe_common = devm_kzalloc(dsaf_dev->dev,
+				  struct_size(ppe_common, ppe_cb, ppe_num),
+				  GFP_KERNEL);
 	if (!ppe_common)
 		return -ENOMEM;
 
@@ -110,8 +111,8 @@ hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
 	dsaf_dev->ppe_common[comm_index] = NULL;
 }
 
-static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
-					int ppe_idx)
+static u8 __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common,
+				      int ppe_idx)
 {
 	return ppe_common->dsaf_dev->ppe_base + ppe_idx * PPE_REG_OFFSET;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
index f670e63a5a01..110c6e8222c7 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h
@@ -80,7 +80,7 @@ struct hns_ppe_cb {
 	struct hns_ppe_hw_stats hw_stats;
 
 	u8 index;	/* index in a ppe common device */
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 	int virq;
 	u32 rss_indir_table[HNS_PPEV2_RSS_IND_TBL_SIZE]; /*shadow indir tab */
 	u32 rss_key[HNS_PPEV2_RSS_KEY_NUM]; /* rss hash key */
@@ -89,7 +89,7 @@ struct hns_ppe_cb {
 struct ppe_common_cb {
 	struct device *dev;
 	struct dsaf_device *dsaf_dev;
-	void __iomem *io_base;
+	u8 __iomem *io_base;
 
 	enum ppe_common_mode ppe_mode;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index 5d64519b9b1d..ac3518ca4d7b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -458,7 +458,7 @@ static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type)
 		mdnum_ppkt = HNS_RCB_RING_MAX_BD_PER_PKT;
 	} else {
 		ring = &q->tx_ring;
-		ring->io_base = (u8 __iomem *)ring_pair_cb->q.io_base +
+		ring->io_base = ring_pair_cb->q.io_base +
 			HNS_RCB_TX_REG_OFFSET;
 		irq_idx = HNS_RCB_IRQ_IDX_TX;
 		mdnum_ppkt = is_ver1 ? HNS_RCB_RING_MAX_TXBD_PER_PKT :
@@ -764,7 +764,7 @@ static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 	}
 }
 
-static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
+static u8 __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
 {
 	struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev;
 
@@ -788,8 +788,9 @@ int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev,
 	int ring_num = hns_rcb_get_ring_num(dsaf_dev);
 
 	rcb_common =
-		devm_kzalloc(dsaf_dev->dev, sizeof(*rcb_common) +
-			ring_num * sizeof(struct ring_pair_cb), GFP_KERNEL);
+		devm_kzalloc(dsaf_dev->dev,
+			     struct_size(rcb_common, ring_pair_cb, ring_num),
+			     GFP_KERNEL);
 	if (!rcb_common) {
 		dev_err(dsaf_dev->dev, "rcb common devm_kzalloc fail!\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
index b9733b0b8482..b9e7f11f0896 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h
@@ -1018,7 +1018,7 @@
 #define XGMAC_PAUSE_CTL_RSP_MODE_B	2
 #define XGMAC_PAUSE_CTL_TX_XOFF_B	3
 
-static inline void dsaf_write_reg(void __iomem *base, u32 reg, u32 value)
+static inline void dsaf_write_reg(u8 __iomem *base, u32 reg, u32 value)
 {
 	writel(value, base + reg);
 }
@@ -1053,7 +1053,7 @@ static inline int dsaf_read_syscon(struct regmap *base, u32 reg, u32 *val)
 #define dsaf_set_bit(origin, shift, val) \
 	dsaf_set_field((origin), (1ull << (shift)), (shift), (val))
 
-static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline void dsaf_set_reg_field(u8 __iomem *base, u32 reg, u32 mask,
 				      u32 shift, u32 val)
 {
 	u32 origin = dsaf_read_reg(base, reg);
@@ -1073,7 +1073,7 @@ static inline void dsaf_set_reg_field(void __iomem *base, u32 reg, u32 mask,
 #define dsaf_get_bit(origin, shift) \
 	dsaf_get_field((origin), (1ull << (shift)), (shift))
 
-static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
+static inline u32 dsaf_get_reg_field(u8 __iomem *base, u32 reg, u32 mask,
 				     u32 shift)
 {
 	u32 origin;
@@ -1089,11 +1089,11 @@ static inline u32 dsaf_get_reg_field(void __iomem *base, u32 reg, u32 mask,
 	dsaf_get_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit))
 
 #define dsaf_write_b(addr, data)\
-	writeb((data), (__iomem unsigned char *)(addr))
+	writeb((data), (__iomem u8 *)(addr))
 #define dsaf_read_b(addr)\
-	readb((__iomem unsigned char *)(addr))
+	readb((__iomem u8 *)(addr))
 
 #define hns_mac_reg_read64(drv, offset) \
-	readq((__iomem void *)(((u8 *)(drv)->io_base + 0xc00 + (offset))))
+	readq((__iomem void *)(((drv)->io_base + 0xc00 + (offset))))
 
 #endif	/* _DSAF_REG_H */
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index ba4316910dea..a60f207768fc 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -129,7 +129,7 @@ static void hns_xgmac_lf_rf_control_init(struct mac_driver *mac_drv)
 	dsaf_set_bit(val, XGMAC_UNIDIR_EN_B, 0);
 	dsaf_set_bit(val, XGMAC_RF_TX_EN_B, 1);
 	dsaf_set_field(val, XGMAC_LF_RF_INSERT_M, XGMAC_LF_RF_INSERT_S, 0);
-	dsaf_write_reg(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
+	dsaf_write_dev(mac_drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG, val);
 }
 
 /**
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 6242249c9f4c..4cd86ba1f050 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -29,9 +29,6 @@
 
 #define SERVICE_TIMER_HZ (1 * HZ)
 
-#define NIC_TX_CLEAN_MAX_NUM 256
-#define NIC_RX_CLEAN_MAX_NUM 64
-
 #define RCB_IRQ_NOT_INITED 0
 #define RCB_IRQ_INITED 1
 #define HNS_BUFFER_SIZE_2048 2048
@@ -376,8 +373,6 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev,
 	wmb(); /* commit all data before submit */
 	assert(skb->queue_mapping < priv->ae_handle->q_num);
 	hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num);
-	ring->stats.tx_pkts++;
-	ring->stats.tx_bytes += skb->len;
 
 	return NETDEV_TX_OK;
 
@@ -999,6 +994,9 @@ static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data,
 		/* issue prefetch for next Tx descriptor */
 		prefetch(&ring->desc_cb[ring->next_to_clean]);
 	}
+	/* update tx ring statistics. */
+	ring->stats.tx_pkts += pkts;
+	ring->stats.tx_bytes += bytes;
 
 	NETIF_TX_UNLOCK(ring);
 
@@ -1163,12 +1161,20 @@ static void hns_nic_adjust_link(struct net_device *ndev)
  */
 int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, };
 	struct phy_device *phy_dev = h->phy_dev;
 	int ret;
 
 	if (!h->phy_dev)
 		return 0;
 
+	ethtool_convert_legacy_u32_to_link_mode(supported, h->if_support);
+	linkmode_and(phy_dev->supported, phy_dev->supported, supported);
+	linkmode_copy(phy_dev->advertising, phy_dev->supported);
+
+	if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
+		phy_dev->autoneg = false;
+
 	if (h->phy_if != PHY_INTERFACE_MODE_XGMII) {
 		phy_dev->dev_flags = 0;
 
@@ -1180,15 +1186,6 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h)
 	if (unlikely(ret))
 		return -ENODEV;
 
-	phy_dev->supported &= h->if_support;
-	phy_dev->advertising = phy_dev->supported;
-
-	if (h->phy_if == PHY_INTERFACE_MODE_XGMII)
-		phy_dev->autoneg = false;
-
-	if (h->phy_if == PHY_INTERFACE_MODE_SGMII)
-		phy_stop(phy_dev);
-
 	return 0;
 }
 
@@ -2153,7 +2150,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
 			hns_nic_tx_fini_pro_v2;
 
 		netif_napi_add(priv->netdev, &rd->napi,
-			       hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM);
+			       hns_nic_common_poll, NAPI_POLL_WEIGHT);
 		rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
 	}
 	for (i = h->q_num; i < h->q_num * 2; i++) {
@@ -2166,7 +2163,7 @@ static int hns_nic_init_ring_data(struct hns_nic_priv *priv)
 			hns_nic_rx_fini_pro_v2;
 
 		netif_napi_add(priv->netdev, &rd->napi,
-			       hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM);
+			       hns_nic_common_poll, NAPI_POLL_WEIGHT);
 		rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED;
 	}
 
@@ -2419,6 +2416,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 out_notify_fail:
 	(void)cancel_work_sync(&priv->service_task);
 out_read_prop_fail:
+	/* safe for ACPI FW */
+	of_node_put(to_of_node(priv->fwnode));
 	free_netdev(ndev);
 	return ret;
 }
@@ -2448,6 +2447,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev)
 	set_bit(NIC_STATE_REMOVING, &priv->state);
 	(void)cancel_work_sync(&priv->service_task);
 
+	/* safe for ACPI FW */
+	of_node_put(to_of_node(priv->fwnode));
+
 	free_netdev(ndev);
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 774beda040a1..ce15d2350db9 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -624,7 +624,7 @@ static void hns_nic_self_test(struct net_device *ndev,
 		clear_bit(NIC_STATE_TESTING, &priv->state);
 
 		if (if_running)
-			(void)dev_open(ndev);
+			(void)dev_open(ndev, NULL);
 	}
 	/* Online tests aren't run; pass by default */
 
@@ -1157,16 +1157,18 @@ static int hns_get_regs_len(struct net_device *net_dev)
  */
 static int hns_nic_nway_reset(struct net_device *netdev)
 {
-	int ret = 0;
 	struct phy_device *phy = netdev->phydev;
 
-	if (netif_running(netdev)) {
-		/* if autoneg is disabled, don't restart auto-negotiation */
-		if (phy && phy->autoneg == AUTONEG_ENABLE)
-			ret = genphy_restart_aneg(phy);
-	}
+	if (!netif_running(netdev))
+		return 0;
 
-	return ret;
+	if (!phy)
+		return -EOPNOTSUPP;
+
+	if (phy->autoneg != AUTONEG_ENABLE)
+		return -EINVAL;
+
+	return genphy_restart_aneg(phy);
 }
 
 static u32
diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile
index 002534f12b66..d01bf536eb86 100644
--- a/drivers/net/ethernet/hisilicon/hns3/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/Makefile
@@ -9,6 +9,6 @@ obj-$(CONFIG_HNS3) += hns3vf/
 obj-$(CONFIG_HNS3) += hnae3.o
 
 obj-$(CONFIG_HNS3_ENET) += hns3.o
-hns3-objs = hns3_enet.o hns3_ethtool.o
+hns3-objs = hns3_enet.o hns3_ethtool.o hns3_debugfs.o
 
 hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
index 038326cfda93..299b277bc7ae 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h
@@ -21,6 +21,7 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_SET_MACVLAN,		/* (VF -> PF) set unicast filter */
 	HCLGE_MBX_API_NEGOTIATE,	/* (VF -> PF) negotiate API version */
 	HCLGE_MBX_GET_QINFO,		/* (VF -> PF) get queue config */
+	HCLGE_MBX_GET_QDEPTH,		/* (VF -> PF) get queue depth */
 	HCLGE_MBX_GET_TCINFO,		/* (VF -> PF) get TC config */
 	HCLGE_MBX_GET_RETA,		/* (VF -> PF) get RETA */
 	HCLGE_MBX_GET_RSS_KEY,		/* (VF -> PF) get RSS key */
@@ -36,6 +37,14 @@ enum HCLGE_MBX_OPCODE {
 	HCLGE_MBX_BIND_FUNC_QUEUE,	/* (VF -> PF) bind function and queue */
 	HCLGE_MBX_GET_LINK_STATUS,	/* (VF -> PF) get link status */
 	HCLGE_MBX_QUEUE_RESET,		/* (VF -> PF) reset queue */
+	HCLGE_MBX_KEEP_ALIVE,		/* (VF -> PF) send keep alive cmd */
+	HCLGE_MBX_SET_ALIVE,		/* (VF -> PF) set alive state */
+	HCLGE_MBX_SET_MTU,		/* (VF -> PF) set mtu */
+	HCLGE_MBX_GET_QID_IN_PF,	/* (VF -> PF) get queue id in pf */
+	HCLGE_MBX_LINK_STAT_MODE,	/* (PF -> VF) link mode has changed */
+	HCLGE_MBX_GET_LINK_MODE,	/* (VF -> PF) get the link mode of pf */
+
+	HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */
 };
 
 /* below are per-VF mac-vlan subcodes */
@@ -56,7 +65,7 @@ enum hclge_mbx_vlan_cfg_subcode {
 };
 
 #define HCLGE_MBX_MAX_MSG_SIZE	16
-#define HCLGE_MBX_MAX_RESP_DATA_SIZE	8
+#define HCLGE_MBX_MAX_RESP_DATA_SIZE	16
 #define HCLGE_MBX_RING_MAP_BASIC_MSG_NUM	3
 #define HCLGE_MBX_RING_NODE_VARIABLE_NUM	3
 
@@ -85,6 +94,12 @@ struct hclge_mbx_pf_to_vf_cmd {
 	u16 msg[8];
 };
 
+struct hclge_vf_rst_cmd {
+	u8 dest_vfid;
+	u8 vf_rst;
+	u8 rsv[22];
+};
+
 /* used by VF to store the received Async responses from PF */
 struct hclgevf_mbx_arq_ring {
 #define HCLGE_MBX_MAX_ARQ_MSG_SIZE	8
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 781e5dee3c70..17ab4f4af6ad 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -32,6 +32,9 @@ static bool hnae3_client_match(enum hnae3_client_type client_type,
 void hnae3_set_client_init_flag(struct hnae3_client *client,
 				struct hnae3_ae_dev *ae_dev, int inited)
 {
+	if (!client || !ae_dev)
+		return;
+
 	switch (client->type) {
 	case HNAE3_CLIENT_KNIC:
 		hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
@@ -109,6 +112,9 @@ int hnae3_register_client(struct hnae3_client *client)
 	struct hnae3_ae_dev *ae_dev;
 	int ret = 0;
 
+	if (!client)
+		return -ENODEV;
+
 	mutex_lock(&hnae3_common_lock);
 	/* one system should only have one client for every type */
 	list_for_each_entry(client_tmp, &hnae3_client_list, node) {
@@ -141,6 +147,9 @@ void hnae3_unregister_client(struct hnae3_client *client)
 {
 	struct hnae3_ae_dev *ae_dev;
 
+	if (!client)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 	/* un-initialize the client on every matched port */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
@@ -163,6 +172,9 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 	struct hnae3_client *client;
 	int ret = 0;
 
+	if (!ae_algo)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 
 	list_add_tail(&ae_algo->node, &hnae3_ae_algo_list);
@@ -173,8 +185,12 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 		if (!id)
 			continue;
 
-		/* ae_dev init should set flag */
+		if (!ae_algo->ops) {
+			dev_err(&ae_dev->pdev->dev, "ae_algo ops are null\n");
+			continue;
+		}
 		ae_dev->ops = ae_algo->ops;
+
 		ret = ae_algo->ops->init_ae_dev(ae_dev);
 		if (ret) {
 			dev_err(&ae_dev->pdev->dev,
@@ -182,6 +198,7 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 			continue;
 		}
 
+		/* ae_dev init should set flag */
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 
 		/* check the client list for the match with this ae_dev type and
@@ -209,6 +226,9 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 	struct hnae3_ae_dev *ae_dev;
 	struct hnae3_client *client;
 
+	if (!ae_algo)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_dev */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
@@ -238,13 +258,16 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo);
  * @ae_dev: the AE device
  * NOTE: the duplicated name will not be checked
  */
-void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
+int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	const struct pci_device_id *id;
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_client *client;
 	int ret = 0;
 
+	if (!ae_dev)
+		return -ENODEV;
+
 	mutex_lock(&hnae3_common_lock);
 
 	list_add_tail(&ae_dev->node, &hnae3_ae_dev_list);
@@ -255,14 +278,13 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 		if (!id)
 			continue;
 
-		ae_dev->ops = ae_algo->ops;
-
-		if (!ae_dev->ops) {
-			dev_err(&ae_dev->pdev->dev, "ae_dev ops are null\n");
+		if (!ae_algo->ops) {
+			dev_err(&ae_dev->pdev->dev, "ae_algo ops are null\n");
+			ret = -EOPNOTSUPP;
 			goto out_err;
 		}
+		ae_dev->ops = ae_algo->ops;
 
-		/* ae_dev init should set flag */
 		ret = ae_dev->ops->init_ae_dev(ae_dev);
 		if (ret) {
 			dev_err(&ae_dev->pdev->dev,
@@ -270,6 +292,7 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 			goto out_err;
 		}
 
+		/* ae_dev init should set flag */
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 		break;
 	}
@@ -285,8 +308,15 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 				ret);
 	}
 
+	mutex_unlock(&hnae3_common_lock);
+
+	return 0;
+
 out_err:
+	list_del(&ae_dev->node);
 	mutex_unlock(&hnae3_common_lock);
+
+	return ret;
 }
 EXPORT_SYMBOL(hnae3_register_ae_dev);
 
@@ -299,6 +329,9 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 	struct hnae3_ae_algo *ae_algo;
 	struct hnae3_client *client;
 
+	if (!ae_dev)
+		return;
+
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_algo */
 	list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 055b40606dbc..38b430f11fc1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -52,6 +52,7 @@
 #define HNAE3_UNIC_CLIENT_INITED_B		0x4
 #define HNAE3_ROCE_CLIENT_INITED_B		0x5
 #define HNAE3_DEV_SUPPORT_FD_B			0x6
+#define HNAE3_DEV_SUPPORT_GRO_B			0x7
 
 #define HNAE3_DEV_SUPPORT_ROCE_DCB_BITS (BIT(HNAE3_DEV_SUPPORT_DCB_B) |\
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
@@ -65,6 +66,9 @@
 #define hnae3_dev_fd_supported(hdev) \
 	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B)
 
+#define hnae3_dev_gro_supported(hdev) \
+	hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B)
+
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
 #define ring_ptr_move_bw(ring, p) \
@@ -83,7 +87,8 @@ struct hnae3_queue {
 	struct hnae3_handle *handle;
 	int tqp_index;	/* index in a handle */
 	u32 buf_size;	/* size for hnae_desc->addr, preset by AE */
-	u16 desc_num;	/* total number of desc */
+	u16 tx_desc_num;/* total number of tx desc */
+	u16 rx_desc_num;/* total number of rx desc */
 };
 
 /*hnae3 loop mode*/
@@ -120,18 +125,28 @@ enum hnae3_reset_notify_type {
 	HNAE3_DOWN_CLIENT,
 	HNAE3_INIT_CLIENT,
 	HNAE3_UNINIT_CLIENT,
+	HNAE3_RESTORE_CLIENT,
 };
 
 enum hnae3_reset_type {
 	HNAE3_VF_RESET,
+	HNAE3_VF_FUNC_RESET,
+	HNAE3_VF_PF_FUNC_RESET,
 	HNAE3_VF_FULL_RESET,
+	HNAE3_FLR_RESET,
 	HNAE3_FUNC_RESET,
 	HNAE3_CORE_RESET,
 	HNAE3_GLOBAL_RESET,
 	HNAE3_IMP_RESET,
+	HNAE3_UNKNOWN_RESET,
 	HNAE3_NONE_RESET,
 };
 
+enum hnae3_flr_state {
+	HNAE3_FLR_DOWN,
+	HNAE3_FLR_DONE,
+};
+
 struct hnae3_vector_info {
 	u8 __iomem *io_addr;
 	int vector;
@@ -162,6 +177,7 @@ struct hnae3_client_ops {
 	int (*setup_tc)(struct hnae3_handle *handle, u8 tc);
 	int (*reset_notify)(struct hnae3_handle *handle,
 			    enum hnae3_reset_notify_type type);
+	enum hnae3_reset_type (*process_hw_error)(struct hnae3_handle *handle);
 };
 
 #define HNAE3_CLIENT_NAME_LENGTH 16
@@ -178,6 +194,7 @@ struct hnae3_ae_dev {
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
 	u32 flag;
+	u8 override_pci_need_reset; /* fix to stop multiple reset happening */
 	enum hnae3_dev_type dev_type;
 	enum hnae3_reset_type reset_type;
 	void *priv;
@@ -197,6 +214,10 @@ struct hnae3_ae_dev {
  *   Enable the hardware
  * stop()
  *   Disable the hardware
+ * start_client()
+ *   Inform the hclge that client has been started
+ * stop_client()
+ *   Inform the hclge that client has been stopped
  * get_status()
  *   Get the carrier state of the back channel of the handle, 1 for ok, 0 for
  *   non-ok
@@ -292,17 +313,22 @@ struct hnae3_ae_dev {
  *   Set vlan filter config of vf
  * enable_hw_strip_rxvtag()
  *   Enable/disable hardware strip vlan tag of packets received
+ * set_gro_en
+ *   Enable/disable HW GRO
  */
 struct hnae3_ae_ops {
 	int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev);
 	void (*uninit_ae_dev)(struct hnae3_ae_dev *ae_dev);
-
+	void (*flr_prepare)(struct hnae3_ae_dev *ae_dev);
+	void (*flr_done)(struct hnae3_ae_dev *ae_dev);
 	int (*init_client_instance)(struct hnae3_client *client,
 				    struct hnae3_ae_dev *ae_dev);
 	void (*uninit_client_instance)(struct hnae3_client *client,
 				       struct hnae3_ae_dev *ae_dev);
 	int (*start)(struct hnae3_handle *handle);
 	void (*stop)(struct hnae3_handle *handle);
+	int (*client_start)(struct hnae3_handle *handle);
+	void (*client_stop)(struct hnae3_handle *handle);
 	int (*get_status)(struct hnae3_handle *handle);
 	void (*get_ksettings_an_result)(struct hnae3_handle *handle,
 					u8 *auto_neg, u32 *speed, u8 *duplex);
@@ -403,11 +429,14 @@ struct hnae3_ae_ops {
 				  u16 vlan, u8 qos, __be16 proto);
 	int (*enable_hw_strip_rxvtag)(struct hnae3_handle *handle, bool enable);
 	void (*reset_event)(struct pci_dev *pdev, struct hnae3_handle *handle);
+	void (*set_default_reset_request)(struct hnae3_ae_dev *ae_dev,
+					  enum hnae3_reset_type rst_type);
 	void (*get_channels)(struct hnae3_handle *handle,
 			     struct ethtool_channels *ch);
 	void (*get_tqps_and_rss_info)(struct hnae3_handle *h,
 				      u16 *alloc_tqps, u16 *max_rss_size);
-	int (*set_channels)(struct hnae3_handle *handle, u32 new_tqps_num);
+	int (*set_channels)(struct hnae3_handle *handle, u32 new_tqps_num,
+			    bool rxfh_configured);
 	void (*get_flowctrl_adv)(struct hnae3_handle *handle,
 				 u32 *flowctrl_adv);
 	int (*set_led_id)(struct hnae3_handle *handle,
@@ -429,7 +458,16 @@ struct hnae3_ae_ops {
 				struct ethtool_rxnfc *cmd, u32 *rule_locs);
 	int (*restore_fd_rules)(struct hnae3_handle *handle);
 	void (*enable_fd)(struct hnae3_handle *handle, bool enable);
-	pci_ers_result_t (*process_hw_error)(struct hnae3_ae_dev *ae_dev);
+	int (*dbg_run_cmd)(struct hnae3_handle *handle, char *cmd_buf);
+	pci_ers_result_t (*handle_hw_ras_error)(struct hnae3_ae_dev *ae_dev);
+	bool (*get_hw_reset_stat)(struct hnae3_handle *handle);
+	bool (*ae_dev_resetting)(struct hnae3_handle *handle);
+	unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle);
+	int (*set_gro_en)(struct hnae3_handle *handle, bool enable);
+	u16 (*get_global_queue_id)(struct hnae3_handle *handle, u16 queue_id);
+	void (*set_timer_task)(struct hnae3_handle *handle, bool enable);
+	int (*mac_connect_phy)(struct hnae3_handle *handle);
+	void (*mac_disconnect_phy)(struct hnae3_handle *handle);
 };
 
 struct hnae3_dcb_ops {
@@ -443,7 +481,6 @@ struct hnae3_dcb_ops {
 	u8   (*getdcbx)(struct hnae3_handle *);
 	u8   (*setdcbx)(struct hnae3_handle *, u8);
 
-	int (*map_update)(struct hnae3_handle *);
 	int (*setup_tc)(struct hnae3_handle *, u8, u8 *);
 };
 
@@ -468,8 +505,10 @@ struct hnae3_tc_info {
 struct hnae3_knic_private_info {
 	struct net_device *netdev; /* Set by KNIC client when init instance */
 	u16 rss_size;		   /* Allocated RSS queues */
+	u16 req_rss_size;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;
+	u16 num_rx_desc;
 
 	u8 num_tc;		   /* Total number of enabled TCs */
 	u8 prio_tc[HNAE3_MAX_USER_PRIO];  /* TC indexed by prio */
@@ -488,12 +527,22 @@ struct hnae3_roce_private_info {
 	void __iomem *roce_io_base;
 	int base_vector;
 	int num_vectors;
+
+	/* The below attributes defined for RoCE client, hnae3 gives
+	 * initial values to them, and RoCE client can modify and use
+	 * them.
+	 */
+	unsigned long reset_state;
+	unsigned long instance_state;
+	unsigned long state;
 };
 
 struct hnae3_unic_private_info {
 	struct net_device *netdev;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;
+	u16 num_rx_desc;
+
 	u16 num_tqps;	/* total number of tqps in this handle */
 	struct hnae3_queue **tqp;  /* array base of all TQPs of this instance */
 };
@@ -520,9 +569,6 @@ struct hnae3_handle {
 	struct hnae3_ae_algo *ae_algo;  /* the class who provides this handle */
 	u64 flags; /* Indicate the capabilities for this handle*/
 
-	unsigned long last_reset_time;
-	enum hnae3_reset_type reset_level;
-
 	union {
 		struct net_device *netdev; /* first member */
 		struct hnae3_knic_private_info kinfo;
@@ -533,6 +579,7 @@ struct hnae3_handle {
 	u32 numa_node_mask;	/* for multi-chip support */
 
 	u8 netdev_flags;
+	struct dentry *hnae3_dbgfs;
 };
 
 #define hnae3_set_field(origin, mask, shift, val) \
@@ -547,7 +594,7 @@ struct hnae3_handle {
 #define hnae3_get_bit(origin, shift) \
 	hnae3_get_field((origin), (0x1 << (shift)), (shift))
 
-void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
+int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
 void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
 
 void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
index ea5f8a84070d..b6fabbbdfd5b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
@@ -9,6 +9,9 @@ int hns3_dcbnl_ieee_getets(struct net_device *ndev, struct ieee_ets *ets)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_getets)
 		return h->kinfo.dcb_ops->ieee_getets(h, ets);
 
@@ -20,6 +23,9 @@ int hns3_dcbnl_ieee_setets(struct net_device *ndev, struct ieee_ets *ets)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_setets)
 		return h->kinfo.dcb_ops->ieee_setets(h, ets);
 
@@ -31,6 +37,9 @@ int hns3_dcbnl_ieee_getpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_getpfc)
 		return h->kinfo.dcb_ops->ieee_getpfc(h, pfc);
 
@@ -42,6 +51,9 @@ int hns3_dcbnl_ieee_setpfc(struct net_device *ndev, struct ieee_pfc *pfc)
 {
 	struct hnae3_handle *h = hns3_get_handle(ndev);
 
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
+
 	if (h->kinfo.dcb_ops->ieee_setpfc)
 		return h->kinfo.dcb_ops->ieee_setpfc(h, pfc);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
new file mode 100644
index 000000000000..0de543faa5b1
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -0,0 +1,399 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+#include <linux/debugfs.h>
+#include <linux/device.h>
+
+#include "hnae3.h"
+#include "hns3_enet.h"
+
+#define HNS3_DBG_READ_LEN 256
+
+static struct dentry *hns3_dbgfs_root;
+
+static int hns3_dbg_queue_info(struct hnae3_handle *h, char *cmd_buf)
+{
+	struct hns3_nic_priv *priv = h->priv;
+	struct hns3_nic_ring_data *ring_data;
+	struct hns3_enet_ring *ring;
+	u32 base_add_l, base_add_h;
+	u32 queue_num, queue_max;
+	u32 value, i = 0;
+	int cnt;
+
+	if (!priv->ring_data) {
+		dev_err(&h->pdev->dev, "ring_data is NULL\n");
+		return -EFAULT;
+	}
+
+	queue_max = h->kinfo.num_tqps;
+	cnt = kstrtouint(&cmd_buf[11], 0, &queue_num);
+	if (cnt)
+		queue_num = 0;
+	else
+		queue_max = queue_num + 1;
+
+	dev_info(&h->pdev->dev, "queue info\n");
+
+	if (queue_num >= h->kinfo.num_tqps) {
+		dev_err(&h->pdev->dev,
+			"Queue number(%u) is out of range(%u)\n", queue_num,
+			h->kinfo.num_tqps - 1);
+		return -EINVAL;
+	}
+
+	ring_data = priv->ring_data;
+	for (i = queue_num; i < queue_max; i++) {
+		/* Each cycle needs to determine whether the instance is reset,
+		 * to prevent reference to invalid memory. And need to ensure
+		 * that the following code is executed within 100ms.
+		 */
+		if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+		    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+			return -EPERM;
+
+		ring = ring_data[(u32)(i + h->kinfo.num_tqps)].ring;
+		base_add_h = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_RX_RING_BASEADDR_H_REG);
+		base_add_l = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_RX_RING_BASEADDR_L_REG);
+		dev_info(&h->pdev->dev, "RX(%d) BASE ADD: 0x%08x%08x\n", i,
+			 base_add_h, base_add_l);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_BD_NUM_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING BD NUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_BD_LEN_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING BD LEN: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_TAIL_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING TAIL: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_HEAD_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING HEAD: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_FBDNUM_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING FBDNUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_RX_RING_PKTNUM_RECORD_REG);
+		dev_info(&h->pdev->dev, "RX(%d) RING PKTNUM: %u\n", i, value);
+
+		ring = ring_data[i].ring;
+		base_add_h = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_TX_RING_BASEADDR_H_REG);
+		base_add_l = readl_relaxed(ring->tqp->io_base +
+					   HNS3_RING_TX_RING_BASEADDR_L_REG);
+		dev_info(&h->pdev->dev, "TX(%d) BASE ADD: 0x%08x%08x\n", i,
+			 base_add_h, base_add_l);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_BD_NUM_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING BD NUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_TC_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING TC: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_TAIL_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING TAIL: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_HEAD_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING HEAD: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_FBDNUM_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING FBDNUM: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_OFFSET_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING OFFSET: %u\n", i, value);
+
+		value = readl_relaxed(ring->tqp->io_base +
+				      HNS3_RING_TX_RING_PKTNUM_RECORD_REG);
+		dev_info(&h->pdev->dev, "TX(%d) RING PKTNUM: %u\n\n", i,
+			 value);
+	}
+
+	return 0;
+}
+
+static int hns3_dbg_queue_map(struct hnae3_handle *h)
+{
+	struct hns3_nic_priv *priv = h->priv;
+	struct hns3_nic_ring_data *ring_data;
+	int i;
+
+	if (!h->ae_algo->ops->get_global_queue_id)
+		return -EOPNOTSUPP;
+
+	dev_info(&h->pdev->dev, "map info for queue id and vector id\n");
+	dev_info(&h->pdev->dev,
+		 "local queue id | global queue id | vector id\n");
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		u16 global_qid;
+
+		global_qid = h->ae_algo->ops->get_global_queue_id(h, i);
+		ring_data = &priv->ring_data[i];
+		if (!ring_data || !ring_data->ring ||
+		    !ring_data->ring->tqp_vector)
+			continue;
+
+		dev_info(&h->pdev->dev,
+			 "      %4d            %4d            %4d\n",
+			 i, global_qid,
+			 ring_data->ring->tqp_vector->vector_irq);
+	}
+
+	return 0;
+}
+
+static int hns3_dbg_bd_info(struct hnae3_handle *h, char *cmd_buf)
+{
+	struct hns3_nic_priv *priv = h->priv;
+	struct hns3_nic_ring_data *ring_data;
+	struct hns3_desc *rx_desc, *tx_desc;
+	struct device *dev = &h->pdev->dev;
+	struct hns3_enet_ring *ring;
+	u32 tx_index, rx_index;
+	u32 q_num, value;
+	int cnt;
+
+	cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index);
+	if (cnt == 2) {
+		rx_index = tx_index;
+	} else if (cnt != 1) {
+		dev_err(dev, "bd info: bad command string, cnt=%d\n", cnt);
+		return -EINVAL;
+	}
+
+	if (q_num >= h->kinfo.num_tqps) {
+		dev_err(dev, "Queue number(%u) is out of range(%u)\n", q_num,
+			h->kinfo.num_tqps - 1);
+		return -EINVAL;
+	}
+
+	ring_data = priv->ring_data;
+	ring  = ring_data[q_num].ring;
+	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_TX_RING_TAIL_REG);
+	tx_index = (cnt == 1) ? value : tx_index;
+
+	if (tx_index >= ring->desc_num) {
+		dev_err(dev, "bd index (%u) is out of range(%u)\n", tx_index,
+			ring->desc_num - 1);
+		return -EINVAL;
+	}
+
+	tx_desc = &ring->desc[tx_index];
+	dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index);
+	dev_info(dev, "(TX) addr: 0x%llx\n", tx_desc->addr);
+	dev_info(dev, "(TX)vlan_tag: %u\n", tx_desc->tx.vlan_tag);
+	dev_info(dev, "(TX)send_size: %u\n", tx_desc->tx.send_size);
+	dev_info(dev, "(TX)vlan_tso: %u\n", tx_desc->tx.type_cs_vlan_tso);
+	dev_info(dev, "(TX)l2_len: %u\n", tx_desc->tx.l2_len);
+	dev_info(dev, "(TX)l3_len: %u\n", tx_desc->tx.l3_len);
+	dev_info(dev, "(TX)l4_len: %u\n", tx_desc->tx.l4_len);
+	dev_info(dev, "(TX)vlan_tag: %u\n", tx_desc->tx.outer_vlan_tag);
+	dev_info(dev, "(TX)tv: %u\n", tx_desc->tx.tv);
+	dev_info(dev, "(TX)vlan_msec: %u\n", tx_desc->tx.ol_type_vlan_msec);
+	dev_info(dev, "(TX)ol2_len: %u\n", tx_desc->tx.ol2_len);
+	dev_info(dev, "(TX)ol3_len: %u\n", tx_desc->tx.ol3_len);
+	dev_info(dev, "(TX)ol4_len: %u\n", tx_desc->tx.ol4_len);
+	dev_info(dev, "(TX)paylen: %u\n", tx_desc->tx.paylen);
+	dev_info(dev, "(TX)vld_ra_ri: %u\n", tx_desc->tx.bdtp_fe_sc_vld_ra_ri);
+	dev_info(dev, "(TX)mss: %u\n", tx_desc->tx.mss);
+
+	ring  = ring_data[q_num + h->kinfo.num_tqps].ring;
+	value = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_TAIL_REG);
+	rx_index = (cnt == 1) ? value : tx_index;
+	rx_desc	 = &ring->desc[rx_index];
+
+	dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index);
+	dev_info(dev, "(RX)addr: 0x%llx\n", rx_desc->addr);
+	dev_info(dev, "(RX)pkt_len: %u\n", rx_desc->rx.pkt_len);
+	dev_info(dev, "(RX)size: %u\n", rx_desc->rx.size);
+	dev_info(dev, "(RX)rss_hash: %u\n", rx_desc->rx.rss_hash);
+	dev_info(dev, "(RX)fd_id: %u\n", rx_desc->rx.fd_id);
+	dev_info(dev, "(RX)vlan_tag: %u\n", rx_desc->rx.vlan_tag);
+	dev_info(dev, "(RX)o_dm_vlan_id_fb: %u\n", rx_desc->rx.o_dm_vlan_id_fb);
+	dev_info(dev, "(RX)ot_vlan_tag: %u\n", rx_desc->rx.ot_vlan_tag);
+	dev_info(dev, "(RX)bd_base_info: %u\n", rx_desc->rx.bd_base_info);
+
+	return 0;
+}
+
+static void hns3_dbg_help(struct hnae3_handle *h)
+{
+#define HNS3_DBG_BUF_LEN 256
+
+	char printf_buf[HNS3_DBG_BUF_LEN];
+
+	dev_info(&h->pdev->dev, "available commands\n");
+	dev_info(&h->pdev->dev, "queue info [number]\n");
+	dev_info(&h->pdev->dev, "queue map\n");
+	dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n");
+	dev_info(&h->pdev->dev, "dump fd tcam\n");
+	dev_info(&h->pdev->dev, "dump tc\n");
+	dev_info(&h->pdev->dev, "dump tm map [q_num]\n");
+	dev_info(&h->pdev->dev, "dump tm\n");
+	dev_info(&h->pdev->dev, "dump qos pause cfg\n");
+	dev_info(&h->pdev->dev, "dump qos pri map\n");
+	dev_info(&h->pdev->dev, "dump qos buf cfg\n");
+	dev_info(&h->pdev->dev, "dump mng tbl\n");
+
+	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
+	strncat(printf_buf, "dump reg [[bios common] [ssu <prt_id>]",
+		HNS3_DBG_BUF_LEN - 1);
+	strncat(printf_buf + strlen(printf_buf),
+		" [igu egu <prt_id>] [rpu <tc_queue_num>]",
+		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
+	strncat(printf_buf + strlen(printf_buf),
+		" [rtc] [ppp] [rcb] [tqp <q_num>]]\n",
+		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
+	dev_info(&h->pdev->dev, "%s", printf_buf);
+
+	memset(printf_buf, 0, HNS3_DBG_BUF_LEN);
+	strncat(printf_buf, "dump reg dcb [port_id] [pri_id] [pg_id]",
+		HNS3_DBG_BUF_LEN - 1);
+	strncat(printf_buf + strlen(printf_buf), " [rq_id] [nq_id] [qset_id]\n",
+		HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1);
+	dev_info(&h->pdev->dev, "%s", printf_buf);
+}
+
+static ssize_t hns3_dbg_cmd_read(struct file *filp, char __user *buffer,
+				 size_t count, loff_t *ppos)
+{
+	int uncopy_bytes;
+	char *buf;
+	int len;
+
+	if (*ppos != 0)
+		return 0;
+
+	if (count < HNS3_DBG_READ_LEN)
+		return -ENOSPC;
+
+	buf = kzalloc(HNS3_DBG_READ_LEN, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	len = snprintf(buf, HNS3_DBG_READ_LEN, "%s\n",
+		       "Please echo help to cmd to get help information");
+	uncopy_bytes = copy_to_user(buffer, buf, len);
+
+	kfree(buf);
+
+	if (uncopy_bytes)
+		return -EFAULT;
+
+	return (*ppos = len);
+}
+
+static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer,
+				  size_t count, loff_t *ppos)
+{
+	struct hnae3_handle *handle = filp->private_data;
+	struct hns3_nic_priv *priv  = handle->priv;
+	char *cmd_buf, *cmd_buf_tmp;
+	int uncopied_bytes;
+	int ret = 0;
+
+	if (*ppos != 0)
+		return 0;
+
+	/* Judge if the instance is being reset. */
+	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state) ||
+	    test_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+		return 0;
+
+	cmd_buf = kzalloc(count + 1, GFP_KERNEL);
+	if (!cmd_buf)
+		return count;
+
+	uncopied_bytes = copy_from_user(cmd_buf, buffer, count);
+	if (uncopied_bytes) {
+		kfree(cmd_buf);
+		return -EFAULT;
+	}
+
+	cmd_buf[count] = '\0';
+
+	cmd_buf_tmp = strchr(cmd_buf, '\n');
+	if (cmd_buf_tmp) {
+		*cmd_buf_tmp = '\0';
+		count = cmd_buf_tmp - cmd_buf + 1;
+	}
+
+	if (strncmp(cmd_buf, "help", 4) == 0)
+		hns3_dbg_help(handle);
+	else if (strncmp(cmd_buf, "queue info", 10) == 0)
+		ret = hns3_dbg_queue_info(handle, cmd_buf);
+	else if (strncmp(cmd_buf, "queue map", 9) == 0)
+		ret = hns3_dbg_queue_map(handle);
+	else if (strncmp(cmd_buf, "bd info", 7) == 0)
+		ret = hns3_dbg_bd_info(handle, cmd_buf);
+	else if (handle->ae_algo->ops->dbg_run_cmd)
+		ret = handle->ae_algo->ops->dbg_run_cmd(handle, cmd_buf);
+
+	if (ret)
+		hns3_dbg_help(handle);
+
+	kfree(cmd_buf);
+	cmd_buf = NULL;
+
+	return count;
+}
+
+static const struct file_operations hns3_dbg_cmd_fops = {
+	.owner = THIS_MODULE,
+	.open  = simple_open,
+	.read  = hns3_dbg_cmd_read,
+	.write = hns3_dbg_cmd_write,
+};
+
+void hns3_dbg_init(struct hnae3_handle *handle)
+{
+	const char *name = pci_name(handle->pdev);
+	struct dentry *pfile;
+
+	handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root);
+	if (!handle->hnae3_dbgfs)
+		return;
+
+	pfile = debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle,
+				    &hns3_dbg_cmd_fops);
+	if (!pfile) {
+		debugfs_remove_recursive(handle->hnae3_dbgfs);
+		handle->hnae3_dbgfs = NULL;
+		dev_warn(&handle->pdev->dev, "create file for %s fail\n",
+			 name);
+	}
+}
+
+void hns3_dbg_uninit(struct hnae3_handle *handle)
+{
+	debugfs_remove_recursive(handle->hnae3_dbgfs);
+	handle->hnae3_dbgfs = NULL;
+}
+
+void hns3_dbg_register_debugfs(const char *debugfs_dir_name)
+{
+	hns3_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL);
+	if (!hns3_dbgfs_root) {
+		pr_warn("Register debugfs for %s fail\n", debugfs_dir_name);
+		return;
+	}
+}
+
+void hns3_dbg_unregister_debugfs(void)
+{
+	debugfs_remove_recursive(hns3_dbgfs_root);
+	hns3_dbgfs_root = NULL;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 20fcf0d1c2ce..162cb9afa0e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -15,11 +15,15 @@
 #include <linux/vermagic.h>
 #include <net/gre.h>
 #include <net/pkt_cls.h>
+#include <net/tcp.h>
 #include <net/vxlan.h>
 
 #include "hnae3.h"
 #include "hns3_enet.h"
 
+#define hns3_set_field(origin, shift, val)	((origin) |= ((val) << (shift)))
+#define hns3_tx_bd_count(S)	DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE)
+
 static void hns3_clear_all_ring(struct hnae3_handle *h);
 static void hns3_force_clear_all_rx_ring(struct hnae3_handle *h);
 static void hns3_remove_hw_addr(struct net_device *netdev);
@@ -239,7 +243,6 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector,
 	tqp_vector->tx_group.coal.int_gl = HNS3_INT_GL_50K;
 	tqp_vector->rx_group.coal.int_gl = HNS3_INT_GL_50K;
 
-	tqp_vector->int_adapt_down = HNS3_INT_ADAPT_DOWN_START;
 	tqp_vector->rx_group.coal.flow_level = HNS3_FLOW_LOW;
 	tqp_vector->tx_group.coal.flow_level = HNS3_FLOW_LOW;
 }
@@ -312,6 +315,24 @@ static u16 hns3_get_max_available_channels(struct hnae3_handle *h)
 	return min_t(u16, rss_size, max_rss_size);
 }
 
+static void hns3_tqp_enable(struct hnae3_queue *tqp)
+{
+	u32 rcb_reg;
+
+	rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
+	rcb_reg |= BIT(HNS3_RING_EN_B);
+	hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
+}
+
+static void hns3_tqp_disable(struct hnae3_queue *tqp)
+{
+	u32 rcb_reg;
+
+	rcb_reg = hns3_read_dev(tqp, HNS3_RING_EN_REG);
+	rcb_reg &= ~BIT(HNS3_RING_EN_B);
+	hns3_write_dev(tqp, HNS3_RING_EN_REG, rcb_reg);
+}
+
 static int hns3_nic_net_up(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -330,20 +351,28 @@ static int hns3_nic_net_up(struct net_device *netdev)
 		return ret;
 	}
 
+	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
+
 	/* enable the vectors */
 	for (i = 0; i < priv->vector_num; i++)
 		hns3_vector_enable(&priv->tqp_vector[i]);
 
+	/* enable rcb */
+	for (j = 0; j < h->kinfo.num_tqps; j++)
+		hns3_tqp_enable(h->kinfo.tqp[j]);
+
 	/* start the ae_dev */
 	ret = h->ae_algo->ops->start ? h->ae_algo->ops->start(h) : 0;
 	if (ret)
 		goto out_start_err;
 
-	clear_bit(HNS3_NIC_STATE_DOWN, &priv->state);
-
 	return 0;
 
 out_start_err:
+	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
+	while (j--)
+		hns3_tqp_disable(h->kinfo.tqp[j]);
+
 	for (j = i - 1; j >= 0; j--)
 		hns3_vector_disable(&priv->tqp_vector[j]);
 
@@ -352,6 +381,29 @@ out_start_err:
 	return ret;
 }
 
+static void hns3_config_xps(struct hns3_nic_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->vector_num; i++) {
+		struct hns3_enet_tqp_vector *tqp_vector = &priv->tqp_vector[i];
+		struct hns3_enet_ring *ring = tqp_vector->tx_group.ring;
+
+		while (ring) {
+			int ret;
+
+			ret = netif_set_xps_queue(priv->netdev,
+						  &tqp_vector->affinity_mask,
+						  ring->tqp->tqp_index);
+			if (ret)
+				netdev_warn(priv->netdev,
+					    "set xps queue failed: %d", ret);
+
+			ring = ring->next;
+		}
+	}
+}
+
 static int hns3_nic_net_open(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
@@ -359,6 +411,9 @@ static int hns3_nic_net_open(struct net_device *netdev)
 	struct hnae3_knic_private_info *kinfo;
 	int i, ret;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	netif_carrier_off(netdev);
 
 	ret = hns3_nic_set_real_num_queue(netdev);
@@ -378,23 +433,28 @@ static int hns3_nic_net_open(struct net_device *netdev)
 				       kinfo->prio_tc[i]);
 	}
 
-	priv->ae_handle->last_reset_time = jiffies;
+	if (h->ae_algo->ops->set_timer_task)
+		h->ae_algo->ops->set_timer_task(priv->ae_handle, true);
+
+	hns3_config_xps(priv);
 	return 0;
 }
 
 static void hns3_nic_net_down(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = hns3_get_handle(netdev);
 	const struct hnae3_ae_ops *ops;
 	int i;
 
-	if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state))
-		return;
-
 	/* disable vectors */
 	for (i = 0; i < priv->vector_num; i++)
 		hns3_vector_disable(&priv->tqp_vector[i]);
 
+	/* disable rcb */
+	for (i = 0; i < h->kinfo.num_tqps; i++)
+		hns3_tqp_disable(h->kinfo.tqp[i]);
+
 	/* stop ae_dev */
 	ops = priv->ae_handle->ae_algo->ops;
 	if (ops->stop)
@@ -408,6 +468,15 @@ static void hns3_nic_net_down(struct net_device *netdev)
 
 static int hns3_nic_net_stop(struct net_device *netdev)
 {
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state))
+		return 0;
+
+	if (h->ae_algo->ops->set_timer_task)
+		h->ae_algo->ops->set_timer_task(priv->ae_handle, false);
+
 	netif_tx_stop_all_queues(netdev);
 	netif_carrier_off(netdev);
 
@@ -465,7 +534,7 @@ static u8 hns3_get_netdev_flags(struct net_device *netdev)
 	u8 flags = 0;
 
 	if (netdev->flags & IFF_PROMISC) {
-		flags = HNAE3_USER_UPE | HNAE3_USER_MPE;
+		flags = HNAE3_USER_UPE | HNAE3_USER_MPE | HNAE3_BPE;
 	} else {
 		flags |= HNAE3_VLAN_FLTR;
 		if (netdev->flags & IFF_ALLMULTI)
@@ -500,13 +569,13 @@ static void hns3_nic_set_rx_mode(struct net_device *netdev)
 		}
 	}
 
-	hns3_update_promisc_mode(netdev, new_flags);
 	/* User mode Promisc mode enable and vlan filtering is disabled to
 	 * let all packets in. MAC-VLAN Table overflow Promisc enabled and
 	 * vlan fitering is enabled
 	 */
 	hns3_enable_vlan_filter(netdev, new_flags & HNAE3_VLAN_FLTR);
 	h->netdev_flags = new_flags;
+	hns3_update_promisc_mode(netdev, new_flags);
 }
 
 int hns3_update_promisc_mode(struct net_device *netdev, u8 promisc_flags)
@@ -553,7 +622,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 		return 0;
 
 	ret = skb_cow_head(skb, 0);
-	if (ret)
+	if (unlikely(ret))
 		return ret;
 
 	l3.hdr = skb_network_header(skb);
@@ -592,7 +661,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 
 	/* normal or tunnel packet*/
 	l4_offset = l4.hdr - skb->data;
-	hdr_len = (l4.tcp->doff * 4) + l4_offset;
+	hdr_len = (l4.tcp->doff << 2) + l4_offset;
 
 	/* remove payload length from inner pseudo checksum when tso*/
 	l4_paylen = skb->len - l4_offset;
@@ -601,8 +670,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 
 	/* find the txbd field values */
 	*paylen = skb->len - hdr_len;
-	hnae3_set_bit(*type_cs_vlan_tso,
-		      HNS3_TXD_TSO_B, 1);
+	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_TSO_B, 1);
 
 	/* get MSS for TSO */
 	*mss = skb_shinfo(skb)->gso_size;
@@ -613,11 +681,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto,
 				u8 *il4_proto)
 {
-	union {
-		struct iphdr *v4;
-		struct ipv6hdr *v6;
-		unsigned char *hdr;
-	} l3;
+	union l3_hdr_info l3;
 	unsigned char *l4_hdr;
 	unsigned char *exthdr;
 	u8 l4_proto_tmp;
@@ -670,17 +734,8 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 				u8 il4_proto, u32 *type_cs_vlan_tso,
 				u32 *ol_type_vlan_len_msec)
 {
-	union {
-		struct iphdr *v4;
-		struct ipv6hdr *v6;
-		unsigned char *hdr;
-	} l3;
-	union {
-		struct tcphdr *tcp;
-		struct udphdr *udp;
-		struct gre_base_hdr *gre;
-		unsigned char *hdr;
-	} l4;
+	union l3_hdr_info l3;
+	union l4_hdr_info l4;
 	unsigned char *l2_hdr;
 	u8 l4_proto = ol4_proto;
 	u32 ol2_len;
@@ -694,21 +749,19 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 	/* compute L2 header size for normal packet, defined in 2 Bytes */
 	l2_len = l3.hdr - skb->data;
-	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-			HNS3_TXD_L2LEN_S, l2_len >> 1);
+	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_S, l2_len >> 1);
 
 	/* tunnel packet*/
 	if (skb->encapsulation) {
 		/* compute OL2 header size, defined in 2 Bytes */
 		ol2_len = l2_len;
-		hnae3_set_field(*ol_type_vlan_len_msec,
-				HNS3_TXD_L2LEN_M,
-				HNS3_TXD_L2LEN_S, ol2_len >> 1);
+		hns3_set_field(*ol_type_vlan_len_msec,
+			       HNS3_TXD_L2LEN_S, ol2_len >> 1);
 
 		/* compute OL3 header size, defined in 4 Bytes */
 		ol3_len = l4.hdr - l3.hdr;
-		hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
-				HNS3_TXD_L3LEN_S, ol3_len >> 2);
+		hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_S,
+			       ol3_len >> 2);
 
 		/* MAC in UDP, MAC in GRE (0x6558)*/
 		if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) {
@@ -717,17 +770,16 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 			/* compute OL4 header size, defined in 4 Bytes. */
 			ol4_len = l2_hdr - l4.hdr;
-			hnae3_set_field(*ol_type_vlan_len_msec,
-					HNS3_TXD_L4LEN_M, HNS3_TXD_L4LEN_S,
-					ol4_len >> 2);
+			hns3_set_field(*ol_type_vlan_len_msec,
+				       HNS3_TXD_L4LEN_S, ol4_len >> 2);
 
 			/* switch IP header ptr from outer to inner header */
 			l3.hdr = skb_inner_network_header(skb);
 
 			/* compute inner l2 header size, defined in 2 Bytes. */
 			l2_len = l3.hdr - l2_hdr;
-			hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-					HNS3_TXD_L2LEN_S, l2_len >> 1);
+			hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_S,
+				       l2_len >> 1);
 		} else {
 			/* skb packet types not supported by hardware,
 			 * txbd len fild doesn't be filled.
@@ -743,24 +795,21 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 	/* compute inner(/normal) L3 header size, defined in 4 Bytes */
 	l3_len = l4.hdr - l3.hdr;
-	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
-			HNS3_TXD_L3LEN_S, l3_len >> 2);
+	hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_S, l3_len >> 2);
 
 	/* compute inner(/normal) L4 header size, defined in 4 Bytes */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-				HNS3_TXD_L4LEN_S, l4.tcp->doff);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
+			       l4.tcp->doff);
 		break;
 	case IPPROTO_SCTP:
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-				HNS3_TXD_L4LEN_S,
-				(sizeof(struct sctphdr) >> 2));
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
+			       (sizeof(struct sctphdr) >> 2));
 		break;
 	case IPPROTO_UDP:
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-				HNS3_TXD_L4LEN_S,
-				(sizeof(struct udphdr) >> 2));
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_S,
+			       (sizeof(struct udphdr) >> 2));
 		break;
 	default:
 		/* skb packet types not supported by hardware,
@@ -779,12 +828,7 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 static bool hns3_tunnel_csum_bug(struct sk_buff *skb)
 {
 #define IANA_VXLAN_PORT	4789
-	union {
-		struct tcphdr *tcp;
-		struct udphdr *udp;
-		struct gre_base_hdr *gre;
-		unsigned char *hdr;
-	} l4;
+	union l4_hdr_info l4;
 
 	l4.hdr = skb_transport_header(skb);
 
@@ -800,11 +844,7 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 				   u8 il4_proto, u32 *type_cs_vlan_tso,
 				   u32 *ol_type_vlan_len_msec)
 {
-	union {
-		struct iphdr *v4;
-		struct ipv6hdr *v6;
-		unsigned char *hdr;
-	} l3;
+	union l3_hdr_info l3;
 	u32 l4_proto = ol4_proto;
 
 	l3.hdr = skb_network_header(skb);
@@ -814,34 +854,30 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 		/* define outer network header type.*/
 		if (skb->protocol == htons(ETH_P_IP)) {
 			if (skb_is_gso(skb))
-				hnae3_set_field(*ol_type_vlan_len_msec,
-						HNS3_TXD_OL3T_M,
-						HNS3_TXD_OL3T_S,
-						HNS3_OL3T_IPV4_CSUM);
+				hns3_set_field(*ol_type_vlan_len_msec,
+					       HNS3_TXD_OL3T_S,
+					       HNS3_OL3T_IPV4_CSUM);
 			else
-				hnae3_set_field(*ol_type_vlan_len_msec,
-						HNS3_TXD_OL3T_M,
-						HNS3_TXD_OL3T_S,
-						HNS3_OL3T_IPV4_NO_CSUM);
+				hns3_set_field(*ol_type_vlan_len_msec,
+					       HNS3_TXD_OL3T_S,
+					       HNS3_OL3T_IPV4_NO_CSUM);
 
 		} else if (skb->protocol == htons(ETH_P_IPV6)) {
-			hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
-					HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
+			hns3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_S,
+				       HNS3_OL3T_IPV6);
 		}
 
 		/* define tunnel type(OL4).*/
 		switch (l4_proto) {
 		case IPPROTO_UDP:
-			hnae3_set_field(*ol_type_vlan_len_msec,
-					HNS3_TXD_TUNTYPE_M,
-					HNS3_TXD_TUNTYPE_S,
-					HNS3_TUN_MAC_IN_UDP);
+			hns3_set_field(*ol_type_vlan_len_msec,
+				       HNS3_TXD_TUNTYPE_S,
+				       HNS3_TUN_MAC_IN_UDP);
 			break;
 		case IPPROTO_GRE:
-			hnae3_set_field(*ol_type_vlan_len_msec,
-					HNS3_TXD_TUNTYPE_M,
-					HNS3_TXD_TUNTYPE_S,
-					HNS3_TUN_NVGRE);
+			hns3_set_field(*ol_type_vlan_len_msec,
+				       HNS3_TXD_TUNTYPE_S,
+				       HNS3_TUN_NVGRE);
 			break;
 		default:
 			/* drop the skb tunnel packet if hardware don't support,
@@ -862,43 +898,37 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 	}
 
 	if (l3.v4->version == 4) {
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-				HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_S,
+			       HNS3_L3T_IPV4);
 
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
 		if (skb_is_gso(skb))
-			hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
+			hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
 	} else if (l3.v6->version == 6) {
-		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-				HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_S,
+			       HNS3_L3T_IPV6);
 	}
 
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
-		hnae3_set_field(*type_cs_vlan_tso,
-				HNS3_TXD_L4T_M,
-				HNS3_TXD_L4T_S,
-				HNS3_L4T_TCP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
+			       HNS3_L4T_TCP);
 		break;
 	case IPPROTO_UDP:
 		if (hns3_tunnel_csum_bug(skb))
 			break;
 
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
-		hnae3_set_field(*type_cs_vlan_tso,
-				HNS3_TXD_L4T_M,
-				HNS3_TXD_L4T_S,
-				HNS3_L4T_UDP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
+			       HNS3_L4T_UDP);
 		break;
 	case IPPROTO_SCTP:
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
-		hnae3_set_field(*type_cs_vlan_tso,
-				HNS3_TXD_L4T_M,
-				HNS3_TXD_L4T_S,
-				HNS3_L4T_SCTP);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hns3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4T_S,
+			       HNS3_L4T_SCTP);
 		break;
 	default:
 		/* drop the skb tunnel packet if hardware don't support,
@@ -920,11 +950,8 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 {
 	/* Config bd buffer end */
-	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
-			HNS3_TXD_BDTYPE_S, 0);
-	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
-	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
-	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
+	hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
+	hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
 }
 
 static int hns3_fill_desc_vtags(struct sk_buff *skb,
@@ -957,10 +984,10 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		 * and use inner_vtag in one tag case.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q)) {
-			hnae3_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
+			hns3_set_field(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
 			*out_vtag = vlan_tag;
 		} else {
-			hnae3_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
+			hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
 			*inner_vtag = vlan_tag;
 		}
 	} else if (skb->protocol == htons(ETH_P_8021Q)) {
@@ -968,7 +995,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		int rc;
 
 		rc = skb_cow_head(skb, 0);
-		if (rc < 0)
+		if (unlikely(rc < 0))
 			return rc;
 		vhdr = (struct vlan_ethhdr *)skb->data;
 		vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7)
@@ -985,26 +1012,21 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
 	struct hns3_desc *desc = &ring->desc[ring->next_to_use];
 	struct device *dev = ring_to_dev(ring);
-	u32 ol_type_vlan_len_msec = 0;
 	u16 bdtp_fe_sc_vld_ra_ri = 0;
 	struct skb_frag_struct *frag;
 	unsigned int frag_buf_num;
-	u32 type_cs_vlan_tso = 0;
-	struct sk_buff *skb;
-	u16 inner_vtag = 0;
-	u16 out_vtag = 0;
-	unsigned int k;
-	int sizeoflast;
-	u32 paylen = 0;
+	int k, sizeoflast;
 	dma_addr_t dma;
-	u16 mss = 0;
-	u8 ol4_proto;
-	u8 il4_proto;
-	int ret;
 
 	if (type == DESC_TYPE_SKB) {
-		skb = (struct sk_buff *)priv;
-		paylen = skb->len;
+		struct sk_buff *skb = (struct sk_buff *)priv;
+		u32 ol_type_vlan_len_msec = 0;
+		u32 type_cs_vlan_tso = 0;
+		u32 paylen = skb->len;
+		u16 inner_vtag = 0;
+		u16 out_vtag = 0;
+		u16 mss = 0;
+		int ret;
 
 		ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso,
 					   &ol_type_vlan_len_msec,
@@ -1013,10 +1035,12 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 			return ret;
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			u8 ol4_proto, il4_proto;
+
 			skb_reset_mac_len(skb);
 
 			ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
-			if (ret)
+			if (unlikely(ret))
 				return ret;
 			hns3_set_l2l3l4_len(skb, ol4_proto, il4_proto,
 					    &type_cs_vlan_tso,
@@ -1024,12 +1048,12 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 			ret = hns3_set_l3l4_type_csum(skb, ol4_proto, il4_proto,
 						      &type_cs_vlan_tso,
 						      &ol_type_vlan_len_msec);
-			if (ret)
+			if (unlikely(ret))
 				return ret;
 
 			ret = hns3_set_tso(skb, &paylen, &mss,
 					   &type_cs_vlan_tso);
-			if (ret)
+			if (unlikely(ret))
 				return ret;
 		}
 
@@ -1049,15 +1073,15 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 		dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE);
 	}
 
-	if (dma_mapping_error(ring->dev, dma)) {
+	if (unlikely(dma_mapping_error(ring->dev, dma))) {
 		ring->stats.sw_err_cnt++;
 		return -ENOMEM;
 	}
 
 	desc_cb->length = size;
 
-	frag_buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
-	sizeoflast = size % HNS3_MAX_BD_SIZE;
+	frag_buf_num = hns3_tx_bd_count(size);
+	sizeoflast = size & HNS3_TX_LAST_SIZE_M;
 	sizeoflast = sizeoflast ? sizeoflast : HNS3_MAX_BD_SIZE;
 
 	/* When frag size is bigger than hardware limit, split this frag */
@@ -1092,6 +1116,7 @@ static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum,
 				   struct hns3_enet_ring *ring)
 {
 	struct sk_buff *skb = *out_skb;
+	struct sk_buff *new_skb = NULL;
 	struct skb_frag_struct *frag;
 	int bdnum_for_frag;
 	int frag_num;
@@ -1100,21 +1125,32 @@ static int hns3_nic_maybe_stop_tso(struct sk_buff **out_skb, int *bnum,
 	int i;
 
 	size = skb_headlen(skb);
-	buf_num = (size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
+	buf_num = hns3_tx_bd_count(size);
 
 	frag_num = skb_shinfo(skb)->nr_frags;
 	for (i = 0; i < frag_num; i++) {
 		frag = &skb_shinfo(skb)->frags[i];
 		size = skb_frag_size(frag);
-		bdnum_for_frag =
-			(size + HNS3_MAX_BD_SIZE - 1) / HNS3_MAX_BD_SIZE;
-		if (bdnum_for_frag > HNS3_MAX_BD_PER_FRAG)
+		bdnum_for_frag = hns3_tx_bd_count(size);
+		if (unlikely(bdnum_for_frag > HNS3_MAX_BD_PER_FRAG))
 			return -ENOMEM;
 
 		buf_num += bdnum_for_frag;
 	}
 
-	if (buf_num > ring_space(ring))
+	if (unlikely(buf_num > HNS3_MAX_BD_PER_FRAG)) {
+		buf_num = hns3_tx_bd_count(skb->len);
+		if (ring_space(ring) < buf_num)
+			return -EBUSY;
+		/* manual split the send packet */
+		new_skb = skb_copy(skb, GFP_ATOMIC);
+		if (!new_skb)
+			return -ENOMEM;
+		dev_kfree_skb_any(skb);
+		*out_skb = new_skb;
+	}
+
+	if (unlikely(ring_space(ring) < buf_num))
 		return -EBUSY;
 
 	*bnum = buf_num;
@@ -1125,11 +1161,24 @@ static int hns3_nic_maybe_stop_tx(struct sk_buff **out_skb, int *bnum,
 				  struct hns3_enet_ring *ring)
 {
 	struct sk_buff *skb = *out_skb;
+	struct sk_buff *new_skb = NULL;
 	int buf_num;
 
 	/* No. of segments (plus a header) */
 	buf_num = skb_shinfo(skb)->nr_frags + 1;
 
+	if (unlikely(buf_num > HNS3_MAX_BD_PER_FRAG)) {
+		buf_num = hns3_tx_bd_count(skb->len);
+		if (ring_space(ring) < buf_num)
+			return -EBUSY;
+		/* manual split the send packet */
+		new_skb = skb_copy(skb, GFP_ATOMIC);
+		if (!new_skb)
+			return -ENOMEM;
+		dev_kfree_skb_any(skb);
+		*out_skb = new_skb;
+	}
+
 	if (unlikely(ring_space(ring) < buf_num))
 		return -EBUSY;
 
@@ -1211,9 +1260,9 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	next_to_use_head = ring->next_to_use;
 
-	ret = priv->ops.fill_desc(ring, skb, size, seg_num == 1 ? 1 : 0,
-				  DESC_TYPE_SKB);
-	if (ret)
+	ret = hns3_fill_desc(ring, skb, size, seg_num == 1 ? 1 : 0,
+			     DESC_TYPE_SKB);
+	if (unlikely(ret))
 		goto head_fill_err;
 
 	next_to_use_frag = ring->next_to_use;
@@ -1222,11 +1271,11 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 		frag = &skb_shinfo(skb)->frags[i - 1];
 		size = skb_frag_size(frag);
 
-		ret = priv->ops.fill_desc(ring, frag, size,
-					  seg_num - 1 == i ? 1 : 0,
-					  DESC_TYPE_PAGE);
+		ret = hns3_fill_desc(ring, frag, size,
+				     seg_num - 1 == i ? 1 : 0,
+				     DESC_TYPE_PAGE);
 
-		if (ret)
+		if (unlikely(ret))
 			goto frag_fill_err;
 	}
 
@@ -1303,6 +1352,7 @@ static int hns3_nic_set_features(struct net_device *netdev,
 	netdev_features_t changed = netdev->features ^ features;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = priv->ae_handle;
+	bool enable;
 	int ret;
 
 	if (changed & (NETIF_F_TSO | NETIF_F_TSO6)) {
@@ -1312,30 +1362,30 @@ static int hns3_nic_set_features(struct net_device *netdev,
 			priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx;
 	}
 
+	if (changed & (NETIF_F_GRO_HW) && h->ae_algo->ops->set_gro_en) {
+		enable = !!(features & NETIF_F_GRO_HW);
+		ret = h->ae_algo->ops->set_gro_en(h, enable);
+		if (ret)
+			return ret;
+	}
+
 	if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) &&
 	    h->ae_algo->ops->enable_vlan_filter) {
-		if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
-			h->ae_algo->ops->enable_vlan_filter(h, true);
-		else
-			h->ae_algo->ops->enable_vlan_filter(h, false);
+		enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER);
+		h->ae_algo->ops->enable_vlan_filter(h, enable);
 	}
 
 	if ((changed & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    h->ae_algo->ops->enable_hw_strip_rxvtag) {
-		if (features & NETIF_F_HW_VLAN_CTAG_RX)
-			ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, true);
-		else
-			ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, false);
-
+		enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX);
+		ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, enable);
 		if (ret)
 			return ret;
 	}
 
 	if ((changed & NETIF_F_NTUPLE) && h->ae_algo->ops->enable_fd) {
-		if (features & NETIF_F_NTUPLE)
-			h->ae_algo->ops->enable_fd(h, true);
-		else
-			h->ae_algo->ops->enable_fd(h, false);
+		enable = !!(features & NETIF_F_NTUPLE);
+		h->ae_algo->ops->enable_fd(h, enable);
 	}
 
 	netdev->features = features;
@@ -1349,7 +1399,12 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 	int queue_num = priv->ae_handle->kinfo.num_tqps;
 	struct hnae3_handle *handle = priv->ae_handle;
 	struct hns3_enet_ring *ring;
+	u64 rx_length_errors = 0;
+	u64 rx_crc_errors = 0;
+	u64 rx_multicast = 0;
 	unsigned int start;
+	u64 tx_errors = 0;
+	u64 rx_errors = 0;
 	unsigned int idx;
 	u64 tx_bytes = 0;
 	u64 rx_bytes = 0;
@@ -1370,8 +1425,8 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			start = u64_stats_fetch_begin_irq(&ring->syncp);
 			tx_bytes += ring->stats.tx_bytes;
 			tx_pkts += ring->stats.tx_pkts;
-			tx_drop += ring->stats.tx_busy;
 			tx_drop += ring->stats.sw_err_cnt;
+			tx_errors += ring->stats.sw_err_cnt;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 
 		/* fetch the rx stats */
@@ -1381,8 +1436,13 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 			rx_bytes += ring->stats.rx_bytes;
 			rx_pkts += ring->stats.rx_pkts;
 			rx_drop += ring->stats.non_vld_descs;
-			rx_drop += ring->stats.err_pkt_len;
 			rx_drop += ring->stats.l2_err;
+			rx_errors += ring->stats.non_vld_descs;
+			rx_errors += ring->stats.l2_err;
+			rx_crc_errors += ring->stats.l2_err;
+			rx_crc_errors += ring->stats.l3l4_csum_err;
+			rx_multicast += ring->stats.rx_multicast;
+			rx_length_errors += ring->stats.err_pkt_len;
 		} while (u64_stats_fetch_retry_irq(&ring->syncp, start));
 	}
 
@@ -1391,15 +1451,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev,
 	stats->rx_bytes = rx_bytes;
 	stats->rx_packets = rx_pkts;
 
-	stats->rx_errors = netdev->stats.rx_errors;
-	stats->multicast = netdev->stats.multicast;
-	stats->rx_length_errors = netdev->stats.rx_length_errors;
-	stats->rx_crc_errors = netdev->stats.rx_crc_errors;
+	stats->rx_errors = rx_errors;
+	stats->multicast = rx_multicast;
+	stats->rx_length_errors = rx_length_errors;
+	stats->rx_crc_errors = rx_crc_errors;
 	stats->rx_missed_errors = netdev->stats.rx_missed_errors;
 
-	stats->tx_errors = netdev->stats.tx_errors;
-	stats->rx_dropped = rx_drop + netdev->stats.rx_dropped;
-	stats->tx_dropped = tx_drop + netdev->stats.tx_dropped;
+	stats->tx_errors = tx_errors;
+	stats->rx_dropped = rx_drop;
+	stats->tx_dropped = tx_drop;
 	stats->collisions = netdev->stats.collisions;
 	stats->rx_over_errors = netdev->stats.rx_over_errors;
 	stats->rx_frame_errors = netdev->stats.rx_frame_errors;
@@ -1422,8 +1482,6 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	u8 tc = mqprio_qopt->qopt.num_tc;
 	u16 mode = mqprio_qopt->mode;
 	u8 hw = mqprio_qopt->qopt.hw;
-	bool if_running;
-	int ret;
 
 	if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
 	       mode == TC_MQPRIO_MODE_CHANNEL) || (!hw && tc == 0)))
@@ -1435,24 +1493,8 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	if (!netdev)
 		return -EINVAL;
 
-	if_running = netif_running(netdev);
-	if (if_running) {
-		hns3_nic_net_stop(netdev);
-		msleep(100);
-	}
-
-	ret = (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
+	return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ?
 		kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP;
-	if (ret)
-		goto out;
-
-	ret = hns3_nic_set_real_num_queue(netdev);
-
-out:
-	if (if_running)
-		hns3_nic_net_open(netdev);
-
-	return ret;
 }
 
 static int hns3_nic_setup_tc(struct net_device *dev, enum tc_setup_type type,
@@ -1530,18 +1572,11 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan,
 static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
-	bool if_running = netif_running(netdev);
 	int ret;
 
 	if (!h->ae_algo->ops->set_mtu)
 		return -EOPNOTSUPP;
 
-	/* if this was called with netdev up then bring netdevice down */
-	if (if_running) {
-		(void)hns3_nic_net_stop(netdev);
-		msleep(100);
-	}
-
 	ret = h->ae_algo->ops->set_mtu(h, new_mtu);
 	if (ret)
 		netdev_err(netdev, "failed to change MTU in hardware %d\n",
@@ -1549,10 +1584,6 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu)
 	else
 		netdev->mtu = new_mtu;
 
-	/* if the netdev was running earlier, bring it up again */
-	if (if_running && hns3_nic_net_open(netdev))
-		ret = -EINVAL;
-
 	return ret;
 }
 
@@ -1615,10 +1646,9 @@ static void hns3_nic_net_timeout(struct net_device *ndev)
 
 	priv->tx_timeout_count++;
 
-	if (time_before(jiffies, (h->last_reset_time + ndev->watchdog_timeo)))
-		return;
-
-	/* request the reset */
+	/* request the reset, and let the hclge to determine
+	 * which reset level should be done
+	 */
 	if (h->ae_algo->ops->reset_event)
 		h->ae_algo->ops->reset_event(h->pdev, h);
 }
@@ -1682,8 +1712,10 @@ static void hns3_disable_sriov(struct pci_dev *pdev)
 static void hns3_get_dev_capability(struct pci_dev *pdev,
 				    struct hnae3_ae_dev *ae_dev)
 {
-	if (pdev->revision >= 0x21)
+	if (pdev->revision >= 0x21) {
 		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B, 1);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_SUPPORT_GRO_B, 1);
+	}
 }
 
 /* hns3_probe - Device initialization routine
@@ -1715,9 +1747,13 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	hns3_get_dev_capability(pdev, ae_dev);
 	pci_set_drvdata(pdev, ae_dev);
 
-	hnae3_register_ae_dev(ae_dev);
+	ret = hnae3_register_ae_dev(ae_dev);
+	if (ret) {
+		devm_kfree(&pdev->dev, ae_dev);
+		pci_set_drvdata(pdev, NULL);
+	}
 
-	return 0;
+	return ret;
 }
 
 /* hns3_remove - Device removal routine
@@ -1731,6 +1767,7 @@ static void hns3_remove(struct pci_dev *pdev)
 		hns3_disable_sriov(pdev);
 
 	hnae3_unregister_ae_dev(ae_dev);
+	pci_set_drvdata(pdev, NULL);
 }
 
 /**
@@ -1795,8 +1832,8 @@ static pci_ers_result_t hns3_error_detected(struct pci_dev *pdev,
 		return PCI_ERS_RESULT_NONE;
 	}
 
-	if (ae_dev->ops->process_hw_error)
-		ret = ae_dev->ops->process_hw_error(ae_dev);
+	if (ae_dev->ops->handle_hw_ras_error)
+		ret = ae_dev->ops->handle_hw_ras_error(ae_dev);
 	else
 		return PCI_ERS_RESULT_NONE;
 
@@ -1812,16 +1849,38 @@ static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev)
 
 	/* request the reset */
 	if (ae_dev->ops->reset_event) {
-		ae_dev->ops->reset_event(pdev, NULL);
+		if (!ae_dev->override_pci_need_reset)
+			ae_dev->ops->reset_event(pdev, NULL);
+
 		return PCI_ERS_RESULT_RECOVERED;
 	}
 
 	return PCI_ERS_RESULT_DISCONNECT;
 }
 
+static void hns3_reset_prepare(struct pci_dev *pdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+
+	dev_info(&pdev->dev, "hns3 flr prepare\n");
+	if (ae_dev && ae_dev->ops && ae_dev->ops->flr_prepare)
+		ae_dev->ops->flr_prepare(ae_dev);
+}
+
+static void hns3_reset_done(struct pci_dev *pdev)
+{
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+
+	dev_info(&pdev->dev, "hns3 flr done\n");
+	if (ae_dev && ae_dev->ops && ae_dev->ops->flr_done)
+		ae_dev->ops->flr_done(ae_dev);
+}
+
 static const struct pci_error_handlers hns3_err_handler = {
 	.error_detected = hns3_error_detected,
 	.slot_reset     = hns3_slot_reset,
+	.reset_prepare	= hns3_reset_prepare,
+	.reset_done	= hns3_reset_done,
 };
 
 static struct pci_driver hns3_driver = {
@@ -1875,7 +1934,8 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC;
 
 	if (pdev->revision >= 0x21) {
-		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+		netdev->hw_features |= NETIF_F_GRO_HW;
+		netdev->features |= NETIF_F_GRO_HW;
 
 		if (!(h->flags & HNAE3_SUPPORT_VF)) {
 			netdev->hw_features |= NETIF_F_NTUPLE;
@@ -1979,9 +2039,8 @@ static int hns3_alloc_desc(struct hns3_enet_ring *ring)
 {
 	int size = ring->desc_num * sizeof(ring->desc[0]);
 
-	ring->desc = dma_zalloc_coherent(ring_to_dev(ring), size,
-					 &ring->desc_dma_addr,
-					 GFP_KERNEL);
+	ring->desc = dma_alloc_coherent(ring_to_dev(ring), size,
+					&ring->desc_dma_addr, GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
@@ -2253,14 +2312,19 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	if (!(netdev->features & NETIF_F_RXCSUM))
 		return;
 
+	/* We MUST enable hardware checksum before enabling hardware GRO */
+	if (skb_shinfo(skb)->gso_size) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		return;
+	}
+
 	/* check if hardware has done checksum */
-	if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
+	if (!(bd_base_info & BIT(HNS3_RXD_L3L4P_B)))
 		return;
 
-	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L3E_B) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_L4E_B) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) {
+	if (unlikely(l234info & (BIT(HNS3_RXD_L3E_B) | BIT(HNS3_RXD_L4E_B) |
+				 BIT(HNS3_RXD_OL3E_B) |
+				 BIT(HNS3_RXD_OL4E_B)))) {
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.l3l4_csum_err++;
 		u64_stats_update_end(&ring->syncp);
@@ -2268,11 +2332,6 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		return;
 	}
 
-	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
-				  HNS3_RXD_L3ID_S);
-	l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
-				  HNS3_RXD_L4ID_S);
-
 	ol4_type = hnae3_get_field(l234info, HNS3_RXD_OL4ID_M,
 				   HNS3_RXD_OL4ID_S);
 	switch (ol4_type) {
@@ -2281,6 +2340,11 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		skb->csum_level = 1;
 		/* fall through */
 	case HNS3_OL4_TYPE_NO_TUN:
+		l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+					  HNS3_RXD_L3ID_S);
+		l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
+					  HNS3_RXD_L4ID_S);
+
 		/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
 		if ((l3_type == HNS3_L3_TYPE_IPV4 ||
 		     l3_type == HNS3_L3_TYPE_IPV6) &&
@@ -2296,6 +2360,9 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 
 static void hns3_rx_skb(struct hns3_enet_ring *ring, struct sk_buff *skb)
 {
+	if (skb_has_frag_list(skb))
+		napi_gro_flush(&ring->tqp_vector->napi, false);
+
 	napi_gro_receive(&ring->tqp_vector->napi, skb);
 }
 
@@ -2329,12 +2396,168 @@ static bool hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 	}
 }
 
+static int hns3_alloc_skb(struct hns3_enet_ring *ring, int length,
+			  unsigned char *va)
+{
+#define HNS3_NEED_ADD_FRAG	1
+	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean];
+	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	struct sk_buff *skb;
+
+	ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE);
+	skb = ring->skb;
+	if (unlikely(!skb)) {
+		netdev_err(netdev, "alloc rx skb fail\n");
+
+		u64_stats_update_begin(&ring->syncp);
+		ring->stats.sw_err_cnt++;
+		u64_stats_update_end(&ring->syncp);
+
+		return -ENOMEM;
+	}
+
+	prefetchw(skb->data);
+
+	ring->pending_buf = 1;
+	ring->frag_num = 0;
+	ring->tail_skb = NULL;
+	if (length <= HNS3_RX_HEAD_SIZE) {
+		memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
+
+		/* We can reuse buffer as-is, just make sure it is local */
+		if (likely(page_to_nid(desc_cb->priv) == numa_node_id()))
+			desc_cb->reuse_flag = 1;
+		else /* This page cannot be reused so discard it */
+			put_page(desc_cb->priv);
+
+		ring_ptr_move_fw(ring, next_to_clean);
+		return 0;
+	}
+	u64_stats_update_begin(&ring->syncp);
+	ring->stats.seg_pkt_cnt++;
+	u64_stats_update_end(&ring->syncp);
+
+	ring->pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
+	__skb_put(skb, ring->pull_len);
+	hns3_nic_reuse_page(skb, ring->frag_num++, ring, ring->pull_len,
+			    desc_cb);
+	ring_ptr_move_fw(ring, next_to_clean);
+
+	return HNS3_NEED_ADD_FRAG;
+}
+
+static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc,
+			 struct sk_buff **out_skb, bool pending)
+{
+	struct sk_buff *skb = *out_skb;
+	struct sk_buff *head_skb = *out_skb;
+	struct sk_buff *new_skb;
+	struct hns3_desc_cb *desc_cb;
+	struct hns3_desc *pre_desc;
+	u32 bd_base_info;
+	int pre_bd;
+
+	/* if there is pending bd, the SW param next_to_clean has moved
+	 * to next and the next is NULL
+	 */
+	if (pending) {
+		pre_bd = (ring->next_to_clean - 1 + ring->desc_num) %
+			ring->desc_num;
+		pre_desc = &ring->desc[pre_bd];
+		bd_base_info = le32_to_cpu(pre_desc->rx.bd_base_info);
+	} else {
+		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+	}
+
+	while (!(bd_base_info & BIT(HNS3_RXD_FE_B))) {
+		desc = &ring->desc[ring->next_to_clean];
+		desc_cb = &ring->desc_cb[ring->next_to_clean];
+		bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
+		/* make sure HW write desc complete */
+		dma_rmb();
+		if (!(bd_base_info & BIT(HNS3_RXD_VLD_B)))
+			return -ENXIO;
+
+		if (unlikely(ring->frag_num >= MAX_SKB_FRAGS)) {
+			new_skb = napi_alloc_skb(&ring->tqp_vector->napi,
+						 HNS3_RX_HEAD_SIZE);
+			if (unlikely(!new_skb)) {
+				netdev_err(ring->tqp->handle->kinfo.netdev,
+					   "alloc rx skb frag fail\n");
+				return -ENXIO;
+			}
+			ring->frag_num = 0;
+
+			if (ring->tail_skb) {
+				ring->tail_skb->next = new_skb;
+				ring->tail_skb = new_skb;
+			} else {
+				skb_shinfo(skb)->frag_list = new_skb;
+				ring->tail_skb = new_skb;
+			}
+		}
+
+		if (ring->tail_skb) {
+			head_skb->truesize += hnae3_buf_size(ring);
+			head_skb->data_len += le16_to_cpu(desc->rx.size);
+			head_skb->len += le16_to_cpu(desc->rx.size);
+			skb = ring->tail_skb;
+		}
+
+		hns3_nic_reuse_page(skb, ring->frag_num++, ring, 0, desc_cb);
+		ring_ptr_move_fw(ring, next_to_clean);
+		ring->pending_buf++;
+	}
+
+	return 0;
+}
+
+static void hns3_set_gro_param(struct sk_buff *skb, u32 l234info,
+			       u32 bd_base_info)
+{
+	u16 gro_count;
+	u32 l3_type;
+
+	gro_count = hnae3_get_field(l234info, HNS3_RXD_GRO_COUNT_M,
+				    HNS3_RXD_GRO_COUNT_S);
+	/* if there is no HW GRO, do not set gro params */
+	if (!gro_count)
+		return;
+
+	/* tcp_gro_complete() will copy NAPI_GRO_CB(skb)->count
+	 * to skb_shinfo(skb)->gso_segs
+	 */
+	NAPI_GRO_CB(skb)->count = gro_count;
+
+	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+				  HNS3_RXD_L3ID_S);
+	if (l3_type == HNS3_L3_TYPE_IPV4)
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+	else if (l3_type == HNS3_L3_TYPE_IPV6)
+		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
+	else
+		return;
+
+	skb_shinfo(skb)->gso_size = hnae3_get_field(bd_base_info,
+						    HNS3_RXD_GRO_SIZE_M,
+						    HNS3_RXD_GRO_SIZE_S);
+	if (skb_shinfo(skb)->gso_size)
+		tcp_gro_complete(skb);
+}
+
 static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 				     struct sk_buff *skb)
 {
-	struct hns3_desc *desc = &ring->desc[ring->next_to_clean];
 	struct hnae3_handle *handle = ring->tqp->handle;
 	enum pkt_hash_types rss_type;
+	struct hns3_desc *desc;
+	int last_bd;
+
+	/* When driver handle the rss type, ring->next_to_clean indicates the
+	 * first descriptor of next packet, need -1 here.
+	 */
+	last_bd = (ring->next_to_clean - 1 + ring->desc_num) % ring->desc_num;
+	desc = &ring->desc[last_bd];
 
 	if (le32_to_cpu(desc->rx.rss_hash))
 		rss_type = handle->kinfo.rss_type;
@@ -2345,18 +2568,17 @@ static void hns3_set_rx_skb_rss_type(struct hns3_enet_ring *ring,
 }
 
 static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
-			     struct sk_buff **out_skb, int *out_bnum)
+			     struct sk_buff **out_skb)
 {
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
+	enum hns3_pkt_l2t_type l2_frame_type;
+	struct sk_buff *skb = ring->skb;
 	struct hns3_desc_cb *desc_cb;
 	struct hns3_desc *desc;
-	struct sk_buff *skb;
-	unsigned char *va;
 	u32 bd_base_info;
-	int pull_len;
 	u32 l234info;
 	int length;
-	int bnum;
+	int ret;
 
 	desc = &ring->desc[ring->next_to_clean];
 	desc_cb = &ring->desc_cb[ring->next_to_clean];
@@ -2367,10 +2589,11 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Check valid BD */
-	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
-		return -EFAULT;
+	if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B))))
+		return -ENXIO;
 
-	va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
+	if (!skb)
+		ring->va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
 
 	/* Prefetch first cache line of first page
 	 * Idea is to cache few bytes of the header of the packet. Our L1 Cache
@@ -2379,62 +2602,42 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	 * lines. In such a case, single fetch would suffice to cache in the
 	 * relevant part of the header.
 	 */
-	prefetch(va);
+	prefetch(ring->va);
 #if L1_CACHE_BYTES < 128
-	prefetch(va + L1_CACHE_BYTES);
+	prefetch(ring->va + L1_CACHE_BYTES);
 #endif
 
-	skb = *out_skb = napi_alloc_skb(&ring->tqp_vector->napi,
-					HNS3_RX_HEAD_SIZE);
-	if (unlikely(!skb)) {
-		netdev_err(netdev, "alloc rx skb fail\n");
-
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.sw_err_cnt++;
-		u64_stats_update_end(&ring->syncp);
-
-		return -ENOMEM;
-	}
-
-	prefetchw(skb->data);
-
-	bnum = 1;
-	if (length <= HNS3_RX_HEAD_SIZE) {
-		memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long)));
+	if (!skb) {
+		ret = hns3_alloc_skb(ring, length, ring->va);
+		*out_skb = skb = ring->skb;
 
-		/* We can reuse buffer as-is, just make sure it is local */
-		if (likely(page_to_nid(desc_cb->priv) == numa_node_id()))
-			desc_cb->reuse_flag = 1;
-		else /* This page cannot be reused so discard it */
-			put_page(desc_cb->priv);
+		if (ret < 0) /* alloc buffer fail */
+			return ret;
+		if (ret > 0) { /* need add frag */
+			ret = hns3_add_frag(ring, desc, &skb, false);
+			if (ret)
+				return ret;
 
-		ring_ptr_move_fw(ring, next_to_clean);
+			/* As the head data may be changed when GRO enable, copy
+			 * the head data in after other data rx completed
+			 */
+			memcpy(skb->data, ring->va,
+			       ALIGN(ring->pull_len, sizeof(long)));
+		}
 	} else {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.seg_pkt_cnt++;
-		u64_stats_update_end(&ring->syncp);
-
-		pull_len = eth_get_headlen(va, HNS3_RX_HEAD_SIZE);
-
-		memcpy(__skb_put(skb, pull_len), va,
-		       ALIGN(pull_len, sizeof(long)));
-
-		hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb);
-		ring_ptr_move_fw(ring, next_to_clean);
+		ret = hns3_add_frag(ring, desc, &skb, true);
+		if (ret)
+			return ret;
 
-		while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
-			desc = &ring->desc[ring->next_to_clean];
-			desc_cb = &ring->desc_cb[ring->next_to_clean];
-			bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
-			hns3_nic_reuse_page(skb, bnum, ring, 0, desc_cb);
-			ring_ptr_move_fw(ring, next_to_clean);
-			bnum++;
-		}
+		/* As the head data may be changed when GRO enable, copy
+		 * the head data in after other data rx completed
+		 */
+		memcpy(skb->data, ring->va,
+		       ALIGN(ring->pull_len, sizeof(long)));
 	}
 
-	*out_bnum = bnum;
-
 	l234info = le32_to_cpu(desc->rx.l234_info);
+	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Based on hw strategy, the tag offloaded will be stored at
 	 * ot_vlan_tag in two layer tag case, and stored at vlan_tag
@@ -2449,7 +2652,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 					       vlan_tag);
 	}
 
-	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
+	if (unlikely(!(bd_base_info & BIT(HNS3_RXD_VLD_B)))) {
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.non_vld_descs++;
 		u64_stats_update_end(&ring->syncp);
@@ -2459,32 +2662,37 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	}
 
 	if (unlikely((!desc->rx.pkt_len) ||
-		     hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
+		     (l234info & (BIT(HNS3_RXD_TRUNCAT_B) |
+				  BIT(HNS3_RXD_L2E_B))))) {
 		u64_stats_update_begin(&ring->syncp);
-		ring->stats.err_pkt_len++;
+		if (l234info & BIT(HNS3_RXD_L2E_B))
+			ring->stats.l2_err++;
+		else
+			ring->stats.err_pkt_len++;
 		u64_stats_update_end(&ring->syncp);
 
 		dev_kfree_skb_any(skb);
 		return -EFAULT;
 	}
 
-	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) {
-		u64_stats_update_begin(&ring->syncp);
-		ring->stats.l2_err++;
-		u64_stats_update_end(&ring->syncp);
-
-		dev_kfree_skb_any(skb);
-		return -EFAULT;
-	}
 
+	l2_frame_type = hnae3_get_field(l234info, HNS3_RXD_DMAC_M,
+					HNS3_RXD_DMAC_S);
 	u64_stats_update_begin(&ring->syncp);
+	if (l2_frame_type == HNS3_L2_TYPE_MULTICAST)
+		ring->stats.rx_multicast++;
+
 	ring->stats.rx_pkts++;
 	ring->stats.rx_bytes += skb->len;
 	u64_stats_update_end(&ring->syncp);
 
 	ring->tqp_vector->rx_group.total_bytes += skb->len;
 
+	/* This is needed in order to enable forwarding support */
+	hns3_set_gro_param(skb, l234info, bd_base_info);
+
 	hns3_rx_checksum(ring, skb, desc);
+	*out_skb = skb;
 	hns3_set_rx_skb_rss_type(ring, skb);
 
 	return 0;
@@ -2497,9 +2705,9 @@ int hns3_clean_rx_ring(
 #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16
 	struct net_device *netdev = ring->tqp->handle->kinfo.netdev;
 	int recv_pkts, recv_bds, clean_count, err;
-	int unused_count = hns3_desc_unused(ring);
-	struct sk_buff *skb = NULL;
-	int num, bnum = 0;
+	int unused_count = hns3_desc_unused(ring) - ring->pending_buf;
+	struct sk_buff *skb = ring->skb;
+	int num;
 
 	num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG);
 	rmb(); /* Make sure num taken effect before the other data is touched */
@@ -2513,24 +2721,32 @@ int hns3_clean_rx_ring(
 			hns3_nic_alloc_rx_buffers(ring,
 						  clean_count + unused_count);
 			clean_count = 0;
-			unused_count = hns3_desc_unused(ring);
+			unused_count = hns3_desc_unused(ring) -
+					ring->pending_buf;
 		}
 
 		/* Poll one pkt */
-		err = hns3_handle_rx_bd(ring, &skb, &bnum);
+		err = hns3_handle_rx_bd(ring, &skb);
 		if (unlikely(!skb)) /* This fault cannot be repaired */
 			goto out;
 
-		recv_bds += bnum;
-		clean_count += bnum;
-		if (unlikely(err)) {  /* Do jump the err */
-			recv_pkts++;
+		if (err == -ENXIO) { /* Do not get FE for the packet */
+			goto out;
+		} else if (unlikely(err)) {  /* Do jump the err */
+			recv_bds += ring->pending_buf;
+			clean_count += ring->pending_buf;
+			ring->skb = NULL;
+			ring->pending_buf = 0;
 			continue;
 		}
 
 		/* Do update ip stack process */
 		skb->protocol = eth_type_trans(skb, netdev);
 		rx_fn(ring, skb);
+		recv_bds += ring->pending_buf;
+		clean_count += ring->pending_buf;
+		ring->skb = NULL;
+		ring->pending_buf = 0;
 
 		recv_pkts++;
 	}
@@ -2554,7 +2770,7 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group)
 	u32 time_passed_ms;
 	u16 new_int_gl;
 
-	if (!ring_group->coal.int_gl || !tqp_vector->last_jiffies)
+	if (!tqp_vector->last_jiffies)
 		return false;
 
 	if (ring_group->total_packets == 0) {
@@ -2644,10 +2860,10 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
 	struct hns3_enet_ring_group *tx_group = &tqp_vector->tx_group;
 	bool rx_update, tx_update;
 
-	if (tqp_vector->int_adapt_down > 0) {
-		tqp_vector->int_adapt_down--;
+	/* update param every 1000ms */
+	if (time_before(jiffies,
+			tqp_vector->last_jiffies + msecs_to_jiffies(1000)))
 		return;
-	}
 
 	if (rx_group->coal.gl_adapt_enable) {
 		rx_update = hns3_get_new_int_gl(rx_group);
@@ -2657,18 +2873,18 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector)
 	}
 
 	if (tx_group->coal.gl_adapt_enable) {
-		tx_update = hns3_get_new_int_gl(&tqp_vector->tx_group);
+		tx_update = hns3_get_new_int_gl(tx_group);
 		if (tx_update)
 			hns3_set_vector_coalesce_tx_gl(tqp_vector,
 						       tx_group->coal.int_gl);
 	}
 
 	tqp_vector->last_jiffies = jiffies;
-	tqp_vector->int_adapt_down = HNS3_INT_ADAPT_DOWN_START;
 }
 
 static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 {
+	struct hns3_nic_priv *priv = netdev_priv(napi->dev);
 	struct hns3_enet_ring *ring;
 	int rx_pkt_total = 0;
 
@@ -2677,6 +2893,11 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	bool clean_complete = true;
 	int rx_budget;
 
+	if (unlikely(test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
+		napi_complete(napi);
+		return 0;
+	}
+
 	/* Since the actual Tx work is minimal, we can give the Tx a larger
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
@@ -2701,9 +2922,11 @@ static int hns3_nic_common_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	napi_complete(napi);
-	hns3_update_new_int_gl(tqp_vector);
-	hns3_mask_vector_irq(tqp_vector, 1);
+	if (napi_complete(napi) &&
+	    likely(!test_bit(HNS3_NIC_STATE_DOWN, &priv->state))) {
+		hns3_update_new_int_gl(tqp_vector);
+		hns3_mask_vector_irq(tqp_vector, 1);
+	}
 
 	return rx_pkt_total;
 }
@@ -2783,9 +3006,10 @@ err_free_chain:
 	cur_chain = head->next;
 	while (cur_chain) {
 		chain = cur_chain->next;
-		devm_kfree(&pdev->dev, chain);
+		devm_kfree(&pdev->dev, cur_chain);
 		cur_chain = chain;
 	}
+	head->next = NULL;
 
 	return -ENOMEM;
 }
@@ -2876,7 +3100,7 @@ static int hns3_nic_init_vector_data(struct hns3_nic_priv *priv)
 		ret = hns3_get_vector_ring_chain(tqp_vector,
 						 &vector_ring_chain);
 		if (ret)
-			return ret;
+			goto map_ring_fail;
 
 		ret = h->ae_algo->ops->map_ring_to_vector(h,
 			tqp_vector->vector_irq, &vector_ring_chain);
@@ -2901,6 +3125,8 @@ map_ring_fail:
 
 static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
 {
+#define HNS3_VECTOR_PF_MAX_NUM		64
+
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hns3_enet_tqp_vector *tqp_vector;
 	struct hnae3_vector_info *vector;
@@ -2913,6 +3139,8 @@ static int hns3_nic_alloc_vector_data(struct hns3_nic_priv *priv)
 	/* RSS size, cpu online and vector_num should be the same */
 	/* Should consider 2p/4p later */
 	vector_num = min_t(u16, num_online_cpus(), tqp_num);
+	vector_num = min_t(u16, vector_num, HNS3_VECTOR_PF_MAX_NUM);
+
 	vector = devm_kcalloc(&pdev->dev, vector_num, sizeof(*vector),
 			      GFP_KERNEL);
 	if (!vector)
@@ -2948,43 +3176,38 @@ static void hns3_clear_ring_group(struct hns3_enet_ring_group *group)
 	group->count = 0;
 }
 
-static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
+static void hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 {
 	struct hnae3_ring_chain_node vector_ring_chain;
 	struct hnae3_handle *h = priv->ae_handle;
 	struct hns3_enet_tqp_vector *tqp_vector;
-	int i, ret;
+	int i;
 
 	for (i = 0; i < priv->vector_num; i++) {
 		tqp_vector = &priv->tqp_vector[i];
 
-		ret = hns3_get_vector_ring_chain(tqp_vector,
-						 &vector_ring_chain);
-		if (ret)
-			return ret;
+		if (!tqp_vector->rx_group.ring && !tqp_vector->tx_group.ring)
+			continue;
+
+		hns3_get_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
-		ret = h->ae_algo->ops->unmap_ring_from_vector(h,
+		h->ae_algo->ops->unmap_ring_from_vector(h,
 			tqp_vector->vector_irq, &vector_ring_chain);
-		if (ret)
-			return ret;
 
 		hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
-		if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) {
-			(void)irq_set_affinity_hint(
-				priv->tqp_vector[i].vector_irq,
-						    NULL);
-			free_irq(priv->tqp_vector[i].vector_irq,
-				 &priv->tqp_vector[i]);
+		if (tqp_vector->irq_init_flag == HNS3_VECTOR_INITED) {
+			irq_set_affinity_notifier(tqp_vector->vector_irq,
+						  NULL);
+			irq_set_affinity_hint(tqp_vector->vector_irq, NULL);
+			free_irq(tqp_vector->vector_irq, tqp_vector);
+			tqp_vector->irq_init_flag = HNS3_VECTOR_NOT_INITED;
 		}
 
-		priv->ring_data[i].ring->irq_init_flag = HNS3_VECTOR_NOT_INITED;
 		hns3_clear_ring_group(&tqp_vector->rx_group);
 		hns3_clear_ring_group(&tqp_vector->tx_group);
 		netif_napi_del(&priv->tqp_vector[i].napi);
 	}
-
-	return 0;
 }
 
 static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
@@ -3013,16 +3236,19 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 	int queue_num = priv->ae_handle->kinfo.num_tqps;
 	struct pci_dev *pdev = priv->ae_handle->pdev;
 	struct hns3_enet_ring *ring;
+	int desc_num;
 
 	ring = devm_kzalloc(&pdev->dev, sizeof(*ring), GFP_KERNEL);
 	if (!ring)
 		return -ENOMEM;
 
 	if (ring_type == HNAE3_RING_TYPE_TX) {
+		desc_num = priv->ae_handle->kinfo.num_tx_desc;
 		ring_data[q->tqp_index].ring = ring;
 		ring_data[q->tqp_index].queue_index = q->tqp_index;
 		ring->io_base = (u8 __iomem *)q->io_base + HNS3_TX_REG_OFFSET;
 	} else {
+		desc_num = priv->ae_handle->kinfo.num_rx_desc;
 		ring_data[q->tqp_index + queue_num].ring = ring;
 		ring_data[q->tqp_index + queue_num].queue_index = q->tqp_index;
 		ring->io_base = q->io_base;
@@ -3036,7 +3262,7 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 	ring->dev = priv->dev;
 	ring->desc_dma_addr = 0;
 	ring->buf_size = q->buf_size;
-	ring->desc_num = q->desc_num;
+	ring->desc_num = desc_num;
 	ring->next_to_use = 0;
 	ring->next_to_clean = 0;
 
@@ -3148,6 +3374,11 @@ static void hns3_fini_ring(struct hns3_enet_ring *ring)
 	ring->desc_cb = NULL;
 	ring->next_to_clean = 0;
 	ring->next_to_use = 0;
+	ring->pending_buf = 0;
+	if (ring->skb) {
+		dev_kfree_skb_any(ring->skb);
+		ring->skb = NULL;
+	}
 }
 
 static int hns3_buf_size2type(u32 buf_size)
@@ -3288,6 +3519,25 @@ static int hns3_init_mac_addr(struct net_device *netdev, bool init)
 	return ret;
 }
 
+static int hns3_init_phy(struct net_device *netdev)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	int ret = 0;
+
+	if (h->ae_algo->ops->mac_connect_phy)
+		ret = h->ae_algo->ops->mac_connect_phy(h);
+
+	return ret;
+}
+
+static void hns3_uninit_phy(struct net_device *netdev)
+{
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+
+	if (h->ae_algo->ops->mac_disconnect_phy)
+		h->ae_algo->ops->mac_disconnect_phy(h);
+}
+
 static int hns3_restore_fd_rules(struct net_device *netdev)
 {
 	struct hnae3_handle *h = hns3_get_handle(netdev);
@@ -3311,7 +3561,6 @@ static void hns3_nic_set_priv_ops(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 
-	priv->ops.fill_desc = hns3_fill_desc;
 	if ((netdev->features & NETIF_F_TSO) ||
 	    (netdev->features & NETIF_F_TSO6))
 		priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tso;
@@ -3319,6 +3568,22 @@ static void hns3_nic_set_priv_ops(struct net_device *netdev)
 		priv->ops.maybe_stop_tx = hns3_nic_maybe_stop_tx;
 }
 
+static int hns3_client_start(struct hnae3_handle *handle)
+{
+	if (!handle->ae_algo->ops->client_start)
+		return 0;
+
+	return handle->ae_algo->ops->client_start(handle);
+}
+
+static void hns3_client_stop(struct hnae3_handle *handle)
+{
+	if (!handle->ae_algo->ops->client_stop)
+		return;
+
+	handle->ae_algo->ops->client_stop(handle);
+}
+
 static int hns3_client_init(struct hnae3_handle *handle)
 {
 	struct pci_dev *pdev = handle->pdev;
@@ -3337,8 +3602,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->dev = &pdev->dev;
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
-	priv->ae_handle->last_reset_time = jiffies;
 	priv->tx_timeout_count = 0;
+	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->kinfo.netdev = netdev;
 	handle->priv = (void *)priv;
@@ -3357,11 +3622,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
-	if (handle->flags & HNAE3_SUPPORT_VF)
-		handle->reset_level = HNAE3_VF_RESET;
-	else
-		handle->reset_level = HNAE3_FUNC_RESET;
-
 	ret = hns3_get_ring_config(priv);
 	if (ret) {
 		ret = -ENOMEM;
@@ -3386,22 +3646,41 @@ static int hns3_client_init(struct hnae3_handle *handle)
 		goto out_init_ring_data;
 	}
 
+	ret = hns3_init_phy(netdev);
+	if (ret)
+		goto out_init_phy;
+
 	ret = register_netdev(netdev);
 	if (ret) {
 		dev_err(priv->dev, "probe register netdev fail!\n");
 		goto out_reg_netdev_fail;
 	}
 
+	ret = hns3_client_start(handle);
+	if (ret) {
+		dev_err(priv->dev, "hns3_client_start fail! ret=%d\n", ret);
+			goto out_client_start;
+	}
+
 	hns3_dcbnl_setup(handle);
 
-	/* MTU range: (ETH_MIN_MTU(kernel default) - 9706) */
-	netdev->max_mtu = HNS3_MAX_MTU - (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN);
+	hns3_dbg_init(handle);
+
+	/* MTU range: (ETH_MIN_MTU(kernel default) - 9702) */
+	netdev->max_mtu = HNS3_MAX_MTU;
+
+	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
 	return ret;
 
+out_client_start:
+	unregister_netdev(netdev);
 out_reg_netdev_fail:
+	hns3_uninit_phy(netdev);
+out_init_phy:
+	hns3_uninit_all_ring(priv);
 out_init_ring_data:
-	(void)hns3_nic_uninit_vector_data(priv);
+	hns3_nic_uninit_vector_data(priv);
 out_init_vector_data:
 	hns3_nic_dealloc_vector_data(priv);
 out_alloc_vector_data:
@@ -3418,18 +3697,25 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
+	hns3_client_stop(handle);
+
 	hns3_remove_hw_addr(netdev);
 
 	if (netdev->reg_state != NETREG_UNINITIALIZED)
 		unregister_netdev(netdev);
 
+	if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+		netdev_warn(netdev, "already uninitialized\n");
+		goto out_netdev_free;
+	}
+
 	hns3_del_all_fd_rules(netdev, true);
 
 	hns3_force_clear_all_rx_ring(handle);
 
-	ret = hns3_nic_uninit_vector_data(priv);
-	if (ret)
-		netdev_err(netdev, "uninit vector error\n");
+	hns3_uninit_phy(netdev);
+
+	hns3_nic_uninit_vector_data(priv);
 
 	ret = hns3_nic_dealloc_vector_data(priv);
 	if (ret)
@@ -3441,8 +3727,11 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset)
 
 	hns3_put_ring_config(priv);
 
+	hns3_dbg_uninit(handle);
+
 	priv->ring_data = NULL;
 
+out_netdev_free:
 	free_netdev(netdev);
 }
 
@@ -3468,8 +3757,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct net_device *ndev = kinfo->netdev;
-	bool if_running;
-	int ret;
 
 	if (tc > HNAE3_MAX_TC)
 		return -EINVAL;
@@ -3477,25 +3764,7 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	if (!ndev)
 		return -ENODEV;
 
-	if_running = netif_running(ndev);
-
-	if (if_running) {
-		(void)hns3_nic_net_stop(ndev);
-		msleep(100);
-	}
-
-	ret = (kinfo->dcb_ops && kinfo->dcb_ops->map_update) ?
-		kinfo->dcb_ops->map_update(handle) : -EOPNOTSUPP;
-	if (ret)
-		goto err_out;
-
-	ret = hns3_nic_set_real_num_queue(ndev);
-
-err_out:
-	if (if_running)
-		(void)hns3_nic_net_open(ndev);
-
-	return ret;
+	return hns3_nic_set_real_num_queue(ndev);
 }
 
 static int hns3_recover_hw_addr(struct net_device *ndev)
@@ -3708,8 +3977,22 @@ static void hns3_restore_coal(struct hns3_nic_priv *priv)
 
 static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct net_device *ndev = kinfo->netdev;
+	struct hns3_nic_priv *priv = netdev_priv(ndev);
+
+	if (test_and_set_bit(HNS3_NIC_STATE_RESETTING, &priv->state))
+		return 0;
+
+	/* it is cumbersome for hardware to pick-and-choose entries for deletion
+	 * from table space. Hence, for function reset software intervention is
+	 * required to delete the entries
+	 */
+	if (hns3_dev_ongoing_func_reset(ae_dev)) {
+		hns3_remove_hw_addr(ndev);
+		hns3_del_all_fd_rules(ndev, false);
+	}
 
 	if (!netif_running(ndev))
 		return 0;
@@ -3720,16 +4003,19 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 static int hns3_reset_notify_up_enet(struct hnae3_handle *handle)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
+	struct hns3_nic_priv *priv = netdev_priv(kinfo->netdev);
 	int ret = 0;
 
+	clear_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
+
 	if (netif_running(kinfo->netdev)) {
-		ret = hns3_nic_net_up(kinfo->netdev);
+		ret = hns3_nic_net_open(kinfo->netdev);
 		if (ret) {
+			set_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
 			netdev_err(kinfo->netdev,
 				   "hns net up fail, ret=%d!\n", ret);
 			return ret;
 		}
-		handle->last_reset_time = jiffies;
 	}
 
 	return ret;
@@ -3739,6 +4025,48 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 {
 	struct net_device *netdev = handle->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
+	int ret;
+
+	/* Carrier off reporting is important to ethtool even BEFORE open */
+	netif_carrier_off(netdev);
+
+	ret = hns3_get_ring_config(priv);
+	if (ret)
+		return ret;
+
+	ret = hns3_nic_alloc_vector_data(priv);
+	if (ret)
+		goto err_put_ring;
+
+	hns3_restore_coal(priv);
+
+	ret = hns3_nic_init_vector_data(priv);
+	if (ret)
+		goto err_dealloc_vector;
+
+	ret = hns3_init_all_ring(priv);
+	if (ret)
+		goto err_uninit_vector;
+
+	set_bit(HNS3_NIC_STATE_INITED, &priv->state);
+
+	return ret;
+
+err_uninit_vector:
+	hns3_nic_uninit_vector_data(priv);
+	priv->ring_data = NULL;
+err_dealloc_vector:
+	hns3_nic_dealloc_vector_data(priv);
+err_put_ring:
+	hns3_put_ring_config(priv);
+	priv->ring_data = NULL;
+
+	return ret;
+}
+
+static int hns3_reset_notify_restore_enet(struct hnae3_handle *handle)
+{
+	struct net_device *netdev = handle->kinfo.netdev;
 	bool vlan_filter_enable;
 	int ret;
 
@@ -3764,57 +4092,38 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 			return ret;
 	}
 
-	ret = hns3_restore_fd_rules(netdev);
-	if (ret)
-		return ret;
-
-	/* Carrier off reporting is important to ethtool even BEFORE open */
-	netif_carrier_off(netdev);
-
-	hns3_restore_coal(priv);
-
-	ret = hns3_nic_init_vector_data(priv);
-	if (ret)
-		return ret;
-
-	ret = hns3_init_all_ring(priv);
-	if (ret) {
-		hns3_nic_uninit_vector_data(priv);
-		priv->ring_data = NULL;
-	}
-
-	return ret;
+	return hns3_restore_fd_rules(netdev);
 }
 
 static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 {
-	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(handle->pdev);
 	struct net_device *netdev = handle->kinfo.netdev;
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	int ret;
 
+	if (!test_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+		netdev_warn(netdev, "already uninitialized\n");
+		return 0;
+	}
+
 	hns3_force_clear_all_rx_ring(handle);
 
-	ret = hns3_nic_uninit_vector_data(priv);
-	if (ret) {
-		netdev_err(netdev, "uninit vector error\n");
-		return ret;
-	}
+	hns3_nic_uninit_vector_data(priv);
 
 	hns3_store_coal(priv);
 
+	ret = hns3_nic_dealloc_vector_data(priv);
+	if (ret)
+		netdev_err(netdev, "dealloc vector error\n");
+
 	ret = hns3_uninit_all_ring(priv);
 	if (ret)
 		netdev_err(netdev, "uninit ring error\n");
 
-	/* it is cumbersome for hardware to pick-and-choose entries for deletion
-	 * from table space. Hence, for function reset software intervention is
-	 * required to delete the entries
-	 */
-	if (hns3_dev_ongoing_func_reset(ae_dev)) {
-		hns3_remove_hw_addr(netdev);
-		hns3_del_all_fd_rules(netdev, false);
-	}
+	hns3_put_ring_config(priv);
+	priv->ring_data = NULL;
+
+	clear_bit(HNS3_NIC_STATE_INITED, &priv->state);
 
 	return ret;
 }
@@ -3837,6 +4146,9 @@ static int hns3_reset_notify(struct hnae3_handle *handle,
 	case HNAE3_UNINIT_CLIENT:
 		ret = hns3_reset_notify_uninit_enet(handle);
 		break;
+	case HNAE3_RESTORE_CLIENT:
+		ret = hns3_reset_notify_restore_enet(handle);
+		break;
 	default:
 		break;
 	}
@@ -3844,57 +4156,12 @@ static int hns3_reset_notify(struct hnae3_handle *handle,
 	return ret;
 }
 
-static int hns3_modify_tqp_num(struct net_device *netdev, u16 new_tqp_num)
-{
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	struct hnae3_handle *h = hns3_get_handle(netdev);
-	int ret;
-
-	ret = h->ae_algo->ops->set_channels(h, new_tqp_num);
-	if (ret)
-		return ret;
-
-	ret = hns3_get_ring_config(priv);
-	if (ret)
-		return ret;
-
-	ret = hns3_nic_alloc_vector_data(priv);
-	if (ret)
-		goto err_alloc_vector;
-
-	hns3_restore_coal(priv);
-
-	ret = hns3_nic_init_vector_data(priv);
-	if (ret)
-		goto err_uninit_vector;
-
-	ret = hns3_init_all_ring(priv);
-	if (ret)
-		goto err_put_ring;
-
-	return 0;
-
-err_put_ring:
-	hns3_put_ring_config(priv);
-err_uninit_vector:
-	hns3_nic_uninit_vector_data(priv);
-err_alloc_vector:
-	hns3_nic_dealloc_vector_data(priv);
-	return ret;
-}
-
-static int hns3_adjust_tqps_num(u8 num_tc, u32 new_tqp_num)
-{
-	return (new_tqp_num / num_tc) * num_tc;
-}
-
 int hns3_set_channels(struct net_device *netdev,
 		      struct ethtool_channels *ch)
 {
-	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
-	bool if_running = netif_running(netdev);
+	bool rxfh_configured = netif_is_rxfh_configured(netdev);
 	u32 new_tqp_num = ch->combined_count;
 	u16 org_tqp_num;
 	int ret;
@@ -3903,39 +4170,29 @@ int hns3_set_channels(struct net_device *netdev,
 		return -EINVAL;
 
 	if (new_tqp_num > hns3_get_max_available_channels(h) ||
-	    new_tqp_num < kinfo->num_tc) {
+	    new_tqp_num < 1) {
 		dev_err(&netdev->dev,
-			"Change tqps fail, the tqp range is from %d to %d",
-			kinfo->num_tc,
+			"Change tqps fail, the tqp range is from 1 to %d",
 			hns3_get_max_available_channels(h));
 		return -EINVAL;
 	}
 
-	new_tqp_num = hns3_adjust_tqps_num(kinfo->num_tc, new_tqp_num);
-	if (kinfo->num_tqps == new_tqp_num)
+	if (kinfo->rss_size == new_tqp_num)
 		return 0;
 
-	if (if_running)
-		hns3_nic_net_stop(netdev);
-
-	ret = hns3_nic_uninit_vector_data(priv);
-	if (ret) {
-		dev_err(&netdev->dev,
-			"Unbind vector with tqp fail, nothing is changed");
-		goto open_netdev;
-	}
-
-	hns3_store_coal(priv);
-
-	hns3_nic_dealloc_vector_data(priv);
+	ret = hns3_reset_notify(h, HNAE3_DOWN_CLIENT);
+	if (ret)
+		return ret;
 
-	hns3_uninit_all_ring(priv);
-	hns3_put_ring_config(priv);
+	ret = hns3_reset_notify(h, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
 
 	org_tqp_num = h->kinfo.num_tqps;
-	ret = hns3_modify_tqp_num(netdev, new_tqp_num);
+	ret = h->ae_algo->ops->set_channels(h, new_tqp_num, rxfh_configured);
 	if (ret) {
-		ret = hns3_modify_tqp_num(netdev, org_tqp_num);
+		ret = h->ae_algo->ops->set_channels(h, org_tqp_num,
+						    rxfh_configured);
 		if (ret) {
 			/* If revert to old tqp failed, fatal error occurred */
 			dev_err(&netdev->dev,
@@ -3945,12 +4202,11 @@ int hns3_set_channels(struct net_device *netdev,
 		dev_info(&netdev->dev,
 			 "Change tqp num fail, Revert to old tqp num");
 	}
+	ret = hns3_reset_notify(h, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
 
-open_netdev:
-	if (if_running)
-		hns3_nic_net_open(netdev);
-
-	return ret;
+	return hns3_reset_notify(h, HNAE3_UP_CLIENT);
 }
 
 static const struct hnae3_client_ops client_ops = {
@@ -3980,15 +4236,23 @@ static int __init hns3_init_module(void)
 
 	INIT_LIST_HEAD(&client.node);
 
+	hns3_dbg_register_debugfs(hns3_driver_name);
+
 	ret = hnae3_register_client(&client);
 	if (ret)
-		return ret;
+		goto err_reg_client;
 
 	ret = pci_register_driver(&hns3_driver);
 	if (ret)
-		hnae3_unregister_client(&client);
+		goto err_reg_driver;
 
 	return ret;
+
+err_reg_driver:
+	hnae3_unregister_client(&client);
+err_reg_client:
+	hns3_dbg_unregister_debugfs();
+	return ret;
 }
 module_init(hns3_init_module);
 
@@ -4000,6 +4264,7 @@ static void __exit hns3_exit_module(void)
 {
 	pci_unregister_driver(&hns3_driver);
 	hnae3_unregister_client(&client);
+	hns3_dbg_unregister_debugfs();
 }
 module_exit(hns3_exit_module);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index d3636d088aa3..75669cd0c311 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -15,7 +15,7 @@ extern const char hns3_driver_version[];
 enum hns3_nic_state {
 	HNS3_NIC_STATE_TESTING,
 	HNS3_NIC_STATE_RESETTING,
-	HNS3_NIC_STATE_REINITING,
+	HNS3_NIC_STATE_INITED,
 	HNS3_NIC_STATE_DOWN,
 	HNS3_NIC_STATE_DISABLED,
 	HNS3_NIC_STATE_REMOVING,
@@ -47,7 +47,7 @@ enum hns3_nic_state {
 #define HNS3_RING_PREFETCH_EN_REG		0x0007C
 #define HNS3_RING_CFG_VF_NUM_REG		0x00080
 #define HNS3_RING_ASID_REG			0x0008C
-#define HNS3_RING_RX_VM_REG			0x00090
+#define HNS3_RING_EN_REG			0x00090
 #define HNS3_RING_T0_BE_RST			0x00094
 #define HNS3_RING_COULD_BE_RST			0x00098
 #define HNS3_RING_WRR_WEIGHT_REG		0x0009c
@@ -74,9 +74,12 @@ enum hns3_nic_state {
 #define HNS3_RING_NAME_LEN			16
 #define HNS3_BUFFER_SIZE_2048			2048
 #define HNS3_RING_MAX_PENDING			32768
-#define HNS3_RING_MIN_PENDING			8
+#define HNS3_RING_MIN_PENDING			24
 #define HNS3_RING_BD_MULTIPLE			8
-#define HNS3_MAX_MTU				9728
+/* max frame size of mac */
+#define HNS3_MAC_MAX_FRAME			9728
+#define HNS3_MAX_MTU \
+	(HNS3_MAC_MAX_FRAME - (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN))
 
 #define HNS3_BD_SIZE_512_TYPE			0
 #define HNS3_BD_SIZE_1024_TYPE			1
@@ -109,6 +112,10 @@ enum hns3_nic_state {
 #define HNS3_RXD_DOI_B				21
 #define HNS3_RXD_OL3E_B				22
 #define HNS3_RXD_OL4E_B				23
+#define HNS3_RXD_GRO_COUNT_S			24
+#define HNS3_RXD_GRO_COUNT_M			(0x3f << HNS3_RXD_GRO_COUNT_S)
+#define HNS3_RXD_GRO_FIXID_B			30
+#define HNS3_RXD_GRO_ECN_B			31
 
 #define HNS3_RXD_ODMAC_S			0
 #define HNS3_RXD_ODMAC_M			(0x3 << HNS3_RXD_ODMAC_S)
@@ -135,9 +142,8 @@ enum hns3_nic_state {
 #define HNS3_RXD_TSIND_S			12
 #define HNS3_RXD_TSIND_M			(0x7 << HNS3_RXD_TSIND_S)
 #define HNS3_RXD_LKBK_B				15
-#define HNS3_RXD_HDL_S				16
-#define HNS3_RXD_HDL_M				(0x7ff << HNS3_RXD_HDL_S)
-#define HNS3_RXD_HSIND_B			31
+#define HNS3_RXD_GRO_SIZE_S			16
+#define HNS3_RXD_GRO_SIZE_M			(0x3ff << HNS3_RXD_GRO_SIZE_S)
 
 #define HNS3_TXD_L3T_S				0
 #define HNS3_TXD_L3T_M				(0x3 << HNS3_TXD_L3T_S)
@@ -178,6 +184,8 @@ enum hns3_nic_state {
 #define HNS3_TXD_MSS_S				0
 #define HNS3_TXD_MSS_M				(0x3fff << HNS3_TXD_MSS_S)
 
+#define HNS3_TX_LAST_SIZE_M                    0xffff
+
 #define HNS3_VECTOR_TX_IRQ			BIT_ULL(0)
 #define HNS3_VECTOR_RX_IRQ			BIT_ULL(1)
 
@@ -194,6 +202,15 @@ enum hns3_nic_state {
 #define HNS3_VECTOR_RL_OFFSET			0x900
 #define HNS3_VECTOR_RL_EN_B			6
 
+#define HNS3_RING_EN_B				0
+
+enum hns3_pkt_l2t_type {
+	HNS3_L2_TYPE_UNICAST,
+	HNS3_L2_TYPE_MULTICAST,
+	HNS3_L2_TYPE_BROADCAST,
+	HNS3_L2_TYPE_INVALID,
+};
+
 enum hns3_pkt_l3t_type {
 	HNS3_L3T_NONE,
 	HNS3_L3T_IPV6,
@@ -368,6 +385,7 @@ struct ring_stats {
 			u64 err_bd_num;
 			u64 l2_err;
 			u64 l3l4_csum_err;
+			u64 rx_multicast;
 		};
 	};
 };
@@ -399,11 +417,18 @@ struct hns3_enet_ring {
 	 */
 	int next_to_clean;
 
+	int pull_len; /* head length for current packet */
+	u32 frag_num;
+	unsigned char *va; /* first buffer address for current packet */
+
 	u32 flag;          /* ring attribute */
-	int irq_init_flag;
 
 	int numa_node;
 	cpumask_t affinity_mask;
+
+	int pending_buf;
+	struct sk_buff *skb;
+	struct sk_buff *tail_skb;
 };
 
 struct hns_queue;
@@ -418,11 +443,8 @@ struct hns3_nic_ring_data {
 };
 
 struct hns3_nic_ops {
-	int (*fill_desc)(struct hns3_enet_ring *ring, void *priv,
-			 int size, int frag_end, enum hns_desc_type type);
 	int (*maybe_stop_tx)(struct sk_buff **out_skb,
 			     int *bnum, struct hns3_enet_ring *ring);
-	void (*get_rxd_bnum)(u32 bnum_flag, int *out_bnum);
 };
 
 enum hns3_flow_level_range {
@@ -460,8 +482,6 @@ enum hns3_link_mode_bits {
 #define HNS3_INT_RL_MAX			0x00EC
 #define HNS3_INT_RL_ENABLE_MASK		0x40
 
-#define HNS3_INT_ADAPT_DOWN_START	100
-
 struct hns3_enet_coalesce {
 	u16 int_gl;
 	u8 gl_adapt_enable;
@@ -496,8 +516,6 @@ struct hns3_enet_tqp_vector {
 
 	char name[HNAE3_INT_NAME_LEN];
 
-	/* when 0 should adjust interrupt coalesce parameter */
-	u8 int_adapt_down;
 	unsigned long last_jiffies;
 } ____cacheline_internodealigned_in_smp;
 
@@ -555,6 +573,7 @@ union l3_hdr_info {
 union l4_hdr_info {
 	struct tcphdr *tcp;
 	struct udphdr *udp;
+	struct gre_base_hdr *gre;
 	unsigned char *hdr;
 };
 
@@ -577,6 +596,11 @@ static inline int is_ring_empty(struct hns3_enet_ring *ring)
 	return ring->next_to_use == ring->next_to_clean;
 }
 
+static inline u32 hns3_read_reg(void __iomem *base, u32 reg)
+{
+	return readl(base + reg);
+}
+
 static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 {
 	u8 __iomem *reg_addr = READ_ONCE(base);
@@ -586,7 +610,21 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 
 static inline bool hns3_dev_ongoing_func_reset(struct hnae3_ae_dev *ae_dev)
 {
-	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET));
+	return (ae_dev && (ae_dev->reset_type == HNAE3_FUNC_RESET ||
+			   ae_dev->reset_type == HNAE3_FLR_RESET ||
+			   ae_dev->reset_type == HNAE3_VF_FUNC_RESET ||
+			   ae_dev->reset_type == HNAE3_VF_FULL_RESET ||
+			   ae_dev->reset_type == HNAE3_VF_PF_FUNC_RESET));
+}
+
+#define hns3_read_dev(a, reg) \
+	hns3_read_reg((a)->io_base, (reg))
+
+static inline bool hns3_nic_resetting(struct net_device *netdev)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	return test_bit(HNS3_NIC_STATE_RESETTING, &priv->state);
 }
 
 #define hns3_write_dev(a, reg, value) \
@@ -648,4 +686,8 @@ void hns3_dcbnl_setup(struct hnae3_handle *handle);
 static inline void hns3_dcbnl_setup(struct hnae3_handle *handle) {}
 #endif
 
+void hns3_dbg_init(struct hnae3_handle *handle);
+void hns3_dbg_uninit(struct hnae3_handle *handle);
+void hns3_dbg_register_debugfs(const char *debugfs_dir_name);
+void hns3_dbg_unregister_debugfs(void);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index a4762c2b8ba1..359d4731fb2d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -47,6 +47,7 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 	HNS3_TQP_STAT("err_bd_num", err_bd_num),
 	HNS3_TQP_STAT("l2_err", l2_err),
 	HNS3_TQP_STAT("l3l4_csum_err", l3l4_csum_err),
+	HNS3_TQP_STAT("multicast", rx_multicast),
 };
 
 #define HNS3_RXQ_STATS_COUNT ARRAY_SIZE(hns3_rxq_stats)
@@ -116,7 +117,7 @@ static int hns3_lp_up(struct net_device *ndev, enum hnae3_loop loop_mode)
 	ret = hns3_lp_setup(ndev, loop_mode, true);
 	usleep_range(10000, 20000);
 
-	return 0;
+	return ret;
 }
 
 static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode)
@@ -291,6 +292,11 @@ static void hns3_self_test(struct net_device *ndev,
 	int test_index = 0;
 	u32 i;
 
+	if (hns3_nic_resetting(ndev)) {
+		netdev_err(ndev, "dev resetting!");
+		return;
+	}
+
 	/* Only do offline selftest, or pass by default */
 	if (eth_test->flags != ETH_TEST_FL_OFFLINE)
 		return;
@@ -328,10 +334,10 @@ static void hns3_self_test(struct net_device *ndev,
 			continue;
 
 		data[test_index] = hns3_lp_up(ndev, loop_type);
-		if (!data[test_index]) {
+		if (!data[test_index])
 			data[test_index] = hns3_lp_run_test(ndev, loop_type);
-			hns3_lp_down(ndev, loop_type);
-		}
+
+		hns3_lp_down(ndev, loop_type);
 
 		if (data[test_index])
 			eth_test->flags |= ETH_TEST_FL_FAILED;
@@ -530,6 +536,11 @@ static void hns3_get_ringparam(struct net_device *netdev,
 	struct hnae3_handle *h = priv->ae_handle;
 	int queue_num = h->kinfo.num_tqps;
 
+	if (hns3_nic_resetting(netdev)) {
+		netdev_err(netdev, "dev resetting!");
+		return;
+	}
+
 	param->tx_max_pending = HNS3_RING_MAX_PENDING;
 	param->rx_max_pending = HNS3_RING_MAX_PENDING;
 
@@ -610,12 +621,11 @@ static int hns3_get_link_ksettings(struct net_device *netdev,
 		hns3_get_ksettings(h, cmd);
 		break;
 	case HNAE3_MEDIA_TYPE_COPPER:
-		if (!netdev->phydev)
-			return -EOPNOTSUPP;
-
 		cmd->base.port = PORT_TP;
-		phy_ethtool_ksettings_get(netdev->phydev, cmd);
-
+		if (!netdev->phydev)
+			hns3_get_ksettings(h, cmd);
+		else
+			phy_ethtool_ksettings_get(netdev->phydev, cmd);
 		break;
 	default:
 
@@ -738,15 +748,19 @@ static int hns3_get_rxnfc(struct net_device *netdev,
 }
 
 static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv,
-				       u32 new_desc_num)
+				       u32 tx_desc_num, u32 rx_desc_num)
 {
 	struct hnae3_handle *h = priv->ae_handle;
 	int i;
 
-	h->kinfo.num_desc = new_desc_num;
+	h->kinfo.num_tx_desc = tx_desc_num;
+	h->kinfo.num_rx_desc = rx_desc_num;
 
-	for (i = 0; i < h->kinfo.num_tqps * 2; i++)
-		priv->ring_data[i].ring->desc_num = new_desc_num;
+	for (i = 0; i < h->kinfo.num_tqps; i++) {
+		priv->ring_data[i].ring->desc_num = tx_desc_num;
+		priv->ring_data[i + h->kinfo.num_tqps].ring->desc_num =
+			rx_desc_num;
+	}
 
 	return hns3_init_all_ring(priv);
 }
@@ -757,49 +771,52 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
 	bool if_running = netif_running(ndev);
-	u32 old_desc_num, new_desc_num;
+	u32 old_tx_desc_num, new_tx_desc_num;
+	u32 old_rx_desc_num, new_rx_desc_num;
+	int queue_num = h->kinfo.num_tqps;
 	int ret;
 
-	if (param->rx_mini_pending || param->rx_jumbo_pending)
-		return -EINVAL;
+	if (hns3_nic_resetting(ndev))
+		return -EBUSY;
 
-	if (param->tx_pending != param->rx_pending) {
-		netdev_err(ndev,
-			   "Descriptors of tx and rx must be equal");
+	if (param->rx_mini_pending || param->rx_jumbo_pending)
 		return -EINVAL;
-	}
 
 	if (param->tx_pending > HNS3_RING_MAX_PENDING ||
-	    param->tx_pending < HNS3_RING_MIN_PENDING) {
-		netdev_err(ndev,
-			   "Descriptors requested (Tx/Rx: %d) out of range [%d-%d]\n",
-			   param->tx_pending, HNS3_RING_MIN_PENDING,
-			   HNS3_RING_MAX_PENDING);
+	    param->tx_pending < HNS3_RING_MIN_PENDING ||
+	    param->rx_pending > HNS3_RING_MAX_PENDING ||
+	    param->rx_pending < HNS3_RING_MIN_PENDING) {
+		netdev_err(ndev, "Queue depth out of range [%d-%d]\n",
+			   HNS3_RING_MIN_PENDING, HNS3_RING_MAX_PENDING);
 		return -EINVAL;
 	}
 
-	new_desc_num = param->tx_pending;
-
 	/* Hardware requires that its descriptors must be multiple of eight */
-	new_desc_num = ALIGN(new_desc_num, HNS3_RING_BD_MULTIPLE);
-	old_desc_num = h->kinfo.num_desc;
-	if (old_desc_num == new_desc_num)
+	new_tx_desc_num = ALIGN(param->tx_pending, HNS3_RING_BD_MULTIPLE);
+	new_rx_desc_num = ALIGN(param->rx_pending, HNS3_RING_BD_MULTIPLE);
+	old_tx_desc_num = priv->ring_data[0].ring->desc_num;
+	old_rx_desc_num = priv->ring_data[queue_num].ring->desc_num;
+	if (old_tx_desc_num == new_tx_desc_num &&
+	    old_rx_desc_num == new_rx_desc_num)
 		return 0;
 
 	netdev_info(ndev,
-		    "Changing descriptor count from %d to %d.\n",
-		    old_desc_num, new_desc_num);
+		    "Changing Tx/Rx ring depth from %d/%d to %d/%d\n",
+		    old_tx_desc_num, old_rx_desc_num,
+		    new_tx_desc_num, new_rx_desc_num);
 
 	if (if_running)
-		dev_close(ndev);
+		ndev->netdev_ops->ndo_stop(ndev);
 
 	ret = hns3_uninit_all_ring(priv);
 	if (ret)
 		return ret;
 
-	ret = hns3_change_all_ring_bd_num(priv, new_desc_num);
+	ret = hns3_change_all_ring_bd_num(priv, new_tx_desc_num,
+					  new_rx_desc_num);
 	if (ret) {
-		ret = hns3_change_all_ring_bd_num(priv, old_desc_num);
+		ret = hns3_change_all_ring_bd_num(priv, old_tx_desc_num,
+						  old_rx_desc_num);
 		if (ret) {
 			netdev_err(ndev,
 				   "Revert to old bd num fail, ret=%d.\n", ret);
@@ -808,7 +825,7 @@ static int hns3_set_ringparam(struct net_device *ndev,
 	}
 
 	if (if_running)
-		ret = dev_open(ndev);
+		ret = ndev->netdev_ops->ndo_open(ndev);
 
 	return ret;
 }
@@ -872,6 +889,9 @@ static int hns3_get_coalesce_per_queue(struct net_device *netdev, u32 queue,
 	struct hnae3_handle *h = priv->ae_handle;
 	u16 queue_num = h->kinfo.num_tqps;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	if (queue >= queue_num) {
 		netdev_err(netdev,
 			   "Invalid queue value %d! Queue max id=%d\n",
@@ -1033,6 +1053,9 @@ static int hns3_set_coalesce(struct net_device *netdev,
 	int ret;
 	int i;
 
+	if (hns3_nic_resetting(netdev))
+		return -EBUSY;
+
 	ret = hns3_check_coalesce_para(netdev, cmd);
 	if (ret)
 		return ret;
@@ -1095,6 +1118,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = {
 	.get_channels = hns3_get_channels,
 	.get_coalesce = hns3_get_coalesce,
 	.set_coalesce = hns3_set_coalesce,
+	.get_regs_len = hns3_get_regs_len,
+	.get_regs = hns3_get_regs,
 	.get_link = hns3_get_link,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
index 580e81743681..0fb61d440d3b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile
@@ -3,9 +3,9 @@
 # Makefile for the HISILICON network device drivers.
 #
 
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGE) += hclge.o
-hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o
+hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o  hclge_debugfs.o
 
 hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 690f62ed87dc..3a093a92eac5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -39,9 +39,8 @@ static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring)
 {
 	int size  = ring->desc_num * sizeof(struct hclge_desc);
 
-	ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
-					 size, &ring->desc_dma_addr,
-					 GFP_KERNEL);
+	ring->desc = dma_alloc_coherent(cmq_ring_to_dev(ring), size,
+					&ring->desc_dma_addr, GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
@@ -171,8 +170,12 @@ static bool hclge_is_special_opcode(u16 opcode)
 	/* these commands have several descriptors,
 	 * and use the first one to save opcode and return value
 	 */
-	u16 spec_opcode[3] = {HCLGE_OPC_STATS_64_BIT,
-		HCLGE_OPC_STATS_32_BIT, HCLGE_OPC_STATS_MAC};
+	u16 spec_opcode[] = {HCLGE_OPC_STATS_64_BIT,
+			     HCLGE_OPC_STATS_32_BIT,
+			     HCLGE_OPC_STATS_MAC,
+			     HCLGE_OPC_STATS_MAC_ALL,
+			     HCLGE_OPC_QUERY_32_BIT_REG,
+			     HCLGE_OPC_QUERY_64_BIT_REG};
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) {
@@ -183,6 +186,38 @@ static bool hclge_is_special_opcode(u16 opcode)
 	return false;
 }
 
+static int hclge_cmd_check_retval(struct hclge_hw *hw, struct hclge_desc *desc,
+				  int num, int ntc)
+{
+	u16 opcode, desc_ret;
+	int handle;
+	int retval;
+
+	opcode = le16_to_cpu(desc[0].opcode);
+	for (handle = 0; handle < num; handle++) {
+		desc[handle] = hw->cmq.csq.desc[ntc];
+		ntc++;
+		if (ntc >= hw->cmq.csq.desc_num)
+			ntc = 0;
+	}
+	if (likely(!hclge_is_special_opcode(opcode)))
+		desc_ret = le16_to_cpu(desc[num - 1].retval);
+	else
+		desc_ret = le16_to_cpu(desc[0].retval);
+
+	if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
+		retval = 0;
+	else if (desc_ret == HCLGE_CMD_NO_AUTH)
+		retval = -EPERM;
+	else if (desc_ret == HCLGE_CMD_NOT_SUPPORTED)
+		retval = -EOPNOTSUPP;
+	else
+		retval = -EIO;
+	hw->cmq.last_status = desc_ret;
+
+	return retval;
+}
+
 /**
  * hclge_cmd_send - send command to command queue
  * @hw: pointer to the hw struct
@@ -200,7 +235,6 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	u32 timeout = 0;
 	int handle = 0;
 	int retval = 0;
-	u16 opcode, desc_ret;
 	int ntc;
 
 	spin_lock_bh(&hw->cmq.csq.lock);
@@ -216,12 +250,11 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	 * which will be use for hardware to write back
 	 */
 	ntc = hw->cmq.csq.next_to_use;
-	opcode = le16_to_cpu(desc[0].opcode);
 	while (handle < num) {
 		desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use];
 		*desc_to_use = desc[handle];
 		(hw->cmq.csq.next_to_use)++;
-		if (hw->cmq.csq.next_to_use == hw->cmq.csq.desc_num)
+		if (hw->cmq.csq.next_to_use >= hw->cmq.csq.desc_num)
 			hw->cmq.csq.next_to_use = 0;
 		handle++;
 	}
@@ -247,27 +280,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	if (!complete) {
 		retval = -EAGAIN;
 	} else {
-		handle = 0;
-		while (handle < num) {
-			/* Get the result of hardware write back */
-			desc_to_use = &hw->cmq.csq.desc[ntc];
-			desc[handle] = *desc_to_use;
-
-			if (likely(!hclge_is_special_opcode(opcode)))
-				desc_ret = le16_to_cpu(desc[handle].retval);
-			else
-				desc_ret = le16_to_cpu(desc[0].retval);
-
-			if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
-				retval = 0;
-			else
-				retval = -EIO;
-			hw->cmq.last_status = desc_ret;
-			ntc++;
-			handle++;
-			if (ntc == hw->cmq.csq.desc_num)
-				ntc = 0;
-		}
+		retval = hclge_cmd_check_retval(hw, desc, num, ntc);
 	}
 
 	/* Clean the command send queue */
@@ -350,11 +363,20 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	hdev->hw.cmq.crq.next_to_use = 0;
 
 	hclge_cmd_init_regs(&hdev->hw);
-	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 
 	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
 	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 
+	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+
+	/* Check if there is new reset pending, because the higher level
+	 * reset may happen when lower level reset is being processed.
+	 */
+	if ((hclge_is_reset_pending(hdev))) {
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		return -EBUSY;
+	}
+
 	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
@@ -368,6 +390,20 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	return 0;
 }
 
+static void hclge_cmd_uninit_regs(struct hclge_hw *hw)
+{
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0);
+	hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
+}
+
 static void hclge_destroy_queue(struct hclge_cmq_ring *ring)
 {
 	spin_lock(&ring->lock);
@@ -380,3 +416,15 @@ void hclge_destroy_cmd_queue(struct hclge_hw *hw)
 	hclge_destroy_queue(&hw->cmq.csq);
 	hclge_destroy_queue(&hw->cmq.crq);
 }
+
+void hclge_cmd_uninit(struct hclge_dev *hdev)
+{
+	spin_lock_bh(&hdev->hw.cmq.csq.lock);
+	spin_lock(&hdev->hw.cmq.crq.lock);
+	set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+	hclge_cmd_uninit_regs(&hdev->hw);
+	spin_unlock(&hdev->hw.cmq.crq.lock);
+	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
+
+	hclge_destroy_cmd_queue(&hdev->hw);
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 872cd4bdd70d..3714733c96d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -39,7 +39,7 @@ struct hclge_cmq_ring {
 enum hclge_cmd_return_status {
 	HCLGE_CMD_EXEC_SUCCESS	= 0,
 	HCLGE_CMD_NO_AUTH	= 1,
-	HCLGE_CMD_NOT_EXEC	= 2,
+	HCLGE_CMD_NOT_SUPPORTED	= 2,
 	HCLGE_CMD_QUEUE_FULL	= 3,
 };
 
@@ -82,15 +82,30 @@ enum hclge_opcode_type {
 	HCLGE_OPC_STATS_64_BIT		= 0x0030,
 	HCLGE_OPC_STATS_32_BIT		= 0x0031,
 	HCLGE_OPC_STATS_MAC		= 0x0032,
+	HCLGE_OPC_QUERY_MAC_REG_NUM	= 0x0033,
+	HCLGE_OPC_STATS_MAC_ALL		= 0x0034,
 
 	HCLGE_OPC_QUERY_REG_NUM		= 0x0040,
 	HCLGE_OPC_QUERY_32_BIT_REG	= 0x0041,
 	HCLGE_OPC_QUERY_64_BIT_REG	= 0x0042,
+	HCLGE_OPC_DFX_BD_NUM		= 0x0043,
+	HCLGE_OPC_DFX_BIOS_COMMON_REG	= 0x0044,
+	HCLGE_OPC_DFX_SSU_REG_0		= 0x0045,
+	HCLGE_OPC_DFX_SSU_REG_1		= 0x0046,
+	HCLGE_OPC_DFX_IGU_EGU_REG	= 0x0047,
+	HCLGE_OPC_DFX_RPU_REG_0		= 0x0048,
+	HCLGE_OPC_DFX_RPU_REG_1		= 0x0049,
+	HCLGE_OPC_DFX_NCSI_REG		= 0x004A,
+	HCLGE_OPC_DFX_RTC_REG		= 0x004B,
+	HCLGE_OPC_DFX_PPP_REG		= 0x004C,
+	HCLGE_OPC_DFX_RCB_REG		= 0x004D,
+	HCLGE_OPC_DFX_TQP_REG		= 0x004E,
+	HCLGE_OPC_DFX_SSU_REG_2		= 0x004F,
+	HCLGE_OPC_DFX_QUERY_CHIP_CAP	= 0x0050,
 
 	/* MAC command */
 	HCLGE_OPC_CONFIG_MAC_MODE	= 0x0301,
 	HCLGE_OPC_CONFIG_AN_MODE	= 0x0304,
-	HCLGE_OPC_QUERY_AN_RESULT	= 0x0306,
 	HCLGE_OPC_QUERY_LINK_STATUS	= 0x0307,
 	HCLGE_OPC_CONFIG_MAX_FRM_SIZE	= 0x0308,
 	HCLGE_OPC_CONFIG_SPEED_DUP	= 0x0309,
@@ -126,6 +141,16 @@ enum hclge_opcode_type {
 	HCLGE_OPC_TM_PRI_SCH_MODE_CFG   = 0x0813,
 	HCLGE_OPC_TM_QS_SCH_MODE_CFG    = 0x0814,
 	HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815,
+	HCLGE_OPC_ETS_TC_WEIGHT		= 0x0843,
+	HCLGE_OPC_QSET_DFX_STS		= 0x0844,
+	HCLGE_OPC_PRI_DFX_STS		= 0x0845,
+	HCLGE_OPC_PG_DFX_STS		= 0x0846,
+	HCLGE_OPC_PORT_DFX_STS		= 0x0847,
+	HCLGE_OPC_SCH_NQ_CNT		= 0x0848,
+	HCLGE_OPC_SCH_RQ_CNT		= 0x0849,
+	HCLGE_OPC_TM_INTERNAL_STS	= 0x0850,
+	HCLGE_OPC_TM_INTERNAL_CNT	= 0x0851,
+	HCLGE_OPC_TM_INTERNAL_STS_1	= 0x0852,
 
 	/* Packet buffer allocate commands */
 	HCLGE_OPC_TX_BUFF_ALLOC		= 0x0901,
@@ -142,6 +167,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_CFG_TX_QUEUE		= 0x0B01,
 	HCLGE_OPC_QUERY_TX_POINTER	= 0x0B02,
 	HCLGE_OPC_QUERY_TX_STATUS	= 0x0B03,
+	HCLGE_OPC_TQP_TX_QUEUE_TC	= 0x0B04,
 	HCLGE_OPC_CFG_RX_QUEUE		= 0x0B11,
 	HCLGE_OPC_QUERY_RX_POINTER	= 0x0B12,
 	HCLGE_OPC_QUERY_RX_STATUS	= 0x0B13,
@@ -152,6 +178,7 @@ enum hclge_opcode_type {
 
 	/* TSO command */
 	HCLGE_OPC_TSO_GENERIC_CONFIG	= 0x0C01,
+	HCLGE_OPC_GRO_GENERIC_CONFIG    = 0x0C10,
 
 	/* RSS commands */
 	HCLGE_OPC_RSS_GENERIC_CONFIG	= 0x0D01,
@@ -210,27 +237,34 @@ enum hclge_opcode_type {
 	/* Led command */
 	HCLGE_OPC_LED_STATUS_CFG	= 0xB000,
 
+	/* SFP command */
+	HCLGE_OPC_SFP_GET_SPEED		= 0x7104,
+
 	/* Error INT commands */
+	HCLGE_MAC_COMMON_INT_EN		= 0x030E,
 	HCLGE_TM_SCH_ECC_INT_EN		= 0x0829,
-	HCLGE_TM_SCH_ECC_ERR_RINT_CMD	= 0x082d,
-	HCLGE_TM_SCH_ECC_ERR_RINT_CE	= 0x082f,
-	HCLGE_TM_SCH_ECC_ERR_RINT_NFE	= 0x0830,
-	HCLGE_TM_SCH_ECC_ERR_RINT_FE	= 0x0831,
-	HCLGE_TM_SCH_MBIT_ECC_INFO_CMD	= 0x0833,
+	HCLGE_SSU_ECC_INT_CMD		= 0x0989,
+	HCLGE_SSU_COMMON_INT_CMD	= 0x098C,
+	HCLGE_PPU_MPF_ECC_INT_CMD	= 0x0B40,
+	HCLGE_PPU_MPF_OTHER_INT_CMD	= 0x0B41,
+	HCLGE_PPU_PF_OTHER_INT_CMD	= 0x0B42,
 	HCLGE_COMMON_ECC_INT_CFG	= 0x1505,
-	HCLGE_IGU_EGU_TNL_INT_QUERY	= 0x1802,
+	HCLGE_QUERY_RAS_INT_STS_BD_NUM	= 0x1510,
+	HCLGE_QUERY_CLEAR_MPF_RAS_INT	= 0x1511,
+	HCLGE_QUERY_CLEAR_PF_RAS_INT	= 0x1512,
+	HCLGE_QUERY_MSIX_INT_STS_BD_NUM	= 0x1513,
+	HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT	= 0x1514,
+	HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT	= 0x1515,
+	HCLGE_CONFIG_ROCEE_RAS_INT_EN	= 0x1580,
+	HCLGE_QUERY_CLEAR_ROCEE_RAS_INT = 0x1581,
+	HCLGE_ROCEE_PF_RAS_INT_CMD	= 0x1584,
 	HCLGE_IGU_EGU_TNL_INT_EN	= 0x1803,
-	HCLGE_IGU_EGU_TNL_INT_CLR	= 0x1804,
-	HCLGE_IGU_COMMON_INT_QUERY	= 0x1805,
 	HCLGE_IGU_COMMON_INT_EN		= 0x1806,
-	HCLGE_IGU_COMMON_INT_CLR	= 0x1807,
 	HCLGE_TM_QCN_MEM_INT_CFG	= 0x1A14,
-	HCLGE_TM_QCN_MEM_INT_INFO_CMD	= 0x1A17,
 	HCLGE_PPP_CMD0_INT_CMD		= 0x2100,
 	HCLGE_PPP_CMD1_INT_CMD		= 0x2101,
-	HCLGE_NCSI_INT_QUERY		= 0x2400,
+	HCLGE_MAC_ETHERTYPE_IDX_RD      = 0x2105,
 	HCLGE_NCSI_INT_EN		= 0x2401,
-	HCLGE_NCSI_INT_CLR		= 0x2402,
 };
 
 #define HCLGE_TQP_REG_OFFSET		0x80000
@@ -278,16 +312,16 @@ struct hclge_ctrl_vector_chain_cmd {
 	u8 rsv;
 };
 
-#define HCLGE_TC_NUM		8
+#define HCLGE_MAX_TC_NUM		8
 #define HCLGE_TC0_PRI_BUF_EN_B	15 /* Bit 15 indicate enable or not */
 #define HCLGE_BUF_UNIT_S	7  /* Buf size is united by 128 bytes */
 struct hclge_tx_buff_alloc_cmd {
-	__le16 tx_pkt_buff[HCLGE_TC_NUM];
+	__le16 tx_pkt_buff[HCLGE_MAX_TC_NUM];
 	u8 tx_buff_rsv[8];
 };
 
 struct hclge_rx_priv_buff_cmd {
-	__le16 buf_num[HCLGE_TC_NUM];
+	__le16 buf_num[HCLGE_MAX_TC_NUM];
 	__le16 shared_buf;
 	u8 rsv[6];
 };
@@ -333,7 +367,6 @@ struct hclge_priv_buf {
 	u32 enable;	/* Enable TC private buffer or not */
 };
 
-#define HCLGE_MAX_TC_NUM	8
 struct hclge_shared_buf {
 	struct hclge_waterline self;
 	struct hclge_tc_thrd tc_thrd[HCLGE_MAX_TC_NUM];
@@ -388,7 +421,9 @@ struct hclge_pf_res_cmd {
 #define HCLGE_PF_VEC_NUM_M		GENMASK(7, 0)
 	__le16 pf_intr_vector_number;
 	__le16 pf_own_fun_number;
-	__le32 rsv[3];
+	__le16 tx_buf_size;
+	__le16 dv_buf_size;
+	__le32 rsv[2];
 };
 
 #define HCLGE_CFG_OFFSET_S	0
@@ -542,20 +577,6 @@ struct hclge_config_mac_speed_dup_cmd {
 	u8 rsv[22];
 };
 
-#define HCLGE_QUERY_SPEED_S		3
-#define HCLGE_QUERY_AN_B		0
-#define HCLGE_QUERY_DUPLEX_B		2
-
-#define HCLGE_QUERY_SPEED_M		GENMASK(4, 0)
-#define HCLGE_QUERY_AN_M		BIT(HCLGE_QUERY_AN_B)
-#define HCLGE_QUERY_DUPLEX_M		BIT(HCLGE_QUERY_DUPLEX_B)
-
-struct hclge_query_an_speed_dup_cmd {
-	u8 an_syn_dup_speed;
-	u8 pause;
-	u8 rsv[23];
-};
-
 #define HCLGE_RING_ID_MASK		GENMASK(9, 0)
 #define HCLGE_TQP_ENABLE_B		0
 
@@ -572,6 +593,11 @@ struct hclge_config_auto_neg_cmd {
 	u8      rsv[20];
 };
 
+struct hclge_sfp_speed_cmd {
+	__le32	sfp_speed;
+	u32	rsv[5];
+};
+
 #define HCLGE_MAC_UPLINK_PORT		0x100
 
 struct hclge_config_max_frm_size_cmd {
@@ -667,7 +693,9 @@ struct hclge_mac_vlan_remove_cmd {
 struct hclge_vlan_filter_ctrl_cmd {
 	u8 vlan_type;
 	u8 vlan_fe;
-	u8 rsv[22];
+	u8 rsv1[2];
+	u8 vf_id;
+	u8 rsv2[19];
 };
 
 struct hclge_vlan_filter_pf_cfg_cmd {
@@ -746,6 +774,24 @@ struct hclge_cfg_tx_queue_pointer_cmd {
 	u8 rsv[14];
 };
 
+#pragma pack(1)
+struct hclge_mac_ethertype_idx_rd_cmd {
+	u8	flags;
+	u8	resp_code;
+	__le16  vlan_tag;
+	u8      mac_add[6];
+	__le16  index;
+	__le16	ethter_type;
+	__le16  egress_port;
+	__le16  egress_queue;
+	__le16  rev0;
+	u8	i_port_bitmap;
+	u8	i_port_direction;
+	u8	rev1[2];
+};
+
+#pragma pack()
+
 #define HCLGE_TSO_MSS_MIN_S	0
 #define HCLGE_TSO_MSS_MIN_M	GENMASK(13, 0)
 
@@ -758,6 +804,12 @@ struct hclge_cfg_tso_status_cmd {
 	u8 rsv[20];
 };
 
+#define HCLGE_GRO_EN_B		0
+struct hclge_cfg_gro_status_cmd {
+	__le16 gro_en;
+	u8 rsv[22];
+};
+
 #define HCLGE_TSO_MSS_MIN	256
 #define HCLGE_TSO_MSS_MAX	9668
 
@@ -792,6 +844,7 @@ struct hclge_serdes_lb_cmd {
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
 #define HCLGE_DEFAULT_NON_DCB_DV	0x7800	/* 30K byte */
+#define HCLGE_NON_DCB_ADDITIONAL_BUF	0x200	/* 512 byte */
 
 #define HCLGE_TYPE_CRQ			0
 #define HCLGE_TYPE_CSQ			1
@@ -924,6 +977,6 @@ enum hclge_cmd_status hclge_cmd_mdio_write(struct hclge_hw *hw,
 enum hclge_cmd_status hclge_cmd_mdio_read(struct hclge_hw *hw,
 					  struct hclge_desc *desc);
 
-void hclge_destroy_cmd_queue(struct hclge_hw *hw);
+void hclge_cmd_uninit(struct hclge_dev *hdev);
 int hclge_cmd_queue_init(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index e72f724123d7..1161361a973b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -35,7 +35,9 @@ static int hclge_ieee_ets_to_tm_info(struct hclge_dev *hdev,
 		}
 	}
 
-	return hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+	hclge_tm_prio_tc_info_update(hdev, ets->prio_tc);
+
+	return 0;
 }
 
 static void hclge_tm_info_to_ieee_ets(struct hclge_dev *hdev,
@@ -70,25 +72,59 @@ static int hclge_ieee_getets(struct hnae3_handle *h, struct ieee_ets *ets)
 	return 0;
 }
 
+static int hclge_dcb_common_validate(struct hclge_dev *hdev, u8 num_tc,
+				     u8 *prio_tc)
+{
+	int i;
+
+	if (num_tc > hdev->tc_max) {
+		dev_err(&hdev->pdev->dev,
+			"tc num checking failed, %u > tc_max(%u)\n",
+			num_tc, hdev->tc_max);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		if (prio_tc[i] >= num_tc) {
+			dev_err(&hdev->pdev->dev,
+				"prio_tc[%u] checking failed, %u >= num_tc(%u)\n",
+				i, prio_tc[i], num_tc);
+			return -EINVAL;
+		}
+	}
+
+	if (num_tc > hdev->vport[0].alloc_tqps) {
+		dev_err(&hdev->pdev->dev,
+			"allocated tqp checking failed, %u > tqp(%u)\n",
+			num_tc, hdev->vport[0].alloc_tqps);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
 			      u8 *tc, bool *changed)
 {
 	bool has_ets_tc = false;
 	u32 total_ets_bw = 0;
 	u8 max_tc = 0;
+	int ret;
 	u8 i;
 
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		if (ets->prio_tc[i] >= hdev->tc_max ||
-		    i >= hdev->tc_max)
-			return -EINVAL;
-
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
 		if (ets->prio_tc[i] != hdev->tm_info.prio_tc[i])
 			*changed = true;
 
 		if (ets->prio_tc[i] > max_tc)
 			max_tc = ets->prio_tc[i];
+	}
 
+	ret = hclge_dcb_common_validate(hdev, max_tc + 1, ets->prio_tc);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
 		switch (ets->tc_tsa[i]) {
 		case IEEE_8021QAZ_TSA_STRICT:
 			if (hdev->tm_info.tc_info[i].tc_sch_mode !=
@@ -118,21 +154,15 @@ static int hclge_ets_validate(struct hclge_dev *hdev, struct ieee_ets *ets,
 	return 0;
 }
 
-static int hclge_map_update(struct hnae3_handle *h)
+static int hclge_map_update(struct hclge_dev *hdev)
 {
-	struct hclge_vport *vport = hclge_get_vport(h);
-	struct hclge_dev *hdev = vport->back;
 	int ret;
 
-	ret = hclge_tm_map_cfg(hdev);
-	if (ret)
-		return ret;
-
-	ret = hclge_tm_schd_mode_hw(hdev);
+	ret = hclge_tm_schd_setup_hw(hdev);
 	if (ret)
 		return ret;
 
-	ret = hclge_pause_setup_hw(hdev);
+	ret = hclge_pause_setup_hw(hdev, false);
 	if (ret)
 		return ret;
 
@@ -184,21 +214,51 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets)
 	if (ret)
 		return ret;
 
-	ret = hclge_tm_schd_info_update(hdev, num_tc);
-	if (ret)
-		return ret;
+	if (map_changed) {
+		ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+		if (ret)
+			return ret;
+
+		ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+		if (ret)
+			return ret;
+	}
+
+	hclge_tm_schd_info_update(hdev, num_tc);
 
 	ret = hclge_ieee_ets_to_tm_info(hdev, ets);
 	if (ret)
-		return ret;
+		goto err_out;
 
 	if (map_changed) {
+		ret = hclge_map_update(hdev);
+		if (ret)
+			goto err_out;
+
 		ret = hclge_client_setup_tc(hdev);
 		if (ret)
+			goto err_out;
+
+		ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+		if (ret)
+			return ret;
+
+		ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+		if (ret)
 			return ret;
 	}
 
 	return hclge_tm_dwrr_cfg(hdev);
+
+err_out:
+	if (!map_changed)
+		return ret;
+
+	if (hclge_notify_client(hdev, HNAE3_INIT_CLIENT))
+		return ret;
+
+	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	return ret;
 }
 
 static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
@@ -247,6 +307,9 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 	    hdev->flag & HCLGE_FLAG_MQPRIO_ENABLE)
 		return -EINVAL;
 
+	if (pfc->pfc_en == hdev->tm_info.pfc_en)
+		return 0;
+
 	prio_tc = hdev->tm_info.prio_tc;
 	pfc_map = 0;
 
@@ -259,12 +322,10 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc)
 		}
 	}
 
-	if (pfc_map == hdev->tm_info.hw_pfc_map)
-		return 0;
-
 	hdev->tm_info.hw_pfc_map = pfc_map;
+	hdev->tm_info.pfc_en = pfc->pfc_en;
 
-	return hclge_pause_setup_hw(hdev);
+	return hclge_pause_setup_hw(hdev, false);
 }
 
 /* DCBX configuration */
@@ -305,24 +366,28 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
 	if (hdev->flag & HCLGE_FLAG_DCB_ENABLE)
 		return -EINVAL;
 
-	if (tc > hdev->tc_max) {
-		dev_err(&hdev->pdev->dev,
-			"setup tc failed, tc(%u) > tc_max(%u)\n",
-			tc, hdev->tc_max);
+	ret = hclge_dcb_common_validate(hdev, tc, prio_tc);
+	if (ret)
 		return -EINVAL;
-	}
 
-	ret = hclge_tm_schd_info_update(hdev, tc);
+	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 	if (ret)
 		return ret;
 
-	ret = hclge_tm_prio_tc_info_update(hdev, prio_tc);
+	ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
 	if (ret)
 		return ret;
 
-	ret = hclge_tm_init_hw(hdev);
+	hclge_tm_schd_info_update(hdev, tc);
+	hclge_tm_prio_tc_info_update(hdev, prio_tc);
+
+	ret = hclge_tm_init_hw(hdev, false);
 	if (ret)
-		return ret;
+		goto err_out;
+
+	ret = hclge_client_setup_tc(hdev);
+	if (ret)
+		goto err_out;
 
 	hdev->flag &= ~HCLGE_FLAG_DCB_ENABLE;
 
@@ -331,7 +396,18 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc)
 	else
 		hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE;
 
-	return 0;
+	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
+
+	return hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+
+err_out:
+	if (hclge_notify_client(hdev, HNAE3_INIT_CLIENT))
+		return ret;
+
+	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	return ret;
 }
 
 static const struct hnae3_dcb_ops hns3_dcb_ops = {
@@ -341,7 +417,6 @@ static const struct hnae3_dcb_ops hns3_dcb_ops = {
 	.ieee_setpfc	= hclge_ieee_setpfc,
 	.getdcbx	= hclge_getdcbx,
 	.setdcbx	= hclge_setdcbx,
-	.map_update	= hclge_map_update,
 	.setup_tc	= hclge_setup_tc,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
new file mode 100644
index 000000000000..1192cf6f2321
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -0,0 +1,933 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+#include <linux/device.h>
+
+#include "hclge_debugfs.h"
+#include "hclge_cmd.h"
+#include "hclge_main.h"
+#include "hclge_tm.h"
+#include "hnae3.h"
+
+static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset)
+{
+	struct hclge_desc desc[4];
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true);
+	desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true);
+
+	ret = hclge_cmd_send(&hdev->hw, desc, 4);
+	if (ret != HCLGE_CMD_EXEC_SUCCESS) {
+		dev_err(&hdev->pdev->dev,
+			"get dfx bdnum fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	return (int)desc[offset / 6].data[offset % 6];
+}
+
+static int hclge_dbg_cmd_send(struct hclge_dev *hdev,
+			      struct hclge_desc *desc_src,
+			      int index, int bd_num,
+			      enum hclge_opcode_type cmd)
+{
+	struct hclge_desc *desc = desc_src;
+	int ret, i;
+
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	desc->data[0] = cpu_to_le32(index);
+
+	for (i = 1; i < bd_num; i++) {
+		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+		desc++;
+		hclge_cmd_setup_basic_desc(desc, cmd, true);
+	}
+
+	ret = hclge_cmd_send(&hdev->hw, desc_src, bd_num);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"read reg cmd send fail, status is %d.\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev,
+				      struct hclge_dbg_dfx_message *dfx_message,
+				      char *cmd_buf, int msg_num, int offset,
+				      enum hclge_opcode_type cmd)
+{
+	struct hclge_desc *desc_src;
+	struct hclge_desc *desc;
+	int bd_num, buf_len;
+	int ret, i;
+	int index;
+	int max;
+
+	ret = kstrtouint(cmd_buf, 10, &index);
+	index = (ret != 0) ? 0 : index;
+
+	bd_num = hclge_dbg_get_dfx_bd_num(hdev, offset);
+	if (bd_num <= 0)
+		return;
+
+	buf_len	 = sizeof(struct hclge_desc) * bd_num;
+	desc_src = kzalloc(buf_len, GFP_KERNEL);
+	if (!desc_src) {
+		dev_err(&hdev->pdev->dev, "call kzalloc failed\n");
+		return;
+	}
+
+	desc = desc_src;
+	ret  = hclge_dbg_cmd_send(hdev, desc, index, bd_num, cmd);
+	if (ret != HCLGE_CMD_EXEC_SUCCESS) {
+		kfree(desc_src);
+		return;
+	}
+
+	max = (bd_num * 6) <= msg_num ? (bd_num * 6) : msg_num;
+
+	desc = desc_src;
+	for (i = 0; i < max; i++) {
+		(((i / 6) > 0) && ((i % 6) == 0)) ? desc++ : desc;
+		if (dfx_message->flag)
+			dev_info(&hdev->pdev->dev, "%s: 0x%x\n",
+				 dfx_message->message, desc->data[i % 6]);
+
+		dfx_message++;
+	}
+
+	kfree(desc_src);
+}
+
+static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, char *cmd_buf)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_dbg_bitmap_cmd *bitmap;
+	int rq_id, pri_id, qset_id;
+	int port_id, nq_id, pg_id;
+	struct hclge_desc desc[2];
+
+	int cnt, ret;
+
+	cnt = sscanf(cmd_buf, "%i %i %i %i %i %i",
+		     &port_id, &pri_id, &pg_id, &rq_id, &nq_id, &qset_id);
+	if (cnt != 6) {
+		dev_err(&hdev->pdev->dev,
+			"dump dcb: bad command parameter, cnt=%d\n", cnt);
+		return;
+	}
+
+	ret = hclge_dbg_cmd_send(hdev, desc, qset_id, 1,
+				 HCLGE_OPC_QSET_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "roce_qset_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "nic_qs_mask: 0x%x\n", bitmap->bit1);
+	dev_info(dev, "qs_shaping_pass: 0x%x\n", bitmap->bit2);
+	dev_info(dev, "qs_bp_sts: 0x%x\n", bitmap->bit3);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, pri_id, 1, HCLGE_OPC_PRI_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "pri_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "pri_cshaping_pass: 0x%x\n", bitmap->bit1);
+	dev_info(dev, "pri_pshaping_pass: 0x%x\n", bitmap->bit2);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, pg_id, 1, HCLGE_OPC_PG_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "pg_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "pg_cshaping_pass: 0x%x\n", bitmap->bit1);
+	dev_info(dev, "pg_pshaping_pass: 0x%x\n", bitmap->bit2);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_PORT_DFX_STS);
+	if (ret)
+		return;
+
+	bitmap = (struct hclge_dbg_bitmap_cmd *)&desc[0].data[1];
+	dev_info(dev, "port_mask: 0x%x\n", bitmap->bit0);
+	dev_info(dev, "port_shaping_pass: 0x%x\n", bitmap->bit1);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, HCLGE_OPC_SCH_NQ_CNT);
+	if (ret)
+		return;
+
+	dev_info(dev, "sch_nq_cnt: 0x%x\n", desc[0].data[1]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, nq_id, 1, HCLGE_OPC_SCH_RQ_CNT);
+	if (ret)
+		return;
+
+	dev_info(dev, "sch_rq_cnt: 0x%x\n", desc[0].data[1]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, 0, 2, HCLGE_OPC_TM_INTERNAL_STS);
+	if (ret)
+		return;
+
+	dev_info(dev, "pri_bp: 0x%x\n", desc[0].data[1]);
+	dev_info(dev, "fifo_dfx_info: 0x%x\n", desc[0].data[2]);
+	dev_info(dev, "sch_roce_fifo_afull_gap: 0x%x\n", desc[0].data[3]);
+	dev_info(dev, "tx_private_waterline: 0x%x\n", desc[0].data[4]);
+	dev_info(dev, "tm_bypass_en: 0x%x\n", desc[0].data[5]);
+	dev_info(dev, "SSU_TM_BYPASS_EN: 0x%x\n", desc[1].data[0]);
+	dev_info(dev, "SSU_RESERVE_CFG: 0x%x\n", desc[1].data[1]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_TM_INTERNAL_CNT);
+	if (ret)
+		return;
+
+	dev_info(dev, "SCH_NIC_NUM: 0x%x\n", desc[0].data[1]);
+	dev_info(dev, "SCH_ROCE_NUM: 0x%x\n", desc[0].data[2]);
+
+	ret = hclge_dbg_cmd_send(hdev, desc, port_id, 1,
+				 HCLGE_OPC_TM_INTERNAL_STS_1);
+	if (ret)
+		return;
+
+	dev_info(dev, "TC_MAP_SEL: 0x%x\n", desc[0].data[1]);
+	dev_info(dev, "IGU_PFC_PRI_EN: 0x%x\n", desc[0].data[2]);
+	dev_info(dev, "MAC_PFC_PRI_EN: 0x%x\n", desc[0].data[3]);
+	dev_info(dev, "IGU_PRI_MAP_TC_CFG: 0x%x\n", desc[0].data[4]);
+	dev_info(dev, "IGU_TX_PRI_MAP_TC_CFG: 0x%x\n", desc[0].data[5]);
+}
+
+static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, char *cmd_buf)
+{
+	int msg_num;
+
+	if (strncmp(&cmd_buf[9], "bios common", 11) == 0) {
+		msg_num = sizeof(hclge_dbg_bios_common_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_bios_common_reg,
+					  &cmd_buf[21], msg_num,
+					  HCLGE_DBG_DFX_BIOS_OFFSET,
+					  HCLGE_OPC_DFX_BIOS_COMMON_REG);
+	} else if (strncmp(&cmd_buf[9], "ssu", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_ssu_reg_0) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_0,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_SSU_0_OFFSET,
+					  HCLGE_OPC_DFX_SSU_REG_0);
+
+		msg_num = sizeof(hclge_dbg_ssu_reg_1) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_1,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_SSU_1_OFFSET,
+					  HCLGE_OPC_DFX_SSU_REG_1);
+
+		msg_num = sizeof(hclge_dbg_ssu_reg_2) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_2,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_SSU_2_OFFSET,
+					  HCLGE_OPC_DFX_SSU_REG_2);
+	} else if (strncmp(&cmd_buf[9], "igu egu", 7) == 0) {
+		msg_num = sizeof(hclge_dbg_igu_egu_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_igu_egu_reg,
+					  &cmd_buf[17], msg_num,
+					  HCLGE_DBG_DFX_IGU_OFFSET,
+					  HCLGE_OPC_DFX_IGU_EGU_REG);
+	} else if (strncmp(&cmd_buf[9], "rpu", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_rpu_reg_0) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rpu_reg_0,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RPU_0_OFFSET,
+					  HCLGE_OPC_DFX_RPU_REG_0);
+
+		msg_num = sizeof(hclge_dbg_rpu_reg_1) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rpu_reg_1,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RPU_1_OFFSET,
+					  HCLGE_OPC_DFX_RPU_REG_1);
+	} else if (strncmp(&cmd_buf[9], "ncsi", 4) == 0) {
+		msg_num = sizeof(hclge_dbg_ncsi_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ncsi_reg,
+					  &cmd_buf[14], msg_num,
+					  HCLGE_DBG_DFX_NCSI_OFFSET,
+					  HCLGE_OPC_DFX_NCSI_REG);
+	} else if (strncmp(&cmd_buf[9], "rtc", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_rtc_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rtc_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RTC_OFFSET,
+					  HCLGE_OPC_DFX_RTC_REG);
+	} else if (strncmp(&cmd_buf[9], "ppp", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_ppp_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_ppp_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_PPP_OFFSET,
+					  HCLGE_OPC_DFX_PPP_REG);
+	} else if (strncmp(&cmd_buf[9], "rcb", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_rcb_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_rcb_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_RCB_OFFSET,
+					  HCLGE_OPC_DFX_RCB_REG);
+	} else if (strncmp(&cmd_buf[9], "tqp", 3) == 0) {
+		msg_num = sizeof(hclge_dbg_tqp_reg) /
+			  sizeof(struct hclge_dbg_dfx_message);
+		hclge_dbg_dump_reg_common(hdev, hclge_dbg_tqp_reg,
+					  &cmd_buf[13], msg_num,
+					  HCLGE_DBG_DFX_TQP_OFFSET,
+					  HCLGE_OPC_DFX_TQP_REG);
+	} else if (strncmp(&cmd_buf[9], "dcb", 3) == 0) {
+		hclge_dbg_dump_dcb(hdev, &cmd_buf[13]);
+	} else {
+		dev_info(&hdev->pdev->dev, "unknown command\n");
+		return;
+	}
+}
+
+static void hclge_title_idx_print(struct hclge_dev *hdev, bool flag, int index,
+				  char *title_buf, char *true_buf,
+				  char *false_buf)
+{
+	if (flag)
+		dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index,
+			 true_buf);
+	else
+		dev_info(&hdev->pdev->dev, "%s(%d): %s\n", title_buf, index,
+			 false_buf);
+}
+
+static void hclge_dbg_dump_tc(struct hclge_dev *hdev)
+{
+	struct hclge_ets_tc_weight_cmd *ets_weight;
+	struct hclge_desc desc;
+	int i, ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "dump tc fail, status is %d.\n", ret);
+		return;
+	}
+
+	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
+
+	dev_info(&hdev->pdev->dev, "dump tc\n");
+	dev_info(&hdev->pdev->dev, "weight_offset: %u\n",
+		 ets_weight->weight_offset);
+
+	for (i = 0; i < HNAE3_MAX_TC; i++)
+		hclge_title_idx_print(hdev, ets_weight->tc_weight[i], i,
+				      "tc", "no sp mode", "sp mode");
+}
+
+static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev)
+{
+	struct hclge_port_shapping_cmd *port_shap_cfg_cmd;
+	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
+	struct hclge_pg_shapping_cmd *pg_shap_cfg_cmd;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	cmd = HCLGE_OPC_TM_PG_C_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PG_C pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
+	dev_info(&hdev->pdev->dev, "PG_C pg_shapping: 0x%x\n",
+		 pg_shap_cfg_cmd->pg_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PG_P_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	pg_shap_cfg_cmd = (struct hclge_pg_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PG_P pg_id: %u\n", pg_shap_cfg_cmd->pg_id);
+	dev_info(&hdev->pdev->dev, "PG_P pg_shapping: 0x%x\n",
+		 pg_shap_cfg_cmd->pg_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PORT_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	port_shap_cfg_cmd = (struct hclge_port_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PORT port_shapping: 0x%x\n",
+		 port_shap_cfg_cmd->port_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PG_SCH_MODE_CFG;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "PG_SCH pg_id: %u\n", desc.data[0]);
+
+	cmd = HCLGE_OPC_TM_PRI_SCH_MODE_CFG;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "PRI_SCH pg_id: %u\n", desc.data[0]);
+
+	cmd = HCLGE_OPC_TM_QS_SCH_MODE_CFG;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "QS_SCH pg_id: %u\n", desc.data[0]);
+
+	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_pg_cmd_send;
+
+	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET pg_id: %u\n",
+		 bp_to_qs_map_cmd->tc_id);
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET pg_shapping: 0x%x\n",
+		 bp_to_qs_map_cmd->qs_group_id);
+	dev_info(&hdev->pdev->dev, "BP_TO_QSET qs_bit_map: 0x%x\n",
+		 bp_to_qs_map_cmd->qs_bit_map);
+	return;
+
+err_tm_pg_cmd_send:
+	dev_err(&hdev->pdev->dev, "dump tm_pg fail(0x%x), status is %d\n",
+		cmd, ret);
+}
+
+static void hclge_dbg_dump_tm(struct hclge_dev *hdev)
+{
+	struct hclge_priority_weight_cmd *priority_weight;
+	struct hclge_pg_to_pri_link_cmd *pg_to_pri_map;
+	struct hclge_qs_to_pri_link_cmd *qs_to_pri_map;
+	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
+	struct hclge_pri_shapping_cmd *shap_cfg_cmd;
+	struct hclge_pg_weight_cmd *pg_weight;
+	struct hclge_qs_weight_cmd *qs_weight;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc;
+	int ret;
+
+	cmd = HCLGE_OPC_TM_PG_TO_PRI_LINK;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	pg_to_pri_map = (struct hclge_pg_to_pri_link_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "dump tm\n");
+	dev_info(&hdev->pdev->dev, "PG_TO_PRI gp_id: %u\n",
+		 pg_to_pri_map->pg_id);
+	dev_info(&hdev->pdev->dev, "PG_TO_PRI map: 0x%x\n",
+		 pg_to_pri_map->pri_bit_map);
+
+	cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	qs_to_pri_map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "QS_TO_PRI qs_id: %u\n",
+		 qs_to_pri_map->qs_id);
+	dev_info(&hdev->pdev->dev, "QS_TO_PRI priority: %u\n",
+		 qs_to_pri_map->priority);
+	dev_info(&hdev->pdev->dev, "QS_TO_PRI link_vld: %u\n",
+		 qs_to_pri_map->link_vld);
+
+	cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "NQ_TO_QS nq_id: %u\n", nq_to_qs_map->nq_id);
+	dev_info(&hdev->pdev->dev, "NQ_TO_QS qset_id: %u\n",
+		 nq_to_qs_map->qset_id);
+
+	cmd = HCLGE_OPC_TM_PG_WEIGHT;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	pg_weight = (struct hclge_pg_weight_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PG pg_id: %u\n", pg_weight->pg_id);
+	dev_info(&hdev->pdev->dev, "PG dwrr: %u\n", pg_weight->dwrr);
+
+	cmd = HCLGE_OPC_TM_QS_WEIGHT;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	qs_weight = (struct hclge_qs_weight_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "QS qs_id: %u\n", qs_weight->qs_id);
+	dev_info(&hdev->pdev->dev, "QS dwrr: %u\n", qs_weight->dwrr);
+
+	cmd = HCLGE_OPC_TM_PRI_WEIGHT;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	priority_weight = (struct hclge_priority_weight_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PRI pri_id: %u\n", priority_weight->pri_id);
+	dev_info(&hdev->pdev->dev, "PRI dwrr: %u\n", priority_weight->dwrr);
+
+	cmd = HCLGE_OPC_TM_PRI_C_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PRI_C pri_id: %u\n", shap_cfg_cmd->pri_id);
+	dev_info(&hdev->pdev->dev, "PRI_C pri_shapping: 0x%x\n",
+		 shap_cfg_cmd->pri_shapping_para);
+
+	cmd = HCLGE_OPC_TM_PRI_P_SHAPPING;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_cmd_send;
+
+	shap_cfg_cmd = (struct hclge_pri_shapping_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "PRI_P pri_id: %u\n", shap_cfg_cmd->pri_id);
+	dev_info(&hdev->pdev->dev, "PRI_P pri_shapping: 0x%x\n",
+		 shap_cfg_cmd->pri_shapping_para);
+
+	hclge_dbg_dump_tm_pg(hdev);
+
+	return;
+
+err_tm_cmd_send:
+	dev_err(&hdev->pdev->dev, "dump tm fail(0x%x), status is %d\n",
+		cmd, ret);
+}
+
+static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, char *cmd_buf)
+{
+	struct hclge_bp_to_qs_map_cmd *bp_to_qs_map_cmd;
+	struct hclge_nq_to_qs_link_cmd *nq_to_qs_map;
+	struct hclge_qs_to_pri_link_cmd *map;
+	struct hclge_tqp_tx_queue_tc_cmd *tc;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc;
+	int queue_id, group_id;
+	u32 qset_maping[32];
+	int tc_id, qset_id;
+	int pri_id, ret;
+	u32 i;
+
+	ret = kstrtouint(&cmd_buf[12], 10, &queue_id);
+	queue_id = (ret != 0) ? 0 : queue_id;
+
+	cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK;
+	nq_to_qs_map = (struct hclge_nq_to_qs_link_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	nq_to_qs_map->nq_id = cpu_to_le16(queue_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_map_cmd_send;
+	qset_id = nq_to_qs_map->qset_id & 0x3FF;
+
+	cmd = HCLGE_OPC_TM_QS_TO_PRI_LINK;
+	map = (struct hclge_qs_to_pri_link_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	map->qs_id = cpu_to_le16(qset_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_map_cmd_send;
+	pri_id = map->priority;
+
+	cmd = HCLGE_OPC_TQP_TX_QUEUE_TC;
+	tc = (struct hclge_tqp_tx_queue_tc_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, cmd, true);
+	tc->queue_id = cpu_to_le16(queue_id);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		goto err_tm_map_cmd_send;
+	tc_id = tc->tc_id & 0x7;
+
+	dev_info(&hdev->pdev->dev, "queue_id | qset_id | pri_id | tc_id\n");
+	dev_info(&hdev->pdev->dev, "%04d     | %04d    | %02d     | %02d\n",
+		 queue_id, qset_id, pri_id, tc_id);
+
+	cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING;
+	bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data;
+	for (group_id = 0; group_id < 32; group_id++) {
+		hclge_cmd_setup_basic_desc(&desc, cmd, true);
+		bp_to_qs_map_cmd->tc_id = tc_id;
+		bp_to_qs_map_cmd->qs_group_id = group_id;
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret)
+			goto err_tm_map_cmd_send;
+
+		qset_maping[group_id] = bp_to_qs_map_cmd->qs_bit_map;
+	}
+
+	dev_info(&hdev->pdev->dev, "index | tm bp qset maping:\n");
+
+	i = 0;
+	for (group_id = 0; group_id < 4; group_id++) {
+		dev_info(&hdev->pdev->dev,
+			 "%04d  | %08x:%08x:%08x:%08x:%08x:%08x:%08x:%08x\n",
+			 group_id * 256, qset_maping[(u32)(i + 7)],
+			 qset_maping[(u32)(i + 6)], qset_maping[(u32)(i + 5)],
+			 qset_maping[(u32)(i + 4)], qset_maping[(u32)(i + 3)],
+			 qset_maping[(u32)(i + 2)], qset_maping[(u32)(i + 1)],
+			 qset_maping[i]);
+		i += 8;
+	}
+
+	return;
+
+err_tm_map_cmd_send:
+	dev_err(&hdev->pdev->dev, "dump tqp map fail(0x%x), status is %d\n",
+		cmd, ret);
+}
+
+static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev)
+{
+	struct hclge_cfg_pause_param_cmd *pause_param;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_MAC_PARA, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "dump checksum fail, status is %d.\n",
+			ret);
+		return;
+	}
+
+	pause_param = (struct hclge_cfg_pause_param_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "dump qos pause cfg\n");
+	dev_info(&hdev->pdev->dev, "pause_trans_gap: 0x%x\n",
+		 pause_param->pause_trans_gap);
+	dev_info(&hdev->pdev->dev, "pause_trans_time: 0x%x\n",
+		 pause_param->pause_trans_time);
+}
+
+static void hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev)
+{
+	struct hclge_qos_pri_map_cmd *pri_map;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PRI_TO_TC_MAPPING, true);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"dump qos pri map fail, status is %d.\n", ret);
+		return;
+	}
+
+	pri_map = (struct hclge_qos_pri_map_cmd *)desc.data;
+	dev_info(&hdev->pdev->dev, "dump qos pri map\n");
+	dev_info(&hdev->pdev->dev, "vlan_to_pri: 0x%x\n", pri_map->vlan_pri);
+	dev_info(&hdev->pdev->dev, "pri_0_to_tc: 0x%x\n", pri_map->pri0_tc);
+	dev_info(&hdev->pdev->dev, "pri_1_to_tc: 0x%x\n", pri_map->pri1_tc);
+	dev_info(&hdev->pdev->dev, "pri_2_to_tc: 0x%x\n", pri_map->pri2_tc);
+	dev_info(&hdev->pdev->dev, "pri_3_to_tc: 0x%x\n", pri_map->pri3_tc);
+	dev_info(&hdev->pdev->dev, "pri_4_to_tc: 0x%x\n", pri_map->pri4_tc);
+	dev_info(&hdev->pdev->dev, "pri_5_to_tc: 0x%x\n", pri_map->pri5_tc);
+	dev_info(&hdev->pdev->dev, "pri_6_to_tc: 0x%x\n", pri_map->pri6_tc);
+	dev_info(&hdev->pdev->dev, "pri_7_to_tc: 0x%x\n", pri_map->pri7_tc);
+}
+
+static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev)
+{
+	struct hclge_tx_buff_alloc_cmd *tx_buf_cmd;
+	struct hclge_rx_priv_buff_cmd *rx_buf_cmd;
+	struct hclge_rx_priv_wl_buf *rx_priv_wl;
+	struct hclge_rx_com_wl *rx_packet_cnt;
+	struct hclge_rx_com_thrd *rx_com_thrd;
+	struct hclge_rx_com_wl *rx_com_wl;
+	enum hclge_opcode_type cmd;
+	struct hclge_desc desc[2];
+	int i, ret;
+
+	cmd = HCLGE_OPC_TX_BUFF_ALLOC;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "dump qos buf cfg\n");
+
+	tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc[0].data;
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
+		dev_info(&hdev->pdev->dev, "tx_packet_buf_tc_%d: 0x%x\n", i,
+			 tx_buf_cmd->tx_pkt_buff[i]);
+
+	cmd = HCLGE_OPC_RX_PRIV_BUFF_ALLOC;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "\n");
+	rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc[0].data;
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++)
+		dev_info(&hdev->pdev->dev, "rx_packet_buf_tc_%d: 0x%x\n", i,
+			 rx_buf_cmd->buf_num[i]);
+
+	dev_info(&hdev->pdev->dev, "rx_share_buf: 0x%x\n",
+		 rx_buf_cmd->shared_buf);
+
+	cmd = HCLGE_OPC_RX_PRIV_WL_ALLOC;
+	hclge_cmd_setup_basic_desc(&desc[0], cmd, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 2);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "\n");
+	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i,
+			 rx_priv_wl->tc_wl[i].high, rx_priv_wl->tc_wl[i].low);
+
+	rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[1].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i + 4,
+			 rx_priv_wl->tc_wl[i].high, rx_priv_wl->tc_wl[i].low);
+
+	cmd = HCLGE_OPC_RX_COM_THRD_ALLOC;
+	hclge_cmd_setup_basic_desc(&desc[0], cmd, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 2);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	dev_info(&hdev->pdev->dev, "\n");
+	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[0].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i,
+			 rx_com_thrd->com_thrd[i].high,
+			 rx_com_thrd->com_thrd[i].low);
+
+	rx_com_thrd = (struct hclge_rx_com_thrd *)desc[1].data;
+	for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++)
+		dev_info(&hdev->pdev->dev,
+			 "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i + 4,
+			 rx_com_thrd->com_thrd[i].high,
+			 rx_com_thrd->com_thrd[i].low);
+
+	cmd = HCLGE_OPC_RX_COM_WL_ALLOC;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	rx_com_wl = (struct hclge_rx_com_wl *)desc[0].data;
+	dev_info(&hdev->pdev->dev, "\n");
+	dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n",
+		 rx_com_wl->com_wl.high, rx_com_wl->com_wl.low);
+
+	cmd = HCLGE_OPC_RX_GBL_PKT_CNT;
+	hclge_cmd_setup_basic_desc(desc, cmd, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, 1);
+	if (ret)
+		goto err_qos_cmd_send;
+
+	rx_packet_cnt = (struct hclge_rx_com_wl *)desc[0].data;
+	dev_info(&hdev->pdev->dev,
+		 "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n",
+		 rx_packet_cnt->com_wl.high, rx_packet_cnt->com_wl.low);
+
+	return;
+
+err_qos_cmd_send:
+	dev_err(&hdev->pdev->dev,
+		"dump qos buf cfg fail(0x%x), status is %d\n", cmd, ret);
+}
+
+static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev)
+{
+	struct hclge_mac_ethertype_idx_rd_cmd *req0;
+	char printf_buf[HCLGE_DBG_BUF_LEN];
+	struct hclge_desc desc;
+	int ret, i;
+
+	dev_info(&hdev->pdev->dev, "mng tab:\n");
+	memset(printf_buf, 0, HCLGE_DBG_BUF_LEN);
+	strncat(printf_buf,
+		"entry|mac_addr         |mask|ether|mask|vlan|mask",
+		HCLGE_DBG_BUF_LEN - 1);
+	strncat(printf_buf + strlen(printf_buf),
+		"|i_map|i_dir|e_type|pf_id|vf_id|q_id|drop\n",
+		HCLGE_DBG_BUF_LEN - strlen(printf_buf) - 1);
+
+	dev_info(&hdev->pdev->dev, "%s", printf_buf);
+
+	for (i = 0; i < HCLGE_DBG_MNG_TBL_MAX; i++) {
+		hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_ETHERTYPE_IDX_RD,
+					   true);
+		req0 = (struct hclge_mac_ethertype_idx_rd_cmd *)&desc.data;
+		req0->index = cpu_to_le16(i);
+
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"call hclge_cmd_send fail, ret = %d\n", ret);
+			return;
+		}
+
+		if (!req0->resp_code)
+			continue;
+
+		memset(printf_buf, 0, HCLGE_DBG_BUF_LEN);
+		snprintf(printf_buf, HCLGE_DBG_BUF_LEN,
+			 "%02u   |%02x:%02x:%02x:%02x:%02x:%02x|",
+			 req0->index, req0->mac_add[0], req0->mac_add[1],
+			 req0->mac_add[2], req0->mac_add[3], req0->mac_add[4],
+			 req0->mac_add[5]);
+
+		snprintf(printf_buf + strlen(printf_buf),
+			 HCLGE_DBG_BUF_LEN - strlen(printf_buf),
+			 "%x   |%04x |%x   |%04x|%x   |%02x   |%02x   |",
+			 !!(req0->flags & HCLGE_DBG_MNG_MAC_MASK_B),
+			 req0->ethter_type,
+			 !!(req0->flags & HCLGE_DBG_MNG_ETHER_MASK_B),
+			 req0->vlan_tag & HCLGE_DBG_MNG_VLAN_TAG,
+			 !!(req0->flags & HCLGE_DBG_MNG_VLAN_MASK_B),
+			 req0->i_port_bitmap, req0->i_port_direction);
+
+		snprintf(printf_buf + strlen(printf_buf),
+			 HCLGE_DBG_BUF_LEN - strlen(printf_buf),
+			 "%d     |%d    |%02d   |%04d|%x\n",
+			 !!(req0->egress_port & HCLGE_DBG_MNG_E_TYPE_B),
+			 req0->egress_port & HCLGE_DBG_MNG_PF_ID,
+			 (req0->egress_port >> 3) & HCLGE_DBG_MNG_VF_ID,
+			 req0->egress_queue,
+			 !!(req0->egress_port & HCLGE_DBG_MNG_DROP_B));
+
+		dev_info(&hdev->pdev->dev, "%s", printf_buf);
+	}
+}
+
+static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage,
+				   bool sel_x, u32 loc)
+{
+	struct hclge_fd_tcam_config_1_cmd *req1;
+	struct hclge_fd_tcam_config_2_cmd *req2;
+	struct hclge_fd_tcam_config_3_cmd *req3;
+	struct hclge_desc desc[3];
+	int ret, i;
+	u32 *req;
+
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_FD_TCAM_OP, true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_FD_TCAM_OP, true);
+	desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_FD_TCAM_OP, true);
+
+	req1 = (struct hclge_fd_tcam_config_1_cmd *)desc[0].data;
+	req2 = (struct hclge_fd_tcam_config_2_cmd *)desc[1].data;
+	req3 = (struct hclge_fd_tcam_config_3_cmd *)desc[2].data;
+
+	req1->stage  = stage;
+	req1->xy_sel = sel_x ? 1 : 0;
+	req1->index  = cpu_to_le32(loc);
+
+	ret = hclge_cmd_send(&hdev->hw, desc, 3);
+	if (ret)
+		return;
+
+	dev_info(&hdev->pdev->dev, " read result tcam key %s(%u):\n",
+		 sel_x ? "x" : "y", loc);
+
+	req = (u32 *)req1->tcam_data;
+	for (i = 0; i < 2; i++)
+		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+
+	req = (u32 *)req2->tcam_data;
+	for (i = 0; i < 6; i++)
+		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+
+	req = (u32 *)req3->tcam_data;
+	for (i = 0; i < 5; i++)
+		dev_info(&hdev->pdev->dev, "%08x\n", *req++);
+}
+
+static void hclge_dbg_fd_tcam(struct hclge_dev *hdev)
+{
+	u32 i;
+
+	for (i = 0; i < hdev->fd_cfg.rule_num[0]; i++) {
+		hclge_dbg_fd_tcam_read(hdev, 0, true, i);
+		hclge_dbg_fd_tcam_read(hdev, 0, false, i);
+	}
+}
+
+int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	if (strncmp(cmd_buf, "dump fd tcam", 12) == 0) {
+		hclge_dbg_fd_tcam(hdev);
+	} else if (strncmp(cmd_buf, "dump tc", 7) == 0) {
+		hclge_dbg_dump_tc(hdev);
+	} else if (strncmp(cmd_buf, "dump tm map", 11) == 0) {
+		hclge_dbg_dump_tm_map(hdev, cmd_buf);
+	} else if (strncmp(cmd_buf, "dump tm", 7) == 0) {
+		hclge_dbg_dump_tm(hdev);
+	} else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) {
+		hclge_dbg_dump_qos_pause_cfg(hdev);
+	} else if (strncmp(cmd_buf, "dump qos pri map", 16) == 0) {
+		hclge_dbg_dump_qos_pri_map(hdev);
+	} else if (strncmp(cmd_buf, "dump qos buf cfg", 16) == 0) {
+		hclge_dbg_dump_qos_buf_cfg(hdev);
+	} else if (strncmp(cmd_buf, "dump mng tbl", 12) == 0) {
+		hclge_dbg_dump_mng_table(hdev);
+	} else if (strncmp(cmd_buf, "dump reg", 8) == 0) {
+		hclge_dbg_dump_reg_cmd(hdev, cmd_buf);
+	} else {
+		dev_info(&hdev->pdev->dev, "unknown command\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
new file mode 100644
index 000000000000..d055fda41775
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h
@@ -0,0 +1,713 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018-2019 Hisilicon Limited. */
+
+#ifndef __HCLGE_DEBUGFS_H
+#define __HCLGE_DEBUGFS_H
+
+#define HCLGE_DBG_BUF_LEN	   256
+#define HCLGE_DBG_MNG_TBL_MAX	   64
+
+#define HCLGE_DBG_MNG_VLAN_MASK_B  BIT(0)
+#define HCLGE_DBG_MNG_MAC_MASK_B   BIT(1)
+#define HCLGE_DBG_MNG_ETHER_MASK_B BIT(2)
+#define HCLGE_DBG_MNG_E_TYPE_B	   BIT(11)
+#define HCLGE_DBG_MNG_DROP_B	   BIT(13)
+#define HCLGE_DBG_MNG_VLAN_TAG	   0x0FFF
+#define HCLGE_DBG_MNG_PF_ID	   0x0007
+#define HCLGE_DBG_MNG_VF_ID	   0x00FF
+
+/* Get DFX BD number offset */
+#define HCLGE_DBG_DFX_BIOS_OFFSET  1
+#define HCLGE_DBG_DFX_SSU_0_OFFSET 2
+#define HCLGE_DBG_DFX_SSU_1_OFFSET 3
+#define HCLGE_DBG_DFX_IGU_OFFSET   4
+#define HCLGE_DBG_DFX_RPU_0_OFFSET 5
+
+#define HCLGE_DBG_DFX_RPU_1_OFFSET 6
+#define HCLGE_DBG_DFX_NCSI_OFFSET  7
+#define HCLGE_DBG_DFX_RTC_OFFSET   8
+#define HCLGE_DBG_DFX_PPP_OFFSET   9
+#define HCLGE_DBG_DFX_RCB_OFFSET   10
+#define HCLGE_DBG_DFX_TQP_OFFSET   11
+
+#define HCLGE_DBG_DFX_SSU_2_OFFSET 12
+
+#pragma pack(1)
+
+struct hclge_qos_pri_map_cmd {
+	u8 pri0_tc  : 4,
+	   pri1_tc  : 4;
+	u8 pri2_tc  : 4,
+	   pri3_tc  : 4;
+	u8 pri4_tc  : 4,
+	   pri5_tc  : 4;
+	u8 pri6_tc  : 4,
+	   pri7_tc  : 4;
+	u8 vlan_pri : 4,
+	   rev	    : 4;
+};
+
+struct hclge_dbg_bitmap_cmd {
+	union {
+		u8 bitmap;
+		struct {
+			u8 bit0 : 1,
+			   bit1 : 1,
+			   bit2 : 1,
+			   bit3 : 1,
+			   bit4 : 1,
+			   bit5 : 1,
+			   bit6 : 1,
+			   bit7 : 1;
+		};
+	};
+};
+
+struct hclge_dbg_dfx_message {
+	int flag;
+	char message[60];
+};
+
+#pragma pack()
+
+static struct hclge_dbg_dfx_message hclge_dbg_bios_common_reg[] = {
+	{false, "Reserved"},
+	{true,	"BP_CPU_STATE"},
+	{true,	"DFX_MSIX_INFO_NIC_0"},
+	{true,	"DFX_MSIX_INFO_NIC_1"},
+	{true,	"DFX_MSIX_INFO_NIC_2"},
+	{true,	"DFX_MSIX_INFO_NIC_3"},
+
+	{true,	"DFX_MSIX_INFO_ROC_0"},
+	{true,	"DFX_MSIX_INFO_ROC_1"},
+	{true,	"DFX_MSIX_INFO_ROC_2"},
+	{true,	"DFX_MSIX_INFO_ROC_3"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_0[] = {
+	{false, "Reserved"},
+	{true,	"SSU_ETS_PORT_STATUS"},
+	{true,	"SSU_ETS_TCG_STATUS"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{true,	"SSU_BP_STATUS_0"},
+
+	{true,	"SSU_BP_STATUS_1"},
+	{true,	"SSU_BP_STATUS_2"},
+	{true,	"SSU_BP_STATUS_3"},
+	{true,	"SSU_BP_STATUS_4"},
+	{true,	"SSU_BP_STATUS_5"},
+	{true,	"SSU_MAC_TX_PFC_IND"},
+
+	{true,	"MAC_SSU_RX_PFC_IND"},
+	{true,	"BTMP_AGEING_ST_B0"},
+	{true,	"BTMP_AGEING_ST_B1"},
+	{true,	"BTMP_AGEING_ST_B2"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"FULL_DROP_NUM"},
+	{true,	"PART_DROP_NUM"},
+	{true,	"PPP_KEY_DROP_NUM"},
+	{true,	"PPP_RLT_DROP_NUM"},
+	{true,	"LO_PRI_UNICAST_RLT_DROP_NUM"},
+	{true,	"HI_PRI_MULTICAST_RLT_DROP_NUM"},
+
+	{true,	"LO_PRI_MULTICAST_RLT_DROP_NUM"},
+	{true,	"NCSI_PACKET_CURR_BUFFER_CNT"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK0"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK1"},
+	{true,	"BTMP_AGEING_RLS_CNT_BANK2"},
+	{true,	"SSU_MB_RD_RLT_DROP_CNT"},
+
+	{true,	"SSU_PPP_MAC_KEY_NUM_L"},
+	{true,	"SSU_PPP_MAC_KEY_NUM_H"},
+	{true,	"SSU_PPP_HOST_KEY_NUM_L"},
+	{true,	"SSU_PPP_HOST_KEY_NUM_H"},
+	{true,	"PPP_SSU_MAC_RLT_NUM_L"},
+	{true,	"PPP_SSU_MAC_RLT_NUM_H"},
+
+	{true,	"PPP_SSU_HOST_RLT_NUM_L"},
+	{true,	"PPP_SSU_HOST_RLT_NUM_H"},
+	{true,	"NCSI_RX_PACKET_IN_CNT_L"},
+	{true,	"NCSI_RX_PACKET_IN_CNT_H"},
+	{true,	"NCSI_TX_PACKET_OUT_CNT_L"},
+	{true,	"NCSI_TX_PACKET_OUT_CNT_H"},
+
+	{true,	"SSU_KEY_DROP_NUM"},
+	{true,	"MB_UNCOPY_NUM"},
+	{true,	"RX_OQ_DROP_PKT_CNT"},
+	{true,	"TX_OQ_DROP_PKT_CNT"},
+	{true,	"BANK_UNBALANCE_DROP_CNT"},
+	{true,	"BANK_UNBALANCE_RX_DROP_CNT"},
+
+	{true,	"NIC_L2_ERR_DROP_PKT_CNT"},
+	{true,	"ROC_L2_ERR_DROP_PKT_CNT"},
+	{true,	"NIC_L2_ERR_DROP_PKT_CNT_RX"},
+	{true,	"ROC_L2_ERR_DROP_PKT_CNT_RX"},
+	{true,	"RX_OQ_GLB_DROP_PKT_CNT"},
+	{false, "Reserved"},
+
+	{true,	"LO_PRI_UNICAST_CUR_CNT"},
+	{true,	"HI_PRI_MULTICAST_CUR_CNT"},
+	{true,	"LO_PRI_MULTICAST_CUR_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_1[] = {
+	{true,	"prt_id"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_0"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_1"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_2"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_3"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_4"},
+
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_5"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_6"},
+	{true,	"PACKET_TC_CURR_BUFFER_CNT_7"},
+	{true,	"PACKET_CURR_BUFFER_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"RX_PACKET_IN_CNT_L"},
+	{true,	"RX_PACKET_IN_CNT_H"},
+	{true,	"RX_PACKET_OUT_CNT_L"},
+	{true,	"RX_PACKET_OUT_CNT_H"},
+	{true,	"TX_PACKET_IN_CNT_L"},
+	{true,	"TX_PACKET_IN_CNT_H"},
+
+	{true,	"TX_PACKET_OUT_CNT_L"},
+	{true,	"TX_PACKET_OUT_CNT_H"},
+	{true,	"ROC_RX_PACKET_IN_CNT_L"},
+	{true,	"ROC_RX_PACKET_IN_CNT_H"},
+	{true,	"ROC_TX_PACKET_OUT_CNT_L"},
+	{true,	"ROC_TX_PACKET_OUT_CNT_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_0_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_0_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_1_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_1_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_2_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_2_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_3_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_3_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_4_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_4_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_5_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_5_H"},
+
+	{true,	"RX_PACKET_TC_IN_CNT_6_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_6_H"},
+	{true,	"RX_PACKET_TC_IN_CNT_7_L"},
+	{true,	"RX_PACKET_TC_IN_CNT_7_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_0_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_0_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_1_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_1_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_2_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_2_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_3_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_3_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_4_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_4_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_5_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_5_H"},
+	{true,	"RX_PACKET_TC_OUT_CNT_6_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_6_H"},
+
+	{true,	"RX_PACKET_TC_OUT_CNT_7_L"},
+	{true,	"RX_PACKET_TC_OUT_CNT_7_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_0_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_0_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_1_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_1_H"},
+
+	{true,	"TX_PACKET_TC_IN_CNT_2_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_2_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_3_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_3_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_4_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_4_H"},
+
+	{true,	"TX_PACKET_TC_IN_CNT_5_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_5_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_6_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_6_H"},
+	{true,	"TX_PACKET_TC_IN_CNT_7_L"},
+	{true,	"TX_PACKET_TC_IN_CNT_7_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_0_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_0_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_1_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_1_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_2_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_2_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_3_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_3_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_4_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_4_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_5_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_5_H"},
+
+	{true,	"TX_PACKET_TC_OUT_CNT_6_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_6_H"},
+	{true,	"TX_PACKET_TC_OUT_CNT_7_L"},
+	{true,	"TX_PACKET_TC_OUT_CNT_7_H"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ssu_reg_2[] = {
+	{true,	"OQ_INDEX"},
+	{true,	"QUEUE_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_igu_egu_reg[] = {
+	{true,	"prt_id"},
+	{true,	"IGU_RX_ERR_PKT"},
+	{true,	"IGU_RX_NO_SOF_PKT"},
+	{true,	"EGU_TX_1588_SHORT_PKT"},
+	{true,	"EGU_TX_1588_PKT"},
+	{true,	"EGU_TX_ERR_PKT"},
+
+	{true,	"IGU_RX_OUT_L2_PKT"},
+	{true,	"IGU_RX_OUT_L3_PKT"},
+	{true,	"IGU_RX_OUT_L4_PKT"},
+	{true,	"IGU_RX_IN_L2_PKT"},
+	{true,	"IGU_RX_IN_L3_PKT"},
+	{true,	"IGU_RX_IN_L4_PKT"},
+
+	{true,	"IGU_RX_EL3E_PKT"},
+	{true,	"IGU_RX_EL4E_PKT"},
+	{true,	"IGU_RX_L3E_PKT"},
+	{true,	"IGU_RX_L4E_PKT"},
+	{true,	"IGU_RX_ROCEE_PKT"},
+	{true,	"IGU_RX_OUT_UDP0_PKT"},
+
+	{true,	"IGU_RX_IN_UDP0_PKT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"IGU_RX_OVERSIZE_PKT_L"},
+	{true,	"IGU_RX_OVERSIZE_PKT_H"},
+	{true,	"IGU_RX_UNDERSIZE_PKT_L"},
+	{true,	"IGU_RX_UNDERSIZE_PKT_H"},
+	{true,	"IGU_RX_OUT_ALL_PKT_L"},
+	{true,	"IGU_RX_OUT_ALL_PKT_H"},
+
+	{true,	"IGU_TX_OUT_ALL_PKT_L"},
+	{true,	"IGU_TX_OUT_ALL_PKT_H"},
+	{true,	"IGU_RX_UNI_PKT_L"},
+	{true,	"IGU_RX_UNI_PKT_H"},
+	{true,	"IGU_RX_MULTI_PKT_L"},
+	{true,	"IGU_RX_MULTI_PKT_H"},
+
+	{true,	"IGU_RX_BROAD_PKT_L"},
+	{true,	"IGU_RX_BROAD_PKT_H"},
+	{true,	"EGU_TX_OUT_ALL_PKT_L"},
+	{true,	"EGU_TX_OUT_ALL_PKT_H"},
+	{true,	"EGU_TX_UNI_PKT_L"},
+	{true,	"EGU_TX_UNI_PKT_H"},
+
+	{true,	"EGU_TX_MULTI_PKT_L"},
+	{true,	"EGU_TX_MULTI_PKT_H"},
+	{true,	"EGU_TX_BROAD_PKT_L"},
+	{true,	"EGU_TX_BROAD_PKT_H"},
+	{true,	"IGU_TX_KEY_NUM_L"},
+	{true,	"IGU_TX_KEY_NUM_H"},
+
+	{true,	"IGU_RX_NON_TUN_PKT_L"},
+	{true,	"IGU_RX_NON_TUN_PKT_H"},
+	{true,	"IGU_RX_TUN_PKT_L"},
+	{true,	"IGU_RX_TUN_PKT_H"},
+	{false,	"Reserved"},
+	{false,	"Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_0[] = {
+	{true, "tc_queue_num"},
+	{true, "FSM_DFX_ST0"},
+	{true, "FSM_DFX_ST1"},
+	{true, "RPU_RX_PKT_DROP_CNT"},
+	{true, "BUF_WAIT_TIMEOUT"},
+	{true, "BUF_WAIT_TIMEOUT_QID"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rpu_reg_1[] = {
+	{false, "Reserved"},
+	{true,	"FIFO_DFX_ST0"},
+	{true,	"FIFO_DFX_ST1"},
+	{true,	"FIFO_DFX_ST2"},
+	{true,	"FIFO_DFX_ST3"},
+	{true,	"FIFO_DFX_ST4"},
+
+	{true,	"FIFO_DFX_ST5"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ncsi_reg[] = {
+	{false, "Reserved"},
+	{true,	"NCSI_EGU_TX_FIFO_STS"},
+	{true,	"NCSI_PAUSE_STATUS"},
+	{true,	"NCSI_RX_CTRL_DMAC_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_SMAC_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_CKS_ERR_CNT"},
+
+	{true,	"NCSI_RX_CTRL_PKT_CNT"},
+	{true,	"NCSI_RX_PT_DMAC_ERR_CNT"},
+	{true,	"NCSI_RX_PT_SMAC_ERR_CNT"},
+	{true,	"NCSI_RX_PT_PKT_CNT"},
+	{true,	"NCSI_RX_FCS_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_DMAC_ERR_CNT"},
+
+	{true,	"NCSI_TX_CTRL_SMAC_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_PKT_CNT"},
+	{true,	"NCSI_TX_PT_DMAC_ERR_CNT"},
+	{true,	"NCSI_TX_PT_SMAC_ERR_CNT"},
+	{true,	"NCSI_TX_PT_PKT_CNT"},
+	{true,	"NCSI_TX_PT_PKT_TRUNC_CNT"},
+
+	{true,	"NCSI_TX_PT_PKT_ERR_CNT"},
+	{true,	"NCSI_TX_CTRL_PKT_ERR_CNT"},
+	{true,	"NCSI_RX_CTRL_PKT_TRUNC_CNT"},
+	{true,	"NCSI_RX_CTRL_PKT_CFLIT_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"NCSI_MAC_RX_OCTETS_OK"},
+	{true,	"NCSI_MAC_RX_OCTETS_BAD"},
+	{true,	"NCSI_MAC_RX_UC_PKTS"},
+	{true,	"NCSI_MAC_RX_MC_PKTS"},
+	{true,	"NCSI_MAC_RX_BC_PKTS"},
+	{true,	"NCSI_MAC_RX_PKTS_64OCTETS"},
+
+	{true,	"NCSI_MAC_RX_PKTS_65TO127OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_128TO255OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_255TO511OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_512TO1023OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_1024TO1518OCTETS"},
+	{true,	"NCSI_MAC_RX_PKTS_1519TOMAXOCTETS"},
+
+	{true,	"NCSI_MAC_RX_FCS_ERRORS"},
+	{true,	"NCSI_MAC_RX_LONG_ERRORS"},
+	{true,	"NCSI_MAC_RX_JABBER_ERRORS"},
+	{true,	"NCSI_MAC_RX_RUNT_ERR_CNT"},
+	{true,	"NCSI_MAC_RX_SHORT_ERR_CNT"},
+	{true,	"NCSI_MAC_RX_FILT_PKT_CNT"},
+
+	{true,	"NCSI_MAC_RX_OCTETS_TOTAL_FILT"},
+	{true,	"NCSI_MAC_TX_OCTETS_OK"},
+	{true,	"NCSI_MAC_TX_OCTETS_BAD"},
+	{true,	"NCSI_MAC_TX_UC_PKTS"},
+	{true,	"NCSI_MAC_TX_MC_PKTS"},
+	{true,	"NCSI_MAC_TX_BC_PKTS"},
+
+	{true,	"NCSI_MAC_TX_PKTS_64OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_65TO127OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_128TO255OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_256TO511OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_512TO1023OCTETS"},
+	{true,	"NCSI_MAC_TX_PKTS_1024TO1518OCTETS"},
+
+	{true,	"NCSI_MAC_TX_PKTS_1519TOMAXOCTETS"},
+	{true,	"NCSI_MAC_TX_UNDERRUN"},
+	{true,	"NCSI_MAC_TX_CRC_ERROR"},
+	{true,	"NCSI_MAC_TX_PAUSE_FRAMES"},
+	{true,	"NCSI_MAC_RX_PAD_PKTS"},
+	{true,	"NCSI_MAC_RX_PAUSE_FRAMES"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rtc_reg[] = {
+	{false, "Reserved"},
+	{true,	"LGE_IGU_AFIFO_DFX_0"},
+	{true,	"LGE_IGU_AFIFO_DFX_1"},
+	{true,	"LGE_IGU_AFIFO_DFX_2"},
+	{true,	"LGE_IGU_AFIFO_DFX_3"},
+	{true,	"LGE_IGU_AFIFO_DFX_4"},
+
+	{true,	"LGE_IGU_AFIFO_DFX_5"},
+	{true,	"LGE_IGU_AFIFO_DFX_6"},
+	{true,	"LGE_IGU_AFIFO_DFX_7"},
+	{true,	"LGE_EGU_AFIFO_DFX_0"},
+	{true,	"LGE_EGU_AFIFO_DFX_1"},
+	{true,	"LGE_EGU_AFIFO_DFX_2"},
+
+	{true,	"LGE_EGU_AFIFO_DFX_3"},
+	{true,	"LGE_EGU_AFIFO_DFX_4"},
+	{true,	"LGE_EGU_AFIFO_DFX_5"},
+	{true,	"LGE_EGU_AFIFO_DFX_6"},
+	{true,	"LGE_EGU_AFIFO_DFX_7"},
+	{true,	"CGE_IGU_AFIFO_DFX_0"},
+
+	{true,	"CGE_IGU_AFIFO_DFX_1"},
+	{true,	"CGE_EGU_AFIFO_DFX_0"},
+	{true,	"CGE_EGU_AFIFO_DFX_1"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_ppp_reg[] = {
+	{false, "Reserved"},
+	{true,	"DROP_FROM_PRT_PKT_CNT"},
+	{true,	"DROP_FROM_HOST_PKT_CNT"},
+	{true,	"DROP_TX_VLAN_PROC_CNT"},
+	{true,	"DROP_MNG_CNT"},
+	{true,	"DROP_FD_CNT"},
+
+	{true,	"DROP_NO_DST_CNT"},
+	{true,	"DROP_MC_MBID_FULL_CNT"},
+	{true,	"DROP_SC_FILTERED"},
+	{true,	"PPP_MC_DROP_PKT_CNT"},
+	{true,	"DROP_PT_CNT"},
+	{true,	"DROP_MAC_ANTI_SPOOF_CNT"},
+
+	{true,	"DROP_IG_VFV_CNT"},
+	{true,	"DROP_IG_PRTV_CNT"},
+	{true,	"DROP_CNM_PFC_PAUSE_CNT"},
+	{true,	"DROP_TORUS_TC_CNT"},
+	{true,	"DROP_TORUS_LPBK_CNT"},
+	{true,	"PPP_HFS_STS"},
+
+	{true,	"PPP_MC_RSLT_STS"},
+	{true,	"PPP_P3U_STS"},
+	{true,	"PPP_RSLT_DESCR_STS"},
+	{true,	"PPP_UMV_STS_0"},
+	{true,	"PPP_UMV_STS_1"},
+	{true,	"PPP_VFV_STS"},
+
+	{true,	"PPP_GRO_KEY_CNT"},
+	{true,	"PPP_GRO_INFO_CNT"},
+	{true,	"PPP_GRO_DROP_CNT"},
+	{true,	"PPP_GRO_OUT_CNT"},
+	{true,	"PPP_GRO_KEY_MATCH_DATA_CNT"},
+	{true,	"PPP_GRO_KEY_MATCH_TCAM_CNT"},
+
+	{true,	"PPP_GRO_INFO_MATCH_CNT"},
+	{true,	"PPP_GRO_FREE_ENTRY_CNT"},
+	{true,	"PPP_GRO_INNER_DFX_SIGNAL"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+
+	{true,	"GET_RX_PKT_CNT_L"},
+	{true,	"GET_RX_PKT_CNT_H"},
+	{true,	"GET_TX_PKT_CNT_L"},
+	{true,	"GET_TX_PKT_CNT_H"},
+	{true,	"SEND_UC_PRT2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2HOST_PKT_CNT_H"},
+
+	{true,	"SEND_UC_PRT2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2PRT_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2HOST_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2PRT_PKT_CNT_H"},
+
+	{true,	"SEND_MC_FROM_PRT_CNT_L"},
+	{true,	"SEND_MC_FROM_PRT_CNT_H"},
+	{true,	"SEND_MC_FROM_HOST_CNT_L"},
+	{true,	"SEND_MC_FROM_HOST_CNT_H"},
+	{true,	"SSU_MC_RD_CNT_L"},
+	{true,	"SSU_MC_RD_CNT_H"},
+
+	{true,	"SSU_MC_DROP_CNT_L"},
+	{true,	"SSU_MC_DROP_CNT_H"},
+	{true,	"SSU_MC_RD_PKT_CNT_L"},
+	{true,	"SSU_MC_RD_PKT_CNT_H"},
+	{true,	"PPP_MC_2HOST_PKT_CNT_L"},
+	{true,	"PPP_MC_2HOST_PKT_CNT_H"},
+
+	{true,	"PPP_MC_2PRT_PKT_CNT_L"},
+	{true,	"PPP_MC_2PRT_PKT_CNT_H"},
+	{true,	"NTSNOS_PKT_CNT_L"},
+	{true,	"NTSNOS_PKT_CNT_H"},
+	{true,	"NTUP_PKT_CNT_L"},
+	{true,	"NTUP_PKT_CNT_H"},
+
+	{true,	"NTLCL_PKT_CNT_L"},
+	{true,	"NTLCL_PKT_CNT_H"},
+	{true,	"NTTGT_PKT_CNT_L"},
+	{true,	"NTTGT_PKT_CNT_H"},
+	{true,	"RTNS_PKT_CNT_L"},
+	{true,	"RTNS_PKT_CNT_H"},
+
+	{true,	"RTLPBK_PKT_CNT_L"},
+	{true,	"RTLPBK_PKT_CNT_H"},
+	{true,	"NR_PKT_CNT_L"},
+	{true,	"NR_PKT_CNT_H"},
+	{true,	"RR_PKT_CNT_L"},
+	{true,	"RR_PKT_CNT_H"},
+
+	{true,	"MNG_TBL_HIT_CNT_L"},
+	{true,	"MNG_TBL_HIT_CNT_H"},
+	{true,	"FD_TBL_HIT_CNT_L"},
+	{true,	"FD_TBL_HIT_CNT_H"},
+	{true,	"FD_LKUP_CNT_L"},
+	{true,	"FD_LKUP_CNT_H"},
+
+	{true,	"BC_HIT_CNT_L"},
+	{true,	"BC_HIT_CNT_H"},
+	{true,	"UM_TBL_UC_HIT_CNT_L"},
+	{true,	"UM_TBL_UC_HIT_CNT_H"},
+	{true,	"UM_TBL_MC_HIT_CNT_L"},
+	{true,	"UM_TBL_MC_HIT_CNT_H"},
+
+	{true,	"UM_TBL_VMDQ1_HIT_CNT_L"},
+	{true,	"UM_TBL_VMDQ1_HIT_CNT_H"},
+	{true,	"MTA_TBL_HIT_CNT_L"},
+	{true,	"MTA_TBL_HIT_CNT_H"},
+	{true,	"FWD_BONDING_HIT_CNT_L"},
+	{true,	"FWD_BONDING_HIT_CNT_H"},
+
+	{true,	"PROMIS_TBL_HIT_CNT_L"},
+	{true,	"PROMIS_TBL_HIT_CNT_H"},
+	{true,	"GET_TUNL_PKT_CNT_L"},
+	{true,	"GET_TUNL_PKT_CNT_H"},
+	{true,	"GET_BMC_PKT_CNT_L"},
+	{true,	"GET_BMC_PKT_CNT_H"},
+
+	{true,	"SEND_UC_PRT2BMC_PKT_CNT_L"},
+	{true,	"SEND_UC_PRT2BMC_PKT_CNT_H"},
+	{true,	"SEND_UC_HOST2BMC_PKT_CNT_L"},
+	{true,	"SEND_UC_HOST2BMC_PKT_CNT_H"},
+	{true,	"SEND_UC_BMC2HOST_PKT_CNT_L"},
+	{true,	"SEND_UC_BMC2HOST_PKT_CNT_H"},
+
+	{true,	"SEND_UC_BMC2PRT_PKT_CNT_L"},
+	{true,	"SEND_UC_BMC2PRT_PKT_CNT_H"},
+	{true,	"PPP_MC_2BMC_PKT_CNT_L"},
+	{true,	"PPP_MC_2BMC_PKT_CNT_H"},
+	{true,	"VLAN_MIRR_CNT_L"},
+	{true,	"VLAN_MIRR_CNT_H"},
+
+	{true,	"IG_MIRR_CNT_L"},
+	{true,	"IG_MIRR_CNT_H"},
+	{true,	"EG_MIRR_CNT_L"},
+	{true,	"EG_MIRR_CNT_H"},
+	{true,	"RX_DEFAULT_HOST_HIT_CNT_L"},
+	{true,	"RX_DEFAULT_HOST_HIT_CNT_H"},
+
+	{true,	"LAN_PAIR_CNT_L"},
+	{true,	"LAN_PAIR_CNT_H"},
+	{true,	"UM_TBL_MC_HIT_PKT_CNT_L"},
+	{true,	"UM_TBL_MC_HIT_PKT_CNT_H"},
+	{true,	"MTA_TBL_HIT_PKT_CNT_L"},
+	{true,	"MTA_TBL_HIT_PKT_CNT_H"},
+
+	{true,	"PROMIS_TBL_HIT_PKT_CNT_L"},
+	{true,	"PROMIS_TBL_HIT_PKT_CNT_H"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_rcb_reg[] = {
+	{false, "Reserved"},
+	{true,	"FSM_DFX_ST0"},
+	{true,	"FSM_DFX_ST1"},
+	{true,	"FSM_DFX_ST2"},
+	{true,	"FIFO_DFX_ST0"},
+	{true,	"FIFO_DFX_ST1"},
+
+	{true,	"FIFO_DFX_ST2"},
+	{true,	"FIFO_DFX_ST3"},
+	{true,	"FIFO_DFX_ST4"},
+	{true,	"FIFO_DFX_ST5"},
+	{true,	"FIFO_DFX_ST6"},
+	{true,	"FIFO_DFX_ST7"},
+
+	{true,	"FIFO_DFX_ST8"},
+	{true,	"FIFO_DFX_ST9"},
+	{true,	"FIFO_DFX_ST10"},
+	{true,	"FIFO_DFX_ST11"},
+	{true,	"Q_CREDIT_VLD_0"},
+	{true,	"Q_CREDIT_VLD_1"},
+
+	{true,	"Q_CREDIT_VLD_2"},
+	{true,	"Q_CREDIT_VLD_3"},
+	{true,	"Q_CREDIT_VLD_4"},
+	{true,	"Q_CREDIT_VLD_5"},
+	{true,	"Q_CREDIT_VLD_6"},
+	{true,	"Q_CREDIT_VLD_7"},
+
+	{true,	"Q_CREDIT_VLD_8"},
+	{true,	"Q_CREDIT_VLD_9"},
+	{true,	"Q_CREDIT_VLD_10"},
+	{true,	"Q_CREDIT_VLD_11"},
+	{true,	"Q_CREDIT_VLD_12"},
+	{true,	"Q_CREDIT_VLD_13"},
+
+	{true,	"Q_CREDIT_VLD_14"},
+	{true,	"Q_CREDIT_VLD_15"},
+	{true,	"Q_CREDIT_VLD_16"},
+	{true,	"Q_CREDIT_VLD_17"},
+	{true,	"Q_CREDIT_VLD_18"},
+	{true,	"Q_CREDIT_VLD_19"},
+
+	{true,	"Q_CREDIT_VLD_20"},
+	{true,	"Q_CREDIT_VLD_21"},
+	{true,	"Q_CREDIT_VLD_22"},
+	{true,	"Q_CREDIT_VLD_23"},
+	{true,	"Q_CREDIT_VLD_24"},
+	{true,	"Q_CREDIT_VLD_25"},
+
+	{true,	"Q_CREDIT_VLD_26"},
+	{true,	"Q_CREDIT_VLD_27"},
+	{true,	"Q_CREDIT_VLD_28"},
+	{true,	"Q_CREDIT_VLD_29"},
+	{true,	"Q_CREDIT_VLD_30"},
+	{true,	"Q_CREDIT_VLD_31"},
+
+	{true,	"GRO_BD_SERR_CNT"},
+	{true,	"GRO_CONTEXT_SERR_CNT"},
+	{true,	"RX_STASH_CFG_SERR_CNT"},
+	{true,	"AXI_RD_FBD_SERR_CNT"},
+	{true,	"GRO_BD_MERR_CNT"},
+	{true,	"GRO_CONTEXT_MERR_CNT"},
+
+	{true,	"RX_STASH_CFG_MERR_CNT"},
+	{true,	"AXI_RD_FBD_MERR_CNT"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+	{false, "Reserved"},
+};
+
+static struct hclge_dbg_dfx_message hclge_dbg_tqp_reg[] = {
+	{true, "q_num"},
+	{true, "RCB_CFG_RX_RING_TAIL"},
+	{true, "RCB_CFG_RX_RING_HEAD"},
+	{true, "RCB_CFG_RX_RING_FBDNUM"},
+	{true, "RCB_CFG_RX_RING_OFFSET"},
+	{true, "RCB_CFG_RX_RING_FBDOFFSET"},
+
+	{true, "RCB_CFG_RX_RING_PKTNUM_RECORD"},
+	{true, "RCB_CFG_TX_RING_TAIL"},
+	{true, "RCB_CFG_TX_RING_HEAD"},
+	{true, "RCB_CFG_TX_RING_FBDNUM"},
+	{true, "RCB_CFG_TX_RING_OFFSET"},
+	{true, "RCB_CFG_TX_RING_EBDNUM"},
+};
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
index 123c37e653f3..1f52d11f77b5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
@@ -4,78 +4,39 @@
 #include "hclge_err.h"
 
 static const struct hclge_hw_error hclge_imp_tcm_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "imp_itcm0_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "imp_itcm0_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "imp_itcm1_ecc_1bit_err" },
 	{ .int_msk = BIT(3), .msg = "imp_itcm1_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "imp_itcm2_ecc_1bit_err" },
 	{ .int_msk = BIT(5), .msg = "imp_itcm2_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "imp_itcm3_ecc_1bit_err" },
 	{ .int_msk = BIT(7), .msg = "imp_itcm3_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "imp_dtcm0_mem0_ecc_1bit_err" },
 	{ .int_msk = BIT(9), .msg = "imp_dtcm0_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "imp_dtcm0_mem1_ecc_1bit_err" },
 	{ .int_msk = BIT(11), .msg = "imp_dtcm0_mem1_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "imp_dtcm1_mem0_ecc_1bit_err" },
 	{ .int_msk = BIT(13), .msg = "imp_dtcm1_mem0_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "imp_dtcm1_mem1_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "imp_dtcm1_mem1_ecc_mbit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_imp_itcm4_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "imp_itcm4_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "imp_itcm4_ecc_mbit_err" },
+	{ .int_msk = BIT(17), .msg = "imp_itcm4_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_cmdq_nic_mem_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "cmdq_nic_rx_depth_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "cmdq_nic_rx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "cmdq_nic_tx_depth_ecc_1bit_err" },
 	{ .int_msk = BIT(3), .msg = "cmdq_nic_tx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "cmdq_nic_rx_tail_ecc_1bit_err" },
 	{ .int_msk = BIT(5), .msg = "cmdq_nic_rx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "cmdq_nic_tx_tail_ecc_1bit_err" },
 	{ .int_msk = BIT(7), .msg = "cmdq_nic_tx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "cmdq_nic_rx_head_ecc_1bit_err" },
 	{ .int_msk = BIT(9), .msg = "cmdq_nic_rx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "cmdq_nic_tx_head_ecc_1bit_err" },
 	{ .int_msk = BIT(11), .msg = "cmdq_nic_tx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "cmdq_nic_rx_addr_ecc_1bit_err" },
 	{ .int_msk = BIT(13), .msg = "cmdq_nic_rx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "cmdq_nic_tx_addr_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "cmdq_nic_tx_addr_ecc_mbit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_cmdq_rocee_mem_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "cmdq_rocee_rx_depth_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "cmdq_rocee_tx_depth_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "cmdq_rocee_rx_tail_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "cmdq_rocee_tx_tail_ecc_1bit_err" },
-	{ .int_msk = BIT(7), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "cmdq_rocee_rx_head_ecc_1bit_err" },
-	{ .int_msk = BIT(9), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "cmdq_rocee_tx_head_ecc_1bit_err" },
-	{ .int_msk = BIT(11), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "cmdq_rocee_rx_addr_ecc_1bit_err" },
-	{ .int_msk = BIT(13), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "cmdq_rocee_tx_addr_ecc_1bit_err" },
-	{ .int_msk = BIT(15), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(17), .msg = "cmdq_rocee_rx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(19), .msg = "cmdq_rocee_tx_depth_ecc_mbit_err" },
+	{ .int_msk = BIT(21), .msg = "cmdq_rocee_rx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(23), .msg = "cmdq_rocee_tx_tail_ecc_mbit_err" },
+	{ .int_msk = BIT(25), .msg = "cmdq_rocee_rx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(27), .msg = "cmdq_rocee_tx_head_ecc_mbit_err" },
+	{ .int_msk = BIT(29), .msg = "cmdq_rocee_rx_addr_ecc_mbit_err" },
+	{ .int_msk = BIT(31), .msg = "cmdq_rocee_tx_addr_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
 static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
-	{ .int_msk = BIT(0), .msg = "tqp_int_cfg_even_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "tqp_int_cfg_odd_ecc_1bit_err" },
-	{ .int_msk = BIT(2), .msg = "tqp_int_ctrl_even_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "tqp_int_ctrl_odd_ecc_1bit_err" },
-	{ .int_msk = BIT(4), .msg = "tx_que_scan_int_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "rx_que_scan_int_ecc_1bit_err" },
 	{ .int_msk = BIT(6), .msg = "tqp_int_cfg_even_ecc_mbit_err" },
 	{ .int_msk = BIT(7), .msg = "tqp_int_cfg_odd_ecc_mbit_err" },
 	{ .int_msk = BIT(8), .msg = "tqp_int_ctrl_even_ecc_mbit_err" },
@@ -85,15 +46,19 @@ static const struct hclge_hw_error hclge_tqp_int_ecc_int[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_igu_com_err_int[] = {
+static const struct hclge_hw_error hclge_msix_sram_ecc_int[] = {
+	{ .int_msk = BIT(1), .msg = "msix_nic_ecc_mbit_err" },
+	{ .int_msk = BIT(3), .msg = "msix_rocee_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_igu_int[] = {
 	{ .int_msk = BIT(0), .msg = "igu_rx_buf0_ecc_mbit_err" },
-	{ .int_msk = BIT(1), .msg = "igu_rx_buf0_ecc_1bit_err" },
 	{ .int_msk = BIT(2), .msg = "igu_rx_buf1_ecc_mbit_err" },
-	{ .int_msk = BIT(3), .msg = "igu_rx_buf1_ecc_1bit_err" },
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_igu_egu_tnl_err_int[] = {
+static const struct hclge_hw_error hclge_igu_egu_tnl_int[] = {
 	{ .int_msk = BIT(0), .msg = "rx_buf_overflow" },
 	{ .int_msk = BIT(1), .msg = "rx_stp_fifo_overflow" },
 	{ .int_msk = BIT(2), .msg = "rx_stp_fifo_undeflow" },
@@ -104,58 +69,18 @@ static const struct hclge_hw_error hclge_igu_egu_tnl_err_int[] = {
 };
 
 static const struct hclge_hw_error hclge_ncsi_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "ncsi_tx_ecc_1bit_err" },
 	{ .int_msk = BIT(1), .msg = "ncsi_tx_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_ppp_mpf_int0[] = {
-	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_1bit_err" },
-	{ .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_1bit_err" },
-	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_1bit_err" },
-	{ .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_1bit_err" },
-	{ .int_msk = BIT(10), .msg = "rss_idt_mem2_ecc_1bit_err" },
-	{ .int_msk = BIT(11), .msg = "rss_idt_mem3_ecc_1bit_err" },
-	{ .int_msk = BIT(12), .msg = "rss_idt_mem4_ecc_1bit_err" },
-	{ .int_msk = BIT(13), .msg = "rss_idt_mem5_ecc_1bit_err" },
-	{ .int_msk = BIT(14), .msg = "rss_idt_mem6_ecc_1bit_err" },
-	{ .int_msk = BIT(15), .msg = "rss_idt_mem7_ecc_1bit_err" },
-	{ .int_msk = BIT(16), .msg = "rss_idt_mem8_ecc_1bit_err" },
-	{ .int_msk = BIT(17), .msg = "rss_idt_mem9_ecc_1bit_err" },
-	{ .int_msk = BIT(18), .msg = "rss_idt_mem10_ecc_1bit_err" },
-	{ .int_msk = BIT(19), .msg = "rss_idt_mem11_ecc_1bit_err" },
-	{ .int_msk = BIT(20), .msg = "rss_idt_mem12_ecc_1bit_err" },
-	{ .int_msk = BIT(21), .msg = "rss_idt_mem13_ecc_1bit_err" },
-	{ .int_msk = BIT(22), .msg = "rss_idt_mem14_ecc_1bit_err" },
-	{ .int_msk = BIT(23), .msg = "rss_idt_mem15_ecc_1bit_err" },
-	{ .int_msk = BIT(24), .msg = "port_vlan_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(25), .msg = "mcast_linear_table_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(26), .msg = "mcast_result_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(27),
-		.msg = "flow_director_ad_mem0_ecc_1bit_err" },
-	{ .int_msk = BIT(28),
-		.msg = "flow_director_ad_mem1_ecc_1bit_err" },
-	{ .int_msk = BIT(29),
-		.msg = "rx_vlan_tag_memory_ecc_1bit_err" },
-	{ .int_msk = BIT(30),
-		.msg = "Tx_UP_mapping_config_mem_ecc_1bit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_ppp_mpf_int1[] = {
+static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st1[] = {
 	{ .int_msk = BIT(0), .msg = "vf_vlan_ad_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(1), .msg = "umv_mcast_group_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(2), .msg = "umv_key_mem0_ecc_mbit_err" },
 	{ .int_msk = BIT(3), .msg = "umv_key_mem1_ecc_mbit_err" },
 	{ .int_msk = BIT(4), .msg = "umv_key_mem2_ecc_mbit_err" },
 	{ .int_msk = BIT(5), .msg = "umv_key_mem3_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_erre" },
+	{ .int_msk = BIT(6), .msg = "umv_ad_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(7), .msg = "rss_tc_mode_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(8), .msg = "rss_idt_mem0_ecc_mbit_err" },
 	{ .int_msk = BIT(9), .msg = "rss_idt_mem1_ecc_mbit_err" },
@@ -187,23 +112,13 @@ static const struct hclge_hw_error hclge_ppp_mpf_int1[] = {
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_ppp_pf_int[] = {
-	{ .int_msk = BIT(0), .msg = "Tx_vlan_tag_err" },
+static const struct hclge_hw_error hclge_ppp_pf_abnormal_int[] = {
+	{ .int_msk = BIT(0), .msg = "tx_vlan_tag_err" },
 	{ .int_msk = BIT(1), .msg = "rss_list_tc_unassigned_queue_err" },
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_ppp_mpf_int2[] = {
-	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_1bit_err" },
-	{ .int_msk = BIT(3), .msg = "FD_CN0_memory_ecc_1bit_err" },
-	{ .int_msk = BIT(4), .msg = "FD_CN1_memory_ecc_1bit_err" },
-	{ .int_msk = BIT(5), .msg = "GRO_AD_memory_ecc_1bit_err" },
-	{ /* sentinel */ }
-};
-
-static const struct hclge_hw_error hclge_ppp_mpf_int3[] = {
+static const struct hclge_hw_error hclge_ppp_mpf_abnormal_int_st3[] = {
 	{ .int_msk = BIT(0), .msg = "hfs_fifo_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(1), .msg = "rslt_descr_fifo_mem_ecc_mbit_err" },
 	{ .int_msk = BIT(2), .msg = "tx_vlan_tag_mem_ecc_mbit_err" },
@@ -213,145 +128,293 @@ static const struct hclge_hw_error hclge_ppp_mpf_int3[] = {
 	{ /* sentinel */ }
 };
 
-struct hclge_tm_sch_ecc_info {
-	const char *name;
-};
-
-static const struct hclge_tm_sch_ecc_info hclge_tm_sch_ecc_err[7][15] = {
-	{
-		{ .name = "QSET_QUEUE_CTRL:PRI_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPA_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPB_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRA_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRB_LEN TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPA_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPB_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRA_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRB_HPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:QS_LINKLIST TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPA_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:SPB_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRA_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:WRRB_TPTR TAB" },
-		{ .name = "QSET_QUEUE_CTRL:QS_DEFICITCNT TAB" },
-	},
-	{
-		{ .name = "ROCE_QUEUE_CTRL:QS_LEN TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QS_TPTR TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QS_HPTR TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QLINKLIST TAB" },
-		{ .name = "ROCE_QUEUE_CTRL:QCLEN TAB" },
-	},
-	{
-		{ .name = "NIC_QUEUE_CTRL:QS_LEN TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QS_TPTR TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QS_HPTR TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QLINKLIST TAB" },
-		{ .name = "NIC_QUEUE_CTRL:QCLEN TAB" },
-	},
-	{
-		{ .name = "RAM_CFG_CTRL:CSHAP TAB" },
-		{ .name = "RAM_CFG_CTRL:PSHAP TAB" },
-	},
-	{
-		{ .name = "SHAPER_CTRL:PSHAP TAB" },
-	},
-	{
-		{ .name = "MSCH_CTRL" },
-	},
-	{
-		{ .name = "TOP_CTRL" },
-	},
-};
-
-static const struct hclge_hw_error hclge_tm_sch_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "tm_sch_ecc_1bit_err" },
+static const struct hclge_hw_error hclge_tm_sch_rint[] = {
 	{ .int_msk = BIT(1), .msg = "tm_sch_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_empty_err" },
-	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_full_err" },
-	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_empty_err" },
+	{ .int_msk = BIT(2), .msg = "tm_sch_port_shap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(3), .msg = "tm_sch_port_shap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(4), .msg = "tm_sch_pg_pshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(5), .msg = "tm_sch_pg_pshap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(6), .msg = "tm_sch_pg_cshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(7), .msg = "tm_sch_pg_cshap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(8), .msg = "tm_sch_pri_pshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(9), .msg = "tm_sch_pri_pshap_sub_fifo_rd_err" },
+	{ .int_msk = BIT(10), .msg = "tm_sch_pri_cshap_sub_fifo_wr_err" },
+	{ .int_msk = BIT(11), .msg = "tm_sch_pri_cshap_sub_fifo_rd_err" },
 	{ .int_msk = BIT(12),
-	  .msg = "tm_sch_port_shap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_port_shap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(13),
-	  .msg = "tm_sch_port_shap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_port_shap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(14),
-	  .msg = "tm_sch_pg_pshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pg_pshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(15),
-	  .msg = "tm_sch_pg_pshap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pg_pshap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(16),
-	  .msg = "tm_sch_pg_cshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pg_cshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(17),
-	  .msg = "tm_sch_pg_cshap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pg_cshap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(18),
-	  .msg = "tm_sch_pri_pshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pri_pshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(19),
-	  .msg = "tm_sch_pri_pshap_offset_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pri_pshap_offset_fifo_rd_err" },
 	{ .int_msk = BIT(20),
-	  .msg = "tm_sch_pri_cshap_offset_fifo_wr_full_err" },
+	  .msg = "tm_sch_pri_cshap_offset_fifo_wr_err" },
 	{ .int_msk = BIT(21),
-	  .msg = "tm_sch_pri_cshap_offset_fifo_rd_empty_err" },
-	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_full_err" },
-	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_empty_err" },
-	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_full_err" },
-	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_empty_err" },
-	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_full_err" },
-	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_empty_err" },
-	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_full_err" },
-	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_empty_err" },
-	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_full_err" },
-	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_empty_err" },
+	  .msg = "tm_sch_pri_cshap_offset_fifo_rd_err" },
+	{ .int_msk = BIT(22), .msg = "tm_sch_rq_fifo_wr_err" },
+	{ .int_msk = BIT(23), .msg = "tm_sch_rq_fifo_rd_err" },
+	{ .int_msk = BIT(24), .msg = "tm_sch_nq_fifo_wr_err" },
+	{ .int_msk = BIT(25), .msg = "tm_sch_nq_fifo_rd_err" },
+	{ .int_msk = BIT(26), .msg = "tm_sch_roce_up_fifo_wr_err" },
+	{ .int_msk = BIT(27), .msg = "tm_sch_roce_up_fifo_rd_err" },
+	{ .int_msk = BIT(28), .msg = "tm_sch_rcb_byte_fifo_wr_err" },
+	{ .int_msk = BIT(29), .msg = "tm_sch_rcb_byte_fifo_rd_err" },
+	{ .int_msk = BIT(30), .msg = "tm_sch_ssu_byte_fifo_wr_err" },
+	{ .int_msk = BIT(31), .msg = "tm_sch_ssu_byte_fifo_rd_err" },
 	{ /* sentinel */ }
 };
 
-static const struct hclge_hw_error hclge_qcn_ecc_err_int[] = {
-	{ .int_msk = BIT(0), .msg = "qcn_byte_mem_ecc_1bit_err" },
+static const struct hclge_hw_error hclge_qcn_fifo_rint[] = {
+	{ .int_msk = BIT(0), .msg = "qcn_shap_gp0_sch_fifo_rd_err" },
+	{ .int_msk = BIT(1), .msg = "qcn_shap_gp0_sch_fifo_wr_err" },
+	{ .int_msk = BIT(2), .msg = "qcn_shap_gp1_sch_fifo_rd_err" },
+	{ .int_msk = BIT(3), .msg = "qcn_shap_gp1_sch_fifo_wr_err" },
+	{ .int_msk = BIT(4), .msg = "qcn_shap_gp2_sch_fifo_rd_err" },
+	{ .int_msk = BIT(5), .msg = "qcn_shap_gp2_sch_fifo_wr_err" },
+	{ .int_msk = BIT(6), .msg = "qcn_shap_gp3_sch_fifo_rd_err" },
+	{ .int_msk = BIT(7), .msg = "qcn_shap_gp3_sch_fifo_wr_err" },
+	{ .int_msk = BIT(8), .msg = "qcn_shap_gp0_offset_fifo_rd_err" },
+	{ .int_msk = BIT(9), .msg = "qcn_shap_gp0_offset_fifo_wr_err" },
+	{ .int_msk = BIT(10), .msg = "qcn_shap_gp1_offset_fifo_rd_err" },
+	{ .int_msk = BIT(11), .msg = "qcn_shap_gp1_offset_fifo_wr_err" },
+	{ .int_msk = BIT(12), .msg = "qcn_shap_gp2_offset_fifo_rd_err" },
+	{ .int_msk = BIT(13), .msg = "qcn_shap_gp2_offset_fifo_wr_err" },
+	{ .int_msk = BIT(14), .msg = "qcn_shap_gp3_offset_fifo_rd_err" },
+	{ .int_msk = BIT(15), .msg = "qcn_shap_gp3_offset_fifo_wr_err" },
+	{ .int_msk = BIT(16), .msg = "qcn_byte_info_fifo_rd_err" },
+	{ .int_msk = BIT(17), .msg = "qcn_byte_info_fifo_wr_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_qcn_ecc_rint[] = {
 	{ .int_msk = BIT(1), .msg = "qcn_byte_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(2), .msg = "qcn_time_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(3), .msg = "qcn_time_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(4), .msg = "qcn_fb_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(5), .msg = "qcn_fb_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(6), .msg = "qcn_link_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(7), .msg = "qcn_link_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(8), .msg = "qcn_rate_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(9), .msg = "qcn_rate_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(10), .msg = "qcn_tmplt_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(11), .msg = "qcn_tmplt_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(12), .msg = "qcn_shap_cfg_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(13), .msg = "qcn_shap_cfg_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(14), .msg = "qcn_gp0_barrel_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(15), .msg = "qcn_gp0_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(16), .msg = "qcn_gp1_barrel_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(17), .msg = "qcn_gp1_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(18), .msg = "qcn_gp2_barrel_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(19), .msg = "qcn_gp2_barrel_mem_ecc_mbit_err" },
-	{ .int_msk = BIT(20), .msg = "qcn_gp3_barral_mem_ecc_1bit_err" },
 	{ .int_msk = BIT(21), .msg = "qcn_gp3_barral_mem_ecc_mbit_err" },
 	{ /* sentinel */ }
 };
 
-static void hclge_log_error(struct device *dev,
-			    const struct hclge_hw_error *err_list,
+static const struct hclge_hw_error hclge_mac_afifo_tnl_int[] = {
+	{ .int_msk = BIT(0), .msg = "egu_cge_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(1), .msg = "egu_cge_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(2), .msg = "egu_lge_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(3), .msg = "egu_lge_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(4), .msg = "cge_igu_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(5), .msg = "cge_igu_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "lge_igu_afifo_ecc_1bit_err" },
+	{ .int_msk = BIT(7), .msg = "lge_igu_afifo_ecc_mbit_err" },
+	{ .int_msk = BIT(8), .msg = "cge_igu_afifo_overflow_err" },
+	{ .int_msk = BIT(9), .msg = "lge_igu_afifo_overflow_err" },
+	{ .int_msk = BIT(10), .msg = "egu_cge_afifo_underrun_err" },
+	{ .int_msk = BIT(11), .msg = "egu_lge_afifo_underrun_err" },
+	{ .int_msk = BIT(12), .msg = "egu_ge_afifo_underrun_err" },
+	{ .int_msk = BIT(13), .msg = "ge_igu_afifo_overflow_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st2[] = {
+	{ .int_msk = BIT(13), .msg = "rpu_rx_pkt_bit32_ecc_mbit_err" },
+	{ .int_msk = BIT(14), .msg = "rpu_rx_pkt_bit33_ecc_mbit_err" },
+	{ .int_msk = BIT(15), .msg = "rpu_rx_pkt_bit34_ecc_mbit_err" },
+	{ .int_msk = BIT(16), .msg = "rpu_rx_pkt_bit35_ecc_mbit_err" },
+	{ .int_msk = BIT(17), .msg = "rcb_tx_ring_ecc_mbit_err" },
+	{ .int_msk = BIT(18), .msg = "rcb_rx_ring_ecc_mbit_err" },
+	{ .int_msk = BIT(19), .msg = "rcb_tx_fbd_ecc_mbit_err" },
+	{ .int_msk = BIT(20), .msg = "rcb_rx_ebd_ecc_mbit_err" },
+	{ .int_msk = BIT(21), .msg = "rcb_tso_info_ecc_mbit_err" },
+	{ .int_msk = BIT(22), .msg = "rcb_tx_int_info_ecc_mbit_err" },
+	{ .int_msk = BIT(23), .msg = "rcb_rx_int_info_ecc_mbit_err" },
+	{ .int_msk = BIT(24), .msg = "tpu_tx_pkt_0_ecc_mbit_err" },
+	{ .int_msk = BIT(25), .msg = "tpu_tx_pkt_1_ecc_mbit_err" },
+	{ .int_msk = BIT(26), .msg = "rd_bus_err" },
+	{ .int_msk = BIT(27), .msg = "wr_bus_err" },
+	{ .int_msk = BIT(28), .msg = "reg_search_miss" },
+	{ .int_msk = BIT(29), .msg = "rx_q_search_miss" },
+	{ .int_msk = BIT(30), .msg = "ooo_ecc_err_detect" },
+	{ .int_msk = BIT(31), .msg = "ooo_ecc_err_multpl" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ppu_mpf_abnormal_int_st3[] = {
+	{ .int_msk = BIT(4), .msg = "gro_bd_ecc_mbit_err" },
+	{ .int_msk = BIT(5), .msg = "gro_context_ecc_mbit_err" },
+	{ .int_msk = BIT(6), .msg = "rx_stash_cfg_ecc_mbit_err" },
+	{ .int_msk = BIT(7), .msg = "axi_rd_fbd_ecc_mbit_err" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ppu_pf_abnormal_int[] = {
+	{ .int_msk = BIT(0), .msg = "over_8bd_no_fe" },
+	{ .int_msk = BIT(1), .msg = "tso_mss_cmp_min_err" },
+	{ .int_msk = BIT(2), .msg = "tso_mss_cmp_max_err" },
+	{ .int_msk = BIT(3), .msg = "tx_rd_fbd_poison" },
+	{ .int_msk = BIT(4), .msg = "rx_rd_ebd_poison" },
+	{ .int_msk = BIT(5), .msg = "buf_wait_timeout" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_com_err_int[] = {
+	{ .int_msk = BIT(0), .msg = "buf_sum_err" },
+	{ .int_msk = BIT(1), .msg = "ppp_mb_num_err" },
+	{ .int_msk = BIT(2), .msg = "ppp_mbid_err" },
+	{ .int_msk = BIT(3), .msg = "ppp_rlt_mac_err" },
+	{ .int_msk = BIT(4), .msg = "ppp_rlt_host_err" },
+	{ .int_msk = BIT(5), .msg = "cks_edit_position_err" },
+	{ .int_msk = BIT(6), .msg = "cks_edit_condition_err" },
+	{ .int_msk = BIT(7), .msg = "vlan_edit_condition_err" },
+	{ .int_msk = BIT(8), .msg = "vlan_num_ot_err" },
+	{ .int_msk = BIT(9), .msg = "vlan_num_in_err" },
+	{ /* sentinel */ }
+};
+
+#define HCLGE_SSU_MEM_ECC_ERR(x) \
+	{ .int_msk = BIT(x), .msg = "ssu_mem" #x "_ecc_mbit_err" }
+
+static const struct hclge_hw_error hclge_ssu_mem_ecc_err_int[] = {
+	HCLGE_SSU_MEM_ECC_ERR(0),
+	HCLGE_SSU_MEM_ECC_ERR(1),
+	HCLGE_SSU_MEM_ECC_ERR(2),
+	HCLGE_SSU_MEM_ECC_ERR(3),
+	HCLGE_SSU_MEM_ECC_ERR(4),
+	HCLGE_SSU_MEM_ECC_ERR(5),
+	HCLGE_SSU_MEM_ECC_ERR(6),
+	HCLGE_SSU_MEM_ECC_ERR(7),
+	HCLGE_SSU_MEM_ECC_ERR(8),
+	HCLGE_SSU_MEM_ECC_ERR(9),
+	HCLGE_SSU_MEM_ECC_ERR(10),
+	HCLGE_SSU_MEM_ECC_ERR(11),
+	HCLGE_SSU_MEM_ECC_ERR(12),
+	HCLGE_SSU_MEM_ECC_ERR(13),
+	HCLGE_SSU_MEM_ECC_ERR(14),
+	HCLGE_SSU_MEM_ECC_ERR(15),
+	HCLGE_SSU_MEM_ECC_ERR(16),
+	HCLGE_SSU_MEM_ECC_ERR(17),
+	HCLGE_SSU_MEM_ECC_ERR(18),
+	HCLGE_SSU_MEM_ECC_ERR(19),
+	HCLGE_SSU_MEM_ECC_ERR(20),
+	HCLGE_SSU_MEM_ECC_ERR(21),
+	HCLGE_SSU_MEM_ECC_ERR(22),
+	HCLGE_SSU_MEM_ECC_ERR(23),
+	HCLGE_SSU_MEM_ECC_ERR(24),
+	HCLGE_SSU_MEM_ECC_ERR(25),
+	HCLGE_SSU_MEM_ECC_ERR(26),
+	HCLGE_SSU_MEM_ECC_ERR(27),
+	HCLGE_SSU_MEM_ECC_ERR(28),
+	HCLGE_SSU_MEM_ECC_ERR(29),
+	HCLGE_SSU_MEM_ECC_ERR(30),
+	HCLGE_SSU_MEM_ECC_ERR(31),
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_port_based_err_int[] = {
+	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
+	{ .int_msk = BIT(1), .msg = "tpu_pkt_without_key_port" },
+	{ .int_msk = BIT(2), .msg = "igu_pkt_without_key_port" },
+	{ .int_msk = BIT(3), .msg = "roc_eof_mis_match_port" },
+	{ .int_msk = BIT(4), .msg = "tpu_eof_mis_match_port" },
+	{ .int_msk = BIT(5), .msg = "igu_eof_mis_match_port" },
+	{ .int_msk = BIT(6), .msg = "roc_sof_mis_match_port" },
+	{ .int_msk = BIT(7), .msg = "tpu_sof_mis_match_port" },
+	{ .int_msk = BIT(8), .msg = "igu_sof_mis_match_port" },
+	{ .int_msk = BIT(11), .msg = "ets_rd_int_rx_port" },
+	{ .int_msk = BIT(12), .msg = "ets_wr_int_rx_port" },
+	{ .int_msk = BIT(13), .msg = "ets_rd_int_tx_port" },
+	{ .int_msk = BIT(14), .msg = "ets_wr_int_tx_port" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_fifo_overflow_int[] = {
+	{ .int_msk = BIT(0), .msg = "ig_mac_inf_int" },
+	{ .int_msk = BIT(1), .msg = "ig_host_inf_int" },
+	{ .int_msk = BIT(2), .msg = "ig_roc_buf_int" },
+	{ .int_msk = BIT(3), .msg = "ig_host_data_fifo_int" },
+	{ .int_msk = BIT(4), .msg = "ig_host_key_fifo_int" },
+	{ .int_msk = BIT(5), .msg = "tx_qcn_fifo_int" },
+	{ .int_msk = BIT(6), .msg = "rx_qcn_fifo_int" },
+	{ .int_msk = BIT(7), .msg = "tx_pf_rd_fifo_int" },
+	{ .int_msk = BIT(8), .msg = "rx_pf_rd_fifo_int" },
+	{ .int_msk = BIT(9), .msg = "qm_eof_fifo_int" },
+	{ .int_msk = BIT(10), .msg = "mb_rlt_fifo_int" },
+	{ .int_msk = BIT(11), .msg = "dup_uncopy_fifo_int" },
+	{ .int_msk = BIT(12), .msg = "dup_cnt_rd_fifo_int" },
+	{ .int_msk = BIT(13), .msg = "dup_cnt_drop_fifo_int" },
+	{ .int_msk = BIT(14), .msg = "dup_cnt_wrb_fifo_int" },
+	{ .int_msk = BIT(15), .msg = "host_cmd_fifo_int" },
+	{ .int_msk = BIT(16), .msg = "mac_cmd_fifo_int" },
+	{ .int_msk = BIT(17), .msg = "host_cmd_bitmap_empty_int" },
+	{ .int_msk = BIT(18), .msg = "mac_cmd_bitmap_empty_int" },
+	{ .int_msk = BIT(19), .msg = "dup_bitmap_empty_int" },
+	{ .int_msk = BIT(20), .msg = "out_queue_bitmap_empty_int" },
+	{ .int_msk = BIT(21), .msg = "bank2_bitmap_empty_int" },
+	{ .int_msk = BIT(22), .msg = "bank1_bitmap_empty_int" },
+	{ .int_msk = BIT(23), .msg = "bank0_bitmap_empty_int" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_ets_tcg_int[] = {
+	{ .int_msk = BIT(0), .msg = "ets_rd_int_rx_tcg" },
+	{ .int_msk = BIT(1), .msg = "ets_wr_int_rx_tcg" },
+	{ .int_msk = BIT(2), .msg = "ets_rd_int_tx_tcg" },
+	{ .int_msk = BIT(3), .msg = "ets_wr_int_tx_tcg" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_ssu_port_based_pf_int[] = {
+	{ .int_msk = BIT(0), .msg = "roc_pkt_without_key_port" },
+	{ .int_msk = BIT(9), .msg = "low_water_line_err_port" },
+	{ .int_msk = BIT(10), .msg = "hi_water_line_err_port" },
+	{ /* sentinel */ }
+};
+
+static const struct hclge_hw_error hclge_rocee_qmm_ovf_err_int[] = {
+	{ .int_msk = 0, .msg = "rocee qmm ovf: sgid invalid err" },
+	{ .int_msk = 0x4, .msg = "rocee qmm ovf: sgid ovf err" },
+	{ .int_msk = 0x8, .msg = "rocee qmm ovf: smac invalid err" },
+	{ .int_msk = 0xC, .msg = "rocee qmm ovf: smac ovf err" },
+	{ .int_msk = 0x10, .msg = "rocee qmm ovf: cqc invalid err" },
+	{ .int_msk = 0x11, .msg = "rocee qmm ovf: cqc ovf err" },
+	{ .int_msk = 0x12, .msg = "rocee qmm ovf: cqc hopnum err" },
+	{ .int_msk = 0x13, .msg = "rocee qmm ovf: cqc ba0 err" },
+	{ .int_msk = 0x14, .msg = "rocee qmm ovf: srqc invalid err" },
+	{ .int_msk = 0x15, .msg = "rocee qmm ovf: srqc ovf err" },
+	{ .int_msk = 0x16, .msg = "rocee qmm ovf: srqc hopnum err" },
+	{ .int_msk = 0x17, .msg = "rocee qmm ovf: srqc ba0 err" },
+	{ .int_msk = 0x18, .msg = "rocee qmm ovf: mpt invalid err" },
+	{ .int_msk = 0x19, .msg = "rocee qmm ovf: mpt ovf err" },
+	{ .int_msk = 0x1A, .msg = "rocee qmm ovf: mpt hopnum err" },
+	{ .int_msk = 0x1B, .msg = "rocee qmm ovf: mpt ba0 err" },
+	{ .int_msk = 0x1C, .msg = "rocee qmm ovf: qpc invalid err" },
+	{ .int_msk = 0x1D, .msg = "rocee qmm ovf: qpc ovf err" },
+	{ .int_msk = 0x1E, .msg = "rocee qmm ovf: qpc hopnum err" },
+	{ .int_msk = 0x1F, .msg = "rocee qmm ovf: qpc ba0 err" },
+	{ /* sentinel */ }
+};
+
+static void hclge_log_error(struct device *dev, char *reg,
+			    const struct hclge_hw_error *err,
 			    u32 err_sts)
 {
-	const struct hclge_hw_error *err;
-	int i = 0;
-
-	while (err_list[i].msg) {
-		err = &err_list[i];
-		if (!(err->int_msk & err_sts)) {
-			i++;
-			continue;
-		}
-		dev_warn(dev, "%s [error status=0x%x] found\n",
-			 err->msg, err_sts);
-		i++;
+	while (err->msg) {
+		if (err->int_msk & err_sts)
+			dev_warn(dev, "%s %s found [error status=0x%x]\n",
+				 reg, err->msg, err_sts);
+		err++;
 	}
 }
 
@@ -391,96 +454,44 @@ static int hclge_cmd_query_error(struct hclge_dev *hdev,
 	return ret;
 }
 
-/* hclge_cmd_clear_error: clear the error status
- * @hdev: pointer to struct hclge_dev
- * @desc: descriptor for describing the command
- * @desc_src: prefilled descriptor from the previous command for reusing
- * @cmd:  command opcode
- * @flag: flag for extended command structure
- *
- * This function clear the error status in the hw register/s using command
- */
-static int hclge_cmd_clear_error(struct hclge_dev *hdev,
-				 struct hclge_desc *desc,
-				 struct hclge_desc *desc_src,
-				 u32 cmd, u16 flag)
-{
-	struct device *dev = &hdev->pdev->dev;
-	int num = 1;
-	int ret, i;
-
-	if (cmd) {
-		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
-		if (flag) {
-			desc[0].flag |= cpu_to_le16(flag);
-			hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
-			num = 2;
-		}
-		if (desc_src) {
-			for (i = 0; i < 6; i++) {
-				desc[0].data[i] = desc_src[0].data[i];
-				if (flag)
-					desc[1].data[i] = desc_src[1].data[i];
-			}
-		}
-	} else {
-		hclge_cmd_reuse_desc(&desc[0], false);
-		if (flag) {
-			desc[0].flag |= cpu_to_le16(flag);
-			hclge_cmd_reuse_desc(&desc[1], false);
-			num = 2;
-		}
-	}
-	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
-	if (ret)
-		dev_err(dev, "clear error cmd failed (%d)\n", ret);
-
-	return ret;
-}
-
-static int hclge_enable_common_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_common_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc[2];
 	int ret;
 
+	/* configure common error interrupts */
 	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_COMMON_ECC_INT_CFG, false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_COMMON_ECC_INT_CFG, false);
 
 	if (en) {
-		/* enable COMMON error interrupts */
 		desc[0].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_ERR_INT_EN);
 		desc[0].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN |
 					HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN);
 		desc[0].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN);
-		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN);
+		desc[0].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN |
+					      HCLGE_MSIX_SRAM_ECC_ERR_INT_EN);
 		desc[0].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN);
-	} else {
-		/* disable COMMON error interrupts */
-		desc[0].data[0] = 0;
-		desc[0].data[2] = 0;
-		desc[0].data[3] = 0;
-		desc[0].data[4] = 0;
-		desc[0].data[5] = 0;
 	}
+
 	desc[1].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK);
 	desc[1].data[2] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_ERR_INT_EN_MASK |
 				HCLGE_CMDQ_ROCEE_ECC_ERR_INT_EN_MASK);
 	desc[1].data[3] = cpu_to_le32(HCLGE_IMP_RD_POISON_ERR_INT_EN_MASK);
-	desc[1].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN_MASK);
+	desc[1].data[4] = cpu_to_le32(HCLGE_TQP_ECC_ERR_INT_EN_MASK |
+				      HCLGE_MSIX_SRAM_ECC_ERR_INT_EN_MASK);
 	desc[1].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_ERR_INT_EN_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
 	if (ret)
 		dev_err(dev,
-			"failed(%d) to enable/disable COMMON err interrupts\n",
-			ret);
+			"fail(%d) to configure common err interrupts\n", ret);
 
 	return ret;
 }
 
-static int hclge_enable_ncsi_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_ncsi_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
@@ -489,74 +500,65 @@ static int hclge_enable_ncsi_error(struct hclge_dev *hdev, bool en)
 	if (hdev->pdev->revision < 0x21)
 		return 0;
 
-	/* enable/disable NCSI  error interrupts */
+	/* configure NCSI error interrupts */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_NCSI_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_NCSI_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
 		dev_err(dev,
-			"failed(%d) to enable/disable NCSI error interrupts\n",
-			ret);
+			"fail(%d) to configure  NCSI error interrupts\n", ret);
 
 	return ret;
 }
 
-static int hclge_enable_igu_egu_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_igu_egu_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
 	int ret;
 
-	/* enable/disable error interrupts */
+	/* configure IGU,EGU error interrupts */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_IGU_COMMON_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
+
 	desc.data[1] = cpu_to_le32(HCLGE_IGU_ERR_INT_EN_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(dev,
-			"failed(%d) to enable/disable IGU common interrupts\n",
-			ret);
+			"fail(%d) to configure IGU common interrupts\n", ret);
 		return ret;
 	}
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_IGU_EGU_TNL_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_IGU_TNL_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
+
 	desc.data[1] = cpu_to_le32(HCLGE_IGU_TNL_ERR_INT_EN_MASK);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
 		dev_err(dev,
-			"failed(%d) to enable/disable IGU-EGU TNL interrupts\n",
-			ret);
+			"fail(%d) to configure IGU-EGU TNL interrupts\n", ret);
 		return ret;
 	}
 
-	ret = hclge_enable_ncsi_error(hdev, en);
-	if (ret)
-		dev_err(dev, "fail(%d) to en/disable err int\n", ret);
+	ret = hclge_config_ncsi_hw_err_int(hdev, en);
 
 	return ret;
 }
 
-static int hclge_enable_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
+static int hclge_config_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 					    bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc[2];
 	int ret;
 
-	/* enable/disable PPP error interrupts */
+	/* configure PPP error interrupts */
 	hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
 	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
 	hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
@@ -567,24 +569,24 @@ static int hclge_enable_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN);
 			desc[0].data[1] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT1_EN);
-		} else {
-			desc[0].data[0] = 0;
-			desc[0].data[1] = 0;
+			desc[0].data[4] = cpu_to_le32(HCLGE_PPP_PF_ERR_INT_EN);
 		}
+
 		desc[1].data[0] =
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT0_EN_MASK);
 		desc[1].data[1] =
 			cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT1_EN_MASK);
+		if (hdev->pdev->revision >= 0x21)
+			desc[1].data[2] =
+				cpu_to_le32(HCLGE_PPP_PF_ERR_INT_EN_MASK);
 	} else if (cmd == HCLGE_PPP_CMD1_INT_CMD) {
 		if (en) {
 			desc[0].data[0] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT2_EN);
 			desc[0].data[1] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT3_EN);
-		} else {
-			desc[0].data[0] = 0;
-			desc[0].data[1] = 0;
 		}
+
 		desc[1].data[0] =
 				cpu_to_le32(HCLGE_PPP_MPF_ECC_ERR_INT2_EN_MASK);
 		desc[1].data[1] =
@@ -593,498 +595,880 @@ static int hclge_enable_ppp_error_interrupt(struct hclge_dev *hdev, u32 cmd,
 
 	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
 	if (ret)
-		dev_err(dev,
-			"failed(%d) to enable/disable PPP error interrupts\n",
-			ret);
+		dev_err(dev, "fail(%d) to configure PPP error intr\n", ret);
 
 	return ret;
 }
 
-static int hclge_enable_ppp_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_ppp_hw_err_int(struct hclge_dev *hdev, bool en)
 {
-	struct device *dev = &hdev->pdev->dev;
 	int ret;
 
-	ret = hclge_enable_ppp_error_interrupt(hdev, HCLGE_PPP_CMD0_INT_CMD,
+	ret = hclge_config_ppp_error_interrupt(hdev, HCLGE_PPP_CMD0_INT_CMD,
 					       en);
-	if (ret) {
-		dev_err(dev,
-			"failed(%d) to enable/disable PPP error intr 0,1\n",
-			ret);
+	if (ret)
 		return ret;
-	}
 
-	ret = hclge_enable_ppp_error_interrupt(hdev, HCLGE_PPP_CMD1_INT_CMD,
+	ret = hclge_config_ppp_error_interrupt(hdev, HCLGE_PPP_CMD1_INT_CMD,
 					       en);
-	if (ret)
-		dev_err(dev,
-			"failed(%d) to enable/disable PPP error intr 2,3\n",
-			ret);
 
 	return ret;
 }
 
-int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en)
+static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
 	int ret;
 
-	/* enable TM SCH hw errors */
+	/* configure TM SCH hw errors */
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_TM_SCH_ECC_INT_EN, false);
 	if (en)
 		desc.data[0] = cpu_to_le32(HCLGE_TM_SCH_ECC_ERR_INT_EN);
-	else
-		desc.data[0] = 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-		dev_err(dev, "failed(%d) to configure TM SCH errors\n", ret);
+		dev_err(dev, "fail(%d) to configure TM SCH errors\n", ret);
 		return ret;
 	}
 
-	/* enable TM QCN hw errors */
+	/* configure TM QCN hw errors */
 	ret = hclge_cmd_query_error(hdev, &desc, HCLGE_TM_QCN_MEM_INT_CFG,
 				    0, 0, 0);
 	if (ret) {
-		dev_err(dev, "failed(%d) to read TM QCN CFG status\n", ret);
+		dev_err(dev, "fail(%d) to read TM QCN CFG status\n", ret);
 		return ret;
 	}
 
 	hclge_cmd_reuse_desc(&desc, false);
 	if (en)
 		desc.data[1] = cpu_to_le32(HCLGE_TM_QCN_MEM_ERR_INT_EN);
-	else
-		desc.data[1] = 0;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
 		dev_err(dev,
-			"failed(%d) to configure TM QCN mem errors\n", ret);
+			"fail(%d) to configure TM QCN mem errors\n", ret);
 
 	return ret;
 }
 
-static void hclge_process_common_error(struct hclge_dev *hdev,
-				       enum hclge_err_int_type type)
+static int hclge_config_mac_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc[2];
-	u32 err_sts;
+	struct hclge_desc desc;
 	int ret;
 
-	/* read err sts */
-	ret = hclge_cmd_query_error(hdev, &desc[0],
-				    HCLGE_COMMON_ECC_INT_CFG,
-				    HCLGE_CMD_FLAG_NEXT, 0, 0);
-	if (ret) {
+	/* configure MAC common error interrupts */
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_MAC_COMMON_INT_EN, false);
+	if (en)
+		desc.data[0] = cpu_to_le32(HCLGE_MAC_COMMON_ERR_INT_EN);
+
+	desc.data[1] = cpu_to_le32(HCLGE_MAC_COMMON_ERR_INT_EN_MASK);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
 		dev_err(dev,
-			"failed(=%d) to query COMMON error interrupt status\n",
-			ret);
-		return;
-	}
+			"fail(%d) to configure MAC COMMON error intr\n", ret);
 
-	/* log err */
-	err_sts = (le32_to_cpu(desc[0].data[0])) & HCLGE_IMP_TCM_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_imp_tcm_ecc_int[0], err_sts);
+	return ret;
+}
 
-	err_sts = (le32_to_cpu(desc[0].data[1])) & HCLGE_CMDQ_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_cmdq_nic_mem_ecc_int[0], err_sts);
+static int hclge_config_ppu_error_interrupts(struct hclge_dev *hdev, u32 cmd,
+					     bool en)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int num = 1;
+	int ret;
 
-	err_sts = (le32_to_cpu(desc[0].data[1]) >> HCLGE_CMDQ_ROC_ECC_INT_SHIFT)
-		   & HCLGE_CMDQ_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_cmdq_rocee_mem_ecc_int[0], err_sts);
+	/* configure PPU error interrupts */
+	if (cmd == HCLGE_PPU_MPF_ECC_INT_CMD) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		desc[0].flag |= HCLGE_CMD_FLAG_NEXT;
+		hclge_cmd_setup_basic_desc(&desc[1], cmd, false);
+		if (en) {
+			desc[0].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT0_EN;
+			desc[0].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN;
+			desc[1].data[3] = HCLGE_PPU_MPF_ABNORMAL_INT3_EN;
+			desc[1].data[4] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN;
+		}
 
-	if ((le32_to_cpu(desc[0].data[3])) & BIT(0))
-		dev_warn(dev, "imp_rd_data_poison_err found\n");
+		desc[1].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK;
+		desc[1].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK;
+		desc[1].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK;
+		desc[1].data[3] |= HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK;
+		num = 2;
+	} else if (cmd == HCLGE_PPU_MPF_OTHER_INT_CMD) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		if (en)
+			desc[0].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN2;
 
-	err_sts = (le32_to_cpu(desc[0].data[3]) >> HCLGE_TQP_ECC_INT_SHIFT) &
-		   HCLGE_TQP_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_tqp_int_ecc_int[0], err_sts);
+		desc[0].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN2_MASK;
+	} else if (cmd == HCLGE_PPU_PF_OTHER_INT_CMD) {
+		hclge_cmd_setup_basic_desc(&desc[0], cmd, false);
+		if (en)
+			desc[0].data[0] = HCLGE_PPU_PF_ABNORMAL_INT_EN;
 
-	err_sts = (le32_to_cpu(desc[0].data[5])) &
-		   HCLGE_IMP_ITCM4_ECC_INT_MASK;
-	hclge_log_error(dev, &hclge_imp_itcm4_ecc_int[0], err_sts);
+		desc[0].data[2] = HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK;
+	} else {
+		dev_err(dev, "Invalid cmd to configure PPU error interrupts\n");
+		return -EINVAL;
+	}
 
-	/* clear error interrupts */
-	desc[1].data[0] = cpu_to_le32(HCLGE_IMP_TCM_ECC_CLR_MASK);
-	desc[1].data[1] = cpu_to_le32(HCLGE_CMDQ_NIC_ECC_CLR_MASK |
-				HCLGE_CMDQ_ROCEE_ECC_CLR_MASK);
-	desc[1].data[3] = cpu_to_le32(HCLGE_TQP_IMP_ERR_CLR_MASK);
-	desc[1].data[5] = cpu_to_le32(HCLGE_IMP_ITCM4_ECC_CLR_MASK);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
 
-	ret = hclge_cmd_clear_error(hdev, &desc[0], NULL, 0,
-				    HCLGE_CMD_FLAG_NEXT);
-	if (ret)
-		dev_err(dev,
-			"failed(%d) to clear COMMON error interrupt status\n",
-			ret);
+	return ret;
 }
 
-static void hclge_process_ncsi_error(struct hclge_dev *hdev,
-				     enum hclge_err_int_type type)
+static int hclge_config_ppu_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc_rd;
-	struct hclge_desc desc_wr;
-	u32 err_sts;
 	int ret;
 
-	if (hdev->pdev->revision < 0x21)
-		return;
-
-	/* read NCSI error status */
-	ret = hclge_cmd_query_error(hdev, &desc_rd, HCLGE_NCSI_INT_QUERY,
-				    0, 1, HCLGE_NCSI_ERR_INT_TYPE);
+	ret = hclge_config_ppu_error_interrupts(hdev, HCLGE_PPU_MPF_ECC_INT_CMD,
+						en);
 	if (ret) {
-		dev_err(dev,
-			"failed(=%d) to query NCSI error interrupt status\n",
+		dev_err(dev, "fail(%d) to configure PPU MPF ECC error intr\n",
 			ret);
-		return;
+		return ret;
 	}
 
-	/* log err */
-	err_sts = le32_to_cpu(desc_rd.data[0]);
-	hclge_log_error(dev, &hclge_ncsi_err_int[0], err_sts);
+	ret = hclge_config_ppu_error_interrupts(hdev,
+						HCLGE_PPU_MPF_OTHER_INT_CMD,
+						en);
+	if (ret) {
+		dev_err(dev, "fail(%d) to configure PPU MPF other intr\n", ret);
+		return ret;
+	}
 
-	/* clear err int */
-	ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
-				    HCLGE_NCSI_INT_CLR, 0);
+	ret = hclge_config_ppu_error_interrupts(hdev,
+						HCLGE_PPU_PF_OTHER_INT_CMD, en);
 	if (ret)
-		dev_err(dev, "failed(=%d) to clear NCSI interrupt status\n",
+		dev_err(dev, "fail(%d) to configure PPU PF error interrupts\n",
 			ret);
+	return ret;
 }
 
-static void hclge_process_igu_egu_error(struct hclge_dev *hdev,
-					enum hclge_err_int_type int_type)
+static int hclge_config_ssu_hw_err_int(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
-	struct hclge_desc desc_rd;
-	struct hclge_desc desc_wr;
-	u32 err_sts;
+	struct hclge_desc desc[2];
 	int ret;
 
-	/* read IGU common err sts */
-	ret = hclge_cmd_query_error(hdev, &desc_rd,
-				    HCLGE_IGU_COMMON_INT_QUERY,
-				    0, 1, int_type);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to query IGU common int status\n",
-			ret);
-		return;
+	/* configure SSU ecc error interrupts */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_SSU_ECC_INT_CMD, false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_ECC_INT_CMD, false);
+	if (en) {
+		desc[0].data[0] = cpu_to_le32(HCLGE_SSU_1BIT_ECC_ERR_INT_EN);
+		desc[0].data[1] =
+			cpu_to_le32(HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN);
+		desc[0].data[4] = cpu_to_le32(HCLGE_SSU_BIT32_ECC_ERR_INT_EN);
 	}
 
-	/* log err */
-	err_sts = le32_to_cpu(desc_rd.data[0]) &
-				   HCLGE_IGU_COM_INT_MASK;
-	hclge_log_error(dev, &hclge_igu_com_err_int[0], err_sts);
+	desc[1].data[0] = cpu_to_le32(HCLGE_SSU_1BIT_ECC_ERR_INT_EN_MASK);
+	desc[1].data[1] = cpu_to_le32(HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN_MASK);
+	desc[1].data[2] = cpu_to_le32(HCLGE_SSU_BIT32_ECC_ERR_INT_EN_MASK);
 
-	/* clear err int */
-	ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
-				    HCLGE_IGU_COMMON_INT_CLR, 0);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
 	if (ret) {
-		dev_err(dev, "failed(=%d) to clear IGU common int status\n",
-			ret);
-		return;
+		dev_err(dev,
+			"fail(%d) to configure SSU ECC error interrupt\n", ret);
+		return ret;
 	}
 
-	/* read IGU-EGU TNL err sts */
-	ret = hclge_cmd_query_error(hdev, &desc_rd,
-				    HCLGE_IGU_EGU_TNL_INT_QUERY,
-				    0, 1, int_type);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to query IGU-EGU TNL int status\n",
-			ret);
-		return;
+	/* configure SSU common error interrupts */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_SSU_COMMON_INT_CMD, false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+	hclge_cmd_setup_basic_desc(&desc[1], HCLGE_SSU_COMMON_INT_CMD, false);
+
+	if (en) {
+		if (hdev->pdev->revision >= 0x21)
+			desc[0].data[0] =
+				cpu_to_le32(HCLGE_SSU_COMMON_INT_EN);
+		else
+			desc[0].data[0] =
+				cpu_to_le32(HCLGE_SSU_COMMON_INT_EN & ~BIT(5));
+		desc[0].data[1] = cpu_to_le32(HCLGE_SSU_PORT_BASED_ERR_INT_EN);
+		desc[0].data[2] =
+			cpu_to_le32(HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN);
 	}
 
-	/* log err */
-	err_sts = le32_to_cpu(desc_rd.data[0]) &
-				   HCLGE_IGU_EGU_TNL_INT_MASK;
-	hclge_log_error(dev, &hclge_igu_egu_tnl_err_int[0], err_sts);
+	desc[1].data[0] = cpu_to_le32(HCLGE_SSU_COMMON_INT_EN_MASK |
+				HCLGE_SSU_PORT_BASED_ERR_INT_EN_MASK);
+	desc[1].data[1] = cpu_to_le32(HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN_MASK);
 
-	/* clear err int */
-	ret = hclge_cmd_clear_error(hdev, &desc_wr, &desc_rd,
-				    HCLGE_IGU_EGU_TNL_INT_CLR, 0);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to clear IGU-EGU TNL int status\n",
-			ret);
-		return;
-	}
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 2);
+	if (ret)
+		dev_err(dev,
+			"fail(%d) to configure SSU COMMON error intr\n", ret);
 
-	hclge_process_ncsi_error(hdev, HCLGE_ERR_INT_RAS_NFE);
+	return ret;
 }
 
-static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
-					 enum hclge_err_int_type int_type)
+#define HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type) \
+	do { \
+		if (ae_dev->ops->set_default_reset_request) \
+			ae_dev->ops->set_default_reset_request(ae_dev, \
+							       reset_type); \
+	} while (0)
+
+/* hclge_handle_mpf_ras_error: handle all main PF RAS errors
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @num:  number of extended command structures
+ *
+ * This function handles all the main PF RAS errors in the
+ * hw register/s using command.
+ */
+static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev,
+				      struct hclge_desc *desc,
+				      int num)
 {
-	enum hnae3_reset_type reset_level = HNAE3_NONE_RESET;
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
 	struct device *dev = &hdev->pdev->dev;
-	const struct hclge_hw_error *hw_err_lst1, *hw_err_lst2, *hw_err_lst3;
-	struct hclge_desc desc[2];
-	u32 err_sts;
+	__le32 *desc_data;
+	u32 status;
 	int ret;
 
-	/* read PPP INT sts */
-	ret = hclge_cmd_query_error(hdev, &desc[0], cmd,
-				    HCLGE_CMD_FLAG_NEXT, 5, int_type);
+	/* query all main PF RAS errors */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_MPF_RAS_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
 	if (ret) {
-		dev_err(dev, "failed(=%d) to query PPP interrupt status\n",
-			ret);
-		return -EIO;
+		dev_err(dev, "query all mpf ras int cmd failed (%d)\n", ret);
+		return ret;
 	}
 
-	/* log error */
-	if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
-		hw_err_lst1 = &hclge_ppp_mpf_int0[0];
-		hw_err_lst2 = &hclge_ppp_mpf_int1[0];
-		hw_err_lst3 = &hclge_ppp_pf_int[0];
-	} else if (cmd == HCLGE_PPP_CMD1_INT_CMD) {
-		hw_err_lst1 = &hclge_ppp_mpf_int2[0];
-		hw_err_lst2 = &hclge_ppp_mpf_int3[0];
-	} else {
-		dev_err(dev, "invalid command(=%d)\n", cmd);
-		return -EINVAL;
+	/* log HNS common errors */
+	status = le32_to_cpu(desc[0].data[0]);
+	if (status) {
+		hclge_log_error(dev, "IMP_TCM_ECC_INT_STS",
+				&hclge_imp_tcm_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
 	}
 
-	err_sts = le32_to_cpu(desc[0].data[2]);
-	if (err_sts) {
-		hclge_log_error(dev, hw_err_lst1, err_sts);
-		reset_level = HNAE3_FUNC_RESET;
+	status = le32_to_cpu(desc[0].data[1]);
+	if (status) {
+		hclge_log_error(dev, "CMDQ_MEM_ECC_INT_STS",
+				&hclge_cmdq_nic_mem_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
 	}
 
-	err_sts = le32_to_cpu(desc[0].data[3]);
-	if (err_sts) {
-		hclge_log_error(dev, hw_err_lst2, err_sts);
-		reset_level = HNAE3_FUNC_RESET;
+	if ((le32_to_cpu(desc[0].data[2])) & BIT(0)) {
+		dev_warn(dev, "imp_rd_data_poison_err found\n");
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
 	}
 
-	if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
-		err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3;
-		if (err_sts) {
-			hclge_log_error(dev, hw_err_lst3, err_sts);
-			reset_level = HNAE3_FUNC_RESET;
-		}
+	status = le32_to_cpu(desc[0].data[3]);
+	if (status) {
+		hclge_log_error(dev, "TQP_INT_ECC_INT_STS",
+				&hclge_tqp_int_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
 	}
 
-	/* clear PPP INT */
-	ret = hclge_cmd_clear_error(hdev, &desc[0], NULL, 0,
-				    HCLGE_CMD_FLAG_NEXT);
-	if (ret) {
-		dev_err(dev, "failed(=%d) to clear PPP interrupt status\n",
-			ret);
-		return -EIO;
+	status = le32_to_cpu(desc[0].data[4]);
+	if (status) {
+		hclge_log_error(dev, "MSIX_ECC_INT_STS",
+				&hclge_msix_sram_ecc_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
 	}
 
-	return 0;
+	/* log SSU(Storage Switch Unit) errors */
+	desc_data = (__le32 *)&desc[2];
+	status = le32_to_cpu(*(desc_data + 2));
+	if (status) {
+		hclge_log_error(dev, "SSU_ECC_MULTI_BIT_INT_0",
+				&hclge_ssu_mem_ecc_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 3)) & BIT(0);
+	if (status) {
+		dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n",
+			 status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 4)) & HCLGE_SSU_COMMON_ERR_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "SSU_COMMON_ERR_INT",
+				&hclge_ssu_com_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	/* log IGU(Ingress Unit) errors */
+	desc_data = (__le32 *)&desc[3];
+	status = le32_to_cpu(*desc_data) & HCLGE_IGU_INT_MASK;
+	if (status)
+		hclge_log_error(dev, "IGU_INT_STS",
+				&hclge_igu_int[0], status);
+
+	/* log PPP(Programmable Packet Process) errors */
+	desc_data = (__le32 *)&desc[4];
+	status = le32_to_cpu(*(desc_data + 1));
+	if (status)
+		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST1",
+				&hclge_ppp_mpf_abnormal_int_st1[0], status);
+
+	status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPP_MPF_INT_ST3_MASK;
+	if (status)
+		hclge_log_error(dev, "PPP_MPF_ABNORMAL_INT_ST3",
+				&hclge_ppp_mpf_abnormal_int_st3[0], status);
+
+	/* log PPU(RCB) errors */
+	desc_data = (__le32 *)&desc[5];
+	status = le32_to_cpu(*(desc_data + 1));
+	if (status) {
+		dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST1 %s found\n",
+			 "rpu_rx_pkt_ecc_mbit_err");
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 2));
+	if (status) {
+		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
+				&hclge_ppu_mpf_abnormal_int_st2[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 3)) & HCLGE_PPU_MPF_INT_ST3_MASK;
+	if (status) {
+		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST3",
+				&hclge_ppu_mpf_abnormal_int_st3[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* log TM(Traffic Manager) errors */
+	desc_data = (__le32 *)&desc[6];
+	status = le32_to_cpu(*desc_data);
+	if (status) {
+		hclge_log_error(dev, "TM_SCH_RINT",
+				&hclge_tm_sch_rint[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* log QCN(Quantized Congestion Control) errors */
+	desc_data = (__le32 *)&desc[7];
+	status = le32_to_cpu(*desc_data) & HCLGE_QCN_FIFO_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "QCN_FIFO_RINT",
+				&hclge_qcn_fifo_rint[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	status = le32_to_cpu(*(desc_data + 1)) & HCLGE_QCN_ECC_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "QCN_ECC_RINT",
+				&hclge_qcn_ecc_rint[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* log NCSI errors */
+	desc_data = (__le32 *)&desc[9];
+	status = le32_to_cpu(*desc_data) & HCLGE_NCSI_ECC_INT_MASK;
+	if (status) {
+		hclge_log_error(dev, "NCSI_ECC_INT_RPT",
+				&hclge_ncsi_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_CORE_RESET);
+	}
+
+	/* clear all main PF RAS errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret)
+		dev_err(dev, "clear all mpf ras int cmd failed (%d)\n", ret);
+
+	return ret;
 }
 
-static void hclge_process_ppp_error(struct hclge_dev *hdev,
-				    enum hclge_err_int_type int_type)
+/* hclge_handle_pf_ras_error: handle all PF RAS errors
+ * @hdev: pointer to struct hclge_dev
+ * @desc: descriptor for describing the command
+ * @num:  number of extended command structures
+ *
+ * This function handles all the PF RAS errors in the
+ * hw register/s using command.
+ */
+static int hclge_handle_pf_ras_error(struct hclge_dev *hdev,
+				     struct hclge_desc *desc,
+				     int num)
 {
+	struct hnae3_ae_dev *ae_dev = hdev->ae_dev;
 	struct device *dev = &hdev->pdev->dev;
+	__le32 *desc_data;
+	u32 status;
 	int ret;
 
-	/* read PPP INT0,1 sts */
-	ret = hclge_log_and_clear_ppp_error(hdev, HCLGE_PPP_CMD0_INT_CMD,
-					    int_type);
-	if (ret < 0) {
-		dev_err(dev, "failed(=%d) to clear PPP interrupt 0,1 status\n",
-			ret);
-		return;
+	/* query all PF RAS errors */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_PF_RAS_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret) {
+		dev_err(dev, "query all pf ras int cmd failed (%d)\n", ret);
+		return ret;
 	}
 
-	/* read err PPP INT2,3 sts */
-	ret = hclge_log_and_clear_ppp_error(hdev, HCLGE_PPP_CMD1_INT_CMD,
-					    int_type);
-	if (ret < 0)
-		dev_err(dev, "failed(=%d) to clear PPP interrupt 2,3 status\n",
-			ret);
+	/* log SSU(Storage Switch Unit) errors */
+	status = le32_to_cpu(desc[0].data[0]);
+	if (status) {
+		hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
+				&hclge_ssu_port_based_err_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[1]);
+	if (status) {
+		hclge_log_error(dev, "SSU_FIFO_OVERFLOW_INT",
+				&hclge_ssu_fifo_overflow_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	status = le32_to_cpu(desc[0].data[2]);
+	if (status) {
+		hclge_log_error(dev, "SSU_ETS_TCG_INT",
+				&hclge_ssu_ets_tcg_int[0], status);
+		HCLGE_SET_DEFAULT_RESET_REQUEST(HNAE3_GLOBAL_RESET);
+	}
+
+	/* log IGU(Ingress Unit) EGU(Egress Unit) TNL errors */
+	desc_data = (__le32 *)&desc[1];
+	status = le32_to_cpu(*desc_data) & HCLGE_IGU_EGU_TNL_INT_MASK;
+	if (status)
+		hclge_log_error(dev, "IGU_EGU_TNL_INT_STS",
+				&hclge_igu_egu_tnl_int[0], status);
+
+	/* log PPU(RCB) errors */
+	desc_data = (__le32 *)&desc[3];
+	status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_RAS_MASK;
+	if (status)
+		hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST0",
+				&hclge_ppu_pf_abnormal_int[0], status);
+
+	/* clear all PF RAS errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], num);
+	if (ret)
+		dev_err(dev, "clear all pf ras int cmd failed (%d)\n", ret);
+
+	return ret;
 }
 
-static void hclge_process_tm_sch_error(struct hclge_dev *hdev)
+static int hclge_handle_all_ras_errors(struct hclge_dev *hdev)
 {
 	struct device *dev = &hdev->pdev->dev;
-	const struct hclge_tm_sch_ecc_info *tm_sch_ecc_info;
-	struct hclge_desc desc;
-	u32 ecc_info;
-	u8 module_no;
-	u8 ram_no;
+	u32 mpf_bd_num, pf_bd_num, bd_num;
+	struct hclge_desc desc_bd;
+	struct hclge_desc *desc;
 	int ret;
 
-	/* read TM scheduler errors */
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_MBIT_ECC_INFO_CMD, 0, 0, 0);
+	/* query the number of registers in the RAS int status */
+	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_RAS_INT_STS_BD_NUM,
+				   true);
+	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
 	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH mbit ECC err info\n", ret);
-		return;
+		dev_err(dev, "fail(%d) to query ras int status bd num\n", ret);
+		return ret;
 	}
-	ecc_info = le32_to_cpu(desc.data[0]);
+	mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
+	pf_bd_num = le32_to_cpu(desc_bd.data[1]);
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
 
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_CMD, 0, 0, 0);
+	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+
+	/* handle all main PF RAS errors */
+	ret = hclge_handle_mpf_ras_error(hdev, desc, mpf_bd_num);
 	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH ECC err status\n", ret);
-		return;
+		kfree(desc);
+		return ret;
 	}
+	memset(desc, 0, bd_num * sizeof(struct hclge_desc));
 
-	/* log TM scheduler errors */
-	if (le32_to_cpu(desc.data[0])) {
-		hclge_log_error(dev, &hclge_tm_sch_err_int[0],
-				le32_to_cpu(desc.data[0]));
-		if (le32_to_cpu(desc.data[0]) & 0x2) {
-			module_no = (ecc_info >> 20) & 0xF;
-			ram_no = (ecc_info >> 16) & 0xF;
-			tm_sch_ecc_info =
-				&hclge_tm_sch_ecc_err[module_no][ram_no];
-			dev_warn(dev, "ecc err module:ram=%s\n",
-				 tm_sch_ecc_info->name);
-			dev_warn(dev, "ecc memory address = 0x%x\n",
-				 ecc_info & 0xFFFF);
+	/* handle all PF RAS errors */
+	ret = hclge_handle_pf_ras_error(hdev, desc, pf_bd_num);
+	kfree(desc);
+
+	return ret;
+}
+
+static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev)
+{
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	int ret;
+
+	/* read overflow error status */
+	ret = hclge_cmd_query_error(hdev, &desc[0],
+				    HCLGE_ROCEE_PF_RAS_INT_CMD,
+				    0, 0, 0);
+	if (ret) {
+		dev_err(dev, "failed(%d) to query ROCEE OVF error sts\n", ret);
+		return ret;
+	}
+
+	/* log overflow error */
+	if (le32_to_cpu(desc[0].data[0]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) {
+		const struct hclge_hw_error *err;
+		u32 err_sts;
+
+		err = &hclge_rocee_qmm_ovf_err_int[0];
+		err_sts = HCLGE_ROCEE_OVF_ERR_TYPE_MASK &
+			  le32_to_cpu(desc[0].data[0]);
+		while (err->msg) {
+			if (err->int_msk == err_sts) {
+				dev_warn(dev, "%s [error status=0x%x] found\n",
+					 err->msg,
+					 le32_to_cpu(desc[0].data[0]));
+				break;
+			}
+			err++;
 		}
 	}
 
-	/* clear TM scheduler errors */
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to clear TM SCH error status\n", ret);
-		return;
+	if (le32_to_cpu(desc[0].data[1]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) {
+		dev_warn(dev, "ROCEE TSP OVF [error status=0x%x] found\n",
+			 le32_to_cpu(desc[0].data[1]));
 	}
 
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_CE, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH CE status\n", ret);
-		return;
+	if (le32_to_cpu(desc[0].data[2]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) {
+		dev_warn(dev, "ROCEE SCC OVF [error status=0x%x] found\n",
+			 le32_to_cpu(desc[0].data[2]));
 	}
 
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
+	return 0;
+}
+
+static enum hnae3_reset_type
+hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev)
+{
+	enum hnae3_reset_type reset_type = HNAE3_NONE_RESET;
+	struct device *dev = &hdev->pdev->dev;
+	struct hclge_desc desc[2];
+	unsigned int status;
+	int ret;
+
+	/* read RAS error interrupt status */
+	ret = hclge_cmd_query_error(hdev, &desc[0],
+				    HCLGE_QUERY_CLEAR_ROCEE_RAS_INT,
+				    0, 0, 0);
 	if (ret) {
-		dev_err(dev, "failed(%d) to clear TM SCH CE status\n", ret);
-		return;
+		dev_err(dev, "failed(%d) to query ROCEE RAS INT SRC\n", ret);
+		/* reset everything for now */
+		return HNAE3_GLOBAL_RESET;
 	}
 
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_NFE, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH NFE status\n", ret);
-		return;
+	status = le32_to_cpu(desc[0].data[0]);
+
+	if (status & HCLGE_ROCEE_RERR_INT_MASK) {
+		dev_warn(dev, "ROCEE RAS AXI rresp error\n");
+		reset_type = HNAE3_FUNC_RESET;
 	}
 
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to clear TM SCH NFE status\n", ret);
-		return;
+	if (status & HCLGE_ROCEE_BERR_INT_MASK) {
+		dev_warn(dev, "ROCEE RAS AXI bresp error\n");
+		reset_type = HNAE3_FUNC_RESET;
 	}
 
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_SCH_ECC_ERR_RINT_FE, 0, 0, 0);
+	if (status & HCLGE_ROCEE_ECC_INT_MASK) {
+		dev_warn(dev, "ROCEE RAS 2bit ECC error\n");
+		reset_type = HNAE3_GLOBAL_RESET;
+	}
+
+	if (status & HCLGE_ROCEE_OVF_INT_MASK) {
+		ret = hclge_log_rocee_ovf_error(hdev);
+		if (ret) {
+			dev_err(dev, "failed(%d) to process ovf error\n", ret);
+			/* reset everything for now */
+			return HNAE3_GLOBAL_RESET;
+		}
+		reset_type = HNAE3_FUNC_RESET;
+	}
+
+	/* clear error status */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], 1);
 	if (ret) {
-		dev_err(dev, "failed(%d) to read SCH FE status\n", ret);
-		return;
+		dev_err(dev, "failed(%d) to clear ROCEE RAS error\n", ret);
+		/* reset everything for now */
+		return HNAE3_GLOBAL_RESET;
 	}
 
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
-	if (ret)
-		dev_err(dev, "failed(%d) to clear TM SCH FE status\n", ret);
+	return reset_type;
 }
 
-static void hclge_process_tm_qcn_error(struct hclge_dev *hdev)
+static int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en)
 {
 	struct device *dev = &hdev->pdev->dev;
 	struct hclge_desc desc;
 	int ret;
 
-	/* read QCN errors */
-	ret = hclge_cmd_query_error(hdev, &desc,
-				    HCLGE_TM_QCN_MEM_INT_INFO_CMD, 0, 0, 0);
-	if (ret) {
-		dev_err(dev, "failed(%d) to read QCN ECC err status\n", ret);
-		return;
-	}
+	if (hdev->pdev->revision < 0x21 || !hnae3_dev_roce_supported(hdev))
+		return 0;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_CONFIG_ROCEE_RAS_INT_EN, false);
+	if (en) {
+		/* enable ROCEE hw error interrupts */
+		desc.data[0] = cpu_to_le32(HCLGE_ROCEE_RAS_NFE_INT_EN);
+		desc.data[1] = cpu_to_le32(HCLGE_ROCEE_RAS_CE_INT_EN);
 
-	/* log QCN errors */
-	if (le32_to_cpu(desc.data[0]))
-		hclge_log_error(dev, &hclge_qcn_ecc_err_int[0],
-				le32_to_cpu(desc.data[0]));
+		hclge_log_and_clear_rocee_ras_error(hdev);
+	}
+	desc.data[2] = cpu_to_le32(HCLGE_ROCEE_RAS_NFE_INT_EN_MASK);
+	desc.data[3] = cpu_to_le32(HCLGE_ROCEE_RAS_CE_INT_EN_MASK);
 
-	/* clear QCN errors */
-	ret = hclge_cmd_clear_error(hdev, &desc, NULL, 0, 0);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
-		dev_err(dev, "failed(%d) to clear QCN error status\n", ret);
+		dev_err(dev, "failed(%d) to config ROCEE RAS interrupt\n", ret);
+
+	return ret;
 }
 
-static void hclge_process_tm_error(struct hclge_dev *hdev,
-				   enum hclge_err_int_type type)
+static void hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev)
 {
-	hclge_process_tm_sch_error(hdev);
-	hclge_process_tm_qcn_error(hdev);
+	enum hnae3_reset_type reset_type = HNAE3_NONE_RESET;
+	struct hclge_dev *hdev = ae_dev->priv;
+
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+	    hdev->pdev->revision < 0x21)
+		return;
+
+	reset_type = hclge_log_and_clear_rocee_ras_error(hdev);
+	if (reset_type != HNAE3_NONE_RESET)
+		HCLGE_SET_DEFAULT_RESET_REQUEST(reset_type);
 }
 
 static const struct hclge_hw_blk hw_blk[] = {
-	{ .msk = BIT(0), .name = "IGU_EGU",
-	  .enable_error = hclge_enable_igu_egu_error,
-	  .process_error = hclge_process_igu_egu_error, },
-	{ .msk = BIT(5), .name = "COMMON",
-	  .enable_error = hclge_enable_common_error,
-	  .process_error = hclge_process_common_error, },
-	{ .msk = BIT(4), .name = "TM",
-	  .enable_error = hclge_enable_tm_hw_error,
-	  .process_error = hclge_process_tm_error, },
-	{ .msk = BIT(1), .name = "PPP",
-	  .enable_error = hclge_enable_ppp_error,
-	  .process_error = hclge_process_ppp_error, },
+	{
+	  .msk = BIT(0), .name = "IGU_EGU",
+	  .config_err_int = hclge_config_igu_egu_hw_err_int,
+	},
+	{
+	  .msk = BIT(1), .name = "PPP",
+	  .config_err_int = hclge_config_ppp_hw_err_int,
+	},
+	{
+	  .msk = BIT(2), .name = "SSU",
+	  .config_err_int = hclge_config_ssu_hw_err_int,
+	},
+	{
+	  .msk = BIT(3), .name = "PPU",
+	  .config_err_int = hclge_config_ppu_hw_err_int,
+	},
+	{
+	  .msk = BIT(4), .name = "TM",
+	  .config_err_int = hclge_config_tm_hw_err_int,
+	},
+	{
+	  .msk = BIT(5), .name = "COMMON",
+	  .config_err_int = hclge_config_common_hw_err_int,
+	},
+	{
+	  .msk = BIT(8), .name = "MAC",
+	  .config_err_int = hclge_config_mac_err_int,
+	},
 	{ /* sentinel */ }
 };
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state)
 {
+	const struct hclge_hw_blk *module = hw_blk;
 	struct device *dev = &hdev->pdev->dev;
 	int ret = 0;
-	int i = 0;
 
-	while (hw_blk[i].name) {
-		if (!hw_blk[i].enable_error) {
-			i++;
-			continue;
-		}
-		ret = hw_blk[i].enable_error(hdev, state);
-		if (ret) {
-			dev_err(dev, "fail(%d) to en/disable err int\n", ret);
-			return ret;
+	while (module->name) {
+		if (module->config_err_int) {
+			ret = module->config_err_int(hdev, state);
+			if (ret)
+				return ret;
 		}
-		i++;
+		module++;
 	}
 
+	ret = hclge_config_rocee_ras_interrupt(hdev, state);
+	if (ret)
+		dev_err(dev, "fail(%d) to configure ROCEE err int\n", ret);
+
 	return ret;
 }
 
-pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev)
+pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct device *dev = &hdev->pdev->dev;
-	u32 sts, val;
-	int i = 0;
-
-	sts = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
-
-	/* Processing Non-fatal errors */
-	if (sts & HCLGE_RAS_REG_NFE_MASK) {
-		val = (sts >> HCLGE_RAS_REG_NFE_SHIFT) & 0xFF;
-		i = 0;
-		while (hw_blk[i].name) {
-			if (!(hw_blk[i].msk & val)) {
-				i++;
-				continue;
-			}
-			dev_warn(dev, "%s ras non-fatal error identified\n",
-				 hw_blk[i].name);
-			if (hw_blk[i].process_error)
-				hw_blk[i].process_error(hdev,
-							 HCLGE_ERR_INT_RAS_NFE);
-			i++;
+	u32 status;
+
+	status = hclge_read_dev(&hdev->hw, HCLGE_RAS_PF_OTHER_INT_STS_REG);
+
+	/* Handling Non-fatal HNS RAS errors */
+	if (status & HCLGE_RAS_REG_NFE_MASK) {
+		dev_warn(dev,
+			 "HNS Non-Fatal RAS error(status=0x%x) identified\n",
+			 status);
+		hclge_handle_all_ras_errors(hdev);
+	} else {
+		if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) ||
+		    hdev->pdev->revision < 0x21) {
+			ae_dev->override_pci_need_reset = 1;
+			return PCI_ERS_RESULT_RECOVERED;
 		}
 	}
 
-	return PCI_ERS_RESULT_NEED_RESET;
+	if (status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
+		dev_warn(dev, "ROCEE uncorrected RAS error identified\n");
+		hclge_handle_rocee_ras_error(ae_dev);
+	}
+
+	if (status & HCLGE_RAS_REG_NFE_MASK ||
+	    status & HCLGE_RAS_REG_ROCEE_ERR_MASK) {
+		ae_dev->override_pci_need_reset = 0;
+		return PCI_ERS_RESULT_NEED_RESET;
+	}
+	ae_dev->override_pci_need_reset = 1;
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
+			       unsigned long *reset_requests)
+{
+	struct device *dev = &hdev->pdev->dev;
+	u32 mpf_bd_num, pf_bd_num, bd_num;
+	struct hclge_desc desc_bd;
+	struct hclge_desc *desc;
+	__le32 *desc_data;
+	int ret = 0;
+	u32 status;
+
+	/* set default handling */
+	set_bit(HNAE3_FUNC_RESET, reset_requests);
+
+	/* query the number of bds for the MSIx int status */
+	hclge_cmd_setup_basic_desc(&desc_bd, HCLGE_QUERY_MSIX_INT_STS_BD_NUM,
+				   true);
+	ret = hclge_cmd_send(&hdev->hw, &desc_bd, 1);
+	if (ret) {
+		dev_err(dev, "fail(%d) to query msix int status bd num\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		return ret;
+	}
+
+	mpf_bd_num = le32_to_cpu(desc_bd.data[0]);
+	pf_bd_num = le32_to_cpu(desc_bd.data[1]);
+	bd_num = max_t(u32, mpf_bd_num, pf_bd_num);
+
+	desc = kcalloc(bd_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	/* query all main PF MSIx errors */
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_ALL_MPF_MSIX_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], mpf_bd_num);
+	if (ret) {
+		dev_err(dev, "query all mpf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		goto msi_error;
+	}
+
+	/* log MAC errors */
+	desc_data = (__le32 *)&desc[1];
+	status = le32_to_cpu(*desc_data);
+	if (status) {
+		hclge_log_error(dev, "MAC_AFIFO_TNL_INT_R",
+				&hclge_mac_afifo_tnl_int[0], status);
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+	}
+
+	/* log PPU(RCB) MPF errors */
+	desc_data = (__le32 *)&desc[5];
+	status = le32_to_cpu(*(desc_data + 2)) &
+			HCLGE_PPU_MPF_INT_ST2_MSIX_MASK;
+	if (status) {
+		hclge_log_error(dev, "PPU_MPF_ABNORMAL_INT_ST2",
+				&hclge_ppu_mpf_abnormal_int_st2[0], status);
+		set_bit(HNAE3_CORE_RESET, reset_requests);
+	}
+
+	/* clear all main PF MSIx errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], mpf_bd_num);
+	if (ret) {
+		dev_err(dev, "clear all mpf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		goto msi_error;
+	}
+
+	/* query all PF MSIx errors */
+	memset(desc, 0, bd_num * sizeof(struct hclge_desc));
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_QUERY_CLEAR_ALL_PF_MSIX_INT,
+				   true);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], pf_bd_num);
+	if (ret) {
+		dev_err(dev, "query all pf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+		goto msi_error;
+	}
+
+	/* log SSU PF errors */
+	status = le32_to_cpu(desc[0].data[0]) & HCLGE_SSU_PORT_INT_MSIX_MASK;
+	if (status) {
+		hclge_log_error(dev, "SSU_PORT_BASED_ERR_INT",
+				&hclge_ssu_port_based_pf_int[0], status);
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+	}
+
+	/* read and log PPP PF errors */
+	desc_data = (__le32 *)&desc[2];
+	status = le32_to_cpu(*desc_data);
+	if (status)
+		hclge_log_error(dev, "PPP_PF_ABNORMAL_INT_ST0",
+				&hclge_ppp_pf_abnormal_int[0], status);
+
+	/* log PPU(RCB) PF errors */
+	desc_data = (__le32 *)&desc[3];
+	status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_MSIX_MASK;
+	if (status)
+		hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST",
+				&hclge_ppu_pf_abnormal_int[0], status);
+
+	/* clear all PF MSIx errors */
+	hclge_cmd_reuse_desc(&desc[0], false);
+	desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc[0], pf_bd_num);
+	if (ret) {
+		dev_err(dev, "clear all pf msix int cmd failed (%d)\n",
+			ret);
+		/* reset everything for now */
+		set_bit(HNAE3_GLOBAL_RESET, reset_requests);
+	}
+
+msi_error:
+	kfree(desc);
+out:
+	return ret;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
index e0e3b5861495..fc068280d391 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h
@@ -7,9 +7,11 @@
 #include "hclge_main.h"
 
 #define HCLGE_RAS_PF_OTHER_INT_STS_REG   0x20B00
-#define HCLGE_RAS_REG_FE_MASK    0xFF
 #define HCLGE_RAS_REG_NFE_MASK   0xFF00
-#define HCLGE_RAS_REG_NFE_SHIFT	8
+#define HCLGE_RAS_REG_ROCEE_ERR_MASK   0x3000000
+
+#define HCLGE_VECTOR0_PF_OTHER_INT_STS_REG   0x20800
+#define HCLGE_VECTOR0_REG_MSIX_MASK   0x1FF00
 
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN	0xFFFF0000
 #define HCLGE_IMP_TCM_ECC_ERR_INT_EN_MASK	0xFFFF0000
@@ -23,6 +25,8 @@
 #define HCLGE_IMP_RD_POISON_ERR_INT_EN_MASK	0x0100
 #define HCLGE_TQP_ECC_ERR_INT_EN	0x0FFF
 #define HCLGE_TQP_ECC_ERR_INT_EN_MASK	0x0FFF
+#define HCLGE_MSIX_SRAM_ECC_ERR_INT_EN_MASK	0x0F000000
+#define HCLGE_MSIX_SRAM_ECC_ERR_INT_EN	0x0F000000
 #define HCLGE_IGU_ERR_INT_EN	0x0000066F
 #define HCLGE_IGU_ERR_INT_EN_MASK	0x000F
 #define HCLGE_IGU_TNL_ERR_INT_EN    0x0002AABF
@@ -41,21 +45,56 @@
 #define HCLGE_TM_QCN_MEM_ERR_INT_EN	0xFFFFFF
 #define HCLGE_NCSI_ERR_INT_EN	0x3
 #define HCLGE_NCSI_ERR_INT_TYPE	0x9
+#define HCLGE_MAC_COMMON_ERR_INT_EN		0x107FF
+#define HCLGE_MAC_COMMON_ERR_INT_EN_MASK	0x107FF
+#define HCLGE_PPU_MPF_ABNORMAL_INT0_EN		GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK	GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT1_EN		GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK	GENMASK(31, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN		0x3FFF3FFF
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK	0x3FFF3FFF
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN2		0xB
+#define HCLGE_PPU_MPF_ABNORMAL_INT2_EN2_MASK	0xB
+#define HCLGE_PPU_MPF_ABNORMAL_INT3_EN		GENMASK(7, 0)
+#define HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK	GENMASK(23, 16)
+#define HCLGE_PPU_PF_ABNORMAL_INT_EN		GENMASK(5, 0)
+#define HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK	GENMASK(5, 0)
+#define HCLGE_SSU_1BIT_ECC_ERR_INT_EN		GENMASK(31, 0)
+#define HCLGE_SSU_1BIT_ECC_ERR_INT_EN_MASK	GENMASK(31, 0)
+#define HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN	GENMASK(31, 0)
+#define HCLGE_SSU_MULTI_BIT_ECC_ERR_INT_EN_MASK	GENMASK(31, 0)
+#define HCLGE_SSU_BIT32_ECC_ERR_INT_EN		0x0101
+#define HCLGE_SSU_BIT32_ECC_ERR_INT_EN_MASK	0x0101
+#define HCLGE_SSU_COMMON_INT_EN			GENMASK(9, 0)
+#define HCLGE_SSU_COMMON_INT_EN_MASK		GENMASK(9, 0)
+#define HCLGE_SSU_PORT_BASED_ERR_INT_EN		0x0BFF
+#define HCLGE_SSU_PORT_BASED_ERR_INT_EN_MASK	0x0BFF0000
+#define HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN	GENMASK(23, 0)
+#define HCLGE_SSU_FIFO_OVERFLOW_ERR_INT_EN_MASK	GENMASK(23, 0)
+
+#define HCLGE_SSU_COMMON_ERR_INT_MASK	GENMASK(9, 0)
+#define HCLGE_SSU_PORT_INT_MSIX_MASK	0x7BFF
+#define HCLGE_IGU_INT_MASK		GENMASK(3, 0)
+#define HCLGE_IGU_EGU_TNL_INT_MASK	GENMASK(5, 0)
+#define HCLGE_PPP_MPF_INT_ST3_MASK	GENMASK(5, 0)
+#define HCLGE_PPU_MPF_INT_ST3_MASK	GENMASK(7, 0)
+#define HCLGE_PPU_MPF_INT_ST2_MSIX_MASK	GENMASK(29, 28)
+#define HCLGE_PPU_PF_INT_RAS_MASK	0x18
+#define HCLGE_PPU_PF_INT_MSIX_MASK	0x27
+#define HCLGE_QCN_FIFO_INT_MASK		GENMASK(17, 0)
+#define HCLGE_QCN_ECC_INT_MASK		GENMASK(21, 0)
+#define HCLGE_NCSI_ECC_INT_MASK		GENMASK(1, 0)
 
-#define HCLGE_IMP_TCM_ECC_INT_MASK	0xFFFF
-#define HCLGE_IMP_ITCM4_ECC_INT_MASK	0x3
-#define HCLGE_CMDQ_ECC_INT_MASK		0xFFFF
-#define HCLGE_CMDQ_ROC_ECC_INT_SHIFT	16
-#define HCLGE_TQP_ECC_INT_MASK		0xFFF
-#define HCLGE_TQP_ECC_INT_SHIFT		16
-#define HCLGE_IMP_TCM_ECC_CLR_MASK	0xFFFF
-#define HCLGE_IMP_ITCM4_ECC_CLR_MASK	0x3
-#define HCLGE_CMDQ_NIC_ECC_CLR_MASK	0xFFFF
-#define HCLGE_CMDQ_ROCEE_ECC_CLR_MASK	0xFFFF0000
-#define HCLGE_TQP_IMP_ERR_CLR_MASK	0x0FFF0001
-#define HCLGE_IGU_COM_INT_MASK		0xF
-#define HCLGE_IGU_EGU_TNL_INT_MASK	0x3F
-#define HCLGE_PPP_PF_INT_MASK		0x100
+#define HCLGE_ROCEE_RAS_NFE_INT_EN		0xF
+#define HCLGE_ROCEE_RAS_CE_INT_EN		0x1
+#define HCLGE_ROCEE_RAS_NFE_INT_EN_MASK		0xF
+#define HCLGE_ROCEE_RAS_CE_INT_EN_MASK		0x1
+#define HCLGE_ROCEE_RERR_INT_MASK		BIT(0)
+#define HCLGE_ROCEE_BERR_INT_MASK		BIT(1)
+#define HCLGE_ROCEE_ECC_INT_MASK		BIT(2)
+#define HCLGE_ROCEE_OVF_INT_MASK		BIT(3)
+#define HCLGE_ROCEE_OVF_ERR_INT_MASK		0x10000
+#define HCLGE_ROCEE_OVF_ERR_TYPE_MASK		0x3F
 
 enum hclge_err_int_type {
 	HCLGE_ERR_INT_MSIX = 0,
@@ -67,9 +106,7 @@ enum hclge_err_int_type {
 struct hclge_hw_blk {
 	u32 msk;
 	const char *name;
-	int (*enable_error)(struct hclge_dev *hdev, bool en);
-	void (*process_error)(struct hclge_dev *hdev,
-			      enum hclge_err_int_type type);
+	int (*config_err_int)(struct hclge_dev *hdev, bool en);
 };
 
 struct hclge_hw_error {
@@ -78,6 +115,7 @@ struct hclge_hw_error {
 };
 
 int hclge_hw_error_set_state(struct hclge_dev *hdev, bool state);
-int hclge_enable_tm_hw_error(struct hclge_dev *hdev, bool en);
-pci_ers_result_t hclge_process_ras_hw_error(struct hnae3_ae_dev *ae_dev);
+pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev);
+int hclge_handle_hw_msix_error(struct hclge_dev *hdev,
+			       unsigned long *reset_requests);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index ffdd96020860..deda606c51e7 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -26,7 +26,9 @@
 #define HCLGE_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset))))
 #define HCLGE_MAC_STATS_FIELD_OFF(f) (offsetof(struct hclge_mac_stats, f))
 
-static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu);
+#define HCLGE_BUF_SIZE_UNIT	256
+
+static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps);
 static int hclge_init_vlan_config(struct hclge_dev *hdev);
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev);
 static int hclge_set_umv_space(struct hclge_dev *hdev, u16 space_size,
@@ -48,6 +50,62 @@ static const struct pci_device_id ae_algo_pci_tbl[] = {
 
 MODULE_DEVICE_TABLE(pci, ae_algo_pci_tbl);
 
+static const u32 cmdq_reg_addr_list[] = {HCLGE_CMDQ_TX_ADDR_L_REG,
+					 HCLGE_CMDQ_TX_ADDR_H_REG,
+					 HCLGE_CMDQ_TX_DEPTH_REG,
+					 HCLGE_CMDQ_TX_TAIL_REG,
+					 HCLGE_CMDQ_TX_HEAD_REG,
+					 HCLGE_CMDQ_RX_ADDR_L_REG,
+					 HCLGE_CMDQ_RX_ADDR_H_REG,
+					 HCLGE_CMDQ_RX_DEPTH_REG,
+					 HCLGE_CMDQ_RX_TAIL_REG,
+					 HCLGE_CMDQ_RX_HEAD_REG,
+					 HCLGE_VECTOR0_CMDQ_SRC_REG,
+					 HCLGE_CMDQ_INTR_STS_REG,
+					 HCLGE_CMDQ_INTR_EN_REG,
+					 HCLGE_CMDQ_INTR_GEN_REG};
+
+static const u32 common_reg_addr_list[] = {HCLGE_MISC_VECTOR_REG_BASE,
+					   HCLGE_VECTOR0_OTER_EN_REG,
+					   HCLGE_MISC_RESET_STS_REG,
+					   HCLGE_MISC_VECTOR_INT_STS,
+					   HCLGE_GLOBAL_RESET_REG,
+					   HCLGE_FUN_RST_ING,
+					   HCLGE_GRO_EN_REG};
+
+static const u32 ring_reg_addr_list[] = {HCLGE_RING_RX_ADDR_L_REG,
+					 HCLGE_RING_RX_ADDR_H_REG,
+					 HCLGE_RING_RX_BD_NUM_REG,
+					 HCLGE_RING_RX_BD_LENGTH_REG,
+					 HCLGE_RING_RX_MERGE_EN_REG,
+					 HCLGE_RING_RX_TAIL_REG,
+					 HCLGE_RING_RX_HEAD_REG,
+					 HCLGE_RING_RX_FBD_NUM_REG,
+					 HCLGE_RING_RX_OFFSET_REG,
+					 HCLGE_RING_RX_FBD_OFFSET_REG,
+					 HCLGE_RING_RX_STASH_REG,
+					 HCLGE_RING_RX_BD_ERR_REG,
+					 HCLGE_RING_TX_ADDR_L_REG,
+					 HCLGE_RING_TX_ADDR_H_REG,
+					 HCLGE_RING_TX_BD_NUM_REG,
+					 HCLGE_RING_TX_PRIORITY_REG,
+					 HCLGE_RING_TX_TC_REG,
+					 HCLGE_RING_TX_MERGE_EN_REG,
+					 HCLGE_RING_TX_TAIL_REG,
+					 HCLGE_RING_TX_HEAD_REG,
+					 HCLGE_RING_TX_FBD_NUM_REG,
+					 HCLGE_RING_TX_OFFSET_REG,
+					 HCLGE_RING_TX_EBD_NUM_REG,
+					 HCLGE_RING_TX_EBD_OFFSET_REG,
+					 HCLGE_RING_TX_BD_ERR_REG,
+					 HCLGE_RING_EN_REG};
+
+static const u32 tqp_intr_reg_addr_list[] = {HCLGE_TQP_INTR_CTRL_REG,
+					     HCLGE_TQP_INTR_GL0_REG,
+					     HCLGE_TQP_INTR_GL1_REG,
+					     HCLGE_TQP_INTR_GL2_REG,
+					     HCLGE_TQP_INTR_RL_REG};
+
 static const char hns3_nic_test_strs[][ETH_GSTRING_LEN] = {
 	"App    Loopback test",
 	"Serdes serial Loopback test",
@@ -60,6 +118,12 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = {
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_mac_pause_num)},
 	{"mac_rx_mac_pause_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_mac_pause_num)},
+	{"mac_tx_control_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_ctrl_pkt_num)},
+	{"mac_rx_control_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_ctrl_pkt_num)},
+	{"mac_tx_pfc_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pause_pkt_num)},
 	{"mac_tx_pfc_pri0_pkt_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri0_pkt_num)},
 	{"mac_tx_pfc_pri1_pkt_num",
@@ -76,6 +140,8 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = {
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri6_pkt_num)},
 	{"mac_tx_pfc_pri7_pkt_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_tx_pfc_pri7_pkt_num)},
+	{"mac_rx_pfc_pkt_num",
+		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pause_pkt_num)},
 	{"mac_rx_pfc_pri0_pkt_num",
 		HCLGE_MAC_STATS_FIELD_OFF(mac_rx_pfc_pri0_pkt_num)},
 	{"mac_rx_pfc_pri1_pkt_num",
@@ -229,10 +295,17 @@ static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = {
 	},
 };
 
-static int hclge_mac_update_stats(struct hclge_dev *hdev)
+static const u8 hclge_hash_key[] = {
+	0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2,
+	0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0,
+	0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4,
+	0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C,
+	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA
+};
+
+static int hclge_mac_update_stats_defective(struct hclge_dev *hdev)
 {
 #define HCLGE_MAC_CMD_NUM 21
-#define HCLGE_RTN_DATA_NUM 4
 
 	u64 *data = (u64 *)(&hdev->hw_stats.mac_stats);
 	struct hclge_desc desc[HCLGE_MAC_CMD_NUM];
@@ -250,15 +323,18 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev)
 	}
 
 	for (i = 0; i < HCLGE_MAC_CMD_NUM; i++) {
+		/* for special opcode 0032, only the first desc has the head */
 		if (unlikely(i == 0)) {
 			desc_data = (__le64 *)(&desc[i].data[0]);
-			n = HCLGE_RTN_DATA_NUM - 2;
+			n = HCLGE_RD_FIRST_STATS_NUM;
 		} else {
 			desc_data = (__le64 *)(&desc[i]);
-			n = HCLGE_RTN_DATA_NUM;
+			n = HCLGE_RD_OTHER_STATS_NUM;
 		}
+
 		for (k = 0; k < n; k++) {
-			*data++ += le64_to_cpu(*desc_data);
+			*data += le64_to_cpu(*desc_data);
+			data++;
 			desc_data++;
 		}
 	}
@@ -266,6 +342,85 @@ static int hclge_mac_update_stats(struct hclge_dev *hdev)
 	return 0;
 }
 
+static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num)
+{
+	u64 *data = (u64 *)(&hdev->hw_stats.mac_stats);
+	struct hclge_desc *desc;
+	__le64 *desc_data;
+	u16 i, k, n;
+	int ret;
+
+	desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL);
+	if (!desc)
+		return -ENOMEM;
+	hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true);
+	ret = hclge_cmd_send(&hdev->hw, desc, desc_num);
+	if (ret) {
+		kfree(desc);
+		return ret;
+	}
+
+	for (i = 0; i < desc_num; i++) {
+		/* for special opcode 0034, only the first desc has the head */
+		if (i == 0) {
+			desc_data = (__le64 *)(&desc[i].data[0]);
+			n = HCLGE_RD_FIRST_STATS_NUM;
+		} else {
+			desc_data = (__le64 *)(&desc[i]);
+			n = HCLGE_RD_OTHER_STATS_NUM;
+		}
+
+		for (k = 0; k < n; k++) {
+			*data += le64_to_cpu(*desc_data);
+			data++;
+			desc_data++;
+		}
+	}
+
+	kfree(desc);
+
+	return 0;
+}
+
+static int hclge_mac_query_reg_num(struct hclge_dev *hdev, u32 *desc_num)
+{
+	struct hclge_desc desc;
+	__le32 *desc_data;
+	u32 reg_num;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_MAC_REG_NUM, true);
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		return ret;
+
+	desc_data = (__le32 *)(&desc.data[0]);
+	reg_num = le32_to_cpu(*desc_data);
+
+	*desc_num = 1 + ((reg_num - 3) >> 2) +
+		    (u32)(((reg_num - 3) & 0x3) ? 1 : 0);
+
+	return 0;
+}
+
+static int hclge_mac_update_stats(struct hclge_dev *hdev)
+{
+	u32 desc_num;
+	int ret;
+
+	ret = hclge_mac_query_reg_num(hdev, &desc_num);
+
+	/* The firmware supports the new statistics acquisition method */
+	if (!ret)
+		ret = hclge_mac_update_stats_complete(hdev, desc_num);
+	else if (ret == -EOPNOTSUPP)
+		ret = hclge_mac_update_stats_defective(hdev);
+	else
+		dev_err(&hdev->pdev->dev, "query mac reg num fail!\n");
+
+	return ret;
+}
+
 static int hclge_tqps_update_stats(struct hnae3_handle *handle)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
@@ -403,26 +558,6 @@ static u8 *hclge_comm_get_strings(u32 stringset,
 	return (u8 *)buff;
 }
 
-static void hclge_update_netstat(struct hclge_hw_stats *hw_stats,
-				 struct net_device_stats *net_stats)
-{
-	net_stats->tx_dropped = 0;
-	net_stats->rx_errors = hw_stats->mac_stats.mac_rx_oversize_pkt_num;
-	net_stats->rx_errors += hw_stats->mac_stats.mac_rx_undersize_pkt_num;
-	net_stats->rx_errors += hw_stats->mac_stats.mac_rx_fcs_err_pkt_num;
-
-	net_stats->multicast = hw_stats->mac_stats.mac_tx_multi_pkt_num;
-	net_stats->multicast += hw_stats->mac_stats.mac_rx_multi_pkt_num;
-
-	net_stats->rx_crc_errors = hw_stats->mac_stats.mac_rx_fcs_err_pkt_num;
-	net_stats->rx_length_errors =
-		hw_stats->mac_stats.mac_rx_undersize_pkt_num;
-	net_stats->rx_length_errors +=
-		hw_stats->mac_stats.mac_rx_oversize_pkt_num;
-	net_stats->rx_over_errors =
-		hw_stats->mac_stats.mac_rx_oversize_pkt_num;
-}
-
 static void hclge_update_stats_for_all(struct hclge_dev *hdev)
 {
 	struct hnae3_handle *handle;
@@ -442,8 +577,6 @@ static void hclge_update_stats_for_all(struct hclge_dev *hdev)
 	if (status)
 		dev_err(&hdev->pdev->dev,
 			"Update MAC stats fail, status = %d.\n", status);
-
-	hclge_update_netstat(&hdev->hw_stats, &handle->kinfo.netdev->stats);
 }
 
 static void hclge_update_stats(struct hnae3_handle *handle,
@@ -451,7 +584,6 @@ static void hclge_update_stats(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	struct hclge_hw_stats *hw_stats = &hdev->hw_stats;
 	int status;
 
 	if (test_and_set_bit(HCLGE_STATE_STATISTICS_UPDATING, &hdev->state))
@@ -469,8 +601,6 @@ static void hclge_update_stats(struct hnae3_handle *handle,
 			"Update TQPS stats fail, status = %d.\n",
 			status);
 
-	hclge_update_netstat(hw_stats, net_stats);
-
 	clear_bit(HCLGE_STATE_STATISTICS_UPDATING, &hdev->state);
 }
 
@@ -631,6 +761,22 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 	hdev->num_tqps = __le16_to_cpu(req->tqp_num);
 	hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
 
+	if (req->tx_buf_size)
+		hdev->tx_buf_size =
+			__le16_to_cpu(req->tx_buf_size) << HCLGE_BUF_UNIT_S;
+	else
+		hdev->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
+
+	hdev->tx_buf_size = roundup(hdev->tx_buf_size, HCLGE_BUF_SIZE_UNIT);
+
+	if (req->dv_buf_size)
+		hdev->dv_buf_size =
+			__le16_to_cpu(req->dv_buf_size) << HCLGE_BUF_UNIT_S;
+	else
+		hdev->dv_buf_size = HCLGE_DEFAULT_DV;
+
+	hdev->dv_buf_size = roundup(hdev->dv_buf_size, HCLGE_BUF_SIZE_UNIT);
+
 	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->roce_base_msix_offset =
 		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
@@ -693,37 +839,67 @@ static void hclge_parse_fiber_link_mode(struct hclge_dev *hdev,
 	unsigned long *supported = hdev->hw.mac.supported;
 
 	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT,
+				 supported);
 
 	if (speed_ability & HCLGE_SUPPORT_10G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+				 supported);
 
 	if (speed_ability & HCLGE_SUPPORT_25G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+				 supported);
 
 	if (speed_ability & HCLGE_SUPPORT_50G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+				 supported);
 
 	if (speed_ability & HCLGE_SUPPORT_100G_BIT)
-		set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
-			supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+				 supported);
 
-	set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported);
-	set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported);
+}
+
+static void hclge_parse_copper_link_mode(struct hclge_dev *hdev,
+					 u8 speed_ability)
+{
+	unsigned long *supported = hdev->hw.mac.supported;
+
+	/* default to support all speed for GE port */
+	if (!speed_ability)
+		speed_ability = HCLGE_SUPPORT_GE;
+
+	if (speed_ability & HCLGE_SUPPORT_1G_BIT)
+		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				 supported);
+
+	if (speed_ability & HCLGE_SUPPORT_100M_BIT) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+				 supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT,
+				 supported);
+	}
+
+	if (speed_ability & HCLGE_SUPPORT_10M_BIT) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported);
+	}
+
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported);
 }
 
 static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability)
 {
 	u8 media_type = hdev->hw.mac.media_type;
 
-	if (media_type != HNAE3_MEDIA_TYPE_FIBER)
-		return;
-
-	hclge_parse_fiber_link_mode(hdev, speed_ability);
+	if (media_type == HNAE3_MEDIA_TYPE_FIBER)
+		hclge_parse_fiber_link_mode(hdev, speed_ability);
+	else if (media_type == HNAE3_MEDIA_TYPE_COPPER)
+		hclge_parse_copper_link_mode(hdev, speed_ability);
 }
 
 static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
@@ -857,12 +1033,16 @@ static int hclge_configure(struct hclge_dev *hdev)
 	ether_addr_copy(hdev->hw.mac.mac_addr, cfg.mac_addr);
 	hdev->hw.mac.media_type = cfg.media_type;
 	hdev->hw.mac.phy_addr = cfg.phy_addr;
-	hdev->num_desc = cfg.tqp_desc_num;
+	hdev->num_tx_desc = cfg.tqp_desc_num;
+	hdev->num_rx_desc = cfg.tqp_desc_num;
 	hdev->tm_info.num_pg = 1;
 	hdev->tc_max = cfg.tc_num;
 	hdev->tm_info.hw_pfc_map = 0;
 	hdev->wanted_umv_size = cfg.umv_space;
 
+	if (hnae3_dev_fd_supported(hdev))
+		hdev->fd_en = true;
+
 	ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "Get wrong speed ret=%d.\n", ret);
@@ -886,7 +1066,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 		hdev->pfc_max = hdev->tc_max;
 	}
 
-	hdev->tm_info.num_tc = hdev->tc_max;
+	hdev->tm_info.num_tc = 1;
 
 	/* Currently not support uncontiuous tc */
 	for (i = 0; i < hdev->tm_info.num_tc; i++)
@@ -921,6 +1101,28 @@ static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min,
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
+static int hclge_config_gro(struct hclge_dev *hdev, bool en)
+{
+	struct hclge_cfg_gro_status_cmd *req;
+	struct hclge_desc desc;
+	int ret;
+
+	if (!hnae3_dev_gro_supported(hdev))
+		return 0;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GRO_GENERIC_CONFIG, false);
+	req = (struct hclge_cfg_gro_status_cmd *)desc.data;
+
+	req->gro_en = cpu_to_le16(en ? 1 : 0);
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"GRO hardware config cmd failed, ret = %d\n", ret);
+
+	return ret;
+}
+
 static int hclge_alloc_tqps(struct hclge_dev *hdev)
 {
 	struct hclge_tqp *tqp;
@@ -939,7 +1141,8 @@ static int hclge_alloc_tqps(struct hclge_dev *hdev)
 
 		tqp->q.ae_algo = &ae_algo;
 		tqp->q.buf_size = hdev->rx_buf_len;
-		tqp->q.desc_num = hdev->num_desc;
+		tqp->q.tx_desc_num = hdev->num_tx_desc;
+		tqp->q.rx_desc_num = hdev->num_rx_desc;
 		tqp->q.io_base = hdev->hw.io_base + HCLGE_TQP_REG_OFFSET +
 			i * HCLGE_TQP_REG_SIZE;
 
@@ -972,64 +1175,51 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 	return ret;
 }
 
-static int  hclge_assign_tqp(struct hclge_vport *vport)
+static int  hclge_assign_tqp(struct hclge_vport *vport, u16 num_tqps)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, alloced;
 
 	for (i = 0, alloced = 0; i < hdev->num_tqps &&
-	     alloced < kinfo->num_tqps; i++) {
+	     alloced < num_tqps; i++) {
 		if (!hdev->htqp[i].alloced) {
 			hdev->htqp[i].q.handle = &vport->nic;
 			hdev->htqp[i].q.tqp_index = alloced;
-			hdev->htqp[i].q.desc_num = kinfo->num_desc;
+			hdev->htqp[i].q.tx_desc_num = kinfo->num_tx_desc;
+			hdev->htqp[i].q.rx_desc_num = kinfo->num_rx_desc;
 			kinfo->tqp[alloced] = &hdev->htqp[i].q;
 			hdev->htqp[i].alloced = true;
 			alloced++;
 		}
 	}
-	vport->alloc_tqps = kinfo->num_tqps;
+	vport->alloc_tqps = alloced;
+	kinfo->rss_size = min_t(u16, hdev->rss_size_max,
+				vport->alloc_tqps / hdev->tm_info.num_tc);
 
 	return 0;
 }
 
-static int hclge_knic_setup(struct hclge_vport *vport,
-			    u16 num_tqps, u16 num_desc)
+static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps,
+			    u16 num_tx_desc, u16 num_rx_desc)
+
 {
 	struct hnae3_handle *nic = &vport->nic;
 	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
 	struct hclge_dev *hdev = vport->back;
-	int i, ret;
+	int ret;
 
-	kinfo->num_desc = num_desc;
-	kinfo->rx_buf_len = hdev->rx_buf_len;
-	kinfo->num_tc = min_t(u16, num_tqps, hdev->tm_info.num_tc);
-	kinfo->rss_size
-		= min_t(u16, hdev->rss_size_max, num_tqps / kinfo->num_tc);
-	kinfo->num_tqps = kinfo->rss_size * kinfo->num_tc;
+	kinfo->num_tx_desc = num_tx_desc;
+	kinfo->num_rx_desc = num_rx_desc;
 
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		if (hdev->hw_tc_map & BIT(i)) {
-			kinfo->tc_info[i].enable = true;
-			kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
-			kinfo->tc_info[i].tqp_count = kinfo->rss_size;
-			kinfo->tc_info[i].tc = i;
-		} else {
-			/* Set to default queue if TC is disable */
-			kinfo->tc_info[i].enable = false;
-			kinfo->tc_info[i].tqp_offset = 0;
-			kinfo->tc_info[i].tqp_count = 1;
-			kinfo->tc_info[i].tc = 0;
-		}
-	}
+	kinfo->rx_buf_len = hdev->rx_buf_len;
 
-	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps,
+	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
 	if (!kinfo->tqp)
 		return -ENOMEM;
 
-	ret = hclge_assign_tqp(vport);
+	ret = hclge_assign_tqp(vport, num_tqps);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "fail to assign TQPs %d.\n", ret);
 
@@ -1044,7 +1234,7 @@ static int hclge_map_tqp_to_vport(struct hclge_dev *hdev,
 	u16 i;
 
 	kinfo = &nic->kinfo;
-	for (i = 0; i < kinfo->num_tqps; i++) {
+	for (i = 0; i < vport->alloc_tqps; i++) {
 		struct hclge_tqp *q =
 			container_of(kinfo->tqp[i], struct hclge_tqp, q);
 		bool is_pf;
@@ -1095,7 +1285,9 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
 	nic->numa_node_mask = hdev->numa_node_mask;
 
 	if (hdev->ae_dev->dev_type == HNAE3_DEV_KNIC) {
-		ret = hclge_knic_setup(vport, num_tqps, hdev->num_desc);
+		ret = hclge_knic_setup(vport, num_tqps,
+				       hdev->num_tx_desc, hdev->num_rx_desc);
+
 		if (ret) {
 			dev_err(&hdev->pdev->dev, "knic setup failed %d\n",
 				ret);
@@ -1144,6 +1336,10 @@ static int hclge_alloc_vport(struct hclge_dev *hdev)
 	for (i = 0; i < num_vport; i++) {
 		vport->back = hdev;
 		vport->vport_id = i;
+		vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+		INIT_LIST_HEAD(&vport->vlan_list);
+		INIT_LIST_HEAD(&vport->uc_mac_list);
+		INIT_LIST_HEAD(&vport->mc_mac_list);
 
 		if (i == 0)
 			ret = hclge_vport_setup(vport, tqp_main_vport);
@@ -1176,7 +1372,7 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
 	req = (struct hclge_tx_buff_alloc_cmd *)desc.data;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0);
-	for (i = 0; i < HCLGE_TC_NUM; i++) {
+	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		u32 buf_size = buf_alloc->priv_buf[i].tx_buf_size;
 
 		req->tx_pkt_buff[i] =
@@ -1289,40 +1485,51 @@ static bool  hclge_is_rx_buf_ok(struct hclge_dev *hdev,
 {
 	u32 shared_buf_min, shared_buf_tc, shared_std;
 	int tc_num, pfc_enable_num;
-	u32 shared_buf;
+	u32 shared_buf, aligned_mps;
 	u32 rx_priv;
 	int i;
 
 	tc_num = hclge_get_tc_num(hdev);
 	pfc_enable_num = hclge_get_pfc_enalbe_num(hdev);
+	aligned_mps = roundup(hdev->mps, HCLGE_BUF_SIZE_UNIT);
 
 	if (hnae3_dev_dcb_supported(hdev))
-		shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_DV;
+		shared_buf_min = 2 * aligned_mps + hdev->dv_buf_size;
 	else
-		shared_buf_min = 2 * hdev->mps + HCLGE_DEFAULT_NON_DCB_DV;
+		shared_buf_min = aligned_mps + HCLGE_NON_DCB_ADDITIONAL_BUF
+					+ hdev->dv_buf_size;
 
-	shared_buf_tc = pfc_enable_num * hdev->mps +
-			(tc_num - pfc_enable_num) * hdev->mps / 2 +
-			hdev->mps;
-	shared_std = max_t(u32, shared_buf_min, shared_buf_tc);
+	shared_buf_tc = pfc_enable_num * aligned_mps +
+			(tc_num - pfc_enable_num) * aligned_mps / 2 +
+			aligned_mps;
+	shared_std = roundup(max_t(u32, shared_buf_min, shared_buf_tc),
+			     HCLGE_BUF_SIZE_UNIT);
 
 	rx_priv = hclge_get_rx_priv_buff_alloced(buf_alloc);
-	if (rx_all <= rx_priv + shared_std)
+	if (rx_all < rx_priv + shared_std)
 		return false;
 
-	shared_buf = rx_all - rx_priv;
+	shared_buf = rounddown(rx_all - rx_priv, HCLGE_BUF_SIZE_UNIT);
 	buf_alloc->s_buf.buf_size = shared_buf;
-	buf_alloc->s_buf.self.high = shared_buf;
-	buf_alloc->s_buf.self.low =  2 * hdev->mps;
+	if (hnae3_dev_dcb_supported(hdev)) {
+		buf_alloc->s_buf.self.high = shared_buf - hdev->dv_buf_size;
+		buf_alloc->s_buf.self.low = buf_alloc->s_buf.self.high
+			- roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
+	} else {
+		buf_alloc->s_buf.self.high = aligned_mps +
+						HCLGE_NON_DCB_ADDITIONAL_BUF;
+		buf_alloc->s_buf.self.low =
+			roundup(aligned_mps / 2, HCLGE_BUF_SIZE_UNIT);
+	}
 
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		if ((hdev->hw_tc_map & BIT(i)) &&
 		    (hdev->tm_info.hw_pfc_map & BIT(i))) {
-			buf_alloc->s_buf.tc_thrd[i].low = hdev->mps;
-			buf_alloc->s_buf.tc_thrd[i].high = 2 * hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].low = aligned_mps;
+			buf_alloc->s_buf.tc_thrd[i].high = 2 * aligned_mps;
 		} else {
 			buf_alloc->s_buf.tc_thrd[i].low = 0;
-			buf_alloc->s_buf.tc_thrd[i].high = hdev->mps;
+			buf_alloc->s_buf.tc_thrd[i].high = aligned_mps;
 		}
 	}
 
@@ -1340,13 +1547,14 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
-		if (total_size < HCLGE_DEFAULT_TX_BUF)
-			return -ENOMEM;
+		if (hdev->hw_tc_map & BIT(i)) {
+			if (total_size < hdev->tx_buf_size)
+				return -ENOMEM;
 
-		if (hdev->hw_tc_map & BIT(i))
-			priv->tx_buf_size = HCLGE_DEFAULT_TX_BUF;
-		else
+			priv->tx_buf_size = hdev->tx_buf_size;
+		} else {
 			priv->tx_buf_size = 0;
+		}
 
 		total_size -= priv->tx_buf_size;
 	}
@@ -1354,64 +1562,15 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev,
 	return 0;
 }
 
-/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
- * @hdev: pointer to struct hclge_dev
- * @buf_alloc: pointer to buffer calculation data
- * @return: 0: calculate sucessful, negative: fail
- */
-static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
-				struct hclge_pkt_buf_alloc *buf_alloc)
+static bool hclge_rx_buf_calc_all(struct hclge_dev *hdev, bool max,
+				  struct hclge_pkt_buf_alloc *buf_alloc)
 {
-#define HCLGE_BUF_SIZE_UNIT	128
-	u32 rx_all = hdev->pkt_buf_size, aligned_mps;
-	int no_pfc_priv_num, pfc_priv_num;
-	struct hclge_priv_buf *priv;
+	u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	u32 aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT);
 	int i;
 
-	aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT);
-	rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
-
-	/* When DCB is not supported, rx private
-	 * buffer is not allocated.
-	 */
-	if (!hnae3_dev_dcb_supported(hdev)) {
-		if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-			return -ENOMEM;
-
-		return 0;
-	}
-
-	/* step 1, try to alloc private buffer for all enabled tc */
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &buf_alloc->priv_buf[i];
-		if (hdev->hw_tc_map & BIT(i)) {
-			priv->enable = 1;
-			if (hdev->tm_info.hw_pfc_map & BIT(i)) {
-				priv->wl.low = aligned_mps;
-				priv->wl.high = priv->wl.low + aligned_mps;
-				priv->buf_size = priv->wl.high +
-						HCLGE_DEFAULT_DV;
-			} else {
-				priv->wl.low = 0;
-				priv->wl.high = 2 * aligned_mps;
-				priv->buf_size = priv->wl.high;
-			}
-		} else {
-			priv->enable = 0;
-			priv->wl.low = 0;
-			priv->wl.high = 0;
-			priv->buf_size = 0;
-		}
-	}
-
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-		return 0;
-
-	/* step 2, try to decrease the buffer size of
-	 * no pfc TC's private buffer
-	 */
-	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
-		priv = &buf_alloc->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
 		priv->enable = 0;
 		priv->wl.low = 0;
@@ -1424,28 +1583,30 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 		priv->enable = 1;
 
 		if (hdev->tm_info.hw_pfc_map & BIT(i)) {
-			priv->wl.low = 128;
-			priv->wl.high = priv->wl.low + aligned_mps;
-			priv->buf_size = priv->wl.high + HCLGE_DEFAULT_DV;
+			priv->wl.low = max ? aligned_mps : 256;
+			priv->wl.high = roundup(priv->wl.low + aligned_mps,
+						HCLGE_BUF_SIZE_UNIT);
 		} else {
 			priv->wl.low = 0;
-			priv->wl.high = aligned_mps;
-			priv->buf_size = priv->wl.high;
+			priv->wl.high = max ? (aligned_mps * 2) : aligned_mps;
 		}
+
+		priv->buf_size = priv->wl.high + hdev->dv_buf_size;
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-		return 0;
+	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
+}
 
-	/* step 3, try to reduce the number of pfc disabled TCs,
-	 * which have private buffer
-	 */
-	/* get the total no pfc enable TC number, which have private buffer */
-	no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
+static bool hclge_drop_nopfc_buf_till_fit(struct hclge_dev *hdev,
+					  struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	int no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc);
+	int i;
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &buf_alloc->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
 		if (hdev->hw_tc_map & BIT(i) &&
 		    !(hdev->tm_info.hw_pfc_map & BIT(i))) {
@@ -1462,17 +1623,19 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 			break;
 	}
 
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
-		return 0;
+	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
+}
 
-	/* step 4, try to reduce the number of pfc enabled TCs
-	 * which have private buffer.
-	 */
-	pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
+static bool hclge_drop_pfc_buf_till_fit(struct hclge_dev *hdev,
+					struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc);
+	int pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc);
+	int i;
 
 	/* let the last to be cleared first */
 	for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) {
-		priv = &buf_alloc->priv_buf[i];
+		struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i];
 
 		if (hdev->hw_tc_map & BIT(i) &&
 		    hdev->tm_info.hw_pfc_map & BIT(i)) {
@@ -1488,7 +1651,40 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
 		    pfc_priv_num == 0)
 			break;
 	}
-	if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
+
+	return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all);
+}
+
+/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs
+ * @hdev: pointer to struct hclge_dev
+ * @buf_alloc: pointer to buffer calculation data
+ * @return: 0: calculate sucessful, negative: fail
+ */
+static int hclge_rx_buffer_calc(struct hclge_dev *hdev,
+				struct hclge_pkt_buf_alloc *buf_alloc)
+{
+	/* When DCB is not supported, rx private buffer is not allocated. */
+	if (!hnae3_dev_dcb_supported(hdev)) {
+		u32 rx_all = hdev->pkt_buf_size;
+
+		rx_all -= hclge_get_tx_buff_alloced(buf_alloc);
+		if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all))
+			return -ENOMEM;
+
+		return 0;
+	}
+
+	if (hclge_rx_buf_calc_all(hdev, true, buf_alloc))
+		return 0;
+
+	/* try to decrease the buffer size */
+	if (hclge_rx_buf_calc_all(hdev, false, buf_alloc))
+		return 0;
+
+	if (hclge_drop_nopfc_buf_till_fit(hdev, buf_alloc))
+		return 0;
+
+	if (hclge_drop_pfc_buf_till_fit(hdev, buf_alloc))
 		return 0;
 
 	return -ENOMEM;
@@ -1873,37 +2069,6 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed,
 	return hclge_cfg_mac_speed_dup(hdev, speed, duplex);
 }
 
-static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
-					u8 *duplex)
-{
-	struct hclge_query_an_speed_dup_cmd *req;
-	struct hclge_desc desc;
-	int speed_tmp;
-	int ret;
-
-	req = (struct hclge_query_an_speed_dup_cmd *)desc.data;
-
-	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_AN_RESULT, true);
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"mac speed/autoneg/duplex query cmd failed %d\n",
-			ret);
-		return ret;
-	}
-
-	*duplex = hnae3_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
-	speed_tmp = hnae3_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
-				    HCLGE_QUERY_SPEED_S);
-
-	ret = hclge_parse_speed(speed_tmp, speed);
-	if (ret)
-		dev_err(&hdev->pdev->dev,
-			"could not parse speed(=%d), %d\n", speed_tmp, ret);
-
-	return ret;
-}
-
 static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 {
 	struct hclge_config_auto_neg_cmd *req;
@@ -1947,12 +2112,10 @@ static int hclge_get_autoneg(struct hnae3_handle *handle)
 
 static int hclge_mac_init(struct hclge_dev *hdev)
 {
-	struct hnae3_handle *handle = &hdev->vport[0].nic;
-	struct net_device *netdev = handle->kinfo.netdev;
 	struct hclge_mac *mac = &hdev->hw.mac;
-	int mtu;
 	int ret;
 
+	hdev->support_sfp_query = true;
 	hdev->hw.mac.duplex = HCLGE_MAC_FULL;
 	ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed,
 					 hdev->hw.mac.duplex);
@@ -1964,15 +2127,16 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 
 	mac->link = 0;
 
-	if (netdev)
-		mtu = netdev->mtu;
-	else
-		mtu = ETH_DATA_LEN;
+	ret = hclge_set_mac_mtu(hdev, hdev->mps);
+	if (ret) {
+		dev_err(&hdev->pdev->dev, "set mtu failed ret=%d\n", ret);
+		return ret;
+	}
 
-	ret = hclge_set_mtu(handle, mtu);
+	ret = hclge_buffer_alloc(hdev);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
-			"set mtu failed ret=%d\n", ret);
+			"allocate buffer fail, ret=%d\n", ret);
 
 	return ret;
 }
@@ -2044,7 +2208,9 @@ static int hclge_get_mac_phy_link(struct hclge_dev *hdev)
 
 static void hclge_update_link_status(struct hclge_dev *hdev)
 {
+	struct hnae3_client *rclient = hdev->roce_client;
 	struct hnae3_client *client = hdev->nic_client;
+	struct hnae3_handle *rhandle;
 	struct hnae3_handle *handle;
 	int state;
 	int i;
@@ -2056,39 +2222,67 @@ static void hclge_update_link_status(struct hclge_dev *hdev)
 		for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
 			handle = &hdev->vport[i].nic;
 			client->ops->link_status_change(handle, state);
+			rhandle = &hdev->vport[i].roce;
+			if (rclient && rclient->ops->link_status_change)
+				rclient->ops->link_status_change(rhandle,
+								 state);
 		}
 		hdev->hw.mac.link = state;
 	}
 }
 
+static int hclge_get_sfp_speed(struct hclge_dev *hdev, u32 *speed)
+{
+	struct hclge_sfp_speed_cmd *resp = NULL;
+	struct hclge_desc desc;
+	int ret;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SFP_GET_SPEED, true);
+	resp = (struct hclge_sfp_speed_cmd *)desc.data;
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret == -EOPNOTSUPP) {
+		dev_warn(&hdev->pdev->dev,
+			 "IMP do not support get SFP speed %d\n", ret);
+		return ret;
+	} else if (ret) {
+		dev_err(&hdev->pdev->dev, "get sfp speed failed %d\n", ret);
+		return ret;
+	}
+
+	*speed = resp->sfp_speed;
+
+	return 0;
+}
+
 static int hclge_update_speed_duplex(struct hclge_dev *hdev)
 {
 	struct hclge_mac mac = hdev->hw.mac;
-	u8 duplex;
 	int speed;
 	int ret;
 
-	/* get the speed and duplex as autoneg'result from mac cmd when phy
+	/* get the speed from SFP cmd when phy
 	 * doesn't exit.
 	 */
-	if (mac.phydev || !mac.autoneg)
+	if (mac.phydev)
 		return 0;
 
-	ret = hclge_query_mac_an_speed_dup(hdev, &speed, &duplex);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"mac autoneg/speed/duplex query failed %d\n", ret);
-		return ret;
-	}
+	/* if IMP does not support get SFP/qSFP speed, return directly */
+	if (!hdev->support_sfp_query)
+		return 0;
 
-	ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"mac speed/duplex config failed %d\n", ret);
+	ret = hclge_get_sfp_speed(hdev, &speed);
+	if (ret == -EOPNOTSUPP) {
+		hdev->support_sfp_query = false;
+		return ret;
+	} else if (ret) {
 		return ret;
 	}
 
-	return 0;
+	if (speed == HCLGE_MAC_SPEED_UNKNOWN)
+		return 0; /* do nothing if no SFP */
+
+	/* must config full duplex for SFP */
+	return hclge_cfg_mac_speed_dup(hdev, speed, HCLGE_MAC_FULL);
 }
 
 static int hclge_update_speed_duplex_h(struct hnae3_handle *handle)
@@ -2129,12 +2323,13 @@ static void hclge_service_complete(struct hclge_dev *hdev)
 
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
-	u32 rst_src_reg;
-	u32 cmdq_src_reg;
+	u32 rst_src_reg, cmdq_src_reg, msix_src_reg;
 
 	/* fetch the events from their corresponding regs */
 	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
 	cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
+	msix_src_reg = hclge_read_dev(&hdev->hw,
+				      HCLGE_VECTOR0_PF_OTHER_INT_STS_REG);
 
 	/* Assumption: If by any chance reset and mailbox events are reported
 	 * together then we will only process reset event in this go and will
@@ -2144,7 +2339,16 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	 */
 
 	/* check for vector0 reset event sources */
+	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
+		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
+		return HCLGE_VECTOR0_EVENT_RST;
+	}
+
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
@@ -2152,17 +2356,16 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	}
 
 	if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
+		dev_info(&hdev->pdev->dev, "core reset interrupt\n");
 		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
-	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) {
-		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
-		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
-		return HCLGE_VECTOR0_EVENT_RST;
-	}
+	/* check for vector0 msix event source */
+	if (msix_src_reg & HCLGE_VECTOR0_REG_MSIX_MASK)
+		return HCLGE_VECTOR0_EVENT_ERR;
 
 	/* check for vector0 mailbox(=CMDQ RX) event source */
 	if (BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
@@ -2214,6 +2417,19 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 
 	/* vector 0 interrupt is shared with reset and mailbox source events.*/
 	switch (event_cause) {
+	case HCLGE_VECTOR0_EVENT_ERR:
+		/* we do not know what type of reset is required now. This could
+		 * only be decided after we fetch the type of errors which
+		 * caused this event. Therefore, we will do below for now:
+		 * 1. Assert HNAE3_UNKNOWN_RESET type of reset. This means we
+		 *    have defered type of reset to be used.
+		 * 2. Schedule the reset serivce task.
+		 * 3. When service task receives  HNAE3_UNKNOWN_RESET type it
+		 *    will fetch the correct type of reset.  This would be done
+		 *    by first decoding the types of errors.
+		 */
+		set_bit(HNAE3_UNKNOWN_RESET, &hdev->reset_request);
+		/* fall through */
 	case HCLGE_VECTOR0_EVENT_RST:
 		hclge_reset_task_schedule(hdev);
 		break;
@@ -2294,8 +2510,8 @@ static void hclge_misc_irq_uninit(struct hclge_dev *hdev)
 	hclge_free_vector(hdev, 0);
 }
 
-static int hclge_notify_client(struct hclge_dev *hdev,
-			       enum hnae3_reset_notify_type type)
+int hclge_notify_client(struct hclge_dev *hdev,
+			enum hnae3_reset_notify_type type)
 {
 	struct hnae3_client *client = hdev->nic_client;
 	u16 i;
@@ -2308,21 +2524,56 @@ static int hclge_notify_client(struct hclge_dev *hdev,
 		int ret;
 
 		ret = client->ops->reset_notify(handle, type);
-		if (ret)
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"notify nic client failed %d(%d)\n", type, ret);
 			return ret;
+		}
 	}
 
 	return 0;
 }
 
+static int hclge_notify_roce_client(struct hclge_dev *hdev,
+				    enum hnae3_reset_notify_type type)
+{
+	struct hnae3_client *client = hdev->roce_client;
+	int ret = 0;
+	u16 i;
+
+	if (!client)
+		return 0;
+
+	if (!client->ops->reset_notify)
+		return -EOPNOTSUPP;
+
+	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
+		struct hnae3_handle *handle = &hdev->vport[i].roce;
+
+		ret = client->ops->reset_notify(handle, type);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"notify roce client failed %d(%d)",
+				type, ret);
+			return ret;
+		}
+	}
+
+	return ret;
+}
+
 static int hclge_reset_wait(struct hclge_dev *hdev)
 {
 #define HCLGE_RESET_WATI_MS	100
-#define HCLGE_RESET_WAIT_CNT	5
+#define HCLGE_RESET_WAIT_CNT	200
 	u32 val, reg, reg_bit;
 	u32 cnt = 0;
 
 	switch (hdev->reset_type) {
+	case HNAE3_IMP_RESET:
+		reg = HCLGE_GLOBAL_RESET_REG;
+		reg_bit = HCLGE_IMP_RESET_BIT;
+		break;
 	case HNAE3_GLOBAL_RESET:
 		reg = HCLGE_GLOBAL_RESET_REG;
 		reg_bit = HCLGE_GLOBAL_RESET_BIT;
@@ -2335,6 +2586,8 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 		reg = HCLGE_FUN_RST_ING;
 		reg_bit = HCLGE_FUN_RST_ING_B;
 		break;
+	case HNAE3_FLR_RESET:
+		break;
 	default:
 		dev_err(&hdev->pdev->dev,
 			"Wait for unsupported reset type: %d\n",
@@ -2342,6 +2595,20 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 		return -EINVAL;
 	}
 
+	if (hdev->reset_type == HNAE3_FLR_RESET) {
+		while (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state) &&
+		       cnt++ < HCLGE_RESET_WAIT_CNT)
+			msleep(HCLGE_RESET_WATI_MS);
+
+		if (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state)) {
+			dev_err(&hdev->pdev->dev,
+				"flr wait timeout: %d\n", cnt);
+			return -EBUSY;
+		}
+
+		return 0;
+	}
+
 	val = hclge_read_dev(&hdev->hw, reg);
 	while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
 		msleep(HCLGE_RESET_WATI_MS);
@@ -2358,6 +2625,55 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 	return 0;
 }
 
+static int hclge_set_vf_rst(struct hclge_dev *hdev, int func_id, bool reset)
+{
+	struct hclge_vf_rst_cmd *req;
+	struct hclge_desc desc;
+
+	req = (struct hclge_vf_rst_cmd *)desc.data;
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_GBL_RST_STATUS, false);
+	req->dest_vfid = func_id;
+
+	if (reset)
+		req->vf_rst = 0x1;
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
+static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset)
+{
+	int i;
+
+	for (i = hdev->num_vmdq_vport + 1; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+		int ret;
+
+		/* Send cmd to set/clear VF's FUNC_RST_ING */
+		ret = hclge_set_vf_rst(hdev, vport->vport_id, reset);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"set vf(%d) rst failed %d!\n",
+				vport->vport_id, ret);
+			return ret;
+		}
+
+		if (!reset)
+			continue;
+
+		/* Inform VF to process the reset.
+		 * hclge_inform_reset_assert_to_vf may fail if VF
+		 * driver is not loaded.
+		 */
+		ret = hclge_inform_reset_assert_to_vf(vport);
+		if (ret)
+			dev_warn(&hdev->pdev->dev,
+				 "inform reset to vf(%d) failed %d!\n",
+				 vport->vport_id, ret);
+	}
+
+	return 0;
+}
+
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 {
 	struct hclge_desc desc;
@@ -2396,11 +2712,16 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 		break;
 	case HNAE3_FUNC_RESET:
 		dev_info(&pdev->dev, "PF Reset requested\n");
-		hclge_func_reset_cmd(hdev, 0);
 		/* schedule again to check later */
 		set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
 		hclge_reset_task_schedule(hdev);
 		break;
+	case HNAE3_FLR_RESET:
+		dev_info(&pdev->dev, "FLR requested\n");
+		/* schedule again to check later */
+		set_bit(HNAE3_FLR_RESET, &hdev->reset_pending);
+		hclge_reset_task_schedule(hdev);
+		break;
 	default:
 		dev_warn(&pdev->dev,
 			 "Unsupported reset type: %d\n", hdev->reset_type);
@@ -2413,21 +2734,46 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hclge_dev *hdev,
 {
 	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
 
+	/* first, resolve any unknown reset type to the known type(s) */
+	if (test_bit(HNAE3_UNKNOWN_RESET, addr)) {
+		/* we will intentionally ignore any errors from this function
+		 *  as we will end up in *some* reset request in any case
+		 */
+		hclge_handle_hw_msix_error(hdev, addr);
+		clear_bit(HNAE3_UNKNOWN_RESET, addr);
+		/* We defered the clearing of the error event which caused
+		 * interrupt since it was not posssible to do that in
+		 * interrupt context (and this is the reason we introduced
+		 * new UNKNOWN reset type). Now, the errors have been
+		 * handled and cleared in hardware we can safely enable
+		 * interrupts. This is an exception to the norm.
+		 */
+		hclge_enable_vector(&hdev->misc_vector, true);
+	}
+
 	/* return the highest priority reset level amongst all */
-	if (test_bit(HNAE3_GLOBAL_RESET, addr))
+	if (test_bit(HNAE3_IMP_RESET, addr)) {
+		rst_level = HNAE3_IMP_RESET;
+		clear_bit(HNAE3_IMP_RESET, addr);
+		clear_bit(HNAE3_GLOBAL_RESET, addr);
+		clear_bit(HNAE3_CORE_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_GLOBAL_RESET, addr)) {
 		rst_level = HNAE3_GLOBAL_RESET;
-	else if (test_bit(HNAE3_CORE_RESET, addr))
+		clear_bit(HNAE3_GLOBAL_RESET, addr);
+		clear_bit(HNAE3_CORE_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_CORE_RESET, addr)) {
 		rst_level = HNAE3_CORE_RESET;
-	else if (test_bit(HNAE3_IMP_RESET, addr))
-		rst_level = HNAE3_IMP_RESET;
-	else if (test_bit(HNAE3_FUNC_RESET, addr))
+		clear_bit(HNAE3_CORE_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_FUNC_RESET, addr)) {
 		rst_level = HNAE3_FUNC_RESET;
-
-	/* now, clear all other resets */
-	clear_bit(HNAE3_GLOBAL_RESET, addr);
-	clear_bit(HNAE3_CORE_RESET, addr);
-	clear_bit(HNAE3_IMP_RESET, addr);
-	clear_bit(HNAE3_FUNC_RESET, addr);
+		clear_bit(HNAE3_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_FLR_RESET, addr)) {
+		rst_level = HNAE3_FLR_RESET;
+		clear_bit(HNAE3_FLR_RESET, addr);
+	}
 
 	return rst_level;
 }
@@ -2457,39 +2803,213 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 	hclge_enable_vector(&hdev->misc_vector, true);
 }
 
+static int hclge_reset_prepare_down(struct hclge_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+		/* fall through */
+	case HNAE3_FLR_RESET:
+		ret = hclge_set_all_vf_rst(hdev, true);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int hclge_reset_prepare_wait(struct hclge_dev *hdev)
+{
+	u32 reg_val;
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+		/* There is no mechanism for PF to know if VF has stopped IO
+		 * for now, just wait 100 ms for VF to stop IO
+		 */
+		msleep(100);
+		ret = hclge_func_reset_cmd(hdev, 0);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"asserting function reset fail %d!\n", ret);
+			return ret;
+		}
+
+		/* After performaning pf reset, it is not necessary to do the
+		 * mailbox handling or send any command to firmware, because
+		 * any mailbox handling or command to firmware is only valid
+		 * after hclge_cmd_init is called.
+		 */
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		break;
+	case HNAE3_FLR_RESET:
+		/* There is no mechanism for PF to know if VF has stopped IO
+		 * for now, just wait 100 ms for VF to stop IO
+		 */
+		msleep(100);
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+		break;
+	case HNAE3_IMP_RESET:
+		reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG);
+		hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG,
+				BIT(HCLGE_VECTOR0_IMP_RESET_INT_B) | reg_val);
+		break;
+	default:
+		break;
+	}
+
+	dev_info(&hdev->pdev->dev, "prepare wait ok\n");
+
+	return ret;
+}
+
+static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout)
+{
+#define MAX_RESET_FAIL_CNT 5
+#define RESET_UPGRADE_DELAY_SEC 10
+
+	if (hdev->reset_pending) {
+		dev_info(&hdev->pdev->dev, "Reset pending %lu\n",
+			 hdev->reset_pending);
+		return true;
+	} else if ((hdev->reset_type != HNAE3_IMP_RESET) &&
+		   (hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) &
+		    BIT(HCLGE_IMP_RESET_BIT))) {
+		dev_info(&hdev->pdev->dev,
+			 "reset failed because IMP Reset is pending\n");
+		hclge_clear_reset_cause(hdev);
+		return false;
+	} else if (hdev->reset_fail_cnt < MAX_RESET_FAIL_CNT) {
+		hdev->reset_fail_cnt++;
+		if (is_timeout) {
+			set_bit(hdev->reset_type, &hdev->reset_pending);
+			dev_info(&hdev->pdev->dev,
+				 "re-schedule to wait for hw reset done\n");
+			return true;
+		}
+
+		dev_info(&hdev->pdev->dev, "Upgrade reset level\n");
+		hclge_clear_reset_cause(hdev);
+		mod_timer(&hdev->reset_timer,
+			  jiffies + RESET_UPGRADE_DELAY_SEC * HZ);
+
+		return false;
+	}
+
+	hclge_clear_reset_cause(hdev);
+	dev_err(&hdev->pdev->dev, "Reset fail!\n");
+	return false;
+}
+
+static int hclge_reset_prepare_up(struct hclge_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_FUNC_RESET:
+		/* fall through */
+	case HNAE3_FLR_RESET:
+		ret = hclge_set_all_vf_rst(hdev, false);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
-	struct hnae3_handle *handle;
+	bool is_timeout = false;
+	int ret;
 
 	/* Initialize ae_dev reset status as well, in case enet layer wants to
 	 * know if device is undergoing reset
 	 */
 	ae_dev->reset_type = hdev->reset_type;
+	hdev->reset_count++;
 	/* perform reset of the stack & ae device for a client */
-	handle = &hdev->vport[0].nic;
+	ret = hclge_notify_roce_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	ret = hclge_reset_prepare_down(hdev);
+	if (ret)
+		goto err_reset;
+
 	rtnl_lock();
-	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
 	rtnl_unlock();
 
-	if (!hclge_reset_wait(hdev)) {
-		rtnl_lock();
-		hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
-		hclge_reset_ae_dev(hdev->ae_dev);
-		hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	ret = hclge_reset_prepare_wait(hdev);
+	if (ret)
+		goto err_reset;
 
-		hclge_clear_reset_cause(hdev);
-	} else {
-		rtnl_lock();
-		/* schedule again to check pending resets later */
-		set_bit(hdev->reset_type, &hdev->reset_pending);
-		hclge_reset_task_schedule(hdev);
+	if (hclge_reset_wait(hdev)) {
+		is_timeout = true;
+		goto err_reset;
 	}
 
-	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
-	handle->last_reset_time = jiffies;
+	ret = hclge_notify_roce_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	rtnl_lock();
+	ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
+	ret = hclge_reset_ae_dev(hdev->ae_dev);
+	if (ret)
+		goto err_reset_lock;
+
+	ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
+	ret = hclge_notify_client(hdev, HNAE3_RESTORE_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
+	hclge_clear_reset_cause(hdev);
+
+	ret = hclge_reset_prepare_up(hdev);
+	if (ret)
+		goto err_reset_lock;
+
+	ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		goto err_reset_lock;
+
 	rtnl_unlock();
+
+	ret = hclge_notify_roce_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	ret = hclge_notify_roce_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		goto err_reset;
+
+	hdev->last_reset_time = jiffies;
+	hdev->reset_fail_cnt = 0;
 	ae_dev->reset_type = HNAE3_NONE_RESET;
+
+	return;
+
+err_reset_lock:
+	rtnl_unlock();
+err_reset:
+	if (hclge_reset_err_handle(hdev, is_timeout))
+		hclge_reset_task_schedule(hdev);
 }
 
 static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
@@ -2515,20 +3035,42 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 	if (!handle)
 		handle = &hdev->vport[0].nic;
 
-	if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
+	if (time_before(jiffies, (hdev->last_reset_time + 3 * HZ)))
 		return;
-	else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
-		handle->reset_level = HNAE3_FUNC_RESET;
+	else if (hdev->default_reset_request)
+		hdev->reset_level =
+			hclge_get_reset_level(hdev,
+					      &hdev->default_reset_request);
+	else if (time_after(jiffies, (hdev->last_reset_time + 4 * 5 * HZ)))
+		hdev->reset_level = HNAE3_FUNC_RESET;
 
 	dev_info(&hdev->pdev->dev, "received reset event , reset type is %d",
-		 handle->reset_level);
+		 hdev->reset_level);
 
 	/* request reset & schedule reset task */
-	set_bit(handle->reset_level, &hdev->reset_request);
+	set_bit(hdev->reset_level, &hdev->reset_request);
 	hclge_reset_task_schedule(hdev);
 
-	if (handle->reset_level < HNAE3_GLOBAL_RESET)
-		handle->reset_level++;
+	if (hdev->reset_level < HNAE3_GLOBAL_RESET)
+		hdev->reset_level++;
+}
+
+static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
+					enum hnae3_reset_type rst_type)
+{
+	struct hclge_dev *hdev = ae_dev->priv;
+
+	set_bit(rst_type, &hdev->default_reset_request);
+}
+
+static void hclge_reset_timer(struct timer_list *t)
+{
+	struct hclge_dev *hdev = from_timer(hdev, t, reset_timer);
+
+	dev_info(&hdev->pdev->dev,
+		 "triggering global reset in reset timer\n");
+	set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request);
+	hclge_reset_event(hdev->pdev, NULL);
 }
 
 static void hclge_reset_subtask(struct hclge_dev *hdev)
@@ -2542,6 +3084,7 @@ static void hclge_reset_subtask(struct hclge_dev *hdev)
 	 *    b. else, we can come back later to check this status so re-sched
 	 *       now.
 	 */
+	hdev->last_reset_time = jiffies;
 	hdev->reset_type = hclge_get_reset_level(hdev, &hdev->reset_pending);
 	if (hdev->reset_type != HNAE3_NONE_RESET)
 		hclge_reset(hdev);
@@ -2584,6 +3127,23 @@ static void hclge_mailbox_service_task(struct work_struct *work)
 	clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
 }
 
+static void hclge_update_vport_alive(struct hclge_dev *hdev)
+{
+	int i;
+
+	/* start from vport 1 for PF is always alive */
+	for (i = 1; i < hdev->num_alloc_vport; i++) {
+		struct hclge_vport *vport = &hdev->vport[i];
+
+		if (time_after(jiffies, vport->last_active_jiffies + 8 * HZ))
+			clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+
+		/* If vf is not alive, set to default value */
+		if (!test_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state))
+			vport->mps = HCLGE_MAC_DEFAULT_FRAME;
+	}
+}
+
 static void hclge_service_task(struct work_struct *work)
 {
 	struct hclge_dev *hdev =
@@ -2596,6 +3156,7 @@ static void hclge_service_task(struct work_struct *work)
 
 	hclge_update_speed_duplex(hdev);
 	hclge_update_link_status(hdev);
+	hclge_update_vport_alive(hdev);
 	hclge_service_complete(hdev);
 }
 
@@ -3132,8 +3693,11 @@ void hclge_rss_indir_init_cfg(struct hclge_dev *hdev)
 
 static void hclge_rss_init_cfg(struct hclge_dev *hdev)
 {
+	int i, rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
 	struct hclge_vport *vport = hdev->vport;
-	int i;
+
+	if (hdev->pdev->revision >= 0x21)
+		rss_algo = HCLGE_RSS_HASH_ALGO_SIMPLE;
 
 	for (i = 0; i < hdev->num_vmdq_vport + 1; i++) {
 		vport[i].rss_tuple_sets.ipv4_tcp_en =
@@ -3153,9 +3717,10 @@ static void hclge_rss_init_cfg(struct hclge_dev *hdev)
 		vport[i].rss_tuple_sets.ipv6_fragment_en =
 			HCLGE_RSS_INPUT_TUPLE_OTHER;
 
-		vport[i].rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ;
+		vport[i].rss_algo = rss_algo;
 
-		netdev_rss_key_fill(vport[i].rss_hash_key, HCLGE_RSS_KEY_SIZE);
+		memcpy(vport[i].rss_hash_key, hclge_hash_key,
+		       HCLGE_RSS_KEY_SIZE);
 	}
 
 	hclge_rss_indir_init_cfg(hdev);
@@ -3323,8 +3888,16 @@ static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc,
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_promisc_param param;
+	bool en_bc_pmc = true;
 
-	hclge_promisc_param_init(&param, en_uc_pmc, en_mc_pmc, true,
+	/* For revision 0x20, if broadcast promisc enabled, vlan filter is
+	 * always bypassed. So broadcast promisc should be disabled until
+	 * user enable promisc mode
+	 */
+	if (handle->pdev->revision == 0x20)
+		en_bc_pmc = handle->netdev_flags & HNAE3_BPE ? true : false;
+
+	hclge_promisc_param_init(&param, en_uc_pmc, en_mc_pmc, en_bc_pmc,
 				 vport->vport_id);
 	return hclge_cmd_set_promisc_mode(hdev, &param);
 }
@@ -3433,7 +4006,6 @@ static int hclge_init_fd_config(struct hclge_dev *hdev)
 		return -EOPNOTSUPP;
 	}
 
-	hdev->fd_cfg.fd_en = true;
 	hdev->fd_cfg.proto_support =
 		TCP_V4_FLOW | UDP_V4_FLOW | SCTP_V4_FLOW | TCP_V6_FLOW |
 		UDP_V6_FLOW | SCTP_V6_FLOW | IPV4_USER_FLOW | IPV6_USER_FLOW;
@@ -4191,7 +4763,7 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 	if (!hnae3_dev_fd_supported(hdev))
 		return -EOPNOTSUPP;
 
-	if (!hdev->fd_cfg.fd_en) {
+	if (!hdev->fd_en) {
 		dev_warn(&hdev->pdev->dev,
 			 "Please enable flow director first\n");
 		return -EOPNOTSUPP;
@@ -4212,6 +4784,13 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 		u8 vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie);
 		u16 tqps;
 
+		if (vf > hdev->num_req_vfs) {
+			dev_err(&hdev->pdev->dev,
+				"Error: vf id (%d) > max vf num (%d)\n",
+				vf, hdev->num_req_vfs);
+			return -EINVAL;
+		}
+
 		dst_vport_id = vf ? hdev->vport[vf].vport_id : vport->vport_id;
 		tqps = vf ? hdev->vport[vf].alloc_tqps : vport->alloc_tqps;
 
@@ -4222,13 +4801,6 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle,
 			return -EINVAL;
 		}
 
-		if (vf > hdev->num_req_vfs) {
-			dev_err(&hdev->pdev->dev,
-				"Error: vf id (%d) > max vf num (%d)\n",
-				vf, hdev->num_req_vfs);
-			return -EINVAL;
-		}
-
 		action = HCLGE_FD_ACTION_ACCEPT_PACKET;
 		q_index = ring;
 	}
@@ -4336,8 +4908,16 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle)
 	struct hlist_node *node;
 	int ret;
 
+	/* Return ok here, because reset error handling will check this
+	 * return value. If error is returned here, the reset process will
+	 * fail.
+	 */
 	if (!hnae3_dev_fd_supported(hdev))
-		return -EOPNOTSUPP;
+		return 0;
+
+	/* if fd is disabled, should not restore it when reset */
+	if (!hdev->fd_en)
+		return 0;
 
 	hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) {
 		ret = hclge_config_action(hdev, HCLGE_FD_STAGE_1, rule);
@@ -4592,12 +5172,37 @@ static int hclge_get_all_rules(struct hnae3_handle *handle,
 	return 0;
 }
 
+static bool hclge_get_hw_reset_stat(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) ||
+	       hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING);
+}
+
+static bool hclge_ae_dev_resetting(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+}
+
+static unsigned long hclge_ae_dev_reset_cnt(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return hdev->reset_count;
+}
+
 static void hclge_enable_fd(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	hdev->fd_cfg.fd_en = enable;
+	hdev->fd_en = enable;
 	if (!enable)
 		hclge_del_all_fd_entries(handle, false);
 	else
@@ -4676,8 +5281,15 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 {
 #define HCLGE_SERDES_RETRY_MS	10
 #define HCLGE_SERDES_RETRY_NUM	100
+
+#define HCLGE_MAC_LINK_STATUS_MS   20
+#define HCLGE_MAC_LINK_STATUS_NUM  10
+#define HCLGE_MAC_LINK_STATUS_DOWN 0
+#define HCLGE_MAC_LINK_STATUS_UP   1
+
 	struct hclge_serdes_lb_cmd *req;
 	struct hclge_desc desc;
+	int mac_link_ret = 0;
 	int ret, i = 0;
 	u8 loop_mode_b;
 
@@ -4700,8 +5312,10 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 	if (en) {
 		req->enable = loop_mode_b;
 		req->mask = loop_mode_b;
+		mac_link_ret = HCLGE_MAC_LINK_STATUS_UP;
 	} else {
 		req->mask = loop_mode_b;
+		mac_link_ret = HCLGE_MAC_LINK_STATUS_DOWN;
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -4733,7 +5347,19 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en,
 	}
 
 	hclge_cfg_mac_mode(hdev, en);
-	return 0;
+
+	i = 0;
+	do {
+		/* serdes Internal loopback, independent of the network cable.*/
+		msleep(HCLGE_MAC_LINK_STATUS_MS);
+		ret = hclge_get_mac_link_status(hdev);
+		if (ret == mac_link_ret)
+			return 0;
+	} while (++i < HCLGE_MAC_LINK_STATUS_NUM);
+
+	dev_err(&hdev->pdev->dev, "config mac mode timeout\n");
+
+	return -EBUSY;
 }
 
 static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id,
@@ -4760,6 +5386,7 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 			      enum hnae3_loop loop_mode, bool en)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hnae3_knic_private_info *kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, ret;
 
@@ -4778,7 +5405,11 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 		break;
 	}
 
-	for (i = 0; i < vport->alloc_tqps; i++) {
+	if (ret)
+		return ret;
+
+	kinfo = &vport->nic.kinfo;
+	for (i = 0; i < kinfo->num_tqps; i++) {
 		ret = hclge_tqp_enable(hdev, i, 0, en);
 		if (ret)
 			return ret;
@@ -4790,30 +5421,41 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 static void hclge_reset_tqp_stats(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hnae3_knic_private_info *kinfo;
 	struct hnae3_queue *queue;
 	struct hclge_tqp *tqp;
 	int i;
 
-	for (i = 0; i < vport->alloc_tqps; i++) {
+	kinfo = &vport->nic.kinfo;
+	for (i = 0; i < kinfo->num_tqps; i++) {
 		queue = handle->kinfo.tqp[i];
 		tqp = container_of(queue, struct hclge_tqp, q);
 		memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats));
 	}
 }
 
-static int hclge_ae_start(struct hnae3_handle *handle)
+static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int i;
 
-	for (i = 0; i < vport->alloc_tqps; i++)
-		hclge_tqp_enable(hdev, i, 0, true);
+	if (enable) {
+		mod_timer(&hdev->service_timer, jiffies + HZ);
+	} else {
+		del_timer_sync(&hdev->service_timer);
+		cancel_work_sync(&hdev->service_task);
+		clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
+	}
+}
+
+static int hclge_ae_start(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 
 	/* mac enable */
 	hclge_cfg_mac_mode(hdev, true);
 	clear_bit(HCLGE_STATE_DOWN, &hdev->state);
-	mod_timer(&hdev->service_timer, jiffies + HZ);
 	hdev->hw.mac.link = 0;
 
 	/* reset tqp stats */
@@ -4832,17 +5474,17 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 
 	set_bit(HCLGE_STATE_DOWN, &hdev->state);
 
-	del_timer_sync(&hdev->service_timer);
-	cancel_work_sync(&hdev->service_task);
-	clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state);
-
-	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) {
+	/* If it is not PF reset, the firmware will disable the MAC,
+	 * so it only need to stop phy here.
+	 */
+	if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) &&
+	    hdev->reset_type != HNAE3_FUNC_RESET) {
 		hclge_mac_stop_phy(hdev);
 		return;
 	}
 
-	for (i = 0; i < vport->alloc_tqps; i++)
-		hclge_tqp_enable(hdev, i, 0, false);
+	for (i = 0; i < handle->kinfo.num_tqps; i++)
+		hclge_reset_tqp(handle, i);
 
 	/* Mac disable */
 	hclge_cfg_mac_mode(hdev, false);
@@ -4851,11 +5493,35 @@ static void hclge_ae_stop(struct hnae3_handle *handle)
 
 	/* reset tqp stats */
 	hclge_reset_tqp_stats(handle);
-	del_timer_sync(&hdev->service_timer);
-	cancel_work_sync(&hdev->service_task);
 	hclge_update_link_status(hdev);
 }
 
+int hclge_vport_start(struct hclge_vport *vport)
+{
+	set_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+	vport->last_active_jiffies = jiffies;
+	return 0;
+}
+
+void hclge_vport_stop(struct hclge_vport *vport)
+{
+	clear_bit(HCLGE_VPORT_STATE_ALIVE, &vport->state);
+}
+
+static int hclge_client_start(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	return hclge_vport_start(vport);
+}
+
+static void hclge_client_stop(struct hnae3_handle *handle)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	hclge_vport_stop(vport);
+}
+
 static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport,
 					 u16 cmdq_resp, u8  resp_code,
 					 enum hclge_mac_vlan_tbl_opcode op)
@@ -4962,13 +5628,19 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc)
 }
 
 static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req,
-				   const u8 *addr)
+				   const u8 *addr, bool is_mc)
 {
 	const unsigned char *mac_addr = addr;
 	u32 high_val = mac_addr[2] << 16 | (mac_addr[3] << 24) |
 		       (mac_addr[0]) | (mac_addr[1] << 8);
 	u32 low_val  = mac_addr[4] | (mac_addr[5] << 8);
 
+	hnae3_set_bit(new_req->flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	if (is_mc) {
+		hnae3_set_bit(new_req->entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+		hnae3_set_bit(new_req->mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	}
+
 	new_req->mac_addr_hi32 = cpu_to_le32(high_val);
 	new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff);
 }
@@ -5199,9 +5871,12 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free)
 	if (is_free) {
 		if (vport->used_umv_num > hdev->priv_umv_size)
 			hdev->share_umv_size++;
-		vport->used_umv_num--;
+
+		if (vport->used_umv_num > 0)
+			vport->used_umv_num--;
 	} else {
-		if (vport->used_umv_num >= hdev->priv_umv_size)
+		if (vport->used_umv_num >= hdev->priv_umv_size &&
+		    hdev->share_umv_size > 0)
 			hdev->share_umv_size--;
 		vport->used_umv_num++;
 	}
@@ -5239,14 +5914,13 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 
 	hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
 			HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
 
 	req.egress_port = cpu_to_le16(egress_port);
 
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, false);
 
 	/* Lookup the mac address in the mac_vlan table, and add
 	 * it if the entry is inexistent. Repeated unicast entry
@@ -5304,9 +5978,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, false);
 	ret = hclge_remove_mac_vlan_tbl(vport, &req);
 	if (!ret)
 		hclge_update_umv_space(vport, true);
@@ -5338,11 +6011,8 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport,
 		return -EINVAL;
 	}
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, true);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
 		/* This mac addr exist, update VFID for it */
@@ -5388,11 +6058,8 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hclge_prepare_mac_addr(&req, addr);
+	hclge_prepare_mac_addr(&req, addr, true);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
 		/* This mac addr exist, remove this handle's VFID for it */
@@ -5418,6 +6085,103 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 	return status;
 }
 
+void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			       enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_vport_mac_addr_cfg *mac_cfg;
+	struct list_head *list;
+
+	if (!vport->vport_id)
+		return;
+
+	mac_cfg = kzalloc(sizeof(*mac_cfg), GFP_KERNEL);
+	if (!mac_cfg)
+		return;
+
+	mac_cfg->hd_tbl_status = true;
+	memcpy(mac_cfg->mac_addr, mac_addr, ETH_ALEN);
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+	       &vport->uc_mac_list : &vport->mc_mac_list;
+
+	list_add_tail(&mac_cfg->node, list);
+}
+
+void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			      bool is_write_tbl,
+			      enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp;
+	struct list_head *list;
+	bool uc_flag, mc_flag;
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+	       &vport->uc_mac_list : &vport->mc_mac_list;
+
+	uc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_UC;
+	mc_flag = is_write_tbl && mac_type == HCLGE_MAC_ADDR_MC;
+
+	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
+		if (strncmp(mac_cfg->mac_addr, mac_addr, ETH_ALEN) == 0) {
+			if (uc_flag && mac_cfg->hd_tbl_status)
+				hclge_rm_uc_addr_common(vport, mac_addr);
+
+			if (mc_flag && mac_cfg->hd_tbl_status)
+				hclge_rm_mc_addr_common(vport, mac_addr);
+
+			list_del(&mac_cfg->node);
+			kfree(mac_cfg);
+			break;
+		}
+	}
+}
+
+void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
+				  enum HCLGE_MAC_ADDR_TYPE mac_type)
+{
+	struct hclge_vport_mac_addr_cfg *mac_cfg, *tmp;
+	struct list_head *list;
+
+	list = (mac_type == HCLGE_MAC_ADDR_UC) ?
+	       &vport->uc_mac_list : &vport->mc_mac_list;
+
+	list_for_each_entry_safe(mac_cfg, tmp, list, node) {
+		if (mac_type == HCLGE_MAC_ADDR_UC && mac_cfg->hd_tbl_status)
+			hclge_rm_uc_addr_common(vport, mac_cfg->mac_addr);
+
+		if (mac_type == HCLGE_MAC_ADDR_MC && mac_cfg->hd_tbl_status)
+			hclge_rm_mc_addr_common(vport, mac_cfg->mac_addr);
+
+		mac_cfg->hd_tbl_status = false;
+		if (is_del_list) {
+			list_del(&mac_cfg->node);
+			kfree(mac_cfg);
+		}
+	}
+}
+
+void hclge_uninit_vport_mac_table(struct hclge_dev *hdev)
+{
+	struct hclge_vport_mac_addr_cfg *mac, *tmp;
+	struct hclge_vport *vport;
+	int i;
+
+	mutex_lock(&hdev->vport_cfg_mutex);
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+		list_for_each_entry_safe(mac, tmp, &vport->uc_mac_list, node) {
+			list_del(&mac->node);
+			kfree(mac);
+		}
+
+		list_for_each_entry_safe(mac, tmp, &vport->mc_mac_list, node) {
+			list_del(&mac->node);
+			kfree(mac);
+		}
+	}
+	mutex_unlock(&hdev->vport_cfg_mutex);
+}
+
 static int hclge_get_mac_ethertype_cmd_status(struct hclge_dev *hdev,
 					      u16 cmdq_resp, u8 resp_code)
 {
@@ -5573,7 +6337,7 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr,
 }
 
 static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
-				      u8 fe_type, bool filter_en)
+				      u8 fe_type, bool filter_en, u8 vf_id)
 {
 	struct hclge_vlan_filter_ctrl_cmd *req;
 	struct hclge_desc desc;
@@ -5584,6 +6348,7 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 	req = (struct hclge_vlan_filter_ctrl_cmd *)desc.data;
 	req->vlan_type = vlan_type;
 	req->vlan_fe = filter_en ? fe_type : 0;
+	req->vf_id = vf_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
@@ -5612,12 +6377,13 @@ static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable)
 
 	if (hdev->pdev->revision >= 0x21) {
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-					   HCLGE_FILTER_FE_EGRESS, enable);
+					   HCLGE_FILTER_FE_EGRESS, enable, 0);
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
-					   HCLGE_FILTER_FE_INGRESS, enable);
+					   HCLGE_FILTER_FE_INGRESS, enable, 0);
 	} else {
 		hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-					   HCLGE_FILTER_FE_EGRESS_V1_B, enable);
+					   HCLGE_FILTER_FE_EGRESS_V1_B, enable,
+					   0);
 	}
 	if (enable)
 		handle->netdev_flags |= HNAE3_VLAN_FLTR;
@@ -5925,19 +6691,27 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 	int i;
 
 	if (hdev->pdev->revision >= 0x21) {
-		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
-						 HCLGE_FILTER_FE_EGRESS, true);
-		if (ret)
-			return ret;
+		/* for revision 0x21, vf vlan filter is per function */
+		for (i = 0; i < hdev->num_alloc_vport; i++) {
+			vport = &hdev->vport[i];
+			ret = hclge_set_vlan_filter_ctrl(hdev,
+							 HCLGE_FILTER_TYPE_VF,
+							 HCLGE_FILTER_FE_EGRESS,
+							 true,
+							 vport->vport_id);
+			if (ret)
+				return ret;
+		}
 
 		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_PORT,
-						 HCLGE_FILTER_FE_INGRESS, true);
+						 HCLGE_FILTER_FE_INGRESS, true,
+						 0);
 		if (ret)
 			return ret;
 	} else {
 		ret = hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF,
 						 HCLGE_FILTER_FE_EGRESS_V1_B,
-						 true);
+						 true, 0);
 		if (ret)
 			return ret;
 	}
@@ -5991,6 +6765,84 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev)
 	return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false);
 }
 
+void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id)
+{
+	struct hclge_vport_vlan_cfg *vlan;
+
+	/* vlan 0 is reserved */
+	if (!vlan_id)
+		return;
+
+	vlan = kzalloc(sizeof(*vlan), GFP_KERNEL);
+	if (!vlan)
+		return;
+
+	vlan->hd_tbl_status = true;
+	vlan->vlan_id = vlan_id;
+
+	list_add_tail(&vlan->node, &vport->vlan_list);
+}
+
+void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
+			       bool is_write_tbl)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_dev *hdev = vport->back;
+
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+		if (vlan->vlan_id == vlan_id) {
+			if (is_write_tbl && vlan->hd_tbl_status)
+				hclge_set_vlan_filter_hw(hdev,
+							 htons(ETH_P_8021Q),
+							 vport->vport_id,
+							 vlan_id, 0,
+							 true);
+
+			list_del(&vlan->node);
+			kfree(vlan);
+			break;
+		}
+	}
+}
+
+void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_dev *hdev = vport->back;
+
+	list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+		if (vlan->hd_tbl_status)
+			hclge_set_vlan_filter_hw(hdev,
+						 htons(ETH_P_8021Q),
+						 vport->vport_id,
+						 vlan->vlan_id, 0,
+						 true);
+
+		vlan->hd_tbl_status = false;
+		if (is_del_list) {
+			list_del(&vlan->node);
+			kfree(vlan);
+		}
+	}
+}
+
+void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev)
+{
+	struct hclge_vport_vlan_cfg *vlan, *tmp;
+	struct hclge_vport *vport;
+	int i;
+
+	mutex_lock(&hdev->vport_cfg_mutex);
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		vport = &hdev->vport[i];
+		list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) {
+			list_del(&vlan->node);
+			kfree(vlan);
+		}
+	}
+	mutex_unlock(&hdev->vport_cfg_mutex);
+}
+
 int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
@@ -6003,54 +6855,76 @@ int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable)
 	return hclge_set_vlan_rx_offload_cfg(vport);
 }
 
-static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mtu)
+static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps)
 {
 	struct hclge_config_max_frm_size_cmd *req;
 	struct hclge_desc desc;
-	int max_frm_size;
-	int ret;
-
-	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
-
-	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
-	    max_frm_size > HCLGE_MAC_MAX_FRAME)
-		return -EINVAL;
-
-	max_frm_size = max(max_frm_size, HCLGE_MAC_DEFAULT_FRAME);
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAX_FRM_SIZE, false);
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
-	req->max_frm_size = cpu_to_le16(max_frm_size);
+	req->max_frm_size = cpu_to_le16(new_mps);
 	req->min_frm_size = HCLGE_MAC_MIN_FRAME;
 
-	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret)
-		dev_err(&hdev->pdev->dev, "set mtu fail, ret =%d.\n", ret);
-	else
-		hdev->mps = max_frm_size;
-
-	return ret;
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
 }
 
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
+
+	return hclge_set_vport_mtu(vport, new_mtu);
+}
+
+int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu)
+{
 	struct hclge_dev *hdev = vport->back;
-	int ret;
+	int i, max_frm_size, ret = 0;
+
+	max_frm_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
+	if (max_frm_size < HCLGE_MAC_MIN_FRAME ||
+	    max_frm_size > HCLGE_MAC_MAX_FRAME)
+		return -EINVAL;
+
+	max_frm_size = max(max_frm_size, HCLGE_MAC_DEFAULT_FRAME);
+	mutex_lock(&hdev->vport_lock);
+	/* VF's mps must fit within hdev->mps */
+	if (vport->vport_id && max_frm_size > hdev->mps) {
+		mutex_unlock(&hdev->vport_lock);
+		return -EINVAL;
+	} else if (vport->vport_id) {
+		vport->mps = max_frm_size;
+		mutex_unlock(&hdev->vport_lock);
+		return 0;
+	}
+
+	/* PF's mps must be greater then VF's mps */
+	for (i = 1; i < hdev->num_alloc_vport; i++)
+		if (max_frm_size < hdev->vport[i].mps) {
+			mutex_unlock(&hdev->vport_lock);
+			return -EINVAL;
+		}
 
-	ret = hclge_set_mac_mtu(hdev, new_mtu);
+	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
+
+	ret = hclge_set_mac_mtu(hdev, max_frm_size);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Change mtu fail, ret =%d\n", ret);
-		return ret;
+		goto out;
 	}
 
+	hdev->mps = max_frm_size;
+	vport->mps = max_frm_size;
+
 	ret = hclge_buffer_alloc(hdev);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Allocate buffer fail, ret =%d\n", ret);
 
+out:
+	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	mutex_unlock(&hdev->vport_lock);
 	return ret;
 }
 
@@ -6098,8 +6972,7 @@ static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id)
 	return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
 }
 
-static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle,
-					  u16 queue_id)
+u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id)
 {
 	struct hnae3_queue *queue;
 	struct hclge_tqp *tqp;
@@ -6250,7 +7123,7 @@ int hclge_cfg_flowctrl(struct hclge_dev *hdev)
 	if (!phydev->link || !phydev->autoneg)
 		return 0;
 
-	local_advertising = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+	local_advertising = linkmode_adv_to_lcl_adv_t(phydev->advertising);
 
 	if (phydev->pause)
 		remote_advertising = LPA_PAUSE_CAP;
@@ -6407,16 +7280,6 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 		*tp_mdix = ETH_TP_MDI;
 }
 
-static int hclge_init_instance_hw(struct hclge_dev *hdev)
-{
-	return hclge_mac_connect_phy(hdev);
-}
-
-static void hclge_uninit_instance_hw(struct hclge_dev *hdev)
-{
-	hclge_mac_disconnect_phy(hdev);
-}
-
 static int hclge_init_client_instance(struct hnae3_client *client,
 				      struct hnae3_ae_dev *ae_dev)
 {
@@ -6436,13 +7299,6 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 			if (ret)
 				goto clear_nic;
 
-			ret = hclge_init_instance_hw(hdev);
-			if (ret) {
-			        client->ops->uninit_instance(&vport->nic,
-			                                     0);
-				goto clear_nic;
-			}
-
 			hnae3_set_client_init_flag(client, ae_dev, 1);
 
 			if (hdev->roce_client &&
@@ -6527,7 +7383,6 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 		if (client->type == HNAE3_CLIENT_ROCE)
 			return;
 		if (hdev->nic_client && client->ops->uninit_instance) {
-			hclge_uninit_instance_hw(hdev);
 			client->ops->uninit_instance(&vport->nic, 0);
 			hdev->nic_client = NULL;
 			vport->nic.client = NULL;
@@ -6612,6 +7467,8 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
 
 	if (hdev->service_timer.function)
 		del_timer_sync(&hdev->service_timer);
+	if (hdev->reset_timer.function)
+		del_timer_sync(&hdev->reset_timer);
 	if (hdev->service_task.func)
 		cancel_work_sync(&hdev->service_task);
 	if (hdev->rst_service_task.func)
@@ -6620,6 +7477,34 @@ static void hclge_state_uninit(struct hclge_dev *hdev)
 		cancel_work_sync(&hdev->mbx_service_task);
 }
 
+static void hclge_flr_prepare(struct hnae3_ae_dev *ae_dev)
+{
+#define HCLGE_FLR_WAIT_MS	100
+#define HCLGE_FLR_WAIT_CNT	50
+	struct hclge_dev *hdev = ae_dev->priv;
+	int cnt = 0;
+
+	clear_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+	clear_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+	set_bit(HNAE3_FLR_RESET, &hdev->default_reset_request);
+	hclge_reset_event(hdev->pdev, NULL);
+
+	while (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state) &&
+	       cnt++ < HCLGE_FLR_WAIT_CNT)
+		msleep(HCLGE_FLR_WAIT_MS);
+
+	if (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state))
+		dev_err(&hdev->pdev->dev,
+			"flr wait down timeout: %d\n", cnt);
+}
+
+static void hclge_flr_done(struct hnae3_ae_dev *ae_dev)
+{
+	struct hclge_dev *hdev = ae_dev->priv;
+
+	set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+}
+
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
@@ -6635,7 +7520,12 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->pdev = pdev;
 	hdev->ae_dev = ae_dev;
 	hdev->reset_type = HNAE3_NONE_RESET;
+	hdev->reset_level = HNAE3_FUNC_RESET;
 	ae_dev->priv = hdev;
+	hdev->mps = ETH_FRAME_LEN + ETH_FCS_LEN + 2 * VLAN_HLEN;
+
+	mutex_init(&hdev->vport_lock);
+	mutex_init(&hdev->vport_cfg_mutex);
 
 	ret = hclge_pci_init(hdev);
 	if (ret) {
@@ -6712,7 +7602,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	ret = hclge_init_umv_space(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "umv space init error, ret=%d.\n", ret);
-		goto err_msi_irq_uninit;
+		goto err_mdiobus_unreg;
 	}
 
 	ret = hclge_mac_init(hdev);
@@ -6727,6 +7617,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 		goto err_mdiobus_unreg;
 	}
 
+	ret = hclge_config_gro(hdev, true);
+	if (ret)
+		goto err_mdiobus_unreg;
+
 	ret = hclge_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
@@ -6762,13 +7656,14 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	ret = hclge_hw_error_set_state(hdev, true);
 	if (ret) {
 		dev_err(&pdev->dev,
-			"hw error interrupts enable failed, ret =%d\n", ret);
+			"fail(%d) to enable hw error interrupts\n", ret);
 		goto err_mdiobus_unreg;
 	}
 
 	hclge_dcb_ops_set(hdev);
 
 	timer_setup(&hdev->service_timer, hclge_service_timer, 0);
+	timer_setup(&hdev->reset_timer, hclge_reset_timer, 0);
 	INIT_WORK(&hdev->service_task, hclge_service_task);
 	INIT_WORK(&hdev->rst_service_task, hclge_reset_service_task);
 	INIT_WORK(&hdev->mbx_service_task, hclge_mailbox_service_task);
@@ -6779,6 +7674,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_enable_vector(&hdev->misc_vector, true);
 
 	hclge_state_init(hdev);
+	hdev->last_reset_time = jiffies;
 
 	pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
 	return 0;
@@ -6791,7 +7687,7 @@ err_msi_irq_uninit:
 err_msi_uninit:
 	pci_free_irq_vectors(pdev);
 err_cmd_uninit:
-	hclge_destroy_cmd_queue(&hdev->hw);
+	hclge_cmd_uninit(hdev);
 err_pci_uninit:
 	pcim_iounmap(pdev, hdev->hw.io_base);
 	pci_clear_master(pdev);
@@ -6806,6 +7702,17 @@ static void hclge_stats_clear(struct hclge_dev *hdev)
 	memset(&hdev->hw_stats, 0, sizeof(hdev->hw_stats));
 }
 
+static void hclge_reset_vport_state(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	int i;
+
+	for (i = 0; i < hdev->num_alloc_vport; i++) {
+		hclge_vport_start(vport);
+		vport++;
+	}
+}
+
 static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct hclge_dev *hdev = ae_dev->priv;
@@ -6823,19 +7730,6 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	ret = hclge_get_cap(hdev);
-	if (ret) {
-		dev_err(&pdev->dev, "get hw capability error, ret = %d.\n",
-			ret);
-		return ret;
-	}
-
-	ret = hclge_configure(hdev);
-	if (ret) {
-		dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret);
-		return ret;
-	}
-
 	ret = hclge_map_tqp(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret);
@@ -6856,13 +7750,17 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
+	ret = hclge_config_gro(hdev, true);
+	if (ret)
+		return ret;
+
 	ret = hclge_init_vlan_config(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret);
 		return ret;
 	}
 
-	ret = hclge_tm_init_hw(hdev);
+	ret = hclge_tm_init_hw(hdev, true);
 	if (ret) {
 		dev_err(&pdev->dev, "tm init hw fail, ret =%d\n", ret);
 		return ret;
@@ -6881,11 +7779,17 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev)
 		return ret;
 	}
 
-	/* Re-enable the TM hw error interrupts because
-	 * they get disabled on core/global reset.
+	/* Re-enable the hw error interrupts because
+	 * the interrupts get disabled on core/global reset.
 	 */
-	if (hclge_enable_tm_hw_error(hdev, true))
-		dev_err(&pdev->dev, "failed to enable TM hw error interrupts\n");
+	ret = hclge_hw_error_set_state(hdev, true);
+	if (ret) {
+		dev_err(&pdev->dev,
+			"fail(%d) to re-enable HNS hw error interrupts\n", ret);
+		return ret;
+	}
+
+	hclge_reset_vport_state(hdev);
 
 	dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
@@ -6910,9 +7814,13 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	synchronize_irq(hdev->misc_vector.vector_irq);
 
 	hclge_hw_error_set_state(hdev, false);
-	hclge_destroy_cmd_queue(&hdev->hw);
+	hclge_cmd_uninit(hdev);
 	hclge_misc_irq_uninit(hdev);
 	hclge_pci_uninit(hdev);
+	mutex_destroy(&hdev->vport_lock);
+	hclge_uninit_vport_mac_table(hdev);
+	hclge_uninit_vport_vlan_table(hdev);
+	mutex_destroy(&hdev->vport_cfg_mutex);
 	ae_dev->priv = NULL;
 }
 
@@ -6922,18 +7830,17 @@ static u32 hclge_get_max_channels(struct hnae3_handle *handle)
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 
-	return min_t(u32, hdev->rss_size_max * kinfo->num_tc, hdev->num_tqps);
+	return min_t(u32, hdev->rss_size_max,
+		     vport->alloc_tqps / kinfo->num_tc);
 }
 
 static void hclge_get_channels(struct hnae3_handle *handle,
 			       struct ethtool_channels *ch)
 {
-	struct hclge_vport *vport = hclge_get_vport(handle);
-
 	ch->max_combined = hclge_get_max_channels(handle);
 	ch->other_count = 1;
 	ch->max_other = 1;
-	ch->combined_count = vport->alloc_tqps;
+	ch->combined_count = handle->kinfo.rss_size;
 }
 
 static void hclge_get_tqps_and_rss_info(struct hnae3_handle *handle,
@@ -6946,26 +7853,8 @@ static void hclge_get_tqps_and_rss_info(struct hnae3_handle *handle,
 	*max_rss_size = hdev->rss_size_max;
 }
 
-static void hclge_release_tqp(struct hclge_vport *vport)
-{
-	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
-	struct hclge_dev *hdev = vport->back;
-	int i;
-
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		struct hclge_tqp *tqp =
-			container_of(kinfo->tqp[i], struct hclge_tqp, q);
-
-		tqp->q.handle = NULL;
-		tqp->q.tqp_index = 0;
-		tqp->alloced = false;
-	}
-
-	devm_kfree(&hdev->pdev->dev, kinfo->tqp);
-	kinfo->tqp = NULL;
-}
-
-static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
+static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num,
+			      bool rxfh_configured)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
@@ -6979,24 +7868,11 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 	u32 *rss_indir;
 	int ret, i;
 
-	/* Free old tqps, and reallocate with new tqp number when nic setup */
-	hclge_release_tqp(vport);
-
-	ret = hclge_knic_setup(vport, new_tqps_num, kinfo->num_desc);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "setup nic fail, ret =%d\n", ret);
-		return ret;
-	}
-
-	ret = hclge_map_tqp_to_vport(hdev, vport);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "map vport tqp fail, ret =%d\n", ret);
-		return ret;
-	}
+	kinfo->req_rss_size = new_tqps_num;
 
-	ret = hclge_tm_schd_init(hdev);
+	ret = hclge_tm_vport_map_update(hdev);
 	if (ret) {
-		dev_err(&hdev->pdev->dev, "tm schd init fail, ret =%d\n", ret);
+		dev_err(&hdev->pdev->dev, "tm vport map fail, ret =%d\n", ret);
 		return ret;
 	}
 
@@ -7017,6 +7893,10 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 	if (ret)
 		return ret;
 
+	/* RSS indirection table has been configuared by user */
+	if (rxfh_configured)
+		goto out;
+
 	/* Reinitializes the rss indirect table according to the new RSS size */
 	rss_indir = kcalloc(HCLGE_RSS_IND_TBL_SIZE, sizeof(u32), GFP_KERNEL);
 	if (!rss_indir)
@@ -7032,6 +7912,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 
 	kfree(rss_indir);
 
+out:
 	if (!ret)
 		dev_info(&hdev->pdev->dev,
 			 "Channels changed, rss_size from %d to %d, tqps from %d to %d",
@@ -7166,8 +8047,15 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num,
 	return 0;
 }
 
+#define MAX_SEPARATE_NUM	4
+#define SEPARATOR_VALUE		0xFFFFFFFF
+#define REG_NUM_PER_LINE	4
+#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+
 static int hclge_get_regs_len(struct hnae3_handle *handle)
 {
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 regs_num_32_bit, regs_num_64_bit;
@@ -7180,15 +8068,25 @@ static int hclge_get_regs_len(struct hnae3_handle *handle)
 		return -EOPNOTSUPP;
 	}
 
-	return regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64);
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+
+	return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE +
+		regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64);
 }
 
 static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 			   void *data)
 {
+	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
 	u32 regs_num_32_bit, regs_num_64_bit;
+	int i, j, reg_um, separator_num;
+	u32 *reg = data;
 	int ret;
 
 	*version = hdev->fw_version;
@@ -7200,16 +8098,53 @@ static void hclge_get_regs(struct hnae3_handle *handle, u32 *version,
 		return;
 	}
 
-	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, data);
+	/* fetching per-PF registers valus from PF PCIe register space */
+	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < kinfo->num_tqps; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						ring_reg_addr_list[i] +
+						0x200 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclge_read_dev(&hdev->hw,
+						tqp_intr_reg_addr_list[i] +
+						4 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	/* fetching PF common registers values from firmware */
+	ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Get 32 bit register failed, ret = %d.\n", ret);
 		return;
 	}
 
-	data = (u32 *)data + regs_num_32_bit;
-	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit,
-				    data);
+	reg += regs_num_32_bit;
+	ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg);
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Get 64 bit register failed, ret = %d.\n", ret);
@@ -7272,9 +8207,19 @@ static void hclge_get_link_mode(struct hnae3_handle *handle,
 	}
 }
 
+static int hclge_gro_en(struct hnae3_handle *handle, bool enable)
+{
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
+
+	return hclge_config_gro(hdev, enable);
+}
+
 static const struct hnae3_ae_ops hclge_ops = {
 	.init_ae_dev = hclge_init_ae_dev,
 	.uninit_ae_dev = hclge_uninit_ae_dev,
+	.flr_prepare = hclge_flr_prepare,
+	.flr_done = hclge_flr_done,
 	.init_client_instance = hclge_init_client_instance,
 	.uninit_client_instance = hclge_uninit_client_instance,
 	.map_ring_to_vector = hclge_map_ring_to_vector,
@@ -7285,6 +8230,8 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_loopback = hclge_set_loopback,
 	.start = hclge_ae_start,
 	.stop = hclge_ae_stop,
+	.client_start = hclge_client_start,
+	.client_stop = hclge_client_stop,
 	.get_status = hclge_get_status,
 	.get_ksettings_an_result = hclge_get_ksettings_an_result,
 	.update_speed_duplex_h = hclge_update_speed_duplex_h,
@@ -7321,6 +8268,7 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.set_vf_vlan_filter = hclge_set_vf_vlan_filter,
 	.enable_hw_strip_rxvtag = hclge_en_hw_strip_rxvtag,
 	.reset_event = hclge_reset_event,
+	.set_default_reset_request = hclge_set_def_reset_request,
 	.get_tqps_and_rss_info = hclge_get_tqps_and_rss_info,
 	.set_channels = hclge_set_channels,
 	.get_channels = hclge_get_channels,
@@ -7336,7 +8284,16 @@ static const struct hnae3_ae_ops hclge_ops = {
 	.get_fd_all_rules = hclge_get_all_rules,
 	.restore_fd_rules = hclge_restore_fd_entries,
 	.enable_fd = hclge_enable_fd,
-	.process_hw_error = hclge_process_ras_hw_error,
+	.dbg_run_cmd = hclge_dbg_run_cmd,
+	.handle_hw_ras_error = hclge_handle_hw_ras_error,
+	.get_hw_reset_stat = hclge_get_hw_reset_stat,
+	.ae_dev_resetting = hclge_ae_dev_resetting,
+	.ae_dev_reset_cnt = hclge_ae_dev_reset_cnt,
+	.set_gro_en = hclge_gro_en,
+	.get_global_queue_id = hclge_covert_handle_qid_global,
+	.set_timer_task = hclge_set_timer_task,
+	.mac_connect_phy = hclge_mac_connect_phy,
+	.mac_disconnect_phy = hclge_mac_disconnect_phy,
 };
 
 static struct hnae3_ae_algo ae_algo = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 0d9215404269..b57ac4beb313 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -16,6 +16,9 @@
 
 #define HCLGE_MAX_PF_NUM		8
 
+#define HCLGE_RD_FIRST_STATS_NUM        2
+#define HCLGE_RD_OTHER_STATS_NUM        4
+
 #define HCLGE_INVALID_VPORT 0xffff
 
 #define HCLGE_PF_CFG_BLOCK_SIZE		32
@@ -28,6 +31,62 @@
 #define HCLGE_VECTOR_REG_OFFSET		0x4
 #define HCLGE_VECTOR_VF_OFFSET		0x100000
 
+#define HCLGE_CMDQ_TX_ADDR_L_REG	0x27000
+#define HCLGE_CMDQ_TX_ADDR_H_REG	0x27004
+#define HCLGE_CMDQ_TX_DEPTH_REG		0x27008
+#define HCLGE_CMDQ_TX_TAIL_REG		0x27010
+#define HCLGE_CMDQ_TX_HEAD_REG		0x27014
+#define HCLGE_CMDQ_RX_ADDR_L_REG	0x27018
+#define HCLGE_CMDQ_RX_ADDR_H_REG	0x2701C
+#define HCLGE_CMDQ_RX_DEPTH_REG		0x27020
+#define HCLGE_CMDQ_RX_TAIL_REG		0x27024
+#define HCLGE_CMDQ_RX_HEAD_REG		0x27028
+#define HCLGE_CMDQ_INTR_SRC_REG		0x27100
+#define HCLGE_CMDQ_INTR_STS_REG		0x27104
+#define HCLGE_CMDQ_INTR_EN_REG		0x27108
+#define HCLGE_CMDQ_INTR_GEN_REG		0x2710C
+
+/* bar registers for common func */
+#define HCLGE_VECTOR0_OTER_EN_REG	0x20600
+#define HCLGE_RAS_OTHER_STS_REG		0x20B00
+#define HCLGE_FUNC_RESET_STS_REG	0x20C00
+#define HCLGE_GRO_EN_REG		0x28000
+
+/* bar registers for rcb */
+#define HCLGE_RING_RX_ADDR_L_REG	0x80000
+#define HCLGE_RING_RX_ADDR_H_REG	0x80004
+#define HCLGE_RING_RX_BD_NUM_REG	0x80008
+#define HCLGE_RING_RX_BD_LENGTH_REG	0x8000C
+#define HCLGE_RING_RX_MERGE_EN_REG	0x80014
+#define HCLGE_RING_RX_TAIL_REG		0x80018
+#define HCLGE_RING_RX_HEAD_REG		0x8001C
+#define HCLGE_RING_RX_FBD_NUM_REG	0x80020
+#define HCLGE_RING_RX_OFFSET_REG	0x80024
+#define HCLGE_RING_RX_FBD_OFFSET_REG	0x80028
+#define HCLGE_RING_RX_STASH_REG		0x80030
+#define HCLGE_RING_RX_BD_ERR_REG	0x80034
+#define HCLGE_RING_TX_ADDR_L_REG	0x80040
+#define HCLGE_RING_TX_ADDR_H_REG	0x80044
+#define HCLGE_RING_TX_BD_NUM_REG	0x80048
+#define HCLGE_RING_TX_PRIORITY_REG	0x8004C
+#define HCLGE_RING_TX_TC_REG		0x80050
+#define HCLGE_RING_TX_MERGE_EN_REG	0x80054
+#define HCLGE_RING_TX_TAIL_REG		0x80058
+#define HCLGE_RING_TX_HEAD_REG		0x8005C
+#define HCLGE_RING_TX_FBD_NUM_REG	0x80060
+#define HCLGE_RING_TX_OFFSET_REG	0x80064
+#define HCLGE_RING_TX_EBD_NUM_REG	0x80068
+#define HCLGE_RING_TX_EBD_OFFSET_REG	0x80070
+#define HCLGE_RING_TX_BD_ERR_REG	0x80074
+#define HCLGE_RING_EN_REG		0x80090
+
+/* bar registers for tqp interrupt */
+#define HCLGE_TQP_INTR_CTRL_REG		0x20000
+#define HCLGE_TQP_INTR_GL0_REG		0x20100
+#define HCLGE_TQP_INTR_GL1_REG		0x20200
+#define HCLGE_TQP_INTR_GL2_REG		0x20300
+#define HCLGE_TQP_INTR_RL_REG		0x20900
+
 #define HCLGE_RSS_IND_TBL_SIZE		512
 #define HCLGE_RSS_SET_BITMAP_MSK	GENMASK(15, 0)
 #define HCLGE_RSS_KEY_SIZE		40
@@ -97,11 +156,13 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_NETWORK_PORT_ID_M		GENMASK(3, 0)
 
 /* Reset related Registers */
+#define HCLGE_PF_OTHER_INT_REG		0x20600
 #define HCLGE_MISC_RESET_STS_REG	0x20700
 #define HCLGE_MISC_VECTOR_INT_STS	0x20800
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
 #define HCLGE_GLOBAL_RESET_BIT		0
 #define HCLGE_CORE_RESET_BIT		1
+#define HCLGE_IMP_RESET_BIT		2
 #define HCLGE_FUN_RST_ING		0x20C00
 #define HCLGE_FUN_RST_ING_B		0
 
@@ -115,8 +176,10 @@ enum HLCGE_PORT_TYPE {
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGE_VECTOR0_RX_CMDQ_INT_B	1
 
+#define HCLGE_VECTOR0_IMP_RESET_INT_B	1
+
 #define HCLGE_MAC_DEFAULT_FRAME \
-	(ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN + ETH_DATA_LEN)
+	(ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN)
 #define HCLGE_MAC_MIN_FRAME		64
 #define HCLGE_MAC_MAX_FRAME		9728
 
@@ -125,6 +188,10 @@ enum HLCGE_PORT_TYPE {
 #define HCLGE_SUPPORT_25G_BIT		BIT(2)
 #define HCLGE_SUPPORT_50G_BIT		BIT(3)
 #define HCLGE_SUPPORT_100G_BIT		BIT(4)
+#define HCLGE_SUPPORT_100M_BIT		BIT(6)
+#define HCLGE_SUPPORT_10M_BIT		BIT(7)
+#define HCLGE_SUPPORT_GE \
+	(HCLGE_SUPPORT_1G_BIT | HCLGE_SUPPORT_100M_BIT | HCLGE_SUPPORT_10M_BIT)
 
 enum HCLGE_DEV_STATE {
 	HCLGE_STATE_REINITING,
@@ -145,12 +212,14 @@ enum HCLGE_DEV_STATE {
 enum hclge_evt_cause {
 	HCLGE_VECTOR0_EVENT_RST,
 	HCLGE_VECTOR0_EVENT_MBX,
+	HCLGE_VECTOR0_EVENT_ERR,
 	HCLGE_VECTOR0_EVENT_OTHER,
 };
 
 #define HCLGE_MPF_ENBALE 1
 
 enum HCLGE_MAC_SPEED {
+	HCLGE_MAC_SPEED_UNKNOWN = 0,		/* unknown */
 	HCLGE_MAC_SPEED_10M	= 10,		/* 10 Mbps */
 	HCLGE_MAC_SPEED_100M	= 100,		/* 100 Mbps */
 	HCLGE_MAC_SPEED_1G	= 1000,		/* 1000 Mbps   = 1 Gbps */
@@ -260,6 +329,7 @@ struct hclge_tm_info {
 	struct hclge_tc_info tc_info[HNAE3_MAX_TC];
 	enum hclge_fc_mode fc_mode;
 	u8 hw_pfc_map; /* Allow for packet drop or not on this TC */
+	u8 pfc_en;	/* PFC enabled or not for user priority */
 };
 
 struct hclge_comm_stats_str {
@@ -353,6 +423,10 @@ struct hclge_mac_stats {
 	u64 mac_rx_fcs_err_pkt_num;
 	u64 mac_rx_send_app_good_pkt_num;
 	u64 mac_rx_send_app_bad_pkt_num;
+	u64 mac_tx_pfc_pause_pkt_num;
+	u64 mac_rx_pfc_pause_pkt_num;
+	u64 mac_tx_ctrl_pkt_num;
+	u64 mac_rx_ctrl_pkt_num;
 };
 
 #define HCLGE_STATS_TIMER_INTERVAL	(60 * 5)
@@ -513,7 +587,6 @@ struct hclge_fd_key_cfg {
 
 struct hclge_fd_cfg {
 	u8 fd_mode;
-	u8 fd_en;
 	u16 max_key_length;
 	u32 proto_support;
 	u32 rule_num[2]; /* rule entry number */
@@ -559,6 +632,23 @@ struct hclge_fd_ad_data {
 	u16 rule_id;
 };
 
+struct hclge_vport_mac_addr_cfg {
+	struct list_head node;
+	int hd_tbl_status;
+	u8 mac_addr[ETH_ALEN];
+};
+
+enum HCLGE_MAC_ADDR_TYPE {
+	HCLGE_MAC_ADDR_UC,
+	HCLGE_MAC_ADDR_MC
+};
+
+struct hclge_vport_vlan_cfg {
+	struct list_head node;
+	int hd_tbl_status;
+	u16 vlan_id;
+};
+
 /* For each bit of TCAM entry, it uses a pair of 'x' and
  * 'y' to indicate which value to match, like below:
  * ----------------------------------
@@ -593,10 +683,16 @@ struct hclge_dev {
 	struct hclge_misc_vector misc_vector;
 	struct hclge_hw_stats hw_stats;
 	unsigned long state;
+	unsigned long flr_state;
+	unsigned long last_reset_time;
 
 	enum hnae3_reset_type reset_type;
+	enum hnae3_reset_type reset_level;
+	unsigned long default_reset_request;
 	unsigned long reset_request;	/* reset has been requested */
 	unsigned long reset_pending;	/* client rst is pending to be served */
+	unsigned long reset_count;	/* the number of reset has been done */
+	u32 reset_fail_cnt;
 	u32 fw_version;
 	u16 num_vmdq_vport;		/* Num vmdq vport this PF has set up */
 	u16 num_tqps;			/* Num task queue pairs of this PF */
@@ -610,10 +706,12 @@ struct hclge_dev {
 	u16 num_alloc_vport;		/* Num vports this driver supports */
 	u32 numa_node_mask;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;		/* desc num of per tx queue */
+	u16 num_rx_desc;		/* desc num of per rx queue */
 	u8 hw_tc_map;
 	u8 tc_num_last_time;
 	enum hclge_fc_mode fc_mode_last_time;
+	u8 support_sfp_query;
 
 #define HCLGE_FLAG_TC_BASE_SCH_MODE		1
 #define HCLGE_FLAG_VNET_BASE_SCH_MODE		2
@@ -644,6 +742,7 @@ struct hclge_dev {
 	unsigned long service_timer_period;
 	unsigned long service_timer_previous;
 	struct timer_list service_timer;
+	struct timer_list reset_timer;
 	struct work_struct service_task;
 	struct work_struct rst_service_task;
 	struct work_struct mbx_service_task;
@@ -666,7 +765,12 @@ struct hclge_dev {
 	u32 flag;
 
 	u32 pkt_buf_size; /* Total pf buf size for tx/rx */
+	u32 tx_buf_size; /* Tx buffer size for each TC */
+	u32 dv_buf_size; /* Dv buffer size for each TC */
+
 	u32 mps; /* Max packet size */
+	/* vport_lock protect resource shared by vports */
+	struct mutex vport_lock;
 
 	struct hclge_vlan_type_cfg vlan_type_cfg;
 
@@ -675,6 +779,7 @@ struct hclge_dev {
 	struct hclge_fd_cfg fd_cfg;
 	struct hlist_head fd_rule_list;
 	u16 hclge_fd_rule_num;
+	u8 fd_en;
 
 	u16 wanted_umv_size;
 	/* max available unicast mac vlan space */
@@ -684,6 +789,8 @@ struct hclge_dev {
 	/* unicast mac vlan space shared by PF and its VFs */
 	u16 share_umv_size;
 	struct mutex umv_mutex; /* protect share_umv_size */
+
+	struct mutex vport_cfg_mutex;   /* Protect stored vf table */
 };
 
 /* VPort level vlan tag configuration for TX direction */
@@ -717,6 +824,11 @@ struct hclge_rss_tuple_cfg {
 	u8 ipv6_fragment_en;
 };
 
+enum HCLGE_VPORT_STATE {
+	HCLGE_VPORT_STATE_ALIVE,
+	HCLGE_VPORT_STATE_MAX
+};
+
 struct hclge_vport {
 	u16 alloc_tqps;	/* Allocated Tx/Rx queues */
 
@@ -742,6 +854,14 @@ struct hclge_vport {
 	struct hclge_dev *back;  /* Back reference to associated dev */
 	struct hnae3_handle nic;
 	struct hnae3_handle roce;
+
+	unsigned long state;
+	unsigned long last_active_jiffies;
+	u32 mps; /* Max packet size */
+
+	struct list_head uc_mac_list;   /* Store VF unicast table */
+	struct list_head mc_mac_list;   /* Store VF multicast table */
+	struct list_head vlan_list;     /* Store VF vlan table */
 };
 
 void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc,
@@ -768,6 +888,12 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue)
 	return tqp->index;
 }
 
+static inline bool hclge_is_reset_pending(struct hclge_dev *hdev)
+{
+	return !!hdev->reset_pending;
+}
+
+int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport);
 int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex);
 int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto,
 			  u16 vlan_id, bool is_kill);
@@ -777,9 +903,30 @@ int hclge_buffer_alloc(struct hclge_dev *hdev);
 int hclge_rss_init_hw(struct hclge_dev *hdev);
 void hclge_rss_indir_init_cfg(struct hclge_dev *hdev);
 
+int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport);
 void hclge_mbx_handler(struct hclge_dev *hdev);
 int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id);
 void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id);
 int hclge_cfg_flowctrl(struct hclge_dev *hdev);
 int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id);
+int hclge_vport_start(struct hclge_vport *vport);
+void hclge_vport_stop(struct hclge_vport *vport);
+int hclge_set_vport_mtu(struct hclge_vport *vport, int new_mtu);
+int hclge_dbg_run_cmd(struct hnae3_handle *handle, char *cmd_buf);
+u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle, u16 queue_id);
+int hclge_notify_client(struct hclge_dev *hdev,
+			enum hnae3_reset_notify_type type);
+void hclge_add_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			       enum HCLGE_MAC_ADDR_TYPE mac_type);
+void hclge_rm_vport_mac_table(struct hclge_vport *vport, const u8 *mac_addr,
+			      bool is_write_tbl,
+			      enum HCLGE_MAC_ADDR_TYPE mac_type);
+void hclge_rm_vport_all_mac_table(struct hclge_vport *vport, bool is_del_list,
+				  enum HCLGE_MAC_ADDR_TYPE mac_type);
+void hclge_uninit_vport_mac_table(struct hclge_dev *hdev);
+void hclge_add_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id);
+void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id,
+			       bool is_write_tbl);
+void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list);
+void hclge_uninit_vport_vlan_table(struct hclge_dev *hdev);
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index f890022938d9..306a23e486de 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -79,15 +79,26 @@ static int hclge_send_mbx_msg(struct hclge_vport *vport, u8 *msg, u16 msg_len,
 	return status;
 }
 
-static int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
+int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport)
 {
+	struct hclge_dev *hdev = vport->back;
+	enum hnae3_reset_type reset_type;
 	u8 msg_data[2];
 	u8 dest_vfid;
 
 	dest_vfid = (u8)vport->vport_id;
 
+	if (hdev->reset_type == HNAE3_FUNC_RESET)
+		reset_type = HNAE3_VF_PF_FUNC_RESET;
+	else if (hdev->reset_type == HNAE3_FLR_RESET)
+		reset_type = HNAE3_VF_FULL_RESET;
+	else
+		return -EINVAL;
+
+	memcpy(&msg_data[0], &reset_type, sizeof(u16));
+
 	/* send this requested info to VF */
-	return hclge_send_mbx_msg(vport, msg_data, sizeof(u8),
+	return hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
 				  HCLGE_MBX_ASSERTING_RESET, dest_vfid);
 }
 
@@ -192,12 +203,11 @@ static int hclge_map_unmap_ring_to_vf_vector(struct hclge_vport *vport, bool en,
 static int hclge_set_vf_promisc_mode(struct hclge_vport *vport,
 				     struct hclge_mbx_vf_to_pf_cmd *req)
 {
-	bool en_uc = req->msg[1] ? true : false;
-	bool en_mc = req->msg[2] ? true : false;
+	bool en_bc = req->msg[1] ? true : false;
 	struct hclge_promisc_param param;
 
-	/* always enable broadcast promisc bit */
-	hclge_promisc_param_init(&param, en_uc, en_mc, true, vport->vport_id);
+	/* vf is not allowed to enable unicast/multicast broadcast */
+	hclge_promisc_param_init(&param, false, false, en_bc, vport->vport_id);
 	return hclge_cmd_set_promisc_mode(vport->back, &param);
 }
 
@@ -214,12 +224,24 @@ static int hclge_set_vf_uc_mac_addr(struct hclge_vport *vport,
 
 		hclge_rm_uc_addr_common(vport, old_addr);
 		status = hclge_add_uc_addr_common(vport, mac_addr);
-		if (status)
+		if (status) {
 			hclge_add_uc_addr_common(vport, old_addr);
+		} else {
+			hclge_rm_vport_mac_table(vport, mac_addr,
+						 false, HCLGE_MAC_ADDR_UC);
+			hclge_add_vport_mac_table(vport, mac_addr,
+						  HCLGE_MAC_ADDR_UC);
+		}
 	} else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_UC_ADD) {
 		status = hclge_add_uc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_add_vport_mac_table(vport, mac_addr,
+						  HCLGE_MAC_ADDR_UC);
 	} else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_UC_REMOVE) {
 		status = hclge_rm_uc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_rm_vport_mac_table(vport, mac_addr,
+						 false, HCLGE_MAC_ADDR_UC);
 	} else {
 		dev_err(&hdev->pdev->dev,
 			"failed to set unicast mac addr, unknown subcode %d\n",
@@ -245,8 +267,14 @@ static int hclge_set_vf_mc_mac_addr(struct hclge_vport *vport,
 
 	if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_ADD) {
 		status = hclge_add_mc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_add_vport_mac_table(vport, mac_addr,
+						  HCLGE_MAC_ADDR_MC);
 	} else if (mbx_req->msg[1] == HCLGE_MBX_MAC_VLAN_MC_REMOVE) {
 		status = hclge_rm_mc_addr_common(vport, mac_addr);
+		if (!status)
+			hclge_rm_vport_mac_table(vport, mac_addr,
+						 false, HCLGE_MAC_ADDR_MC);
 	} else {
 		dev_err(&hdev->pdev->dev,
 			"failed to set mcast mac addr, unknown subcode %d\n",
@@ -277,6 +305,9 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
 		memcpy(&proto, &mbx_req->msg[5], sizeof(proto));
 		status = hclge_set_vlan_filter(handle, cpu_to_be16(proto),
 					       vlan, is_kill);
+		if (!status)
+			is_kill ? hclge_rm_vport_vlan_table(vport, vlan, false)
+			: hclge_add_vport_vlan_table(vport, vlan);
 	} else if (mbx_req->msg[1] == HCLGE_MBX_VLAN_RX_OFF_CFG) {
 		struct hnae3_handle *handle = &vport->nic;
 		bool en = mbx_req->msg[2] ? true : false;
@@ -290,14 +321,33 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport,
 	return status;
 }
 
+static int hclge_set_vf_alive(struct hclge_vport *vport,
+			      struct hclge_mbx_vf_to_pf_cmd *mbx_req,
+			      bool gen_resp)
+{
+	bool alive = !!mbx_req->msg[2];
+	int ret = 0;
+
+	if (alive)
+		ret = hclge_vport_start(vport);
+	else
+		hclge_vport_stop(vport);
+
+	return ret;
+}
+
 static int hclge_get_vf_tcinfo(struct hclge_vport *vport,
 			       struct hclge_mbx_vf_to_pf_cmd *mbx_req,
 			       bool gen_resp)
 {
-	struct hclge_dev *hdev = vport->back;
-	int ret;
+	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
+	u8 vf_tc_map = 0;
+	int i, ret;
 
-	ret = hclge_gen_resp_to_vf(vport, mbx_req, 0, &hdev->hw_tc_map,
+	for (i = 0; i < kinfo->num_tc; i++)
+		vf_tc_map |= BIT(i);
+
+	ret = hclge_gen_resp_to_vf(vport, mbx_req, 0, &vf_tc_map,
 				   sizeof(u8));
 
 	return ret;
@@ -307,35 +357,52 @@ static int hclge_get_vf_queue_info(struct hclge_vport *vport,
 				   struct hclge_mbx_vf_to_pf_cmd *mbx_req,
 				   bool gen_resp)
 {
-#define HCLGE_TQPS_RSS_INFO_LEN		8
+#define HCLGE_TQPS_RSS_INFO_LEN		6
 	u8 resp_data[HCLGE_TQPS_RSS_INFO_LEN];
 	struct hclge_dev *hdev = vport->back;
 
 	/* get the queue related info */
 	memcpy(&resp_data[0], &vport->alloc_tqps, sizeof(u16));
 	memcpy(&resp_data[2], &vport->nic.kinfo.rss_size, sizeof(u16));
-	memcpy(&resp_data[4], &hdev->num_desc, sizeof(u16));
-	memcpy(&resp_data[6], &hdev->rx_buf_len, sizeof(u16));
+	memcpy(&resp_data[4], &hdev->rx_buf_len, sizeof(u16));
 
 	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
 				    HCLGE_TQPS_RSS_INFO_LEN);
 }
 
+static int hclge_get_vf_queue_depth(struct hclge_vport *vport,
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req,
+				    bool gen_resp)
+{
+#define HCLGE_TQPS_DEPTH_INFO_LEN	4
+	u8 resp_data[HCLGE_TQPS_DEPTH_INFO_LEN];
+	struct hclge_dev *hdev = vport->back;
+
+	/* get the queue depth info */
+	memcpy(&resp_data[0], &hdev->num_tx_desc, sizeof(u16));
+	memcpy(&resp_data[2], &hdev->num_rx_desc, sizeof(u16));
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
+				    HCLGE_TQPS_DEPTH_INFO_LEN);
+}
+
 static int hclge_get_link_info(struct hclge_vport *vport,
 			       struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
 	struct hclge_dev *hdev = vport->back;
 	u16 link_status;
-	u8 msg_data[8];
+	u8 msg_data[10];
+	u16 media_type;
 	u8 dest_vfid;
 	u16 duplex;
 
 	/* mac.link can only be 0 or 1 */
 	link_status = (u16)hdev->hw.mac.link;
 	duplex = hdev->hw.mac.duplex;
+	media_type = hdev->hw.mac.media_type;
 	memcpy(&msg_data[0], &link_status, sizeof(u16));
 	memcpy(&msg_data[2], &hdev->hw.mac.speed, sizeof(u32));
 	memcpy(&msg_data[6], &duplex, sizeof(u16));
+	memcpy(&msg_data[8], &media_type, sizeof(u16));
 	dest_vfid = mbx_req->mbx_src_vfid;
 
 	/* send this requested info to VF */
@@ -343,6 +410,29 @@ static int hclge_get_link_info(struct hclge_vport *vport,
 				  HCLGE_MBX_LINK_STAT_CHANGE, dest_vfid);
 }
 
+static void hclge_get_link_mode(struct hclge_vport *vport,
+				struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+#define HCLGE_SUPPORTED   1
+	struct hclge_dev *hdev = vport->back;
+	unsigned long advertising;
+	unsigned long supported;
+	unsigned long send_data;
+	u8 msg_data[10];
+	u8 dest_vfid;
+
+	advertising = hdev->hw.mac.advertising[0];
+	supported = hdev->hw.mac.supported[0];
+	dest_vfid = mbx_req->mbx_src_vfid;
+	msg_data[0] = mbx_req->msg[2];
+
+	send_data = msg_data[0] == HCLGE_SUPPORTED ? supported : advertising;
+
+	memcpy(&msg_data[2], &send_data, sizeof(unsigned long));
+	hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data),
+			   HCLGE_MBX_LINK_STAT_MODE, dest_vfid);
+}
+
 static void hclge_mbx_reset_vf_queue(struct hclge_vport *vport,
 				     struct hclge_mbx_vf_to_pf_cmd *mbx_req)
 {
@@ -363,24 +453,59 @@ static void hclge_reset_vf(struct hclge_vport *vport,
 	int ret;
 
 	dev_warn(&hdev->pdev->dev, "PF received VF reset request from VF %d!",
-		 mbx_req->mbx_src_vfid);
-
-	/* Acknowledge VF that PF is now about to assert the reset for the VF.
-	 * On receiving this message VF will get into pending state and will
-	 * start polling for the hardware reset completion status.
-	 */
-	ret = hclge_inform_reset_assert_to_vf(vport);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"PF fail(%d) to inform VF(%d)of reset, reset failed!\n",
-			ret, vport->vport_id);
-		return;
-	}
+		 vport->vport_id);
+
+	ret = hclge_func_reset_cmd(hdev, vport->vport_id);
+	hclge_gen_resp_to_vf(vport, mbx_req, ret, NULL, 0);
+}
 
-	dev_warn(&hdev->pdev->dev, "PF is now resetting VF %d.\n",
-		 mbx_req->mbx_src_vfid);
-	/* reset this virtual function */
-	hclge_func_reset_cmd(hdev, mbx_req->mbx_src_vfid);
+static void hclge_vf_keep_alive(struct hclge_vport *vport,
+				struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	vport->last_active_jiffies = jiffies;
+}
+
+static int hclge_set_vf_mtu(struct hclge_vport *vport,
+			    struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	int ret;
+	u32 mtu;
+
+	memcpy(&mtu, &mbx_req->msg[2], sizeof(mtu));
+	ret = hclge_set_vport_mtu(vport, mtu);
+
+	return hclge_gen_resp_to_vf(vport, mbx_req, ret, NULL, 0);
+}
+
+static int hclge_get_queue_id_in_pf(struct hclge_vport *vport,
+				    struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+	u16 queue_id, qid_in_pf;
+	u8 resp_data[2];
+
+	memcpy(&queue_id, &mbx_req->msg[2], sizeof(queue_id));
+	qid_in_pf = hclge_covert_handle_qid_global(&vport->nic, queue_id);
+	memcpy(resp_data, &qid_in_pf, sizeof(qid_in_pf));
+
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data, 2);
+}
+
+static int hclge_get_rss_key(struct hclge_vport *vport,
+			     struct hclge_mbx_vf_to_pf_cmd *mbx_req)
+{
+#define HCLGE_RSS_MBX_RESP_LEN	8
+	u8 resp_data[HCLGE_RSS_MBX_RESP_LEN];
+	struct hclge_dev *hdev = vport->back;
+	u8 index;
+
+	index = mbx_req->msg[2];
+
+	memcpy(&resp_data[0],
+	       &hdev->vport[0].rss_hash_key[index * HCLGE_RSS_MBX_RESP_LEN],
+	       HCLGE_RSS_MBX_RESP_LEN);
+
+	return hclge_gen_resp_to_vf(vport, mbx_req, 0, resp_data,
+				    HCLGE_RSS_MBX_RESP_LEN);
 }
 
 static bool hclge_cmd_crq_empty(struct hclge_hw *hw)
@@ -460,6 +585,13 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					"PF failed(%d) to config VF's VLAN\n",
 					ret);
 			break;
+		case HCLGE_MBX_SET_ALIVE:
+			ret = hclge_set_vf_alive(vport, req, false);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF failed(%d) to set VF's ALIVE\n",
+					ret);
+			break;
 		case HCLGE_MBX_GET_QINFO:
 			ret = hclge_get_vf_queue_info(vport, req, true);
 			if (ret)
@@ -467,6 +599,14 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 					"PF failed(%d) to get Q info for VF\n",
 					ret);
 			break;
+		case HCLGE_MBX_GET_QDEPTH:
+			ret = hclge_get_vf_queue_depth(vport, req, true);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF failed(%d) to get Q depth for VF\n",
+					ret);
+			break;
+
 		case HCLGE_MBX_GET_TCINFO:
 			ret = hclge_get_vf_tcinfo(vport, req, true);
 			if (ret)
@@ -487,6 +627,41 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		case HCLGE_MBX_RESET:
 			hclge_reset_vf(vport, req);
 			break;
+		case HCLGE_MBX_KEEP_ALIVE:
+			hclge_vf_keep_alive(vport, req);
+			break;
+		case HCLGE_MBX_SET_MTU:
+			ret = hclge_set_vf_mtu(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"VF fail(%d) to set mtu\n", ret);
+			break;
+		case HCLGE_MBX_GET_QID_IN_PF:
+			ret = hclge_get_queue_id_in_pf(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF failed(%d) to get qid for VF\n",
+					ret);
+			break;
+		case HCLGE_MBX_GET_RSS_KEY:
+			ret = hclge_get_rss_key(vport, req);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"PF fail(%d) to get rss key for VF\n",
+					ret);
+			break;
+		case HCLGE_MBX_GET_LINK_MODE:
+			hclge_get_link_mode(vport, req);
+			break;
+		case HCLGE_MBX_GET_VF_FLR_STATUS:
+			mutex_lock(&hdev->vport_cfg_mutex);
+			hclge_rm_vport_all_mac_table(vport, true,
+						     HCLGE_MAC_ADDR_UC);
+			hclge_rm_vport_all_mac_table(vport, true,
+						     HCLGE_MAC_ADDR_MC);
+			hclge_rm_vport_all_vlan_table(vport, true);
+			mutex_unlock(&hdev->vport_cfg_mutex);
+			break;
 		default:
 			dev_err(&hdev->pdev->dev,
 				"un-supported mailbox message, code = %d\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 03018638f701..48eda2c6fdae 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -8,12 +8,6 @@
 #include "hclge_main.h"
 #include "hclge_mdio.h"
 
-#define HCLGE_PHY_SUPPORTED_FEATURES	(SUPPORTED_Autoneg | \
-					 SUPPORTED_TP | \
-					 PHY_10BT_FEATURES | \
-					 PHY_100BT_FEATURES | \
-					 PHY_1000BT_FEATURES)
-
 enum hclge_mdio_c22_op_seq {
 	HCLGE_MDIO_C22_WRITE = 1,
 	HCLGE_MDIO_C22_READ = 2
@@ -179,6 +173,10 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
 	int duplex, speed;
 	int ret;
 
+	/* When phy link down, do nothing */
+	if (netdev->phydev->link == 0)
+		return;
+
 	speed = netdev->phydev->speed;
 	duplex = netdev->phydev->duplex;
 
@@ -191,16 +189,19 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
 		netdev_err(netdev, "failed to configure flow control.\n");
 }
 
-int hclge_mac_connect_phy(struct hclge_dev *hdev)
+int hclge_mac_connect_phy(struct hnae3_handle *handle)
 {
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	int ret;
 
 	if (!phydev)
 		return 0;
 
-	phydev->supported &= ~SUPPORTED_FIBRE;
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported);
 
 	ret = phy_connect_direct(netdev, phydev,
 				 hclge_mac_adjust_link,
@@ -210,14 +211,17 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev)
 		return ret;
 	}
 
-	phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES;
-	phy_support_asym_pause(phydev);
+	linkmode_copy(mask, hdev->hw.mac.supported);
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	return 0;
 }
 
-void hclge_mac_disconnect_phy(struct hclge_dev *hdev)
+void hclge_mac_disconnect_phy(struct hnae3_handle *handle)
 {
+	struct hclge_vport *vport = hclge_get_vport(handle);
+	struct hclge_dev *hdev = vport->back;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
 
 	if (!phydev)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index 5fbf7dddb5d9..ef095d9c566f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -5,8 +5,8 @@
 #define __HCLGE_MDIO_H
 
 int hclge_mac_mdio_config(struct hclge_dev *hdev);
-int hclge_mac_connect_phy(struct hclge_dev *hdev);
-void hclge_mac_disconnect_phy(struct hclge_dev *hdev);
+int hclge_mac_connect_phy(struct hnae3_handle *handle);
+void hclge_mac_disconnect_phy(struct hnae3_handle *handle);
 void hclge_mac_start_phy(struct hclge_dev *hdev);
 void hclge_mac_stop_phy(struct hclge_dev *hdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 494e562fe8c7..aafc69f4bfdd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -517,20 +517,39 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
+	u16 max_rss_size;
 	u8 i;
 
-	vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit;
-	kinfo->num_tc =
-		min_t(u16, kinfo->num_tqps, hdev->tm_info.num_tc);
-	kinfo->rss_size
-		= min_t(u16, hdev->rss_size_max,
-			kinfo->num_tqps / kinfo->num_tc);
-	vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id;
+	/* TC configuration is shared by PF/VF in one port, only allow
+	 * one tc for VF for simplicity. VF's vport_id is non zero.
+	 */
+	kinfo->num_tc = vport->vport_id ? 1 :
+			min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc);
+	vport->qs_offset = (vport->vport_id ? hdev->tm_info.num_tc : 0) +
+				(vport->vport_id ? (vport->vport_id - 1) : 0);
+
+	max_rss_size = min_t(u16, hdev->rss_size_max,
+			     vport->alloc_tqps / kinfo->num_tc);
+
+	if (kinfo->req_rss_size != kinfo->rss_size && kinfo->req_rss_size &&
+	    kinfo->req_rss_size <= max_rss_size) {
+		dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n",
+			 kinfo->rss_size, kinfo->req_rss_size);
+		kinfo->rss_size = kinfo->req_rss_size;
+	} else if (kinfo->rss_size > max_rss_size ||
+		   (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) {
+		dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n",
+			 kinfo->rss_size, max_rss_size);
+		kinfo->rss_size = max_rss_size;
+	}
+
+	kinfo->num_tqps = kinfo->num_tc * kinfo->rss_size;
 	vport->dwrr = 100;  /* 100 percent as init */
 	vport->alloc_rss_size = kinfo->rss_size;
+	vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit;
 
-	for (i = 0; i < kinfo->num_tc; i++) {
-		if (hdev->hw_tc_map & BIT(i)) {
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		if (hdev->hw_tc_map & BIT(i) && i < kinfo->num_tc) {
 			kinfo->tc_info[i].enable = true;
 			kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size;
 			kinfo->tc_info[i].tqp_count = kinfo->rss_size;
@@ -753,13 +772,17 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev)
 
 	if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) {
 		/* Cfg qs -> pri mapping, one by one mapping */
-		for (k = 0; k < hdev->num_alloc_vport; k++)
-			for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		for (k = 0; k < hdev->num_alloc_vport; k++) {
+			struct hnae3_knic_private_info *kinfo =
+				&vport[k].nic.kinfo;
+
+			for (i = 0; i < kinfo->num_tc; i++) {
 				ret = hclge_tm_qs_to_pri_map_cfg(
 					hdev, vport[k].qs_offset + i, i);
 				if (ret)
 					return ret;
 			}
+		}
 	} else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) {
 		/* Cfg qs -> pri mapping,  qs = tc, pri = vf, 8 qs -> 1 pri */
 		for (k = 0; k < hdev->num_alloc_vport; k++)
@@ -934,6 +957,36 @@ static int hclge_tm_pri_tc_base_dwrr_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
+static int hclge_tm_ets_tc_dwrr_cfg(struct hclge_dev *hdev)
+{
+#define DEFAULT_TC_WEIGHT	1
+#define DEFAULT_TC_OFFSET	14
+
+	struct hclge_ets_tc_weight_cmd *ets_weight;
+	struct hclge_desc desc;
+	int i;
+
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, false);
+	ets_weight = (struct hclge_ets_tc_weight_cmd *)desc.data;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		struct hclge_pg_info *pg_info;
+
+		ets_weight->tc_weight[i] = DEFAULT_TC_WEIGHT;
+
+		if (!(hdev->hw_tc_map & BIT(i)))
+			continue;
+
+		pg_info =
+			&hdev->tm_info.pg_info[hdev->tm_info.tc_info[i].pgid];
+		ets_weight->tc_weight[i] = pg_info->tc_dwrr[i];
+	}
+
+	ets_weight->weight_offset = DEFAULT_TC_OFFSET;
+
+	return hclge_cmd_send(&hdev->hw, &desc, 1);
+}
+
 static int hclge_tm_pri_vnet_base_dwrr_pri_cfg(struct hclge_vport *vport)
 {
 	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
@@ -983,6 +1036,19 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 		ret = hclge_tm_pri_tc_base_dwrr_cfg(hdev);
 		if (ret)
 			return ret;
+
+		if (!hnae3_dev_dcb_supported(hdev))
+			return 0;
+
+		ret = hclge_tm_ets_tc_dwrr_cfg(hdev);
+		if (ret == -EOPNOTSUPP) {
+			dev_warn(&hdev->pdev->dev,
+				 "fw %08x does't support ets tc weight cmd\n",
+				 hdev->fw_version);
+			ret = 0;
+		}
+
+		return ret;
 	} else {
 		ret = hclge_tm_pri_vnet_base_dwrr_cfg(hdev);
 		if (ret)
@@ -992,7 +1058,7 @@ static int hclge_tm_pri_dwrr_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-int hclge_tm_map_cfg(struct hclge_dev *hdev)
+static int hclge_tm_map_cfg(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1107,7 +1173,7 @@ static int hclge_tm_lvl34_schd_mode_cfg(struct hclge_dev *hdev)
 	return 0;
 }
 
-int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
+static int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1118,7 +1184,7 @@ int hclge_tm_schd_mode_hw(struct hclge_dev *hdev)
 	return hclge_tm_lvl34_schd_mode_cfg(hdev);
 }
 
-static int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
+int hclge_tm_schd_setup_hw(struct hclge_dev *hdev)
 {
 	int ret;
 
@@ -1159,7 +1225,7 @@ static int hclge_pfc_setup_hw(struct hclge_dev *hdev)
 				HCLGE_RX_MAC_PAUSE_EN_MSK;
 
 	return hclge_pfc_pause_en_cfg(hdev, enable_bitmap,
-				      hdev->tm_info.hw_pfc_map);
+				      hdev->tm_info.pfc_en);
 }
 
 /* Each Tc has a 1024 queue sets to backpress, it divides to
@@ -1228,10 +1294,23 @@ static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
 	return hclge_mac_pause_en_cfg(hdev, tx_en, rx_en);
 }
 
-int hclge_pause_setup_hw(struct hclge_dev *hdev)
+static int hclge_tm_bp_setup(struct hclge_dev *hdev)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < hdev->tm_info.num_tc; i++) {
+		ret = hclge_bp_setup_hw(hdev, i);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init)
 {
 	int ret;
-	u8 i;
 
 	ret = hclge_pause_param_setup_hw(hdev);
 	if (ret)
@@ -1245,29 +1324,26 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev)
 	if (!hnae3_dev_dcb_supported(hdev))
 		return 0;
 
-	/* When MAC is GE Mode, hdev does not support pfc setting */
+	/* GE MAC does not support PFC, when driver is initializing and MAC
+	 * is in GE Mode, ignore the error here, otherwise initialization
+	 * will fail.
+	 */
 	ret = hclge_pfc_setup_hw(hdev);
-	if (ret)
-		dev_warn(&hdev->pdev->dev, "set pfc pause failed:%d\n", ret);
-
-	for (i = 0; i < hdev->tm_info.num_tc; i++) {
-		ret = hclge_bp_setup_hw(hdev, i);
-		if (ret)
-			return ret;
-	}
+	if (init && ret == -EOPNOTSUPP)
+		dev_warn(&hdev->pdev->dev, "GE MAC does not support pfc\n");
+	else
+		return ret;
 
-	return 0;
+	return hclge_tm_bp_setup(hdev);
 }
 
-int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
+void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
 {
 	struct hclge_vport *vport = hdev->vport;
 	struct hnae3_knic_private_info *kinfo;
 	u32 i, k;
 
 	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
-		if (prio_tc[i] >= hdev->tm_info.num_tc)
-			return -EINVAL;
 		hdev->tm_info.prio_tc[i] = prio_tc[i];
 
 		for (k = 0;  k < hdev->num_alloc_vport; k++) {
@@ -1275,18 +1351,12 @@ int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc)
 			kinfo->prio_tc[i] = prio_tc[i];
 		}
 	}
-	return 0;
 }
 
-int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
 {
 	u8 i, bit_map = 0;
 
-	for (i = 0; i < hdev->num_alloc_vport; i++) {
-		if (num_tc > hdev->vport[i].alloc_tqps)
-			return -EINVAL;
-	}
-
 	hdev->tm_info.num_tc = num_tc;
 
 	for (i = 0; i < hdev->tm_info.num_tc; i++)
@@ -1300,11 +1370,9 @@ int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc)
 	hdev->hw_tc_map = bit_map;
 
 	hclge_tm_schd_info_init(hdev);
-
-	return 0;
 }
 
-int hclge_tm_init_hw(struct hclge_dev *hdev)
+int hclge_tm_init_hw(struct hclge_dev *hdev, bool init)
 {
 	int ret;
 
@@ -1316,7 +1384,7 @@ int hclge_tm_init_hw(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	ret = hclge_pause_setup_hw(hdev);
+	ret = hclge_pause_setup_hw(hdev, init);
 	if (ret)
 		return ret;
 
@@ -1335,5 +1403,22 @@ int hclge_tm_schd_init(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	return hclge_tm_init_hw(hdev);
+	return hclge_tm_init_hw(hdev, true);
+}
+
+int hclge_tm_vport_map_update(struct hclge_dev *hdev)
+{
+	struct hclge_vport *vport = hdev->vport;
+	int ret;
+
+	hclge_tm_vport_tc_info_update(vport);
+
+	ret = hclge_vport_q_to_qs_map(hdev, vport);
+	if (ret)
+		return ret;
+
+	if (!(hdev->flag & HCLGE_FLAG_DCB_ENABLE))
+		return 0;
+
+	return hclge_tm_bp_setup(hdev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index 25eef13a3e14..f60e540c7a62 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -40,6 +40,13 @@ struct hclge_nq_to_qs_link_cmd {
 	__le16 qset_id;
 };
 
+struct hclge_tqp_tx_queue_tc_cmd {
+	__le16 queue_id;
+	__le16 rsvd;
+	u8 tc_id;
+	u8 rev[3];
+};
+
 struct hclge_pg_weight_cmd {
 	u8 pg_id;
 	u8 dwrr;
@@ -55,6 +62,12 @@ struct hclge_qs_weight_cmd {
 	u8 dwrr;
 };
 
+struct hclge_ets_tc_weight_cmd {
+	u8 tc_weight[HNAE3_MAX_TC];
+	u8 weight_offset;
+	u8 rsvd[15];
+};
+
 #define HCLGE_TM_SHAP_IR_B_MSK  GENMASK(7, 0)
 #define HCLGE_TM_SHAP_IR_B_LSH	0
 #define HCLGE_TM_SHAP_IR_U_MSK  GENMASK(11, 8)
@@ -129,13 +142,13 @@ struct hclge_port_shapping_cmd {
 				       (HCLGE_TM_SHAP_##string##_LSH))
 
 int hclge_tm_schd_init(struct hclge_dev *hdev);
-int hclge_pause_setup_hw(struct hclge_dev *hdev);
-int hclge_tm_schd_mode_hw(struct hclge_dev *hdev);
-int hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
-int hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
+int hclge_tm_vport_map_update(struct hclge_dev *hdev);
+int hclge_pause_setup_hw(struct hclge_dev *hdev, bool init);
+int hclge_tm_schd_setup_hw(struct hclge_dev *hdev);
+void hclge_tm_prio_tc_info_update(struct hclge_dev *hdev, u8 *prio_tc);
+void hclge_tm_schd_info_update(struct hclge_dev *hdev, u8 num_tc);
 int hclge_tm_dwrr_cfg(struct hclge_dev *hdev);
-int hclge_tm_map_cfg(struct hclge_dev *hdev);
-int hclge_tm_init_hw(struct hclge_dev *hdev);
+int hclge_tm_init_hw(struct hclge_dev *hdev, bool init);
 int hclge_mac_pause_en_cfg(struct hclge_dev *hdev, bool tx, bool rx);
 int hclge_pause_addr_cfg(struct hclge_dev *hdev, const u8 *mac_addr);
 int hclge_pfc_rx_stats_get(struct hclge_dev *hdev, u64 *stats);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
index fb93bbd35845..6193f8fa7cf3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the HISILICON network device drivers.
 #
 
-ccflags-y := -Idrivers/net/ethernet/hisilicon/hns3
+ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3
 
 obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
 hclgevf-objs = hclgevf_main.o hclgevf_cmd.o hclgevf_mbx.o
\ No newline at end of file
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 0d3b445f6799..9441b453d38d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -72,13 +72,51 @@ static bool hclgevf_is_special_opcode(u16 opcode)
 	return false;
 }
 
+static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring)
+{
+	struct hclgevf_dev *hdev = ring->dev;
+	struct hclgevf_hw *hw = &hdev->hw;
+	u32 reg_val;
+
+	if (ring->flag == HCLGEVF_TYPE_CSQ) {
+		reg_val = (u32)ring->desc_dma_addr;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, reg_val);
+		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
+
+		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
+		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
+
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
+	} else {
+		reg_val = (u32)ring->desc_dma_addr;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
+		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
+
+		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
+		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
+
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
+		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
+	}
+}
+
+static void hclgevf_cmd_init_regs(struct hclgevf_hw *hw)
+{
+	hclgevf_cmd_config_regs(&hw->cmq.csq);
+	hclgevf_cmd_config_regs(&hw->cmq.crq);
+}
+
 static int hclgevf_alloc_cmd_desc(struct hclgevf_cmq_ring *ring)
 {
 	int size = ring->desc_num * sizeof(struct hclgevf_desc);
 
-	ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
-					 size, &ring->desc_dma_addr,
-					 GFP_KERNEL);
+	ring->desc = dma_alloc_coherent(cmq_ring_to_dev(ring), size,
+					&ring->desc_dma_addr, GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
@@ -96,61 +134,23 @@ static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring)
 	}
 }
 
-static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
-				  struct hclgevf_cmq_ring *ring)
+static int hclgevf_alloc_cmd_queue(struct hclgevf_dev *hdev, int ring_type)
 {
 	struct hclgevf_hw *hw = &hdev->hw;
-	int ring_type = ring->flag;
-	u32 reg_val;
+	struct hclgevf_cmq_ring *ring =
+		(ring_type == HCLGEVF_TYPE_CSQ) ? &hw->cmq.csq : &hw->cmq.crq;
 	int ret;
 
-	ring->desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
-	spin_lock_init(&ring->lock);
-	ring->next_to_clean = 0;
-	ring->next_to_use = 0;
 	ring->dev = hdev;
+	ring->flag = ring_type;
 
 	/* allocate CSQ/CRQ descriptor */
 	ret = hclgevf_alloc_cmd_desc(ring);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "failed(%d) to alloc %s desc\n", ret,
 			(ring_type == HCLGEVF_TYPE_CSQ) ? "CSQ" : "CRQ");
-		return ret;
-	}
-
-	/* initialize the hardware registers with csq/crq dma-address,
-	 * descriptor number, head & tail pointers
-	 */
-	switch (ring_type) {
-	case HCLGEVF_TYPE_CSQ:
-		reg_val = (u32)ring->desc_dma_addr;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, reg_val);
-		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val);
-
-		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
-		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val);
-
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
-		return 0;
-	case HCLGEVF_TYPE_CRQ:
-		reg_val = (u32)ring->desc_dma_addr;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, reg_val);
-		reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, reg_val);
-
-		reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S);
-		reg_val |= HCLGEVF_NIC_CMQ_ENABLE;
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, reg_val);
 
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
-		hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
-		return 0;
-	default:
-		return -EINVAL;
-	}
+	return ret;
 }
 
 void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
@@ -188,7 +188,8 @@ int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num)
 
 	spin_lock_bh(&hw->cmq.csq.lock);
 
-	if (num > hclgevf_ring_space(&hw->cmq.csq)) {
+	if (num > hclgevf_ring_space(&hw->cmq.csq) ||
+	    test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
 		spin_unlock_bh(&hw->cmq.csq.lock);
 		return -EBUSY;
 	}
@@ -282,59 +283,107 @@ static int  hclgevf_cmd_query_firmware_version(struct hclgevf_hw *hw,
 	return status;
 }
 
-int hclgevf_cmd_init(struct hclgevf_dev *hdev)
+int hclgevf_cmd_queue_init(struct hclgevf_dev *hdev)
 {
-	u32 version;
 	int ret;
 
-	/* setup Tx write back timeout */
+	/* Setup the lock for command queue */
+	spin_lock_init(&hdev->hw.cmq.csq.lock);
+	spin_lock_init(&hdev->hw.cmq.crq.lock);
+
 	hdev->hw.cmq.tx_timeout = HCLGEVF_CMDQ_TX_TIMEOUT;
+	hdev->hw.cmq.csq.desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
+	hdev->hw.cmq.crq.desc_num = HCLGEVF_NIC_CMQ_DESC_NUM;
 
-	/* setup queue CSQ/CRQ rings */
-	hdev->hw.cmq.csq.flag = HCLGEVF_TYPE_CSQ;
-	ret = hclgevf_init_cmd_queue(hdev, &hdev->hw.cmq.csq);
+	ret = hclgevf_alloc_cmd_queue(hdev, HCLGEVF_TYPE_CSQ);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"failed(%d) to initialize CSQ ring\n", ret);
+			"CSQ ring setup error %d\n", ret);
 		return ret;
 	}
 
-	hdev->hw.cmq.crq.flag = HCLGEVF_TYPE_CRQ;
-	ret = hclgevf_init_cmd_queue(hdev, &hdev->hw.cmq.crq);
+	ret = hclgevf_alloc_cmd_queue(hdev, HCLGEVF_TYPE_CRQ);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
-			"failed(%d) to initialize CRQ ring\n", ret);
+			"CRQ ring setup error %d\n", ret);
 		goto err_csq;
 	}
 
+	return 0;
+err_csq:
+	hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
+	return ret;
+}
+
+int hclgevf_cmd_init(struct hclgevf_dev *hdev)
+{
+	u32 version;
+	int ret;
+
+	spin_lock_bh(&hdev->hw.cmq.csq.lock);
+	spin_lock_bh(&hdev->hw.cmq.crq.lock);
+
 	/* initialize the pointers of async rx queue of mailbox */
 	hdev->arq.hdev = hdev;
 	hdev->arq.head = 0;
 	hdev->arq.tail = 0;
 	hdev->arq.count = 0;
+	hdev->hw.cmq.csq.next_to_clean = 0;
+	hdev->hw.cmq.csq.next_to_use = 0;
+	hdev->hw.cmq.crq.next_to_clean = 0;
+	hdev->hw.cmq.crq.next_to_use = 0;
+
+	hclgevf_cmd_init_regs(&hdev->hw);
+
+	spin_unlock_bh(&hdev->hw.cmq.crq.lock);
+	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
+
+	clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+
+	/* Check if there is new reset pending, because the higher level
+	 * reset may happen when lower level reset is being processed.
+	 */
+	if (hclgevf_is_reset_pending(hdev)) {
+		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+		return -EBUSY;
+	}
 
 	/* get firmware version */
 	ret = hclgevf_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"failed(%d) to query firmware version\n", ret);
-		goto err_crq;
+		return ret;
 	}
 	hdev->fw_version = version;
 
 	dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version);
 
 	return 0;
-err_crq:
-	hclgevf_free_cmd_desc(&hdev->hw.cmq.crq);
-err_csq:
-	hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
+}
 
-	return ret;
+static void hclgevf_cmd_uninit_regs(struct hclgevf_hw *hw)
+{
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_L_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_TAIL_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_L_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_BASEADDR_H_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_DEPTH_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_HEAD_REG, 0);
+	hclgevf_write_dev(hw, HCLGEVF_NIC_CRQ_TAIL_REG, 0);
 }
 
 void hclgevf_cmd_uninit(struct hclgevf_dev *hdev)
 {
+	spin_lock_bh(&hdev->hw.cmq.csq.lock);
+	spin_lock(&hdev->hw.cmq.crq.lock);
+	clear_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+	hclgevf_cmd_uninit_regs(&hdev->hw);
+	spin_unlock(&hdev->hw.cmq.crq.lock);
+	spin_unlock_bh(&hdev->hw.cmq.csq.lock);
 	hclgevf_free_cmd_desc(&hdev->hw.cmq.csq);
 	hclgevf_free_cmd_desc(&hdev->hw.cmq.crq);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index bc294b0c8b62..47030b42341f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -87,6 +87,8 @@ enum hclgevf_opcode_type {
 	HCLGEVF_OPC_QUERY_TX_STATUS	= 0x0B03,
 	HCLGEVF_OPC_QUERY_RX_STATUS	= 0x0B13,
 	HCLGEVF_OPC_CFG_COM_TQP_QUEUE	= 0x0B20,
+	/* GRO command */
+	HCLGEVF_OPC_GRO_GENERIC_CONFIG  = 0x0C10,
 	/* RSS cmd */
 	HCLGEVF_OPC_RSS_GENERIC_CONFIG	= 0x0D01,
 	HCLGEVF_OPC_RSS_INPUT_TUPLE     = 0x0D02,
@@ -149,6 +151,12 @@ struct hclgevf_query_res_cmd {
 	__le16 rsv[7];
 };
 
+#define HCLGEVF_GRO_EN_B               0
+struct hclgevf_cfg_gro_status_cmd {
+	__le16 gro_en;
+	u8 rsv[22];
+};
+
 #define HCLGEVF_RSS_DEFAULT_OUTPORT_B	4
 #define HCLGEVF_RSS_HASH_KEY_OFFSET_B	4
 #define HCLGEVF_RSS_HASH_KEY_NUM	16
@@ -256,6 +264,7 @@ static inline u32 hclgevf_read_reg(u8 __iomem *base, u32 reg)
 
 int hclgevf_cmd_init(struct hclgevf_dev *hdev);
 void hclgevf_cmd_uninit(struct hclgevf_dev *hdev);
+int hclgevf_cmd_queue_init(struct hclgevf_dev *hdev);
 
 int hclgevf_cmd_send(struct hclgevf_hw *hw, struct hclgevf_desc *desc, int num);
 void hclgevf_cmd_setup_basic_desc(struct hclgevf_desc *desc,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 085edb945389..8bc28e6f465f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
+#include <linux/iopoll.h>
 #include <net/rtnetlink.h>
 #include "hclgevf_cmd.h"
 #include "hclgevf_main.h"
@@ -10,8 +11,7 @@
 
 #define HCLGEVF_NAME	"hclgevf"
 
-static int hclgevf_init_hdev(struct hclgevf_dev *hdev);
-static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev);
+static int hclgevf_reset_hdev(struct hclgevf_dev *hdev);
 static struct hnae3_ae_algo ae_algovf;
 
 static const struct pci_device_id ae_algovf_pci_tbl[] = {
@@ -21,12 +21,77 @@ static const struct pci_device_id ae_algovf_pci_tbl[] = {
 	{0, }
 };
 
+static const u8 hclgevf_hash_key[] = {
+	0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2,
+	0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0,
+	0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4,
+	0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C,
+	0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA
+};
+
 MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl);
 
+static const u32 cmdq_reg_addr_list[] = {HCLGEVF_CMDQ_TX_ADDR_L_REG,
+					 HCLGEVF_CMDQ_TX_ADDR_H_REG,
+					 HCLGEVF_CMDQ_TX_DEPTH_REG,
+					 HCLGEVF_CMDQ_TX_TAIL_REG,
+					 HCLGEVF_CMDQ_TX_HEAD_REG,
+					 HCLGEVF_CMDQ_RX_ADDR_L_REG,
+					 HCLGEVF_CMDQ_RX_ADDR_H_REG,
+					 HCLGEVF_CMDQ_RX_DEPTH_REG,
+					 HCLGEVF_CMDQ_RX_TAIL_REG,
+					 HCLGEVF_CMDQ_RX_HEAD_REG,
+					 HCLGEVF_VECTOR0_CMDQ_SRC_REG,
+					 HCLGEVF_CMDQ_INTR_STS_REG,
+					 HCLGEVF_CMDQ_INTR_EN_REG,
+					 HCLGEVF_CMDQ_INTR_GEN_REG};
+
+static const u32 common_reg_addr_list[] = {HCLGEVF_MISC_VECTOR_REG_BASE,
+					   HCLGEVF_RST_ING,
+					   HCLGEVF_GRO_EN_REG};
+
+static const u32 ring_reg_addr_list[] = {HCLGEVF_RING_RX_ADDR_L_REG,
+					 HCLGEVF_RING_RX_ADDR_H_REG,
+					 HCLGEVF_RING_RX_BD_NUM_REG,
+					 HCLGEVF_RING_RX_BD_LENGTH_REG,
+					 HCLGEVF_RING_RX_MERGE_EN_REG,
+					 HCLGEVF_RING_RX_TAIL_REG,
+					 HCLGEVF_RING_RX_HEAD_REG,
+					 HCLGEVF_RING_RX_FBD_NUM_REG,
+					 HCLGEVF_RING_RX_OFFSET_REG,
+					 HCLGEVF_RING_RX_FBD_OFFSET_REG,
+					 HCLGEVF_RING_RX_STASH_REG,
+					 HCLGEVF_RING_RX_BD_ERR_REG,
+					 HCLGEVF_RING_TX_ADDR_L_REG,
+					 HCLGEVF_RING_TX_ADDR_H_REG,
+					 HCLGEVF_RING_TX_BD_NUM_REG,
+					 HCLGEVF_RING_TX_PRIORITY_REG,
+					 HCLGEVF_RING_TX_TC_REG,
+					 HCLGEVF_RING_TX_MERGE_EN_REG,
+					 HCLGEVF_RING_TX_TAIL_REG,
+					 HCLGEVF_RING_TX_HEAD_REG,
+					 HCLGEVF_RING_TX_FBD_NUM_REG,
+					 HCLGEVF_RING_TX_OFFSET_REG,
+					 HCLGEVF_RING_TX_EBD_NUM_REG,
+					 HCLGEVF_RING_TX_EBD_OFFSET_REG,
+					 HCLGEVF_RING_TX_BD_ERR_REG,
+					 HCLGEVF_RING_EN_REG};
+
+static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG,
+					     HCLGEVF_TQP_INTR_GL0_REG,
+					     HCLGEVF_TQP_INTR_GL1_REG,
+					     HCLGEVF_TQP_INTR_GL2_REG,
+					     HCLGEVF_TQP_INTR_RL_REG};
+
 static inline struct hclgevf_dev *hclgevf_ae_get_hdev(
 	struct hnae3_handle *handle)
 {
-	return container_of(handle, struct hclgevf_dev, nic);
+	if (!handle->client)
+		return container_of(handle, struct hclgevf_dev, nic);
+	else if (handle->client->type == HNAE3_CLIENT_ROCE)
+		return container_of(handle, struct hclgevf_dev, roce);
+	else
+		return container_of(handle, struct hclgevf_dev, nic);
 }
 
 static int hclgevf_tqps_update_stats(struct hnae3_handle *handle)
@@ -182,7 +247,7 @@ static int hclgevf_get_tc_info(struct hclgevf_dev *hdev)
 
 static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
 {
-#define HCLGEVF_TQPS_RSS_INFO_LEN	8
+#define HCLGEVF_TQPS_RSS_INFO_LEN	6
 	u8 resp_msg[HCLGEVF_TQPS_RSS_INFO_LEN];
 	int status;
 
@@ -198,23 +263,55 @@ static int hclgevf_get_queue_info(struct hclgevf_dev *hdev)
 
 	memcpy(&hdev->num_tqps, &resp_msg[0], sizeof(u16));
 	memcpy(&hdev->rss_size_max, &resp_msg[2], sizeof(u16));
-	memcpy(&hdev->num_desc, &resp_msg[4], sizeof(u16));
-	memcpy(&hdev->rx_buf_len, &resp_msg[6], sizeof(u16));
+	memcpy(&hdev->rx_buf_len, &resp_msg[4], sizeof(u16));
 
 	return 0;
 }
 
+static int hclgevf_get_queue_depth(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_TQPS_DEPTH_INFO_LEN	4
+	u8 resp_msg[HCLGEVF_TQPS_DEPTH_INFO_LEN];
+	int ret;
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_QDEPTH, 0, NULL, 0,
+				   true, resp_msg,
+				   HCLGEVF_TQPS_DEPTH_INFO_LEN);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"VF request to get tqp depth info from PF failed %d",
+			ret);
+		return ret;
+	}
+
+	memcpy(&hdev->num_tx_desc, &resp_msg[0], sizeof(u16));
+	memcpy(&hdev->num_rx_desc, &resp_msg[2], sizeof(u16));
+
+	return 0;
+}
+
+static u16 hclgevf_get_qid_global(struct hnae3_handle *handle, u16 queue_id)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	u8 msg_data[2], resp_data[2];
+	u16 qid_in_pf = 0;
+	int ret;
+
+	memcpy(&msg_data[0], &queue_id, sizeof(queue_id));
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_QID_IN_PF, 0, msg_data,
+				   2, true, resp_data, 2);
+	if (!ret)
+		qid_in_pf = *(u16 *)resp_data;
+
+	return qid_in_pf;
+}
+
 static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 {
 	struct hclgevf_tqp *tqp;
 	int i;
 
-	/* if this is on going reset then we need to re-allocate the TPQs
-	 * since we cannot assume we would get same number of TPQs back from PF
-	 */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		devm_kfree(&hdev->pdev->dev, hdev->htqp);
-
 	hdev->htqp = devm_kcalloc(&hdev->pdev->dev, hdev->num_tqps,
 				  sizeof(struct hclgevf_tqp), GFP_KERNEL);
 	if (!hdev->htqp)
@@ -228,7 +325,8 @@ static int hclgevf_alloc_tqps(struct hclgevf_dev *hdev)
 
 		tqp->q.ae_algo = &ae_algovf;
 		tqp->q.buf_size = hdev->rx_buf_len;
-		tqp->q.desc_num = hdev->num_desc;
+		tqp->q.tx_desc_num = hdev->num_tx_desc;
+		tqp->q.rx_desc_num = hdev->num_rx_desc;
 		tqp->q.io_base = hdev->hw.io_base + HCLGEVF_TQP_REG_OFFSET +
 			i * HCLGEVF_TQP_REG_SIZE;
 
@@ -247,7 +345,8 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 
 	kinfo = &nic->kinfo;
 	kinfo->num_tc = 0;
-	kinfo->num_desc = hdev->num_desc;
+	kinfo->num_tx_desc = hdev->num_tx_desc;
+	kinfo->num_rx_desc = hdev->num_rx_desc;
 	kinfo->rx_buf_len = hdev->rx_buf_len;
 	for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++)
 		if (hdev->hw_tc_map & BIT(i))
@@ -258,12 +357,6 @@ static int hclgevf_knic_setup(struct hclgevf_dev *hdev)
 	new_tqps = kinfo->rss_size * kinfo->num_tc;
 	kinfo->num_tqps = min(new_tqps, hdev->num_tqps);
 
-	/* if this is on going reset then we need to re-allocate the hnae queues
-	 * as well since number of TPQs from PF might have changed.
-	 */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		devm_kfree(&hdev->pdev->dev, kinfo->tqp);
-
 	kinfo->tqp = devm_kcalloc(&hdev->pdev->dev, kinfo->num_tqps,
 				  sizeof(struct hnae3_queue *), GFP_KERNEL);
 	if (!kinfo->tqp)
@@ -292,20 +385,40 @@ static void hclgevf_request_link_info(struct hclgevf_dev *hdev)
 
 void hclgevf_update_link_status(struct hclgevf_dev *hdev, int link_state)
 {
+	struct hnae3_handle *rhandle = &hdev->roce;
 	struct hnae3_handle *handle = &hdev->nic;
+	struct hnae3_client *rclient;
 	struct hnae3_client *client;
 
 	client = handle->client;
+	rclient = hdev->roce_client;
 
 	link_state =
 		test_bit(HCLGEVF_STATE_DOWN, &hdev->state) ? 0 : link_state;
 
 	if (link_state != hdev->hw.mac.link) {
 		client->ops->link_status_change(handle, !!link_state);
+		if (rclient && rclient->ops->link_status_change)
+			rclient->ops->link_status_change(rhandle, !!link_state);
 		hdev->hw.mac.link = link_state;
 	}
 }
 
+void hclgevf_update_link_mode(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_ADVERTISING 0
+#define HCLGEVF_SUPPORTED   1
+	u8 send_msg;
+	u8 resp_msg;
+
+	send_msg = HCLGEVF_ADVERTISING;
+	hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_MODE, 0, &send_msg,
+			     sizeof(u8), false, &resp_msg, sizeof(u8));
+	send_msg = HCLGEVF_SUPPORTED;
+	hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_MODE, 0, &send_msg,
+			     sizeof(u8), false, &resp_msg, sizeof(u8));
+}
+
 static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
 {
 	struct hnae3_handle *nic = &hdev->nic;
@@ -507,12 +620,50 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 	return status;
 }
 
+/* for revision 0x20, vf shared the same rss config with pf */
+static int hclgevf_get_rss_hash_key(struct hclgevf_dev *hdev)
+{
+#define HCLGEVF_RSS_MBX_RESP_LEN	8
+
+	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
+	u8 resp_msg[HCLGEVF_RSS_MBX_RESP_LEN];
+	u16 msg_num, hash_key_index;
+	u8 index;
+	int ret;
+
+	msg_num = (HCLGEVF_RSS_KEY_SIZE + HCLGEVF_RSS_MBX_RESP_LEN - 1) /
+			HCLGEVF_RSS_MBX_RESP_LEN;
+	for (index = 0; index < msg_num; index++) {
+		ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_RSS_KEY, 0,
+					   &index, sizeof(index),
+					   true, resp_msg,
+					   HCLGEVF_RSS_MBX_RESP_LEN);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"VF get rss hash key from PF failed, ret=%d",
+				ret);
+			return ret;
+		}
+
+		hash_key_index = HCLGEVF_RSS_MBX_RESP_LEN * index;
+		if (index == msg_num - 1)
+			memcpy(&rss_cfg->rss_hash_key[hash_key_index],
+			       &resp_msg[0],
+			       HCLGEVF_RSS_KEY_SIZE - hash_key_index);
+		else
+			memcpy(&rss_cfg->rss_hash_key[hash_key_index],
+			       &resp_msg[0], HCLGEVF_RSS_MBX_RESP_LEN);
+	}
+
+	return 0;
+}
+
 static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key,
 			   u8 *hfunc)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
-	int i;
+	int i, ret;
 
 	if (handle->pdev->revision >= 0x21) {
 		/* Get hash algorithm */
@@ -534,6 +685,16 @@ static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key,
 		if (key)
 			memcpy(key, rss_cfg->rss_hash_key,
 			       HCLGEVF_RSS_KEY_SIZE);
+	} else {
+		if (hfunc)
+			*hfunc = ETH_RSS_HASH_TOP;
+		if (key) {
+			ret = hclgevf_get_rss_hash_key(hdev);
+			if (ret)
+				return ret;
+			memcpy(key, rss_cfg->rss_hash_key,
+			       HCLGEVF_RSS_KEY_SIZE);
+		}
 	}
 
 	if (indir)
@@ -868,6 +1029,9 @@ static int hclgevf_unmap_ring_from_vector(
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	int ret, vector_id;
 
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
+		return 0;
+
 	vector_id = hclgevf_get_vector_index(hdev, vector);
 	if (vector_id < 0) {
 		dev_err(&handle->pdev->dev,
@@ -904,33 +1068,29 @@ static int hclgevf_put_vector(struct hnae3_handle *handle, int vector)
 }
 
 static int hclgevf_cmd_set_promisc_mode(struct hclgevf_dev *hdev,
-					bool en_uc_pmc, bool en_mc_pmc)
+					bool en_bc_pmc)
 {
 	struct hclge_mbx_vf_to_pf_cmd *req;
 	struct hclgevf_desc desc;
-	int status;
+	int ret;
 
 	req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data;
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_MBX_VF_TO_PF, false);
 	req->msg[0] = HCLGE_MBX_SET_PROMISC_MODE;
-	req->msg[1] = en_uc_pmc ? 1 : 0;
-	req->msg[2] = en_mc_pmc ? 1 : 0;
+	req->msg[1] = en_bc_pmc ? 1 : 0;
 
-	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
-	if (status)
+	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
 		dev_err(&hdev->pdev->dev,
-			"Set promisc mode fail, status is %d.\n", status);
+			"Set promisc mode fail, status is %d.\n", ret);
 
-	return status;
+	return ret;
 }
 
-static int hclgevf_set_promisc_mode(struct hnae3_handle *handle,
-				    bool en_uc_pmc, bool en_mc_pmc)
+static int hclgevf_set_promisc_mode(struct hclgevf_dev *hdev, bool en_bc_pmc)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-
-	return hclgevf_cmd_set_promisc_mode(hdev, en_uc_pmc, en_mc_pmc);
+	return hclgevf_cmd_set_promisc_mode(hdev, en_bc_pmc);
 }
 
 static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
@@ -956,13 +1116,6 @@ static int hclgevf_tqp_enable(struct hclgevf_dev *hdev, int tqp_id,
 	return status;
 }
 
-static int hclgevf_get_queue_id(struct hnae3_queue *queue)
-{
-	struct hclgevf_tqp *tqp = container_of(queue, struct hclgevf_tqp, q);
-
-	return tqp->index;
-}
-
 static void hclgevf_reset_tqp_stats(struct hnae3_handle *handle)
 {
 	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
@@ -1097,38 +1250,87 @@ static int hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id)
 				    2, true, NULL, 0);
 }
 
+static int hclgevf_set_mtu(struct hnae3_handle *handle, int new_mtu)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_MTU, 0, (u8 *)&new_mtu,
+				    sizeof(new_mtu), true, NULL, 0);
+}
+
 static int hclgevf_notify_client(struct hclgevf_dev *hdev,
 				 enum hnae3_reset_notify_type type)
 {
 	struct hnae3_client *client = hdev->nic_client;
 	struct hnae3_handle *handle = &hdev->nic;
+	int ret;
 
 	if (!client->ops->reset_notify)
 		return -EOPNOTSUPP;
 
-	return client->ops->reset_notify(handle, type);
+	ret = client->ops->reset_notify(handle, type);
+	if (ret)
+		dev_err(&hdev->pdev->dev, "notify nic client failed %d(%d)\n",
+			type, ret);
+
+	return ret;
+}
+
+static void hclgevf_flr_done(struct hnae3_ae_dev *ae_dev)
+{
+	struct hclgevf_dev *hdev = ae_dev->priv;
+
+	set_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+}
+
+static int hclgevf_flr_poll_timeout(struct hclgevf_dev *hdev,
+				    unsigned long delay_us,
+				    unsigned long wait_cnt)
+{
+	unsigned long cnt = 0;
+
+	while (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state) &&
+	       cnt++ < wait_cnt)
+		usleep_range(delay_us, delay_us * 2);
+
+	if (!test_bit(HNAE3_FLR_DONE, &hdev->flr_state)) {
+		dev_err(&hdev->pdev->dev,
+			"flr wait timeout\n");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
 }
 
 static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 {
-#define HCLGEVF_RESET_WAIT_MS	500
-#define HCLGEVF_RESET_WAIT_CNT	20
-	u32 val, cnt = 0;
+#define HCLGEVF_RESET_WAIT_US	20000
+#define HCLGEVF_RESET_WAIT_CNT	2000
+#define HCLGEVF_RESET_WAIT_TIMEOUT_US	\
+	(HCLGEVF_RESET_WAIT_US * HCLGEVF_RESET_WAIT_CNT)
+
+	u32 val;
+	int ret;
 
 	/* wait to check the hardware reset completion status */
-	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
-	while (hnae3_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
-	       (cnt < HCLGEVF_RESET_WAIT_CNT)) {
-		msleep(HCLGEVF_RESET_WAIT_MS);
-		val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
-		cnt++;
-	}
+	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
+	dev_info(&hdev->pdev->dev, "checking vf resetting status: %x\n", val);
+
+	if (hdev->reset_type == HNAE3_FLR_RESET)
+		return hclgevf_flr_poll_timeout(hdev,
+						HCLGEVF_RESET_WAIT_US,
+						HCLGEVF_RESET_WAIT_CNT);
+
+	ret = readl_poll_timeout(hdev->hw.io_base + HCLGEVF_RST_ING, val,
+				 !(val & HCLGEVF_RST_ING_BITS),
+				 HCLGEVF_RESET_WAIT_US,
+				 HCLGEVF_RESET_WAIT_TIMEOUT_US);
 
 	/* hardware completion status should be available by this time */
-	if (cnt >= HCLGEVF_RESET_WAIT_CNT) {
-		dev_warn(&hdev->pdev->dev,
-			 "could'nt get reset done status from h/w, timeout!\n");
-		return -EBUSY;
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"could'nt get reset done status from h/w, timeout!\n");
+		return ret;
 	}
 
 	/* we will wait a bit more to let reset of the stack to complete. This
@@ -1145,10 +1347,12 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	int ret;
 
 	/* uninitialize the nic client */
-	hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
+	if (ret)
+		return ret;
 
 	/* re-initialize the hclge device */
-	ret = hclgevf_init_hdev(hdev);
+	ret = hclgevf_reset_hdev(hdev);
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"hclge device re-init failed, VF is disabled!\n");
@@ -1156,22 +1360,60 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev)
 	}
 
 	/* bring up the nic client again */
-	hclgevf_notify_client(hdev, HNAE3_INIT_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_INIT_CLIENT);
+	if (ret)
+		return ret;
 
-	return 0;
+	return hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT);
+}
+
+static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev)
+{
+	int ret = 0;
+
+	switch (hdev->reset_type) {
+	case HNAE3_VF_FUNC_RESET:
+		ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
+					   0, true, NULL, sizeof(u8));
+		break;
+	case HNAE3_FLR_RESET:
+		set_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+		break;
+	default:
+		break;
+	}
+
+	set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+
+	dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n",
+		 hdev->reset_type, ret);
+
+	return ret;
 }
 
 static int hclgevf_reset(struct hclgevf_dev *hdev)
 {
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev);
 	int ret;
 
+	/* Initialize ae_dev reset status as well, in case enet layer wants to
+	 * know if device is undergoing reset
+	 */
+	ae_dev->reset_type = hdev->reset_type;
+	hdev->reset_count++;
 	rtnl_lock();
 
 	/* bring down the nic to stop any ongoing TX/RX */
-	hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_DOWN_CLIENT);
+	if (ret)
+		goto err_reset_lock;
 
 	rtnl_unlock();
 
+	ret = hclgevf_reset_prepare_wait(hdev);
+	if (ret)
+		goto err_reset;
+
 	/* check if VF could successfully fetch the hardware reset completion
 	 * status from the hardware
 	 */
@@ -1181,58 +1423,121 @@ static int hclgevf_reset(struct hclgevf_dev *hdev)
 		dev_err(&hdev->pdev->dev,
 			"VF failed(=%d) to fetch H/W reset completion status\n",
 			ret);
-
-		dev_warn(&hdev->pdev->dev, "VF reset failed, disabling VF!\n");
-		rtnl_lock();
-		hclgevf_notify_client(hdev, HNAE3_UNINIT_CLIENT);
-
-		rtnl_unlock();
-		return ret;
+		goto err_reset;
 	}
 
 	rtnl_lock();
 
 	/* now, re-initialize the nic client and ae device*/
 	ret = hclgevf_reset_stack(hdev);
-	if (ret)
+	if (ret) {
 		dev_err(&hdev->pdev->dev, "failed to reset VF stack\n");
+		goto err_reset_lock;
+	}
 
 	/* bring up the nic to enable TX/RX again */
-	hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
+	ret = hclgevf_notify_client(hdev, HNAE3_UP_CLIENT);
+	if (ret)
+		goto err_reset_lock;
 
 	rtnl_unlock();
 
+	hdev->last_reset_time = jiffies;
+	ae_dev->reset_type = HNAE3_NONE_RESET;
+
 	return ret;
-}
+err_reset_lock:
+	rtnl_unlock();
+err_reset:
+	/* When VF reset failed, only the higher level reset asserted by PF
+	 * can restore it, so re-initialize the command queue to receive
+	 * this higher reset event.
+	 */
+	hclgevf_cmd_init(hdev);
+	dev_err(&hdev->pdev->dev, "failed to reset VF\n");
 
-static int hclgevf_do_reset(struct hclgevf_dev *hdev)
-{
-	int status;
-	u8 respmsg;
+	return ret;
+}
 
-	status = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_RESET, 0, NULL,
-				      0, false, &respmsg, sizeof(u8));
-	if (status)
-		dev_err(&hdev->pdev->dev,
-			"VF reset request to PF failed(=%d)\n", status);
+static enum hnae3_reset_type hclgevf_get_reset_level(struct hclgevf_dev *hdev,
+						     unsigned long *addr)
+{
+	enum hnae3_reset_type rst_level = HNAE3_NONE_RESET;
+
+	/* return the highest priority reset level amongst all */
+	if (test_bit(HNAE3_VF_RESET, addr)) {
+		rst_level = HNAE3_VF_RESET;
+		clear_bit(HNAE3_VF_RESET, addr);
+		clear_bit(HNAE3_VF_PF_FUNC_RESET, addr);
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_VF_FULL_RESET, addr)) {
+		rst_level = HNAE3_VF_FULL_RESET;
+		clear_bit(HNAE3_VF_FULL_RESET, addr);
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_VF_PF_FUNC_RESET, addr)) {
+		rst_level = HNAE3_VF_PF_FUNC_RESET;
+		clear_bit(HNAE3_VF_PF_FUNC_RESET, addr);
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_VF_FUNC_RESET, addr)) {
+		rst_level = HNAE3_VF_FUNC_RESET;
+		clear_bit(HNAE3_VF_FUNC_RESET, addr);
+	} else if (test_bit(HNAE3_FLR_RESET, addr)) {
+		rst_level = HNAE3_FLR_RESET;
+		clear_bit(HNAE3_FLR_RESET, addr);
+	}
 
-	return status;
+	return rst_level;
 }
 
 static void hclgevf_reset_event(struct pci_dev *pdev,
 				struct hnae3_handle *handle)
 {
-	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+	struct hclgevf_dev *hdev = ae_dev->priv;
 
 	dev_info(&hdev->pdev->dev, "received reset request from VF enet\n");
 
-	handle->reset_level = HNAE3_VF_RESET;
+	if (hdev->default_reset_request)
+		hdev->reset_level =
+			hclgevf_get_reset_level(hdev,
+						&hdev->default_reset_request);
+	else
+		hdev->reset_level = HNAE3_VF_FUNC_RESET;
 
 	/* reset of this VF requested */
 	set_bit(HCLGEVF_RESET_REQUESTED, &hdev->reset_state);
 	hclgevf_reset_task_schedule(hdev);
 
-	handle->last_reset_time = jiffies;
+	hdev->last_reset_time = jiffies;
+}
+
+static void hclgevf_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
+					  enum hnae3_reset_type rst_type)
+{
+	struct hclgevf_dev *hdev = ae_dev->priv;
+
+	set_bit(rst_type, &hdev->default_reset_request);
+}
+
+static void hclgevf_flr_prepare(struct hnae3_ae_dev *ae_dev)
+{
+#define HCLGEVF_FLR_WAIT_MS	100
+#define HCLGEVF_FLR_WAIT_CNT	50
+	struct hclgevf_dev *hdev = ae_dev->priv;
+	int cnt = 0;
+
+	clear_bit(HNAE3_FLR_DOWN, &hdev->flr_state);
+	clear_bit(HNAE3_FLR_DONE, &hdev->flr_state);
+	set_bit(HNAE3_FLR_RESET, &hdev->default_reset_request);
+	hclgevf_reset_event(hdev->pdev, NULL);
+
+	while (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state) &&
+	       cnt++ < HCLGEVF_FLR_WAIT_CNT)
+		msleep(HCLGEVF_FLR_WAIT_MS);
+
+	if (!test_bit(HNAE3_FLR_DOWN, &hdev->flr_state))
+		dev_err(&hdev->pdev->dev,
+			"flr wait down timeout: %d\n", cnt);
 }
 
 static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
@@ -1321,9 +1626,15 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 		 */
 		hdev->reset_attempts = 0;
 
-		ret = hclgevf_reset(hdev);
-		if (ret)
-			dev_err(&hdev->pdev->dev, "VF stack reset failed.\n");
+		hdev->last_reset_time = jiffies;
+		while ((hdev->reset_type =
+			hclgevf_get_reset_level(hdev, &hdev->reset_pending))
+		       != HNAE3_NONE_RESET) {
+			ret = hclgevf_reset(hdev);
+			if (ret)
+				dev_err(&hdev->pdev->dev,
+					"VF stack reset failed %d.\n", ret);
+		}
 	} else if (test_and_clear_bit(HCLGEVF_RESET_REQUESTED,
 				      &hdev->reset_state)) {
 		/* we could be here when either of below happens:
@@ -1352,19 +1663,17 @@ static void hclgevf_reset_service_task(struct work_struct *work)
 		 */
 		if (hdev->reset_attempts > 3) {
 			/* prepare for full reset of stack + pcie interface */
-			hdev->nic.reset_level = HNAE3_VF_FULL_RESET;
+			set_bit(HNAE3_VF_FULL_RESET, &hdev->reset_pending);
 
 			/* "defer" schedule the reset task again */
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		} else {
 			hdev->reset_attempts++;
 
-			/* request PF for resetting this VF via mailbox */
-			ret = hclgevf_do_reset(hdev);
-			if (ret)
-				dev_warn(&hdev->pdev->dev,
-					 "VF rst fail, stack will call\n");
+			set_bit(hdev->reset_level, &hdev->reset_pending);
+			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 		}
+		hclgevf_reset_task_schedule(hdev);
 	}
 
 	clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
@@ -1386,6 +1695,32 @@ static void hclgevf_mailbox_service_task(struct work_struct *work)
 	clear_bit(HCLGEVF_STATE_MBX_HANDLING, &hdev->state);
 }
 
+static void hclgevf_keep_alive_timer(struct timer_list *t)
+{
+	struct hclgevf_dev *hdev = from_timer(hdev, t, keep_alive_timer);
+
+	schedule_work(&hdev->keep_alive_task);
+	mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
+}
+
+static void hclgevf_keep_alive_task(struct work_struct *work)
+{
+	struct hclgevf_dev *hdev;
+	u8 respmsg;
+	int ret;
+
+	hdev = container_of(work, struct hclgevf_dev, keep_alive_task);
+
+	if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
+		return;
+
+	ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_KEEP_ALIVE, 0, NULL,
+				   0, false, &respmsg, sizeof(u8));
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"VF sends keep alive cmd failed(=%d)\n", ret);
+}
+
 static void hclgevf_service_task(struct work_struct *work)
 {
 	struct hclgevf_dev *hdev;
@@ -1397,6 +1732,8 @@ static void hclgevf_service_task(struct work_struct *work)
 	 */
 	hclgevf_request_link_info(hdev);
 
+	hclgevf_update_link_mode(hdev);
+
 	hclgevf_deferred_task_schedule(hdev);
 
 	clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
@@ -1407,24 +1744,37 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr)
 	hclgevf_write_dev(&hdev->hw, HCLGEVF_VECTOR0_CMDQ_SRC_REG, regclr);
 }
 
-static bool hclgevf_check_event_cause(struct hclgevf_dev *hdev, u32 *clearval)
+static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev,
+						      u32 *clearval)
 {
-	u32 cmdq_src_reg;
+	u32 cmdq_src_reg, rst_ing_reg;
 
 	/* fetch the events from their corresponding regs */
 	cmdq_src_reg = hclgevf_read_dev(&hdev->hw,
 					HCLGEVF_VECTOR0_CMDQ_SRC_REG);
 
+	if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) {
+		rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
+		dev_info(&hdev->pdev->dev,
+			 "receive reset interrupt 0x%x!\n", rst_ing_reg);
+		set_bit(HNAE3_VF_RESET, &hdev->reset_pending);
+		set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
+		set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state);
+		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B);
+		*clearval = cmdq_src_reg;
+		return HCLGEVF_VECTOR0_EVENT_RST;
+	}
+
 	/* check for vector0 mailbox(=CMDQ RX) event source */
 	if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) {
 		cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B);
 		*clearval = cmdq_src_reg;
-		return true;
+		return HCLGEVF_VECTOR0_EVENT_MBX;
 	}
 
 	dev_dbg(&hdev->pdev->dev, "vector 0 interrupt from unknown source\n");
 
-	return false;
+	return HCLGEVF_VECTOR0_EVENT_OTHER;
 }
 
 static void hclgevf_enable_vector(struct hclgevf_misc_vector *vector, bool en)
@@ -1434,19 +1784,28 @@ static void hclgevf_enable_vector(struct hclgevf_misc_vector *vector, bool en)
 
 static irqreturn_t hclgevf_misc_irq_handle(int irq, void *data)
 {
+	enum hclgevf_evt_cause event_cause;
 	struct hclgevf_dev *hdev = data;
 	u32 clearval;
 
 	hclgevf_enable_vector(&hdev->misc_vector, false);
-	if (!hclgevf_check_event_cause(hdev, &clearval))
-		goto skip_sched;
-
-	hclgevf_mbx_handler(hdev);
+	event_cause = hclgevf_check_evt_cause(hdev, &clearval);
 
-	hclgevf_clear_event_cause(hdev, clearval);
+	switch (event_cause) {
+	case HCLGEVF_VECTOR0_EVENT_RST:
+		hclgevf_reset_task_schedule(hdev);
+		break;
+	case HCLGEVF_VECTOR0_EVENT_MBX:
+		hclgevf_mbx_handler(hdev);
+		break;
+	default:
+		break;
+	}
 
-skip_sched:
-	hclgevf_enable_vector(&hdev->misc_vector, true);
+	if (event_cause != HCLGEVF_VECTOR0_EVENT_OTHER) {
+		hclgevf_clear_event_cause(hdev, clearval);
+		hclgevf_enable_vector(&hdev->misc_vector, true);
+	}
 
 	return IRQ_HANDLED;
 }
@@ -1455,12 +1814,16 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
 {
 	int ret;
 
-	hdev->hw.mac.media_type = HNAE3_MEDIA_TYPE_NONE;
-
 	/* get queue configuration from PF */
 	ret = hclgevf_get_queue_info(hdev);
 	if (ret)
 		return ret;
+
+	/* get queue depth info from PF */
+	ret = hclgevf_get_queue_depth(hdev);
+	if (ret)
+		return ret;
+
 	/* get tc configuration from PF */
 	return hclgevf_get_tc_info(hdev);
 }
@@ -1468,7 +1831,7 @@ static int hclgevf_configure(struct hclgevf_dev *hdev)
 static int hclgevf_alloc_hdev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
-	struct hclgevf_dev *hdev = ae_dev->priv;
+	struct hclgevf_dev *hdev;
 
 	hdev = devm_kzalloc(&pdev->dev, sizeof(*hdev), GFP_KERNEL);
 	if (!hdev)
@@ -1504,6 +1867,29 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev)
 	return 0;
 }
 
+static int hclgevf_config_gro(struct hclgevf_dev *hdev, bool en)
+{
+	struct hclgevf_cfg_gro_status_cmd *req;
+	struct hclgevf_desc desc;
+	int ret;
+
+	if (!hnae3_dev_gro_supported(hdev))
+		return 0;
+
+	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_GRO_GENERIC_CONFIG,
+				     false);
+	req = (struct hclgevf_cfg_gro_status_cmd *)desc.data;
+
+	req->gro_en = cpu_to_le16(en ? 1 : 0);
+
+	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (ret)
+		dev_err(&hdev->pdev->dev,
+			"VF GRO hardware config cmd failed, ret = %d.\n", ret);
+
+	return ret;
+}
+
 static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 {
 	struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg;
@@ -1512,9 +1898,9 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev)
 	rss_cfg->rss_size = hdev->rss_size_max;
 
 	if (hdev->pdev->revision >= 0x21) {
-		rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_TOEPLITZ;
-		netdev_rss_key_fill(rss_cfg->rss_hash_key,
-				    HCLGEVF_RSS_KEY_SIZE);
+		rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE;
+		memcpy(rss_cfg->rss_hash_key, hclgevf_hash_key,
+		       HCLGEVF_RSS_KEY_SIZE);
 
 		ret = hclgevf_set_rss_algo_key(hdev, rss_cfg->hash_algo,
 					       rss_cfg->rss_hash_key);
@@ -1564,69 +1950,84 @@ static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev)
 				       false);
 }
 
-static int hclgevf_ae_start(struct hnae3_handle *handle)
+static void hclgevf_set_timer_task(struct hnae3_handle *handle, bool enable)
 {
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, queue_id;
-
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		/* ring enable */
-		queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
-		if (queue_id < 0) {
-			dev_warn(&hdev->pdev->dev,
-				 "Get invalid queue id, ignore it\n");
-			continue;
-		}
 
-		hclgevf_tqp_enable(hdev, queue_id, 0, true);
+	if (enable) {
+		mod_timer(&hdev->service_timer, jiffies + HZ);
+	} else {
+		del_timer_sync(&hdev->service_timer);
+		cancel_work_sync(&hdev->service_task);
+		clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
 	}
+}
+
+static int hclgevf_ae_start(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
 
 	hclgevf_request_link_info(hdev);
 
+	hclgevf_update_link_mode(hdev);
+
 	clear_bit(HCLGEVF_STATE_DOWN, &hdev->state);
-	mod_timer(&hdev->service_timer, jiffies + HZ);
 
 	return 0;
 }
 
 static void hclgevf_ae_stop(struct hnae3_handle *handle)
 {
-	struct hnae3_knic_private_info *kinfo = &handle->kinfo;
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
-	int i, queue_id;
+	int i;
 
 	set_bit(HCLGEVF_STATE_DOWN, &hdev->state);
 
-	for (i = 0; i < kinfo->num_tqps; i++) {
-		/* Ring disable */
-		queue_id = hclgevf_get_queue_id(kinfo->tqp[i]);
-		if (queue_id < 0) {
-			dev_warn(&hdev->pdev->dev,
-				 "Get invalid queue id, ignore it\n");
-			continue;
-		}
-
-		hclgevf_tqp_enable(hdev, queue_id, 0, false);
-	}
+	for (i = 0; i < handle->kinfo.num_tqps; i++)
+		hclgevf_reset_tqp(handle, i);
 
 	/* reset tqp stats */
 	hclgevf_reset_tqp_stats(handle);
-	del_timer_sync(&hdev->service_timer);
-	cancel_work_sync(&hdev->service_task);
-	clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state);
 	hclgevf_update_link_status(hdev, 0);
 }
 
-static void hclgevf_state_init(struct hclgevf_dev *hdev)
+static int hclgevf_set_alive(struct hnae3_handle *handle, bool alive)
 {
-	/* if this is on going reset then skip this initialization */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return;
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	u8 msg_data;
+
+	msg_data = alive ? 1 : 0;
+	return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_ALIVE,
+				    0, &msg_data, 1, false, NULL, 0);
+}
+
+static int hclgevf_client_start(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	mod_timer(&hdev->keep_alive_timer, jiffies + 2 * HZ);
+	return hclgevf_set_alive(handle, true);
+}
+
+static void hclgevf_client_stop(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int ret;
 
+	ret = hclgevf_set_alive(handle, false);
+	if (ret)
+		dev_warn(&hdev->pdev->dev,
+			 "%s failed %d\n", __func__, ret);
+
+	del_timer_sync(&hdev->keep_alive_timer);
+	cancel_work_sync(&hdev->keep_alive_task);
+}
+
+static void hclgevf_state_init(struct hclgevf_dev *hdev)
+{
 	/* setup tasks for the MBX */
 	INIT_WORK(&hdev->mbx_service_task, hclgevf_mailbox_service_task);
 	clear_bit(HCLGEVF_STATE_MBX_SERVICE_SCHED, &hdev->state);
@@ -1668,10 +2069,6 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	int vectors;
 	int i;
 
-	/* if this is on going reset then skip this initialization */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return 0;
-
 	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
 		vectors = pci_alloc_irq_vectors(pdev,
 						hdev->roce_base_msix_offset + 1,
@@ -1710,6 +2107,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	hdev->vector_irq = devm_kcalloc(&pdev->dev, hdev->num_msi,
 					sizeof(int), GFP_KERNEL);
 	if (!hdev->vector_irq) {
+		devm_kfree(&pdev->dev, hdev->vector_status);
 		pci_free_irq_vectors(pdev);
 		return -ENOMEM;
 	}
@@ -1721,6 +2119,8 @@ static void hclgevf_uninit_msi(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
 
+	devm_kfree(&pdev->dev, hdev->vector_status);
+	devm_kfree(&pdev->dev, hdev->vector_irq);
 	pci_free_irq_vectors(pdev);
 }
 
@@ -1728,10 +2128,6 @@ static int hclgevf_misc_irq_init(struct hclgevf_dev *hdev)
 {
 	int ret = 0;
 
-	/* if this is on going reset then skip this initialization */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return 0;
-
 	hclgevf_get_misc_vector(hdev);
 
 	ret = request_irq(hdev->misc_vector.vector_irq, hclgevf_misc_irq_handle,
@@ -1861,14 +2257,6 @@ static int hclgevf_pci_init(struct hclgevf_dev *hdev)
 	struct hclgevf_hw *hw;
 	int ret;
 
-	/* check if we need to skip initialization of pci. This will happen if
-	 * device is undergoing VF reset. Otherwise, we would need to
-	 * re-initialize pci interface again i.e. when device is not going
-	 * through *any* reset or actually undergoing full reset.
-	 */
-	if (hclgevf_dev_ongoing_reset(hdev))
-		return 0;
-
 	ret = pci_enable_device(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed to enable PCI device\n");
@@ -1957,23 +2345,98 @@ static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
 	return 0;
 }
 
-static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+static int hclgevf_pci_reset(struct hclgevf_dev *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int ret = 0;
+
+	if (hdev->reset_type == HNAE3_VF_FULL_RESET &&
+	    test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
+		hclgevf_misc_irq_uninit(hdev);
+		hclgevf_uninit_msi(hdev);
+		clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+	}
+
+	if (!test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
+		pci_set_master(pdev);
+		ret = hclgevf_init_msi(hdev);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"failed(%d) to init MSI/MSI-X\n", ret);
+			return ret;
+		}
+
+		ret = hclgevf_misc_irq_init(hdev);
+		if (ret) {
+			hclgevf_uninit_msi(hdev);
+			dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n",
+				ret);
+			return ret;
+		}
+
+		set_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+	}
+
+	return ret;
+}
+
+static int hclgevf_reset_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
 	int ret;
 
-	/* check if device is on-going full reset(i.e. pcie as well) */
-	if (hclgevf_dev_ongoing_full_reset(hdev)) {
-		dev_warn(&pdev->dev, "device is going full reset\n");
-		hclgevf_uninit_hdev(hdev);
+	ret = hclgevf_pci_reset(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "pci reset failed %d\n", ret);
+		return ret;
+	}
+
+	ret = hclgevf_cmd_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "cmd failed %d\n", ret);
+		return ret;
 	}
 
+	ret = hclgevf_rss_init_hw(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed(%d) to initialize RSS\n", ret);
+		return ret;
+	}
+
+	ret = hclgevf_config_gro(hdev, true);
+	if (ret)
+		return ret;
+
+	ret = hclgevf_init_vlan_config(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"failed(%d) to initialize VLAN config\n", ret);
+		return ret;
+	}
+
+	dev_info(&hdev->pdev->dev, "Reset done\n");
+
+	return 0;
+}
+
+static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
+{
+	struct pci_dev *pdev = hdev->pdev;
+	int ret;
+
 	ret = hclgevf_pci_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "PCI initialization failed\n");
 		return ret;
 	}
 
+	ret = hclgevf_cmd_queue_init(hdev);
+	if (ret) {
+		dev_err(&pdev->dev, "Cmd queue init failed: %d\n", ret);
+		goto err_cmd_queue_init;
+	}
+
 	ret = hclgevf_cmd_init(hdev);
 	if (ret)
 		goto err_cmd_init;
@@ -1983,16 +2446,17 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Query vf status error, ret = %d.\n", ret);
-		goto err_query_vf;
+		goto err_cmd_init;
 	}
 
 	ret = hclgevf_init_msi(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret);
-		goto err_query_vf;
+		goto err_cmd_init;
 	}
 
 	hclgevf_state_init(hdev);
+	hdev->reset_level = HNAE3_VF_FUNC_RESET;
 
 	ret = hclgevf_misc_irq_init(hdev);
 	if (ret) {
@@ -2001,6 +2465,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_misc_irq_init;
 	}
 
+	set_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
+
 	ret = hclgevf_configure(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to fetch configuration\n", ret);
@@ -2019,6 +2485,19 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
+	ret = hclgevf_config_gro(hdev, true);
+	if (ret)
+		goto err_config;
+
+	/* vf is not allowed to enable unicast/multicast promisc mode.
+	 * For revision 0x20, default to disable broadcast promisc mode,
+	 * firmware makes sure broadcast packets can be accepted.
+	 * For revision 0x21, default to enable broadcast promisc mode.
+	 */
+	ret = hclgevf_set_promisc_mode(hdev, true);
+	if (ret)
+		goto err_config;
+
 	/* Initialize RSS for this VF */
 	ret = hclgevf_rss_init_hw(hdev);
 	if (ret) {
@@ -2034,6 +2513,7 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		goto err_config;
 	}
 
+	hdev->last_reset_time = jiffies;
 	pr_info("finished initializing %s driver\n", HCLGEVF_DRIVER_NAME);
 
 	return 0;
@@ -2043,25 +2523,31 @@ err_config:
 err_misc_irq_init:
 	hclgevf_state_uninit(hdev);
 	hclgevf_uninit_msi(hdev);
-err_query_vf:
-	hclgevf_cmd_uninit(hdev);
 err_cmd_init:
+	hclgevf_cmd_uninit(hdev);
+err_cmd_queue_init:
 	hclgevf_pci_uninit(hdev);
+	clear_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state);
 	return ret;
 }
 
 static void hclgevf_uninit_hdev(struct hclgevf_dev *hdev)
 {
 	hclgevf_state_uninit(hdev);
-	hclgevf_misc_irq_uninit(hdev);
-	hclgevf_cmd_uninit(hdev);
-	hclgevf_uninit_msi(hdev);
+
+	if (test_bit(HCLGEVF_STATE_IRQ_INITED, &hdev->state)) {
+		hclgevf_misc_irq_uninit(hdev);
+		hclgevf_uninit_msi(hdev);
+	}
+
 	hclgevf_pci_uninit(hdev);
+	hclgevf_cmd_uninit(hdev);
 }
 
 static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
+	struct hclgevf_dev *hdev;
 	int ret;
 
 	ret = hclgevf_alloc_hdev(ae_dev);
@@ -2071,10 +2557,16 @@ static int hclgevf_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	}
 
 	ret = hclgevf_init_hdev(ae_dev->priv);
-	if (ret)
+	if (ret) {
 		dev_err(&pdev->dev, "hclge device initialization failed\n");
+		return ret;
+	}
 
-	return ret;
+	hdev = ae_dev->priv;
+	timer_setup(&hdev->keep_alive_timer, hclgevf_keep_alive_timer, 0);
+	INIT_WORK(&hdev->keep_alive_task, hclgevf_keep_alive_task);
+
+	return 0;
 }
 
 static void hclgevf_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
@@ -2090,7 +2582,8 @@ static u32 hclgevf_get_max_channels(struct hclgevf_dev *hdev)
 	struct hnae3_handle *nic = &hdev->nic;
 	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
 
-	return min_t(u32, hdev->rss_size_max * kinfo->num_tc, hdev->num_tqps);
+	return min_t(u32, hdev->rss_size_max,
+		     hdev->num_tqps / kinfo->num_tc);
 }
 
 /**
@@ -2111,7 +2604,7 @@ static void hclgevf_get_channels(struct hnae3_handle *handle,
 	ch->max_combined = hclgevf_get_max_channels(hdev);
 	ch->other_count = 0;
 	ch->max_other = 0;
-	ch->combined_count = hdev->num_tqps;
+	ch->combined_count = handle->kinfo.rss_size;
 }
 
 static void hclgevf_get_tqps_and_rss_info(struct hnae3_handle *handle,
@@ -2151,6 +2644,13 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
 	hdev->hw.mac.duplex = duplex;
 }
 
+static int hclgevf_gro_en(struct hnae3_handle *handle, bool enable)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return hclgevf_config_gro(hdev, enable);
+}
+
 static void hclgevf_get_media_type(struct hnae3_handle *handle,
 				  u8 *media_type)
 {
@@ -2159,19 +2659,119 @@ static void hclgevf_get_media_type(struct hnae3_handle *handle,
 		*media_type = hdev->hw.mac.media_type;
 }
 
+static bool hclgevf_get_hw_reset_stat(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return !!hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING);
+}
+
+static bool hclgevf_ae_dev_resetting(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+}
+
+static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	return hdev->reset_count;
+}
+
+static void hclgevf_get_link_mode(struct hnae3_handle *handle,
+				  unsigned long *supported,
+				  unsigned long *advertising)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	*supported = hdev->hw.mac.supported;
+	*advertising = hdev->hw.mac.advertising;
+}
+
+#define MAX_SEPARATE_NUM	4
+#define SEPARATOR_VALUE		0xFFFFFFFF
+#define REG_NUM_PER_LINE	4
+#define REG_LEN_PER_LINE	(REG_NUM_PER_LINE * sizeof(u32))
+
+static int hclgevf_get_regs_len(struct hnae3_handle *handle)
+{
+	int cmdq_lines, common_lines, ring_lines, tqp_intr_lines;
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+
+	cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1;
+	tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1;
+
+	return (cmdq_lines + common_lines + ring_lines * hdev->num_tqps +
+		tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE;
+}
+
+static void hclgevf_get_regs(struct hnae3_handle *handle, u32 *version,
+			     void *data)
+{
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int i, j, reg_um, separator_num;
+	u32 *reg = data;
+
+	*version = hdev->fw_version;
+
+	/* fetching per-VF registers values from VF PCIe register space */
+	reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclgevf_read_dev(&hdev->hw, cmdq_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(common_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (i = 0; i < reg_um; i++)
+		*reg++ = hclgevf_read_dev(&hdev->hw, common_reg_addr_list[i]);
+	for (i = 0; i < separator_num; i++)
+		*reg++ = SEPARATOR_VALUE;
+
+	reg_um = sizeof(ring_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_tqps; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclgevf_read_dev(&hdev->hw,
+						  ring_reg_addr_list[i] +
+						  0x200 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+
+	reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32);
+	separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE;
+	for (j = 0; j < hdev->num_msi_used - 1; j++) {
+		for (i = 0; i < reg_um; i++)
+			*reg++ = hclgevf_read_dev(&hdev->hw,
+						  tqp_intr_reg_addr_list[i] +
+						  4 * j);
+		for (i = 0; i < separator_num; i++)
+			*reg++ = SEPARATOR_VALUE;
+	}
+}
+
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
+	.flr_prepare = hclgevf_flr_prepare,
+	.flr_done = hclgevf_flr_done,
 	.init_client_instance = hclgevf_init_client_instance,
 	.uninit_client_instance = hclgevf_uninit_client_instance,
 	.start = hclgevf_ae_start,
 	.stop = hclgevf_ae_stop,
+	.client_start = hclgevf_client_start,
+	.client_stop = hclgevf_client_stop,
 	.map_ring_to_vector = hclgevf_map_ring_to_vector,
 	.unmap_ring_from_vector = hclgevf_unmap_ring_from_vector,
 	.get_vector = hclgevf_get_vector,
 	.put_vector = hclgevf_put_vector,
 	.reset_queue = hclgevf_reset_tqp,
-	.set_promisc_mode = hclgevf_set_promisc_mode,
 	.get_mac_addr = hclgevf_get_mac_addr,
 	.set_mac_addr = hclgevf_set_mac_addr,
 	.add_uc_addr = hclgevf_add_uc_addr,
@@ -2193,11 +2793,22 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 	.set_vlan_filter = hclgevf_set_vlan_filter,
 	.enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag,
 	.reset_event = hclgevf_reset_event,
+	.set_default_reset_request = hclgevf_set_def_reset_request,
 	.get_channels = hclgevf_get_channels,
 	.get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info,
+	.get_regs_len = hclgevf_get_regs_len,
+	.get_regs = hclgevf_get_regs,
 	.get_status = hclgevf_get_status,
 	.get_ksettings_an_result = hclgevf_get_ksettings_an_result,
 	.get_media_type = hclgevf_get_media_type,
+	.get_hw_reset_stat = hclgevf_get_hw_reset_stat,
+	.ae_dev_resetting = hclgevf_ae_dev_resetting,
+	.ae_dev_reset_cnt = hclgevf_ae_dev_reset_cnt,
+	.set_gro_en = hclgevf_gro_en,
+	.set_mtu = hclgevf_set_mtu,
+	.get_global_queue_id = hclgevf_get_qid_global,
+	.set_timer_task = hclgevf_set_timer_task,
+	.get_link_mode = hclgevf_get_link_mode,
 };
 
 static struct hnae3_ae_algo ae_algovf = {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index aed241e8ffab..c128863ee7d0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -27,15 +27,77 @@
 #define HCLGEVF_VECTOR_REG_OFFSET	0x4
 #define HCLGEVF_VECTOR_VF_OFFSET		0x100000
 
+/* bar registers for cmdq */
+#define HCLGEVF_CMDQ_TX_ADDR_L_REG		0x27000
+#define HCLGEVF_CMDQ_TX_ADDR_H_REG		0x27004
+#define HCLGEVF_CMDQ_TX_DEPTH_REG		0x27008
+#define HCLGEVF_CMDQ_TX_TAIL_REG		0x27010
+#define HCLGEVF_CMDQ_TX_HEAD_REG		0x27014
+#define HCLGEVF_CMDQ_RX_ADDR_L_REG		0x27018
+#define HCLGEVF_CMDQ_RX_ADDR_H_REG		0x2701C
+#define HCLGEVF_CMDQ_RX_DEPTH_REG		0x27020
+#define HCLGEVF_CMDQ_RX_TAIL_REG		0x27024
+#define HCLGEVF_CMDQ_RX_HEAD_REG		0x27028
+#define HCLGEVF_CMDQ_INTR_SRC_REG		0x27100
+#define HCLGEVF_CMDQ_INTR_STS_REG		0x27104
+#define HCLGEVF_CMDQ_INTR_EN_REG		0x27108
+#define HCLGEVF_CMDQ_INTR_GEN_REG		0x2710C
+
+/* bar registers for common func */
+#define HCLGEVF_GRO_EN_REG			0x28000
+
+/* bar registers for rcb */
+#define HCLGEVF_RING_RX_ADDR_L_REG		0x80000
+#define HCLGEVF_RING_RX_ADDR_H_REG		0x80004
+#define HCLGEVF_RING_RX_BD_NUM_REG		0x80008
+#define HCLGEVF_RING_RX_BD_LENGTH_REG		0x8000C
+#define HCLGEVF_RING_RX_MERGE_EN_REG		0x80014
+#define HCLGEVF_RING_RX_TAIL_REG		0x80018
+#define HCLGEVF_RING_RX_HEAD_REG		0x8001C
+#define HCLGEVF_RING_RX_FBD_NUM_REG		0x80020
+#define HCLGEVF_RING_RX_OFFSET_REG		0x80024
+#define HCLGEVF_RING_RX_FBD_OFFSET_REG		0x80028
+#define HCLGEVF_RING_RX_STASH_REG		0x80030
+#define HCLGEVF_RING_RX_BD_ERR_REG		0x80034
+#define HCLGEVF_RING_TX_ADDR_L_REG		0x80040
+#define HCLGEVF_RING_TX_ADDR_H_REG		0x80044
+#define HCLGEVF_RING_TX_BD_NUM_REG		0x80048
+#define HCLGEVF_RING_TX_PRIORITY_REG		0x8004C
+#define HCLGEVF_RING_TX_TC_REG			0x80050
+#define HCLGEVF_RING_TX_MERGE_EN_REG		0x80054
+#define HCLGEVF_RING_TX_TAIL_REG		0x80058
+#define HCLGEVF_RING_TX_HEAD_REG		0x8005C
+#define HCLGEVF_RING_TX_FBD_NUM_REG		0x80060
+#define HCLGEVF_RING_TX_OFFSET_REG		0x80064
+#define HCLGEVF_RING_TX_EBD_NUM_REG		0x80068
+#define HCLGEVF_RING_TX_EBD_OFFSET_REG		0x80070
+#define HCLGEVF_RING_TX_BD_ERR_REG		0x80074
+#define HCLGEVF_RING_EN_REG			0x80090
+
+/* bar registers for tqp interrupt */
+#define HCLGEVF_TQP_INTR_CTRL_REG		0x20000
+#define HCLGEVF_TQP_INTR_GL0_REG		0x20100
+#define HCLGEVF_TQP_INTR_GL1_REG		0x20200
+#define HCLGEVF_TQP_INTR_GL2_REG		0x20300
+#define HCLGEVF_TQP_INTR_RL_REG			0x20900
+
 /* Vector0 interrupt CMDQ event source register(RW) */
 #define HCLGEVF_VECTOR0_CMDQ_SRC_REG	0x27100
 /* CMDQ register bits for RX event(=MBX event) */
 #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B	1
+/* RST register bits for RESET event */
+#define HCLGEVF_VECTOR0_RST_INT_B	2
 
 #define HCLGEVF_TQP_RESET_TRY_TIMES	10
 /* Reset related Registers */
-#define HCLGEVF_FUN_RST_ING		0x20C00
-#define HCLGEVF_FUN_RST_ING_B		0
+#define HCLGEVF_RST_ING			0x20C00
+#define HCLGEVF_FUN_RST_ING_BIT		BIT(0)
+#define HCLGEVF_GLOBAL_RST_ING_BIT	BIT(5)
+#define HCLGEVF_CORE_RST_ING_BIT	BIT(6)
+#define HCLGEVF_IMP_RST_ING_BIT		BIT(7)
+#define HCLGEVF_RST_ING_BITS \
+	(HCLGEVF_FUN_RST_ING_BIT | HCLGEVF_GLOBAL_RST_ING_BIT | \
+	 HCLGEVF_CORE_RST_ING_BIT | HCLGEVF_IMP_RST_ING_BIT)
 
 #define HCLGEVF_RSS_IND_TBL_SIZE		512
 #define HCLGEVF_RSS_SET_BITMAP_MSK	0xffff
@@ -54,17 +116,25 @@
 #define HCLGEVF_S_IP_BIT		BIT(3)
 #define HCLGEVF_V_TAG_BIT		BIT(4)
 
+enum hclgevf_evt_cause {
+	HCLGEVF_VECTOR0_EVENT_RST,
+	HCLGEVF_VECTOR0_EVENT_MBX,
+	HCLGEVF_VECTOR0_EVENT_OTHER,
+};
+
 /* states of hclgevf device & tasks */
 enum hclgevf_states {
 	/* device states */
 	HCLGEVF_STATE_DOWN,
 	HCLGEVF_STATE_DISABLED,
+	HCLGEVF_STATE_IRQ_INITED,
 	/* task states */
 	HCLGEVF_STATE_SERVICE_SCHED,
 	HCLGEVF_STATE_RST_SERVICE_SCHED,
 	HCLGEVF_STATE_RST_HANDLING,
 	HCLGEVF_STATE_MBX_SERVICE_SCHED,
 	HCLGEVF_STATE_MBX_HANDLING,
+	HCLGEVF_STATE_CMD_DISABLE,
 };
 
 #define HCLGEVF_MPF_ENBALE 1
@@ -75,6 +145,8 @@ struct hclgevf_mac {
 	int link;
 	u8 duplex;
 	u32 speed;
+	u64 supported;
+	u64 advertising;
 };
 
 struct hclgevf_hw {
@@ -145,10 +217,17 @@ struct hclgevf_dev {
 	struct hclgevf_misc_vector misc_vector;
 	struct hclgevf_rss_cfg rss_cfg;
 	unsigned long state;
+	unsigned long flr_state;
+	unsigned long default_reset_request;
+	unsigned long last_reset_time;
+	enum hnae3_reset_type reset_level;
+	unsigned long reset_pending;
+	enum hnae3_reset_type reset_type;
 
 #define HCLGEVF_RESET_REQUESTED		0
 #define HCLGEVF_RESET_PENDING		1
 	unsigned long reset_state;	/* requested, pending */
+	unsigned long reset_count;	/* the number of reset has been done */
 	u32 reset_attempts;
 
 	u32 fw_version;
@@ -160,7 +239,8 @@ struct hclgevf_dev {
 	u16 num_alloc_vport;	/* num vports this driver supports */
 	u32 numa_node_mask;
 	u16 rx_buf_len;
-	u16 num_desc;
+	u16 num_tx_desc;	/* desc num of per tx queue */
+	u16 num_rx_desc;	/* desc num of per rx queue */
 	u8 hw_tc_map;
 
 	u16 num_msi;
@@ -178,7 +258,9 @@ struct hclgevf_dev {
 	struct hclgevf_mbx_arq_ring arq; /* mailbox async rx queue */
 
 	struct timer_list service_timer;
+	struct timer_list keep_alive_timer;
 	struct work_struct service_task;
+	struct work_struct keep_alive_task;
 	struct work_struct rst_service_task;
 	struct work_struct mbx_service_task;
 
@@ -192,18 +274,9 @@ struct hclgevf_dev {
 	u32 flag;
 };
 
-static inline bool hclgevf_dev_ongoing_reset(struct hclgevf_dev *hdev)
-{
-	return (hdev &&
-		(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
-		(hdev->nic.reset_level == HNAE3_VF_RESET));
-}
-
-static inline bool hclgevf_dev_ongoing_full_reset(struct hclgevf_dev *hdev)
+static inline bool hclgevf_is_reset_pending(struct hclgevf_dev *hdev)
 {
-	return (hdev &&
-		(test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) &&
-		(hdev->nic.reset_level == HNAE3_VF_FULL_RESET));
+	return !!hdev->reset_pending;
 }
 
 int hclgevf_send_mbx_msg(struct hclgevf_dev *hdev, u16 code, u16 subcode,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index e9d5a4f96304..7dc3c9f79169 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -26,7 +26,7 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 				u8 *resp_data, u16 resp_len)
 {
 #define HCLGEVF_MAX_TRY_TIMES	500
-#define HCLGEVF_SLEEP_USCOEND	1000
+#define HCLGEVF_SLEEP_USECOND	1000
 	struct hclgevf_mbx_resp_status *mbx_resp;
 	u16 r_code0, r_code1;
 	int i = 0;
@@ -40,7 +40,10 @@ static int hclgevf_get_mbx_resp(struct hclgevf_dev *hdev, u16 code0, u16 code1,
 	}
 
 	while ((!hdev->mbx_resp.received_resp) && (i < HCLGEVF_MAX_TRY_TIMES)) {
-		udelay(HCLGEVF_SLEEP_USCOEND);
+		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state))
+			return -EIO;
+
+		usleep_range(HCLGEVF_SLEEP_USECOND, HCLGEVF_SLEEP_USECOND * 2);
 		i++;
 	}
 
@@ -148,6 +151,11 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 	crq = &hdev->hw.cmq.crq;
 
 	while (!hclgevf_cmd_crq_empty(&hdev->hw)) {
+		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
+			dev_info(&hdev->pdev->dev, "vf crq need init\n");
+			return;
+		}
+
 		desc = &crq->desc[crq->next_to_use];
 		req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data;
 
@@ -189,6 +197,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 			break;
 		case HCLGE_MBX_LINK_STAT_CHANGE:
 		case HCLGE_MBX_ASSERTING_RESET:
+		case HCLGE_MBX_LINK_STAT_MODE:
 			/* set this mbx event as pending. This is required as we
 			 * might loose interrupt event when mbx task is busy
 			 * handling. This shall be cleared when mbx task just
@@ -233,11 +242,13 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 
 void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 {
+	enum hnae3_reset_type reset_type;
 	u16 link_status;
 	u16 *msg_q;
 	u8 duplex;
 	u32 speed;
 	u32 tail;
+	u8 idx;
 
 	/* we can safely clear it now as we are at start of the async message
 	 * processing
@@ -248,6 +259,12 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 
 	/* process all the async queue messages */
 	while (tail != hdev->arq.head) {
+		if (test_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state)) {
+			dev_info(&hdev->pdev->dev,
+				 "vf crq need init in async\n");
+			return;
+		}
+
 		msg_q = hdev->arq.msg_q[hdev->arq.head];
 
 		switch (msg_q[0]) {
@@ -255,19 +272,30 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev)
 			link_status = le16_to_cpu(msg_q[1]);
 			memcpy(&speed, &msg_q[2], sizeof(speed));
 			duplex = (u8)le16_to_cpu(msg_q[4]);
+			hdev->hw.mac.media_type = (u8)le16_to_cpu(msg_q[5]);
 
 			/* update upper layer with new link link status */
 			hclgevf_update_link_status(hdev, link_status);
 			hclgevf_update_speed_duplex(hdev, speed, duplex);
 
 			break;
+		case HCLGE_MBX_LINK_STAT_MODE:
+			idx = (u8)le16_to_cpu(msg_q[1]);
+			if (idx)
+				memcpy(&hdev->hw.mac.supported, &msg_q[2],
+				       sizeof(unsigned long));
+			else
+				memcpy(&hdev->hw.mac.advertising, &msg_q[2],
+				       sizeof(unsigned long));
+			break;
 		case HCLGE_MBX_ASSERTING_RESET:
 			/* PF has asserted reset hence VF should go in pending
 			 * state and poll for the hardware reset status till it
 			 * has been completely reset. After this stack should
 			 * eventually be re-initialized.
 			 */
-			hdev->nic.reset_level = HNAE3_VF_RESET;
+			reset_type = le16_to_cpu(msg_q[1]);
+			set_bit(reset_type, &hdev->reset_pending);
 			set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state);
 			hclgevf_reset_task_schedule(hdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 017e08452d8c..8b8a7d00e8e0 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -39,7 +39,7 @@ struct hns_mdio_sc_reg {
 };
 
 struct hns_mdio_device {
-	void *vbase;		/* mdio reg base address */
+	u8 __iomem *vbase;		/* mdio reg base address */
 	struct regmap *subctrl_vbase;
 	struct hns_mdio_sc_reg sc_reg;
 };
@@ -96,21 +96,17 @@ enum mdio_c45_op_seq {
 #define MDIO_SC_CLK_ST		0x531C
 #define MDIO_SC_RESET_ST	0x5A1C
 
-static void mdio_write_reg(void *base, u32 reg, u32 value)
+static void mdio_write_reg(u8 __iomem *base, u32 reg, u32 value)
 {
-	u8 __iomem *reg_addr = (u8 __iomem *)base;
-
-	writel_relaxed(value, reg_addr + reg);
+	writel_relaxed(value, base + reg);
 }
 
 #define MDIO_WRITE_REG(a, reg, value) \
 	mdio_write_reg((a)->vbase, (reg), (value))
 
-static u32 mdio_read_reg(void *base, u32 reg)
+static u32 mdio_read_reg(u8 __iomem *base, u32 reg)
 {
-	u8 __iomem *reg_addr = (u8 __iomem *)base;
-
-	return readl_relaxed(reg_addr + reg);
+	return readl_relaxed(base + reg);
 }
 
 #define mdio_set_field(origin, mask, shift, val) \
@@ -121,7 +117,7 @@ static u32 mdio_read_reg(void *base, u32 reg)
 
 #define mdio_get_field(origin, mask, shift) (((origin) >> (shift)) & (mask))
 
-static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
+static void mdio_set_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift,
 			       u32 val)
 {
 	u32 origin = mdio_read_reg(base, reg);
@@ -133,7 +129,7 @@ static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift,
 #define MDIO_SET_REG_FIELD(dev, reg, mask, shift, val) \
 	mdio_set_reg_field((dev)->vbase, (reg), (mask), (shift), (val))
 
-static u32 mdio_get_reg_field(void *base, u32 reg, u32 mask, u32 shift)
+static u32 mdio_get_reg_field(u8 __iomem *base, u32 reg, u32 mask, u32 shift)
 {
 	u32 origin;
 
@@ -321,7 +317,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
 		}
 
 		hns_mdio_cmd_write(mdio_dev, is_c45,
-				   MDIO_C45_WRITE_ADDR, phy_id, devad);
+				   MDIO_C45_READ, phy_id, devad);
 	}
 
 	/* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
index c40603a183df..b4fefb4c3064 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_api_cmd.c
@@ -613,8 +613,8 @@ static int alloc_cmd_buf(struct hinic_api_cmd_chain *chain,
 	u8 *cmd_vaddr;
 	int err = 0;
 
-	cmd_vaddr = dma_zalloc_coherent(&pdev->dev, API_CMD_BUF_SIZE,
-					&cmd_paddr, GFP_KERNEL);
+	cmd_vaddr = dma_alloc_coherent(&pdev->dev, API_CMD_BUF_SIZE,
+				       &cmd_paddr, GFP_KERNEL);
 	if (!cmd_vaddr) {
 		dev_err(&pdev->dev, "Failed to allocate API CMD DMA memory\n");
 		return -ENOMEM;
@@ -663,8 +663,8 @@ static int api_cmd_create_cell(struct hinic_api_cmd_chain *chain,
 	dma_addr_t node_paddr;
 	int err;
 
-	node = dma_zalloc_coherent(&pdev->dev, chain->cell_size,
-				   &node_paddr, GFP_KERNEL);
+	node = dma_alloc_coherent(&pdev->dev, chain->cell_size, &node_paddr,
+				  GFP_KERNEL);
 	if (!node) {
 		dev_err(&pdev->dev, "Failed to allocate dma API CMD cell\n");
 		return -ENOMEM;
@@ -821,10 +821,10 @@ static int api_chain_init(struct hinic_api_cmd_chain *chain,
 	if (!chain->cell_ctxt)
 		return -ENOMEM;
 
-	chain->wb_status = dma_zalloc_coherent(&pdev->dev,
-					       sizeof(*chain->wb_status),
-					       &chain->wb_status_paddr,
-					       GFP_KERNEL);
+	chain->wb_status = dma_alloc_coherent(&pdev->dev,
+					      sizeof(*chain->wb_status),
+					      &chain->wb_status_paddr,
+					      GFP_KERNEL);
 	if (!chain->wb_status) {
 		dev_err(&pdev->dev, "Failed to allocate DMA wb status\n");
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 6b19607a4caa..3875f39f43bb 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -1008,3 +1008,16 @@ int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq,
 				 &hw_ci, sizeof(hw_ci), NULL,
 				 NULL, HINIC_MGMT_MSG_SYNC);
 }
+
+/**
+ * hinic_hwdev_set_msix_state- set msix state
+ * @hwdev: the NIC HW device
+ * @msix_index: IRQ corresponding index number
+ * @flag: msix state
+ *
+ **/
+void hinic_hwdev_set_msix_state(struct hinic_hwdev *hwdev, u16 msix_index,
+				enum hinic_msix_state flag)
+{
+	hinic_set_msix_state(hwdev->hwif, msix_index, flag);
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
index 097b5502603f..c9e621e19dd0 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.h
@@ -50,6 +50,8 @@ enum hinic_port_cmd {
 
 	HINIC_PORT_CMD_GET_LINK_STATE   = 24,
 
+	HINIC_PORT_CMD_SET_RX_CSUM	= 26,
+
 	HINIC_PORT_CMD_SET_PORT_STATE   = 41,
 
 	HINIC_PORT_CMD_FWCTXT_INIT      = 69,
@@ -238,4 +240,7 @@ int hinic_hwdev_msix_set(struct hinic_hwdev *hwdev, u16 msix_index,
 int hinic_hwdev_hw_ci_addr_set(struct hinic_hwdev *hwdev, struct hinic_sq *sq,
 			       u8 pending_limit, u8 coalesc_timer);
 
+void hinic_hwdev_set_msix_state(struct hinic_hwdev *hwdev, u16 msix_index,
+				enum hinic_msix_state flag);
+
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
index 7cb8b9b94726..683e67515016 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c
@@ -593,10 +593,10 @@ static int alloc_eq_pages(struct hinic_eq *eq)
 	}
 
 	for (pg = 0; pg < eq->num_pages; pg++) {
-		eq->virt_addr[pg] = dma_zalloc_coherent(&pdev->dev,
-							eq->page_size,
-							&eq->dma_addr[pg],
-							GFP_KERNEL);
+		eq->virt_addr[pg] = dma_alloc_coherent(&pdev->dev,
+						       eq->page_size,
+						       &eq->dma_addr[pg],
+						       GFP_KERNEL);
 		if (!eq->virt_addr[pg]) {
 			err = -ENOMEM;
 			goto err_dma_alloc;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
index 823a17061a97..9b160f076904 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.c
@@ -168,6 +168,22 @@ void hinic_db_state_set(struct hinic_hwif *hwif,
 	hinic_hwif_write_reg(hwif, HINIC_CSR_FUNC_ATTR4_ADDR, attr4);
 }
 
+void hinic_set_msix_state(struct hinic_hwif *hwif, u16 msix_idx,
+			  enum hinic_msix_state flag)
+{
+	u32 offset = msix_idx * HINIC_PCI_MSIX_ENTRY_SIZE +
+			HINIC_PCI_MSIX_ENTRY_VECTOR_CTRL;
+	u32 mask_bits;
+
+	mask_bits = readl(hwif->intr_regs_base + offset);
+	mask_bits &= ~HINIC_PCI_MSIX_ENTRY_CTRL_MASKBIT;
+
+	if (flag)
+		mask_bits |= HINIC_PCI_MSIX_ENTRY_CTRL_MASKBIT;
+
+	writel(mask_bits, hwif->intr_regs_base + offset);
+}
+
 /**
  * hwif_ready - test if the HW is ready for use
  * @hwif: the HW interface of a pci function device
@@ -321,6 +337,13 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
 		return -ENOMEM;
 	}
 
+	hwif->intr_regs_base = pci_ioremap_bar(pdev, HINIC_PCI_INTR_REGS_BAR);
+	if (!hwif->intr_regs_base) {
+		dev_err(&pdev->dev, "Failed to map configuration regs\n");
+		err = -ENOMEM;
+		goto err_map_intr_bar;
+	}
+
 	err = hwif_ready(hwif);
 	if (err) {
 		dev_err(&pdev->dev, "HW interface is not ready\n");
@@ -337,7 +360,11 @@ int hinic_init_hwif(struct hinic_hwif *hwif, struct pci_dev *pdev)
 	return 0;
 
 err_hwif_ready:
+	iounmap(hwif->intr_regs_base);
+
+err_map_intr_bar:
 	iounmap(hwif->cfg_regs_bar);
+
 	return err;
 }
 
@@ -347,5 +374,6 @@ err_hwif_ready:
  **/
 void hinic_free_hwif(struct hinic_hwif *hwif)
 {
+	iounmap(hwif->intr_regs_base);
 	iounmap(hwif->cfg_regs_bar);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
index 5b4760c0e9f5..22ec7f73e0a6 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_if.h
@@ -152,6 +152,7 @@
 #define HINIC_IS_PPF(hwif)              (HINIC_FUNC_TYPE(hwif) == HINIC_PPF)
 
 #define HINIC_PCI_CFG_REGS_BAR          0
+#define HINIC_PCI_INTR_REGS_BAR         2
 #define HINIC_PCI_DB_BAR                4
 
 #define HINIC_PCIE_ST_DISABLE           0
@@ -164,6 +165,10 @@
 #define HINIC_EQ_MSIX_LLI_CREDIT_LIMIT_DEFAULT  0       /* Disabled */
 #define HINIC_EQ_MSIX_RESEND_TIMER_DEFAULT      7       /* max */
 
+#define HINIC_PCI_MSIX_ENTRY_SIZE               16
+#define HINIC_PCI_MSIX_ENTRY_VECTOR_CTRL        12
+#define HINIC_PCI_MSIX_ENTRY_CTRL_MASKBIT       1
+
 enum hinic_pcie_nosnoop {
 	HINIC_PCIE_SNOOP        = 0,
 	HINIC_PCIE_NO_SNOOP     = 1,
@@ -207,6 +212,11 @@ enum hinic_db_state {
 	HINIC_DB_DISABLE = 1,
 };
 
+enum hinic_msix_state {
+	HINIC_MSIX_ENABLE,
+	HINIC_MSIX_DISABLE,
+};
+
 struct hinic_func_attr {
 	u16                     func_idx;
 	u8                      pf_idx;
@@ -226,6 +236,7 @@ struct hinic_func_attr {
 struct hinic_hwif {
 	struct pci_dev          *pdev;
 	void __iomem            *cfg_regs_bar;
+	void __iomem		*intr_regs_base;
 
 	struct hinic_func_attr  attr;
 };
@@ -251,6 +262,9 @@ int hinic_msix_attr_get(struct hinic_hwif *hwif, u16 msix_index,
 			u8 *lli_timer, u8 *lli_credit_limit,
 			u8 *resend_timer);
 
+void hinic_set_msix_state(struct hinic_hwif *hwif, u16 msix_idx,
+			  enum hinic_msix_state flag);
+
 int hinic_msix_attr_cnt_clear(struct hinic_hwif *hwif, u16 msix_index);
 
 void hinic_set_pf_action(struct hinic_hwif *hwif, enum hinic_pf_action action);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
index 8e5897669a3a..a322a22d9357 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_io.c
@@ -355,9 +355,9 @@ int hinic_io_create_qps(struct hinic_func_to_io *func_to_io,
 		goto err_sq_db;
 	}
 
-	ci_addr_base = dma_zalloc_coherent(&pdev->dev, CI_TABLE_SIZE(num_qps),
-					   &func_to_io->ci_dma_base,
-					   GFP_KERNEL);
+	ci_addr_base = dma_alloc_coherent(&pdev->dev, CI_TABLE_SIZE(num_qps),
+					  &func_to_io->ci_dma_base,
+					  GFP_KERNEL);
 	if (!ci_addr_base) {
 		dev_err(&pdev->dev, "Failed to allocate CI area\n");
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index bbf9bdd0ee3e..d62cf509646a 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -336,9 +336,9 @@ static int alloc_rq_cqe(struct hinic_rq *rq)
 		goto err_cqe_dma_arr_alloc;
 
 	for (i = 0; i < wq->q_depth; i++) {
-		rq->cqe[i] = dma_zalloc_coherent(&pdev->dev,
-						 sizeof(*rq->cqe[i]),
-						 &rq->cqe_dma[i], GFP_KERNEL);
+		rq->cqe[i] = dma_alloc_coherent(&pdev->dev,
+						sizeof(*rq->cqe[i]),
+						&rq->cqe_dma[i], GFP_KERNEL);
 		if (!rq->cqe[i])
 			goto err_cqe_alloc;
 	}
@@ -415,8 +415,8 @@ int hinic_init_rq(struct hinic_rq *rq, struct hinic_hwif *hwif,
 
 	/* HW requirements: Must be at least 32 bit */
 	pi_size = ALIGN(sizeof(*rq->pi_virt_addr), sizeof(u32));
-	rq->pi_virt_addr = dma_zalloc_coherent(&pdev->dev, pi_size,
-					       &rq->pi_dma_addr, GFP_KERNEL);
+	rq->pi_virt_addr = dma_alloc_coherent(&pdev->dev, pi_size,
+					      &rq->pi_dma_addr, GFP_KERNEL);
 	if (!rq->pi_virt_addr) {
 		dev_err(&pdev->dev, "Failed to allocate PI address\n");
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
index f92f1bf3901a..cb66e7024659 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.c
@@ -74,12 +74,6 @@
 			((void *)((cmdq_pages)->shadow_page_vaddr) \
 				+ (wq)->block_idx * CMDQ_BLOCK_SIZE)
 
-#define WQE_PAGE_OFF(wq, idx)   (((idx) & ((wq)->num_wqebbs_per_page - 1)) * \
-					(wq)->wqebb_size)
-
-#define WQE_PAGE_NUM(wq, idx)   (((idx) / ((wq)->num_wqebbs_per_page)) \
-					& ((wq)->num_q_pages - 1))
-
 #define WQ_PAGE_ADDR(wq, idx)           \
 			((wq)->shadow_block_vaddr[WQE_PAGE_NUM(wq, idx)])
 
@@ -93,6 +87,17 @@
 		(((unsigned long)(wqe) - (unsigned long)(wq)->shadow_wqe) \
 			/ (wq)->max_wqe_size)
 
+static inline int WQE_PAGE_OFF(struct hinic_wq *wq, u16 idx)
+{
+	return (((idx) & ((wq)->num_wqebbs_per_page - 1))
+		<< (wq)->wqebb_size_shift);
+}
+
+static inline int WQE_PAGE_NUM(struct hinic_wq *wq, u16 idx)
+{
+	return (((idx) >> ((wq)->wqebbs_per_page_shift))
+		& ((wq)->num_q_pages - 1));
+}
 /**
  * queue_alloc_page - allocate page for Queue
  * @hwif: HW interface for allocating DMA
@@ -109,8 +114,8 @@ static int queue_alloc_page(struct hinic_hwif *hwif, u64 **vaddr, u64 *paddr,
 	struct pci_dev *pdev = hwif->pdev;
 	dma_addr_t dma_addr;
 
-	*vaddr = dma_zalloc_coherent(&pdev->dev, page_sz, &dma_addr,
-				     GFP_KERNEL);
+	*vaddr = dma_alloc_coherent(&pdev->dev, page_sz, &dma_addr,
+				    GFP_KERNEL);
 	if (!*vaddr) {
 		dev_err(&pdev->dev, "Failed to allocate dma for wqs page\n");
 		return -ENOMEM;
@@ -477,8 +482,8 @@ static int alloc_wq_pages(struct hinic_wq *wq, struct hinic_hwif *hwif,
 		u64 *paddr = &wq->block_vaddr[i];
 		dma_addr_t dma_addr;
 
-		*vaddr = dma_zalloc_coherent(&pdev->dev, wq->wq_page_size,
-					     &dma_addr, GFP_KERNEL);
+		*vaddr = dma_alloc_coherent(&pdev->dev, wq->wq_page_size,
+					    &dma_addr, GFP_KERNEL);
 		if (!*vaddr) {
 			dev_err(&pdev->dev, "Failed to allocate wq page\n");
 			goto err_alloc_wq_pages;
@@ -513,10 +518,11 @@ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
 	struct hinic_hwif *hwif = wqs->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	u16 num_wqebbs_per_page;
+	u16 wqebb_size_shift;
 	int err;
 
-	if (wqebb_size == 0) {
-		dev_err(&pdev->dev, "wqebb_size must be > 0\n");
+	if (!is_power_of_2(wqebb_size)) {
+		dev_err(&pdev->dev, "wqebb_size must be power of 2\n");
 		return -EINVAL;
 	}
 
@@ -530,9 +536,11 @@ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
 		return -EINVAL;
 	}
 
-	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size) / wqebb_size;
+	wqebb_size_shift = ilog2(wqebb_size);
+	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size)
+				>> wqebb_size_shift;
 
-	if (num_wqebbs_per_page & (num_wqebbs_per_page - 1)) {
+	if (!is_power_of_2(num_wqebbs_per_page)) {
 		dev_err(&pdev->dev, "num wqebbs per page must be power of 2\n");
 		return -EINVAL;
 	}
@@ -550,7 +558,8 @@ int hinic_wq_allocate(struct hinic_wqs *wqs, struct hinic_wq *wq,
 	wq->q_depth = q_depth;
 	wq->max_wqe_size = max_wqe_size;
 	wq->num_wqebbs_per_page = num_wqebbs_per_page;
-
+	wq->wqebbs_per_page_shift = ilog2(num_wqebbs_per_page);
+	wq->wqebb_size_shift = wqebb_size_shift;
 	wq->block_vaddr = WQ_BASE_VADDR(wqs, wq);
 	wq->shadow_block_vaddr = WQ_BASE_ADDR(wqs, wq);
 	wq->block_paddr = WQ_BASE_PADDR(wqs, wq);
@@ -604,11 +613,13 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 			 u16 q_depth, u16 max_wqe_size)
 {
 	struct pci_dev *pdev = hwif->pdev;
+	u16 num_wqebbs_per_page_shift;
 	u16 num_wqebbs_per_page;
+	u16 wqebb_size_shift;
 	int i, j, err = -ENOMEM;
 
-	if (wqebb_size == 0) {
-		dev_err(&pdev->dev, "wqebb_size must be > 0\n");
+	if (!is_power_of_2(wqebb_size)) {
+		dev_err(&pdev->dev, "wqebb_size must be power of 2\n");
 		return -EINVAL;
 	}
 
@@ -622,9 +633,11 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 		return -EINVAL;
 	}
 
-	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size) / wqebb_size;
+	wqebb_size_shift = ilog2(wqebb_size);
+	num_wqebbs_per_page = ALIGN(wq_page_size, wqebb_size)
+				>> wqebb_size_shift;
 
-	if (num_wqebbs_per_page & (num_wqebbs_per_page - 1)) {
+	if (!is_power_of_2(num_wqebbs_per_page)) {
 		dev_err(&pdev->dev, "num wqebbs per page must be power of 2\n");
 		return -EINVAL;
 	}
@@ -636,6 +649,7 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 		dev_err(&pdev->dev, "Failed to allocate CMDQ page\n");
 		return err;
 	}
+	num_wqebbs_per_page_shift = ilog2(num_wqebbs_per_page);
 
 	for (i = 0; i < cmdq_blocks; i++) {
 		wq[i].hwif = hwif;
@@ -647,7 +661,8 @@ int hinic_wqs_cmdq_alloc(struct hinic_cmdq_pages *cmdq_pages,
 		wq[i].q_depth = q_depth;
 		wq[i].max_wqe_size = max_wqe_size;
 		wq[i].num_wqebbs_per_page = num_wqebbs_per_page;
-
+		wq[i].wqebbs_per_page_shift = num_wqebbs_per_page_shift;
+		wq[i].wqebb_size_shift = wqebb_size_shift;
 		wq[i].block_vaddr = CMDQ_BASE_VADDR(cmdq_pages, &wq[i]);
 		wq[i].shadow_block_vaddr = CMDQ_BASE_ADDR(cmdq_pages, &wq[i]);
 		wq[i].block_paddr = CMDQ_BASE_PADDR(cmdq_pages, &wq[i]);
@@ -741,7 +756,7 @@ struct hinic_hw_wqe *hinic_get_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 
 	*prod_idx = MASKED_WQE_IDX(wq, atomic_read(&wq->prod_idx));
 
-	num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) >> wq->wqebb_size_shift;
 
 	if (atomic_sub_return(num_wqebbs, &wq->delta) <= 0) {
 		atomic_add(num_wqebbs, &wq->delta);
@@ -795,7 +810,8 @@ void hinic_return_wqe(struct hinic_wq *wq, unsigned int wqe_size)
  **/
 void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size)
 {
-	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size)
+			>> wq->wqebb_size_shift;
 
 	atomic_add(num_wqebbs, &wq->cons_idx);
 
@@ -813,7 +829,8 @@ void hinic_put_wqe(struct hinic_wq *wq, unsigned int wqe_size)
 struct hinic_hw_wqe *hinic_read_wqe(struct hinic_wq *wq, unsigned int wqe_size,
 				    u16 *cons_idx)
 {
-	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size) / wq->wqebb_size;
+	int num_wqebbs = ALIGN(wqe_size, wq->wqebb_size)
+			>> wq->wqebb_size_shift;
 	u16 curr_cons_idx, end_cons_idx;
 	int curr_pg, end_pg;
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
index 9b66545ba563..0a936cd6709b 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wq.h
@@ -39,7 +39,8 @@ struct hinic_wq {
 	u16             q_depth;
 	u16             max_wqe_size;
 	u16             num_wqebbs_per_page;
-
+	u16		wqebbs_per_page_shift;
+	u16		wqebb_size_shift;
 	/* The addresses are 64 bit in the HW */
 	u64             block_paddr;
 	void            **shadow_block_vaddr;
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
index 9754d6ed5f4a..138941527872 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_wqe.h
@@ -170,6 +170,10 @@
 
 #define HINIC_RQ_CQE_STATUS_RXDONE_MASK         0x1
 
+#define HINIC_RQ_CQE_STATUS_CSUM_ERR_SHIFT	0
+
+#define HINIC_RQ_CQE_STATUS_CSUM_ERR_MASK	0xFFFFU
+
 #define HINIC_RQ_CQE_STATUS_GET(val, member)    \
 		(((val) >> HINIC_RQ_CQE_STATUS_##member##_SHIFT) & \
 		 HINIC_RQ_CQE_STATUS_##member##_MASK)
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c
index fdf2bdb6b0d0..e64bc664f687 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_main.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c
@@ -51,9 +51,10 @@ static unsigned int rx_weight = 64;
 module_param(rx_weight, uint, 0644);
 MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)");
 
-#define HINIC_DEV_ID_QUAD_PORT_25GE     0x1822
-#define HINIC_DEV_ID_DUAL_PORT_25GE     0x0200
-#define HINIC_DEV_ID_DUAL_PORT_100GE    0x0201
+#define HINIC_DEV_ID_QUAD_PORT_25GE         0x1822
+#define HINIC_DEV_ID_DUAL_PORT_100GE        0x0200
+#define HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ   0x0205
+#define HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ    0x0210
 
 #define HINIC_WQ_NAME                   "hinic_dev"
 
@@ -600,9 +601,6 @@ static int add_mac_addr(struct net_device *netdev, const u8 *addr)
 	u16 vid = 0;
 	int err;
 
-	if (!is_valid_ether_addr(addr))
-		return -EADDRNOTAVAIL;
-
 	netif_info(nic_dev, drv, netdev, "set mac addr = %02x %02x %02x %02x %02x %02x\n",
 		   addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
 
@@ -726,6 +724,7 @@ static void set_rx_mode(struct work_struct *work)
 {
 	struct hinic_rx_mode_work *rx_mode_work = work_to_rx_mode_work(work);
 	struct hinic_dev *nic_dev = rx_mode_work_to_nic_dev(rx_mode_work);
+	struct netdev_hw_addr *ha;
 
 	netif_info(nic_dev, drv, nic_dev->netdev, "set rx mode work\n");
 
@@ -733,6 +732,9 @@ static void set_rx_mode(struct work_struct *work)
 
 	__dev_uc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
 	__dev_mc_sync(nic_dev->netdev, add_mac_addr, remove_mac_addr);
+
+	netdev_for_each_mc_addr(ha, nic_dev->netdev)
+		add_mac_addr(nic_dev->netdev, ha->addr);
 }
 
 static void hinic_set_rx_mode(struct net_device *netdev)
@@ -806,7 +808,8 @@ static const struct net_device_ops hinic_netdev_ops = {
 static void netdev_features_init(struct net_device *netdev)
 {
 	netdev->hw_features = NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_IP_CSUM |
-			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6;
+			      NETIF_F_IPV6_CSUM | NETIF_F_TSO | NETIF_F_TSO6 |
+			      NETIF_F_RXCSUM;
 
 	netdev->vlan_features = netdev->hw_features;
 
@@ -869,12 +872,16 @@ static int set_features(struct hinic_dev *nic_dev,
 			netdev_features_t features, bool force_change)
 {
 	netdev_features_t changed = force_change ? ~0 : pre_features ^ features;
+	u32 csum_en = HINIC_RX_CSUM_OFFLOAD_EN;
 	int err = 0;
 
 	if (changed & NETIF_F_TSO)
 		err = hinic_port_set_tso(nic_dev, (features & NETIF_F_TSO) ?
 					 HINIC_TSO_ENABLE : HINIC_TSO_DISABLE);
 
+	if (changed & NETIF_F_RXCSUM)
+		err = hinic_set_rx_csum_offload(nic_dev, csum_en);
+
 	return err;
 }
 
@@ -1100,10 +1107,16 @@ static void hinic_remove(struct pci_dev *pdev)
 	dev_info(&pdev->dev, "HiNIC driver - removed\n");
 }
 
+static void hinic_shutdown(struct pci_dev *pdev)
+{
+	pci_disable_device(pdev);
+}
+
 static const struct pci_device_id hinic_pci_table[] = {
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0},
-	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0},
 	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0},
+	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE_MEZZ), 0},
+	{ PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE_MEZZ), 0},
 	{ 0, 0}
 };
 MODULE_DEVICE_TABLE(pci, hinic_pci_table);
@@ -1113,6 +1126,7 @@ static struct pci_driver hinic_driver = {
 	.id_table       = hinic_pci_table,
 	.probe          = hinic_probe,
 	.remove         = hinic_remove,
+	.shutdown       = hinic_shutdown,
 };
 
 module_pci_driver(hinic_driver);
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.c b/drivers/net/ethernet/huawei/hinic/hinic_port.c
index 7575a7d3bd9f..122c93597268 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.c
@@ -409,3 +409,33 @@ int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state)
 
 	return 0;
 }
+
+int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en)
+{
+	struct hinic_checksum_offload rx_csum_cfg = {0};
+	struct hinic_hwdev *hwdev = nic_dev->hwdev;
+	struct hinic_hwif *hwif;
+	struct pci_dev *pdev;
+	u16 out_size;
+	int err;
+
+	if (!hwdev)
+		return -EINVAL;
+
+	hwif = hwdev->hwif;
+	pdev = hwif->pdev;
+	rx_csum_cfg.func_id = HINIC_HWIF_FUNC_IDX(hwif);
+	rx_csum_cfg.rx_csum_offload = en;
+
+	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_SET_RX_CSUM,
+				 &rx_csum_cfg, sizeof(rx_csum_cfg),
+				 &rx_csum_cfg, &out_size);
+	if (err || !out_size || rx_csum_cfg.status) {
+		dev_err(&pdev->dev,
+			"Failed to set rx csum offload, ret = %d\n",
+			rx_csum_cfg.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_port.h b/drivers/net/ethernet/huawei/hinic/hinic_port.h
index f6e3220fe28f..02d896eed455 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_port.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_port.h
@@ -183,6 +183,15 @@ struct hinic_tso_config {
 	u8	resv2[3];
 };
 
+struct hinic_checksum_offload {
+	u8	status;
+	u8	version;
+	u8	rsvd0[6];
+
+	u16	func_id;
+	u16	rsvd1;
+	u32	rx_csum_offload;
+};
 int hinic_port_add_mac(struct hinic_dev *nic_dev, const u8 *addr,
 		       u16 vlan_id);
 
@@ -213,4 +222,5 @@ int hinic_port_get_cap(struct hinic_dev *nic_dev,
 
 int hinic_port_set_tso(struct hinic_dev *nic_dev, enum hinic_tso_state state);
 
+int hinic_set_rx_csum_offload(struct hinic_dev *nic_dev, u32 en);
 #endif
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
index 4c0f7eda1166..b6d218768ec1 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c
@@ -43,6 +43,7 @@
 #define RX_IRQ_NO_LLI_TIMER             0
 #define RX_IRQ_NO_CREDIT                0
 #define RX_IRQ_NO_RESEND_TIMER          0
+#define HINIC_RX_BUFFER_WRITE           16
 
 /**
  * hinic_rxq_clean_stats - Clean the statistics of specific queue
@@ -89,6 +90,28 @@ static void rxq_stats_init(struct hinic_rxq *rxq)
 	hinic_rxq_clean_stats(rxq);
 }
 
+static void rx_csum(struct hinic_rxq *rxq, u16 cons_idx,
+		    struct sk_buff *skb)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct hinic_rq_cqe *cqe;
+	struct hinic_rq *rq;
+	u32 csum_err;
+	u32 status;
+
+	rq = rxq->rq;
+	cqe = rq->cqe[cons_idx];
+	status = be32_to_cpu(cqe->status);
+	csum_err = HINIC_RQ_CQE_STATUS_GET(status, CSUM_ERR);
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (!csum_err)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	else
+		skb->ip_summed = CHECKSUM_NONE;
+}
 /**
  * rx_alloc_skb - allocate skb and map it to dma address
  * @rxq: rx queue
@@ -209,7 +232,6 @@ skb_out:
 		hinic_rq_update(rxq->rq, prod_idx);
 	}
 
-	tasklet_schedule(&rxq->rx_task);
 	return i;
 }
 
@@ -237,17 +259,6 @@ static void free_all_rx_skbs(struct hinic_rxq *rxq)
 }
 
 /**
- * rx_alloc_task - tasklet for queue allocation
- * @data: rx queue
- **/
-static void rx_alloc_task(unsigned long data)
-{
-	struct hinic_rxq *rxq = (struct hinic_rxq *)data;
-
-	(void)rx_alloc_pkts(rxq);
-}
-
-/**
  * rx_recv_jumbo_pkt - Rx handler for jumbo pkt
  * @rxq: rx queue
  * @head_skb: the first skb in the list
@@ -311,6 +322,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 	struct hinic_qp *qp = container_of(rxq->rq, struct hinic_qp, rq);
 	u64 pkt_len = 0, rx_bytes = 0;
 	struct hinic_rq_wqe *rq_wqe;
+	unsigned int free_wqebbs;
 	int num_wqes, pkts = 0;
 	struct hinic_sge sge;
 	struct sk_buff *skb;
@@ -328,6 +340,8 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 
 		rx_unmap_skb(rxq, hinic_sge_to_dma(&sge));
 
+		rx_csum(rxq, ci, skb);
+
 		prefetch(skb->data);
 
 		pkt_len = sge.len;
@@ -352,8 +366,9 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 		rx_bytes += pkt_len;
 	}
 
-	if (pkts)
-		tasklet_schedule(&rxq->rx_task); /* rx_alloc_pkts */
+	free_wqebbs = hinic_get_rq_free_wqebbs(rxq->rq);
+	if (free_wqebbs > HINIC_RX_BUFFER_WRITE)
+		rx_alloc_pkts(rxq);
 
 	u64_stats_update_begin(&rxq->rxq_stats.syncp);
 	rxq->rxq_stats.pkts += pkts;
@@ -366,6 +381,7 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 static int rx_poll(struct napi_struct *napi, int budget)
 {
 	struct hinic_rxq *rxq = container_of(napi, struct hinic_rxq, napi);
+	struct hinic_dev *nic_dev = netdev_priv(rxq->netdev);
 	struct hinic_rq *rq = rxq->rq;
 	int pkts;
 
@@ -374,7 +390,10 @@ static int rx_poll(struct napi_struct *napi, int budget)
 		return budget;
 
 	napi_complete(napi);
-	enable_irq(rq->irq);
+	hinic_hwdev_set_msix_state(nic_dev->hwdev,
+				   rq->msix_entry,
+				   HINIC_MSIX_ENABLE);
+
 	return pkts;
 }
 
@@ -399,7 +418,10 @@ static irqreturn_t rx_irq(int irq, void *data)
 	struct hinic_dev *nic_dev;
 
 	/* Disable the interrupt until napi will be completed */
-	disable_irq_nosync(rq->irq);
+	nic_dev = netdev_priv(rxq->netdev);
+	hinic_hwdev_set_msix_state(nic_dev->hwdev,
+				   rq->msix_entry,
+				   HINIC_MSIX_DISABLE);
 
 	nic_dev = netdev_priv(rxq->netdev);
 	hinic_hwdev_msix_cnt_set(nic_dev->hwdev, rq->msix_entry);
@@ -470,8 +492,6 @@ int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
 
 	sprintf(rxq->irq_name, "hinic_rxq%d", qp->q_id);
 
-	tasklet_init(&rxq->rx_task, rx_alloc_task, (unsigned long)rxq);
-
 	pkts = rx_alloc_pkts(rxq);
 	if (!pkts) {
 		err = -ENOMEM;
@@ -488,7 +508,6 @@ int hinic_init_rxq(struct hinic_rxq *rxq, struct hinic_rq *rq,
 
 err_req_rx_irq:
 err_rx_pkts:
-	tasklet_kill(&rxq->rx_task);
 	free_all_rx_skbs(rxq);
 	devm_kfree(&netdev->dev, rxq->irq_name);
 	return err;
@@ -504,7 +523,6 @@ void hinic_clean_rxq(struct hinic_rxq *rxq)
 
 	rx_free_irq(rxq);
 
-	tasklet_kill(&rxq->rx_task);
 	free_all_rx_skbs(rxq);
 	devm_kfree(&netdev->dev, rxq->irq_name);
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.h b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
index 27c9af4b1c12..f8ed3fa6c8ee 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_rx.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.h
@@ -23,6 +23,10 @@
 
 #include "hinic_hw_qp.h"
 
+#define HINIC_RX_CSUM_OFFLOAD_EN	0xFFF
+#define HINIC_RX_CSUM_HW_CHECK_NONE	BIT(7)
+#define HINIC_RX_CSUM_IPSU_OTHER_ERR	BIT(8)
+
 struct hinic_rxq_stats {
 	u64                     pkts;
 	u64                     bytes;
@@ -38,8 +42,6 @@ struct hinic_rxq {
 
 	char                    *irq_name;
 
-	struct tasklet_struct   rx_task;
-
 	struct napi_struct      napi;
 };
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 11e73e67358d..e17bf33eba0c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -655,7 +655,9 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 
 	if (pkts < budget) {
 		napi_complete(napi);
-		enable_irq(sq->irq);
+		hinic_hwdev_set_msix_state(nic_dev->hwdev,
+					   sq->msix_entry,
+					   HINIC_MSIX_ENABLE);
 		return pkts;
 	}
 
@@ -682,7 +684,9 @@ static irqreturn_t tx_irq(int irq, void *data)
 	nic_dev = netdev_priv(txq->netdev);
 
 	/* Disable the interrupt until napi will be completed */
-	disable_irq_nosync(txq->sq->irq);
+	hinic_hwdev_set_msix_state(nic_dev->hwdev,
+				   txq->sq->msix_entry,
+				   HINIC_MSIX_DISABLE);
 
 	hinic_hwdev_msix_cnt_set(nic_dev->hwdev, txq->sq->msix_entry);
 
diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c
index d719668a6684..92929750f832 100644
--- a/drivers/net/ethernet/i825xx/82596.c
+++ b/drivers/net/ethernet/i825xx/82596.c
@@ -1310,7 +1310,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 						dev->stats.tx_aborted_errors++;
 				}
 
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 
 				tx_cmd->cmd.command = 0; /* Mark free */
 				break;
diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c
index 2f7ae118217f..1274ad24d6af 100644
--- a/drivers/net/ethernet/i825xx/lib82596.c
+++ b/drivers/net/ethernet/i825xx/lib82596.c
@@ -1194,7 +1194,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id)
 				dma_unmap_single(dev->dev.parent,
 						 tx_cmd->dma_addr,
 						 skb->len, DMA_TO_DEVICE);
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 
 				tx_cmd->cmd.command = 0; /* Mark free */
 				break;
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 3baabdc89726..90b62c1412c8 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -3160,6 +3160,7 @@ static ssize_t ehea_probe_port(struct device *dev,
 
 	if (ehea_add_adapter_mr(adapter)) {
 		pr_err("creating MR failed\n");
+		of_node_put(eth_dn);
 		return -EIO;
 	}
 
diff --git a/drivers/net/ethernet/ibm/emac/Kconfig b/drivers/net/ethernet/ibm/emac/Kconfig
index 90d49191beb3..eacf7e141fdc 100644
--- a/drivers/net/ethernet/ibm/emac/Kconfig
+++ b/drivers/net/ethernet/ibm/emac/Kconfig
@@ -28,18 +28,6 @@ config IBM_EMAC_RX_COPY_THRESHOLD
 	depends on IBM_EMAC
 	default "256"
 
-config IBM_EMAC_RX_SKB_HEADROOM
-	int "Additional RX skb headroom (bytes)"
-	depends on IBM_EMAC
-	default "0"
-	help
-	  Additional receive skb headroom. Note, that driver
-	  will always reserve at least 2 bytes to make IP header
-	  aligned, so usually there is no need to add any additional
-	  headroom.
-
-	  If unsure, set to 0.
-
 config IBM_EMAC_DEBUG
 	bool "Debugging"
 	depends on IBM_EMAC
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 760b2ad8e295..3c2a5759844a 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -1071,7 +1071,9 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 
 	/* Second pass, allocate new skbs */
 	for (i = 0; i < NUM_RX_BUFF; ++i) {
-		struct sk_buff *skb = alloc_skb(rx_skb_size, GFP_ATOMIC);
+		struct sk_buff *skb;
+
+		skb = netdev_alloc_skb_ip_align(dev->ndev, rx_skb_size);
 		if (!skb) {
 			ret = -ENOMEM;
 			goto oom;
@@ -1080,10 +1082,10 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu)
 		BUG_ON(!dev->rx_skb[i]);
 		dev_kfree_skb(dev->rx_skb[i]);
 
-		skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2);
 		dev->rx_desc[i].data_ptr =
-		    dma_map_single(&dev->ofdev->dev, skb->data - 2, rx_sync_size,
-				   DMA_FROM_DEVICE) + 2;
+		    dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+				   rx_sync_size, DMA_FROM_DEVICE)
+				   + NET_IP_ALIGN;
 		dev->rx_skb[i] = skb;
 	}
  skip:
@@ -1174,20 +1176,18 @@ static void emac_clean_rx_ring(struct emac_instance *dev)
 	}
 }
 
-static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot,
-				    gfp_t flags)
+static int
+__emac_prepare_rx_skb(struct sk_buff *skb, struct emac_instance *dev, int slot)
 {
-	struct sk_buff *skb = alloc_skb(dev->rx_skb_size, flags);
 	if (unlikely(!skb))
 		return -ENOMEM;
 
 	dev->rx_skb[slot] = skb;
 	dev->rx_desc[slot].data_len = 0;
 
-	skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2);
 	dev->rx_desc[slot].data_ptr =
-	    dma_map_single(&dev->ofdev->dev, skb->data - 2, dev->rx_sync_size,
-			   DMA_FROM_DEVICE) + 2;
+	    dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+			   dev->rx_sync_size, DMA_FROM_DEVICE) + NET_IP_ALIGN;
 	wmb();
 	dev->rx_desc[slot].ctrl = MAL_RX_CTRL_EMPTY |
 	    (slot == (NUM_RX_BUFF - 1) ? MAL_RX_CTRL_WRAP : 0);
@@ -1195,6 +1195,27 @@ static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot,
 	return 0;
 }
 
+static int
+emac_alloc_rx_skb(struct emac_instance *dev, int slot)
+{
+	struct sk_buff *skb;
+
+	skb = __netdev_alloc_skb_ip_align(dev->ndev, dev->rx_skb_size,
+					  GFP_KERNEL);
+
+	return __emac_prepare_rx_skb(skb, dev, slot);
+}
+
+static int
+emac_alloc_rx_skb_napi(struct emac_instance *dev, int slot)
+{
+	struct sk_buff *skb;
+
+	skb = napi_alloc_skb(&dev->mal->napi, dev->rx_skb_size);
+
+	return __emac_prepare_rx_skb(skb, dev, slot);
+}
+
 static void emac_print_link_status(struct emac_instance *dev)
 {
 	if (netif_carrier_ok(dev->ndev))
@@ -1225,7 +1246,7 @@ static int emac_open(struct net_device *ndev)
 
 	/* Allocate RX ring */
 	for (i = 0; i < NUM_RX_BUFF; ++i)
-		if (emac_alloc_rx_skb(dev, i, GFP_KERNEL)) {
+		if (emac_alloc_rx_skb(dev, i)) {
 			printk(KERN_ERR "%s: failed to allocate RX ring\n",
 			       ndev->name);
 			goto oom;
@@ -1660,8 +1681,9 @@ static inline void emac_recycle_rx_skb(struct emac_instance *dev, int slot,
 	DBG2(dev, "recycle %d %d" NL, slot, len);
 
 	if (len)
-		dma_map_single(&dev->ofdev->dev, skb->data - 2,
-			       EMAC_DMA_ALIGN(len + 2), DMA_FROM_DEVICE);
+		dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN,
+			       SKB_DATA_ALIGN(len + NET_IP_ALIGN),
+			       DMA_FROM_DEVICE);
 
 	dev->rx_desc[slot].data_len = 0;
 	wmb();
@@ -1713,7 +1735,7 @@ static inline int emac_rx_sg_append(struct emac_instance *dev, int slot)
 		int len = dev->rx_desc[slot].data_len;
 		int tot_len = dev->rx_sg_skb->len + len;
 
-		if (unlikely(tot_len + 2 > dev->rx_skb_size)) {
+		if (unlikely(tot_len + NET_IP_ALIGN > dev->rx_skb_size)) {
 			++dev->estats.rx_dropped_mtu;
 			dev_kfree_skb(dev->rx_sg_skb);
 			dev->rx_sg_skb = NULL;
@@ -1769,16 +1791,18 @@ static int emac_poll_rx(void *param, int budget)
 		}
 
 		if (len && len < EMAC_RX_COPY_THRESH) {
-			struct sk_buff *copy_skb =
-			    alloc_skb(len + EMAC_RX_SKB_HEADROOM + 2, GFP_ATOMIC);
+			struct sk_buff *copy_skb;
+
+			copy_skb = napi_alloc_skb(&dev->mal->napi, len);
 			if (unlikely(!copy_skb))
 				goto oom;
 
-			skb_reserve(copy_skb, EMAC_RX_SKB_HEADROOM + 2);
-			memcpy(copy_skb->data - 2, skb->data - 2, len + 2);
+			memcpy(copy_skb->data - NET_IP_ALIGN,
+			       skb->data - NET_IP_ALIGN,
+			       len + NET_IP_ALIGN);
 			emac_recycle_rx_skb(dev, slot, len);
 			skb = copy_skb;
-		} else if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC)))
+		} else if (unlikely(emac_alloc_rx_skb_napi(dev, slot)))
 			goto oom;
 
 		skb_put(skb, len);
@@ -1799,7 +1823,7 @@ static int emac_poll_rx(void *param, int budget)
 	sg:
 		if (ctrl & MAL_RX_CTRL_FIRST) {
 			BUG_ON(dev->rx_sg_skb);
-			if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC))) {
+			if (unlikely(emac_alloc_rx_skb_napi(dev, slot))) {
 				DBG(dev, "rx OOM %d" NL, slot);
 				++dev->estats.rx_dropped_oom;
 				emac_recycle_rx_skb(dev, slot, 0);
@@ -2455,7 +2479,8 @@ static void emac_adjust_link(struct net_device *ndev)
 	dev->phy.duplex = phy->duplex;
 	dev->phy.pause = phy->pause;
 	dev->phy.asym_pause = phy->asym_pause;
-	dev->phy.advertising = phy->advertising;
+	ethtool_convert_link_mode_to_legacy_u32(&dev->phy.advertising,
+						phy->advertising);
 }
 
 static int emac_mii_bus_read(struct mii_bus *bus, int addr, int regnum)
@@ -2490,7 +2515,8 @@ static int emac_mdio_phy_start_aneg(struct mii_phy *phy,
 	phy_dev->autoneg = phy->autoneg;
 	phy_dev->speed = phy->speed;
 	phy_dev->duplex = phy->duplex;
-	phy_dev->advertising = phy->advertising;
+	ethtool_convert_legacy_u32_to_link_mode(phy_dev->advertising,
+						phy->advertising);
 	return phy_start_aneg(phy_dev);
 }
 
@@ -2624,7 +2650,8 @@ static int emac_dt_phy_connect(struct emac_instance *dev,
 	dev->phy.def->phy_id_mask = dev->phy_dev->drv->phy_id_mask;
 	dev->phy.def->name = dev->phy_dev->drv->name;
 	dev->phy.def->ops = &emac_dt_mdio_phy_ops;
-	dev->phy.features = dev->phy_dev->supported;
+	ethtool_convert_link_mode_to_legacy_u32(&dev->phy.features,
+						dev->phy_dev->supported);
 	dev->phy.address = dev->phy_dev->mdio.addr;
 	dev->phy.mode = dev->phy_dev->interface;
 	return 0;
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index 84caa4a3fc52..187689cd8212 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -68,22 +68,18 @@ static inline int emac_rx_size(int mtu)
 		return mal_rx_size(ETH_DATA_LEN + EMAC_MTU_OVERHEAD);
 }
 
-#define EMAC_DMA_ALIGN(x)		ALIGN((x), dma_get_cache_alignment())
-
-#define EMAC_RX_SKB_HEADROOM		\
-	EMAC_DMA_ALIGN(CONFIG_IBM_EMAC_RX_SKB_HEADROOM)
-
 /* Size of RX skb for the given MTU */
 static inline int emac_rx_skb_size(int mtu)
 {
 	int size = max(mtu + EMAC_MTU_OVERHEAD, emac_rx_size(mtu));
-	return EMAC_DMA_ALIGN(size + 2) + EMAC_RX_SKB_HEADROOM;
+
+	return SKB_DATA_ALIGN(size + NET_IP_ALIGN) + NET_SKB_PAD;
 }
 
 /* RX DMA sync size */
 static inline int emac_rx_sync_size(int mtu)
 {
-	return EMAC_DMA_ALIGN(emac_rx_size(mtu) + 2);
+	return SKB_DATA_ALIGN(emac_rx_size(mtu) + NET_IP_ALIGN);
 }
 
 /* Driver statistcs is split into two parts to make it more cache friendly:
diff --git a/drivers/net/ethernet/ibm/emac/mal.c b/drivers/net/ethernet/ibm/emac/mal.c
index fff09dcf9e34..787d5aca5278 100644
--- a/drivers/net/ethernet/ibm/emac/mal.c
+++ b/drivers/net/ethernet/ibm/emac/mal.c
@@ -636,8 +636,8 @@ static int mal_probe(struct platform_device *ofdev)
 	bd_size = sizeof(struct mal_descriptor) *
 		(NUM_TX_BUFF * mal->num_tx_chans +
 		 NUM_RX_BUFF * mal->num_rx_chans);
-	mal->bd_virt = dma_zalloc_coherent(&ofdev->dev, bd_size, &mal->bd_dma,
-					   GFP_KERNEL);
+	mal->bd_virt = dma_alloc_coherent(&ofdev->dev, bd_size, &mal->bd_dma,
+					  GFP_KERNEL);
 	if (mal->bd_virt == NULL) {
 		err = -ENOMEM;
 		goto fail_unmap;
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index a4681780a55d..dd71d5db7274 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -1171,11 +1171,15 @@ out:
 
 map_failed_frags:
 	last = i+1;
-	for (i = 0; i < last; i++)
+	for (i = 1; i < last; i++)
 		dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address,
 			       descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK,
 			       DMA_TO_DEVICE);
 
+	dma_unmap_single(&adapter->vdev->dev,
+			 descs[0].fields.address,
+			 descs[0].fields.flags_len & IBMVETH_BUF_LEN_MASK,
+			 DMA_TO_DEVICE);
 map_failed:
 	if (!firmware_has_feature(FW_FEATURE_CMO))
 		netdev_err(netdev, "tx: unable to map xmit buffer\n");
@@ -1309,7 +1313,6 @@ static int ibmveth_poll(struct napi_struct *napi, int budget)
 	unsigned long lpar_rc;
 	u16 mss = 0;
 
-restart_poll:
 	while (frames_processed < budget) {
 		if (!ibmveth_rxq_pending_buffer(adapter))
 			break;
@@ -1397,7 +1400,6 @@ restart_poll:
 		    napi_reschedule(napi)) {
 			lpar_rc = h_vio_signal(adapter->vdev->unit_address,
 					       VIO_IRQ_DISABLE);
-			goto restart_poll;
 		}
 	}
 
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 67cc6d9c8fd7..3dfb2d131eb7 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -773,11 +773,8 @@ static void release_napi(struct ibmvnic_adapter *adapter)
 		return;
 
 	for (i = 0; i < adapter->num_active_rx_napi; i++) {
-		if (&adapter->napi[i]) {
-			netdev_dbg(adapter->netdev,
-				   "Releasing napi[%d]\n", i);
-			netif_napi_del(&adapter->napi[i]);
-		}
+		netdev_dbg(adapter->netdev, "Releasing napi[%d]\n", i);
+		netif_napi_del(&adapter->napi[i]);
 	}
 
 	kfree(adapter->napi);
@@ -1888,6 +1885,7 @@ static int do_hard_reset(struct ibmvnic_adapter *adapter,
 	 */
 	adapter->state = VNIC_PROBED;
 
+	reinit_completion(&adapter->init_done);
 	rc = init_crq_queue(adapter);
 	if (rc) {
 		netdev_err(adapter->netdev,
@@ -3764,6 +3762,7 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
+	netdev_features_t old_hw_features = 0;
 	union ibmvnic_crq crq;
 	int i;
 
@@ -3839,24 +3838,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	adapter->ip_offload_ctrl.large_rx_ipv4 = 0;
 	adapter->ip_offload_ctrl.large_rx_ipv6 = 0;
 
-	adapter->netdev->features = NETIF_F_SG | NETIF_F_GSO;
+	if (adapter->state != VNIC_PROBING) {
+		old_hw_features = adapter->netdev->hw_features;
+		adapter->netdev->hw_features = 0;
+	}
+
+	adapter->netdev->hw_features = NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO;
 
 	if (buf->tcp_ipv4_chksum || buf->udp_ipv4_chksum)
-		adapter->netdev->features |= NETIF_F_IP_CSUM;
+		adapter->netdev->hw_features |= NETIF_F_IP_CSUM;
 
 	if (buf->tcp_ipv6_chksum || buf->udp_ipv6_chksum)
-		adapter->netdev->features |= NETIF_F_IPV6_CSUM;
+		adapter->netdev->hw_features |= NETIF_F_IPV6_CSUM;
 
 	if ((adapter->netdev->features &
 	    (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)))
-		adapter->netdev->features |= NETIF_F_RXCSUM;
+		adapter->netdev->hw_features |= NETIF_F_RXCSUM;
 
 	if (buf->large_tx_ipv4)
-		adapter->netdev->features |= NETIF_F_TSO;
+		adapter->netdev->hw_features |= NETIF_F_TSO;
 	if (buf->large_tx_ipv6)
-		adapter->netdev->features |= NETIF_F_TSO6;
+		adapter->netdev->hw_features |= NETIF_F_TSO6;
 
-	adapter->netdev->hw_features |= adapter->netdev->features;
+	if (adapter->state == VNIC_PROBING) {
+		adapter->netdev->features |= adapter->netdev->hw_features;
+	} else if (old_hw_features != adapter->netdev->hw_features) {
+		netdev_features_t tmp = 0;
+
+		/* disable features no longer supported */
+		adapter->netdev->features &= adapter->netdev->hw_features;
+		/* turn on features now supported if previously enabled */
+		tmp = (old_hw_features ^ adapter->netdev->hw_features) &
+			adapter->netdev->hw_features;
+		adapter->netdev->features |=
+				tmp & adapter->netdev->wanted_features;
+	}
 
 	memset(&crq, 0, sizeof(crq));
 	crq.control_ip_offload.first = IBMVNIC_CRQ_CMD;
@@ -4628,7 +4644,7 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter)
 	old_num_rx_queues = adapter->req_rx_queues;
 	old_num_tx_queues = adapter->req_tx_queues;
 
-	init_completion(&adapter->init_done);
+	reinit_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4683,7 +4699,6 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
 
 	adapter->from_passive_init = false;
 
-	init_completion(&adapter->init_done);
 	adapter->init_done_rc = 0;
 	ibmvnic_send_crq_init(adapter);
 	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
@@ -4762,6 +4777,7 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	spin_lock_init(&adapter->rwi_lock);
+	init_completion(&adapter->init_done);
 	adapter->resetting = false;
 
 	adapter->mac_change_pending = false;
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 59e1bc0f609e..a1246e89aad4 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -33,7 +33,7 @@ config E100
 	  to identify the adapter.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/e100.rst>.
+	  <file:Documentation/networking/device_drivers/intel/e100.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called e100.
@@ -49,7 +49,7 @@ config E1000
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/e1000.rst>.
+	  <file:Documentation/networking/device_drivers/intel/e1000.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called e1000.
@@ -69,7 +69,7 @@ config E1000E
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/e1000e.rst>.
+	  <file:Documentation/networking/device_drivers/intel/e1000e.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called e1000e.
@@ -97,7 +97,7 @@ config IGB
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/igb.rst>.
+	  <file:Documentation/networking/device_drivers/intel/igb.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called igb.
@@ -133,7 +133,7 @@ config IGBVF
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/igbvf.rst>.
+	  <file:Documentation/networking/device_drivers/intel/igbvf.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called igbvf.
@@ -150,7 +150,7 @@ config IXGB
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ixgb.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ixgb.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgb.
@@ -159,6 +159,7 @@ config IXGBE
 	tristate "Intel(R) 10GbE PCI Express adapters support"
 	depends on PCI
 	select MDIO
+	select PHYLIB
 	imply PTP_1588_CLOCK
 	---help---
 	  This driver supports Intel(R) 10GbE PCI Express family of
@@ -168,7 +169,7 @@ config IXGBE
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ixgbe.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ixgbe.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgbe.
@@ -220,7 +221,7 @@ config IXGBEVF
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ixgbevf.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ixgbevf.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ixgbevf.  MSI-X interrupt support is required
@@ -247,7 +248,7 @@ config I40E
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/i40e.rst>.
+	  <file:Documentation/networking/device_drivers/intel/i40e.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called i40e.
@@ -282,7 +283,7 @@ config I40EVF
 	  This driver was formerly named i40evf.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/iavf.rst>.
+	  <file:Documentation/networking/device_drivers/intel/iavf.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called iavf.  MSI-X interrupt support is required
@@ -300,7 +301,7 @@ config ICE
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/ice.rst>.
+	  <file:Documentation/networking/device_drivers/intel/ice.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called ice.
@@ -318,7 +319,7 @@ config FM10K
 	  <http://support.intel.com>
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/fm10k.rst>.
+	  <file:Documentation/networking/device_drivers/intel/fm10k.rst>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called fm10k.  MSI-X interrupt support is required
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 7c4b55482f72..0fd268070fb4 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -1345,8 +1345,8 @@ static inline int e100_load_ucode_wait(struct nic *nic)
 
 	fw = e100_request_firmware(nic);
 	/* If it's NULL, then no ucode is required */
-	if (!fw || IS_ERR(fw))
-		return PTR_ERR(fw);
+	if (IS_ERR_OR_NULL(fw))
+		return PTR_ERR_OR_ZERO(fw);
 
 	if ((err = e100_exec_cb(nic, (void *)fw, e100_setup_ucode)))
 		netif_err(nic, probe, nic->netdev,
@@ -2225,11 +2225,13 @@ static int e100_poll(struct napi_struct *napi, int budget)
 	e100_rx_clean(nic, &work_done, budget);
 	e100_tx_clean(nic);
 
-	/* If budget not fully consumed, exit the polling mode */
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
+	/* If budget fully consumed, continue polling */
+	if (work_done == budget)
+		return budget;
+
+	/* only re-enable interrupt if stack agrees polling is really done */
+	if (likely(napi_complete_done(napi, work_done)))
 		e100_enable_irq(nic);
-	}
 
 	return work_done;
 }
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 2569a168334c..a41008523c98 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -993,8 +993,8 @@ static int e1000_setup_desc_rings(struct e1000_adapter *adapter)
 
 	txdr->size = txdr->count * sizeof(struct e1000_tx_desc);
 	txdr->size = ALIGN(txdr->size, 4096);
-	txdr->desc = dma_zalloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
-					 GFP_KERNEL);
+	txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
+					GFP_KERNEL);
 	if (!txdr->desc) {
 		ret_val = 2;
 		goto err_nomem;
@@ -1051,8 +1051,8 @@ static int e1000_setup_desc_rings(struct e1000_adapter *adapter)
 	}
 
 	rxdr->size = rxdr->count * sizeof(struct e1000_rx_desc);
-	rxdr->desc = dma_zalloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
-					 GFP_KERNEL);
+	rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
+					GFP_KERNEL);
 	if (!rxdr->desc) {
 		ret_val = 6;
 		goto err_nomem;
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 43b6d3cec3b3..8fe9af0e2ab7 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -3803,14 +3803,15 @@ static int e1000_clean(struct napi_struct *napi, int budget)
 
 	adapter->clean_rx(adapter, &adapter->rx_ring[0], &work_done, budget);
 
-	if (!tx_clean_complete)
-		work_done = budget;
+	if (!tx_clean_complete || work_done == budget)
+		return budget;
 
-	/* If budget not fully consumed, exit the polling mode */
-	if (work_done < budget) {
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
 		if (likely(adapter->itr_setting & 3))
 			e1000_set_itr(adapter);
-		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->flags))
 			e1000_irq_enable(adapter);
 	}
diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
index 257bd59bc9c6..f86d55657959 100644
--- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c
+++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c
@@ -696,11 +696,16 @@ static s32 e1000_reset_hw_80003es2lan(struct e1000_hw *hw)
 	ret_val =
 	    e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
 					    &kum_reg_data);
-	if (ret_val)
-		return ret_val;
-	kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
-	e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					 kum_reg_data);
+	if (!ret_val) {
+		kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
+		ret_val = e1000_write_kmrn_reg_80003es2lan(hw,
+						 E1000_KMRNCTRLSTA_INBAND_PARAM,
+						 kum_reg_data);
+		if (ret_val)
+			e_dbg("Error disabling far-end loopback\n");
+	} else {
+		e_dbg("Error disabling far-end loopback\n");
+	}
 
 	ret_val = e1000e_get_auto_rd_done(hw);
 	if (ret_val)
@@ -754,11 +759,19 @@ static s32 e1000_init_hw_80003es2lan(struct e1000_hw *hw)
 		return ret_val;
 
 	/* Disable IBIST slave mode (far-end loopback) */
-	e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					&kum_reg_data);
-	kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
-	e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
-					 kum_reg_data);
+	ret_val =
+	    e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM,
+					    &kum_reg_data);
+	if (!ret_val) {
+		kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE;
+		ret_val = e1000_write_kmrn_reg_80003es2lan(hw,
+						 E1000_KMRNCTRLSTA_INBAND_PARAM,
+						 kum_reg_data);
+		if (ret_val)
+			e_dbg("Error disabling far-end loopback\n");
+	} else {
+		e_dbg("Error disabling far-end loopback\n");
+	}
 
 	/* Set the transmit descriptor write-back policy */
 	reg_data = er32(TXDCTL(0));
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index c760dc72c520..be13227f1697 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -505,6 +505,9 @@ extern const struct e1000_info e1000_es2_info;
 void e1000e_ptp_init(struct e1000_adapter *adapter);
 void e1000e_ptp_remove(struct e1000_adapter *adapter);
 
+u64 e1000e_read_systim(struct e1000_adapter *adapter,
+		       struct ptp_system_timestamp *sts);
+
 static inline s32 e1000_phy_hw_reset(struct e1000_hw *hw)
 {
 	return hw->phy.ops.reset(hw);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 16a73bd9f4cb..7acc61e4f645 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -2106,7 +2106,7 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 	if (strlen(netdev->name) < (IFNAMSIZ - 5))
 		snprintf(adapter->rx_ring->name,
 			 sizeof(adapter->rx_ring->name) - 1,
-			 "%s-rx-0", netdev->name);
+			 "%.14s-rx-0", netdev->name);
 	else
 		memcpy(adapter->rx_ring->name, netdev->name, IFNAMSIZ);
 	err = request_irq(adapter->msix_entries[vector].vector,
@@ -2122,7 +2122,7 @@ static int e1000_request_msix(struct e1000_adapter *adapter)
 	if (strlen(netdev->name) < (IFNAMSIZ - 5))
 		snprintf(adapter->tx_ring->name,
 			 sizeof(adapter->tx_ring->name) - 1,
-			 "%s-tx-0", netdev->name);
+			 "%.14s-tx-0", netdev->name);
 	else
 		memcpy(adapter->tx_ring->name, netdev->name, IFNAMSIZ);
 	err = request_irq(adapter->msix_entries[vector].vector,
@@ -2305,8 +2305,8 @@ static int e1000_alloc_ring_dma(struct e1000_adapter *adapter,
 {
 	struct pci_dev *pdev = adapter->pdev;
 
-	ring->desc = dma_zalloc_coherent(&pdev->dev, ring->size, &ring->dma,
-					 GFP_KERNEL);
+	ring->desc = dma_alloc_coherent(&pdev->dev, ring->size, &ring->dma,
+					GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
@@ -2651,9 +2651,9 @@ err:
 /**
  * e1000e_poll - NAPI Rx polling callback
  * @napi: struct associated with this polling callback
- * @weight: number of packets driver is allowed to process this poll
+ * @budget: number of packets driver is allowed to process this poll
  **/
-static int e1000e_poll(struct napi_struct *napi, int weight)
+static int e1000e_poll(struct napi_struct *napi, int budget)
 {
 	struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter,
 						     napi);
@@ -2667,16 +2667,17 @@ static int e1000e_poll(struct napi_struct *napi, int weight)
 	    (adapter->rx_ring->ims_val & adapter->tx_ring->ims_val))
 		tx_cleaned = e1000_clean_tx_irq(adapter->tx_ring);
 
-	adapter->clean_rx(adapter->rx_ring, &work_done, weight);
+	adapter->clean_rx(adapter->rx_ring, &work_done, budget);
 
-	if (!tx_cleaned)
-		work_done = weight;
+	if (!tx_cleaned || work_done == budget)
+		return budget;
 
-	/* If weight not fully consumed, exit the polling mode */
-	if (work_done < weight) {
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
 		if (adapter->itr_setting & 3)
 			e1000_set_itr(adapter);
-		napi_complete_done(napi, work_done);
 		if (!test_bit(__E1000_DOWN, &adapter->state)) {
 			if (adapter->msix_entries)
 				ew32(IMS, adapter->rx_ring->ims_val);
@@ -4319,13 +4320,16 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter)
 /**
  * e1000e_sanitize_systim - sanitize raw cycle counter reads
  * @hw: pointer to the HW structure
- * @systim: time value read, sanitized and returned
+ * @systim: PHC time value read, sanitized and returned
+ * @sts: structure to hold system time before and after reading SYSTIML,
+ * may be NULL
  *
  * Errata for 82574/82583 possible bad bits read from SYSTIMH/L:
  * check to see that the time is incrementing at a reasonable
  * rate and is a multiple of incvalue.
  **/
-static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
+static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim,
+				  struct ptp_system_timestamp *sts)
 {
 	u64 time_delta, rem, temp;
 	u64 systim_next;
@@ -4335,7 +4339,9 @@ static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
 	incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK;
 	for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) {
 		/* latch SYSTIMH on read of SYSTIML */
+		ptp_read_system_prets(sts);
 		systim_next = (u64)er32(SYSTIML);
+		ptp_read_system_postts(sts);
 		systim_next |= (u64)er32(SYSTIMH) << 32;
 
 		time_delta = systim_next - systim;
@@ -4353,15 +4359,16 @@ static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim)
 }
 
 /**
- * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
- * @cc: cyclecounter structure
+ * e1000e_read_systim - read SYSTIM register
+ * @adapter: board private structure
+ * @sts: structure which will contain system time before and after reading
+ * SYSTIML, may be NULL
  **/
-static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+u64 e1000e_read_systim(struct e1000_adapter *adapter,
+		       struct ptp_system_timestamp *sts)
 {
-	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
-						     cc);
 	struct e1000_hw *hw = &adapter->hw;
-	u32 systimel, systimeh;
+	u32 systimel, systimel_2, systimeh;
 	u64 systim;
 	/* SYSTIMH latching upon SYSTIML read does not work well.
 	 * This means that if SYSTIML overflows after we read it but before
@@ -4369,11 +4376,15 @@ static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
 	 * will experience a huge non linear increment in the systime value
 	 * to fix that we test for overflow and if true, we re-read systime.
 	 */
+	ptp_read_system_prets(sts);
 	systimel = er32(SYSTIML);
+	ptp_read_system_postts(sts);
 	systimeh = er32(SYSTIMH);
 	/* Is systimel is so large that overflow is possible? */
 	if (systimel >= (u32)0xffffffff - E1000_TIMINCA_INCVALUE_MASK) {
-		u32 systimel_2 = er32(SYSTIML);
+		ptp_read_system_prets(sts);
+		systimel_2 = er32(SYSTIML);
+		ptp_read_system_postts(sts);
 		if (systimel > systimel_2) {
 			/* There was an overflow, read again SYSTIMH, and use
 			 * systimel_2
@@ -4386,12 +4397,24 @@ static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
 	systim |= (u64)systimeh << 32;
 
 	if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW)
-		systim = e1000e_sanitize_systim(hw, systim);
+		systim = e1000e_sanitize_systim(hw, systim, sts);
 
 	return systim;
 }
 
 /**
+ * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
+ * @cc: cyclecounter structure
+ **/
+static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+{
+	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
+						     cc);
+
+	return e1000e_read_systim(adapter, NULL);
+}
+
+/**
  * e1000_sw_init - Initialize general software structures (struct e1000_adapter)
  * @adapter: board private structure to initialize
  *
@@ -5286,8 +5309,13 @@ static void e1000_watchdog_task(struct work_struct *work)
 			/* 8000ES2LAN requires a Rx packet buffer work-around
 			 * on link down event; reset the controller to flush
 			 * the Rx packet buffer.
+			 *
+			 * If the link is lost the controller stops DMA, but
+			 * if there is queued Tx work it cannot be done.  So
+			 * reset the controller to flush the Tx packet buffers.
 			 */
-			if (adapter->flags & FLAG_RX_NEEDS_RESTART)
+			if ((adapter->flags & FLAG_RX_NEEDS_RESTART) ||
+			    e1000_desc_unused(tx_ring) + 1 < tx_ring->count)
 				adapter->flags |= FLAG_RESTART_NOW;
 			else
 				pm_schedule_suspend(netdev->dev.parent,
@@ -5310,14 +5338,6 @@ link_up:
 	adapter->gotc_old = adapter->stats.gotc;
 	spin_unlock(&adapter->stats64_lock);
 
-	/* If the link is lost the controller stops DMA, but
-	 * if there is queued Tx work it cannot be done.  So
-	 * reset the controller to flush the Tx packet buffers.
-	 */
-	if (!netif_carrier_ok(netdev) &&
-	    (e1000_desc_unused(tx_ring) + 1 < tx_ring->count))
-		adapter->flags |= FLAG_RESTART_NOW;
-
 	/* If reset is necessary, do it outside of interrupt context. */
 	if (adapter->flags & FLAG_RESTART_NOW) {
 		schedule_work(&adapter->reset_task);
@@ -7328,6 +7348,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	e1000_print_device_info(adapter);
 
+	dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP);
+
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_noidle(&pdev->dev);
 
diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c
index 37c76945ad9b..1a4c65d9feb4 100644
--- a/drivers/net/ethernet/intel/e1000e/ptp.c
+++ b/drivers/net/ethernet/intel/e1000e/ptp.c
@@ -161,22 +161,30 @@ static int e1000e_phc_getcrosststamp(struct ptp_clock_info *ptp,
 #endif/*CONFIG_E1000E_HWTS*/
 
 /**
- * e1000e_phc_gettime - Reads the current time from the hardware clock
+ * e1000e_phc_gettimex - Reads the current time from the hardware clock and
+ *                       system clock
  * @ptp: ptp clock structure
- * @ts: timespec structure to hold the current time value
+ * @ts: timespec structure to hold the current PHC time
+ * @sts: structure to hold the current system time
  *
  * Read the timecounter and return the correct value in ns after converting
  * it into a struct timespec.
  **/
-static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int e1000e_phc_gettimex(struct ptp_clock_info *ptp,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
 {
 	struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter,
 						     ptp_clock_info);
 	unsigned long flags;
-	u64 ns;
+	u64 cycles, ns;
 
 	spin_lock_irqsave(&adapter->systim_lock, flags);
-	ns = timecounter_read(&adapter->tc);
+
+	/* NOTE: Non-monotonic SYSTIM readings may be returned */
+	cycles = e1000e_read_systim(adapter, sts);
+	ns = timecounter_cyc2time(&adapter->tc, cycles);
+
 	spin_unlock_irqrestore(&adapter->systim_lock, flags);
 
 	*ts = ns_to_timespec64(ns);
@@ -232,9 +240,12 @@ static void e1000e_systim_overflow_work(struct work_struct *work)
 						     systim_overflow_work.work);
 	struct e1000_hw *hw = &adapter->hw;
 	struct timespec64 ts;
+	u64 ns;
 
-	adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts);
+	/* Update the timecounter */
+	ns = timecounter_read(&adapter->tc);
 
+	ts = ns_to_timespec64(ns);
 	e_dbg("SYSTIM overflow check at %lld.%09lu\n",
 	      (long long) ts.tv_sec, ts.tv_nsec);
 
@@ -251,7 +262,7 @@ static const struct ptp_clock_info e1000e_ptp_clock_info = {
 	.pps		= 0,
 	.adjfreq	= e1000e_phc_adjfreq,
 	.adjtime	= e1000e_phc_adjtime,
-	.gettime64	= e1000e_phc_gettime,
+	.gettimex64	= e1000e_phc_gettimex,
 	.settime64	= e1000e_phc_settime,
 	.enable		= e1000e_phc_enable,
 };
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 5b2a50e5798f..ecef949f3baa 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -41,6 +41,8 @@ static int __init fm10k_init_module(void)
 	/* create driver workqueue */
 	fm10k_workqueue = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0,
 					  fm10k_driver_name);
+	if (!fm10k_workqueue)
+		return -ENOMEM;
 
 	fm10k_dbg_init();
 
@@ -1465,11 +1467,11 @@ static int fm10k_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* all work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-
-	/* re-enable the q_vector */
-	fm10k_qv_enable(q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		fm10k_qv_enable(q_vector);
 
 	return min(work_done, budget - 1);
 }
@@ -1603,14 +1605,12 @@ static int fm10k_alloc_q_vector(struct fm10k_intfc *interface,
 {
 	struct fm10k_q_vector *q_vector;
 	struct fm10k_ring *ring;
-	int ring_count, size;
+	int ring_count;
 
 	ring_count = txr_count + rxr_count;
-	size = sizeof(struct fm10k_q_vector) +
-	       (sizeof(struct fm10k_ring) * ring_count);
 
 	/* allocate q_vector and rings */
-	q_vector = kzalloc(size, GFP_KERNEL);
+	q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL);
 	if (!q_vector)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
index 8f0a99b6a537..cb4d02629b86 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c
@@ -1148,7 +1148,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw,
  *  @results: Pointer array to message, results[0] is pointer to message
  *  @mbx: Pointer to mailbox information structure
  *
- *  This function is a default handler for MSI-X requests from the VF.  The
+ *  This function is a default handler for MSI-X requests from the VF. The
  *  assumption is that in this case it is acceptable to just directly
  *  hand off the message from the VF to the underlying shared code.
  **/
diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h
index 876cac317e79..d3cc3427caad 100644
--- a/drivers/net/ethernet/intel/i40e/i40e.h
+++ b/drivers/net/ethernet/intel/i40e/i40e.h
@@ -34,6 +34,7 @@
 #include <net/pkt_cls.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
+#include <net/xdp_sock.h>
 #include "i40e_type.h"
 #include "i40e_prototype.h"
 #include "i40e_client.h"
@@ -122,6 +123,7 @@ enum i40e_state_t {
 	__I40E_MDD_EVENT_PENDING,
 	__I40E_VFLR_EVENT_PENDING,
 	__I40E_RESET_RECOVERY_PENDING,
+	__I40E_TIMEOUT_RECOVERY_PENDING,
 	__I40E_MISC_IRQ_REQUESTED,
 	__I40E_RESET_INTR_RECEIVED,
 	__I40E_REINIT_REQUESTED,
@@ -146,6 +148,7 @@ enum i40e_state_t {
 	__I40E_CLIENT_SERVICE_REQUESTED,
 	__I40E_CLIENT_L2_CHANGE,
 	__I40E_CLIENT_RESET,
+	__I40E_VIRTCHNL_OP_PENDING,
 	/* This must be last as it determines the size of the BITMAP */
 	__I40E_STATE_SIZE__,
 };
@@ -494,7 +497,6 @@ struct i40e_pf {
 #define I40E_HW_STOP_FW_LLDP			BIT(16)
 #define I40E_HW_PORT_ID_VALID			BIT(17)
 #define I40E_HW_RESTART_AUTONEG			BIT(18)
-#define I40E_HW_STOPPABLE_FW_LLDP		BIT(19)
 
 	u32 flags;
 #define I40E_FLAG_RX_CSUM_ENABLED		BIT(0)
@@ -522,6 +524,8 @@ struct i40e_pf {
 #define I40E_FLAG_FD_SB_INACTIVE		BIT(22)
 #define I40E_FLAG_FD_SB_TO_CLOUD_FILTER		BIT(23)
 #define I40E_FLAG_DISABLE_FW_LLDP		BIT(24)
+#define I40E_FLAG_RS_FEC			BIT(25)
+#define I40E_FLAG_BASE_R_FEC			BIT(26)
 
 	struct i40e_client_instance *cinst;
 	bool stat_offsets_loaded;
@@ -787,10 +791,7 @@ struct i40e_vsi {
 	/* VSI specific handlers */
 	irqreturn_t (*irq_handler)(int irq, void *data);
 
-	/* AF_XDP zero-copy */
-	struct xdp_umem **xsk_umems;
-	u16 num_xsk_umems_used;
-	u16 num_xsk_umems;
+	unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled qps */
 } ____cacheline_internodealigned_in_smp;
 
 struct i40e_netdev_priv {
@@ -1090,25 +1091,13 @@ i40e_status i40e_set_partition_bw_setting(struct i40e_pf *pf);
 i40e_status i40e_commit_partition_bw_setting(struct i40e_pf *pf);
 void i40e_print_link_message(struct i40e_vsi *vsi, bool isup);
 
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags);
+
 static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi)
 {
 	return !!vsi->xdp_prog;
 }
 
-static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
-{
-	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
-	int qid = ring->queue_index;
-
-	if (ring_is_xdp(ring))
-		qid -= ring->vsi->alloc_queue_pairs;
-
-	if (!ring->vsi->xsk_umems || !ring->vsi->xsk_umems[qid] || !xdp_on)
-		return NULL;
-
-	return ring->vsi->xsk_umems[qid];
-}
-
 int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch);
 int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate);
 int i40e_add_del_cloud_filter(struct i40e_vsi *vsi,
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 501ee718177f..7ab61f6ebb5f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -588,6 +588,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
 	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
 	    hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) {
 		hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
+		hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
+	}
+	if (hw->mac.type == I40E_MAC_X722 &&
+	    hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR &&
+	    hw->aq.api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722) {
+		hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE;
 	}
 
 	/* Newer versions of firmware require lock when reading the NVM */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 80e3eec6134e..11506102471c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -11,7 +11,7 @@
  */
 
 #define I40E_FW_API_VERSION_MAJOR	0x0001
-#define I40E_FW_API_VERSION_MINOR_X722	0x0005
+#define I40E_FW_API_VERSION_MINOR_X722	0x0006
 #define I40E_FW_API_VERSION_MINOR_X710	0x0007
 
 #define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \
@@ -20,6 +20,8 @@
 
 /* API version 1.7 implements additional link and PHY-specific APIs  */
 #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007
+/* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */
+#define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006
 
 struct i40e_aq_desc {
 	__le16 flags;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index 85f75b5978fc..97a9b1fb4763 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -3723,6 +3723,9 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 		(struct i40e_aqc_set_dcb_parameters *)&desc.params.raw;
 	i40e_status status;
 
+	if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+		return I40E_ERR_DEVICE_NOT_SUPPORTED;
+
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_dcb_parameters);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index a20d1cf058ad..c67d485d6f99 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -1642,30 +1642,7 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 		count = buf_tmp - i40e_dbg_netdev_ops_buf + 1;
 	}
 
-	if (strncmp(i40e_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) {
-		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i", &vsi_seid);
-		if (cnt != 1) {
-			dev_info(&pf->pdev->dev, "tx_timeout <vsi_seid>\n");
-			goto netdev_ops_write_done;
-		}
-		vsi = i40e_dbg_find_vsi(pf, vsi_seid);
-		if (!vsi) {
-			dev_info(&pf->pdev->dev,
-				 "tx_timeout: VSI %d not found\n", vsi_seid);
-		} else if (!vsi->netdev) {
-			dev_info(&pf->pdev->dev, "tx_timeout: no netdev for VSI %d\n",
-				 vsi_seid);
-		} else if (test_bit(__I40E_VSI_DOWN, vsi->state)) {
-			dev_info(&pf->pdev->dev, "tx_timeout: VSI %d not UP\n",
-				 vsi_seid);
-		} else if (rtnl_trylock()) {
-			vsi->netdev->netdev_ops->ndo_tx_timeout(vsi->netdev);
-			rtnl_unlock();
-			dev_info(&pf->pdev->dev, "tx_timeout called\n");
-		} else {
-			dev_info(&pf->pdev->dev, "Could not acquire RTNL - please try again\n");
-		}
-	} else if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
+	if (strncmp(i40e_dbg_netdev_ops_buf, "change_mtu", 10) == 0) {
 		int mtu;
 
 		cnt = sscanf(&i40e_dbg_netdev_ops_buf[11], "%i %i",
@@ -1733,7 +1710,6 @@ static ssize_t i40e_dbg_netdev_ops_write(struct file *filp,
 		dev_info(&pf->pdev->dev, "unknown command '%s'\n",
 			 i40e_dbg_netdev_ops_buf);
 		dev_info(&pf->pdev->dev, "available commands\n");
-		dev_info(&pf->pdev->dev, "  tx_timeout <vsi_seid>\n");
 		dev_info(&pf->pdev->dev, "  change_mtu <vsi_seid> <mtu>\n");
 		dev_info(&pf->pdev->dev, "  set_rx_mode <vsi_seid>\n");
 		dev_info(&pf->pdev->dev, "  napi <vsi_seid>\n");
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 9f8464f80783..7874d0ec7fb0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -438,6 +438,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = {
 	I40E_PRIV_FLAG("disable-source-pruning",
 		       I40E_FLAG_SOURCE_PRUNING_DISABLED, 0),
 	I40E_PRIV_FLAG("disable-fw-lldp", I40E_FLAG_DISABLE_FW_LLDP, 0),
+	I40E_PRIV_FLAG("rs-fec", I40E_FLAG_RS_FEC, 0),
+	I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0),
 };
 
 #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags)
@@ -606,6 +608,24 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf,
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     25000baseCR_Full);
 	}
+	if (phy_types & I40E_CAP_PHY_TYPE_25GBASE_KR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_CR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_SR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_LR ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_AOC ||
+	    phy_types & I40E_CAP_PHY_TYPE_25GBASE_ACC) {
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		if (hw_link_info->requested_speeds & I40E_LINK_SPEED_25GB) {
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     FEC_NONE);
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     FEC_RS);
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     FEC_BASER);
+		}
+	}
 	/* need to add new 10G PHY types */
 	if (phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1 ||
 	    phy_types & I40E_CAP_PHY_TYPE_10GBASE_CR1_CU) {
@@ -721,6 +741,13 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     25000baseSR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseSR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseSR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -825,6 +852,9 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     40000baseKR4_Full);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     20000baseKR2_Full);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
@@ -838,6 +868,10 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     40000baseKR4_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseKR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     20000baseKR2_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -855,6 +889,13 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 						     25000baseCR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		break;
 	case I40E_PHY_TYPE_25GBASE_AOC:
 	case I40E_PHY_TYPE_25GBASE_ACC:
@@ -862,9 +903,15 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     25000baseCR_Full);
-
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     25000baseCR_Full);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     FEC_BASER);
 		ethtool_link_ksettings_add_link_mode(ks, supported,
 						     10000baseCR_Full);
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
@@ -906,6 +953,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw,
 		ks->base.speed = SPEED_100;
 		break;
 	default:
+		ks->base.speed = SPEED_UNKNOWN;
 		break;
 	}
 	ks->base.duplex = DUPLEX_FULL;
@@ -1260,6 +1308,154 @@ done:
 	return err;
 }
 
+static int i40e_set_fec_cfg(struct net_device *netdev, u8 fec_cfg)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_aq_get_phy_abilities_resp abilities;
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	i40e_status status = 0;
+	u32 flags = 0;
+	int err = 0;
+
+	flags = READ_ONCE(pf->flags);
+	i40e_set_fec_in_flags(fec_cfg, &flags);
+
+	/* Get the current phy config */
+	memset(&abilities, 0, sizeof(abilities));
+	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
+					      NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	if (abilities.fec_cfg_curr_mod_ext_info != fec_cfg) {
+		struct i40e_aq_set_phy_config config;
+
+		memset(&config, 0, sizeof(config));
+		config.phy_type = abilities.phy_type;
+		config.abilities = abilities.abilities;
+		config.phy_type_ext = abilities.phy_type_ext;
+		config.link_speed = abilities.link_speed;
+		config.eee_capability = abilities.eee_capability;
+		config.eeer = abilities.eeer_val;
+		config.low_power_ctrl = abilities.d3_lpan;
+		config.fec_config = fec_cfg & I40E_AQ_PHY_FEC_CONFIG_MASK;
+		status = i40e_aq_set_phy_config(hw, &config, NULL);
+		if (status) {
+			netdev_info(netdev,
+				    "Set phy config failed, err %s aq_err %s\n",
+				    i40e_stat_str(hw, status),
+				    i40e_aq_str(hw, hw->aq.asq_last_status));
+			err = -EAGAIN;
+			goto done;
+		}
+		pf->flags = flags;
+		status = i40e_update_link_info(hw);
+		if (status)
+			/* debug level message only due to relation to the link
+			 * itself rather than to the FEC settings
+			 * (e.g. no physical connection etc.)
+			 */
+			netdev_dbg(netdev,
+				   "Updating link info failed with err %s aq_err %s\n",
+				   i40e_stat_str(hw, status),
+				   i40e_aq_str(hw, hw->aq.asq_last_status));
+	}
+
+done:
+	return err;
+}
+
+static int i40e_get_fec_param(struct net_device *netdev,
+			      struct ethtool_fecparam *fecparam)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_aq_get_phy_abilities_resp abilities;
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	i40e_status status = 0;
+	int err = 0;
+
+	/* Get the current phy config */
+	memset(&abilities, 0, sizeof(abilities));
+	status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities,
+					      NULL);
+	if (status) {
+		err = -EAGAIN;
+		goto done;
+	}
+
+	fecparam->fec = 0;
+	if (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_AUTO)
+		fecparam->fec |= ETHTOOL_FEC_AUTO;
+	if ((abilities.fec_cfg_curr_mod_ext_info &
+	     I40E_AQ_SET_FEC_REQUEST_RS) ||
+	    (abilities.fec_cfg_curr_mod_ext_info &
+	     I40E_AQ_SET_FEC_ABILITY_RS))
+		fecparam->fec |= ETHTOOL_FEC_RS;
+	if ((abilities.fec_cfg_curr_mod_ext_info &
+	     I40E_AQ_SET_FEC_REQUEST_KR) ||
+	    (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_ABILITY_KR))
+		fecparam->fec |= ETHTOOL_FEC_BASER;
+	if (abilities.fec_cfg_curr_mod_ext_info == 0)
+		fecparam->fec |= ETHTOOL_FEC_OFF;
+
+	if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA)
+		fecparam->active_fec = ETHTOOL_FEC_BASER;
+	else if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA)
+		fecparam->active_fec = ETHTOOL_FEC_RS;
+	else
+		fecparam->active_fec = ETHTOOL_FEC_OFF;
+done:
+	return err;
+}
+
+static int i40e_set_fec_param(struct net_device *netdev,
+			      struct ethtool_fecparam *fecparam)
+{
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+	struct i40e_pf *pf = np->vsi->back;
+	struct i40e_hw *hw = &pf->hw;
+	u8 fec_cfg = 0;
+	int err = 0;
+
+	if (hw->device_id != I40E_DEV_ID_25G_SFP28 &&
+	    hw->device_id != I40E_DEV_ID_25G_B) {
+		err = -EPERM;
+		goto done;
+	}
+
+	switch (fecparam->fec) {
+	case ETHTOOL_FEC_AUTO:
+		fec_cfg = I40E_AQ_SET_FEC_AUTO;
+		break;
+	case ETHTOOL_FEC_RS:
+		fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
+			     I40E_AQ_SET_FEC_ABILITY_RS);
+		break;
+	case ETHTOOL_FEC_BASER:
+		fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
+			     I40E_AQ_SET_FEC_ABILITY_KR);
+		break;
+	case ETHTOOL_FEC_OFF:
+	case ETHTOOL_FEC_NONE:
+		fec_cfg = 0;
+		break;
+	default:
+		dev_warn(&pf->pdev->dev, "Unsupported FEC mode: %d",
+			 fecparam->fec);
+		err = -EINVAL;
+		goto done;
+	}
+
+	err = i40e_set_fec_cfg(netdev, fec_cfg);
+
+done:
+	return err;
+}
+
 static int i40e_nway_reset(struct net_device *netdev)
 {
 	/* restart autonegotiation */
@@ -1335,6 +1531,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	i40e_status status;
 	u8 aq_failures;
 	int err = 0;
+	u32 is_an;
 
 	/* Changing the port's flow control is not supported if this isn't the
 	 * port's controlling PF
@@ -1347,15 +1544,14 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	if (vsi != pf->vsi[pf->lan_vsi])
 		return -EOPNOTSUPP;
 
-	if (pause->autoneg != ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ?
-	    AUTONEG_ENABLE : AUTONEG_DISABLE)) {
+	is_an = hw_link_info->an_info & I40E_AQ_AN_COMPLETED;
+	if (pause->autoneg != is_an) {
 		netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n");
 		return -EOPNOTSUPP;
 	}
 
 	/* If we have link and don't have autoneg */
-	if (!test_bit(__I40E_DOWN, pf->state) &&
-	    !(hw_link_info->an_info & I40E_AQ_AN_COMPLETED)) {
+	if (!test_bit(__I40E_DOWN, pf->state) && !is_an) {
 		/* Send message that it might not necessarily work*/
 		netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n");
 	}
@@ -1375,7 +1571,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 	else if (!pause->rx_pause && !pause->tx_pause)
 		hw->fc.requested_mode = I40E_FC_NONE;
 	else
-		 return -EINVAL;
+		return -EINVAL;
 
 	/* Tell the OS link is going down, the link will go back up when fw
 	 * says it is ready asynchronously
@@ -1406,7 +1602,7 @@ static int i40e_set_pauseparam(struct net_device *netdev,
 		err = -EAGAIN;
 	}
 
-	if (!test_bit(__I40E_DOWN, pf->state)) {
+	if (!test_bit(__I40E_DOWN, pf->state) && is_an) {
 		/* Give it a little more time to try to come back */
 		msleep(75);
 		if (!test_bit(__I40E_DOWN, pf->state))
@@ -2174,7 +2370,7 @@ static int i40e_get_ts_info(struct net_device *dev,
 	return 0;
 }
 
-static int i40e_link_test(struct net_device *netdev, u64 *data)
+static u64 i40e_link_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2197,7 +2393,7 @@ static int i40e_link_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
-static int i40e_reg_test(struct net_device *netdev, u64 *data)
+static u64 i40e_reg_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2208,7 +2404,7 @@ static int i40e_reg_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
-static int i40e_eeprom_test(struct net_device *netdev, u64 *data)
+static u64 i40e_eeprom_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2222,7 +2418,7 @@ static int i40e_eeprom_test(struct net_device *netdev, u64 *data)
 	return *data;
 }
 
-static int i40e_intr_test(struct net_device *netdev, u64 *data)
+static u64 i40e_intr_test(struct net_device *netdev, u64 *data)
 {
 	struct i40e_netdev_priv *np = netdev_priv(netdev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -2377,7 +2573,7 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 		return -EOPNOTSUPP;
 
 	/* only magic packet is supported */
-	if (wol->wolopts && (wol->wolopts != WAKE_MAGIC))
+	if (wol->wolopts & ~WAKE_MAGIC)
 		return -EOPNOTSUPP;
 
 	/* is this a new value? */
@@ -2438,10 +2634,10 @@ static int i40e_set_phys_id(struct net_device *netdev,
 	default:
 		break;
 	}
-		if (ret)
-			return -ENOENT;
-		else
-			return 0;
+	if (ret)
+		return -ENOENT;
+	else
+		return 0;
 }
 
 /* NOTE: i40e hardware uses a conversion factor of 2 for Interrupt
@@ -4659,20 +4855,30 @@ flags_complete:
 		return -EOPNOTSUPP;
 
 	/* If the driver detected FW LLDP was disabled on init, this flag could
-	 * be set, however we do not support _changing_ the flag if NPAR is
-	 * enabled or FW API version < 1.7.  There are situations where older
-	 * FW versions/NPAR enabled PFs could disable LLDP, however we _must_
-	 * not allow the user to enable/disable LLDP with this flag on
-	 * unsupported FW versions.
+	 * be set, however we do not support _changing_ the flag:
+	 * - on XL710 if NPAR is enabled or FW API version < 1.7
+	 * - on X722 with FW API version < 1.6
+	 * There are situations where older FW versions/NPAR enabled PFs could
+	 * disable LLDP, however we _must_ not allow the user to enable/disable
+	 * LLDP with this flag on unsupported FW versions.
 	 */
 	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
-		if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) {
+		if (!(pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) {
 			dev_warn(&pf->pdev->dev,
 				 "Device does not support changing FW LLDP\n");
 			return -EOPNOTSUPP;
 		}
 	}
 
+	if (((changed_flags & I40E_FLAG_RS_FEC) ||
+	     (changed_flags & I40E_FLAG_BASE_R_FEC)) &&
+	    pf->hw.device_id != I40E_DEV_ID_25G_SFP28 &&
+	    pf->hw.device_id != I40E_DEV_ID_25G_B) {
+		dev_warn(&pf->pdev->dev,
+			 "Device does not support changing FEC configuration\n");
+		return -EOPNOTSUPP;
+	}
+
 	/* Now that we've checked to ensure that the new flags are valid, load
 	 * them into place. Since we only modify flags either (a) during
 	 * initialization or (b) while holding the RTNL lock, we don't need
@@ -4711,6 +4917,24 @@ flags_complete:
 		}
 	}
 
+	if ((changed_flags & I40E_FLAG_RS_FEC) ||
+	    (changed_flags & I40E_FLAG_BASE_R_FEC)) {
+		u8 fec_cfg = 0;
+
+		if (pf->flags & I40E_FLAG_RS_FEC &&
+		    pf->flags & I40E_FLAG_BASE_R_FEC) {
+			fec_cfg = I40E_AQ_SET_FEC_AUTO;
+		} else if (pf->flags & I40E_FLAG_RS_FEC) {
+			fec_cfg = (I40E_AQ_SET_FEC_REQUEST_RS |
+				   I40E_AQ_SET_FEC_ABILITY_RS);
+		} else if (pf->flags & I40E_FLAG_BASE_R_FEC) {
+			fec_cfg = (I40E_AQ_SET_FEC_REQUEST_KR |
+				   I40E_AQ_SET_FEC_ABILITY_KR);
+		}
+		if (i40e_set_fec_cfg(dev, fec_cfg))
+			dev_warn(&pf->pdev->dev, "Cannot change FEC config\n");
+	}
+
 	if ((changed_flags & pf->flags &
 	     I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) &&
 	    (pf->flags & I40E_FLAG_MFP_ENABLED))
@@ -4945,6 +5169,8 @@ static const struct ethtool_ops i40e_ethtool_ops = {
 	.set_per_queue_coalesce	= i40e_set_per_queue_coalesce,
 	.get_link_ksettings	= i40e_get_link_ksettings,
 	.set_link_ksettings	= i40e_set_link_ksettings,
+	.get_fecparam = i40e_get_fec_param,
+	.set_fecparam = i40e_set_fec_param,
 };
 
 void i40e_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 0e5dc74b4ef2..b1c265012c8a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -26,8 +26,8 @@ static const char i40e_driver_string[] =
 #define DRV_KERN "-k"
 
 #define DRV_VERSION_MAJOR 2
-#define DRV_VERSION_MINOR 3
-#define DRV_VERSION_BUILD 2
+#define DRV_VERSION_MINOR 8
+#define DRV_VERSION_BUILD 10
 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \
 	     __stringify(DRV_VERSION_MINOR) "." \
 	     __stringify(DRV_VERSION_BUILD)    DRV_KERN
@@ -109,8 +109,8 @@ int i40e_allocate_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem,
 	struct i40e_pf *pf = (struct i40e_pf *)hw->back;
 
 	mem->size = ALIGN(size, alignment);
-	mem->va = dma_zalloc_coherent(&pf->pdev->dev, mem->size,
-				      &mem->pa, GFP_KERNEL);
+	mem->va = dma_alloc_coherent(&pf->pdev->dev, mem->size, &mem->pa,
+				     GFP_KERNEL);
 	if (!mem->va)
 		return -ENOMEM;
 
@@ -338,6 +338,10 @@ static void i40e_tx_timeout(struct net_device *netdev)
 		      (pf->tx_timeout_last_recovery + netdev->watchdog_timeo)))
 		return;   /* don't do any new action before the next timeout */
 
+	/* don't kick off another recovery if one is already pending */
+	if (test_and_set_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state))
+		return;
+
 	if (tx_ring) {
 		head = i40e_get_head(tx_ring);
 		/* Read interrupt register */
@@ -1493,8 +1497,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr)
 	bool found = false;
 	int bkt;
 
-	WARN(!spin_is_locked(&vsi->mac_filter_hash_lock),
-	     "Missing mac_filter_hash_lock\n");
+	lockdep_assert_held(&vsi->mac_filter_hash_lock);
 	hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) {
 		if (ether_addr_equal(macaddr, f->macaddr)) {
 			__i40e_del_filter(vsi, f);
@@ -3061,6 +3064,26 @@ static void i40e_config_xps_tx_ring(struct i40e_ring *ring)
 }
 
 /**
+ * i40e_xsk_umem - Retrieve the AF_XDP ZC if XDP and ZC is enabled
+ * @ring: The Tx or Rx ring
+ *
+ * Returns the UMEM or NULL.
+ **/
+static struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring)
+{
+	bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi);
+	int qid = ring->queue_index;
+
+	if (ring_is_xdp(ring))
+		qid -= ring->vsi->alloc_queue_pairs;
+
+	if (!xdp_on || !test_bit(qid, ring->vsi->af_xdp_zc_qps))
+		return NULL;
+
+	return xdp_get_umem_from_qid(ring->vsi->netdev, qid);
+}
+
+/**
  * i40e_configure_tx_ring - Configure a transmit ring context and rest
  * @ring: The Tx ring to configure
  *
@@ -3286,8 +3309,11 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 	     i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) :
 	     !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring));
 	if (!ok) {
+		/* Log this in case the user has forgotten to give the kernel
+		 * any buffers, even later in the application.
+		 */
 		dev_info(&vsi->back->pdev->dev,
-			 "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n",
+			 "Failed to allocate some buffers on %sRx ring %d (pf_q %d)\n",
 			 ring->xsk_umem ? "UMEM enabled " : "",
 			 ring->queue_index, pf_q);
 	}
@@ -3607,7 +3633,7 @@ static void i40e_configure_msi_and_legacy(struct i40e_vsi *vsi)
 		      (I40E_QUEUE_TYPE_TX
 		       << I40E_QINT_TQCTL_NEXTQ_TYPE_SHIFT);
 
-	       wr32(hw, I40E_QINT_TQCTL(nextqp), val);
+		wr32(hw, I40E_QINT_TQCTL(nextqp), val);
 	}
 
 	val = I40E_QINT_TQCTL_CAUSE_ENA_MASK		      |
@@ -6722,8 +6748,13 @@ void i40e_down(struct i40e_vsi *vsi)
 
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
 		i40e_clean_tx_ring(vsi->tx_rings[i]);
-		if (i40e_enabled_xdp_vsi(vsi))
+		if (i40e_enabled_xdp_vsi(vsi)) {
+			/* Make sure that in-progress ndo_xdp_xmit
+			 * calls are completed.
+			 */
+			synchronize_rcu();
 			i40e_clean_tx_ring(vsi->xdp_rings[i]);
+		}
 		i40e_clean_rx_ring(vsi->rx_rings[i]);
 	}
 
@@ -7166,11 +7197,13 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 				 struct tc_cls_flower_offload *f,
 				 struct i40e_cloud_filter *filter)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0;
 	struct i40e_pf *pf = vsi->back;
 	u8 field_flags = 0;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -7180,143 +7213,109 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
 		dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n",
-			f->dissector->used_keys);
+			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->key);
-
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 
-		if (mask->keyid != 0)
+		flow_rule_match_enc_keyid(rule, &match);
+		if (match.mask->keyid != 0)
 			field_flags |= I40E_CLOUD_FIELD_TEN_ID;
 
-		filter->tenant_id = be32_to_cpu(key->keyid);
+		filter->tenant_id = be32_to_cpu(match.key->keyid);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		n_proto_key = ntohs(key->n_proto);
-		n_proto_mask = ntohs(mask->n_proto);
+		flow_rule_match_basic(rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
 
 		if (n_proto_key == ETH_P_ALL) {
 			n_proto_key = 0;
 			n_proto_mask = 0;
 		}
 		filter->n_proto = n_proto_key & n_proto_mask;
-		filter->ip_proto = key->ip_proto;
+		filter->ip_proto = match.key->ip_proto;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
+		flow_rule_match_eth_addrs(rule, &match);
 
 		/* use is_broadcast and is_zero to check for all 0xf or 0 */
-		if (!is_zero_ether_addr(mask->dst)) {
-			if (is_broadcast_ether_addr(mask->dst)) {
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (is_broadcast_ether_addr(match.mask->dst)) {
 				field_flags |= I40E_CLOUD_FIELD_OMAC;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n",
-					mask->dst);
+					match.mask->dst);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (!is_zero_ether_addr(mask->src)) {
-			if (is_broadcast_ether_addr(mask->src)) {
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (is_broadcast_ether_addr(match.mask->src)) {
 				field_flags |= I40E_CLOUD_FIELD_IMAC;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n",
-					mask->src);
+					match.mask->src);
 				return I40E_ERR_CONFIG;
 			}
 		}
-		ether_addr_copy(filter->dst_mac, key->dst);
-		ether_addr_copy(filter->src_mac, key->src);
+		ether_addr_copy(filter->dst_mac, match.key->dst);
+		ether_addr_copy(filter->src_mac, match.key->src);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
-		if (mask->vlan_id) {
-			if (mask->vlan_id == VLAN_VID_MASK) {
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_id) {
+			if (match.mask->vlan_id == VLAN_VID_MASK) {
 				field_flags |= I40E_CLOUD_FIELD_IVLAN;
 
 			} else {
 				dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n",
-					mask->vlan_id);
+					match.mask->vlan_id);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		filter->vlan_id = cpu_to_be16(key->vlan_id);
+		filter->vlan_id = cpu_to_be16(match.key->vlan_id);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->mask);
-
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be32(0xffffffff)) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be32(0xffffffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n",
-					&mask->dst);
+					&match.mask->dst);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (mask->src) {
-			if (mask->src == cpu_to_be32(0xffffffff)) {
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be32(0xffffffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n",
-					&mask->src);
+					&match.mask->src);
 				return I40E_ERR_CONFIG;
 			}
 		}
@@ -7325,70 +7324,60 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
 			dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n");
 			return I40E_ERR_CONFIG;
 		}
-		filter->dst_ipv4 = key->dst;
-		filter->src_ipv4 = key->src;
+		filter->dst_ipv4 = match.key->dst;
+		filter->src_ipv4 = match.key->src;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->mask);
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
 
 		/* src and dest IPV6 address should not be LOOPBACK
 		 * (0:0:0:0:0:0:0:1), which can be represented as ::1
 		 */
-		if (ipv6_addr_loopback(&key->dst) ||
-		    ipv6_addr_loopback(&key->src)) {
+		if (ipv6_addr_loopback(&match.key->dst) ||
+		    ipv6_addr_loopback(&match.key->src)) {
 			dev_err(&pf->pdev->dev,
 				"Bad ipv6, addr is LOOPBACK\n");
 			return I40E_ERR_CONFIG;
 		}
-		if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+		if (!ipv6_addr_any(&match.mask->dst) ||
+		    !ipv6_addr_any(&match.mask->src))
 			field_flags |= I40E_CLOUD_FIELD_IIP;
 
-		memcpy(&filter->src_ipv6, &key->src.s6_addr32,
+		memcpy(&filter->src_ipv6, &match.key->src.s6_addr32,
 		       sizeof(filter->src_ipv6));
-		memcpy(&filter->dst_ipv6, &key->dst.s6_addr32,
+		memcpy(&filter->dst_ipv6, &match.key->dst.s6_addr32,
 		       sizeof(filter->dst_ipv6));
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
-		if (mask->src) {
-			if (mask->src == cpu_to_be16(0xffff)) {
+		flow_rule_match_ports(rule, &match);
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be16(0xffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n",
-					be16_to_cpu(mask->src));
+					be16_to_cpu(match.mask->src));
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be16(0xffff)) {
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be16(0xffff)) {
 				field_flags |= I40E_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n",
-					be16_to_cpu(mask->dst));
+					be16_to_cpu(match.mask->dst));
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		filter->dst_port = key->dst;
-		filter->src_port = key->src;
+		filter->dst_port = match.key->dst;
+		filter->src_port = match.key->src;
 
 		switch (filter->ip_proto) {
 		case IPPROTO_TCP:
@@ -8128,8 +8117,8 @@ static int i40e_handle_lldp_event(struct i40e_pf *pf,
 		i40e_service_event_schedule(pf);
 	} else {
 		i40e_pf_unquiesce_all_vsi(pf);
-	set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
-	set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
+		set_bit(__I40E_CLIENT_SERVICE_REQUESTED, pf->state);
+		set_bit(__I40E_CLIENT_L2_CHANGE, pf->state);
 	}
 
 exit:
@@ -9632,6 +9621,7 @@ end_core_reset:
 	clear_bit(__I40E_RESET_FAILED, pf->state);
 clear_recovery:
 	clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state);
+	clear_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state);
 }
 
 /**
@@ -10094,6 +10084,12 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	hash_init(vsi->mac_filter_hash);
 	vsi->irqs_ready = false;
 
+	if (type == I40E_VSI_MAIN) {
+		vsi->af_xdp_zc_qps = bitmap_zalloc(pf->num_lan_qps, GFP_KERNEL);
+		if (!vsi->af_xdp_zc_qps)
+			goto err_rings;
+	}
+
 	ret = i40e_set_num_rings_in_vsi(vsi);
 	if (ret)
 		goto err_rings;
@@ -10112,6 +10108,7 @@ static int i40e_vsi_mem_alloc(struct i40e_pf *pf, enum i40e_vsi_type type)
 	goto unlock_pf;
 
 err_rings:
+	bitmap_free(vsi->af_xdp_zc_qps);
 	pf->next_vsi = i - 1;
 	kfree(vsi);
 unlock_pf:
@@ -10192,6 +10189,7 @@ static int i40e_vsi_clear(struct i40e_vsi *vsi)
 	i40e_put_lump(pf->qp_pile, vsi->base_queue, vsi->idx);
 	i40e_put_lump(pf->irq_pile, vsi->base_vector, vsi->idx);
 
+	bitmap_free(vsi->af_xdp_zc_qps);
 	i40e_vsi_free_arrays(vsi, true);
 	i40e_clear_rss_config_user(vsi);
 
@@ -11038,6 +11036,7 @@ int i40e_reconfig_rss_queues(struct i40e_pf *pf, int queue_count)
 	if (!(pf->flags & I40E_FLAG_RSS_ENABLED))
 		return 0;
 
+	queue_count = min_t(int, queue_count, num_online_cpus());
 	new_rss_size = min_t(int, queue_count, pf->rss_size_max);
 
 	if (queue_count != vsi->num_queue_pairs) {
@@ -11332,16 +11331,15 @@ static int i40e_sw_init(struct i40e_pf *pf)
 		/* IWARP needs one extra vector for CQP just like MISC.*/
 		pf->num_iwarp_msix = (int)num_online_cpus() + 1;
 	}
-	/* Stopping the FW LLDP engine is only supported on the
-	 * XL710 with a FW ver >= 1.7.  Also, stopping FW LLDP
-	 * engine is not supported if NPAR is functioning on this
-	 * part
+	/* Stopping FW LLDP engine is supported on XL710 and X722
+	 * starting from FW versions determined in i40e_init_adminq.
+	 * Stopping the FW LLDP engine is not supported on XL710
+	 * if NPAR is functioning so unset this hw flag in this case.
 	 */
 	if (pf->hw.mac.type == I40E_MAC_XL710 &&
-	    !pf->hw.func_caps.npar_enable &&
-	    (pf->hw.aq.api_maj_ver > 1 ||
-	     (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6)))
-		pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP;
+	    pf->hw.func_caps.npar_enable &&
+	    (pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE))
+		pf->hw.flags &= ~I40E_HW_FLAG_FW_LLDP_STOPPABLE;
 
 #ifdef CONFIG_PCI_IOV
 	if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) {
@@ -11641,7 +11639,8 @@ static int i40e_get_phys_port_id(struct net_device *netdev,
 static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			    struct net_device *dev,
 			    const unsigned char *addr, u16 vid,
-			    u16 flags)
+			    u16 flags,
+			    struct netlink_ext_ack *extack)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_pf *pf = np->vsi->back;
@@ -11682,6 +11681,7 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
  * @dev: the netdev being configured
  * @nlh: RTNL message
  * @flags: bridge flags
+ * @extack: netlink extended ack
  *
  * Inserts a new hardware bridge if not already created and
  * enables the bridging mode requested (VEB or VEPA). If the
@@ -11694,7 +11694,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
  **/
 static int i40e_ndo_bridge_setlink(struct net_device *dev,
 				   struct nlmsghdr *nlh,
-				   u16 flags)
+				   u16 flags,
+				   struct netlink_ext_ack *extack)
 {
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	struct i40e_vsi *vsi = np->vsi;
@@ -11890,6 +11891,14 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi,
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	/* Kick start the NAPI context if there is an AF_XDP socket open
+	 * on that queue id. This so that receiving will start.
+	 */
+	if (need_reset && prog)
+		for (i = 0; i < vsi->num_queue_pairs; i++)
+			if (vsi->xdp_rings[i]->xsk_umem)
+				(void)i40e_xsk_async_xmit(vsi->netdev, i);
+
 	return 0;
 }
 
@@ -11950,8 +11959,13 @@ static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair)
 static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair)
 {
 	i40e_clean_tx_ring(vsi->tx_rings[queue_pair]);
-	if (i40e_enabled_xdp_vsi(vsi))
+	if (i40e_enabled_xdp_vsi(vsi)) {
+		/* Make sure that in-progress ndo_xdp_xmit calls are
+		 * completed.
+		 */
+		synchronize_rcu();
 		i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]);
+	}
 	i40e_clean_rx_ring(vsi->rx_rings[queue_pair]);
 }
 
@@ -12163,9 +12177,6 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_QUERY_PROG:
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
-	case XDP_QUERY_XSK_UMEM:
-		return i40e_xsk_umem_query(vsi, &xdp->xsk.umem,
-					   xdp->xsk.queue_id);
 	case XDP_SETUP_XSK_UMEM:
 		return i40e_xsk_umem_setup(vsi, xdp->xsk.umem,
 					   xdp->xsk.queue_id);
@@ -12334,6 +12345,9 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 	ether_addr_copy(netdev->dev_addr, mac_addr);
 	ether_addr_copy(netdev->perm_addr, mac_addr);
 
+	/* i40iw_net_event() reads 16 bytes from neigh->primary_key */
+	netdev->neigh_priv_len = sizeof(u32) * 4;
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 	netdev->priv_flags |= IFF_SUPP_NOFCS;
 	/* Setup netdev TC information */
@@ -13851,6 +13865,29 @@ static void i40e_get_platform_mac_addr(struct pci_dev *pdev, struct i40e_pf *pf)
 }
 
 /**
+ * i40e_set_fec_in_flags - helper function for setting FEC options in flags
+ * @fec_cfg: FEC option to set in flags
+ * @flags: ptr to flags in which we set FEC option
+ **/
+void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags)
+{
+	if (fec_cfg & I40E_AQ_SET_FEC_AUTO)
+		*flags |= I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC;
+	if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_RS) ||
+	    (fec_cfg & I40E_AQ_SET_FEC_ABILITY_RS)) {
+		*flags |= I40E_FLAG_RS_FEC;
+		*flags &= ~I40E_FLAG_BASE_R_FEC;
+	}
+	if ((fec_cfg & I40E_AQ_SET_FEC_REQUEST_KR) ||
+	    (fec_cfg & I40E_AQ_SET_FEC_ABILITY_KR)) {
+		*flags |= I40E_FLAG_BASE_R_FEC;
+		*flags &= ~I40E_FLAG_RS_FEC;
+	}
+	if (fec_cfg == 0)
+		*flags &= ~(I40E_FLAG_RS_FEC | I40E_FLAG_BASE_R_FEC);
+}
+
+/**
  * i40e_probe - Device initialization routine
  * @pdev: PCI device information struct
  * @ent: entry in i40e_pci_tbl
@@ -14302,23 +14339,23 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 		switch (hw->bus.speed) {
 		case i40e_bus_speed_8000:
-			strncpy(speed, "8.0", PCI_SPEED_SIZE); break;
+			strlcpy(speed, "8.0", PCI_SPEED_SIZE); break;
 		case i40e_bus_speed_5000:
-			strncpy(speed, "5.0", PCI_SPEED_SIZE); break;
+			strlcpy(speed, "5.0", PCI_SPEED_SIZE); break;
 		case i40e_bus_speed_2500:
-			strncpy(speed, "2.5", PCI_SPEED_SIZE); break;
+			strlcpy(speed, "2.5", PCI_SPEED_SIZE); break;
 		default:
 			break;
 		}
 		switch (hw->bus.width) {
 		case i40e_bus_width_pcie_x8:
-			strncpy(width, "8", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "8", PCI_WIDTH_SIZE); break;
 		case i40e_bus_width_pcie_x4:
-			strncpy(width, "4", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "4", PCI_WIDTH_SIZE); break;
 		case i40e_bus_width_pcie_x2:
-			strncpy(width, "2", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "2", PCI_WIDTH_SIZE); break;
 		case i40e_bus_width_pcie_x1:
-			strncpy(width, "1", PCI_WIDTH_SIZE); break;
+			strlcpy(width, "1", PCI_WIDTH_SIZE); break;
 		default:
 			break;
 		}
@@ -14341,6 +14378,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 			i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
 	pf->hw.phy.link_info.requested_speeds = abilities.link_speed;
 
+	/* set the FEC config due to the board capabilities */
+	i40e_set_fec_in_flags(abilities.fec_cfg_curr_mod_ext_info, &pf->flags);
+
 	/* get the supported phy types from the fw */
 	err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, NULL);
 	if (err)
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
index 1199f0502d6d..31575c0bb884 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c
@@ -28,19 +28,23 @@
  * i40e_ptp_read - Read the PHC time from the device
  * @pf: Board private structure
  * @ts: timespec structure to hold the current time value
+ * @sts: structure to hold the system time before and after reading the PHC
  *
  * This function reads the PRTTSYN_TIME registers and stores them in a
  * timespec. However, since the registers are 64 bits of nanoseconds, we must
  * convert the result to a timespec before we can return.
  **/
-static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts)
+static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts,
+			  struct ptp_system_timestamp *sts)
 {
 	struct i40e_hw *hw = &pf->hw;
 	u32 hi, lo;
 	u64 ns;
 
 	/* The timer latches on the lowest register read. */
+	ptp_read_system_prets(sts);
 	lo = rd32(hw, I40E_PRTTSYN_TIME_L);
+	ptp_read_system_postts(sts);
 	hi = rd32(hw, I40E_PRTTSYN_TIME_H);
 
 	ns = (((u64)hi) << 32) | lo;
@@ -142,12 +146,13 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 {
 	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
-	struct timespec64 now;
+	struct timespec64 now, then;
 
+	then = ns_to_timespec64(delta);
 	mutex_lock(&pf->tmreg_lock);
 
-	i40e_ptp_read(pf, &now);
-	timespec64_add_ns(&now, delta);
+	i40e_ptp_read(pf, &now, NULL);
+	now = timespec64_add(now, then);
 	i40e_ptp_write(pf, (const struct timespec64 *)&now);
 
 	mutex_unlock(&pf->tmreg_lock);
@@ -156,19 +161,21 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 }
 
 /**
- * i40e_ptp_gettime - Get the time of the PHC
+ * i40e_ptp_gettimex - Get the time of the PHC
  * @ptp: The PTP clock structure
  * @ts: timespec structure to hold the current time value
+ * @sts: structure to hold the system time before and after reading the PHC
  *
  * Read the device clock and return the correct value on ns, after converting it
  * into a timespec struct.
  **/
-static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int i40e_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			     struct ptp_system_timestamp *sts)
 {
 	struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps);
 
 	mutex_lock(&pf->tmreg_lock);
-	i40e_ptp_read(pf, ts);
+	i40e_ptp_read(pf, ts, sts);
 	mutex_unlock(&pf->tmreg_lock);
 
 	return 0;
@@ -694,7 +701,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 	if (!IS_ERR_OR_NULL(pf->ptp_clock))
 		return 0;
 
-	strncpy(pf->ptp_caps.name, i40e_driver_name,
+	strlcpy(pf->ptp_caps.name, i40e_driver_name,
 		sizeof(pf->ptp_caps.name) - 1);
 	pf->ptp_caps.owner = THIS_MODULE;
 	pf->ptp_caps.max_adj = 999999999;
@@ -702,7 +709,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf)
 	pf->ptp_caps.pps = 0;
 	pf->ptp_caps.adjfreq = i40e_ptp_adjfreq;
 	pf->ptp_caps.adjtime = i40e_ptp_adjtime;
-	pf->ptp_caps.gettime64 = i40e_ptp_gettime;
+	pf->ptp_caps.gettimex64 = i40e_ptp_gettimex;
 	pf->ptp_caps.settime64 = i40e_ptp_settime;
 	pf->ptp_caps.enable = i40e_ptp_feature_enable;
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index d0a95424ce58..6c97667d20ef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2648,10 +2648,11 @@ tx_only:
 	if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR)
 		q_vector->arm_wb_state = false;
 
-	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete_done(napi, work_done);
-
-	i40e_update_enable_itr(vsi, q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		i40e_update_enable_itr(vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
@@ -3454,6 +3455,8 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.
 	 *
@@ -3507,6 +3510,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 	u16 i = xdp_ring->next_to_use;
 	struct i40e_tx_buffer *tx_bi;
 	struct i40e_tx_desc *tx_desc;
+	void *data = xdpf->data;
 	u32 size = xdpf->len;
 	dma_addr_t dma;
 
@@ -3514,8 +3518,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf,
 		xdp_ring->tx_stats.tx_busy++;
 		return I40E_XDP_CONSUMED;
 	}
-
-	dma = dma_map_single(xdp_ring->dev, xdpf->data, size, DMA_TO_DEVICE);
+	dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(xdp_ring->dev, dma))
 		return I40E_XDP_CONSUMED;
 
@@ -3633,8 +3636,6 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb,
 	if (tsyn)
 		tx_flags |= I40E_TX_FLAGS_TSYN;
 
-	skb_tx_timestamp(skb);
-
 	/* always enable CRC insertion offload */
 	td_cmd |= I40E_TX_DESC_CMD_ICRC;
 
@@ -3708,6 +3709,7 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	struct i40e_netdev_priv *np = netdev_priv(dev);
 	unsigned int queue_index = smp_processor_id();
 	struct i40e_vsi *vsi = np->vsi;
+	struct i40e_pf *pf = vsi->back;
 	struct i40e_ring *xdp_ring;
 	int drops = 0;
 	int i;
@@ -3715,7 +3717,8 @@ int i40e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	if (test_bit(__I40E_VSI_DOWN, vsi->state))
 		return -ENETDOWN;
 
-	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs)
+	if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs ||
+	    test_bit(__I40E_CONFIG_BUSY, pf->state))
 		return -ENXIO;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 7df969c59855..2781ab91ca82 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -615,6 +615,7 @@ struct i40e_hw {
 #define I40E_HW_FLAG_802_1AD_CAPABLE        BIT_ULL(1)
 #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
 #define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3)
+#define I40E_HW_FLAG_FW_LLDP_STOPPABLE      BIT_ULL(4)
 	u64 flags;
 
 	/* Used in set switch config AQ command */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index ac5698ed0b11..831d52bc3c9a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -1112,7 +1112,8 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf,
 	if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi)
 		return I40E_ERR_PARAM;
 
-	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) {
+	if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) &&
+	    (allmulti || alluni)) {
 		dev_err(&pf->pdev->dev,
 			"Unprivileged VF %d is attempting to configure promiscuous mode\n",
 			vf->vf_id);
@@ -1675,13 +1676,20 @@ err_out:
 int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 {
 	struct i40e_pf *pf = pci_get_drvdata(pdev);
+	int ret = 0;
+
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
 
 	if (num_vfs) {
 		if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) {
 			pf->flags |= I40E_FLAG_VEB_MODE_ENABLED;
 			i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 		}
-		return i40e_pci_sriov_enable(pdev, num_vfs);
+		ret = i40e_pci_sriov_enable(pdev, num_vfs);
+		goto sriov_configure_out;
 	}
 
 	if (!pci_vfs_assigned(pf->pdev)) {
@@ -1690,9 +1698,12 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 		i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG);
 	} else {
 		dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto sriov_configure_out;
 	}
-	return 0;
+sriov_configure_out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
+	return ret;
 }
 
 /***********************virtual channel routines******************/
@@ -2058,6 +2069,11 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
+	if (qci->num_queue_pairs > I40E_MAX_VF_QUEUES) {
+		aq_ret = I40E_ERR_PARAM;
+		goto error_param;
+	}
+
 	for (i = 0; i < qci->num_queue_pairs; i++) {
 		qpi = &qci->qpair[i];
 
@@ -3373,8 +3389,8 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg)
 		dev_info(&pf->pdev->dev,
 			 "VF %d: Invalid input/s, can't apply cloud filter\n",
 			 vf->vf_id);
-			aq_ret = I40E_ERR_PARAM;
-			goto err;
+		aq_ret = I40E_ERR_PARAM;
+		goto err;
 	}
 
 	cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL);
@@ -3645,7 +3661,7 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 	int ret;
 
 	pf->vf_aq_requests++;
-	if (local_vf_id >= pf->num_alloc_vfs)
+	if (local_vf_id < 0 || local_vf_id >= pf->num_alloc_vfs)
 		return -EINVAL;
 	vf = &(pf->vf[local_vf_id]);
 
@@ -3893,6 +3909,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 		goto error_param;
 	}
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	if (is_multicast_ether_addr(mac)) {
 		dev_err(&pf->pdev->dev,
 			"Invalid Ethernet address %pM for VF %d\n", mac, vf_id);
@@ -3941,6 +3962,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac)
 	dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n");
 
 error_param:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -3992,6 +4014,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -4107,6 +4134,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	ret = 0;
 
 error_pvid:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4128,6 +4156,11 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -4154,6 +4187,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate,
 
 	vf->tx_rate = max_tx_rate;
 error:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4174,6 +4208,11 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	ret = i40e_validate_vf(pf, vf_id);
 	if (ret)
@@ -4209,6 +4248,7 @@ int i40e_ndo_get_vf_config(struct net_device *netdev,
 	ret = 0;
 
 error_param:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4230,6 +4270,11 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 	int abs_vf_id;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
 		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
@@ -4273,6 +4318,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link)
 			       0, (u8 *)&pfe, sizeof(pfe), NULL);
 
 error_out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4294,6 +4340,11 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable)
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
 		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
@@ -4327,6 +4378,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable)
 		ret = -EIO;
 	}
 out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
 
@@ -4345,15 +4397,22 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 	struct i40e_vf *vf;
 	int ret = 0;
 
+	if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) {
+		dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n");
+		return -EAGAIN;
+	}
+
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
 		dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id);
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	if (pf->flags & I40E_FLAG_MFP_ENABLED) {
 		dev_err(&pf->pdev->dev, "Trusted VF not supported in MFP mode.\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto out;
 	}
 
 	vf = &pf->vf[vf_id];
@@ -4376,5 +4435,6 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting)
 	}
 
 out:
+	clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state);
 	return ret;
 }
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
index bf67d62e2b5f..f9621026beef 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h
@@ -13,9 +13,9 @@
 #define I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED	3
 #define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED	10
 
-#define I40E_VLAN_PRIORITY_SHIFT	12
+#define I40E_VLAN_PRIORITY_SHIFT	13
 #define I40E_VLAN_MASK			0xFFF
-#define I40E_PRIORITY_MASK		0x7000
+#define I40E_PRIORITY_MASK		0xE000
 
 /* Various queue ctrls */
 enum i40e_queue_ctrl {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 870cf654e436..1b17486543ac 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -10,69 +10,6 @@
 #include "i40e_xsk.h"
 
 /**
- * i40e_alloc_xsk_umems - Allocate an array to store per ring UMEMs
- * @vsi: Current VSI
- *
- * Returns 0 on success, <0 on failure
- **/
-static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi)
-{
-	if (vsi->xsk_umems)
-		return 0;
-
-	vsi->num_xsk_umems_used = 0;
-	vsi->num_xsk_umems = vsi->alloc_queue_pairs;
-	vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems),
-				 GFP_KERNEL);
-	if (!vsi->xsk_umems) {
-		vsi->num_xsk_umems = 0;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-/**
- * i40e_add_xsk_umem - Store a UMEM for a certain ring/qid
- * @vsi: Current VSI
- * @umem: UMEM to store
- * @qid: Ring/qid to associate with the UMEM
- *
- * Returns 0 on success, <0 on failure
- **/
-static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem,
-			     u16 qid)
-{
-	int err;
-
-	err = i40e_alloc_xsk_umems(vsi);
-	if (err)
-		return err;
-
-	vsi->xsk_umems[qid] = umem;
-	vsi->num_xsk_umems_used++;
-
-	return 0;
-}
-
-/**
- * i40e_remove_xsk_umem - Remove a UMEM for a certain ring/qid
- * @vsi: Current VSI
- * @qid: Ring/qid associated with the UMEM
- **/
-static void i40e_remove_xsk_umem(struct i40e_vsi *vsi, u16 qid)
-{
-	vsi->xsk_umems[qid] = NULL;
-	vsi->num_xsk_umems_used--;
-
-	if (vsi->num_xsk_umems == 0) {
-		kfree(vsi->xsk_umems);
-		vsi->xsk_umems = NULL;
-		vsi->num_xsk_umems = 0;
-	}
-}
-
-/**
  * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev
  * @vsi: Current VSI
  * @umem: UMEM to DMA map
@@ -140,6 +77,7 @@ static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem)
 static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 				u16 qid)
 {
+	struct net_device *netdev = vsi->netdev;
 	struct xdp_umem_fq_reuse *reuseq;
 	bool if_running;
 	int err;
@@ -150,12 +88,9 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	if (qid >= vsi->num_queue_pairs)
 		return -EINVAL;
 
-	if (vsi->xsk_umems) {
-		if (qid >= vsi->num_xsk_umems)
-			return -EINVAL;
-		if (vsi->xsk_umems[qid])
-			return -EBUSY;
-	}
+	if (qid >= netdev->real_num_rx_queues ||
+	    qid >= netdev->real_num_tx_queues)
+		return -EINVAL;
 
 	reuseq = xsk_reuseq_prepare(vsi->rx_rings[0]->count);
 	if (!reuseq)
@@ -167,22 +102,23 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
 	if (err)
 		return err;
 
+	set_bit(qid, vsi->af_xdp_zc_qps);
+
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
 
 	if (if_running) {
 		err = i40e_queue_pair_disable(vsi, qid);
 		if (err)
 			return err;
-	}
 
-	err = i40e_add_xsk_umem(vsi, umem, qid);
-	if (err)
-		return err;
-
-	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
+
+		/* Kick start the NAPI context so that receiving will start */
+		err = i40e_xsk_async_xmit(vsi->netdev, qid);
+		if (err)
+			return err;
 	}
 
 	return 0;
@@ -197,11 +133,13 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem,
  **/
 static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 {
+	struct net_device *netdev = vsi->netdev;
+	struct xdp_umem *umem;
 	bool if_running;
 	int err;
 
-	if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems ||
-	    !vsi->xsk_umems[qid])
+	umem = xdp_get_umem_from_qid(netdev, qid);
+	if (!umem)
 		return -EINVAL;
 
 	if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi);
@@ -212,8 +150,8 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 			return err;
 	}
 
-	i40e_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]);
-	i40e_remove_xsk_umem(vsi, qid);
+	clear_bit(qid, vsi->af_xdp_zc_qps);
+	i40e_xsk_umem_dma_unmap(vsi, umem);
 
 	if (if_running) {
 		err = i40e_queue_pair_enable(vsi, qid);
@@ -225,36 +163,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid)
 }
 
 /**
- * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM
- * @vsi: Current VSI
- * @umem: UMEM associated to the ring, if any
- * @qid: Rx ring to associate UMEM to
- *
- * This function will store, if any, the UMEM associated to certain ring.
- *
- * Returns 0 on success, <0 on failure
- **/
-int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
-			u16 qid)
-{
-	if (vsi->type != I40E_VSI_MAIN)
-		return -EINVAL;
-
-	if (qid >= vsi->num_queue_pairs)
-		return -EINVAL;
-
-	if (vsi->xsk_umems) {
-		if (qid >= vsi->num_xsk_umems)
-			return -EINVAL;
-		*umem = vsi->xsk_umems[qid];
-		return 0;
-	}
-
-	*umem = NULL;
-	return 0;
-}
-
-/**
  * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid
  * @vsi: Current VSI
  * @umem: UMEM to enable/associate to a ring, or NULL to disable
@@ -945,13 +853,11 @@ void i40e_xsk_clean_tx_ring(struct i40e_ring *tx_ring)
  **/
 bool i40e_xsk_any_rx_ring_enabled(struct i40e_vsi *vsi)
 {
+	struct net_device *netdev = vsi->netdev;
 	int i;
 
-	if (!vsi->xsk_umems)
-		return false;
-
 	for (i = 0; i < vsi->num_queue_pairs; i++) {
-		if (vsi->xsk_umems[i])
+		if (xdp_get_umem_from_qid(netdev, i))
 			return true;
 	}
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index 9038c5d5cf08..8cc0a2e7d9a2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -10,8 +10,6 @@ struct zero_copy_allocator;
 
 int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair);
 int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair);
-int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem,
-			u16 qid);
 int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem,
 			u16 qid);
 void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 9f2b7b7adf6b..4569d69a2b55 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2439,6 +2439,8 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 				 struct tc_cls_flower_offload *f,
 				 struct iavf_cloud_filter *filter)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0;
 	u16 n_proto_key = 0;
 	u8 field_flags = 0;
@@ -2447,7 +2449,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 	int i = 0;
 	struct virtchnl_filter *vf = &filter->f;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -2457,32 +2459,24 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) {
 		dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n",
-			f->dissector->used_keys);
+			dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 
-		if (mask->keyid != 0)
+		flow_rule_match_enc_keyid(rule, &match);
+		if (match.mask->keyid != 0)
 			field_flags |= IAVF_CLOUD_FIELD_TEN_ID;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-		n_proto_key = ntohs(key->n_proto);
-		n_proto_mask = ntohs(mask->n_proto);
+		flow_rule_match_basic(rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
 
 		if (n_proto_key == ETH_P_ALL) {
 			n_proto_key = 0;
@@ -2496,122 +2490,103 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 			vf->flow_type = VIRTCHNL_TCP_V6_FLOW;
 		}
 
-		if (key->ip_proto != IPPROTO_TCP) {
+		if (match.key->ip_proto != IPPROTO_TCP) {
 			dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n");
 			return -EINVAL;
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
+
+		flow_rule_match_eth_addrs(rule, &match);
 
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
 		/* use is_broadcast and is_zero to check for all 0xf or 0 */
-		if (!is_zero_ether_addr(mask->dst)) {
-			if (is_broadcast_ether_addr(mask->dst)) {
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (is_broadcast_ether_addr(match.mask->dst)) {
 				field_flags |= IAVF_CLOUD_FIELD_OMAC;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n",
-					mask->dst);
+					match.mask->dst);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (!is_zero_ether_addr(mask->src)) {
-			if (is_broadcast_ether_addr(mask->src)) {
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (is_broadcast_ether_addr(match.mask->src)) {
 				field_flags |= IAVF_CLOUD_FIELD_IMAC;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n",
-					mask->src);
+					match.mask->src);
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (!is_zero_ether_addr(key->dst))
-			if (is_valid_ether_addr(key->dst) ||
-			    is_multicast_ether_addr(key->dst)) {
+		if (!is_zero_ether_addr(match.key->dst))
+			if (is_valid_ether_addr(match.key->dst) ||
+			    is_multicast_ether_addr(match.key->dst)) {
 				/* set the mask if a valid dst_mac address */
 				for (i = 0; i < ETH_ALEN; i++)
 					vf->mask.tcp_spec.dst_mac[i] |= 0xff;
 				ether_addr_copy(vf->data.tcp_spec.dst_mac,
-						key->dst);
+						match.key->dst);
 			}
 
-		if (!is_zero_ether_addr(key->src))
-			if (is_valid_ether_addr(key->src) ||
-			    is_multicast_ether_addr(key->src)) {
+		if (!is_zero_ether_addr(match.key->src))
+			if (is_valid_ether_addr(match.key->src) ||
+			    is_multicast_ether_addr(match.key->src)) {
 				/* set the mask if a valid dst_mac address */
 				for (i = 0; i < ETH_ALEN; i++)
 					vf->mask.tcp_spec.src_mac[i] |= 0xff;
 				ether_addr_copy(vf->data.tcp_spec.src_mac,
-						key->src);
+						match.key->src);
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
-		if (mask->vlan_id) {
-			if (mask->vlan_id == VLAN_VID_MASK) {
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_id) {
+			if (match.mask->vlan_id == VLAN_VID_MASK) {
 				field_flags |= IAVF_CLOUD_FIELD_IVLAN;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n",
-					mask->vlan_id);
+					match.mask->vlan_id);
 				return I40E_ERR_CONFIG;
 			}
 		}
 		vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff);
-		vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id);
+		vf->data.tcp_spec.vlan_id = cpu_to_be16(match.key->vlan_id);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->mask);
-
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be32(0xffffffff)) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_ipv4_addrs(rule, &match);
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be32(0xffffffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n",
-					be32_to_cpu(mask->dst));
+					be32_to_cpu(match.mask->dst));
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (mask->src) {
-			if (mask->src == cpu_to_be32(0xffffffff)) {
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be32(0xffffffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n",
-					be32_to_cpu(mask->dst));
+					be32_to_cpu(match.mask->dst));
 				return I40E_ERR_CONFIG;
 			}
 		}
@@ -2620,28 +2595,23 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 			dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n");
 			return I40E_ERR_CONFIG;
 		}
-		if (key->dst) {
+		if (match.key->dst) {
 			vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff);
-			vf->data.tcp_spec.dst_ip[0] = key->dst;
+			vf->data.tcp_spec.dst_ip[0] = match.key->dst;
 		}
-		if (key->src) {
+		if (match.key->src) {
 			vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff);
-			vf->data.tcp_spec.src_ip[0] = key->src;
+			vf->data.tcp_spec.src_ip[0] = match.key->src;
 		}
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->mask);
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
 
 		/* validate mask, make sure it is not IPV6_ADDR_ANY */
-		if (ipv6_addr_any(&mask->dst)) {
+		if (ipv6_addr_any(&match.mask->dst)) {
 			dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n",
 				IPV6_ADDR_ANY);
 			return I40E_ERR_CONFIG;
@@ -2650,61 +2620,56 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
 		/* src and dest IPv6 address should not be LOOPBACK
 		 * (0:0:0:0:0:0:0:1) which can be represented as ::1
 		 */
-		if (ipv6_addr_loopback(&key->dst) ||
-		    ipv6_addr_loopback(&key->src)) {
+		if (ipv6_addr_loopback(&match.key->dst) ||
+		    ipv6_addr_loopback(&match.key->src)) {
 			dev_err(&adapter->pdev->dev,
 				"ipv6 addr should not be loopback\n");
 			return I40E_ERR_CONFIG;
 		}
-		if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src))
+		if (!ipv6_addr_any(&match.mask->dst) ||
+		    !ipv6_addr_any(&match.mask->src))
 			field_flags |= IAVF_CLOUD_FIELD_IIP;
 
 		for (i = 0; i < 4; i++)
 			vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff);
-		memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32,
+		memcpy(&vf->data.tcp_spec.dst_ip, &match.key->dst.s6_addr32,
 		       sizeof(vf->data.tcp_spec.dst_ip));
 		for (i = 0; i < 4; i++)
 			vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff);
-		memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32,
+		memcpy(&vf->data.tcp_spec.src_ip, &match.key->src.s6_addr32,
 		       sizeof(vf->data.tcp_spec.src_ip));
 	}
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->mask);
-
-		if (mask->src) {
-			if (mask->src == cpu_to_be16(0xffff)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
+		if (match.mask->src) {
+			if (match.mask->src == cpu_to_be16(0xffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad src port mask %u\n",
-					be16_to_cpu(mask->src));
+					be16_to_cpu(match.mask->src));
 				return I40E_ERR_CONFIG;
 			}
 		}
 
-		if (mask->dst) {
-			if (mask->dst == cpu_to_be16(0xffff)) {
+		if (match.mask->dst) {
+			if (match.mask->dst == cpu_to_be16(0xffff)) {
 				field_flags |= IAVF_CLOUD_FIELD_IIP;
 			} else {
 				dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n",
-					be16_to_cpu(mask->dst));
+					be16_to_cpu(match.mask->dst));
 				return I40E_ERR_CONFIG;
 			}
 		}
-		if (key->dst) {
+		if (match.key->dst) {
 			vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff);
-			vf->data.tcp_spec.dst_port = key->dst;
+			vf->data.tcp_spec.dst_port = match.key->dst;
 		}
 
-		if (key->src) {
+		if (match.key->src) {
 			vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff);
-			vf->data.tcp_spec.src_port = key->src;
+			vf->data.tcp_spec.src_port = match.key->src;
 		}
 	}
 	vf->field_flags = field_flags;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index fb9bfad96daf..9b4d7cec2e18 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -1761,10 +1761,11 @@ tx_only:
 	if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR)
 		q_vector->arm_wb_state = false;
 
-	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete_done(napi, work_done);
-
-	iavf_update_enable_itr(vsi, q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		iavf_update_enable_itr(vsi, q_vector);
 
 	return min(work_done, budget - 1);
 }
@@ -2343,6 +2344,8 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb,
 	tx_desc->cmd_type_offset_bsz =
 			build_ctob(td_cmd, td_offset, size, td_tag);
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.
 	 *
@@ -2461,8 +2464,6 @@ static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb,
 	if (tso < 0)
 		goto out_drop;
 
-	skb_tx_timestamp(skb);
-
 	/* always enable CRC insertion offload */
 	td_cmd |= IAVF_TX_DESC_CMD_ICRC;
 
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index b8548370f1c7..89440775aea1 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -26,6 +26,7 @@
 #include <linux/bitmap.h>
 #include <linux/log2.h>
 #include <linux/ip.h>
+#include <linux/sctp.h>
 #include <linux/ipv6.h>
 #include <linux/if_bridge.h>
 #include <linux/avf/virtchnl.h>
@@ -52,7 +53,6 @@ extern const char ice_drv_ver[];
 #define ICE_MBXQ_LEN		64
 #define ICE_MIN_MSIX		2
 #define ICE_NO_VSI		0xffff
-#define ICE_MAX_VSI_ALLOC	130
 #define ICE_MAX_TXQS		2048
 #define ICE_MAX_RXQS		2048
 #define ICE_VSI_MAP_CONTIG	0
@@ -83,7 +83,7 @@ extern const char ice_drv_ver[];
 #define ICE_DFLT_NETIF_M (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
 
 #define ICE_MAX_MTU	(ICE_AQ_SET_MAC_FRAME_SIZE_MAX - \
-			 ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN)
+			(ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)))
 
 #define ICE_UP_TABLE_TRANSLATE(val, i) \
 		(((val) << ICE_AQ_VSI_UP_TABLE_UP##i##_S) & \
@@ -97,23 +97,28 @@ extern const char ice_drv_ver[];
 #define ice_for_each_vsi(pf, i) \
 	for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++)
 
-/* Macros for each tx/rx ring in a VSI */
+/* Macros for each Tx/Rx ring in a VSI */
 #define ice_for_each_txq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->num_txq; (i)++)
 
 #define ice_for_each_rxq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->num_rxq; (i)++)
 
-/* Macros for each allocated tx/rx ring whether used or not in a VSI */
+/* Macros for each allocated Tx/Rx ring whether used or not in a VSI */
 #define ice_for_each_alloc_txq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->alloc_txq; (i)++)
 
 #define ice_for_each_alloc_rxq(vsi, i) \
 	for ((i) = 0; (i) < (vsi)->alloc_rxq; (i)++)
 
+#define ice_for_each_q_vector(vsi, i) \
+	for ((i) = 0; (i) < (vsi)->num_q_vectors; (i)++)
+
 struct ice_tc_info {
 	u16 qoffset;
-	u16 qcount;
+	u16 qcount_tx;
+	u16 qcount_rx;
+	u8 netdev_tc;
 };
 
 struct ice_tc_cfg {
@@ -128,6 +133,17 @@ struct ice_res_tracker {
 	u16 list[1];
 };
 
+struct ice_qs_cfg {
+	struct mutex *qs_mutex;  /* will be assgined to &pf->avail_q_mutex */
+	unsigned long *pf_map;
+	unsigned long pf_map_size;
+	unsigned int q_count;
+	unsigned int scatter_count;
+	u16 *vsi_map;
+	u16 vsi_map_offset;
+	u8 mapping_mode;
+};
+
 struct ice_sw {
 	struct ice_pf *pf;
 	u16 sw_id;		/* switch ID for this switch */
@@ -149,10 +165,10 @@ enum ice_state {
 	__ICE_RESET_FAILED,		/* set by reset/rebuild */
 	/* When checking for the PF to be in a nominal operating state, the
 	 * bits that are grouped at the beginning of the list need to be
-	 * checked.  Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will
-	 * be checked.  If you need to add a bit into consideration for nominal
+	 * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will
+	 * be checked. If you need to add a bit into consideration for nominal
 	 * operating state, it must be added before
-	 * __ICE_STATE_NOMINAL_CHECK_BITS.  Do not move this entry's position
+	 * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position
 	 * without appropriate consideration.
 	 */
 	__ICE_STATE_NOMINAL_CHECK_BITS,
@@ -182,8 +198,8 @@ struct ice_vsi {
 	struct ice_sw *vsw;		 /* switch this VSI is on */
 	struct ice_pf *back;		 /* back pointer to PF */
 	struct ice_port_info *port_info; /* back pointer to port_info */
-	struct ice_ring **rx_rings;	 /* rx ring array */
-	struct ice_ring **tx_rings;	 /* tx ring array */
+	struct ice_ring **rx_rings;	 /* Rx ring array */
+	struct ice_ring **tx_rings;	 /* Tx ring array */
 	struct ice_q_vector **q_vectors; /* q_vector array */
 
 	irqreturn_t (*irq_handler)(int irq, void *data);
@@ -200,8 +216,8 @@ struct ice_vsi {
 	int sw_base_vector;		/* Irq base for OS reserved vectors */
 	int hw_base_vector;		/* HW (absolute) index of a vector */
 	enum ice_vsi_type type;
-	u16 vsi_num;			 /* HW (absolute) index of this VSI */
-	u16 idx;			 /* software index in pf->vsi[] */
+	u16 vsi_num;			/* HW (absolute) index of this VSI */
+	u16 idx;			/* software index in pf->vsi[] */
 
 	/* Interrupt thresholds */
 	u16 work_lmt;
@@ -254,8 +270,8 @@ struct ice_q_vector {
 	struct ice_ring_container tx;
 	struct irq_affinity_notify affinity_notify;
 	u16 v_idx;			/* index in the vsi->q_vector array. */
-	u8 num_ring_tx;			/* total number of tx rings in vector */
-	u8 num_ring_rx;			/* total number of rx rings in vector */
+	u8 num_ring_tx;			/* total number of Tx rings in vector */
+	u8 num_ring_rx;			/* total number of Rx rings in vector */
 	char name[ICE_INT_NAME_STR_LEN];
 	/* in usecs, need to use ice_intrl_to_usecs_reg() before writing this
 	 * value to the device
@@ -269,6 +285,7 @@ enum ice_pf_flags {
 	ICE_FLAG_RSS_ENA,
 	ICE_FLAG_SRIOV_ENA,
 	ICE_FLAG_SRIOV_CAPABLE,
+	ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA,
 	ICE_PF_FLAGS_NBITS		/* must be last */
 };
 
@@ -307,10 +324,10 @@ struct ice_pf {
 	u32 hw_oicr_idx;	/* Other interrupt cause vector HW index */
 	u32 num_avail_hw_msix;	/* remaining HW MSIX vectors left unclaimed */
 	u32 num_lan_msix;	/* Total MSIX vectors for base driver */
-	u16 num_lan_tx;		/* num lan tx queues setup */
-	u16 num_lan_rx;		/* num lan rx queues setup */
-	u16 q_left_tx;		/* remaining num tx queues left unclaimed */
-	u16 q_left_rx;		/* remaining num rx queues left unclaimed */
+	u16 num_lan_tx;		/* num lan Tx queues setup */
+	u16 num_lan_rx;		/* num lan Rx queues setup */
+	u16 q_left_tx;		/* remaining num Tx queues left unclaimed */
+	u16 q_left_rx;		/* remaining num Rx queues left unclaimed */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
 	u16 num_alloc_vsi;
 	u16 corer_count;	/* Core reset count */
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 6653555f55dd..242c78469181 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -5,7 +5,7 @@
 #define _ICE_ADMINQ_CMD_H_
 
 /* This header file defines the Admin Queue commands, error codes and
- * descriptor format.  It is shared between Firmware and Software.
+ * descriptor format. It is shared between Firmware and Software.
  */
 
 #define ICE_MAX_VSI			768
@@ -87,6 +87,7 @@ struct ice_aqc_list_caps {
 /* Device/Function buffer entry, repeated per reported capability */
 struct ice_aqc_list_caps_elem {
 	__le16 cap;
+#define ICE_AQC_CAPS_VALID_FUNCTIONS			0x0005
 #define ICE_AQC_CAPS_SRIOV				0x0012
 #define ICE_AQC_CAPS_VF					0x0013
 #define ICE_AQC_CAPS_VSI				0x0017
@@ -462,7 +463,7 @@ struct ice_aqc_sw_rules {
 };
 
 /* Add/Update/Get/Remove lookup Rx/Tx command/response entry
- * This structures describes the lookup rules and associated actions.  "index"
+ * This structures describes the lookup rules and associated actions. "index"
  * is returned as part of a response to a successful Add command, and can be
  * used to identify the rule for Update/Get/Remove commands.
  */
@@ -656,8 +657,13 @@ struct ice_aqc_get_topo {
 
 /* Update TSE (indirect 0x0403)
  * Get TSE (indirect 0x0404)
+ * Add TSE (indirect 0x0401)
+ * Delete TSE (indirect 0x040F)
+ * Move TSE (indirect 0x0408)
+ * Suspend Nodes (indirect 0x0409)
+ * Resume Nodes (indirect 0x040A)
  */
-struct ice_aqc_get_cfg_elem {
+struct ice_aqc_sched_elem_cmd {
 	__le16 num_elem_req;	/* Used by commands */
 	__le16 num_elem_resp;	/* Used by responses */
 	__le32 reserved;
@@ -673,18 +679,6 @@ struct ice_aqc_suspend_resume_elem {
 	__le32 teid[1];
 };
 
-/* Add TSE (indirect 0x0401)
- * Delete TSE (indirect 0x040F)
- * Move TSE (indirect 0x0408)
- */
-struct ice_aqc_add_move_delete_elem {
-	__le16 num_grps_req;
-	__le16 num_grps_updated;
-	__le32 reserved;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
 struct ice_aqc_elem_info_bw {
 	__le16 bw_profile_idx;
 	__le16 bw_alloc;
@@ -853,11 +847,46 @@ struct ice_aqc_get_phy_caps {
 #define ICE_PHY_TYPE_LOW_40GBASE_KR4		BIT_ULL(33)
 #define ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC	BIT_ULL(34)
 #define ICE_PHY_TYPE_LOW_40G_XLAUI		BIT_ULL(35)
+#define ICE_PHY_TYPE_LOW_50GBASE_CR2		BIT_ULL(36)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR2		BIT_ULL(37)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR2		BIT_ULL(38)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR2		BIT_ULL(39)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC	BIT_ULL(40)
+#define ICE_PHY_TYPE_LOW_50G_LAUI2		BIT_ULL(41)
+#define ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC	BIT_ULL(42)
+#define ICE_PHY_TYPE_LOW_50G_AUI2		BIT_ULL(43)
+#define ICE_PHY_TYPE_LOW_50GBASE_CP		BIT_ULL(44)
+#define ICE_PHY_TYPE_LOW_50GBASE_SR		BIT_ULL(45)
+#define ICE_PHY_TYPE_LOW_50GBASE_FR		BIT_ULL(46)
+#define ICE_PHY_TYPE_LOW_50GBASE_LR		BIT_ULL(47)
+#define ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4	BIT_ULL(48)
+#define ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC	BIT_ULL(49)
+#define ICE_PHY_TYPE_LOW_50G_AUI1		BIT_ULL(50)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR4		BIT_ULL(51)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR4		BIT_ULL(52)
+#define ICE_PHY_TYPE_LOW_100GBASE_LR4		BIT_ULL(53)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR4		BIT_ULL(54)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC	BIT_ULL(55)
+#define ICE_PHY_TYPE_LOW_100G_CAUI4		BIT_ULL(56)
+#define ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC	BIT_ULL(57)
+#define ICE_PHY_TYPE_LOW_100G_AUI4		BIT_ULL(58)
+#define ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4	BIT_ULL(59)
+#define ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4	BIT_ULL(60)
+#define ICE_PHY_TYPE_LOW_100GBASE_CP2		BIT_ULL(61)
+#define ICE_PHY_TYPE_LOW_100GBASE_SR2		BIT_ULL(62)
+#define ICE_PHY_TYPE_LOW_100GBASE_DR		BIT_ULL(63)
 #define ICE_PHY_TYPE_LOW_MAX_INDEX		63
+/* The second set of defines is for phy_type_high. */
+#define ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4	BIT_ULL(0)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC	BIT_ULL(1)
+#define ICE_PHY_TYPE_HIGH_100G_CAUI2		BIT_ULL(2)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC	BIT_ULL(3)
+#define ICE_PHY_TYPE_HIGH_100G_AUI2		BIT_ULL(4)
+#define ICE_PHY_TYPE_HIGH_MAX_INDEX		19
 
 struct ice_aqc_get_phy_caps_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 reserved;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 	u8 caps;
 #define ICE_AQC_PHY_EN_TX_LINK_PAUSE			BIT(0)
 #define ICE_AQC_PHY_EN_RX_LINK_PAUSE			BIT(1)
@@ -922,7 +951,7 @@ struct ice_aqc_set_phy_cfg {
 /* Set PHY config command data structure */
 struct ice_aqc_set_phy_cfg_data {
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 rsvd0;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 	u8 caps;
 #define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY		BIT(0)
 #define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY		BIT(1)
@@ -1031,10 +1060,12 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_LINK_SPEED_20GB		BIT(6)
 #define ICE_AQ_LINK_SPEED_25GB		BIT(7)
 #define ICE_AQ_LINK_SPEED_40GB		BIT(8)
+#define ICE_AQ_LINK_SPEED_50GB		BIT(9)
+#define ICE_AQ_LINK_SPEED_100GB		BIT(10)
 #define ICE_AQ_LINK_SPEED_UNKNOWN	BIT(15)
 	__le32 reserved3; /* Aligns next field to 8-byte boundary */
 	__le64 phy_type_low; /* Use values from ICE_PHY_TYPE_LOW_* */
-	__le64 reserved4;
+	__le64 phy_type_high; /* Use values from ICE_PHY_TYPE_HIGH_* */
 };
 
 /* Set event mask command (direct 0x0613) */
@@ -1054,6 +1085,16 @@ struct ice_aqc_set_event_mask {
 	u8	reserved1[6];
 };
 
+/* Set Port Identification LED (direct, 0x06E9) */
+struct ice_aqc_set_port_id_led {
+	u8 lport_num;
+	u8 lport_num_valid;
+	u8 ident_mode;
+#define ICE_AQC_PORT_IDENT_LED_BLINK	BIT(0)
+#define ICE_AQC_PORT_IDENT_LED_ORIG	0
+	u8 rsvd[13];
+};
+
 /* NVM Read command (indirect 0x0701)
  * NVM Erase commands (direct 0x0702)
  * NVM Update commands (indirect 0x0703)
@@ -1065,10 +1106,10 @@ struct ice_aqc_nvm {
 #define ICE_AQC_NVM_LAST_CMD		BIT(0)
 #define ICE_AQC_NVM_PCIR_REQ		BIT(0)	/* Used by NVM Update reply */
 #define ICE_AQC_NVM_PRESERVATION_S	1
-#define ICE_AQC_NVM_PRESERVATION_M	(3 << CSR_AQ_NVM_PRESERVATION_S)
-#define ICE_AQC_NVM_NO_PRESERVATION	(0 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVATION_M	(3 << ICE_AQC_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_NO_PRESERVATION	(0 << ICE_AQC_NVM_PRESERVATION_S)
 #define ICE_AQC_NVM_PRESERVE_ALL	BIT(1)
-#define ICE_AQC_NVM_PRESERVE_SELECTED	(3 << CSR_AQ_NVM_PRESERVATION_S)
+#define ICE_AQC_NVM_PRESERVE_SELECTED	(3 << ICE_AQC_NVM_PRESERVATION_S)
 #define ICE_AQC_NVM_FLASH_ONLY		BIT(7)
 	__le16 module_typeid;
 	__le16 length;
@@ -1110,7 +1151,7 @@ struct ice_aqc_get_set_rss_keys {
 };
 
 /* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */
-struct  ice_aqc_get_set_rss_lut {
+struct ice_aqc_get_set_rss_lut {
 #define ICE_AQC_GSET_RSS_LUT_VSI_VALID	BIT(15)
 #define ICE_AQC_GSET_RSS_LUT_VSI_ID_S	0
 #define ICE_AQC_GSET_RSS_LUT_VSI_ID_M	(0x1FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S)
@@ -1314,10 +1355,10 @@ struct ice_aqc_get_clear_fw_log {
  * @params: command-specific parameters
  *
  * Descriptor format for commands the driver posts on the Admin Transmit Queue
- * (ATQ).  The firmware writes back onto the command descriptor and returns
- * the result of the command.  Asynchronous events that are not an immediate
+ * (ATQ). The firmware writes back onto the command descriptor and returns
+ * the result of the command. Asynchronous events that are not an immediate
  * result of the command are written to the Admin Receive Queue (ARQ) using
- * the same descriptor format.  Descriptors are in little-endian notation with
+ * the same descriptor format. Descriptors are in little-endian notation with
  * 32-bit words.
  */
 struct ice_aq_desc {
@@ -1340,12 +1381,12 @@ struct ice_aq_desc {
 		struct ice_aqc_get_phy_caps get_phy;
 		struct ice_aqc_set_phy_cfg set_phy;
 		struct ice_aqc_restart_an restart_an;
+		struct ice_aqc_set_port_id_led set_port_id_led;
 		struct ice_aqc_get_sw_cfg get_sw_conf;
 		struct ice_aqc_sw_rules sw_rules;
 		struct ice_aqc_get_topo get_topo;
-		struct ice_aqc_get_cfg_elem get_update_elem;
+		struct ice_aqc_sched_elem_cmd sched_elem_cmd;
 		struct ice_aqc_query_txsched_res query_sched_res;
-		struct ice_aqc_add_move_delete_elem add_move_delete_elem;
 		struct ice_aqc_nvm nvm;
 		struct ice_aqc_pf_vf_msg virt;
 		struct ice_aqc_get_set_rss_lut get_set_rss_lut;
@@ -1379,10 +1420,10 @@ struct ice_aq_desc {
 
 /* error codes */
 enum ice_aq_err {
-	ICE_AQ_RC_OK		= 0,  /* success */
+	ICE_AQ_RC_OK		= 0,  /* Success */
 	ICE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
 	ICE_AQ_RC_EBUSY		= 12, /* Device or resource busy */
-	ICE_AQ_RC_EEXIST	= 13, /* object already exists */
+	ICE_AQ_RC_EEXIST	= 13, /* Object already exists */
 	ICE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
 };
 
@@ -1441,6 +1482,7 @@ enum ice_adminq_opc {
 	ice_aqc_opc_restart_an				= 0x0605,
 	ice_aqc_opc_get_link_status			= 0x0607,
 	ice_aqc_opc_set_event_mask			= 0x0613,
+	ice_aqc_opc_set_port_id_led			= 0x06E9,
 
 	/* NVM commands */
 	ice_aqc_opc_nvm_read				= 0x0701,
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 554fd707a6d6..63f003441300 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -165,8 +165,10 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 	cmd->param0 |= cpu_to_le16(report_mode);
 	status = ice_aq_send_cmd(pi->hw, &desc, pcaps, pcaps_size, cd);
 
-	if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP)
+	if (!status && report_mode == ICE_AQC_REPORT_TOPO_CAP) {
 		pi->phy.phy_type_low = le64_to_cpu(pcaps->phy_type_low);
+		pi->phy.phy_type_high = le64_to_cpu(pcaps->phy_type_high);
+	}
 
 	return status;
 }
@@ -183,6 +185,9 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		return ICE_MEDIA_UNKNOWN;
 
 	hw_link_info = &pi->phy.link_info;
+	if (hw_link_info->phy_type_low && hw_link_info->phy_type_high)
+		/* If more than one media type is selected, report unknown */
+		return ICE_MEDIA_UNKNOWN;
 
 	if (hw_link_info->phy_type_low) {
 		switch (hw_link_info->phy_type_low) {
@@ -196,6 +201,15 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		case ICE_PHY_TYPE_LOW_25G_AUI_C2C:
 		case ICE_PHY_TYPE_LOW_40GBASE_SR4:
 		case ICE_PHY_TYPE_LOW_40GBASE_LR4:
+		case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+		case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+		case ICE_PHY_TYPE_LOW_50GBASE_SR:
+		case ICE_PHY_TYPE_LOW_50GBASE_FR:
+		case ICE_PHY_TYPE_LOW_50GBASE_LR:
+		case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+		case ICE_PHY_TYPE_LOW_100GBASE_DR:
 			return ICE_MEDIA_FIBER;
 		case ICE_PHY_TYPE_LOW_100BASE_TX:
 		case ICE_PHY_TYPE_LOW_1000BASE_T:
@@ -209,6 +223,11 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		case ICE_PHY_TYPE_LOW_25GBASE_CR_S:
 		case ICE_PHY_TYPE_LOW_25GBASE_CR1:
 		case ICE_PHY_TYPE_LOW_40GBASE_CR4:
+		case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+		case ICE_PHY_TYPE_LOW_50GBASE_CP:
+		case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+		case ICE_PHY_TYPE_LOW_100GBASE_CP2:
 			return ICE_MEDIA_DA;
 		case ICE_PHY_TYPE_LOW_1000BASE_KX:
 		case ICE_PHY_TYPE_LOW_2500BASE_KX:
@@ -219,10 +238,18 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
 		case ICE_PHY_TYPE_LOW_25GBASE_KR1:
 		case ICE_PHY_TYPE_LOW_25GBASE_KR_S:
 		case ICE_PHY_TYPE_LOW_40GBASE_KR4:
+		case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+		case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+		case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+		case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+			return ICE_MEDIA_BACKPLANE;
+		}
+	} else {
+		switch (hw_link_info->phy_type_high) {
+		case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
 			return ICE_MEDIA_BACKPLANE;
 		}
 	}
-
 	return ICE_MEDIA_UNKNOWN;
 }
 
@@ -274,6 +301,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	/* update current link status information */
 	hw_link_info->link_speed = le16_to_cpu(link_data.link_speed);
 	hw_link_info->phy_type_low = le64_to_cpu(link_data.phy_type_low);
+	hw_link_info->phy_type_high = le64_to_cpu(link_data.phy_type_high);
 	*hw_media_type = ice_get_media_type(pi);
 	hw_link_info->link_info = link_data.link_info;
 	hw_link_info->an_info = link_data.an_info;
@@ -405,9 +433,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw)
 
 	INIT_LIST_HEAD(&sw->vsi_list_map_head);
 
-	ice_init_def_sw_recp(hw);
-
-	return 0;
+	return ice_init_def_sw_recp(hw);
 }
 
 /**
@@ -715,7 +741,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 
 	hw->evb_veb = true;
 
-	/* Query the allocated resources for tx scheduler */
+	/* Query the allocated resources for Tx scheduler */
 	status = ice_sched_query_res_alloc(hw);
 	if (status) {
 		ice_debug(hw, ICE_DBG_SCHED,
@@ -752,6 +778,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 		status = ICE_ERR_CFG;
 		goto err_unroll_sched;
 	}
+	INIT_LIST_HEAD(&hw->agg_list);
 
 	status = ice_init_fltr_mgmt_struct(hw);
 	if (status)
@@ -802,6 +829,7 @@ void ice_deinit_hw(struct ice_hw *hw)
 	ice_cleanup_fltr_mgmt_struct(hw);
 
 	ice_sched_cleanup_all(hw);
+	ice_sched_clear_agg(hw);
 
 	if (hw->port_info) {
 		devm_kfree(ice_hw_to_dev(hw), hw->port_info);
@@ -958,7 +986,7 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req)
  * ice_copy_rxq_ctx_to_hw
  * @hw: pointer to the hardware structure
  * @ice_rxq_ctx: pointer to the rxq context
- * @rxq_index: the index of the rx queue
+ * @rxq_index: the index of the Rx queue
  *
  * Copies rxq context from dense structure to hw register space
  */
@@ -1014,7 +1042,7 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = {
  * ice_write_rxq_ctx
  * @hw: pointer to the hardware structure
  * @rlan_ctx: pointer to the rxq context
- * @rxq_index: the index of the rx queue
+ * @rxq_index: the index of the Rx queue
  *
  * Converts rxq context from sparse to dense structure and then writes
  * it to hw register space
@@ -1387,6 +1415,27 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res)
 }
 
 /**
+ * ice_get_guar_num_vsi - determine number of guar VSI for a PF
+ * @hw: pointer to the hw structure
+ *
+ * Determine the number of valid functions by going through the bitmap returned
+ * from parsing capabilities and use this to calculate the number of VSI per PF.
+ */
+static u32 ice_get_guar_num_vsi(struct ice_hw *hw)
+{
+	u8 funcs;
+
+#define ICE_CAPS_VALID_FUNCS_M	0xFF
+	funcs = hweight8(hw->dev_caps.common_cap.valid_functions &
+			 ICE_CAPS_VALID_FUNCS_M);
+
+	if (!funcs)
+		return 0;
+
+	return ICE_MAX_VSI / funcs;
+}
+
+/**
  * ice_parse_caps - parse function/device capabilities
  * @hw: pointer to the hw struct
  * @buf: pointer to a buffer containing function/device capability records
@@ -1428,6 +1477,12 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 		u16 cap = le16_to_cpu(cap_resp->cap);
 
 		switch (cap) {
+		case ICE_AQC_CAPS_VALID_FUNCTIONS:
+			caps->valid_functions = number;
+			ice_debug(hw, ICE_DBG_INIT,
+				  "HW caps: Valid Functions = %d\n",
+				  caps->valid_functions);
+			break;
 		case ICE_AQC_CAPS_SRIOV:
 			caps->sr_iov_1_1 = (number == 1);
 			ice_debug(hw, ICE_DBG_INIT,
@@ -1457,10 +1512,10 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,
 					  "HW caps: Dev.VSI cnt = %d\n",
 					  dev_p->num_vsi_allocd_to_host);
 			} else if (func_p) {
-				func_p->guaranteed_num_vsi = number;
+				func_p->guar_num_vsi = ice_get_guar_num_vsi(hw);
 				ice_debug(hw, ICE_DBG_INIT,
 					  "HW caps: Func.VSI cnt = %d\n",
-					  func_p->guaranteed_num_vsi);
+					  number);
 			}
 			break;
 		case ICE_AQC_CAPS_RSS:
@@ -1630,7 +1685,7 @@ enum ice_status ice_get_caps(struct ice_hw *hw)
  * This function is used to write MAC address to the NVM (0x0108).
  */
 enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd)
 {
 	struct ice_aqc_manage_mac_write *cmd;
@@ -1642,8 +1697,8 @@ ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
 	cmd->flags = flags;
 
 	/* Prep values for flags, sah, sal */
-	cmd->sah = htons(*((u16 *)mac_addr));
-	cmd->sal = htonl(*((u32 *)(mac_addr + 2)));
+	cmd->sah = htons(*((const u16 *)mac_addr));
+	cmd->sal = htonl(*((const u32 *)(mac_addr + 2)));
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
 }
@@ -1680,17 +1735,20 @@ void ice_clear_pxe_mode(struct ice_hw *hw)
 /**
  * ice_get_link_speed_based_on_phy_type - returns link speed
  * @phy_type_low: lower part of phy_type
+ * @phy_type_high: higher part of phy_type
  *
- * This helper function will convert a phy_type_low to its corresponding link
+ * This helper function will convert an entry in phy type structure
+ * [phy_type_low, phy_type_high] to its corresponding link speed.
+ * Note: In the structure of [phy_type_low, phy_type_high], there should
+ * be one bit set, as this function will convert one phy type to its
  * speed.
- * Note: In the structure of phy_type_low, there should be one bit set, as
- * this function will convert one phy type to its speed.
  * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
  * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned
  */
 static u16
-ice_get_link_speed_based_on_phy_type(u64 phy_type_low)
+ice_get_link_speed_based_on_phy_type(u64 phy_type_low, u64 phy_type_high)
 {
+	u16 speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
 	u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
 
 	switch (phy_type_low) {
@@ -1744,41 +1802,110 @@ ice_get_link_speed_based_on_phy_type(u64 phy_type_low)
 	case ICE_PHY_TYPE_LOW_40G_XLAUI:
 		speed_phy_type_low = ICE_AQ_LINK_SPEED_40GB;
 		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+	case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_LAUI2:
+	case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI2:
+	case ICE_PHY_TYPE_LOW_50GBASE_CP:
+	case ICE_PHY_TYPE_LOW_50GBASE_SR:
+	case ICE_PHY_TYPE_LOW_50GBASE_FR:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR:
+	case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+	case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI1:
+		speed_phy_type_low = ICE_AQ_LINK_SPEED_50GB;
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+	case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_CAUI4:
+	case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_AUI4:
+	case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+	case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+	case ICE_PHY_TYPE_LOW_100GBASE_CP2:
+	case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+	case ICE_PHY_TYPE_LOW_100GBASE_DR:
+		speed_phy_type_low = ICE_AQ_LINK_SPEED_100GB;
+		break;
 	default:
 		speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN;
 		break;
 	}
 
-	return speed_phy_type_low;
+	switch (phy_type_high) {
+	case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2:
+		speed_phy_type_high = ICE_AQ_LINK_SPEED_100GB;
+		break;
+	default:
+		speed_phy_type_high = ICE_AQ_LINK_SPEED_UNKNOWN;
+		break;
+	}
+
+	if (speed_phy_type_low == ICE_AQ_LINK_SPEED_UNKNOWN &&
+	    speed_phy_type_high == ICE_AQ_LINK_SPEED_UNKNOWN)
+		return ICE_AQ_LINK_SPEED_UNKNOWN;
+	else if (speed_phy_type_low != ICE_AQ_LINK_SPEED_UNKNOWN &&
+		 speed_phy_type_high != ICE_AQ_LINK_SPEED_UNKNOWN)
+		return ICE_AQ_LINK_SPEED_UNKNOWN;
+	else if (speed_phy_type_low != ICE_AQ_LINK_SPEED_UNKNOWN &&
+		 speed_phy_type_high == ICE_AQ_LINK_SPEED_UNKNOWN)
+		return speed_phy_type_low;
+	else
+		return speed_phy_type_high;
 }
 
 /**
  * ice_update_phy_type
  * @phy_type_low: pointer to the lower part of phy_type
+ * @phy_type_high: pointer to the higher part of phy_type
  * @link_speeds_bitmap: targeted link speeds bitmap
  *
  * Note: For the link_speeds_bitmap structure, you can check it at
  * [ice_aqc_get_link_status->link_speed]. Caller can pass in
  * link_speeds_bitmap include multiple speeds.
  *
- * The value of phy_type_low will present a certain link speed. This helper
- * function will turn on bits in the phy_type_low based on the value of
+ * Each entry in this [phy_type_low, phy_type_high] structure will
+ * present a certain link speed. This helper function will turn on bits
+ * in [phy_type_low, phy_type_high] structure based on the value of
  * link_speeds_bitmap input parameter.
  */
-void ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap)
+void
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+		    u16 link_speeds_bitmap)
 {
 	u16 speed = ICE_AQ_LINK_SPEED_UNKNOWN;
+	u64 pt_high;
 	u64 pt_low;
 	int index;
 
 	/* We first check with low part of phy_type */
 	for (index = 0; index <= ICE_PHY_TYPE_LOW_MAX_INDEX; index++) {
 		pt_low = BIT_ULL(index);
-		speed = ice_get_link_speed_based_on_phy_type(pt_low);
+		speed = ice_get_link_speed_based_on_phy_type(pt_low, 0);
 
 		if (link_speeds_bitmap & speed)
 			*phy_type_low |= BIT_ULL(index);
 	}
+
+	/* We then check with high part of phy_type */
+	for (index = 0; index <= ICE_PHY_TYPE_HIGH_MAX_INDEX; index++) {
+		pt_high = BIT_ULL(index);
+		speed = ice_get_link_speed_based_on_phy_type(0, pt_high);
+
+		if (link_speeds_bitmap & speed)
+			*phy_type_high |= BIT_ULL(index);
+	}
 }
 
 /**
@@ -1910,6 +2037,7 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update)
 		if (ena_auto_link_update)
 			cfg.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
 		/* Copy over all the old settings */
+		cfg.phy_type_high = pcaps->phy_type_high;
 		cfg.phy_type_low = pcaps->phy_type_low;
 		cfg.low_power_ctrl = pcaps->low_power_ctrl;
 		cfg.eee_cap = pcaps->eee_cap;
@@ -2008,6 +2136,34 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 }
 
 /**
+ * ice_aq_set_port_id_led
+ * @pi: pointer to the port information
+ * @is_orig_mode: is this LED set to original mode (by the net-list)
+ * @cd: pointer to command details structure or NULL
+ *
+ * Set LED value for the given port (0x06e9)
+ */
+enum ice_status
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+		       struct ice_sq_cd *cd)
+{
+	struct ice_aqc_set_port_id_led *cmd;
+	struct ice_hw *hw = pi->hw;
+	struct ice_aq_desc desc;
+
+	cmd = &desc.params.set_port_id_led;
+
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_id_led);
+
+	if (is_orig_mode)
+		cmd->ident_mode = ICE_AQC_PORT_IDENT_LED_ORIG;
+	else
+		cmd->ident_mode = ICE_AQC_PORT_IDENT_LED_BLINK;
+
+	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
+}
+
+/**
  * __ice_aq_get_set_rss_lut
  * @hw: pointer to the hardware structure
  * @vsi_id: VSI FW index
@@ -2294,6 +2450,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 {
 	struct ice_aqc_dis_txqs *cmd;
 	struct ice_aq_desc desc;
+	enum ice_status status;
 	u16 i, sz = 0;
 
 	cmd = &desc.params.dis_txqs;
@@ -2329,6 +2486,8 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 		break;
 	}
 
+	/* flush pipe on time out */
+	cmd->cmd_type |= ICE_AQC_Q_DIS_CMD_FLUSH_PIPE;
 	/* If no queue group info, we are in a reset flow. Issue the AQ */
 	if (!qg_list)
 		goto do_aq;
@@ -2354,7 +2513,17 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 		return ICE_ERR_PARAM;
 
 do_aq:
-	return ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+	status = ice_aq_send_cmd(hw, &desc, qg_list, buf_size, cd);
+	if (status) {
+		if (!qg_list)
+			ice_debug(hw, ICE_DBG_SCHED, "VM%d disable failed %d\n",
+				  vmvf_num, hw->adminq.sq_last_status);
+		else
+			ice_debug(hw, ICE_DBG_SCHED, "disable Q %d failed %d\n",
+				  le16_to_cpu(qg_list[0].q_id[0]),
+				  hw->adminq.sq_last_status);
+	}
+	return status;
 }
 
 /* End of FW Admin Queue command wrappers */
@@ -2640,8 +2809,12 @@ ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_qgrps,
 
 	/* add the lan q */
 	status = ice_aq_add_lan_txq(hw, num_qgrps, buf, buf_size, cd);
-	if (status)
+	if (status) {
+		ice_debug(hw, ICE_DBG_SCHED, "enable Q %d failed %d\n",
+			  le16_to_cpu(buf->txqs[0].txq_id),
+			  hw->adminq.sq_last_status);
 		goto ena_txq_exit;
+	}
 
 	node.node_teid = buf->txqs[0].q_teid;
 	node.data.elem_type = ICE_AQC_ELEM_TYPE_LEAF;
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index cf760c24a6aa..d7c7c2ed8823 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -28,6 +28,8 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 		enum ice_aq_res_access_type access, u32 timeout);
 void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res);
 enum ice_status ice_init_nvm(struct ice_hw *hw);
+enum ice_status ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words,
+				u16 *data);
 enum ice_status
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		struct ice_aq_desc *desc, void *buf, u16 buf_size,
@@ -70,9 +72,10 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 		    struct ice_aqc_get_phy_caps_data *caps,
 		    struct ice_sq_cd *cd);
 void
-ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap);
+ice_update_phy_type(u64 *phy_type_low, u64 *phy_type_high,
+		    u16 link_speeds_bitmap);
 enum ice_status
-ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags,
+ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
 enum ice_status ice_clear_pf_cfg(struct ice_hw *hw);
 enum ice_status
@@ -86,6 +89,10 @@ enum ice_status
 ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd);
 enum ice_status
+ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
+		       struct ice_sq_cd *cd);
+
+enum ice_status
 ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
 		u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num,
 		struct ice_sq_cd *cmd_details);
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index 84c967294eaf..2bf5e11f559a 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -3,6 +3,26 @@
 
 #include "ice_common.h"
 
+#define ICE_CQ_INIT_REGS(qinfo, prefix)				\
+do {								\
+	(qinfo)->sq.head = prefix##_ATQH;			\
+	(qinfo)->sq.tail = prefix##_ATQT;			\
+	(qinfo)->sq.len = prefix##_ATQLEN;			\
+	(qinfo)->sq.bah = prefix##_ATQBAH;			\
+	(qinfo)->sq.bal = prefix##_ATQBAL;			\
+	(qinfo)->sq.len_mask = prefix##_ATQLEN_ATQLEN_M;	\
+	(qinfo)->sq.len_ena_mask = prefix##_ATQLEN_ATQENABLE_M;	\
+	(qinfo)->sq.head_mask = prefix##_ATQH_ATQH_M;		\
+	(qinfo)->rq.head = prefix##_ARQH;			\
+	(qinfo)->rq.tail = prefix##_ARQT;			\
+	(qinfo)->rq.len = prefix##_ARQLEN;			\
+	(qinfo)->rq.bah = prefix##_ARQBAH;			\
+	(qinfo)->rq.bal = prefix##_ARQBAL;			\
+	(qinfo)->rq.len_mask = prefix##_ARQLEN_ARQLEN_M;	\
+	(qinfo)->rq.len_ena_mask = prefix##_ARQLEN_ARQENABLE_M;	\
+	(qinfo)->rq.head_mask = prefix##_ARQH_ARQH_M;		\
+} while (0)
+
 /**
  * ice_adminq_init_regs - Initialize AdminQ registers
  * @hw: pointer to the hardware structure
@@ -13,23 +33,7 @@ static void ice_adminq_init_regs(struct ice_hw *hw)
 {
 	struct ice_ctl_q_info *cq = &hw->adminq;
 
-	cq->sq.head = PF_FW_ATQH;
-	cq->sq.tail = PF_FW_ATQT;
-	cq->sq.len = PF_FW_ATQLEN;
-	cq->sq.bah = PF_FW_ATQBAH;
-	cq->sq.bal = PF_FW_ATQBAL;
-	cq->sq.len_mask = PF_FW_ATQLEN_ATQLEN_M;
-	cq->sq.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M;
-	cq->sq.head_mask = PF_FW_ATQH_ATQH_M;
-
-	cq->rq.head = PF_FW_ARQH;
-	cq->rq.tail = PF_FW_ARQT;
-	cq->rq.len = PF_FW_ARQLEN;
-	cq->rq.bah = PF_FW_ARQBAH;
-	cq->rq.bal = PF_FW_ARQBAL;
-	cq->rq.len_mask = PF_FW_ARQLEN_ARQLEN_M;
-	cq->rq.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M;
-	cq->rq.head_mask = PF_FW_ARQH_ARQH_M;
+	ICE_CQ_INIT_REGS(cq, PF_FW);
 }
 
 /**
@@ -42,24 +46,7 @@ static void ice_mailbox_init_regs(struct ice_hw *hw)
 {
 	struct ice_ctl_q_info *cq = &hw->mailboxq;
 
-	/* set head and tail registers in our local struct */
-	cq->sq.head = PF_MBX_ATQH;
-	cq->sq.tail = PF_MBX_ATQT;
-	cq->sq.len = PF_MBX_ATQLEN;
-	cq->sq.bah = PF_MBX_ATQBAH;
-	cq->sq.bal = PF_MBX_ATQBAL;
-	cq->sq.len_mask = PF_MBX_ATQLEN_ATQLEN_M;
-	cq->sq.len_ena_mask = PF_MBX_ATQLEN_ATQENABLE_M;
-	cq->sq.head_mask = PF_MBX_ATQH_ATQH_M;
-
-	cq->rq.head = PF_MBX_ARQH;
-	cq->rq.tail = PF_MBX_ARQT;
-	cq->rq.len = PF_MBX_ARQLEN;
-	cq->rq.bah = PF_MBX_ARQBAH;
-	cq->rq.bal = PF_MBX_ARQBAL;
-	cq->rq.len_mask = PF_MBX_ARQLEN_ARQLEN_M;
-	cq->rq.len_ena_mask = PF_MBX_ARQLEN_ARQENABLE_M;
-	cq->rq.head_mask = PF_MBX_ARQH_ARQH_M;
+	ICE_CQ_INIT_REGS(cq, PF_MBX);
 }
 
 /**
@@ -131,37 +118,20 @@ ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 }
 
 /**
- * ice_free_ctrlq_sq_ring - Free Control Transmit Queue (ATQ) rings
+ * ice_free_cq_ring - Free control queue ring
  * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
+ * @ring: pointer to the specific control queue ring
  *
- * This assumes the posted send buffers have already been cleaned
+ * This assumes the posted buffers have already been cleaned
  * and de-allocated
  */
-static void ice_free_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
+static void ice_free_cq_ring(struct ice_hw *hw, struct ice_ctl_q_ring *ring)
 {
-	dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size,
-			   cq->sq.desc_buf.va, cq->sq.desc_buf.pa);
-	cq->sq.desc_buf.va = NULL;
-	cq->sq.desc_buf.pa = 0;
-	cq->sq.desc_buf.size = 0;
-}
-
-/**
- * ice_free_ctrlq_rq_ring - Free Control Receive Queue (ARQ) rings
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- *
- * This assumes the posted receive buffers have already been cleaned
- * and de-allocated
- */
-static void ice_free_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
-{
-	dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.desc_buf.size,
-			   cq->rq.desc_buf.va, cq->rq.desc_buf.pa);
-	cq->rq.desc_buf.va = NULL;
-	cq->rq.desc_buf.pa = 0;
-	cq->rq.desc_buf.size = 0;
+	dmam_free_coherent(ice_hw_to_dev(hw), ring->desc_buf.size,
+			   ring->desc_buf.va, ring->desc_buf.pa);
+	ring->desc_buf.va = NULL;
+	ring->desc_buf.pa = 0;
+	ring->desc_buf.size = 0;
 }
 
 /**
@@ -280,54 +250,23 @@ unwind_alloc_sq_bufs:
 	return ICE_ERR_NO_MEMORY;
 }
 
-/**
- * ice_free_rq_bufs - Free ARQ buffer info elements
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- */
-static void ice_free_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
-{
-	int i;
-
-	/* free descriptors */
-	for (i = 0; i < cq->num_rq_entries; i++) {
-		dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.r.rq_bi[i].size,
-				   cq->rq.r.rq_bi[i].va, cq->rq.r.rq_bi[i].pa);
-		cq->rq.r.rq_bi[i].va = NULL;
-		cq->rq.r.rq_bi[i].pa = 0;
-		cq->rq.r.rq_bi[i].size = 0;
-	}
-
-	/* free the dma header */
-	devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head);
-}
-
-/**
- * ice_free_sq_bufs - Free ATQ buffer info elements
- * @hw: pointer to the hardware structure
- * @cq: pointer to the specific Control queue
- */
-static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
+static enum ice_status
+ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries)
 {
-	int i;
+	/* Clear Head and Tail */
+	wr32(hw, ring->head, 0);
+	wr32(hw, ring->tail, 0);
 
-	/* only unmap if the address is non-NULL */
-	for (i = 0; i < cq->num_sq_entries; i++)
-		if (cq->sq.r.sq_bi[i].pa) {
-			dmam_free_coherent(ice_hw_to_dev(hw),
-					   cq->sq.r.sq_bi[i].size,
-					   cq->sq.r.sq_bi[i].va,
-					   cq->sq.r.sq_bi[i].pa);
-			cq->sq.r.sq_bi[i].va = NULL;
-			cq->sq.r.sq_bi[i].pa = 0;
-			cq->sq.r.sq_bi[i].size = 0;
-		}
+	/* set starting point */
+	wr32(hw, ring->len, (num_entries | ring->len_ena_mask));
+	wr32(hw, ring->bal, lower_32_bits(ring->desc_buf.pa));
+	wr32(hw, ring->bah, upper_32_bits(ring->desc_buf.pa));
 
-	/* free the buffer info list */
-	devm_kfree(ice_hw_to_dev(hw), cq->sq.cmd_buf);
+	/* Check one register to verify that config was applied */
+	if (rd32(hw, ring->bal) != lower_32_bits(ring->desc_buf.pa))
+		return ICE_ERR_AQ_ERROR;
 
-	/* free the dma header */
-	devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head);
+	return 0;
 }
 
 /**
@@ -340,23 +279,7 @@ static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static enum ice_status
 ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	u32 reg = 0;
-
-	/* Clear Head and Tail */
-	wr32(hw, cq->sq.head, 0);
-	wr32(hw, cq->sq.tail, 0);
-
-	/* set starting point */
-	wr32(hw, cq->sq.len, (cq->num_sq_entries | cq->sq.len_ena_mask));
-	wr32(hw, cq->sq.bal, lower_32_bits(cq->sq.desc_buf.pa));
-	wr32(hw, cq->sq.bah, upper_32_bits(cq->sq.desc_buf.pa));
-
-	/* Check one register to verify that config was applied */
-	reg = rd32(hw, cq->sq.bal);
-	if (reg != lower_32_bits(cq->sq.desc_buf.pa))
-		return ICE_ERR_AQ_ERROR;
-
-	return 0;
+	return ice_cfg_cq_regs(hw, &cq->sq, cq->num_sq_entries);
 }
 
 /**
@@ -369,25 +292,15 @@ ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static enum ice_status
 ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	u32 reg = 0;
-
-	/* Clear Head and Tail */
-	wr32(hw, cq->rq.head, 0);
-	wr32(hw, cq->rq.tail, 0);
+	enum ice_status status;
 
-	/* set starting point */
-	wr32(hw, cq->rq.len, (cq->num_rq_entries | cq->rq.len_ena_mask));
-	wr32(hw, cq->rq.bal, lower_32_bits(cq->rq.desc_buf.pa));
-	wr32(hw, cq->rq.bah, upper_32_bits(cq->rq.desc_buf.pa));
+	status = ice_cfg_cq_regs(hw, &cq->rq, cq->num_rq_entries);
+	if (status)
+		return status;
 
 	/* Update tail in the HW to post pre-allocated buffers */
 	wr32(hw, cq->rq.tail, (u32)(cq->num_rq_entries - 1));
 
-	/* Check one register to verify that config was applied */
-	reg = rd32(hw, cq->rq.bal);
-	if (reg != lower_32_bits(cq->rq.desc_buf.pa))
-		return ICE_ERR_AQ_ERROR;
-
 	return 0;
 }
 
@@ -444,7 +357,7 @@ static enum ice_status ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
-	ice_free_ctrlq_sq_ring(hw, cq);
+	ice_free_cq_ring(hw, &cq->sq);
 
 init_ctrlq_exit:
 	return ret_code;
@@ -503,12 +416,33 @@ static enum ice_status ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	goto init_ctrlq_exit;
 
 init_ctrlq_free_rings:
-	ice_free_ctrlq_rq_ring(hw, cq);
+	ice_free_cq_ring(hw, &cq->rq);
 
 init_ctrlq_exit:
 	return ret_code;
 }
 
+#define ICE_FREE_CQ_BUFS(hw, qi, ring)					\
+do {									\
+	int i;								\
+	/* free descriptors */						\
+	for (i = 0; i < (qi)->num_##ring##_entries; i++)		\
+		if ((qi)->ring.r.ring##_bi[i].pa) {			\
+			dmam_free_coherent(ice_hw_to_dev(hw),		\
+					   (qi)->ring.r.ring##_bi[i].size,\
+					   (qi)->ring.r.ring##_bi[i].va,\
+					   (qi)->ring.r.ring##_bi[i].pa);\
+			(qi)->ring.r.ring##_bi[i].va = NULL;		\
+			(qi)->ring.r.ring##_bi[i].pa = 0;		\
+			(qi)->ring.r.ring##_bi[i].size = 0;		\
+		}							\
+	/* free the buffer info list */					\
+	if ((qi)->ring.cmd_buf)						\
+		devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf);	\
+	/* free dma head */						\
+	devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head);		\
+} while (0)
+
 /**
  * ice_shutdown_sq - shutdown the Control ATQ
  * @hw: pointer to the hardware structure
@@ -538,8 +472,8 @@ ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	cq->sq.count = 0;	/* to indicate uninitialized queue */
 
 	/* free ring buffers and the ring itself */
-	ice_free_sq_bufs(hw, cq);
-	ice_free_ctrlq_sq_ring(hw, cq);
+	ICE_FREE_CQ_BUFS(hw, cq, sq);
+	ice_free_cq_ring(hw, &cq->sq);
 
 shutdown_sq_out:
 	mutex_unlock(&cq->sq_lock);
@@ -606,8 +540,8 @@ ice_shutdown_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 	cq->rq.count = 0;
 
 	/* free ring buffers and the ring itself */
-	ice_free_rq_bufs(hw, cq);
-	ice_free_ctrlq_rq_ring(hw, cq);
+	ICE_FREE_CQ_BUFS(hw, cq, rq);
+	ice_free_cq_ring(hw, &cq->rq);
 
 shutdown_rq_out:
 	mutex_unlock(&cq->rq_lock);
@@ -657,7 +591,6 @@ init_ctrlq_free_rq:
  *     - cq->num_rq_entries
  *     - cq->rq_buf_size
  *     - cq->sq_buf_size
- *
  */
 static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type)
 {
@@ -841,7 +774,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
  * @buf_size: size of buffer for indirect commands (or 0 for direct commands)
  * @cd: pointer to command details structure
  *
- * This is the main send command routine for the ATQ.  It runs the q,
+ * This is the main send command routine for the ATQ. It runs the queue,
  * cleans the queue, etc.
  */
 enum ice_status
@@ -1035,7 +968,7 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
  * @pending: number of events that could be left to process
  *
  * This function cleans one Admin Receive Queue element and returns
- * the contents through e.  It can also return how many events are
+ * the contents through e. It can also return how many events are
  * left to process through 'pending'.
  */
 enum ice_status
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 648acdb4c644..eb8d149e317c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -62,49 +62,49 @@ static const struct ice_stats ice_gstrings_vsi_stats[] = {
  * The PF_STATs are appended to the netdev stats only when ethtool -S
  * is queried on the base PF netdev.
  */
-static struct ice_stats ice_gstrings_pf_stats[] = {
-	ICE_PF_STAT("tx_bytes", stats.eth.tx_bytes),
-	ICE_PF_STAT("rx_bytes", stats.eth.rx_bytes),
-	ICE_PF_STAT("tx_unicast", stats.eth.tx_unicast),
-	ICE_PF_STAT("rx_unicast", stats.eth.rx_unicast),
-	ICE_PF_STAT("tx_multicast", stats.eth.tx_multicast),
-	ICE_PF_STAT("rx_multicast", stats.eth.rx_multicast),
-	ICE_PF_STAT("tx_broadcast", stats.eth.tx_broadcast),
-	ICE_PF_STAT("rx_broadcast", stats.eth.rx_broadcast),
-	ICE_PF_STAT("tx_errors", stats.eth.tx_errors),
-	ICE_PF_STAT("tx_size_64", stats.tx_size_64),
-	ICE_PF_STAT("rx_size_64", stats.rx_size_64),
-	ICE_PF_STAT("tx_size_127", stats.tx_size_127),
-	ICE_PF_STAT("rx_size_127", stats.rx_size_127),
-	ICE_PF_STAT("tx_size_255", stats.tx_size_255),
-	ICE_PF_STAT("rx_size_255", stats.rx_size_255),
-	ICE_PF_STAT("tx_size_511", stats.tx_size_511),
-	ICE_PF_STAT("rx_size_511", stats.rx_size_511),
-	ICE_PF_STAT("tx_size_1023", stats.tx_size_1023),
-	ICE_PF_STAT("rx_size_1023", stats.rx_size_1023),
-	ICE_PF_STAT("tx_size_1522", stats.tx_size_1522),
-	ICE_PF_STAT("rx_size_1522", stats.rx_size_1522),
-	ICE_PF_STAT("tx_size_big", stats.tx_size_big),
-	ICE_PF_STAT("rx_size_big", stats.rx_size_big),
-	ICE_PF_STAT("link_xon_tx", stats.link_xon_tx),
-	ICE_PF_STAT("link_xon_rx", stats.link_xon_rx),
-	ICE_PF_STAT("link_xoff_tx", stats.link_xoff_tx),
-	ICE_PF_STAT("link_xoff_rx", stats.link_xoff_rx),
-	ICE_PF_STAT("tx_dropped_link_down", stats.tx_dropped_link_down),
-	ICE_PF_STAT("rx_undersize", stats.rx_undersize),
-	ICE_PF_STAT("rx_fragments", stats.rx_fragments),
-	ICE_PF_STAT("rx_oversize", stats.rx_oversize),
-	ICE_PF_STAT("rx_jabber", stats.rx_jabber),
-	ICE_PF_STAT("rx_csum_bad", hw_csum_rx_error),
-	ICE_PF_STAT("rx_length_errors", stats.rx_len_errors),
-	ICE_PF_STAT("rx_dropped", stats.eth.rx_discards),
-	ICE_PF_STAT("rx_crc_errors", stats.crc_errors),
-	ICE_PF_STAT("illegal_bytes", stats.illegal_bytes),
-	ICE_PF_STAT("mac_local_faults", stats.mac_local_faults),
-	ICE_PF_STAT("mac_remote_faults", stats.mac_remote_faults),
+static const struct ice_stats ice_gstrings_pf_stats[] = {
+	ICE_PF_STAT("port.tx_bytes", stats.eth.tx_bytes),
+	ICE_PF_STAT("port.rx_bytes", stats.eth.rx_bytes),
+	ICE_PF_STAT("port.tx_unicast", stats.eth.tx_unicast),
+	ICE_PF_STAT("port.rx_unicast", stats.eth.rx_unicast),
+	ICE_PF_STAT("port.tx_multicast", stats.eth.tx_multicast),
+	ICE_PF_STAT("port.rx_multicast", stats.eth.rx_multicast),
+	ICE_PF_STAT("port.tx_broadcast", stats.eth.tx_broadcast),
+	ICE_PF_STAT("port.rx_broadcast", stats.eth.rx_broadcast),
+	ICE_PF_STAT("port.tx_errors", stats.eth.tx_errors),
+	ICE_PF_STAT("port.tx_size_64", stats.tx_size_64),
+	ICE_PF_STAT("port.rx_size_64", stats.rx_size_64),
+	ICE_PF_STAT("port.tx_size_127", stats.tx_size_127),
+	ICE_PF_STAT("port.rx_size_127", stats.rx_size_127),
+	ICE_PF_STAT("port.tx_size_255", stats.tx_size_255),
+	ICE_PF_STAT("port.rx_size_255", stats.rx_size_255),
+	ICE_PF_STAT("port.tx_size_511", stats.tx_size_511),
+	ICE_PF_STAT("port.rx_size_511", stats.rx_size_511),
+	ICE_PF_STAT("port.tx_size_1023", stats.tx_size_1023),
+	ICE_PF_STAT("port.rx_size_1023", stats.rx_size_1023),
+	ICE_PF_STAT("port.tx_size_1522", stats.tx_size_1522),
+	ICE_PF_STAT("port.rx_size_1522", stats.rx_size_1522),
+	ICE_PF_STAT("port.tx_size_big", stats.tx_size_big),
+	ICE_PF_STAT("port.rx_size_big", stats.rx_size_big),
+	ICE_PF_STAT("port.link_xon_tx", stats.link_xon_tx),
+	ICE_PF_STAT("port.link_xon_rx", stats.link_xon_rx),
+	ICE_PF_STAT("port.link_xoff_tx", stats.link_xoff_tx),
+	ICE_PF_STAT("port.link_xoff_rx", stats.link_xoff_rx),
+	ICE_PF_STAT("port.tx_dropped_link_down", stats.tx_dropped_link_down),
+	ICE_PF_STAT("port.rx_undersize", stats.rx_undersize),
+	ICE_PF_STAT("port.rx_fragments", stats.rx_fragments),
+	ICE_PF_STAT("port.rx_oversize", stats.rx_oversize),
+	ICE_PF_STAT("port.rx_jabber", stats.rx_jabber),
+	ICE_PF_STAT("port.rx_csum_bad", hw_csum_rx_error),
+	ICE_PF_STAT("port.rx_length_errors", stats.rx_len_errors),
+	ICE_PF_STAT("port.rx_dropped", stats.eth.rx_discards),
+	ICE_PF_STAT("port.rx_crc_errors", stats.crc_errors),
+	ICE_PF_STAT("port.illegal_bytes", stats.illegal_bytes),
+	ICE_PF_STAT("port.mac_local_faults", stats.mac_local_faults),
+	ICE_PF_STAT("port.mac_remote_faults", stats.mac_remote_faults),
 };
 
-static u32 ice_regs_dump_list[] = {
+static const u32 ice_regs_dump_list[] = {
 	PFGEN_STATE,
 	PRTGEN_STATUS,
 	QRX_CTRL(0),
@@ -114,6 +114,22 @@ static u32 ice_regs_dump_list[] = {
 	QRX_ITR(0),
 };
 
+struct ice_priv_flag {
+	char name[ETH_GSTRING_LEN];
+	u32 bitno;			/* bit position in pf->flags */
+};
+
+#define ICE_PRIV_FLAG(_name, _bitno) { \
+	.name = _name, \
+	.bitno = _bitno, \
+}
+
+static const struct ice_priv_flag ice_gstrings_priv_flags[] = {
+	ICE_PRIV_FLAG("link-down-on-close", ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA),
+};
+
+#define ICE_PRIV_FLAG_ARRAY_SIZE	ARRAY_SIZE(ice_gstrings_priv_flags)
+
 /**
  * ice_nvm_version_str - format the NVM version strings
  * @hw: ptr to the hardware info
@@ -152,6 +168,7 @@ ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 		sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(pf->pdev),
 		sizeof(drvinfo->bus_info));
+	drvinfo->n_priv_flags = ICE_PRIV_FLAG_ARRAY_SIZE;
 }
 
 static int ice_get_regs_len(struct net_device __always_unused *netdev)
@@ -203,6 +220,55 @@ static void ice_set_msglevel(struct net_device *netdev, u32 data)
 #endif /* !CONFIG_DYNAMIC_DEBUG */
 }
 
+static int ice_get_eeprom_len(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_pf *pf = np->vsi->back;
+
+	return (int)(pf->hw.nvm.sr_words * sizeof(u16));
+}
+
+static int
+ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
+	       u8 *bytes)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	u16 first_word, last_word, nwords;
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	struct ice_hw *hw = &pf->hw;
+	enum ice_status status;
+	struct device *dev;
+	int ret = 0;
+	u16 *buf;
+
+	dev = &pf->pdev->dev;
+
+	eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+	first_word = eeprom->offset >> 1;
+	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+	nwords = last_word - first_word + 1;
+
+	buf = devm_kcalloc(dev, nwords, sizeof(u16), GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	status = ice_read_sr_buf(hw, first_word, &nwords, buf);
+	if (status) {
+		dev_err(dev, "ice_read_sr_buf failed, err %d aq_err %d\n",
+			status, hw->adminq.sq_last_status);
+		eeprom->len = sizeof(u16) * nwords;
+		ret = -EIO;
+		goto out;
+	}
+
+	memcpy(bytes, (u8 *)buf + (eeprom->offset & 1), eeprom->len);
+out:
+	devm_kfree(dev, buf);
+	return ret;
+}
+
 static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
@@ -238,17 +304,105 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 			return;
 
 		for (i = 0; i < ICE_PF_STATS_LEN; i++) {
-			snprintf(p, ETH_GSTRING_LEN, "port.%s",
+			snprintf(p, ETH_GSTRING_LEN, "%s",
 				 ice_gstrings_pf_stats[i].stat_string);
 			p += ETH_GSTRING_LEN;
 		}
 
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+			snprintf(p, ETH_GSTRING_LEN, "%s",
+				 ice_gstrings_priv_flags[i].name);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
 	default:
 		break;
 	}
 }
 
+static int
+ice_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	bool led_active;
+
+	switch (state) {
+	case ETHTOOL_ID_ACTIVE:
+		led_active = true;
+		break;
+	case ETHTOOL_ID_INACTIVE:
+		led_active = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (ice_aq_set_port_id_led(np->vsi->port_info, !led_active, NULL))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * ice_get_priv_flags - report device private flags
+ * @netdev: network interface device structure
+ *
+ * The get string set count and the string set should be matched for each
+ * flag returned.  Add new strings for each flag to the ice_gstrings_priv_flags
+ * array.
+ *
+ * Returns a u32 bitmap of flags.
+ */
+static u32 ice_get_priv_flags(struct net_device *netdev)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	u32 i, ret_flags = 0;
+
+	for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+		const struct ice_priv_flag *priv_flag;
+
+		priv_flag = &ice_gstrings_priv_flags[i];
+
+		if (test_bit(priv_flag->bitno, pf->flags))
+			ret_flags |= BIT(i);
+	}
+
+	return ret_flags;
+}
+
+/**
+ * ice_set_priv_flags - set private flags
+ * @netdev: network interface device structure
+ * @flags: bit flags to be set
+ */
+static int ice_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	struct ice_vsi *vsi = np->vsi;
+	struct ice_pf *pf = vsi->back;
+	u32 i;
+
+	if (flags > BIT(ICE_PRIV_FLAG_ARRAY_SIZE))
+		return -EINVAL;
+
+	for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) {
+		const struct ice_priv_flag *priv_flag;
+
+		priv_flag = &ice_gstrings_priv_flags[i];
+
+		if (flags & BIT(i))
+			set_bit(priv_flag->bitno, pf->flags);
+		else
+			clear_bit(priv_flag->bitno, pf->flags);
+	}
+
+	return 0;
+}
+
 static int ice_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
@@ -260,10 +414,10 @@ static int ice_get_sset_count(struct net_device *netdev, int sset)
 		 * a private ethtool flag). This is due to the nature of the
 		 * ethtool stats API.
 		 *
-		 * User space programs such as ethtool must make 3 separate
+		 * Userspace programs such as ethtool must make 3 separate
 		 * ioctl requests, one for size, one for the strings, and
 		 * finally one for the stats. Since these cross into
-		 * user space, changes to the number or size could result in
+		 * userspace, changes to the number or size could result in
 		 * undefined memory access or incorrect string<->value
 		 * correlations for statistics.
 		 *
@@ -272,6 +426,8 @@ static int ice_get_sset_count(struct net_device *netdev, int sset)
 		 * not safe.
 		 */
 		return ICE_ALL_STATS_LEN(netdev);
+	case ETH_SS_PRIV_FLAGS:
+		return ICE_PRIV_FLAG_ARRAY_SIZE;
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -337,16 +493,20 @@ ice_get_ethtool_stats(struct net_device *netdev,
  * @netdev: network interface device structure
  * @ks: ethtool link ksettings struct to fill out
  */
-static void ice_phy_type_to_ethtool(struct net_device *netdev,
-				    struct ethtool_link_ksettings *ks)
+static void
+ice_phy_type_to_ethtool(struct net_device *netdev,
+			struct ethtool_link_ksettings *ks)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ice_link_status *hw_link_info;
+	bool need_add_adv_mode = false;
 	struct ice_vsi *vsi = np->vsi;
+	u64 phy_types_high;
 	u64 phy_types_low;
 
 	hw_link_info = &vsi->port_info->phy.link_info;
 	phy_types_low = vsi->port_info->phy.phy_type_low;
+	phy_types_high = vsi->port_info->phy.phy_type_high;
 
 	ethtool_link_ksettings_zero_link_mode(ks, supported);
 	ethtool_link_ksettings_zero_link_mode(ks, advertising);
@@ -495,6 +655,95 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 			ethtool_link_ksettings_add_link_mode(ks, advertising,
 							     40000baseLR4_Full);
 	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_LAUI2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_SR ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50G_AUI1) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     50000baseCR2_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseKR2_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     50000baseKR2_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_SR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_LR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_FR ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_LR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseSR2_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_50GB)
+			ethtool_link_ksettings_add_link_mode(ks, advertising,
+							     50000baseSR2_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_CAUI4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100G_AUI4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2  ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_CAUI2 ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100G_AUI2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode) {
+		need_add_adv_mode = false;
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseCR4_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_SR2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseSR4_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode) {
+		need_add_adv_mode = false;
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseSR4_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_LR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_DR) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseLR4_ER4_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode) {
+		need_add_adv_mode = false;
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseLR4_ER4_Full);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
+	    phy_types_high & ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR4_Full);
+		if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100GB)
+			need_add_adv_mode = true;
+	}
+	if (need_add_adv_mode)
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseKR4_Full);
 
 	/* Autoneg PHY types */
 	if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX ||
@@ -520,6 +769,24 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     Autoneg);
 	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR2 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_CP ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     Autoneg);
+	}
+	if (phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4 ||
+	    phy_types_low & ICE_PHY_TYPE_LOW_100GBASE_CP2) {
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     Autoneg);
+	}
 }
 
 #define TEST_SET_BITS_TIMEOUT	50
@@ -531,13 +798,15 @@ static void ice_phy_type_to_ethtool(struct net_device *netdev,
  * @ks: ethtool ksettings to fill in
  * @netdev: network interface device structure
  */
-static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
-				     struct net_device *netdev)
+static void
+ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
+			 struct net_device *netdev)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
 	struct ethtool_link_ksettings cap_ksettings;
 	struct ice_link_status *link_info;
 	struct ice_vsi *vsi = np->vsi;
+	bool unrecog_phy_high = false;
 	bool unrecog_phy_low = false;
 
 	link_info = &vsi->port_info->phy.link_info;
@@ -699,25 +968,133 @@ static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks,
 		ethtool_link_ksettings_add_link_mode(ks, advertising,
 						     40000baseKR4_Full);
 		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_CR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_CP:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     50000baseCR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_50G_LAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_LAUI2:
+	case ICE_PHY_TYPE_LOW_50G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI2:
+	case ICE_PHY_TYPE_LOW_50GBASE_SR:
+	case ICE_PHY_TYPE_LOW_50G_AUI1_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_50G_AUI1:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseCR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_KR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_KR_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseKR2_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     50000baseKR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_50GBASE_SR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR2:
+	case ICE_PHY_TYPE_LOW_50GBASE_FR:
+	case ICE_PHY_TYPE_LOW_50GBASE_LR:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     50000baseSR2_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_CR4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseCR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100G_CAUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_CAUI4:
+	case ICE_PHY_TYPE_LOW_100G_AUI4_AOC_ACC:
+	case ICE_PHY_TYPE_LOW_100G_AUI4:
+	case ICE_PHY_TYPE_LOW_100GBASE_CR_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_CP2:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseCR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_SR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_SR2:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseSR4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_LR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_DR:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseLR4_ER4_Full);
+		break;
+	case ICE_PHY_TYPE_LOW_100GBASE_KR4:
+	case ICE_PHY_TYPE_LOW_100GBASE_KR_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseKR4_Full);
+		break;
 	default:
 		unrecog_phy_low = true;
 	}
 
-	if (unrecog_phy_low) {
+	switch (link_info->phy_type_high) {
+	case ICE_PHY_TYPE_HIGH_100GBASE_KR2_PAM4:
+		ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseKR4_Full);
+		ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg);
+		ethtool_link_ksettings_add_link_mode(ks, advertising,
+						     100000baseKR4_Full);
+		break;
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_CAUI2:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2_AOC_ACC:
+	case ICE_PHY_TYPE_HIGH_100G_AUI2:
+		ethtool_link_ksettings_add_link_mode(ks, supported,
+						     100000baseCR4_Full);
+		break;
+	default:
+		unrecog_phy_high = true;
+	}
+
+	if (unrecog_phy_low && unrecog_phy_high) {
 		/* if we got here and link is up something bad is afoot */
-		netdev_info(netdev, "WARNING: Unrecognized PHY_Low (0x%llx).\n",
+		netdev_info(netdev,
+			    "WARNING: Unrecognized PHY_Low (0x%llx).\n",
 			    (u64)link_info->phy_type_low);
+		netdev_info(netdev,
+			    "WARNING: Unrecognized PHY_High (0x%llx).\n",
+			    (u64)link_info->phy_type_high);
 	}
 
 	/* Now that we've worked out everything that could be supported by the
 	 * current PHY type, get what is supported by the NVM and intersect
 	 * them to get what is truly supported
 	 */
-	memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings));
+	memset(&cap_ksettings, 0, sizeof(cap_ksettings));
 	ice_phy_type_to_ethtool(netdev, &cap_ksettings);
 	ethtool_intersect_link_masks(ks, &cap_ksettings);
 
 	switch (link_info->link_speed) {
+	case ICE_AQ_LINK_SPEED_100GB:
+		ks->base.speed = SPEED_100000;
+		break;
+	case ICE_AQ_LINK_SPEED_50GB:
+		ks->base.speed = SPEED_50000;
+		break;
 	case ICE_AQ_LINK_SPEED_40GB:
 		ks->base.speed = SPEED_40000;
 		break;
@@ -911,6 +1288,23 @@ ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks)
 	    ethtool_link_ksettings_test_link_mode(ks, advertising,
 						  40000baseKR4_Full))
 		adv_link_speed |= ICE_AQ_LINK_SPEED_40GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseCR2_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseKR2_Full))
+		adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  50000baseSR2_Full))
+		adv_link_speed |= ICE_AQ_LINK_SPEED_50GB;
+	if (ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseCR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseSR4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseLR4_ER4_Full) ||
+	    ethtool_link_ksettings_test_link_mode(ks, advertising,
+						  100000baseKR4_Full))
+		adv_link_speed |= ICE_AQ_LINK_SPEED_100GB;
 
 	return adv_link_speed;
 }
@@ -981,8 +1375,9 @@ ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks,
  *
  * Set speed/duplex per media_types advertised/forced
  */
-static int ice_set_link_ksettings(struct net_device *netdev,
-				  const struct ethtool_link_ksettings *ks)
+static int
+ice_set_link_ksettings(struct net_device *netdev,
+		       const struct ethtool_link_ksettings *ks)
 {
 	u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT, lport = 0;
 	struct ice_netdev_priv *np = netdev_priv(netdev);
@@ -994,6 +1389,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	struct ice_port_info *p;
 	u8 autoneg_changed = 0;
 	enum ice_status status;
+	u64 phy_type_high;
 	u64 phy_type_low;
 	int err = 0;
 	bool linkup;
@@ -1020,7 +1416,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 		return -EOPNOTSUPP;
 
 	/* copy the ksettings to copy_ks to avoid modifying the original */
-	memcpy(&copy_ks, ks, sizeof(struct ethtool_link_ksettings));
+	memcpy(&copy_ks, ks, sizeof(copy_ks));
 
 	/* save autoneg out of ksettings */
 	autoneg = copy_ks.base.autoneg;
@@ -1039,7 +1435,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 		return -EINVAL;
 
 	/* get our own copy of the bits to check against */
-	memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings));
+	memset(&safe_ks, 0, sizeof(safe_ks));
 	safe_ks.base.cmd = copy_ks.base.cmd;
 	safe_ks.base.link_mode_masks_nwords =
 		copy_ks.base.link_mode_masks_nwords;
@@ -1053,8 +1449,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	/* If copy_ks.base and safe_ks.base are not the same now, then they are
 	 * trying to set something that we do not support.
 	 */
-	if (memcmp(&copy_ks.base, &safe_ks.base,
-		   sizeof(struct ethtool_link_settings)))
+	if (memcmp(&copy_ks.base, &safe_ks.base, sizeof(copy_ks.base)))
 		return -EOPNOTSUPP;
 
 	while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) {
@@ -1078,7 +1473,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	}
 
 	/* Copy abilities to config in case autoneg is not set below */
-	memset(&config, 0, sizeof(struct ice_aqc_set_phy_cfg_data));
+	memset(&config, 0, sizeof(config));
 	config.caps = abilities->caps & ~ICE_AQC_PHY_AN_MODE;
 	if (abilities->caps & ICE_AQC_PHY_AN_MODE)
 		config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
@@ -1109,7 +1504,7 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 		adv_link_speed = curr_link_speed;
 
 	/* Convert the advertise link speeds to their corresponded PHY_TYPE */
-	ice_update_phy_type(&phy_type_low, adv_link_speed);
+	ice_update_phy_type(&phy_type_low, &phy_type_high, adv_link_speed);
 
 	if (!autoneg_changed && adv_link_speed == curr_link_speed) {
 		netdev_info(netdev, "Nothing changed, exiting without setting anything.\n");
@@ -1128,7 +1523,9 @@ static int ice_set_link_ksettings(struct net_device *netdev,
 	/* set link and auto negotiation so changes take effect */
 	config.caps |= ICE_AQ_PHY_ENA_LINK;
 
-	if (phy_type_low) {
+	if (phy_type_low || phy_type_high) {
+		config.phy_type_high = cpu_to_le64(phy_type_high) &
+			abilities->phy_type_high;
 		config.phy_type_low = cpu_to_le64(phy_type_low) &
 			abilities->phy_type_low;
 	} else {
@@ -1270,7 +1667,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
 		    vsi->tx_rings[0]->count, new_tx_cnt);
 
 	tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
-				sizeof(struct ice_ring), GFP_KERNEL);
+				sizeof(*tx_rings), GFP_KERNEL);
 	if (!tx_rings) {
 		err = -ENOMEM;
 		goto done;
@@ -1302,7 +1699,7 @@ process_rx:
 		    vsi->rx_rings[0]->count, new_rx_cnt);
 
 	rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
-				sizeof(struct ice_ring), GFP_KERNEL);
+				sizeof(*rx_rings), GFP_KERNEL);
 	if (!rx_rings) {
 		err = -ENOMEM;
 		goto done;
@@ -1392,17 +1789,17 @@ static int ice_nway_reset(struct net_device *netdev)
 {
 	/* restart autonegotiation */
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_link_status *hw_link_info;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_port_info *pi;
 	enum ice_status status;
-	bool link_up;
 
 	pi = vsi->port_info;
-	hw_link_info = &pi->phy.link_info;
-	link_up = hw_link_info->link_info & ICE_AQ_LINK_UP;
+	/* If VSI state is up, then restart autoneg with link up */
+	if (!test_bit(__ICE_DOWN, vsi->back->state))
+		status = ice_aq_set_link_restart_an(pi, true, NULL);
+	else
+		status = ice_aq_set_link_restart_an(pi, false, NULL);
 
-	status = ice_aq_set_link_restart_an(pi, link_up, NULL);
 	if (status) {
 		netdev_info(netdev, "link restart failed, err %d aq_err %d\n",
 			    status, pi->hw->adminq.sq_last_status);
@@ -1421,27 +1818,42 @@ static void
 ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_port_info *pi;
+	struct ice_port_info *pi = np->vsi->port_info;
+	struct ice_aqc_get_phy_caps_data *pcaps;
+	struct ice_vsi *vsi = np->vsi;
+	enum ice_status status;
 
-	pi = np->vsi->port_info;
-	pause->autoneg =
-		((pi->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) ?
-		 AUTONEG_ENABLE : AUTONEG_DISABLE);
+	/* Initialize pause params */
+	pause->rx_pause = 0;
+	pause->tx_pause = 0;
 
-	if (pi->fc.current_mode == ICE_FC_RX_PAUSE) {
-		pause->rx_pause = 1;
-	} else if (pi->fc.current_mode == ICE_FC_TX_PAUSE) {
+	pcaps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*pcaps),
+			     GFP_KERNEL);
+	if (!pcaps)
+		return;
+
+	/* Get current phy config */
+	status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+				     NULL);
+	if (status)
+		goto out;
+
+	pause->autoneg = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ?
+			AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+	if (pcaps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE)
 		pause->tx_pause = 1;
-	} else if (pi->fc.current_mode == ICE_FC_FULL) {
+	if (pcaps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE)
 		pause->rx_pause = 1;
-		pause->tx_pause = 1;
-	}
+
+out:
+	devm_kfree(&vsi->back->pdev->dev, pcaps);
 }
 
 /**
  * ice_set_pauseparam - Set Flow Control parameter
  * @netdev: network interface device structure
- * @pause: return tx/rx flow control status
+ * @pause: return Tx/Rx flow control status
  */
 static int
 ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
@@ -1543,7 +1955,7 @@ static u32 ice_get_rxfh_key_size(struct net_device __always_unused *netdev)
 }
 
 /**
- * ice_get_rxfh_indir_size - get the rx flow hash indirection table size
+ * ice_get_rxfh_indir_size - get the Rx flow hash indirection table size
  * @netdev: network interface device structure
  *
  * Returns the table size.
@@ -1556,7 +1968,7 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev)
 }
 
 /**
- * ice_get_rxfh - get the rx flow hash indirection table
+ * ice_get_rxfh - get the Rx flow hash indirection table
  * @netdev: network interface device structure
  * @indir: indirection table
  * @key: hash key
@@ -1603,7 +2015,7 @@ out:
 }
 
 /**
- * ice_set_rxfh - set the rx flow hash indirection table
+ * ice_set_rxfh - set the Rx flow hash indirection table
  * @netdev: network interface device structure
  * @indir: indirection table
  * @key: hash key
@@ -1667,6 +2079,258 @@ static int ice_set_rxfh(struct net_device *netdev, const u32 *indir,
 	return 0;
 }
 
+enum ice_container_type {
+	ICE_RX_CONTAINER,
+	ICE_TX_CONTAINER,
+};
+
+/**
+ * ice_get_rc_coalesce - get ITR values for specific ring container
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @c_type: container type, RX or TX
+ * @rc: ring container that the ITR values will come from
+ *
+ * Query the device for ice_ring_container specific ITR values. This is
+ * done per ice_ring_container because each q_vector can have 1 or more rings
+ * and all of said ring(s) will have the same ITR values.
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+static int
+ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
+		    struct ice_ring_container *rc)
+{
+	struct ice_pf *pf = rc->ring->vsi->back;
+
+	switch (c_type) {
+	case ICE_RX_CONTAINER:
+		ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting);
+		ec->rx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+		break;
+	case ICE_TX_CONTAINER:
+		ec->use_adaptive_tx_coalesce = ITR_IS_DYNAMIC(rc->itr_setting);
+		ec->tx_coalesce_usecs = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+		break;
+	default:
+		dev_dbg(&pf->pdev->dev, "Invalid c_type %d\n", c_type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * __ice_get_coalesce - get ITR/INTRL values for the device
+ * @netdev: pointer to the netdev associated with this query
+ * @ec: ethtool structure to fill with driver's coalesce settings
+ * @q_num: queue number to get the coalesce settings for
+ */
+static int
+__ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
+		   int q_num)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	int tx = -EINVAL, rx = -EINVAL;
+	struct ice_vsi *vsi = np->vsi;
+
+	if (q_num < 0) {
+		rx = ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+					 &vsi->rx_rings[0]->q_vector->rx);
+		tx = ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+					 &vsi->tx_rings[0]->q_vector->tx);
+
+		goto update_coalesced_frames;
+	}
+
+	if (q_num < vsi->num_rxq && q_num < vsi->num_txq) {
+		rx = ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+					 &vsi->rx_rings[q_num]->q_vector->rx);
+		tx = ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+					 &vsi->tx_rings[q_num]->q_vector->tx);
+	} else if (q_num < vsi->num_rxq) {
+		rx = ice_get_rc_coalesce(ec, ICE_RX_CONTAINER,
+					 &vsi->rx_rings[q_num]->q_vector->rx);
+	} else if (q_num < vsi->num_txq) {
+		tx = ice_get_rc_coalesce(ec, ICE_TX_CONTAINER,
+					 &vsi->tx_rings[q_num]->q_vector->tx);
+	} else {
+		/* q_num is invalid for both Rx and Tx queues */
+		return -EINVAL;
+	}
+
+update_coalesced_frames:
+	/* either q_num is invalid for both Rx and Tx queues or setting coalesce
+	 * failed completely
+	 */
+	if (tx && rx)
+		return -EINVAL;
+
+	if (q_num < vsi->num_txq)
+		ec->tx_max_coalesced_frames_irq = vsi->work_lmt;
+
+	if (q_num < vsi->num_rxq)
+		ec->rx_max_coalesced_frames_irq = vsi->work_lmt;
+
+	return 0;
+}
+
+static int
+ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	return __ice_get_coalesce(netdev, ec, -1);
+}
+
+static int ice_get_per_q_coalesce(struct net_device *netdev, u32 q_num,
+				  struct ethtool_coalesce *ec)
+{
+	return __ice_get_coalesce(netdev, ec, q_num);
+}
+
+/**
+ * ice_set_rc_coalesce - set ITR values for specific ring container
+ * @c_type: container type, RX or TX
+ * @ec: ethtool structure from user to update ITR settings
+ * @rc: ring container that the ITR values will come from
+ * @vsi: VSI associated to the ring container
+ *
+ * Set specific ITR values. This is done per ice_ring_container because each
+ * q_vector can have 1 or more rings and all of said ring(s) will have the same
+ * ITR values.
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+static int
+ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec,
+		    struct ice_ring_container *rc, struct ice_vsi *vsi)
+{
+	struct ice_pf *pf = vsi->back;
+	u16 itr_setting;
+
+	if (!rc->ring)
+		return -EINVAL;
+
+	itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC;
+
+	switch (c_type) {
+	case ICE_RX_CONTAINER:
+		if (ec->rx_coalesce_usecs != itr_setting &&
+		    ec->use_adaptive_rx_coalesce) {
+			netdev_info(vsi->netdev,
+				    "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n");
+			return -EINVAL;
+		}
+
+		if (ec->rx_coalesce_usecs > ICE_ITR_MAX) {
+			netdev_info(vsi->netdev,
+				    "Invalid value, rx-usecs range is 0-%d\n",
+				   ICE_ITR_MAX);
+			return -EINVAL;
+		}
+
+		if (ec->use_adaptive_rx_coalesce) {
+			rc->itr_setting |= ICE_ITR_DYNAMIC;
+		} else {
+			rc->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs);
+			rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		}
+		break;
+	case ICE_TX_CONTAINER:
+		if (ec->tx_coalesce_usecs != itr_setting &&
+		    ec->use_adaptive_tx_coalesce) {
+			netdev_info(vsi->netdev,
+				    "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n");
+			return -EINVAL;
+		}
+
+		if (ec->tx_coalesce_usecs > ICE_ITR_MAX) {
+			netdev_info(vsi->netdev,
+				    "Invalid value, tx-usecs range is 0-%d\n",
+				   ICE_ITR_MAX);
+			return -EINVAL;
+		}
+
+		if (ec->use_adaptive_tx_coalesce) {
+			rc->itr_setting |= ICE_ITR_DYNAMIC;
+		} else {
+			rc->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs);
+			rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		}
+		break;
+	default:
+		dev_dbg(&pf->pdev->dev, "Invalid container type %d\n", c_type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+__ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec,
+		   int q_num)
+{
+	struct ice_netdev_priv *np = netdev_priv(netdev);
+	int rx = -EINVAL, tx = -EINVAL;
+	struct ice_vsi *vsi = np->vsi;
+
+	if (q_num < 0) {
+		int i;
+
+		ice_for_each_q_vector(vsi, i) {
+			struct ice_q_vector *q_vector = vsi->q_vectors[i];
+
+			if (ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+						&q_vector->rx, vsi) ||
+			    ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+						&q_vector->tx, vsi))
+				return -EINVAL;
+		}
+
+		goto set_work_lmt;
+	}
+
+	if (q_num < vsi->num_rxq && q_num < vsi->num_txq) {
+		rx = ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+					 &vsi->rx_rings[q_num]->q_vector->rx,
+					 vsi);
+		tx = ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+					 &vsi->tx_rings[q_num]->q_vector->tx,
+					 vsi);
+	} else if (q_num < vsi->num_rxq) {
+		rx = ice_set_rc_coalesce(ICE_RX_CONTAINER, ec,
+					 &vsi->rx_rings[q_num]->q_vector->rx,
+					 vsi);
+	} else if (q_num < vsi->num_txq) {
+		tx  = ice_set_rc_coalesce(ICE_TX_CONTAINER, ec,
+					  &vsi->tx_rings[q_num]->q_vector->tx,
+					  vsi);
+	}
+
+	/* either q_num is invalid for both Rx and Tx queues or setting coalesce
+	 * failed completely
+	 */
+	if (rx && tx)
+		return -EINVAL;
+
+set_work_lmt:
+	if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq)
+		vsi->work_lmt = max(ec->tx_max_coalesced_frames_irq,
+				    ec->rx_max_coalesced_frames_irq);
+
+	return 0;
+}
+
+static int
+ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec)
+{
+	return __ice_set_coalesce(netdev, ec, -1);
+}
+
+static int ice_set_per_q_coalesce(struct net_device *netdev, u32 q_num,
+				  struct ethtool_coalesce *ec)
+{
+	return __ice_set_coalesce(netdev, ec, q_num);
+}
+
 static const struct ethtool_ops ice_ethtool_ops = {
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
@@ -1676,8 +2340,15 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.get_msglevel           = ice_get_msglevel,
 	.set_msglevel           = ice_set_msglevel,
 	.get_link		= ethtool_op_get_link,
+	.get_eeprom_len		= ice_get_eeprom_len,
+	.get_eeprom		= ice_get_eeprom,
+	.get_coalesce		= ice_get_coalesce,
+	.set_coalesce		= ice_set_coalesce,
 	.get_strings		= ice_get_strings,
+	.set_phys_id		= ice_set_phys_id,
 	.get_ethtool_stats      = ice_get_ethtool_stats,
+	.get_priv_flags		= ice_get_priv_flags,
+	.set_priv_flags		= ice_set_priv_flags,
 	.get_sset_count		= ice_get_sset_count,
 	.get_rxnfc		= ice_get_rxnfc,
 	.get_ringparam		= ice_get_ringparam,
@@ -1689,6 +2360,9 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.get_rxfh_indir_size	= ice_get_rxfh_indir_size,
 	.get_rxfh		= ice_get_rxfh,
 	.set_rxfh		= ice_set_rxfh,
+	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_per_queue_coalesce = ice_get_per_q_coalesce,
+	.set_per_queue_coalesce = ice_set_per_q_coalesce,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index 596b9fb1c510..6bf5cc064270 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -7,6 +7,9 @@
 #define _ICE_HW_AUTOGEN_H_
 
 #define QTX_COMM_DBELL(_DBQM)			(0x002C0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD(_DBQM)			(0x000E0000 + ((_DBQM) * 4))
+#define QTX_COMM_HEAD_HEAD_S			0
+#define QTX_COMM_HEAD_HEAD_M			ICE_M(0x1FFF, 0)
 #define PF_FW_ARQBAH				0x00080180
 #define PF_FW_ARQBAL				0x00080080
 #define PF_FW_ARQH				0x00080380
@@ -27,6 +30,7 @@
 #define PF_FW_ATQLEN_ATQVFE_M			BIT(28)
 #define PF_FW_ATQLEN_ATQOVFL_M			BIT(29)
 #define PF_FW_ATQLEN_ATQCRIT_M			BIT(30)
+#define VF_MBX_ARQLEN(_VF)			(0x0022BC00 + ((_VF) * 4))
 #define PF_FW_ATQLEN_ATQENABLE_M		BIT(31)
 #define PF_FW_ATQT				0x00080400
 #define PF_MBX_ARQBAH				0x0022E400
@@ -107,6 +111,7 @@
 #define GLINT_DYN_CTL_CLEARPBA_M		BIT(1)
 #define GLINT_DYN_CTL_SWINT_TRIG_M		BIT(2)
 #define GLINT_DYN_CTL_ITR_INDX_S		3
+#define GLINT_DYN_CTL_INTERVAL_S		5
 #define GLINT_DYN_CTL_SW_ITR_INDX_M		ICE_M(0x3, 25)
 #define GLINT_DYN_CTL_INTENA_MSK_M		BIT(31)
 #define GLINT_ITR(_i, _INT)			(0x00154000 + ((_i) * 8192 + (_INT) * 4))
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 7d2a66739e3f..ef4c79b5aa32 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -6,11 +6,11 @@
 
 union ice_32byte_rx_desc {
 	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
 			/* bit 0 of hdr_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
+		__le64 rsvd1;
+		__le64 rsvd2;
 	} read;
 	struct {
 		struct {
@@ -105,11 +105,11 @@ enum ice_rx_ptype_payload_layer {
  */
 union ice_32b_rx_flex_desc {
 	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
-				  /* bit 0 of hdr_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
+		__le64 pkt_addr; /* Packet buffer address */
+		__le64 hdr_addr; /* Header buffer address */
+				 /* bit 0 of hdr_addr is DD bit */
+		__le64 rsvd1;
+		__le64 rsvd2;
 	} read;
 	struct {
 		/* Qword 0 */
@@ -256,6 +256,9 @@ enum ice_rx_flex_desc_status_error_0_bits {
 
 #define ICE_RXQ_CTX_SIZE_DWORDS		8
 #define ICE_RXQ_CTX_SZ			(ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32))
+#define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS	22
+#define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS	5
+#define GLTCLAN_CQ_CNTX(i, CQ)		(GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800))
 
 /* RLAN Rx queue context data
  *
@@ -274,18 +277,18 @@ struct ice_rlan_ctx {
 	u16 dbuf; /* bigger than needed, see above for reason */
 #define ICE_RLAN_CTX_HBUF_S 6
 	u16 hbuf; /* bigger than needed, see above for reason */
-	u8  dtype;
-	u8  dsize;
-	u8  crcstrip;
-	u8  l2tsel;
-	u8  hsplit_0;
-	u8  hsplit_1;
-	u8  showiv;
+	u8 dtype;
+	u8 dsize;
+	u8 crcstrip;
+	u8 l2tsel;
+	u8 hsplit_0;
+	u8 hsplit_1;
+	u8 showiv;
 	u32 rxmax; /* bigger than needed, see above for reason */
-	u8  tphrdesc_ena;
-	u8  tphwdesc_ena;
-	u8  tphdata_ena;
-	u8  tphhead_ena;
+	u8 tphrdesc_ena;
+	u8 tphwdesc_ena;
+	u8 tphdata_ena;
+	u8 tphhead_ena;
 	u16 lrxqthresh; /* bigger than needed, see above for reason */
 };
 
@@ -343,6 +346,7 @@ enum ice_tx_desc_cmd_bits {
 	ICE_TX_DESC_CMD_IIPT_IPV4		= 0x0040, /* 2 BITS */
 	ICE_TX_DESC_CMD_IIPT_IPV4_CSUM		= 0x0060, /* 2 BITS */
 	ICE_TX_DESC_CMD_L4T_EOFT_TCP		= 0x0100, /* 2 BITS */
+	ICE_TX_DESC_CMD_L4T_EOFT_SCTP		= 0x0200, /* 2 BITS */
 	ICE_TX_DESC_CMD_L4T_EOFT_UDP		= 0x0300, /* 2 BITS */
 };
 
@@ -413,35 +417,35 @@ enum ice_tx_ctx_desc_cmd_bits {
 struct ice_tlan_ctx {
 #define ICE_TLAN_CTX_BASE_S	7
 	u64 base;		/* base is defined in 128-byte units */
-	u8  port_num;
+	u8 port_num;
 	u16 cgd_num;		/* bigger than needed, see above for reason */
-	u8  pf_num;
+	u8 pf_num;
 	u16 vmvf_num;
-	u8  vmvf_type;
+	u8 vmvf_type;
 #define ICE_TLAN_CTX_VMVF_TYPE_VF	0
 #define ICE_TLAN_CTX_VMVF_TYPE_VMQ	1
 #define ICE_TLAN_CTX_VMVF_TYPE_PF	2
 	u16 src_vsi;
-	u8  tsyn_ena;
-	u8  alt_vlan;
+	u8 tsyn_ena;
+	u8 alt_vlan;
 	u16 cpuid;		/* bigger than needed, see above for reason */
-	u8  wb_mode;
-	u8  tphrd_desc;
-	u8  tphrd;
-	u8  tphwr_desc;
+	u8 wb_mode;
+	u8 tphrd_desc;
+	u8 tphrd;
+	u8 tphwr_desc;
 	u16 cmpq_id;
 	u16 qnum_in_func;
-	u8  itr_notification_mode;
-	u8  adjust_prof_id;
+	u8 itr_notification_mode;
+	u8 adjust_prof_id;
 	u32 qlen;		/* bigger than needed, see above for reason */
-	u8  quanta_prof_idx;
-	u8  tso_ena;
+	u8 quanta_prof_idx;
+	u8 tso_ena;
 	u16 tso_qnum;
-	u8  legacy_int;
-	u8  drop_ena;
-	u8  cache_prof_idx;
-	u8  pkt_shaper_prof_idx;
-	u8  int_q_state;	/* width not needed - internal do not write */
+	u8 legacy_int;
+	u8 drop_ena;
+	u8 cache_prof_idx;
+	u8 pkt_shaper_prof_idx;
+	u8 int_q_state;	/* width not needed - internal do not write */
 };
 
 /* macro to make the table lines short */
@@ -485,5 +489,7 @@ static inline struct ice_rx_ptype_decoded ice_decode_rx_desc_ptype(u16 ptype)
 #define ICE_LINK_SPEED_20000MBPS	20000
 #define ICE_LINK_SPEED_25000MBPS	25000
 #define ICE_LINK_SPEED_40000MBPS	40000
+#define ICE_LINK_SPEED_50000MBPS	50000
+#define ICE_LINK_SPEED_100000MBPS	100000
 
 #endif /* _ICE_LAN_TX_RX_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 1041fa2a7767..fa61203bee26 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -20,7 +20,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring)
 	u16 pf_q;
 	int err;
 
-	/* what is RX queue number in global space of 2K Rx queues */
+	/* what is Rx queue number in global space of 2K Rx queues */
 	pf_q = vsi->rxq_map[ring->q_index];
 
 	/* clear the context structure first */
@@ -174,15 +174,15 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena)
 {
 	int i;
 
-	for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) {
+	for (i = 0; i < ICE_Q_WAIT_MAX_RETRY; i++) {
 		u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q));
 
 		if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M))
 			break;
 
-		usleep_range(10, 20);
+		usleep_range(20, 40);
 	}
-	if (i >= ICE_Q_WAIT_RETRY_LIMIT)
+	if (i >= ICE_Q_WAIT_MAX_RETRY)
 		return -ETIMEDOUT;
 
 	return 0;
@@ -249,12 +249,12 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors)
 
 	/* allocate memory for both Tx and Rx ring pointers */
 	vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq,
-				     sizeof(struct ice_ring *), GFP_KERNEL);
+				     sizeof(*vsi->tx_rings), GFP_KERNEL);
 	if (!vsi->tx_rings)
 		goto err_txrings;
 
 	vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq,
-				     sizeof(struct ice_ring *), GFP_KERNEL);
+				     sizeof(*vsi->rx_rings), GFP_KERNEL);
 	if (!vsi->rx_rings)
 		goto err_rxrings;
 
@@ -262,7 +262,7 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi, bool alloc_qvectors)
 		/* allocate memory for q_vector pointers */
 		vsi->q_vectors = devm_kcalloc(&pf->pdev->dev,
 					      vsi->num_q_vectors,
-					      sizeof(struct ice_q_vector *),
+					      sizeof(*vsi->q_vectors),
 					      GFP_KERNEL);
 		if (!vsi->q_vectors)
 			goto err_vectors;
@@ -348,19 +348,25 @@ static int ice_get_free_slot(void *array, int size, int curr)
 void ice_vsi_delete(struct ice_vsi *vsi)
 {
 	struct ice_pf *pf = vsi->back;
-	struct ice_vsi_ctx ctxt;
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
 
+	ctxt = devm_kzalloc(&pf->pdev->dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return;
+
 	if (vsi->type == ICE_VSI_VF)
-		ctxt.vf_num = vsi->vf_id;
-	ctxt.vsi_num = vsi->vsi_num;
+		ctxt->vf_num = vsi->vf_id;
+	ctxt->vsi_num = vsi->vsi_num;
 
-	memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props));
+	memcpy(&ctxt->info, &vsi->info, sizeof(ctxt->info));
 
-	status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL);
+	status = ice_free_vsi(&pf->hw, vsi->idx, ctxt, false, NULL);
 	if (status)
 		dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n",
 			vsi->vsi_num);
+
+	devm_kfree(&pf->pdev->dev, ctxt);
 }
 
 /**
@@ -514,110 +520,89 @@ unlock_pf:
 }
 
 /**
- * ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
- * @vsi: the VSI getting queues
+ * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
+ * @qs_cfg: gathered variables needed for PF->VSI queues assignment
  *
- * Return 0 on success and a negative value on error
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
  */
-static int ice_vsi_get_qs_contig(struct ice_vsi *vsi)
+static int __ice_vsi_get_qs_contig(struct ice_qs_cfg *qs_cfg)
 {
-	struct ice_pf *pf = vsi->back;
-	int offset, ret = 0;
+	int offset, i;
 
-	mutex_lock(&pf->avail_q_mutex);
-	/* look for contiguous block of queues for Tx */
-	offset = bitmap_find_next_zero_area(pf->avail_txqs, ICE_MAX_TXQS,
-					    0, vsi->alloc_txq, 0);
-	if (offset < ICE_MAX_TXQS) {
-		int i;
-
-		bitmap_set(pf->avail_txqs, offset, vsi->alloc_txq);
-		for (i = 0; i < vsi->alloc_txq; i++)
-			vsi->txq_map[i] = i + offset;
-	} else {
-		ret = -ENOMEM;
-		vsi->tx_mapping_mode = ICE_VSI_MAP_SCATTER;
+	mutex_lock(qs_cfg->qs_mutex);
+	offset = bitmap_find_next_zero_area(qs_cfg->pf_map, qs_cfg->pf_map_size,
+					    0, qs_cfg->q_count, 0);
+	if (offset >= qs_cfg->pf_map_size) {
+		mutex_unlock(qs_cfg->qs_mutex);
+		return -ENOMEM;
 	}
 
-	/* look for contiguous block of queues for Rx */
-	offset = bitmap_find_next_zero_area(pf->avail_rxqs, ICE_MAX_RXQS,
-					    0, vsi->alloc_rxq, 0);
-	if (offset < ICE_MAX_RXQS) {
-		int i;
-
-		bitmap_set(pf->avail_rxqs, offset, vsi->alloc_rxq);
-		for (i = 0; i < vsi->alloc_rxq; i++)
-			vsi->rxq_map[i] = i + offset;
-	} else {
-		ret = -ENOMEM;
-		vsi->rx_mapping_mode = ICE_VSI_MAP_SCATTER;
-	}
-	mutex_unlock(&pf->avail_q_mutex);
+	bitmap_set(qs_cfg->pf_map, offset, qs_cfg->q_count);
+	for (i = 0; i < qs_cfg->q_count; i++)
+		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = i + offset;
+	mutex_unlock(qs_cfg->qs_mutex);
 
-	return ret;
+	return 0;
 }
 
 /**
- * ice_vsi_get_qs_scatter - Assign a scattered queues to VSI
- * @vsi: the VSI getting queues
+ * __ice_vsi_get_qs_sc - Assign a scattered queues from PF to VSI
+ * @qs_cfg: gathered variables needed for PF->VSI queues assignment
  *
- * Return 0 on success and a negative value on error
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
  */
-static int ice_vsi_get_qs_scatter(struct ice_vsi *vsi)
+static int __ice_vsi_get_qs_sc(struct ice_qs_cfg *qs_cfg)
 {
-	struct ice_pf *pf = vsi->back;
 	int i, index = 0;
 
-	mutex_lock(&pf->avail_q_mutex);
-
-	if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER) {
-		for (i = 0; i < vsi->alloc_txq; i++) {
-			index = find_next_zero_bit(pf->avail_txqs,
-						   ICE_MAX_TXQS, index);
-			if (index < ICE_MAX_TXQS) {
-				set_bit(index, pf->avail_txqs);
-				vsi->txq_map[i] = index;
-			} else {
-				goto err_scatter_tx;
-			}
-		}
-	}
-
-	if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER) {
-		for (i = 0; i < vsi->alloc_rxq; i++) {
-			index = find_next_zero_bit(pf->avail_rxqs,
-						   ICE_MAX_RXQS, index);
-			if (index < ICE_MAX_RXQS) {
-				set_bit(index, pf->avail_rxqs);
-				vsi->rxq_map[i] = index;
-			} else {
-				goto err_scatter_rx;
-			}
-		}
+	mutex_lock(qs_cfg->qs_mutex);
+	for (i = 0; i < qs_cfg->q_count; i++) {
+		index = find_next_zero_bit(qs_cfg->pf_map,
+					   qs_cfg->pf_map_size, index);
+		if (index >= qs_cfg->pf_map_size)
+			goto err_scatter;
+		set_bit(index, qs_cfg->pf_map);
+		qs_cfg->vsi_map[i + qs_cfg->vsi_map_offset] = index;
 	}
+	mutex_unlock(qs_cfg->qs_mutex);
 
-	mutex_unlock(&pf->avail_q_mutex);
 	return 0;
-
-err_scatter_rx:
-	/* unflag any queues we have grabbed (i is failed position) */
+err_scatter:
 	for (index = 0; index < i; index++) {
-		clear_bit(vsi->rxq_map[index], pf->avail_rxqs);
-		vsi->rxq_map[index] = 0;
-	}
-	i = vsi->alloc_txq;
-err_scatter_tx:
-	/* i is either position of failed attempt or vsi->alloc_txq */
-	for (index = 0; index < i; index++) {
-		clear_bit(vsi->txq_map[index], pf->avail_txqs);
-		vsi->txq_map[index] = 0;
+		clear_bit(qs_cfg->vsi_map[index], qs_cfg->pf_map);
+		qs_cfg->vsi_map[index + qs_cfg->vsi_map_offset] = 0;
 	}
+	mutex_unlock(qs_cfg->qs_mutex);
 
-	mutex_unlock(&pf->avail_q_mutex);
 	return -ENOMEM;
 }
 
 /**
+ * __ice_vsi_get_qs - helper function for assigning queues from PF to VSI
+ * @qs_cfg: gathered variables needed for PF->VSI queues assignment
+ *
+ * This is an internal function for assigning queues from the PF to VSI and
+ * initially tries to find contiguous space.  If it is not successful to find
+ * contiguous space, then it tries with the scatter approach.
+ *
+ * Return 0 on success and -ENOMEM in case of no left space in PF queue bitmap
+ */
+static int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg)
+{
+	int ret = 0;
+
+	ret = __ice_vsi_get_qs_contig(qs_cfg);
+	if (ret) {
+		/* contig failed, so try with scatter approach */
+		qs_cfg->mapping_mode = ICE_VSI_MAP_SCATTER;
+		qs_cfg->q_count = min_t(u16, qs_cfg->q_count,
+					qs_cfg->scatter_count);
+		ret = __ice_vsi_get_qs_sc(qs_cfg);
+	}
+	return ret;
+}
+
+/**
  * ice_vsi_get_qs - Assign queues from PF to VSI
  * @vsi: the VSI to assign queues to
  *
@@ -625,25 +610,35 @@ err_scatter_tx:
  */
 static int ice_vsi_get_qs(struct ice_vsi *vsi)
 {
+	struct ice_pf *pf = vsi->back;
+	struct ice_qs_cfg tx_qs_cfg = {
+		.qs_mutex = &pf->avail_q_mutex,
+		.pf_map = pf->avail_txqs,
+		.pf_map_size = ICE_MAX_TXQS,
+		.q_count = vsi->alloc_txq,
+		.scatter_count = ICE_MAX_SCATTER_TXQS,
+		.vsi_map = vsi->txq_map,
+		.vsi_map_offset = 0,
+		.mapping_mode = vsi->tx_mapping_mode
+	};
+	struct ice_qs_cfg rx_qs_cfg = {
+		.qs_mutex = &pf->avail_q_mutex,
+		.pf_map = pf->avail_rxqs,
+		.pf_map_size = ICE_MAX_RXQS,
+		.q_count = vsi->alloc_rxq,
+		.scatter_count = ICE_MAX_SCATTER_RXQS,
+		.vsi_map = vsi->rxq_map,
+		.vsi_map_offset = 0,
+		.mapping_mode = vsi->rx_mapping_mode
+	};
 	int ret = 0;
 
 	vsi->tx_mapping_mode = ICE_VSI_MAP_CONTIG;
 	vsi->rx_mapping_mode = ICE_VSI_MAP_CONTIG;
 
-	/* NOTE: ice_vsi_get_qs_contig() will set the Rx/Tx mapping
-	 * modes individually to scatter if assigning contiguous queues
-	 * to Rx or Tx fails
-	 */
-	ret = ice_vsi_get_qs_contig(vsi);
-	if (ret < 0) {
-		if (vsi->tx_mapping_mode == ICE_VSI_MAP_SCATTER)
-			vsi->alloc_txq = max_t(u16, vsi->alloc_txq,
-					       ICE_MAX_SCATTER_TXQS);
-		if (vsi->rx_mapping_mode == ICE_VSI_MAP_SCATTER)
-			vsi->alloc_rxq = max_t(u16, vsi->alloc_rxq,
-					       ICE_MAX_SCATTER_RXQS);
-		ret = ice_vsi_get_qs_scatter(vsi);
-	}
+	ret = __ice_vsi_get_qs(&tx_qs_cfg);
+	if (!ret)
+		ret = __ice_vsi_get_qs(&rx_qs_cfg);
 
 	return ret;
 }
@@ -774,11 +769,13 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt)
  */
 static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	u16 offset = 0, qmap = 0, numq_tc;
-	u16 pow = 0, max_rss = 0, qcount;
+	u16 offset = 0, qmap = 0, tx_count = 0;
 	u16 qcount_tx = vsi->alloc_txq;
 	u16 qcount_rx = vsi->alloc_rxq;
+	u16 tx_numq_tc, rx_numq_tc;
+	u16 pow = 0, max_rss = 0;
 	bool ena_tc0 = false;
+	u8 netdev_tc = 0;
 	int i;
 
 	/* at least TC0 should be enabled by default */
@@ -794,7 +791,12 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 		vsi->tc_cfg.ena_tc |= 1;
 	}
 
-	numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+	rx_numq_tc = qcount_rx / vsi->tc_cfg.numtc;
+	if (!rx_numq_tc)
+		rx_numq_tc = 1;
+	tx_numq_tc = qcount_tx / vsi->tc_cfg.numtc;
+	if (!tx_numq_tc)
+		tx_numq_tc = 1;
 
 	/* TC mapping is a function of the number of Rx queues assigned to the
 	 * VSI for each traffic class and the offset of these queues.
@@ -808,7 +810,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 	 * Setup number and offset of Rx queues for all TCs for the VSI
 	 */
 
-	qcount = numq_tc;
+	qcount_rx = rx_numq_tc;
+
 	/* qcount will change if RSS is enabled */
 	if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) {
 		if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) {
@@ -816,37 +819,41 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 				max_rss = ICE_MAX_LG_RSS_QS;
 			else
 				max_rss = ICE_MAX_SMALL_RSS_QS;
-			qcount = min_t(int, numq_tc, max_rss);
-			qcount = min_t(int, qcount, vsi->rss_size);
+			qcount_rx = min_t(int, rx_numq_tc, max_rss);
+			qcount_rx = min_t(int, qcount_rx, vsi->rss_size);
 		}
 	}
 
 	/* find the (rounded up) power-of-2 of qcount */
-	pow = order_base_2(qcount);
+	pow = order_base_2(qcount_rx);
 
 	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
 		if (!(vsi->tc_cfg.ena_tc & BIT(i))) {
 			/* TC is not enabled */
 			vsi->tc_cfg.tc_info[i].qoffset = 0;
-			vsi->tc_cfg.tc_info[i].qcount = 1;
+			vsi->tc_cfg.tc_info[i].qcount_rx = 1;
+			vsi->tc_cfg.tc_info[i].qcount_tx = 1;
+			vsi->tc_cfg.tc_info[i].netdev_tc = 0;
 			ctxt->info.tc_mapping[i] = 0;
 			continue;
 		}
 
 		/* TC is enabled */
 		vsi->tc_cfg.tc_info[i].qoffset = offset;
-		vsi->tc_cfg.tc_info[i].qcount = qcount;
+		vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx;
+		vsi->tc_cfg.tc_info[i].qcount_tx = tx_numq_tc;
+		vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++;
 
 		qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) &
 			ICE_AQ_VSI_TC_Q_OFFSET_M) |
 			((pow << ICE_AQ_VSI_TC_Q_NUM_S) &
 			 ICE_AQ_VSI_TC_Q_NUM_M);
-		offset += qcount;
+		offset += qcount_rx;
+		tx_count += tx_numq_tc;
 		ctxt->info.tc_mapping[i] = cpu_to_le16(qmap);
 	}
-
-	vsi->num_txq = qcount_tx;
 	vsi->num_rxq = offset;
+	vsi->num_txq = tx_count;
 
 	if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) {
 		dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n");
@@ -907,37 +914,41 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
  */
 static int ice_vsi_init(struct ice_vsi *vsi)
 {
-	struct ice_vsi_ctx ctxt = { 0 };
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
+	struct ice_vsi_ctx *ctxt;
 	int ret = 0;
 
+	ctxt = devm_kzalloc(&pf->pdev->dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-		ctxt.flags = ICE_AQ_VSI_TYPE_PF;
+		ctxt->flags = ICE_AQ_VSI_TYPE_PF;
 		break;
 	case ICE_VSI_VF:
-		ctxt.flags = ICE_AQ_VSI_TYPE_VF;
+		ctxt->flags = ICE_AQ_VSI_TYPE_VF;
 		/* VF number here is the absolute VF number (0-255) */
-		ctxt.vf_num = vsi->vf_id + hw->func_caps.vf_base_id;
+		ctxt->vf_num = vsi->vf_id + hw->func_caps.vf_base_id;
 		break;
 	default:
 		return -ENODEV;
 	}
 
-	ice_set_dflt_vsi_ctx(&ctxt);
+	ice_set_dflt_vsi_ctx(ctxt);
 	/* if the switch is in VEB mode, allow VSI loopback */
 	if (vsi->vsw->bridge_mode == BRIDGE_MODE_VEB)
-		ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+		ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
 
 	/* Set LUT type and HASH type if RSS is enabled */
 	if (test_bit(ICE_FLAG_RSS_ENA, pf->flags))
-		ice_set_rss_vsi_ctx(&ctxt, vsi);
+		ice_set_rss_vsi_ctx(ctxt, vsi);
 
-	ctxt.info.sw_id = vsi->port_info->sw_id;
-	ice_vsi_setup_q_map(vsi, &ctxt);
+	ctxt->info.sw_id = vsi->port_info->sw_id;
+	ice_vsi_setup_q_map(vsi, ctxt);
 
-	ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL);
+	ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL);
 	if (ret) {
 		dev_err(&pf->pdev->dev,
 			"Add VSI failed, err %d\n", ret);
@@ -945,11 +956,12 @@ static int ice_vsi_init(struct ice_vsi *vsi)
 	}
 
 	/* keep context for update VSI operations */
-	vsi->info = ctxt.info;
+	vsi->info = ctxt->info;
 
 	/* record VSI number returned */
-	vsi->vsi_num = ctxt.vsi_num;
+	vsi->vsi_num = ctxt->vsi_num;
 
+	devm_kfree(&pf->pdev->dev, ctxt);
 	return ret;
 }
 
@@ -1000,7 +1012,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi)
  * @vsi: the VSI being configured
  * @v_idx: index of the vector in the VSI struct
  *
- * We allocate one q_vector.  If allocation fails we return -ENOMEM.
+ * We allocate one q_vector. If allocation fails we return -ENOMEM.
  */
 static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx)
 {
@@ -1039,7 +1051,7 @@ out:
  * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors
  * @vsi: the VSI being configured
  *
- * We allocate one q_vector per queue interrupt.  If allocation fails we
+ * We allocate one q_vector per queue interrupt. If allocation fails we
  * return -ENOMEM.
  */
 static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
@@ -1188,7 +1200,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 	struct ice_pf *pf = vsi->back;
 	int i;
 
-	/* Allocate tx_rings */
+	/* Allocate Tx rings */
 	for (i = 0; i < vsi->alloc_txq; i++) {
 		struct ice_ring *ring;
 
@@ -1207,7 +1219,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		vsi->tx_rings[i] = ring;
 	}
 
-	/* Allocate rx_rings */
+	/* Allocate Rx rings */
 	for (i = 0; i < vsi->alloc_rxq; i++) {
 		struct ice_ring *ring;
 
@@ -1602,64 +1614,73 @@ setup_rings:
 /**
  * ice_vsi_cfg_txqs - Configure the VSI for Tx
  * @vsi: the VSI being configured
+ * @rings: Tx ring array to be configured
+ * @offset: offset within vsi->txq_map
  *
  * Return 0 on success and a negative value on error
  * Configure the Tx VSI for operation.
  */
-int ice_vsi_cfg_txqs(struct ice_vsi *vsi)
+static int
+ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, int offset)
 {
 	struct ice_aqc_add_tx_qgrp *qg_buf;
 	struct ice_aqc_add_txqs_perq *txq;
 	struct ice_pf *pf = vsi->back;
+	u8 num_q_grps, q_idx = 0;
 	enum ice_status status;
 	u16 buf_len, i, pf_q;
-	int err = 0, tc = 0;
-	u8 num_q_grps;
+	int err = 0, tc;
 
-	buf_len = sizeof(struct ice_aqc_add_tx_qgrp);
+	buf_len = sizeof(*qg_buf);
 	qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL);
 	if (!qg_buf)
 		return -ENOMEM;
 
-	if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) {
-		err = -EINVAL;
-		goto err_cfg_txqs;
-	}
 	qg_buf->num_txqs = 1;
 	num_q_grps = 1;
 
-	/* set up and configure the Tx queues */
-	ice_for_each_txq(vsi, i) {
-		struct ice_tlan_ctx tlan_ctx = { 0 };
+	/* set up and configure the Tx queues for each enabled TC */
+	for (tc = 0; tc < ICE_MAX_TRAFFIC_CLASS; tc++) {
+		if (!(vsi->tc_cfg.ena_tc & BIT(tc)))
+			break;
 
-		pf_q = vsi->txq_map[i];
-		ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q);
-		/* copy context contents into the qg_buf */
-		qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
-		ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
-			    ice_tlan_ctx_info);
+		for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) {
+			struct ice_tlan_ctx tlan_ctx = { 0 };
+
+			pf_q = vsi->txq_map[q_idx + offset];
+			ice_setup_tx_ctx(rings[q_idx], &tlan_ctx, pf_q);
+			/* copy context contents into the qg_buf */
+			qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q);
+			ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx,
+				    ice_tlan_ctx_info);
+
+			/* init queue specific tail reg. It is referred as
+			 * transmit comm scheduler queue doorbell.
+			 */
+			rings[q_idx]->tail =
+				pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
+			status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
+						 num_q_grps, qg_buf, buf_len,
+						 NULL);
+			if (status) {
+				dev_err(&vsi->back->pdev->dev,
+					"Failed to set LAN Tx queue context, error: %d\n",
+					status);
+				err = -ENODEV;
+				goto err_cfg_txqs;
+			}
 
-		/* init queue specific tail reg. It is referred as transmit
-		 * comm scheduler queue doorbell.
-		 */
-		vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q);
-		status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc,
-					 num_q_grps, qg_buf, buf_len, NULL);
-		if (status) {
-			dev_err(&vsi->back->pdev->dev,
-				"Failed to set LAN Tx queue context, error: %d\n",
-				status);
-			err = -ENODEV;
-			goto err_cfg_txqs;
-		}
+			/* Add Tx Queue TEID into the VSI Tx ring from the
+			 * response. This will complete configuring and
+			 * enabling the queue.
+			 */
+			txq = &qg_buf->txqs[0];
+			if (pf_q == le16_to_cpu(txq->txq_id))
+				rings[q_idx]->txq_teid =
+					le32_to_cpu(txq->q_teid);
 
-		/* Add Tx Queue TEID into the VSI Tx ring from the response
-		 * This will complete configuring and enabling the queue.
-		 */
-		txq = &qg_buf->txqs[0];
-		if (pf_q == le16_to_cpu(txq->txq_id))
-			vsi->tx_rings[i]->txq_teid =
-				le32_to_cpu(txq->q_teid);
+			q_idx++;
+		}
 	}
 err_cfg_txqs:
 	devm_kfree(&pf->pdev->dev, qg_buf);
@@ -1667,6 +1688,18 @@ err_cfg_txqs:
 }
 
 /**
+ * ice_vsi_cfg_lan_txqs - Configure the VSI for Tx
+ * @vsi: the VSI being configured
+ *
+ * Return 0 on success and a negative value on error
+ * Configure the Tx VSI for operation.
+ */
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi)
+{
+	return ice_vsi_cfg_txqs(vsi, vsi->tx_rings, 0);
+}
+
+/**
  * ice_intrl_usec_to_reg - convert interrupt rate limit to register value
  * @intrl: interrupt rate limit in usecs
  * @gran: interrupt rate limit granularity in usecs
@@ -1695,22 +1728,34 @@ static u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran)
 static void
 ice_cfg_itr(struct ice_hw *hw, struct ice_q_vector *q_vector, u16 vector)
 {
-	u8 itr_gran = hw->itr_gran;
-
 	if (q_vector->num_ring_rx) {
 		struct ice_ring_container *rc = &q_vector->rx;
 
-		rc->itr = ITR_TO_REG(ICE_DFLT_RX_ITR, itr_gran);
+		/* if this value is set then don't overwrite with default */
+		if (!rc->itr_setting)
+			rc->itr_setting = ICE_DFLT_RX_ITR;
+
+		rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		rc->next_update = jiffies + 1;
+		rc->current_itr = rc->target_itr;
 		rc->latency_range = ICE_LOW_LATENCY;
-		wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr);
+		wr32(hw, GLINT_ITR(rc->itr_idx, vector),
+		     ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
 	}
 
 	if (q_vector->num_ring_tx) {
 		struct ice_ring_container *rc = &q_vector->tx;
 
-		rc->itr = ITR_TO_REG(ICE_DFLT_TX_ITR, itr_gran);
+		/* if this value is set then don't overwrite with default */
+		if (!rc->itr_setting)
+			rc->itr_setting = ICE_DFLT_TX_ITR;
+
+		rc->target_itr = ITR_TO_REG(rc->itr_setting);
+		rc->next_update = jiffies + 1;
+		rc->current_itr = rc->target_itr;
 		rc->latency_range = ICE_LOW_LATENCY;
-		wr32(hw, GLINT_ITR(rc->itr_idx, vector), rc->itr);
+		wr32(hw, GLINT_ITR(rc->itr_idx, vector),
+		     ITR_REG_ALIGN(rc->current_itr) >> ICE_ITR_GRAN_S);
 	}
 }
 
@@ -1789,26 +1834,34 @@ int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi)
 {
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
+
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
 
 	/* Here we are configuring the VSI to let the driver add VLAN tags by
 	 * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag
 	 * insertion happens in the Tx hot path, in ice_tx_map.
 	 */
-	ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL;
+	ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL;
 
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
 			status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	vsi->info.vlan_flags = ctxt.info.vlan_flags;
-	return 0;
+	vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -1820,35 +1873,42 @@ int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena)
 {
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
+
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
 
 	/* Here we are configuring what the VSI should do with the VLAN tag in
 	 * the Rx packet. We can either leave the tag in the packet or put it in
 	 * the Rx descriptor.
 	 */
-	if (ena) {
+	if (ena)
 		/* Strip VLAN tag from Rx packet and put it in the desc */
-		ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH;
-	} else {
+		ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH;
+	else
 		/* Disable stripping. Leave tag in packet */
-		ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
-	}
+		ctxt->info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING;
 
 	/* Allow all packets untagged/tagged */
-	ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
+	ctxt->info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL;
 
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(dev, "update VSI for VLAN strip failed, ena = %d err %d aq_err %d\n",
 			ena, status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	vsi->info.vlan_flags = ctxt.info.vlan_flags;
-	return 0;
+	vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -1878,9 +1938,12 @@ int ice_vsi_stop_rx_rings(struct ice_vsi *vsi)
  * @vsi: the VSI being configured
  * @rst_src: reset source
  * @rel_vmvf_num: Relative id of VF/VM
+ * @rings: Tx ring array to be stopped
+ * @offset: offset within vsi->txq_map
  */
-int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
-			  u16 rel_vmvf_num)
+static int
+ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+		      u16 rel_vmvf_num, struct ice_ring **rings, int offset)
 {
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
@@ -1908,18 +1971,18 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 	ice_for_each_txq(vsi, i) {
 		u16 v_idx;
 
-		if (!vsi->tx_rings || !vsi->tx_rings[i]) {
+		if (!rings || !rings[i] || !rings[i]->q_vector) {
 			err = -EINVAL;
 			goto err_out;
 		}
 
-		q_ids[i] = vsi->txq_map[i];
-		q_teids[i] = vsi->tx_rings[i]->txq_teid;
+		q_ids[i] = vsi->txq_map[i + offset];
+		q_teids[i] = rings[i]->txq_teid;
 
 		/* clear cause_ena bit for disabled queues */
-		val = rd32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx));
+		val = rd32(hw, QINT_TQCTL(rings[i]->reg_idx));
 		val &= ~QINT_TQCTL_CAUSE_ENA_M;
-		wr32(hw, QINT_TQCTL(vsi->tx_rings[i]->reg_idx), val);
+		wr32(hw, QINT_TQCTL(rings[i]->reg_idx), val);
 
 		/* software is expected to wait for 100 ns */
 		ndelay(100);
@@ -1927,7 +1990,7 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 		/* trigger a software interrupt for the vector associated to
 		 * the queue to schedule NAPI handler
 		 */
-		v_idx = vsi->tx_rings[i]->q_vector->v_idx;
+		v_idx = rings[i]->q_vector->v_idx;
 		wr32(hw, GLINT_DYN_CTL(vsi->hw_base_vector + v_idx),
 		     GLINT_DYN_CTL_SWINT_TRIG_M | GLINT_DYN_CTL_INTENA_MSK_M);
 	}
@@ -1957,6 +2020,19 @@ err_alloc_q_ids:
 }
 
 /**
+ * ice_vsi_stop_lan_tx_rings - Disable LAN Tx rings
+ * @vsi: the VSI being configured
+ * @rst_src: reset source
+ * @rel_vmvf_num: Relative id of VF/VM
+ */
+int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi,
+			      enum ice_disq_rst_src rst_src, u16 rel_vmvf_num)
+{
+	return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings,
+				     0);
+}
+
+/**
  * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI
  * @vsi: VSI to enable or disable VLAN pruning on
  * @ena: set to true to enable VLAN pruning and false to disable it
@@ -2056,6 +2132,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 	/* set RSS capabilities */
 	ice_vsi_set_rss_params(vsi);
 
+	/* set tc configuration */
+	ice_vsi_set_tc_cfg(vsi);
+
 	/* create the VSI */
 	ret = ice_vsi_init(vsi);
 	if (ret)
@@ -2113,17 +2192,13 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
 		pf->q_left_rx -= vsi->alloc_rxq;
 		break;
 	default:
-		/* if VSI type is not recognized, clean up the resources and
-		 * exit
-		 */
+		/* clean up the resources and exit */
 		goto unroll_vsi_init;
 	}
 
-	ice_vsi_set_tc_cfg(vsi);
-
 	/* configure VSI nodes based on number of queues and TC's */
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
-		max_txqs[i] = vsi->num_txq;
+		max_txqs[i] = pf->num_lan_tx;
 
 	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			      max_txqs);
@@ -2314,7 +2389,7 @@ static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id)
 	int start = res->search_hint;
 	int end = start;
 
-	if ((start + needed) >  res->num_entries)
+	if ((start + needed) > res->num_entries)
 		return -ENOMEM;
 
 	id |= ICE_RES_VALID_BIT;
@@ -2443,13 +2518,15 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi)
  */
 int ice_vsi_release(struct ice_vsi *vsi)
 {
+	struct ice_vf *vf = NULL;
 	struct ice_pf *pf;
-	struct ice_vf *vf;
 
 	if (!vsi->back)
 		return -ENODEV;
 	pf = vsi->back;
-	vf = &pf->vf[vsi->vf_id];
+
+	if (vsi->type == ICE_VSI_VF)
+		vf = &pf->vf[vsi->vf_id];
 	/* do not unregister and free netdevs while driver is in the reset
 	 * recovery pending state. Since reset/rebuild happens through PF
 	 * service task workqueue, its not a good idea to unregister netdev
@@ -2491,6 +2568,7 @@ int ice_vsi_release(struct ice_vsi *vsi)
 	}
 
 	ice_remove_vsi_fltr(&pf->hw, vsi->idx);
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_delete(vsi);
 	ice_vsi_free_q_vectors(vsi);
 	ice_vsi_clear_rings(vsi);
@@ -2518,11 +2596,14 @@ int ice_vsi_release(struct ice_vsi *vsi)
 int ice_vsi_rebuild(struct ice_vsi *vsi)
 {
 	u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
+	struct ice_pf *pf;
 	int ret, i;
 
 	if (!vsi)
 		return -EINVAL;
 
+	pf = vsi->back;
+	ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
 	ice_vsi_free_q_vectors(vsi);
 	ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx);
 	ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx);
@@ -2532,6 +2613,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 	ice_vsi_free_arrays(vsi, false);
 	ice_dev_onetime_setup(&vsi->back->hw);
 	ice_vsi_set_num_qs(vsi);
+	ice_vsi_set_tc_cfg(vsi);
 
 	/* Initialize VSI struct elements and create VSI in FW */
 	ret = ice_vsi_init(vsi);
@@ -2557,6 +2639,12 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 			goto err_vectors;
 
 		ice_vsi_map_rings_to_vectors(vsi);
+		/* Do not exit if configuring RSS had an issue, at least
+		 * receive traffic on first queue. Hence no need to capture
+		 * return value
+		 */
+		if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags))
+			ice_vsi_cfg_rss_lut_key(vsi);
 		break;
 	case ICE_VSI_VF:
 		ret = ice_vsi_alloc_q_vectors(vsi);
@@ -2578,11 +2666,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 		break;
 	}
 
-	ice_vsi_set_tc_cfg(vsi);
-
 	/* configure VSI nodes based on number of queues and TC's */
 	for (i = 0; i < vsi->tc_cfg.numtc; i++)
-		max_txqs[i] = vsi->num_txq;
+		max_txqs[i] = pf->num_lan_tx;
 
 	ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc,
 			      max_txqs);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index 3831b4f0960a..7988a53729a9 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -15,7 +15,7 @@ void ice_update_eth_stats(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
 
-int ice_vsi_cfg_txqs(struct ice_vsi *vsi);
+int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
 
 void ice_vsi_cfg_msix(struct ice_vsi *vsi);
 
@@ -31,7 +31,8 @@ int ice_vsi_start_rx_rings(struct ice_vsi *vsi);
 
 int ice_vsi_stop_rx_rings(struct ice_vsi *vsi);
 
-int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
+int
+ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src,
 			  u16 rel_vmvf_num);
 
 int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 333312a1d595..47cc3f905b7f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -349,6 +349,9 @@ ice_prepare_for_reset(struct ice_pf *pf)
 	/* disable the VSIs and their queues that are not already DOWN */
 	ice_pf_dis_all_vsi(pf);
 
+	if (hw->port_info)
+		ice_sched_clear_port(hw->port_info);
+
 	ice_shutdown_all_ctrlq(hw);
 
 	set_bit(__ICE_PREPARED_FOR_RESET, pf->state);
@@ -405,7 +408,7 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	/* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an
 	 * OICR interrupt. The OICR handler (ice_misc_intr) determines what type
 	 * of reset is pending and sets bits in pf->state indicating the reset
-	 * type and __ICE_RESET_OICR_RECV.  So, if the latter bit is set
+	 * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set
 	 * prepare for pending reset if not already (for PF software-initiated
 	 * global resets the software should already be prepared for it as
 	 * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated
@@ -606,7 +609,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi)
 		}
 	}
 
-	ice_vc_notify_link_state(pf);
+	if (!new_link_same_as_old && pf->num_alloc_vfs)
+		ice_vc_notify_link_state(pf);
 
 	return 0;
 }
@@ -1353,14 +1357,39 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 }
 
 /**
+ * ice_dis_ctrlq_interrupts - disable control queue interrupts
+ * @hw: pointer to HW structure
+ */
+static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
+{
+	/* disable Admin queue Interrupt causes */
+	wr32(hw, PFINT_FW_CTL,
+	     rd32(hw, PFINT_FW_CTL) & ~PFINT_FW_CTL_CAUSE_ENA_M);
+
+	/* disable Mailbox queue Interrupt causes */
+	wr32(hw, PFINT_MBX_CTL,
+	     rd32(hw, PFINT_MBX_CTL) & ~PFINT_MBX_CTL_CAUSE_ENA_M);
+
+	/* disable Control queue Interrupt causes */
+	wr32(hw, PFINT_OICR_CTL,
+	     rd32(hw, PFINT_OICR_CTL) & ~PFINT_OICR_CTL_CAUSE_ENA_M);
+
+	ice_flush(hw);
+}
+
+/**
  * ice_free_irq_msix_misc - Unroll misc vector setup
  * @pf: board private structure
  */
 static void ice_free_irq_msix_misc(struct ice_pf *pf)
 {
+	struct ice_hw *hw = &pf->hw;
+
+	ice_dis_ctrlq_interrupts(hw);
+
 	/* disable OICR interrupt */
-	wr32(&pf->hw, PFINT_OICR_ENA, 0);
-	ice_flush(&pf->hw);
+	wr32(hw, PFINT_OICR_ENA, 0);
+	ice_flush(hw);
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) {
 		synchronize_irq(pf->msix_entries[pf->sw_oicr_idx].vector);
@@ -1375,19 +1404,43 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
 }
 
 /**
+ * ice_ena_ctrlq_interrupts - enable control queue interrupts
+ * @hw: pointer to HW structure
+ * @v_idx: HW vector index to associate the control queue interrupts with
+ */
+static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 v_idx)
+{
+	u32 val;
+
+	val = ((v_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
+	       PFINT_OICR_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_OICR_CTL, val);
+
+	/* enable Admin queue Interrupt causes */
+	val = ((v_idx & PFINT_FW_CTL_MSIX_INDX_M) |
+	       PFINT_FW_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_FW_CTL, val);
+
+	/* enable Mailbox queue Interrupt causes */
+	val = ((v_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
+	       PFINT_MBX_CTL_CAUSE_ENA_M);
+	wr32(hw, PFINT_MBX_CTL, val);
+
+	ice_flush(hw);
+}
+
+/**
  * ice_req_irq_msix_misc - Setup the misc vector to handle non queue events
  * @pf: board private structure
  *
  * This sets up the handler for MSIX 0, which is used to manage the
- * non-queue interrupts, e.g. AdminQ and errors.  This is not used
+ * non-queue interrupts, e.g. AdminQ and errors. This is not used
  * when in MSI or Legacy interrupt mode.
  */
 static int ice_req_irq_msix_misc(struct ice_pf *pf)
 {
 	struct ice_hw *hw = &pf->hw;
 	int oicr_idx, err = 0;
-	u8 itr_gran;
-	u32 val;
 
 	if (!pf->int_name[0])
 		snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
@@ -1436,24 +1489,9 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
 skip_req_irq:
 	ice_ena_misc_vector(pf);
 
-	val = ((pf->hw_oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) |
-	       PFINT_OICR_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_OICR_CTL, val);
-
-	/* This enables Admin queue Interrupt causes */
-	val = ((pf->hw_oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) |
-	       PFINT_FW_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_FW_CTL, val);
-
-	/* This enables Mailbox queue Interrupt causes */
-	val = ((pf->hw_oicr_idx & PFINT_MBX_CTL_MSIX_INDX_M) |
-	       PFINT_MBX_CTL_CAUSE_ENA_M);
-	wr32(hw, PFINT_MBX_CTL, val);
-
-	itr_gran = hw->itr_gran;
-
+	ice_ena_ctrlq_interrupts(hw, pf->hw_oicr_idx);
 	wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->hw_oicr_idx),
-	     ITR_TO_REG(ICE_ITR_8K, itr_gran));
+	     ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
 
 	ice_flush(hw);
 	ice_irq_dynamic_ena(hw, NULL, NULL);
@@ -1513,8 +1551,8 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 	u8 mac_addr[ETH_ALEN];
 	int err;
 
-	netdev = alloc_etherdev_mqs(sizeof(struct ice_netdev_priv),
-				    vsi->alloc_txq, vsi->alloc_rxq);
+	netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq,
+				    vsi->alloc_rxq);
 	if (!netdev)
 		return -ENOMEM;
 
@@ -1528,6 +1566,7 @@ static int ice_cfg_netdev(struct ice_vsi *vsi)
 
 	csumo_features = NETIF_F_RXCSUM	  |
 			 NETIF_F_IP_CSUM  |
+			 NETIF_F_SCTP_CRC |
 			 NETIF_F_IPV6_CSUM;
 
 	vlano_features = NETIF_F_HW_VLAN_CTAG_FILTER |
@@ -1783,7 +1822,7 @@ static void ice_determine_q_usage(struct ice_pf *pf)
 
 	pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus());
 
-	/* only 1 rx queue unless RSS is enabled */
+	/* only 1 Rx queue unless RSS is enabled */
 	if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags))
 		pf->num_lan_rx = 1;
 	else
@@ -1866,7 +1905,7 @@ static int ice_ena_msix_range(struct ice_pf *pf)
 	v_left -= pf->num_lan_msix;
 
 	pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget,
-					sizeof(struct msix_entry), GFP_KERNEL);
+					sizeof(*pf->msix_entries), GFP_KERNEL);
 
 	if (!pf->msix_entries) {
 		err = -ENOMEM;
@@ -1954,7 +1993,6 @@ static void ice_clear_interrupt_scheme(struct ice_pf *pf)
 static int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
 	int vectors = 0, hw_vectors = 0;
-	ssize_t size;
 
 	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
 		vectors = ice_ena_msix_range(pf);
@@ -1965,9 +2003,9 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 		return vectors;
 
 	/* set up vector assignment tracking */
-	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * vectors);
-
-	pf->sw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+	pf->sw_irq_tracker =
+		devm_kzalloc(&pf->pdev->dev, sizeof(*pf->sw_irq_tracker) +
+			     (sizeof(u16) * vectors), GFP_KERNEL);
 	if (!pf->sw_irq_tracker) {
 		ice_dis_msix(pf);
 		return -ENOMEM;
@@ -1979,9 +2017,9 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 
 	/* set up HW vector assignment tracking */
 	hw_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	size = sizeof(struct ice_res_tracker) + (sizeof(u16) * hw_vectors);
-
-	pf->hw_irq_tracker = devm_kzalloc(&pf->pdev->dev, size, GFP_KERNEL);
+	pf->hw_irq_tracker =
+		devm_kzalloc(&pf->pdev->dev, sizeof(*pf->hw_irq_tracker) +
+			     (sizeof(u16) * hw_vectors), GFP_KERNEL);
 	if (!pf->hw_irq_tracker) {
 		ice_clear_interrupt_scheme(pf);
 		return -ENOMEM;
@@ -1995,6 +2033,23 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf)
 }
 
 /**
+ * ice_verify_itr_gran - verify driver's assumption of ITR granularity
+ * @pf: pointer to the PF structure
+ *
+ * There is no error returned here because the driver will be able to handle a
+ * different ITR granularity, but interrupt moderation will not be accurate if
+ * the driver's assumptions are not verified. This assumption is made so we can
+ * use constants in the hot path instead of accessing structure members.
+ */
+static void ice_verify_itr_gran(struct ice_pf *pf)
+{
+	if (pf->hw.itr_gran != (ICE_ITR_GRAN_S << 1))
+		dev_warn(&pf->pdev->dev,
+			 "%d ITR granularity assumption is invalid, actual ITR granularity is %d. Interrupt moderation will be inaccurate!\n",
+			 (ICE_ITR_GRAN_S << 1), pf->hw.itr_gran);
+}
+
+/**
  * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines
  * @pf: pointer to the PF structure
  *
@@ -2091,15 +2146,14 @@ static int ice_probe(struct pci_dev *pdev,
 
 	ice_determine_q_usage(pf);
 
-	pf->num_alloc_vsi = min_t(u16, ICE_MAX_VSI_ALLOC,
-				  hw->func_caps.guaranteed_num_vsi);
+	pf->num_alloc_vsi = hw->func_caps.guar_num_vsi;
 	if (!pf->num_alloc_vsi) {
 		err = -EIO;
 		goto err_init_pf_unroll;
 	}
 
 	pf->vsi = devm_kcalloc(&pdev->dev, pf->num_alloc_vsi,
-			       sizeof(struct ice_vsi *), GFP_KERNEL);
+			       sizeof(*pf->vsi), GFP_KERNEL);
 	if (!pf->vsi) {
 		err = -ENOMEM;
 		goto err_init_pf_unroll;
@@ -2131,7 +2185,7 @@ static int ice_probe(struct pci_dev *pdev,
 	}
 
 	/* create switch struct for the switch element created by FW on boot */
-	pf->first_sw = devm_kzalloc(&pdev->dev, sizeof(struct ice_sw),
+	pf->first_sw = devm_kzalloc(&pdev->dev, sizeof(*pf->first_sw),
 				    GFP_KERNEL);
 	if (!pf->first_sw) {
 		err = -ENOMEM;
@@ -2161,6 +2215,7 @@ static int ice_probe(struct pci_dev *pdev,
 	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
 	ice_verify_cacheline_size(pf);
+	ice_verify_itr_gran(pf);
 
 	return 0;
 
@@ -2417,10 +2472,12 @@ static void ice_set_rx_mode(struct net_device *netdev)
  * @addr: the MAC address entry being added
  * @vid: VLAN id
  * @flags: instructions from stack about fdb operation
+ * @extack: netlink extended ack
  */
-static int ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
-		       struct net_device *dev, const unsigned char *addr,
-		       u16 vid, u16 flags)
+static int
+ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
+	    struct net_device *dev, const unsigned char *addr, u16 vid,
+	    u16 flags, struct netlink_ext_ack __always_unused *extack)
 {
 	int err;
 
@@ -2545,7 +2602,7 @@ static int ice_vsi_cfg(struct ice_vsi *vsi)
 			return err;
 	}
 
-	err = ice_vsi_cfg_txqs(vsi);
+	err = ice_vsi_cfg_lan_txqs(vsi);
 	if (!err)
 		err = ice_vsi_cfg_rxqs(vsi);
 
@@ -2563,8 +2620,12 @@ static void ice_napi_enable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_enable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_enable(&q_vector->napi);
+	}
 }
 
 /**
@@ -2931,8 +2992,91 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
 	if (!vsi->netdev)
 		return;
 
-	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++)
-		napi_disable(&vsi->q_vectors[q_idx]->napi);
+	for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
+
+		if (q_vector->rx.ring || q_vector->tx.ring)
+			napi_disable(&q_vector->napi);
+	}
+}
+
+/**
+ * ice_force_phys_link_state - Force the physical link state
+ * @vsi: VSI to force the physical link state to up/down
+ * @link_up: true/false indicates to set the physical link to up/down
+ *
+ * Force the physical link state by getting the current PHY capabilities from
+ * hardware and setting the PHY config based on the determined capabilities. If
+ * link changes a link event will be triggered because both the Enable Automatic
+ * Link Update and LESM Enable bits are set when setting the PHY capabilities.
+ *
+ * Returns 0 on success, negative on failure
+ */
+static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up)
+{
+	struct ice_aqc_get_phy_caps_data *pcaps;
+	struct ice_aqc_set_phy_cfg_data *cfg;
+	struct ice_port_info *pi;
+	struct device *dev;
+	int retcode;
+
+	if (!vsi || !vsi->port_info || !vsi->back)
+		return -EINVAL;
+	if (vsi->type != ICE_VSI_PF)
+		return 0;
+
+	dev = &vsi->back->pdev->dev;
+
+	pi = vsi->port_info;
+
+	pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL);
+	if (!pcaps)
+		return -ENOMEM;
+
+	retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps,
+				      NULL);
+	if (retcode) {
+		dev_err(dev,
+			"Failed to get phy capabilities, VSI %d error %d\n",
+			vsi->vsi_num, retcode);
+		retcode = -EIO;
+		goto out;
+	}
+
+	/* No change in link */
+	if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) &&
+	    link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP))
+		goto out;
+
+	cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL);
+	if (!cfg) {
+		retcode = -ENOMEM;
+		goto out;
+	}
+
+	cfg->phy_type_low = pcaps->phy_type_low;
+	cfg->phy_type_high = pcaps->phy_type_high;
+	cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT;
+	cfg->low_power_ctrl = pcaps->low_power_ctrl;
+	cfg->eee_cap = pcaps->eee_cap;
+	cfg->eeer_value = pcaps->eeer_value;
+	cfg->link_fec_opt = pcaps->link_fec_options;
+	if (link_up)
+		cfg->caps |= ICE_AQ_PHY_ENA_LINK;
+	else
+		cfg->caps &= ~ICE_AQ_PHY_ENA_LINK;
+
+	retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL);
+	if (retcode) {
+		dev_err(dev, "Failed to set phy config, VSI %d error %d\n",
+			vsi->vsi_num, retcode);
+		retcode = -EIO;
+	}
+
+	devm_kfree(dev, cfg);
+out:
+	devm_kfree(dev, pcaps);
+	return retcode;
 }
 
 /**
@@ -2941,7 +3085,7 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
  */
 int ice_down(struct ice_vsi *vsi)
 {
-	int i, tx_err, rx_err;
+	int i, tx_err, rx_err, link_err = 0;
 
 	/* Caller of this function is expected to set the
 	 * vsi->state __ICE_DOWN bit
@@ -2952,7 +3096,8 @@ int ice_down(struct ice_vsi *vsi)
 	}
 
 	ice_vsi_dis_irq(vsi);
-	tx_err = ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, 0);
+
+	tx_err = ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, 0);
 	if (tx_err)
 		netdev_err(vsi->netdev,
 			   "Failed stop Tx rings, VSI %d error %d\n",
@@ -2966,13 +3111,21 @@ int ice_down(struct ice_vsi *vsi)
 
 	ice_napi_disable_all(vsi);
 
+	if (test_bit(ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, vsi->back->flags)) {
+		link_err = ice_force_phys_link_state(vsi, false);
+		if (link_err)
+			netdev_err(vsi->netdev,
+				   "Failed to set physical link down, VSI %d error %d\n",
+				   vsi->vsi_num, link_err);
+	}
+
 	ice_for_each_txq(vsi, i)
 		ice_clean_tx_ring(vsi->tx_rings[i]);
 
 	ice_for_each_rxq(vsi, i)
 		ice_clean_rx_ring(vsi->rx_rings[i]);
 
-	if (tx_err || rx_err) {
+	if (tx_err || rx_err || link_err) {
 		netdev_err(vsi->netdev,
 			   "Failed to close VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
@@ -3138,8 +3291,9 @@ static void ice_vsi_release_all(struct ice_pf *pf)
 /**
  * ice_dis_vsi - pause a VSI
  * @vsi: the VSI being paused
+ * @locked: is the rtnl_lock already held
  */
-static void ice_dis_vsi(struct ice_vsi *vsi)
+static void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
 {
 	if (test_bit(__ICE_DOWN, vsi->state))
 		return;
@@ -3148,9 +3302,13 @@ static void ice_dis_vsi(struct ice_vsi *vsi)
 
 	if (vsi->type == ICE_VSI_PF && vsi->netdev) {
 		if (netif_running(vsi->netdev)) {
-			rtnl_lock();
-			vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
-			rtnl_unlock();
+			if (!locked) {
+				rtnl_lock();
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+				rtnl_unlock();
+			} else {
+				vsi->netdev->netdev_ops->ndo_stop(vsi->netdev);
+			}
 		} else {
 			ice_vsi_close(vsi);
 		}
@@ -3189,7 +3347,7 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf)
 
 	ice_for_each_vsi(pf, v)
 		if (pf->vsi[v])
-			ice_dis_vsi(pf->vsi[v]);
+			ice_dis_vsi(pf->vsi[v], false);
 }
 
 /**
@@ -3587,30 +3745,39 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_aqc_vsi_props *vsi_props;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
 
 	vsi_props = &vsi->info;
-	ctxt.info = vsi->info;
+
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
+
+	ctxt->info = vsi->info;
 
 	if (bmode == BRIDGE_MODE_VEB)
 		/* change from VEPA to VEB mode */
-		ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+		ctxt->info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
 	else
 		/* change from VEB to VEPA mode */
-		ctxt.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
+		ctxt->info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB;
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID);
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n",
 			bmode, status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 	/* Update sw flags for book keeping */
-	vsi_props->sw_flags = ctxt.info.sw_flags;
+	vsi_props->sw_flags = ctxt->info.sw_flags;
 
-	return 0;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -3618,6 +3785,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
  * @dev: the netdev being configured
  * @nlh: RTNL message
  * @flags: bridge setlink flags
+ * @extack: netlink extended ack
  *
  * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is
  * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if
@@ -3626,7 +3794,8 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode)
  */
 static int
 ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
-		   u16 __always_unused flags)
+		   u16 __always_unused flags,
+		   struct netlink_ext_ack __always_unused *extack)
 {
 	struct ice_netdev_priv *np = netdev_priv(dev);
 	struct ice_pf *pf = np->vsi->back;
@@ -3668,7 +3837,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
 		 */
 		status = ice_update_sw_rule_bridge_mode(hw);
 		if (status) {
-			netdev_err(dev, "update SW_RULE for bridge mode failed,  = %d err %d aq_err %d\n",
+			netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %d\n",
 				   mode, status, hw->adminq.sq_last_status);
 			/* revert hw->evb_veb */
 			hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB);
@@ -3691,40 +3860,36 @@ static void ice_tx_timeout(struct net_device *netdev)
 	struct ice_ring *tx_ring = NULL;
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
-	u32 head, val = 0, i;
 	int hung_queue = -1;
+	u32 i;
 
 	pf->tx_timeout_count++;
 
-	/* find the stopped queue the same way the stack does */
+	/* find the stopped queue the same way dev_watchdog() does */
 	for (i = 0; i < netdev->num_tx_queues; i++) {
-		struct netdev_queue *q;
 		unsigned long trans_start;
+		struct netdev_queue *q;
 
 		q = netdev_get_tx_queue(netdev, i);
 		trans_start = q->trans_start;
 		if (netif_xmit_stopped(q) &&
 		    time_after(jiffies,
-			       (trans_start + netdev->watchdog_timeo))) {
+			       trans_start + netdev->watchdog_timeo)) {
 			hung_queue = i;
 			break;
 		}
 	}
 
-	if (i == netdev->num_tx_queues) {
+	if (i == netdev->num_tx_queues)
 		netdev_info(netdev, "tx_timeout: no netdev hung queue found\n");
-	} else {
+	else
 		/* now that we have an index, find the tx_ring struct */
-		for (i = 0; i < vsi->num_txq; i++) {
-			if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) {
-				if (hung_queue ==
-				    vsi->tx_rings[i]->q_index) {
+		for (i = 0; i < vsi->num_txq; i++)
+			if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc)
+				if (hung_queue == vsi->tx_rings[i]->q_index) {
 					tx_ring = vsi->tx_rings[i];
 					break;
 				}
-			}
-		}
-	}
 
 	/* Reset recovery level if enough time has elapsed after last timeout.
 	 * Also ensure no new reset action happens before next timeout period.
@@ -3736,17 +3901,20 @@ static void ice_tx_timeout(struct net_device *netdev)
 		return;
 
 	if (tx_ring) {
-		head = tx_ring->next_to_clean;
+		struct ice_hw *hw = &pf->hw;
+		u32 head, val = 0;
+
+		head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) &
+			QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
 		/* Read interrupt register */
 		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-			val = rd32(&pf->hw,
+			val = rd32(hw,
 				   GLINT_DYN_CTL(tx_ring->q_vector->v_idx +
-					tx_ring->vsi->hw_base_vector));
+						 tx_ring->vsi->hw_base_vector));
 
-		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n",
+		netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
 			    vsi->vsi_num, hung_queue, tx_ring->next_to_clean,
-			    head, tx_ring->next_to_use,
-			    readl(tx_ring->tail), val);
+			    head, tx_ring->next_to_use, val);
 	}
 
 	pf->tx_timeout_last_recovery = jiffies;
@@ -3780,7 +3948,7 @@ static void ice_tx_timeout(struct net_device *netdev)
  * @netdev: network interface device structure
  *
  * The open entry point is called when a network interface is made
- * active by the system (IFF_UP).  At this point all resources needed
+ * active by the system (IFF_UP). At this point all resources needed
  * for transmit and receive operations are allocated, the interrupt
  * handler is registered with the OS, the netdev watchdog is enabled,
  * and the stack is notified that the interface is ready.
@@ -3800,8 +3968,14 @@ static int ice_open(struct net_device *netdev)
 
 	netif_carrier_off(netdev);
 
-	err = ice_vsi_open(vsi);
+	err = ice_force_phys_link_state(vsi, true);
+	if (err) {
+		netdev_err(netdev,
+			   "Failed to set physical link up, error %d\n", err);
+		return err;
+	}
 
+	err = ice_vsi_open(vsi);
 	if (err)
 		netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n",
 			   vsi->vsi_num, vsi->vsw->sw_id);
@@ -3813,7 +3987,7 @@ static int ice_open(struct net_device *netdev)
  * @netdev: network interface device structure
  *
  * The stop entry point is called when an interface is de-activated by the OS,
- * and the netdevice enters the DOWN state.  The hardware is still under the
+ * and the netdevice enters the DOWN state. The hardware is still under the
  * driver's control, but the netdev interface is disabled.
  *
  * Returns success only - not allowed to fail
@@ -3842,14 +4016,14 @@ ice_features_check(struct sk_buff *skb,
 	size_t len;
 
 	/* No point in doing any of this if neither checksum nor GSO are
-	 * being requested for this frame.  We can rule out both by just
+	 * being requested for this frame. We can rule out both by just
 	 * checking for CHECKSUM_PARTIAL
 	 */
 	if (skb->ip_summed != CHECKSUM_PARTIAL)
 		return features;
 
 	/* We cannot support GSO if the MSS is going to be less than
-	 * 64 bytes.  If it is then we need to drop support for GSO.
+	 * 64 bytes. If it is then we need to drop support for GSO.
 	 */
 	if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64))
 		features &= ~NETIF_F_GSO_MASK;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 3274c543283c..413fdbbcc4d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -125,6 +125,63 @@ ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data)
 }
 
 /**
+ * ice_read_sr_buf_aq - Reads Shadow RAM buf via AQ
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_sr_aq
+ * method. Ownership of the NVM is taken before reading the buffer and later
+ * released.
+ */
+static enum ice_status
+ice_read_sr_buf_aq(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+	enum ice_status status;
+	bool last_cmd = false;
+	u16 words_read = 0;
+	u16 i = 0;
+
+	do {
+		u16 read_size, off_w;
+
+		/* Calculate number of bytes we should read in this step.
+		 * It's not allowed to read more than one page at a time or
+		 * to cross page boundaries.
+		 */
+		off_w = offset % ICE_SR_SECTOR_SIZE_IN_WORDS;
+		read_size = off_w ?
+			min_t(u16, *words,
+			      (ICE_SR_SECTOR_SIZE_IN_WORDS - off_w)) :
+			min_t(u16, (*words - words_read),
+			      ICE_SR_SECTOR_SIZE_IN_WORDS);
+
+		/* Check if this is last command, if so set proper flag */
+		if ((words_read + read_size) >= *words)
+			last_cmd = true;
+
+		status = ice_read_sr_aq(hw, offset, read_size,
+					data + words_read, last_cmd);
+		if (status)
+			goto read_nvm_buf_aq_exit;
+
+		/* Increment counter for words already read and move offset to
+		 * new read location
+		 */
+		words_read += read_size;
+		offset += read_size;
+	} while (words_read < *words);
+
+	for (i = 0; i < *words; i++)
+		data[i] = le16_to_cpu(((__le16 *)data)[i]);
+
+read_nvm_buf_aq_exit:
+	*words = words_read;
+	return status;
+}
+
+/**
  * ice_acquire_nvm - Generic request for acquiring the NVM ownership
  * @hw: pointer to the HW structure
  * @access: NVM access type (read or write)
@@ -234,3 +291,28 @@ enum ice_status ice_init_nvm(struct ice_hw *hw)
 
 	return status;
 }
+
+/**
+ * ice_read_sr_buf - Reads Shadow RAM buf and acquire lock if necessary
+ * @hw: pointer to the HW structure
+ * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF)
+ * @words: (in) number of words to read; (out) number of words actually read
+ * @data: words read from the Shadow RAM
+ *
+ * Reads 16 bit words (data buf) from the SR using the ice_read_nvm_buf_aq
+ * method. The buf read is preceded by the NVM ownership take
+ * and followed by the release.
+ */
+enum ice_status
+ice_read_sr_buf(struct ice_hw *hw, u16 offset, u16 *words, u16 *data)
+{
+	enum ice_status status;
+
+	status = ice_acquire_nvm(hw, ICE_RES_READ);
+	if (!status) {
+		status = ice_read_sr_buf_aq(hw, offset, words, data);
+		ice_release_nvm(hw);
+	}
+
+	return status;
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index 7cc8aa18a22b..56049739a250 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -85,37 +85,59 @@ ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid)
 }
 
 /**
- * ice_aq_query_sched_elems - query scheduler elements
+ * ice_aqc_send_sched_elem_cmd - send scheduling elements cmd
  * @hw: pointer to the hw struct
- * @elems_req: number of elements to query
+ * @cmd_opc: cmd opcode
+ * @elems_req: number of elements to request
  * @buf: pointer to buffer
  * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements returned
+ * @elems_resp: returns total number of elements response
  * @cd: pointer to command details structure or NULL
  *
- * Query scheduling elements (0x0404)
+ * This function sends a scheduling elements cmd (cmd_opc)
  */
 static enum ice_status
-ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
-			 struct ice_aqc_get_elem *buf, u16 buf_size,
-			 u16 *elems_ret, struct ice_sq_cd *cd)
+ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc,
+			    u16 elems_req, void *buf, u16 buf_size,
+			    u16 *elems_resp, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_get_cfg_elem *cmd;
+	struct ice_aqc_sched_elem_cmd *cmd;
 	struct ice_aq_desc desc;
 	enum ice_status status;
 
-	cmd = &desc.params.get_update_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sched_elems);
+	cmd = &desc.params.sched_elem_cmd;
+	ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc);
 	cmd->num_elem_req = cpu_to_le16(elems_req);
 	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && elems_ret)
-		*elems_ret = le16_to_cpu(cmd->num_elem_resp);
+	if (!status && elems_resp)
+		*elems_resp = le16_to_cpu(cmd->num_elem_resp);
 
 	return status;
 }
 
 /**
+ * ice_aq_query_sched_elems - query scheduler elements
+ * @hw: pointer to the hw struct
+ * @elems_req: number of elements to query
+ * @buf: pointer to buffer
+ * @buf_size: buffer size in bytes
+ * @elems_ret: returns total number of elements returned
+ * @cd: pointer to command details structure or NULL
+ *
+ * Query scheduling elements (0x0404)
+ */
+static enum ice_status
+ice_aq_query_sched_elems(struct ice_hw *hw, u16 elems_req,
+			 struct ice_aqc_get_elem *buf, u16 buf_size,
+			 u16 *elems_ret, struct ice_sq_cd *cd)
+{
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_get_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
+}
+
+/**
  * ice_sched_query_elem - query element information from hw
  * @hw: pointer to the hw struct
  * @node_teid: node teid to be queried
@@ -218,20 +240,9 @@ ice_aq_delete_sched_elems(struct ice_hw *hw, u16 grps_req,
 			  struct ice_aqc_delete_elem *buf, u16 buf_size,
 			  u16 *grps_del, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_add_move_delete_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.add_move_delete_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_delete_sched_elems);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	cmd->num_grps_req = cpu_to_le16(grps_req);
-
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && grps_del)
-		*grps_del = le16_to_cpu(cmd->num_grps_updated);
-
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_delete_sched_elems,
+					   grps_req, (void *)buf, buf_size,
+					   grps_del, cd);
 }
 
 /**
@@ -442,52 +453,9 @@ ice_aq_add_sched_elems(struct ice_hw *hw, u16 grps_req,
 		       struct ice_aqc_add_elem *buf, u16 buf_size,
 		       u16 *grps_added, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_add_move_delete_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.add_move_delete_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_sched_elems);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-
-	cmd->num_grps_req = cpu_to_le16(grps_req);
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && grps_added)
-		*grps_added = le16_to_cpu(cmd->num_grps_updated);
-
-	return status;
-}
-
-/**
- * ice_suspend_resume_elems - suspend/resume scheduler elements
- * @hw: pointer to the hw struct
- * @elems_req: number of elements to suspend
- * @buf: pointer to buffer
- * @buf_size: buffer size in bytes
- * @elems_ret: returns total number of elements suspended
- * @cd: pointer to command details structure or NULL
- * @cmd_code: command code for suspend or resume
- *
- * suspend/resume scheduler elements
- */
-static enum ice_status
-ice_suspend_resume_elems(struct ice_hw *hw, u16 elems_req,
-			 struct ice_aqc_suspend_resume_elem *buf, u16 buf_size,
-			 u16 *elems_ret, struct ice_sq_cd *cd,
-			 enum ice_adminq_opc cmd_code)
-{
-	struct ice_aqc_get_cfg_elem *cmd;
-	struct ice_aq_desc desc;
-	enum ice_status status;
-
-	cmd = &desc.params.get_update_elem;
-	ice_fill_dflt_direct_cmd_desc(&desc, cmd_code);
-	cmd->num_elem_req = cpu_to_le16(elems_req);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
-	if (!status && elems_ret)
-		*elems_ret = le16_to_cpu(cmd->num_elem_resp);
-	return status;
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_add_sched_elems,
+					   grps_req, (void *)buf, buf_size,
+					   grps_added, cd);
 }
 
 /**
@@ -506,8 +474,9 @@ ice_aq_suspend_sched_elems(struct ice_hw *hw, u16 elems_req,
 			   struct ice_aqc_suspend_resume_elem *buf,
 			   u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
-					cd, ice_aqc_opc_suspend_sched_elems);
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_suspend_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
@@ -526,8 +495,9 @@ ice_aq_resume_sched_elems(struct ice_hw *hw, u16 elems_req,
 			  struct ice_aqc_suspend_resume_elem *buf,
 			  u16 buf_size, u16 *elems_ret, struct ice_sq_cd *cd)
 {
-	return ice_suspend_resume_elems(hw, elems_req, buf, buf_size, elems_ret,
-					cd, ice_aqc_opc_resume_sched_elems);
+	return ice_aqc_send_sched_elem_cmd(hw, ice_aqc_opc_resume_sched_elems,
+					   elems_req, (void *)buf, buf_size,
+					   elems_ret, cd);
 }
 
 /**
@@ -591,23 +561,18 @@ ice_sched_suspend_resume_elems(struct ice_hw *hw, u8 num_nodes, u32 *node_teids,
 }
 
 /**
- * ice_sched_clear_tx_topo - clears the schduler tree nodes
- * @pi: port information structure
+ * ice_sched_clear_agg - clears the agg related information
+ * @hw: pointer to the hardware structure
  *
- * This function removes all the nodes from HW as well as from SW DB.
+ * This function removes agg list and free up agg related memory
+ * previously allocated.
  */
-static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+void ice_sched_clear_agg(struct ice_hw *hw)
 {
 	struct ice_sched_agg_info *agg_info;
 	struct ice_sched_agg_info *atmp;
-	struct ice_hw *hw;
-
-	if (!pi)
-		return;
 
-	hw = pi->hw;
-
-	list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) {
+	list_for_each_entry_safe(agg_info, atmp, &hw->agg_list, list_entry) {
 		struct ice_sched_agg_vsi_info *agg_vsi_info;
 		struct ice_sched_agg_vsi_info *vtmp;
 
@@ -616,8 +581,21 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
 			list_del(&agg_vsi_info->list_entry);
 			devm_kfree(ice_hw_to_dev(hw), agg_vsi_info);
 		}
+		list_del(&agg_info->list_entry);
+		devm_kfree(ice_hw_to_dev(hw), agg_info);
 	}
+}
 
+/**
+ * ice_sched_clear_tx_topo - clears the scheduler tree nodes
+ * @pi: port information structure
+ *
+ * This function removes all the nodes from HW as well as from SW DB.
+ */
+static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
+{
+	if (!pi)
+		return;
 	if (pi->root) {
 		ice_free_sched_node(pi, pi->root);
 		pi->root = NULL;
@@ -630,7 +608,7 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi)
  *
  * Cleanup scheduling elements from SW DB
  */
-static void ice_sched_clear_port(struct ice_port_info *pi)
+void ice_sched_clear_port(struct ice_port_info *pi)
 {
 	if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY)
 		return;
@@ -894,8 +872,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw)
  * This function removes the leaf node that was created by the FW
  * during initialization
  */
-static void
-ice_rm_dflt_leaf_node(struct ice_port_info *pi)
+static void ice_rm_dflt_leaf_node(struct ice_port_info *pi)
 {
 	struct ice_sched_node *node;
 
@@ -923,8 +900,7 @@ ice_rm_dflt_leaf_node(struct ice_port_info *pi)
  * This function frees all the nodes except root and TC that were created by
  * the FW during initialization
  */
-static void
-ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
+static void ice_sched_rm_dflt_nodes(struct ice_port_info *pi)
 {
 	struct ice_sched_node *node;
 
@@ -1037,7 +1013,6 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi)
 	/* initialize the port for handling the scheduler tree */
 	pi->port_state = ICE_SCHED_PORT_STATE_READY;
 	mutex_init(&pi->sched_lock);
-	INIT_LIST_HEAD(&pi->agg_list);
 
 err_init_port:
 	if (status && pi->root) {
@@ -1091,11 +1066,10 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw)
 		hw->max_children[i] = le16_to_cpu(max_sibl);
 	}
 
-	hw->layer_info = (struct ice_aqc_layer_props *)
-			  devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props,
-				       (hw->num_tx_sched_layers *
-					sizeof(*hw->layer_info)),
-				       GFP_KERNEL);
+	hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props,
+				      (hw->num_tx_sched_layers *
+				       sizeof(*hw->layer_info)),
+				      GFP_KERNEL);
 	if (!hw->layer_info) {
 		status = ICE_ERR_NO_MEMORY;
 		goto sched_query_out;
@@ -1339,7 +1313,7 @@ ice_sched_rm_vsi_child_nodes(struct ice_port_info *pi,
  * @num_nodes: pointer to num nodes array
  *
  * This function calculates the number of supported nodes needed to add this
- * VSI into tx tree including the VSI, parent and intermediate nodes in below
+ * VSI into Tx tree including the VSI, parent and intermediate nodes in below
  * layers
  */
 static void
@@ -1369,20 +1343,25 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw,
 				node = node->sibling;
 			}
 
+			/* tree has one intermediate node to add this new VSI.
+			 * So no need to calculate supported nodes for below
+			 * layers.
+			 */
+			if (node)
+				break;
 			/* all the nodes are full, allocate a new one */
-			if (!node)
-				num_nodes[i]++;
+			num_nodes[i]++;
 		}
 }
 
 /**
- * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree
+ * ice_sched_add_vsi_support_nodes - add VSI supported nodes into Tx tree
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc_node: pointer to TC node
  * @num_nodes: pointer to num nodes array
  *
- * This function adds the VSI supported nodes into tx tree including the
+ * This function adds the VSI supported nodes into Tx tree including the
  * VSI, its parent and intermediate nodes in below layers
  */
 static enum ice_status
@@ -1527,7 +1506,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle,
 }
 
 /**
- * ice_sched_cfg_vsi - configure the new/exisiting VSI
+ * ice_sched_cfg_vsi - configure the new/existing VSI
  * @pi: port information structure
  * @vsi_handle: software VSI handle
  * @tc: TC number
@@ -1605,3 +1584,133 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 
 	return status;
 }
+
+/**
+ * ice_sched_rm_agg_vsi_entry - remove agg related VSI info entry
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function removes single aggregator VSI info entry from
+ * aggregator list.
+ */
+static void
+ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle)
+{
+	struct ice_sched_agg_info *agg_info;
+	struct ice_sched_agg_info *atmp;
+
+	list_for_each_entry_safe(agg_info, atmp, &pi->hw->agg_list,
+				 list_entry) {
+		struct ice_sched_agg_vsi_info *agg_vsi_info;
+		struct ice_sched_agg_vsi_info *vtmp;
+
+		list_for_each_entry_safe(agg_vsi_info, vtmp,
+					 &agg_info->agg_vsi_list, list_entry)
+			if (agg_vsi_info->vsi_handle == vsi_handle) {
+				list_del(&agg_vsi_info->list_entry);
+				devm_kfree(ice_hw_to_dev(pi->hw),
+					   agg_vsi_info);
+				return;
+			}
+	}
+}
+
+/**
+ * ice_sched_is_leaf_node_present - check for a leaf node in the sub-tree
+ * @node: pointer to the sub-tree node
+ *
+ * This function checks for a leaf node presence in a given sub-tree node.
+ */
+static bool ice_sched_is_leaf_node_present(struct ice_sched_node *node)
+{
+	u8 i;
+
+	for (i = 0; i < node->num_children; i++)
+		if (ice_sched_is_leaf_node_present(node->children[i]))
+			return true;
+	/* check for a leaf node */
+	return (node->info.data.elem_type == ICE_AQC_ELEM_TYPE_LEAF);
+}
+
+/**
+ * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ * @owner: LAN or RDMA
+ *
+ * This function removes the VSI and its LAN or RDMA children nodes from the
+ * scheduler tree.
+ */
+static enum ice_status
+ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner)
+{
+	enum ice_status status = ICE_ERR_PARAM;
+	struct ice_vsi_ctx *vsi_ctx;
+	u8 i, j = 0;
+
+	if (!ice_is_vsi_valid(pi->hw, vsi_handle))
+		return status;
+	mutex_lock(&pi->sched_lock);
+	vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle);
+	if (!vsi_ctx)
+		goto exit_sched_rm_vsi_cfg;
+
+	for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) {
+		struct ice_sched_node *vsi_node, *tc_node;
+
+		tc_node = ice_sched_get_tc_node(pi, i);
+		if (!tc_node)
+			continue;
+
+		vsi_node = ice_sched_get_vsi_node(pi->hw, tc_node, vsi_handle);
+		if (!vsi_node)
+			continue;
+
+		if (ice_sched_is_leaf_node_present(vsi_node)) {
+			ice_debug(pi->hw, ICE_DBG_SCHED,
+				  "VSI has leaf nodes in TC %d\n", i);
+			status = ICE_ERR_IN_USE;
+			goto exit_sched_rm_vsi_cfg;
+		}
+		while (j < vsi_node->num_children) {
+			if (vsi_node->children[j]->owner == owner) {
+				ice_free_sched_node(pi, vsi_node->children[j]);
+
+				/* reset the counter again since the num
+				 * children will be updated after node removal
+				 */
+				j = 0;
+			} else {
+				j++;
+			}
+		}
+		/* remove the VSI if it has no children */
+		if (!vsi_node->num_children) {
+			ice_free_sched_node(pi, vsi_node);
+			vsi_ctx->sched.vsi_node[i] = NULL;
+
+			/* clean up agg related vsi info if any */
+			ice_sched_rm_agg_vsi_info(pi, vsi_handle);
+		}
+		if (owner == ICE_SCHED_NODE_OWNER_LAN)
+			vsi_ctx->sched.max_lanq[i] = 0;
+	}
+	status = 0;
+
+exit_sched_rm_vsi_cfg:
+	mutex_unlock(&pi->sched_lock);
+	return status;
+}
+
+/**
+ * ice_rm_vsi_lan_cfg - remove VSI and its LAN children nodes
+ * @pi: port information structure
+ * @vsi_handle: software VSI handle
+ *
+ * This function clears the VSI and its LAN children nodes from scheduler tree
+ * for all TCs.
+ */
+enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle)
+{
+	return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_LAN);
+}
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h
index 5dc9cfa04c58..bee8221ad146 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.h
+++ b/drivers/net/ethernet/intel/ice/ice_sched.h
@@ -12,6 +12,7 @@
 struct ice_sched_agg_vsi_info {
 	struct list_head list_entry;
 	DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS);
+	u16 vsi_handle;
 };
 
 struct ice_sched_agg_info {
@@ -25,7 +26,10 @@ struct ice_sched_agg_info {
 /* FW AQ command calls */
 enum ice_status ice_sched_init_port(struct ice_port_info *pi);
 enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw);
+void ice_sched_clear_port(struct ice_port_info *pi);
 void ice_sched_cleanup_all(struct ice_hw *hw);
+void ice_sched_clear_agg(struct ice_hw *hw);
+
 struct ice_sched_node *
 ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid);
 enum ice_status
@@ -39,4 +43,5 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc,
 enum ice_status
 ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs,
 		  u8 owner, bool enable);
+enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle);
 #endif /* _ICE_SCHED_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index 027eba4e13f8..d2db0d04e117 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -46,7 +46,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
  * @link_speed: variable containing the link_speed to be converted
  *
  * Convert link speed supported by HW to link speed supported by virtchnl.
- * If adv_link_support is true, then return link speed in Mbps.  Else return
+ * If adv_link_support is true, then return link speed in Mbps. Else return
  * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller
  * needs to cast back to an enum virtchnl_link_speed in the case where
  * adv_link_support is false, but when adv_link_support is true the caller can
@@ -85,6 +85,12 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
 		case ICE_AQ_LINK_SPEED_40GB:
 			speed = ICE_LINK_SPEED_40000MBPS;
 			break;
+		case ICE_AQ_LINK_SPEED_50GB:
+			speed = ICE_LINK_SPEED_50000MBPS;
+			break;
+		case ICE_AQ_LINK_SPEED_100GB:
+			speed = ICE_LINK_SPEED_100000MBPS;
+			break;
 		default:
 			speed = ICE_LINK_SPEED_UNKNOWN;
 			break;
@@ -116,6 +122,9 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed)
 			break;
 		case ICE_AQ_LINK_SPEED_40GB:
 			/* fall through */
+		case ICE_AQ_LINK_SPEED_50GB:
+			/* fall through */
+		case ICE_AQ_LINK_SPEED_100GB:
 			speed = (u32)VIRTCHNL_LINK_SPEED_40GB;
 			break;
 		default:
diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h
index f49f299ddf2c..683f48824a29 100644
--- a/drivers/net/ethernet/intel/ice/ice_status.h
+++ b/drivers/net/ethernet/intel/ice/ice_status.h
@@ -22,6 +22,7 @@ enum ice_status {
 	ICE_ERR_OUT_OF_RANGE			= -13,
 	ICE_ERR_ALREADY_EXISTS			= -14,
 	ICE_ERR_DOES_NOT_EXIST			= -15,
+	ICE_ERR_IN_USE				= -16,
 	ICE_ERR_MAX_LIMIT			= -17,
 	ICE_ERR_RESET_ONGOING			= -18,
 	ICE_ERR_BUF_TOO_SHORT			= -52,
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 40c9c6558956..09d1c314b68f 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -92,14 +92,13 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries,
  * Allocate memory for the entire recipe table and initialize the structures/
  * entries corresponding to basic recipes.
  */
-enum ice_status
-ice_init_def_sw_recp(struct ice_hw *hw)
+enum ice_status ice_init_def_sw_recp(struct ice_hw *hw)
 {
 	struct ice_sw_recipe *recps;
 	u8 i;
 
 	recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES,
-			     sizeof(struct ice_sw_recipe), GFP_KERNEL);
+			     sizeof(*recps), GFP_KERNEL);
 	if (!recps)
 		return ICE_ERR_NO_MEMORY;
 
@@ -130,7 +129,7 @@ ice_init_def_sw_recp(struct ice_hw *hw)
  *
  * NOTE: *req_desc is both an input/output parameter.
  * The caller of this function first calls this function with *request_desc set
- * to 0.  If the response from f/w has *req_desc set to 0, all the switch
+ * to 0. If the response from f/w has *req_desc set to 0, all the switch
  * configuration information has been returned; if non-zero (meaning not all
  * the information was returned), the caller should call this function again
  * with *req_desc set to the previous value returned by f/w to get the
@@ -629,25 +628,36 @@ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw)
 /**
  * ice_fill_sw_info - Helper function to populate lb_en and lan_en
  * @hw: pointer to the hardware structure
- * @f_info: filter info structure to fill/update
+ * @fi: filter info structure to fill/update
  *
  * This helper function populates the lb_en and lan_en elements of the provided
  * ice_fltr_info struct using the switch's type and characteristics of the
  * switch rule being configured.
  */
-static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *f_info)
+static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi)
 {
-	f_info->lb_en = false;
-	f_info->lan_en = false;
-	if ((f_info->flag & ICE_FLTR_TX) &&
-	    (f_info->fltr_act == ICE_FWD_TO_VSI ||
-	     f_info->fltr_act == ICE_FWD_TO_VSI_LIST ||
-	     f_info->fltr_act == ICE_FWD_TO_Q ||
-	     f_info->fltr_act == ICE_FWD_TO_QGRP)) {
-		f_info->lb_en = true;
-		if (!(hw->evb_veb && f_info->lkup_type == ICE_SW_LKUP_MAC &&
-		      is_unicast_ether_addr(f_info->l_data.mac.mac_addr)))
-			f_info->lan_en = true;
+	fi->lb_en = false;
+	fi->lan_en = false;
+	if ((fi->flag & ICE_FLTR_TX) &&
+	    (fi->fltr_act == ICE_FWD_TO_VSI ||
+	     fi->fltr_act == ICE_FWD_TO_VSI_LIST ||
+	     fi->fltr_act == ICE_FWD_TO_Q ||
+	     fi->fltr_act == ICE_FWD_TO_QGRP)) {
+		fi->lb_en = true;
+		/* Do not set lan_en to TRUE if
+		 * 1. The switch is a VEB AND
+		 * 2
+		 * 2.1 The lookup is MAC with unicast addr for MAC, OR
+		 * 2.2 The lookup is MAC_VLAN with unicast addr for MAC
+		 *
+		 * In all other cases, the LAN enable has to be set to true.
+		 */
+		if (!(hw->evb_veb &&
+		      ((fi->lkup_type == ICE_SW_LKUP_MAC &&
+			is_unicast_ether_addr(fi->l_data.mac.mac_addr)) ||
+		       (fi->lkup_type == ICE_SW_LKUP_MAC_VLAN &&
+			is_unicast_ether_addr(fi->l_data.mac_vlan.mac_addr)))))
+			fi->lan_en = true;
 	}
 }
 
@@ -817,7 +827,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 	/* Create two back-to-back switch rules and submit them to the HW using
 	 * one memory buffer:
 	 *    1. Large Action
-	 *    2. Look up tx rx
+	 *    2. Look up Tx Rx
 	 */
 	lg_act_size = (u16)ICE_SW_RULE_LG_ACT_SIZE(num_lg_acts);
 	rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE;
@@ -861,7 +871,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent,
 
 	lg_act->pdata.lg_act.act[2] = cpu_to_le32(act);
 
-	/* call the fill switch rule to fill the lookup tx rx structure */
+	/* call the fill switch rule to fill the lookup Tx Rx structure */
 	ice_fill_sw_rule(hw, &m_ent->fltr_info, rx_tx,
 			 ice_aqc_opc_update_sw_rules);
 
@@ -1158,8 +1168,8 @@ enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw)
  * Call AQ command to add or update previously created VSI list with new VSI.
  *
  * Helper function to do book keeping associated with adding filter information
- * The algorithm to do the booking keeping is described below :
- * When a VSI needs to subscribe to a given filter( MAC/VLAN/Ethtype etc.)
+ * The algorithm to do the book keeping is described below :
+ * When a VSI needs to subscribe to a given filter (MAC/VLAN/Ethtype etc.)
  *	if only one VSI has been added till now
  *		Allocate a new VSI list and add two VSIs
  *		to this list using switch rule command
@@ -1237,6 +1247,9 @@ ice_add_update_vsi_list(struct ice_hw *hw,
 		u16 vsi_handle = new_fltr->vsi_handle;
 		enum ice_adminq_opc opcode;
 
+		if (!m_entry->vsi_list_info)
+			return ICE_ERR_CFG;
+
 		/* A rule already exists with the new VSI being added */
 		if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
 			return 0;
@@ -1525,9 +1538,20 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id,
 	} else if (!list_elem->vsi_list_info) {
 		status = ICE_ERR_DOES_NOT_EXIST;
 		goto exit;
+	} else if (list_elem->vsi_list_info->ref_cnt > 1) {
+		/* a ref_cnt > 1 indicates that the vsi_list is being
+		 * shared by multiple rules. Decrement the ref_cnt and
+		 * remove this rule, but do not modify the list, as it
+		 * is in-use by other rules.
+		 */
+		list_elem->vsi_list_info->ref_cnt--;
+		remove_rule = true;
 	} else {
-		if (list_elem->vsi_list_info->ref_cnt > 1)
-			list_elem->vsi_list_info->ref_cnt--;
+		/* a ref_cnt of 1 indicates the vsi_list is only used
+		 * by one rule. However, the original removal request is only
+		 * for a single VSI. Update the vsi_list first, and only
+		 * remove the rule if there are no further VSIs in this list.
+		 */
 		vsi_handle = f_entry->fltr_info.vsi_handle;
 		status = ice_rem_update_vsi_list(hw, vsi_handle, list_elem);
 		if (status)
@@ -1853,7 +1877,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry)
 		tmp_fltr.fwd_id.vsi_list_id = vsi_list_id;
 		tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST;
 		/* Update the previous switch rule to a new VSI list which
-		 * includes current VSI thats requested
+		 * includes current VSI that is requested
 		 */
 		status = ice_update_pkt_fwd_rule(hw, &tmp_fltr);
 		if (status)
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index fe5bbabbb41e..c289d97f477d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -48,7 +48,6 @@ static struct netdev_queue *txring_txq(const struct ice_ring *ring)
  */
 void ice_clean_tx_ring(struct ice_ring *tx_ring)
 {
-	unsigned long size;
 	u16 i;
 
 	/* ring already cleared, nothing to do */
@@ -59,8 +58,7 @@ void ice_clean_tx_ring(struct ice_ring *tx_ring)
 	for (i = 0; i < tx_ring->count; i++)
 		ice_unmap_and_free_tx_buf(tx_ring, &tx_ring->tx_buf[i]);
 
-	size = sizeof(struct ice_tx_buf) * tx_ring->count;
-	memset(tx_ring->tx_buf, 0, size);
+	memset(tx_ring->tx_buf, 0, sizeof(*tx_ring->tx_buf) * tx_ring->count);
 
 	/* Zero out the descriptor ring */
 	memset(tx_ring->desc, 0, tx_ring->size);
@@ -219,28 +217,28 @@ static bool ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring,
 
 /**
  * ice_setup_tx_ring - Allocate the Tx descriptors
- * @tx_ring: the tx ring to set up
+ * @tx_ring: the Tx ring to set up
  *
  * Return 0 on success, negative on error
  */
 int ice_setup_tx_ring(struct ice_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
-	int bi_size;
 
 	if (!dev)
 		return -ENOMEM;
 
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(tx_ring->tx_buf);
-	bi_size = sizeof(struct ice_tx_buf) * tx_ring->count;
-	tx_ring->tx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+	tx_ring->tx_buf =
+		devm_kzalloc(dev, sizeof(*tx_ring->tx_buf) * tx_ring->count,
+			     GFP_KERNEL);
 	if (!tx_ring->tx_buf)
 		return -ENOMEM;
 
 	/* round up to nearest 4K */
-	tx_ring->size = tx_ring->count * sizeof(struct ice_tx_desc);
-	tx_ring->size = ALIGN(tx_ring->size, 4096);
+	tx_ring->size = ALIGN(tx_ring->count * sizeof(struct ice_tx_desc),
+			      4096);
 	tx_ring->desc = dmam_alloc_coherent(dev, tx_ring->size, &tx_ring->dma,
 					    GFP_KERNEL);
 	if (!tx_ring->desc) {
@@ -267,7 +265,6 @@ err:
 void ice_clean_rx_ring(struct ice_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	unsigned long size;
 	u16 i;
 
 	/* ring already cleared, nothing to do */
@@ -292,8 +289,7 @@ void ice_clean_rx_ring(struct ice_ring *rx_ring)
 		rx_buf->page_offset = 0;
 	}
 
-	size = sizeof(struct ice_rx_buf) * rx_ring->count;
-	memset(rx_ring->rx_buf, 0, size);
+	memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);
 
 	/* Zero out the descriptor ring */
 	memset(rx_ring->desc, 0, rx_ring->size);
@@ -324,22 +320,22 @@ void ice_free_rx_ring(struct ice_ring *rx_ring)
 
 /**
  * ice_setup_rx_ring - Allocate the Rx descriptors
- * @rx_ring: the rx ring to set up
+ * @rx_ring: the Rx ring to set up
  *
  * Return 0 on success, negative on error
  */
 int ice_setup_rx_ring(struct ice_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
-	int bi_size;
 
 	if (!dev)
 		return -ENOMEM;
 
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(rx_ring->rx_buf);
-	bi_size = sizeof(struct ice_rx_buf) * rx_ring->count;
-	rx_ring->rx_buf = devm_kzalloc(dev, bi_size, GFP_KERNEL);
+	rx_ring->rx_buf =
+		devm_kzalloc(dev, sizeof(*rx_ring->rx_buf) * rx_ring->count,
+			     GFP_KERNEL);
 	if (!rx_ring->rx_buf)
 		return -ENOMEM;
 
@@ -377,7 +373,7 @@ static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val)
 	rx_ring->next_to_alloc = val;
 
 	/* Force memory writes to complete before letting h/w
-	 * know there are new descriptors to fetch.  (Only
+	 * know there are new descriptors to fetch. (Only
 	 * applicable for weak-ordered memory model archs,
 	 * such as IA-64).
 	 */
@@ -586,7 +582,7 @@ static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf,
 
 /**
  * ice_reuse_rx_page - page flip buffer and store it back on the ring
- * @rx_ring: rx descriptor ring to store buffers on
+ * @rx_ring: Rx descriptor ring to store buffers on
  * @old_buf: donor buffer to have page reused
  *
  * Synchronizes page for reuse by the adapter
@@ -609,7 +605,7 @@ static void ice_reuse_rx_page(struct ice_ring *rx_ring,
 
 /**
  * ice_fetch_rx_buf - Allocate skb and populate it
- * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_ring: Rx descriptor ring to transact packets on
  * @rx_desc: descriptor containing info written by hardware
  *
  * This function allocates an skb on the fly, and populates it with the page
@@ -686,7 +682,7 @@ static struct sk_buff *ice_fetch_rx_buf(struct ice_ring *rx_ring,
  * ice_pull_tail - ice specific version of skb_pull_tail
  * @skb: pointer to current skb being adjusted
  *
- * This function is an ice specific version of __pskb_pull_tail.  The
+ * This function is an ice specific version of __pskb_pull_tail. The
  * main difference between this version and the original function is that
  * this function can make several assumptions about the state of things
  * that allow for significant optimizations versus the standard function.
@@ -768,7 +764,7 @@ static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc,
  * @rx_desc: Rx descriptor for current buffer
  * @skb: Current socket buffer containing buffer in progress
  *
- * This function updates next to clean.  If the buffer is an EOP buffer
+ * This function updates next to clean. If the buffer is an EOP buffer
  * this function exits returning false, otherwise it will place the
  * sk_buff in the next buffer to be chained and return true indicating
  * that this is in fact a non-EOP buffer.
@@ -904,7 +900,7 @@ checksum_fail:
 
 /**
  * ice_process_skb_fields - Populate skb header fields from Rx descriptor
- * @rx_ring: rx descriptor ring packet is being transacted on
+ * @rx_ring: Rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
  * @ptype: the packet type decoded by hardware
@@ -927,7 +923,7 @@ static void ice_process_skb_fields(struct ice_ring *rx_ring,
 
 /**
  * ice_receive_skb - Send a completed packet up the stack
- * @rx_ring: rx ring in play
+ * @rx_ring: Rx ring in play
  * @skb: packet to send up
  * @vlan_tag: vlan tag for packet
  *
@@ -946,11 +942,11 @@ static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb,
 
 /**
  * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
- * @rx_ring: rx descriptor ring to transact packets on
+ * @rx_ring: Rx descriptor ring to transact packets on
  * @budget: Total limit on number of packets to process
  *
  * This function provides a "bounce buffer" approach to Rx interrupt
- * processing.  The advantage to this is that on systems that have
+ * processing. The advantage to this is that on systems that have
  * expensive overhead for IOMMU access this provides a means of avoiding
  * it by maintaining the mapping of the page to the system.
  *
@@ -1053,6 +1049,69 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget)
 }
 
 /**
+ * ice_buildreg_itr - build value for writing to the GLINT_DYN_CTL register
+ * @itr_idx: interrupt throttling index
+ * @reg_itr: interrupt throttling value adjusted based on ITR granularity
+ */
+static u32 ice_buildreg_itr(int itr_idx, u16 reg_itr)
+{
+	return GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+		(itr_idx << GLINT_DYN_CTL_ITR_INDX_S) |
+		(reg_itr << GLINT_DYN_CTL_INTERVAL_S);
+}
+
+/**
+ * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt
+ * @vsi: the VSI associated with the q_vector
+ * @q_vector: q_vector for which ITR is being updated and interrupt enabled
+ */
+static void
+ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+{
+	struct ice_hw *hw = &vsi->back->hw;
+	struct ice_ring_container *rc;
+	u32 itr_val;
+
+	/* This block of logic allows us to get away with only updating
+	 * one ITR value with each interrupt. The idea is to perform a
+	 * pseudo-lazy update with the following criteria.
+	 *
+	 * 1. Rx is given higher priority than Tx if both are in same state
+	 * 2. If we must reduce an ITR that is given highest priority.
+	 * 3. We then give priority to increasing ITR based on amount.
+	 */
+	if (q_vector->rx.target_itr < q_vector->rx.current_itr) {
+		rc = &q_vector->rx;
+		/* Rx ITR needs to be reduced, this is highest priority */
+		itr_val = ice_buildreg_itr(rc->itr_idx, rc->target_itr);
+		rc->current_itr = rc->target_itr;
+	} else if ((q_vector->tx.target_itr < q_vector->tx.current_itr) ||
+		   ((q_vector->rx.target_itr - q_vector->rx.current_itr) <
+		    (q_vector->tx.target_itr - q_vector->tx.current_itr))) {
+		rc = &q_vector->tx;
+		/* Tx ITR needs to be reduced, this is second priority
+		 * Tx ITR needs to be increased more than Rx, fourth priority
+		 */
+		itr_val = ice_buildreg_itr(rc->itr_idx, rc->target_itr);
+		rc->current_itr = rc->target_itr;
+	} else if (q_vector->rx.current_itr != q_vector->rx.target_itr) {
+		rc = &q_vector->rx;
+		/* Rx ITR needs to be increased, third priority */
+		itr_val = ice_buildreg_itr(rc->itr_idx, rc->target_itr);
+		rc->current_itr = rc->target_itr;
+	} else {
+		/* Still have to re-enable the interrupts */
+		itr_val = ice_buildreg_itr(ICE_ITR_NONE, 0);
+	}
+
+	if (!test_bit(__ICE_DOWN, vsi->state)) {
+		int vector = vsi->hw_base_vector + q_vector->v_idx;
+
+		wr32(hw, GLINT_DYN_CTL(vector), itr_val);
+	}
+}
+
+/**
  * ice_napi_poll - NAPI polling Rx/Tx cleanup routine
  * @napi: napi struct with our devices info in it
  * @budget: amount of work driver is allowed to do this pass, in packets
@@ -1103,11 +1162,14 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* Work is done so exit the polling mode and re-enable the interrupt */
-	napi_complete_done(napi, work_done);
-	if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
-		ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector);
-	return 0;
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags))
+			ice_update_ena_itr(vsi, q_vector);
+
+	return min_t(int, work_done, budget - 1);
 }
 
 /* helper function for building cmd/type/offset */
@@ -1122,7 +1184,7 @@ build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag)
 }
 
 /**
- * __ice_maybe_stop_tx - 2nd level check for tx stop conditions
+ * __ice_maybe_stop_tx - 2nd level check for Tx stop conditions
  * @tx_ring: the ring to be checked
  * @size: the size buffer we want to assure is available
  *
@@ -1145,7 +1207,7 @@ static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
 }
 
 /**
- * ice_maybe_stop_tx - 1st level check for tx stop conditions
+ * ice_maybe_stop_tx - 1st level check for Tx stop conditions
  * @tx_ring: the ring to be checked
  * @size:    the size buffer we want to assure is available
  *
@@ -1155,6 +1217,7 @@ static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size)
 {
 	if (likely(ICE_DESC_UNUSED(tx_ring) >= size))
 		return 0;
+
 	return __ice_maybe_stop_tx(tx_ring, size);
 }
 
@@ -1398,6 +1461,12 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
 		break;
 	case IPPROTO_SCTP:
+		/* enable SCTP checksum offload */
+		cmd |= ICE_TX_DESC_CMD_L4T_EOFT_SCTP;
+		l4_len = sizeof(struct sctphdr) >> 2;
+		offset |= l4_len << ICE_TX_DESC_LEN_L4_LEN_S;
+		break;
+
 	default:
 		if (first->tx_flags & ICE_TX_FLAGS_TSO)
 			return -1;
@@ -1552,7 +1621,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
  * Finally, we add one to round up. Because 256 isn't an exact multiple of
  * 3, we'll underestimate near each multiple of 12K. This is actually more
  * accurate as we have 4K - 1 of wiggle room that we can fit into the last
- * segment.  For our purposes this is accurate out to 1M which is orders of
+ * segment. For our purposes this is accurate out to 1M which is orders of
  * magnitude greater than our largest possible GSO size.
  *
  * This would then be implemented as:
@@ -1568,7 +1637,7 @@ static unsigned int ice_txd_use_count(unsigned int size)
 }
 
 /**
- * ice_xmit_desc_count - calculate number of tx descriptors needed
+ * ice_xmit_desc_count - calculate number of Tx descriptors needed
  * @skb: send buffer
  *
  * Returns number of data descriptors needed for this skb.
@@ -1620,7 +1689,7 @@ static bool __ice_chk_linearize(struct sk_buff *skb)
 	nr_frags -= ICE_MAX_BUF_TXD - 2;
 	frag = &skb_shinfo(skb)->frags[0];
 
-	/* Initialize size to the negative value of gso_size minus 1.  We
+	/* Initialize size to the negative value of gso_size minus 1. We
 	 * use this as the worst case scenerio in which the frag ahead
 	 * of us only provides one byte which is why we are limited to 6
 	 * descriptors for a single transmit as the header and previous
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 75d0eaf6c9dd..fc358ea81816 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -116,16 +116,17 @@ enum ice_rx_dtype {
 /* indices into GLINT_ITR registers */
 #define ICE_RX_ITR	ICE_IDX_ITR0
 #define ICE_TX_ITR	ICE_IDX_ITR1
-#define ICE_ITR_DYNAMIC	0x8000  /* use top bit as a flag */
-#define ICE_ITR_8K	125
+#define ICE_ITR_8K	124
 #define ICE_ITR_20K	50
-#define ICE_DFLT_TX_ITR	ICE_ITR_20K
-#define ICE_DFLT_RX_ITR	ICE_ITR_20K
-/* apply ITR granularity translation to program the register. itr_gran is either
- * 2 or 4 usecs so we need to divide by 2 first then shift by that value
- */
-#define ITR_TO_REG(val, itr_gran) (((val) & ~ICE_ITR_DYNAMIC) >> \
-				   ((itr_gran) / 2))
+#define ICE_ITR_MAX	8160
+#define ICE_DFLT_TX_ITR	(ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_DFLT_RX_ITR	(ICE_ITR_20K | ICE_ITR_DYNAMIC)
+#define ICE_ITR_DYNAMIC	0x8000  /* used as flag for itr_setting */
+#define ITR_IS_DYNAMIC(setting) (!!((setting) & ICE_ITR_DYNAMIC))
+#define ITR_TO_REG(setting)	((setting) & ~ICE_ITR_DYNAMIC)
+#define ICE_ITR_GRAN_S		1	/* Assume ITR granularity is 2us */
+#define ICE_ITR_MASK		0x1FFE	/* ITR register value alignment mask */
+#define ITR_REG_ALIGN(setting)	__ALIGN_MASK(setting, ~ICE_ITR_MASK)
 
 #define ICE_DFLT_INTRL	0
 
@@ -180,13 +181,20 @@ enum ice_latency_range {
 };
 
 struct ice_ring_container {
-	/* array of pointers to rings */
+	/* head of linked-list of rings */
 	struct ice_ring *ring;
+	unsigned long next_update;	/* jiffies value of next queue update */
 	unsigned int total_bytes;	/* total bytes processed this int */
 	unsigned int total_pkts;	/* total packets processed this int */
 	enum ice_latency_range latency_range;
-	int itr_idx;	/* index in the interrupt vector */
-	u16 itr;
+	int itr_idx;		/* index in the interrupt vector */
+	u16 target_itr;		/* value in usecs divided by the hw->itr_gran */
+	u16 current_itr;	/* value in usecs divided by the hw->itr_gran */
+	/* high bit set means dynamic ITR, rest is used to store user
+	 * readable ITR value in usecs and must be converted before programming
+	 * to a register.
+	 */
+	u16 itr_setting;
 };
 
 /* iterator for handling rings in ring container */
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f4dbc81c1988..17086d5b5c33 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -90,6 +90,7 @@ enum ice_vsi_type {
 struct ice_link_status {
 	/* Refer to ice_aq_phy_type for bits definition */
 	u64 phy_type_low;
+	u64 phy_type_high;
 	u16 max_frame_size;
 	u16 link_speed;
 	u16 req_speeds;
@@ -118,12 +119,15 @@ struct ice_phy_info {
 	struct ice_link_status link_info;
 	struct ice_link_status link_info_old;
 	u64 phy_type_low;
+	u64 phy_type_high;
 	enum ice_media_type media_type;
 	u8 get_link_info;
 };
 
 /* Common HW capabilities for SW use */
 struct ice_hw_common_caps {
+	u32 valid_functions;
+
 	/* TX/RX queues */
 	u16 num_rxq;		/* Number/Total RX queues */
 	u16 rxq_first_id;	/* First queue ID for RX queues */
@@ -150,7 +154,7 @@ struct ice_hw_func_caps {
 	struct ice_hw_common_caps common_cap;
 	u32 num_allocd_vfs;		/* Number of allocated VFs */
 	u32 vf_base_id;			/* Logical ID of the first VF */
-	u32 guaranteed_num_vsi;
+	u32 guar_num_vsi;
 };
 
 /* Device wide capabilities */
@@ -270,7 +274,6 @@ struct ice_port_info {
 	struct ice_mac_info mac;
 	struct ice_phy_info phy;
 	struct mutex sched_lock;	/* protect access to TXSched tree */
-	struct list_head agg_list;	/* lists all aggregator */
 	u8 lport;
 #define ICE_LPORT_MASK		0xff
 	u8 is_vf;
@@ -324,6 +327,7 @@ struct ice_hw {
 	u8 max_cgds;
 	u8 sw_entry_point_layer;
 	u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM];
+	struct list_head agg_list;	/* lists all aggregator */
 
 	struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI];
 	u8 evb_veb;		/* true for VEB, false for VEPA */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
index e71065f9d391..57155b4a59dc 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c
@@ -156,8 +156,6 @@ static void ice_free_vf_res(struct ice_vf *vf)
 	clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states);
 }
 
-/***********************enable_vf routines*****************************/
-
 /**
  * ice_dis_vf_mappings
  * @vf: pointer to the VF structure
@@ -175,7 +173,8 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 	wr32(hw, VPINT_ALLOC(vf->vf_id), 0);
 	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0);
 
-	first = vf->first_vector_idx;
+	first = vf->first_vector_idx +
+		hw->func_caps.common_cap.msix_vector_first_id;
 	last = first + pf->num_vf_msix - 1;
 	for (v = first; v <= last; v++) {
 		u32 reg;
@@ -215,28 +214,30 @@ void ice_free_vfs(struct ice_pf *pf)
 	while (test_and_set_bit(__ICE_VF_DIS, pf->state))
 		usleep_range(1000, 2000);
 
+	/* Disable IOV before freeing resources. This lets any VF drivers
+	 * running in the host get themselves cleaned up before we yank
+	 * the carpet out from underneath their feet.
+	 */
+	if (!pci_vfs_assigned(pf->pdev))
+		pci_disable_sriov(pf->pdev);
+	else
+		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
+
 	/* Avoid wait time by stopping all VFs at the same time */
 	for (i = 0; i < pf->num_alloc_vfs; i++) {
+		struct ice_vsi *vsi;
+
 		if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states))
 			continue;
 
+		vsi = pf->vsi[pf->vf[i].lan_vsi_idx];
 		/* stop rings without wait time */
-		ice_vsi_stop_tx_rings(pf->vsi[pf->vf[i].lan_vsi_idx],
-				      ICE_NO_RESET, i);
-		ice_vsi_stop_rx_rings(pf->vsi[pf->vf[i].lan_vsi_idx]);
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, i);
+		ice_vsi_stop_rx_rings(vsi);
 
 		clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states);
 	}
 
-	/* Disable IOV before freeing resources. This lets any VF drivers
-	 * running in the host get themselves cleaned up before we yank
-	 * the carpet out from underneath their feet.
-	 */
-	if (!pci_vfs_assigned(pf->pdev))
-		pci_disable_sriov(pf->pdev);
-	else
-		dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n");
-
 	tmp = pf->num_alloc_vfs;
 	pf->num_vf_qps = 0;
 	pf->num_alloc_vfs = 0;
@@ -310,6 +311,11 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr)
 	 */
 	clear_bit(ICE_VF_STATE_INIT, vf->vf_states);
 
+	/* Clear the VF's ARQLEN register. This is how the VF detects reset,
+	 * since the VFGEN_RSTAT register doesn't stick at 0 after reset.
+	 */
+	wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0);
+
 	/* In the case of a VFLR, the HW has already reset the VF and we
 	 * just need to clean up, so don't hit the VFRTRIG register.
 	 */
@@ -345,25 +351,33 @@ static int ice_vsi_set_pvid(struct ice_vsi *vsi, u16 vid)
 {
 	struct device *dev = &vsi->back->pdev->dev;
 	struct ice_hw *hw = &vsi->back->hw;
-	struct ice_vsi_ctx ctxt = { 0 };
+	struct ice_vsi_ctx *ctxt;
 	enum ice_status status;
+	int ret = 0;
 
-	ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_UNTAGGED |
-			       ICE_AQ_VSI_PVLAN_INSERT_PVID |
-			       ICE_AQ_VSI_VLAN_EMOD_STR;
-	ctxt.info.pvid = cpu_to_le16(vid);
-	ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+	ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL);
+	if (!ctxt)
+		return -ENOMEM;
 
-	status = ice_update_vsi(hw, vsi->idx, &ctxt, NULL);
+	ctxt->info.vlan_flags = (ICE_AQ_VSI_VLAN_MODE_UNTAGGED |
+				 ICE_AQ_VSI_PVLAN_INSERT_PVID |
+				 ICE_AQ_VSI_VLAN_EMOD_STR);
+	ctxt->info.pvid = cpu_to_le16(vid);
+	ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID);
+
+	status = ice_update_vsi(hw, vsi->idx, ctxt, NULL);
 	if (status) {
 		dev_info(dev, "update VSI for VLAN insert failed, err %d aq_err %d\n",
 			 status, hw->adminq.sq_last_status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
-	vsi->info.pvid = ctxt.info.pvid;
-	vsi->info.vlan_flags = ctxt.info.vlan_flags;
-	return 0;
+	vsi->info.pvid = ctxt->info.pvid;
+	vsi->info.vlan_flags = ctxt->info.vlan_flags;
+out:
+	devm_kfree(dev, ctxt);
+	return ret;
 }
 
 /**
@@ -454,7 +468,7 @@ static int ice_alloc_vsi_res(struct ice_vf *vf)
 
 	/* Clear this bit after VF initialization since we shouldn't reclaim
 	 * and reassign interrupts for synchronous or asynchronous VFR events.
-	 * We don't want to reconfigure interrupts since AVF driver doesn't
+	 * We dont want to reconfigure interrupts since AVF driver doesn't
 	 * expect vector assignment to be changed unless there is a request for
 	 * more vectors.
 	 */
@@ -510,7 +524,8 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 
 	hw = &pf->hw;
 	vsi = pf->vsi[vf->lan_vsi_idx];
-	first = vf->first_vector_idx;
+	first = vf->first_vector_idx +
+		hw->func_caps.common_cap.msix_vector_first_id;
 	last = (first + pf->num_vf_msix) - 1;
 	abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id;
 
@@ -833,6 +848,7 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 {
 	struct ice_pf *pf = vf->pf;
 	struct ice_hw *hw = &pf->hw;
+	struct ice_vsi *vsi;
 	bool rsd = false;
 	u32 reg;
 	int i;
@@ -845,17 +861,18 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr)
 
 	ice_trigger_vf_reset(vf, is_vflr);
 
+	vsi = pf->vsi[vf->lan_vsi_idx];
+
 	if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) {
-		ice_vsi_stop_tx_rings(pf->vsi[vf->lan_vsi_idx], ICE_VF_RESET,
-				      vf->vf_id);
-		ice_vsi_stop_rx_rings(pf->vsi[vf->lan_vsi_idx]);
+		ice_vsi_stop_lan_tx_rings(vsi, ICE_VF_RESET, vf->vf_id);
+		ice_vsi_stop_rx_rings(vsi);
 		clear_bit(ICE_VF_STATE_ENA, vf->vf_states);
 	} else {
 		/* Call Disable LAN Tx queue AQ call even when queues are not
 		 * enabled. This is needed for successful completiom of VFR
 		 */
-		ice_dis_vsi_txq(pf->vsi[vf->lan_vsi_idx]->port_info, 0,
-				NULL, NULL, ICE_VF_RESET, vf->vf_id, NULL);
+		ice_dis_vsi_txq(vsi->port_info, 0, NULL, NULL, ICE_VF_RESET,
+				vf->vf_id, NULL);
 	}
 
 	/* poll VPGEN_VFRSTAT reg to make sure
@@ -1105,7 +1122,7 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs)
  * ice_process_vflr_event - Free VF resources via IRQ calls
  * @pf: pointer to the PF structure
  *
- * called from the VLFR IRQ handler to
+ * called from the VFLR IRQ handler to
  * free up VF resources and state variables
  */
 void ice_process_vflr_event(struct ice_pf *pf)
@@ -1616,7 +1633,7 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg)
 		goto error_param;
 	}
 
-	if (ice_vsi_stop_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) {
+	if (ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) {
 		dev_err(&vsi->back->pdev->dev,
 			"Failed to stop tx rings on VSI %d\n",
 			vsi->vsi_num);
@@ -1764,7 +1781,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 		/* copy Tx queue info from VF into VSI */
 		vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr;
 		vsi->tx_rings[i]->count = qpi->txq.ring_len;
-		/* copy Rx queue info from VF into vsi */
+		/* copy Rx queue info from VF into VSI */
 		vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr;
 		vsi->rx_rings[i]->count = qpi->rxq.ring_len;
 		if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) {
@@ -1786,7 +1803,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	vsi->num_txq = qci->num_queue_pairs;
 	vsi->num_rxq = qci->num_queue_pairs;
 
-	if (!ice_vsi_cfg_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi))
+	if (!ice_vsi_cfg_lan_txqs(vsi) && !ice_vsi_cfg_rxqs(vsi))
 		aq_ret = 0;
 	else
 		aq_ret = ICE_ERR_PARAM;
@@ -1830,7 +1847,7 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf)
  * @msg: pointer to the msg buffer
  * @set: true if mac filters are being set, false otherwise
  *
- * add guest mac address filter
+ * add guest MAC address filter
  */
 static int
 ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set)
@@ -1968,9 +1985,9 @@ static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg)
  * @msg: pointer to the msg buffer
  *
  * VFs get a default number of queues but can use this message to request a
- * different number.  If the request is successful, PF will reset the VF and
+ * different number. If the request is successful, PF will reset the VF and
  * return 0. If unsuccessful, PF will send message informing VF of number of
- * available queue pairs via virtchnl message response to VF.
+ * available queue pairs via virtchnl message response to vf.
  */
 static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 {
@@ -1991,7 +2008,7 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg)
 	tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx);
 	if (req_queues <= 0) {
 		dev_err(&pf->pdev->dev,
-			"VF %d tried to request %d queues.  Ignoring.\n",
+			"VF %d tried to request %d queues. Ignoring.\n",
 			vf->vf_id, req_queues);
 	} else if (req_queues > ICE_MAX_QS_PER_VF) {
 		dev_err(&pf->pdev->dev,
@@ -2477,11 +2494,12 @@ int ice_get_vf_cfg(struct net_device *netdev, int vf_id,
 int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
 {
 	struct ice_netdev_priv *np = netdev_priv(netdev);
-	struct ice_vsi_ctx ctx = { 0 };
 	struct ice_vsi *vsi = np->vsi;
 	struct ice_pf *pf = vsi->back;
+	struct ice_vsi_ctx *ctx;
+	enum ice_status status;
 	struct ice_vf *vf;
-	int status;
+	int ret = 0;
 
 	/* validate the request */
 	if (vf_id >= pf->num_alloc_vfs) {
@@ -2501,25 +2519,31 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena)
 		return 0;
 	}
 
-	ctx.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
+	ctx = devm_kzalloc(&pf->pdev->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID);
 
 	if (ena) {
-		ctx.info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
-		ctx.info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M;
+		ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF;
+		ctx->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_PRUNE_EN_M;
 	}
 
-	status = ice_update_vsi(&pf->hw, vsi->idx, &ctx, NULL);
+	status = ice_update_vsi(&pf->hw, vsi->idx, ctx, NULL);
 	if (status) {
 		dev_dbg(&pf->pdev->dev,
 			"Error %d, failed to update VSI* parameters\n", status);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	vf->spoofchk = ena;
-	vsi->info.sec_flags = ctx.info.sec_flags;
-	vsi->info.sw_flags2 = ctx.info.sw_flags2;
-
-	return status;
+	vsi->info.sec_flags = ctx->info.sec_flags;
+	vsi->info.sw_flags2 = ctx->info.sw_flags2;
+out:
+	devm_kfree(&pf->pdev->dev, ctx);
+	return ret;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
index 10131e0180f9..01470a8ee03a 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h
@@ -70,7 +70,7 @@ struct ice_vf {
 	u8 spoofchk;
 	u16 num_mac;
 	u16 num_vlan;
-	u8 num_req_qs;		/* num of queue pairs requested by VF */
+	u8 num_req_qs;			/* num of queue pairs requested by VF */
 };
 
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 8a28f3388f69..d2e2c50ce257 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -194,6 +194,8 @@
 /* enable link status from external LINK_0 and LINK_1 pins */
 #define E1000_CTRL_SWDPIN0  0x00040000  /* SWDPIN 0 value */
 #define E1000_CTRL_SWDPIN1  0x00080000  /* SWDPIN 1 value */
+#define E1000_CTRL_ADVD3WUC 0x00100000  /* D3 WUC */
+#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000 /* PHY PM enable */
 #define E1000_CTRL_SDP0_DIR 0x00400000  /* SDP0 Data direction */
 #define E1000_CTRL_SDP1_DIR 0x00800000  /* SDP1 Data direction */
 #define E1000_CTRL_RST      0x04000000  /* Global reset */
@@ -334,6 +336,7 @@
 
 #define I210_RXPBSIZE_DEFAULT		0x000000A2 /* RXPBSIZE default */
 #define I210_RXPBSIZE_MASK		0x0000003F
+#define I210_RXPBSIZE_PB_30KB		0x0000001E
 #define I210_RXPBSIZE_PB_32KB		0x00000020
 #define I210_TXPBSIZE_DEFAULT		0x04000014 /* TXPBSIZE default */
 #define I210_TXPBSIZE_MASK		0xC0FFFFFF
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 5acf3b743876..c57671068245 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -2113,7 +2113,7 @@ static int igb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 
-	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE))
+	if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER))
 		return -EOPNOTSUPP;
 
 	if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED))
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 5df88ad8ac81..3269d8e94744 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -39,7 +39,7 @@
 #include "igb.h"
 
 #define MAJ 5
-#define MIN 4
+#define MIN 6
 #define BUILD 0
 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
 __stringify(BUILD) "-k"
@@ -1189,15 +1189,15 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
 {
 	struct igb_q_vector *q_vector;
 	struct igb_ring *ring;
-	int ring_count, size;
+	int ring_count;
+	size_t size;
 
 	/* igb only supports 1 Tx and/or 1 Rx queue per vector */
 	if (txr_count > 1 || rxr_count > 1)
 		return -ENOMEM;
 
 	ring_count = txr_count + rxr_count;
-	size = sizeof(struct igb_q_vector) +
-	       (sizeof(struct igb_ring) * ring_count);
+	size = struct_size(q_vector, ring, ring_count);
 
 	/* allocate q_vector and rings */
 	q_vector = adapter->q_vector[v_idx];
@@ -1850,13 +1850,12 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 	 * configuration' in respect to these parameters.
 	 */
 
-	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
-			    idleslope %d sendslope %d hiCredit %d \
-			    locredit %d\n",
-		   (ring->cbs_enable) ? "enabled" : "disabled",
-		   (ring->launchtime_enable) ? "enabled" : "disabled", queue,
-		   ring->idleslope, ring->sendslope, ring->hicredit,
-		   ring->locredit);
+	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
+		   ring->cbs_enable ? "enabled" : "disabled",
+		   ring->launchtime_enable ? "enabled" : "disabled",
+		   queue,
+		   ring->idleslope, ring->sendslope,
+		   ring->hicredit, ring->locredit);
 }
 
 static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
@@ -1935,7 +1934,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 
 		val = rd32(E1000_RXPBS);
 		val &= ~I210_RXPBSIZE_MASK;
-		val |= I210_RXPBSIZE_PB_32KB;
+		val |= I210_RXPBSIZE_PB_30KB;
 		wr32(E1000_RXPBS, val);
 
 		/* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ
@@ -2487,7 +2486,8 @@ static int igb_set_features(struct net_device *netdev,
 static int igb_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			   struct net_device *dev,
 			   const unsigned char *addr, u16 vid,
-			   u16 flags)
+			   u16 flags,
+			   struct netlink_ext_ack *extack)
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -2581,9 +2581,11 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 				int traffic_class,
 				struct igb_nfc_filter *input)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	struct netlink_ext_ack *extack = f->common.extack;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -2593,78 +2595,60 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 		return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key, *mask;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						 f->mask);
-
-		if (!is_zero_ether_addr(mask->dst)) {
-			if (!is_broadcast_ether_addr(mask->dst)) {
+		flow_rule_match_eth_addrs(rule, &match);
+		if (!is_zero_ether_addr(match.mask->dst)) {
+			if (!is_broadcast_ether_addr(match.mask->dst)) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |=
 				IGB_FILTER_FLAG_DST_MAC_ADDR;
-			ether_addr_copy(input->filter.dst_addr, key->dst);
+			ether_addr_copy(input->filter.dst_addr, match.key->dst);
 		}
 
-		if (!is_zero_ether_addr(mask->src)) {
-			if (!is_broadcast_ether_addr(mask->src)) {
+		if (!is_zero_ether_addr(match.mask->src)) {
+			if (!is_broadcast_ether_addr(match.mask->src)) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |=
 				IGB_FILTER_FLAG_SRC_MAC_ADDR;
-			ether_addr_copy(input->filter.src_addr, key->src);
+			ether_addr_copy(input->filter.src_addr, match.key->src);
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_BASIC,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_BASIC,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		if (mask->n_proto) {
-			if (mask->n_proto != ETHER_TYPE_FULL_MASK) {
+		flow_rule_match_basic(rule, &match);
+		if (match.mask->n_proto) {
+			if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE;
-			input->filter.etype = key->n_proto;
+			input->filter.etype = match.key->n_proto;
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_VLAN,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_VLAN,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
-		if (mask->vlan_priority) {
-			if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_priority) {
+			if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) {
 				NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority");
 				return -EINVAL;
 			}
 
 			input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI;
-			input->filter.vlan_tci = key->vlan_priority;
+			input->filter.vlan_tci = match.key->vlan_priority;
 		}
 	}
 
@@ -6019,6 +6003,8 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
 	 * memory model archs, such as IA-64).
@@ -6147,8 +6133,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	else if (!tso)
 		igb_tx_csum(tx_ring, first);
 
-	skb_tx_timestamp(skb);
-
 	if (igb_tx_map(tx_ring, first, hdr_len))
 		goto cleanup_tx_tstamp;
 
@@ -7753,11 +7737,13 @@ static int igb_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* If not enough Rx work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-	igb_ring_irq_enable(q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		igb_ring_irq_enable(q_vector);
 
-	return 0;
+	return min(work_done, budget - 1);
 }
 
 /**
@@ -8754,9 +8740,7 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl, rctl, status;
 	u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
-#ifdef CONFIG_PM
-	int retval = 0;
-#endif
+	bool wake;
 
 	rtnl_lock();
 	netif_device_detach(netdev);
@@ -8769,12 +8753,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 	igb_clear_interrupt_scheme(adapter);
 	rtnl_unlock();
 
-#ifdef CONFIG_PM
-	retval = pci_save_state(pdev);
-	if (retval)
-		return retval;
-#endif
-
 	status = rd32(E1000_STATUS);
 	if (status & E1000_STATUS_LU)
 		wufc &= ~E1000_WUFC_LNKC;
@@ -8791,10 +8769,6 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 		}
 
 		ctrl = rd32(E1000_CTRL);
-		/* advertise wake from D3Cold */
-		#define E1000_CTRL_ADVD3WUC 0x00100000
-		/* phy power management enable */
-		#define E1000_CTRL_EN_PHY_PWR_MGMT 0x00200000
 		ctrl |= E1000_CTRL_ADVD3WUC;
 		wr32(E1000_CTRL, ctrl);
 
@@ -8808,12 +8782,15 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake,
 		wr32(E1000_WUFC, 0);
 	}
 
-	*enable_wake = wufc || adapter->en_mng_pt;
-	if (!*enable_wake)
+	wake = wufc || adapter->en_mng_pt;
+	if (!wake)
 		igb_power_down_link(adapter);
 	else
 		igb_power_up_link(adapter);
 
+	if (enable_wake)
+		*enable_wake = wake;
+
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant.
 	 */
@@ -8856,22 +8833,7 @@ static void igb_deliver_wake_packet(struct net_device *netdev)
 
 static int __maybe_unused igb_suspend(struct device *dev)
 {
-	int retval;
-	bool wake;
-	struct pci_dev *pdev = to_pci_dev(dev);
-
-	retval = __igb_shutdown(pdev, &wake, 0);
-	if (retval)
-		return retval;
-
-	if (wake) {
-		pci_prepare_to_sleep(pdev);
-	} else {
-		pci_wake_from_d3(pdev, false);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
-
-	return 0;
+	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
 static int __maybe_unused igb_resume(struct device *dev)
@@ -8942,22 +8904,7 @@ static int __maybe_unused igb_runtime_idle(struct device *dev)
 
 static int __maybe_unused igb_runtime_suspend(struct device *dev)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	int retval;
-	bool wake;
-
-	retval = __igb_shutdown(pdev, &wake, 1);
-	if (retval)
-		return retval;
-
-	if (wake) {
-		pci_prepare_to_sleep(pdev);
-	} else {
-		pci_wake_from_d3(pdev, false);
-		pci_set_power_state(pdev, PCI_D3hot);
-	}
-
-	return 0;
+	return __igb_shutdown(to_pci_dev(dev), NULL, 1);
 }
 
 static int __maybe_unused igb_runtime_resume(struct device *dev)
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 2b95dc9c7a6a..fd3071f55bd3 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -277,17 +277,53 @@ static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta)
 	return 0;
 }
 
-static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp,
-				 struct timespec64 *ts)
+static int igb_ptp_gettimex_82576(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
 {
 	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
 					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
 	unsigned long flags;
+	u32 lo, hi;
 	u64 ns;
 
 	spin_lock_irqsave(&igb->tmreg_lock, flags);
 
-	ns = timecounter_read(&igb->tc);
+	ptp_read_system_prets(sts);
+	lo = rd32(E1000_SYSTIML);
+	ptp_read_system_postts(sts);
+	hi = rd32(E1000_SYSTIMH);
+
+	ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo);
+
+	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
+
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int igb_ptp_gettimex_82580(struct ptp_clock_info *ptp,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
+					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
+	unsigned long flags;
+	u32 lo, hi;
+	u64 ns;
+
+	spin_lock_irqsave(&igb->tmreg_lock, flags);
+
+	ptp_read_system_prets(sts);
+	rd32(E1000_SYSTIMR);
+	ptp_read_system_postts(sts);
+	lo = rd32(E1000_SYSTIML);
+	hi = rd32(E1000_SYSTIMH);
+
+	ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo);
 
 	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
 
@@ -296,16 +332,22 @@ static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp,
-				struct timespec64 *ts)
+static int igb_ptp_gettimex_i210(struct ptp_clock_info *ptp,
+				 struct timespec64 *ts,
+				 struct ptp_system_timestamp *sts)
 {
 	struct igb_adapter *igb = container_of(ptp, struct igb_adapter,
 					       ptp_caps);
+	struct e1000_hw *hw = &igb->hw;
 	unsigned long flags;
 
 	spin_lock_irqsave(&igb->tmreg_lock, flags);
 
-	igb_ptp_read_i210(igb, ts);
+	ptp_read_system_prets(sts);
+	rd32(E1000_SYSTIMR);
+	ptp_read_system_postts(sts);
+	ts->tv_nsec = rd32(E1000_SYSTIML);
+	ts->tv_sec = rd32(E1000_SYSTIMH);
 
 	spin_unlock_irqrestore(&igb->tmreg_lock, flags);
 
@@ -658,9 +700,12 @@ static void igb_ptp_overflow_check(struct work_struct *work)
 	struct igb_adapter *igb =
 		container_of(work, struct igb_adapter, ptp_overflow_work.work);
 	struct timespec64 ts;
+	u64 ns;
 
-	igb->ptp_caps.gettime64(&igb->ptp_caps, &ts);
+	/* Update the timecounter */
+	ns = timecounter_read(&igb->tc);
 
+	ts = ns_to_timespec64(ns);
 	pr_debug("igb overflow check at %lld.%09lu\n",
 		 (long long) ts.tv_sec, ts.tv_nsec);
 
@@ -1126,7 +1171,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
-		adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
+		adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82576;
 		adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		adapter->cc.read = igb_ptp_read_82576;
@@ -1145,7 +1190,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576;
-		adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576;
+		adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82580;
 		adapter->ptp_caps.settime64 = igb_ptp_settime_82576;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable;
 		adapter->cc.read = igb_ptp_read_82580;
@@ -1173,7 +1218,7 @@ void igb_ptp_init(struct igb_adapter *adapter)
 		adapter->ptp_caps.pin_config = adapter->sdp_config;
 		adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580;
 		adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210;
-		adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210;
+		adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_i210;
 		adapter->ptp_caps.settime64 = igb_ptp_settime_i210;
 		adapter->ptp_caps.enable = igb_ptp_feature_enable_i210;
 		adapter->ptp_caps.verify = igb_ptp_verify_pin;
diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c
index 163e5838f7c2..a3cd7ac48d4b 100644
--- a/drivers/net/ethernet/intel/igbvf/mbx.c
+++ b/drivers/net/ethernet/intel/igbvf/mbx.c
@@ -241,7 +241,7 @@ static s32 e1000_write_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size)
 	s32 err;
 	u16 i;
 
-	WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock));
+	lockdep_assert_held(&hw->mbx_lock);
 
 	/* lock the mailbox to prevent pf/vf race condition */
 	err = e1000_obtain_mbx_lock_vf(hw);
@@ -279,7 +279,7 @@ static s32 e1000_read_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size)
 	s32 err;
 	u16 i;
 
-	WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock));
+	lockdep_assert_held(&hw->mbx_lock);
 
 	/* lock the mailbox to prevent pf/vf race condition */
 	err = e1000_obtain_mbx_lock_vf(hw);
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 820d49eb41ab..4eab83faec62 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1186,10 +1186,13 @@ static int igbvf_poll(struct napi_struct *napi, int budget)
 
 	igbvf_clean_rx_irq(adapter, &work_done, budget);
 
-	/* If not enough Rx work done, exit the polling mode */
-	if (work_done < budget) {
-		napi_complete_done(napi, work_done);
+	if (work_done == budget)
+		return budget;
 
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
 		if (adapter->requested_itr & 3)
 			igbvf_set_itr(adapter);
 
diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile
index 4387f6ba8e67..88c6f88baac5 100644
--- a/drivers/net/ethernet/intel/igc/Makefile
+++ b/drivers/net/ethernet/intel/igc/Makefile
@@ -7,4 +7,5 @@
 
 obj-$(CONFIG_IGC) += igc.o
 
-igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o
+igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \
+igc_ethtool.o
diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index cdf18a5d9e08..80faccc34cda 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -5,38 +5,51 @@
 #define _IGC_H_
 
 #include <linux/kobject.h>
-
 #include <linux/pci.h>
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
-
 #include <linux/ethtool.h>
-
 #include <linux/sctp.h>
 
-#define IGC_ERR(args...) pr_err("igc: " args)
-
-#define PFX "igc: "
-
-#include <linux/timecounter.h>
-#include <linux/net_tstamp.h>
-#include <linux/ptp_clock_kernel.h>
-
 #include "igc_hw.h"
 
-/* main */
+/* forward declaration */
+void igc_set_ethtool_ops(struct net_device *);
+
+struct igc_adapter;
+struct igc_ring;
+
+void igc_up(struct igc_adapter *adapter);
+void igc_down(struct igc_adapter *adapter);
+int igc_setup_tx_resources(struct igc_ring *ring);
+int igc_setup_rx_resources(struct igc_ring *ring);
+void igc_free_tx_resources(struct igc_ring *ring);
+void igc_free_rx_resources(struct igc_ring *ring);
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter);
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+			      const u32 max_rss_queues);
+int igc_reinit_queues(struct igc_adapter *adapter);
+bool igc_has_link(struct igc_adapter *adapter);
+void igc_reset(struct igc_adapter *adapter);
+int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx);
+
 extern char igc_driver_name[];
 extern char igc_driver_version[];
 
+#define IGC_REGS_LEN			740
+#define IGC_RETA_SIZE			128
+
 /* Interrupt defines */
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_FLAG_HAS_MSI		BIT(0)
-#define IGC_FLAG_QUEUE_PAIRS		BIT(4)
+#define IGC_FLAG_QUEUE_PAIRS		BIT(3)
+#define IGC_FLAG_DMAC			BIT(4)
 #define IGC_FLAG_NEED_LINK_UPDATE	BIT(9)
 #define IGC_FLAG_MEDIA_RESET		BIT(10)
 #define IGC_FLAG_MAS_ENABLE		BIT(12)
 #define IGC_FLAG_HAS_MSIX		BIT(13)
 #define IGC_FLAG_VLAN_PROMISC		BIT(15)
+#define IGC_FLAG_RX_LEGACY		BIT(16)
 
 #define IGC_START_ITR			648 /* ~6000 ints/sec */
 #define IGC_4K_ITR			980
@@ -71,6 +84,7 @@ extern char igc_driver_version[];
 #define IGC_RXBUFFER_2048		2048
 #define IGC_RXBUFFER_3072		3072
 
+#define AUTO_ALL_MODES		0
 #define IGC_RX_HDR_LEN			IGC_RXBUFFER_256
 
 /* RX and TX descriptor control thresholds.
@@ -351,6 +365,8 @@ struct igc_adapter {
 
 	struct igc_mac_addr *mac_table;
 
+	u8 rss_indir_tbl[IGC_RETA_SIZE];
+
 	unsigned long link_check_timeout;
 	struct igc_info ei;
 };
@@ -429,6 +445,9 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data)
 	return 0;
 }
 
+/* forward declaration */
+void igc_reinit_locked(struct igc_adapter *);
+
 #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring))
 
 #define IGC_TXD_DCMD	(IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS)
diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c
index 832da609d9a7..51a8b8769c67 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.c
+++ b/drivers/net/ethernet/intel/igc/igc_base.c
@@ -54,22 +54,6 @@ out:
 }
 
 /**
- * igc_check_for_link_base - Check for link
- * @hw: pointer to the HW structure
- *
- * If sgmii is enabled, then use the pcs register to determine link, otherwise
- * use the generic interface for determining link.
- */
-static s32 igc_check_for_link_base(struct igc_hw *hw)
-{
-	s32 ret_val = 0;
-
-	ret_val = igc_check_for_copper_link(hw);
-
-	return ret_val;
-}
-
-/**
  * igc_reset_hw_base - Reset hardware
  * @hw: pointer to the HW structure
  *
@@ -124,22 +108,6 @@ static s32 igc_reset_hw_base(struct igc_hw *hw)
 }
 
 /**
- * igc_get_phy_id_base - Retrieve PHY addr and id
- * @hw: pointer to the HW structure
- *
- * Retrieves the PHY address and ID for both PHY's which do and do not use
- * sgmi interface.
- */
-static s32 igc_get_phy_id_base(struct igc_hw *hw)
-{
-	s32  ret_val = 0;
-
-	ret_val = igc_get_phy_id(hw);
-
-	return ret_val;
-}
-
-/**
  * igc_init_nvm_params_base - Init NVM func ptrs.
  * @hw: pointer to the HW structure
  */
@@ -163,6 +131,7 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw)
 	if (size > 15)
 		size = 15;
 
+	nvm->type = igc_nvm_eeprom_spi;
 	nvm->word_size = BIT(size);
 	nvm->opcode_bits = 8;
 	nvm->delay_usec = 1;
@@ -237,7 +206,6 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 {
 	struct igc_phy_info *phy = &hw->phy;
 	s32 ret_val = 0;
-	u32 ctrl_ext;
 
 	if (hw->phy.media_type != igc_media_type_copper) {
 		phy->type = igc_phy_none;
@@ -247,8 +215,6 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 	phy->autoneg_mask	= AUTONEG_ADVERTISE_SPEED_DEFAULT_2500;
 	phy->reset_delay_us	= 100;
 
-	ctrl_ext = rd32(IGC_CTRL_EXT);
-
 	/* set lan id */
 	hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >>
 			IGC_STATUS_FUNC_SHIFT;
@@ -264,11 +230,11 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw)
 		goto out;
 	}
 
-	ret_val = igc_get_phy_id_base(hw);
+	ret_val = igc_get_phy_id(hw);
 	if (ret_val)
 		return ret_val;
 
-	igc_check_for_link_base(hw);
+	igc_check_for_copper_link(hw);
 
 	/* Verify phy id and set remaining function pointers */
 	switch (phy->id) {
@@ -287,8 +253,6 @@ out:
 static s32 igc_get_invariants_base(struct igc_hw *hw)
 {
 	struct igc_mac_info *mac = &hw->mac;
-	u32 link_mode = 0;
-	u32 ctrl_ext = 0;
 	s32 ret_val = 0;
 
 	switch (hw->device_id) {
@@ -302,9 +266,6 @@ static s32 igc_get_invariants_base(struct igc_hw *hw)
 
 	hw->phy.media_type = igc_media_type_copper;
 
-	ctrl_ext = rd32(IGC_CTRL_EXT);
-	link_mode = ctrl_ext & IGC_CTRL_EXT_LINK_MODE_MASK;
-
 	/* mac initialization and operations */
 	ret_val = igc_init_mac_params_base(hw);
 	if (ret_val)
@@ -358,26 +319,6 @@ static void igc_release_phy_base(struct igc_hw *hw)
 }
 
 /**
- * igc_get_link_up_info_base - Get link speed/duplex info
- * @hw: pointer to the HW structure
- * @speed: stores the current speed
- * @duplex: stores the current duplex
- *
- * This is a wrapper function, if using the serial gigabit media independent
- * interface, use PCS to retrieve the link speed and duplex information.
- * Otherwise, use the generic function to get the link speed and duplex info.
- */
-static s32 igc_get_link_up_info_base(struct igc_hw *hw, u16 *speed,
-				     u16 *duplex)
-{
-	s32 ret_val;
-
-	ret_val = igc_get_speed_and_duplex_copper(hw, speed, duplex);
-
-	return ret_val;
-}
-
-/**
  * igc_init_hw_base - Initialize hardware
  * @hw: pointer to the HW structure
  *
@@ -416,19 +357,6 @@ static s32 igc_init_hw_base(struct igc_hw *hw)
 }
 
 /**
- * igc_read_mac_addr_base - Read device MAC address
- * @hw: pointer to the HW structure
- */
-static s32 igc_read_mac_addr_base(struct igc_hw *hw)
-{
-	s32 ret_val = 0;
-
-	ret_val = igc_read_mac_addr(hw);
-
-	return ret_val;
-}
-
-/**
  * igc_power_down_phy_copper_base - Remove link during PHY power down
  * @hw: pointer to the HW structure
  *
@@ -520,10 +448,10 @@ void igc_rx_fifo_flush_base(struct igc_hw *hw)
 
 static struct igc_mac_operations igc_mac_ops_base = {
 	.init_hw		= igc_init_hw_base,
-	.check_for_link		= igc_check_for_link_base,
+	.check_for_link		= igc_check_for_copper_link,
 	.rar_set		= igc_rar_set,
-	.read_mac_addr		= igc_read_mac_addr_base,
-	.get_speed_and_duplex	= igc_get_link_up_info_base,
+	.read_mac_addr		= igc_read_mac_addr,
+	.get_speed_and_duplex	= igc_get_speed_and_duplex_copper,
 };
 
 static const struct igc_phy_operations igc_phy_ops_base = {
diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h
index 35588fa7b8c5..76d4991d7284 100644
--- a/drivers/net/ethernet/intel/igc/igc_base.h
+++ b/drivers/net/ethernet/intel/igc/igc_base.h
@@ -36,28 +36,6 @@ union igc_adv_tx_desc {
 
 #define IGC_RAR_ENTRIES		16
 
-struct igc_adv_data_desc {
-	__le64 buffer_addr;    /* Address of the descriptor's data buffer */
-	union {
-		u32 data;
-		struct {
-			u32 datalen:16; /* Data buffer length */
-			u32 rsvd:4;
-			u32 dtyp:4;  /* Descriptor type */
-			u32 dcmd:8;  /* Descriptor command */
-		} config;
-	} lower;
-	union {
-		u32 data;
-		struct {
-			u32 status:4;  /* Descriptor status */
-			u32 idx:4;
-			u32 popts:6;  /* Packet Options */
-			u32 paylen:18; /* Payload length */
-		} options;
-	} upper;
-};
-
 /* Receive Descriptor - Advanced */
 union igc_adv_rx_desc {
 	struct {
@@ -90,9 +68,6 @@ union igc_adv_rx_desc {
 	} wb;  /* writeback */
 };
 
-/* Adv Transmit Descriptor Config Masks */
-#define IGC_ADVTXD_PAYLEN_SHIFT	14 /* Adv desc PAYLEN shift */
-
 /* Additional Transmit Descriptor Control definitions */
 #define IGC_TXDCTL_QUEUE_ENABLE	0x02000000 /* Ena specific Tx Queue */
 
diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
index 8740754ea1fd..7d1bdcd1225a 100644
--- a/drivers/net/ethernet/intel/igc/igc_defines.h
+++ b/drivers/net/ethernet/intel/igc/igc_defines.h
@@ -4,6 +4,10 @@
 #ifndef _IGC_DEFINES_H_
 #define _IGC_DEFINES_H_
 
+/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+#define REQ_TX_DESCRIPTOR_MULTIPLE  8
+#define REQ_RX_DESCRIPTOR_MULTIPLE  8
+
 #define IGC_CTRL_EXT_DRV_LOAD	0x10000000 /* Drv loaded bit for FW */
 
 /* PCI Bus Info */
diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c
new file mode 100644
index 000000000000..eff37a6c0afa
--- /dev/null
+++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c
@@ -0,0 +1,1032 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c)  2018 Intel Corporation */
+
+/* ethtool support for igc */
+#include <linux/pm_runtime.h>
+
+#include "igc.h"
+
+static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = {
+#define IGC_PRIV_FLAGS_LEGACY_RX	BIT(0)
+	"legacy-rx",
+};
+
+#define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings)
+
+static void igc_get_drvinfo(struct net_device *netdev,
+			    struct ethtool_drvinfo *drvinfo)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(drvinfo->driver,  igc_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, igc_driver_version, sizeof(drvinfo->version));
+
+	/* add fw_version here */
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
+
+	drvinfo->n_priv_flags = IGC_PRIV_FLAGS_STR_LEN;
+}
+
+static int igc_get_regs_len(struct net_device *netdev)
+{
+	return IGC_REGS_LEN * sizeof(u32);
+}
+
+static void igc_get_regs(struct net_device *netdev,
+			 struct ethtool_regs *regs, void *p)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 *regs_buff = p;
+	u8 i;
+
+	memset(p, 0, IGC_REGS_LEN * sizeof(u32));
+
+	regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id;
+
+	/* General Registers */
+	regs_buff[0] = rd32(IGC_CTRL);
+	regs_buff[1] = rd32(IGC_STATUS);
+	regs_buff[2] = rd32(IGC_CTRL_EXT);
+	regs_buff[3] = rd32(IGC_MDIC);
+	regs_buff[4] = rd32(IGC_CONNSW);
+
+	/* NVM Register */
+	regs_buff[5] = rd32(IGC_EECD);
+
+	/* Interrupt */
+	/* Reading EICS for EICR because they read the
+	 * same but EICS does not clear on read
+	 */
+	regs_buff[6] = rd32(IGC_EICS);
+	regs_buff[7] = rd32(IGC_EICS);
+	regs_buff[8] = rd32(IGC_EIMS);
+	regs_buff[9] = rd32(IGC_EIMC);
+	regs_buff[10] = rd32(IGC_EIAC);
+	regs_buff[11] = rd32(IGC_EIAM);
+	/* Reading ICS for ICR because they read the
+	 * same but ICS does not clear on read
+	 */
+	regs_buff[12] = rd32(IGC_ICS);
+	regs_buff[13] = rd32(IGC_ICS);
+	regs_buff[14] = rd32(IGC_IMS);
+	regs_buff[15] = rd32(IGC_IMC);
+	regs_buff[16] = rd32(IGC_IAC);
+	regs_buff[17] = rd32(IGC_IAM);
+
+	/* Flow Control */
+	regs_buff[18] = rd32(IGC_FCAL);
+	regs_buff[19] = rd32(IGC_FCAH);
+	regs_buff[20] = rd32(IGC_FCTTV);
+	regs_buff[21] = rd32(IGC_FCRTL);
+	regs_buff[22] = rd32(IGC_FCRTH);
+	regs_buff[23] = rd32(IGC_FCRTV);
+
+	/* Receive */
+	regs_buff[24] = rd32(IGC_RCTL);
+	regs_buff[25] = rd32(IGC_RXCSUM);
+	regs_buff[26] = rd32(IGC_RLPML);
+	regs_buff[27] = rd32(IGC_RFCTL);
+
+	/* Transmit */
+	regs_buff[28] = rd32(IGC_TCTL);
+	regs_buff[29] = rd32(IGC_TIPG);
+
+	/* Wake Up */
+
+	/* MAC */
+
+	/* Statistics */
+	regs_buff[30] = adapter->stats.crcerrs;
+	regs_buff[31] = adapter->stats.algnerrc;
+	regs_buff[32] = adapter->stats.symerrs;
+	regs_buff[33] = adapter->stats.rxerrc;
+	regs_buff[34] = adapter->stats.mpc;
+	regs_buff[35] = adapter->stats.scc;
+	regs_buff[36] = adapter->stats.ecol;
+	regs_buff[37] = adapter->stats.mcc;
+	regs_buff[38] = adapter->stats.latecol;
+	regs_buff[39] = adapter->stats.colc;
+	regs_buff[40] = adapter->stats.dc;
+	regs_buff[41] = adapter->stats.tncrs;
+	regs_buff[42] = adapter->stats.sec;
+	regs_buff[43] = adapter->stats.htdpmc;
+	regs_buff[44] = adapter->stats.rlec;
+	regs_buff[45] = adapter->stats.xonrxc;
+	regs_buff[46] = adapter->stats.xontxc;
+	regs_buff[47] = adapter->stats.xoffrxc;
+	regs_buff[48] = adapter->stats.xofftxc;
+	regs_buff[49] = adapter->stats.fcruc;
+	regs_buff[50] = adapter->stats.prc64;
+	regs_buff[51] = adapter->stats.prc127;
+	regs_buff[52] = adapter->stats.prc255;
+	regs_buff[53] = adapter->stats.prc511;
+	regs_buff[54] = adapter->stats.prc1023;
+	regs_buff[55] = adapter->stats.prc1522;
+	regs_buff[56] = adapter->stats.gprc;
+	regs_buff[57] = adapter->stats.bprc;
+	regs_buff[58] = adapter->stats.mprc;
+	regs_buff[59] = adapter->stats.gptc;
+	regs_buff[60] = adapter->stats.gorc;
+	regs_buff[61] = adapter->stats.gotc;
+	regs_buff[62] = adapter->stats.rnbc;
+	regs_buff[63] = adapter->stats.ruc;
+	regs_buff[64] = adapter->stats.rfc;
+	regs_buff[65] = adapter->stats.roc;
+	regs_buff[66] = adapter->stats.rjc;
+	regs_buff[67] = adapter->stats.mgprc;
+	regs_buff[68] = adapter->stats.mgpdc;
+	regs_buff[69] = adapter->stats.mgptc;
+	regs_buff[70] = adapter->stats.tor;
+	regs_buff[71] = adapter->stats.tot;
+	regs_buff[72] = adapter->stats.tpr;
+	regs_buff[73] = adapter->stats.tpt;
+	regs_buff[74] = adapter->stats.ptc64;
+	regs_buff[75] = adapter->stats.ptc127;
+	regs_buff[76] = adapter->stats.ptc255;
+	regs_buff[77] = adapter->stats.ptc511;
+	regs_buff[78] = adapter->stats.ptc1023;
+	regs_buff[79] = adapter->stats.ptc1522;
+	regs_buff[80] = adapter->stats.mptc;
+	regs_buff[81] = adapter->stats.bptc;
+	regs_buff[82] = adapter->stats.tsctc;
+	regs_buff[83] = adapter->stats.iac;
+	regs_buff[84] = adapter->stats.rpthc;
+	regs_buff[85] = adapter->stats.hgptc;
+	regs_buff[86] = adapter->stats.hgorc;
+	regs_buff[87] = adapter->stats.hgotc;
+	regs_buff[88] = adapter->stats.lenerrs;
+	regs_buff[89] = adapter->stats.scvpc;
+	regs_buff[90] = adapter->stats.hrmpc;
+
+	for (i = 0; i < 4; i++)
+		regs_buff[91 + i] = rd32(IGC_SRRCTL(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[95 + i] = rd32(IGC_PSRTYPE(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[99 + i] = rd32(IGC_RDBAL(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[103 + i] = rd32(IGC_RDBAH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[107 + i] = rd32(IGC_RDLEN(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[111 + i] = rd32(IGC_RDH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[115 + i] = rd32(IGC_RDT(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[119 + i] = rd32(IGC_RXDCTL(i));
+
+	for (i = 0; i < 10; i++)
+		regs_buff[123 + i] = rd32(IGC_EITR(i));
+	for (i = 0; i < 16; i++)
+		regs_buff[139 + i] = rd32(IGC_RAL(i));
+	for (i = 0; i < 16; i++)
+		regs_buff[145 + i] = rd32(IGC_RAH(i));
+
+	for (i = 0; i < 4; i++)
+		regs_buff[149 + i] = rd32(IGC_TDBAL(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[152 + i] = rd32(IGC_TDBAH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[156 + i] = rd32(IGC_TDLEN(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[160 + i] = rd32(IGC_TDH(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[164 + i] = rd32(IGC_TDT(i));
+	for (i = 0; i < 4; i++)
+		regs_buff[168 + i] = rd32(IGC_TXDCTL(i));
+}
+
+static u32 igc_get_msglevel(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->msg_enable;
+}
+
+static void igc_set_msglevel(struct net_device *netdev, u32 data)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	adapter->msg_enable = data;
+}
+
+static int igc_nway_reset(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	if (netif_running(netdev))
+		igc_reinit_locked(adapter);
+	return 0;
+}
+
+static u32 igc_get_link(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_mac_info *mac = &adapter->hw.mac;
+
+	/* If the link is not reported up to netdev, interrupts are disabled,
+	 * and so the physical link state may have changed since we last
+	 * looked. Set get_link_status to make sure that the true link
+	 * state is interrogated, rather than pulling a cached and possibly
+	 * stale link state from the driver.
+	 */
+	if (!netif_carrier_ok(netdev))
+		mac->get_link_status = 1;
+
+	return igc_has_link(adapter);
+}
+
+static int igc_get_eeprom_len(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->hw.nvm.word_size * 2;
+}
+
+static int igc_get_eeprom(struct net_device *netdev,
+			  struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int first_word, last_word;
+	u16 *eeprom_buff;
+	int ret_val = 0;
+	u16 i;
+
+	if (eeprom->len == 0)
+		return -EINVAL;
+
+	eeprom->magic = hw->vendor_id | (hw->device_id << 16);
+
+	first_word = eeprom->offset >> 1;
+	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+
+	eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16),
+				    GFP_KERNEL);
+	if (!eeprom_buff)
+		return -ENOMEM;
+
+	if (hw->nvm.type == igc_nvm_eeprom_spi) {
+		ret_val = hw->nvm.ops.read(hw, first_word,
+					   last_word - first_word + 1,
+					   eeprom_buff);
+	} else {
+		for (i = 0; i < last_word - first_word + 1; i++) {
+			ret_val = hw->nvm.ops.read(hw, first_word + i, 1,
+						   &eeprom_buff[i]);
+			if (ret_val)
+				break;
+		}
+	}
+
+	/* Device's eeprom is always little-endian, word addressable */
+	for (i = 0; i < last_word - first_word + 1; i++)
+		le16_to_cpus(&eeprom_buff[i]);
+
+	memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1),
+	       eeprom->len);
+	kfree(eeprom_buff);
+
+	return ret_val;
+}
+
+static int igc_set_eeprom(struct net_device *netdev,
+			  struct ethtool_eeprom *eeprom, u8 *bytes)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int max_len, first_word, last_word, ret_val = 0;
+	u16 *eeprom_buff;
+	void *ptr;
+	u16 i;
+
+	if (eeprom->len == 0)
+		return -EOPNOTSUPP;
+
+	if (hw->mac.type >= igc_i225 &&
+	    !igc_get_flash_presence_i225(hw)) {
+		return -EOPNOTSUPP;
+	}
+
+	if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16)))
+		return -EFAULT;
+
+	max_len = hw->nvm.word_size * 2;
+
+	first_word = eeprom->offset >> 1;
+	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+	eeprom_buff = kmalloc(max_len, GFP_KERNEL);
+	if (!eeprom_buff)
+		return -ENOMEM;
+
+	ptr = (void *)eeprom_buff;
+
+	if (eeprom->offset & 1) {
+		/* need read/modify/write of first changed EEPROM word
+		 * only the second byte of the word is being modified
+		 */
+		ret_val = hw->nvm.ops.read(hw, first_word, 1,
+					    &eeprom_buff[0]);
+		ptr++;
+	}
+	if (((eeprom->offset + eeprom->len) & 1) && ret_val == 0) {
+		/* need read/modify/write of last changed EEPROM word
+		 * only the first byte of the word is being modified
+		 */
+		ret_val = hw->nvm.ops.read(hw, last_word, 1,
+				   &eeprom_buff[last_word - first_word]);
+	}
+
+	/* Device's eeprom is always little-endian, word addressable */
+	for (i = 0; i < last_word - first_word + 1; i++)
+		le16_to_cpus(&eeprom_buff[i]);
+
+	memcpy(ptr, bytes, eeprom->len);
+
+	for (i = 0; i < last_word - first_word + 1; i++)
+		eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+
+	ret_val = hw->nvm.ops.write(hw, first_word,
+				    last_word - first_word + 1, eeprom_buff);
+
+	/* Update the checksum if nvm write succeeded */
+	if (ret_val == 0)
+		hw->nvm.ops.update(hw);
+
+	/* check if need: igc_set_fw_version(adapter); */
+	kfree(eeprom_buff);
+	return ret_val;
+}
+
+static void igc_get_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *ring)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	ring->rx_max_pending = IGC_MAX_RXD;
+	ring->tx_max_pending = IGC_MAX_TXD;
+	ring->rx_pending = adapter->rx_ring_count;
+	ring->tx_pending = adapter->tx_ring_count;
+}
+
+static int igc_set_ringparam(struct net_device *netdev,
+			     struct ethtool_ringparam *ring)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_ring *temp_ring;
+	u16 new_rx_count, new_tx_count;
+	int i, err = 0;
+
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending)
+		return -EINVAL;
+
+	new_rx_count = min_t(u32, ring->rx_pending, IGC_MAX_RXD);
+	new_rx_count = max_t(u16, new_rx_count, IGC_MIN_RXD);
+	new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE);
+
+	new_tx_count = min_t(u32, ring->tx_pending, IGC_MAX_TXD);
+	new_tx_count = max_t(u16, new_tx_count, IGC_MIN_TXD);
+	new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE);
+
+	if (new_tx_count == adapter->tx_ring_count &&
+	    new_rx_count == adapter->rx_ring_count) {
+		/* nothing to do */
+		return 0;
+	}
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	if (!netif_running(adapter->netdev)) {
+		for (i = 0; i < adapter->num_tx_queues; i++)
+			adapter->tx_ring[i]->count = new_tx_count;
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			adapter->rx_ring[i]->count = new_rx_count;
+		adapter->tx_ring_count = new_tx_count;
+		adapter->rx_ring_count = new_rx_count;
+		goto clear_reset;
+	}
+
+	if (adapter->num_tx_queues > adapter->num_rx_queues)
+		temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
+					       adapter->num_tx_queues));
+	else
+		temp_ring = vmalloc(array_size(sizeof(struct igc_ring),
+					       adapter->num_rx_queues));
+
+	if (!temp_ring) {
+		err = -ENOMEM;
+		goto clear_reset;
+	}
+
+	igc_down(adapter);
+
+	/* We can't just free everything and then setup again,
+	 * because the ISRs in MSI-X mode get passed pointers
+	 * to the Tx and Rx ring structs.
+	 */
+	if (new_tx_count != adapter->tx_ring_count) {
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			memcpy(&temp_ring[i], adapter->tx_ring[i],
+			       sizeof(struct igc_ring));
+
+			temp_ring[i].count = new_tx_count;
+			err = igc_setup_tx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					igc_free_tx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			igc_free_tx_resources(adapter->tx_ring[i]);
+
+			memcpy(adapter->tx_ring[i], &temp_ring[i],
+			       sizeof(struct igc_ring));
+		}
+
+		adapter->tx_ring_count = new_tx_count;
+	}
+
+	if (new_rx_count != adapter->rx_ring_count) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			memcpy(&temp_ring[i], adapter->rx_ring[i],
+			       sizeof(struct igc_ring));
+
+			temp_ring[i].count = new_rx_count;
+			err = igc_setup_rx_resources(&temp_ring[i]);
+			if (err) {
+				while (i) {
+					i--;
+					igc_free_rx_resources(&temp_ring[i]);
+				}
+				goto err_setup;
+			}
+		}
+
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			igc_free_rx_resources(adapter->rx_ring[i]);
+
+			memcpy(adapter->rx_ring[i], &temp_ring[i],
+			       sizeof(struct igc_ring));
+		}
+
+		adapter->rx_ring_count = new_rx_count;
+	}
+err_setup:
+	igc_up(adapter);
+	vfree(temp_ring);
+clear_reset:
+	clear_bit(__IGC_RESETTING, &adapter->state);
+	return err;
+}
+
+static void igc_get_pauseparam(struct net_device *netdev,
+			       struct ethtool_pauseparam *pause)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+
+	pause->autoneg =
+		(adapter->fc_autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE);
+
+	if (hw->fc.current_mode == igc_fc_rx_pause) {
+		pause->rx_pause = 1;
+	} else if (hw->fc.current_mode == igc_fc_tx_pause) {
+		pause->tx_pause = 1;
+	} else if (hw->fc.current_mode == igc_fc_full) {
+		pause->rx_pause = 1;
+		pause->tx_pause = 1;
+	}
+}
+
+static int igc_set_pauseparam(struct net_device *netdev,
+			      struct ethtool_pauseparam *pause)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	int retval = 0;
+
+	adapter->fc_autoneg = pause->autoneg;
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	if (adapter->fc_autoneg == AUTONEG_ENABLE) {
+		hw->fc.requested_mode = igc_fc_default;
+		if (netif_running(adapter->netdev)) {
+			igc_down(adapter);
+			igc_up(adapter);
+		} else {
+			igc_reset(adapter);
+		}
+	} else {
+		if (pause->rx_pause && pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_full;
+		else if (pause->rx_pause && !pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_rx_pause;
+		else if (!pause->rx_pause && pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_tx_pause;
+		else if (!pause->rx_pause && !pause->tx_pause)
+			hw->fc.requested_mode = igc_fc_none;
+
+		hw->fc.current_mode = hw->fc.requested_mode;
+
+		retval = ((hw->phy.media_type == igc_media_type_copper) ?
+			  igc_force_mac_fc(hw) : igc_setup_link(hw));
+	}
+
+	clear_bit(__IGC_RESETTING, &adapter->state);
+	return retval;
+}
+
+static int igc_get_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	if (adapter->rx_itr_setting <= 3)
+		ec->rx_coalesce_usecs = adapter->rx_itr_setting;
+	else
+		ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2;
+
+	if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) {
+		if (adapter->tx_itr_setting <= 3)
+			ec->tx_coalesce_usecs = adapter->tx_itr_setting;
+		else
+			ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2;
+	}
+
+	return 0;
+}
+
+static int igc_set_coalesce(struct net_device *netdev,
+			    struct ethtool_coalesce *ec)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	if (ec->rx_max_coalesced_frames ||
+	    ec->rx_coalesce_usecs_irq ||
+	    ec->rx_max_coalesced_frames_irq ||
+	    ec->tx_max_coalesced_frames ||
+	    ec->tx_coalesce_usecs_irq ||
+	    ec->stats_block_coalesce_usecs ||
+	    ec->use_adaptive_rx_coalesce ||
+	    ec->use_adaptive_tx_coalesce ||
+	    ec->pkt_rate_low ||
+	    ec->rx_coalesce_usecs_low ||
+	    ec->rx_max_coalesced_frames_low ||
+	    ec->tx_coalesce_usecs_low ||
+	    ec->tx_max_coalesced_frames_low ||
+	    ec->pkt_rate_high ||
+	    ec->rx_coalesce_usecs_high ||
+	    ec->rx_max_coalesced_frames_high ||
+	    ec->tx_coalesce_usecs_high ||
+	    ec->tx_max_coalesced_frames_high ||
+	    ec->rate_sample_interval)
+		return -ENOTSUPP;
+
+	if (ec->rx_coalesce_usecs > IGC_MAX_ITR_USECS ||
+	    (ec->rx_coalesce_usecs > 3 &&
+	     ec->rx_coalesce_usecs < IGC_MIN_ITR_USECS) ||
+	    ec->rx_coalesce_usecs == 2)
+		return -EINVAL;
+
+	if (ec->tx_coalesce_usecs > IGC_MAX_ITR_USECS ||
+	    (ec->tx_coalesce_usecs > 3 &&
+	     ec->tx_coalesce_usecs < IGC_MIN_ITR_USECS) ||
+	    ec->tx_coalesce_usecs == 2)
+		return -EINVAL;
+
+	if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs)
+		return -EINVAL;
+
+	/* If ITR is disabled, disable DMAC */
+	if (ec->rx_coalesce_usecs == 0) {
+		if (adapter->flags & IGC_FLAG_DMAC)
+			adapter->flags &= ~IGC_FLAG_DMAC;
+	}
+
+	/* convert to rate of irq's per second */
+	if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3)
+		adapter->rx_itr_setting = ec->rx_coalesce_usecs;
+	else
+		adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2;
+
+	/* convert to rate of irq's per second */
+	if (adapter->flags & IGC_FLAG_QUEUE_PAIRS)
+		adapter->tx_itr_setting = adapter->rx_itr_setting;
+	else if (ec->tx_coalesce_usecs && ec->tx_coalesce_usecs <= 3)
+		adapter->tx_itr_setting = ec->tx_coalesce_usecs;
+	else
+		adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2;
+
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		struct igc_q_vector *q_vector = adapter->q_vector[i];
+
+		q_vector->tx.work_limit = adapter->tx_work_limit;
+		if (q_vector->rx.ring)
+			q_vector->itr_val = adapter->rx_itr_setting;
+		else
+			q_vector->itr_val = adapter->tx_itr_setting;
+		if (q_vector->itr_val && q_vector->itr_val <= 3)
+			q_vector->itr_val = IGC_START_ITR;
+		q_vector->set_itr = 1;
+	}
+
+	return 0;
+}
+
+void igc_write_rss_indir_tbl(struct igc_adapter *adapter)
+{
+	struct igc_hw *hw = &adapter->hw;
+	u32 reg = IGC_RETA(0);
+	u32 shift = 0;
+	int i = 0;
+
+	while (i < IGC_RETA_SIZE) {
+		u32 val = 0;
+		int j;
+
+		for (j = 3; j >= 0; j--) {
+			val <<= 8;
+			val |= adapter->rss_indir_tbl[i + j];
+		}
+
+		wr32(reg, val << shift);
+		reg += 4;
+		i += 4;
+	}
+}
+
+static u32 igc_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return IGC_RETA_SIZE;
+}
+
+static int igc_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
+			u8 *hfunc)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	int i;
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_TOP;
+	if (!indir)
+		return 0;
+	for (i = 0; i < IGC_RETA_SIZE; i++)
+		indir[i] = adapter->rss_indir_tbl[i];
+
+	return 0;
+}
+
+static int igc_set_rxfh(struct net_device *netdev, const u32 *indir,
+			const u8 *key, const u8 hfunc)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	u32 num_queues;
+	int i;
+
+	/* We do not allow change in unsupported parameters */
+	if (key ||
+	    (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP))
+		return -EOPNOTSUPP;
+	if (!indir)
+		return 0;
+
+	num_queues = adapter->rss_queues;
+
+	/* Verify user input. */
+	for (i = 0; i < IGC_RETA_SIZE; i++)
+		if (indir[i] >= num_queues)
+			return -EINVAL;
+
+	for (i = 0; i < IGC_RETA_SIZE; i++)
+		adapter->rss_indir_tbl[i] = indir[i];
+
+	igc_write_rss_indir_tbl(adapter);
+
+	return 0;
+}
+
+static unsigned int igc_max_channels(struct igc_adapter *adapter)
+{
+	return igc_get_max_rss_queues(adapter);
+}
+
+static void igc_get_channels(struct net_device *netdev,
+			     struct ethtool_channels *ch)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	/* Report maximum channels */
+	ch->max_combined = igc_max_channels(adapter);
+
+	/* Report info for other vector */
+	if (adapter->flags & IGC_FLAG_HAS_MSIX) {
+		ch->max_other = NON_Q_VECTORS;
+		ch->other_count = NON_Q_VECTORS;
+	}
+
+	ch->combined_count = adapter->rss_queues;
+}
+
+static int igc_set_channels(struct net_device *netdev,
+			    struct ethtool_channels *ch)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	unsigned int count = ch->combined_count;
+	unsigned int max_combined = 0;
+
+	/* Verify they are not requesting separate vectors */
+	if (!count || ch->rx_count || ch->tx_count)
+		return -EINVAL;
+
+	/* Verify other_count is valid and has not been changed */
+	if (ch->other_count != NON_Q_VECTORS)
+		return -EINVAL;
+
+	/* Verify the number of channels doesn't exceed hw limits */
+	max_combined = igc_max_channels(adapter);
+	if (count > max_combined)
+		return -EINVAL;
+
+	if (count != adapter->rss_queues) {
+		adapter->rss_queues = count;
+		igc_set_flag_queue_pairs(adapter, max_combined);
+
+		/* Hardware has to reinitialize queues and interrupts to
+		 * match the new configuration.
+		 */
+		return igc_reinit_queues(adapter);
+	}
+
+	return 0;
+}
+
+static u32 igc_get_priv_flags(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	u32 priv_flags = 0;
+
+	if (adapter->flags & IGC_FLAG_RX_LEGACY)
+		priv_flags |= IGC_PRIV_FLAGS_LEGACY_RX;
+
+	return priv_flags;
+}
+
+static int igc_set_priv_flags(struct net_device *netdev, u32 priv_flags)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	unsigned int flags = adapter->flags;
+
+	flags &= ~IGC_FLAG_RX_LEGACY;
+	if (priv_flags & IGC_PRIV_FLAGS_LEGACY_RX)
+		flags |= IGC_FLAG_RX_LEGACY;
+
+	if (flags != adapter->flags) {
+		adapter->flags = flags;
+
+		/* reset interface to repopulate queues */
+		if (netif_running(netdev))
+			igc_reinit_locked(adapter);
+	}
+
+	return 0;
+}
+
+static int igc_ethtool_begin(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	pm_runtime_get_sync(&adapter->pdev->dev);
+	return 0;
+}
+
+static void igc_ethtool_complete(struct net_device *netdev)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+
+	pm_runtime_put(&adapter->pdev->dev);
+}
+
+static int igc_get_link_ksettings(struct net_device *netdev,
+				  struct ethtool_link_ksettings *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 status;
+	u32 speed;
+
+	ethtool_link_ksettings_zero_link_mode(cmd, supported);
+	ethtool_link_ksettings_zero_link_mode(cmd, advertising);
+
+	/* supported link modes */
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, 2500baseT_Full);
+
+	/* twisted pair */
+	cmd->base.port = PORT_TP;
+	cmd->base.phy_address = hw->phy.addr;
+
+	/* advertising link modes */
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full);
+	ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full);
+
+	/* set autoneg settings */
+	if (hw->mac.autoneg == 1) {
+		ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Autoneg);
+	}
+
+	switch (hw->fc.requested_mode) {
+	case igc_fc_full:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+		break;
+	case igc_fc_rx_pause:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+		break;
+	case igc_fc_tx_pause:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+		break;
+	default:
+		ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause);
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+	}
+
+	status = rd32(IGC_STATUS);
+
+	if (status & IGC_STATUS_LU) {
+		if (status & IGC_STATUS_SPEED_1000) {
+			/* For I225, STATUS will indicate 1G speed in both
+			 * 1 Gbps and 2.5 Gbps link modes.
+			 * An additional bit is used
+			 * to differentiate between 1 Gbps and 2.5 Gbps.
+			 */
+			if (hw->mac.type == igc_i225 &&
+			    (status & IGC_STATUS_SPEED_2500)) {
+				speed = SPEED_2500;
+				hw_dbg("2500 Mbs, ");
+			} else {
+				speed = SPEED_1000;
+				hw_dbg("1000 Mbs, ");
+			}
+		} else if (status & IGC_STATUS_SPEED_100) {
+			speed = SPEED_100;
+			hw_dbg("100 Mbs, ");
+		} else {
+			speed = SPEED_10;
+			hw_dbg("10 Mbs, ");
+		}
+		if ((status & IGC_STATUS_FD) ||
+		    hw->phy.media_type != igc_media_type_copper)
+			cmd->base.duplex = DUPLEX_FULL;
+		else
+			cmd->base.duplex = DUPLEX_HALF;
+	} else {
+		speed = SPEED_UNKNOWN;
+		cmd->base.duplex = DUPLEX_UNKNOWN;
+	}
+	cmd->base.speed = speed;
+	if (hw->mac.autoneg)
+		cmd->base.autoneg = AUTONEG_ENABLE;
+	else
+		cmd->base.autoneg = AUTONEG_DISABLE;
+
+	/* MDI-X => 2; MDI =>1; Invalid =>0 */
+	if (hw->phy.media_type == igc_media_type_copper)
+		cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+						      ETH_TP_MDI;
+	else
+		cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID;
+
+	if (hw->phy.mdix == AUTO_ALL_MODES)
+		cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO;
+	else
+		cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix;
+
+	return 0;
+}
+
+static int igc_set_link_ksettings(struct net_device *netdev,
+				  const struct ethtool_link_ksettings *cmd)
+{
+	struct igc_adapter *adapter = netdev_priv(netdev);
+	struct igc_hw *hw = &adapter->hw;
+	u32 advertising;
+
+	/* When adapter in resetting mode, autoneg/speed/duplex
+	 * cannot be changed
+	 */
+	if (igc_check_reset_block(hw)) {
+		dev_err(&adapter->pdev->dev,
+			"Cannot change link characteristics when reset is active.\n");
+		return -EINVAL;
+	}
+
+	/* MDI setting is only allowed when autoneg enabled because
+	 * some hardware doesn't allow MDI setting when speed or
+	 * duplex is forced.
+	 */
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO &&
+		    cmd->base.autoneg != AUTONEG_ENABLE) {
+			dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+			return -EINVAL;
+		}
+	}
+
+	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	ethtool_convert_link_mode_to_legacy_u32(&advertising,
+						cmd->link_modes.advertising);
+
+	if (cmd->base.autoneg == AUTONEG_ENABLE) {
+		hw->mac.autoneg = 1;
+		hw->phy.autoneg_advertised = advertising;
+		if (adapter->fc_autoneg)
+			hw->fc.requested_mode = igc_fc_default;
+	} else {
+		/* calling this overrides forced MDI setting */
+		dev_info(&adapter->pdev->dev,
+			 "Force mode currently not supported\n");
+	}
+
+	/* MDI-X => 2; MDI => 1; Auto => 3 */
+	if (cmd->base.eth_tp_mdix_ctrl) {
+		/* fix up the value for auto (3 => 0) as zero is mapped
+		 * internally to auto
+		 */
+		if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+			hw->phy.mdix = AUTO_ALL_MODES;
+		else
+			hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl;
+	}
+
+	/* reset the link */
+	if (netif_running(adapter->netdev)) {
+		igc_down(adapter);
+		igc_up(adapter);
+	} else {
+		igc_reset(adapter);
+	}
+
+	clear_bit(__IGC_RESETTING, &adapter->state);
+
+	return 0;
+}
+
+static const struct ethtool_ops igc_ethtool_ops = {
+	.get_drvinfo		= igc_get_drvinfo,
+	.get_regs_len		= igc_get_regs_len,
+	.get_regs		= igc_get_regs,
+	.get_msglevel		= igc_get_msglevel,
+	.set_msglevel		= igc_set_msglevel,
+	.nway_reset		= igc_nway_reset,
+	.get_link		= igc_get_link,
+	.get_eeprom_len		= igc_get_eeprom_len,
+	.get_eeprom		= igc_get_eeprom,
+	.set_eeprom		= igc_set_eeprom,
+	.get_ringparam		= igc_get_ringparam,
+	.set_ringparam		= igc_set_ringparam,
+	.get_pauseparam		= igc_get_pauseparam,
+	.set_pauseparam		= igc_set_pauseparam,
+	.get_coalesce		= igc_get_coalesce,
+	.set_coalesce		= igc_set_coalesce,
+	.get_rxfh_indir_size	= igc_get_rxfh_indir_size,
+	.get_rxfh		= igc_get_rxfh,
+	.set_rxfh		= igc_set_rxfh,
+	.get_channels		= igc_get_channels,
+	.set_channels		= igc_set_channels,
+	.get_priv_flags		= igc_get_priv_flags,
+	.set_priv_flags		= igc_set_priv_flags,
+	.begin			= igc_ethtool_begin,
+	.complete		= igc_ethtool_complete,
+	.get_link_ksettings	= igc_get_link_ksettings,
+	.set_link_ksettings	= igc_set_link_ksettings,
+};
+
+void igc_set_ethtool_ops(struct net_device *netdev)
+{
+	netdev->ethtool_ops = &igc_ethtool_ops;
+}
diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h
index c50414f48f0d..7c88b7bd4799 100644
--- a/drivers/net/ethernet/intel/igc/igc_hw.h
+++ b/drivers/net/ethernet/intel/igc/igc_hw.h
@@ -55,6 +55,7 @@ enum igc_media_type {
 
 enum igc_nvm_type {
 	igc_nvm_unknown = 0,
+	igc_nvm_eeprom_spi,
 	igc_nvm_flash_hw,
 	igc_nvm_invm,
 };
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 9d85707e8a81..87a11879bf2d 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -12,6 +12,8 @@
 #define DRV_VERSION	"0.0.1-k"
 #define DRV_SUMMARY	"Intel(R) 2.5G Ethernet Linux Driver"
 
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+
 static int debug = -1;
 
 MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
@@ -66,7 +68,7 @@ enum latency_range {
 	latency_invalid = 255
 };
 
-static void igc_reset(struct igc_adapter *adapter)
+void igc_reset(struct igc_adapter *adapter)
 {
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
@@ -150,7 +152,7 @@ static void igc_get_hw_control(struct igc_adapter *adapter)
  *
  * Free all transmit software resources
  */
-static void igc_free_tx_resources(struct igc_ring *tx_ring)
+void igc_free_tx_resources(struct igc_ring *tx_ring)
 {
 	igc_clean_tx_ring(tx_ring);
 
@@ -261,7 +263,7 @@ static void igc_clean_all_tx_rings(struct igc_adapter *adapter)
  *
  * Return 0 on success, negative on failure
  */
-static int igc_setup_tx_resources(struct igc_ring *tx_ring)
+int igc_setup_tx_resources(struct igc_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
 	int size = 0;
@@ -381,7 +383,7 @@ static void igc_clean_all_rx_rings(struct igc_adapter *adapter)
  *
  * Free all receive software resources
  */
-static void igc_free_rx_resources(struct igc_ring *rx_ring)
+void igc_free_rx_resources(struct igc_ring *rx_ring)
 {
 	igc_clean_rx_ring(rx_ring);
 
@@ -418,7 +420,7 @@ static void igc_free_all_rx_resources(struct igc_adapter *adapter)
  *
  * Returns 0 on success, negative on failure
  */
-static int igc_setup_rx_resources(struct igc_ring *rx_ring)
+int igc_setup_rx_resources(struct igc_ring *rx_ring)
 {
 	struct device *dev = rx_ring->dev;
 	int size, desc_len;
@@ -865,6 +867,8 @@ static int igc_tx_map(struct igc_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
 	 * memory model archs, such as IA-64).
@@ -959,8 +963,6 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
-	skb_tx_timestamp(skb);
-
 	/* record initial flags and protocol */
 	first->tx_flags = tx_flags;
 	first->protocol = protocol;
@@ -1108,7 +1110,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring,
 
 	/* update pointers within the skb to store the data */
 	skb_reserve(skb, IGC_SKB_PAD);
-	 __skb_put(skb, size);
+	__skb_put(skb, size);
 
 	/* update buffer offset */
 #if (PAGE_SIZE < 8192)
@@ -1160,9 +1162,9 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring,
 				(va + headlen) - page_address(rx_buffer->page),
 				size, truesize);
 #if (PAGE_SIZE < 8192)
-	rx_buffer->page_offset ^= truesize;
+		rx_buffer->page_offset ^= truesize;
 #else
-	rx_buffer->page_offset += truesize;
+		rx_buffer->page_offset += truesize;
 #endif
 	} else {
 		rx_buffer->pagecnt_bias++;
@@ -1668,8 +1670,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 				tx_buffer->next_to_watch,
 				jiffies,
 				tx_buffer->next_to_watch->wb.status);
-				netif_stop_subqueue(tx_ring->netdev,
-						    tx_ring->queue_index);
+			netif_stop_subqueue(tx_ring->netdev,
+					    tx_ring->queue_index);
 
 			/* we are about to reset, no point in enabling stuff */
 			return true;
@@ -1700,24 +1702,10 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 }
 
 /**
- * igc_ioctl - I/O control method
- * @netdev: network interface device structure
- * @ifreq: frequency
- * @cmd: command
- */
-static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
-{
-	switch (cmd) {
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-/**
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
  */
-static void igc_up(struct igc_adapter *adapter)
+void igc_up(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	int i = 0;
@@ -1762,7 +1750,7 @@ static void igc_nfc_filter_exit(struct igc_adapter *adapter)
  * igc_down - Close the interface
  * @adapter: board private structure
  */
-static void igc_down(struct igc_adapter *adapter)
+void igc_down(struct igc_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	struct igc_hw *hw = &adapter->hw;
@@ -1824,7 +1812,7 @@ static void igc_down(struct igc_adapter *adapter)
 	igc_clean_all_rx_rings(adapter);
 }
 
-static void igc_reinit_locked(struct igc_adapter *adapter)
+void igc_reinit_locked(struct igc_adapter *adapter)
 {
 	WARN_ON(in_interrupt());
 	while (test_and_set_bit(__IGC_RESETTING, &adapter->state))
@@ -1936,7 +1924,7 @@ static void igc_configure(struct igc_adapter *adapter)
 
 /**
  * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table
- * @adapter: Pointer to adapter structure
+ * @adapter: address of board private structure
  * @index: Index of the RAR entry which need to be synced with MAC table
  */
 static void igc_rar_set_index(struct igc_adapter *adapter, u32 index)
@@ -2312,7 +2300,7 @@ static void igc_update_phy_info(struct timer_list *t)
  * igc_has_link - check shared code for link and determine up/down
  * @adapter: pointer to driver private info
  */
-static bool igc_has_link(struct igc_adapter *adapter)
+bool igc_has_link(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
 	bool link_active = false;
@@ -2866,11 +2854,13 @@ static int igc_poll(struct napi_struct *napi, int budget)
 	if (!clean_complete)
 		return budget;
 
-	/* If not enough Rx work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-	igc_ring_irq_enable(q_vector);
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done)))
+		igc_ring_irq_enable(q_vector);
 
-	return 0;
+	return min(work_done, budget - 1);
 }
 
 /**
@@ -2968,22 +2958,21 @@ static int igc_alloc_q_vector(struct igc_adapter *adapter,
 {
 	struct igc_q_vector *q_vector;
 	struct igc_ring *ring;
-	int ring_count, size;
+	int ring_count;
 
 	/* igc only supports 1 Tx and/or 1 Rx queue per vector */
 	if (txr_count > 1 || rxr_count > 1)
 		return -ENOMEM;
 
 	ring_count = txr_count + rxr_count;
-	size = sizeof(struct igc_q_vector) +
-		(sizeof(struct igc_ring) * ring_count);
 
 	/* allocate q_vector and rings */
 	q_vector = adapter->q_vector[v_idx];
 	if (!q_vector)
-		q_vector = kzalloc(size, GFP_KERNEL);
+		q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+				   GFP_KERNEL);
 	else
-		memset(q_vector, 0, size);
+		memset(q_vector, 0, struct_size(q_vector, ring, ring_count));
 	if (!q_vector)
 		return -ENOMEM;
 
@@ -3358,7 +3347,7 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 		goto err_req_irq;
 
 	/* Notify the stack of the actual queue counts. */
-	netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
+	err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues);
 	if (err)
 		goto err_set_queues;
 
@@ -3445,7 +3434,6 @@ static const struct net_device_ops igc_netdev_ops = {
 	.ndo_set_mac_address	= igc_set_mac,
 	.ndo_change_mtu		= igc_change_mtu,
 	.ndo_get_stats		= igc_get_stats,
-	.ndo_do_ioctl		= igc_ioctl,
 };
 
 /* PCIe configuration access */
@@ -3514,6 +3502,57 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg)
 	return value;
 }
 
+int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct igc_mac_info *mac = &adapter->hw.mac;
+
+	mac->autoneg = 0;
+
+	/* Make sure dplx is at most 1 bit and lsb of speed is not set
+	 * for the switch() below to work
+	 */
+	if ((spd & 1) || (dplx & ~1))
+		goto err_inval;
+
+	switch (spd + dplx) {
+	case SPEED_10 + DUPLEX_HALF:
+		mac->forced_speed_duplex = ADVERTISE_10_HALF;
+		break;
+	case SPEED_10 + DUPLEX_FULL:
+		mac->forced_speed_duplex = ADVERTISE_10_FULL;
+		break;
+	case SPEED_100 + DUPLEX_HALF:
+		mac->forced_speed_duplex = ADVERTISE_100_HALF;
+		break;
+	case SPEED_100 + DUPLEX_FULL:
+		mac->forced_speed_duplex = ADVERTISE_100_FULL;
+		break;
+	case SPEED_1000 + DUPLEX_FULL:
+		mac->autoneg = 1;
+		adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL;
+		break;
+	case SPEED_1000 + DUPLEX_HALF: /* not supported */
+		goto err_inval;
+	case SPEED_2500 + DUPLEX_FULL:
+		mac->autoneg = 1;
+		adapter->hw.phy.autoneg_advertised = ADVERTISE_2500_FULL;
+		break;
+	case SPEED_2500 + DUPLEX_HALF: /* not supported */
+	default:
+		goto err_inval;
+	}
+
+	/* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+	adapter->hw.phy.mdix = AUTO_ALL_MODES;
+
+	return 0;
+
+err_inval:
+	dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n");
+	return -EINVAL;
+}
+
 /**
  * igc_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -3532,26 +3571,23 @@ static int igc_probe(struct pci_dev *pdev,
 	struct net_device *netdev;
 	struct igc_hw *hw;
 	const struct igc_info *ei = igc_info_tbl[ent->driver_data];
-	int err, pci_using_dac;
+	int err;
 
 	err = pci_enable_device_mem(pdev);
 	if (err)
 		return err;
 
-	pci_using_dac = 0;
 	err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64));
 	if (!err) {
 		err = dma_set_coherent_mask(&pdev->dev,
 					    DMA_BIT_MASK(64));
-		if (!err)
-			pci_using_dac = 1;
 	} else {
 		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32));
 		if (err) {
 			err = dma_set_coherent_mask(&pdev->dev,
 						    DMA_BIT_MASK(32));
 			if (err) {
-				IGC_ERR("Wrong DMA configuration, aborting\n");
+				dev_err(&pdev->dev, "igc: Wrong DMA config\n");
 				goto err_dma;
 			}
 		}
@@ -3584,7 +3620,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw = &adapter->hw;
 	hw->back = adapter;
 	adapter->port_num = hw->bus.func;
-	adapter->msg_enable = GENMASK(debug - 1, 0);
+	adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	err = pci_save_state(pdev);
 	if (err)
@@ -3600,7 +3636,7 @@ static int igc_probe(struct pci_dev *pdev,
 	hw->hw_addr = adapter->io_addr;
 
 	netdev->netdev_ops = &igc_netdev_ops;
-
+	igc_set_ethtool_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;
 
 	netdev->mem_start = pci_resource_start(pdev, 0);
@@ -3760,8 +3796,8 @@ static struct pci_driver igc_driver = {
 	.remove   = igc_remove,
 };
 
-static void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
-				     const u32 max_rss_queues)
+void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
+			      const u32 max_rss_queues)
 {
 	/* Determine if we need to pair queues. */
 	/* If rss_queues > half of max_rss_queues, pair the queues in
@@ -3773,7 +3809,7 @@ static void igc_set_flag_queue_pairs(struct igc_adapter *adapter,
 		adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS;
 }
 
-static unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
+unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter)
 {
 	unsigned int max_rss_queues;
 
@@ -3853,6 +3889,32 @@ static int igc_sw_init(struct igc_adapter *adapter)
 }
 
 /**
+ * igc_reinit_queues - return error
+ * @adapter: pointer to adapter structure
+ */
+int igc_reinit_queues(struct igc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+	int err = 0;
+
+	if (netif_running(netdev))
+		igc_close(netdev);
+
+	igc_reset_interrupt_capability(adapter);
+
+	if (igc_init_interrupt_scheme(adapter, true)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		return -ENOMEM;
+	}
+
+	if (netif_running(netdev))
+		err = igc_open(netdev);
+
+	return err;
+}
+
+/**
  * igc_get_hw_dev - return device
  * @hw: pointer to hardware structure
  *
diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c
index 38e43e6fc1c7..4c8f96a9a148 100644
--- a/drivers/net/ethernet/intel/igc/igc_phy.c
+++ b/drivers/net/ethernet/intel/igc/igc_phy.c
@@ -152,7 +152,6 @@ void igc_power_down_phy_copper(struct igc_hw *hw)
 s32 igc_check_downshift(struct igc_hw *hw)
 {
 	struct igc_phy_info *phy = &hw->phy;
-	u16 phy_data, offset, mask;
 	s32 ret_val;
 
 	switch (phy->type) {
@@ -161,15 +160,8 @@ s32 igc_check_downshift(struct igc_hw *hw)
 		/* speed downshift not supported */
 		phy->speed_downgraded = false;
 		ret_val = 0;
-		goto out;
 	}
 
-	ret_val = phy->ops.read_reg(hw, offset, &phy_data);
-
-	if (!ret_val)
-		phy->speed_downgraded = (phy_data & mask) ? true : false;
-
-out:
 	return ret_val;
 }
 
diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h
index a1bd3216c906..5afe7a8d3faf 100644
--- a/drivers/net/ethernet/intel/igc/igc_regs.h
+++ b/drivers/net/ethernet/intel/igc/igc_regs.h
@@ -80,6 +80,9 @@
 /* MSI-X Table Register Descriptions */
 #define IGC_PBACL		0x05B68  /* MSIx PBA Clear - R/W 1 to clear */
 
+/* Redirection Table - RW Array */
+#define IGC_RETA(_i)		(0x05C00 + ((_i) * 4))
+
 /* Receive Register Descriptions */
 #define IGC_RCTL		0x00100  /* Rx Control - RW */
 #define IGC_SRRCTL(_n)		(0x0C00C + ((_n) * 0x40))
@@ -188,7 +191,6 @@
 #define IGC_HGOTCL	0x04130  /* Host Good Octets Transmit Count Low */
 #define IGC_HGOTCH	0x04134  /* Host Good Octets Transmit Count High */
 #define IGC_LENERRS	0x04138  /* Length Errors Count */
-#define IGC_SCVPC	0x04228  /* SerDes/SGMII Code Violation Pkt Count */
 #define IGC_HRMPC	0x0A018  /* Header Redirection Missed Packet Count */
 
 /* Management registers */
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index 1d4d1686909a..e5ac2d3fd816 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -680,8 +680,8 @@ ixgb_setup_tx_resources(struct ixgb_adapter *adapter)
 	txdr->size = txdr->count * sizeof(struct ixgb_tx_desc);
 	txdr->size = ALIGN(txdr->size, 4096);
 
-	txdr->desc = dma_zalloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
-					 GFP_KERNEL);
+	txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size, &txdr->dma,
+					GFP_KERNEL);
 	if (!txdr->desc) {
 		vfree(txdr->buffer_info);
 		return -ENOMEM;
@@ -763,8 +763,8 @@ ixgb_setup_rx_resources(struct ixgb_adapter *adapter)
 	rxdr->size = rxdr->count * sizeof(struct ixgb_rx_desc);
 	rxdr->size = ALIGN(rxdr->size, 4096);
 
-	rxdr->desc = dma_zalloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
-					 GFP_KERNEL);
+	rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma,
+					GFP_KERNEL);
 
 	if (!rxdr->desc) {
 		vfree(rxdr->buffer_info);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 143bdd5ee2a0..08d85e336bd4 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -12,6 +12,7 @@
 #include <linux/aer.h>
 #include <linux/if_vlan.h>
 #include <linux/jiffies.h>
+#include <linux/phy.h>
 
 #include <linux/timecounter.h>
 #include <linux/net_tstamp.h>
@@ -561,6 +562,7 @@ struct ixgbe_adapter {
 	struct net_device *netdev;
 	struct bpf_prog *xdp_prog;
 	struct pci_dev *pdev;
+	struct mii_bus *mii_bus;
 
 	unsigned long state;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
index 1e49716f52bc..109f8de5a1c2 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c
@@ -1048,7 +1048,7 @@ mac_reset_top:
 	 * clear the multicast table.  Also reset num_rar_entries to 128,
 	 * since we modify this value when programming the SAN MAC address.
 	 */
-	hw->mac.num_rar_entries = 128;
+	hw->mac.num_rar_entries = IXGBE_82599_RAR_ENTRIES;
 	hw->mac.ops.init_rx_addrs(hw);
 
 	/* Store the permanent SAN mac address */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 732b1e6ecc43..acba067cc15a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -2206,7 +2206,8 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE))
+	if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE |
+			    WAKE_FILTER))
 		return -EOPNOTSUPP;
 
 	if (ixgbe_wol_exclusion(adapter, wol))
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
index fd1b0546fd67..ff85ce5791a3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c
@@ -4,6 +4,7 @@
 #include "ixgbe.h"
 #include <net/xfrm.h>
 #include <crypto/aead.h>
+#include <linux/if_bridge.h>
 
 #define IXGBE_IPSEC_KEY_BITS  160
 static const char aes_gcm_name[] = "rfc4106(gcm(aes))";
@@ -693,7 +694,8 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs)
 	} else {
 		struct tx_sa tsa;
 
-		if (adapter->num_vfs)
+		if (adapter->num_vfs &&
+		    adapter->bridge_mode != BRIDGE_MODE_VEPA)
 			return -EOPNOTSUPP;
 
 		/* find the first unused index */
@@ -1063,11 +1065,13 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring,
 	struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev);
 	struct ixgbe_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
+	struct sec_path *sp;
 	struct tx_sa *tsa;
 
-	if (unlikely(!first->skb->sp->len)) {
+	sp = skb_sec_path(first->skb);
+	if (unlikely(!sp->len)) {
 		netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n",
-			   __func__, first->skb->sp->len);
+			   __func__, sp->len);
 		return 0;
 	}
 
@@ -1157,6 +1161,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 	struct xfrm_state *xs = NULL;
 	struct ipv6hdr *ip6 = NULL;
 	struct iphdr *ip4 = NULL;
+	struct sec_path *sp;
 	void *daddr;
 	__be32 spi;
 	u8 *c_hdr;
@@ -1196,12 +1201,12 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring,
 	if (unlikely(!xs))
 		return;
 
-	skb->sp = secpath_dup(skb->sp);
-	if (unlikely(!skb->sp))
+	sp = secpath_set(skb);
+	if (unlikely(!sp))
 		return;
 
-	skb->sp->xvec[skb->sp->len++] = xs;
-	skb->sp->olen++;
+	sp->xvec[sp->len++] = xs;
+	sp->olen++;
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
 	xo->status = CRYPTO_SUCCESS;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
index 62e6499e4146..cc3196ae5aea 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c
@@ -836,12 +836,10 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	struct ixgbe_ring *ring;
 	int node = NUMA_NO_NODE;
 	int cpu = -1;
-	int ring_count, size;
+	int ring_count;
 	u8 tcs = adapter->hw_tcs;
 
 	ring_count = txr_count + rxr_count + xdp_count;
-	size = sizeof(struct ixgbe_q_vector) +
-	       (sizeof(struct ixgbe_ring) * ring_count);
 
 	/* customize cpu for Flow Director mapping */
 	if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) {
@@ -855,9 +853,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter,
 	}
 
 	/* allocate q_vector and rings */
-	q_vector = kzalloc_node(size, GFP_KERNEL, node);
+	q_vector = kzalloc_node(struct_size(q_vector, ring, ring_count),
+				GFP_KERNEL, node);
 	if (!q_vector)
-		q_vector = kzalloc(size, GFP_KERNEL);
+		q_vector = kzalloc(struct_size(q_vector, ring, ring_count),
+				   GFP_KERNEL);
 	if (!q_vector)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 113b38e0defb..e100054a3765 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -27,6 +27,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/atomic.h>
+#include <linux/numa.h>
 #include <scsi/fc/fc_fcoe.h>
 #include <net/udp_tunnel.h>
 #include <net/pkt_cls.h>
@@ -39,6 +40,7 @@
 #include "ixgbe.h"
 #include "ixgbe_common.h"
 #include "ixgbe_dcb_82599.h"
+#include "ixgbe_phy.h"
 #include "ixgbe_sriov.h"
 #include "ixgbe_model.h"
 #include "ixgbe_txrx_common.h"
@@ -3952,8 +3954,11 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter)
 			else
 				mrqc = IXGBE_MRQC_VMDQRSS64EN;
 
-			/* Enable L3/L4 for Tx Switched packets */
-			mrqc |= IXGBE_MRQC_L3L4TXSWEN;
+			/* Enable L3/L4 for Tx Switched packets only for X550,
+			 * older devices do not support this feature
+			 */
+			if (hw->mac.type >= ixgbe_mac_X550)
+				mrqc |= IXGBE_MRQC_L3L4TXSWEN;
 		} else {
 			if (tcs > 4)
 				mrqc = IXGBE_MRQC_RTRSS8TCEN;
@@ -6077,9 +6082,9 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	/* Disable Rx */
 	ixgbe_disable_rx(adapter);
 
-	/* synchronize_sched() needed for pending XDP buffers to drain */
+	/* synchronize_rcu() needed for pending XDP buffers to drain */
 	if (adapter->xdp_ring[0])
-		synchronize_sched();
+		synchronize_rcu();
 
 	ixgbe_irq_disable(adapter);
 
@@ -6414,7 +6419,7 @@ int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring)
 {
 	struct device *dev = tx_ring->dev;
 	int orig_node = dev_to_node(dev);
-	int ring_node = -1;
+	int ring_node = NUMA_NO_NODE;
 	int size;
 
 	size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count;
@@ -6508,7 +6513,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter,
 {
 	struct device *dev = rx_ring->dev;
 	int orig_node = dev_to_node(dev);
-	int ring_node = -1;
+	int ring_node = NUMA_NO_NODE;
 	int size;
 
 	size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count;
@@ -8269,6 +8274,8 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/*
 	 * Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
@@ -8646,8 +8653,6 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 		}
 	}
 
-	skb_tx_timestamp(skb);
-
 #ifdef CONFIG_PCI_IOV
 	/*
 	 * Use the l2switch_enable flag - would be false if the DMA
@@ -8695,7 +8700,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb,
 #endif /* IXGBE_FCOE */
 
 #ifdef CONFIG_IXGBE_IPSEC
-	if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
+	if (secpath_exists(skb) &&
+	    !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
 	tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx);
@@ -8789,6 +8795,15 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr)
 	u16 value;
 	int rc;
 
+	if (adapter->mii_bus) {
+		int regnum = addr;
+
+		if (devad != MDIO_DEVAD_NONE)
+			regnum |= (devad << 16) | MII_ADDR_C45;
+
+		return mdiobus_read(adapter->mii_bus, prtad, regnum);
+	}
+
 	if (prtad != hw->phy.mdio.prtad)
 		return -EINVAL;
 	rc = hw->phy.ops.read_reg(hw, addr, devad, &value);
@@ -8803,6 +8818,15 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
+	if (adapter->mii_bus) {
+		int regnum = addr;
+
+		if (devad != MDIO_DEVAD_NONE)
+			regnum |= (devad << 16) | MII_ADDR_C45;
+
+		return mdiobus_write(adapter->mii_bus, prtad, regnum, value);
+	}
+
 	if (prtad != hw->phy.mdio.prtad)
 		return -EINVAL;
 	return hw->phy.ops.write_reg(hw, addr, devad, value);
@@ -9890,7 +9914,8 @@ static void ixgbe_del_udp_tunnel_port(struct net_device *dev,
 static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			     struct net_device *dev,
 			     const unsigned char *addr, u16 vid,
-			     u16 flags)
+			     u16 flags,
+			     struct netlink_ext_ack *extack)
 {
 	/* guarantee we can provide a unique filter for the unicast address */
 	if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) {
@@ -9979,7 +10004,8 @@ static int ixgbe_configure_bridge_mode(struct ixgbe_adapter *adapter,
 }
 
 static int ixgbe_ndo_bridge_setlink(struct net_device *dev,
-				    struct nlmsghdr *nlh, u16 flags)
+				    struct nlmsghdr *nlh, u16 flags,
+				    struct netlink_ext_ack *extack)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct nlattr *attr, *br_spec;
@@ -10191,7 +10217,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev,
 	 */
 	if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) {
 #ifdef CONFIG_IXGBE_IPSEC
-		if (!skb->sp)
+		if (!secpath_exists(skb))
 #endif
 			features &= ~NETIF_F_TSO;
 	}
@@ -10204,6 +10230,7 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
 	struct ixgbe_adapter *adapter = netdev_priv(dev);
 	struct bpf_prog *old_prog;
+	bool need_reset;
 
 	if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)
 		return -EINVAL;
@@ -10226,9 +10253,10 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 		return -ENOMEM;
 
 	old_prog = xchg(&adapter->xdp_prog, prog);
+	need_reset = (!!prog != !!old_prog);
 
 	/* If transitioning XDP modes reconfigure rings */
-	if (!!prog != !!old_prog) {
+	if (need_reset) {
 		int err = ixgbe_setup_tc(dev, adapter->hw_tcs);
 
 		if (err) {
@@ -10244,6 +10272,14 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
+	/* Kick start the NAPI context if there is an AF_XDP socket open
+	 * on that queue id. This so that receiving will start.
+	 */
+	if (need_reset && prog)
+		for (i = 0; i < adapter->num_rx_queues; i++)
+			if (adapter->xdp_ring[i]->xsk_umem)
+				(void)ixgbe_xsk_async_xmit(adapter->netdev, i);
+
 	return 0;
 }
 
@@ -10258,9 +10294,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
-	case XDP_QUERY_XSK_UMEM:
-		return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem,
-					    xdp->xsk.queue_id);
 	case XDP_SETUP_XSK_UMEM:
 		return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem,
 					    xdp->xsk.queue_id);
@@ -10476,7 +10509,7 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring)
 	ixgbe_disable_rxr_hw(adapter, rx_ring);
 
 	if (xdp_ring)
-		synchronize_sched();
+		synchronize_rcu();
 
 	/* Rx/Tx/XDP Tx share the same napi context. */
 	napi_disable(&rx_ring->q_vector->napi);
@@ -10517,7 +10550,8 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring)
 	ixgbe_configure_rx_ring(adapter, rx_ring);
 
 	clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state);
-	clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
+	if (xdp_ring)
+		clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state);
 }
 
 /**
@@ -11119,6 +11153,8 @@ skip_sriov:
 			IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL,
 			true);
 
+	ixgbe_mii_bus_init(hw);
+
 	return 0;
 
 err_register:
@@ -11169,6 +11205,8 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	set_bit(__IXGBE_REMOVING, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
+	if (adapter->mii_bus)
+		mdiobus_unregister(adapter->mii_bus);
 
 #ifdef CONFIG_IXGBE_DCA
 	if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
index 919a7af84b42..2fb97967961c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c
@@ -3,6 +3,7 @@
 
 #include <linux/pci.h>
 #include <linux/delay.h>
+#include <linux/iopoll.h>
 #include <linux/sched.h>
 
 #include "ixgbe.h"
@@ -658,6 +659,306 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
 	return status;
 }
 
+#define IXGBE_HW_READ_REG(addr) IXGBE_READ_REG(hw, addr)
+
+/**
+ *  ixgbe_msca_cmd - Write the command register and poll for completion/timeout
+ *  @hw: pointer to hardware structure
+ *  @cmd: command register value to write
+ **/
+static s32 ixgbe_msca_cmd(struct ixgbe_hw *hw, u32 cmd)
+{
+	IXGBE_WRITE_REG(hw, IXGBE_MSCA, cmd);
+
+	return readx_poll_timeout(IXGBE_HW_READ_REG, IXGBE_MSCA, cmd,
+				  !(cmd & IXGBE_MSCA_MDI_COMMAND), 10,
+				  10 * IXGBE_MDIO_COMMAND_TIMEOUT);
+}
+
+/**
+ *  ixgbe_mii_bus_read_generic - Read a clause 22/45 register with gssr flags
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @gssr: semaphore flags to acquire
+ **/
+static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr,
+				      int regnum, u32 gssr)
+{
+	u32 hwaddr, cmd;
+	s32 data;
+
+	if (hw->mac.ops.acquire_swfw_sync(hw, gssr))
+		return -EBUSY;
+
+	hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT;
+	if (regnum & MII_ADDR_C45) {
+		hwaddr |= regnum & GENMASK(21, 0);
+		cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND;
+	} else {
+		hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT;
+		cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL |
+			IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND;
+	}
+
+	data = ixgbe_msca_cmd(hw, cmd);
+	if (data < 0)
+		goto mii_bus_read_done;
+
+	/* For a clause 45 access the address cycle just completed, we still
+	 * need to do the read command, otherwise just get the data
+	 */
+	if (!(regnum & MII_ADDR_C45))
+		goto do_mii_bus_read;
+
+	cmd = hwaddr | IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND;
+	data = ixgbe_msca_cmd(hw, cmd);
+	if (data < 0)
+		goto mii_bus_read_done;
+
+do_mii_bus_read:
+	data = IXGBE_READ_REG(hw, IXGBE_MSRWD);
+	data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0);
+
+mii_bus_read_done:
+	hw->mac.ops.release_swfw_sync(hw, gssr);
+	return data;
+}
+
+/**
+ *  ixgbe_mii_bus_write_generic - Write a clause 22/45 register with gssr flags
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @val: value to write
+ *  @gssr: semaphore flags to acquire
+ **/
+static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr,
+				       int regnum, u16 val, u32 gssr)
+{
+	u32 hwaddr, cmd;
+	s32 err;
+
+	if (hw->mac.ops.acquire_swfw_sync(hw, gssr))
+		return -EBUSY;
+
+	IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val);
+
+	hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT;
+	if (regnum & MII_ADDR_C45) {
+		hwaddr |= regnum & GENMASK(21, 0);
+		cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND;
+	} else {
+		hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT;
+		cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE |
+			IXGBE_MSCA_MDI_COMMAND;
+	}
+
+	/* For clause 45 this is an address cycle, for clause 22 this is the
+	 * entire transaction
+	 */
+	err = ixgbe_msca_cmd(hw, cmd);
+	if (err < 0 || !(regnum & MII_ADDR_C45))
+		goto mii_bus_write_done;
+
+	cmd = hwaddr | IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND;
+	err = ixgbe_msca_cmd(hw, cmd);
+
+mii_bus_write_done:
+	hw->mac.ops.release_swfw_sync(hw, gssr);
+	return err;
+}
+
+/**
+ *  ixgbe_mii_bus_read - Read a clause 22/45 register
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ **/
+static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr);
+}
+
+/**
+ *  ixgbe_mii_bus_write - Write a clause 22/45 register
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @val: value to write
+ **/
+static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum,
+			       u16 val)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr);
+}
+
+/**
+ *  ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ **/
+static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr,
+				       int regnum)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM;
+	return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr);
+}
+
+/**
+ *  ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a
+ *  @hw: pointer to hardware structure
+ *  @addr: address
+ *  @regnum: register number
+ *  @val: value to write
+ **/
+static s32 ixgbe_x550em_a_mii_bus_write(struct mii_bus *bus, int addr,
+					int regnum, u16 val)
+{
+	struct ixgbe_adapter *adapter = bus->priv;
+	struct ixgbe_hw *hw = &adapter->hw;
+	u32 gssr = hw->phy.phy_semaphore_mask;
+
+	gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM;
+	return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr);
+}
+
+/**
+ * ixgbe_get_first_secondary_devfn - get first device downstream of root port
+ * @devfn: PCI_DEVFN of root port on domain 0, bus 0
+ *
+ * Returns pci_dev pointer to PCI_DEVFN(0, 0) on subordinate side of root
+ * on domain 0, bus 0, devfn = 'devfn'
+ **/
+static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn)
+{
+	struct pci_dev *rp_pdev;
+	int bus;
+
+	rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn);
+	if (rp_pdev && rp_pdev->subordinate) {
+		bus = rp_pdev->subordinate->number;
+		return pci_get_domain_bus_and_slot(0, bus, 0);
+	}
+
+	return NULL;
+}
+
+/**
+ * ixgbe_x550em_a_has_mii - is this the first ixgbe x550em_a PCI function?
+ * @hw: pointer to hardware structure
+ *
+ * Returns true if hw points to lowest numbered PCI B:D.F x550_em_a device in
+ * the SoC.  There are up to 4 MACs sharing a single MDIO bus on the x550em_a,
+ * but we only want to register one MDIO bus.
+ **/
+static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw)
+{
+	struct ixgbe_adapter *adapter = hw->back;
+	struct pci_dev *pdev = adapter->pdev;
+	struct pci_dev *func0_pdev;
+
+	/* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices
+	 * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0
+	 * It's not valid for function 0 to be disabled and function 1 is up,
+	 * so the lowest numbered ixgbe dev will be device 0 function 0 on one
+	 * of those two root ports
+	 */
+	func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0));
+	if (func0_pdev) {
+		if (func0_pdev == pdev)
+			return true;
+		else
+			return false;
+	}
+	func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0));
+	if (func0_pdev == pdev)
+		return true;
+
+	return false;
+}
+
+/**
+ * ixgbe_mii_bus_init - mii_bus structure setup
+ * @hw: pointer to hardware structure
+ *
+ * Returns 0 on success, negative on failure
+ *
+ * ixgbe_mii_bus_init initializes a mii_bus structure in adapter
+ **/
+s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw)
+{
+	struct ixgbe_adapter *adapter = hw->back;
+	struct pci_dev *pdev = adapter->pdev;
+	struct device *dev = &adapter->netdev->dev;
+	struct mii_bus *bus;
+	int err = -ENODEV;
+
+	bus = devm_mdiobus_alloc(dev);
+	if (!bus)
+		return -ENOMEM;
+
+	switch (hw->device_id) {
+	/* C3000 SoCs */
+	case IXGBE_DEV_ID_X550EM_A_KR:
+	case IXGBE_DEV_ID_X550EM_A_KR_L:
+	case IXGBE_DEV_ID_X550EM_A_SFP_N:
+	case IXGBE_DEV_ID_X550EM_A_SGMII:
+	case IXGBE_DEV_ID_X550EM_A_SGMII_L:
+	case IXGBE_DEV_ID_X550EM_A_10G_T:
+	case IXGBE_DEV_ID_X550EM_A_SFP:
+	case IXGBE_DEV_ID_X550EM_A_1G_T:
+	case IXGBE_DEV_ID_X550EM_A_1G_T_L:
+		if (!ixgbe_x550em_a_has_mii(hw))
+			goto ixgbe_no_mii_bus;
+		bus->read = &ixgbe_x550em_a_mii_bus_read;
+		bus->write = &ixgbe_x550em_a_mii_bus_write;
+		break;
+	default:
+		bus->read = &ixgbe_mii_bus_read;
+		bus->write = &ixgbe_mii_bus_write;
+		break;
+	}
+
+	/* Use the position of the device in the PCI hierarchy as the id */
+	snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mdio-%s", ixgbe_driver_name,
+		 pci_name(pdev));
+
+	bus->name = "ixgbe-mdio";
+	bus->priv = adapter;
+	bus->parent = dev;
+	bus->phy_mask = GENMASK(31, 0);
+
+	/* Support clause 22/45 natively.  ixgbe_probe() sets MDIO_EMULATE_C22
+	 * unfortunately that causes some clause 22 frames to be sent with
+	 * clause 45 addressing.  We don't want that.
+	 */
+	hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22;
+
+	err = mdiobus_register(bus);
+	if (!err) {
+		adapter->mii_bus = bus;
+		return 0;
+	}
+
+ixgbe_no_mii_bus:
+	devm_mdiobus_free(dev, bus);
+	return err;
+}
+
 /**
  *  ixgbe_setup_phy_link_generic - Set and restart autoneg
  *  @hw: pointer to hardware structure
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
index 64e44e01c973..214b01085718 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h
@@ -120,6 +120,8 @@
 /* SFP+ SFF-8472 Compliance code */
 #define IXGBE_SFF_SFF_8472_UNSUP      0x00
 
+s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw);
+
 s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw);
 s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw);
 s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index b3e0d8bb5cbd..d81a50dc9535 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -443,22 +443,52 @@ static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 }
 
 /**
- * ixgbe_ptp_gettime
+ * ixgbe_ptp_gettimex
  * @ptp: the ptp clock structure
- * @ts: timespec structure to hold the current time value
+ * @ts: timespec to hold the PHC timestamp
+ * @sts: structure to hold the system time before and after reading the PHC
  *
  * read the timecounter and return the correct value on ns,
  * after converting it into a struct timespec.
  */
-static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp,
+			      struct timespec64 *ts,
+			      struct ptp_system_timestamp *sts)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(ptp, struct ixgbe_adapter, ptp_caps);
+	struct ixgbe_hw *hw = &adapter->hw;
 	unsigned long flags;
-	u64 ns;
+	u64 ns, stamp;
 
 	spin_lock_irqsave(&adapter->tmreg_lock, flags);
-	ns = timecounter_read(&adapter->hw_tc);
+
+	switch (adapter->hw.mac.type) {
+	case ixgbe_mac_X550:
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+		/* Upper 32 bits represent billions of cycles, lower 32 bits
+		 * represent cycles. However, we use timespec64_to_ns for the
+		 * correct math even though the units haven't been corrected
+		 * yet.
+		 */
+		ptp_read_system_prets(sts);
+		IXGBE_READ_REG(hw, IXGBE_SYSTIMR);
+		ptp_read_system_postts(sts);
+		ts->tv_nsec = IXGBE_READ_REG(hw, IXGBE_SYSTIML);
+		ts->tv_sec = IXGBE_READ_REG(hw, IXGBE_SYSTIMH);
+		stamp = timespec64_to_ns(ts);
+		break;
+	default:
+		ptp_read_system_prets(sts);
+		stamp = IXGBE_READ_REG(hw, IXGBE_SYSTIML);
+		ptp_read_system_postts(sts);
+		stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32;
+		break;
+	}
+
+	ns = timecounter_cyc2time(&adapter->hw_tc, stamp);
+
 	spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
 
 	*ts = ns_to_timespec64(ns);
@@ -567,10 +597,14 @@ void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter)
 {
 	bool timeout = time_is_before_jiffies(adapter->last_overflow_check +
 					     IXGBE_OVERFLOW_PERIOD);
-	struct timespec64 ts;
+	unsigned long flags;
 
 	if (timeout) {
-		ixgbe_ptp_gettime(&adapter->ptp_caps, &ts);
+		/* Update the timecounter */
+		spin_lock_irqsave(&adapter->tmreg_lock, flags);
+		timecounter_read(&adapter->hw_tc);
+		spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
 		adapter->last_overflow_check = jiffies;
 	}
 }
@@ -1216,7 +1250,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.pps = 1;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
-		adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_x540;
@@ -1233,7 +1267,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
-		adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		break;
@@ -1249,7 +1283,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 		adapter->ptp_caps.pps = 0;
 		adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_X550;
 		adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime;
-		adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime;
+		adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex;
 		adapter->ptp_caps.settime64 = ixgbe_ptp_settime;
 		adapter->ptp_caps.enable = ixgbe_ptp_feature_enable;
 		adapter->ptp_setup_sdp = NULL;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
index 53d4089f5644..d93a690aff74 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h
@@ -30,8 +30,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring);
 
 struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter,
 				struct ixgbe_ring *ring);
-int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem,
-			 u16 qid);
 int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
 			 u16 qid);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index 65c3e2c979d4..bfe95ce0bd7f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -144,11 +144,19 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter,
 		ixgbe_txrx_ring_disable(adapter, qid);
 
 	err = ixgbe_add_xsk_umem(adapter, umem, qid);
+	if (err)
+		return err;
 
-	if (if_running)
+	if (if_running) {
 		ixgbe_txrx_ring_enable(adapter, qid);
 
-	return err;
+		/* Kick start the NAPI context so that receiving will start */
+		err = ixgbe_xsk_async_xmit(adapter->netdev, qid);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
@@ -174,23 +182,6 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid)
 	return 0;
 }
 
-int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem,
-			 u16 qid)
-{
-	if (qid >= adapter->num_rx_queues)
-		return -EINVAL;
-
-	if (adapter->xsk_umems) {
-		if (qid >= adapter->num_xsk_umems)
-			return -EINVAL;
-		*umem = adapter->xsk_umems[qid];
-		return 0;
-	}
-
-	*umem = NULL;
-	return 0;
-}
-
 int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem,
 			 u16 qid)
 {
@@ -634,7 +625,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget)
 	dma_addr_t dma;
 
 	while (budget-- > 0) {
-		if (unlikely(!ixgbe_desc_unused(xdp_ring))) {
+		if (unlikely(!ixgbe_desc_unused(xdp_ring)) ||
+		    !netif_carrier_ok(xdp_ring->netdev)) {
 			work_done = false;
 			break;
 		}
diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
index e8a3231be0bf..5170dd9d8705 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c
@@ -450,12 +450,14 @@ int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring,
 	struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev);
 	struct ixgbevf_ipsec *ipsec = adapter->ipsec;
 	struct xfrm_state *xs;
+	struct sec_path *sp;
 	struct tx_sa *tsa;
 	u16 sa_idx;
 
-	if (unlikely(!first->skb->sp->len)) {
+	sp = skb_sec_path(first->skb);
+	if (unlikely(!sp->len)) {
 		netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n",
-			   __func__, first->skb->sp->len);
+			   __func__, sp->len);
 		return 0;
 	}
 
@@ -546,6 +548,7 @@ void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
 	struct xfrm_state *xs = NULL;
 	struct ipv6hdr *ip6 = NULL;
 	struct iphdr *ip4 = NULL;
+	struct sec_path *sp;
 	void *daddr;
 	__be32 spi;
 	u8 *c_hdr;
@@ -585,12 +588,12 @@ void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring,
 	if (unlikely(!xs))
 		return;
 
-	skb->sp = secpath_dup(skb->sp);
-	if (unlikely(!skb->sp))
+	sp = secpath_set(skb);
+	if (unlikely(!sp))
 		return;
 
-	skb->sp->xvec[skb->sp->len++] = xs;
-	skb->sp->olen++;
+	sp->xvec[sp->len++] = xs;
+	sp->olen++;
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
 	xo->status = CRYPTO_SUCCESS;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 5e47ede7e832..49e23afa05a2 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -1293,16 +1293,20 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget)
 	/* If all work not completed, return budget and keep polling */
 	if (!clean_complete)
 		return budget;
-	/* all work done, exit the polling mode */
-	napi_complete_done(napi, work_done);
-	if (adapter->rx_itr_setting == 1)
-		ixgbevf_set_itr(q_vector);
-	if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
-	    !test_bit(__IXGBEVF_REMOVING, &adapter->state))
-		ixgbevf_irq_enable_queues(adapter,
-					  BIT(q_vector->v_idx));
 
-	return 0;
+	/* Exit the polling mode, but don't re-enable interrupts if stack might
+	 * poll us due to busy-polling
+	 */
+	if (likely(napi_complete_done(napi, work_done))) {
+		if (adapter->rx_itr_setting == 1)
+			ixgbevf_set_itr(q_vector);
+		if (!test_bit(__IXGBEVF_DOWN, &adapter->state) &&
+		    !test_bit(__IXGBEVF_REMOVING, &adapter->state))
+			ixgbevf_irq_enable_queues(adapter,
+						  BIT(q_vector->v_idx));
+	}
+
+	return min(work_done, budget - 1);
 }
 
 /**
@@ -4016,6 +4020,8 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring,
 	/* set the timestamp */
 	first->time_stamp = jiffies;
 
+	skb_tx_timestamp(skb);
+
 	/* Force memory writes to complete before letting h/w know there
 	 * are new descriptors to fetch.  (Only applicable for weak-ordered
 	 * memory model archs, such as IA-64).
@@ -4151,7 +4157,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb,
 	first->protocol = vlan_get_protocol(skb);
 
 #ifdef CONFIG_IXGBEVF_IPSEC
-	if (skb->sp && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
+	if (secpath_exists(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx))
 		goto out_drop;
 #endif
 	tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx);
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index a5ab6f3403ae..763ee5281177 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -2034,10 +2034,9 @@ static void jme_drop_tx_map(struct jme_adapter *jme, int startidx, int count)
 				ctxbi->len,
 				PCI_DMA_TODEVICE);
 
-				ctxbi->mapping = 0;
-				ctxbi->len = 0;
+		ctxbi->mapping = 0;
+		ctxbi->len = 0;
 	}
-
 }
 
 static int
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 32ac9045cdae..f9bb890733b5 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -112,10 +112,12 @@ struct ltq_etop_priv {
 static int
 ltq_etop_alloc_skb(struct ltq_etop_chan *ch)
 {
+	struct ltq_etop_priv *priv = netdev_priv(ch->netdev);
+
 	ch->skb[ch->dma.desc] = netdev_alloc_skb(ch->netdev, MAX_DMA_DATA_LEN);
 	if (!ch->skb[ch->dma.desc])
 		return -ENOMEM;
-	ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(NULL,
+	ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(&priv->pdev->dev,
 		ch->skb[ch->dma.desc]->data, MAX_DMA_DATA_LEN,
 		DMA_FROM_DEVICE);
 	ch->dma.desc_base[ch->dma.desc].addr =
@@ -487,7 +489,7 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev)
 	netif_trans_update(dev);
 
 	spin_lock_irqsave(&priv->lock, flags);
-	desc->addr = ((unsigned int) dma_map_single(NULL, skb->data, len,
+	desc->addr = ((unsigned int) dma_map_single(&priv->pdev->dev, skb->data, len,
 						DMA_TO_DEVICE)) - byte_offset;
 	wmb();
 	desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP |
diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c
index 2d4d10a017e5..d29104de0d53 100644
--- a/drivers/net/ethernet/lantiq_xrx200.c
+++ b/drivers/net/ethernet/lantiq_xrx200.c
@@ -335,7 +335,6 @@ static const struct net_device_ops xrx200_netdev_ops = {
 	.ndo_start_xmit		= xrx200_start_xmit,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_change_mtu		= eth_change_mtu,
 };
 
 static irqreturn_t xrx200_dma_irq(int irq, void *ptr)
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 1e9bcbdc6a90..292a668ce88e 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1499,23 +1499,16 @@ mv643xx_eth_get_link_ksettings_phy(struct mv643xx_eth_private *mp,
 				   struct ethtool_link_ksettings *cmd)
 {
 	struct net_device *dev = mp->dev;
-	u32 supported, advertising;
 
 	phy_ethtool_ksettings_get(dev->phydev, cmd);
 
 	/*
 	 * The MAC does not support 1000baseT_Half.
 	 */
-	ethtool_convert_link_mode_to_legacy_u32(&supported,
-						cmd->link_modes.supported);
-	ethtool_convert_link_mode_to_legacy_u32(&advertising,
-						cmd->link_modes.advertising);
-	supported &= ~SUPPORTED_1000baseT_Half;
-	advertising &= ~ADVERTISED_1000baseT_Half;
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			   cmd->link_modes.supported);
+	linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
+			   cmd->link_modes.advertising);
 
 	return 0;
 }
@@ -2886,7 +2879,7 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev)
 
 	ret = mv643xx_eth_shared_of_probe(pdev);
 	if (ret)
-		return ret;
+		goto err_put_clk;
 	pd = dev_get_platdata(&pdev->dev);
 
 	msp->tx_csum_limit = (pd != NULL && pd->tx_csum_limit) ?
@@ -2894,6 +2887,11 @@ static int mv643xx_eth_shared_probe(struct platform_device *pdev)
 	infer_hw_params(msp);
 
 	return 0;
+
+err_put_clk:
+	if (!IS_ERR(msp->clk))
+		clk_disable_unprepare(msp->clk);
+	return ret;
 }
 
 static int mv643xx_eth_shared_remove(struct platform_device *pdev)
@@ -3031,10 +3029,12 @@ static void phy_init(struct mv643xx_eth_private *mp, int speed, int duplex)
 		phy->autoneg = AUTONEG_ENABLE;
 		phy->speed = 0;
 		phy->duplex = 0;
-		phy->advertising = phy->supported | ADVERTISED_Autoneg;
+		linkmode_copy(phy->advertising, phy->supported);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
+				 phy->advertising);
 	} else {
 		phy->autoneg = AUTONEG_DISABLE;
-		phy->advertising = 0;
+		linkmode_zero(phy->advertising);
 		phy->speed = speed;
 		phy->duplex = duplex;
 	}
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 61b23497f836..c0a3718b2e2a 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -27,6 +27,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
+#include <linux/phy/phy.h>
 #include <linux/phy.h>
 #include <linux/phylink.h>
 #include <linux/platform_device.h>
@@ -436,6 +437,7 @@ struct mvneta_port {
 	struct device_node *dn;
 	unsigned int tx_csum_limit;
 	struct phylink *phylink;
+	struct phy *comphy;
 
 	struct mvneta_bm *bm_priv;
 	struct mvneta_bm_pool *pool_long;
@@ -2146,7 +2148,7 @@ err_drop_frame:
 			if (unlikely(!skb))
 				goto err_drop_frame_ret_pool;
 
-			dma_sync_single_range_for_cpu(dev->dev.parent,
+			dma_sync_single_range_for_cpu(&pp->bm_priv->pdev->dev,
 			                              rx_desc->buf_phys_addr,
 			                              MVNETA_MH_SIZE + NET_SKB_PAD,
 			                              rx_bytes,
@@ -3147,10 +3149,27 @@ static int mvneta_setup_txqs(struct mvneta_port *pp)
 	return 0;
 }
 
+static int mvneta_comphy_init(struct mvneta_port *pp)
+{
+	int ret;
+
+	if (!pp->comphy)
+		return 0;
+
+	ret = phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET,
+			       pp->phy_interface);
+	if (ret)
+		return ret;
+
+	return phy_power_on(pp->comphy);
+}
+
 static void mvneta_start_dev(struct mvneta_port *pp)
 {
 	int cpu;
 
+	WARN_ON(mvneta_comphy_init(pp));
+
 	mvneta_max_rx_size_set(pp, pp->pkt_size);
 	mvneta_txq_max_tx_size_set(pp, pp->pkt_size);
 
@@ -3213,6 +3232,8 @@ static void mvneta_stop_dev(struct mvneta_port *pp)
 
 	mvneta_tx_reset(pp);
 	mvneta_rx_reset(pp);
+
+	WARN_ON(phy_power_off(pp->comphy));
 }
 
 static void mvneta_percpu_enable(void *arg)
@@ -3338,6 +3359,7 @@ static int mvneta_set_mac_addr(struct net_device *dev, void *addr)
 static void mvneta_validate(struct net_device *ndev, unsigned long *supported,
 			    struct phylink_link_state *state)
 {
+	struct mvneta_port *pp = netdev_priv(ndev);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 
 	/* We only support QSGMII, SGMII, 802.3z and RGMII modes */
@@ -3358,8 +3380,13 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported,
 	phylink_set(mask, Pause);
 
 	/* Half-duplex at speeds higher than 100Mbit is unsupported */
-	phylink_set(mask, 1000baseT_Full);
-	phylink_set(mask, 1000baseX_Full);
+	if (pp->comphy || state->interface != PHY_INTERFACE_MODE_2500BASEX) {
+		phylink_set(mask, 1000baseT_Full);
+		phylink_set(mask, 1000baseX_Full);
+	}
+	if (pp->comphy || state->interface == PHY_INTERFACE_MODE_2500BASEX) {
+		phylink_set(mask, 2500baseX_Full);
+	}
 
 	if (!phy_interface_mode_is_8023z(state->interface)) {
 		/* 10M and 100M are only supported in non-802.3z mode */
@@ -3373,6 +3400,11 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
 	bitmap_and(state->advertising, state->advertising, mask,
 		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	/* We can only operate at 2500BaseX or 1000BaseX.  If requested
+	 * to advertise both, only report advertising at 2500BaseX.
+	 */
+	phylink_helper_basex_speed(state);
 }
 
 static int mvneta_mac_link_state(struct net_device *ndev,
@@ -3384,7 +3416,9 @@ static int mvneta_mac_link_state(struct net_device *ndev,
 	gmac_stat = mvreg_read(pp, MVNETA_GMAC_STATUS);
 
 	if (gmac_stat & MVNETA_GMAC_SPEED_1000)
-		state->speed = SPEED_1000;
+		state->speed =
+			state->interface == PHY_INTERFACE_MODE_2500BASEX ?
+			SPEED_2500 : SPEED_1000;
 	else if (gmac_stat & MVNETA_GMAC_SPEED_100)
 		state->speed = SPEED_100;
 	else
@@ -3499,12 +3533,23 @@ static void mvneta_mac_config(struct net_device *ndev, unsigned int mode,
 			    MVNETA_GMAC_FORCE_LINK_DOWN);
 	}
 
+
 	/* When at 2.5G, the link partner can send frames with shortened
 	 * preambles.
 	 */
 	if (state->speed == SPEED_2500)
 		new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE;
 
+	if (pp->comphy && pp->phy_interface != state->interface &&
+	    (state->interface == PHY_INTERFACE_MODE_SGMII ||
+	     state->interface == PHY_INTERFACE_MODE_1000BASEX ||
+	     state->interface == PHY_INTERFACE_MODE_2500BASEX)) {
+		pp->phy_interface = state->interface;
+
+		WARN_ON(phy_power_off(pp->comphy));
+		WARN_ON(mvneta_comphy_init(pp));
+	}
+
 	if (new_ctrl0 != gmac_ctrl0)
 		mvreg_write(pp, MVNETA_GMAC_CTRL_0, new_ctrl0);
 	if (new_ctrl2 != gmac_ctrl2)
@@ -4248,8 +4293,7 @@ static int mvneta_ethtool_set_eee(struct net_device *dev,
 
 	/* The Armada 37x documents do not give limits for this other than
 	 * it being an 8-bit register. */
-	if (eee->tx_lpi_enabled &&
-	    (eee->tx_lpi_timer < 0 || eee->tx_lpi_timer > 255))
+	if (eee->tx_lpi_enabled && eee->tx_lpi_timer > 255)
 		return -EINVAL;
 
 	lpi_ctl0 = mvreg_read(pp, MVNETA_LPI_CTRL_0);
@@ -4405,7 +4449,7 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode)
 	if (phy_mode == PHY_INTERFACE_MODE_QSGMII)
 		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO);
 	else if (phy_mode == PHY_INTERFACE_MODE_SGMII ||
-		 phy_mode == PHY_INTERFACE_MODE_1000BASEX)
+		 phy_interface_mode_is_8023z(phy_mode))
 		mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO);
 	else if (!phy_interface_mode_is_rgmii(phy_mode))
 		return -EINVAL;
@@ -4422,6 +4466,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	struct mvneta_port *pp;
 	struct net_device *dev;
 	struct phylink *phylink;
+	struct phy *comphy;
 	const char *dt_mac_addr;
 	char hw_mac_addr[ETH_ALEN];
 	const char *mac_from;
@@ -4447,6 +4492,14 @@ static int mvneta_probe(struct platform_device *pdev)
 		goto err_free_irq;
 	}
 
+	comphy = devm_of_phy_get(&pdev->dev, dn, NULL);
+	if (comphy == ERR_PTR(-EPROBE_DEFER)) {
+		err = -EPROBE_DEFER;
+		goto err_free_irq;
+	} else if (IS_ERR(comphy)) {
+		comphy = NULL;
+	}
+
 	phylink = phylink_create(dev, pdev->dev.fwnode, phy_mode,
 				 &mvneta_phylink_ops);
 	if (IS_ERR(phylink)) {
@@ -4463,6 +4516,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp = netdev_priv(dev);
 	spin_lock_init(&pp->lock);
 	pp->phylink = phylink;
+	pp->comphy = comphy;
 	pp->phy_interface = phy_mode;
 	pp->dn = dn;
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 398328f10743..ff0f4c503f53 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -389,7 +389,7 @@
 #define     MVPP2_GMAC_IN_BAND_AUTONEG		BIT(2)
 #define     MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS	BIT(3)
 #define     MVPP2_GMAC_IN_BAND_RESTART_AN	BIT(4)
-#define     MVPP2_GMAC_CONFIG_MII_SPEED	BIT(5)
+#define     MVPP2_GMAC_CONFIG_MII_SPEED		BIT(5)
 #define     MVPP2_GMAC_CONFIG_GMII_SPEED	BIT(6)
 #define     MVPP2_GMAC_AN_SPEED_EN		BIT(7)
 #define     MVPP2_GMAC_FC_ADV_EN		BIT(9)
@@ -402,8 +402,8 @@
 #define     MVPP2_GMAC_STATUS0_GMII_SPEED	BIT(1)
 #define     MVPP2_GMAC_STATUS0_MII_SPEED	BIT(2)
 #define     MVPP2_GMAC_STATUS0_FULL_DUPLEX	BIT(3)
-#define     MVPP2_GMAC_STATUS0_RX_PAUSE		BIT(6)
-#define     MVPP2_GMAC_STATUS0_TX_PAUSE		BIT(7)
+#define     MVPP2_GMAC_STATUS0_RX_PAUSE		BIT(4)
+#define     MVPP2_GMAC_STATUS0_TX_PAUSE		BIT(5)
 #define     MVPP2_GMAC_STATUS0_AN_COMPLETE	BIT(11)
 #define MVPP2_GMAC_PORT_FIFO_CFG_1_REG		0x1c
 #define     MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS	6
@@ -430,6 +430,8 @@
 #define MVPP22_XLG_CTRL0_REG			0x100
 #define     MVPP22_XLG_CTRL0_PORT_EN		BIT(0)
 #define     MVPP22_XLG_CTRL0_MAC_RESET_DIS	BIT(1)
+#define     MVPP22_XLG_CTRL0_FORCE_LINK_DOWN	BIT(2)
+#define     MVPP22_XLG_CTRL0_FORCE_LINK_PASS	BIT(3)
 #define     MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN	BIT(7)
 #define     MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN	BIT(8)
 #define     MVPP22_XLG_CTRL0_MIB_CNT_DIS	BIT(14)
@@ -481,6 +483,7 @@
 /* XPCS registers. PPv2.2 only */
 #define MVPP22_XPCS_BASE(port)			(0x7400 + (port) * 0x1000)
 #define MVPP22_XPCS_CFG0			0x0
+#define     MVPP22_XPCS_CFG0_RESET_DIS		BIT(0)
 #define     MVPP22_XPCS_CFG0_PCS_MODE(n)	((n) << 3)
 #define     MVPP22_XPCS_CFG0_ACTIVE_LANE(n)	((n) << 5)
 
@@ -549,8 +552,8 @@
 #define MVPP2_MAX_TSO_SEGS		300
 #define MVPP2_MAX_SKB_DESCS		(MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
 
-/* Dfault number of RXQs in use */
-#define MVPP2_DEFAULT_RXQ		1
+/* Max number of RXQs per port */
+#define MVPP2_PORT_MAX_RXQ		32
 
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD_MAX		1024
@@ -803,7 +806,7 @@ struct mvpp2_port {
 	u8 id;
 
 	/* Index of the port from the "group of ports" complex point
-	 * of view
+	 * of view. This is specific to PPv2.2.
 	 */
 	int gop_id;
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index f1dab0b55769..25fbed2b8d94 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -965,6 +965,11 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask)
 }
 
 /* Port configuration routines */
+static bool mvpp2_is_xlg(phy_interface_t interface)
+{
+	return interface == PHY_INTERFACE_MODE_10GKR ||
+	       interface == PHY_INTERFACE_MODE_XAUI;
+}
 
 static void mvpp22_gop_init_rgmii(struct mvpp2_port *port)
 {
@@ -1010,27 +1015,20 @@ static void mvpp22_gop_init_10gkr(struct mvpp2_port *port)
 	void __iomem *xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
 	u32 val;
 
-	/* XPCS */
 	val = readl(xpcs + MVPP22_XPCS_CFG0);
 	val &= ~(MVPP22_XPCS_CFG0_PCS_MODE(0x3) |
 		 MVPP22_XPCS_CFG0_ACTIVE_LANE(0x3));
 	val |= MVPP22_XPCS_CFG0_ACTIVE_LANE(2);
 	writel(val, xpcs + MVPP22_XPCS_CFG0);
 
-	/* MPCS */
 	val = readl(mpcs + MVPP22_MPCS_CTRL);
 	val &= ~MVPP22_MPCS_CTRL_FWD_ERR_CONN;
 	writel(val, mpcs + MVPP22_MPCS_CTRL);
 
 	val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
-	val &= ~(MVPP22_MPCS_CLK_RESET_DIV_RATIO(0x7) | MAC_CLK_RESET_MAC |
-		 MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX);
+	val &= ~MVPP22_MPCS_CLK_RESET_DIV_RATIO(0x7);
 	val |= MVPP22_MPCS_CLK_RESET_DIV_RATIO(1);
 	writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
-
-	val &= ~MVPP22_MPCS_CLK_RESET_DIV_SET;
-	val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX;
-	writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
 }
 
 static int mvpp22_gop_init(struct mvpp2_port *port)
@@ -1090,9 +1088,8 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port)
 	u32 val;
 
 	if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-	    port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+	    phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		/* Enable the GMAC link status irq for this port */
 		val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK);
 		val |= MVPP22_GMAC_INT_SUM_MASK_LINK_STAT;
@@ -1102,7 +1099,7 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port)
 	if (port->gop_id == 0) {
 		/* Enable the XLG/GIG irqs for this port */
 		val = readl(port->base + MVPP22_XLG_EXT_INT_MASK);
-		if (port->phy_interface == PHY_INTERFACE_MODE_10GKR)
+		if (mvpp2_is_xlg(port->phy_interface))
 			val |= MVPP22_XLG_EXT_INT_MASK_XLG;
 		else
 			val |= MVPP22_XLG_EXT_INT_MASK_GIG;
@@ -1122,9 +1119,8 @@ static void mvpp22_gop_mask_irq(struct mvpp2_port *port)
 	}
 
 	if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-	    port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+	    phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK);
 		val &= ~MVPP22_GMAC_INT_SUM_MASK_LINK_STAT;
 		writel(val, port->base + MVPP22_GMAC_INT_SUM_MASK);
@@ -1135,10 +1131,10 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port)
 {
 	u32 val;
 
-	if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-	    port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+	if (port->phylink ||
+	    phy_interface_mode_is_rgmii(port->phy_interface) ||
+	    phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		val = readl(port->base + MVPP22_GMAC_INT_MASK);
 		val |= MVPP22_GMAC_INT_MASK_LINK_STAT;
 		writel(val, port->base + MVPP22_GMAC_INT_MASK);
@@ -1165,28 +1161,13 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port)
  */
 static int mvpp22_comphy_init(struct mvpp2_port *port)
 {
-	enum phy_mode mode;
 	int ret;
 
 	if (!port->comphy)
 		return 0;
 
-	switch (port->phy_interface) {
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_1000BASEX:
-		mode = PHY_MODE_SGMII;
-		break;
-	case PHY_INTERFACE_MODE_2500BASEX:
-		mode = PHY_MODE_2500SGMII;
-		break;
-	case PHY_INTERFACE_MODE_10GKR:
-		mode = PHY_MODE_10GKR;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = phy_set_mode(port->comphy, mode);
+	ret = phy_set_mode_ext(port->comphy, PHY_MODE_ETHERNET,
+			       port->phy_interface);
 	if (ret)
 		return ret;
 
@@ -1198,12 +1179,9 @@ static void mvpp2_port_enable(struct mvpp2_port *port)
 	u32 val;
 
 	/* Only GOP port 0 has an XLG MAC */
-	if (port->gop_id == 0 &&
-	    (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-	     port->phy_interface == PHY_INTERFACE_MODE_10GKR)) {
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) {
 		val = readl(port->base + MVPP22_XLG_CTRL0_REG);
-		val |= MVPP22_XLG_CTRL0_PORT_EN |
-		       MVPP22_XLG_CTRL0_MAC_RESET_DIS;
+		val |= MVPP22_XLG_CTRL0_PORT_EN;
 		val &= ~MVPP22_XLG_CTRL0_MIB_CNT_DIS;
 		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
 	} else {
@@ -1219,21 +1197,15 @@ static void mvpp2_port_disable(struct mvpp2_port *port)
 	u32 val;
 
 	/* Only GOP port 0 has an XLG MAC */
-	if (port->gop_id == 0 &&
-	    (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-	     port->phy_interface == PHY_INTERFACE_MODE_10GKR)) {
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) {
 		val = readl(port->base + MVPP22_XLG_CTRL0_REG);
 		val &= ~MVPP22_XLG_CTRL0_PORT_EN;
 		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
-
-		/* Disable & reset should be done separately */
-		val &= ~MVPP22_XLG_CTRL0_MAC_RESET_DIS;
-		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
-	} else {
-		val = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
-		val &= ~(MVPP2_GMAC_PORT_EN_MASK);
-		writel(val, port->base + MVPP2_GMAC_CTRL_0_REG);
 	}
+
+	val = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
+	val &= ~(MVPP2_GMAC_PORT_EN_MASK);
+	writel(val, port->base + MVPP2_GMAC_CTRL_0_REG);
 }
 
 /* Set IEEE 802.3x Flow Control Xon Packet Transmission Mode */
@@ -1259,9 +1231,8 @@ static void mvpp2_port_loopback_set(struct mvpp2_port *port,
 	else
 		val &= ~MVPP2_GMAC_GMII_LB_EN_MASK;
 
-	if (port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-	    port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    port->phy_interface == PHY_INTERFACE_MODE_2500BASEX)
+	if (phy_interface_mode_is_8023z(port->phy_interface) ||
+	    port->phy_interface == PHY_INTERFACE_MODE_SGMII)
 		val |= MVPP2_GMAC_PCS_LB_EN_MASK;
 	else
 		val &= ~MVPP2_GMAC_PCS_LB_EN_MASK;
@@ -1386,22 +1357,75 @@ static int mvpp2_ethtool_get_sset_count(struct net_device *dev, int sset)
 	return -EOPNOTSUPP;
 }
 
-static void mvpp2_port_reset(struct mvpp2_port *port)
+static void mvpp2_mac_reset_assert(struct mvpp2_port *port)
 {
-	u32 val;
 	unsigned int i;
+	u32 val;
 
 	/* Read the GOP statistics to reset the hardware counters */
 	for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++)
 		mvpp2_read_count(port, &mvpp2_ethtool_regs[i]);
 
-	val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) &
-		    ~MVPP2_GMAC_PORT_RESET_MASK;
+	val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) |
+	      MVPP2_GMAC_PORT_RESET_MASK;
 	writel(val, port->base + MVPP2_GMAC_CTRL_2_REG);
 
-	while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) &
-	       MVPP2_GMAC_PORT_RESET_MASK)
-		continue;
+	if (port->priv->hw_version == MVPP22 && port->gop_id == 0) {
+		val = readl(port->base + MVPP22_XLG_CTRL0_REG) &
+		      ~MVPP22_XLG_CTRL0_MAC_RESET_DIS;
+		writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+	}
+}
+
+static void mvpp22_pcs_reset_assert(struct mvpp2_port *port)
+{
+	struct mvpp2 *priv = port->priv;
+	void __iomem *mpcs, *xpcs;
+	u32 val;
+
+	if (port->priv->hw_version != MVPP22 || port->gop_id != 0)
+		return;
+
+	mpcs = priv->iface_base + MVPP22_MPCS_BASE(port->gop_id);
+	xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
+
+	val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
+	val &= ~(MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX | MAC_CLK_RESET_SD_TX);
+	val |= MVPP22_MPCS_CLK_RESET_DIV_SET;
+	writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
+
+	val = readl(xpcs + MVPP22_XPCS_CFG0);
+	writel(val & ~MVPP22_XPCS_CFG0_RESET_DIS, xpcs + MVPP22_XPCS_CFG0);
+}
+
+static void mvpp22_pcs_reset_deassert(struct mvpp2_port *port)
+{
+	struct mvpp2 *priv = port->priv;
+	void __iomem *mpcs, *xpcs;
+	u32 val;
+
+	if (port->priv->hw_version != MVPP22 || port->gop_id != 0)
+		return;
+
+	mpcs = priv->iface_base + MVPP22_MPCS_BASE(port->gop_id);
+	xpcs = priv->iface_base + MVPP22_XPCS_BASE(port->gop_id);
+
+	switch (port->phy_interface) {
+	case PHY_INTERFACE_MODE_10GKR:
+		val = readl(mpcs + MVPP22_MPCS_CLK_RESET);
+		val |= MAC_CLK_RESET_MAC | MAC_CLK_RESET_SD_RX |
+		       MAC_CLK_RESET_SD_TX;
+		val &= ~MVPP22_MPCS_CLK_RESET_DIV_SET;
+		writel(val, mpcs + MVPP22_MPCS_CLK_RESET);
+		break;
+	case PHY_INTERFACE_MODE_XAUI:
+	case PHY_INTERFACE_MODE_RXAUI:
+		val = readl(xpcs + MVPP22_XPCS_CFG0);
+		writel(val | MVPP22_XPCS_CFG0_RESET_DIS, xpcs + MVPP22_XPCS_CFG0);
+		break;
+	default:
+		break;
+	}
 }
 
 /* Change maximum receive size of the port */
@@ -2059,9 +2083,9 @@ static int mvpp2_aggr_txq_init(struct platform_device *pdev,
 	u32 txq_dma;
 
 	/* Allocate memory for TX descriptors */
-	aggr_txq->descs = dma_zalloc_coherent(&pdev->dev,
-				MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
-				&aggr_txq->descs_dma, GFP_KERNEL);
+	aggr_txq->descs = dma_alloc_coherent(&pdev->dev,
+					     MVPP2_AGGR_TXQ_SIZE * MVPP2_DESC_ALIGNED_SIZE,
+					     &aggr_txq->descs_dma, GFP_KERNEL);
 	if (!aggr_txq->descs)
 		return -ENOMEM;
 
@@ -2477,8 +2501,7 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id)
 
 	mvpp22_gop_mask_irq(port);
 
-	if (port->gop_id == 0 &&
-	    port->phy_interface == PHY_INTERFACE_MODE_10GKR) {
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) {
 		val = readl(port->base + MVPP22_XLG_INT_STAT);
 		if (val & MVPP22_XLG_INT_STAT_LINK) {
 			event = true;
@@ -2487,9 +2510,8 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id)
 				link = true;
 		}
 	} else if (phy_interface_mode_is_rgmii(port->phy_interface) ||
-		   port->phy_interface == PHY_INTERFACE_MODE_SGMII ||
-		   port->phy_interface == PHY_INTERFACE_MODE_1000BASEX ||
-		   port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) {
+		   phy_interface_mode_is_8023z(port->phy_interface) ||
+		   port->phy_interface == PHY_INTERFACE_MODE_SGMII) {
 		val = readl(port->base + MVPP22_GMAC_INT_STAT);
 		if (val & MVPP22_GMAC_INT_STAT_LINK) {
 			event = true;
@@ -3158,19 +3180,26 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port)
 {
 	u32 ctrl3;
 
+	/* Set the GMAC & XLG MAC in reset */
+	mvpp2_mac_reset_assert(port);
+
+	/* Set the MPCS and XPCS in reset */
+	mvpp22_pcs_reset_assert(port);
+
 	/* comphy reconfiguration */
 	mvpp22_comphy_init(port);
 
 	/* gop reconfiguration */
 	mvpp22_gop_init(port);
 
+	mvpp22_pcs_reset_deassert(port);
+
 	/* Only GOP port 0 has an XLG MAC */
 	if (port->gop_id == 0) {
 		ctrl3 = readl(port->base + MVPP22_XLG_CTRL3_REG);
 		ctrl3 &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK;
 
-		if (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-		    port->phy_interface == PHY_INTERFACE_MODE_10GKR)
+		if (mvpp2_is_xlg(port->phy_interface))
 			ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_10G;
 		else
 			ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC;
@@ -3178,9 +3207,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port)
 		writel(ctrl3, port->base + MVPP22_XLG_CTRL3_REG);
 	}
 
-	if (port->gop_id == 0 &&
-	    (port->phy_interface == PHY_INTERFACE_MODE_XAUI ||
-	     port->phy_interface == PHY_INTERFACE_MODE_10GKR))
+	if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface))
 		mvpp2_xlg_max_rx_size_set(port);
 	else
 		mvpp2_gmac_max_rx_size_set(port);
@@ -3498,6 +3525,9 @@ static int mvpp2_stop(struct net_device *dev)
 
 	cancel_delayed_work_sync(&port->stats_work);
 
+	mvpp2_mac_reset_assert(port);
+	mvpp22_pcs_reset_assert(port);
+
 	return 0;
 }
 
@@ -4087,8 +4117,8 @@ static int mvpp2_multi_queue_vectors_init(struct mvpp2_port *port,
 			snprintf(irqname, sizeof(irqname), "hif%d", i);
 
 		if (queue_mode == MVPP2_QDIST_MULTI_MODE) {
-			v->first_rxq = i * MVPP2_DEFAULT_RXQ;
-			v->nrxqs = MVPP2_DEFAULT_RXQ;
+			v->first_rxq = i;
+			v->nrxqs = 1;
 		} else if (queue_mode == MVPP2_QDIST_SINGLE_MODE &&
 			   i == (port->nqvecs - 1)) {
 			v->first_rxq = 0;
@@ -4181,8 +4211,7 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	    MVPP2_MAX_PORTS * priv->max_port_rxqs)
 		return -EINVAL;
 
-	if (port->nrxqs % MVPP2_DEFAULT_RXQ ||
-	    port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
+	if (port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
 		return -EINVAL;
 
 	/* Disable port */
@@ -4389,7 +4418,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 	case PHY_INTERFACE_MODE_RGMII_ID:
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
-		if (port->gop_id == 0)
+		if (port->priv->hw_version == MVPP22 && port->gop_id == 0)
 			goto empty_set;
 		break;
 	default:
@@ -4429,6 +4458,7 @@ static void mvpp2_phylink_validate(struct net_device *dev,
 	case PHY_INTERFACE_MODE_2500BASEX:
 		phylink_set(mask, 1000baseT_Full);
 		phylink_set(mask, 1000baseX_Full);
+		phylink_set(mask, 2500baseT_Full);
 		phylink_set(mask, 2500baseX_Full);
 		break;
 	default:
@@ -4520,131 +4550,198 @@ static int mvpp2_phylink_mac_link_state(struct net_device *dev,
 static void mvpp2_mac_an_restart(struct net_device *dev)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
-	u32 val;
-
-	if (port->phy_interface != PHY_INTERFACE_MODE_SGMII)
-		return;
+	u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
 
-	val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-	/* The RESTART_AN bit is cleared by the h/w after restarting the AN
-	 * process.
-	 */
-	val |= MVPP2_GMAC_IN_BAND_RESTART_AN | MVPP2_GMAC_IN_BAND_AUTONEG;
-	writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN,
+	       port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	writel(val & ~MVPP2_GMAC_IN_BAND_RESTART_AN,
+	       port->base + MVPP2_GMAC_AUTONEG_CONFIG);
 }
 
 static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode,
 			     const struct phylink_link_state *state)
 {
-	u32 ctrl0, ctrl4;
+	u32 old_ctrl0, ctrl0;
+	u32 old_ctrl4, ctrl4;
 
-	ctrl0 = readl(port->base + MVPP22_XLG_CTRL0_REG);
-	ctrl4 = readl(port->base + MVPP22_XLG_CTRL4_REG);
+	old_ctrl0 = ctrl0 = readl(port->base + MVPP22_XLG_CTRL0_REG);
+	old_ctrl4 = ctrl4 = readl(port->base + MVPP22_XLG_CTRL4_REG);
+
+	ctrl0 |= MVPP22_XLG_CTRL0_MAC_RESET_DIS;
 
 	if (state->pause & MLO_PAUSE_TX)
 		ctrl0 |= MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN;
+	else
+		ctrl0 &= ~MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN;
+
 	if (state->pause & MLO_PAUSE_RX)
 		ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
+	else
+		ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN;
 
 	ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC;
 	ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC |
 		 MVPP22_XLG_CTRL4_EN_IDLE_CHECK;
 
-	writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
-	writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG);
+	if (old_ctrl0 != ctrl0)
+		writel(ctrl0, port->base + MVPP22_XLG_CTRL0_REG);
+	if (old_ctrl4 != ctrl4)
+		writel(ctrl4, port->base + MVPP22_XLG_CTRL4_REG);
+
+	if (!(old_ctrl0 & MVPP22_XLG_CTRL0_MAC_RESET_DIS)) {
+		while (!(readl(port->base + MVPP22_XLG_CTRL0_REG) &
+			 MVPP22_XLG_CTRL0_MAC_RESET_DIS))
+			continue;
+	}
 }
 
 static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode,
 			      const struct phylink_link_state *state)
 {
-	u32 an, ctrl0, ctrl2, ctrl4;
+	u32 old_an, an;
+	u32 old_ctrl0, ctrl0;
+	u32 old_ctrl2, ctrl2;
+	u32 old_ctrl4, ctrl4;
 
-	an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-	ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
-	ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
-	ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
-
-	/* Force link down */
-	an &= ~MVPP2_GMAC_FORCE_LINK_PASS;
-	an |= MVPP2_GMAC_FORCE_LINK_DOWN;
-	writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-
-	/* Set the GMAC in a reset state */
-	ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK;
-	writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+	old_an = an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	old_ctrl0 = ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG);
+	old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG);
+	old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG);
 
 	an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED |
 		MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN |
 		MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG |
 		MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN |
-		MVPP2_GMAC_FORCE_LINK_DOWN);
+		MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS);
 	ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK;
-	ctrl2 &= ~(MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK);
-
-	if (state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    state->interface == PHY_INTERFACE_MODE_2500BASEX) {
-		/* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can
-		 * they negotiate duplex: they are always operating with a fixed
-		 * speed of 1000/2500Mbps in full duplex, so force 1000/2500
-		 * speed and full duplex here.
-		 */
-		ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK;
-		an |= MVPP2_GMAC_CONFIG_GMII_SPEED |
-		      MVPP2_GMAC_CONFIG_FULL_DUPLEX;
-	} else if (!phy_interface_mode_is_rgmii(state->interface)) {
-		an |= MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG;
+	ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK |
+		   MVPP2_GMAC_PCS_ENABLE_MASK);
+	ctrl4 &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN);
+
+	/* Configure port type */
+	if (phy_interface_mode_is_8023z(state->interface)) {
+		ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK;
+		ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+		ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
+			 MVPP22_CTRL4_DP_CLK_SEL |
+			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+	} else if (state->interface == PHY_INTERFACE_MODE_SGMII) {
+		ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK | MVPP2_GMAC_INBAND_AN_MASK;
+		ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL;
+		ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
+			 MVPP22_CTRL4_DP_CLK_SEL |
+			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+	} else if (phy_interface_mode_is_rgmii(state->interface)) {
+		ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL;
+		ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
+			 MVPP22_CTRL4_SYNC_BYPASS_DIS |
+			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
 	}
 
-	if (state->duplex)
-		an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX;
+	/* Configure advertisement bits */
 	if (phylink_test(state->advertising, Pause))
 		an |= MVPP2_GMAC_FC_ADV_EN;
 	if (phylink_test(state->advertising, Asym_Pause))
 		an |= MVPP2_GMAC_FC_ADV_ASM_EN;
 
-	if (state->interface == PHY_INTERFACE_MODE_SGMII ||
-	    state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-	    state->interface == PHY_INTERFACE_MODE_2500BASEX) {
-		an |= MVPP2_GMAC_IN_BAND_AUTONEG;
-		ctrl2 |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK;
+	/* Configure negotiation style */
+	if (!phylink_autoneg_inband(mode)) {
+		/* Phy or fixed speed - no in-band AN */
+		if (state->duplex)
+			an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX;
 
-		ctrl4 &= ~(MVPP22_CTRL4_EXT_PIN_GMII_SEL |
-			   MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN);
-		ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS |
-			 MVPP22_CTRL4_DP_CLK_SEL |
-			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+		if (state->speed == SPEED_1000 || state->speed == SPEED_2500)
+			an |= MVPP2_GMAC_CONFIG_GMII_SPEED;
+		else if (state->speed == SPEED_100)
+			an |= MVPP2_GMAC_CONFIG_MII_SPEED;
 
 		if (state->pause & MLO_PAUSE_TX)
 			ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
 		if (state->pause & MLO_PAUSE_RX)
 			ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
-	} else if (phy_interface_mode_is_rgmii(state->interface)) {
-		an |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS;
+	} else if (state->interface == PHY_INTERFACE_MODE_SGMII) {
+		/* SGMII in-band mode receives the speed and duplex from
+		 * the PHY. Flow control information is not received. */
+		an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS);
+		an |= MVPP2_GMAC_IN_BAND_AUTONEG |
+		      MVPP2_GMAC_AN_SPEED_EN |
+		      MVPP2_GMAC_AN_DUPLEX_EN;
 
-		if (state->speed == SPEED_1000)
-			an |= MVPP2_GMAC_CONFIG_GMII_SPEED;
-		else if (state->speed == SPEED_100)
-			an |= MVPP2_GMAC_CONFIG_MII_SPEED;
+		if (state->pause & MLO_PAUSE_TX)
+			ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
+		if (state->pause & MLO_PAUSE_RX)
+			ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
+	} else if (phy_interface_mode_is_8023z(state->interface)) {
+		/* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can
+		 * they negotiate duplex: they are always operating with a fixed
+		 * speed of 1000/2500Mbps in full duplex, so force 1000/2500
+		 * speed and full duplex here.
+		 */
+		ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK;
+		an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS);
+		an |= MVPP2_GMAC_IN_BAND_AUTONEG |
+		      MVPP2_GMAC_CONFIG_GMII_SPEED |
+		      MVPP2_GMAC_CONFIG_FULL_DUPLEX;
 
-		ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL;
-		ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL |
-			 MVPP22_CTRL4_SYNC_BYPASS_DIS |
-			 MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE;
+		if (state->pause & MLO_PAUSE_AN && state->an_enabled) {
+			an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG;
+		} else {
+			if (state->pause & MLO_PAUSE_TX)
+				ctrl4 |= MVPP22_CTRL4_TX_FC_EN;
+			if (state->pause & MLO_PAUSE_RX)
+				ctrl4 |= MVPP22_CTRL4_RX_FC_EN;
+		}
 	}
 
-	writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG);
-	writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
-	writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG);
-	writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+/* Some fields of the auto-negotiation register require the port to be down when
+ * their value is updated.
+ */
+#define MVPP2_GMAC_AN_PORT_DOWN_MASK	\
+		(MVPP2_GMAC_IN_BAND_AUTONEG | \
+		 MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS | \
+		 MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | \
+		 MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_CONFIG_FULL_DUPLEX | \
+		 MVPP2_GMAC_AN_DUPLEX_EN)
+
+	if ((old_ctrl0 ^ ctrl0) & MVPP2_GMAC_PORT_TYPE_MASK ||
+	    (old_ctrl2 ^ ctrl2) & MVPP2_GMAC_INBAND_AN_MASK ||
+	    (old_an ^ an) & MVPP2_GMAC_AN_PORT_DOWN_MASK) {
+		/* Force link down */
+		old_an &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+		old_an |= MVPP2_GMAC_FORCE_LINK_DOWN;
+		writel(old_an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+
+		/* Set the GMAC in a reset state - do this in a way that
+		 * ensures we clear it below.
+		 */
+		old_ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK;
+		writel(old_ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+	}
+
+	if (old_ctrl0 != ctrl0)
+		writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG);
+	if (old_ctrl2 != ctrl2)
+		writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG);
+	if (old_ctrl4 != ctrl4)
+		writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG);
+	if (old_an != an)
+		writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+
+	if (old_ctrl2 & MVPP2_GMAC_PORT_RESET_MASK) {
+		while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) &
+		       MVPP2_GMAC_PORT_RESET_MASK)
+			continue;
+	}
 }
 
 static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 			     const struct phylink_link_state *state)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	bool change_interface = port->phy_interface != state->interface;
 
 	/* Check for invalid configuration */
-	if (state->interface == PHY_INTERFACE_MODE_10GKR && port->gop_id != 0) {
+	if (mvpp2_is_xlg(state->interface) && port->gop_id != 0) {
 		netdev_err(dev, "Invalid mode on %s\n", dev->name);
 		return;
 	}
@@ -4652,8 +4749,9 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 	/* Make sure the port is disabled when reconfiguring the mode */
 	mvpp2_port_disable(port);
 
-	if (port->priv->hw_version == MVPP22 &&
-	    port->phy_interface != state->interface) {
+	if (port->priv->hw_version == MVPP22 && change_interface) {
+		mvpp22_gop_mask_irq(port);
+
 		port->phy_interface = state->interface;
 
 		/* Reconfigure the serdes lanes */
@@ -4662,17 +4760,19 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 	}
 
 	/* mac (re)configuration */
-	if (state->interface == PHY_INTERFACE_MODE_10GKR)
+	if (mvpp2_is_xlg(state->interface))
 		mvpp2_xlg_config(port, mode, state);
 	else if (phy_interface_mode_is_rgmii(state->interface) ||
-		 state->interface == PHY_INTERFACE_MODE_SGMII ||
-		 state->interface == PHY_INTERFACE_MODE_1000BASEX ||
-		 state->interface == PHY_INTERFACE_MODE_2500BASEX)
+		 phy_interface_mode_is_8023z(state->interface) ||
+		 state->interface == PHY_INTERFACE_MODE_SGMII)
 		mvpp2_gmac_config(port, mode, state);
 
 	if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK)
 		mvpp2_port_loopback_set(port, state);
 
+	if (port->priv->hw_version == MVPP22 && change_interface)
+		mvpp22_gop_unmask_irq(port);
+
 	mvpp2_port_enable(port);
 }
 
@@ -4682,13 +4782,18 @@ static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode,
 	struct mvpp2_port *port = netdev_priv(dev);
 	u32 val;
 
-	if (!phylink_autoneg_inband(mode) &&
-	    interface != PHY_INTERFACE_MODE_10GKR) {
-		val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-		val &= ~MVPP2_GMAC_FORCE_LINK_DOWN;
-		if (phy_interface_mode_is_rgmii(interface))
+	if (!phylink_autoneg_inband(mode)) {
+		if (mvpp2_is_xlg(interface)) {
+			val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+			val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_DOWN;
+			val |= MVPP22_XLG_CTRL0_FORCE_LINK_PASS;
+			writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+		} else {
+			val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+			val &= ~MVPP2_GMAC_FORCE_LINK_DOWN;
 			val |= MVPP2_GMAC_FORCE_LINK_PASS;
-		writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+			writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+		}
 	}
 
 	mvpp2_port_enable(port);
@@ -4704,25 +4809,24 @@ static void mvpp2_mac_link_down(struct net_device *dev, unsigned int mode,
 	struct mvpp2_port *port = netdev_priv(dev);
 	u32 val;
 
-	if (!phylink_autoneg_inband(mode) &&
-	    interface != PHY_INTERFACE_MODE_10GKR) {
-		val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
-		val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
-		val |= MVPP2_GMAC_FORCE_LINK_DOWN;
-		writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+	if (!phylink_autoneg_inband(mode)) {
+		if (mvpp2_is_xlg(interface)) {
+			val = readl(port->base + MVPP22_XLG_CTRL0_REG);
+			val &= ~MVPP22_XLG_CTRL0_FORCE_LINK_PASS;
+			val |= MVPP22_XLG_CTRL0_FORCE_LINK_DOWN;
+			writel(val, port->base + MVPP22_XLG_CTRL0_REG);
+		} else {
+			val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+			val &= ~MVPP2_GMAC_FORCE_LINK_PASS;
+			val |= MVPP2_GMAC_FORCE_LINK_DOWN;
+			writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG);
+		}
 	}
 
 	netif_tx_stop_all_queues(dev);
 	mvpp2_egress_disable(port);
 	mvpp2_ingress_disable(port);
 
-	/* When using link interrupts to notify phylink of a MAC state change,
-	 * we do not want the port to be disabled (we want to receive further
-	 * interrupts, to be notified when the port will have a link later).
-	 */
-	if (!port->has_phy)
-		return;
-
 	mvpp2_port_disable(port);
 }
 
@@ -4764,10 +4868,18 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	}
 
 	ntxqs = MVPP2_MAX_TXQ;
-	if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_MULTI_MODE)
-		nrxqs = MVPP2_DEFAULT_RXQ * num_possible_cpus();
-	else
-		nrxqs = MVPP2_DEFAULT_RXQ;
+	if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_SINGLE_MODE) {
+		nrxqs = 1;
+	} else {
+		/* According to the PPv2.2 datasheet and our experiments on
+		 * PPv2.1, RX queues have an allocation granularity of 4 (when
+		 * more than a single one on PPv2.2).
+		 * Round up to nearest multiple of 4.
+		 */
+		nrxqs = (num_possible_cpus() + 3) & ~0x3;
+		if (nrxqs > MVPP2_PORT_MAX_RXQ)
+			nrxqs = MVPP2_PORT_MAX_RXQ;
+	}
 
 	dev = alloc_etherdev_mqs(sizeof(*port), ntxqs, nrxqs);
 	if (!dev)
@@ -4898,7 +5010,8 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 
 	mvpp2_port_periodic_xon_disable(port);
 
-	mvpp2_port_reset(port);
+	mvpp2_mac_reset_assert(port);
+	mvpp22_pcs_reset_assert(port);
 
 	port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
 	if (!port->pcpu) {
@@ -5255,6 +5368,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (has_acpi_companion(&pdev->dev)) {
 		acpi_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
 					    &pdev->dev);
+		if (!acpi_id)
+			return -EINVAL;
 		priv->hw_version = (unsigned long)acpi_id->driver_data;
 	} else {
 		priv->hw_version =
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 12db256c8c9f..6d55e3d0b7ea 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -31,6 +31,7 @@
  * @resp:		command response
  * @link_info:		link related information
  * @event_cb:		callback for linkchange events
+ * @event_cb_lock:	lock for serializing callback with unregister
  * @cmd_pend:		flag set before new command is started
  *			flag cleared after command response is received
  * @cgx:		parent cgx port
@@ -43,6 +44,7 @@ struct lmac {
 	u64 resp;
 	struct cgx_link_user_info link_info;
 	struct cgx_event_cb event_cb;
+	spinlock_t event_cb_lock;
 	bool cmd_pend;
 	struct cgx *cgx;
 	u8 lmac_id;
@@ -55,6 +57,8 @@ struct cgx {
 	u8			cgx_id;
 	u8			lmac_count;
 	struct lmac		*lmac_idmap[MAX_LMAC_PER_CGX];
+	struct			work_struct cgx_cmd_work;
+	struct			workqueue_struct *cgx_cmd_workq;
 	struct list_head	cgx_list;
 };
 
@@ -66,6 +70,9 @@ static u32 cgx_speed_mbps[CGX_LINK_SPEED_MAX];
 /* Convert firmware lmac type encoding to string */
 static char *cgx_lmactype_string[LMAC_MODE_MAX];
 
+/* CGX PHY management internal APIs */
+static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en);
+
 /* Supported devices */
 static const struct pci_device_id cgx_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) },
@@ -92,17 +99,21 @@ static inline struct lmac *lmac_pdata(u8 lmac_id, struct cgx *cgx)
 	return cgx->lmac_idmap[lmac_id];
 }
 
-int cgx_get_cgx_cnt(void)
+int cgx_get_cgxcnt_max(void)
 {
 	struct cgx *cgx_dev;
-	int count = 0;
+	int idmax = -ENODEV;
 
 	list_for_each_entry(cgx_dev, &cgx_list, cgx_list)
-		count++;
+		if (cgx_dev->cgx_id > idmax)
+			idmax = cgx_dev->cgx_id;
+
+	if (idmax < 0)
+		return 0;
 
-	return count;
+	return idmax + 1;
 }
-EXPORT_SYMBOL(cgx_get_cgx_cnt);
+EXPORT_SYMBOL(cgx_get_cgxcnt_max);
 
 int cgx_get_lmac_cnt(void *cgxd)
 {
@@ -445,6 +456,9 @@ static inline void cgx_link_change_handler(u64 lstat,
 	lmac->link_info = event.link_uinfo;
 	linfo = &lmac->link_info;
 
+	/* Ensure callback doesn't get unregistered until we finish it */
+	spin_lock(&lmac->event_cb_lock);
+
 	if (!lmac->event_cb.notify_link_chg) {
 		dev_dbg(dev, "cgx port %d:%d Link change handler null",
 			cgx->cgx_id, lmac->lmac_id);
@@ -455,11 +469,13 @@ static inline void cgx_link_change_handler(u64 lstat,
 		dev_info(dev, "cgx port %d:%d Link is %s %d Mbps\n",
 			 cgx->cgx_id, lmac->lmac_id,
 			 linfo->link_up ? "UP" : "DOWN", linfo->speed);
-		return;
+		goto err;
 	}
 
 	if (lmac->event_cb.notify_link_chg(&event, lmac->event_cb.data))
 		dev_err(dev, "event notification failure\n");
+err:
+	spin_unlock(&lmac->event_cb_lock);
 }
 
 static inline bool cgx_cmdresp_is_linkevent(u64 event)
@@ -482,6 +498,60 @@ static inline bool cgx_event_is_linkevent(u64 event)
 		return false;
 }
 
+static inline int cgx_fwi_get_mkex_prfl_sz(u64 *prfl_sz,
+					   struct cgx *cgx)
+{
+	u64 req = 0;
+	u64 resp;
+	int err;
+
+	req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_MKEX_PRFL_SIZE, req);
+	err = cgx_fwi_cmd_generic(req, &resp, cgx, 0);
+	if (!err)
+		*prfl_sz = FIELD_GET(RESP_MKEX_PRFL_SIZE, resp);
+
+	return err;
+}
+
+static inline int cgx_fwi_get_mkex_prfl_addr(u64 *prfl_addr,
+					     struct cgx *cgx)
+{
+	u64 req = 0;
+	u64 resp;
+	int err;
+
+	req = FIELD_SET(CMDREG_ID, CGX_CMD_GET_MKEX_PRFL_ADDR, req);
+	err = cgx_fwi_cmd_generic(req, &resp, cgx, 0);
+	if (!err)
+		*prfl_addr = FIELD_GET(RESP_MKEX_PRFL_ADDR, resp);
+
+	return err;
+}
+
+int cgx_get_mkex_prfl_info(u64 *addr, u64 *size)
+{
+	struct cgx *cgx_dev;
+	int err;
+
+	if (!addr || !size)
+		return -EINVAL;
+
+	cgx_dev = list_first_entry(&cgx_list, struct cgx, cgx_list);
+	if (!cgx_dev)
+		return -ENXIO;
+
+	err = cgx_fwi_get_mkex_prfl_sz(size, cgx_dev);
+	if (err)
+		return -EIO;
+
+	err = cgx_fwi_get_mkex_prfl_addr(addr, cgx_dev);
+	if (err)
+		return -EIO;
+
+	return 0;
+}
+EXPORT_SYMBOL(cgx_get_mkex_prfl_info);
+
 static irqreturn_t cgx_fwi_event_handler(int irq, void *data)
 {
 	struct lmac *lmac = data;
@@ -548,6 +618,38 @@ int cgx_lmac_evh_register(struct cgx_event_cb *cb, void *cgxd, int lmac_id)
 }
 EXPORT_SYMBOL(cgx_lmac_evh_register);
 
+int cgx_lmac_evh_unregister(void *cgxd, int lmac_id)
+{
+	struct lmac *lmac;
+	unsigned long flags;
+	struct cgx *cgx = cgxd;
+
+	lmac = lmac_pdata(lmac_id, cgx);
+	if (!lmac)
+		return -ENODEV;
+
+	spin_lock_irqsave(&lmac->event_cb_lock, flags);
+	lmac->event_cb.notify_link_chg = NULL;
+	lmac->event_cb.data = NULL;
+	spin_unlock_irqrestore(&lmac->event_cb_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(cgx_lmac_evh_unregister);
+
+static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool enable)
+{
+	u64 req = 0;
+	u64 resp;
+
+	if (enable)
+		req = FIELD_SET(CMDREG_ID, CGX_CMD_LINK_BRING_UP, req);
+	else
+		req = FIELD_SET(CMDREG_ID, CGX_CMD_LINK_BRING_DOWN, req);
+
+	return cgx_fwi_cmd_generic(req, &resp, cgx, lmac_id);
+}
+
 static inline int cgx_fwi_read_version(u64 *resp, struct cgx *cgx)
 {
 	u64 req = 0;
@@ -581,6 +683,34 @@ static int cgx_lmac_verify_fwi_version(struct cgx *cgx)
 		return 0;
 }
 
+static void cgx_lmac_linkup_work(struct work_struct *work)
+{
+	struct cgx *cgx = container_of(work, struct cgx, cgx_cmd_work);
+	struct device *dev = &cgx->pdev->dev;
+	int i, err;
+
+	/* Do Link up for all the lmacs */
+	for (i = 0; i < cgx->lmac_count; i++) {
+		err = cgx_fwi_link_change(cgx, i, true);
+		if (err)
+			dev_info(dev, "cgx port %d:%d Link up command failed\n",
+				 cgx->cgx_id, i);
+	}
+}
+
+int cgx_lmac_linkup_start(void *cgxd)
+{
+	struct cgx *cgx = cgxd;
+
+	if (!cgx)
+		return -ENODEV;
+
+	queue_work(cgx->cgx_cmd_workq, &cgx->cgx_cmd_work);
+
+	return 0;
+}
+EXPORT_SYMBOL(cgx_lmac_linkup_start);
+
 static int cgx_lmac_init(struct cgx *cgx)
 {
 	struct lmac *lmac;
@@ -602,6 +732,7 @@ static int cgx_lmac_init(struct cgx *cgx)
 		lmac->cgx = cgx;
 		init_waitqueue_head(&lmac->wq_cmd_cmplt);
 		mutex_init(&lmac->cmd_lock);
+		spin_lock_init(&lmac->event_cb_lock);
 		err = request_irq(pci_irq_vector(cgx->pdev,
 						 CGX_LMAC_FWI + i * 9),
 				   cgx_fwi_event_handler, 0, lmac->name, lmac);
@@ -624,6 +755,12 @@ static int cgx_lmac_exit(struct cgx *cgx)
 	struct lmac *lmac;
 	int i;
 
+	if (cgx->cgx_cmd_workq) {
+		flush_workqueue(cgx->cgx_cmd_workq);
+		destroy_workqueue(cgx->cgx_cmd_workq);
+		cgx->cgx_cmd_workq = NULL;
+	}
+
 	/* Free all lmac related resources */
 	for (i = 0; i < cgx->lmac_count; i++) {
 		lmac = cgx->lmac_idmap[i];
@@ -679,8 +816,19 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	cgx->cgx_id = (pci_resource_start(pdev, PCI_CFG_REG_BAR_NUM) >> 24)
+		& CGX_ID_MASK;
+
+	/* init wq for processing linkup requests */
+	INIT_WORK(&cgx->cgx_cmd_work, cgx_lmac_linkup_work);
+	cgx->cgx_cmd_workq = alloc_workqueue("cgx_cmd_workq", 0, 0);
+	if (!cgx->cgx_cmd_workq) {
+		dev_err(dev, "alloc workqueue failed for cgx cmd");
+		err = -ENOMEM;
+		goto err_free_irq_vectors;
+	}
+
 	list_add(&cgx->cgx_list, &cgx_list);
-	cgx->cgx_id = cgx_get_cgx_cnt() - 1;
 
 	cgx_link_usertable_init();
 
@@ -693,6 +841,8 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 err_release_lmac:
 	cgx_lmac_exit(cgx);
 	list_del(&cgx->cgx_list);
+err_free_irq_vectors:
+	pci_free_irq_vectors(pdev);
 err_release_regions:
 	pci_release_regions(pdev);
 err_disable_device:
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
index 0a66d2717442..206dc5dc1df8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h
@@ -20,40 +20,41 @@
 /* PCI BAR nos */
 #define PCI_CFG_REG_BAR_NUM		0
 
-#define MAX_CGX				3
+#define CGX_ID_MASK			0x7
 #define MAX_LMAC_PER_CGX		4
+#define CGX_FIFO_LEN			65536 /* 64K for both Rx & Tx */
 #define CGX_OFFSET(x)			((x) * MAX_LMAC_PER_CGX)
 
 /* Registers */
 #define CGXX_CMRX_CFG			0x00
-#define  CMR_EN					BIT_ULL(55)
-#define  DATA_PKT_TX_EN				BIT_ULL(53)
-#define  DATA_PKT_RX_EN				BIT_ULL(54)
-#define  CGX_LMAC_TYPE_SHIFT			40
-#define  CGX_LMAC_TYPE_MASK			0xF
+#define CMR_EN				BIT_ULL(55)
+#define DATA_PKT_TX_EN			BIT_ULL(53)
+#define DATA_PKT_RX_EN			BIT_ULL(54)
+#define CGX_LMAC_TYPE_SHIFT		40
+#define CGX_LMAC_TYPE_MASK		0xF
 #define CGXX_CMRX_INT			0x040
-#define  FW_CGX_INT				BIT_ULL(1)
+#define FW_CGX_INT			BIT_ULL(1)
 #define CGXX_CMRX_INT_ENA_W1S		0x058
 #define CGXX_CMRX_RX_ID_MAP		0x060
 #define CGXX_CMRX_RX_STAT0		0x070
 #define CGXX_CMRX_RX_LMACS		0x128
 #define CGXX_CMRX_RX_DMAC_CTL0		0x1F8
-#define  CGX_DMAC_CTL0_CAM_ENABLE		BIT_ULL(3)
-#define  CGX_DMAC_CAM_ACCEPT			BIT_ULL(3)
-#define  CGX_DMAC_MCAST_MODE			BIT_ULL(1)
-#define  CGX_DMAC_BCAST_MODE			BIT_ULL(0)
+#define CGX_DMAC_CTL0_CAM_ENABLE	BIT_ULL(3)
+#define CGX_DMAC_CAM_ACCEPT		BIT_ULL(3)
+#define CGX_DMAC_MCAST_MODE		BIT_ULL(1)
+#define CGX_DMAC_BCAST_MODE		BIT_ULL(0)
 #define CGXX_CMRX_RX_DMAC_CAM0		0x200
-#define  CGX_DMAC_CAM_ADDR_ENABLE		BIT_ULL(48)
+#define CGX_DMAC_CAM_ADDR_ENABLE	BIT_ULL(48)
 #define CGXX_CMRX_RX_DMAC_CAM1		0x400
-#define CGX_RX_DMAC_ADR_MASK			GENMASK_ULL(47, 0)
+#define CGX_RX_DMAC_ADR_MASK		GENMASK_ULL(47, 0)
 #define CGXX_CMRX_TX_STAT0		0x700
 #define CGXX_SCRATCH0_REG		0x1050
 #define CGXX_SCRATCH1_REG		0x1058
 #define CGX_CONST			0x2000
 #define CGXX_SPUX_CONTROL1		0x10000
-#define  CGXX_SPUX_CONTROL1_LBK			BIT_ULL(14)
+#define CGXX_SPUX_CONTROL1_LBK		BIT_ULL(14)
 #define CGXX_GMP_PCS_MRX_CTL		0x30000
-#define  CGXX_GMP_PCS_MRX_CTL_LBK		BIT_ULL(14)
+#define CGXX_GMP_PCS_MRX_CTL_LBK	BIT_ULL(14)
 
 #define CGX_COMMAND_REG			CGXX_SCRATCH1_REG
 #define CGX_EVENT_REG			CGXX_SCRATCH0_REG
@@ -94,11 +95,12 @@ struct cgx_event_cb {
 
 extern struct pci_driver cgx_driver;
 
-int cgx_get_cgx_cnt(void);
+int cgx_get_cgxcnt_max(void);
 int cgx_get_lmac_cnt(void *cgxd);
 void *cgx_get_pdata(int cgx_id);
 int cgx_set_pkind(void *cgxd, u8 lmac_id, int pkind);
 int cgx_lmac_evh_register(struct cgx_event_cb *cb, void *cgxd, int lmac_id);
+int cgx_lmac_evh_unregister(void *cgxd, int lmac_id);
 int cgx_get_tx_stats(void *cgxd, int lmac_id, int idx, u64 *tx_stat);
 int cgx_get_rx_stats(void *cgxd, int lmac_id, int idx, u64 *rx_stat);
 int cgx_lmac_rx_tx_enable(void *cgxd, int lmac_id, bool enable);
@@ -108,4 +110,6 @@ void cgx_lmac_promisc_config(int cgx_id, int lmac_id, bool enable);
 int cgx_lmac_internal_loopback(void *cgxd, int lmac_id, bool enable);
 int cgx_get_link_info(void *cgxd, int lmac_id,
 		      struct cgx_link_user_info *linfo);
+int cgx_lmac_linkup_start(void *cgxd);
+int cgx_get_mkex_prfl_info(u64 *addr, u64 *size);
 #endif /* CGX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
index fa17af3f4ba7..fb3ba4968a9b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx_fw_if.h
@@ -78,8 +78,8 @@ enum cgx_cmd_id {
 	CGX_CMD_LINK_STATE_CHANGE,
 	CGX_CMD_MODE_CHANGE,		/* hot plug support */
 	CGX_CMD_INTF_SHUTDOWN,
-	CGX_CMD_IRQ_ENABLE,
-	CGX_CMD_IRQ_DISABLE,
+	CGX_CMD_GET_MKEX_PRFL_SIZE,
+	CGX_CMD_GET_MKEX_PRFL_ADDR
 };
 
 /* async event ids */
@@ -139,6 +139,16 @@ enum cgx_cmd_own {
  */
 #define RESP_MAC_ADDR		GENMASK_ULL(56, 9)
 
+/* Response to cmd ID as CGX_CMD_GET_MKEX_PRFL_SIZE with cmd status as
+ * CGX_STAT_SUCCESS
+ */
+#define RESP_MKEX_PRFL_SIZE		GENMASK_ULL(63, 9)
+
+/* Response to cmd ID as CGX_CMD_GET_MKEX_PRFL_ADDR with cmd status as
+ * CGX_STAT_SUCCESS
+ */
+#define RESP_MKEX_PRFL_ADDR		GENMASK_ULL(63, 9)
+
 /* Response to cmd ID - CGX_CMD_LINK_BRING_UP/DOWN, event ID CGX_EVT_LINK_CHANGE
  * status can be either CGX_STAT_FAIL or CGX_STAT_SUCCESS
  *
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h
index d39ada404c8f..e332e82fc066 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h
@@ -64,7 +64,7 @@ static inline int qmem_alloc(struct device *dev, struct qmem **q,
 
 	qmem->entry_sz = entry_sz;
 	qmem->alloc_sz = (qsize * entry_sz) + OTX2_ALIGN;
-	qmem->base = dma_zalloc_coherent(dev, qmem->alloc_sz,
+	qmem->base = dma_alloc_coherent(dev, qmem->alloc_sz,
 					 &qmem->iova, GFP_KERNEL);
 	if (!qmem->base)
 		return -ENOMEM;
@@ -143,6 +143,14 @@ enum nix_scheduler {
 	NIX_TXSCH_LVL_CNT = 0x5,
 };
 
+#define TXSCH_TL1_DFLT_RR_QTM      ((1 << 24) - 1)
+#define TXSCH_TL1_DFLT_RR_PRIO     (0x1ull)
+
+/* Min/Max packet sizes, excluding FCS */
+#define	NIC_HW_MIN_FRS			40
+#define	NIC_HW_MAX_FRS			9212
+#define	SDP_HW_MAX_FRS			65535
+
 /* NIX RX action operation*/
 #define NIX_RX_ACTIONOP_DROP		(0x0ull)
 #define NIX_RX_ACTIONOP_UCAST		(0x1ull)
@@ -169,7 +177,9 @@ enum nix_scheduler {
 
 #define MAX_LMAC_PKIND			12
 #define NIX_LINK_CGX_LMAC(a, b)		(0 + 4 * (a) + (b))
+#define NIX_LINK_LBK(a)			(12 + (a))
 #define NIX_CHAN_CGX_LMAC_CHX(a, b, c)	(0x800 + 0x100 * (a) + 0x10 * (b) + (c))
+#define NIX_CHAN_LBK_CHX(a, b)		(0 + 0x100 * (a) + (b))
 
 /* NIX LSO format indices.
  * As of now TSO is the only one using, so statically assigning indices.
@@ -186,26 +196,4 @@ enum nix_scheduler {
 #define DEFAULT_RSS_CONTEXT_GROUP	0
 #define MAX_RSS_INDIR_TBL_SIZE		256 /* 1 << Max adder bits */
 
-/* NIX flow tag, key type flags */
-#define FLOW_KEY_TYPE_PORT	BIT(0)
-#define FLOW_KEY_TYPE_IPV4	BIT(1)
-#define FLOW_KEY_TYPE_IPV6	BIT(2)
-#define FLOW_KEY_TYPE_TCP	BIT(3)
-#define FLOW_KEY_TYPE_UDP	BIT(4)
-#define FLOW_KEY_TYPE_SCTP	BIT(5)
-
-/* NIX flow tag algorithm indices, max is 31 */
-enum {
-	FLOW_KEY_ALG_PORT,
-	FLOW_KEY_ALG_IP,
-	FLOW_KEY_ALG_TCP,
-	FLOW_KEY_ALG_UDP,
-	FLOW_KEY_ALG_SCTP,
-	FLOW_KEY_ALG_TCP_UDP,
-	FLOW_KEY_ALG_TCP_SCTP,
-	FLOW_KEY_ALG_UDP_SCTP,
-	FLOW_KEY_ALG_TCP_UDP_SCTP,
-	FLOW_KEY_ALG_MAX,
-};
-
 #endif /* COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
index 85ba24a05774..d6f9ed8ea966 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.c
@@ -290,7 +290,7 @@ EXPORT_SYMBOL(otx2_mbox_nonempty);
 const char *otx2_mbox_id2name(u16 id)
 {
 	switch (id) {
-#define M(_name, _id, _1, _2) case _id: return # _name;
+#define M(_name, _id, _1, _2, _3) case _id: return # _name;
 	MBOX_MESSAGES
 #undef M
 	default:
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
index a15a59c9a239..76a4575d18ff 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h
@@ -120,54 +120,101 @@ static inline struct mbox_msghdr *otx2_mbox_alloc_msg(struct otx2_mbox *mbox,
 
 #define MBOX_MESSAGES							\
 /* Generic mbox IDs (range 0x000 - 0x1FF) */				\
-M(READY,		0x001, msg_req, ready_msg_rsp)			\
-M(ATTACH_RESOURCES,	0x002, rsrc_attach, msg_rsp)			\
-M(DETACH_RESOURCES,	0x003, rsrc_detach, msg_rsp)			\
-M(MSIX_OFFSET,		0x004, msg_req, msix_offset_rsp)		\
+M(READY,		0x001, ready, msg_req, ready_msg_rsp)		\
+M(ATTACH_RESOURCES,	0x002, attach_resources, rsrc_attach, msg_rsp)	\
+M(DETACH_RESOURCES,	0x003, detach_resources, rsrc_detach, msg_rsp)	\
+M(MSIX_OFFSET,		0x004, msix_offset, msg_req, msix_offset_rsp)	\
+M(VF_FLR,		0x006, vf_flr, msg_req, msg_rsp)		\
 /* CGX mbox IDs (range 0x200 - 0x3FF) */				\
-M(CGX_START_RXTX,	0x200, msg_req, msg_rsp)			\
-M(CGX_STOP_RXTX,	0x201, msg_req, msg_rsp)			\
-M(CGX_STATS,		0x202, msg_req, cgx_stats_rsp)			\
-M(CGX_MAC_ADDR_SET,	0x203, cgx_mac_addr_set_or_get,			\
+M(CGX_START_RXTX,	0x200, cgx_start_rxtx, msg_req, msg_rsp)	\
+M(CGX_STOP_RXTX,	0x201, cgx_stop_rxtx, msg_req, msg_rsp)		\
+M(CGX_STATS,		0x202, cgx_stats, msg_req, cgx_stats_rsp)	\
+M(CGX_MAC_ADDR_SET,	0x203, cgx_mac_addr_set, cgx_mac_addr_set_or_get,    \
 				cgx_mac_addr_set_or_get)		\
-M(CGX_MAC_ADDR_GET,	0x204, cgx_mac_addr_set_or_get,			\
+M(CGX_MAC_ADDR_GET,	0x204, cgx_mac_addr_get, cgx_mac_addr_set_or_get,    \
 				cgx_mac_addr_set_or_get)		\
-M(CGX_PROMISC_ENABLE,	0x205, msg_req, msg_rsp)			\
-M(CGX_PROMISC_DISABLE,	0x206, msg_req, msg_rsp)			\
-M(CGX_START_LINKEVENTS, 0x207, msg_req, msg_rsp)			\
-M(CGX_STOP_LINKEVENTS,	0x208, msg_req, msg_rsp)			\
-M(CGX_GET_LINKINFO,	0x209, msg_req, cgx_link_info_msg)		\
-M(CGX_INTLBK_ENABLE,	0x20A, msg_req, msg_rsp)			\
-M(CGX_INTLBK_DISABLE,	0x20B, msg_req, msg_rsp)			\
+M(CGX_PROMISC_ENABLE,	0x205, cgx_promisc_enable, msg_req, msg_rsp)	\
+M(CGX_PROMISC_DISABLE,	0x206, cgx_promisc_disable, msg_req, msg_rsp)	\
+M(CGX_START_LINKEVENTS, 0x207, cgx_start_linkevents, msg_req, msg_rsp)	\
+M(CGX_STOP_LINKEVENTS,	0x208, cgx_stop_linkevents, msg_req, msg_rsp)	\
+M(CGX_GET_LINKINFO,	0x209, cgx_get_linkinfo, msg_req, cgx_link_info_msg) \
+M(CGX_INTLBK_ENABLE,	0x20A, cgx_intlbk_enable, msg_req, msg_rsp)	\
+M(CGX_INTLBK_DISABLE,	0x20B, cgx_intlbk_disable, msg_req, msg_rsp)	\
 /* NPA mbox IDs (range 0x400 - 0x5FF) */				\
-M(NPA_LF_ALLOC,		0x400, npa_lf_alloc_req, npa_lf_alloc_rsp)	\
-M(NPA_LF_FREE,		0x401, msg_req, msg_rsp)			\
-M(NPA_AQ_ENQ,		0x402, npa_aq_enq_req, npa_aq_enq_rsp)		\
-M(NPA_HWCTX_DISABLE,	0x403, hwctx_disable_req, msg_rsp)		\
+M(NPA_LF_ALLOC,		0x400, npa_lf_alloc,				\
+				npa_lf_alloc_req, npa_lf_alloc_rsp)	\
+M(NPA_LF_FREE,		0x401, npa_lf_free, msg_req, msg_rsp)		\
+M(NPA_AQ_ENQ,		0x402, npa_aq_enq, npa_aq_enq_req, npa_aq_enq_rsp)   \
+M(NPA_HWCTX_DISABLE,	0x403, npa_hwctx_disable, hwctx_disable_req, msg_rsp)\
 /* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */				\
 /* TIM mbox IDs (range 0x800 - 0x9FF) */				\
 /* CPT mbox IDs (range 0xA00 - 0xBFF) */				\
 /* NPC mbox IDs (range 0x6000 - 0x7FFF) */				\
+M(NPC_MCAM_ALLOC_ENTRY,	0x6000, npc_mcam_alloc_entry, npc_mcam_alloc_entry_req,\
+				npc_mcam_alloc_entry_rsp)		\
+M(NPC_MCAM_FREE_ENTRY,	0x6001, npc_mcam_free_entry,			\
+				 npc_mcam_free_entry_req, msg_rsp)	\
+M(NPC_MCAM_WRITE_ENTRY,	0x6002, npc_mcam_write_entry,			\
+				 npc_mcam_write_entry_req, msg_rsp)	\
+M(NPC_MCAM_ENA_ENTRY,   0x6003, npc_mcam_ena_entry,			\
+				 npc_mcam_ena_dis_entry_req, msg_rsp)	\
+M(NPC_MCAM_DIS_ENTRY,   0x6004, npc_mcam_dis_entry,			\
+				 npc_mcam_ena_dis_entry_req, msg_rsp)	\
+M(NPC_MCAM_SHIFT_ENTRY, 0x6005, npc_mcam_shift_entry, npc_mcam_shift_entry_req,\
+				npc_mcam_shift_entry_rsp)		\
+M(NPC_MCAM_ALLOC_COUNTER, 0x6006, npc_mcam_alloc_counter,		\
+					npc_mcam_alloc_counter_req,	\
+					npc_mcam_alloc_counter_rsp)	\
+M(NPC_MCAM_FREE_COUNTER,  0x6007, npc_mcam_free_counter,		\
+				    npc_mcam_oper_counter_req, msg_rsp)	\
+M(NPC_MCAM_UNMAP_COUNTER, 0x6008, npc_mcam_unmap_counter,		\
+				   npc_mcam_unmap_counter_req, msg_rsp)	\
+M(NPC_MCAM_CLEAR_COUNTER, 0x6009, npc_mcam_clear_counter,		\
+				   npc_mcam_oper_counter_req, msg_rsp)	\
+M(NPC_MCAM_COUNTER_STATS, 0x600a, npc_mcam_counter_stats,		\
+				   npc_mcam_oper_counter_req,		\
+				   npc_mcam_oper_counter_rsp)		\
+M(NPC_MCAM_ALLOC_AND_WRITE_ENTRY, 0x600b, npc_mcam_alloc_and_write_entry,      \
+					  npc_mcam_alloc_and_write_entry_req,  \
+					  npc_mcam_alloc_and_write_entry_rsp)  \
+M(NPC_GET_KEX_CFG,	  0x600c, npc_get_kex_cfg,			\
+				   msg_req, npc_get_kex_cfg_rsp)	\
 /* NIX mbox IDs (range 0x8000 - 0xFFFF) */				\
-M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc_req, nix_lf_alloc_rsp)	\
-M(NIX_LF_FREE,		0x8001, msg_req, msg_rsp)			\
-M(NIX_AQ_ENQ,		0x8002, nix_aq_enq_req, nix_aq_enq_rsp)		\
-M(NIX_HWCTX_DISABLE,	0x8003, hwctx_disable_req, msg_rsp)		\
-M(NIX_TXSCH_ALLOC,	0x8004, nix_txsch_alloc_req, nix_txsch_alloc_rsp) \
-M(NIX_TXSCH_FREE,	0x8005, nix_txsch_free_req, msg_rsp)		\
-M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_config, msg_rsp)		\
-M(NIX_STATS_RST,	0x8007, msg_req, msg_rsp)			\
-M(NIX_VTAG_CFG,	0x8008, nix_vtag_config, msg_rsp)		\
-M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg, msg_rsp)		\
-M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, msg_rsp)		\
-M(NIX_SET_RX_MODE,	0x800b, nix_rx_mode, msg_rsp)
+M(NIX_LF_ALLOC,		0x8000, nix_lf_alloc,				\
+				 nix_lf_alloc_req, nix_lf_alloc_rsp)	\
+M(NIX_LF_FREE,		0x8001, nix_lf_free, msg_req, msg_rsp)		\
+M(NIX_AQ_ENQ,		0x8002, nix_aq_enq, nix_aq_enq_req, nix_aq_enq_rsp)  \
+M(NIX_HWCTX_DISABLE,	0x8003, nix_hwctx_disable,			\
+				 hwctx_disable_req, msg_rsp)		\
+M(NIX_TXSCH_ALLOC,	0x8004, nix_txsch_alloc,			\
+				 nix_txsch_alloc_req, nix_txsch_alloc_rsp)   \
+M(NIX_TXSCH_FREE,	0x8005, nix_txsch_free, nix_txsch_free_req, msg_rsp) \
+M(NIX_TXSCHQ_CFG,	0x8006, nix_txschq_cfg, nix_txschq_config, msg_rsp)  \
+M(NIX_STATS_RST,	0x8007, nix_stats_rst, msg_req, msg_rsp)	\
+M(NIX_VTAG_CFG,		0x8008, nix_vtag_cfg, nix_vtag_config, msg_rsp)	\
+M(NIX_RSS_FLOWKEY_CFG,  0x8009, nix_rss_flowkey_cfg,			\
+				 nix_rss_flowkey_cfg,			\
+				 nix_rss_flowkey_cfg_rsp)		\
+M(NIX_SET_MAC_ADDR,	0x800a, nix_set_mac_addr, nix_set_mac_addr, msg_rsp) \
+M(NIX_SET_RX_MODE,	0x800b, nix_set_rx_mode, nix_rx_mode, msg_rsp)	\
+M(NIX_SET_HW_FRS,	0x800c, nix_set_hw_frs, nix_frs_cfg, msg_rsp)	\
+M(NIX_LF_START_RX,	0x800d, nix_lf_start_rx, msg_req, msg_rsp)	\
+M(NIX_LF_STOP_RX,	0x800e, nix_lf_stop_rx, msg_req, msg_rsp)	\
+M(NIX_MARK_FORMAT_CFG,	0x800f, nix_mark_format_cfg,			\
+				 nix_mark_format_cfg,			\
+				 nix_mark_format_cfg_rsp)		\
+M(NIX_SET_RX_CFG,	0x8010, nix_set_rx_cfg, nix_rx_cfg, msg_rsp)	\
+M(NIX_LSO_FORMAT_CFG,	0x8011, nix_lso_format_cfg,			\
+				 nix_lso_format_cfg,			\
+				 nix_lso_format_cfg_rsp)		\
+M(NIX_RXVLAN_ALLOC,	0x8012, nix_rxvlan_alloc, msg_req, msg_rsp)
 
 /* Messages initiated by AF (range 0xC00 - 0xDFF) */
 #define MBOX_UP_CGX_MESSAGES						\
-M(CGX_LINK_EVENT,		0xC00, cgx_link_info_msg, msg_rsp)
+M(CGX_LINK_EVENT,	0xC00, cgx_link_event, cgx_link_info_msg, msg_rsp)
 
 enum {
-#define M(_name, _id, _1, _2) MBOX_MSG_ ## _name = _id,
+#define M(_name, _id, _1, _2, _3) MBOX_MSG_ ## _name = _id,
 MBOX_MESSAGES
 MBOX_UP_CGX_MESSAGES
 #undef M
@@ -191,6 +238,13 @@ struct msg_rsp {
 	struct mbox_msghdr hdr;
 };
 
+/* RVU mailbox error codes
+ * Range 256 - 300.
+ */
+enum rvu_af_status {
+	RVU_INVALID_VF_ID           = -256,
+};
+
 struct ready_msg_rsp {
 	struct mbox_msghdr hdr;
 	u16    sclk_feq;	/* SCLK frequency */
@@ -347,6 +401,8 @@ struct hwctx_disable_req {
 	u8 ctype;
 };
 
+/* NIX mbox message formats */
+
 /* NIX mailbox error codes
  * Range 401 - 500.
  */
@@ -365,6 +421,12 @@ enum nix_af_status {
 	NIX_AF_INVAL_TXSCHQ_CFG     = -412,
 	NIX_AF_SMQ_FLUSH_FAILED     = -413,
 	NIX_AF_ERR_LF_RESET         = -414,
+	NIX_AF_ERR_RSS_NOSPC_FIELD  = -415,
+	NIX_AF_ERR_RSS_NOSPC_ALGO   = -416,
+	NIX_AF_ERR_MARK_CFG_FAIL    = -417,
+	NIX_AF_ERR_LSO_CFG_FAIL     = -418,
+	NIX_AF_INVAL_NPA_PF_FUNC    = -419,
+	NIX_AF_INVAL_SSO_PF_FUNC    = -420,
 };
 
 /* For NIX LF context alloc and init */
@@ -392,6 +454,10 @@ struct nix_lf_alloc_rsp {
 	u8	lso_tsov4_idx;
 	u8	lso_tsov6_idx;
 	u8      mac_addr[ETH_ALEN];
+	u8	lf_rx_stats; /* NIX_AF_CONST1::LF_RX_STATS */
+	u8	lf_tx_stats; /* NIX_AF_CONST1::LF_TX_STATS */
+	u16	cints; /* NIX_AF_CONST2::CINTS */
+	u16	qints; /* NIX_AF_CONST2::QINTS */
 };
 
 /* NIX AQ enqueue msg */
@@ -472,6 +538,7 @@ struct nix_txschq_config {
 
 struct nix_vtag_config {
 	struct mbox_msghdr hdr;
+	/* '0' for 4 octet VTAG, '1' for 8 octet VTAG */
 	u8 vtag_size;
 	/* cfg_type is '0' for tx vlan cfg
 	 * cfg_type is '1' for rx vlan cfg
@@ -492,7 +559,7 @@ struct nix_vtag_config {
 
 		/* valid when cfg_type is '1' */
 		struct {
-			/* rx vtag type index */
+			/* rx vtag type index, valid values are in 0..7 range */
 			u8 vtag_type;
 			/* rx vtag strip */
 			u8 strip_vtag :1;
@@ -505,15 +572,40 @@ struct nix_vtag_config {
 struct nix_rss_flowkey_cfg {
 	struct mbox_msghdr hdr;
 	int	mcam_index;  /* MCAM entry index to modify */
+#define NIX_FLOW_KEY_TYPE_PORT	BIT(0)
+#define NIX_FLOW_KEY_TYPE_IPV4	BIT(1)
+#define NIX_FLOW_KEY_TYPE_IPV6	BIT(2)
+#define NIX_FLOW_KEY_TYPE_TCP	BIT(3)
+#define NIX_FLOW_KEY_TYPE_UDP	BIT(4)
+#define NIX_FLOW_KEY_TYPE_SCTP	BIT(5)
 	u32	flowkey_cfg; /* Flowkey types selected */
 	u8	group;       /* RSS context or group */
 };
 
+struct nix_rss_flowkey_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u8	alg_idx; /* Selected algo index */
+};
+
 struct nix_set_mac_addr {
 	struct mbox_msghdr hdr;
 	u8 mac_addr[ETH_ALEN]; /* MAC address to be set for this pcifunc */
 };
 
+struct nix_mark_format_cfg {
+	struct mbox_msghdr hdr;
+	u8 offset;
+	u8 y_mask;
+	u8 y_val;
+	u8 r_mask;
+	u8 r_val;
+};
+
+struct nix_mark_format_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u8 mark_format_idx;
+};
+
 struct nix_rx_mode {
 	struct mbox_msghdr hdr;
 #define NIX_RX_MODE_UCAST	BIT(0)
@@ -522,4 +614,182 @@ struct nix_rx_mode {
 	u16	mode;
 };
 
+struct nix_rx_cfg {
+	struct mbox_msghdr hdr;
+#define NIX_RX_OL3_VERIFY   BIT(0)
+#define NIX_RX_OL4_VERIFY   BIT(1)
+	u8 len_verify; /* Outer L3/L4 len check */
+#define NIX_RX_CSUM_OL4_VERIFY  BIT(0)
+	u8 csum_verify; /* Outer L4 checksum verification */
+};
+
+struct nix_frs_cfg {
+	struct mbox_msghdr hdr;
+	u8	update_smq;    /* Update SMQ's min/max lens */
+	u8	update_minlen; /* Set minlen also */
+	u8	sdp_link;      /* Set SDP RX link */
+	u16	maxlen;
+	u16	minlen;
+};
+
+struct nix_lso_format_cfg {
+	struct mbox_msghdr hdr;
+	u64 field_mask;
+#define NIX_LSO_FIELD_MAX	8
+	u64 fields[NIX_LSO_FIELD_MAX];
+};
+
+struct nix_lso_format_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u8 lso_format_idx;
+};
+
+/* NPC mbox message structs */
+
+#define NPC_MCAM_ENTRY_INVALID	0xFFFF
+#define NPC_MCAM_INVALID_MAP	0xFFFF
+
+/* NPC mailbox error codes
+ * Range 701 - 800.
+ */
+enum npc_af_status {
+	NPC_MCAM_INVALID_REQ	= -701,
+	NPC_MCAM_ALLOC_DENIED	= -702,
+	NPC_MCAM_ALLOC_FAILED	= -703,
+	NPC_MCAM_PERM_DENIED	= -704,
+};
+
+struct npc_mcam_alloc_entry_req {
+	struct mbox_msghdr hdr;
+#define NPC_MAX_NONCONTIG_ENTRIES	256
+	u8  contig;   /* Contiguous entries ? */
+#define NPC_MCAM_ANY_PRIO		0
+#define NPC_MCAM_LOWER_PRIO		1
+#define NPC_MCAM_HIGHER_PRIO		2
+	u8  priority; /* Lower or higher w.r.t ref_entry */
+	u16 ref_entry;
+	u16 count;    /* Number of entries requested */
+};
+
+struct npc_mcam_alloc_entry_rsp {
+	struct mbox_msghdr hdr;
+	u16 entry; /* Entry allocated or start index if contiguous.
+		    * Invalid incase of non-contiguous.
+		    */
+	u16 count; /* Number of entries allocated */
+	u16 free_count; /* Number of entries available */
+	u16 entry_list[NPC_MAX_NONCONTIG_ENTRIES];
+};
+
+struct npc_mcam_free_entry_req {
+	struct mbox_msghdr hdr;
+	u16 entry; /* Entry index to be freed */
+	u8  all;   /* If all entries allocated to this PFVF to be freed */
+};
+
+struct mcam_entry {
+#define NPC_MAX_KWS_IN_KEY	7 /* Number of keywords in max keywidth */
+	u64	kw[NPC_MAX_KWS_IN_KEY];
+	u64	kw_mask[NPC_MAX_KWS_IN_KEY];
+	u64	action;
+	u64	vtag_action;
+};
+
+struct npc_mcam_write_entry_req {
+	struct mbox_msghdr hdr;
+	struct mcam_entry entry_data;
+	u16 entry;	 /* MCAM entry to write this match key */
+	u16 cntr;	 /* Counter for this MCAM entry */
+	u8  intf;	 /* Rx or Tx interface */
+	u8  enable_entry;/* Enable this MCAM entry ? */
+	u8  set_cntr;    /* Set counter for this entry ? */
+};
+
+/* Enable/Disable a given entry */
+struct npc_mcam_ena_dis_entry_req {
+	struct mbox_msghdr hdr;
+	u16 entry;
+};
+
+struct npc_mcam_shift_entry_req {
+	struct mbox_msghdr hdr;
+#define NPC_MCAM_MAX_SHIFTS	64
+	u16 curr_entry[NPC_MCAM_MAX_SHIFTS];
+	u16 new_entry[NPC_MCAM_MAX_SHIFTS];
+	u16 shift_count; /* Number of entries to shift */
+};
+
+struct npc_mcam_shift_entry_rsp {
+	struct mbox_msghdr hdr;
+	u16 failed_entry_idx; /* Index in 'curr_entry', not entry itself */
+};
+
+struct npc_mcam_alloc_counter_req {
+	struct mbox_msghdr hdr;
+	u8  contig;	/* Contiguous counters ? */
+#define NPC_MAX_NONCONTIG_COUNTERS       64
+	u16 count;	/* Number of counters requested */
+};
+
+struct npc_mcam_alloc_counter_rsp {
+	struct mbox_msghdr hdr;
+	u16 cntr;   /* Counter allocated or start index if contiguous.
+		     * Invalid incase of non-contiguous.
+		     */
+	u16 count;  /* Number of counters allocated */
+	u16 cntr_list[NPC_MAX_NONCONTIG_COUNTERS];
+};
+
+struct npc_mcam_oper_counter_req {
+	struct mbox_msghdr hdr;
+	u16 cntr;   /* Free a counter or clear/fetch it's stats */
+};
+
+struct npc_mcam_oper_counter_rsp {
+	struct mbox_msghdr hdr;
+	u64 stat;  /* valid only while fetching counter's stats */
+};
+
+struct npc_mcam_unmap_counter_req {
+	struct mbox_msghdr hdr;
+	u16 cntr;
+	u16 entry; /* Entry and counter to be unmapped */
+	u8  all;   /* Unmap all entries using this counter ? */
+};
+
+struct npc_mcam_alloc_and_write_entry_req {
+	struct mbox_msghdr hdr;
+	struct mcam_entry entry_data;
+	u16 ref_entry;
+	u8  priority;    /* Lower or higher w.r.t ref_entry */
+	u8  intf;	 /* Rx or Tx interface */
+	u8  enable_entry;/* Enable this MCAM entry ? */
+	u8  alloc_cntr;  /* Allocate counter and map ? */
+};
+
+struct npc_mcam_alloc_and_write_entry_rsp {
+	struct mbox_msghdr hdr;
+	u16 entry;
+	u16 cntr;
+};
+
+struct npc_get_kex_cfg_rsp {
+	struct mbox_msghdr hdr;
+	u64 rx_keyx_cfg;   /* NPC_AF_INTF(0)_KEX_CFG */
+	u64 tx_keyx_cfg;   /* NPC_AF_INTF(1)_KEX_CFG */
+#define NPC_MAX_INTF	2
+#define NPC_MAX_LID	8
+#define NPC_MAX_LT	16
+#define NPC_MAX_LD	2
+#define NPC_MAX_LFL	16
+	/* NPC_AF_KEX_LDATA(0..1)_FLAGS_CFG */
+	u64 kex_ld_flags[NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LID(0..7)_LT(0..15)_LD(0..1)_CFG */
+	u64 intf_lid_lt_ld[NPC_MAX_INTF][NPC_MAX_LID][NPC_MAX_LT][NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LDATA(0..1)_FLAGS(0..15)_CFG */
+	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
+#define MKEX_NAME_LEN 128
+	u8 mkex_pfl_name[MKEX_NAME_LEN];
+};
+
 #endif /* MBOX_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
index f98b0113def3..8d6d90fdfb73 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h
@@ -259,4 +259,28 @@ struct nix_rx_action {
 #endif
 };
 
+/* NIX Receive Vtag Action Structure */
+#define VTAG0_VALID_BIT		BIT_ULL(15)
+#define VTAG0_TYPE_MASK		GENMASK_ULL(14, 12)
+#define VTAG0_LID_MASK		GENMASK_ULL(10, 8)
+#define VTAG0_RELPTR_MASK	GENMASK_ULL(7, 0)
+
+struct npc_mcam_kex {
+	/* MKEX Profle Header */
+	u64 mkex_sign; /* "mcam-kex-profile" (8 bytes/ASCII characters) */
+	u8 name[MKEX_NAME_LEN];   /* MKEX Profile name */
+	u64 cpu_model;   /* Format as profiled by CPU hardware */
+	u64 kpu_version; /* KPU firmware/profile version */
+	u64 reserved; /* Reserved for extension */
+
+	/* MKEX Profle Data */
+	u64 keyx_cfg[NPC_MAX_INTF]; /* NPC_AF_INTF(0..1)_KEX_CFG */
+	/* NPC_AF_KEX_LDATA(0..1)_FLAGS_CFG */
+	u64 kex_ld_flags[NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LID(0..7)_LT(0..15)_LD(0..1)_CFG */
+	u64 intf_lid_lt_ld[NPC_MAX_INTF][NPC_MAX_LID][NPC_MAX_LT][NPC_MAX_LD];
+	/* NPC_AF_INTF(0..1)_LDATA(0..1)_FLAGS(0..15)_CFG */
+	u64 intf_ld_flags[NPC_MAX_INTF][NPC_MAX_LD][NPC_MAX_LFL];
+} __packed;
+
 #endif /* NPC_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index dc28fa2b9481..e581091c09c4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -29,6 +29,16 @@ static void rvu_set_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				struct rvu_block *block, int lf);
 static void rvu_clear_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 				  struct rvu_block *block, int lf);
+static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc);
+
+static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
+			 int type, int num,
+			 void (mbox_handler)(struct work_struct *),
+			 void (mbox_up_handler)(struct work_struct *));
+enum {
+	TYPE_AFVF,
+	TYPE_AFPF,
+};
 
 /* Supported devices */
 static const struct pci_device_id rvu_id_table[] = {
@@ -42,6 +52,10 @@ MODULE_LICENSE("GPL v2");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, rvu_id_table);
 
+static char *mkex_profile; /* MKEX profile name */
+module_param(mkex_profile, charp, 0000);
+MODULE_PARM_DESC(mkex_profile, "MKEX profile name string");
+
 /* Poll a RVU block's register 'offset', for a 'zero'
  * or 'nonzero' at bits specified by 'mask'
  */
@@ -153,17 +167,17 @@ int rvu_get_lf(struct rvu *rvu, struct rvu_block *block, u16 pcifunc, u16 slot)
 	u16 match = 0;
 	int lf;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (lf = 0; lf < block->lf.max; lf++) {
 		if (block->fn_map[lf] == pcifunc) {
 			if (slot == match) {
-				spin_unlock(&rvu->rsrc_lock);
+				mutex_unlock(&rvu->rsrc_lock);
 				return lf;
 			}
 			match++;
 		}
 	}
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return -ENODEV;
 }
 
@@ -337,6 +351,28 @@ struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc)
 		return &rvu->pf[rvu_get_pf(pcifunc)];
 }
 
+static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc)
+{
+	int pf, vf, nvfs;
+	u64 cfg;
+
+	pf = rvu_get_pf(pcifunc);
+	if (pf >= rvu->hw->total_pfs)
+		return false;
+
+	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
+		return true;
+
+	/* Check if VF is within number of VFs attached to this PF */
+	vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1;
+	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
+	nvfs = (cfg >> 12) & 0xFF;
+	if (vf >= nvfs)
+		return false;
+
+	return true;
+}
+
 bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr)
 {
 	struct rvu_block *block;
@@ -597,6 +633,8 @@ static void rvu_free_hw_resources(struct rvu *rvu)
 	dma_unmap_resource(rvu->dev, rvu->msix_base_iova,
 			   max_msix * PCI_MSIX_ENTRY_SIZE,
 			   DMA_BIDIRECTIONAL, 0);
+
+	mutex_destroy(&rvu->rsrc_lock);
 }
 
 static int rvu_setup_hw_resources(struct rvu *rvu)
@@ -752,7 +790,7 @@ init:
 	if (!rvu->hwvf)
 		return -ENOMEM;
 
-	spin_lock_init(&rvu->rsrc_lock);
+	mutex_init(&rvu->rsrc_lock);
 
 	err = rvu_setup_msix_resources(rvu);
 	if (err)
@@ -777,17 +815,26 @@ init:
 
 	err = rvu_npc_init(rvu);
 	if (err)
-		return err;
+		goto exit;
+
+	err = rvu_cgx_init(rvu);
+	if (err)
+		goto exit;
 
 	err = rvu_npa_init(rvu);
 	if (err)
-		return err;
+		goto cgx_err;
 
 	err = rvu_nix_init(rvu);
 	if (err)
-		return err;
+		goto cgx_err;
 
 	return 0;
+
+cgx_err:
+	rvu_cgx_exit(rvu);
+exit:
+	return err;
 }
 
 /* NPA and NIX admin queue APIs */
@@ -830,7 +877,7 @@ int rvu_aq_alloc(struct rvu *rvu, struct admin_queue **ad_queue,
 	return 0;
 }
 
-static int rvu_mbox_handler_READY(struct rvu *rvu, struct msg_req *req,
+static int rvu_mbox_handler_ready(struct rvu *rvu, struct msg_req *req,
 				  struct ready_msg_rsp *rsp)
 {
 	return 0;
@@ -858,6 +905,22 @@ static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype)
 	return 0;
 }
 
+bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype)
+{
+	struct rvu_pfvf *pfvf;
+
+	if (!is_pf_func_valid(rvu, pcifunc))
+		return false;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+
+	/* Check if this PFFUNC has a LF of type blktype attached */
+	if (!rvu_get_rsrc_mapcount(pfvf, blktype))
+		return false;
+
+	return true;
+}
+
 static int rvu_lookup_rsrc(struct rvu *rvu, struct rvu_block *block,
 			   int pcifunc, int slot)
 {
@@ -926,7 +989,7 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach,
 	struct rvu_block *block;
 	int blkid;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 
 	/* Check for partial resource detach */
 	if (detach && detach->partial)
@@ -956,11 +1019,11 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach,
 		rvu_detach_block(rvu, pcifunc, block->type);
 	}
 
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return 0;
 }
 
-static int rvu_mbox_handler_DETACH_RESOURCES(struct rvu *rvu,
+static int rvu_mbox_handler_detach_resources(struct rvu *rvu,
 					     struct rsrc_detach *detach,
 					     struct msg_rsp *rsp)
 {
@@ -1108,7 +1171,7 @@ fail:
 	return -ENOSPC;
 }
 
-static int rvu_mbox_handler_ATTACH_RESOURCES(struct rvu *rvu,
+static int rvu_mbox_handler_attach_resources(struct rvu *rvu,
 					     struct rsrc_attach *attach,
 					     struct msg_rsp *rsp)
 {
@@ -1119,7 +1182,7 @@ static int rvu_mbox_handler_ATTACH_RESOURCES(struct rvu *rvu,
 	if (!attach->modify)
 		rvu_detach_rsrcs(rvu, NULL, pcifunc);
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 
 	/* Check if the request can be accommodated */
 	err = rvu_check_rsrc_availability(rvu, attach, pcifunc);
@@ -1163,7 +1226,7 @@ static int rvu_mbox_handler_ATTACH_RESOURCES(struct rvu *rvu,
 	}
 
 exit:
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return err;
 }
 
@@ -1231,7 +1294,7 @@ static void rvu_clear_msix_offset(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	rvu_free_rsrc_contig(&pfvf->msix, nvecs, offset);
 }
 
-static int rvu_mbox_handler_MSIX_OFFSET(struct rvu *rvu, struct msg_req *req,
+static int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req,
 					struct msix_offset_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -1280,22 +1343,51 @@ static int rvu_mbox_handler_MSIX_OFFSET(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
+static int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
+				   struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	u16 vf, numvfs;
+	u64 cfg;
+
+	vf = pcifunc & RVU_PFVF_FUNC_MASK;
+	cfg = rvu_read64(rvu, BLKADDR_RVUM,
+			 RVU_PRIV_PFX_CFG(rvu_get_pf(pcifunc)));
+	numvfs = (cfg >> 12) & 0xFF;
+
+	if (vf && vf <= numvfs)
+		__rvu_flr_handler(rvu, pcifunc);
+	else
+		return RVU_INVALID_VF_ID;
+
+	return 0;
+}
+
+static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid,
 				struct mbox_msghdr *req)
 {
+	struct rvu *rvu = pci_get_drvdata(mbox->pdev);
+
 	/* Check if valid, if not reply with a invalid msg */
 	if (req->sig != OTX2_MBOX_REQ_SIG)
 		goto bad_message;
 
 	switch (req->id) {
-#define M(_name, _id, _req_type, _rsp_type)				\
+#define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
 	case _id: {							\
 		struct _rsp_type *rsp;					\
 		int err;						\
 									\
 		rsp = (struct _rsp_type *)otx2_mbox_alloc_msg(		\
-			&rvu->mbox, devid,				\
+			mbox, devid,					\
 			sizeof(struct _rsp_type));			\
+		/* some handlers should complete even if reply */	\
+		/* could not be allocated */				\
+		if (!rsp &&						\
+		    _id != MBOX_MSG_DETACH_RESOURCES &&			\
+		    _id != MBOX_MSG_NIX_TXSCH_FREE &&			\
+		    _id != MBOX_MSG_VF_FLR)				\
+			return -ENOMEM;					\
 		if (rsp) {						\
 			rsp->hdr.id = _id;				\
 			rsp->hdr.sig = OTX2_MBOX_RSP_SIG;		\
@@ -1303,9 +1395,9 @@ static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 			rsp->hdr.rc = 0;				\
 		}							\
 									\
-		err = rvu_mbox_handler_ ## _name(rvu,			\
-						 (struct _req_type *)req, \
-						 rsp);			\
+		err = rvu_mbox_handler_ ## _fn_name(rvu,		\
+						    (struct _req_type *)req, \
+						    rsp);		\
 		if (rsp && err)						\
 			rsp->hdr.rc = err;				\
 									\
@@ -1313,29 +1405,38 @@ static int rvu_process_mbox_msg(struct rvu *rvu, int devid,
 	}
 MBOX_MESSAGES
 #undef M
-		break;
+
 bad_message:
 	default:
-		otx2_reply_invalid_msg(&rvu->mbox, devid, req->pcifunc,
-				       req->id);
+		otx2_reply_invalid_msg(mbox, devid, req->pcifunc, req->id);
 		return -ENODEV;
 	}
 }
 
-static void rvu_mbox_handler(struct work_struct *work)
+static void __rvu_mbox_handler(struct rvu_work *mwork, int type)
 {
-	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
 	struct rvu *rvu = mwork->rvu;
+	int offset, err, id, devid;
 	struct otx2_mbox_dev *mdev;
 	struct mbox_hdr *req_hdr;
 	struct mbox_msghdr *msg;
+	struct mbox_wq_info *mw;
 	struct otx2_mbox *mbox;
-	int offset, id, err;
-	u16 pf;
 
-	mbox = &rvu->mbox;
-	pf = mwork - rvu->mbox_wrk;
-	mdev = &mbox->dev[pf];
+	switch (type) {
+	case TYPE_AFPF:
+		mw = &rvu->afpf_wq_info;
+		break;
+	case TYPE_AFVF:
+		mw = &rvu->afvf_wq_info;
+		break;
+	default:
+		return;
+	}
+
+	devid = mwork - mw->mbox_wrk;
+	mbox = &mw->mbox;
+	mdev = &mbox->dev[devid];
 
 	/* Process received mbox messages */
 	req_hdr = mdev->mbase + mbox->rx_start;
@@ -1347,10 +1448,21 @@ static void rvu_mbox_handler(struct work_struct *work)
 	for (id = 0; id < req_hdr->num_msgs; id++) {
 		msg = mdev->mbase + offset;
 
-		/* Set which PF sent this message based on mbox IRQ */
-		msg->pcifunc &= ~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
-		msg->pcifunc |= (pf << RVU_PFVF_PF_SHIFT);
-		err = rvu_process_mbox_msg(rvu, pf, msg);
+		/* Set which PF/VF sent this message based on mbox IRQ */
+		switch (type) {
+		case TYPE_AFPF:
+			msg->pcifunc &=
+				~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
+			msg->pcifunc |= (devid << RVU_PFVF_PF_SHIFT);
+			break;
+		case TYPE_AFVF:
+			msg->pcifunc &=
+				~(RVU_PFVF_FUNC_MASK << RVU_PFVF_FUNC_SHIFT);
+			msg->pcifunc |= (devid << RVU_PFVF_FUNC_SHIFT) + 1;
+			break;
+		}
+
+		err = rvu_process_mbox_msg(mbox, devid, msg);
 		if (!err) {
 			offset = mbox->rx_start + msg->next_msgoff;
 			continue;
@@ -1358,31 +1470,57 @@ static void rvu_mbox_handler(struct work_struct *work)
 
 		if (msg->pcifunc & RVU_PFVF_FUNC_MASK)
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n",
-				 err, otx2_mbox_id2name(msg->id), msg->id, pf,
+				 err, otx2_mbox_id2name(msg->id),
+				 msg->id, devid,
 				 (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 		else
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n",
-				 err, otx2_mbox_id2name(msg->id), msg->id, pf);
+				 err, otx2_mbox_id2name(msg->id),
+				 msg->id, devid);
 	}
 
-	/* Send mbox responses to PF */
-	otx2_mbox_msg_send(mbox, pf);
+	/* Send mbox responses to VF/PF */
+	otx2_mbox_msg_send(mbox, devid);
+}
+
+static inline void rvu_afpf_mbox_handler(struct work_struct *work)
+{
+	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_handler(mwork, TYPE_AFPF);
 }
 
-static void rvu_mbox_up_handler(struct work_struct *work)
+static inline void rvu_afvf_mbox_handler(struct work_struct *work)
 {
 	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_handler(mwork, TYPE_AFVF);
+}
+
+static void __rvu_mbox_up_handler(struct rvu_work *mwork, int type)
+{
 	struct rvu *rvu = mwork->rvu;
 	struct otx2_mbox_dev *mdev;
 	struct mbox_hdr *rsp_hdr;
 	struct mbox_msghdr *msg;
+	struct mbox_wq_info *mw;
 	struct otx2_mbox *mbox;
-	int offset, id;
-	u16 pf;
+	int offset, id, devid;
+
+	switch (type) {
+	case TYPE_AFPF:
+		mw = &rvu->afpf_wq_info;
+		break;
+	case TYPE_AFVF:
+		mw = &rvu->afvf_wq_info;
+		break;
+	default:
+		return;
+	}
 
-	mbox = &rvu->mbox_up;
-	pf = mwork - rvu->mbox_wrk_up;
-	mdev = &mbox->dev[pf];
+	devid = mwork - mw->mbox_wrk_up;
+	mbox = &mw->mbox_up;
+	mdev = &mbox->dev[devid];
 
 	rsp_hdr = mdev->mbase + mbox->rx_start;
 	if (rsp_hdr->num_msgs == 0) {
@@ -1423,128 +1561,182 @@ end:
 		mdev->msgs_acked++;
 	}
 
-	otx2_mbox_reset(mbox, 0);
+	otx2_mbox_reset(mbox, devid);
 }
 
-static int rvu_mbox_init(struct rvu *rvu)
+static inline void rvu_afpf_mbox_up_handler(struct work_struct *work)
 {
-	struct rvu_hwinfo *hw = rvu->hw;
-	void __iomem *hwbase = NULL;
+	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_up_handler(mwork, TYPE_AFPF);
+}
+
+static inline void rvu_afvf_mbox_up_handler(struct work_struct *work)
+{
+	struct rvu_work *mwork = container_of(work, struct rvu_work, work);
+
+	__rvu_mbox_up_handler(mwork, TYPE_AFVF);
+}
+
+static int rvu_mbox_init(struct rvu *rvu, struct mbox_wq_info *mw,
+			 int type, int num,
+			 void (mbox_handler)(struct work_struct *),
+			 void (mbox_up_handler)(struct work_struct *))
+{
+	void __iomem *hwbase = NULL, *reg_base;
+	int err, i, dir, dir_up;
 	struct rvu_work *mwork;
+	const char *name;
 	u64 bar4_addr;
-	int err, pf;
 
-	rvu->mbox_wq = alloc_workqueue("rvu_afpf_mailbox",
-				       WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
-				       hw->total_pfs);
-	if (!rvu->mbox_wq)
+	switch (type) {
+	case TYPE_AFPF:
+		name = "rvu_afpf_mailbox";
+		bar4_addr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PF_BAR4_ADDR);
+		dir = MBOX_DIR_AFPF;
+		dir_up = MBOX_DIR_AFPF_UP;
+		reg_base = rvu->afreg_base;
+		break;
+	case TYPE_AFVF:
+		name = "rvu_afvf_mailbox";
+		bar4_addr = rvupf_read64(rvu, RVU_PF_VF_BAR4_ADDR);
+		dir = MBOX_DIR_PFVF;
+		dir_up = MBOX_DIR_PFVF_UP;
+		reg_base = rvu->pfreg_base;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	mw->mbox_wq = alloc_workqueue(name,
+				      WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
+				      num);
+	if (!mw->mbox_wq)
 		return -ENOMEM;
 
-	rvu->mbox_wrk = devm_kcalloc(rvu->dev, hw->total_pfs,
-				     sizeof(struct rvu_work), GFP_KERNEL);
-	if (!rvu->mbox_wrk) {
+	mw->mbox_wrk = devm_kcalloc(rvu->dev, num,
+				    sizeof(struct rvu_work), GFP_KERNEL);
+	if (!mw->mbox_wrk) {
 		err = -ENOMEM;
 		goto exit;
 	}
 
-	rvu->mbox_wrk_up = devm_kcalloc(rvu->dev, hw->total_pfs,
-					sizeof(struct rvu_work), GFP_KERNEL);
-	if (!rvu->mbox_wrk_up) {
+	mw->mbox_wrk_up = devm_kcalloc(rvu->dev, num,
+				       sizeof(struct rvu_work), GFP_KERNEL);
+	if (!mw->mbox_wrk_up) {
 		err = -ENOMEM;
 		goto exit;
 	}
 
-	/* Map mbox region shared with PFs */
-	bar4_addr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PF_BAR4_ADDR);
 	/* Mailbox is a reserved memory (in RAM) region shared between
 	 * RVU devices, shouldn't be mapped as device memory to allow
 	 * unaligned accesses.
 	 */
-	hwbase = ioremap_wc(bar4_addr, MBOX_SIZE * hw->total_pfs);
+	hwbase = ioremap_wc(bar4_addr, MBOX_SIZE * num);
 	if (!hwbase) {
 		dev_err(rvu->dev, "Unable to map mailbox region\n");
 		err = -ENOMEM;
 		goto exit;
 	}
 
-	err = otx2_mbox_init(&rvu->mbox, hwbase, rvu->pdev, rvu->afreg_base,
-			     MBOX_DIR_AFPF, hw->total_pfs);
+	err = otx2_mbox_init(&mw->mbox, hwbase, rvu->pdev, reg_base, dir, num);
 	if (err)
 		goto exit;
 
-	err = otx2_mbox_init(&rvu->mbox_up, hwbase, rvu->pdev, rvu->afreg_base,
-			     MBOX_DIR_AFPF_UP, hw->total_pfs);
+	err = otx2_mbox_init(&mw->mbox_up, hwbase, rvu->pdev,
+			     reg_base, dir_up, num);
 	if (err)
 		goto exit;
 
-	for (pf = 0; pf < hw->total_pfs; pf++) {
-		mwork = &rvu->mbox_wrk[pf];
+	for (i = 0; i < num; i++) {
+		mwork = &mw->mbox_wrk[i];
 		mwork->rvu = rvu;
-		INIT_WORK(&mwork->work, rvu_mbox_handler);
-	}
+		INIT_WORK(&mwork->work, mbox_handler);
 
-	for (pf = 0; pf < hw->total_pfs; pf++) {
-		mwork = &rvu->mbox_wrk_up[pf];
+		mwork = &mw->mbox_wrk_up[i];
 		mwork->rvu = rvu;
-		INIT_WORK(&mwork->work, rvu_mbox_up_handler);
+		INIT_WORK(&mwork->work, mbox_up_handler);
 	}
 
 	return 0;
 exit:
 	if (hwbase)
 		iounmap((void __iomem *)hwbase);
-	destroy_workqueue(rvu->mbox_wq);
+	destroy_workqueue(mw->mbox_wq);
 	return err;
 }
 
-static void rvu_mbox_destroy(struct rvu *rvu)
+static void rvu_mbox_destroy(struct mbox_wq_info *mw)
 {
-	if (rvu->mbox_wq) {
-		flush_workqueue(rvu->mbox_wq);
-		destroy_workqueue(rvu->mbox_wq);
-		rvu->mbox_wq = NULL;
+	if (mw->mbox_wq) {
+		flush_workqueue(mw->mbox_wq);
+		destroy_workqueue(mw->mbox_wq);
+		mw->mbox_wq = NULL;
 	}
 
-	if (rvu->mbox.hwbase)
-		iounmap((void __iomem *)rvu->mbox.hwbase);
+	if (mw->mbox.hwbase)
+		iounmap((void __iomem *)mw->mbox.hwbase);
 
-	otx2_mbox_destroy(&rvu->mbox);
-	otx2_mbox_destroy(&rvu->mbox_up);
+	otx2_mbox_destroy(&mw->mbox);
+	otx2_mbox_destroy(&mw->mbox_up);
 }
 
-static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+static void rvu_queue_work(struct mbox_wq_info *mw, int first,
+			   int mdevs, u64 intr)
 {
-	struct rvu *rvu = (struct rvu *)rvu_irq;
 	struct otx2_mbox_dev *mdev;
 	struct otx2_mbox *mbox;
 	struct mbox_hdr *hdr;
+	int i;
+
+	for (i = first; i < mdevs; i++) {
+		/* start from 0 */
+		if (!(intr & BIT_ULL(i - first)))
+			continue;
+
+		mbox = &mw->mbox;
+		mdev = &mbox->dev[i];
+		hdr = mdev->mbase + mbox->rx_start;
+		if (hdr->num_msgs)
+			queue_work(mw->mbox_wq, &mw->mbox_wrk[i].work);
+
+		mbox = &mw->mbox_up;
+		mdev = &mbox->dev[i];
+		hdr = mdev->mbase + mbox->rx_start;
+		if (hdr->num_msgs)
+			queue_work(mw->mbox_wq, &mw->mbox_wrk_up[i].work);
+	}
+}
+
+static irqreturn_t rvu_mbox_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	int vfs = rvu->vfs;
 	u64 intr;
-	u8  pf;
 
 	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT);
 	/* Clear interrupts */
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT, intr);
 
 	/* Sync with mbox memory region */
-	smp_wmb();
+	rmb();
 
-	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
-		if (intr & (1ULL << pf)) {
-			mbox = &rvu->mbox;
-			mdev = &mbox->dev[pf];
-			hdr = mdev->mbase + mbox->rx_start;
-			if (hdr->num_msgs)
-				queue_work(rvu->mbox_wq,
-					   &rvu->mbox_wrk[pf].work);
-			mbox = &rvu->mbox_up;
-			mdev = &mbox->dev[pf];
-			hdr = mdev->mbase + mbox->rx_start;
-			if (hdr->num_msgs)
-				queue_work(rvu->mbox_wq,
-					   &rvu->mbox_wrk_up[pf].work);
-		}
+	rvu_queue_work(&rvu->afpf_wq_info, 0, rvu->hw->total_pfs, intr);
+
+	/* Handle VF interrupts */
+	if (vfs > 64) {
+		intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(1));
+		rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), intr);
+
+		rvu_queue_work(&rvu->afvf_wq_info, 64, vfs, intr);
+		vfs -= 64;
 	}
 
+	intr = rvupf_read64(rvu, RVU_PF_VFPF_MBOX_INTX(0));
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(0), intr);
+
+	rvu_queue_work(&rvu->afvf_wq_info, 0, vfs, intr);
+
 	return IRQ_HANDLED;
 }
 
@@ -1561,6 +1753,216 @@ static void rvu_enable_mbox_intr(struct rvu *rvu)
 		    INTR_MASK(hw->total_pfs) & ~1ULL);
 }
 
+static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr)
+{
+	struct rvu_block *block;
+	int slot, lf, num_lfs;
+	int err;
+
+	block = &rvu->hw->block[blkaddr];
+	num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc),
+					block->type);
+	if (!num_lfs)
+		return;
+	for (slot = 0; slot < num_lfs; slot++) {
+		lf = rvu_get_lf(rvu, block, pcifunc, slot);
+		if (lf < 0)
+			continue;
+
+		/* Cleanup LF and reset it */
+		if (block->addr == BLKADDR_NIX0)
+			rvu_nix_lf_teardown(rvu, pcifunc, block->addr, lf);
+		else if (block->addr == BLKADDR_NPA)
+			rvu_npa_lf_teardown(rvu, pcifunc, lf);
+
+		err = rvu_lf_reset(rvu, block, lf);
+		if (err) {
+			dev_err(rvu->dev, "Failed to reset blkaddr %d LF%d\n",
+				block->addr, lf);
+		}
+	}
+}
+
+static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc)
+{
+	mutex_lock(&rvu->flr_lock);
+	/* Reset order should reflect inter-block dependencies:
+	 * 1. Reset any packet/work sources (NIX, CPT, TIM)
+	 * 2. Flush and reset SSO/SSOW
+	 * 3. Cleanup pools (NPA)
+	 */
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX0);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT0);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_TIM);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO);
+	rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NPA);
+	rvu_detach_rsrcs(rvu, NULL, pcifunc);
+	mutex_unlock(&rvu->flr_lock);
+}
+
+static void rvu_afvf_flr_handler(struct rvu *rvu, int vf)
+{
+	int reg = 0;
+
+	/* pcifunc = 0(PF0) | (vf + 1) */
+	__rvu_flr_handler(rvu, vf + 1);
+
+	if (vf >= 64) {
+		reg = 1;
+		vf = vf - 64;
+	}
+
+	/* Signal FLR finish and enable IRQ */
+	rvupf_write64(rvu, RVU_PF_VFTRPENDX(reg), BIT_ULL(vf));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(reg), BIT_ULL(vf));
+}
+
+static void rvu_flr_handler(struct work_struct *work)
+{
+	struct rvu_work *flrwork = container_of(work, struct rvu_work, work);
+	struct rvu *rvu = flrwork->rvu;
+	u16 pcifunc, numvfs, vf;
+	u64 cfg;
+	int pf;
+
+	pf = flrwork - rvu->flr_wrk;
+	if (pf >= rvu->hw->total_pfs) {
+		rvu_afvf_flr_handler(rvu, pf - rvu->hw->total_pfs);
+		return;
+	}
+
+	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
+	numvfs = (cfg >> 12) & 0xFF;
+	pcifunc  = pf << RVU_PFVF_PF_SHIFT;
+
+	for (vf = 0; vf < numvfs; vf++)
+		__rvu_flr_handler(rvu, (pcifunc | (vf + 1)));
+
+	__rvu_flr_handler(rvu, pcifunc);
+
+	/* Signal FLR finish */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFTRPEND, BIT_ULL(pf));
+
+	/* Enable interrupt */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,  BIT_ULL(pf));
+}
+
+static void rvu_afvf_queue_flr_work(struct rvu *rvu, int start_vf, int numvfs)
+{
+	int dev, vf, reg = 0;
+	u64 intr;
+
+	if (start_vf >= 64)
+		reg = 1;
+
+	intr = rvupf_read64(rvu, RVU_PF_VFFLR_INTX(reg));
+	if (!intr)
+		return;
+
+	for (vf = 0; vf < numvfs; vf++) {
+		if (!(intr & BIT_ULL(vf)))
+			continue;
+		dev = vf + start_vf + rvu->hw->total_pfs;
+		queue_work(rvu->flr_wq, &rvu->flr_wrk[dev].work);
+		/* Clear and disable the interrupt */
+		rvupf_write64(rvu, RVU_PF_VFFLR_INTX(reg), BIT_ULL(vf));
+		rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(reg), BIT_ULL(vf));
+	}
+}
+
+static irqreturn_t rvu_flr_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	u64 intr;
+	u8  pf;
+
+	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT);
+	if (!intr)
+		goto afvf_flr;
+
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+		if (intr & (1ULL << pf)) {
+			/* PF is already dead do only AF related operations */
+			queue_work(rvu->flr_wq, &rvu->flr_wrk[pf].work);
+			/* clear interrupt */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT,
+				    BIT_ULL(pf));
+			/* Disable the interrupt */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
+				    BIT_ULL(pf));
+		}
+	}
+
+afvf_flr:
+	rvu_afvf_queue_flr_work(rvu, 0, 64);
+	if (rvu->vfs > 64)
+		rvu_afvf_queue_flr_work(rvu, 64, rvu->vfs - 64);
+
+	return IRQ_HANDLED;
+}
+
+static void rvu_me_handle_vfset(struct rvu *rvu, int idx, u64 intr)
+{
+	int vf;
+
+	/* Nothing to be done here other than clearing the
+	 * TRPEND bit.
+	 */
+	for (vf = 0; vf < 64; vf++) {
+		if (intr & (1ULL << vf)) {
+			/* clear the trpend due to ME(master enable) */
+			rvupf_write64(rvu, RVU_PF_VFTRPENDX(idx), BIT_ULL(vf));
+			/* clear interrupt */
+			rvupf_write64(rvu, RVU_PF_VFME_INTX(idx), BIT_ULL(vf));
+		}
+	}
+}
+
+/* Handles ME interrupts from VFs of AF */
+static irqreturn_t rvu_me_vf_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	int vfset;
+	u64 intr;
+
+	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT);
+
+	for (vfset = 0; vfset <= 1; vfset++) {
+		intr = rvupf_read64(rvu, RVU_PF_VFME_INTX(vfset));
+		if (intr)
+			rvu_me_handle_vfset(rvu, vfset, intr);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/* Handles ME interrupts from PFs */
+static irqreturn_t rvu_me_pf_intr_handler(int irq, void *rvu_irq)
+{
+	struct rvu *rvu = (struct rvu *)rvu_irq;
+	u64 intr;
+	u8  pf;
+
+	intr = rvu_read64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT);
+
+	/* Nothing to be done here other than clearing the
+	 * TRPEND bit.
+	 */
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+		if (intr & (1ULL << pf)) {
+			/* clear the trpend due to ME(master enable) */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFTRPEND,
+				    BIT_ULL(pf));
+			/* clear interrupt */
+			rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT,
+				    BIT_ULL(pf));
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
 static void rvu_unregister_interrupts(struct rvu *rvu)
 {
 	int irq;
@@ -1569,6 +1971,14 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFAF_MBOX_INT_ENA_W1C,
 		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
 
+	/* Disable the PF FLR interrupt */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1C,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
+	/* Disable the PF ME interrupt */
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT_ENA_W1C,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
 	for (irq = 0; irq < rvu->num_vec; irq++) {
 		if (rvu->irq_allocated[irq])
 			free_irq(pci_irq_vector(rvu->pdev, irq), rvu);
@@ -1578,9 +1988,25 @@ static void rvu_unregister_interrupts(struct rvu *rvu)
 	rvu->num_vec = 0;
 }
 
+static int rvu_afvf_msix_vectors_num_ok(struct rvu *rvu)
+{
+	struct rvu_pfvf *pfvf = &rvu->pf[0];
+	int offset;
+
+	pfvf = &rvu->pf[0];
+	offset = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
+
+	/* Make sure there are enough MSIX vectors configured so that
+	 * VF interrupts can be handled. Offset equal to zero means
+	 * that PF vectors are not configured and overlapping AF vectors.
+	 */
+	return (pfvf->msix.max >= RVU_AF_INT_VEC_CNT + RVU_PF_INT_VEC_CNT) &&
+	       offset;
+}
+
 static int rvu_register_interrupts(struct rvu *rvu)
 {
-	int ret;
+	int ret, offset, pf_vec_start;
 
 	rvu->num_vec = pci_msix_vec_count(rvu->pdev);
 
@@ -1620,13 +2046,331 @@ static int rvu_register_interrupts(struct rvu *rvu)
 	/* Enable mailbox interrupts from all PFs */
 	rvu_enable_mbox_intr(rvu);
 
+	/* Register FLR interrupt handler */
+	sprintf(&rvu->irq_name[RVU_AF_INT_VEC_PFFLR * NAME_SIZE],
+		"RVUAF FLR");
+	ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_PFFLR),
+			  rvu_flr_intr_handler, 0,
+			  &rvu->irq_name[RVU_AF_INT_VEC_PFFLR * NAME_SIZE],
+			  rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for FLR\n");
+		goto fail;
+	}
+	rvu->irq_allocated[RVU_AF_INT_VEC_PFFLR] = true;
+
+	/* Enable FLR interrupt for all PFs*/
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_AF_PFFLR_INT, INTR_MASK(rvu->hw->total_pfs));
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFFLR_INT_ENA_W1S,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
+	/* Register ME interrupt handler */
+	sprintf(&rvu->irq_name[RVU_AF_INT_VEC_PFME * NAME_SIZE],
+		"RVUAF ME");
+	ret = request_irq(pci_irq_vector(rvu->pdev, RVU_AF_INT_VEC_PFME),
+			  rvu_me_pf_intr_handler, 0,
+			  &rvu->irq_name[RVU_AF_INT_VEC_PFME * NAME_SIZE],
+			  rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for ME\n");
+	}
+	rvu->irq_allocated[RVU_AF_INT_VEC_PFME] = true;
+
+	/* Enable ME interrupt for all PFs*/
+	rvu_write64(rvu, BLKADDR_RVUM,
+		    RVU_AF_PFME_INT, INTR_MASK(rvu->hw->total_pfs));
+
+	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_PFME_INT_ENA_W1S,
+		    INTR_MASK(rvu->hw->total_pfs) & ~1ULL);
+
+	if (!rvu_afvf_msix_vectors_num_ok(rvu))
+		return 0;
+
+	/* Get PF MSIX vectors offset. */
+	pf_vec_start = rvu_read64(rvu, BLKADDR_RVUM,
+				  RVU_PRIV_PFX_INT_CFG(0)) & 0x3ff;
+
+	/* Register MBOX0 interrupt. */
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX0;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox0");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_mbox_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE],
+			  rvu);
+	if (ret)
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for Mbox0\n");
+
+	rvu->irq_allocated[offset] = true;
+
+	/* Register MBOX1 interrupt. MBOX1 IRQ number follows MBOX0 so
+	 * simply increment current offset by 1.
+	 */
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFPF_MBOX1;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF Mbox1");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_mbox_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE],
+			  rvu);
+	if (ret)
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for Mbox1\n");
+
+	rvu->irq_allocated[offset] = true;
+
+	/* Register FLR interrupt handler for AF's VFs */
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFFLR0;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF FLR0");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_flr_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF FLR0\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
+
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFFLR1;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF FLR1");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_flr_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF FLR1\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
+
+	/* Register ME interrupt handler for AF's VFs */
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFME0;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF ME0");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_me_vf_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF ME0\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
+
+	offset = pf_vec_start + RVU_PF_INT_VEC_VFME1;
+	sprintf(&rvu->irq_name[offset * NAME_SIZE], "RVUAFVF ME1");
+	ret = request_irq(pci_irq_vector(rvu->pdev, offset),
+			  rvu_me_vf_intr_handler, 0,
+			  &rvu->irq_name[offset * NAME_SIZE], rvu);
+	if (ret) {
+		dev_err(rvu->dev,
+			"RVUAF: IRQ registration failed for RVUAFVF ME1\n");
+		goto fail;
+	}
+	rvu->irq_allocated[offset] = true;
 	return 0;
 
 fail:
-	pci_free_irq_vectors(rvu->pdev);
+	rvu_unregister_interrupts(rvu);
+	return ret;
+}
+
+static void rvu_flr_wq_destroy(struct rvu *rvu)
+{
+	if (rvu->flr_wq) {
+		flush_workqueue(rvu->flr_wq);
+		destroy_workqueue(rvu->flr_wq);
+		rvu->flr_wq = NULL;
+	}
+}
+
+static int rvu_flr_init(struct rvu *rvu)
+{
+	int dev, num_devs;
+	u64 cfg;
+	int pf;
+
+	/* Enable FLR for all PFs*/
+	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
+		cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
+		rvu_write64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf),
+			    cfg | BIT_ULL(22));
+	}
+
+	rvu->flr_wq = alloc_workqueue("rvu_afpf_flr",
+				      WQ_UNBOUND | WQ_HIGHPRI | WQ_MEM_RECLAIM,
+				       1);
+	if (!rvu->flr_wq)
+		return -ENOMEM;
+
+	num_devs = rvu->hw->total_pfs + pci_sriov_get_totalvfs(rvu->pdev);
+	rvu->flr_wrk = devm_kcalloc(rvu->dev, num_devs,
+				    sizeof(struct rvu_work), GFP_KERNEL);
+	if (!rvu->flr_wrk) {
+		destroy_workqueue(rvu->flr_wq);
+		return -ENOMEM;
+	}
+
+	for (dev = 0; dev < num_devs; dev++) {
+		rvu->flr_wrk[dev].rvu = rvu;
+		INIT_WORK(&rvu->flr_wrk[dev].work, rvu_flr_handler);
+	}
+
+	mutex_init(&rvu->flr_lock);
+
+	return 0;
+}
+
+static void rvu_disable_afvf_intr(struct rvu *rvu)
+{
+	int vfs = rvu->vfs;
+
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(0), INTR_MASK(vfs));
+	if (vfs <= 64)
+		return;
+
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1CX(1),
+		      INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1CX(1), INTR_MASK(vfs - 64));
+}
+
+static void rvu_enable_afvf_intr(struct rvu *rvu)
+{
+	int vfs = rvu->vfs;
+
+	/* Clear any pending interrupts and enable AF VF interrupts for
+	 * the first 64 VFs.
+	 */
+	/* Mbox */
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(0), INTR_MASK(vfs));
+
+	/* FLR */
+	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(0), INTR_MASK(vfs));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1SX(0), INTR_MASK(vfs));
+
+	/* Same for remaining VFs, if any. */
+	if (vfs <= 64)
+		return;
+
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFPF_MBOX_INT_ENA_W1SX(1),
+		      INTR_MASK(vfs - 64));
+
+	rvupf_write64(rvu, RVU_PF_VFFLR_INTX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFFLR_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+	rvupf_write64(rvu, RVU_PF_VFME_INT_ENA_W1SX(1), INTR_MASK(vfs - 64));
+}
+
+#define PCI_DEVID_OCTEONTX2_LBK 0xA061
+
+static int lbk_get_num_chans(void)
+{
+	struct pci_dev *pdev;
+	void __iomem *base;
+	int ret = -EIO;
+
+	pdev = pci_get_device(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_LBK,
+			      NULL);
+	if (!pdev)
+		goto err;
+
+	base = pci_ioremap_bar(pdev, 0);
+	if (!base)
+		goto err_put;
+
+	/* Read number of available LBK channels from LBK(0)_CONST register. */
+	ret = (readq(base + 0x10) >> 32) & 0xffff;
+	iounmap(base);
+err_put:
+	pci_dev_put(pdev);
+err:
 	return ret;
 }
 
+static int rvu_enable_sriov(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+	int err, chans, vfs;
+
+	if (!rvu_afvf_msix_vectors_num_ok(rvu)) {
+		dev_warn(&pdev->dev,
+			 "Skipping SRIOV enablement since not enough IRQs are available\n");
+		return 0;
+	}
+
+	chans = lbk_get_num_chans();
+	if (chans < 0)
+		return chans;
+
+	vfs = pci_sriov_get_totalvfs(pdev);
+
+	/* Limit VFs in case we have more VFs than LBK channels available. */
+	if (vfs > chans)
+		vfs = chans;
+
+	/* AF's VFs work in pairs and talk over consecutive loopback channels.
+	 * Thus we want to enable maximum even number of VFs. In case
+	 * odd number of VFs are available then the last VF on the list
+	 * remains disabled.
+	 */
+	if (vfs & 0x1) {
+		dev_warn(&pdev->dev,
+			 "Number of VFs should be even. Enabling %d out of %d.\n",
+			 vfs - 1, vfs);
+		vfs--;
+	}
+
+	if (!vfs)
+		return 0;
+
+	/* Save VFs number for reference in VF interrupts handlers.
+	 * Since interrupts might start arriving during SRIOV enablement
+	 * ordinary API cannot be used to get number of enabled VFs.
+	 */
+	rvu->vfs = vfs;
+
+	err = rvu_mbox_init(rvu, &rvu->afvf_wq_info, TYPE_AFVF, vfs,
+			    rvu_afvf_mbox_handler, rvu_afvf_mbox_up_handler);
+	if (err)
+		return err;
+
+	rvu_enable_afvf_intr(rvu);
+	/* Make sure IRQs are enabled before SRIOV. */
+	mb();
+
+	err = pci_enable_sriov(pdev, vfs);
+	if (err) {
+		rvu_disable_afvf_intr(rvu);
+		rvu_mbox_destroy(&rvu->afvf_wq_info);
+		return err;
+	}
+
+	return 0;
+}
+
+static void rvu_disable_sriov(struct rvu *rvu)
+{
+	rvu_disable_afvf_intr(rvu);
+	rvu_mbox_destroy(&rvu->afvf_wq_info);
+	pci_disable_sriov(rvu->pdev);
+}
+
+static void rvu_update_module_params(struct rvu *rvu)
+{
+	const char *default_pfl_name = "default";
+
+	strscpy(rvu->mkex_pfl_name,
+		mkex_profile ? mkex_profile : default_pfl_name, MKEX_NAME_LEN);
+}
+
 static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct device *dev = &pdev->dev;
@@ -1680,6 +2424,9 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_release_regions;
 	}
 
+	/* Store module params in rvu structure */
+	rvu_update_module_params(rvu);
+
 	/* Check which blocks the HW supports */
 	rvu_check_block_implemented(rvu);
 
@@ -1689,24 +2436,35 @@ static int rvu_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_release_regions;
 
-	err = rvu_mbox_init(rvu);
+	/* Init mailbox btw AF and PFs */
+	err = rvu_mbox_init(rvu, &rvu->afpf_wq_info, TYPE_AFPF,
+			    rvu->hw->total_pfs, rvu_afpf_mbox_handler,
+			    rvu_afpf_mbox_up_handler);
 	if (err)
 		goto err_hwsetup;
 
-	err = rvu_cgx_probe(rvu);
+	err = rvu_flr_init(rvu);
 	if (err)
 		goto err_mbox;
 
 	err = rvu_register_interrupts(rvu);
 	if (err)
-		goto err_cgx;
+		goto err_flr;
+
+	/* Enable AF's VFs (if any) */
+	err = rvu_enable_sriov(rvu);
+	if (err)
+		goto err_irq;
 
 	return 0;
-err_cgx:
-	rvu_cgx_wq_destroy(rvu);
+err_irq:
+	rvu_unregister_interrupts(rvu);
+err_flr:
+	rvu_flr_wq_destroy(rvu);
 err_mbox:
-	rvu_mbox_destroy(rvu);
+	rvu_mbox_destroy(&rvu->afpf_wq_info);
 err_hwsetup:
+	rvu_cgx_exit(rvu);
 	rvu_reset_all_blocks(rvu);
 	rvu_free_hw_resources(rvu);
 err_release_regions:
@@ -1725,8 +2483,10 @@ static void rvu_remove(struct pci_dev *pdev)
 	struct rvu *rvu = pci_get_drvdata(pdev);
 
 	rvu_unregister_interrupts(rvu);
-	rvu_cgx_wq_destroy(rvu);
-	rvu_mbox_destroy(rvu);
+	rvu_flr_wq_destroy(rvu);
+	rvu_cgx_exit(rvu);
+	rvu_mbox_destroy(&rvu->afpf_wq_info);
+	rvu_disable_sriov(rvu);
 	rvu_reset_all_blocks(rvu);
 	rvu_free_hw_resources(rvu);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 2c0580cd2807..c9d60b0554c0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -11,6 +11,7 @@
 #ifndef RVU_H
 #define RVU_H
 
+#include <linux/pci.h>
 #include "rvu_struct.h"
 #include "common.h"
 #include "mbox.h"
@@ -18,6 +19,9 @@
 /* PCI device IDs */
 #define	PCI_DEVID_OCTEONTX2_RVU_AF		0xA065
 
+/* Subsystem Device ID */
+#define PCI_SUBSYS_DEVID_96XX                  0xB200
+
 /* PCI BAR nos */
 #define	PCI_AF_REG_BAR_NUM			0
 #define	PCI_PF_REG_BAR_NUM			2
@@ -64,7 +68,7 @@ struct nix_mcast {
 	struct qmem	*mcast_buf;
 	int		replay_pkind;
 	int		next_free_mce;
-	spinlock_t	mce_lock; /* Serialize MCE updates */
+	struct mutex	mce_lock; /* Serialize MCE updates */
 };
 
 struct nix_mce_list {
@@ -74,15 +78,27 @@ struct nix_mce_list {
 };
 
 struct npc_mcam {
-	spinlock_t	lock;	/* MCAM entries and counters update lock */
+	struct rsrc_bmap counters;
+	struct mutex	lock;	/* MCAM entries and counters update lock */
+	unsigned long	*bmap;		/* bitmap, 0 => bmap_entries */
+	unsigned long	*bmap_reverse;	/* Reverse bitmap, bmap_entries => 0 */
+	u16	bmap_entries;	/* Number of unreserved MCAM entries */
+	u16	bmap_fcnt;	/* MCAM entries free count */
+	u16	*entry2pfvf_map;
+	u16	*entry2cntr_map;
+	u16	*cntr2pfvf_map;
+	u16	*cntr_refcnt;
 	u8	keysize;	/* MCAM keysize 112/224/448 bits */
 	u8	banks;		/* Number of MCAM banks */
 	u8	banks_per_entry;/* Number of keywords in key */
 	u16	banksize;	/* Number of MCAM entries in each bank */
 	u16	total_entries;	/* Total number of MCAM entries */
-	u16     entries;	/* Total minus reserved for NIX LFs */
 	u16	nixlf_offset;	/* Offset of nixlf rsvd uncast entries */
 	u16	pf_offset;	/* Offset of PF's rsvd bcast, promisc entries */
+	u16	lprio_count;
+	u16	lprio_start;
+	u16	hprio_count;
+	u16	hprio_end;
 };
 
 /* Structure for per RVU func info ie PF/VF */
@@ -122,18 +138,35 @@ struct rvu_pfvf {
 	u16		tx_chan_base;
 	u8              rx_chan_cnt; /* total number of RX channels */
 	u8              tx_chan_cnt; /* total number of TX channels */
+	u16		maxlen;
+	u16		minlen;
 
 	u8		mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */
 
 	/* Broadcast pkt replication info */
 	u16			bcast_mce_idx;
 	struct nix_mce_list	bcast_mce_list;
+
+	/* VLAN offload */
+	struct mcam_entry entry;
+	int rxvlan_index;
+	bool rxvlan;
 };
 
 struct nix_txsch {
 	struct rsrc_bmap schq;
 	u8   lvl;
-	u16  *pfvf_map;
+#define NIX_TXSCHQ_TL1_CFG_DONE       BIT_ULL(0)
+#define TXSCH_MAP_FUNC(__pfvf_map)    ((__pfvf_map) & 0xFFFF)
+#define TXSCH_MAP_FLAGS(__pfvf_map)   ((__pfvf_map) >> 16)
+#define TXSCH_MAP(__func, __flags)    (((__func) & 0xFFFF) | ((__flags) << 16))
+	u32  *pfvf_map;
+};
+
+struct nix_mark_format {
+	u8 total;
+	u8 in_use;
+	u32 *cfg;
 };
 
 struct npc_pkind {
@@ -141,9 +174,23 @@ struct npc_pkind {
 	u32	*pfchan_map;
 };
 
+struct nix_flowkey {
+#define NIX_FLOW_KEY_ALG_MAX 32
+	u32 flowkey[NIX_FLOW_KEY_ALG_MAX];
+	int in_use;
+};
+
+struct nix_lso {
+	u8 total;
+	u8 in_use;
+};
+
 struct nix_hw {
 	struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */
 	struct nix_mcast mcast;
+	struct nix_flowkey flowkey;
+	struct nix_mark_format mark_format;
+	struct nix_lso lso;
 };
 
 struct rvu_hwinfo {
@@ -164,6 +211,16 @@ struct rvu_hwinfo {
 	struct npc_mcam  mcam;
 };
 
+struct mbox_wq_info {
+	struct otx2_mbox mbox;
+	struct rvu_work *mbox_wrk;
+
+	struct otx2_mbox mbox_up;
+	struct rvu_work *mbox_wrk_up;
+
+	struct workqueue_struct *mbox_wq;
+};
+
 struct rvu {
 	void __iomem		*afreg_base;
 	void __iomem		*pfreg_base;
@@ -172,14 +229,17 @@ struct rvu {
 	struct rvu_hwinfo       *hw;
 	struct rvu_pfvf		*pf;
 	struct rvu_pfvf		*hwvf;
-	spinlock_t		rsrc_lock; /* Serialize resource alloc/free */
+	struct mutex		rsrc_lock; /* Serialize resource alloc/free */
+	int			vfs; /* Number of VFs attached to RVU */
 
 	/* Mbox */
-	struct otx2_mbox	mbox;
-	struct rvu_work		*mbox_wrk;
-	struct otx2_mbox        mbox_up;
-	struct rvu_work		*mbox_wrk_up;
-	struct workqueue_struct *mbox_wq;
+	struct mbox_wq_info	afpf_wq_info;
+	struct mbox_wq_info	afvf_wq_info;
+
+	/* PF FLR */
+	struct rvu_work		*flr_wrk;
+	struct workqueue_struct *flr_wq;
+	struct mutex		flr_lock; /* Serialize FLRs */
 
 	/* MSI-X */
 	u16			num_vec;
@@ -190,7 +250,7 @@ struct rvu {
 	/* CGX */
 #define PF_CGXMAP_BASE		1 /* PF 0 is reserved for RVU PF */
 	u8			cgx_mapped_pfs;
-	u8			cgx_cnt; /* available cgx ports */
+	u8			cgx_cnt_max;	 /* CGX port count max */
 	u8			*pf2cgxlmac_map; /* pf to cgx_lmac map */
 	u16			*cgxlmac2pf_map; /* bitmap of mapped pfs for
 						  * every cgx lmac port
@@ -201,6 +261,8 @@ struct rvu {
 	struct			workqueue_struct *cgx_evh_wq;
 	spinlock_t		cgx_evq_lock; /* cgx event queue lock */
 	struct list_head	cgx_evq_head; /* cgx event queue head */
+
+	char mkex_pfl_name[MKEX_NAME_LEN]; /* Configured MKEX profile name */
 };
 
 static inline void rvu_write64(struct rvu *rvu, u64 block, u64 offset, u64 val)
@@ -223,9 +285,22 @@ static inline u64 rvupf_read64(struct rvu *rvu, u64 offset)
 	return readq(rvu->pfreg_base + offset);
 }
 
+static inline bool is_rvu_9xxx_A0(struct rvu *rvu)
+{
+	struct pci_dev *pdev = rvu->pdev;
+
+	return (pdev->revision == 0x00) &&
+		(pdev->subsystem_device == PCI_SUBSYS_DEVID_96XX);
+}
+
 /* Function Prototypes
  * RVU
  */
+static inline int is_afvf(u16 pcifunc)
+{
+	return !(pcifunc & ~RVU_PFVF_FUNC_MASK);
+}
+
 int rvu_alloc_bitmap(struct rsrc_bmap *rsrc);
 int rvu_alloc_rsrc(struct rsrc_bmap *rsrc);
 void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id);
@@ -236,6 +311,7 @@ int rvu_get_pf(u16 pcifunc);
 struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc);
 void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf);
 bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr);
+bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype);
 int rvu_get_lf(struct rvu *rvu, struct rvu_block *block, u16 pcifunc, u16 slot);
 int rvu_lf_reset(struct rvu *rvu, struct rvu_block *block, int lf);
 int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc);
@@ -266,89 +342,110 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
 	*lmac_id = (map & 0xF);
 }
 
-int rvu_cgx_probe(struct rvu *rvu);
-void rvu_cgx_wq_destroy(struct rvu *rvu);
+int rvu_cgx_init(struct rvu *rvu);
+int rvu_cgx_exit(struct rvu *rvu);
 void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu);
 int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start);
-int rvu_mbox_handler_CGX_START_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
 				    struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_STOP_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_STATS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stats(struct rvu *rvu, struct msg_req *req,
 			       struct cgx_stats_rsp *rsp);
-int rvu_mbox_handler_CGX_MAC_ADDR_SET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp);
-int rvu_mbox_handler_CGX_MAC_ADDR_GET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp);
-int rvu_mbox_handler_CGX_PROMISC_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_PROMISC_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_START_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_linkevents(struct rvu *rvu, struct msg_req *req,
 					  struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_STOP_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_linkevents(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_GET_LINKINFO(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req,
 				      struct cgx_link_info_msg *rsp);
-int rvu_mbox_handler_CGX_INTLBK_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_enable(struct rvu *rvu, struct msg_req *req,
 				       struct msg_rsp *rsp);
-int rvu_mbox_handler_CGX_INTLBK_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp);
 
 /* NPA APIs */
 int rvu_npa_init(struct rvu *rvu);
 void rvu_npa_freemem(struct rvu *rvu);
-int rvu_mbox_handler_NPA_AQ_ENQ(struct rvu *rvu,
+void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf);
+int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
 				struct npa_aq_enq_req *req,
 				struct npa_aq_enq_rsp *rsp);
-int rvu_mbox_handler_NPA_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_npa_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp);
-int rvu_mbox_handler_NPA_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 				  struct npa_lf_alloc_req *req,
 				  struct npa_lf_alloc_rsp *rsp);
-int rvu_mbox_handler_NPA_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp);
 
 /* NIX APIs */
+bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc);
 int rvu_nix_init(struct rvu *rvu);
+int rvu_nix_reserve_mark_format(struct rvu *rvu, struct nix_hw *nix_hw,
+				int blkaddr, u32 cfg);
 void rvu_nix_freemem(struct rvu *rvu);
 int rvu_get_nixlf_count(struct rvu *rvu);
-int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
+void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf);
+int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 				  struct nix_lf_alloc_req *req,
 				  struct nix_lf_alloc_rsp *rsp);
-int rvu_mbox_handler_NIX_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_nix_aq_enq(struct rvu *rvu,
 				struct nix_aq_enq_req *req,
 				struct nix_aq_enq_rsp *rsp);
-int rvu_mbox_handler_NIX_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_nix_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 				     struct nix_txsch_alloc_req *req,
 				     struct nix_txsch_alloc_rsp *rsp);
-int rvu_mbox_handler_NIX_TXSCH_FREE(struct rvu *rvu,
+int rvu_mbox_handler_nix_txsch_free(struct rvu *rvu,
 				    struct nix_txsch_free_req *req,
 				    struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
 				    struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_STATS_RST(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_VTAG_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
 				  struct nix_vtag_config *req,
 				  struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_RSS_FLOWKEY_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
+				      struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
 					 struct nix_rss_flowkey_cfg *req,
-					 struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_SET_MAC_ADDR(struct rvu *rvu,
+					 struct nix_rss_flowkey_cfg_rsp *rsp);
+int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 				      struct nix_set_mac_addr *req,
 				      struct msg_rsp *rsp);
-int rvu_mbox_handler_NIX_SET_RX_MODE(struct rvu *rvu, struct nix_rx_mode *req,
+int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
+				    struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
+				     struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
+				    struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
+					 struct nix_mark_format_cfg  *req,
+					 struct nix_mark_format_cfg_rsp *rsp);
+int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
+				    struct msg_rsp *rsp);
+int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu,
+					struct nix_lso_format_cfg *req,
+					struct nix_lso_format_cfg_rsp *rsp);
 
 /* NPC APIs */
 int rvu_npc_init(struct rvu *rvu);
@@ -360,9 +457,48 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 				   int nixlf, u64 chan, bool allmulti);
 void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 				       int nixlf, u64 chan);
+int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
+void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf);
 void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 				    int group, int alg_idx, int mcam_index);
+int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
+					  struct npc_mcam_alloc_entry_req *req,
+					  struct npc_mcam_alloc_entry_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
+					 struct npc_mcam_free_entry_req *req,
+					 struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
+					  struct npc_mcam_write_entry_req *req,
+					  struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_ena_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_dis_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
+					  struct npc_mcam_shift_entry_req *req,
+					  struct npc_mcam_shift_entry_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu,
+				struct npc_mcam_alloc_counter_req *req,
+				struct npc_mcam_alloc_counter_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
+		   struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_clear_counter(struct rvu *rvu,
+		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu,
+		struct npc_mcam_unmap_counter_req *req, struct msg_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
+			struct npc_mcam_oper_counter_req *req,
+			struct npc_mcam_oper_counter_rsp *rsp);
+int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
+			  struct npc_mcam_alloc_and_write_entry_req *req,
+			  struct npc_mcam_alloc_and_write_entry_rsp *rsp);
+int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req,
+				     struct npc_get_kex_cfg_rsp *rsp);
 #endif /* RVU_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index 188185c15b4a..7d7133c5f799 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -20,14 +20,14 @@ struct cgx_evq_entry {
 	struct cgx_link_event link_event;
 };
 
-#define M(_name, _id, _req_type, _rsp_type)				\
+#define M(_name, _id, _fn_name, _req_type, _rsp_type)			\
 static struct _req_type __maybe_unused					\
-*otx2_mbox_alloc_msg_ ## _name(struct rvu *rvu, int devid)		\
+*otx2_mbox_alloc_msg_ ## _fn_name(struct rvu *rvu, int devid)		\
 {									\
 	struct _req_type *req;						\
 									\
 	req = (struct _req_type *)otx2_mbox_alloc_msg_rsp(		\
-		&rvu->mbox_up, devid, sizeof(struct _req_type),		\
+		&rvu->afpf_wq_info.mbox_up, devid, sizeof(struct _req_type), \
 		sizeof(struct _rsp_type));				\
 	if (!req)							\
 		return NULL;						\
@@ -52,7 +52,7 @@ static inline u8 cgxlmac_id_to_bmap(u8 cgx_id, u8 lmac_id)
 
 void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu)
 {
-	if (cgx_id >= rvu->cgx_cnt)
+	if (cgx_id >= rvu->cgx_cnt_max)
 		return NULL;
 
 	return rvu->cgx_idmap[cgx_id];
@@ -61,38 +61,40 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu)
 static int rvu_map_cgx_lmac_pf(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
-	int cgx_cnt = rvu->cgx_cnt;
+	int cgx_cnt_max = rvu->cgx_cnt_max;
 	int cgx, lmac_cnt, lmac;
 	int pf = PF_CGXMAP_BASE;
 	int size, free_pkind;
 
-	if (!cgx_cnt)
+	if (!cgx_cnt_max)
 		return 0;
 
-	if (cgx_cnt > 0xF || MAX_LMAC_PER_CGX > 0xF)
+	if (cgx_cnt_max > 0xF || MAX_LMAC_PER_CGX > 0xF)
 		return -EINVAL;
 
 	/* Alloc map table
 	 * An additional entry is required since PF id starts from 1 and
 	 * hence entry at offset 0 is invalid.
 	 */
-	size = (cgx_cnt * MAX_LMAC_PER_CGX + 1) * sizeof(u8);
-	rvu->pf2cgxlmac_map = devm_kzalloc(rvu->dev, size, GFP_KERNEL);
+	size = (cgx_cnt_max * MAX_LMAC_PER_CGX + 1) * sizeof(u8);
+	rvu->pf2cgxlmac_map = devm_kmalloc(rvu->dev, size, GFP_KERNEL);
 	if (!rvu->pf2cgxlmac_map)
 		return -ENOMEM;
 
-	/* Initialize offset 0 with an invalid cgx and lmac id */
-	rvu->pf2cgxlmac_map[0] = 0xFF;
+	/* Initialize all entries with an invalid cgx and lmac id */
+	memset(rvu->pf2cgxlmac_map, 0xFF, size);
 
 	/* Reverse map table */
 	rvu->cgxlmac2pf_map = devm_kzalloc(rvu->dev,
-				  cgx_cnt * MAX_LMAC_PER_CGX * sizeof(u16),
+				  cgx_cnt_max * MAX_LMAC_PER_CGX * sizeof(u16),
 				  GFP_KERNEL);
 	if (!rvu->cgxlmac2pf_map)
 		return -ENOMEM;
 
 	rvu->cgx_mapped_pfs = 0;
-	for (cgx = 0; cgx < cgx_cnt; cgx++) {
+	for (cgx = 0; cgx < cgx_cnt_max; cgx++) {
+		if (!rvu_cgx_pdata(cgx, rvu))
+			continue;
 		lmac_cnt = cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
 		for (lmac = 0; lmac < lmac_cnt; lmac++, pf++) {
 			rvu->pf2cgxlmac_map[pf] = cgxlmac_id_to_bmap(cgx, lmac);
@@ -177,12 +179,12 @@ static void cgx_notify_pfs(struct cgx_link_event *event, struct rvu *rvu)
 		}
 
 		/* Send mbox message to PF */
-		msg = otx2_mbox_alloc_msg_CGX_LINK_EVENT(rvu, pfid);
+		msg = otx2_mbox_alloc_msg_cgx_link_event(rvu, pfid);
 		if (!msg)
 			continue;
 		msg->link_info = *linfo;
-		otx2_mbox_msg_send(&rvu->mbox_up, pfid);
-		err = otx2_mbox_wait_for_rsp(&rvu->mbox_up, pfid);
+		otx2_mbox_msg_send(&rvu->afpf_wq_info.mbox_up, pfid);
+		err = otx2_mbox_wait_for_rsp(&rvu->afpf_wq_info.mbox_up, pfid);
 		if (err)
 			dev_warn(rvu->dev, "notification to pf %d failed\n",
 				 pfid);
@@ -216,7 +218,7 @@ static void cgx_evhandler_task(struct work_struct *work)
 	} while (1);
 }
 
-static void cgx_lmac_event_handler_init(struct rvu *rvu)
+static int cgx_lmac_event_handler_init(struct rvu *rvu)
 {
 	struct cgx_event_cb cb;
 	int cgx, lmac, err;
@@ -228,14 +230,16 @@ static void cgx_lmac_event_handler_init(struct rvu *rvu)
 	rvu->cgx_evh_wq = alloc_workqueue("rvu_evh_wq", 0, 0);
 	if (!rvu->cgx_evh_wq) {
 		dev_err(rvu->dev, "alloc workqueue failed");
-		return;
+		return -ENOMEM;
 	}
 
 	cb.notify_link_chg = cgx_lmac_postevent; /* link change call back */
 	cb.data = rvu;
 
-	for (cgx = 0; cgx < rvu->cgx_cnt; cgx++) {
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
 		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
 		for (lmac = 0; lmac < cgx_get_lmac_cnt(cgxd); lmac++) {
 			err = cgx_lmac_evh_register(&cb, cgxd, lmac);
 			if (err)
@@ -244,9 +248,11 @@ static void cgx_lmac_event_handler_init(struct rvu *rvu)
 					cgx, lmac);
 		}
 	}
+
+	return 0;
 }
 
-void rvu_cgx_wq_destroy(struct rvu *rvu)
+static void rvu_cgx_wq_destroy(struct rvu *rvu)
 {
 	if (rvu->cgx_evh_wq) {
 		flush_workqueue(rvu->cgx_evh_wq);
@@ -255,25 +261,28 @@ void rvu_cgx_wq_destroy(struct rvu *rvu)
 	}
 }
 
-int rvu_cgx_probe(struct rvu *rvu)
+int rvu_cgx_init(struct rvu *rvu)
 {
-	int i, err;
+	int cgx, err;
+	void *cgxd;
 
-	/* find available cgx ports */
-	rvu->cgx_cnt = cgx_get_cgx_cnt();
-	if (!rvu->cgx_cnt) {
+	/* CGX port id starts from 0 and are not necessarily contiguous
+	 * Hence we allocate resources based on the maximum port id value.
+	 */
+	rvu->cgx_cnt_max = cgx_get_cgxcnt_max();
+	if (!rvu->cgx_cnt_max) {
 		dev_info(rvu->dev, "No CGX devices found!\n");
 		return -ENODEV;
 	}
 
-	rvu->cgx_idmap = devm_kzalloc(rvu->dev, rvu->cgx_cnt * sizeof(void *),
-				      GFP_KERNEL);
+	rvu->cgx_idmap = devm_kzalloc(rvu->dev, rvu->cgx_cnt_max *
+				      sizeof(void *), GFP_KERNEL);
 	if (!rvu->cgx_idmap)
 		return -ENOMEM;
 
 	/* Initialize the cgxdata table */
-	for (i = 0; i < rvu->cgx_cnt; i++)
-		rvu->cgx_idmap[i] = cgx_get_pdata(i);
+	for (cgx = 0; cgx < rvu->cgx_cnt_max; cgx++)
+		rvu->cgx_idmap[cgx] = cgx_get_pdata(cgx);
 
 	/* Map CGX LMAC interfaces to RVU PFs */
 	err = rvu_map_cgx_lmac_pf(rvu);
@@ -281,7 +290,47 @@ int rvu_cgx_probe(struct rvu *rvu)
 		return err;
 
 	/* Register for CGX events */
-	cgx_lmac_event_handler_init(rvu);
+	err = cgx_lmac_event_handler_init(rvu);
+	if (err)
+		return err;
+
+	/* Ensure event handler registration is completed, before
+	 * we turn on the links
+	 */
+	mb();
+
+	/* Do link up for all CGX ports */
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
+		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
+		err = cgx_lmac_linkup_start(cgxd);
+		if (err)
+			dev_err(rvu->dev,
+				"Link up process failed to start on cgx %d\n",
+				cgx);
+	}
+
+	return 0;
+}
+
+int rvu_cgx_exit(struct rvu *rvu)
+{
+	int cgx, lmac;
+	void *cgxd;
+
+	for (cgx = 0; cgx <= rvu->cgx_cnt_max; cgx++) {
+		cgxd = rvu_cgx_pdata(cgx, rvu);
+		if (!cgxd)
+			continue;
+		for (lmac = 0; lmac < cgx_get_lmac_cnt(cgxd); lmac++)
+			cgx_lmac_evh_unregister(cgxd, lmac);
+	}
+
+	/* Ensure event handler unregister is completed */
+	mb();
+
+	rvu_cgx_wq_destroy(rvu);
 	return 0;
 }
 
@@ -303,21 +352,21 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_START_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_rxtx(struct rvu *rvu, struct msg_req *req,
 				    struct msg_rsp *rsp)
 {
 	rvu_cgx_config_rxtx(rvu, req->hdr.pcifunc, true);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_STOP_RXTX(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
 	rvu_cgx_config_rxtx(rvu, req->hdr.pcifunc, false);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_STATS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stats(struct rvu *rvu, struct msg_req *req,
 			       struct cgx_stats_rsp *rsp)
 {
 	int pf = rvu_get_pf(req->hdr.pcifunc);
@@ -354,7 +403,7 @@ int rvu_mbox_handler_CGX_STATS(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_MAC_ADDR_SET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
@@ -368,7 +417,7 @@ int rvu_mbox_handler_CGX_MAC_ADDR_SET(struct rvu *rvu,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_MAC_ADDR_GET(struct rvu *rvu,
+int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
@@ -387,7 +436,7 @@ int rvu_mbox_handler_CGX_MAC_ADDR_GET(struct rvu *rvu,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_PROMISC_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
@@ -407,7 +456,7 @@ int rvu_mbox_handler_CGX_PROMISC_ENABLE(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_PROMISC_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
@@ -451,21 +500,21 @@ static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en)
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_START_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_start_linkevents(struct rvu *rvu, struct msg_req *req,
 					  struct msg_rsp *rsp)
 {
 	rvu_cgx_config_linkevents(rvu, req->hdr.pcifunc, true);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_STOP_LINKEVENTS(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_stop_linkevents(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp)
 {
 	rvu_cgx_config_linkevents(rvu, req->hdr.pcifunc, false);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_GET_LINKINFO(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req,
 				      struct cgx_link_info_msg *rsp)
 {
 	u8 cgx_id, lmac_id;
@@ -500,14 +549,14 @@ static int rvu_cgx_config_intlbk(struct rvu *rvu, u16 pcifunc, bool en)
 					  lmac_id, en);
 }
 
-int rvu_mbox_handler_CGX_INTLBK_ENABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_enable(struct rvu *rvu, struct msg_req *req,
 				       struct msg_rsp *rsp)
 {
 	rvu_cgx_config_intlbk(rvu, req->hdr.pcifunc, true);
 	return 0;
 }
 
-int rvu_mbox_handler_CGX_INTLBK_DISABLE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp)
 {
 	rvu_cgx_config_intlbk(rvu, req->hdr.pcifunc, false);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index a5ab7eff2301..4a7609fd6dd0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -43,6 +43,19 @@ enum mc_buf_cnt {
 	MC_BUF_CNT_2048,
 };
 
+enum nix_makr_fmt_indexes {
+	NIX_MARK_CFG_IP_DSCP_RED,
+	NIX_MARK_CFG_IP_DSCP_YELLOW,
+	NIX_MARK_CFG_IP_DSCP_YELLOW_RED,
+	NIX_MARK_CFG_IP_ECN_RED,
+	NIX_MARK_CFG_IP_ECN_YELLOW,
+	NIX_MARK_CFG_IP_ECN_YELLOW_RED,
+	NIX_MARK_CFG_VLAN_DEI_RED,
+	NIX_MARK_CFG_VLAN_DEI_YELLOW,
+	NIX_MARK_CFG_VLAN_DEI_YELLOW_RED,
+	NIX_MARK_CFG_MAX,
+};
+
 /* For now considering MC resources needed for broadcast
  * pkt replication only. i.e 256 HWVFs + 12 PFs.
  */
@@ -55,6 +68,17 @@ struct mce {
 	u16			pcifunc;
 };
 
+bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return false;
+	return true;
+}
+
 int rvu_get_nixlf_count(struct rvu *rvu)
 {
 	struct rvu_block *block;
@@ -94,11 +118,29 @@ static inline struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr)
 	return NULL;
 }
 
+static void nix_rx_sync(struct rvu *rvu, int blkaddr)
+{
+	int err;
+
+	/*Sync all in flight RX packets to LLC/DRAM */
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0));
+	err = rvu_poll_reg(rvu, blkaddr, NIX_AF_RX_SW_SYNC, BIT_ULL(0), true);
+	if (err)
+		dev_err(rvu->dev, "NIX RX software sync failed\n");
+
+	/* As per a HW errata in 9xxx A0 silicon, HW may clear SW_SYNC[ENA]
+	 * bit too early. Hence wait for 50us more.
+	 */
+	if (is_rvu_9xxx_A0(rvu))
+		usleep_range(50, 60);
+}
+
 static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 			    int lvl, u16 pcifunc, u16 schq)
 {
 	struct nix_txsch *txsch;
 	struct nix_hw *nix_hw;
+	u16 map_func;
 
 	nix_hw = get_nix_hw(rvu->hw, blkaddr);
 	if (!nix_hw)
@@ -109,12 +151,19 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 	if (schq >= txsch->schq.max)
 		return false;
 
-	spin_lock(&rvu->rsrc_lock);
-	if (txsch->pfvf_map[schq] != pcifunc) {
-		spin_unlock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
+	map_func = TXSCH_MAP_FUNC(txsch->pfvf_map[schq]);
+	mutex_unlock(&rvu->rsrc_lock);
+
+	/* For TL1 schq, sharing across VF's of same PF is ok */
+	if (lvl == NIX_TXSCH_LVL_TL1 &&
+	    rvu_get_pf(map_func) != rvu_get_pf(pcifunc))
 		return false;
-	}
-	spin_unlock(&rvu->rsrc_lock);
+
+	if (lvl != NIX_TXSCH_LVL_TL1 &&
+	    map_func != pcifunc)
+		return false;
+
 	return true;
 }
 
@@ -122,7 +171,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	u8 cgx_id, lmac_id;
-	int pkind, pf;
+	int pkind, pf, vf;
 	int err;
 
 	pf = rvu_get_pf(pcifunc);
@@ -148,6 +197,14 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 		rvu_npc_set_pkind(rvu, pkind, pfvf);
 		break;
 	case NIX_INTF_TYPE_LBK:
+		vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1;
+		pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(0, vf);
+		pfvf->tx_chan_base = vf & 0x1 ? NIX_CHAN_LBK_CHX(0, vf - 1) :
+						NIX_CHAN_LBK_CHX(0, vf + 1);
+		pfvf->rx_chan_cnt = 1;
+		pfvf->tx_chan_cnt = 1;
+		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
+					      pfvf->rx_chan_base, false);
 		break;
 	}
 
@@ -168,14 +225,21 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf)
 
 	rvu_npc_install_bcast_match_entry(rvu, pcifunc,
 					  nixlf, pfvf->rx_chan_base);
+	pfvf->maxlen = NIC_HW_MIN_FRS;
+	pfvf->minlen = NIC_HW_MIN_FRS;
 
 	return 0;
 }
 
 static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	int err;
 
+	pfvf->maxlen = 0;
+	pfvf->minlen = 0;
+	pfvf->rxvlan = false;
+
 	/* Remove this PF_FUNC from bcast pkt replication list */
 	err = nix_update_bcast_mce_list(rvu, pcifunc, false);
 	if (err) {
@@ -234,17 +298,21 @@ static void nix_setup_lso_tso_l4(struct rvu *rvu, int blkaddr,
 	/* TCP's flags field */
 	field.layer = NIX_TXLAYER_OL4;
 	field.offset = 12;
-	field.sizem1 = 0; /* not needed */
+	field.sizem1 = 1; /* 2 bytes */
 	field.alg = NIX_LSOALG_TCP_FLAGS;
 	rvu_write64(rvu, blkaddr,
 		    NIX_AF_LSO_FORMATX_FIELDX(format, (*fidx)++),
 		    *(u64 *)&field);
 }
 
-static void nix_setup_lso(struct rvu *rvu, int blkaddr)
+static void nix_setup_lso(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 {
 	u64 cfg, idx, fidx = 0;
 
+	/* Get max HW supported format indices */
+	cfg = (rvu_read64(rvu, blkaddr, NIX_AF_CONST1) >> 48) & 0xFF;
+	nix_hw->lso.total = cfg;
+
 	/* Enable LSO */
 	cfg = rvu_read64(rvu, blkaddr, NIX_AF_LSO_CFG);
 	/* For TSO, set first and middle segment flags to
@@ -254,7 +322,10 @@ static void nix_setup_lso(struct rvu *rvu, int blkaddr)
 	cfg |= (0xFFF2ULL << 32) | (0xFFF2ULL << 16);
 	rvu_write64(rvu, blkaddr, NIX_AF_LSO_CFG, cfg | BIT_ULL(63));
 
-	/* Configure format fields for TCPv4 segmentation offload */
+	/* Setup default static LSO formats
+	 *
+	 * Configure format fields for TCPv4 segmentation offload
+	 */
 	idx = NIX_LSO_FORMAT_IDX_TSOV4;
 	nix_setup_lso_tso_l3(rvu, blkaddr, idx, true, &fidx);
 	nix_setup_lso_tso_l4(rvu, blkaddr, idx, &fidx);
@@ -264,6 +335,7 @@ static void nix_setup_lso(struct rvu *rvu, int blkaddr)
 		rvu_write64(rvu, blkaddr,
 			    NIX_AF_LSO_FORMATX_FIELDX(idx, fidx), 0x0ULL);
 	}
+	nix_hw->lso.in_use++;
 
 	/* Configure format fields for TCPv6 segmentation offload */
 	idx = NIX_LSO_FORMAT_IDX_TSOV6;
@@ -276,6 +348,7 @@ static void nix_setup_lso(struct rvu *rvu, int blkaddr)
 		rvu_write64(rvu, blkaddr,
 			    NIX_AF_LSO_FORMATX_FIELDX(idx, fidx), 0x0ULL);
 	}
+	nix_hw->lso.in_use++;
 }
 
 static void nix_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
@@ -388,9 +461,8 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 	bool ena;
 	u64 cfg;
 
-	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
-	if (!pfvf->nixlf || blkaddr < 0)
+	if (blkaddr < 0)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	block = &hw->block[blkaddr];
@@ -400,9 +472,14 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 		return NIX_AF_ERR_AQ_ENQUEUE;
 	}
 
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	nixlf = rvu_get_lf(rvu, block, pcifunc, 0);
-	if (nixlf < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
+
+	/* Skip NIXLF check for broadcast MCE entry init */
+	if (!(!rsp && req->ctype == NIX_AQ_CTYPE_MCE)) {
+		if (!pfvf->nixlf || nixlf < 0)
+			return NIX_AF_ERR_AF_LF_INVALID;
+	}
 
 	switch (req->ctype) {
 	case NIX_AQ_CTYPE_RQ:
@@ -447,7 +524,9 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 
 	/* Check if SQ pointed SMQ belongs to this PF/VF or not */
 	if (req->ctype == NIX_AQ_CTYPE_SQ &&
-	    req->op != NIX_AQ_INSTOP_WRITE) {
+	    ((req->op == NIX_AQ_INSTOP_INIT && req->sq.ena) ||
+	     (req->op == NIX_AQ_INSTOP_WRITE &&
+	      req->sq_mask.ena && req->sq_mask.smq && req->sq.ena))) {
 		if (!is_valid_txschq(rvu, blkaddr, NIX_TXSCH_LVL_SMQ,
 				     pcifunc, req->sq.smq))
 			return NIX_AF_ERR_AQ_ENQUEUE;
@@ -637,25 +716,25 @@ static int nix_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 	return err;
 }
 
-int rvu_mbox_handler_NIX_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_nix_aq_enq(struct rvu *rvu,
 				struct nix_aq_enq_req *req,
 				struct nix_aq_enq_rsp *rsp)
 {
 	return rvu_nix_aq_enq_inst(rvu, req, rsp);
 }
 
-int rvu_mbox_handler_NIX_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_nix_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp)
 {
 	return nix_lf_hwctx_disable(rvu, req);
 }
 
-int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 				  struct nix_lf_alloc_req *req,
 				  struct nix_lf_alloc_rsp *rsp)
 {
-	int nixlf, qints, hwctx_size, err, rc = 0;
+	int nixlf, qints, hwctx_size, intf, err, rc = 0;
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
 	struct rvu_block *block;
@@ -676,6 +755,24 @@ int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
 	if (nixlf < 0)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
+	/* Check if requested 'NIXLF <=> NPALF' mapping is valid */
+	if (req->npa_func) {
+		/* If default, use 'this' NIXLF's PFFUNC */
+		if (req->npa_func == RVU_DEFAULT_PF_FUNC)
+			req->npa_func = pcifunc;
+		if (!is_pffunc_map_valid(rvu, req->npa_func, BLKTYPE_NPA))
+			return NIX_AF_INVAL_NPA_PF_FUNC;
+	}
+
+	/* Check if requested 'NIXLF <=> SSOLF' mapping is valid */
+	if (req->sso_func) {
+		/* If default, use 'this' NIXLF's PFFUNC */
+		if (req->sso_func == RVU_DEFAULT_PF_FUNC)
+			req->sso_func = pcifunc;
+		if (!is_pffunc_map_valid(rvu, req->sso_func, BLKTYPE_SSO))
+			return NIX_AF_INVAL_SSO_PF_FUNC;
+	}
+
 	/* If RSS is being enabled, check if requested config is valid.
 	 * RSS table size should be power of two, otherwise
 	 * RSS_GRP::OFFSET + adder might go beyond that group or
@@ -777,21 +874,20 @@ int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
 		    (u64)pfvf->nix_qints_ctx->iova);
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_QINTS_CFG(nixlf), BIT_ULL(36));
 
+	/* Setup VLANX TPID's.
+	 * Use VLAN1 for 802.1Q
+	 * and VLAN0 for 802.1AD.
+	 */
+	cfg = (0x8100ULL << 16) | 0x88A8ULL;
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG(nixlf), cfg);
+
 	/* Enable LMTST for this NIX LF */
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_TX_CFG2(nixlf), BIT_ULL(0));
 
-	/* Set CQE/WQE size, NPA_PF_FUNC for SQBs and also SSO_PF_FUNC
-	 * If requester has sent a 'RVU_DEFAULT_PF_FUNC' use this NIX LF's
-	 * PCIFUNC itself.
-	 */
-	if (req->npa_func == RVU_DEFAULT_PF_FUNC)
-		cfg = pcifunc;
-	else
+	/* Set CQE/WQE size, NPA_PF_FUNC for SQBs and also SSO_PF_FUNC */
+	if (req->npa_func)
 		cfg = req->npa_func;
-
-	if (req->sso_func == RVU_DEFAULT_PF_FUNC)
-		cfg |= (u64)pcifunc << 16;
-	else
+	if (req->sso_func)
 		cfg |= (u64)req->sso_func << 16;
 
 	cfg |= (u64)req->xqe_sz << 33;
@@ -800,10 +896,14 @@ int rvu_mbox_handler_NIX_LF_ALLOC(struct rvu *rvu,
 	/* Config Rx pkt length, csum checks and apad  enable / disable */
 	rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf), req->rx_cfg);
 
-	err = nix_interface_init(rvu, pcifunc, NIX_INTF_TYPE_CGX, nixlf);
+	intf = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
+	err = nix_interface_init(rvu, pcifunc, intf, nixlf);
 	if (err)
 		goto free_mem;
 
+	/* Disable NPC entries as NIXLF's contexts are not initialized yet */
+	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+
 	goto exit;
 
 free_mem:
@@ -823,10 +923,18 @@ exit:
 	rsp->tx_chan_cnt = pfvf->tx_chan_cnt;
 	rsp->lso_tsov4_idx = NIX_LSO_FORMAT_IDX_TSOV4;
 	rsp->lso_tsov6_idx = NIX_LSO_FORMAT_IDX_TSOV6;
+	/* Get HW supported stat count */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST1);
+	rsp->lf_rx_stats = ((cfg >> 32) & 0xFF);
+	rsp->lf_tx_stats = ((cfg >> 24) & 0xFF);
+	/* Get count of CQ IRQs and error IRQs supported per LF */
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2);
+	rsp->qints = ((cfg >> 12) & 0xFFF);
+	rsp->cints = ((cfg >> 24) & 0xFFF);
 	return rc;
 }
 
-int rvu_mbox_handler_NIX_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_nix_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -860,6 +968,41 @@ int rvu_mbox_handler_NIX_LF_FREE(struct rvu *rvu, struct msg_req *req,
 	return 0;
 }
 
+int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
+					 struct nix_mark_format_cfg  *req,
+					 struct nix_mark_format_cfg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
+	int blkaddr, rc;
+	u32 cfg;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	cfg = (((u32)req->offset & 0x7) << 16) |
+	      (((u32)req->y_mask & 0xF) << 12) |
+	      (((u32)req->y_val & 0xF) << 8) |
+	      (((u32)req->r_mask & 0xF) << 4) | ((u32)req->r_val & 0xF);
+
+	rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfg);
+	if (rc < 0) {
+		dev_err(rvu->dev, "No mark_format_ctl for (pf:%d, vf:%d)",
+			rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
+		return NIX_AF_ERR_MARK_CFG_FAIL;
+	}
+
+	rsp->mark_format_idx = rc;
+	return 0;
+}
+
 /* Disable shaping of pkts by a scheduler queue
  * at a given scheduler level.
  */
@@ -918,7 +1061,74 @@ static void nix_reset_tx_linkcfg(struct rvu *rvu, int blkaddr,
 			    NIX_AF_TL3_TL2X_LINKX_CFG(schq, link), 0x00);
 }
 
-int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
+static int
+rvu_get_tl1_schqs(struct rvu *rvu, int blkaddr, u16 pcifunc,
+		  u16 *schq_list, u16 *schq_cnt)
+{
+	struct nix_txsch *txsch;
+	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
+	u8 cgx_id, lmac_id;
+	u16 schq_base;
+	u32 *pfvf_map;
+	int pf, intf;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -ENODEV;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL1];
+	pfvf_map = txsch->pfvf_map;
+	pf = rvu_get_pf(pcifunc);
+
+	/* static allocation as two TL1's per link */
+	intf = is_afvf(pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
+
+	switch (intf) {
+	case NIX_INTF_TYPE_CGX:
+		rvu_get_cgx_lmac_id(pfvf->cgx_lmac, &cgx_id, &lmac_id);
+		schq_base = (cgx_id * MAX_LMAC_PER_CGX + lmac_id) * 2;
+		break;
+	case NIX_INTF_TYPE_LBK:
+		schq_base = rvu->cgx_cnt_max * MAX_LMAC_PER_CGX * 2;
+		break;
+	default:
+		return -ENODEV;
+	}
+
+	if (schq_base + 1 > txsch->schq.max)
+		return -ENODEV;
+
+	/* init pfvf_map as we store flags */
+	if (pfvf_map[schq_base] == U32_MAX) {
+		pfvf_map[schq_base] =
+			TXSCH_MAP((pf << RVU_PFVF_PF_SHIFT), 0);
+		pfvf_map[schq_base + 1] =
+			TXSCH_MAP((pf << RVU_PFVF_PF_SHIFT), 0);
+
+		/* Onetime reset for TL1 */
+		nix_reset_tx_linkcfg(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base);
+		nix_reset_tx_shaping(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base);
+
+		nix_reset_tx_linkcfg(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base + 1);
+		nix_reset_tx_shaping(rvu, blkaddr,
+				     NIX_TXSCH_LVL_TL1, schq_base + 1);
+	}
+
+	if (schq_list && schq_cnt) {
+		schq_list[0] = schq_base;
+		schq_list[1] = schq_base + 1;
+		*schq_cnt = 2;
+	}
+
+	return 0;
+}
+
+int rvu_mbox_handler_nix_txsch_alloc(struct rvu *rvu,
 				     struct nix_txsch_alloc_req *req,
 				     struct nix_txsch_alloc_rsp *rsp)
 {
@@ -928,6 +1138,7 @@ int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
 	struct rvu_pfvf *pfvf;
 	struct nix_hw *nix_hw;
 	int blkaddr, rc = 0;
+	u32 *pfvf_map;
 	u16 schq;
 
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
@@ -939,17 +1150,27 @@ int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
 	if (!nix_hw)
 		return -EINVAL;
 
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		txsch = &nix_hw->txsch[lvl];
 		req_schq = req->schq_contig[lvl] + req->schq[lvl];
+		pfvf_map = txsch->pfvf_map;
+
+		if (!req_schq)
+			continue;
 
 		/* There are only 28 TL1s */
-		if (lvl == NIX_TXSCH_LVL_TL1 && req_schq > txsch->schq.max)
-			goto err;
+		if (lvl == NIX_TXSCH_LVL_TL1) {
+			if (req->schq_contig[lvl] ||
+			    req->schq[lvl] > 2 ||
+			    rvu_get_tl1_schqs(rvu, blkaddr,
+					      pcifunc, NULL, NULL))
+				goto err;
+			continue;
+		}
 
 		/* Check if request is valid */
-		if (!req_schq || req_schq > MAX_TXSCHQ_PER_FUNC)
+		if (req_schq > MAX_TXSCHQ_PER_FUNC)
 			goto err;
 
 		/* If contiguous queues are needed, check for availability */
@@ -965,16 +1186,32 @@ int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		txsch = &nix_hw->txsch[lvl];
 		rsp->schq_contig[lvl] = req->schq_contig[lvl];
+		pfvf_map = txsch->pfvf_map;
 		rsp->schq[lvl] = req->schq[lvl];
 
-		schq = 0;
+		if (!req->schq[lvl] && !req->schq_contig[lvl])
+			continue;
+
+		/* Handle TL1 specially as it is
+		 * allocation is restricted to 2 TL1's
+		 * per link
+		 */
+
+		if (lvl == NIX_TXSCH_LVL_TL1) {
+			rsp->schq_contig[lvl] = 0;
+			rvu_get_tl1_schqs(rvu, blkaddr, pcifunc,
+					  &rsp->schq_list[lvl][0],
+					  &rsp->schq[lvl]);
+			continue;
+		}
+
 		/* Alloc contiguous queues first */
 		if (req->schq_contig[lvl]) {
 			schq = rvu_alloc_rsrc_contig(&txsch->schq,
 						     req->schq_contig[lvl]);
 
 			for (idx = 0; idx < req->schq_contig[lvl]; idx++) {
-				txsch->pfvf_map[schq] = pcifunc;
+				pfvf_map[schq] = TXSCH_MAP(pcifunc, 0);
 				nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
 				nix_reset_tx_shaping(rvu, blkaddr, lvl, schq);
 				rsp->schq_contig_list[lvl][idx] = schq;
@@ -985,7 +1222,7 @@ int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
 		/* Alloc non-contiguous queues */
 		for (idx = 0; idx < req->schq[lvl]; idx++) {
 			schq = rvu_alloc_rsrc(&txsch->schq);
-			txsch->pfvf_map[schq] = pcifunc;
+			pfvf_map[schq] = TXSCH_MAP(pcifunc, 0);
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
 			nix_reset_tx_shaping(rvu, blkaddr, lvl, schq);
 			rsp->schq_list[lvl][idx] = schq;
@@ -995,7 +1232,7 @@ int rvu_mbox_handler_NIX_TXSCH_ALLOC(struct rvu *rvu,
 err:
 	rc = NIX_AF_ERR_TLX_ALLOC_FAIL;
 exit:
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 	return rc;
 }
 
@@ -1020,14 +1257,14 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	/* Disable TL2/3 queue links before SMQ flush*/
-	spin_lock(&rvu->rsrc_lock);
+	mutex_lock(&rvu->rsrc_lock);
 	for (lvl = NIX_TXSCH_LVL_TL4; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
 		if (lvl != NIX_TXSCH_LVL_TL2 && lvl != NIX_TXSCH_LVL_TL4)
 			continue;
 
 		txsch = &nix_hw->txsch[lvl];
 		for (schq = 0; schq < txsch->schq.max; schq++) {
-			if (txsch->pfvf_map[schq] != pcifunc)
+			if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 				continue;
 			nix_reset_tx_linkcfg(rvu, blkaddr, lvl, schq);
 		}
@@ -1036,7 +1273,7 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 	/* Flush SMQs */
 	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
 	for (schq = 0; schq < txsch->schq.max; schq++) {
-		if (txsch->pfvf_map[schq] != pcifunc)
+		if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 			continue;
 		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
 		/* Do SMQ flush and set enqueue xoff */
@@ -1054,15 +1291,21 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 
 	/* Now free scheduler queues to free pool */
 	for (lvl = 0; lvl < NIX_TXSCH_LVL_CNT; lvl++) {
+		/* Free all SCHQ's except TL1 as
+		 * TL1 is shared across all VF's for a RVU PF
+		 */
+		if (lvl == NIX_TXSCH_LVL_TL1)
+			continue;
+
 		txsch = &nix_hw->txsch[lvl];
 		for (schq = 0; schq < txsch->schq.max; schq++) {
-			if (txsch->pfvf_map[schq] != pcifunc)
+			if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
 				continue;
 			rvu_free_rsrc(&txsch->schq, schq);
 			txsch->pfvf_map[schq] = 0;
 		}
 	}
-	spin_unlock(&rvu->rsrc_lock);
+	mutex_unlock(&rvu->rsrc_lock);
 
 	/* Sync cached info for this LF in NDC-TX to LLC/DRAM */
 	rvu_write64(rvu, blkaddr, NIX_AF_NDC_TX_SYNC, BIT_ULL(12) | nixlf);
@@ -1073,11 +1316,81 @@ static int nix_txschq_free(struct rvu *rvu, u16 pcifunc)
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_TXSCH_FREE(struct rvu *rvu,
+static int nix_txschq_free_one(struct rvu *rvu,
+			       struct nix_txsch_free_req *req)
+{
+	int lvl, schq, nixlf, blkaddr, rc;
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_txsch *txsch;
+	struct nix_hw *nix_hw;
+	u32 *pfvf_map;
+	u64 cfg;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	lvl = req->schq_lvl;
+	schq = req->schq;
+	txsch = &nix_hw->txsch[lvl];
+
+	/* Don't allow freeing TL1 */
+	if (lvl > NIX_TXSCH_LVL_TL2 ||
+	    schq >= txsch->schq.max)
+		goto err;
+
+	pfvf_map = txsch->pfvf_map;
+	mutex_lock(&rvu->rsrc_lock);
+
+	if (TXSCH_MAP_FUNC(pfvf_map[schq]) != pcifunc) {
+		mutex_unlock(&rvu->rsrc_lock);
+		goto err;
+	}
+
+	/* Flush if it is a SMQ. Onus of disabling
+	 * TL2/3 queue links before SMQ flush is on user
+	 */
+	if (lvl == NIX_TXSCH_LVL_SMQ) {
+		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
+		/* Do SMQ flush and set enqueue xoff */
+		cfg |= BIT_ULL(50) | BIT_ULL(49);
+		rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg);
+
+		/* Wait for flush to complete */
+		rc = rvu_poll_reg(rvu, blkaddr,
+				  NIX_AF_SMQX_CFG(schq), BIT_ULL(49), true);
+		if (rc) {
+			dev_err(rvu->dev,
+				"NIXLF%d: SMQ%d flush failed\n", nixlf, schq);
+		}
+	}
+
+	/* Free the resource */
+	rvu_free_rsrc(&txsch->schq, schq);
+	txsch->pfvf_map[schq] = 0;
+	mutex_unlock(&rvu->rsrc_lock);
+	return 0;
+err:
+	return NIX_AF_ERR_TLX_INVALID;
+}
+
+int rvu_mbox_handler_nix_txsch_free(struct rvu *rvu,
 				    struct nix_txsch_free_req *req,
 				    struct msg_rsp *rsp)
 {
-	return nix_txschq_free(rvu, req->hdr.pcifunc);
+	if (req->flags & TXSCHQ_FREE_ALL)
+		return nix_txschq_free(rvu, req->hdr.pcifunc);
+	else
+		return nix_txschq_free_one(rvu, req);
 }
 
 static bool is_txschq_config_valid(struct rvu *rvu, u16 pcifunc, int blkaddr,
@@ -1118,16 +1431,73 @@ static bool is_txschq_config_valid(struct rvu *rvu, u16 pcifunc, int blkaddr,
 	return true;
 }
 
-int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
+static int
+nix_tl1_default_cfg(struct rvu *rvu, u16 pcifunc)
+{
+	u16 schq_list[2], schq_cnt, schq;
+	int blkaddr, idx, err = 0;
+	u16 map_func, map_flags;
+	struct nix_hw *nix_hw;
+	u64 reg, regval;
+	u32 *pfvf_map;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	pfvf_map = nix_hw->txsch[NIX_TXSCH_LVL_TL1].pfvf_map;
+
+	mutex_lock(&rvu->rsrc_lock);
+
+	err = rvu_get_tl1_schqs(rvu, blkaddr,
+				pcifunc, schq_list, &schq_cnt);
+	if (err)
+		goto unlock;
+
+	for (idx = 0; idx < schq_cnt; idx++) {
+		schq = schq_list[idx];
+		map_func = TXSCH_MAP_FUNC(pfvf_map[schq]);
+		map_flags = TXSCH_MAP_FLAGS(pfvf_map[schq]);
+
+		/* check if config is already done or this is pf */
+		if (map_flags & NIX_TXSCHQ_TL1_CFG_DONE)
+			continue;
+
+		/* default configuration */
+		reg = NIX_AF_TL1X_TOPOLOGY(schq);
+		regval = (TXSCH_TL1_DFLT_RR_PRIO << 1);
+		rvu_write64(rvu, blkaddr, reg, regval);
+		reg = NIX_AF_TL1X_SCHEDULE(schq);
+		regval = TXSCH_TL1_DFLT_RR_QTM;
+		rvu_write64(rvu, blkaddr, reg, regval);
+		reg = NIX_AF_TL1X_CIR(schq);
+		regval = 0;
+		rvu_write64(rvu, blkaddr, reg, regval);
+
+		map_flags |= NIX_TXSCHQ_TL1_CFG_DONE;
+		pfvf_map[schq] = TXSCH_MAP(map_func, map_flags);
+	}
+unlock:
+	mutex_unlock(&rvu->rsrc_lock);
+	return err;
+}
+
+int rvu_mbox_handler_nix_txschq_cfg(struct rvu *rvu,
 				    struct nix_txschq_config *req,
 				    struct msg_rsp *rsp)
 {
+	u16 schq, pcifunc = req->hdr.pcifunc;
 	struct rvu_hwinfo *hw = rvu->hw;
-	u16 pcifunc = req->hdr.pcifunc;
 	u64 reg, regval, schq_regbase;
 	struct nix_txsch *txsch;
+	u16 map_func, map_flags;
 	struct nix_hw *nix_hw;
 	int blkaddr, idx, err;
+	u32 *pfvf_map;
 	int nixlf;
 
 	if (req->lvl >= NIX_TXSCH_LVL_CNT ||
@@ -1147,6 +1517,16 @@ int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
 		return NIX_AF_ERR_AF_LF_INVALID;
 
 	txsch = &nix_hw->txsch[req->lvl];
+	pfvf_map = txsch->pfvf_map;
+
+	/* VF is only allowed to trigger
+	 * setting default cfg on TL1
+	 */
+	if (pcifunc & RVU_PFVF_FUNC_MASK &&
+	    req->lvl == NIX_TXSCH_LVL_TL1) {
+		return nix_tl1_default_cfg(rvu, pcifunc);
+	}
+
 	for (idx = 0; idx < req->num_regs; idx++) {
 		reg = req->reg[idx];
 		regval = req->regval[idx];
@@ -1164,6 +1544,21 @@ int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
 			regval |= ((u64)nixlf << 24);
 		}
 
+		/* Mark config as done for TL1 by PF */
+		if (schq_regbase >= NIX_AF_TL1X_SCHEDULE(0) &&
+		    schq_regbase <= NIX_AF_TL1X_GREEN_BYTES(0)) {
+			schq = TXSCHQ_IDX(reg, TXSCHQ_IDX_SHIFT);
+
+			mutex_lock(&rvu->rsrc_lock);
+
+			map_func = TXSCH_MAP_FUNC(pfvf_map[schq]);
+			map_flags = TXSCH_MAP_FLAGS(pfvf_map[schq]);
+
+			map_flags |= NIX_TXSCHQ_TL1_CFG_DONE;
+			pfvf_map[schq] = TXSCH_MAP(map_func, map_flags);
+			mutex_unlock(&rvu->rsrc_lock);
+		}
+
 		rvu_write64(rvu, blkaddr, reg, regval);
 
 		/* Check for SMQ flush, if so, poll for its completion */
@@ -1181,35 +1576,22 @@ int rvu_mbox_handler_NIX_TXSCHQ_CFG(struct rvu *rvu,
 static int nix_rx_vtag_cfg(struct rvu *rvu, int nixlf, int blkaddr,
 			   struct nix_vtag_config *req)
 {
-	u64 regval = 0;
-
-#define NIX_VTAGTYPE_MAX 0x8ull
-#define NIX_VTAGSIZE_MASK 0x7ull
-#define NIX_VTAGSTRIP_CAP_MASK 0x30ull
+	u64 regval = req->vtag_size;
 
-	if (req->rx.vtag_type >= NIX_VTAGTYPE_MAX ||
-	    req->vtag_size > VTAGSIZE_T8)
+	if (req->rx.vtag_type > 7 || req->vtag_size > VTAGSIZE_T8)
 		return -EINVAL;
 
-	regval = rvu_read64(rvu, blkaddr,
-			    NIX_AF_LFX_RX_VTAG_TYPEX(nixlf, req->rx.vtag_type));
-
-	if (req->rx.strip_vtag && req->rx.capture_vtag)
-		regval |= BIT_ULL(4) | BIT_ULL(5);
-	else if (req->rx.strip_vtag)
+	if (req->rx.capture_vtag)
+		regval |= BIT_ULL(5);
+	if (req->rx.strip_vtag)
 		regval |= BIT_ULL(4);
-	else
-		regval &= ~(BIT_ULL(4) | BIT_ULL(5));
-
-	regval &= ~NIX_VTAGSIZE_MASK;
-	regval |= req->vtag_size & NIX_VTAGSIZE_MASK;
 
 	rvu_write64(rvu, blkaddr,
 		    NIX_AF_LFX_RX_VTAG_TYPEX(nixlf, req->rx.vtag_type), regval);
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_VTAG_CFG(struct rvu *rvu,
+int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu,
 				  struct nix_vtag_config *req,
 				  struct msg_rsp *rsp)
 {
@@ -1243,7 +1625,7 @@ static int nix_setup_mce(struct rvu *rvu, int mce, u8 op,
 	struct nix_aq_enq_req aq_req;
 	int err;
 
-	aq_req.hdr.pcifunc = pcifunc;
+	aq_req.hdr.pcifunc = 0;
 	aq_req.ctype = NIX_AQ_CTYPE_MCE;
 	aq_req.op = op;
 	aq_req.qidx = mce;
@@ -1294,7 +1676,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list,
 		return 0;
 
 	/* Add a new one to the list, at the tail */
-	mce = kzalloc(sizeof(*mce), GFP_ATOMIC);
+	mce = kzalloc(sizeof(*mce), GFP_KERNEL);
 	if (!mce)
 		return -ENOMEM;
 	mce->idx = idx;
@@ -1317,6 +1699,10 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 	struct rvu_pfvf *pfvf;
 	int blkaddr;
 
+	/* Broadcast pkt replication is not needed for AF's VFs, hence skip */
+	if (is_afvf(pcifunc))
+		return 0;
+
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
 		return 0;
@@ -1340,7 +1726,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 		return -EINVAL;
 	}
 
-	spin_lock(&mcast->mce_lock);
+	mutex_lock(&mcast->mce_lock);
 
 	err = nix_update_mce_list(mce_list, pcifunc, idx, add);
 	if (err)
@@ -1370,7 +1756,7 @@ static int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add)
 	}
 
 end:
-	spin_unlock(&mcast->mce_lock);
+	mutex_unlock(&mcast->mce_lock);
 	return err;
 }
 
@@ -1455,7 +1841,7 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 		    BIT_ULL(63) | (mcast->replay_pkind << 24) |
 		    BIT_ULL(20) | MC_BUF_CNT);
 
-	spin_lock_init(&mcast->mce_lock);
+	mutex_init(&mcast->mce_lock);
 
 	return nix_setup_bcast_tables(rvu, nix_hw);
 }
@@ -1499,14 +1885,66 @@ static int nix_setup_txschq(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr)
 		 * PF/VF pcifunc mapping info.
 		 */
 		txsch->pfvf_map = devm_kcalloc(rvu->dev, txsch->schq.max,
-					       sizeof(u16), GFP_KERNEL);
+					       sizeof(u32), GFP_KERNEL);
 		if (!txsch->pfvf_map)
 			return -ENOMEM;
+		memset(txsch->pfvf_map, U8_MAX, txsch->schq.max * sizeof(u32));
 	}
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_STATS_RST(struct rvu *rvu, struct msg_req *req,
+int rvu_nix_reserve_mark_format(struct rvu *rvu, struct nix_hw *nix_hw,
+				int blkaddr, u32 cfg)
+{
+	int fmt_idx;
+
+	for (fmt_idx = 0; fmt_idx < nix_hw->mark_format.in_use; fmt_idx++) {
+		if (nix_hw->mark_format.cfg[fmt_idx] == cfg)
+			return fmt_idx;
+	}
+	if (fmt_idx >= nix_hw->mark_format.total)
+		return -ERANGE;
+
+	rvu_write64(rvu, blkaddr, NIX_AF_MARK_FORMATX_CTL(fmt_idx), cfg);
+	nix_hw->mark_format.cfg[fmt_idx] = cfg;
+	nix_hw->mark_format.in_use++;
+	return fmt_idx;
+}
+
+static int nix_af_mark_format_setup(struct rvu *rvu, struct nix_hw *nix_hw,
+				    int blkaddr)
+{
+	u64 cfgs[] = {
+		[NIX_MARK_CFG_IP_DSCP_RED]         = 0x10003,
+		[NIX_MARK_CFG_IP_DSCP_YELLOW]      = 0x11200,
+		[NIX_MARK_CFG_IP_DSCP_YELLOW_RED]  = 0x11203,
+		[NIX_MARK_CFG_IP_ECN_RED]          = 0x6000c,
+		[NIX_MARK_CFG_IP_ECN_YELLOW]       = 0x60c00,
+		[NIX_MARK_CFG_IP_ECN_YELLOW_RED]   = 0x60c0c,
+		[NIX_MARK_CFG_VLAN_DEI_RED]        = 0x30008,
+		[NIX_MARK_CFG_VLAN_DEI_YELLOW]     = 0x30800,
+		[NIX_MARK_CFG_VLAN_DEI_YELLOW_RED] = 0x30808,
+	};
+	int i, rc;
+	u64 total;
+
+	total = (rvu_read64(rvu, blkaddr, NIX_AF_PSE_CONST) & 0xFF00) >> 8;
+	nix_hw->mark_format.total = (u8)total;
+	nix_hw->mark_format.cfg = devm_kcalloc(rvu->dev, total, sizeof(u32),
+					       GFP_KERNEL);
+	if (!nix_hw->mark_format.cfg)
+		return -ENOMEM;
+	for (i = 0; i < NIX_MARK_CFG_MAX; i++) {
+		rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfgs[i]);
+		if (rc < 0)
+			dev_err(rvu->dev, "Err %d in setup mark format %d\n",
+				i, rc);
+	}
+
+	return 0;
+}
+
+int rvu_mbox_handler_nix_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -1537,190 +1975,287 @@ int rvu_mbox_handler_NIX_STATS_RST(struct rvu *rvu, struct msg_req *req,
 }
 
 /* Returns the ALG index to be set into NPC_RX_ACTION */
-static int get_flowkey_alg_idx(u32 flow_cfg)
-{
-	u32 ip_cfg;
-
-	flow_cfg &= ~FLOW_KEY_TYPE_PORT;
-	ip_cfg = FLOW_KEY_TYPE_IPV4 | FLOW_KEY_TYPE_IPV6;
-	if (flow_cfg == ip_cfg)
-		return FLOW_KEY_ALG_IP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP))
-		return FLOW_KEY_ALG_TCP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_UDP))
-		return FLOW_KEY_ALG_UDP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_SCTP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_UDP))
-		return FLOW_KEY_ALG_TCP_UDP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_TCP_SCTP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_UDP_SCTP;
-	else if (flow_cfg == (ip_cfg | FLOW_KEY_TYPE_TCP |
-			      FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP))
-		return FLOW_KEY_ALG_TCP_UDP_SCTP;
-
-	return FLOW_KEY_ALG_PORT;
-}
-
-int rvu_mbox_handler_NIX_RSS_FLOWKEY_CFG(struct rvu *rvu,
-					 struct nix_rss_flowkey_cfg *req,
-					 struct msg_rsp *rsp)
+static int get_flowkey_alg_idx(struct nix_hw *nix_hw, u32 flow_cfg)
 {
-	struct rvu_hwinfo *hw = rvu->hw;
-	u16 pcifunc = req->hdr.pcifunc;
-	int alg_idx, nixlf, blkaddr;
-
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
-	if (blkaddr < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
-
-	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
-	if (nixlf < 0)
-		return NIX_AF_ERR_AF_LF_INVALID;
+	int i;
 
-	alg_idx = get_flowkey_alg_idx(req->flowkey_cfg);
+	/* Scan over exiting algo entries to find a match */
+	for (i = 0; i < nix_hw->flowkey.in_use; i++)
+		if (nix_hw->flowkey.flowkey[i] == flow_cfg)
+			return i;
 
-	rvu_npc_update_flowkey_alg_idx(rvu, pcifunc, nixlf, req->group,
-				       alg_idx, req->mcam_index);
-	return 0;
+	return -ERANGE;
 }
 
-static void set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
+static int set_flowkey_fields(struct nix_rx_flowkey_alg *alg, u32 flow_cfg)
 {
-	struct nix_rx_flowkey_alg *field = NULL;
-	int idx, key_type;
+	int idx, nr_field, key_off, field_marker, keyoff_marker;
+	int max_key_off, max_bit_pos, group_member;
+	struct nix_rx_flowkey_alg *field;
+	struct nix_rx_flowkey_alg tmp;
+	u32 key_type, valid_key;
 
 	if (!alg)
-		return;
+		return -EINVAL;
 
-	/* FIELD0: IPv4
-	 * FIELD1: IPv6
-	 * FIELD2: TCP/UDP/SCTP/ALL
-	 * FIELD3: Unused
-	 * FIELD4: Unused
-	 *
-	 * Each of the 32 possible flow key algorithm definitions should
+#define FIELDS_PER_ALG  5
+#define MAX_KEY_OFF	40
+	/* Clear all fields */
+	memset(alg, 0, sizeof(uint64_t) * FIELDS_PER_ALG);
+
+	/* Each of the 32 possible flow key algorithm definitions should
 	 * fall into above incremental config (except ALG0). Otherwise a
 	 * single NPC MCAM entry is not sufficient for supporting RSS.
 	 *
 	 * If a different definition or combination needed then NPC MCAM
 	 * has to be programmed to filter such pkts and it's action should
 	 * point to this definition to calculate flowtag or hash.
+	 *
+	 * The `for loop` goes over _all_ protocol field and the following
+	 * variables depicts the state machine forward progress logic.
+	 *
+	 * keyoff_marker - Enabled when hash byte length needs to be accounted
+	 * in field->key_offset update.
+	 * field_marker - Enabled when a new field needs to be selected.
+	 * group_member - Enabled when protocol is part of a group.
 	 */
-	for (idx = 0; idx < 32; idx++) {
-		key_type = flow_cfg & BIT_ULL(idx);
-		if (!key_type)
-			continue;
+
+	keyoff_marker = 0; max_key_off = 0; group_member = 0;
+	nr_field = 0; key_off = 0; field_marker = 1;
+	field = &tmp; max_bit_pos = fls(flow_cfg);
+	for (idx = 0;
+	     idx < max_bit_pos && nr_field < FIELDS_PER_ALG &&
+	     key_off < MAX_KEY_OFF; idx++) {
+		key_type = BIT(idx);
+		valid_key = flow_cfg & key_type;
+		/* Found a field marker, reset the field values */
+		if (field_marker)
+			memset(&tmp, 0, sizeof(tmp));
+
 		switch (key_type) {
-		case FLOW_KEY_TYPE_PORT:
-			field = &alg[0];
+		case NIX_FLOW_KEY_TYPE_PORT:
 			field->sel_chan = true;
 			/* This should be set to 1, when SEL_CHAN is set */
 			field->bytesm1 = 1;
+			field_marker = true;
+			keyoff_marker = true;
 			break;
-		case FLOW_KEY_TYPE_IPV4:
-			field = &alg[0];
+		case NIX_FLOW_KEY_TYPE_IPV4:
 			field->lid = NPC_LID_LC;
 			field->ltype_match = NPC_LT_LC_IP;
 			field->hdr_offset = 12; /* SIP offset */
 			field->bytesm1 = 7; /* SIP + DIP, 8 bytes */
 			field->ltype_mask = 0xF; /* Match only IPv4 */
+			field_marker = true;
+			keyoff_marker = false;
 			break;
-		case FLOW_KEY_TYPE_IPV6:
-			field = &alg[1];
+		case NIX_FLOW_KEY_TYPE_IPV6:
 			field->lid = NPC_LID_LC;
 			field->ltype_match = NPC_LT_LC_IP6;
 			field->hdr_offset = 8; /* SIP offset */
 			field->bytesm1 = 31; /* SIP + DIP, 32 bytes */
 			field->ltype_mask = 0xF; /* Match only IPv6 */
+			field_marker = true;
+			keyoff_marker = true;
 			break;
-		case FLOW_KEY_TYPE_TCP:
-		case FLOW_KEY_TYPE_UDP:
-		case FLOW_KEY_TYPE_SCTP:
-			field = &alg[2];
+		case NIX_FLOW_KEY_TYPE_TCP:
+		case NIX_FLOW_KEY_TYPE_UDP:
+		case NIX_FLOW_KEY_TYPE_SCTP:
 			field->lid = NPC_LID_LD;
 			field->bytesm1 = 3; /* Sport + Dport, 4 bytes */
-			if (key_type == FLOW_KEY_TYPE_TCP)
+			if (key_type == NIX_FLOW_KEY_TYPE_TCP && valid_key) {
 				field->ltype_match |= NPC_LT_LD_TCP;
-			else if (key_type == FLOW_KEY_TYPE_UDP)
+				group_member = true;
+			} else if (key_type == NIX_FLOW_KEY_TYPE_UDP &&
+				   valid_key) {
 				field->ltype_match |= NPC_LT_LD_UDP;
-			else if (key_type == FLOW_KEY_TYPE_SCTP)
+				group_member = true;
+			} else if (key_type == NIX_FLOW_KEY_TYPE_SCTP &&
+				   valid_key) {
 				field->ltype_match |= NPC_LT_LD_SCTP;
-			field->key_offset = 32; /* After IPv4/v6 SIP, DIP */
+				group_member = true;
+			}
 			field->ltype_mask = ~field->ltype_match;
+			if (key_type == NIX_FLOW_KEY_TYPE_SCTP) {
+				/* Handle the case where any of the group item
+				 * is enabled in the group but not the final one
+				 */
+				if (group_member) {
+					valid_key = true;
+					group_member = false;
+				}
+				field_marker = true;
+				keyoff_marker = true;
+			} else {
+				field_marker = false;
+				keyoff_marker = false;
+			}
 			break;
 		}
-		if (field)
-			field->ena = 1;
-		field = NULL;
+		field->ena = 1;
+
+		/* Found a valid flow key type */
+		if (valid_key) {
+			field->key_offset = key_off;
+			memcpy(&alg[nr_field], field, sizeof(*field));
+			max_key_off = max(max_key_off, field->bytesm1 + 1);
+
+			/* Found a field marker, get the next field */
+			if (field_marker)
+				nr_field++;
+		}
+
+		/* Found a keyoff marker, update the new key_off */
+		if (keyoff_marker) {
+			key_off += max_key_off;
+			max_key_off = 0;
+		}
 	}
+	/* Processed all the flow key types */
+	if (idx == max_bit_pos && key_off <= MAX_KEY_OFF)
+		return 0;
+	else
+		return NIX_AF_ERR_RSS_NOSPC_FIELD;
 }
 
-static void nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
+static int reserve_flowkey_alg_idx(struct rvu *rvu, int blkaddr, u32 flow_cfg)
 {
-#define FIELDS_PER_ALG	5
-	u64 field[FLOW_KEY_ALG_MAX][FIELDS_PER_ALG];
-	u32 flowkey_cfg, minkey_cfg;
-	int alg, fid;
+	u64 field[FIELDS_PER_ALG];
+	struct nix_hw *hw;
+	int fid, rc;
 
-	memset(&field, 0, sizeof(u64) * FLOW_KEY_ALG_MAX * FIELDS_PER_ALG);
+	hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!hw)
+		return -EINVAL;
 
-	/* Only incoming channel number */
-	flowkey_cfg = FLOW_KEY_TYPE_PORT;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_PORT], flowkey_cfg);
+	/* No room to add new flow hash algoritham */
+	if (hw->flowkey.in_use >= NIX_FLOW_KEY_ALG_MAX)
+		return NIX_AF_ERR_RSS_NOSPC_ALGO;
 
-	/* For a incoming pkt if none of the fields match then flowkey
-	 * will be zero, hence tag generated will also be zero.
-	 * RSS entry at rsse_index = NIX_AF_LF()_RSS_GRP()[OFFSET] will
-	 * be used to queue the packet.
-	 */
+	/* Generate algo fields for the given flow_cfg */
+	rc = set_flowkey_fields((struct nix_rx_flowkey_alg *)field, flow_cfg);
+	if (rc)
+		return rc;
+
+	/* Update ALGX_FIELDX register with generated fields */
+	for (fid = 0; fid < FIELDS_PER_ALG; fid++)
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(hw->flowkey.in_use,
+							   fid), field[fid]);
+
+	/* Store the flow_cfg for futher lookup */
+	rc = hw->flowkey.in_use;
+	hw->flowkey.flowkey[rc] = flow_cfg;
+	hw->flowkey.in_use++;
+
+	return rc;
+}
+
+int rvu_mbox_handler_nix_rss_flowkey_cfg(struct rvu *rvu,
+					 struct nix_rss_flowkey_cfg *req,
+					 struct nix_rss_flowkey_cfg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	int alg_idx, nixlf, blkaddr;
+	struct nix_hw *nix_hw;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	alg_idx = get_flowkey_alg_idx(nix_hw, req->flowkey_cfg);
+	/* Failed to get algo index from the exiting list, reserve new  */
+	if (alg_idx < 0) {
+		alg_idx = reserve_flowkey_alg_idx(rvu, blkaddr,
+						  req->flowkey_cfg);
+		if (alg_idx < 0)
+			return alg_idx;
+	}
+	rsp->alg_idx = alg_idx;
+	rvu_npc_update_flowkey_alg_idx(rvu, pcifunc, nixlf, req->group,
+				       alg_idx, req->mcam_index);
+	return 0;
+}
+
+static int nix_rx_flowkey_alg_cfg(struct rvu *rvu, int blkaddr)
+{
+	u32 flowkey_cfg, minkey_cfg;
+	int alg, fid, rc;
+
+	/* Disable all flow key algx fieldx */
+	for (alg = 0; alg < NIX_FLOW_KEY_ALG_MAX; alg++) {
+		for (fid = 0; fid < FIELDS_PER_ALG; fid++)
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(alg, fid),
+				    0);
+	}
 
 	/* IPv4/IPv6 SIP/DIPs */
-	flowkey_cfg = FLOW_KEY_TYPE_IPV4 | FLOW_KEY_TYPE_IPV6;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_IP], flowkey_cfg);
+	flowkey_cfg = NIX_FLOW_KEY_TYPE_IPV4 | NIX_FLOW_KEY_TYPE_IPV6;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
 	minkey_cfg = flowkey_cfg;
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* UDPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_UDP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_UDP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_UDP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* SCTPv4/v6 4-tuple, SIP, DIP, Sport, Dport */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_SCTP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_SCTP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCP/UDP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_UDP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP_UDP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			NIX_FLOW_KEY_TYPE_UDP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP_SCTP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
+			NIX_FLOW_KEY_TYPE_SCTP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* UDP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_UDP_SCTP], flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_UDP |
+			NIX_FLOW_KEY_TYPE_SCTP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
 	/* TCP/UDP/SCTP v4/v6 4-tuple, rest IP pkts 2-tuple */
-	flowkey_cfg = minkey_cfg | FLOW_KEY_TYPE_TCP |
-		      FLOW_KEY_TYPE_UDP | FLOW_KEY_TYPE_SCTP;
-	set_flowkey_fields((void *)&field[FLOW_KEY_ALG_TCP_UDP_SCTP],
-			   flowkey_cfg);
+	flowkey_cfg = minkey_cfg | NIX_FLOW_KEY_TYPE_TCP |
+		      NIX_FLOW_KEY_TYPE_UDP | NIX_FLOW_KEY_TYPE_SCTP;
+	rc = reserve_flowkey_alg_idx(rvu, blkaddr, flowkey_cfg);
+	if (rc < 0)
+		return rc;
 
-	for (alg = 0; alg < FLOW_KEY_ALG_MAX; alg++) {
-		for (fid = 0; fid < FIELDS_PER_ALG; fid++)
-			rvu_write64(rvu, blkaddr,
-				    NIX_AF_RX_FLOW_KEY_ALGX_FIELDX(alg, fid),
-				    field[alg][fid]);
-	}
+	return 0;
 }
 
-int rvu_mbox_handler_NIX_SET_MAC_ADDR(struct rvu *rvu,
+int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu,
 				      struct nix_set_mac_addr *req,
 				      struct msg_rsp *rsp)
 {
@@ -1742,10 +2277,13 @@ int rvu_mbox_handler_NIX_SET_MAC_ADDR(struct rvu *rvu,
 
 	rvu_npc_install_ucast_entry(rvu, pcifunc, nixlf,
 				    pfvf->rx_chan_base, req->mac_addr);
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+
 	return 0;
 }
 
-int rvu_mbox_handler_NIX_SET_RX_MODE(struct rvu *rvu, struct nix_rx_mode *req,
+int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 				     struct msg_rsp *rsp)
 {
 	bool allmulti = false, disable_promisc = false;
@@ -1775,9 +2313,303 @@ int rvu_mbox_handler_NIX_SET_RX_MODE(struct rvu *rvu, struct nix_rx_mode *req,
 	else
 		rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf,
 					      pfvf->rx_chan_base, allmulti);
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+
+	return 0;
+}
+
+static void nix_find_link_frs(struct rvu *rvu,
+			      struct nix_frs_cfg *req, u16 pcifunc)
+{
+	int pf = rvu_get_pf(pcifunc);
+	struct rvu_pfvf *pfvf;
+	int maxlen, minlen;
+	int numvfs, hwvf;
+	int vf;
+
+	/* Update with requester's min/max lengths */
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	pfvf->maxlen = req->maxlen;
+	if (req->update_minlen)
+		pfvf->minlen = req->minlen;
+
+	maxlen = req->maxlen;
+	minlen = req->update_minlen ? req->minlen : 0;
+
+	/* Get this PF's numVFs and starting hwvf */
+	rvu_get_pf_numvfs(rvu, pf, &numvfs, &hwvf);
+
+	/* For each VF, compare requested max/minlen */
+	for (vf = 0; vf < numvfs; vf++) {
+		pfvf =  &rvu->hwvf[hwvf + vf];
+		if (pfvf->maxlen > maxlen)
+			maxlen = pfvf->maxlen;
+		if (req->update_minlen &&
+		    pfvf->minlen && pfvf->minlen < minlen)
+			minlen = pfvf->minlen;
+	}
+
+	/* Compare requested max/minlen with PF's max/minlen */
+	pfvf = &rvu->pf[pf];
+	if (pfvf->maxlen > maxlen)
+		maxlen = pfvf->maxlen;
+	if (req->update_minlen &&
+	    pfvf->minlen && pfvf->minlen < minlen)
+		minlen = pfvf->minlen;
+
+	/* Update the request with max/min PF's and it's VF's max/min */
+	req->maxlen = maxlen;
+	if (req->update_minlen)
+		req->minlen = minlen;
+}
+
+int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
+				    struct msg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	int pf = rvu_get_pf(pcifunc);
+	int blkaddr, schq, link = -1;
+	struct nix_txsch *txsch;
+	u64 cfg, lmac_fifo_len;
+	struct nix_hw *nix_hw;
+	u8 cgx = 0, lmac = 0;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	if (!req->sdp_link && req->maxlen > NIC_HW_MAX_FRS)
+		return NIX_AF_ERR_FRS_INVALID;
+
+	if (req->update_minlen && req->minlen < NIC_HW_MIN_FRS)
+		return NIX_AF_ERR_FRS_INVALID;
+
+	/* Check if requester wants to update SMQ's */
+	if (!req->update_smq)
+		goto rx_frscfg;
+
+	/* Update min/maxlen in each of the SMQ attached to this PF/VF */
+	txsch = &nix_hw->txsch[NIX_TXSCH_LVL_SMQ];
+	mutex_lock(&rvu->rsrc_lock);
+	for (schq = 0; schq < txsch->schq.max; schq++) {
+		if (TXSCH_MAP_FUNC(txsch->pfvf_map[schq]) != pcifunc)
+			continue;
+		cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq));
+		cfg = (cfg & ~(0xFFFFULL << 8)) | ((u64)req->maxlen << 8);
+		if (req->update_minlen)
+			cfg = (cfg & ~0x7FULL) | ((u64)req->minlen & 0x7F);
+		rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(schq), cfg);
+	}
+	mutex_unlock(&rvu->rsrc_lock);
+
+rx_frscfg:
+	/* Check if config is for SDP link */
+	if (req->sdp_link) {
+		if (!hw->sdp_links)
+			return NIX_AF_ERR_RX_LINK_INVALID;
+		link = hw->cgx_links + hw->lbk_links;
+		goto linkcfg;
+	}
+
+	/* Check if the request is from CGX mapped RVU PF */
+	if (is_pf_cgxmapped(rvu, pf)) {
+		/* Get CGX and LMAC to which this PF is mapped and find link */
+		rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx, &lmac);
+		link = (cgx * hw->lmac_per_cgx) + lmac;
+	} else if (pf == 0) {
+		/* For VFs of PF0 ingress is LBK port, so config LBK link */
+		link = hw->cgx_links;
+	}
+
+	if (link < 0)
+		return NIX_AF_ERR_RX_LINK_INVALID;
+
+	nix_find_link_frs(rvu, req, pcifunc);
+
+linkcfg:
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link));
+	cfg = (cfg & ~(0xFFFFULL << 16)) | ((u64)req->maxlen << 16);
+	if (req->update_minlen)
+		cfg = (cfg & ~0xFFFFULL) | req->minlen;
+	rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link), cfg);
+
+	if (req->sdp_link || pf == 0)
+		return 0;
+
+	/* Update transmit credits for CGX links */
+	lmac_fifo_len =
+		CGX_FIFO_LEN / cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link));
+	cfg &= ~(0xFFFFFULL << 12);
+	cfg |=  ((lmac_fifo_len - req->maxlen) / 16) << 12;
+	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_NORM_CREDIT(link), cfg);
+	rvu_write64(rvu, blkaddr, NIX_AF_TX_LINKX_EXPR_CREDIT(link), cfg);
+
+	return 0;
+}
+
+int rvu_mbox_handler_nix_rxvlan_alloc(struct rvu *rvu, struct msg_req *req,
+				      struct msg_rsp *rsp)
+{
+	struct npc_mcam_alloc_entry_req alloc_req = { };
+	struct npc_mcam_alloc_entry_rsp alloc_rsp = { };
+	struct npc_mcam_free_entry_req free_req = { };
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, nixlf, err;
+	struct rvu_pfvf *pfvf;
+
+	/* LBK VFs do not have separate MCAM UCAST entry hence
+	 * skip allocating rxvlan for them
+	 */
+	if (is_afvf(pcifunc))
+		return 0;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	if (pfvf->rxvlan)
+		return 0;
+
+	/* alloc new mcam entry */
+	alloc_req.hdr.pcifunc = pcifunc;
+	alloc_req.count = 1;
+
+	err = rvu_mbox_handler_npc_mcam_alloc_entry(rvu, &alloc_req,
+						    &alloc_rsp);
+	if (err)
+		return err;
+
+	/* update entry to enable rxvlan offload */
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (blkaddr < 0) {
+		err = NIX_AF_ERR_AF_LF_INVALID;
+		goto free_entry;
+	}
+
+	nixlf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], pcifunc, 0);
+	if (nixlf < 0) {
+		err = NIX_AF_ERR_AF_LF_INVALID;
+		goto free_entry;
+	}
+
+	pfvf->rxvlan_index = alloc_rsp.entry_list[0];
+	/* all it means is that rxvlan_index is valid */
+	pfvf->rxvlan = true;
+
+	err = rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+	if (err)
+		goto free_entry;
+
+	return 0;
+free_entry:
+	free_req.hdr.pcifunc = pcifunc;
+	free_req.entry = alloc_rsp.entry_list[0];
+	rvu_mbox_handler_npc_mcam_free_entry(rvu, &free_req, rsp);
+	pfvf->rxvlan = false;
+	return err;
+}
+
+int rvu_mbox_handler_nix_set_rx_cfg(struct rvu *rvu, struct nix_rx_cfg *req,
+				    struct msg_rsp *rsp)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	u16 pcifunc = req->hdr.pcifunc;
+	struct rvu_block *block;
+	struct rvu_pfvf *pfvf;
+	int nixlf, blkaddr;
+	u64 cfg;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	block = &hw->block[blkaddr];
+	nixlf = rvu_get_lf(rvu, block, pcifunc, 0);
+	if (nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	cfg = rvu_read64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf));
+	/* Set the interface configuration */
+	if (req->len_verify & BIT(0))
+		cfg |= BIT_ULL(41);
+	else
+		cfg &= ~BIT_ULL(41);
+
+	if (req->len_verify & BIT(1))
+		cfg |= BIT_ULL(40);
+	else
+		cfg &= ~BIT_ULL(40);
+
+	if (req->csum_verify & BIT(0))
+		cfg |= BIT_ULL(37);
+	else
+		cfg &= ~BIT_ULL(37);
+
+	rvu_write64(rvu, blkaddr, NIX_AF_LFX_RX_CFG(nixlf), cfg);
+
 	return 0;
 }
 
+static void nix_link_config(struct rvu *rvu, int blkaddr)
+{
+	struct rvu_hwinfo *hw = rvu->hw;
+	int cgx, lmac_cnt, slink, link;
+	u64 tx_credits;
+
+	/* Set default min/max packet lengths allowed on NIX Rx links.
+	 *
+	 * With HW reset minlen value of 60byte, HW will treat ARP pkts
+	 * as undersize and report them to SW as error pkts, hence
+	 * setting it to 40 bytes.
+	 */
+	for (link = 0; link < (hw->cgx_links + hw->lbk_links); link++) {
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link),
+			    NIC_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS);
+	}
+
+	if (hw->sdp_links) {
+		link = hw->cgx_links + hw->lbk_links;
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_LINKX_CFG(link),
+			    SDP_HW_MAX_FRS << 16 | NIC_HW_MIN_FRS);
+	}
+
+	/* Set credits for Tx links assuming max packet length allowed.
+	 * This will be reconfigured based on MTU set for PF/VF.
+	 */
+	for (cgx = 0; cgx < hw->cgx; cgx++) {
+		lmac_cnt = cgx_get_lmac_cnt(rvu_cgx_pdata(cgx, rvu));
+		tx_credits = ((CGX_FIFO_LEN / lmac_cnt) - NIC_HW_MAX_FRS) / 16;
+		/* Enable credits and set credit pkt count to max allowed */
+		tx_credits =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+		slink = cgx * hw->lmac_per_cgx;
+		for (link = slink; link < (slink + lmac_cnt); link++) {
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_TX_LINKX_NORM_CREDIT(link),
+				    tx_credits);
+			rvu_write64(rvu, blkaddr,
+				    NIX_AF_TX_LINKX_EXPR_CREDIT(link),
+				    tx_credits);
+		}
+	}
+
+	/* Set Tx credits for LBK link */
+	slink = hw->cgx_links;
+	for (link = slink; link < (slink + hw->lbk_links); link++) {
+		tx_credits = 1000; /* 10 * max LBK datarate = 10 * 100Gbps */
+		/* Enable credits and set credit pkt count to max allowed */
+		tx_credits =  (tx_credits << 12) | (0x1FF << 2) | BIT_ULL(1);
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TX_LINKX_NORM_CREDIT(link), tx_credits);
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_TX_LINKX_EXPR_CREDIT(link), tx_credits);
+	}
+}
+
 static int nix_calibrate_x2p(struct rvu *rvu, int blkaddr)
 {
 	int idx, err;
@@ -1796,8 +2628,10 @@ static int nix_calibrate_x2p(struct rvu *rvu, int blkaddr)
 
 	status = rvu_read64(rvu, blkaddr, NIX_AF_STATUS);
 	/* Check if CGX devices are ready */
-	for (idx = 0; idx < cgx_get_cgx_cnt(); idx++) {
-		if (status & (BIT_ULL(16 + idx)))
+	for (idx = 0; idx < rvu->cgx_cnt_max; idx++) {
+		/* Skip when cgx port is not available */
+		if (!rvu_cgx_pdata(idx, rvu) ||
+		    (status & (BIT_ULL(16 + idx))))
 			continue;
 		dev_err(rvu->dev,
 			"CGX%d didn't respond to NIX X2P calibration\n", idx);
@@ -1830,10 +2664,10 @@ static int nix_aq_init(struct rvu *rvu, struct rvu_block *block)
 	/* Set admin queue endianness */
 	cfg = rvu_read64(rvu, block->addr, NIX_AF_CFG);
 #ifdef __BIG_ENDIAN
-	cfg |= BIT_ULL(1);
+	cfg |= BIT_ULL(8);
 	rvu_write64(rvu, block->addr, NIX_AF_CFG, cfg);
 #else
-	cfg &= ~BIT_ULL(1);
+	cfg &= ~BIT_ULL(8);
 	rvu_write64(rvu, block->addr, NIX_AF_CFG, cfg);
 #endif
 
@@ -1870,6 +2704,14 @@ int rvu_nix_init(struct rvu *rvu)
 		return 0;
 	block = &hw->block[blkaddr];
 
+	/* As per a HW errata in 9xxx A0 silicon, NIX may corrupt
+	 * internal state when conditional clocks are turned off.
+	 * Hence enable them.
+	 */
+	if (is_rvu_9xxx_A0(rvu))
+		rvu_write64(rvu, blkaddr, NIX_AF_CFG,
+			    rvu_read64(rvu, blkaddr, NIX_AF_CFG) | 0x5EULL);
+
 	/* Calibrate X2P bus to check if CGX/LBK links are fine */
 	err = nix_calibrate_x2p(rvu, blkaddr);
 	if (err)
@@ -1891,9 +2733,6 @@ int rvu_nix_init(struct rvu *rvu)
 	/* Restore CINT timer delay to HW reset values */
 	rvu_write64(rvu, blkaddr, NIX_AF_CINT_DELAY, 0x0ULL);
 
-	/* Configure segmentation offload formats */
-	nix_setup_lso(rvu, blkaddr);
-
 	if (blkaddr == BLKADDR_NIX0) {
 		hw->nix0 = devm_kzalloc(rvu->dev,
 					sizeof(struct nix_hw), GFP_KERNEL);
@@ -1904,24 +2743,51 @@ int rvu_nix_init(struct rvu *rvu)
 		if (err)
 			return err;
 
+		err = nix_af_mark_format_setup(rvu, hw->nix0, blkaddr);
+		if (err)
+			return err;
+
 		err = nix_setup_mcast(rvu, hw->nix0, blkaddr);
 		if (err)
 			return err;
 
-		/* Config Outer L2, IP, TCP and UDP's NPC layer info.
+		/* Configure segmentation offload formats */
+		nix_setup_lso(rvu, hw->nix0, blkaddr);
+
+		/* Config Outer/Inner L2, IP, TCP, UDP and SCTP NPC layer info.
 		 * This helps HW protocol checker to identify headers
 		 * and validate length and checksums.
 		 */
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OL2,
 			    (NPC_LID_LA << 8) | (NPC_LT_LA_ETHER << 4) | 0x0F);
-		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OUDP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_UDP << 4) | 0x0F);
-		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OTCP,
-			    (NPC_LID_LD << 8) | (NPC_LT_LD_TCP << 4) | 0x0F);
 		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP4,
 			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP4,
+			    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OIP6,
+			    (NPC_LID_LC << 8) | (NPC_LT_LC_IP6 << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IIP6,
+			    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP6 << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OTCP,
+			    (NPC_LID_LD << 8) | (NPC_LT_LD_TCP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ITCP,
+			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_TCP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OUDP,
+			    (NPC_LID_LD << 8) | (NPC_LT_LD_UDP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_IUDP,
+			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_UDP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_OSCTP,
+			    (NPC_LID_LD << 8) | (NPC_LT_LD_SCTP << 4) | 0x0F);
+		rvu_write64(rvu, blkaddr, NIX_AF_RX_DEF_ISCTP,
+			    (NPC_LID_LG << 8) | (NPC_LT_LG_TU_SCTP << 4) |
+			    0x0F);
+
+		err = nix_rx_flowkey_alg_cfg(rvu, blkaddr);
+		if (err)
+			return err;
 
-		nix_rx_flowkey_alg_cfg(rvu, blkaddr);
+		/* Initialize CGX/LBK/SDP link credits, min/max pkt lengths */
+		nix_link_config(rvu, blkaddr);
 	}
 	return 0;
 }
@@ -1955,5 +2821,139 @@ void rvu_nix_freemem(struct rvu *rvu)
 		mcast = &nix_hw->mcast;
 		qmem_free(rvu->dev, mcast->mce_ctx);
 		qmem_free(rvu->dev, mcast->mcast_buf);
+		mutex_destroy(&mcast->mce_lock);
+	}
+}
+
+static int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct rvu_hwinfo *hw = rvu->hw;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	*nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0);
+	if (*nixlf < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	return 0;
+}
+
+int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
+				     struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	int nixlf, err;
+
+	err = nix_get_nixlf(rvu, pcifunc, &nixlf);
+	if (err)
+		return err;
+
+	rvu_npc_enable_default_entries(rvu, pcifunc, nixlf);
+	return 0;
+}
+
+int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
+				    struct msg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	int nixlf, err;
+
+	err = nix_get_nixlf(rvu, pcifunc, &nixlf);
+	if (err)
+		return err;
+
+	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
+	return 0;
+}
+
+void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct hwctx_disable_req ctx_req;
+	int err;
+
+	ctx_req.hdr.pcifunc = pcifunc;
+
+	/* Cleanup NPC MCAM entries, free Tx scheduler queues being used */
+	nix_interface_deinit(rvu, pcifunc, nixlf);
+	nix_rx_sync(rvu, blkaddr);
+	nix_txschq_free(rvu, pcifunc);
+
+	if (pfvf->sq_ctx) {
+		ctx_req.ctype = NIX_AQ_CTYPE_SQ;
+		err = nix_lf_hwctx_disable(rvu, &ctx_req);
+		if (err)
+			dev_err(rvu->dev, "SQ ctx disable failed\n");
+	}
+
+	if (pfvf->rq_ctx) {
+		ctx_req.ctype = NIX_AQ_CTYPE_RQ;
+		err = nix_lf_hwctx_disable(rvu, &ctx_req);
+		if (err)
+			dev_err(rvu->dev, "RQ ctx disable failed\n");
+	}
+
+	if (pfvf->cq_ctx) {
+		ctx_req.ctype = NIX_AQ_CTYPE_CQ;
+		err = nix_lf_hwctx_disable(rvu, &ctx_req);
+		if (err)
+			dev_err(rvu->dev, "CQ ctx disable failed\n");
 	}
+
+	nix_ctx_free(rvu, pfvf);
+}
+
+int rvu_mbox_handler_nix_lso_format_cfg(struct rvu *rvu,
+					struct nix_lso_format_cfg *req,
+					struct nix_lso_format_cfg_rsp *rsp)
+{
+	u16 pcifunc = req->hdr.pcifunc;
+	struct nix_hw *nix_hw;
+	struct rvu_pfvf *pfvf;
+	int blkaddr, idx, f;
+	u64 reg;
+
+	pfvf = rvu_get_pfvf(rvu, pcifunc);
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
+	if (!pfvf->nixlf || blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	nix_hw = get_nix_hw(rvu->hw, blkaddr);
+	if (!nix_hw)
+		return -EINVAL;
+
+	/* Find existing matching LSO format, if any */
+	for (idx = 0; idx < nix_hw->lso.in_use; idx++) {
+		for (f = 0; f < NIX_LSO_FIELD_MAX; f++) {
+			reg = rvu_read64(rvu, blkaddr,
+					 NIX_AF_LSO_FORMATX_FIELDX(idx, f));
+			if (req->fields[f] != (reg & req->field_mask))
+				break;
+		}
+
+		if (f == NIX_LSO_FIELD_MAX)
+			break;
+	}
+
+	if (idx < nix_hw->lso.in_use) {
+		/* Match found */
+		rsp->lso_format_idx = idx;
+		return 0;
+	}
+
+	if (nix_hw->lso.in_use == nix_hw->lso.total)
+		return NIX_AF_ERR_LSO_CFG_FAIL;
+
+	rsp->lso_format_idx = nix_hw->lso.in_use++;
+
+	for (f = 0; f < NIX_LSO_FIELD_MAX; f++)
+		rvu_write64(rvu, blkaddr,
+			    NIX_AF_LSO_FORMATX_FIELDX(rsp->lso_format_idx, f),
+			    req->fields[f]);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
index 7531fdc54fa1..c0e165dfc403 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c
@@ -241,14 +241,14 @@ static int npa_lf_hwctx_disable(struct rvu *rvu, struct hwctx_disable_req *req)
 	return err;
 }
 
-int rvu_mbox_handler_NPA_AQ_ENQ(struct rvu *rvu,
+int rvu_mbox_handler_npa_aq_enq(struct rvu *rvu,
 				struct npa_aq_enq_req *req,
 				struct npa_aq_enq_rsp *rsp)
 {
 	return rvu_npa_aq_enq_inst(rvu, req, rsp);
 }
 
-int rvu_mbox_handler_NPA_HWCTX_DISABLE(struct rvu *rvu,
+int rvu_mbox_handler_npa_hwctx_disable(struct rvu *rvu,
 				       struct hwctx_disable_req *req,
 				       struct msg_rsp *rsp)
 {
@@ -273,7 +273,7 @@ static void npa_ctx_free(struct rvu *rvu, struct rvu_pfvf *pfvf)
 	pfvf->npa_qints_ctx = NULL;
 }
 
-int rvu_mbox_handler_NPA_LF_ALLOC(struct rvu *rvu,
+int rvu_mbox_handler_npa_lf_alloc(struct rvu *rvu,
 				  struct npa_lf_alloc_req *req,
 				  struct npa_lf_alloc_rsp *rsp)
 {
@@ -372,7 +372,7 @@ exit:
 	return rc;
 }
 
-int rvu_mbox_handler_NPA_LF_FREE(struct rvu *rvu, struct msg_req *req,
+int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req,
 				 struct msg_rsp *rsp)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
@@ -470,3 +470,20 @@ void rvu_npa_freemem(struct rvu *rvu)
 	block = &hw->block[blkaddr];
 	rvu_aq_free(rvu, block->aq);
 }
+
+void rvu_npa_lf_teardown(struct rvu *rvu, u16 pcifunc, int npalf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct hwctx_disable_req ctx_req;
+
+	/* Disable all pools */
+	ctx_req.hdr.pcifunc = pcifunc;
+	ctx_req.ctype = NPA_AQ_CTYPE_POOL;
+	npa_lf_hwctx_disable(rvu, &ctx_req);
+
+	/* Disable all auras */
+	ctx_req.ctype = NPA_AQ_CTYPE_AURA;
+	npa_lf_hwctx_disable(rvu, &ctx_req);
+
+	npa_ctx_free(rvu, pfvf);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index 23ff47f7efc5..15f70273e29c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -8,6 +8,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/bitfield.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 
@@ -15,6 +16,7 @@
 #include "rvu_reg.h"
 #include "rvu.h"
 #include "npc.h"
+#include "cgx.h"
 #include "npc_profile.h"
 
 #define RSVD_MCAM_ENTRIES_PER_PF	2 /* Bcast & Promisc */
@@ -26,13 +28,10 @@
 
 #define NPC_PARSE_RESULT_DMAC_OFFSET	8
 
-struct mcam_entry {
-#define NPC_MAX_KWS_IN_KEY	7 /* Number of keywords in max keywidth */
-	u64	kw[NPC_MAX_KWS_IN_KEY];
-	u64	kw_mask[NPC_MAX_KWS_IN_KEY];
-	u64	action;
-	u64	vtag_action;
-};
+static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
+				      int blkaddr, u16 pcifunc);
+static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam,
+				       u16 pcifunc);
 
 void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf)
 {
@@ -256,6 +255,46 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
 		npc_enable_mcam_entry(rvu, mcam, blkaddr, actindex, false);
 }
 
+static void npc_copy_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam,
+				int blkaddr, u16 src, u16 dest)
+{
+	int dbank = npc_get_bank(mcam, dest);
+	int sbank = npc_get_bank(mcam, src);
+	u64 cfg, sreg, dreg;
+	int bank, i;
+
+	src &= (mcam->banksize - 1);
+	dest &= (mcam->banksize - 1);
+
+	/* Copy INTF's, W0's, W1's CAM0 and CAM1 configuration */
+	for (bank = 0; bank < mcam->banks_per_entry; bank++) {
+		sreg = NPC_AF_MCAMEX_BANKX_CAMX_INTF(src, sbank + bank, 0);
+		dreg = NPC_AF_MCAMEX_BANKX_CAMX_INTF(dest, dbank + bank, 0);
+		for (i = 0; i < 6; i++) {
+			cfg = rvu_read64(rvu, blkaddr, sreg + (i * 8));
+			rvu_write64(rvu, blkaddr, dreg + (i * 8), cfg);
+		}
+	}
+
+	/* Copy action */
+	cfg = rvu_read64(rvu, blkaddr,
+			 NPC_AF_MCAMEX_BANKX_ACTION(src, sbank));
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_ACTION(dest, dbank), cfg);
+
+	/* Copy TAG action */
+	cfg = rvu_read64(rvu, blkaddr,
+			 NPC_AF_MCAMEX_BANKX_TAG_ACT(src, sbank));
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_TAG_ACT(dest, dbank), cfg);
+
+	/* Enable or disable */
+	cfg = rvu_read64(rvu, blkaddr,
+			 NPC_AF_MCAMEX_BANKX_CFG(src, sbank));
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_CFG(dest, dbank), cfg);
+}
+
 static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
 			       int blkaddr, int index)
 {
@@ -269,12 +308,17 @@ static u64 npc_get_mcam_action(struct rvu *rvu, struct npc_mcam *mcam,
 void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 				 int nixlf, u64 chan, u8 *mac_addr)
 {
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct mcam_entry entry = { {0} };
 	struct nix_rx_action action;
 	int blkaddr, index, kwi;
 	u64 mac = 0;
 
+	/* AF's VFs work in promiscuous mode */
+	if (is_afvf(pcifunc))
+		return;
+
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
 		return;
@@ -308,22 +352,33 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc,
 	entry.action = *(u64 *)&action;
 	npc_config_mcam_entry(rvu, mcam, blkaddr, index,
 			      NIX_INTF_RX, &entry, true);
+
+	/* add VLAN matching, setup action and save entry back for later */
+	entry.kw[0] |= (NPC_LT_LB_STAG | NPC_LT_LB_CTAG) << 20;
+	entry.kw_mask[0] |= (NPC_LT_LB_STAG & NPC_LT_LB_CTAG) << 20;
+
+	entry.vtag_action = VTAG0_VALID_BIT |
+			    FIELD_PREP(VTAG0_TYPE_MASK, 0) |
+			    FIELD_PREP(VTAG0_LID_MASK, NPC_LID_LA) |
+			    FIELD_PREP(VTAG0_RELPTR_MASK, 12);
+
+	memcpy(&pfvf->entry, &entry, sizeof(entry));
 }
 
 void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 				   int nixlf, u64 chan, bool allmulti)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, ucast_idx, index, kwi;
 	struct mcam_entry entry = { {0} };
-	struct nix_rx_action action;
-	int blkaddr, index, kwi;
+	struct nix_rx_action action = { };
 
-	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
-	if (blkaddr < 0)
+	/* Only PF or AF VF can add a promiscuous entry */
+	if ((pcifunc & RVU_PFVF_FUNC_MASK) && !is_afvf(pcifunc))
 		return;
 
-	/* Only PF or AF VF can add a promiscuous entry */
-	if (pcifunc & RVU_PFVF_FUNC_MASK)
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
 		return;
 
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
@@ -338,16 +393,29 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 		entry.kw_mask[kwi] = BIT_ULL(40);
 	}
 
-	*(u64 *)&action = 0x00;
-	action.op = NIX_RX_ACTIONOP_UCAST;
-	action.pf_func = pcifunc;
+	ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					     nixlf, NIXLF_UCAST_ENTRY);
+
+	/* If the corresponding PF's ucast action is RSS,
+	 * use the same action for promisc also
+	 */
+	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx))
+		*(u64 *)&action = npc_get_mcam_action(rvu, mcam,
+							blkaddr, ucast_idx);
+
+	if (action.op != NIX_RX_ACTIONOP_RSS) {
+		*(u64 *)&action = 0x00;
+		action.op = NIX_RX_ACTIONOP_UCAST;
+		action.pf_func = pcifunc;
+	}
 
 	entry.action = *(u64 *)&action;
 	npc_config_mcam_entry(rvu, mcam, blkaddr, index,
 			      NIX_INTF_RX, &entry, true);
 }
 
-void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
+static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc,
+				     int nixlf, bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	int blkaddr, index;
@@ -362,7 +430,17 @@ void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
 
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_PROMISC_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
+}
+
+void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_promisc_entry(rvu, pcifunc, nixlf, false);
+}
+
+void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_promisc_entry(rvu, pcifunc, nixlf, true);
 }
 
 void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
@@ -390,9 +468,28 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc,
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_BCAST_ENTRY);
 
-	/* Check for L2B bit and LMAC channel */
-	entry.kw[0] = BIT_ULL(25) | chan;
-	entry.kw_mask[0] = BIT_ULL(25) | 0xFFFULL;
+	/* Check for L2B bit and LMAC channel
+	 * NOTE: Since MKEX default profile(a reduced version intended to
+	 * accommodate more capability but igoring few bits) a stap-gap
+	 * approach.
+	 * Since we care for L2B which by HRM NPC_PARSE_KEX_S at BIT_POS[25], So
+	 * moved to BIT_POS[13], ignoring ERRCODE, ERRLEV as we'll loose out
+	 * on capability features needed for CoS (/from ODP PoV) e.g: VLAN,
+	 * DSCP.
+	 *
+	 * Reduced layout of MKEX default profile -
+	 * Includes following are (i.e.CHAN, L2/3{B/M}, LA, LB, LC, LD):
+	 *
+	 * BIT_POS[31:28] : LD
+	 * BIT_POS[27:24] : LC
+	 * BIT_POS[23:20] : LB
+	 * BIT_POS[19:16] : LA
+	 * BIT_POS[15:12] : L3B, L3M, L2B, L2M
+	 * BIT_POS[11:00] : CHAN
+	 *
+	 */
+	entry.kw[0] = BIT_ULL(13) | chan;
+	entry.kw_mask[0] = BIT_ULL(13) | 0xFFFULL;
 
 	*(u64 *)&action = 0x00;
 #ifdef MCAST_MCE
@@ -454,51 +551,110 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 
 	rvu_write64(rvu, blkaddr,
 		    NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action);
+
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_PROMISC_ENTRY);
+
+	/* If PF's promiscuous entry is enabled,
+	 * Set RSS action for that entry as well
+	 */
+	if (is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) {
+		bank = npc_get_bank(mcam, index);
+		index &= (mcam->banksize - 1);
+
+		rvu_write64(rvu, blkaddr,
+			    NPC_AF_MCAMEX_BANKX_ACTION(index, bank),
+			    *(u64 *)&action);
+	}
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
 }
 
-void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc,
+				       int nixlf, bool enable)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
 	struct nix_rx_action action;
-	int blkaddr, index, bank;
+	int index, bank, blkaddr;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0)
 		return;
 
-	/* Disable ucast MCAM match entry of this PF/VF */
+	/* Ucast MCAM match entry of this PF/VF */
 	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
 					 nixlf, NIXLF_UCAST_ENTRY);
-	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable);
 
-	/* For PF, disable promisc and bcast MCAM match entries */
-	if (!(pcifunc & RVU_PFVF_FUNC_MASK)) {
-		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-						 nixlf, NIXLF_BCAST_ENTRY);
-		/* For bcast, disable only if it's action is not
-		 * packet replication, incase if action is replication
-		 * then this PF's nixlf is removed from bcast replication
-		 * list.
-		 */
-		bank = npc_get_bank(mcam, index);
-		index &= (mcam->banksize - 1);
-		*(u64 *)&action = rvu_read64(rvu, blkaddr,
-				     NPC_AF_MCAMEX_BANKX_ACTION(index, bank));
-		if (action.op != NIX_RX_ACTIONOP_MCAST)
-			npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+	/* For PF, ena/dis promisc and bcast MCAM match entries */
+	if (pcifunc & RVU_PFVF_FUNC_MASK)
+		return;
 
+	/* For bcast, enable/disable only if it's action is not
+	 * packet replication, incase if action is replication
+	 * then this PF's nixlf is removed from bcast replication
+	 * list.
+	 */
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+					 nixlf, NIXLF_BCAST_ENTRY);
+	bank = npc_get_bank(mcam, index);
+	*(u64 *)&action = rvu_read64(rvu, blkaddr,
+	     NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank));
+	if (action.op != NIX_RX_ACTIONOP_MCAST)
+		npc_enable_mcam_entry(rvu, mcam,
+				      blkaddr, index, enable);
+	if (enable)
+		rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf);
+	else
 		rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf);
-	}
+
+	rvu_npc_update_rxvlan(rvu, pcifunc, nixlf);
+}
+
+void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_default_entries(rvu, pcifunc, nixlf, false);
+}
+
+void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	npc_enadis_default_entries(rvu, pcifunc, nixlf, true);
+}
+
+void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return;
+
+	mutex_lock(&mcam->lock);
+
+	/* Disable and free all MCAM entries mapped to this 'pcifunc' */
+	npc_mcam_free_all_entries(rvu, mcam, blkaddr, pcifunc);
+
+	/* Free all MCAM counters mapped to this 'pcifunc' */
+	npc_mcam_free_all_counters(rvu, mcam, pcifunc);
+
+	mutex_unlock(&mcam->lock);
+
+	rvu_npc_disable_default_entries(rvu, pcifunc, nixlf);
 }
 
-#define LDATA_EXTRACT_CONFIG(intf, lid, ltype, ld, cfg) \
+#define SET_KEX_LD(intf, lid, ltype, ld, cfg)	\
 	rvu_write64(rvu, blkaddr,			\
 		NPC_AF_INTFX_LIDX_LTX_LDX_CFG(intf, lid, ltype, ld), cfg)
 
-#define LDATA_FLAGS_CONFIG(intf, ld, flags, cfg)	\
+#define SET_KEX_LDFLAGS(intf, ld, flags, cfg)	\
 	rvu_write64(rvu, blkaddr,			\
 		NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, flags), cfg)
 
+#define KEX_LD_CFG(bytesm1, hdr_ofs, ena, flags_ena, key_ofs)		\
+			(((bytesm1) << 16) | ((hdr_ofs) << 8) | ((ena) << 7) | \
+			 ((flags_ena) << 6) | ((key_ofs) & 0x3F))
+
 static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
 {
 	struct npc_mcam *mcam = &rvu->hw->mcam;
@@ -514,28 +670,171 @@ static void npc_config_ldata_extract(struct rvu *rvu, int blkaddr)
 	 */
 	for (lid = 0; lid < lid_count; lid++) {
 		for (ltype = 0; ltype < 16; ltype++) {
-			LDATA_EXTRACT_CONFIG(NIX_INTF_RX, lid, ltype, 0, 0ULL);
-			LDATA_EXTRACT_CONFIG(NIX_INTF_RX, lid, ltype, 1, 0ULL);
-			LDATA_EXTRACT_CONFIG(NIX_INTF_TX, lid, ltype, 0, 0ULL);
-			LDATA_EXTRACT_CONFIG(NIX_INTF_TX, lid, ltype, 1, 0ULL);
-
-			LDATA_FLAGS_CONFIG(NIX_INTF_RX, 0, ltype, 0ULL);
-			LDATA_FLAGS_CONFIG(NIX_INTF_RX, 1, ltype, 0ULL);
-			LDATA_FLAGS_CONFIG(NIX_INTF_TX, 0, ltype, 0ULL);
-			LDATA_FLAGS_CONFIG(NIX_INTF_TX, 1, ltype, 0ULL);
+			SET_KEX_LD(NIX_INTF_RX, lid, ltype, 0, 0ULL);
+			SET_KEX_LD(NIX_INTF_RX, lid, ltype, 1, 0ULL);
+			SET_KEX_LD(NIX_INTF_TX, lid, ltype, 0, 0ULL);
+			SET_KEX_LD(NIX_INTF_TX, lid, ltype, 1, 0ULL);
+
+			SET_KEX_LDFLAGS(NIX_INTF_RX, 0, ltype, 0ULL);
+			SET_KEX_LDFLAGS(NIX_INTF_RX, 1, ltype, 0ULL);
+			SET_KEX_LDFLAGS(NIX_INTF_TX, 0, ltype, 0ULL);
+			SET_KEX_LDFLAGS(NIX_INTF_TX, 1, ltype, 0ULL);
 		}
 	}
 
-	/* If we plan to extract Outer IPv4 tuple for TCP/UDP pkts
-	 * then 112bit key is not sufficient
-	 */
 	if (mcam->keysize != NPC_MCAM_KEY_X2)
 		return;
 
-	/* Start placing extracted data/flags from 64bit onwards, for now */
-	/* Extract DMAC from the packet */
-	cfg = (0x05 << 16) | BIT_ULL(7) | NPC_PARSE_RESULT_DMAC_OFFSET;
-	LDATA_EXTRACT_CONFIG(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 0, cfg);
+	/* Default MCAM KEX profile */
+	/* Layer A: Ethernet: */
+
+	/* DMAC: 6 bytes, KW1[47:0] */
+	cfg = KEX_LD_CFG(0x05, 0x0, 0x1, 0x0, NPC_PARSE_RESULT_DMAC_OFFSET);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 0, cfg);
+
+	/* Ethertype: 2 bytes, KW0[47:32] */
+	cfg = KEX_LD_CFG(0x01, 0xc, 0x1, 0x0, 0x4);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LA, NPC_LT_LA_ETHER, 1, cfg);
+
+	/* Layer B: Single VLAN (CTAG) */
+	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
+	cfg = KEX_LD_CFG(0x03, 0x0, 0x1, 0x0, 0x4);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_CTAG, 0, cfg);
+
+	/* Layer B: Stacked VLAN (STAG|QinQ) */
+	/* CTAG VLAN[2..3] + Ethertype, 4 bytes, KW0[63:32] */
+	cfg = KEX_LD_CFG(0x03, 0x4, 0x1, 0x0, 0x4);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_STAG, 0, cfg);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LB, NPC_LT_LB_QINQ, 0, cfg);
+
+	/* Layer C: IPv4 */
+	/* SIP+DIP: 8 bytes, KW2[63:0] */
+	cfg = KEX_LD_CFG(0x07, 0xc, 0x1, 0x0, 0x10);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LC, NPC_LT_LC_IP, 0, cfg);
+	/* TOS: 1 byte, KW1[63:56] */
+	cfg = KEX_LD_CFG(0x0, 0x1, 0x1, 0x0, 0xf);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LC, NPC_LT_LC_IP, 1, cfg);
+
+	/* Layer D:UDP */
+	/* SPORT: 2 bytes, KW3[15:0] */
+	cfg = KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_UDP, 0, cfg);
+	/* DPORT: 2 bytes, KW3[31:16] */
+	cfg = KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_UDP, 1, cfg);
+
+	/* Layer D:TCP */
+	/* SPORT: 2 bytes, KW3[15:0] */
+	cfg = KEX_LD_CFG(0x1, 0x0, 0x1, 0x0, 0x18);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 0, cfg);
+	/* DPORT: 2 bytes, KW3[31:16] */
+	cfg = KEX_LD_CFG(0x1, 0x2, 0x1, 0x0, 0x1a);
+	SET_KEX_LD(NIX_INTF_RX, NPC_LID_LD, NPC_LT_LD_TCP, 1, cfg);
+}
+
+static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr,
+				     struct npc_mcam_kex *mkex)
+{
+	int lid, lt, ld, fl;
+
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
+		    mkex->keyx_cfg[NIX_INTF_RX]);
+	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
+		    mkex->keyx_cfg[NIX_INTF_TX]);
+
+	for (ld = 0; ld < NPC_MAX_LD; ld++)
+		rvu_write64(rvu, blkaddr, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld),
+			    mkex->kex_ld_flags[ld]);
+
+	for (lid = 0; lid < NPC_MAX_LID; lid++) {
+		for (lt = 0; lt < NPC_MAX_LT; lt++) {
+			for (ld = 0; ld < NPC_MAX_LD; ld++) {
+				SET_KEX_LD(NIX_INTF_RX, lid, lt, ld,
+					   mkex->intf_lid_lt_ld[NIX_INTF_RX]
+					   [lid][lt][ld]);
+
+				SET_KEX_LD(NIX_INTF_TX, lid, lt, ld,
+					   mkex->intf_lid_lt_ld[NIX_INTF_TX]
+					   [lid][lt][ld]);
+			}
+		}
+	}
+
+	for (ld = 0; ld < NPC_MAX_LD; ld++) {
+		for (fl = 0; fl < NPC_MAX_LFL; fl++) {
+			SET_KEX_LDFLAGS(NIX_INTF_RX, ld, fl,
+					mkex->intf_ld_flags[NIX_INTF_RX]
+					[ld][fl]);
+
+			SET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl,
+					mkex->intf_ld_flags[NIX_INTF_TX]
+					[ld][fl]);
+		}
+	}
+}
+
+/* strtoull of "mkexprof" with base:36 */
+#define MKEX_SIGN      0x19bbfdbd15f
+#define MKEX_END_SIGN  0xdeadbeef
+
+static void npc_load_mkex_profile(struct rvu *rvu, int blkaddr)
+{
+	const char *mkex_profile = rvu->mkex_pfl_name;
+	struct device *dev = &rvu->pdev->dev;
+	void __iomem *mkex_prfl_addr = NULL;
+	struct npc_mcam_kex *mcam_kex;
+	u64 prfl_addr;
+	u64 prfl_sz;
+
+	/* If user not selected mkex profile */
+	if (!strncmp(mkex_profile, "default", MKEX_NAME_LEN))
+		goto load_default;
+
+	if (cgx_get_mkex_prfl_info(&prfl_addr, &prfl_sz))
+		goto load_default;
+
+	if (!prfl_addr || !prfl_sz)
+		goto load_default;
+
+	mkex_prfl_addr = ioremap_wc(prfl_addr, prfl_sz);
+	if (!mkex_prfl_addr)
+		goto load_default;
+
+	mcam_kex = (struct npc_mcam_kex *)mkex_prfl_addr;
+
+	while (((s64)prfl_sz > 0) && (mcam_kex->mkex_sign != MKEX_END_SIGN)) {
+		/* Compare with mkex mod_param name string */
+		if (mcam_kex->mkex_sign == MKEX_SIGN &&
+		    !strncmp(mcam_kex->name, mkex_profile, MKEX_NAME_LEN)) {
+			/* Due to an errata (35786) in A0 pass silicon,
+			 * parse nibble enable configuration has to be
+			 * identical for both Rx and Tx interfaces.
+			 */
+			if (is_rvu_9xxx_A0(rvu) &&
+			    mcam_kex->keyx_cfg[NIX_INTF_RX] !=
+			    mcam_kex->keyx_cfg[NIX_INTF_TX])
+				goto load_default;
+
+			/* Program selected mkex profile */
+			npc_program_mkex_profile(rvu, blkaddr, mcam_kex);
+
+			goto unmap;
+		}
+
+		mcam_kex++;
+		prfl_sz -= sizeof(struct npc_mcam_kex);
+	}
+	dev_warn(dev, "Failed to load requested profile: %s\n",
+		 rvu->mkex_pfl_name);
+
+load_default:
+	dev_info(rvu->dev, "Using default mkex profile\n");
+	/* Config packet data and flags extraction into PARSE result */
+	npc_config_ldata_extract(rvu, blkaddr);
+
+unmap:
+	if (mkex_prfl_addr)
+		iounmap(mkex_prfl_addr);
 }
 
 static void npc_config_kpuaction(struct rvu *rvu, int blkaddr,
@@ -690,13 +989,14 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 {
 	int nixlf_count = rvu_get_nixlf_count(rvu);
 	struct npc_mcam *mcam = &rvu->hw->mcam;
-	int rsvd;
+	int rsvd, err;
 	u64 cfg;
 
 	/* Get HW limits */
 	cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
 	mcam->banks = (cfg >> 44) & 0xF;
 	mcam->banksize = (cfg >> 28) & 0xFFFF;
+	mcam->counters.max = (cfg >> 48) & 0xFFFF;
 
 	/* Actual number of MCAM entries vary by entry size */
 	cfg = (rvu_read64(rvu, blkaddr,
@@ -728,20 +1028,82 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr)
 		return -ENOMEM;
 	}
 
-	mcam->entries = mcam->total_entries - rsvd;
-	mcam->nixlf_offset = mcam->entries;
+	mcam->bmap_entries = mcam->total_entries - rsvd;
+	mcam->nixlf_offset = mcam->bmap_entries;
 	mcam->pf_offset = mcam->nixlf_offset + nixlf_count;
 
-	spin_lock_init(&mcam->lock);
+	/* Allocate bitmaps for managing MCAM entries */
+	mcam->bmap = devm_kcalloc(rvu->dev, BITS_TO_LONGS(mcam->bmap_entries),
+				  sizeof(long), GFP_KERNEL);
+	if (!mcam->bmap)
+		return -ENOMEM;
+
+	mcam->bmap_reverse = devm_kcalloc(rvu->dev,
+					  BITS_TO_LONGS(mcam->bmap_entries),
+					  sizeof(long), GFP_KERNEL);
+	if (!mcam->bmap_reverse)
+		return -ENOMEM;
+
+	mcam->bmap_fcnt = mcam->bmap_entries;
+
+	/* Alloc memory for saving entry to RVU PFFUNC allocation mapping */
+	mcam->entry2pfvf_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
+					    sizeof(u16), GFP_KERNEL);
+	if (!mcam->entry2pfvf_map)
+		return -ENOMEM;
+
+	/* Reserve 1/8th of MCAM entries at the bottom for low priority
+	 * allocations and another 1/8th at the top for high priority
+	 * allocations.
+	 */
+	mcam->lprio_count = mcam->bmap_entries / 8;
+	if (mcam->lprio_count > BITS_PER_LONG)
+		mcam->lprio_count = round_down(mcam->lprio_count,
+					       BITS_PER_LONG);
+	mcam->lprio_start = mcam->bmap_entries - mcam->lprio_count;
+	mcam->hprio_count = mcam->lprio_count;
+	mcam->hprio_end = mcam->hprio_count;
+
+	/* Allocate bitmap for managing MCAM counters and memory
+	 * for saving counter to RVU PFFUNC allocation mapping.
+	 */
+	err = rvu_alloc_bitmap(&mcam->counters);
+	if (err)
+		return err;
+
+	mcam->cntr2pfvf_map = devm_kcalloc(rvu->dev, mcam->counters.max,
+					   sizeof(u16), GFP_KERNEL);
+	if (!mcam->cntr2pfvf_map)
+		goto free_mem;
+
+	/* Alloc memory for MCAM entry to counter mapping and for tracking
+	 * counter's reference count.
+	 */
+	mcam->entry2cntr_map = devm_kcalloc(rvu->dev, mcam->bmap_entries,
+					    sizeof(u16), GFP_KERNEL);
+	if (!mcam->entry2cntr_map)
+		goto free_mem;
+
+	mcam->cntr_refcnt = devm_kcalloc(rvu->dev, mcam->counters.max,
+					 sizeof(u16), GFP_KERNEL);
+	if (!mcam->cntr_refcnt)
+		goto free_mem;
+
+	mutex_init(&mcam->lock);
 
 	return 0;
+
+free_mem:
+	kfree(mcam->counters.bmap);
+	return -ENOMEM;
 }
 
 int rvu_npc_init(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
 	u64 keyz = NPC_MCAM_KEY_X2;
-	int blkaddr, err;
+	int blkaddr, entry, bank, err;
+	u64 cfg, nibble_ena;
 
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
 	if (blkaddr < 0) {
@@ -749,6 +1111,14 @@ int rvu_npc_init(struct rvu *rvu)
 		return -ENODEV;
 	}
 
+	/* First disable all MCAM entries, to stop traffic towards NIXLFs */
+	cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST);
+	for (bank = 0; bank < ((cfg >> 44) & 0xF); bank++) {
+		for (entry = 0; entry < ((cfg >> 28) & 0xFFFF); entry++)
+			rvu_write64(rvu, blkaddr,
+				    NPC_AF_MCAMEX_BANKX_CFG(entry, bank), 0);
+	}
+
 	/* Allocate resource bimap for pkind*/
 	pkind->rsrc.max = (rvu_read64(rvu, blkaddr,
 				      NPC_AF_CONST1) >> 12) & 0xFF;
@@ -771,29 +1141,41 @@ int rvu_npc_init(struct rvu *rvu)
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_OIP4,
 		    (NPC_LID_LC << 8) | (NPC_LT_LC_IP << 4) | 0x0F);
 
+	/* Config Inner IPV4 NPC layer info */
+	rvu_write64(rvu, blkaddr, NPC_AF_PCK_DEF_IIP4,
+		    (NPC_LID_LF << 8) | (NPC_LT_LF_TU_IP << 4) | 0x0F);
+
 	/* Enable below for Rx pkts.
 	 * - Outer IPv4 header checksum validation.
 	 * - Detect outer L2 broadcast address and set NPC_RESULT_S[L2M].
+	 * - Inner IPv4 header checksum validation.
+	 * - Set non zero checksum error code value
 	 */
 	rvu_write64(rvu, blkaddr, NPC_AF_PCK_CFG,
 		    rvu_read64(rvu, blkaddr, NPC_AF_PCK_CFG) |
-		    BIT_ULL(6) | BIT_ULL(2));
+		    BIT_ULL(32) | BIT_ULL(24) | BIT_ULL(6) |
+		    BIT_ULL(2) | BIT_ULL(1));
 
 	/* Set RX and TX side MCAM search key size.
-	 * Also enable parse key extract nibbles suchthat except
-	 * layer E to H, rest of the key is included for MCAM search.
+	 * LA..LD (ltype only) + Channel
 	 */
+	nibble_ena = 0x49247;
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX),
-		    ((keyz & 0x3) << 32) | ((1ULL << 20) - 1));
+			((keyz & 0x3) << 32) | nibble_ena);
+	/* Due to an errata (35786) in A0 pass silicon, parse nibble enable
+	 * configuration has to be identical for both Rx and Tx interfaces.
+	 */
+	if (!is_rvu_9xxx_A0(rvu))
+		nibble_ena = (1ULL << 19) - 1;
 	rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX),
-		    ((keyz & 0x3) << 32) | ((1ULL << 20) - 1));
+			((keyz & 0x3) << 32) | nibble_ena);
 
 	err = npc_mcam_rsrcs_init(rvu, blkaddr);
 	if (err)
 		return err;
 
-	/* Config packet data and flags extraction into PARSE result */
-	npc_config_ldata_extract(rvu, blkaddr);
+	/* Configure MKEX profile */
+	npc_load_mkex_profile(rvu, blkaddr);
 
 	/* Set TX miss action to UCAST_DEFAULT i.e
 	 * transmit the packet on NIX LF SQ's default channel.
@@ -811,6 +1193,1020 @@ int rvu_npc_init(struct rvu *rvu)
 void rvu_npc_freemem(struct rvu *rvu)
 {
 	struct npc_pkind *pkind = &rvu->hw->pkind;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
 
 	kfree(pkind->rsrc.bmap);
+	kfree(mcam->counters.bmap);
+	mutex_destroy(&mcam->lock);
+}
+
+static int npc_mcam_verify_entry(struct npc_mcam *mcam,
+				 u16 pcifunc, int entry)
+{
+	/* Verify if entry is valid and if it is indeed
+	 * allocated to the requesting PFFUNC.
+	 */
+	if (entry >= mcam->bmap_entries)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (pcifunc != mcam->entry2pfvf_map[entry])
+		return NPC_MCAM_PERM_DENIED;
+
+	return 0;
+}
+
+static int npc_mcam_verify_counter(struct npc_mcam *mcam,
+				   u16 pcifunc, int cntr)
+{
+	/* Verify if counter is valid and if it is indeed
+	 * allocated to the requesting PFFUNC.
+	 */
+	if (cntr >= mcam->counters.max)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (pcifunc != mcam->cntr2pfvf_map[cntr])
+		return NPC_MCAM_PERM_DENIED;
+
+	return 0;
+}
+
+static void npc_map_mcam_entry_and_cntr(struct rvu *rvu, struct npc_mcam *mcam,
+					int blkaddr, u16 entry, u16 cntr)
+{
+	u16 index = entry & (mcam->banksize - 1);
+	u16 bank = npc_get_bank(mcam, entry);
+
+	/* Set mapping and increment counter's refcnt */
+	mcam->entry2cntr_map[entry] = cntr;
+	mcam->cntr_refcnt[cntr]++;
+	/* Enable stats */
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank),
+		    BIT_ULL(9) | cntr);
+}
+
+static void npc_unmap_mcam_entry_and_cntr(struct rvu *rvu,
+					  struct npc_mcam *mcam,
+					  int blkaddr, u16 entry, u16 cntr)
+{
+	u16 index = entry & (mcam->banksize - 1);
+	u16 bank = npc_get_bank(mcam, entry);
+
+	/* Remove mapping and reduce counter's refcnt */
+	mcam->entry2cntr_map[entry] = NPC_MCAM_INVALID_MAP;
+	mcam->cntr_refcnt[cntr]--;
+	/* Disable stats */
+	rvu_write64(rvu, blkaddr,
+		    NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank), 0x00);
+}
+
+/* Sets MCAM entry in bitmap as used. Update
+ * reverse bitmap too. Should be called with
+ * 'mcam->lock' held.
+ */
+static void npc_mcam_set_bit(struct npc_mcam *mcam, u16 index)
+{
+	u16 entry, rentry;
+
+	entry = index;
+	rentry = mcam->bmap_entries - index - 1;
+
+	__set_bit(entry, mcam->bmap);
+	__set_bit(rentry, mcam->bmap_reverse);
+	mcam->bmap_fcnt--;
+}
+
+/* Sets MCAM entry in bitmap as free. Update
+ * reverse bitmap too. Should be called with
+ * 'mcam->lock' held.
+ */
+static void npc_mcam_clear_bit(struct npc_mcam *mcam, u16 index)
+{
+	u16 entry, rentry;
+
+	entry = index;
+	rentry = mcam->bmap_entries - index - 1;
+
+	__clear_bit(entry, mcam->bmap);
+	__clear_bit(rentry, mcam->bmap_reverse);
+	mcam->bmap_fcnt++;
+}
+
+static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam,
+				      int blkaddr, u16 pcifunc)
+{
+	u16 index, cntr;
+
+	/* Scan all MCAM entries and free the ones mapped to 'pcifunc' */
+	for (index = 0; index < mcam->bmap_entries; index++) {
+		if (mcam->entry2pfvf_map[index] == pcifunc) {
+			mcam->entry2pfvf_map[index] = NPC_MCAM_INVALID_MAP;
+			/* Free the entry in bitmap */
+			npc_mcam_clear_bit(mcam, index);
+			/* Disable the entry */
+			npc_enable_mcam_entry(rvu, mcam, blkaddr, index, false);
+
+			/* Update entry2counter mapping */
+			cntr = mcam->entry2cntr_map[index];
+			if (cntr != NPC_MCAM_INVALID_MAP)
+				npc_unmap_mcam_entry_and_cntr(rvu, mcam,
+							      blkaddr, index,
+							      cntr);
+		}
+	}
+}
+
+static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam,
+				       u16 pcifunc)
+{
+	u16 cntr;
+
+	/* Scan all MCAM counters and free the ones mapped to 'pcifunc' */
+	for (cntr = 0; cntr < mcam->counters.max; cntr++) {
+		if (mcam->cntr2pfvf_map[cntr] == pcifunc) {
+			mcam->cntr2pfvf_map[cntr] = NPC_MCAM_INVALID_MAP;
+			mcam->cntr_refcnt[cntr] = 0;
+			rvu_free_rsrc(&mcam->counters, cntr);
+			/* This API is expected to be called after freeing
+			 * MCAM entries, which inturn will remove
+			 * 'entry to counter' mapping.
+			 * No need to do it again.
+			 */
+		}
+	}
+}
+
+/* Find area of contiguous free entries of size 'nr'.
+ * If not found return max contiguous free entries available.
+ */
+static u16 npc_mcam_find_zero_area(unsigned long *map, u16 size, u16 start,
+				   u16 nr, u16 *max_area)
+{
+	u16 max_area_start = 0;
+	u16 index, next, end;
+
+	*max_area = 0;
+
+again:
+	index = find_next_zero_bit(map, size, start);
+	if (index >= size)
+		return max_area_start;
+
+	end = ((index + nr) >= size) ? size : index + nr;
+	next = find_next_bit(map, end, index);
+	if (*max_area < (next - index)) {
+		*max_area = next - index;
+		max_area_start = index;
+	}
+
+	if (next < end) {
+		start = next + 1;
+		goto again;
+	}
+
+	return max_area_start;
+}
+
+/* Find number of free MCAM entries available
+ * within range i.e in between 'start' and 'end'.
+ */
+static u16 npc_mcam_get_free_count(unsigned long *map, u16 start, u16 end)
+{
+	u16 index, next;
+	u16 fcnt = 0;
+
+again:
+	if (start >= end)
+		return fcnt;
+
+	index = find_next_zero_bit(map, end, start);
+	if (index >= end)
+		return fcnt;
+
+	next = find_next_bit(map, end, index);
+	if (next <= end) {
+		fcnt += next - index;
+		start = next + 1;
+		goto again;
+	}
+
+	fcnt += end - index;
+	return fcnt;
+}
+
+static void
+npc_get_mcam_search_range_priority(struct npc_mcam *mcam,
+				   struct npc_mcam_alloc_entry_req *req,
+				   u16 *start, u16 *end, bool *reverse)
+{
+	u16 fcnt;
+
+	if (req->priority == NPC_MCAM_HIGHER_PRIO)
+		goto hprio;
+
+	/* For a low priority entry allocation
+	 * - If reference entry is not in hprio zone then
+	 *      search range: ref_entry to end.
+	 * - If reference entry is in hprio zone and if
+	 *   request can be accomodated in non-hprio zone then
+	 *      search range: 'start of middle zone' to 'end'
+	 * - else search in reverse, so that less number of hprio
+	 *   zone entries are allocated.
+	 */
+
+	*reverse = false;
+	*start = req->ref_entry + 1;
+	*end = mcam->bmap_entries;
+
+	if (req->ref_entry >= mcam->hprio_end)
+		return;
+
+	fcnt = npc_mcam_get_free_count(mcam->bmap,
+				       mcam->hprio_end, mcam->bmap_entries);
+	if (fcnt > req->count)
+		*start = mcam->hprio_end;
+	else
+		*reverse = true;
+	return;
+
+hprio:
+	/* For a high priority entry allocation, search is always
+	 * in reverse to preserve hprio zone entries.
+	 * - If reference entry is not in lprio zone then
+	 *      search range: 0 to ref_entry.
+	 * - If reference entry is in lprio zone and if
+	 *   request can be accomodated in middle zone then
+	 *      search range: 'hprio_end' to 'lprio_start'
+	 */
+
+	*reverse = true;
+	*start = 0;
+	*end = req->ref_entry;
+
+	if (req->ref_entry <= mcam->lprio_start)
+		return;
+
+	fcnt = npc_mcam_get_free_count(mcam->bmap,
+				       mcam->hprio_end, mcam->lprio_start);
+	if (fcnt < req->count)
+		return;
+	*start = mcam->hprio_end;
+	*end = mcam->lprio_start;
+}
+
+static int npc_mcam_alloc_entries(struct npc_mcam *mcam, u16 pcifunc,
+				  struct npc_mcam_alloc_entry_req *req,
+				  struct npc_mcam_alloc_entry_rsp *rsp)
+{
+	u16 entry_list[NPC_MAX_NONCONTIG_ENTRIES];
+	u16 fcnt, hp_fcnt, lp_fcnt;
+	u16 start, end, index;
+	int entry, next_start;
+	bool reverse = false;
+	unsigned long *bmap;
+	u16 max_contig;
+
+	mutex_lock(&mcam->lock);
+
+	/* Check if there are any free entries */
+	if (!mcam->bmap_fcnt) {
+		mutex_unlock(&mcam->lock);
+		return NPC_MCAM_ALLOC_FAILED;
+	}
+
+	/* MCAM entries are divided into high priority, middle and
+	 * low priority zones. Idea is to not allocate top and lower
+	 * most entries as much as possible, this is to increase
+	 * probability of honouring priority allocation requests.
+	 *
+	 * Two bitmaps are used for mcam entry management,
+	 * mcam->bmap for forward search i.e '0 to mcam->bmap_entries'.
+	 * mcam->bmap_reverse for reverse search i.e 'mcam->bmap_entries to 0'.
+	 *
+	 * Reverse bitmap is used to allocate entries
+	 * - when a higher priority entry is requested
+	 * - when available free entries are less.
+	 * Lower priority ones out of avaialble free entries are always
+	 * chosen when 'high vs low' question arises.
+	 */
+
+	/* Get the search range for priority allocation request */
+	if (req->priority) {
+		npc_get_mcam_search_range_priority(mcam, req,
+						   &start, &end, &reverse);
+		goto alloc;
+	}
+
+	/* Find out the search range for non-priority allocation request
+	 *
+	 * Get MCAM free entry count in middle zone.
+	 */
+	lp_fcnt = npc_mcam_get_free_count(mcam->bmap,
+					  mcam->lprio_start,
+					  mcam->bmap_entries);
+	hp_fcnt = npc_mcam_get_free_count(mcam->bmap, 0, mcam->hprio_end);
+	fcnt = mcam->bmap_fcnt - lp_fcnt - hp_fcnt;
+
+	/* Check if request can be accomodated in the middle zone */
+	if (fcnt > req->count) {
+		start = mcam->hprio_end;
+		end = mcam->lprio_start;
+	} else if ((fcnt + (hp_fcnt / 2) + (lp_fcnt / 2)) > req->count) {
+		/* Expand search zone from half of hprio zone to
+		 * half of lprio zone.
+		 */
+		start = mcam->hprio_end / 2;
+		end = mcam->bmap_entries - (mcam->lprio_count / 2);
+		reverse = true;
+	} else {
+		/* Not enough free entries, search all entries in reverse,
+		 * so that low priority ones will get used up.
+		 */
+		reverse = true;
+		start = 0;
+		end = mcam->bmap_entries;
+	}
+
+alloc:
+	if (reverse) {
+		bmap = mcam->bmap_reverse;
+		start = mcam->bmap_entries - start;
+		end = mcam->bmap_entries - end;
+		index = start;
+		start = end;
+		end = index;
+	} else {
+		bmap = mcam->bmap;
+	}
+
+	if (req->contig) {
+		/* Allocate requested number of contiguous entries, if
+		 * unsuccessful find max contiguous entries available.
+		 */
+		index = npc_mcam_find_zero_area(bmap, end, start,
+						req->count, &max_contig);
+		rsp->count = max_contig;
+		if (reverse)
+			rsp->entry = mcam->bmap_entries - index - max_contig;
+		else
+			rsp->entry = index;
+	} else {
+		/* Allocate requested number of non-contiguous entries,
+		 * if unsuccessful allocate as many as possible.
+		 */
+		rsp->count = 0;
+		next_start = start;
+		for (entry = 0; entry < req->count; entry++) {
+			index = find_next_zero_bit(bmap, end, next_start);
+			if (index >= end)
+				break;
+
+			next_start = start + (index - start) + 1;
+
+			/* Save the entry's index */
+			if (reverse)
+				index = mcam->bmap_entries - index - 1;
+			entry_list[entry] = index;
+			rsp->count++;
+		}
+	}
+
+	/* If allocating requested no of entries is unsucessful,
+	 * expand the search range to full bitmap length and retry.
+	 */
+	if (!req->priority && (rsp->count < req->count) &&
+	    ((end - start) != mcam->bmap_entries)) {
+		reverse = true;
+		start = 0;
+		end = mcam->bmap_entries;
+		goto alloc;
+	}
+
+	/* For priority entry allocation requests, if allocation is
+	 * failed then expand search to max possible range and retry.
+	 */
+	if (req->priority && rsp->count < req->count) {
+		if (req->priority == NPC_MCAM_LOWER_PRIO &&
+		    (start != (req->ref_entry + 1))) {
+			start = req->ref_entry + 1;
+			end = mcam->bmap_entries;
+			reverse = false;
+			goto alloc;
+		} else if ((req->priority == NPC_MCAM_HIGHER_PRIO) &&
+			   ((end - start) != req->ref_entry)) {
+			start = 0;
+			end = req->ref_entry;
+			reverse = true;
+			goto alloc;
+		}
+	}
+
+	/* Copy MCAM entry indices into mbox response entry_list.
+	 * Requester always expects indices in ascending order, so
+	 * so reverse the list if reverse bitmap is used for allocation.
+	 */
+	if (!req->contig && rsp->count) {
+		index = 0;
+		for (entry = rsp->count - 1; entry >= 0; entry--) {
+			if (reverse)
+				rsp->entry_list[index++] = entry_list[entry];
+			else
+				rsp->entry_list[entry] = entry_list[entry];
+		}
+	}
+
+	/* Mark the allocated entries as used and set nixlf mapping */
+	for (entry = 0; entry < rsp->count; entry++) {
+		index = req->contig ?
+			(rsp->entry + entry) : rsp->entry_list[entry];
+		npc_mcam_set_bit(mcam, index);
+		mcam->entry2pfvf_map[index] = pcifunc;
+		mcam->entry2cntr_map[index] = NPC_MCAM_INVALID_MAP;
+	}
+
+	/* Update available free count in mbox response */
+	rsp->free_count = mcam->bmap_fcnt;
+
+	mutex_unlock(&mcam->lock);
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_alloc_entry(struct rvu *rvu,
+					  struct npc_mcam_alloc_entry_req *req,
+					  struct npc_mcam_alloc_entry_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	rsp->entry = NPC_MCAM_ENTRY_INVALID;
+	rsp->free_count = 0;
+
+	/* Check if ref_entry is within range */
+	if (req->priority && req->ref_entry >= mcam->bmap_entries)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* ref_entry can't be '0' if requested priority is high.
+	 * Can't be last entry if requested priority is low.
+	 */
+	if ((!req->ref_entry && req->priority == NPC_MCAM_HIGHER_PRIO) ||
+	    ((req->ref_entry == (mcam->bmap_entries - 1)) &&
+	     req->priority == NPC_MCAM_LOWER_PRIO))
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Since list of allocated indices needs to be sent to requester,
+	 * max number of non-contiguous entries per mbox msg is limited.
+	 */
+	if (!req->contig && req->count > NPC_MAX_NONCONTIG_ENTRIES)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Alloc request from PFFUNC with no NIXLF attached should be denied */
+	if (!is_nixlf_attached(rvu, pcifunc))
+		return NPC_MCAM_ALLOC_DENIED;
+
+	return npc_mcam_alloc_entries(mcam, pcifunc, req, rsp);
+}
+
+int rvu_mbox_handler_npc_mcam_free_entry(struct rvu *rvu,
+					 struct npc_mcam_free_entry_req *req,
+					 struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc = 0;
+	u16 cntr;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Free request from PFFUNC with no NIXLF attached, ignore */
+	if (!is_nixlf_attached(rvu, pcifunc))
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+
+	if (req->all)
+		goto free_all;
+
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	if (rc)
+		goto exit;
+
+	mcam->entry2pfvf_map[req->entry] = 0;
+	npc_mcam_clear_bit(mcam, req->entry);
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
+
+	/* Update entry2counter mapping */
+	cntr = mcam->entry2cntr_map[req->entry];
+	if (cntr != NPC_MCAM_INVALID_MAP)
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      req->entry, cntr);
+
+	goto exit;
+
+free_all:
+	/* Free up all entries allocated to requesting PFFUNC */
+	npc_mcam_free_all_entries(rvu, mcam, blkaddr, pcifunc);
+exit:
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
+
+int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu,
+					  struct npc_mcam_write_entry_req *req,
+					  struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	if (rc)
+		goto exit;
+
+	if (req->set_cntr &&
+	    npc_mcam_verify_counter(mcam, pcifunc, req->cntr)) {
+		rc = NPC_MCAM_INVALID_REQ;
+		goto exit;
+	}
+
+	if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX) {
+		rc = NPC_MCAM_INVALID_REQ;
+		goto exit;
+	}
+
+	npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, req->intf,
+			      &req->entry_data, req->enable_entry);
+
+	if (req->set_cntr)
+		npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					    req->entry, req->cntr);
+
+	rc = 0;
+exit:
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
+
+int rvu_mbox_handler_npc_mcam_ena_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	mutex_unlock(&mcam->lock);
+	if (rc)
+		return rc;
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, true);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_dis_entry(struct rvu *rvu,
+					struct npc_mcam_ena_dis_entry_req *req,
+					struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_entry(mcam, pcifunc, req->entry);
+	mutex_unlock(&mcam->lock);
+	if (rc)
+		return rc;
+
+	npc_enable_mcam_entry(rvu, mcam, blkaddr, req->entry, false);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_shift_entry(struct rvu *rvu,
+					  struct npc_mcam_shift_entry_req *req,
+					  struct npc_mcam_shift_entry_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	u16 old_entry, new_entry;
+	u16 index, cntr;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (req->shift_count > NPC_MCAM_MAX_SHIFTS)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	for (index = 0; index < req->shift_count; index++) {
+		old_entry = req->curr_entry[index];
+		new_entry = req->new_entry[index];
+
+		/* Check if both old and new entries are valid and
+		 * does belong to this PFFUNC or not.
+		 */
+		rc = npc_mcam_verify_entry(mcam, pcifunc, old_entry);
+		if (rc)
+			break;
+
+		rc = npc_mcam_verify_entry(mcam, pcifunc, new_entry);
+		if (rc)
+			break;
+
+		/* new_entry should not have a counter mapped */
+		if (mcam->entry2cntr_map[new_entry] != NPC_MCAM_INVALID_MAP) {
+			rc = NPC_MCAM_PERM_DENIED;
+			break;
+		}
+
+		/* Disable the new_entry */
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, false);
+
+		/* Copy rule from old entry to new entry */
+		npc_copy_mcam_entry(rvu, mcam, blkaddr, old_entry, new_entry);
+
+		/* Copy counter mapping, if any */
+		cntr = mcam->entry2cntr_map[old_entry];
+		if (cntr != NPC_MCAM_INVALID_MAP) {
+			npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+						      old_entry, cntr);
+			npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+						    new_entry, cntr);
+		}
+
+		/* Enable new_entry and disable old_entry */
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, new_entry, true);
+		npc_enable_mcam_entry(rvu, mcam, blkaddr, old_entry, false);
+	}
+
+	/* If shift has failed then report the failed index */
+	if (index != req->shift_count) {
+		rc = NPC_MCAM_PERM_DENIED;
+		rsp->failed_entry_idx = index;
+	}
+
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
+
+int rvu_mbox_handler_npc_mcam_alloc_counter(struct rvu *rvu,
+			struct npc_mcam_alloc_counter_req *req,
+			struct npc_mcam_alloc_counter_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 pcifunc = req->hdr.pcifunc;
+	u16 max_contig, cntr;
+	int blkaddr, index;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* If the request is from a PFFUNC with no NIXLF attached, ignore */
+	if (!is_nixlf_attached(rvu, pcifunc))
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Since list of allocated counter IDs needs to be sent to requester,
+	 * max number of non-contiguous counters per mbox msg is limited.
+	 */
+	if (!req->contig && req->count > NPC_MAX_NONCONTIG_COUNTERS)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+
+	/* Check if unused counters are available or not */
+	if (!rvu_rsrc_free_count(&mcam->counters)) {
+		mutex_unlock(&mcam->lock);
+		return NPC_MCAM_ALLOC_FAILED;
+	}
+
+	rsp->count = 0;
+
+	if (req->contig) {
+		/* Allocate requested number of contiguous counters, if
+		 * unsuccessful find max contiguous entries available.
+		 */
+		index = npc_mcam_find_zero_area(mcam->counters.bmap,
+						mcam->counters.max, 0,
+						req->count, &max_contig);
+		rsp->count = max_contig;
+		rsp->cntr = index;
+		for (cntr = index; cntr < (index + max_contig); cntr++) {
+			__set_bit(cntr, mcam->counters.bmap);
+			mcam->cntr2pfvf_map[cntr] = pcifunc;
+		}
+	} else {
+		/* Allocate requested number of non-contiguous counters,
+		 * if unsuccessful allocate as many as possible.
+		 */
+		for (cntr = 0; cntr < req->count; cntr++) {
+			index = rvu_alloc_rsrc(&mcam->counters);
+			if (index < 0)
+				break;
+			rsp->cntr_list[cntr] = index;
+			rsp->count++;
+			mcam->cntr2pfvf_map[index] = pcifunc;
+		}
+	}
+
+	mutex_unlock(&mcam->lock);
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_free_counter(struct rvu *rvu,
+		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 index, entry = 0;
+	int blkaddr, err;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	if (err) {
+		mutex_unlock(&mcam->lock);
+		return err;
+	}
+
+	/* Mark counter as free/unused */
+	mcam->cntr2pfvf_map[req->cntr] = NPC_MCAM_INVALID_MAP;
+	rvu_free_rsrc(&mcam->counters, req->cntr);
+
+	/* Disable all MCAM entry's stats which are using this counter */
+	while (entry < mcam->bmap_entries) {
+		if (!mcam->cntr_refcnt[req->cntr])
+			break;
+
+		index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
+		if (index >= mcam->bmap_entries)
+			break;
+		if (mcam->entry2cntr_map[index] != req->cntr)
+			continue;
+
+		entry = index + 1;
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      index, req->cntr);
+	}
+
+	mutex_unlock(&mcam->lock);
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_unmap_counter(struct rvu *rvu,
+		struct npc_mcam_unmap_counter_req *req, struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 index, entry = 0;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	rc = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	if (rc)
+		goto exit;
+
+	/* Unmap the MCAM entry and counter */
+	if (!req->all) {
+		rc = npc_mcam_verify_entry(mcam, req->hdr.pcifunc, req->entry);
+		if (rc)
+			goto exit;
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      req->entry, req->cntr);
+		goto exit;
+	}
+
+	/* Disable all MCAM entry's stats which are using this counter */
+	while (entry < mcam->bmap_entries) {
+		if (!mcam->cntr_refcnt[req->cntr])
+			break;
+
+		index = find_next_bit(mcam->bmap, mcam->bmap_entries, entry);
+		if (index >= mcam->bmap_entries)
+			break;
+		if (mcam->entry2cntr_map[index] != req->cntr)
+			continue;
+
+		entry = index + 1;
+		npc_unmap_mcam_entry_and_cntr(rvu, mcam, blkaddr,
+					      index, req->cntr);
+	}
+exit:
+	mutex_unlock(&mcam->lock);
+	return rc;
+}
+
+int rvu_mbox_handler_npc_mcam_clear_counter(struct rvu *rvu,
+		struct npc_mcam_oper_counter_req *req, struct msg_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, err;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	mutex_unlock(&mcam->lock);
+	if (err)
+		return err;
+
+	rvu_write64(rvu, blkaddr, NPC_AF_MATCH_STATX(req->cntr), 0x00);
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_counter_stats(struct rvu *rvu,
+			struct npc_mcam_oper_counter_req *req,
+			struct npc_mcam_oper_counter_rsp *rsp)
+{
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, err;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	mutex_lock(&mcam->lock);
+	err = npc_mcam_verify_counter(mcam, req->hdr.pcifunc, req->cntr);
+	mutex_unlock(&mcam->lock);
+	if (err)
+		return err;
+
+	rsp->stat = rvu_read64(rvu, blkaddr, NPC_AF_MATCH_STATX(req->cntr));
+	rsp->stat &= BIT_ULL(48) - 1;
+
+	return 0;
+}
+
+int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu,
+			  struct npc_mcam_alloc_and_write_entry_req *req,
+			  struct npc_mcam_alloc_and_write_entry_rsp *rsp)
+{
+	struct npc_mcam_alloc_counter_req cntr_req;
+	struct npc_mcam_alloc_counter_rsp cntr_rsp;
+	struct npc_mcam_alloc_entry_req entry_req;
+	struct npc_mcam_alloc_entry_rsp entry_rsp;
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	u16 entry = NPC_MCAM_ENTRY_INVALID;
+	u16 cntr = NPC_MCAM_ENTRY_INVALID;
+	int blkaddr, rc;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NPC_MCAM_INVALID_REQ;
+
+	if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX)
+		return NPC_MCAM_INVALID_REQ;
+
+	/* Try to allocate a MCAM entry */
+	entry_req.hdr.pcifunc = req->hdr.pcifunc;
+	entry_req.contig = true;
+	entry_req.priority = req->priority;
+	entry_req.ref_entry = req->ref_entry;
+	entry_req.count = 1;
+
+	rc = rvu_mbox_handler_npc_mcam_alloc_entry(rvu,
+						   &entry_req, &entry_rsp);
+	if (rc)
+		return rc;
+
+	if (!entry_rsp.count)
+		return NPC_MCAM_ALLOC_FAILED;
+
+	entry = entry_rsp.entry;
+
+	if (!req->alloc_cntr)
+		goto write_entry;
+
+	/* Now allocate counter */
+	cntr_req.hdr.pcifunc = req->hdr.pcifunc;
+	cntr_req.contig = true;
+	cntr_req.count = 1;
+
+	rc = rvu_mbox_handler_npc_mcam_alloc_counter(rvu, &cntr_req, &cntr_rsp);
+	if (rc) {
+		/* Free allocated MCAM entry */
+		mutex_lock(&mcam->lock);
+		mcam->entry2pfvf_map[entry] = 0;
+		npc_mcam_clear_bit(mcam, entry);
+		mutex_unlock(&mcam->lock);
+		return rc;
+	}
+
+	cntr = cntr_rsp.cntr;
+
+write_entry:
+	mutex_lock(&mcam->lock);
+	npc_config_mcam_entry(rvu, mcam, blkaddr, entry, req->intf,
+			      &req->entry_data, req->enable_entry);
+
+	if (req->alloc_cntr)
+		npc_map_mcam_entry_and_cntr(rvu, mcam, blkaddr, entry, cntr);
+	mutex_unlock(&mcam->lock);
+
+	rsp->entry = entry;
+	rsp->cntr = cntr;
+
+	return 0;
+}
+
+#define GET_KEX_CFG(intf) \
+	rvu_read64(rvu, BLKADDR_NPC, NPC_AF_INTFX_KEX_CFG(intf))
+
+#define GET_KEX_FLAGS(ld) \
+	rvu_read64(rvu, BLKADDR_NPC, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld))
+
+#define GET_KEX_LD(intf, lid, lt, ld)	\
+	rvu_read64(rvu, BLKADDR_NPC,	\
+		NPC_AF_INTFX_LIDX_LTX_LDX_CFG(intf, lid, lt, ld))
+
+#define GET_KEX_LDFLAGS(intf, ld, fl)	\
+	rvu_read64(rvu, BLKADDR_NPC,	\
+		NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, fl))
+
+int rvu_mbox_handler_npc_get_kex_cfg(struct rvu *rvu, struct msg_req *req,
+				     struct npc_get_kex_cfg_rsp *rsp)
+{
+	int lid, lt, ld, fl;
+
+	rsp->rx_keyx_cfg = GET_KEX_CFG(NIX_INTF_RX);
+	rsp->tx_keyx_cfg = GET_KEX_CFG(NIX_INTF_TX);
+	for (lid = 0; lid < NPC_MAX_LID; lid++) {
+		for (lt = 0; lt < NPC_MAX_LT; lt++) {
+			for (ld = 0; ld < NPC_MAX_LD; ld++) {
+				rsp->intf_lid_lt_ld[NIX_INTF_RX][lid][lt][ld] =
+					GET_KEX_LD(NIX_INTF_RX, lid, lt, ld);
+				rsp->intf_lid_lt_ld[NIX_INTF_TX][lid][lt][ld] =
+					GET_KEX_LD(NIX_INTF_TX, lid, lt, ld);
+			}
+		}
+	}
+	for (ld = 0; ld < NPC_MAX_LD; ld++)
+		rsp->kex_ld_flags[ld] = GET_KEX_FLAGS(ld);
+
+	for (ld = 0; ld < NPC_MAX_LD; ld++) {
+		for (fl = 0; fl < NPC_MAX_LFL; fl++) {
+			rsp->intf_ld_flags[NIX_INTF_RX][ld][fl] =
+					GET_KEX_LDFLAGS(NIX_INTF_RX, ld, fl);
+			rsp->intf_ld_flags[NIX_INTF_TX][ld][fl] =
+					GET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl);
+		}
+	}
+	memcpy(rsp->mkex_pfl_name, rvu->mkex_pfl_name, MKEX_NAME_LEN);
+	return 0;
+}
+
+int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf)
+{
+	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
+	struct npc_mcam *mcam = &rvu->hw->mcam;
+	int blkaddr, index;
+	bool enable;
+
+	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0);
+	if (blkaddr < 0)
+		return NIX_AF_ERR_AF_LF_INVALID;
+
+	if (!pfvf->rxvlan)
+		return 0;
+
+	index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf,
+					 NIXLF_UCAST_ENTRY);
+	pfvf->entry.action = npc_get_mcam_action(rvu, mcam, blkaddr, index);
+	enable = is_mcam_entry_enabled(rvu, mcam, blkaddr, index);
+	npc_config_mcam_entry(rvu, mcam, blkaddr, pfvf->rxvlan_index,
+			      NIX_INTF_RX, &pfvf->entry, enable);
+
+	return 0;
 }
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index 0bd4351b2a49..35f2142aac5e 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -201,6 +201,7 @@ struct tx_desc {
 };
 
 struct pxa168_eth_private {
+	struct platform_device *pdev;
 	int port_num;		/* User Ethernet port number    */
 	int phy_addr;
 	int phy_speed;
@@ -331,7 +332,7 @@ static void rxq_refill(struct net_device *dev)
 		used_rx_desc = pep->rx_used_desc_q;
 		p_used_rx_desc = &pep->p_rx_desc_area[used_rx_desc];
 		size = skb_end_pointer(skb) - skb->data;
-		p_used_rx_desc->buf_ptr = dma_map_single(NULL,
+		p_used_rx_desc->buf_ptr = dma_map_single(&pep->pdev->dev,
 							 skb->data,
 							 size,
 							 DMA_FROM_DEVICE);
@@ -557,9 +558,9 @@ static int init_hash_table(struct pxa168_eth_private *pep)
 	 * table is full.
 	 */
 	if (!pep->htpr) {
-		pep->htpr = dma_zalloc_coherent(pep->dev->dev.parent,
-						HASH_ADDR_TABLE_SIZE,
-						&pep->htpr_dma, GFP_KERNEL);
+		pep->htpr = dma_alloc_coherent(pep->dev->dev.parent,
+					       HASH_ADDR_TABLE_SIZE,
+					       &pep->htpr_dma, GFP_KERNEL);
 		if (!pep->htpr)
 			return -ENOMEM;
 	} else {
@@ -743,7 +744,7 @@ static int txq_reclaim(struct net_device *dev, int force)
 				netdev_err(dev, "Error in TX\n");
 			dev->stats.tx_errors++;
 		}
-		dma_unmap_single(NULL, addr, count, DMA_TO_DEVICE);
+		dma_unmap_single(&pep->pdev->dev, addr, count, DMA_TO_DEVICE);
 		if (skb)
 			dev_kfree_skb_irq(skb);
 		released++;
@@ -805,7 +806,7 @@ static int rxq_process(struct net_device *dev, int budget)
 		if (rx_next_curr_desc == rx_used_desc)
 			pep->rx_resource_err = 1;
 		pep->rx_desc_count--;
-		dma_unmap_single(NULL, rx_desc->buf_ptr,
+		dma_unmap_single(&pep->pdev->dev, rx_desc->buf_ptr,
 				 rx_desc->buf_size,
 				 DMA_FROM_DEVICE);
 		received_packets++;
@@ -1044,9 +1045,9 @@ static int rxq_init(struct net_device *dev)
 	pep->rx_desc_count = 0;
 	size = pep->rx_ring_size * sizeof(struct rx_desc);
 	pep->rx_desc_area_size = size;
-	pep->p_rx_desc_area = dma_zalloc_coherent(pep->dev->dev.parent, size,
-						  &pep->rx_desc_dma,
-						  GFP_KERNEL);
+	pep->p_rx_desc_area = dma_alloc_coherent(pep->dev->dev.parent, size,
+						 &pep->rx_desc_dma,
+						 GFP_KERNEL);
 	if (!pep->p_rx_desc_area)
 		goto out;
 
@@ -1103,9 +1104,9 @@ static int txq_init(struct net_device *dev)
 	pep->tx_desc_count = 0;
 	size = pep->tx_ring_size * sizeof(struct tx_desc);
 	pep->tx_desc_area_size = size;
-	pep->p_tx_desc_area = dma_zalloc_coherent(pep->dev->dev.parent, size,
-						  &pep->tx_desc_dma,
-						  GFP_KERNEL);
+	pep->p_tx_desc_area = dma_alloc_coherent(pep->dev->dev.parent, size,
+						 &pep->tx_desc_dma,
+						 GFP_KERNEL);
 	if (!pep->p_tx_desc_area)
 		goto out;
 	/* Initialize the next_desc_ptr links in the Tx descriptors ring */
@@ -1274,7 +1275,8 @@ pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	length = skb->len;
 	pep->tx_skb[tx_index] = skb;
 	desc->byte_cnt = length;
-	desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE);
+	desc->buf_ptr = dma_map_single(&pep->pdev->dev, skb->data, length,
+					DMA_TO_DEVICE);
 
 	skb_tx_timestamp(skb);
 
@@ -1528,6 +1530,7 @@ static int pxa168_eth_probe(struct platform_device *pdev)
 	if (err)
 		goto err_free_mdio;
 
+	pep->pdev = pdev;
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	pxa168_init_hw(pep);
 	err = register_netdev(dev);
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index 9c08c3650c02..654ac534b10e 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	memset(p, 0, regs->len);
 	memcpy_fromio(p, io, B3_RAM_ADDR);
 
-	memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
-		      regs->len - B3_RI_WTO_R1);
+	if (regs->len > B3_RI_WTO_R1) {
+		memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1,
+			      regs->len - B3_RI_WTO_R1);
+	}
 }
 
 /* Wake on Lan only supported on Yukon chips with rev 1 or above */
@@ -3732,19 +3734,7 @@ static int skge_debug_show(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int skge_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, skge_debug_show, inode->i_private);
-}
-
-static const struct file_operations skge_debug_fops = {
-	.owner		= THIS_MODULE,
-	.open		= skge_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(skge_debug);
 
 /*
  * Use network device events to create/remove/rename
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index 697d9b374f5e..8b3495ee2b6e 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -46,6 +46,7 @@
 #include <linux/mii.h>
 #include <linux/of_device.h>
 #include <linux/of_net.h>
+#include <linux/dmi.h>
 
 #include <asm/irq.h>
 
@@ -93,7 +94,7 @@ static int copybreak __read_mostly = 128;
 module_param(copybreak, int, 0);
 MODULE_PARM_DESC(copybreak, "Receive copy threshold");
 
-static int disable_msi = 0;
+static int disable_msi = -1;
 module_param(disable_msi, int, 0);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
@@ -2485,13 +2486,11 @@ static struct sk_buff *receive_copy(struct sky2_port *sky2,
 		skb->ip_summed = re->skb->ip_summed;
 		skb->csum = re->skb->csum;
 		skb_copy_hash(skb, re->skb);
-		skb->vlan_proto = re->skb->vlan_proto;
-		skb->vlan_tci = re->skb->vlan_tci;
+		__vlan_hwaccel_copy_tag(skb, re->skb);
 
 		pci_dma_sync_single_for_device(sky2->hw->pdev, re->data_addr,
 					       length, PCI_DMA_FROMDEVICE);
-		re->skb->vlan_proto = 0;
-		re->skb->vlan_tci = 0;
+		__vlan_hwaccel_clear_tag(re->skb);
 		skb_clear_hash(re->skb);
 		re->skb->ip_summed = CHECKSUM_NONE;
 		skb_put(skb, length);
@@ -4623,19 +4622,7 @@ static int sky2_debug_show(struct seq_file *seq, void *v)
 	napi_enable(&hw->napi);
 	return 0;
 }
-
-static int sky2_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, sky2_debug_show, inode->i_private);
-}
-
-static const struct file_operations sky2_debug_fops = {
-	.owner		= THIS_MODULE,
-	.open		= sky2_debug_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(sky2_debug);
 
 /*
  * Use network device events to create/remove/rename
@@ -4931,6 +4918,24 @@ static const char *sky2_name(u8 chipid, char *buf, int sz)
 	return buf;
 }
 
+static const struct dmi_system_id msi_blacklist[] = {
+	{
+		.ident = "Dell Inspiron 1545",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Inspiron 1545"),
+		},
+	},
+	{
+		.ident = "Gateway P-79",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Gateway"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P-79"),
+		},
+	},
+	{}
+};
+
 static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	struct net_device *dev, *dev1;
@@ -5042,6 +5047,9 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_out_free_pci;
 	}
 
+	if (disable_msi == -1)
+		disable_msi = !!dmi_check_system(msi_blacklist);
+
 	if (!disable_msi && pci_enable_msi(pdev) == 0) {
 		err = sky2_test_msi(hw);
 		if (err) {
@@ -5087,7 +5095,7 @@ static int sky2_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	INIT_WORK(&hw->restart_work, sky2_restart);
 
 	pci_set_drvdata(pdev, hw);
-	pdev->d3_delay = 200;
+	pdev->d3_delay = 300;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index f9149d2a4694..43656f961891 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -1,6 +1,6 @@
 config NET_VENDOR_MEDIATEK
 	bool "MediaTek ethernet driver"
-	depends on ARCH_MEDIATEK
+	depends on ARCH_MEDIATEK || SOC_MT7621
 	---help---
 	  If you have a Mediatek SoC with ethernet, say Y.
 
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 7dbfdac4067a..549d36497b8c 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -226,7 +226,7 @@ static void mtk_phy_link_adjust(struct net_device *dev)
 	case SPEED_100:
 		mcr |= MAC_MCR_SPEED_100;
 		break;
-	};
+	}
 
 	if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII) &&
 	    !mac->id && !mac->trgmii)
@@ -243,7 +243,7 @@ static void mtk_phy_link_adjust(struct net_device *dev)
 		if (dev->phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = ethtool_adv_to_lcl_adv_t(dev->phydev->advertising);
+		lcl_adv = linkmode_adv_to_lcl_adv_t(dev->phydev->advertising);
 		flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 
 		if (flowctrl & FLOW_CTRL_TX)
@@ -258,11 +258,6 @@ static void mtk_phy_link_adjust(struct net_device *dev)
 
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 
-	if (dev->phydev->link)
-		netif_carrier_on(dev);
-	else
-		netif_carrier_off(dev);
-
 	if (!of_phy_is_fixed_link(mac->of_node))
 		phy_print_status(dev->phydev);
 }
@@ -347,16 +342,6 @@ static int mtk_phy_connect(struct net_device *dev)
 	if (mtk_phy_connect_node(eth, mac, np))
 		goto err_phy;
 
-	dev->phydev->autoneg = AUTONEG_ENABLE;
-	dev->phydev->speed = 0;
-	dev->phydev->duplex = 0;
-
-	phy_set_max_speed(dev->phydev, SPEED_1000);
-	phy_support_asym_pause(dev->phydev);
-	dev->phydev->advertising = dev->phydev->supported |
-				    ADVERTISED_Autoneg;
-	phy_start_aneg(dev->phydev);
-
 	of_node_put(np);
 
 	return 0;
@@ -597,10 +582,10 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	dma_addr_t dma_addr;
 	int i;
 
-	eth->scratch_ring = dma_zalloc_coherent(eth->dev,
-						cnt * sizeof(struct mtk_tx_dma),
-						&eth->phy_scratch_ring,
-						GFP_ATOMIC);
+	eth->scratch_ring = dma_alloc_coherent(eth->dev,
+					       cnt * sizeof(struct mtk_tx_dma),
+					       &eth->phy_scratch_ring,
+					       GFP_ATOMIC);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
@@ -1212,8 +1197,8 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	if (!ring->buf)
 		goto no_tx_mem;
 
-	ring->dma = dma_zalloc_coherent(eth->dev, MTK_DMA_SIZE * sz,
-					&ring->phys, GFP_ATOMIC);
+	ring->dma = dma_alloc_coherent(eth->dev, MTK_DMA_SIZE * sz,
+				       &ring->phys, GFP_ATOMIC);
 	if (!ring->dma)
 		goto no_tx_mem;
 
@@ -1309,9 +1294,9 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 			return -ENOMEM;
 	}
 
-	ring->dma = dma_zalloc_coherent(eth->dev,
-					rx_dma_size * sizeof(*ring->dma),
-					&ring->phys, GFP_ATOMIC);
+	ring->dma = dma_alloc_coherent(eth->dev,
+				       rx_dma_size * sizeof(*ring->dma),
+				       &ring->phys, GFP_ATOMIC);
 	if (!ring->dma)
 		return -ENOMEM;
 
@@ -1760,6 +1745,22 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t mtk_handle_irq(int irq, void *_eth)
+{
+	struct mtk_eth *eth = _eth;
+
+	if (mtk_r32(eth, MTK_PDMA_INT_MASK) & MTK_RX_DONE_INT) {
+		if (mtk_r32(eth, MTK_PDMA_INT_STATUS) & MTK_RX_DONE_INT)
+			mtk_handle_irq_rx(irq, _eth);
+	}
+	if (mtk_r32(eth, MTK_QDMA_INT_MASK) & MTK_TX_DONE_INT) {
+		if (mtk_r32(eth, MTK_QMTK_INT_STATUS) & MTK_TX_DONE_INT)
+			mtk_handle_irq_tx(irq, _eth);
+	}
+
+	return IRQ_HANDLED;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void mtk_poll_controller(struct net_device *dev)
 {
@@ -2500,7 +2501,10 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	for (i = 0; i < 3; i++) {
-		eth->irq[i] = platform_get_irq(pdev, i);
+		if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT) && i > 0)
+			eth->irq[i] = eth->irq[0];
+		else
+			eth->irq[i] = platform_get_irq(pdev, i);
 		if (eth->irq[i] < 0) {
 			dev_err(&pdev->dev, "no IRQ%d resource found\n", i);
 			return -ENXIO;
@@ -2543,13 +2547,21 @@ static int mtk_probe(struct platform_device *pdev)
 			goto err_deinit_hw;
 	}
 
-	err = devm_request_irq(eth->dev, eth->irq[1], mtk_handle_irq_tx, 0,
-			       dev_name(eth->dev), eth);
-	if (err)
-		goto err_free_dev;
+	if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT)) {
+		err = devm_request_irq(eth->dev, eth->irq[0],
+				       mtk_handle_irq, 0,
+				       dev_name(eth->dev), eth);
+	} else {
+		err = devm_request_irq(eth->dev, eth->irq[1],
+				       mtk_handle_irq_tx, 0,
+				       dev_name(eth->dev), eth);
+		if (err)
+			goto err_free_dev;
 
-	err = devm_request_irq(eth->dev, eth->irq[2], mtk_handle_irq_rx, 0,
-			       dev_name(eth->dev), eth);
+		err = devm_request_irq(eth->dev, eth->irq[2],
+				       mtk_handle_irq_rx, 0,
+				       dev_name(eth->dev), eth);
+	}
 	if (err)
 		goto err_free_dev;
 
@@ -2622,6 +2634,12 @@ static const struct mtk_soc_data mt2701_data = {
 	.required_pctl = true,
 };
 
+static const struct mtk_soc_data mt7621_data = {
+	.caps = MTK_SHARED_INT,
+	.required_clks = MT7621_CLKS_BITMAP,
+	.required_pctl = false,
+};
+
 static const struct mtk_soc_data mt7622_data = {
 	.caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW | MTK_HWLRO,
 	.required_clks = MT7622_CLKS_BITMAP,
@@ -2636,6 +2654,7 @@ static const struct mtk_soc_data mt7623_data = {
 
 const struct of_device_id of_mtk_match[] = {
 	{ .compatible = "mediatek,mt2701-eth", .data = &mt2701_data},
+	{ .compatible = "mediatek,mt7621-eth", .data = &mt7621_data},
 	{ .compatible = "mediatek,mt7622-eth", .data = &mt7622_data},
 	{ .compatible = "mediatek,mt7623-eth", .data = &mt7623_data},
 	{},
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 46819297fc3e..f7501997cea0 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -363,6 +363,7 @@
 #define ETHSYS_CHIPID4_7	0x4
 #define MT7623_ETH		7623
 #define MT7622_ETH		7622
+#define MT7621_ETH		7621
 
 /* ethernet subsystem config register */
 #define ETHSYS_SYSCFG0		0x14
@@ -488,6 +489,8 @@ enum mtk_clks_map {
 				 BIT(MTK_CLK_SGMII_CDR_FB) | \
 				 BIT(MTK_CLK_SGMII_CK) | \
 				 BIT(MTK_CLK_ETH2PLL))
+#define MT7621_CLKS_BITMAP	(0)
+
 enum mtk_dev_state {
 	MTK_HW_INIT,
 	MTK_RESETTING
@@ -567,6 +570,7 @@ struct mtk_rx_ring {
 #define MTK_DUAL_GMAC_SHARED_SGMII	(BIT(11) | MTK_GMAC1_SGMII | \
 					 MTK_GMAC2_SGMII)
 #define MTK_HWLRO			BIT(12)
+#define MTK_SHARED_INT			BIT(13)
 #define MTK_HAS_CAPS(caps, _x)		(((caps) & (_x)) == (_x))
 
 /* struct mtk_eth_data -	This is the structure holding all differences
diff --git a/drivers/net/ethernet/mellanox/mlx4/Kconfig b/drivers/net/ethernet/mellanox/mlx4/Kconfig
index f200b8c420d5..ff8057ed97ee 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx4/Kconfig
@@ -4,7 +4,6 @@
 
 config MLX4_EN
 	tristate "Mellanox Technologies 1/10/40Gbit Ethernet support"
-	depends on MAY_USE_DEVLINK
 	depends on PCI && NETDEVICES && ETHERNET && INET
 	select MLX4_CORE
 	imply PTP_1588_CLOCK
diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index 9af34e03892c..b330020dc0d6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -185,8 +185,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 	bitmap->avail = num - reserved_top - reserved_bot;
 	bitmap->effective_len = bitmap->avail;
 	spin_lock_init(&bitmap->lock);
-	bitmap->table = kcalloc(BITS_TO_LONGS(bitmap->max), sizeof(long),
-				GFP_KERNEL);
+	bitmap->table = bitmap_zalloc(bitmap->max, GFP_KERNEL);
 	if (!bitmap->table)
 		return -ENOMEM;
 
@@ -197,7 +196,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 
 void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap)
 {
-	kfree(bitmap->table);
+	bitmap_free(bitmap->table);
 }
 
 struct mlx4_zone_allocator {
@@ -584,8 +583,8 @@ static int mlx4_buf_direct_alloc(struct mlx4_dev *dev, int size,
 	buf->npages       = 1;
 	buf->page_shift   = get_order(size) + PAGE_SHIFT;
 	buf->direct.buf   =
-		dma_zalloc_coherent(&dev->persist->pdev->dev,
-				    size, &t, GFP_KERNEL);
+		dma_alloc_coherent(&dev->persist->pdev->dev, size, &t,
+				   GFP_KERNEL);
 	if (!buf->direct.buf)
 		return -ENOMEM;
 
@@ -624,8 +623,8 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 
 		for (i = 0; i < buf->nbufs; ++i) {
 			buf->page_list[i].buf =
-				dma_zalloc_coherent(&dev->persist->pdev->dev,
-						    PAGE_SIZE, &t, GFP_KERNEL);
+				dma_alloc_coherent(&dev->persist->pdev->dev,
+						   PAGE_SIZE, &t, GFP_KERNEL);
 			if (!buf->page_list[i].buf)
 				goto err_free;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index e65bc3c95630..a5d5d6fc1da0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -2645,6 +2645,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	if (!priv->cmd.context)
 		return -ENOMEM;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	for (i = 0; i < priv->cmd.max_cmds; ++i) {
 		priv->cmd.context[i].token = i;
@@ -2670,6 +2672,8 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 	down(&priv->cmd.poll_sem);
 	priv->cmd.use_events = 1;
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 
 	return err;
 }
@@ -2682,6 +2686,8 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
 
+	if (mlx4_is_mfunc(dev))
+		mutex_lock(&priv->cmd.slave_cmd_mutex);
 	down_write(&priv->cmd.switch_sem);
 	priv->cmd.use_events = 0;
 
@@ -2689,9 +2695,12 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev)
 		down(&priv->cmd.event_sem);
 
 	kfree(priv->cmd.context);
+	priv->cmd.context = NULL;
 
 	up(&priv->cmd.poll_sem);
 	up_write(&priv->cmd.switch_sem);
+	if (mlx4_is_mfunc(dev))
+		mutex_unlock(&priv->cmd.slave_cmd_mutex);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
@@ -3274,7 +3283,7 @@ int mlx4_set_vf_link_state(struct mlx4_dev *dev, int port, int vf, int link_stat
 		mlx4_warn(dev, "unknown value for link_state %02x on slave %d port %d\n",
 			  link_state, slave, port);
 		return -EINVAL;
-	};
+	}
 	s_info = &priv->mfunc.master.vf_admin[slave].vport[port];
 	s_info->link_state = link_state;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index d8e9a323122e..65f8a4b6ed0c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -144,9 +144,9 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
 }
 
 static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
-			 int cq_num)
+			 int cq_num, u8 opmod)
 {
-	return mlx4_cmd(dev, mailbox->dma, cq_num, 0,
+	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod,
 			MLX4_CMD_SW2HW_CQ, MLX4_CMD_TIME_CLASS_A,
 			MLX4_CMD_WRAPPED);
 }
@@ -287,11 +287,63 @@ static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
 		__mlx4_cq_free_icm(dev, cqn);
 }
 
+static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size)
+{
+	int entries_per_copy = PAGE_SIZE / cqe_size;
+	void *init_ents;
+	int err = 0;
+	int i;
+
+	init_ents = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!init_ents)
+		return -ENOMEM;
+
+	/* Populate a list of CQ entries to reduce the number of
+	 * copy_to_user calls. 0xcc is the initialization value
+	 * required by the FW.
+	 */
+	memset(init_ents, 0xcc, PAGE_SIZE);
+
+	if (entries_per_copy < entries) {
+		for (i = 0; i < entries / entries_per_copy; i++) {
+			err = copy_to_user((void __user *)buf, init_ents, PAGE_SIZE) ?
+				-EFAULT : 0;
+			if (err)
+				goto out;
+
+			buf += PAGE_SIZE;
+		}
+	} else {
+		err = copy_to_user((void __user *)buf, init_ents, entries * cqe_size) ?
+			-EFAULT : 0;
+	}
+
+out:
+	kfree(init_ents);
+
+	return err;
+}
+
+static void mlx4_init_kernel_cqes(struct mlx4_buf *buf,
+				  int entries,
+				  int cqe_size)
+{
+	int i;
+
+	if (buf->nbufs == 1)
+		memset(buf->direct.buf, 0xcc, entries * cqe_size);
+	else
+		for (i = 0; i < buf->npages; i++)
+			memset(buf->page_list[i].buf, 0xcc,
+			       1UL << buf->page_shift);
+}
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 		  struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec,
 		  struct mlx4_cq *cq, unsigned vector, int collapsed,
-		  int timestamp_en)
+		  int timestamp_en, void *buf_addr, bool user_cq)
 {
+	bool sw_cq_init = dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SW_CQ_INIT;
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cq_table *cq_table = &priv->cq_table;
 	struct mlx4_cmd_mailbox *mailbox;
@@ -336,7 +388,20 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
 	cq_context->db_rec_addr     = cpu_to_be64(db_rec);
 
-	err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn);
+	if (sw_cq_init) {
+		if (user_cq) {
+			err = mlx4_init_user_cqes(buf_addr, nent,
+						  dev->caps.cqe_size);
+			if (err)
+				sw_cq_init = false;
+		} else {
+			mlx4_init_kernel_cqes(buf_addr, nent,
+					      dev->caps.cqe_size);
+		}
+	}
+
+	err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn, sw_cq_init);
+
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	if (err)
 		goto err_radix;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 1e487acb4667..74d466796b7c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -54,11 +54,8 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 
 	cq = kzalloc_node(sizeof(*cq), GFP_KERNEL, node);
 	if (!cq) {
-		cq = kzalloc(sizeof(*cq), GFP_KERNEL);
-		if (!cq) {
-			en_err(priv, "Failed to allocate CQ structure\n");
-			return -ENOMEM;
-		}
+		en_err(priv, "Failed to allocate CQ structure\n");
+		return -ENOMEM;
 	}
 
 	cq->size = entries;
@@ -143,7 +140,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 	cq->mcq.usage = MLX4_RES_USAGE_DRIVER;
 	err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt,
 			    &mdev->priv_uar, cq->wqres.db.dma, &cq->mcq,
-			    cq->vector, 0, timestamp_en);
+			    cq->vector, 0, timestamp_en, &cq->wqres.buf, false);
 	if (err)
 		goto free_eq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 6b88881b8e35..c1438ae52a11 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -3360,7 +3360,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	dev->addr_len = ETH_ALEN;
 	mlx4_en_u64_to_mac(dev->dev_addr, mdev->dev->caps.def_mac[priv->port]);
 	if (!is_valid_ether_addr(dev->dev_addr)) {
-		en_err(priv, "Port: %d, invalid mac burned: %pM, quiting\n",
+		en_err(priv, "Port: %d, invalid mac burned: %pM, quitting\n",
 		       priv->port, dev->dev_addr);
 		err = -EINVAL;
 		goto out;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index db00bf1c23f5..6c01314e87b0 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -271,11 +271,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 
 	ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
 	if (!ring) {
-		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-		if (!ring) {
-			en_err(priv, "Failed to allocate RX ring structure\n");
-			return -ENOMEM;
-		}
+		en_err(priv, "Failed to allocate RX ring structure\n");
+		return -ENOMEM;
 	}
 
 	ring->prod = 0;
@@ -620,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb,
 }
 #endif
 
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
+
 /* We reach this function only after checking that any of
  * the (IPv4 | IPv6) bits are set in cqe->status.
  */
@@ -627,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va,
 		      netdev_features_t dev_features)
 {
 	__wsum hw_checksum = 0;
+	void *hdr;
+
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to skip
+	 * checksum complete.
+	 */
+	if (short_frame(skb->len))
+		return -EINVAL;
 
-	void *hdr = (u8 *)va + sizeof(struct ethhdr);
-
+	hdr = (u8 *)va + sizeof(struct ethhdr);
 	hw_checksum = csum_unfold((__force __sum16)cqe->checksum);
 
 	if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) &&
@@ -822,6 +832,11 @@ xdp_drop_no_cnt:
 		skb_record_rx_queue(skb, cq_ring);
 
 		if (likely(dev->features & NETIF_F_RXCSUM)) {
+			/* TODO: For IP non TCP/UDP packets when csum complete is
+			 * not an option (not supported or any other reason) we can
+			 * actually check cqe IPOK status bit and report
+			 * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE
+			 */
 			if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP |
 						       MLX4_CQE_STATUS_UDP)) &&
 			    (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) &&
@@ -875,7 +890,7 @@ csum_none:
 			skb->data_len = length;
 			napi_gro_frags(&cq->napi);
 		} else {
-			skb->vlan_tci = 0;
+			__vlan_hwaccel_clear_tag(skb);
 			skb_clear_hash(skb);
 		}
 next:
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 6f5153afcab4..2cbd2bd7c67c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -57,11 +57,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 
 	ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, node);
 	if (!ring) {
-		ring = kzalloc(sizeof(*ring), GFP_KERNEL);
-		if (!ring) {
-			en_err(priv, "Failed allocating TX ring\n");
-			return -ENOMEM;
-		}
+		en_err(priv, "Failed allocating TX ring\n");
+		return -ENOMEM;
 	}
 
 	ring->size = size;
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 2df92dbd38e1..a5be27772b8e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -100,7 +100,7 @@ static void eq_set_ci(struct mlx4_eq *eq, int req_not)
 					       req_not << 31),
 		     eq->doorbell);
 	/* We still want ordering, just not swabbing, so add a barrier */
-	mb();
+	wmb();
 }
 
 static struct mlx4_eqe *get_eqe(struct mlx4_eq *eq, u32 entry, u8 eqe_factor,
@@ -558,6 +558,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			mlx4_dbg(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT. srq_no=0x%x, eq 0x%x\n",
 				 __func__, be32_to_cpu(eqe->event.srq.srqn),
 				 eq->eqn);
+			/* fall through */
 		case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
 			if (mlx4_is_master(dev)) {
 				/* forward only to slave owning the SRQ */
@@ -820,7 +821,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				  !!(eqe->owner & 0x80) ^
 				  !!(eq->cons_index & eq->nent) ? "HW" : "SW");
 			break;
-		};
+		}
 
 		++eq->cons_index;
 		eqes_found = 1;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index babcfd9c0571..6e501af0e532 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -166,6 +166,7 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[37] = "sl to vl mapping table change event support",
 		[38] = "user MAC support",
 		[39] = "Report driver version to FW support",
+		[40] = "SW CQ initialization support",
 	};
 	int i;
 
@@ -1098,6 +1099,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FSM;
 	if (field32 & (1 << 21))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_80_VFS;
+	if (field32 & (1 << 23))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_SW_CQ_INIT;
 
 	for (i = 1; i <= dev_cap->num_ports; i++) {
 		err = mlx4_QUERY_PORT(dev, i, dev_cap->port_cap + i);
@@ -2064,9 +2067,11 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *outbox;
+	u64 qword_field;
 	u32 dword_field;
-	int err;
+	u16 word_field;
 	u8 byte_field;
+	int err;
 	static const u8 a0_dmfs_query_hw_steering[] =  {
 		[0] = MLX4_STEERING_DMFS_A0_DEFAULT,
 		[1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
@@ -2094,19 +2099,32 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 
 	/* QPC/EEC/CQC/EQC/RDMARC attributes */
 
-	MLX4_GET(param->qpc_base,      outbox, INIT_HCA_QPC_BASE_OFFSET);
-	MLX4_GET(param->log_num_qps,   outbox, INIT_HCA_LOG_QP_OFFSET);
-	MLX4_GET(param->srqc_base,     outbox, INIT_HCA_SRQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_srqs,  outbox, INIT_HCA_LOG_SRQ_OFFSET);
-	MLX4_GET(param->cqc_base,      outbox, INIT_HCA_CQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_cqs,   outbox, INIT_HCA_LOG_CQ_OFFSET);
-	MLX4_GET(param->altc_base,     outbox, INIT_HCA_ALTC_BASE_OFFSET);
-	MLX4_GET(param->auxc_base,     outbox, INIT_HCA_AUXC_BASE_OFFSET);
-	MLX4_GET(param->eqc_base,      outbox, INIT_HCA_EQC_BASE_OFFSET);
-	MLX4_GET(param->log_num_eqs,   outbox, INIT_HCA_LOG_EQ_OFFSET);
-	MLX4_GET(param->num_sys_eqs,   outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
-	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
-	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
+	MLX4_GET(qword_field, outbox, INIT_HCA_QPC_BASE_OFFSET);
+	param->qpc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_QP_OFFSET);
+	param->log_num_qps = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_SRQC_BASE_OFFSET);
+	param->srqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_SRQ_OFFSET);
+	param->log_num_srqs = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_CQC_BASE_OFFSET);
+	param->cqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_CQ_OFFSET);
+	param->log_num_cqs = byte_field & 0x1f;
+	MLX4_GET(qword_field, outbox, INIT_HCA_ALTC_BASE_OFFSET);
+	param->altc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_AUXC_BASE_OFFSET);
+	param->auxc_base = qword_field;
+	MLX4_GET(qword_field, outbox, INIT_HCA_EQC_BASE_OFFSET);
+	param->eqc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_EQ_OFFSET);
+	param->log_num_eqs = byte_field & 0x1f;
+	MLX4_GET(word_field, outbox, INIT_HCA_NUM_SYS_EQS_OFFSET);
+	param->num_sys_eqs = word_field & 0xfff;
+	MLX4_GET(qword_field, outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+	param->rdmarc_base = qword_field & ~((u64)0x1f);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_RD_OFFSET);
+	param->log_rd_per_qp = byte_field & 0x7;
 
 	MLX4_GET(dword_field, outbox, INIT_HCA_FLAGS_OFFSET);
 	if (dword_field & (1 << INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN)) {
@@ -2125,22 +2143,21 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* steering attributes */
 	if (param->steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_FS_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
-			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
-		MLX4_GET(param->log_mc_table_sz, outbox,
-			 INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
-		MLX4_GET(byte_field, outbox,
-			 INIT_HCA_FS_A0_OFFSET);
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_FS_A0_OFFSET);
 		param->dmfs_high_steer_mode =
 			a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
 	} else {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
-		MLX4_GET(param->log_mc_entry_sz, outbox,
-			 INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
-		MLX4_GET(param->log_mc_hash_sz,  outbox,
-			 INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
-		MLX4_GET(param->log_mc_table_sz, outbox,
-			 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+		param->log_mc_entry_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field,  outbox, INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+		param->log_mc_hash_sz = byte_field & 0x1f;
+		MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+		param->log_mc_table_sz = byte_field & 0x1f;
 	}
 
 	/* CX3 is capable of extending CQEs/EQEs from 32 to 64 bytes */
@@ -2164,15 +2181,18 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	/* TPT attributes */
 
 	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
-	MLX4_GET(param->mw_enabled, outbox, INIT_HCA_TPT_MW_OFFSET);
-	MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_TPT_MW_OFFSET);
+	param->mw_enabled = byte_field >> 7;
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	param->log_mpt_sz = byte_field & 0x3f;
 	MLX4_GET(param->mtt_base,   outbox, INIT_HCA_MTT_BASE_OFFSET);
 	MLX4_GET(param->cmpt_base,  outbox, INIT_HCA_CMPT_BASE_OFFSET);
 
 	/* UAR attributes */
 
 	MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
-	MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	MLX4_GET(byte_field, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+	param->log_uar_sz = byte_field & 0xf;
 
 	/* phv_check enable */
 	MLX4_GET(byte_field, outbox, INIT_HCA_CACHELINE_SZ_OFFSET);
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 4b4351141b94..d89a3da89e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -57,12 +57,12 @@ static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chu
 	int i;
 
 	if (chunk->nsg > 0)
-		pci_unmap_sg(dev->persist->pdev, chunk->mem, chunk->npages,
-			     PCI_DMA_BIDIRECTIONAL);
+		dma_unmap_sg(&dev->persist->pdev->dev, chunk->sg, chunk->npages,
+			     DMA_BIDIRECTIONAL);
 
 	for (i = 0; i < chunk->npages; ++i)
-		__free_pages(sg_page(&chunk->mem[i]),
-			     get_order(chunk->mem[i].length));
+		__free_pages(sg_page(&chunk->sg[i]),
+			     get_order(chunk->sg[i].length));
 }
 
 static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
@@ -71,9 +71,9 @@ static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *
 
 	for (i = 0; i < chunk->npages; ++i)
 		dma_free_coherent(&dev->persist->pdev->dev,
-				  chunk->mem[i].length,
-				  lowmem_page_address(sg_page(&chunk->mem[i])),
-				  sg_dma_address(&chunk->mem[i]));
+				  chunk->buf[i].size,
+				  chunk->buf[i].addr,
+				  chunk->buf[i].dma_addr);
 }
 
 void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent)
@@ -111,22 +111,21 @@ static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order,
 	return 0;
 }
 
-static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem,
-				    int order, gfp_t gfp_mask)
+static int mlx4_alloc_icm_coherent(struct device *dev, struct mlx4_icm_buf *buf,
+				   int order, gfp_t gfp_mask)
 {
-	void *buf = dma_alloc_coherent(dev, PAGE_SIZE << order,
-				       &sg_dma_address(mem), gfp_mask);
-	if (!buf)
+	buf->addr = dma_alloc_coherent(dev, PAGE_SIZE << order,
+				       &buf->dma_addr, gfp_mask);
+	if (!buf->addr)
 		return -ENOMEM;
 
-	if (offset_in_page(buf)) {
-		dma_free_coherent(dev, PAGE_SIZE << order,
-				  buf, sg_dma_address(mem));
+	if (offset_in_page(buf->addr)) {
+		dma_free_coherent(dev, PAGE_SIZE << order, buf->addr,
+				  buf->dma_addr);
 		return -ENOMEM;
 	}
 
-	sg_set_buf(mem, buf, PAGE_SIZE << order);
-	sg_dma_len(mem) = PAGE_SIZE << order;
+	buf->size = PAGE_SIZE << order;
 	return 0;
 }
 
@@ -159,21 +158,21 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 
 	while (npages > 0) {
 		if (!chunk) {
-			chunk = kmalloc_node(sizeof(*chunk),
+			chunk = kzalloc_node(sizeof(*chunk),
 					     gfp_mask & ~(__GFP_HIGHMEM |
 							  __GFP_NOWARN),
 					     dev->numa_node);
 			if (!chunk) {
-				chunk = kmalloc(sizeof(*chunk),
+				chunk = kzalloc(sizeof(*chunk),
 						gfp_mask & ~(__GFP_HIGHMEM |
 							     __GFP_NOWARN));
 				if (!chunk)
 					goto fail;
 			}
+			chunk->coherent = coherent;
 
-			sg_init_table(chunk->mem, MLX4_ICM_CHUNK_LEN);
-			chunk->npages = 0;
-			chunk->nsg    = 0;
+			if (!coherent)
+				sg_init_table(chunk->sg, MLX4_ICM_CHUNK_LEN);
 			list_add_tail(&chunk->list, &icm->chunk_list);
 		}
 
@@ -186,10 +185,10 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 
 		if (coherent)
 			ret = mlx4_alloc_icm_coherent(&dev->persist->pdev->dev,
-						      &chunk->mem[chunk->npages],
-						      cur_order, mask);
+						&chunk->buf[chunk->npages],
+						cur_order, mask);
 		else
-			ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages],
+			ret = mlx4_alloc_icm_pages(&chunk->sg[chunk->npages],
 						   cur_order, mask,
 						   dev->numa_node);
 
@@ -205,9 +204,9 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 		if (coherent)
 			++chunk->nsg;
 		else if (chunk->npages == MLX4_ICM_CHUNK_LEN) {
-			chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
-						chunk->npages,
-						PCI_DMA_BIDIRECTIONAL);
+			chunk->nsg = dma_map_sg(&dev->persist->pdev->dev,
+						chunk->sg, chunk->npages,
+						DMA_BIDIRECTIONAL);
 
 			if (chunk->nsg <= 0)
 				goto fail;
@@ -220,9 +219,8 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
 	}
 
 	if (!coherent && chunk) {
-		chunk->nsg = pci_map_sg(dev->persist->pdev, chunk->mem,
-					chunk->npages,
-					PCI_DMA_BIDIRECTIONAL);
+		chunk->nsg = dma_map_sg(&dev->persist->pdev->dev, chunk->sg,
+					chunk->npages, DMA_BIDIRECTIONAL);
 
 		if (chunk->nsg <= 0)
 			goto fail;
@@ -320,7 +318,7 @@ void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj,
 	u64 idx;
 	struct mlx4_icm_chunk *chunk;
 	struct mlx4_icm *icm;
-	struct page *page = NULL;
+	void *addr = NULL;
 
 	if (!table->lowmem)
 		return NULL;
@@ -336,28 +334,49 @@ void *mlx4_table_find(struct mlx4_icm_table *table, u32 obj,
 
 	list_for_each_entry(chunk, &icm->chunk_list, list) {
 		for (i = 0; i < chunk->npages; ++i) {
+			dma_addr_t dma_addr;
+			size_t len;
+
+			if (table->coherent) {
+				len = chunk->buf[i].size;
+				dma_addr = chunk->buf[i].dma_addr;
+				addr = chunk->buf[i].addr;
+			} else {
+				struct page *page;
+
+				len = sg_dma_len(&chunk->sg[i]);
+				dma_addr = sg_dma_address(&chunk->sg[i]);
+
+				/* XXX: we should never do this for highmem
+				 * allocation.  This function either needs
+				 * to be split, or the kernel virtual address
+				 * return needs to be made optional.
+				 */
+				page = sg_page(&chunk->sg[i]);
+				addr = lowmem_page_address(page);
+			}
+
 			if (dma_handle && dma_offset >= 0) {
-				if (sg_dma_len(&chunk->mem[i]) > dma_offset)
-					*dma_handle = sg_dma_address(&chunk->mem[i]) +
-						dma_offset;
-				dma_offset -= sg_dma_len(&chunk->mem[i]);
+				if (len > dma_offset)
+					*dma_handle = dma_addr + dma_offset;
+				dma_offset -= len;
 			}
+
 			/*
 			 * DMA mapping can merge pages but not split them,
 			 * so if we found the page, dma_handle has already
 			 * been assigned to.
 			 */
-			if (chunk->mem[i].length > offset) {
-				page = sg_page(&chunk->mem[i]);
+			if (len > offset)
 				goto out;
-			}
-			offset -= chunk->mem[i].length;
+			offset -= len;
 		}
 	}
 
+	addr = NULL;
 out:
 	mutex_unlock(&table->mutex);
-	return page ? lowmem_page_address(page) + offset : NULL;
+	return addr ? addr + offset : NULL;
 }
 
 int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.h b/drivers/net/ethernet/mellanox/mlx4/icm.h
index c9169a490557..d199874b1c07 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.h
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.h
@@ -47,11 +47,21 @@ enum {
 	MLX4_ICM_PAGE_SIZE	= 1 << MLX4_ICM_PAGE_SHIFT,
 };
 
+struct mlx4_icm_buf {
+	void			*addr;
+	size_t			size;
+	dma_addr_t		dma_addr;
+};
+
 struct mlx4_icm_chunk {
 	struct list_head	list;
 	int			npages;
 	int			nsg;
-	struct scatterlist	mem[MLX4_ICM_CHUNK_LEN];
+	bool			coherent;
+	union {
+		struct scatterlist	sg[MLX4_ICM_CHUNK_LEN];
+		struct mlx4_icm_buf	buf[MLX4_ICM_CHUNK_LEN];
+	};
 };
 
 struct mlx4_icm {
@@ -114,12 +124,18 @@ static inline void mlx4_icm_next(struct mlx4_icm_iter *iter)
 
 static inline dma_addr_t mlx4_icm_addr(struct mlx4_icm_iter *iter)
 {
-	return sg_dma_address(&iter->chunk->mem[iter->page_idx]);
+	if (iter->chunk->coherent)
+		return iter->chunk->buf[iter->page_idx].dma_addr;
+	else
+		return sg_dma_address(&iter->chunk->sg[iter->page_idx]);
 }
 
 static inline unsigned long mlx4_icm_size(struct mlx4_icm_iter *iter)
 {
-	return sg_dma_len(&iter->chunk->mem[iter->page_idx]);
+	if (iter->chunk->coherent)
+		return iter->chunk->buf[iter->page_idx].size;
+	else
+		return sg_dma_len(&iter->chunk->sg[iter->page_idx]);
 }
 
 int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm);
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 6a046030e873..1f6e16d5ea6b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -63,7 +63,7 @@ struct workqueue_struct *mlx4_wq;
 
 #ifdef CONFIG_MLX4_DEBUG
 
-int mlx4_debug_level = 0;
+int mlx4_debug_level; /* 0 by default */
 module_param_named(debug_level, mlx4_debug_level, int, 0644);
 MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0");
 
@@ -83,7 +83,7 @@ MODULE_PARM_DESC(msi_x, "0 - don't use MSI-X, 1 - use MSI-X, >1 - limit number o
 
 static uint8_t num_vfs[3] = {0, 0, 0};
 static int num_vfs_argc;
-module_param_array(num_vfs, byte , &num_vfs_argc, 0444);
+module_param_array(num_vfs, byte, &num_vfs_argc, 0444);
 MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0\n"
 			  "num_vfs=port1,port2,port1+2");
 
@@ -313,7 +313,7 @@ int mlx4_check_port_params(struct mlx4_dev *dev,
 		for (i = 0; i < dev->caps.num_ports - 1; i++) {
 			if (port_type[i] != port_type[i + 1]) {
 				mlx4_err(dev, "Only same port types supported on this HCA, aborting\n");
-				return -EINVAL;
+				return -EOPNOTSUPP;
 			}
 		}
 	}
@@ -322,7 +322,7 @@ int mlx4_check_port_params(struct mlx4_dev *dev,
 		if (!(port_type[i] & dev->caps.supported_type[i+1])) {
 			mlx4_err(dev, "Requested port type for port %d is not supported on this HCA\n",
 				 i + 1);
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		}
 	}
 	return 0;
@@ -1188,8 +1188,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 		mlx4_err(mdev,
 			 "Requested port type for port %d is not supported on this HCA\n",
 			 info->port);
-		err = -EINVAL;
-		goto err_sup;
+		return -EOPNOTSUPP;
 	}
 
 	mlx4_stop_sense(mdev);
@@ -1211,7 +1210,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 		for (i = 1; i <= mdev->caps.num_ports; i++) {
 			if (mdev->caps.possible_type[i] == MLX4_PORT_TYPE_AUTO) {
 				mdev->caps.possible_type[i] = mdev->caps.port_type[i];
-				err = -EINVAL;
+				err = -EOPNOTSUPP;
 			}
 		}
 	}
@@ -1237,7 +1236,7 @@ static int __set_port_type(struct mlx4_port_info *info,
 out:
 	mlx4_start_sense(mdev);
 	mutex_unlock(&priv->port_mutex);
-err_sup:
+
 	return err;
 }
 
@@ -3252,7 +3251,7 @@ disable_sriov:
 free_mem:
 	dev->persist->num_vfs = 0;
 	kfree(dev->dev_vfs);
-        dev->dev_vfs = NULL;
+	dev->dev_vfs = NULL;
 	return dev_flags & ~MLX4_FLAG_MASTER;
 }
 
@@ -3982,6 +3981,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (ret)
 		goto err_params_unregister;
 
+	devlink_params_publish(devlink);
 	pci_save_state(pdev);
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 31bd56727022..4356f3a58002 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -2719,13 +2719,13 @@ static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
 	int total_pages;
 	int total_mem;
 	int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f;
+	int tot;
 
 	sq_size = 1 << (log_sq_size + log_sq_sride + 4);
 	rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4));
 	total_mem = sq_size + rq_size;
-	total_pages =
-		roundup_pow_of_two((total_mem + (page_offset << 6)) >>
-				   page_shift);
+	tot = (total_mem + (page_offset << 6)) >> page_shift;
+	total_pages = !tot ? 1 : roundup_pow_of_two(tot);
 
 	return total_pages;
 }
@@ -4729,7 +4729,6 @@ static void rem_slave_srqs(struct mlx4_dev *dev, int slave)
 	struct res_srq *tmp;
 	int state;
 	u64 in_param;
-	LIST_HEAD(tlist);
 	int srqn;
 	int err;
 
@@ -4795,7 +4794,6 @@ static void rem_slave_cqs(struct mlx4_dev *dev, int slave)
 	struct res_cq *tmp;
 	int state;
 	u64 in_param;
-	LIST_HEAD(tlist);
 	int cqn;
 	int err;
 
@@ -4858,7 +4856,6 @@ static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
 	struct res_mpt *tmp;
 	int state;
 	u64 in_param;
-	LIST_HEAD(tlist);
 	int mptn;
 	int err;
 
@@ -4926,7 +4923,6 @@ static void rem_slave_mtts(struct mlx4_dev *dev, int slave)
 	struct res_mtt *mtt;
 	struct res_mtt *tmp;
 	int state;
-	LIST_HEAD(tlist);
 	int base;
 	int err;
 
@@ -5115,7 +5111,6 @@ static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
 	struct res_eq *tmp;
 	int err;
 	int state;
-	LIST_HEAD(tlist);
 	int eqn;
 
 	err = move_all_busy(dev, slave, RES_EQ);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 37a551436e4a..6debffb8336b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -4,7 +4,6 @@
 
 config MLX5_CORE
 	tristate "Mellanox 5th generation network adapters (ConnectX series) core driver"
-	depends on MAY_USE_DEVLINK
 	depends on PCI
 	imply PTP_1588_CLOCK
 	imply VXLAN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d324a3884462..1a16f6d73cbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -12,17 +12,17 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
 # mlx5 core basic
 #
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
-		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
-		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o  \
-		diag/fs_tracepoint.o diag/fw_tracer.o
+		health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \
+		transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
+		fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \
+		lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o
 
 #
 # Netdev basic
 #
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o
+		en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o
 
 #
 # Netdev extra
@@ -30,12 +30,12 @@ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
-mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o
 
 #
 # Core extra
 #
-mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o ecpf.o
 mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
 mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
index 456f30007ad6..9008e17126db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/alloc.c
@@ -63,8 +63,8 @@ static void *mlx5_dma_zalloc_coherent_node(struct mlx5_core_dev *dev,
 	mutex_lock(&priv->alloc_mutex);
 	original_node = dev_to_node(&dev->pdev->dev);
 	set_dev_node(&dev->pdev->dev, node);
-	cpu_handle = dma_zalloc_coherent(&dev->pdev->dev, size,
-					 dma_handle, GFP_KERNEL);
+	cpu_handle = dma_alloc_coherent(&dev->pdev->dev, size, dma_handle,
+					GFP_KERNEL);
 	set_dev_node(&dev->pdev->dev, original_node);
 	mutex_unlock(&priv->alloc_mutex);
 	return cpu_handle;
@@ -186,10 +186,7 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 	if (!pgdir)
 		return NULL;
 
-	pgdir->bitmap = kcalloc(BITS_TO_LONGS(db_per_page),
-				sizeof(unsigned long),
-				GFP_KERNEL);
-
+	pgdir->bitmap = bitmap_zalloc(db_per_page, GFP_KERNEL);
 	if (!pgdir->bitmap) {
 		kfree(pgdir);
 		return NULL;
@@ -200,7 +197,7 @@ static struct mlx5_db_pgdir *mlx5_alloc_db_pgdir(struct mlx5_core_dev *dev,
 	pgdir->db_page = mlx5_dma_zalloc_coherent_node(dev, PAGE_SIZE,
 						       &pgdir->db_dma, node);
 	if (!pgdir->db_page) {
-		kfree(pgdir->bitmap);
+		bitmap_free(pgdir->bitmap);
 		kfree(pgdir);
 		return NULL;
 	}
@@ -280,7 +277,7 @@ void mlx5_db_free(struct mlx5_core_dev *dev, struct mlx5_db *db)
 		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
 				  db->u.pgdir->db_page, db->u.pgdir->db_dma);
 		list_del(&db->u.pgdir->list);
-		kfree(db->u.pgdir->bitmap);
+		bitmap_free(db->u.pgdir->bitmap);
 		kfree(db->u.pgdir);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index a5a0823e5ada..be48c6440251 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -40,9 +40,11 @@
 #include <linux/random.h>
 #include <linux/io-mapping.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
 #include <linux/debugfs.h>
 
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	CMD_IF_REV = 5,
@@ -313,6 +315,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_FPGA_DESTROY_QP:
 	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
 	case MLX5_CMD_OP_DEALLOC_MEMIC:
+	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
+	case MLX5_CMD_OP_QUERY_HOST_PARAMS:
 		return MLX5_CMD_STAT_OK;
 
 	case MLX5_CMD_OP_QUERY_HCA_CAP:
@@ -326,7 +330,6 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_CREATE_MKEY:
 	case MLX5_CMD_OP_QUERY_MKEY:
 	case MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS:
-	case MLX5_CMD_OP_PAGE_FAULT_RESUME:
 	case MLX5_CMD_OP_CREATE_EQ:
 	case MLX5_CMD_OP_QUERY_EQ:
 	case MLX5_CMD_OP_GEN_EQE:
@@ -371,6 +374,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op,
 	case MLX5_CMD_OP_QUERY_VPORT_COUNTER:
 	case MLX5_CMD_OP_ALLOC_Q_COUNTER:
 	case MLX5_CMD_OP_QUERY_Q_COUNTER:
+	case MLX5_CMD_OP_SET_MONITOR_COUNTER:
+	case MLX5_CMD_OP_ARM_MONITOR_COUNTER:
 	case MLX5_CMD_OP_SET_PP_RATE_LIMIT:
 	case MLX5_CMD_OP_QUERY_RATE_LIMIT:
 	case MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT:
@@ -520,6 +525,8 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(ALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(DEALLOC_Q_COUNTER);
 	MLX5_COMMAND_STR_CASE(QUERY_Q_COUNTER);
+	MLX5_COMMAND_STR_CASE(SET_MONITOR_COUNTER);
+	MLX5_COMMAND_STR_CASE(ARM_MONITOR_COUNTER);
 	MLX5_COMMAND_STR_CASE(SET_PP_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(QUERY_RATE_LIMIT);
 	MLX5_COMMAND_STR_CASE(CREATE_SCHEDULING_ELEMENT);
@@ -621,6 +628,7 @@ const char *mlx5_command_str(int command)
 	MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT);
 	MLX5_COMMAND_STR_CASE(ALLOC_MEMIC);
 	MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC);
+	MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS);
 	default: return "unknown command opcode";
 	}
 }
@@ -805,6 +813,8 @@ static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
 	return MLX5_GET(mbox_in, in->first.data, opcode);
 }
 
+static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
+
 static void cb_timeout_handler(struct work_struct *work)
 {
 	struct delayed_work *dwork = container_of(work, struct delayed_work,
@@ -1412,14 +1422,32 @@ static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode)
 		up(&cmd->sem);
 }
 
+static int cmd_comp_notifier(struct notifier_block *nb,
+			     unsigned long type, void *data)
+{
+	struct mlx5_core_dev *dev;
+	struct mlx5_cmd *cmd;
+	struct mlx5_eqe *eqe;
+
+	cmd = mlx5_nb_cof(nb, struct mlx5_cmd, nb);
+	dev = container_of(cmd, struct mlx5_core_dev, cmd);
+	eqe = data;
+
+	mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
+
+	return NOTIFY_OK;
+}
 void mlx5_cmd_use_events(struct mlx5_core_dev *dev)
 {
+	MLX5_NB_INIT(&dev->cmd.nb, cmd_comp_notifier, CMD);
+	mlx5_eq_notifier_register(dev, &dev->cmd.nb);
 	mlx5_cmd_change_mod(dev, CMD_MODE_EVENTS);
 }
 
 void mlx5_cmd_use_polling(struct mlx5_core_dev *dev)
 {
 	mlx5_cmd_change_mod(dev, CMD_MODE_POLLING);
+	mlx5_eq_notifier_unregister(dev, &dev->cmd.nb);
 }
 
 static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
@@ -1435,7 +1463,7 @@ static void free_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg)
 	}
 }
 
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
+static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 {
 	struct mlx5_cmd *cmd = &dev->cmd;
 	struct mlx5_cmd_work_ent *ent;
@@ -1533,7 +1561,47 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced)
 		}
 	}
 }
-EXPORT_SYMBOL(mlx5_cmd_comp_handler);
+
+void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev)
+{
+	unsigned long flags;
+	u64 vector;
+
+	/* wait for pending handlers to complete */
+	mlx5_eq_synchronize_cmd_irq(dev);
+	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
+	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
+	if (!vector)
+		goto no_trig;
+
+	vector |= MLX5_TRIGGERED_CMD_COMP;
+	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
+
+	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
+	mlx5_cmd_comp_handler(dev, vector, true);
+	return;
+
+no_trig:
+	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
+}
+
+void mlx5_cmd_flush(struct mlx5_core_dev *dev)
+{
+	struct mlx5_cmd *cmd = &dev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		while (down_trylock(&cmd->sem))
+			mlx5_cmd_trigger_completions(dev);
+
+	while (down_trylock(&cmd->pages_sem))
+		mlx5_cmd_trigger_completions(dev);
+
+	/* Unlock cmdif */
+	up(&cmd->pages_sem);
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
 
 static int status_to_err(u8 status)
 {
@@ -1663,12 +1731,57 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 }
 EXPORT_SYMBOL(mlx5_cmd_exec);
 
-int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size,
-		     void *out, int out_size, mlx5_cmd_cbk_t callback,
-		     void *context)
+void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev,
+			     struct mlx5_async_ctx *ctx)
+{
+	ctx->dev = dev;
+	/* Starts at 1 to avoid doing wake_up if we are not cleaning up */
+	atomic_set(&ctx->num_inflight, 1);
+	init_waitqueue_head(&ctx->wait);
+}
+EXPORT_SYMBOL(mlx5_cmd_init_async_ctx);
+
+/**
+ * mlx5_cmd_cleanup_async_ctx - Clean up an async_ctx
+ * @ctx: The ctx to clean
+ *
+ * Upon return all callbacks given to mlx5_cmd_exec_cb() have been called. The
+ * caller must ensure that mlx5_cmd_exec_cb() is not called during or after
+ * the call mlx5_cleanup_async_ctx().
+ */
+void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx)
+{
+	atomic_dec(&ctx->num_inflight);
+	wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0);
+}
+EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx);
+
+static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 {
-	return cmd_exec(dev, in, in_size, out, out_size, callback, context,
-			false);
+	struct mlx5_async_work *work = _work;
+	struct mlx5_async_ctx *ctx = work->ctx;
+
+	work->user_callback(status, work);
+	if (atomic_dec_and_test(&ctx->num_inflight))
+		wake_up(&ctx->wait);
+}
+
+int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
+		     void *out, int out_size, mlx5_async_cbk_t callback,
+		     struct mlx5_async_work *work)
+{
+	int ret;
+
+	work->ctx = ctx;
+	work->user_callback = callback;
+	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
+		return -EIO;
+	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
+		       mlx5_cmd_exec_cb_handler, work, false);
+	if (ret && atomic_dec_and_test(&ctx->num_inflight))
+		wake_up(&ctx->wait);
+
+	return ret;
 }
 EXPORT_SYMBOL(mlx5_cmd_exec_cb);
 
@@ -1741,8 +1854,8 @@ static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 {
 	struct device *ddev = &dev->pdev->dev;
 
-	cmd->cmd_alloc_buf = dma_zalloc_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE,
-						 &cmd->alloc_dma, GFP_KERNEL);
+	cmd->cmd_alloc_buf = dma_alloc_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE,
+						&cmd->alloc_dma, GFP_KERNEL);
 	if (!cmd->cmd_alloc_buf)
 		return -ENOMEM;
 
@@ -1756,9 +1869,9 @@ static int alloc_cmd_page(struct mlx5_core_dev *dev, struct mlx5_cmd *cmd)
 
 	dma_free_coherent(ddev, MLX5_ADAPTER_PAGE_SIZE, cmd->cmd_alloc_buf,
 			  cmd->alloc_dma);
-	cmd->cmd_alloc_buf = dma_zalloc_coherent(ddev,
-						 2 * MLX5_ADAPTER_PAGE_SIZE - 1,
-						 &cmd->alloc_dma, GFP_KERNEL);
+	cmd->cmd_alloc_buf = dma_alloc_coherent(ddev,
+						2 * MLX5_ADAPTER_PAGE_SIZE - 1,
+						&cmd->alloc_dma, GFP_KERNEL);
 	if (!cmd->cmd_alloc_buf)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 4b85abb5c9f7..713a17ee3751 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -38,6 +38,7 @@
 #include <rdma/ib_verbs.h>
 #include <linux/mlx5/cq.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 #define TASKLET_MAX_TIME 2
 #define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
@@ -92,10 +93,10 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
 	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
-	struct mlx5_eq *eq;
+	struct mlx5_eq_comp *eq;
 	int err;
 
-	eq = mlx5_eqn2eq(dev, eqn);
+	eq = mlx5_eqn2comp_eq(dev, eqn);
 	if (IS_ERR(eq))
 		return PTR_ERR(eq);
 
@@ -119,12 +120,12 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
 
 	/* Add to comp EQ CQ tree to recv comp events */
-	err = mlx5_eq_add_cq(eq, cq);
+	err = mlx5_eq_add_cq(&eq->core, cq);
 	if (err)
 		goto err_cmd;
 
 	/* Add to async EQ CQ tree to recv async events */
-	err = mlx5_eq_add_cq(&dev->priv.eq_table.async_eq, cq);
+	err = mlx5_eq_add_cq(mlx5_get_async_eq(dev), cq);
 	if (err)
 		goto err_cq_add;
 
@@ -139,7 +140,7 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	return 0;
 
 err_cq_add:
-	mlx5_eq_del_cq(eq, cq);
+	mlx5_eq_del_cq(&eq->core, cq);
 err_cmd:
 	memset(din, 0, sizeof(din));
 	memset(dout, 0, sizeof(dout));
@@ -157,11 +158,11 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
 	int err;
 
-	err = mlx5_eq_del_cq(&dev->priv.eq_table.async_eq, cq);
+	err = mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
 	if (err)
 		return err;
 
-	err = mlx5_eq_del_cq(cq->eq, cq);
+	err = mlx5_eq_del_cq(&cq->eq->core, cq);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
index 90fabd612b6c..a11e22d0b0cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c
@@ -36,6 +36,7 @@
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/driver.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	QP_PID,
@@ -349,6 +350,16 @@ out:
 	return param;
 }
 
+static int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
+			      u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {};
+
+	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
+	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
 static u64 eq_read_field(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 			 int index)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index 37ba7c78859d..ebc046fa97d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -45,75 +45,11 @@ struct mlx5_device_context {
 	unsigned long		state;
 };
 
-struct mlx5_delayed_event {
-	struct list_head	list;
-	struct mlx5_core_dev	*dev;
-	enum mlx5_dev_event	event;
-	unsigned long		param;
-};
-
 enum {
 	MLX5_INTERFACE_ADDED,
 	MLX5_INTERFACE_ATTACHED,
 };
 
-static void add_delayed_event(struct mlx5_priv *priv,
-			      struct mlx5_core_dev *dev,
-			      enum mlx5_dev_event event,
-			      unsigned long param)
-{
-	struct mlx5_delayed_event *delayed_event;
-
-	delayed_event = kzalloc(sizeof(*delayed_event), GFP_ATOMIC);
-	if (!delayed_event) {
-		mlx5_core_err(dev, "event %d is missed\n", event);
-		return;
-	}
-
-	mlx5_core_dbg(dev, "Accumulating event %d\n", event);
-	delayed_event->dev = dev;
-	delayed_event->event = event;
-	delayed_event->param = param;
-	list_add_tail(&delayed_event->list, &priv->waiting_events_list);
-}
-
-static void delayed_event_release(struct mlx5_device_context *dev_ctx,
-				  struct mlx5_priv *priv)
-{
-	struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv);
-	struct mlx5_delayed_event *de;
-	struct mlx5_delayed_event *n;
-	struct list_head temp;
-
-	INIT_LIST_HEAD(&temp);
-
-	spin_lock_irq(&priv->ctx_lock);
-
-	priv->is_accum_events = false;
-	list_splice_init(&priv->waiting_events_list, &temp);
-	if (!dev_ctx->context)
-		goto out;
-	list_for_each_entry_safe(de, n, &temp, list)
-		dev_ctx->intf->event(dev, dev_ctx->context, de->event, de->param);
-
-out:
-	spin_unlock_irq(&priv->ctx_lock);
-
-	list_for_each_entry_safe(de, n, &temp, list) {
-		list_del(&de->list);
-		kfree(de);
-	}
-}
-
-/* accumulating events that can come after mlx5_ib calls to
- * ib_register_device, till adding that interface to the events list.
- */
-static void delayed_event_start(struct mlx5_priv *priv)
-{
-	spin_lock_irq(&priv->ctx_lock);
-	priv->is_accum_events = true;
-	spin_unlock_irq(&priv->ctx_lock);
-}
 
 void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 {
@@ -129,8 +65,6 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 
 	dev_ctx->intf = intf;
 
-	delayed_event_start(priv);
-
 	dev_ctx->context = intf->add(dev);
 	if (dev_ctx->context) {
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
@@ -139,22 +73,9 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 
 		spin_lock_irq(&priv->ctx_lock);
 		list_add_tail(&dev_ctx->list, &priv->ctx_list);
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-		if (dev_ctx->intf->pfault) {
-			if (priv->pfault) {
-				mlx5_core_err(dev, "multiple page fault handlers not supported");
-			} else {
-				priv->pfault_ctx = dev_ctx->context;
-				priv->pfault = dev_ctx->intf->pfault;
-			}
-		}
-#endif
 		spin_unlock_irq(&priv->ctx_lock);
 	}
 
-	delayed_event_release(dev_ctx, priv);
-
 	if (!dev_ctx->context)
 		kfree(dev_ctx);
 }
@@ -179,15 +100,6 @@ void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv)
 	if (!dev_ctx)
 		return;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	spin_lock_irq(&priv->ctx_lock);
-	if (priv->pfault == dev_ctx->intf->pfault)
-		priv->pfault = NULL;
-	spin_unlock_irq(&priv->ctx_lock);
-
-	synchronize_srcu(&priv->pfault_srcu);
-#endif
-
 	spin_lock_irq(&priv->ctx_lock);
 	list_del(&dev_ctx->list);
 	spin_unlock_irq(&priv->ctx_lock);
@@ -207,26 +119,20 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv
 	if (!dev_ctx)
 		return;
 
-	delayed_event_start(priv);
 	if (intf->attach) {
 		if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state))
-			goto out;
+			return;
 		if (intf->attach(dev, dev_ctx->context))
-			goto out;
-
+			return;
 		set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state);
 	} else {
 		if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state))
-			goto out;
+			return;
 		dev_ctx->context = intf->add(dev);
 		if (!dev_ctx->context)
-			goto out;
-
+			return;
 		set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state);
 	}
-
-out:
-	delayed_event_release(dev_ctx, priv);
 }
 
 void mlx5_attach_device(struct mlx5_core_dev *dev)
@@ -350,28 +256,6 @@ void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol)
 	mutex_unlock(&mlx5_intf_mutex);
 }
 
-void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol)
-{
-	struct mlx5_priv *priv = &mdev->priv;
-	struct mlx5_device_context *dev_ctx;
-	unsigned long flags;
-	void *result = NULL;
-
-	spin_lock_irqsave(&priv->ctx_lock, flags);
-
-	list_for_each_entry(dev_ctx, &mdev->priv.ctx_list, list)
-		if ((dev_ctx->intf->protocol == protocol) &&
-		    dev_ctx->intf->get_dev) {
-			result = dev_ctx->intf->get_dev(dev_ctx->context);
-			break;
-		}
-
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
-
-	return result;
-}
-EXPORT_SYMBOL(mlx5_get_protocol_dev);
-
 /* Must be called with intf_mutex held */
 void mlx5_add_dev_by_protocol(struct mlx5_core_dev *dev, int protocol)
 {
@@ -422,44 +306,6 @@ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 	return res;
 }
 
-void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
-		     unsigned long param)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_device_context *dev_ctx;
-	unsigned long flags;
-
-	spin_lock_irqsave(&priv->ctx_lock, flags);
-
-	if (priv->is_accum_events)
-		add_delayed_event(priv, dev, event, param);
-
-	/* After mlx5_detach_device, the dev_ctx->intf is still set and dev_ctx is
-	 * still in priv->ctx_list. In this case, only notify the dev_ctx if its
-	 * ADDED or ATTACHED bit are set.
-	 */
-	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
-		if (dev_ctx->intf->event &&
-		    (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state) ||
-		     test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)))
-			dev_ctx->intf->event(dev, dev_ctx->context, event, param);
-
-	spin_unlock_irqrestore(&priv->ctx_lock, flags);
-}
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-void mlx5_core_page_fault(struct mlx5_core_dev *dev,
-			  struct mlx5_pagefault *pfault)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	int srcu_idx;
-
-	srcu_idx = srcu_read_lock(&priv->pfault_srcu);
-	if (priv->pfault)
-		priv->pfault(dev, priv->pfault_ctx, pfault);
-	srcu_read_unlock(&priv->pfault_srcu, srcu_idx);
-}
-#endif
 
 void mlx5_dev_list_lock(void)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
index 0f11fff32a9b..8ecac81a385d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.c
@@ -161,10 +161,10 @@ static void print_misc_parameters_hdrs(struct trace_seq *p,
 	PRINT_MASKED_VAL(name, p, format);		   \
 }
 	DECLARE_MASK_VAL(u64, gre_key) = {
-		.m = MLX5_GET(fte_match_set_misc, mask, gre_key_h) << 8 |
-		     MLX5_GET(fte_match_set_misc, mask, gre_key_l),
-		.v = MLX5_GET(fte_match_set_misc, value, gre_key_h) << 8 |
-		     MLX5_GET(fte_match_set_misc, value, gre_key_l)};
+		.m = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi) << 8 |
+		     MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo),
+		.v = MLX5_GET(fte_match_set_misc, value, gre_key.nvgre.hi) << 8 |
+		     MLX5_GET(fte_match_set_misc, value, gre_key.nvgre.lo)};
 
 	PRINT_MASKED_VAL(gre_key, p, "%llu");
 	PRINT_MASKED_VAL_MISC(u32, source_sqn, source_sqn, p, "%u");
@@ -258,6 +258,8 @@ const char *parse_fs_dst(struct trace_seq *p,
 	return ret;
 }
 
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_add_ft);
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_ft);
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_add_fg);
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_del_fg);
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fs_set_fte);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index d027ce00c8ce..a4cf123e3f17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -61,6 +61,41 @@ const char *parse_fs_dst(struct trace_seq *p,
 			 const struct mlx5_flow_destination *dst,
 			 u32 counter_id);
 
+TRACE_EVENT(mlx5_fs_add_ft,
+	    TP_PROTO(const struct mlx5_flow_table *ft),
+	    TP_ARGS(ft),
+	    TP_STRUCT__entry(
+		__field(const struct mlx5_flow_table *, ft)
+		__field(u32, id)
+		__field(u32, level)
+		__field(u32, type)
+	    ),
+	    TP_fast_assign(
+			   __entry->ft = ft;
+			   __entry->id = ft->id;
+			   __entry->level = ft->level;
+			   __entry->type = ft->type;
+	    ),
+	    TP_printk("ft=%p id=%u level=%u type=%u \n",
+		      __entry->ft, __entry->id, __entry->level, __entry->type)
+	    );
+
+TRACE_EVENT(mlx5_fs_del_ft,
+	    TP_PROTO(const struct mlx5_flow_table *ft),
+	    TP_ARGS(ft),
+	    TP_STRUCT__entry(
+		__field(const struct mlx5_flow_table *, ft)
+		__field(u32, id)
+	    ),
+	    TP_fast_assign(
+			   __entry->ft = ft;
+			   __entry->id = ft->id;
+
+	    ),
+	    TP_printk("ft=%p id=%u\n",
+		      __entry->ft, __entry->id)
+	    );
+
 TRACE_EVENT(mlx5_fs_add_fg,
 	    TP_PROTO(const struct mlx5_flow_group *fg),
 	    TP_ARGS(fg),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index d4ec93bde4de..6999f4486e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 #define CREATE_TRACE_POINTS
+#include "lib/eq.h"
 #include "fw_tracer.h"
 #include "fw_tracer_tracepoint.h"
 
@@ -846,9 +847,9 @@ free_tracer:
 	return ERR_PTR(err);
 }
 
-/* Create HW resources + start tracer
- * must be called before Async EQ is created
- */
+static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data);
+
+/* Create HW resources + start tracer */
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 {
 	struct mlx5_core_dev *dev;
@@ -874,6 +875,9 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 		goto err_dealloc_pd;
 	}
 
+	MLX5_NB_INIT(&tracer->nb, fw_tracer_event, DEVICE_TRACER);
+	mlx5_eq_notifier_register(dev, &tracer->nb);
+
 	mlx5_fw_tracer_start(tracer);
 
 	return 0;
@@ -883,9 +887,7 @@ err_dealloc_pd:
 	return err;
 }
 
-/* Stop tracer + Cleanup HW resources
- * must be called after Async EQ is destroyed
- */
+/* Stop tracer + Cleanup HW resources */
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 {
 	if (IS_ERR_OR_NULL(tracer))
@@ -893,7 +895,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 
 	mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n",
 		      tracer->owner);
-
+	mlx5_eq_notifier_unregister(tracer->dev, &tracer->nb);
 	cancel_work_sync(&tracer->ownership_change_work);
 	cancel_work_sync(&tracer->handle_traces_work);
 
@@ -922,12 +924,11 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	kfree(tracer);
 }
 
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+static int fw_tracer_event(struct notifier_block *nb, unsigned long action, void *data)
 {
-	struct mlx5_fw_tracer *tracer = dev->tracer;
-
-	if (!tracer)
-		return;
+	struct mlx5_fw_tracer *tracer = mlx5_nb_cof(nb, struct mlx5_fw_tracer, nb);
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct mlx5_eqe *eqe = data;
 
 	switch (eqe->sub_type) {
 	case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
@@ -942,6 +943,8 @@ void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
 		mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",
 			      eqe->sub_type);
 	}
+
+	return NOTIFY_OK;
 }
 
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 0347f2dd5cee..a8b8747f2b61 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -55,6 +55,7 @@
 
 struct mlx5_fw_tracer {
 	struct mlx5_core_dev *dev;
+	struct mlx5_nb        nb;
 	bool owner;
 	u8   trc_ver;
 	struct workqueue_struct *work_queue;
@@ -170,6 +171,5 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
new file mode 100644
index 000000000000..4746f2d28fb6
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include "ecpf.h"
+
+bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev)
+{
+	return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1;
+}
+
+static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(enable_hca_in)]   = {};
+
+	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
+	MLX5_SET(enable_hca_in, in, function_id, 0);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+}
+
+static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(disable_hca_in)]   = {};
+
+	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
+	MLX5_SET(disable_hca_in, in, function_id, 0);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0);
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_peer_pf_init(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_peer_pf_enable_hca(dev);
+	if (err)
+		mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n",
+			      err);
+
+	return err;
+}
+
+static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = mlx5_peer_pf_disable_hca(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n",
+			      err);
+		return;
+	}
+
+	err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages);
+	if (err)
+		mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n",
+			       err);
+}
+
+int mlx5_ec_init(struct mlx5_core_dev *dev)
+{
+	int err = 0;
+
+	if (!mlx5_core_is_ecpf(dev))
+		return 0;
+
+	/* ECPF shall enable HCA for peer PF in the same way a PF
+	 * does this for its VFs.
+	 */
+	err = mlx5_peer_pf_init(dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
+{
+	if (!mlx5_core_is_ecpf(dev))
+		return;
+
+	mlx5_peer_pf_cleanup(dev);
+}
+
+static int mlx5_query_host_params_context(struct mlx5_core_dev *dev,
+					  u32 *out, int outlen)
+{
+	u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {};
+
+	MLX5_SET(query_host_params_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_HOST_PARAMS);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+}
+
+int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
+{
+	u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {};
+	int err;
+
+	err = mlx5_query_host_params_context(dev, out, sizeof(out));
+	if (err)
+		return err;
+
+	*num_vf = MLX5_GET(query_host_params_out, out,
+			   host_params_context.host_num_of_vfs);
+	mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
new file mode 100644
index 000000000000..346372df218f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_ECPF_H__
+#define __MLX5_ECPF_H__
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+enum {
+	MLX5_ECPU_BIT_NUM = 23,
+};
+
+bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev);
+int mlx5_ec_init(struct mlx5_core_dev *dev);
+void mlx5_ec_cleanup(struct mlx5_core_dev *dev);
+int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf);
+
+#else  /* CONFIG_MLX5_ESWITCH */
+
+static inline bool
+mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; }
+static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; }
+static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {}
+static inline int
+mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf)
+{ return -EOPNOTSUPP; }
+
+#endif /* CONFIG_MLX5_ESWITCH */
+
+#endif /* __MLX5_ECPF_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 118324802926..d3eaf2ceaa39 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -49,6 +49,7 @@
 #include <net/switchdev.h>
 #include <net/xdp.h>
 #include <linux/net_dim.h>
+#include <linux/bits.h>
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
@@ -75,15 +76,14 @@ struct page_pool;
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
 
+#define MLX5E_RX_MAX_HEAD (256)
+
 #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \
 	(6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */
 #define MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, req) \
 	max_t(u32, MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev), req)
-#define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev)       MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 6)
-#define MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, 8)
-#define MLX5E_MPWQE_STRIDE_SZ(mdev, cqe_cmprs) \
-	(cqe_cmprs ? MLX5_MPWRQ_CQE_CMPRS_LOG_STRIDE_SZ(mdev) : \
-	MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev))
+#define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) \
+	MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, order_base_2(MLX5E_RX_MAX_HEAD))
 
 #define MLX5_MPWRQ_LOG_WQE_SZ			18
 #define MLX5_MPWRQ_WQE_PAGE_ORDER  (MLX5_MPWRQ_LOG_WQE_SZ - PAGE_SHIFT > 0 ? \
@@ -118,8 +118,6 @@ struct page_pool;
 
 #define MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE_MPW            0x2
 
-#define MLX5E_RX_MAX_HEAD (256)
-
 #define MLX5E_PARAMS_DEFAULT_LRO_WQE_SZ                 (64 * 1024)
 #define MLX5E_DEFAULT_LRO_TIMEOUT                       32
 #define MLX5E_LRO_TIMEOUT_ARR_SIZE                      4
@@ -147,9 +145,6 @@ struct page_pool;
 	       MLX5_UMR_MTT_ALIGNMENT))
 #define MLX5E_UMR_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
-#define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
-
-#define MLX5E_NUM_MAIN_GROUPS 9
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
 
@@ -178,8 +173,7 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
 		MLX5E_MIN_NUM_CHANNELS :
-		min_t(int, mdev->priv.eq_table.num_comp_vectors,
-		      MLX5E_MAX_NUM_CHANNELS);
+		min_t(int, mlx5_comp_vectors_count(mdev), MLX5E_MAX_NUM_CHANNELS);
 }
 
 /* Use this function to get max num channels after netdev was created */
@@ -214,22 +208,24 @@ struct mlx5e_umr_wqe {
 extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
 
 enum mlx5e_priv_flag {
-	MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0),
-	MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1),
-	MLX5E_PFLAG_RX_CQE_COMPRESS = (1 << 2),
-	MLX5E_PFLAG_RX_STRIDING_RQ = (1 << 3),
-	MLX5E_PFLAG_RX_NO_CSUM_COMPLETE = (1 << 4),
+	MLX5E_PFLAG_RX_CQE_BASED_MODER,
+	MLX5E_PFLAG_TX_CQE_BASED_MODER,
+	MLX5E_PFLAG_RX_CQE_COMPRESS,
+	MLX5E_PFLAG_RX_STRIDING_RQ,
+	MLX5E_PFLAG_RX_NO_CSUM_COMPLETE,
+	MLX5E_PFLAG_XDP_TX_MPWQE,
+	MLX5E_NUM_PFLAGS, /* Keep last */
 };
 
 #define MLX5E_SET_PFLAG(params, pflag, enable)			\
 	do {							\
 		if (enable)					\
-			(params)->pflags |= (pflag);		\
+			(params)->pflags |= BIT(pflag);		\
 		else						\
-			(params)->pflags &= ~(pflag);		\
+			(params)->pflags &= ~(BIT(pflag));	\
 	} while (0)
 
-#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (pflag)))
+#define MLX5E_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag))))
 
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
@@ -247,9 +243,6 @@ struct mlx5e_params {
 	bool lro_en;
 	u32 lro_wqe_sz;
 	u8  tx_min_inline_mode;
-	u8  rss_hfunc;
-	u8  toeplitz_hash_key[40];
-	u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE];
 	bool vlan_strip_disable;
 	bool scatter_fcs_en;
 	bool rx_dim_enabled;
@@ -313,16 +306,18 @@ struct mlx5e_cq {
 	struct mlx5_core_cq        mcq;
 	struct mlx5e_channel      *channel;
 
+	/* control */
+	struct mlx5_core_dev      *mdev;
+	struct mlx5_wq_ctrl        wq_ctrl;
+} ____cacheline_aligned_in_smp;
+
+struct mlx5e_cq_decomp {
 	/* cqe decompression */
 	struct mlx5_cqe64          title;
 	struct mlx5_mini_cqe8      mini_arr[MLX5_MINI_CQE_ARRAY_SIZE];
 	u8                         mini_arr_idx;
-	u16                        decmprs_left;
-	u16                        decmprs_wqe_counter;
-
-	/* control */
-	struct mlx5_core_dev      *mdev;
-	struct mlx5_wq_ctrl        wq_ctrl;
+	u16                        left;
+	u16                        wqe_counter;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_tx_wqe_info {
@@ -349,7 +344,6 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
-	MLX5E_SQ_STATE_REDIRECT,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -393,10 +387,7 @@ struct mlx5e_txqsq {
 	struct mlx5e_channel      *channel;
 	int                        txq_ix;
 	u32                        rate_limit;
-	struct mlx5e_txqsq_recover {
-		struct work_struct         recover_work;
-		u64                        last_recover;
-	} recover;
+	struct work_struct         recover_work;
 } ____cacheline_aligned_in_smp;
 
 struct mlx5e_dma_info {
@@ -410,24 +401,51 @@ struct mlx5e_xdp_info {
 	struct mlx5e_dma_info di;
 };
 
+struct mlx5e_xdp_info_fifo {
+	struct mlx5e_xdp_info *xi;
+	u32 *cc;
+	u32 *pc;
+	u32 mask;
+};
+
+struct mlx5e_xdp_wqe_info {
+	u8 num_wqebbs;
+	u8 num_ds;
+};
+
+struct mlx5e_xdp_mpwqe {
+	/* Current MPWQE session */
+	struct mlx5e_tx_wqe *wqe;
+	u8                   ds_count;
+	u8                   max_ds_count;
+};
+
+struct mlx5e_xdpsq;
+typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*,
+					struct mlx5e_xdp_info*);
 struct mlx5e_xdpsq {
 	/* data path */
 
 	/* dirtied @completion */
+	u32                        xdpi_fifo_cc;
 	u16                        cc;
 	bool                       redirect_flush;
 
 	/* dirtied @xmit */
-	u16                        pc ____cacheline_aligned_in_smp;
-	bool                       doorbell;
+	u32                        xdpi_fifo_pc ____cacheline_aligned_in_smp;
+	u16                        pc;
+	struct mlx5_wqe_ctrl_seg   *doorbell_cseg;
+	struct mlx5e_xdp_mpwqe     mpwqe;
 
 	struct mlx5e_cq            cq;
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
+	mlx5e_fp_xmit_xdp_frame    xmit_xdp_frame;
 	struct {
-		struct mlx5e_xdp_info     *xdpi;
+		struct mlx5e_xdp_wqe_info *wqe_info;
+		struct mlx5e_xdp_info_fifo xdpi_fifo;
 	} db;
 	void __iomem              *uar_map;
 	u32                        sqn;
@@ -559,6 +577,7 @@ struct mlx5e_rq {
 	struct net_device     *netdev;
 	struct mlx5e_rq_stats *stats;
 	struct mlx5e_cq        cq;
+	struct mlx5e_cq_decomp cqd;
 	struct mlx5e_page_cache page_cache;
 	struct hwtstamp_config *tstamp;
 	struct mlx5_clock      *clock;
@@ -616,6 +635,7 @@ struct mlx5e_channel {
 	struct hwtstamp_config    *tstamp;
 	int                        ix;
 	int                        cpu;
+	cpumask_var_t              xps_cpumask;
 };
 
 struct mlx5e_channels {
@@ -633,9 +653,9 @@ struct mlx5e_channel_stats {
 } ____cacheline_aligned_in_smp;
 
 enum {
-	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
+	MLX5E_STATE_XDP_TX_ENABLED,
 };
 
 struct mlx5e_rqt {
@@ -654,6 +674,20 @@ enum {
 	MLX5E_NIC_PRIO
 };
 
+struct mlx5e_rss_params {
+	u32	indirection_rqt[MLX5E_INDIR_RQT_SIZE];
+	u32	rx_hash_fields[MLX5E_NUM_INDIR_TIRS];
+	u8	toeplitz_hash_key[40];
+	u8	hfunc;
+};
+
+struct mlx5e_modify_sq_param {
+	int curr_state;
+	int next_state;
+	int rl_update;
+	int rl_index;
+};
+
 struct mlx5e_priv {
 	/* priv data path fields - start */
 	struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC];
@@ -674,6 +708,7 @@ struct mlx5e_priv {
 	struct mlx5e_tir           indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           inner_indir_tir[MLX5E_NUM_INDIR_TIRS];
 	struct mlx5e_tir           direct_tir[MLX5E_MAX_NUM_CHANNELS];
+	struct mlx5e_rss_params    rss_params;
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
@@ -683,6 +718,8 @@ struct mlx5e_priv {
 	struct work_struct         set_rx_mode_work;
 	struct work_struct         tx_timeout_work;
 	struct work_struct         update_stats_work;
+	struct work_struct         monitor_counters_work;
+	struct mlx5_nb             monitor_counters_nb;
 
 	struct mlx5_core_dev      *mdev;
 	struct net_device         *netdev;
@@ -692,6 +729,8 @@ struct mlx5e_priv {
 	struct hwtstamp_config     tstamp;
 	u16                        q_counter;
 	u16                        drop_rq_q_counter;
+	struct notifier_block      events_nb;
+
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	struct mlx5e_dcbx          dcbx;
 #endif
@@ -704,6 +743,7 @@ struct mlx5e_priv {
 #ifdef CONFIG_MLX5_EN_TLS
 	struct mlx5e_tls          *tls;
 #endif
+	struct devlink_health_reporter *tx_reporter;
 };
 
 struct mlx5e_profile {
@@ -769,6 +809,8 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 			     struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt);
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
+void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
+void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
 
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
@@ -799,9 +841,11 @@ struct mlx5e_redirect_rqt_param {
 
 int mlx5e_redirect_rqt(struct mlx5e_priv *priv, u32 rqtn, int sz,
 		       struct mlx5e_redirect_rqt_param rrp);
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
-				    enum mlx5e_traffic_types tt,
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
+				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner);
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen);
+struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt);
 
 int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);
@@ -814,9 +858,10 @@ void mlx5e_close_channels(struct mlx5e_channels *chs);
  * switching channels
  */
 typedef int (*mlx5e_fp_hw_modify)(struct mlx5e_priv *priv);
-void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
-				struct mlx5e_channels *new_chs,
-				mlx5e_fp_hw_modify hw_modify);
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv);
+int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
+			       struct mlx5e_channels *new_chs,
+			       mlx5e_fp_hw_modify hw_modify);
 void mlx5e_activate_priv_channels(struct mlx5e_priv *priv);
 void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv);
 
@@ -830,6 +875,11 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params);
 void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev,
 			       struct mlx5e_params *params);
 
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p);
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq);
+void mlx5e_tx_disable_queue(struct netdev_queue *txq);
+
 static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev)
 {
 	return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) &&
@@ -931,14 +981,16 @@ int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
 
 int mlx5e_create_tises(struct mlx5e_priv *priv);
-void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv);
+void mlx5e_update_carrier(struct mlx5e_priv *priv);
 int mlx5e_close(struct net_device *netdev);
 int mlx5e_open(struct net_device *netdev);
+void mlx5e_update_ndo_stats(struct mlx5e_priv *priv);
 
 void mlx5e_queue_update_stats(struct mlx5e_priv *priv);
 int mlx5e_bits_invert(unsigned long a, int size);
 
 typedef int (*change_hw_mtu_cb)(struct mlx5e_priv *priv);
+int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv);
 int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		     change_hw_mtu_cb set_mtu_cb);
 
@@ -962,12 +1014,20 @@ int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal);
 int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 			       struct ethtool_coalesce *coal);
+int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
+				     struct ethtool_link_ksettings *link_ksettings);
+int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
+				     const struct ethtool_link_ksettings *link_ksettings);
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv);
 u32 mlx5e_ethtool_get_rxfh_indir_size(struct mlx5e_priv *priv);
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info);
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash);
+void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
+				  struct ethtool_pauseparam *pauseparam);
+int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
+				 struct ethtool_pauseparam *pauseparam);
 
 /* mlx5e generic netdev management API */
 int mlx5e_netdev_init(struct net_device *netdev,
@@ -983,12 +1043,26 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv);
 void mlx5e_detach_netdev(struct mlx5e_priv *priv);
 void mlx5e_destroy_netdev(struct mlx5e_priv *priv);
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu);
 void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 			   struct mlx5e_params *params);
-void mlx5e_build_rss_params(struct mlx5e_params *params);
+void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
+			    u16 num_channels);
 u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
 void mlx5e_rx_dim_work(struct work_struct *work);
 void mlx5e_tx_dim_work(struct work_struct *work);
+
+void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti);
+void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti);
+netdev_features_t mlx5e_features_check(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       netdev_features_t features);
+#ifdef CONFIG_MLX5_ESWITCH
+int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
+int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate);
+int mlx5e_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi);
+int mlx5e_get_vf_stats(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats);
+#endif
 #endif /* __MLX5_EN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1431232c9a09..be5961ff24cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -73,6 +73,22 @@ enum mlx5e_traffic_types {
 	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
 };
 
+struct mlx5e_tirc_config {
+	u8 l3_prot_type;
+	u8 l4_prot_type;
+	u32 rx_hash_fields;
+};
+
+#define MLX5_HASH_IP		(MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP)
+#define MLX5_HASH_IP_L4PORTS	(MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
+				 MLX5_HASH_FIELD_SEL_L4_DPORT)
+#define MLX5_HASH_IP_IPSEC_SPI	(MLX5_HASH_FIELD_SEL_SRC_IP   |\
+				 MLX5_HASH_FIELD_SEL_DST_IP   |\
+				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
+
 enum mlx5e_tunnel_types {
 	MLX5E_TT_IPV4_GRE,
 	MLX5E_TT_IPV6_GRE,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
new file mode 100644
index 000000000000..7cd5b02e0f10
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.c
@@ -0,0 +1,169 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include "en.h"
+#include "monitor_stats.h"
+#include "lib/eq.h"
+
+/* Driver will set the following watch counters list:
+ * Ppcnt.802_3:
+ * a_in_range_length_errors      Type: 0x0, Counter:  0x0, group_id = N/A
+ * a_out_of_range_length_field   Type: 0x0, Counter:  0x1, group_id = N/A
+ * a_frame_too_long_errors       Type: 0x0, Counter:  0x2, group_id = N/A
+ * a_frame_check_sequence_errors Type: 0x0, Counter:  0x3, group_id = N/A
+ * a_alignment_errors            Type: 0x0, Counter:  0x4, group_id = N/A
+ * if_out_discards               Type: 0x0, Counter:  0x5, group_id = N/A
+ * Q_Counters:
+ * Q[index].rx_out_of_buffer   Type: 0x1, Counter:  0x4, group_id = counter_ix
+ */
+
+#define NUM_REQ_PPCNT_COUNTER_S1 MLX5_CMD_SET_MONITOR_NUM_PPCNT_COUNTER_SET1
+#define NUM_REQ_Q_COUNTERS_S1    MLX5_CMD_SET_MONITOR_NUM_Q_COUNTERS_SET1
+
+int mlx5e_monitor_counter_supported(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+
+	if (!MLX5_CAP_GEN(mdev, max_num_of_monitor_counters))
+		return false;
+	if (MLX5_CAP_PCAM_REG(mdev, ppcnt) &&
+	    MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters) <
+	    NUM_REQ_PPCNT_COUNTER_S1)
+		return false;
+	if (MLX5_CAP_GEN(mdev, num_q_monitor_counters) <
+	    NUM_REQ_Q_COUNTERS_S1)
+		return false;
+	return true;
+}
+
+void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv)
+{
+	u32  in[MLX5_ST_SZ_DW(arm_monitor_counter_in)]  = {};
+	u32 out[MLX5_ST_SZ_DW(arm_monitor_counter_out)] = {};
+
+	MLX5_SET(arm_monitor_counter_in, in, opcode,
+		 MLX5_CMD_OP_ARM_MONITOR_COUNTER);
+	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static void mlx5e_monitor_counters_work(struct work_struct *work)
+{
+	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
+					       monitor_counters_work);
+
+	mutex_lock(&priv->state_lock);
+	mlx5e_update_ndo_stats(priv);
+	mutex_unlock(&priv->state_lock);
+	mlx5e_monitor_counter_arm(priv);
+}
+
+static int mlx5e_monitor_event_handler(struct notifier_block *nb,
+				       unsigned long event, void *eqe)
+{
+	struct mlx5e_priv *priv = mlx5_nb_cof(nb, struct mlx5e_priv,
+					      monitor_counters_nb);
+	queue_work(priv->wq, &priv->monitor_counters_work);
+	return NOTIFY_OK;
+}
+
+static void mlx5e_monitor_counter_start(struct mlx5e_priv *priv)
+{
+	MLX5_NB_INIT(&priv->monitor_counters_nb, mlx5e_monitor_event_handler,
+		     MONITOR_COUNTER);
+	mlx5_eq_notifier_register(priv->mdev, &priv->monitor_counters_nb);
+}
+
+static void mlx5e_monitor_counter_stop(struct mlx5e_priv *priv)
+{
+	mlx5_eq_notifier_unregister(priv->mdev, &priv->monitor_counters_nb);
+	cancel_work_sync(&priv->monitor_counters_work);
+}
+
+static int fill_monitor_counter_ppcnt_set1(int cnt, u32 *in)
+{
+	enum mlx5_monitor_counter_ppcnt ppcnt_cnt;
+
+	for (ppcnt_cnt = 0;
+	     ppcnt_cnt < NUM_REQ_PPCNT_COUNTER_S1;
+	     ppcnt_cnt++, cnt++) {
+		MLX5_SET(set_monitor_counter_in, in,
+			 monitor_counter[cnt].type,
+			 MLX5_QUERY_MONITOR_CNT_TYPE_PPCNT);
+		MLX5_SET(set_monitor_counter_in, in,
+			 monitor_counter[cnt].counter,
+			 ppcnt_cnt);
+	}
+	return ppcnt_cnt;
+}
+
+static int fill_monitor_counter_q_counter_set1(int cnt, int q_counter, u32 *in)
+{
+	MLX5_SET(set_monitor_counter_in, in,
+		 monitor_counter[cnt].type,
+		 MLX5_QUERY_MONITOR_CNT_TYPE_Q_COUNTER);
+	MLX5_SET(set_monitor_counter_in, in,
+		 monitor_counter[cnt].counter,
+		 MLX5_QUERY_MONITOR_Q_COUNTER_RX_OUT_OF_BUFFER);
+	MLX5_SET(set_monitor_counter_in, in,
+		 monitor_counter[cnt].counter_group_id,
+		 q_counter);
+	return 1;
+}
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+static void mlx5e_set_monitor_counter(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int max_num_of_counters = MLX5_CAP_GEN(mdev, max_num_of_monitor_counters);
+	int num_q_counters      = MLX5_CAP_GEN(mdev, num_q_monitor_counters);
+	int num_ppcnt_counters  = !MLX5_CAP_PCAM_REG(mdev, ppcnt) ? 0 :
+				  MLX5_CAP_GEN(mdev, num_ppcnt_monitor_counters);
+	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
+	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
+	int q_counter = priv->q_counter;
+	int cnt	= 0;
+
+	if (num_ppcnt_counters  >=  NUM_REQ_PPCNT_COUNTER_S1 &&
+	    max_num_of_counters >= (NUM_REQ_PPCNT_COUNTER_S1 + cnt))
+		cnt += fill_monitor_counter_ppcnt_set1(cnt, in);
+
+	if (num_q_counters      >=  NUM_REQ_Q_COUNTERS_S1 &&
+	    max_num_of_counters >= (NUM_REQ_Q_COUNTERS_S1 + cnt) &&
+	    q_counter)
+		cnt += fill_monitor_counter_q_counter_set1(cnt, q_counter, in);
+
+	MLX5_SET(set_monitor_counter_in, in, num_of_counters, cnt);
+	MLX5_SET(set_monitor_counter_in, in, opcode,
+		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
+
+	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+void mlx5e_monitor_counter_init(struct mlx5e_priv *priv)
+{
+	INIT_WORK(&priv->monitor_counters_work, mlx5e_monitor_counters_work);
+	mlx5e_monitor_counter_start(priv);
+	mlx5e_set_monitor_counter(priv);
+	mlx5e_monitor_counter_arm(priv);
+	queue_work(priv->wq, &priv->update_stats_work);
+}
+
+static void mlx5e_monitor_counter_disable(struct mlx5e_priv *priv)
+{
+	u32  in[MLX5_ST_SZ_DW(set_monitor_counter_in)]  = {};
+	u32 out[MLX5_ST_SZ_DW(set_monitor_counter_out)] = {};
+
+	MLX5_SET(set_monitor_counter_in, in, num_of_counters, 0);
+	MLX5_SET(set_monitor_counter_in, in, opcode,
+		 MLX5_CMD_OP_SET_MONITOR_COUNTER);
+
+	mlx5_cmd_exec(priv->mdev, in, sizeof(in), out, sizeof(out));
+}
+
+/* check if mlx5e_monitor_counter_supported before calling this function*/
+void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv)
+{
+	mlx5e_monitor_counter_disable(priv);
+	mlx5e_monitor_counter_stop(priv);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
new file mode 100644
index 000000000000..e1ac4b3d22fb
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/monitor_stats.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5_MONITOR_H__
+#define __MLX5_MONITOR_H__
+
+int  mlx5e_monitor_counter_supported(struct mlx5e_priv *priv);
+void mlx5e_monitor_counter_init(struct mlx5e_priv *priv);
+void mlx5e_monitor_counter_cleanup(struct mlx5e_priv *priv);
+void mlx5e_monitor_counter_arm(struct mlx5e_priv *priv);
+
+#endif /* __MLX5_MONITOR_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 4a37713023be..d5e5afbdca6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -63,66 +63,165 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
 	[MLX5E_50GBASE_KR2]       = 50000,
 };
 
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper)
+static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
+	[MLX5E_SGMII_100M]			= 100,
+	[MLX5E_1000BASE_X_SGMII]		= 1000,
+	[MLX5E_5GBASE_R]			= 5000,
+	[MLX5E_10GBASE_XFI_XAUI_1]		= 10000,
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= 40000,
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= 25000,
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= 50000,
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= 50000,
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= 100000,
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= 200000,
+	[MLX5E_400GAUI_8]			= 400000,
+};
+
+static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
+				     const u32 **arr, u32 *size)
+{
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+
+	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
+		      ARRAY_SIZE(mlx5e_link_speed);
+	*arr  = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+}
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5e_port_eth_proto *eproto)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	int err;
+
+	if (!eproto)
+		return -EINVAL;
+
+	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port);
+	if (err)
+		return err;
+
+	eproto->cap   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					   eth_proto_capability);
+	eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin);
+	eproto->oper  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper);
+	return 0;
+}
+
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+				 u8 *an_disable_cap, u8 *an_disable_admin)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+
+	*an_status = 0;
+	*an_disable_cap = 0;
+	*an_disable_admin = 0;
+
+	if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1))
+		return;
+
+	*an_status = MLX5_GET(ptys_reg, out, an_status);
+	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
+	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
+}
+
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+			   u32 proto_admin, bool ext)
+{
+	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
+	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
+	u8 an_disable_admin;
+	u8 an_disable_cap;
+	u8 an_status;
+
+	mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap,
+				    &an_disable_admin);
+	if (!an_disable_cap && an_disable)
+		return -EPERM;
+
+	memset(in, 0, sizeof(in));
+
+	MLX5_SET(ptys_reg, in, local_port, 1);
+	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
+	MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN);
+	if (ext)
+		MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin);
+	else
+		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out,
+			    sizeof(out), MLX5_REG_PTYS, 0, 1);
+}
+
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper)
 {
 	unsigned long temp = eth_proto_oper;
+	const u32 *table;
 	u32 speed = 0;
+	u32 max_size;
 	int i;
 
-	i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER);
-	if (i < MLX5E_LINK_MODES_NUMBER)
-		speed = mlx5e_link_speed[i];
-
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	i = find_first_bit(&temp, max_size);
+	if (i < max_size)
+		speed = table[i];
 	return speed;
 }
 
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {};
-	u32 eth_proto_oper;
+	struct mlx5e_port_eth_proto eproto;
+	bool ext;
 	int err;
 
-	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
-		return err;
+		goto out;
 
-	eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	*speed = mlx5e_port_ptys2speed(eth_proto_oper);
+	*speed = mlx5e_port_ptys2speed(mdev, eproto.oper);
 	if (!(*speed))
 		err = -EINVAL;
 
+out:
 	return err;
 }
 
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
+	struct mlx5e_port_eth_proto eproto;
 	u32 max_speed = 0;
-	u32 proto_cap;
+	const u32 *table;
+	u32 max_size;
+	bool ext;
 	int err;
 	int i;
 
-	err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN);
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i)
-		if (proto_cap & MLX5E_PROT_MASK(i))
-			max_speed = max(max_speed, mlx5e_link_speed[i]);
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	for (i = 0; i < max_size; ++i)
+		if (eproto.cap & MLX5E_PROT_MASK(i))
+			max_speed = max(max_speed, table[i]);
 
 	*speed = max_speed;
 	return 0;
 }
 
-u32 mlx5e_port_speed2linkmodes(u32 speed)
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed)
 {
 	u32 link_modes = 0;
+	const u32 *table;
+	u32 max_size;
 	int i;
 
-	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (mlx5e_link_speed[i] == speed)
+	mlx5e_port_get_speed_arr(mdev, &table, &max_size);
+	for (i = 0; i < max_size; ++i) {
+		if (table[i] == speed)
 			link_modes |= MLX5E_PROT_MASK(i);
 	}
-
 	return link_modes;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index cd2160b8c9bf..70f536ec51c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -36,10 +36,22 @@
 #include <linux/mlx5/driver.h>
 #include "en.h"
 
-u32 mlx5e_port_ptys2speed(u32 eth_proto_oper);
+struct mlx5e_port_eth_proto {
+	u32 cap;
+	u32 admin;
+	u32 oper;
+};
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5e_port_eth_proto *eproto);
+void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status,
+				 u8 *an_disable_cap, u8 *an_disable_admin);
+int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
+			   u32 proto_admin, bool ext);
+u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper);
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-u32 mlx5e_port_speed2linkmodes(u32 speed);
+u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed);
 
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index eac245a93f91..4ab0d030b544 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -122,7 +122,9 @@ out:
 	return err;
 }
 
-/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B]) */
+/* xoff = ((301+2.16 * len [m]) * speed [Gbps] + 2.72 MTU [B])
+ * minimum speed value is 40Gbps
+ */
 static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 {
 	u32 speed;
@@ -130,10 +132,9 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 	int err;
 
 	err = mlx5e_port_linkspeed(priv->mdev, &speed);
-	if (err) {
-		mlx5_core_warn(priv->mdev, "cannot get port speed\n");
-		return 0;
-	}
+	if (err)
+		speed = SPEED_40000;
+	speed = max_t(u32, speed, SPEED_40000);
 
 	xoff = (301 + 216 * priv->dcbx.cable_len / 100) * speed / 1000 + 272 * mtu / 100;
 
@@ -142,7 +143,7 @@ static u32 calculate_xoff(struct mlx5e_priv *priv, unsigned int mtu)
 }
 
 static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
-				 u32 xoff, unsigned int mtu)
+				 u32 xoff, unsigned int max_mtu)
 {
 	int i;
 
@@ -154,11 +155,12 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 		}
 
 		if (port_buffer->buffer[i].size <
-		    (xoff + mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
+		    (xoff + max_mtu + (1 << MLX5E_BUFFER_CELL_SHIFT)))
 			return -ENOMEM;
 
 		port_buffer->buffer[i].xoff = port_buffer->buffer[i].size - xoff;
-		port_buffer->buffer[i].xon  = port_buffer->buffer[i].xoff - mtu;
+		port_buffer->buffer[i].xon  =
+			port_buffer->buffer[i].xoff - max_mtu;
 	}
 
 	return 0;
@@ -166,7 +168,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 
 /**
  * update_buffer_lossy()
- *   mtu: device's MTU
+ *   max_mtu: netdev's max_mtu
  *   pfc_en: <input> current pfc configuration
  *   buffer: <input> current prio to buffer mapping
  *   xoff:   <input> xoff value
@@ -183,7 +185,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *     Return 0 if no error.
  *     Set change to true if buffer configuration is modified.
  */
-static int update_buffer_lossy(unsigned int mtu,
+static int update_buffer_lossy(unsigned int max_mtu,
 			       u8 pfc_en, u8 *buffer, u32 xoff,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
@@ -220,7 +222,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	}
 
 	if (changed) {
-		err = update_xoff_threshold(port_buffer, xoff, mtu);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 
@@ -230,6 +232,7 @@ static int update_buffer_lossy(unsigned int mtu,
 	return 0;
 }
 
+#define MINIMUM_MAX_MTU 9216
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 				    u32 change, unsigned int mtu,
 				    struct ieee_pfc *pfc,
@@ -241,12 +244,14 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	bool update_prio2buffer = false;
 	u8 buffer[MLX5E_MAX_PRIORITY];
 	bool update_buffer = false;
+	unsigned int max_mtu;
 	u32 total_used = 0;
 	u8 curr_pfc_en;
 	int err;
 	int i;
 
 	mlx5e_dbg(HW, priv, "%s: change=%x\n", __func__, change);
+	max_mtu = max_t(unsigned int, priv->netdev->max_mtu, MINIMUM_MAX_MTU);
 
 	err = mlx5e_port_query_buffer(priv, &port_buffer);
 	if (err)
@@ -254,7 +259,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_CABLE_LEN) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -264,7 +269,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, pfc->pfc_en, buffer, xoff,
+		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff,
 					  &port_buffer, &update_buffer);
 		if (err)
 			return err;
@@ -276,8 +281,8 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(mtu, curr_pfc_en, prio2buffer, xoff,
-					  &port_buffer, &update_buffer);
+		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer,
+					  xoff, &port_buffer, &update_buffer);
 		if (err)
 			return err;
 	}
@@ -301,7 +306,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 			return -EINVAL;
 
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
@@ -309,7 +314,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	/* Need to update buffer configuration if xoff value is changed */
 	if (!update_buffer && xoff != priv->dcbx.xoff) {
 		update_buffer = true;
-		err = update_xoff_threshold(&port_buffer, xoff, mtu);
+		err = update_xoff_threshold(&port_buffer, xoff, max_mtu);
 		if (err)
 			return err;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
new file mode 100644
index 000000000000..e78e92753d73
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5E_EN_REPORTER_H
+#define __MLX5E_EN_REPORTER_H
+
+#include <linux/mlx5/driver.h>
+#include "en.h"
+
+int mlx5e_tx_reporter_create(struct mlx5e_priv *priv);
+void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv);
+void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq);
+int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
new file mode 100644
index 000000000000..476dd97f7f2f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -0,0 +1,314 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <net/devlink.h>
+#include "reporter.h"
+#include "lib/eq.h"
+
+#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256
+
+struct mlx5e_tx_err_ctx {
+	int (*recover)(struct mlx5e_txqsq *sq);
+	struct mlx5e_txqsq *sq;
+};
+
+static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
+{
+	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+
+	while (time_before(jiffies, exp_time)) {
+		if (sq->cc == sq->pc)
+			return 0;
+
+		msleep(20);
+	}
+
+	netdev_err(sq->channel->netdev,
+		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
+		   sq->sqn, sq->cc, sq->pc);
+
+	return -ETIMEDOUT;
+}
+
+static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
+{
+	WARN_ONCE(sq->cc != sq->pc,
+		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
+		  sq->sqn, sq->cc, sq->pc);
+	sq->cc = 0;
+	sq->dma_fifo_cc = 0;
+	sq->pc = 0;
+}
+
+static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+	struct net_device *dev = sq->channel->netdev;
+	struct mlx5e_modify_sq_param msp = {0};
+	int err;
+
+	msp.curr_state = curr_state;
+	msp.next_state = MLX5_SQC_STATE_RST;
+
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
+		return err;
+	}
+
+	memset(&msp, 0, sizeof(msp));
+	msp.curr_state = MLX5_SQC_STATE_RST;
+	msp.next_state = MLX5_SQC_STATE_RDY;
+
+	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
+	if (err) {
+		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
+		return err;
+	}
+
+	return 0;
+}
+
+static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_core_dev *mdev = sq->channel->mdev;
+	struct net_device *dev = sq->channel->netdev;
+	u8 state;
+	int err;
+
+	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
+		return 0;
+
+	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
+	if (err) {
+		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
+			   sq->sqn, err);
+		return err;
+	}
+
+	if (state != MLX5_SQC_STATE_ERR) {
+		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
+		return -EINVAL;
+	}
+
+	mlx5e_tx_disable_queue(sq->txq);
+
+	err = mlx5e_wait_for_sq_flush(sq);
+	if (err)
+		return err;
+
+	/* At this point, no new packets will arrive from the stack as TXQ is
+	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
+	 * pending WQEs. SQ can safely reset the SQ.
+	 */
+
+	err = mlx5e_sq_to_ready(sq, state);
+	if (err)
+		return err;
+
+	mlx5e_reset_txqsq_cc_pc(sq);
+	sq->stats->recover++;
+	mlx5e_activate_txqsq(sq);
+
+	return 0;
+}
+
+static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter,
+				 char *err_str,
+				 struct mlx5e_tx_err_ctx *err_ctx)
+{
+	if (IS_ERR_OR_NULL(tx_reporter)) {
+		netdev_err(err_ctx->sq->channel->netdev, err_str);
+		return err_ctx->recover(err_ctx->sq);
+	}
+
+	return devlink_health_report(tx_reporter, err_str, err_ctx);
+}
+
+void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq)
+{
+	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
+	struct mlx5e_tx_err_ctx err_ctx = {0};
+
+	err_ctx.sq       = sq;
+	err_ctx.recover  = mlx5e_tx_reporter_err_cqe_recover;
+	sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn);
+
+	mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
+			      &err_ctx);
+}
+
+static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq)
+{
+	struct mlx5_eq_comp *eq = sq->cq.mcq.eq;
+	u32 eqe_count;
+	int ret;
+
+	netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
+		   eq->core.eqn, eq->core.cons_index, eq->core.irqn);
+
+	eqe_count = mlx5_eq_poll_irq_disabled(eq);
+	ret = eqe_count ? false : true;
+	if (!eqe_count) {
+		clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
+		return ret;
+	}
+
+	netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n",
+		   eqe_count, eq->core.eqn);
+	sq->channel->stats->eq_rearm++;
+	return ret;
+}
+
+int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq)
+{
+	char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN];
+	struct mlx5e_tx_err_ctx err_ctx;
+
+	err_ctx.sq       = sq;
+	err_ctx.recover  = mlx5e_tx_reporter_timeout_recover;
+	sprintf(err_str,
+		"TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
+		sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
+		jiffies_to_usecs(jiffies - sq->txq->trans_start));
+
+	return mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str,
+				     &err_ctx);
+}
+
+/* state lock cannot be grabbed within this function.
+ * It can cause a dead lock or a read-after-free.
+ */
+static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx)
+{
+	return err_ctx->recover(err_ctx->sq);
+}
+
+static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv)
+{
+	int err = 0;
+
+	rtnl_lock();
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto out;
+
+	err = mlx5e_safe_reopen_channels(priv);
+
+out:
+	mutex_unlock(&priv->state_lock);
+	rtnl_unlock();
+
+	return err;
+}
+
+static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
+				     void *context)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	struct mlx5e_tx_err_ctx *err_ctx = context;
+
+	return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) :
+			 mlx5e_tx_reporter_recover_all(priv);
+}
+
+static int
+mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
+					u32 sqn, u8 state, bool stopped)
+{
+	int err;
+
+	err = devlink_fmsg_obj_nest_start(fmsg);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_u8_pair_put(fmsg, "HW state", state);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped);
+	if (err)
+		return err;
+
+	err = devlink_fmsg_obj_nest_end(fmsg);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+	int i, err = 0;
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs");
+	if (err)
+		goto unlock;
+
+	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc;
+	     i++) {
+		struct mlx5e_txqsq *sq = priv->txq2sq[i];
+		u8 state;
+
+		err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state);
+		if (err)
+			break;
+
+		err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn,
+							      state,
+							      netif_xmit_stopped(sq->txq));
+		if (err)
+			break;
+	}
+	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+	if (err)
+		goto unlock;
+
+unlock:
+	mutex_unlock(&priv->state_lock);
+	return err;
+}
+
+static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = {
+		.name = "tx",
+		.recover = mlx5e_tx_reporter_recover,
+		.diagnose = mlx5e_tx_reporter_diagnose,
+};
+
+#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500
+
+int mlx5e_tx_reporter_create(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct devlink *devlink = priv_to_devlink(mdev);
+
+	priv->tx_reporter =
+		devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops,
+					       MLX5_REPORTER_TX_GRACEFUL_PERIOD,
+					       true, priv);
+	if (IS_ERR(priv->tx_reporter))
+		netdev_warn(priv->netdev,
+			    "Failed to create tx reporter, err = %ld\n",
+			    PTR_ERR(priv->tx_reporter));
+	return IS_ERR_OR_NULL(priv->tx_reporter);
+}
+
+void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv)
+{
+	if (IS_ERR_OR_NULL(priv->tx_reporter))
+		return;
+
+	devlink_health_reporter_destroy(priv->tx_reporter);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
new file mode 100644
index 000000000000..eec07b34b4ad
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -0,0 +1,648 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#include <net/vxlan.h>
+#include <net/gre.h>
+#include "lib/vxlan.h"
+#include "en/tc_tun.h"
+
+static int get_route_and_out_devs(struct mlx5e_priv *priv,
+				  struct net_device *dev,
+				  struct net_device **route_dev,
+				  struct net_device **out_dev)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *uplink_dev, *uplink_upper;
+	bool dst_is_lag_dev;
+
+	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+	uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+	dst_is_lag_dev = (uplink_upper &&
+			  netif_is_lag_master(uplink_upper) &&
+			  dev == uplink_upper &&
+			  mlx5_lag_is_sriov(priv->mdev));
+
+	/* if the egress device isn't on the same HW e-switch or
+	 * it's a LAG device, use the uplink
+	 */
+	if (!netdev_port_same_parent_id(priv->netdev, dev) ||
+	    dst_is_lag_dev) {
+		*route_dev = uplink_dev;
+		*out_dev = *route_dev;
+	} else {
+		*route_dev = dev;
+		if (is_vlan_dev(*route_dev))
+			*out_dev = uplink_dev;
+		else if (mlx5e_eswitch_rep(dev))
+			*out_dev = *route_dev;
+		else
+			return -EOPNOTSUPP;
+	}
+
+	if (!(mlx5e_eswitch_rep(*out_dev) &&
+	      mlx5e_is_uplink_rep(netdev_priv(*out_dev))))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
+				   struct net_device *mirred_dev,
+				   struct net_device **out_dev,
+				   struct net_device **route_dev,
+				   struct flowi4 *fl4,
+				   struct neighbour **out_n,
+				   u8 *out_ttl)
+{
+	struct rtable *rt;
+	struct neighbour *n = NULL;
+
+#if IS_ENABLED(CONFIG_INET)
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct net_device *uplink_dev;
+	int ret;
+
+	if (mlx5_lag_is_multipath(mdev)) {
+		struct mlx5_eswitch *esw = mdev->priv.eswitch;
+
+		uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+		fl4->flowi4_oif = uplink_dev->ifindex;
+	}
+
+	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
+	ret = PTR_ERR_OR_ZERO(rt);
+	if (ret)
+		return ret;
+
+	if (mlx5_lag_is_multipath(mdev) && !rt->rt_gateway)
+		return -ENETUNREACH;
+#else
+	return -EOPNOTSUPP;
+#endif
+
+	ret = get_route_and_out_devs(priv, rt->dst.dev, route_dev, out_dev);
+	if (ret < 0)
+		return ret;
+
+	if (!(*out_ttl))
+		*out_ttl = ip4_dst_hoplimit(&rt->dst);
+	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
+	ip_rt_put(rt);
+	if (!n)
+		return -ENOMEM;
+
+	*out_n = n;
+	return 0;
+}
+
+static const char *mlx5e_netdev_kind(struct net_device *dev)
+{
+	if (dev->rtnl_link_ops)
+		return dev->rtnl_link_ops->kind;
+	else
+		return "";
+}
+
+static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
+				   struct net_device *mirred_dev,
+				   struct net_device **out_dev,
+				   struct net_device **route_dev,
+				   struct flowi6 *fl6,
+				   struct neighbour **out_n,
+				   u8 *out_ttl)
+{
+	struct neighbour *n = NULL;
+	struct dst_entry *dst;
+
+#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
+	int ret;
+
+	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
+					 fl6);
+	if (ret < 0)
+		return ret;
+
+	if (!(*out_ttl))
+		*out_ttl = ip6_dst_hoplimit(dst);
+
+	ret = get_route_and_out_devs(priv, dst->dev, route_dev, out_dev);
+	if (ret < 0)
+		return ret;
+#else
+	return -EOPNOTSUPP;
+#endif
+
+	n = dst_neigh_lookup(dst, &fl6->daddr);
+	dst_release(dst);
+	if (!n)
+		return -ENOMEM;
+
+	*out_n = n;
+	return 0;
+}
+
+static int mlx5e_gen_vxlan_header(char buf[], struct ip_tunnel_key *tun_key)
+{
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	struct udphdr *udp = (struct udphdr *)(buf);
+	struct vxlanhdr *vxh = (struct vxlanhdr *)
+			       ((char *)udp + sizeof(struct udphdr));
+
+	udp->dest = tun_key->tp_dst;
+	vxh->vx_flags = VXLAN_HF_VNI;
+	vxh->vx_vni = vxlan_vni_field(tun_id);
+
+	return 0;
+}
+
+static int mlx5e_gen_gre_header(char buf[], struct ip_tunnel_key *tun_key)
+{
+	__be32 tun_id = tunnel_id_to_key32(tun_key->tun_id);
+	int hdr_len;
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(buf);
+
+	/* the HW does not calculate GRE csum or sequences */
+	if (tun_key->tun_flags & (TUNNEL_CSUM | TUNNEL_SEQ))
+		return -EOPNOTSUPP;
+
+	greh->protocol = htons(ETH_P_TEB);
+
+	/* GRE key */
+	hdr_len = gre_calc_hlen(tun_key->tun_flags);
+	greh->flags = gre_tnl_flags_to_gre_flags(tun_key->tun_flags);
+	if (tun_key->tun_flags & TUNNEL_KEY) {
+		__be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4);
+
+		*ptr = tun_id;
+	}
+
+	return 0;
+}
+
+static int mlx5e_gen_ip_tunnel_header(char buf[], __u8 *ip_proto,
+				      struct mlx5e_encap_entry *e)
+{
+	int err = 0;
+	struct ip_tunnel_key *key = &e->tun_info.key;
+
+	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		*ip_proto = IPPROTO_UDP;
+		err = mlx5e_gen_vxlan_header(buf, key);
+	} else if  (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		*ip_proto = IPPROTO_GRE;
+		err = mlx5e_gen_gre_header(buf, key);
+	} else {
+		pr_warn("mlx5: Cannot generate tunnel header for tunnel type (%d)\n"
+			, e->tunnel_type);
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static char *gen_eth_tnl_hdr(char *buf, struct net_device *dev,
+			     struct mlx5e_encap_entry *e,
+			     u16 proto)
+{
+	struct ethhdr *eth = (struct ethhdr *)buf;
+	char *ip;
+
+	ether_addr_copy(eth->h_dest, e->h_dest);
+	ether_addr_copy(eth->h_source, dev->dev_addr);
+	if (is_vlan_dev(dev)) {
+		struct vlan_hdr *vlan = (struct vlan_hdr *)
+					((char *)eth + ETH_HLEN);
+		ip = (char *)vlan + VLAN_HLEN;
+		eth->h_proto = vlan_dev_vlan_proto(dev);
+		vlan->h_vlan_TCI = htons(vlan_dev_vlan_id(dev));
+		vlan->h_vlan_encapsulated_proto = htons(proto);
+	} else {
+		eth->h_proto = htons(proto);
+		ip = (char *)eth + ETH_HLEN;
+	}
+
+	return ip;
+}
+
+int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e)
+{
+	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	struct net_device *out_dev, *route_dev;
+	struct neighbour *n = NULL;
+	struct flowi4 fl4 = {};
+	int ipv4_encap_size;
+	char *encap_header;
+	u8 nud_state, ttl;
+	struct iphdr *ip;
+	int err;
+
+	/* add the IP fields */
+	fl4.flowi4_tos = tun_key->tos;
+	fl4.daddr = tun_key->u.ipv4.dst;
+	fl4.saddr = tun_key->u.ipv4.src;
+	ttl = tun_key->ttl;
+
+	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev, &route_dev,
+				      &fl4, &n, &ttl);
+	if (err)
+		return err;
+
+	ipv4_encap_size =
+		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
+		sizeof(struct iphdr) +
+		e->tunnel_hlen;
+
+	if (max_encap_size < ipv4_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv4_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
+
+	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
+	if (!encap_header)
+		return -ENOMEM;
+
+	/* used by mlx5e_detach_encap to lookup a neigh hash table
+	 * entry in the neigh hash table when a user deletes a rule
+	 */
+	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
+	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+	e->out_dev = out_dev;
+	e->route_dev = route_dev;
+
+	/* It's important to add the neigh to the hash table before checking
+	 * the neigh validity state. So if we'll get a notification, in case the
+	 * neigh changes it's validity state, we would find the relevant neigh
+	 * in the hash.
+	 */
+	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
+	if (err)
+		goto free_encap;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(e->h_dest, n->ha);
+	read_unlock_bh(&n->lock);
+
+	/* add ethernet header */
+	ip = (struct iphdr *)gen_eth_tnl_hdr(encap_header, route_dev, e,
+					     ETH_P_IP);
+
+	/* add ip header */
+	ip->tos = tun_key->tos;
+	ip->version = 0x4;
+	ip->ihl = 0x5;
+	ip->ttl = ttl;
+	ip->daddr = fl4.daddr;
+	ip->saddr = fl4.saddr;
+
+	/* add tunneling protocol header */
+	err = mlx5e_gen_ip_tunnel_header((char *)ip + sizeof(struct iphdr),
+					 &ip->protocol, e);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->encap_size = ipv4_encap_size;
+	e->encap_header = encap_header;
+
+	if (!(nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+		/* the encap entry will be made valid on neigh update event
+		 * and not used before that.
+		 */
+		goto out;
+	}
+
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
+					 ipv4_encap_size, encap_header,
+					 MLX5_FLOW_NAMESPACE_FDB,
+					 &e->encap_id);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
+	neigh_release(n);
+	return err;
+
+destroy_neigh_entry:
+	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
+free_encap:
+	kfree(encap_header);
+out:
+	if (n)
+		neigh_release(n);
+	return err;
+}
+
+int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e)
+{
+	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
+	struct ip_tunnel_key *tun_key = &e->tun_info.key;
+	struct net_device *out_dev, *route_dev;
+	struct neighbour *n = NULL;
+	struct flowi6 fl6 = {};
+	struct ipv6hdr *ip6h;
+	int ipv6_encap_size;
+	char *encap_header;
+	u8 nud_state, ttl;
+	int err;
+
+	ttl = tun_key->ttl;
+
+	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
+	fl6.daddr = tun_key->u.ipv6.dst;
+	fl6.saddr = tun_key->u.ipv6.src;
+
+	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev, &route_dev,
+				      &fl6, &n, &ttl);
+	if (err)
+		return err;
+
+	ipv6_encap_size =
+		(is_vlan_dev(route_dev) ? VLAN_ETH_HLEN : ETH_HLEN) +
+		sizeof(struct ipv6hdr) +
+		e->tunnel_hlen;
+
+	if (max_encap_size < ipv6_encap_size) {
+		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
+			       ipv6_encap_size, max_encap_size);
+		return -EOPNOTSUPP;
+	}
+
+	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
+	if (!encap_header)
+		return -ENOMEM;
+
+	/* used by mlx5e_detach_encap to lookup a neigh hash table
+	 * entry in the neigh hash table when a user deletes a rule
+	 */
+	e->m_neigh.dev = n->dev;
+	e->m_neigh.family = n->ops->family;
+	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
+	e->out_dev = out_dev;
+	e->route_dev = route_dev;
+
+	/* It's importent to add the neigh to the hash table before checking
+	 * the neigh validity state. So if we'll get a notification, in case the
+	 * neigh changes it's validity state, we would find the relevant neigh
+	 * in the hash.
+	 */
+	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
+	if (err)
+		goto free_encap;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(e->h_dest, n->ha);
+	read_unlock_bh(&n->lock);
+
+	/* add ethernet header */
+	ip6h = (struct ipv6hdr *)gen_eth_tnl_hdr(encap_header, route_dev, e,
+						 ETH_P_IPV6);
+
+	/* add ip header */
+	ip6_flow_hdr(ip6h, tun_key->tos, 0);
+	/* the HW fills up ipv6 payload len */
+	ip6h->hop_limit   = ttl;
+	ip6h->daddr	  = fl6.daddr;
+	ip6h->saddr	  = fl6.saddr;
+
+	/* add tunneling protocol header */
+	err = mlx5e_gen_ip_tunnel_header((char *)ip6h + sizeof(struct ipv6hdr),
+					 &ip6h->nexthdr, e);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->encap_size = ipv6_encap_size;
+	e->encap_header = encap_header;
+
+	if (!(nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+		/* the encap entry will be made valid on neigh update event
+		 * and not used before that.
+		 */
+		goto out;
+	}
+
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
+					 ipv6_encap_size, encap_header,
+					 MLX5_FLOW_NAMESPACE_FDB,
+					 &e->encap_id);
+	if (err)
+		goto destroy_neigh_entry;
+
+	e->flags |= MLX5_ENCAP_ENTRY_VALID;
+	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
+	neigh_release(n);
+	return err;
+
+destroy_neigh_entry:
+	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
+free_encap:
+	kfree(encap_header);
+out:
+	if (n)
+		neigh_release(n);
+	return err;
+}
+
+int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev)
+{
+	if (netif_is_vxlan(tunnel_dev))
+		return MLX5E_TC_TUNNEL_TYPE_VXLAN;
+	else if (netif_is_gretap(tunnel_dev) ||
+		 netif_is_ip6gretap(tunnel_dev))
+		return MLX5E_TC_TUNNEL_TYPE_GRETAP;
+	else
+		return MLX5E_TC_TUNNEL_TYPE_UNKNOWN;
+}
+
+bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
+				    struct net_device *netdev)
+{
+	int tunnel_type = mlx5e_tc_tun_get_type(netdev);
+
+	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN &&
+	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
+		return true;
+	else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP &&
+		 MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap))
+		return true;
+	else
+		return false;
+}
+
+int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
+				 struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct netlink_ext_ack *extack)
+{
+	e->tunnel_type = mlx5e_tc_tun_get_type(tunnel_dev);
+
+	if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		int dst_port =  be16_to_cpu(e->tun_info.key.tp_dst);
+
+		if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, dst_port)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "vxlan udp dport was not registered with the HW");
+			netdev_warn(priv->netdev,
+				    "%d isn't an offloaded vxlan udp dport\n",
+				    dst_port);
+			return -EOPNOTSUPP;
+		}
+		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
+		e->tunnel_hlen = VXLAN_HLEN;
+	} else if (e->tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		e->reformat_type = MLX5_REFORMAT_TYPE_L2_TO_NVGRE;
+		e->tunnel_hlen = gre_calc_hlen(e->tun_info.key.tun_flags);
+	} else {
+		e->reformat_type = -1;
+		e->tunnel_hlen = -1;
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
+				    struct mlx5_flow_spec *spec,
+				    struct tc_cls_flower_offload *f,
+				    void *headers_c,
+				    void *headers_v)
+{
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct netlink_ext_ack *extack = f->common.extack;
+	void *misc_c = MLX5_ADDR_OF(fte_match_param,
+				    spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param,
+				    spec->match_value,
+				    misc_parameters);
+	struct flow_match_ports enc_ports;
+
+	flow_rule_match_enc_ports(rule, &enc_ports);
+
+	/* Full udp dst port must be given */
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) ||
+	    memchr_inv(&enc_ports.mask->dst, 0xff, sizeof(enc_ports.mask->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "VXLAN decap filter must include enc_dst_port condition");
+		netdev_warn(priv->netdev,
+			    "VXLAN decap filter must include enc_dst_port condition\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* udp dst port must be knonwn as a VXLAN port */
+	if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(enc_ports.key->dst))) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Matched UDP port is not registered as a VXLAN port");
+		netdev_warn(priv->netdev,
+			    "UDP port %d is not registered as a VXLAN port\n",
+			    be16_to_cpu(enc_ports.key->dst));
+		return -EOPNOTSUPP;
+	}
+
+	/* dst UDP port is valid here */
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
+
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport,
+		 ntohs(enc_ports.mask->dst));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport,
+		 ntohs(enc_ports.key->dst));
+
+	MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport,
+		 ntohs(enc_ports.mask->src));
+	MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport,
+		 ntohs(enc_ports.key->src));
+
+	/* match on VNI */
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid enc_keyid;
+
+		flow_rule_match_enc_keyid(rule, &enc_keyid);
+
+		MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
+			 be32_to_cpu(enc_keyid.mask->keyid));
+		MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
+			 be32_to_cpu(enc_keyid.key->keyid));
+	}
+	return 0;
+}
+
+static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
+				     struct mlx5_flow_spec *spec,
+				     struct tc_cls_flower_offload *f,
+				     void *outer_headers_c,
+				     void *outer_headers_v)
+{
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+
+	if (!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap)) {
+		NL_SET_ERR_MSG_MOD(f->common.extack,
+				   "GRE HW offloading is not supported");
+		netdev_warn(priv->netdev, "GRE HW offloading is not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol);
+	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
+		 ip_protocol, IPPROTO_GRE);
+
+	/* gre protocol*/
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc_c, gre_protocol);
+	MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB);
+
+	/* gre key */
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid enc_keyid;
+
+		flow_rule_match_enc_keyid(rule, &enc_keyid);
+		MLX5_SET(fte_match_set_misc, misc_c,
+			 gre_key.key, be32_to_cpu(enc_keyid.mask->keyid));
+		MLX5_SET(fte_match_set_misc, misc_v,
+			 gre_key.key, be32_to_cpu(enc_keyid.key->keyid));
+	}
+
+	return 0;
+}
+
+int mlx5e_tc_tun_parse(struct net_device *filter_dev,
+		       struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct tc_cls_flower_offload *f,
+		       void *headers_c,
+		       void *headers_v, u8 *match_level)
+{
+	int tunnel_type;
+	int err = 0;
+
+	tunnel_type = mlx5e_tc_tun_get_type(filter_dev);
+	if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) {
+		*match_level = MLX5_MATCH_L4;
+		err = mlx5e_tc_tun_parse_vxlan(priv, spec, f,
+					       headers_c, headers_v);
+	} else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) {
+		*match_level = MLX5_MATCH_L3;
+		err = mlx5e_tc_tun_parse_gretap(priv, spec, f,
+						headers_c, headers_v);
+	} else {
+		netdev_warn(priv->netdev,
+			    "decapsulation offload is not supported for %s net device (%d)\n",
+			    mlx5e_netdev_kind(filter_dev), tunnel_type);
+		return -EOPNOTSUPP;
+	}
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
new file mode 100644
index 000000000000..b63f15de899d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_TC_TUNNEL_H__
+#define __MLX5_EN_TC_TUNNEL_H__
+
+#include <linux/netdevice.h>
+#include <linux/mlx5/fs.h>
+#include <net/pkt_cls.h>
+#include <linux/netlink.h>
+#include "en.h"
+#include "en_rep.h"
+
+enum {
+	MLX5E_TC_TUNNEL_TYPE_UNKNOWN,
+	MLX5E_TC_TUNNEL_TYPE_VXLAN,
+	MLX5E_TC_TUNNEL_TYPE_GRETAP
+};
+
+int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
+				 struct mlx5e_priv *priv,
+				 struct mlx5e_encap_entry *e,
+				 struct netlink_ext_ack *extack);
+
+int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e);
+
+int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
+				    struct net_device *mirred_dev,
+				    struct mlx5e_encap_entry *e);
+
+int mlx5e_tc_tun_get_type(struct net_device *tunnel_dev);
+bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
+				    struct net_device *netdev);
+
+int mlx5e_tc_tun_parse(struct net_device *filter_dev,
+		       struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct tc_cls_flower_offload *f,
+		       void *headers_c,
+		       void *headers_v, u8 *match_level);
+
+#endif //__MLX5_EN_TC_TUNNEL_H__
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index ad6d471d00dd..cad34d6f5f45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -33,6 +33,26 @@
 #include <linux/bpf_trace.h>
 #include "en/xdp.h"
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params)
+{
+	int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM;
+
+	/* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)).
+	 * The condition checked in mlx5e_rx_is_linear_skb is:
+	 *   SKB_DATA_ALIGN(sw_mtu + hard_mtu + hr) + S <= PAGE_SIZE         (1)
+	 *   (Note that hw_mtu == sw_mtu + hard_mtu.)
+	 * What is returned from this function is:
+	 *   max_mtu = PAGE_SIZE - S - hr - hard_mtu                         (2)
+	 * After assigning sw_mtu := max_mtu, the left side of (1) turns to
+	 * SKB_DATA_ALIGN(PAGE_SIZE - S) + S, which is equal to PAGE_SIZE,
+	 * because both PAGE_SIZE and S are already aligned. Any number greater
+	 * than max_mtu would make the left side of (1) greater than PAGE_SIZE,
+	 * so max_mtu is the maximum MTU allowed.
+	 */
+
+	return MLX5E_HW2SW_MTU(params, SKB_MAX_HEAD(hr));
+}
+
 static inline bool
 mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
 		    struct xdp_buff *xdp)
@@ -47,7 +67,7 @@ mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
 				   xdpi.xdpf->len, PCI_DMA_TODEVICE);
 	xdpi.di = *di;
 
-	return mlx5e_xmit_xdp_frame(sq, &xdpi);
+	return sq->xmit_xdp_frame(sq, &xdpi);
 }
 
 /* returns true if packet was consumed by xdp */
@@ -102,7 +122,98 @@ xdp_abort:
 	}
 }
 
-bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
+static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u8  wqebbs;
+	u16 pi;
+
+	mlx5e_xdpsq_fetch_wqe(sq, &session->wqe);
+
+	prefetchw(session->wqe->data);
+	session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+
+/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS
+ * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment.
+ * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a
+ * full-session WQE be cache-aligned.
+ */
+#if L1_CACHE_BYTES < 128
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1)
+#else
+#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2)
+#endif
+
+	wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi),
+		       MLX5E_XDP_MPW_MAX_WQEBBS);
+
+	session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs;
+}
+
+static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5_wq_cyc       *wq    = &sq->wq;
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wqe_ctrl_seg *cseg = &session->wqe->ctrl;
+	u16 ds_count = session->ds_count;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_xdp_wqe_info *wi = &sq->db.wqe_info[pi];
+
+	cseg->opmod_idx_opcode =
+		cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_ENHANCED_MPSW);
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_count);
+
+	wi->num_wqebbs = DIV_ROUND_UP(ds_count, MLX5_SEND_WQEBB_NUM_DS);
+	wi->num_ds     = ds_count - MLX5E_XDP_TX_EMPTY_DS_COUNT;
+
+	sq->pc += wi->num_wqebbs;
+
+	sq->doorbell_cseg = cseg;
+
+	session->wqe = NULL; /* Close session */
+}
+
+static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq,
+				       struct mlx5e_xdp_info *xdpi)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
+
+	dma_addr_t dma_addr    = xdpi->dma_addr;
+	struct xdp_frame *xdpf = xdpi->xdpf;
+	unsigned int dma_len   = xdpf->len;
+
+	if (unlikely(sq->hw_mtu < dma_len)) {
+		stats->err++;
+		return false;
+	}
+
+	if (unlikely(!session->wqe)) {
+		if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc,
+						     MLX5_SEND_WQE_MAX_WQEBBS))) {
+			/* SQ is full, ring doorbell */
+			mlx5e_xmit_xdp_doorbell(sq);
+			stats->full++;
+			return false;
+		}
+
+		mlx5e_xdp_mpwqe_session_start(sq);
+	}
+
+	mlx5e_xdp_mpwqe_add_dseg(sq, dma_addr, dma_len);
+
+	if (unlikely(session->ds_count == session->max_ds_count))
+		mlx5e_xdp_mpwqe_complete(sq);
+
+	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
+	stats->xmit++;
+	return true;
+}
+
+static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 {
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
 	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
@@ -126,11 +237,8 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	}
 
 	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		if (sq->doorbell) {
-			/* SQ is full, ring doorbell */
-			mlx5e_xmit_xdp_doorbell(sq);
-			sq->doorbell = false;
-		}
+		/* SQ is full, ring doorbell */
+		mlx5e_xmit_xdp_doorbell(sq);
 		stats->full++;
 		return false;
 	}
@@ -152,23 +260,20 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
 
-	/* move page to reference to sq responsibility,
-	 * and mark so it's not put back in page-cache.
-	 */
-	sq->db.xdpi[pi] = *xdpi;
 	sq->pc++;
 
-	sq->doorbell = true;
+	sq->doorbell_cseg = cseg;
 
+	mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi);
 	stats->xmit++;
 	return true;
 }
 
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq)
 {
+	struct mlx5e_xdp_info_fifo *xdpi_fifo;
 	struct mlx5e_xdpsq *sq;
 	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
 	bool is_redirect;
 	u16 sqcc;
 	int i;
@@ -182,8 +287,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	if (!cqe)
 		return false;
 
-	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
-	rq = container_of(sq, struct mlx5e_rq, xdpsq);
+	is_redirect = !rq;
+	xdpi_fifo = &sq->db.xdpi_fifo;
 
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
 	 * otherwise a cq overrun may occur
@@ -199,20 +304,33 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
+		if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ))
+			netdev_WARN_ONCE(sq->channel->netdev,
+					 "Bad OP in XDPSQ CQE: 0x%x\n",
+					 get_cqe_opcode(cqe));
+
 		do {
-			u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+			struct mlx5e_xdp_wqe_info *wi;
+			u16 ci, j;
 
 			last_wqe = (sqcc == wqe_counter);
-			sqcc++;
-
-			if (is_redirect) {
-				xdp_return_frame(xdpi->xdpf);
-				dma_unmap_single(sq->pdev, xdpi->dma_addr,
-						 xdpi->xdpf->len, DMA_TO_DEVICE);
-			} else {
-				/* Recycle RX page */
-				mlx5e_page_release(rq, &xdpi->di, true);
+			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			wi = &sq->db.wqe_info[ci];
+
+			sqcc += wi->num_wqebbs;
+
+			for (j = 0; j < wi->num_ds; j++) {
+				struct mlx5e_xdp_info xdpi =
+					mlx5e_xdpi_fifo_pop(xdpi_fifo);
+
+				if (is_redirect) {
+					dma_unmap_single(sq->pdev, xdpi.dma_addr,
+							 xdpi.xdpf->len, DMA_TO_DEVICE);
+					xdp_return_frame(xdpi.xdpf);
+				} else {
+					/* Recycle RX page */
+					mlx5e_page_release(rq, &xdpi.di, true);
+				}
 			}
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
@@ -228,27 +346,32 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }
 
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 {
-	struct mlx5e_rq *rq;
-	bool is_redirect;
-
-	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
-	rq = is_redirect ? NULL : container_of(sq, struct mlx5e_rq, xdpsq);
+	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
+	bool is_redirect = !rq;
 
 	while (sq->cc != sq->pc) {
-		u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
-
-		sq->cc++;
-
-		if (is_redirect) {
-			xdp_return_frame(xdpi->xdpf);
-			dma_unmap_single(sq->pdev, xdpi->dma_addr,
-					 xdpi->xdpf->len, DMA_TO_DEVICE);
-		} else {
-			/* Recycle RX page */
-			mlx5e_page_release(rq, &xdpi->di, false);
+		struct mlx5e_xdp_wqe_info *wi;
+		u16 ci, i;
+
+		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+		wi = &sq->db.wqe_info[ci];
+
+		sq->cc += wi->num_wqebbs;
+
+		for (i = 0; i < wi->num_ds; i++) {
+			struct mlx5e_xdp_info xdpi =
+				mlx5e_xdpi_fifo_pop(xdpi_fifo);
+
+			if (is_redirect) {
+				dma_unmap_single(sq->pdev, xdpi.dma_addr,
+						 xdpi.xdpf->len, DMA_TO_DEVICE);
+				xdp_return_frame(xdpi.xdpf);
+			} else {
+				/* Recycle RX page */
+				mlx5e_page_release(rq, &xdpi.di, false);
+			}
 		}
 	}
 }
@@ -262,7 +385,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	int sq_num;
 	int i;
 
-	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+	/* this flag is sufficient, no need to test internal sq state */
+	if (unlikely(!mlx5e_xdp_tx_is_enabled(priv)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -275,9 +399,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 	sq = &priv->channels.c[sq_num]->xdpsq;
 
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return -ENETDOWN;
-
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *xdpf = frames[i];
 		struct mlx5e_xdp_info xdpi;
@@ -292,7 +413,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 
 		xdpi.xdpf = xdpf;
 
-		if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) {
+		if (unlikely(!sq->xmit_xdp_frame(sq, &xdpi))) {
 			dma_unmap_single(sq->pdev, xdpi.dma_addr,
 					 xdpf->len, DMA_TO_DEVICE);
 			xdp_return_frame_rx_napi(xdpf);
@@ -300,8 +421,33 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		}
 	}
 
-	if (flags & XDP_XMIT_FLUSH)
+	if (flags & XDP_XMIT_FLUSH) {
+		if (sq->mpwqe.wqe)
+			mlx5e_xdp_mpwqe_complete(sq);
 		mlx5e_xmit_xdp_doorbell(sq);
+	}
 
 	return n - drops;
 }
+
+void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq)
+{
+	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
+
+	if (xdpsq->mpwqe.wqe)
+		mlx5e_xdp_mpwqe_complete(xdpsq);
+
+	mlx5e_xmit_xdp_doorbell(xdpsq);
+
+	if (xdpsq->redirect_flush) {
+		xdp_do_flush_map();
+		xdpsq->redirect_flush = false;
+	}
+}
+
+void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw)
+{
+	sq->xmit_xdp_frame = is_mpw ?
+		mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame;
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 6dfab045925f..553956cadc8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -34,30 +34,81 @@
 
 #include "en.h"
 
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
-				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 #define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_TX_DS_COUNT \
-	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
+#define MLX5E_XDP_TX_EMPTY_DS_COUNT \
+	(sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS)
+#define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */)
 
+int mlx5e_xdp_max_mtu(struct mlx5e_params *params);
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len);
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
-
-bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq);
+void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw);
+void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq);
 int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		   u32 flags);
 
+static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv)
+{
+	set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
+static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv)
+{
+	clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+	/* let other device's napi(s) see our new state */
+	synchronize_rcu();
+}
+
+static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv)
+{
+	return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state);
+}
+
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
+	if (sq->doorbell_cseg) {
+		mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, sq->doorbell_cseg);
+		sq->doorbell_cseg = NULL;
+	}
+}
+
+static inline void
+mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, dma_addr_t dma_addr, u16 dma_len)
+{
+	struct mlx5e_xdp_mpwqe *session = &sq->mpwqe;
+	struct mlx5_wqe_data_seg *dseg =
+		(struct mlx5_wqe_data_seg *)session->wqe + session->ds_count++;
+
+	dseg->addr       = cpu_to_be64(dma_addr);
+	dseg->byte_count = cpu_to_be32(dma_len);
+	dseg->lkey       = sq->mkey_be;
+}
+
+static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq,
+					 struct mlx5e_tx_wqe **wqe)
+{
 	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *wqe;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 
-	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+	*wqe = mlx5_wq_cyc_get_wqe(wq, pi);
+	memset(*wqe, 0, sizeof(**wqe));
+}
 
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
+static inline void
+mlx5e_xdpi_fifo_push(struct mlx5e_xdp_info_fifo *fifo,
+		     struct mlx5e_xdp_info *xi)
+{
+	u32 i = (*fifo->pc)++ & fifo->mask;
+
+	fifo->xi[i] = *xi;
+}
+
+static inline struct mlx5e_xdp_info
+mlx5e_xdpi_fifo_pop(struct mlx5e_xdp_info_fifo *fifo)
+{
+	return fifo->xi[(*fifo->cc)++ & fifo->mask];
 }
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index 128a82b1dbfc..53608afd39b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -254,11 +254,13 @@ struct sk_buff *mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 	struct mlx5e_ipsec_metadata *mdata;
 	struct mlx5e_ipsec_sa_entry *sa_entry;
 	struct xfrm_state *x;
+	struct sec_path *sp;
 
 	if (!xo)
 		return skb;
 
-	if (unlikely(skb->sp->len != 1)) {
+	sp = skb_sec_path(skb);
+	if (unlikely(sp->len != 1)) {
 		atomic64_inc(&priv->ipsec->sw_stats.ipsec_tx_drop_bundle);
 		goto drop;
 	}
@@ -305,10 +307,11 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct xfrm_offload *xo;
 	struct xfrm_state *xs;
+	struct sec_path *sp;
 	u32 sa_handle;
 
-	skb->sp = secpath_dup(skb->sp);
-	if (unlikely(!skb->sp)) {
+	sp = secpath_set(skb);
+	if (unlikely(!sp)) {
 		atomic64_inc(&priv->ipsec->sw_stats.ipsec_rx_drop_sp_alloc);
 		return NULL;
 	}
@@ -320,8 +323,9 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 		return NULL;
 	}
 
-	skb->sp->xvec[skb->sp->len++] = xs;
-	skb->sp->olen++;
+	sp = skb_sec_path(skb);
+	sp->xvec[sp->len++] = xs;
+	sp->olen++;
 
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
@@ -372,10 +376,11 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 bool mlx5e_ipsec_feature_check(struct sk_buff *skb, struct net_device *netdev,
 			       netdev_features_t features)
 {
+	struct sec_path *sp = skb_sec_path(skb);
 	struct xfrm_state *x;
 
-	if (skb->sp && skb->sp->len) {
-		x = skb->sp->xvec[0];
+	if (sp && sp->len) {
+		x = sp->xvec[0];
 		if (x && x->xso.offload_handle)
 			return true;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index 3078491cc0d0..1539cf3de5dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 	if (err)
 		return err;
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 }
@@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
 		       struct mlx5e_tir *tir)
 {
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	mlx5_core_destroy_tir(mdev, tir->tirn);
 	list_del(&tir->list);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 }
 
 static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
@@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev)
 	}
 
 	INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list);
+	mutex_init(&mdev->mlx5e_res.td.list_lock);
 
 	return 0;
 
@@ -141,15 +146,17 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_tir *tir;
-	int err  = -ENOMEM;
+	int err  = 0;
 	u32 tirn = 0;
 	int inlen;
 	void *in;
 
 	inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	in = kvzalloc(inlen, GFP_KERNEL);
-	if (!in)
+	if (!in) {
+		err = -ENOMEM;
 		goto out;
+	}
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
@@ -157,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
+	mutex_lock(&mdev->mlx5e_res.td.list_lock);
 	list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) {
 		tirn = tir->tirn;
 		err = mlx5_core_modify_tir(mdev, tirn, in, inlen);
@@ -168,6 +176,7 @@ out:
 	kvfree(in);
 	if (err)
 		netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err);
+	mutex_unlock(&mdev->mlx5e_res.td.list_lock);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 722998d68564..554672edf8c3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -1126,9 +1126,7 @@ static void mlx5e_trust_update_sq_inline_mode(struct mlx5e_priv *priv)
 	    priv->channels.params.tx_min_inline_mode)
 		goto out;
 
-	if (mlx5e_open_channels(priv, &new_channels))
-		goto out;
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 out:
 	mutex_unlock(&priv->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index f480763dcd0d..78dc8fe2a83c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -63,86 +63,158 @@ struct ptys2ethtool_config {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertised);
 };
 
-static struct ptys2ethtool_config ptys2ethtool_table[MLX5E_LINK_MODES_NUMBER];
+static
+struct ptys2ethtool_config ptys2legacy_ethtool_table[MLX5E_LINK_MODES_NUMBER];
+static
+struct ptys2ethtool_config ptys2ext_ethtool_table[MLX5E_EXT_LINK_MODES_NUMBER];
 
-#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, ...)                       \
+#define MLX5_BUILD_PTYS2ETHTOOL_CONFIG(reg_, table, ...)                  \
 	({                                                              \
 		struct ptys2ethtool_config *cfg;                        \
 		const unsigned int modes[] = { __VA_ARGS__ };           \
-		unsigned int i;                                         \
-		cfg = &ptys2ethtool_table[reg_];                        \
+		unsigned int i, bit, idx;                               \
+		cfg = &ptys2##table##_ethtool_table[reg_];		\
 		bitmap_zero(cfg->supported,                             \
 			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
 		bitmap_zero(cfg->advertised,                            \
 			    __ETHTOOL_LINK_MODE_MASK_NBITS);            \
 		for (i = 0 ; i < ARRAY_SIZE(modes) ; ++i) {             \
-			__set_bit(modes[i], cfg->supported);            \
-			__set_bit(modes[i], cfg->advertised);           \
+			bit = modes[i] % 64;                            \
+			idx = modes[i] / 64;                            \
+			__set_bit(bit, &cfg->supported[idx]);           \
+			__set_bit(bit, &cfg->advertised[idx]);          \
 		}                                                       \
 	})
 
 void mlx5e_build_ptys2ethtool_map(void)
 {
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII,
+	memset(ptys2legacy_ethtool_table, 0, sizeof(ptys2legacy_ethtool_table));
+	memset(ptys2ext_ethtool_table, 0, sizeof(ptys2ext_ethtool_table));
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_CX_SGMII, legacy,
 				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_KX, legacy,
 				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CX4, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KX4, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_KR, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_20GBASE_KR2, legacy,
 				       ETHTOOL_LINK_MODE_20000baseKR2_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_CR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_KR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_56GBASE_R4, legacy,
 				       ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_CR, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_SR, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_ER, legacy,
 				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_SR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_LR4, legacy,
 				       ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_SR2, legacy,
 				       ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_CR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_SR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_KR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, legacy,
 				       ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, legacy,
 				       ETHTOOL_LINK_MODE_10000baseT_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, legacy,
 				       ETHTOOL_LINK_MODE_25000baseCR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_KR, legacy,
 				       ETHTOOL_LINK_MODE_25000baseKR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_SR, legacy,
 				       ETHTOOL_LINK_MODE_25000baseSR_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_CR2, legacy,
 				       ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT);
-	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2,
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GBASE_KR2, legacy,
 				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_SGMII_100M, ext,
+				       ETHTOOL_LINK_MODE_100baseT_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_X_SGMII, ext,
+				       ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+				       ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+				       ETHTOOL_LINK_MODE_1000baseX_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_5GBASE_R, ext,
+				       ETHTOOL_LINK_MODE_5000baseT_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_XFI_XAUI_1, ext,
+				       ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+				       ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+				       ETHTOOL_LINK_MODE_10000baseER_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_40GBASE_XLAUI_4_XLPPI_4, ext,
+				       ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GAUI_1_25GBASE_CR_KR, ext,
+				       ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_25000baseSR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2,
+				       ext,
+				       ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR, ext,
+				       ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+				       ETHTOOL_LINK_MODE_50000baseDR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_CAUI_4_100GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_2_100GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_4_200GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT);
+}
+
+static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
+					struct ptys2ethtool_config **arr,
+					u32 *size)
+{
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+
+	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
+	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
+		      ARRAY_SIZE(ptys2legacy_ethtool_table);
 }
 
-static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = {
-	"rx_cqe_moder",
-	"tx_cqe_moder",
-	"rx_cqe_compress",
-	"rx_striding_rq",
-	"rx_no_csum_complete",
+typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable);
+
+struct pflag_desc {
+	char name[ETH_GSTRING_LEN];
+	mlx5e_pflag_handler handler;
 };
 
+static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS];
+
 int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
 {
 	int i, num_stats = 0;
@@ -153,7 +225,7 @@ int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
 			num_stats += mlx5e_stats_grps[i].get_num_stats(priv);
 		return num_stats;
 	case ETH_SS_PRIV_FLAGS:
-		return ARRAY_SIZE(mlx5e_priv_flags);
+		return MLX5E_NUM_PFLAGS;
 	case ETH_SS_TEST:
 		return mlx5e_self_test_num(priv);
 	/* fallthrough */
@@ -183,8 +255,9 @@ void mlx5e_ethtool_get_strings(struct mlx5e_priv *priv, u32 stringset, u8 *data)
 
 	switch (stringset) {
 	case ETH_SS_PRIV_FLAGS:
-		for (i = 0; i < ARRAY_SIZE(mlx5e_priv_flags); i++)
-			strcpy(data + i * ETH_GSTRING_LEN, mlx5e_priv_flags[i]);
+		for (i = 0; i < MLX5E_NUM_PFLAGS; i++)
+			strcpy(data + i * ETH_GSTRING_LEN,
+			       mlx5e_priv_flags[i].name);
 		break;
 
 	case ETH_SS_TEST:
@@ -296,11 +369,7 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv,
 		goto unlock;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto unlock;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
@@ -352,32 +421,32 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv,
 
 	new_channels.params = priv->channels.params;
 	new_channels.params.num_channels = count;
-	if (!netif_is_rxfh_configured(priv->netdev))
-		mlx5e_build_default_indir_rqt(new_channels.params.indirection_rqt,
-					      MLX5E_INDIR_RQT_SIZE, count);
 
 	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 		priv->channels.params = new_channels.params;
+		if (!netif_is_rxfh_configured(priv->netdev))
+			mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+						      MLX5E_INDIR_RQT_SIZE, count);
 		goto out;
 	}
 
-	/* Create fresh channels with new parameters */
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
 	arfs_enabled = priv->netdev->features & NETIF_F_NTUPLE;
 	if (arfs_enabled)
 		mlx5e_arfs_disable(priv);
 
+	if (!netif_is_rxfh_configured(priv->netdev))
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
+					      MLX5E_INDIR_RQT_SIZE, count);
+
 	/* Switch to new channels, set new parameters and close old ones */
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 	if (arfs_enabled) {
-		err = mlx5e_arfs_enable(priv);
-		if (err)
+		int err2 = mlx5e_arfs_enable(priv);
+
+		if (err2)
 			netdev_err(priv->netdev, "%s: mlx5e_arfs_enable failed: %d\n",
-				   __func__, err);
+				   __func__, err2);
 	}
 
 out:
@@ -503,12 +572,7 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	/* open fresh channels with new coal parameters */
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 
 out:
 	mutex_unlock(&priv->state_lock);
@@ -523,27 +587,37 @@ static int mlx5e_set_coalesce(struct net_device *netdev,
 	return mlx5e_ethtool_set_coalesce(priv, coal);
 }
 
-static void ptys2ethtool_supported_link(unsigned long *supported_modes,
+static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
+					unsigned long *supported_modes,
 					u32 eth_proto_cap)
 {
 	unsigned long proto_cap = eth_proto_cap;
+	struct ptys2ethtool_config *table;
+	u32 max_size;
 	int proto;
 
-	for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
+	mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
+	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(supported_modes, supported_modes,
-			  ptys2ethtool_table[proto].supported,
+			  table[proto].supported,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
 static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
-				    u32 eth_proto_cap)
+				    u32 eth_proto_cap, bool ext)
 {
 	unsigned long proto_cap = eth_proto_cap;
+	struct ptys2ethtool_config *table;
+	u32 max_size;
 	int proto;
 
-	for_each_set_bit(proto, &proto_cap, MLX5E_LINK_MODES_NUMBER)
+	table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
+	max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
+			 ARRAY_SIZE(ptys2legacy_ethtool_table);
+
+	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(advertising_modes, advertising_modes,
-			  ptys2ethtool_table[proto].advertised,
+			  table[proto].advertised,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
@@ -693,13 +767,14 @@ static void get_speed_duplex(struct net_device *netdev,
 			     u32 eth_proto_oper,
 			     struct ethtool_link_ksettings *link_ksettings)
 {
+	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 speed = SPEED_UNKNOWN;
 	u8 duplex = DUPLEX_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5e_port_ptys2speed(eth_proto_oper);
+	speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper);
 	if (!speed) {
 		speed = SPEED_UNKNOWN;
 		goto out;
@@ -712,22 +787,22 @@ out:
 	link_ksettings->base.duplex = duplex;
 }
 
-static void get_supported(u32 eth_proto_cap,
+static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 			  struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *supported = link_ksettings->link_modes.supported;
+	ptys2ethtool_supported_link(mdev, supported, eth_proto_cap);
 
-	ptys2ethtool_supported_link(supported, eth_proto_cap);
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
 
-static void get_advertising(u32 eth_proto_cap, u8 tx_pause,
-			    u8 rx_pause,
-			    struct ethtool_link_ksettings *link_ksettings)
+static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+			    struct ethtool_link_ksettings *link_ksettings,
+			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
+	ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
 
-	ptys2ethtool_adver_link(advertising, eth_proto_cap);
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
@@ -777,18 +852,18 @@ static u8 get_connector_port(u32 eth_proto, u8 connector_type)
 	return PORT_OTHER;
 }
 
-static void get_lp_advertising(u32 eth_proto_lp,
+static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 			       struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
+	bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
 
-	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp);
+	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
 }
 
-static int mlx5e_get_link_ksettings(struct net_device *netdev,
-				    struct ethtool_link_ksettings *link_ksettings)
+int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
+				     struct ethtool_link_ksettings *link_ksettings)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0};
 	u32 rx_pause = 0;
@@ -800,31 +875,50 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	u8 an_disable_admin;
 	u8 an_status;
 	u8 connector_type;
+	bool admin_ext;
+	bool ext;
 	int err;
 
 	err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1);
 	if (err) {
-		netdev_err(netdev, "%s: query port ptys failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port ptys failed: %d\n",
 			   __func__, err);
 		goto err_query_regs;
 	}
+	ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	eth_proto_cap    = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					      eth_proto_capability);
+	eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					      eth_proto_admin);
+	/* Fields: eth_proto_admin and ext_eth_proto_admin  are
+	 * mutually exclusive. Hence try reading legacy advertising
+	 * when extended advertising is zero.
+	 * admin_ext indicates how eth_proto_admin should be
+	 * interpreted
+	 */
+	admin_ext = ext;
+	if (ext && !eth_proto_admin) {
+		eth_proto_admin  = MLX5_GET_ETH_PROTO(ptys_reg, out, false,
+						      eth_proto_admin);
+		admin_ext = false;
+	}
 
-	eth_proto_cap    = MLX5_GET(ptys_reg, out, eth_proto_capability);
-	eth_proto_admin  = MLX5_GET(ptys_reg, out, eth_proto_admin);
-	eth_proto_oper   = MLX5_GET(ptys_reg, out, eth_proto_oper);
-	eth_proto_lp     = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
-	an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
-	an_status        = MLX5_GET(ptys_reg, out, an_status);
-	connector_type   = MLX5_GET(ptys_reg, out, connector_type);
+	eth_proto_oper   = MLX5_GET_ETH_PROTO(ptys_reg, out, ext,
+					      eth_proto_oper);
+	eth_proto_lp	    = MLX5_GET(ptys_reg, out, eth_proto_lp_advertise);
+	an_disable_admin    = MLX5_GET(ptys_reg, out, an_disable_admin);
+	an_status	    = MLX5_GET(ptys_reg, out, an_status);
+	connector_type	    = MLX5_GET(ptys_reg, out, connector_type);
 
 	mlx5_query_port_pause(mdev, &rx_pause, &tx_pause);
 
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, supported);
 	ethtool_link_ksettings_zero_link_mode(link_ksettings, advertising);
 
-	get_supported(eth_proto_cap, link_ksettings);
-	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings);
-	get_speed_duplex(netdev, eth_proto_oper, link_ksettings);
+	get_supported(mdev, eth_proto_cap, link_ksettings);
+	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
+			admin_ext);
+	get_speed_duplex(priv->netdev, eth_proto_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 
@@ -832,7 +926,7 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 						       connector_type);
 	ptys2ethtool_supported_advertised_port(link_ksettings, eth_proto_admin,
 					       connector_type);
-	get_lp_advertising(eth_proto_lp, link_ksettings);
+	get_lp_advertising(mdev, eth_proto_lp, link_ksettings);
 
 	if (an_status == MLX5_AN_COMPLETE)
 		ethtool_link_ksettings_add_link_mode(link_ksettings,
@@ -843,9 +937,12 @@ static int mlx5e_get_link_ksettings(struct net_device *netdev,
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported,
 					     Autoneg);
 
-	if (get_fec_supported_advertised(mdev, link_ksettings))
-		netdev_dbg(netdev, "%s: FEC caps query failed: %d\n",
+	err = get_fec_supported_advertised(mdev, link_ksettings);
+	if (err) {
+		netdev_dbg(priv->netdev, "%s: FEC caps query failed: %d\n",
 			   __func__, err);
+		err = 0; /* don't fail caps query because of FEC error */
+	}
 
 	if (!an_disable_admin)
 		ethtool_link_ksettings_add_link_mode(link_ksettings,
@@ -855,12 +952,22 @@ err_query_regs:
 	return err;
 }
 
+static int mlx5e_get_link_ksettings(struct net_device *netdev,
+				    struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
+}
+
 static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 {
 	u32 i, ptys_modes = 0;
 
 	for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) {
-		if (bitmap_intersects(ptys2ethtool_table[i].advertised,
+		if (*ptys2legacy_ethtool_table[i].advertised == 0)
+			continue;
+		if (bitmap_intersects(ptys2legacy_ethtool_table[i].advertised,
 				      link_modes,
 				      __ETHTOOL_LINK_MODE_MASK_NBITS))
 			ptys_modes |= MLX5E_PROT_MASK(i);
@@ -869,14 +976,34 @@ static u32 mlx5e_ethtool2ptys_adver_link(const unsigned long *link_modes)
 	return ptys_modes;
 }
 
-static int mlx5e_set_link_ksettings(struct net_device *netdev,
-				    const struct ethtool_link_ksettings *link_ksettings)
+static u32 mlx5e_ethtool2ptys_ext_adver_link(const unsigned long *link_modes)
+{
+	u32 i, ptys_modes = 0;
+	unsigned long modes[2];
+
+	for (i = 0; i < MLX5E_EXT_LINK_MODES_NUMBER; ++i) {
+		if (*ptys2ext_ethtool_table[i].advertised == 0)
+			continue;
+		memset(modes, 0, sizeof(modes));
+		bitmap_and(modes, ptys2ext_ethtool_table[i].advertised,
+			   link_modes, __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+		if (modes[0] == ptys2ext_ethtool_table[i].advertised[0] &&
+		    modes[1] == ptys2ext_ethtool_table[i].advertised[1])
+			ptys_modes |= MLX5E_PROT_MASK(i);
+	}
+	return ptys_modes;
+}
+
+int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
+				     const struct ethtool_link_ksettings *link_ksettings)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u32 eth_proto_cap, eth_proto_admin;
+	struct mlx5e_port_eth_proto eproto;
 	bool an_changes = false;
 	u8 an_disable_admin;
+	bool ext_supported;
+	bool ext_requested;
 	u8 an_disable_cap;
 	bool an_disable;
 	u32 link_modes;
@@ -884,54 +1011,66 @@ static int mlx5e_set_link_ksettings(struct net_device *netdev,
 	u32 speed;
 	int err;
 
-	speed = link_ksettings->base.speed;
+	u32 (*ethtool2ptys_adver_func)(const unsigned long *adver);
 
-	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
-		mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) :
-		mlx5e_port_speed2linkmodes(speed);
+#define MLX5E_PTYS_EXT ((1ULL << ETHTOOL_LINK_MODE_50000baseKR_Full_BIT) - 1)
+
+	ext_requested = !!(link_ksettings->link_modes.advertising[0] >
+			MLX5E_PTYS_EXT ||
+			link_ksettings->link_modes.advertising[1]);
+	ext_supported = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet);
+	ext_requested &= ext_supported;
 
-	err = mlx5_query_port_proto_cap(mdev, &eth_proto_cap, MLX5_PTYS_EN);
+	speed = link_ksettings->base.speed;
+	ethtool2ptys_adver_func = ext_requested ?
+				  mlx5e_ethtool2ptys_ext_adver_link :
+				  mlx5e_ethtool2ptys_adver_link;
+	err = mlx5_port_query_eth_proto(mdev, 1, ext_requested, &eproto);
 	if (err) {
-		netdev_err(netdev, "%s: query port eth proto cap failed: %d\n",
+		netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n",
 			   __func__, err);
 		goto out;
 	}
+	link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ?
+		ethtool2ptys_adver_func(link_ksettings->link_modes.advertising) :
+		mlx5e_port_speed2linkmodes(mdev, speed);
 
-	link_modes = link_modes & eth_proto_cap;
+	link_modes = link_modes & eproto.cap;
 	if (!link_modes) {
-		netdev_err(netdev, "%s: Not supported link mode(s) requested",
+		netdev_err(priv->netdev, "%s: Not supported link mode(s) requested",
 			   __func__);
 		err = -EINVAL;
 		goto out;
 	}
 
-	err = mlx5_query_port_proto_admin(mdev, &eth_proto_admin, MLX5_PTYS_EN);
-	if (err) {
-		netdev_err(netdev, "%s: query port eth proto admin failed: %d\n",
-			   __func__, err);
-		goto out;
-	}
-
-	mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status,
-				&an_disable_cap, &an_disable_admin);
+	mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap,
+				    &an_disable_admin);
 
 	an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE;
 	an_changes = ((!an_disable && an_disable_admin) ||
 		      (an_disable && !an_disable_admin));
 
-	if (!an_changes && link_modes == eth_proto_admin)
+	if (!an_changes && link_modes == eproto.admin)
 		goto out;
 
-	mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN);
+	mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext_requested);
 	mlx5_toggle_port_link(mdev);
 
 out:
 	return err;
 }
 
+static int mlx5e_set_link_ksettings(struct net_device *netdev,
+				    const struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_link_ksettings(priv, link_ksettings);
+}
+
 u32 mlx5e_ethtool_get_rxfh_key_size(struct mlx5e_priv *priv)
 {
-	return sizeof(priv->channels.params.toeplitz_hash_key);
+	return sizeof(priv->rss_params.toeplitz_hash_key);
 }
 
 static u32 mlx5e_get_rxfh_key_size(struct net_device *netdev)
@@ -957,50 +1096,27 @@ static int mlx5e_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key,
 			  u8 *hfunc)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 
 	if (indir)
-		memcpy(indir, priv->channels.params.indirection_rqt,
-		       sizeof(priv->channels.params.indirection_rqt));
+		memcpy(indir, rss->indirection_rqt,
+		       sizeof(rss->indirection_rqt));
 
 	if (key)
-		memcpy(key, priv->channels.params.toeplitz_hash_key,
-		       sizeof(priv->channels.params.toeplitz_hash_key));
+		memcpy(key, rss->toeplitz_hash_key,
+		       sizeof(rss->toeplitz_hash_key));
 
 	if (hfunc)
-		*hfunc = priv->channels.params.rss_hfunc;
+		*hfunc = rss->hfunc;
 
 	return 0;
 }
 
-static void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
-{
-	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
-	int tt;
-
-	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
-		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
-	}
-
-	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
-		return;
-
-	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
-		memset(tirc, 0, ctxlen);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
-		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in, inlen);
-	}
-}
-
 static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 			  const u8 *key, const u8 hfunc)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
 	bool hash_changed = false;
 	void *in;
@@ -1016,15 +1132,14 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 
 	mutex_lock(&priv->state_lock);
 
-	if (hfunc != ETH_RSS_HASH_NO_CHANGE &&
-	    hfunc != priv->channels.params.rss_hfunc) {
-		priv->channels.params.rss_hfunc = hfunc;
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != rss->hfunc) {
+		rss->hfunc = hfunc;
 		hash_changed = true;
 	}
 
 	if (indir) {
-		memcpy(priv->channels.params.indirection_rqt, indir,
-		       sizeof(priv->channels.params.indirection_rqt));
+		memcpy(rss->indirection_rqt, indir,
+		       sizeof(rss->indirection_rqt));
 
 		if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
 			u32 rqtn = priv->indir_rqt.rqtn;
@@ -1032,7 +1147,7 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 				.is_rss = true,
 				{
 					.rss = {
-						.hfunc = priv->channels.params.rss_hfunc,
+						.hfunc = rss->hfunc,
 						.channels  = &priv->channels,
 					},
 				},
@@ -1043,10 +1158,9 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	}
 
 	if (key) {
-		memcpy(priv->channels.params.toeplitz_hash_key, key,
-		       sizeof(priv->channels.params.toeplitz_hash_key));
-		hash_changed = hash_changed ||
-			       priv->channels.params.rss_hfunc == ETH_RSS_HASH_TOP;
+		memcpy(rss->toeplitz_hash_key, key,
+		       sizeof(rss->toeplitz_hash_key));
+		hash_changed = hash_changed || rss->hfunc == ETH_RSS_HASH_TOP;
 	}
 
 	if (hash_changed)
@@ -1150,25 +1264,31 @@ static int mlx5e_set_tunable(struct net_device *dev,
 	return err;
 }
 
-static void mlx5e_get_pauseparam(struct net_device *netdev,
-				 struct ethtool_pauseparam *pauseparam)
+void mlx5e_ethtool_get_pauseparam(struct mlx5e_priv *priv,
+				  struct ethtool_pauseparam *pauseparam)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
 	err = mlx5_query_port_pause(mdev, &pauseparam->rx_pause,
 				    &pauseparam->tx_pause);
 	if (err) {
-		netdev_err(netdev, "%s: mlx5_query_port_pause failed:0x%x\n",
+		netdev_err(priv->netdev, "%s: mlx5_query_port_pause failed:0x%x\n",
 			   __func__, err);
 	}
 }
 
-static int mlx5e_set_pauseparam(struct net_device *netdev,
-				struct ethtool_pauseparam *pauseparam)
+static void mlx5e_get_pauseparam(struct net_device *netdev,
+				 struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	mlx5e_ethtool_get_pauseparam(priv, pauseparam);
+}
+
+int mlx5e_ethtool_set_pauseparam(struct mlx5e_priv *priv,
+				 struct ethtool_pauseparam *pauseparam)
 {
-	struct mlx5e_priv *priv    = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int err;
 
@@ -1179,13 +1299,21 @@ static int mlx5e_set_pauseparam(struct net_device *netdev,
 				  pauseparam->rx_pause ? 1 : 0,
 				  pauseparam->tx_pause ? 1 : 0);
 	if (err) {
-		netdev_err(netdev, "%s: mlx5_set_port_pause failed:0x%x\n",
+		netdev_err(priv->netdev, "%s: mlx5_set_port_pause failed:0x%x\n",
 			   __func__, err);
 	}
 
 	return err;
 }
 
+static int mlx5e_set_pauseparam(struct net_device *netdev,
+				struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_pauseparam(priv, pauseparam);
+}
+
 int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 			      struct ethtool_ts_info *info)
 {
@@ -1458,7 +1586,7 @@ static int mlx5e_get_module_info(struct net_device *netdev,
 		break;
 	case MLX5_MODULE_ID_SFP:
 		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		modinfo->eeprom_len = MLX5_EEPROM_PAGE_LENGTH;
 		break;
 	default:
 		netdev_err(priv->netdev, "%s: cable type not recognized:0x%x\n",
@@ -1505,8 +1633,6 @@ static int mlx5e_get_module_eeprom(struct net_device *netdev,
 	return 0;
 }
 
-typedef int (*mlx5e_pflag_handler)(struct net_device *netdev, bool enable);
-
 static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 				     bool is_rx_cq)
 {
@@ -1515,7 +1641,6 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 	struct mlx5e_channels new_channels = {};
 	bool mode_changed;
 	u8 cq_period_mode, current_cq_period_mode;
-	int err = 0;
 
 	cq_period_mode = enable ?
 		MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
@@ -1543,12 +1668,7 @@ static int set_pflag_cqe_based_moder(struct net_device *netdev, bool enable,
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		return err;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
-	return 0;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 }
 
 static int set_pflag_tx_cqe_based_moder(struct net_device *netdev, bool enable)
@@ -1581,11 +1701,10 @@ int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool new_val
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 	if (err)
 		return err;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 	mlx5e_dbg(DRV, priv, "MLX5E: RxCqeCmprss was turned %s\n",
 		  MLX5E_GET_PFLAG(&priv->channels.params,
 				  MLX5E_PFLAG_RX_CQE_COMPRESS) ? "ON" : "OFF");
@@ -1618,7 +1737,6 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5e_channels new_channels = {};
-	int err;
 
 	if (enable) {
 		if (!mlx5e_check_fragmented_striding_rq_cap(mdev))
@@ -1640,12 +1758,7 @@ static int set_pflag_rx_striding_rq(struct net_device *netdev, bool enable)
 		return 0;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		return err;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
-	return 0;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 }
 
 static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
@@ -1655,7 +1768,8 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	struct mlx5e_channel *c;
 	int i;
 
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state) ||
+	    priv->channels.params.xdp_prog)
 		return 0;
 
 	for (i = 0; i < channels->num; i++) {
@@ -1669,23 +1783,54 @@ static int set_pflag_rx_no_csum_complete(struct net_device *netdev, bool enable)
 	return 0;
 }
 
+static int set_pflag_xdp_tx_mpwqe(struct net_device *netdev, bool enable)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_channels new_channels = {};
+	int err;
+
+	if (enable && !MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe))
+		return -EOPNOTSUPP;
+
+	new_channels.params = priv->channels.params;
+
+	MLX5E_SET_PFLAG(&new_channels.params, MLX5E_PFLAG_XDP_TX_MPWQE, enable);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
+		priv->channels.params = new_channels.params;
+		return 0;
+	}
+
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+	return err;
+}
+
+static const struct pflag_desc mlx5e_priv_flags[MLX5E_NUM_PFLAGS] = {
+	{ "rx_cqe_moder",        set_pflag_rx_cqe_based_moder },
+	{ "tx_cqe_moder",        set_pflag_tx_cqe_based_moder },
+	{ "rx_cqe_compress",     set_pflag_rx_cqe_compress },
+	{ "rx_striding_rq",      set_pflag_rx_striding_rq },
+	{ "rx_no_csum_complete", set_pflag_rx_no_csum_complete },
+	{ "xdp_tx_mpwqe",        set_pflag_xdp_tx_mpwqe },
+};
+
 static int mlx5e_handle_pflag(struct net_device *netdev,
 			      u32 wanted_flags,
-			      enum mlx5e_priv_flag flag,
-			      mlx5e_pflag_handler pflag_handler)
+			      enum mlx5e_priv_flag flag)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	bool enable = !!(wanted_flags & flag);
+	bool enable = !!(wanted_flags & BIT(flag));
 	u32 changes = wanted_flags ^ priv->channels.params.pflags;
 	int err;
 
-	if (!(changes & flag))
+	if (!(changes & BIT(flag)))
 		return 0;
 
-	err = pflag_handler(netdev, enable);
+	err = mlx5e_priv_flags[flag].handler(netdev, enable);
 	if (err) {
-		netdev_err(netdev, "%s private flag 0x%x failed err %d\n",
-			   enable ? "Enable" : "Disable", flag, err);
+		netdev_err(netdev, "%s private flag '%s' failed err %d\n",
+			   enable ? "Enable" : "Disable", mlx5e_priv_flags[flag].name, err);
 		return err;
 	}
 
@@ -1696,38 +1841,17 @@ static int mlx5e_handle_pflag(struct net_device *netdev,
 static int mlx5e_set_priv_flags(struct net_device *netdev, u32 pflags)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	enum mlx5e_priv_flag pflag;
 	int err;
 
 	mutex_lock(&priv->state_lock);
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_CQE_BASED_MODER,
-				 set_pflag_rx_cqe_based_moder);
-	if (err)
-		goto out;
-
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_TX_CQE_BASED_MODER,
-				 set_pflag_tx_cqe_based_moder);
-	if (err)
-		goto out;
 
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_CQE_COMPRESS,
-				 set_pflag_rx_cqe_compress);
-	if (err)
-		goto out;
-
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_STRIDING_RQ,
-				 set_pflag_rx_striding_rq);
-	if (err)
-		goto out;
-
-	err = mlx5e_handle_pflag(netdev, pflags,
-				 MLX5E_PFLAG_RX_NO_CSUM_COMPLETE,
-				 set_pflag_rx_no_csum_complete);
+	for (pflag = 0; pflag < MLX5E_NUM_PFLAGS; pflag++) {
+		err = mlx5e_handle_pflag(netdev, pflags, pflag);
+		if (err)
+			break;
+	}
 
-out:
 	mutex_unlock(&priv->state_lock);
 
 	/* Need to fix some features.. */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index c18dcebe1462..4421c10f58ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -771,6 +771,112 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
 	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
 }
 
+static enum mlx5e_traffic_types flow_type_to_traffic_type(u32 flow_type)
+{
+	switch (flow_type) {
+	case TCP_V4_FLOW:
+		return  MLX5E_TT_IPV4_TCP;
+	case TCP_V6_FLOW:
+		return MLX5E_TT_IPV6_TCP;
+	case UDP_V4_FLOW:
+		return MLX5E_TT_IPV4_UDP;
+	case UDP_V6_FLOW:
+		return MLX5E_TT_IPV6_UDP;
+	case AH_V4_FLOW:
+		return MLX5E_TT_IPV4_IPSEC_AH;
+	case AH_V6_FLOW:
+		return MLX5E_TT_IPV6_IPSEC_AH;
+	case ESP_V4_FLOW:
+		return MLX5E_TT_IPV4_IPSEC_ESP;
+	case ESP_V6_FLOW:
+		return MLX5E_TT_IPV6_IPSEC_ESP;
+	case IPV4_FLOW:
+		return MLX5E_TT_IPV4;
+	case IPV6_FLOW:
+		return MLX5E_TT_IPV6;
+	default:
+		return MLX5E_NUM_INDIR_TIRS;
+	}
+}
+
+static int mlx5e_set_rss_hash_opt(struct mlx5e_priv *priv,
+				  struct ethtool_rxnfc *nfc)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_tir_in);
+	enum mlx5e_traffic_types tt;
+	u8 rx_hash_field = 0;
+	void *in;
+
+	tt = flow_type_to_traffic_type(nfc->flow_type);
+	if (tt == MLX5E_NUM_INDIR_TIRS)
+		return -EINVAL;
+
+	/*  RSS does not support anything other than hashing to queues
+	 *  on src IP, dest IP, TCP/UDP src port and TCP/UDP dest
+	 *  port.
+	 */
+	if (nfc->flow_type != TCP_V4_FLOW &&
+	    nfc->flow_type != TCP_V6_FLOW &&
+	    nfc->flow_type != UDP_V4_FLOW &&
+	    nfc->flow_type != UDP_V6_FLOW)
+		return -EOPNOTSUPP;
+
+	if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST |
+			  RXH_L4_B_0_1 | RXH_L4_B_2_3))
+		return -EOPNOTSUPP;
+
+	if (nfc->data & RXH_IP_SRC)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_SRC_IP;
+	if (nfc->data & RXH_IP_DST)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_DST_IP;
+	if (nfc->data & RXH_L4_B_0_1)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_SPORT;
+	if (nfc->data & RXH_L4_B_2_3)
+		rx_hash_field |= MLX5_HASH_FIELD_SEL_L4_DPORT;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	mutex_lock(&priv->state_lock);
+
+	if (rx_hash_field == priv->rss_params.rx_hash_fields[tt])
+		goto out;
+
+	priv->rss_params.rx_hash_fields[tt] = rx_hash_field;
+	mlx5e_modify_tirs_hash(priv, in, inlen);
+
+out:
+	mutex_unlock(&priv->state_lock);
+	kvfree(in);
+	return 0;
+}
+
+static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv,
+				  struct ethtool_rxnfc *nfc)
+{
+	enum mlx5e_traffic_types tt;
+	u32 hash_field = 0;
+
+	tt = flow_type_to_traffic_type(nfc->flow_type);
+	if (tt == MLX5E_NUM_INDIR_TIRS)
+		return -EINVAL;
+
+	hash_field = priv->rss_params.rx_hash_fields[tt];
+	nfc->data = 0;
+
+	if (hash_field & MLX5_HASH_FIELD_SEL_SRC_IP)
+		nfc->data |= RXH_IP_SRC;
+	if (hash_field & MLX5_HASH_FIELD_SEL_DST_IP)
+		nfc->data |= RXH_IP_DST;
+	if (hash_field & MLX5_HASH_FIELD_SEL_L4_SPORT)
+		nfc->data |= RXH_L4_B_0_1;
+	if (hash_field & MLX5_HASH_FIELD_SEL_L4_DPORT)
+		nfc->data |= RXH_L4_B_2_3;
+
+	return 0;
+}
+
 int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 {
 	int err = 0;
@@ -783,6 +889,9 @@ int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXCLSRLDEL:
 		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
 		break;
+	case ETHTOOL_SRXFH:
+		err = mlx5e_set_rss_hash_opt(priv, cmd);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
@@ -810,6 +919,9 @@ int mlx5e_get_rxnfc(struct net_device *dev,
 	case ETHTOOL_GRXCLSRLALL:
 		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
 		break;
+	case ETHTOOL_GRXFH:
+		err =  mlx5e_get_rss_hash_opt(priv, info);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 		break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index b70cb6fd164c..46157e2a1e5a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -35,6 +35,7 @@
 #include <linux/mlx5/fs.h>
 #include <net/vxlan.h>
 #include <linux/bpf.h>
+#include <linux/if_bridge.h>
 #include <net/page_pool.h>
 #include "eswitch.h"
 #include "en.h"
@@ -49,6 +50,9 @@
 #include "lib/clock.h"
 #include "en/port.h"
 #include "en/xdp.h"
+#include "lib/eq.h"
+#include "en/monitor_stats.h"
+#include "en/reporter.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
@@ -59,6 +63,7 @@ struct mlx5e_rq_param {
 struct mlx5e_sq_param {
 	u32                        sqc[MLX5_ST_SZ_DW(sqc)];
 	struct mlx5_wq_param       wq;
+	bool                       is_mpw;
 };
 
 struct mlx5e_cq_param {
@@ -168,8 +173,7 @@ static u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev,
 	if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params))
 		return order_base_2(mlx5e_rx_get_linear_frag_sz(params));
 
-	return MLX5E_MPWQE_STRIDE_SZ(mdev,
-		MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS));
+	return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev);
 }
 
 static u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev,
@@ -228,7 +232,7 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params)
 		MLX5_WQ_TYPE_CYCLIC;
 }
 
-static void mlx5e_update_carrier(struct mlx5e_priv *priv)
+void mlx5e_update_carrier(struct mlx5e_priv *priv)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 port_state;
@@ -267,7 +271,7 @@ void mlx5e_update_stats(struct mlx5e_priv *priv)
 			mlx5e_stats_grps[i].update_stats(priv);
 }
 
-static void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
+void mlx5e_update_ndo_stats(struct mlx5e_priv *priv)
 {
 	int i;
 
@@ -298,33 +302,35 @@ void mlx5e_queue_update_stats(struct mlx5e_priv *priv)
 	queue_work(priv->wq, &priv->update_stats_work);
 }
 
-static void mlx5e_async_event(struct mlx5_core_dev *mdev, void *vpriv,
-			      enum mlx5_dev_event event, unsigned long param)
+static int async_event(struct notifier_block *nb, unsigned long event, void *data)
 {
-	struct mlx5e_priv *priv = vpriv;
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+	struct mlx5_eqe   *eqe = data;
 
-	if (!test_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state))
-		return;
+	if (event != MLX5_EVENT_TYPE_PORT_CHANGE)
+		return NOTIFY_DONE;
 
-	switch (event) {
-	case MLX5_DEV_EVENT_PORT_UP:
-	case MLX5_DEV_EVENT_PORT_DOWN:
+	switch (eqe->sub_type) {
+	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
 		queue_work(priv->wq, &priv->update_carrier_work);
 		break;
 	default:
-		break;
+		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_OK;
 }
 
 static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 {
-	set_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
+	priv->events_nb.notifier_call = async_event;
+	mlx5_notifier_register(priv->mdev, &priv->events_nb);
 }
 
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
-	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
+	mlx5_notifier_unregister(priv->mdev, &priv->events_nb);
 }
 
 static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
@@ -945,7 +951,11 @@ static int mlx5e_open_rq(struct mlx5e_channel *c,
 	if (params->rx_dim_enabled)
 		__set_bit(MLX5E_RQ_STATE_AM, &c->rq.state);
 
-	if (params->pflags & MLX5E_PFLAG_RX_NO_CSUM_COMPLETE)
+	/* We disable csum_complete when XDP is enabled since
+	 * XDP programs might manipulate packets which will render
+	 * skb->checksum incorrect.
+	 */
+	if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) || c->xdp)
 		__set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state);
 
 	return 0;
@@ -988,18 +998,42 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kvfree(sq->db.xdpi);
+	kvfree(sq->db.xdpi_fifo.xi);
+	kvfree(sq->db.wqe_info);
+}
+
+static int mlx5e_alloc_xdpsq_fifo(struct mlx5e_xdpsq *sq, int numa)
+{
+	struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo;
+	int wq_sz        = mlx5_wq_cyc_get_size(&sq->wq);
+	int dsegs_per_wq = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
+
+	xdpi_fifo->xi = kvzalloc_node(sizeof(*xdpi_fifo->xi) * dsegs_per_wq,
+				      GFP_KERNEL, numa);
+	if (!xdpi_fifo->xi)
+		return -ENOMEM;
+
+	xdpi_fifo->pc   = &sq->xdpi_fifo_pc;
+	xdpi_fifo->cc   = &sq->xdpi_fifo_cc;
+	xdpi_fifo->mask = dsegs_per_wq - 1;
+
+	return 0;
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
+	int err;
 
-	sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)),
-				    GFP_KERNEL, numa);
-	if (!sq->db.xdpi) {
-		mlx5e_free_xdpsq_db(sq);
+	sq->db.wqe_info = kvzalloc_node(sizeof(*sq->db.wqe_info) * wq_sz,
+					GFP_KERNEL, numa);
+	if (!sq->db.wqe_info)
 		return -ENOMEM;
+
+	err = mlx5e_alloc_xdpsq_fifo(sq, numa);
+	if (err) {
+		mlx5e_free_xdpsq_db(sq);
+		return err;
 	}
 
 	return 0;
@@ -1131,7 +1165,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	return 0;
 }
 
-static void mlx5e_sq_recover(struct work_struct *work);
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work);
 static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 			     int txq_ix,
 			     struct mlx5e_params *params,
@@ -1153,7 +1187,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->stats     = &c->priv->channel_stats[c->ix].sq[tc];
-	INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover);
+	INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work);
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 	if (mlx5_accel_is_tls_device(c->priv->mdev))
@@ -1241,15 +1275,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
 	return err;
 }
 
-struct mlx5e_modify_sq_param {
-	int curr_state;
-	int next_state;
-	bool rl_update;
-	int rl_index;
-};
-
-static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
-			   struct mlx5e_modify_sq_param *p)
+int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn,
+		    struct mlx5e_modify_sq_param *p)
 {
 	void *in;
 	void *sqc;
@@ -1347,17 +1374,7 @@ err_free_txqsq:
 	return err;
 }
 
-static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq)
-{
-	WARN_ONCE(sq->cc != sq->pc,
-		  "SQ 0x%x: cc (0x%x) != pc (0x%x)\n",
-		  sq->sqn, sq->cc, sq->pc);
-	sq->cc = 0;
-	sq->dma_fifo_cc = 0;
-	sq->pc = 0;
-}
-
-static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
+void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 {
 	sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix);
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
@@ -1366,7 +1383,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq)
 	netif_tx_start_queue(sq->txq);
 }
 
-static inline void netif_tx_disable_queue(struct netdev_queue *txq)
+void mlx5e_tx_disable_queue(struct netdev_queue *txq)
 {
 	__netif_tx_lock_bh(txq);
 	netif_tx_stop_queue(txq);
@@ -1382,7 +1399,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq)
 	/* prevent netif_tx_wake_queue */
 	napi_synchronize(&c->napi);
 
-	netif_tx_disable_queue(sq->txq);
+	mlx5e_tx_disable_queue(sq->txq);
 
 	/* last doorbell out, godspeed .. */
 	if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) {
@@ -1402,6 +1419,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	struct mlx5_rate_limit rl = {0};
 
 	cancel_work_sync(&sq->dim.work);
+	cancel_work_sync(&sq->recover_work);
 	mlx5e_destroy_sq(mdev, sq->sqn);
 	if (sq->rate_limit) {
 		rl.rate = sq->rate_limit;
@@ -1411,105 +1429,12 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq)
 	mlx5e_free_txqsq(sq);
 }
 
-static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
+static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work)
 {
-	unsigned long exp_time = jiffies + msecs_to_jiffies(2000);
+	struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq,
+					      recover_work);
 
-	while (time_before(jiffies, exp_time)) {
-		if (sq->cc == sq->pc)
-			return 0;
-
-		msleep(20);
-	}
-
-	netdev_err(sq->channel->netdev,
-		   "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n",
-		   sq->sqn, sq->cc, sq->pc);
-
-	return -ETIMEDOUT;
-}
-
-static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state)
-{
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	struct mlx5e_modify_sq_param msp = {0};
-	int err;
-
-	msp.curr_state = curr_state;
-	msp.next_state = MLX5_SQC_STATE_RST;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn);
-		return err;
-	}
-
-	memset(&msp, 0, sizeof(msp));
-	msp.curr_state = MLX5_SQC_STATE_RST;
-	msp.next_state = MLX5_SQC_STATE_RDY;
-
-	err = mlx5e_modify_sq(mdev, sq->sqn, &msp);
-	if (err) {
-		netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn);
-		return err;
-	}
-
-	return 0;
-}
-
-static void mlx5e_sq_recover(struct work_struct *work)
-{
-	struct mlx5e_txqsq_recover *recover =
-		container_of(work, struct mlx5e_txqsq_recover,
-			     recover_work);
-	struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq,
-					      recover);
-	struct mlx5_core_dev *mdev = sq->channel->mdev;
-	struct net_device *dev = sq->channel->netdev;
-	u8 state;
-	int err;
-
-	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
-	if (err) {
-		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
-			   sq->sqn, err);
-		return;
-	}
-
-	if (state != MLX5_RQC_STATE_ERR) {
-		netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn);
-		return;
-	}
-
-	netif_tx_disable_queue(sq->txq);
-
-	if (mlx5e_wait_for_sq_flush(sq))
-		return;
-
-	/* If the interval between two consecutive recovers per SQ is too
-	 * short, don't recover to avoid infinite loop of ERR_CQE -> recover.
-	 * If we reached this state, there is probably a bug that needs to be
-	 * fixed. let's keep the queue close and let tx timeout cleanup.
-	 */
-	if (jiffies_to_msecs(jiffies - recover->last_recover) <
-	    MLX5E_SQ_RECOVER_MIN_INTERVAL) {
-		netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n",
-			   sq->sqn);
-		return;
-	}
-
-	/* At this point, no new packets will arrive from the stack as TXQ is
-	 * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all
-	 * pending WQEs.  SQ can safely reset the SQ.
-	 */
-	if (mlx5e_sq_to_ready(sq, state))
-		return;
-
-	mlx5e_reset_txqsq_cc_pc(sq);
-	sq->stats->recover++;
-	recover->last_recover = jiffies;
-	mlx5e_activate_txqsq(sq);
+	mlx5e_tx_reporter_err_cqe(sq);
 }
 
 static int mlx5e_open_icosq(struct mlx5e_channel *c,
@@ -1558,11 +1483,8 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			    struct mlx5e_xdpsq *sq,
 			    bool is_redirect)
 {
-	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 	struct mlx5e_create_sq_param csp = {};
-	unsigned int inline_hdr_sz = 0;
 	int err;
-	int i;
 
 	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
 	if (err)
@@ -1573,30 +1495,40 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
-	if (is_redirect)
-		set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
 		goto err_free_xdpsq;
 
-	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-		ds_cnt++;
-	}
+	mlx5e_set_xmit_fp(sq, param->is_mpw);
+
+	if (!param->is_mpw) {
+		unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
+		unsigned int inline_hdr_sz = 0;
+		int i;
+
+		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
+			ds_cnt++;
+		}
 
-	/* Pre initialize fixed WQE fields */
-	for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-		struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-		struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-		struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-		struct mlx5_wqe_data_seg *dseg;
+		/* Pre initialize fixed WQE fields */
+		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
+			struct mlx5e_xdp_wqe_info *wi  = &sq->db.wqe_info[i];
+			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
+			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+			struct mlx5_wqe_data_seg *dseg;
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
-		dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
-		dseg->lkey = sq->mkey_be;
+			dseg = (struct mlx5_wqe_data_seg *)cseg + (ds_cnt - 1);
+			dseg->lkey = sq->mkey_be;
+
+			wi->num_wqebbs = 1;
+			wi->num_ds     = 1;
+		}
 	}
 
 	return 0;
@@ -1608,7 +1540,7 @@ err_free_xdpsq:
 	return err;
 }
 
-static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
+static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq)
 {
 	struct mlx5e_channel *c = sq->channel;
 
@@ -1616,7 +1548,7 @@ static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq)
 	napi_synchronize(&c->napi);
 
 	mlx5e_destroy_sq(c->mdev, sq->sqn);
-	mlx5e_free_xdpsq_descs(sq);
+	mlx5e_free_xdpsq_descs(sq, rq);
 	mlx5e_free_xdpsq(sq);
 }
 
@@ -1769,11 +1701,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
-}
-
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1919,14 +1846,37 @@ static int mlx5e_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 	return err;
 }
 
+static int mlx5e_alloc_xps_cpumask(struct mlx5e_channel *c,
+				   struct mlx5e_params *params)
+{
+	int num_comp_vectors = mlx5_comp_vectors_count(c->mdev);
+	int irq;
+
+	if (!zalloc_cpumask_var(&c->xps_cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	for (irq = c->ix; irq < num_comp_vectors; irq += params->num_channels) {
+		int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(c->mdev, irq));
+
+		cpumask_set_cpu(cpu, c->xps_cpumask);
+	}
+
+	return 0;
+}
+
+static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c)
+{
+	free_cpumask_var(c->xps_cpumask);
+}
+
 static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 			      struct mlx5e_params *params,
 			      struct mlx5e_channel_param *cparam,
 			      struct mlx5e_channel **cp)
 {
+	int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix));
 	struct net_dim_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	unsigned int irq;
 	int err;
@@ -1951,9 +1901,12 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->num_tc   = params->num_tc;
 	c->xdp      = !!params->xdp_prog;
 	c->stats    = &priv->channel_stats[ix].ch;
-
 	c->irq_desc = irq_to_desc(irq);
 
+	err = mlx5e_alloc_xps_cpumask(c, params);
+	if (err)
+		goto err_free_channel;
+
 	netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64);
 
 	err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq);
@@ -2009,7 +1962,7 @@ err_close_rq:
 
 err_close_xdp_sq:
 	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
 
 err_close_sqs:
 	mlx5e_close_sqs(c);
@@ -2036,6 +1989,9 @@ err_close_icosq_cq:
 
 err_napi_del:
 	netif_napi_del(&c->napi);
+	mlx5e_free_xps_cpumask(c);
+
+err_free_channel:
 	kvfree(c);
 
 	return err;
@@ -2048,7 +2004,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+	netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -2062,10 +2018,10 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
-	mlx5e_close_xdpsq(&c->xdpsq);
+	mlx5e_close_xdpsq(&c->xdpsq, NULL);
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
-		mlx5e_close_xdpsq(&c->rq.xdpsq);
+		mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq);
 	mlx5e_close_sqs(c);
 	mlx5e_close_icosq(&c->icosq);
 	napi_disable(&c->napi);
@@ -2076,6 +2032,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	mlx5e_close_tx_cqs(c);
 	mlx5e_close_cq(&c->icosq.cq);
 	netif_napi_del(&c->napi);
+	mlx5e_free_xps_cpumask(c);
 
 	kvfree(c);
 }
@@ -2232,6 +2189,8 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv,
 	void *cqc = param->cqc;
 
 	MLX5_SET(cqc, cqc, uar_page, priv->mdev->priv.uar->index);
+	if (MLX5_CAP_GEN(priv->mdev, cqe_128_always) && cache_line_size() >= 128)
+		MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD);
 }
 
 static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv,
@@ -2308,6 +2267,7 @@ static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv,
 
 	mlx5e_build_sq_param_common(priv, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
+	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
 }
 
 static void mlx5e_build_channel_param(struct mlx5e_priv *priv,
@@ -2346,6 +2306,10 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
+	if (!IS_ERR_OR_NULL(priv->tx_reporter))
+		devlink_health_reporter_state_update(priv->tx_reporter,
+						     DEVLINK_HEALTH_REPORTER_STATE_HEALTHY);
+
 	kvfree(cparam);
 	return 0;
 
@@ -2510,7 +2474,7 @@ static void mlx5e_fill_rqt_rqns(struct mlx5e_priv *priv, int sz,
 			if (rrp.rss.hfunc == ETH_RSS_HASH_XOR)
 				ix = mlx5e_bits_invert(i, ilog2(sz));
 
-			ix = priv->channels.params.indirection_rqt[ix];
+			ix = priv->rss_params.indirection_rqt[ix];
 			rqn = rrp.rss.channels->c[ix]->rq.rqn;
 		} else {
 			rqn = rrp.rqn;
@@ -2593,7 +2557,7 @@ static void mlx5e_redirect_rqts_to_channels(struct mlx5e_priv *priv,
 		{
 			.rss = {
 				.channels  = chs,
-				.hfunc     = chs->params.rss_hfunc,
+				.hfunc     = priv->rss_params.hfunc,
 			}
 		},
 	};
@@ -2613,6 +2577,54 @@ static void mlx5e_redirect_rqts_to_drop(struct mlx5e_priv *priv)
 	mlx5e_redirect_rqts(priv, drop_rrp);
 }
 
+static const struct mlx5e_tirc_config tirc_default_config[MLX5E_NUM_INDIR_TIRS] = {
+	[MLX5E_TT_IPV4_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV6_TCP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV4_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV6_UDP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = MLX5_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = MLX5_HASH_IP_L4PORTS,
+	},
+	[MLX5E_TT_IPV4_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				     .l4_prot_type = 0,
+				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV6_IPSEC_AH] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				     .l4_prot_type = 0,
+				     .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV4_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+				      .l4_prot_type = 0,
+				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV6_IPSEC_ESP] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+				      .l4_prot_type = 0,
+				      .rx_hash_fields = MLX5_HASH_IP_IPSEC_SPI,
+	},
+	[MLX5E_TT_IPV4] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV4,
+			    .l4_prot_type = 0,
+			    .rx_hash_fields = MLX5_HASH_IP,
+	},
+	[MLX5E_TT_IPV6] = { .l3_prot_type = MLX5_L3_PROT_TYPE_IPV6,
+			    .l4_prot_type = 0,
+			    .rx_hash_fields = MLX5_HASH_IP,
+	},
+};
+
+struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt)
+{
+	return tirc_default_config[tt];
+}
+
 static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 {
 	if (!params->lro_en)
@@ -2628,116 +2640,68 @@ static void mlx5e_build_tir_ctx_lro(struct mlx5e_params *params, void *tirc)
 	MLX5_SET(tirc, tirc, lro_timeout_period_usecs, params->lro_timeout);
 }
 
-void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_params *params,
-				    enum mlx5e_traffic_types tt,
+void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params,
+				    const struct mlx5e_tirc_config *ttconfig,
 				    void *tirc, bool inner)
 {
 	void *hfso = inner ? MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner) :
 			     MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_outer);
 
-#define MLX5_HASH_IP            (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP)
-
-#define MLX5_HASH_IP_L4PORTS    (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_L4_SPORT |\
-				 MLX5_HASH_FIELD_SEL_L4_DPORT)
-
-#define MLX5_HASH_IP_IPSEC_SPI  (MLX5_HASH_FIELD_SEL_SRC_IP   |\
-				 MLX5_HASH_FIELD_SEL_DST_IP   |\
-				 MLX5_HASH_FIELD_SEL_IPSEC_SPI)
-
-	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(params->rss_hfunc));
-	if (params->rss_hfunc == ETH_RSS_HASH_TOP) {
+	MLX5_SET(tirc, tirc, rx_hash_fn, mlx5e_rx_hash_fn(rss_params->hfunc));
+	if (rss_params->hfunc == ETH_RSS_HASH_TOP) {
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc,
 					     rx_hash_toeplitz_key);
 		size_t len = MLX5_FLD_SZ_BYTES(tirc,
 					       rx_hash_toeplitz_key);
 
 		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
-		memcpy(rss_key, params->toeplitz_hash_key, len);
+		memcpy(rss_key, rss_params->toeplitz_hash_key, len);
 	}
+	MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
+		 ttconfig->l3_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
+		 ttconfig->l4_prot_type);
+	MLX5_SET(rx_hash_field_select, hfso, selected_fields,
+		 ttconfig->rx_hash_fields);
+}
 
-	switch (tt) {
-	case MLX5E_TT_IPV4_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_TCP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_TCP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV6_UDP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, l4_prot_type,
-			 MLX5_L4_PROT_TYPE_UDP);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_L4PORTS);
-		break;
-
-	case MLX5E_TT_IPV4_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
+static void mlx5e_update_rx_hash_fields(struct mlx5e_tirc_config *ttconfig,
+					enum mlx5e_traffic_types tt,
+					u32 rx_hash_fields)
+{
+	*ttconfig                = tirc_default_config[tt];
+	ttconfig->rx_hash_fields = rx_hash_fields;
+}
 
-	case MLX5E_TT_IPV6_IPSEC_AH:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
+void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen)
+{
+	void *tirc = MLX5_ADDR_OF(modify_tir_in, in, ctx);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	int ctxlen = MLX5_ST_SZ_BYTES(tirc);
+	struct mlx5e_tirc_config ttconfig;
+	int tt;
 
-	case MLX5E_TT_IPV4_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
+	MLX5_SET(modify_tir_in, in, bitmask.hash, 1);
 
-	case MLX5E_TT_IPV6_IPSEC_ESP:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP_IPSEC_SPI);
-		break;
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_update_rx_hash_fields(&ttconfig, tt,
+					    rss->rx_hash_fields[tt]);
+		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, false);
+		mlx5_core_modify_tir(mdev, priv->indir_tir[tt].tirn, in, inlen);
+	}
 
-	case MLX5E_TT_IPV4:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV4);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
+	if (!mlx5e_tunnel_inner_ft_supported(priv->mdev))
+		return;
 
-	case MLX5E_TT_IPV6:
-		MLX5_SET(rx_hash_field_select, hfso, l3_prot_type,
-			 MLX5_L3_PROT_TYPE_IPV6);
-		MLX5_SET(rx_hash_field_select, hfso, selected_fields,
-			 MLX5_HASH_IP);
-		break;
-	default:
-		WARN_ONCE(true, "%s: bad traffic type!\n", __func__);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		memset(tirc, 0, ctxlen);
+		mlx5e_update_rx_hash_fields(&ttconfig, tt,
+					    rss->rx_hash_fields[tt]);
+		mlx5e_build_indir_tir_ctx_hash(rss, &ttconfig, tirc, true);
+		mlx5_core_modify_tir(mdev, priv->inner_indir_tir[tt].tirn, in,
+				     inlen);
 	}
 }
 
@@ -2794,7 +2758,8 @@ static void mlx5e_build_inner_indir_tir_ctx(struct mlx5e_priv *priv,
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
 	MLX5_SET(tirc, tirc, tunneled_offload_en, 0x1);
 
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, true);
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
+				       &tirc_default_config[tt], tirc, true);
 }
 
 static int mlx5e_set_mtu(struct mlx5_core_dev *mdev,
@@ -2825,7 +2790,7 @@ static void mlx5e_query_mtu(struct mlx5_core_dev *mdev,
 	*mtu = MLX5E_HW2SW_MTU(params, hw_mtu);
 }
 
-static int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
+int mlx5e_set_dev_port_mtu(struct mlx5e_priv *priv)
 {
 	struct mlx5e_params *params = &priv->channels.params;
 	struct net_device *netdev = priv->netdev;
@@ -2903,9 +2868,10 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv)
 
 	mlx5e_build_tx2sq_maps(priv);
 	mlx5e_activate_channels(&priv->channels);
+	mlx5e_xdp_tx_enable(priv);
 	netif_tx_start_all_queues(priv->netdev);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (mlx5e_is_vport_rep(priv))
 		mlx5e_add_sqs_fwd_rules(priv);
 
 	mlx5e_wait_channels_min_rx_wqes(&priv->channels);
@@ -2916,7 +2882,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 {
 	mlx5e_redirect_rqts_to_drop(priv);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (mlx5e_is_vport_rep(priv))
 		mlx5e_remove_sqs_fwd_rules(priv);
 
 	/* FIXME: This is a W/A only for tx timeout watch dog false alarm when
@@ -2924,16 +2890,18 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv)
 	 */
 	netif_tx_stop_all_queues(priv->netdev);
 	netif_tx_disable(priv->netdev);
+	mlx5e_xdp_tx_disable(priv);
 	mlx5e_deactivate_channels(&priv->channels);
 }
 
-void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
-				struct mlx5e_channels *new_chs,
-				mlx5e_fp_hw_modify hw_modify)
+static void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
+				       struct mlx5e_channels *new_chs,
+				       mlx5e_fp_hw_modify hw_modify)
 {
 	struct net_device *netdev = priv->netdev;
 	int new_num_txqs;
 	int carrier_ok;
+
 	new_num_txqs = new_chs->num * new_chs->params.num_tc;
 
 	carrier_ok = netif_carrier_ok(netdev);
@@ -2959,6 +2927,28 @@ void mlx5e_switch_priv_channels(struct mlx5e_priv *priv,
 		netif_carrier_on(netdev);
 }
 
+int mlx5e_safe_switch_channels(struct mlx5e_priv *priv,
+			       struct mlx5e_channels *new_chs,
+			       mlx5e_fp_hw_modify hw_modify)
+{
+	int err;
+
+	err = mlx5e_open_channels(priv, new_chs);
+	if (err)
+		return err;
+
+	mlx5e_switch_priv_channels(priv, new_chs, hw_modify);
+	return 0;
+}
+
+int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv)
+{
+	struct mlx5e_channels new_channels = {};
+
+	new_channels.params = priv->channels.params;
+	return mlx5e_safe_switch_channels(priv, &new_channels, NULL);
+}
+
 void mlx5e_timestamp_init(struct mlx5e_priv *priv)
 {
 	priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
@@ -3168,10 +3158,11 @@ err_close_tises:
 	return err;
 }
 
-void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
+static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv)
 {
 	int tc;
 
+	mlx5e_tx_reporter_destroy(priv);
 	for (tc = 0; tc < priv->profile->max_tc; tc++)
 		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 }
@@ -3186,7 +3177,9 @@ static void mlx5e_build_indir_tir_ctx(struct mlx5e_priv *priv,
 
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 	MLX5_SET(tirc, tirc, indirect_table, priv->indir_rqt.rqtn);
-	mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
+
+	mlx5e_build_indir_tir_ctx_hash(&priv->rss_params,
+				       &tirc_default_config[tt], tirc, false);
 }
 
 static void mlx5e_build_direct_tir_ctx(struct mlx5e_priv *priv, u32 rqtn, u32 *tirc)
@@ -3372,13 +3365,12 @@ static int mlx5e_setup_tc_mqprio(struct net_device *netdev,
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 	if (err)
 		goto out;
 
 	priv->max_opened_tc = max_t(u8, priv->max_opened_tc,
 				    new_channels.params.num_tc);
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3391,11 +3383,14 @@ static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower, flags);
+		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
+					      flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower, flags);
+		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
+					   flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower, flags);
+		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
+					  flags);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3408,7 +3403,8 @@ static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
+		return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS |
+						 MLX5E_TC_NIC_OFFLOAD);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -3451,16 +3447,39 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	}
 }
 
-static void
+void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s)
+{
+	int i;
+
+	for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) {
+		struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i];
+		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
+		int j;
+
+		s->rx_packets   += rq_stats->packets;
+		s->rx_bytes     += rq_stats->bytes;
+
+		for (j = 0; j < priv->max_opened_tc; j++) {
+			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
+
+			s->tx_packets    += sq_stats->packets;
+			s->tx_bytes      += sq_stats->bytes;
+			s->tx_dropped    += sq_stats->dropped;
+		}
+	}
+}
+
+void
 mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sw_stats *sstats = &priv->stats.sw;
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
-	/* update HW stats in background for next time */
-	mlx5e_queue_update_stats(priv);
+	if (!mlx5e_monitor_counter_supported(priv)) {
+		/* update HW stats in background for next time */
+		mlx5e_queue_update_stats(priv);
+	}
 
 	if (mlx5e_is_uplink_rep(priv)) {
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
@@ -3468,12 +3487,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
 		stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
 	} else {
-		mlx5e_grp_sw_update_stats(priv);
-		stats->rx_packets = sstats->rx_packets;
-		stats->rx_bytes   = sstats->rx_bytes;
-		stats->tx_packets = sstats->tx_packets;
-		stats->tx_bytes   = sstats->tx_bytes;
-		stats->tx_dropped = sstats->tx_queue_dropped;
+		mlx5e_fold_sw_stats64(priv, stats);
 	}
 
 	stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;
@@ -3566,11 +3580,7 @@ static int set_feature_lro(struct net_device *netdev, bool enable)
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
-	if (err)
-		goto out;
-
-	mlx5e_switch_priv_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_modify_tirs_lro);
 out:
 	mutex_unlock(&priv->state_lock);
 	return err;
@@ -3593,7 +3603,7 @@ static int set_feature_tc_num_filters(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	if (!enable && mlx5e_tc_num_filters(priv)) {
+	if (!enable && mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD)) {
 		netdev_err(netdev,
 			   "Active offloaded tc filters, can't turn hw_tc_offload off\n");
 		return -EINVAL;
@@ -3767,7 +3777,7 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	if (params->xdp_prog &&
 	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
-			   new_mtu, MLX5E_XDP_MAX_MTU);
+			   new_mtu, mlx5e_xdp_max_mtu(params));
 		err = -EINVAL;
 		goto out;
 	}
@@ -3788,11 +3798,10 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 		goto out;
 	}
 
-	err = mlx5e_open_channels(priv, &new_channels);
+	err = mlx5e_safe_switch_channels(priv, &new_channels, set_mtu_cb);
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, set_mtu_cb);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
@@ -3895,7 +3904,7 @@ static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 }
 
 #ifdef CONFIG_MLX5_ESWITCH
-static int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
+int mlx5e_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3932,8 +3941,8 @@ static int mlx5e_set_vf_trust(struct net_device *dev, int vf, bool setting)
 	return mlx5_eswitch_set_vport_trust(mdev->priv.eswitch, vf + 1, setting);
 }
 
-static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
-			     int max_tx_rate)
+int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
+		      int max_tx_rate)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3974,8 +3983,8 @@ static int mlx5e_set_vf_link_state(struct net_device *dev, int vf,
 					    mlx5_ifla_link2vport(link_state));
 }
 
-static int mlx5e_get_vf_config(struct net_device *dev,
-			       int vf, struct ifla_vf_info *ivi)
+int mlx5e_get_vf_config(struct net_device *dev,
+			int vf, struct ifla_vf_info *ivi)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -3988,8 +3997,8 @@ static int mlx5e_get_vf_config(struct net_device *dev,
 	return 0;
 }
 
-static int mlx5e_get_vf_stats(struct net_device *dev,
-			      int vf, struct ifla_vf_stats *vf_stats)
+int mlx5e_get_vf_stats(struct net_device *dev,
+		       int vf, struct ifla_vf_stats *vf_stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -4050,8 +4059,7 @@ static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
 	queue_work(priv->wq, &vxlan_work->work);
 }
 
-static void mlx5e_add_vxlan_port(struct net_device *netdev,
-				 struct udp_tunnel_info *ti)
+void mlx5e_add_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -4064,8 +4072,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
 }
 
-static void mlx5e_del_vxlan_port(struct net_device *netdev,
-				 struct udp_tunnel_info *ti)
+void mlx5e_del_vxlan_port(struct net_device *netdev, struct udp_tunnel_info *ti)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -4115,9 +4122,9 @@ out:
 	return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 }
 
-static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
-					      struct net_device *netdev,
-					      netdev_features_t features)
+netdev_features_t mlx5e_features_check(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       netdev_features_t features)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
@@ -4137,31 +4144,13 @@ static netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	return features;
 }
 
-static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev,
-					struct mlx5e_txqsq *sq)
-{
-	struct mlx5_eq *eq = sq->cq.mcq.eq;
-	u32 eqe_count;
-
-	netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n",
-		   eq->eqn, eq->cons_index, eq->irqn);
-
-	eqe_count = mlx5_eq_poll_irq_disabled(eq);
-	if (!eqe_count)
-		return false;
-
-	netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->eqn);
-	sq->channel->stats->eq_rearm++;
-	return true;
-}
-
 static void mlx5e_tx_timeout_work(struct work_struct *work)
 {
 	struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv,
 					       tx_timeout_work);
-	struct net_device *dev = priv->netdev;
-	bool reopen_channels = false;
-	int i, err;
+	bool report_failed = false;
+	int err;
+	int i;
 
 	rtnl_lock();
 	mutex_lock(&priv->state_lock);
@@ -4170,34 +4159,24 @@ static void mlx5e_tx_timeout_work(struct work_struct *work)
 		goto unlock;
 
 	for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) {
-		struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i);
+		struct netdev_queue *dev_queue =
+			netdev_get_tx_queue(priv->netdev, i);
 		struct mlx5e_txqsq *sq = priv->txq2sq[i];
 
 		if (!netif_xmit_stopped(dev_queue))
 			continue;
 
-		netdev_err(dev,
-			   "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n",
-			   i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc,
-			   jiffies_to_usecs(jiffies - dev_queue->trans_start));
-
-		/* If we recover a lost interrupt, most likely TX timeout will
-		 * be resolved, skip reopening channels
-		 */
-		if (!mlx5e_tx_timeout_eq_recover(dev, sq)) {
-			clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
-			reopen_channels = true;
-		}
+		if (mlx5e_tx_reporter_timeout(sq))
+			report_failed = true;
 	}
 
-	if (!reopen_channels)
+	if (!report_failed)
 		goto unlock;
 
-	mlx5e_close_locked(dev);
-	err = mlx5e_open_locked(dev);
+	err = mlx5e_safe_reopen_channels(priv);
 	if (err)
 		netdev_err(priv->netdev,
-			   "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n",
+			   "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
 			   err);
 
 unlock:
@@ -4233,7 +4212,8 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 
 	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
 		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
-			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+			    new_channels.params.sw_mtu,
+			    mlx5e_xdp_max_mtu(&new_channels.params));
 		return -EINVAL;
 	}
 
@@ -4342,6 +4322,61 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+#ifdef CONFIG_MLX5_ESWITCH
+static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
+				struct net_device *dev, u32 filter_mask,
+				int nlflags)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u8 mode, setting;
+	int err;
+
+	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
+	if (err)
+		return err;
+	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
+	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
+				       mode,
+				       0, 0, nlflags, filter_mask, NULL);
+}
+
+static int mlx5e_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
+				u16 flags, struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct nlattr *attr, *br_spec;
+	u16 mode = BRIDGE_MODE_UNDEF;
+	u8 setting;
+	int rem;
+
+	br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+	if (!br_spec)
+		return -EINVAL;
+
+	nla_for_each_nested(attr, br_spec, rem) {
+		if (nla_type(attr) != IFLA_BRIDGE_MODE)
+			continue;
+
+		if (nla_len(attr) < sizeof(mode))
+			return -EINVAL;
+
+		mode = nla_get_u16(attr);
+		if (mode > BRIDGE_MODE_VEPA)
+			return -EINVAL;
+
+		break;
+	}
+
+	if (mode == BRIDGE_MODE_UNDEF)
+		return -EINVAL;
+
+	setting = (mode == BRIDGE_MODE_VEPA) ?  1 : 0;
+	return mlx5_eswitch_set_vepa(mdev->priv.eswitch, setting);
+}
+#endif
+
 const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_open                = mlx5e_open,
 	.ndo_stop                = mlx5e_close,
@@ -4368,6 +4403,9 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
 #endif
 #ifdef CONFIG_MLX5_ESWITCH
+	.ndo_bridge_setlink      = mlx5e_bridge_setlink,
+	.ndo_bridge_getlink      = mlx5e_bridge_getlink,
+
 	/* SRIOV E-Switch NDOs */
 	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
 	.ndo_set_vf_vlan         = mlx5e_set_vf_vlan,
@@ -4377,8 +4415,6 @@ const struct net_device_ops mlx5e_netdev_ops = {
 	.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_has_offload_stats	 = mlx5e_has_offload_stats,
-	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
 #endif
 };
 
@@ -4524,15 +4560,23 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev,
 	mlx5e_init_rq_type_params(mdev, params);
 }
 
-void mlx5e_build_rss_params(struct mlx5e_params *params)
+void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params,
+			    u16 num_channels)
 {
-	params->rss_hfunc = ETH_RSS_HASH_XOR;
-	netdev_rss_key_fill(params->toeplitz_hash_key, sizeof(params->toeplitz_hash_key));
-	mlx5e_build_default_indir_rqt(params->indirection_rqt,
-				      MLX5E_INDIR_RQT_SIZE, params->num_channels);
+	enum mlx5e_traffic_types tt;
+
+	rss_params->hfunc = ETH_RSS_HASH_TOP;
+	netdev_rss_key_fill(rss_params->toeplitz_hash_key,
+			    sizeof(rss_params->toeplitz_hash_key));
+	mlx5e_build_default_indir_rqt(rss_params->indirection_rqt,
+				      MLX5E_INDIR_RQT_SIZE, num_channels);
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++)
+		rss_params->rx_hash_fields[tt] =
+			tirc_default_config[tt].rx_hash_fields;
 }
 
 void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
+			    struct mlx5e_rss_params *rss_params,
 			    struct mlx5e_params *params,
 			    u16 max_channels, u16 mtu)
 {
@@ -4548,6 +4592,10 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 		MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE :
 		MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
 
+	/* XDP SQ */
+	MLX5E_SET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE,
+			MLX5_CAP_ETH(mdev, enhanced_multi_pkt_send_wqe));
+
 	/* set CQE compression */
 	params->rx_cqe_compress_def = false;
 	if (MLX5_CAP_GEN(mdev, cqe_compression) &&
@@ -4581,7 +4629,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev,
 	params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev);
 
 	/* RSS */
-	mlx5e_build_rss_params(params);
+	mlx5e_build_rss_params(rss_params, params->num_channels);
 }
 
 static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
@@ -4596,12 +4644,6 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 	}
 }
 
-#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-static const struct switchdev_ops mlx5e_switchdev_ops = {
-	.switchdev_port_attr_get	= mlx5e_attr_get,
-};
-#endif
-
 static void mlx5e_build_nic_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -4711,12 +4753,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
-
-#if IS_ENABLED(CONFIG_MLX5_ESWITCH)
-	if (MLX5_ESWITCH_MANAGER(mdev))
-		netdev->switchdev_ops = &mlx5e_switchdev_ops;
-#endif
-
 	mlx5e_ipsec_build_netdev(priv);
 	mlx5e_tls_build_netdev(priv);
 }
@@ -4754,14 +4790,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 			  void *ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rss_params *rss = &priv->rss_params;
 	int err;
 
 	err = mlx5e_netdev_init(netdev, priv, mdev, profile, ppriv);
 	if (err)
 		return err;
 
-	mlx5e_build_nic_params(mdev, &priv->channels.params,
-			       mlx5e_get_netdev_max_channels(netdev), netdev->mtu);
+	mlx5e_build_nic_params(mdev, rss, &priv->channels.params,
+			       mlx5e_get_netdev_max_channels(netdev),
+			       netdev->mtu);
 
 	mlx5e_timestamp_init(priv);
 
@@ -4867,6 +4905,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_initialize(priv);
 #endif
+	mlx5e_tx_reporter_create(priv);
 	return 0;
 }
 
@@ -4891,9 +4930,8 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv)
 	mlx5_lag_add(mdev, netdev);
 
 	mlx5e_enable_async_events(priv);
-
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_register_vport_reps(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_init(priv);
 
 	if (netdev->reg_state != NETREG_REGISTERED)
 		return;
@@ -4927,8 +4965,8 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv)
 
 	queue_work(priv->wq, &priv->set_rx_mode_work);
 
-	if (MLX5_ESWITCH_MANAGER(priv->mdev))
-		mlx5e_unregister_vport_reps(priv);
+	if (mlx5e_monitor_counter_supported(priv))
+		mlx5e_monitor_counter_cleanup(priv);
 
 	mlx5e_disable_async_events(priv);
 	mlx5_lag_remove(mdev);
@@ -4981,7 +5019,7 @@ int mlx5e_netdev_init(struct net_device *netdev,
 	netif_carrier_off(netdev);
 
 #ifdef CONFIG_MLX5_EN_ARFS
-	netdev->rx_cpu_rmap = mdev->rmap;
+	netdev->rx_cpu_rmap =  mlx5_eq_table_get_rmap(mdev);
 #endif
 
 	return 0;
@@ -5036,7 +5074,7 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
 	if (priv->channels.params.num_channels > max_nch) {
 		mlx5_core_warn(priv->mdev, "MLX5E: Reducing number of channels to %d\n", max_nch);
 		priv->channels.params.num_channels = max_nch;
-		mlx5e_build_default_indir_rqt(priv->channels.params.indirection_rqt,
+		mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt,
 					      MLX5E_INDIR_RQT_SIZE, max_nch);
 	}
 
@@ -5125,7 +5163,6 @@ static void mlx5e_detach(struct mlx5_core_dev *mdev, void *vpriv)
 static void *mlx5e_add(struct mlx5_core_dev *mdev)
 {
 	struct net_device *netdev;
-	void *rpriv = NULL;
 	void *priv;
 	int err;
 	int nch;
@@ -5135,20 +5172,18 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		return NULL;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	if (MLX5_ESWITCH_MANAGER(mdev)) {
-		rpriv = mlx5e_alloc_nic_rep_priv(mdev);
-		if (!rpriv) {
-			mlx5_core_warn(mdev, "Failed to alloc NIC rep priv data\n");
-			return NULL;
-		}
+	if (MLX5_ESWITCH_MANAGER(mdev) &&
+	    mlx5_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+		mlx5e_rep_register_vport_reps(mdev);
+		return mdev;
 	}
 #endif
 
 	nch = mlx5e_get_max_num_channels(mdev);
-	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, rpriv);
+	netdev = mlx5e_create_netdev(mdev, &mlx5e_nic_profile, nch, NULL);
 	if (!netdev) {
 		mlx5_core_err(mdev, "mlx5e_create_netdev failed\n");
-		goto err_free_rpriv;
+		return NULL;
 	}
 
 	priv = netdev_priv(netdev);
@@ -5174,30 +5209,26 @@ err_detach:
 	mlx5e_detach(mdev, priv);
 err_destroy_netdev:
 	mlx5e_destroy_netdev(priv);
-err_free_rpriv:
-	kfree(rpriv);
 	return NULL;
 }
 
 static void mlx5e_remove(struct mlx5_core_dev *mdev, void *vpriv)
 {
-	struct mlx5e_priv *priv = vpriv;
-	void *ppriv = priv->ppriv;
+	struct mlx5e_priv *priv;
 
+#ifdef CONFIG_MLX5_ESWITCH
+	if (MLX5_ESWITCH_MANAGER(mdev) && vpriv == mdev) {
+		mlx5e_rep_unregister_vport_reps(mdev);
+		return;
+	}
+#endif
+	priv = vpriv;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 	mlx5e_dcbnl_delete_app(priv);
 #endif
 	unregister_netdev(priv->netdev);
 	mlx5e_detach(mdev, vpriv);
 	mlx5e_destroy_netdev(priv);
-	kfree(ppriv);
-}
-
-static void *mlx5e_get_netdev(void *vpriv)
-{
-	struct mlx5e_priv *priv = vpriv;
-
-	return priv->netdev;
 }
 
 static struct mlx5_interface mlx5e_interface = {
@@ -5205,9 +5236,7 @@ static struct mlx5_interface mlx5e_interface = {
 	.remove    = mlx5e_remove,
 	.attach    = mlx5e_attach,
 	.detach    = mlx5e_detach,
-	.event     = mlx5e_async_event,
 	.protocol  = MLX5_INTERFACE_PROTOCOL_ETH,
-	.get_dev   = mlx5e_get_netdev,
 };
 
 void mlx5e_init(void)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 820fe85100b0..a66b6ed80b30 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -42,14 +42,26 @@
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
+#include "en/tc_tun.h"
 #include "fs_core.h"
+#include "lib/port_tun.h"
 
-#define MLX5E_REP_PARAMS_LOG_SQ_SIZE \
-	max(0x6, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
+#define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
+        max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
 #define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
+struct mlx5e_rep_indr_block_priv {
+	struct net_device *netdev;
+	struct mlx5e_rep_priv *rpriv;
+
+	struct list_head list;
+};
+
+static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
+					    struct net_device *netdev);
+
 static void mlx5e_rep_get_drvinfo(struct net_device *dev,
 				  struct ethtool_drvinfo *drvinfo)
 {
@@ -99,7 +111,7 @@ static void mlx5e_rep_get_strings(struct net_device *dev,
 	}
 }
 
-static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
+static void mlx5e_vf_rep_update_hw_counters(struct mlx5e_priv *priv)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -122,29 +134,45 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
 	vport_stats->tx_bytes   = vf_stats.rx_bytes;
 }
 
-static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
+static void mlx5e_uplink_rep_update_hw_counters(struct mlx5e_priv *priv)
 {
-	struct mlx5e_sw_stats *s = &priv->stats.sw;
-	struct mlx5e_rq_stats *rq_stats;
-	struct mlx5e_sq_stats *sq_stats;
-	int i, j;
+	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
+	struct rtnl_link_stats64 *vport_stats;
 
-	memset(s, 0, sizeof(*s));
-	for (i = 0; i < priv->channels.num; i++) {
-		struct mlx5e_channel *c = priv->channels.c[i];
+	mlx5e_grp_802_3_update_stats(priv);
 
-		rq_stats = c->rq.stats;
+	vport_stats = &priv->stats.vf_vport;
 
-		s->rx_packets	+= rq_stats->packets;
-		s->rx_bytes	+= rq_stats->bytes;
+	vport_stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
+	vport_stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
+	vport_stats->tx_packets = PPORT_802_3_GET(pstats, a_frames_transmitted_ok);
+	vport_stats->tx_bytes   = PPORT_802_3_GET(pstats, a_octets_transmitted_ok);
+}
 
-		for (j = 0; j < priv->channels.params.num_tc; j++) {
-			sq_stats = c->sq[j].stats;
+static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 
-			s->tx_packets		+= sq_stats->packets;
-			s->tx_bytes		+= sq_stats->bytes;
-		}
-	}
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		mlx5e_uplink_rep_update_hw_counters(priv);
+	else
+		mlx5e_vf_rep_update_hw_counters(priv);
+}
+
+static void mlx5e_rep_update_sw_counters(struct mlx5e_priv *priv)
+{
+	struct mlx5e_sw_stats *s = &priv->stats.sw;
+	struct rtnl_link_stats64 stats64 = {};
+
+	memset(s, 0, sizeof(*s));
+	mlx5e_fold_sw_stats64(priv, &stats64);
+
+	s->rx_packets = stats64.rx_packets;
+	s->rx_bytes   = stats64.rx_bytes;
+	s->tx_packets = stats64.tx_packets;
+	s->tx_bytes   = stats64.tx_bytes;
+	s->tx_queue_dropped = stats64.tx_dropped;
 }
 
 static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
@@ -157,8 +185,7 @@ static void mlx5e_rep_get_ethtool_stats(struct net_device *dev,
 		return;
 
 	mutex_lock(&priv->state_lock);
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-		mlx5e_rep_update_sw_counters(priv);
+	mlx5e_rep_update_sw_counters(priv);
 	mlx5e_rep_update_hw_counters(priv);
 	mutex_unlock(&priv->state_lock);
 
@@ -257,6 +284,22 @@ static int mlx5e_rep_set_channels(struct net_device *dev,
 	return 0;
 }
 
+static int mlx5e_rep_get_coalesce(struct net_device *netdev,
+				  struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_get_coalesce(priv, coal);
+}
+
+static int mlx5e_rep_set_coalesce(struct net_device *netdev,
+				  struct ethtool_coalesce *coal)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_coalesce(priv, coal);
+}
+
 static u32 mlx5e_rep_get_rxfh_key_size(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -271,7 +314,39 @@ static u32 mlx5e_rep_get_rxfh_indir_size(struct net_device *netdev)
 	return mlx5e_ethtool_get_rxfh_indir_size(priv);
 }
 
-static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
+static void mlx5e_uplink_rep_get_pauseparam(struct net_device *netdev,
+					    struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	mlx5e_ethtool_get_pauseparam(priv, pauseparam);
+}
+
+static int mlx5e_uplink_rep_set_pauseparam(struct net_device *netdev,
+					   struct ethtool_pauseparam *pauseparam)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_pauseparam(priv, pauseparam);
+}
+
+static int mlx5e_uplink_rep_get_link_ksettings(struct net_device *netdev,
+					       struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_get_link_ksettings(priv, link_ksettings);
+}
+
+static int mlx5e_uplink_rep_set_link_ksettings(struct net_device *netdev,
+					       const struct ethtool_link_ksettings *link_ksettings)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+
+	return mlx5e_ethtool_set_link_ksettings(priv, link_ksettings);
+}
+
+static const struct ethtool_ops mlx5e_vf_rep_ethtool_ops = {
 	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
 	.get_link	   = ethtool_op_get_link,
 	.get_strings       = mlx5e_rep_get_strings,
@@ -281,27 +356,58 @@ static const struct ethtool_ops mlx5e_rep_ethtool_ops = {
 	.set_ringparam     = mlx5e_rep_set_ringparam,
 	.get_channels      = mlx5e_rep_get_channels,
 	.set_channels      = mlx5e_rep_set_channels,
+	.get_coalesce      = mlx5e_rep_get_coalesce,
+	.set_coalesce      = mlx5e_rep_set_coalesce,
 	.get_rxfh_key_size   = mlx5e_rep_get_rxfh_key_size,
 	.get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size,
 };
 
-int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = {
+	.get_drvinfo	   = mlx5e_rep_get_drvinfo,
+	.get_link	   = ethtool_op_get_link,
+	.get_strings       = mlx5e_rep_get_strings,
+	.get_sset_count    = mlx5e_rep_get_sset_count,
+	.get_ethtool_stats = mlx5e_rep_get_ethtool_stats,
+	.get_ringparam     = mlx5e_rep_get_ringparam,
+	.set_ringparam     = mlx5e_rep_set_ringparam,
+	.get_channels      = mlx5e_rep_get_channels,
+	.set_channels      = mlx5e_rep_set_channels,
+	.get_coalesce      = mlx5e_rep_get_coalesce,
+	.set_coalesce      = mlx5e_rep_set_coalesce,
+	.get_link_ksettings = mlx5e_uplink_rep_get_link_ksettings,
+	.set_link_ksettings = mlx5e_uplink_rep_set_link_ksettings,
+	.get_rxfh_key_size   = mlx5e_rep_get_rxfh_key_size,
+	.get_rxfh_indir_size = mlx5e_rep_get_rxfh_indir_size,
+	.get_pauseparam    = mlx5e_uplink_rep_get_pauseparam,
+	.set_pauseparam    = mlx5e_uplink_rep_set_pauseparam,
+};
+
+static int mlx5e_rep_get_port_parent_id(struct net_device *dev,
+					struct netdev_phys_item_id *ppid)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+	struct net_device *uplink_upper = NULL;
+	struct mlx5e_priv *uplink_priv = NULL;
+	struct net_device *uplink_dev;
 
 	if (esw->mode == SRIOV_NONE)
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = ETH_ALEN;
-		ether_addr_copy(attr->u.ppid.id, rep->hw_id);
-		break;
-	default:
-		return -EOPNOTSUPP;
+	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+	if (uplink_dev) {
+		uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+		uplink_priv = netdev_priv(uplink_dev);
+	}
+
+	ppid->id_len = ETH_ALEN;
+	if (uplink_upper && mlx5_lag_is_sriov(uplink_priv->mdev)) {
+		ether_addr_copy(ppid->id, uplink_upper->dev_addr);
+	} else {
+		struct mlx5e_rep_priv *rpriv = priv->ppriv;
+		struct mlx5_eswitch_rep *rep = rpriv->rep;
+
+		ether_addr_copy(ppid->id, rep->hw_id);
 	}
 
 	return 0;
@@ -474,6 +580,10 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv,
 	if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) {
 		ether_addr_copy(e->h_dest, ha);
 		ether_addr_copy(eth->h_dest, ha);
+		/* Update the encap source mac, in case that we delete
+		 * the flows when encap source mac changed.
+		 */
+		ether_addr_copy(eth->h_source, e->route_dev->dev_addr);
 
 		mlx5e_tc_encap_flows_add(priv, e);
 	}
@@ -519,6 +629,186 @@ static void mlx5e_rep_neigh_update(struct work_struct *work)
 	neigh_release(n);
 }
 
+static struct mlx5e_rep_indr_block_priv *
+mlx5e_rep_indr_block_priv_lookup(struct mlx5e_rep_priv *rpriv,
+				 struct net_device *netdev)
+{
+	struct mlx5e_rep_indr_block_priv *cb_priv;
+
+	/* All callback list access should be protected by RTNL. */
+	ASSERT_RTNL();
+
+	list_for_each_entry(cb_priv,
+			    &rpriv->uplink_priv.tc_indr_block_priv_list,
+			    list)
+		if (cb_priv->netdev == netdev)
+			return cb_priv;
+
+	return NULL;
+}
+
+static void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
+{
+	struct mlx5e_rep_indr_block_priv *cb_priv, *temp;
+	struct list_head *head = &rpriv->uplink_priv.tc_indr_block_priv_list;
+
+	list_for_each_entry_safe(cb_priv, temp, head, list) {
+		mlx5e_rep_indr_unregister_block(rpriv, cb_priv->netdev);
+		kfree(cb_priv);
+	}
+}
+
+static int
+mlx5e_rep_indr_offload(struct net_device *netdev,
+		       struct tc_cls_flower_offload *flower,
+		       struct mlx5e_rep_indr_block_priv *indr_priv)
+{
+	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
+	int flags = MLX5E_TC_EGRESS | MLX5E_TC_ESW_OFFLOAD;
+	int err = 0;
+
+	switch (flower->command) {
+	case TC_CLSFLOWER_REPLACE:
+		err = mlx5e_configure_flower(netdev, priv, flower, flags);
+		break;
+	case TC_CLSFLOWER_DESTROY:
+		err = mlx5e_delete_flower(netdev, priv, flower, flags);
+		break;
+	case TC_CLSFLOWER_STATS:
+		err = mlx5e_stats_flower(netdev, priv, flower, flags);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int mlx5e_rep_indr_setup_block_cb(enum tc_setup_type type,
+					 void *type_data, void *indr_priv)
+{
+	struct mlx5e_rep_indr_block_priv *priv = indr_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return mlx5e_rep_indr_offload(priv->netdev, type_data, priv);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
+			      struct mlx5e_rep_priv *rpriv,
+			      struct tc_block_offload *f)
+{
+	struct mlx5e_rep_indr_block_priv *indr_priv;
+	int err = 0;
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		if (indr_priv)
+			return -EEXIST;
+
+		indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL);
+		if (!indr_priv)
+			return -ENOMEM;
+
+		indr_priv->netdev = netdev;
+		indr_priv->rpriv = rpriv;
+		list_add(&indr_priv->list,
+			 &rpriv->uplink_priv.tc_indr_block_priv_list);
+
+		err = tcf_block_cb_register(f->block,
+					    mlx5e_rep_indr_setup_block_cb,
+					    indr_priv, indr_priv, f->extack);
+		if (err) {
+			list_del(&indr_priv->list);
+			kfree(indr_priv);
+		}
+
+		return err;
+	case TC_BLOCK_UNBIND:
+		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
+		if (!indr_priv)
+			return -ENOENT;
+
+		tcf_block_cb_unregister(f->block,
+					mlx5e_rep_indr_setup_block_cb,
+					indr_priv);
+		list_del(&indr_priv->list);
+		kfree(indr_priv);
+
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static
+int mlx5e_rep_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+			       enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return mlx5e_rep_indr_setup_tc_block(netdev, cb_priv,
+						      type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
+					 struct net_device *netdev)
+{
+	int err;
+
+	err = __tc_indr_block_cb_register(netdev, rpriv,
+					  mlx5e_rep_indr_setup_tc_cb,
+					  rpriv);
+	if (err) {
+		struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+
+		mlx5_core_err(priv->mdev, "Failed to register remote block notifier for %s err=%d\n",
+			      netdev_name(netdev), err);
+	}
+	return err;
+}
+
+static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
+					    struct net_device *netdev)
+{
+	__tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb,
+				      rpriv);
+}
+
+static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
+					 unsigned long event, void *ptr)
+{
+	struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
+						     uplink_priv.netdevice_nb);
+	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	if (!mlx5e_tc_tun_device_to_offload(priv, netdev))
+		return NOTIFY_OK;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		mlx5e_rep_indr_register_block(rpriv, netdev);
+		break;
+	case NETDEV_UNREGISTER:
+		mlx5e_rep_indr_unregister_block(rpriv, netdev);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
 static struct mlx5e_neigh_hash_entry *
 mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv,
 			     struct mlx5e_neigh *m_neigh);
@@ -755,14 +1045,23 @@ static void mlx5e_rep_neigh_entry_destroy(struct mlx5e_priv *priv,
 int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
 				 struct mlx5e_encap_entry *e)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
 	struct mlx5e_neigh_hash_entry *nhe;
 	int err;
 
+	err = mlx5_tun_entropy_refcount_inc(tun_entropy, e->reformat_type);
+	if (err)
+		return err;
 	nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh);
 	if (!nhe) {
 		err = mlx5e_rep_neigh_entry_create(priv, e, &nhe);
-		if (err)
+		if (err) {
+			mlx5_tun_entropy_refcount_dec(tun_entropy,
+						      e->reformat_type);
 			return err;
+		}
 	}
 	list_add(&e->encap_list, &nhe->encap_list);
 	return 0;
@@ -771,6 +1070,9 @@ int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
 void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 				  struct mlx5e_encap_entry *e)
 {
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv;
+	struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy;
 	struct mlx5e_neigh_hash_entry *nhe;
 
 	list_del(&e->encap_list);
@@ -778,9 +1080,10 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 
 	if (list_empty(&nhe->encap_list))
 		mlx5e_rep_neigh_entry_destroy(priv, nhe);
+	mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type);
 }
 
-static int mlx5e_rep_open(struct net_device *dev)
+static int mlx5e_vf_rep_open(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -794,7 +1097,8 @@ static int mlx5e_rep_open(struct net_device *dev)
 
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
 					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					   rep->vport, MLX5_VPORT_ADMIN_STATE_UP))
+					   rep->vport, 1,
+					   MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -802,7 +1106,7 @@ unlock:
 	return err;
 }
 
-static int mlx5e_rep_close(struct net_device *dev)
+static int mlx5e_vf_rep_close(struct net_device *dev)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
@@ -812,7 +1116,8 @@ static int mlx5e_rep_close(struct net_device *dev)
 	mutex_lock(&priv->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-				      rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN);
+				      rep->vport, 1,
+				      MLX5_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
@@ -824,9 +1129,18 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	unsigned int fn;
 	int ret;
 
-	ret = snprintf(buf, len, "%d", rep->vport - 1);
+	fn = PCI_FUNC(priv->mdev->pdev->devfn);
+	if (fn >= MLX5_MAX_PORTS)
+		return -EOPNOTSUPP;
+
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		ret = snprintf(buf, len, "p%d", fn);
+	else
+		ret = snprintf(buf, len, "pf%dvf%d", fn, rep->vport - 1);
+
 	if (ret >= len)
 		return -EOPNOTSUPP;
 
@@ -839,24 +1153,14 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
 {
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return mlx5e_configure_flower(priv, cls_flower, flags);
+		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
+					      flags);
 	case TC_CLSFLOWER_DESTROY:
-		return mlx5e_delete_flower(priv, cls_flower, flags);
+		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
+					   flags);
 	case TC_CLSFLOWER_STATS:
-		return mlx5e_stats_flower(priv, cls_flower, flags);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int mlx5e_rep_setup_tc_cb_egdev(enum tc_setup_type type, void *type_data,
-				       void *cb_priv)
-{
-	struct mlx5e_priv *priv = cb_priv;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_EGRESS);
+		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
+					  flags);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -869,7 +1173,8 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
-		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS);
+		return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS |
+						     MLX5E_TC_ESW_OFFLOAD);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -908,43 +1213,23 @@ static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv)
 {
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	struct mlx5_eswitch_rep *rep;
 
 	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
 		return false;
 
-	rep = rpriv->rep;
-	if (esw->mode == SRIOV_OFFLOADS &&
-	    rep && rep->vport == FDB_UPLINK_VPORT)
-		return true;
-
-	return false;
-}
-
-static bool mlx5e_is_vf_vport_rep(struct mlx5e_priv *priv)
-{
-	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct mlx5_eswitch_rep *rep;
-
-	if (!MLX5_ESWITCH_MANAGER(priv->mdev))
+	if (!rpriv) /* non vport rep mlx5e instances don't use this field */
 		return false;
 
 	rep = rpriv->rep;
-	if (rep && rep->vport != FDB_UPLINK_VPORT)
-		return true;
-
-	return false;
+	return (rep->vport == MLX5_VPORT_UPLINK);
 }
 
-bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id)
+static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id)
 {
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
 	switch (attr_id) {
 	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
-		if (mlx5e_is_vf_vport_rep(priv) || mlx5e_is_uplink_rep(priv))
 			return true;
 	}
 
@@ -956,22 +1241,13 @@ mlx5e_get_sw_stats64(const struct net_device *dev,
 		     struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	struct mlx5e_sw_stats *sstats = &priv->stats.sw;
-
-	mlx5e_rep_update_sw_counters(priv);
-
-	stats->rx_packets = sstats->rx_packets;
-	stats->rx_bytes   = sstats->rx_bytes;
-	stats->tx_packets = sstats->tx_packets;
-	stats->tx_bytes   = sstats->tx_bytes;
-
-	stats->tx_dropped = sstats->tx_queue_dropped;
 
+	mlx5e_fold_sw_stats64(priv, stats);
 	return 0;
 }
 
-int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
-			    void *sp)
+static int mlx5e_rep_get_offload_stats(int attr_id, const struct net_device *dev,
+				       void *sp)
 {
 	switch (attr_id) {
 	case IFLA_OFFLOAD_XSTATS_CPU_HIT:
@@ -982,7 +1258,7 @@ int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev,
 }
 
 static void
-mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
+mlx5e_vf_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
@@ -991,37 +1267,104 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
-static const struct switchdev_ops mlx5e_rep_switchdev_ops = {
-	.switchdev_port_attr_get	= mlx5e_attr_get,
-};
-
-static int mlx5e_change_rep_mtu(struct net_device *netdev, int new_mtu)
+static int mlx5e_vf_rep_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	return mlx5e_change_mtu(netdev, new_mtu, NULL);
 }
 
-static const struct net_device_ops mlx5e_netdev_ops_rep = {
-	.ndo_open                = mlx5e_rep_open,
-	.ndo_stop                = mlx5e_rep_close,
+static int mlx5e_uplink_rep_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	return mlx5e_change_mtu(netdev, new_mtu, mlx5e_set_dev_port_mtu);
+}
+
+static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr)
+{
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	ether_addr_copy(netdev->dev_addr, saddr->sa_data);
+	return 0;
+}
+
+static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos,
+					__be16 vlan_proto)
+{
+	netdev_warn_once(dev, "legacy vf vlan setting isn't supported in switchdev mode\n");
+
+	if (vlan != 0)
+		return -EOPNOTSUPP;
+
+	/* allow setting 0-vid for compatibility with libvirt */
+	return 0;
+}
+
+static const struct net_device_ops mlx5e_netdev_ops_vf_rep = {
+	.ndo_open                = mlx5e_vf_rep_open,
+	.ndo_stop                = mlx5e_vf_rep_close,
+	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
+	.ndo_setup_tc            = mlx5e_rep_setup_tc,
+	.ndo_get_stats64         = mlx5e_vf_rep_get_stats,
+	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
+	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
+	.ndo_change_mtu          = mlx5e_vf_rep_change_mtu,
+	.ndo_get_port_parent_id	 = mlx5e_rep_get_port_parent_id,
+};
+
+static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = {
+	.ndo_open                = mlx5e_open,
+	.ndo_stop                = mlx5e_close,
 	.ndo_start_xmit          = mlx5e_xmit,
+	.ndo_set_mac_address     = mlx5e_uplink_rep_set_mac,
 	.ndo_get_phys_port_name  = mlx5e_rep_get_phys_port_name,
 	.ndo_setup_tc            = mlx5e_rep_setup_tc,
-	.ndo_get_stats64         = mlx5e_rep_get_stats,
-	.ndo_has_offload_stats	 = mlx5e_has_offload_stats,
-	.ndo_get_offload_stats	 = mlx5e_get_offload_stats,
-	.ndo_change_mtu          = mlx5e_change_rep_mtu,
+	.ndo_get_stats64         = mlx5e_get_stats,
+	.ndo_has_offload_stats	 = mlx5e_rep_has_offload_stats,
+	.ndo_get_offload_stats	 = mlx5e_rep_get_offload_stats,
+	.ndo_change_mtu          = mlx5e_uplink_rep_change_mtu,
+	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
+	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
+	.ndo_features_check      = mlx5e_features_check,
+	.ndo_set_vf_mac          = mlx5e_set_vf_mac,
+	.ndo_set_vf_rate         = mlx5e_set_vf_rate,
+	.ndo_get_vf_config       = mlx5e_get_vf_config,
+	.ndo_get_vf_stats        = mlx5e_get_vf_stats,
+	.ndo_set_vf_vlan         = mlx5e_uplink_rep_set_vf_vlan,
+	.ndo_get_port_parent_id	 = mlx5e_rep_get_port_parent_id,
 };
 
-static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
-				   struct mlx5e_params *params, u16 mtu)
+bool mlx5e_eswitch_rep(struct net_device *netdev)
+{
+	if (netdev->netdev_ops == &mlx5e_netdev_ops_vf_rep ||
+	    netdev->netdev_ops == &mlx5e_netdev_ops_uplink_rep)
+		return true;
+
+	return false;
+}
+
+static void mlx5e_build_rep_params(struct net_device *netdev)
 {
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_params *params;
+
 	u8 cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
 					 MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
 					 MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
 
+	params = &priv->channels.params;
 	params->hard_mtu    = MLX5E_ETH_HARD_MTU;
-	params->sw_mtu      = mtu;
-	params->log_sq_size = MLX5E_REP_PARAMS_LOG_SQ_SIZE;
+	params->sw_mtu      = netdev->mtu;
+
+	/* SQ */
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE;
+	else
+		params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
@@ -1035,24 +1378,36 @@ static void mlx5e_build_rep_params(struct mlx5_core_dev *mdev,
 	mlx5_query_min_inline(mdev, &params->tx_min_inline_mode);
 
 	/* RSS */
-	mlx5e_build_rss_params(params);
+	mlx5e_build_rss_params(&priv->rss_params, params->num_channels);
 }
 
 static void mlx5e_build_rep_netdev(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *rep = rpriv->rep;
 	struct mlx5_core_dev *mdev = priv->mdev;
-	u16 max_mtu;
 
-	netdev->netdev_ops = &mlx5e_netdev_ops_rep;
+	if (rep->vport == MLX5_VPORT_UPLINK) {
+		SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev);
+		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
+		/* we want a persistent mac for the uplink rep */
+		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);
+		netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops;
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+		if (MLX5_CAP_GEN(mdev, qos))
+			netdev->dcbnl_ops = &mlx5e_dcbnl_ops;
+#endif
+	} else {
+		netdev->netdev_ops = &mlx5e_netdev_ops_vf_rep;
+		eth_hw_addr_random(netdev);
+		netdev->ethtool_ops = &mlx5e_vf_rep_ethtool_ops;
+	}
 
 	netdev->watchdog_timeo    = 15 * HZ;
 
-	netdev->ethtool_ops	  = &mlx5e_rep_ethtool_ops;
-
-	netdev->switchdev_ops = &mlx5e_rep_switchdev_ops;
 
-	netdev->features	 |= NETIF_F_VLAN_CHALLENGED | NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
+	netdev->features	 |= NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL;
 	netdev->hw_features      |= NETIF_F_HW_TC;
 
 	netdev->hw_features    |= NETIF_F_SG;
@@ -1063,13 +1418,10 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 	netdev->hw_features    |= NETIF_F_TSO6;
 	netdev->hw_features    |= NETIF_F_RXCSUM;
 
-	netdev->features |= netdev->hw_features;
-
-	eth_hw_addr_random(netdev);
+	if (rep->vport != MLX5_VPORT_UPLINK)
+		netdev->features |= NETIF_F_VLAN_CHALLENGED;
 
-	netdev->min_mtu = ETH_MIN_MTU;
-	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
-	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	netdev->features |= netdev->hw_features;
 }
 
 static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
@@ -1086,7 +1438,7 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 
 	priv->channels.params.num_channels = MLX5E_REP_PARAMS_DEF_NUM_CHANNELS;
 
-	mlx5e_build_rep_params(mdev, &priv->channels.params, netdev->mtu);
+	mlx5e_build_rep_params(netdev);
 	mlx5e_build_rep_netdev(netdev);
 
 	mlx5e_timestamp_init(priv);
@@ -1209,94 +1561,193 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
 
 static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
 {
-	int err;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	int tc, err;
 
 	err = mlx5e_create_tises(priv);
 	if (err) {
 		mlx5_core_warn(priv->mdev, "create tises failed, %d\n", err);
 		return err;
 	}
+
+	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
+		uplink_priv = &rpriv->uplink_priv;
+
+		INIT_LIST_HEAD(&uplink_priv->unready_flows);
+
+		/* init shared tc flow table */
+		err = mlx5e_tc_esw_init(&uplink_priv->tc_ht);
+		if (err)
+			goto destroy_tises;
+
+		mlx5_init_port_tun_entropy(&uplink_priv->tun_entropy, priv->mdev);
+
+		/* init indirect block notifications */
+		INIT_LIST_HEAD(&uplink_priv->tc_indr_block_priv_list);
+		uplink_priv->netdevice_nb.notifier_call = mlx5e_nic_rep_netdevice_event;
+		err = register_netdevice_notifier(&uplink_priv->netdevice_nb);
+		if (err) {
+			mlx5_core_err(priv->mdev, "Failed to register netdev notifier\n");
+			goto tc_esw_cleanup;
+		}
+	}
+
 	return 0;
+
+tc_esw_cleanup:
+	mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht);
+destroy_tises:
+	for (tc = 0; tc < priv->profile->max_tc; tc++)
+		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
+	return err;
 }
 
-static const struct mlx5e_profile mlx5e_rep_profile = {
-	.init			= mlx5e_init_rep,
-	.cleanup		= mlx5e_cleanup_rep,
-	.init_rx		= mlx5e_init_rep_rx,
-	.cleanup_rx		= mlx5e_cleanup_rep_rx,
-	.init_tx		= mlx5e_init_rep_tx,
-	.cleanup_tx		= mlx5e_cleanup_nic_tx,
-	.update_stats           = mlx5e_rep_update_hw_counters,
-	.update_carrier		= NULL,
-	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
-	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
-	.max_tc			= 1,
-};
+static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	int tc;
 
-/* e-Switch vport representors */
+	for (tc = 0; tc < priv->profile->max_tc; tc++)
+		mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]);
 
-static int
-mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
+	if (rpriv->rep->vport == MLX5_VPORT_UPLINK) {
+		/* clean indirect TC block notifications */
+		unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb);
+		mlx5e_rep_indr_clean_block_privs(rpriv);
+
+		/* delete shared tc flow table */
+		mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht);
+	}
+}
+
+static void mlx5e_vf_rep_enable(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	u16 max_mtu;
 
-	int err;
+	netdev->min_mtu = ETH_MIN_MTU;
+	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+}
 
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		err = mlx5e_add_sqs_fwd_rules(priv);
-		if (err)
-			return err;
+static int uplink_rep_async_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5e_priv *priv = container_of(nb, struct mlx5e_priv, events_nb);
+
+	if (event == MLX5_EVENT_TYPE_PORT_CHANGE) {
+		struct mlx5_eqe *eqe = data;
+
+		switch (eqe->sub_type) {
+		case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
+		case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
+			queue_work(priv->wq, &priv->update_carrier_work);
+			break;
+		default:
+			return NOTIFY_DONE;
+		}
+
+		return NOTIFY_OK;
 	}
 
-	err = mlx5e_rep_neigh_init(rpriv);
-	if (err)
-		goto err_remove_sqs;
+	if (event == MLX5_DEV_EVENT_PORT_AFFINITY) {
+		struct mlx5e_rep_priv *rpriv = priv->ppriv;
 
-	/* init shared tc flow table */
-	err = mlx5e_tc_esw_init(&rpriv->tc_ht);
-	if (err)
-		goto  err_neigh_cleanup;
+		queue_work(priv->wq, &rpriv->uplink_priv.reoffload_flows_work);
 
-	return 0;
+		return NOTIFY_OK;
+	}
 
-err_neigh_cleanup:
-	mlx5e_rep_neigh_cleanup(rpriv);
-err_remove_sqs:
-	mlx5e_remove_sqs_fwd_rules(priv);
-	return err;
+	return NOTIFY_DONE;
 }
 
-static void
-mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
+static void mlx5e_uplink_rep_enable(struct mlx5e_priv *priv)
 {
-	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
-	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
+	struct net_device *netdev = priv->netdev;
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	u16 max_mtu;
+
+	netdev->min_mtu = ETH_MIN_MTU;
+	mlx5_query_port_max_mtu(priv->mdev, &max_mtu, 1);
+	netdev->max_mtu = MLX5E_HW2SW_MTU(&priv->channels.params, max_mtu);
+	mlx5e_set_dev_port_mtu(priv);
 
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
-		mlx5e_remove_sqs_fwd_rules(priv);
+	INIT_WORK(&rpriv->uplink_priv.reoffload_flows_work,
+		  mlx5e_tc_reoffload_flows_work);
 
-	/* clean uplink offloaded TC rules, delete shared tc flow table */
-	mlx5e_tc_esw_cleanup(&rpriv->tc_ht);
+	mlx5_lag_add(mdev, netdev);
+	priv->events_nb.notifier_call = uplink_rep_async_event;
+	mlx5_notifier_register(mdev, &priv->events_nb);
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+	mlx5e_dcbnl_initialize(priv);
+	mlx5e_dcbnl_init_app(priv);
+#endif
+}
 
-	mlx5e_rep_neigh_cleanup(rpriv);
+static void mlx5e_uplink_rep_disable(struct mlx5e_priv *priv)
+{
+	struct mlx5_core_dev *mdev = priv->mdev;
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+
+#ifdef CONFIG_MLX5_CORE_EN_DCB
+	mlx5e_dcbnl_delete_app(priv);
+#endif
+	mlx5_notifier_unregister(mdev, &priv->events_nb);
+	cancel_work_sync(&rpriv->uplink_priv.reoffload_flows_work);
+	mlx5_lag_remove(mdev);
 }
 
+static const struct mlx5e_profile mlx5e_vf_rep_profile = {
+	.init			= mlx5e_init_rep,
+	.cleanup		= mlx5e_cleanup_rep,
+	.init_rx		= mlx5e_init_rep_rx,
+	.cleanup_rx		= mlx5e_cleanup_rep_rx,
+	.init_tx		= mlx5e_init_rep_tx,
+	.cleanup_tx		= mlx5e_cleanup_rep_tx,
+	.enable		        = mlx5e_vf_rep_enable,
+	.update_stats           = mlx5e_vf_rep_update_hw_counters,
+	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
+	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+	.max_tc			= 1,
+};
+
+static const struct mlx5e_profile mlx5e_uplink_rep_profile = {
+	.init			= mlx5e_init_rep,
+	.cleanup		= mlx5e_cleanup_rep,
+	.init_rx		= mlx5e_init_rep_rx,
+	.cleanup_rx		= mlx5e_cleanup_rep_rx,
+	.init_tx		= mlx5e_init_rep_tx,
+	.cleanup_tx		= mlx5e_cleanup_rep_tx,
+	.enable		        = mlx5e_uplink_rep_enable,
+	.disable	        = mlx5e_uplink_rep_disable,
+	.update_stats           = mlx5e_uplink_rep_update_hw_counters,
+	.update_carrier	        = mlx5e_update_carrier,
+	.rx_handlers.handle_rx_cqe       = mlx5e_handle_rx_cqe_rep,
+	.rx_handlers.handle_rx_cqe_mpwqe = mlx5e_handle_rx_cqe_mpwrq,
+	.max_tc			= MLX5E_MAX_NUM_TC,
+};
+
+/* e-Switch vport representors */
 static int
 mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 {
-	struct mlx5e_rep_priv *uplink_rpriv;
+	const struct mlx5e_profile *profile;
 	struct mlx5e_rep_priv *rpriv;
 	struct net_device *netdev;
-	struct mlx5e_priv *upriv;
 	int nch, err;
 
 	rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
 	if (!rpriv)
 		return -ENOMEM;
 
+	/* rpriv->rep to be looked up when profile->init() is called */
+	rpriv->rep = rep;
+
 	nch = mlx5e_get_max_num_channels(dev);
-	netdev = mlx5e_create_netdev(dev, &mlx5e_rep_profile, nch, rpriv);
+	profile = (rep->vport == MLX5_VPORT_UPLINK) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile;
+	netdev = mlx5e_create_netdev(dev, profile, nch, rpriv);
 	if (!netdev) {
 		pr_warn("Failed to create representor netdev for vport %d\n",
 			rep->vport);
@@ -1305,15 +1756,20 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	}
 
 	rpriv->netdev = netdev;
-	rpriv->rep = rep;
 	rep->rep_if[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
 
+	if (rep->vport == MLX5_VPORT_UPLINK) {
+		err = mlx5e_create_mdev_resources(dev);
+		if (err)
+			goto err_destroy_netdev;
+	}
+
 	err = mlx5e_attach_netdev(netdev_priv(netdev));
 	if (err) {
 		pr_warn("Failed to attach representor netdev for vport %d\n",
 			rep->vport);
-		goto err_destroy_netdev;
+		goto err_destroy_mdev_resources;
 	}
 
 	err = mlx5e_rep_neigh_init(rpriv);
@@ -1323,32 +1779,25 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		goto err_detach_netdev;
 	}
 
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
-	upriv = netdev_priv(uplink_rpriv->netdev);
-	err = tc_setup_cb_egdev_register(netdev, mlx5e_rep_setup_tc_cb_egdev,
-					 upriv);
-	if (err)
-		goto err_neigh_cleanup;
-
 	err = register_netdev(netdev);
 	if (err) {
 		pr_warn("Failed to register representor netdev for vport %d\n",
 			rep->vport);
-		goto err_egdev_cleanup;
+		goto err_neigh_cleanup;
 	}
 
 	return 0;
 
-err_egdev_cleanup:
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
-				     upriv);
-
 err_neigh_cleanup:
 	mlx5e_rep_neigh_cleanup(rpriv);
 
 err_detach_netdev:
 	mlx5e_detach_netdev(netdev_priv(netdev));
 
+err_destroy_mdev_resources:
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		mlx5e_destroy_mdev_resources(dev);
+
 err_destroy_netdev:
 	mlx5e_destroy_netdev(netdev_priv(netdev));
 	kfree(rpriv);
@@ -1361,18 +1810,13 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
 	struct net_device *netdev = rpriv->netdev;
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_rep_priv *uplink_rpriv;
 	void *ppriv = priv->ppriv;
-	struct mlx5e_priv *upriv;
 
 	unregister_netdev(netdev);
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
-						    REP_ETH);
-	upriv = netdev_priv(uplink_rpriv->netdev);
-	tc_setup_cb_egdev_unregister(netdev, mlx5e_rep_setup_tc_cb_egdev,
-				     upriv);
 	mlx5e_rep_neigh_cleanup(rpriv);
 	mlx5e_detach_netdev(priv);
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		mlx5e_destroy_mdev_resources(priv->mdev);
 	mlx5e_destroy_netdev(priv);
 	kfree(ppriv); /* mlx5e_rep_priv */
 }
@@ -1386,72 +1830,21 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep)
 	return rpriv->netdev;
 }
 
-static void mlx5e_rep_register_vf_vports(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++) {
-		struct mlx5_eswitch_rep_if rep_if = {};
-
-		rep_if.load = mlx5e_vport_rep_load;
-		rep_if.unload = mlx5e_vport_rep_unload;
-		rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
-		mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH);
-	}
-}
-
-static void mlx5e_rep_unregister_vf_vports(struct mlx5e_priv *priv)
+void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	int total_vfs = MLX5_TOTAL_VPORTS(mdev);
-	int vport;
-
-	for (vport = 1; vport < total_vfs; vport++)
-		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
-}
-
-void mlx5e_register_vport_reps(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
-	struct mlx5_eswitch_rep_if rep_if;
-	struct mlx5e_rep_priv *rpriv;
-
-	rpriv = priv->ppriv;
-	rpriv->netdev = priv->netdev;
+	struct mlx5_eswitch_rep_if rep_if = {};
 
-	rep_if.load = mlx5e_nic_rep_load;
-	rep_if.unload = mlx5e_nic_rep_unload;
+	rep_if.load = mlx5e_vport_rep_load;
+	rep_if.unload = mlx5e_vport_rep_unload;
 	rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev;
-	rep_if.priv = rpriv;
-	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
-	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_ETH); /* UPLINK PF vport*/
-
-	mlx5e_rep_register_vf_vports(priv); /* VFs vports */
-}
-
-void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv)
-{
-	struct mlx5_core_dev *mdev = priv->mdev;
-	struct mlx5_eswitch *esw   = mdev->priv.eswitch;
 
-	mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
-	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_ETH); /* UPLINK PF*/
+	mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_ETH);
 }
 
-void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev)
+void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5e_rep_priv *rpriv;
-
-	rpriv = kzalloc(sizeof(*rpriv), GFP_KERNEL);
-	if (!rpriv)
-		return NULL;
 
-	rpriv->rep = &esw->offloads.vport_reps[0];
-	return rpriv;
+	mlx5_eswitch_unregister_vport_reps(esw, REP_ETH);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
index 844d32d5c29f..83b573b1abac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h
@@ -37,6 +37,7 @@
 #include <linux/rhashtable.h>
 #include "eswitch.h"
 #include "en.h"
+#include "lib/port_tun.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
 struct mlx5e_neigh_update_table {
@@ -53,13 +54,38 @@ struct mlx5e_neigh_update_table {
 	unsigned long           min_interval; /* jiffies */
 };
 
+struct mlx5_rep_uplink_priv {
+	/* Filters DB - instantiated by the uplink representor and shared by
+	 * the uplink's VFs
+	 */
+	struct rhashtable  tc_ht;
+
+	/* indirect block callbacks are invoked on bind/unbind events
+	 * on registered higher level devices (e.g. tunnel devices)
+	 *
+	 * tc_indr_block_cb_priv_list is used to lookup indirect callback
+	 * private data
+	 *
+	 * netdevice_nb is the netdev events notifier - used to register
+	 * tunnel devices for block events
+	 *
+	 */
+	struct list_head	    tc_indr_block_priv_list;
+	struct notifier_block	    netdevice_nb;
+
+	struct mlx5_tun_entropy tun_entropy;
+
+	struct list_head            unready_flows;
+	struct work_struct          reoffload_flows_work;
+};
+
 struct mlx5e_rep_priv {
 	struct mlx5_eswitch_rep *rep;
 	struct mlx5e_neigh_update_table neigh_update;
 	struct net_device      *netdev;
 	struct mlx5_flow_handle *vport_rx_rule;
 	struct list_head       vport_sqs_list;
-	struct rhashtable      tc_ht; /* valid for uplink rep */
+	struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */
 };
 
 static inline
@@ -128,7 +154,10 @@ struct mlx5e_encap_entry {
 	unsigned char h_dest[ETH_ALEN];	/* destination eth addr	*/
 
 	struct net_device *out_dev;
+	struct net_device *route_dev;
 	int tunnel_type;
+	int tunnel_hlen;
+	int reformat_type;
 	u8 flags;
 	char *encap_header;
 	int encap_size;
@@ -140,16 +169,12 @@ struct mlx5e_rep_sq {
 };
 
 void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev);
-void mlx5e_register_vport_reps(struct mlx5e_priv *priv);
-void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv);
+void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev);
+void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev);
 bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv);
 int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv);
 void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv);
 
-int mlx5e_get_offload_stats(int attr_id, const struct net_device *dev, void *sp);
-bool mlx5e_has_offload_stats(const struct net_device *dev, int attr_id);
-
-int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr);
 void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv,
@@ -158,12 +183,17 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv,
 				  struct mlx5e_encap_entry *e);
 
 void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv);
+
+bool mlx5e_eswitch_rep(struct net_device *netdev);
+
 #else /* CONFIG_MLX5_ESWITCH */
-static inline void mlx5e_register_vport_reps(struct mlx5e_priv *priv) {}
-static inline void mlx5e_unregister_vport_reps(struct mlx5e_priv *priv) {}
 static inline bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) { return false; }
 static inline int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) {}
 #endif
 
+static inline bool mlx5e_is_vport_rep(struct mlx5e_priv *priv)
+{
+	return (MLX5_ESWITCH_MANAGER(priv->mdev) && priv->ppriv);
+}
 #endif /* __MLX5E_REP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0b5ef6d4e815..c3b3002ff62f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -52,40 +52,45 @@ static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 	return config->rx_filter == HWTSTAMP_FILTER_ALL;
 }
 
-static inline void mlx5e_read_cqe_slot(struct mlx5e_cq *cq, u32 cqcc,
-				       void *data)
+static inline void mlx5e_read_cqe_slot(struct mlx5_cqwq *wq,
+				       u32 cqcc, void *data)
 {
-	u32 ci = mlx5_cqwq_ctr2ix(&cq->wq, cqcc);
+	u32 ci = mlx5_cqwq_ctr2ix(wq, cqcc);
 
-	memcpy(data, mlx5_cqwq_get_wqe(&cq->wq, ci), sizeof(struct mlx5_cqe64));
+	memcpy(data, mlx5_cqwq_get_wqe(wq, ci), sizeof(struct mlx5_cqe64));
 }
 
 static inline void mlx5e_read_title_slot(struct mlx5e_rq *rq,
-					 struct mlx5e_cq *cq, u32 cqcc)
+					 struct mlx5_cqwq *wq,
+					 u32 cqcc)
 {
-	mlx5e_read_cqe_slot(cq, cqcc, &cq->title);
-	cq->decmprs_left        = be32_to_cpu(cq->title.byte_cnt);
-	cq->decmprs_wqe_counter = be16_to_cpu(cq->title.wqe_counter);
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	struct mlx5_cqe64 *title = &cqd->title;
+
+	mlx5e_read_cqe_slot(wq, cqcc, title);
+	cqd->left        = be32_to_cpu(title->byte_cnt);
+	cqd->wqe_counter = be16_to_cpu(title->wqe_counter);
 	rq->stats->cqe_compress_blks++;
 }
 
-static inline void mlx5e_read_mini_arr_slot(struct mlx5e_cq *cq, u32 cqcc)
+static inline void mlx5e_read_mini_arr_slot(struct mlx5_cqwq *wq,
+					    struct mlx5e_cq_decomp *cqd,
+					    u32 cqcc)
 {
-	mlx5e_read_cqe_slot(cq, cqcc, cq->mini_arr);
-	cq->mini_arr_idx = 0;
+	mlx5e_read_cqe_slot(wq, cqcc, cqd->mini_arr);
+	cqd->mini_arr_idx = 0;
 }
 
-static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
+static inline void mlx5e_cqes_update_owner(struct mlx5_cqwq *wq, int n)
 {
-	struct mlx5_cqwq *wq = &cq->wq;
-
+	u32 cqcc   = wq->cc;
 	u8  op_own = mlx5_cqwq_get_ctr_wrap_cnt(wq, cqcc) & 1;
 	u32 ci     = mlx5_cqwq_ctr2ix(wq, cqcc);
 	u32 wq_sz  = mlx5_cqwq_get_size(wq);
 	u32 ci_top = min_t(u32, wq_sz, ci + n);
 
 	for (; ci < ci_top; ci++, n--) {
-		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, ci);
+		struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci);
 
 		cqe->op_own = op_own;
 	}
@@ -93,7 +98,7 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 	if (unlikely(ci == wq_sz)) {
 		op_own = !op_own;
 		for (ci = 0; ci < n; ci++) {
-			struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(&cq->wq, ci);
+			struct mlx5_cqe64 *cqe = mlx5_cqwq_get_wqe(wq, ci);
 
 			cqe->op_own = op_own;
 		}
@@ -101,68 +106,79 @@ static inline void mlx5e_cqes_update_owner(struct mlx5e_cq *cq, u32 cqcc, int n)
 }
 
 static inline void mlx5e_decompress_cqe(struct mlx5e_rq *rq,
-					struct mlx5e_cq *cq, u32 cqcc)
+					struct mlx5_cqwq *wq,
+					u32 cqcc)
 {
-	cq->title.byte_cnt     = cq->mini_arr[cq->mini_arr_idx].byte_cnt;
-	cq->title.check_sum    = cq->mini_arr[cq->mini_arr_idx].checksum;
-	cq->title.op_own      &= 0xf0;
-	cq->title.op_own      |= 0x01 & (cqcc >> cq->wq.fbc.log_sz);
-	cq->title.wqe_counter  = cpu_to_be16(cq->decmprs_wqe_counter);
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	struct mlx5_mini_cqe8 *mini_cqe = &cqd->mini_arr[cqd->mini_arr_idx];
+	struct mlx5_cqe64 *title = &cqd->title;
+
+	title->byte_cnt     = mini_cqe->byte_cnt;
+	title->check_sum    = mini_cqe->checksum;
+	title->op_own      &= 0xf0;
+	title->op_own      |= 0x01 & (cqcc >> wq->fbc.log_sz);
+	title->wqe_counter  = cpu_to_be16(cqd->wqe_counter);
 
 	if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ)
-		cq->decmprs_wqe_counter +=
-			mpwrq_get_cqe_consumed_strides(&cq->title);
+		cqd->wqe_counter += mpwrq_get_cqe_consumed_strides(title);
 	else
-		cq->decmprs_wqe_counter =
-			mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, cq->decmprs_wqe_counter + 1);
+		cqd->wqe_counter =
+			mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, cqd->wqe_counter + 1);
 }
 
 static inline void mlx5e_decompress_cqe_no_hash(struct mlx5e_rq *rq,
-						struct mlx5e_cq *cq, u32 cqcc)
+						struct mlx5_cqwq *wq,
+						u32 cqcc)
 {
-	mlx5e_decompress_cqe(rq, cq, cqcc);
-	cq->title.rss_hash_type   = 0;
-	cq->title.rss_hash_result = 0;
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+
+	mlx5e_decompress_cqe(rq, wq, cqcc);
+	cqd->title.rss_hash_type   = 0;
+	cqd->title.rss_hash_result = 0;
 }
 
 static inline u32 mlx5e_decompress_cqes_cont(struct mlx5e_rq *rq,
-					     struct mlx5e_cq *cq,
+					     struct mlx5_cqwq *wq,
 					     int update_owner_only,
 					     int budget_rem)
 {
-	u32 cqcc = cq->wq.cc + update_owner_only;
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	u32 cqcc = wq->cc + update_owner_only;
 	u32 cqe_count;
 	u32 i;
 
-	cqe_count = min_t(u32, cq->decmprs_left, budget_rem);
+	cqe_count = min_t(u32, cqd->left, budget_rem);
 
 	for (i = update_owner_only; i < cqe_count;
-	     i++, cq->mini_arr_idx++, cqcc++) {
-		if (cq->mini_arr_idx == MLX5_MINI_CQE_ARRAY_SIZE)
-			mlx5e_read_mini_arr_slot(cq, cqcc);
+	     i++, cqd->mini_arr_idx++, cqcc++) {
+		if (cqd->mini_arr_idx == MLX5_MINI_CQE_ARRAY_SIZE)
+			mlx5e_read_mini_arr_slot(wq, cqd, cqcc);
 
-		mlx5e_decompress_cqe_no_hash(rq, cq, cqcc);
-		rq->handle_rx_cqe(rq, &cq->title);
+		mlx5e_decompress_cqe_no_hash(rq, wq, cqcc);
+		rq->handle_rx_cqe(rq, &cqd->title);
 	}
-	mlx5e_cqes_update_owner(cq, cq->wq.cc, cqcc - cq->wq.cc);
-	cq->wq.cc = cqcc;
-	cq->decmprs_left -= cqe_count;
+	mlx5e_cqes_update_owner(wq, cqcc - wq->cc);
+	wq->cc = cqcc;
+	cqd->left -= cqe_count;
 	rq->stats->cqe_compress_pkts += cqe_count;
 
 	return cqe_count;
 }
 
 static inline u32 mlx5e_decompress_cqes_start(struct mlx5e_rq *rq,
-					      struct mlx5e_cq *cq,
+					      struct mlx5_cqwq *wq,
 					      int budget_rem)
 {
-	mlx5e_read_title_slot(rq, cq, cq->wq.cc);
-	mlx5e_read_mini_arr_slot(cq, cq->wq.cc + 1);
-	mlx5e_decompress_cqe(rq, cq, cq->wq.cc);
-	rq->handle_rx_cqe(rq, &cq->title);
-	cq->mini_arr_idx++;
+	struct mlx5e_cq_decomp *cqd = &rq->cqd;
+	u32 cc = wq->cc;
 
-	return mlx5e_decompress_cqes_cont(rq, cq, 1, budget_rem) - 1;
+	mlx5e_read_title_slot(rq, wq, cc);
+	mlx5e_read_mini_arr_slot(wq, cqd, cc + 1);
+	mlx5e_decompress_cqe(rq, wq, cc);
+	rq->handle_rx_cqe(rq, &cqd->title);
+	cqd->mini_arr_idx++;
+
+	return mlx5e_decompress_cqes_cont(rq, wq, 1, budget_rem) - 1;
 }
 
 static inline bool mlx5e_page_is_reserved(struct page *page)
@@ -369,7 +385,7 @@ mlx5e_add_skb_frag(struct mlx5e_rq *rq, struct sk_buff *skb,
 static inline void
 mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
 		      struct mlx5e_dma_info *dma_info,
-		      int offset_from, int offset_to, u32 headlen)
+		      int offset_from, u32 headlen)
 {
 	const void *from = page_address(dma_info->page) + offset_from;
 	/* Aligning len to sizeof(long) optimizes memcpy performance */
@@ -377,24 +393,7 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb,
 
 	dma_sync_single_for_cpu(pdev, dma_info->addr + offset_from, len,
 				DMA_FROM_DEVICE);
-	skb_copy_to_linear_data_offset(skb, offset_to, from, len);
-}
-
-static inline void
-mlx5e_copy_skb_header_mpwqe(struct device *pdev,
-			    struct sk_buff *skb,
-			    struct mlx5e_dma_info *dma_info,
-			    u32 offset, u32 headlen)
-{
-	u16 headlen_pg = min_t(u32, headlen, PAGE_SIZE - offset);
-
-	mlx5e_copy_skb_header(pdev, skb, dma_info, offset, 0, headlen_pg);
-
-	if (unlikely(offset + headlen > PAGE_SIZE)) {
-		dma_info++;
-		mlx5e_copy_skb_header(pdev, skb, dma_info, 0, headlen_pg,
-				      headlen - headlen_pg);
-	}
+	skb_copy_to_linear_data(skb, from, len);
 }
 
 static void
@@ -554,9 +553,9 @@ static inline void mlx5e_poll_ico_single_cqe(struct mlx5e_cq *cq,
 
 	mlx5_cqwq_pop(&cq->wq);
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_REQ)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) {
 		netdev_WARN_ONCE(cq->channel->netdev,
-				 "Bad OP in ICOSQ CQE: 0x%x\n", cqe->op_own);
+				 "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe));
 		return;
 	}
 
@@ -693,7 +692,14 @@ static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
 {
 	*proto = ((struct ethhdr *)skb->data)->h_proto;
 	*proto = __vlan_get_protocol(skb, *proto, network_depth);
-	return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+
+	if (*proto == htons(ETH_P_IP))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct iphdr));
+
+	if (*proto == htons(ETH_P_IPV6))
+		return pskb_may_pull(skb, *network_depth + sizeof(struct ipv6hdr));
+
+	return false;
 }
 
 static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
@@ -713,23 +719,76 @@ static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
 	rq->stats->ecn_mark += !!rc;
 }
 
-static u32 mlx5e_get_fcs(const struct sk_buff *skb)
+static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
 {
-	const void *fcs_bytes;
-	u32 _fcs_bytes;
+	void *ip_p = skb->data + network_depth;
+
+	return (proto == htons(ETH_P_IP)) ? ((struct iphdr *)ip_p)->protocol :
+					    ((struct ipv6hdr *)ip_p)->nexthdr;
+}
+
+#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN)
 
-	fcs_bytes = skb_header_pointer(skb, skb->len - ETH_FCS_LEN,
-				       ETH_FCS_LEN, &_fcs_bytes);
+#define MAX_PADDING 8
 
-	return __get_unaligned_cpu32(fcs_bytes);
+static void
+tail_padding_csum_slow(struct sk_buff *skb, int offset, int len,
+		       struct mlx5e_rq_stats *stats)
+{
+	stats->csum_complete_tail_slow++;
+	skb->csum = csum_block_add(skb->csum,
+				   skb_checksum(skb, offset, len, 0),
+				   offset);
 }
 
-static u8 get_ip_proto(struct sk_buff *skb, int network_depth, __be16 proto)
+static void
+tail_padding_csum(struct sk_buff *skb, int offset,
+		  struct mlx5e_rq_stats *stats)
 {
-	void *ip_p = skb->data + network_depth;
+	u8 tail_padding[MAX_PADDING];
+	int len = skb->len - offset;
+	void *tail;
 
-	return (proto == htons(ETH_P_IP)) ? ((struct iphdr *)ip_p)->protocol :
-					    ((struct ipv6hdr *)ip_p)->nexthdr;
+	if (unlikely(len > MAX_PADDING)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	tail = skb_header_pointer(skb, offset, len, tail_padding);
+	if (unlikely(!tail)) {
+		tail_padding_csum_slow(skb, offset, len, stats);
+		return;
+	}
+
+	stats->csum_complete_tail++;
+	skb->csum = csum_block_add(skb->csum, csum_partial(tail, len, 0), offset);
+}
+
+static void
+mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto,
+		       struct mlx5e_rq_stats *stats)
+{
+	struct ipv6hdr *ip6;
+	struct iphdr   *ip4;
+	int pkt_len;
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		ip4 = (struct iphdr *)(skb->data + network_depth);
+		pkt_len = network_depth + ntohs(ip4->tot_len);
+		break;
+	case htons(ETH_P_IPV6):
+		ip6 = (struct ipv6hdr *)(skb->data + network_depth);
+		pkt_len = network_depth + sizeof(*ip6) + ntohs(ip6->payload_len);
+		break;
+	default:
+		return;
+	}
+
+	if (likely(pkt_len >= skb->len))
+		return;
+
+	tail_padding_csum(skb, pkt_len, stats);
 }
 
 static inline void mlx5e_handle_csum(struct net_device *netdev,
@@ -751,7 +810,19 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 		return;
 	}
 
-	if (unlikely(test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state)))
+	/* True when explicitly set via priv flag, or XDP prog is loaded */
+	if (test_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &rq->state))
+		goto csum_unnecessary;
+
+	/* CQE csum doesn't cover padding octets in short ethernet
+	 * frames. And the pad field is appended prior to calculating
+	 * and appending the FCS field.
+	 *
+	 * Detecting these padded frames requires to verify and parse
+	 * IP headers, so we simply force all those small frames to be
+	 * CHECKSUM_UNNECESSARY even if they are not padded.
+	 */
+	if (short_frame(skb->len))
 		goto csum_unnecessary;
 
 	if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
@@ -768,18 +839,15 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
 			skb->csum = csum_partial(skb->data + ETH_HLEN,
 						 network_depth - ETH_HLEN,
 						 skb->csum);
-		if (unlikely(netdev->features & NETIF_F_RXFCS))
-			skb->csum = csum_block_add(skb->csum,
-						   (__force __wsum)mlx5e_get_fcs(skb),
-						   skb->len - ETH_FCS_LEN);
+
+		mlx5e_skb_padding_csum(skb, network_depth, proto, stats);
 		stats->csum_complete++;
 		return;
 	}
 
 csum_unnecessary:
 	if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
-		   ((cqe->hds_ip_ext & CQE_L4_OK) ||
-		    (get_cqe_l4_hdr_type(cqe) == CQE_L4_HDR_TYPE_NONE)))) {
+		   (cqe->hds_ip_ext & CQE_L4_OK))) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		if (cqe_is_tunneled(cqe)) {
 			skb->csum_level = 1;
@@ -898,7 +966,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
 		return NULL;
 	}
@@ -930,7 +998,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	u16 byte_cnt     = cqe_bcnt - headlen;
 	struct sk_buff *skb;
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
 		return NULL;
 	}
@@ -960,8 +1028,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 	}
 
 	/* copy header */
-	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset,
-			      0, headlen);
+	mlx5e_copy_skb_header(rq->pdev, skb, head_wi->di, head_wi->offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
@@ -1083,8 +1150,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 		di++;
 	}
 	/* copy header */
-	mlx5e_copy_skb_header_mpwqe(rq->pdev, skb, head_di,
-				    head_offset, headlen);
+	mlx5e_copy_skb_header(rq->pdev, skb, head_di, head_offset, headlen);
 	/* skb linear part was allocated with headlen and aligned to long */
 	skb->tail += headlen;
 	skb->len  += headlen;
@@ -1154,7 +1220,7 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 
 	wi->consumed_strides += cstrides;
 
-	if (unlikely((cqe->op_own >> 4) != MLX5_CQE_RESP_SEND)) {
+	if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) {
 		rq->stats->wqe_err++;
 		goto mpwrq_cqe_out;
 	}
@@ -1190,17 +1256,17 @@ mpwrq_cqe_out:
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 {
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
-	struct mlx5e_xdpsq *xdpsq = &rq->xdpsq;
+	struct mlx5_cqwq *cqwq = &cq->wq;
 	struct mlx5_cqe64 *cqe;
 	int work_done = 0;
 
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return 0;
 
-	if (cq->decmprs_left)
-		work_done += mlx5e_decompress_cqes_cont(rq, cq, 0, budget);
+	if (rq->cqd.left)
+		work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget);
 
-	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	cqe = mlx5_cqwq_get_cqe(cqwq);
 	if (!cqe) {
 		if (unlikely(work_done))
 			goto out;
@@ -1210,28 +1276,21 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	do {
 		if (mlx5_get_cqe_format(cqe) == MLX5_COMPRESSED) {
 			work_done +=
-				mlx5e_decompress_cqes_start(rq, cq,
+				mlx5e_decompress_cqes_start(rq, cqwq,
 							    budget - work_done);
 			continue;
 		}
 
-		mlx5_cqwq_pop(&cq->wq);
+		mlx5_cqwq_pop(cqwq);
 
 		rq->handle_rx_cqe(rq, cqe);
-	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(cqwq)));
 
 out:
-	if (xdpsq->doorbell) {
-		mlx5e_xmit_xdp_doorbell(xdpsq);
-		xdpsq->doorbell = false;
-	}
-
-	if (xdpsq->redirect_flush) {
-		xdp_do_flush_map();
-		xdpsq->redirect_flush = false;
-	}
+	if (rq->xdp_prog)
+		mlx5e_xdp_rx_poll_complete(rq);
 
-	mlx5_cqwq_update_db_record(&cq->wq);
+	mlx5_cqwq_update_db_record(cqwq);
 
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
@@ -1292,8 +1351,14 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	skb->protocol = *((__be16 *)(skb->data));
 
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+	if (netdev->features & NETIF_F_RXCSUM) {
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
+		stats->csum_complete++;
+	} else {
+		skb->ip_summed = CHECKSUM_NONE;
+		stats->csum_none++;
+	}
 
 	if (unlikely(mlx5e_rx_hw_stamp(tstamp)))
 		skb_hwtstamps(skb)->hwtstamp =
@@ -1312,7 +1377,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq,
 
 	skb->dev = netdev;
 
-	stats->csum_complete++;
 	stats->packets++;
 	stats->bytes += cqe_bcnt;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 4337afd610d7..b75aa8b8bf04 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include "lib/mlx5.h"
 #include "en.h"
 #include "en_accel/ipsec.h"
 #include "en_accel/tls.h"
@@ -58,6 +59,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ 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_complete) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
@@ -126,9 +129,9 @@ static int mlx5e_grp_sw_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx)
 	return idx;
 }
 
-void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
+static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 {
-	struct mlx5e_sw_stats temp, *s = &temp;
+	struct mlx5e_sw_stats *s = &priv->stats.sw;
 	int i;
 
 	memset(s, 0, sizeof(*s));
@@ -150,6 +153,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
 		s->rx_csum_none	+= rq_stats->csum_none;
 		s->rx_csum_complete += rq_stats->csum_complete;
+		s->rx_csum_complete_tail += rq_stats->csum_complete_tail;
+		s->rx_csum_complete_tail_slow += rq_stats->csum_complete_tail_slow;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop     += rq_stats->xdp_drop;
@@ -211,8 +216,6 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
-
-	memcpy(&priv->stats.sw, s, sizeof(*s));
 }
 
 static const struct counter_desc q_stats_desc[] = {
@@ -480,7 +483,10 @@ static int mlx5e_grp_802_3_fill_stats(struct mlx5e_priv *priv, u64 *data,
 	return idx;
 }
 
-static void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
+#define MLX5_BASIC_PPCNT_SUPPORTED(mdev) \
+	(MLX5_CAP_GEN(mdev, pcam_reg) ? MLX5_CAP_PCAM_REG(mdev, ppcnt) : 1)
+
+void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
 {
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -488,6 +494,9 @@ static void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv)
 	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
 	void *out;
 
+	if (!MLX5_BASIC_PPCNT_SUPPORTED(mdev))
+		return;
+
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	out = pstats->IEEE_802_3_counters;
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_IEEE_802_3_COUNTERS_GROUP);
@@ -600,6 +609,9 @@ static void mlx5e_grp_2819_update_stats(struct mlx5e_priv *priv)
 	int sz = MLX5_ST_SZ_BYTES(ppcnt_reg);
 	void *out;
 
+	if (!MLX5_BASIC_PPCNT_SUPPORTED(mdev))
+		return;
+
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	out = pstats->RFC_2819_counters;
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_RFC_2819_COUNTERS_GROUP);
@@ -934,7 +946,7 @@ static const struct counter_desc pport_per_prio_pfc_stats_desc[] = {
 };
 
 static const struct counter_desc pport_pfc_stall_stats_desc[] = {
-	{ "tx_pause_storm_warning_events ", PPORT_PER_PRIO_OFF(device_stall_minor_watermark_cnt) },
+	{ "tx_pause_storm_warning_events", PPORT_PER_PRIO_OFF(device_stall_minor_watermark_cnt) },
 	{ "tx_pause_storm_error_events", PPORT_PER_PRIO_OFF(device_stall_critical_watermark_cnt) },
 };
 
@@ -1075,6 +1087,9 @@ static void mlx5e_grp_per_prio_update_stats(struct mlx5e_priv *priv)
 	int prio;
 	void *out;
 
+	if (!MLX5_BASIC_PPCNT_SUPPORTED(mdev))
+		return;
+
 	MLX5_SET(ppcnt_reg, in, local_port, 1);
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_PER_PRIORITY_COUNTERS_GROUP);
 	for (prio = 0; prio < NUM_PPORT_PRIO; prio++) {
@@ -1086,13 +1101,13 @@ static void mlx5e_grp_per_prio_update_stats(struct mlx5e_priv *priv)
 }
 
 static const struct counter_desc mlx5e_pme_status_desc[] = {
-	{ "module_unplug", 8 },
+	{ "module_unplug",       sizeof(u64) * MLX5_MODULE_STATUS_UNPLUGGED },
 };
 
 static const struct counter_desc mlx5e_pme_error_desc[] = {
-	{ "module_bus_stuck", 16 },       /* bus stuck (I2C or data shorted) */
-	{ "module_high_temp", 48 },       /* high temperature */
-	{ "module_bad_shorted", 56 },    /* bad or shorted cable/module */
+	{ "module_bus_stuck",    sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BUS_STUCK },
+	{ "module_high_temp",    sizeof(u64) * MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE },
+	{ "module_bad_shorted",  sizeof(u64) * MLX5_MODULE_EVENT_ERROR_BAD_CABLE },
 };
 
 #define NUM_PME_STATUS_STATS		ARRAY_SIZE(mlx5e_pme_status_desc)
@@ -1120,15 +1135,17 @@ static int mlx5e_grp_pme_fill_strings(struct mlx5e_priv *priv, u8 *data,
 static int mlx5e_grp_pme_fill_stats(struct mlx5e_priv *priv, u64 *data,
 				    int idx)
 {
-	struct mlx5_priv *mlx5_priv = &priv->mdev->priv;
+	struct mlx5_pme_stats pme_stats;
 	int i;
 
+	mlx5_get_pme_stats(priv->mdev, &pme_stats);
+
 	for (i = 0; i < NUM_PME_STATUS_STATS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.status_counters,
+		data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.status_counters,
 						   mlx5e_pme_status_desc, i);
 
 	for (i = 0; i < NUM_PME_ERR_STATS; i++)
-		data[idx++] = MLX5E_READ_CTR64_CPU(mlx5_priv->pme_stats.error_counters,
+		data[idx++] = MLX5E_READ_CTR64_CPU(pme_stats.error_counters,
 						   mlx5e_pme_error_desc, i);
 
 	return idx;
@@ -1177,6 +1194,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ 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_complete_tail) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_complete_tail_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 3ff69ddae2d3..16c3b785f282 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -71,6 +71,8 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary;
 	u64 rx_csum_none;
 	u64 rx_csum_complete;
+	u64 rx_csum_complete_tail;
+	u64 rx_csum_complete_tail_slow;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
@@ -181,6 +183,8 @@ struct mlx5e_rq_stats {
 	u64 packets;
 	u64 bytes;
 	u64 csum_complete;
+	u64 csum_complete_tail;
+	u64 csum_complete_tail_slow;
 	u64 csum_unnecessary;
 	u64 csum_unnecessary_inner;
 	u64 csum_none;
@@ -277,6 +281,6 @@ struct mlx5e_stats_grp {
 extern const struct mlx5e_stats_grp mlx5e_stats_grps[];
 extern const int mlx5e_num_stats_grps;
 
-void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv);
+void mlx5e_grp_802_3_update_stats(struct mlx5e_priv *priv);
 
 #endif /* __MLX5_EN_STATS_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 9dabe9d4b279..d75dc44eb2ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -38,21 +38,20 @@
 #include <linux/mlx5/fs.h>
 #include <linux/mlx5/device.h>
 #include <linux/rhashtable.h>
-#include <net/switchdev.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_vlan.h>
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_csum.h>
-#include <net/vxlan.h>
 #include <net/arp.h>
 #include "en.h"
 #include "en_rep.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "lib/vxlan.h"
 #include "fs_core.h"
 #include "en/port.h"
+#include "en/tc_tun.h"
+#include "lib/devcom.h"
 
 struct mlx5_nic_flow_attr {
 	u32 action;
@@ -69,25 +68,56 @@ struct mlx5_nic_flow_attr {
 enum {
 	MLX5E_TC_FLOW_INGRESS	= MLX5E_TC_INGRESS,
 	MLX5E_TC_FLOW_EGRESS	= MLX5E_TC_EGRESS,
-	MLX5E_TC_FLOW_ESWITCH	= BIT(MLX5E_TC_FLOW_BASE),
-	MLX5E_TC_FLOW_NIC	= BIT(MLX5E_TC_FLOW_BASE + 1),
-	MLX5E_TC_FLOW_OFFLOADED	= BIT(MLX5E_TC_FLOW_BASE + 2),
-	MLX5E_TC_FLOW_HAIRPIN	= BIT(MLX5E_TC_FLOW_BASE + 3),
-	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 4),
-	MLX5E_TC_FLOW_SLOW	  = BIT(MLX5E_TC_FLOW_BASE + 5),
+	MLX5E_TC_FLOW_ESWITCH	= MLX5E_TC_ESW_OFFLOAD,
+	MLX5E_TC_FLOW_NIC	= MLX5E_TC_NIC_OFFLOAD,
+	MLX5E_TC_FLOW_OFFLOADED	= BIT(MLX5E_TC_FLOW_BASE),
+	MLX5E_TC_FLOW_HAIRPIN	= BIT(MLX5E_TC_FLOW_BASE + 1),
+	MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 2),
+	MLX5E_TC_FLOW_SLOW	  = BIT(MLX5E_TC_FLOW_BASE + 3),
+	MLX5E_TC_FLOW_DUP         = BIT(MLX5E_TC_FLOW_BASE + 4),
+	MLX5E_TC_FLOW_NOT_READY   = BIT(MLX5E_TC_FLOW_BASE + 5),
 };
 
 #define MLX5E_TC_MAX_SPLITS 1
 
+/* Helper struct for accessing a struct containing list_head array.
+ * Containing struct
+ *   |- Helper array
+ *      [0] Helper item 0
+ *          |- list_head item 0
+ *          |- index (0)
+ *      [1] Helper item 1
+ *          |- list_head item 1
+ *          |- index (1)
+ * To access the containing struct from one of the list_head items:
+ * 1. Get the helper item from the list_head item using
+ *    helper item =
+ *        container_of(list_head item, helper struct type, list_head field)
+ * 2. Get the contining struct from the helper item and its index in the array:
+ *    containing struct =
+ *        container_of(helper item, containing struct type, helper field[index])
+ */
+struct encap_flow_item {
+	struct list_head list;
+	int index;
+};
+
 struct mlx5e_tc_flow {
 	struct rhash_head	node;
 	struct mlx5e_priv	*priv;
 	u64			cookie;
 	u16			flags;
 	struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1];
-	struct list_head	encap;   /* flows sharing the same encap ID */
+	/* Flow can be associated with multiple encap IDs.
+	 * The number of encaps is bounded by the number of supported
+	 * destinations.
+	 */
+	struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS];
+	struct mlx5e_tc_flow    *peer_flow;
 	struct list_head	mod_hdr; /* flows sharing the same mod hdr ID */
 	struct list_head	hairpin; /* flows sharing the same hairpin */
+	struct list_head	peer;    /* flows with peer flow */
+	struct list_head	unready; /* flows not ready to be offloaded (e.g due to missing route) */
 	union {
 		struct mlx5_esw_flow_attr esw_attr[0];
 		struct mlx5_nic_flow_attr nic_attr[0];
@@ -95,11 +125,13 @@ struct mlx5e_tc_flow {
 };
 
 struct mlx5e_tc_flow_parse_attr {
-	struct ip_tunnel_info tun_info;
+	struct ip_tunnel_info tun_info[MLX5_MAX_FLOW_FWD_VPORTS];
+	struct net_device *filter_dev;
 	struct mlx5_flow_spec spec;
 	int num_mod_hdr_actions;
+	int max_mod_hdr_actions;
 	void *mod_hdr_actions;
-	int mirred_ifindex;
+	int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS];
 };
 
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
@@ -316,7 +348,7 @@ static void mlx5e_hairpin_fill_rqt_rqns(struct mlx5e_hairpin *hp, void *rqtc)
 
 	for (i = 0; i < sz; i++) {
 		ix = i;
-		if (priv->channels.params.rss_hfunc == ETH_RSS_HASH_XOR)
+		if (priv->rss_params.hfunc == ETH_RSS_HASH_XOR)
 			ix = mlx5e_bits_invert(i, ilog2(sz));
 		ix = indirection_rqt[ix];
 		rqn = hp->pair->rqn[ix];
@@ -360,13 +392,15 @@ static int mlx5e_hairpin_create_indirect_tirs(struct mlx5e_hairpin *hp)
 	void *tirc;
 
 	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		struct mlx5e_tirc_config ttconfig = mlx5e_tirc_get_default_config(tt);
+
 		memset(in, 0, MLX5_ST_SZ_BYTES(create_tir_in));
 		tirc = MLX5_ADDR_OF(create_tir_in, in, ctx);
 
 		MLX5_SET(tirc, tirc, transport_domain, hp->tdn);
 		MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_INDIRECT);
 		MLX5_SET(tirc, tirc, indirect_table, hp->indir_rqt.rqtn);
-		mlx5e_build_indir_tir_ctx_hash(&priv->channels.params, tt, tirc, false);
+		mlx5e_build_indir_tir_ctx_hash(&priv->rss_params, &ttconfig, tirc, false);
 
 		err = mlx5_core_create_tir(hp->func_mdev, in,
 					   MLX5_ST_SZ_BYTES(create_tir_in), &hp->indir_tirn[tt]);
@@ -569,7 +603,7 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow_parse_attr *parse_attr,
 				  struct netlink_ext_ack *extack)
 {
-	int peer_ifindex = parse_attr->mirred_ifindex;
+	int peer_ifindex = parse_attr->mirred_ifindex[0];
 	struct mlx5_hairpin_params params;
 	struct mlx5_core_dev *peer_mdev;
 	struct mlx5e_hairpin_entry *hpe;
@@ -802,7 +836,7 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 	mlx5_del_flow_rules(flow->rule[0]);
 	mlx5_fc_destroy(priv->mdev, counter);
 
-	if (!mlx5e_tc_num_filters(priv) && priv->fs.tc.t) {
+	if (!mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD)  && priv->fs.tc.t) {
 		mlx5_destroy_flow_table(priv->fs.tc.t);
 		priv->fs.tc.t = NULL;
 	}
@@ -815,14 +849,15 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv,
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow);
+			       struct mlx5e_tc_flow *flow, int out_index);
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
-			      struct ip_tunnel_info *tun_info,
+			      struct mlx5e_tc_flow *flow,
 			      struct net_device *mirred_dev,
+			      int out_index,
+			      struct netlink_ext_ack *extack,
 			      struct net_device **encap_dev,
-			      struct mlx5e_tc_flow *flow,
-			      struct netlink_ext_ack *extack);
+			      bool *encap_valid);
 
 static struct mlx5_flow_handle *
 mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
@@ -836,7 +871,7 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 	if (IS_ERR(rule))
 		return rule;
 
-	if (attr->mirror_count) {
+	if (attr->split_count) {
 		flow->rule[1] = mlx5_eswitch_add_fwd_rule(esw, spec, attr);
 		if (IS_ERR(flow->rule[1])) {
 			mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
@@ -855,7 +890,7 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 {
 	flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED;
 
-	if (attr->mirror_count)
+	if (attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
 	mlx5_eswitch_del_offloaded_rule(esw, flow->rule[0], attr);
@@ -871,7 +906,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 
 	memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	slow_attr->mirror_count = 0;
+	slow_attr->split_count = 0;
 	slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN;
 
 	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
@@ -888,27 +923,49 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 {
 	memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	slow_attr->mirror_count = 0;
+	slow_attr->split_count = 0;
 	slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN;
 	mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
 	flow->flags &= ~MLX5E_TC_FLOW_SLOW;
 }
 
+static void add_unready_flow(struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_rep_uplink_priv *uplink_priv;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5_eswitch *esw;
+
+	esw = flow->priv->mdev->priv.eswitch;
+	rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
+	uplink_priv = &rpriv->uplink_priv;
+
+	flow->flags |= MLX5E_TC_FLOW_NOT_READY;
+	list_add_tail(&flow->unready, &uplink_priv->unready_flows);
+}
+
+static void remove_unready_flow(struct mlx5e_tc_flow *flow)
+{
+	list_del(&flow->unready);
+	flow->flags &= ~MLX5E_TC_FLOW_NOT_READY;
+}
+
 static int
 mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
-		      struct mlx5e_tc_flow_parse_attr *parse_attr,
 		      struct mlx5e_tc_flow *flow,
 		      struct netlink_ext_ack *extack)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	u32 max_chain = mlx5_eswitch_get_chain_range(esw);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
 	u16 max_prio = mlx5_eswitch_get_prio_range(esw);
 	struct net_device *out_dev, *encap_dev = NULL;
 	struct mlx5_fc *counter = NULL;
 	struct mlx5e_rep_priv *rpriv;
 	struct mlx5e_priv *out_priv;
-	int err = 0, encap_err = 0;
+	bool encap_valid = true;
+	int err = 0;
+	int out_index;
 
 	if (!mlx5_eswitch_prios_supported(esw) && attr->prio != 1) {
 		NL_SET_ERR_MSG(extack, "E-switch priorities unsupported, upgrade FW");
@@ -927,20 +984,24 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		goto err_max_prio_chain;
 	}
 
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		int mirred_ifindex;
+
+		if (!(attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+			continue;
+
+		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
 		out_dev = __dev_get_by_index(dev_net(priv->netdev),
-					     attr->parse_attr->mirred_ifindex);
-		encap_err = mlx5e_attach_encap(priv, &parse_attr->tun_info,
-					       out_dev, &encap_dev, flow,
-					       extack);
-		if (encap_err && encap_err != -EAGAIN) {
-			err = encap_err;
+					     mirred_ifindex);
+		err = mlx5e_attach_encap(priv, flow, out_dev, out_index,
+					 extack, &encap_dev, &encap_valid);
+		if (err)
 			goto err_attach_encap;
-		}
+
 		out_priv = netdev_priv(encap_dev);
 		rpriv = out_priv->ppriv;
-		attr->out_rep[attr->out_count] = rpriv->rep;
-		attr->out_mdev[attr->out_count++] = out_priv->mdev;
+		attr->dests[out_index].rep = rpriv->rep;
+		attr->dests[out_index].mdev = out_priv->mdev;
 	}
 
 	err = mlx5_eswitch_add_vlan_action(esw, attr);
@@ -955,7 +1016,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	}
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) {
-		counter = mlx5_fc_create(esw->dev, true);
+		counter = mlx5_fc_create(attr->counter_dev, true);
 		if (IS_ERR(counter)) {
 			err = PTR_ERR(counter);
 			goto err_create_counter;
@@ -964,10 +1025,11 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		attr->counter = counter;
 	}
 
-	/* we get here if (1) there's no error or when
-	 * (2) there's an encap action and we're on -EAGAIN (no valid neigh)
+	/* we get here if one of the following takes place:
+	 * (1) there's no error
+	 * (2) there's an encap action and we don't have valid neigh
 	 */
-	if (encap_err == -EAGAIN) {
+	if (!encap_valid) {
 		/* continue with goto slow path rule instead */
 		struct mlx5_esw_flow_attr slow_attr;
 
@@ -984,15 +1046,16 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	return 0;
 
 err_add_rule:
-	mlx5_fc_destroy(esw->dev, counter);
+	mlx5_fc_destroy(attr->counter_dev, counter);
 err_create_counter:
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
 err_mod_hdr:
 	mlx5_eswitch_del_vlan_action(esw, attr);
 err_add_vlan:
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
-		mlx5e_detach_encap(priv, flow);
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+			mlx5e_detach_encap(priv, flow, out_index);
 err_attach_encap:
 err_max_prio_chain:
 	return err;
@@ -1004,6 +1067,13 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5_esw_flow_attr slow_attr;
+	int out_index;
+
+	if (flow->flags & MLX5E_TC_FLOW_NOT_READY) {
+		remove_unready_flow(flow);
+		kvfree(attr->parse_attr);
+		return;
+	}
 
 	if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 		if (flow->flags & MLX5E_TC_FLOW_SLOW)
@@ -1014,16 +1084,16 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 
 	mlx5_eswitch_del_vlan_action(esw, attr);
 
-	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) {
-		mlx5e_detach_encap(priv, flow);
-		kvfree(attr->parse_attr);
-	}
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++)
+		if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP)
+			mlx5e_detach_encap(priv, flow, out_index);
+	kvfree(attr->parse_attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		mlx5e_detach_mod_hdr(priv, flow);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
-		mlx5_fc_destroy(esw->dev, attr->counter);
+		mlx5_fc_destroy(attr->counter_dev, attr->counter);
 }
 
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
@@ -1033,10 +1103,12 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr slow_attr, *esw_attr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
+	struct encap_flow_item *efi;
 	struct mlx5e_tc_flow *flow;
 	int err;
 
-	err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type,
+	err = mlx5_packet_reformat_alloc(priv->mdev,
+					 e->reformat_type,
 					 e->encap_size, e->encap_header,
 					 MLX5_FLOW_NAMESPACE_FDB,
 					 &e->encap_id);
@@ -1048,11 +1120,31 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
 	e->flags |= MLX5_ENCAP_ENTRY_VALID;
 	mlx5e_rep_queue_neigh_stats_work(priv);
 
-	list_for_each_entry(flow, &e->flows, encap) {
+	list_for_each_entry(efi, &e->flows, list) {
+		bool all_flow_encaps_valid = true;
+		int i;
+
+		flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]);
 		esw_attr = flow->esw_attr;
-		esw_attr->encap_id = e->encap_id;
 		spec = &esw_attr->parse_attr->spec;
 
+		esw_attr->dests[efi->index].encap_id = e->encap_id;
+		esw_attr->dests[efi->index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+		/* Flow can be associated with multiple encap entries.
+		 * Before offloading the flow verify that all of them have
+		 * a valid neighbour.
+		 */
+		for (i = 0; i < MLX5_MAX_FLOW_FWD_VPORTS; i++) {
+			if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP))
+				continue;
+			if (!(esw_attr->dests[i].flags & MLX5_ESW_DEST_ENCAP_VALID)) {
+				all_flow_encaps_valid = false;
+				break;
+			}
+		}
+		/* Do not offload flows with unresolved neighbors */
+		if (!all_flow_encaps_valid)
+			continue;
 		/* update from slow path rule to encap rule */
 		rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, esw_attr);
 		if (IS_ERR(rule)) {
@@ -1075,14 +1167,18 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 	struct mlx5_esw_flow_attr slow_attr;
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_spec *spec;
+	struct encap_flow_item *efi;
 	struct mlx5e_tc_flow *flow;
 	int err;
 
-	list_for_each_entry(flow, &e->flows, encap) {
+	list_for_each_entry(efi, &e->flows, list) {
+		flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]);
 		spec = &flow->esw_attr->parse_attr->spec;
 
 		/* update from encap rule to slow path rule */
 		rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec, &slow_attr);
+		/* mark the flow's encap dest as non-valid */
+		flow->esw_attr->dests[efi->index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID;
 
 		if (IS_ERR(rule)) {
 			err = PTR_ERR(rule);
@@ -1130,9 +1226,12 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		return;
 
 	list_for_each_entry(e, &nhe->encap_list, encap_list) {
+		struct encap_flow_item *efi;
 		if (!(e->flags & MLX5_ENCAP_ENTRY_VALID))
 			continue;
-		list_for_each_entry(flow, &e->flows, encap) {
+		list_for_each_entry(efi, &e->flows, list) {
+			flow = container_of(efi, struct mlx5e_tc_flow,
+					    encaps[efi->index]);
 			if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
 				counter = mlx5e_tc_get_counter(flow);
 				mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
@@ -1162,11 +1261,11 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 }
 
 static void mlx5e_detach_encap(struct mlx5e_priv *priv,
-			       struct mlx5e_tc_flow *flow)
+			       struct mlx5e_tc_flow *flow, int out_index)
 {
-	struct list_head *next = flow->encap.next;
+	struct list_head *next = flow->encaps[out_index].list.next;
 
-	list_del(&flow->encap);
+	list_del(&flow->encaps[out_index].list);
 	if (list_empty(next)) {
 		struct mlx5e_encap_entry *e;
 
@@ -1182,177 +1281,137 @@ static void mlx5e_detach_encap(struct mlx5e_priv *priv,
 	}
 }
 
-static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
-			      struct mlx5e_tc_flow *flow)
+static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
 {
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
-		mlx5e_tc_del_fdb_flow(priv, flow);
-	else
-		mlx5e_tc_del_nic_flow(priv, flow);
+	struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch;
+
+	if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) ||
+	    !(flow->flags & MLX5E_TC_FLOW_DUP))
+		return;
+
+	mutex_lock(&esw->offloads.peer_mutex);
+	list_del(&flow->peer);
+	mutex_unlock(&esw->offloads.peer_mutex);
+
+	flow->flags &= ~MLX5E_TC_FLOW_DUP;
+
+	mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow);
+	kvfree(flow->peer_flow);
+	flow->peer_flow = NULL;
 }
 
-static void parse_vxlan_attr(struct mlx5_flow_spec *spec,
-			     struct tc_cls_flower_offload *f)
+static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow)
 {
-	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				       outer_headers);
-	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				       outer_headers);
-	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    misc_parameters);
-	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				    misc_parameters);
+	struct mlx5_core_dev *dev = flow->priv->mdev;
+	struct mlx5_devcom *devcom = dev->priv.devcom;
+	struct mlx5_eswitch *peer_esw;
 
-	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
-	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP);
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return;
+
+	__mlx5e_tc_del_fdb_peer_flow(flow);
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
-		struct flow_dissector_key_keyid *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->key);
-		struct flow_dissector_key_keyid *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_KEYID,
-						  f->mask);
-		MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni,
-			 be32_to_cpu(mask->keyid));
-		MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni,
-			 be32_to_cpu(key->keyid));
+static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
+			      struct mlx5e_tc_flow *flow)
+{
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
+		mlx5e_tc_del_fdb_peer_flow(flow);
+		mlx5e_tc_del_fdb_flow(priv, flow);
+	} else {
+		mlx5e_tc_del_nic_flow(priv, flow);
 	}
 }
 
+
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5_flow_spec *spec,
-			     struct tc_cls_flower_offload *f)
+			     struct tc_cls_flower_offload *f,
+			     struct net_device *filter_dev, u8 *match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 				       outer_headers);
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_match_control enc_control;
+	int err;
 
-	struct flow_dissector_key_control *enc_control =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-					  f->key);
-
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  f->mask);
-
-		/* Full udp dst port must be given */
-		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
-			goto vxlan_match_offload_err;
-
-		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
-		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
-			parse_vxlan_attr(spec, f);
-		else {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "port isn't an offloaded vxlan udp dport");
-			netdev_warn(priv->netdev,
-				    "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->dst));
-			return -EOPNOTSUPP;
-		}
-
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-			 udp_dport, ntohs(mask->dst));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-			 udp_dport, ntohs(key->dst));
-
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-			 udp_sport, ntohs(mask->src));
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-			 udp_sport, ntohs(key->src));
-	} else { /* udp dst port must be given */
-vxlan_match_offload_err:
+	err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f,
+				 headers_c, headers_v, match_level);
+	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "IP tunnel decap offload supported only for vxlan, must set UDP dport");
-		netdev_warn(priv->netdev,
-			    "IP tunnel decap offload supported only for vxlan, must set UDP dport\n");
-		return -EOPNOTSUPP;
+				   "failed to parse tunnel attributes");
+		return err;
 	}
 
-	if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-						  f->mask);
+	flow_rule_match_enc_control(rule, &enc_control);
+
+	if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_enc_ipv4_addrs(rule, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 src_ipv4_src_ipv6.ipv4_layout.ipv4,
-			 ntohl(mask->src));
+			 ntohl(match.mask->src));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
 			 src_ipv4_src_ipv6.ipv4_layout.ipv4,
-			 ntohl(key->src));
+			 ntohl(match.key->src));
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(mask->dst));
+			 ntohl(match.mask->dst));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v,
 			 dst_ipv4_dst_ipv6.ipv4_layout.ipv4,
-			 ntohl(key->dst));
+			 ntohl(match.key->dst));
 
 		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP);
-	} else if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS,
-						  f->mask);
+	} else if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_match_ipv6_addrs match;
 
+		flow_rule_match_enc_ipv6_addrs(rule, &match);
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
+		       &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6));
 
 		MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
-		struct flow_dissector_key_ip *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IP,
-						  f->key);
-		struct flow_dissector_key_ip *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IP,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_match_ip match;
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+		flow_rule_match_enc_ip(rule, &match);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn,
+			 match.mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn,
+			 match.key->tos & 0x3);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp,
+			 match.mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp,
+			 match.key->tos  >> 2);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit,
+			 match.mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit,
+			 match.key->ttl);
 
-		if (mask->ttl &&
+		if (match.mask->ttl &&
 		    !MLX5_CAP_ESW_FLOWTABLE_FDB
 			(priv->mdev,
 			 ft_field_support.outer_ipv4_ttl)) {
@@ -1381,7 +1440,8 @@ vxlan_match_offload_err:
 static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
 			      struct tc_cls_flower_offload *f,
-			      u8 *match_level)
+			      struct net_device *filter_dev,
+			      u8 *match_level, u8 *tunnel_match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
@@ -1392,12 +1452,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				    misc_parameters);
 	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    misc_parameters);
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 
 	*match_level = MLX5_MATCH_NONE;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -1416,23 +1478,21 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_IP))) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported key");
 		netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
-			    f->dissector->used_keys);
+			    dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
-	if ((dissector_uses_key(f->dissector,
-				FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) ||
-	     dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) ||
-	     dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) &&
-	    dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-						  f->key);
-		switch (key->addr_type) {
+	if ((flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) ||
+	     flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID) ||
+	     flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) &&
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_enc_control(rule, &match);
+		switch (match.key->addr_type) {
 		case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
 		case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
-			if (parse_tunnel_attr(priv, spec, f))
+			if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level))
 				return -EOPNOTSUPP;
 			break;
 		default:
@@ -1448,35 +1508,27 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 					 inner_headers);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype,
-			 ntohs(mask->n_proto));
+			 ntohs(match.mask->n_proto));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype,
-			 ntohs(key->n_proto));
+			 ntohs(match.key->n_proto));
 
-		if (mask->n_proto)
+		if (match.mask->n_proto)
 			*match_level = MLX5_MATCH_L2;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
-			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_id ||
+		    match.mask->vlan_priority ||
+		    match.mask->vlan_tpid) {
+			if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
 				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
 					 svlan_tag, 1);
 				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
@@ -1488,11 +1540,15 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 					 cvlan_tag, 1);
 			}
 
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid,
+				 match.mask->vlan_id);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid,
+				 match.key->vlan_id);
 
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio,
+				 match.mask->vlan_priority);
+			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio,
+				 match.key->vlan_priority);
 
 			*match_level = MLX5_MATCH_L2;
 		}
@@ -1502,17 +1558,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		*match_level = MLX5_MATCH_L2;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CVLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CVLAN,
-						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
-			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
+		if (match.mask->vlan_id ||
+		    match.mask->vlan_priority ||
+		    match.mask->vlan_tpid) {
+			if (match.key->vlan_tpid == htons(ETH_P_8021AD)) {
 				MLX5_SET(fte_match_set_misc, misc_c,
 					 outer_second_svlan_tag, 1);
 				MLX5_SET(fte_match_set_misc, misc_v,
@@ -1525,69 +1578,58 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			}
 
 			MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid,
-				 mask->vlan_id);
+				 match.mask->vlan_id);
 			MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid,
-				 key->vlan_id);
+				 match.key->vlan_id);
 			MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio,
-				 mask->vlan_priority);
+				 match.mask->vlan_priority);
 			MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio,
-				 key->vlan_priority);
+				 match.key->vlan_priority);
 
 			*match_level = MLX5_MATCH_L2;
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
+		flow_rule_match_eth_addrs(rule, &match);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 					     dmac_47_16),
-				mask->dst);
+				match.mask->dst);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 					     dmac_47_16),
-				key->dst);
+				match.key->dst);
 
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 					     smac_47_16),
-				mask->src);
+				match.mask->src);
 		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 					     smac_47_16),
-				key->src);
+				match.key->src);
 
-		if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst))
+		if (!is_zero_ether_addr(match.mask->src) ||
+		    !is_zero_ether_addr(match.mask->dst))
 			*match_level = MLX5_MATCH_L2;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
 
-		struct flow_dissector_key_control *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->mask);
-		addr_type = key->addr_type;
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 
 		/* the HW doesn't support frag first/later */
-		if (mask->flags & FLOW_DIS_FIRST_FRAG)
+		if (match.mask->flags & FLOW_DIS_FIRST_FRAG)
 			return -EOPNOTSUPP;
 
-		if (mask->flags & FLOW_DIS_IS_FRAGMENT) {
+		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) {
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag,
-				 key->flags & FLOW_DIS_IS_FRAGMENT);
+				 match.key->flags & FLOW_DIS_IS_FRAGMENT);
 
 			/* the HW doesn't need L3 inline to match on frag=no */
-			if (!(key->flags & FLOW_DIS_IS_FRAGMENT))
+			if (!(match.key->flags & FLOW_DIS_IS_FRAGMENT))
 				*match_level = MLX5_MATCH_L2;
 	/* ***  L2 attributes parsing up to here *** */
 			else
@@ -1595,102 +1637,85 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-		ip_proto = key->ip_proto;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		ip_proto = match.key->ip_proto;
 
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol,
-			 mask->ip_proto);
+			 match.mask->ip_proto);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
-			 key->ip_proto);
+			 match.key->ip_proto);
 
-		if (mask->ip_proto)
+		if (match.mask->ip_proto)
 			*match_level = MLX5_MATCH_L3;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
-		struct flow_dissector_key_ipv4_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv4_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						  f->mask);
+		struct flow_match_ipv4_addrs match;
 
+		flow_rule_match_ipv4_addrs(rule, &match);
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
-		       &mask->src, sizeof(mask->src));
+		       &match.mask->src, sizeof(match.mask->src));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
-		       &key->src, sizeof(key->src));
+		       &match.key->src, sizeof(match.key->src));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-		       &mask->dst, sizeof(mask->dst));
+		       &match.mask->dst, sizeof(match.mask->dst));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-		       &key->dst, sizeof(key->dst));
+		       &match.key->dst, sizeof(match.key->dst));
 
-		if (mask->src || mask->dst)
+		if (match.mask->src || match.mask->dst)
 			*match_level = MLX5_MATCH_L3;
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
-		struct flow_dissector_key_ipv6_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->key);
-		struct flow_dissector_key_ipv6_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						  f->mask);
+		struct flow_match_ipv6_addrs match;
 
+		flow_rule_match_ipv6_addrs(rule, &match);
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &mask->src, sizeof(mask->src));
+		       &match.mask->src, sizeof(match.mask->src));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    src_ipv4_src_ipv6.ipv6_layout.ipv6),
-		       &key->src, sizeof(key->src));
+		       &match.key->src, sizeof(match.key->src));
 
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &mask->dst, sizeof(mask->dst));
+		       &match.mask->dst, sizeof(match.mask->dst));
 		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v,
 				    dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
-		       &key->dst, sizeof(key->dst));
+		       &match.key->dst, sizeof(match.key->dst));
 
-		if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY ||
-		    ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY)
+		if (ipv6_addr_type(&match.mask->src) != IPV6_ADDR_ANY ||
+		    ipv6_addr_type(&match.mask->dst) != IPV6_ADDR_ANY)
 			*match_level = MLX5_MATCH_L3;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) {
-		struct flow_dissector_key_ip *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IP,
-						  f->key);
-		struct flow_dissector_key_ip *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_IP,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match;
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+		flow_rule_match_ip(rule, &match);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn,
+			 match.mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn,
+			 match.key->tos & 0x3);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp,
+			 match.mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp,
+			 match.key->tos  >> 2);
 
-		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
-		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit,
+			 match.mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit,
+			 match.key->ttl);
 
-		if (mask->ttl &&
+		if (match.mask->ttl &&
 		    !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev,
 						ft_field_support.outer_ipv4_ttl)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1698,44 +1723,39 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			return -EOPNOTSUPP;
 		}
 
-		if (mask->tos || mask->ttl)
+		if (match.mask->tos || match.mask->ttl)
 			*match_level = MLX5_MATCH_L3;
 	}
 
 	/* ***  L3 attributes parsing up to here *** */
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->key);
-		struct flow_dissector_key_ports *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_PORTS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
 		switch (ip_proto) {
 		case IPPROTO_TCP:
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 tcp_sport, ntohs(mask->src));
+				 tcp_sport, ntohs(match.mask->src));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 tcp_sport, ntohs(key->src));
+				 tcp_sport, ntohs(match.key->src));
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 tcp_dport, ntohs(mask->dst));
+				 tcp_dport, ntohs(match.mask->dst));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 tcp_dport, ntohs(key->dst));
+				 tcp_dport, ntohs(match.key->dst));
 			break;
 
 		case IPPROTO_UDP:
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 udp_sport, ntohs(mask->src));
+				 udp_sport, ntohs(match.mask->src));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 udp_sport, ntohs(key->src));
+				 udp_sport, ntohs(match.key->src));
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c,
-				 udp_dport, ntohs(mask->dst));
+				 udp_dport, ntohs(match.mask->dst));
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v,
-				 udp_dport, ntohs(key->dst));
+				 udp_dport, ntohs(match.key->dst));
 			break;
 		default:
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1745,26 +1765,20 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			return -EINVAL;
 		}
 
-		if (mask->src || mask->dst)
+		if (match.mask->src || match.mask->dst)
 			*match_level = MLX5_MATCH_L4;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) {
-		struct flow_dissector_key_tcp *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_TCP,
-						  f->key);
-		struct flow_dissector_key_tcp *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_TCP,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
+		struct flow_match_tcp match;
 
+		flow_rule_match_tcp(rule, &match);
 		MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags,
-			 ntohs(mask->flags));
+			 ntohs(match.mask->flags));
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_flags,
-			 ntohs(key->flags));
+			 ntohs(match.key->flags));
 
-		if (mask->flags)
+		if (match.mask->flags)
 			*match_level = MLX5_MATCH_L4;
 	}
 
@@ -1774,21 +1788,22 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 static int parse_cls_flower(struct mlx5e_priv *priv,
 			    struct mlx5e_tc_flow *flow,
 			    struct mlx5_flow_spec *spec,
-			    struct tc_cls_flower_offload *f)
+			    struct tc_cls_flower_offload *f,
+			    struct net_device *filter_dev)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	u8 match_level, tunnel_match_level = MLX5_MATCH_NONE;
 	struct mlx5_eswitch_rep *rep;
-	u8 match_level;
 	int err;
 
-	err = __parse_cls_flower(priv, spec, f, &match_level);
+	err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level);
 
 	if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) {
 		rep = rpriv->rep;
-		if (rep->vport != FDB_UPLINK_VPORT &&
+		if (rep->vport != MLX5_VPORT_UPLINK &&
 		    (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE &&
 		    esw->offloads.inline_mode < match_level)) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1800,10 +1815,12 @@ static int parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
-	if (flow->flags & MLX5E_TC_FLOW_ESWITCH)
+	if (flow->flags & MLX5E_TC_FLOW_ESWITCH) {
 		flow->esw_attr->match_level = match_level;
-	else
+		flow->esw_attr->tunnel_match_level = tunnel_match_level;
+	} else {
 		flow->nic_attr->match_level = match_level;
+	}
 
 	return err;
 }
@@ -1816,27 +1833,29 @@ struct pedit_headers {
 	struct udphdr  udp;
 };
 
+struct pedit_headers_action {
+	struct pedit_headers	vals;
+	struct pedit_headers	masks;
+	u32			pedits;
+};
+
 static int pedit_header_offsets[] = {
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
-	[TCA_PEDIT_KEY_EX_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
+	[FLOW_ACT_MANGLE_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth),
+	[FLOW_ACT_MANGLE_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4),
+	[FLOW_ACT_MANGLE_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6),
+	[FLOW_ACT_MANGLE_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp),
+	[FLOW_ACT_MANGLE_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp),
 };
 
 #define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype])
 
 static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset,
-			 struct pedit_headers *masks,
-			 struct pedit_headers *vals)
+			 struct pedit_headers_action *hdrs)
 {
 	u32 *curr_pmask, *curr_pval;
 
-	if (hdr_type >= __PEDIT_HDR_TYPE_MAX)
-		goto out_err;
-
-	curr_pmask = (u32 *)(pedit_header(masks, hdr_type) + offset);
-	curr_pval  = (u32 *)(pedit_header(vals, hdr_type) + offset);
+	curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset);
+	curr_pval  = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset);
 
 	if (*curr_pmask & mask)  /* disallow acting twice on the same location */
 		goto out_err;
@@ -1888,12 +1907,11 @@ static struct mlx5_fields fields[] = {
 	OFFLOAD(UDP_DPORT, 2, udp.dest,   0),
 };
 
-/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at
- * max from the SW pedit action. On success, it says how many HW actions were
- * actually parsed.
+/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
+ * max from the SW pedit action. On success, attr->num_mod_hdr_actions
+ * says how many HW actions were actually parsed.
  */
-static int offload_pedit_fields(struct pedit_headers *masks,
-				struct pedit_headers *vals,
+static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct netlink_ext_ack *extack)
 {
@@ -1908,15 +1926,17 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 	__be16 mask_be16;
 	void *action;
 
-	set_masks = &masks[TCA_PEDIT_KEY_EX_CMD_SET];
-	add_masks = &masks[TCA_PEDIT_KEY_EX_CMD_ADD];
-	set_vals = &vals[TCA_PEDIT_KEY_EX_CMD_SET];
-	add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD];
+	set_masks = &hdrs[0].masks;
+	add_masks = &hdrs[1].masks;
+	set_vals = &hdrs[0].vals;
+	add_vals = &hdrs[1].vals;
 
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
-	action = parse_attr->mod_hdr_actions;
-	max_actions = parse_attr->num_mod_hdr_actions;
-	nactions = 0;
+	action = parse_attr->mod_hdr_actions +
+		 parse_attr->num_mod_hdr_actions * action_size;
+
+	max_actions = parse_attr->max_mod_hdr_actions;
+	nactions = parse_attr->num_mod_hdr_actions;
 
 	for (i = 0; i < ARRAY_SIZE(fields); i++) {
 		f = &fields[i];
@@ -2007,12 +2027,14 @@ static int offload_pedit_fields(struct pedit_headers *masks,
 }
 
 static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
-				 const struct tc_action *a, int namespace,
+				 struct pedit_headers_action *hdrs,
+				 int namespace,
 				 struct mlx5e_tc_flow_parse_attr *parse_attr)
 {
 	int nkeys, action_size, max_actions;
 
-	nkeys = tcf_pedit_nkeys(a);
+	nkeys = hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits +
+		hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits;
 	action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto);
 
 	if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */
@@ -2027,62 +2049,67 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv,
 	if (!parse_attr->mod_hdr_actions)
 		return -ENOMEM;
 
-	parse_attr->num_mod_hdr_actions = max_actions;
+	parse_attr->max_mod_hdr_actions = max_actions;
 	return 0;
 }
 
 static const struct pedit_headers zero_masks = {};
 
 static int parse_tc_pedit_action(struct mlx5e_priv *priv,
-				 const struct tc_action *a, int namespace,
+				 const struct flow_action_entry *act, int namespace,
 				 struct mlx5e_tc_flow_parse_attr *parse_attr,
+				 struct pedit_headers_action *hdrs,
 				 struct netlink_ext_ack *extack)
 {
-	struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks;
-	int nkeys, i, err = -EOPNOTSUPP;
+	u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1;
+	int err = -EOPNOTSUPP;
 	u32 mask, val, offset;
-	u8 cmd, htype;
+	u8 htype;
 
-	nkeys = tcf_pedit_nkeys(a);
+	htype = act->mangle.htype;
+	err = -EOPNOTSUPP; /* can't be all optimistic */
 
-	memset(masks, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
-	memset(vals,  0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX);
+	if (htype == FLOW_ACT_MANGLE_UNSPEC) {
+		NL_SET_ERR_MSG_MOD(extack, "legacy pedit isn't offloaded");
+		goto out_err;
+	}
 
-	for (i = 0; i < nkeys; i++) {
-		htype = tcf_pedit_htype(a, i);
-		cmd = tcf_pedit_cmd(a, i);
-		err = -EOPNOTSUPP; /* can't be all optimistic */
+	mask = act->mangle.mask;
+	val = act->mangle.val;
+	offset = act->mangle.offset;
 
-		if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "legacy pedit isn't offloaded");
-			goto out_err;
-		}
+	err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd]);
+	if (err)
+		goto out_err;
 
-		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) {
-			NL_SET_ERR_MSG_MOD(extack, "pedit cmd isn't offloaded");
-			goto out_err;
-		}
+	hdrs[cmd].pedits++;
+
+	return 0;
+out_err:
+	return err;
+}
 
-		mask = tcf_pedit_mask(a, i);
-		val = tcf_pedit_val(a, i);
-		offset = tcf_pedit_offset(a, i);
+static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace,
+				 struct mlx5e_tc_flow_parse_attr *parse_attr,
+				 struct pedit_headers_action *hdrs,
+				 struct netlink_ext_ack *extack)
+{
+	struct pedit_headers *cmd_masks;
+	int err;
+	u8 cmd;
 
-		err = set_pedit_val(htype, ~mask, val, offset, &masks[cmd], &vals[cmd]);
+	if (!parse_attr->mod_hdr_actions) {
+		err = alloc_mod_hdr_actions(priv, hdrs, namespace, parse_attr);
 		if (err)
 			goto out_err;
 	}
 
-	err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr);
-	if (err)
-		goto out_err;
-
-	err = offload_pedit_fields(masks, vals, parse_attr, extack);
+	err = offload_pedit_fields(hdrs, parse_attr, extack);
 	if (err < 0)
 		goto out_dealloc_parsed_actions;
 
 	for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) {
-		cmd_masks = &masks[cmd];
+		cmd_masks = &hdrs[cmd].masks;
 		if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "attempt to offload an unsupported field");
@@ -2131,19 +2158,69 @@ static bool csum_offload_supported(struct mlx5e_priv *priv,
 	return true;
 }
 
+struct ip_ttl_word {
+	__u8	ttl;
+	__u8	protocol;
+	__sum16	check;
+};
+
+struct ipv6_hoplimit_word {
+	__be16	payload_len;
+	__u8	nexthdr;
+	__u8	hop_limit;
+};
+
+static bool is_action_keys_supported(const struct flow_action_entry *act)
+{
+	u32 mask, offset;
+	u8 htype;
+
+	htype = act->mangle.htype;
+	offset = act->mangle.offset;
+	mask = ~act->mangle.mask;
+	/* For IPv4 & IPv6 header check 4 byte word,
+	 * to determine that modified fields
+	 * are NOT ttl & hop_limit only.
+	 */
+	if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4) {
+		struct ip_ttl_word *ttl_word =
+			(struct ip_ttl_word *)&mask;
+
+		if (offset != offsetof(struct iphdr, ttl) ||
+		    ttl_word->protocol ||
+		    ttl_word->check) {
+			return true;
+		}
+	} else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
+		struct ipv6_hoplimit_word *hoplimit_word =
+			(struct ipv6_hoplimit_word *)&mask;
+
+		if (offset != offsetof(struct ipv6hdr, payload_len) ||
+		    hoplimit_word->payload_len ||
+		    hoplimit_word->nexthdr) {
+			return true;
+		}
+	}
+	return false;
+}
+
 static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
-					  struct tcf_exts *exts,
+					  struct flow_action *flow_action,
+					  u32 actions,
 					  struct netlink_ext_ack *extack)
 {
-	const struct tc_action *a;
+	const struct flow_action_entry *act;
 	bool modify_ip_header;
-	LIST_HEAD(actions);
-	u8 htype, ip_proto;
 	void *headers_v;
 	u16 ethertype;
-	int nkeys, i;
+	u8 ip_proto;
+	int i;
+
+	if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP)
+		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers);
+	else
+		headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
 
-	headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers);
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
 
 	/* for non-IP we only re-write MACs, so we're okay */
@@ -2151,20 +2228,14 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 		goto out_ok;
 
 	modify_ip_header = false;
-	tcf_exts_for_each_action(i, a, exts) {
-		int k;
-
-		if (!is_tcf_pedit(a))
+	flow_action_for_each(i, act, flow_action) {
+		if (act->id != FLOW_ACTION_MANGLE &&
+		    act->id != FLOW_ACTION_ADD)
 			continue;
 
-		nkeys = tcf_pedit_nkeys(a);
-		for (k = 0; k < nkeys; k++) {
-			htype = tcf_pedit_htype(a, k);
-			if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 ||
-			    htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) {
-				modify_ip_header = true;
-				break;
-			}
+		if (is_action_keys_supported(act)) {
+			modify_ip_header = true;
+			break;
 		}
 	}
 
@@ -2182,7 +2253,7 @@ out_ok:
 }
 
 static bool actions_match_supported(struct mlx5e_priv *priv,
-				    struct tcf_exts *exts,
+				    struct flow_action *flow_action,
 				    struct mlx5e_tc_flow_parse_attr *parse_attr,
 				    struct mlx5e_tc_flow *flow,
 				    struct netlink_ext_ack *extack)
@@ -2199,7 +2270,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 		return false;
 
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
-		return modify_header_match_supported(&parse_attr->spec, exts,
+		return modify_header_match_supported(&parse_attr->spec,
+						     flow_action, actions,
 						     extack);
 
 	return true;
@@ -2219,57 +2291,54 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv)
 	return (fsystem_guid == psystem_guid);
 }
 
-static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+static int parse_tc_nic_actions(struct mlx5e_priv *priv,
+				struct flow_action *flow_action,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
 	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
-	const struct tc_action *a;
-	LIST_HEAD(actions);
+	struct pedit_headers_action hdrs[2] = {};
+	const struct flow_action_entry *act;
 	u32 action = 0;
 	int err, i;
 
-	if (!tcf_exts_has_actions(exts))
+	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
 	attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 
-	tcf_exts_for_each_action(i, a, exts) {
-		if (is_tcf_gact_shot(a)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DROP;
 			if (MLX5_CAP_FLOWTABLE(priv->mdev,
 					       flow_table_properties_nic_receive.flow_counter))
 				action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
-			continue;
-		}
-
-		if (is_tcf_pedit(a)) {
-			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL,
-						    parse_attr, extack);
+			break;
+		case FLOW_ACTION_MANGLE:
+		case FLOW_ACTION_ADD:
+			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_KERNEL,
+						    parse_attr, hdrs, extack);
 			if (err)
 				return err;
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR |
 				  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-			continue;
-		}
-
-		if (is_tcf_csum(a)) {
+			break;
+		case FLOW_ACTION_CSUM:
 			if (csum_offload_supported(priv, action,
-						   tcf_csum_update_flags(a),
+						   act->csum_flags,
 						   extack))
-				continue;
+				break;
 
 			return -EOPNOTSUPP;
-		}
-
-		if (is_tcf_mirred_egress_redirect(a)) {
-			struct net_device *peer_dev = tcf_mirred_dev(a);
+		case FLOW_ACTION_REDIRECT: {
+			struct net_device *peer_dev = act->dev;
 
 			if (priv->netdev->netdev_ops == peer_dev->netdev_ops &&
 			    same_hw_devs(priv, netdev_priv(peer_dev))) {
-				parse_attr->mirred_ifindex = peer_dev->ifindex;
+				parse_attr->mirred_ifindex[0] = peer_dev->ifindex;
 				flow->flags |= MLX5E_TC_FLOW_HAIRPIN;
 				action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
@@ -2280,11 +2349,10 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 					    peer_dev->name);
 				return -EINVAL;
 			}
-			continue;
-		}
-
-		if (is_tcf_skbedit_mark(a)) {
-			u32 mark = tcf_skbedit_mark(a);
+			}
+			break;
+		case FLOW_ACTION_MARK: {
+			u32 mark = act->mark;
 
 			if (mark & ~MLX5E_TC_FLOW_ID_MASK) {
 				NL_SET_ERR_MSG_MOD(extack,
@@ -2294,70 +2362,47 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 
 			attr->flow_tag = mark;
 			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-			continue;
+			}
+			break;
+		default:
+			return -EINVAL;
 		}
+	}
 
-		return -EINVAL;
+	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
+	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
+		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL,
+					    parse_attr, hdrs, extack);
+		if (err)
+			return err;
 	}
 
 	attr->action = action;
-	if (!actions_match_supported(priv, exts, parse_attr, flow, extack))
+	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
 	return 0;
 }
 
-static inline int cmp_encap_info(struct ip_tunnel_key *a,
-				 struct ip_tunnel_key *b)
-{
-	return memcmp(a, b, sizeof(*a));
-}
+struct encap_key {
+	struct ip_tunnel_key *ip_tun_key;
+	int tunnel_type;
+};
 
-static inline int hash_encap_info(struct ip_tunnel_key *key)
+static inline int cmp_encap_info(struct encap_key *a,
+				 struct encap_key *b)
 {
-	return jhash(key, sizeof(*key), 0);
+	return memcmp(a->ip_tun_key, b->ip_tun_key, sizeof(*a->ip_tun_key)) ||
+	       a->tunnel_type != b->tunnel_type;
 }
 
-static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct flowi4 *fl4,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
+static inline int hash_encap_info(struct encap_key *key)
 {
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct rtable *rt;
-	struct neighbour *n = NULL;
-
-#if IS_ENABLED(CONFIG_INET)
-	int ret;
-
-	rt = ip_route_output_key(dev_net(mirred_dev), fl4);
-	ret = PTR_ERR_OR_ZERO(rt);
-	if (ret)
-		return ret;
-#else
-	return -EOPNOTSUPP;
-#endif
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	/* if the egress device isn't on the same HW e-switch, we use the uplink */
-	if (!switchdev_port_same_parent_id(priv->netdev, rt->dst.dev))
-		*out_dev = uplink_rpriv->netdev;
-	else
-		*out_dev = rt->dst.dev;
-
-	if (!(*out_ttl))
-		*out_ttl = ip4_dst_hoplimit(&rt->dst);
-	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
-	ip_rt_put(rt);
-	if (!n)
-		return -ENOMEM;
-
-	*out_n = n;
-	return 0;
+	return jhash(key->ip_tun_key, sizeof(*key->ip_tun_key),
+		     key->tunnel_type);
 }
 
+
 static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 				  struct net_device *peer_netdev)
 {
@@ -2366,389 +2411,45 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv,
 	peer_priv = netdev_priv(peer_netdev);
 
 	return (MLX5_CAP_ESW(priv->mdev, merged_eswitch) &&
-		(priv->netdev->netdev_ops == peer_netdev->netdev_ops) &&
-		same_hw_devs(priv, peer_priv) &&
-		MLX5_VPORT_MANAGER(peer_priv->mdev) &&
-		(peer_priv->mdev->priv.eswitch->mode == SRIOV_OFFLOADS));
-}
-
-static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
-				   struct net_device *mirred_dev,
-				   struct net_device **out_dev,
-				   struct flowi6 *fl6,
-				   struct neighbour **out_n,
-				   u8 *out_ttl)
-{
-	struct neighbour *n = NULL;
-	struct dst_entry *dst;
-
-#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
-	struct mlx5e_rep_priv *uplink_rpriv;
-	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	int ret;
-
-	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
-					 fl6);
-	if (ret < 0)
-		return ret;
-
-	if (!(*out_ttl))
-		*out_ttl = ip6_dst_hoplimit(dst);
-
-	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-	/* if the egress device isn't on the same HW e-switch, we use the uplink */
-	if (!switchdev_port_same_parent_id(priv->netdev, dst->dev))
-		*out_dev = uplink_rpriv->netdev;
-	else
-		*out_dev = dst->dev;
-#else
-	return -EOPNOTSUPP;
-#endif
-
-	n = dst_neigh_lookup(dst, &fl6->daddr);
-	dst_release(dst);
-	if (!n)
-		return -ENOMEM;
-
-	*out_n = n;
-	return 0;
-}
-
-static void gen_vxlan_header_ipv4(struct net_device *out_dev,
-				  char buf[], int encap_size,
-				  unsigned char h_dest[ETH_ALEN],
-				  u8 tos, u8 ttl,
-				  __be32 daddr,
-				  __be32 saddr,
-				  __be16 udp_dst_port,
-				  __be32 vx_vni)
-{
-	struct ethhdr *eth = (struct ethhdr *)buf;
-	struct iphdr  *ip = (struct iphdr *)((char *)eth + sizeof(struct ethhdr));
-	struct udphdr *udp = (struct udphdr *)((char *)ip + sizeof(struct iphdr));
-	struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
-
-	memset(buf, 0, encap_size);
-
-	ether_addr_copy(eth->h_dest, h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IP);
-
-	ip->daddr = daddr;
-	ip->saddr = saddr;
-
-	ip->tos = tos;
-	ip->ttl = ttl;
-	ip->protocol = IPPROTO_UDP;
-	ip->version = 0x4;
-	ip->ihl = 0x5;
-
-	udp->dest = udp_dst_port;
-	vxh->vx_flags = VXLAN_HF_VNI;
-	vxh->vx_vni = vxlan_vni_field(vx_vni);
-}
-
-static void gen_vxlan_header_ipv6(struct net_device *out_dev,
-				  char buf[], int encap_size,
-				  unsigned char h_dest[ETH_ALEN],
-				  u8 tos, u8 ttl,
-				  struct in6_addr *daddr,
-				  struct in6_addr *saddr,
-				  __be16 udp_dst_port,
-				  __be32 vx_vni)
-{
-	struct ethhdr *eth = (struct ethhdr *)buf;
-	struct ipv6hdr *ip6h = (struct ipv6hdr *)((char *)eth + sizeof(struct ethhdr));
-	struct udphdr *udp = (struct udphdr *)((char *)ip6h + sizeof(struct ipv6hdr));
-	struct vxlanhdr *vxh = (struct vxlanhdr *)((char *)udp + sizeof(struct udphdr));
-
-	memset(buf, 0, encap_size);
-
-	ether_addr_copy(eth->h_dest, h_dest);
-	ether_addr_copy(eth->h_source, out_dev->dev_addr);
-	eth->h_proto = htons(ETH_P_IPV6);
-
-	ip6_flow_hdr(ip6h, tos, 0);
-	/* the HW fills up ipv6 payload len */
-	ip6h->nexthdr     = IPPROTO_UDP;
-	ip6h->hop_limit   = ttl;
-	ip6h->daddr	  = *daddr;
-	ip6h->saddr	  = *saddr;
-
-	udp->dest = udp_dst_port;
-	vxh->vx_flags = VXLAN_HF_VNI;
-	vxh->vx_vni = vxlan_vni_field(vx_vni);
-}
-
-static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
-					  struct net_device *mirred_dev,
-					  struct mlx5e_encap_entry *e)
-{
-	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv4_encap_size = ETH_HLEN + sizeof(struct iphdr) + VXLAN_HLEN;
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	struct net_device *out_dev;
-	struct neighbour *n = NULL;
-	struct flowi4 fl4 = {};
-	u8 nud_state, tos, ttl;
-	char *encap_header;
-	int err;
-
-	if (max_encap_size < ipv4_encap_size) {
-		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
-			       ipv4_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
-	}
-
-	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
-
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		fl4.flowi4_proto = IPPROTO_UDP;
-		fl4.fl4_dport = tun_key->tp_dst;
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		goto free_encap;
-	}
-
-	tos = tun_key->tos;
-	ttl = tun_key->ttl;
-
-	fl4.flowi4_tos = tun_key->tos;
-	fl4.daddr = tun_key->u.ipv4.dst;
-	fl4.saddr = tun_key->u.ipv4.src;
-
-	err = mlx5e_route_lookup_ipv4(priv, mirred_dev, &out_dev,
-				      &fl4, &n, &ttl);
-	if (err)
-		goto free_encap;
-
-	/* used by mlx5e_detach_encap to lookup a neigh hash table
-	 * entry in the neigh hash table when a user deletes a rule
-	 */
-	e->m_neigh.dev = n->dev;
-	e->m_neigh.family = n->ops->family;
-	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-	e->out_dev = out_dev;
-
-	/* It's importent to add the neigh to the hash table before checking
-	 * the neigh validity state. So if we'll get a notification, in case the
-	 * neigh changes it's validity state, we would find the relevant neigh
-	 * in the hash.
-	 */
-	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
-	if (err)
-		goto free_encap;
-
-	read_lock_bh(&n->lock);
-	nud_state = n->nud_state;
-	ether_addr_copy(e->h_dest, n->ha);
-	read_unlock_bh(&n->lock);
-
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		gen_vxlan_header_ipv4(out_dev, encap_header,
-				      ipv4_encap_size, e->h_dest, tos, ttl,
-				      fl4.daddr,
-				      fl4.saddr, tun_key->tp_dst,
-				      tunnel_id_to_key32(tun_key->tun_id));
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		goto destroy_neigh_entry;
-	}
-	e->encap_size = ipv4_encap_size;
-	e->encap_header = encap_header;
-
-	if (!(nud_state & NUD_VALID)) {
-		neigh_event_send(n, NULL);
-		err = -EAGAIN;
-		goto out;
-	}
-
-	err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type,
-					 ipv4_encap_size, encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
-					 &e->encap_id);
-	if (err)
-		goto destroy_neigh_entry;
-
-	e->flags |= MLX5_ENCAP_ENTRY_VALID;
-	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
-	return err;
-
-destroy_neigh_entry:
-	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-free_encap:
-	kfree(encap_header);
-out:
-	if (n)
-		neigh_release(n);
-	return err;
+		mlx5e_eswitch_rep(priv->netdev) &&
+		mlx5e_eswitch_rep(peer_netdev) &&
+		same_hw_devs(priv, peer_priv));
 }
 
-static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
-					  struct net_device *mirred_dev,
-					  struct mlx5e_encap_entry *e)
-{
-	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
-	int ipv6_encap_size = ETH_HLEN + sizeof(struct ipv6hdr) + VXLAN_HLEN;
-	struct ip_tunnel_key *tun_key = &e->tun_info.key;
-	struct net_device *out_dev;
-	struct neighbour *n = NULL;
-	struct flowi6 fl6 = {};
-	u8 nud_state, tos, ttl;
-	char *encap_header;
-	int err;
-
-	if (max_encap_size < ipv6_encap_size) {
-		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
-			       ipv6_encap_size, max_encap_size);
-		return -EOPNOTSUPP;
-	}
-
-	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
-	if (!encap_header)
-		return -ENOMEM;
-
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		fl6.flowi6_proto = IPPROTO_UDP;
-		fl6.fl6_dport = tun_key->tp_dst;
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		goto free_encap;
-	}
-
-	tos = tun_key->tos;
-	ttl = tun_key->ttl;
-
-	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
-	fl6.daddr = tun_key->u.ipv6.dst;
-	fl6.saddr = tun_key->u.ipv6.src;
-
-	err = mlx5e_route_lookup_ipv6(priv, mirred_dev, &out_dev,
-				      &fl6, &n, &ttl);
-	if (err)
-		goto free_encap;
-
-	/* used by mlx5e_detach_encap to lookup a neigh hash table
-	 * entry in the neigh hash table when a user deletes a rule
-	 */
-	e->m_neigh.dev = n->dev;
-	e->m_neigh.family = n->ops->family;
-	memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len);
-	e->out_dev = out_dev;
-
-	/* It's importent to add the neigh to the hash table before checking
-	 * the neigh validity state. So if we'll get a notification, in case the
-	 * neigh changes it's validity state, we would find the relevant neigh
-	 * in the hash.
-	 */
-	err = mlx5e_rep_encap_entry_attach(netdev_priv(out_dev), e);
-	if (err)
-		goto free_encap;
-
-	read_lock_bh(&n->lock);
-	nud_state = n->nud_state;
-	ether_addr_copy(e->h_dest, n->ha);
-	read_unlock_bh(&n->lock);
-
-	switch (e->tunnel_type) {
-	case MLX5_REFORMAT_TYPE_L2_TO_VXLAN:
-		gen_vxlan_header_ipv6(out_dev, encap_header,
-				      ipv6_encap_size, e->h_dest, tos, ttl,
-				      &fl6.daddr,
-				      &fl6.saddr, tun_key->tp_dst,
-				      tunnel_id_to_key32(tun_key->tun_id));
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		goto destroy_neigh_entry;
-	}
-
-	e->encap_size = ipv6_encap_size;
-	e->encap_header = encap_header;
-
-	if (!(nud_state & NUD_VALID)) {
-		neigh_event_send(n, NULL);
-		err = -EAGAIN;
-		goto out;
-	}
-
-	err = mlx5_packet_reformat_alloc(priv->mdev, e->tunnel_type,
-					 ipv6_encap_size, encap_header,
-					 MLX5_FLOW_NAMESPACE_FDB,
-					 &e->encap_id);
-	if (err)
-		goto destroy_neigh_entry;
 
-	e->flags |= MLX5_ENCAP_ENTRY_VALID;
-	mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev));
-	neigh_release(n);
-	return err;
-
-destroy_neigh_entry:
-	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
-free_encap:
-	kfree(encap_header);
-out:
-	if (n)
-		neigh_release(n);
-	return err;
-}
 
 static int mlx5e_attach_encap(struct mlx5e_priv *priv,
-			      struct ip_tunnel_info *tun_info,
+			      struct mlx5e_tc_flow *flow,
 			      struct net_device *mirred_dev,
+			      int out_index,
+			      struct netlink_ext_ack *extack,
 			      struct net_device **encap_dev,
-			      struct mlx5e_tc_flow *flow,
-			      struct netlink_ext_ack *extack)
+			      bool *encap_valid)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	unsigned short family = ip_tunnel_info_af(tun_info);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
-	struct ip_tunnel_key *key = &tun_info->key;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct ip_tunnel_info *tun_info;
+	struct encap_key key, e_key;
 	struct mlx5e_encap_entry *e;
-	int tunnel_type, err = 0;
+	unsigned short family;
 	uintptr_t hash_key;
 	bool found = false;
+	int err = 0;
 
-	/* udp dst port must be set */
-	if (!memchr_inv(&key->tp_dst, 0, sizeof(key->tp_dst)))
-		goto vxlan_encap_offload_err;
-
-	/* setting udp src port isn't supported */
-	if (memchr_inv(&key->tp_src, 0, sizeof(key->tp_src))) {
-vxlan_encap_offload_err:
-		NL_SET_ERR_MSG_MOD(extack,
-				   "must set udp dst port and not set udp src port");
-		netdev_warn(priv->netdev,
-			    "must set udp dst port and not set udp src port\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
-	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
-		tunnel_type = MLX5_REFORMAT_TYPE_L2_TO_VXLAN;
-	} else {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "port isn't an offloaded vxlan udp dport");
-		netdev_warn(priv->netdev,
-			    "%d isn't an offloaded vxlan udp dport\n", be16_to_cpu(key->tp_dst));
-		return -EOPNOTSUPP;
-	}
+	parse_attr = attr->parse_attr;
+	tun_info = &parse_attr->tun_info[out_index];
+	family = ip_tunnel_info_af(tun_info);
+	key.ip_tun_key = &tun_info->key;
+	key.tunnel_type = mlx5e_tc_tun_get_type(mirred_dev);
 
-	hash_key = hash_encap_info(key);
+	hash_key = hash_encap_info(&key);
 
 	hash_for_each_possible_rcu(esw->offloads.encap_tbl, e,
 				   encap_hlist, hash_key) {
-		if (!cmp_encap_info(&e->tun_info.key, key)) {
+		e_key.ip_tun_key = &e->tun_info.key;
+		e_key.tunnel_type = e->tunnel_type;
+		if (!cmp_encap_info(&e_key, &key)) {
 			found = true;
 			break;
 		}
@@ -2763,26 +2464,33 @@ vxlan_encap_offload_err:
 		return -ENOMEM;
 
 	e->tun_info = *tun_info;
-	e->tunnel_type = tunnel_type;
+	err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack);
+	if (err)
+		goto out_err;
+
 	INIT_LIST_HEAD(&e->flows);
 
 	if (family == AF_INET)
-		err = mlx5e_create_encap_header_ipv4(priv, mirred_dev, e);
+		err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e);
 	else if (family == AF_INET6)
-		err = mlx5e_create_encap_header_ipv6(priv, mirred_dev, e);
+		err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e);
 
-	if (err && err != -EAGAIN)
+	if (err)
 		goto out_err;
 
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 
 attach_flow:
-	list_add(&flow->encap, &e->flows);
+	list_add(&flow->encaps[out_index].list, &e->flows);
+	flow->encaps[out_index].index = out_index;
 	*encap_dev = e->out_dev;
-	if (e->flags & MLX5_ENCAP_ENTRY_VALID)
-		attr->encap_id = e->encap_id;
-	else
-		err = -EAGAIN;
+	if (e->flags & MLX5_ENCAP_ENTRY_VALID) {
+		attr->dests[out_index].encap_id = e->encap_id;
+		attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID;
+		*encap_valid = true;
+	} else {
+		*encap_valid = false;
+	}
 
 	return err;
 
@@ -2792,7 +2500,7 @@ out_err:
 }
 
 static int parse_tc_vlan_action(struct mlx5e_priv *priv,
-				const struct tc_action *a,
+				const struct flow_action_entry *act,
 				struct mlx5_esw_flow_attr *attr,
 				u32 *action)
 {
@@ -2801,7 +2509,8 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 	if (vlan_idx >= MLX5_FS_VLAN_DEPTH)
 		return -EOPNOTSUPP;
 
-	if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
+	switch (act->id) {
+	case FLOW_ACTION_VLAN_POP:
 		if (vlan_idx) {
 			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
 								 MLX5_FS_VLAN_DEPTH))
@@ -2811,10 +2520,11 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 		} else {
 			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
 		}
-	} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-		attr->vlan_vid[vlan_idx] = tcf_vlan_push_vid(a);
-		attr->vlan_prio[vlan_idx] = tcf_vlan_push_prio(a);
-		attr->vlan_proto[vlan_idx] = tcf_vlan_push_proto(a);
+		break;
+	case FLOW_ACTION_VLAN_PUSH:
+		attr->vlan_vid[vlan_idx] = act->vlan.vid;
+		attr->vlan_prio[vlan_idx] = act->vlan.prio;
+		attr->vlan_proto[vlan_idx] = act->vlan.proto;
 		if (!attr->vlan_proto[vlan_idx])
 			attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q);
 
@@ -2826,13 +2536,15 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
 		} else {
 			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) &&
-			    (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
-			     tcf_vlan_push_prio(a)))
+			    (act->vlan.proto != htons(ETH_P_8021Q) ||
+			     act->vlan.prio))
 				return -EOPNOTSUPP;
 
 			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 		}
-	} else { /* action is TCA_VLAN_ACT_MODIFY */
+		break;
+	default:
+		/* action is FLOW_ACT_VLAN_MANGLE */
 		return -EOPNOTSUPP;
 	}
 
@@ -2841,59 +2553,63 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 	return 0;
 }
 
-static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
+static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
+				struct flow_action *flow_action,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow,
 				struct netlink_ext_ack *extack)
 {
+	struct pedit_headers_action hdrs[2] = {};
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
-	struct ip_tunnel_info *info = NULL;
-	const struct tc_action *a;
-	LIST_HEAD(actions);
+	const struct ip_tunnel_info *info = NULL;
+	const struct flow_action_entry *act;
 	bool encap = false;
 	u32 action = 0;
 	int err, i;
 
-	if (!tcf_exts_has_actions(exts))
+	if (!flow_action_has_entries(flow_action))
 		return -EINVAL;
 
 	attr->in_rep = rpriv->rep;
 	attr->in_mdev = priv->mdev;
 
-	tcf_exts_for_each_action(i, a, exts) {
-		if (is_tcf_gact_shot(a)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DROP |
 				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-			continue;
-		}
-
-		if (is_tcf_pedit(a)) {
-			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
-						    parse_attr, extack);
+			break;
+		case FLOW_ACTION_MANGLE:
+		case FLOW_ACTION_ADD:
+			err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB,
+						    parse_attr, hdrs, extack);
 			if (err)
 				return err;
 
 			action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-			attr->mirror_count = attr->out_count;
-			continue;
-		}
-
-		if (is_tcf_csum(a)) {
+			attr->split_count = attr->out_count;
+			break;
+		case FLOW_ACTION_CSUM:
 			if (csum_offload_supported(priv, action,
-						   tcf_csum_update_flags(a),
-						   extack))
-				continue;
+						   act->csum_flags, extack))
+				break;
 
 			return -EOPNOTSUPP;
-		}
-
-		if (is_tcf_mirred_egress_redirect(a) || is_tcf_mirred_egress_mirror(a)) {
+		case FLOW_ACTION_REDIRECT:
+		case FLOW_ACTION_MIRRED: {
 			struct mlx5e_priv *out_priv;
 			struct net_device *out_dev;
 
-			out_dev = tcf_mirred_dev(a);
+			out_dev = act->dev;
+			if (!out_dev) {
+				/* out_dev is NULL when filters with
+				 * non-existing mirred device are replayed to
+				 * the driver.
+				 */
+				return -EINVAL;
+			}
 
 			if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) {
 				NL_SET_ERR_MSG_MOD(extack,
@@ -2903,23 +2619,47 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				return -EOPNOTSUPP;
 			}
 
-			if (switchdev_port_same_parent_id(priv->netdev,
-							  out_dev) ||
+			action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+				  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+			if (netdev_port_same_parent_id(priv->netdev,
+						       out_dev) ||
 			    is_merged_eswitch_dev(priv, out_dev)) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+				struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+				struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
+				struct net_device *uplink_upper = netdev_master_upper_dev_get(uplink_dev);
+
+				if (uplink_upper &&
+				    netif_is_lag_master(uplink_upper) &&
+				    uplink_upper == out_dev)
+					out_dev = uplink_dev;
+
+				if (!mlx5e_eswitch_rep(out_dev))
+					return -EOPNOTSUPP;
+
 				out_priv = netdev_priv(out_dev);
 				rpriv = out_priv->ppriv;
-				attr->out_rep[attr->out_count] = rpriv->rep;
-				attr->out_mdev[attr->out_count++] = out_priv->mdev;
+				attr->dests[attr->out_count].rep = rpriv->rep;
+				attr->dests[attr->out_count].mdev = out_priv->mdev;
+				attr->out_count++;
 			} else if (encap) {
-				parse_attr->mirred_ifindex = out_dev->ifindex;
-				parse_attr->tun_info = *info;
+				parse_attr->mirred_ifindex[attr->out_count] =
+					out_dev->ifindex;
+				parse_attr->tun_info[attr->out_count] = *info;
+				encap = false;
 				attr->parse_attr = parse_attr;
-				action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT |
-					  MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
-					  MLX5_FLOW_CONTEXT_ACTION_COUNT;
-				/* attr->out_rep is resolved when we handle encap */
+				attr->dests[attr->out_count].flags |=
+					MLX5_ESW_DEST_ENCAP;
+				attr->out_count++;
+				/* attr->dests[].rep is resolved when we
+				 * handle encap
+				 */
+			} else if (parse_attr->filter_dev != priv->netdev) {
+				/* All mlx5 devices are called to configure
+				 * high level device filters. Therefore, the
+				 * *attempt* to  install a filter on invalid
+				 * eswitch should not trigger an explicit error
+				 */
+				return -EINVAL;
 			} else {
 				NL_SET_ERR_MSG_MOD(extack,
 						   "devices are not on same switch HW, can't offload forwarding");
@@ -2927,36 +2667,29 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				       priv->netdev->name, out_dev->name);
 				return -EINVAL;
 			}
-			continue;
-		}
-
-		if (is_tcf_tunnel_set(a)) {
-			info = tcf_tunnel_info(a);
+			}
+			break;
+		case FLOW_ACTION_TUNNEL_ENCAP:
+			info = act->tunnel;
 			if (info)
 				encap = true;
 			else
 				return -EOPNOTSUPP;
-			attr->mirror_count = attr->out_count;
-			continue;
-		}
-
-		if (is_tcf_vlan(a)) {
-			err = parse_tc_vlan_action(priv, a, attr, &action);
 
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+		case FLOW_ACTION_VLAN_POP:
+			err = parse_tc_vlan_action(priv, act, attr, &action);
 			if (err)
 				return err;
 
-			attr->mirror_count = attr->out_count;
-			continue;
-		}
-
-		if (is_tcf_tunnel_release(a)) {
+			attr->split_count = attr->out_count;
+			break;
+		case FLOW_ACTION_TUNNEL_DECAP:
 			action |= MLX5_FLOW_CONTEXT_ACTION_DECAP;
-			continue;
-		}
-
-		if (is_tcf_gact_goto_chain(a)) {
-			u32 dest_chain = tcf_gact_goto_chain_index(a);
+			break;
+		case FLOW_ACTION_GOTO: {
+			u32 dest_chain = act->chain_index;
 			u32 max_chain = mlx5_eswitch_get_chain_range(esw);
 
 			if (dest_chain <= attr->chain) {
@@ -2969,15 +2702,23 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 			}
 			action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			attr->dest_chain = dest_chain;
-
-			continue;
+			break;
+			}
+		default:
+			return -EINVAL;
 		}
+	}
 
-		return -EINVAL;
+	if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits ||
+	    hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) {
+		err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_FDB,
+					    parse_attr, hdrs, extack);
+		if (err)
+			return err;
 	}
 
 	attr->action = action;
-	if (!actions_match_supported(priv, exts, parse_attr, flow, extack))
+	if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack))
 		return -EOPNOTSUPP;
 
 	if (attr->dest_chain) {
@@ -2988,7 +2729,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	}
 
-	if (attr->mirror_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
+	if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "current firmware doesn't support split rule for port mirroring");
 		netdev_warn_once(priv->netdev, "current firmware doesn't support split rule for port mirroring\n");
@@ -3007,6 +2748,11 @@ static void get_flags(int flags, u16 *flow_flags)
 	if (flags & MLX5E_TC_EGRESS)
 		__flow_flags |= MLX5E_TC_FLOW_EGRESS;
 
+	if (flags & MLX5E_TC_ESW_OFFLOAD)
+		__flow_flags |= MLX5E_TC_FLOW_ESWITCH;
+	if (flags & MLX5E_TC_NIC_OFFLOAD)
+		__flow_flags |= MLX5E_TC_FLOW_NIC;
+
 	*flow_flags = __flow_flags;
 }
 
@@ -3017,18 +2763,39 @@ static const struct rhashtable_params tc_ht_params = {
 	.automatic_shrinking = true,
 };
 
-static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv)
+static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *uplink_rpriv;
 
-	if (MLX5_VPORT_MANAGER(priv->mdev) && esw->mode == SRIOV_OFFLOADS) {
+	if (flags & MLX5E_TC_ESW_OFFLOAD) {
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		return &uplink_rpriv->tc_ht;
-	} else
+		return &uplink_rpriv->uplink_priv.tc_ht;
+	} else /* NIC offload */
 		return &priv->fs.tc.ht;
 }
 
+static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
+{
+	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
+	bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK &&
+			      flow->flags & MLX5E_TC_FLOW_INGRESS;
+	bool act_is_encap = !!(attr->action &
+			       MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT);
+	bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom,
+						MLX5_DEVCOM_ESW_OFFLOADS);
+
+	if (!esw_paired)
+		return false;
+
+	if ((mlx5_lag_is_sriov(attr->in_mdev) ||
+	     mlx5_lag_is_multipath(attr->in_mdev)) &&
+	    (is_rep_ingress || act_is_encap))
+		return true;
+
+	return false;
+}
+
 static int
 mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 		 struct tc_cls_flower_offload *f, u16 flow_flags,
@@ -3050,10 +2817,6 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
 	flow->flags = flow_flags;
 	flow->priv = priv;
 
-	err = parse_cls_flower(priv, flow, &parse_attr->spec, f);
-	if (err)
-		goto err_free;
-
 	*__flow = flow;
 	*__parse_attr = parse_attr;
 
@@ -3065,12 +2828,39 @@ err_free:
 	return err;
 }
 
-static int
-mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
-		   struct tc_cls_flower_offload *f,
-		   u16 flow_flags,
-		   struct mlx5e_tc_flow **__flow)
+static void
+mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
+			 struct mlx5e_priv *priv,
+			 struct mlx5e_tc_flow_parse_attr *parse_attr,
+			 struct tc_cls_flower_offload *f,
+			 struct mlx5_eswitch_rep *in_rep,
+			 struct mlx5_core_dev *in_mdev)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	esw_attr->parse_attr = parse_attr;
+	esw_attr->chain = f->common.chain_index;
+	esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
+
+	esw_attr->in_rep = in_rep;
+	esw_attr->in_mdev = in_mdev;
+
+	if (MLX5_CAP_ESW(esw->dev, counter_eswitch_affinity) ==
+	    MLX5_COUNTER_SOURCE_ESWITCH)
+		esw_attr->counter_dev = in_mdev;
+	else
+		esw_attr->counter_dev = priv->mdev;
+}
+
+static struct mlx5e_tc_flow *
+__mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
+		     struct tc_cls_flower_offload *f,
+		     u16 flow_flags,
+		     struct net_device *filter_dev,
+		     struct mlx5_eswitch_rep *in_rep,
+		     struct mlx5_core_dev *in_mdev)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
@@ -3083,28 +2873,118 @@ mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
-	flow->esw_attr->chain = f->common.chain_index;
-	flow->esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
-	err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow, extack);
+	parse_attr->filter_dev = filter_dev;
+	mlx5e_flow_esw_attr_init(flow->esw_attr,
+				 priv, parse_attr,
+				 f, in_rep, in_mdev);
+
+	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec,
+			       f, filter_dev);
 	if (err)
 		goto err_free;
 
-	err = mlx5e_tc_add_fdb_flow(priv, parse_attr, flow, extack);
+	err = parse_tc_fdb_actions(priv, &rule->action, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
 
-	if (!(flow->esw_attr->action &
-	      MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT))
-		kvfree(parse_attr);
+	err = mlx5e_tc_add_fdb_flow(priv, flow, extack);
+	if (err) {
+		if (!(err == -ENETUNREACH && mlx5_lag_is_multipath(in_mdev)))
+			goto err_free;
 
-	*__flow = flow;
+		add_unready_flow(flow);
+	}
 
-	return 0;
+	return flow;
 
 err_free:
 	kfree(flow);
 	kvfree(parse_attr);
 out:
+	return ERR_PTR(err);
+}
+
+static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f,
+				      struct mlx5e_tc_flow *flow,
+				      u16 flow_flags)
+{
+	struct mlx5e_priv *priv = flow->priv, *peer_priv;
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw;
+	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5e_rep_priv *peer_urpriv;
+	struct mlx5e_tc_flow *peer_flow;
+	struct mlx5_core_dev *in_mdev;
+	int err = 0;
+
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return -ENODEV;
+
+	peer_urpriv = mlx5_eswitch_get_uplink_priv(peer_esw, REP_ETH);
+	peer_priv = netdev_priv(peer_urpriv->netdev);
+
+	/* in_mdev is assigned of which the packet originated from.
+	 * So packets redirected to uplink use the same mdev of the
+	 * original flow and packets redirected from uplink use the
+	 * peer mdev.
+	 */
+	if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK)
+		in_mdev = peer_priv->mdev;
+	else
+		in_mdev = priv->mdev;
+
+	parse_attr = flow->esw_attr->parse_attr;
+	peer_flow = __mlx5e_add_fdb_flow(peer_priv, f, flow_flags,
+					 parse_attr->filter_dev,
+					 flow->esw_attr->in_rep, in_mdev);
+	if (IS_ERR(peer_flow)) {
+		err = PTR_ERR(peer_flow);
+		goto out;
+	}
+
+	flow->peer_flow = peer_flow;
+	flow->flags |= MLX5E_TC_FLOW_DUP;
+	mutex_lock(&esw->offloads.peer_mutex);
+	list_add_tail(&flow->peer, &esw->offloads.peer_flows);
+	mutex_unlock(&esw->offloads.peer_mutex);
+
+out:
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	return err;
+}
+
+static int
+mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
+		   struct tc_cls_flower_offload *f,
+		   u16 flow_flags,
+		   struct net_device *filter_dev,
+		   struct mlx5e_tc_flow **__flow)
+{
+	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+	struct mlx5_eswitch_rep *in_rep = rpriv->rep;
+	struct mlx5_core_dev *in_mdev = priv->mdev;
+	struct mlx5e_tc_flow *flow;
+	int err;
+
+	flow = __mlx5e_add_fdb_flow(priv, f, flow_flags, filter_dev, in_rep,
+				    in_mdev);
+	if (IS_ERR(flow))
+		return PTR_ERR(flow);
+
+	if (is_peer_flow_needed(flow)) {
+		err = mlx5e_tc_add_fdb_peer_flow(f, flow, flow_flags);
+		if (err) {
+			mlx5e_tc_del_fdb_flow(priv, flow);
+			goto out;
+		}
+	}
+
+	*__flow = flow;
+
+	return 0;
+
+out:
 	return err;
 }
 
@@ -3112,8 +2992,10 @@ static int
 mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 		   struct tc_cls_flower_offload *f,
 		   u16 flow_flags,
+		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
@@ -3130,7 +3012,13 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
-	err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow, extack);
+	parse_attr->filter_dev = filter_dev;
+	err = parse_cls_flower(flow->priv, flow, &parse_attr->spec,
+			       f, filter_dev);
+	if (err)
+		goto err_free;
+
+	err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack);
 	if (err)
 		goto err_free;
 
@@ -3155,6 +3043,7 @@ static int
 mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 		  struct tc_cls_flower_offload *f,
 		  int flags,
+		  struct net_device *filter_dev,
 		  struct mlx5e_tc_flow **flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -3167,18 +3056,20 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 
 	if (esw && esw->mode == SRIOV_OFFLOADS)
-		err = mlx5e_add_fdb_flow(priv, f, flow_flags, flow);
+		err = mlx5e_add_fdb_flow(priv, f, flow_flags,
+					 filter_dev, flow);
 	else
-		err = mlx5e_add_nic_flow(priv, f, flow_flags, flow);
+		err = mlx5e_add_nic_flow(priv, f, flow_flags,
+					 filter_dev, flow);
 
 	return err;
 }
 
-int mlx5e_configure_flower(struct mlx5e_priv *priv,
+int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct tc_cls_flower_offload *f, int flags)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
 	int err = 0;
 
@@ -3192,7 +3083,7 @@ int mlx5e_configure_flower(struct mlx5e_priv *priv,
 		goto out;
 	}
 
-	err = mlx5e_tc_add_flow(priv, f, flags, &flow);
+	err = mlx5e_tc_add_flow(priv, f, flags, dev, &flow);
 	if (err)
 		goto out;
 
@@ -3220,10 +3111,10 @@ static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags)
 	return false;
 }
 
-int mlx5e_delete_flower(struct mlx5e_priv *priv,
+int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			struct tc_cls_flower_offload *f, int flags)
 {
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
 
 	flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
@@ -3239,30 +3130,57 @@ int mlx5e_delete_flower(struct mlx5e_priv *priv,
 	return 0;
 }
 
-int mlx5e_stats_flower(struct mlx5e_priv *priv,
+int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f, int flags)
 {
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
+	struct mlx5_eswitch *peer_esw;
 	struct mlx5e_tc_flow *flow;
 	struct mlx5_fc *counter;
-	u64 bytes;
-	u64 packets;
-	u64 lastuse;
+	u64 lastuse = 0;
+	u64 packets = 0;
+	u64 bytes = 0;
 
 	flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
 	if (!flow || !same_flow_direction(flow, flags))
 		return -EINVAL;
 
-	if (!(flow->flags & MLX5E_TC_FLOW_OFFLOADED))
-		return 0;
+	if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) {
+		counter = mlx5e_tc_get_counter(flow);
+		if (!counter)
+			return 0;
 
-	counter = mlx5e_tc_get_counter(flow);
-	if (!counter)
-		return 0;
+		mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+	}
+
+	/* Under multipath it's possible for one rule to be currently
+	 * un-offloaded while the other rule is offloaded.
+	 */
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		goto out;
 
-	mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse);
+	if ((flow->flags & MLX5E_TC_FLOW_DUP) &&
+	    (flow->peer_flow->flags & MLX5E_TC_FLOW_OFFLOADED)) {
+		u64 bytes2;
+		u64 packets2;
+		u64 lastuse2;
 
-	tcf_exts_stats_update(f->exts, bytes, packets, lastuse);
+		counter = mlx5e_tc_get_counter(flow->peer_flow);
+		if (!counter)
+			goto no_peer_counter;
+		mlx5_fc_query_cached(counter, &bytes2, &packets2, &lastuse2);
+
+		bytes += bytes2;
+		packets += packets2;
+		lastuse = max_t(u64, lastuse, lastuse2);
+	}
+
+no_peer_counter:
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+out:
+	flow_stats_update(&f->stats, bytes, packets, lastuse);
 
 	return 0;
 }
@@ -3350,7 +3268,7 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 	if (tc->netdevice_nb.notifier_call)
 		unregister_netdevice_notifier(&tc->netdevice_nb);
 
-	rhashtable_free_and_destroy(&tc->ht, _mlx5e_tc_del_flow, NULL);
+	rhashtable_destroy(&tc->ht);
 
 	if (!IS_ERR_OR_NULL(tc->t)) {
 		mlx5_destroy_flow_table(tc->t);
@@ -3368,9 +3286,32 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht)
 	rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL);
 }
 
-int mlx5e_tc_num_filters(struct mlx5e_priv *priv)
+int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags)
 {
-	struct rhashtable *tc_ht = get_tc_ht(priv);
+	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 
 	return atomic_read(&tc_ht->nelems);
 }
+
+void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw)
+{
+	struct mlx5e_tc_flow *flow, *tmp;
+
+	list_for_each_entry_safe(flow, tmp, &esw->offloads.peer_flows, peer)
+		__mlx5e_tc_del_fdb_peer_flow(flow);
+}
+
+void mlx5e_tc_reoffload_flows_work(struct work_struct *work)
+{
+	struct mlx5_rep_uplink_priv *rpriv =
+		container_of(work, struct mlx5_rep_uplink_priv,
+			     reoffload_flows_work);
+	struct mlx5e_tc_flow *flow, *tmp;
+
+	rtnl_lock();
+	list_for_each_entry_safe(flow, tmp, &rpriv->unready_flows, unready) {
+		if (!mlx5e_tc_add_fdb_flow(flow->priv, flow, NULL))
+			remove_unready_flow(flow);
+	}
+	rtnl_unlock();
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 49436bf3b80a..f62e81902d27 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -42,7 +42,9 @@
 enum {
 	MLX5E_TC_INGRESS = BIT(0),
 	MLX5E_TC_EGRESS  = BIT(1),
-	MLX5E_TC_LAST_EXPORTED_BIT = 1,
+	MLX5E_TC_NIC_OFFLOAD = BIT(2),
+	MLX5E_TC_ESW_OFFLOAD = BIT(3),
+	MLX5E_TC_LAST_EXPORTED_BIT = 3,
 };
 
 int mlx5e_tc_nic_init(struct mlx5e_priv *priv);
@@ -51,12 +53,12 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv);
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
 
-int mlx5e_configure_flower(struct mlx5e_priv *priv,
+int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct tc_cls_flower_offload *f, int flags);
-int mlx5e_delete_flower(struct mlx5e_priv *priv,
+int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			struct tc_cls_flower_offload *f, int flags);
 
-int mlx5e_stats_flower(struct mlx5e_priv *priv,
+int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		       struct tc_cls_flower_offload *f, int flags);
 
 struct mlx5e_encap_entry;
@@ -68,12 +70,14 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv,
 struct mlx5e_neigh_hash_entry;
 void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe);
 
-int mlx5e_tc_num_filters(struct mlx5e_priv *priv);
+int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags);
+
+void mlx5e_tc_reoffload_flows_work(struct work_struct *work);
 
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
-static inline int  mlx5e_tc_num_filters(struct mlx5e_priv *priv) { return 0; }
+static inline int  mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags) { return 0; }
 #endif
 
 #endif /* __MLX5_EN_TC_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 6dacaeba2fbf..25a8f8260c14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -127,7 +127,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 	else
 #endif
 		if (skb_vlan_tag_present(skb))
-			up = skb->vlan_tci >> VLAN_PRIO_SHIFT;
+			up = skb_vlan_tag_get_prio(skb);
 
 	/* channel_ix can be larger than num_channels since
 	 * dev->num_real_tx_queues = num_channels * num_tc
@@ -148,12 +148,8 @@ static inline int mlx5e_skb_l2_header_offset(struct sk_buff *skb)
 
 static inline int mlx5e_skb_l3_header_offset(struct sk_buff *skb)
 {
-	struct flow_keys keys;
-
 	if (skb_transport_header_was_set(skb))
 		return skb_transport_offset(skb);
-	else if (skb_flow_dissect_flow_keys(skb, &keys, 0))
-		return keys.control.thoff;
 	else
 		return mlx5e_skb_l2_header_offset(skb);
 }
@@ -172,15 +168,8 @@ static inline u16 mlx5e_calc_min_inline(enum mlx5_inline_modes mode,
 			hlen += VLAN_HLEN;
 		break;
 	case MLX5_INLINE_MODE_IP:
-		/* When transport header is set to zero, it means no transport
-		 * header. When transport header is set to 0xff's, it means
-		 * transport header wasn't set.
-		 */
-		if (skb_transport_offset(skb)) {
-			hlen = mlx5e_skb_l3_header_offset(skb);
-			break;
-		}
-		/* fall through */
+		hlen = mlx5e_skb_l3_header_offset(skb);
+		break;
 	case MLX5_INLINE_MODE_L2:
 	default:
 		hlen = mlx5e_skb_l2_header_offset(skb);
@@ -387,8 +376,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS);
 	contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
 	if (unlikely(contig_wqebbs_room < num_wqebbs)) {
+#ifdef CONFIG_MLX5_EN_IPSEC
+		struct mlx5_wqe_eth_seg cur_eth = wqe->eth;
+#endif
 		mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room);
 		mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
+#ifdef CONFIG_MLX5_EN_IPSEC
+		wqe->eth = cur_eth;
+#endif
 	}
 
 	/* fill wqe */
@@ -459,9 +454,10 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 	u32 ci = mlx5_cqwq_get_ci(&sq->cq.wq);
 
 	netdev_err(sq->channel->netdev,
-		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
-		   sq->cq.mcq.cqn, ci, sq->sqn, err_cqe->syndrome,
-		   err_cqe->vendor_err_synd);
+		   "Error cqe on cqn 0x%x, ci 0x%x, sqn 0x%x, opcode 0x%x, syndrome 0x%x, vendor syndrome 0x%x\n",
+		   sq->cq.mcq.cqn, ci, sq->sqn,
+		   get_cqe_opcode((struct mlx5_cqe64 *)err_cqe),
+		   err_cqe->syndrome, err_cqe->vendor_err_synd);
 	mlx5_dump_err_cqe(sq->cq.mdev, err_cqe);
 }
 
@@ -507,13 +503,13 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
-		if (unlikely(cqe->op_own >> 4 == MLX5_CQE_REQ_ERR)) {
+		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
 			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
 					      &sq->state)) {
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
 				queue_work(cq->channel->priv->wq,
-					   &sq->recover.recover_work);
+					   &sq->recover_work);
 			}
 			stats->cqe_err++;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 85d517360157..b4af5e19f6ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -76,6 +76,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
 	struct mlx5e_ch_stats *ch_stats = c->stats;
+	struct mlx5e_rq *rq = &c->rq;
 	bool busy = false;
 	int work_done = 0;
 	int i;
@@ -85,17 +86,17 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
-	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
+	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq, NULL);
 
 	if (c->xdp)
-		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
+		busy |= mlx5e_poll_xdpsq_cq(&rq->xdpsq.cq, rq);
 
 	if (likely(budget)) { /* budget=0 means: don't poll rx rings */
-		work_done = mlx5e_poll_rx_cq(&c->rq.cq, budget);
+		work_done = mlx5e_poll_rx_cq(&rq->cq, budget);
 		busy |= work_done == budget;
 	}
 
-	busy |= c->rq.post_wqes(&c->rq);
+	busy |= c->rq.post_wqes(rq);
 
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
@@ -115,9 +116,9 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 		mlx5e_cq_arm(&c->sq[i].cq);
 	}
 
-	mlx5e_handle_rx_dim(&c->rq);
+	mlx5e_handle_rx_dim(rq);
 
-	mlx5e_cq_arm(&c->rq.cq);
+	mlx5e_cq_arm(&rq->cq);
 	mlx5e_cq_arm(&c->icosq.cq);
 	mlx5e_cq_arm(&c->xdpsq.cq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index c1e1a16a9b07..bb6e5b5d9681 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -31,20 +31,23 @@
  */
 
 #include <linux/interrupt.h>
+#include <linux/notifier.h>
 #include <linux/module.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
+#include <linux/mlx5/eq.h>
 #include <linux/mlx5/cmd.h>
 #ifdef CONFIG_RFS_ACCEL
 #include <linux/cpu_rmap.h>
 #endif
 #include "mlx5_core.h"
+#include "lib/eq.h"
 #include "fpga/core.h"
 #include "eswitch.h"
 #include "lib/clock.h"
 #include "diag/fw_tracer.h"
 
 enum {
-	MLX5_EQE_SIZE		= sizeof(struct mlx5_eqe),
 	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
 };
 
@@ -55,14 +58,32 @@ enum {
 };
 
 enum {
-	MLX5_NUM_SPARE_EQE	= 0x80,
-	MLX5_NUM_ASYNC_EQE	= 0x1000,
-	MLX5_NUM_CMD_EQE	= 32,
-	MLX5_NUM_PF_DRAIN	= 64,
+	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
 };
 
-enum {
-	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
+struct mlx5_irq_info {
+	cpumask_var_t mask;
+	char name[MLX5_MAX_IRQ_NAME];
+	void *context; /* dev_id provided to request_irq */
+};
+
+struct mlx5_eq_table {
+	struct list_head        comp_eqs_list;
+	struct mlx5_eq          pages_eq;
+	struct mlx5_eq	        cmd_eq;
+	struct mlx5_eq          async_eq;
+
+	struct atomic_notifier_head nh[MLX5_EVENT_TYPE_MAX];
+
+	/* Since CQ DB is stored in async_eq */
+	struct mlx5_nb          cq_err_nb;
+
+	struct mutex            lock; /* sync async eqs creations */
+	int			num_comp_vectors;
+	struct mlx5_irq_info	*irq_info;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap         *rmap;
+#endif
 };
 
 #define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG)	    | \
@@ -78,17 +99,6 @@ enum {
 			       (1ull << MLX5_EVENT_TYPE_SRQ_LAST_WQE)	    | \
 			       (1ull << MLX5_EVENT_TYPE_SRQ_RQ_LIMIT))
 
-struct map_eq_in {
-	u64	mask;
-	u32	reserved;
-	u32	unmap_eqn;
-};
-
-struct cre_des_eq {
-	u8	reserved[15];
-	u8	eqn;
-};
-
 static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 {
 	u32 out[MLX5_ST_SZ_DW(destroy_eq_out)] = {0};
@@ -99,213 +109,56 @@ static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-static struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
-{
-	return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
-}
-
-static struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
-{
-	struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
-
-	return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
-}
-
-static const char *eqe_type_str(u8 type)
-{
-	switch (type) {
-	case MLX5_EVENT_TYPE_COMP:
-		return "MLX5_EVENT_TYPE_COMP";
-	case MLX5_EVENT_TYPE_PATH_MIG:
-		return "MLX5_EVENT_TYPE_PATH_MIG";
-	case MLX5_EVENT_TYPE_COMM_EST:
-		return "MLX5_EVENT_TYPE_COMM_EST";
-	case MLX5_EVENT_TYPE_SQ_DRAINED:
-		return "MLX5_EVENT_TYPE_SQ_DRAINED";
-	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
-		return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
-	case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
-		return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
-	case MLX5_EVENT_TYPE_CQ_ERROR:
-		return "MLX5_EVENT_TYPE_CQ_ERROR";
-	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
-		return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
-	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
-		return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
-	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-		return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
-	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
-		return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
-	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
-		return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
-	case MLX5_EVENT_TYPE_INTERNAL_ERROR:
-		return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
-	case MLX5_EVENT_TYPE_PORT_CHANGE:
-		return "MLX5_EVENT_TYPE_PORT_CHANGE";
-	case MLX5_EVENT_TYPE_GPIO_EVENT:
-		return "MLX5_EVENT_TYPE_GPIO_EVENT";
-	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
-		return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
-	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
-		return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
-	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
-		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
-	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
-		return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
-	case MLX5_EVENT_TYPE_STALL_EVENT:
-		return "MLX5_EVENT_TYPE_STALL_EVENT";
-	case MLX5_EVENT_TYPE_CMD:
-		return "MLX5_EVENT_TYPE_CMD";
-	case MLX5_EVENT_TYPE_PAGE_REQUEST:
-		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
-	case MLX5_EVENT_TYPE_PAGE_FAULT:
-		return "MLX5_EVENT_TYPE_PAGE_FAULT";
-	case MLX5_EVENT_TYPE_PPS_EVENT:
-		return "MLX5_EVENT_TYPE_PPS_EVENT";
-	case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
-		return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
-	case MLX5_EVENT_TYPE_FPGA_ERROR:
-		return "MLX5_EVENT_TYPE_FPGA_ERROR";
-	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
-		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
-	case MLX5_EVENT_TYPE_GENERAL_EVENT:
-		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
-	case MLX5_EVENT_TYPE_DEVICE_TRACER:
-		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
-	default:
-		return "Unrecognized event";
-	}
-}
-
-static enum mlx5_dev_event port_subtype_event(u8 subtype)
-{
-	switch (subtype) {
-	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-		return MLX5_DEV_EVENT_PORT_DOWN;
-	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-		return MLX5_DEV_EVENT_PORT_UP;
-	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-		return MLX5_DEV_EVENT_PORT_INITIALIZED;
-	case MLX5_PORT_CHANGE_SUBTYPE_LID:
-		return MLX5_DEV_EVENT_LID_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-		return MLX5_DEV_EVENT_PKEY_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-		return MLX5_DEV_EVENT_GUID_CHANGE;
-	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-		return MLX5_DEV_EVENT_CLIENT_REREG;
-	}
-	return -1;
-}
-
-static void eq_update_ci(struct mlx5_eq *eq, int arm)
+/* caller must eventually call mlx5_cq_put on the returned cq */
+static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
 {
-	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
-	u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
-
-	__raw_writel((__force u32)cpu_to_be32(val), addr);
-	/* We still want ordering, just not swabbing, so add a barrier */
-	mb();
-}
+	struct mlx5_cq_table *table = &eq->cq_table;
+	struct mlx5_core_cq *cq = NULL;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-static void eqe_pf_action(struct work_struct *work)
-{
-	struct mlx5_pagefault *pfault = container_of(work,
-						     struct mlx5_pagefault,
-						     work);
-	struct mlx5_eq *eq = pfault->eq;
+	rcu_read_lock();
+	cq = radix_tree_lookup(&table->tree, cqn);
+	if (likely(cq))
+		mlx5_cq_hold(cq);
+	rcu_read_unlock();
 
-	mlx5_core_page_fault(eq->dev, pfault);
-	mempool_free(pfault, eq->pf_ctx.pool);
+	return cq;
 }
 
-static void eq_pf_process(struct mlx5_eq *eq)
+static irqreturn_t mlx5_eq_comp_int(int irq, void *eq_ptr)
 {
-	struct mlx5_core_dev *dev = eq->dev;
-	struct mlx5_eqe_page_fault *pf_eqe;
-	struct mlx5_pagefault *pfault;
+	struct mlx5_eq_comp *eq_comp = eq_ptr;
+	struct mlx5_eq *eq = eq_ptr;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
+	u32 cqn = -1;
 
 	while ((eqe = next_eqe_sw(eq))) {
-		pfault = mempool_alloc(eq->pf_ctx.pool, GFP_ATOMIC);
-		if (!pfault) {
-			schedule_work(&eq->pf_ctx.work);
-			break;
-		}
-
+		struct mlx5_core_cq *cq;
+		/* Make sure we read EQ entry contents after we've
+		 * checked the ownership bit.
+		 */
 		dma_rmb();
-		pf_eqe = &eqe->data.page_fault;
-		pfault->event_subtype = eqe->sub_type;
-		pfault->bytes_committed = be32_to_cpu(pf_eqe->bytes_committed);
-
-		mlx5_core_dbg(dev,
-			      "PAGE_FAULT: subtype: 0x%02x, bytes_committed: 0x%06x\n",
-			      eqe->sub_type, pfault->bytes_committed);
-
-		switch (eqe->sub_type) {
-		case MLX5_PFAULT_SUBTYPE_RDMA:
-			/* RDMA based event */
-			pfault->type =
-				be32_to_cpu(pf_eqe->rdma.pftype_token) >> 24;
-			pfault->token =
-				be32_to_cpu(pf_eqe->rdma.pftype_token) &
-				MLX5_24BIT_MASK;
-			pfault->rdma.r_key =
-				be32_to_cpu(pf_eqe->rdma.r_key);
-			pfault->rdma.packet_size =
-				be16_to_cpu(pf_eqe->rdma.packet_length);
-			pfault->rdma.rdma_op_len =
-				be32_to_cpu(pf_eqe->rdma.rdma_op_len);
-			pfault->rdma.rdma_va =
-				be64_to_cpu(pf_eqe->rdma.rdma_va);
-			mlx5_core_dbg(dev,
-				      "PAGE_FAULT: type:0x%x, token: 0x%06x, r_key: 0x%08x\n",
-				      pfault->type, pfault->token,
-				      pfault->rdma.r_key);
-			mlx5_core_dbg(dev,
-				      "PAGE_FAULT: rdma_op_len: 0x%08x, rdma_va: 0x%016llx\n",
-				      pfault->rdma.rdma_op_len,
-				      pfault->rdma.rdma_va);
-			break;
-
-		case MLX5_PFAULT_SUBTYPE_WQE:
-			/* WQE based event */
-			pfault->type =
-				(be32_to_cpu(pf_eqe->wqe.pftype_wq) >> 24) & 0x7;
-			pfault->token =
-				be32_to_cpu(pf_eqe->wqe.token);
-			pfault->wqe.wq_num =
-				be32_to_cpu(pf_eqe->wqe.pftype_wq) &
-				MLX5_24BIT_MASK;
-			pfault->wqe.wqe_index =
-				be16_to_cpu(pf_eqe->wqe.wqe_index);
-			pfault->wqe.packet_size =
-				be16_to_cpu(pf_eqe->wqe.packet_length);
-			mlx5_core_dbg(dev,
-				      "PAGE_FAULT: type:0x%x, token: 0x%06x, wq_num: 0x%06x, wqe_index: 0x%04x\n",
-				      pfault->type, pfault->token,
-				      pfault->wqe.wq_num,
-				      pfault->wqe.wqe_index);
-			break;
-
-		default:
-			mlx5_core_warn(dev,
-				       "Unsupported page fault event sub-type: 0x%02hhx\n",
-				       eqe->sub_type);
-			/* Unsupported page faults should still be
-			 * resolved by the page fault handler
-			 */
+		/* Assume (eqe->type) is always MLX5_EVENT_TYPE_COMP */
+		cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
+
+		cq = mlx5_eq_cq_get(eq, cqn);
+		if (likely(cq)) {
+			++cq->arm_sn;
+			cq->comp(cq);
+			mlx5_cq_put(cq);
+		} else {
+			mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
 		}
 
-		pfault->eq = eq;
-		INIT_WORK(&pfault->work, eqe_pf_action);
-		queue_work(eq->pf_ctx.wq, &pfault->work);
-
 		++eq->cons_index;
 		++set_ci;
 
+		/* The HCA will think the queue has overflowed if we
+		 * don't tell it we've been processing events.  We
+		 * create our EQs with MLX5_NUM_SPARE_EQE extra
+		 * entries, so we must update our consumer index at
+		 * least that often.
+		 */
 		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
 			eq_update_ci(eq, 0);
 			set_ci = 0;
@@ -313,165 +166,41 @@ static void eq_pf_process(struct mlx5_eq *eq)
 	}
 
 	eq_update_ci(eq, 1);
-}
-
-static irqreturn_t mlx5_eq_pf_int(int irq, void *eq_ptr)
-{
-	struct mlx5_eq *eq = eq_ptr;
-	unsigned long flags;
 
-	if (spin_trylock_irqsave(&eq->pf_ctx.lock, flags)) {
-		eq_pf_process(eq);
-		spin_unlock_irqrestore(&eq->pf_ctx.lock, flags);
-	} else {
-		schedule_work(&eq->pf_ctx.work);
-	}
+	if (cqn != -1)
+		tasklet_schedule(&eq_comp->tasklet_ctx.task);
 
 	return IRQ_HANDLED;
 }
 
-/* mempool_refill() was proposed but unfortunately wasn't accepted
- * http://lkml.iu.edu/hypermail/linux/kernel/1512.1/05073.html
- * Chip workaround.
+/* Some architectures don't latch interrupts when they are disabled, so using
+ * mlx5_eq_poll_irq_disabled could end up losing interrupts while trying to
+ * avoid losing them.  It is not recommended to use it, unless this is the last
+ * resort.
  */
-static void mempool_refill(mempool_t *pool)
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq)
 {
-	while (pool->curr_nr < pool->min_nr)
-		mempool_free(mempool_alloc(pool, GFP_KERNEL), pool);
-}
-
-static void eq_pf_action(struct work_struct *work)
-{
-	struct mlx5_eq *eq = container_of(work, struct mlx5_eq, pf_ctx.work);
-
-	mempool_refill(eq->pf_ctx.pool);
-
-	spin_lock_irq(&eq->pf_ctx.lock);
-	eq_pf_process(eq);
-	spin_unlock_irq(&eq->pf_ctx.lock);
-}
-
-static int init_pf_ctx(struct mlx5_eq_pagefault *pf_ctx, const char *name)
-{
-	spin_lock_init(&pf_ctx->lock);
-	INIT_WORK(&pf_ctx->work, eq_pf_action);
-
-	pf_ctx->wq = alloc_ordered_workqueue(name,
-					     WQ_MEM_RECLAIM);
-	if (!pf_ctx->wq)
-		return -ENOMEM;
-
-	pf_ctx->pool = mempool_create_kmalloc_pool
-		(MLX5_NUM_PF_DRAIN, sizeof(struct mlx5_pagefault));
-	if (!pf_ctx->pool)
-		goto err_wq;
-
-	return 0;
-err_wq:
-	destroy_workqueue(pf_ctx->wq);
-	return -ENOMEM;
-}
-
-int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 token,
-				u32 wq_num, u8 type, int error)
-{
-	u32 out[MLX5_ST_SZ_DW(page_fault_resume_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(page_fault_resume_in)]   = {0};
-
-	MLX5_SET(page_fault_resume_in, in, opcode,
-		 MLX5_CMD_OP_PAGE_FAULT_RESUME);
-	MLX5_SET(page_fault_resume_in, in, error, !!error);
-	MLX5_SET(page_fault_resume_in, in, page_fault_type, type);
-	MLX5_SET(page_fault_resume_in, in, wq_number, wq_num);
-	MLX5_SET(page_fault_resume_in, in, token, token);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
-#endif
-
-static void general_event_handler(struct mlx5_core_dev *dev,
-				  struct mlx5_eqe *eqe)
-{
-	switch (eqe->sub_type) {
-	case MLX5_GENERAL_SUBTYPE_DELAY_DROP_TIMEOUT:
-		if (dev->event)
-			dev->event(dev, MLX5_DEV_EVENT_DELAY_DROP_TIMEOUT, 0);
-		break;
-	default:
-		mlx5_core_dbg(dev, "General event with unrecognized subtype: sub_type %d\n",
-			      eqe->sub_type);
-	}
-}
-
-static void mlx5_temp_warning_event(struct mlx5_core_dev *dev,
-				    struct mlx5_eqe *eqe)
-{
-	u64 value_lsb;
-	u64 value_msb;
-
-	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
-	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
-
-	mlx5_core_warn(dev,
-		       "High temperature on sensors with bit set %llx %llx",
-		       value_msb, value_lsb);
-}
-
-/* caller must eventually call mlx5_cq_put on the returned cq */
-static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn)
-{
-	struct mlx5_cq_table *table = &eq->cq_table;
-	struct mlx5_core_cq *cq = NULL;
-
-	spin_lock(&table->lock);
-	cq = radix_tree_lookup(&table->tree, cqn);
-	if (likely(cq))
-		mlx5_cq_hold(cq);
-	spin_unlock(&table->lock);
-
-	return cq;
-}
-
-static void mlx5_eq_cq_completion(struct mlx5_eq *eq, u32 cqn)
-{
-	struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
-
-	if (unlikely(!cq)) {
-		mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
-		return;
-	}
-
-	++cq->arm_sn;
-
-	cq->comp(cq);
-
-	mlx5_cq_put(cq);
-}
-
-static void mlx5_eq_cq_event(struct mlx5_eq *eq, u32 cqn, int event_type)
-{
-	struct mlx5_core_cq *cq = mlx5_eq_cq_get(eq, cqn);
-
-	if (unlikely(!cq)) {
-		mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
-		return;
-	}
+	u32 count_eqe;
 
-	cq->event(cq, event_type);
+	disable_irq(eq->core.irqn);
+	count_eqe = eq->core.cons_index;
+	mlx5_eq_comp_int(eq->core.irqn, eq);
+	count_eqe = eq->core.cons_index - count_eqe;
+	enable_irq(eq->core.irqn);
 
-	mlx5_cq_put(cq);
+	return count_eqe;
 }
 
-static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
+static irqreturn_t mlx5_eq_async_int(int irq, void *eq_ptr)
 {
 	struct mlx5_eq *eq = eq_ptr;
-	struct mlx5_core_dev *dev = eq->dev;
+	struct mlx5_eq_table *eqt;
+	struct mlx5_core_dev *dev;
 	struct mlx5_eqe *eqe;
 	int set_ci = 0;
-	u32 cqn = -1;
-	u32 rsn;
-	u8 port;
+
+	dev = eq->dev;
+	eqt = dev->priv.eq_table;
 
 	while ((eqe = next_eqe_sw(eq))) {
 		/*
@@ -480,116 +209,12 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 		 */
 		dma_rmb();
 
-		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
-			      eq->eqn, eqe_type_str(eqe->type));
-		switch (eqe->type) {
-		case MLX5_EVENT_TYPE_COMP:
-			cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
-			mlx5_eq_cq_completion(eq, cqn);
-			break;
-		case MLX5_EVENT_TYPE_DCT_DRAINED:
-			rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
-			rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
-			mlx5_rsc_event(dev, rsn, eqe->type);
-			break;
-		case MLX5_EVENT_TYPE_PATH_MIG:
-		case MLX5_EVENT_TYPE_COMM_EST:
-		case MLX5_EVENT_TYPE_SQ_DRAINED:
-		case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
-		case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
-		case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
-		case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
-		case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
-			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-			rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
-			mlx5_core_dbg(dev, "event %s(%d) arrived on resource 0x%x\n",
-				      eqe_type_str(eqe->type), eqe->type, rsn);
-			mlx5_rsc_event(dev, rsn, eqe->type);
-			break;
-
-		case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
-		case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
-			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
-			mlx5_core_dbg(dev, "SRQ event %s(%d): srqn 0x%x\n",
-				      eqe_type_str(eqe->type), eqe->type, rsn);
-			mlx5_srq_event(dev, rsn, eqe->type);
-			break;
-
-		case MLX5_EVENT_TYPE_CMD:
-			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector), false);
-			break;
-
-		case MLX5_EVENT_TYPE_PORT_CHANGE:
-			port = (eqe->data.port.port >> 4) & 0xf;
-			switch (eqe->sub_type) {
-			case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
-			case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
-			case MLX5_PORT_CHANGE_SUBTYPE_LID:
-			case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
-			case MLX5_PORT_CHANGE_SUBTYPE_GUID:
-			case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
-			case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
-				if (dev->event)
-					dev->event(dev, port_subtype_event(eqe->sub_type),
-						   (unsigned long)port);
-				break;
-			default:
-				mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
-					       port, eqe->sub_type);
-			}
-			break;
-		case MLX5_EVENT_TYPE_CQ_ERROR:
-			cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
-			mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
-				       cqn, eqe->data.cq_err.syndrome);
-			mlx5_eq_cq_event(eq, cqn, eqe->type);
-			break;
+		if (likely(eqe->type < MLX5_EVENT_TYPE_MAX))
+			atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe);
+		else
+			mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type);
 
-		case MLX5_EVENT_TYPE_PAGE_REQUEST:
-			{
-				u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
-				s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);
-
-				mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
-					      func_id, npages);
-				mlx5_core_req_pages_handler(dev, func_id, npages);
-			}
-			break;
-
-		case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
-			mlx5_eswitch_vport_event(dev->priv.eswitch, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
-			mlx5_port_module_event(dev, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_PPS_EVENT:
-			mlx5_pps_event(dev, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_FPGA_ERROR:
-		case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
-			mlx5_fpga_event(dev, eqe->type, &eqe->data.raw);
-			break;
-
-		case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
-			mlx5_temp_warning_event(dev, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_GENERAL_EVENT:
-			general_event_handler(dev, eqe);
-			break;
-
-		case MLX5_EVENT_TYPE_DEVICE_TRACER:
-			mlx5_fw_tracer_event(dev, eqe);
-			break;
-
-		default:
-			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
-				       eqe->type, eq->eqn);
-			break;
-		}
+		atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe);
 
 		++eq->cons_index;
 		++set_ci;
@@ -608,30 +233,9 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 
 	eq_update_ci(eq, 1);
 
-	if (cqn != -1)
-		tasklet_schedule(&eq->tasklet_ctx.task);
-
 	return IRQ_HANDLED;
 }
 
-/* Some architectures don't latch interrupts when they are disabled, so using
- * mlx5_eq_poll_irq_disabled could end up losing interrupts while trying to
- * avoid losing them.  It is not recommended to use it, unless this is the last
- * resort.
- */
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq)
-{
-	u32 count_eqe;
-
-	disable_irq(eq->irqn);
-	count_eqe = eq->cons_index;
-	mlx5_eq_int(eq->irqn, eq);
-	count_eqe = eq->cons_index - count_eqe;
-	enable_irq(eq->irqn);
-
-	return count_eqe;
-}
-
 static void init_eq_buf(struct mlx5_eq *eq)
 {
 	struct mlx5_eqe *eqe;
@@ -643,39 +247,35 @@ static void init_eq_buf(struct mlx5_eq *eq)
 	}
 }
 
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name,
-		       enum mlx5_eq_type type)
+static int
+create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, const char *name,
+	      struct mlx5_eq_param *param)
 {
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	struct mlx5_cq_table *cq_table = &eq->cq_table;
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
-	irq_handler_t handler;
+	u8 vecidx = param->index;
 	__be64 *pas;
 	void *eqc;
 	int inlen;
 	u32 *in;
 	int err;
 
+	if (eq_table->irq_info[vecidx].context)
+		return -EEXIST;
+
 	/* Init CQ table */
 	memset(cq_table, 0, sizeof(*cq_table));
 	spin_lock_init(&cq_table->lock);
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
 
-	eq->type = type;
-	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
+	eq->nent = roundup_pow_of_two(param->nent + MLX5_NUM_SPARE_EQE);
 	eq->cons_index = 0;
 	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf);
 	if (err)
 		return err;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (type == MLX5_EQ_TYPE_PF)
-		handler = mlx5_eq_pf_int;
-	else
-#endif
-		handler = mlx5_eq_int;
-
 	init_eq_buf(eq);
 
 	inlen = MLX5_ST_SZ_BYTES(create_eq_in) +
@@ -691,7 +291,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	mlx5_fill_page_array(&eq->buf, pas);
 
 	MLX5_SET(create_eq_in, in, opcode, MLX5_CMD_OP_CREATE_EQ);
-	MLX5_SET64(create_eq_in, in, event_bitmask, mask);
+	MLX5_SET64(create_eq_in, in, event_bitmask, param->mask);
 
 	eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry);
 	MLX5_SET(eqc, eqc, log_eq_size, ilog2(eq->nent));
@@ -704,15 +304,17 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	if (err)
 		goto err_in;
 
-	snprintf(priv->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
+	snprintf(eq_table->irq_info[vecidx].name, MLX5_MAX_IRQ_NAME, "%s@pci:%s",
 		 name, pci_name(dev->pdev));
+	eq_table->irq_info[vecidx].context = param->context;
 
+	eq->vecidx = vecidx;
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
 	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
-	err = request_irq(eq->irqn, handler, 0,
-			  priv->irq_info[vecidx].name, eq);
+	err = request_irq(eq->irqn, param->handler, 0,
+			  eq_table->irq_info[vecidx].name, param->context);
 	if (err)
 		goto err_eq;
 
@@ -720,21 +322,6 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	if (err)
 		goto err_irq;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (type == MLX5_EQ_TYPE_PF) {
-		err = init_pf_ctx(&eq->pf_ctx, name);
-		if (err)
-			goto err_irq;
-	} else
-#endif
-	{
-		INIT_LIST_HEAD(&eq->tasklet_ctx.list);
-		INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
-		spin_lock_init(&eq->tasklet_ctx.lock);
-		tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
-			     (unsigned long)&eq->tasklet_ctx);
-	}
-
 	/* EQs are created in ARMED state
 	 */
 	eq_update_ci(eq, 1);
@@ -756,27 +343,25 @@ err_buf:
 	return err;
 }
 
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+static int destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 {
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	struct mlx5_irq_info *irq_info;
 	int err;
 
+	irq_info = &eq_table->irq_info[eq->vecidx];
+
 	mlx5_debug_eq_remove(dev, eq);
-	free_irq(eq->irqn, eq);
+
+	free_irq(eq->irqn, irq_info->context);
+	irq_info->context = NULL;
+
 	err = mlx5_cmd_destroy_eq(dev, eq->eqn);
 	if (err)
 		mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
 			       eq->eqn);
 	synchronize_irq(eq->irqn);
 
-	if (eq->type == MLX5_EQ_TYPE_COMP) {
-		tasklet_disable(&eq->tasklet_ctx.task);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	} else if (eq->type == MLX5_EQ_TYPE_PF) {
-		cancel_work_sync(&eq->pf_ctx.work);
-		destroy_workqueue(eq->pf_ctx.wq);
-		mempool_destroy(eq->pf_ctx.pool);
-#endif
-	}
 	mlx5_buf_free(dev, &eq->buf);
 
 	return err;
@@ -787,9 +372,9 @@ int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	int err;
 
-	spin_lock_irq(&table->lock);
+	spin_lock(&table->lock);
 	err = radix_tree_insert(&table->tree, cq->cqn, cq);
-	spin_unlock_irq(&table->lock);
+	spin_unlock(&table->lock);
 
 	return err;
 }
@@ -799,9 +384,9 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	struct mlx5_cq_table *table = &eq->cq_table;
 	struct mlx5_core_cq *tmp;
 
-	spin_lock_irq(&table->lock);
+	spin_lock(&table->lock);
 	tmp = radix_tree_delete(&table->tree, cq->cqn);
-	spin_unlock_irq(&table->lock);
+	spin_unlock(&table->lock);
 
 	if (!tmp) {
 		mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn);
@@ -816,28 +401,106 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	return 0;
 }
 
-int mlx5_eq_init(struct mlx5_core_dev *dev)
+int mlx5_eq_table_init(struct mlx5_core_dev *dev)
 {
-	int err;
+	struct mlx5_eq_table *eq_table;
+	int i, err;
 
-	spin_lock_init(&dev->priv.eq_table.lock);
+	eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL);
+	if (!eq_table)
+		return -ENOMEM;
+
+	dev->priv.eq_table = eq_table;
 
 	err = mlx5_eq_debugfs_init(dev);
+	if (err)
+		goto kvfree_eq_table;
 
+	mutex_init(&eq_table->lock);
+	for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++)
+		ATOMIC_INIT_NOTIFIER_HEAD(&eq_table->nh[i]);
+
+	return 0;
+
+kvfree_eq_table:
+	kvfree(eq_table);
+	dev->priv.eq_table = NULL;
 	return err;
 }
 
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev)
 {
 	mlx5_eq_debugfs_cleanup(dev);
+	kvfree(dev->priv.eq_table);
 }
 
-int mlx5_start_eqs(struct mlx5_core_dev *dev)
+/* Async EQs */
+
+static int create_async_eq(struct mlx5_core_dev *dev, const char *name,
+			   struct mlx5_eq *eq, struct mlx5_eq_param *param)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
+	int err;
+
+	mutex_lock(&eq_table->lock);
+	if (param->index >= MLX5_EQ_MAX_ASYNC_EQS) {
+		err = -ENOSPC;
+		goto unlock;
+	}
+
+	err = create_map_eq(dev, eq, name, param);
+unlock:
+	mutex_unlock(&eq_table->lock);
+	return err;
+}
+
+static int destroy_async_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+	struct mlx5_eq_table *eq_table = dev->priv.eq_table;
 	int err;
 
+	mutex_lock(&eq_table->lock);
+	err = destroy_unmap_eq(dev, eq);
+	mutex_unlock(&eq_table->lock);
+	return err;
+}
+
+static int cq_err_event_notifier(struct notifier_block *nb,
+				 unsigned long type, void *data)
+{
+	struct mlx5_eq_table *eqt;
+	struct mlx5_core_cq *cq;
+	struct mlx5_eqe *eqe;
+	struct mlx5_eq *eq;
+	u32 cqn;
+
+	/* type == MLX5_EVENT_TYPE_CQ_ERROR */
+
+	eqt = mlx5_nb_cof(nb, struct mlx5_eq_table, cq_err_nb);
+	eq  = &eqt->async_eq;
+	eqe = data;
+
+	cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
+	mlx5_core_warn(eq->dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
+		       cqn, eqe->data.cq_err.syndrome);
+
+	cq = mlx5_eq_cq_get(eq, cqn);
+	if (unlikely(!cq)) {
+		mlx5_core_warn(eq->dev, "Async event for bogus CQ 0x%x\n", cqn);
+		return NOTIFY_OK;
+	}
+
+	cq->event(cq, type);
+
+	mlx5_cq_put(cq);
+
+	return NOTIFY_OK;
+}
+
+static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
+{
+	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
+
 	if (MLX5_VPORT_MANAGER(dev))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_NIC_VPORT_CHANGE);
 
@@ -865,127 +528,524 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
 
-	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
-				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
-				 "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC);
+	if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER);
+
+	if (mlx5_core_is_ecpf_esw_manager(dev))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE);
+
+	return async_event_mask;
+}
+
+static int create_async_eqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_param param = {};
+	int err;
+
+	MLX5_NB_INIT(&table->cq_err_nb, cq_err_event_notifier, CQ_ERROR);
+	mlx5_eq_notifier_register(dev, &table->cq_err_nb);
+
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_CMD_IDX,
+		.mask = 1ull << MLX5_EVENT_TYPE_CMD,
+		.nent = MLX5_NUM_CMD_EQE,
+		.context = &table->cmd_eq,
+		.handler = mlx5_eq_async_int,
+	};
+	err = create_async_eq(dev, "mlx5_cmd_eq", &table->cmd_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
-		return err;
+		goto err0;
 	}
 
 	mlx5_cmd_use_events(dev);
 
-	err = mlx5_create_map_eq(dev, &table->async_eq, MLX5_EQ_VEC_ASYNC,
-				 MLX5_NUM_ASYNC_EQE, async_event_mask,
-				 "mlx5_async_eq", MLX5_EQ_TYPE_ASYNC);
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_ASYNC_IDX,
+		.mask = gather_async_events_mask(dev),
+		.nent = MLX5_NUM_ASYNC_EQE,
+		.context = &table->async_eq,
+		.handler = mlx5_eq_async_int,
+	};
+	err = create_async_eq(dev, "mlx5_async_eq", &table->async_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
 		goto err1;
 	}
 
-	err = mlx5_create_map_eq(dev, &table->pages_eq,
-				 MLX5_EQ_VEC_PAGES,
-				 /* TODO: sriov max_vf + */ 1,
-				 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
-				 MLX5_EQ_TYPE_ASYNC);
+	param = (struct mlx5_eq_param) {
+		.index = MLX5_EQ_PAGEREQ_IDX,
+		.mask =  1 << MLX5_EVENT_TYPE_PAGE_REQUEST,
+		.nent = /* TODO: sriov max_vf + */ 1,
+		.context = &table->pages_eq,
+		.handler = mlx5_eq_async_int,
+	};
+	err = create_async_eq(dev, "mlx5_pages_eq", &table->pages_eq, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
 		goto err2;
 	}
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (MLX5_CAP_GEN(dev, pg)) {
-		err = mlx5_create_map_eq(dev, &table->pfault_eq,
-					 MLX5_EQ_VEC_PFAULT,
-					 MLX5_NUM_ASYNC_EQE,
-					 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
-					 "mlx5_page_fault_eq",
-					 MLX5_EQ_TYPE_PF);
-		if (err) {
-			mlx5_core_warn(dev, "failed to create page fault EQ %d\n",
-				       err);
-			goto err3;
-		}
-	}
-
 	return err;
-err3:
-	mlx5_destroy_unmap_eq(dev, &table->pages_eq);
-#else
-	return err;
-#endif
 
 err2:
-	mlx5_destroy_unmap_eq(dev, &table->async_eq);
+	destroy_async_eq(dev, &table->async_eq);
 
 err1:
 	mlx5_cmd_use_polling(dev);
-	mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
+	destroy_async_eq(dev, &table->cmd_eq);
+err0:
+	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
 	return err;
 }
 
-void mlx5_stop_eqs(struct mlx5_core_dev *dev)
+static void destroy_async_eqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
 	int err;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (MLX5_CAP_GEN(dev, pg)) {
-		err = mlx5_destroy_unmap_eq(dev, &table->pfault_eq);
-		if (err)
-			mlx5_core_err(dev, "failed to destroy page fault eq, err(%d)\n",
-				      err);
-	}
-#endif
-
-	err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
+	err = destroy_async_eq(dev, &table->pages_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy pages eq, err(%d)\n",
 			      err);
 
-	err = mlx5_destroy_unmap_eq(dev, &table->async_eq);
+	err = destroy_async_eq(dev, &table->async_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy async eq, err(%d)\n",
 			      err);
+
 	mlx5_cmd_use_polling(dev);
 
-	err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
+	err = destroy_async_eq(dev, &table->cmd_eq);
 	if (err)
 		mlx5_core_err(dev, "failed to destroy command eq, err(%d)\n",
 			      err);
+
+	mlx5_eq_notifier_unregister(dev, &table->cq_err_nb);
+}
+
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev)
+{
+	return &dev->priv.eq_table->async_eq;
+}
+
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev)
+{
+	synchronize_irq(dev->priv.eq_table->async_eq.irqn);
+}
+
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev)
+{
+	synchronize_irq(dev->priv.eq_table->cmd_eq.irqn);
+}
+
+/* Generic EQ API for mlx5_core consumers
+ * Needed For RDMA ODP EQ for now
+ */
+struct mlx5_eq *
+mlx5_eq_create_generic(struct mlx5_core_dev *dev, const char *name,
+		       struct mlx5_eq_param *param)
+{
+	struct mlx5_eq *eq = kvzalloc(sizeof(*eq), GFP_KERNEL);
+	int err;
+
+	if (!eq)
+		return ERR_PTR(-ENOMEM);
+
+	err = create_async_eq(dev, name, eq, param);
+	if (err) {
+		kvfree(eq);
+		eq = ERR_PTR(err);
+	}
+
+	return eq;
+}
+EXPORT_SYMBOL(mlx5_eq_create_generic);
+
+int mlx5_eq_destroy_generic(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
+{
+	int err;
+
+	if (IS_ERR(eq))
+		return -EINVAL;
+
+	err = destroy_async_eq(dev, eq);
+	if (err)
+		goto out;
+
+	kvfree(eq);
+out:
+	return err;
 }
+EXPORT_SYMBOL(mlx5_eq_destroy_generic);
 
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-		       u32 *out, int outlen)
+struct mlx5_eqe *mlx5_eq_get_eqe(struct mlx5_eq *eq, u32 cc)
 {
-	u32 in[MLX5_ST_SZ_DW(query_eq_in)] = {0};
+	u32 ci = eq->cons_index + cc;
+	struct mlx5_eqe *eqe;
+
+	eqe = get_eqe(eq, ci & (eq->nent - 1));
+	eqe = ((eqe->owner & 1) ^ !!(ci & eq->nent)) ? NULL : eqe;
+	/* Make sure we read EQ entry contents after we've
+	 * checked the ownership bit.
+	 */
+	if (eqe)
+		dma_rmb();
 
-	MLX5_SET(query_eq_in, in, opcode, MLX5_CMD_OP_QUERY_EQ);
-	MLX5_SET(query_eq_in, in, eq_number, eq->eqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
+	return eqe;
+}
+EXPORT_SYMBOL(mlx5_eq_get_eqe);
+
+void mlx5_eq_update_ci(struct mlx5_eq *eq, u32 cc, bool arm)
+{
+	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+	u32 val;
+
+	eq->cons_index += cc;
+	val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+	__raw_writel((__force u32)cpu_to_be32(val), addr);
+	/* We still want ordering, just not swabbing, so add a barrier */
+	mb();
+}
+EXPORT_SYMBOL(mlx5_eq_update_ci);
+
+/* Completion EQs */
+
+static int set_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	struct mlx5_priv *priv  = &mdev->priv;
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	int irq = pci_irq_vector(mdev->pdev, vecidx);
+	struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
+
+	if (!zalloc_cpumask_var(&irq_info->mask, GFP_KERNEL)) {
+		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
+			irq_info->mask);
+
+	if (IS_ENABLED(CONFIG_SMP) &&
+	    irq_set_affinity_hint(irq, irq_info->mask))
+		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
+
+	return 0;
+}
+
+static void clear_comp_irq_affinity_hint(struct mlx5_core_dev *mdev, int i)
+{
+	int vecidx = MLX5_EQ_VEC_COMP_BASE + i;
+	struct mlx5_priv *priv  = &mdev->priv;
+	int irq = pci_irq_vector(mdev->pdev, vecidx);
+	struct mlx5_irq_info *irq_info = &priv->eq_table->irq_info[vecidx];
+
+	irq_set_affinity_hint(irq, NULL);
+	free_cpumask_var(irq_info->mask);
+}
+
+static int set_comp_irq_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int err;
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++) {
+		err = set_comp_irq_affinity_hint(mdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		clear_comp_irq_affinity_hint(mdev, i);
+
+	return err;
+}
+
+static void clear_comp_irqs_affinity_hints(struct mlx5_core_dev *mdev)
+{
+	int i;
+
+	for (i = 0; i < mdev->priv.eq_table->num_comp_vectors; i++)
+		clear_comp_irq_affinity_hint(mdev, i);
+}
+
+static void destroy_comp_eqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_comp *eq, *n;
+
+	clear_comp_irqs_affinity_hints(dev);
+
+#ifdef CONFIG_RFS_ACCEL
+	if (table->rmap) {
+		free_irq_cpu_rmap(table->rmap);
+		table->rmap = NULL;
+	}
+#endif
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		list_del(&eq->list);
+		if (destroy_unmap_eq(dev, &eq->core))
+			mlx5_core_warn(dev, "failed to destroy comp EQ 0x%x\n",
+				       eq->core.eqn);
+		tasklet_disable(&eq->tasklet_ctx.task);
+		kfree(eq);
+	}
+}
+
+static int create_comp_eqs(struct mlx5_core_dev *dev)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	char name[MLX5_MAX_IRQ_NAME];
+	struct mlx5_eq_comp *eq;
+	int ncomp_vec;
+	int nent;
+	int err;
+	int i;
+
+	INIT_LIST_HEAD(&table->comp_eqs_list);
+	ncomp_vec = table->num_comp_vectors;
+	nent = MLX5_COMP_EQ_SIZE;
+#ifdef CONFIG_RFS_ACCEL
+	table->rmap = alloc_irq_cpu_rmap(ncomp_vec);
+	if (!table->rmap)
+		return -ENOMEM;
+#endif
+	for (i = 0; i < ncomp_vec; i++) {
+		int vecidx = i + MLX5_EQ_VEC_COMP_BASE;
+		struct mlx5_eq_param param = {};
+
+		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
+		if (!eq) {
+			err = -ENOMEM;
+			goto clean;
+		}
+
+		INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+		INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+		spin_lock_init(&eq->tasklet_ctx.lock);
+		tasklet_init(&eq->tasklet_ctx.task, mlx5_cq_tasklet_cb,
+			     (unsigned long)&eq->tasklet_ctx);
+
+#ifdef CONFIG_RFS_ACCEL
+		irq_cpu_rmap_add(table->rmap, pci_irq_vector(dev->pdev, vecidx));
+#endif
+		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
+		param = (struct mlx5_eq_param) {
+			.index = vecidx,
+			.mask = 0,
+			.nent = nent,
+			.context = &eq->core,
+			.handler = mlx5_eq_comp_int
+		};
+		err = create_map_eq(dev, &eq->core, name, &param);
+		if (err) {
+			kfree(eq);
+			goto clean;
+		}
+		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->core.eqn);
+		/* add tail, to keep the list ordered, for mlx5_vector2eqn to work */
+		list_add_tail(&eq->list, &table->comp_eqs_list);
+	}
+
+	err = set_comp_irq_affinity_hints(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to alloc affinity hint cpumask\n");
+		goto clean;
+	}
+
+	return 0;
+
+clean:
+	destroy_comp_eqs(dev);
+	return err;
+}
+
+int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
+		    unsigned int *irqn)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_comp *eq, *n;
+	int err = -ENOENT;
+	int i = 0;
+
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		if (i++ == vector) {
+			*eqn = eq->core.eqn;
+			*irqn = eq->core.irqn;
+			err = 0;
+			break;
+		}
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(mlx5_vector2eqn);
+
+unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev)
+{
+	return dev->priv.eq_table->num_comp_vectors;
+}
+EXPORT_SYMBOL(mlx5_comp_vectors_count);
+
+struct cpumask *
+mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector)
+{
+	/* TODO: consider irq_get_affinity_mask(irq) */
+	return dev->priv.eq_table->irq_info[vector + MLX5_EQ_VEC_COMP_BASE].mask;
+}
+EXPORT_SYMBOL(mlx5_comp_irq_get_affinity_mask);
+
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev)
+{
+#ifdef CONFIG_RFS_ACCEL
+	return dev->priv.eq_table->rmap;
+#else
+	return NULL;
+#endif
+}
+
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn)
+{
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	struct mlx5_eq_comp *eq;
+
+	list_for_each_entry(eq, &table->comp_eqs_list, list) {
+		if (eq->core.eqn == eqn)
+			return eq;
+	}
+
+	return ERR_PTR(-ENOENT);
 }
 
 /* This function should only be called after mlx5_cmd_force_teardown_hca */
 void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev)
 {
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq;
+	struct mlx5_eq_table *table = dev->priv.eq_table;
+	int i, max_eqs;
+
+	clear_comp_irqs_affinity_hints(dev);
 
 #ifdef CONFIG_RFS_ACCEL
-	if (dev->rmap) {
-		free_irq_cpu_rmap(dev->rmap);
-		dev->rmap = NULL;
+	if (table->rmap) {
+		free_irq_cpu_rmap(table->rmap);
+		table->rmap = NULL;
 	}
 #endif
-	list_for_each_entry(eq, &table->comp_eqs_list, list)
-		free_irq(eq->irqn, eq);
-
-	free_irq(table->pages_eq.irqn, &table->pages_eq);
-	free_irq(table->async_eq.irqn, &table->async_eq);
-	free_irq(table->cmd_eq.irqn, &table->cmd_eq);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (MLX5_CAP_GEN(dev, pg))
-		free_irq(table->pfault_eq.irqn, &table->pfault_eq);
-#endif
+
+	mutex_lock(&table->lock); /* sync with create/destroy_async_eq */
+	max_eqs = table->num_comp_vectors + MLX5_EQ_VEC_COMP_BASE;
+	for (i = max_eqs - 1; i >= 0; i--) {
+		if (!table->irq_info[i].context)
+			continue;
+		free_irq(pci_irq_vector(dev->pdev, i), table->irq_info[i].context);
+		table->irq_info[i].context = NULL;
+	}
+	mutex_unlock(&table->lock);
+	pci_free_irq_vectors(dev->pdev);
+}
+
+static int alloc_irq_vectors(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+	struct mlx5_eq_table *table = priv->eq_table;
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int nvec;
+	int err;
+
+	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
+	       MLX5_EQ_VEC_COMP_BASE;
+	nvec = min_t(int, nvec, num_eqs);
+	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
+		return -ENOMEM;
+
+	table->irq_info = kcalloc(nvec, sizeof(*table->irq_info), GFP_KERNEL);
+	if (!table->irq_info)
+		return -ENOMEM;
+
+	nvec = pci_alloc_irq_vectors(dev->pdev, MLX5_EQ_VEC_COMP_BASE + 1,
+				     nvec, PCI_IRQ_MSIX);
+	if (nvec < 0) {
+		err = nvec;
+		goto err_free_irq_info;
+	}
+
+	table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
+
+	return 0;
+
+err_free_irq_info:
+	kfree(table->irq_info);
+	return err;
+}
+
+static void free_irq_vectors(struct mlx5_core_dev *dev)
+{
+	struct mlx5_priv *priv = &dev->priv;
+
 	pci_free_irq_vectors(dev->pdev);
+	kfree(priv->eq_table->irq_info);
+}
+
+int mlx5_eq_table_create(struct mlx5_core_dev *dev)
+{
+	int err;
+
+	err = alloc_irq_vectors(dev);
+	if (err) {
+		mlx5_core_err(dev, "alloc irq vectors failed\n");
+		return err;
+	}
+
+	err = create_async_eqs(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to create async EQs\n");
+		goto err_async_eqs;
+	}
+
+	err = create_comp_eqs(dev);
+	if (err) {
+		mlx5_core_err(dev, "Failed to create completion EQs\n");
+		goto err_comp_eqs;
+	}
+
+	return 0;
+err_comp_eqs:
+	destroy_async_eqs(dev);
+err_async_eqs:
+	free_irq_vectors(dev);
+	return err;
+}
+
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev)
+{
+	destroy_comp_eqs(dev);
+	destroy_async_eqs(dev);
+	free_irq_vectors(dev);
+}
+
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
+{
+	struct mlx5_eq_table *eqt = dev->priv.eq_table;
+
+	if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb);
+}
+
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
+{
+	struct mlx5_eq_table *eqt = dev->priv.eq_table;
+
+	if (nb->event_type >= MLX5_EVENT_TYPE_MAX)
+		return -EINVAL;
+
+	return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index d004957328f9..8a67fd197b79 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -36,10 +36,10 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 #include "eswitch.h"
 #include "fs_core.h"
-
-#define UPLINK_VPORT 0xFFFF
+#include "ecpf.h"
 
 enum {
 	MLX5_ACTION_NONE = 0,
@@ -51,7 +51,7 @@ enum {
 struct vport_addr {
 	struct l2addr_node     node;
 	u8                     action;
-	u32                    vport;
+	u16                    vport;
 	struct mlx5_flow_handle *flow_rule;
 	bool mpfs; /* UC MAC was added to MPFs */
 	/* A flag indicating that mac was added due to mc promiscuous vport */
@@ -64,11 +64,36 @@ enum {
 	PROMISC_CHANGE = BIT(3),
 };
 
+static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw);
+static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw);
+
 /* Vport context events */
 #define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \
 			    MC_ADDR_CHANGE | \
 			    PROMISC_CHANGE)
 
+/* The vport getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_vports(esw, i, vport)			\
+	for ((i) = MLX5_VPORT_PF;				\
+	     (vport) = &(esw)->vports[i],			\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)	\
+	for ((i) = MLX5_VPORT_FIRST_VF;				\
+	     (vport) = &(esw)->vports[i],			\
+	     (i) <= (nvfs); (i)++)
+
+static struct mlx5_vport *mlx5_eswitch_get_vport(struct mlx5_eswitch *esw,
+						 u16 vport_num)
+{
+	u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	WARN_ON(idx > esw->total_vports - 1);
+	return &esw->vports[idx];
+}
+
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 					u32 events_mask)
 {
@@ -80,8 +105,7 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 		 opcode, MLX5_CMD_OP_MODIFY_NIC_VPORT_CONTEXT);
 	MLX5_SET(modify_nic_vport_context_in, in, field_select.change_event, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 	nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
 				     in, nic_vport_context);
 
@@ -109,12 +133,11 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
 	MLX5_SET(modify_esw_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
 	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
 	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 }
 
-static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
+static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 				  u16 vlan, u8 qos, u8 set_flags)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0};
@@ -151,7 +174,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport,
 
 /* E-Switch FDB */
 static struct mlx5_flow_handle *
-__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
+__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule,
 			 u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN])
 {
 	int match_header = (is_zero_ether_addr(mac_c) ? 0 :
@@ -187,7 +210,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 					misc_parameters);
 		mc_misc  = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
 					misc_parameters);
-		MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT);
+		MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK);
 		MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port);
 	}
 
@@ -214,7 +237,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule,
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
+esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 
@@ -223,7 +246,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport)
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 	u8 mac_v[ETH_ALEN];
@@ -236,7 +259,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport)
 }
 
 static struct mlx5_flow_handle *
-esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
+esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport)
 {
 	u8 mac_c[ETH_ALEN];
 	u8 mac_v[ETH_ALEN];
@@ -246,6 +269,37 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
 }
 
+enum {
+	LEGACY_VEPA_PRIO = 0,
+	LEGACY_FDB_PRIO,
+};
+
+static int esw_create_legacy_vepa_table(struct mlx5_eswitch *esw)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *fdb;
+	int err;
+
+	root_ns = mlx5_get_fdb_sub_ns(dev, 0);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get FDB flow namespace\n");
+		return -EOPNOTSUPP;
+	}
+
+	/* num FTE 2, num FG 2 */
+	fdb = mlx5_create_auto_grouped_flow_table(root_ns, LEGACY_VEPA_PRIO,
+						  2, 2, 0, 0);
+	if (IS_ERR(fdb)) {
+		err = PTR_ERR(fdb);
+		esw_warn(dev, "Failed to create VEPA FDB err %d\n", err);
+		return err;
+	}
+	esw->fdb_table.legacy.vepa_fdb = fdb;
+
+	return 0;
+}
+
 static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -274,8 +328,8 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 		return -ENOMEM;
 
 	table_size = BIT(MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size));
-
 	ft_attr.max_fte = table_size;
+	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
 		err = PTR_ERR(fdb);
@@ -334,41 +388,67 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	esw->fdb_table.legacy.promisc_grp = g;
 
 out:
-	if (err) {
-		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.allmulti_grp)) {
-			mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
-			esw->fdb_table.legacy.allmulti_grp = NULL;
-		}
-		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.addr_grp)) {
-			mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
-			esw->fdb_table.legacy.addr_grp = NULL;
-		}
-		if (!IS_ERR_OR_NULL(esw->fdb_table.legacy.fdb)) {
-			mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);
-			esw->fdb_table.legacy.fdb = NULL;
-		}
-	}
+	if (err)
+		esw_destroy_legacy_fdb_table(esw);
 
 	kvfree(flow_group_in);
 	return err;
 }
 
+static void esw_destroy_legacy_vepa_table(struct mlx5_eswitch *esw)
+{
+	esw_debug(esw->dev, "Destroy VEPA Table\n");
+	if (!esw->fdb_table.legacy.vepa_fdb)
+		return;
+
+	mlx5_destroy_flow_table(esw->fdb_table.legacy.vepa_fdb);
+	esw->fdb_table.legacy.vepa_fdb = NULL;
+}
+
 static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
+	esw_debug(esw->dev, "Destroy FDB Table\n");
 	if (!esw->fdb_table.legacy.fdb)
 		return;
 
-	esw_debug(esw->dev, "Destroy FDB Table\n");
-	mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
-	mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
+	if (esw->fdb_table.legacy.promisc_grp)
+		mlx5_destroy_flow_group(esw->fdb_table.legacy.promisc_grp);
+	if (esw->fdb_table.legacy.allmulti_grp)
+		mlx5_destroy_flow_group(esw->fdb_table.legacy.allmulti_grp);
+	if (esw->fdb_table.legacy.addr_grp)
+		mlx5_destroy_flow_group(esw->fdb_table.legacy.addr_grp);
 	mlx5_destroy_flow_table(esw->fdb_table.legacy.fdb);
+
 	esw->fdb_table.legacy.fdb = NULL;
 	esw->fdb_table.legacy.addr_grp = NULL;
 	esw->fdb_table.legacy.allmulti_grp = NULL;
 	esw->fdb_table.legacy.promisc_grp = NULL;
 }
 
+static int esw_create_legacy_table(struct mlx5_eswitch *esw)
+{
+	int err;
+
+	memset(&esw->fdb_table.legacy, 0, sizeof(struct legacy_fdb));
+
+	err = esw_create_legacy_vepa_table(esw);
+	if (err)
+		return err;
+
+	err = esw_create_legacy_fdb_table(esw);
+	if (err)
+		esw_destroy_legacy_vepa_table(esw);
+
+	return err;
+}
+
+static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
+{
+	esw_cleanup_vepa_rules(esw);
+	esw_destroy_legacy_fdb_table(esw);
+	esw_destroy_legacy_vepa_table(esw);
+}
+
 /* E-Switch vport UC/MC lists management */
 typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
 				 struct vport_addr *vaddr);
@@ -376,19 +456,19 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw,
 static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 	int err;
 
-	/* Skip mlx5_mpfs_add_mac for PFs,
-	 * it is already done by the PF netdev in mlx5e_execute_l2_action
+	/* Skip mlx5_mpfs_add_mac for eswitch_managers,
+	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vport)
+	if (esw->manager_vport == vport)
 		goto fdb_add;
 
 	err = mlx5_mpfs_add_mac(esw->dev, mac);
 	if (err) {
 		esw_warn(esw->dev,
-			 "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n",
+			 "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n",
 			 mac, vport, err);
 		return err;
 	}
@@ -408,13 +488,13 @@ fdb_add:
 static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 	int err = 0;
 
-	/* Skip mlx5_mpfs_del_mac for PFs,
-	 * it is already done by the PF netdev in mlx5e_execute_l2_action
+	/* Skip mlx5_mpfs_del_mac for eswitch managerss,
+	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vport || !vaddr->mpfs)
+	if (!vaddr->mpfs || esw->manager_vport == vport)
 		goto fdb_del;
 
 	err = mlx5_mpfs_del_mac(esw->dev, mac);
@@ -437,17 +517,18 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 				   struct esw_mc_addr *esw_mc)
 {
 	u8 *mac = vaddr->node.addr;
-	u32 vport_idx = 0;
+	struct mlx5_vport *vport;
+	u16 i, vport_num;
 
-	for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) {
-		struct mlx5_vport *vport = &esw->vports[vport_idx];
+	mlx5_esw_for_all_vports(esw, i, vport) {
 		struct hlist_head *vport_hash = vport->mc_list;
 		struct vport_addr *iter_vaddr =
 					l2addr_hash_find(vport_hash,
 							 mac,
 							 struct vport_addr);
+		vport_num = vport->vport;
 		if (IS_ERR_OR_NULL(vport->allmulti_rule) ||
-		    vaddr->vport == vport_idx)
+		    vaddr->vport == vport_num)
 			continue;
 		switch (vaddr->action) {
 		case MLX5_ACTION_ADD:
@@ -459,14 +540,14 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 			if (!iter_vaddr) {
 				esw_warn(esw->dev,
 					 "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n",
-					 mac, vport_idx);
+					 mac, vport_num);
 				continue;
 			}
-			iter_vaddr->vport = vport_idx;
+			iter_vaddr->vport = vport_num;
 			iter_vaddr->flow_rule =
 					esw_fdb_set_vport_rule(esw,
 							       mac,
-							       vport_idx);
+							       vport_num);
 			iter_vaddr->mc_promisc = true;
 			break;
 		case MLX5_ACTION_DEL:
@@ -484,7 +565,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	struct hlist_head *hash = esw->mc_table;
 	struct esw_mc_addr *esw_mc;
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 
 	if (!esw->fdb_table.legacy.fdb)
 		return 0;
@@ -498,7 +579,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 		return -ENOMEM;
 
 	esw_mc->uplink_rule = /* Forward MC MAC to Uplink */
-		esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT);
+		esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK);
 
 	/* Add this multicast mac to all the mc promiscuous vports */
 	update_allmulti_vports(esw, vaddr, esw_mc);
@@ -524,7 +605,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	struct hlist_head *hash = esw->mc_table;
 	struct esw_mc_addr *esw_mc;
 	u8 *mac = vaddr->node.addr;
-	u32 vport = vaddr->vport;
+	u16 vport = vaddr->vport;
 
 	if (!esw->fdb_table.legacy.fdb)
 		return 0;
@@ -563,9 +644,9 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 
 /* Apply vport UC/MC list to HW l2 table and FDB table */
 static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
-				      u32 vport_num, int list_type)
+				      u16 vport_num, int list_type)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
 	vport_addr_action vport_addr_add;
 	vport_addr_action vport_addr_del;
@@ -598,9 +679,9 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw,
 
 /* Sync vport UC/MC list from vport context */
 static void esw_update_vport_addr_list(struct mlx5_eswitch *esw,
-				       u32 vport_num, int list_type)
+				       u16 vport_num, int list_type)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC;
 	u8 (*mac_list)[ETH_ALEN];
 	struct l2addr_node *node;
@@ -685,9 +766,9 @@ out:
 /* Sync vport UC/MC list from vport context
  * Must be called after esw_update_vport_addr_list
  */
-static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	struct l2addr_node *node;
 	struct vport_addr *addr;
 	struct hlist_head *hash;
@@ -720,11 +801,11 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num)
 }
 
 /* Apply vport rx mode to HW FDB table */
-static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
+static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num,
 				    bool promisc, bool mc_promisc)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	struct esw_mc_addr *allmulti_addr = &esw->mc_promisc;
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 
 	if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc)
 		goto promisc;
@@ -735,7 +816,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num,
 		if (!allmulti_addr->uplink_rule)
 			allmulti_addr->uplink_rule =
 				esw_fdb_set_vport_allmulti_rule(esw,
-								UPLINK_VPORT);
+								MLX5_VPORT_UPLINK);
 		allmulti_addr->refcnt++;
 	} else if (vport->allmulti_rule) {
 		mlx5_del_flow_rules(vport->allmulti_rule);
@@ -763,9 +844,9 @@ promisc:
 }
 
 /* Sync vport rx mode from vport context */
-static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num)
+static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	int promisc_all = 0;
 	int promisc_uc = 0;
 	int promisc_mc = 0;
@@ -1133,13 +1214,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 	int err = 0;
 	u8 *smac_v;
 
-	if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) {
-		mlx5_core_warn(esw->dev,
-			       "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n",
-			       vport->vport);
-		return -EPERM;
-	}
-
 	esw_vport_cleanup_ingress_rules(esw, vport);
 
 	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
@@ -1349,8 +1423,8 @@ static void esw_destroy_tsar(struct mlx5_eswitch *esw)
 static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 				u32 initial_max_rate, u32 initial_bw_share)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct mlx5_core_dev *dev = esw->dev;
 	void *vport_elem;
 	int err = 0;
@@ -1389,7 +1463,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num,
 
 static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	int err = 0;
 
 	if (!vport->qos.enabled)
@@ -1408,8 +1482,8 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num)
 static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num,
 				u32 max_rate, u32 bw_share)
 {
+	struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num);
 	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
-	struct mlx5_vport *vport = &esw->vports[vport_num];
 	struct mlx5_core_dev *dev = esw->dev;
 	void *vport_elem;
 	u32 bitmask = 0;
@@ -1465,15 +1539,22 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 {
 	int vport_num = vport->vport;
 
-	if (!vport_num)
+	if (esw->manager_vport == vport_num)
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
 				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-				      vport_num,
+				      vport_num, 1,
 				      vport->info.link_state);
-	mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
-	mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid);
+
+	/* Host PF has its own mac/guid. */
+	if (vport_num) {
+		mlx5_modify_nic_vport_mac_address(esw->dev, vport_num,
+						  vport->info.mac);
+		mlx5_modify_nic_vport_node_guid(esw->dev, vport_num,
+						vport->info.node_guid);
+	}
+
 	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
 			       (vport->info.vlan || vport->info.qos));
 
@@ -1519,10 +1600,10 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport)
 		mlx5_fc_destroy(dev, vport->egress.drop_counter);
 }
 
-static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
+static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 			     int enable_events)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	u16 vport_num = vport->vport;
 
 	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
@@ -1545,8 +1626,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	vport->enabled_events = enable_events;
 	vport->enabled = true;
 
-	/* only PF is trusted by default */
-	if (!vport_num)
+	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
+	 * in smartNIC as it's a vport group manager.
+	 */
+	if (esw->manager_vport == vport_num ||
+	    (!vport_num && mlx5_core_is_ecpf(esw->dev)))
 		vport->info.trusted = true;
 
 	esw_vport_change_handle_locked(vport);
@@ -1556,9 +1640,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num,
 	mutex_unlock(&esw->state_lock);
 }
 
-static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
+static void esw_disable_vport(struct mlx5_eswitch *esw,
+			      struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = &esw->vports[vport_num];
+	u16 vport_num = vport->vport;
 
 	if (!vport->enabled)
 		return;
@@ -1567,7 +1652,6 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */
@@ -1580,10 +1664,11 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	esw_vport_change_handle_locked(vport);
 	vport->enabled_events = 0;
 	esw_vport_disable_qos(esw, vport_num);
-	if (vport_num && esw->mode == SRIOV_LEGACY) {
+	if (esw->manager_vport != vport_num &&
+	    esw->mode == SRIOV_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
 					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					      vport_num,
+					      vport_num, 1,
 					      MLX5_VPORT_ADMIN_STATE_DOWN);
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
@@ -1593,12 +1678,29 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	mutex_unlock(&esw->state_lock);
 }
 
+static int eswitch_vport_event(struct notifier_block *nb,
+			       unsigned long type, void *data)
+{
+	struct mlx5_eswitch *esw = mlx5_nb_cof(nb, struct mlx5_eswitch, nb);
+	struct mlx5_eqe *eqe = data;
+	struct mlx5_vport *vport;
+	u16 vport_num;
+
+	vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (vport->enabled)
+		queue_work(esw->work_queue, &vport->vport_change_handler);
+
+	return NOTIFY_OK;
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
-
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 {
+	int vf_nvports = 0, total_nvports = 0;
+	struct mlx5_vport *vport;
 	int err;
 	int i, enabled_events;
 
@@ -1615,14 +1717,31 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
 
 	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
+
+	if (mode == SRIOV_OFFLOADS) {
+		if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+			err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports);
+			if (err)
+				return err;
+			total_nvports = esw->total_vports;
+		} else {
+			vf_nvports = nvfs;
+			total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev);
+		}
+	}
+
 	esw->mode = mode;
 
+	mlx5_lag_update(esw->dev);
+
 	if (mode == SRIOV_LEGACY) {
-		err = esw_create_legacy_fdb_table(esw);
+		err = esw_create_legacy_table(esw);
+		if (err)
+			goto abort;
 	} else {
+		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-
-		err = esw_offloads_init(esw, nvfs + 1);
+		err = esw_offloads_init(esw, vf_nvports, total_nvports);
 	}
 
 	if (err)
@@ -1637,8 +1756,25 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	 * 2. FDB/Eswitch is programmed by user space tools
 	 */
 	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0;
-	for (i = 0; i <= nvfs; i++)
-		esw_enable_vport(esw, i, enabled_events);
+
+	/* Enable PF vport */
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+	esw_enable_vport(esw, vport, enabled_events);
+
+	/* Enable ECPF vports */
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		esw_enable_vport(esw, vport, enabled_events);
+	}
+
+	/* Enable VF vports */
+	mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)
+		esw_enable_vport(esw, vport, enabled_events);
+
+	if (mode == SRIOV_LEGACY) {
+		MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+		mlx5_eq_notifier_register(esw->dev, &esw->nb);
+	}
 
 	esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
 		 esw->enabled_vports);
@@ -1647,8 +1783,10 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 abort:
 	esw->mode = SRIOV_NONE;
 
-	if (mode == SRIOV_OFFLOADS)
+	if (mode == SRIOV_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+	}
 
 	return err;
 }
@@ -1656,8 +1794,8 @@ abort:
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 {
 	struct esw_mc_addr *mc_promisc;
+	struct mlx5_vport *vport;
 	int old_mode;
-	int nvports;
 	int i;
 
 	if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE)
@@ -1667,10 +1805,12 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 		 esw->enabled_vports, esw->mode);
 
 	mc_promisc = &esw->mc_promisc;
-	nvports = esw->enabled_vports;
 
-	for (i = 0; i < esw->total_vports; i++)
-		esw_disable_vport(esw, i);
+	if (esw->mode == SRIOV_LEGACY)
+		mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
+	mlx5_esw_for_all_vports(esw, i, vport)
+		esw_disable_vport(esw, vport);
 
 	if (mc_promisc && mc_promisc->uplink_rule)
 		mlx5_del_flow_rules(mc_promisc->uplink_rule);
@@ -1678,25 +1818,29 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 	esw_destroy_tsar(esw);
 
 	if (esw->mode == SRIOV_LEGACY)
-		esw_destroy_legacy_fdb_table(esw);
+		esw_destroy_legacy_table(esw);
 	else if (esw->mode == SRIOV_OFFLOADS)
-		esw_offloads_cleanup(esw, nvports);
+		esw_offloads_cleanup(esw);
 
 	old_mode = esw->mode;
 	esw->mode = SRIOV_NONE;
 
-	if (old_mode == SRIOV_OFFLOADS)
+	mlx5_lag_update(esw->dev);
+
+	if (old_mode == SRIOV_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
+		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
+	}
 }
 
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 {
 	int total_vports = MLX5_TOTAL_VPORTS(dev);
 	struct mlx5_eswitch *esw;
-	int vport_num;
-	int err;
+	struct mlx5_vport *vport;
+	int err, i;
 
-	if (!MLX5_ESWITCH_MANAGER(dev))
+	if (!MLX5_VPORT_MANAGER(dev))
 		return 0;
 
 	esw_info(dev,
@@ -1710,6 +1854,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		return -ENOMEM;
 
 	esw->dev = dev;
+	esw->manager_vport = mlx5_eswitch_manager_vport(dev);
 
 	esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
 	if (!esw->work_queue) {
@@ -1724,6 +1869,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
+	esw->total_vports = total_vports;
+
 	err = esw_offloads_init_reps(esw);
 	if (err)
 		goto abort;
@@ -1732,17 +1879,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	hash_init(esw->offloads.mod_hdr_tbl);
 	mutex_init(&esw->state_lock);
 
-	for (vport_num = 0; vport_num < total_vports; vport_num++) {
-		struct mlx5_vport *vport = &esw->vports[vport_num];
-
-		vport->vport = vport_num;
+	mlx5_esw_for_all_vports(esw, i, vport) {
+		vport->vport = mlx5_eswitch_index_to_vport_num(esw, i);
 		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
 	}
 
-	esw->total_vports = total_vports;
 	esw->enabled_vports = 0;
 	esw->mode = SRIOV_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
@@ -1765,7 +1909,7 @@ abort:
 
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 {
-	if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev))
+	if (!esw || !MLX5_VPORT_MANAGER(esw->dev))
 		return;
 
 	esw_info(esw->dev, "cleanup\n");
@@ -1777,23 +1921,6 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	kfree(esw);
 }
 
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe)
-{
-	struct mlx5_eqe_vport_change *vc_eqe = &eqe->data.vport_change;
-	u16 vport_num = be16_to_cpu(vc_eqe->vport_num);
-	struct mlx5_vport *vport;
-
-	if (!esw) {
-		pr_warn("MLX5 E-Switch: vport %d got an event while eswitch is not initialized\n",
-			vport_num);
-		return;
-	}
-
-	vport = &esw->vports[vport_num];
-	if (vport->enabled)
-		queue_work(esw->work_queue, &vport->vport_change_handler);
-}
-
 /* Vport Administration */
 #define LEGAL_VPORT(esw, vport) (vport >= 0 && vport < esw->total_vports)
 
@@ -1804,7 +1931,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	u64 node_guid;
 	int err = 0;
 
-	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
+	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport) || is_multicast_ether_addr(mac))
 		return -EINVAL;
@@ -1812,13 +1939,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	mutex_lock(&esw->state_lock);
 	evport = &esw->vports[vport];
 
-	if (evport->info.spoofchk && !is_valid_ether_addr(mac)) {
+	if (evport->info.spoofchk && !is_valid_ether_addr(mac))
 		mlx5_core_warn(esw->dev,
-			       "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n",
+			       "Set invalid MAC while spoofchk is on, vport(%d)\n",
 			       vport);
-		err = -EPERM;
-		goto unlock;
-	}
 
 	err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac);
 	if (err) {
@@ -1861,7 +1985,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 
 	err = mlx5_modify_vport_admin_state(esw->dev,
 					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
-					    vport, link_state);
+					    vport, 1, link_state);
 	if (err) {
 		mlx5_core_warn(esw->dev,
 			       "Failed to set vport %d link state, err = %d",
@@ -1881,7 +2005,7 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 {
 	struct mlx5_vport *evport;
 
-	if (!MLX5_CAP_GEN(esw->dev, vport_group_manager))
+	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport))
 		return -EINVAL;
@@ -1964,6 +2088,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 	pschk = evport->info.spoofchk;
 	evport->info.spoofchk = spoofchk;
+	if (pschk && !is_valid_ether_addr(evport->info.mac))
+		mlx5_core_warn(esw->dev,
+			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
+			       evport->vport);
 	if (evport->enabled && esw->mode == SRIOV_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 	if (err)
@@ -1973,6 +2101,128 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 	return err;
 }
 
+static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw)
+{
+	if (esw->fdb_table.legacy.vepa_uplink_rule)
+		mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_uplink_rule);
+
+	if (esw->fdb_table.legacy.vepa_star_rule)
+		mlx5_del_flow_rules(esw->fdb_table.legacy.vepa_star_rule);
+
+	esw->fdb_table.legacy.vepa_uplink_rule = NULL;
+	esw->fdb_table.legacy.vepa_star_rule = NULL;
+}
+
+static int _mlx5_eswitch_set_vepa_locked(struct mlx5_eswitch *esw,
+					 u8 setting)
+{
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *flow_rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	void *misc;
+
+	if (!setting) {
+		esw_cleanup_vepa_rules(esw);
+		return 0;
+	}
+
+	if (esw->fdb_table.legacy.vepa_uplink_rule)
+		return 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	/* Uplink rule forward uplink traffic to FDB */
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK);
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest.ft = esw->fdb_table.legacy.fdb;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec,
+					&flow_act, &dest, 1);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		goto out;
+	} else {
+		esw->fdb_table.legacy.vepa_uplink_rule = flow_rule;
+	}
+
+	/* Star rule to forward all traffic to uplink vport */
+	memset(spec, 0, sizeof(*spec));
+	memset(&dest, 0, sizeof(dest));
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.vport.num = MLX5_VPORT_UPLINK;
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	flow_rule = mlx5_add_flow_rules(esw->fdb_table.legacy.vepa_fdb, spec,
+					&flow_act, &dest, 1);
+	if (IS_ERR(flow_rule)) {
+		err = PTR_ERR(flow_rule);
+		goto out;
+	} else {
+		esw->fdb_table.legacy.vepa_star_rule = flow_rule;
+	}
+
+out:
+	kvfree(spec);
+	if (err)
+		esw_cleanup_vepa_rules(esw);
+	return err;
+}
+
+int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting)
+{
+	int err = 0;
+
+	if (!esw)
+		return -EOPNOTSUPP;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->mode != SRIOV_LEGACY) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	err = _mlx5_eswitch_set_vepa_locked(esw, setting);
+
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
+{
+	int err = 0;
+
+	if (!esw)
+		return -EOPNOTSUPP;
+
+	if (!ESW_ALLOWED(esw))
+		return -EPERM;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->mode != SRIOV_LEGACY) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	*setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
+
+out:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
 int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
 				 int vport, bool setting)
 {
@@ -2000,8 +2250,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
 	u32 max_guarantee = 0;
 	int i;
 
-	for (i = 0; i < esw->total_vports; i++) {
-		evport = &esw->vports[i];
+	mlx5_esw_for_all_vports(esw, i, evport) {
 		if (!evport->enabled || evport->info.min_rate < max_guarantee)
 			continue;
 		max_guarantee = evport->info.min_rate;
@@ -2020,8 +2269,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 	int err;
 	int i;
 
-	for (i = 0; i < esw->total_vports; i++) {
-		evport = &esw->vports[i];
+	mlx5_esw_for_all_vports(esw, i, evport) {
 		if (!evport->enabled)
 			continue;
 		vport_min_rate = evport->info.min_rate;
@@ -2036,7 +2284,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 		if (bw_share == evport->qos.bw_share)
 			continue;
 
-		err = esw_vport_qos_config(esw, i, vport_max_rate,
+		err = esw_vport_qos_config(esw, evport->vport, vport_max_rate,
 					   bw_share);
 		if (!err)
 			evport->qos.bw_share = bw_share;
@@ -2050,19 +2298,24 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider)
 int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, int vport,
 				u32 max_rate, u32 min_rate)
 {
-	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
-	bool min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
-					fw_max_bw_share >= MLX5_MIN_BW_SHARE;
-	bool max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
 	struct mlx5_vport *evport;
+	u32 fw_max_bw_share;
 	u32 previous_min_rate;
 	u32 divider;
+	bool min_rate_supported;
+	bool max_rate_supported;
 	int err = 0;
 
 	if (!ESW_ALLOWED(esw))
 		return -EPERM;
 	if (!LEGAL_VPORT(esw, vport))
 		return -EINVAL;
+
+	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
+				fw_max_bw_share >= MLX5_MIN_BW_SHARE;
+	max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
+
 	if ((min_rate && !min_rate_supported) || (max_rate && !max_rate_supported))
 		return -EOPNOTSUPP;
 
@@ -2119,7 +2372,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 	    !MLX5_CAP_GEN(dev, transmit_discard_vport_down))
 		return 0;
 
-	err = mlx5_query_vport_down_stats(dev, vport_idx,
+	err = mlx5_query_vport_down_stats(dev, vport_idx, 1,
 					  &rx_discard_vport_down,
 					  &tx_discard_vport_down);
 	if (err)
@@ -2156,8 +2409,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 		 MLX5_CMD_OP_QUERY_VPORT_COUNTER);
 	MLX5_SET(query_vport_counter_in, in, op_mod, 0);
 	MLX5_SET(query_vport_counter_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_vport_counter_in, in, other_vport, 1);
+	MLX5_SET(query_vport_counter_in, in, other_vport, 1);
 
 	memset(out, 0, outlen);
 	err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen);
@@ -2219,3 +2471,21 @@ u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
+
+bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
+{
+	if ((dev0->priv.eswitch->mode == SRIOV_NONE &&
+	     dev1->priv.eswitch->mode == SRIOV_NONE) ||
+	    (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
+	     dev1->priv.eswitch->mode == SRIOV_OFFLOADS))
+		return true;
+
+	return false;
+}
+
+bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
+			       struct mlx5_core_dev *dev1)
+{
+	return (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
+		dev1->priv.eswitch->mode == SRIOV_OFFLOADS);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index aaafc9f17115..3f3cd32ae60a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -38,6 +38,7 @@
 #include <net/devlink.h>
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/eswitch.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
@@ -49,8 +50,6 @@
 #define MLX5_MAX_MC_PER_VPORT(dev) \
 	(1 << MLX5_CAP_GEN(dev, log_max_current_mc_list))
 
-#define FDB_UPLINK_VPORT 0xffff
-
 #define MLX5_MIN_BW_SHARE 1
 
 #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \
@@ -138,11 +137,16 @@ struct mlx5_eswitch_fdb {
 			struct mlx5_flow_group *addr_grp;
 			struct mlx5_flow_group *allmulti_grp;
 			struct mlx5_flow_group *promisc_grp;
+			struct mlx5_flow_table *vepa_fdb;
+			struct mlx5_flow_handle *vepa_uplink_rule;
+			struct mlx5_flow_handle *vepa_star_rule;
 		} legacy;
 
 		struct offloads_fdb {
 			struct mlx5_flow_table *slow_fdb;
 			struct mlx5_flow_group *send_to_vport_grp;
+			struct mlx5_flow_group *peer_miss_grp;
+			struct mlx5_flow_handle **peer_miss_rules;
 			struct mlx5_flow_group *miss_grp;
 			struct mlx5_flow_handle *miss_rule_uni;
 			struct mlx5_flow_handle *miss_rule_multi;
@@ -165,6 +169,8 @@ struct mlx5_esw_offload {
 	struct mlx5_flow_table *ft_offloads;
 	struct mlx5_flow_group *vport_rx_group;
 	struct mlx5_eswitch_rep *vport_reps;
+	struct list_head peer_flows;
+	struct mutex peer_mutex;
 	DECLARE_HASHTABLE(encap_tbl, 8);
 	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
 	u8 inline_mode;
@@ -179,8 +185,19 @@ struct esw_mc_addr { /* SRIOV only */
 	u32                    refcnt;
 };
 
+struct mlx5_host_work {
+	struct work_struct	work;
+	struct mlx5_eswitch	*esw;
+};
+
+struct mlx5_host_info {
+	struct mlx5_nb		nb;
+	u16			num_vfs;
+};
+
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
+	struct mlx5_nb          nb;
 	struct mlx5_eswitch_fdb fdb_table;
 	struct hlist_head       mc_table[MLX5_L2_ADDR_HASH_SIZE];
 	struct workqueue_struct *work_queue;
@@ -201,17 +218,19 @@ struct mlx5_eswitch {
 	struct mlx5_esw_offload offloads;
 	int                     mode;
 	int                     nvports;
+	u16                     manager_vport;
+	struct mlx5_host_info	host_info;
 };
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports);
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports);
+void esw_offloads_cleanup(struct mlx5_eswitch *esw);
+int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
+		      int total_nvports);
 void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
 
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
-void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe);
 int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode);
 void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
@@ -226,6 +245,8 @@ int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw,
 				 int vport_num, bool setting);
 int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, int vport,
 				u32 max_rate, u32 min_rate);
+int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting);
+int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting);
 int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw,
 				  int vport, struct ifla_vf_info *ivi);
 int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
@@ -281,13 +302,17 @@ enum mlx5_flow_match_level {
 /* current maximum for flow based vport multicasting */
 #define MLX5_MAX_FLOW_FWD_VPORTS 2
 
+enum {
+	MLX5_ESW_DEST_ENCAP         = BIT(0),
+	MLX5_ESW_DEST_ENCAP_VALID   = BIT(1),
+};
+
 struct mlx5_esw_flow_attr {
 	struct mlx5_eswitch_rep *in_rep;
-	struct mlx5_eswitch_rep *out_rep[MLX5_MAX_FLOW_FWD_VPORTS];
-	struct mlx5_core_dev	*out_mdev[MLX5_MAX_FLOW_FWD_VPORTS];
 	struct mlx5_core_dev	*in_mdev;
+	struct mlx5_core_dev    *counter_dev;
 
-	int mirror_count;
+	int split_count;
 	int out_count;
 
 	int	action;
@@ -296,9 +321,15 @@ struct mlx5_esw_flow_attr {
 	u8	vlan_prio[MLX5_FS_VLAN_DEPTH];
 	u8	total_vlan;
 	bool	vlan_handled;
-	u32	encap_id;
+	struct {
+		u32 flags;
+		struct mlx5_eswitch_rep *rep;
+		struct mlx5_core_dev *mdev;
+		u32 encap_id;
+	} dests[MLX5_MAX_FLOW_FWD_VPORTS];
 	u32	mod_hdr_id;
 	u8	match_level;
+	u8	tunnel_match_level;
 	struct mlx5_fc *counter;
 	u32	chain;
 	u16	prio;
@@ -338,6 +369,11 @@ static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev
 		MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan_2);
 }
 
+bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0,
+			 struct mlx5_core_dev *dev1);
+bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
+			       struct mlx5_core_dev *dev1);
+
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
 
 #define esw_info(dev, format, ...)				\
@@ -348,13 +384,60 @@ static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev
 
 #define esw_debug(dev, format, ...)				\
 	mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__)
+
+/* The returned number is valid only when the dev is eswitch manager. */
+static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
+}
+
+static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw)
+{
+	/* Uplink always locate at the last element of the array.*/
+	return esw->total_vports - 1;
+}
+
+static inline int mlx5_eswitch_ecpf_idx(struct mlx5_eswitch *esw)
+{
+	return esw->total_vports - 2;
+}
+
+static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw,
+						  u16 vport_num)
+{
+	if (vport_num == MLX5_VPORT_ECPF) {
+		if (!mlx5_ecpf_vport_exists(esw->dev))
+			esw_warn(esw->dev, "ECPF vport doesn't exist!\n");
+		return mlx5_eswitch_ecpf_idx(esw);
+	}
+
+	if (vport_num == MLX5_VPORT_UPLINK)
+		return mlx5_eswitch_uplink_idx(esw);
+
+	return vport_num;
+}
+
+static inline int mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw,
+						  int index)
+{
+	if (index == mlx5_eswitch_ecpf_idx(esw) &&
+	    mlx5_ecpf_vport_exists(esw->dev))
+		return MLX5_VPORT_ECPF;
+
+	if (index == mlx5_eswitch_uplink_idx(esw))
+		return MLX5_VPORT_UPLINK;
+
+	return index;
+}
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
-static inline void mlx5_eswitch_vport_event(struct mlx5_eswitch *esw, struct mlx5_eqe *eqe) {}
 static inline int  mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
 static inline void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) {}
+static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
 
 #define FDB_MAX_CHAIN 1
 #define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 9eac137790f5..9b2d78ee22b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -39,15 +39,60 @@
 #include "eswitch.h"
 #include "en.h"
 #include "fs_core.h"
+#include "lib/devcom.h"
+#include "ecpf.h"
+#include "lib/eq.h"
 
 enum {
 	FDB_FAST_PATH = 0,
 	FDB_SLOW_PATH
 };
 
+/* There are two match-all miss flows, one for unicast dst mac and
+ * one for multicast.
+ */
+#define MLX5_ESW_MISS_FLOWS (2)
+
 #define fdb_prio_table(esw, chain, prio, level) \
 	(esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)]
 
+#define UPLINK_REP_INDEX 0
+
+/* The rep getter/iterator are only valid after esw->total_vports
+ * and vport->vport are initialized in mlx5_eswitch_init.
+ */
+#define mlx5_esw_for_all_reps(esw, i, rep)			\
+	for ((i) = MLX5_VPORT_PF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) < (esw)->total_vports; (i)++)
+
+#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs)		\
+	for ((i) = MLX5_VPORT_FIRST_VF;				\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs)	\
+	for ((i) = (nvfs);					\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
+
+#define mlx5_esw_for_each_vf_vport(esw, vport, nvfs)		\
+	for ((vport) = MLX5_VPORT_FIRST_VF;			\
+	     (vport) <= (nvfs); (vport)++)
+
+#define mlx5_esw_for_each_vf_vport_reverse(esw, vport, nvfs)	\
+	for ((vport) = (nvfs);					\
+	     (vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
+
+static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
+						     u16 vport_num)
+{
+	u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
+
+	WARN_ON(idx > esw->total_vports - 1);
+	return &esw->offloads.vport_reps[idx];
+}
+
 static struct mlx5_flow_table *
 esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level);
 static void
@@ -81,7 +126,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 {
 	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
-	bool mirror = !!(attr->mirror_count);
+	bool split = !!(attr->split_count);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
 	int j, i = 0;
@@ -120,13 +165,21 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 			dest[i].ft = ft;
 			i++;
 		} else {
-			for (j = attr->mirror_count; j < attr->out_count; j++) {
+			for (j = attr->split_count; j < attr->out_count; j++) {
 				dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-				dest[i].vport.num = attr->out_rep[j]->vport;
+				dest[i].vport.num = attr->dests[j].rep->vport;
 				dest[i].vport.vhca_id =
-					MLX5_CAP_GEN(attr->out_mdev[j], vhca_id);
-				dest[i].vport.vhca_id_valid =
-					!!MLX5_CAP_ESW(esw->dev, merged_eswitch);
+					MLX5_CAP_GEN(attr->dests[j].mdev, vhca_id);
+				if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+					dest[i].vport.flags |=
+						MLX5_FLOW_DEST_VPORT_VHCA_ID;
+				if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) {
+					flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+					flow_act.reformat_id = attr->dests[j].encap_id;
+					dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
+					dest[i].vport.reformat_id =
+						attr->dests[j].encap_id;
+				}
 				i++;
 			}
 		}
@@ -151,22 +204,20 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
 				 source_eswitch_owner_vhca_id);
 
-	if (attr->match_level == MLX5_MATCH_NONE)
-		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
-	else
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
-					      MLX5_MATCH_MISC_PARAMETERS;
-
-	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP)
-		spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
+		if (attr->tunnel_match_level != MLX5_MATCH_NONE)
+			spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+		if (attr->match_level != MLX5_MATCH_NONE)
+			spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS;
+	} else if (attr->match_level != MLX5_MATCH_NONE) {
+		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
+	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		flow_act.modify_id = attr->mod_hdr_id;
 
-	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT)
-		flow_act.reformat_id = attr->encap_id;
-
-	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!mirror);
+	fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split);
 	if (IS_ERR(fdb)) {
 		rule = ERR_CAST(fdb);
 		goto err_esw_get;
@@ -181,7 +232,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	return rule;
 
 err_add_rule:
-	esw_put_prio_table(esw, attr->chain, attr->prio, !!mirror);
+	esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
 err_esw_get:
 	if (attr->dest_chain)
 		esw_put_prio_table(esw, attr->dest_chain, 1, 0);
@@ -215,12 +266,17 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	for (i = 0; i < attr->mirror_count; i++) {
+	for (i = 0; i < attr->split_count; i++) {
 		dest[i].type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-		dest[i].vport.num = attr->out_rep[i]->vport;
+		dest[i].vport.num = attr->dests[i].rep->vport;
 		dest[i].vport.vhca_id =
-			MLX5_CAP_GEN(attr->out_mdev[i], vhca_id);
-		dest[i].vport.vhca_id_valid = !!MLX5_CAP_ESW(esw->dev, merged_eswitch);
+			MLX5_CAP_GEN(attr->dests[i].mdev, vhca_id);
+		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+		if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) {
+			dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID;
+			dest[i].vport.reformat_id = attr->dests[i].encap_id;
+		}
 	}
 	dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	dest[i].ft = fwd_fdb,
@@ -268,7 +324,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 			struct mlx5_esw_flow_attr *attr,
 			bool fwd_rule)
 {
-	bool mirror = (attr->mirror_count > 0);
+	bool split = (attr->split_count > 0);
 
 	mlx5_del_flow_rules(rule);
 	esw->offloads.num_flows--;
@@ -277,7 +333,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 		esw_put_prio_table(esw, attr->chain, attr->prio, 1);
 		esw_put_prio_table(esw, attr->chain, attr->prio, 0);
 	} else {
-		esw_put_prio_table(esw, attr->chain, attr->prio, !!mirror);
+		esw_put_prio_table(esw, attr->chain, attr->prio, !!split);
 		if (attr->dest_chain)
 			esw_put_prio_table(esw, attr->dest_chain, 1, 0);
 	}
@@ -307,7 +363,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
 	for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
 		rep = &esw->offloads.vport_reps[vf_vport];
-		if (!rep->rep_if[REP_ETH].valid)
+		if (rep->rep_if[REP_ETH].state != REP_LOADED)
 			continue;
 
 		err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val);
@@ -325,7 +381,7 @@ esw_vlan_action_get_vport(struct mlx5_esw_flow_attr *attr, bool push, bool pop)
 	struct mlx5_eswitch_rep *in_rep, *out_rep, *vport = NULL;
 
 	in_rep  = attr->in_rep;
-	out_rep = attr->out_rep[0];
+	out_rep = attr->dests[0].rep;
 
 	if (push)
 		vport = in_rep;
@@ -346,17 +402,17 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 		goto out_notsupp;
 
 	in_rep  = attr->in_rep;
-	out_rep = attr->out_rep[0];
+	out_rep = attr->dests[0].rep;
 
-	if (push && in_rep->vport == FDB_UPLINK_VPORT)
+	if (push && in_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
-	if (pop && out_rep->vport == FDB_UPLINK_VPORT)
+	if (pop && out_rep->vport == MLX5_VPORT_UPLINK)
 		goto out_notsupp;
 
 	/* vport has vlan push configured, can't offload VF --> wire rules w.o it */
 	if (!push && !pop && fwd)
-		if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT)
+		if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK)
 			goto out_notsupp;
 
 	/* protects against (1) setting rules with different vlans to push and
@@ -398,7 +454,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->out_rep[0]->vport == FDB_UPLINK_VPORT) {
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) {
 			vport->vlan_refcount++;
 			attr->vlan_handled = true;
 		}
@@ -458,7 +514,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 
 	if (!push && !pop && fwd) {
 		/* tracks VF --> wire rules without vlan push action */
-		if (attr->out_rep[0]->vport == FDB_UPLINK_VPORT)
+		if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK)
 			vport->vlan_refcount--;
 
 		return 0;
@@ -505,7 +561,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
 	MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn);
-	MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */
+	/* source vport is the esw manager */
+	MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport);
 
 	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn);
@@ -531,6 +588,134 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
 	mlx5_del_flow_rules(rule);
 }
 
+static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
+				  struct mlx5_flow_spec *spec,
+				  struct mlx5_flow_destination *dest)
+{
+	void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				  misc_parameters);
+
+	MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+		 MLX5_CAP_GEN(peer_dev, vhca_id));
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+			    misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+			 source_eswitch_owner_vhca_id);
+
+	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest->vport.num = peer_dev->priv.eswitch->manager_vport;
+	dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id);
+	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+}
+
+static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
+				       struct mlx5_core_dev *peer_dev)
+{
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {0};
+	struct mlx5_flow_handle **flows;
+	struct mlx5_flow_handle *flow;
+	struct mlx5_flow_spec *spec;
+	/* total vports is the same for both e-switches */
+	int nvports = esw->total_vports;
+	void *misc;
+	int err, i;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	peer_miss_rules_setup(peer_dev, spec, &dest);
+
+	flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
+	if (!flows) {
+		err = -ENOMEM;
+		goto alloc_flows_err;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_pf_flow_err;
+		}
+		flows[MLX5_VPORT_PF] = flow;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_ecpf_flow_err;
+		}
+		flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
+	}
+
+	mlx5_esw_for_each_vf_vport(esw, i, mlx5_core_max_vfs(esw->dev)) {
+		MLX5_SET(fte_match_set_misc, misc, source_port, i);
+		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
+					   spec, &flow_act, &dest, 1);
+		if (IS_ERR(flow)) {
+			err = PTR_ERR(flow);
+			goto add_vf_flow_err;
+		}
+		flows[i] = flow;
+	}
+
+	esw->fdb_table.offloads.peer_miss_rules = flows;
+
+	kvfree(spec);
+	return 0;
+
+add_vf_flow_err:
+	nvports = --i;
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, nvports)
+		mlx5_del_flow_rules(flows[i]);
+
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+add_ecpf_flow_err:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+add_pf_flow_err:
+	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
+	kvfree(flows);
+alloc_flows_err:
+	kvfree(spec);
+	return err;
+}
+
+static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
+{
+	struct mlx5_flow_handle **flows;
+	int i;
+
+	flows = esw->fdb_table.offloads.peer_miss_rules;
+
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, mlx5_core_max_vfs(esw->dev))
+		mlx5_del_flow_rules(flows[i]);
+
+	if (mlx5_ecpf_vport_exists(esw->dev))
+		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+
+	kvfree(flows);
+}
+
 static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 {
 	struct mlx5_flow_act flow_act = {0};
@@ -557,7 +742,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw)
 	dmac_c[0] = 0x01;
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
-	dest.vport.num = 0;
+	dest.vport.num = esw->manager_vport;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
 	flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec,
@@ -801,7 +986,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		esw->fdb_table.offloads.fdb_left[i] =
 			ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0;
 
-	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2;
+	table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ +
+		MLX5_ESW_MISS_FLOWS + esw->total_vports;
 
 	/* create the slow path fdb with encap set, so further table instances
 	 * can be created at run time while VFs are probed if the FW allows that.
@@ -856,6 +1042,34 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	}
 	esw->fdb_table.offloads.send_to_vport_grp = g;
 
+	/* create peer esw miss group */
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_port);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_eswitch_owner_vhca_id);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 source_eswitch_owner_vhca_id_valid, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ix + esw->total_vports - 1);
+	ix += esw->total_vports;
+
+	g = mlx5_create_flow_group(fdb, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		esw_warn(dev, "Failed to create peer miss flow group err(%d)\n", err);
+		goto peer_miss_err;
+	}
+	esw->fdb_table.offloads.peer_miss_grp = g;
+
 	/* create miss group */
 	memset(flow_group_in, 0, inlen);
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
@@ -867,7 +1081,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	dmac[0] = 0x01;
 
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
-	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ix + MLX5_ESW_MISS_FLOWS);
 
 	g = mlx5_create_flow_group(fdb, flow_group_in);
 	if (IS_ERR(g)) {
@@ -888,6 +1103,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 miss_rule_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 miss_err:
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
+peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
 	esw_destroy_offloads_fast_fdb_tables(esw);
@@ -907,13 +1124,14 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_multi);
 	mlx5_del_flow_rules(esw->fdb_table.offloads.miss_rule_uni);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
+	mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 	esw_destroy_offloads_fast_fdb_tables(esw);
 }
 
-static int esw_create_offloads_table(struct mlx5_eswitch *esw)
+static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
@@ -927,7 +1145,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw)
 		return -EOPNOTSUPP;
 	}
 
-	ft_attr.max_fte = dev->priv.sriov.num_vfs + 2;
+	ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS;
 
 	ft_offloads = mlx5_create_flow_table(ns, &ft_attr);
 	if (IS_ERR(ft_offloads)) {
@@ -947,16 +1165,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw)
 	mlx5_destroy_flow_table(offloads->ft_offloads);
 }
 
-static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
+static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *g;
-	struct mlx5_priv *priv = &esw->dev->priv;
 	u32 *flow_group_in;
 	void *match_criteria, *misc;
 	int err = 0;
-	int nvports = priv->sriov.num_vfs + 2;
 
+	nvports = nvports + MLX5_ESW_MISS_FLOWS;
 	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	if (!flow_group_in)
 		return -ENOMEM;
@@ -1033,7 +1250,8 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 {
 	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
 
-	if (esw->mode != SRIOV_LEGACY) {
+	if (esw->mode != SRIOV_LEGACY &&
+	    !mlx5_core_is_ecpf_esw_manager(esw->dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't set offloads mode, SRIOV legacy not enabled");
 		return -EINVAL;
@@ -1071,9 +1289,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 {
 	int total_vfs = MLX5_TOTAL_VPORTS(esw->dev);
 	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_esw_offload *offloads;
 	struct mlx5_eswitch_rep *rep;
-	u8 hw_id[ETH_ALEN];
+	u8 hw_id[ETH_ALEN], rep_type;
 	int vport;
 
 	esw->offloads.vport_reps = kcalloc(total_vfs,
@@ -1082,75 +1299,203 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 	if (!esw->offloads.vport_reps)
 		return -ENOMEM;
 
-	offloads = &esw->offloads;
 	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
 
-	for (vport = 0; vport < total_vfs; vport++) {
-		rep = &offloads->vport_reps[vport];
-
-		rep->vport = vport;
+	mlx5_esw_for_all_reps(esw, vport, rep) {
+		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport);
 		ether_addr_copy(rep->hw_id, hw_id);
-	}
 
-	offloads->vport_reps[0].vport = FDB_UPLINK_VPORT;
+		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
+			rep->rep_if[rep_type].state = REP_UNREGISTERED;
+	}
 
 	return 0;
 }
 
-static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports,
-					  u8 rep_type)
+static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	if (rep->rep_if[rep_type].state != REP_LOADED)
+		return;
+
+	rep->rep_if[rep_type].unload(rep);
+	rep->rep_if[rep_type].state = REP_REGISTERED;
+}
+
+static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 
-	for (vport = nvports - 1; vport >= 0; vport--) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
 
-		rep->rep_if[rep_type].unload(rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
 	}
+
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+}
+
+static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				   u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int i;
+
+	mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports)
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+}
+
+static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = NUM_REP_TYPES;
+
+	while (rep_type-- > 0)
+		__unload_reps_vf_vport(esw, nvports, rep_type);
+}
+
+static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
+				    u8 rep_type)
+{
+	__unload_reps_vf_vport(esw, nvports, rep_type);
+
+	/* Special vports must be the last to unload. */
+	__unload_reps_special_vport(esw, rep_type);
 }
 
-static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports)
+static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = NUM_REP_TYPES;
 
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, nvports, rep_type);
 }
 
-static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports,
-				       u8 rep_type)
+static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
+				   struct mlx5_eswitch_rep *rep, u8 rep_type)
+{
+	int err = 0;
+
+	if (rep->rep_if[rep_type].state != REP_REGISTERED)
+		return 0;
+
+	err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (err)
+		return err;
+
+	rep->rep_if[rep_type].state = REP_LOADED;
+
+	return 0;
+}
+
+static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vport;
 	int err;
 
-	for (vport = 0; vport < nvports; vport++) {
-		rep = &esw->offloads.vport_reps[vport];
-		if (!rep->rep_if[rep_type].valid)
-			continue;
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	err = __esw_offloads_load_rep(esw, rep, rep_type);
+	if (err)
+		return err;
 
-		err = rep->rep_if[rep_type].load(esw->dev, rep);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
 		if (err)
-			goto err_reps;
+			goto err_pf;
+	}
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF);
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_ecpf;
+	}
+
+	return 0;
+
+err_ecpf:
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF);
+		__esw_offloads_unload_rep(esw, rep, rep_type);
+	}
+
+err_pf:
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	__esw_offloads_unload_rep(esw, rep, rep_type);
+	return err;
+}
+
+static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports,
+				u8 rep_type)
+{
+	struct mlx5_eswitch_rep *rep;
+	int err, i;
+
+	mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) {
+		err = __esw_offloads_load_rep(esw, rep, rep_type);
+		if (err)
+			goto err_vf;
 	}
 
 	return 0;
 
+err_vf:
+	__unload_reps_vf_vport(esw, --i, rep_type);
+	return err;
+}
+
+static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
+{
+	u8 rep_type = 0;
+	int err;
+
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
+		err = __load_reps_vf_vport(esw, nvports, rep_type);
+		if (err)
+			goto err_reps;
+	}
+
+	return err;
+
 err_reps:
-	esw_offloads_unload_reps_type(esw, vport, rep_type);
+	while (rep_type-- > 0)
+		__unload_reps_vf_vport(esw, nvports, rep_type);
+	return err;
+}
+
+static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
+				 u8 rep_type)
+{
+	int err;
+
+	/* Special vports must be loaded first. */
+	err = __load_reps_special_vport(esw, rep_type);
+	if (err)
+		return err;
+
+	err = __load_reps_vf_vport(esw, nvports, rep_type);
+	if (err)
+		goto err_vfs;
+
+	return 0;
+
+err_vfs:
+	__unload_reps_special_vport(esw, rep_type);
 	return err;
 }
 
-static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
+static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = 0;
 	int err;
 
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
-		err = esw_offloads_load_reps_type(esw, nvports, rep_type);
+		err = __load_reps_all_vport(esw, nvports, rep_type);
 		if (err)
 			goto err_reps;
 	}
@@ -1159,37 +1504,130 @@ static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports)
 
 err_reps:
 	while (rep_type-- > 0)
-		esw_offloads_unload_reps_type(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, nvports, rep_type);
 	return err;
 }
 
-int esw_offloads_init(struct mlx5_eswitch *esw, int nvports)
+#define ESW_OFFLOADS_DEVCOM_PAIR	(0)
+#define ESW_OFFLOADS_DEVCOM_UNPAIR	(1)
+
+static int mlx5_esw_offloads_pair(struct mlx5_eswitch *esw,
+				  struct mlx5_eswitch *peer_esw)
 {
 	int err;
 
+	err = esw_add_fdb_peer_miss_rules(esw, peer_esw->dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
+
+static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
+{
+	mlx5e_tc_clean_fdb_peer_flows(esw);
+	esw_del_fdb_peer_miss_rules(esw);
+}
+
+static int mlx5_esw_offloads_devcom_event(int event,
+					  void *my_data,
+					  void *event_data)
+{
+	struct mlx5_eswitch *esw = my_data;
+	struct mlx5_eswitch *peer_esw = event_data;
+	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+	int err;
+
+	switch (event) {
+	case ESW_OFFLOADS_DEVCOM_PAIR:
+		err = mlx5_esw_offloads_pair(esw, peer_esw);
+		if (err)
+			goto err_out;
+
+		err = mlx5_esw_offloads_pair(peer_esw, esw);
+		if (err)
+			goto err_pair;
+
+		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, true);
+		break;
+
+	case ESW_OFFLOADS_DEVCOM_UNPAIR:
+		if (!mlx5_devcom_is_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS))
+			break;
+
+		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
+		mlx5_esw_offloads_unpair(peer_esw);
+		mlx5_esw_offloads_unpair(esw);
+		break;
+	}
+
+	return 0;
+
+err_pair:
+	mlx5_esw_offloads_unpair(esw);
+
+err_out:
+	mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
+		      event, err);
+	return err;
+}
+
+static void esw_offloads_devcom_init(struct mlx5_eswitch *esw)
+{
+	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+
+	INIT_LIST_HEAD(&esw->offloads.peer_flows);
+	mutex_init(&esw->offloads.peer_mutex);
+
+	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		return;
+
+	mlx5_devcom_register_component(devcom,
+				       MLX5_DEVCOM_ESW_OFFLOADS,
+				       mlx5_esw_offloads_devcom_event,
+				       esw);
+
+	mlx5_devcom_send_event(devcom,
+			       MLX5_DEVCOM_ESW_OFFLOADS,
+			       ESW_OFFLOADS_DEVCOM_PAIR, esw);
+}
+
+static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
+{
+	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+
+	if (!MLX5_CAP_ESW(esw->dev, merged_eswitch))
+		return;
+
+	mlx5_devcom_send_event(devcom, MLX5_DEVCOM_ESW_OFFLOADS,
+			       ESW_OFFLOADS_DEVCOM_UNPAIR, esw);
+
+	mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+}
+
+static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports)
+{
+	int err;
+
+	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
 
 	err = esw_create_offloads_fdb_tables(esw, nvports);
 	if (err)
 		return err;
 
-	err = esw_create_offloads_table(esw);
+	err = esw_create_offloads_table(esw, nvports);
 	if (err)
 		goto create_ft_err;
 
-	err = esw_create_vport_rx_group(esw);
+	err = esw_create_vport_rx_group(esw, nvports);
 	if (err)
 		goto create_fg_err;
 
-	err = esw_offloads_load_reps(esw, nvports);
-	if (err)
-		goto err_reps;
-
 	return 0;
 
-err_reps:
-	esw_destroy_vport_rx_group(esw);
-
 create_fg_err:
 	esw_destroy_offloads_table(esw);
 
@@ -1199,6 +1637,95 @@ create_ft_err:
 	return err;
 }
 
+static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
+{
+	esw_destroy_vport_rx_group(esw);
+	esw_destroy_offloads_table(esw);
+	esw_destroy_offloads_fdb_tables(esw);
+}
+
+static void esw_host_params_event_handler(struct work_struct *work)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_eswitch *esw;
+	int err, num_vf = 0;
+
+	host_work = container_of(work, struct mlx5_host_work, work);
+	esw = host_work->esw;
+
+	err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf);
+	if (err || num_vf == esw->host_info.num_vfs)
+		goto out;
+
+	/* Number of VFs can only change from "0 to x" or "x to 0". */
+	if (esw->host_info.num_vfs > 0) {
+		esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs);
+	} else {
+		err = esw_offloads_load_vf_reps(esw, num_vf);
+
+		if (err)
+			goto out;
+	}
+
+	esw->host_info.num_vfs = num_vf;
+
+out:
+	kfree(host_work);
+}
+
+static int esw_host_params_event(struct notifier_block *nb,
+				 unsigned long type, void *data)
+{
+	struct mlx5_host_work *host_work;
+	struct mlx5_host_info *host_info;
+	struct mlx5_eswitch *esw;
+
+	host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC);
+	if (!host_work)
+		return NOTIFY_DONE;
+
+	host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb);
+	esw = container_of(host_info, struct mlx5_eswitch, host_info);
+
+	host_work->esw = esw;
+
+	INIT_WORK(&host_work->work, esw_host_params_event_handler);
+	queue_work(esw->work_queue, &host_work->work);
+
+	return NOTIFY_OK;
+}
+
+int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
+		      int total_nvports)
+{
+	int err;
+
+	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
+
+	err = esw_offloads_steering_init(esw, total_nvports);
+	if (err)
+		return err;
+
+	err = esw_offloads_load_all_reps(esw, vf_nvports);
+	if (err)
+		goto err_reps;
+
+	esw_offloads_devcom_init(esw);
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event,
+			     HOST_PARAMS_CHANGE);
+		mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb);
+		esw->host_info.num_vfs = vf_nvports;
+	}
+
+	return 0;
+
+err_reps:
+	esw_offloads_steering_cleanup(esw);
+	return err;
+}
+
 static int esw_offloads_stop(struct mlx5_eswitch *esw,
 			     struct netlink_ext_ack *extack)
 {
@@ -1215,18 +1742,24 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 		}
 	}
 
-	/* enable back PF RoCE */
-	mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-
 	return err;
 }
 
-void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports)
+void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 {
-	esw_offloads_unload_reps(esw, nvports);
-	esw_destroy_vport_rx_group(esw);
-	esw_destroy_offloads_table(esw);
-	esw_destroy_offloads_fdb_tables(esw);
+	u16 num_vfs;
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb);
+		flush_workqueue(esw->work_queue);
+		num_vfs = esw->host_info.num_vfs;
+	} else {
+		num_vfs = esw->dev->priv.sriov.num_vfs;
+	}
+
+	esw_offloads_devcom_cleanup(esw);
+	esw_offloads_unload_all_reps(esw, num_vfs);
+	esw_offloads_steering_cleanup(esw);
 }
 
 static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
@@ -1315,7 +1848,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if(!MLX5_ESWITCH_MANAGER(dev))
 		return -EPERM;
 
-	if (dev->priv.eswitch->mode == SRIOV_NONE)
+	if (dev->priv.eswitch->mode == SRIOV_NONE &&
+	    !mlx5_core_is_ecpf_esw_manager(dev))
 		return -EOPNOTSUPP;
 
 	return 0;
@@ -1527,47 +2061,45 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap)
 	return 0;
 }
 
-void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw,
-				     int vport_index,
-				     struct mlx5_eswitch_rep_if *__rep_if,
-				     u8 rep_type)
+void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
+				      struct mlx5_eswitch_rep_if *__rep_if,
+				      u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep_if *rep_if;
+	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type];
-
-	rep_if->load   = __rep_if->load;
-	rep_if->unload = __rep_if->unload;
-	rep_if->get_proto_dev = __rep_if->get_proto_dev;
-	rep_if->priv = __rep_if->priv;
+	mlx5_esw_for_all_reps(esw, i, rep) {
+		rep_if = &rep->rep_if[rep_type];
+		rep_if->load   = __rep_if->load;
+		rep_if->unload = __rep_if->unload;
+		rep_if->get_proto_dev = __rep_if->get_proto_dev;
+		rep_if->priv = __rep_if->priv;
 
-	rep_if->valid = true;
+		rep_if->state = REP_REGISTERED;
+	}
 }
-EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 
-void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw,
-				       int vport_index, u8 rep_type)
+void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
+	u16 max_vf = mlx5_core_max_vfs(esw->dev);
 	struct mlx5_eswitch_rep *rep;
+	int i;
 
-	rep = &offloads->vport_reps[vport_index];
-
-	if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled)
-		rep->rep_if[rep_type].unload(rep);
+	if (esw->mode == SRIOV_OFFLOADS)
+		__unload_reps_all_vport(esw, max_vf, rep_type);
 
-	rep->rep_if[rep_type].valid = false;
+	mlx5_esw_for_all_reps(esw, i, rep)
+		rep->rep_if[rep_type].state = REP_UNREGISTERED;
 }
-EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep);
+EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
 
 void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type)
 {
-#define UPLINK_REP_INDEX 0
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	rep = &offloads->vport_reps[UPLINK_REP_INDEX];
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
 	return rep->rep_if[rep_type].priv;
 }
 
@@ -1575,15 +2107,11 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw,
 				 int vport,
 				 u8 rep_type)
 {
-	struct mlx5_esw_offload *offloads = &esw->offloads;
 	struct mlx5_eswitch_rep *rep;
 
-	if (vport == FDB_UPLINK_VPORT)
-		vport = UPLINK_REP_INDEX;
-
-	rep = &offloads->vport_reps[vport];
+	rep = mlx5_eswitch_get_rep(esw, vport);
 
-	if (rep->rep_if[rep_type].valid &&
+	if (rep->rep_if[rep_type].state == REP_LOADED &&
 	    rep->rep_if[rep_type].get_proto_dev)
 		return rep->rep_if[rep_type].get_proto_dev(rep);
 	return NULL;
@@ -1592,13 +2120,13 @@ EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev);
 
 void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type);
+	return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type);
 }
 EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev);
 
 struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
 						int vport)
 {
-	return &esw->offloads.vport_reps[vport];
+	return mlx5_eswitch_get_rep(esw, vport);
 }
 EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
new file mode 100644
index 000000000000..5d5864e8df3c
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -0,0 +1,328 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+// Copyright (c) 2018 Mellanox Technologies
+
+#include <linux/mlx5/driver.h>
+
+#include "mlx5_core.h"
+#include "lib/eq.h"
+#include "lib/mlx5.h"
+
+struct mlx5_event_nb {
+	struct mlx5_nb  nb;
+	void           *ctx;
+};
+
+/* General events handlers for the low level mlx5_core driver
+ *
+ * Other Major feature specific events such as
+ * clock/eswitch/fpga/FW trace and many others, are handled elsewhere, with
+ * separate notifiers callbacks, specifically by those mlx5 components.
+ */
+static int any_notifier(struct notifier_block *, unsigned long, void *);
+static int temp_warn(struct notifier_block *, unsigned long, void *);
+static int port_module(struct notifier_block *, unsigned long, void *);
+
+/* handler which forwards the event to events->nh, driver notifiers */
+static int forward_event(struct notifier_block *, unsigned long, void *);
+
+static struct mlx5_nb events_nbs_ref[] = {
+	/* Events to be proccessed by mlx5_core */
+	{.nb.notifier_call = any_notifier,  .event_type = MLX5_EVENT_TYPE_NOTIFY_ANY },
+	{.nb.notifier_call = temp_warn,     .event_type = MLX5_EVENT_TYPE_TEMP_WARN_EVENT },
+	{.nb.notifier_call = port_module,   .event_type = MLX5_EVENT_TYPE_PORT_MODULE_EVENT },
+
+	/* Events to be forwarded (as is) to mlx5 core interfaces (mlx5e/mlx5_ib) */
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PORT_CHANGE },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_GENERAL_EVENT },
+	/* QP/WQ resource events to forward */
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_DCT_DRAINED },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PATH_MIG },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_COMM_EST },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SQ_DRAINED },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SRQ_LAST_WQE },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_CATAS_ERROR },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_PATH_MIG_FAILED },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_WQ_ACCESS_ERROR },
+	/* SRQ events */
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SRQ_CATAS_ERROR },
+	{.nb.notifier_call = forward_event,   .event_type = MLX5_EVENT_TYPE_SRQ_RQ_LIMIT },
+};
+
+struct mlx5_events {
+	struct mlx5_core_dev *dev;
+	struct mlx5_event_nb  notifiers[ARRAY_SIZE(events_nbs_ref)];
+	/* driver notifier chain */
+	struct atomic_notifier_head nh;
+	/* port module events stats */
+	struct mlx5_pme_stats pme_stats;
+};
+
+static const char *eqe_type_str(u8 type)
+{
+	switch (type) {
+	case MLX5_EVENT_TYPE_COMP:
+		return "MLX5_EVENT_TYPE_COMP";
+	case MLX5_EVENT_TYPE_PATH_MIG:
+		return "MLX5_EVENT_TYPE_PATH_MIG";
+	case MLX5_EVENT_TYPE_COMM_EST:
+		return "MLX5_EVENT_TYPE_COMM_EST";
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+		return "MLX5_EVENT_TYPE_SQ_DRAINED";
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+		return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
+	case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
+		return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
+	case MLX5_EVENT_TYPE_CQ_ERROR:
+		return "MLX5_EVENT_TYPE_CQ_ERROR";
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+		return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+		return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+		return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+		return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
+	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
+		return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
+	case MLX5_EVENT_TYPE_INTERNAL_ERROR:
+		return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
+	case MLX5_EVENT_TYPE_PORT_CHANGE:
+		return "MLX5_EVENT_TYPE_PORT_CHANGE";
+	case MLX5_EVENT_TYPE_GPIO_EVENT:
+		return "MLX5_EVENT_TYPE_GPIO_EVENT";
+	case MLX5_EVENT_TYPE_PORT_MODULE_EVENT:
+		return "MLX5_EVENT_TYPE_PORT_MODULE_EVENT";
+	case MLX5_EVENT_TYPE_TEMP_WARN_EVENT:
+		return "MLX5_EVENT_TYPE_TEMP_WARN_EVENT";
+	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
+		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
+	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
+		return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
+	case MLX5_EVENT_TYPE_STALL_EVENT:
+		return "MLX5_EVENT_TYPE_STALL_EVENT";
+	case MLX5_EVENT_TYPE_CMD:
+		return "MLX5_EVENT_TYPE_CMD";
+	case MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE:
+		return "MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE";
+	case MLX5_EVENT_TYPE_PAGE_REQUEST:
+		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
+	case MLX5_EVENT_TYPE_PAGE_FAULT:
+		return "MLX5_EVENT_TYPE_PAGE_FAULT";
+	case MLX5_EVENT_TYPE_PPS_EVENT:
+		return "MLX5_EVENT_TYPE_PPS_EVENT";
+	case MLX5_EVENT_TYPE_NIC_VPORT_CHANGE:
+		return "MLX5_EVENT_TYPE_NIC_VPORT_CHANGE";
+	case MLX5_EVENT_TYPE_FPGA_ERROR:
+		return "MLX5_EVENT_TYPE_FPGA_ERROR";
+	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
+		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
+	case MLX5_EVENT_TYPE_GENERAL_EVENT:
+		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+	case MLX5_EVENT_TYPE_MONITOR_COUNTER:
+		return "MLX5_EVENT_TYPE_MONITOR_COUNTER";
+	case MLX5_EVENT_TYPE_DEVICE_TRACER:
+		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
+	default:
+		return "Unrecognized event";
+	}
+}
+
+/* handles all FW events, type == eqe->type */
+static int any_notifier(struct notifier_block *nb,
+			unsigned long type, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
+
+	mlx5_core_dbg(events->dev, "Async eqe type %s, subtype (%d)\n",
+		      eqe_type_str(eqe->type), eqe->sub_type);
+	return NOTIFY_OK;
+}
+
+/* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
+static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
+	u64 value_lsb;
+	u64 value_msb;
+
+	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
+
+	mlx5_core_warn(events->dev,
+		       "High temperature on sensors with bit set %llx %llx",
+		       value_msb, value_lsb);
+
+	return NOTIFY_OK;
+}
+
+/* MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
+static const char *mlx5_pme_status_to_string(enum port_module_event_status_type status)
+{
+	switch (status) {
+	case MLX5_MODULE_STATUS_PLUGGED:
+		return "Cable plugged";
+	case MLX5_MODULE_STATUS_UNPLUGGED:
+		return "Cable unplugged";
+	case MLX5_MODULE_STATUS_ERROR:
+		return "Cable error";
+	case MLX5_MODULE_STATUS_DISABLED:
+		return "Cable disabled";
+	default:
+		return "Unknown status";
+	}
+}
+
+static const char *mlx5_pme_error_to_string(enum port_module_event_error_type error)
+{
+	switch (error) {
+	case MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED:
+		return "Power budget exceeded";
+	case MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX:
+		return "Long Range for non MLNX cable";
+	case MLX5_MODULE_EVENT_ERROR_BUS_STUCK:
+		return "Bus stuck (I2C or data shorted)";
+	case MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT:
+		return "No EEPROM/retry timeout";
+	case MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST:
+		return "Enforce part number list";
+	case MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER:
+		return "Unknown identifier";
+	case MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE:
+		return "High Temperature";
+	case MLX5_MODULE_EVENT_ERROR_BAD_CABLE:
+		return "Bad or shorted cable/module";
+	case MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED:
+		return "One or more network ports have been powered down due to insufficient/unadvertised power on the PCIe slot";
+	default:
+		return "Unknown error";
+	}
+}
+
+/* type == MLX5_EVENT_TYPE_PORT_MODULE_EVENT */
+static int port_module(struct notifier_block *nb, unsigned long type, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
+
+	enum port_module_event_status_type module_status;
+	enum port_module_event_error_type error_type;
+	struct mlx5_eqe_port_module *module_event_eqe;
+	const char *status_str;
+	u8 module_num;
+
+	module_event_eqe = &eqe->data.port_module;
+	module_status = module_event_eqe->module_status &
+			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
+	error_type = module_event_eqe->error_type &
+		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
+
+	if (module_status < MLX5_MODULE_STATUS_NUM)
+		events->pme_stats.status_counters[module_status]++;
+
+	if (module_status == MLX5_MODULE_STATUS_ERROR)
+		if (error_type < MLX5_MODULE_EVENT_ERROR_NUM)
+			events->pme_stats.error_counters[error_type]++;
+
+	if (!printk_ratelimit())
+		return NOTIFY_OK;
+
+	module_num = module_event_eqe->module;
+	status_str = mlx5_pme_status_to_string(module_status);
+	if (module_status == MLX5_MODULE_STATUS_ERROR) {
+		const char *error_str = mlx5_pme_error_to_string(error_type);
+
+		mlx5_core_err(events->dev,
+			      "Port module event[error]: module %u, %s, %s\n",
+			      module_num, status_str, error_str);
+	} else {
+		mlx5_core_info(events->dev,
+			       "Port module event: module %u, %s\n",
+			       module_num, status_str);
+	}
+
+	return NOTIFY_OK;
+}
+
+void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats)
+{
+	*stats = dev->priv.events->pme_stats;
+}
+
+/* forward event as is to registered interfaces (mlx5e/mlx5_ib) */
+static int forward_event(struct notifier_block *nb, unsigned long event, void *data)
+{
+	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
+	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_eqe      *eqe      = data;
+
+	mlx5_core_dbg(events->dev, "Async eqe type %s, subtype (%d) forward to interfaces\n",
+		      eqe_type_str(eqe->type), eqe->sub_type);
+	atomic_notifier_call_chain(&events->nh, event, data);
+	return NOTIFY_OK;
+}
+
+int mlx5_events_init(struct mlx5_core_dev *dev)
+{
+	struct mlx5_events *events = kzalloc(sizeof(*events), GFP_KERNEL);
+
+	if (!events)
+		return -ENOMEM;
+
+	ATOMIC_INIT_NOTIFIER_HEAD(&events->nh);
+	events->dev = dev;
+	dev->priv.events = events;
+	return 0;
+}
+
+void mlx5_events_cleanup(struct mlx5_core_dev *dev)
+{
+	kvfree(dev->priv.events);
+}
+
+void mlx5_events_start(struct mlx5_core_dev *dev)
+{
+	struct mlx5_events *events = dev->priv.events;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(events_nbs_ref); i++) {
+		events->notifiers[i].nb  = events_nbs_ref[i];
+		events->notifiers[i].ctx = events;
+		mlx5_eq_notifier_register(dev, &events->notifiers[i].nb);
+	}
+}
+
+void mlx5_events_stop(struct mlx5_core_dev *dev)
+{
+	struct mlx5_events *events = dev->priv.events;
+	int i;
+
+	for (i = ARRAY_SIZE(events_nbs_ref) - 1; i >= 0 ; i--)
+		mlx5_eq_notifier_unregister(dev, &events->notifiers[i].nb);
+}
+
+int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+	struct mlx5_events *events = dev->priv.events;
+
+	return atomic_notifier_chain_register(&events->nh, nb);
+}
+EXPORT_SYMBOL(mlx5_notifier_register);
+
+int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb)
+{
+	struct mlx5_events *events = dev->priv.events;
+
+	return atomic_notifier_chain_unregister(&events->nh, nb);
+}
+EXPORT_SYMBOL(mlx5_notifier_unregister);
+
+int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data)
+{
+	return atomic_notifier_call_chain(&events->nh, event, data);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index 8ca1d1949d93..873541ef4c1b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -334,7 +334,7 @@ static void mlx5_fpga_conn_handle_cqe(struct mlx5_fpga_conn *conn,
 {
 	u8 opcode, status = 0;
 
-	opcode = cqe->op_own >> 4;
+	opcode = get_cqe_opcode(cqe);
 
 	switch (opcode) {
 	case MLX5_CQE_REQ_ERR:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index 436a8136f26f..d046d1ec2a86 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -36,6 +36,7 @@
 
 #include "mlx5_core.h"
 #include "lib/mlx5.h"
+#include "lib/eq.h"
 #include "fpga/core.h"
 #include "fpga/conn.h"
 
@@ -145,6 +146,22 @@ static int mlx5_fpga_device_brb(struct mlx5_fpga_device *fdev)
 	return 0;
 }
 
+static int mlx5_fpga_event(struct mlx5_fpga_device *, unsigned long, void *);
+
+static int fpga_err_event(struct notifier_block *nb, unsigned long event, void *eqe)
+{
+	struct mlx5_fpga_device *fdev = mlx5_nb_cof(nb, struct mlx5_fpga_device, fpga_err_nb);
+
+	return mlx5_fpga_event(fdev, event, eqe);
+}
+
+static int fpga_qp_err_event(struct notifier_block *nb, unsigned long event, void *eqe)
+{
+	struct mlx5_fpga_device *fdev = mlx5_nb_cof(nb, struct mlx5_fpga_device, fpga_qp_err_nb);
+
+	return mlx5_fpga_event(fdev, event, eqe);
+}
+
 int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_fpga_device *fdev = mdev->fpga;
@@ -185,6 +202,11 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 	if (err)
 		goto out;
 
+	MLX5_NB_INIT(&fdev->fpga_err_nb, fpga_err_event, FPGA_ERROR);
+	MLX5_NB_INIT(&fdev->fpga_qp_err_nb, fpga_qp_err_event, FPGA_QP_ERROR);
+	mlx5_eq_notifier_register(fdev->mdev, &fdev->fpga_err_nb);
+	mlx5_eq_notifier_register(fdev->mdev, &fdev->fpga_qp_err_nb);
+
 	err = mlx5_fpga_conn_device_init(fdev);
 	if (err)
 		goto err_rsvd_gid;
@@ -201,6 +223,8 @@ err_conn_init:
 	mlx5_fpga_conn_device_cleanup(fdev);
 
 err_rsvd_gid:
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_err_nb);
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_qp_err_nb);
 	mlx5_core_unreserve_gids(mdev, max_num_qps);
 out:
 	spin_lock_irqsave(&fdev->state_lock, flags);
@@ -256,6 +280,9 @@ void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev)
 	}
 
 	mlx5_fpga_conn_device_cleanup(fdev);
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_err_nb);
+	mlx5_eq_notifier_unregister(fdev->mdev, &fdev->fpga_qp_err_nb);
+
 	max_num_qps = MLX5_CAP_FPGA(mdev, shell_caps.max_num_qps);
 	mlx5_core_unreserve_gids(mdev, max_num_qps);
 }
@@ -283,13 +310,13 @@ static const char *mlx5_fpga_qp_syndrome_to_string(u8 syndrome)
 	return "Unknown";
 }
 
-void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
+static int mlx5_fpga_event(struct mlx5_fpga_device *fdev,
+			   unsigned long event, void *eqe)
 {
-	struct mlx5_fpga_device *fdev = mdev->fpga;
+	void *data = ((struct mlx5_eqe *)eqe)->data.raw;
 	const char *event_name;
 	bool teardown = false;
 	unsigned long flags;
-	u32 fpga_qpn;
 	u8 syndrome;
 
 	switch (event) {
@@ -300,12 +327,9 @@ void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
 	case MLX5_EVENT_TYPE_FPGA_QP_ERROR:
 		syndrome = MLX5_GET(fpga_qp_error_event, data, syndrome);
 		event_name = mlx5_fpga_qp_syndrome_to_string(syndrome);
-		fpga_qpn = MLX5_GET(fpga_qp_error_event, data, fpga_qpn);
 		break;
 	default:
-		mlx5_fpga_warn_ratelimited(fdev, "Unexpected event %u\n",
-					   event);
-		return;
+		return NOTIFY_DONE;
 	}
 
 	spin_lock_irqsave(&fdev->state_lock, flags);
@@ -326,4 +350,6 @@ void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data)
 	 */
 	if (teardown)
 		mlx5_trigger_health_work(fdev->mdev);
+
+	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
index 3e2355c8df3f..7e2e871dbf83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h
@@ -35,11 +35,16 @@
 
 #ifdef CONFIG_MLX5_FPGA
 
+#include <linux/mlx5/eq.h>
+
+#include "lib/eq.h"
 #include "fpga/cmd.h"
 
 /* Represents an Innova device */
 struct mlx5_fpga_device {
 	struct mlx5_core_dev *mdev;
+	struct mlx5_nb fpga_err_nb;
+	struct mlx5_nb fpga_qp_err_nb;
 	spinlock_t state_lock; /* Protects state transitions */
 	enum mlx5_fpga_status state;
 	enum mlx5_fpga_image last_admin_image;
@@ -82,7 +87,6 @@ int mlx5_fpga_init(struct mlx5_core_dev *mdev);
 void mlx5_fpga_cleanup(struct mlx5_core_dev *mdev);
 int mlx5_fpga_device_start(struct mlx5_core_dev *mdev);
 void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev);
-void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event, void *data);
 
 #else
 
@@ -104,11 +108,6 @@ static inline void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev)
 {
 }
 
-static inline void mlx5_fpga_event(struct mlx5_core_dev *mdev, u8 event,
-				   void *data)
-{
-}
-
 #endif
 
 #endif /* __MLX5_FPGA_CORE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index 5cf5f2a9d51f..22a2ef111514 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -148,14 +148,16 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	return ret;
 }
 
-static void mlx5_fpga_tls_release_swid(struct idr *idr,
-				       spinlock_t *idr_spinlock, u32 swid)
+static void *mlx5_fpga_tls_release_swid(struct idr *idr,
+					spinlock_t *idr_spinlock, u32 swid)
 {
 	unsigned long flags;
+	void *ptr;
 
 	spin_lock_irqsave(idr_spinlock, flags);
-	idr_remove(idr, swid);
+	ptr = idr_remove(idr, swid);
 	spin_unlock_irqrestore(idr_spinlock, flags);
+	return ptr;
 }
 
 static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
@@ -165,20 +167,12 @@ static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
 	kfree(buf);
 }
 
-struct mlx5_teardown_stream_context {
-	struct mlx5_fpga_tls_command_context cmd;
-	u32 swid;
-};
-
 static void
 mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 				  struct mlx5_fpga_device *fdev,
 				  struct mlx5_fpga_tls_command_context *cmd,
 				  struct mlx5_fpga_dma_buf *resp)
 {
-	struct mlx5_teardown_stream_context *ctx =
-		    container_of(cmd, struct mlx5_teardown_stream_context, cmd);
-
 	if (resp) {
 		u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome);
 
@@ -186,14 +180,6 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
-			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->tx_idr_spinlock,
-						   ctx->swid);
-		else
-			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
-						   &fdev->tls->rx_idr_spinlock,
-						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
 }
@@ -225,8 +211,14 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 
 	rcu_read_lock();
 	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
-	rcu_read_unlock();
+	if (unlikely(!flow)) {
+		rcu_read_unlock();
+		WARN_ONCE(1, "Received NULL pointer for handle\n");
+		kfree(buf);
+		return -EINVAL;
+	}
 	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+	rcu_read_unlock();
 
 	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
 	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
@@ -238,6 +230,8 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 	buf->complete = mlx_tls_kfree_complete;
 
 	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+	if (ret < 0)
+		kfree(buf);
 
 	return ret;
 }
@@ -245,7 +239,7 @@ int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
-	struct mlx5_teardown_stream_context *ctx;
+	struct mlx5_fpga_tls_command_context *ctx;
 	struct mlx5_fpga_dma_buf *buf;
 	void *cmd;
 
@@ -253,7 +247,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	if (!ctx)
 		return;
 
-	buf = &ctx->cmd.buf;
+	buf = &ctx->buf;
 	cmd = (ctx + 1);
 	MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM);
 	MLX5_SET(tls_cmd, cmd, swid, swid);
@@ -264,8 +258,7 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 	buf->sg[0].data = cmd;
 	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
 
-	ctx->swid = swid;
-	mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd,
+	mlx5_fpga_tls_cmd_send(mdev->fpga, ctx,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
@@ -275,13 +268,14 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
-	rcu_read_lock();
 	if (direction_sx)
-		flow = idr_find(&tls->tx_idr, swid);
+		flow = mlx5_fpga_tls_release_swid(&tls->tx_idr,
+						  &tls->tx_idr_spinlock,
+						  swid);
 	else
-		flow = idr_find(&tls->rx_idr, swid);
-
-	rcu_read_unlock();
+		flow = mlx5_fpga_tls_release_swid(&tls->rx_idr,
+						  &tls->rx_idr_spinlock,
+						  swid);
 
 	if (!flow) {
 		mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n",
@@ -289,6 +283,7 @@ void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
 		return;
 	}
 
+	synchronize_rcu(); /* before kfree(flow) */
 	mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index 08a891f9aade..c44ccb67c4a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -308,22 +308,68 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
+static int mlx5_set_extended_dest(struct mlx5_core_dev *dev,
+				  struct fs_fte *fte, bool *extended_dest)
+{
+	int fw_log_max_fdb_encap_uplink =
+		MLX5_CAP_ESW(dev, log_max_fdb_encap_uplink);
+	int num_fwd_destinations = 0;
+	struct mlx5_flow_rule *dst;
+	int num_encap = 0;
+
+	*extended_dest = false;
+	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
+		return 0;
+
+	list_for_each_entry(dst, &fte->node.children, node.list) {
+		if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER)
+			continue;
+		if (dst->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
+		    dst->dest_attr.vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID)
+			num_encap++;
+		num_fwd_destinations++;
+	}
+	if (num_fwd_destinations > 1 && num_encap > 0)
+		*extended_dest = true;
+
+	if (*extended_dest && !fw_log_max_fdb_encap_uplink) {
+		mlx5_core_warn(dev, "FW does not support extended destination");
+		return -EOPNOTSUPP;
+	}
+	if (num_encap > (1 << fw_log_max_fdb_encap_uplink)) {
+		mlx5_core_warn(dev, "FW does not support more than %d encaps",
+			       1 << fw_log_max_fdb_encap_uplink);
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
 static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			    int opmod, int modify_mask,
 			    struct mlx5_flow_table *ft,
 			    unsigned group_id,
 			    struct fs_fte *fte)
 {
-	unsigned int inlen = MLX5_ST_SZ_BYTES(set_fte_in) +
-		fte->dests_size * MLX5_ST_SZ_BYTES(dest_format_struct);
 	u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {0};
+	bool extended_dest = false;
 	struct mlx5_flow_rule *dst;
 	void *in_flow_context, *vlan;
 	void *in_match_value;
+	unsigned int inlen;
+	int dst_cnt_size;
 	void *in_dests;
 	u32 *in;
 	int err;
 
+	if (mlx5_set_extended_dest(dev, fte, &extended_dest))
+		return -EOPNOTSUPP;
+
+	if (!extended_dest)
+		dst_cnt_size = MLX5_ST_SZ_BYTES(dest_format_struct);
+	else
+		dst_cnt_size = MLX5_ST_SZ_BYTES(extended_dest_format);
+
+	inlen = MLX5_ST_SZ_BYTES(set_fte_in) + fte->dests_size * dst_cnt_size;
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -343,9 +389,20 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
 
 	MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag);
-	MLX5_SET(flow_context, in_flow_context, action, fte->action.action);
-	MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
-		 fte->action.reformat_id);
+	MLX5_SET(flow_context, in_flow_context, extended_destination,
+		 extended_dest);
+	if (extended_dest) {
+		u32 action;
+
+		action = fte->action.action &
+			~MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
+		MLX5_SET(flow_context, in_flow_context, action, action);
+	} else {
+		MLX5_SET(flow_context, in_flow_context, action,
+			 fte->action.action);
+		MLX5_SET(flow_context, in_flow_context, packet_reformat_id,
+			 fte->action.reformat_id);
+	}
 	MLX5_SET(flow_context, in_flow_context, modify_header_id,
 		 fte->action.modify_id);
 
@@ -387,10 +444,20 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 				id = dst->dest_attr.vport.num;
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id_valid,
-					 dst->dest_attr.vport.vhca_id_valid);
+					 !!(dst->dest_attr.vport.flags &
+					    MLX5_FLOW_DEST_VPORT_VHCA_ID));
 				MLX5_SET(dest_format_struct, in_dests,
 					 destination_eswitch_owner_vhca_id,
 					 dst->dest_attr.vport.vhca_id);
+				if (extended_dest) {
+					MLX5_SET(dest_format_struct, in_dests,
+						 packet_reformat,
+						 !!(dst->dest_attr.vport.flags &
+						    MLX5_FLOW_DEST_VPORT_REFORMAT_ID));
+					MLX5_SET(extended_dest_format, in_dests,
+						 packet_reformat_id,
+						 dst->dest_attr.vport.reformat_id);
+				}
 				break;
 			default:
 				id = dst->dest_attr.tir_num;
@@ -399,7 +466,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 			MLX5_SET(dest_format_struct, in_dests, destination_type,
 				 type);
 			MLX5_SET(dest_format_struct, in_dests, destination_id, id);
-			in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
+			in_dests += dst_cnt_size;
 			list_size++;
 		}
 
@@ -420,7 +487,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 
 			MLX5_SET(flow_counter_list, in_dests, flow_counter_id,
 				 dst->dest_attr.counter_id);
-			in_dests += MLX5_ST_SZ_BYTES(dest_format_struct);
+			in_dests += dst_cnt_size;
 			list_size++;
 		}
 		if (list_size > max_list_size) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 08233cf44871..0be3eb86dd84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -32,6 +32,7 @@
 
 #include <linux/mutex.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <linux/mlx5/eswitch.h>
 
 #include "mlx5_core.h"
@@ -262,10 +263,11 @@ static void nested_down_write_ref_node(struct fs_node *node,
 	}
 }
 
-static void down_write_ref_node(struct fs_node *node)
+static void down_write_ref_node(struct fs_node *node, bool locked)
 {
 	if (node) {
-		down_write(&node->lock);
+		if (!locked)
+			down_write(&node->lock);
 		refcount_inc(&node->refcount);
 	}
 }
@@ -276,13 +278,14 @@ static void up_read_ref_node(struct fs_node *node)
 	up_read(&node->lock);
 }
 
-static void up_write_ref_node(struct fs_node *node)
+static void up_write_ref_node(struct fs_node *node, bool locked)
 {
 	refcount_dec(&node->refcount);
-	up_write(&node->lock);
+	if (!locked)
+		up_write(&node->lock);
 }
 
-static void tree_put_node(struct fs_node *node)
+static void tree_put_node(struct fs_node *node, bool locked)
 {
 	struct fs_node *parent_node = node->parent;
 
@@ -293,27 +296,27 @@ static void tree_put_node(struct fs_node *node)
 			/* Only root namespace doesn't have parent and we just
 			 * need to free its node.
 			 */
-			down_write_ref_node(parent_node);
+			down_write_ref_node(parent_node, locked);
 			list_del_init(&node->list);
 			if (node->del_sw_func)
 				node->del_sw_func(node);
-			up_write_ref_node(parent_node);
+			up_write_ref_node(parent_node, locked);
 		} else {
 			kfree(node);
 		}
 		node = NULL;
 	}
 	if (!node && parent_node)
-		tree_put_node(parent_node);
+		tree_put_node(parent_node, locked);
 }
 
-static int tree_remove_node(struct fs_node *node)
+static int tree_remove_node(struct fs_node *node, bool locked)
 {
 	if (refcount_read(&node->refcount) > 1) {
 		refcount_dec(&node->refcount);
 		return -EEXIST;
 	}
-	tree_put_node(node);
+	tree_put_node(node, locked);
 	return 0;
 }
 
@@ -397,6 +400,7 @@ static void del_hw_flow_table(struct fs_node *node)
 	fs_get_obj(ft, node);
 	dev = get_dev(&ft->node);
 	root = find_root(&ft->node);
+	trace_mlx5_fs_del_ft(ft);
 
 	if (node->active) {
 		err = root->cmds->destroy_flow_table(dev, ft);
@@ -418,22 +422,34 @@ static void del_sw_flow_table(struct fs_node *node)
 	kfree(ft);
 }
 
-static void del_sw_hw_rule(struct fs_node *node)
+static void modify_fte(struct fs_fte *fte)
 {
 	struct mlx5_flow_root_namespace *root;
-	struct mlx5_flow_rule *rule;
 	struct mlx5_flow_table *ft;
 	struct mlx5_flow_group *fg;
-	struct fs_fte *fte;
-	int modify_mask;
-	struct mlx5_core_dev *dev = get_dev(node);
+	struct mlx5_core_dev *dev;
 	int err;
-	bool update_fte = false;
 
-	fs_get_obj(rule, node);
-	fs_get_obj(fte, rule->node.parent);
 	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
+	dev = get_dev(&fte->node);
+
+	root = find_root(&ft->node);
+	err = root->cmds->update_fte(dev, ft, fg->id, fte->modify_mask, fte);
+	if (err)
+		mlx5_core_warn(dev,
+			       "%s can't del rule fg id=%d fte_index=%d\n",
+			       __func__, fg->id, fte->index);
+	fte->modify_mask = 0;
+}
+
+static void del_sw_hw_rule(struct fs_node *node)
+{
+	struct mlx5_flow_rule *rule;
+	struct fs_fte *fte;
+
+	fs_get_obj(rule, node);
+	fs_get_obj(fte, rule->node.parent);
 	trace_mlx5_fs_del_rule(rule);
 	if (rule->sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		mutex_lock(&rule->dest_attr.ft->lock);
@@ -443,27 +459,19 @@ static void del_sw_hw_rule(struct fs_node *node)
 
 	if (rule->dest_attr.type == MLX5_FLOW_DESTINATION_TYPE_COUNTER  &&
 	    --fte->dests_size) {
-		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
-			      BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
+		fte->modify_mask |=
+			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_ACTION) |
+			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_FLOW_COUNTERS);
 		fte->action.action &= ~MLX5_FLOW_CONTEXT_ACTION_COUNT;
-		update_fte = true;
 		goto out;
 	}
 
 	if ((fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) &&
 	    --fte->dests_size) {
-		modify_mask = BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
-		update_fte = true;
+		fte->modify_mask |=
+			BIT(MLX5_SET_FTE_MODIFY_ENABLE_MASK_DESTINATION_LIST);
 	}
 out:
-	root = find_root(&ft->node);
-	if (update_fte && fte->dests_size) {
-		err = root->cmds->update_fte(dev, ft, fg->id, modify_mask, fte);
-		if (err)
-			mlx5_core_warn(dev,
-				       "%s can't del rule fg id=%d fte_index=%d\n",
-				       __func__, fg->id, fte->index);
-	}
 	kfree(rule);
 }
 
@@ -489,6 +497,7 @@ static void del_hw_fte(struct fs_node *node)
 			mlx5_core_warn(dev,
 				       "flow steering can't delete fte in index %d of flow group id %d\n",
 				       fte->index, fg->id);
+		node->active = 0;
 	}
 }
 
@@ -589,7 +598,7 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	fte->node.type =  FS_TYPE_FLOW_ENTRY;
 	fte->action = *flow_act;
 
-	tree_init_node(&fte->node, del_hw_fte, del_sw_fte);
+	tree_init_node(&fte->node, NULL, del_sw_fte);
 
 	return fte;
 }
@@ -618,7 +627,8 @@ static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steer
 	if (ret) {
 		kmem_cache_free(steering->fgs_cache, fg);
 		return ERR_PTR(ret);
-}
+	}
+
 	ida_init(&fg->fte_allocator);
 	fg->mask.match_criteria_enable = match_criteria_enable;
 	memcpy(&fg->mask.match_criteria, match_criteria,
@@ -855,7 +865,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 	fs_get_obj(fte, rule->node.parent);
 	if (!(fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST))
 		return -EINVAL;
-	down_write_ref_node(&fte->node);
+	down_write_ref_node(&fte->node, false);
 	fs_get_obj(fg, fte->node.parent);
 	fs_get_obj(ft, fg->node.parent);
 
@@ -863,7 +873,7 @@ static int _mlx5_modify_rule_destination(struct mlx5_flow_rule *rule,
 	root = find_root(&ft->node);
 	err = root->cmds->update_fte(get_dev(&ft->node), ft, fg->id,
 				     modify_mask, fte);
-	up_write_ref_node(&fte->node);
+	up_write_ref_node(&fte->node, false);
 
 	return err;
 }
@@ -1013,12 +1023,13 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa
 	if (err)
 		goto destroy_ft;
 	ft->node.active = true;
-	down_write_ref_node(&fs_prio->node);
+	down_write_ref_node(&fs_prio->node, false);
 	tree_add_node(&ft->node, &fs_prio->node);
 	list_add_flow_table(ft, fs_prio);
 	fs_prio->num_ft++;
-	up_write_ref_node(&fs_prio->node);
+	up_write_ref_node(&fs_prio->node, false);
 	mutex_unlock(&root->chain_lock);
+	trace_mlx5_fs_add_ft(ft);
 	return ft;
 destroy_ft:
 	root->cmds->destroy_flow_table(root->dev, ft);
@@ -1110,17 +1121,17 @@ struct mlx5_flow_group *mlx5_create_flow_group(struct mlx5_flow_table *ft,
 	if (ft->autogroup.active)
 		return ERR_PTR(-EPERM);
 
-	down_write_ref_node(&ft->node);
+	down_write_ref_node(&ft->node, false);
 	fg = alloc_insert_flow_group(ft, match_criteria_enable, match_criteria,
 				     start_index, end_index,
 				     ft->node.children.prev);
-	up_write_ref_node(&ft->node);
+	up_write_ref_node(&ft->node, false);
 	if (IS_ERR(fg))
 		return fg;
 
 	err = root->cmds->create_flow_group(dev, ft, fg_in, &fg->id);
 	if (err) {
-		tree_put_node(&fg->node);
+		tree_put_node(&fg->node, false);
 		return ERR_PTR(err);
 	}
 	trace_mlx5_fs_add_fg(fg);
@@ -1373,7 +1384,10 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1,
 {
 	if (d1->type == d2->type) {
 		if ((d1->type == MLX5_FLOW_DESTINATION_TYPE_VPORT &&
-		     d1->vport.num == d2->vport.num) ||
+		     d1->vport.num == d2->vport.num &&
+		     d1->vport.flags == d2->vport.flags &&
+		     ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ?
+		      (d1->vport.reformat_id == d2->vport.reformat_id) : true)) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE &&
 		     d1->ft == d2->ft) ||
 		    (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR &&
@@ -1514,10 +1528,10 @@ static void free_match_list(struct match_list_head *head)
 		struct match_list *iter, *match_tmp;
 
 		list_del(&head->first.list);
-		tree_put_node(&head->first.g->node);
+		tree_put_node(&head->first.g->node, false);
 		list_for_each_entry_safe(iter, match_tmp, &head->list,
 					 list) {
-			tree_put_node(&iter->g->node);
+			tree_put_node(&iter->g->node, false);
 			list_del(&iter->list);
 			kfree(iter);
 		}
@@ -1594,11 +1608,16 @@ lookup_fte_locked(struct mlx5_flow_group *g,
 		fte_tmp = NULL;
 		goto out;
 	}
+	if (!fte_tmp->node.active) {
+		tree_put_node(&fte_tmp->node, false);
+		fte_tmp = NULL;
+		goto out;
+	}
 
 	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
 out:
 	if (take_write)
-		up_write_ref_node(&g->node);
+		up_write_ref_node(&g->node, false);
 	else
 		up_read_ref_node(&g->node);
 	return fte_tmp;
@@ -1640,8 +1659,8 @@ search_again_locked:
 			continue;
 		rule = add_rule_fg(g, spec->match_value,
 				   flow_act, dest, dest_num, fte_tmp);
-		up_write_ref_node(&fte_tmp->node);
-		tree_put_node(&fte_tmp->node);
+		up_write_ref_node(&fte_tmp->node, false);
+		tree_put_node(&fte_tmp->node, false);
 		kmem_cache_free(steering->ftes_cache, fte);
 		return rule;
 	}
@@ -1677,7 +1696,7 @@ skip_search:
 
 		err = insert_fte(g, fte);
 		if (err) {
-			up_write_ref_node(&g->node);
+			up_write_ref_node(&g->node, false);
 			if (err == -ENOSPC)
 				continue;
 			kmem_cache_free(steering->ftes_cache, fte);
@@ -1685,11 +1704,11 @@ skip_search:
 		}
 
 		nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
-		up_write_ref_node(&g->node);
+		up_write_ref_node(&g->node, false);
 		rule = add_rule_fg(g, spec->match_value,
 				   flow_act, dest, dest_num, fte);
-		up_write_ref_node(&fte->node);
-		tree_put_node(&fte->node);
+		up_write_ref_node(&fte->node, false);
+		tree_put_node(&fte->node, false);
 		return rule;
 	}
 	rule = ERR_PTR(-ENOENT);
@@ -1731,7 +1750,7 @@ search_again_locked:
 	err = build_match_list(&match_head, ft, spec);
 	if (err) {
 		if (take_write)
-			up_write_ref_node(&ft->node);
+			up_write_ref_node(&ft->node, false);
 		else
 			up_read_ref_node(&ft->node);
 		return ERR_PTR(err);
@@ -1746,7 +1765,7 @@ search_again_locked:
 	if (!IS_ERR(rule) ||
 	    (PTR_ERR(rule) != -ENOENT && PTR_ERR(rule) != -EAGAIN)) {
 		if (take_write)
-			up_write_ref_node(&ft->node);
+			up_write_ref_node(&ft->node, false);
 		return rule;
 	}
 
@@ -1762,12 +1781,12 @@ search_again_locked:
 	g = alloc_auto_flow_group(ft, spec);
 	if (IS_ERR(g)) {
 		rule = ERR_CAST(g);
-		up_write_ref_node(&ft->node);
+		up_write_ref_node(&ft->node, false);
 		return rule;
 	}
 
 	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
-	up_write_ref_node(&ft->node);
+	up_write_ref_node(&ft->node, false);
 
 	err = create_auto_flow_group(ft, g);
 	if (err)
@@ -1786,17 +1805,17 @@ search_again_locked:
 	}
 
 	nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
-	up_write_ref_node(&g->node);
+	up_write_ref_node(&g->node, false);
 	rule = add_rule_fg(g, spec->match_value, flow_act, dest,
 			   dest_num, fte);
-	up_write_ref_node(&fte->node);
-	tree_put_node(&fte->node);
-	tree_put_node(&g->node);
+	up_write_ref_node(&fte->node, false);
+	tree_put_node(&fte->node, false);
+	tree_put_node(&g->node, false);
 	return rule;
 
 err_release_fg:
-	up_write_ref_node(&g->node);
-	tree_put_node(&g->node);
+	up_write_ref_node(&g->node, false);
+	tree_put_node(&g->node, false);
 	return ERR_PTR(err);
 }
 
@@ -1859,10 +1878,33 @@ EXPORT_SYMBOL(mlx5_add_flow_rules);
 
 void mlx5_del_flow_rules(struct mlx5_flow_handle *handle)
 {
+	struct fs_fte *fte;
 	int i;
 
+	/* In order to consolidate the HW changes we lock the FTE for other
+	 * changes, and increase its refcount, in order not to perform the
+	 * "del" functions of the FTE. Will handle them here.
+	 * The removal of the rules is done under locked FTE.
+	 * After removing all the handle's rules, if there are remaining
+	 * rules, it means we just need to modify the FTE in FW, and
+	 * unlock/decrease the refcount we increased before.
+	 * Otherwise, it means the FTE should be deleted. First delete the
+	 * FTE in FW. Then, unlock the FTE, and proceed the tree_put_node of
+	 * the FTE, which will handle the last decrease of the refcount, as
+	 * well as required handling of its parent.
+	 */
+	fs_get_obj(fte, handle->rule[0]->node.parent);
+	down_write_ref_node(&fte->node, false);
 	for (i = handle->num_rules - 1; i >= 0; i--)
-		tree_remove_node(&handle->rule[i]->node);
+		tree_remove_node(&handle->rule[i]->node, true);
+	if (fte->modify_mask && fte->dests_size) {
+		modify_fte(fte);
+		up_write_ref_node(&fte->node, false);
+	} else {
+		del_hw_fte(&fte->node);
+		up_write(&fte->node.lock);
+		tree_put_node(&fte->node, false);
+	}
 	kfree(handle);
 }
 EXPORT_SYMBOL(mlx5_del_flow_rules);
@@ -1965,7 +2007,7 @@ int mlx5_destroy_flow_table(struct mlx5_flow_table *ft)
 		mutex_unlock(&root->chain_lock);
 		return err;
 	}
-	if (tree_remove_node(&ft->node))
+	if (tree_remove_node(&ft->node, false))
 		mlx5_core_warn(get_dev(&ft->node), "Flow table %d wasn't destroyed, refcount > 1\n",
 			       ft->id);
 	mutex_unlock(&root->chain_lock);
@@ -1976,7 +2018,7 @@ EXPORT_SYMBOL(mlx5_destroy_flow_table);
 
 void mlx5_destroy_flow_group(struct mlx5_flow_group *fg)
 {
-	if (tree_remove_node(&fg->node))
+	if (tree_remove_node(&fg->node, false))
 		mlx5_core_warn(get_dev(&fg->node), "Flow group %d wasn't destroyed, refcount > 1\n",
 			       fg->id);
 }
@@ -2360,8 +2402,8 @@ static void clean_tree(struct fs_node *node)
 		tree_get_node(node);
 		list_for_each_entry_safe(iter, temp, &node->children, list)
 			clean_tree(iter);
-		tree_put_node(node);
-		tree_remove_node(node);
+		tree_put_node(node, false);
+		tree_remove_node(node, false);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index b51ad217da32..87de0e4d9124 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -145,29 +145,6 @@ struct mlx5_flow_table {
 	struct rhltable			fgs_hash;
 };
 
-struct mlx5_fc_cache {
-	u64 packets;
-	u64 bytes;
-	u64 lastuse;
-};
-
-struct mlx5_fc {
-	struct list_head list;
-	struct llist_node addlist;
-	struct llist_node dellist;
-
-	/* last{packets,bytes} members are used when calculating the delta since
-	 * last reading
-	 */
-	u64 lastpackets;
-	u64 lastbytes;
-
-	u32 id;
-	bool aging;
-
-	struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
-};
-
 struct mlx5_ft_underlay_qp {
 	struct list_head list;
 	u32 qpn;
@@ -195,6 +172,7 @@ struct fs_fte {
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
 	struct rhash_head		hash;
+	int				modify_mask;
 };
 
 /* Type of children is mlx5_flow_table/namespace */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 32accd6b041b..c6c28f56aa29 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -41,6 +41,29 @@
 /* Max number of counters to query in bulk read is 32K */
 #define MLX5_SW_MAX_COUNTERS_BULK BIT(15)
 
+struct mlx5_fc_cache {
+	u64 packets;
+	u64 bytes;
+	u64 lastuse;
+};
+
+struct mlx5_fc {
+	struct list_head list;
+	struct llist_node addlist;
+	struct llist_node dellist;
+
+	/* last{packets,bytes} members are used when calculating the delta since
+	 * last reading
+	 */
+	u64 lastpackets;
+	u64 lastbytes;
+
+	u32 id;
+	bool aging;
+
+	struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
+};
+
 /* locking scheme:
  *
  * It is the responsibility of the user to prevent concurrent calls or bad
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 43118de8ee99..cb9fa3430c53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -38,6 +38,8 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
+#include "lib/mlx5.h"
 
 enum {
 	MLX5_HEALTH_POLL_INTERVAL	= 2 * HZ,
@@ -78,29 +80,6 @@ void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state)
 		    &dev->iseg->cmdq_addr_l_sz);
 }
 
-static void trigger_cmd_completions(struct mlx5_core_dev *dev)
-{
-	unsigned long flags;
-	u64 vector;
-
-	/* wait for pending handlers to complete */
-	synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
-	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
-	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
-	if (!vector)
-		goto no_trig;
-
-	vector |= MLX5_TRIGGERED_CMD_COMP;
-	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
-
-	mlx5_core_dbg(dev, "vector 0x%llx\n", vector);
-	mlx5_cmd_comp_handler(dev, vector, true);
-	return;
-
-no_trig:
-	spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags);
-}
-
 static int in_fatal(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -124,10 +103,10 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force)
 	mlx5_core_err(dev, "start\n");
 	if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) {
 		dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR;
-		trigger_cmd_completions(dev);
+		mlx5_cmd_flush(dev);
 	}
 
-	mlx5_core_event(dev, MLX5_DEV_EVENT_SYS_ERROR, 1);
+	mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1);
 	mlx5_core_err(dev, "end\n");
 
 unlock:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 11dabd62e2c7..4eac42555c7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -87,7 +87,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev,
 	mlx5_query_port_max_mtu(mdev, &max_mtu, 1);
 	netdev->mtu = max_mtu;
 
-	mlx5e_build_nic_params(mdev, &priv->channels.params,
+	mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params,
 			       mlx5e_get_netdev_max_channels(netdev),
 			       netdev->mtu);
 	mlx5i_build_nic_params(mdev, &priv->channels.params);
@@ -446,11 +446,11 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu)
 
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
-	err = mlx5e_open_channels(priv, &new_channels);
+
+	err = mlx5e_safe_switch_channels(priv, &new_channels, NULL);
 	if (err)
 		goto out;
 
-	mlx5e_switch_priv_channels(priv, &new_channels, NULL);
 	netdev->mtu = new_channels.params.sw_mtu;
 
 out:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 582b2f18010a..959605559858 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -34,39 +34,9 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/vport.h>
 #include "mlx5_core.h"
-
-enum {
-	MLX5_LAG_FLAG_BONDED = 1 << 0,
-};
-
-struct lag_func {
-	struct mlx5_core_dev *dev;
-	struct net_device    *netdev;
-};
-
-/* Used for collection of netdev event info. */
-struct lag_tracker {
-	enum   netdev_lag_tx_type           tx_type;
-	struct netdev_lag_lower_state_info  netdev_state[MLX5_MAX_PORTS];
-	bool is_bonded;
-};
-
-/* LAG data of a ConnectX card.
- * It serves both its phys functions.
- */
-struct mlx5_lag {
-	u8                        flags;
-	u8                        v2p_map[MLX5_MAX_PORTS];
-	struct lag_func           pf[MLX5_MAX_PORTS];
-	struct lag_tracker        tracker;
-	struct delayed_work       bond_work;
-	struct notifier_block     nb;
-
-	/* Admin state. Allow lag only if allowed is true
-	 * even if network conditions for lag were met
-	 */
-	bool                      allowed;
-};
+#include "eswitch.h"
+#include "lag.h"
+#include "lag_mp.h"
 
 /* General purpose, use for short periods of time.
  * Beware of lock dependencies (preferably, no locks should be acquired
@@ -148,13 +118,8 @@ static int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
 
-static struct mlx5_lag *mlx5_lag_dev_get(struct mlx5_core_dev *dev)
-{
-	return dev->priv.lag;
-}
-
-static int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
-				       struct net_device *ndev)
+int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
+				struct net_device *ndev)
 {
 	int i;
 
@@ -165,9 +130,14 @@ static int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
 	return -1;
 }
 
-static bool mlx5_lag_is_bonded(struct mlx5_lag *ldev)
+static bool __mlx5_lag_is_roce(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_ROCE);
+}
+
+static bool __mlx5_lag_is_sriov(struct mlx5_lag *ldev)
 {
-	return !!(ldev->flags & MLX5_LAG_FLAG_BONDED);
+	return !!(ldev->flags & MLX5_LAG_FLAG_SRIOV);
 }
 
 static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
@@ -186,36 +156,131 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 		*port2 = 1;
 }
 
-static void mlx5_activate_lag(struct mlx5_lag *ldev,
-			      struct lag_tracker *tracker)
+void mlx5_modify_lag(struct mlx5_lag *ldev,
+		     struct lag_tracker *tracker)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	u8 v2p_port1, v2p_port2;
 	int err;
 
-	ldev->flags |= MLX5_LAG_FLAG_BONDED;
+	mlx5_infer_tx_affinity_mapping(tracker, &v2p_port1,
+				       &v2p_port2);
+
+	if (v2p_port1 != ldev->v2p_map[0] ||
+	    v2p_port2 != ldev->v2p_map[1]) {
+		ldev->v2p_map[0] = v2p_port1;
+		ldev->v2p_map[1] = v2p_port2;
+
+		mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d",
+			       ldev->v2p_map[0], ldev->v2p_map[1]);
+
+		err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
+		if (err)
+			mlx5_core_err(dev0,
+				      "Failed to modify LAG (%d)\n",
+				      err);
+	}
+}
+
+static int mlx5_create_lag(struct mlx5_lag *ldev,
+			   struct lag_tracker *tracker)
+{
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	int err;
 
 	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0],
 				       &ldev->v2p_map[1]);
 
+	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d",
+		       ldev->v2p_map[0], ldev->v2p_map[1]);
+
 	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[0], ldev->v2p_map[1]);
 	if (err)
 		mlx5_core_err(dev0,
 			      "Failed to create LAG (%d)\n",
 			      err);
+	return err;
+}
+
+int mlx5_activate_lag(struct mlx5_lag *ldev,
+		      struct lag_tracker *tracker,
+		      u8 flags)
+{
+	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
+	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	int err;
+
+	err = mlx5_create_lag(ldev, tracker);
+	if (err) {
+		if (roce_lag) {
+			mlx5_core_err(dev0,
+				      "Failed to activate RoCE LAG\n");
+		} else {
+			mlx5_core_err(dev0,
+				      "Failed to activate VF LAG\n"
+				      "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n");
+		}
+		return err;
+	}
+
+	ldev->flags |= flags;
+	return 0;
 }
 
-static void mlx5_deactivate_lag(struct mlx5_lag *ldev)
+static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 {
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	bool roce_lag = __mlx5_lag_is_roce(ldev);
 	int err;
 
-	ldev->flags &= ~MLX5_LAG_FLAG_BONDED;
+	ldev->flags &= ~MLX5_LAG_MODE_FLAGS;
 
 	err = mlx5_cmd_destroy_lag(dev0);
-	if (err)
-		mlx5_core_err(dev0,
-			      "Failed to destroy LAG (%d)\n",
-			      err);
+	if (err) {
+		if (roce_lag) {
+			mlx5_core_err(dev0,
+				      "Failed to deactivate RoCE LAG; driver restart required\n");
+		} else {
+			mlx5_core_err(dev0,
+				      "Failed to deactivate VF LAG; driver restart required\n"
+				      "Make sure all VFs are unbound prior to VF LAG activation or deactivation\n");
+		}
+	}
+
+	return err;
+}
+
+static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
+{
+	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+		return false;
+
+#ifdef CONFIG_MLX5_ESWITCH
+	return mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+#else
+	return (!mlx5_sriov_is_enabled(ldev->pf[0].dev) &&
+		!mlx5_sriov_is_enabled(ldev->pf[1].dev));
+#endif
+}
+
+static void mlx5_lag_add_ib_devices(struct mlx5_lag *ldev)
+{
+	int i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev)
+			mlx5_add_dev_by_protocol(ldev->pf[i].dev,
+						 MLX5_INTERFACE_PROTOCOL_IB);
+}
+
+static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev)
+{
+	int i;
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (ldev->pf[i].dev)
+			mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
+						    MLX5_INTERFACE_PROTOCOL_IB);
 }
 
 static void mlx5_do_bond(struct mlx5_lag *ldev)
@@ -223,9 +288,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
 	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
 	struct lag_tracker tracker;
-	u8 v2p_port1, v2p_port2;
-	int i, err;
-	bool do_bond;
+	bool do_bond, roce_lag;
+	int err;
 
 	if (!dev0 || !dev1)
 		return;
@@ -234,48 +298,56 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	tracker = ldev->tracker;
 	mutex_unlock(&lag_mutex);
 
-	do_bond = tracker.is_bonded && ldev->allowed;
+	do_bond = tracker.is_bonded && mlx5_lag_check_prereq(ldev);
 
-	if (do_bond && !mlx5_lag_is_bonded(ldev)) {
-		for (i = 0; i < MLX5_MAX_PORTS; i++)
-			mlx5_remove_dev_by_protocol(ldev->pf[i].dev,
-						    MLX5_INTERFACE_PROTOCOL_IB);
+	if (do_bond && !__mlx5_lag_is_active(ldev)) {
+		roce_lag = !mlx5_sriov_is_enabled(dev0) &&
+			   !mlx5_sriov_is_enabled(dev1);
 
-		mlx5_activate_lag(ldev, &tracker);
+#ifdef CONFIG_MLX5_ESWITCH
+		roce_lag &= dev0->priv.eswitch->mode == SRIOV_NONE &&
+			    dev1->priv.eswitch->mode == SRIOV_NONE;
+#endif
 
-		mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
-		mlx5_nic_vport_enable_roce(dev1);
-	} else if (do_bond && mlx5_lag_is_bonded(ldev)) {
-		mlx5_infer_tx_affinity_mapping(&tracker, &v2p_port1,
-					       &v2p_port2);
+		if (roce_lag)
+			mlx5_lag_remove_ib_devices(ldev);
 
-		if ((v2p_port1 != ldev->v2p_map[0]) ||
-		    (v2p_port2 != ldev->v2p_map[1])) {
-			ldev->v2p_map[0] = v2p_port1;
-			ldev->v2p_map[1] = v2p_port2;
+		err = mlx5_activate_lag(ldev, &tracker,
+					roce_lag ? MLX5_LAG_FLAG_ROCE :
+					MLX5_LAG_FLAG_SRIOV);
+		if (err) {
+			if (roce_lag)
+				mlx5_lag_add_ib_devices(ldev);
 
-			err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
-			if (err)
-				mlx5_core_err(dev0,
-					      "Failed to modify LAG (%d)\n",
-					      err);
+			return;
 		}
-	} else if (!do_bond && mlx5_lag_is_bonded(ldev)) {
-		mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
-		mlx5_nic_vport_disable_roce(dev1);
 
-		mlx5_deactivate_lag(ldev);
+		if (roce_lag) {
+			mlx5_add_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
+			mlx5_nic_vport_enable_roce(dev1);
+		}
+	} else if (do_bond && __mlx5_lag_is_active(ldev)) {
+		mlx5_modify_lag(ldev, &tracker);
+	} else if (!do_bond && __mlx5_lag_is_active(ldev)) {
+		roce_lag = __mlx5_lag_is_roce(ldev);
+
+		if (roce_lag) {
+			mlx5_remove_dev_by_protocol(dev0, MLX5_INTERFACE_PROTOCOL_IB);
+			mlx5_nic_vport_disable_roce(dev1);
+		}
 
-		for (i = 0; i < MLX5_MAX_PORTS; i++)
-			if (ldev->pf[i].dev)
-				mlx5_add_dev_by_protocol(ldev->pf[i].dev,
-							 MLX5_INTERFACE_PROTOCOL_IB);
+		err = mlx5_deactivate_lag(ldev);
+		if (err)
+			return;
+
+		if (roce_lag)
+			mlx5_lag_add_ib_devices(ldev);
 	}
 }
 
 static void mlx5_queue_bond_work(struct mlx5_lag *ldev, unsigned long delay)
 {
-	schedule_delayed_work(&ldev->bond_work, delay);
+	queue_delayed_work(ldev->wq, &ldev->bond_work, delay);
 }
 
 static void mlx5_do_bond_work(struct work_struct *work)
@@ -419,15 +491,6 @@ static int mlx5_lag_netdev_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
-{
-	if ((ldev->pf[0].dev && mlx5_sriov_is_enabled(ldev->pf[0].dev)) ||
-	    (ldev->pf[1].dev && mlx5_sriov_is_enabled(ldev->pf[1].dev)))
-		return false;
-	else
-		return true;
-}
-
 static struct mlx5_lag *mlx5_lag_dev_alloc(void)
 {
 	struct mlx5_lag *ldev;
@@ -436,14 +499,20 @@ static struct mlx5_lag *mlx5_lag_dev_alloc(void)
 	if (!ldev)
 		return NULL;
 
+	ldev->wq = create_singlethread_workqueue("mlx5_lag");
+	if (!ldev->wq) {
+		kfree(ldev);
+		return NULL;
+	}
+
 	INIT_DELAYED_WORK(&ldev->bond_work, mlx5_do_bond_work);
-	ldev->allowed = mlx5_lag_check_prereq(ldev);
 
 	return ldev;
 }
 
 static void mlx5_lag_dev_free(struct mlx5_lag *ldev)
 {
+	destroy_workqueue(ldev->wq);
 	kfree(ldev);
 }
 
@@ -462,7 +531,6 @@ static void mlx5_lag_dev_add_pf(struct mlx5_lag *ldev,
 	ldev->tracker.netdev_state[fn].link_up = 0;
 	ldev->tracker.netdev_state[fn].tx_enabled = 0;
 
-	ldev->allowed = mlx5_lag_check_prereq(ldev);
 	dev->priv.lag = ldev;
 
 	mutex_unlock(&lag_mutex);
@@ -484,7 +552,6 @@ static void mlx5_lag_dev_remove_pf(struct mlx5_lag *ldev,
 	memset(&ldev->pf[i], 0, sizeof(*ldev->pf));
 
 	dev->priv.lag = NULL;
-	ldev->allowed = mlx5_lag_check_prereq(ldev);
 	mutex_unlock(&lag_mutex);
 }
 
@@ -493,6 +560,7 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 {
 	struct mlx5_lag *ldev = NULL;
 	struct mlx5_core_dev *tmp_dev;
+	int err;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager) ||
 	    !MLX5_CAP_GEN(dev, lag_master) ||
@@ -520,6 +588,11 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev)
 			mlx5_core_err(dev, "Failed to register LAG netdev notifier\n");
 		}
 	}
+
+	err = mlx5_lag_mp_init(ldev);
+	if (err)
+		mlx5_core_err(dev, "Failed to init multipath lag err=%d\n",
+			      err);
 }
 
 /* Must be called with intf_mutex held */
@@ -532,7 +605,7 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
 	if (!ldev)
 		return;
 
-	if (mlx5_lag_is_bonded(ldev))
+	if (__mlx5_lag_is_active(ldev))
 		mlx5_deactivate_lag(ldev);
 
 	mlx5_lag_dev_remove_pf(ldev, dev);
@@ -544,61 +617,67 @@ void mlx5_lag_remove(struct mlx5_core_dev *dev)
 	if (i == MLX5_MAX_PORTS) {
 		if (ldev->nb.notifier_call)
 			unregister_netdevice_notifier(&ldev->nb);
+		mlx5_lag_mp_cleanup(ldev);
 		cancel_delayed_work_sync(&ldev->bond_work);
 		mlx5_lag_dev_free(ldev);
 	}
 }
 
-bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
+bool mlx5_lag_is_roce(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
 	bool res;
 
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
-	res  = ldev && mlx5_lag_is_bonded(ldev);
+	res  = ldev && __mlx5_lag_is_roce(ldev);
 	mutex_unlock(&lag_mutex);
 
 	return res;
 }
-EXPORT_SYMBOL(mlx5_lag_is_active);
+EXPORT_SYMBOL(mlx5_lag_is_roce);
 
-static int mlx5_lag_set_state(struct mlx5_core_dev *dev, bool allow)
+bool mlx5_lag_is_active(struct mlx5_core_dev *dev)
 {
 	struct mlx5_lag *ldev;
-	int ret = 0;
-	bool lag_active;
-
-	mlx5_dev_list_lock();
+	bool res;
 
+	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev) {
-		ret = -ENODEV;
-		goto unlock;
-	}
-	lag_active = mlx5_lag_is_bonded(ldev);
-	if (!mlx5_lag_check_prereq(ldev) && allow) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-	if (ldev->allowed == allow)
-		goto unlock;
-	ldev->allowed = allow;
-	if ((lag_active && !allow) || allow)
-		mlx5_do_bond(ldev);
-unlock:
-	mlx5_dev_list_unlock();
-	return ret;
+	res  = ldev && __mlx5_lag_is_active(ldev);
+	mutex_unlock(&lag_mutex);
+
+	return res;
 }
+EXPORT_SYMBOL(mlx5_lag_is_active);
 
-int mlx5_lag_forbid(struct mlx5_core_dev *dev)
+bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev)
 {
-	return mlx5_lag_set_state(dev, false);
+	struct mlx5_lag *ldev;
+	bool res;
+
+	mutex_lock(&lag_mutex);
+	ldev = mlx5_lag_dev_get(dev);
+	res  = ldev && __mlx5_lag_is_sriov(ldev);
+	mutex_unlock(&lag_mutex);
+
+	return res;
 }
+EXPORT_SYMBOL(mlx5_lag_is_sriov);
 
-int mlx5_lag_allow(struct mlx5_core_dev *dev)
+void mlx5_lag_update(struct mlx5_core_dev *dev)
 {
-	return mlx5_lag_set_state(dev, true);
+	struct mlx5_lag *ldev;
+
+	mlx5_dev_list_lock();
+	ldev = mlx5_lag_dev_get(dev);
+	if (!ldev)
+		goto unlock;
+
+	mlx5_do_bond(ldev);
+
+unlock:
+	mlx5_dev_list_unlock();
 }
 
 struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
@@ -609,7 +688,7 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
 
-	if (!(ldev && mlx5_lag_is_bonded(ldev)))
+	if (!(ldev && __mlx5_lag_is_roce(ldev)))
 		goto unlock;
 
 	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
@@ -638,7 +717,7 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 		return true;
 
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev || !mlx5_lag_is_bonded(ldev) || ldev->pf[0].dev == dev)
+	if (!ldev || !__mlx5_lag_is_roce(ldev) || ldev->pf[0].dev == dev)
 		return true;
 
 	/* If bonded, we do not add an IB device for PF1. */
@@ -665,7 +744,7 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 
 	mutex_lock(&lag_mutex);
 	ldev = mlx5_lag_dev_get(dev);
-	if (ldev && mlx5_lag_is_bonded(ldev)) {
+	if (ldev && __mlx5_lag_is_roce(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
 		mdev[0] = ldev->pf[0].dev;
 		mdev[1] = ldev->pf[1].dev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
new file mode 100644
index 000000000000..1dea0b1c9826
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_LAG_H__
+#define __MLX5_LAG_H__
+
+#include "mlx5_core.h"
+#include "lag_mp.h"
+
+enum {
+	MLX5_LAG_FLAG_ROCE   = 1 << 0,
+	MLX5_LAG_FLAG_SRIOV  = 1 << 1,
+	MLX5_LAG_FLAG_MULTIPATH = 1 << 2,
+};
+
+#define MLX5_LAG_MODE_FLAGS (MLX5_LAG_FLAG_ROCE | MLX5_LAG_FLAG_SRIOV |\
+			     MLX5_LAG_FLAG_MULTIPATH)
+
+struct lag_func {
+	struct mlx5_core_dev *dev;
+	struct net_device    *netdev;
+};
+
+/* Used for collection of netdev event info. */
+struct lag_tracker {
+	enum   netdev_lag_tx_type           tx_type;
+	struct netdev_lag_lower_state_info  netdev_state[MLX5_MAX_PORTS];
+	unsigned int is_bonded:1;
+};
+
+/* LAG data of a ConnectX card.
+ * It serves both its phys functions.
+ */
+struct mlx5_lag {
+	u8                        flags;
+	u8                        v2p_map[MLX5_MAX_PORTS];
+	struct lag_func           pf[MLX5_MAX_PORTS];
+	struct lag_tracker        tracker;
+	struct workqueue_struct   *wq;
+	struct delayed_work       bond_work;
+	struct notifier_block     nb;
+	struct lag_mp             lag_mp;
+};
+
+static inline struct mlx5_lag *
+mlx5_lag_dev_get(struct mlx5_core_dev *dev)
+{
+	return dev->priv.lag;
+}
+
+static inline bool
+__mlx5_lag_is_active(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_MODE_FLAGS);
+}
+
+void mlx5_modify_lag(struct mlx5_lag *ldev,
+		     struct lag_tracker *tracker);
+int mlx5_activate_lag(struct mlx5_lag *ldev,
+		      struct lag_tracker *tracker,
+		      u8 flags);
+int mlx5_lag_dev_get_netdev_idx(struct mlx5_lag *ldev,
+				struct net_device *ndev);
+
+#endif /* __MLX5_LAG_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
new file mode 100644
index 000000000000..5633f8572800
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -0,0 +1,315 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/netdevice.h>
+#include "lag.h"
+#include "lag_mp.h"
+#include "mlx5_core.h"
+#include "eswitch.h"
+#include "lib/mlx5.h"
+
+static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
+{
+	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+		return false;
+
+	return mlx5_esw_multipath_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+}
+
+static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
+{
+	return !!(ldev->flags & MLX5_LAG_FLAG_MULTIPATH);
+}
+
+bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
+{
+	struct mlx5_lag *ldev;
+	bool res;
+
+	ldev = mlx5_lag_dev_get(dev);
+	res  = ldev && __mlx5_lag_is_multipath(ldev);
+
+	return res;
+}
+
+/**
+ * Set lag port affinity
+ *
+ * @ldev: lag device
+ * @port:
+ *     0 - set normal affinity.
+ *     1 - set affinity to port 1.
+ *     2 - set affinity to port 2.
+ *
+ **/
+static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port)
+{
+	struct lag_tracker tracker;
+
+	if (!__mlx5_lag_is_multipath(ldev))
+		return;
+
+	switch (port) {
+	case 0:
+		tracker.netdev_state[0].tx_enabled = true;
+		tracker.netdev_state[1].tx_enabled = true;
+		tracker.netdev_state[0].link_up = true;
+		tracker.netdev_state[1].link_up = true;
+		break;
+	case 1:
+		tracker.netdev_state[0].tx_enabled = true;
+		tracker.netdev_state[0].link_up = true;
+		tracker.netdev_state[1].tx_enabled = false;
+		tracker.netdev_state[1].link_up = false;
+		break;
+	case 2:
+		tracker.netdev_state[0].tx_enabled = false;
+		tracker.netdev_state[0].link_up = false;
+		tracker.netdev_state[1].tx_enabled = true;
+		tracker.netdev_state[1].link_up = true;
+		break;
+	default:
+		mlx5_core_warn(ldev->pf[0].dev, "Invalid affinity port %d",
+			       port);
+		return;
+	}
+
+	if (tracker.netdev_state[0].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[0].dev->priv.events,
+					 MLX5_DEV_EVENT_PORT_AFFINITY,
+					 (void *)0);
+
+	if (tracker.netdev_state[1].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[1].dev->priv.events,
+					 MLX5_DEV_EVENT_PORT_AFFINITY,
+					 (void *)0);
+
+	mlx5_modify_lag(ldev, &tracker);
+}
+
+static void mlx5_lag_fib_event_flush(struct notifier_block *nb)
+{
+	struct lag_mp *mp = container_of(nb, struct lag_mp, fib_nb);
+	struct mlx5_lag *ldev = container_of(mp, struct mlx5_lag, lag_mp);
+
+	flush_workqueue(ldev->wq);
+}
+
+struct mlx5_fib_event_work {
+	struct work_struct work;
+	struct mlx5_lag *ldev;
+	unsigned long event;
+	union {
+		struct fib_entry_notifier_info fen_info;
+		struct fib_nh_notifier_info fnh_info;
+	};
+};
+
+static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
+				     unsigned long event,
+				     struct fib_info *fi)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+
+	/* Handle delete event */
+	if (event == FIB_EVENT_ENTRY_DEL) {
+		/* stop track */
+		if (mp->mfi == fi)
+			mp->mfi = NULL;
+		return;
+	}
+
+	/* Handle add/replace event */
+	if (fi->fib_nhs == 1) {
+		if (__mlx5_lag_is_active(ldev)) {
+			struct net_device *nh_dev = fi->fib_nh[0].nh_dev;
+			int i = mlx5_lag_dev_get_netdev_idx(ldev, nh_dev);
+
+			mlx5_lag_set_port_affinity(ldev, ++i);
+		}
+		return;
+	}
+
+	if (fi->fib_nhs != 2)
+		return;
+
+	/* Verify next hops are ports of the same hca */
+	if (!(fi->fib_nh[0].nh_dev == ldev->pf[0].netdev &&
+	      fi->fib_nh[1].nh_dev == ldev->pf[1].netdev) &&
+	    !(fi->fib_nh[0].nh_dev == ldev->pf[1].netdev &&
+	      fi->fib_nh[1].nh_dev == ldev->pf[0].netdev)) {
+		mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n");
+		return;
+	}
+
+	/* First time we see multipath route */
+	if (!mp->mfi && !__mlx5_lag_is_active(ldev)) {
+		struct lag_tracker tracker;
+
+		tracker = ldev->tracker;
+		mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH);
+	}
+
+	mlx5_lag_set_port_affinity(ldev, 0);
+	mp->mfi = fi;
+}
+
+static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
+				       unsigned long event,
+				       struct fib_nh *fib_nh,
+				       struct fib_info *fi)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+
+	/* Check the nh event is related to the route */
+	if (!mp->mfi || mp->mfi != fi)
+		return;
+
+	/* nh added/removed */
+	if (event == FIB_EVENT_NH_DEL) {
+		int i = mlx5_lag_dev_get_netdev_idx(ldev, fib_nh->nh_dev);
+
+		if (i >= 0) {
+			i = (i + 1) % 2 + 1; /* peer port */
+			mlx5_lag_set_port_affinity(ldev, i);
+		}
+	} else if (event == FIB_EVENT_NH_ADD &&
+		   fi->fib_nhs == 2) {
+		mlx5_lag_set_port_affinity(ldev, 0);
+	}
+}
+
+static void mlx5_lag_fib_update(struct work_struct *work)
+{
+	struct mlx5_fib_event_work *fib_work =
+		container_of(work, struct mlx5_fib_event_work, work);
+	struct mlx5_lag *ldev = fib_work->ldev;
+	struct fib_nh *fib_nh;
+
+	/* Protect internal structures from changes */
+	rtnl_lock();
+	switch (fib_work->event) {
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_APPEND: /* fall through */
+	case FIB_EVENT_ENTRY_ADD: /* fall through */
+	case FIB_EVENT_ENTRY_DEL:
+		mlx5_lag_fib_route_event(ldev, fib_work->event,
+					 fib_work->fen_info.fi);
+		fib_info_put(fib_work->fen_info.fi);
+		break;
+	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_DEL:
+		fib_nh = fib_work->fnh_info.fib_nh;
+		mlx5_lag_fib_nexthop_event(ldev,
+					   fib_work->event,
+					   fib_work->fnh_info.fib_nh,
+					   fib_nh->nh_parent);
+		fib_info_put(fib_work->fnh_info.fib_nh->nh_parent);
+		break;
+	}
+
+	rtnl_unlock();
+	kfree(fib_work);
+}
+
+static struct mlx5_fib_event_work *
+mlx5_lag_init_fib_work(struct mlx5_lag *ldev, unsigned long event)
+{
+	struct mlx5_fib_event_work *fib_work;
+
+	fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC);
+	if (WARN_ON(!fib_work))
+		return NULL;
+
+	INIT_WORK(&fib_work->work, mlx5_lag_fib_update);
+	fib_work->ldev = ldev;
+	fib_work->event = event;
+
+	return fib_work;
+}
+
+static int mlx5_lag_fib_event(struct notifier_block *nb,
+			      unsigned long event,
+			      void *ptr)
+{
+	struct lag_mp *mp = container_of(nb, struct lag_mp, fib_nb);
+	struct mlx5_lag *ldev = container_of(mp, struct mlx5_lag, lag_mp);
+	struct fib_notifier_info *info = ptr;
+	struct mlx5_fib_event_work *fib_work;
+	struct fib_entry_notifier_info *fen_info;
+	struct fib_nh_notifier_info *fnh_info;
+	struct fib_info *fi;
+
+	if (info->family != AF_INET)
+		return NOTIFY_DONE;
+
+	if (!mlx5_lag_multipath_check_prereq(ldev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case FIB_EVENT_ENTRY_REPLACE: /* fall through */
+	case FIB_EVENT_ENTRY_APPEND: /* fall through */
+	case FIB_EVENT_ENTRY_ADD: /* fall through */
+	case FIB_EVENT_ENTRY_DEL:
+		fen_info = container_of(info, struct fib_entry_notifier_info,
+					info);
+		fi = fen_info->fi;
+		if (fi->fib_dev != ldev->pf[0].netdev &&
+		    fi->fib_dev != ldev->pf[1].netdev) {
+			return NOTIFY_DONE;
+		}
+		fib_work = mlx5_lag_init_fib_work(ldev, event);
+		if (!fib_work)
+			return NOTIFY_DONE;
+		fib_work->fen_info = *fen_info;
+		/* Take reference on fib_info to prevent it from being
+		 * freed while work is queued. Release it afterwards.
+		 */
+		fib_info_hold(fib_work->fen_info.fi);
+		break;
+	case FIB_EVENT_NH_ADD: /* fall through */
+	case FIB_EVENT_NH_DEL:
+		fnh_info = container_of(info, struct fib_nh_notifier_info,
+					info);
+		fib_work = mlx5_lag_init_fib_work(ldev, event);
+		if (!fib_work)
+			return NOTIFY_DONE;
+		fib_work->fnh_info = *fnh_info;
+		fib_info_hold(fib_work->fnh_info.fib_nh->nh_parent);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	queue_work(ldev->wq, &fib_work->work);
+
+	return NOTIFY_DONE;
+}
+
+int mlx5_lag_mp_init(struct mlx5_lag *ldev)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+	int err;
+
+	if (mp->fib_nb.notifier_call)
+		return 0;
+
+	mp->fib_nb.notifier_call = mlx5_lag_fib_event;
+	err = register_fib_notifier(&mp->fib_nb,
+				    mlx5_lag_fib_event_flush);
+	if (err)
+		mp->fib_nb.notifier_call = NULL;
+
+	return err;
+}
+
+void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev)
+{
+	struct lag_mp *mp = &ldev->lag_mp;
+
+	if (!mp->fib_nb.notifier_call)
+		return;
+
+	unregister_fib_notifier(&mp->fib_nb);
+	mp->fib_nb.notifier_call = NULL;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
new file mode 100644
index 000000000000..6d14b1100be9
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_LAG_MP_H__
+#define __MLX5_LAG_MP_H__
+
+#include "lag.h"
+#include "mlx5_core.h"
+
+struct lag_mp {
+	struct notifier_block     fib_nb;
+	struct fib_info           *mfi; /* used in tracking fib events */
+};
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+int mlx5_lag_mp_init(struct mlx5_lag *ldev);
+void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev);
+
+#else /* CONFIG_MLX5_ESWITCH */
+
+static inline int mlx5_lag_mp_init(struct mlx5_lag *ldev) { return 0; }
+static inline void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev) {}
+
+#endif /* CONFIG_MLX5_ESWITCH */
+#endif /* __MLX5_LAG_MP_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 0d90b1b4a3d3..ca0ee9916e9e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -33,6 +33,7 @@
 #include <linux/clocksource.h>
 #include <linux/highmem.h>
 #include <rdma/mlx5-abi.h>
+#include "lib/eq.h"
 #include "en.h"
 #include "clock.h"
 
@@ -71,7 +72,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
 						  clock);
 
-	return mlx5_read_internal_timer(mdev) & cc->mask;
+	return mlx5_read_internal_timer(mdev, NULL) & cc->mask;
 }
 
 static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
@@ -155,15 +156,19 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
+static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
+			     struct ptp_system_timestamp *sts)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock,
 						ptp_info);
-	u64 ns;
+	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
+						  clock);
 	unsigned long flags;
+	u64 cycles, ns;
 
 	write_seqlock_irqsave(&clock->lock, flags);
-	ns = timecounter_read(&clock->tc);
+	cycles = mlx5_read_internal_timer(mdev, sts);
+	ns = timecounter_cyc2time(&clock->tc, cycles);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 	*ts = ns_to_timespec64(ns);
@@ -306,7 +311,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		ts.tv_sec = rq->perout.start.sec;
 		ts.tv_nsec = rq->perout.start.nsec;
 		ns = timespec64_to_ns(&ts);
-		cycles_now = mlx5_read_internal_timer(mdev);
+		cycles_now = mlx5_read_internal_timer(mdev, NULL);
 		write_seqlock_irqsave(&clock->lock, flags);
 		nsec_now = timecounter_cyc2time(&clock->tc, cycles_now);
 		nsec_delta = ns - nsec_now;
@@ -383,7 +388,7 @@ static const struct ptp_clock_info mlx5_ptp_clock_info = {
 	.pps		= 0,
 	.adjfreq	= mlx5_ptp_adjfreq,
 	.adjtime	= mlx5_ptp_adjtime,
-	.gettime64	= mlx5_ptp_gettime,
+	.gettimex64	= mlx5_ptp_gettimex,
 	.settime64	= mlx5_ptp_settime,
 	.enable		= NULL,
 	.verify		= NULL,
@@ -439,16 +444,17 @@ static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
 	clock->pps_info.pin_caps[7] = MLX5_GET(mtpps_reg, out, cap_pin_7_mode);
 }
 
-void mlx5_pps_event(struct mlx5_core_dev *mdev,
-		    struct mlx5_eqe *eqe)
+static int mlx5_pps_event(struct notifier_block *nb,
+			  unsigned long type, void *data)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+	struct mlx5_core_dev *mdev = clock->mdev;
 	struct ptp_clock_event ptp_event;
-	struct timespec64 ts;
-	u64 nsec_now, nsec_delta;
 	u64 cycles_now, cycles_delta;
+	u64 nsec_now, nsec_delta, ns;
+	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
-	s64 ns;
+	struct timespec64 ts;
 	unsigned long flags;
 
 	switch (clock->ptp_info.pin_config[pin].func) {
@@ -463,11 +469,12 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 		} else {
 			ptp_event.type = PTP_CLOCK_EXTTS;
 		}
+		/* TODOL clock->ptp can be NULL if ptp_clock_register failes */
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
-		mlx5_ptp_gettime(&clock->ptp_info, &ts);
-		cycles_now = mlx5_read_internal_timer(mdev);
+		mlx5_ptp_gettimex(&clock->ptp_info, &ts, NULL);
+		cycles_now = mlx5_read_internal_timer(mdev, NULL);
 		ts.tv_sec += 1;
 		ts.tv_nsec = 0;
 		ns = timespec64_to_ns(&ts);
@@ -481,8 +488,11 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
 		write_sequnlock_irqrestore(&clock->lock, flags);
 		break;
 	default:
-		mlx5_core_err(mdev, " Unhandled event\n");
+		mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
+			      clock->ptp_info.pin_config[pin].func);
 	}
+
+	return NOTIFY_OK;
 }
 
 void mlx5_init_clock(struct mlx5_core_dev *mdev)
@@ -511,14 +521,14 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 
 	/* Calculate period in seconds to call the overflow watchdog - to make
-	 * sure counter is checked at least once every wrap around.
+	 * sure counter is checked at least twice every wrap around.
 	 * The period is calculated as the minimum between max HW cycles count
 	 * (The clock source mask) and max amount of cycles that can be
 	 * multiplied by clock multiplier where the result doesn't exceed
 	 * 64bits.
 	 */
 	overflow_cycles = div64_u64(~0ULL >> 1, clock->cycles.mult);
-	overflow_cycles = min(overflow_cycles, clock->cycles.mask >> 1);
+	overflow_cycles = min(overflow_cycles, div_u64(clock->cycles.mask, 3));
 
 	ns = cyclecounter_cyc2ns(&clock->cycles, overflow_cycles,
 				 frac, &frac);
@@ -567,6 +577,9 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 			       PTR_ERR(clock->ptp));
 		clock->ptp = NULL;
 	}
+
+	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
 }
 
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
@@ -576,6 +589,7 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
 		return;
 
+	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
 		clock->ptp = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index 263cb6e2aeee..31600924bdc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -36,7 +36,6 @@
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
@@ -60,8 +59,6 @@ static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 #else
 static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
-static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
-
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
 	return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
new file mode 100644
index 000000000000..bced2efe9bef
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.c
@@ -0,0 +1,255 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#include <linux/mlx5/vport.h>
+#include "lib/devcom.h"
+
+static LIST_HEAD(devcom_list);
+
+#define devcom_for_each_component(priv, comp, iter) \
+	for (iter = 0; \
+	     comp = &(priv)->components[iter], iter < MLX5_DEVCOM_NUM_COMPONENTS; \
+	     iter++)
+
+struct mlx5_devcom_component {
+	struct {
+		void *data;
+	} device[MLX5_MAX_PORTS];
+
+	mlx5_devcom_event_handler_t handler;
+	struct rw_semaphore sem;
+	bool paired;
+};
+
+struct mlx5_devcom_list {
+	struct list_head list;
+
+	struct mlx5_devcom_component components[MLX5_DEVCOM_NUM_COMPONENTS];
+	struct mlx5_core_dev *devs[MLX5_MAX_PORTS];
+};
+
+struct mlx5_devcom {
+	struct mlx5_devcom_list *priv;
+	int idx;
+};
+
+static struct mlx5_devcom_list *mlx5_devcom_list_alloc(void)
+{
+	struct mlx5_devcom_component *comp;
+	struct mlx5_devcom_list *priv;
+	int i;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return NULL;
+
+	devcom_for_each_component(priv, comp, i)
+		init_rwsem(&comp->sem);
+
+	return priv;
+}
+
+static struct mlx5_devcom *mlx5_devcom_alloc(struct mlx5_devcom_list *priv,
+					     u8 idx)
+{
+	struct mlx5_devcom *devcom;
+
+	devcom = kzalloc(sizeof(*devcom), GFP_KERNEL);
+	if (!devcom)
+		return NULL;
+
+	devcom->priv = priv;
+	devcom->idx = idx;
+	return devcom;
+}
+
+/* Must be called with intf_mutex held */
+struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev)
+{
+	struct mlx5_devcom_list *priv = NULL, *iter;
+	struct mlx5_devcom *devcom = NULL;
+	bool new_priv = false;
+	u64 sguid0, sguid1;
+	int idx, i;
+
+	if (!mlx5_core_is_pf(dev))
+		return NULL;
+
+	sguid0 = mlx5_query_nic_system_image_guid(dev);
+	list_for_each_entry(iter, &devcom_list, list) {
+		struct mlx5_core_dev *tmp_dev = NULL;
+
+		idx = -1;
+		for (i = 0; i < MLX5_MAX_PORTS; i++) {
+			if (iter->devs[i])
+				tmp_dev = iter->devs[i];
+			else
+				idx = i;
+		}
+
+		if (idx == -1)
+			continue;
+
+		sguid1 = mlx5_query_nic_system_image_guid(tmp_dev);
+		if (sguid0 != sguid1)
+			continue;
+
+		priv = iter;
+		break;
+	}
+
+	if (!priv) {
+		priv = mlx5_devcom_list_alloc();
+		if (!priv)
+			return ERR_PTR(-ENOMEM);
+
+		idx = 0;
+		new_priv = true;
+	}
+
+	priv->devs[idx] = dev;
+	devcom = mlx5_devcom_alloc(priv, idx);
+	if (!devcom) {
+		kfree(priv);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	if (new_priv)
+		list_add(&priv->list, &devcom_list);
+
+	return devcom;
+}
+
+/* Must be called with intf_mutex held */
+void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom)
+{
+	struct mlx5_devcom_list *priv;
+	int i;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+
+	priv = devcom->priv;
+	priv->devs[devcom->idx] = NULL;
+
+	kfree(devcom);
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (priv->devs[i])
+			break;
+
+	if (i != MLX5_MAX_PORTS)
+		return;
+
+	list_del(&priv->list);
+	kfree(priv);
+}
+
+void mlx5_devcom_register_component(struct mlx5_devcom *devcom,
+				    enum mlx5_devcom_components id,
+				    mlx5_devcom_event_handler_t handler,
+				    void *data)
+{
+	struct mlx5_devcom_component *comp;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+
+	WARN_ON(!data);
+
+	comp = &devcom->priv->components[id];
+	down_write(&comp->sem);
+	comp->handler = handler;
+	comp->device[devcom->idx].data = data;
+	up_write(&comp->sem);
+}
+
+void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,
+				      enum mlx5_devcom_components id)
+{
+	struct mlx5_devcom_component *comp;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return;
+
+	comp = &devcom->priv->components[id];
+	down_write(&comp->sem);
+	comp->device[devcom->idx].data = NULL;
+	up_write(&comp->sem);
+}
+
+int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id,
+			   int event,
+			   void *event_data)
+{
+	struct mlx5_devcom_component *comp;
+	int err = -ENODEV, i;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return err;
+
+	comp = &devcom->priv->components[id];
+	down_write(&comp->sem);
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (i != devcom->idx && comp->device[i].data) {
+			err = comp->handler(event, comp->device[i].data,
+					    event_data);
+			break;
+		}
+
+	up_write(&comp->sem);
+	return err;
+}
+
+void mlx5_devcom_set_paired(struct mlx5_devcom *devcom,
+			    enum mlx5_devcom_components id,
+			    bool paired)
+{
+	struct mlx5_devcom_component *comp;
+
+	comp = &devcom->priv->components[id];
+	WARN_ON(!rwsem_is_locked(&comp->sem));
+
+	comp->paired = paired;
+}
+
+bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id)
+{
+	if (IS_ERR_OR_NULL(devcom))
+		return false;
+
+	return devcom->priv->components[id].paired;
+}
+
+void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom,
+				enum mlx5_devcom_components id)
+{
+	struct mlx5_devcom_component *comp;
+	int i;
+
+	if (IS_ERR_OR_NULL(devcom))
+		return NULL;
+
+	comp = &devcom->priv->components[id];
+	down_read(&comp->sem);
+	if (!comp->paired) {
+		up_read(&comp->sem);
+		return NULL;
+	}
+
+	for (i = 0; i < MLX5_MAX_PORTS; i++)
+		if (i != devcom->idx)
+			break;
+
+	return comp->device[i].data;
+}
+
+void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom,
+				   enum mlx5_devcom_components id)
+{
+	struct mlx5_devcom_component *comp = &devcom->priv->components[id];
+
+	up_read(&comp->sem);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
new file mode 100644
index 000000000000..939d5bf1581b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#ifndef __LIB_MLX5_DEVCOM_H__
+#define __LIB_MLX5_DEVCOM_H__
+
+#include <linux/mlx5/driver.h>
+
+enum mlx5_devcom_components {
+	MLX5_DEVCOM_ESW_OFFLOADS,
+
+	MLX5_DEVCOM_NUM_COMPONENTS,
+};
+
+typedef int (*mlx5_devcom_event_handler_t)(int event,
+					   void *my_data,
+					   void *event_data);
+
+struct mlx5_devcom *mlx5_devcom_register_device(struct mlx5_core_dev *dev);
+void mlx5_devcom_unregister_device(struct mlx5_devcom *devcom);
+
+void mlx5_devcom_register_component(struct mlx5_devcom *devcom,
+				    enum mlx5_devcom_components id,
+				    mlx5_devcom_event_handler_t handler,
+				    void *data);
+void mlx5_devcom_unregister_component(struct mlx5_devcom *devcom,
+				      enum mlx5_devcom_components id);
+
+int mlx5_devcom_send_event(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id,
+			   int event,
+			   void *event_data);
+
+void mlx5_devcom_set_paired(struct mlx5_devcom *devcom,
+			    enum mlx5_devcom_components id,
+			    bool paired);
+bool mlx5_devcom_is_paired(struct mlx5_devcom *devcom,
+			   enum mlx5_devcom_components id);
+
+void *mlx5_devcom_get_peer_data(struct mlx5_devcom *devcom,
+				enum mlx5_devcom_components id);
+void mlx5_devcom_release_peer_data(struct mlx5_devcom *devcom,
+				   enum mlx5_devcom_components id);
+
+#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
new file mode 100644
index 000000000000..c0fb6d72b695
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -0,0 +1,98 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies */
+
+#ifndef __LIB_MLX5_EQ_H__
+#define __LIB_MLX5_EQ_H__
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/eq.h>
+#include <linux/mlx5/cq.h>
+
+#define MLX5_MAX_IRQ_NAME   (32)
+#define MLX5_EQE_SIZE       (sizeof(struct mlx5_eqe))
+
+struct mlx5_eq_tasklet {
+	struct list_head      list;
+	struct list_head      process_list;
+	struct tasklet_struct task;
+	spinlock_t            lock; /* lock completion tasklet list */
+};
+
+struct mlx5_cq_table {
+	spinlock_t              lock;	/* protect radix tree */
+	struct radix_tree_root  tree;
+};
+
+struct mlx5_eq {
+	struct mlx5_core_dev    *dev;
+	struct mlx5_cq_table    cq_table;
+	__be32 __iomem	        *doorbell;
+	u32                     cons_index;
+	struct mlx5_frag_buf    buf;
+	int                     size;
+	unsigned int            vecidx;
+	unsigned int            irqn;
+	u8                      eqn;
+	int                     nent;
+	struct mlx5_rsc_debug   *dbg;
+};
+
+struct mlx5_eq_comp {
+	struct mlx5_eq          core; /* Must be first */
+	struct mlx5_eq_tasklet  tasklet_ctx;
+	struct list_head        list;
+};
+
+static inline struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
+{
+	return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
+}
+
+static inline struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
+{
+	struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
+
+	return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
+}
+
+static inline void eq_update_ci(struct mlx5_eq *eq, int arm)
+{
+	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
+	u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
+
+	__raw_writel((__force u32)cpu_to_be32(val), addr);
+	/* We still want ordering, just not swabbing, so add a barrier */
+	mb();
+}
+
+int mlx5_eq_table_init(struct mlx5_core_dev *dev);
+void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev);
+int mlx5_eq_table_create(struct mlx5_core_dev *dev);
+void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
+
+int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn);
+struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
+void mlx5_cq_tasklet_cb(unsigned long data);
+struct cpumask *mlx5_eq_comp_cpumask(struct mlx5_core_dev *dev, int ix);
+
+u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq);
+void mlx5_eq_synchronize_async_irq(struct mlx5_core_dev *dev);
+void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev);
+
+int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
+int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
+void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
+
+/* This function should only be called after mlx5_cmd_force_teardown_hca */
+void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
+
+#ifdef CONFIG_RFS_ACCEL
+struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
+#endif
+
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 7550b1cc8c6a..397a2847867a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -33,6 +33,8 @@
 #ifndef __LIB_MLX5_H__
 #define __LIB_MLX5_H__
 
+#include "mlx5_core.h"
+
 void mlx5_init_reserved_gids(struct mlx5_core_dev *dev);
 void mlx5_cleanup_reserved_gids(struct mlx5_core_dev *dev);
 int  mlx5_core_reserve_gids(struct mlx5_core_dev *dev, unsigned int count);
@@ -40,4 +42,38 @@ void mlx5_core_unreserve_gids(struct mlx5_core_dev *dev, unsigned int count);
 int  mlx5_core_reserved_gid_alloc(struct mlx5_core_dev *dev, int *gid_index);
 void mlx5_core_reserved_gid_free(struct mlx5_core_dev *dev, int gid_index);
 
+/* TODO move to lib/events.h */
+
+#define PORT_MODULE_EVENT_MODULE_STATUS_MASK 0xF
+#define PORT_MODULE_EVENT_ERROR_TYPE_MASK    0xF
+
+enum port_module_event_status_type {
+	MLX5_MODULE_STATUS_PLUGGED   = 0x1,
+	MLX5_MODULE_STATUS_UNPLUGGED = 0x2,
+	MLX5_MODULE_STATUS_ERROR     = 0x3,
+	MLX5_MODULE_STATUS_DISABLED  = 0x4,
+	MLX5_MODULE_STATUS_NUM,
+};
+
+enum  port_module_event_error_type {
+	MLX5_MODULE_EVENT_ERROR_POWER_BUDGET_EXCEEDED    = 0x0,
+	MLX5_MODULE_EVENT_ERROR_LONG_RANGE_FOR_NON_MLNX  = 0x1,
+	MLX5_MODULE_EVENT_ERROR_BUS_STUCK                = 0x2,
+	MLX5_MODULE_EVENT_ERROR_NO_EEPROM_RETRY_TIMEOUT  = 0x3,
+	MLX5_MODULE_EVENT_ERROR_ENFORCE_PART_NUMBER_LIST = 0x4,
+	MLX5_MODULE_EVENT_ERROR_UNKNOWN_IDENTIFIER       = 0x5,
+	MLX5_MODULE_EVENT_ERROR_HIGH_TEMPERATURE         = 0x6,
+	MLX5_MODULE_EVENT_ERROR_BAD_CABLE                = 0x7,
+	MLX5_MODULE_EVENT_ERROR_PCIE_POWER_SLOT_EXCEEDED = 0xc,
+	MLX5_MODULE_EVENT_ERROR_NUM,
+};
+
+struct mlx5_pme_stats {
+	u64 status_counters[MLX5_MODULE_STATUS_NUM];
+	u64 error_counters[MLX5_MODULE_EVENT_ERROR_NUM];
+};
+
+void mlx5_get_pme_stats(struct mlx5_core_dev *dev, struct mlx5_pme_stats *stats);
+int mlx5_notifier_call_chain(struct mlx5_events *events, unsigned int event, void *data);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
index 98359559c77e..a71d5b9c7ab2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c
@@ -108,8 +108,7 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev)
 
 	mutex_init(&mpfs->lock);
 	mpfs->size   = l2table_size;
-	mpfs->bitmap = kcalloc(BITS_TO_LONGS(l2table_size),
-			       sizeof(uintptr_t), GFP_KERNEL);
+	mpfs->bitmap = bitmap_zalloc(l2table_size, GFP_KERNEL);
 	if (!mpfs->bitmap) {
 		kfree(mpfs);
 		return -ENOMEM;
@@ -127,7 +126,7 @@ void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev)
 		return;
 
 	WARN_ON(!hlist_empty(mpfs->hash));
-	kfree(mpfs->bitmap);
+	bitmap_free(mpfs->bitmap);
 	kfree(mpfs);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
new file mode 100644
index 000000000000..40f4a19b1ce1
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.c
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/port.h>
+#include <linux/mlx5/cmd.h>
+#include "mlx5_core.h"
+#include "lib/port_tun.h"
+
+struct mlx5_port_tun_entropy_flags {
+	bool force_supported, force_enabled;
+	bool calc_supported, calc_enabled;
+	bool gre_calc_supported, gre_calc_enabled;
+};
+
+static void mlx5_query_port_tun_entropy(struct mlx5_core_dev *mdev,
+					struct mlx5_port_tun_entropy_flags *entropy_flags)
+{
+	u32 out[MLX5_ST_SZ_DW(pcmr_reg)];
+	/* Default values for FW which do not support MLX5_REG_PCMR */
+	entropy_flags->force_supported = false;
+	entropy_flags->calc_supported = false;
+	entropy_flags->gre_calc_supported = false;
+	entropy_flags->force_enabled = false;
+	entropy_flags->calc_enabled = true;
+	entropy_flags->gre_calc_enabled = true;
+
+	if (!MLX5_CAP_GEN(mdev, ports_check))
+		return;
+
+	if (mlx5_query_ports_check(mdev, out, sizeof(out)))
+		return;
+
+	entropy_flags->force_supported = !!(MLX5_GET(pcmr_reg, out, entropy_force_cap));
+	entropy_flags->calc_supported = !!(MLX5_GET(pcmr_reg, out, entropy_calc_cap));
+	entropy_flags->gre_calc_supported = !!(MLX5_GET(pcmr_reg, out, entropy_gre_calc_cap));
+	entropy_flags->force_enabled = !!(MLX5_GET(pcmr_reg, out, entropy_force));
+	entropy_flags->calc_enabled = !!(MLX5_GET(pcmr_reg, out, entropy_calc));
+	entropy_flags->gre_calc_enabled = !!(MLX5_GET(pcmr_reg, out, entropy_gre_calc));
+}
+
+static int mlx5_set_port_tun_entropy_calc(struct mlx5_core_dev *mdev, u8 enable,
+					  u8 force)
+{
+	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
+	int err;
+
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
+	MLX5_SET(pcmr_reg, in, local_port, 1);
+	MLX5_SET(pcmr_reg, in, entropy_force, force);
+	MLX5_SET(pcmr_reg, in, entropy_calc, enable);
+	return mlx5_set_ports_check(mdev, in, sizeof(in));
+}
+
+static int mlx5_set_port_gre_tun_entropy_calc(struct mlx5_core_dev *mdev,
+					      u8 enable, u8 force)
+{
+	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
+	int err;
+
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
+	MLX5_SET(pcmr_reg, in, local_port, 1);
+	MLX5_SET(pcmr_reg, in, entropy_force, force);
+	MLX5_SET(pcmr_reg, in, entropy_gre_calc, enable);
+	return mlx5_set_ports_check(mdev, in, sizeof(in));
+}
+
+void mlx5_init_port_tun_entropy(struct mlx5_tun_entropy *tun_entropy,
+				struct mlx5_core_dev *mdev)
+{
+	struct mlx5_port_tun_entropy_flags entropy_flags;
+
+	tun_entropy->mdev = mdev;
+	mutex_init(&tun_entropy->lock);
+	mlx5_query_port_tun_entropy(mdev, &entropy_flags);
+	tun_entropy->num_enabling_entries = 0;
+	tun_entropy->num_disabling_entries = 0;
+	tun_entropy->enabled = entropy_flags.calc_enabled;
+	tun_entropy->enabled =
+		(entropy_flags.calc_supported) ?
+		entropy_flags.calc_enabled : true;
+}
+
+static int mlx5_set_entropy(struct mlx5_tun_entropy *tun_entropy,
+			    int reformat_type, bool enable)
+{
+	struct mlx5_port_tun_entropy_flags entropy_flags;
+	int err;
+
+	mlx5_query_port_tun_entropy(tun_entropy->mdev, &entropy_flags);
+	/* Tunnel entropy calculation may be controlled either on port basis
+	 * for all tunneling protocols or specifically for GRE protocol.
+	 * Prioritize GRE protocol control (if capable) over global port
+	 * configuration.
+	 */
+	if (entropy_flags.gre_calc_supported &&
+	    reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE) {
+		/* Other applications may change the global FW entropy
+		 * calculations settings. Check that the current entropy value
+		 * is the negative of the updated value.
+		 */
+		if (entropy_flags.force_enabled &&
+		    enable == entropy_flags.gre_calc_enabled) {
+			mlx5_core_warn(tun_entropy->mdev,
+				       "Unexpected GRE entropy calc setting - expected %d",
+				       !entropy_flags.gre_calc_enabled);
+			return -EOPNOTSUPP;
+		}
+		err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev, enable,
+							 entropy_flags.force_supported);
+		if (err)
+			return err;
+		/* if we turn on the entropy we don't need to force it anymore */
+		if (entropy_flags.force_supported && enable) {
+			err = mlx5_set_port_gre_tun_entropy_calc(tun_entropy->mdev, 1, 0);
+			if (err)
+				return err;
+		}
+	} else if (entropy_flags.calc_supported) {
+		/* Other applications may change the global FW entropy
+		 * calculations settings. Check that the current entropy value
+		 * is the negative of the updated value.
+		 */
+		if (entropy_flags.force_enabled &&
+		    enable == entropy_flags.calc_enabled) {
+			mlx5_core_warn(tun_entropy->mdev,
+				       "Unexpected entropy calc setting - expected %d",
+				       !entropy_flags.calc_enabled);
+			return -EOPNOTSUPP;
+		}
+		/* GRE requires disabling entropy calculation. if there are
+		 * enabling entries (i.e VXLAN) we cannot turn it off for them,
+		 * thus fail.
+		 */
+		if (tun_entropy->num_enabling_entries)
+			return -EOPNOTSUPP;
+		err = mlx5_set_port_tun_entropy_calc(tun_entropy->mdev, enable,
+						     entropy_flags.force_supported);
+		if (err)
+			return err;
+		tun_entropy->enabled = enable;
+		/* if we turn on the entropy we don't need to force it anymore */
+		if (entropy_flags.force_supported && enable) {
+			err = mlx5_set_port_tun_entropy_calc(tun_entropy->mdev, 1, 0);
+			if (err)
+				return err;
+		}
+	}
+
+	return 0;
+}
+
+/* the function manages the refcount for enabling/disabling tunnel types.
+ * the return value indicates if the inc is successful or not, depending on
+ * entropy capabilities and configuration.
+ */
+int mlx5_tun_entropy_refcount_inc(struct mlx5_tun_entropy *tun_entropy,
+				  int reformat_type)
+{
+	/* the default is error for unknown (non VXLAN/GRE tunnel types) */
+	int err = -EOPNOTSUPP;
+
+	mutex_lock(&tun_entropy->lock);
+	if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN &&
+	    tun_entropy->enabled) {
+		/* in case entropy calculation is enabled for all tunneling
+		 * types, it is ok for VXLAN, so approve.
+		 * otherwise keep the error default.
+		 */
+		tun_entropy->num_enabling_entries++;
+		err = 0;
+	} else if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE) {
+		/* turn off the entropy only for the first GRE rule.
+		 * for the next rules the entropy was already disabled
+		 * successfully.
+		 */
+		if (tun_entropy->num_disabling_entries == 0)
+			err = mlx5_set_entropy(tun_entropy, reformat_type, 0);
+		else
+			err = 0;
+		if (!err)
+			tun_entropy->num_disabling_entries++;
+	}
+	mutex_unlock(&tun_entropy->lock);
+
+	return err;
+}
+
+void mlx5_tun_entropy_refcount_dec(struct mlx5_tun_entropy *tun_entropy,
+				   int reformat_type)
+{
+	mutex_lock(&tun_entropy->lock);
+	if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_VXLAN)
+		tun_entropy->num_enabling_entries--;
+	else if (reformat_type == MLX5_REFORMAT_TYPE_L2_TO_NVGRE &&
+		 --tun_entropy->num_disabling_entries == 0)
+		mlx5_set_entropy(tun_entropy, reformat_type, 1);
+	mutex_unlock(&tun_entropy->lock);
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.h
new file mode 100644
index 000000000000..54c42a88705e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/port_tun.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2019 Mellanox Technologies. */
+
+#ifndef __MLX5_PORT_TUN_H__
+#define __MLX5_PORT_TUN_H__
+
+#include <linux/mlx5/driver.h>
+
+struct mlx5_tun_entropy {
+	struct mlx5_core_dev *mdev;
+	u32 num_enabling_entries;
+	u32 num_disabling_entries;
+	u8  enabled;
+	struct mutex lock;	/* lock the entropy fields */
+};
+
+void mlx5_init_port_tun_entropy(struct mlx5_tun_entropy *tun_entropy,
+				struct mlx5_core_dev *mdev);
+int mlx5_tun_entropy_refcount_inc(struct mlx5_tun_entropy *tun_entropy,
+				  int reformat_type);
+void mlx5_tun_entropy_refcount_dec(struct mlx5_tun_entropy *tun_entropy,
+				   int reformat_type);
+
+#endif /* __MLX5_PORT_TUN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c
deleted file mode 100644
index 3a3b0005fd2b..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c
+++ /dev/null
@@ -1,75 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
-#include "mlx5_core.h"
-
-int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
-		      u16 opmod, u8 port)
-{
-	int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out);
-	int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in);
-	int err = -ENOMEM;
-	void *data;
-	void *resp;
-	u32 *out;
-	u32 *in;
-
-	in = kzalloc(inlen, GFP_KERNEL);
-	out = kzalloc(outlen, GFP_KERNEL);
-	if (!in || !out)
-		goto out;
-
-	MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC);
-	MLX5_SET(mad_ifc_in, in, op_mod, opmod);
-	MLX5_SET(mad_ifc_in, in, port, port);
-
-	data = MLX5_ADDR_OF(mad_ifc_in, in, mad);
-	memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad));
-
-	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
-	if (err)
-		goto out;
-
-	resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet);
-	memcpy(outb, resp,
-	       MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet));
-
-out:
-	kfree(out);
-	kfree(in);
-	return err;
-}
-EXPORT_SYMBOL_GPL(mlx5_core_mad_ifc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 28132c7dc05f..76716419370d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -43,7 +43,6 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/qp.h>
-#include <linux/mlx5/srq.h>
 #include <linux/debugfs.h>
 #include <linux/kmod.h>
 #include <linux/mlx5/mlx5_ifc.h>
@@ -53,6 +52,7 @@
 #endif
 #include <net/devlink.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 #include "fs_core.h"
 #include "lib/mpfs.h"
 #include "eswitch.h"
@@ -63,7 +63,9 @@
 #include "accel/tls.h"
 #include "lib/clock.h"
 #include "lib/vxlan.h"
+#include "lib/devcom.h"
 #include "diag/fw_tracer.h"
+#include "ecpf.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -162,26 +164,6 @@ static struct mlx5_profile profile[] = {
 			.size	= 8,
 			.limit	= 4
 		},
-		.mr_cache[16]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[17]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[18]	= {
-			.size	= 8,
-			.limit	= 4
-		},
-		.mr_cache[19]	= {
-			.size	= 4,
-			.limit	= 2
-		},
-		.mr_cache[20]	= {
-			.size	= 4,
-			.limit	= 2
-		},
 	},
 };
 
@@ -319,51 +301,6 @@ static void release_bar(struct pci_dev *pdev)
 	pci_release_regions(pdev);
 }
 
-static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-	struct mlx5_eq_table *table = &priv->eq_table;
-	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
-		      MLX5_CAP_GEN(dev, max_num_eqs) :
-		      1 << MLX5_CAP_GEN(dev, log_max_eq);
-	int nvec;
-	int err;
-
-	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
-	       MLX5_EQ_VEC_COMP_BASE;
-	nvec = min_t(int, nvec, num_eqs);
-	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
-		return -ENOMEM;
-
-	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
-	if (!priv->irq_info)
-		return -ENOMEM;
-
-	nvec = pci_alloc_irq_vectors(dev->pdev,
-			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
-			PCI_IRQ_MSIX);
-	if (nvec < 0) {
-		err = nvec;
-		goto err_free_irq_info;
-	}
-
-	table->num_comp_vectors = nvec - MLX5_EQ_VEC_COMP_BASE;
-
-	return 0;
-
-err_free_irq_info:
-	kfree(priv->irq_info);
-	return err;
-}
-
-static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev)
-{
-	struct mlx5_priv *priv = &dev->priv;
-
-	pci_free_irq_vectors(dev->pdev);
-	kfree(priv->irq_info);
-}
-
 struct mlx5_reg_host_endianness {
 	u8	he;
 	u8      rsvd[15];
@@ -503,6 +440,58 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int handle_hca_cap_odp(struct mlx5_core_dev *dev)
+{
+	void *set_hca_cap;
+	void *set_ctx;
+	int set_sz;
+	bool do_set = false;
+	int err;
+
+	if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) ||
+	    !MLX5_CAP_GEN(dev, pg))
+		return 0;
+
+	err = mlx5_core_get_caps(dev, MLX5_CAP_ODP);
+	if (err)
+		return err;
+
+	set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in);
+	set_ctx = kzalloc(set_sz, GFP_KERNEL);
+	if (!set_ctx)
+		return -ENOMEM;
+
+	set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability);
+	memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP],
+	       MLX5_ST_SZ_BYTES(odp_cap));
+
+#define ODP_CAP_SET_MAX(dev, field)                                            \
+	do {                                                                   \
+		u32 _res = MLX5_CAP_ODP_MAX(dev, field);                       \
+		if (_res) {                                                    \
+			do_set = true;                                         \
+			MLX5_SET(odp_cap, set_hca_cap, field, _res);           \
+		}                                                              \
+	} while (0)
+
+	ODP_CAP_SET_MAX(dev, ud_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, rc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.srq_receive);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.send);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.receive);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.write);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.read);
+	ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic);
+
+	if (do_set)
+		err = set_caps(dev, set_ctx, set_sz,
+			       MLX5_SET_HCA_CAP_OP_MOD_ODP);
+
+	kfree(set_ctx);
+
+	return err;
+}
+
 static int handle_hca_cap(struct mlx5_core_dev *dev)
 {
 	void *set_ctx = NULL;
@@ -576,6 +565,33 @@ query_ex:
 	return err;
 }
 
+static int set_hca_cap(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *pdev = dev->pdev;
+	int err;
+
+	err = handle_hca_cap(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap failed\n");
+		goto out;
+	}
+
+	err = handle_hca_cap_atomic(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
+		goto out;
+	}
+
+	err = handle_hca_cap_odp(dev);
+	if (err) {
+		dev_err(&pdev->dev, "handle_hca_cap_odp failed\n");
+		goto out;
+	}
+
+out:
+	return err;
+}
+
 static int set_hca_ctrl(struct mlx5_core_dev *dev)
 {
 	struct mlx5_reg_host_endianness he_in;
@@ -611,6 +627,8 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id)
 
 	MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA);
 	MLX5_SET(enable_hca_in, in, function_id, func_id);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
+		 dev->caps.embedded_cpu);
 	return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
 }
 
@@ -621,191 +639,29 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id)
 
 	MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA);
 	MLX5_SET(disable_hca_in, in, function_id, func_id);
+	MLX5_SET(enable_hca_in, in, embedded_cpu_function,
+		 dev->caps.embedded_cpu);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 }
 
-u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
+u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
+			     struct ptp_system_timestamp *sts)
 {
 	u32 timer_h, timer_h1, timer_l;
 
 	timer_h = ioread32be(&dev->iseg->internal_timer_h);
+	ptp_read_system_prets(sts);
 	timer_l = ioread32be(&dev->iseg->internal_timer_l);
+	ptp_read_system_postts(sts);
 	timer_h1 = ioread32be(&dev->iseg->internal_timer_h);
-	if (timer_h != timer_h1) /* wrap around */
+	if (timer_h != timer_h1) {
+		/* wrap around */
+		ptp_read_system_prets(sts);
 		timer_l = ioread32be(&dev->iseg->internal_timer_l);
-
-	return (u64)timer_l | (u64)timer_h1 << 32;
-}
-
-static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
-
-	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
-	}
-
-	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			priv->irq_info[i].mask);
-
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, priv->irq_info[i].mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
-	return 0;
-}
-
-static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	int irq = pci_irq_vector(mdev->pdev, MLX5_EQ_VEC_COMP_BASE + i);
-
-	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(priv->irq_info[i].mask);
-}
-
-static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int err;
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
-		err = mlx5_irq_set_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
+		ptp_read_system_postts(sts);
 	}
 
-	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-
-	return err;
-}
-
-static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-}
-
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
-		    unsigned int *irqn)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq, *n;
-	int err = -ENOENT;
-
-	spin_lock(&table->lock);
-	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
-		if (eq->index == vector) {
-			*eqn = eq->eqn;
-			*irqn = eq->irqn;
-			err = 0;
-			break;
-		}
-	}
-	spin_unlock(&table->lock);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_vector2eqn);
-
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq;
-
-	spin_lock(&table->lock);
-	list_for_each_entry(eq, &table->comp_eqs_list, list)
-		if (eq->eqn == eqn) {
-			spin_unlock(&table->lock);
-			return eq;
-		}
-
-	spin_unlock(&table->lock);
-
-	return ERR_PTR(-ENOENT);
-}
-
-static void free_comp_eqs(struct mlx5_core_dev *dev)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	struct mlx5_eq *eq, *n;
-
-#ifdef CONFIG_RFS_ACCEL
-	if (dev->rmap) {
-		free_irq_cpu_rmap(dev->rmap);
-		dev->rmap = NULL;
-	}
-#endif
-	spin_lock(&table->lock);
-	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
-		list_del(&eq->list);
-		spin_unlock(&table->lock);
-		if (mlx5_destroy_unmap_eq(dev, eq))
-			mlx5_core_warn(dev, "failed to destroy EQ 0x%x\n",
-				       eq->eqn);
-		kfree(eq);
-		spin_lock(&table->lock);
-	}
-	spin_unlock(&table->lock);
-}
-
-static int alloc_comp_eqs(struct mlx5_core_dev *dev)
-{
-	struct mlx5_eq_table *table = &dev->priv.eq_table;
-	char name[MLX5_MAX_IRQ_NAME];
-	struct mlx5_eq *eq;
-	int ncomp_vec;
-	int nent;
-	int err;
-	int i;
-
-	INIT_LIST_HEAD(&table->comp_eqs_list);
-	ncomp_vec = table->num_comp_vectors;
-	nent = MLX5_COMP_EQ_SIZE;
-#ifdef CONFIG_RFS_ACCEL
-	dev->rmap = alloc_irq_cpu_rmap(ncomp_vec);
-	if (!dev->rmap)
-		return -ENOMEM;
-#endif
-	for (i = 0; i < ncomp_vec; i++) {
-		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
-		if (!eq) {
-			err = -ENOMEM;
-			goto clean;
-		}
-
-#ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev,
-				 MLX5_EQ_VEC_COMP_BASE + i));
-#endif
-		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
-		err = mlx5_create_map_eq(dev, eq,
-					 i + MLX5_EQ_VEC_COMP_BASE, nent, 0,
-					 name, MLX5_EQ_TYPE_COMP);
-		if (err) {
-			kfree(eq);
-			goto clean;
-		}
-		mlx5_core_dbg(dev, "allocated completion EQN %d\n", eq->eqn);
-		eq->index = i;
-		spin_lock(&table->lock);
-		list_add_tail(&eq->list, &table->comp_eqs_list);
-		spin_unlock(&table->lock);
-	}
-
-	return 0;
-
-clean:
-	free_comp_eqs(dev);
-	return err;
+	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
 static int mlx5_core_set_issi(struct mlx5_core_dev *dev)
@@ -877,11 +733,9 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	priv->numa_node = dev_to_node(&dev->pdev->dev);
 
-	priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root);
-	if (!priv->dbg_root) {
-		dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n");
-		return -ENOMEM;
-	}
+	if (mlx5_debugfs_root)
+		priv->dbg_root =
+			debugfs_create_dir(pci_name(pdev), mlx5_debugfs_root);
 
 	err = mlx5_pci_enable_device(dev);
 	if (err) {
@@ -903,6 +757,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto err_clr_master;
 	}
 
+	if (pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP32) &&
+	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP64) &&
+	    pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128))
+		mlx5_core_dbg(dev, "Enabling pci atomics failed\n");
+
 	dev->iseg_base = pci_resource_start(dev->pdev, 0);
 	dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg));
 	if (!dev->iseg) {
@@ -938,28 +797,37 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 	struct pci_dev *pdev = dev->pdev;
 	int err;
 
+	priv->devcom = mlx5_devcom_register_device(dev);
+	if (IS_ERR(priv->devcom))
+		dev_err(&pdev->dev, "failed to register with devcom (0x%p)\n",
+			priv->devcom);
+
 	err = mlx5_query_board_id(dev);
 	if (err) {
 		dev_err(&pdev->dev, "query board id failed\n");
-		goto out;
+		goto err_devcom;
 	}
 
-	err = mlx5_eq_init(dev);
+	err = mlx5_eq_table_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize eq\n");
-		goto out;
+		goto err_devcom;
+	}
+
+	err = mlx5_events_init(dev);
+	if (err) {
+		dev_err(&pdev->dev, "failed to initialize events\n");
+		goto err_eq_cleanup;
 	}
 
 	err = mlx5_cq_debugfs_init(dev);
 	if (err) {
 		dev_err(&pdev->dev, "failed to initialize cq debugfs\n");
-		goto err_eq_cleanup;
+		goto err_events_cleanup;
 	}
 
 	mlx5_init_qp_table(dev);
 
-	mlx5_init_srq_table(dev);
-
 	mlx5_init_mkey_table(dev);
 
 	mlx5_init_reserved_gids(dev);
@@ -1013,14 +881,15 @@ err_rl_cleanup:
 err_tables_cleanup:
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_mkey_table(dev);
-	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
-
+err_events_cleanup:
+	mlx5_events_cleanup(dev);
 err_eq_cleanup:
-	mlx5_eq_cleanup(dev);
+	mlx5_eq_table_cleanup(dev);
+err_devcom:
+	mlx5_devcom_unregister_device(dev->priv.devcom);
 
-out:
 	return err;
 }
 
@@ -1036,10 +905,11 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cleanup_mkey_table(dev);
-	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
 	mlx5_cq_debugfs_cleanup(dev);
-	mlx5_eq_cleanup(dev);
+	mlx5_events_cleanup(dev);
+	mlx5_eq_table_cleanup(dev);
+	mlx5_devcom_unregister_device(dev->priv.devcom);
 }
 
 static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
@@ -1048,6 +918,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	struct pci_dev *pdev = dev->pdev;
 	int err;
 
+	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mutex_lock(&dev->intf_state_mutex);
 	if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) {
 		dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n",
@@ -1113,15 +984,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto reclaim_boot_pages;
 	}
 
-	err = handle_hca_cap(dev);
+	err = set_hca_cap(dev);
 	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap failed\n");
-		goto reclaim_boot_pages;
-	}
-
-	err = handle_hca_cap_atomic(dev);
-	if (err) {
-		dev_err(&pdev->dev, "handle_hca_cap_atomic failed\n");
+		dev_err(&pdev->dev, "set_hca_cap failed\n");
 		goto reclaim_boot_pages;
 	}
 
@@ -1131,16 +996,10 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto reclaim_boot_pages;
 	}
 
-	err = mlx5_pagealloc_start(dev);
-	if (err) {
-		dev_err(&pdev->dev, "mlx5_pagealloc_start failed\n");
-		goto reclaim_boot_pages;
-	}
-
 	err = mlx5_cmd_init_hca(dev, sw_owner_id);
 	if (err) {
 		dev_err(&pdev->dev, "init hca failed\n");
-		goto err_pagealloc_stop;
+		goto reclaim_boot_pages;
 	}
 
 	mlx5_set_driver_version(dev);
@@ -1161,23 +1020,20 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		}
 	}
 
-	err = mlx5_alloc_irq_vectors(dev);
-	if (err) {
-		dev_err(&pdev->dev, "alloc irq vectors failed\n");
-		goto err_cleanup_once;
-	}
-
 	dev->priv.uar = mlx5_get_uars_page(dev);
 	if (IS_ERR(dev->priv.uar)) {
 		dev_err(&pdev->dev, "Failed allocating uar, aborting\n");
 		err = PTR_ERR(dev->priv.uar);
-		goto err_disable_msix;
+		goto err_get_uars;
 	}
 
-	err = mlx5_start_eqs(dev);
+	mlx5_events_start(dev);
+	mlx5_pagealloc_start(dev);
+
+	err = mlx5_eq_table_create(dev);
 	if (err) {
-		dev_err(&pdev->dev, "Failed to start pages and async EQs\n");
-		goto err_put_uars;
+		dev_err(&pdev->dev, "Failed to create EQs\n");
+		goto err_eq_table;
 	}
 
 	err = mlx5_fw_tracer_init(dev->tracer);
@@ -1186,18 +1042,6 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_fw_tracer;
 	}
 
-	err = alloc_comp_eqs(dev);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
-		goto err_comp_eqs;
-	}
-
-	err = mlx5_irq_set_affinity_hints(dev);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
-		goto err_affinity_hints;
-	}
-
 	err = mlx5_fpga_device_start(dev);
 	if (err) {
 		dev_err(&pdev->dev, "fpga device start failed %d\n", err);
@@ -1234,6 +1078,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_sriov;
 	}
 
+	err = mlx5_ec_init(dev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init embedded CPU\n");
+		goto err_ec;
+	}
+
 	if (mlx5_device_registered(dev)) {
 		mlx5_attach_device(dev);
 	} else {
@@ -1251,6 +1101,9 @@ out:
 	return 0;
 
 err_reg_dev:
+	mlx5_ec_cleanup(dev);
+
+err_ec:
 	mlx5_sriov_detach(dev);
 
 err_sriov:
@@ -1266,24 +1119,17 @@ err_ipsec_start:
 	mlx5_fpga_device_stop(dev);
 
 err_fpga_start:
-	mlx5_irq_clear_affinity_hints(dev);
-
-err_affinity_hints:
-	free_comp_eqs(dev);
-
-err_comp_eqs:
 	mlx5_fw_tracer_cleanup(dev->tracer);
 
 err_fw_tracer:
-	mlx5_stop_eqs(dev);
+	mlx5_eq_table_destroy(dev);
 
-err_put_uars:
+err_eq_table:
+	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
 	mlx5_put_uars_page(dev, priv->uar);
 
-err_disable_msix:
-	mlx5_free_irq_vectors(dev);
-
-err_cleanup_once:
+err_get_uars:
 	if (boot)
 		mlx5_cleanup_once(dev);
 
@@ -1294,9 +1140,6 @@ err_stop_poll:
 		goto out_err;
 	}
 
-err_pagealloc_stop:
-	mlx5_pagealloc_stop(dev);
-
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
 
@@ -1335,26 +1178,26 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	if (mlx5_device_registered(dev))
 		mlx5_detach_device(dev);
 
+	mlx5_ec_cleanup(dev);
 	mlx5_sriov_detach(dev);
 	mlx5_cleanup_fs(dev);
 	mlx5_accel_ipsec_cleanup(dev);
 	mlx5_accel_tls_cleanup(dev);
 	mlx5_fpga_device_stop(dev);
-	mlx5_irq_clear_affinity_hints(dev);
-	free_comp_eqs(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
-	mlx5_stop_eqs(dev);
+	mlx5_eq_table_destroy(dev);
+	mlx5_pagealloc_stop(dev);
+	mlx5_events_stop(dev);
 	mlx5_put_uars_page(dev, priv->uar);
-	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev, cleanup);
+
 	err = mlx5_cmd_teardown_hca(dev);
 	if (err) {
 		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
 		goto out;
 	}
-	mlx5_pagealloc_stop(dev);
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_cleanup(dev);
@@ -1364,12 +1207,6 @@ out:
 	return err;
 }
 
-struct mlx5_core_event_handler {
-	void (*event)(struct mlx5_core_dev *dev,
-		      enum mlx5_dev_event event,
-		      void *data);
-};
-
 static const struct devlink_ops mlx5_devlink_ops = {
 #ifdef CONFIG_MLX5_ESWITCH
 	.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
@@ -1403,7 +1240,6 @@ static int init_one(struct pci_dev *pdev,
 	pci_set_drvdata(pdev, dev);
 
 	dev->pdev = pdev;
-	dev->event = mlx5_core_event;
 	dev->profile = &profile[prof_sel];
 
 	INIT_LIST_HEAD(&priv->ctx_list);
@@ -1411,17 +1247,6 @@ static int init_one(struct pci_dev *pdev,
 	mutex_init(&dev->pci_status_mutex);
 	mutex_init(&dev->intf_state_mutex);
 
-	INIT_LIST_HEAD(&priv->waiting_events_list);
-	priv->is_accum_events = false;
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	err = init_srcu_struct(&priv->pfault_srcu);
-	if (err) {
-		dev_err(&pdev->dev, "init_srcu_struct failed with error code %d\n",
-			err);
-		goto clean_dev;
-	}
-#endif
 	mutex_init(&priv->bfregs.reg_head.lock);
 	mutex_init(&priv->bfregs.wc_head.lock);
 	INIT_LIST_HEAD(&priv->bfregs.reg_head.list);
@@ -1430,7 +1255,7 @@ static int init_one(struct pci_dev *pdev,
 	err = mlx5_pci_init(dev, priv);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err);
-		goto clean_srcu;
+		goto clean_dev;
 	}
 
 	err = mlx5_health_init(dev);
@@ -1439,12 +1264,14 @@ static int init_one(struct pci_dev *pdev,
 		goto close_pci;
 	}
 
-	mlx5_pagealloc_init(dev);
+	err = mlx5_pagealloc_init(dev);
+	if (err)
+		goto err_pagealloc_init;
 
 	err = mlx5_load_one(dev, priv, true);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err);
-		goto clean_health;
+		goto err_load_one;
 	}
 
 	request_module_nowait(MLX5_IB_MOD);
@@ -1458,16 +1285,13 @@ static int init_one(struct pci_dev *pdev,
 
 clean_load:
 	mlx5_unload_one(dev, priv, true);
-clean_health:
+err_load_one:
 	mlx5_pagealloc_cleanup(dev);
+err_pagealloc_init:
 	mlx5_health_cleanup(dev);
 close_pci:
 	mlx5_pci_close(dev, priv);
-clean_srcu:
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	cleanup_srcu_struct(&priv->pfault_srcu);
 clean_dev:
-#endif
 	devlink_free(devlink);
 
 	return err;
@@ -1491,9 +1315,6 @@ static void remove_one(struct pci_dev *pdev)
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_health_cleanup(dev);
 	mlx5_pci_close(dev, priv);
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	cleanup_srcu_struct(&priv->pfault_srcu);
-#endif
 	devlink_free(devlink);
 }
 
@@ -1637,7 +1458,6 @@ succeed:
 	 * kexec. There is no need to cleanup the mlx5_core software
 	 * contexts.
 	 */
-	mlx5_irq_clear_affinity_hints(dev);
 	mlx5_core_eq_free_irqs(dev);
 
 	return 0;
@@ -1669,6 +1489,8 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
 	{ PCI_VDEVICE(MELLANOX, 0x101a), MLX5_PCI_DEV_IS_VF},	/* ConnectX-5 Ex VF */
 	{ PCI_VDEVICE(MELLANOX, 0x101b) },			/* ConnectX-6 */
 	{ PCI_VDEVICE(MELLANOX, 0x101c), MLX5_PCI_DEV_IS_VF},	/* ConnectX-6 VF */
+	{ PCI_VDEVICE(MELLANOX, 0x101d) },			/* ConnectX-6 Dx */
+	{ PCI_VDEVICE(MELLANOX, 0x101e), MLX5_PCI_DEV_IS_VF},	/* ConnectX Family mlx5Gen Virtual Function */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d2) },			/* BlueField integrated ConnectX-5 network controller */
 	{ PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF},	/* BlueField integrated ConnectX-5 network controller VF */
 	{ 0, }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 0594d0961cb3..7b331674622c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -38,6 +38,7 @@
 #include <linux/sched.h>
 #include <linux/if_link.h>
 #include <linux/firmware.h>
+#include <linux/ptp_clock_kernel.h>
 #include <linux/mlx5/cq.h>
 #include <linux/mlx5/fs.h>
 
@@ -78,6 +79,11 @@ do {									\
 		 __func__, __LINE__, current->pid,			\
 		##__VA_ARGS__)
 
+#define mlx5_core_warn_once(__dev, format, ...)				\
+	dev_warn_once(&(__dev)->pdev->dev, "%s:%d:(pid %d): " format,	\
+		      __func__, __LINE__, current->pid,			\
+		      ##__VA_ARGS__)
+
 #define mlx5_core_info(__dev, format, ...)				\
 	dev_info(&(__dev)->pdev->dev, format, ##__VA_ARGS__)
 
@@ -97,12 +103,6 @@ int mlx5_cmd_init_hca(struct mlx5_core_dev *dev, uint32_t *sw_owner_id);
 int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_force_teardown_hca(struct mlx5_core_dev *dev);
 int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev);
-
-void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
-		     unsigned long param);
-void mlx5_core_page_fault(struct mlx5_core_dev *dev,
-			  struct mlx5_pagefault *pfault);
-void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
 void mlx5_recover_device(struct mlx5_core_dev *dev);
@@ -121,31 +121,12 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 				       u32 modify_bitmask);
 int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
-int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
-u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
-
-int mlx5_eq_init(struct mlx5_core_dev *dev);
-void mlx5_eq_cleanup(struct mlx5_core_dev *dev);
-int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
-		       int nent, u64 mask, const char *name,
-		       enum mlx5_eq_type type);
-int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
-		       u32 *out, int outlen);
-int mlx5_start_eqs(struct mlx5_core_dev *dev);
-void mlx5_stop_eqs(struct mlx5_core_dev *dev);
-/* This function should only be called after mlx5_cmd_force_teardown_hca */
-void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
-struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
-u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq *eq);
-void mlx5_cq_tasklet_cb(unsigned long data);
-void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
-int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq);
-int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev);
-void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev);
+int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages);
+u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev,
+			     struct ptp_system_timestamp *sts);
+
+void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev);
+void mlx5_cmd_flush(struct mlx5_core_dev *dev);
 int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev);
 
@@ -159,6 +140,11 @@ int mlx5_query_qcam_reg(struct mlx5_core_dev *mdev, u32 *qcam,
 void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev);
 void mlx5_lag_remove(struct mlx5_core_dev *dev);
 
+int mlx5_events_init(struct mlx5_core_dev *dev);
+void mlx5_events_cleanup(struct mlx5_core_dev *dev);
+void mlx5_events_start(struct mlx5_core_dev *dev);
+void mlx5_events_stop(struct mlx5_core_dev *dev);
+
 void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
 void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv);
 void mlx5_attach_device(struct mlx5_core_dev *dev);
@@ -202,10 +188,8 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
 		    MLX5_CAP_GEN(dev, lag_master);
 }
 
-int mlx5_lag_allow(struct mlx5_core_dev *dev);
-int mlx5_lag_forbid(struct mlx5_core_dev *dev);
-
 void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol);
+void mlx5_lag_update(struct mlx5_core_dev *dev);
 
 enum {
 	MLX5_NIC_IFC_FULL		= 0,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index 0670165afd5f..ea744d8466ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -51,9 +51,10 @@ void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev)
 
 int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 			     struct mlx5_core_mkey *mkey,
-			     u32 *in, int inlen,
-			     u32 *out, int outlen,
-			     mlx5_cmd_cbk_t callback, void *context)
+			     struct mlx5_async_ctx *async_ctx, u32 *in,
+			     int inlen, u32 *out, int outlen,
+			     mlx5_async_cbk_t callback,
+			     struct mlx5_async_work *context)
 {
 	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0};
@@ -71,7 +72,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 	MLX5_SET(mkc, mkc, mkey_7_0, key);
 
 	if (callback)
-		return mlx5_cmd_exec_cb(dev, in, inlen, out, outlen,
+		return mlx5_cmd_exec_cb(async_ctx, in, inlen, out, outlen,
 					callback, context);
 
 	err = mlx5_cmd_exec(dev, in, inlen, lout, sizeof(lout));
@@ -105,7 +106,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev,
 			  struct mlx5_core_mkey *mkey,
 			  u32 *in, int inlen)
 {
-	return mlx5_core_create_mkey_cb(dev, mkey, in, inlen,
+	return mlx5_core_create_mkey_cb(dev, mkey, NULL, in, inlen,
 					NULL, 0, NULL, NULL);
 }
 EXPORT_SYMBOL(mlx5_core_create_mkey);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
index e36d3e3675f9..41025387ff2c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c
@@ -37,6 +37,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
 enum {
 	MLX5_PAGES_CANT_GIVE	= 0,
@@ -47,6 +48,7 @@ enum {
 struct mlx5_pages_req {
 	struct mlx5_core_dev *dev;
 	u16	func_id;
+	u8	ec_function;
 	s32	npages;
 	struct work_struct work;
 };
@@ -142,6 +144,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 	MLX5_SET(query_pages_in, in, op_mod, boot ?
 		 MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES :
 		 MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES);
+	MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev));
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -252,7 +255,8 @@ err_mapping:
 	return err;
 }
 
-static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
+static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id,
+			     bool ec_function)
 {
 	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(manage_pages_in)]   = {0};
@@ -261,6 +265,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
 	MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES);
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -269,7 +274,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id)
 }
 
 static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages,
-		      int notify_fail)
+		      int notify_fail, bool ec_function)
 {
 	u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0};
 	int inlen = MLX5_ST_SZ_BYTES(manage_pages_in);
@@ -304,6 +309,7 @@ retry:
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 	if (err) {
@@ -315,8 +321,11 @@ retry:
 	dev->priv.fw_pages += npages;
 	if (func_id)
 		dev->priv.vfs_pages += npages;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages += npages;
 
-	mlx5_core_dbg(dev, "err %d\n", err);
+	mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n",
+		      npages, ec_function, func_id, err);
 
 	kvfree(in);
 	return 0;
@@ -327,7 +336,7 @@ out_4k:
 out_free:
 	kvfree(in);
 	if (notify_fail)
-		page_notify_fail(dev, func_id);
+		page_notify_fail(dev, func_id, ec_function);
 	return err;
 }
 
@@ -363,7 +372,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev,
 }
 
 static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
-			 int *nclaimed)
+			 int *nclaimed, bool ec_function)
 {
 	int outlen = MLX5_ST_SZ_BYTES(manage_pages_out);
 	u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0};
@@ -384,6 +393,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE);
 	MLX5_SET(manage_pages_in, in, function_id, func_id);
 	MLX5_SET(manage_pages_in, in, input_num_entries, npages);
+	MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function);
 
 	mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen);
 	err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen);
@@ -409,6 +419,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages,
 	dev->priv.fw_pages -= num_claimed;
 	if (func_id)
 		dev->priv.vfs_pages -= num_claimed;
+	else if (mlx5_core_is_ecpf(dev) && !ec_function)
+		dev->priv.peer_pf_pages -= num_claimed;
 
 out_free:
 	kvfree(out);
@@ -422,9 +434,10 @@ static void pages_work_handler(struct work_struct *work)
 	int err = 0;
 
 	if (req->npages < 0)
-		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL);
+		err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL,
+				    req->ec_function);
 	else if (req->npages > 0)
-		err = give_pages(dev, req->func_id, req->npages, 1);
+		err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function);
 
 	if (err)
 		mlx5_core_warn(dev, "%s fail %d\n",
@@ -433,22 +446,43 @@ static void pages_work_handler(struct work_struct *work)
 	kfree(req);
 }
 
-void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
-				 s32 npages)
+enum {
+	EC_FUNCTION_MASK = 0x8000,
+};
+
+static int req_pages_handler(struct notifier_block *nb,
+			     unsigned long type, void *data)
 {
 	struct mlx5_pages_req *req;
-
+	struct mlx5_core_dev *dev;
+	struct mlx5_priv *priv;
+	struct mlx5_eqe *eqe;
+	bool ec_function;
+	u16 func_id;
+	s32 npages;
+
+	priv = mlx5_nb_cof(nb, struct mlx5_priv, pg_nb);
+	dev  = container_of(priv, struct mlx5_core_dev, priv);
+	eqe  = data;
+
+	func_id = be16_to_cpu(eqe->data.req_pages.func_id);
+	npages  = be32_to_cpu(eqe->data.req_pages.num_pages);
+	ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK;
+	mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
+		      func_id, npages);
 	req = kzalloc(sizeof(*req), GFP_ATOMIC);
 	if (!req) {
 		mlx5_core_warn(dev, "failed to allocate pages request\n");
-		return;
+		return NOTIFY_DONE;
 	}
 
 	req->dev = dev;
 	req->func_id = func_id;
 	req->npages = npages;
+	req->ec_function = ec_function;
 	INIT_WORK(&req->work, pages_work_handler);
 	queue_work(dev->priv.pg_wq, &req->work);
+	return NOTIFY_OK;
 }
 
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
@@ -464,7 +498,7 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
 	mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n",
 		      npages, boot ? "boot" : "init", func_id);
 
-	return give_pages(dev, func_id, npages, 0);
+	return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev));
 }
 
 enum {
@@ -498,7 +532,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 			fwp = rb_entry(p, struct fw_page, rb_node);
 			err = reclaim_pages(dev, fwp->func_id,
 					    optimal_reclaimed_pages(),
-					    &nclaimed);
+					    &nclaimed, mlx5_core_is_ecpf(dev));
 
 			if (err) {
 				mlx5_core_warn(dev, "failed reclaiming pages (%d)\n",
@@ -520,39 +554,45 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev)
 	WARN(dev->priv.vfs_pages,
 	     "VFs FW pages counter is %d after reclaiming all pages\n",
 	     dev->priv.vfs_pages);
+	WARN(dev->priv.peer_pf_pages,
+	     "Peer PF FW pages counter is %d after reclaiming all pages\n",
+	     dev->priv.peer_pf_pages);
 
 	return 0;
 }
 
-void mlx5_pagealloc_init(struct mlx5_core_dev *dev)
+int mlx5_pagealloc_init(struct mlx5_core_dev *dev)
 {
 	dev->priv.page_root = RB_ROOT;
 	INIT_LIST_HEAD(&dev->priv.free_list);
+	dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
+	if (!dev->priv.pg_wq)
+		return -ENOMEM;
+
+	return 0;
 }
 
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev)
 {
-	/* nothing */
+	destroy_workqueue(dev->priv.pg_wq);
 }
 
-int mlx5_pagealloc_start(struct mlx5_core_dev *dev)
+void mlx5_pagealloc_start(struct mlx5_core_dev *dev)
 {
-	dev->priv.pg_wq = create_singlethread_workqueue("mlx5_page_allocator");
-	if (!dev->priv.pg_wq)
-		return -ENOMEM;
-
-	return 0;
+	MLX5_NB_INIT(&dev->priv.pg_nb, req_pages_handler, PAGE_REQUEST);
+	mlx5_eq_notifier_register(dev, &dev->priv.pg_nb);
 }
 
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev)
 {
-	destroy_workqueue(dev->priv.pg_wq);
+	mlx5_eq_notifier_unregister(dev, &dev->priv.pg_nb);
+	flush_workqueue(dev->priv.pg_wq);
 }
 
-int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
+int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages)
 {
 	unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS);
-	int prev_vfs_pages = dev->priv.vfs_pages;
+	int prev_pages = *pages;
 
 	/* In case of internal error we will free the pages manually later */
 	if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
@@ -560,16 +600,16 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev)
 		return 0;
 	}
 
-	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_vfs_pages,
+	mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages,
 		      dev->priv.name);
-	while (dev->priv.vfs_pages) {
+	while (*pages) {
 		if (time_after(jiffies, end)) {
-			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", dev->priv.vfs_pages);
+			mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages);
 			return -ETIMEDOUT;
 		}
-		if (dev->priv.vfs_pages < prev_vfs_pages) {
+		if (*pages < prev_pages) {
 			end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS);
-			prev_vfs_pages = dev->priv.vfs_pages;
+			prev_pages = *pages;
 		}
 		msleep(50);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 31a9cbd85689..361468e0435d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -30,10 +30,7 @@
  * SOFTWARE.
  */
 
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
 #include <linux/mlx5/port.h>
-#include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
 int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
@@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration)
 				    sizeof(out), MLX5_REG_MLCR, 0, 1);
 }
 
-int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev,
-			      u32 *proto_cap, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
-	if (err)
-		return err;
-
-	if (proto_mask == MLX5_PTYS_EN)
-		*proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability);
-	else
-		*proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap);
-
-int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev,
-				u32 *proto_admin, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1);
-	if (err)
-		return err;
-
-	if (proto_mask == MLX5_PTYS_EN)
-		*proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin);
-	else
-		*proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin);
-
 int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 				    u8 *link_width_oper, u8 local_port)
 {
@@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper);
 
-int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev,
-				   u32 *proto_oper, u8 local_port)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	int err;
-
-	err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN,
-				   local_port);
-	if (err)
-		return err;
-
-	*proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper);
-
 int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 				  u8 *proto_oper, u8 local_port)
 {
@@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper);
 
-int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable,
-		       u32 proto_admin, int proto_mask)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-	u32 in[MLX5_ST_SZ_DW(ptys_reg)];
-	u8 an_disable_admin;
-	u8 an_disable_cap;
-	u8 an_status;
-
-	mlx5_query_port_autoneg(dev, proto_mask, &an_status,
-				&an_disable_cap, &an_disable_admin);
-	if (!an_disable_cap && an_disable)
-		return -EPERM;
-
-	memset(in, 0, sizeof(in));
-
-	MLX5_SET(ptys_reg, in, local_port, 1);
-	MLX5_SET(ptys_reg, in, an_disable_admin, an_disable);
-	MLX5_SET(ptys_reg, in, proto_mask, proto_mask);
-	if (proto_mask == MLX5_PTYS_EN)
-		MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin);
-	else
-		MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin);
-
-	return mlx5_core_access_reg(dev, in, sizeof(in), out,
-				    sizeof(out), MLX5_REG_PTYS, 0, 1);
-}
-EXPORT_SYMBOL_GPL(mlx5_set_port_ptys);
-
 /* This function should be used after setting a port register only */
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
 {
@@ -404,10 +317,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 		size -= offset + size - MLX5_EEPROM_PAGE_LENGTH;
 
 	i2c_addr = MLX5_I2C_ADDR_LOW;
-	if (offset >= MLX5_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLX5_I2C_ADDR_HIGH;
-		offset -= MLX5_EEPROM_PAGE_LENGTH;
-	}
 
 	MLX5_SET(mcia_reg, in, l, 0);
 	MLX5_SET(mcia_reg, in, module, module_num);
@@ -606,25 +515,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
-void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask,
-			     u8 *an_status,
-			     u8 *an_disable_cap, u8 *an_disable_admin)
-{
-	u32 out[MLX5_ST_SZ_DW(ptys_reg)];
-
-	*an_status = 0;
-	*an_disable_cap = 0;
-	*an_disable_admin = 0;
-
-	if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1))
-		return;
-
-	*an_status = MLX5_GET(ptys_reg, out, an_status);
-	*an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap);
-	*an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg);
-
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
 	u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8;
@@ -870,8 +760,7 @@ int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_port_wol);
 
-static int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out,
-				  int outlen)
+int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen)
 {
 	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
 
@@ -880,7 +769,7 @@ static int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out,
 				    outlen, MLX5_REG_PCMR, 0, 0);
 }
 
-static int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen)
+int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen)
 {
 	u32 out[MLX5_ST_SZ_DW(pcmr_reg)];
 
@@ -891,7 +780,11 @@ static int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen)
 int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable)
 {
 	u32 in[MLX5_ST_SZ_DW(pcmr_reg)] = {0};
+	int err;
 
+	err = mlx5_query_ports_check(mdev, in, sizeof(in));
+	if (err)
+		return err;
 	MLX5_SET(pcmr_reg, in, local_port, 1);
 	MLX5_SET(pcmr_reg, in, fcs_chk, enable);
 	return mlx5_set_ports_check(mdev, in, sizeof(in));
@@ -915,63 +808,6 @@ void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
 	*enabled = !!(MLX5_GET(pcmr_reg, out, fcs_chk));
 }
 
-static const char *mlx5_pme_status[MLX5_MODULE_STATUS_NUM] = {
-	"Cable plugged",   /* MLX5_MODULE_STATUS_PLUGGED    = 0x1 */
-	"Cable unplugged", /* MLX5_MODULE_STATUS_UNPLUGGED  = 0x2 */
-	"Cable error",     /* MLX5_MODULE_STATUS_ERROR      = 0x3 */
-};
-
-static const char *mlx5_pme_error[MLX5_MODULE_EVENT_ERROR_NUM] = {
-	"Power budget exceeded",
-	"Long Range for non MLNX cable",
-	"Bus stuck(I2C or data shorted)",
-	"No EEPROM/retry timeout",
-	"Enforce part number list",
-	"Unknown identifier",
-	"High Temperature",
-	"Bad or shorted cable/module",
-	"Unknown status",
-};
-
-void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
-{
-	enum port_module_event_status_type module_status;
-	enum port_module_event_error_type error_type;
-	struct mlx5_eqe_port_module *module_event_eqe;
-	struct mlx5_priv *priv = &dev->priv;
-	u8 module_num;
-
-	module_event_eqe = &eqe->data.port_module;
-	module_num = module_event_eqe->module;
-	module_status = module_event_eqe->module_status &
-			PORT_MODULE_EVENT_MODULE_STATUS_MASK;
-	error_type = module_event_eqe->error_type &
-		     PORT_MODULE_EVENT_ERROR_TYPE_MASK;
-
-	if (module_status < MLX5_MODULE_STATUS_ERROR) {
-		priv->pme_stats.status_counters[module_status - 1]++;
-	} else if (module_status == MLX5_MODULE_STATUS_ERROR) {
-		if (error_type >= MLX5_MODULE_EVENT_ERROR_UNKNOWN)
-			/* Unknown error type */
-			error_type = MLX5_MODULE_EVENT_ERROR_UNKNOWN;
-		priv->pme_stats.error_counters[error_type]++;
-	}
-
-	if (!printk_ratelimit())
-		return;
-
-	if (module_status < MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(dev,
-			       "Port module event: module %u, %s\n",
-			       module_num, mlx5_pme_status[module_status - 1]);
-
-	else if (module_status == MLX5_MODULE_STATUS_ERROR)
-		mlx5_core_info(dev,
-			       "Port module event[error]: module %u, %s, %s\n",
-			       module_num, mlx5_pme_status[module_status - 1],
-			       mlx5_pme_error[error_type]);
-}
-
 int mlx5_query_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size)
 {
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 91b8139a388d..b8ba74de9555 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -38,26 +38,25 @@
 #include <linux/mlx5/transobj.h>
 
 #include "mlx5_core.h"
+#include "lib/eq.h"
 
-static struct mlx5_core_rsc_common *mlx5_get_rsc(struct mlx5_core_dev *dev,
-						 u32 rsn)
+static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
+			       struct mlx5_core_dct *dct);
+
+static struct mlx5_core_rsc_common *
+mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn)
 {
-	struct mlx5_qp_table *table = &dev->priv.qp_table;
 	struct mlx5_core_rsc_common *common;
+	unsigned long flags;
 
-	spin_lock(&table->lock);
+	spin_lock_irqsave(&table->lock, flags);
 
 	common = radix_tree_lookup(&table->tree, rsn);
 	if (common)
 		atomic_inc(&common->refcount);
 
-	spin_unlock(&table->lock);
+	spin_unlock_irqrestore(&table->lock, flags);
 
-	if (!common) {
-		mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n",
-			       rsn);
-		return NULL;
-	}
 	return common;
 }
 
@@ -120,19 +119,57 @@ static bool is_event_type_allowed(int rsc_type, int event_type)
 	}
 }
 
-void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
+static int rsc_event_notifier(struct notifier_block *nb,
+			      unsigned long type, void *data)
 {
-	struct mlx5_core_rsc_common *common = mlx5_get_rsc(dev, rsn);
+	struct mlx5_core_rsc_common *common;
+	struct mlx5_qp_table *table;
+	struct mlx5_core_dev *dev;
 	struct mlx5_core_dct *dct;
+	u8 event_type = (u8)type;
 	struct mlx5_core_qp *qp;
+	struct mlx5_priv *priv;
+	struct mlx5_eqe *eqe;
+	u32 rsn;
+
+	switch (event_type) {
+	case MLX5_EVENT_TYPE_DCT_DRAINED:
+		eqe = data;
+		rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
+		rsn |= (MLX5_RES_DCT << MLX5_USER_INDEX_LEN);
+		break;
+	case MLX5_EVENT_TYPE_PATH_MIG:
+	case MLX5_EVENT_TYPE_COMM_EST:
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+		eqe = data;
+		rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
+		rsn |= (eqe->data.qp_srq.type << MLX5_USER_INDEX_LEN);
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
 
-	if (!common)
-		return;
+	table = container_of(nb, struct mlx5_qp_table, nb);
+	priv  = container_of(table, struct mlx5_priv, qp_table);
+	dev   = container_of(priv, struct mlx5_core_dev, priv);
+
+	mlx5_core_dbg(dev, "event (%d) arrived on resource 0x%x\n", eqe->type, rsn);
+
+	common = mlx5_get_rsc(table, rsn);
+	if (!common) {
+		mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n", rsn);
+		return NOTIFY_OK;
+	}
 
 	if (!is_event_type_allowed((rsn >> MLX5_USER_INDEX_LEN), event_type)) {
 		mlx5_core_warn(dev, "event 0x%.2x is not allowed on resource 0x%.8x\n",
 			       event_type, rsn);
-		return;
+		goto out;
 	}
 
 	switch (common->res) {
@@ -150,8 +187,10 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	default:
 		mlx5_core_warn(dev, "invalid resource type for 0x%x\n", rsn);
 	}
-
+out:
 	mlx5_core_put_rsc(common);
+
+	return NOTIFY_OK;
 }
 
 static int create_resource_common(struct mlx5_core_dev *dev,
@@ -191,20 +230,49 @@ static void destroy_resource_common(struct mlx5_core_dev *dev,
 	wait_for_completion(&qp->common.free);
 }
 
+static int _mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
+				  struct mlx5_core_dct *dct, bool need_cleanup)
+{
+	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
+	struct mlx5_core_qp *qp = &dct->mqp;
+	int err;
+
+	err = mlx5_core_drain_dct(dev, dct);
+	if (err) {
+		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+			goto destroy;
+		} else {
+			mlx5_core_warn(
+				dev, "failed drain DCT 0x%x with error 0x%x\n",
+				qp->qpn, err);
+			return err;
+		}
+	}
+	wait_for_completion(&dct->drained);
+destroy:
+	if (need_cleanup)
+		destroy_resource_common(dev, &dct->mqp);
+	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
+	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
+	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
+	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
+			    (void *)&out, sizeof(out));
+	return err;
+}
+
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 			 struct mlx5_core_dct *dct,
-			 u32 *in, int inlen)
+			 u32 *in, int inlen,
+			 u32 *out, int outlen)
 {
-	u32 out[MLX5_ST_SZ_DW(create_dct_out)]   = {0};
-	u32 din[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	u32 dout[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
 	struct mlx5_core_qp *qp = &dct->mqp;
 	int err;
 
 	init_completion(&dct->drained);
 	MLX5_SET(create_dct_in, in, opcode, MLX5_CMD_OP_CREATE_DCT);
 
-	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
 	if (err) {
 		mlx5_core_warn(dev, "create DCT failed, ret %d\n", err);
 		return err;
@@ -218,11 +286,7 @@ int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 
 	return 0;
 err_cmd:
-	MLX5_SET(destroy_dct_in, din, opcode, MLX5_CMD_OP_DESTROY_DCT);
-	MLX5_SET(destroy_dct_in, din, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, din, uid, qp->uid);
-	mlx5_cmd_exec(dev, (void *)&in, sizeof(din),
-		      (void *)&out, sizeof(dout));
+	_mlx5_core_destroy_dct(dev, dct, false);
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_create_dct);
@@ -287,29 +351,7 @@ static int mlx5_core_drain_dct(struct mlx5_core_dev *dev,
 int mlx5_core_destroy_dct(struct mlx5_core_dev *dev,
 			  struct mlx5_core_dct *dct)
 {
-	u32 out[MLX5_ST_SZ_DW(destroy_dct_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(destroy_dct_in)]   = {0};
-	struct mlx5_core_qp *qp = &dct->mqp;
-	int err;
-
-	err = mlx5_core_drain_dct(dev, dct);
-	if (err) {
-		if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
-			goto destroy;
-		} else {
-			mlx5_core_warn(dev, "failed drain DCT 0x%x with error 0x%x\n", qp->qpn, err);
-			return err;
-		}
-	}
-	wait_for_completion(&dct->drained);
-destroy:
-	destroy_resource_common(dev, &dct->mqp);
-	MLX5_SET(destroy_dct_in, in, opcode, MLX5_CMD_OP_DESTROY_DCT);
-	MLX5_SET(destroy_dct_in, in, dctn, qp->qpn);
-	MLX5_SET(destroy_dct_in, in, uid, qp->uid);
-	err = mlx5_cmd_exec(dev, (void *)&in, sizeof(in),
-			    (void *)&out, sizeof(out));
-	return err;
+	return _mlx5_core_destroy_dct(dev, dct, true);
 }
 EXPORT_SYMBOL_GPL(mlx5_core_destroy_dct);
 
@@ -487,10 +529,16 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev)
 	spin_lock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 	mlx5_qp_debugfs_init(dev);
+
+	table->nb.notifier_call = rsc_event_notifier;
+	mlx5_notifier_register(dev, &table->nb);
 }
 
 void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev)
 {
+	struct mlx5_qp_table *table = &dev->priv.qp_table;
+
+	mlx5_notifier_unregister(dev, &table->nb);
 	mlx5_qp_debugfs_cleanup(dev);
 }
 
@@ -670,3 +718,20 @@ int mlx5_core_query_q_counter(struct mlx5_core_dev *dev, u16 counter_id,
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
 EXPORT_SYMBOL_GPL(mlx5_core_query_q_counter);
+
+struct mlx5_core_rsc_common *mlx5_core_res_hold(struct mlx5_core_dev *dev,
+						int res_num,
+						enum mlx5_res_type res_type)
+{
+	u32 rsn = res_num | (res_type << MLX5_USER_INDEX_LEN);
+	struct mlx5_qp_table *table = &dev->priv.qp_table;
+
+	return mlx5_get_rsc(table, rsn);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_hold);
+
+void mlx5_core_res_put(struct mlx5_core_rsc_common *res)
+{
+	mlx5_core_put_rsc(res);
+}
+EXPORT_SYMBOL_GPL(mlx5_core_res_put);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index a0674962f02c..7b23fa8d2d60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -147,7 +147,7 @@ out:
 	if (MLX5_ESWITCH_MANAGER(dev))
 		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
 
-	if (mlx5_wait_for_vf_pages(dev))
+	if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
 }
 
@@ -216,20 +216,10 @@ int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	if (!mlx5_core_is_pf(dev))
 		return -EPERM;
 
-	if (num_vfs) {
-		int ret;
-
-		ret = mlx5_lag_forbid(dev);
-		if (ret && (ret != -ENODEV))
-			return ret;
-	}
-
-	if (num_vfs) {
+	if (num_vfs)
 		err = mlx5_sriov_enable(pdev, num_vfs);
-	} else {
+	else
 		mlx5_sriov_disable(pdev);
-		mlx5_lag_allow(dev);
-	}
 
 	return err ? err : num_vfs;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c
deleted file mode 100644
index 6a6fc9be01e6..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c
+++ /dev/null
@@ -1,716 +0,0 @@
-/*
- * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include <linux/mlx5/cmd.h>
-#include <linux/mlx5/srq.h>
-#include <rdma/ib_verbs.h>
-#include "mlx5_core.h"
-#include <linux/mlx5/transobj.h>
-
-void mlx5_srq_event(struct mlx5_core_dev *dev, u32 srqn, int event_type)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-	struct mlx5_core_srq *srq;
-
-	spin_lock(&table->lock);
-
-	srq = radix_tree_lookup(&table->tree, srqn);
-	if (srq)
-		atomic_inc(&srq->refcount);
-
-	spin_unlock(&table->lock);
-
-	if (!srq) {
-		mlx5_core_warn(dev, "Async event for bogus SRQ 0x%08x\n", srqn);
-		return;
-	}
-
-	srq->event(srq, event_type);
-
-	if (atomic_dec_and_test(&srq->refcount))
-		complete(&srq->free);
-}
-
-static int get_pas_size(struct mlx5_srq_attr *in)
-{
-	u32 log_page_size = in->log_page_size + 12;
-	u32 log_srq_size  = in->log_size;
-	u32 log_rq_stride = in->wqe_shift;
-	u32 page_offset   = in->page_offset;
-	u32 po_quanta	  = 1 << (log_page_size - 6);
-	u32 rq_sz	  = 1 << (log_srq_size + 4 + log_rq_stride);
-	u32 page_size	  = 1 << log_page_size;
-	u32 rq_sz_po      = rq_sz + (page_offset * po_quanta);
-	u32 rq_num_pas    = DIV_ROUND_UP(rq_sz_po, page_size);
-
-	return rq_num_pas * sizeof(u64);
-}
-
-static void set_wq(void *wq, struct mlx5_srq_attr *in)
-{
-	MLX5_SET(wq,   wq, wq_signature,  !!(in->flags
-		 & MLX5_SRQ_FLAG_WQ_SIG));
-	MLX5_SET(wq,   wq, log_wq_pg_sz,  in->log_page_size);
-	MLX5_SET(wq,   wq, log_wq_stride, in->wqe_shift + 4);
-	MLX5_SET(wq,   wq, log_wq_sz,     in->log_size);
-	MLX5_SET(wq,   wq, page_offset,   in->page_offset);
-	MLX5_SET(wq,   wq, lwm,		  in->lwm);
-	MLX5_SET(wq,   wq, pd,		  in->pd);
-	MLX5_SET64(wq, wq, dbr_addr,	  in->db_record);
-}
-
-static void set_srqc(void *srqc, struct mlx5_srq_attr *in)
-{
-	MLX5_SET(srqc,   srqc, wq_signature,  !!(in->flags
-		 & MLX5_SRQ_FLAG_WQ_SIG));
-	MLX5_SET(srqc,   srqc, log_page_size, in->log_page_size);
-	MLX5_SET(srqc,   srqc, log_rq_stride, in->wqe_shift);
-	MLX5_SET(srqc,   srqc, log_srq_size,  in->log_size);
-	MLX5_SET(srqc,   srqc, page_offset,   in->page_offset);
-	MLX5_SET(srqc,	 srqc, lwm,	      in->lwm);
-	MLX5_SET(srqc,	 srqc, pd,	      in->pd);
-	MLX5_SET64(srqc, srqc, dbr_addr,      in->db_record);
-	MLX5_SET(srqc,	 srqc, xrcd,	      in->xrcd);
-	MLX5_SET(srqc,	 srqc, cqn,	      in->cqn);
-}
-
-static void get_wq(void *wq, struct mlx5_srq_attr *in)
-{
-	if (MLX5_GET(wq, wq, wq_signature))
-		in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
-	in->log_page_size = MLX5_GET(wq,   wq, log_wq_pg_sz);
-	in->wqe_shift	  = MLX5_GET(wq,   wq, log_wq_stride) - 4;
-	in->log_size	  = MLX5_GET(wq,   wq, log_wq_sz);
-	in->page_offset   = MLX5_GET(wq,   wq, page_offset);
-	in->lwm		  = MLX5_GET(wq,   wq, lwm);
-	in->pd		  = MLX5_GET(wq,   wq, pd);
-	in->db_record	  = MLX5_GET64(wq, wq, dbr_addr);
-}
-
-static void get_srqc(void *srqc, struct mlx5_srq_attr *in)
-{
-	if (MLX5_GET(srqc, srqc, wq_signature))
-		in->flags &= MLX5_SRQ_FLAG_WQ_SIG;
-	in->log_page_size = MLX5_GET(srqc,   srqc, log_page_size);
-	in->wqe_shift	  = MLX5_GET(srqc,   srqc, log_rq_stride);
-	in->log_size	  = MLX5_GET(srqc,   srqc, log_srq_size);
-	in->page_offset   = MLX5_GET(srqc,   srqc, page_offset);
-	in->lwm		  = MLX5_GET(srqc,   srqc, lwm);
-	in->pd		  = MLX5_GET(srqc,   srqc, pd);
-	in->db_record	  = MLX5_GET64(srqc, srqc, dbr_addr);
-}
-
-struct mlx5_core_srq *mlx5_core_get_srq(struct mlx5_core_dev *dev, u32 srqn)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-	struct mlx5_core_srq *srq;
-
-	spin_lock(&table->lock);
-
-	srq = radix_tree_lookup(&table->tree, srqn);
-	if (srq)
-		atomic_inc(&srq->refcount);
-
-	spin_unlock(&table->lock);
-
-	return srq;
-}
-EXPORT_SYMBOL(mlx5_core_get_srq);
-
-static int create_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			  struct mlx5_srq_attr *in)
-{
-	u32 create_out[MLX5_ST_SZ_DW(create_srq_out)] = {0};
-	void *create_in;
-	void *srqc;
-	void *pas;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size  = get_pas_size(in);
-	inlen	  = MLX5_ST_SZ_BYTES(create_srq_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	MLX5_SET(create_srq_in, create_in, uid, in->uid);
-	srqc = MLX5_ADDR_OF(create_srq_in, create_in, srq_context_entry);
-	pas = MLX5_ADDR_OF(create_srq_in, create_in, pas);
-
-	set_srqc(srqc, in);
-	memcpy(pas, in->pas, pas_size);
-
-	MLX5_SET(create_srq_in, create_in, opcode,
-		 MLX5_CMD_OP_CREATE_SRQ);
-
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
-			    sizeof(create_out));
-	kvfree(create_in);
-	if (!err) {
-		srq->srqn = MLX5_GET(create_srq_out, create_out, srqn);
-		srq->uid = in->uid;
-	}
-
-	return err;
-}
-
-static int destroy_srq_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq)
-{
-	u32 srq_in[MLX5_ST_SZ_DW(destroy_srq_in)] = {0};
-	u32 srq_out[MLX5_ST_SZ_DW(destroy_srq_out)] = {0};
-
-	MLX5_SET(destroy_srq_in, srq_in, opcode,
-		 MLX5_CMD_OP_DESTROY_SRQ);
-	MLX5_SET(destroy_srq_in, srq_in, srqn, srq->srqn);
-	MLX5_SET(destroy_srq_in, srq_in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			     srq_out, sizeof(srq_out));
-}
-
-static int arm_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		       u16 lwm, int is_srq)
-{
-	u32 srq_in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
-	u32 srq_out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
-
-	MLX5_SET(arm_rq_in, srq_in, opcode, MLX5_CMD_OP_ARM_RQ);
-	MLX5_SET(arm_rq_in, srq_in, op_mod, MLX5_ARM_RQ_IN_OP_MOD_SRQ);
-	MLX5_SET(arm_rq_in, srq_in, srq_number, srq->srqn);
-	MLX5_SET(arm_rq_in, srq_in, lwm,      lwm);
-	MLX5_SET(arm_rq_in, srq_in, uid, srq->uid);
-
-	return  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			      srq_out, sizeof(srq_out));
-}
-
-static int query_srq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *out)
-{
-	u32 srq_in[MLX5_ST_SZ_DW(query_srq_in)] = {0};
-	u32 *srq_out;
-	void *srqc;
-	int err;
-
-	srq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_srq_out), GFP_KERNEL);
-	if (!srq_out)
-		return -ENOMEM;
-
-	MLX5_SET(query_srq_in, srq_in, opcode,
-		 MLX5_CMD_OP_QUERY_SRQ);
-	MLX5_SET(query_srq_in, srq_in, srqn, srq->srqn);
-	err =  mlx5_cmd_exec(dev, srq_in, sizeof(srq_in),
-			     srq_out, MLX5_ST_SZ_BYTES(query_srq_out));
-	if (err)
-		goto out;
-
-	srqc = MLX5_ADDR_OF(query_srq_out, srq_out, srq_context_entry);
-	get_srqc(srqc, out);
-	if (MLX5_GET(srqc, srqc, state) != MLX5_SRQC_STATE_GOOD)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-out:
-	kvfree(srq_out);
-	return err;
-}
-
-static int create_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			      struct mlx5_core_srq *srq,
-			      struct mlx5_srq_attr *in)
-{
-	u32 create_out[MLX5_ST_SZ_DW(create_xrc_srq_out)];
-	void *create_in;
-	void *xrc_srqc;
-	void *pas;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size  = get_pas_size(in);
-	inlen	  = MLX5_ST_SZ_BYTES(create_xrc_srq_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	MLX5_SET(create_xrc_srq_in, create_in, uid, in->uid);
-	xrc_srqc = MLX5_ADDR_OF(create_xrc_srq_in, create_in,
-				xrc_srq_context_entry);
-	pas	 = MLX5_ADDR_OF(create_xrc_srq_in, create_in, pas);
-
-	set_srqc(xrc_srqc, in);
-	MLX5_SET(xrc_srqc, xrc_srqc, user_index, in->user_index);
-	memcpy(pas, in->pas, pas_size);
-	MLX5_SET(create_xrc_srq_in, create_in, opcode,
-		 MLX5_CMD_OP_CREATE_XRC_SRQ);
-
-	memset(create_out, 0, sizeof(create_out));
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
-			    sizeof(create_out));
-	if (err)
-		goto out;
-
-	srq->srqn = MLX5_GET(create_xrc_srq_out, create_out, xrc_srqn);
-	srq->uid = in->uid;
-out:
-	kvfree(create_in);
-	return err;
-}
-
-static int destroy_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			       struct mlx5_core_srq *srq)
-{
-	u32 xrcsrq_in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)]   = {0};
-	u32 xrcsrq_out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
-
-	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, opcode,
-		 MLX5_CMD_OP_DESTROY_XRC_SRQ);
-	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-	MLX5_SET(destroy_xrc_srq_in, xrcsrq_in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
-			     xrcsrq_out, sizeof(xrcsrq_out));
-}
-
-static int arm_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq, u16 lwm)
-{
-	u32 xrcsrq_in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};
-	u32 xrcsrq_out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
-
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, op_mod,   MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, lwm,      lwm);
-	MLX5_SET(arm_xrc_srq_in, xrcsrq_in, uid, srq->uid);
-
-	return  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in),
-			      xrcsrq_out, sizeof(xrcsrq_out));
-}
-
-static int query_xrc_srq_cmd(struct mlx5_core_dev *dev,
-			     struct mlx5_core_srq *srq,
-			     struct mlx5_srq_attr *out)
-{
-	u32 xrcsrq_in[MLX5_ST_SZ_DW(query_xrc_srq_in)];
-	u32 *xrcsrq_out;
-	void *xrc_srqc;
-	int err;
-
-	xrcsrq_out = kvzalloc(MLX5_ST_SZ_BYTES(query_xrc_srq_out), GFP_KERNEL);
-	if (!xrcsrq_out)
-		return -ENOMEM;
-	memset(xrcsrq_in, 0, sizeof(xrcsrq_in));
-
-	MLX5_SET(query_xrc_srq_in, xrcsrq_in, opcode,
-		 MLX5_CMD_OP_QUERY_XRC_SRQ);
-	MLX5_SET(query_xrc_srq_in, xrcsrq_in, xrc_srqn, srq->srqn);
-
-	err =  mlx5_cmd_exec(dev, xrcsrq_in, sizeof(xrcsrq_in), xrcsrq_out,
-			     MLX5_ST_SZ_BYTES(query_xrc_srq_out));
-	if (err)
-		goto out;
-
-	xrc_srqc = MLX5_ADDR_OF(query_xrc_srq_out, xrcsrq_out,
-				xrc_srq_context_entry);
-	get_srqc(xrc_srqc, out);
-	if (MLX5_GET(xrc_srqc, xrc_srqc, state) != MLX5_XRC_SRQC_STATE_GOOD)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-
-out:
-	kvfree(xrcsrq_out);
-	return err;
-}
-
-static int create_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			  struct mlx5_srq_attr *in)
-{
-	void *create_in;
-	void *rmpc;
-	void *wq;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size = get_pas_size(in);
-	inlen = MLX5_ST_SZ_BYTES(create_rmp_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	rmpc = MLX5_ADDR_OF(create_rmp_in, create_in, ctx);
-	wq = MLX5_ADDR_OF(rmpc, rmpc, wq);
-
-	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
-	MLX5_SET(create_rmp_in, create_in, uid, in->uid);
-	set_wq(wq, in);
-	memcpy(MLX5_ADDR_OF(rmpc, rmpc, wq.pas), in->pas, pas_size);
-
-	err = mlx5_core_create_rmp(dev, create_in, inlen, &srq->srqn);
-	if (!err)
-		srq->uid = in->uid;
-
-	kvfree(create_in);
-	return err;
-}
-
-static int destroy_rmp_cmd(struct mlx5_core_dev *dev,
-			   struct mlx5_core_srq *srq)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)]   = {};
-	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {};
-
-	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
-	MLX5_SET(destroy_rmp_in, in, rmpn, srq->srqn);
-	MLX5_SET(destroy_rmp_in, in, uid, srq->uid);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int arm_rmp_cmd(struct mlx5_core_dev *dev,
-		       struct mlx5_core_srq *srq,
-		       u16 lwm)
-{
-	void *in;
-	void *rmpc;
-	void *wq;
-	void *bitmask;
-	int err;
-
-	in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	rmpc =	  MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
-	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
-	wq   =	  MLX5_ADDR_OF(rmpc,	        rmpc, wq);
-
-	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
-	MLX5_SET(modify_rmp_in, in,	 rmpn,      srq->srqn);
-	MLX5_SET(modify_rmp_in, in, uid, srq->uid);
-	MLX5_SET(wq,		wq,	 lwm,	    lwm);
-	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
-	MLX5_SET(rmpc, rmpc, state, MLX5_RMPC_STATE_RDY);
-
-	err = mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
-
-	kvfree(in);
-	return err;
-}
-
-static int query_rmp_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *out)
-{
-	u32 *rmp_out;
-	void *rmpc;
-	int err;
-
-	rmp_out =  kvzalloc(MLX5_ST_SZ_BYTES(query_rmp_out), GFP_KERNEL);
-	if (!rmp_out)
-		return -ENOMEM;
-
-	err = mlx5_core_query_rmp(dev, srq->srqn, rmp_out);
-	if (err)
-		goto out;
-
-	rmpc = MLX5_ADDR_OF(query_rmp_out, rmp_out, rmp_context);
-	get_wq(MLX5_ADDR_OF(rmpc, rmpc, wq), out);
-	if (MLX5_GET(rmpc, rmpc, state) != MLX5_RMPC_STATE_RDY)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-
-out:
-	kvfree(rmp_out);
-	return err;
-}
-
-static int create_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			  struct mlx5_srq_attr *in)
-{
-	u32 create_out[MLX5_ST_SZ_DW(create_xrq_out)] = {0};
-	void *create_in;
-	void *xrqc;
-	void *wq;
-	int pas_size;
-	int inlen;
-	int err;
-
-	pas_size = get_pas_size(in);
-	inlen = MLX5_ST_SZ_BYTES(create_xrq_in) + pas_size;
-	create_in = kvzalloc(inlen, GFP_KERNEL);
-	if (!create_in)
-		return -ENOMEM;
-
-	xrqc = MLX5_ADDR_OF(create_xrq_in, create_in, xrq_context);
-	wq = MLX5_ADDR_OF(xrqc, xrqc, wq);
-
-	set_wq(wq, in);
-	memcpy(MLX5_ADDR_OF(xrqc, xrqc, wq.pas), in->pas, pas_size);
-
-	if (in->type == IB_SRQT_TM) {
-		MLX5_SET(xrqc, xrqc, topology, MLX5_XRQC_TOPOLOGY_TAG_MATCHING);
-		if (in->flags & MLX5_SRQ_FLAG_RNDV)
-			MLX5_SET(xrqc, xrqc, offload, MLX5_XRQC_OFFLOAD_RNDV);
-		MLX5_SET(xrqc, xrqc,
-			 tag_matching_topology_context.log_matching_list_sz,
-			 in->tm_log_list_size);
-	}
-	MLX5_SET(xrqc, xrqc, user_index, in->user_index);
-	MLX5_SET(xrqc, xrqc, cqn, in->cqn);
-	MLX5_SET(create_xrq_in, create_in, opcode, MLX5_CMD_OP_CREATE_XRQ);
-	MLX5_SET(create_xrq_in, create_in, uid, in->uid);
-	err = mlx5_cmd_exec(dev, create_in, inlen, create_out,
-			    sizeof(create_out));
-	kvfree(create_in);
-	if (!err) {
-		srq->srqn = MLX5_GET(create_xrq_out, create_out, xrqn);
-		srq->uid = in->uid;
-	}
-
-	return err;
-}
-
-static int destroy_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_xrq_in)] = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_xrq_out)] = {0};
-
-	MLX5_SET(destroy_xrq_in, in, opcode, MLX5_CMD_OP_DESTROY_XRQ);
-	MLX5_SET(destroy_xrq_in, in, xrqn,   srq->srqn);
-	MLX5_SET(destroy_xrq_in, in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int arm_xrq_cmd(struct mlx5_core_dev *dev,
-		       struct mlx5_core_srq *srq,
-		       u16 lwm)
-{
-	u32 out[MLX5_ST_SZ_DW(arm_rq_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(arm_rq_in)] = {0};
-
-	MLX5_SET(arm_rq_in, in, opcode,     MLX5_CMD_OP_ARM_RQ);
-	MLX5_SET(arm_rq_in, in, op_mod,     MLX5_ARM_RQ_IN_OP_MOD_XRQ);
-	MLX5_SET(arm_rq_in, in, srq_number, srq->srqn);
-	MLX5_SET(arm_rq_in, in, lwm,	    lwm);
-	MLX5_SET(arm_rq_in, in, uid, srq->uid);
-
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-static int query_xrq_cmd(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *out)
-{
-	u32 in[MLX5_ST_SZ_DW(query_xrq_in)] = {0};
-	u32 *xrq_out;
-	int outlen = MLX5_ST_SZ_BYTES(query_xrq_out);
-	void *xrqc;
-	int err;
-
-	xrq_out = kvzalloc(outlen, GFP_KERNEL);
-	if (!xrq_out)
-		return -ENOMEM;
-
-	MLX5_SET(query_xrq_in, in, opcode, MLX5_CMD_OP_QUERY_XRQ);
-	MLX5_SET(query_xrq_in, in, xrqn, srq->srqn);
-
-	err = mlx5_cmd_exec(dev, in, sizeof(in), xrq_out, outlen);
-	if (err)
-		goto out;
-
-	xrqc = MLX5_ADDR_OF(query_xrq_out, xrq_out, xrq_context);
-	get_wq(MLX5_ADDR_OF(xrqc, xrqc, wq), out);
-	if (MLX5_GET(xrqc, xrqc, state) != MLX5_XRQC_STATE_GOOD)
-		out->flags |= MLX5_SRQ_FLAG_ERR;
-	out->tm_next_tag =
-		MLX5_GET(xrqc, xrqc,
-			 tag_matching_topology_context.append_next_index);
-	out->tm_hw_phase_cnt =
-		MLX5_GET(xrqc, xrqc,
-			 tag_matching_topology_context.hw_phase_cnt);
-	out->tm_sw_phase_cnt =
-		MLX5_GET(xrqc, xrqc,
-			 tag_matching_topology_context.sw_phase_cnt);
-
-out:
-	kvfree(xrq_out);
-	return err;
-}
-
-static int create_srq_split(struct mlx5_core_dev *dev,
-			    struct mlx5_core_srq *srq,
-			    struct mlx5_srq_attr *in)
-{
-	if (!dev->issi)
-		return create_srq_cmd(dev, srq, in);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return create_xrc_srq_cmd(dev, srq, in);
-	case MLX5_RES_XRQ:
-		return create_xrq_cmd(dev, srq, in);
-	default:
-		return create_rmp_cmd(dev, srq, in);
-	}
-}
-
-static int destroy_srq_split(struct mlx5_core_dev *dev,
-			     struct mlx5_core_srq *srq)
-{
-	if (!dev->issi)
-		return destroy_srq_cmd(dev, srq);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return destroy_xrc_srq_cmd(dev, srq);
-	case MLX5_RES_XRQ:
-		return destroy_xrq_cmd(dev, srq);
-	default:
-		return destroy_rmp_cmd(dev, srq);
-	}
-}
-
-int mlx5_core_create_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			 struct mlx5_srq_attr *in)
-{
-	int err;
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-
-	switch (in->type) {
-	case IB_SRQT_XRC:
-		srq->common.res = MLX5_RES_XSRQ;
-		break;
-	case IB_SRQT_TM:
-		srq->common.res = MLX5_RES_XRQ;
-		break;
-	default:
-		srq->common.res = MLX5_RES_SRQ;
-	}
-
-	err = create_srq_split(dev, srq, in);
-	if (err)
-		return err;
-
-	atomic_set(&srq->refcount, 1);
-	init_completion(&srq->free);
-
-	spin_lock_irq(&table->lock);
-	err = radix_tree_insert(&table->tree, srq->srqn, srq);
-	spin_unlock_irq(&table->lock);
-	if (err) {
-		mlx5_core_warn(dev, "err %d, srqn 0x%x\n", err, srq->srqn);
-		goto err_destroy_srq_split;
-	}
-
-	return 0;
-
-err_destroy_srq_split:
-	destroy_srq_split(dev, srq);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_create_srq);
-
-int mlx5_core_destroy_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-	struct mlx5_core_srq *tmp;
-	int err;
-
-	spin_lock_irq(&table->lock);
-	tmp = radix_tree_delete(&table->tree, srq->srqn);
-	spin_unlock_irq(&table->lock);
-	if (!tmp) {
-		mlx5_core_warn(dev, "srq 0x%x not found in tree\n", srq->srqn);
-		return -EINVAL;
-	}
-	if (tmp != srq) {
-		mlx5_core_warn(dev, "corruption on srqn 0x%x\n", srq->srqn);
-		return -EINVAL;
-	}
-
-	err = destroy_srq_split(dev, srq);
-	if (err)
-		return err;
-
-	if (atomic_dec_and_test(&srq->refcount))
-		complete(&srq->free);
-	wait_for_completion(&srq->free);
-
-	return 0;
-}
-EXPORT_SYMBOL(mlx5_core_destroy_srq);
-
-int mlx5_core_query_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-			struct mlx5_srq_attr *out)
-{
-	if (!dev->issi)
-		return query_srq_cmd(dev, srq, out);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return query_xrc_srq_cmd(dev, srq, out);
-	case MLX5_RES_XRQ:
-		return query_xrq_cmd(dev, srq, out);
-	default:
-		return query_rmp_cmd(dev, srq, out);
-	}
-}
-EXPORT_SYMBOL(mlx5_core_query_srq);
-
-int mlx5_core_arm_srq(struct mlx5_core_dev *dev, struct mlx5_core_srq *srq,
-		      u16 lwm, int is_srq)
-{
-	if (!dev->issi)
-		return arm_srq_cmd(dev, srq, lwm, is_srq);
-	switch (srq->common.res) {
-	case MLX5_RES_XSRQ:
-		return arm_xrc_srq_cmd(dev, srq, lwm);
-	case MLX5_RES_XRQ:
-		return arm_xrq_cmd(dev, srq, lwm);
-	default:
-		return arm_rmp_cmd(dev, srq, lwm);
-	}
-}
-EXPORT_SYMBOL(mlx5_core_arm_srq);
-
-void mlx5_init_srq_table(struct mlx5_core_dev *dev)
-{
-	struct mlx5_srq_table *table = &dev->priv.srq_table;
-
-	memset(table, 0, sizeof(*table));
-	spin_lock_init(&table->lock);
-	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
-}
-
-void mlx5_cleanup_srq_table(struct mlx5_core_dev *dev)
-{
-	/* nothing */
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
index a1ee9a8a769e..c4d4b76096dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c
@@ -258,115 +258,6 @@ void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn)
 }
 EXPORT_SYMBOL(mlx5_core_destroy_tis);
 
-int mlx5_core_create_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			 u32 *rmpn)
-{
-	u32 out[MLX5_ST_SZ_DW(create_rmp_out)] = {0};
-	int err;
-
-	MLX5_SET(create_rmp_in, in, opcode, MLX5_CMD_OP_CREATE_RMP);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-	if (!err)
-		*rmpn = MLX5_GET(create_rmp_out, out, rmpn);
-
-	return err;
-}
-
-int mlx5_core_modify_rmp(struct mlx5_core_dev *dev, u32 *in, int inlen)
-{
-	u32 out[MLX5_ST_SZ_DW(modify_rmp_out)] = {0};
-
-	MLX5_SET(modify_rmp_in, in, opcode, MLX5_CMD_OP_MODIFY_RMP);
-	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-}
-
-int mlx5_core_destroy_rmp(struct mlx5_core_dev *dev, u32 rmpn)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_rmp_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_rmp_out)] = {0};
-
-	MLX5_SET(destroy_rmp_in, in, opcode, MLX5_CMD_OP_DESTROY_RMP);
-	MLX5_SET(destroy_rmp_in, in, rmpn, rmpn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out,
-					  sizeof(out));
-}
-
-int mlx5_core_query_rmp(struct mlx5_core_dev *dev, u32 rmpn, u32 *out)
-{
-	u32 in[MLX5_ST_SZ_DW(query_rmp_in)] = {0};
-	int outlen = MLX5_ST_SZ_BYTES(query_rmp_out);
-
-	MLX5_SET(query_rmp_in, in, opcode, MLX5_CMD_OP_QUERY_RMP);
-	MLX5_SET(query_rmp_in, in, rmpn,   rmpn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
-}
-
-int mlx5_core_arm_rmp(struct mlx5_core_dev *dev, u32 rmpn, u16 lwm)
-{
-	void *in;
-	void *rmpc;
-	void *wq;
-	void *bitmask;
-	int  err;
-
-	in = kvzalloc(MLX5_ST_SZ_BYTES(modify_rmp_in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	rmpc    = MLX5_ADDR_OF(modify_rmp_in,   in,   ctx);
-	bitmask = MLX5_ADDR_OF(modify_rmp_in,   in,   bitmask);
-	wq      = MLX5_ADDR_OF(rmpc,	        rmpc, wq);
-
-	MLX5_SET(modify_rmp_in, in,	 rmp_state, MLX5_RMPC_STATE_RDY);
-	MLX5_SET(modify_rmp_in, in,	 rmpn,      rmpn);
-	MLX5_SET(wq,		wq,	 lwm,	    lwm);
-	MLX5_SET(rmp_bitmask,	bitmask, lwm,	    1);
-	MLX5_SET(rmpc,		rmpc,	 state,	    MLX5_RMPC_STATE_RDY);
-
-	err =  mlx5_core_modify_rmp(dev, in, MLX5_ST_SZ_BYTES(modify_rmp_in));
-
-	kvfree(in);
-
-	return err;
-}
-
-int mlx5_core_create_xsrq(struct mlx5_core_dev *dev, u32 *in, int inlen,
-			  u32 *xsrqn)
-{
-	u32 out[MLX5_ST_SZ_DW(create_xrc_srq_out)] = {0};
-	int err;
-
-	MLX5_SET(create_xrc_srq_in, in, opcode,     MLX5_CMD_OP_CREATE_XRC_SRQ);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
-	if (!err)
-		*xsrqn = MLX5_GET(create_xrc_srq_out, out, xrc_srqn);
-
-	return err;
-}
-
-int mlx5_core_destroy_xsrq(struct mlx5_core_dev *dev, u32 xsrqn)
-{
-	u32 in[MLX5_ST_SZ_DW(destroy_xrc_srq_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(destroy_xrc_srq_out)] = {0};
-
-	MLX5_SET(destroy_xrc_srq_in, in, opcode,   MLX5_CMD_OP_DESTROY_XRC_SRQ);
-	MLX5_SET(destroy_xrc_srq_in, in, xrc_srqn, xsrqn);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
-int mlx5_core_arm_xsrq(struct mlx5_core_dev *dev, u32 xsrqn, u16 lwm)
-{
-	u32 in[MLX5_ST_SZ_DW(arm_xrc_srq_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(arm_xrc_srq_out)] = {0};
-
-	MLX5_SET(arm_xrc_srq_in, in, opcode,   MLX5_CMD_OP_ARM_XRC_SRQ);
-	MLX5_SET(arm_xrc_srq_in, in, xrc_srqn, xsrqn);
-	MLX5_SET(arm_xrc_srq_in, in, lwm,      lwm);
-	MLX5_SET(arm_xrc_srq_in, in, op_mod,
-		 MLX5_ARM_XRC_SRQ_IN_OP_MOD_XRC_SRQ);
-	return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
-}
-
 int mlx5_core_create_rqt(struct mlx5_core_dev *dev, u32 *in, int inlen,
 			 u32 *rqtn)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/uar.c b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
index 8b97066dd1f1..94464723ff77 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/uar.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/uar.c
@@ -90,8 +90,8 @@ static void up_rel_func(struct kref *kref)
 	iounmap(up->map);
 	if (mlx5_cmd_free_uar(up->mdev, up->index))
 		mlx5_core_warn(up->mdev, "failed to free uar index %d\n", up->index);
-	kfree(up->reg_bitmap);
-	kfree(up->fp_bitmap);
+	bitmap_free(up->reg_bitmap);
+	bitmap_free(up->fp_bitmap);
 	kfree(up);
 }
 
@@ -110,11 +110,11 @@ static struct mlx5_uars_page *alloc_uars_page(struct mlx5_core_dev *mdev,
 		return ERR_PTR(err);
 
 	up->mdev = mdev;
-	up->reg_bitmap = kcalloc(BITS_TO_LONGS(bfregs), sizeof(unsigned long), GFP_KERNEL);
+	up->reg_bitmap = bitmap_zalloc(bfregs, GFP_KERNEL);
 	if (!up->reg_bitmap)
 		goto error1;
 
-	up->fp_bitmap = kcalloc(BITS_TO_LONGS(bfregs), sizeof(unsigned long), GFP_KERNEL);
+	up->fp_bitmap = bitmap_zalloc(bfregs, GFP_KERNEL);
 	if (!up->fp_bitmap)
 		goto error1;
 
@@ -157,8 +157,8 @@ error2:
 	if (mlx5_cmd_free_uar(mdev, up->index))
 		mlx5_core_warn(mdev, "failed to free uar index %d\n", up->index);
 error1:
-	kfree(up->fp_bitmap);
-	kfree(up->reg_bitmap);
+	bitmap_free(up->fp_bitmap);
+	bitmap_free(up->reg_bitmap);
 	kfree(up);
 	return ERR_PTR(err);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index cfbea66b4879..ef95feca9961 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -64,7 +64,7 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 }
 
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
-				  u16 vport, u8 state)
+				  u16 vport, u8 other_vport, u8 state)
 {
 	u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(modify_vport_state_out)] = {0};
@@ -73,8 +73,7 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 		 MLX5_CMD_OP_MODIFY_VPORT_STATE);
 	MLX5_SET(modify_vport_state_in, in, op_mod, opmod);
 	MLX5_SET(modify_vport_state_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(modify_vport_state_in, in, other_vport, 1);
+	MLX5_SET(modify_vport_state_in, in, other_vport, other_vport);
 	MLX5_SET(modify_vport_state_in, in, admin_state, state);
 
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
@@ -255,7 +254,7 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu)
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu);
 
 int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
-				  u32 vport,
+				  u16 vport,
 				  enum mlx5_list_type list_type,
 				  u8 addr_list[][ETH_ALEN],
 				  int *list_size)
@@ -373,7 +372,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev,
 EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list);
 
 int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev,
-			       u32 vport,
+			       u16 vport,
 			       u16 vlans[],
 			       int *size)
 {
@@ -526,7 +525,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid);
 
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
-				    u32 vport, u64 node_guid)
+				    u16 vport, u64 node_guid)
 {
 	int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in);
 	void *nic_vport_context;
@@ -827,7 +826,7 @@ int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev,
 EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid);
 
 int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev,
-				 u32 vport,
+				 u16 vport,
 				 int *promisc_uc,
 				 int *promisc_mc,
 				 int *promisc_all)
@@ -1057,7 +1056,7 @@ free:
 EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter);
 
 int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
-				u64 *rx_discard_vport_down,
+				u8 other_vport, u64 *rx_discard_vport_down,
 				u64 *tx_discard_vport_down)
 {
 	u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0};
@@ -1068,8 +1067,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport,
 		 MLX5_CMD_OP_QUERY_VNIC_ENV);
 	MLX5_SET(query_vnic_env_in, in, op_mod, 0);
 	MLX5_SET(query_vnic_env_in, in, vport_number, vport);
-	if (vport)
-		MLX5_SET(query_vnic_env_in, in, other_vport, 1);
+	MLX5_SET(query_vnic_env_in, in, other_vport, other_vport);
 
 	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (err)
@@ -1204,9 +1202,19 @@ EXPORT_SYMBOL_GPL(mlx5_nic_vport_unaffiliate_multiport);
 
 u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev)
 {
-	if (!mdev->sys_image_guid)
-		mlx5_query_nic_vport_system_image_guid(mdev, &mdev->sys_image_guid);
+	int port_type_cap = MLX5_CAP_GEN(mdev, port_type);
+	u64 tmp = 0;
+
+	if (mdev->sys_image_guid)
+		return mdev->sys_image_guid;
+
+	if (port_type_cap == MLX5_CAP_PORT_TYPE_ETH)
+		mlx5_query_nic_vport_system_image_guid(mdev, &tmp);
+	else
+		mlx5_query_hca_vport_system_image_guid(mdev, &tmp);
+
+	mdev->sys_image_guid = tmp;
 
-	return mdev->sys_image_guid;
+	return tmp;
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index 2dcbf1ebfd6a..953cc8efba69 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -155,7 +155,8 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
 		     struct mlx5_wq_ctrl *wq_ctrl)
 {
-	u8 log_wq_stride = MLX5_GET(cqc, cqc, cqe_sz) + 6;
+	/* CQE_STRIDE_128 and CQE_STRIDE_128_PAD both mean 128B stride */
+	u8 log_wq_stride = MLX5_GET(cqc, cqc, cqe_sz) == CQE_STRIDE_64 ? 6 : 7;
 	u8 log_wq_sz     = MLX5_GET(cqc, cqc, log_cq_size);
 	int err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index b1293d153a58..ea934a48c90a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -177,9 +177,14 @@ static inline u32 mlx5_cqwq_get_ci(struct mlx5_cqwq *wq)
 	return mlx5_cqwq_ctr2ix(wq, wq->cc);
 }
 
-static inline void *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
+static inline struct mlx5_cqe64 *mlx5_cqwq_get_wqe(struct mlx5_cqwq *wq, u32 ix)
 {
-	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
+	struct mlx5_cqe64 *cqe = mlx5_frag_buf_get_wqe(&wq->fbc, ix);
+
+	/* For 128B CQEs the data is in the last 64B */
+	cqe += wq->fbc.log_stride == 7;
+
+	return cqe;
 }
 
 static inline u32 mlx5_cqwq_get_ctr_wrap_cnt(struct mlx5_cqwq *wq, u32 ctr)
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
index 7a712b6b09ec..14c0c62f8e73 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_H
 #define _MLXFW_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
index 2cf89126fb23..240c027e5f07 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_fsm.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #define pr_fmt(fmt) "mlxfw: " fmt
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
index 993cb5ba934e..544344ac4894 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #define pr_fmt(fmt) "mlxfw_mfa2: " fmt
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
index 20472aa139cd..5bba6ad79d34 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_MFA2_H
 #define _MLXFW_MFA2_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
index f667942b1ea3..874c0a2474ae 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_file.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_MFA2_FILE_H
 #define _MLXFW_MFA2_FILE_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
index dd66737c033d..b001e5258091 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
@@ -1,36 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_format.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXFW_MFA2_FORMAT_H
 #define _MLXFW_MFA2_FORMAT_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
index cc013e77b326..33c971190bba 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXFW_MFA2_TLV_H
 #define _MLXFW_MFA2_TLV_H
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
index 0094b92a233b..017d68f1e123 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
 
 #define pr_fmt(fmt) "MFA2: " fmt
 
diff --git a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
index 2c667894f3a2..633284eeded7 100644
--- a/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
+++ b/drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
@@ -1,36 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxfw/mlxfw_mfa2_tlv_multi.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2019 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXFW_MFA2_TLV_MULTI_H
 #define _MLXFW_MFA2_TLV_MULTI_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 8a291eb36c64..9c195dfed031 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -4,7 +4,6 @@
 
 config MLXSW_CORE
 	tristate "Mellanox Technologies Switch ASICs support"
-	depends on MAY_USE_DEVLINK
 	---help---
 	  This driver supports Mellanox Technologies Switch ASICs family.
 
@@ -78,8 +77,10 @@ config MLXSW_SPECTRUM
 	depends on IPV6 || IPV6=n
 	depends on NET_IPGRE || NET_IPGRE=n
 	depends on IPV6_GRE || IPV6_GRE=n
+	depends on VXLAN || VXLAN=n
 	select GENERIC_ALLOCATOR
 	select PARMAN
+	select OBJAGG
 	select MLXFW
 	default m
 	---help---
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 1f77e97e2d7a..a01d15546e37 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_MLXSW_CORE)	+= mlxsw_core.o
 mlxsw_core-objs			:= core.o core_acl_flex_keys.o \
-				   core_acl_flex_actions.o
+				   core_acl_flex_actions.o core_env.o
 mlxsw_core-$(CONFIG_MLXSW_CORE_HWMON) += core_hwmon.o
 mlxsw_core-$(CONFIG_MLXSW_CORE_THERMAL) += core_thermal.o
 obj-$(CONFIG_MLXSW_PCI)		+= mlxsw_pci.o
@@ -20,7 +20,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
 				   spectrum_acl_atcam.o spectrum_acl_erp.o \
 				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
-				   spectrum_acl.o \
+				   spectrum_acl_bloom_filter.o spectrum_acl.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f7154f358f27..f26a4ca29363 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -568,7 +568,7 @@ static int mlxsw_emad_init(struct mlxsw_core *mlxsw_core)
 	if (!(mlxsw_core->bus->features & MLXSW_BUS_F_TXRX))
 		return 0;
 
-	emad_wq = alloc_workqueue("mlxsw_core_emad", WQ_MEM_RECLAIM, 0);
+	emad_wq = alloc_workqueue("mlxsw_core_emad", 0, 0);
 	if (!emad_wq)
 		return -ENOMEM;
 	mlxsw_core->emad_wq = emad_wq;
@@ -970,10 +970,11 @@ static const struct devlink_ops mlxsw_devlink_ops = {
 	.sb_occ_tc_port_bind_get	= mlxsw_devlink_sb_occ_tc_port_bind_get,
 };
 
-int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
-				   const struct mlxsw_bus *mlxsw_bus,
-				   void *bus_priv, bool reload,
-				   struct devlink *devlink)
+static int
+__mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
+				 const struct mlxsw_bus *mlxsw_bus,
+				 void *bus_priv, bool reload,
+				 struct devlink *devlink)
 {
 	const char *device_kind = mlxsw_bus_info->device_kind;
 	struct mlxsw_core *mlxsw_core;
@@ -1040,6 +1041,12 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 			goto err_devlink_register;
 	}
 
+	if (mlxsw_driver->params_register && !reload) {
+		err = mlxsw_driver->params_register(mlxsw_core);
+		if (err)
+			goto err_register_params;
+	}
+
 	err = mlxsw_hwmon_init(mlxsw_core, mlxsw_bus_info, &mlxsw_core->hwmon);
 	if (err)
 		goto err_hwmon_init;
@@ -1055,6 +1062,9 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 			goto err_driver_init;
 	}
 
+	if (mlxsw_driver->params_register && !reload)
+		devlink_params_publish(devlink);
+
 	return 0;
 
 err_driver_init:
@@ -1062,6 +1072,9 @@ err_driver_init:
 err_thermal_init:
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 err_hwmon_init:
+	if (mlxsw_driver->params_unregister && !reload)
+		mlxsw_driver->params_unregister(mlxsw_core);
+err_register_params:
 	if (!reload)
 		devlink_unregister(devlink);
 err_devlink_register:
@@ -1081,6 +1094,29 @@ err_bus_init:
 err_devlink_alloc:
 	return err;
 }
+
+int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
+				   const struct mlxsw_bus *mlxsw_bus,
+				   void *bus_priv, bool reload,
+				   struct devlink *devlink)
+{
+	bool called_again = false;
+	int err;
+
+again:
+	err = __mlxsw_core_bus_device_register(mlxsw_bus_info, mlxsw_bus,
+					       bus_priv, reload, devlink);
+	/* -EAGAIN is returned in case the FW was updated. FW needs
+	 * a reset, so lets try to call __mlxsw_core_bus_device_register()
+	 * again.
+	 */
+	if (err == -EAGAIN && !called_again) {
+		called_again = true;
+		goto again;
+	}
+
+	return err;
+}
 EXPORT_SYMBOL(mlxsw_core_bus_device_register);
 
 void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
@@ -1098,10 +1134,14 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 			return;
 	}
 
+	if (mlxsw_core->driver->params_unregister && !reload)
+		devlink_params_unpublish(devlink);
 	if (mlxsw_core->driver->fini)
 		mlxsw_core->driver->fini(mlxsw_core);
 	mlxsw_thermal_fini(mlxsw_core->thermal);
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
+	if (mlxsw_core->driver->params_unregister && !reload)
+		mlxsw_core->driver->params_unregister(mlxsw_core);
 	if (!reload)
 		devlink_unregister(devlink);
 	mlxsw_emad_fini(mlxsw_core);
@@ -1114,6 +1154,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 	return;
 
 reload_fail_deinit:
+	if (mlxsw_core->driver->params_unregister)
+		mlxsw_core->driver->params_unregister(mlxsw_core);
 	devlink_unregister(devlink);
 	devlink_resources_unregister(devlink, NULL);
 	devlink_free(devlink);
@@ -1423,13 +1465,17 @@ static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans)
 	if (trans->retries)
 		dev_warn(mlxsw_core->bus_info->dev, "EMAD retries (%d/%d) (tid=%llx)\n",
 			 trans->retries, MLXSW_EMAD_MAX_RETRY, trans->tid);
-	if (err)
+	if (err) {
 		dev_err(mlxsw_core->bus_info->dev, "EMAD reg access failed (tid=%llx,reg_id=%x(%s),type=%s,status=%x(%s))\n",
 			trans->tid, trans->reg->id,
 			mlxsw_reg_id_str(trans->reg->id),
 			mlxsw_core_reg_access_type_str(trans->type),
 			trans->emad_status,
 			mlxsw_emad_op_tlv_status_str(trans->emad_status));
+		trace_devlink_hwerr(priv_to_devlink(mlxsw_core),
+				    trans->emad_status,
+				    mlxsw_emad_op_tlv_status_str(trans->emad_status));
+	}
 
 	list_del(&trans->bulk_list);
 	kfree_rcu(trans, rcu);
@@ -1871,14 +1917,51 @@ void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core)
 }
 EXPORT_SYMBOL(mlxsw_core_fw_flash_end);
 
+int mlxsw_core_resources_query(struct mlxsw_core *mlxsw_core, char *mbox,
+			       struct mlxsw_res *res)
+{
+	int index, i;
+	u64 data;
+	u16 id;
+	int err;
+
+	if (!res)
+		return 0;
+
+	mlxsw_cmd_mbox_zero(mbox);
+
+	for (index = 0; index < MLXSW_CMD_QUERY_RESOURCES_MAX_QUERIES;
+	     index++) {
+		err = mlxsw_cmd_query_resources(mlxsw_core, mbox, index);
+		if (err)
+			return err;
+
+		for (i = 0; i < MLXSW_CMD_QUERY_RESOURCES_PER_QUERY; i++) {
+			id = mlxsw_cmd_mbox_query_resource_id_get(mbox, i);
+			data = mlxsw_cmd_mbox_query_resource_data_get(mbox, i);
+
+			if (id == MLXSW_CMD_QUERY_RESOURCES_TABLE_END_ID)
+				return 0;
+
+			mlxsw_res_parse(res, id, data);
+		}
+	}
+
+	/* If after MLXSW_RESOURCES_QUERY_MAX_QUERIES we still didn't get
+	 * MLXSW_RESOURCES_TABLE_END_ID, something went bad in the FW.
+	 */
+	return -EIO;
+}
+EXPORT_SYMBOL(mlxsw_core_resources_query);
+
 static int __init mlxsw_core_module_init(void)
 {
 	int err;
 
-	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, WQ_MEM_RECLAIM, 0);
+	mlxsw_wq = alloc_workqueue(mlxsw_core_driver_name, 0, 0);
 	if (!mlxsw_wq)
 		return -ENOMEM;
-	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", WQ_MEM_RECLAIM,
+	mlxsw_owq = alloc_ordered_workqueue("%s_ordered", 0,
 					    mlxsw_core_driver_name);
 	if (!mlxsw_owq) {
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index c4e4971764e5..8ec53f027575 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -182,6 +182,8 @@ int mlxsw_core_port_get_phys_port_name(struct mlxsw_core *mlxsw_core,
 int mlxsw_core_schedule_dw(struct delayed_work *dwork, unsigned long delay);
 bool mlxsw_core_schedule_work(struct work_struct *work);
 void mlxsw_core_flush_owq(void);
+int mlxsw_core_resources_query(struct mlxsw_core *mlxsw_core, char *mbox,
+			       struct mlxsw_res *res);
 
 #define MLXSW_CONFIG_PROFILE_SWID_COUNT 8
 
@@ -282,6 +284,8 @@ struct mlxsw_driver {
 			     const struct mlxsw_config_profile *profile,
 			     u64 *p_single_size, u64 *p_double_size,
 			     u64 *p_linear_size);
+	int (*params_register)(struct mlxsw_core *mlxsw_core);
+	void (*params_unregister)(struct mlxsw_core *mlxsw_core);
 	u8 txhdr_len;
 	const struct mlxsw_config_profile *profile;
 	bool res_query_enabled;
@@ -342,6 +346,7 @@ struct mlxsw_bus_info {
 	struct mlxsw_fw_rev fw_rev;
 	u8 vsd[MLXSW_CMD_BOARDINFO_VSD_LEN];
 	u8 psid[MLXSW_CMD_BOARDINFO_PSID_LEN];
+	u8 low_frequency;
 };
 
 struct mlxsw_hwmon;
@@ -392,4 +397,9 @@ static inline void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 
 #endif
 
+enum mlxsw_devlink_param_id {
+	MLXSW_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
+};
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 785bf01fe2be..cb3e663b1d37 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -236,12 +236,10 @@ mlxsw_afk_key_info_create(struct mlxsw_afk *mlxsw_afk,
 			  struct mlxsw_afk_element_usage *elusage)
 {
 	struct mlxsw_afk_key_info *key_info;
-	size_t alloc_size;
 	int err;
 
-	alloc_size = sizeof(*key_info) +
-		     sizeof(key_info->blocks[0]) * mlxsw_afk->max_blocks;
-	key_info = kzalloc(alloc_size, GFP_KERNEL);
+	key_info = kzalloc(struct_size(key_info, blocks, mlxsw_afk->max_blocks),
+			   GFP_KERNEL);
 	if (!key_info)
 		return ERR_PTR(-ENOMEM);
 	err = mlxsw_afk_picker(mlxsw_afk, key_info, elusage);
@@ -426,15 +424,17 @@ mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask, int block_start, int block_end)
+		      char *key, char *mask)
 {
+	unsigned int blocks_count =
+			mlxsw_afk_key_info_blocks_count_get(key_info);
 	char block_mask[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	char block_key[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	const struct mlxsw_afk_element_inst *elinst;
 	enum mlxsw_afk_element element;
 	int block_index, i;
 
-	for (i = block_start; i <= block_end; i++) {
+	for (i = 0; i < blocks_count; i++) {
 		memset(block_key, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
 		memset(block_mask, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
 
@@ -451,10 +451,18 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 						values->storage.mask);
 		}
 
-		if (key)
-			mlxsw_afk->ops->encode_block(block_key, i, key);
-		if (mask)
-			mlxsw_afk->ops->encode_block(block_mask, i, mask);
+		mlxsw_afk->ops->encode_block(key, i, block_key);
+		mlxsw_afk->ops->encode_block(mask, i, block_mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
+
+void mlxsw_afk_clear(struct mlxsw_afk *mlxsw_afk, char *key,
+		     int block_start, int block_end)
+{
+	int i;
+
+	for (i = block_start; i <= block_end; i++)
+		mlxsw_afk->ops->clear_block(key, i);
+}
+EXPORT_SYMBOL(mlxsw_afk_clear);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index c29c045d826d..4a625cdf3e7c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -33,6 +33,8 @@ enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_IP_TTL_,
 	MLXSW_AFK_ELEMENT_IP_ECN,
 	MLXSW_AFK_ELEMENT_IP_DSCP,
+	MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+	MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
 	MLXSW_AFK_ELEMENT_MAX,
 };
 
@@ -87,6 +89,8 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6),
+	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_8_10, 0x18, 17, 3),
+	MLXSW_AFK_ELEMENT_INFO_U32(VIRT_ROUTER_0_7, 0x18, 20, 8),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4),
@@ -188,7 +192,8 @@ struct mlxsw_afk;
 struct mlxsw_afk_ops {
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
-	void (*encode_block)(char *block, int block_index, char *output);
+	void (*encode_block)(char *output, int block_index, char *block);
+	void (*clear_block)(char *output, int block_index);
 };
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
@@ -228,6 +233,8 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask, int block_start, int block_end);
+		      char *key, char *mask);
+void mlxsw_afk_clear(struct mlxsw_afk *mlxsw_afk, char *key,
+		     int block_start, int block_end);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
new file mode 100644
index 000000000000..c1c1965d7acc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include "core.h"
+#include "core_env.h"
+#include "item.h"
+#include "reg.h"
+
+static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id,
+					  bool *qsfp)
+{
+	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
+	char mcia_pl[MLXSW_REG_MCIA_LEN];
+	u8 ident;
+	int err;
+
+	mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1,
+			    MLXSW_REG_MCIA_I2C_ADDR_LOW);
+	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
+	if (err)
+		return err;
+	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
+	ident = eeprom_tmp[0];
+	switch (ident) {
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
+		*qsfp = false;
+		break;
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD:
+		*qsfp = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+mlxsw_env_query_module_eeprom(struct mlxsw_core *mlxsw_core, int module,
+			      u16 offset, u16 size, void *data,
+			      unsigned int *p_read_size)
+{
+	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
+	char mcia_pl[MLXSW_REG_MCIA_LEN];
+	u16 i2c_addr;
+	int status;
+	int err;
+
+	size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE);
+
+	if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH &&
+	    offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH)
+		/* Cross pages read, read until offset 256 in low page */
+		size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset;
+
+	i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW;
+	if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) {
+		i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH;
+		offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH;
+	}
+
+	mlxsw_reg_mcia_pack(mcia_pl, module, 0, 0, offset, size, i2c_addr);
+
+	err = mlxsw_reg_query(mlxsw_core, MLXSW_REG(mcia), mcia_pl);
+	if (err)
+		return err;
+
+	status = mlxsw_reg_mcia_status_get(mcia_pl);
+	if (status)
+		return -EIO;
+
+	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
+	memcpy(data, eeprom_tmp, size);
+	*p_read_size = size;
+
+	return 0;
+}
+
+int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
+					 int off, int *temp)
+{
+	char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE];
+	union {
+		u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE];
+		u16 temp;
+	} temp_thresh;
+	char mcia_pl[MLXSW_REG_MCIA_LEN] = {0};
+	char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0};
+	u16 module_temp;
+	bool qsfp;
+	int err;
+
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module,
+			    1);
+	err = mlxsw_reg_query(core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err)
+		return err;
+
+	/* Don't read temperature thresholds for module with no valid info. */
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &module_temp, NULL);
+	switch (module_temp) {
+	case MLXSW_REG_MTBR_BAD_SENS_INFO: /* fall-through */
+	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
+	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_INDEX_NA:
+		*temp = 0;
+		return 0;
+	default:
+		/* Do not consider thresholds for zero temperature. */
+		if (MLXSW_REG_MTMP_TEMP_TO_MC(module_temp) == 0) {
+			*temp = 0;
+			return 0;
+		}
+		break;
+	}
+
+	/* Read Free Side Device Temperature Thresholds from page 03h
+	 * (MSB at lower byte address).
+	 * Bytes:
+	 * 128-129 - Temp High Alarm (SFP_TEMP_HIGH_ALARM);
+	 * 130-131 - Temp Low Alarm (SFP_TEMP_LOW_ALARM);
+	 * 132-133 - Temp High Warning (SFP_TEMP_HIGH_WARN);
+	 * 134-135 - Temp Low Warning (SFP_TEMP_LOW_WARN);
+	 */
+
+	/* Validate module identifier value. */
+	err = mlxsw_env_validate_cable_ident(core, module, &qsfp);
+	if (err)
+		return err;
+
+	if (qsfp)
+		mlxsw_reg_mcia_pack(mcia_pl, module, 0,
+				    MLXSW_REG_MCIA_TH_PAGE_NUM,
+				    MLXSW_REG_MCIA_TH_PAGE_OFF + off,
+				    MLXSW_REG_MCIA_TH_ITEM_SIZE,
+				    MLXSW_REG_MCIA_I2C_ADDR_LOW);
+	else
+		mlxsw_reg_mcia_pack(mcia_pl, module, 0,
+				    MLXSW_REG_MCIA_PAGE0_LO,
+				    off, MLXSW_REG_MCIA_TH_ITEM_SIZE,
+				    MLXSW_REG_MCIA_I2C_ADDR_HIGH);
+
+	err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
+	memcpy(temp_thresh.buf, eeprom_tmp, MLXSW_REG_MCIA_TH_ITEM_SIZE);
+	*temp = temp_thresh.temp * 1000;
+
+	return 0;
+}
+
+int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
+			      struct ethtool_modinfo *modinfo)
+{
+	u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE];
+	u16 offset = MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE;
+	u8 module_rev_id, module_id;
+	unsigned int read_size;
+	int err;
+
+	err = mlxsw_env_query_module_eeprom(mlxsw_core, module, 0, offset,
+					    module_info, &read_size);
+	if (err)
+		return err;
+
+	if (read_size < offset)
+		return -EIO;
+
+	module_rev_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID];
+	module_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID];
+
+	switch (module_id) {
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP:
+		modinfo->type       = ETH_MODULE_SFF_8436;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		break;
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28:
+		if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 ||
+		    module_rev_id >=
+		    MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636) {
+			modinfo->type       = ETH_MODULE_SFF_8636;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		} else {
+			modinfo->type       = ETH_MODULE_SFF_8436;
+			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		}
+		break;
+	case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP:
+		modinfo->type       = ETH_MODULE_SFF_8472;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_get_module_info);
+
+int mlxsw_env_get_module_eeprom(struct net_device *netdev,
+				struct mlxsw_core *mlxsw_core, int module,
+				struct ethtool_eeprom *ee, u8 *data)
+{
+	int offset = ee->offset;
+	unsigned int read_size;
+	int i = 0;
+	int err;
+
+	if (!ee->len)
+		return -EINVAL;
+
+	memset(data, 0, ee->len);
+
+	while (i < ee->len) {
+		err = mlxsw_env_query_module_eeprom(mlxsw_core, module, offset,
+						    ee->len - i, data + i,
+						    &read_size);
+		if (err) {
+			netdev_err(netdev, "Eeprom query failed\n");
+			return err;
+		}
+
+		i += read_size;
+		offset += read_size;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(mlxsw_env_get_module_eeprom);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
new file mode 100644
index 000000000000..064d0e770c01
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#ifndef _MLXSW_CORE_ENV_H
+#define _MLXSW_CORE_ENV_H
+
+int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module,
+					 int off, int *temp);
+
+int mlxsw_env_get_module_info(struct mlxsw_core *mlxsw_core, int module,
+			      struct ethtool_modinfo *modinfo);
+
+int mlxsw_env_get_module_eeprom(struct net_device *netdev,
+				struct mlxsw_core *mlxsw_core, int module,
+				struct ethtool_eeprom *ee, u8 *data);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index e04e8162aa14..6956bbebe2f1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -7,8 +7,10 @@
 #include <linux/sysfs.h>
 #include <linux/hwmon.h>
 #include <linux/err.h>
+#include <linux/sfp.h>
 
 #include "core.h"
+#include "core_env.h"
 
 #define MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT 127
 #define MLXSW_HWMON_ATTR_COUNT (MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT * 4 + \
@@ -30,6 +32,7 @@ struct mlxsw_hwmon {
 	struct attribute *attrs[MLXSW_HWMON_ATTR_COUNT + 1];
 	struct mlxsw_hwmon_attr hwmon_attrs[MLXSW_HWMON_ATTR_COUNT];
 	unsigned int attrs_count;
+	u8 sensor_count;
 };
 
 static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
@@ -121,6 +124,27 @@ static ssize_t mlxsw_hwmon_fan_rpm_show(struct device *dev,
 	return sprintf(buf, "%u\n", mlxsw_reg_mfsm_rpm_get(mfsm_pl));
 }
 
+static ssize_t mlxsw_hwmon_fan_fault_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	char fore_pl[MLXSW_REG_FORE_LEN];
+	bool fault;
+	int err;
+
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(fore), fore_pl);
+	if (err) {
+		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query fan\n");
+		return err;
+	}
+	mlxsw_reg_fore_unpack(fore_pl, mlwsw_hwmon_attr->type_index, &fault);
+
+	return sprintf(buf, "%u\n", fault);
+}
+
 static ssize_t mlxsw_hwmon_pwm_show(struct device *dev,
 				    struct device_attribute *attr,
 				    char *buf)
@@ -167,12 +191,160 @@ static ssize_t mlxsw_hwmon_pwm_store(struct device *dev,
 	return len;
 }
 
+static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev,
+					    struct device_attribute *attr,
+					    char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0};
+	u16 temp;
+	u8 module;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module,
+			    1);
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature sensor\n");
+		return err;
+	}
+
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);
+	/* Update status and temperature cache. */
+	switch (temp) {
+	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
+	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_INDEX_NA:
+		temp = 0;
+		break;
+	case MLXSW_REG_MTBR_BAD_SENS_INFO:
+		/* Untrusted cable is connected. Reading temperature from its
+		 * sensor is faulty.
+		 */
+		temp = 0;
+		break;
+	default:
+		temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp);
+		break;
+	}
+
+	return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev,
+						  struct device_attribute *attr,
+						  char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0};
+	u8 module, fault;
+	u16 temp;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module,
+			    1);
+	err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature sensor\n");
+		return err;
+	}
+
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);
+
+	/* Update status and temperature cache. */
+	switch (temp) {
+	case MLXSW_REG_MTBR_BAD_SENS_INFO:
+		/* Untrusted cable is connected. Reading temperature from its
+		 * sensor is faulty.
+		 */
+		fault = 1;
+		break;
+	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
+	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_INDEX_NA:
+	default:
+		fault = 0;
+		break;
+	}
+
+	return sprintf(buf, "%u\n", fault);
+}
+
+static ssize_t
+mlxsw_hwmon_module_temp_critical_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	int temp;
+	u8 module;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module,
+						   SFP_TEMP_HIGH_WARN, &temp);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature thresholds\n");
+		return err;
+	}
+
+	return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t
+mlxsw_hwmon_module_temp_emergency_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
+	u8 module;
+	int temp;
+	int err;
+
+	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
+	err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module,
+						   SFP_TEMP_HIGH_ALARM, &temp);
+	if (err) {
+		dev_err(dev, "Failed to query module temperature thresholds\n");
+		return err;
+	}
+
+	return sprintf(buf, "%u\n", temp);
+}
+
+static ssize_t
+mlxsw_hwmon_module_temp_label_show(struct device *dev,
+				   struct device_attribute *attr,
+				   char *buf)
+{
+	struct mlxsw_hwmon_attr *mlwsw_hwmon_attr =
+			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
+
+	return sprintf(buf, "front panel %03u\n",
+		       mlwsw_hwmon_attr->type_index);
+}
+
 enum mlxsw_hwmon_attr_type {
 	MLXSW_HWMON_ATTR_TYPE_TEMP,
 	MLXSW_HWMON_ATTR_TYPE_TEMP_MAX,
 	MLXSW_HWMON_ATTR_TYPE_TEMP_RST,
 	MLXSW_HWMON_ATTR_TYPE_FAN_RPM,
+	MLXSW_HWMON_ATTR_TYPE_FAN_FAULT,
 	MLXSW_HWMON_ATTR_TYPE_PWM,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG,
+	MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL,
 };
 
 static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
@@ -209,6 +381,12 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
 		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
 			 "fan%u_input", num + 1);
 		break;
+	case MLXSW_HWMON_ATTR_TYPE_FAN_FAULT:
+		mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_fan_fault_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "fan%u_fault", num + 1);
+		break;
 	case MLXSW_HWMON_ATTR_TYPE_PWM:
 		mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_pwm_show;
 		mlxsw_hwmon_attr->dev_attr.store = mlxsw_hwmon_pwm_store;
@@ -216,6 +394,40 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon,
 		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
 			 "pwm%u", num + 1);
 		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE:
+		mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_module_temp_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_input", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT:
+		mlxsw_hwmon_attr->dev_attr.show =
+					mlxsw_hwmon_module_temp_fault_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_fault", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_module_temp_critical_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_crit", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_module_temp_emergency_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_emergency", num + 1);
+		break;
+	case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL:
+		mlxsw_hwmon_attr->dev_attr.show =
+			mlxsw_hwmon_module_temp_label_show;
+		mlxsw_hwmon_attr->dev_attr.attr.mode = 0444;
+		snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name),
+			 "temp%u_label", num + 1);
+		break;
 	default:
 		WARN_ON(1);
 	}
@@ -233,7 +445,6 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
 {
 	char mtcap_pl[MLXSW_REG_MTCAP_LEN] = {0};
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	u8 sensor_count;
 	int i;
 	int err;
 
@@ -242,8 +453,8 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon)
 		dev_err(mlxsw_hwmon->bus_info->dev, "Failed to get number of temp sensors\n");
 		return err;
 	}
-	sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl);
-	for (i = 0; i < sensor_count; i++) {
+	mlxsw_hwmon->sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl);
+	for (i = 0; i < mlxsw_hwmon->sensor_count; i++) {
 		mlxsw_reg_mtmp_pack(mtmp_pl, i, true, true);
 		err = mlxsw_reg_write(mlxsw_hwmon->core,
 				      MLXSW_REG(mtmp), mtmp_pl);
@@ -280,10 +491,14 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon)
 	mlxsw_reg_mfcr_unpack(mfcr_pl, &freq, &tacho_active, &pwm_active);
 	num = 0;
 	for (type_index = 0; type_index < MLXSW_MFCR_TACHOS_MAX; type_index++) {
-		if (tacho_active & BIT(type_index))
+		if (tacho_active & BIT(type_index)) {
 			mlxsw_hwmon_attr_add(mlxsw_hwmon,
 					     MLXSW_HWMON_ATTR_TYPE_FAN_RPM,
+					     type_index, num);
+			mlxsw_hwmon_attr_add(mlxsw_hwmon,
+					     MLXSW_HWMON_ATTR_TYPE_FAN_FAULT,
 					     type_index, num++);
+		}
 	}
 	num = 0;
 	for (type_index = 0; type_index < MLXSW_MFCR_PWMS_MAX; type_index++) {
@@ -295,6 +510,53 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon)
 	return 0;
 }
 
+static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon)
+{
+	unsigned int module_count = mlxsw_core_max_ports(mlxsw_hwmon->core);
+	char pmlp_pl[MLXSW_REG_PMLP_LEN] = {0};
+	int i, index;
+	u8 width;
+	int err;
+
+	/* Add extra attributes for module temperature. Sensor index is
+	 * assigned to sensor_count value, while all indexed before
+	 * sensor_count are already utilized by the sensors connected through
+	 * mtmp register by mlxsw_hwmon_temp_init().
+	 */
+	index = mlxsw_hwmon->sensor_count;
+	for (i = 1; i < module_count; i++) {
+		mlxsw_reg_pmlp_pack(pmlp_pl, i);
+		err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(pmlp),
+				      pmlp_pl);
+		if (err) {
+			dev_err(mlxsw_hwmon->bus_info->dev, "Failed to read module index %d\n",
+				i);
+			return err;
+		}
+		width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+		if (!width)
+			continue;
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, index,
+				     index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG,
+				     index, index);
+		mlxsw_hwmon_attr_add(mlxsw_hwmon,
+				     MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL,
+				     index, index);
+		index++;
+	}
+
+	return 0;
+}
+
 int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 		     const struct mlxsw_bus_info *mlxsw_bus_info,
 		     struct mlxsw_hwmon **p_hwmon)
@@ -317,6 +579,10 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_fans_init;
 
+	err = mlxsw_hwmon_module_init(mlxsw_hwmon);
+	if (err)
+		goto err_temp_module_init;
+
 	mlxsw_hwmon->groups[0] = &mlxsw_hwmon->group;
 	mlxsw_hwmon->group.attrs = mlxsw_hwmon->attrs;
 
@@ -333,6 +599,7 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core,
 	return 0;
 
 err_hwmon_register:
+err_temp_module_init:
 err_fans_init:
 err_temp_init:
 	kfree(mlxsw_hwmon);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 6d29dc428608..472f63f9fac5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -9,17 +9,48 @@
 #include <linux/sysfs.h>
 #include <linux/thermal.h>
 #include <linux/err.h>
+#include <linux/sfp.h>
 
 #include "core.h"
+#include "core_env.h"
 
 #define MLXSW_THERMAL_POLL_INT	1000	/* ms */
-#define MLXSW_THERMAL_MAX_TEMP	110000	/* 110C */
+#define MLXSW_THERMAL_SLOW_POLL_INT	20000	/* ms */
+#define MLXSW_THERMAL_ASIC_TEMP_NORM	75000	/* 75C */
+#define MLXSW_THERMAL_ASIC_TEMP_HIGH	85000	/* 85C */
+#define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
+#define MLXSW_THERMAL_ASIC_TEMP_CRIT	110000	/* 110C */
+#define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
+#define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
+#define MLXSW_THERMAL_ZONE_MAX_NAME	16
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MAX_DUTY	255
+/* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values
+ * MLXSW_THERMAL_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting fan speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXSW_THERMAL_SPEED_MIN		(MLXSW_THERMAL_MAX_STATE + 2)
+#define MLXSW_THERMAL_SPEED_MAX		(MLXSW_THERMAL_MAX_STATE * 2)
+#define MLXSW_THERMAL_SPEED_MIN_LEVEL	2		/* 20% */
+
+/* External cooling devices, allowed for binding to mlxsw thermal zones. */
+static char * const mlxsw_thermal_external_allowed_cdev[] = {
+	"mlxreg_fan",
+};
+
+enum mlxsw_thermal_trips {
+	MLXSW_THERMAL_TEMP_TRIP_NORM,
+	MLXSW_THERMAL_TEMP_TRIP_HIGH,
+	MLXSW_THERMAL_TEMP_TRIP_HOT,
+	MLXSW_THERMAL_TEMP_TRIP_CRIT,
+};
 
 struct mlxsw_thermal_trip {
 	int	type;
 	int	temp;
+	int	hyst;
 	int	min_state;
 	int	max_state;
 };
@@ -27,32 +58,29 @@ struct mlxsw_thermal_trip {
 static const struct mlxsw_thermal_trip default_thermal_trips[] = {
 	{	/* In range - 0-40% PWM */
 		.type		= THERMAL_TRIP_ACTIVE,
-		.temp		= 75000,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_NORM,
+		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
 		.min_state	= 0,
 		.max_state	= (4 * MLXSW_THERMAL_MAX_STATE) / 10,
 	},
-	{	/* High - 40-100% PWM */
-		.type		= THERMAL_TRIP_ACTIVE,
-		.temp		= 80000,
-		.min_state	= (4 * MLXSW_THERMAL_MAX_STATE) / 10,
-		.max_state	= MLXSW_THERMAL_MAX_STATE,
-	},
 	{
-		/* Very high - 100% PWM */
+		/* In range - 40-100% PWM */
 		.type		= THERMAL_TRIP_ACTIVE,
-		.temp		= 85000,
-		.min_state	= MLXSW_THERMAL_MAX_STATE,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_HIGH,
+		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
+		.min_state	= (4 * MLXSW_THERMAL_MAX_STATE) / 10,
 		.max_state	= MLXSW_THERMAL_MAX_STATE,
 	},
 	{	/* Warning */
 		.type		= THERMAL_TRIP_HOT,
-		.temp		= 105000,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_HOT,
+		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
 		.min_state	= MLXSW_THERMAL_MAX_STATE,
 		.max_state	= MLXSW_THERMAL_MAX_STATE,
 	},
 	{	/* Critical - soft poweroff */
 		.type		= THERMAL_TRIP_CRITICAL,
-		.temp		= MLXSW_THERMAL_MAX_TEMP,
+		.temp		= MLXSW_THERMAL_ASIC_TEMP_CRIT,
 		.min_state	= MLXSW_THERMAL_MAX_STATE,
 		.max_state	= MLXSW_THERMAL_MAX_STATE,
 	}
@@ -63,13 +91,26 @@ static const struct mlxsw_thermal_trip default_thermal_trips[] = {
 /* Make sure all trips are writable */
 #define MLXSW_THERMAL_TRIP_MASK	(BIT(MLXSW_THERMAL_NUM_TRIPS) - 1)
 
+struct mlxsw_thermal;
+
+struct mlxsw_thermal_module {
+	struct mlxsw_thermal *parent;
+	struct thermal_zone_device *tzdev;
+	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
+	enum thermal_device_mode mode;
+	int module;
+};
+
 struct mlxsw_thermal {
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
 	struct thermal_zone_device *tzdev;
+	int polling_delay;
 	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
+	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	enum thermal_device_mode mode;
+	struct mlxsw_thermal_module *tz_module_arr;
 };
 
 static inline u8 mlxsw_state_to_duty(int state)
@@ -93,9 +134,67 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal,
 		if (thermal->cdevs[i] == cdev)
 			return i;
 
+	/* Allow mlxsw thermal zone binding to an external cooling device */
+	for (i = 0; i < ARRAY_SIZE(mlxsw_thermal_external_allowed_cdev); i++) {
+		if (strnstr(cdev->type, mlxsw_thermal_external_allowed_cdev[i],
+			    sizeof(cdev->type)))
+			return 0;
+	}
+
 	return -ENODEV;
 }
 
+static void
+mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz)
+{
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = 0;
+}
+
+static int
+mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
+				  struct mlxsw_thermal_module *tz)
+{
+	int crit_temp, emerg_temp;
+	int err;
+
+	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+						   SFP_TEMP_HIGH_WARN,
+						   &crit_temp);
+	if (err)
+		return err;
+
+	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+						   SFP_TEMP_HIGH_ALARM,
+						   &emerg_temp);
+	if (err)
+		return err;
+
+	/* According to the system thermal requirements, the thermal zones are
+	 * defined with four trip points. The critical and emergency
+	 * temperature thresholds, provided by QSFP module are set as "active"
+	 * and "hot" trip points, "normal" and "critical" trip points are
+	 * derived from "active" and "hot" by subtracting or adding double
+	 * hysteresis value.
+	 */
+	if (crit_temp >= MLXSW_THERMAL_MODULE_TEMP_SHIFT)
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp -
+					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
+	else
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp;
+	if (emerg_temp > crit_temp)
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
+					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
+	else
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp;
+
+	return 0;
+}
+
 static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
 			      struct thermal_cooling_device *cdev)
 {
@@ -162,7 +261,7 @@ static int mlxsw_thermal_set_mode(struct thermal_zone_device *tzdev,
 	mutex_lock(&tzdev->lock);
 
 	if (mode == THERMAL_DEVICE_ENABLED)
-		tzdev->polling_delay = MLXSW_THERMAL_POLL_INT;
+		tzdev->polling_delay = thermal->polling_delay;
 	else
 		tzdev->polling_delay = 0;
 
@@ -227,13 +326,31 @@ static int mlxsw_thermal_set_trip_temp(struct thermal_zone_device *tzdev,
 	struct mlxsw_thermal *thermal = tzdev->devdata;
 
 	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
-	    temp > MLXSW_THERMAL_MAX_TEMP)
+	    temp > MLXSW_THERMAL_ASIC_TEMP_CRIT)
 		return -EINVAL;
 
 	thermal->trips[trip].temp = temp;
 	return 0;
 }
 
+static int mlxsw_thermal_get_trip_hyst(struct thermal_zone_device *tzdev,
+				       int trip, int *p_hyst)
+{
+	struct mlxsw_thermal *thermal = tzdev->devdata;
+
+	*p_hyst = thermal->trips[trip].hyst;
+	return 0;
+}
+
+static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
+				       int trip, int hyst)
+{
+	struct mlxsw_thermal *thermal = tzdev->devdata;
+
+	thermal->trips[trip].hyst = hyst;
+	return 0;
+}
+
 static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.bind = mlxsw_thermal_bind,
 	.unbind = mlxsw_thermal_unbind,
@@ -243,6 +360,206 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.get_trip_type	= mlxsw_thermal_get_trip_type,
 	.get_trip_temp	= mlxsw_thermal_get_trip_temp,
 	.set_trip_temp	= mlxsw_thermal_set_trip_temp,
+	.get_trip_hyst	= mlxsw_thermal_get_trip_hyst,
+	.set_trip_hyst	= mlxsw_thermal_set_trip_hyst,
+};
+
+static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
+				     struct thermal_cooling_device *cdev)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int i, j, err;
+
+	/* If the cooling device is one of ours bind it */
+	if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0)
+		return 0;
+
+	for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) {
+		const struct mlxsw_thermal_trip *trip = &tz->trips[i];
+
+		err = thermal_zone_bind_cooling_device(tzdev, i, cdev,
+						       trip->max_state,
+						       trip->min_state,
+						       THERMAL_WEIGHT_DEFAULT);
+		if (err < 0)
+			goto err_bind_cooling_device;
+	}
+	return 0;
+
+err_bind_cooling_device:
+	for (j = i - 1; j >= 0; j--)
+		thermal_zone_unbind_cooling_device(tzdev, j, cdev);
+	return err;
+}
+
+static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev,
+				       struct thermal_cooling_device *cdev)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int i;
+	int err;
+
+	/* If the cooling device is one of ours unbind it */
+	if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0)
+		return 0;
+
+	for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) {
+		err = thermal_zone_unbind_cooling_device(tzdev, i, cdev);
+		WARN_ON(err);
+	}
+	return err;
+}
+
+static int mlxsw_thermal_module_mode_get(struct thermal_zone_device *tzdev,
+					 enum thermal_device_mode *mode)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	*mode = tz->mode;
+
+	return 0;
+}
+
+static int mlxsw_thermal_module_mode_set(struct thermal_zone_device *tzdev,
+					 enum thermal_device_mode mode)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	mutex_lock(&tzdev->lock);
+
+	if (mode == THERMAL_DEVICE_ENABLED)
+		tzdev->polling_delay = thermal->polling_delay;
+	else
+		tzdev->polling_delay = 0;
+
+	mutex_unlock(&tzdev->lock);
+
+	tz->mode = mode;
+	thermal_zone_device_update(tzdev, THERMAL_EVENT_UNSPECIFIED);
+
+	return 0;
+}
+
+static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
+					 int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	struct device *dev = thermal->bus_info->dev;
+	char mtbr_pl[MLXSW_REG_MTBR_LEN];
+	u16 temp;
+	int err;
+
+	/* Read module temperature. */
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX +
+			    tz->module, 1);
+	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);
+	/* Update temperature. */
+	switch (temp) {
+	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
+	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_INDEX_NA: /* fall-through */
+	case MLXSW_REG_MTBR_BAD_SENS_INFO:
+		temp = 0;
+		break;
+	default:
+		temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp);
+		/* Reset all trip point. */
+		mlxsw_thermal_module_trips_reset(tz);
+		/* Update trip points. */
+		err = mlxsw_thermal_module_trips_update(dev, thermal->core,
+							tz);
+		if (err)
+			return err;
+		break;
+	}
+
+	*p_temp = (int) temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_type_get(struct thermal_zone_device *tzdev, int trip,
+				   enum thermal_trip_type *p_type)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	*p_type = tz->trips[trip].type;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_temp_get(struct thermal_zone_device *tzdev,
+				   int trip, int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	*p_temp = tz->trips[trip].temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_temp_set(struct thermal_zone_device *tzdev,
+				   int trip, int temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
+	    temp > tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp)
+		return -EINVAL;
+
+	tz->trips[trip].temp = temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_hyst_get(struct thermal_zone_device *tzdev, int trip,
+				   int *p_hyst)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	*p_hyst = tz->trips[trip].hyst;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
+				   int hyst)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	tz->trips[trip].hyst = hyst;
+	return 0;
+}
+
+static struct thermal_zone_params mlxsw_thermal_module_params = {
+	.governor_name = "user_space",
+};
+
+static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
+	.bind		= mlxsw_thermal_module_bind,
+	.unbind		= mlxsw_thermal_module_unbind,
+	.get_mode	= mlxsw_thermal_module_mode_get,
+	.set_mode	= mlxsw_thermal_module_mode_set,
+	.get_temp	= mlxsw_thermal_module_temp_get,
+	.get_trip_type	= mlxsw_thermal_module_trip_type_get,
+	.get_trip_temp	= mlxsw_thermal_module_trip_temp_get,
+	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
+	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
+	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
@@ -285,12 +602,51 @@ static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev,
 	struct mlxsw_thermal *thermal = cdev->devdata;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int err, idx;
+	unsigned long cur_state, i;
+	int idx;
+	u8 duty;
+	int err;
 
 	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
 	if (idx < 0)
 		return idx;
 
+	/* Verify if this request is for changing allowed fan dynamical
+	 * minimum. If it is - update cooling levels accordingly and update
+	 * state, if current state is below the newly requested minimum state.
+	 * For example, if current state is 5, and minimal state is to be
+	 * changed from 4 to 6, thermal->cooling_levels[0 to 5] will be changed
+	 * all from 4 to 6. And state 5 (thermal->cooling_levels[4]) should be
+	 * overwritten.
+	 */
+	if (state >= MLXSW_THERMAL_SPEED_MIN &&
+	    state <= MLXSW_THERMAL_SPEED_MAX) {
+		state -= MLXSW_THERMAL_MAX_STATE;
+		for (i = 0; i <= MLXSW_THERMAL_MAX_STATE; i++)
+			thermal->cooling_levels[i] = max(state, i);
+
+		mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0);
+		err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
+		if (err)
+			return err;
+
+		duty = mlxsw_reg_mfsc_pwm_duty_cycle_get(mfsc_pl);
+		cur_state = mlxsw_duty_to_state(duty);
+
+		/* If current fan state is lower than requested dynamical
+		 * minimum, increase fan speed up to dynamical minimum.
+		 */
+		if (state < cur_state)
+			return 0;
+
+		state = cur_state;
+	}
+
+	if (state > MLXSW_THERMAL_MAX_STATE)
+		return -EINVAL;
+
+	/* Normalize the state to the valid speed range. */
+	state = thermal->cooling_levels[state];
 	mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state));
 	err = mlxsw_reg_write(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
@@ -306,6 +662,125 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = {
 	.set_cur_state	= mlxsw_thermal_set_cur_state,
 };
 
+static int
+mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
+{
+	char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME];
+	int err;
+
+	snprintf(tz_name, sizeof(tz_name), "mlxsw-module%d",
+		 module_tz->module + 1);
+	module_tz->tzdev = thermal_zone_device_register(tz_name,
+							MLXSW_THERMAL_NUM_TRIPS,
+							MLXSW_THERMAL_TRIP_MASK,
+							module_tz,
+							&mlxsw_thermal_module_ops,
+							&mlxsw_thermal_module_params,
+							0, 0);
+	if (IS_ERR(module_tz->tzdev)) {
+		err = PTR_ERR(module_tz->tzdev);
+		return err;
+	}
+
+	return 0;
+}
+
+static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev)
+{
+	thermal_zone_device_unregister(tzdev);
+}
+
+static int
+mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
+			  struct mlxsw_thermal *thermal, u8 local_port)
+{
+	struct mlxsw_thermal_module *module_tz;
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+	u8 width, module;
+	int err;
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	err = mlxsw_reg_query(core, MLXSW_REG(pmlp), pmlp_pl);
+	if (err)
+		return err;
+
+	width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+	if (!width)
+		return 0;
+
+	module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+	module_tz = &thermal->tz_module_arr[module];
+	/* Skip if parent is already set (case of port split). */
+	if (module_tz->parent)
+		return 0;
+	module_tz->module = module;
+	module_tz->parent = thermal;
+	memcpy(module_tz->trips, default_thermal_trips,
+	       sizeof(thermal->trips));
+	/* Initialize all trip point. */
+	mlxsw_thermal_module_trips_reset(module_tz);
+	/* Update trip point according to the module data. */
+	return mlxsw_thermal_module_trips_update(dev, core, module_tz);
+}
+
+static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
+{
+	if (module_tz && module_tz->tzdev) {
+		mlxsw_thermal_module_tz_fini(module_tz->tzdev);
+		module_tz->tzdev = NULL;
+		module_tz->parent = NULL;
+	}
+}
+
+static int
+mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
+			   struct mlxsw_thermal *thermal)
+{
+	unsigned int module_count = mlxsw_core_max_ports(core);
+	struct mlxsw_thermal_module *module_tz;
+	int i, err;
+
+	thermal->tz_module_arr = kcalloc(module_count,
+					 sizeof(*thermal->tz_module_arr),
+					 GFP_KERNEL);
+	if (!thermal->tz_module_arr)
+		return -ENOMEM;
+
+	for (i = 1; i < module_count; i++) {
+		err = mlxsw_thermal_module_init(dev, core, thermal, i);
+		if (err)
+			goto err_unreg_tz_module_arr;
+	}
+
+	for (i = 0; i < module_count - 1; i++) {
+		module_tz = &thermal->tz_module_arr[i];
+		if (!module_tz->parent)
+			continue;
+		err = mlxsw_thermal_module_tz_init(module_tz);
+		if (err)
+			goto err_unreg_tz_module_arr;
+	}
+
+	return 0;
+
+err_unreg_tz_module_arr:
+	for (i = module_count - 1; i >= 0; i--)
+		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
+	kfree(thermal->tz_module_arr);
+	return err;
+}
+
+static void
+mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal)
+{
+	unsigned int module_count = mlxsw_core_max_ports(thermal->core);
+	int i;
+
+	for (i = module_count - 1; i >= 0; i--)
+		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
+	kfree(thermal->tz_module_arr);
+}
+
 int mlxsw_thermal_init(struct mlxsw_core *core,
 		       const struct mlxsw_bus_info *bus_info,
 		       struct mlxsw_thermal **p_thermal)
@@ -358,8 +833,9 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 		if (pwm_active & BIT(i)) {
 			struct thermal_cooling_device *cdev;
 
-			cdev = thermal_cooling_device_register("Fan", thermal,
-							&mlxsw_cooling_ops);
+			cdev = thermal_cooling_device_register("mlxsw_fan",
+							       thermal,
+							       &mlxsw_cooling_ops);
 			if (IS_ERR(cdev)) {
 				err = PTR_ERR(cdev);
 				dev_err(dev, "Failed to register cooling device\n");
@@ -369,22 +845,41 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 		}
 	}
 
+	/* Initialize cooling levels per PWM state. */
+	for (i = 0; i < MLXSW_THERMAL_MAX_STATE; i++)
+		thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL,
+						 i);
+
+	thermal->polling_delay = bus_info->low_frequency ?
+				 MLXSW_THERMAL_SLOW_POLL_INT :
+				 MLXSW_THERMAL_POLL_INT;
+
 	thermal->tzdev = thermal_zone_device_register("mlxsw",
 						      MLXSW_THERMAL_NUM_TRIPS,
 						      MLXSW_THERMAL_TRIP_MASK,
 						      thermal,
 						      &mlxsw_thermal_ops,
 						      NULL, 0,
-						      MLXSW_THERMAL_POLL_INT);
+						      thermal->polling_delay);
 	if (IS_ERR(thermal->tzdev)) {
 		err = PTR_ERR(thermal->tzdev);
 		dev_err(dev, "Failed to register thermal zone\n");
 		goto err_unreg_cdevs;
 	}
 
+	err = mlxsw_thermal_modules_init(dev, core, thermal);
+	if (err)
+		goto err_unreg_tzdev;
+
 	thermal->mode = THERMAL_DEVICE_ENABLED;
 	*p_thermal = thermal;
 	return 0;
+
+err_unreg_tzdev:
+	if (thermal->tzdev) {
+		thermal_zone_device_unregister(thermal->tzdev);
+		thermal->tzdev = NULL;
+	}
 err_unreg_cdevs:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
 		if (thermal->cdevs[i])
@@ -398,6 +893,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 {
 	int i;
 
+	mlxsw_thermal_modules_fini(thermal);
 	if (thermal->tzdev) {
 		thermal_zone_device_unregister(thermal->tzdev);
 		thermal->tzdev = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 798bd5aca384..06aea1999518 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -14,14 +14,17 @@
 #include "cmd.h"
 #include "core.h"
 #include "i2c.h"
+#include "resources.h"
 
 #define MLXSW_I2C_CIR2_BASE		0x72000
 #define MLXSW_I2C_CIR_STATUS_OFF	0x18
 #define MLXSW_I2C_CIR2_OFF_STATUS	(MLXSW_I2C_CIR2_BASE + \
 					 MLXSW_I2C_CIR_STATUS_OFF)
 #define MLXSW_I2C_OPMOD_SHIFT		12
+#define MLXSW_I2C_EVENT_BIT_SHIFT	22
 #define MLXSW_I2C_GO_BIT_SHIFT		23
 #define MLXSW_I2C_CIR_CTRL_STATUS_SHIFT	24
+#define MLXSW_I2C_EVENT_BIT		BIT(MLXSW_I2C_EVENT_BIT_SHIFT)
 #define MLXSW_I2C_GO_BIT		BIT(MLXSW_I2C_GO_BIT_SHIFT)
 #define MLXSW_I2C_GO_OPMODE		BIT(MLXSW_I2C_OPMOD_SHIFT)
 #define MLXSW_I2C_SET_IMM_CMD		(MLXSW_I2C_GO_OPMODE | \
@@ -33,6 +36,9 @@
 #define MLXSW_I2C_TLV_HDR_SIZE		0x10
 #define MLXSW_I2C_ADDR_WIDTH		4
 #define MLXSW_I2C_PUSH_CMD_SIZE		(MLXSW_I2C_ADDR_WIDTH + 4)
+#define MLXSW_I2C_SET_EVENT_CMD		(MLXSW_I2C_EVENT_BIT)
+#define MLXSW_I2C_PUSH_EVENT_CMD	(MLXSW_I2C_GO_BIT | \
+					 MLXSW_I2C_SET_EVENT_CMD)
 #define MLXSW_I2C_READ_SEMA_SIZE	4
 #define MLXSW_I2C_PREP_SIZE		(MLXSW_I2C_ADDR_WIDTH + 28)
 #define MLXSW_I2C_MBOX_SIZE		20
@@ -44,6 +50,7 @@
 #define MLXSW_I2C_BLK_MAX		32
 #define MLXSW_I2C_RETRY			5
 #define MLXSW_I2C_TIMEOUT_MSECS		5000
+#define MLXSW_I2C_MAX_DATA_SIZE		256
 
 /**
  * struct mlxsw_i2c - device private data:
@@ -167,7 +174,7 @@ static int mlxsw_i2c_wait_go_bit(struct i2c_client *client,
 	return err > 0 ? 0 : err;
 }
 
-/* Routine posts a command to ASIC though mail box. */
+/* Routine posts a command to ASIC through mail box. */
 static int mlxsw_i2c_write_cmd(struct i2c_client *client,
 			       struct mlxsw_i2c *mlxsw_i2c,
 			       int immediate)
@@ -213,6 +220,66 @@ static int mlxsw_i2c_write_cmd(struct i2c_client *client,
 	return 0;
 }
 
+/* Routine posts initialization command to ASIC through mail box. */
+static int
+mlxsw_i2c_write_init_cmd(struct i2c_client *client,
+			 struct mlxsw_i2c *mlxsw_i2c, u16 opcode, u32 in_mod)
+{
+	__be32 push_cmd_buf[MLXSW_I2C_PUSH_CMD_SIZE / 4] = {
+		0, cpu_to_be32(MLXSW_I2C_PUSH_EVENT_CMD)
+	};
+	__be32 prep_cmd_buf[MLXSW_I2C_PREP_SIZE / 4] = {
+		0, 0, 0, 0, 0, 0,
+		cpu_to_be32(client->adapter->nr & 0xffff),
+		cpu_to_be32(MLXSW_I2C_SET_EVENT_CMD)
+	};
+	struct i2c_msg push_cmd =
+		MLXSW_I2C_WRITE_MSG(client, push_cmd_buf,
+				    MLXSW_I2C_PUSH_CMD_SIZE);
+	struct i2c_msg prep_cmd =
+		MLXSW_I2C_WRITE_MSG(client, prep_cmd_buf, MLXSW_I2C_PREP_SIZE);
+	u8 status;
+	int err;
+
+	push_cmd_buf[1] = cpu_to_be32(MLXSW_I2C_PUSH_EVENT_CMD | opcode);
+	prep_cmd_buf[3] = cpu_to_be32(in_mod);
+	prep_cmd_buf[7] = cpu_to_be32(MLXSW_I2C_GO_BIT | opcode);
+	mlxsw_i2c_set_slave_addr((u8 *)prep_cmd_buf,
+				 MLXSW_I2C_CIR2_BASE);
+	mlxsw_i2c_set_slave_addr((u8 *)push_cmd_buf,
+				 MLXSW_I2C_CIR2_OFF_STATUS);
+
+	/* Prepare Command Interface Register for transaction */
+	err = i2c_transfer(client->adapter, &prep_cmd, 1);
+	if (err < 0)
+		return err;
+	else if (err != 1)
+		return -EIO;
+
+	/* Write out Command Interface Register GO bit to push transaction */
+	err = i2c_transfer(client->adapter, &push_cmd, 1);
+	if (err < 0)
+		return err;
+	else if (err != 1)
+		return -EIO;
+
+	/* Wait until go bit is cleared. */
+	err = mlxsw_i2c_wait_go_bit(client, mlxsw_i2c, &status);
+	if (err) {
+		dev_err(&client->dev, "HW semaphore is not released");
+		return err;
+	}
+
+	/* Validate transaction completion status. */
+	if (status) {
+		dev_err(&client->dev, "Bad transaction completion status %x\n",
+			status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 /* Routine obtains mail box offsets from ASIC register space. */
 static int mlxsw_i2c_get_mbox(struct i2c_client *client,
 			      struct mlxsw_i2c *mlxsw_i2c)
@@ -310,8 +377,8 @@ mlxsw_i2c_write(struct device *dev, size_t in_mbox_size, u8 *in_mbox, int num,
 
 /* Routine executes I2C command. */
 static int
-mlxsw_i2c_cmd(struct device *dev, size_t in_mbox_size, u8 *in_mbox,
-	      size_t out_mbox_size, u8 *out_mbox, u8 *status)
+mlxsw_i2c_cmd(struct device *dev, u16 opcode, u32 in_mod, size_t in_mbox_size,
+	      u8 *in_mbox, size_t out_mbox_size, u8 *out_mbox, u8 *status)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct mlxsw_i2c *mlxsw_i2c = i2c_get_clientdata(client);
@@ -326,24 +393,40 @@ mlxsw_i2c_cmd(struct device *dev, size_t in_mbox_size, u8 *in_mbox,
 
 	WARN_ON(in_mbox_size % sizeof(u32) || out_mbox_size % sizeof(u32));
 
-	reg_size = mlxsw_i2c_get_reg_size(in_mbox);
-	num = reg_size / MLXSW_I2C_BLK_MAX;
-	if (reg_size % MLXSW_I2C_BLK_MAX)
-		num++;
+	if (in_mbox) {
+		reg_size = mlxsw_i2c_get_reg_size(in_mbox);
+		num = reg_size / MLXSW_I2C_BLK_MAX;
+		if (reg_size % MLXSW_I2C_BLK_MAX)
+			num++;
 
-	if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
-		dev_err(&client->dev, "Could not acquire lock");
-		return -EINVAL;
-	}
+		if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
+			dev_err(&client->dev, "Could not acquire lock");
+			return -EINVAL;
+		}
+
+		err = mlxsw_i2c_write(dev, reg_size, in_mbox, num, status);
+		if (err)
+			goto cmd_fail;
+
+		/* No out mailbox is case of write transaction. */
+		if (!out_mbox) {
+			mutex_unlock(&mlxsw_i2c->cmd.lock);
+			return 0;
+		}
+	} else {
+		/* No input mailbox is case of initialization query command. */
+		reg_size = MLXSW_I2C_MAX_DATA_SIZE;
+		num = reg_size / MLXSW_I2C_BLK_MAX;
 
-	err = mlxsw_i2c_write(dev, reg_size, in_mbox, num, status);
-	if (err)
-		goto cmd_fail;
+		if (mutex_lock_interruptible(&mlxsw_i2c->cmd.lock) < 0) {
+			dev_err(&client->dev, "Could not acquire lock");
+			return -EINVAL;
+		}
 
-	/* No out mailbox is case of write transaction. */
-	if (!out_mbox) {
-		mutex_unlock(&mlxsw_i2c->cmd.lock);
-		return 0;
+		err = mlxsw_i2c_write_init_cmd(client, mlxsw_i2c, opcode,
+					       in_mod);
+		if (err)
+			goto cmd_fail;
 	}
 
 	/* Send read transaction to get output mailbox content. */
@@ -395,8 +478,8 @@ static int mlxsw_i2c_cmd_exec(void *bus_priv, u16 opcode, u8 opcode_mod,
 {
 	struct mlxsw_i2c *mlxsw_i2c = bus_priv;
 
-	return mlxsw_i2c_cmd(mlxsw_i2c->dev, in_mbox_size, in_mbox,
-			     out_mbox_size, out_mbox, status);
+	return mlxsw_i2c_cmd(mlxsw_i2c->dev, opcode, in_mod, in_mbox_size,
+			     in_mbox, out_mbox_size, out_mbox, status);
 }
 
 static bool mlxsw_i2c_skb_transmit_busy(void *bus_priv,
@@ -414,13 +497,22 @@ static int mlxsw_i2c_skb_transmit(void *bus_priv, struct sk_buff *skb,
 static int
 mlxsw_i2c_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	       const struct mlxsw_config_profile *profile,
-	       struct mlxsw_res *resources)
+	       struct mlxsw_res *res)
 {
 	struct mlxsw_i2c *mlxsw_i2c = bus_priv;
+	char *mbox;
+	int err;
 
 	mlxsw_i2c->core = mlxsw_core;
 
-	return 0;
+	mbox = mlxsw_cmd_mbox_alloc();
+	if (!mbox)
+		return -ENOMEM;
+
+	err = mlxsw_core_resources_query(mlxsw_core, mbox, res);
+
+	mlxsw_cmd_mbox_free(mbox);
+	return err;
 }
 
 static void mlxsw_i2c_fini(void *bus_priv)
@@ -503,6 +595,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client,
 	mlxsw_i2c->bus_info.device_kind = id->name;
 	mlxsw_i2c->bus_info.device_name = client->name;
 	mlxsw_i2c->bus_info.dev = &client->dev;
+	mlxsw_i2c->bus_info.low_frequency = true;
 	mlxsw_i2c->dev = &client->dev;
 
 	err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 5a6c4457fb55..00c390024350 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
-/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
+/* Copyright (c) 2016-2019 Mellanox Technologies. All rights reserved */
 
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
 #include <linux/i2c.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -8,59 +11,395 @@
 #include <linux/types.h>
 
 #include "core.h"
+#include "core_env.h"
 #include "i2c.h"
 
-static const char mlxsw_minimal_driver_name[] = "mlxsw_minimal";
+static const char mlxsw_m_driver_name[] = "mlxsw_minimal";
 
-static const struct mlxsw_config_profile mlxsw_minimal_config_profile;
+struct mlxsw_m_port;
 
-static struct mlxsw_driver mlxsw_minimal_driver = {
-	.kind		= mlxsw_minimal_driver_name,
-	.priv_size	= 1,
-	.profile	= &mlxsw_minimal_config_profile,
+struct mlxsw_m {
+	struct mlxsw_m_port **ports;
+	int *module_to_port;
+	struct mlxsw_core *core;
+	const struct mlxsw_bus_info *bus_info;
+	u8 base_mac[ETH_ALEN];
+	u8 max_ports;
 };
 
-static const struct i2c_device_id mlxsw_minimal_i2c_id[] = {
+struct mlxsw_m_port {
+	struct net_device *dev;
+	struct mlxsw_m *mlxsw_m;
+	u8 local_port;
+	u8 module;
+};
+
+static int mlxsw_m_base_mac_get(struct mlxsw_m *mlxsw_m)
+{
+	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
+	int err;
+
+	err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(spad), spad_pl);
+	if (err)
+		return err;
+	mlxsw_reg_spad_base_mac_memcpy_from(spad_pl, mlxsw_m->base_mac);
+	return 0;
+}
+
+static int mlxsw_m_port_dummy_open_stop(struct net_device *dev)
+{
+	return 0;
+}
+
+static int
+mlxsw_m_port_get_phys_port_name(struct net_device *dev, char *name, size_t len)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+	u8 local_port = mlxsw_m_port->local_port;
+
+	return mlxsw_core_port_get_phys_port_name(core, local_port, name, len);
+}
+
+static int mlxsw_m_port_get_port_parent_id(struct net_device *dev,
+					   struct netdev_phys_item_id *ppid)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(dev);
+	struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m;
+
+	ppid->id_len = sizeof(mlxsw_m->base_mac);
+	memcpy(&ppid->id, &mlxsw_m->base_mac, ppid->id_len);
+
+	return 0;
+}
+
+static const struct net_device_ops mlxsw_m_port_netdev_ops = {
+	.ndo_open		= mlxsw_m_port_dummy_open_stop,
+	.ndo_stop		= mlxsw_m_port_dummy_open_stop,
+	.ndo_get_phys_port_name	= mlxsw_m_port_get_phys_port_name,
+	.ndo_get_port_parent_id	= mlxsw_m_port_get_port_parent_id,
+};
+
+static int mlxsw_m_get_module_info(struct net_device *netdev,
+				   struct ethtool_modinfo *modinfo)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_get_module_info(core, mlxsw_m_port->module, modinfo);
+}
+
+static int
+mlxsw_m_get_module_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee,
+			  u8 *data)
+{
+	struct mlxsw_m_port *mlxsw_m_port = netdev_priv(netdev);
+	struct mlxsw_core *core = mlxsw_m_port->mlxsw_m->core;
+
+	return mlxsw_env_get_module_eeprom(netdev, core, mlxsw_m_port->module,
+					   ee, data);
+}
+
+static const struct ethtool_ops mlxsw_m_port_ethtool_ops = {
+	.get_module_info	= mlxsw_m_get_module_info,
+	.get_module_eeprom	= mlxsw_m_get_module_eeprom,
+};
+
+static int
+mlxsw_m_port_module_info_get(struct mlxsw_m *mlxsw_m, u8 local_port,
+			     u8 *p_module, u8 *p_width)
+{
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+	int err;
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(pmlp), pmlp_pl);
+	if (err)
+		return err;
+	*p_module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+	*p_width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+
+	return 0;
+}
+
+static int
+mlxsw_m_port_dev_addr_get(struct mlxsw_m_port *mlxsw_m_port)
+{
+	struct mlxsw_m *mlxsw_m = mlxsw_m_port->mlxsw_m;
+	struct net_device *dev = mlxsw_m_port->dev;
+	char ppad_pl[MLXSW_REG_PPAD_LEN];
+	int err;
+
+	mlxsw_reg_ppad_pack(ppad_pl, false, 0);
+	err = mlxsw_reg_query(mlxsw_m->core, MLXSW_REG(ppad), ppad_pl);
+	if (err)
+		return err;
+	mlxsw_reg_ppad_mac_memcpy_from(ppad_pl, dev->dev_addr);
+	/* The last byte value in base mac address is guaranteed
+	 * to be such it does not overflow when adding local_port
+	 * value.
+	 */
+	dev->dev_addr[ETH_ALEN - 1] += mlxsw_m_port->module + 1;
+	return 0;
+}
+
+static int
+mlxsw_m_port_create(struct mlxsw_m *mlxsw_m, u8 local_port, u8 module)
+{
+	struct mlxsw_m_port *mlxsw_m_port;
+	struct net_device *dev;
+	int err;
+
+	err = mlxsw_core_port_init(mlxsw_m->core, local_port);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Port %d: Failed to init core port\n",
+			local_port);
+		return err;
+	}
+
+	dev = alloc_etherdev(sizeof(struct mlxsw_m_port));
+	if (!dev) {
+		err = -ENOMEM;
+		goto err_alloc_etherdev;
+	}
+
+	SET_NETDEV_DEV(dev, mlxsw_m->bus_info->dev);
+	mlxsw_m_port = netdev_priv(dev);
+	mlxsw_m_port->dev = dev;
+	mlxsw_m_port->mlxsw_m = mlxsw_m;
+	mlxsw_m_port->local_port = local_port;
+	mlxsw_m_port->module = module;
+
+	dev->netdev_ops = &mlxsw_m_port_netdev_ops;
+	dev->ethtool_ops = &mlxsw_m_port_ethtool_ops;
+
+	err = mlxsw_m_port_dev_addr_get(mlxsw_m_port);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Port %d: Unable to get port mac address\n",
+			mlxsw_m_port->local_port);
+		goto err_dev_addr_get;
+	}
+
+	netif_carrier_off(dev);
+	mlxsw_m->ports[local_port] = mlxsw_m_port;
+	err = register_netdev(dev);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Port %d: Failed to register netdev\n",
+			mlxsw_m_port->local_port);
+		goto err_register_netdev;
+	}
+
+	mlxsw_core_port_eth_set(mlxsw_m->core, mlxsw_m_port->local_port,
+				mlxsw_m_port, dev, module + 1, false, 0);
+
+	return 0;
+
+err_register_netdev:
+	mlxsw_m->ports[local_port] = NULL;
+	free_netdev(dev);
+err_dev_addr_get:
+err_alloc_etherdev:
+	mlxsw_core_port_fini(mlxsw_m->core, local_port);
+	return err;
+}
+
+static void mlxsw_m_port_remove(struct mlxsw_m *mlxsw_m, u8 local_port)
+{
+	struct mlxsw_m_port *mlxsw_m_port = mlxsw_m->ports[local_port];
+
+	mlxsw_core_port_clear(mlxsw_m->core, local_port, mlxsw_m);
+	unregister_netdev(mlxsw_m_port->dev); /* This calls ndo_stop */
+	mlxsw_m->ports[local_port] = NULL;
+	free_netdev(mlxsw_m_port->dev);
+	mlxsw_core_port_fini(mlxsw_m->core, local_port);
+}
+
+static int mlxsw_m_port_module_map(struct mlxsw_m *mlxsw_m, u8 local_port,
+				   u8 *last_module)
+{
+	u8 module, width;
+	int err;
+
+	/* Fill out to local port mapping array */
+	err = mlxsw_m_port_module_info_get(mlxsw_m, local_port, &module,
+					   &width);
+	if (err)
+		return err;
+
+	if (!width)
+		return 0;
+	/* Skip, if port belongs to the cluster */
+	if (module == *last_module)
+		return 0;
+	*last_module = module;
+	mlxsw_m->module_to_port[module] = ++mlxsw_m->max_ports;
+
+	return 0;
+}
+
+static void mlxsw_m_port_module_unmap(struct mlxsw_m *mlxsw_m, u8 module)
+{
+	mlxsw_m->module_to_port[module] = -1;
+}
+
+static int mlxsw_m_ports_create(struct mlxsw_m *mlxsw_m)
+{
+	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_m->core);
+	u8 last_module = max_ports;
+	int i;
+	int err;
+
+	mlxsw_m->ports = kcalloc(max_ports, sizeof(*mlxsw_m->ports),
+				 GFP_KERNEL);
+	if (!mlxsw_m->ports)
+		return -ENOMEM;
+
+	mlxsw_m->module_to_port = kmalloc_array(max_ports, sizeof(int),
+						GFP_KERNEL);
+	if (!mlxsw_m->module_to_port) {
+		err = -ENOMEM;
+		goto err_module_to_port_alloc;
+	}
+
+	/* Invalidate the entries of module to local port mapping array */
+	for (i = 0; i < max_ports; i++)
+		mlxsw_m->module_to_port[i] = -1;
+
+	/* Fill out module to local port mapping array */
+	for (i = 1; i < max_ports; i++) {
+		err = mlxsw_m_port_module_map(mlxsw_m, i, &last_module);
+		if (err)
+			goto err_module_to_port_map;
+	}
+
+	/* Create port objects for each valid entry */
+	for (i = 0; i < mlxsw_m->max_ports; i++) {
+		if (mlxsw_m->module_to_port[i] > 0) {
+			err = mlxsw_m_port_create(mlxsw_m,
+						  mlxsw_m->module_to_port[i],
+						  i);
+			if (err)
+				goto err_module_to_port_create;
+		}
+	}
+
+	return 0;
+
+err_module_to_port_create:
+	for (i--; i >= 0; i--) {
+		if (mlxsw_m->module_to_port[i] > 0)
+			mlxsw_m_port_remove(mlxsw_m,
+					    mlxsw_m->module_to_port[i]);
+	}
+	i = max_ports;
+err_module_to_port_map:
+	for (i--; i > 0; i--)
+		mlxsw_m_port_module_unmap(mlxsw_m, i);
+	kfree(mlxsw_m->module_to_port);
+err_module_to_port_alloc:
+	kfree(mlxsw_m->ports);
+	return err;
+}
+
+static void mlxsw_m_ports_remove(struct mlxsw_m *mlxsw_m)
+{
+	int i;
+
+	for (i = 0; i < mlxsw_m->max_ports; i++) {
+		if (mlxsw_m->module_to_port[i] > 0) {
+			mlxsw_m_port_remove(mlxsw_m,
+					    mlxsw_m->module_to_port[i]);
+			mlxsw_m_port_module_unmap(mlxsw_m, i);
+		}
+	}
+
+	kfree(mlxsw_m->module_to_port);
+	kfree(mlxsw_m->ports);
+}
+
+static int mlxsw_m_init(struct mlxsw_core *mlxsw_core,
+			const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+	struct mlxsw_m *mlxsw_m = mlxsw_core_driver_priv(mlxsw_core);
+	int err;
+
+	mlxsw_m->core = mlxsw_core;
+	mlxsw_m->bus_info = mlxsw_bus_info;
+
+	err = mlxsw_m_base_mac_get(mlxsw_m);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Failed to get base mac\n");
+		return err;
+	}
+
+	err = mlxsw_m_ports_create(mlxsw_m);
+	if (err) {
+		dev_err(mlxsw_m->bus_info->dev, "Failed to create ports\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void mlxsw_m_fini(struct mlxsw_core *mlxsw_core)
+{
+	struct mlxsw_m *mlxsw_m = mlxsw_core_driver_priv(mlxsw_core);
+
+	mlxsw_m_ports_remove(mlxsw_m);
+}
+
+static const struct mlxsw_config_profile mlxsw_m_config_profile;
+
+static struct mlxsw_driver mlxsw_m_driver = {
+	.kind			= mlxsw_m_driver_name,
+	.priv_size		= sizeof(struct mlxsw_m),
+	.init			= mlxsw_m_init,
+	.fini			= mlxsw_m_fini,
+	.profile		= &mlxsw_m_config_profile,
+	.res_query_enabled	= true,
+};
+
+static const struct i2c_device_id mlxsw_m_i2c_id[] = {
 	{ "mlxsw_minimal", 0},
 	{ },
 };
 
-static struct i2c_driver mlxsw_minimal_i2c_driver = {
+static struct i2c_driver mlxsw_m_i2c_driver = {
 	.driver.name = "mlxsw_minimal",
 	.class = I2C_CLASS_HWMON,
-	.id_table = mlxsw_minimal_i2c_id,
+	.id_table = mlxsw_m_i2c_id,
 };
 
-static int __init mlxsw_minimal_module_init(void)
+static int __init mlxsw_m_module_init(void)
 {
 	int err;
 
-	err = mlxsw_core_driver_register(&mlxsw_minimal_driver);
+	err = mlxsw_core_driver_register(&mlxsw_m_driver);
 	if (err)
 		return err;
 
-	err = mlxsw_i2c_driver_register(&mlxsw_minimal_i2c_driver);
+	err = mlxsw_i2c_driver_register(&mlxsw_m_i2c_driver);
 	if (err)
 		goto err_i2c_driver_register;
 
 	return 0;
 
 err_i2c_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_minimal_driver);
+	mlxsw_core_driver_unregister(&mlxsw_m_driver);
 
 	return err;
 }
 
-static void __exit mlxsw_minimal_module_exit(void)
+static void __exit mlxsw_m_module_exit(void)
 {
-	mlxsw_i2c_driver_unregister(&mlxsw_minimal_i2c_driver);
-	mlxsw_core_driver_unregister(&mlxsw_minimal_driver);
+	mlxsw_i2c_driver_unregister(&mlxsw_m_i2c_driver);
+	mlxsw_core_driver_unregister(&mlxsw_m_driver);
 }
 
-module_init(mlxsw_minimal_module_init);
-module_exit(mlxsw_minimal_module_exit);
+module_init(mlxsw_m_module_init);
+module_exit(mlxsw_m_module_exit);
 
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox minimal driver");
-MODULE_DEVICE_TABLE(i2c, mlxsw_minimal_i2c_id);
+MODULE_DEVICE_TABLE(i2c, mlxsw_m_i2c_id);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 5890fdfd62c3..b40455f8293d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -604,29 +604,31 @@ static void mlxsw_pci_cq_tasklet(unsigned long data)
 		u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe);
 		u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe);
 		u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe);
+		char ncqe[MLXSW_PCI_CQE_SIZE_MAX];
+
+		memcpy(ncqe, cqe, q->elem_size);
+		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
 
 		if (sendq) {
 			struct mlxsw_pci_queue *sdq;
 
 			sdq = mlxsw_pci_sdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_sdq_handle(mlxsw_pci, sdq,
-						 wqe_counter, cqe);
+						 wqe_counter, ncqe);
 			q->u.cq.comp_sdq_count++;
 		} else {
 			struct mlxsw_pci_queue *rdq;
 
 			rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn);
 			mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq,
-						 wqe_counter, q->u.cq.v, cqe);
+						 wqe_counter, q->u.cq.v, ncqe);
 			q->u.cq.comp_rdq_count++;
 		}
 		if (++items == credits)
 			break;
 	}
-	if (items) {
-		mlxsw_pci_queue_doorbell_consumer_ring(mlxsw_pci, q);
+	if (items)
 		mlxsw_pci_queue_doorbell_arm_consumer_ring(mlxsw_pci, q);
-	}
 }
 
 static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q)
@@ -1037,42 +1039,6 @@ mlxsw_pci_config_profile_swid_config(struct mlxsw_pci *mlxsw_pci,
 	mlxsw_cmd_mbox_config_profile_swid_config_mask_set(mbox, index, mask);
 }
 
-static int mlxsw_pci_resources_query(struct mlxsw_pci *mlxsw_pci, char *mbox,
-				     struct mlxsw_res *res)
-{
-	int index, i;
-	u64 data;
-	u16 id;
-	int err;
-
-	if (!res)
-		return 0;
-
-	mlxsw_cmd_mbox_zero(mbox);
-
-	for (index = 0; index < MLXSW_CMD_QUERY_RESOURCES_MAX_QUERIES;
-	     index++) {
-		err = mlxsw_cmd_query_resources(mlxsw_pci->core, mbox, index);
-		if (err)
-			return err;
-
-		for (i = 0; i < MLXSW_CMD_QUERY_RESOURCES_PER_QUERY; i++) {
-			id = mlxsw_cmd_mbox_query_resource_id_get(mbox, i);
-			data = mlxsw_cmd_mbox_query_resource_data_get(mbox, i);
-
-			if (id == MLXSW_CMD_QUERY_RESOURCES_TABLE_END_ID)
-				return 0;
-
-			mlxsw_res_parse(res, id, data);
-		}
-	}
-
-	/* If after MLXSW_RESOURCES_QUERY_MAX_QUERIES we still didn't get
-	 * MLXSW_RESOURCES_TABLE_END_ID, something went bad in the FW.
-	 */
-	return -EIO;
-}
-
 static int
 mlxsw_pci_profile_get_kvd_sizes(const struct mlxsw_pci *mlxsw_pci,
 				const struct mlxsw_config_profile *profile,
@@ -1365,10 +1331,10 @@ static int mlxsw_pci_sw_reset(struct mlxsw_pci *mlxsw_pci,
 		u32 val = mlxsw_pci_read32(mlxsw_pci, FW_READY);
 
 		if ((val & MLXSW_PCI_FW_READY_MASK) == MLXSW_PCI_FW_READY_MAGIC)
-			break;
+			return 0;
 		cond_resched();
 	} while (time_before(jiffies, end));
-	return 0;
+	return -EBUSY;
 }
 
 static int mlxsw_pci_alloc_irq_vectors(struct mlxsw_pci *mlxsw_pci)
@@ -1457,7 +1423,7 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core,
 	if (err)
 		goto err_boardinfo;
 
-	err = mlxsw_pci_resources_query(mlxsw_pci, mbox, res);
+	err = mlxsw_core_resources_query(mlxsw_core, mbox, res);
 	if (err)
 		goto err_query_resources;
 
@@ -1720,7 +1686,6 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
 	struct mlxsw_pci *mlxsw_pci;
-	bool called_again = false;
 	int err;
 
 	mlxsw_pci = kzalloc(sizeof(*mlxsw_pci), GFP_KERNEL);
@@ -1777,18 +1742,10 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.dev = &pdev->dev;
 	mlxsw_pci->id = id;
 
-again:
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
 					     &mlxsw_pci_bus, mlxsw_pci, false,
 					     NULL);
-	/* -EAGAIN is returned in case the FW was updated. FW needs
-	 * a reset, so lets try to call mlxsw_core_bus_device_register()
-	 * again.
-	 */
-	if (err == -EAGAIN && !called_again) {
-		called_again = true;
-		goto again;
-	} else if (err) {
+	if (err) {
 		dev_err(&pdev->dev, "cannot register bus device\n");
 		goto err_bus_device_register;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index bb99f6d41fe0..8648ca171254 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -27,7 +27,7 @@
 
 #define MLXSW_PCI_SW_RESET			0xF0010
 #define MLXSW_PCI_SW_RESET_RST_BIT		BIT(0)
-#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	5000
+#define MLXSW_PCI_SW_RESET_TIMEOUT_MSECS	20000
 #define MLXSW_PCI_SW_RESET_WAIT_MSECS		100
 #define MLXSW_PCI_FW_READY			0xA1844
 #define MLXSW_PCI_FW_READY_MASK			0xFFFF
@@ -53,6 +53,7 @@
 #define MLXSW_PCI_WQE_SIZE	32 /* 32 bytes per element */
 #define MLXSW_PCI_CQE01_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_CQE2_SIZE	32 /* 32 bytes per element */
+#define MLXSW_PCI_CQE_SIZE_MAX	MLXSW_PCI_CQE2_SIZE
 #define MLXSW_PCI_EQE_SIZE	16 /* 16 bytes per element */
 #define MLXSW_PCI_WQE_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE)
 #define MLXSW_PCI_CQE01_COUNT	(MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index db3d2790aeec..eb4c5e8964cd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -641,6 +641,10 @@ enum mlxsw_reg_sfn_rec_type {
 	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC = 0x7,
 	/* Aged-out MAC address on a LAG port. */
 	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC_LAG = 0x8,
+	/* Learned unicast tunnel record. */
+	MLXSW_REG_SFN_REC_TYPE_LEARNED_UNICAST_TUNNEL = 0xD,
+	/* Aged-out unicast tunnel record. */
+	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_UNICAST_TUNNEL = 0xE,
 };
 
 /* reg_sfn_rec_type
@@ -704,6 +708,66 @@ static inline void mlxsw_reg_sfn_mac_lag_unpack(char *payload, int rec_index,
 	*p_lag_id = mlxsw_reg_sfn_mac_lag_lag_id_get(payload, rec_index);
 }
 
+/* reg_sfn_uc_tunnel_uip_msb
+ * When protocol is IPv4, the most significant byte of the underlay IPv4
+ * address of the remote VTEP.
+ * When protocol is IPv6, reserved.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_uip_msb, MLXSW_REG_SFN_BASE_LEN, 24,
+		     8, MLXSW_REG_SFN_REC_LEN, 0x08, false);
+
+enum mlxsw_reg_sfn_uc_tunnel_protocol {
+	MLXSW_REG_SFN_UC_TUNNEL_PROTOCOL_IPV4,
+	MLXSW_REG_SFN_UC_TUNNEL_PROTOCOL_IPV6,
+};
+
+/* reg_sfn_uc_tunnel_protocol
+ * IP protocol.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_protocol, MLXSW_REG_SFN_BASE_LEN, 27,
+		     1, MLXSW_REG_SFN_REC_LEN, 0x0C, false);
+
+/* reg_sfn_uc_tunnel_uip_lsb
+ * When protocol is IPv4, the least significant bytes of the underlay
+ * IPv4 address of the remote VTEP.
+ * When protocol is IPv6, ipv6_id to be queried from TNIPSD.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, uc_tunnel_uip_lsb, MLXSW_REG_SFN_BASE_LEN, 0,
+		     24, MLXSW_REG_SFN_REC_LEN, 0x0C, false);
+
+enum mlxsw_reg_sfn_tunnel_port {
+	MLXSW_REG_SFN_TUNNEL_PORT_NVE,
+	MLXSW_REG_SFN_TUNNEL_PORT_VPLS,
+	MLXSW_REG_SFN_TUNNEL_FLEX_TUNNEL0,
+	MLXSW_REG_SFN_TUNNEL_FLEX_TUNNEL1,
+};
+
+/* reg_sfn_uc_tunnel_port
+ * Tunnel port.
+ * Reserved on Spectrum.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, tunnel_port, MLXSW_REG_SFN_BASE_LEN, 0, 4,
+		     MLXSW_REG_SFN_REC_LEN, 0x10, false);
+
+static inline void
+mlxsw_reg_sfn_uc_tunnel_unpack(char *payload, int rec_index, char *mac,
+			       u16 *p_fid, u32 *p_uip,
+			       enum mlxsw_reg_sfn_uc_tunnel_protocol *p_proto)
+{
+	u32 uip_msb, uip_lsb;
+
+	mlxsw_reg_sfn_rec_mac_memcpy_from(payload, rec_index, mac);
+	*p_fid = mlxsw_reg_sfn_mac_fid_get(payload, rec_index);
+	uip_msb = mlxsw_reg_sfn_uc_tunnel_uip_msb_get(payload, rec_index);
+	uip_lsb = mlxsw_reg_sfn_uc_tunnel_uip_lsb_get(payload, rec_index);
+	*p_uip = uip_msb << 24 | uip_lsb;
+	*p_proto = mlxsw_reg_sfn_uc_tunnel_protocol_get(payload, rec_index);
+}
+
 /* SPMS - Switch Port MSTP/RSTP State Register
  * -------------------------------------------
  * Configures the spanning tree state of a physical port.
@@ -2135,6 +2199,14 @@ MLXSW_ITEM32(reg, pagt, size, 0x00, 0, 8);
  */
 MLXSW_ITEM32(reg, pagt, acl_group_id, 0x08, 0, 16);
 
+/* reg_pagt_multi
+ * Multi-ACL
+ * 0 - This ACL is the last ACL in the multi-ACL
+ * 1 - This ACL is part of a multi-ACL
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, pagt, multi, 0x30, 31, 1, 0x04, 0x00, false);
+
 /* reg_pagt_acl_id
  * ACL identifier
  * Access: RW
@@ -2148,12 +2220,13 @@ static inline void mlxsw_reg_pagt_pack(char *payload, u16 acl_group_id)
 }
 
 static inline void mlxsw_reg_pagt_acl_id_pack(char *payload, int index,
-					      u16 acl_id)
+					      u16 acl_id, bool multi)
 {
 	u8 size = mlxsw_reg_pagt_size_get(payload);
 
 	if (index >= size)
 		mlxsw_reg_pagt_size_set(payload, index + 1);
+	mlxsw_reg_pagt_multi_set(payload, index, multi);
 	mlxsw_reg_pagt_acl_id_set(payload, index, acl_id);
 }
 
@@ -2431,6 +2504,43 @@ static inline void mlxsw_reg_pefa_unpack(char *payload, bool *p_a)
 	*p_a = mlxsw_reg_pefa_a_get(payload);
 }
 
+/* PEMRBT - Policy-Engine Multicast Router Binding Table Register
+ * --------------------------------------------------------------
+ * This register is used for binding Multicast router to an ACL group
+ * that serves the MC router.
+ * This register is not supported by SwitchX/-2 and Spectrum.
+ */
+#define MLXSW_REG_PEMRBT_ID 0x3014
+#define MLXSW_REG_PEMRBT_LEN 0x14
+
+MLXSW_REG_DEFINE(pemrbt, MLXSW_REG_PEMRBT_ID, MLXSW_REG_PEMRBT_LEN);
+
+enum mlxsw_reg_pemrbt_protocol {
+	MLXSW_REG_PEMRBT_PROTO_IPV4,
+	MLXSW_REG_PEMRBT_PROTO_IPV6,
+};
+
+/* reg_pemrbt_protocol
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pemrbt, protocol, 0x00, 0, 1);
+
+/* reg_pemrbt_group_id
+ * ACL group identifier.
+ * Range 0..cap_max_acl_groups-1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pemrbt, group_id, 0x10, 0, 16);
+
+static inline void
+mlxsw_reg_pemrbt_pack(char *payload, enum mlxsw_reg_pemrbt_protocol protocol,
+		      u16 group_id)
+{
+	MLXSW_REG_ZERO(pemrbt, payload);
+	mlxsw_reg_pemrbt_protocol_set(payload, protocol);
+	mlxsw_reg_pemrbt_group_id_set(payload, group_id);
+}
+
 /* PTCE-V2 - Policy-Engine TCAM Entry Register Version 2
  * -----------------------------------------------------
  * This register is used for accessing rules within a TCAM region.
@@ -2642,7 +2752,7 @@ mlxsw_reg_perpt_pack(char *payload, u8 erpt_bank, u8 erpt_index,
 	mlxsw_reg_perpt_erpt_bank_set(payload, erpt_bank);
 	mlxsw_reg_perpt_erpt_index_set(payload, erpt_index);
 	mlxsw_reg_perpt_key_size_set(payload, key_size);
-	mlxsw_reg_perpt_bf_bypass_set(payload, true);
+	mlxsw_reg_perpt_bf_bypass_set(payload, false);
 	mlxsw_reg_perpt_erp_id_set(payload, erp_id);
 	mlxsw_reg_perpt_erpt_base_bank_set(payload, erpt_base_bank);
 	mlxsw_reg_perpt_erpt_base_index_set(payload, erpt_base_index);
@@ -2834,8 +2944,9 @@ static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid,
 					u32 priority,
 					const char *tcam_region_info,
 					const char *key, u8 erp_id,
-					bool large_exists, u32 lkey_id,
-					u32 action_pointer)
+					u16 delta_start, u8 delta_mask,
+					u8 delta_value, bool large_exists,
+					u32 lkey_id, u32 action_pointer)
 {
 	MLXSW_REG_ZERO(ptce3, payload);
 	mlxsw_reg_ptce3_v_set(payload, valid);
@@ -2844,6 +2955,9 @@ static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid,
 	mlxsw_reg_ptce3_tcam_region_info_memcpy_to(payload, tcam_region_info);
 	mlxsw_reg_ptce3_flex2_key_blocks_memcpy_to(payload, key);
 	mlxsw_reg_ptce3_erp_id_set(payload, erp_id);
+	mlxsw_reg_ptce3_delta_start_set(payload, delta_start);
+	mlxsw_reg_ptce3_delta_mask_set(payload, delta_mask);
+	mlxsw_reg_ptce3_delta_value_set(payload, delta_value);
 	mlxsw_reg_ptce3_large_exists_set(payload, large_exists);
 	mlxsw_reg_ptce3_large_entry_key_id_set(payload, lkey_id);
 	mlxsw_reg_ptce3_action_pointer_set(payload, action_pointer);
@@ -2901,7 +3015,7 @@ static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id)
 	mlxsw_reg_percr_region_id_set(payload, region_id);
 	mlxsw_reg_percr_atcam_ignore_prune_set(payload, false);
 	mlxsw_reg_percr_ctcam_ignore_prune_set(payload, false);
-	mlxsw_reg_percr_bf_bypass_set(payload, true);
+	mlxsw_reg_percr_bf_bypass_set(payload, false);
 }
 
 /* PERERP - Policy-Engine Region eRP Register
@@ -2990,6 +3104,72 @@ static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id,
 	mlxsw_reg_pererp_master_rp_id_set(payload, master_rp_id);
 }
 
+/* PEABFE - Policy-Engine Algorithmic Bloom Filter Entries Register
+ * ----------------------------------------------------------------
+ * This register configures the Bloom filter entries.
+ */
+#define MLXSW_REG_PEABFE_ID 0x3022
+#define MLXSW_REG_PEABFE_BASE_LEN 0x10
+#define MLXSW_REG_PEABFE_BF_REC_LEN 0x4
+#define MLXSW_REG_PEABFE_BF_REC_MAX_COUNT 256
+#define MLXSW_REG_PEABFE_LEN (MLXSW_REG_PEABFE_BASE_LEN + \
+			      MLXSW_REG_PEABFE_BF_REC_LEN * \
+			      MLXSW_REG_PEABFE_BF_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(peabfe, MLXSW_REG_PEABFE_ID, MLXSW_REG_PEABFE_LEN);
+
+/* reg_peabfe_size
+ * Number of BF entries to be updated.
+ * Range 1..256
+ * Access: Op
+ */
+MLXSW_ITEM32(reg, peabfe, size, 0x00, 0, 9);
+
+/* reg_peabfe_bf_entry_state
+ * Bloom filter state
+ * 0 - Clear
+ * 1 - Set
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, peabfe, bf_entry_state,
+		     MLXSW_REG_PEABFE_BASE_LEN,	31, 1,
+		     MLXSW_REG_PEABFE_BF_REC_LEN, 0x00, false);
+
+/* reg_peabfe_bf_entry_bank
+ * Bloom filter bank ID
+ * Range 0..cap_max_erp_table_banks-1
+ * Access: Index
+ */
+MLXSW_ITEM32_INDEXED(reg, peabfe, bf_entry_bank,
+		     MLXSW_REG_PEABFE_BASE_LEN,	24, 4,
+		     MLXSW_REG_PEABFE_BF_REC_LEN, 0x00, false);
+
+/* reg_peabfe_bf_entry_index
+ * Bloom filter entry index
+ * Range 0..2^cap_max_bf_log-1
+ * Access: Index
+ */
+MLXSW_ITEM32_INDEXED(reg, peabfe, bf_entry_index,
+		     MLXSW_REG_PEABFE_BASE_LEN,	0, 24,
+		     MLXSW_REG_PEABFE_BF_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_peabfe_pack(char *payload)
+{
+	MLXSW_REG_ZERO(peabfe, payload);
+}
+
+static inline void mlxsw_reg_peabfe_rec_pack(char *payload, int rec_index,
+					     u8 state, u8 bank, u32 bf_index)
+{
+	u8 num_rec = mlxsw_reg_peabfe_size_get(payload);
+
+	if (rec_index >= num_rec)
+		mlxsw_reg_peabfe_size_set(payload, rec_index + 1);
+	mlxsw_reg_peabfe_bf_entry_state_set(payload, rec_index, state);
+	mlxsw_reg_peabfe_bf_entry_bank_set(payload, rec_index, bank);
+	mlxsw_reg_peabfe_bf_entry_index_set(payload, rec_index, bf_index);
+}
+
 /* IEDR - Infrastructure Entry Delete Register
  * ----------------------------------------------------
  * This register is used for deleting entries from the entry tables.
@@ -3791,6 +3971,25 @@ enum {
  */
 MLXSW_ITEM32(reg, ptys, an_status, 0x04, 28, 4);
 
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M				BIT(0)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII			BIT(1)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII			BIT(2)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R				BIT(3)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G			BIT(4)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G		BIT(5)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR		BIT(6)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_2_LAUI_2_50GBASE_CR2_KR2	BIT(7)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR	BIT(8)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4		BIT(9)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2		BIT(10)
+#define MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4		BIT(12)
+
+/* reg_ptys_ext_eth_proto_cap
+ * Extended Ethernet port supported speeds and protocols.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32);
+
 #define MLXSW_REG_PTYS_ETH_SPEED_SGMII			BIT(0)
 #define MLXSW_REG_PTYS_ETH_SPEED_1000BASE_KX		BIT(1)
 #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CX4		BIT(2)
@@ -3845,6 +4044,12 @@ MLXSW_ITEM32(reg, ptys, ib_link_width_cap, 0x10, 16, 16);
  */
 MLXSW_ITEM32(reg, ptys, ib_proto_cap, 0x10, 0, 16);
 
+/* reg_ptys_ext_eth_proto_admin
+ * Extended speed and protocol to set port to.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptys, ext_eth_proto_admin, 0x14, 0, 32);
+
 /* reg_ptys_eth_proto_admin
  * Speed and protocol to set port to.
  * Access: RW
@@ -3863,6 +4068,12 @@ MLXSW_ITEM32(reg, ptys, ib_link_width_admin, 0x1C, 16, 16);
  */
 MLXSW_ITEM32(reg, ptys, ib_proto_admin, 0x1C, 0, 16);
 
+/* reg_ptys_ext_eth_proto_oper
+ * The extended current speed and protocol configured for the port.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, ptys, ext_eth_proto_oper, 0x20, 0, 32);
+
 /* reg_ptys_eth_proto_oper
  * The current speed and protocol configured for the port.
  * Access: RO
@@ -3881,12 +4092,23 @@ MLXSW_ITEM32(reg, ptys, ib_link_width_oper, 0x28, 16, 16);
  */
 MLXSW_ITEM32(reg, ptys, ib_proto_oper, 0x28, 0, 16);
 
-/* reg_ptys_eth_proto_lp_advertise
- * The protocols that were advertised by the link partner during
- * autonegotiation.
+enum mlxsw_reg_ptys_connector_type {
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_UNKNOWN_OR_NO_CONNECTOR,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_NONE,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_TP,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_AUI,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_BNC,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_MII,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_FIBRE,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_DA,
+	MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_OTHER,
+};
+
+/* reg_ptys_connector_type
+ * Connector type indication.
  * Access: RO
  */
-MLXSW_ITEM32(reg, ptys, eth_proto_lp_advertise, 0x30, 0, 32);
+MLXSW_ITEM32(reg, ptys, connector_type, 0x2C, 0, 4);
 
 static inline void mlxsw_reg_ptys_eth_pack(char *payload, u8 local_port,
 					   u32 proto_admin, bool autoneg)
@@ -3898,17 +4120,46 @@ static inline void mlxsw_reg_ptys_eth_pack(char *payload, u8 local_port,
 	mlxsw_reg_ptys_an_disable_admin_set(payload, !autoneg);
 }
 
+static inline void mlxsw_reg_ptys_ext_eth_pack(char *payload, u8 local_port,
+					       u32 proto_admin, bool autoneg)
+{
+	MLXSW_REG_ZERO(ptys, payload);
+	mlxsw_reg_ptys_local_port_set(payload, local_port);
+	mlxsw_reg_ptys_proto_mask_set(payload, MLXSW_REG_PTYS_PROTO_MASK_ETH);
+	mlxsw_reg_ptys_ext_eth_proto_admin_set(payload, proto_admin);
+	mlxsw_reg_ptys_an_disable_admin_set(payload, !autoneg);
+}
+
 static inline void mlxsw_reg_ptys_eth_unpack(char *payload,
 					     u32 *p_eth_proto_cap,
-					     u32 *p_eth_proto_adm,
+					     u32 *p_eth_proto_admin,
 					     u32 *p_eth_proto_oper)
 {
 	if (p_eth_proto_cap)
-		*p_eth_proto_cap = mlxsw_reg_ptys_eth_proto_cap_get(payload);
-	if (p_eth_proto_adm)
-		*p_eth_proto_adm = mlxsw_reg_ptys_eth_proto_admin_get(payload);
+		*p_eth_proto_cap =
+			mlxsw_reg_ptys_eth_proto_cap_get(payload);
+	if (p_eth_proto_admin)
+		*p_eth_proto_admin =
+			mlxsw_reg_ptys_eth_proto_admin_get(payload);
 	if (p_eth_proto_oper)
-		*p_eth_proto_oper = mlxsw_reg_ptys_eth_proto_oper_get(payload);
+		*p_eth_proto_oper =
+			mlxsw_reg_ptys_eth_proto_oper_get(payload);
+}
+
+static inline void mlxsw_reg_ptys_ext_eth_unpack(char *payload,
+						 u32 *p_eth_proto_cap,
+						 u32 *p_eth_proto_admin,
+						 u32 *p_eth_proto_oper)
+{
+	if (p_eth_proto_cap)
+		*p_eth_proto_cap =
+			mlxsw_reg_ptys_ext_eth_proto_cap_get(payload);
+	if (p_eth_proto_admin)
+		*p_eth_proto_admin =
+			mlxsw_reg_ptys_ext_eth_proto_admin_get(payload);
+	if (p_eth_proto_oper)
+		*p_eth_proto_oper =
+			mlxsw_reg_ptys_ext_eth_proto_oper_get(payload);
 }
 
 static inline void mlxsw_reg_ptys_ib_pack(char *payload, u8 local_port,
@@ -4231,8 +4482,11 @@ MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2);
 
 enum mlxsw_reg_ppcnt_grp {
 	MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0,
+	MLXSW_REG_PPCNT_RFC_2863_CNT = 0x1,
 	MLXSW_REG_PPCNT_RFC_2819_CNT = 0x2,
+	MLXSW_REG_PPCNT_RFC_3635_CNT = 0x3,
 	MLXSW_REG_PPCNT_EXT_CNT = 0x5,
+	MLXSW_REG_PPCNT_DISCARD_CNT = 0x6,
 	MLXSW_REG_PPCNT_PRIO_CNT = 0x10,
 	MLXSW_REG_PPCNT_TC_CNT = 0x11,
 	MLXSW_REG_PPCNT_TC_CONG_TC = 0x13,
@@ -4247,6 +4501,7 @@ enum mlxsw_reg_ppcnt_grp {
  * 0x2: RFC 2819 Counters
  * 0x3: RFC 3635 Counters
  * 0x5: Ethernet Extended Counters
+ * 0x6: Ethernet Discard Counters
  * 0x8: Link Level Retransmission Counters
  * 0x10: Per Priority Counters
  * 0x11: Per Traffic Class Counters
@@ -4390,8 +4645,46 @@ MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_received,
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
 
+/* Ethernet RFC 2863 Counter Group */
+
+/* reg_ppcnt_if_in_discards
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, if_in_discards,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x10, 0, 64);
+
+/* reg_ppcnt_if_out_discards
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, if_out_discards,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x38, 0, 64);
+
+/* reg_ppcnt_if_out_errors
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, if_out_errors,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
+
 /* Ethernet RFC 2819 Counter Group */
 
+/* reg_ppcnt_ether_stats_undersize_pkts
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_undersize_pkts,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x30, 0, 64);
+
+/* reg_ppcnt_ether_stats_oversize_pkts
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_oversize_pkts,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x38, 0, 64);
+
+/* reg_ppcnt_ether_stats_fragments
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_fragments,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
+
 /* reg_ppcnt_ether_stats_pkts64octets
  * Access: RO
  */
@@ -4452,6 +4745,32 @@ MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts4096to8191octets,
 MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0xA0, 0, 64);
 
+/* Ethernet RFC 3635 Counter Group */
+
+/* reg_ppcnt_dot3stats_fcs_errors
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3stats_fcs_errors,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
+
+/* reg_ppcnt_dot3stats_symbol_errors
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3stats_symbol_errors,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_dot3control_in_unknown_opcodes
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3control_in_unknown_opcodes,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
+
+/* reg_ppcnt_dot3in_pause_frames
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, dot3in_pause_frames,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
 /* Ethernet Extended Counter Group Counters */
 
 /* reg_ppcnt_ecn_marked
@@ -4460,6 +4779,80 @@ MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
 MLXSW_ITEM64(reg, ppcnt, ecn_marked,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
 
+/* Ethernet Discard Counter Group Counters */
+
+/* reg_ppcnt_ingress_general
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_general,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x00, 0, 64);
+
+/* reg_ppcnt_ingress_policy_engine
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_policy_engine,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x08, 0, 64);
+
+/* reg_ppcnt_ingress_vlan_membership
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_vlan_membership,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x10, 0, 64);
+
+/* reg_ppcnt_ingress_tag_frame_type
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_tag_frame_type,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x18, 0, 64);
+
+/* reg_ppcnt_egress_vlan_membership
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_vlan_membership,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x20, 0, 64);
+
+/* reg_ppcnt_loopback_filter
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, loopback_filter,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x28, 0, 64);
+
+/* reg_ppcnt_egress_general
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_general,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x30, 0, 64);
+
+/* reg_ppcnt_egress_hoq
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_hoq,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x40, 0, 64);
+
+/* reg_ppcnt_egress_policy_engine
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_policy_engine,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x50, 0, 64);
+
+/* reg_ppcnt_ingress_tx_link_down
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ingress_tx_link_down,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
+
+/* reg_ppcnt_egress_stp_filter
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_stp_filter,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_egress_sll
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, egress_sll,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
 /* Ethernet Per Priority Group Counters */
 
 /* reg_ppcnt_rx_octets
@@ -4862,6 +5255,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_MLD,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6_ND,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
 };
 
 /* reg_htgt_trap_group
@@ -5352,6 +5746,8 @@ enum mlxsw_reg_ritr_loopback_protocol {
 	MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4,
 	/* IPinIP IPv6 underlay Unicast */
 	MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV6,
+	/* IPinIP generic - used for Spectrum-2 underlay RIF */
+	MLXSW_REG_RITR_LOOPBACK_GENERIC,
 };
 
 /* reg_ritr_loopback_protocol
@@ -5392,6 +5788,13 @@ MLXSW_ITEM32(reg, ritr, loopback_ipip_options, 0x10, 20, 4);
  */
 MLXSW_ITEM32(reg, ritr, loopback_ipip_uvr, 0x10, 0, 16);
 
+/* reg_ritr_loopback_ipip_underlay_rif
+ * Underlay ingress router interface.
+ * Reserved for Spectrum.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, loopback_ipip_underlay_rif, 0x14, 0, 16);
+
 /* reg_ritr_loopback_ipip_usip*
  * Encapsulation Underlay source IP.
  * Access: RW
@@ -5507,11 +5910,12 @@ static inline void
 mlxsw_reg_ritr_loopback_ipip_common_pack(char *payload,
 			    enum mlxsw_reg_ritr_loopback_ipip_type ipip_type,
 			    enum mlxsw_reg_ritr_loopback_ipip_options options,
-			    u16 uvr_id, u32 gre_key)
+			    u16 uvr_id, u16 underlay_rif, u32 gre_key)
 {
 	mlxsw_reg_ritr_loopback_ipip_type_set(payload, ipip_type);
 	mlxsw_reg_ritr_loopback_ipip_options_set(payload, options);
 	mlxsw_reg_ritr_loopback_ipip_uvr_set(payload, uvr_id);
+	mlxsw_reg_ritr_loopback_ipip_underlay_rif_set(payload, underlay_rif);
 	mlxsw_reg_ritr_loopback_ipip_gre_key_set(payload, gre_key);
 }
 
@@ -5519,12 +5923,12 @@ static inline void
 mlxsw_reg_ritr_loopback_ipip4_pack(char *payload,
 			    enum mlxsw_reg_ritr_loopback_ipip_type ipip_type,
 			    enum mlxsw_reg_ritr_loopback_ipip_options options,
-			    u16 uvr_id, u32 usip, u32 gre_key)
+			    u16 uvr_id, u16 underlay_rif, u32 usip, u32 gre_key)
 {
 	mlxsw_reg_ritr_loopback_protocol_set(payload,
 				    MLXSW_REG_RITR_LOOPBACK_PROTOCOL_IPIP_IPV4);
 	mlxsw_reg_ritr_loopback_ipip_common_pack(payload, ipip_type, options,
-						 uvr_id, gre_key);
+						 uvr_id, underlay_rif, gre_key);
 	mlxsw_reg_ritr_loopback_ipip_usip4_set(payload, usip);
 }
 
@@ -6886,6 +7290,13 @@ MLXSW_ITEM32(reg, rtdp, type, 0x00, 28, 4);
  */
 MLXSW_ITEM32(reg, rtdp, tunnel_index, 0x00, 0, 24);
 
+/* reg_rtdp_egress_router_interface
+ * Underlay egress router interface.
+ * Valid range is from 0 to cap_max_router_interfaces - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, rtdp, egress_router_interface, 0x40, 0, 16);
+
 /* IPinIP */
 
 /* reg_rtdp_ipip_irif
@@ -7535,6 +7946,35 @@ static inline void mlxsw_reg_mfsl_unpack(char *payload, u8 tacho,
 		*p_tach_max = mlxsw_reg_mfsl_tach_max_get(payload);
 }
 
+/* FORE - Fan Out of Range Event Register
+ * --------------------------------------
+ * This register reports the status of the controlled fans compared to the
+ * range defined by the MFSL register.
+ */
+#define MLXSW_REG_FORE_ID 0x9007
+#define MLXSW_REG_FORE_LEN 0x0C
+
+MLXSW_REG_DEFINE(fore, MLXSW_REG_FORE_ID, MLXSW_REG_FORE_LEN);
+
+/* fan_under_limit
+ * Fan speed is below the low limit defined in MFSL register. Each bit relates
+ * to a single tachometer and indicates the specific tachometer reading is
+ * below the threshold.
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, fore, fan_under_limit, 0x00, 16, 10);
+
+static inline void mlxsw_reg_fore_unpack(char *payload, u8 tacho,
+					 bool *fault)
+{
+	u16 limit;
+
+	if (fault) {
+		limit = mlxsw_reg_fore_fan_under_limit_get(payload);
+		*fault = limit & BIT(tacho);
+	}
+}
+
 /* MTCAP - Management Temperature Capabilities
  * -------------------------------------------
  * This register exposes the capabilities of the device and
@@ -7661,6 +8101,80 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp,
 		mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name);
 }
 
+/* MTBR - Management Temperature Bulk Register
+ * -------------------------------------------
+ * This register is used for bulk temperature reading.
+ */
+#define MLXSW_REG_MTBR_ID 0x900F
+#define MLXSW_REG_MTBR_BASE_LEN 0x10 /* base length, without records */
+#define MLXSW_REG_MTBR_REC_LEN 0x04 /* record length */
+#define MLXSW_REG_MTBR_REC_MAX_COUNT 47 /* firmware limitation */
+#define MLXSW_REG_MTBR_LEN (MLXSW_REG_MTBR_BASE_LEN +	\
+			    MLXSW_REG_MTBR_REC_LEN *	\
+			    MLXSW_REG_MTBR_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(mtbr, MLXSW_REG_MTBR_ID, MLXSW_REG_MTBR_LEN);
+
+/* reg_mtbr_base_sensor_index
+ * Base sensors index to access (0 - ASIC sensor, 1-63 - ambient sensors,
+ * 64-127 are mapped to the SFP+/QSFP modules sequentially).
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mtbr, base_sensor_index, 0x00, 0, 7);
+
+/* reg_mtbr_num_rec
+ * Request: Number of records to read
+ * Response: Number of records read
+ * See above description for more details.
+ * Range 1..255
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mtbr, num_rec, 0x04, 0, 8);
+
+/* reg_mtbr_rec_max_temp
+ * The highest measured temperature from the sensor.
+ * When the bit mte is cleared, the field max_temperature is reserved.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtbr, rec_max_temp, MLXSW_REG_MTBR_BASE_LEN, 16,
+		     16, MLXSW_REG_MTBR_REC_LEN, 0x00, false);
+
+/* reg_mtbr_rec_temp
+ * Temperature reading from the sensor. Reading is in 0..125 Celsius
+ * degrees units.
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, mtbr, rec_temp, MLXSW_REG_MTBR_BASE_LEN, 0, 16,
+		     MLXSW_REG_MTBR_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_mtbr_pack(char *payload, u8 base_sensor_index,
+				       u8 num_rec)
+{
+	MLXSW_REG_ZERO(mtbr, payload);
+	mlxsw_reg_mtbr_base_sensor_index_set(payload, base_sensor_index);
+	mlxsw_reg_mtbr_num_rec_set(payload, num_rec);
+}
+
+/* Error codes from temperatute reading */
+enum mlxsw_reg_mtbr_temp_status {
+	MLXSW_REG_MTBR_NO_CONN		= 0x8000,
+	MLXSW_REG_MTBR_NO_TEMP_SENS	= 0x8001,
+	MLXSW_REG_MTBR_INDEX_NA		= 0x8002,
+	MLXSW_REG_MTBR_BAD_SENS_INFO	= 0x8003,
+};
+
+/* Base index for reading modules temperature */
+#define MLXSW_REG_MTBR_BASE_MODULE_INDEX 64
+
+static inline void mlxsw_reg_mtbr_temp_unpack(char *payload, int rec_ind,
+					      u16 *p_temp, u16 *p_max_temp)
+{
+	if (p_temp)
+		*p_temp = mlxsw_reg_mtbr_rec_temp_get(payload, rec_ind);
+	if (p_max_temp)
+		*p_max_temp = mlxsw_reg_mtbr_rec_max_temp_get(payload, rec_ind);
+}
+
 /* MCIA - Management Cable Info Access
  * -----------------------------------
  * MCIA register is used to access the SFP+ and QSFP connector's EPROM.
@@ -7715,13 +8229,41 @@ MLXSW_ITEM32(reg, mcia, device_address, 0x04, 0, 16);
  */
 MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16);
 
-#define MLXSW_SP_REG_MCIA_EEPROM_SIZE 48
+#define MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH	256
+#define MLXSW_REG_MCIA_EEPROM_SIZE		48
+#define MLXSW_REG_MCIA_I2C_ADDR_LOW		0x50
+#define MLXSW_REG_MCIA_I2C_ADDR_HIGH		0x51
+#define MLXSW_REG_MCIA_PAGE0_LO_OFF		0xa0
+#define MLXSW_REG_MCIA_TH_ITEM_SIZE		2
+#define MLXSW_REG_MCIA_TH_PAGE_NUM		3
+#define MLXSW_REG_MCIA_PAGE0_LO			0
+#define MLXSW_REG_MCIA_TH_PAGE_OFF		0x80
+
+enum mlxsw_reg_mcia_eeprom_module_info_rev_id {
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_UNSPC	= 0x00,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8436	= 0x01,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636	= 0x03,
+};
+
+enum mlxsw_reg_mcia_eeprom_module_info_id {
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP	= 0x03,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP	= 0x0C,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS	= 0x0D,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28	= 0x11,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD	= 0x18,
+};
+
+enum mlxsw_reg_mcia_eeprom_module_info {
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID,
+	MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE,
+};
 
 /* reg_mcia_eeprom
  * Bytes to read/write.
  * Access: RW
  */
-MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
+MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE);
 
 static inline void mlxsw_reg_mcia_pack(char *payload, u8 module, u8 lock,
 				       u8 page_number, u16 device_addr,
@@ -9357,8 +9899,10 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(ppbs),
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
+	MLXSW_REG(pemrbt),
 	MLXSW_REG(ptce2),
 	MLXSW_REG(perpt),
+	MLXSW_REG(peabfe),
 	MLXSW_REG(perar),
 	MLXSW_REG(ptce3),
 	MLXSW_REG(percr),
@@ -9407,8 +9951,10 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mfsc),
 	MLXSW_REG(mfsm),
 	MLXSW_REG(mfsl),
+	MLXSW_REG(fore),
 	MLXSW_REG(mtcap),
 	MLXSW_REG(mtmp),
+	MLXSW_REG(mtbr),
 	MLXSW_REG(mcia),
 	MLXSW_REG(mpat),
 	MLXSW_REG(mpar),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 99b341539870..773ef7fdb285 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -26,6 +26,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_MAX_LAG_MEMBERS,
 	MLXSW_RES_ID_MAX_BUFFER_SIZE,
 	MLXSW_RES_ID_CELL_SIZE,
+	MLXSW_RES_ID_MAX_HEADROOM_SIZE,
 	MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS,
 	MLXSW_RES_ID_ACL_MAX_TCAM_RULES,
 	MLXSW_RES_ID_ACL_MAX_REGIONS,
@@ -41,6 +42,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB,
 	MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB,
 	MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB,
+	MLXSW_RES_ID_ACL_MAX_BF_LOG,
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
@@ -78,6 +80,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_MAX_LAG_MEMBERS] = 0x2521,
 	[MLXSW_RES_ID_MAX_BUFFER_SIZE] = 0x2802,	/* Bytes */
 	[MLXSW_RES_ID_CELL_SIZE] = 0x2803,	/* Bytes */
+	[MLXSW_RES_ID_MAX_HEADROOM_SIZE] = 0x2811,	/* Bytes */
 	[MLXSW_RES_ID_ACL_MAX_TCAM_REGIONS] = 0x2901,
 	[MLXSW_RES_ID_ACL_MAX_TCAM_RULES] = 0x2902,
 	[MLXSW_RES_ID_ACL_MAX_REGIONS] = 0x2903,
@@ -93,6 +96,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB] = 0x2951,
 	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB] = 0x2952,
 	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB] = 0x2953,
+	[MLXSW_RES_ID_ACL_MAX_BF_LOG] = 0x2960,
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f84b9c02fcc5..6b8aa3761899 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -32,6 +32,7 @@
 #include "spectrum.h"
 #include "pci.h"
 #include "core.h"
+#include "core_env.h"
 #include "reg.h"
 #include "port.h"
 #include "trap.h"
@@ -45,8 +46,8 @@
 #define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
 
 #define MLXSW_SP1_FWREV_MAJOR 13
-#define MLXSW_SP1_FWREV_MINOR 1703
-#define MLXSW_SP1_FWREV_SUBMINOR 4
+#define MLXSW_SP1_FWREV_MINOR 1910
+#define MLXSW_SP1_FWREV_SUBMINOR 622
 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
 
 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
@@ -65,6 +66,13 @@ static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum";
 static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2";
 static const char mlxsw_sp_driver_version[] = "1.0";
 
+static const unsigned char mlxsw_sp1_mac_mask[ETH_ALEN] = {
+	0xff, 0xff, 0xff, 0xff, 0xfc, 0x00
+};
+static const unsigned char mlxsw_sp2_mac_mask[ETH_ALEN] = {
+	0xff, 0xff, 0xff, 0xff, 0xf0, 0x00
+};
+
 /* tx_hdr_version
  * Tx header version.
  * Must be set to 1.
@@ -323,6 +331,7 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 	const struct mlxsw_fw_rev *rev = &mlxsw_sp->bus_info->fw_rev;
 	const struct mlxsw_fw_rev *req_rev = mlxsw_sp->req_rev;
 	const char *fw_filename = mlxsw_sp->fw_filename;
+	union devlink_param_value value;
 	const struct firmware *firmware;
 	int err;
 
@@ -330,6 +339,15 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 	if (!req_rev || !fw_filename)
 		return 0;
 
+	/* Don't check if devlink 'fw_load_policy' param is 'flash' */
+	err = devlink_param_driverinit_value_get(priv_to_devlink(mlxsw_sp->core),
+						 DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+						 &value);
+	if (err)
+		return err;
+	if (value.vu8 == DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH)
+		return 0;
+
 	/* Validate driver & FW are compatible */
 	if (rev->major != req_rev->major) {
 		WARN(1, "Mismatch in major FW version [%d:%d] is never expected; Please contact support\n",
@@ -835,8 +853,12 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	u8 pfc_en = !!my_pfc ? my_pfc->pfc_en : 0;
 	u16 delay = !!my_pfc ? my_pfc->delay : 0;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
+	u32 taken_headroom_cells = 0;
+	u32 max_headroom_cells;
 	int i, j, err;
 
+	max_headroom_cells = mlxsw_sp_sb_max_headroom_cells(mlxsw_sp);
+
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port, 0, 0);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
 	if (err)
@@ -845,8 +867,10 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		bool configure = false;
 		bool pfc = false;
+		u16 thres_cells;
+		u16 delay_cells;
+		u16 total_cells;
 		bool lossy;
-		u16 thres;
 
 		for (j = 0; j < IEEE_8021QAZ_MAX_TCS; j++) {
 			if (prio_tc[j] == i) {
@@ -860,10 +884,17 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu,
 			continue;
 
 		lossy = !(pfc || pause_en);
-		thres = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
-		delay = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay, pfc,
-						  pause_en);
-		mlxsw_sp_pg_buf_pack(pbmc_pl, i, thres + delay, thres, lossy);
+		thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+		delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
+							pfc, pause_en);
+		total_cells = thres_cells + delay_cells;
+
+		taken_headroom_cells += total_cells;
+		if (taken_headroom_cells > max_headroom_cells)
+			return -ENOBUFS;
+
+		mlxsw_sp_pg_buf_pack(pbmc_pl, i, total_cells,
+				     thres_cells, lossy);
 	}
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pbmc), pbmc_pl);
@@ -1123,22 +1154,40 @@ int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 	return 0;
 }
 
-static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port)
+static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port,
+				     bool flush_default)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan, *tmp;
 
 	list_for_each_entry_safe(mlxsw_sp_port_vlan, tmp,
-				 &mlxsw_sp_port->vlans_list, list)
-		mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+				 &mlxsw_sp_port->vlans_list, list) {
+		if (!flush_default &&
+		    mlxsw_sp_port_vlan->vid == MLXSW_SP_DEFAULT_VID)
+			continue;
+		mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+	}
+}
+
+static void
+mlxsw_sp_port_vlan_cleanup(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
+{
+	if (mlxsw_sp_port_vlan->bridge_port)
+		mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
+	else if (mlxsw_sp_port_vlan->fid)
+		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 }
 
-static struct mlxsw_sp_port_vlan *
+struct mlxsw_sp_port_vlan *
 mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-	bool untagged = vid == 1;
+	bool untagged = vid == MLXSW_SP_DEFAULT_VID;
 	int err;
 
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
+	if (mlxsw_sp_port_vlan)
+		return ERR_PTR(-EEXIST);
+
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true, untagged);
 	if (err)
 		return ERR_PTR(err);
@@ -1150,7 +1199,6 @@ mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 	}
 
 	mlxsw_sp_port_vlan->mlxsw_sp_port = mlxsw_sp_port;
-	mlxsw_sp_port_vlan->ref_count = 1;
 	mlxsw_sp_port_vlan->vid = vid;
 	list_add(&mlxsw_sp_port_vlan->list, &mlxsw_sp_port->vlans_list);
 
@@ -1161,46 +1209,17 @@ err_port_vlan_alloc:
 	return ERR_PTR(err);
 }
 
-static void
-mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
+void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
+	mlxsw_sp_port_vlan_cleanup(mlxsw_sp_port_vlan);
 	list_del(&mlxsw_sp_port_vlan->list);
 	kfree(mlxsw_sp_port_vlan);
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
 }
 
-struct mlxsw_sp_port_vlan *
-mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
-{
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (mlxsw_sp_port_vlan) {
-		mlxsw_sp_port_vlan->ref_count++;
-		return mlxsw_sp_port_vlan;
-	}
-
-	return mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid);
-}
-
-void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
-{
-	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
-
-	if (--mlxsw_sp_port_vlan->ref_count != 0)
-		return;
-
-	if (mlxsw_sp_port_vlan->bridge_port)
-		mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
-	else if (fid)
-		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
-
-	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
-}
-
 static int mlxsw_sp_port_add_vid(struct net_device *dev,
 				 __be16 __always_unused proto, u16 vid)
 {
@@ -1212,7 +1231,7 @@ static int mlxsw_sp_port_add_vid(struct net_device *dev,
 	if (!vid)
 		return 0;
 
-	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_get(mlxsw_sp_port, vid));
+	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid));
 }
 
 static int mlxsw_sp_port_kill_vid(struct net_device *dev,
@@ -1230,7 +1249,7 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (!mlxsw_sp_port_vlan)
 		return 0;
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 
 	return 0;
 }
@@ -1342,7 +1361,6 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp_port_mall_tc_entry *mall_tc_entry;
 	__be16 protocol = f->common.protocol;
 	const struct tc_action *a;
-	LIST_HEAD(actions);
 	int err;
 
 	if (!tcf_exts_has_one_action(f->exts)) {
@@ -1696,6 +1714,18 @@ static int mlxsw_sp_set_features(struct net_device *dev,
 				       mlxsw_sp_feature_hw_tc);
 }
 
+static int mlxsw_sp_port_get_port_parent_id(struct net_device *dev,
+					    struct netdev_phys_item_id *ppid)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+
+	ppid->id_len = sizeof(mlxsw_sp->base_mac);
+	memcpy(&ppid->id, &mlxsw_sp->base_mac, ppid->id_len);
+
+	return 0;
+}
+
 static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_open		= mlxsw_sp_port_open,
 	.ndo_stop		= mlxsw_sp_port_stop,
@@ -1711,6 +1741,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_vlan_rx_kill_vid	= mlxsw_sp_port_kill_vid,
 	.ndo_get_phys_port_name	= mlxsw_sp_port_get_phys_port_name,
 	.ndo_set_features	= mlxsw_sp_set_features,
+	.ndo_get_port_parent_id	= mlxsw_sp_port_get_port_parent_id,
 };
 
 static void mlxsw_sp_port_get_drvinfo(struct net_device *dev,
@@ -1881,8 +1912,38 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
 
 #define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats)
 
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2863_stats[] = {
+	{
+		.str = "if_in_discards",
+		.getter = mlxsw_reg_ppcnt_if_in_discards_get,
+	},
+	{
+		.str = "if_out_discards",
+		.getter = mlxsw_reg_ppcnt_if_out_discards_get,
+	},
+	{
+		.str = "if_out_errors",
+		.getter = mlxsw_reg_ppcnt_if_out_errors_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2863_stats)
+
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
 	{
+		.str = "ether_stats_undersize_pkts",
+		.getter = mlxsw_reg_ppcnt_ether_stats_undersize_pkts_get,
+	},
+	{
+		.str = "ether_stats_oversize_pkts",
+		.getter = mlxsw_reg_ppcnt_ether_stats_oversize_pkts_get,
+	},
+	{
+		.str = "ether_stats_fragments",
+		.getter = mlxsw_reg_ppcnt_ether_stats_fragments_get,
+	},
+	{
 		.str = "ether_pkts64octets",
 		.getter = mlxsw_reg_ppcnt_ether_stats_pkts64octets_get,
 	},
@@ -1927,6 +1988,82 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
 #define MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN \
 	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2819_stats)
 
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_3635_stats[] = {
+	{
+		.str = "dot3stats_fcs_errors",
+		.getter = mlxsw_reg_ppcnt_dot3stats_fcs_errors_get,
+	},
+	{
+		.str = "dot3stats_symbol_errors",
+		.getter = mlxsw_reg_ppcnt_dot3stats_symbol_errors_get,
+	},
+	{
+		.str = "dot3control_in_unknown_opcodes",
+		.getter = mlxsw_reg_ppcnt_dot3control_in_unknown_opcodes_get,
+	},
+	{
+		.str = "dot3in_pause_frames",
+		.getter = mlxsw_reg_ppcnt_dot3in_pause_frames_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_3635_stats)
+
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_discard_stats[] = {
+	{
+		.str = "discard_ingress_general",
+		.getter = mlxsw_reg_ppcnt_ingress_general_get,
+	},
+	{
+		.str = "discard_ingress_policy_engine",
+		.getter = mlxsw_reg_ppcnt_ingress_policy_engine_get,
+	},
+	{
+		.str = "discard_ingress_vlan_membership",
+		.getter = mlxsw_reg_ppcnt_ingress_vlan_membership_get,
+	},
+	{
+		.str = "discard_ingress_tag_frame_type",
+		.getter = mlxsw_reg_ppcnt_ingress_tag_frame_type_get,
+	},
+	{
+		.str = "discard_egress_vlan_membership",
+		.getter = mlxsw_reg_ppcnt_egress_vlan_membership_get,
+	},
+	{
+		.str = "discard_loopback_filter",
+		.getter = mlxsw_reg_ppcnt_loopback_filter_get,
+	},
+	{
+		.str = "discard_egress_general",
+		.getter = mlxsw_reg_ppcnt_egress_general_get,
+	},
+	{
+		.str = "discard_egress_hoq",
+		.getter = mlxsw_reg_ppcnt_egress_hoq_get,
+	},
+	{
+		.str = "discard_egress_policy_engine",
+		.getter = mlxsw_reg_ppcnt_egress_policy_engine_get,
+	},
+	{
+		.str = "discard_ingress_tx_link_down",
+		.getter = mlxsw_reg_ppcnt_ingress_tx_link_down_get,
+	},
+	{
+		.str = "discard_egress_stp_filter",
+		.getter = mlxsw_reg_ppcnt_egress_stp_filter_get,
+	},
+	{
+		.str = "discard_egress_sll",
+		.getter = mlxsw_reg_ppcnt_egress_sll_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_DISCARD_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_discard_stats)
+
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
 	{
 		.str = "rx_octets_prio",
@@ -1979,7 +2116,10 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 #define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats)
 
 #define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN + \
 					 MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_DISCARD_STATS_LEN + \
 					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \
 					  IEEE_8021QAZ_MAX_TCS) + \
 					 (MLXSW_SP_PORT_HW_TC_STATS_LEN * \
@@ -1990,7 +2130,7 @@ static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio)
 	int i;
 
 	for (i = 0; i < MLXSW_SP_PORT_HW_PRIO_STATS_LEN; i++) {
-		snprintf(*p, ETH_GSTRING_LEN, "%s_%d",
+		snprintf(*p, ETH_GSTRING_LEN, "%.29s_%.1d",
 			 mlxsw_sp_port_hw_prio_stats[i].str, prio);
 		*p += ETH_GSTRING_LEN;
 	}
@@ -2001,7 +2141,7 @@ static void mlxsw_sp_port_get_tc_strings(u8 **p, int tc)
 	int i;
 
 	for (i = 0; i < MLXSW_SP_PORT_HW_TC_STATS_LEN; i++) {
-		snprintf(*p, ETH_GSTRING_LEN, "%s_%d",
+		snprintf(*p, ETH_GSTRING_LEN, "%.29s_%.1d",
 			 mlxsw_sp_port_hw_tc_stats[i].str, tc);
 		*p += ETH_GSTRING_LEN;
 	}
@@ -2020,12 +2160,31 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
+
+		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_rfc_2863_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
 		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN; i++) {
 			memcpy(p, mlxsw_sp_port_hw_rfc_2819_stats[i].str,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
 
+		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_rfc_3635_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
+		for (i = 0; i < MLXSW_SP_PORT_HW_DISCARD_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_discard_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+
 		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
 			mlxsw_sp_port_get_prio_strings(&p, i);
 
@@ -2068,10 +2227,22 @@ mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats,
 		*p_hw_stats = mlxsw_sp_port_hw_stats;
 		*p_len = MLXSW_SP_PORT_HW_STATS_LEN;
 		break;
+	case MLXSW_REG_PPCNT_RFC_2863_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_rfc_2863_stats;
+		*p_len = MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN;
+		break;
 	case MLXSW_REG_PPCNT_RFC_2819_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_rfc_2819_stats;
 		*p_len = MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
 		break;
+	case MLXSW_REG_PPCNT_RFC_3635_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_rfc_3635_stats;
+		*p_len = MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN;
+		break;
+	case MLXSW_REG_PPCNT_DISCARD_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_discard_stats;
+		*p_len = MLXSW_SP_PORT_HW_DISCARD_STATS_LEN;
+		break;
 	case MLXSW_REG_PPCNT_PRIO_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_prio_stats;
 		*p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN;
@@ -2121,11 +2292,26 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 				  data, data_index);
 	data_index = MLXSW_SP_PORT_HW_STATS_LEN;
 
+	/* RFC 2863 Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2863_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_RFC_2863_STATS_LEN;
+
 	/* RFC 2819 Counters */
 	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2819_CNT, 0,
 				  data, data_index);
 	data_index += MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
 
+	/* RFC 3635 Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_3635_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_RFC_3635_STATS_LEN;
+
+	/* Discard Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_DISCARD_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_DISCARD_STATS_LEN;
+
 	/* Per-Priority Counters */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i,
@@ -2151,13 +2337,13 @@ static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
-struct mlxsw_sp_port_link_mode {
+struct mlxsw_sp1_port_link_mode {
 	enum ethtool_link_mode_bit_indices mask_ethtool;
 	u32 mask;
 	u32 speed;
 };
 
-static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
+static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = {
 	{
 		.mask		= MLXSW_REG_PTYS_ETH_SPEED_100BASE_T,
 		.mask_ethtool	= ETHTOOL_LINK_MODE_100baseT_Full_BIT,
@@ -2229,11 +2415,6 @@ static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
 		.speed		= SPEED_25000,
 	},
 	{
-		.mask		= MLXSW_REG_PTYS_ETH_SPEED_25GBASE_SR,
-		.mask_ethtool	= ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
-		.speed		= SPEED_25000,
-	},
-	{
 		.mask		= MLXSW_REG_PTYS_ETH_SPEED_50GBASE_CR2,
 		.mask_ethtool	= ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
 		.speed		= SPEED_50000,
@@ -2290,11 +2471,12 @@ static const struct mlxsw_sp_port_link_mode mlxsw_sp_port_link_mode[] = {
 	},
 };
 
-#define MLXSW_SP_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp_port_link_mode)
+#define MLXSW_SP1_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp1_port_link_mode)
 
 static void
-mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto,
-				  struct ethtool_link_ksettings *cmd)
+mlxsw_sp1_from_ptys_supported_port(struct mlxsw_sp *mlxsw_sp,
+				   u32 ptys_eth_proto,
+				   struct ethtool_link_ksettings *cmd)
 {
 	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
 			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
@@ -2312,19 +2494,23 @@ mlxsw_sp_from_ptys_supported_port(u32 ptys_eth_proto,
 		ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
 }
 
-static void mlxsw_sp_from_ptys_link(u32 ptys_eth_proto, unsigned long *mode)
+static void
+mlxsw_sp1_from_ptys_link(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto,
+			 unsigned long *mode)
 {
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask)
-			__set_bit(mlxsw_sp_port_link_mode[i].mask_ethtool,
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask)
+			__set_bit(mlxsw_sp1_port_link_mode[i].mask_ethtool,
 				  mode);
 	}
 }
 
-static void mlxsw_sp_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto,
-					    struct ethtool_link_ksettings *cmd)
+static void
+mlxsw_sp1_from_ptys_speed_duplex(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
+				 u32 ptys_eth_proto,
+				 struct ethtool_link_ksettings *cmd)
 {
 	u32 speed = SPEED_UNKNOWN;
 	u8 duplex = DUPLEX_UNKNOWN;
@@ -2333,9 +2519,9 @@ static void mlxsw_sp_from_ptys_speed_duplex(bool carrier_ok, u32 ptys_eth_proto,
 	if (!carrier_ok)
 		goto out;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (ptys_eth_proto & mlxsw_sp_port_link_mode[i].mask) {
-			speed = mlxsw_sp_port_link_mode[i].speed;
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp1_port_link_mode[i].mask) {
+			speed = mlxsw_sp1_port_link_mode[i].speed;
 			duplex = DUPLEX_FULL;
 			break;
 		}
@@ -2345,129 +2531,559 @@ out:
 	cmd->base.duplex = duplex;
 }
 
-static u8 mlxsw_sp_port_connector_port(u32 ptys_eth_proto)
+static u32
+mlxsw_sp1_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp,
+			      const struct ethtool_link_ksettings *cmd)
 {
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_SGMII))
-		return PORT_FIBRE;
+	u32 ptys_proto = 0;
+	int i;
 
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4))
-		return PORT_DA;
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (test_bit(mlxsw_sp1_port_link_mode[i].mask_ethtool,
+			     cmd->link_modes.advertising))
+			ptys_proto |= mlxsw_sp1_port_link_mode[i].mask;
+	}
+	return ptys_proto;
+}
 
-	if (ptys_eth_proto & (MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KR |
-			      MLXSW_REG_PTYS_ETH_SPEED_10GBASE_KX4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 |
-			      MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4))
-		return PORT_NONE;
+static u32 mlxsw_sp1_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 speed)
+{
+	u32 ptys_proto = 0;
+	int i;
 
-	return PORT_OTHER;
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (speed == mlxsw_sp1_port_link_mode[i].speed)
+			ptys_proto |= mlxsw_sp1_port_link_mode[i].mask;
+	}
+	return ptys_proto;
 }
 
 static u32
-mlxsw_sp_to_ptys_advert_link(const struct ethtool_link_ksettings *cmd)
+mlxsw_sp1_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed)
 {
 	u32 ptys_proto = 0;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (test_bit(mlxsw_sp_port_link_mode[i].mask_ethtool,
-			     cmd->link_modes.advertising))
-			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	for (i = 0; i < MLXSW_SP1_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp1_port_link_mode[i].speed <= upper_speed)
+			ptys_proto |= mlxsw_sp1_port_link_mode[i].mask;
+	}
+	return ptys_proto;
+}
+
+static int
+mlxsw_sp1_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+			  u32 *base_speed)
+{
+	*base_speed = MLXSW_SP_PORT_BASE_SPEED_25G;
+	return 0;
+}
+
+static void
+mlxsw_sp1_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			    u8 local_port, u32 proto_admin, bool autoneg)
+{
+	mlxsw_reg_ptys_eth_pack(payload, local_port, proto_admin, autoneg);
+}
+
+static void
+mlxsw_sp1_reg_ptys_eth_unpack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			      u32 *p_eth_proto_cap, u32 *p_eth_proto_admin,
+			      u32 *p_eth_proto_oper)
+{
+	mlxsw_reg_ptys_eth_unpack(payload, p_eth_proto_cap, p_eth_proto_admin,
+				  p_eth_proto_oper);
+}
+
+static const struct mlxsw_sp_port_type_speed_ops
+mlxsw_sp1_port_type_speed_ops = {
+	.from_ptys_supported_port	= mlxsw_sp1_from_ptys_supported_port,
+	.from_ptys_link			= mlxsw_sp1_from_ptys_link,
+	.from_ptys_speed_duplex		= mlxsw_sp1_from_ptys_speed_duplex,
+	.to_ptys_advert_link		= mlxsw_sp1_to_ptys_advert_link,
+	.to_ptys_speed			= mlxsw_sp1_to_ptys_speed,
+	.to_ptys_upper_speed		= mlxsw_sp1_to_ptys_upper_speed,
+	.port_speed_base		= mlxsw_sp1_port_speed_base,
+	.reg_ptys_eth_pack		= mlxsw_sp1_reg_ptys_eth_pack,
+	.reg_ptys_eth_unpack		= mlxsw_sp1_reg_ptys_eth_unpack,
+};
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_sgmii_100m[] = {
+	ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_SGMII_100M_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_sgmii_100m)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_1000base_x_sgmii[] = {
+	ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
+	ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_1000BASE_X_SGMII_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_1000base_x_sgmii)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii[] = {
+	ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_5gbase_r[] = {
+	ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_5gbase_r)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g[] = {
+	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseR_FEC_BIT,
+	ETHTOOL_LINK_MODE_10000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseLR_Full_BIT,
+	ETHTOOL_LINK_MODE_10000baseER_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_XFI_XAUI_1_10G_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g[] = {
+	ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_XLAUI_4_XLPPI_4_40G_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr[] = {
+	ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_25000baseSR_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_25GAUI_1_25GBASE_CR_KR_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2[] = {
+	ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_50GAUI_2_LAUI_2_50GBASE_CR2_KR2_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr[] = {
+	ETHTOOL_LINK_MODE_50000baseKR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseSR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseCR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
+	ETHTOOL_LINK_MODE_50000baseDR_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_50GAUI_1_LAUI_1_50GBASE_CR_KR_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4[] = {
+	ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_CAUI_4_100GBASE_CR4_KR4_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2[] = {
+	ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
+	ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_100GAUI_2_100GBASE_CR2_KR2_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2)
+
+static const enum ethtool_link_mode_bit_indices
+mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4[] = {
+	ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
+	ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT,
+};
+
+#define MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN \
+	ARRAY_SIZE(mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4)
+
+struct mlxsw_sp2_port_link_mode {
+	const enum ethtool_link_mode_bit_indices *mask_ethtool;
+	int m_ethtool_len;
+	u32 mask;
+	u32 speed;
+};
+
+static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = {
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_sgmii_100m,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_SGMII_100M_LEN,
+		.speed		= SPEED_100,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_1000base_x_sgmii,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_1000BASE_X_SGMII_LEN,
+		.speed		= SPEED_1000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN,
+		.speed		= SPEED_2500,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_5gbase_r,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN,
+		.speed		= SPEED_5000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_XFI_XAUI_1_10G_LEN,
+		.speed		= SPEED_10000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_XLAUI_4_XLPPI_4_40G_LEN,
+		.speed		= SPEED_40000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_25GAUI_1_25GBASE_CR_KR_LEN,
+		.speed		= SPEED_25000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_2_LAUI_2_50GBASE_CR2_KR2,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_50GAUI_2_LAUI_2_50GBASE_CR2_KR2_LEN,
+		.speed		= SPEED_50000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_50GAUI_1_LAUI_1_50GBASE_CR_KR_LEN,
+		.speed		= SPEED_50000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_CAUI_4_100GBASE_CR4_KR4_LEN,
+		.speed		= SPEED_100000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_100GAUI_2_100GBASE_CR2_KR2_LEN,
+		.speed		= SPEED_100000,
+	},
+	{
+		.mask		= MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4,
+		.mask_ethtool	= mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4,
+		.m_ethtool_len	= MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN,
+		.speed		= SPEED_200000,
+	},
+};
+
+#define MLXSW_SP2_PORT_LINK_MODE_LEN ARRAY_SIZE(mlxsw_sp2_port_link_mode)
+
+static void
+mlxsw_sp2_from_ptys_supported_port(struct mlxsw_sp *mlxsw_sp,
+				   u32 ptys_eth_proto,
+				   struct ethtool_link_ksettings *cmd)
+{
+	ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE);
+	ethtool_link_ksettings_add_link_mode(cmd, supported, Backplane);
+}
+
+static void
+mlxsw_sp2_set_bit_ethtool(const struct mlxsw_sp2_port_link_mode *link_mode,
+			  unsigned long *mode)
+{
+	int i;
+
+	for (i = 0; i < link_mode->m_ethtool_len; i++)
+		__set_bit(link_mode->mask_ethtool[i], mode);
+}
+
+static void
+mlxsw_sp2_from_ptys_link(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto,
+			 unsigned long *mode)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask)
+			mlxsw_sp2_set_bit_ethtool(&mlxsw_sp2_port_link_mode[i],
+						  mode);
+	}
+}
+
+static void
+mlxsw_sp2_from_ptys_speed_duplex(struct mlxsw_sp *mlxsw_sp, bool carrier_ok,
+				 u32 ptys_eth_proto,
+				 struct ethtool_link_ksettings *cmd)
+{
+	u32 speed = SPEED_UNKNOWN;
+	u8 duplex = DUPLEX_UNKNOWN;
+	int i;
+
+	if (!carrier_ok)
+		goto out;
+
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) {
+			speed = mlxsw_sp2_port_link_mode[i].speed;
+			duplex = DUPLEX_FULL;
+			break;
+		}
+	}
+out:
+	cmd->base.speed = speed;
+	cmd->base.duplex = duplex;
+}
+
+static bool
+mlxsw_sp2_test_bit_ethtool(const struct mlxsw_sp2_port_link_mode *link_mode,
+			   const unsigned long *mode)
+{
+	int cnt = 0;
+	int i;
+
+	for (i = 0; i < link_mode->m_ethtool_len; i++) {
+		if (test_bit(link_mode->mask_ethtool[i], mode))
+			cnt++;
+	}
+
+	return cnt == link_mode->m_ethtool_len;
+}
+
+static u32
+mlxsw_sp2_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp,
+			      const struct ethtool_link_ksettings *cmd)
+{
+	u32 ptys_proto = 0;
+	int i;
+
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp2_test_bit_ethtool(&mlxsw_sp2_port_link_mode[i],
+					       cmd->link_modes.advertising))
+			ptys_proto |= mlxsw_sp2_port_link_mode[i].mask;
 	}
 	return ptys_proto;
 }
 
-static u32 mlxsw_sp_to_ptys_speed(u32 speed)
+static u32 mlxsw_sp2_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 speed)
 {
 	u32 ptys_proto = 0;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (speed == mlxsw_sp_port_link_mode[i].speed)
-			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (speed == mlxsw_sp2_port_link_mode[i].speed)
+			ptys_proto |= mlxsw_sp2_port_link_mode[i].mask;
 	}
 	return ptys_proto;
 }
 
-static u32 mlxsw_sp_to_ptys_upper_speed(u32 upper_speed)
+static u32
+mlxsw_sp2_to_ptys_upper_speed(struct mlxsw_sp *mlxsw_sp, u32 upper_speed)
 {
 	u32 ptys_proto = 0;
 	int i;
 
-	for (i = 0; i < MLXSW_SP_PORT_LINK_MODE_LEN; i++) {
-		if (mlxsw_sp_port_link_mode[i].speed <= upper_speed)
-			ptys_proto |= mlxsw_sp_port_link_mode[i].mask;
+	for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) {
+		if (mlxsw_sp2_port_link_mode[i].speed <= upper_speed)
+			ptys_proto |= mlxsw_sp2_port_link_mode[i].mask;
 	}
 	return ptys_proto;
 }
 
-static void mlxsw_sp_port_get_link_supported(u32 eth_proto_cap,
-					     struct ethtool_link_ksettings *cmd)
+static int
+mlxsw_sp2_port_speed_base(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+			  u32 *base_speed)
+{
+	char ptys_pl[MLXSW_REG_PTYS_LEN];
+	u32 eth_proto_cap;
+	int err;
+
+	/* In Spectrum-2, the speed of 1x can change from port to port, so query
+	 * it from firmware.
+	 */
+	mlxsw_reg_ptys_ext_eth_pack(ptys_pl, local_port, 0, false);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
+	if (err)
+		return err;
+	mlxsw_reg_ptys_ext_eth_unpack(ptys_pl, &eth_proto_cap, NULL, NULL);
+
+	if (eth_proto_cap &
+	    MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR) {
+		*base_speed = MLXSW_SP_PORT_BASE_SPEED_50G;
+		return 0;
+	}
+
+	if (eth_proto_cap &
+	    MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR) {
+		*base_speed = MLXSW_SP_PORT_BASE_SPEED_25G;
+		return 0;
+	}
+
+	return -EIO;
+}
+
+static void
+mlxsw_sp2_reg_ptys_eth_pack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			    u8 local_port, u32 proto_admin,
+			    bool autoneg)
+{
+	mlxsw_reg_ptys_ext_eth_pack(payload, local_port, proto_admin, autoneg);
+}
+
+static void
+mlxsw_sp2_reg_ptys_eth_unpack(struct mlxsw_sp *mlxsw_sp, char *payload,
+			      u32 *p_eth_proto_cap, u32 *p_eth_proto_admin,
+			      u32 *p_eth_proto_oper)
+{
+	mlxsw_reg_ptys_ext_eth_unpack(payload, p_eth_proto_cap,
+				      p_eth_proto_admin, p_eth_proto_oper);
+}
+
+static const struct mlxsw_sp_port_type_speed_ops
+mlxsw_sp2_port_type_speed_ops = {
+	.from_ptys_supported_port	= mlxsw_sp2_from_ptys_supported_port,
+	.from_ptys_link			= mlxsw_sp2_from_ptys_link,
+	.from_ptys_speed_duplex		= mlxsw_sp2_from_ptys_speed_duplex,
+	.to_ptys_advert_link		= mlxsw_sp2_to_ptys_advert_link,
+	.to_ptys_speed			= mlxsw_sp2_to_ptys_speed,
+	.to_ptys_upper_speed		= mlxsw_sp2_to_ptys_upper_speed,
+	.port_speed_base		= mlxsw_sp2_port_speed_base,
+	.reg_ptys_eth_pack		= mlxsw_sp2_reg_ptys_eth_pack,
+	.reg_ptys_eth_unpack		= mlxsw_sp2_reg_ptys_eth_unpack,
+};
+
+static void
+mlxsw_sp_port_get_link_supported(struct mlxsw_sp *mlxsw_sp, u32 eth_proto_cap,
+				 struct ethtool_link_ksettings *cmd)
 {
+	const struct mlxsw_sp_port_type_speed_ops *ops;
+
+	ops = mlxsw_sp->port_type_speed_ops;
+
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Asym_Pause);
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg);
 	ethtool_link_ksettings_add_link_mode(cmd, supported, Pause);
 
-	mlxsw_sp_from_ptys_supported_port(eth_proto_cap, cmd);
-	mlxsw_sp_from_ptys_link(eth_proto_cap, cmd->link_modes.supported);
+	ops->from_ptys_supported_port(mlxsw_sp, eth_proto_cap, cmd);
+	ops->from_ptys_link(mlxsw_sp, eth_proto_cap, cmd->link_modes.supported);
 }
 
-static void mlxsw_sp_port_get_link_advertise(u32 eth_proto_admin, bool autoneg,
-					     struct ethtool_link_ksettings *cmd)
+static void
+mlxsw_sp_port_get_link_advertise(struct mlxsw_sp *mlxsw_sp,
+				 u32 eth_proto_admin, bool autoneg,
+				 struct ethtool_link_ksettings *cmd)
 {
+	const struct mlxsw_sp_port_type_speed_ops *ops;
+
+	ops = mlxsw_sp->port_type_speed_ops;
+
 	if (!autoneg)
 		return;
 
 	ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg);
-	mlxsw_sp_from_ptys_link(eth_proto_admin, cmd->link_modes.advertising);
+	ops->from_ptys_link(mlxsw_sp, eth_proto_admin,
+			    cmd->link_modes.advertising);
 }
 
-static void
-mlxsw_sp_port_get_link_lp_advertise(u32 eth_proto_lp, u8 autoneg_status,
-				    struct ethtool_link_ksettings *cmd)
+static u8
+mlxsw_sp_port_connector_port(enum mlxsw_reg_ptys_connector_type connector_type)
 {
-	if (autoneg_status != MLXSW_REG_PTYS_AN_STATUS_OK || !eth_proto_lp)
-		return;
-
-	ethtool_link_ksettings_add_link_mode(cmd, lp_advertising, Autoneg);
-	mlxsw_sp_from_ptys_link(eth_proto_lp, cmd->link_modes.lp_advertising);
+	switch (connector_type) {
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_UNKNOWN_OR_NO_CONNECTOR:
+		return PORT_OTHER;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_NONE:
+		return PORT_NONE;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_TP:
+		return PORT_TP;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_AUI:
+		return PORT_AUI;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_BNC:
+		return PORT_BNC;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_MII:
+		return PORT_MII;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_FIBRE:
+		return PORT_FIBRE;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_DA:
+		return PORT_DA;
+	case MLXSW_REG_PTYS_CONNECTOR_TYPE_PORT_OTHER:
+		return PORT_OTHER;
+	default:
+		WARN_ON_ONCE(1);
+		return PORT_OTHER;
+	}
 }
 
 static int mlxsw_sp_port_get_link_ksettings(struct net_device *dev,
 					    struct ethtool_link_ksettings *cmd)
 {
-	u32 eth_proto_cap, eth_proto_admin, eth_proto_oper, eth_proto_lp;
+	u32 eth_proto_cap, eth_proto_admin, eth_proto_oper;
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	const struct mlxsw_sp_port_type_speed_ops *ops;
 	char ptys_pl[MLXSW_REG_PTYS_LEN];
-	u8 autoneg_status;
+	u8 connector_type;
 	bool autoneg;
 	int err;
 
+	ops = mlxsw_sp->port_type_speed_ops;
+
 	autoneg = mlxsw_sp_port->link.autoneg;
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port, 0, false);
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       0, false);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 	if (err)
 		return err;
-	mlxsw_reg_ptys_eth_unpack(ptys_pl, &eth_proto_cap, &eth_proto_admin,
-				  &eth_proto_oper);
+	ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, &eth_proto_cap,
+				 &eth_proto_admin, &eth_proto_oper);
 
-	mlxsw_sp_port_get_link_supported(eth_proto_cap, cmd);
+	mlxsw_sp_port_get_link_supported(mlxsw_sp, eth_proto_cap, cmd);
 
-	mlxsw_sp_port_get_link_advertise(eth_proto_admin, autoneg, cmd);
-
-	eth_proto_lp = mlxsw_reg_ptys_eth_proto_lp_advertise_get(ptys_pl);
-	autoneg_status = mlxsw_reg_ptys_an_status_get(ptys_pl);
-	mlxsw_sp_port_get_link_lp_advertise(eth_proto_lp, autoneg_status, cmd);
+	mlxsw_sp_port_get_link_advertise(mlxsw_sp, eth_proto_admin, autoneg,
+					 cmd);
 
 	cmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
-	cmd->base.port = mlxsw_sp_port_connector_port(eth_proto_oper);
-	mlxsw_sp_from_ptys_speed_duplex(netif_carrier_ok(dev), eth_proto_oper,
-					cmd);
+	connector_type = mlxsw_reg_ptys_connector_type_get(ptys_pl);
+	cmd->base.port = mlxsw_sp_port_connector_port(connector_type);
+	ops->from_ptys_speed_duplex(mlxsw_sp, netif_carrier_ok(dev),
+				    eth_proto_oper, cmd);
 
 	return 0;
 }
@@ -2478,21 +3094,25 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	const struct mlxsw_sp_port_type_speed_ops *ops;
 	char ptys_pl[MLXSW_REG_PTYS_LEN];
 	u32 eth_proto_cap, eth_proto_new;
 	bool autoneg;
 	int err;
 
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port, 0, false);
+	ops = mlxsw_sp->port_type_speed_ops;
+
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       0, false);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 	if (err)
 		return err;
-	mlxsw_reg_ptys_eth_unpack(ptys_pl, &eth_proto_cap, NULL, NULL);
+	ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, &eth_proto_cap, NULL, NULL);
 
 	autoneg = cmd->base.autoneg == AUTONEG_ENABLE;
 	eth_proto_new = autoneg ?
-		mlxsw_sp_to_ptys_advert_link(cmd) :
-		mlxsw_sp_to_ptys_speed(cmd->base.speed);
+		ops->to_ptys_advert_link(mlxsw_sp, cmd) :
+		ops->to_ptys_speed(mlxsw_sp, cmd->base.speed);
 
 	eth_proto_new = eth_proto_new & eth_proto_cap;
 	if (!eth_proto_new) {
@@ -2500,17 +3120,17 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port,
-				eth_proto_new, autoneg);
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       eth_proto_new, autoneg);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 	if (err)
 		return err;
 
+	mlxsw_sp_port->link.autoneg = autoneg;
+
 	if (!netif_running(dev))
 		return 0;
 
-	mlxsw_sp_port->link.autoneg = autoneg;
-
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_admin_status_set(mlxsw_sp_port, true);
 
@@ -2542,117 +3162,18 @@ out:
 	return err;
 }
 
-#define MLXSW_SP_I2C_ADDR_LOW 0x50
-#define MLXSW_SP_I2C_ADDR_HIGH 0x51
-#define MLXSW_SP_EEPROM_PAGE_LENGTH 256
-
-static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port,
-					u16 offset, u16 size, void *data,
-					unsigned int *p_read_size)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE];
-	char mcia_pl[MLXSW_REG_MCIA_LEN];
-	u16 i2c_addr;
-	int status;
-	int err;
-
-	size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE);
-
-	if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH &&
-	    offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH)
-		/* Cross pages read, read until offset 256 in low page */
-		size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset;
-
-	i2c_addr = MLXSW_SP_I2C_ADDR_LOW;
-	if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) {
-		i2c_addr = MLXSW_SP_I2C_ADDR_HIGH;
-		offset -= MLXSW_SP_EEPROM_PAGE_LENGTH;
-	}
-
-	mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module,
-			    0, 0, offset, size, i2c_addr);
-
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(mcia), mcia_pl);
-	if (err)
-		return err;
-
-	status = mlxsw_reg_mcia_status_get(mcia_pl);
-	if (status)
-		return -EIO;
-
-	mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp);
-	memcpy(data, eeprom_tmp, size);
-	*p_read_size = size;
-
-	return 0;
-}
-
-enum mlxsw_sp_eeprom_module_info_rev_id {
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_UNSPC      = 0x00,
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8436       = 0x01,
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636       = 0x03,
-};
-
-enum mlxsw_sp_eeprom_module_info_id {
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP              = 0x03,
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP             = 0x0C,
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS        = 0x0D,
-	MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28           = 0x11,
-};
-
-enum mlxsw_sp_eeprom_module_info {
-	MLXSW_SP_EEPROM_MODULE_INFO_ID,
-	MLXSW_SP_EEPROM_MODULE_INFO_REV_ID,
-	MLXSW_SP_EEPROM_MODULE_INFO_SIZE,
-};
-
 static int mlxsw_sp_get_module_info(struct net_device *netdev,
 				    struct ethtool_modinfo *modinfo)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
-	u8 module_info[MLXSW_SP_EEPROM_MODULE_INFO_SIZE];
-	u8 module_rev_id, module_id;
-	unsigned int read_size;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	int err;
 
-	err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, 0,
-					   MLXSW_SP_EEPROM_MODULE_INFO_SIZE,
-					   module_info, &read_size);
-	if (err)
-		return err;
+	err = mlxsw_env_get_module_info(mlxsw_sp->core,
+					mlxsw_sp_port->mapping.module,
+					modinfo);
 
-	if (read_size < MLXSW_SP_EEPROM_MODULE_INFO_SIZE)
-		return -EIO;
-
-	module_rev_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_REV_ID];
-	module_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_ID];
-
-	switch (module_id) {
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP:
-		modinfo->type       = ETH_MODULE_SFF_8436;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
-		break;
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS:
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28:
-		if (module_id  == MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28 ||
-		    module_rev_id >= MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636) {
-			modinfo->type       = ETH_MODULE_SFF_8636;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
-		} else {
-			modinfo->type       = ETH_MODULE_SFF_8436;
-			modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
-		}
-		break;
-	case MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP:
-		modinfo->type       = ETH_MODULE_SFF_8472;
-		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	return 0;
+	return err;
 }
 
 static int mlxsw_sp_get_module_eeprom(struct net_device *netdev,
@@ -2660,30 +3181,14 @@ static int mlxsw_sp_get_module_eeprom(struct net_device *netdev,
 				      u8 *data)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev);
-	int offset = ee->offset;
-	unsigned int read_size;
-	int i = 0;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	int err;
 
-	if (!ee->len)
-		return -EINVAL;
-
-	memset(data, 0, ee->len);
+	err = mlxsw_env_get_module_eeprom(netdev, mlxsw_sp->core,
+					  mlxsw_sp_port->mapping.module, ee,
+					  data);
 
-	while (i < ee->len) {
-		err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, offset,
-						   ee->len - i, data + i,
-						   &read_size);
-		if (err) {
-			netdev_err(mlxsw_sp_port->dev, "Eeprom query failed\n");
-			return err;
-		}
-
-		i += read_size;
-		offset += read_size;
-	}
-
-	return 0;
+	return err;
 }
 
 static const struct ethtool_ops mlxsw_sp_port_ethtool_ops = {
@@ -2706,13 +3211,24 @@ static int
 mlxsw_sp_port_speed_by_width_set(struct mlxsw_sp_port *mlxsw_sp_port, u8 width)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	u32 upper_speed = MLXSW_SP_PORT_BASE_SPEED * width;
+	const struct mlxsw_sp_port_type_speed_ops *ops;
 	char ptys_pl[MLXSW_REG_PTYS_LEN];
 	u32 eth_proto_admin;
+	u32 upper_speed;
+	u32 base_speed;
+	int err;
+
+	ops = mlxsw_sp->port_type_speed_ops;
+
+	err = ops->port_speed_base(mlxsw_sp, mlxsw_sp_port->local_port,
+				   &base_speed);
+	if (err)
+		return err;
+	upper_speed = base_speed * width;
 
-	eth_proto_admin = mlxsw_sp_to_ptys_upper_speed(upper_speed);
-	mlxsw_reg_ptys_eth_pack(ptys_pl, mlxsw_sp_port->local_port,
-				eth_proto_admin, mlxsw_sp_port->link.autoneg);
+	eth_proto_admin = ops->to_ptys_upper_speed(mlxsw_sp, upper_speed);
+	ops->reg_ptys_eth_pack(mlxsw_sp, ptys_pl, mlxsw_sp_port->local_port,
+			       eth_proto_admin, mlxsw_sp_port->link.autoneg);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptys), ptys_pl);
 }
 
@@ -2800,7 +3316,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
 					    MLXSW_REG_QEEC_HIERARCY_TC,
 					    i + 8, i,
-					    false, 0);
+					    true, 100);
 		if (err)
 			return err;
 	}
@@ -2892,7 +3408,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 	mlxsw_sp_port->dev = dev;
 	mlxsw_sp_port->mlxsw_sp = mlxsw_sp;
 	mlxsw_sp_port->local_port = local_port;
-	mlxsw_sp_port->pvid = 1;
+	mlxsw_sp_port->pvid = MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port->split = split;
 	mlxsw_sp_port->mapping.module = module;
 	mlxsw_sp_port->mapping.width = width;
@@ -3031,15 +3547,23 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_nve_init;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to set PVID\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_pvid_set;
+	}
+
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port,
+						       MLXSW_SP_DEFAULT_VID);
 	if (IS_ERR(mlxsw_sp_port_vlan)) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create VID 1\n",
 			mlxsw_sp_port->local_port);
 		err = PTR_ERR(mlxsw_sp_port_vlan);
-		goto err_port_vlan_get;
+		goto err_port_vlan_create;
 	}
+	mlxsw_sp_port->default_vlan = mlxsw_sp_port_vlan;
 
-	mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
 	mlxsw_sp->ports[local_port] = mlxsw_sp_port;
 	err = register_netdev(dev);
 	if (err) {
@@ -3056,9 +3580,9 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 err_register_netdev:
 	mlxsw_sp->ports[local_port] = NULL;
-	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
-err_port_vlan_get:
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+err_port_vlan_create:
+err_port_pvid_set:
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 err_port_nve_init:
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
@@ -3098,8 +3622,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_core_port_clear(mlxsw_sp->core, local_port, mlxsw_sp);
 	unregister_netdev(mlxsw_sp_port->dev); /* This calls ndo_stop */
 	mlxsw_sp->ports[local_port] = NULL;
-	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
-	mlxsw_sp_port_vlan_flush(mlxsw_sp_port);
+	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, true);
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
 	mlxsw_sp_port_fids_fini(mlxsw_sp_port);
@@ -3394,10 +3917,10 @@ static void mlxsw_sp_rx_listener_mark_func(struct sk_buff *skb, u8 local_port,
 	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
 }
 
-static void mlxsw_sp_rx_listener_mr_mark_func(struct sk_buff *skb,
+static void mlxsw_sp_rx_listener_l3_mark_func(struct sk_buff *skb,
 					      u8 local_port, void *priv)
 {
-	skb->offload_mr_fwd_mark = 1;
+	skb->offload_l3_fwd_mark = 1;
 	skb->offload_fwd_mark = 1;
 	return mlxsw_sp_rx_listener_no_mark_func(skb, local_port, priv);
 }
@@ -3445,8 +3968,8 @@ out:
 	MLXSW_RXL(mlxsw_sp_rx_listener_mark_func, _trap_id, _action,	\
 		_is_ctrl, SP_##_trap_group, DISCARD)
 
-#define MLXSW_SP_RXL_MR_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
-	MLXSW_RXL(mlxsw_sp_rx_listener_mr_mark_func, _trap_id, _action,	\
+#define MLXSW_SP_RXL_L3_MARK(_trap_id, _action, _trap_group, _is_ctrl)	\
+	MLXSW_RXL(mlxsw_sp_rx_listener_l3_mark_func, _trap_id, _action,	\
 		_is_ctrl, SP_##_trap_group, DISCARD)
 
 #define MLXSW_SP_EVENTL(_func, _trap_id)		\
@@ -3479,7 +4002,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* L3 traps */
 	MLXSW_SP_RXL_MARK(MTUERROR, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(TTLERROR, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(LBERROR, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_L3_MARK(LBERROR, MIRROR_TO_CPU, LBERROR, false),
 	MLXSW_SP_RXL_MARK(IP2ME, TRAP_TO_CPU, IP2ME, false),
 	MLXSW_SP_RXL_MARK(IPV6_UNSPECIFIED_ADDRESS, TRAP_TO_CPU, ROUTER_EXP,
 			  false),
@@ -3523,7 +4046,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(IPV6_PIM, TRAP_TO_CPU, PIM, false),
 	MLXSW_SP_RXL_MARK(RPF, TRAP_TO_CPU, RPF, false),
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
-	MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
+	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
 	/* NVE traps */
 	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false),
 	MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, ARP, false),
@@ -3554,6 +4077,7 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_RPF:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			rate = 128;
 			burst_size = 7;
 			break;
@@ -3574,8 +4098,8 @@ static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core)
 			burst_size = 7;
 			break;
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME:
-			rate = 4 * 1024;
-			burst_size = 4;
+			rate = 1024;
+			burst_size = 7;
 			break;
 		default:
 			continue;
@@ -3639,6 +4163,7 @@ static int mlxsw_sp_trap_groups_set(struct mlxsw_core *mlxsw_core)
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_REMOTE_ROUTE:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR:
 			priority = 1;
 			tc = 1;
 			break;
@@ -3841,6 +4366,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_nve_init;
 	}
 
+	err = mlxsw_sp_acl_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n");
+		goto err_acl_init;
+	}
+
 	err = mlxsw_sp_router_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n");
@@ -3858,12 +4389,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 		goto err_netdev_notifier;
 	}
 
-	err = mlxsw_sp_acl_init(mlxsw_sp);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize ACL\n");
-		goto err_acl_init;
-	}
-
 	err = mlxsw_sp_dpipe_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to init pipeline debug\n");
@@ -3881,12 +4406,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 err_ports_create:
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
 err_dpipe_init:
-	mlxsw_sp_acl_fini(mlxsw_sp);
-err_acl_init:
 	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
 err_netdev_notifier:
 	mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
+	mlxsw_sp_acl_fini(mlxsw_sp);
+err_acl_init:
 	mlxsw_sp_nve_fini(mlxsw_sp);
 err_nve_init:
 	mlxsw_sp_afa_fini(mlxsw_sp);
@@ -3922,6 +4447,10 @@ static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
 	mlxsw_sp->nve_ops_arr = mlxsw_sp1_nve_ops_arr;
+	mlxsw_sp->mac_mask = mlxsw_sp1_mac_mask;
+	mlxsw_sp->rif_ops_arr = mlxsw_sp1_rif_ops_arr;
+	mlxsw_sp->sb_vals = &mlxsw_sp1_sb_vals;
+	mlxsw_sp->port_type_speed_ops = &mlxsw_sp1_port_type_speed_ops;
 
 	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
 }
@@ -3937,6 +4466,10 @@ static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->mr_tcam_ops = &mlxsw_sp2_mr_tcam_ops;
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp2_acl_tcam_ops;
 	mlxsw_sp->nve_ops_arr = mlxsw_sp2_nve_ops_arr;
+	mlxsw_sp->mac_mask = mlxsw_sp2_mac_mask;
+	mlxsw_sp->rif_ops_arr = mlxsw_sp2_rif_ops_arr;
+	mlxsw_sp->sb_vals = &mlxsw_sp2_sb_vals;
+	mlxsw_sp->port_type_speed_ops = &mlxsw_sp2_port_type_speed_ops;
 
 	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
 }
@@ -3947,9 +4480,9 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 
 	mlxsw_sp_ports_remove(mlxsw_sp);
 	mlxsw_sp_dpipe_fini(mlxsw_sp);
-	mlxsw_sp_acl_fini(mlxsw_sp);
 	unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb);
 	mlxsw_sp_router_fini(mlxsw_sp);
+	mlxsw_sp_acl_fini(mlxsw_sp);
 	mlxsw_sp_nve_fini(mlxsw_sp);
 	mlxsw_sp_afa_fini(mlxsw_sp);
 	mlxsw_sp_counter_pool_fini(mlxsw_sp);
@@ -3962,16 +4495,20 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
 }
 
+/* Per-FID flood tables are used for both "true" 802.1D FIDs and emulated
+ * 802.1Q FIDs
+ */
+#define MLXSW_SP_FID_FLOOD_TABLE_SIZE	(MLXSW_SP_FID_8021D_MAX + \
+					 VLAN_VID_MASK - 1)
+
 static const struct mlxsw_config_profile mlxsw_sp1_config_profile = {
 	.used_max_mid			= 1,
 	.max_mid			= MLXSW_SP_MID_MAX,
 	.used_flood_tables		= 1,
 	.used_flood_mode		= 1,
 	.flood_mode			= 3,
-	.max_fid_offset_flood_tables	= 3,
-	.fid_offset_flood_table_size	= VLAN_N_VID - 1,
 	.max_fid_flood_tables		= 3,
-	.fid_flood_table_size		= MLXSW_SP_FID_8021D_MAX,
+	.fid_flood_table_size		= MLXSW_SP_FID_FLOOD_TABLE_SIZE,
 	.used_max_ib_mc			= 1,
 	.max_ib_mc			= 0,
 	.used_max_pkey			= 1,
@@ -3994,10 +4531,8 @@ static const struct mlxsw_config_profile mlxsw_sp2_config_profile = {
 	.used_flood_tables		= 1,
 	.used_flood_mode		= 1,
 	.flood_mode			= 3,
-	.max_fid_offset_flood_tables	= 3,
-	.fid_offset_flood_table_size	= VLAN_N_VID - 1,
 	.max_fid_flood_tables		= 3,
-	.fid_flood_table_size		= MLXSW_SP_FID_8021D_MAX,
+	.fid_flood_table_size		= MLXSW_SP_FID_FLOOD_TABLE_SIZE,
 	.used_max_ib_mc			= 1,
 	.max_ib_mc			= 0,
 	.used_max_pkey			= 1,
@@ -4177,6 +4712,117 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 	return 0;
 }
 
+static int
+mlxsw_sp_devlink_param_fw_load_policy_validate(struct devlink *devlink, u32 id,
+					       union devlink_param_value val,
+					       struct netlink_ext_ack *extack)
+{
+	if ((val.vu8 != DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER) &&
+	    (val.vu8 != DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH)) {
+		NL_SET_ERR_MSG_MOD(extack, "'fw_load_policy' must be 'driver' or 'flash'");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct devlink_param mlxsw_sp_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(FW_LOAD_POLICY,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL,
+			      mlxsw_sp_devlink_param_fw_load_policy_validate),
+};
+
+static int mlxsw_sp_params_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	union devlink_param_value value;
+	int err;
+
+	err = devlink_params_register(devlink, mlxsw_sp_devlink_params,
+				      ARRAY_SIZE(mlxsw_sp_devlink_params));
+	if (err)
+		return err;
+
+	value.vu8 = DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER;
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY,
+					   value);
+	return 0;
+}
+
+static void mlxsw_sp_params_unregister(struct mlxsw_core *mlxsw_core)
+{
+	devlink_params_unregister(priv_to_devlink(mlxsw_core),
+				  mlxsw_sp_devlink_params,
+				  ARRAY_SIZE(mlxsw_sp_devlink_params));
+}
+
+static int
+mlxsw_sp_params_acl_region_rehash_intrvl_get(struct devlink *devlink, u32 id,
+					     struct devlink_param_gset_ctx *ctx)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	ctx->val.vu32 = mlxsw_sp_acl_region_rehash_intrvl_get(mlxsw_sp);
+	return 0;
+}
+
+static int
+mlxsw_sp_params_acl_region_rehash_intrvl_set(struct devlink *devlink, u32 id,
+					     struct devlink_param_gset_ctx *ctx)
+{
+	struct mlxsw_core *mlxsw_core = devlink_priv(devlink);
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	return mlxsw_sp_acl_region_rehash_intrvl_set(mlxsw_sp, ctx->val.vu32);
+}
+
+static const struct devlink_param mlxsw_sp2_devlink_params[] = {
+	DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
+			     "acl_region_rehash_interval",
+			     DEVLINK_PARAM_TYPE_U32,
+			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
+			     mlxsw_sp_params_acl_region_rehash_intrvl_get,
+			     mlxsw_sp_params_acl_region_rehash_intrvl_set,
+			     NULL),
+};
+
+static int mlxsw_sp2_params_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	union devlink_param_value value;
+	int err;
+
+	err = mlxsw_sp_params_register(mlxsw_core);
+	if (err)
+		return err;
+
+	err = devlink_params_register(devlink, mlxsw_sp2_devlink_params,
+				      ARRAY_SIZE(mlxsw_sp2_devlink_params));
+	if (err)
+		goto err_devlink_params_register;
+
+	value.vu32 = 0;
+	devlink_param_driverinit_value_set(devlink,
+					   MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL,
+					   value);
+	return 0;
+
+err_devlink_params_register:
+	mlxsw_sp_params_unregister(mlxsw_core);
+	return err;
+}
+
+static void mlxsw_sp2_params_unregister(struct mlxsw_core *mlxsw_core)
+{
+	devlink_params_unregister(priv_to_devlink(mlxsw_core),
+				  mlxsw_sp2_devlink_params,
+				  ARRAY_SIZE(mlxsw_sp2_devlink_params));
+	mlxsw_sp_params_unregister(mlxsw_core);
+}
+
 static struct mlxsw_driver mlxsw_sp1_driver = {
 	.kind				= mlxsw_sp1_driver_name,
 	.priv_size			= sizeof(struct mlxsw_sp),
@@ -4198,6 +4844,8 @@ static struct mlxsw_driver mlxsw_sp1_driver = {
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
+	.params_register		= mlxsw_sp_params_register,
+	.params_unregister		= mlxsw_sp_params_unregister,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp1_config_profile,
 	.res_query_enabled		= true,
@@ -4223,6 +4871,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = {
 	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
 	.resources_register		= mlxsw_sp2_resources_register,
+	.params_register		= mlxsw_sp2_params_register,
+	.params_unregister		= mlxsw_sp2_params_unregister,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
 	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
@@ -4298,6 +4948,25 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
 	dev_put(mlxsw_sp_port->dev);
 }
 
+static void
+mlxsw_sp_port_lag_uppers_cleanup(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct net_device *lag_dev)
+{
+	struct net_device *br_dev = netdev_master_upper_dev_get(lag_dev);
+	struct net_device *upper_dev;
+	struct list_head *iter;
+
+	if (netif_is_bridge_port(lag_dev))
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lag_dev, br_dev);
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!netif_is_bridge_port(upper_dev))
+			continue;
+		br_dev = netdev_master_upper_dev_get(upper_dev);
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev, br_dev);
+	}
+}
+
 static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 {
 	char sldr_pl[MLXSW_REG_SLDR_LEN];
@@ -4425,7 +5094,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct net_device *lag_dev)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	struct mlxsw_sp_upper *lag;
 	u16 lag_id;
 	u8 port_index;
@@ -4448,9 +5116,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	err = mlxsw_sp_lag_col_port_add(mlxsw_sp_port, lag_id, port_index);
 	if (err)
 		goto err_col_port_add;
-	err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, lag_id);
-	if (err)
-		goto err_col_port_enable;
 
 	mlxsw_core_lag_mapping_set(mlxsw_sp->core, lag_id, port_index,
 				   mlxsw_sp_port->local_port);
@@ -4459,14 +5124,11 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
 	lag->ref_count++;
 
 	/* Port is no longer usable as a router interface */
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1);
-	if (mlxsw_sp_port_vlan->fid)
-		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
+	if (mlxsw_sp_port->default_vlan->fid)
+		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan);
 
 	return 0;
 
-err_col_port_enable:
-	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 err_col_port_add:
 	if (!lag->ref_count)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
@@ -4485,11 +5147,15 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id);
 	WARN_ON(lag->ref_count == 0);
 
-	mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
 	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
 
 	/* Any VLANs configured on the port are no longer valid */
-	mlxsw_sp_port_vlan_flush(mlxsw_sp_port);
+	mlxsw_sp_port_vlan_flush(mlxsw_sp_port, false);
+	mlxsw_sp_port_vlan_cleanup(mlxsw_sp_port->default_vlan);
+	/* Make the LAG and its directly linked uppers leave bridges they
+	 * are memeber in
+	 */
+	mlxsw_sp_port_lag_uppers_cleanup(mlxsw_sp_port, lag_dev);
 
 	if (lag->ref_count == 1)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
@@ -4499,9 +5165,8 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
 
-	mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
 	/* Make sure untagged frames are allowed to ingress */
-	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 }
 
 static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -4526,21 +5191,56 @@ static int mlxsw_sp_lag_dist_port_remove(struct mlxsw_sp_port *mlxsw_sp_port,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl);
 }
 
-static int mlxsw_sp_port_lag_tx_en_set(struct mlxsw_sp_port *mlxsw_sp_port,
-				       bool lag_tx_enabled)
+static int
+mlxsw_sp_port_lag_col_dist_enable(struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	if (lag_tx_enabled)
-		return mlxsw_sp_lag_dist_port_add(mlxsw_sp_port,
-						  mlxsw_sp_port->lag_id);
-	else
-		return mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port,
-						     mlxsw_sp_port->lag_id);
+	int err;
+
+	err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port,
+					   mlxsw_sp_port->lag_id);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id);
+	if (err)
+		goto err_dist_port_add;
+
+	return 0;
+
+err_dist_port_add:
+	mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, mlxsw_sp_port->lag_id);
+	return err;
+}
+
+static int
+mlxsw_sp_port_lag_col_dist_disable(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	int err;
+
+	err = mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port,
+					    mlxsw_sp_port->lag_id);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port,
+					    mlxsw_sp_port->lag_id);
+	if (err)
+		goto err_col_port_disable;
+
+	return 0;
+
+err_col_port_disable:
+	mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id);
+	return err;
 }
 
 static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port,
 				     struct netdev_lag_lower_state_info *info)
 {
-	return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled);
+	if (info->tx_enabled)
+		return mlxsw_sp_port_lag_col_dist_enable(mlxsw_sp_port);
+	else
+		return mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port);
 }
 
 static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -4579,7 +5279,7 @@ static int mlxsw_sp_port_ovs_join(struct mlxsw_sp_port *mlxsw_sp_port)
 	err = mlxsw_sp_port_stp_set(mlxsw_sp_port, true);
 	if (err)
 		goto err_port_stp_set;
-	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
+	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, 1, VLAN_N_VID - 2,
 				     true, false);
 	if (err)
 		goto err_port_vlan_set;
@@ -4611,7 +5311,7 @@ static void mlxsw_sp_port_ovs_leave(struct mlxsw_sp_port *mlxsw_sp_port)
 		mlxsw_sp_port_vid_learning_set(mlxsw_sp_port,
 					       vid, true);
 
-	mlxsw_sp_port_vlan_set(mlxsw_sp_port, 2, VLAN_N_VID - 1,
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, 1, VLAN_N_VID - 2,
 			       false, false);
 	mlxsw_sp_port_stp_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_vp_mode_set(mlxsw_sp_port, false);
@@ -4631,6 +5331,30 @@ static bool mlxsw_sp_bridge_has_multiple_vxlans(struct net_device *br_dev)
 	return num_vxlans > 1;
 }
 
+static bool mlxsw_sp_bridge_vxlan_vlan_is_valid(struct net_device *br_dev)
+{
+	DECLARE_BITMAP(vlans, VLAN_N_VID) = {0};
+	struct net_device *dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(br_dev, dev, iter) {
+		u16 pvid;
+		int err;
+
+		if (!netif_is_vxlan(dev))
+			continue;
+
+		err = mlxsw_sp_vxlan_mapped_vid(dev, &pvid);
+		if (err || !pvid)
+			continue;
+
+		if (test_and_set_bit(pvid, vlans))
+			return false;
+	}
+
+	return true;
+}
+
 static bool mlxsw_sp_bridge_vxlan_is_valid(struct net_device *br_dev,
 					   struct netlink_ext_ack *extack)
 {
@@ -4639,13 +5363,15 @@ static bool mlxsw_sp_bridge_vxlan_is_valid(struct net_device *br_dev,
 		return false;
 	}
 
-	if (br_vlan_enabled(br_dev)) {
-		NL_SET_ERR_MSG_MOD(extack, "VLAN filtering can not be enabled on a bridge with a VxLAN device");
+	if (!br_vlan_enabled(br_dev) &&
+	    mlxsw_sp_bridge_has_multiple_vxlans(br_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Multiple VxLAN devices are not supported in a VLAN-unaware bridge");
 		return false;
 	}
 
-	if (mlxsw_sp_bridge_has_multiple_vxlans(br_dev)) {
-		NL_SET_ERR_MSG_MOD(extack, "Multiple VxLAN devices are not supported in a VLAN-unaware bridge");
+	if (br_vlan_enabled(br_dev) &&
+	    !mlxsw_sp_bridge_vxlan_vlan_is_valid(br_dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Multiple VxLAN devices cannot have the same VLAN as PVID and egress untagged");
 		return false;
 	}
 
@@ -4719,11 +5445,6 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on an OVS port");
 			return -EINVAL;
 		}
-		if (is_vlan_dev(upper_dev) &&
-		    vlan_dev_vlan_id(upper_dev) == 1) {
-			NL_SET_ERR_MSG_MOD(extack, "Creating a VLAN device with VID 1 is unsupported: VLAN 1 carries untagged traffic");
-			return -EINVAL;
-		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -4738,12 +5459,14 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 							   lower_dev,
 							   upper_dev);
 		} else if (netif_is_lag_master(upper_dev)) {
-			if (info->linking)
+			if (info->linking) {
 				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
 							     upper_dev);
-			else
+			} else {
+				mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port);
 				mlxsw_sp_port_lag_leave(mlxsw_sp_port,
 							upper_dev);
+			}
 		} else if (netif_is_ovs_master(upper_dev)) {
 			if (info->linking)
 				err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
@@ -4752,6 +5475,16 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		} else if (netif_is_macvlan(upper_dev)) {
 			if (!info->linking)
 				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		} else if (is_vlan_dev(upper_dev)) {
+			struct net_device *br_dev;
+
+			if (!netif_is_bridge_port(upper_dev))
+				break;
+			if (info->linking)
+				break;
+			br_dev = netdev_master_upper_dev_get(upper_dev);
+			mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev,
+						   br_dev);
 		}
 		break;
 	}
@@ -4908,6 +5641,48 @@ static int mlxsw_sp_netdevice_lag_port_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
+						struct net_device *br_dev,
+						unsigned long event, void *ptr,
+						u16 vid)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper_dev;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+			return -EOPNOTSUPP;
+		}
+		if (!info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev))
+			mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		break;
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 					 unsigned long event, void *ptr)
 {
@@ -4921,6 +5696,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 		return mlxsw_sp_netdevice_lag_port_vlan_event(vlan_dev,
 							      real_dev, event,
 							      ptr, vid);
+	else if (netif_is_bridge_master(real_dev))
+		return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, real_dev,
+							    event, ptr, vid);
 
 	return 0;
 }
@@ -5020,10 +5798,21 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 		if (cu_info->linking) {
 			if (!netif_running(dev))
 				return 0;
+			/* When the bridge is VLAN-aware, the VNI of the VxLAN
+			 * device needs to be mapped to a VLAN, but at this
+			 * point no VLANs are configured on the VxLAN device
+			 */
+			if (br_vlan_enabled(upper_dev))
+				return 0;
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
-							  dev, extack);
+							  dev, 0, extack);
 		} else {
-			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, upper_dev, dev);
+			/* VLANs were already flushed, which triggered the
+			 * necessary cleanup
+			 */
+			if (br_vlan_enabled(upper_dev))
+				return 0;
+			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
 		}
 		break;
 	case NETDEV_PRE_UP:
@@ -5034,7 +5823,7 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_lower_get(upper_dev))
 			return 0;
-		return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev, dev,
+		return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev, dev, 0,
 						  extack);
 	case NETDEV_DOWN:
 		upper_dev = netdev_master_upper_dev_get(dev);
@@ -5044,7 +5833,7 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_lower_get(upper_dev))
 			return 0;
-		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, upper_dev, dev);
+		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
 		break;
 	}
 
@@ -5075,8 +5864,10 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 	else if (mlxsw_sp_netdev_is_ipip_ul(mlxsw_sp, dev))
 		err = mlxsw_sp_netdevice_ipip_ul_event(mlxsw_sp, dev,
 						       event, ptr);
-	else if (event == NETDEV_CHANGEADDR || event == NETDEV_CHANGEMTU)
-		err = mlxsw_sp_netdevice_router_port_event(dev);
+	else if (event == NETDEV_PRE_CHANGEADDR ||
+		 event == NETDEV_CHANGEADDR ||
+		 event == NETDEV_CHANGEMTU)
+		err = mlxsw_sp_netdevice_router_port_event(dev, event, ptr);
 	else if (mlxsw_sp_is_vrf_event(event, ptr))
 		err = mlxsw_sp_netdevice_vrf_event(dev, event, ptr);
 	else if (mlxsw_sp_port_dev_check(dev))
@@ -5097,18 +5888,10 @@ static struct notifier_block mlxsw_sp_inetaddr_valid_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inetaddr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inetaddr_event,
-};
-
 static struct notifier_block mlxsw_sp_inet6addr_valid_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inet6addr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inet6addr_event,
-};
-
 static const struct pci_device_id mlxsw_sp1_pci_id_table[] = {
 	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
 	{0, },
@@ -5134,9 +5917,7 @@ static int __init mlxsw_sp_module_init(void)
 	int err;
 
 	register_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
-	register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 
 	err = mlxsw_core_driver_register(&mlxsw_sp1_driver);
 	if (err)
@@ -5163,9 +5944,7 @@ err_sp1_pci_driver_register:
 err_sp2_core_driver_register:
 	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
 err_sp1_core_driver_register:
-	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 	return err;
 }
@@ -5176,9 +5955,7 @@ static void __exit mlxsw_sp_module_exit(void)
 	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
-	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 0875a79cbe7b..da6278b0caa4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -8,6 +8,7 @@
 #include <linux/netdevice.h>
 #include <linux/rhashtable.h>
 #include <linux/bitops.h>
+#include <linux/if_bridge.h>
 #include <linux/if_vlan.h>
 #include <linux/list.h>
 #include <linux/dcbnl.h>
@@ -24,13 +25,16 @@
 #include "core_acl_flex_actions.h"
 #include "reg.h"
 
+#define MLXSW_SP_DEFAULT_VID (VLAN_N_VID - 1)
+
 #define MLXSW_SP_FID_8021D_MAX 1024
 
 #define MLXSW_SP_MID_MAX 7000
 
 #define MLXSW_SP_PORTS_PER_CLUSTER_MAX 4
 
-#define MLXSW_SP_PORT_BASE_SPEED 25000	/* Mb/s */
+#define MLXSW_SP_PORT_BASE_SPEED_25G 25000 /* Mb/s */
+#define MLXSW_SP_PORT_BASE_SPEED_50G 50000 /* Mb/s */
 
 #define MLXSW_SP_KVD_LINEAR_SIZE 98304 /* entries */
 #define MLXSW_SP_KVD_GRANULARITY 128
@@ -72,6 +76,11 @@ enum mlxsw_sp_rif_type {
 	MLXSW_SP_RIF_TYPE_MAX,
 };
 
+struct mlxsw_sp_rif_ops;
+
+extern const struct mlxsw_sp_rif_ops *mlxsw_sp1_rif_ops_arr[];
+extern const struct mlxsw_sp_rif_ops *mlxsw_sp2_rif_ops_arr[];
+
 enum mlxsw_sp_fid_type {
 	MLXSW_SP_FID_TYPE_8021Q,
 	MLXSW_SP_FID_TYPE_8021D,
@@ -80,6 +89,10 @@ enum mlxsw_sp_fid_type {
 	MLXSW_SP_FID_TYPE_MAX,
 };
 
+enum mlxsw_sp_nve_type {
+	MLXSW_SP_NVE_TYPE_VXLAN,
+};
+
 struct mlxsw_sp_mid {
 	struct list_head list;
 	unsigned char addr[ETH_ALEN];
@@ -121,12 +134,15 @@ struct mlxsw_sp_kvdl_ops;
 struct mlxsw_sp_mr_tcam_ops;
 struct mlxsw_sp_acl_tcam_ops;
 struct mlxsw_sp_nve_ops;
+struct mlxsw_sp_sb_vals;
+struct mlxsw_sp_port_type_speed_ops;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
 	unsigned char base_mac[ETH_ALEN];
+	const unsigned char *mac_mask;
 	struct mlxsw_sp_upper *lags;
 	int *port_to_module;
 	struct mlxsw_sp_sb *sb;
@@ -153,6 +169,9 @@ struct mlxsw_sp {
 	const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
 	const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops;
 	const struct mlxsw_sp_nve_ops **nve_ops_arr;
+	const struct mlxsw_sp_rif_ops **rif_ops_arr;
+	const struct mlxsw_sp_sb_vals *sb_vals;
+	const struct mlxsw_sp_port_type_speed_ops *port_type_speed_ops;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -184,7 +203,6 @@ struct mlxsw_sp_port_vlan {
 	struct list_head list;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid;
-	unsigned int ref_count;
 	u16 vid;
 	struct mlxsw_sp_bridge_port *bridge_port;
 	struct list_head bridge_vlan_node;
@@ -235,6 +253,7 @@ struct mlxsw_sp_port {
 	} periodic_hw_stats;
 	struct mlxsw_sp_port_sample *sample;
 	struct list_head vlans_list;
+	struct mlxsw_sp_port_vlan *default_vlan;
 	struct mlxsw_sp_qdisc *root_qdisc;
 	struct mlxsw_sp_qdisc *tclass_qdiscs;
 	unsigned acl_rule_count;
@@ -242,6 +261,29 @@ struct mlxsw_sp_port {
 	struct mlxsw_sp_acl_block *eg_acl_block;
 };
 
+struct mlxsw_sp_port_type_speed_ops {
+	void (*from_ptys_supported_port)(struct mlxsw_sp *mlxsw_sp,
+					 u32 ptys_eth_proto,
+					 struct ethtool_link_ksettings *cmd);
+	void (*from_ptys_link)(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto,
+			       unsigned long *mode);
+	void (*from_ptys_speed_duplex)(struct mlxsw_sp *mlxsw_sp,
+				       bool carrier_ok, u32 ptys_eth_proto,
+				       struct ethtool_link_ksettings *cmd);
+	u32 (*to_ptys_advert_link)(struct mlxsw_sp *mlxsw_sp,
+				   const struct ethtool_link_ksettings *cmd);
+	u32 (*to_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u32 speed);
+	u32 (*to_ptys_upper_speed)(struct mlxsw_sp *mlxsw_sp, u32 upper_speed);
+	int (*port_speed_base)(struct mlxsw_sp *mlxsw_sp, u8 local_port,
+			       u32 *base_speed);
+	void (*reg_ptys_eth_pack)(struct mlxsw_sp *mlxsw_sp, char *payload,
+				  u8 local_port, u32 proto_admin, bool autoneg);
+	void (*reg_ptys_eth_unpack)(struct mlxsw_sp *mlxsw_sp, char *payload,
+				    u32 *p_eth_proto_cap,
+				    u32 *p_eth_proto_admin,
+				    u32 *p_eth_proto_oper);
+};
+
 static inline struct net_device *
 mlxsw_sp_bridge_vxlan_dev_find(struct net_device *br_dev)
 {
@@ -261,6 +303,26 @@ static inline bool mlxsw_sp_bridge_has_vxlan(struct net_device *br_dev)
 	return !!mlxsw_sp_bridge_vxlan_dev_find(br_dev);
 }
 
+static inline int
+mlxsw_sp_vxlan_mapped_vid(const struct net_device *vxlan_dev, u16 *p_vid)
+{
+	struct bridge_vlan_info vinfo;
+	u16 vid = 0;
+	int err;
+
+	err = br_vlan_get_pvid(vxlan_dev, &vid);
+	if (err || !vid)
+		goto out;
+
+	err = br_vlan_get_info(vxlan_dev, vid, &vinfo);
+	if (err || !(vinfo.flags & BRIDGE_VLAN_INFO_UNTAGGED))
+		vid = 0;
+
+out:
+	*p_vid = vid;
+	return err;
+}
+
 static inline bool
 mlxsw_sp_port_is_pause_en(const struct mlxsw_sp_port *mlxsw_sp_port)
 {
@@ -337,12 +399,14 @@ int mlxsw_sp_sb_occ_tc_port_bind_get(struct mlxsw_core_port *mlxsw_core_port,
 				     u32 *p_cur, u32 *p_max);
 u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells);
 u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes);
+u32 mlxsw_sp_sb_max_headroom_cells(const struct mlxsw_sp *mlxsw_sp);
+
+extern const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals;
+extern const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals;
 
 /* spectrum_switchdev.c */
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp);
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port);
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
 			bool adding);
 void
@@ -358,11 +422,15 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 					 const struct net_device *br_dev);
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev,
+			       const struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *br_dev,
 				 const struct net_device *vxlan_dev);
+struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+					     const struct net_device *br_dev,
+					     u16 vid,
+					     struct netlink_ext_ack *extack);
+extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
 int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -384,8 +452,8 @@ int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
 				   bool learn_enable);
 int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 struct mlxsw_sp_port_vlan *
-mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
-void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
+mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 			   u16 vid_end, bool is_member, bool untagged);
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
@@ -429,15 +497,12 @@ union mlxsw_sp_l3addr {
 
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
+					 unsigned long event, void *ptr);
 void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			      const struct net_device *macvlan_dev);
-int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-			    unsigned long event, void *ptr);
 int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 				  unsigned long event, void *ptr);
-int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
-			     unsigned long event, void *ptr);
 int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 				   unsigned long event, void *ptr);
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
@@ -457,7 +522,6 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
 				 struct netdev_notifier_info *info);
 void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
 struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
@@ -473,6 +537,9 @@ void mlxsw_sp_router_nve_demote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
 				      const union mlxsw_sp_l3addr *ul_sip);
 int mlxsw_sp_router_tb_id_vr_id(struct mlxsw_sp *mlxsw_sp, u32 tb_id,
 				u16 *vr_id);
+int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
+			       u16 *ul_rif_index);
+void mlxsw_sp_router_ul_rif_put(struct mlxsw_sp *mlxsw_sp, u16 ul_rif_index);
 
 /* spectrum_kvdl.c */
 enum mlxsw_sp_kvdl_entry_type {
@@ -538,6 +605,7 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
 	struct mlxsw_afk_element_values values;
 	struct mlxsw_afa_block *act_block;
+	u8 action_created:1;
 	unsigned int counter_index;
 };
 
@@ -547,6 +615,7 @@ struct mlxsw_sp_acl_ruleset;
 /* spectrum_acl.c */
 enum mlxsw_sp_acl_profile {
 	MLXSW_SP_ACL_PROFILE_FLOWER,
+	MLXSW_SP_ACL_PROFILE_MR,
 };
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
@@ -581,7 +650,8 @@ void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset);
 
 struct mlxsw_sp_acl_rule_info *
-mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl);
+mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
+			  struct mlxsw_afa_block *afa_block);
 void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_commit(struct mlxsw_sp_acl_rule_info *rulei);
 void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
@@ -625,6 +695,7 @@ struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
 			 unsigned long cookie,
+			 struct mlxsw_afa_block *afa_block,
 			 struct netlink_ext_ack *extack);
 void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule *rule);
@@ -632,6 +703,9 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_rule *rule);
 void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_rule *rule);
+int mlxsw_sp_acl_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_rule *rule,
+				     struct mlxsw_afa_block *afa_block);
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
@@ -646,6 +720,8 @@ struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp);
 
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
+u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val);
 
 /* spectrum_acl_tcam.c */
 struct mlxsw_sp_acl_tcam;
@@ -660,10 +736,13 @@ struct mlxsw_sp_acl_tcam_ops {
 	size_t region_priv_size;
 	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			   void *tcam_priv,
-			   struct mlxsw_sp_acl_tcam_region *region);
+			   struct mlxsw_sp_acl_tcam_region *region,
+			   void *hints_priv);
 	void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
 	int (*region_associate)(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam_region *region);
+	void * (*region_rehash_hints_get)(void *region_priv);
+	void (*region_rehash_hints_put)(void *hints_priv);
 	size_t chunk_priv_size;
 	void (*chunk_init)(void *region_priv, void *chunk_priv,
 			   unsigned int priority);
@@ -676,6 +755,9 @@ struct mlxsw_sp_acl_tcam_ops {
 	void (*entry_del)(struct mlxsw_sp *mlxsw_sp,
 			  void *region_priv, void *chunk_priv,
 			  void *entry_priv);
+	int (*entry_action_replace)(struct mlxsw_sp *mlxsw_sp,
+				    void *region_priv, void *entry_priv,
+				    struct mlxsw_sp_acl_rule_info *rulei);
 	int (*entry_activity_get)(struct mlxsw_sp *mlxsw_sp,
 				  void *region_priv, void *entry_priv,
 				  bool *activity);
@@ -721,6 +803,12 @@ int mlxsw_sp_setup_tc_prio(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct tc_prio_qopt_offload *p);
 
 /* spectrum_fid.c */
+bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid);
+struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
+						  u16 fid_index);
+int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex);
+int mlxsw_sp_fid_nve_type(const struct mlxsw_sp_fid *fid,
+			  enum mlxsw_sp_nve_type *p_type);
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni);
 int mlxsw_sp_fid_vni(const struct mlxsw_sp_fid *fid, __be32 *vni);
@@ -728,9 +816,12 @@ int mlxsw_sp_fid_nve_flood_index_set(struct mlxsw_sp_fid *fid,
 				     u32 nve_flood_index);
 void mlxsw_sp_fid_nve_flood_index_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_nve_flood_index_is_set(const struct mlxsw_sp_fid *fid);
-int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni);
+int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, enum mlxsw_sp_nve_type type,
+			 __be32 vni, int nve_ifindex);
 void mlxsw_sp_fid_vni_clear(struct mlxsw_sp_fid *fid);
 bool mlxsw_sp_fid_vni_is_set(const struct mlxsw_sp_fid *fid);
+void mlxsw_sp_fid_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				    const struct net_device *nve_dev);
 int mlxsw_sp_fid_flood_set(struct mlxsw_sp_fid *fid,
 			   enum mlxsw_sp_flood_type packet_type, u8 local_port,
 			   bool member);
@@ -738,10 +829,10 @@ int mlxsw_sp_fid_port_vid_map(struct mlxsw_sp_fid *fid,
 			      struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 void mlxsw_sp_fid_port_vid_unmap(struct mlxsw_sp_fid *fid,
 				 struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
-enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid);
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_fid_type mlxsw_sp_fid_type(const struct mlxsw_sp_fid *fid);
 void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif);
+struct mlxsw_sp_rif *mlxsw_sp_fid_rif(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_rif_type
 mlxsw_sp_fid_type_rif_type(const struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_fid_type type);
@@ -749,6 +840,8 @@ u16 mlxsw_sp_fid_8021q_vid(const struct mlxsw_sp_fid *fid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_get(struct mlxsw_sp *mlxsw_sp, u16 vid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_get(struct mlxsw_sp *mlxsw_sp,
 					    int br_ifindex);
+struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_lookup(struct mlxsw_sp *mlxsw_sp,
+					       u16 vid);
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_lookup(struct mlxsw_sp *mlxsw_sp,
 					       int br_ifindex);
 struct mlxsw_sp_fid *mlxsw_sp_fid_rfid_get(struct mlxsw_sp *mlxsw_sp,
@@ -797,10 +890,6 @@ extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops;
 extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops;
 
 /* spectrum_nve.c */
-enum mlxsw_sp_nve_type {
-	MLXSW_SP_NVE_TYPE_VXLAN,
-};
-
 struct mlxsw_sp_nve_params {
 	enum mlxsw_sp_nve_type type;
 	__be32 vni;
@@ -810,6 +899,9 @@ struct mlxsw_sp_nve_params {
 extern const struct mlxsw_sp_nve_ops *mlxsw_sp1_nve_ops_arr[];
 extern const struct mlxsw_sp_nve_ops *mlxsw_sp2_nve_ops_arr[];
 
+int mlxsw_sp_nve_learned_ip_resolve(struct mlxsw_sp *mlxsw_sp, u32 uip,
+				    enum mlxsw_sp_l3proto proto,
+				    union mlxsw_sp_l3addr *addr);
 int mlxsw_sp_nve_flood_ip_add(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_fid *fid,
 			      enum mlxsw_sp_l3proto proto,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 2a9eac90002e..3a636f753607 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -67,7 +67,7 @@ mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion,
 				      &region->catchall.cchunk,
 				      MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
-	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl, NULL);
 	if (IS_ERR(rulei)) {
 		err = PTR_ERR(rulei);
 		goto err_rulei_create;
@@ -112,7 +112,8 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
 static int
 mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			       void *tcam_priv,
-			       struct mlxsw_sp_acl_tcam_region *_region)
+			       struct mlxsw_sp_acl_tcam_region *_region,
+			       void *hints_priv)
 {
 	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
 	int err;
@@ -193,6 +194,14 @@ static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int
+mlxsw_sp1_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return -EOPNOTSUPP;
+}
+
+static int
 mlxsw_sp1_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 					     struct mlxsw_sp_acl_tcam_region *_region,
 					     unsigned int offset,
@@ -240,5 +249,6 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
 	.entry_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_entry),
 	.entry_add		= mlxsw_sp1_acl_tcam_entry_add,
 	.entry_del		= mlxsw_sp1_acl_tcam_entry_del,
+	.entry_action_replace	= mlxsw_sp1_acl_tcam_entry_action_replace,
 	.entry_activity_get	= mlxsw_sp1_acl_tcam_entry_activity_get,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 8ca77f3e8f27..6c66a0f1b79e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -34,15 +34,15 @@ mlxsw_sp2_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregio
 {
 	struct mlxsw_sp_acl_atcam_region *aregion;
 	struct mlxsw_sp_acl_atcam_entry *aentry;
-	struct mlxsw_sp_acl_erp *erp;
+	struct mlxsw_sp_acl_erp_mask *erp_mask;
 
 	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
 	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
 
-	erp = mlxsw_sp_acl_erp_get(aregion, mask, true);
-	if (IS_ERR(erp))
-		return PTR_ERR(erp);
-	aentry->erp = erp;
+	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, true);
+	if (IS_ERR(erp_mask))
+		return PTR_ERR(erp_mask);
+	aentry->erp_mask = erp_mask;
 
 	return 0;
 }
@@ -57,7 +57,7 @@ mlxsw_sp2_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregio
 	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
 	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
 
-	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
 }
 
 static const struct mlxsw_sp_acl_ctcam_region_ops
@@ -139,7 +139,8 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
 static int
 mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			       void *tcam_priv,
-			       struct mlxsw_sp_acl_tcam_region *_region)
+			       struct mlxsw_sp_acl_tcam_region *_region,
+			       void *hints_priv)
 {
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
 	struct mlxsw_sp2_acl_tcam *tcam = tcam_priv;
@@ -147,7 +148,8 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 	region->region = _region;
 
 	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam,
-					      &region->aregion, _region,
+					      &region->aregion,
+					      _region, hints_priv,
 					      &mlxsw_sp2_acl_ctcam_region_ops);
 }
 
@@ -166,6 +168,18 @@ mlxsw_sp2_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id);
 }
 
+static void *mlxsw_sp2_acl_tcam_region_rehash_hints_get(void *region_priv)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+
+	return mlxsw_sp_acl_atcam_rehash_hints_get(&region->aregion);
+}
+
+static void mlxsw_sp2_acl_tcam_region_rehash_hints_put(void *hints_priv)
+{
+	mlxsw_sp_acl_atcam_rehash_hints_put(hints_priv);
+}
+
 static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
 					  unsigned int priority)
 {
@@ -211,6 +225,20 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int
+mlxsw_sp2_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	entry->act_block = rulei->act_block;
+	return mlxsw_sp_acl_atcam_entry_action_replace(mlxsw_sp,
+						       &region->aregion,
+						       &entry->aentry, rulei);
+}
+
+static int
 mlxsw_sp2_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 				      void *region_priv, void *entry_priv,
 				      bool *activity)
@@ -229,11 +257,14 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = {
 	.region_init		= mlxsw_sp2_acl_tcam_region_init,
 	.region_fini		= mlxsw_sp2_acl_tcam_region_fini,
 	.region_associate	= mlxsw_sp2_acl_tcam_region_associate,
+	.region_rehash_hints_get = mlxsw_sp2_acl_tcam_region_rehash_hints_get,
+	.region_rehash_hints_put = mlxsw_sp2_acl_tcam_region_rehash_hints_put,
 	.chunk_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_chunk),
 	.chunk_init		= mlxsw_sp2_acl_tcam_chunk_init,
 	.chunk_fini		= mlxsw_sp2_acl_tcam_chunk_fini,
 	.entry_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_entry),
 	.entry_add		= mlxsw_sp2_acl_tcam_entry_add,
 	.entry_del		= mlxsw_sp2_acl_tcam_entry_del,
+	.entry_action_replace	= mlxsw_sp2_acl_tcam_entry_action_replace,
 	.entry_activity_get	= mlxsw_sp2_acl_tcam_entry_activity_get,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
index 4dd62478162e..e31ec75ac035 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
@@ -7,6 +7,201 @@
 #include "spectrum.h"
 #include "spectrum_mr.h"
 
+struct mlxsw_sp2_mr_tcam {
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_acl_block *acl_block;
+	struct mlxsw_sp_acl_ruleset *ruleset4;
+	struct mlxsw_sp_acl_ruleset *ruleset6;
+};
+
+struct mlxsw_sp2_mr_route {
+	struct mlxsw_sp2_mr_tcam *mr_tcam;
+};
+
+static struct mlxsw_sp_acl_ruleset *
+mlxsw_sp2_mr_tcam_proto_ruleset(struct mlxsw_sp2_mr_tcam *mr_tcam,
+				enum mlxsw_sp_l3proto proto)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return mr_tcam->ruleset4;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		return mr_tcam->ruleset6;
+	}
+	return NULL;
+}
+
+static int mlxsw_sp2_mr_tcam_bind_group(struct mlxsw_sp *mlxsw_sp,
+					enum mlxsw_reg_pemrbt_protocol protocol,
+					struct mlxsw_sp_acl_ruleset *ruleset)
+{
+	char pemrbt_pl[MLXSW_REG_PEMRBT_LEN];
+	u16 group_id;
+
+	group_id = mlxsw_sp_acl_ruleset_group_id(ruleset);
+
+	mlxsw_reg_pemrbt_pack(pemrbt_pl, protocol, group_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pemrbt), pemrbt_pl);
+}
+
+static const enum mlxsw_afk_element mlxsw_sp2_mr_tcam_usage_ipv4[] = {
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
+		MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+		MLXSW_AFK_ELEMENT_DST_IP_0_31,
+};
+
+static int mlxsw_sp2_mr_tcam_ipv4_init(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	struct mlxsw_afk_element_usage elusage;
+	int err;
+
+	/* Initialize IPv4 ACL group. */
+	mlxsw_afk_element_usage_fill(&elusage,
+				     mlxsw_sp2_mr_tcam_usage_ipv4,
+				     ARRAY_SIZE(mlxsw_sp2_mr_tcam_usage_ipv4));
+	mr_tcam->ruleset4 = mlxsw_sp_acl_ruleset_get(mr_tcam->mlxsw_sp,
+						     mr_tcam->acl_block,
+						     MLXSW_SP_L3_PROTO_IPV4,
+						     MLXSW_SP_ACL_PROFILE_MR,
+						     &elusage);
+
+	if (IS_ERR(mr_tcam->ruleset4))
+		return PTR_ERR(mr_tcam->ruleset4);
+
+	/* MC Router groups should be bound before routes are inserted. */
+	err = mlxsw_sp2_mr_tcam_bind_group(mr_tcam->mlxsw_sp,
+					   MLXSW_REG_PEMRBT_PROTO_IPV4,
+					   mr_tcam->ruleset4);
+	if (err)
+		goto err_bind_group;
+
+	return 0;
+
+err_bind_group:
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset4);
+	return err;
+}
+
+static void mlxsw_sp2_mr_tcam_ipv4_fini(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset4);
+}
+
+static const enum mlxsw_afk_element mlxsw_sp2_mr_tcam_usage_ipv6[] = {
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+		MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
+		MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+		MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+		MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+		MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+		MLXSW_AFK_ELEMENT_DST_IP_96_127,
+		MLXSW_AFK_ELEMENT_DST_IP_64_95,
+		MLXSW_AFK_ELEMENT_DST_IP_32_63,
+		MLXSW_AFK_ELEMENT_DST_IP_0_31,
+};
+
+static int mlxsw_sp2_mr_tcam_ipv6_init(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	struct mlxsw_afk_element_usage elusage;
+	int err;
+
+	/* Initialize IPv6 ACL group */
+	mlxsw_afk_element_usage_fill(&elusage,
+				     mlxsw_sp2_mr_tcam_usage_ipv6,
+				     ARRAY_SIZE(mlxsw_sp2_mr_tcam_usage_ipv6));
+	mr_tcam->ruleset6 = mlxsw_sp_acl_ruleset_get(mr_tcam->mlxsw_sp,
+						     mr_tcam->acl_block,
+						     MLXSW_SP_L3_PROTO_IPV6,
+						     MLXSW_SP_ACL_PROFILE_MR,
+						     &elusage);
+
+	if (IS_ERR(mr_tcam->ruleset6))
+		return PTR_ERR(mr_tcam->ruleset6);
+
+	/* MC Router groups should be bound before routes are inserted. */
+	err = mlxsw_sp2_mr_tcam_bind_group(mr_tcam->mlxsw_sp,
+					   MLXSW_REG_PEMRBT_PROTO_IPV6,
+					   mr_tcam->ruleset6);
+	if (err)
+		goto err_bind_group;
+
+	return 0;
+
+err_bind_group:
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset6);
+	return err;
+}
+
+static void mlxsw_sp2_mr_tcam_ipv6_fini(struct mlxsw_sp2_mr_tcam *mr_tcam)
+{
+	mlxsw_sp_acl_ruleset_put(mr_tcam->mlxsw_sp, mr_tcam->ruleset6);
+}
+
+static void
+mlxsw_sp2_mr_tcam_rule_parse4(struct mlxsw_sp_acl_rule_info *rulei,
+			      struct mlxsw_sp_mr_route_key *key)
+{
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       (char *) &key->source.addr4,
+				       (char *) &key->source_mask.addr4, 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       (char *) &key->group.addr4,
+				       (char *) &key->group_mask.addr4, 4);
+}
+
+static void
+mlxsw_sp2_mr_tcam_rule_parse6(struct mlxsw_sp_acl_rule_info *rulei,
+			      struct mlxsw_sp_mr_route_key *key)
+{
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+				       &key->source.addr6.s6_addr[0x0],
+				       &key->source_mask.addr6.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+				       &key->source.addr6.s6_addr[0x4],
+				       &key->source_mask.addr6.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+				       &key->source.addr6.s6_addr[0x8],
+				       &key->source_mask.addr6.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       &key->source.addr6.s6_addr[0xc],
+				       &key->source_mask.addr6.s6_addr[0xc], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
+				       &key->group.addr6.s6_addr[0x0],
+				       &key->group_mask.addr6.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
+				       &key->group.addr6.s6_addr[0x4],
+				       &key->group_mask.addr6.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
+				       &key->group.addr6.s6_addr[0x8],
+				       &key->group_mask.addr6.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       &key->group.addr6.s6_addr[0xc],
+				       &key->group_mask.addr6.s6_addr[0xc], 4);
+}
+
+static void
+mlxsw_sp2_mr_tcam_rule_parse(struct mlxsw_sp_acl_rule *rule,
+			     struct mlxsw_sp_mr_route_key *key,
+			     unsigned int priority)
+{
+	struct mlxsw_sp_acl_rule_info *rulei;
+
+	rulei = mlxsw_sp_acl_rule_rulei(rule);
+	rulei->priority = priority;
+	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VIRT_ROUTER_0_7,
+				       key->vrid, GENMASK(7, 0));
+	mlxsw_sp_acl_rulei_keymask_u32(rulei,
+				       MLXSW_AFK_ELEMENT_VIRT_ROUTER_8_10,
+				       key->vrid >> 8, GENMASK(2, 0));
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		return mlxsw_sp2_mr_tcam_rule_parse4(rulei, key);
+	case MLXSW_SP_L3_PROTO_IPV6:
+		return mlxsw_sp2_mr_tcam_rule_parse6(rulei, key);
+	}
+}
+
 static int
 mlxsw_sp2_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 			       void *route_priv,
@@ -14,7 +209,33 @@ mlxsw_sp2_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 			       struct mlxsw_afa_block *afa_block,
 			       enum mlxsw_sp_mr_route_prio prio)
 {
+	struct mlxsw_sp2_mr_route *mr_route = route_priv;
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+	int err;
+
+	mr_route->mr_tcam = mr_tcam;
+	ruleset = mlxsw_sp2_mr_tcam_proto_ruleset(mr_tcam, key->proto);
+	if (WARN_ON(!ruleset))
+		return -EINVAL;
+
+	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset,
+					(unsigned long) route_priv, afa_block,
+					NULL);
+	if (IS_ERR(rule))
+		return PTR_ERR(rule);
+
+	mlxsw_sp2_mr_tcam_rule_parse(rule, key, prio);
+	err = mlxsw_sp_acl_rule_add(mlxsw_sp, rule);
+	if (err)
+		goto err_rule_add;
+
 	return 0;
+
+err_rule_add:
+	mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
+	return err;
 }
 
 static void
@@ -22,6 +243,21 @@ mlxsw_sp2_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
 				void *route_priv,
 				struct mlxsw_sp_mr_route_key *key)
 {
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+
+	ruleset = mlxsw_sp2_mr_tcam_proto_ruleset(mr_tcam, key->proto);
+	if (WARN_ON(!ruleset))
+		return;
+
+	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset,
+					(unsigned long) route_priv);
+	if (WARN_ON(!rule))
+		return;
+
+	mlxsw_sp_acl_rule_del(mlxsw_sp, rule);
+	mlxsw_sp_acl_rule_destroy(mlxsw_sp, rule);
 }
 
 static int
@@ -30,21 +266,64 @@ mlxsw_sp2_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_mr_route_key *key,
 			       struct mlxsw_afa_block *afa_block)
 {
-	return 0;
+	struct mlxsw_sp2_mr_route *mr_route = route_priv;
+	struct mlxsw_sp2_mr_tcam *mr_tcam = mr_route->mr_tcam;
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule *rule;
+
+	ruleset = mlxsw_sp2_mr_tcam_proto_ruleset(mr_tcam, key->proto);
+	if (WARN_ON(!ruleset))
+		return -EINVAL;
+
+	rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset,
+					(unsigned long) route_priv);
+	if (WARN_ON(!rule))
+		return -EINVAL;
+
+	return mlxsw_sp_acl_rule_action_replace(mlxsw_sp, rule, afa_block);
 }
 
 static int mlxsw_sp2_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+	int err;
+
+	mr_tcam->mlxsw_sp = mlxsw_sp;
+	mr_tcam->acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, NULL);
+	if (!mr_tcam->acl_block)
+		return -ENOMEM;
+
+	err = mlxsw_sp2_mr_tcam_ipv4_init(mr_tcam);
+	if (err)
+		goto err_ipv4_init;
+
+	err = mlxsw_sp2_mr_tcam_ipv6_init(mr_tcam);
+	if (err)
+		goto err_ipv6_init;
+
 	return 0;
+
+err_ipv6_init:
+	mlxsw_sp2_mr_tcam_ipv4_fini(mr_tcam);
+err_ipv4_init:
+	mlxsw_sp_acl_block_destroy(mr_tcam->acl_block);
+	return err;
 }
 
 static void mlxsw_sp2_mr_tcam_fini(void *priv)
 {
+	struct mlxsw_sp2_mr_tcam *mr_tcam = priv;
+
+	mlxsw_sp2_mr_tcam_ipv6_fini(mr_tcam);
+	mlxsw_sp2_mr_tcam_ipv4_fini(mr_tcam);
+	mlxsw_sp_acl_block_destroy(mr_tcam->acl_block);
 }
 
 const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops = {
+	.priv_size = sizeof(struct mlxsw_sp2_mr_tcam),
 	.init = mlxsw_sp2_mr_tcam_init,
 	.fini = mlxsw_sp2_mr_tcam_fini,
+	.route_priv_size = sizeof(struct mlxsw_sp2_mr_route),
 	.route_create = mlxsw_sp2_mr_tcam_route_create,
 	.route_destroy = mlxsw_sp2_mr_tcam_route_destroy,
 	.route_update = mlxsw_sp2_mr_tcam_route_update,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index c4f9238591e6..a146a44634e9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -435,7 +435,8 @@ u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset)
 }
 
 struct mlxsw_sp_acl_rule_info *
-mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
+mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl,
+			  struct mlxsw_afa_block *afa_block)
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
 	int err;
@@ -443,11 +444,18 @@ mlxsw_sp_acl_rulei_create(struct mlxsw_sp_acl *acl)
 	rulei = kzalloc(sizeof(*rulei), GFP_KERNEL);
 	if (!rulei)
 		return NULL;
+
+	if (afa_block) {
+		rulei->act_block = afa_block;
+		return rulei;
+	}
+
 	rulei->act_block = mlxsw_afa_block_create(acl->mlxsw_sp->afa);
 	if (IS_ERR(rulei->act_block)) {
 		err = PTR_ERR(rulei->act_block);
 		goto err_afa_block_create;
 	}
+	rulei->action_created = 1;
 	return rulei;
 
 err_afa_block_create:
@@ -457,7 +465,8 @@ err_afa_block_create:
 
 void mlxsw_sp_acl_rulei_destroy(struct mlxsw_sp_acl_rule_info *rulei)
 {
-	mlxsw_afa_block_destroy(rulei->act_block);
+	if (rulei->action_created)
+		mlxsw_afa_block_destroy(rulei->act_block);
 	kfree(rulei);
 }
 
@@ -579,7 +588,7 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 {
 	u8 ethertype;
 
-	if (action == TCA_VLAN_ACT_MODIFY) {
+	if (action == FLOW_ACTION_VLAN_MANGLE) {
 		switch (proto) {
 		case ETH_P_8021Q:
 			ethertype = 0;
@@ -623,6 +632,7 @@ struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
 			 unsigned long cookie,
+			 struct mlxsw_afa_block *afa_block,
 			 struct netlink_ext_ack *extack)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
@@ -630,7 +640,7 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_sp_acl_ruleset_ref_inc(ruleset);
-	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp),
+	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size,
 		       GFP_KERNEL);
 	if (!rule) {
 		err = -ENOMEM;
@@ -639,7 +649,7 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 	rule->cookie = cookie;
 	rule->ruleset = ruleset;
 
-	rule->rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+	rule->rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl, afa_block);
 	if (IS_ERR(rule->rulei)) {
 		err = PTR_ERR(rule->rulei);
 		goto err_rulei_create;
@@ -721,6 +731,20 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp,
 	ops->rule_del(mlxsw_sp, rule->priv);
 }
 
+int mlxsw_sp_acl_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_rule *rule,
+				     struct mlxsw_afa_block *afa_block)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset;
+	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
+	struct mlxsw_sp_acl_rule_info *rulei;
+
+	rulei = mlxsw_sp_acl_rule_rulei(rule);
+	rulei->act_block = afa_block;
+
+	return ops->rule_action_replace(mlxsw_sp, rule->priv, rule->rulei);
+}
+
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_lookup(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
@@ -781,7 +805,7 @@ static void mlxsw_sp_acl_rule_activity_work_schedule(struct mlxsw_sp_acl *acl)
 			       msecs_to_jiffies(interval));
 }
 
-static void mlxsw_sp_acl_rul_activity_update_work(struct work_struct *work)
+static void mlxsw_sp_acl_rule_activity_update_work(struct work_struct *work)
 {
 	struct mlxsw_sp_acl *acl = container_of(work, struct mlxsw_sp_acl,
 						rule_activity_update.dw.work);
@@ -860,7 +884,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 
 	/* Create the delayed work for the rule activity_update */
 	INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
-			  mlxsw_sp_acl_rul_activity_update_work);
+			  mlxsw_sp_acl_rule_activity_update_work);
 	acl->rule_activity_update.interval = MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS;
 	mlxsw_core_schedule_dw(&acl->rule_activity_update.dw, 0);
 	return 0;
@@ -888,3 +912,19 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_afk_destroy(acl->afk);
 	kfree(acl);
 }
+
+u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp)
+{
+	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
+
+	return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(mlxsw_sp,
+							   &acl->tcam);
+}
+
+int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val)
+{
+	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
+
+	return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(mlxsw_sp,
+							   &acl->tcam, val);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 2dda028f94db..ded4cf658680 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -7,6 +7,8 @@
 #include <linux/gfp.h>
 #include <linux/refcount.h>
 #include <linux/rhashtable.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/mlxsw.h>
 
 #include "reg.h"
 #include "core.h"
@@ -14,8 +16,8 @@
 #include "spectrum_acl_tcam.h"
 #include "core_acl_flex_keys.h"
 
-#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START	6
-#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END	11
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_START	0
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_END	5
 
 struct mlxsw_sp_acl_atcam_lkey_id_ht_key {
 	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* MSB blocks */
@@ -34,7 +36,7 @@ struct mlxsw_sp_acl_atcam_region_ops {
 	void (*fini)(struct mlxsw_sp_acl_atcam_region *aregion);
 	struct mlxsw_sp_acl_atcam_lkey_id *
 		(*lkey_id_get)(struct mlxsw_sp_acl_atcam_region *aregion,
-			       struct mlxsw_sp_acl_rule_info *rulei, u8 erp_id);
+			       char *enc_key, u8 erp_id);
 	void (*lkey_id_put)(struct mlxsw_sp_acl_atcam_region *aregion,
 			    struct mlxsw_sp_acl_atcam_lkey_id *lkey_id);
 };
@@ -64,7 +66,7 @@ static const struct rhashtable_params mlxsw_sp_acl_atcam_entries_ht_params = {
 static bool
 mlxsw_sp_acl_atcam_is_centry(const struct mlxsw_sp_acl_atcam_entry *aentry)
 {
-	return mlxsw_sp_acl_erp_is_ctcam_erp(aentry->erp);
+	return mlxsw_sp_acl_erp_mask_is_ctcam(aentry->erp_mask);
 }
 
 static int
@@ -90,8 +92,7 @@ mlxsw_sp_acl_atcam_region_generic_fini(struct mlxsw_sp_acl_atcam_region *aregion
 
 static struct mlxsw_sp_acl_atcam_lkey_id *
 mlxsw_sp_acl_atcam_generic_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
-				       struct mlxsw_sp_acl_rule_info *rulei,
-				       u8 erp_id)
+				       char *enc_key, u8 erp_id)
 {
 	struct mlxsw_sp_acl_atcam_region_generic *region_generic;
 
@@ -220,8 +221,7 @@ mlxsw_sp_acl_atcam_lkey_id_destroy(struct mlxsw_sp_acl_atcam_region *aregion,
 
 static struct mlxsw_sp_acl_atcam_lkey_id *
 mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
-				    struct mlxsw_sp_acl_rule_info *rulei,
-				    u8 erp_id)
+				    char *enc_key, u8 erp_id)
 {
 	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
@@ -230,9 +230,10 @@ mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
 
-	mlxsw_afk_encode(afk, region->key_info, &rulei->values, ht_key.enc_key,
-			 NULL, MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START,
-			 MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END);
+	memcpy(ht_key.enc_key, enc_key, sizeof(ht_key.enc_key));
+	mlxsw_afk_clear(afk, ht_key.enc_key,
+			MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_START,
+			MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_CLEAR_END);
 	ht_key.erp_id = erp_id;
 	lkey_id = rhashtable_lookup_fast(&region_12kb->lkey_ht, &ht_key,
 					 mlxsw_sp_acl_atcam_lkey_id_ht_params);
@@ -317,6 +318,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam *atcam,
 			       struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_tcam_region *region,
+			       void *hints_priv,
 			       const struct mlxsw_sp_acl_ctcam_region_ops *ops)
 {
 	int err;
@@ -324,6 +326,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	aregion->region = region;
 	aregion->atcam = atcam;
 	mlxsw_sp_acl_atcam_region_type_init(aregion);
+	INIT_LIST_HEAD(&aregion->entries_list);
 
 	err = rhashtable_init(&aregion->entries_ht,
 			      &mlxsw_sp_acl_atcam_entries_ht_params);
@@ -332,7 +335,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	err = aregion->ops->init(aregion);
 	if (err)
 		goto err_ops_init;
-	err = mlxsw_sp_acl_erp_region_init(aregion);
+	err = mlxsw_sp_acl_erp_region_init(aregion, hints_priv);
 	if (err)
 		goto err_erp_region_init;
 	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
@@ -357,6 +360,7 @@ void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
 	mlxsw_sp_acl_erp_region_fini(aregion);
 	aregion->ops->fini(aregion);
 	rhashtable_destroy(&aregion->entries_ht);
+	WARN_ON(!list_empty(&aregion->entries_list));
 }
 
 void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
@@ -379,7 +383,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
-	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
 	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
 	u32 kvdl_index, priority;
@@ -389,7 +393,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	lkey_id = aregion->ops->lkey_id_get(aregion, rulei, erp_id);
+	lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id);
 	if (IS_ERR(lkey_id))
 		return PTR_ERR(lkey_id);
 	aentry->lkey_id = lkey_id;
@@ -397,7 +401,10 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
 	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
 			     priority, region->tcam_region_info,
-			     aentry->ht_key.enc_key, erp_id,
+			     aentry->enc_key, erp_id,
+			     aentry->delta_info.start,
+			     aentry->delta_info.mask,
+			     aentry->delta_info.value,
 			     refcount_read(&lkey_id->refcnt) != 1, lkey_id->id,
 			     kvdl_index);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
@@ -418,18 +425,50 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
-	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
 	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
 
 	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
-			     region->tcam_region_info, aentry->ht_key.enc_key,
-			     erp_id, refcount_read(&lkey_id->refcnt) != 1,
+			     region->tcam_region_info,
+			     aentry->enc_key, erp_id,
+			     aentry->delta_info.start,
+			     aentry->delta_info.mask,
+			     aentry->delta_info.value,
+			     refcount_read(&lkey_id->refcnt) != 1,
 			     lkey_id->id, 0);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
 	aregion->ops->lkey_id_put(aregion, lkey_id);
 }
 
 static int
+mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					       struct mlxsw_sp_acl_atcam_region *aregion,
+					       struct mlxsw_sp_acl_atcam_entry *aentry,
+					       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
+	u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask);
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
+	u32 kvdl_index, priority;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority, true);
+	if (err)
+		return err;
+	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
+	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE,
+			     priority, region->tcam_region_info,
+			     aentry->enc_key, erp_id,
+			     aentry->delta_info.start,
+			     aentry->delta_info.mask,
+			     aentry->delta_info.value,
+			     refcount_read(&lkey_id->refcnt) != 1, lkey_id->id,
+			     kvdl_index);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
+}
+
+static int
 __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_atcam_entry *aentry,
@@ -438,19 +477,37 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
-	struct mlxsw_sp_acl_erp *erp;
-	unsigned int blocks_count;
+	const struct mlxsw_sp_acl_erp_delta *delta;
+	struct mlxsw_sp_acl_erp_mask *erp_mask;
 	int err;
 
-	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
-			 aentry->ht_key.enc_key, mask, 0, blocks_count - 1);
-
-	erp = mlxsw_sp_acl_erp_get(aregion, mask, false);
-	if (IS_ERR(erp))
-		return PTR_ERR(erp);
-	aentry->erp = erp;
-	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_id(erp);
+			 aentry->ht_key.full_enc_key, mask);
+
+	erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
+	if (IS_ERR(erp_mask))
+		return PTR_ERR(erp_mask);
+	aentry->erp_mask = erp_mask;
+	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
+	memcpy(aentry->enc_key, aentry->ht_key.full_enc_key,
+	       sizeof(aentry->enc_key));
+
+	/* Compute all needed delta information and clear the delta bits
+	 * from the encrypted key.
+	 */
+	delta = mlxsw_sp_acl_erp_delta(aentry->erp_mask);
+	aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
+	aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta);
+	aentry->delta_info.value =
+		mlxsw_sp_acl_erp_delta_value(delta,
+					     aentry->ht_key.full_enc_key);
+	mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key);
+
+	/* Add rule to the list of A-TCAM rules, assuming this
+	 * rule is intended to A-TCAM. In case this rule does
+	 * not fit into A-TCAM it will be removed from the list.
+	 */
+	list_add(&aentry->list, &aregion->entries_list);
 
 	/* We can't insert identical rules into the A-TCAM, so fail and
 	 * let the rule spill into C-TCAM
@@ -461,6 +518,13 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_insert;
 
+	/* Bloom filter must be updated here, before inserting the rule into
+	 * the A-TCAM.
+	 */
+	err = mlxsw_sp_acl_erp_bf_insert(mlxsw_sp, aregion, erp_mask, aentry);
+	if (err)
+		goto err_bf_insert;
+
 	err = mlxsw_sp_acl_atcam_region_entry_insert(mlxsw_sp, aregion, aentry,
 						     rulei);
 	if (err)
@@ -469,10 +533,13 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_rule_insert:
+	mlxsw_sp_acl_erp_bf_remove(mlxsw_sp, aregion, erp_mask, aentry);
+err_bf_insert:
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
 err_rhashtable_insert:
-	mlxsw_sp_acl_erp_put(aregion, erp);
+	list_del(&aentry->list);
+	mlxsw_sp_acl_erp_mask_put(aregion, erp_mask);
 	return err;
 }
 
@@ -482,9 +549,21 @@ __mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam_entry *aentry)
 {
 	mlxsw_sp_acl_atcam_region_entry_remove(mlxsw_sp, aregion, aentry);
+	mlxsw_sp_acl_erp_bf_remove(mlxsw_sp, aregion, aentry->erp_mask, aentry);
 	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
 			       mlxsw_sp_acl_atcam_entries_ht_params);
-	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+	list_del(&aentry->list);
+	mlxsw_sp_acl_erp_mask_put(aregion, aentry->erp_mask);
+}
+
+static int
+__mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					  struct mlxsw_sp_acl_atcam_region *aregion,
+					  struct mlxsw_sp_acl_atcam_entry *aentry,
+					  struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return mlxsw_sp_acl_atcam_region_entry_action_replace(mlxsw_sp, aregion,
+							      aentry, rulei);
 }
 
 int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
@@ -502,6 +581,7 @@ int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	/* It is possible we failed to add the rule to the A-TCAM due to
 	 * exceeded number of masks. Try to spill into C-TCAM.
 	 */
+	trace_mlxsw_sp_acl_atcam_entry_add_ctcam_spill(mlxsw_sp, aregion);
 	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion,
 					   &achunk->cchunk, &aentry->centry,
 					   rulei, true);
@@ -523,6 +603,27 @@ void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 		__mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, aregion, aentry);
 }
 
+int
+mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_atcam_region *aregion,
+					struct mlxsw_sp_acl_atcam_entry *aentry,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	if (mlxsw_sp_acl_atcam_is_centry(aentry))
+		err = mlxsw_sp_acl_ctcam_entry_action_replace(mlxsw_sp,
+							      &aregion->cregion,
+							      &aentry->centry,
+							      rulei);
+	else
+		err = __mlxsw_sp_acl_atcam_entry_action_replace(mlxsw_sp,
+								aregion, aentry,
+								rulei);
+
+	return err;
+}
+
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam)
 {
@@ -534,3 +635,14 @@ void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 {
 	mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam);
 }
+
+void *
+mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	return mlxsw_sp_acl_erp_rehash_hints_get(aregion);
+}
+
+void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv)
+{
+	mlxsw_sp_acl_erp_rehash_hints_put(hints_priv);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
new file mode 100644
index 000000000000..3a2de13fcb68
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -0,0 +1,269 @@
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
+
+#include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/refcount.h>
+#include <linux/mutex.h>
+
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+struct mlxsw_sp_acl_bf {
+	struct mutex lock; /* Protects Bloom Filter updates. */
+	unsigned int bank_size;
+	refcount_t refcnt[0];
+};
+
+/* Bloom filter uses a crc-16 hash over chunks of data which contain 4 key
+ * blocks, eRP ID and region ID. In Spectrum-2, region key is combined of up to
+ * 12 key blocks, so there can be up to 3 chunks in the Bloom filter key,
+ * depending on the actual number of key blocks used in the region.
+ * The layout of the Bloom filter key is as follows:
+ *
+ * +-------------------------+------------------------+------------------------+
+ * | Chunk 2 Key blocks 11-8 | Chunk 1 Key blocks 7-4 | Chunk 0 Key blocks 3-0 |
+ * +-------------------------+------------------------+------------------------+
+ */
+#define MLXSW_BLOOM_KEY_CHUNKS 3
+#define MLXSW_BLOOM_KEY_LEN 69
+
+/* Each chunk size is 23 bytes. 18 bytes of it contain 4 key blocks, each is
+ * 36 bits, 2 bytes which hold eRP ID and region ID, and 3 bytes of zero
+ * padding.
+ * The layout of each chunk is as follows:
+ *
+ * +---------+----------------------+-----------------------------------+
+ * | 3 bytes |        2 bytes       |              18 bytes             |
+ * +---------+-----------+----------+-----------------------------------+
+ * | 183:158 |  157:148  | 147:144  |               143:0               |
+ * +---------+-----------+----------+-----------------------------------+
+ * |    0    | region ID |  eRP ID  |      4 Key blocks (18 Bytes)      |
+ * +---------+-----------+----------+-----------------------------------+
+ */
+#define MLXSW_BLOOM_CHUNK_PAD_BYTES 3
+#define MLXSW_BLOOM_CHUNK_KEY_BYTES 18
+#define MLXSW_BLOOM_KEY_CHUNK_BYTES 23
+
+/* The offset of the key block within a chunk is 5 bytes as it comes after
+ * 3 bytes of zero padding and 16 bits of region ID and eRP ID.
+ */
+#define MLXSW_BLOOM_CHUNK_KEY_OFFSET 5
+
+/* Each chunk contains 4 key blocks. Chunk 2 uses key blocks 11-8,
+ * and we need to populate it with 4 key blocks copied from the entry encoded
+ * key. Since the encoded key contains a padding, key block 11 starts at offset
+ * 2. block 7 that is used in chunk 1 starts at offset 20 as 4 key blocks take
+ * 18 bytes.
+ * This array defines key offsets for easy access when copying key blocks from
+ * entry key to Bloom filter chunk.
+ */
+static const u8 chunk_key_offsets[MLXSW_BLOOM_KEY_CHUNKS] = {2, 20, 38};
+
+/* This table is just the CRC of each possible byte. It is
+ * computed, Msbit first, for the Bloom filter polynomial
+ * which is 0x8529 (1 + x^3 + x^5 + x^8 + x^10 + x^15 and
+ * the implicit x^16).
+ */
+static const u16 mlxsw_sp_acl_bf_crc_tab[256] = {
+0x0000, 0x8529, 0x8f7b, 0x0a52, 0x9bdf, 0x1ef6, 0x14a4, 0x918d,
+0xb297, 0x37be, 0x3dec, 0xb8c5, 0x2948, 0xac61, 0xa633, 0x231a,
+0xe007, 0x652e, 0x6f7c, 0xea55, 0x7bd8, 0xfef1, 0xf4a3, 0x718a,
+0x5290, 0xd7b9, 0xddeb, 0x58c2, 0xc94f, 0x4c66, 0x4634, 0xc31d,
+0x4527, 0xc00e, 0xca5c, 0x4f75, 0xdef8, 0x5bd1, 0x5183, 0xd4aa,
+0xf7b0, 0x7299, 0x78cb, 0xfde2, 0x6c6f, 0xe946, 0xe314, 0x663d,
+0xa520, 0x2009, 0x2a5b, 0xaf72, 0x3eff, 0xbbd6, 0xb184, 0x34ad,
+0x17b7, 0x929e, 0x98cc, 0x1de5, 0x8c68, 0x0941, 0x0313, 0x863a,
+0x8a4e, 0x0f67, 0x0535, 0x801c, 0x1191, 0x94b8, 0x9eea, 0x1bc3,
+0x38d9, 0xbdf0, 0xb7a2, 0x328b, 0xa306, 0x262f, 0x2c7d, 0xa954,
+0x6a49, 0xef60, 0xe532, 0x601b, 0xf196, 0x74bf, 0x7eed, 0xfbc4,
+0xd8de, 0x5df7, 0x57a5, 0xd28c, 0x4301, 0xc628, 0xcc7a, 0x4953,
+0xcf69, 0x4a40, 0x4012, 0xc53b, 0x54b6, 0xd19f, 0xdbcd, 0x5ee4,
+0x7dfe, 0xf8d7, 0xf285, 0x77ac, 0xe621, 0x6308, 0x695a, 0xec73,
+0x2f6e, 0xaa47, 0xa015, 0x253c, 0xb4b1, 0x3198, 0x3bca, 0xbee3,
+0x9df9, 0x18d0, 0x1282, 0x97ab, 0x0626, 0x830f, 0x895d, 0x0c74,
+0x91b5, 0x149c, 0x1ece, 0x9be7, 0x0a6a, 0x8f43, 0x8511, 0x0038,
+0x2322, 0xa60b, 0xac59, 0x2970, 0xb8fd, 0x3dd4, 0x3786, 0xb2af,
+0x71b2, 0xf49b, 0xfec9, 0x7be0, 0xea6d, 0x6f44, 0x6516, 0xe03f,
+0xc325, 0x460c, 0x4c5e, 0xc977, 0x58fa, 0xddd3, 0xd781, 0x52a8,
+0xd492, 0x51bb, 0x5be9, 0xdec0, 0x4f4d, 0xca64, 0xc036, 0x451f,
+0x6605, 0xe32c, 0xe97e, 0x6c57, 0xfdda, 0x78f3, 0x72a1, 0xf788,
+0x3495, 0xb1bc, 0xbbee, 0x3ec7, 0xaf4a, 0x2a63, 0x2031, 0xa518,
+0x8602, 0x032b, 0x0979, 0x8c50, 0x1ddd, 0x98f4, 0x92a6, 0x178f,
+0x1bfb, 0x9ed2, 0x9480, 0x11a9, 0x8024, 0x050d, 0x0f5f, 0x8a76,
+0xa96c, 0x2c45, 0x2617, 0xa33e, 0x32b3, 0xb79a, 0xbdc8, 0x38e1,
+0xfbfc, 0x7ed5, 0x7487, 0xf1ae, 0x6023, 0xe50a, 0xef58, 0x6a71,
+0x496b, 0xcc42, 0xc610, 0x4339, 0xd2b4, 0x579d, 0x5dcf, 0xd8e6,
+0x5edc, 0xdbf5, 0xd1a7, 0x548e, 0xc503, 0x402a, 0x4a78, 0xcf51,
+0xec4b, 0x6962, 0x6330, 0xe619, 0x7794, 0xf2bd, 0xf8ef, 0x7dc6,
+0xbedb, 0x3bf2, 0x31a0, 0xb489, 0x2504, 0xa02d, 0xaa7f, 0x2f56,
+0x0c4c, 0x8965, 0x8337, 0x061e, 0x9793, 0x12ba, 0x18e8, 0x9dc1,
+};
+
+static u16 mlxsw_sp_acl_bf_crc_byte(u16 crc, u8 c)
+{
+	return (crc << 8) ^ mlxsw_sp_acl_bf_crc_tab[(crc >> 8) ^ c];
+}
+
+static u16 mlxsw_sp_acl_bf_crc(const u8 *buffer, size_t len)
+{
+	u16 crc = 0;
+
+	while (len--)
+		crc = mlxsw_sp_acl_bf_crc_byte(crc, *buffer++);
+	return crc;
+}
+
+static void
+mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
+			   struct mlxsw_sp_acl_atcam_entry *aentry,
+			   char *output, u8 *len)
+{
+	struct mlxsw_afk_key_info *key_info = aregion->region->key_info;
+	u8 chunk_index, chunk_count, block_count;
+	char *chunk = output;
+	__be16 erp_region_id;
+
+	block_count = mlxsw_afk_key_info_blocks_count_get(key_info);
+	chunk_count = 1 + ((block_count - 1) >> 2);
+	erp_region_id = cpu_to_be16(aentry->ht_key.erp_id |
+				   (aregion->region->id << 4));
+	for (chunk_index = MLXSW_BLOOM_KEY_CHUNKS - chunk_count;
+	     chunk_index < MLXSW_BLOOM_KEY_CHUNKS; chunk_index++) {
+		memset(chunk, 0, MLXSW_BLOOM_CHUNK_PAD_BYTES);
+		memcpy(chunk + MLXSW_BLOOM_CHUNK_PAD_BYTES, &erp_region_id,
+		       sizeof(erp_region_id));
+		memcpy(chunk + MLXSW_BLOOM_CHUNK_KEY_OFFSET,
+		       &aentry->enc_key[chunk_key_offsets[chunk_index]],
+		       MLXSW_BLOOM_CHUNK_KEY_BYTES);
+		chunk += MLXSW_BLOOM_KEY_CHUNK_BYTES;
+	}
+	*len = chunk_count * MLXSW_BLOOM_KEY_CHUNK_BYTES;
+}
+
+static unsigned int
+mlxsw_sp_acl_bf_rule_count_index_get(struct mlxsw_sp_acl_bf *bf,
+				     unsigned int erp_bank,
+				     unsigned int bf_index)
+{
+	return erp_bank * bf->bank_size + bf_index;
+}
+
+static unsigned int
+mlxsw_sp_acl_bf_index_get(struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	char bf_key[MLXSW_BLOOM_KEY_LEN];
+	u8 bf_size;
+
+	mlxsw_sp_acl_bf_key_encode(aregion, aentry, bf_key, &bf_size);
+	return mlxsw_sp_acl_bf_crc(bf_key, bf_size);
+}
+
+int
+mlxsw_sp_acl_bf_entry_add(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	unsigned int rule_index;
+	char *peabfe_pl;
+	u16 bf_index;
+	int err;
+
+	mutex_lock(&bf->lock);
+
+	bf_index = mlxsw_sp_acl_bf_index_get(bf, aregion, aentry);
+	rule_index = mlxsw_sp_acl_bf_rule_count_index_get(bf, erp_bank,
+							  bf_index);
+
+	if (refcount_inc_not_zero(&bf->refcnt[rule_index])) {
+		err = 0;
+		goto unlock;
+	}
+
+	peabfe_pl = kmalloc(MLXSW_REG_PEABFE_LEN, GFP_KERNEL);
+	if (!peabfe_pl) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	mlxsw_reg_peabfe_pack(peabfe_pl);
+	mlxsw_reg_peabfe_rec_pack(peabfe_pl, 0, 1, erp_bank, bf_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(peabfe), peabfe_pl);
+	kfree(peabfe_pl);
+	if (err)
+		goto unlock;
+
+	refcount_set(&bf->refcnt[rule_index], 1);
+	err = 0;
+
+unlock:
+	mutex_unlock(&bf->lock);
+	return err;
+}
+
+void
+mlxsw_sp_acl_bf_entry_del(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	unsigned int rule_index;
+	char *peabfe_pl;
+	u16 bf_index;
+
+	mutex_lock(&bf->lock);
+
+	bf_index = mlxsw_sp_acl_bf_index_get(bf, aregion, aentry);
+	rule_index = mlxsw_sp_acl_bf_rule_count_index_get(bf, erp_bank,
+							  bf_index);
+
+	if (refcount_dec_and_test(&bf->refcnt[rule_index])) {
+		peabfe_pl = kmalloc(MLXSW_REG_PEABFE_LEN, GFP_KERNEL);
+		if (!peabfe_pl)
+			goto unlock;
+
+		mlxsw_reg_peabfe_pack(peabfe_pl);
+		mlxsw_reg_peabfe_rec_pack(peabfe_pl, 0, 0, erp_bank, bf_index);
+		mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(peabfe), peabfe_pl);
+		kfree(peabfe_pl);
+	}
+
+unlock:
+	mutex_unlock(&bf->lock);
+}
+
+struct mlxsw_sp_acl_bf *
+mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks)
+{
+	struct mlxsw_sp_acl_bf *bf;
+	unsigned int bf_bank_size;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_BF_LOG))
+		return ERR_PTR(-EIO);
+
+	/* Bloom filter size per erp_table_bank
+	 * is 2^ACL_MAX_BF_LOG
+	 */
+	bf_bank_size = 1 << MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_BF_LOG);
+	bf = kzalloc(struct_size(bf, refcnt, bf_bank_size * num_erp_banks),
+		     GFP_KERNEL);
+	if (!bf)
+		return ERR_PTR(-ENOMEM);
+
+	bf->bank_size = bf_bank_size;
+	mutex_init(&bf->lock);
+
+	return bf;
+}
+
+void mlxsw_sp_acl_bf_fini(struct mlxsw_sp_acl_bf *bf)
+{
+	mutex_destroy(&bf->lock);
+	kfree(bf);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index e3c6fe8b1d40..05680a7e6c56 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -46,7 +46,6 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-	unsigned int blocks_count;
 	char *act_set;
 	u32 priority;
 	char *mask;
@@ -63,9 +62,7 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 			     centry->parman_item.index, priority);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
-	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
-	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask, 0,
-			 blocks_count - 1);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
 
 	err = cregion->ops->entry_insert(cregion, centry, mask);
 	if (err)
@@ -75,7 +72,15 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	act_set = mlxsw_afa_block_first_set(rulei->act_block);
 	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
 
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	if (err)
+		goto err_ptce2_write;
+
+	return 0;
+
+err_ptce2_write:
+	cregion->ops->entry_remove(cregion, centry);
+	return err;
 }
 
 static void
@@ -92,6 +97,27 @@ mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	cregion->ops->entry_remove(cregion, centry);
 }
 
+static int
+mlxsw_sp_acl_ctcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					       struct mlxsw_sp_acl_ctcam_region *cregion,
+					       struct mlxsw_sp_acl_ctcam_entry *centry,
+					       struct mlxsw_afa_block *afa_block,
+					       unsigned int priority)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	char *act_set;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_UPDATE,
+			     cregion->region->tcam_region_info,
+			     centry->parman_item.index, priority);
+
+	act_set = mlxsw_afa_block_first_set(afa_block);
+	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+
 static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv,
 						   unsigned long new_count)
 {
@@ -194,3 +220,14 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	parman_item_remove(cregion->parman, &cchunk->parman_prio,
 			   &centry->parman_item);
 }
+
+int mlxsw_sp_acl_ctcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_ctcam_region *cregion,
+					    struct mlxsw_sp_acl_ctcam_entry *centry,
+					    struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return mlxsw_sp_acl_ctcam_region_entry_action_replace(mlxsw_sp, cregion,
+							      centry,
+							      rulei->act_block,
+							      rulei->priority);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 0a4fd3c8662a..c1a9cc9a3292 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -7,7 +7,8 @@
 #include <linux/gfp.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/rhashtable.h>
+#include <linux/mutex.h>
+#include <linux/objagg.h>
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
 
@@ -24,11 +25,14 @@ struct mlxsw_sp_acl_erp_core {
 	unsigned int erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX + 1];
 	struct gen_pool *erp_tables;
 	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_acl_bf *bf;
 	unsigned int num_erp_banks;
 };
 
 struct mlxsw_sp_acl_erp_key {
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN];
+#define __MASK_LEN 0x38
+#define __MASK_IDX(i) (__MASK_LEN - (i) - 1)
 	bool ctcam;
 };
 
@@ -36,10 +40,8 @@ struct mlxsw_sp_acl_erp {
 	struct mlxsw_sp_acl_erp_key key;
 	u8 id;
 	u8 index;
-	refcount_t refcnt;
 	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
 	struct list_head list;
-	struct rhash_head ht_node;
 	struct mlxsw_sp_acl_erp_table *erp_table;
 };
 
@@ -53,7 +55,6 @@ struct mlxsw_sp_acl_erp_table {
 	DECLARE_BITMAP(erp_id_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
 	DECLARE_BITMAP(erp_index_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
 	struct list_head atcam_erps_list;
-	struct rhashtable erp_ht;
 	struct mlxsw_sp_acl_erp_core *erp_core;
 	struct mlxsw_sp_acl_atcam_region *aregion;
 	const struct mlxsw_sp_acl_erp_table_ops *ops;
@@ -61,12 +62,9 @@ struct mlxsw_sp_acl_erp_table {
 	unsigned int num_atcam_erps;
 	unsigned int num_max_atcam_erps;
 	unsigned int num_ctcam_erps;
-};
-
-static const struct rhashtable_params mlxsw_sp_acl_erp_ht_params = {
-	.key_len = sizeof(struct mlxsw_sp_acl_erp_key),
-	.key_offset = offsetof(struct mlxsw_sp_acl_erp, key),
-	.head_offset = offsetof(struct mlxsw_sp_acl_erp, ht_node),
+	unsigned int num_deltas;
+	struct objagg *objagg;
+	struct mutex objagg_lock; /* guards objagg manipulation */
 };
 
 struct mlxsw_sp_acl_erp_table_ops {
@@ -119,14 +117,17 @@ static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = {
 	.erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy,
 };
 
-bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp)
+static bool
+mlxsw_sp_acl_erp_table_is_used(const struct mlxsw_sp_acl_erp_table *erp_table)
 {
-	return erp->key.ctcam;
+	return erp_table->ops != &erp_single_mask_ops &&
+	       erp_table->ops != &erp_no_mask_ops;
 }
 
-u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp)
+static unsigned int
+mlxsw_sp_acl_erp_bank_get(const struct mlxsw_sp_acl_erp *erp)
 {
-	return erp->id;
+	return erp->index % erp->erp_table->erp_core->num_erp_banks;
 }
 
 static unsigned int
@@ -194,12 +195,15 @@ mlxsw_sp_acl_erp_master_mask_update(struct mlxsw_sp_acl_erp_table *erp_table)
 
 static int
 mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table,
-				 const struct mlxsw_sp_acl_erp *erp)
+				 struct mlxsw_sp_acl_erp_key *key)
 {
+	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
 	unsigned long bit;
 	int err;
 
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	bitmap_from_arr32(mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
 						     &erp_table->master_mask);
 
@@ -210,7 +214,7 @@ mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table,
 	return 0;
 
 err_master_mask_update:
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
 						       &erp_table->master_mask);
 	return err;
@@ -218,12 +222,15 @@ err_master_mask_update:
 
 static int
 mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table,
-				   const struct mlxsw_sp_acl_erp *erp)
+				   struct mlxsw_sp_acl_erp_key *key)
 {
+	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
 	unsigned long bit;
 	int err;
 
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	bitmap_from_arr32(mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
 						       &erp_table->master_mask);
 
@@ -234,7 +241,7 @@ mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table,
 	return 0;
 
 err_master_mask_update:
-	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+	for_each_set_bit(bit, mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
 		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
 						     &erp_table->master_mask);
 	return err;
@@ -256,26 +263,16 @@ mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table,
 		goto err_erp_id_get;
 
 	memcpy(&erp->key, key, sizeof(*key));
-	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
-			  MLXSW_SP_ACL_TCAM_MASK_LEN);
 	list_add(&erp->list, &erp_table->atcam_erps_list);
-	refcount_set(&erp->refcnt, 1);
 	erp_table->num_atcam_erps++;
 	erp->erp_table = erp_table;
 
-	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &erp->key);
 	if (err)
 		goto err_master_mask_set;
 
-	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
-				     mlxsw_sp_acl_erp_ht_params);
-	if (err)
-		goto err_rhashtable_insert;
-
 	return erp;
 
-err_rhashtable_insert:
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
 err_master_mask_set:
 	erp_table->num_atcam_erps--;
 	list_del(&erp->list);
@@ -290,9 +287,7 @@ mlxsw_sp_acl_erp_generic_destroy(struct mlxsw_sp_acl_erp *erp)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 
-	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
-			       mlxsw_sp_acl_erp_ht_params);
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
 	erp_table->num_atcam_erps--;
 	list_del(&erp->list);
 	mlxsw_sp_acl_erp_id_put(erp_table, erp->id);
@@ -525,6 +520,48 @@ err_table_relocate:
 }
 
 static int
+mlxsw_acl_erp_table_bf_add(struct mlxsw_sp_acl_erp_table *erp_table,
+			   struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion;
+	unsigned int erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+	int err;
+
+	list_for_each_entry(aentry, &aregion->entries_list, list) {
+		err = mlxsw_sp_acl_bf_entry_add(aregion->region->mlxsw_sp,
+						erp_table->erp_core->bf,
+						aregion, erp_bank, aentry);
+		if (err)
+			goto bf_entry_add_err;
+	}
+
+	return 0;
+
+bf_entry_add_err:
+	list_for_each_entry_continue_reverse(aentry, &aregion->entries_list,
+					     list)
+		mlxsw_sp_acl_bf_entry_del(aregion->region->mlxsw_sp,
+					  erp_table->erp_core->bf,
+					  aregion, erp_bank, aentry);
+	return err;
+}
+
+static void
+mlxsw_acl_erp_table_bf_del(struct mlxsw_sp_acl_erp_table *erp_table,
+			   struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion;
+	unsigned int erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+
+	list_for_each_entry_reverse(aentry, &aregion->entries_list, list)
+		mlxsw_sp_acl_bf_entry_del(aregion->region->mlxsw_sp,
+					  erp_table->erp_core->bf,
+					  aregion, erp_bank, aentry);
+}
+
+static int
 mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 {
 	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
@@ -548,16 +585,24 @@ mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 		goto err_table_master_rp;
 	}
 
-	/* Maintain the same eRP bank for the master RP, so that we
-	 * wouldn't need to update the bloom filter
+	/* Make sure the master RP is using a valid index, as
+	 * only a single eRP row is currently allocated.
 	 */
-	master_rp->index = master_rp->index % erp_core->num_erp_banks;
+	master_rp->index = 0;
 	__set_bit(master_rp->index, erp_table->erp_index_bitmap);
 
 	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, master_rp);
 	if (err)
 		goto err_table_master_rp_add;
 
+	/* Update Bloom filter before enabling eRP table, as rules
+	 * on the master RP were not set to Bloom filter up to this
+	 * point.
+	 */
+	err = mlxsw_acl_erp_table_bf_add(erp_table, master_rp);
+	if (err)
+		goto err_table_bf_add;
+
 	err = mlxsw_sp_acl_erp_table_enable(erp_table, false);
 	if (err)
 		goto err_table_enable;
@@ -565,6 +610,8 @@ mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 	return 0;
 
 err_table_enable:
+	mlxsw_acl_erp_table_bf_del(erp_table, master_rp);
+err_table_bf_add:
 	mlxsw_sp_acl_erp_table_erp_del(master_rp);
 err_table_master_rp_add:
 	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
@@ -585,6 +632,7 @@ mlxsw_sp_acl_erp_region_master_mask_trans(struct mlxsw_sp_acl_erp_table *erp_tab
 	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
 	if (!master_rp)
 		return;
+	mlxsw_acl_erp_table_bf_del(erp_table, master_rp);
 	mlxsw_sp_acl_erp_table_erp_del(master_rp);
 	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
 	mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps,
@@ -647,9 +695,55 @@ mlxsw_sp_acl_erp_region_ctcam_disable(struct mlxsw_sp_acl_erp_table *erp_table)
 	mlxsw_sp_acl_erp_table_enable(erp_table, false);
 }
 
+static int
+__mlxsw_sp_acl_erp_table_other_inc(struct mlxsw_sp_acl_erp_table *erp_table,
+				   unsigned int *inc_num)
+{
+	int err;
+
+	/* If there are C-TCAM eRP or deltas in use we need to transition
+	 * the region to use eRP table, if it is not already done
+	 */
+	if (!mlxsw_sp_acl_erp_table_is_used(erp_table)) {
+		err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
+		if (err)
+			return err;
+	}
+
+	/* When C-TCAM or deltas are used, the eRP table must be used */
+	if (erp_table->ops != &erp_multiple_masks_ops)
+		erp_table->ops = &erp_multiple_masks_ops;
+
+	(*inc_num)++;
+
+	return 0;
+}
+
+static int mlxsw_sp_acl_erp_ctcam_inc(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	return __mlxsw_sp_acl_erp_table_other_inc(erp_table,
+						  &erp_table->num_ctcam_erps);
+}
+
+static int mlxsw_sp_acl_erp_delta_inc(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	return __mlxsw_sp_acl_erp_table_other_inc(erp_table,
+						  &erp_table->num_deltas);
+}
+
 static void
-mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table)
+__mlxsw_sp_acl_erp_table_other_dec(struct mlxsw_sp_acl_erp_table *erp_table,
+				   unsigned int *dec_num)
 {
+	(*dec_num)--;
+
+	/* If there are no C-TCAM eRP or deltas in use, the state we
+	 * transition to depends on the number of A-TCAM eRPs currently
+	 * in use.
+	 */
+	if (erp_table->num_ctcam_erps > 0 || erp_table->num_deltas > 0)
+		return;
+
 	switch (erp_table->num_atcam_erps) {
 	case 2:
 		/* Keep using the eRP table, but correctly set the
@@ -683,9 +777,21 @@ mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table)
 	}
 }
 
+static void mlxsw_sp_acl_erp_ctcam_dec(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	__mlxsw_sp_acl_erp_table_other_dec(erp_table,
+					   &erp_table->num_ctcam_erps);
+}
+
+static void mlxsw_sp_acl_erp_delta_dec(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	__mlxsw_sp_acl_erp_table_other_dec(erp_table,
+					   &erp_table->num_deltas);
+}
+
 static struct mlxsw_sp_acl_erp *
-__mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
-				     struct mlxsw_sp_acl_erp_key *key)
+mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key)
 {
 	struct mlxsw_sp_acl_erp *erp;
 	int err;
@@ -697,89 +803,41 @@ __mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	memcpy(&erp->key, key, sizeof(*key));
 	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
 			  MLXSW_SP_ACL_TCAM_MASK_LEN);
-	refcount_set(&erp->refcnt, 1);
-	erp_table->num_ctcam_erps++;
-	erp->erp_table = erp_table;
 
-	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	err = mlxsw_sp_acl_erp_ctcam_inc(erp_table);
 	if (err)
-		goto err_master_mask_set;
+		goto err_erp_ctcam_inc;
 
-	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
-				     mlxsw_sp_acl_erp_ht_params);
+	erp->erp_table = erp_table;
+
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &erp->key);
 	if (err)
-		goto err_rhashtable_insert;
+		goto err_master_mask_set;
 
 	err = mlxsw_sp_acl_erp_region_ctcam_enable(erp_table);
 	if (err)
 		goto err_erp_region_ctcam_enable;
 
-	/* When C-TCAM is used, the eRP table must be used */
-	erp_table->ops = &erp_multiple_masks_ops;
-
 	return erp;
 
 err_erp_region_ctcam_enable:
-	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
-			       mlxsw_sp_acl_erp_ht_params);
-err_rhashtable_insert:
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
 err_master_mask_set:
-	erp_table->num_ctcam_erps--;
+	mlxsw_sp_acl_erp_ctcam_dec(erp_table);
+err_erp_ctcam_inc:
 	kfree(erp);
 	return ERR_PTR(err);
 }
 
-static struct mlxsw_sp_acl_erp *
-mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
-				   struct mlxsw_sp_acl_erp_key *key)
-{
-	struct mlxsw_sp_acl_erp *erp;
-	int err;
-
-	/* There is a special situation where we need to spill rules
-	 * into the C-TCAM, yet the region is still using a master
-	 * mask and thus not performing a lookup in the C-TCAM. This
-	 * can happen when two rules that only differ in priority - and
-	 * thus sharing the same key - are programmed. In this case
-	 * we transition the region to use an eRP table
-	 */
-	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
-	if (err)
-		return ERR_PTR(err);
-
-	erp = __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
-	if (IS_ERR(erp)) {
-		err = PTR_ERR(erp);
-		goto err_erp_create;
-	}
-
-	return erp;
-
-err_erp_create:
-	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
-	return ERR_PTR(err);
-}
-
 static void
 mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 
 	mlxsw_sp_acl_erp_region_ctcam_disable(erp_table);
-	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
-			       mlxsw_sp_acl_erp_ht_params);
-	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
-	erp_table->num_ctcam_erps--;
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &erp->key);
+	mlxsw_sp_acl_erp_ctcam_dec(erp_table);
 	kfree(erp);
-
-	/* Once the last C-TCAM eRP was destroyed, the state we
-	 * transition to depends on the number of A-TCAM eRPs currently
-	 * in use
-	 */
-	if (erp_table->num_ctcam_erps > 0)
-		return;
-	mlxsw_sp_acl_erp_ctcam_table_ops_set(erp_table);
 }
 
 static struct mlxsw_sp_acl_erp *
@@ -790,7 +848,7 @@ mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	int err;
 
 	if (key->ctcam)
-		return __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+		return mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
 
 	/* Expand the eRP table for the new eRP, if needed */
 	err = mlxsw_sp_acl_erp_table_expand(erp_table);
@@ -838,7 +896,8 @@ mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
 	mlxsw_sp_acl_erp_generic_destroy(erp);
 
-	if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0)
+	if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0 &&
+	    erp_table->num_deltas == 0)
 		erp_table->ops = &erp_two_masks_ops;
 }
 
@@ -940,46 +999,324 @@ mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 	WARN_ON(1);
 }
 
-struct mlxsw_sp_acl_erp *
-mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-		     const char *mask, bool ctcam)
+struct mlxsw_sp_acl_erp_mask *
+mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
+			  const char *mask, bool ctcam)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 	struct mlxsw_sp_acl_erp_key key;
-	struct mlxsw_sp_acl_erp *erp;
-
-	/* eRPs are allocated from a shared resource, but currently all
-	 * allocations are done under RTNL.
-	 */
-	ASSERT_RTNL();
+	struct objagg_obj *objagg_obj;
 
 	memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 	key.ctcam = ctcam;
-	erp = rhashtable_lookup_fast(&erp_table->erp_ht, &key,
-				     mlxsw_sp_acl_erp_ht_params);
-	if (erp) {
-		refcount_inc(&erp->refcnt);
-		return erp;
+	mutex_lock(&erp_table->objagg_lock);
+	objagg_obj = objagg_obj_get(erp_table->objagg, &key);
+	mutex_unlock(&erp_table->objagg_lock);
+	if (IS_ERR(objagg_obj))
+		return ERR_CAST(objagg_obj);
+	return (struct mlxsw_sp_acl_erp_mask *) objagg_obj;
+}
+
+void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+
+	mutex_lock(&erp_table->objagg_lock);
+	objagg_obj_put(erp_table->objagg, objagg_obj);
+	mutex_unlock(&erp_table->objagg_lock);
+}
+
+int mlxsw_sp_acl_erp_bf_insert(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask,
+			       struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
+	unsigned int erp_bank;
+
+	if (!mlxsw_sp_acl_erp_table_is_used(erp->erp_table))
+		return 0;
+
+	erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	return mlxsw_sp_acl_bf_entry_add(mlxsw_sp,
+					erp->erp_table->erp_core->bf,
+					aregion, erp_bank, aentry);
+}
+
+void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_atcam_region *aregion,
+				struct mlxsw_sp_acl_erp_mask *erp_mask,
+				struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
+	unsigned int erp_bank;
+
+	if (!mlxsw_sp_acl_erp_table_is_used(erp->erp_table))
+		return;
+
+	erp_bank = mlxsw_sp_acl_erp_bank_get(erp);
+	mlxsw_sp_acl_bf_entry_del(mlxsw_sp,
+				  erp->erp_table->erp_core->bf,
+				  aregion, erp_bank, aentry);
+}
+
+bool
+mlxsw_sp_acl_erp_mask_is_ctcam(const struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp_key *key = objagg_obj_raw(objagg_obj);
+
+	return key->ctcam;
+}
+
+u8 mlxsw_sp_acl_erp_mask_erp_id(const struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp *erp = objagg_obj_root_priv(objagg_obj);
+
+	return erp->id;
+}
+
+struct mlxsw_sp_acl_erp_delta {
+	struct mlxsw_sp_acl_erp_key key;
+	u16 start;
+	u8 mask;
+};
+
+u16 mlxsw_sp_acl_erp_delta_start(const struct mlxsw_sp_acl_erp_delta *delta)
+{
+	return delta->start;
+}
+
+u8 mlxsw_sp_acl_erp_delta_mask(const struct mlxsw_sp_acl_erp_delta *delta)
+{
+	return delta->mask;
+}
+
+u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta,
+				const char *enc_key)
+{
+	u16 start = delta->start;
+	u8 mask = delta->mask;
+	u16 tmp;
+
+	if (!mask)
+		return 0;
+
+	tmp = (unsigned char) enc_key[__MASK_IDX(start / 8)];
+	if (start / 8 + 1 < __MASK_LEN)
+		tmp |= (unsigned char) enc_key[__MASK_IDX(start / 8 + 1)] << 8;
+	tmp >>= start % 8;
+	tmp &= mask;
+	return tmp;
+}
+
+void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta,
+				  const char *enc_key)
+{
+	u16 start = delta->start;
+	u8 mask = delta->mask;
+	unsigned char *byte;
+	u16 tmp;
+
+	tmp = mask;
+	tmp <<= start % 8;
+	tmp = ~tmp;
+
+	byte = (unsigned char *) &enc_key[__MASK_IDX(start / 8)];
+	*byte &= tmp & 0xff;
+	if (start / 8 + 1 < __MASK_LEN) {
+		byte = (unsigned char *) &enc_key[__MASK_IDX(start / 8 + 1)];
+		*byte &= (tmp >> 8) & 0xff;
+	}
+}
+
+static const struct mlxsw_sp_acl_erp_delta
+mlxsw_sp_acl_erp_delta_default = {};
+
+const struct mlxsw_sp_acl_erp_delta *
+mlxsw_sp_acl_erp_delta(const struct mlxsw_sp_acl_erp_mask *erp_mask)
+{
+	struct objagg_obj *objagg_obj = (struct objagg_obj *) erp_mask;
+	const struct mlxsw_sp_acl_erp_delta *delta;
+
+	delta = objagg_obj_delta_priv(objagg_obj);
+	if (!delta)
+		delta = &mlxsw_sp_acl_erp_delta_default;
+	return delta;
+}
+
+static int
+mlxsw_sp_acl_erp_delta_fill(const struct mlxsw_sp_acl_erp_key *parent_key,
+			    const struct mlxsw_sp_acl_erp_key *key,
+			    u16 *delta_start, u8 *delta_mask)
+{
+	int offset = 0;
+	int si = -1;
+	u16 pmask;
+	u16 mask;
+	int i;
+
+	/* The difference between 2 masks can be up to 8 consecutive bits. */
+	for (i = 0; i < __MASK_LEN; i++) {
+		if (parent_key->mask[__MASK_IDX(i)] == key->mask[__MASK_IDX(i)])
+			continue;
+		if (si == -1)
+			si = i;
+		else if (si != i - 1)
+			return -EINVAL;
+	}
+	if (si == -1) {
+		/* The masks are the same, this cannot happen.
+		 * That means the caller is broken.
+		 */
+		WARN_ON(1);
+		*delta_start = 0;
+		*delta_mask = 0;
+		return 0;
 	}
+	pmask = (unsigned char) parent_key->mask[__MASK_IDX(si)];
+	mask = (unsigned char) key->mask[__MASK_IDX(si)];
+	if (si + 1 < __MASK_LEN) {
+		pmask |= (unsigned char) parent_key->mask[__MASK_IDX(si + 1)] << 8;
+		mask |= (unsigned char) key->mask[__MASK_IDX(si + 1)] << 8;
+	}
+
+	if ((pmask ^ mask) & pmask)
+		return -EINVAL;
+	mask &= ~pmask;
+	while (!(mask & (1 << offset)))
+		offset++;
+	while (!(mask & 1))
+		mask >>= 1;
+	if (mask & 0xff00)
+		return -EINVAL;
 
-	return erp_table->ops->erp_create(erp_table, &key);
+	*delta_start = si * 8 + offset;
+	*delta_mask = mask;
+
+	return 0;
 }
 
-void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
-			  struct mlxsw_sp_acl_erp *erp)
+static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj,
+					 const void *obj)
 {
+	const struct mlxsw_sp_acl_erp_key *parent_key = parent_obj;
+	const struct mlxsw_sp_acl_erp_key *key = obj;
+	u16 delta_start;
+	u8 delta_mask;
+	int err;
+
+	err = mlxsw_sp_acl_erp_delta_fill(parent_key, key,
+					  &delta_start, &delta_mask);
+	return err ? false : true;
+}
+
+static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2)
+{
+	const struct mlxsw_sp_acl_erp_key *key1 = obj1;
+	const struct mlxsw_sp_acl_erp_key *key2 = obj2;
+
+	/* For hints purposes, two objects are considered equal
+	 * in case the masks are the same. Does not matter what
+	 * the "ctcam" value is.
+	 */
+	return memcmp(key1->mask, key2->mask, sizeof(key1->mask));
+}
+
+static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
+					   void *obj)
+{
+	struct mlxsw_sp_acl_erp_key *parent_key = parent_obj;
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
 	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp_acl_erp_key *key = obj;
+	struct mlxsw_sp_acl_erp_delta *delta;
+	u16 delta_start;
+	u8 delta_mask;
+	int err;
 
-	ASSERT_RTNL();
+	if (parent_key->ctcam || key->ctcam)
+		return ERR_PTR(-EINVAL);
+	err = mlxsw_sp_acl_erp_delta_fill(parent_key, key,
+					  &delta_start, &delta_mask);
+	if (err)
+		return ERR_PTR(-EINVAL);
 
-	if (!refcount_dec_and_test(&erp->refcnt))
-		return;
+	delta = kzalloc(sizeof(*delta), GFP_KERNEL);
+	if (!delta)
+		return ERR_PTR(-ENOMEM);
+	delta->start = delta_start;
+	delta->mask = delta_mask;
+
+	err = mlxsw_sp_acl_erp_delta_inc(erp_table);
+	if (err)
+		goto err_erp_delta_inc;
+
+	memcpy(&delta->key, key, sizeof(*key));
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, &delta->key);
+	if (err)
+		goto err_master_mask_set;
+
+	return delta;
+
+err_master_mask_set:
+	mlxsw_sp_acl_erp_delta_dec(erp_table);
+err_erp_delta_inc:
+	kfree(delta);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_acl_erp_delta_destroy(void *priv, void *delta_priv)
+{
+	struct mlxsw_sp_acl_erp_delta *delta = delta_priv;
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 
-	erp_table->ops->erp_destroy(erp_table, erp);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, &delta->key);
+	mlxsw_sp_acl_erp_delta_dec(erp_table);
+	kfree(delta);
 }
 
+static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj,
+					  unsigned int root_id)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp_acl_erp_key *key = obj;
+
+	if (!key->ctcam &&
+	    root_id != OBJAGG_OBJ_ROOT_ID_INVALID &&
+	    root_id >= MLXSW_SP_ACL_ERP_MAX_PER_REGION)
+		return ERR_PTR(-ENOBUFS);
+	return erp_table->ops->erp_create(erp_table, key);
+}
+
+static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = priv;
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+
+	erp_table->ops->erp_destroy(erp_table, root_priv);
+}
+
+static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
+	.obj_size = sizeof(struct mlxsw_sp_acl_erp_key),
+	.delta_check = mlxsw_sp_acl_erp_delta_check,
+	.hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp,
+	.delta_create = mlxsw_sp_acl_erp_delta_create,
+	.delta_destroy = mlxsw_sp_acl_erp_delta_destroy,
+	.root_create = mlxsw_sp_acl_erp_root_create,
+	.root_destroy = mlxsw_sp_acl_erp_root_destroy,
+};
+
 static struct mlxsw_sp_acl_erp_table *
-mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
+mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion,
+			      struct objagg_hints *hints)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table;
 	int err;
@@ -988,18 +1325,22 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
 	if (!erp_table)
 		return ERR_PTR(-ENOMEM);
 
-	err = rhashtable_init(&erp_table->erp_ht, &mlxsw_sp_acl_erp_ht_params);
-	if (err)
-		goto err_rhashtable_init;
+	erp_table->objagg = objagg_create(&mlxsw_sp_acl_erp_objagg_ops,
+					  hints, aregion);
+	if (IS_ERR(erp_table->objagg)) {
+		err = PTR_ERR(erp_table->objagg);
+		goto err_objagg_create;
+	}
 
 	erp_table->erp_core = aregion->atcam->erp_core;
 	erp_table->ops = &erp_no_mask_ops;
 	INIT_LIST_HEAD(&erp_table->atcam_erps_list);
 	erp_table->aregion = aregion;
+	mutex_init(&erp_table->objagg_lock);
 
 	return erp_table;
 
-err_rhashtable_init:
+err_objagg_create:
 	kfree(erp_table);
 	return ERR_PTR(err);
 }
@@ -1008,7 +1349,8 @@ static void
 mlxsw_sp_acl_erp_table_destroy(struct mlxsw_sp_acl_erp_table *erp_table)
 {
 	WARN_ON(!list_empty(&erp_table->atcam_erps_list));
-	rhashtable_destroy(&erp_table->erp_ht);
+	mutex_destroy(&erp_table->objagg_lock);
+	objagg_destroy(erp_table->objagg);
 	kfree(erp_table);
 }
 
@@ -1033,12 +1375,93 @@ mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion)
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
 
-int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion)
+static int
+mlxsw_sp_acl_erp_hints_check(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_atcam_region *aregion,
+			     struct objagg_hints *hints, bool *p_rehash_needed)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	const struct objagg_stats *ostats;
+	const struct objagg_stats *hstats;
+	int err;
+
+	*p_rehash_needed = false;
+
+	mutex_lock(&erp_table->objagg_lock);
+	ostats = objagg_stats_get(erp_table->objagg);
+	mutex_unlock(&erp_table->objagg_lock);
+	if (IS_ERR(ostats)) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP stats\n");
+		return PTR_ERR(ostats);
+	}
+
+	hstats = objagg_hints_stats_get(hints);
+	if (IS_ERR(hstats)) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP hints stats\n");
+		err = PTR_ERR(hstats);
+		goto err_hints_stats_get;
+	}
+
+	/* Very basic criterion for now. */
+	if (hstats->root_count < ostats->root_count)
+		*p_rehash_needed = true;
+
+	err = 0;
+
+	objagg_stats_put(hstats);
+err_hints_stats_get:
+	objagg_stats_put(ostats);
+	return err;
+}
+
+void *
+mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	struct objagg_hints *hints;
+	bool rehash_needed;
+	int err;
+
+	mutex_lock(&erp_table->objagg_lock);
+	hints = objagg_hints_get(erp_table->objagg,
+				 OBJAGG_OPT_ALGO_SIMPLE_GREEDY);
+	mutex_unlock(&erp_table->objagg_lock);
+	if (IS_ERR(hints)) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to create ERP hints\n");
+		return ERR_CAST(hints);
+	}
+	err = mlxsw_sp_acl_erp_hints_check(mlxsw_sp, aregion, hints,
+					   &rehash_needed);
+	if (err)
+		goto errout;
+
+	if (!rehash_needed) {
+		err = -EAGAIN;
+		goto errout;
+	}
+	return hints;
+
+errout:
+	objagg_hints_put(hints);
+	return ERR_PTR(err);
+}
+
+void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv)
+{
+	struct objagg_hints *hints = hints_priv;
+
+	objagg_hints_put(hints);
+}
+
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				 void *hints_priv)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table;
+	struct objagg_hints *hints = hints_priv;
 	int err;
 
-	erp_table = mlxsw_sp_acl_erp_table_create(aregion);
+	erp_table = mlxsw_sp_acl_erp_table_create(aregion, hints);
 	if (IS_ERR(erp_table))
 		return PTR_ERR(erp_table);
 	aregion->erp_table = erp_table;
@@ -1118,6 +1541,12 @@ static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_gen_pool_add;
 
+	erp_core->bf = mlxsw_sp_acl_bf_init(mlxsw_sp, erp_core->num_erp_banks);
+	if (IS_ERR(erp_core->bf)) {
+		err = PTR_ERR(erp_core->bf);
+		goto err_bf_init;
+	}
+
 	/* Different regions require masks of different sizes */
 	err = mlxsw_sp_acl_erp_tables_sizes_query(mlxsw_sp, erp_core);
 	if (err)
@@ -1126,6 +1555,8 @@ static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_erp_tables_sizes_query:
+	mlxsw_sp_acl_bf_fini(erp_core->bf);
+err_bf_init:
 err_gen_pool_add:
 	gen_pool_destroy(erp_core->erp_tables);
 	return err;
@@ -1134,6 +1565,7 @@ err_gen_pool_add:
 static void mlxsw_sp_acl_erp_tables_fini(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_acl_erp_core *erp_core)
 {
+	mlxsw_sp_acl_bf_fini(erp_core->bf);
 	gen_pool_destroy(erp_core->erp_tables);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index d409b09ba8df..2a998dea4f39 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -98,8 +98,8 @@ static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
 
 #define MLXSW_SP1_AFK_KEY_BLOCK_SIZE 16
 
-static void mlxsw_sp1_afk_encode_block(char *block, int block_index,
-				       char *output)
+static void mlxsw_sp1_afk_encode_block(char *output, int block_index,
+				       char *block)
 {
 	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
 	char *output_indexed = output + offset;
@@ -107,10 +107,19 @@ static void mlxsw_sp1_afk_encode_block(char *block, int block_index,
 	memcpy(output_indexed, block, MLXSW_SP1_AFK_KEY_BLOCK_SIZE);
 }
 
+static void mlxsw_sp1_afk_clear_block(char *output, int block_index)
+{
+	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
+	char *output_indexed = output + offset;
+
+	memset(output_indexed, 0, MLXSW_SP1_AFK_KEY_BLOCK_SIZE);
+}
+
 const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
 	.blocks		= mlxsw_sp1_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
 	.encode_block	= mlxsw_sp1_afk_encode_block,
+	.clear_block	= mlxsw_sp1_afk_clear_block,
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = {
@@ -158,6 +167,11 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x04, 16, 8),
 };
 
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_4[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_0_7, 0x04, 24, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(VIRT_ROUTER_8_10, 0x00, 0, 3),
+};
+
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x04, 4),
 };
@@ -201,6 +215,7 @@ static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0x38, mlxsw_sp_afk_element_info_ipv4_0),
 	MLXSW_AFK_BLOCK(0x39, mlxsw_sp_afk_element_info_ipv4_1),
 	MLXSW_AFK_BLOCK(0x3A, mlxsw_sp_afk_element_info_ipv4_2),
+	MLXSW_AFK_BLOCK(0x3C, mlxsw_sp_afk_element_info_ipv4_4),
 	MLXSW_AFK_BLOCK(0x40, mlxsw_sp_afk_element_info_ipv6_0),
 	MLXSW_AFK_BLOCK(0x41, mlxsw_sp_afk_element_info_ipv6_1),
 	MLXSW_AFK_BLOCK(0x42, mlxsw_sp_afk_element_info_ipv6_2),
@@ -263,10 +278,9 @@ static const struct mlxsw_sp2_afk_block_layout mlxsw_sp2_afk_blocks_layout[] = {
 	MLXSW_SP2_AFK_BLOCK_LAYOUT(block11, 0x00, 12),
 };
 
-static void mlxsw_sp2_afk_encode_block(char *block, int block_index,
-				       char *output)
+static void __mlxsw_sp2_afk_block_value_set(char *output, int block_index,
+					    u64 block_value)
 {
-	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
 	const struct mlxsw_sp2_afk_block_layout *block_layout;
 
 	if (WARN_ON(block_index < 0 ||
@@ -278,8 +292,22 @@ static void mlxsw_sp2_afk_encode_block(char *block, int block_index,
 			   &block_layout->item, 0, block_value);
 }
 
+static void mlxsw_sp2_afk_encode_block(char *output, int block_index,
+				       char *block)
+{
+	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
+
+	__mlxsw_sp2_afk_block_value_set(output, block_index, block_value);
+}
+
+static void mlxsw_sp2_afk_clear_block(char *output, int block_index)
+{
+	__mlxsw_sp2_afk_block_value_set(output, block_index, 0);
+}
+
 const struct mlxsw_afk_ops mlxsw_sp2_afk_ops = {
 	.blocks		= mlxsw_sp2_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp2_afk_blocks),
 	.encode_block	= mlxsw_sp2_afk_encode_block,
+	.clear_block	= mlxsw_sp2_afk_clear_block,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index e171513bb32a..8811f6513e36 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -8,6 +8,8 @@
 #include <linux/list.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
+#include <linux/mutex.h>
+#include <trace/events/mlxsw.h>
 
 #include "reg.h"
 #include "core.h"
@@ -23,6 +25,10 @@ size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp)
 	return ops->priv_size;
 }
 
+#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT 5000 /* ms */
+#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN 3000 /* ms */
+#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS 100 /* number of entries */
+
 int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_tcam *tcam)
 {
@@ -33,6 +39,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 	size_t alloc_size;
 	int err;
 
+	mutex_init(&tcam->lock);
+	tcam->vregion_rehash_intrvl =
+			MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT;
+	INIT_LIST_HEAD(&tcam->vregion_list);
+
 	max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 					      ACL_MAX_TCAM_REGIONS);
 	max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS);
@@ -76,6 +87,7 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
+	mutex_destroy(&tcam->lock);
 	ops->fini(mlxsw_sp, tcam->priv);
 	kfree(tcam->used_groups);
 	kfree(tcam->used_regions);
@@ -95,8 +107,9 @@ int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, KVD_SIZE))
 		return -EIO;
 
-	max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE);
-	if (rulei->priority > max_priority)
+	/* Priority range is 1..cap_kvd_size-1. */
+	max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE) - 1;
+	if (rulei->priority >= max_priority)
 		return -EINVAL;
 
 	/* Unlike in TC, in HW, higher number means higher priority. */
@@ -152,37 +165,100 @@ struct mlxsw_sp_acl_tcam_pattern {
 struct mlxsw_sp_acl_tcam_group {
 	struct mlxsw_sp_acl_tcam *tcam;
 	u16 id;
+	struct mutex lock; /* guards region list updates */
 	struct list_head region_list;
 	unsigned int region_count;
-	struct rhashtable chunk_ht;
-	struct mlxsw_sp_acl_tcam_group_ops *ops;
+};
+
+struct mlxsw_sp_acl_tcam_vgroup {
+	struct mlxsw_sp_acl_tcam_group group;
+	struct list_head vregion_list;
+	struct rhashtable vchunk_ht;
 	const struct mlxsw_sp_acl_tcam_pattern *patterns;
 	unsigned int patterns_count;
 	bool tmplt_elusage_set;
 	struct mlxsw_afk_element_usage tmplt_elusage;
+	bool vregion_rehash_enabled;
 };
 
-struct mlxsw_sp_acl_tcam_chunk {
-	struct list_head list; /* Member of a TCAM region */
-	struct rhash_head ht_node; /* Member of a chunk HT */
-	unsigned int priority; /* Priority within the region and group */
-	struct mlxsw_sp_acl_tcam_group *group;
+struct mlxsw_sp_acl_tcam_rehash_ctx {
+	void *hints_priv;
+	bool this_is_rollback;
+	struct mlxsw_sp_acl_tcam_vchunk *current_vchunk; /* vchunk being
+							  * currently migrated.
+							  */
+	struct mlxsw_sp_acl_tcam_ventry *start_ventry; /* ventry to start
+							* migration from in
+							* a vchunk being
+							* currently migrated.
+							*/
+	struct mlxsw_sp_acl_tcam_ventry *stop_ventry; /* ventry to stop
+						       * migration at
+						       * a vchunk being
+						       * currently migrated.
+						       */
+};
+
+struct mlxsw_sp_acl_tcam_vregion {
+	struct mutex lock; /* Protects consistency of region, region2 pointers
+			    * and vchunk_list.
+			    */
 	struct mlxsw_sp_acl_tcam_region *region;
+	struct mlxsw_sp_acl_tcam_region *region2; /* Used during migration */
+	struct list_head list; /* Member of a TCAM group */
+	struct list_head tlist; /* Member of a TCAM */
+	struct list_head vchunk_list; /* List of vchunks under this vregion */
+	struct mlxsw_afk_key_info *key_info;
+	struct mlxsw_sp_acl_tcam *tcam;
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup;
+	struct {
+		struct delayed_work dw;
+		struct mlxsw_sp_acl_tcam_rehash_ctx ctx;
+	} rehash;
+	struct mlxsw_sp *mlxsw_sp;
+	bool failed_rollback; /* Indicates failed rollback during migration */
 	unsigned int ref_count;
+};
+
+struct mlxsw_sp_acl_tcam_vchunk;
+
+struct mlxsw_sp_acl_tcam_chunk {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct mlxsw_sp_acl_tcam_region *region;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
 
+struct mlxsw_sp_acl_tcam_vchunk {
+	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_chunk *chunk2; /* Used during migration */
+	struct list_head list; /* Member of a TCAM vregion */
+	struct rhash_head ht_node; /* Member of a chunk HT */
+	struct list_head ventry_list;
+	unsigned int priority; /* Priority within the vregion and group */
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	unsigned int ref_count;
+};
+
 struct mlxsw_sp_acl_tcam_entry {
+	struct mlxsw_sp_acl_tcam_ventry *ventry;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
 
-static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = {
+struct mlxsw_sp_acl_tcam_ventry {
+	struct mlxsw_sp_acl_tcam_entry *entry;
+	struct list_head list; /* Member of a TCAM vchunk */
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct mlxsw_sp_acl_rule_info *rulei;
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_tcam_vchunk_ht_params = {
 	.key_len = sizeof(unsigned int),
-	.key_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, priority),
-	.head_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, ht_node),
+	.key_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, priority),
+	.head_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, ht_node),
 	.automatic_shrinking = true,
 };
 
@@ -194,55 +270,90 @@ static int mlxsw_sp_acl_tcam_group_update(struct mlxsw_sp *mlxsw_sp,
 	int acl_index = 0;
 
 	mlxsw_reg_pagt_pack(pagt_pl, group->id);
-	list_for_each_entry(region, &group->region_list, list)
-		mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, region->id);
+	list_for_each_entry(region, &group->region_list, list) {
+		bool multi = false;
+
+		/* Check if the next entry in the list has the same vregion. */
+		if (region->list.next != &group->region_list &&
+		    list_next_entry(region, list)->vregion == region->vregion)
+			multi = true;
+		mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++,
+					   region->id, multi);
+	}
 	mlxsw_reg_pagt_size_set(pagt_pl, acl_index);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pagt), pagt_pl);
 }
 
 static int
-mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_tcam *tcam,
-			    struct mlxsw_sp_acl_tcam_group *group,
-			    const struct mlxsw_sp_acl_tcam_pattern *patterns,
-			    unsigned int patterns_count,
-			    struct mlxsw_afk_element_usage *tmplt_elusage)
+mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp_acl_tcam *tcam,
+			    struct mlxsw_sp_acl_tcam_group *group)
 {
 	int err;
 
 	group->tcam = tcam;
-	group->patterns = patterns;
-	group->patterns_count = patterns_count;
-	if (tmplt_elusage) {
-		group->tmplt_elusage_set = true;
-		memcpy(&group->tmplt_elusage, tmplt_elusage,
-		       sizeof(group->tmplt_elusage));
-	}
+	mutex_init(&group->lock);
 	INIT_LIST_HEAD(&group->region_list);
+
 	err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
 	if (err)
 		return err;
 
-	err = rhashtable_init(&group->chunk_ht,
-			      &mlxsw_sp_acl_tcam_chunk_ht_params);
+	return 0;
+}
+
+static void mlxsw_sp_acl_tcam_group_del(struct mlxsw_sp_acl_tcam_group *group)
+{
+	struct mlxsw_sp_acl_tcam *tcam = group->tcam;
+
+	mutex_destroy(&group->lock);
+	mlxsw_sp_acl_tcam_group_id_put(tcam, group->id);
+	WARN_ON(!list_empty(&group->region_list));
+}
+
+static int
+mlxsw_sp_acl_tcam_vgroup_add(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_tcam *tcam,
+			     struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+			     const struct mlxsw_sp_acl_tcam_pattern *patterns,
+			     unsigned int patterns_count,
+			     struct mlxsw_afk_element_usage *tmplt_elusage,
+			     bool vregion_rehash_enabled)
+{
+	int err;
+
+	vgroup->patterns = patterns;
+	vgroup->patterns_count = patterns_count;
+	vgroup->vregion_rehash_enabled = vregion_rehash_enabled;
+
+	if (tmplt_elusage) {
+		vgroup->tmplt_elusage_set = true;
+		memcpy(&vgroup->tmplt_elusage, tmplt_elusage,
+		       sizeof(vgroup->tmplt_elusage));
+	}
+	INIT_LIST_HEAD(&vgroup->vregion_list);
+
+	err = mlxsw_sp_acl_tcam_group_add(tcam, &vgroup->group);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&vgroup->vchunk_ht,
+			      &mlxsw_sp_acl_tcam_vchunk_ht_params);
 	if (err)
 		goto err_rhashtable_init;
 
 	return 0;
 
 err_rhashtable_init:
-	mlxsw_sp_acl_tcam_group_id_put(tcam, group->id);
+	mlxsw_sp_acl_tcam_group_del(&vgroup->group);
 	return err;
 }
 
-static void mlxsw_sp_acl_tcam_group_del(struct mlxsw_sp *mlxsw_sp,
-					struct mlxsw_sp_acl_tcam_group *group)
+static void
+mlxsw_sp_acl_tcam_vgroup_del(struct mlxsw_sp_acl_tcam_vgroup *vgroup)
 {
-	struct mlxsw_sp_acl_tcam *tcam = group->tcam;
-
-	rhashtable_destroy(&group->chunk_ht);
-	mlxsw_sp_acl_tcam_group_id_put(tcam, group->id);
-	WARN_ON(!list_empty(&group->region_list));
+	rhashtable_destroy(&vgroup->vchunk_ht);
+	mlxsw_sp_acl_tcam_group_del(&vgroup->group);
+	WARN_ON(!list_empty(&vgroup->vregion_list));
 }
 
 static int
@@ -282,146 +393,194 @@ mlxsw_sp_acl_tcam_group_id(struct mlxsw_sp_acl_tcam_group *group)
 }
 
 static unsigned int
-mlxsw_sp_acl_tcam_region_prio(struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vregion_prio(struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 
-	if (list_empty(&region->chunk_list))
+	if (list_empty(&vregion->vchunk_list))
 		return 0;
-	/* As a priority of a region, return priority of the first chunk */
-	chunk = list_first_entry(&region->chunk_list, typeof(*chunk), list);
-	return chunk->priority;
+	/* As a priority of a vregion, return priority of the first vchunk */
+	vchunk = list_first_entry(&vregion->vchunk_list,
+				  typeof(*vchunk), list);
+	return vchunk->priority;
 }
 
 static unsigned int
-mlxsw_sp_acl_tcam_region_max_prio(struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vregion_max_prio(struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 
-	if (list_empty(&region->chunk_list))
+	if (list_empty(&vregion->vchunk_list))
 		return 0;
-	chunk = list_last_entry(&region->chunk_list, typeof(*chunk), list);
-	return chunk->priority;
+	vchunk = list_last_entry(&vregion->vchunk_list,
+				 typeof(*vchunk), list);
+	return vchunk->priority;
 }
 
-static void
-mlxsw_sp_acl_tcam_group_list_add(struct mlxsw_sp_acl_tcam_group *group,
-				 struct mlxsw_sp_acl_tcam_region *region)
+static int
+mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_acl_tcam_group *group,
+				      struct mlxsw_sp_acl_tcam_region *region,
+				      unsigned int priority,
+				      struct mlxsw_sp_acl_tcam_region *next_region)
 {
 	struct mlxsw_sp_acl_tcam_region *region2;
 	struct list_head *pos;
+	int err;
 
-	/* Position the region inside the list according to priority */
-	list_for_each(pos, &group->region_list) {
-		region2 = list_entry(pos, typeof(*region2), list);
-		if (mlxsw_sp_acl_tcam_region_prio(region2) >
-		    mlxsw_sp_acl_tcam_region_prio(region))
-			break;
+	mutex_lock(&group->lock);
+	if (group->region_count == group->tcam->max_group_size) {
+		err = -ENOBUFS;
+		goto err_region_count_check;
+	}
+
+	if (next_region) {
+		/* If the next region is defined, place the new one
+		 * before it. The next one is a sibling.
+		 */
+		pos = &next_region->list;
+	} else {
+		/* Position the region inside the list according to priority */
+		list_for_each(pos, &group->region_list) {
+			region2 = list_entry(pos, typeof(*region2), list);
+			if (mlxsw_sp_acl_tcam_vregion_prio(region2->vregion) >
+			    priority)
+				break;
+		}
 	}
 	list_add_tail(&region->list, pos);
+	region->group = group;
+
+	err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	if (err)
+		goto err_group_update;
+
 	group->region_count++;
+	mutex_unlock(&group->lock);
+	return 0;
+
+err_group_update:
+	list_del(&region->list);
+err_region_count_check:
+	mutex_unlock(&group->lock);
+	return err;
 }
 
 static void
-mlxsw_sp_acl_tcam_group_list_del(struct mlxsw_sp_acl_tcam_group *group,
-				 struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_acl_tcam_region *region)
 {
-	group->region_count--;
+	struct mlxsw_sp_acl_tcam_group *group = region->group;
+
+	mutex_lock(&group->lock);
 	list_del(&region->list);
+	group->region_count--;
+	mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	mutex_unlock(&group->lock);
 }
 
 static int
-mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_group *group,
-				      struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vgroup_vregion_attach(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+					struct mlxsw_sp_acl_tcam_vregion *vregion,
+					unsigned int priority)
 {
+	struct mlxsw_sp_acl_tcam_vregion *vregion2;
+	struct list_head *pos;
 	int err;
 
-	if (group->region_count == group->tcam->max_group_size)
-		return -ENOBUFS;
-
-	mlxsw_sp_acl_tcam_group_list_add(group, region);
+	/* Position the vregion inside the list according to priority */
+	list_for_each(pos, &vgroup->vregion_list) {
+		vregion2 = list_entry(pos, typeof(*vregion2), list);
+		if (mlxsw_sp_acl_tcam_vregion_prio(vregion2) > priority)
+			break;
+	}
+	list_add_tail(&vregion->list, pos);
 
-	err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, &vgroup->group,
+						    vregion->region,
+						    priority, NULL);
 	if (err)
-		goto err_group_update;
-	region->group = group;
+		goto err_region_attach;
 
 	return 0;
 
-err_group_update:
-	mlxsw_sp_acl_tcam_group_list_del(group, region);
-	mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+err_region_attach:
+	list_del(&vregion->list);
 	return err;
 }
 
 static void
-mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region)
+mlxsw_sp_acl_tcam_vgroup_vregion_detach(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_group *group = region->group;
-
-	mlxsw_sp_acl_tcam_group_list_del(group, region);
-	mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group);
+	list_del(&vregion->list);
+	if (vregion->region2)
+		mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp,
+						      vregion->region2);
+	mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, vregion->region);
 }
 
-static struct mlxsw_sp_acl_tcam_region *
-mlxsw_sp_acl_tcam_group_region_find(struct mlxsw_sp_acl_tcam_group *group,
-				    unsigned int priority,
-				    struct mlxsw_afk_element_usage *elusage,
-				    bool *p_need_split)
+static struct mlxsw_sp_acl_tcam_vregion *
+mlxsw_sp_acl_tcam_vgroup_vregion_find(struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				      unsigned int priority,
+				      struct mlxsw_afk_element_usage *elusage,
+				      bool *p_need_split)
 {
-	struct mlxsw_sp_acl_tcam_region *region, *region2;
+	struct mlxsw_sp_acl_tcam_vregion *vregion, *vregion2;
 	struct list_head *pos;
 	bool issubset;
 
-	list_for_each(pos, &group->region_list) {
-		region = list_entry(pos, typeof(*region), list);
+	list_for_each(pos, &vgroup->vregion_list) {
+		vregion = list_entry(pos, typeof(*vregion), list);
 
 		/* First, check if the requested priority does not rather belong
-		 * under some of the next regions.
+		 * under some of the next vregions.
 		 */
-		if (pos->next != &group->region_list) { /* not last */
-			region2 = list_entry(pos->next, typeof(*region2), list);
-			if (priority >= mlxsw_sp_acl_tcam_region_prio(region2))
+		if (pos->next != &vgroup->vregion_list) { /* not last */
+			vregion2 = list_entry(pos->next, typeof(*vregion2),
+					      list);
+			if (priority >=
+			    mlxsw_sp_acl_tcam_vregion_prio(vregion2))
 				continue;
 		}
 
-		issubset = mlxsw_afk_key_info_subset(region->key_info, elusage);
+		issubset = mlxsw_afk_key_info_subset(vregion->key_info,
+						     elusage);
 
 		/* If requested element usage would not fit and the priority
-		 * is lower than the currently inspected region we cannot
-		 * use this region, so return NULL to indicate new region has
+		 * is lower than the currently inspected vregion we cannot
+		 * use this region, so return NULL to indicate new vregion has
 		 * to be created.
 		 */
 		if (!issubset &&
-		    priority < mlxsw_sp_acl_tcam_region_prio(region))
+		    priority < mlxsw_sp_acl_tcam_vregion_prio(vregion))
 			return NULL;
 
 		/* If requested element usage would not fit and the priority
-		 * is higher than the currently inspected region we cannot
-		 * use this region. There is still some hope that the next
-		 * region would be the fit. So let it be processed and
+		 * is higher than the currently inspected vregion we cannot
+		 * use this vregion. There is still some hope that the next
+		 * vregion would be the fit. So let it be processed and
 		 * eventually break at the check right above this.
 		 */
 		if (!issubset &&
-		    priority > mlxsw_sp_acl_tcam_region_max_prio(region))
+		    priority > mlxsw_sp_acl_tcam_vregion_max_prio(vregion))
 			continue;
 
-		/* Indicate if the region needs to be split in order to add
+		/* Indicate if the vregion needs to be split in order to add
 		 * the requested priority. Split is needed when requested
-		 * element usage won't fit into the found region.
+		 * element usage won't fit into the found vregion.
 		 */
 		*p_need_split = !issubset;
-		return region;
+		return vregion;
 	}
-	return NULL; /* New region has to be created. */
+	return NULL; /* New vregion has to be created. */
 }
 
 static void
-mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
-				     struct mlxsw_afk_element_usage *elusage,
-				     struct mlxsw_afk_element_usage *out)
+mlxsw_sp_acl_tcam_vgroup_use_patterns(struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				      struct mlxsw_afk_element_usage *elusage,
+				      struct mlxsw_afk_element_usage *out)
 {
 	const struct mlxsw_sp_acl_tcam_pattern *pattern;
 	int i;
@@ -429,14 +588,14 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
 	/* In case the template is set, we don't have to look up the pattern
 	 * and just use the template.
 	 */
-	if (group->tmplt_elusage_set) {
-		memcpy(out, &group->tmplt_elusage, sizeof(*out));
+	if (vgroup->tmplt_elusage_set) {
+		memcpy(out, &vgroup->tmplt_elusage, sizeof(*out));
 		WARN_ON(!mlxsw_afk_element_usage_subset(elusage, out));
 		return;
 	}
 
-	for (i = 0; i < group->patterns_count; i++) {
-		pattern = &group->patterns[i];
+	for (i = 0; i < vgroup->patterns_count; i++) {
+		pattern = &vgroup->patterns[i];
 		mlxsw_afk_element_usage_fill(out, pattern->elements,
 					     pattern->elements_count);
 		if (mlxsw_afk_element_usage_subset(elusage, out))
@@ -510,24 +669,19 @@ mlxsw_sp_acl_tcam_region_disable(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_acl_tcam_region *
 mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam *tcam,
-				struct mlxsw_afk_element_usage *elusage)
+				struct mlxsw_sp_acl_tcam_vregion *vregion,
+				void *hints_priv)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_tcam_region *region;
 	int err;
 
 	region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL);
 	if (!region)
 		return ERR_PTR(-ENOMEM);
-	INIT_LIST_HEAD(&region->chunk_list);
 	region->mlxsw_sp = mlxsw_sp;
-
-	region->key_info = mlxsw_afk_key_info_get(afk, elusage);
-	if (IS_ERR(region->key_info)) {
-		err = PTR_ERR(region->key_info);
-		goto err_key_info_get;
-	}
+	region->vregion = vregion;
+	region->key_info = vregion->key_info;
 
 	err = mlxsw_sp_acl_tcam_region_id_get(tcam, &region->id);
 	if (err)
@@ -546,7 +700,8 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_tcam_region_enable;
 
-	err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region);
+	err = ops->region_init(mlxsw_sp, region->priv, tcam->priv,
+			       region, hints_priv);
 	if (err)
 		goto err_tcam_region_init;
 
@@ -560,8 +715,6 @@ err_tcam_region_alloc:
 err_tcam_region_associate:
 	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 err_region_id_get:
-	mlxsw_afk_key_info_put(region->key_info);
-err_key_info_get:
 	kfree(region);
 	return ERR_PTR(err);
 }
@@ -575,220 +728,793 @@ mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
-	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id);
-	mlxsw_afk_key_info_put(region->key_info);
+	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam,
+					region->id);
 	kfree(region);
 }
 
-static int
-mlxsw_sp_acl_tcam_chunk_assoc(struct mlxsw_sp *mlxsw_sp,
-			      struct mlxsw_sp_acl_tcam_group *group,
-			      unsigned int priority,
-			      struct mlxsw_afk_element_usage *elusage,
-			      struct mlxsw_sp_acl_tcam_chunk *chunk)
+static void
+mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(struct mlxsw_sp_acl_tcam_vregion *vregion)
 {
-	struct mlxsw_sp_acl_tcam_region *region;
-	bool region_created = false;
-	bool need_split;
-	int err;
+	unsigned long interval = vregion->tcam->vregion_rehash_intrvl;
+
+	if (!interval)
+		return;
+	mlxsw_core_schedule_dw(&vregion->rehash.dw,
+			       msecs_to_jiffies(interval));
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vregion *vregion,
+				 int *credits);
 
-	region = mlxsw_sp_acl_tcam_group_region_find(group, priority, elusage,
-						     &need_split);
-	if (region && need_split) {
-		/* According to priority, the chunk should belong to an
-		 * existing region. However, this chunk needs elements
-		 * that region does not contain. We need to split the existing
-		 * region into two and create a new region for this chunk
-		 * in between. This is not supported now.
+static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion =
+		container_of(work, struct mlxsw_sp_acl_tcam_vregion,
+			     rehash.dw.work);
+	int credits = MLXSW_SP_ACL_TCAM_VREGION_REHASH_CREDITS;
+
+	mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion, &credits);
+	if (credits < 0)
+		/* Rehash gone out of credits so it was interrupted.
+		 * Schedule the work as soon as possible to continue.
 		 */
-		return -EOPNOTSUPP;
-	}
-	if (!region) {
-		struct mlxsw_afk_element_usage region_elusage;
+		mlxsw_core_schedule_dw(&vregion->rehash.dw, 0);
+	else
+		mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion);
+}
 
-		mlxsw_sp_acl_tcam_group_use_patterns(group, elusage,
-						     &region_elusage);
-		region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, group->tcam,
-							 &region_elusage);
-		if (IS_ERR(region))
-			return PTR_ERR(region);
-		region_created = true;
+static void
+mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(struct mlxsw_sp_acl_tcam_vchunk *vchunk)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
+
+	/* If a rule was added or deleted from vchunk which is currently
+	 * under rehash migration, we have to reset the ventry pointers
+	 * to make sure all rules are properly migrated.
+	 */
+	if (vregion->rehash.ctx.current_vchunk == vchunk) {
+		vregion->rehash.ctx.start_ventry = NULL;
+		vregion->rehash.ctx.stop_ventry = NULL;
 	}
+}
 
-	chunk->region = region;
-	list_add_tail(&chunk->list, &region->chunk_list);
+static void
+mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(struct mlxsw_sp_acl_tcam_vregion *vregion)
+{
+	/* If a chunk was added or deleted from vregion we have to reset
+	 * the current chunk pointer to make sure all chunks
+	 * are properly migrated.
+	 */
+	vregion->rehash.ctx.current_vchunk = NULL;
+}
 
-	if (!region_created)
-		return 0;
+static struct mlxsw_sp_acl_tcam_vregion *
+mlxsw_sp_acl_tcam_vregion_create(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				 unsigned int priority,
+				 struct mlxsw_afk_element_usage *elusage)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	struct mlxsw_sp_acl_tcam *tcam = vgroup->group.tcam;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	int err;
+
+	vregion = kzalloc(sizeof(*vregion), GFP_KERNEL);
+	if (!vregion)
+		return ERR_PTR(-ENOMEM);
+	INIT_LIST_HEAD(&vregion->vchunk_list);
+	mutex_init(&vregion->lock);
+	vregion->tcam = tcam;
+	vregion->mlxsw_sp = mlxsw_sp;
+	vregion->vgroup = vgroup;
+	vregion->ref_count = 1;
+
+	vregion->key_info = mlxsw_afk_key_info_get(afk, elusage);
+	if (IS_ERR(vregion->key_info)) {
+		err = PTR_ERR(vregion->key_info);
+		goto err_key_info_get;
+	}
+
+	vregion->region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, tcam,
+							  vregion, NULL);
+	if (IS_ERR(vregion->region)) {
+		err = PTR_ERR(vregion->region);
+		goto err_region_create;
+	}
 
-	err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, group, region);
+	err = mlxsw_sp_acl_tcam_vgroup_vregion_attach(mlxsw_sp, vgroup, vregion,
+						      priority);
 	if (err)
-		goto err_group_region_attach;
+		goto err_vgroup_vregion_attach;
+
+	if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) {
+		/* Create the delayed work for vregion periodic rehash */
+		INIT_DELAYED_WORK(&vregion->rehash.dw,
+				  mlxsw_sp_acl_tcam_vregion_rehash_work);
+		mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion);
+		mutex_lock(&tcam->lock);
+		list_add_tail(&vregion->tlist, &tcam->vregion_list);
+		mutex_unlock(&tcam->lock);
+	}
 
-	return 0;
+	return vregion;
 
-err_group_region_attach:
-	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region);
-	return err;
+err_vgroup_vregion_attach:
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region);
+err_region_create:
+	mlxsw_afk_key_info_put(vregion->key_info);
+err_key_info_get:
+	kfree(vregion);
+	return ERR_PTR(err);
 }
 
 static void
-mlxsw_sp_acl_tcam_chunk_deassoc(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_acl_tcam_chunk *chunk)
+mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_tcam_vregion *vregion)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup = vregion->vgroup;
+	struct mlxsw_sp_acl_tcam *tcam = vregion->tcam;
+
+	if (vgroup->vregion_rehash_enabled && ops->region_rehash_hints_get) {
+		mutex_lock(&tcam->lock);
+		list_del(&vregion->tlist);
+		mutex_unlock(&tcam->lock);
+		cancel_delayed_work_sync(&vregion->rehash.dw);
+	}
+	mlxsw_sp_acl_tcam_vgroup_vregion_detach(mlxsw_sp, vregion);
+	if (vregion->region2)
+		mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region2);
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region);
+	mlxsw_afk_key_info_put(vregion->key_info);
+	mutex_destroy(&vregion->lock);
+	kfree(vregion);
+}
+
+u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	u32 vregion_rehash_intrvl;
+
+	if (WARN_ON(!ops->region_rehash_hints_get))
+		return 0;
+	vregion_rehash_intrvl = tcam->vregion_rehash_intrvl;
+	return vregion_rehash_intrvl;
+}
+
+int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam,
+						u32 val)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+
+	if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val)
+		return -EINVAL;
+	if (WARN_ON(!ops->region_rehash_hints_get))
+		return -EOPNOTSUPP;
+	tcam->vregion_rehash_intrvl = val;
+	mutex_lock(&tcam->lock);
+	list_for_each_entry(vregion, &tcam->vregion_list, tlist) {
+		if (val)
+			mlxsw_core_schedule_dw(&vregion->rehash.dw, 0);
+		else
+			cancel_delayed_work_sync(&vregion->rehash.dw);
+	}
+	mutex_unlock(&tcam->lock);
+	return 0;
+}
+
+static struct mlxsw_sp_acl_tcam_vregion *
+mlxsw_sp_acl_tcam_vregion_get(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+			      unsigned int priority,
+			      struct mlxsw_afk_element_usage *elusage)
 {
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+	struct mlxsw_afk_element_usage vregion_elusage;
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	bool need_split;
 
-	list_del(&chunk->list);
-	if (list_empty(&region->chunk_list)) {
-		mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, region);
-		mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region);
+	vregion = mlxsw_sp_acl_tcam_vgroup_vregion_find(vgroup, priority,
+							elusage, &need_split);
+	if (vregion) {
+		if (need_split) {
+			/* According to priority, new vchunk should belong to
+			 * an existing vregion. However, this vchunk needs
+			 * elements that vregion does not contain. We need
+			 * to split the existing vregion into two and create
+			 * a new vregion for the new vchunk in between.
+			 * This is not supported now.
+			 */
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+		vregion->ref_count++;
+		return vregion;
 	}
+
+	mlxsw_sp_acl_tcam_vgroup_use_patterns(vgroup, elusage,
+					      &vregion_elusage);
+
+	return mlxsw_sp_acl_tcam_vregion_create(mlxsw_sp, vgroup, priority,
+						&vregion_elusage);
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_put(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp_acl_tcam_vregion *vregion)
+{
+	if (--vregion->ref_count)
+		return;
+	mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion);
 }
 
 static struct mlxsw_sp_acl_tcam_chunk *
 mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
-			       struct mlxsw_sp_acl_tcam_group *group,
-			       unsigned int priority,
-			       struct mlxsw_afk_element_usage *elusage)
+			       struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+			       struct mlxsw_sp_acl_tcam_region *region)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
+
+	chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
+	if (!chunk)
+		return ERR_PTR(-ENOMEM);
+	chunk->vchunk = vchunk;
+	chunk->region = region;
+
+	ops->chunk_init(region->priv, chunk->priv, vchunk->priority);
+	return chunk;
+}
+
+static void
+mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_tcam_chunk *chunk)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	ops->chunk_fini(chunk->priv);
+	kfree(chunk);
+}
+
+static struct mlxsw_sp_acl_tcam_vchunk *
+mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+				unsigned int priority,
+				struct mlxsw_afk_element_usage *elusage)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
 		return ERR_PTR(-EINVAL);
 
-	chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
-	if (!chunk)
+	vchunk = kzalloc(sizeof(*vchunk), GFP_KERNEL);
+	if (!vchunk)
 		return ERR_PTR(-ENOMEM);
-	chunk->priority = priority;
-	chunk->group = group;
-	chunk->ref_count = 1;
-
-	err = mlxsw_sp_acl_tcam_chunk_assoc(mlxsw_sp, group, priority,
-					    elusage, chunk);
-	if (err)
-		goto err_chunk_assoc;
+	INIT_LIST_HEAD(&vchunk->ventry_list);
+	vchunk->priority = priority;
+	vchunk->vgroup = vgroup;
+	vchunk->ref_count = 1;
+
+	vregion = mlxsw_sp_acl_tcam_vregion_get(mlxsw_sp, vgroup,
+						priority, elusage);
+	if (IS_ERR(vregion)) {
+		err = PTR_ERR(vregion);
+		goto err_vregion_get;
+	}
 
-	ops->chunk_init(chunk->region->priv, chunk->priv, priority);
+	vchunk->vregion = vregion;
 
-	err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node,
-				     mlxsw_sp_acl_tcam_chunk_ht_params);
+	err = rhashtable_insert_fast(&vgroup->vchunk_ht, &vchunk->ht_node,
+				     mlxsw_sp_acl_tcam_vchunk_ht_params);
 	if (err)
 		goto err_rhashtable_insert;
 
-	return chunk;
+	mutex_lock(&vregion->lock);
+	vchunk->chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk,
+						       vchunk->vregion->region);
+	if (IS_ERR(vchunk->chunk)) {
+		mutex_unlock(&vregion->lock);
+		err = PTR_ERR(vchunk->chunk);
+		goto err_chunk_create;
+	}
+
+	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
+	list_add_tail(&vchunk->list, &vregion->vchunk_list);
+	mutex_unlock(&vregion->lock);
 
+	return vchunk;
+
+err_chunk_create:
+	rhashtable_remove_fast(&vgroup->vchunk_ht, &vchunk->ht_node,
+			       mlxsw_sp_acl_tcam_vchunk_ht_params);
 err_rhashtable_insert:
-	ops->chunk_fini(chunk->priv);
-	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
-err_chunk_assoc:
-	kfree(chunk);
+	mlxsw_sp_acl_tcam_vregion_put(mlxsw_sp, vregion);
+err_vregion_get:
+	kfree(vchunk);
 	return ERR_PTR(err);
 }
 
 static void
-mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_acl_tcam_chunk *chunk)
+mlxsw_sp_acl_tcam_vchunk_destroy(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vchunk *vchunk)
 {
-	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_group *group = chunk->group;
-
-	rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node,
-			       mlxsw_sp_acl_tcam_chunk_ht_params);
-	ops->chunk_fini(chunk->priv);
-	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
-	kfree(chunk);
+	struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
+	struct mlxsw_sp_acl_tcam_vgroup *vgroup = vchunk->vgroup;
+
+	mutex_lock(&vregion->lock);
+	mlxsw_sp_acl_tcam_rehash_ctx_vregion_changed(vregion);
+	list_del(&vchunk->list);
+	if (vchunk->chunk2)
+		mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2);
+	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk);
+	mutex_unlock(&vregion->lock);
+	rhashtable_remove_fast(&vgroup->vchunk_ht, &vchunk->ht_node,
+			       mlxsw_sp_acl_tcam_vchunk_ht_params);
+	mlxsw_sp_acl_tcam_vregion_put(mlxsw_sp, vchunk->vregion);
+	kfree(vchunk);
 }
 
-static struct mlxsw_sp_acl_tcam_chunk *
-mlxsw_sp_acl_tcam_chunk_get(struct mlxsw_sp *mlxsw_sp,
-			    struct mlxsw_sp_acl_tcam_group *group,
-			    unsigned int priority,
-			    struct mlxsw_afk_element_usage *elusage)
+static struct mlxsw_sp_acl_tcam_vchunk *
+mlxsw_sp_acl_tcam_vchunk_get(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+			     unsigned int priority,
+			     struct mlxsw_afk_element_usage *elusage)
 {
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 
-	chunk = rhashtable_lookup_fast(&group->chunk_ht, &priority,
-				       mlxsw_sp_acl_tcam_chunk_ht_params);
-	if (chunk) {
-		if (WARN_ON(!mlxsw_afk_key_info_subset(chunk->region->key_info,
+	vchunk = rhashtable_lookup_fast(&vgroup->vchunk_ht, &priority,
+					mlxsw_sp_acl_tcam_vchunk_ht_params);
+	if (vchunk) {
+		if (WARN_ON(!mlxsw_afk_key_info_subset(vchunk->vregion->key_info,
 						       elusage)))
 			return ERR_PTR(-EINVAL);
-		chunk->ref_count++;
-		return chunk;
+		vchunk->ref_count++;
+		return vchunk;
 	}
-	return mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, group,
-					      priority, elusage);
+	return mlxsw_sp_acl_tcam_vchunk_create(mlxsw_sp, vgroup,
+					       priority, elusage);
 }
 
-static void mlxsw_sp_acl_tcam_chunk_put(struct mlxsw_sp *mlxsw_sp,
-					struct mlxsw_sp_acl_tcam_chunk *chunk)
+static void
+mlxsw_sp_acl_tcam_vchunk_put(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_tcam_vchunk *vchunk)
 {
-	if (--chunk->ref_count)
+	if (--vchunk->ref_count)
 		return;
-	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk);
+	mlxsw_sp_acl_tcam_vchunk_destroy(mlxsw_sp, vchunk);
+}
+
+static struct mlxsw_sp_acl_tcam_entry *
+mlxsw_sp_acl_tcam_entry_create(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_tcam_ventry *ventry,
+			       struct mlxsw_sp_acl_tcam_chunk *chunk)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+	struct mlxsw_sp_acl_tcam_entry *entry;
+	int err;
+
+	entry = kzalloc(sizeof(*entry) + ops->entry_priv_size, GFP_KERNEL);
+	if (!entry)
+		return ERR_PTR(-ENOMEM);
+	entry->ventry = ventry;
+	entry->chunk = chunk;
+
+	err = ops->entry_add(mlxsw_sp, chunk->region->priv, chunk->priv,
+			     entry->priv, ventry->rulei);
+	if (err)
+		goto err_entry_add;
+
+	return entry;
+
+err_entry_add:
+	kfree(entry);
+	return ERR_PTR(err);
 }
 
-static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp)
+static void mlxsw_sp_acl_tcam_entry_destroy(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_tcam_entry *entry)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
-	return ops->entry_priv_size;
+	ops->entry_del(mlxsw_sp, entry->chunk->region->priv,
+		       entry->chunk->priv, entry->priv);
+	kfree(entry);
 }
 
-static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_acl_tcam_group *group,
+static int
+mlxsw_sp_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_region *region,
 				       struct mlxsw_sp_acl_tcam_entry *entry,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk;
-	struct mlxsw_sp_acl_tcam_region *region;
+
+	return ops->entry_action_replace(mlxsw_sp, region->priv,
+					 entry->priv, rulei);
+}
+
+static int
+mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_entry *entry,
+				     bool *activity)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	return ops->entry_activity_get(mlxsw_sp, entry->chunk->region->priv,
+				       entry->priv, activity);
+}
+
+static int mlxsw_sp_acl_tcam_ventry_add(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_vgroup *vgroup,
+					struct mlxsw_sp_acl_tcam_ventry *ventry,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
 	int err;
 
-	chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, group, rulei->priority,
-					    &rulei->values.elusage);
-	if (IS_ERR(chunk))
-		return PTR_ERR(chunk);
+	vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp, vgroup, rulei->priority,
+					      &rulei->values.elusage);
+	if (IS_ERR(vchunk))
+		return PTR_ERR(vchunk);
+
+	ventry->vchunk = vchunk;
+	ventry->rulei = rulei;
+	vregion = vchunk->vregion;
+
+	mutex_lock(&vregion->lock);
+	ventry->entry = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry,
+						       vchunk->chunk);
+	if (IS_ERR(ventry->entry)) {
+		mutex_unlock(&vregion->lock);
+		err = PTR_ERR(ventry->entry);
+		goto err_entry_create;
+	}
 
-	region = chunk->region;
+	list_add_tail(&ventry->list, &vchunk->ventry_list);
+	mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(vchunk);
+	mutex_unlock(&vregion->lock);
 
-	err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv,
-			     entry->priv, rulei);
-	if (err)
-		goto err_entry_add;
-	entry->chunk = chunk;
+	return 0;
+
+err_entry_create:
+	mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk);
+	return err;
+}
+
+static void mlxsw_sp_acl_tcam_ventry_del(struct mlxsw_sp *mlxsw_sp,
+					 struct mlxsw_sp_acl_tcam_ventry *ventry)
+{
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk;
+	struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion;
+
+	mutex_lock(&vregion->lock);
+	mlxsw_sp_acl_tcam_rehash_ctx_vchunk_changed(vchunk);
+	list_del(&ventry->list);
+	mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry);
+	mutex_unlock(&vregion->lock);
+	mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk);
+}
+
+static int
+mlxsw_sp_acl_tcam_ventry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_tcam_ventry *ventry,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk;
+
+	return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp,
+						      vchunk->vregion->region,
+						      ventry->entry, rulei);
+}
+
+static int
+mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				      struct mlxsw_sp_acl_tcam_ventry *ventry,
+				      bool *activity)
+{
+	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp,
+						    ventry->entry, activity);
+}
+
+static int
+mlxsw_sp_acl_tcam_ventry_migrate(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_ventry *ventry,
+				 struct mlxsw_sp_acl_tcam_chunk *chunk,
+				 int *credits)
+{
+	struct mlxsw_sp_acl_tcam_entry *new_entry;
+
+	/* First check if the entry is not already where we want it to be. */
+	if (ventry->entry->chunk == chunk)
+		return 0;
+
+	if (--(*credits) < 0)
+		return 0;
 
+	new_entry = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry, chunk);
+	if (IS_ERR(new_entry))
+		return PTR_ERR(new_entry);
+	mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry);
+	ventry->entry = new_entry;
 	return 0;
+}
 
-err_entry_add:
-	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
+static int
+mlxsw_sp_acl_tcam_vchunk_migrate_start(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+				       struct mlxsw_sp_acl_tcam_region *region,
+				       struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	struct mlxsw_sp_acl_tcam_chunk *new_chunk;
+
+	new_chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region);
+	if (IS_ERR(new_chunk)) {
+		if (ctx->this_is_rollback)
+			vchunk->vregion->failed_rollback = true;
+		return PTR_ERR(new_chunk);
+	}
+	vchunk->chunk2 = vchunk->chunk;
+	vchunk->chunk = new_chunk;
+	ctx->current_vchunk = vchunk;
+	ctx->start_ventry = NULL;
+	ctx->stop_ventry = NULL;
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_tcam_vchunk_migrate_end(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2);
+	vchunk->chunk2 = NULL;
+	ctx->current_vchunk = NULL;
+}
+
+static int
+mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vchunk *vchunk,
+				     struct mlxsw_sp_acl_tcam_region *region,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx,
+				     int *credits)
+{
+	struct mlxsw_sp_acl_tcam_ventry *ventry;
+	int err;
+
+	if (vchunk->chunk->region != region) {
+		err = mlxsw_sp_acl_tcam_vchunk_migrate_start(mlxsw_sp, vchunk,
+							     region, ctx);
+		if (err)
+			return err;
+	} else if (!vchunk->chunk2) {
+		/* The chunk is already as it should be, nothing to do. */
+		return 0;
+	}
+
+	/* If the migration got interrupted, we have the ventry to start from
+	 * stored in context.
+	 */
+	if (ctx->start_ventry)
+		ventry = ctx->start_ventry;
+	else
+		ventry = list_first_entry(&vchunk->ventry_list,
+					  typeof(*ventry), list);
+
+	list_for_each_entry_from(ventry, &vchunk->ventry_list, list) {
+		/* During rollback, once we reach the ventry that failed
+		 * to migrate, we are done.
+		 */
+		if (ventry == ctx->stop_ventry)
+			break;
+
+		err = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry,
+						       vchunk->chunk, credits);
+		if (err) {
+			if (ctx->this_is_rollback)
+				return err;
+			/* Swap the chunk and chunk2 pointers so the follow-up
+			 * rollback call will see the original chunk pointer
+			 * in vchunk->chunk.
+			 */
+			swap(vchunk->chunk, vchunk->chunk2);
+			/* The rollback has to be done from beginning of the
+			 * chunk, that is why we have to null the start_ventry.
+			 * However, we know where to stop the rollback,
+			 * at the current ventry.
+			 */
+			ctx->start_ventry = NULL;
+			ctx->stop_ventry = ventry;
+			return err;
+		} else if (*credits < 0) {
+			/* We are out of credits, the rest of the ventries
+			 * will be migrated later. Save the ventry
+			 * which we ended with.
+			 */
+			ctx->start_ventry = ventry;
+			return 0;
+		}
+	}
+
+	mlxsw_sp_acl_tcam_vchunk_migrate_end(mlxsw_sp, vchunk, ctx);
+	return 0;
+}
+
+static int
+mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vregion *vregion,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx,
+				     int *credits)
+{
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	int err;
+
+	/* If the migration got interrupted, we have the vchunk
+	 * we are working on stored in context.
+	 */
+	if (ctx->current_vchunk)
+		vchunk = ctx->current_vchunk;
+	else
+		vchunk = list_first_entry(&vregion->vchunk_list,
+					  typeof(*vchunk), list);
+
+	list_for_each_entry_from(vchunk, &vregion->vchunk_list, list) {
+		err = mlxsw_sp_acl_tcam_vchunk_migrate_one(mlxsw_sp, vchunk,
+							   vregion->region,
+							   ctx, credits);
+		if (err || *credits < 0)
+			return err;
+	}
+	return 0;
+}
+
+static int
+mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_tcam_vregion *vregion,
+				  struct mlxsw_sp_acl_tcam_rehash_ctx *ctx,
+				  int *credits)
+{
+	int err, err2;
+
+	trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion);
+	mutex_lock(&vregion->lock);
+	err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
+						   ctx, credits);
+	if (err) {
+		/* In case migration was not successful, we need to swap
+		 * so the original region pointer is assigned again
+		 * to vregion->region.
+		 */
+		swap(vregion->region, vregion->region2);
+		ctx->current_vchunk = NULL;
+		ctx->this_is_rollback = true;
+		err2 = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion,
+							    ctx, credits);
+		if (err2)
+			vregion->failed_rollback = true;
+	}
+	mutex_unlock(&vregion->lock);
+	trace_mlxsw_sp_acl_tcam_vregion_migrate_end(mlxsw_sp, vregion);
 	return err;
 }
 
-static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
-					struct mlxsw_sp_acl_tcam_entry *entry)
+static bool
+mlxsw_sp_acl_tcam_vregion_rehash_in_progress(const struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
+{
+	return ctx->hints_priv;
+}
+
+static int
+mlxsw_sp_acl_tcam_vregion_rehash_start(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_vregion *vregion,
+				       struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
 {
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
+	unsigned int priority = mlxsw_sp_acl_tcam_vregion_prio(vregion);
+	struct mlxsw_sp_acl_tcam_region *new_region;
+	void *hints_priv;
+	int err;
+
+	trace_mlxsw_sp_acl_tcam_vregion_rehash(mlxsw_sp, vregion);
+	if (vregion->failed_rollback)
+		return -EBUSY;
+
+	hints_priv = ops->region_rehash_hints_get(vregion->region->priv);
+	if (IS_ERR(hints_priv))
+		return PTR_ERR(hints_priv);
+
+	new_region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, vregion->tcam,
+						     vregion, hints_priv);
+	if (IS_ERR(new_region)) {
+		err = PTR_ERR(new_region);
+		goto err_region_create;
+	}
+
+	/* vregion->region contains the pointer to the new region
+	 * we are going to migrate to.
+	 */
+	vregion->region2 = vregion->region;
+	vregion->region = new_region;
+	err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp,
+						    vregion->region2->group,
+						    new_region, priority,
+						    vregion->region2);
+	if (err)
+		goto err_group_region_attach;
+
+	ctx->hints_priv = hints_priv;
+	ctx->this_is_rollback = false;
+
+	return 0;
 
-	ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv);
-	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
+err_group_region_attach:
+	vregion->region = vregion->region2;
+	vregion->region2 = NULL;
+	mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, new_region);
+err_region_create:
+	ops->region_rehash_hints_put(hints_priv);
+	return err;
 }
 
-static int
-mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
-				     struct mlxsw_sp_acl_tcam_entry *entry,
-				     bool *activity)
+static void
+mlxsw_sp_acl_tcam_vregion_rehash_end(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp_acl_tcam_vregion *vregion,
+				     struct mlxsw_sp_acl_tcam_rehash_ctx *ctx)
 {
+	struct mlxsw_sp_acl_tcam_region *unused_region = vregion->region2;
 	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
-	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
-	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	return ops->entry_activity_get(mlxsw_sp, region->priv,
-				       entry->priv, activity);
+	if (!vregion->failed_rollback) {
+		vregion->region2 = NULL;
+		mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, unused_region);
+		mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, unused_region);
+	}
+	ops->region_rehash_hints_put(ctx->hints_priv);
+	ctx->hints_priv = NULL;
+}
+
+static void
+mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_vregion *vregion,
+				 int *credits)
+{
+	struct mlxsw_sp_acl_tcam_rehash_ctx *ctx = &vregion->rehash.ctx;
+	int err;
+
+	/* Check if the previous rehash work was interrupted
+	 * which means we have to continue it now.
+	 * If not, start a new rehash.
+	 */
+	if (!mlxsw_sp_acl_tcam_vregion_rehash_in_progress(ctx)) {
+		err = mlxsw_sp_acl_tcam_vregion_rehash_start(mlxsw_sp,
+							     vregion, ctx);
+		if (err) {
+			if (err != -EAGAIN)
+				dev_err(mlxsw_sp->bus_info->dev, "Failed get rehash hints\n");
+			return;
+		}
+	}
+
+	err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion,
+						ctx, credits);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n");
+		if (vregion->failed_rollback) {
+			trace_mlxsw_sp_acl_tcam_vregion_rehash_dis(mlxsw_sp,
+								   vregion);
+			dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n");
+		}
+	}
+
+	if (*credits >= 0)
+		mlxsw_sp_acl_tcam_vregion_rehash_end(mlxsw_sp, vregion, ctx);
 }
 
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
@@ -841,11 +1567,11 @@ static const struct mlxsw_sp_acl_tcam_pattern mlxsw_sp_acl_tcam_patterns[] = {
 	ARRAY_SIZE(mlxsw_sp_acl_tcam_patterns)
 
 struct mlxsw_sp_acl_tcam_flower_ruleset {
-	struct mlxsw_sp_acl_tcam_group group;
+	struct mlxsw_sp_acl_tcam_vgroup vgroup;
 };
 
 struct mlxsw_sp_acl_tcam_flower_rule {
-	struct mlxsw_sp_acl_tcam_entry entry;
+	struct mlxsw_sp_acl_tcam_ventry ventry;
 };
 
 static int
@@ -856,10 +1582,10 @@ mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
-					   mlxsw_sp_acl_tcam_patterns,
-					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
-					   tmplt_elusage);
+	return mlxsw_sp_acl_tcam_vgroup_add(mlxsw_sp, tcam, &ruleset->vgroup,
+					    mlxsw_sp_acl_tcam_patterns,
+					    MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					    tmplt_elusage, true);
 }
 
 static void
@@ -868,7 +1594,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_del(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group);
+	mlxsw_sp_acl_tcam_vgroup_del(&ruleset->vgroup);
 }
 
 static int
@@ -879,7 +1605,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_bind(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_bind(mlxsw_sp, &ruleset->group,
+	return mlxsw_sp_acl_tcam_group_bind(mlxsw_sp, &ruleset->vgroup.group,
 					    mlxsw_sp_port, ingress);
 }
 
@@ -891,7 +1617,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	mlxsw_sp_acl_tcam_group_unbind(mlxsw_sp, &ruleset->group,
+	mlxsw_sp_acl_tcam_group_unbind(mlxsw_sp, &ruleset->vgroup.group,
 				       mlxsw_sp_port, ingress);
 }
 
@@ -900,13 +1626,7 @@ mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv)
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
-	return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
-}
-
-static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
-{
-	return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) +
-	       mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+	return mlxsw_sp_acl_tcam_group_id(&ruleset->vgroup.group);
 }
 
 static int
@@ -917,8 +1637,8 @@ mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group,
-					   &rule->entry, rulei);
+	return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->vgroup,
+					    &rule->ventry, rulei);
 }
 
 static void
@@ -926,7 +1646,15 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
 {
 	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
 
-	mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry);
+	mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry);
+}
+
+static int
+mlxsw_sp_acl_tcam_flower_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+					     void *rule_priv,
+					     struct mlxsw_sp_acl_rule_info *rulei)
+{
+	return -EOPNOTSUPP;
 }
 
 static int
@@ -935,8 +1663,8 @@ mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv;
 
-	return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry,
-						    activity);
+	return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry,
+						     activity);
 }
 
 static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
@@ -946,15 +1674,152 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.ruleset_bind		= mlxsw_sp_acl_tcam_flower_ruleset_bind,
 	.ruleset_unbind		= mlxsw_sp_acl_tcam_flower_ruleset_unbind,
 	.ruleset_group_id	= mlxsw_sp_acl_tcam_flower_ruleset_group_id,
-	.rule_priv_size		= mlxsw_sp_acl_tcam_flower_rule_priv_size,
+	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
+	.rule_action_replace	= mlxsw_sp_acl_tcam_flower_rule_action_replace,
 	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
 };
 
+struct mlxsw_sp_acl_tcam_mr_ruleset {
+	struct mlxsw_sp_acl_tcam_vchunk *vchunk;
+	struct mlxsw_sp_acl_tcam_vgroup vgroup;
+};
+
+struct mlxsw_sp_acl_tcam_mr_rule {
+	struct mlxsw_sp_acl_tcam_ventry ventry;
+};
+
+static int
+mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam *tcam,
+				 void *ruleset_priv,
+				 struct mlxsw_afk_element_usage *tmplt_elusage)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_vgroup_add(mlxsw_sp, tcam, &ruleset->vgroup,
+					   mlxsw_sp_acl_tcam_patterns,
+					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					   tmplt_elusage, false);
+	if (err)
+		return err;
+
+	/* For most of the TCAM clients it would make sense to take a tcam chunk
+	 * only when the first rule is written. This is not the case for
+	 * multicast router as it is required to bind the multicast router to a
+	 * specific ACL Group ID which must exist in HW before multicast router
+	 * is initialized.
+	 */
+	ruleset->vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp,
+						       &ruleset->vgroup, 1,
+						       tmplt_elusage);
+	if (IS_ERR(ruleset->vchunk)) {
+		err = PTR_ERR(ruleset->vchunk);
+		goto err_chunk_get;
+	}
+
+	return 0;
+
+err_chunk_get:
+	mlxsw_sp_acl_tcam_vgroup_del(&ruleset->vgroup);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_tcam_mr_ruleset_del(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+
+	mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, ruleset->vchunk);
+	mlxsw_sp_acl_tcam_vgroup_del(&ruleset->vgroup);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_ruleset_bind(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+				  struct mlxsw_sp_port *mlxsw_sp_port,
+				  bool ingress)
+{
+	/* Binding is done when initializing multicast router */
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_tcam_mr_ruleset_unbind(struct mlxsw_sp *mlxsw_sp,
+				    void *ruleset_priv,
+				    struct mlxsw_sp_port *mlxsw_sp_port,
+				    bool ingress)
+{
+}
+
+static u16
+mlxsw_sp_acl_tcam_mr_ruleset_group_id(void *ruleset_priv)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+
+	return mlxsw_sp_acl_tcam_group_id(&ruleset->vgroup.group);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+			      void *rule_priv,
+			      struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv;
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->vgroup,
+					   &rule->ventry, rulei);
+}
+
+static void
+mlxsw_sp_acl_tcam_mr_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv)
+{
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_rule_action_replace(struct mlxsw_sp *mlxsw_sp,
+					 void *rule_priv,
+					 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_ventry_action_replace(mlxsw_sp, &rule->ventry,
+						       rulei);
+}
+
+static int
+mlxsw_sp_acl_tcam_mr_rule_activity_get(struct mlxsw_sp *mlxsw_sp,
+				       void *rule_priv, bool *activity)
+{
+	struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv;
+
+	return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry,
+						     activity);
+}
+
+static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = {
+	.ruleset_priv_size	= sizeof(struct mlxsw_sp_acl_tcam_mr_ruleset),
+	.ruleset_add		= mlxsw_sp_acl_tcam_mr_ruleset_add,
+	.ruleset_del		= mlxsw_sp_acl_tcam_mr_ruleset_del,
+	.ruleset_bind		= mlxsw_sp_acl_tcam_mr_ruleset_bind,
+	.ruleset_unbind		= mlxsw_sp_acl_tcam_mr_ruleset_unbind,
+	.ruleset_group_id	= mlxsw_sp_acl_tcam_mr_ruleset_group_id,
+	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_mr_rule),
+	.rule_add		= mlxsw_sp_acl_tcam_mr_rule_add,
+	.rule_del		= mlxsw_sp_acl_tcam_mr_rule_del,
+	.rule_action_replace	= mlxsw_sp_acl_tcam_mr_rule_action_replace,
+	.rule_activity_get	= mlxsw_sp_acl_tcam_mr_rule_activity_get,
+};
+
 static const struct mlxsw_sp_acl_profile_ops *
 mlxsw_sp_acl_tcam_profile_ops_arr[] = {
 	[MLXSW_SP_ACL_PROFILE_FLOWER] = &mlxsw_sp_acl_tcam_flower_ops,
+	[MLXSW_SP_ACL_PROFILE_MR] = &mlxsw_sp_acl_tcam_mr_ops,
 };
 
 const struct mlxsw_sp_acl_profile_ops *
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 219a4e26c332..5965913565a5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -17,6 +17,9 @@ struct mlxsw_sp_acl_tcam {
 	unsigned long *used_groups;  /* bit array */
 	unsigned int max_groups;
 	unsigned int max_group_size;
+	struct mutex lock; /* guards vregion list */
+	struct list_head vregion_list;
+	u32 vregion_rehash_intrvl;   /* ms */
 	unsigned long priv[0];
 	/* priv has to be always the last item */
 };
@@ -26,6 +29,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_tcam *tcam);
 void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_tcam *tcam);
+u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam);
+int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp,
+						struct mlxsw_sp_acl_tcam *tcam,
+						u32 val);
 int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
 				   u32 *priority, bool fillup_priority);
@@ -43,11 +51,13 @@ struct mlxsw_sp_acl_profile_ops {
 			       struct mlxsw_sp_port *mlxsw_sp_port,
 			       bool ingress);
 	u16 (*ruleset_group_id)(void *ruleset_priv);
-	size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
+	size_t rule_priv_size;
 	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
 			void *ruleset_priv, void *rule_priv,
 			struct mlxsw_sp_acl_rule_info *rulei);
 	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+	int (*rule_action_replace)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+				   struct mlxsw_sp_acl_rule_info *rulei);
 	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
 				 bool *activity);
 };
@@ -65,11 +75,12 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 	(MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE)
 
 struct mlxsw_sp_acl_tcam_group;
+struct mlxsw_sp_acl_tcam_vregion;
 
 struct mlxsw_sp_acl_tcam_region {
-	struct list_head list; /* Member of a TCAM group */
-	struct list_head chunk_list; /* List of chunks under this region */
+	struct mlxsw_sp_acl_tcam_vregion *vregion;
 	struct mlxsw_sp_acl_tcam_group *group;
+	struct list_head list; /* Member of a TCAM group */
 	enum mlxsw_reg_ptar_key_type key_type;
 	u16 id; /* ACL ID and region ID - they are same */
 	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
@@ -121,6 +132,10 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_ctcam_region *cregion,
 				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 				  struct mlxsw_sp_acl_ctcam_entry *centry);
+int mlxsw_sp_acl_ctcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_ctcam_region *cregion,
+					    struct mlxsw_sp_acl_ctcam_entry *centry,
+					    struct mlxsw_sp_acl_rule_info *rulei);
 static inline unsigned int
 mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
 {
@@ -144,6 +159,7 @@ struct mlxsw_sp_acl_atcam {
 
 struct mlxsw_sp_acl_atcam_region {
 	struct rhashtable entries_ht; /* A-TCAM only */
+	struct list_head entries_list; /* A-TCAM only */
 	struct mlxsw_sp_acl_ctcam_region cregion;
 	const struct mlxsw_sp_acl_atcam_region_ops *ops;
 	struct mlxsw_sp_acl_tcam_region *region;
@@ -154,7 +170,9 @@ struct mlxsw_sp_acl_atcam_region {
 };
 
 struct mlxsw_sp_acl_atcam_entry_ht_key {
-	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
+	char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded
+								 * key.
+								 */
 	u8 erp_id;
 };
 
@@ -164,10 +182,19 @@ struct mlxsw_sp_acl_atcam_chunk {
 
 struct mlxsw_sp_acl_atcam_entry {
 	struct rhash_head ht_node;
+	struct list_head list; /* Member in entries_list */
 	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
+							    * minus delta bits.
+							    */
+	struct {
+		u16 start;
+		u8 mask;
+		u8 value;
+	} delta_info;
 	struct mlxsw_sp_acl_ctcam_entry centry;
 	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
-	struct mlxsw_sp_acl_erp *erp;
+	struct mlxsw_sp_acl_erp_mask *erp_mask;
 };
 
 static inline struct mlxsw_sp_acl_atcam_region *
@@ -189,6 +216,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_atcam *atcam,
 			       struct mlxsw_sp_acl_atcam_region *aregion,
 			       struct mlxsw_sp_acl_tcam_region *region,
+			       void *hints_priv,
 			       const struct mlxsw_sp_acl_ctcam_region_ops *ops);
 void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
@@ -204,25 +232,74 @@ void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_atcam_region *aregion,
 				  struct mlxsw_sp_acl_atcam_chunk *achunk,
 				  struct mlxsw_sp_acl_atcam_entry *aentry);
+int mlxsw_sp_acl_atcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+					    struct mlxsw_sp_acl_atcam_region *aregion,
+					    struct mlxsw_sp_acl_atcam_entry *aentry,
+					    struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_atcam *atcam);
+void *
+mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv);
+
+struct mlxsw_sp_acl_erp_delta;
+
+u16 mlxsw_sp_acl_erp_delta_start(const struct mlxsw_sp_acl_erp_delta *delta);
+u8 mlxsw_sp_acl_erp_delta_mask(const struct mlxsw_sp_acl_erp_delta *delta);
+u8 mlxsw_sp_acl_erp_delta_value(const struct mlxsw_sp_acl_erp_delta *delta,
+				const char *enc_key);
+void mlxsw_sp_acl_erp_delta_clear(const struct mlxsw_sp_acl_erp_delta *delta,
+				  const char *enc_key);
 
-struct mlxsw_sp_acl_erp;
+struct mlxsw_sp_acl_erp_mask;
 
-bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp);
-u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp);
-struct mlxsw_sp_acl_erp *
-mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-		     const char *mask, bool ctcam);
-void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
-			  struct mlxsw_sp_acl_erp *erp);
-int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
+bool
+mlxsw_sp_acl_erp_mask_is_ctcam(const struct mlxsw_sp_acl_erp_mask *erp_mask);
+u8 mlxsw_sp_acl_erp_mask_erp_id(const struct mlxsw_sp_acl_erp_mask *erp_mask);
+const struct mlxsw_sp_acl_erp_delta *
+mlxsw_sp_acl_erp_delta(const struct mlxsw_sp_acl_erp_mask *erp_mask);
+struct mlxsw_sp_acl_erp_mask *
+mlxsw_sp_acl_erp_mask_get(struct mlxsw_sp_acl_atcam_region *aregion,
+			  const char *mask, bool ctcam);
+void mlxsw_sp_acl_erp_mask_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask);
+int mlxsw_sp_acl_erp_bf_insert(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_erp_mask *erp_mask,
+			       struct mlxsw_sp_acl_atcam_entry *aentry);
+void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_atcam_region *aregion,
+				struct mlxsw_sp_acl_erp_mask *erp_mask,
+				struct mlxsw_sp_acl_atcam_entry *aentry);
+void *
+mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv);
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				 void *hints_priv);
 void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_atcam *atcam);
 void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 
+struct mlxsw_sp_acl_bf;
+
+int
+mlxsw_sp_acl_bf_entry_add(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry);
+void
+mlxsw_sp_acl_bf_entry_del(struct mlxsw_sp *mlxsw_sp,
+			  struct mlxsw_sp_acl_bf *bf,
+			  struct mlxsw_sp_acl_atcam_region *aregion,
+			  unsigned int erp_bank,
+			  struct mlxsw_sp_acl_atcam_entry *aentry);
+struct mlxsw_sp_acl_bf *
+mlxsw_sp_acl_bf_init(struct mlxsw_sp *mlxsw_sp, unsigned int num_erp_banks);
+void mlxsw_sp_acl_bf_fini(struct mlxsw_sp_acl_bf *bf);
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 12c61e0cc570..d633bef5f105 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -37,13 +37,19 @@ struct mlxsw_sp_sb_pm {
 	struct mlxsw_cp_sb_occ occ;
 };
 
+struct mlxsw_sp_sb_mm {
+	u32 min_buff;
+	u32 max_buff;
+	u16 pool_index;
+};
+
 struct mlxsw_sp_sb_pool_des {
 	enum mlxsw_reg_sbxx_dir dir;
 	u8 pool;
 };
 
 /* Order ingress pools before egress pools. */
-static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = {
+static const struct mlxsw_sp_sb_pool_des mlxsw_sp1_sb_pool_dess[] = {
 	{MLXSW_REG_SBXX_DIR_INGRESS, 0},
 	{MLXSW_REG_SBXX_DIR_INGRESS, 1},
 	{MLXSW_REG_SBXX_DIR_INGRESS, 2},
@@ -55,7 +61,17 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = {
 	{MLXSW_REG_SBXX_DIR_EGRESS, 15},
 };
 
-#define MLXSW_SP_SB_POOL_DESS_LEN ARRAY_SIZE(mlxsw_sp_sb_pool_dess)
+static const struct mlxsw_sp_sb_pool_des mlxsw_sp2_sb_pool_dess[] = {
+	{MLXSW_REG_SBXX_DIR_INGRESS, 0},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 1},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 2},
+	{MLXSW_REG_SBXX_DIR_INGRESS, 3},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 0},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 1},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 2},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 3},
+	{MLXSW_REG_SBXX_DIR_EGRESS, 15},
+};
 
 #define MLXSW_SP_SB_ING_TC_COUNT 8
 #define MLXSW_SP_SB_EG_TC_COUNT 16
@@ -63,16 +79,32 @@ static const struct mlxsw_sp_sb_pool_des mlxsw_sp_sb_pool_dess[] = {
 struct mlxsw_sp_sb_port {
 	struct mlxsw_sp_sb_cm ing_cms[MLXSW_SP_SB_ING_TC_COUNT];
 	struct mlxsw_sp_sb_cm eg_cms[MLXSW_SP_SB_EG_TC_COUNT];
-	struct mlxsw_sp_sb_pm pms[MLXSW_SP_SB_POOL_DESS_LEN];
+	struct mlxsw_sp_sb_pm *pms;
 };
 
 struct mlxsw_sp_sb {
-	struct mlxsw_sp_sb_pr prs[MLXSW_SP_SB_POOL_DESS_LEN];
+	struct mlxsw_sp_sb_pr *prs;
 	struct mlxsw_sp_sb_port *ports;
 	u32 cell_size;
+	u32 max_headroom_cells;
 	u64 sb_size;
 };
 
+struct mlxsw_sp_sb_vals {
+	unsigned int pool_count;
+	const struct mlxsw_sp_sb_pool_des *pool_dess;
+	const struct mlxsw_sp_sb_pm *pms;
+	const struct mlxsw_sp_sb_pr *prs;
+	const struct mlxsw_sp_sb_mm *mms;
+	const struct mlxsw_sp_sb_cm *cms_ingress;
+	const struct mlxsw_sp_sb_cm *cms_egress;
+	const struct mlxsw_sp_sb_cm *cms_cpu;
+	unsigned int mms_count;
+	unsigned int cms_ingress_count;
+	unsigned int cms_egress_count;
+	unsigned int cms_cpu_count;
+};
+
 u32 mlxsw_sp_cells_bytes(const struct mlxsw_sp *mlxsw_sp, u32 cells)
 {
 	return mlxsw_sp->sb->cell_size * cells;
@@ -83,6 +115,11 @@ u32 mlxsw_sp_bytes_cells(const struct mlxsw_sp *mlxsw_sp, u32 bytes)
 	return DIV_ROUND_UP(bytes, mlxsw_sp->sb->cell_size);
 }
 
+u32 mlxsw_sp_sb_max_headroom_cells(const struct mlxsw_sp *mlxsw_sp)
+{
+	return mlxsw_sp->sb->max_headroom_cells;
+}
+
 static struct mlxsw_sp_sb_pr *mlxsw_sp_sb_pr_get(struct mlxsw_sp *mlxsw_sp,
 						 u16 pool_index)
 {
@@ -121,7 +158,7 @@ static int mlxsw_sp_sb_pr_write(struct mlxsw_sp *mlxsw_sp, u16 pool_index,
 				u32 size, bool infi_size)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpr_pl[MLXSW_REG_SBPR_LEN];
 	struct mlxsw_sp_sb_pr *pr;
 	int err;
@@ -145,7 +182,7 @@ static int mlxsw_sp_sb_cm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				bool infi_max, u16 pool_index)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbcm_pl[MLXSW_REG_SBCM_LEN];
 	struct mlxsw_sp_sb_cm *cm;
 	int err;
@@ -174,7 +211,7 @@ static int mlxsw_sp_sb_pm_write(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				u16 pool_index, u32 min_buff, u32 max_buff)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 	struct mlxsw_sp_sb_pm *pm;
 	int err;
@@ -195,7 +232,7 @@ static int mlxsw_sp_sb_pm_occ_clear(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				    u16 pool_index, struct list_head *bulk_list)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 
 	mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir,
@@ -217,7 +254,7 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				    u16 pool_index, struct list_head *bulk_list)
 {
 	const struct mlxsw_sp_sb_pool_des *des =
-		&mlxsw_sp_sb_pool_dess[pool_index];
+		&mlxsw_sp->sb_vals->pool_dess[pool_index];
 	char sbpm_pl[MLXSW_REG_SBPM_LEN];
 	struct mlxsw_sp_sb_pm *pm;
 
@@ -230,24 +267,24 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				     (unsigned long) pm);
 }
 
-static const u16 mlxsw_sp_pbs[] = {
-	[0] = 2 * ETH_FRAME_LEN,
-	[9] = 2 * MLXSW_PORT_MAX_MTU,
-};
-
-#define MLXSW_SP_PBS_LEN ARRAY_SIZE(mlxsw_sp_pbs)
+/* 1/4 of a headroom necessary for 100Gbps port and 100m cable. */
+#define MLXSW_SP_PB_HEADROOM 25632
 #define MLXSW_SP_PB_UNUSED 8
 
 static int mlxsw_sp_port_pb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	const u32 pbs[] = {
+		[0] = MLXSW_SP_PB_HEADROOM * mlxsw_sp_port->mapping.width,
+		[9] = 2 * MLXSW_PORT_MAX_MTU,
+	};
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char pbmc_pl[MLXSW_REG_PBMC_LEN];
 	int i;
 
 	mlxsw_reg_pbmc_pack(pbmc_pl, mlxsw_sp_port->local_port,
 			    0xffff, 0xffff / 2);
-	for (i = 0; i < MLXSW_SP_PBS_LEN; i++) {
-		u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, mlxsw_sp_pbs[i]);
+	for (i = 0; i < ARRAY_SIZE(pbs); i++) {
+		u16 size = mlxsw_sp_bytes_cells(mlxsw_sp, pbs[i]);
 
 		if (i == MLXSW_SP_PB_UNUSED)
 			continue;
@@ -280,50 +317,120 @@ static int mlxsw_sp_port_headroom_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return mlxsw_sp_port_pb_prio_init(mlxsw_sp_port);
 }
 
+static int mlxsw_sp_sb_port_init(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_sb_port *sb_port)
+{
+	struct mlxsw_sp_sb_pm *pms;
+
+	pms = kcalloc(mlxsw_sp->sb_vals->pool_count, sizeof(*pms),
+		      GFP_KERNEL);
+	if (!pms)
+		return -ENOMEM;
+	sb_port->pms = pms;
+	return 0;
+}
+
+static void mlxsw_sp_sb_port_fini(struct mlxsw_sp_sb_port *sb_port)
+{
+	kfree(sb_port->pms);
+}
+
 static int mlxsw_sp_sb_ports_init(struct mlxsw_sp *mlxsw_sp)
 {
 	unsigned int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+	struct mlxsw_sp_sb_pr *prs;
+	int i;
+	int err;
 
 	mlxsw_sp->sb->ports = kcalloc(max_ports,
 				      sizeof(struct mlxsw_sp_sb_port),
 				      GFP_KERNEL);
 	if (!mlxsw_sp->sb->ports)
 		return -ENOMEM;
+
+	prs = kcalloc(mlxsw_sp->sb_vals->pool_count, sizeof(*prs),
+		      GFP_KERNEL);
+	if (!prs) {
+		err = -ENOMEM;
+		goto err_alloc_prs;
+	}
+	mlxsw_sp->sb->prs = prs;
+
+	for (i = 0; i < max_ports; i++) {
+		err = mlxsw_sp_sb_port_init(mlxsw_sp, &mlxsw_sp->sb->ports[i]);
+		if (err)
+			goto err_sb_port_init;
+	}
+
 	return 0;
+
+err_sb_port_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp_sb_port_fini(&mlxsw_sp->sb->ports[i]);
+	kfree(mlxsw_sp->sb->prs);
+err_alloc_prs:
+	kfree(mlxsw_sp->sb->ports);
+	return err;
 }
 
 static void mlxsw_sp_sb_ports_fini(struct mlxsw_sp *mlxsw_sp)
 {
+	int max_ports = mlxsw_core_max_ports(mlxsw_sp->core);
+	int i;
+
+	for (i = max_ports - 1; i >= 0; i--)
+		mlxsw_sp_sb_port_fini(&mlxsw_sp->sb->ports[i]);
+	kfree(mlxsw_sp->sb->prs);
 	kfree(mlxsw_sp->sb->ports);
 }
 
-#define MLXSW_SP_SB_PR_INGRESS_SIZE	12440000
-#define MLXSW_SP_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
-#define MLXSW_SP_SB_PR_EGRESS_SIZE	13232000
-
 #define MLXSW_SP_SB_PR(_mode, _size)	\
 	{				\
 		.mode = _mode,		\
 		.size = _size,		\
 	}
 
-static const struct mlxsw_sp_sb_pr mlxsw_sp_sb_prs[] = {
+#define MLXSW_SP1_SB_PR_INGRESS_SIZE	12440000
+#define MLXSW_SP1_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
+#define MLXSW_SP1_SB_PR_EGRESS_SIZE	13232000
+
+static const struct mlxsw_sp_sb_pr mlxsw_sp1_sb_prs[] = {
 	/* Ingress pools. */
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_SB_PR_INGRESS_SIZE),
+		       MLXSW_SP1_SB_PR_INGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
-		       MLXSW_SP_SB_PR_INGRESS_MNG_SIZE),
+		       MLXSW_SP1_SB_PR_INGRESS_MNG_SIZE),
 	/* Egress pools. */
-	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, MLXSW_SP_SB_PR_EGRESS_SIZE),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP1_SB_PR_EGRESS_SIZE),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC, 0),
 	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
 };
 
-#define MLXSW_SP_SB_PRS_LEN ARRAY_SIZE(mlxsw_sp_sb_prs)
+#define MLXSW_SP2_SB_PR_INGRESS_SIZE	40960000
+#define MLXSW_SP2_SB_PR_INGRESS_MNG_SIZE (200 * 1000)
+#define MLXSW_SP2_SB_PR_EGRESS_SIZE	40960000
+
+static const struct mlxsw_sp_sb_pr mlxsw_sp2_sb_prs[] = {
+	/* Ingress pools. */
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP2_SB_PR_INGRESS_SIZE),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP2_SB_PR_INGRESS_MNG_SIZE),
+	/* Egress pools. */
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_DYNAMIC,
+		       MLXSW_SP2_SB_PR_EGRESS_SIZE),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, 0),
+	MLXSW_SP_SB_PR(MLXSW_REG_SBPR_MODE_STATIC, MLXSW_SP_SB_INFI),
+};
 
 static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
 				const struct mlxsw_sp_sb_pr *prs,
@@ -357,7 +464,7 @@ static int mlxsw_sp_sb_prs_init(struct mlxsw_sp *mlxsw_sp,
 		.pool_index = _pool,			\
 	}
 
-static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
+static const struct mlxsw_sp_sb_cm mlxsw_sp1_sb_cms_ingress[] = {
 	MLXSW_SP_SB_CM(10000, 8, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
 	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
@@ -370,9 +477,20 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_ingress[] = {
 	MLXSW_SP_SB_CM(20000, 1, 3),
 };
 
-#define MLXSW_SP_SB_CMS_INGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_ingress)
+static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_ingress[] = {
+	MLXSW_SP_SB_CM(0, 7, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN, 0),
+	MLXSW_SP_SB_CM(0, 0, 0), /* dummy, this PG does not exist */
+	MLXSW_SP_SB_CM(20000, 1, 3),
+};
 
-static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
+static const struct mlxsw_sp_sb_cm mlxsw_sp1_sb_cms_egress[] = {
 	MLXSW_SP_SB_CM(1500, 9, 4),
 	MLXSW_SP_SB_CM(1500, 9, 4),
 	MLXSW_SP_SB_CM(1500, 9, 4),
@@ -392,7 +510,25 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = {
 	MLXSW_SP_SB_CM(1, 0xff, 4),
 };
 
-#define MLXSW_SP_SB_CMS_EGRESS_LEN ARRAY_SIZE(mlxsw_sp_sb_cms_egress)
+static const struct mlxsw_sp_sb_cm mlxsw_sp2_sb_cms_egress[] = {
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, 7, 4),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(0, MLXSW_SP_SB_INFI, 8),
+	MLXSW_SP_SB_CM(1, 0xff, 4),
+};
 
 #define MLXSW_SP_CPU_PORT_SB_CM MLXSW_SP_SB_CM(0, 0, 4)
 
@@ -431,9 +567,6 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_cpu_port_sb_cms[] = {
 	MLXSW_SP_CPU_PORT_SB_CM,
 };
 
-#define MLXSW_SP_CPU_PORT_SB_MCS_LEN \
-	ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms)
-
 static bool
 mlxsw_sp_sb_pool_is_static(struct mlxsw_sp *mlxsw_sp, u16 pool_index)
 {
@@ -447,6 +580,7 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				  const struct mlxsw_sp_sb_cm *cms,
 				  size_t cms_len)
 {
+	const struct mlxsw_sp_sb_vals *sb_vals = mlxsw_sp->sb_vals;
 	int i;
 	int err;
 
@@ -458,7 +592,7 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		if (i == 8 && dir == MLXSW_REG_SBXX_DIR_INGRESS)
 			continue; /* PG number 8 does not exist, skip it */
 		cm = &cms[i];
-		if (WARN_ON(mlxsw_sp_sb_pool_dess[cm->pool_index].dir != dir))
+		if (WARN_ON(sb_vals->pool_dess[cm->pool_index].dir != dir))
 			continue;
 
 		min_buff = mlxsw_sp_bytes_cells(mlxsw_sp, cm->min_buff);
@@ -484,27 +618,28 @@ static int __mlxsw_sp_sb_cms_init(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 
 static int mlxsw_sp_port_sb_cms_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	int err;
 
-	err = __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
+	err = __mlxsw_sp_sb_cms_init(mlxsw_sp,
 				     mlxsw_sp_port->local_port,
 				     MLXSW_REG_SBXX_DIR_INGRESS,
-				     mlxsw_sp_sb_cms_ingress,
-				     MLXSW_SP_SB_CMS_INGRESS_LEN);
+				     mlxsw_sp->sb_vals->cms_ingress,
+				     mlxsw_sp->sb_vals->cms_ingress_count);
 	if (err)
 		return err;
 	return __mlxsw_sp_sb_cms_init(mlxsw_sp_port->mlxsw_sp,
 				      mlxsw_sp_port->local_port,
 				      MLXSW_REG_SBXX_DIR_EGRESS,
-				      mlxsw_sp_sb_cms_egress,
-				      MLXSW_SP_SB_CMS_EGRESS_LEN);
+				      mlxsw_sp->sb_vals->cms_egress,
+				      mlxsw_sp->sb_vals->cms_egress_count);
 }
 
 static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp)
 {
 	return __mlxsw_sp_sb_cms_init(mlxsw_sp, 0, MLXSW_REG_SBXX_DIR_EGRESS,
-				      mlxsw_sp_cpu_port_sb_cms,
-				      MLXSW_SP_CPU_PORT_SB_MCS_LEN);
+				      mlxsw_sp->sb_vals->cms_cpu,
+				      mlxsw_sp->sb_vals->cms_cpu_count);
 }
 
 #define MLXSW_SP_SB_PM(_min_buff, _max_buff)	\
@@ -513,7 +648,7 @@ static int mlxsw_sp_cpu_port_sb_cms_init(struct mlxsw_sp *mlxsw_sp)
 		.max_buff = _max_buff,		\
 	}
 
-static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = {
+static const struct mlxsw_sp_sb_pm mlxsw_sp1_sb_pms[] = {
 	/* Ingress pools. */
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
 	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MIN),
@@ -527,7 +662,19 @@ static const struct mlxsw_sp_sb_pm mlxsw_sp_sb_pms[] = {
 	MLXSW_SP_SB_PM(10000, 90000),
 };
 
-#define MLXSW_SP_SB_PMS_LEN ARRAY_SIZE(mlxsw_sp_sb_pms)
+static const struct mlxsw_sp_sb_pm mlxsw_sp2_sb_pms[] = {
+	/* Ingress pools. */
+	MLXSW_SP_SB_PM(0, 7),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, MLXSW_REG_SBXX_DYN_MAX_BUFF_MAX),
+	/* Egress pools. */
+	MLXSW_SP_SB_PM(0, 7),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(0, 0),
+	MLXSW_SP_SB_PM(10000, 90000),
+};
 
 static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
 {
@@ -535,8 +682,8 @@ static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	int i;
 	int err;
 
-	for (i = 0; i < MLXSW_SP_SB_PMS_LEN; i++) {
-		const struct mlxsw_sp_sb_pm *pm = &mlxsw_sp_sb_pms[i];
+	for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
+		const struct mlxsw_sp_sb_pm *pm = &mlxsw_sp->sb_vals->pms[i];
 		u32 max_buff;
 		u32 min_buff;
 
@@ -552,12 +699,6 @@ static int mlxsw_sp_port_sb_pms_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return 0;
 }
 
-struct mlxsw_sp_sb_mm {
-	u32 min_buff;
-	u32 max_buff;
-	u16 pool_index;
-};
-
 #define MLXSW_SP_SB_MM(_min_buff, _max_buff, _pool)	\
 	{						\
 		.min_buff = _min_buff,			\
@@ -583,21 +724,19 @@ static const struct mlxsw_sp_sb_mm mlxsw_sp_sb_mms[] = {
 	MLXSW_SP_SB_MM(0, 6, 4),
 };
 
-#define MLXSW_SP_SB_MMS_LEN ARRAY_SIZE(mlxsw_sp_sb_mms)
-
 static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 {
 	char sbmm_pl[MLXSW_REG_SBMM_LEN];
 	int i;
 	int err;
 
-	for (i = 0; i < MLXSW_SP_SB_MMS_LEN; i++) {
+	for (i = 0; i < mlxsw_sp->sb_vals->mms_count; i++) {
 		const struct mlxsw_sp_sb_pool_des *des;
 		const struct mlxsw_sp_sb_mm *mc;
 		u32 min_buff;
 
-		mc = &mlxsw_sp_sb_mms[i];
-		des = &mlxsw_sp_sb_pool_dess[mc->pool_index];
+		mc = &mlxsw_sp->sb_vals->mms[i];
+		des = &mlxsw_sp->sb_vals->pool_dess[mc->pool_index];
 		/* All pools used by sb_mm's are initialized using dynamic
 		 * thresholds, therefore 'max_buff' isn't specified in cells.
 		 */
@@ -611,22 +750,55 @@ static int mlxsw_sp_sb_mms_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
-static void mlxsw_sp_pool_count(u16 *p_ingress_len, u16 *p_egress_len)
+static void mlxsw_sp_pool_count(struct mlxsw_sp *mlxsw_sp,
+				u16 *p_ingress_len, u16 *p_egress_len)
 {
 	int i;
 
-	for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; ++i)
-		if (mlxsw_sp_sb_pool_dess[i].dir == MLXSW_REG_SBXX_DIR_EGRESS)
+	for (i = 0; i < mlxsw_sp->sb_vals->pool_count; ++i)
+		if (mlxsw_sp->sb_vals->pool_dess[i].dir ==
+		    MLXSW_REG_SBXX_DIR_EGRESS)
 			goto out;
 	WARN(1, "No egress pools\n");
 
 out:
 	*p_ingress_len = i;
-	*p_egress_len = MLXSW_SP_SB_POOL_DESS_LEN - i;
+	*p_egress_len = mlxsw_sp->sb_vals->pool_count - i;
 }
 
+const struct mlxsw_sp_sb_vals mlxsw_sp1_sb_vals = {
+	.pool_count = ARRAY_SIZE(mlxsw_sp1_sb_pool_dess),
+	.pool_dess = mlxsw_sp1_sb_pool_dess,
+	.pms = mlxsw_sp1_sb_pms,
+	.prs = mlxsw_sp1_sb_prs,
+	.mms = mlxsw_sp_sb_mms,
+	.cms_ingress = mlxsw_sp1_sb_cms_ingress,
+	.cms_egress = mlxsw_sp1_sb_cms_egress,
+	.cms_cpu = mlxsw_sp_cpu_port_sb_cms,
+	.mms_count = ARRAY_SIZE(mlxsw_sp_sb_mms),
+	.cms_ingress_count = ARRAY_SIZE(mlxsw_sp1_sb_cms_ingress),
+	.cms_egress_count = ARRAY_SIZE(mlxsw_sp1_sb_cms_egress),
+	.cms_cpu_count = ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms),
+};
+
+const struct mlxsw_sp_sb_vals mlxsw_sp2_sb_vals = {
+	.pool_count = ARRAY_SIZE(mlxsw_sp2_sb_pool_dess),
+	.pool_dess = mlxsw_sp2_sb_pool_dess,
+	.pms = mlxsw_sp2_sb_pms,
+	.prs = mlxsw_sp2_sb_prs,
+	.mms = mlxsw_sp_sb_mms,
+	.cms_ingress = mlxsw_sp2_sb_cms_ingress,
+	.cms_egress = mlxsw_sp2_sb_cms_egress,
+	.cms_cpu = mlxsw_sp_cpu_port_sb_cms,
+	.mms_count = ARRAY_SIZE(mlxsw_sp_sb_mms),
+	.cms_ingress_count = ARRAY_SIZE(mlxsw_sp2_sb_cms_ingress),
+	.cms_egress_count = ARRAY_SIZE(mlxsw_sp2_sb_cms_egress),
+	.cms_cpu_count = ARRAY_SIZE(mlxsw_sp_cpu_port_sb_cms),
+};
+
 int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 {
+	u32 max_headroom_size;
 	u16 ing_pool_count;
 	u16 eg_pool_count;
 	int err;
@@ -637,18 +809,26 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_BUFFER_SIZE))
 		return -EIO;
 
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_HEADROOM_SIZE))
+		return -EIO;
+
 	mlxsw_sp->sb = kzalloc(sizeof(*mlxsw_sp->sb), GFP_KERNEL);
 	if (!mlxsw_sp->sb)
 		return -ENOMEM;
 	mlxsw_sp->sb->cell_size = MLXSW_CORE_RES_GET(mlxsw_sp->core, CELL_SIZE);
 	mlxsw_sp->sb->sb_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						   MAX_BUFFER_SIZE);
+	max_headroom_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+					       MAX_HEADROOM_SIZE);
+	/* Round down, because this limit must not be overstepped. */
+	mlxsw_sp->sb->max_headroom_cells = max_headroom_size /
+						mlxsw_sp->sb->cell_size;
 
 	err = mlxsw_sp_sb_ports_init(mlxsw_sp);
 	if (err)
 		goto err_sb_ports_init;
-	err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp_sb_prs,
-				   MLXSW_SP_SB_PRS_LEN);
+	err = mlxsw_sp_sb_prs_init(mlxsw_sp, mlxsw_sp->sb_vals->prs,
+				   mlxsw_sp->sb_vals->pool_count);
 	if (err)
 		goto err_sb_prs_init;
 	err = mlxsw_sp_cpu_port_sb_cms_init(mlxsw_sp);
@@ -657,7 +837,7 @@ int mlxsw_sp_buffers_init(struct mlxsw_sp *mlxsw_sp)
 	err = mlxsw_sp_sb_mms_init(mlxsw_sp);
 	if (err)
 		goto err_sb_mms_init;
-	mlxsw_sp_pool_count(&ing_pool_count, &eg_pool_count);
+	mlxsw_sp_pool_count(mlxsw_sp, &ing_pool_count, &eg_pool_count);
 	err = devlink_sb_register(priv_to_devlink(mlxsw_sp->core), 0,
 				  mlxsw_sp->sb->sb_size,
 				  ing_pool_count,
@@ -705,14 +885,16 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core,
 			 unsigned int sb_index, u16 pool_index,
 			 struct devlink_sb_pool_info *pool_info)
 {
-	enum mlxsw_reg_sbxx_dir dir = mlxsw_sp_sb_pool_dess[pool_index].dir;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+	enum mlxsw_reg_sbxx_dir dir;
 	struct mlxsw_sp_sb_pr *pr;
 
+	dir = mlxsw_sp->sb_vals->pool_dess[pool_index].dir;
 	pr = mlxsw_sp_sb_pr_get(mlxsw_sp, pool_index);
 	pool_info->pool_type = (enum devlink_sb_pool_type) dir;
 	pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size);
 	pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode;
+	pool_info->cell_size = mlxsw_sp->sb->cell_size;
 	return 0;
 }
 
@@ -833,7 +1015,7 @@ int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port,
 	u32 max_buff;
 	int err;
 
-	if (dir != mlxsw_sp_sb_pool_dess[pool_index].dir)
+	if (dir != mlxsw_sp->sb_vals->pool_dess[pool_index].dir)
 		return -EINVAL;
 
 	err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index,
@@ -931,7 +1113,7 @@ next_batch:
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
 		mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
-		for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) {
+		for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
 			err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i,
 						       &bulk_list);
 			if (err)
@@ -990,7 +1172,7 @@ next_batch:
 			continue;
 		mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1);
 		mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1);
-		for (i = 0; i < MLXSW_SP_SB_POOL_DESS_LEN; i++) {
+		for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) {
 			err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i,
 						       &bulk_list);
 			if (err)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index 41e607a14846..49933818c6f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -220,7 +220,7 @@ start_again:
 	for (; i < rif_count; i++) {
 		struct mlxsw_sp_rif *rif = mlxsw_sp_rif_by_index(mlxsw_sp, i);
 
-		if (!rif)
+		if (!rif || !mlxsw_sp_rif_dev(rif))
 			continue;
 		err = mlxsw_sp_erif_entry_get(mlxsw_sp, &entry, rif,
 					      counters_enabled);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index a3db033d7399..46baf3b44309 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -15,6 +15,7 @@
 struct mlxsw_sp_fid_family;
 
 struct mlxsw_sp_fid_core {
+	struct rhashtable fid_ht;
 	struct rhashtable vni_ht;
 	struct mlxsw_sp_fid_family *fid_family_arr[MLXSW_SP_FID_TYPE_MAX];
 	unsigned int *port_fid_mappings;
@@ -26,10 +27,13 @@ struct mlxsw_sp_fid {
 	unsigned int ref_count;
 	u16 fid_index;
 	struct mlxsw_sp_fid_family *fid_family;
+	struct rhash_head ht_node;
 
 	struct rhash_head vni_ht_node;
+	enum mlxsw_sp_nve_type nve_type;
 	__be32 vni;
 	u32 nve_flood_index;
+	int nve_ifindex;
 	u8 vni_valid:1,
 	   nve_flood_index_valid:1;
 };
@@ -44,6 +48,12 @@ struct mlxsw_sp_fid_8021d {
 	int br_ifindex;
 };
 
+static const struct rhashtable_params mlxsw_sp_fid_ht_params = {
+	.key_len = sizeof_field(struct mlxsw_sp_fid, fid_index),
+	.key_offset = offsetof(struct mlxsw_sp_fid, fid_index),
+	.head_offset = offsetof(struct mlxsw_sp_fid, ht_node),
+};
+
 static const struct rhashtable_params mlxsw_sp_fid_vni_ht_params = {
 	.key_len = sizeof_field(struct mlxsw_sp_fid, vni),
 	.key_offset = offsetof(struct mlxsw_sp_fid, vni),
@@ -75,6 +85,8 @@ struct mlxsw_sp_fid_ops {
 	int (*nve_flood_index_set)(struct mlxsw_sp_fid *fid,
 				   u32 nve_flood_index);
 	void (*nve_flood_index_clear)(struct mlxsw_sp_fid *fid);
+	void (*fdb_clear_offload)(const struct mlxsw_sp_fid *fid,
+				  const struct net_device *nve_dev);
 };
 
 struct mlxsw_sp_fid_family {
@@ -89,6 +101,7 @@ struct mlxsw_sp_fid_family {
 	enum mlxsw_sp_rif_type rif_type;
 	const struct mlxsw_sp_fid_ops *ops;
 	struct mlxsw_sp *mlxsw_sp;
+	u8 lag_vid_valid:1;
 };
 
 static const int mlxsw_sp_sfgc_uc_packet_types[MLXSW_REG_SFGC_TYPE_MAX] = {
@@ -113,6 +126,45 @@ static const int *mlxsw_sp_packet_type_sfgc_types[] = {
 	[MLXSW_SP_FLOOD_TYPE_MC]	= mlxsw_sp_sfgc_mc_packet_types,
 };
 
+bool mlxsw_sp_fid_lag_vid_valid(const struct mlxsw_sp_fid *fid)
+{
+	return fid->fid_family->lag_vid_valid;
+}
+
+struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_index(struct mlxsw_sp *mlxsw_sp,
+						  u16 fid_index)
+{
+	struct mlxsw_sp_fid *fid;
+
+	fid = rhashtable_lookup_fast(&mlxsw_sp->fid_core->fid_ht, &fid_index,
+				     mlxsw_sp_fid_ht_params);
+	if (fid)
+		fid->ref_count++;
+
+	return fid;
+}
+
+int mlxsw_sp_fid_nve_ifindex(const struct mlxsw_sp_fid *fid, int *nve_ifindex)
+{
+	if (!fid->vni_valid)
+		return -EINVAL;
+
+	*nve_ifindex = fid->nve_ifindex;
+
+	return 0;
+}
+
+int mlxsw_sp_fid_nve_type(const struct mlxsw_sp_fid *fid,
+			  enum mlxsw_sp_nve_type *p_type)
+{
+	if (!fid->vni_valid)
+		return -EINVAL;
+
+	*p_type = fid->nve_type;
+
+	return 0;
+}
+
 struct mlxsw_sp_fid *mlxsw_sp_fid_lookup_by_vni(struct mlxsw_sp *mlxsw_sp,
 						__be32 vni)
 {
@@ -173,7 +225,8 @@ bool mlxsw_sp_fid_nve_flood_index_is_set(const struct mlxsw_sp_fid *fid)
 	return fid->nve_flood_index_valid;
 }
 
-int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni)
+int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, enum mlxsw_sp_nve_type type,
+			 __be32 vni, int nve_ifindex)
 {
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
 	const struct mlxsw_sp_fid_ops *ops = fid_family->ops;
@@ -183,6 +236,8 @@ int mlxsw_sp_fid_vni_set(struct mlxsw_sp_fid *fid, __be32 vni)
 	if (WARN_ON(!ops->vni_set || fid->vni_valid))
 		return -EINVAL;
 
+	fid->nve_type = type;
+	fid->nve_ifindex = nve_ifindex;
 	fid->vni = vni;
 	err = rhashtable_lookup_insert_fast(&mlxsw_sp->fid_core->vni_ht,
 					    &fid->vni_ht_node,
@@ -224,6 +279,16 @@ bool mlxsw_sp_fid_vni_is_set(const struct mlxsw_sp_fid *fid)
 	return fid->vni_valid;
 }
 
+void mlxsw_sp_fid_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				    const struct net_device *nve_dev)
+{
+	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
+	const struct mlxsw_sp_fid_ops *ops = fid_family->ops;
+
+	if (ops->fdb_clear_offload)
+		ops->fdb_clear_offload(fid, nve_dev);
+}
+
 static const struct mlxsw_sp_flood_table *
 mlxsw_sp_fid_flood_table_lookup(const struct mlxsw_sp_fid *fid,
 				enum mlxsw_sp_flood_type packet_type)
@@ -284,11 +349,6 @@ void mlxsw_sp_fid_port_vid_unmap(struct mlxsw_sp_fid *fid,
 	fid->fid_family->ops->port_vid_unmap(fid, mlxsw_sp_port, vid);
 }
 
-enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid)
-{
-	return fid->fid_family->rif_type;
-}
-
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid)
 {
 	return fid->fid_index;
@@ -304,6 +364,11 @@ void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif)
 	fid->rif = rif;
 }
 
+struct mlxsw_sp_rif *mlxsw_sp_fid_rif(const struct mlxsw_sp_fid *fid)
+{
+	return fid->rif;
+}
+
 enum mlxsw_sp_rif_type
 mlxsw_sp_fid_type_rif_type(const struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_fid_type type)
@@ -568,7 +633,7 @@ mlxsw_sp_fid_8021d_compare(const struct mlxsw_sp_fid *fid, const void *arg)
 
 static u16 mlxsw_sp_fid_8021d_flood_index(const struct mlxsw_sp_fid *fid)
 {
-	return fid->fid_index - fid->fid_family->start_index;
+	return fid->fid_index - VLAN_N_VID;
 }
 
 static int mlxsw_sp_port_vp_mode_trans(struct mlxsw_sp_port *mlxsw_sp_port)
@@ -713,6 +778,13 @@ static void mlxsw_sp_fid_8021d_nve_flood_index_clear(struct mlxsw_sp_fid *fid)
 			    fid->vni_valid, 0, false);
 }
 
+static void
+mlxsw_sp_fid_8021d_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				     const struct net_device *nve_dev)
+{
+	br_fdb_clear_offload(nve_dev, 0);
+}
+
 static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = {
 	.setup			= mlxsw_sp_fid_8021d_setup,
 	.configure		= mlxsw_sp_fid_8021d_configure,
@@ -726,6 +798,7 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = {
 	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
 	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
 	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+	.fdb_clear_offload	= mlxsw_sp_fid_8021d_fdb_clear_offload,
 };
 
 static const struct mlxsw_sp_flood_table mlxsw_sp_fid_8021d_flood_tables[] = {
@@ -759,6 +832,48 @@ static const struct mlxsw_sp_fid_family mlxsw_sp_fid_8021d_family = {
 	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
 	.rif_type		= MLXSW_SP_RIF_TYPE_FID,
 	.ops			= &mlxsw_sp_fid_8021d_ops,
+	.lag_vid_valid		= 1,
+};
+
+static void
+mlxsw_sp_fid_8021q_fdb_clear_offload(const struct mlxsw_sp_fid *fid,
+				     const struct net_device *nve_dev)
+{
+	br_fdb_clear_offload(nve_dev, mlxsw_sp_fid_8021q_vid(fid));
+}
+
+static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021q_emu_ops = {
+	.setup			= mlxsw_sp_fid_8021q_setup,
+	.configure		= mlxsw_sp_fid_8021d_configure,
+	.deconfigure		= mlxsw_sp_fid_8021d_deconfigure,
+	.index_alloc		= mlxsw_sp_fid_8021d_index_alloc,
+	.compare		= mlxsw_sp_fid_8021q_compare,
+	.flood_index		= mlxsw_sp_fid_8021d_flood_index,
+	.port_vid_map		= mlxsw_sp_fid_8021d_port_vid_map,
+	.port_vid_unmap		= mlxsw_sp_fid_8021d_port_vid_unmap,
+	.vni_set		= mlxsw_sp_fid_8021d_vni_set,
+	.vni_clear		= mlxsw_sp_fid_8021d_vni_clear,
+	.nve_flood_index_set	= mlxsw_sp_fid_8021d_nve_flood_index_set,
+	.nve_flood_index_clear	= mlxsw_sp_fid_8021d_nve_flood_index_clear,
+	.fdb_clear_offload	= mlxsw_sp_fid_8021q_fdb_clear_offload,
+};
+
+/* There are 4K-2 emulated 802.1Q FIDs, starting right after the 802.1D FIDs */
+#define MLXSW_SP_FID_8021Q_EMU_START	(VLAN_N_VID + MLXSW_SP_FID_8021D_MAX)
+#define MLXSW_SP_FID_8021Q_EMU_END	(MLXSW_SP_FID_8021Q_EMU_START + \
+					 VLAN_VID_MASK - 2)
+
+/* Range and flood configuration must match mlxsw_config_profile */
+static const struct mlxsw_sp_fid_family mlxsw_sp_fid_8021q_emu_family = {
+	.type			= MLXSW_SP_FID_TYPE_8021Q,
+	.fid_size		= sizeof(struct mlxsw_sp_fid_8021q),
+	.start_index		= MLXSW_SP_FID_8021Q_EMU_START,
+	.end_index		= MLXSW_SP_FID_8021Q_EMU_END,
+	.flood_tables		= mlxsw_sp_fid_8021d_flood_tables,
+	.nr_flood_tables	= ARRAY_SIZE(mlxsw_sp_fid_8021d_flood_tables),
+	.rif_type		= MLXSW_SP_RIF_TYPE_VLAN,
+	.ops			= &mlxsw_sp_fid_8021q_emu_ops,
+	.lag_vid_valid		= 1,
 };
 
 static int mlxsw_sp_fid_rfid_configure(struct mlxsw_sp_fid *fid)
@@ -882,13 +997,13 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_dummy_ops = {
 static const struct mlxsw_sp_fid_family mlxsw_sp_fid_dummy_family = {
 	.type			= MLXSW_SP_FID_TYPE_DUMMY,
 	.fid_size		= sizeof(struct mlxsw_sp_fid),
-	.start_index		= MLXSW_SP_RFID_BASE - 1,
-	.end_index		= MLXSW_SP_RFID_BASE - 1,
+	.start_index		= VLAN_N_VID - 1,
+	.end_index		= VLAN_N_VID - 1,
 	.ops			= &mlxsw_sp_fid_dummy_ops,
 };
 
 static const struct mlxsw_sp_fid_family *mlxsw_sp_fid_family_arr[] = {
-	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp_fid_8021q_family,
+	[MLXSW_SP_FID_TYPE_8021Q]	= &mlxsw_sp_fid_8021q_emu_family,
 	[MLXSW_SP_FID_TYPE_8021D]	= &mlxsw_sp_fid_8021d_family,
 	[MLXSW_SP_FID_TYPE_RFID]	= &mlxsw_sp_fid_rfid_family,
 	[MLXSW_SP_FID_TYPE_DUMMY]	= &mlxsw_sp_fid_dummy_family,
@@ -944,10 +1059,17 @@ static struct mlxsw_sp_fid *mlxsw_sp_fid_get(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_configure;
 
+	err = rhashtable_insert_fast(&mlxsw_sp->fid_core->fid_ht, &fid->ht_node,
+				     mlxsw_sp_fid_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
 	list_add(&fid->list, &fid_family->fids_list);
 	fid->ref_count++;
 	return fid;
 
+err_rhashtable_insert:
+	fid->fid_family->ops->deconfigure(fid);
 err_configure:
 	__clear_bit(fid_index - fid_family->start_index,
 		    fid_family->fids_bitmap);
@@ -959,19 +1081,18 @@ err_index_alloc:
 void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid)
 {
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
+	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
 
-	if (--fid->ref_count == 1 && fid->rif) {
-		/* Destroy the associated RIF and let it drop the last
-		 * reference on the FID.
-		 */
-		return mlxsw_sp_rif_destroy(fid->rif);
-	} else if (fid->ref_count == 0) {
-		list_del(&fid->list);
-		fid->fid_family->ops->deconfigure(fid);
-		__clear_bit(fid->fid_index - fid_family->start_index,
-			    fid_family->fids_bitmap);
-		kfree(fid);
-	}
+	if (--fid->ref_count != 0)
+		return;
+
+	list_del(&fid->list);
+	rhashtable_remove_fast(&mlxsw_sp->fid_core->fid_ht,
+			       &fid->ht_node, mlxsw_sp_fid_ht_params);
+	fid->fid_family->ops->deconfigure(fid);
+	__clear_bit(fid->fid_index - fid_family->start_index,
+		    fid_family->fids_bitmap);
+	kfree(fid);
 }
 
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_get(struct mlxsw_sp *mlxsw_sp, u16 vid)
@@ -985,6 +1106,12 @@ struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_get(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_sp_fid_get(mlxsw_sp, MLXSW_SP_FID_TYPE_8021D, &br_ifindex);
 }
 
+struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_lookup(struct mlxsw_sp *mlxsw_sp,
+					       u16 vid)
+{
+	return mlxsw_sp_fid_lookup(mlxsw_sp, MLXSW_SP_FID_TYPE_8021Q, &vid);
+}
+
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021d_lookup(struct mlxsw_sp *mlxsw_sp,
 					       int br_ifindex)
 {
@@ -1061,8 +1188,7 @@ static int mlxsw_sp_fid_family_register(struct mlxsw_sp *mlxsw_sp,
 
 	fid_family->mlxsw_sp = mlxsw_sp;
 	INIT_LIST_HEAD(&fid_family->fids_list);
-	fid_family->fids_bitmap = kcalloc(BITS_TO_LONGS(nr_fids),
-					  sizeof(unsigned long), GFP_KERNEL);
+	fid_family->fids_bitmap = bitmap_zalloc(nr_fids, GFP_KERNEL);
 	if (!fid_family->fids_bitmap) {
 		err = -ENOMEM;
 		goto err_alloc_fids_bitmap;
@@ -1079,7 +1205,7 @@ static int mlxsw_sp_fid_family_register(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 
 err_fid_flood_tables_init:
-	kfree(fid_family->fids_bitmap);
+	bitmap_free(fid_family->fids_bitmap);
 err_alloc_fids_bitmap:
 	kfree(fid_family);
 	return err;
@@ -1090,7 +1216,7 @@ mlxsw_sp_fid_family_unregister(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_fid_family *fid_family)
 {
 	mlxsw_sp->fid_core->fid_family_arr[fid_family->type] = NULL;
-	kfree(fid_family->fids_bitmap);
+	bitmap_free(fid_family->fids_bitmap);
 	WARN_ON_ONCE(!list_empty(&fid_family->fids_list));
 	kfree(fid_family);
 }
@@ -1126,9 +1252,13 @@ int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp)
 		return -ENOMEM;
 	mlxsw_sp->fid_core = fid_core;
 
+	err = rhashtable_init(&fid_core->fid_ht, &mlxsw_sp_fid_ht_params);
+	if (err)
+		goto err_rhashtable_fid_init;
+
 	err = rhashtable_init(&fid_core->vni_ht, &mlxsw_sp_fid_vni_ht_params);
 	if (err)
-		goto err_rhashtable_init;
+		goto err_rhashtable_vni_init;
 
 	fid_core->port_fid_mappings = kcalloc(max_ports, sizeof(unsigned int),
 					      GFP_KERNEL);
@@ -1157,7 +1287,9 @@ err_fid_ops_register:
 	kfree(fid_core->port_fid_mappings);
 err_alloc_port_fid_mappings:
 	rhashtable_destroy(&fid_core->vni_ht);
-err_rhashtable_init:
+err_rhashtable_vni_init:
+	rhashtable_destroy(&fid_core->fid_ht);
+err_rhashtable_fid_init:
 	kfree(fid_core);
 	return err;
 }
@@ -1172,5 +1304,6 @@ void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp)
 					       fid_core->fid_family_arr[i]);
 	kfree(fid_core->port_fid_mappings);
 	rhashtable_destroy(&fid_core->vni_ht);
+	rhashtable_destroy(&fid_core->fid_ht);
 	kfree(fid_core);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8d211972c5e9..15f804453cd6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -17,13 +17,13 @@
 static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_acl_block *block,
 					 struct mlxsw_sp_acl_rule_info *rulei,
-					 struct tcf_exts *exts,
+					 struct flow_action *flow_action,
 					 struct netlink_ext_ack *extack)
 {
-	const struct tc_action *a;
+	const struct flow_action_entry *act;
 	int err, i;
 
-	if (!tcf_exts_has_actions(exts))
+	if (!flow_action_has_entries(flow_action))
 		return 0;
 
 	/* Count action is inserted first */
@@ -31,27 +31,31 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	tcf_exts_for_each_action(i, a, exts) {
-		if (is_tcf_gact_ok(a)) {
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_ACCEPT:
 			err = mlxsw_sp_acl_rulei_act_terminate(rulei);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append terminate action");
 				return err;
 			}
-		} else if (is_tcf_gact_shot(a)) {
+			break;
+		case FLOW_ACTION_DROP:
 			err = mlxsw_sp_acl_rulei_act_drop(rulei);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action");
 				return err;
 			}
-		} else if (is_tcf_gact_trap(a)) {
+			break;
+		case FLOW_ACTION_TRAP:
 			err = mlxsw_sp_acl_rulei_act_trap(rulei);
 			if (err) {
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append trap action");
 				return err;
 			}
-		} else if (is_tcf_gact_goto_chain(a)) {
-			u32 chain_index = tcf_gact_goto_chain_index(a);
+			break;
+		case FLOW_ACTION_GOTO: {
+			u32 chain_index = act->chain_index;
 			struct mlxsw_sp_acl_ruleset *ruleset;
 			u16 group_id;
 
@@ -67,7 +71,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 				NL_SET_ERR_MSG_MOD(extack, "Cannot append jump action");
 				return err;
 			}
-		} else if (is_tcf_mirred_egress_redirect(a)) {
+			}
+			break;
+		case FLOW_ACTION_REDIRECT: {
 			struct net_device *out_dev;
 			struct mlxsw_sp_fid *fid;
 			u16 fid_index;
@@ -79,29 +85,33 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			if (err)
 				return err;
 
-			out_dev = tcf_mirred_dev(a);
+			out_dev = act->dev;
 			err = mlxsw_sp_acl_rulei_act_fwd(mlxsw_sp, rulei,
 							 out_dev, extack);
 			if (err)
 				return err;
-		} else if (is_tcf_mirred_egress_mirror(a)) {
-			struct net_device *out_dev = tcf_mirred_dev(a);
+			}
+			break;
+		case FLOW_ACTION_MIRRED: {
+			struct net_device *out_dev = act->dev;
 
 			err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei,
 							    block, out_dev,
 							    extack);
 			if (err)
 				return err;
-		} else if (is_tcf_vlan(a)) {
-			u16 proto = be16_to_cpu(tcf_vlan_push_proto(a));
-			u32 action = tcf_vlan_action(a);
-			u8 prio = tcf_vlan_push_prio(a);
-			u16 vid = tcf_vlan_push_vid(a);
+			}
+			break;
+		case FLOW_ACTION_VLAN_MANGLE: {
+			u16 proto = be16_to_cpu(act->vlan.proto);
+			u8 prio = act->vlan.prio;
+			u16 vid = act->vlan.vid;
 
 			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
-							   action, vid,
+							   act->id, vid,
 							   proto, prio, extack);
-		} else {
+			}
+		default:
 			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
@@ -113,59 +123,49 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei,
 				       struct tc_cls_flower_offload *f)
 {
-	struct flow_dissector_key_ipv4_addrs *key =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-					  f->key);
-	struct flow_dissector_key_ipv4_addrs *mask =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-					  f->mask);
+	struct flow_match_ipv4_addrs match;
+
+	flow_rule_match_ipv4_addrs(f->rule, &match);
 
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
-				       (char *) &key->src,
-				       (char *) &mask->src, 4);
+				       (char *) &match.key->src,
+				       (char *) &match.mask->src, 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
-				       (char *) &key->dst,
-				       (char *) &mask->dst, 4);
+				       (char *) &match.key->dst,
+				       (char *) &match.mask->dst, 4);
 }
 
 static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
 				       struct tc_cls_flower_offload *f)
 {
-	struct flow_dissector_key_ipv6_addrs *key =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-					  f->key);
-	struct flow_dissector_key_ipv6_addrs *mask =
-		skb_flow_dissector_target(f->dissector,
-					  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-					  f->mask);
+	struct flow_match_ipv6_addrs match;
+
+	flow_rule_match_ipv6_addrs(f->rule, &match);
 
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
-				       &key->src.s6_addr[0x0],
-				       &mask->src.s6_addr[0x0], 4);
+				       &match.key->src.s6_addr[0x0],
+				       &match.mask->src.s6_addr[0x0], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
-				       &key->src.s6_addr[0x4],
-				       &mask->src.s6_addr[0x4], 4);
+				       &match.key->src.s6_addr[0x4],
+				       &match.mask->src.s6_addr[0x4], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
-				       &key->src.s6_addr[0x8],
-				       &mask->src.s6_addr[0x8], 4);
+				       &match.key->src.s6_addr[0x8],
+				       &match.mask->src.s6_addr[0x8], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
-				       &key->src.s6_addr[0xC],
-				       &mask->src.s6_addr[0xC], 4);
+				       &match.key->src.s6_addr[0xC],
+				       &match.mask->src.s6_addr[0xC], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
-				       &key->dst.s6_addr[0x0],
-				       &mask->dst.s6_addr[0x0], 4);
+				       &match.key->dst.s6_addr[0x0],
+				       &match.mask->dst.s6_addr[0x0], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
-				       &key->dst.s6_addr[0x4],
-				       &mask->dst.s6_addr[0x4], 4);
+				       &match.key->dst.s6_addr[0x4],
+				       &match.mask->dst.s6_addr[0x4], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
-				       &key->dst.s6_addr[0x8],
-				       &mask->dst.s6_addr[0x8], 4);
+				       &match.key->dst.s6_addr[0x8],
+				       &match.mask->dst.s6_addr[0x8], 4);
 	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
-				       &key->dst.s6_addr[0xC],
-				       &mask->dst.s6_addr[0xC], 4);
+				       &match.key->dst.s6_addr[0xC],
+				       &match.mask->dst.s6_addr[0xC], 4);
 }
 
 static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
@@ -173,9 +173,10 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 				       struct tc_cls_flower_offload *f,
 				       u8 ip_proto)
 {
-	struct flow_dissector_key_ports *key, *mask;
+	const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_match_ports match;
 
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS))
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
@@ -184,16 +185,13 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 	}
 
-	key = skb_flow_dissector_target(f->dissector,
-					FLOW_DISSECTOR_KEY_PORTS,
-					f->key);
-	mask = skb_flow_dissector_target(f->dissector,
-					 FLOW_DISSECTOR_KEY_PORTS,
-					 f->mask);
+	flow_rule_match_ports(rule, &match);
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_L4_PORT,
-				       ntohs(key->dst), ntohs(mask->dst));
+				       ntohs(match.key->dst),
+				       ntohs(match.mask->dst));
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_L4_PORT,
-				       ntohs(key->src), ntohs(mask->src));
+				       ntohs(match.key->src),
+				       ntohs(match.mask->src));
 	return 0;
 }
 
@@ -202,9 +200,10 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 				     struct tc_cls_flower_offload *f,
 				     u8 ip_proto)
 {
-	struct flow_dissector_key_tcp *key, *mask;
+	const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_match_tcp match;
 
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP))
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP) {
@@ -213,14 +212,11 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 	}
 
-	key = skb_flow_dissector_target(f->dissector,
-					FLOW_DISSECTOR_KEY_TCP,
-					f->key);
-	mask = skb_flow_dissector_target(f->dissector,
-					 FLOW_DISSECTOR_KEY_TCP,
-					 f->mask);
+	flow_rule_match_tcp(rule, &match);
+
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_TCP_FLAGS,
-				       ntohs(key->flags), ntohs(mask->flags));
+				       ntohs(match.key->flags),
+				       ntohs(match.mask->flags));
 	return 0;
 }
 
@@ -229,9 +225,10 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 				    struct tc_cls_flower_offload *f,
 				    u16 n_proto)
 {
-	struct flow_dissector_key_ip *key, *mask;
+	const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_match_ip match;
 
-	if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP))
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP))
 		return 0;
 
 	if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) {
@@ -240,20 +237,18 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 		return -EINVAL;
 	}
 
-	key = skb_flow_dissector_target(f->dissector,
-					FLOW_DISSECTOR_KEY_IP,
-					f->key);
-	mask = skb_flow_dissector_target(f->dissector,
-					 FLOW_DISSECTOR_KEY_IP,
-					 f->mask);
+	flow_rule_match_ip(rule, &match);
+
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_TTL_,
-				       key->ttl, mask->ttl);
+				       match.key->ttl, match.mask->ttl);
 
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_ECN,
-				       key->tos & 0x3, mask->tos & 0x3);
+				       match.key->tos & 0x3,
+				       match.mask->tos & 0x3);
 
 	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_DSCP,
-				       key->tos >> 6, mask->tos >> 6);
+				       match.key->tos >> 6,
+				       match.mask->tos >> 6);
 
 	return 0;
 }
@@ -263,13 +258,15 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_rule_info *rulei,
 				 struct tc_cls_flower_offload *f)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0;
 	u16 n_proto_key = 0;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 	int err;
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
@@ -286,25 +283,19 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 
 	mlxsw_sp_acl_rulei_priority(rulei, f->common.prio);
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_CONTROL,
-						  f->key);
-		addr_type = key->addr_type;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->key);
-		struct flow_dissector_key_basic *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  f->mask);
-		n_proto_key = ntohs(key->n_proto);
-		n_proto_mask = ntohs(mask->n_proto);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		n_proto_key = ntohs(match.key->n_proto);
+		n_proto_mask = ntohs(match.mask->n_proto);
 
 		if (n_proto_key == ETH_P_ALL) {
 			n_proto_key = 0;
@@ -314,60 +305,53 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 					       MLXSW_AFK_ELEMENT_ETHERTYPE,
 					       n_proto_key, n_proto_mask);
 
-		ip_proto = key->ip_proto;
+		ip_proto = match.key->ip_proto;
 		mlxsw_sp_acl_rulei_keymask_u32(rulei,
 					       MLXSW_AFK_ELEMENT_IP_PROTO,
-					       key->ip_proto, mask->ip_proto);
+					       match.key->ip_proto,
+					       match.mask->ip_proto);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		struct flow_dissector_key_eth_addrs *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->key);
-		struct flow_dissector_key_eth_addrs *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
+		flow_rule_match_eth_addrs(rule, &match);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_DMAC_32_47,
-					       key->dst, mask->dst, 2);
+					       match.key->dst,
+					       match.mask->dst, 2);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_DMAC_0_31,
-					       key->dst + 2, mask->dst + 2, 4);
+					       match.key->dst + 2,
+					       match.mask->dst + 2, 4);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_SMAC_32_47,
-					       key->src, mask->src, 2);
+					       match.key->src,
+					       match.mask->src, 2);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
 					       MLXSW_AFK_ELEMENT_SMAC_0_31,
-					       key->src + 2, mask->src + 2, 4);
+					       match.key->src + 2,
+					       match.mask->src + 2, 4);
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *key =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->key);
-		struct flow_dissector_key_vlan *mask =
-			skb_flow_dissector_target(f->dissector,
-						  FLOW_DISSECTOR_KEY_VLAN,
-						  f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
 
+		flow_rule_match_vlan(rule, &match);
 		if (mlxsw_sp_acl_block_is_egress_bound(block)) {
 			NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress");
 			return -EOPNOTSUPP;
 		}
-		if (mask->vlan_id != 0)
+		if (match.mask->vlan_id != 0)
 			mlxsw_sp_acl_rulei_keymask_u32(rulei,
 						       MLXSW_AFK_ELEMENT_VID,
-						       key->vlan_id,
-						       mask->vlan_id);
-		if (mask->vlan_priority != 0)
+						       match.key->vlan_id,
+						       match.mask->vlan_id);
+		if (match.mask->vlan_priority != 0)
 			mlxsw_sp_acl_rulei_keymask_u32(rulei,
 						       MLXSW_AFK_ELEMENT_PCP,
-						       key->vlan_priority,
-						       mask->vlan_priority);
+						       match.key->vlan_priority,
+						       match.mask->vlan_priority);
 	}
 
 	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS)
@@ -387,7 +371,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts,
+	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei,
+					     &f->rule->action,
 					     f->common.extack);
 }
 
@@ -406,7 +391,7 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 	if (IS_ERR(ruleset))
 		return PTR_ERR(ruleset);
 
-	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie,
+	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie, NULL,
 					f->common.extack);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -486,7 +471,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rule_get_stats;
 
-	tcf_exts_stats_update(f->exts, bytes, packets, lastuse);
+	flow_stats_update(&f->stats, bytes, packets, lastuse);
 
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 00db26c96bf5..6400cd644b7a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -145,6 +145,7 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_ipip_entry *ipip_entry)
 {
 	u16 rif_index = mlxsw_sp_ipip_lb_rif_index(ipip_entry->ol_lb);
+	u16 ul_rif_id = mlxsw_sp_ipip_lb_ul_rif_id(ipip_entry->ol_lb);
 	char rtdp_pl[MLXSW_REG_RTDP_LEN];
 	struct ip_tunnel_parm parms;
 	unsigned int type_check;
@@ -157,6 +158,7 @@ mlxsw_sp_ipip_fib_entry_op_gre4_rtdp(struct mlxsw_sp *mlxsw_sp,
 	ikey = mlxsw_sp_ipip_parms4_ikey(parms);
 
 	mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_IPIP, tunnel_index);
+	mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_id);
 
 	type_check = has_ikey ?
 		MLXSW_REG_RTDP_IPIP_TYPE_CHECK_ALLOW_GRE_KEY :
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
index b5b54b41349a..1df164a4b06d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c
@@ -174,6 +174,20 @@ mlxsw_sp_nve_mc_record_ops_arr[] = {
 	[MLXSW_SP_L3_PROTO_IPV6] = &mlxsw_sp_nve_mc_record_ipv6_ops,
 };
 
+int mlxsw_sp_nve_learned_ip_resolve(struct mlxsw_sp *mlxsw_sp, u32 uip,
+				    enum mlxsw_sp_l3proto proto,
+				    union mlxsw_sp_l3addr *addr)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		addr->addr4 = cpu_to_be32(uip);
+		return 0;
+	default:
+		WARN_ON(1);
+		return -EINVAL;
+	}
+}
+
 static struct mlxsw_sp_nve_mc_list *
 mlxsw_sp_nve_mc_list_find(struct mlxsw_sp *mlxsw_sp,
 			  const struct mlxsw_sp_nve_mc_list_key *key)
@@ -253,8 +267,8 @@ mlxsw_sp_nve_mc_record_create(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_nve_mc_record *mc_record;
 	int err;
 
-	mc_record = kzalloc(sizeof(*mc_record) + num_max_entries *
-			    sizeof(struct mlxsw_sp_nve_mc_entry), GFP_KERNEL);
+	mc_record = kzalloc(struct_size(mc_record, entries, num_max_entries),
+			    GFP_KERNEL);
 	if (!mc_record)
 		return ERR_PTR(-ENOMEM);
 
@@ -775,6 +789,21 @@ static void mlxsw_sp_nve_fdb_flush_by_fid(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfdf), sfdf_pl);
 }
 
+static void mlxsw_sp_nve_fdb_clear_offload(struct mlxsw_sp *mlxsw_sp,
+					   const struct mlxsw_sp_fid *fid,
+					   const struct net_device *nve_dev,
+					   __be32 vni)
+{
+	const struct mlxsw_sp_nve_ops *ops;
+	enum mlxsw_sp_nve_type type;
+
+	if (WARN_ON(mlxsw_sp_fid_nve_type(fid, &type)))
+		return;
+
+	ops = mlxsw_sp->nve->nve_ops_arr[type];
+	ops->fdb_clear_offload(nve_dev, vni);
+}
+
 int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 			    struct mlxsw_sp_nve_params *params,
 			    struct netlink_ext_ack *extack)
@@ -787,14 +816,14 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 	ops = nve->nve_ops_arr[params->type];
 
 	if (!ops->can_offload(nve, params->dev, extack))
-		return -EOPNOTSUPP;
+		return -EINVAL;
 
 	memset(&config, 0, sizeof(config));
 	ops->nve_config(nve, params->dev, &config);
 	if (nve->num_nve_tunnels &&
 	    memcmp(&config, &nve->config, sizeof(config))) {
 		NL_SET_ERR_MSG_MOD(extack, "Conflicting NVE tunnels configuration");
-		return -EOPNOTSUPP;
+		return -EINVAL;
 	}
 
 	err = mlxsw_sp_nve_tunnel_init(mlxsw_sp, &config);
@@ -803,7 +832,8 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 		return err;
 	}
 
-	err = mlxsw_sp_fid_vni_set(fid, params->vni);
+	err = mlxsw_sp_fid_vni_set(fid, params->type, params->vni,
+				   params->dev->ifindex);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to set VNI on FID");
 		goto err_fid_vni_set;
@@ -811,8 +841,14 @@ int mlxsw_sp_nve_fid_enable(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid,
 
 	nve->config = config;
 
+	err = ops->fdb_replay(params->dev, params->vni, extack);
+	if (err)
+		goto err_fdb_replay;
+
 	return 0;
 
+err_fdb_replay:
+	mlxsw_sp_fid_vni_clear(fid);
 err_fid_vni_set:
 	mlxsw_sp_nve_tunnel_fini(mlxsw_sp);
 	return err;
@@ -822,9 +858,27 @@ void mlxsw_sp_nve_fid_disable(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_fid *fid)
 {
 	u16 fid_index = mlxsw_sp_fid_index(fid);
+	struct net_device *nve_dev;
+	int nve_ifindex;
+	__be32 vni;
 
 	mlxsw_sp_nve_flood_ip_flush(mlxsw_sp, fid);
 	mlxsw_sp_nve_fdb_flush_by_fid(mlxsw_sp, fid_index);
+
+	if (WARN_ON(mlxsw_sp_fid_nve_ifindex(fid, &nve_ifindex) ||
+		    mlxsw_sp_fid_vni(fid, &vni)))
+		goto out;
+
+	nve_dev = dev_get_by_index(&init_net, nve_ifindex);
+	if (!nve_dev)
+		goto out;
+
+	mlxsw_sp_nve_fdb_clear_offload(mlxsw_sp, fid, nve_dev, vni);
+	mlxsw_sp_fid_fdb_clear_offload(fid, nve_dev);
+
+	dev_put(nve_dev);
+
+out:
 	mlxsw_sp_fid_vni_clear(fid);
 	mlxsw_sp_nve_tunnel_fini(mlxsw_sp);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
index 4cc3297e13d6..0035640156a1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.h
@@ -28,6 +28,7 @@ struct mlxsw_sp_nve {
 	unsigned int num_nve_tunnels;	/* Protected by RTNL */
 	unsigned int num_max_mc_entries[MLXSW_SP_L3_PROTO_MAX];
 	u32 tunnel_index;
+	u16 ul_rif_index;	/* Reserved for Spectrum */
 };
 
 struct mlxsw_sp_nve_ops {
@@ -41,6 +42,9 @@ struct mlxsw_sp_nve_ops {
 	int (*init)(struct mlxsw_sp_nve *nve,
 		    const struct mlxsw_sp_nve_config *config);
 	void (*fini)(struct mlxsw_sp_nve *nve);
+	int (*fdb_replay)(const struct net_device *nve_dev, __be32 vni,
+			  struct netlink_ext_ack *extack);
+	void (*fdb_clear_offload)(const struct net_device *nve_dev, __be32 vni);
 };
 
 extern const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
index d21c7be5b1c9..93ccd9fc2266 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c
@@ -7,6 +7,7 @@
 #include <net/vxlan.h>
 
 #include "reg.h"
+#include "spectrum.h"
 #include "spectrum_nve.h"
 
 /* Eth (18B) | IPv6 (40B) | UDP (8B) | VxLAN (8B) | Eth (14B) | IPv6 (40B)
@@ -17,11 +18,12 @@
 #define MLXSW_SP_NVE_VXLAN_PARSING_DEPTH 128
 #define MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH 96
 
-#define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS	VXLAN_F_UDP_ZERO_CSUM_TX
+#define MLXSW_SP_NVE_VXLAN_SUPPORTED_FLAGS	(VXLAN_F_UDP_ZERO_CSUM_TX | \
+						 VXLAN_F_LEARN)
 
-static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
-					    const struct net_device *dev,
-					    struct netlink_ext_ack *extack)
+static bool mlxsw_sp_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
+					   const struct net_device *dev,
+					   struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_config *cfg = &vxlan->cfg;
@@ -61,11 +63,6 @@ static bool mlxsw_sp1_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
 		return false;
 	}
 
-	if (cfg->flags & VXLAN_F_LEARN) {
-		NL_SET_ERR_MSG_MOD(extack, "VxLAN: Learning is not supported");
-		return false;
-	}
-
 	if (!(cfg->flags & VXLAN_F_UDP_ZERO_CSUM_TX)) {
 		NL_SET_ERR_MSG_MOD(extack, "VxLAN: UDP checksum is not supported");
 		return false;
@@ -116,13 +113,30 @@ static int mlxsw_sp_nve_parsing_set(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mprs), mprs_pl);
 }
 
+static void
+mlxsw_sp_nve_vxlan_config_prepare(char *tngcr_pl,
+				  const struct mlxsw_sp_nve_config *config)
+{
+	u8 udp_sport;
+
+	mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, true,
+			     config->ttl);
+	/* VxLAN driver's default UDP source port range is 32768 (0x8000)
+	 * to 60999 (0xee47). Set the upper 8 bits of the UDP source port
+	 * to a random number between 0x80 and 0xee
+	 */
+	get_random_bytes(&udp_sport, sizeof(udp_sport));
+	udp_sport = (udp_sport % (0xee - 0x80 + 1)) + 0x80;
+	mlxsw_reg_tngcr_nve_udp_sport_prefix_set(tngcr_pl, udp_sport);
+	mlxsw_reg_tngcr_usipv4_set(tngcr_pl, be32_to_cpu(config->ul_sip.addr4));
+}
+
 static int
 mlxsw_sp1_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp,
 			       const struct mlxsw_sp_nve_config *config)
 {
 	char tngcr_pl[MLXSW_REG_TNGCR_LEN];
 	u16 ul_vr_id;
-	u8 udp_sport;
 	int err;
 
 	err = mlxsw_sp_router_tb_id_vr_id(mlxsw_sp, config->ul_tb_id,
@@ -130,18 +144,9 @@ mlxsw_sp1_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, true,
-			     config->ttl);
-	/* VxLAN driver's default UDP source port range is 32768 (0x8000)
-	 * to 60999 (0xee47). Set the upper 8 bits of the UDP source port
-	 * to a random number between 0x80 and 0xee
-	 */
-	get_random_bytes(&udp_sport, sizeof(udp_sport));
-	udp_sport = (udp_sport % (0xee - 0x80 + 1)) + 0x80;
-	mlxsw_reg_tngcr_nve_udp_sport_prefix_set(tngcr_pl, udp_sport);
+	mlxsw_sp_nve_vxlan_config_prepare(tngcr_pl, config);
 	mlxsw_reg_tngcr_learn_enable_set(tngcr_pl, config->learning_en);
 	mlxsw_reg_tngcr_underlay_virtual_router_set(tngcr_pl, ul_vr_id);
-	mlxsw_reg_tngcr_usipv4_set(tngcr_pl, be32_to_cpu(config->ul_sip.addr4));
 
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl);
 }
@@ -215,35 +220,157 @@ static void mlxsw_sp1_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 				 config->udp_dport);
 }
 
+static int
+mlxsw_sp_nve_vxlan_fdb_replay(const struct net_device *nve_dev, __be32 vni,
+			      struct netlink_ext_ack *extack)
+{
+	if (WARN_ON(!netif_is_vxlan(nve_dev)))
+		return -EINVAL;
+	return vxlan_fdb_replay(nve_dev, vni, &mlxsw_sp_switchdev_notifier,
+				extack);
+}
+
+static void
+mlxsw_sp_nve_vxlan_clear_offload(const struct net_device *nve_dev, __be32 vni)
+{
+	if (WARN_ON(!netif_is_vxlan(nve_dev)))
+		return;
+	vxlan_fdb_clear_offload(nve_dev, vni);
+}
+
 const struct mlxsw_sp_nve_ops mlxsw_sp1_nve_vxlan_ops = {
 	.type		= MLXSW_SP_NVE_TYPE_VXLAN,
-	.can_offload	= mlxsw_sp1_nve_vxlan_can_offload,
+	.can_offload	= mlxsw_sp_nve_vxlan_can_offload,
 	.nve_config	= mlxsw_sp_nve_vxlan_config,
 	.init		= mlxsw_sp1_nve_vxlan_init,
 	.fini		= mlxsw_sp1_nve_vxlan_fini,
+	.fdb_replay	= mlxsw_sp_nve_vxlan_fdb_replay,
+	.fdb_clear_offload = mlxsw_sp_nve_vxlan_clear_offload,
 };
 
-static bool mlxsw_sp2_nve_vxlan_can_offload(const struct mlxsw_sp_nve *nve,
-					    const struct net_device *dev,
-					    struct netlink_ext_ack *extack)
+static bool mlxsw_sp2_nve_vxlan_learning_set(struct mlxsw_sp *mlxsw_sp,
+					     bool learning_en)
+{
+	char tnpc_pl[MLXSW_REG_TNPC_LEN];
+
+	mlxsw_reg_tnpc_pack(tnpc_pl, MLXSW_REG_TNPC_TUNNEL_PORT_NVE,
+			    learning_en);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tnpc), tnpc_pl);
+}
+
+static int
+mlxsw_sp2_nve_vxlan_config_set(struct mlxsw_sp *mlxsw_sp,
+			       const struct mlxsw_sp_nve_config *config)
+{
+	char tngcr_pl[MLXSW_REG_TNGCR_LEN];
+	u16 ul_rif_index;
+	int err;
+
+	err = mlxsw_sp_router_ul_rif_get(mlxsw_sp, config->ul_tb_id,
+					 &ul_rif_index);
+	if (err)
+		return err;
+	mlxsw_sp->nve->ul_rif_index = ul_rif_index;
+
+	err = mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, config->learning_en);
+	if (err)
+		goto err_vxlan_learning_set;
+
+	mlxsw_sp_nve_vxlan_config_prepare(tngcr_pl, config);
+	mlxsw_reg_tngcr_underlay_rif_set(tngcr_pl, ul_rif_index);
+
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl);
+	if (err)
+		goto err_tngcr_write;
+
+	return 0;
+
+err_tngcr_write:
+	mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, false);
+err_vxlan_learning_set:
+	mlxsw_sp_router_ul_rif_put(mlxsw_sp, ul_rif_index);
+	return err;
+}
+
+static void mlxsw_sp2_nve_vxlan_config_clear(struct mlxsw_sp *mlxsw_sp)
 {
-	return false;
+	char tngcr_pl[MLXSW_REG_TNGCR_LEN];
+
+	mlxsw_reg_tngcr_pack(tngcr_pl, MLXSW_REG_TNGCR_TYPE_VXLAN, false, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(tngcr), tngcr_pl);
+	mlxsw_sp2_nve_vxlan_learning_set(mlxsw_sp, false);
+	mlxsw_sp_router_ul_rif_put(mlxsw_sp, mlxsw_sp->nve->ul_rif_index);
+}
+
+static int mlxsw_sp2_nve_vxlan_rtdp_set(struct mlxsw_sp *mlxsw_sp,
+					unsigned int tunnel_index,
+					u16 ul_rif_index)
+{
+	char rtdp_pl[MLXSW_REG_RTDP_LEN];
+
+	mlxsw_reg_rtdp_pack(rtdp_pl, MLXSW_REG_RTDP_TYPE_NVE, tunnel_index);
+	mlxsw_reg_rtdp_egress_router_interface_set(rtdp_pl, ul_rif_index);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtdp), rtdp_pl);
 }
 
 static int mlxsw_sp2_nve_vxlan_init(struct mlxsw_sp_nve *nve,
 				    const struct mlxsw_sp_nve_config *config)
 {
-	return -EOPNOTSUPP;
+	struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
+	int err;
+
+	err = mlxsw_sp_nve_parsing_set(mlxsw_sp,
+				       MLXSW_SP_NVE_VXLAN_PARSING_DEPTH,
+				       config->udp_dport);
+	if (err)
+		return err;
+
+	err = mlxsw_sp2_nve_vxlan_config_set(mlxsw_sp, config);
+	if (err)
+		goto err_config_set;
+
+	err = mlxsw_sp2_nve_vxlan_rtdp_set(mlxsw_sp, nve->tunnel_index,
+					   nve->ul_rif_index);
+	if (err)
+		goto err_rtdp_set;
+
+	err = mlxsw_sp_router_nve_promote_decap(mlxsw_sp, config->ul_tb_id,
+						config->ul_proto,
+						&config->ul_sip,
+						nve->tunnel_index);
+	if (err)
+		goto err_promote_decap;
+
+	return 0;
+
+err_promote_decap:
+err_rtdp_set:
+	mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
+err_config_set:
+	mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
+				 config->udp_dport);
+	return err;
 }
 
 static void mlxsw_sp2_nve_vxlan_fini(struct mlxsw_sp_nve *nve)
 {
+	struct mlxsw_sp_nve_config *config = &nve->config;
+	struct mlxsw_sp *mlxsw_sp = nve->mlxsw_sp;
+
+	mlxsw_sp_router_nve_demote_decap(mlxsw_sp, config->ul_tb_id,
+					 config->ul_proto, &config->ul_sip);
+	mlxsw_sp2_nve_vxlan_config_clear(mlxsw_sp);
+	mlxsw_sp_nve_parsing_set(mlxsw_sp, MLXSW_SP_NVE_DEFAULT_PARSING_DEPTH,
+				 config->udp_dport);
 }
 
 const struct mlxsw_sp_nve_ops mlxsw_sp2_nve_vxlan_ops = {
 	.type		= MLXSW_SP_NVE_TYPE_VXLAN,
-	.can_offload	= mlxsw_sp2_nve_vxlan_can_offload,
+	.can_offload	= mlxsw_sp_nve_vxlan_can_offload,
 	.nve_config	= mlxsw_sp_nve_vxlan_config,
 	.init		= mlxsw_sp2_nve_vxlan_init,
 	.fini		= mlxsw_sp2_nve_vxlan_fini,
+	.fdb_replay	= mlxsw_sp_nve_vxlan_fdb_replay,
+	.fdb_clear_offload = mlxsw_sp_nve_vxlan_clear_offload,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 6ebf99cc3154..902e766a8ed3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -15,6 +15,7 @@
 #include <linux/gcd.h>
 #include <linux/random.h>
 #include <linux/if_macvlan.h>
+#include <linux/refcount.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -70,6 +71,8 @@ struct mlxsw_sp_router {
 	bool aborted;
 	struct notifier_block fib_nb;
 	struct notifier_block netevent_nb;
+	struct notifier_block inetaddr_nb;
+	struct notifier_block inet6addr_nb;
 	const struct mlxsw_sp_rif_ops **rif_ops_arr;
 	const struct mlxsw_sp_ipip_ops **ipip_ops_arr;
 };
@@ -77,7 +80,7 @@ struct mlxsw_sp_router {
 struct mlxsw_sp_rif {
 	struct list_head nexthop_list;
 	struct list_head neigh_list;
-	struct net_device *dev;
+	struct net_device *dev; /* NULL for underlay RIF */
 	struct mlxsw_sp_fid *fid;
 	unsigned char addr[ETH_ALEN];
 	int mtu;
@@ -104,6 +107,7 @@ struct mlxsw_sp_rif_params {
 
 struct mlxsw_sp_rif_subport {
 	struct mlxsw_sp_rif common;
+	refcount_t ref_count;
 	union {
 		u16 system_port;
 		u16 lag_id;
@@ -116,6 +120,7 @@ struct mlxsw_sp_rif_ipip_lb {
 	struct mlxsw_sp_rif common;
 	struct mlxsw_sp_rif_ipip_lb_config lb_config;
 	u16 ul_vr_id; /* Reserved for Spectrum-2. */
+	u16 ul_rif_id; /* Reserved for Spectrum. */
 };
 
 struct mlxsw_sp_rif_params_ipip_lb {
@@ -136,6 +141,7 @@ struct mlxsw_sp_rif_ops {
 	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
 
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
 static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -358,6 +364,7 @@ enum mlxsw_sp_fib_entry_type {
 	MLXSW_SP_FIB_ENTRY_TYPE_REMOTE,
 	MLXSW_SP_FIB_ENTRY_TYPE_LOCAL,
 	MLXSW_SP_FIB_ENTRY_TYPE_TRAP,
+	MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE,
 
 	/* This is a special case of local delivery, where a packet should be
 	 * decapsulated on reception. Note that there is no corresponding ENCAP,
@@ -435,6 +442,8 @@ struct mlxsw_sp_vr {
 	struct mlxsw_sp_fib *fib4;
 	struct mlxsw_sp_fib *fib6;
 	struct mlxsw_sp_mr_table *mr_table[MLXSW_SP_L3_PROTO_MAX];
+	struct mlxsw_sp_rif *ul_rif;
+	refcount_t ul_rif_refcnt;
 };
 
 static const struct rhashtable_params mlxsw_sp_fib_ht_params;
@@ -1432,8 +1441,8 @@ mlxsw_sp_ipip_entry_ol_up_event(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int
-mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
-			struct mlxsw_sp_vr *ul_vr, bool enable)
+mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif, u16 ul_vr_id,
+			u16 ul_rif_id, bool enable)
 {
 	struct mlxsw_sp_rif_ipip_lb_config lb_cf = lb_rif->lb_config;
 	struct mlxsw_sp_rif *rif = &lb_rif->common;
@@ -1448,7 +1457,7 @@ mlxsw_sp_rif_ipip_lb_op(struct mlxsw_sp_rif_ipip_lb *lb_rif,
 				    rif->rif_index, rif->vr_id, rif->dev->mtu);
 		mlxsw_reg_ritr_loopback_ipip4_pack(ritr_pl, lb_cf.lb_ipipt,
 			    MLXSW_REG_RITR_LOOPBACK_IPIP_OPTIONS_GRE_KEY_PRESET,
-			    ul_vr->id, saddr4, lb_cf.okey);
+			    ul_vr_id, ul_rif_id, saddr4, lb_cf.okey);
 		break;
 
 	case MLXSW_SP_L3_PROTO_IPV6:
@@ -1463,14 +1472,13 @@ static int mlxsw_sp_netdevice_ipip_ol_update_mtu(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_sp_ipip_entry *ipip_entry;
 	struct mlxsw_sp_rif_ipip_lb *lb_rif;
-	struct mlxsw_sp_vr *ul_vr;
 	int err = 0;
 
 	ipip_entry = mlxsw_sp_ipip_entry_find_by_ol_dev(mlxsw_sp, ol_dev);
 	if (ipip_entry) {
 		lb_rif = ipip_entry->ol_lb;
-		ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id];
-		err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true);
+		err = mlxsw_sp_rif_ipip_lb_op(lb_rif, lb_rif->ul_vr_id,
+					      lb_rif->ul_rif_id, true);
 		if (err)
 			goto out;
 		lb_rif->common.mtu = ol_dev->mtu;
@@ -3806,13 +3814,11 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi)
 	struct mlxsw_sp_nexthop_group *nh_grp;
 	struct mlxsw_sp_nexthop *nh;
 	struct fib_nh *fib_nh;
-	size_t alloc_size;
 	int i;
 	int err;
 
-	alloc_size = sizeof(*nh_grp) +
-		     fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop);
-	nh_grp = kzalloc(alloc_size, GFP_KERNEL);
+	nh_grp = kzalloc(struct_size(nh_grp, nexthops, fi->fib_nhs),
+			 GFP_KERNEL);
 	if (!nh_grp)
 		return ERR_PTR(-ENOMEM);
 	nh_grp->priv = fi;
@@ -3921,6 +3927,7 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry)
 		return !!nh_group->adj_index_valid;
 	case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL:
 		return !!nh_group->nh_rif;
+	case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE:
 	case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP:
 	case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP:
 		return true;
@@ -3956,6 +3963,7 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 	int i;
 
 	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
+	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP ||
 	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) {
 		nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD;
@@ -3997,7 +4005,8 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
 	fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
 				  common);
 
-	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) {
+	if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL ||
+	    fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) {
 		list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
 				 list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
 		return;
@@ -4165,6 +4174,19 @@ static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
 }
 
+static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp,
+					   struct mlxsw_sp_fib_entry *fib_entry,
+					   enum mlxsw_reg_ralue_op op)
+{
+	enum mlxsw_reg_ralue_trap_action trap_action;
+	char ralue_pl[MLXSW_REG_RALUE_LEN];
+
+	trap_action = MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR;
+	mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op);
+	mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, 0, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl);
+}
+
 static int
 mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_fib_entry *fib_entry,
@@ -4204,6 +4226,8 @@ static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp,
 		return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op);
 	case MLXSW_SP_FIB_ENTRY_TYPE_TRAP:
 		return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op);
+	case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE:
+		return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op);
 	case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP:
 		return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp,
 							fib_entry, op);
@@ -4272,8 +4296,10 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 	case RTN_BROADCAST:
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
 		return 0;
+	case RTN_BLACKHOLE:
+		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE;
+		return 0;
 	case RTN_UNREACHABLE: /* fall through */
-	case RTN_BLACKHOLE: /* fall through */
 	case RTN_PROHIBIT:
 		/* Packets hitting these routes need to be trapped, but
 		 * can do so with a lower priority than packets directed
@@ -5038,13 +5064,11 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_nexthop_group *nh_grp;
 	struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
 	struct mlxsw_sp_nexthop *nh;
-	size_t alloc_size;
 	int i = 0;
 	int err;
 
-	alloc_size = sizeof(*nh_grp) +
-		     fib6_entry->nrt6 * sizeof(struct mlxsw_sp_nexthop);
-	nh_grp = kzalloc(alloc_size, GFP_KERNEL);
+	nh_grp = kzalloc(struct_size(nh_grp, nexthops, fib6_entry->nrt6),
+			 GFP_KERNEL);
 	if (!nh_grp)
 		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&nh_grp->fib_list);
@@ -5222,6 +5246,8 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
 	 */
 	if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP;
+	else if (rt->fib6_type == RTN_BLACKHOLE)
+		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE;
 	else if (rt->fib6_flags & RTF_REJECT)
 		fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL;
 	else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt))
@@ -6116,7 +6142,7 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 
 	mlxsw_reg_ritr_rif_pack(ritr_pl, rif);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
-	if (WARN_ON_ONCE(err))
+	if (err)
 		return err;
 
 	mlxsw_reg_ritr_enable_set(ritr_pl, false);
@@ -6219,10 +6245,12 @@ static struct mlxsw_sp_rif *mlxsw_sp_rif_alloc(size_t rif_size, u16 rif_index,
 
 	INIT_LIST_HEAD(&rif->nexthop_list);
 	INIT_LIST_HEAD(&rif->neigh_list);
-	ether_addr_copy(rif->addr, l3_dev->dev_addr);
-	rif->mtu = l3_dev->mtu;
+	if (l3_dev) {
+		ether_addr_copy(rif->addr, l3_dev->dev_addr);
+		rif->mtu = l3_dev->mtu;
+		rif->dev = l3_dev;
+	}
 	rif->vr_id = vr_id;
-	rif->dev = l3_dev;
 	rif->rif_index = rif_index;
 
 	return rif;
@@ -6246,7 +6274,19 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 
 u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 {
-	return lb_rif->ul_vr_id;
+	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(lb_rif->common.dev);
+	struct mlxsw_sp_vr *ul_vr;
+
+	ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL);
+	if (WARN_ON(IS_ERR(ul_vr)))
+		return 0;
+
+	return ul_vr->id;
+}
+
+u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
+{
+	return lb_rif->ul_rif_id;
 }
 
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif)
@@ -6279,7 +6319,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	int i, err;
 
 	type = mlxsw_sp_dev_rif_type(mlxsw_sp, params->dev);
-	ops = mlxsw_sp->router->rif_ops_arr[type];
+	ops = mlxsw_sp->rif_ops_arr[type];
 
 	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id ? : RT_TABLE_MAIN, extack);
 	if (IS_ERR(vr))
@@ -6297,6 +6337,8 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		err = -ENOMEM;
 		goto err_rif_alloc;
 	}
+	dev_hold(rif->dev);
+	mlxsw_sp->router->rifs[rif_index] = rif;
 	rif->mlxsw_sp = mlxsw_sp;
 	rif->ops = ops;
 
@@ -6323,7 +6365,6 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	mlxsw_sp_rif_counters_alloc(rif);
-	mlxsw_sp->router->rifs[rif_index] = rif;
 
 	return rif;
 
@@ -6335,6 +6376,8 @@ err_configure:
 	if (fid)
 		mlxsw_sp_fid_put(fid);
 err_fid_get:
+	mlxsw_sp->router->rifs[rif_index] = NULL;
+	dev_put(rif->dev);
 	kfree(rif);
 err_rif_alloc:
 err_rif_index_alloc:
@@ -6343,7 +6386,7 @@ err_rif_index_alloc:
 	return ERR_PTR(err);
 }
 
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 {
 	const struct mlxsw_sp_rif_ops *ops = rif->ops;
 	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
@@ -6354,7 +6397,6 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_router_rif_gone_sync(mlxsw_sp, rif);
 	vr = &mlxsw_sp->router->vrs[rif->vr_id];
 
-	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
 	mlxsw_sp_rif_counters_free(rif);
 	for (i = 0; i < MLXSW_SP_L3_PROTO_MAX; i++)
 		mlxsw_sp_mr_rif_del(vr->mr_table[i], rif);
@@ -6362,6 +6404,8 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	if (fid)
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
+	mlxsw_sp->router->rifs[rif->rif_index] = NULL;
+	dev_put(rif->dev);
 	kfree(rif);
 	vr->rif_count--;
 	mlxsw_sp_vr_put(mlxsw_sp, vr);
@@ -6392,6 +6436,40 @@ mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 		params->system_port = mlxsw_sp_port->local_port;
 }
 
+static struct mlxsw_sp_rif_subport *
+mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
+{
+	return container_of(rif, struct mlxsw_sp_rif_subport, common);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_subport_get(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp_rif_params *params,
+			 struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, params->dev);
+	if (!rif)
+		return mlxsw_sp_rif_create(mlxsw_sp, params, extack);
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_inc(&rif_subport->ref_count);
+	return rif;
+}
+
+static void mlxsw_sp_rif_subport_put(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	if (!refcount_dec_and_test(&rif_subport->ref_count))
+		return;
+
+	mlxsw_sp_rif_destroy(rif);
+}
+
 static int
 mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 			       struct net_device *l3_dev,
@@ -6399,22 +6477,18 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_rif_params params = {
+		.dev = l3_dev,
+	};
 	u16 vid = mlxsw_sp_port_vlan->vid;
 	struct mlxsw_sp_rif *rif;
 	struct mlxsw_sp_fid *fid;
 	int err;
 
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
-	if (!rif) {
-		struct mlxsw_sp_rif_params params = {
-			.dev = l3_dev,
-		};
-
-		mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
-		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
-		if (IS_ERR(rif))
-			return PTR_ERR(rif);
-	}
+	mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
+	rif = mlxsw_sp_rif_subport_get(mlxsw_sp, &params, extack);
+	if (IS_ERR(rif))
+		return PTR_ERR(rif);
 
 	/* FID was already created, just take a reference */
 	fid = rif->ops->fid_get(rif, extack);
@@ -6441,6 +6515,7 @@ err_port_vid_learning_set:
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
 err_fid_port_vid_map:
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 	return err;
 }
 
@@ -6449,6 +6524,7 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
+	struct mlxsw_sp_rif *rif = mlxsw_sp_fid_rif(fid);
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
 	if (WARN_ON(mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_RFID))
@@ -6458,10 +6534,8 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 	mlxsw_sp_port_vid_stp_set(mlxsw_sp_port, vid, BR_STATE_BLOCKING);
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
-	/* If router port holds the last reference on the rFID, then the
-	 * associated Sub-port RIF will be destroyed.
-	 */
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 }
 
 static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
@@ -6497,8 +6571,8 @@ static int mlxsw_sp_inetaddr_port_event(struct net_device *port_dev,
 	    netif_is_ovs_port(port_dev))
 		return 0;
 
-	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event, 1,
-						 extack);
+	return mlxsw_sp_inetaddr_port_vlan_event(port_dev, port_dev, event,
+						 MLXSW_SP_DEFAULT_VID, extack);
 }
 
 static int __mlxsw_sp_inetaddr_lag_event(struct net_device *l3_dev,
@@ -6531,15 +6605,15 @@ static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
 	if (netif_is_bridge_port(lag_dev))
 		return 0;
 
-	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event, 1,
-					     extack);
+	return __mlxsw_sp_inetaddr_lag_event(lag_dev, lag_dev, event,
+					     MLXSW_SP_DEFAULT_VID, extack);
 }
 
-static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
+					  struct net_device *l3_dev,
 					  unsigned long event,
 					  struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
 	struct mlxsw_sp_rif_params params = {
 		.dev = l3_dev,
 	};
@@ -6560,7 +6634,8 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
 	return 0;
 }
 
-static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
+					struct net_device *vlan_dev,
 					unsigned long event,
 					struct netlink_ext_ack *extack)
 {
@@ -6577,7 +6652,8 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
 						     vid, extack);
 	else if (netif_is_bridge_master(real_dev) && br_vlan_enabled(real_dev))
-		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event, extack);
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, vlan_dev, event,
+						      extack);
 
 	return 0;
 }
@@ -6678,16 +6754,11 @@ void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			    mlxsw_sp_fid_index(rif->fid), false);
 }
 
-static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
+static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp,
+					   struct net_device *macvlan_dev,
 					   unsigned long event,
 					   struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp *mlxsw_sp;
-
-	mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
-	if (!mlxsw_sp)
-		return 0;
-
 	switch (event) {
 	case NETDEV_UP:
 		return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack);
@@ -6699,7 +6770,35 @@ static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
 	return 0;
 }
 
-static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
+static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
+					       struct net_device *dev,
+					       const unsigned char *dev_addr,
+					       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif *rif;
+	int i;
+
+	/* A RIF is not created for macvlan netdevs. Their MAC is used to
+	 * populate the FDB
+	 */
+	if (netif_is_macvlan(dev) || netif_is_l3_master(dev))
+		return 0;
+
+	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
+		rif = mlxsw_sp->router->rifs[i];
+		if (rif && rif->dev && rif->dev != dev &&
+		    !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr,
+					     mlxsw_sp->mac_mask)) {
+			NL_SET_ERR_MSG_MOD(extack, "All router interface MAC addresses must have the same prefix");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp,
+				     struct net_device *dev,
 				     unsigned long event,
 				     struct netlink_ext_ack *extack)
 {
@@ -6708,21 +6807,24 @@ static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 	else if (netif_is_lag_master(dev))
 		return mlxsw_sp_inetaddr_lag_event(dev, event, extack);
 	else if (netif_is_bridge_master(dev))
-		return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, dev, event,
+						      extack);
 	else if (is_vlan_dev(dev))
-		return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_vlan_event(mlxsw_sp, dev, event,
+						    extack);
 	else if (netif_is_macvlan(dev))
-		return mlxsw_sp_inetaddr_macvlan_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_macvlan_event(mlxsw_sp, dev, event,
+						       extack);
 	else
 		return 0;
 }
 
-int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-			    unsigned long event, void *ptr)
+static int mlxsw_sp_inetaddr_event(struct notifier_block *nb,
+				   unsigned long event, void *ptr)
 {
 	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
 	struct net_device *dev = ifa->ifa_dev->dev;
-	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_router *router;
 	struct mlxsw_sp_rif *rif;
 	int err = 0;
 
@@ -6730,15 +6832,12 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 	if (event == NETDEV_UP)
 		goto out;
 
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
-
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	router = container_of(nb, struct mlxsw_sp_router, inetaddr_nb);
+	rif = mlxsw_sp_rif_find_by_dev(router->mlxsw_sp, dev);
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, NULL);
+	err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, NULL);
 out:
 	return notifier_from_errno(err);
 }
@@ -6760,13 +6859,19 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, ivi->extack);
+	err = mlxsw_sp_router_port_check_rif_addr(mlxsw_sp, dev, dev->dev_addr,
+						  ivi->extack);
+	if (err)
+		goto out;
+
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack);
 out:
 	return notifier_from_errno(err);
 }
 
 struct mlxsw_sp_inet6addr_event_work {
 	struct work_struct work;
+	struct mlxsw_sp *mlxsw_sp;
 	struct net_device *dev;
 	unsigned long event;
 };
@@ -6775,21 +6880,18 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 {
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work =
 		container_of(work, struct mlxsw_sp_inet6addr_event_work, work);
+	struct mlxsw_sp *mlxsw_sp = inet6addr_work->mlxsw_sp;
 	struct net_device *dev = inet6addr_work->dev;
 	unsigned long event = inet6addr_work->event;
-	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_sp_rif *rif;
 
 	rtnl_lock();
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
 
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	__mlxsw_sp_inetaddr_event(dev, event, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL);
 out:
 	rtnl_unlock();
 	dev_put(dev);
@@ -6797,25 +6899,25 @@ out:
 }
 
 /* Called with rcu_read_lock() */
-int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
-			     unsigned long event, void *ptr)
+static int mlxsw_sp_inet6addr_event(struct notifier_block *nb,
+				    unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *if6 = (struct inet6_ifaddr *) ptr;
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work;
 	struct net_device *dev = if6->idev->dev;
+	struct mlxsw_sp_router *router;
 
 	/* NETDEV_UP event is handled by mlxsw_sp_inet6addr_valid_event */
 	if (event == NETDEV_UP)
 		return NOTIFY_DONE;
 
-	if (!mlxsw_sp_port_dev_lower_find_rcu(dev))
-		return NOTIFY_DONE;
-
 	inet6addr_work = kzalloc(sizeof(*inet6addr_work), GFP_ATOMIC);
 	if (!inet6addr_work)
 		return NOTIFY_BAD;
 
+	router = container_of(nb, struct mlxsw_sp_router, inet6addr_nb);
 	INIT_WORK(&inet6addr_work->work, mlxsw_sp_inet6addr_event_work);
+	inet6addr_work->mlxsw_sp = router->mlxsw_sp;
 	inet6addr_work->dev = dev;
 	inet6addr_work->event = event;
 	dev_hold(dev);
@@ -6841,7 +6943,12 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, i6vi->extack);
+	err = mlxsw_sp_router_port_check_rif_addr(mlxsw_sp, dev, dev->dev_addr,
+						  i6vi->extack);
+	if (err)
+		goto out;
+
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack);
 out:
 	return notifier_from_errno(err);
 }
@@ -6863,20 +6970,14 @@ static int mlxsw_sp_rif_edit(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
 }
 
-int mlxsw_sp_netdevice_router_port_event(struct net_device *dev)
+static int
+mlxsw_sp_router_port_change_event(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_rif *rif)
 {
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_rif *rif;
+	struct net_device *dev = rif->dev;
 	u16 fid_index;
 	int err;
 
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		return 0;
-
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!rif)
-		return 0;
 	fid_index = mlxsw_sp_fid_index(rif->fid);
 
 	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, rif->addr, fid_index, false);
@@ -6920,6 +7021,41 @@ err_rif_edit:
 	return err;
 }
 
+static int mlxsw_sp_router_port_pre_changeaddr_event(struct mlxsw_sp_rif *rif,
+			    struct netdev_notifier_pre_changeaddr_info *info)
+{
+	struct netlink_ext_ack *extack;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+	return mlxsw_sp_router_port_check_rif_addr(rif->mlxsw_sp, rif->dev,
+						   info->dev_addr, extack);
+}
+
+int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
+					 unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_rif *rif;
+
+	mlxsw_sp = mlxsw_sp_lower_get(dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	if (!rif)
+		return 0;
+
+	switch (event) {
+	case NETDEV_CHANGEMTU: /* fall through */
+	case NETDEV_CHANGEADDR:
+		return mlxsw_sp_router_port_change_event(mlxsw_sp, rif);
+	case NETDEV_PRE_CHANGEADDR:
+		return mlxsw_sp_router_port_pre_changeaddr_event(rif, ptr);
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 				  struct net_device *l3_dev,
 				  struct netlink_ext_ack *extack)
@@ -6931,9 +7067,10 @@ static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 	 */
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (rif)
-		__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, extack);
+		__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN,
+					  extack);
 
-	return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP, extack);
+	return __mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_UP, extack);
 }
 
 static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
@@ -6944,7 +7081,7 @@ static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (!rif)
 		return;
-	__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN, NULL);
 }
 
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
@@ -6998,18 +7135,13 @@ static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
 					     __mlxsw_sp_rif_macvlan_flush, rif);
 }
 
-static struct mlxsw_sp_rif_subport *
-mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
-{
-	return container_of(rif, struct mlxsw_sp_rif_subport, common);
-}
-
 static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif,
 				       const struct mlxsw_sp_rif_params *params)
 {
 	struct mlxsw_sp_rif_subport *rif_subport;
 
 	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_set(&rif_subport->ref_count, 1);
 	rif_subport->vid = params->vid;
 	rif_subport->lag = params->lag;
 	if (params->lag)
@@ -7164,11 +7296,15 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 			  struct netlink_ext_ack *extack)
 {
+	struct net_device *br_dev = rif->dev;
 	u16 vid;
 	int err;
 
 	if (is_vlan_dev(rif->dev)) {
 		vid = vlan_dev_vlan_id(rif->dev);
+		br_dev = vlan_dev_real_dev(rif->dev);
+		if (WARN_ON(!netif_is_bridge_master(br_dev)))
+			return ERR_PTR(-EINVAL);
 	} else {
 		err = br_vlan_get_pvid(rif->dev, &vid);
 		if (err < 0 || !vid) {
@@ -7177,7 +7313,7 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 		}
 	}
 
-	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
+	return mlxsw_sp_bridge_fid_get(rif->mlxsw_sp, br_dev, vid, extack);
 }
 
 static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
@@ -7194,7 +7330,8 @@ static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
 
 	info.addr = mac;
 	info.vid = vid;
-	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info,
+				 NULL);
 }
 
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_ops = {
@@ -7267,7 +7404,7 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
 			 struct netlink_ext_ack *extack)
 {
-	return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex);
+	return mlxsw_sp_bridge_fid_get(rif->mlxsw_sp, rif->dev, 0, extack);
 }
 
 static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
@@ -7281,7 +7418,8 @@ static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
 
 	info.addr = mac;
 	info.vid = 0;
-	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info,
+				 NULL);
 }
 
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
@@ -7293,6 +7431,15 @@ static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
 	.fdb_del		= mlxsw_sp_rif_fid_fdb_del,
 };
 
+static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_emu_ops = {
+	.type			= MLXSW_SP_RIF_TYPE_VLAN,
+	.rif_size		= sizeof(struct mlxsw_sp_rif),
+	.configure		= mlxsw_sp_rif_fid_configure,
+	.deconfigure		= mlxsw_sp_rif_fid_deconfigure,
+	.fid_get		= mlxsw_sp_rif_vlan_fid_get,
+	.fdb_del		= mlxsw_sp_rif_vlan_fdb_del,
+};
+
 static struct mlxsw_sp_rif_ipip_lb *
 mlxsw_sp_rif_ipip_lb_rif(struct mlxsw_sp_rif *rif)
 {
@@ -7313,7 +7460,7 @@ mlxsw_sp_rif_ipip_lb_setup(struct mlxsw_sp_rif *rif,
 }
 
 static int
-mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
+mlxsw_sp1_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
 	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev);
@@ -7325,11 +7472,12 @@ mlxsw_sp_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
 	if (IS_ERR(ul_vr))
 		return PTR_ERR(ul_vr);
 
-	err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, true);
+	err = mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr->id, 0, true);
 	if (err)
 		goto err_loopback_op;
 
 	lb_rif->ul_vr_id = ul_vr->id;
+	lb_rif->ul_rif_id = 0;
 	++ul_vr->rif_count;
 	return 0;
 
@@ -7338,32 +7486,213 @@ err_loopback_op:
 	return err;
 }
 
-static void mlxsw_sp_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
+static void mlxsw_sp1_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
 {
 	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
 	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
 	struct mlxsw_sp_vr *ul_vr;
 
 	ul_vr = &mlxsw_sp->router->vrs[lb_rif->ul_vr_id];
-	mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr, false);
+	mlxsw_sp_rif_ipip_lb_op(lb_rif, ul_vr->id, 0, false);
 
 	--ul_vr->rif_count;
 	mlxsw_sp_vr_put(mlxsw_sp, ul_vr);
 }
 
-static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_ipip_lb_ops = {
+static const struct mlxsw_sp_rif_ops mlxsw_sp1_rif_ipip_lb_ops = {
+	.type			= MLXSW_SP_RIF_TYPE_IPIP_LB,
+	.rif_size		= sizeof(struct mlxsw_sp_rif_ipip_lb),
+	.setup                  = mlxsw_sp_rif_ipip_lb_setup,
+	.configure		= mlxsw_sp1_rif_ipip_lb_configure,
+	.deconfigure		= mlxsw_sp1_rif_ipip_lb_deconfigure,
+};
+
+const struct mlxsw_sp_rif_ops *mlxsw_sp1_rif_ops_arr[] = {
+	[MLXSW_SP_RIF_TYPE_SUBPORT]	= &mlxsw_sp_rif_subport_ops,
+	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_emu_ops,
+	[MLXSW_SP_RIF_TYPE_FID]		= &mlxsw_sp_rif_fid_ops,
+	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp1_rif_ipip_lb_ops,
+};
+
+static int
+mlxsw_sp_rif_ipip_lb_ul_rif_op(struct mlxsw_sp_rif *ul_rif, bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp;
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+
+	mlxsw_reg_ritr_pack(ritr_pl, enable, MLXSW_REG_RITR_LOOPBACK_IF,
+			    ul_rif->rif_index, ul_rif->vr_id, IP_MAX_MTU);
+	mlxsw_reg_ritr_loopback_protocol_set(ritr_pl,
+					     MLXSW_REG_RITR_LOOPBACK_GENERIC);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_ul_rif_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr,
+		       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif *ul_rif;
+	u16 rif_index;
+	int err;
+
+	err = mlxsw_sp_rif_index_alloc(mlxsw_sp, &rif_index);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported router interfaces");
+		return ERR_PTR(err);
+	}
+
+	ul_rif = mlxsw_sp_rif_alloc(sizeof(*ul_rif), rif_index, vr->id, NULL);
+	if (!ul_rif)
+		return ERR_PTR(-ENOMEM);
+
+	mlxsw_sp->router->rifs[rif_index] = ul_rif;
+	ul_rif->mlxsw_sp = mlxsw_sp;
+	err = mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, true);
+	if (err)
+		goto ul_rif_op_err;
+
+	return ul_rif;
+
+ul_rif_op_err:
+	mlxsw_sp->router->rifs[rif_index] = NULL;
+	kfree(ul_rif);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_ul_rif_destroy(struct mlxsw_sp_rif *ul_rif)
+{
+	struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp;
+
+	mlxsw_sp_rif_ipip_lb_ul_rif_op(ul_rif, false);
+	mlxsw_sp->router->rifs[ul_rif->rif_index] = NULL;
+	kfree(ul_rif);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 tb_id,
+		    struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_vr *vr;
+	int err;
+
+	vr = mlxsw_sp_vr_get(mlxsw_sp, tb_id, extack);
+	if (IS_ERR(vr))
+		return ERR_CAST(vr);
+
+	if (refcount_inc_not_zero(&vr->ul_rif_refcnt))
+		return vr->ul_rif;
+
+	vr->ul_rif = mlxsw_sp_ul_rif_create(mlxsw_sp, vr, extack);
+	if (IS_ERR(vr->ul_rif)) {
+		err = PTR_ERR(vr->ul_rif);
+		goto err_ul_rif_create;
+	}
+
+	vr->rif_count++;
+	refcount_set(&vr->ul_rif_refcnt, 1);
+
+	return vr->ul_rif;
+
+err_ul_rif_create:
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+	return ERR_PTR(err);
+}
+
+static void mlxsw_sp_ul_rif_put(struct mlxsw_sp_rif *ul_rif)
+{
+	struct mlxsw_sp *mlxsw_sp = ul_rif->mlxsw_sp;
+	struct mlxsw_sp_vr *vr;
+
+	vr = &mlxsw_sp->router->vrs[ul_rif->vr_id];
+
+	if (!refcount_dec_and_test(&vr->ul_rif_refcnt))
+		return;
+
+	vr->rif_count--;
+	mlxsw_sp_ul_rif_destroy(ul_rif);
+	mlxsw_sp_vr_put(mlxsw_sp, vr);
+}
+
+int mlxsw_sp_router_ul_rif_get(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
+			       u16 *ul_rif_index)
+{
+	struct mlxsw_sp_rif *ul_rif;
+
+	ASSERT_RTNL();
+
+	ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL);
+	if (IS_ERR(ul_rif))
+		return PTR_ERR(ul_rif);
+	*ul_rif_index = ul_rif->rif_index;
+
+	return 0;
+}
+
+void mlxsw_sp_router_ul_rif_put(struct mlxsw_sp *mlxsw_sp, u16 ul_rif_index)
+{
+	struct mlxsw_sp_rif *ul_rif;
+
+	ASSERT_RTNL();
+
+	ul_rif = mlxsw_sp->router->rifs[ul_rif_index];
+	if (WARN_ON(!ul_rif))
+		return;
+
+	mlxsw_sp_ul_rif_put(ul_rif);
+}
+
+static int
+mlxsw_sp2_rif_ipip_lb_configure(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
+	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(rif->dev);
+	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+	struct mlxsw_sp_rif *ul_rif;
+	int err;
+
+	ul_rif = mlxsw_sp_ul_rif_get(mlxsw_sp, ul_tb_id, NULL);
+	if (IS_ERR(ul_rif))
+		return PTR_ERR(ul_rif);
+
+	err = mlxsw_sp_rif_ipip_lb_op(lb_rif, 0, ul_rif->rif_index, true);
+	if (err)
+		goto err_loopback_op;
+
+	lb_rif->ul_vr_id = 0;
+	lb_rif->ul_rif_id = ul_rif->rif_index;
+
+	return 0;
+
+err_loopback_op:
+	mlxsw_sp_ul_rif_put(ul_rif);
+	return err;
+}
+
+static void mlxsw_sp2_rif_ipip_lb_deconfigure(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_ipip_lb *lb_rif = mlxsw_sp_rif_ipip_lb_rif(rif);
+	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
+	struct mlxsw_sp_rif *ul_rif;
+
+	ul_rif = mlxsw_sp_rif_by_index(mlxsw_sp, lb_rif->ul_rif_id);
+	mlxsw_sp_rif_ipip_lb_op(lb_rif, 0, lb_rif->ul_rif_id, false);
+	mlxsw_sp_ul_rif_put(ul_rif);
+}
+
+static const struct mlxsw_sp_rif_ops mlxsw_sp2_rif_ipip_lb_ops = {
 	.type			= MLXSW_SP_RIF_TYPE_IPIP_LB,
 	.rif_size		= sizeof(struct mlxsw_sp_rif_ipip_lb),
 	.setup                  = mlxsw_sp_rif_ipip_lb_setup,
-	.configure		= mlxsw_sp_rif_ipip_lb_configure,
-	.deconfigure		= mlxsw_sp_rif_ipip_lb_deconfigure,
+	.configure		= mlxsw_sp2_rif_ipip_lb_configure,
+	.deconfigure		= mlxsw_sp2_rif_ipip_lb_deconfigure,
 };
 
-static const struct mlxsw_sp_rif_ops *mlxsw_sp_rif_ops_arr[] = {
+const struct mlxsw_sp_rif_ops *mlxsw_sp2_rif_ops_arr[] = {
 	[MLXSW_SP_RIF_TYPE_SUBPORT]	= &mlxsw_sp_rif_subport_ops,
-	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_ops,
+	[MLXSW_SP_RIF_TYPE_VLAN]	= &mlxsw_sp_rif_vlan_emu_ops,
 	[MLXSW_SP_RIF_TYPE_FID]		= &mlxsw_sp_rif_fid_ops,
-	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp_rif_ipip_lb_ops,
+	[MLXSW_SP_RIF_TYPE_IPIP_LB]	= &mlxsw_sp2_rif_ipip_lb_ops,
 };
 
 static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp)
@@ -7376,8 +7705,6 @@ static int mlxsw_sp_rifs_init(struct mlxsw_sp *mlxsw_sp)
 	if (!mlxsw_sp->router->rifs)
 		return -ENOMEM;
 
-	mlxsw_sp->router->rif_ops_arr = mlxsw_sp_rif_ops_arr;
-
 	return 0;
 }
 
@@ -7552,6 +7879,16 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp->router = router;
 	router->mlxsw_sp = mlxsw_sp;
 
+	router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event;
+	err = register_inetaddr_notifier(&router->inetaddr_nb);
+	if (err)
+		goto err_register_inetaddr_notifier;
+
+	router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event;
+	err = register_inet6addr_notifier(&router->inet6addr_nb);
+	if (err)
+		goto err_register_inet6addr_notifier;
+
 	INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list);
 	err = __mlxsw_sp_router_init(mlxsw_sp);
 	if (err)
@@ -7637,6 +7974,10 @@ err_ipips_init:
 err_rifs_init:
 	__mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
+	unregister_inet6addr_notifier(&router->inet6addr_nb);
+err_register_inet6addr_notifier:
+	unregister_inetaddr_notifier(&router->inetaddr_nb);
+err_register_inetaddr_notifier:
 	kfree(mlxsw_sp->router);
 	return err;
 }
@@ -7654,5 +7995,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp_ipips_fini(mlxsw_sp);
 	mlxsw_sp_rifs_fini(mlxsw_sp);
 	__mlxsw_sp_router_fini(mlxsw_sp);
+	unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb);
+	unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb);
 	kfree(mlxsw_sp->router);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 3dbafdeaab2b..cc1de91e8217 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -29,6 +29,7 @@ struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
+u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif);
 u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
 const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index d965fd275c90..536c23c578c3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -305,7 +305,7 @@ mlxsw_sp_span_gretap4_route(const struct net_device *to_dev,
 
 	parms = mlxsw_sp_ipip_netdev_parms4(to_dev);
 	ip_tunnel_init_flow(&fl4, parms.iph.protocol, *daddrp, *saddrp,
-			    0, 0, parms.link, tun->fwmark);
+			    0, 0, parms.link, tun->fwmark, 0);
 
 	rt = ip_route_output_key(tun->net, &fl4);
 	if (IS_ERR(rt))
@@ -383,7 +383,7 @@ mlxsw_sp_span_entry_gretap4_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 }
 
 static const struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap4 = {
-	.can_handle = is_gretap_dev,
+	.can_handle = netif_is_gretap,
 	.parms = mlxsw_sp_span_entry_gretap4_parms,
 	.configure = mlxsw_sp_span_entry_gretap4_configure,
 	.deconfigure = mlxsw_sp_span_entry_gretap4_deconfigure,
@@ -484,7 +484,7 @@ mlxsw_sp_span_entry_gretap6_deconfigure(struct mlxsw_sp_span_entry *span_entry)
 
 static const
 struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = {
-	.can_handle = is_ip6gretap_dev,
+	.can_handle = netif_is_ip6gretap,
 	.parms = mlxsw_sp_span_entry_gretap6_parms,
 	.configure = mlxsw_sp_span_entry_gretap6_configure,
 	.deconfigure = mlxsw_sp_span_entry_gretap6_deconfigure,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 50080c60a279..50111f228d77 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -85,13 +85,11 @@ struct mlxsw_sp_bridge_ops {
 			   struct mlxsw_sp_bridge_port *bridge_port,
 			   struct mlxsw_sp_port *mlxsw_sp_port);
 	int (*vxlan_join)(struct mlxsw_sp_bridge_device *bridge_device,
-			  const struct net_device *vxlan_dev,
+			  const struct net_device *vxlan_dev, u16 vid,
 			  struct netlink_ext_ack *extack);
-	void (*vxlan_leave)(struct mlxsw_sp_bridge_device *bridge_device,
-			    const struct net_device *vxlan_dev);
 	struct mlxsw_sp_fid *
 		(*fid_get)(struct mlxsw_sp_bridge_device *bridge_device,
-			   u16 vid);
+			   u16 vid, struct netlink_ext_ack *extack);
 	struct mlxsw_sp_fid *
 		(*fid_lookup)(struct mlxsw_sp_bridge_device *bridge_device,
 			      u16 vid);
@@ -292,30 +290,6 @@ mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port)
 	kfree(bridge_port);
 }
 
-static bool
-mlxsw_sp_bridge_port_should_destroy(const struct mlxsw_sp_bridge_port *
-				    bridge_port)
-{
-	struct net_device *dev = bridge_port->dev;
-	struct mlxsw_sp *mlxsw_sp;
-
-	if (is_vlan_dev(dev))
-		mlxsw_sp = mlxsw_sp_lower_get(vlan_dev_real_dev(dev));
-	else
-		mlxsw_sp = mlxsw_sp_lower_get(dev);
-
-	/* In case ports were pulled from out of a bridged LAG, then
-	 * it's possible the reference count isn't zero, yet the bridge
-	 * port should be destroyed, as it's no longer an upper of ours.
-	 */
-	if (!mlxsw_sp && list_empty(&bridge_port->vlans_list))
-		return true;
-	else if (bridge_port->ref_count == 0)
-		return true;
-	else
-		return false;
-}
-
 static struct mlxsw_sp_bridge_port *
 mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge,
 			 struct net_device *brport_dev)
@@ -353,8 +327,7 @@ static void mlxsw_sp_bridge_port_put(struct mlxsw_sp_bridge *bridge,
 {
 	struct mlxsw_sp_bridge_device *bridge_device;
 
-	bridge_port->ref_count--;
-	if (!mlxsw_sp_bridge_port_should_destroy(bridge_port))
+	if (--bridge_port->ref_count != 0)
 		return;
 	bridge_device = bridge_port->bridge_device;
 	mlxsw_sp_bridge_port_destroy(bridge_port);
@@ -458,46 +431,6 @@ static void mlxsw_sp_bridge_vlan_put(struct mlxsw_sp_bridge_vlan *bridge_vlan)
 		mlxsw_sp_bridge_vlan_destroy(bridge_vlan);
 }
 
-static void mlxsw_sp_port_bridge_flags_get(struct mlxsw_sp_bridge *bridge,
-					   struct net_device *dev,
-					   unsigned long *brport_flags)
-{
-	struct mlxsw_sp_bridge_port *bridge_port;
-
-	bridge_port = mlxsw_sp_bridge_port_find(bridge, dev);
-	if (WARN_ON(!bridge_port))
-		return;
-
-	memcpy(brport_flags, &bridge_port->flags, sizeof(*brport_flags));
-}
-
-static int mlxsw_sp_port_attr_get(struct net_device *dev,
-				  struct switchdev_attr *attr)
-{
-	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(mlxsw_sp->base_mac);
-		memcpy(&attr->u.ppid.id, &mlxsw_sp->base_mac,
-		       attr->u.ppid.id_len);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
-		mlxsw_sp_port_bridge_flags_get(mlxsw_sp->bridge, attr->orig_dev,
-					       &attr->u.brport_flags);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
-		attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD |
-					       BR_MCAST_FLOOD;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 static int
 mlxsw_sp_port_bridge_vlan_stp_set(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct mlxsw_sp_bridge_vlan *bridge_vlan,
@@ -647,6 +580,17 @@ err_port_bridge_vlan_learning_set:
 	return err;
 }
 
+static int mlxsw_sp_port_attr_br_pre_flags_set(struct mlxsw_sp_port
+					       *mlxsw_sp_port,
+					       struct switchdev_trans *trans,
+					       unsigned long brport_flags)
+{
+	if (brport_flags & ~(BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int mlxsw_sp_port_attr_br_flags_set(struct mlxsw_sp_port *mlxsw_sp_port,
 					   struct switchdev_trans *trans,
 					   struct net_device *orig_dev,
@@ -893,6 +837,11 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 						       attr->orig_dev,
 						       attr->u.stp_state);
 		break;
+	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		err = mlxsw_sp_port_attr_br_pre_flags_set(mlxsw_sp_port,
+							  trans,
+							  attr->u.brport_flags);
+		break;
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
 		err = mlxsw_sp_port_attr_br_flags_set(mlxsw_sp_port, trans,
 						      attr->orig_dev,
@@ -935,7 +884,8 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev,
 
 static int
 mlxsw_sp_port_vlan_fid_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
-			    struct mlxsw_sp_bridge_port *bridge_port)
+			    struct mlxsw_sp_bridge_port *bridge_port,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_bridge_device *bridge_device;
@@ -945,7 +895,7 @@ mlxsw_sp_port_vlan_fid_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	int err;
 
 	bridge_device = bridge_port->bridge_device;
-	fid = bridge_device->ops->fid_get(bridge_device, vid);
+	fid = bridge_device->ops->fid_get(bridge_device, vid, extack);
 	if (IS_ERR(fid))
 		return PTR_ERR(fid);
 
@@ -1013,7 +963,8 @@ mlxsw_sp_port_pvid_determine(const struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int
 mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
-			       struct mlxsw_sp_bridge_port *bridge_port)
+			       struct mlxsw_sp_bridge_port *bridge_port,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_bridge_vlan *bridge_vlan;
@@ -1021,12 +972,11 @@ mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	int err;
 
 	/* No need to continue if only VLAN flags were changed */
-	if (mlxsw_sp_port_vlan->bridge_port) {
-		mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	if (mlxsw_sp_port_vlan->bridge_port)
 		return 0;
-	}
 
-	err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port);
+	err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port,
+					  extack);
 	if (err)
 		return err;
 
@@ -1103,16 +1053,29 @@ mlxsw_sp_port_vlan_bridge_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 static int
 mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port,
-			      u16 vid, bool is_untagged, bool is_pvid)
+			      u16 vid, bool is_untagged, bool is_pvid,
+			      struct netlink_ext_ack *extack)
 {
 	u16 pvid = mlxsw_sp_port_pvid_determine(mlxsw_sp_port, vid, is_pvid);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	u16 old_pvid = mlxsw_sp_port->pvid;
 	int err;
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_get(mlxsw_sp_port, vid);
-	if (IS_ERR(mlxsw_sp_port_vlan))
-		return PTR_ERR(mlxsw_sp_port_vlan);
+	/* The only valid scenario in which a port-vlan already exists, is if
+	 * the VLAN flags were changed and the port-vlan is associated with the
+	 * correct bridge port
+	 */
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
+	if (mlxsw_sp_port_vlan &&
+	    mlxsw_sp_port_vlan->bridge_port != bridge_port)
+		return -EEXIST;
+
+	if (!mlxsw_sp_port_vlan) {
+		mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port,
+							       vid);
+		if (IS_ERR(mlxsw_sp_port_vlan))
+			return PTR_ERR(mlxsw_sp_port_vlan);
+	}
 
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true,
 				     is_untagged);
@@ -1123,7 +1086,8 @@ mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	if (err)
 		goto err_port_pvid_set;
 
-	err = mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port);
+	err = mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port,
+					     extack);
 	if (err)
 		goto err_port_vlan_bridge_join;
 
@@ -1134,7 +1098,7 @@ err_port_vlan_bridge_join:
 err_port_pvid_set:
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
 err_port_vlan_set:
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 	return err;
 }
 
@@ -1173,7 +1137,8 @@ mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 				   const struct switchdev_obj_port_vlan *vlan,
-				   struct switchdev_trans *trans)
+				   struct switchdev_trans *trans,
+				   struct netlink_ext_ack *extack)
 {
 	bool flag_untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
 	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
@@ -1195,7 +1160,7 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		return err;
 	}
 
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_commit(trans))
 		return 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
@@ -1210,7 +1175,7 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 		err = mlxsw_sp_bridge_port_vlan_add(mlxsw_sp_port, bridge_port,
 						    vid, flag_untagged,
-						    flag_pvid);
+						    flag_pvid, extack);
 		if (err)
 			return err;
 	}
@@ -1244,7 +1209,7 @@ mlxsw_sp_bridge_port_fdb_flush(struct mlxsw_sp *mlxsw_sp,
 static enum mlxsw_reg_sfd_rec_policy mlxsw_sp_sfd_rec_policy(bool dynamic)
 {
 	return dynamic ? MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_INGRESS :
-			 MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY;
+			 MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_MLAG;
 }
 
 static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding)
@@ -1301,7 +1266,7 @@ out:
 static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				     const char *mac, u16 fid, bool adding,
 				     enum mlxsw_reg_sfd_rec_action action,
-				     bool dynamic)
+				     enum mlxsw_reg_sfd_rec_policy policy)
 {
 	char *sfd_pl;
 	u8 num_rec;
@@ -1312,8 +1277,7 @@ static int __mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		return -ENOMEM;
 
 	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
-	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
-			      mac, fid, action, local_port);
+	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, policy, mac, fid, action, local_port);
 	num_rec = mlxsw_reg_sfd_num_rec_get(sfd_pl);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
 	if (err)
@@ -1332,7 +1296,8 @@ static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				   bool dynamic)
 {
 	return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, local_port, mac, fid, adding,
-					 MLXSW_REG_SFD_REC_ACTION_NOP, dynamic);
+					 MLXSW_REG_SFD_REC_ACTION_NOP,
+					 mlxsw_sp_sfd_rec_policy(dynamic));
 }
 
 int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
@@ -1340,7 +1305,7 @@ int mlxsw_sp_rif_fdb_op(struct mlxsw_sp *mlxsw_sp, const char *mac, u16 fid,
 {
 	return __mlxsw_sp_port_fdb_uc_op(mlxsw_sp, 0, mac, fid, adding,
 					 MLXSW_REG_SFD_REC_ACTION_FORWARD_IP_ROUTER,
-					 false);
+					 MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY);
 }
 
 static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
@@ -1665,7 +1630,7 @@ static int mlxsw_sp_port_mdb_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	u16 fid_index;
 	int err = 0;
 
-	if (switchdev_trans_ph_prepare(trans))
+	if (switchdev_trans_ph_commit(trans))
 		return 0;
 
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
@@ -1779,7 +1744,8 @@ static void mlxsw_sp_span_respin_schedule(struct mlxsw_sp *mlxsw_sp)
 
 static int mlxsw_sp_port_obj_add(struct net_device *dev,
 				 const struct switchdev_obj *obj,
-				 struct switchdev_trans *trans)
+				 struct switchdev_trans *trans,
+				 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	const struct switchdev_obj_port_vlan *vlan;
@@ -1788,7 +1754,8 @@ static int mlxsw_sp_port_obj_add(struct net_device *dev,
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
-		err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans);
+		err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans,
+					      extack);
 
 		if (switchdev_trans_ph_prepare(trans)) {
 			/* The event is emitted before the changes are actually
@@ -1816,7 +1783,7 @@ static void
 mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port, u16 vid)
 {
-	u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : vid;
+	u16 pvid = mlxsw_sp_port->pvid == vid ? 0 : mlxsw_sp_port->pvid;
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
@@ -1826,7 +1793,7 @@ mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid);
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 }
 
 static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -1971,32 +1938,20 @@ static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
-	.switchdev_port_attr_get	= mlxsw_sp_port_attr_get,
-	.switchdev_port_attr_set	= mlxsw_sp_port_attr_set,
-	.switchdev_port_obj_add		= mlxsw_sp_port_obj_add,
-	.switchdev_port_obj_del		= mlxsw_sp_port_obj_del,
-};
-
 static int
 mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 				struct mlxsw_sp_bridge_port *bridge_port,
 				struct mlxsw_sp_port *mlxsw_sp_port,
 				struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-
 	if (is_vlan_dev(bridge_port->dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "Can not enslave a VLAN device to a VLAN-aware bridge");
 		return -EINVAL;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, 1);
-	if (WARN_ON(!mlxsw_sp_port_vlan))
-		return -EINVAL;
-
-	/* Let VLAN-aware bridge take care of its own VLANs */
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	/* Port is no longer usable as a router interface */
+	if (mlxsw_sp_port->default_vlan->fid)
+		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port->default_vlan);
 
 	return 0;
 }
@@ -2006,41 +1961,134 @@ mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 				 struct mlxsw_sp_bridge_port *bridge_port,
 				 struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
 	/* Make sure untagged frames are allowed to ingress */
-	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
+	mlxsw_sp_port_pvid_set(mlxsw_sp_port, MLXSW_SP_DEFAULT_VID);
 }
 
 static int
 mlxsw_sp_bridge_8021q_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
-				 const struct net_device *vxlan_dev,
+				 const struct net_device *vxlan_dev, u16 vid,
 				 struct netlink_ext_ack *extack)
 {
-	WARN_ON(1);
-	return -EINVAL;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	struct mlxsw_sp_nve_params params = {
+		.type = MLXSW_SP_NVE_TYPE_VXLAN,
+		.vni = vxlan->cfg.vni,
+		.dev = vxlan_dev,
+	};
+	struct mlxsw_sp_fid *fid;
+	int err;
+
+	/* If the VLAN is 0, we need to find the VLAN that is configured as
+	 * PVID and egress untagged on the bridge port of the VxLAN device.
+	 * It is possible no such VLAN exists
+	 */
+	if (!vid) {
+		err = mlxsw_sp_vxlan_mapped_vid(vxlan_dev, &vid);
+		if (err || !vid)
+			return err;
+	}
+
+	/* If no other port is member in the VLAN, then the FID does not exist.
+	 * NVE will be enabled on the FID once a port joins the VLAN
+	 */
+	fid = mlxsw_sp_fid_8021q_lookup(mlxsw_sp, vid);
+	if (!fid)
+		return 0;
+
+	if (mlxsw_sp_fid_vni_is_set(fid)) {
+		NL_SET_ERR_MSG_MOD(extack, "VNI is already set on FID");
+		err = -EINVAL;
+		goto err_vni_exists;
+	}
+
+	err = mlxsw_sp_nve_fid_enable(mlxsw_sp, fid, &params, extack);
+	if (err)
+		goto err_nve_fid_enable;
+
+	/* The tunnel port does not hold a reference on the FID. Only
+	 * local ports and the router port
+	 */
+	mlxsw_sp_fid_put(fid);
+
+	return 0;
+
+err_nve_fid_enable:
+err_vni_exists:
+	mlxsw_sp_fid_put(fid);
+	return err;
 }
 
-static void
-mlxsw_sp_bridge_8021q_vxlan_leave(struct mlxsw_sp_bridge_device *bridge_device,
-				  const struct net_device *vxlan_dev)
+static struct net_device *
+mlxsw_sp_bridge_8021q_vxlan_dev_find(struct net_device *br_dev, u16 vid)
 {
+	struct net_device *dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(br_dev, dev, iter) {
+		u16 pvid;
+		int err;
+
+		if (!netif_is_vxlan(dev))
+			continue;
+
+		err = mlxsw_sp_vxlan_mapped_vid(dev, &pvid);
+		if (err || pvid != vid)
+			continue;
+
+		return dev;
+	}
+
+	return NULL;
 }
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021q_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
-			      u16 vid)
+			      u16 vid, struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
+	struct net_device *vxlan_dev;
+	struct mlxsw_sp_fid *fid;
+	int err;
+
+	fid = mlxsw_sp_fid_8021q_get(mlxsw_sp, vid);
+	if (IS_ERR(fid))
+		return fid;
+
+	if (mlxsw_sp_fid_vni_is_set(fid))
+		return fid;
+
+	/* Find the VxLAN device that has the specified VLAN configured as
+	 * PVID and egress untagged. There can be at most one such device
+	 */
+	vxlan_dev = mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev,
+							 vid);
+	if (!vxlan_dev)
+		return fid;
+
+	if (!netif_running(vxlan_dev))
+		return fid;
+
+	err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid,
+					       extack);
+	if (err)
+		goto err_vxlan_join;
 
-	return mlxsw_sp_fid_8021q_get(mlxsw_sp, vid);
+	return fid;
+
+err_vxlan_join:
+	mlxsw_sp_fid_put(fid);
+	return ERR_PTR(err);
 }
 
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021q_fid_lookup(struct mlxsw_sp_bridge_device *bridge_device,
 				 u16 vid)
 {
-	WARN_ON(1);
-	return NULL;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
+
+	return mlxsw_sp_fid_8021q_lookup(mlxsw_sp, vid);
 }
 
 static u16
@@ -2054,7 +2102,6 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021q_ops = {
 	.port_join	= mlxsw_sp_bridge_8021q_port_join,
 	.port_leave	= mlxsw_sp_bridge_8021q_port_leave,
 	.vxlan_join	= mlxsw_sp_bridge_8021q_vxlan_join,
-	.vxlan_leave	= mlxsw_sp_bridge_8021q_vxlan_leave,
 	.fid_get	= mlxsw_sp_bridge_8021q_fid_get,
 	.fid_lookup	= mlxsw_sp_bridge_8021q_fid_lookup,
 	.fid_vid	= mlxsw_sp_bridge_8021q_fid_vid,
@@ -2087,7 +2134,7 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 	struct net_device *dev = bridge_port->dev;
 	u16 vid;
 
-	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1;
+	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (WARN_ON(!mlxsw_sp_port_vlan))
 		return -EINVAL;
@@ -2101,7 +2148,8 @@ mlxsw_sp_bridge_8021d_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 	if (mlxsw_sp_port_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 
-	return mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port);
+	return mlxsw_sp_port_vlan_bridge_join(mlxsw_sp_port_vlan, bridge_port,
+					      extack);
 }
 
 static void
@@ -2113,9 +2161,9 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 	struct net_device *dev = bridge_port->dev;
 	u16 vid;
 
-	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : 1;
+	vid = is_vlan_dev(dev) ? vlan_dev_vlan_id(dev) : MLXSW_SP_DEFAULT_VID;
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (!mlxsw_sp_port_vlan)
+	if (!mlxsw_sp_port_vlan || !mlxsw_sp_port_vlan->bridge_port)
 		return;
 
 	mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
@@ -2123,7 +2171,7 @@ mlxsw_sp_bridge_8021d_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 
 static int
 mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
-				 const struct net_device *vxlan_dev,
+				 const struct net_device *vxlan_dev, u16 vid,
 				 struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
@@ -2137,10 +2185,13 @@ mlxsw_sp_bridge_8021d_vxlan_join(struct mlxsw_sp_bridge_device *bridge_device,
 	int err;
 
 	fid = mlxsw_sp_fid_8021d_lookup(mlxsw_sp, bridge_device->dev->ifindex);
-	if (!fid)
+	if (!fid) {
+		NL_SET_ERR_MSG_MOD(extack, "Did not find a corresponding FID");
 		return -EINVAL;
+	}
 
 	if (mlxsw_sp_fid_vni_is_set(fid)) {
+		NL_SET_ERR_MSG_MOD(extack, "VNI is already set on FID");
 		err = -EINVAL;
 		goto err_vni_exists;
 	}
@@ -2162,29 +2213,9 @@ err_vni_exists:
 	return err;
 }
 
-static void
-mlxsw_sp_bridge_8021d_vxlan_leave(struct mlxsw_sp_bridge_device *bridge_device,
-				  const struct net_device *vxlan_dev)
-{
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
-	struct mlxsw_sp_fid *fid;
-
-	fid = mlxsw_sp_fid_8021d_lookup(mlxsw_sp, bridge_device->dev->ifindex);
-	if (WARN_ON(!fid))
-		return;
-
-	/* If the VxLAN device is down, then the FID does not have a VNI */
-	if (!mlxsw_sp_fid_vni_is_set(fid))
-		goto out;
-
-	mlxsw_sp_nve_fid_disable(mlxsw_sp, fid);
-out:
-	mlxsw_sp_fid_put(fid);
-}
-
 static struct mlxsw_sp_fid *
 mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
-			      u16 vid)
+			      u16 vid, struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(bridge_device->dev);
 	struct net_device *vxlan_dev;
@@ -2205,7 +2236,8 @@ mlxsw_sp_bridge_8021d_fid_get(struct mlxsw_sp_bridge_device *bridge_device,
 	if (!netif_running(vxlan_dev))
 		return fid;
 
-	err = mlxsw_sp_bridge_8021d_vxlan_join(bridge_device, vxlan_dev, NULL);
+	err = mlxsw_sp_bridge_8021d_vxlan_join(bridge_device, vxlan_dev, 0,
+					       extack);
 	if (err)
 		goto err_vxlan_join;
 
@@ -2240,7 +2272,6 @@ static const struct mlxsw_sp_bridge_ops mlxsw_sp_bridge_8021d_ops = {
 	.port_join	= mlxsw_sp_bridge_8021d_port_join,
 	.port_leave	= mlxsw_sp_bridge_8021d_port_leave,
 	.vxlan_join	= mlxsw_sp_bridge_8021d_vxlan_join,
-	.vxlan_leave	= mlxsw_sp_bridge_8021d_vxlan_leave,
 	.fid_get	= mlxsw_sp_bridge_8021d_fid_get,
 	.fid_lookup	= mlxsw_sp_bridge_8021d_fid_lookup,
 	.fid_vid	= mlxsw_sp_bridge_8021d_fid_vid,
@@ -2295,7 +2326,7 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev,
+			       const struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_bridge_device *bridge_device;
@@ -2304,20 +2335,102 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 	if (WARN_ON(!bridge_device))
 		return -EINVAL;
 
-	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, extack);
+	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
+					      extack);
 }
 
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *br_dev,
 				 const struct net_device *vxlan_dev)
 {
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	struct mlxsw_sp_fid *fid;
+
+	/* If the VxLAN device is down, then the FID does not have a VNI */
+	fid = mlxsw_sp_fid_lookup_by_vni(mlxsw_sp, vxlan->cfg.vni);
+	if (!fid)
+		return;
+
+	mlxsw_sp_nve_fid_disable(mlxsw_sp, fid);
+	mlxsw_sp_fid_put(fid);
+}
+
+struct mlxsw_sp_fid *mlxsw_sp_bridge_fid_get(struct mlxsw_sp *mlxsw_sp,
+					     const struct net_device *br_dev,
+					     u16 vid,
+					     struct netlink_ext_ack *extack)
+{
 	struct mlxsw_sp_bridge_device *bridge_device;
 
 	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
 	if (WARN_ON(!bridge_device))
-		return;
+		return ERR_PTR(-EINVAL);
+
+	return bridge_device->ops->fid_get(bridge_device, vid, extack);
+}
+
+static void
+mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
+				      enum mlxsw_sp_l3proto *proto,
+				      union mlxsw_sp_l3addr *addr)
+{
+	if (vxlan_addr->sa.sa_family == AF_INET) {
+		addr->addr4 = vxlan_addr->sin.sin_addr.s_addr;
+		*proto = MLXSW_SP_L3_PROTO_IPV4;
+	} else {
+		addr->addr6 = vxlan_addr->sin6.sin6_addr;
+		*proto = MLXSW_SP_L3_PROTO_IPV6;
+	}
+}
+
+static void
+mlxsw_sp_switchdev_addr_vxlan_convert(enum mlxsw_sp_l3proto proto,
+				      const union mlxsw_sp_l3addr *addr,
+				      union vxlan_addr *vxlan_addr)
+{
+	switch (proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		vxlan_addr->sa.sa_family = AF_INET;
+		vxlan_addr->sin.sin_addr.s_addr = addr->addr4;
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		vxlan_addr->sa.sa_family = AF_INET6;
+		vxlan_addr->sin6.sin6_addr = addr->addr6;
+		break;
+	}
+}
+
+static void mlxsw_sp_fdb_vxlan_call_notifiers(struct net_device *dev,
+					      const char *mac,
+					      enum mlxsw_sp_l3proto proto,
+					      union mlxsw_sp_l3addr *addr,
+					      __be32 vni, bool adding)
+{
+	struct switchdev_notifier_vxlan_fdb_info info;
+	struct vxlan_dev *vxlan = netdev_priv(dev);
+	enum switchdev_notifier_type type;
 
-	bridge_device->ops->vxlan_leave(bridge_device, vxlan_dev);
+	type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_BRIDGE :
+			SWITCHDEV_VXLAN_FDB_DEL_TO_BRIDGE;
+	mlxsw_sp_switchdev_addr_vxlan_convert(proto, addr, &info.remote_ip);
+	info.remote_port = vxlan->cfg.dst_port;
+	info.remote_vni = vni;
+	info.remote_ifindex = 0;
+	ether_addr_copy(info.eth_addr, mac);
+	info.vni = vni;
+	info.offloaded = adding;
+	call_switchdev_notifiers(type, dev, &info.info, NULL);
+}
+
+static void mlxsw_sp_fdb_nve_call_notifiers(struct net_device *dev,
+					    const char *mac,
+					    enum mlxsw_sp_l3proto proto,
+					    union mlxsw_sp_l3addr *addr,
+					    __be32 vni,
+					    bool adding)
+{
+	if (netif_is_vxlan(dev))
+		mlxsw_sp_fdb_vxlan_call_notifiers(dev, mac, proto, addr, vni,
+						  adding);
 }
 
 static void
@@ -2330,7 +2443,7 @@ mlxsw_sp_fdb_call_notifiers(enum switchdev_notifier_type type,
 	info.addr = mac;
 	info.vid = vid;
 	info.offloaded = offloaded;
-	call_switchdev_notifiers(type, dev, &info.info);
+	call_switchdev_notifiers(type, dev, &info.info, NULL);
 }
 
 static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
@@ -2428,7 +2541,8 @@ static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp,
 
 	bridge_device = bridge_port->bridge_device;
 	vid = bridge_device->vlan_enabled ? mlxsw_sp_port_vlan->vid : 0;
-	lag_vid = mlxsw_sp_port_vlan->vid;
+	lag_vid = mlxsw_sp_fid_lag_vid_valid(mlxsw_sp_port_vlan->fid) ?
+		  mlxsw_sp_port_vlan->vid : 0;
 
 do_fdb_op:
 	err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, fid, lag_vid,
@@ -2451,6 +2565,122 @@ just_remove:
 	goto do_fdb_op;
 }
 
+static int
+__mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp,
+					    const struct mlxsw_sp_fid *fid,
+					    bool adding,
+					    struct net_device **nve_dev,
+					    u16 *p_vid, __be32 *p_vni)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct net_device *br_dev, *dev;
+	int nve_ifindex;
+	int err;
+
+	err = mlxsw_sp_fid_nve_ifindex(fid, &nve_ifindex);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_fid_vni(fid, p_vni);
+	if (err)
+		return err;
+
+	dev = __dev_get_by_index(&init_net, nve_ifindex);
+	if (!dev)
+		return -EINVAL;
+	*nve_dev = dev;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	if (adding && !br_port_flag_is_set(dev, BR_LEARNING))
+		return -EINVAL;
+
+	if (adding && netif_is_vxlan(dev)) {
+		struct vxlan_dev *vxlan = netdev_priv(dev);
+
+		if (!(vxlan->cfg.flags & VXLAN_F_LEARN))
+			return -EINVAL;
+	}
+
+	br_dev = netdev_master_upper_dev_get(dev);
+	if (!br_dev)
+		return -EINVAL;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (!bridge_device)
+		return -EINVAL;
+
+	*p_vid = bridge_device->ops->fid_vid(bridge_device, fid);
+
+	return 0;
+}
+
+static void mlxsw_sp_fdb_notify_mac_uc_tunnel_process(struct mlxsw_sp *mlxsw_sp,
+						      char *sfn_pl,
+						      int rec_index,
+						      bool adding)
+{
+	enum mlxsw_reg_sfn_uc_tunnel_protocol sfn_proto;
+	enum switchdev_notifier_type type;
+	struct net_device *nve_dev;
+	union mlxsw_sp_l3addr addr;
+	struct mlxsw_sp_fid *fid;
+	char mac[ETH_ALEN];
+	u16 fid_index, vid;
+	__be32 vni;
+	u32 uip;
+	int err;
+
+	mlxsw_reg_sfn_uc_tunnel_unpack(sfn_pl, rec_index, mac, &fid_index,
+				       &uip, &sfn_proto);
+
+	fid = mlxsw_sp_fid_lookup_by_index(mlxsw_sp, fid_index);
+	if (!fid)
+		goto err_fid_lookup;
+
+	err = mlxsw_sp_nve_learned_ip_resolve(mlxsw_sp, uip,
+					      (enum mlxsw_sp_l3proto) sfn_proto,
+					      &addr);
+	if (err)
+		goto err_ip_resolve;
+
+	err = __mlxsw_sp_fdb_notify_mac_uc_tunnel_process(mlxsw_sp, fid, adding,
+							  &nve_dev, &vid, &vni);
+	if (err)
+		goto err_fdb_process;
+
+	err = mlxsw_sp_port_fdb_tunnel_uc_op(mlxsw_sp, mac, fid_index,
+					     (enum mlxsw_sp_l3proto) sfn_proto,
+					     &addr, adding, true);
+	if (err)
+		goto err_fdb_op;
+
+	mlxsw_sp_fdb_nve_call_notifiers(nve_dev, mac,
+					(enum mlxsw_sp_l3proto) sfn_proto,
+					&addr, vni, adding);
+
+	type = adding ? SWITCHDEV_FDB_ADD_TO_BRIDGE :
+			SWITCHDEV_FDB_DEL_TO_BRIDGE;
+	mlxsw_sp_fdb_call_notifiers(type, mac, vid, nve_dev, adding);
+
+	mlxsw_sp_fid_put(fid);
+
+	return;
+
+err_fdb_op:
+err_fdb_process:
+err_ip_resolve:
+	mlxsw_sp_fid_put(fid);
+err_fid_lookup:
+	/* Remove an FDB entry in case we cannot process it. Otherwise the
+	 * device will keep sending the same notification over and over again.
+	 */
+	mlxsw_sp_port_fdb_tunnel_uc_op(mlxsw_sp, mac, fid_index,
+				       (enum mlxsw_sp_l3proto) sfn_proto, &addr,
+				       false, true);
+}
+
 static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
 					    char *sfn_pl, int rec_index)
 {
@@ -2471,6 +2701,14 @@ static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_fdb_notify_mac_lag_process(mlxsw_sp, sfn_pl,
 						    rec_index, false);
 		break;
+	case MLXSW_REG_SFN_REC_TYPE_LEARNED_UNICAST_TUNNEL:
+		mlxsw_sp_fdb_notify_mac_uc_tunnel_process(mlxsw_sp, sfn_pl,
+							  rec_index, true);
+		break;
+	case MLXSW_REG_SFN_REC_TYPE_AGED_OUT_UNICAST_TUNNEL:
+		mlxsw_sp_fdb_notify_mac_uc_tunnel_process(mlxsw_sp, sfn_pl,
+							  rec_index, false);
+		break;
 	}
 }
 
@@ -2526,20 +2764,6 @@ struct mlxsw_sp_switchdev_event_work {
 };
 
 static void
-mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
-				      enum mlxsw_sp_l3proto *proto,
-				      union mlxsw_sp_l3addr *addr)
-{
-	if (vxlan_addr->sa.sa_family == AF_INET) {
-		addr->addr4 = vxlan_addr->sin.sin_addr.s_addr;
-		*proto = MLXSW_SP_L3_PROTO_IPV4;
-	} else {
-		addr->addr6 = vxlan_addr->sin6.sin6_addr;
-		*proto = MLXSW_SP_L3_PROTO_IPV6;
-	}
-}
-
-static void
 mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp,
 					  struct mlxsw_sp_switchdev_event_work *
 					  switchdev_work,
@@ -2570,7 +2794,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp,
 			return;
 		vxlan_fdb_info.offloaded = true;
 		call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-					 &vxlan_fdb_info.info);
+					 &vxlan_fdb_info.info, NULL);
 		mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED,
 					    vxlan_fdb_info.eth_addr,
 					    fdb_info->vid, dev, true);
@@ -2583,7 +2807,7 @@ mlxsw_sp_switchdev_bridge_vxlan_fdb_event(struct mlxsw_sp *mlxsw_sp,
 						     false);
 		vxlan_fdb_info.offloaded = false;
 		call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-					 &vxlan_fdb_info.info);
+					 &vxlan_fdb_info.info, NULL);
 		break;
 	}
 }
@@ -2604,7 +2828,8 @@ mlxsw_sp_switchdev_bridge_nve_fdb_event(struct mlxsw_sp_switchdev_event_work *
 	    switchdev_work->event != SWITCHDEV_FDB_DEL_TO_DEVICE)
 		return;
 
-	if (!switchdev_work->fdb_info.added_by_user)
+	if (switchdev_work->event == SWITCHDEV_FDB_ADD_TO_DEVICE &&
+	    !switchdev_work->fdb_info.added_by_user)
 		return;
 
 	if (!netif_running(dev))
@@ -2727,7 +2952,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp,
 		}
 		vxlan_fdb_info->offloaded = true;
 		call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-					 &vxlan_fdb_info->info);
+					 &vxlan_fdb_info->info, NULL);
 		mlxsw_sp_fid_put(fid);
 		return;
 	}
@@ -2748,7 +2973,7 @@ mlxsw_sp_switchdev_vxlan_fdb_add(struct mlxsw_sp *mlxsw_sp,
 		goto err_fdb_tunnel_uc_op;
 	vxlan_fdb_info->offloaded = true;
 	call_switchdev_notifiers(SWITCHDEV_VXLAN_FDB_OFFLOADED, dev,
-				 &vxlan_fdb_info->info);
+				 &vxlan_fdb_info->info, NULL);
 	mlxsw_sp_fdb_call_notifiers(SWITCHDEV_FDB_OFFLOADED,
 				    vxlan_fdb_info->eth_addr, vid, dev, true);
 
@@ -2849,23 +3074,34 @@ mlxsw_sp_switchdev_vxlan_work_prepare(struct mlxsw_sp_switchdev_event_work *
 	struct vxlan_dev *vxlan = netdev_priv(switchdev_work->dev);
 	struct switchdev_notifier_vxlan_fdb_info *vxlan_fdb_info;
 	struct vxlan_config *cfg = &vxlan->cfg;
+	struct netlink_ext_ack *extack;
 
+	extack = switchdev_notifier_info_to_extack(info);
 	vxlan_fdb_info = container_of(info,
 				      struct switchdev_notifier_vxlan_fdb_info,
 				      info);
 
-	if (vxlan_fdb_info->remote_port != cfg->dst_port)
-		return -EOPNOTSUPP;
-	if (vxlan_fdb_info->remote_vni != cfg->vni)
+	if (vxlan_fdb_info->remote_port != cfg->dst_port) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Non-default remote port is not supported");
 		return -EOPNOTSUPP;
-	if (vxlan_fdb_info->vni != cfg->vni)
+	}
+	if (vxlan_fdb_info->remote_vni != cfg->vni ||
+	    vxlan_fdb_info->vni != cfg->vni) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Non-default VNI is not supported");
 		return -EOPNOTSUPP;
-	if (vxlan_fdb_info->remote_ifindex)
+	}
+	if (vxlan_fdb_info->remote_ifindex) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Local interface is not supported");
 		return -EOPNOTSUPP;
-	if (is_multicast_ether_addr(vxlan_fdb_info->eth_addr))
+	}
+	if (is_multicast_ether_addr(vxlan_fdb_info->eth_addr)) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Multicast MAC addresses not supported");
 		return -EOPNOTSUPP;
-	if (vxlan_addr_multicast(&vxlan_fdb_info->remote_ip))
+	}
+	if (vxlan_addr_multicast(&vxlan_fdb_info->remote_ip)) {
+		NL_SET_ERR_MSG_MOD(extack, "VxLAN: FDB: Multicast destination IP is not supported");
 		return -EOPNOTSUPP;
+	}
 
 	switchdev_work->vxlan_fdb_info = *vxlan_fdb_info;
 
@@ -2883,6 +3119,13 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused,
 	struct net_device *br_dev;
 	int err;
 
+	if (event == SWITCHDEV_PORT_ATTR_SET) {
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     mlxsw_sp_port_dev_check,
+						     mlxsw_sp_port_attr_set);
+		return notifier_from_errno(err);
+	}
+
 	/* Tunnel devices are not our uppers, so check their master instead */
 	br_dev = netdev_master_upper_dev_get_rcu(dev);
 	if (!br_dev)
@@ -2947,10 +3190,279 @@ err_addr_alloc:
 	return NOTIFY_BAD;
 }
 
-static struct notifier_block mlxsw_sp_switchdev_notifier = {
+struct notifier_block mlxsw_sp_switchdev_notifier = {
 	.notifier_call = mlxsw_sp_switchdev_event,
 };
 
+static int
+mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_bridge_device *bridge_device,
+				  const struct net_device *vxlan_dev, u16 vid,
+				  bool flag_untagged, bool flag_pvid,
+				  struct netlink_ext_ack *extack)
+{
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	__be32 vni = vxlan->cfg.vni;
+	struct mlxsw_sp_fid *fid;
+	u16 old_vid;
+	int err;
+
+	/* We cannot have the same VLAN as PVID and egress untagged on multiple
+	 * VxLAN devices. Note that we get this notification before the VLAN is
+	 * actually added to the bridge's database, so it is not possible for
+	 * the lookup function to return 'vxlan_dev'
+	 */
+	if (flag_untagged && flag_pvid &&
+	    mlxsw_sp_bridge_8021q_vxlan_dev_find(bridge_device->dev, vid)) {
+		NL_SET_ERR_MSG_MOD(extack, "VLAN already mapped to a different VNI");
+		return -EINVAL;
+	}
+
+	if (!netif_running(vxlan_dev))
+		return 0;
+
+	/* First case: FID is not associated with this VNI, but the new VLAN
+	 * is both PVID and egress untagged. Need to enable NVE on the FID, if
+	 * it exists
+	 */
+	fid = mlxsw_sp_fid_lookup_by_vni(mlxsw_sp, vni);
+	if (!fid) {
+		if (!flag_untagged || !flag_pvid)
+			return 0;
+		return mlxsw_sp_bridge_8021q_vxlan_join(bridge_device,
+							vxlan_dev, vid, extack);
+	}
+
+	/* Second case: FID is associated with the VNI and the VLAN associated
+	 * with the FID is the same as the notified VLAN. This means the flags
+	 * (PVID / egress untagged) were toggled and that NVE should be
+	 * disabled on the FID
+	 */
+	old_vid = mlxsw_sp_fid_8021q_vid(fid);
+	if (vid == old_vid) {
+		if (WARN_ON(flag_untagged && flag_pvid)) {
+			mlxsw_sp_fid_put(fid);
+			return -EINVAL;
+		}
+		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+		mlxsw_sp_fid_put(fid);
+		return 0;
+	}
+
+	/* Third case: A new VLAN was configured on the VxLAN device, but this
+	 * VLAN is not PVID, so there is nothing to do.
+	 */
+	if (!flag_pvid) {
+		mlxsw_sp_fid_put(fid);
+		return 0;
+	}
+
+	/* Fourth case: Thew new VLAN is PVID, which means the VLAN currently
+	 * mapped to the VNI should be unmapped
+	 */
+	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	mlxsw_sp_fid_put(fid);
+
+	/* Fifth case: The new VLAN is also egress untagged, which means the
+	 * VLAN needs to be mapped to the VNI
+	 */
+	if (!flag_untagged)
+		return 0;
+
+	err = mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, vid,
+					       extack);
+	if (err)
+		goto err_vxlan_join;
+
+	return 0;
+
+err_vxlan_join:
+	mlxsw_sp_bridge_8021q_vxlan_join(bridge_device, vxlan_dev, old_vid,
+					 NULL);
+	return err;
+}
+
+static void
+mlxsw_sp_switchdev_vxlan_vlan_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_bridge_device *bridge_device,
+				  const struct net_device *vxlan_dev, u16 vid)
+{
+	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
+	__be32 vni = vxlan->cfg.vni;
+	struct mlxsw_sp_fid *fid;
+
+	if (!netif_running(vxlan_dev))
+		return;
+
+	fid = mlxsw_sp_fid_lookup_by_vni(mlxsw_sp, vni);
+	if (!fid)
+		return;
+
+	/* A different VLAN than the one mapped to the VNI is deleted */
+	if (mlxsw_sp_fid_8021q_vid(fid) != vid)
+		goto out;
+
+	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+
+out:
+	mlxsw_sp_fid_put(fid);
+}
+
+static int
+mlxsw_sp_switchdev_vxlan_vlans_add(struct net_device *vxlan_dev,
+				   struct switchdev_notifier_port_obj_info *
+				   port_obj_info)
+{
+	struct switchdev_obj_port_vlan *vlan =
+		SWITCHDEV_OBJ_PORT_VLAN(port_obj_info->obj);
+	bool flag_untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED;
+	bool flag_pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID;
+	struct switchdev_trans *trans = port_obj_info->trans;
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct netlink_ext_ack *extack;
+	struct mlxsw_sp *mlxsw_sp;
+	struct net_device *br_dev;
+	u16 vid;
+
+	extack = switchdev_notifier_info_to_extack(&port_obj_info->info);
+	br_dev = netdev_master_upper_dev_get(vxlan_dev);
+	if (!br_dev)
+		return 0;
+
+	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	port_obj_info->handled = true;
+
+	if (switchdev_trans_ph_commit(trans))
+		return 0;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (!bridge_device)
+		return -EINVAL;
+
+	if (!bridge_device->vlan_enabled)
+		return 0;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		int err;
+
+		err = mlxsw_sp_switchdev_vxlan_vlan_add(mlxsw_sp, bridge_device,
+							vxlan_dev, vid,
+							flag_untagged,
+							flag_pvid, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void
+mlxsw_sp_switchdev_vxlan_vlans_del(struct net_device *vxlan_dev,
+				   struct switchdev_notifier_port_obj_info *
+				   port_obj_info)
+{
+	struct switchdev_obj_port_vlan *vlan =
+		SWITCHDEV_OBJ_PORT_VLAN(port_obj_info->obj);
+	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp *mlxsw_sp;
+	struct net_device *br_dev;
+	u16 vid;
+
+	br_dev = netdev_master_upper_dev_get(vxlan_dev);
+	if (!br_dev)
+		return;
+
+	mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	if (!mlxsw_sp)
+		return;
+
+	port_obj_info->handled = true;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (!bridge_device)
+		return;
+
+	if (!bridge_device->vlan_enabled)
+		return;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++)
+		mlxsw_sp_switchdev_vxlan_vlan_del(mlxsw_sp, bridge_device,
+						  vxlan_dev, vid);
+}
+
+static int
+mlxsw_sp_switchdev_handle_vxlan_obj_add(struct net_device *vxlan_dev,
+					struct switchdev_notifier_port_obj_info *
+					port_obj_info)
+{
+	int err = 0;
+
+	switch (port_obj_info->obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		err = mlxsw_sp_switchdev_vxlan_vlans_add(vxlan_dev,
+							 port_obj_info);
+		break;
+	default:
+		break;
+	}
+
+	return err;
+}
+
+static void
+mlxsw_sp_switchdev_handle_vxlan_obj_del(struct net_device *vxlan_dev,
+					struct switchdev_notifier_port_obj_info *
+					port_obj_info)
+{
+	switch (port_obj_info->obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		mlxsw_sp_switchdev_vxlan_vlans_del(vxlan_dev, port_obj_info);
+		break;
+	default:
+		break;
+	}
+}
+
+static int mlxsw_sp_switchdev_blocking_event(struct notifier_block *unused,
+					     unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err = 0;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		if (netif_is_vxlan(dev))
+			err = mlxsw_sp_switchdev_handle_vxlan_obj_add(dev, ptr);
+		else
+			err = switchdev_handle_port_obj_add(dev, ptr,
+							mlxsw_sp_port_dev_check,
+							mlxsw_sp_port_obj_add);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_OBJ_DEL:
+		if (netif_is_vxlan(dev))
+			mlxsw_sp_switchdev_handle_vxlan_obj_del(dev, ptr);
+		else
+			err = switchdev_handle_port_obj_del(dev, ptr,
+							mlxsw_sp_port_dev_check,
+							mlxsw_sp_port_obj_del);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     mlxsw_sp_port_dev_check,
+						     mlxsw_sp_port_attr_set);
+		return notifier_from_errno(err);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block mlxsw_sp_switchdev_blocking_notifier = {
+	.notifier_call = mlxsw_sp_switchdev_blocking_event,
+};
+
 u8
 mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port)
 {
@@ -2960,6 +3472,7 @@ mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port)
 static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge;
+	struct notifier_block *nb;
 	int err;
 
 	err = mlxsw_sp_ageing_set(mlxsw_sp, MLXSW_SP_DEFAULT_AGEING_TIME);
@@ -2974,17 +3487,33 @@ static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp)
 		return err;
 	}
 
+	nb = &mlxsw_sp_switchdev_blocking_notifier;
+	err = register_switchdev_blocking_notifier(nb);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to register switchdev blocking notifier\n");
+		goto err_register_switchdev_blocking_notifier;
+	}
+
 	INIT_DELAYED_WORK(&bridge->fdb_notify.dw, mlxsw_sp_fdb_notify_work);
 	bridge->fdb_notify.interval = MLXSW_SP_DEFAULT_LEARNING_INTERVAL;
 	mlxsw_sp_fdb_notify_work_schedule(mlxsw_sp);
 	return 0;
+
+err_register_switchdev_blocking_notifier:
+	unregister_switchdev_notifier(&mlxsw_sp_switchdev_notifier);
+	return err;
 }
 
 static void mlxsw_sp_fdb_fini(struct mlxsw_sp *mlxsw_sp)
 {
+	struct notifier_block *nb;
+
 	cancel_delayed_work_sync(&mlxsw_sp->bridge->fdb_notify.dw);
-	unregister_switchdev_notifier(&mlxsw_sp_switchdev_notifier);
 
+	nb = &mlxsw_sp_switchdev_blocking_notifier;
+	unregister_switchdev_blocking_notifier(nb);
+
+	unregister_switchdev_notifier(&mlxsw_sp_switchdev_notifier);
 }
 
 int mlxsw_sp_switchdev_init(struct mlxsw_sp *mlxsw_sp)
@@ -3012,11 +3541,3 @@ void mlxsw_sp_switchdev_fini(struct mlxsw_sp *mlxsw_sp)
 	kfree(mlxsw_sp->bridge);
 }
 
-void mlxsw_sp_port_switchdev_init(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-	mlxsw_sp_port->dev->switchdev_ops = &mlxsw_sp_port_switchdev_ops;
-}
-
-void mlxsw_sp_port_switchdev_fini(struct mlxsw_sp_port *mlxsw_sp_port)
-{
-}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 2d4f213e154d..533fe6235b7c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -11,7 +11,6 @@
 #include <linux/device.h>
 #include <linux/skbuff.h>
 #include <linux/if_vlan.h>
-#include <net/switchdev.h>
 
 #include "pci.h"
 #include "core.h"
@@ -390,6 +389,18 @@ static int mlxsw_sx_port_get_phys_port_name(struct net_device *dev, char *name,
 						  name, len);
 }
 
+static int mlxsw_sx_port_get_port_parent_id(struct net_device *dev,
+					    struct netdev_phys_item_id *ppid)
+{
+	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
+	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
+
+	ppid->id_len = sizeof(mlxsw_sx->hw_id);
+	memcpy(&ppid->id, &mlxsw_sx->hw_id, ppid->id_len);
+
+	return 0;
+}
+
 static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
 	.ndo_open		= mlxsw_sx_port_open,
 	.ndo_stop		= mlxsw_sx_port_stop,
@@ -397,6 +408,7 @@ static const struct net_device_ops mlxsw_sx_port_netdev_ops = {
 	.ndo_change_mtu		= mlxsw_sx_port_change_mtu,
 	.ndo_get_stats64	= mlxsw_sx_port_get_stats64,
 	.ndo_get_phys_port_name = mlxsw_sx_port_get_phys_port_name,
+	.ndo_get_port_parent_id	= mlxsw_sx_port_get_port_parent_id,
 };
 
 static void mlxsw_sx_port_get_drvinfo(struct net_device *dev,
@@ -901,28 +913,6 @@ static const struct ethtool_ops mlxsw_sx_port_ethtool_ops = {
 	.set_link_ksettings	= mlxsw_sx_port_set_link_ksettings,
 };
 
-static int mlxsw_sx_port_attr_get(struct net_device *dev,
-				  struct switchdev_attr *attr)
-{
-	struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev);
-	struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(mlxsw_sx->hw_id);
-		memcpy(&attr->u.ppid.id, &mlxsw_sx->hw_id, attr->u.ppid.id_len);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static const struct switchdev_ops mlxsw_sx_port_switchdev_ops = {
-	.switchdev_port_attr_get	= mlxsw_sx_port_attr_get,
-};
-
 static int mlxsw_sx_hw_id_get(struct mlxsw_sx *mlxsw_sx)
 {
 	char spad_pl[MLXSW_REG_SPAD_LEN] = {0};
@@ -1034,7 +1024,6 @@ static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port,
 
 	dev->netdev_ops = &mlxsw_sx_port_netdev_ops;
 	dev->ethtool_ops = &mlxsw_sx_port_ethtool_ops;
-	dev->switchdev_ops = &mlxsw_sx_port_switchdev_ops;
 
 	err = mlxsw_sx_port_dev_addr_get(mlxsw_sx_port);
 	if (err) {
diff --git a/drivers/net/ethernet/micrel/ks8695net.c b/drivers/net/ethernet/micrel/ks8695net.c
index b881f5d4a7f9..6006d47707cb 100644
--- a/drivers/net/ethernet/micrel/ks8695net.c
+++ b/drivers/net/ethernet/micrel/ks8695net.c
@@ -391,7 +391,7 @@ ks8695_tx_irq(int irq, void *dev_id)
 					 ksp->tx_buffers[buff_n].dma_ptr,
 					 ksp->tx_buffers[buff_n].length,
 					 DMA_TO_DEVICE);
-			dev_kfree_skb_irq(ksp->tx_buffers[buff_n].skb);
+			dev_consume_skb_irq(ksp->tx_buffers[buff_n].skb);
 			ksp->tx_buffers[buff_n].skb = NULL;
 			ksp->tx_ring_used--;
 		}
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index bd6e9014bc74..7849119d407a 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -142,6 +142,12 @@ struct ks8851_net {
 
 static int msg_enable;
 
+/* SPI frame opcodes */
+#define KS_SPIOP_RD	(0x00)
+#define KS_SPIOP_WR	(0x40)
+#define KS_SPIOP_RXFIFO	(0x80)
+#define KS_SPIOP_TXFIFO	(0xC0)
+
 /* shift for byte-enable data */
 #define BYTE_EN(_x)	((_x) << 2)
 
@@ -535,9 +541,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 		/* set dma read address */
 		ks8851_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI | 0x00);
 
-		/* start the packet dma process, and set auto-dequeue rx */
-		ks8851_wrreg16(ks, KS_RXQCR,
-			       ks->rc_rxqcr | RXQCR_SDA | RXQCR_ADRFE);
+		/* start DMA access */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA);
 
 		if (rxlen > 4) {
 			unsigned int rxalign;
@@ -568,7 +573,8 @@ static void ks8851_rx_pkts(struct ks8851_net *ks)
 			}
 		}
 
-		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr);
+		/* end DMA access and dequeue packet */
+		ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_RRXEF);
 	}
 }
 
@@ -785,6 +791,15 @@ static void ks8851_tx_work(struct work_struct *work)
 static int ks8851_net_open(struct net_device *dev)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
+	int ret;
+
+	ret = request_threaded_irq(dev->irq, NULL, ks8851_irq,
+				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
+				   dev->name, ks);
+	if (ret < 0) {
+		netdev_err(dev, "failed to get irq\n");
+		return ret;
+	}
 
 	/* lock the card, even if we may not actually be doing anything
 	 * else at the moment */
@@ -849,6 +864,7 @@ static int ks8851_net_open(struct net_device *dev)
 	netif_dbg(ks, ifup, ks->netdev, "network device up\n");
 
 	mutex_unlock(&ks->lock);
+	mii_check_link(&ks->mii);
 	return 0;
 }
 
@@ -899,6 +915,8 @@ static int ks8851_net_stop(struct net_device *dev)
 		dev_kfree_skb(txb);
 	}
 
+	free_irq(dev->irq, ks);
+
 	return 0;
 }
 
@@ -1508,6 +1526,7 @@ static int ks8851_probe(struct spi_device *spi)
 
 	spi_set_drvdata(spi, ks);
 
+	netif_carrier_off(ks->netdev);
 	ndev->if_port = IF_PORT_100BASET;
 	ndev->netdev_ops = &ks8851_netdev_ops;
 	ndev->irq = spi->irq;
@@ -1529,14 +1548,6 @@ static int ks8851_probe(struct spi_device *spi)
 	ks8851_read_selftest(ks);
 	ks8851_init_mac(ks);
 
-	ret = request_threaded_irq(spi->irq, NULL, ks8851_irq,
-				   IRQF_TRIGGER_LOW | IRQF_ONESHOT,
-				   ndev->name, ks);
-	if (ret < 0) {
-		dev_err(&spi->dev, "failed to get irq\n");
-		goto err_irq;
-	}
-
 	ret = register_netdev(ndev);
 	if (ret) {
 		dev_err(&spi->dev, "failed to register network device\n");
@@ -1549,14 +1560,10 @@ static int ks8851_probe(struct spi_device *spi)
 
 	return 0;
 
-
 err_netdev:
-	free_irq(ndev->irq, ks);
-
-err_irq:
+err_id:
 	if (gpio_is_valid(gpio))
 		gpio_set_value(gpio, 0);
-err_id:
 	regulator_disable(ks->vdd_reg);
 err_reg:
 	regulator_disable(ks->vdd_io);
@@ -1574,7 +1581,6 @@ static int ks8851_remove(struct spi_device *spi)
 		dev_info(&spi->dev, "remove\n");
 
 	unregister_netdev(priv->netdev);
-	free_irq(spi->irq, priv);
 	if (gpio_is_valid(priv->gpio))
 		gpio_set_value(priv->gpio, 0);
 	regulator_disable(priv->vdd_reg);
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index 852256ef1f22..23da1e3ee429 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -11,9 +11,15 @@
 */
 
 #define KS_CCR					0x08
+#define CCR_LE					(1 << 10)   /* KSZ8851-16MLL */
 #define CCR_EEPROM				(1 << 9)
-#define CCR_SPI					(1 << 8)
-#define CCR_32PIN				(1 << 0)
+#define CCR_SPI					(1 << 8)    /* KSZ8851SNL    */
+#define CCR_8BIT				(1 << 7)    /* KSZ8851-16MLL */
+#define CCR_16BIT				(1 << 6)    /* KSZ8851-16MLL */
+#define CCR_32BIT				(1 << 5)    /* KSZ8851-16MLL */
+#define CCR_SHARED				(1 << 4)    /* KSZ8851-16MLL */
+#define CCR_48PIN				(1 << 1)    /* KSZ8851-16MLL */
+#define CCR_32PIN				(1 << 0)    /* KSZ8851SNL    */
 
 /* MAC address registers */
 #define KS_MAR(_m)				(0x15 - (_m))
@@ -112,13 +118,13 @@
 #define RXCR1_RXE				(1 << 0)
 
 #define KS_RXCR2				0x76
-#define RXCR2_SRDBL_MASK			(0x7 << 5)
-#define RXCR2_SRDBL_SHIFT			(5)
-#define RXCR2_SRDBL_4B				(0x0 << 5)
-#define RXCR2_SRDBL_8B				(0x1 << 5)
-#define RXCR2_SRDBL_16B				(0x2 << 5)
-#define RXCR2_SRDBL_32B				(0x3 << 5)
-#define RXCR2_SRDBL_FRAME			(0x4 << 5)
+#define RXCR2_SRDBL_MASK			(0x7 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_SHIFT			(5)	    /* KSZ8851SNL    */
+#define RXCR2_SRDBL_4B				(0x0 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_8B				(0x1 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_16B				(0x2 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_32B				(0x3 << 5)  /* KSZ8851SNL    */
+#define RXCR2_SRDBL_FRAME			(0x4 << 5)  /* KSZ8851SNL    */
 #define RXCR2_IUFFP				(1 << 4)
 #define RXCR2_RXIUFCEZ				(1 << 3)
 #define RXCR2_UDPLFE				(1 << 2)
@@ -143,8 +149,10 @@
 #define RXFSHR_RXCE				(1 << 0)
 
 #define KS_RXFHBCR				0x7E
+#define RXFHBCR_CNT_MASK			(0xfff << 0)
+
 #define KS_TXQCR				0x80
-#define TXQCR_AETFE				(1 << 2)
+#define TXQCR_AETFE				(1 << 2)    /* KSZ8851SNL    */
 #define TXQCR_TXQMAM				(1 << 1)
 #define TXQCR_METFE				(1 << 0)
 
@@ -167,6 +175,10 @@
 
 #define KS_RXFDPR				0x86
 #define RXFDPR_RXFPAI				(1 << 14)
+#define RXFDPR_WST				(1 << 12)   /* KSZ8851-16MLL */
+#define RXFDPR_EMS				(1 << 11)   /* KSZ8851-16MLL */
+#define RXFDPR_RXFP_MASK			(0x7ff << 0)
+#define RXFDPR_RXFP_SHIFT			(0)
 
 #define KS_RXDTTR				0x8C
 #define KS_RXDBCTR				0x8E
@@ -184,7 +196,7 @@
 #define IRQ_RXMPDI				(1 << 4)
 #define IRQ_LDI					(1 << 3)
 #define IRQ_EDI					(1 << 2)
-#define IRQ_SPIBEI				(1 << 1)
+#define IRQ_SPIBEI				(1 << 1)    /* KSZ8851SNL    */
 #define IRQ_DEDI				(1 << 0)
 
 #define KS_RXFCTR				0x9C
@@ -257,42 +269,37 @@
 #define KS_P1ANLPR				0xEE
 
 #define KS_P1SCLMD				0xF4
-#define P1SCLMD_LEDOFF				(1 << 15)
-#define P1SCLMD_TXIDS				(1 << 14)
-#define P1SCLMD_RESTARTAN			(1 << 13)
-#define P1SCLMD_DISAUTOMDIX			(1 << 10)
-#define P1SCLMD_FORCEMDIX			(1 << 9)
-#define P1SCLMD_AUTONEGEN			(1 << 7)
-#define P1SCLMD_FORCE100			(1 << 6)
-#define P1SCLMD_FORCEFDX			(1 << 5)
-#define P1SCLMD_ADV_FLOW			(1 << 4)
-#define P1SCLMD_ADV_100BT_FDX			(1 << 3)
-#define P1SCLMD_ADV_100BT_HDX			(1 << 2)
-#define P1SCLMD_ADV_10BT_FDX			(1 << 1)
-#define P1SCLMD_ADV_10BT_HDX			(1 << 0)
 
 #define KS_P1CR					0xF6
-#define P1CR_HP_MDIX				(1 << 15)
-#define P1CR_REV_POL				(1 << 13)
-#define P1CR_OP_100M				(1 << 10)
-#define P1CR_OP_FDX				(1 << 9)
-#define P1CR_OP_MDI				(1 << 7)
-#define P1CR_AN_DONE				(1 << 6)
-#define P1CR_LINK_GOOD				(1 << 5)
-#define P1CR_PNTR_FLOW				(1 << 4)
-#define P1CR_PNTR_100BT_FDX			(1 << 3)
-#define P1CR_PNTR_100BT_HDX			(1 << 2)
-#define P1CR_PNTR_10BT_FDX			(1 << 1)
-#define P1CR_PNTR_10BT_HDX			(1 << 0)
+#define P1CR_LEDOFF				(1 << 15)
+#define P1CR_TXIDS				(1 << 14)
+#define P1CR_RESTARTAN				(1 << 13)
+#define P1CR_DISAUTOMDIX			(1 << 10)
+#define P1CR_FORCEMDIX				(1 << 9)
+#define P1CR_AUTONEGEN				(1 << 7)
+#define P1CR_FORCE100				(1 << 6)
+#define P1CR_FORCEFDX				(1 << 5)
+#define P1CR_ADV_FLOW				(1 << 4)
+#define P1CR_ADV_100BT_FDX			(1 << 3)
+#define P1CR_ADV_100BT_HDX			(1 << 2)
+#define P1CR_ADV_10BT_FDX			(1 << 1)
+#define P1CR_ADV_10BT_HDX			(1 << 0)
+
+#define KS_P1SR					0xF8
+#define P1SR_HP_MDIX				(1 << 15)
+#define P1SR_REV_POL				(1 << 13)
+#define P1SR_OP_100M				(1 << 10)
+#define P1SR_OP_FDX				(1 << 9)
+#define P1SR_OP_MDI				(1 << 7)
+#define P1SR_AN_DONE				(1 << 6)
+#define P1SR_LINK_GOOD				(1 << 5)
+#define P1SR_PNTR_FLOW				(1 << 4)
+#define P1SR_PNTR_100BT_FDX			(1 << 3)
+#define P1SR_PNTR_100BT_HDX			(1 << 2)
+#define P1SR_PNTR_10BT_FDX			(1 << 1)
+#define P1SR_PNTR_10BT_HDX			(1 << 0)
 
 /* TX Frame control */
-
 #define TXFR_TXIC				(1 << 15)
 #define TXFR_TXFID_MASK				(0x3f << 0)
 #define TXFR_TXFID_SHIFT			(0)
-
-/* SPI frame opcodes */
-#define KS_SPIOP_RD				(0x00)
-#define KS_SPIOP_WR				(0x40)
-#define KS_SPIOP_RXFIFO				(0x80)
-#define KS_SPIOP_TXFIFO				(0xC0)
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index 35f8c9ef204d..c946841c0a06 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -40,6 +40,8 @@
 #include <linux/of_device.h>
 #include <linux/of_net.h>
 
+#include "ks8851.h"
+
 #define	DRV_NAME	"ks8851_mll"
 
 static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
@@ -48,319 +50,10 @@ static u8 KS_DEFAULT_MAC_ADDRESS[] = { 0x00, 0x10, 0xA1, 0x86, 0x95, 0x11 };
 #define TX_BUF_SIZE			2000
 #define RX_BUF_SIZE			2000
 
-#define KS_CCR				0x08
-#define CCR_EEPROM			(1 << 9)
-#define CCR_SPI				(1 << 8)
-#define CCR_8BIT			(1 << 7)
-#define CCR_16BIT			(1 << 6)
-#define CCR_32BIT			(1 << 5)
-#define CCR_SHARED			(1 << 4)
-#define CCR_32PIN			(1 << 0)
-
-/* MAC address registers */
-#define KS_MARL				0x10
-#define KS_MARM				0x12
-#define KS_MARH				0x14
-
-#define KS_OBCR				0x20
-#define OBCR_ODS_16MA			(1 << 6)
-
-#define KS_EEPCR			0x22
-#define EEPCR_EESA			(1 << 4)
-#define EEPCR_EESB			(1 << 3)
-#define EEPCR_EEDO			(1 << 2)
-#define EEPCR_EESCK			(1 << 1)
-#define EEPCR_EECS			(1 << 0)
-
-#define KS_MBIR				0x24
-#define MBIR_TXMBF			(1 << 12)
-#define MBIR_TXMBFA			(1 << 11)
-#define MBIR_RXMBF			(1 << 4)
-#define MBIR_RXMBFA			(1 << 3)
-
-#define KS_GRR				0x26
-#define GRR_QMU				(1 << 1)
-#define GRR_GSR				(1 << 0)
-
-#define KS_WFCR				0x2A
-#define WFCR_MPRXE			(1 << 7)
-#define WFCR_WF3E			(1 << 3)
-#define WFCR_WF2E			(1 << 2)
-#define WFCR_WF1E			(1 << 1)
-#define WFCR_WF0E			(1 << 0)
-
-#define KS_WF0CRC0			0x30
-#define KS_WF0CRC1			0x32
-#define KS_WF0BM0			0x34
-#define KS_WF0BM1			0x36
-#define KS_WF0BM2			0x38
-#define KS_WF0BM3			0x3A
-
-#define KS_WF1CRC0			0x40
-#define KS_WF1CRC1			0x42
-#define KS_WF1BM0			0x44
-#define KS_WF1BM1			0x46
-#define KS_WF1BM2			0x48
-#define KS_WF1BM3			0x4A
-
-#define KS_WF2CRC0			0x50
-#define KS_WF2CRC1			0x52
-#define KS_WF2BM0			0x54
-#define KS_WF2BM1			0x56
-#define KS_WF2BM2			0x58
-#define KS_WF2BM3			0x5A
-
-#define KS_WF3CRC0			0x60
-#define KS_WF3CRC1			0x62
-#define KS_WF3BM0			0x64
-#define KS_WF3BM1			0x66
-#define KS_WF3BM2			0x68
-#define KS_WF3BM3			0x6A
-
-#define KS_TXCR				0x70
-#define TXCR_TCGICMP			(1 << 8)
-#define TXCR_TCGUDP			(1 << 7)
-#define TXCR_TCGTCP			(1 << 6)
-#define TXCR_TCGIP			(1 << 5)
-#define TXCR_FTXQ			(1 << 4)
-#define TXCR_TXFCE			(1 << 3)
-#define TXCR_TXPE			(1 << 2)
-#define TXCR_TXCRC			(1 << 1)
-#define TXCR_TXE			(1 << 0)
-
-#define KS_TXSR				0x72
-#define TXSR_TXLC			(1 << 13)
-#define TXSR_TXMC			(1 << 12)
-#define TXSR_TXFID_MASK			(0x3f << 0)
-#define TXSR_TXFID_SHIFT		(0)
-#define TXSR_TXFID_GET(_v)		(((_v) >> 0) & 0x3f)
-
-
-#define KS_RXCR1			0x74
-#define RXCR1_FRXQ			(1 << 15)
-#define RXCR1_RXUDPFCC			(1 << 14)
-#define RXCR1_RXTCPFCC			(1 << 13)
-#define RXCR1_RXIPFCC			(1 << 12)
-#define RXCR1_RXPAFMA			(1 << 11)
-#define RXCR1_RXFCE			(1 << 10)
-#define RXCR1_RXEFE			(1 << 9)
-#define RXCR1_RXMAFMA			(1 << 8)
-#define RXCR1_RXBE			(1 << 7)
-#define RXCR1_RXME			(1 << 6)
-#define RXCR1_RXUE			(1 << 5)
-#define RXCR1_RXAE			(1 << 4)
-#define RXCR1_RXINVF			(1 << 1)
-#define RXCR1_RXE			(1 << 0)
 #define RXCR1_FILTER_MASK    		(RXCR1_RXINVF | RXCR1_RXAE | \
 					 RXCR1_RXMAFMA | RXCR1_RXPAFMA)
-
-#define KS_RXCR2			0x76
-#define RXCR2_SRDBL_MASK		(0x7 << 5)
-#define RXCR2_SRDBL_SHIFT		(5)
-#define RXCR2_SRDBL_4B			(0x0 << 5)
-#define RXCR2_SRDBL_8B			(0x1 << 5)
-#define RXCR2_SRDBL_16B			(0x2 << 5)
-#define RXCR2_SRDBL_32B			(0x3 << 5)
-/* #define RXCR2_SRDBL_FRAME		(0x4 << 5) */
-#define RXCR2_IUFFP			(1 << 4)
-#define RXCR2_RXIUFCEZ			(1 << 3)
-#define RXCR2_UDPLFE			(1 << 2)
-#define RXCR2_RXICMPFCC			(1 << 1)
-#define RXCR2_RXSAF			(1 << 0)
-
-#define KS_TXMIR			0x78
-
-#define KS_RXFHSR			0x7C
-#define RXFSHR_RXFV			(1 << 15)
-#define RXFSHR_RXICMPFCS		(1 << 13)
-#define RXFSHR_RXIPFCS			(1 << 12)
-#define RXFSHR_RXTCPFCS			(1 << 11)
-#define RXFSHR_RXUDPFCS			(1 << 10)
-#define RXFSHR_RXBF			(1 << 7)
-#define RXFSHR_RXMF			(1 << 6)
-#define RXFSHR_RXUF			(1 << 5)
-#define RXFSHR_RXMR			(1 << 4)
-#define RXFSHR_RXFT			(1 << 3)
-#define RXFSHR_RXFTL			(1 << 2)
-#define RXFSHR_RXRF			(1 << 1)
-#define RXFSHR_RXCE			(1 << 0)
-#define	RXFSHR_ERR			(RXFSHR_RXCE | RXFSHR_RXRF |\
-					RXFSHR_RXFTL | RXFSHR_RXMR |\
-					RXFSHR_RXICMPFCS | RXFSHR_RXIPFCS |\
-					RXFSHR_RXTCPFCS)
-#define KS_RXFHBCR			0x7E
-#define RXFHBCR_CNT_MASK		0x0FFF
-
-#define KS_TXQCR			0x80
-#define TXQCR_AETFE			(1 << 2)
-#define TXQCR_TXQMAM			(1 << 1)
-#define TXQCR_METFE			(1 << 0)
-
-#define KS_RXQCR			0x82
-#define RXQCR_RXDTTS			(1 << 12)
-#define RXQCR_RXDBCTS			(1 << 11)
-#define RXQCR_RXFCTS			(1 << 10)
-#define RXQCR_RXIPHTOE			(1 << 9)
-#define RXQCR_RXDTTE			(1 << 7)
-#define RXQCR_RXDBCTE			(1 << 6)
-#define RXQCR_RXFCTE			(1 << 5)
-#define RXQCR_ADRFE			(1 << 4)
-#define RXQCR_SDA			(1 << 3)
-#define RXQCR_RRXEF			(1 << 0)
 #define RXQCR_CMD_CNTL                	(RXQCR_RXFCTE|RXQCR_ADRFE)
 
-#define KS_TXFDPR			0x84
-#define TXFDPR_TXFPAI			(1 << 14)
-#define TXFDPR_TXFP_MASK		(0x7ff << 0)
-#define TXFDPR_TXFP_SHIFT		(0)
-
-#define KS_RXFDPR			0x86
-#define RXFDPR_RXFPAI			(1 << 14)
-
-#define KS_RXDTTR			0x8C
-#define KS_RXDBCTR			0x8E
-
-#define KS_IER				0x90
-#define KS_ISR				0x92
-#define IRQ_LCI				(1 << 15)
-#define IRQ_TXI				(1 << 14)
-#define IRQ_RXI				(1 << 13)
-#define IRQ_RXOI			(1 << 11)
-#define IRQ_TXPSI			(1 << 9)
-#define IRQ_RXPSI			(1 << 8)
-#define IRQ_TXSAI			(1 << 6)
-#define IRQ_RXWFDI			(1 << 5)
-#define IRQ_RXMPDI			(1 << 4)
-#define IRQ_LDI				(1 << 3)
-#define IRQ_EDI				(1 << 2)
-#define IRQ_SPIBEI			(1 << 1)
-#define IRQ_DEDI			(1 << 0)
-
-#define KS_RXFCTR			0x9C
-#define RXFCTR_THRESHOLD_MASK     	0x00FF
-
-#define KS_RXFC				0x9D
-#define RXFCTR_RXFC_MASK		(0xff << 8)
-#define RXFCTR_RXFC_SHIFT		(8)
-#define RXFCTR_RXFC_GET(_v)		(((_v) >> 8) & 0xff)
-#define RXFCTR_RXFCT_MASK		(0xff << 0)
-#define RXFCTR_RXFCT_SHIFT		(0)
-
-#define KS_TXNTFSR			0x9E
-
-#define KS_MAHTR0			0xA0
-#define KS_MAHTR1			0xA2
-#define KS_MAHTR2			0xA4
-#define KS_MAHTR3			0xA6
-
-#define KS_FCLWR			0xB0
-#define KS_FCHWR			0xB2
-#define KS_FCOWR			0xB4
-
-#define KS_CIDER			0xC0
-#define CIDER_ID			0x8870
-#define CIDER_REV_MASK			(0x7 << 1)
-#define CIDER_REV_SHIFT			(1)
-#define CIDER_REV_GET(_v)		(((_v) >> 1) & 0x7)
-
-#define KS_CGCR				0xC6
-#define KS_IACR				0xC8
-#define IACR_RDEN			(1 << 12)
-#define IACR_TSEL_MASK			(0x3 << 10)
-#define IACR_TSEL_SHIFT			(10)
-#define IACR_TSEL_MIB			(0x3 << 10)
-#define IACR_ADDR_MASK			(0x1f << 0)
-#define IACR_ADDR_SHIFT			(0)
-
-#define KS_IADLR			0xD0
-#define KS_IAHDR			0xD2
-
-#define KS_PMECR			0xD4
-#define PMECR_PME_DELAY			(1 << 14)
-#define PMECR_PME_POL			(1 << 12)
-#define PMECR_WOL_WAKEUP		(1 << 11)
-#define PMECR_WOL_MAGICPKT		(1 << 10)
-#define PMECR_WOL_LINKUP		(1 << 9)
-#define PMECR_WOL_ENERGY		(1 << 8)
-#define PMECR_AUTO_WAKE_EN		(1 << 7)
-#define PMECR_WAKEUP_NORMAL		(1 << 6)
-#define PMECR_WKEVT_MASK		(0xf << 2)
-#define PMECR_WKEVT_SHIFT		(2)
-#define PMECR_WKEVT_GET(_v)		(((_v) >> 2) & 0xf)
-#define PMECR_WKEVT_ENERGY		(0x1 << 2)
-#define PMECR_WKEVT_LINK		(0x2 << 2)
-#define PMECR_WKEVT_MAGICPKT		(0x4 << 2)
-#define PMECR_WKEVT_FRAME		(0x8 << 2)
-#define PMECR_PM_MASK			(0x3 << 0)
-#define PMECR_PM_SHIFT			(0)
-#define PMECR_PM_NORMAL			(0x0 << 0)
-#define PMECR_PM_ENERGY			(0x1 << 0)
-#define PMECR_PM_SOFTDOWN		(0x2 << 0)
-#define PMECR_PM_POWERSAVE		(0x3 << 0)
-
-/* Standard MII PHY data */
-#define KS_P1MBCR			0xE4
-#define P1MBCR_FORCE_FDX		(1 << 8)
-
-#define KS_P1MBSR			0xE6
-#define P1MBSR_AN_COMPLETE		(1 << 5)
-#define P1MBSR_AN_CAPABLE		(1 << 3)
-#define P1MBSR_LINK_UP			(1 << 2)
-
-#define KS_PHY1ILR			0xE8
-#define KS_PHY1IHR			0xEA
-#define KS_P1ANAR			0xEC
-#define KS_P1ANLPR			0xEE
-
-#define KS_P1SCLMD			0xF4
-#define P1SCLMD_LEDOFF			(1 << 15)
-#define P1SCLMD_TXIDS			(1 << 14)
-#define P1SCLMD_RESTARTAN		(1 << 13)
-#define P1SCLMD_DISAUTOMDIX		(1 << 10)
-#define P1SCLMD_FORCEMDIX		(1 << 9)
-#define P1SCLMD_AUTONEGEN		(1 << 7)
-#define P1SCLMD_FORCE100		(1 << 6)
-#define P1SCLMD_FORCEFDX		(1 << 5)
-#define P1SCLMD_ADV_FLOW		(1 << 4)
-#define P1SCLMD_ADV_100BT_FDX		(1 << 3)
-#define P1SCLMD_ADV_100BT_HDX		(1 << 2)
-#define P1SCLMD_ADV_10BT_FDX		(1 << 1)
-#define P1SCLMD_ADV_10BT_HDX		(1 << 0)
-
-#define KS_P1CR				0xF6
-#define P1CR_HP_MDIX			(1 << 15)
-#define P1CR_REV_POL			(1 << 13)
-#define P1CR_OP_100M			(1 << 10)
-#define P1CR_OP_FDX			(1 << 9)
-#define P1CR_OP_MDI			(1 << 7)
-#define P1CR_AN_DONE			(1 << 6)
-#define P1CR_LINK_GOOD			(1 << 5)
-#define P1CR_PNTR_FLOW			(1 << 4)
-#define P1CR_PNTR_100BT_FDX		(1 << 3)
-#define P1CR_PNTR_100BT_HDX		(1 << 2)
-#define P1CR_PNTR_10BT_FDX		(1 << 1)
-#define P1CR_PNTR_10BT_HDX		(1 << 0)
-
-/* TX Frame control */
-
-#define TXFR_TXIC			(1 << 15)
-#define TXFR_TXFID_MASK			(0x3f << 0)
-#define TXFR_TXFID_SHIFT		(0)
-
-#define KS_P1SR				0xF8
-#define P1SR_HP_MDIX			(1 << 15)
-#define P1SR_REV_POL			(1 << 13)
-#define P1SR_OP_100M			(1 << 10)
-#define P1SR_OP_FDX			(1 << 9)
-#define P1SR_OP_MDI			(1 << 7)
-#define P1SR_AN_DONE			(1 << 6)
-#define P1SR_LINK_GOOD			(1 << 5)
-#define P1SR_PNTR_FLOW			(1 << 4)
-#define P1SR_PNTR_100BT_FDX		(1 << 3)
-#define P1SR_PNTR_100BT_HDX		(1 << 2)
-#define P1SR_PNTR_10BT_FDX		(1 << 1)
-#define P1SR_PNTR_10BT_HDX		(1 << 0)
-
 #define	ENUM_BUS_NONE			0
 #define	ENUM_BUS_8BIT			1
 #define	ENUM_BUS_16BIT			2
@@ -1475,7 +1168,7 @@ static void ks_setup(struct ks_net *ks)
 	ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI);
 
 	/* Setup Receive Frame Threshold - 1 frame (RXFCTFC) */
-	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_THRESHOLD_MASK);
+	ks_wrreg16(ks, KS_RXFCTR, 1 & RXFCTR_RXFCT_MASK);
 
 	/* Setup RxQ Command Control (RXQCR) */
 	ks->rc_rxqcr = RXQCR_CMD_CNTL;
@@ -1488,7 +1181,7 @@ static void ks_setup(struct ks_net *ks)
 	 */
 
 	w = ks_rdreg16(ks, KS_P1MBCR);
-	w &= ~P1MBCR_FORCE_FDX;
+	w &= ~BMCR_FULLDPLX;
 	ks_wrreg16(ks, KS_P1MBCR, w);
 
 	w = TXCR_TXFCE | TXCR_TXPE | TXCR_TXCRC | TXCR_TCGIP;
@@ -1629,7 +1322,7 @@ static int ks8851_probe(struct platform_device *pdev)
 	ks_setup_int(ks);
 
 	data = ks_rdreg16(ks, KS_OBCR);
-	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16MA);
+	ks_wrreg16(ks, KS_OBCR, data | OBCR_ODS_16mA);
 
 	/* overwriting the default MAC address */
 	if (pdev->dev.of_node) {
diff --git a/drivers/net/ethernet/microchip/enc28j60.c b/drivers/net/ethernet/microchip/enc28j60.c
index f6ecfa778660..8f72587b5a2c 100644
--- a/drivers/net/ethernet/microchip/enc28j60.c
+++ b/drivers/net/ethernet/microchip/enc28j60.c
@@ -1681,5 +1681,5 @@ MODULE_DESCRIPTION(DRV_NAME " ethernet driver");
 MODULE_AUTHOR("Claudio Lanconelli <lanconelli.claudio@eptar.com>");
 MODULE_LICENSE("GPL");
 module_param_named(debug, debug.msg_enable, int, 0);
-MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., ffff=all)");
+MODULE_PARM_DESC(debug, "Debug verbosity level in amount of bits set (0=none, ..., 31=all)");
 MODULE_ALIAS("spi:" DRV_NAME);
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 07c1eb63415a..3a0b289d9771 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -14,61 +14,138 @@
 #define EEPROM_INDICATOR_1		    (0xA5)
 #define EEPROM_INDICATOR_2		    (0xAA)
 #define EEPROM_MAC_OFFSET		    (0x01)
-#define MAX_EEPROM_SIZE			    512
+#define MAX_EEPROM_SIZE			    (512)
+#define MAX_OTP_SIZE			    (1024)
 #define OTP_INDICATOR_1			    (0xF3)
 #define OTP_INDICATOR_2			    (0xF7)
 
-static int lan743x_otp_write(struct lan743x_adapter *adapter, u32 offset,
-			     u32 length, u8 *data)
+static int lan743x_otp_power_up(struct lan743x_adapter *adapter)
+{
+	u32 reg_value;
+
+	reg_value = lan743x_csr_read(adapter, OTP_PWR_DN);
+
+	if (reg_value & OTP_PWR_DN_PWRDN_N_) {
+		/* clear it and wait to be cleared */
+		reg_value &= ~OTP_PWR_DN_PWRDN_N_;
+		lan743x_csr_write(adapter, OTP_PWR_DN, reg_value);
+
+		usleep_range(100, 20000);
+	}
+
+	return 0;
+}
+
+static void lan743x_otp_power_down(struct lan743x_adapter *adapter)
+{
+	u32 reg_value;
+
+	reg_value = lan743x_csr_read(adapter, OTP_PWR_DN);
+	if (!(reg_value & OTP_PWR_DN_PWRDN_N_)) {
+		/* set power down bit */
+		reg_value |= OTP_PWR_DN_PWRDN_N_;
+		lan743x_csr_write(adapter, OTP_PWR_DN, reg_value);
+	}
+}
+
+static void lan743x_otp_set_address(struct lan743x_adapter *adapter,
+				    u32 address)
+{
+	lan743x_csr_write(adapter, OTP_ADDR_HIGH, (address >> 8) & 0x03);
+	lan743x_csr_write(adapter, OTP_ADDR_LOW, address & 0xFF);
+}
+
+static void lan743x_otp_read_go(struct lan743x_adapter *adapter)
+{
+	lan743x_csr_write(adapter, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_);
+	lan743x_csr_write(adapter, OTP_CMD_GO, OTP_CMD_GO_GO_);
+}
+
+static int lan743x_otp_wait_till_not_busy(struct lan743x_adapter *adapter)
 {
 	unsigned long timeout;
-	u32 buf;
+	u32 reg_val;
+
+	timeout = jiffies + HZ;
+	do {
+		if (time_after(jiffies, timeout)) {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "Timeout on OTP_STATUS completion\n");
+			return -EIO;
+		}
+		udelay(1);
+		reg_val = lan743x_csr_read(adapter, OTP_STATUS);
+	} while (reg_val & OTP_STATUS_BUSY_);
+
+	return 0;
+}
+
+static int lan743x_otp_read(struct lan743x_adapter *adapter, u32 offset,
+			    u32 length, u8 *data)
+{
+	int ret;
 	int i;
 
-	buf = lan743x_csr_read(adapter, OTP_PWR_DN);
+	if (offset + length > MAX_OTP_SIZE)
+		return -EINVAL;
 
-	if (buf & OTP_PWR_DN_PWRDN_N_) {
-		/* clear it and wait to be cleared */
-		lan743x_csr_write(adapter, OTP_PWR_DN, 0);
-
-		timeout = jiffies + HZ;
-		do {
-			udelay(1);
-			buf = lan743x_csr_read(adapter, OTP_PWR_DN);
-			if (time_after(jiffies, timeout)) {
-				netif_warn(adapter, drv, adapter->netdev,
-					   "timeout on OTP_PWR_DN completion\n");
-				return -EIO;
-			}
-		} while (buf & OTP_PWR_DN_PWRDN_N_);
+	ret = lan743x_otp_power_up(adapter);
+	if (ret < 0)
+		return ret;
+
+	ret = lan743x_otp_wait_till_not_busy(adapter);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < length; i++) {
+		lan743x_otp_set_address(adapter, offset + i);
+
+		lan743x_otp_read_go(adapter);
+		ret = lan743x_otp_wait_till_not_busy(adapter);
+		if (ret < 0)
+			return ret;
+		data[i] = lan743x_csr_read(adapter, OTP_READ_DATA);
 	}
 
+	lan743x_otp_power_down(adapter);
+
+	return 0;
+}
+
+static int lan743x_otp_write(struct lan743x_adapter *adapter, u32 offset,
+			     u32 length, u8 *data)
+{
+	int ret;
+	int i;
+
+	if (offset + length > MAX_OTP_SIZE)
+		return -EINVAL;
+
+	ret = lan743x_otp_power_up(adapter);
+	if (ret < 0)
+		return ret;
+
+	ret = lan743x_otp_wait_till_not_busy(adapter);
+	if (ret < 0)
+		return ret;
+
 	/* set to BYTE program mode */
 	lan743x_csr_write(adapter, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_);
 
 	for (i = 0; i < length; i++) {
-		lan743x_csr_write(adapter, OTP_ADDR1,
-				  ((offset + i) >> 8) &
-				  OTP_ADDR1_15_11_MASK_);
-		lan743x_csr_write(adapter, OTP_ADDR2,
-				  ((offset + i) &
-				  OTP_ADDR2_10_3_MASK_));
+		lan743x_otp_set_address(adapter, offset + i);
+
 		lan743x_csr_write(adapter, OTP_PRGM_DATA, data[i]);
 		lan743x_csr_write(adapter, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
 		lan743x_csr_write(adapter, OTP_CMD_GO, OTP_CMD_GO_GO_);
 
-		timeout = jiffies + HZ;
-		do {
-			udelay(1);
-			buf = lan743x_csr_read(adapter, OTP_STATUS);
-			if (time_after(jiffies, timeout)) {
-				netif_warn(adapter, drv, adapter->netdev,
-					   "Timeout on OTP_STATUS completion\n");
-				return -EIO;
-			}
-		} while (buf & OTP_STATUS_BUSY_);
+		ret = lan743x_otp_wait_till_not_busy(adapter);
+		if (ret < 0)
+			return ret;
 	}
 
+	lan743x_otp_power_down(adapter);
+
 	return 0;
 }
 
@@ -120,6 +197,9 @@ static int lan743x_eeprom_read(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_eeprom_confirm_not_busy(adapter);
 	if (retval)
 		return retval;
@@ -148,6 +228,9 @@ static int lan743x_eeprom_write(struct lan743x_adapter *adapter,
 	u32 val;
 	int i;
 
+	if (offset + length > MAX_EEPROM_SIZE)
+		return -EINVAL;
+
 	retval = lan743x_eeprom_confirm_not_busy(adapter);
 	if (retval)
 		return retval;
@@ -207,6 +290,11 @@ static void lan743x_ethtool_set_msglevel(struct net_device *netdev,
 
 static int lan743x_ethtool_get_eeprom_len(struct net_device *netdev)
 {
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP)
+		return MAX_OTP_SIZE;
+
 	return MAX_EEPROM_SIZE;
 }
 
@@ -214,8 +302,14 @@ static int lan743x_ethtool_get_eeprom(struct net_device *netdev,
 				      struct ethtool_eeprom *ee, u8 *data)
 {
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret = 0;
+
+	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP)
+		ret = lan743x_otp_read(adapter, ee->offset, ee->len, data);
+	else
+		ret = lan743x_eeprom_read(adapter, ee->offset, ee->len, data);
 
-	return lan743x_eeprom_read(adapter, ee->offset, ee->len, data);
+	return ret;
 }
 
 static int lan743x_ethtool_set_eeprom(struct net_device *netdev,
@@ -224,17 +318,18 @@ static int lan743x_ethtool_set_eeprom(struct net_device *netdev,
 	struct lan743x_adapter *adapter = netdev_priv(netdev);
 	int ret = -EINVAL;
 
-	if (ee->magic == LAN743X_EEPROM_MAGIC)
-		ret = lan743x_eeprom_write(adapter, ee->offset, ee->len,
-					   data);
-	/* Beware!  OTP is One Time Programming ONLY!
-	 * So do some strict condition check before messing up
-	 */
-	else if ((ee->magic == LAN743X_OTP_MAGIC) &&
-		 (ee->offset == 0) &&
-		 (ee->len == MAX_EEPROM_SIZE) &&
-		 (data[0] == OTP_INDICATOR_1))
-		ret = lan743x_otp_write(adapter, ee->offset, ee->len, data);
+	if (adapter->flags & LAN743X_ADAPTER_FLAG_OTP) {
+		/* Beware!  OTP is One Time Programming ONLY! */
+		if (ee->magic == LAN743X_OTP_MAGIC) {
+			ret = lan743x_otp_write(adapter, ee->offset,
+						ee->len, data);
+		}
+	} else {
+		if (ee->magic == LAN743X_EEPROM_MAGIC) {
+			ret = lan743x_eeprom_write(adapter, ee->offset,
+						   ee->len, data);
+		}
+	}
 
 	return ret;
 }
@@ -360,6 +455,10 @@ static const u32 lan743x_set2_hw_cnt_addr[] = {
 	STAT_TX_COUNTER_ROLLOVER_STATUS
 };
 
+static const char lan743x_priv_flags_strings[][ETH_GSTRING_LEN] = {
+	"OTP_ACCESS",
+};
+
 static void lan743x_ethtool_get_strings(struct net_device *netdev,
 					u32 stringset, u8 *data)
 {
@@ -375,6 +474,10 @@ static void lan743x_ethtool_get_strings(struct net_device *netdev,
 		       lan743x_set2_hw_cnt_strings,
 		       sizeof(lan743x_set2_hw_cnt_strings));
 		break;
+	case ETH_SS_PRIV_FLAGS:
+		memcpy(data, lan743x_priv_flags_strings,
+		       sizeof(lan743x_priv_flags_strings));
+		break;
 	}
 }
 
@@ -399,6 +502,22 @@ static void lan743x_ethtool_get_ethtool_stats(struct net_device *netdev,
 	}
 }
 
+static u32 lan743x_ethtool_get_priv_flags(struct net_device *netdev)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->flags;
+}
+
+static int lan743x_ethtool_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	adapter->flags = flags;
+
+	return 0;
+}
+
 static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 {
 	switch (sset) {
@@ -411,6 +530,8 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 		ret += ARRAY_SIZE(lan743x_set2_hw_cnt_strings);
 		return ret;
 	}
+	case ETH_SS_PRIV_FLAGS:
+		return ARRAY_SIZE(lan743x_priv_flags_strings);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -705,6 +826,8 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.set_eeprom = lan743x_ethtool_set_eeprom,
 	.get_strings = lan743x_ethtool_get_strings,
 	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
+	.get_priv_flags = lan743x_ethtool_get_priv_flags,
+	.set_priv_flags = lan743x_ethtool_set_priv_flags,
 	.get_sset_count = lan743x_ethtool_get_sset_count,
 	.get_rxnfc = lan743x_ethtool_get_rxnfc,
 	.get_rxfh_key_size = lan743x_ethtool_get_rxfh_key_size,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 20c9377e99cb..13e6bf13ac4d 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -585,8 +585,7 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 
 		if (adapter->csr.flags &
 		   LAN743X_CSR_FLAG_SUPPORTS_INTR_AUTO_SET_CLR) {
-			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR |
-				LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
+			flags = LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_SET |
 				LAN743X_VECTOR_FLAG_SOURCE_ENABLE_AUTO_CLEAR |
 				LAN743X_VECTOR_FLAG_SOURCE_STATUS_AUTO_CLEAR;
@@ -599,12 +598,6 @@ static int lan743x_intr_open(struct lan743x_adapter *adapter)
 			/* map TX interrupt to vector */
 			int_vec_map1 |= INT_VEC_MAP1_TX_VEC_(index, vector);
 			lan743x_csr_write(adapter, INT_VEC_MAP1, int_vec_map1);
-			if (flags &
-			    LAN743X_VECTOR_FLAG_VECTOR_ENABLE_AUTO_CLEAR) {
-				int_vec_en_auto_clr |= INT_VEC_EN_(vector);
-				lan743x_csr_write(adapter, INT_VEC_EN_AUTO_CLR,
-						  int_vec_en_auto_clr);
-			}
 
 			/* Remove TX interrupt from shared mask */
 			intr->vector_list[0].int_mask &= ~int_bit;
@@ -962,13 +955,10 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 
 		memset(&ksettings, 0, sizeof(ksettings));
 		phy_ethtool_get_link_ksettings(netdev, &ksettings);
-		local_advertisement = phy_read(phydev, MII_ADVERTISE);
-		if (local_advertisement < 0)
-			return;
-
-		remote_advertisement = phy_read(phydev, MII_LPA);
-		if (remote_advertisement < 0)
-			return;
+		local_advertisement =
+			linkmode_adv_to_mii_adv_t(phydev->advertising);
+		remote_advertisement =
+			linkmode_adv_to_mii_adv_t(phydev->lp_advertising);
 
 		lan743x_phy_update_flowcontrol(adapter,
 					       ksettings.base.duplex,
@@ -1403,7 +1393,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 }
 
 static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
-				     unsigned int frame_length)
+				     unsigned int frame_length,
+				     int nr_frags)
 {
 	/* called only from within lan743x_tx_xmit_frame.
 	 * assuming tx->ring_lock has already been acquired.
@@ -1413,6 +1404,10 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx,
 
 	/* wrap up previous descriptor */
 	tx->frame_data0 |= TX_DESC_DATA0_EXT_;
+	if (nr_frags <= 0) {
+		tx->frame_data0 |= TX_DESC_DATA0_LS_;
+		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	}
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	tx_descriptor->data0 = tx->frame_data0;
 
@@ -1517,8 +1512,11 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	u32 tx_tail_flags = 0;
 
 	/* wrap up previous descriptor */
-	tx->frame_data0 |= TX_DESC_DATA0_LS_;
-	tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	if ((tx->frame_data0 & TX_DESC_DATA0_DTYPE_MASK_) ==
+	    TX_DESC_DATA0_DTYPE_DATA_) {
+		tx->frame_data0 |= TX_DESC_DATA0_LS_;
+		tx->frame_data0 |= TX_DESC_DATA0_IOC_;
+	}
 
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	buffer_info = &tx->buffer_info[tx->frame_tail];
@@ -1603,7 +1601,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 	if (gso)
-		lan743x_tx_frame_add_lso(tx, frame_length);
+		lan743x_tx_frame_add_lso(tx, frame_length, nr_frags);
 
 	if (nr_frags <= 0)
 		goto finish;
@@ -1897,7 +1895,17 @@ static int lan743x_rx_next_index(struct lan743x_rx *rx, int index)
 	return ((++index) % rx->ring_size);
 }
 
-static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
+static struct sk_buff *lan743x_rx_allocate_skb(struct lan743x_rx *rx)
+{
+	int length = 0;
+
+	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
+	return __netdev_alloc_skb(rx->adapter->netdev,
+				  length, GFP_ATOMIC | GFP_DMA);
+}
+
+static int lan743x_rx_init_ring_element(struct lan743x_rx *rx, int index,
+					struct sk_buff *skb)
 {
 	struct lan743x_rx_buffer_info *buffer_info;
 	struct lan743x_rx_descriptor *descriptor;
@@ -1906,9 +1914,7 @@ static int lan743x_rx_allocate_ring_element(struct lan743x_rx *rx, int index)
 	length = (LAN743X_MAX_FRAME_SIZE + ETH_HLEN + 4 + RX_HEAD_PADDING);
 	descriptor = &rx->ring_cpu_ptr[index];
 	buffer_info = &rx->buffer_info[index];
-	buffer_info->skb = __netdev_alloc_skb(rx->adapter->netdev,
-					      length,
-					      GFP_ATOMIC | GFP_DMA);
+	buffer_info->skb = skb;
 	if (!(buffer_info->skb))
 		return -ENOMEM;
 	buffer_info->dma_ptr = dma_map_single(&rx->adapter->pdev->dev,
@@ -2055,8 +2061,19 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 		/* packet is available */
 		if (first_index == last_index) {
 			/* single buffer packet */
+			struct sk_buff *new_skb = NULL;
 			int packet_length;
 
+			new_skb = lan743x_rx_allocate_skb(rx);
+			if (!new_skb) {
+				/* failed to allocate next skb.
+				 * Memory is very low.
+				 * Drop this packet and reuse buffer.
+				 */
+				lan743x_rx_reuse_ring_element(rx, first_index);
+				goto process_extension;
+			}
+
 			buffer_info = &rx->buffer_info[first_index];
 			skb = buffer_info->skb;
 			descriptor = &rx->ring_cpu_ptr[first_index];
@@ -2076,7 +2093,7 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			skb_put(skb, packet_length - 4);
 			skb->protocol = eth_type_trans(skb,
 						       rx->adapter->netdev);
-			lan743x_rx_allocate_ring_element(rx, first_index);
+			lan743x_rx_init_ring_element(rx, first_index, new_skb);
 		} else {
 			int index = first_index;
 
@@ -2089,26 +2106,23 @@ static int lan743x_rx_process_packet(struct lan743x_rx *rx)
 			if (first_index <= last_index) {
 				while ((index >= first_index) &&
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			} else {
 				while ((index >= first_index) ||
 				       (index <= last_index)) {
-					lan743x_rx_release_ring_element(rx,
-									index);
-					lan743x_rx_allocate_ring_element(rx,
-									 index);
+					lan743x_rx_reuse_ring_element(rx,
+								      index);
 					index = lan743x_rx_next_index(rx,
 								      index);
 				}
 			}
 		}
 
+process_extension:
 		if (extension_index >= 0) {
 			descriptor = &rx->ring_cpu_ptr[extension_index];
 			buffer_info = &rx->buffer_info[extension_index];
@@ -2285,7 +2299,9 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
 
 	rx->last_head = 0;
 	for (index = 0; index < rx->ring_size; index++) {
-		ret = lan743x_rx_allocate_ring_element(rx, index);
+		struct sk_buff *new_skb = lan743x_rx_allocate_skb(rx);
+
+		ret = lan743x_rx_init_ring_element(rx, index, new_skb);
 		if (ret)
 			goto cleanup;
 	}
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 2d6eea18973e..3b02eeae5f45 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -26,6 +26,8 @@
 #define FPGA_REV_GET_MAJOR_(fpga_rev)	((fpga_rev) & 0x000000FF)
 
 #define HW_CFG					(0x010)
+#define HW_CFG_RELOAD_TYPE_ALL_			(0x00000FC0)
+#define HW_CFG_EE_OTP_RELOAD_			BIT(4)
 #define HW_CFG_LRST_				BIT(1)
 
 #define PMT_CTL					(0x014)
@@ -453,17 +455,19 @@
 #define OTP_PWR_DN				(0x1000)
 #define OTP_PWR_DN_PWRDN_N_			BIT(0)
 
-#define OTP_ADDR1				(0x1004)
-#define OTP_ADDR1_15_11_MASK_			(0x1F)
-
-#define OTP_ADDR2				(0x1008)
-#define OTP_ADDR2_10_3_MASK_			(0xFF)
+#define OTP_ADDR_HIGH				(0x1004)
+#define OTP_ADDR_LOW				(0x1008)
 
 #define OTP_PRGM_DATA				(0x1010)
 
 #define OTP_PRGM_MODE				(0x1014)
 #define OTP_PRGM_MODE_BYTE_			BIT(0)
 
+#define OTP_READ_DATA				(0x1018)
+
+#define OTP_FUNC_CMD				(0x1020)
+#define OTP_FUNC_CMD_READ_			BIT(0)
+
 #define OTP_TST_CMD				(0x1024)
 #define OTP_TST_CMD_PRGVRFY_			BIT(3)
 
@@ -713,6 +717,9 @@ struct lan743x_adapter {
 	struct lan743x_phy      phy;
 	struct lan743x_tx       tx[LAN743X_MAX_TX_CHANNELS];
 	struct lan743x_rx       rx[LAN743X_MAX_RX_CHANNELS];
+
+#define LAN743X_ADAPTER_FLAG_OTP		BIT(0)
+	u32			flags;
 };
 
 #define LAN743X_COMPONENT_FLAG_RX(channel)  BIT(20 + (channel))
diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c
index b34055ac476f..e1651756bf9d 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -81,11 +81,13 @@ static void moxart_mac_free_memory(struct net_device *ndev)
 				 priv->rx_buf_size, DMA_FROM_DEVICE);
 
 	if (priv->tx_desc_base)
-		dma_free_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM,
+		dma_free_coherent(&priv->pdev->dev,
+				  TX_REG_DESC_SIZE * TX_DESC_NUM,
 				  priv->tx_desc_base, priv->tx_base);
 
 	if (priv->rx_desc_base)
-		dma_free_coherent(NULL, RX_REG_DESC_SIZE * RX_DESC_NUM,
+		dma_free_coherent(&priv->pdev->dev,
+				  RX_REG_DESC_SIZE * RX_DESC_NUM,
 				  priv->rx_desc_base, priv->rx_base);
 
 	kfree(priv->tx_buf_base);
@@ -298,7 +300,7 @@ static void moxart_tx_finished(struct net_device *ndev)
 		ndev->stats.tx_packets++;
 		ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len;
 
-		dev_kfree_skb_irq(priv->tx_skb[tx_tail]);
+		dev_consume_skb_irq(priv->tx_skb[tx_tail]);
 		priv->tx_skb[tx_tail] = NULL;
 
 		tx_tail = TX_NEXT(tx_tail);
@@ -476,6 +478,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 
 	priv = netdev_priv(ndev);
 	priv->ndev = ndev;
+	priv->pdev = pdev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ndev->base_addr = res->start;
@@ -491,7 +494,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 	priv->tx_buf_size = TX_BUF_SIZE;
 	priv->rx_buf_size = RX_BUF_SIZE;
 
-	priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE *
+	priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE *
 						TX_DESC_NUM, &priv->tx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->tx_desc_base) {
@@ -499,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev)
 		goto init_fail;
 	}
 
-	priv->rx_desc_base = dma_alloc_coherent(NULL, RX_REG_DESC_SIZE *
+	priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE *
 						RX_DESC_NUM, &priv->rx_base,
 						GFP_DMA | GFP_KERNEL);
 	if (!priv->rx_desc_base) {
diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h
index bee608b547d1..bf4c3029cd0c 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.h
+++ b/drivers/net/ethernet/moxa/moxart_ether.h
@@ -292,6 +292,7 @@
 #define LINK_STATUS		0x4
 
 struct moxart_mac_priv_t {
+	struct platform_device *pdev;
 	void __iomem *base;
 	unsigned int reg_maccr;
 	unsigned int reg_imr;
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index c84074fa4c95..d715ef4fc92f 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -15,6 +15,7 @@
 #include <linux/netdevice.h>
 #include <linux/phy.h>
 #include <linux/skbuff.h>
+#include <linux/iopoll.h>
 #include <net/arp.h>
 #include <net/netevent.h>
 #include <net/rtnetlink.h>
@@ -22,6 +23,9 @@
 
 #include "ocelot.h"
 
+#define TABLE_UPDATE_SLEEP_US 10
+#define TABLE_UPDATE_TIMEOUT_US 100000
+
 /* MAC table entry types.
  * ENTRYTYPE_NORMAL is subject to aging.
  * ENTRYTYPE_LOCKED is not subject to aging.
@@ -41,23 +45,20 @@ struct ocelot_mact_entry {
 	enum macaccess_entry_type type;
 };
 
-static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
+static inline u32 ocelot_mact_read_macaccess(struct ocelot *ocelot)
 {
-	unsigned int val, timeout = 10;
-
-	/* Wait for the issued mac table command to be completed, or timeout.
-	 * When the command read from  ANA_TABLES_MACACCESS is
-	 * MACACCESS_CMD_IDLE, the issued command completed successfully.
-	 */
-	do {
-		val = ocelot_read(ocelot, ANA_TABLES_MACACCESS);
-		val &= ANA_TABLES_MACACCESS_MAC_TABLE_CMD_M;
-	} while (val != MACACCESS_CMD_IDLE && timeout--);
+	return ocelot_read(ocelot, ANA_TABLES_MACACCESS);
+}
 
-	if (!timeout)
-		return -ETIMEDOUT;
+static inline int ocelot_mact_wait_for_completion(struct ocelot *ocelot)
+{
+	u32 val;
 
-	return 0;
+	return readx_poll_timeout(ocelot_mact_read_macaccess,
+		ocelot, val,
+		(val & ANA_TABLES_MACACCESS_MAC_TABLE_CMD_M) ==
+		MACACCESS_CMD_IDLE,
+		TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US);
 }
 
 static void ocelot_mact_select(struct ocelot *ocelot,
@@ -129,23 +130,21 @@ static void ocelot_mact_init(struct ocelot *ocelot)
 	ocelot_write(ocelot, MACACCESS_CMD_INIT, ANA_TABLES_MACACCESS);
 }
 
-static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
+static inline u32 ocelot_vlant_read_vlanaccess(struct ocelot *ocelot)
 {
-	unsigned int val, timeout = 10;
-
-	/* Wait for the issued vlan table command to be completed, or timeout.
-	 * When the command read from ANA_TABLES_VLANACCESS is
-	 * VLANACCESS_CMD_IDLE, the issued command completed successfully.
-	 */
-	do {
-		val = ocelot_read(ocelot, ANA_TABLES_VLANACCESS);
-		val &= ANA_TABLES_VLANACCESS_VLAN_TBL_CMD_M;
-	} while (val != ANA_TABLES_VLANACCESS_CMD_IDLE && timeout--);
+	return ocelot_read(ocelot, ANA_TABLES_VLANACCESS);
+}
 
-	if (!timeout)
-		return -ETIMEDOUT;
+static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
+{
+	u32 val;
 
-	return 0;
+	return readx_poll_timeout(ocelot_vlant_read_vlanaccess,
+		ocelot,
+		val,
+		(val & ANA_TABLES_VLANACCESS_VLAN_TBL_CMD_M) ==
+		ANA_TABLES_VLANACCESS_CMD_IDLE,
+		TABLE_UPDATE_SLEEP_US, TABLE_UPDATE_TIMEOUT_US);
 }
 
 static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask)
@@ -472,7 +471,6 @@ static int ocelot_port_open(struct net_device *dev)
 {
 	struct ocelot_port *port = netdev_priv(dev);
 	struct ocelot *ocelot = port->ocelot;
-	enum phy_mode phy_mode;
 	int err;
 
 	/* Enable receiving frames on the port, and activate auto-learning of
@@ -484,12 +482,8 @@ static int ocelot_port_open(struct net_device *dev)
 			 ANA_PORT_PORT_CFG, port->chip_port);
 
 	if (port->serdes) {
-		if (port->phy_mode == PHY_INTERFACE_MODE_SGMII)
-			phy_mode = PHY_MODE_SGMII;
-		else
-			phy_mode = PHY_MODE_QSGMII;
-
-		err = phy_set_mode(port->serdes, phy_mode);
+		err = phy_set_mode_ext(port->serdes, PHY_MODE_ETHERNET,
+				       port->phy_mode);
 		if (err) {
 			netdev_err(dev, "Could not set mode of SerDes\n");
 			return err;
@@ -619,7 +613,7 @@ static int ocelot_mact_mc_add(struct ocelot_port *port,
 			      struct netdev_hw_addr *hw_addr)
 {
 	struct ocelot *ocelot = port->ocelot;
-	struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_KERNEL);
+	struct netdev_hw_addr *ha = kzalloc(sizeof(*ha), GFP_ATOMIC);
 
 	if (!ha)
 		return -ENOMEM;
@@ -727,7 +721,8 @@ static void ocelot_get_stats64(struct net_device *dev,
 
 static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			  struct net_device *dev, const unsigned char *addr,
-			  u16 vid, u16 flags)
+			  u16 vid, u16 flags,
+			  struct netlink_ext_ack *extack)
 {
 	struct ocelot_port *port = netdev_priv(dev);
 	struct ocelot *ocelot = port->ocelot;
@@ -921,6 +916,18 @@ static int ocelot_set_features(struct net_device *dev,
 	return 0;
 }
 
+static int ocelot_get_port_parent_id(struct net_device *dev,
+				     struct netdev_phys_item_id *ppid)
+{
+	struct ocelot_port *ocelot_port = netdev_priv(dev);
+	struct ocelot *ocelot = ocelot_port->ocelot;
+
+	ppid->id_len = sizeof(ocelot->base_mac);
+	memcpy(&ppid->id, &ocelot->base_mac, ppid->id_len);
+
+	return 0;
+}
+
 static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_open			= ocelot_port_open,
 	.ndo_stop			= ocelot_port_stop,
@@ -935,6 +942,7 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_vlan_rx_add_vid		= ocelot_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid		= ocelot_vlan_rx_kill_vid,
 	.ndo_set_features		= ocelot_set_features,
+	.ndo_get_port_parent_id		= ocelot_get_port_parent_id,
 };
 
 static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
@@ -951,10 +959,8 @@ static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 		       ETH_GSTRING_LEN);
 }
 
-static void ocelot_check_stats(struct work_struct *work)
+static void ocelot_update_stats(struct ocelot *ocelot)
 {
-	struct delayed_work *del_work = to_delayed_work(work);
-	struct ocelot *ocelot = container_of(del_work, struct ocelot, stats_work);
 	int i, j;
 
 	mutex_lock(&ocelot->stats_lock);
@@ -978,11 +984,19 @@ static void ocelot_check_stats(struct work_struct *work)
 		}
 	}
 
-	cancel_delayed_work(&ocelot->stats_work);
+	mutex_unlock(&ocelot->stats_lock);
+}
+
+static void ocelot_check_stats_work(struct work_struct *work)
+{
+	struct delayed_work *del_work = to_delayed_work(work);
+	struct ocelot *ocelot = container_of(del_work, struct ocelot,
+					     stats_work);
+
+	ocelot_update_stats(ocelot);
+
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
-
-	mutex_unlock(&ocelot->stats_lock);
 }
 
 static void ocelot_get_ethtool_stats(struct net_device *dev,
@@ -993,7 +1007,7 @@ static void ocelot_get_ethtool_stats(struct net_device *dev,
 	int i;
 
 	/* check and update now */
-	ocelot_check_stats(&ocelot->stats_work.work);
+	ocelot_update_stats(ocelot);
 
 	/* Copy all counters */
 	for (i = 0; i < ocelot->num_stats; i++)
@@ -1018,25 +1032,6 @@ static const struct ethtool_ops ocelot_ethtool_ops = {
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
-static int ocelot_port_attr_get(struct net_device *dev,
-				struct switchdev_attr *attr)
-{
-	struct ocelot_port *ocelot_port = netdev_priv(dev);
-	struct ocelot *ocelot = ocelot_port->ocelot;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(ocelot->base_mac);
-		memcpy(&attr->u.ppid.id, &ocelot->base_mac,
-		       attr->u.ppid.id_len);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
 static int ocelot_port_attr_stp_state_set(struct ocelot_port *ocelot_port,
 					  struct switchdev_trans *trans,
 					  u8 state)
@@ -1293,7 +1288,8 @@ static int ocelot_port_obj_del_mdb(struct net_device *dev,
 
 static int ocelot_port_obj_add(struct net_device *dev,
 			       const struct switchdev_obj *obj,
-			       struct switchdev_trans *trans)
+			       struct switchdev_trans *trans,
+			       struct netlink_ext_ack *extack)
 {
 	int ret = 0;
 
@@ -1334,13 +1330,6 @@ static int ocelot_port_obj_del(struct net_device *dev,
 	return ret;
 }
 
-static const struct switchdev_ops ocelot_port_switchdev_ops = {
-	.switchdev_port_attr_get	= ocelot_port_attr_get,
-	.switchdev_port_attr_set	= ocelot_port_attr_set,
-	.switchdev_port_obj_add		= ocelot_port_obj_add,
-	.switchdev_port_obj_del		= ocelot_port_obj_del,
-};
-
 static int ocelot_port_bridge_join(struct ocelot_port *ocelot_port,
 				   struct net_device *bridge)
 {
@@ -1595,6 +1584,61 @@ struct notifier_block ocelot_netdevice_nb __read_mostly = {
 };
 EXPORT_SYMBOL(ocelot_netdevice_nb);
 
+static int ocelot_switchdev_event(struct notifier_block *unused,
+				  unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     ocelot_netdevice_dev_check,
+						     ocelot_port_attr_set);
+		return notifier_from_errno(err);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ocelot_switchdev_nb __read_mostly = {
+	.notifier_call = ocelot_switchdev_event,
+};
+EXPORT_SYMBOL(ocelot_switchdev_nb);
+
+static int ocelot_switchdev_blocking_event(struct notifier_block *unused,
+					   unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
+
+	switch (event) {
+		/* Blocking events. */
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    ocelot_netdevice_dev_check,
+						    ocelot_port_obj_add);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    ocelot_netdevice_dev_check,
+						    ocelot_port_obj_del);
+		return notifier_from_errno(err);
+	case SWITCHDEV_PORT_ATTR_SET:
+		err = switchdev_handle_port_attr_set(dev, ptr,
+						     ocelot_netdevice_dev_check,
+						     ocelot_port_attr_set);
+		return notifier_from_errno(err);
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = {
+	.notifier_call = ocelot_switchdev_blocking_event,
+};
+EXPORT_SYMBOL(ocelot_switchdev_blocking_nb);
+
 int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		      void __iomem *regs,
 		      struct phy_device *phy)
@@ -1618,7 +1662,6 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 
 	dev->netdev_ops = &ocelot_port_netdev_ops;
 	dev->ethtool_ops = &ocelot_ethtool_ops;
-	dev->switchdev_ops = &ocelot_port_switchdev_ops;
 
 	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_RXFCS;
 	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
@@ -1772,7 +1815,7 @@ int ocelot_init(struct ocelot *ocelot)
 				 ANA_CPUQ_8021_CFG_CPUQ_BPDU_VAL(6),
 				 ANA_CPUQ_8021_CFG, i);
 
-	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats);
+	INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work);
 	queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work,
 			   OCELOT_STATS_CHECK_DELAY);
 	return 0;
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 62c7c8eb00d9..ba3b3380b4d0 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -499,5 +499,7 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		      struct phy_device *phy);
 
 extern struct notifier_block ocelot_netdevice_nb;
+extern struct notifier_block ocelot_switchdev_nb;
+extern struct notifier_block ocelot_switchdev_blocking_nb;
 
 #endif
diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 4c23d18bbf44..e7f90101d2e0 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -12,6 +12,7 @@
 #include <linux/of_platform.h>
 #include <linux/mfd/syscon.h>
 #include <linux/skbuff.h>
+#include <net/switchdev.h>
 
 #include "ocelot.h"
 
@@ -266,6 +267,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		struct phy *serdes;
 		void __iomem *regs;
 		char res_name[8];
+		int phy_mode;
 		u32 port;
 
 		if (of_property_read_u32(portnp, "reg", &port))
@@ -291,11 +293,11 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		if (err)
 			return err;
 
-		err = of_get_phy_mode(portnp);
-		if (err < 0)
+		phy_mode = of_get_phy_mode(portnp);
+		if (phy_mode < 0)
 			ocelot->ports[port]->phy_mode = PHY_INTERFACE_MODE_NA;
 		else
-			ocelot->ports[port]->phy_mode = err;
+			ocelot->ports[port]->phy_mode = phy_mode;
 
 		switch (ocelot->ports[port]->phy_mode) {
 		case PHY_INTERFACE_MODE_NA:
@@ -303,6 +305,13 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 		case PHY_INTERFACE_MODE_SGMII:
 			break;
 		case PHY_INTERFACE_MODE_QSGMII:
+			/* Ensure clock signals and speed is set on all
+			 * QSGMII links
+			 */
+			ocelot_port_writel(ocelot->ports[port],
+					   DEV_CLOCK_CFG_LINK_SPEED
+					   (OCELOT_SPEED_1000),
+					   DEV_CLOCK_CFG);
 			break;
 		default:
 			dev_err(ocelot->dev,
@@ -328,6 +337,8 @@ static int mscc_ocelot_probe(struct platform_device *pdev)
 	}
 
 	register_netdevice_notifier(&ocelot_netdevice_nb);
+	register_switchdev_notifier(&ocelot_switchdev_nb);
+	register_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
 
 	dev_info(&pdev->dev, "Ocelot switch probed\n");
 
@@ -342,6 +353,8 @@ static int mscc_ocelot_remove(struct platform_device *pdev)
 	struct ocelot *ocelot = platform_get_drvdata(pdev);
 
 	ocelot_deinit(ocelot);
+	unregister_switchdev_blocking_notifier(&ocelot_switchdev_blocking_nb);
+	unregister_switchdev_notifier(&ocelot_switchdev_nb);
 	unregister_netdevice_notifier(&ocelot_netdevice_nb);
 
 	return 0;
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 5f384f73007d..e0340f778d8f 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -1408,7 +1408,7 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index)
 		if (skb) {
 			ss->stats.tx_bytes += skb->len;
 			ss->stats.tx_packets++;
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			if (len)
 				pci_unmap_single(pdev,
 						 dma_unmap_addr(&tx->info[idx],
@@ -3604,9 +3604,9 @@ static int myri10ge_alloc_slices(struct myri10ge_priv *mgp)
 	for (i = 0; i < mgp->num_slices; i++) {
 		ss = &mgp->ss[i];
 		bytes = mgp->max_intr_slots * sizeof(*ss->rx_done.entry);
-		ss->rx_done.entry = dma_zalloc_coherent(&pdev->dev, bytes,
-							&ss->rx_done.bus,
-							GFP_KERNEL);
+		ss->rx_done.entry = dma_alloc_coherent(&pdev->dev, bytes,
+						       &ss->rx_done.bus,
+						       GFP_KERNEL);
 		if (ss->rx_done.entry == NULL)
 			goto abort;
 		bytes = sizeof(*ss->fw_stats);
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index b9a1a9f999ea..1a2634cbbb69 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -2173,7 +2173,7 @@ static void netdev_tx_done(struct net_device *dev)
 					np->tx_skbuff[entry]->len,
 					PCI_DMA_TODEVICE);
 		/* Free the original skb. */
-		dev_kfree_skb_irq(np->tx_skbuff[entry]);
+		dev_consume_skb_irq(np->tx_skbuff[entry]);
 		np->tx_skbuff[entry] = NULL;
 	}
 	if (netif_queue_stopped(dev) &&
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 958fced4dacf..9098ee7fe0d1 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1003,7 +1003,7 @@ static void do_tx_done(struct net_device *ndev)
 					addr,
 					len,
 					PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			atomic_dec(&dev->nr_tx_skbs);
 		} else
 			pci_unmap_page(dev->pci_dev,
@@ -1869,56 +1869,28 @@ static unsigned ns83820_mii_write_reg(struct ns83820 *dev, unsigned phy, unsigne
 static void ns83820_probe_phy(struct net_device *ndev)
 {
 	struct ns83820 *dev = PRIV(ndev);
-	static int first;
-	int i;
-#define MII_PHYIDR1	0x02
-#define MII_PHYIDR2	0x03
-
-#if 0
-	if (!first) {
-		unsigned tmp;
-		ns83820_mii_read_reg(dev, 1, 0x09);
-		ns83820_mii_write_reg(dev, 1, 0x10, 0x0d3e);
-
-		tmp = ns83820_mii_read_reg(dev, 1, 0x00);
-		ns83820_mii_write_reg(dev, 1, 0x00, tmp | 0x8000);
-		udelay(1300);
-		ns83820_mii_read_reg(dev, 1, 0x09);
-	}
-#endif
-	first = 1;
-
-	for (i=1; i<2; i++) {
-		int j;
-		unsigned a, b;
-		a = ns83820_mii_read_reg(dev, i, MII_PHYIDR1);
-		b = ns83820_mii_read_reg(dev, i, MII_PHYIDR2);
-
-		//printk("%s: phy %d: 0x%04x 0x%04x\n",
-		//	ndev->name, i, a, b);
-
-		for (j=0; j<0x16; j+=4) {
-			dprintk("%s: [0x%02x] %04x %04x %04x %04x\n",
-				ndev->name, j,
-				ns83820_mii_read_reg(dev, i, 0 + j),
-				ns83820_mii_read_reg(dev, i, 1 + j),
-				ns83820_mii_read_reg(dev, i, 2 + j),
-				ns83820_mii_read_reg(dev, i, 3 + j)
-				);
-		}
-	}
-	{
-		unsigned a, b;
-		/* read firmware version: memory addr is 0x8402 and 0x8403 */
-		ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
-		ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
-		a = ns83820_mii_read_reg(dev, 1, 0x1d);
-
-		ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
-		ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
-		b = ns83820_mii_read_reg(dev, 1, 0x1d);
-		dprintk("version: 0x%04x 0x%04x\n", a, b);
+	int j;
+	unsigned a, b;
+
+	for (j = 0; j < 0x16; j += 4) {
+		dprintk("%s: [0x%02x] %04x %04x %04x %04x\n",
+			ndev->name, j,
+			ns83820_mii_read_reg(dev, 1, 0 + j),
+			ns83820_mii_read_reg(dev, 1, 1 + j),
+			ns83820_mii_read_reg(dev, 1, 2 + j),
+			ns83820_mii_read_reg(dev, 1, 3 + j)
+			);
 	}
+
+	/* read firmware version: memory addr is 0x8402 and 0x8403 */
+	ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
+	ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
+	a = ns83820_mii_read_reg(dev, 1, 0x1d);
+
+	ns83820_mii_write_reg(dev, 1, 0x16, 0x000d);
+	ns83820_mii_write_reg(dev, 1, 0x1e, 0x810e);
+	b = ns83820_mii_read_reg(dev, 1, 0x1d);
+	dprintk("version: 0x%04x 0x%04x\n", a, b);
 }
 #endif
 
diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c
index c805dcbebd02..aaec00912ea0 100644
--- a/drivers/net/ethernet/natsemi/sonic.c
+++ b/drivers/net/ethernet/natsemi/sonic.c
@@ -328,7 +328,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id)
 				}
 
 				/* We must free the original skb */
-				dev_kfree_skb_irq(lp->tx_skb[entry]);
+				dev_consume_skb_irq(lp->tx_skb[entry]);
 				lp->tx_skb[entry] = NULL;
 				/* and unmap DMA buffer */
 				dma_unmap_single(lp->device, lp->tx_laddr[entry], lp->tx_len[entry], DMA_TO_DEVICE);
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index c26e0f70c494..7df20561e3fa 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -26,7 +26,7 @@ config S2IO
 	  on its age.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/s2io.txt>.
+	  <file:Documentation/networking/device_drivers/neterion/s2io.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called s2io.
@@ -41,7 +41,7 @@ config VXGE
 	  labeled as either one, depending on its age.
 
 	  More specific information on configuring the driver is in
-	  <file:Documentation/networking/vxge.txt>.
+	  <file:Documentation/networking/device_drivers/neterion/vxge.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called vxge.
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 82be90075695..feda9644289d 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -3055,7 +3055,7 @@ static void tx_intr_handler(struct fifo_info *fifo_data)
 
 		/* Updating the statistics block */
 		swstats->mem_freed += skb->truesize;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 
 		get_info.offset++;
 		if (get_info.offset == get_info.fifo_len + 1)
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 7cde387e5ec6..51cd57ab3d95 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -2366,6 +2366,7 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 				dma_object->addr))) {
 			vxge_os_dma_free(devh->pdev, memblock,
 				&dma_object->acc_handle);
+			memblock = NULL;
 			goto exit;
 		}
 
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index 5ae3fa82909f..b877acec5cde 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -114,7 +114,7 @@ static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo)
 
 		/* free SKBs */
 		for (temp = completed; temp != skb_ptr; temp++)
-			dev_kfree_skb_irq(*temp);
+			dev_consume_skb_irq(*temp);
 	} while (more);
 }
 
@@ -2553,7 +2553,7 @@ static int vxge_add_isr(struct vxgedev *vdev)
 			vxge_debug_init(VXGE_ERR,
 				"%s: Defaulting to INTA",
 				vdev->ndev->name);
-				goto INTA_MODE;
+			goto INTA_MODE;
 		}
 
 		msix_idx = (vdev->vpaths[0].handle->vpath->vp_id *
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
index f7a0d1d5885e..59e77e3086bb 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c
@@ -1695,17 +1695,10 @@ exit:
  */
 void vxge_hw_fifo_txdl_free(struct __vxge_hw_fifo *fifo, void *txdlh)
 {
-	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
-	u32 max_frags;
 	struct __vxge_hw_channel *channel;
 
 	channel = &fifo->channel;
 
-	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo,
-			(struct vxge_hw_fifo_txd *)txdlh);
-
-	max_frags = fifo->config->max_frags;
-
 	vxge_hw_channel_dtr_free(channel, txdlh);
 }
 
diff --git a/drivers/net/ethernet/netronome/Kconfig b/drivers/net/ethernet/netronome/Kconfig
index 66f15b05b65e..549898d5d450 100644
--- a/drivers/net/ethernet/netronome/Kconfig
+++ b/drivers/net/ethernet/netronome/Kconfig
@@ -19,7 +19,6 @@ config NFP
 	tristate "Netronome(R) NFP4000/NFP6000 NIC driver"
 	depends on PCI && PCI_MSI
 	depends on VXLAN || VXLAN=n
-	depends on MAY_USE_DEVLINK
 	---help---
 	  This driver supports the Netronome(R) NFP4000/NFP6000 based
 	  cards working as a advanced Ethernet NIC.  It works with both
diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile
index 4afb10375397..47c708f08ade 100644
--- a/drivers/net/ethernet/netronome/nfp/Makefile
+++ b/drivers/net/ethernet/netronome/nfp/Makefile
@@ -56,7 +56,9 @@ endif
 
 ifeq ($(CONFIG_NFP_APP_ABM_NIC),y)
 nfp-objs += \
+	    abm/cls.o \
 	    abm/ctrl.o \
+	    abm/qdisc.o \
 	    abm/main.o
 endif
 
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
new file mode 100644
index 000000000000..ff3913085665
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#include <linux/bitfield.h>
+#include <net/pkt_cls.h>
+
+#include "../nfpcore/nfp_cpp.h"
+#include "../nfp_app.h"
+#include "../nfp_net_repr.h"
+#include "main.h"
+
+struct nfp_abm_u32_match {
+	u32 handle;
+	u32 band;
+	u8 mask;
+	u8 val;
+	struct list_head list;
+};
+
+static bool
+nfp_abm_u32_check_knode(struct nfp_abm *abm, struct tc_cls_u32_knode *knode,
+			__be16 proto, struct netlink_ext_ack *extack)
+{
+	struct tc_u32_key *k;
+	unsigned int tos_off;
+
+	if (knode->exts && tcf_exts_has_actions(knode->exts)) {
+		NL_SET_ERR_MSG_MOD(extack, "action offload not supported");
+		return false;
+	}
+	if (knode->link_handle) {
+		NL_SET_ERR_MSG_MOD(extack, "linking not supported");
+		return false;
+	}
+	if (knode->sel->flags != TC_U32_TERMINAL) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "flags must be equal to TC_U32_TERMINAL");
+		return false;
+	}
+	if (knode->sel->off || knode->sel->offshift || knode->sel->offmask ||
+	    knode->sel->offoff || knode->fshift) {
+		NL_SET_ERR_MSG_MOD(extack, "variable offsetting not supported");
+		return false;
+	}
+	if (knode->sel->hoff || knode->sel->hmask) {
+		NL_SET_ERR_MSG_MOD(extack, "hashing not supported");
+		return false;
+	}
+	if (knode->val || knode->mask) {
+		NL_SET_ERR_MSG_MOD(extack, "matching on mark not supported");
+		return false;
+	}
+	if (knode->res && knode->res->class) {
+		NL_SET_ERR_MSG_MOD(extack, "setting non-0 class not supported");
+		return false;
+	}
+	if (knode->res && knode->res->classid >= abm->num_bands) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "classid higher than number of bands");
+		return false;
+	}
+	if (knode->sel->nkeys != 1) {
+		NL_SET_ERR_MSG_MOD(extack, "exactly one key required");
+		return false;
+	}
+
+	switch (proto) {
+	case htons(ETH_P_IP):
+		tos_off = 16;
+		break;
+	case htons(ETH_P_IPV6):
+		tos_off = 20;
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "only IP and IPv6 supported as filter protocol");
+		return false;
+	}
+
+	k = &knode->sel->keys[0];
+	if (k->offmask) {
+		NL_SET_ERR_MSG_MOD(extack, "offset mask - variable offsetting not supported");
+		return false;
+	}
+	if (k->off) {
+		NL_SET_ERR_MSG_MOD(extack, "only DSCP fields can be matched");
+		return false;
+	}
+	if (k->val & ~k->mask) {
+		NL_SET_ERR_MSG_MOD(extack, "mask does not cover the key");
+		return false;
+	}
+	if (be32_to_cpu(k->mask) >> tos_off & ~abm->dscp_mask) {
+		NL_SET_ERR_MSG_MOD(extack, "only high DSCP class selector bits can be used");
+		nfp_err(abm->app->cpp,
+			"u32 offload: requested mask %x FW can support only %x\n",
+			be32_to_cpu(k->mask) >> tos_off, abm->dscp_mask);
+		return false;
+	}
+
+	return true;
+}
+
+/* This filter list -> map conversion is O(n * m), we expect single digit or
+ * low double digit number of prios and likewise for the filters.  Also u32
+ * doesn't report stats, so it's really only setup time cost.
+ */
+static unsigned int
+nfp_abm_find_band_for_prio(struct nfp_abm_link *alink, unsigned int prio)
+{
+	struct nfp_abm_u32_match *iter;
+
+	list_for_each_entry(iter, &alink->dscp_map, list)
+		if ((prio & iter->mask) == iter->val)
+			return iter->band;
+
+	return alink->def_band;
+}
+
+static int nfp_abm_update_band_map(struct nfp_abm_link *alink)
+{
+	unsigned int i, bits_per_prio, prios_per_word, base_shift;
+	struct nfp_abm *abm = alink->abm;
+	u32 field_mask;
+
+	alink->has_prio = !list_empty(&alink->dscp_map);
+
+	bits_per_prio = roundup_pow_of_two(order_base_2(abm->num_bands));
+	field_mask = (1 << bits_per_prio) - 1;
+	prios_per_word = sizeof(u32) * BITS_PER_BYTE / bits_per_prio;
+
+	/* FW mask applies from top bits */
+	base_shift = 8 - order_base_2(abm->num_prios);
+
+	for (i = 0; i < abm->num_prios; i++) {
+		unsigned int offset;
+		u32 *word;
+		u8 band;
+
+		word = &alink->prio_map[i / prios_per_word];
+		offset = (i % prios_per_word) * bits_per_prio;
+
+		band = nfp_abm_find_band_for_prio(alink, i << base_shift);
+
+		*word &= ~(field_mask << offset);
+		*word |= band << offset;
+	}
+
+	/* Qdisc offload status may change if has_prio changed */
+	nfp_abm_qdisc_offload_update(alink);
+
+	return nfp_abm_ctrl_prio_map_update(alink, alink->prio_map);
+}
+
+static void
+nfp_abm_u32_knode_delete(struct nfp_abm_link *alink,
+			 struct tc_cls_u32_knode *knode)
+{
+	struct nfp_abm_u32_match *iter;
+
+	list_for_each_entry(iter, &alink->dscp_map, list)
+		if (iter->handle == knode->handle) {
+			list_del(&iter->list);
+			kfree(iter);
+			nfp_abm_update_band_map(alink);
+			return;
+		}
+}
+
+static int
+nfp_abm_u32_knode_replace(struct nfp_abm_link *alink,
+			  struct tc_cls_u32_knode *knode,
+			  __be16 proto, struct netlink_ext_ack *extack)
+{
+	struct nfp_abm_u32_match *match = NULL, *iter;
+	unsigned int tos_off;
+	u8 mask, val;
+	int err;
+
+	if (!nfp_abm_u32_check_knode(alink->abm, knode, proto, extack))
+		goto err_delete;
+
+	tos_off = proto == htons(ETH_P_IP) ? 16 : 20;
+
+	/* Extract the DSCP Class Selector bits */
+	val = be32_to_cpu(knode->sel->keys[0].val) >> tos_off & 0xff;
+	mask = be32_to_cpu(knode->sel->keys[0].mask) >> tos_off & 0xff;
+
+	/* Check if there is no conflicting mapping and find match by handle */
+	list_for_each_entry(iter, &alink->dscp_map, list) {
+		u32 cmask;
+
+		if (iter->handle == knode->handle) {
+			match = iter;
+			continue;
+		}
+
+		cmask = iter->mask & mask;
+		if ((iter->val & cmask) == (val & cmask) &&
+		    iter->band != knode->res->classid) {
+			NL_SET_ERR_MSG_MOD(extack, "conflict with already offloaded filter");
+			goto err_delete;
+		}
+	}
+
+	if (!match) {
+		match = kzalloc(sizeof(*match), GFP_KERNEL);
+		if (!match)
+			return -ENOMEM;
+		list_add(&match->list, &alink->dscp_map);
+	}
+	match->handle = knode->handle;
+	match->band = knode->res->classid;
+	match->mask = mask;
+	match->val = val;
+
+	err = nfp_abm_update_band_map(alink);
+	if (err)
+		goto err_delete;
+
+	return 0;
+
+err_delete:
+	nfp_abm_u32_knode_delete(alink, knode);
+	return -EOPNOTSUPP;
+}
+
+static int nfp_abm_setup_tc_block_cb(enum tc_setup_type type,
+				     void *type_data, void *cb_priv)
+{
+	struct tc_cls_u32_offload *cls_u32 = type_data;
+	struct nfp_repr *repr = cb_priv;
+	struct nfp_abm_link *alink;
+
+	alink = repr->app_priv;
+
+	if (type != TC_SETUP_CLSU32) {
+		NL_SET_ERR_MSG_MOD(cls_u32->common.extack,
+				   "only offload of u32 classifier supported");
+		return -EOPNOTSUPP;
+	}
+	if (!tc_cls_can_offload_and_chain0(repr->netdev, &cls_u32->common))
+		return -EOPNOTSUPP;
+
+	if (cls_u32->common.protocol != htons(ETH_P_IP) &&
+	    cls_u32->common.protocol != htons(ETH_P_IPV6)) {
+		NL_SET_ERR_MSG_MOD(cls_u32->common.extack,
+				   "only IP and IPv6 supported as filter protocol");
+		return -EOPNOTSUPP;
+	}
+
+	switch (cls_u32->command) {
+	case TC_CLSU32_NEW_KNODE:
+	case TC_CLSU32_REPLACE_KNODE:
+		return nfp_abm_u32_knode_replace(alink, &cls_u32->knode,
+						 cls_u32->common.protocol,
+						 cls_u32->common.extack);
+	case TC_CLSU32_DELETE_KNODE:
+		nfp_abm_u32_knode_delete(alink, &cls_u32->knode);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
+			    struct tc_block_offload *f)
+{
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     nfp_abm_setup_tc_block_cb,
+					     repr, repr, f->extack);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, nfp_abm_setup_tc_block_cb,
+					repr);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
index 3c661f422688..9584f03f3efa 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c
@@ -1,7 +1,9 @@
 // SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 
+#include <linux/bitops.h>
 #include <linux/kernel.h>
+#include <linux/log2.h>
 
 #include "../nfpcore/nfp_cpp.h"
 #include "../nfpcore/nfp_nffw.h"
@@ -11,38 +13,58 @@
 #include "../nfp_net.h"
 #include "main.h"
 
-#define NFP_QLVL_SYM_NAME	"_abi_nfd_out_q_lvls_%u"
+#define NFP_NUM_PRIOS_SYM_NAME	"_abi_pci_dscp_num_prio_%u"
+#define NFP_NUM_BANDS_SYM_NAME	"_abi_pci_dscp_num_band_%u"
+#define NFP_ACT_MASK_SYM_NAME	"_abi_nfd_out_q_actions_%u"
+
+#define NFP_RED_SUPPORT_SYM_NAME	"_abi_nfd_out_red_offload_%u"
+
+#define NFP_QLVL_SYM_NAME	"_abi_nfd_out_q_lvls_%u%s"
 #define NFP_QLVL_STRIDE		16
 #define NFP_QLVL_BLOG_BYTES	0
 #define NFP_QLVL_BLOG_PKTS	4
 #define NFP_QLVL_THRS		8
+#define NFP_QLVL_ACT		12
 
-#define NFP_QMSTAT_SYM_NAME	"_abi_nfdqm%u_stats"
+#define NFP_QMSTAT_SYM_NAME	"_abi_nfdqm%u_stats%s"
 #define NFP_QMSTAT_STRIDE	32
 #define NFP_QMSTAT_NON_STO	0
 #define NFP_QMSTAT_STO		8
 #define NFP_QMSTAT_DROP		16
 #define NFP_QMSTAT_ECN		24
 
+#define NFP_Q_STAT_SYM_NAME	"_abi_nfd_rxq_stats%u%s"
+#define NFP_Q_STAT_STRIDE	16
+#define NFP_Q_STAT_PKTS		0
+#define NFP_Q_STAT_BYTES	8
+
+#define NFP_NET_ABM_MBOX_CMD		NFP_NET_CFG_MBOX_SIMPLE_CMD
+#define NFP_NET_ABM_MBOX_RET		NFP_NET_CFG_MBOX_SIMPLE_RET
+#define NFP_NET_ABM_MBOX_DATALEN	NFP_NET_CFG_MBOX_SIMPLE_VAL
+#define NFP_NET_ABM_MBOX_RESERVED	(NFP_NET_CFG_MBOX_SIMPLE_VAL + 4)
+#define NFP_NET_ABM_MBOX_DATA		(NFP_NET_CFG_MBOX_SIMPLE_VAL + 8)
+
 static int
 nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
-		  unsigned int stride, unsigned int offset, unsigned int i,
-		  bool is_u64, u64 *res)
+		  unsigned int stride, unsigned int offset, unsigned int band,
+		  unsigned int queue, bool is_u64, u64 *res)
 {
 	struct nfp_cpp *cpp = alink->abm->app->cpp;
 	u64 val, sym_offset;
+	unsigned int qid;
 	u32 val32;
 	int err;
 
-	sym_offset = (alink->queue_base + i) * stride + offset;
+	qid = band * NFP_NET_MAX_RX_RINGS + alink->queue_base + queue;
+
+	sym_offset = qid * stride + offset;
 	if (is_u64)
 		err = __nfp_rtsym_readq(cpp, sym, 3, 0, sym_offset, &val);
 	else
 		err = __nfp_rtsym_readl(cpp, sym, 3, 0, sym_offset, &val32);
 	if (err) {
-		nfp_err(cpp,
-			"RED offload reading stat failed on vNIC %d queue %d\n",
-			alink->id, i);
+		nfp_err(cpp, "RED offload reading stat failed on vNIC %d band %d queue %d (+ %d)\n",
+			alink->id, band, queue, alink->queue_base);
 		return err;
 	}
 
@@ -50,175 +72,179 @@ nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
 	return 0;
 }
 
-static int
-nfp_abm_ctrl_stat_all(struct nfp_abm_link *alink, const struct nfp_rtsym *sym,
-		      unsigned int stride, unsigned int offset, bool is_u64,
-		      u64 *res)
+int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val)
 {
-	u64 val, sum = 0;
-	unsigned int i;
+	struct nfp_cpp *cpp = abm->app->cpp;
+	u64 sym_offset;
 	int err;
 
-	for (i = 0; i < alink->vnic->max_rx_rings; i++) {
-		err = nfp_abm_ctrl_stat(alink, sym, stride, offset, i,
-					is_u64, &val);
-		if (err)
-			return err;
-		sum += val;
+	__clear_bit(id, abm->threshold_undef);
+	if (abm->thresholds[id] == val)
+		return 0;
+
+	sym_offset = id * NFP_QLVL_STRIDE + NFP_QLVL_THRS;
+	err = __nfp_rtsym_writel(cpp, abm->q_lvls, 4, 0, sym_offset, val);
+	if (err) {
+		nfp_err(cpp,
+			"RED offload setting level failed on subqueue %d\n",
+			id);
+		return err;
 	}
 
-	*res = sum;
+	abm->thresholds[id] = val;
 	return 0;
 }
 
-int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int i, u32 val)
+int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, u32 val)
 {
-	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	unsigned int threshold;
+
+	threshold = band * NFP_NET_MAX_RX_RINGS + alink->queue_base + queue;
+
+	return __nfp_abm_ctrl_set_q_lvl(alink->abm, threshold, val);
+}
+
+int __nfp_abm_ctrl_set_q_act(struct nfp_abm *abm, unsigned int id,
+			     enum nfp_abm_q_action act)
+{
+	struct nfp_cpp *cpp = abm->app->cpp;
 	u64 sym_offset;
 	int err;
 
-	sym_offset = (alink->queue_base + i) * NFP_QLVL_STRIDE + NFP_QLVL_THRS;
-	err = __nfp_rtsym_writel(cpp, alink->abm->q_lvls, 4, 0,
-				 sym_offset, val);
+	if (abm->actions[id] == act)
+		return 0;
+
+	sym_offset = id * NFP_QLVL_STRIDE + NFP_QLVL_ACT;
+	err = __nfp_rtsym_writel(cpp, abm->q_lvls, 4, 0, sym_offset, act);
 	if (err) {
-		nfp_err(cpp, "RED offload setting level failed on vNIC %d queue %d\n",
-			alink->id, i);
+		nfp_err(cpp,
+			"RED offload setting action failed on subqueue %d\n",
+			id);
 		return err;
 	}
 
+	abm->actions[id] = act;
 	return 0;
 }
 
-int nfp_abm_ctrl_set_all_q_lvls(struct nfp_abm_link *alink, u32 val)
+int nfp_abm_ctrl_set_q_act(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, enum nfp_abm_q_action act)
+{
+	unsigned int qid;
+
+	qid = band * NFP_NET_MAX_RX_RINGS + alink->queue_base + queue;
+
+	return __nfp_abm_ctrl_set_q_act(alink->abm, qid, act);
+}
+
+u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int queue)
 {
-	int i, err;
+	unsigned int band;
+	u64 val, sum = 0;
 
-	for (i = 0; i < alink->vnic->max_rx_rings; i++) {
-		err = nfp_abm_ctrl_set_q_lvl(alink, i, val);
-		if (err)
-			return err;
+	for (band = 0; band < alink->abm->num_bands; band++) {
+		if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
+				      NFP_QMSTAT_STRIDE, NFP_QMSTAT_NON_STO,
+				      band, queue, true, &val))
+			return 0;
+		sum += val;
 	}
 
-	return 0;
+	return sum;
 }
 
-u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i)
+u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int queue)
 {
-	u64 val;
+	unsigned int band;
+	u64 val, sum = 0;
 
-	if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats, NFP_QMSTAT_STRIDE,
-			      NFP_QMSTAT_NON_STO, i, true, &val))
-		return 0;
-	return val;
+	for (band = 0; band < alink->abm->num_bands; band++) {
+		if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
+				      NFP_QMSTAT_STRIDE, NFP_QMSTAT_STO,
+				      band, queue, true, &val))
+			return 0;
+		sum += val;
+	}
+
+	return sum;
 }
 
-u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i)
+static int
+nfp_abm_ctrl_stat_basic(struct nfp_abm_link *alink, unsigned int band,
+			unsigned int queue, unsigned int off, u64 *val)
 {
-	u64 val;
+	if (!nfp_abm_has_prio(alink->abm)) {
+		if (!band) {
+			unsigned int id = alink->queue_base + queue;
+
+			*val = nn_readq(alink->vnic,
+					NFP_NET_CFG_RXR_STATS(id) + off);
+		} else {
+			*val = 0;
+		}
 
-	if (nfp_abm_ctrl_stat(alink, alink->abm->qm_stats, NFP_QMSTAT_STRIDE,
-			      NFP_QMSTAT_STO, i, true, &val))
 		return 0;
-	return val;
+	} else {
+		return nfp_abm_ctrl_stat(alink, alink->abm->q_stats,
+					 NFP_Q_STAT_STRIDE, off, band, queue,
+					 true, val);
+	}
 }
 
-int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int i,
-			      struct nfp_alink_stats *stats)
+int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int band,
+			      unsigned int queue, struct nfp_alink_stats *stats)
 {
 	int err;
 
-	stats->tx_pkts = nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i));
-	stats->tx_bytes = nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i) + 8);
+	err = nfp_abm_ctrl_stat_basic(alink, band, queue, NFP_Q_STAT_PKTS,
+				      &stats->tx_pkts);
+	if (err)
+		return err;
 
-	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls,
-				NFP_QLVL_STRIDE, NFP_QLVL_BLOG_BYTES,
-				i, false, &stats->backlog_bytes);
+	err = nfp_abm_ctrl_stat_basic(alink, band, queue, NFP_Q_STAT_BYTES,
+				      &stats->tx_bytes);
+	if (err)
+		return err;
+
+	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls, NFP_QLVL_STRIDE,
+				NFP_QLVL_BLOG_BYTES, band, queue, false,
+				&stats->backlog_bytes);
 	if (err)
 		return err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->q_lvls,
 				NFP_QLVL_STRIDE, NFP_QLVL_BLOG_PKTS,
-				i, false, &stats->backlog_pkts);
+				band, queue, false, &stats->backlog_pkts);
 	if (err)
 		return err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				i, true, &stats->drops);
+				band, queue, true, &stats->drops);
 	if (err)
 		return err;
 
 	return nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				 NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				 i, true, &stats->overlimits);
+				 band, queue, true, &stats->overlimits);
 }
 
-int nfp_abm_ctrl_read_stats(struct nfp_abm_link *alink,
-			    struct nfp_alink_stats *stats)
-{
-	u64 pkts = 0, bytes = 0;
-	int i, err;
-
-	for (i = 0; i < alink->vnic->max_rx_rings; i++) {
-		pkts += nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i));
-		bytes += nn_readq(alink->vnic, NFP_NET_CFG_RXR_STATS(i) + 8);
-	}
-	stats->tx_pkts = pkts;
-	stats->tx_bytes = bytes;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->q_lvls,
-				    NFP_QLVL_STRIDE, NFP_QLVL_BLOG_BYTES,
-				    false, &stats->backlog_bytes);
-	if (err)
-		return err;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->q_lvls,
-				    NFP_QLVL_STRIDE, NFP_QLVL_BLOG_PKTS,
-				    false, &stats->backlog_pkts);
-	if (err)
-		return err;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				    NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				    true, &stats->drops);
-	if (err)
-		return err;
-
-	return nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				     NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				     true, &stats->overlimits);
-}
-
-int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
+int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink,
+			       unsigned int band, unsigned int queue,
 			       struct nfp_alink_xstats *xstats)
 {
 	int err;
 
 	err = nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				i, true, &xstats->pdrop);
+				band, queue, true, &xstats->pdrop);
 	if (err)
 		return err;
 
 	return nfp_abm_ctrl_stat(alink, alink->abm->qm_stats,
 				 NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				 i, true, &xstats->ecn_marked);
-}
-
-int nfp_abm_ctrl_read_xstats(struct nfp_abm_link *alink,
-			     struct nfp_alink_xstats *xstats)
-{
-	int err;
-
-	err = nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				    NFP_QMSTAT_STRIDE, NFP_QMSTAT_DROP,
-				    true, &xstats->pdrop);
-	if (err)
-		return err;
-
-	return nfp_abm_ctrl_stat_all(alink, alink->abm->qm_stats,
-				     NFP_QMSTAT_STRIDE, NFP_QMSTAT_ECN,
-				     true, &xstats->ecn_marked);
+				 band, queue, true, &xstats->ecn_marked);
 }
 
 int nfp_abm_ctrl_qm_enable(struct nfp_abm *abm)
@@ -233,10 +259,64 @@ int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm)
 			    NULL, 0, NULL, 0);
 }
 
-void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink)
+int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed)
+{
+	struct nfp_net *nn = alink->vnic;
+	unsigned int i;
+	int err;
+
+	/* Write data_len and wipe reserved */
+	nn_writeq(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATALEN,
+		  alink->abm->prio_map_len);
+
+	for (i = 0; i < alink->abm->prio_map_len; i += sizeof(u32))
+		nn_writel(nn, nn->tlv_caps.mbox_off + NFP_NET_ABM_MBOX_DATA + i,
+			  packed[i / sizeof(u32)]);
+
+	err = nfp_net_reconfig_mbox(nn,
+				    NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET);
+	if (err)
+		nfp_err(alink->abm->app->cpp,
+			"setting DSCP -> VQ map failed with error %d\n", err);
+	return err;
+}
+
+static int nfp_abm_ctrl_prio_check_params(struct nfp_abm_link *alink)
+{
+	struct nfp_abm *abm = alink->abm;
+	struct nfp_net *nn = alink->vnic;
+	unsigned int min_mbox_sz;
+
+	if (!nfp_abm_has_prio(alink->abm))
+		return 0;
+
+	min_mbox_sz = NFP_NET_ABM_MBOX_DATA + alink->abm->prio_map_len;
+	if (nn->tlv_caps.mbox_len < min_mbox_sz) {
+		nfp_err(abm->app->pf->cpp, "vNIC mailbox too small for prio offload: %u, need: %u\n",
+			nn->tlv_caps.mbox_len,  min_mbox_sz);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink)
 {
 	alink->queue_base = nn_readl(alink->vnic, NFP_NET_CFG_START_RXQ);
 	alink->queue_base /= alink->vnic->stride_rx;
+
+	return nfp_abm_ctrl_prio_check_params(alink);
+}
+
+static unsigned int nfp_abm_ctrl_prio_map_size(struct nfp_abm *abm)
+{
+	unsigned int size;
+
+	size = roundup_pow_of_two(order_base_2(abm->num_bands));
+	size = DIV_ROUND_UP(size * abm->num_prios, BITS_PER_BYTE);
+	size = round_up(size, sizeof(u32));
+
+	return size;
 }
 
 static const struct nfp_rtsym *
@@ -260,33 +340,86 @@ nfp_abm_ctrl_find_rtsym(struct nfp_pf *pf, const char *name, unsigned int size)
 }
 
 static const struct nfp_rtsym *
-nfp_abm_ctrl_find_q_rtsym(struct nfp_pf *pf, const char *name,
-			  unsigned int size)
+nfp_abm_ctrl_find_q_rtsym(struct nfp_abm *abm, const char *name_fmt,
+			  size_t size)
 {
-	return nfp_abm_ctrl_find_rtsym(pf, name, size * NFP_NET_MAX_RX_RINGS);
+	char pf_symbol[64];
+
+	size = array3_size(size, abm->num_bands, NFP_NET_MAX_RX_RINGS);
+	snprintf(pf_symbol, sizeof(pf_symbol), name_fmt,
+		 abm->pf_id, nfp_abm_has_prio(abm) ? "_per_band" : "");
+
+	return nfp_abm_ctrl_find_rtsym(abm->app->pf, pf_symbol, size);
 }
 
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm)
 {
 	struct nfp_pf *pf = abm->app->pf;
 	const struct nfp_rtsym *sym;
-	unsigned int pf_id;
-	char pf_symbol[64];
+	int res;
+
+	abm->pf_id = nfp_cppcore_pcie_unit(pf->cpp);
+
+	/* Check if Qdisc offloads are supported */
+	res = nfp_pf_rtsym_read_optional(pf, NFP_RED_SUPPORT_SYM_NAME, 1);
+	if (res < 0)
+		return res;
+	abm->red_support = res;
+
+	/* Read count of prios and prio bands */
+	res = nfp_pf_rtsym_read_optional(pf, NFP_NUM_BANDS_SYM_NAME, 1);
+	if (res < 0)
+		return res;
+	abm->num_bands = res;
+
+	res = nfp_pf_rtsym_read_optional(pf, NFP_NUM_PRIOS_SYM_NAME, 1);
+	if (res < 0)
+		return res;
+	abm->num_prios = res;
+
+	/* Read available actions */
+	res = nfp_pf_rtsym_read_optional(pf, NFP_ACT_MASK_SYM_NAME,
+					 BIT(NFP_ABM_ACT_MARK_DROP));
+	if (res < 0)
+		return res;
+	abm->action_mask = res;
+
+	abm->prio_map_len = nfp_abm_ctrl_prio_map_size(abm);
+	abm->dscp_mask = GENMASK(7, 8 - order_base_2(abm->num_prios));
+
+	/* Check values are sane, U16_MAX is arbitrarily chosen as max */
+	if (!is_power_of_2(abm->num_bands) || !is_power_of_2(abm->num_prios) ||
+	    abm->num_bands > U16_MAX || abm->num_prios > U16_MAX ||
+	    (abm->num_bands == 1) != (abm->num_prios == 1)) {
+		nfp_err(pf->cpp,
+			"invalid priomap description num bands: %u and num prios: %u\n",
+			abm->num_bands, abm->num_prios);
+		return -EINVAL;
+	}
 
-	pf_id =	nfp_cppcore_pcie_unit(pf->cpp);
-	abm->pf_id = pf_id;
+	/* Find level and stat symbols */
+	if (!abm->red_support)
+		return 0;
 
-	snprintf(pf_symbol, sizeof(pf_symbol), NFP_QLVL_SYM_NAME, pf_id);
-	sym = nfp_abm_ctrl_find_q_rtsym(pf, pf_symbol, NFP_QLVL_STRIDE);
+	sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_QLVL_SYM_NAME,
+					NFP_QLVL_STRIDE);
 	if (IS_ERR(sym))
 		return PTR_ERR(sym);
 	abm->q_lvls = sym;
 
-	snprintf(pf_symbol, sizeof(pf_symbol), NFP_QMSTAT_SYM_NAME, pf_id);
-	sym = nfp_abm_ctrl_find_q_rtsym(pf, pf_symbol, NFP_QMSTAT_STRIDE);
+	sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_QMSTAT_SYM_NAME,
+					NFP_QMSTAT_STRIDE);
 	if (IS_ERR(sym))
 		return PTR_ERR(sym);
 	abm->qm_stats = sym;
 
+	if (nfp_abm_has_prio(abm)) {
+		sym = nfp_abm_ctrl_find_q_rtsym(abm, NFP_Q_STAT_SYM_NAME,
+						NFP_Q_STAT_STRIDE);
+		if (IS_ERR(sym))
+			return PTR_ERR(sym);
+		abm->q_stats = sym;
+	}
+
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c
index c0830c0c2c3f..4d4ff5844c47 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.c
@@ -2,14 +2,13 @@
 /* Copyright (C) 2018 Netronome Systems, Inc. */
 
 #include <linux/bitfield.h>
+#include <linux/bitmap.h>
 #include <linux/etherdevice.h>
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
 #include <linux/slab.h>
-#include <net/pkt_cls.h>
-#include <net/pkt_sched.h>
-#include <net/red.h>
 
 #include "../nfpcore/nfp.h"
 #include "../nfpcore/nfp_cpp.h"
@@ -28,269 +27,6 @@ static u32 nfp_abm_portid(enum nfp_repr_type rtype, unsigned int id)
 }
 
 static int
-__nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		     u32 handle, unsigned int qs, u32 init_val)
-{
-	struct nfp_port *port = nfp_port_from_netdev(netdev);
-	int ret;
-
-	ret = nfp_abm_ctrl_set_all_q_lvls(alink, init_val);
-	memset(alink->qdiscs, 0, sizeof(*alink->qdiscs) * alink->num_qdiscs);
-
-	alink->parent = handle;
-	alink->num_qdiscs = qs;
-	port->tc_offload_cnt = qs;
-
-	return ret;
-}
-
-static void
-nfp_abm_reset_root(struct net_device *netdev, struct nfp_abm_link *alink,
-		   u32 handle, unsigned int qs)
-{
-	__nfp_abm_reset_root(netdev, alink, handle, qs, ~0);
-}
-
-static int
-nfp_abm_red_find(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	unsigned int i = TC_H_MIN(opt->parent) - 1;
-
-	if (opt->parent == TC_H_ROOT)
-		i = 0;
-	else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent))
-		i = TC_H_MIN(opt->parent) - 1;
-	else
-		return -EOPNOTSUPP;
-
-	if (i >= alink->num_qdiscs || opt->handle != alink->qdiscs[i].handle)
-		return -EOPNOTSUPP;
-
-	return i;
-}
-
-static void
-nfp_abm_red_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
-		    u32 handle)
-{
-	unsigned int i;
-
-	for (i = 0; i < alink->num_qdiscs; i++)
-		if (handle == alink->qdiscs[i].handle)
-			break;
-	if (i == alink->num_qdiscs)
-		return;
-
-	if (alink->parent == TC_H_ROOT) {
-		nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-	} else {
-		nfp_abm_ctrl_set_q_lvl(alink, i, ~0);
-		memset(&alink->qdiscs[i], 0, sizeof(*alink->qdiscs));
-	}
-}
-
-static int
-nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
-		    struct tc_red_qopt_offload *opt)
-{
-	bool existing;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	existing = i >= 0;
-
-	if (opt->set.min != opt->set.max || !opt->set.is_ecn) {
-		nfp_warn(alink->abm->app->cpp,
-			 "RED offload failed - unsupported parameters\n");
-		err = -EINVAL;
-		goto err_destroy;
-	}
-
-	if (existing) {
-		if (alink->parent == TC_H_ROOT)
-			err = nfp_abm_ctrl_set_all_q_lvls(alink, opt->set.min);
-		else
-			err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
-		if (err)
-			goto err_destroy;
-		return 0;
-	}
-
-	if (opt->parent == TC_H_ROOT) {
-		i = 0;
-		err = __nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 1,
-					   opt->set.min);
-	} else if (TC_H_MAJ(alink->parent) == TC_H_MAJ(opt->parent)) {
-		i = TC_H_MIN(opt->parent) - 1;
-		err = nfp_abm_ctrl_set_q_lvl(alink, i, opt->set.min);
-	} else {
-		return -EINVAL;
-	}
-	/* Set the handle to try full clean up, in case IO failed */
-	alink->qdiscs[i].handle = opt->handle;
-	if (err)
-		goto err_destroy;
-
-	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink, &alink->qdiscs[i].stats);
-	else
-		err = nfp_abm_ctrl_read_q_stats(alink, i,
-						&alink->qdiscs[i].stats);
-	if (err)
-		goto err_destroy;
-
-	if (opt->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_xstats(alink,
-					       &alink->qdiscs[i].xstats);
-	else
-		err = nfp_abm_ctrl_read_q_xstats(alink, i,
-						 &alink->qdiscs[i].xstats);
-	if (err)
-		goto err_destroy;
-
-	alink->qdiscs[i].stats.backlog_pkts = 0;
-	alink->qdiscs[i].stats.backlog_bytes = 0;
-
-	return 0;
-err_destroy:
-	/* If the qdisc keeps on living, but we can't offload undo changes */
-	if (existing) {
-		opt->set.qstats->qlen -= alink->qdiscs[i].stats.backlog_pkts;
-		opt->set.qstats->backlog -=
-			alink->qdiscs[i].stats.backlog_bytes;
-	}
-	nfp_abm_red_destroy(netdev, alink, opt->handle);
-
-	return err;
-}
-
-static void
-nfp_abm_update_stats(struct nfp_alink_stats *new, struct nfp_alink_stats *old,
-		     struct tc_qopt_offload_stats *stats)
-{
-	_bstats_update(stats->bstats, new->tx_bytes - old->tx_bytes,
-		       new->tx_pkts - old->tx_pkts);
-	stats->qstats->qlen += new->backlog_pkts - old->backlog_pkts;
-	stats->qstats->backlog += new->backlog_bytes - old->backlog_bytes;
-	stats->qstats->overlimits += new->overlimits - old->overlimits;
-	stats->qstats->drops += new->drops - old->drops;
-}
-
-static int
-nfp_abm_red_stats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	struct nfp_alink_stats *prev_stats;
-	struct nfp_alink_stats stats;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	if (i < 0)
-		return i;
-	prev_stats = &alink->qdiscs[i].stats;
-
-	if (alink->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_stats(alink, &stats);
-	else
-		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
-	if (err)
-		return err;
-
-	nfp_abm_update_stats(&stats, prev_stats, &opt->stats);
-
-	*prev_stats = stats;
-
-	return 0;
-}
-
-static int
-nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
-{
-	struct nfp_alink_xstats *prev_xstats;
-	struct nfp_alink_xstats xstats;
-	int i, err;
-
-	i = nfp_abm_red_find(alink, opt);
-	if (i < 0)
-		return i;
-	prev_xstats = &alink->qdiscs[i].xstats;
-
-	if (alink->parent == TC_H_ROOT)
-		err = nfp_abm_ctrl_read_xstats(alink, &xstats);
-	else
-		err = nfp_abm_ctrl_read_q_xstats(alink, i, &xstats);
-	if (err)
-		return err;
-
-	opt->xstats->forced_mark += xstats.ecn_marked - prev_xstats->ecn_marked;
-	opt->xstats->pdrop += xstats.pdrop - prev_xstats->pdrop;
-
-	*prev_xstats = xstats;
-
-	return 0;
-}
-
-static int
-nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
-		     struct tc_red_qopt_offload *opt)
-{
-	switch (opt->command) {
-	case TC_RED_REPLACE:
-		return nfp_abm_red_replace(netdev, alink, opt);
-	case TC_RED_DESTROY:
-		nfp_abm_red_destroy(netdev, alink, opt->handle);
-		return 0;
-	case TC_RED_STATS:
-		return nfp_abm_red_stats(alink, opt);
-	case TC_RED_XSTATS:
-		return nfp_abm_red_xstats(alink, opt);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int
-nfp_abm_mq_stats(struct nfp_abm_link *alink, struct tc_mq_qopt_offload *opt)
-{
-	struct nfp_alink_stats stats;
-	unsigned int i;
-	int err;
-
-	for (i = 0; i < alink->num_qdiscs; i++) {
-		if (alink->qdiscs[i].handle == TC_H_UNSPEC)
-			continue;
-
-		err = nfp_abm_ctrl_read_q_stats(alink, i, &stats);
-		if (err)
-			return err;
-
-		nfp_abm_update_stats(&stats, &alink->qdiscs[i].stats,
-				     &opt->stats);
-	}
-
-	return 0;
-}
-
-static int
-nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
-		    struct tc_mq_qopt_offload *opt)
-{
-	switch (opt->command) {
-	case TC_MQ_CREATE:
-		nfp_abm_reset_root(netdev, alink, opt->handle,
-				   alink->total_queues);
-		return 0;
-	case TC_MQ_DESTROY:
-		if (opt->handle == alink->parent)
-			nfp_abm_reset_root(netdev, alink, TC_H_ROOT, 0);
-		return 0;
-	case TC_MQ_STATS:
-		return nfp_abm_mq_stats(alink, opt);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-static int
 nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		 enum tc_setup_type type, void *type_data)
 {
@@ -302,10 +38,16 @@ nfp_abm_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		return -EOPNOTSUPP;
 
 	switch (type) {
+	case TC_SETUP_ROOT_QDISC:
+		return nfp_abm_setup_root(netdev, repr->app_priv, type_data);
 	case TC_SETUP_QDISC_MQ:
 		return nfp_abm_setup_tc_mq(netdev, repr->app_priv, type_data);
 	case TC_SETUP_QDISC_RED:
 		return nfp_abm_setup_tc_red(netdev, repr->app_priv, type_data);
+	case TC_SETUP_QDISC_GRED:
+		return nfp_abm_setup_tc_gred(netdev, repr->app_priv, type_data);
+	case TC_SETUP_BLOCK:
+		return nfp_abm_setup_cls_block(netdev, repr, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -384,7 +126,9 @@ nfp_abm_spawn_repr(struct nfp_app *app, struct nfp_abm_link *alink,
 
 	reprs = nfp_reprs_get_locked(app, rtype);
 	WARN(nfp_repr_get_locked(app, reprs, alink->id), "duplicate repr");
+	rtnl_lock();
 	rcu_assign_pointer(reprs->reprs[alink->id], netdev);
+	rtnl_unlock();
 
 	nfp_info(app->cpp, "%s Port %d Representor(%s) created\n",
 		 ptype == NFP_PORT_PF_PORT ? "PCIe" : "Phys",
@@ -410,7 +154,9 @@ nfp_abm_kill_repr(struct nfp_app *app, struct nfp_abm_link *alink,
 	netdev = nfp_repr_get_locked(app, reprs, alink->id);
 	if (!netdev)
 		return;
+	rtnl_lock();
 	rcu_assign_pointer(reprs->reprs[alink->id], NULL);
+	rtnl_unlock();
 	synchronize_rcu();
 	/* Cast to make sure nfp_repr_clean_and_free() takes a nfp_repr */
 	nfp_repr_clean_and_free((struct nfp_repr *)netdev_priv(netdev));
@@ -461,6 +207,9 @@ static int nfp_abm_eswitch_set_switchdev(struct nfp_abm *abm)
 	struct nfp_net *nn;
 	int err;
 
+	if (!abm->red_support)
+		return -EOPNOTSUPP;
+
 	err = nfp_abm_ctrl_qm_enable(abm);
 	if (err)
 		return err;
@@ -573,31 +322,34 @@ nfp_abm_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id)
 	alink->abm = abm;
 	alink->vnic = nn;
 	alink->id = id;
-	alink->parent = TC_H_ROOT;
 	alink->total_queues = alink->vnic->max_rx_rings;
-	alink->qdiscs = kvcalloc(alink->total_queues, sizeof(*alink->qdiscs),
-				 GFP_KERNEL);
-	if (!alink->qdiscs) {
-		err = -ENOMEM;
+
+	INIT_LIST_HEAD(&alink->dscp_map);
+
+	err = nfp_abm_ctrl_read_params(alink);
+	if (err)
+		goto err_free_alink;
+
+	alink->prio_map = kzalloc(abm->prio_map_len, GFP_KERNEL);
+	if (!alink->prio_map)
 		goto err_free_alink;
-	}
 
 	/* This is a multi-host app, make sure MAC/PHY is up, but don't
 	 * make the MAC/PHY state follow the state of any of the ports.
 	 */
 	err = nfp_eth_set_configured(app->cpp, eth_port->index, true);
 	if (err < 0)
-		goto err_free_qdiscs;
+		goto err_free_priomap;
 
 	netif_keep_dst(nn->dp.netdev);
 
 	nfp_abm_vnic_set_mac(app->pf, abm, nn, id);
-	nfp_abm_ctrl_read_params(alink);
+	INIT_RADIX_TREE(&alink->qdiscs, GFP_KERNEL);
 
 	return 0;
 
-err_free_qdiscs:
-	kvfree(alink->qdiscs);
+err_free_priomap:
+	kfree(alink->prio_map);
 err_free_alink:
 	kfree(alink);
 	return err;
@@ -608,10 +360,20 @@ static void nfp_abm_vnic_free(struct nfp_app *app, struct nfp_net *nn)
 	struct nfp_abm_link *alink = nn->app_priv;
 
 	nfp_abm_kill_reprs(alink->abm, alink);
-	kvfree(alink->qdiscs);
+	WARN(!radix_tree_empty(&alink->qdiscs), "left over qdiscs\n");
+	kfree(alink->prio_map);
 	kfree(alink);
 }
 
+static int nfp_abm_vnic_init(struct nfp_app *app, struct nfp_net *nn)
+{
+	struct nfp_abm_link *alink = nn->app_priv;
+
+	if (nfp_abm_has_prio(alink->abm))
+		return nfp_abm_ctrl_prio_map_update(alink, alink->prio_map);
+	return 0;
+}
+
 static u64 *
 nfp_abm_port_get_stats(struct nfp_app *app, struct nfp_port *port, u64 *data)
 {
@@ -659,6 +421,21 @@ nfp_abm_port_get_stats_strings(struct nfp_app *app, struct nfp_port *port,
 	return data;
 }
 
+static int nfp_abm_fw_init_reset(struct nfp_abm *abm)
+{
+	unsigned int i;
+
+	if (!abm->red_support)
+		return 0;
+
+	for (i = 0; i < abm->num_bands * NFP_NET_MAX_RX_RINGS; i++) {
+		__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
+		__nfp_abm_ctrl_set_q_act(abm, i, NFP_ABM_ACT_DROP);
+	}
+
+	return nfp_abm_ctrl_qm_disable(abm);
+}
+
 static int nfp_abm_init(struct nfp_app *app)
 {
 	struct nfp_pf *pf = app->pf;
@@ -690,15 +467,31 @@ static int nfp_abm_init(struct nfp_app *app)
 	if (err)
 		goto err_free_abm;
 
+	err = -ENOMEM;
+	abm->num_thresholds = array_size(abm->num_bands, NFP_NET_MAX_RX_RINGS);
+	abm->threshold_undef = bitmap_zalloc(abm->num_thresholds, GFP_KERNEL);
+	if (!abm->threshold_undef)
+		goto err_free_abm;
+
+	abm->thresholds = kvcalloc(abm->num_thresholds,
+				   sizeof(*abm->thresholds), GFP_KERNEL);
+	if (!abm->thresholds)
+		goto err_free_thresh_umap;
+
+	abm->actions = kvcalloc(abm->num_thresholds, sizeof(*abm->actions),
+				GFP_KERNEL);
+	if (!abm->actions)
+		goto err_free_thresh;
+
 	/* We start in legacy mode, make sure advanced queuing is disabled */
-	err = nfp_abm_ctrl_qm_disable(abm);
+	err = nfp_abm_fw_init_reset(abm);
 	if (err)
-		goto err_free_abm;
+		goto err_free_act;
 
 	err = -ENOMEM;
 	reprs = nfp_reprs_alloc(pf->max_data_vnics);
 	if (!reprs)
-		goto err_free_abm;
+		goto err_free_act;
 	RCU_INIT_POINTER(app->reprs[NFP_REPR_TYPE_PHYS_PORT], reprs);
 
 	reprs = nfp_reprs_alloc(pf->max_data_vnics);
@@ -710,6 +503,12 @@ static int nfp_abm_init(struct nfp_app *app)
 
 err_free_phys:
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT);
+err_free_act:
+	kvfree(abm->actions);
+err_free_thresh:
+	kvfree(abm->thresholds);
+err_free_thresh_umap:
+	bitmap_free(abm->threshold_undef);
 err_free_abm:
 	kfree(abm);
 	app->priv = NULL;
@@ -723,6 +522,9 @@ static void nfp_abm_clean(struct nfp_app *app)
 	nfp_abm_eswitch_clean_up(abm);
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PF);
 	nfp_reprs_clean_and_free_by_type(app, NFP_REPR_TYPE_PHYS_PORT);
+	bitmap_free(abm->threshold_undef);
+	kvfree(abm->actions);
+	kvfree(abm->thresholds);
 	kfree(abm);
 	app->priv = NULL;
 }
@@ -736,6 +538,7 @@ const struct nfp_app_type app_abm = {
 
 	.vnic_alloc	= nfp_abm_vnic_alloc,
 	.vnic_free	= nfp_abm_vnic_free,
+	.vnic_init	= nfp_abm_vnic_init,
 
 	.port_get_stats		= nfp_abm_port_get_stats,
 	.port_get_stats_count	= nfp_abm_port_get_stats_count,
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index f907b7d98917..49749c60885e 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -4,7 +4,19 @@
 #ifndef __NFP_ABM_H__
 #define __NFP_ABM_H__ 1
 
+#include <linux/bits.h>
+#include <linux/list.h>
+#include <linux/radix-tree.h>
 #include <net/devlink.h>
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+
+/* Dump of 64 PRIOs and 256 REDs seems to take 850us on Xeon v4 @ 2.20GHz;
+ * 2.5ms / 400Hz seems more than sufficient for stats resolution.
+ */
+#define NFP_ABM_STATS_REFRESH_IVAL	(2500 * 1000) /* ns */
+
+#define NFP_ABM_LVL_INFINITY		S32_MAX
 
 struct nfp_app;
 struct nfp_net;
@@ -12,21 +24,64 @@ struct nfp_net;
 #define NFP_ABM_PORTID_TYPE	GENMASK(23, 16)
 #define NFP_ABM_PORTID_ID	GENMASK(7, 0)
 
+/* The possible actions if thresholds are exceeded */
+enum nfp_abm_q_action {
+	/* mark if ECN capable, otherwise drop */
+	NFP_ABM_ACT_MARK_DROP		= 0,
+	/* mark if ECN capable, otherwise goto QM */
+	NFP_ABM_ACT_MARK_QUEUE		= 1,
+	NFP_ABM_ACT_DROP		= 2,
+	NFP_ABM_ACT_QUEUE		= 3,
+	NFP_ABM_ACT_NOQUEUE		= 4,
+};
+
 /**
  * struct nfp_abm - ABM NIC app structure
  * @app:	back pointer to nfp_app
  * @pf_id:	ID of our PF link
+ *
+ * @red_support:	is RED offload supported
+ * @num_prios:	number of supported DSCP priorities
+ * @num_bands:	number of supported DSCP priority bands
+ * @action_mask:	bitmask of supported actions
+ *
+ * @thresholds:		current threshold configuration
+ * @threshold_undef:	bitmap of thresholds which have not been set
+ * @actions:		current FW action configuration
+ * @num_thresholds:	number of @thresholds and bits in @threshold_undef
+ *
+ * @prio_map_len:	computed length of FW priority map (in bytes)
+ * @dscp_mask:		mask FW will apply on DSCP field
+ *
  * @eswitch_mode:	devlink eswitch mode, advanced functions only visible
  *			in switchdev mode
+ *
  * @q_lvls:	queue level control area
  * @qm_stats:	queue statistics symbol
+ * @q_stats:	basic queue statistics (only in per-band case)
  */
 struct nfp_abm {
 	struct nfp_app *app;
 	unsigned int pf_id;
+
+	unsigned int red_support;
+	unsigned int num_prios;
+	unsigned int num_bands;
+	unsigned int action_mask;
+
+	u32 *thresholds;
+	unsigned long *threshold_undef;
+	u8 *actions;
+	size_t num_thresholds;
+
+	unsigned int prio_map_len;
+	u8 dscp_mask;
+
 	enum devlink_eswitch_mode eswitch_mode;
+
 	const struct nfp_rtsym *q_lvls;
 	const struct nfp_rtsym *qm_stats;
+	const struct nfp_rtsym *q_stats;
 };
 
 /**
@@ -57,16 +112,76 @@ struct nfp_alink_xstats {
 	u64 pdrop;
 };
 
+enum nfp_qdisc_type {
+	NFP_QDISC_NONE = 0,
+	NFP_QDISC_MQ,
+	NFP_QDISC_RED,
+	NFP_QDISC_GRED,
+};
+
+#define NFP_QDISC_UNTRACKED	((struct nfp_qdisc *)1UL)
+
 /**
- * struct nfp_red_qdisc - representation of single RED Qdisc
- * @handle:	handle of currently offloaded RED Qdisc
- * @stats:	statistics from last refresh
- * @xstats:	base of extended statistics
+ * struct nfp_qdisc - tracked TC Qdisc
+ * @netdev:		netdev on which Qdisc was created
+ * @type:		Qdisc type
+ * @handle:		handle of this Qdisc
+ * @parent_handle:	handle of the parent (unreliable if Qdisc was grafted)
+ * @use_cnt:		number of attachment points in the hierarchy
+ * @num_children:	current size of the @children array
+ * @children:		pointers to children
+ *
+ * @params_ok:		parameters of this Qdisc are OK for offload
+ * @offload_mark:	offload refresh state - selected for offload
+ * @offloaded:		Qdisc is currently offloaded to the HW
+ *
+ * @mq:			MQ Qdisc specific parameters and state
+ * @mq.stats:		current stats of the MQ Qdisc
+ * @mq.prev_stats:	previously reported @mq.stats
+ *
+ * @red:		RED Qdisc specific parameters and state
+ * @red.num_bands:	Number of valid entries in the @red.band table
+ * @red.band:		Per-band array of RED instances
+ * @red.band.ecn:		ECN marking is enabled (rather than drop)
+ * @red.band.threshold:		ECN marking threshold
+ * @red.band.stats:		current stats of the RED Qdisc
+ * @red.band.prev_stats:	previously reported @red.stats
+ * @red.band.xstats:		extended stats for RED - current
+ * @red.band.prev_xstats:	extended stats for RED - previously reported
  */
-struct nfp_red_qdisc {
+struct nfp_qdisc {
+	struct net_device *netdev;
+	enum nfp_qdisc_type type;
 	u32 handle;
-	struct nfp_alink_stats stats;
-	struct nfp_alink_xstats xstats;
+	u32 parent_handle;
+	unsigned int use_cnt;
+	unsigned int num_children;
+	struct nfp_qdisc **children;
+
+	bool params_ok;
+	bool offload_mark;
+	bool offloaded;
+
+	union {
+		/* NFP_QDISC_MQ */
+		struct {
+			struct nfp_alink_stats stats;
+			struct nfp_alink_stats prev_stats;
+		} mq;
+		/* TC_SETUP_QDISC_RED, TC_SETUP_QDISC_GRED */
+		struct {
+			unsigned int num_bands;
+
+			struct {
+				bool ecn;
+				u32 threshold;
+				struct nfp_alink_stats stats;
+				struct nfp_alink_stats prev_stats;
+				struct nfp_alink_xstats xstats;
+				struct nfp_alink_xstats prev_xstats;
+			} band[MAX_DPs];
+		} red;
+	};
 };
 
 /**
@@ -76,9 +191,17 @@ struct nfp_red_qdisc {
  * @id:		id of the data vNIC
  * @queue_base:	id of base to host queue within PCIe (not QC idx)
  * @total_queues:	number of PF queues
- * @parent:	handle of expected parent, i.e. handle of MQ, or TC_H_ROOT
- * @num_qdiscs:	number of currently used qdiscs
- * @qdiscs:	array of qdiscs
+ *
+ * @last_stats_update:	ktime of last stats update
+ *
+ * @prio_map:		current map of priorities
+ * @has_prio:		@prio_map is valid
+ *
+ * @def_band:		default band to use
+ * @dscp_map:		list of DSCP to band mappings
+ *
+ * @root_qdisc:	pointer to the current root of the Qdisc hierarchy
+ * @qdiscs:	all qdiscs recorded by major part of the handle
  */
 struct nfp_abm_link {
 	struct nfp_abm *abm;
@@ -86,26 +209,65 @@ struct nfp_abm_link {
 	unsigned int id;
 	unsigned int queue_base;
 	unsigned int total_queues;
-	u32 parent;
-	unsigned int num_qdiscs;
-	struct nfp_red_qdisc *qdiscs;
+
+	u64 last_stats_update;
+
+	u32 *prio_map;
+	bool has_prio;
+
+	u8 def_band;
+	struct list_head dscp_map;
+
+	struct nfp_qdisc *root_qdisc;
+	struct radix_tree_root qdiscs;
 };
 
-void nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
+static inline bool nfp_abm_has_prio(struct nfp_abm *abm)
+{
+	return abm->num_bands > 1;
+}
+
+static inline bool nfp_abm_has_drop(struct nfp_abm *abm)
+{
+	return abm->action_mask & BIT(NFP_ABM_ACT_DROP);
+}
+
+static inline bool nfp_abm_has_mark(struct nfp_abm *abm)
+{
+	return abm->action_mask & BIT(NFP_ABM_ACT_MARK_DROP);
+}
+
+void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink);
+int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct tc_root_qopt_offload *opt);
+int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
+			 struct tc_red_qopt_offload *opt);
+int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+			struct tc_mq_qopt_offload *opt);
+int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
+			  struct tc_gred_qopt_offload *opt);
+int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
+			    struct tc_block_offload *opt);
+
+int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
-int nfp_abm_ctrl_set_all_q_lvls(struct nfp_abm_link *alink, u32 val);
-int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int i,
-			   u32 val);
-int nfp_abm_ctrl_read_stats(struct nfp_abm_link *alink,
-			    struct nfp_alink_stats *stats);
-int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink, unsigned int i,
+int __nfp_abm_ctrl_set_q_lvl(struct nfp_abm *abm, unsigned int id, u32 val);
+int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, u32 val);
+int __nfp_abm_ctrl_set_q_act(struct nfp_abm *abm, unsigned int id,
+			     enum nfp_abm_q_action act);
+int nfp_abm_ctrl_set_q_act(struct nfp_abm_link *alink, unsigned int band,
+			   unsigned int queue, enum nfp_abm_q_action act);
+int nfp_abm_ctrl_read_q_stats(struct nfp_abm_link *alink,
+			      unsigned int band, unsigned int queue,
 			      struct nfp_alink_stats *stats);
-int nfp_abm_ctrl_read_xstats(struct nfp_abm_link *alink,
-			     struct nfp_alink_xstats *xstats);
-int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink, unsigned int i,
+int nfp_abm_ctrl_read_q_xstats(struct nfp_abm_link *alink,
+			       unsigned int band, unsigned int queue,
 			       struct nfp_alink_xstats *xstats);
 u64 nfp_abm_ctrl_stat_non_sto(struct nfp_abm_link *alink, unsigned int i);
 u64 nfp_abm_ctrl_stat_sto(struct nfp_abm_link *alink, unsigned int i);
 int nfp_abm_ctrl_qm_enable(struct nfp_abm *abm);
 int nfp_abm_ctrl_qm_disable(struct nfp_abm *abm);
+void nfp_abm_prio_map_update(struct nfp_abm *abm);
+int nfp_abm_ctrl_prio_map_update(struct nfp_abm_link *alink, u32 *packed);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/abm/qdisc.c b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
new file mode 100644
index 000000000000..2473fb5f75e5
--- /dev/null
+++ b/drivers/net/ethernet/netronome/nfp/abm/qdisc.c
@@ -0,0 +1,850 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#include <linux/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+#include <net/red.h>
+
+#include "../nfpcore/nfp_cpp.h"
+#include "../nfp_app.h"
+#include "../nfp_main.h"
+#include "../nfp_net.h"
+#include "../nfp_port.h"
+#include "main.h"
+
+static bool nfp_abm_qdisc_is_red(struct nfp_qdisc *qdisc)
+{
+	return qdisc->type == NFP_QDISC_RED || qdisc->type == NFP_QDISC_GRED;
+}
+
+static bool nfp_abm_qdisc_child_valid(struct nfp_qdisc *qdisc, unsigned int id)
+{
+	return qdisc->children[id] &&
+	       qdisc->children[id] != NFP_QDISC_UNTRACKED;
+}
+
+static void *nfp_abm_qdisc_tree_deref_slot(void __rcu **slot)
+{
+	return rtnl_dereference(*slot);
+}
+
+static void
+nfp_abm_stats_propagate(struct nfp_alink_stats *parent,
+			struct nfp_alink_stats *child)
+{
+	parent->tx_pkts		+= child->tx_pkts;
+	parent->tx_bytes	+= child->tx_bytes;
+	parent->backlog_pkts	+= child->backlog_pkts;
+	parent->backlog_bytes	+= child->backlog_bytes;
+	parent->overlimits	+= child->overlimits;
+	parent->drops		+= child->drops;
+}
+
+static void
+nfp_abm_stats_update_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
+			 unsigned int queue)
+{
+	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	unsigned int i;
+	int err;
+
+	if (!qdisc->offloaded)
+		return;
+
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		err = nfp_abm_ctrl_read_q_stats(alink, i, queue,
+						&qdisc->red.band[i].stats);
+		if (err)
+			nfp_err(cpp, "RED stats (%d, %d) read failed with error %d\n",
+				i, queue, err);
+
+		err = nfp_abm_ctrl_read_q_xstats(alink, i, queue,
+						 &qdisc->red.band[i].xstats);
+		if (err)
+			nfp_err(cpp, "RED xstats (%d, %d) read failed with error %d\n",
+				i, queue, err);
+	}
+}
+
+static void
+nfp_abm_stats_update_mq(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
+{
+	unsigned int i;
+
+	if (qdisc->type != NFP_QDISC_MQ)
+		return;
+
+	for (i = 0; i < alink->total_queues; i++)
+		if (nfp_abm_qdisc_child_valid(qdisc, i))
+			nfp_abm_stats_update_red(alink, qdisc->children[i], i);
+}
+
+static void __nfp_abm_stats_update(struct nfp_abm_link *alink, u64 time_now)
+{
+	alink->last_stats_update = time_now;
+	if (alink->root_qdisc)
+		nfp_abm_stats_update_mq(alink, alink->root_qdisc);
+}
+
+static void nfp_abm_stats_update(struct nfp_abm_link *alink)
+{
+	u64 now;
+
+	/* Limit the frequency of updates - stats of non-leaf qdiscs are a sum
+	 * of all their leafs, so we would read the same stat multiple times
+	 * for every dump.
+	 */
+	now = ktime_get();
+	if (now - alink->last_stats_update < NFP_ABM_STATS_REFRESH_IVAL)
+		return;
+
+	__nfp_abm_stats_update(alink, now);
+}
+
+static void
+nfp_abm_qdisc_unlink_children(struct nfp_qdisc *qdisc,
+			      unsigned int start, unsigned int end)
+{
+	unsigned int i;
+
+	for (i = start; i < end; i++)
+		if (nfp_abm_qdisc_child_valid(qdisc, i)) {
+			qdisc->children[i]->use_cnt--;
+			qdisc->children[i] = NULL;
+		}
+}
+
+static void
+nfp_abm_qdisc_offload_stop(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
+{
+	unsigned int i;
+
+	/* Don't complain when qdisc is getting unlinked */
+	if (qdisc->use_cnt)
+		nfp_warn(alink->abm->app->cpp, "Offload of '%08x' stopped\n",
+			 qdisc->handle);
+
+	if (!nfp_abm_qdisc_is_red(qdisc))
+		return;
+
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		qdisc->red.band[i].stats.backlog_pkts = 0;
+		qdisc->red.band[i].stats.backlog_bytes = 0;
+	}
+}
+
+static int
+__nfp_abm_stats_init(struct nfp_abm_link *alink, unsigned int band,
+		     unsigned int queue, struct nfp_alink_stats *prev_stats,
+		     struct nfp_alink_xstats *prev_xstats)
+{
+	u64 backlog_pkts, backlog_bytes;
+	int err;
+
+	/* Don't touch the backlog, backlog can only be reset after it has
+	 * been reported back to the tc qdisc stats.
+	 */
+	backlog_pkts = prev_stats->backlog_pkts;
+	backlog_bytes = prev_stats->backlog_bytes;
+
+	err = nfp_abm_ctrl_read_q_stats(alink, band, queue, prev_stats);
+	if (err) {
+		nfp_err(alink->abm->app->cpp,
+			"RED stats init (%d, %d) failed with error %d\n",
+			band, queue, err);
+		return err;
+	}
+
+	err = nfp_abm_ctrl_read_q_xstats(alink, band, queue, prev_xstats);
+	if (err) {
+		nfp_err(alink->abm->app->cpp,
+			"RED xstats init (%d, %d) failed with error %d\n",
+			band, queue, err);
+		return err;
+	}
+
+	prev_stats->backlog_pkts = backlog_pkts;
+	prev_stats->backlog_bytes = backlog_bytes;
+	return 0;
+}
+
+static int
+nfp_abm_stats_init(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
+		   unsigned int queue)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		err = __nfp_abm_stats_init(alink, i, queue,
+					   &qdisc->red.band[i].prev_stats,
+					   &qdisc->red.band[i].prev_xstats);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void
+nfp_abm_offload_compile_red(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc,
+			    unsigned int queue)
+{
+	bool good_red, good_gred;
+	unsigned int i;
+
+	good_red = qdisc->type == NFP_QDISC_RED &&
+		   qdisc->params_ok &&
+		   qdisc->use_cnt == 1 &&
+		   !alink->has_prio &&
+		   !qdisc->children[0];
+	good_gred = qdisc->type == NFP_QDISC_GRED &&
+		    qdisc->params_ok &&
+		    qdisc->use_cnt == 1;
+	qdisc->offload_mark = good_red || good_gred;
+
+	/* If we are starting offload init prev_stats */
+	if (qdisc->offload_mark && !qdisc->offloaded)
+		if (nfp_abm_stats_init(alink, qdisc, queue))
+			qdisc->offload_mark = false;
+
+	if (!qdisc->offload_mark)
+		return;
+
+	for (i = 0; i < alink->abm->num_bands; i++) {
+		enum nfp_abm_q_action act;
+
+		nfp_abm_ctrl_set_q_lvl(alink, i, queue,
+				       qdisc->red.band[i].threshold);
+		act = qdisc->red.band[i].ecn ?
+			NFP_ABM_ACT_MARK_DROP : NFP_ABM_ACT_DROP;
+		nfp_abm_ctrl_set_q_act(alink, i, queue, act);
+	}
+}
+
+static void
+nfp_abm_offload_compile_mq(struct nfp_abm_link *alink, struct nfp_qdisc *qdisc)
+{
+	unsigned int i;
+
+	qdisc->offload_mark = qdisc->type == NFP_QDISC_MQ;
+	if (!qdisc->offload_mark)
+		return;
+
+	for (i = 0; i < alink->total_queues; i++) {
+		struct nfp_qdisc *child = qdisc->children[i];
+
+		if (!nfp_abm_qdisc_child_valid(qdisc, i))
+			continue;
+
+		nfp_abm_offload_compile_red(alink, child, i);
+	}
+}
+
+void nfp_abm_qdisc_offload_update(struct nfp_abm_link *alink)
+{
+	struct nfp_abm *abm = alink->abm;
+	struct radix_tree_iter iter;
+	struct nfp_qdisc *qdisc;
+	void __rcu **slot;
+	size_t i;
+
+	/* Mark all thresholds as unconfigured */
+	for (i = 0; i < abm->num_bands; i++)
+		__bitmap_set(abm->threshold_undef,
+			     i * NFP_NET_MAX_RX_RINGS + alink->queue_base,
+			     alink->total_queues);
+
+	/* Clear offload marks */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		qdisc = nfp_abm_qdisc_tree_deref_slot(slot);
+		qdisc->offload_mark = false;
+	}
+
+	if (alink->root_qdisc)
+		nfp_abm_offload_compile_mq(alink, alink->root_qdisc);
+
+	/* Refresh offload status */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		qdisc = nfp_abm_qdisc_tree_deref_slot(slot);
+		if (!qdisc->offload_mark && qdisc->offloaded)
+			nfp_abm_qdisc_offload_stop(alink, qdisc);
+		qdisc->offloaded = qdisc->offload_mark;
+	}
+
+	/* Reset the unconfigured thresholds */
+	for (i = 0; i < abm->num_thresholds; i++)
+		if (test_bit(i, abm->threshold_undef))
+			__nfp_abm_ctrl_set_q_lvl(abm, i, NFP_ABM_LVL_INFINITY);
+
+	__nfp_abm_stats_update(alink, ktime_get());
+}
+
+static void
+nfp_abm_qdisc_clear_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct nfp_qdisc *qdisc)
+{
+	struct radix_tree_iter iter;
+	unsigned int mq_refs = 0;
+	void __rcu **slot;
+
+	if (!qdisc->use_cnt)
+		return;
+	/* MQ doesn't notify well on destruction, we need special handling of
+	 * MQ's children.
+	 */
+	if (qdisc->type == NFP_QDISC_MQ &&
+	    qdisc == alink->root_qdisc &&
+	    netdev->reg_state == NETREG_UNREGISTERING)
+		return;
+
+	/* Count refs held by MQ instances and clear pointers */
+	radix_tree_for_each_slot(slot, &alink->qdiscs, &iter, 0) {
+		struct nfp_qdisc *mq = nfp_abm_qdisc_tree_deref_slot(slot);
+		unsigned int i;
+
+		if (mq->type != NFP_QDISC_MQ || mq->netdev != netdev)
+			continue;
+		for (i = 0; i < mq->num_children; i++)
+			if (mq->children[i] == qdisc) {
+				mq->children[i] = NULL;
+				mq_refs++;
+			}
+	}
+
+	WARN(qdisc->use_cnt != mq_refs, "non-zero qdisc use count: %d (- %d)\n",
+	     qdisc->use_cnt, mq_refs);
+}
+
+static void
+nfp_abm_qdisc_free(struct net_device *netdev, struct nfp_abm_link *alink,
+		   struct nfp_qdisc *qdisc)
+{
+	struct nfp_port *port = nfp_port_from_netdev(netdev);
+
+	if (!qdisc)
+		return;
+	nfp_abm_qdisc_clear_mq(netdev, alink, qdisc);
+	WARN_ON(radix_tree_delete(&alink->qdiscs,
+				  TC_H_MAJ(qdisc->handle)) != qdisc);
+
+	kfree(qdisc->children);
+	kfree(qdisc);
+
+	port->tc_offload_cnt--;
+}
+
+static struct nfp_qdisc *
+nfp_abm_qdisc_alloc(struct net_device *netdev, struct nfp_abm_link *alink,
+		    enum nfp_qdisc_type type, u32 parent_handle, u32 handle,
+		    unsigned int children)
+{
+	struct nfp_port *port = nfp_port_from_netdev(netdev);
+	struct nfp_qdisc *qdisc;
+	int err;
+
+	qdisc = kzalloc(sizeof(*qdisc), GFP_KERNEL);
+	if (!qdisc)
+		return NULL;
+
+	if (children) {
+		qdisc->children = kcalloc(children, sizeof(void *), GFP_KERNEL);
+		if (!qdisc->children)
+			goto err_free_qdisc;
+	}
+
+	qdisc->netdev = netdev;
+	qdisc->type = type;
+	qdisc->parent_handle = parent_handle;
+	qdisc->handle = handle;
+	qdisc->num_children = children;
+
+	err = radix_tree_insert(&alink->qdiscs, TC_H_MAJ(qdisc->handle), qdisc);
+	if (err) {
+		nfp_err(alink->abm->app->cpp,
+			"Qdisc insertion into radix tree failed: %d\n", err);
+		goto err_free_child_tbl;
+	}
+
+	port->tc_offload_cnt++;
+	return qdisc;
+
+err_free_child_tbl:
+	kfree(qdisc->children);
+err_free_qdisc:
+	kfree(qdisc);
+	return NULL;
+}
+
+static struct nfp_qdisc *
+nfp_abm_qdisc_find(struct nfp_abm_link *alink, u32 handle)
+{
+	return radix_tree_lookup(&alink->qdiscs, TC_H_MAJ(handle));
+}
+
+static int
+nfp_abm_qdisc_replace(struct net_device *netdev, struct nfp_abm_link *alink,
+		      enum nfp_qdisc_type type, u32 parent_handle, u32 handle,
+		      unsigned int children, struct nfp_qdisc **qdisc)
+{
+	*qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (*qdisc) {
+		if (WARN_ON((*qdisc)->type != type))
+			return -EINVAL;
+		return 1;
+	}
+
+	*qdisc = nfp_abm_qdisc_alloc(netdev, alink, type, parent_handle, handle,
+				     children);
+	return *qdisc ? 0 : -ENOMEM;
+}
+
+static void
+nfp_abm_qdisc_destroy(struct net_device *netdev, struct nfp_abm_link *alink,
+		      u32 handle)
+{
+	struct nfp_qdisc *qdisc;
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return;
+
+	/* We don't get TC_SETUP_ROOT_QDISC w/ MQ when netdev is unregistered */
+	if (alink->root_qdisc == qdisc)
+		qdisc->use_cnt--;
+
+	nfp_abm_qdisc_unlink_children(qdisc, 0, qdisc->num_children);
+	nfp_abm_qdisc_free(netdev, alink, qdisc);
+
+	if (alink->root_qdisc == qdisc) {
+		alink->root_qdisc = NULL;
+		/* Only root change matters, other changes are acted upon on
+		 * the graft notification.
+		 */
+		nfp_abm_qdisc_offload_update(alink);
+	}
+}
+
+static int
+nfp_abm_qdisc_graft(struct nfp_abm_link *alink, u32 handle, u32 child_handle,
+		    unsigned int id)
+{
+	struct nfp_qdisc *parent, *child;
+
+	parent = nfp_abm_qdisc_find(alink, handle);
+	if (!parent)
+		return 0;
+
+	if (WARN(id >= parent->num_children,
+		 "graft child out of bound %d >= %d\n",
+		 id, parent->num_children))
+		return -EINVAL;
+
+	nfp_abm_qdisc_unlink_children(parent, id, id + 1);
+
+	child = nfp_abm_qdisc_find(alink, child_handle);
+	if (child)
+		child->use_cnt++;
+	else
+		child = NFP_QDISC_UNTRACKED;
+	parent->children[id] = child;
+
+	nfp_abm_qdisc_offload_update(alink);
+
+	return 0;
+}
+
+static void
+nfp_abm_stats_calculate(struct nfp_alink_stats *new,
+			struct nfp_alink_stats *old,
+			struct gnet_stats_basic_packed *bstats,
+			struct gnet_stats_queue *qstats)
+{
+	_bstats_update(bstats, new->tx_bytes - old->tx_bytes,
+		       new->tx_pkts - old->tx_pkts);
+	qstats->qlen += new->backlog_pkts - old->backlog_pkts;
+	qstats->backlog += new->backlog_bytes - old->backlog_bytes;
+	qstats->overlimits += new->overlimits - old->overlimits;
+	qstats->drops += new->drops - old->drops;
+}
+
+static void
+nfp_abm_stats_red_calculate(struct nfp_alink_xstats *new,
+			    struct nfp_alink_xstats *old,
+			    struct red_stats *stats)
+{
+	stats->forced_mark += new->ecn_marked - old->ecn_marked;
+	stats->pdrop += new->pdrop - old->pdrop;
+}
+
+static int
+nfp_abm_gred_stats(struct nfp_abm_link *alink, u32 handle,
+		   struct tc_gred_qopt_offload_stats *stats)
+{
+	struct nfp_qdisc *qdisc;
+	unsigned int i;
+
+	nfp_abm_stats_update(alink);
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return -EOPNOTSUPP;
+	/* If the qdisc offload has stopped we may need to adjust the backlog
+	 * counters back so carry on even if qdisc is not currently offloaded.
+	 */
+
+	for (i = 0; i < qdisc->red.num_bands; i++) {
+		if (!stats->xstats[i])
+			continue;
+
+		nfp_abm_stats_calculate(&qdisc->red.band[i].stats,
+					&qdisc->red.band[i].prev_stats,
+					&stats->bstats[i], &stats->qstats[i]);
+		qdisc->red.band[i].prev_stats = qdisc->red.band[i].stats;
+
+		nfp_abm_stats_red_calculate(&qdisc->red.band[i].xstats,
+					    &qdisc->red.band[i].prev_xstats,
+					    stats->xstats[i]);
+		qdisc->red.band[i].prev_xstats = qdisc->red.band[i].xstats;
+	}
+
+	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
+}
+
+static bool
+nfp_abm_gred_check_params(struct nfp_abm_link *alink,
+			  struct tc_gred_qopt_offload *opt)
+{
+	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	struct nfp_abm *abm = alink->abm;
+	unsigned int i;
+
+	if (opt->set.grio_on || opt->set.wred_on) {
+		nfp_warn(cpp, "GRED offload failed - GRIO and WRED not supported (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.dp_def != alink->def_band) {
+		nfp_warn(cpp, "GRED offload failed - default band must be %d (p:%08x h:%08x)\n",
+			 alink->def_band, opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.dp_cnt != abm->num_bands) {
+		nfp_warn(cpp, "GRED offload failed - band count must be %d (p:%08x h:%08x)\n",
+			 abm->num_bands, opt->parent, opt->handle);
+		return false;
+	}
+
+	for (i = 0; i < abm->num_bands; i++) {
+		struct tc_gred_vq_qopt_offload_params *band = &opt->set.tab[i];
+
+		if (!band->present)
+			return false;
+		if (!band->is_ecn && !nfp_abm_has_drop(abm)) {
+			nfp_warn(cpp, "GRED offload failed - drop is not supported (ECN option required) (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->is_ecn && !nfp_abm_has_mark(abm)) {
+			nfp_warn(cpp, "GRED offload failed - ECN marking not supported (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->is_harddrop) {
+			nfp_warn(cpp, "GRED offload failed - harddrop is not supported (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->min != band->max) {
+			nfp_warn(cpp, "GRED offload failed - threshold mismatch (p:%08x h:%08x vq:%d)\n",
+				 opt->parent, opt->handle, i);
+			return false;
+		}
+		if (band->min > S32_MAX) {
+			nfp_warn(cpp, "GRED offload failed - threshold too large %d > %d (p:%08x h:%08x vq:%d)\n",
+				 band->min, S32_MAX, opt->parent, opt->handle,
+				 i);
+			return false;
+		}
+	}
+
+	return true;
+}
+
+static int
+nfp_abm_gred_replace(struct net_device *netdev, struct nfp_abm_link *alink,
+		     struct tc_gred_qopt_offload *opt)
+{
+	struct nfp_qdisc *qdisc;
+	unsigned int i;
+	int ret;
+
+	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_GRED, opt->parent,
+				    opt->handle, 0, &qdisc);
+	if (ret < 0)
+		return ret;
+
+	qdisc->params_ok = nfp_abm_gred_check_params(alink, opt);
+	if (qdisc->params_ok) {
+		qdisc->red.num_bands = opt->set.dp_cnt;
+		for (i = 0; i < qdisc->red.num_bands; i++) {
+			qdisc->red.band[i].ecn = opt->set.tab[i].is_ecn;
+			qdisc->red.band[i].threshold = opt->set.tab[i].min;
+		}
+	}
+
+	if (qdisc->use_cnt)
+		nfp_abm_qdisc_offload_update(alink);
+
+	return 0;
+}
+
+int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
+			  struct tc_gred_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_GRED_REPLACE:
+		return nfp_abm_gred_replace(netdev, alink, opt);
+	case TC_GRED_DESTROY:
+		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
+		return 0;
+	case TC_GRED_STATS:
+		return nfp_abm_gred_stats(alink, opt->handle, &opt->stats);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nfp_abm_red_xstats(struct nfp_abm_link *alink, struct tc_red_qopt_offload *opt)
+{
+	struct nfp_qdisc *qdisc;
+
+	nfp_abm_stats_update(alink);
+
+	qdisc = nfp_abm_qdisc_find(alink, opt->handle);
+	if (!qdisc || !qdisc->offloaded)
+		return -EOPNOTSUPP;
+
+	nfp_abm_stats_red_calculate(&qdisc->red.band[0].xstats,
+				    &qdisc->red.band[0].prev_xstats,
+				    opt->xstats);
+	qdisc->red.band[0].prev_xstats = qdisc->red.band[0].xstats;
+	return 0;
+}
+
+static int
+nfp_abm_red_stats(struct nfp_abm_link *alink, u32 handle,
+		  struct tc_qopt_offload_stats *stats)
+{
+	struct nfp_qdisc *qdisc;
+
+	nfp_abm_stats_update(alink);
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return -EOPNOTSUPP;
+	/* If the qdisc offload has stopped we may need to adjust the backlog
+	 * counters back so carry on even if qdisc is not currently offloaded.
+	 */
+
+	nfp_abm_stats_calculate(&qdisc->red.band[0].stats,
+				&qdisc->red.band[0].prev_stats,
+				stats->bstats, stats->qstats);
+	qdisc->red.band[0].prev_stats = qdisc->red.band[0].stats;
+
+	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
+}
+
+static bool
+nfp_abm_red_check_params(struct nfp_abm_link *alink,
+			 struct tc_red_qopt_offload *opt)
+{
+	struct nfp_cpp *cpp = alink->abm->app->cpp;
+	struct nfp_abm *abm = alink->abm;
+
+	if (!opt->set.is_ecn && !nfp_abm_has_drop(abm)) {
+		nfp_warn(cpp, "RED offload failed - drop is not supported (ECN option required) (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.is_ecn && !nfp_abm_has_mark(abm)) {
+		nfp_warn(cpp, "RED offload failed - ECN marking not supported (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.is_harddrop) {
+		nfp_warn(cpp, "RED offload failed - harddrop is not supported (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.min != opt->set.max) {
+		nfp_warn(cpp, "RED offload failed - unsupported min/max parameters (p:%08x h:%08x)\n",
+			 opt->parent, opt->handle);
+		return false;
+	}
+	if (opt->set.min > NFP_ABM_LVL_INFINITY) {
+		nfp_warn(cpp, "RED offload failed - threshold too large %d > %d (p:%08x h:%08x)\n",
+			 opt->set.min, NFP_ABM_LVL_INFINITY, opt->parent,
+			 opt->handle);
+		return false;
+	}
+
+	return true;
+}
+
+static int
+nfp_abm_red_replace(struct net_device *netdev, struct nfp_abm_link *alink,
+		    struct tc_red_qopt_offload *opt)
+{
+	struct nfp_qdisc *qdisc;
+	int ret;
+
+	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_RED, opt->parent,
+				    opt->handle, 1, &qdisc);
+	if (ret < 0)
+		return ret;
+
+	/* If limit != 0 child gets reset */
+	if (opt->set.limit) {
+		if (nfp_abm_qdisc_child_valid(qdisc, 0))
+			qdisc->children[0]->use_cnt--;
+		qdisc->children[0] = NULL;
+	} else {
+		/* Qdisc was just allocated without a limit will use noop_qdisc,
+		 * i.e. a block hole.
+		 */
+		if (!ret)
+			qdisc->children[0] = NFP_QDISC_UNTRACKED;
+	}
+
+	qdisc->params_ok = nfp_abm_red_check_params(alink, opt);
+	if (qdisc->params_ok) {
+		qdisc->red.num_bands = 1;
+		qdisc->red.band[0].ecn = opt->set.is_ecn;
+		qdisc->red.band[0].threshold = opt->set.min;
+	}
+
+	if (qdisc->use_cnt == 1)
+		nfp_abm_qdisc_offload_update(alink);
+
+	return 0;
+}
+
+int nfp_abm_setup_tc_red(struct net_device *netdev, struct nfp_abm_link *alink,
+			 struct tc_red_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_RED_REPLACE:
+		return nfp_abm_red_replace(netdev, alink, opt);
+	case TC_RED_DESTROY:
+		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
+		return 0;
+	case TC_RED_STATS:
+		return nfp_abm_red_stats(alink, opt->handle, &opt->stats);
+	case TC_RED_XSTATS:
+		return nfp_abm_red_xstats(alink, opt);
+	case TC_RED_GRAFT:
+		return nfp_abm_qdisc_graft(alink, opt->handle,
+					   opt->child_handle, 0);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nfp_abm_mq_create(struct net_device *netdev, struct nfp_abm_link *alink,
+		  struct tc_mq_qopt_offload *opt)
+{
+	struct nfp_qdisc *qdisc;
+	int ret;
+
+	ret = nfp_abm_qdisc_replace(netdev, alink, NFP_QDISC_MQ,
+				    TC_H_ROOT, opt->handle, alink->total_queues,
+				    &qdisc);
+	if (ret < 0)
+		return ret;
+
+	qdisc->params_ok = true;
+	qdisc->offloaded = true;
+	nfp_abm_qdisc_offload_update(alink);
+	return 0;
+}
+
+static int
+nfp_abm_mq_stats(struct nfp_abm_link *alink, u32 handle,
+		 struct tc_qopt_offload_stats *stats)
+{
+	struct nfp_qdisc *qdisc, *red;
+	unsigned int i, j;
+
+	qdisc = nfp_abm_qdisc_find(alink, handle);
+	if (!qdisc)
+		return -EOPNOTSUPP;
+
+	nfp_abm_stats_update(alink);
+
+	/* MQ stats are summed over the children in the core, so we need
+	 * to add up the unreported child values.
+	 */
+	memset(&qdisc->mq.stats, 0, sizeof(qdisc->mq.stats));
+	memset(&qdisc->mq.prev_stats, 0, sizeof(qdisc->mq.prev_stats));
+
+	for (i = 0; i < qdisc->num_children; i++) {
+		if (!nfp_abm_qdisc_child_valid(qdisc, i))
+			continue;
+
+		if (!nfp_abm_qdisc_is_red(qdisc->children[i]))
+			continue;
+		red = qdisc->children[i];
+
+		for (j = 0; j < red->red.num_bands; j++) {
+			nfp_abm_stats_propagate(&qdisc->mq.stats,
+						&red->red.band[j].stats);
+			nfp_abm_stats_propagate(&qdisc->mq.prev_stats,
+						&red->red.band[j].prev_stats);
+		}
+	}
+
+	nfp_abm_stats_calculate(&qdisc->mq.stats, &qdisc->mq.prev_stats,
+				stats->bstats, stats->qstats);
+
+	return qdisc->offloaded ? 0 : -EOPNOTSUPP;
+}
+
+int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
+			struct tc_mq_qopt_offload *opt)
+{
+	switch (opt->command) {
+	case TC_MQ_CREATE:
+		return nfp_abm_mq_create(netdev, alink, opt);
+	case TC_MQ_DESTROY:
+		nfp_abm_qdisc_destroy(netdev, alink, opt->handle);
+		return 0;
+	case TC_MQ_STATS:
+		return nfp_abm_mq_stats(alink, opt->handle, &opt->stats);
+	case TC_MQ_GRAFT:
+		return nfp_abm_qdisc_graft(alink, opt->handle,
+					   opt->graft_params.child_handle,
+					   opt->graft_params.queue);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int nfp_abm_setup_root(struct net_device *netdev, struct nfp_abm_link *alink,
+		       struct tc_root_qopt_offload *opt)
+{
+	if (opt->ingress)
+		return -EOPNOTSUPP;
+	if (alink->root_qdisc)
+		alink->root_qdisc->use_cnt--;
+	alink->root_qdisc = nfp_abm_qdisc_find(alink, opt->handle);
+	if (alink->root_qdisc)
+		alink->root_qdisc->use_cnt++;
+
+	nfp_abm_qdisc_offload_update(alink);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 97d33bb4d84d..f272247d1708 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1266,7 +1266,7 @@ wrp_alu64_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	u64 imm = insn->imm; /* sign extend */
 
 	if (skip) {
-		meta->skip = true;
+		meta->flags |= FLAG_INSN_SKIP_NOOP;
 		return 0;
 	}
 
@@ -1291,15 +1291,10 @@ wrp_alu64_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 static int
 wrp_alu32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-	      enum alu_op alu_op, bool skip)
+	      enum alu_op alu_op)
 {
 	const struct bpf_insn *insn = &meta->insn;
 
-	if (skip) {
-		meta->skip = true;
-		return 0;
-	}
-
 	wrp_alu_imm(nfp_prog, insn->dst_reg * 2, alu_op, insn->imm);
 	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
 
@@ -1334,8 +1329,9 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 
 	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2, alu_op,
 			 insn->src_reg * 2, br_mask, insn->off);
-	wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
-			 insn->src_reg * 2 + 1, br_mask, insn->off);
+	if (is_mbpf_jmp64(meta))
+		wrp_test_reg_one(nfp_prog, insn->dst_reg * 2 + 1, alu_op,
+				 insn->src_reg * 2 + 1, br_mask, insn->off);
 
 	return 0;
 }
@@ -1390,13 +1386,15 @@ static int cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	else
 		emit_alu(nfp_prog, reg_none(), tmp_reg, alu_op, reg_a(reg));
 
-	tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
-	if (!code->swap)
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(reg + 1), carry_op, tmp_reg);
-	else
-		emit_alu(nfp_prog, reg_none(),
-			 tmp_reg, carry_op, reg_a(reg + 1));
+	if (is_mbpf_jmp64(meta)) {
+		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
+		if (!code->swap)
+			emit_alu(nfp_prog, reg_none(),
+				 reg_a(reg + 1), carry_op, tmp_reg);
+		else
+			emit_alu(nfp_prog, reg_none(),
+				 tmp_reg, carry_op, reg_a(reg + 1));
+	}
 
 	emit_br(nfp_prog, code->br_mask, insn->off, 0);
 
@@ -1423,8 +1421,9 @@ static int cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	}
 
 	emit_alu(nfp_prog, reg_none(), reg_a(areg), ALU_OP_SUB, reg_b(breg));
-	emit_alu(nfp_prog, reg_none(),
-		 reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
+	if (is_mbpf_jmp64(meta))
+		emit_alu(nfp_prog, reg_none(),
+			 reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1));
 	emit_br(nfp_prog, code->br_mask, insn->off, 0);
 
 	return 0;
@@ -1963,6 +1962,9 @@ static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
  */
 static int __shl_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
 {
+	if (!shift_amt)
+		return 0;
+
 	if (shift_amt < 32) {
 		emit_shf(nfp_prog, reg_both(dst + 1), reg_a(dst + 1),
 			 SHF_OP_NONE, reg_b(dst), SHF_SC_R_DSHF,
@@ -2075,6 +2077,9 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
  */
 static int __shr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
 {
+	if (!shift_amt)
+		return 0;
+
 	if (shift_amt < 32) {
 		emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
 			 reg_b(dst), SHF_SC_R_DSHF, shift_amt);
@@ -2176,6 +2181,9 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
  */
 static int __ashr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
 {
+	if (!shift_amt)
+		return 0;
+
 	if (shift_amt < 32) {
 		emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE,
 			 reg_b(dst), SHF_SC_R_DSHF, shift_amt);
@@ -2309,7 +2317,7 @@ static int xor_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int xor_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_XOR);
 }
 
 static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2319,7 +2327,7 @@ static int and_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int and_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND, !~meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_AND);
 }
 
 static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2329,7 +2337,7 @@ static int or_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int or_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_OR);
 }
 
 static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2339,7 +2347,7 @@ static int add_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int add_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_ADD);
 }
 
 static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2349,7 +2357,7 @@ static int sub_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
-	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
+	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB);
 }
 
 static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
@@ -2382,18 +2390,121 @@ static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int __ashr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	if (shift_amt) {
+		/* Set signedness bit (MSB of result). */
+		emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR,
+			 reg_imm(0));
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+			 reg_b(dst), SHF_SC_R_SHF, shift_amt);
+	}
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+
+	return 0;
+}
+
+static int ashr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __ashr_imm(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	/* NOTE: the first insn will set both indirect shift amount (source A)
+	 * and signedness bit (MSB of result).
+	 */
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_b(dst));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR,
+		       reg_b(dst), SHF_SC_R_SHF);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+
+	return 0;
+}
+
+static int ashr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	return __ashr_imm(nfp_prog, dst, insn->imm);
+}
+
+static int __shr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	if (shift_amt)
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_R_SHF, shift_amt);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	return 0;
+}
+
+static int shr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
+
+	return __shr_imm(nfp_prog, dst, insn->imm);
+}
+
+static int shr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
+
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __shr_imm(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0));
+	emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+		       reg_b(dst), SHF_SC_R_SHF);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	return 0;
+}
+
+static int __shl_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt)
+{
+	if (shift_amt)
+		emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE,
+			 reg_b(dst), SHF_SC_L_SHF, shift_amt);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
+	return 0;
+}
+
 static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
+	u8 dst = insn->dst_reg * 2;
 
-	if (!insn->imm)
-		return 1; /* TODO: zero shift means indirect */
+	return __shl_imm(nfp_prog, dst, insn->imm);
+}
 
-	emit_shf(nfp_prog, reg_both(insn->dst_reg * 2),
-		 reg_none(), SHF_OP_NONE, reg_b(insn->dst_reg * 2),
-		 SHF_SC_L_SHF, insn->imm);
-	wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0);
+static int shl_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 umin, umax;
+	u8 dst, src;
 
+	dst = insn->dst_reg * 2;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
+	if (umin == umax)
+		return __shl_imm(nfp_prog, dst, umin);
+
+	src = insn->src_reg * 2;
+	shl_reg64_lt32_low(nfp_prog, dst, src);
+	wrp_immed(nfp_prog, reg_both(dst + 1), 0);
 	return 0;
 }
 
@@ -3005,30 +3116,37 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
-static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+static int jeq32_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
-	u64 imm = insn->imm; /* sign extend */
 	swreg tmp_reg;
 
-	if (!imm) {
-		meta->skip = true;
-		return 0;
-	}
+	tmp_reg = ur_load_imm_any(nfp_prog, insn->imm, imm_b(nfp_prog));
+	emit_alu(nfp_prog, reg_none(),
+		 reg_a(insn->dst_reg * 2), ALU_OP_XOR, tmp_reg);
+	emit_br(nfp_prog, BR_BEQ, insn->off, 0);
 
-	if (imm & ~0U) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
-		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
-	}
+	return 0;
+}
 
-	if (imm >> 32) {
-		tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
+static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+	u64 imm = insn->imm; /* sign extend */
+	u8 dst_gpr = insn->dst_reg * 2;
+	swreg tmp_reg;
+
+	tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog));
+	emit_alu(nfp_prog, imm_b(nfp_prog),
+		 reg_a(dst_gpr), ALU_OP_AND, tmp_reg);
+	/* Upper word of the mask can only be 0 or ~0 from sign extension,
+	 * so either ignore it or OR the whole thing in.
+	 */
+	if (is_mbpf_jmp64(meta) && imm >> 32) {
 		emit_alu(nfp_prog, reg_none(),
-			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_AND, tmp_reg);
-		emit_br(nfp_prog, BR_BNE, insn->off, 0);
+			 reg_a(dst_gpr + 1), ALU_OP_OR, imm_b(nfp_prog));
 	}
+	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
 	return 0;
 }
@@ -3037,11 +3155,16 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
 	u64 imm = insn->imm; /* sign extend */
+	bool is_jmp32 = is_mbpf_jmp32(meta);
 	swreg tmp_reg;
 
 	if (!imm) {
-		emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
-			 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
+		if (is_jmp32)
+			emit_alu(nfp_prog, reg_none(), reg_none(), ALU_OP_NONE,
+				 reg_b(insn->dst_reg * 2));
+		else
+			emit_alu(nfp_prog, reg_none(), reg_a(insn->dst_reg * 2),
+				 ALU_OP_OR, reg_b(insn->dst_reg * 2 + 1));
 		emit_br(nfp_prog, BR_BNE, insn->off, 0);
 		return 0;
 	}
@@ -3051,6 +3174,9 @@ static int jne_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		 reg_a(insn->dst_reg * 2), ALU_OP_XOR, tmp_reg);
 	emit_br(nfp_prog, BR_BNE, insn->off, 0);
 
+	if (is_jmp32)
+		return 0;
+
 	tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog));
 	emit_alu(nfp_prog, reg_none(),
 		 reg_a(insn->dst_reg * 2 + 1), ALU_OP_XOR, tmp_reg);
@@ -3065,10 +3191,13 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 
 	emit_alu(nfp_prog, imm_a(nfp_prog), reg_a(insn->dst_reg * 2),
 		 ALU_OP_XOR, reg_b(insn->src_reg * 2));
-	emit_alu(nfp_prog, imm_b(nfp_prog), reg_a(insn->dst_reg * 2 + 1),
-		 ALU_OP_XOR, reg_b(insn->src_reg * 2 + 1));
-	emit_alu(nfp_prog, reg_none(),
-		 imm_a(nfp_prog), ALU_OP_OR, imm_b(nfp_prog));
+	if (is_mbpf_jmp64(meta)) {
+		emit_alu(nfp_prog, imm_b(nfp_prog),
+			 reg_a(insn->dst_reg * 2 + 1), ALU_OP_XOR,
+			 reg_b(insn->src_reg * 2 + 1));
+		emit_alu(nfp_prog, reg_none(), imm_a(nfp_prog), ALU_OP_OR,
+			 imm_b(nfp_prog));
+	}
 	emit_br(nfp_prog, BR_BEQ, insn->off, 0);
 
 	return 0;
@@ -3146,7 +3275,7 @@ bpf_to_bpf_call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 		wrp_immed_relo(nfp_prog, imm_b(nfp_prog), 0, RELO_IMMED_REL);
 	} else {
 		ret_tgt = nfp_prog_current_offset(nfp_prog) + 2;
-		emit_br(nfp_prog, BR_UNC, meta->n + 1 + meta->insn.imm, 1);
+		emit_br(nfp_prog, BR_UNC, meta->insn.imm, 1);
 		offset_br = nfp_prog_current_offset(nfp_prog);
 	}
 	wrp_immed_relo(nfp_prog, ret_reg(nfp_prog), ret_tgt, RELO_IMMED_REL);
@@ -3285,7 +3414,12 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_DIV | BPF_X] =	div_reg,
 	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
+	[BPF_ALU | BPF_LSH | BPF_X] =	shl_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
+	[BPF_ALU | BPF_RSH | BPF_X] =	shr_reg,
+	[BPF_ALU | BPF_RSH | BPF_K] =	shr_imm,
+	[BPF_ALU | BPF_ARSH | BPF_X] =	ashr_reg,
+	[BPF_ALU | BPF_ARSH | BPF_K] =	ashr_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
 	[BPF_LD | BPF_IMM | BPF_DW] =	imm_ld8,
 	[BPF_LD | BPF_ABS | BPF_B] =	data_ld1,
@@ -3331,6 +3465,28 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_JMP | BPF_JSLE | BPF_X] =  cmp_reg,
 	[BPF_JMP | BPF_JSET | BPF_X] =	jset_reg,
 	[BPF_JMP | BPF_JNE | BPF_X] =	jne_reg,
+	[BPF_JMP32 | BPF_JEQ | BPF_K] =	jeq32_imm,
+	[BPF_JMP32 | BPF_JGT | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JGE | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JLT | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JLE | BPF_K] =	cmp_imm,
+	[BPF_JMP32 | BPF_JSGT | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSGE | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSLT | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSLE | BPF_K] =cmp_imm,
+	[BPF_JMP32 | BPF_JSET | BPF_K] =jset_imm,
+	[BPF_JMP32 | BPF_JNE | BPF_K] =	jne_imm,
+	[BPF_JMP32 | BPF_JEQ | BPF_X] =	jeq_reg,
+	[BPF_JMP32 | BPF_JGT | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JGE | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JLT | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JLE | BPF_X] =	cmp_reg,
+	[BPF_JMP32 | BPF_JSGT | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSGE | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSLT | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSLE | BPF_X] =cmp_reg,
+	[BPF_JMP32 | BPF_JSET | BPF_X] =jset_reg,
+	[BPF_JMP32 | BPF_JNE | BPF_X] =	jne_reg,
 	[BPF_JMP | BPF_CALL] =		call,
 	[BPF_JMP | BPF_EXIT] =		jmp_exit,
 };
@@ -3357,9 +3513,9 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 	int err;
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
-		if (BPF_CLASS(meta->insn.code) != BPF_JMP)
+		if (!is_mbpf_jmp(meta))
 			continue;
 		if (meta->insn.code == (BPF_JMP | BPF_EXIT) &&
 		    !nfp_is_main_function(meta))
@@ -3401,7 +3557,7 @@ static int nfp_fixup_branches(struct nfp_prog *nfp_prog)
 
 		jmp_dst = meta->jmp_dst;
 
-		if (jmp_dst->skip) {
+		if (jmp_dst->flags & FLAG_INSN_SKIP_PREC_DEPENDENT) {
 			pr_err("Branch landing on removed instruction!!\n");
 			return -ELOOP;
 		}
@@ -3651,7 +3807,7 @@ static int nfp_translate(struct nfp_prog *nfp_prog)
 				return nfp_prog->error;
 		}
 
-		if (meta->skip) {
+		if (meta->flags & FLAG_INSN_SKIP_MASK) {
 			nfp_prog->n_translated++;
 			continue;
 		}
@@ -3699,10 +3855,10 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog)
 		/* Programs start with R6 = R1 but we ignore the skb pointer */
 		if (insn.code == (BPF_ALU64 | BPF_MOV | BPF_X) &&
 		    insn.src_reg == 1 && insn.dst_reg == 6)
-			meta->skip = true;
+			meta->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 
 		/* Return as soon as something doesn't match */
-		if (!meta->skip)
+		if (!(meta->flags & FLAG_INSN_SKIP_MASK))
 			return;
 	}
 }
@@ -3717,19 +3873,17 @@ static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog)
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
 		struct bpf_insn insn = meta->insn;
 
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
-		if (BPF_CLASS(insn.code) != BPF_ALU &&
-		    BPF_CLASS(insn.code) != BPF_ALU64 &&
-		    BPF_CLASS(insn.code) != BPF_JMP)
+		if (!is_mbpf_alu(meta) && !is_mbpf_jmp(meta))
 			continue;
 		if (BPF_SRC(insn.code) != BPF_K)
 			continue;
 		if (insn.imm >= 0)
 			continue;
 
-		if (BPF_CLASS(insn.code) == BPF_JMP) {
+		if (is_mbpf_jmp(meta)) {
 			switch (BPF_OP(insn.code)) {
 			case BPF_JGE:
 			case BPF_JSGE:
@@ -3791,7 +3945,7 @@ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog)
 		if (meta2->flags & FLAG_INSN_IS_JUMP_DST)
 			continue;
 
-		meta2->skip = true;
+		meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 	}
 }
 
@@ -3831,8 +3985,8 @@ static void nfp_bpf_opt_ld_shift(struct nfp_prog *nfp_prog)
 		    meta3->flags & FLAG_INSN_IS_JUMP_DST)
 			continue;
 
-		meta2->skip = true;
-		meta3->skip = true;
+		meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
+		meta3->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 	}
 }
 
@@ -4027,7 +4181,8 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
 				}
 
 				head_ld_meta->paired_st = &head_st_meta->insn;
-				head_st_meta->skip = true;
+				head_st_meta->flags |=
+					FLAG_INSN_SKIP_PREC_DEPENDENT;
 			} else {
 				head_ld_meta->ldst_gather_len = 0;
 			}
@@ -4060,8 +4215,8 @@ static void nfp_bpf_opt_ldst_gather(struct nfp_prog *nfp_prog)
 			head_ld_meta = meta1;
 			head_st_meta = meta2;
 		} else {
-			meta1->skip = true;
-			meta2->skip = true;
+			meta1->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
+			meta2->flags |= FLAG_INSN_SKIP_PREC_DEPENDENT;
 		}
 
 		head_ld_meta->ldst_gather_len += BPF_LDST_BYTES(ld);
@@ -4086,7 +4241,7 @@ static void nfp_bpf_opt_pkt_cache(struct nfp_prog *nfp_prog)
 		if (meta->flags & FLAG_INSN_IS_JUMP_DST)
 			cache_avail = false;
 
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		insn = &meta->insn;
@@ -4172,7 +4327,7 @@ start_new:
 	}
 
 	list_for_each_entry(meta, &nfp_prog->insns, l) {
-		if (meta->skip)
+		if (meta->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		if (is_mbpf_load_pkt(meta) && !meta->ldst_gather_len) {
@@ -4208,7 +4363,8 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 	u32 id;
 
 	nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) {
-		if (meta1->skip || meta2->skip)
+		if (meta1->flags & FLAG_INSN_SKIP_MASK ||
+		    meta2->flags & FLAG_INSN_SKIP_MASK)
 			continue;
 
 		if (meta1->insn.code != (BPF_LD | BPF_IMM | BPF_DW) ||
@@ -4287,7 +4443,7 @@ int nfp_bpf_jit(struct nfp_prog *nfp_prog)
 	return ret;
 }
 
-void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
+void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta;
 
@@ -4298,7 +4454,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 		unsigned int dst_idx;
 		bool pseudo_call;
 
-		if (BPF_CLASS(code) != BPF_JMP)
+		if (!is_mbpf_jmp(meta))
 			continue;
 		if (BPF_OP(code) == BPF_EXIT)
 			continue;
@@ -4315,7 +4471,7 @@ void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt)
 		else
 			dst_idx = meta->n + 1 + meta->insn.off;
 
-		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx, cnt);
+		dst_meta = nfp_bpf_goto_meta(nfp_prog, meta, dst_idx);
 
 		if (pseudo_call)
 			dst_meta->flags |= FLAG_INSN_IS_SUBPROG_START;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 6243af0ab025..275de9f4c61c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -465,7 +465,7 @@ static int nfp_bpf_init(struct nfp_app *app)
 		app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf);
 	}
 
-	bpf->bpf_dev = bpf_offload_dev_create();
+	bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops, bpf);
 	err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
 	if (err)
 		goto err_free_neutral_maps;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 7f591d71ab28..b25a48218bcf 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -243,6 +243,16 @@ struct nfp_bpf_reg_state {
 #define FLAG_INSN_IS_JUMP_DST			BIT(0)
 #define FLAG_INSN_IS_SUBPROG_START		BIT(1)
 #define FLAG_INSN_PTR_CALLER_STACK_FRAME	BIT(2)
+/* Instruction is pointless, noop even on its own */
+#define FLAG_INSN_SKIP_NOOP			BIT(3)
+/* Instruction is optimized out based on preceding instructions */
+#define FLAG_INSN_SKIP_PREC_DEPENDENT		BIT(4)
+/* Instruction is optimized by the verifier */
+#define FLAG_INSN_SKIP_VERIFIER_OPT		BIT(5)
+
+#define FLAG_INSN_SKIP_MASK		(FLAG_INSN_SKIP_NOOP | \
+					 FLAG_INSN_SKIP_PREC_DEPENDENT | \
+					 FLAG_INSN_SKIP_VERIFIER_OPT)
 
 /**
  * struct nfp_insn_meta - BPF instruction wrapper
@@ -271,7 +281,6 @@ struct nfp_bpf_reg_state {
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
  * @subprog_idx: index of subprogram to which the instruction belongs
- * @skip: skip this instruction (optimized out)
  * @double_cb: callback for second part of the instruction
  * @l: link on nfp_prog->insns list
  */
@@ -319,7 +328,6 @@ struct nfp_insn_meta {
 	unsigned short n;
 	unsigned short flags;
 	unsigned short subprog_idx;
-	bool skip;
 	instr_cb_t double_cb;
 
 	struct list_head l;
@@ -357,6 +365,21 @@ static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
 }
 
+static inline bool is_mbpf_jmp32(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_JMP32;
+}
+
+static inline bool is_mbpf_jmp64(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_JMP;
+}
+
+static inline bool is_mbpf_jmp(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_jmp32(meta) || is_mbpf_jmp64(meta);
+}
+
 static inline bool is_mbpf_store(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_MEM);
@@ -407,6 +430,20 @@ static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
 	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
 }
 
+static inline bool is_mbpf_cond_jump(const struct nfp_insn_meta *meta)
+{
+	u8 op;
+
+	if (is_mbpf_jmp32(meta))
+		return true;
+
+	if (!is_mbpf_jmp64(meta))
+		return false;
+
+	op = mbpf_op(meta);
+	return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
+}
+
 static inline bool is_mbpf_helper_call(const struct nfp_insn_meta *meta)
 {
 	struct bpf_insn insn = meta->insn;
@@ -457,6 +494,7 @@ struct nfp_bpf_subprog_info {
  * @subprog_cnt: number of sub-programs, including main function
  * @map_records: the map record pointers from bpf->maps_neutral
  * @subprog: pointer to an array of objects holding info about sub-programs
+ * @n_insns: number of instructions on @insns list
  * @insns: list of BPF instruction wrappers (struct nfp_insn_meta)
  */
 struct nfp_prog {
@@ -489,6 +527,7 @@ struct nfp_prog {
 	struct nfp_bpf_neutral_map **map_records;
 	struct nfp_bpf_subprog_info *subprog;
 
+	unsigned int n_insns;
 	struct list_head insns;
 };
 
@@ -505,11 +544,19 @@ struct nfp_bpf_vnic {
 };
 
 bool nfp_is_subprog_start(struct nfp_insn_meta *meta);
-void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog, unsigned int cnt);
+void nfp_bpf_jit_prepare(struct nfp_prog *nfp_prog);
 int nfp_bpf_jit(struct nfp_prog *prog);
 bool nfp_bpf_supported_opcode(u8 code);
 
-extern const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops;
+int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
+		    int prev_insn_idx);
+int nfp_bpf_finalize(struct bpf_verifier_env *env);
+
+int nfp_bpf_opt_replace_insn(struct bpf_verifier_env *env, u32 off,
+			     struct bpf_insn *insn);
+int nfp_bpf_opt_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
+
+extern const struct bpf_prog_offload_ops nfp_bpf_dev_ops;
 
 struct netdev_bpf;
 struct nfp_app;
@@ -522,7 +569,7 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 
 struct nfp_insn_meta *
 nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-		  unsigned int insn_idx, unsigned int n_insns);
+		  unsigned int insn_idx);
 
 void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv);
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index ba8ceedcf6a2..15dce97650a5 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -33,9 +33,6 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	struct nfp_bpf_neutral_map *record;
 	int err;
 
-	/* Map record paths are entered via ndo, update side is protected. */
-	ASSERT_RTNL();
-
 	/* Reuse path - other offloaded program is already tracking this map. */
 	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map->id,
 					nfp_bpf_maps_neutral_params);
@@ -84,8 +81,6 @@ nfp_map_ptrs_forget(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog)
 	bool freed = false;
 	int i;
 
-	ASSERT_RTNL();
-
 	for (i = 0; i < nfp_prog->map_records_cnt; i++) {
 		if (--nfp_prog->map_records[i]->count) {
 			nfp_prog->map_records[i] = NULL;
@@ -168,8 +163,9 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
+	nfp_prog->n_insns = cnt;
 
-	nfp_bpf_jit_prepare(nfp_prog, cnt);
+	nfp_bpf_jit_prepare(nfp_prog);
 
 	return 0;
 }
@@ -187,11 +183,8 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog)
 	kfree(nfp_prog);
 }
 
-static int
-nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
-		      struct netdev_bpf *bpf)
+static int nfp_bpf_verifier_prep(struct bpf_prog *prog)
 {
-	struct bpf_prog *prog = bpf->verifier.prog;
 	struct nfp_prog *nfp_prog;
 	int ret;
 
@@ -202,14 +195,13 @@ nfp_bpf_verifier_prep(struct nfp_app *app, struct nfp_net *nn,
 
 	INIT_LIST_HEAD(&nfp_prog->insns);
 	nfp_prog->type = prog->type;
-	nfp_prog->bpf = app->priv;
+	nfp_prog->bpf = bpf_offload_dev_priv(prog->aux->offload->offdev);
 
 	ret = nfp_prog_prepare(nfp_prog, prog->insnsi, prog->len);
 	if (ret)
 		goto err_free;
 
 	nfp_prog->verifier_meta = nfp_prog_first_meta(nfp_prog);
-	bpf->verifier.ops = &nfp_bpf_analyzer_ops;
 
 	return 0;
 
@@ -219,12 +211,17 @@ err_free:
 	return ret;
 }
 
-static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
+static int nfp_bpf_translate(struct bpf_prog *prog)
 {
+	struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev);
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
 	unsigned int max_instr;
 	int err;
 
+	/* We depend on dead code elimination succeeding */
+	if (prog->aux->offload->opt_failed)
+		return -EINVAL;
+
 	max_instr = nn_readw(nn, NFP_NET_CFG_BPF_MAX_LEN);
 	nfp_prog->__prog_alloc_len = max_instr * sizeof(u64);
 
@@ -242,15 +239,13 @@ static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog)
 	return nfp_map_ptrs_record(nfp_prog->bpf, nfp_prog, prog);
 }
 
-static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog)
+static void nfp_bpf_destroy(struct bpf_prog *prog)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
 
 	kvfree(nfp_prog->prog);
 	nfp_map_ptrs_forget(nfp_prog->bpf, nfp_prog);
 	nfp_prog_free(nfp_prog);
-
-	return 0;
 }
 
 /* Atomic engine requires values to be in big endian, we need to byte swap
@@ -422,12 +417,6 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
 int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf)
 {
 	switch (bpf->command) {
-	case BPF_OFFLOAD_VERIFIER_PREP:
-		return nfp_bpf_verifier_prep(app, nn, bpf);
-	case BPF_OFFLOAD_TRANSLATE:
-		return nfp_bpf_translate(nn, bpf->offload.prog);
-	case BPF_OFFLOAD_DESTROY:
-		return nfp_bpf_destroy(nn, bpf->offload.prog);
 	case BPF_OFFLOAD_MAP_ALLOC:
 		return nfp_bpf_map_alloc(app->priv, bpf->offmap);
 	case BPF_OFFLOAD_MAP_FREE:
@@ -489,14 +478,15 @@ nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog,
 		 struct netlink_ext_ack *extack)
 {
 	struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv;
-	unsigned int max_mtu, max_stack, max_prog_len;
+	unsigned int fw_mtu, pkt_off, max_stack, max_prog_len;
 	dma_addr_t dma_addr;
 	void *img;
 	int err;
 
-	max_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
-	if (max_mtu < nn->dp.netdev->mtu) {
-		NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with MTU larger than HW packet split boundary");
+	fw_mtu = nn_readb(nn, NFP_NET_CFG_BPF_INL_MTU) * 64 - 32;
+	pkt_off = min(prog->aux->max_pkt_offset, nn->dp.netdev->mtu);
+	if (fw_mtu < pkt_off) {
+		NL_SET_ERR_MSG_MOD(extack, "BPF offload not supported with potential packet access beyond HW packet split boundary");
 		return -EOPNOTSUPP;
 	}
 
@@ -600,3 +590,13 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 
 	return 0;
 }
+
+const struct bpf_prog_offload_ops nfp_bpf_dev_ops = {
+	.insn_hook	= nfp_verify_insn,
+	.finalize	= nfp_bpf_finalize,
+	.replace_insn	= nfp_bpf_opt_replace_insn,
+	.remove_insns	= nfp_bpf_opt_remove_insns,
+	.prepare	= nfp_bpf_verifier_prep,
+	.translate	= nfp_bpf_translate,
+	.destroy	= nfp_bpf_destroy,
+};
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 99f977bfd8cc..36f56eb4cbe2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -18,15 +18,15 @@
 
 struct nfp_insn_meta *
 nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
-		  unsigned int insn_idx, unsigned int n_insns)
+		  unsigned int insn_idx)
 {
 	unsigned int forward, backward, i;
 
 	backward = meta->n - insn_idx;
 	forward = insn_idx - meta->n;
 
-	if (min(forward, backward) > n_insns - insn_idx - 1) {
-		backward = n_insns - insn_idx - 1;
+	if (min(forward, backward) > nfp_prog->n_insns - insn_idx - 1) {
+		backward = nfp_prog->n_insns - insn_idx - 1;
 		meta = nfp_prog_last_meta(nfp_prog);
 	}
 	if (min(forward, backward) > insn_idx && backward > insn_idx) {
@@ -623,13 +623,13 @@ nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	return 0;
 }
 
-static int
-nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
+int nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx,
+		    int prev_insn_idx)
 {
 	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
 	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
 
-	meta = nfp_bpf_goto_meta(nfp_prog, meta, insn_idx, env->prog->len);
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, insn_idx);
 	nfp_prog->verifier_meta = meta;
 
 	if (!nfp_bpf_supported_opcode(meta->insn.code)) {
@@ -690,8 +690,7 @@ nfp_assign_subprog_idx_and_regs(struct bpf_verifier_env *env,
 	return 0;
 }
 
-static unsigned int
-nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog, unsigned int cnt)
+static unsigned int nfp_bpf_get_stack_usage(struct nfp_prog *nfp_prog)
 {
 	struct nfp_insn_meta *meta = nfp_prog_first_meta(nfp_prog);
 	unsigned int max_depth = 0, depth = 0, frame = 0;
@@ -726,7 +725,7 @@ continue_subprog:
 
 		/* Find the callee and start processing it. */
 		meta = nfp_bpf_goto_meta(nfp_prog, meta,
-					 meta->n + 1 + meta->insn.imm, cnt);
+					 meta->n + 1 + meta->insn.imm);
 		idx = meta->subprog_idx;
 		frame++;
 		goto process_subprog;
@@ -745,7 +744,7 @@ continue_subprog:
 	goto continue_subprog;
 }
 
-static int nfp_bpf_finalize(struct bpf_verifier_env *env)
+int nfp_bpf_finalize(struct bpf_verifier_env *env)
 {
 	struct bpf_subprog_info *info;
 	struct nfp_prog *nfp_prog;
@@ -778,8 +777,7 @@ static int nfp_bpf_finalize(struct bpf_verifier_env *env)
 
 	nn = netdev_priv(env->prog->aux->offload->netdev);
 	max_stack = nn_readb(nn, NFP_NET_CFG_BPF_STACK_SZ) * 64;
-	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog,
-						       env->prog->len);
+	nfp_prog->stack_size = nfp_bpf_get_stack_usage(nfp_prog);
 	if (nfp_prog->stack_size > max_stack) {
 		pr_vlog(env, "stack too large: program %dB > FW stack %dB\n",
 			nfp_prog->stack_size, max_stack);
@@ -789,7 +787,60 @@ static int nfp_bpf_finalize(struct bpf_verifier_env *env)
 	return 0;
 }
 
-const struct bpf_prog_offload_ops nfp_bpf_analyzer_ops = {
-	.insn_hook	= nfp_verify_insn,
-	.finalize	= nfp_bpf_finalize,
-};
+int nfp_bpf_opt_replace_insn(struct bpf_verifier_env *env, u32 off,
+			     struct bpf_insn *insn)
+{
+	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
+
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, aux_data[off].orig_idx);
+	nfp_prog->verifier_meta = meta;
+
+	/* conditional jump to jump conversion */
+	if (is_mbpf_cond_jump(meta) &&
+	    insn->code == (BPF_JMP | BPF_JA | BPF_K)) {
+		unsigned int tgt_off;
+
+		tgt_off = off + insn->off + 1;
+
+		if (!insn->off) {
+			meta->jmp_dst = list_next_entry(meta, l);
+			meta->jump_neg_op = false;
+		} else if (meta->jmp_dst->n != aux_data[tgt_off].orig_idx) {
+			pr_vlog(env, "branch hard wire at %d changes target %d -> %d\n",
+				off, meta->jmp_dst->n,
+				aux_data[tgt_off].orig_idx);
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	pr_vlog(env, "unsupported instruction replacement %hhx -> %hhx\n",
+		meta->insn.code, insn->code);
+	return -EINVAL;
+}
+
+int nfp_bpf_opt_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+	struct nfp_prog *nfp_prog = env->prog->aux->offload->dev_priv;
+	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+	struct nfp_insn_meta *meta = nfp_prog->verifier_meta;
+	unsigned int i;
+
+	meta = nfp_bpf_goto_meta(nfp_prog, meta, aux_data[off].orig_idx);
+
+	for (i = 0; i < cnt; i++) {
+		if (WARN_ON_ONCE(&meta->l == &nfp_prog->insns))
+			return -EINVAL;
+
+		/* doesn't count if it already has the flag */
+		if (meta->flags & FLAG_INSN_SKIP_VERIFIER_OPT)
+			i--;
+
+		meta->flags |= FLAG_INSN_SKIP_VERIFIER_OPT;
+		meta = list_next_entry(meta, l);
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 244dc261006e..e336f6ee94f5 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -2,9 +2,7 @@
 /* Copyright (C) 2017-2018 Netronome Systems, Inc. */
 
 #include <linux/bitfield.h>
-#include <net/geneve.h>
 #include <net/pkt_cls.h>
-#include <net/switchdev.h>
 #include <net/tc_act/tc_csum.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
@@ -38,7 +36,7 @@ static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
 
 static void
 nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
-		 const struct tc_action *action)
+		 const struct flow_action_entry *act)
 {
 	size_t act_size = sizeof(struct nfp_fl_push_vlan);
 	u16 tmp_push_vlan_tci;
@@ -46,17 +44,16 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 	push_vlan->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_VLAN;
 	push_vlan->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 	push_vlan->reserved = 0;
-	push_vlan->vlan_tpid = tcf_vlan_push_proto(action);
+	push_vlan->vlan_tpid = act->vlan.proto;
 
 	tmp_push_vlan_tci =
-		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, tcf_vlan_push_prio(action)) |
-		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action)) |
-		NFP_FL_PUSH_VLAN_CFI;
+		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, act->vlan.prio) |
+		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid);
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
 
 static int
-nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
+nfp_fl_pre_lag(struct nfp_app *app, const struct flow_action_entry *act,
 	       struct nfp_fl_payload *nfp_flow, int act_len)
 {
 	size_t act_size = sizeof(struct nfp_fl_pre_lag);
@@ -64,7 +61,7 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
 	struct net_device *out_dev;
 	int err;
 
-	out_dev = tcf_mirred_dev(action);
+	out_dev = act->dev;
 	if (!out_dev || !netif_is_lag_master(out_dev))
 		return 0;
 
@@ -91,24 +88,10 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action,
 	return act_size;
 }
 
-static bool nfp_fl_netdev_is_tunnel_type(struct net_device *out_dev,
-					 enum nfp_flower_tun_type tun_type)
-{
-	if (!out_dev->rtnl_link_ops)
-		return false;
-
-	if (!strcmp(out_dev->rtnl_link_ops->kind, "vxlan"))
-		return tun_type == NFP_FL_TUNNEL_VXLAN;
-
-	if (!strcmp(out_dev->rtnl_link_ops->kind, "geneve"))
-		return tun_type == NFP_FL_TUNNEL_GENEVE;
-
-	return false;
-}
-
 static int
 nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
-	      const struct tc_action *action, struct nfp_fl_payload *nfp_flow,
+	      const struct flow_action_entry *act,
+	      struct nfp_fl_payload *nfp_flow,
 	      bool last, struct net_device *in_dev,
 	      enum nfp_flower_tun_type tun_type, int *tun_out_cnt)
 {
@@ -120,7 +103,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 	output->head.jump_id = NFP_FL_ACTION_OPCODE_OUTPUT;
 	output->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
-	out_dev = tcf_mirred_dev(action);
+	out_dev = act->dev;
 	if (!out_dev)
 		return -EOPNOTSUPP;
 
@@ -151,11 +134,12 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 		/* Set action output parameters. */
 		output->flags = cpu_to_be16(tmp_flags);
 
-		/* Only offload if egress ports are on the same device as the
-		 * ingress port.
-		 */
-		if (!switchdev_port_same_parent_id(in_dev, out_dev))
-			return -EOPNOTSUPP;
+		if (nfp_netdev_is_nfp_repr(in_dev)) {
+			/* Confirm ingress and egress are on same device. */
+			if (!netdev_port_same_parent_id(in_dev, out_dev))
+				return -EOPNOTSUPP;
+		}
+
 		if (!nfp_netdev_is_nfp_repr(out_dev))
 			return -EOPNOTSUPP;
 
@@ -170,9 +154,9 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 
 static enum nfp_flower_tun_type
 nfp_fl_get_tun_from_act_l4_port(struct nfp_app *app,
-				const struct tc_action *action)
+				const struct flow_action_entry *act)
 {
-	struct ip_tunnel_info *tun = tcf_tunnel_info(action);
+	const struct ip_tunnel_info *tun = act->tunnel;
 	struct nfp_flower_priv *priv = app->priv;
 
 	switch (tun->key.tp_dst) {
@@ -210,9 +194,9 @@ static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len)
 
 static int
 nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
-			   const struct tc_action *action)
+			   const struct flow_action_entry *act)
 {
-	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	struct ip_tunnel_info *ip_tun = (struct ip_tunnel_info *)act->tunnel;
 	int opt_len, opt_cnt, act_start, tot_push_len;
 	u8 *src = ip_tunnel_info_opts(ip_tun);
 
@@ -274,13 +258,13 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
 static int
 nfp_fl_set_ipv4_udp_tun(struct nfp_app *app,
 			struct nfp_fl_set_ipv4_udp_tun *set_tun,
-			const struct tc_action *action,
+			const struct flow_action_entry *act,
 			struct nfp_fl_pre_tunnel *pre_tun,
 			enum nfp_flower_tun_type tun_type,
 			struct net_device *netdev)
 {
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
-	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	const struct ip_tunnel_info *ip_tun = act->tunnel;
 	struct nfp_flower_priv *priv = app->priv;
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
@@ -360,7 +344,7 @@ static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask)
 }
 
 static int
-nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off,
+nfp_fl_set_eth(const struct flow_action_entry *act, u32 off,
 	       struct nfp_fl_set_eth *set_eth)
 {
 	u32 exact, mask;
@@ -368,8 +352,8 @@ nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off,
 	if (off + 4 > ETH_ALEN * 2)
 		return -EOPNOTSUPP;
 
-	mask = ~tcf_pedit_mask(action, idx);
-	exact = tcf_pedit_val(action, idx);
+	mask = ~act->mangle.mask;
+	exact = act->mangle.val;
 
 	if (exact & ~mask)
 		return -EOPNOTSUPP;
@@ -384,15 +368,26 @@ nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off,
 	return 0;
 }
 
+struct ipv4_ttl_word {
+	__u8	ttl;
+	__u8	protocol;
+	__sum16	check;
+};
+
 static int
-nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
-	       struct nfp_fl_set_ip4_addrs *set_ip_addr)
+nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off,
+	       struct nfp_fl_set_ip4_addrs *set_ip_addr,
+	       struct nfp_fl_set_ip4_ttl_tos *set_ip_ttl_tos)
 {
+	struct ipv4_ttl_word *ttl_word_mask;
+	struct ipv4_ttl_word *ttl_word;
+	struct iphdr *tos_word_mask;
+	struct iphdr *tos_word;
 	__be32 exact, mask;
 
 	/* We are expecting tcf_pedit to return a big endian value */
-	mask = (__force __be32)~tcf_pedit_mask(action, idx);
-	exact = (__force __be32)tcf_pedit_val(action, idx);
+	mask = (__force __be32)~act->mangle.mask;
+	exact = (__force __be32)act->mangle.val;
 
 	if (exact & ~mask)
 		return -EOPNOTSUPP;
@@ -402,20 +397,53 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off,
 		set_ip_addr->ipv4_dst_mask |= mask;
 		set_ip_addr->ipv4_dst &= ~mask;
 		set_ip_addr->ipv4_dst |= exact & mask;
+		set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
+		set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >>
+					   NFP_FL_LW_SIZ;
 		break;
 	case offsetof(struct iphdr, saddr):
 		set_ip_addr->ipv4_src_mask |= mask;
 		set_ip_addr->ipv4_src &= ~mask;
 		set_ip_addr->ipv4_src |= exact & mask;
+		set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
+		set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >>
+					   NFP_FL_LW_SIZ;
+		break;
+	case offsetof(struct iphdr, ttl):
+		ttl_word_mask = (struct ipv4_ttl_word *)&mask;
+		ttl_word = (struct ipv4_ttl_word *)&exact;
+
+		if (ttl_word_mask->protocol || ttl_word_mask->check)
+			return -EOPNOTSUPP;
+
+		set_ip_ttl_tos->ipv4_ttl_mask |= ttl_word_mask->ttl;
+		set_ip_ttl_tos->ipv4_ttl &= ~ttl_word_mask->ttl;
+		set_ip_ttl_tos->ipv4_ttl |= ttl_word->ttl & ttl_word_mask->ttl;
+		set_ip_ttl_tos->head.jump_id =
+			NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS;
+		set_ip_ttl_tos->head.len_lw = sizeof(*set_ip_ttl_tos) >>
+					      NFP_FL_LW_SIZ;
+		break;
+	case round_down(offsetof(struct iphdr, tos), 4):
+		tos_word_mask = (struct iphdr *)&mask;
+		tos_word = (struct iphdr *)&exact;
+
+		if (tos_word_mask->version || tos_word_mask->ihl ||
+		    tos_word_mask->tot_len)
+			return -EOPNOTSUPP;
+
+		set_ip_ttl_tos->ipv4_tos_mask |= tos_word_mask->tos;
+		set_ip_ttl_tos->ipv4_tos &= ~tos_word_mask->tos;
+		set_ip_ttl_tos->ipv4_tos |= tos_word->tos & tos_word_mask->tos;
+		set_ip_ttl_tos->head.jump_id =
+			NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS;
+		set_ip_ttl_tos->head.len_lw = sizeof(*set_ip_ttl_tos) >>
+					      NFP_FL_LW_SIZ;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
-	set_ip_addr->reserved = cpu_to_be16(0);
-	set_ip_addr->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS;
-	set_ip_addr->head.len_lw = sizeof(*set_ip_addr) >> NFP_FL_LW_SIZ;
-
 	return 0;
 }
 
@@ -432,23 +460,69 @@ nfp_fl_set_ip6_helper(int opcode_tag, u8 word, __be32 exact, __be32 mask,
 	ip6->head.len_lw = sizeof(*ip6) >> NFP_FL_LW_SIZ;
 }
 
+struct ipv6_hop_limit_word {
+	__be16 payload_len;
+	u8 nexthdr;
+	u8 hop_limit;
+};
+
 static int
-nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
+nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask,
+				    struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl)
+{
+	struct ipv6_hop_limit_word *fl_hl_mask;
+	struct ipv6_hop_limit_word *fl_hl;
+
+	switch (off) {
+	case offsetof(struct ipv6hdr, payload_len):
+		fl_hl_mask = (struct ipv6_hop_limit_word *)&mask;
+		fl_hl = (struct ipv6_hop_limit_word *)&exact;
+
+		if (fl_hl_mask->nexthdr || fl_hl_mask->payload_len)
+			return -EOPNOTSUPP;
+
+		ip_hl_fl->ipv6_hop_limit_mask |= fl_hl_mask->hop_limit;
+		ip_hl_fl->ipv6_hop_limit &= ~fl_hl_mask->hop_limit;
+		ip_hl_fl->ipv6_hop_limit |= fl_hl->hop_limit &
+					    fl_hl_mask->hop_limit;
+		break;
+	case round_down(offsetof(struct ipv6hdr, flow_lbl), 4):
+		if (mask & ~IPV6_FLOW_LABEL_MASK ||
+		    exact & ~IPV6_FLOW_LABEL_MASK)
+			return -EOPNOTSUPP;
+
+		ip_hl_fl->ipv6_label_mask |= mask;
+		ip_hl_fl->ipv6_label &= ~mask;
+		ip_hl_fl->ipv6_label |= exact & mask;
+		break;
+	}
+
+	ip_hl_fl->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV6_TC_HL_FL;
+	ip_hl_fl->head.len_lw = sizeof(*ip_hl_fl) >> NFP_FL_LW_SIZ;
+
+	return 0;
+}
+
+static int
+nfp_fl_set_ip6(const struct flow_action_entry *act, u32 off,
 	       struct nfp_fl_set_ipv6_addr *ip_dst,
-	       struct nfp_fl_set_ipv6_addr *ip_src)
+	       struct nfp_fl_set_ipv6_addr *ip_src,
+	       struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl)
 {
 	__be32 exact, mask;
+	int err = 0;
 	u8 word;
 
 	/* We are expecting tcf_pedit to return a big endian value */
-	mask = (__force __be32)~tcf_pedit_mask(action, idx);
-	exact = (__force __be32)tcf_pedit_val(action, idx);
+	mask = (__force __be32)~act->mangle.mask;
+	exact = (__force __be32)act->mangle.val;
 
 	if (exact & ~mask)
 		return -EOPNOTSUPP;
 
 	if (off < offsetof(struct ipv6hdr, saddr)) {
-		return -EOPNOTSUPP;
+		err = nfp_fl_set_ip6_hop_limit_flow_label(off, exact, mask,
+							  ip_hl_fl);
 	} else if (off < offsetof(struct ipv6hdr, daddr)) {
 		word = (off - offsetof(struct ipv6hdr, saddr)) / sizeof(exact);
 		nfp_fl_set_ip6_helper(NFP_FL_ACTION_OPCODE_SET_IPV6_SRC, word,
@@ -462,11 +536,11 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off,
 		return -EOPNOTSUPP;
 	}
 
-	return 0;
+	return err;
 }
 
 static int
-nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off,
+nfp_fl_set_tport(const struct flow_action_entry *act, u32 off,
 		 struct nfp_fl_set_tport *set_tport, int opcode)
 {
 	u32 exact, mask;
@@ -474,8 +548,8 @@ nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off,
 	if (off)
 		return -EOPNOTSUPP;
 
-	mask = ~tcf_pedit_mask(action, idx);
-	exact = tcf_pedit_val(action, idx);
+	mask = ~act->mangle.mask;
+	exact = act->mangle.val;
 
 	if (exact & ~mask)
 		return -EOPNOTSUPP;
@@ -509,67 +583,65 @@ static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto)
 }
 
 static int
-nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
+nfp_fl_pedit(const struct flow_action_entry *act,
+	     struct tc_cls_flower_offload *flow,
 	     char *nfp_action, int *a_len, u32 *csum_updated)
 {
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
 	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
+	struct nfp_fl_set_ipv6_tc_hl_fl set_ip6_tc_hl_fl;
+	struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos;
 	struct nfp_fl_set_ip4_addrs set_ip_addr;
+	enum flow_action_mangle_base htype;
 	struct nfp_fl_set_tport set_tport;
 	struct nfp_fl_set_eth set_eth;
-	enum pedit_header_type htype;
-	int idx, nkeys, err;
 	size_t act_size = 0;
-	u32 offset, cmd;
 	u8 ip_proto = 0;
+	u32 offset;
+	int err;
 
+	memset(&set_ip6_tc_hl_fl, 0, sizeof(set_ip6_tc_hl_fl));
+	memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos));
 	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
 	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
 	memset(&set_ip_addr, 0, sizeof(set_ip_addr));
 	memset(&set_tport, 0, sizeof(set_tport));
 	memset(&set_eth, 0, sizeof(set_eth));
-	nkeys = tcf_pedit_nkeys(action);
 
-	for (idx = 0; idx < nkeys; idx++) {
-		cmd = tcf_pedit_cmd(action, idx);
-		htype = tcf_pedit_htype(action, idx);
-		offset = tcf_pedit_offset(action, idx);
+	htype = act->mangle.htype;
+	offset = act->mangle.offset;
 
-		if (cmd != TCA_PEDIT_KEY_EX_CMD_SET)
-			return -EOPNOTSUPP;
-
-		switch (htype) {
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
-			err = nfp_fl_set_eth(action, idx, offset, &set_eth);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
-			err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
-			err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst,
-					     &set_ip6_src);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
-			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
-					       NFP_FL_ACTION_OPCODE_SET_TCP);
-			break;
-		case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
-			err = nfp_fl_set_tport(action, idx, offset, &set_tport,
-					       NFP_FL_ACTION_OPCODE_SET_UDP);
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-		if (err)
-			return err;
+	switch (htype) {
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH:
+		err = nfp_fl_set_eth(act, offset, &set_eth);
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4:
+		err = nfp_fl_set_ip4(act, offset, &set_ip_addr,
+				     &set_ip_ttl_tos);
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6:
+		err = nfp_fl_set_ip6(act, offset, &set_ip6_dst,
+				     &set_ip6_src, &set_ip6_tc_hl_fl);
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP:
+		err = nfp_fl_set_tport(act, offset, &set_tport,
+				       NFP_FL_ACTION_OPCODE_SET_TCP);
+		break;
+	case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP:
+		err = nfp_fl_set_tport(act, offset, &set_tport,
+				       NFP_FL_ACTION_OPCODE_SET_UDP);
+		break;
+	default:
+		return -EOPNOTSUPP;
 	}
+	if (err)
+		return err;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *basic;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		basic = skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  flow->key);
-		ip_proto = basic->ip_proto;
+		flow_rule_match_basic(rule, &match);
+		ip_proto = match.key->ip_proto;
 	}
 
 	if (set_eth.head.len_lw) {
@@ -577,6 +649,16 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 		memcpy(nfp_action, &set_eth, act_size);
 		*a_len += act_size;
 	}
+	if (set_ip_ttl_tos.head.len_lw) {
+		nfp_action += act_size;
+		act_size = sizeof(set_ip_ttl_tos);
+		memcpy(nfp_action, &set_ip_ttl_tos, act_size);
+		*a_len += act_size;
+
+		/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
+		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
+				nfp_fl_csum_l4_to_flag(ip_proto);
+	}
 	if (set_ip_addr.head.len_lw) {
 		nfp_action += act_size;
 		act_size = sizeof(set_ip_addr);
@@ -587,6 +669,15 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
 				nfp_fl_csum_l4_to_flag(ip_proto);
 	}
+	if (set_ip6_tc_hl_fl.head.len_lw) {
+		nfp_action += act_size;
+		act_size = sizeof(set_ip6_tc_hl_fl);
+		memcpy(nfp_action, &set_ip6_tc_hl_fl, act_size);
+		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
+	}
 	if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
 		/* TC compiles set src and dst IPv6 address as a single action,
 		 * the hardware requires this to be 2 separate actions.
@@ -634,7 +725,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
 }
 
 static int
-nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
+nfp_flower_output_action(struct nfp_app *app, const struct flow_action_entry *act,
 			 struct nfp_fl_payload *nfp_fl, int *a_len,
 			 struct net_device *netdev, bool last,
 			 enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
@@ -654,7 +745,7 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 		return -EOPNOTSUPP;
 
 	output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len];
-	err = nfp_fl_output(app, output, a, nfp_fl, last, netdev, *tun_type,
+	err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type,
 			    tun_out_cnt);
 	if (err)
 		return err;
@@ -665,7 +756,7 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 		/* nfp_fl_pre_lag returns -err or size of prelag action added.
 		 * This will be 0 if it is not egressing to a lag dev.
 		 */
-		prelag_size = nfp_fl_pre_lag(app, a, nfp_fl, *a_len);
+		prelag_size = nfp_fl_pre_lag(app, act, nfp_fl, *a_len);
 		if (prelag_size < 0)
 			return prelag_size;
 		else if (prelag_size > 0 && (!last || *out_cnt))
@@ -679,7 +770,7 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 }
 
 static int
-nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
+nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act,
 		       struct tc_cls_flower_offload *flow,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
 		       struct net_device *netdev,
@@ -692,23 +783,25 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 	struct nfp_fl_pop_vlan *pop_v;
 	int err;
 
-	if (is_tcf_gact_shot(a)) {
+	switch (act->id) {
+	case FLOW_ACTION_DROP:
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP);
-	} else if (is_tcf_mirred_egress_redirect(a)) {
-		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
+		break;
+	case FLOW_ACTION_REDIRECT:
+		err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev,
 					       true, tun_type, tun_out_cnt,
 					       out_cnt, csum_updated);
 		if (err)
 			return err;
-
-	} else if (is_tcf_mirred_egress_mirror(a)) {
-		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
+		break;
+	case FLOW_ACTION_MIRRED:
+		err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev,
 					       false, tun_type, tun_out_cnt,
 					       out_cnt, csum_updated);
 		if (err)
 			return err;
-
-	} else if (is_tcf_vlan(a) && tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
+		break;
+	case FLOW_ACTION_VLAN_POP:
 		if (*a_len + sizeof(struct nfp_fl_pop_vlan) > NFP_FL_MAX_A_SIZ)
 			return -EOPNOTSUPP;
 
@@ -717,20 +810,21 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 
 		nfp_fl_pop_vlan(pop_v);
 		*a_len += sizeof(struct nfp_fl_pop_vlan);
-	} else if (is_tcf_vlan(a) && tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
+		break;
+	case FLOW_ACTION_VLAN_PUSH:
 		if (*a_len + sizeof(struct nfp_fl_push_vlan) > NFP_FL_MAX_A_SIZ)
 			return -EOPNOTSUPP;
 
 		psh_v = (struct nfp_fl_push_vlan *)&nfp_fl->action_data[*a_len];
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
 
-		nfp_fl_push_vlan(psh_v, a);
+		nfp_fl_push_vlan(psh_v, act);
 		*a_len += sizeof(struct nfp_fl_push_vlan);
-	} else if (is_tcf_tunnel_set(a)) {
-		struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a);
-		struct nfp_repr *repr = netdev_priv(netdev);
+		break;
+	case FLOW_ACTION_TUNNEL_ENCAP: {
+		const struct ip_tunnel_info *ip_tun = act->tunnel;
 
-		*tun_type = nfp_fl_get_tun_from_act_l4_port(repr->app, a);
+		*tun_type = nfp_fl_get_tun_from_act_l4_port(app, act);
 		if (*tun_type == NFP_FL_TUNNEL_NONE)
 			return -EOPNOTSUPP;
 
@@ -749,32 +843,36 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
 		*a_len += sizeof(struct nfp_fl_pre_tunnel);
 
-		err = nfp_fl_push_geneve_options(nfp_fl, a_len, a);
+		err = nfp_fl_push_geneve_options(nfp_fl, a_len, act);
 		if (err)
 			return err;
 
 		set_tun = (void *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_set_ipv4_udp_tun(app, set_tun, a, pre_tun,
+		err = nfp_fl_set_ipv4_udp_tun(app, set_tun, act, pre_tun,
 					      *tun_type, netdev);
 		if (err)
 			return err;
 		*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
-	} else if (is_tcf_tunnel_release(a)) {
+		}
+		break;
+	case FLOW_ACTION_TUNNEL_DECAP:
 		/* Tunnel decap is handled by default so accept action. */
 		return 0;
-	} else if (is_tcf_pedit(a)) {
-		if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len],
+	case FLOW_ACTION_MANGLE:
+		if (nfp_fl_pedit(act, flow, &nfp_fl->action_data[*a_len],
 				 a_len, csum_updated))
 			return -EOPNOTSUPP;
-	} else if (is_tcf_csum(a)) {
+		break;
+	case FLOW_ACTION_CSUM:
 		/* csum action requests recalc of something we have not fixed */
-		if (tcf_csum_update_flags(a) & ~*csum_updated)
+		if (act->csum_flags & ~*csum_updated)
 			return -EOPNOTSUPP;
 		/* If we will correctly fix the csum we can remove it from the
 		 * csum update list. Which will later be used to check support.
 		 */
-		*csum_updated &= ~tcf_csum_update_flags(a);
-	} else {
+		*csum_updated &= ~act->csum_flags;
+		break;
+	default:
 		/* Currently we do not handle any other actions. */
 		return -EOPNOTSUPP;
 	}
@@ -789,7 +887,7 @@ int nfp_flower_compile_action(struct nfp_app *app,
 {
 	int act_len, act_cnt, err, tun_out_cnt, out_cnt, i;
 	enum nfp_flower_tun_type tun_type;
-	const struct tc_action *a;
+	struct flow_action_entry *act;
 	u32 csum_updated = 0;
 
 	memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
@@ -800,8 +898,8 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	tun_out_cnt = 0;
 	out_cnt = 0;
 
-	tcf_exts_for_each_action(i, a, flow->exts) {
-		err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len,
+	flow_action_for_each(i, act, &flow->rule->action) {
+		err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len,
 					     netdev, &tun_type, &tun_out_cnt,
 					     &out_cnt, &csum_updated);
 		if (err)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
index 4c5eaf36d5bb..cf9e1118ee8f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c
@@ -45,11 +45,9 @@ nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports)
 {
 	struct nfp_flower_cmsg_mac_repr *msg;
 	struct sk_buff *skb;
-	unsigned int size;
 
-	size = sizeof(*msg) + num_ports * sizeof(msg->ports[0]);
-	skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR,
-				    GFP_KERNEL);
+	skb = nfp_flower_cmsg_alloc(app, struct_size(msg, ports, num_ports),
+				    NFP_FLOWER_CMSG_TYPE_MAC_REPR, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
@@ -203,7 +201,7 @@ nfp_flower_cmsg_portreify_rx(struct nfp_app *app, struct sk_buff *skb)
 	}
 
 	atomic_inc(&priv->reify_replies);
-	wake_up_interruptible(&priv->reify_wait_queue);
+	wake_up(&priv->reify_wait_queue);
 }
 
 static void
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 29d673aa5277..0ed51e79db00 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -8,6 +8,7 @@
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <net/geneve.h>
+#include <net/vxlan.h>
 
 #include "../nfp_app.h"
 #include "../nfpcore/nfp_cpp.h"
@@ -25,7 +26,7 @@
 #define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
-#define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
+#define NFP_FLOWER_MASK_VLAN_PRESENT	BIT(12)
 #define NFP_FLOWER_MASK_VLAN_VID	GENMASK(11, 0)
 
 #define NFP_FLOWER_MASK_MPLS_LB		GENMASK(31, 12)
@@ -65,8 +66,10 @@
 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL	6
 #define NFP_FL_ACTION_OPCODE_SET_ETHERNET	7
 #define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS	9
+#define NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS	10
 #define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC	11
 #define NFP_FL_ACTION_OPCODE_SET_IPV6_DST	12
+#define NFP_FL_ACTION_OPCODE_SET_IPV6_TC_HL_FL	13
 #define NFP_FL_ACTION_OPCODE_SET_UDP		14
 #define NFP_FL_ACTION_OPCODE_SET_TCP		15
 #define NFP_FL_ACTION_OPCODE_PRE_LAG		16
@@ -79,9 +82,10 @@
 #define NFP_FL_OUT_FLAGS_TYPE_IDX	GENMASK(2, 0)
 
 #define NFP_FL_PUSH_VLAN_PRIO		GENMASK(15, 13)
-#define NFP_FL_PUSH_VLAN_CFI		BIT(12)
 #define NFP_FL_PUSH_VLAN_VID		GENMASK(11, 0)
 
+#define IPV6_FLOW_LABEL_MASK		cpu_to_be32(0x000fffff)
+
 /* LAG ports */
 #define NFP_FL_LAG_OUT			0xC0DE0000
 
@@ -92,6 +96,9 @@
 
 #define NFP_FLOWER_WORKQ_MAX_SKBS	30000
 
+/* Cmesg reply (empirical) timeout*/
+#define NFP_FL_REPLY_TIMEOUT		msecs_to_jiffies(40)
+
 #define nfp_flower_cmsg_warn(app, fmt, args...)                         \
 	do {                                                            \
 		if (net_ratelimit())                                    \
@@ -125,6 +132,26 @@ struct nfp_fl_set_ip4_addrs {
 	__be32 ipv4_dst;
 };
 
+struct nfp_fl_set_ip4_ttl_tos {
+	struct nfp_fl_act_head head;
+	u8 ipv4_ttl_mask;
+	u8 ipv4_tos_mask;
+	u8 ipv4_ttl;
+	u8 ipv4_tos;
+	__be16 reserved;
+};
+
+struct nfp_fl_set_ipv6_tc_hl_fl {
+	struct nfp_fl_act_head head;
+	u8 ipv6_tc_mask;
+	u8 ipv6_hop_limit_mask;
+	__be16 reserved;
+	u8 ipv6_tc;
+	u8 ipv6_hop_limit;
+	__be32 ipv6_label_mask;
+	__be32 ipv6_label;
+};
+
 struct nfp_fl_set_ipv6_addr {
 	struct nfp_fl_act_head head;
 	__be16 reserved;
@@ -475,6 +502,32 @@ static inline int nfp_flower_cmsg_get_data_len(struct sk_buff *skb)
 	return skb->len - NFP_FLOWER_CMSG_HLEN;
 }
 
+static inline bool
+nfp_fl_netdev_is_tunnel_type(struct net_device *netdev,
+			     enum nfp_flower_tun_type tun_type)
+{
+	if (netif_is_vxlan(netdev))
+		return tun_type == NFP_FL_TUNNEL_VXLAN;
+	if (netif_is_geneve(netdev))
+		return tun_type == NFP_FL_TUNNEL_GENEVE;
+
+	return false;
+}
+
+static inline bool nfp_fl_is_netdev_to_offload(struct net_device *netdev)
+{
+	if (!netdev->rtnl_link_ops)
+		return false;
+	if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
+		return true;
+	if (netif_is_vxlan(netdev))
+		return true;
+	if (netif_is_geneve(netdev))
+		return true;
+
+	return false;
+}
+
 struct sk_buff *
 nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports);
 void
diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 81dcf5b318ba..5db838f45694 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -472,17 +472,25 @@ nfp_fl_lag_schedule_group_remove(struct nfp_fl_lag *lag,
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
 }
 
-static int
+static void
 nfp_fl_lag_schedule_group_delete(struct nfp_fl_lag *lag,
 				 struct net_device *master)
 {
 	struct nfp_fl_lag_group *group;
+	struct nfp_flower_priv *priv;
+
+	priv = container_of(lag, struct nfp_flower_priv, nfp_lag);
+
+	if (!netif_is_bond_master(master))
+		return;
 
 	mutex_lock(&lag->lock);
 	group = nfp_fl_lag_find_group_for_master_with_lag(lag, master);
 	if (!group) {
 		mutex_unlock(&lag->lock);
-		return -ENOENT;
+		nfp_warn(priv->app->cpp, "untracked bond got unregistered %s\n",
+			 netdev_name(master));
+		return;
 	}
 
 	group->to_remove = true;
@@ -490,7 +498,6 @@ nfp_fl_lag_schedule_group_delete(struct nfp_fl_lag *lag,
 	mutex_unlock(&lag->lock);
 
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
-	return 0;
 }
 
 static int
@@ -575,7 +582,7 @@ nfp_fl_lag_changeupper_event(struct nfp_fl_lag *lag,
 	return 0;
 }
 
-static int
+static void
 nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 			  struct netdev_notifier_changelowerstate_info *info)
 {
@@ -586,18 +593,18 @@ nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 	unsigned long *flags;
 
 	if (!netif_is_lag_port(netdev) || !nfp_netdev_is_nfp_repr(netdev))
-		return 0;
+		return;
 
 	lag_lower_info = info->lower_state_info;
 	if (!lag_lower_info)
-		return 0;
+		return;
 
 	priv = container_of(lag, struct nfp_flower_priv, nfp_lag);
 	repr = netdev_priv(netdev);
 
 	/* Verify that the repr is associated with this app. */
 	if (repr->app != priv->app)
-		return 0;
+		return;
 
 	repr_priv = repr->app_priv;
 	flags = &repr_priv->lag_port_flags;
@@ -617,20 +624,15 @@ nfp_fl_lag_changels_event(struct nfp_fl_lag *lag, struct net_device *netdev,
 	mutex_unlock(&lag->lock);
 
 	schedule_delayed_work(&lag->work, NFP_FL_LAG_DELAY);
-	return 0;
 }
 
-static int
-nfp_fl_lag_netdev_event(struct notifier_block *nb, unsigned long event,
-			void *ptr)
+int nfp_flower_lag_netdev_event(struct nfp_flower_priv *priv,
+				struct net_device *netdev,
+				unsigned long event, void *ptr)
 {
-	struct net_device *netdev;
-	struct nfp_fl_lag *lag;
+	struct nfp_fl_lag *lag = &priv->nfp_lag;
 	int err;
 
-	netdev = netdev_notifier_info_to_dev(ptr);
-	lag = container_of(nb, struct nfp_fl_lag, lag_nb);
-
 	switch (event) {
 	case NETDEV_CHANGEUPPER:
 		err = nfp_fl_lag_changeupper_event(lag, ptr);
@@ -638,17 +640,11 @@ nfp_fl_lag_netdev_event(struct notifier_block *nb, unsigned long event,
 			return NOTIFY_BAD;
 		return NOTIFY_OK;
 	case NETDEV_CHANGELOWERSTATE:
-		err = nfp_fl_lag_changels_event(lag, netdev, ptr);
-		if (err)
-			return NOTIFY_BAD;
+		nfp_fl_lag_changels_event(lag, netdev, ptr);
 		return NOTIFY_OK;
 	case NETDEV_UNREGISTER:
-		if (netif_is_bond_master(netdev)) {
-			err = nfp_fl_lag_schedule_group_delete(lag, netdev);
-			if (err)
-				return NOTIFY_BAD;
-			return NOTIFY_OK;
-		}
+		nfp_fl_lag_schedule_group_delete(lag, netdev);
+		return NOTIFY_OK;
 	}
 
 	return NOTIFY_DONE;
@@ -673,8 +669,6 @@ void nfp_flower_lag_init(struct nfp_fl_lag *lag)
 
 	/* 0 is a reserved batch version so increment to first valid value. */
 	nfp_fl_increment_version(lag);
-
-	lag->lag_nb.notifier_call = nfp_fl_lag_netdev_event;
 }
 
 void nfp_flower_lag_cleanup(struct nfp_fl_lag *lag)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c
index 3a54728d2ea6..408089133599 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.c
@@ -32,6 +32,71 @@ static enum devlink_eswitch_mode eswitch_mode_get(struct nfp_app *app)
 	return DEVLINK_ESWITCH_MODE_SWITCHDEV;
 }
 
+static struct nfp_flower_non_repr_priv *
+nfp_flower_non_repr_priv_lookup(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_flower_non_repr_priv *entry;
+
+	ASSERT_RTNL();
+
+	list_for_each_entry(entry, &priv->non_repr_priv, list)
+		if (entry->netdev == netdev)
+			return entry;
+
+	return NULL;
+}
+
+void
+__nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv)
+{
+	non_repr_priv->ref_count++;
+}
+
+struct nfp_flower_non_repr_priv *
+nfp_flower_non_repr_priv_get(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_priv *priv = app->priv;
+	struct nfp_flower_non_repr_priv *entry;
+
+	entry = nfp_flower_non_repr_priv_lookup(app, netdev);
+	if (entry)
+		goto inc_ref;
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return NULL;
+
+	entry->netdev = netdev;
+	list_add(&entry->list, &priv->non_repr_priv);
+
+inc_ref:
+	__nfp_flower_non_repr_priv_get(entry);
+	return entry;
+}
+
+void
+__nfp_flower_non_repr_priv_put(struct nfp_flower_non_repr_priv *non_repr_priv)
+{
+	if (--non_repr_priv->ref_count)
+		return;
+
+	list_del(&non_repr_priv->list);
+	kfree(non_repr_priv);
+}
+
+void
+nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_flower_non_repr_priv *entry;
+
+	entry = nfp_flower_non_repr_priv_lookup(app, netdev);
+	if (!entry)
+		return;
+
+	__nfp_flower_non_repr_priv_put(entry);
+}
+
 static enum nfp_repr_type
 nfp_flower_repr_get_type_and_port(struct nfp_app *app, u32 port_id, u8 *port)
 {
@@ -107,16 +172,14 @@ static int
 nfp_flower_wait_repr_reify(struct nfp_app *app, atomic_t *replies, int tot_repl)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
 
 	if (!tot_repl)
 		return 0;
 
 	lockdep_assert_held(&app->pf->lock);
-	err = wait_event_interruptible_timeout(priv->reify_wait_queue,
-					       atomic_read(replies) >= tot_repl,
-					       msecs_to_jiffies(10));
-	if (err <= 0) {
+	if (!wait_event_timeout(priv->reify_wait_queue,
+				atomic_read(replies) >= tot_repl,
+				NFP_FL_REPLY_TIMEOUT)) {
 		nfp_warn(app->cpp, "Not all reprs responded to reify\n");
 		return -EIO;
 	}
@@ -146,23 +209,12 @@ nfp_flower_repr_netdev_stop(struct nfp_app *app, struct nfp_repr *repr)
 	return nfp_flower_cmsg_portmod(repr, false, repr->netdev->mtu, false);
 }
 
-static int
-nfp_flower_repr_netdev_init(struct nfp_app *app, struct net_device *netdev)
-{
-	return tc_setup_cb_egdev_register(netdev,
-					  nfp_flower_setup_tc_egress_cb,
-					  netdev_priv(netdev));
-}
-
 static void
 nfp_flower_repr_netdev_clean(struct nfp_app *app, struct net_device *netdev)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
 
 	kfree(repr->app_priv);
-
-	tc_setup_cb_egdev_unregister(netdev, nfp_flower_setup_tc_egress_cb,
-				     netdev_priv(netdev));
 }
 
 static void
@@ -234,6 +286,7 @@ nfp_flower_spawn_vnic_reprs(struct nfp_app *app,
 
 		nfp_repr = netdev_priv(repr);
 		nfp_repr->app_priv = repr_priv;
+		repr_priv->nfp_repr = nfp_repr;
 
 		/* For now we only support 1 PF */
 		WARN_ON(repr_type == NFP_REPR_TYPE_PF && i);
@@ -348,6 +401,7 @@ nfp_flower_spawn_phy_reprs(struct nfp_app *app, struct nfp_flower_priv *priv)
 
 		nfp_repr = netdev_priv(repr);
 		nfp_repr->app_priv = repr_priv;
+		repr_priv->nfp_repr = nfp_repr;
 
 		port = nfp_port_alloc(app, NFP_PORT_PHYS_PORT, repr);
 		if (IS_ERR(port)) {
@@ -487,8 +541,8 @@ err_clear_nn:
 
 static int nfp_flower_init(struct nfp_app *app)
 {
+	u64 version, features, ctx_count, num_mems;
 	const struct nfp_pf *pf = app->pf;
-	u64 version, features, ctx_count;
 	struct nfp_flower_priv *app_priv;
 	int err;
 
@@ -513,6 +567,23 @@ static int nfp_flower_init(struct nfp_app *app)
 		return err;
 	}
 
+	num_mems = nfp_rtsym_read_le(app->pf->rtbl, "CONFIG_FC_HOST_CTX_SPLIT",
+				     &err);
+	if (err) {
+		nfp_warn(app->cpp,
+			 "FlowerNIC: unsupported host context memory: %d\n",
+			 err);
+		err = 0;
+		num_mems = 1;
+	}
+
+	if (!FIELD_FIT(NFP_FL_STAT_ID_MU_NUM, num_mems) || !num_mems) {
+		nfp_warn(app->cpp,
+			 "FlowerNIC: invalid host context memory: %llu\n",
+			 num_mems);
+		return -EINVAL;
+	}
+
 	ctx_count = nfp_rtsym_read_le(app->pf->rtbl, "CONFIG_FC_HOST_CTX_COUNT",
 				      &err);
 	if (err) {
@@ -533,6 +604,8 @@ static int nfp_flower_init(struct nfp_app *app)
 	if (!app_priv)
 		return -ENOMEM;
 
+	app_priv->total_mem_units = num_mems;
+	app_priv->active_mem_unit = 0;
 	app_priv->stats_ring_size = roundup_pow_of_two(ctx_count);
 	app->priv = app_priv;
 	app_priv->app = app;
@@ -544,7 +617,7 @@ static int nfp_flower_init(struct nfp_app *app)
 	init_waitqueue_head(&app_priv->mtu_conf.wait_q);
 	spin_lock_init(&app_priv->mtu_conf.lock);
 
-	err = nfp_flower_metadata_init(app, ctx_count);
+	err = nfp_flower_metadata_init(app, ctx_count, num_mems);
 	if (err)
 		goto err_free_app_priv;
 
@@ -568,6 +641,9 @@ static int nfp_flower_init(struct nfp_app *app)
 		goto err_cleanup_metadata;
 	}
 
+	INIT_LIST_HEAD(&app_priv->indr_block_cb_priv);
+	INIT_LIST_HEAD(&app_priv->non_repr_priv);
+
 	return 0;
 
 err_cleanup_metadata:
@@ -610,7 +686,7 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 {
 	struct nfp_flower_priv *app_priv = app->priv;
 	struct nfp_repr *repr = netdev_priv(netdev);
-	int err, ack;
+	int err;
 
 	/* Only need to config FW for physical port MTU change. */
 	if (repr->port->type != NFP_PORT_PHYS_PORT)
@@ -637,11 +713,9 @@ nfp_flower_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 	}
 
 	/* Wait for fw to ack the change. */
-	ack = wait_event_timeout(app_priv->mtu_conf.wait_q,
-				 nfp_flower_check_ack(app_priv),
-				 msecs_to_jiffies(10));
-
-	if (!ack) {
+	if (!wait_event_timeout(app_priv->mtu_conf.wait_q,
+				nfp_flower_check_ack(app_priv),
+				NFP_FL_REPLY_TIMEOUT)) {
 		spin_lock_bh(&app_priv->mtu_conf.lock);
 		app_priv->mtu_conf.requested_val = 0;
 		spin_unlock_bh(&app_priv->mtu_conf.lock);
@@ -661,10 +735,6 @@ static int nfp_flower_start(struct nfp_app *app)
 		err = nfp_flower_lag_reset(&app_priv->nfp_lag);
 		if (err)
 			return err;
-
-		err = register_netdevice_notifier(&app_priv->nfp_lag.lag_nb);
-		if (err)
-			return err;
 	}
 
 	return nfp_tunnel_config_start(app);
@@ -672,12 +742,27 @@ static int nfp_flower_start(struct nfp_app *app)
 
 static void nfp_flower_stop(struct nfp_app *app)
 {
+	nfp_tunnel_config_stop(app);
+}
+
+static int
+nfp_flower_netdev_event(struct nfp_app *app, struct net_device *netdev,
+			unsigned long event, void *ptr)
+{
 	struct nfp_flower_priv *app_priv = app->priv;
+	int ret;
 
-	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG)
-		unregister_netdevice_notifier(&app_priv->nfp_lag.lag_nb);
+	if (app_priv->flower_ext_feats & NFP_FL_FEATS_LAG) {
+		ret = nfp_flower_lag_netdev_event(app_priv, netdev, event, ptr);
+		if (ret & NOTIFY_STOP_MASK)
+			return ret;
+	}
 
-	nfp_tunnel_config_stop(app);
+	ret = nfp_flower_reg_indir_block_handler(app, netdev, event);
+	if (ret & NOTIFY_STOP_MASK)
+		return ret;
+
+	return nfp_tunnel_mac_event_handler(app, netdev, event, ptr);
 }
 
 const struct nfp_app_type app_flower = {
@@ -698,7 +783,6 @@ const struct nfp_app_type app_flower = {
 	.vnic_init	= nfp_flower_vnic_init,
 	.vnic_clean	= nfp_flower_vnic_clean,
 
-	.repr_init	= nfp_flower_repr_netdev_init,
 	.repr_preclean	= nfp_flower_repr_netdev_preclean,
 	.repr_clean	= nfp_flower_repr_netdev_clean,
 
@@ -708,6 +792,8 @@ const struct nfp_app_type app_flower = {
 	.start		= nfp_flower_start,
 	.stop		= nfp_flower_stop,
 
+	.netdev_event	= nfp_flower_netdev_event,
+
 	.ctrl_msg_rx	= nfp_flower_cmsg_rx,
 
 	.sriov_enable	= nfp_flower_sriov_enable,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 90045bab95bf..c0945a5fd1a4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -20,7 +20,9 @@ struct nfp_fl_pre_lag;
 struct net_device;
 struct nfp_app;
 
-#define NFP_FL_STATS_CTX_DONT_CARE	cpu_to_be32(0xffffffff)
+#define NFP_FL_STAT_ID_MU_NUM		GENMASK(31, 22)
+#define NFP_FL_STAT_ID_STAT		GENMASK(21, 0)
+
 #define NFP_FL_STATS_ELEM_RS		FIELD_SIZEOF(struct nfp_fl_stats_id, \
 						     init_unalloc)
 #define NFP_FLOWER_MASK_ENTRY_RS	256
@@ -55,6 +57,26 @@ struct nfp_fl_stats_id {
 };
 
 /**
+ * struct nfp_fl_tunnel_offloads - priv data for tunnel offloads
+ * @offloaded_macs:	Hashtable of the offloaded MAC addresses
+ * @ipv4_off_list:	List of IPv4 addresses to offload
+ * @neigh_off_list:	List of neighbour offloads
+ * @ipv4_off_lock:	Lock for the IPv4 address list
+ * @neigh_off_lock:	Lock for the neighbour address list
+ * @mac_off_ids:	IDA to manage id assignment for offloaded MACs
+ * @neigh_nb:		Notifier to monitor neighbour state
+ */
+struct nfp_fl_tunnel_offloads {
+	struct rhashtable offloaded_macs;
+	struct list_head ipv4_off_list;
+	struct list_head neigh_off_list;
+	struct mutex ipv4_off_lock;
+	spinlock_t neigh_off_lock;
+	struct ida mac_off_ids;
+	struct notifier_block neigh_nb;
+};
+
+/**
  * struct nfp_mtu_conf - manage MTU setting
  * @portnum:		NFP port number of repr with requested MTU change
  * @requested_val:	MTU value requested for repr
@@ -72,7 +94,6 @@ struct nfp_mtu_conf {
 
 /**
  * struct nfp_fl_lag - Flower APP priv data for link aggregation
- * @lag_nb:		Notifier to track master/slave events
  * @work:		Work queue for writing configs to the HW
  * @lock:		Lock to protect lag_group_list
  * @group_list:		List of all master/slave groups offloaded
@@ -85,7 +106,6 @@ struct nfp_mtu_conf {
  *			retransmission
  */
 struct nfp_fl_lag {
-	struct notifier_block lag_nb;
 	struct delayed_work work;
 	struct mutex lock;
 	struct list_head group_list;
@@ -116,23 +136,16 @@ struct nfp_fl_lag {
  *			processing
  * @cmsg_skbs_low:	List of lower priority skbs for control message
  *			processing
- * @nfp_mac_off_list:	List of MAC addresses to offload
- * @nfp_mac_index_list:	List of unique 8-bit indexes for non NFP netdevs
- * @nfp_ipv4_off_list:	List of IPv4 addresses to offload
- * @nfp_neigh_off_list:	List of neighbour offloads
- * @nfp_mac_off_lock:	Lock for the MAC address list
- * @nfp_mac_index_lock:	Lock for the MAC index list
- * @nfp_ipv4_off_lock:	Lock for the IPv4 address list
- * @nfp_neigh_off_lock:	Lock for the neighbour address list
- * @nfp_mac_off_ids:	IDA to manage id assignment for offloaded macs
- * @nfp_mac_off_count:	Number of MACs in address list
- * @nfp_tun_mac_nb:	Notifier to monitor link state
- * @nfp_tun_neigh_nb:	Notifier to monitor neighbour state
+ * @tun:		Tunnel offload data
  * @reify_replies:	atomically stores the number of replies received
  *			from firmware for repr reify
  * @reify_wait_queue:	wait queue for repr reify response counting
  * @mtu_conf:		Configuration of repr MTU value
  * @nfp_lag:		Link aggregation data block
+ * @indr_block_cb_priv:	List of priv data passed to indirect block cbs
+ * @non_repr_priv:	List of offloaded non-repr ports and their priv data
+ * @active_mem_unit:	Current active memory unit for flower rules
+ * @total_mem_units:	Total number of available memory units for flower rules
  */
 struct nfp_flower_priv {
 	struct nfp_app *app;
@@ -150,30 +163,47 @@ struct nfp_flower_priv {
 	struct work_struct cmsg_work;
 	struct sk_buff_head cmsg_skbs_high;
 	struct sk_buff_head cmsg_skbs_low;
-	struct list_head nfp_mac_off_list;
-	struct list_head nfp_mac_index_list;
-	struct list_head nfp_ipv4_off_list;
-	struct list_head nfp_neigh_off_list;
-	struct mutex nfp_mac_off_lock;
-	struct mutex nfp_mac_index_lock;
-	struct mutex nfp_ipv4_off_lock;
-	spinlock_t nfp_neigh_off_lock;
-	struct ida nfp_mac_off_ids;
-	int nfp_mac_off_count;
-	struct notifier_block nfp_tun_mac_nb;
-	struct notifier_block nfp_tun_neigh_nb;
+	struct nfp_fl_tunnel_offloads tun;
 	atomic_t reify_replies;
 	wait_queue_head_t reify_wait_queue;
 	struct nfp_mtu_conf mtu_conf;
 	struct nfp_fl_lag nfp_lag;
+	struct list_head indr_block_cb_priv;
+	struct list_head non_repr_priv;
+	unsigned int active_mem_unit;
+	unsigned int total_mem_units;
 };
 
 /**
  * struct nfp_flower_repr_priv - Flower APP per-repr priv data
+ * @nfp_repr:		Back pointer to nfp_repr
  * @lag_port_flags:	Extended port flags to record lag state of repr
+ * @mac_offloaded:	Flag indicating a MAC address is offloaded for repr
+ * @offloaded_mac_addr:	MAC address that has been offloaded for repr
+ * @mac_list:		List entry of reprs that share the same offloaded MAC
  */
 struct nfp_flower_repr_priv {
+	struct nfp_repr *nfp_repr;
 	unsigned long lag_port_flags;
+	bool mac_offloaded;
+	u8 offloaded_mac_addr[ETH_ALEN];
+	struct list_head mac_list;
+};
+
+/**
+ * struct nfp_flower_non_repr_priv - Priv data for non-repr offloaded ports
+ * @list:		List entry of offloaded reprs
+ * @netdev:		Pointer to non-repr net_device
+ * @ref_count:		Number of references held for this priv data
+ * @mac_offloaded:	Flag indicating a MAC address is offloaded for device
+ * @offloaded_mac_addr:	MAC address that has been offloaded for dev
+ */
+struct nfp_flower_non_repr_priv {
+	struct list_head list;
+	struct net_device *netdev;
+	int ref_count;
+	bool mac_offloaded;
+	u8 offloaded_mac_addr[ETH_ALEN];
 };
 
 struct nfp_fl_key_ls {
@@ -209,7 +239,6 @@ struct nfp_fl_payload {
 	char *unmasked_data;
 	char *mask_data;
 	char *action_data;
-	bool ingress_offload;
 };
 
 extern const struct rhashtable_params nfp_flower_table_params;
@@ -221,12 +250,14 @@ struct nfp_fl_stats_frame {
 	__be64 stats_cookie;
 };
 
-int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count);
+int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
+			     unsigned int host_ctx_split);
 void nfp_flower_metadata_cleanup(struct nfp_app *app);
 
 int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
 			enum tc_setup_type type, void *type_data);
-int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
+int nfp_flower_compile_flow_match(struct nfp_app *app,
+				  struct tc_cls_flower_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
@@ -244,7 +275,7 @@ int nfp_modify_flow_metadata(struct nfp_app *app,
 
 struct nfp_fl_payload *
 nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
-			   struct net_device *netdev, __be32 host_ctx);
+			   struct net_device *netdev);
 struct nfp_fl_payload *
 nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie);
 
@@ -252,21 +283,35 @@ void nfp_flower_rx_flow_stats(struct nfp_app *app, struct sk_buff *skb);
 
 int nfp_tunnel_config_start(struct nfp_app *app);
 void nfp_tunnel_config_stop(struct nfp_app *app);
-void nfp_tunnel_write_macs(struct nfp_app *app);
+int nfp_tunnel_mac_event_handler(struct nfp_app *app,
+				 struct net_device *netdev,
+				 unsigned long event, void *ptr);
 void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4);
 void nfp_tunnel_request_route(struct nfp_app *app, struct sk_buff *skb);
 void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb);
-int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
-				  void *cb_priv);
 void nfp_flower_lag_init(struct nfp_fl_lag *lag);
 void nfp_flower_lag_cleanup(struct nfp_fl_lag *lag);
 int nfp_flower_lag_reset(struct nfp_fl_lag *lag);
+int nfp_flower_lag_netdev_event(struct nfp_flower_priv *priv,
+				struct net_device *netdev,
+				unsigned long event, void *ptr);
 bool nfp_flower_lag_unprocessed_msg(struct nfp_app *app, struct sk_buff *skb);
 int nfp_flower_lag_populate_pre_action(struct nfp_app *app,
 				       struct net_device *master,
 				       struct nfp_fl_pre_lag *pre_act);
 int nfp_flower_lag_get_output_id(struct nfp_app *app,
 				 struct net_device *master);
+int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
+				       struct net_device *netdev,
+				       unsigned long event);
 
+void
+__nfp_flower_non_repr_priv_get(struct nfp_flower_non_repr_priv *non_repr_priv);
+struct nfp_flower_non_repr_priv *
+nfp_flower_non_repr_priv_get(struct nfp_app *app, struct net_device *netdev);
+void
+__nfp_flower_non_repr_priv_put(struct nfp_flower_non_repr_priv *non_repr_priv);
+void
+nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index e54fb6034326..9b8b843d0340 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -8,32 +8,41 @@
 #include "main.h"
 
 static void
-nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame,
-			    struct tc_cls_flower_offload *flow, u8 key_type,
-			    bool mask_version)
+nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext,
+			    struct nfp_flower_meta_tci *msk,
+			    struct tc_cls_flower_offload *flow, u8 key_type)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_vlan *flow_vlan;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
 	u16 tmp_tci;
 
-	memset(frame, 0, sizeof(struct nfp_flower_meta_tci));
+	memset(ext, 0, sizeof(struct nfp_flower_meta_tci));
+	memset(msk, 0, sizeof(struct nfp_flower_meta_tci));
+
 	/* Populate the metadata frame. */
-	frame->nfp_flow_key_layer = key_type;
-	frame->mask_id = ~0;
+	ext->nfp_flow_key_layer = key_type;
+	ext->mask_id = ~0;
+
+	msk->nfp_flow_key_layer = key_type;
+	msk->mask_id = ~0;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		flow_vlan = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_VLAN,
-						      target);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan match;
+
+		flow_rule_match_vlan(rule, &match);
 		/* Populate the tci field. */
-		if (flow_vlan->vlan_id || flow_vlan->vlan_priority) {
-			tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
-					     flow_vlan->vlan_priority) |
-				  FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
-					     flow_vlan->vlan_id) |
-				  NFP_FLOWER_MASK_VLAN_CFI;
-			frame->tci = cpu_to_be16(tmp_tci);
-		}
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      match.key->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      match.key->vlan_id);
+		ext->tci = cpu_to_be16(tmp_tci);
+
+		tmp_tci = NFP_FLOWER_MASK_VLAN_PRESENT;
+		tmp_tci |= FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO,
+				      match.mask->vlan_priority) |
+			   FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID,
+				      match.mask->vlan_id);
+		msk->tci = cpu_to_be16(tmp_tci);
 	}
 }
 
@@ -52,266 +61,288 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 		return 0;
 	}
 
-	if (tun_type)
+	if (tun_type) {
 		frame->in_port = cpu_to_be32(NFP_FL_PORT_TYPE_TUN | tun_type);
-	else
+	} else {
+		if (!cmsg_port)
+			return -EOPNOTSUPP;
 		frame->in_port = cpu_to_be32(cmsg_port);
+	}
 
 	return 0;
 }
 
 static void
-nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame,
-		       struct tc_cls_flower_offload *flow,
-		       bool mask_version)
+nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
+		       struct nfp_flower_mac_mpls *msk,
+		       struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_eth_addrs *addr;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_mac_mpls));
+	memset(msk, 0, sizeof(struct nfp_flower_mac_mpls));
 
-	memset(frame, 0, sizeof(struct nfp_flower_mac_mpls));
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+		struct flow_match_eth_addrs match;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
-		addr = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_ETH_ADDRS,
-						 target);
+		flow_rule_match_eth_addrs(rule, &match);
 		/* Populate mac frame. */
-		ether_addr_copy(frame->mac_dst, &addr->dst[0]);
-		ether_addr_copy(frame->mac_src, &addr->src[0]);
+		ether_addr_copy(ext->mac_dst, &match.key->dst[0]);
+		ether_addr_copy(ext->mac_src, &match.key->src[0]);
+		ether_addr_copy(msk->mac_dst, &match.mask->dst[0]);
+		ether_addr_copy(msk->mac_src, &match.mask->src[0]);
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) {
-		struct flow_dissector_key_mpls *mpls;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) {
+		struct flow_match_mpls match;
 		u32 t_mpls;
 
-		mpls = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_MPLS,
-						 target);
-
-		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, mpls->mpls_label) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, mpls->mpls_tc) |
-			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, mpls->mpls_bos) |
+		flow_rule_match_mpls(rule, &match);
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.key->mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.key->mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.key->mpls_bos) |
 			 NFP_FLOWER_MASK_MPLS_Q;
-
-		frame->mpls_lse = cpu_to_be32(t_mpls);
-	} else if (dissector_uses_key(flow->dissector,
-				      FLOW_DISSECTOR_KEY_BASIC)) {
+		ext->mpls_lse = cpu_to_be32(t_mpls);
+		t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.mask->mpls_label) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.mask->mpls_tc) |
+			 FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.mask->mpls_bos) |
+			 NFP_FLOWER_MASK_MPLS_Q;
+		msk->mpls_lse = cpu_to_be32(t_mpls);
+	} else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		/* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q
 		 * bit, which indicates an mpls ether type but without any
 		 * mpls fields.
 		 */
-		struct flow_dissector_key_basic *key_basic;
-
-		key_basic = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_BASIC,
-						      flow->key);
-		if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
-		    key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC))
-			frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		if (match.key->n_proto == cpu_to_be16(ETH_P_MPLS_UC) ||
+		    match.key->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) {
+			ext->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+			msk->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q);
+		}
 	}
 }
 
 static void
-nfp_flower_compile_tport(struct nfp_flower_tp_ports *frame,
-			 struct tc_cls_flower_offload *flow,
-			 bool mask_version)
+nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext,
+			 struct nfp_flower_tp_ports *msk,
+			 struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ports *tp;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_tp_ports));
+	memset(msk, 0, sizeof(struct nfp_flower_tp_ports));
 
-	memset(frame, 0, sizeof(struct nfp_flower_tp_ports));
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		tp = skb_flow_dissector_target(flow->dissector,
-					       FLOW_DISSECTOR_KEY_PORTS,
-					       target);
-		frame->port_src = tp->src;
-		frame->port_dst = tp->dst;
+		flow_rule_match_ports(rule, &match);
+		ext->port_src = match.key->src;
+		ext->port_dst = match.key->dst;
+		msk->port_src = match.mask->src;
+		msk->port_dst = match.mask->dst;
 	}
 }
 
 static void
-nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *frame,
-			  struct tc_cls_flower_offload *flow,
-			  bool mask_version)
+nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext,
+			  struct nfp_flower_ip_ext *msk,
+			  struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *basic;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		basic = skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_BASIC,
-						  target);
-		frame->proto = basic->ip_proto;
+		flow_rule_match_basic(rule, &match);
+		ext->proto = match.key->ip_proto;
+		msk->proto = match.mask->ip_proto;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) {
-		struct flow_dissector_key_ip *flow_ip;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) {
+		struct flow_match_ip match;
 
-		flow_ip = skb_flow_dissector_target(flow->dissector,
-						    FLOW_DISSECTOR_KEY_IP,
-						    target);
-		frame->tos = flow_ip->tos;
-		frame->ttl = flow_ip->ttl;
+		flow_rule_match_ip(rule, &match);
+		ext->tos = match.key->tos;
+		ext->ttl = match.key->ttl;
+		msk->tos = match.mask->tos;
+		msk->ttl = match.mask->ttl;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) {
-		struct flow_dissector_key_tcp *tcp;
-		u32 tcp_flags;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
+		u16 tcp_flags, tcp_flags_mask;
+		struct flow_match_tcp match;
 
-		tcp = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_TCP, target);
-		tcp_flags = be16_to_cpu(tcp->flags);
+		flow_rule_match_tcp(rule, &match);
+		tcp_flags = be16_to_cpu(match.key->flags);
+		tcp_flags_mask = be16_to_cpu(match.mask->flags);
 
 		if (tcp_flags & TCPHDR_FIN)
-			frame->flags |= NFP_FL_TCP_FLAG_FIN;
+			ext->flags |= NFP_FL_TCP_FLAG_FIN;
+		if (tcp_flags_mask & TCPHDR_FIN)
+			msk->flags |= NFP_FL_TCP_FLAG_FIN;
+
 		if (tcp_flags & TCPHDR_SYN)
-			frame->flags |= NFP_FL_TCP_FLAG_SYN;
+			ext->flags |= NFP_FL_TCP_FLAG_SYN;
+		if (tcp_flags_mask & TCPHDR_SYN)
+			msk->flags |= NFP_FL_TCP_FLAG_SYN;
+
 		if (tcp_flags & TCPHDR_RST)
-			frame->flags |= NFP_FL_TCP_FLAG_RST;
+			ext->flags |= NFP_FL_TCP_FLAG_RST;
+		if (tcp_flags_mask & TCPHDR_RST)
+			msk->flags |= NFP_FL_TCP_FLAG_RST;
+
 		if (tcp_flags & TCPHDR_PSH)
-			frame->flags |= NFP_FL_TCP_FLAG_PSH;
+			ext->flags |= NFP_FL_TCP_FLAG_PSH;
+		if (tcp_flags_mask & TCPHDR_PSH)
+			msk->flags |= NFP_FL_TCP_FLAG_PSH;
+
 		if (tcp_flags & TCPHDR_URG)
-			frame->flags |= NFP_FL_TCP_FLAG_URG;
+			ext->flags |= NFP_FL_TCP_FLAG_URG;
+		if (tcp_flags_mask & TCPHDR_URG)
+			msk->flags |= NFP_FL_TCP_FLAG_URG;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key;
-
-		key = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_CONTROL,
-						target);
-		if (key->flags & FLOW_DIS_IS_FRAGMENT)
-			frame->flags |= NFP_FL_IP_FRAGMENTED;
-		if (key->flags & FLOW_DIS_FIRST_FRAG)
-			frame->flags |= NFP_FL_IP_FRAG_FIRST;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		if (match.key->flags & FLOW_DIS_IS_FRAGMENT)
+			ext->flags |= NFP_FL_IP_FRAGMENTED;
+		if (match.mask->flags & FLOW_DIS_IS_FRAGMENT)
+			msk->flags |= NFP_FL_IP_FRAGMENTED;
+		if (match.key->flags & FLOW_DIS_FIRST_FRAG)
+			ext->flags |= NFP_FL_IP_FRAG_FIRST;
+		if (match.mask->flags & FLOW_DIS_FIRST_FRAG)
+			msk->flags |= NFP_FL_IP_FRAG_FIRST;
 	}
 }
 
 static void
-nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame,
-			struct tc_cls_flower_offload *flow,
-			bool mask_version)
+nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext,
+			struct nfp_flower_ipv4 *msk,
+			struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ipv4_addrs *addr;
-
-	memset(frame, 0, sizeof(struct nfp_flower_ipv4));
-
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		addr = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						 target);
-		frame->ipv4_src = addr->src;
-		frame->ipv4_dst = addr->dst;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_match_ipv4_addrs match;
+
+	memset(ext, 0, sizeof(struct nfp_flower_ipv4));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv4));
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		flow_rule_match_ipv4_addrs(rule, &match);
+		ext->ipv4_src = match.key->src;
+		ext->ipv4_dst = match.key->dst;
+		msk->ipv4_src = match.mask->src;
+		msk->ipv4_dst = match.mask->dst;
 	}
 
-	nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version);
+	nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow);
 }
 
 static void
-nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
-			struct tc_cls_flower_offload *flow,
-			bool mask_version)
+nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext,
+			struct nfp_flower_ipv6 *msk,
+			struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ipv6_addrs *addr;
-
-	memset(frame, 0, sizeof(struct nfp_flower_ipv6));
-
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		addr = skb_flow_dissector_target(flow->dissector,
-						 FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						 target);
-		frame->ipv6_src = addr->src;
-		frame->ipv6_dst = addr->dst;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+
+	memset(ext, 0, sizeof(struct nfp_flower_ipv6));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv6));
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
+
+		flow_rule_match_ipv6_addrs(rule, &match);
+		ext->ipv6_src = match.key->src;
+		ext->ipv6_dst = match.key->dst;
+		msk->ipv6_src = match.mask->src;
+		msk->ipv6_dst = match.mask->dst;
 	}
 
-	nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version);
+	nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow);
 }
 
 static int
-nfp_flower_compile_geneve_opt(void *key_buf, struct tc_cls_flower_offload *flow,
-			      bool mask_version)
+nfp_flower_compile_geneve_opt(void *ext, void *msk,
+			      struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_enc_opts *opts;
+	struct flow_match_enc_opts match;
 
-	opts = skb_flow_dissector_target(flow->dissector,
-					 FLOW_DISSECTOR_KEY_ENC_OPTS,
-					 target);
-	memcpy(key_buf, opts->data, opts->len);
+	flow_rule_match_enc_opts(flow->rule, &match);
+	memcpy(ext, match.key->data, match.key->len);
+	memcpy(msk, match.mask->data, match.mask->len);
 
 	return 0;
 }
 
 static void
-nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
-				struct tc_cls_flower_offload *flow,
-				bool mask_version)
+nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext,
+				struct nfp_flower_ipv4_udp_tun *msk,
+				struct tc_cls_flower_offload *flow)
 {
-	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
-	struct flow_dissector_key_ipv4_addrs *tun_ips;
-	struct flow_dissector_key_keyid *vni;
-	struct flow_dissector_key_ip *ip;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
 
-	memset(frame, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
+	memset(ext, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
+	memset(msk, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
 
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) {
+		struct flow_match_enc_keyid match;
 		u32 temp_vni;
 
-		vni = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_ENC_KEYID,
-						target);
-		temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET;
-		frame->tun_id = cpu_to_be32(temp_vni);
+		flow_rule_match_enc_keyid(rule, &match);
+		temp_vni = be32_to_cpu(match.key->keyid) << NFP_FL_TUN_VNI_OFFSET;
+		ext->tun_id = cpu_to_be32(temp_vni);
+		temp_vni = be32_to_cpu(match.mask->keyid) << NFP_FL_TUN_VNI_OFFSET;
+		msk->tun_id = cpu_to_be32(temp_vni);
 	}
 
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
-		tun_ips =
-		   skb_flow_dissector_target(flow->dissector,
-					     FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-					     target);
-		frame->ip_src = tun_ips->src;
-		frame->ip_dst = tun_ips->dst;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
+
+		flow_rule_match_enc_ipv4_addrs(rule, &match);
+		ext->ip_src = match.key->src;
+		ext->ip_dst = match.key->dst;
+		msk->ip_src = match.mask->src;
+		msk->ip_dst = match.mask->dst;
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
-		ip = skb_flow_dissector_target(flow->dissector,
-					       FLOW_DISSECTOR_KEY_ENC_IP,
-					       target);
-		frame->tos = ip->tos;
-		frame->ttl = ip->ttl;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_match_ip match;
+
+		flow_rule_match_enc_ip(rule, &match);
+		ext->tos = match.key->tos;
+		ext->ttl = match.key->ttl;
+		msk->tos = match.mask->tos;
+		msk->ttl = match.mask->ttl;
 	}
 }
 
-int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
+int nfp_flower_compile_flow_match(struct nfp_app *app,
+				  struct tc_cls_flower_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
 				  enum nfp_flower_tun_type tun_type)
 {
-	struct nfp_repr *netdev_repr;
+	u32 cmsg_port = 0;
 	int err;
 	u8 *ext;
 	u8 *msk;
 
+	if (nfp_netdev_is_nfp_repr(netdev))
+		cmsg_port = nfp_repr_get_port_id(netdev);
+
 	memset(nfp_flow->unmasked_data, 0, key_ls->key_size);
 	memset(nfp_flow->mask_data, 0, key_ls->key_size);
 
 	ext = nfp_flow->unmasked_data;
 	msk = nfp_flow->mask_data;
 
-	/* Populate Exact Metadata. */
 	nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)ext,
-				    flow, key_ls->key_layer, false);
-	/* Populate Mask Metadata. */
-	nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)msk,
-				    flow, key_ls->key_layer, true);
+				    (struct nfp_flower_meta_tci *)msk,
+				    flow, key_ls->key_layer);
 	ext += sizeof(struct nfp_flower_meta_tci);
 	msk += sizeof(struct nfp_flower_meta_tci);
 
@@ -327,15 +358,13 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 
 	/* Populate Exact Port data. */
 	err = nfp_flower_compile_port((struct nfp_flower_in_port *)ext,
-				      nfp_repr_get_port_id(netdev),
-				      false, tun_type);
+				      cmsg_port, false, tun_type);
 	if (err)
 		return err;
 
 	/* Populate Mask Port Data. */
 	err = nfp_flower_compile_port((struct nfp_flower_in_port *)msk,
-				      nfp_repr_get_port_id(netdev),
-				      true, tun_type);
+				      cmsg_port, true, tun_type);
 	if (err)
 		return err;
 
@@ -343,45 +372,33 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 	msk += sizeof(struct nfp_flower_in_port);
 
 	if (NFP_FLOWER_LAYER_MAC & key_ls->key_layer) {
-		/* Populate Exact MAC Data. */
 		nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext,
-				       flow, false);
-		/* Populate Mask MAC Data. */
-		nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)msk,
-				       flow, true);
+				       (struct nfp_flower_mac_mpls *)msk,
+				       flow);
 		ext += sizeof(struct nfp_flower_mac_mpls);
 		msk += sizeof(struct nfp_flower_mac_mpls);
 	}
 
 	if (NFP_FLOWER_LAYER_TP & key_ls->key_layer) {
-		/* Populate Exact TP Data. */
 		nfp_flower_compile_tport((struct nfp_flower_tp_ports *)ext,
-					 flow, false);
-		/* Populate Mask TP Data. */
-		nfp_flower_compile_tport((struct nfp_flower_tp_ports *)msk,
-					 flow, true);
+					 (struct nfp_flower_tp_ports *)msk,
+					 flow);
 		ext += sizeof(struct nfp_flower_tp_ports);
 		msk += sizeof(struct nfp_flower_tp_ports);
 	}
 
 	if (NFP_FLOWER_LAYER_IPV4 & key_ls->key_layer) {
-		/* Populate Exact IPv4 Data. */
 		nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)ext,
-					flow, false);
-		/* Populate Mask IPv4 Data. */
-		nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)msk,
-					flow, true);
+					(struct nfp_flower_ipv4 *)msk,
+					flow);
 		ext += sizeof(struct nfp_flower_ipv4);
 		msk += sizeof(struct nfp_flower_ipv4);
 	}
 
 	if (NFP_FLOWER_LAYER_IPV6 & key_ls->key_layer) {
-		/* Populate Exact IPv4 Data. */
 		nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)ext,
-					flow, false);
-		/* Populate Mask IPv4 Data. */
-		nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)msk,
-					flow, true);
+					(struct nfp_flower_ipv6 *)msk,
+					flow);
 		ext += sizeof(struct nfp_flower_ipv6);
 		msk += sizeof(struct nfp_flower_ipv6);
 	}
@@ -390,32 +407,19 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 	    key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE) {
 		__be32 tun_dst;
 
-		/* Populate Exact VXLAN Data. */
-		nfp_flower_compile_ipv4_udp_tun((void *)ext, flow, false);
-		/* Populate Mask VXLAN Data. */
-		nfp_flower_compile_ipv4_udp_tun((void *)msk, flow, true);
+		nfp_flower_compile_ipv4_udp_tun((void *)ext, (void *)msk, flow);
 		tun_dst = ((struct nfp_flower_ipv4_udp_tun *)ext)->ip_dst;
 		ext += sizeof(struct nfp_flower_ipv4_udp_tun);
 		msk += sizeof(struct nfp_flower_ipv4_udp_tun);
 
-		/* Configure tunnel end point MAC. */
-		if (nfp_netdev_is_nfp_repr(netdev)) {
-			netdev_repr = netdev_priv(netdev);
-			nfp_tunnel_write_macs(netdev_repr->app);
-
-			/* Store the tunnel destination in the rule data.
-			 * This must be present and be an exact match.
-			 */
-			nfp_flow->nfp_tun_ipv4_addr = tun_dst;
-			nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst);
-		}
+		/* Store the tunnel destination in the rule data.
+		 * This must be present and be an exact match.
+		 */
+		nfp_flow->nfp_tun_ipv4_addr = tun_dst;
+		nfp_tunnel_add_ipv4_off(app, tun_dst);
 
 		if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
-			err = nfp_flower_compile_geneve_opt(ext, flow, false);
-			if (err)
-				return err;
-
-			err = nfp_flower_compile_geneve_opt(msk, flow, true);
+			err = nfp_flower_compile_geneve_opt(ext, msk, flow);
 			if (err)
 				return err;
 		}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 48729bf171e0..492837b852b6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -4,6 +4,7 @@
 #include <linux/hash.h>
 #include <linux/hashtable.h>
 #include <linux/jhash.h>
+#include <linux/math64.h>
 #include <linux/vmalloc.h>
 #include <net/pkt_cls.h>
 
@@ -21,7 +22,6 @@ struct nfp_mask_id_table {
 struct nfp_fl_flow_table_cmp_arg {
 	struct net_device *netdev;
 	unsigned long cookie;
-	__be32 host_ctx;
 };
 
 static int nfp_release_stats_entry(struct nfp_app *app, u32 stats_context_id)
@@ -53,8 +53,17 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id)
 	freed_stats_id = priv->stats_ring_size;
 	/* Check for unallocated entries first. */
 	if (priv->stats_ids.init_unalloc > 0) {
-		*stats_context_id = priv->stats_ids.init_unalloc - 1;
-		priv->stats_ids.init_unalloc--;
+		if (priv->active_mem_unit == priv->total_mem_units) {
+			priv->stats_ids.init_unalloc--;
+			priv->active_mem_unit = 0;
+		}
+
+		*stats_context_id =
+			FIELD_PREP(NFP_FL_STAT_ID_STAT,
+				   priv->stats_ids.init_unalloc - 1) |
+			FIELD_PREP(NFP_FL_STAT_ID_MU_NUM,
+				   priv->active_mem_unit);
+		priv->active_mem_unit++;
 		return 0;
 	}
 
@@ -76,14 +85,13 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id)
 /* Must be called with either RTNL or rcu_read_lock */
 struct nfp_fl_payload *
 nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie,
-			   struct net_device *netdev, __be32 host_ctx)
+			   struct net_device *netdev)
 {
 	struct nfp_fl_flow_table_cmp_arg flower_cmp_arg;
 	struct nfp_flower_priv *priv = app->priv;
 
 	flower_cmp_arg.netdev = netdev;
 	flower_cmp_arg.cookie = tc_flower_cookie;
-	flower_cmp_arg.host_ctx = host_ctx;
 
 	return rhashtable_lookup_fast(&priv->flow_table, &flower_cmp_arg,
 				      nfp_flower_table_params);
@@ -287,6 +295,7 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 
 	nfp_flow->meta.host_ctx_id = cpu_to_be32(stats_cxt);
 	nfp_flow->meta.host_cookie = cpu_to_be64(flow->cookie);
+	nfp_flow->ingress_dev = netdev;
 
 	new_mask_id = 0;
 	if (!nfp_check_mask_add(app, nfp_flow->mask_data,
@@ -306,8 +315,7 @@ int nfp_compile_flow_metadata(struct nfp_app *app,
 	priv->stats[stats_cxt].bytes = 0;
 	priv->stats[stats_cxt].used = jiffies;
 
-	check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev,
-						 NFP_FL_STATS_CTX_DONT_CARE);
+	check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (check_entry) {
 		if (nfp_release_stats_entry(app, stats_cxt))
 			return -EINVAL;
@@ -352,9 +360,7 @@ static int nfp_fl_obj_cmpfn(struct rhashtable_compare_arg *arg,
 	const struct nfp_fl_flow_table_cmp_arg *cmp_arg = arg->key;
 	const struct nfp_fl_payload *flow_entry = obj;
 
-	if ((!cmp_arg->netdev || flow_entry->ingress_dev == cmp_arg->netdev) &&
-	    (cmp_arg->host_ctx == NFP_FL_STATS_CTX_DONT_CARE ||
-	     flow_entry->meta.host_ctx_id == cmp_arg->host_ctx))
+	if (flow_entry->ingress_dev == cmp_arg->netdev)
 		return flow_entry->tc_flower_cookie != cmp_arg->cookie;
 
 	return 1;
@@ -385,10 +391,11 @@ const struct rhashtable_params nfp_flower_table_params = {
 	.automatic_shrinking	= true,
 };
 
-int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count)
+int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count,
+			     unsigned int host_num_mems)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
+	int err, stats_size;
 
 	hash_init(priv->mask_table);
 
@@ -421,10 +428,12 @@ int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count)
 	if (!priv->stats_ids.free_list.buf)
 		goto err_free_last_used;
 
-	priv->stats_ids.init_unalloc = host_ctx_count;
+	priv->stats_ids.init_unalloc = div_u64(host_ctx_count, host_num_mems);
 
-	priv->stats = kvmalloc_array(priv->stats_ring_size,
-				     sizeof(struct nfp_fl_stats), GFP_KERNEL);
+	stats_size = FIELD_PREP(NFP_FL_STAT_ID_STAT, host_ctx_count) |
+		     FIELD_PREP(NFP_FL_STAT_ID_MU_NUM, host_num_mems - 1);
+	priv->stats = kvmalloc_array(stats_size, sizeof(struct nfp_fl_stats),
+				     GFP_KERNEL);
 	if (!priv->stats)
 		goto err_free_ring_buf;
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 67e576fe7fc0..450d7296fd57 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -56,11 +56,10 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
 
 static int
-nfp_flower_xmit_flow(struct net_device *netdev,
-		     struct nfp_fl_payload *nfp_flow, u8 mtype)
+nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
+		     u8 mtype)
 {
 	u32 meta_len, key_len, mask_len, act_len, tot_len;
-	struct nfp_repr *priv = netdev_priv(netdev);
 	struct sk_buff *skb;
 	unsigned char *msg;
 
@@ -78,7 +77,7 @@ nfp_flower_xmit_flow(struct net_device *netdev,
 	nfp_flow->meta.mask_len >>= NFP_FL_LW_SIZ;
 	nfp_flow->meta.act_len >>= NFP_FL_LW_SIZ;
 
-	skb = nfp_flower_cmsg_alloc(priv->app, tot_len, mtype, GFP_KERNEL);
+	skb = nfp_flower_cmsg_alloc(app, tot_len, mtype, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -96,30 +95,29 @@ nfp_flower_xmit_flow(struct net_device *netdev,
 	nfp_flow->meta.mask_len <<= NFP_FL_LW_SIZ;
 	nfp_flow->meta.act_len <<= NFP_FL_LW_SIZ;
 
-	nfp_ctrl_tx(priv->app->ctrl, skb);
+	nfp_ctrl_tx(app->ctrl, skb);
 
 	return 0;
 }
 
 static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f)
 {
-	return dissector_uses_key(f->dissector,
-				  FLOW_DISSECTOR_KEY_IPV4_ADDRS) ||
-		dissector_uses_key(f->dissector,
-				   FLOW_DISSECTOR_KEY_IPV6_ADDRS) ||
-		dissector_uses_key(f->dissector,
-				   FLOW_DISSECTOR_KEY_PORTS) ||
-		dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ICMP);
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+
+	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) ||
+	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
 }
 
 static int
-nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
+nfp_flower_calc_opt_layer(struct flow_match_enc_opts *enc_opts,
 			  u32 *key_layer_two, int *key_size)
 {
-	if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY)
+	if (enc_opts->key->len > NFP_FL_MAX_GENEVE_OPT_KEY)
 		return -EOPNOTSUPP;
 
-	if (enc_opts->len > 0) {
+	if (enc_opts->key->len > 0) {
 		*key_layer_two |= NFP_FLOWER_LAYER2_GENEVE_OP;
 		*key_size += sizeof(struct nfp_flower_geneve_options);
 	}
@@ -129,25 +127,26 @@ nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
 
 static int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
+				struct net_device *netdev,
 				struct nfp_fl_key_ls *ret_key_ls,
 				struct tc_cls_flower_offload *flow,
-				bool egress,
 				enum nfp_flower_tun_type *tun_type)
 {
-	struct flow_dissector_key_basic *mask_basic = NULL;
-	struct flow_dissector_key_basic *key_basic = NULL;
+	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_dissector *dissector = rule->match.dissector;
+	struct flow_match_basic basic = { NULL, NULL};
 	struct nfp_flower_priv *priv = app->priv;
 	u32 key_layer_two;
 	u8 key_layer;
 	int key_size;
 	int err;
 
-	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
+	if (dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
 		return -EOPNOTSUPP;
 
 	/* If any tun dissector is used then the required set must be used. */
-	if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR &&
-	    (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
+	if (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR &&
+	    (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
 	    != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R)
 		return -EOPNOTSUPP;
 
@@ -156,78 +155,52 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 	key_size = sizeof(struct nfp_flower_meta_tci) +
 		   sizeof(struct nfp_flower_in_port);
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS) ||
-	    dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS) ||
+	    flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) {
 		key_layer |= NFP_FLOWER_LAYER_MAC;
 		key_size += sizeof(struct nfp_flower_mac_mpls);
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-		struct flow_dissector_key_vlan *flow_vlan;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) {
+		struct flow_match_vlan vlan;
 
-		flow_vlan = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_VLAN,
-						      flow->mask);
+		flow_rule_match_vlan(rule, &vlan);
 		if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) &&
-		    flow_vlan->vlan_priority)
+		    vlan.key->vlan_priority)
 			return -EOPNOTSUPP;
 	}
 
-	if (dissector_uses_key(flow->dissector,
-			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
-		struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL;
-		struct flow_dissector_key_ports *mask_enc_ports = NULL;
-		struct flow_dissector_key_enc_opts *enc_op = NULL;
-		struct flow_dissector_key_ports *enc_ports = NULL;
-		struct flow_dissector_key_control *mask_enc_ctl =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-						  flow->mask);
-		struct flow_dissector_key_control *enc_ctl =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_CONTROL,
-						  flow->key);
-		if (!egress)
-			return -EOPNOTSUPP;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
+		struct flow_match_enc_opts enc_op = { NULL, NULL };
+		struct flow_match_ipv4_addrs ipv4_addrs;
+		struct flow_match_control enc_ctl;
+		struct flow_match_ports enc_ports;
+
+		flow_rule_match_enc_control(rule, &enc_ctl);
 
-		if (mask_enc_ctl->addr_type != 0xffff ||
-		    enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS)
+		if (enc_ctl.mask->addr_type != 0xffff ||
+		    enc_ctl.key->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS)
 			return -EOPNOTSUPP;
 
 		/* These fields are already verified as used. */
-		mask_ipv4 =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS,
-						  flow->mask);
-		if (mask_ipv4->dst != cpu_to_be32(~0))
+		flow_rule_match_enc_ipv4_addrs(rule, &ipv4_addrs);
+		if (ipv4_addrs.mask->dst != cpu_to_be32(~0))
 			return -EOPNOTSUPP;
 
-		mask_enc_ports =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  flow->mask);
-		enc_ports =
-			skb_flow_dissector_target(flow->dissector,
-						  FLOW_DISSECTOR_KEY_ENC_PORTS,
-						  flow->key);
-
-		if (mask_enc_ports->dst != cpu_to_be16(~0))
+		flow_rule_match_enc_ports(rule, &enc_ports);
+		if (enc_ports.mask->dst != cpu_to_be16(~0))
 			return -EOPNOTSUPP;
 
-		if (dissector_uses_key(flow->dissector,
-				       FLOW_DISSECTOR_KEY_ENC_OPTS)) {
-			enc_op = skb_flow_dissector_target(flow->dissector,
-							   FLOW_DISSECTOR_KEY_ENC_OPTS,
-							   flow->key);
-		}
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS))
+			flow_rule_match_enc_opts(rule, &enc_op);
 
-		switch (enc_ports->dst) {
+		switch (enc_ports.key->dst) {
 		case htons(NFP_FL_VXLAN_PORT):
 			*tun_type = NFP_FL_TUNNEL_VXLAN;
 			key_layer |= NFP_FLOWER_LAYER_VXLAN;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
 
-			if (enc_op)
+			if (enc_op.key)
 				return -EOPNOTSUPP;
 			break;
 		case htons(NFP_FL_GENEVE_PORT):
@@ -239,11 +212,11 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			key_layer_two |= NFP_FLOWER_LAYER2_GENEVE;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
 
-			if (!enc_op)
+			if (!enc_op.key)
 				break;
 			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))
 				return -EOPNOTSUPP;
-			err = nfp_flower_calc_opt_layer(enc_op, &key_layer_two,
+			err = nfp_flower_calc_opt_layer(&enc_op, &key_layer_two,
 							&key_size);
 			if (err)
 				return err;
@@ -251,24 +224,18 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		default:
 			return -EOPNOTSUPP;
 		}
-	} else if (egress) {
-		/* Reject non tunnel matches offloaded to egress repr. */
-		return -EOPNOTSUPP;
-	}
-
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		mask_basic = skb_flow_dissector_target(flow->dissector,
-						       FLOW_DISSECTOR_KEY_BASIC,
-						       flow->mask);
 
-		key_basic = skb_flow_dissector_target(flow->dissector,
-						      FLOW_DISSECTOR_KEY_BASIC,
-						      flow->key);
+		/* Ensure the ingress netdev matches the expected tun type. */
+		if (!nfp_fl_netdev_is_tunnel_type(netdev, *tun_type))
+			return -EOPNOTSUPP;
 	}
 
-	if (mask_basic && mask_basic->n_proto) {
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC))
+		flow_rule_match_basic(rule, &basic);
+
+	if (basic.mask && basic.mask->n_proto) {
 		/* Ethernet type is present in the key. */
-		switch (key_basic->n_proto) {
+		switch (basic.key->n_proto) {
 		case cpu_to_be16(ETH_P_IP):
 			key_layer |= NFP_FLOWER_LAYER_IPV4;
 			key_size += sizeof(struct nfp_flower_ipv4);
@@ -307,9 +274,9 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		}
 	}
 
-	if (mask_basic && mask_basic->ip_proto) {
+	if (basic.mask && basic.mask->ip_proto) {
 		/* Ethernet type is present in the key. */
-		switch (key_basic->ip_proto) {
+		switch (basic.key->ip_proto) {
 		case IPPROTO_TCP:
 		case IPPROTO_UDP:
 		case IPPROTO_SCTP:
@@ -326,14 +293,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		}
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) {
-		struct flow_dissector_key_tcp *tcp;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) {
+		struct flow_match_tcp tcp;
 		u32 tcp_flags;
 
-		tcp = skb_flow_dissector_target(flow->dissector,
-						FLOW_DISSECTOR_KEY_TCP,
-						flow->key);
-		tcp_flags = be16_to_cpu(tcp->flags);
+		flow_rule_match_tcp(rule, &tcp);
+		tcp_flags = be16_to_cpu(tcp.key->flags);
 
 		if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS)
 			return -EOPNOTSUPP;
@@ -349,12 +314,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		 * space, thus we need to ensure we include a IPv4/IPv6 key
 		 * layer if we have not done so already.
 		 */
-		if (!key_basic)
+		if (!basic.key)
 			return -EOPNOTSUPP;
 
 		if (!(key_layer & NFP_FLOWER_LAYER_IPV4) &&
 		    !(key_layer & NFP_FLOWER_LAYER_IPV6)) {
-			switch (key_basic->n_proto) {
+			switch (basic.key->n_proto) {
 			case cpu_to_be16(ETH_P_IP):
 				key_layer |= NFP_FLOWER_LAYER_IPV4;
 				key_size += sizeof(struct nfp_flower_ipv4);
@@ -371,14 +336,11 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		}
 	}
 
-	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) {
-		struct flow_dissector_key_control *key_ctl;
-
-		key_ctl = skb_flow_dissector_target(flow->dissector,
-						    FLOW_DISSECTOR_KEY_CONTROL,
-						    flow->key);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control ctl;
 
-		if (key_ctl->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS)
+		flow_rule_match_control(rule, &ctl);
+		if (ctl.key->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS)
 			return -EOPNOTSUPP;
 	}
 
@@ -390,7 +352,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 }
 
 static struct nfp_fl_payload *
-nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress)
+nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer)
 {
 	struct nfp_fl_payload *flow_pay;
 
@@ -414,7 +376,6 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress)
 
 	flow_pay->nfp_tun_ipv4_addr = 0;
 	flow_pay->meta.flags = 0;
-	flow_pay->ingress_offload = !egress;
 
 	return flow_pay;
 
@@ -432,7 +393,6 @@ err_free_flow:
  * @app:	Pointer to the APP handle
  * @netdev:	netdev structure.
  * @flow:	TC flower classifier offload structure.
- * @egress:	NFP netdev is the egress.
  *
  * Adds a new flow to the repeated hash structure and action payload.
  *
@@ -440,46 +400,35 @@ err_free_flow:
  */
 static int
 nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow, bool egress)
+		       struct tc_cls_flower_offload *flow)
 {
 	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
-	struct nfp_port *port = nfp_port_from_netdev(netdev);
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *flow_pay;
 	struct nfp_fl_key_ls *key_layer;
-	struct net_device *ingr_dev;
+	struct nfp_port *port = NULL;
 	int err;
 
-	ingr_dev = egress ? NULL : netdev;
-	flow_pay = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
-					      NFP_FL_STATS_CTX_DONT_CARE);
-	if (flow_pay) {
-		/* Ignore as duplicate if it has been added by different cb. */
-		if (flow_pay->ingress_offload && egress)
-			return 0;
-		else
-			return -EOPNOTSUPP;
-	}
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_port_from_netdev(netdev);
 
 	key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL);
 	if (!key_layer)
 		return -ENOMEM;
 
-	err = nfp_flower_calculate_key_layers(app, key_layer, flow, egress,
+	err = nfp_flower_calculate_key_layers(app, netdev, key_layer, flow,
 					      &tun_type);
 	if (err)
 		goto err_free_key_ls;
 
-	flow_pay = nfp_flower_allocate_new(key_layer, egress);
+	flow_pay = nfp_flower_allocate_new(key_layer);
 	if (!flow_pay) {
 		err = -ENOMEM;
 		goto err_free_key_ls;
 	}
 
-	flow_pay->ingress_dev = egress ? NULL : netdev;
-
-	err = nfp_flower_compile_flow_match(flow, key_layer, netdev, flow_pay,
-					    tun_type);
+	err = nfp_flower_compile_flow_match(app, flow, key_layer, netdev,
+					    flow_pay, tun_type);
 	if (err)
 		goto err_destroy_flow;
 
@@ -487,8 +436,7 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (err)
 		goto err_destroy_flow;
 
-	err = nfp_compile_flow_metadata(app, flow, flow_pay,
-					flow_pay->ingress_dev);
+	err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev);
 	if (err)
 		goto err_destroy_flow;
 
@@ -498,12 +446,13 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
 	if (err)
 		goto err_release_metadata;
 
-	err = nfp_flower_xmit_flow(netdev, flow_pay,
+	err = nfp_flower_xmit_flow(app, flow_pay,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_ADD);
 	if (err)
 		goto err_remove_rhash;
 
-	port->tc_offload_cnt++;
+	if (port)
+		port->tc_offload_cnt++;
 
 	/* Deallocate flow payload when flower rule has been destroyed. */
 	kfree(key_layer);
@@ -531,7 +480,6 @@ err_free_key_ls:
  * @app:	Pointer to the APP handle
  * @netdev:	netdev structure.
  * @flow:	TC flower classifier offload structure
- * @egress:	Netdev is the egress dev.
  *
  * Removes a flow from the repeated hash structure and clears the
  * action payload.
@@ -540,19 +488,19 @@ err_free_key_ls:
  */
 static int
 nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow, bool egress)
+		       struct tc_cls_flower_offload *flow)
 {
-	struct nfp_port *port = nfp_port_from_netdev(netdev);
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *nfp_flow;
-	struct net_device *ingr_dev;
+	struct nfp_port *port = NULL;
 	int err;
 
-	ingr_dev = egress ? NULL : netdev;
-	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
-					      NFP_FL_STATS_CTX_DONT_CARE);
+	if (nfp_netdev_is_nfp_repr(netdev))
+		port = nfp_port_from_netdev(netdev);
+
+	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (!nfp_flow)
-		return egress ? 0 : -ENOENT;
+		return -ENOENT;
 
 	err = nfp_modify_flow_metadata(app, nfp_flow);
 	if (err)
@@ -561,13 +509,14 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
 	if (nfp_flow->nfp_tun_ipv4_addr)
 		nfp_tunnel_del_ipv4_off(app, nfp_flow->nfp_tun_ipv4_addr);
 
-	err = nfp_flower_xmit_flow(netdev, nfp_flow,
+	err = nfp_flower_xmit_flow(app, nfp_flow,
 				   NFP_FLOWER_CMSG_TYPE_FLOW_DEL);
 	if (err)
 		goto err_free_flow;
 
 err_free_flow:
-	port->tc_offload_cnt--;
+	if (port)
+		port->tc_offload_cnt--;
 	kfree(nfp_flow->action_data);
 	kfree(nfp_flow->mask_data);
 	kfree(nfp_flow->unmasked_data);
@@ -583,7 +532,6 @@ err_free_flow:
  * @app:	Pointer to the APP handle
  * @netdev:	Netdev structure.
  * @flow:	TC flower classifier offload structure
- * @egress:	Netdev is the egress dev.
  *
  * Populates a flow statistics structure which which corresponds to a
  * specific flow.
@@ -592,28 +540,21 @@ err_free_flow:
  */
 static int
 nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
-		     struct tc_cls_flower_offload *flow, bool egress)
+		     struct tc_cls_flower_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_payload *nfp_flow;
-	struct net_device *ingr_dev;
 	u32 ctx_id;
 
-	ingr_dev = egress ? NULL : netdev;
-	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev,
-					      NFP_FL_STATS_CTX_DONT_CARE);
+	nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, netdev);
 	if (!nfp_flow)
 		return -EINVAL;
 
-	if (nfp_flow->ingress_offload && egress)
-		return 0;
-
 	ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id);
 
 	spin_lock_bh(&priv->stats_lock);
-	tcf_exts_stats_update(flow->exts, priv->stats[ctx_id].bytes,
-			      priv->stats[ctx_id].pkts,
-			      priv->stats[ctx_id].used);
+	flow_stats_update(&flow->stats, priv->stats[ctx_id].bytes,
+			  priv->stats[ctx_id].pkts, priv->stats[ctx_id].used);
 
 	priv->stats[ctx_id].pkts = 0;
 	priv->stats[ctx_id].bytes = 0;
@@ -624,35 +565,18 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 
 static int
 nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
-			struct tc_cls_flower_offload *flower, bool egress)
+			struct tc_cls_flower_offload *flower)
 {
 	if (!eth_proto_is_802_3(flower->common.protocol))
 		return -EOPNOTSUPP;
 
 	switch (flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		return nfp_flower_add_offload(app, netdev, flower, egress);
+		return nfp_flower_add_offload(app, netdev, flower);
 	case TC_CLSFLOWER_DESTROY:
-		return nfp_flower_del_offload(app, netdev, flower, egress);
+		return nfp_flower_del_offload(app, netdev, flower);
 	case TC_CLSFLOWER_STATS:
-		return nfp_flower_get_stats(app, netdev, flower, egress);
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
-int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
-				  void *cb_priv)
-{
-	struct nfp_repr *repr = cb_priv;
-
-	if (!tc_cls_can_offload_and_chain0(repr->netdev, type_data))
-		return -EOPNOTSUPP;
-
-	switch (type) {
-	case TC_SETUP_CLSFLOWER:
-		return nfp_flower_repr_offload(repr->app, repr->netdev,
-					       type_data, true);
+		return nfp_flower_get_stats(app, netdev, flower);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -669,7 +593,7 @@ static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_CLSFLOWER:
 		return nfp_flower_repr_offload(repr->app, repr->netdev,
-					       type_data, false);
+					       type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -708,3 +632,130 @@ int nfp_flower_setup_tc(struct nfp_app *app, struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 }
+
+struct nfp_flower_indr_block_cb_priv {
+	struct net_device *netdev;
+	struct nfp_app *app;
+	struct list_head list;
+};
+
+static struct nfp_flower_indr_block_cb_priv *
+nfp_flower_indr_block_cb_priv_lookup(struct nfp_app *app,
+				     struct net_device *netdev)
+{
+	struct nfp_flower_indr_block_cb_priv *cb_priv;
+	struct nfp_flower_priv *priv = app->priv;
+
+	/* All callback list access should be protected by RTNL. */
+	ASSERT_RTNL();
+
+	list_for_each_entry(cb_priv, &priv->indr_block_cb_priv, list)
+		if (cb_priv->netdev == netdev)
+			return cb_priv;
+
+	return NULL;
+}
+
+static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
+{
+	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
+	struct tc_cls_flower_offload *flower = type_data;
+
+	if (flower->common.chain_index)
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		return nfp_flower_repr_offload(priv->app, priv->netdev,
+					       type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int
+nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
+			       struct tc_block_offload *f)
+{
+	struct nfp_flower_indr_block_cb_priv *cb_priv;
+	struct nfp_flower_priv *priv = app->priv;
+	int err;
+
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		cb_priv = kmalloc(sizeof(*cb_priv), GFP_KERNEL);
+		if (!cb_priv)
+			return -ENOMEM;
+
+		cb_priv->netdev = netdev;
+		cb_priv->app = app;
+		list_add(&cb_priv->list, &priv->indr_block_cb_priv);
+
+		err = tcf_block_cb_register(f->block,
+					    nfp_flower_setup_indr_block_cb,
+					    cb_priv, cb_priv, f->extack);
+		if (err) {
+			list_del(&cb_priv->list);
+			kfree(cb_priv);
+		}
+
+		return err;
+	case TC_BLOCK_UNBIND:
+		cb_priv = nfp_flower_indr_block_cb_priv_lookup(app, netdev);
+		if (!cb_priv)
+			return -ENOENT;
+
+		tcf_block_cb_unregister(f->block,
+					nfp_flower_setup_indr_block_cb,
+					cb_priv);
+		list_del(&cb_priv->list);
+		kfree(cb_priv);
+
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return 0;
+}
+
+static int
+nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+			    enum tc_setup_type type, void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_BLOCK:
+		return nfp_flower_setup_indr_tc_block(netdev, cb_priv,
+						      type_data);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
+				       struct net_device *netdev,
+				       unsigned long event)
+{
+	int err;
+
+	if (!nfp_fl_is_netdev_to_offload(netdev))
+		return NOTIFY_OK;
+
+	if (event == NETDEV_REGISTER) {
+		err = __tc_indr_block_cb_register(netdev, app,
+						  nfp_flower_indr_setup_tc_cb,
+						  app);
+		if (err)
+			nfp_flower_cmsg_warn(app,
+					     "Indirect block reg failed - %s\n",
+					     netdev->name);
+	} else if (event == NETDEV_UNREGISTER) {
+		__tc_indr_block_cb_unregister(netdev,
+					      nfp_flower_indr_setup_tc_cb, app);
+	}
+
+	return NOTIFY_OK;
+}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
index 8e5bec04d1f9..4d78be4ec4e9 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c
@@ -4,7 +4,6 @@
 #include <linux/etherdevice.h>
 #include <linux/inetdevice.h>
 #include <net/netevent.h>
-#include <net/vxlan.h>
 #include <linux/idr.h>
 #include <net/dst_metadata.h>
 #include <net/arp.h>
@@ -99,47 +98,51 @@ struct nfp_ipv4_addr_entry {
 	struct list_head list;
 };
 
-/**
- * struct nfp_tun_mac_addr - configure MAC address of tunnel EP on NFP
- * @reserved:	reserved for future use
- * @count:	number of MAC addresses in the message
- * @addresses.index:	index of MAC address in the lookup table
- * @addresses.addr:	interface MAC address
- * @addresses:	series of MACs to offload
- */
-struct nfp_tun_mac_addr {
-	__be16 reserved;
-	__be16 count;
-	struct index_mac_addr {
-		__be16 index;
-		u8 addr[ETH_ALEN];
-	} addresses[];
-};
+#define NFP_TUN_MAC_OFFLOAD_DEL_FLAG	0x2
 
 /**
- * struct nfp_tun_mac_offload_entry - list of MACs to offload
- * @index:	index of MAC address for offloading
+ * struct nfp_tun_mac_addr_offload - configure MAC address of tunnel EP on NFP
+ * @flags:	MAC address offload options
+ * @count:	number of MAC addresses in the message (should be 1)
+ * @index:	index of MAC address in the lookup table
  * @addr:	interface MAC address
- * @list:	list pointer
  */
-struct nfp_tun_mac_offload_entry {
+struct nfp_tun_mac_addr_offload {
+	__be16 flags;
+	__be16 count;
 	__be16 index;
 	u8 addr[ETH_ALEN];
-	struct list_head list;
+};
+
+enum nfp_flower_mac_offload_cmd {
+	NFP_TUNNEL_MAC_OFFLOAD_ADD =		0,
+	NFP_TUNNEL_MAC_OFFLOAD_DEL =		1,
+	NFP_TUNNEL_MAC_OFFLOAD_MOD =		2,
 };
 
 #define NFP_MAX_MAC_INDEX       0xff
 
 /**
- * struct nfp_tun_mac_non_nfp_idx - converts non NFP netdev ifindex to 8-bit id
- * @ifindex:	netdev ifindex of the device
- * @index:	index of netdevs mac on NFP
- * @list:	list pointer
+ * struct nfp_tun_offloaded_mac - hashtable entry for an offloaded MAC
+ * @ht_node:	Hashtable entry
+ * @addr:	Offloaded MAC address
+ * @index:	Offloaded index for given MAC address
+ * @ref_count:	Number of devs using this MAC address
+ * @repr_list:	List of reprs sharing this MAC address
  */
-struct nfp_tun_mac_non_nfp_idx {
-	int ifindex;
-	u8 index;
-	struct list_head list;
+struct nfp_tun_offloaded_mac {
+	struct rhash_head ht_node;
+	u8 addr[ETH_ALEN];
+	u16 index;
+	int ref_count;
+	struct list_head repr_list;
+};
+
+static const struct rhashtable_params offloaded_macs_params = {
+	.key_offset	= offsetof(struct nfp_tun_offloaded_mac, addr),
+	.head_offset	= offsetof(struct nfp_tun_offloaded_mac, ht_node),
+	.key_len	= ETH_ALEN,
+	.automatic_shrinking	= true,
 };
 
 void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
@@ -182,18 +185,6 @@ void nfp_tunnel_keep_alive(struct nfp_app *app, struct sk_buff *skb)
 	}
 }
 
-static bool nfp_tun_is_netdev_to_offload(struct net_device *netdev)
-{
-	if (!netdev->rtnl_link_ops)
-		return false;
-	if (!strcmp(netdev->rtnl_link_ops->kind, "openvswitch"))
-		return true;
-	if (netif_is_vxlan(netdev))
-		return true;
-
-	return false;
-}
-
 static int
 nfp_flower_xmit_tun_conf(struct nfp_app *app, u8 mtype, u16 plen, void *pdata,
 			 gfp_t flag)
@@ -218,15 +209,15 @@ static bool nfp_tun_has_route(struct nfp_app *app, __be32 ipv4_addr)
 	struct nfp_ipv4_route_entry *entry;
 	struct list_head *ptr, *storage;
 
-	spin_lock_bh(&priv->nfp_neigh_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	spin_lock_bh(&priv->tun.neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
 		if (entry->ipv4_addr == ipv4_addr) {
-			spin_unlock_bh(&priv->nfp_neigh_off_lock);
+			spin_unlock_bh(&priv->tun.neigh_off_lock);
 			return true;
 		}
 	}
-	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	spin_unlock_bh(&priv->tun.neigh_off_lock);
 	return false;
 }
 
@@ -236,24 +227,24 @@ static void nfp_tun_add_route_to_cache(struct nfp_app *app, __be32 ipv4_addr)
 	struct nfp_ipv4_route_entry *entry;
 	struct list_head *ptr, *storage;
 
-	spin_lock_bh(&priv->nfp_neigh_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	spin_lock_bh(&priv->tun.neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
 		if (entry->ipv4_addr == ipv4_addr) {
-			spin_unlock_bh(&priv->nfp_neigh_off_lock);
+			spin_unlock_bh(&priv->tun.neigh_off_lock);
 			return;
 		}
 	}
 	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
 	if (!entry) {
-		spin_unlock_bh(&priv->nfp_neigh_off_lock);
+		spin_unlock_bh(&priv->tun.neigh_off_lock);
 		nfp_flower_cmsg_warn(app, "Mem error when storing new route.\n");
 		return;
 	}
 
 	entry->ipv4_addr = ipv4_addr;
-	list_add_tail(&entry->list, &priv->nfp_neigh_off_list);
-	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	list_add_tail(&entry->list, &priv->tun.neigh_off_list);
+	spin_unlock_bh(&priv->tun.neigh_off_lock);
 }
 
 static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
@@ -262,8 +253,8 @@ static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
 	struct nfp_ipv4_route_entry *entry;
 	struct list_head *ptr, *storage;
 
-	spin_lock_bh(&priv->nfp_neigh_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	spin_lock_bh(&priv->tun.neigh_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_route_entry, list);
 		if (entry->ipv4_addr == ipv4_addr) {
 			list_del(&entry->list);
@@ -271,7 +262,7 @@ static void nfp_tun_del_route_from_cache(struct nfp_app *app, __be32 ipv4_addr)
 			break;
 		}
 	}
-	spin_unlock_bh(&priv->nfp_neigh_off_lock);
+	spin_unlock_bh(&priv->tun.neigh_off_lock);
 }
 
 static void
@@ -339,7 +330,7 @@ nfp_tun_neigh_event_handler(struct notifier_block *nb, unsigned long event,
 	if (!nfp_netdev_is_nfp_repr(n->dev))
 		return NOTIFY_DONE;
 
-	app_priv = container_of(nb, struct nfp_flower_priv, nfp_tun_neigh_nb);
+	app_priv = container_of(nb, struct nfp_flower_priv, tun.neigh_nb);
 	app = app_priv->app;
 
 	/* Only concerned with changes to routes already added to NFP. */
@@ -414,11 +405,11 @@ static void nfp_tun_write_ipv4_list(struct nfp_app *app)
 	int count;
 
 	memset(&payload, 0, sizeof(struct nfp_tun_ipv4_addr));
-	mutex_lock(&priv->nfp_ipv4_off_lock);
+	mutex_lock(&priv->tun.ipv4_off_lock);
 	count = 0;
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		if (count >= NFP_FL_IPV4_ADDRS_MAX) {
-			mutex_unlock(&priv->nfp_ipv4_off_lock);
+			mutex_unlock(&priv->tun.ipv4_off_lock);
 			nfp_flower_cmsg_warn(app, "IPv4 offload exceeds limit.\n");
 			return;
 		}
@@ -426,7 +417,7 @@ static void nfp_tun_write_ipv4_list(struct nfp_app *app)
 		payload.ipv4_addr[count++] = entry->ipv4_addr;
 	}
 	payload.count = cpu_to_be32(count);
-	mutex_unlock(&priv->nfp_ipv4_off_lock);
+	mutex_unlock(&priv->tun.ipv4_off_lock);
 
 	nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_IPS,
 				 sizeof(struct nfp_tun_ipv4_addr),
@@ -439,26 +430,26 @@ void nfp_tunnel_add_ipv4_off(struct nfp_app *app, __be32 ipv4)
 	struct nfp_ipv4_addr_entry *entry;
 	struct list_head *ptr, *storage;
 
-	mutex_lock(&priv->nfp_ipv4_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	mutex_lock(&priv->tun.ipv4_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
 		if (entry->ipv4_addr == ipv4) {
 			entry->ref_count++;
-			mutex_unlock(&priv->nfp_ipv4_off_lock);
+			mutex_unlock(&priv->tun.ipv4_off_lock);
 			return;
 		}
 	}
 
 	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
-		mutex_unlock(&priv->nfp_ipv4_off_lock);
+		mutex_unlock(&priv->tun.ipv4_off_lock);
 		nfp_flower_cmsg_warn(app, "Mem error when offloading IP address.\n");
 		return;
 	}
 	entry->ipv4_addr = ipv4;
 	entry->ref_count = 1;
-	list_add_tail(&entry->list, &priv->nfp_ipv4_off_list);
-	mutex_unlock(&priv->nfp_ipv4_off_lock);
+	list_add_tail(&entry->list, &priv->tun.ipv4_off_list);
+	mutex_unlock(&priv->tun.ipv4_off_lock);
 
 	nfp_tun_write_ipv4_list(app);
 }
@@ -469,8 +460,8 @@ void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4)
 	struct nfp_ipv4_addr_entry *entry;
 	struct list_head *ptr, *storage;
 
-	mutex_lock(&priv->nfp_ipv4_off_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	mutex_lock(&priv->tun.ipv4_off_lock);
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
 		if (entry->ipv4_addr == ipv4) {
 			entry->ref_count--;
@@ -481,204 +472,357 @@ void nfp_tunnel_del_ipv4_off(struct nfp_app *app, __be32 ipv4)
 			break;
 		}
 	}
-	mutex_unlock(&priv->nfp_ipv4_off_lock);
+	mutex_unlock(&priv->tun.ipv4_off_lock);
 
 	nfp_tun_write_ipv4_list(app);
 }
 
-void nfp_tunnel_write_macs(struct nfp_app *app)
+static int
+__nfp_tunnel_offload_mac(struct nfp_app *app, u8 *mac, u16 idx, bool del)
 {
-	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_offload_entry *entry;
-	struct nfp_tun_mac_addr *payload;
-	struct list_head *ptr, *storage;
-	int mac_count, err, pay_size;
+	struct nfp_tun_mac_addr_offload payload;
 
-	mutex_lock(&priv->nfp_mac_off_lock);
-	if (!priv->nfp_mac_off_count) {
-		mutex_unlock(&priv->nfp_mac_off_lock);
-		return;
-	}
+	memset(&payload, 0, sizeof(payload));
 
-	pay_size = sizeof(struct nfp_tun_mac_addr) +
-		   sizeof(struct index_mac_addr) * priv->nfp_mac_off_count;
+	if (del)
+		payload.flags = cpu_to_be16(NFP_TUN_MAC_OFFLOAD_DEL_FLAG);
 
-	payload = kzalloc(pay_size, GFP_KERNEL);
-	if (!payload) {
-		mutex_unlock(&priv->nfp_mac_off_lock);
-		return;
-	}
+	/* FW supports multiple MACs per cmsg but restrict to single. */
+	payload.count = cpu_to_be16(1);
+	payload.index = cpu_to_be16(idx);
+	ether_addr_copy(payload.addr, mac);
 
-	payload->count = cpu_to_be16(priv->nfp_mac_off_count);
+	return nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC,
+					sizeof(struct nfp_tun_mac_addr_offload),
+					&payload, GFP_KERNEL);
+}
 
-	mac_count = 0;
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
-				   list);
-		payload->addresses[mac_count].index = entry->index;
-		ether_addr_copy(payload->addresses[mac_count].addr,
-				entry->addr);
-		mac_count++;
-	}
+static bool nfp_tunnel_port_is_phy_repr(int port)
+{
+	if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
+	    NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT)
+		return true;
 
-	err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_TUN_MAC,
-				       pay_size, payload, GFP_KERNEL);
+	return false;
+}
 
-	kfree(payload);
+static u16 nfp_tunnel_get_mac_idx_from_phy_port_id(int port)
+{
+	return port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT;
+}
 
-	if (err) {
-		mutex_unlock(&priv->nfp_mac_off_lock);
-		/* Write failed so retain list for future retry. */
-		return;
-	}
+static u16 nfp_tunnel_get_global_mac_idx_from_ida(int id)
+{
+	return id << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+}
+
+static int nfp_tunnel_get_ida_from_global_mac_idx(u16 nfp_mac_idx)
+{
+	return nfp_mac_idx >> 8;
+}
+
+static bool nfp_tunnel_is_mac_idx_global(u16 nfp_mac_idx)
+{
+	return (nfp_mac_idx & 0xff) == NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+}
+
+static struct nfp_tun_offloaded_mac *
+nfp_tunnel_lookup_offloaded_macs(struct nfp_app *app, u8 *mac)
+{
+	struct nfp_flower_priv *priv = app->priv;
+
+	return rhashtable_lookup_fast(&priv->tun.offloaded_macs, mac,
+				      offloaded_macs_params);
+}
+
+static void
+nfp_tunnel_offloaded_macs_inc_ref_and_link(struct nfp_tun_offloaded_mac *entry,
+					   struct net_device *netdev, bool mod)
+{
+	if (nfp_netdev_is_nfp_repr(netdev)) {
+		struct nfp_flower_repr_priv *repr_priv;
+		struct nfp_repr *repr;
+
+		repr = netdev_priv(netdev);
+		repr_priv = repr->app_priv;
 
-	/* If list was successfully offloaded, flush it. */
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
-				   list);
-		list_del(&entry->list);
-		kfree(entry);
+		/* If modifing MAC, remove repr from old list first. */
+		if (mod)
+			list_del(&repr_priv->mac_list);
+
+		list_add_tail(&repr_priv->mac_list, &entry->repr_list);
 	}
 
-	priv->nfp_mac_off_count = 0;
-	mutex_unlock(&priv->nfp_mac_off_lock);
+	entry->ref_count++;
 }
 
-static int nfp_tun_get_mac_idx(struct nfp_app *app, int ifindex)
+static int
+nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev,
+			  int port, bool mod)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_non_nfp_idx *entry;
-	struct list_head *ptr, *storage;
-	int idx;
-
-	mutex_lock(&priv->nfp_mac_index_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
-		if (entry->ifindex == ifindex) {
-			idx = entry->index;
-			mutex_unlock(&priv->nfp_mac_index_lock);
-			return idx;
-		}
+	int ida_idx = NFP_MAX_MAC_INDEX, err;
+	struct nfp_tun_offloaded_mac *entry;
+	u16 nfp_mac_idx = 0;
+
+	entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr);
+	if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) {
+		nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod);
+		return 0;
 	}
 
-	idx = ida_simple_get(&priv->nfp_mac_off_ids, 0,
-			     NFP_MAX_MAC_INDEX, GFP_KERNEL);
-	if (idx < 0) {
-		mutex_unlock(&priv->nfp_mac_index_lock);
-		return idx;
+	/* Assign a global index if non-repr or MAC address is now shared. */
+	if (entry || !port) {
+		ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0,
+					 NFP_MAX_MAC_INDEX, GFP_KERNEL);
+		if (ida_idx < 0)
+			return ida_idx;
+
+		nfp_mac_idx = nfp_tunnel_get_global_mac_idx_from_ida(ida_idx);
+	} else {
+		nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port);
 	}
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry) {
-		mutex_unlock(&priv->nfp_mac_index_lock);
-		return -ENOMEM;
+		entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+		if (!entry) {
+			err = -ENOMEM;
+			goto err_free_ida;
+		}
+
+		ether_addr_copy(entry->addr, netdev->dev_addr);
+		INIT_LIST_HEAD(&entry->repr_list);
+
+		if (rhashtable_insert_fast(&priv->tun.offloaded_macs,
+					   &entry->ht_node,
+					   offloaded_macs_params)) {
+			err = -ENOMEM;
+			goto err_free_entry;
+		}
+	}
+
+	err = __nfp_tunnel_offload_mac(app, netdev->dev_addr,
+				       nfp_mac_idx, false);
+	if (err) {
+		/* If not shared then free. */
+		if (!entry->ref_count)
+			goto err_remove_hash;
+		goto err_free_ida;
 	}
-	entry->ifindex = ifindex;
-	entry->index = idx;
-	list_add_tail(&entry->list, &priv->nfp_mac_index_list);
-	mutex_unlock(&priv->nfp_mac_index_lock);
 
-	return idx;
+	entry->index = nfp_mac_idx;
+	nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod);
+
+	return 0;
+
+err_remove_hash:
+	rhashtable_remove_fast(&priv->tun.offloaded_macs, &entry->ht_node,
+			       offloaded_macs_params);
+err_free_entry:
+	kfree(entry);
+err_free_ida:
+	if (ida_idx != NFP_MAX_MAC_INDEX)
+		ida_simple_remove(&priv->tun.mac_off_ids, ida_idx);
+
+	return err;
 }
 
-static void nfp_tun_del_mac_idx(struct nfp_app *app, int ifindex)
+static int
+nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev,
+			  u8 *mac, bool mod)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_non_nfp_idx *entry;
-	struct list_head *ptr, *storage;
+	struct nfp_flower_repr_priv *repr_priv;
+	struct nfp_tun_offloaded_mac *entry;
+	struct nfp_repr *repr;
+	int ida_idx;
+
+	entry = nfp_tunnel_lookup_offloaded_macs(app, mac);
+	if (!entry)
+		return 0;
+
+	entry->ref_count--;
+	/* If del is part of a mod then mac_list is still in use elsewheree. */
+	if (nfp_netdev_is_nfp_repr(netdev) && !mod) {
+		repr = netdev_priv(netdev);
+		repr_priv = repr->app_priv;
+		list_del(&repr_priv->mac_list);
+	}
 
-	mutex_lock(&priv->nfp_mac_index_lock);
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
-		entry = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx, list);
-		if (entry->ifindex == ifindex) {
-			ida_simple_remove(&priv->nfp_mac_off_ids,
-					  entry->index);
-			list_del(&entry->list);
-			kfree(entry);
-			break;
+	/* If MAC is now used by 1 repr set the offloaded MAC index to port. */
+	if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) {
+		u16 nfp_mac_idx;
+		int port, err;
+
+		repr_priv = list_first_entry(&entry->repr_list,
+					     struct nfp_flower_repr_priv,
+					     mac_list);
+		repr = repr_priv->nfp_repr;
+		port = nfp_repr_get_port_id(repr->netdev);
+		nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port);
+		err = __nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, false);
+		if (err) {
+			nfp_flower_cmsg_warn(app, "MAC offload index revert failed on %s.\n",
+					     netdev_name(netdev));
+			return 0;
 		}
+
+		ida_idx = nfp_tunnel_get_ida_from_global_mac_idx(entry->index);
+		ida_simple_remove(&priv->tun.mac_off_ids, ida_idx);
+		entry->index = nfp_mac_idx;
+		return 0;
 	}
-	mutex_unlock(&priv->nfp_mac_index_lock);
-}
 
-static void nfp_tun_add_to_mac_offload_list(struct net_device *netdev,
-					    struct nfp_app *app)
-{
-	struct nfp_flower_priv *priv = app->priv;
-	struct nfp_tun_mac_offload_entry *entry;
-	u16 nfp_mac_idx;
-	int port = 0;
+	if (entry->ref_count)
+		return 0;
 
-	/* Check if MAC should be offloaded. */
-	if (!is_valid_ether_addr(netdev->dev_addr))
-		return;
+	WARN_ON_ONCE(rhashtable_remove_fast(&priv->tun.offloaded_macs,
+					    &entry->ht_node,
+					    offloaded_macs_params));
+	/* If MAC has global ID then extract and free the ida entry. */
+	if (nfp_tunnel_is_mac_idx_global(entry->index)) {
+		ida_idx = nfp_tunnel_get_ida_from_global_mac_idx(entry->index);
+		ida_simple_remove(&priv->tun.mac_off_ids, ida_idx);
+	}
+
+	kfree(entry);
 
-	if (nfp_netdev_is_nfp_repr(netdev))
+	return __nfp_tunnel_offload_mac(app, mac, 0, true);
+}
+
+static int
+nfp_tunnel_offload_mac(struct nfp_app *app, struct net_device *netdev,
+		       enum nfp_flower_mac_offload_cmd cmd)
+{
+	struct nfp_flower_non_repr_priv *nr_priv = NULL;
+	bool non_repr = false, *mac_offloaded;
+	u8 *off_mac = NULL;
+	int err, port = 0;
+
+	if (nfp_netdev_is_nfp_repr(netdev)) {
+		struct nfp_flower_repr_priv *repr_priv;
+		struct nfp_repr *repr;
+
+		repr = netdev_priv(netdev);
+		if (repr->app != app)
+			return 0;
+
+		repr_priv = repr->app_priv;
+		mac_offloaded = &repr_priv->mac_offloaded;
+		off_mac = &repr_priv->offloaded_mac_addr[0];
 		port = nfp_repr_get_port_id(netdev);
-	else if (!nfp_tun_is_netdev_to_offload(netdev))
-		return;
+		if (!nfp_tunnel_port_is_phy_repr(port))
+			return 0;
+	} else if (nfp_fl_is_netdev_to_offload(netdev)) {
+		nr_priv = nfp_flower_non_repr_priv_get(app, netdev);
+		if (!nr_priv)
+			return -ENOMEM;
+
+		mac_offloaded = &nr_priv->mac_offloaded;
+		off_mac = &nr_priv->offloaded_mac_addr[0];
+		non_repr = true;
+	} else {
+		return 0;
+	}
 
-	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry) {
-		nfp_flower_cmsg_warn(app, "Mem fail when offloading MAC.\n");
-		return;
+	if (!is_valid_ether_addr(netdev->dev_addr)) {
+		err = -EINVAL;
+		goto err_put_non_repr_priv;
 	}
 
-	if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
-	    NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT) {
-		nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PHYS_PORT;
-	} else if (FIELD_GET(NFP_FLOWER_CMSG_PORT_TYPE, port) ==
-		   NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT) {
-		port = FIELD_GET(NFP_FLOWER_CMSG_PORT_VNIC, port);
-		nfp_mac_idx = port << 8 | NFP_FLOWER_CMSG_PORT_TYPE_PCIE_PORT;
-	} else {
-		/* Must assign our own unique 8-bit index. */
-		int idx = nfp_tun_get_mac_idx(app, netdev->ifindex);
+	if (cmd == NFP_TUNNEL_MAC_OFFLOAD_MOD && !*mac_offloaded)
+		cmd = NFP_TUNNEL_MAC_OFFLOAD_ADD;
 
-		if (idx < 0) {
-			nfp_flower_cmsg_warn(app, "Can't assign non-repr MAC index.\n");
-			kfree(entry);
-			return;
-		}
-		nfp_mac_idx = idx << 8 | NFP_FLOWER_CMSG_PORT_TYPE_OTHER_PORT;
+	switch (cmd) {
+	case NFP_TUNNEL_MAC_OFFLOAD_ADD:
+		err = nfp_tunnel_add_shared_mac(app, netdev, port, false);
+		if (err)
+			goto err_put_non_repr_priv;
+
+		if (non_repr)
+			__nfp_flower_non_repr_priv_get(nr_priv);
+
+		*mac_offloaded = true;
+		ether_addr_copy(off_mac, netdev->dev_addr);
+		break;
+	case NFP_TUNNEL_MAC_OFFLOAD_DEL:
+		/* Only attempt delete if add was successful. */
+		if (!*mac_offloaded)
+			break;
+
+		if (non_repr)
+			__nfp_flower_non_repr_priv_put(nr_priv);
+
+		*mac_offloaded = false;
+
+		err = nfp_tunnel_del_shared_mac(app, netdev, netdev->dev_addr,
+						false);
+		if (err)
+			goto err_put_non_repr_priv;
+
+		break;
+	case NFP_TUNNEL_MAC_OFFLOAD_MOD:
+		/* Ignore if changing to the same address. */
+		if (ether_addr_equal(netdev->dev_addr, off_mac))
+			break;
+
+		err = nfp_tunnel_add_shared_mac(app, netdev, port, true);
+		if (err)
+			goto err_put_non_repr_priv;
+
+		/* Delete the previous MAC address. */
+		err = nfp_tunnel_del_shared_mac(app, netdev, off_mac, true);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to remove offload of replaced MAC addr on %s.\n",
+					     netdev_name(netdev));
+
+		ether_addr_copy(off_mac, netdev->dev_addr);
+		break;
+	default:
+		err = -EINVAL;
+		goto err_put_non_repr_priv;
 	}
 
-	entry->index = cpu_to_be16(nfp_mac_idx);
-	ether_addr_copy(entry->addr, netdev->dev_addr);
+	if (non_repr)
+		__nfp_flower_non_repr_priv_put(nr_priv);
+
+	return 0;
 
-	mutex_lock(&priv->nfp_mac_off_lock);
-	priv->nfp_mac_off_count++;
-	list_add_tail(&entry->list, &priv->nfp_mac_off_list);
-	mutex_unlock(&priv->nfp_mac_off_lock);
+err_put_non_repr_priv:
+	if (non_repr)
+		__nfp_flower_non_repr_priv_put(nr_priv);
+
+	return err;
 }
 
-static int nfp_tun_mac_event_handler(struct notifier_block *nb,
-				     unsigned long event, void *ptr)
+int nfp_tunnel_mac_event_handler(struct nfp_app *app,
+				 struct net_device *netdev,
+				 unsigned long event, void *ptr)
 {
-	struct nfp_flower_priv *app_priv;
-	struct net_device *netdev;
-	struct nfp_app *app;
+	int err;
 
-	if (event == NETDEV_DOWN || event == NETDEV_UNREGISTER) {
-		app_priv = container_of(nb, struct nfp_flower_priv,
-					nfp_tun_mac_nb);
-		app = app_priv->app;
-		netdev = netdev_notifier_info_to_dev(ptr);
-
-		/* If non-nfp netdev then free its offload index. */
-		if (nfp_tun_is_netdev_to_offload(netdev))
-			nfp_tun_del_mac_idx(app, netdev->ifindex);
-	} else if (event == NETDEV_UP || event == NETDEV_CHANGEADDR ||
-		   event == NETDEV_REGISTER) {
-		app_priv = container_of(nb, struct nfp_flower_priv,
-					nfp_tun_mac_nb);
-		app = app_priv->app;
-		netdev = netdev_notifier_info_to_dev(ptr);
-
-		nfp_tun_add_to_mac_offload_list(netdev, app);
-
-		/* Force a list write to keep NFP up to date. */
-		nfp_tunnel_write_macs(app);
+	if (event == NETDEV_DOWN) {
+		err = nfp_tunnel_offload_mac(app, netdev,
+					     NFP_TUNNEL_MAC_OFFLOAD_DEL);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to delete offload MAC on %s.\n",
+					     netdev_name(netdev));
+	} else if (event == NETDEV_UP) {
+		err = nfp_tunnel_offload_mac(app, netdev,
+					     NFP_TUNNEL_MAC_OFFLOAD_ADD);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to offload MAC on %s.\n",
+					     netdev_name(netdev));
+	} else if (event == NETDEV_CHANGEADDR) {
+		/* Only offload addr change if netdev is already up. */
+		if (!(netdev->flags & IFF_UP))
+			return NOTIFY_OK;
+
+		err = nfp_tunnel_offload_mac(app, netdev,
+					     NFP_TUNNEL_MAC_OFFLOAD_MOD);
+		if (err)
+			nfp_flower_cmsg_warn(app, "Failed to offload MAC change on %s.\n",
+					     netdev_name(netdev));
 	}
 	return NOTIFY_OK;
 }
@@ -686,92 +830,62 @@ static int nfp_tun_mac_event_handler(struct notifier_block *nb,
 int nfp_tunnel_config_start(struct nfp_app *app)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct net_device *netdev;
 	int err;
 
-	/* Initialise priv data for MAC offloading. */
-	priv->nfp_mac_off_count = 0;
-	mutex_init(&priv->nfp_mac_off_lock);
-	INIT_LIST_HEAD(&priv->nfp_mac_off_list);
-	priv->nfp_tun_mac_nb.notifier_call = nfp_tun_mac_event_handler;
-	mutex_init(&priv->nfp_mac_index_lock);
-	INIT_LIST_HEAD(&priv->nfp_mac_index_list);
-	ida_init(&priv->nfp_mac_off_ids);
+	/* Initialise rhash for MAC offload tracking. */
+	err = rhashtable_init(&priv->tun.offloaded_macs,
+			      &offloaded_macs_params);
+	if (err)
+		return err;
+
+	ida_init(&priv->tun.mac_off_ids);
 
 	/* Initialise priv data for IPv4 offloading. */
-	mutex_init(&priv->nfp_ipv4_off_lock);
-	INIT_LIST_HEAD(&priv->nfp_ipv4_off_list);
+	mutex_init(&priv->tun.ipv4_off_lock);
+	INIT_LIST_HEAD(&priv->tun.ipv4_off_list);
 
 	/* Initialise priv data for neighbour offloading. */
-	spin_lock_init(&priv->nfp_neigh_off_lock);
-	INIT_LIST_HEAD(&priv->nfp_neigh_off_list);
-	priv->nfp_tun_neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
-
-	err = register_netdevice_notifier(&priv->nfp_tun_mac_nb);
-	if (err)
-		goto err_free_mac_ida;
-
-	err = register_netevent_notifier(&priv->nfp_tun_neigh_nb);
-	if (err)
-		goto err_unreg_mac_nb;
+	spin_lock_init(&priv->tun.neigh_off_lock);
+	INIT_LIST_HEAD(&priv->tun.neigh_off_list);
+	priv->tun.neigh_nb.notifier_call = nfp_tun_neigh_event_handler;
 
-	/* Parse netdevs already registered for MACs that need offloaded. */
-	rtnl_lock();
-	for_each_netdev(&init_net, netdev)
-		nfp_tun_add_to_mac_offload_list(netdev, app);
-	rtnl_unlock();
+	err = register_netevent_notifier(&priv->tun.neigh_nb);
+	if (err) {
+		rhashtable_free_and_destroy(&priv->tun.offloaded_macs,
+					    nfp_check_rhashtable_empty, NULL);
+		return err;
+	}
 
 	return 0;
-
-err_unreg_mac_nb:
-	unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
-err_free_mac_ida:
-	ida_destroy(&priv->nfp_mac_off_ids);
-	return err;
 }
 
 void nfp_tunnel_config_stop(struct nfp_app *app)
 {
-	struct nfp_tun_mac_offload_entry *mac_entry;
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_ipv4_route_entry *route_entry;
-	struct nfp_tun_mac_non_nfp_idx *mac_idx;
 	struct nfp_ipv4_addr_entry *ip_entry;
 	struct list_head *ptr, *storage;
 
-	unregister_netdevice_notifier(&priv->nfp_tun_mac_nb);
-	unregister_netevent_notifier(&priv->nfp_tun_neigh_nb);
+	unregister_netevent_notifier(&priv->tun.neigh_nb);
 
-	/* Free any memory that may be occupied by MAC list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_off_list) {
-		mac_entry = list_entry(ptr, struct nfp_tun_mac_offload_entry,
-				       list);
-		list_del(&mac_entry->list);
-		kfree(mac_entry);
-	}
-
-	/* Free any memory that may be occupied by MAC index list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_mac_index_list) {
-		mac_idx = list_entry(ptr, struct nfp_tun_mac_non_nfp_idx,
-				     list);
-		list_del(&mac_idx->list);
-		kfree(mac_idx);
-	}
-
-	ida_destroy(&priv->nfp_mac_off_ids);
+	ida_destroy(&priv->tun.mac_off_ids);
 
 	/* Free any memory that may be occupied by ipv4 list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_ipv4_off_list) {
+	list_for_each_safe(ptr, storage, &priv->tun.ipv4_off_list) {
 		ip_entry = list_entry(ptr, struct nfp_ipv4_addr_entry, list);
 		list_del(&ip_entry->list);
 		kfree(ip_entry);
 	}
 
 	/* Free any memory that may be occupied by the route list. */
-	list_for_each_safe(ptr, storage, &priv->nfp_neigh_off_list) {
+	list_for_each_safe(ptr, storage, &priv->tun.neigh_off_list) {
 		route_entry = list_entry(ptr, struct nfp_ipv4_route_entry,
 					 list);
 		list_del(&route_entry->list);
 		kfree(route_entry);
 	}
+
+	/* Destroy rhash. Entries should be cleaned on netdev notifier unreg. */
+	rhashtable_free_and_destroy(&priv->tun.offloaded_macs,
+				    nfp_check_rhashtable_empty, NULL);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index 68a0991aac22..3a973282b2bb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -131,11 +131,100 @@ nfp_app_reprs_set(struct nfp_app *app, enum nfp_repr_type type,
 	struct nfp_reprs *old;
 
 	old = nfp_reprs_get_locked(app, type);
+	rtnl_lock();
 	rcu_assign_pointer(app->reprs[type], reprs);
+	rtnl_unlock();
 
 	return old;
 }
 
+static void
+nfp_app_netdev_feat_change(struct nfp_app *app, struct net_device *netdev)
+{
+	struct nfp_net *nn;
+	unsigned int type;
+
+	if (!nfp_netdev_is_nfp_net(netdev))
+		return;
+	nn = netdev_priv(netdev);
+	if (nn->app != app)
+		return;
+
+	for (type = 0; type < __NFP_REPR_TYPE_MAX; type++) {
+		struct nfp_reprs *reprs;
+		unsigned int i;
+
+		reprs = rtnl_dereference(app->reprs[type]);
+		if (!reprs)
+			continue;
+
+		for (i = 0; i < reprs->num_reprs; i++) {
+			struct net_device *repr;
+
+			repr = rtnl_dereference(reprs->reprs[i]);
+			if (!repr)
+				continue;
+
+			nfp_repr_transfer_features(repr, netdev);
+		}
+	}
+}
+
+static int
+nfp_app_netdev_event(struct notifier_block *nb, unsigned long event, void *ptr)
+{
+	struct net_device *netdev;
+	struct nfp_app *app;
+
+	netdev = netdev_notifier_info_to_dev(ptr);
+	app = container_of(nb, struct nfp_app, netdev_nb);
+
+	/* Handle events common code is interested in */
+	switch (event) {
+	case NETDEV_FEAT_CHANGE:
+		nfp_app_netdev_feat_change(app, netdev);
+		break;
+	}
+
+	/* Call offload specific handlers */
+	if (app->type->netdev_event)
+		return app->type->netdev_event(app, netdev, event, ptr);
+	return NOTIFY_DONE;
+}
+
+int nfp_app_start(struct nfp_app *app, struct nfp_net *ctrl)
+{
+	int err;
+
+	app->ctrl = ctrl;
+
+	if (app->type->start) {
+		err = app->type->start(app);
+		if (err)
+			return err;
+	}
+
+	app->netdev_nb.notifier_call = nfp_app_netdev_event;
+	err = register_netdevice_notifier(&app->netdev_nb);
+	if (err)
+		goto err_app_stop;
+
+	return 0;
+
+err_app_stop:
+	if (app->type->stop)
+		app->type->stop(app);
+	return err;
+}
+
+void nfp_app_stop(struct nfp_app *app)
+{
+	unregister_netdevice_notifier(&app->netdev_nb);
+
+	if (app->type->stop)
+		app->type->stop(app);
+}
+
 struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id)
 {
 	struct nfp_app *app;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index 4d6ecf99b1cc..f8d422713705 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -69,6 +69,7 @@ extern const struct nfp_app_type app_abm;
  * @port_get_stats_strings:	get strings for extra statistics
  * @start:	start application logic
  * @stop:	stop application logic
+ * @netdev_event:	Netdevice notifier event
  * @ctrl_msg_rx:    control message handler
  * @ctrl_msg_rx_raw:	handler for control messages from data queues
  * @setup_tc:	setup TC ndo
@@ -122,6 +123,9 @@ struct nfp_app_type {
 	int (*start)(struct nfp_app *app);
 	void (*stop)(struct nfp_app *app);
 
+	int (*netdev_event)(struct nfp_app *app, struct net_device *netdev,
+			    unsigned long event, void *ptr);
+
 	void (*ctrl_msg_rx)(struct nfp_app *app, struct sk_buff *skb);
 	void (*ctrl_msg_rx_raw)(struct nfp_app *app, const void *data,
 				unsigned int len);
@@ -151,6 +155,7 @@ struct nfp_app_type {
  * @reprs:	array of pointers to representors
  * @type:	pointer to const application ops and info
  * @ctrl_mtu:	MTU to set on the control vNIC (set in .init())
+ * @netdev_nb:	Netdevice notifier block
  * @priv:	app-specific priv data
  */
 struct nfp_app {
@@ -163,6 +168,9 @@ struct nfp_app {
 
 	const struct nfp_app_type *type;
 	unsigned int ctrl_mtu;
+
+	struct notifier_block netdev_nb;
+
 	void *priv;
 };
 
@@ -264,21 +272,6 @@ nfp_app_repr_change_mtu(struct nfp_app *app, struct net_device *netdev,
 	return app->type->repr_change_mtu(app, netdev, new_mtu);
 }
 
-static inline int nfp_app_start(struct nfp_app *app, struct nfp_net *ctrl)
-{
-	app->ctrl = ctrl;
-	if (!app->type->start)
-		return 0;
-	return app->type->start(app);
-}
-
-static inline void nfp_app_stop(struct nfp_app *app)
-{
-	if (!app->type->stop)
-		return;
-	app->type->stop(app);
-}
-
 static inline const char *nfp_app_name(struct nfp_app *app)
 {
 	if (!app)
@@ -430,6 +423,8 @@ nfp_app_ctrl_msg_alloc(struct nfp_app *app, unsigned int size, gfp_t priority);
 
 struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id);
 void nfp_app_free(struct nfp_app *app);
+int nfp_app_start(struct nfp_app *app, struct nfp_net *ctrl);
+void nfp_app_stop(struct nfp_app *app);
 
 /* Callbacks shared between apps */
 
@@ -438,4 +433,6 @@ int nfp_app_nic_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
 int nfp_app_nic_vnic_init_phy_port(struct nfp_pf *pf, struct nfp_app *app,
 				   struct nfp_net *nn, unsigned int id);
 
+struct devlink *nfp_devlink_get_devlink(struct net_device *netdev);
+
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
index 808647ec3573..e9eca99cf493 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c
@@ -4,6 +4,7 @@
 #include <linux/rtnetlink.h>
 #include <net/devlink.h>
 
+#include "nfpcore/nfp.h"
 #include "nfpcore/nfp_nsp.h"
 #include "nfp_app.h"
 #include "nfp_main.h"
@@ -171,6 +172,173 @@ static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode,
 	return ret;
 }
 
+static const struct nfp_devlink_versions_simple {
+	const char *key;
+	const char *hwinfo;
+} nfp_devlink_versions_hwinfo[] = {
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_ID,	"assembly.partno", },
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_REV,	"assembly.revision", },
+	{ DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE, "assembly.vendor", },
+	{ "board.model", /* code name */		"assembly.model", },
+};
+
+static int
+nfp_devlink_versions_get_hwinfo(struct nfp_pf *pf, struct devlink_info_req *req)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < ARRAY_SIZE(nfp_devlink_versions_hwinfo); i++) {
+		const struct nfp_devlink_versions_simple *info;
+		const char *val;
+
+		info = &nfp_devlink_versions_hwinfo[i];
+
+		val = nfp_hwinfo_lookup(pf->hwinfo, info->hwinfo);
+		if (!val)
+			continue;
+
+		err = devlink_info_version_fixed_put(req, info->key, val);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static const struct nfp_devlink_versions {
+	enum nfp_nsp_versions id;
+	const char *key;
+} nfp_devlink_versions_nsp[] = {
+	{ NFP_VERSIONS_BUNDLE,	"fw.bundle_id", },
+	{ NFP_VERSIONS_BSP,	DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, },
+	{ NFP_VERSIONS_CPLD,	"fw.cpld", },
+	{ NFP_VERSIONS_APP,	DEVLINK_INFO_VERSION_GENERIC_FW_APP, },
+	{ NFP_VERSIONS_UNDI,	DEVLINK_INFO_VERSION_GENERIC_FW_UNDI, },
+	{ NFP_VERSIONS_NCSI,	DEVLINK_INFO_VERSION_GENERIC_FW_NCSI, },
+	{ NFP_VERSIONS_CFGR,	"chip.init", },
+};
+
+static int
+nfp_devlink_versions_get_nsp(struct devlink_info_req *req, bool flash,
+			     const u8 *buf, unsigned int size)
+{
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < ARRAY_SIZE(nfp_devlink_versions_nsp); i++) {
+		const struct nfp_devlink_versions *info;
+		const char *version;
+
+		info = &nfp_devlink_versions_nsp[i];
+
+		version = nfp_nsp_versions_get(info->id, flash, buf, size);
+		if (IS_ERR(version)) {
+			if (PTR_ERR(version) == -ENOENT)
+				continue;
+			else
+				return PTR_ERR(version);
+		}
+
+		if (flash)
+			err = devlink_info_version_stored_put(req, info->key,
+							      version);
+		else
+			err = devlink_info_version_running_put(req, info->key,
+							       version);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+nfp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
+		     struct netlink_ext_ack *extack)
+{
+	struct nfp_pf *pf = devlink_priv(devlink);
+	const char *sn, *vendor, *part;
+	struct nfp_nsp *nsp;
+	char *buf = NULL;
+	int err;
+
+	err = devlink_info_driver_name_put(req, "nfp");
+	if (err)
+		return err;
+
+	vendor = nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor");
+	part = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno");
+	sn = nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial");
+	if (vendor && part && sn) {
+		char *buf;
+
+		buf = kmalloc(strlen(vendor) + strlen(part) + strlen(sn) + 1,
+			      GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		buf[0] = '\0';
+		strcat(buf, vendor);
+		strcat(buf, part);
+		strcat(buf, sn);
+
+		err = devlink_info_serial_number_put(req, buf);
+		kfree(buf);
+		if (err)
+			return err;
+	}
+
+	nsp = nfp_nsp_open(pf->cpp);
+	if (IS_ERR(nsp)) {
+		NL_SET_ERR_MSG_MOD(extack, "can't access NSP");
+		return PTR_ERR(nsp);
+	}
+
+	if (nfp_nsp_has_versions(nsp)) {
+		buf = kzalloc(NFP_NSP_VERSION_BUFSZ, GFP_KERNEL);
+		if (!buf) {
+			err = -ENOMEM;
+			goto err_close_nsp;
+		}
+
+		err = nfp_nsp_versions(nsp, buf, NFP_NSP_VERSION_BUFSZ);
+		if (err)
+			goto err_free_buf;
+
+		err = nfp_devlink_versions_get_nsp(req, false,
+						   buf, NFP_NSP_VERSION_BUFSZ);
+		if (err)
+			goto err_free_buf;
+
+		err = nfp_devlink_versions_get_nsp(req, true,
+						   buf, NFP_NSP_VERSION_BUFSZ);
+		if (err)
+			goto err_free_buf;
+
+		kfree(buf);
+	}
+
+	nfp_nsp_close(nsp);
+
+	return nfp_devlink_versions_get_hwinfo(pf, req);
+
+err_free_buf:
+	kfree(buf);
+err_close_nsp:
+	nfp_nsp_close(nsp);
+	return err;
+}
+
+static int
+nfp_devlink_flash_update(struct devlink *devlink, const char *path,
+			 const char *component, struct netlink_ext_ack *extack)
+{
+	if (component)
+		return -EOPNOTSUPP;
+	return nfp_flash_update_common(devlink_priv(devlink), path, extack);
+}
+
 const struct devlink_ops nfp_devlink_ops = {
 	.port_split		= nfp_devlink_port_split,
 	.port_unsplit		= nfp_devlink_port_unsplit,
@@ -178,6 +346,8 @@ const struct devlink_ops nfp_devlink_ops = {
 	.sb_pool_set		= nfp_devlink_sb_pool_set,
 	.eswitch_mode_get	= nfp_devlink_eswitch_mode_get,
 	.eswitch_mode_set	= nfp_devlink_eswitch_mode_set,
+	.info_get		= nfp_devlink_info_get,
+	.flash_update		= nfp_devlink_flash_update,
 };
 
 int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port)
@@ -206,3 +376,14 @@ void nfp_devlink_port_unregister(struct nfp_port *port)
 {
 	devlink_port_unregister(&port->dl_port);
 }
+
+struct devlink *nfp_devlink_get_devlink(struct net_device *netdev)
+{
+	struct nfp_app *app;
+
+	app = nfp_app_from_netdev(netdev);
+	if (!app)
+		return NULL;
+
+	return priv_to_devlink(app->pf);
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 6c10e8d119e4..f4c8776e42b6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -300,6 +300,47 @@ static int nfp_pcie_sriov_configure(struct pci_dev *pdev, int num_vfs)
 		return nfp_pcie_sriov_enable(pdev, num_vfs);
 }
 
+int nfp_flash_update_common(struct nfp_pf *pf, const char *path,
+			    struct netlink_ext_ack *extack)
+{
+	struct device *dev = &pf->pdev->dev;
+	const struct firmware *fw;
+	struct nfp_nsp *nsp;
+	int err;
+
+	nsp = nfp_nsp_open(pf->cpp);
+	if (IS_ERR(nsp)) {
+		err = PTR_ERR(nsp);
+		if (extack)
+			NL_SET_ERR_MSG_MOD(extack, "can't access NSP");
+		else
+			dev_err(dev, "Failed to access the NSP: %d\n", err);
+		return err;
+	}
+
+	err = request_firmware_direct(&fw, path, dev);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "unable to read flash file from disk");
+		goto exit_close_nsp;
+	}
+
+	dev_info(dev, "Please be patient while writing flash image: %s\n",
+		 path);
+
+	err = nfp_nsp_write_flash(nsp, fw);
+	if (err < 0)
+		goto exit_release_fw;
+	dev_info(dev, "Finished writing flash image\n");
+	err = 0;
+
+exit_release_fw:
+	release_firmware(fw);
+exit_close_nsp:
+	nfp_nsp_close(nsp);
+	return err;
+}
+
 static const struct firmware *
 nfp_net_fw_request(struct pci_dev *pdev, struct nfp_pf *pf, const char *name)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h
index a3613a2e0aa5..b7211f200d22 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h
@@ -164,6 +164,8 @@ nfp_pf_map_rtsym(struct nfp_pf *pf, const char *name, const char *sym_fmt,
 		 unsigned int min_size, struct nfp_cpp_area **area);
 int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length,
 		 void *out_data, u64 out_length);
+int nfp_flash_update_common(struct nfp_pf *pf, const char *path,
+			    struct netlink_ext_ack *extack);
 
 enum nfp_dump_diag {
 	NFP_DUMP_NSP_DIAG = 0,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 6f0c37d09256..be37c2d6151c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -158,6 +158,7 @@ struct nfp_net_tx_desc {
 			__le16 data_len; /* Length of frame + meta data */
 		} __packed;
 		__le32 vals[4];
+		__le64 vals8[2];
 	};
 };
 
@@ -543,6 +544,7 @@ struct nfp_net_dp {
  * @reconfig_timer_active:  Timer for reading reconfiguration results is pending
  * @reconfig_sync_present:  Some thread is performing synchronous reconfig
  * @reconfig_timer:	Timer for async reading of reconfig results
+ * @reconfig_in_progress_update:	Update FW is processing now (debug only)
  * @link_up:            Is the link up?
  * @link_status_lock:	Protects @link_* and ensures atomicity with BAR reading
  * @rx_coalesce_usecs:      RX interrupt moderation usecs delay parameter
@@ -611,6 +613,7 @@ struct nfp_net {
 	bool reconfig_timer_active;
 	bool reconfig_sync_present;
 	struct timer_list reconfig_timer;
+	u32 reconfig_in_progress_update;
 
 	u32 rx_coalesce_usecs;
 	u32 rx_coalesce_max_frames;
@@ -851,7 +854,7 @@ void nfp_net_get_fw_version(struct nfp_net_fw_version *fw_ver,
 			    void __iomem *ctrl_bar);
 
 struct nfp_net *
-nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
+nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
 	      unsigned int max_tx_rings, unsigned int max_rx_rings);
 void nfp_net_free(struct nfp_net *nn);
 
@@ -868,6 +871,7 @@ unsigned int nfp_net_rss_key_sz(struct nfp_net *nn);
 void nfp_net_rss_write_itbl(struct nfp_net *nn);
 void nfp_net_rss_write_key(struct nfp_net *nn);
 void nfp_net_coalesce_write_cfg(struct nfp_net *nn);
+int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd);
 
 unsigned int
 nfp_net_irqs_alloc(struct pci_dev *pdev, struct msix_entry *irq_entries,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 6bddfcfdec34..6d1b8816552e 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -36,7 +36,6 @@
 #include <linux/vmalloc.h>
 #include <linux/ktime.h>
 
-#include <net/switchdev.h>
 #include <net/vxlan.h>
 
 #include "nfpcore/nfp_nsp.h"
@@ -101,6 +100,7 @@ static void nfp_net_reconfig_start(struct nfp_net *nn, u32 update)
 	/* ensure update is written before pinging HW */
 	nn_pci_flush(nn);
 	nfp_qcp_wr_ptr_add(nn->qcp_cfg, 1);
+	nn->reconfig_in_progress_update = update;
 }
 
 /* Pass 0 as update to run posted reconfigs. */
@@ -123,10 +123,14 @@ static bool nfp_net_reconfig_check_done(struct nfp_net *nn, bool last_check)
 	if (reg == 0)
 		return true;
 	if (reg & NFP_NET_CFG_UPDATE_ERR) {
-		nn_err(nn, "Reconfig error: 0x%08x\n", reg);
+		nn_err(nn, "Reconfig error (status: 0x%08x update: 0x%08x ctrl: 0x%08x)\n",
+		       reg, nn->reconfig_in_progress_update,
+		       nn_readl(nn, NFP_NET_CFG_CTRL));
 		return true;
 	} else if (last_check) {
-		nn_err(nn, "Reconfig timeout: 0x%08x\n", reg);
+		nn_err(nn, "Reconfig timeout (status: 0x%08x update: 0x%08x ctrl: 0x%08x)\n",
+		       reg, nn->reconfig_in_progress_update,
+		       nn_readl(nn, NFP_NET_CFG_CTRL));
 		return true;
 	}
 
@@ -279,7 +283,7 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update)
  *
  * Return: Negative errno on error, 0 on success
  */
-static int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
+int nfp_net_reconfig_mbox(struct nfp_net *nn, u32 mbox_cmd)
 {
 	u32 mbox = nn->tlv_caps.mbox_off;
 	int ret;
@@ -647,27 +651,29 @@ static void nfp_net_tx_ring_stop(struct netdev_queue *nd_q,
  * @txbuf: Pointer to driver soft TX descriptor
  * @txd: Pointer to HW TX descriptor
  * @skb: Pointer to SKB
+ * @md_bytes: Prepend length
  *
  * Set up Tx descriptor for LSO, do nothing for non-LSO skbs.
  * Return error on packet header greater than maximum supported LSO header size.
  */
 static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 			   struct nfp_net_tx_buf *txbuf,
-			   struct nfp_net_tx_desc *txd, struct sk_buff *skb)
+			   struct nfp_net_tx_desc *txd, struct sk_buff *skb,
+			   u32 md_bytes)
 {
-	u32 hdrlen;
+	u32 l3_offset, l4_offset, hdrlen;
 	u16 mss;
 
 	if (!skb_is_gso(skb))
 		return;
 
 	if (!skb->encapsulation) {
-		txd->l3_offset = skb_network_offset(skb);
-		txd->l4_offset = skb_transport_offset(skb);
+		l3_offset = skb_network_offset(skb);
+		l4_offset = skb_transport_offset(skb);
 		hdrlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
 	} else {
-		txd->l3_offset = skb_inner_network_offset(skb);
-		txd->l4_offset = skb_inner_transport_offset(skb);
+		l3_offset = skb_inner_network_offset(skb);
+		l4_offset = skb_inner_transport_offset(skb);
 		hdrlen = skb_inner_transport_header(skb) - skb->data +
 			inner_tcp_hdrlen(skb);
 	}
@@ -676,7 +682,9 @@ static void nfp_net_tx_tso(struct nfp_net_r_vector *r_vec,
 	txbuf->real_len += hdrlen * (txbuf->pkt_cnt - 1);
 
 	mss = skb_shinfo(skb)->gso_size & PCIE_DESC_TX_MSS_MASK;
-	txd->lso_hdrlen = hdrlen;
+	txd->l3_offset = l3_offset - md_bytes;
+	txd->l4_offset = l4_offset - md_bytes;
+	txd->lso_hdrlen = hdrlen - md_bytes;
 	txd->mss = cpu_to_le16(mss);
 	txd->flags |= PCIE_DESC_TX_LSO;
 
@@ -786,11 +794,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 	const struct skb_frag_struct *frag;
-	struct nfp_net_tx_desc *txd, txdg;
 	int f, nr_frags, wr_idx, md_bytes;
 	struct nfp_net_tx_ring *tx_ring;
 	struct nfp_net_r_vector *r_vec;
 	struct nfp_net_tx_buf *txbuf;
+	struct nfp_net_tx_desc *txd;
 	struct netdev_queue *nd_q;
 	struct nfp_net_dp *dp;
 	dma_addr_t dma_addr;
@@ -801,13 +809,13 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	qidx = skb_get_queue_mapping(skb);
 	tx_ring = &dp->tx_rings[qidx];
 	r_vec = tx_ring->r_vec;
-	nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	if (unlikely(nfp_net_tx_full(tx_ring, nr_frags + 1))) {
 		nn_dp_warn(dp, "TX ring %d busy. wrp=%u rdp=%u\n",
 			   qidx, tx_ring->wr_p, tx_ring->rd_p);
+		nd_q = netdev_get_tx_queue(dp->netdev, qidx);
 		netif_tx_stop_queue(nd_q);
 		nfp_net_tx_xmit_more_flush(tx_ring);
 		u64_stats_update_begin(&r_vec->tx_sync);
@@ -851,7 +859,7 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 	txd->lso_hdrlen = 0;
 
 	/* Do not reorder - tso may adjust pkt cnt, vlan may override fields */
-	nfp_net_tx_tso(r_vec, txbuf, txd, skb);
+	nfp_net_tx_tso(r_vec, txbuf, txd, skb, md_bytes);
 	nfp_net_tx_csum(dp, r_vec, txbuf, txd, skb);
 	if (skb_vlan_tag_present(skb) && dp->ctrl & NFP_NET_CFG_CTRL_TXVLAN) {
 		txd->flags |= PCIE_DESC_TX_VLAN;
@@ -860,8 +868,10 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 
 	/* Gather DMA */
 	if (nr_frags > 0) {
+		__le64 second_half;
+
 		/* all descs must match except for in addr, length and eop */
-		txdg = *txd;
+		second_half = txd->vals8[1];
 
 		for (f = 0; f < nr_frags; f++) {
 			frag = &skb_shinfo(skb)->frags[f];
@@ -878,11 +888,11 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 			tx_ring->txbufs[wr_idx].fidx = f;
 
 			txd = &tx_ring->txds[wr_idx];
-			*txd = txdg;
 			txd->dma_len = cpu_to_le16(fsize);
 			nfp_desc_set_dma_addr(txd, dma_addr);
-			txd->offset_eop |=
-				(f == nr_frags - 1) ? PCIE_DESC_TX_EOP : 0;
+			txd->offset_eop = md_bytes |
+				((f == nr_frags - 1) ? PCIE_DESC_TX_EOP : 0);
+			txd->vals8[1] = second_half;
 		}
 
 		u64_stats_update_begin(&r_vec->tx_sync);
@@ -890,16 +900,16 @@ static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev)
 		u64_stats_update_end(&r_vec->tx_sync);
 	}
 
-	netdev_tx_sent_queue(nd_q, txbuf->real_len);
-
 	skb_tx_timestamp(skb);
 
+	nd_q = netdev_get_tx_queue(dp->netdev, tx_ring->idx);
+
 	tx_ring->wr_p += nr_frags + 1;
 	if (nfp_net_tx_ring_should_stop(tx_ring))
 		nfp_net_tx_ring_stop(nd_q, tx_ring);
 
 	tx_ring->wr_ptr_add += nr_frags + 1;
-	if (!skb->xmit_more || netif_xmit_stopped(nd_q))
+	if (__netdev_tx_sent_queue(nd_q, txbuf->real_len, skb->xmit_more))
 		nfp_net_tx_xmit_more_flush(tx_ring);
 
 	return NETDEV_TX_OK;
@@ -940,14 +950,10 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
-	const struct skb_frag_struct *frag;
 	struct netdev_queue *nd_q;
 	u32 done_pkts = 0, done_bytes = 0;
-	struct sk_buff *skb;
-	int todo, nr_frags;
 	u32 qcp_rd_p;
-	int fidx;
-	int idx;
+	int todo;
 
 	if (tx_ring->wr_p == tx_ring->rd_p)
 		return;
@@ -961,26 +967,33 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 	todo = D_IDX(tx_ring, qcp_rd_p - tx_ring->qcp_rd_p);
 
 	while (todo--) {
+		const struct skb_frag_struct *frag;
+		struct nfp_net_tx_buf *tx_buf;
+		struct sk_buff *skb;
+		int fidx, nr_frags;
+		int idx;
+
 		idx = D_IDX(tx_ring, tx_ring->rd_p++);
+		tx_buf = &tx_ring->txbufs[idx];
 
-		skb = tx_ring->txbufs[idx].skb;
+		skb = tx_buf->skb;
 		if (!skb)
 			continue;
 
 		nr_frags = skb_shinfo(skb)->nr_frags;
-		fidx = tx_ring->txbufs[idx].fidx;
+		fidx = tx_buf->fidx;
 
 		if (fidx == -1) {
 			/* unmap head */
-			dma_unmap_single(dp->dev, tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_single(dp->dev, tx_buf->dma_addr,
 					 skb_headlen(skb), DMA_TO_DEVICE);
 
-			done_pkts += tx_ring->txbufs[idx].pkt_cnt;
-			done_bytes += tx_ring->txbufs[idx].real_len;
+			done_pkts += tx_buf->pkt_cnt;
+			done_bytes += tx_buf->real_len;
 		} else {
 			/* unmap fragment */
 			frag = &skb_shinfo(skb)->frags[fidx];
-			dma_unmap_page(dp->dev, tx_ring->txbufs[idx].dma_addr,
+			dma_unmap_page(dp->dev, tx_buf->dma_addr,
 				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
 
@@ -988,9 +1001,9 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 		if (fidx == nr_frags - 1)
 			napi_consume_skb(skb, budget);
 
-		tx_ring->txbufs[idx].dma_addr = 0;
-		tx_ring->txbufs[idx].skb = NULL;
-		tx_ring->txbufs[idx].fidx = -2;
+		tx_buf->dma_addr = 0;
+		tx_buf->skb = NULL;
+		tx_buf->fidx = -2;
 	}
 
 	tx_ring->qcp_rd_p = qcp_rd_p;
@@ -2156,9 +2169,9 @@ nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 	tx_ring->cnt = dp->txd_cnt;
 
 	tx_ring->size = array_size(tx_ring->cnt, sizeof(*tx_ring->txds));
-	tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size,
-					    &tx_ring->dma,
-					    GFP_KERNEL | __GFP_NOWARN);
+	tx_ring->txds = dma_alloc_coherent(dp->dev, tx_ring->size,
+					   &tx_ring->dma,
+					   GFP_KERNEL | __GFP_NOWARN);
 	if (!tx_ring->txds) {
 		netdev_warn(dp->netdev, "failed to allocate TX descriptor ring memory, requested descriptor count: %d, consider lowering descriptor count\n",
 			    tx_ring->cnt);
@@ -2314,9 +2327,9 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 
 	rx_ring->cnt = dp->rxd_cnt;
 	rx_ring->size = array_size(rx_ring->cnt, sizeof(*rx_ring->rxds));
-	rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size,
-					    &rx_ring->dma,
-					    GFP_KERNEL | __GFP_NOWARN);
+	rx_ring->rxds = dma_alloc_coherent(dp->dev, rx_ring->size,
+					   &rx_ring->dma,
+					   GFP_KERNEL | __GFP_NOWARN);
 	if (!rx_ring->rxds) {
 		netdev_warn(dp->netdev, "failed to allocate RX descriptor ring memory, requested descriptor count: %d, consider lowering descriptor count\n",
 			    rx_ring->cnt);
@@ -3275,7 +3288,10 @@ nfp_net_features_check(struct sk_buff *skb, struct net_device *dev,
 		hdrlen = skb_inner_transport_header(skb) - skb->data +
 			inner_tcp_hdrlen(skb);
 
-		if (unlikely(hdrlen > NFP_NET_LSO_MAX_HDR_SZ))
+		/* Assume worst case scenario of having longest possible
+		 * metadata prepend - 8B
+		 */
+		if (unlikely(hdrlen > NFP_NET_LSO_MAX_HDR_SZ - 8))
 			features &= ~NETIF_F_GSO_MASK;
 	}
 
@@ -3514,6 +3530,8 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_udp_tunnel_add	= nfp_net_add_vxlan_port,
 	.ndo_udp_tunnel_del	= nfp_net_del_vxlan_port,
 	.ndo_bpf		= nfp_net_xdp,
+	.ndo_get_port_parent_id	= nfp_port_get_port_parent_id,
+	.ndo_get_devlink	= nfp_devlink_get_devlink,
 };
 
 /**
@@ -3560,6 +3578,7 @@ void nfp_net_info(struct nfp_net *nn)
 /**
  * nfp_net_alloc() - Allocate netdev and related structure
  * @pdev:         PCI device
+ * @ctrl_bar:     PCI IOMEM with vNIC config memory
  * @needs_netdev: Whether to allocate a netdev for this vNIC
  * @max_tx_rings: Maximum number of TX rings supported by device
  * @max_rx_rings: Maximum number of RX rings supported by device
@@ -3570,11 +3589,12 @@ void nfp_net_info(struct nfp_net *nn)
  *
  * Return: NFP Net device structure, or ERR_PTR on error.
  */
-struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
-			      unsigned int max_tx_rings,
-			      unsigned int max_rx_rings)
+struct nfp_net *
+nfp_net_alloc(struct pci_dev *pdev, void __iomem *ctrl_bar, bool needs_netdev,
+	      unsigned int max_tx_rings, unsigned int max_rx_rings)
 {
 	struct nfp_net *nn;
+	int err;
 
 	if (needs_netdev) {
 		struct net_device *netdev;
@@ -3594,6 +3614,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
 	}
 
 	nn->dp.dev = &pdev->dev;
+	nn->dp.ctrl_bar = ctrl_bar;
 	nn->pdev = pdev;
 
 	nn->max_tx_rings = max_tx_rings;
@@ -3616,7 +3637,19 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
 
 	timer_setup(&nn->reconfig_timer, nfp_net_reconfig_timer, 0);
 
+	err = nfp_net_tlv_caps_parse(&nn->pdev->dev, nn->dp.ctrl_bar,
+				     &nn->tlv_caps);
+	if (err)
+		goto err_free_nn;
+
 	return nn;
+
+err_free_nn:
+	if (nn->dp.netdev)
+		free_netdev(nn->dp.netdev);
+	else
+		vfree(nn);
+	return ERR_PTR(err);
 }
 
 /**
@@ -3783,8 +3816,6 @@ static void nfp_net_netdev_init(struct nfp_net *nn)
 	netdev->netdev_ops = &nfp_net_netdev_ops;
 	netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000);
 
-	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
-
 	/* MTU range: 68 - hw-specific max */
 	netdev->min_mtu = ETH_MIN_MTU;
 	netdev->max_mtu = nn->max_mtu;
@@ -3889,11 +3920,6 @@ int nfp_net_init(struct nfp_net *nn)
 		nn->dp.ctrl |= NFP_NET_CFG_CTRL_IRQMOD;
 	}
 
-	err = nfp_net_tlv_caps_parse(&nn->pdev->dev, nn->dp.ctrl_bar,
-				     &nn->tlv_caps);
-	if (err)
-		return err;
-
 	if (nn->dp.netdev)
 		nfp_net_netdev_init(nn);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
index f2aaef976c7d..6d5213b5bcb0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.c
@@ -41,8 +41,8 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 		data += 4;
 
 		if (length % NFP_NET_CFG_TLV_LENGTH_INC) {
-			dev_err(dev, "TLV size not multiple of %u len:%u\n",
-				NFP_NET_CFG_TLV_LENGTH_INC, length);
+			dev_err(dev, "TLV size not multiple of %u offset:%u len:%u\n",
+				NFP_NET_CFG_TLV_LENGTH_INC, offset, length);
 			return -EINVAL;
 		}
 		if (data + length > end) {
@@ -61,14 +61,14 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 			if (!length)
 				return 0;
 
-			dev_err(dev, "END TLV should be empty, has len:%d\n",
-				length);
+			dev_err(dev, "END TLV should be empty, has offset:%u len:%d\n",
+				offset, length);
 			return -EINVAL;
 		case NFP_NET_CFG_TLV_TYPE_ME_FREQ:
 			if (length != 4) {
 				dev_err(dev,
-					"ME FREQ TLV should be 4B, is %dB\n",
-					length);
+					"ME FREQ TLV should be 4B, is %dB offset:%u\n",
+					length, offset);
 				return -EINVAL;
 			}
 
@@ -90,6 +90,15 @@ int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
 				 FIELD_GET(NFP_NET_CFG_TLV_HEADER_TYPE, hdr),
 				 offset, length);
 			break;
+		case NFP_NET_CFG_TLV_TYPE_REPR_CAP:
+			if (length < 4) {
+				dev_err(dev, "REPR CAP TLV short %dB < 4B offset:%u\n",
+					length, offset);
+				return -EINVAL;
+			}
+
+			caps->repr_cap = readl(data);
+			break;
 		default:
 			if (!FIELD_GET(NFP_NET_CFG_TLV_HEADER_REQUIRED, hdr))
 				break;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index d7c8518ac952..372adea10e14 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -392,11 +392,13 @@
 #define NFP_NET_CFG_MBOX_SIMPLE_CMD	0x0
 #define NFP_NET_CFG_MBOX_SIMPLE_RET	0x4
 #define NFP_NET_CFG_MBOX_SIMPLE_VAL	0x8
-#define NFP_NET_CFG_MBOX_SIMPLE_LEN	0x12
+#define NFP_NET_CFG_MBOX_SIMPLE_LEN	12
 
 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_ADD 1
 #define NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL 2
 
+#define NFP_NET_CFG_MBOX_CMD_PCI_DSCP_PRIOMAP_SET	5
+
 /**
  * VLAN filtering using general use mailbox
  * %NFP_NET_CFG_VLAN_FILTER:		Base address of VLAN filter mailbox
@@ -464,6 +466,10 @@
  * Variable, experimental IDs.  IDs designated for internal development and
  * experiments before a stable TLV ID has been allocated to a feature.  Should
  * never be present in production firmware.
+ *
+ * %NFP_NET_CFG_TLV_TYPE_REPR_CAP:
+ * Single word, equivalent of %NFP_NET_CFG_CAP for representors, features which
+ * can be used on representors.
  */
 #define NFP_NET_CFG_TLV_TYPE_UNKNOWN		0
 #define NFP_NET_CFG_TLV_TYPE_RESERVED		1
@@ -472,6 +478,7 @@
 #define NFP_NET_CFG_TLV_TYPE_MBOX		4
 #define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL0	5
 #define NFP_NET_CFG_TLV_TYPE_EXPERIMENTAL1	6
+#define NFP_NET_CFG_TLV_TYPE_REPR_CAP		7
 
 struct device;
 
@@ -480,11 +487,13 @@ struct device;
  * @me_freq_mhz:	ME clock_freq (MHz)
  * @mbox_off:		vNIC mailbox area offset
  * @mbox_len:		vNIC mailbox area length
+ * @repr_cap:		capabilities for representors
  */
 struct nfp_net_tlv_caps {
 	u32 me_freq_mhz;
 	unsigned int mbox_off;
 	unsigned int mbox_len;
+	u32 repr_cap;
 };
 
 int nfp_net_tlv_caps_parse(struct device *dev, u8 __iomem *ctrl_mem,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
index 69b1c9b62e3d..ab7f2498e1c4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c
@@ -8,7 +8,7 @@
 
 static struct dentry *nfp_dir;
 
-static int nfp_net_debugfs_rx_q_read(struct seq_file *file, void *data)
+static int nfp_rx_q_show(struct seq_file *file, void *data)
 {
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_rx_ring *rx_ring;
@@ -65,31 +65,12 @@ out:
 	rtnl_unlock();
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(nfp_rx_q);
 
-static int nfp_net_debugfs_rx_q_open(struct inode *inode, struct file *f)
-{
-	return single_open(f, nfp_net_debugfs_rx_q_read, inode->i_private);
-}
+static int nfp_tx_q_show(struct seq_file *file, void *data);
+DEFINE_SHOW_ATTRIBUTE(nfp_tx_q);
 
-static const struct file_operations nfp_rx_q_fops = {
-	.owner = THIS_MODULE,
-	.open = nfp_net_debugfs_rx_q_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
-
-static int nfp_net_debugfs_tx_q_open(struct inode *inode, struct file *f);
-
-static const struct file_operations nfp_tx_q_fops = {
-	.owner = THIS_MODULE,
-	.open = nfp_net_debugfs_tx_q_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
-
-static int nfp_net_debugfs_tx_q_read(struct seq_file *file, void *data)
+static int nfp_tx_q_show(struct seq_file *file, void *data)
 {
 	struct nfp_net_r_vector *r_vec = file->private;
 	struct nfp_net_tx_ring *tx_ring;
@@ -158,18 +139,11 @@ out:
 	return 0;
 }
 
-static int nfp_net_debugfs_tx_q_open(struct inode *inode, struct file *f)
+static int nfp_xdp_q_show(struct seq_file *file, void *data)
 {
-	return single_open(f, nfp_net_debugfs_tx_q_read, inode->i_private);
+	return nfp_tx_q_show(file, data);
 }
-
-static const struct file_operations nfp_xdp_q_fops = {
-	.owner = THIS_MODULE,
-	.open = nfp_net_debugfs_tx_q_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek
-};
+DEFINE_SHOW_ATTRIBUTE(nfp_xdp_q);
 
 void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index cb9c512abc76..690b62718dbb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -1234,57 +1234,6 @@ static int nfp_net_set_channels(struct net_device *netdev,
 	return nfp_net_set_num_rings(nn, total_rx, total_tx);
 }
 
-static int
-nfp_net_flash_device(struct net_device *netdev, struct ethtool_flash *flash)
-{
-	const struct firmware *fw;
-	struct nfp_app *app;
-	struct nfp_nsp *nsp;
-	struct device *dev;
-	int err;
-
-	if (flash->region != ETHTOOL_FLASH_ALL_REGIONS)
-		return -EOPNOTSUPP;
-
-	app = nfp_app_from_netdev(netdev);
-	if (!app)
-		return -EOPNOTSUPP;
-
-	dev = &app->pdev->dev;
-
-	nsp = nfp_nsp_open(app->cpp);
-	if (IS_ERR(nsp)) {
-		err = PTR_ERR(nsp);
-		dev_err(dev, "Failed to access the NSP: %d\n", err);
-		return err;
-	}
-
-	err = request_firmware_direct(&fw, flash->data, dev);
-	if (err)
-		goto exit_close_nsp;
-
-	dev_info(dev, "Please be patient while writing flash image: %s\n",
-		 flash->data);
-	dev_hold(netdev);
-	rtnl_unlock();
-
-	err = nfp_nsp_write_flash(nsp, fw);
-	if (err < 0) {
-		dev_err(dev, "Flash write failed: %d\n", err);
-		goto exit_rtnl_lock;
-	}
-	dev_info(dev, "Finished writing flash image\n");
-
-exit_rtnl_lock:
-	rtnl_lock();
-	dev_put(netdev);
-	release_firmware(fw);
-
-exit_close_nsp:
-	nfp_nsp_close(nsp);
-	return err;
-}
-
 static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.get_drvinfo		= nfp_net_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
@@ -1295,7 +1244,6 @@ static const struct ethtool_ops nfp_net_ethtool_ops = {
 	.get_sset_count		= nfp_net_get_sset_count,
 	.get_rxnfc		= nfp_net_get_rxnfc,
 	.set_rxnfc		= nfp_net_set_rxnfc,
-	.flash_device		= nfp_net_flash_device,
 	.get_rxfh_indir_size	= nfp_net_get_rxfh_indir_size,
 	.get_rxfh_key_size	= nfp_net_get_rxfh_key_size,
 	.get_rxfh		= nfp_net_get_rxfh,
@@ -1321,7 +1269,6 @@ const struct ethtool_ops nfp_port_ethtool_ops = {
 	.get_strings		= nfp_port_get_strings,
 	.get_ethtool_stats	= nfp_port_get_stats,
 	.get_sset_count		= nfp_port_get_sset_count,
-	.flash_device		= nfp_net_flash_device,
 	.set_dump		= nfp_app_set_dump,
 	.get_dump_flag		= nfp_app_get_dump_flag,
 	.get_dump_data		= nfp_app_get_dump_data,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
index 1e7d20468a34..08f5fdbd8e41 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c
@@ -116,13 +116,13 @@ nfp_net_pf_alloc_vnic(struct nfp_pf *pf, bool needs_netdev,
 	n_rx_rings = readl(ctrl_bar + NFP_NET_CFG_MAX_RXRINGS);
 
 	/* Allocate and initialise the vNIC */
-	nn = nfp_net_alloc(pf->pdev, needs_netdev, n_tx_rings, n_rx_rings);
+	nn = nfp_net_alloc(pf->pdev, ctrl_bar, needs_netdev,
+			   n_tx_rings, n_rx_rings);
 	if (IS_ERR(nn))
 		return nn;
 
 	nn->app = pf->app;
 	nfp_net_get_fw_version(&nn->fw_ver, ctrl_bar);
-	nn->dp.ctrl_bar = ctrl_bar;
 	nn->tx_bar = qc_bar + tx_base * NFP_QCP_QUEUE_ADDR_SZ;
 	nn->rx_bar = qc_bar + rx_base * NFP_QCP_QUEUE_ADDR_SZ;
 	nn->dp.is_vf = 0;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index c09b893c30dd..94d228c04496 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -5,12 +5,12 @@
 #include <linux/io-64-nonatomic-hi-lo.h>
 #include <linux/lockdep.h>
 #include <net/dst_metadata.h>
-#include <net/switchdev.h>
 
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nsp.h"
 #include "nfp_app.h"
 #include "nfp_main.h"
+#include "nfp_net.h"
 #include "nfp_net_ctrl.h"
 #include "nfp_net_repr.h"
 #include "nfp_net_sriov.h"
@@ -195,7 +195,7 @@ static netdev_tx_t nfp_repr_xmit(struct sk_buff *skb, struct net_device *netdev)
 	ret = dev_queue_xmit(skb);
 	nfp_repr_inc_tx_stats(netdev, len, ret);
 
-	return ret;
+	return NETDEV_TX_OK;
 }
 
 static int nfp_repr_stop(struct net_device *netdev)
@@ -231,6 +231,27 @@ err_port_disable:
 	return err;
 }
 
+static netdev_features_t
+nfp_repr_fix_features(struct net_device *netdev, netdev_features_t features)
+{
+	struct nfp_repr *repr = netdev_priv(netdev);
+	netdev_features_t old_features = features;
+	netdev_features_t lower_features;
+	struct net_device *lower_dev;
+
+	lower_dev = repr->dst->u.port_info.lower_dev;
+
+	lower_features = lower_dev->features;
+	if (lower_features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))
+		lower_features |= NETIF_F_HW_CSUM;
+
+	features = netdev_intersect_features(features, lower_features);
+	features |= old_features & (NETIF_F_SOFT_FEATURES | NETIF_F_HW_TC);
+	features |= NETIF_F_LLTX;
+
+	return features;
+}
+
 const struct net_device_ops nfp_repr_netdev_ops = {
 	.ndo_init		= nfp_app_ndo_init,
 	.ndo_uninit		= nfp_app_ndo_uninit,
@@ -248,10 +269,27 @@ const struct net_device_ops nfp_repr_netdev_ops = {
 	.ndo_set_vf_spoofchk	= nfp_app_set_vf_spoofchk,
 	.ndo_get_vf_config	= nfp_app_get_vf_config,
 	.ndo_set_vf_link_state	= nfp_app_set_vf_link_state,
+	.ndo_fix_features	= nfp_repr_fix_features,
 	.ndo_set_features	= nfp_port_set_features,
 	.ndo_set_mac_address    = eth_mac_addr,
+	.ndo_get_port_parent_id	= nfp_port_get_port_parent_id,
+	.ndo_get_devlink	= nfp_devlink_get_devlink,
 };
 
+void
+nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower)
+{
+	struct nfp_repr *repr = netdev_priv(netdev);
+
+	if (repr->dst->u.port_info.lower_dev != lower)
+		return;
+
+	netdev->gso_max_size = lower->gso_max_size;
+	netdev->gso_max_segs = lower->gso_max_segs;
+
+	netdev_update_features(netdev);
+}
+
 static void nfp_repr_clean(struct nfp_repr *repr)
 {
 	unregister_netdev(repr->netdev);
@@ -281,6 +319,8 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  struct net_device *pf_netdev)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
+	struct nfp_net *nn = netdev_priv(pf_netdev);
+	u32 repr_cap = nn->tlv_caps.repr_cap;
 	int err;
 
 	nfp_repr_set_lockdep_class(netdev);
@@ -297,7 +337,54 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 
 	netdev->max_mtu = pf_netdev->max_mtu;
 
-	SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops);
+	/* Set features the lower device can support with representors */
+	if (repr_cap & NFP_NET_CFG_CTRL_LIVE_ADDR)
+		netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
+	netdev->hw_features = NETIF_F_HIGHDMA;
+	if (repr_cap & NFP_NET_CFG_CTRL_RXCSUM_ANY)
+		netdev->hw_features |= NETIF_F_RXCSUM;
+	if (repr_cap & NFP_NET_CFG_CTRL_TXCSUM)
+		netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	if (repr_cap & NFP_NET_CFG_CTRL_GATHER)
+		netdev->hw_features |= NETIF_F_SG;
+	if ((repr_cap & NFP_NET_CFG_CTRL_LSO && nn->fw_ver.major > 2) ||
+	    repr_cap & NFP_NET_CFG_CTRL_LSO2)
+		netdev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6;
+	if (repr_cap & NFP_NET_CFG_CTRL_RSS_ANY)
+		netdev->hw_features |= NETIF_F_RXHASH;
+	if (repr_cap & NFP_NET_CFG_CTRL_VXLAN) {
+		if (repr_cap & NFP_NET_CFG_CTRL_LSO)
+			netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL;
+	}
+	if (repr_cap & NFP_NET_CFG_CTRL_NVGRE) {
+		if (repr_cap & NFP_NET_CFG_CTRL_LSO)
+			netdev->hw_features |= NETIF_F_GSO_GRE;
+	}
+	if (repr_cap & (NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE))
+		netdev->hw_enc_features = netdev->hw_features;
+
+	netdev->vlan_features = netdev->hw_features;
+
+	if (repr_cap & NFP_NET_CFG_CTRL_RXVLAN)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
+	if (repr_cap & NFP_NET_CFG_CTRL_TXVLAN) {
+		if (repr_cap & NFP_NET_CFG_CTRL_LSO2)
+			netdev_warn(netdev, "Device advertises both TSO2 and TXVLAN. Refusing to enable TXVLAN.\n");
+		else
+			netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX;
+	}
+	if (repr_cap & NFP_NET_CFG_CTRL_CTAG_FILTER)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
+	netdev->features = netdev->hw_features;
+
+	/* Advertise but disable TSO by default. */
+	netdev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+	netdev->gso_max_segs = NFP_NET_LSO_MAX_SEGS;
+
+	netdev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL;
+	netdev->features |= NETIF_F_LLTX;
 
 	if (nfp_app_has_tc(app)) {
 		netdev->features |= NETIF_F_HW_TC;
@@ -442,7 +529,9 @@ int nfp_reprs_resync_phys_ports(struct nfp_app *app)
 			continue;
 
 		nfp_app_repr_preclean(app, netdev);
+		rtnl_lock();
 		rcu_assign_pointer(reprs->reprs[i], NULL);
+		rtnl_unlock();
 		synchronize_rcu();
 		nfp_repr_clean(repr);
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h
index c412b94bfb97..e0f13dfe1f39 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.h
@@ -92,6 +92,8 @@ nfp_repr_get_locked(struct nfp_app *app, struct nfp_reprs *set,
 		    unsigned int id);
 
 void nfp_repr_inc_rx_stats(struct net_device *netdev, unsigned int len);
+void
+nfp_repr_transfer_features(struct net_device *netdev, struct net_device *lower);
 int nfp_repr_init(struct nfp_app *app, struct net_device *netdev,
 		  u32 cmsg_port_id, struct nfp_port *port,
 		  struct net_device *pf_netdev);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
index d2c1e9ea5668..1145849ca7ba 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_netvf_main.c
@@ -172,7 +172,7 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	rx_bar_off = NFP_PCIE_QUEUE(startq);
 
 	/* Allocate and initialise the netdev */
-	nn = nfp_net_alloc(pdev, true, max_tx_rings, max_rx_rings);
+	nn = nfp_net_alloc(pdev, ctrl_bar, true, max_tx_rings, max_rx_rings);
 	if (IS_ERR(nn)) {
 		err = PTR_ERR(nn);
 		goto err_ctrl_unmap;
@@ -180,7 +180,6 @@ static int nfp_netvf_pci_probe(struct pci_dev *pdev,
 	vf->nn = nn;
 
 	nn->fw_ver = fw_ver;
-	nn->dp.ctrl_bar = ctrl_bar;
 	nn->dp.is_vf = 1;
 	nn->stride_tx = stride;
 	nn->stride_rx = stride;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c
index 86bc149ca231..93c5bfc0510b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c
@@ -3,7 +3,6 @@
 
 #include <linux/lockdep.h>
 #include <linux/netdevice.h>
-#include <net/switchdev.h>
 
 #include "nfpcore/nfp_cpp.h"
 #include "nfpcore/nfp_nsp.h"
@@ -31,34 +30,22 @@ struct nfp_port *nfp_port_from_netdev(struct net_device *netdev)
 	return NULL;
 }
 
-static int
-nfp_port_attr_get(struct net_device *netdev, struct switchdev_attr *attr)
+int nfp_port_get_port_parent_id(struct net_device *netdev,
+				struct netdev_phys_item_id *ppid)
 {
 	struct nfp_port *port;
+	const u8 *serial;
 
 	port = nfp_port_from_netdev(netdev);
 	if (!port)
 		return -EOPNOTSUPP;
 
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: {
-		const u8 *serial;
-		/* N.B: attr->u.ppid.id is binary data */
-		attr->u.ppid.id_len = nfp_cpp_serial(port->app->cpp, &serial);
-		memcpy(&attr->u.ppid.id, serial, attr->u.ppid.id_len);
-		break;
-	}
-	default:
-		return -EOPNOTSUPP;
-	}
+	ppid->id_len = nfp_cpp_serial(port->app->cpp, &serial);
+	memcpy(&ppid->id, serial, ppid->id_len);
 
 	return 0;
 }
 
-const struct switchdev_ops nfp_port_switchdev_ops = {
-	.switchdev_port_attr_get	= nfp_port_attr_get,
-};
-
 int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 		      void *type_data)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h
index b2479a2a49e5..90ae053f5c07 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_port.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h
@@ -7,6 +7,7 @@
 #include <net/devlink.h>
 
 struct net_device;
+struct netdev_phys_item_id;
 struct nfp_app;
 struct nfp_pf;
 struct nfp_port;
@@ -90,7 +91,6 @@ struct nfp_port {
 };
 
 extern const struct ethtool_ops nfp_port_ethtool_ops;
-extern const struct switchdev_ops nfp_port_switchdev_ops;
 
 __printf(2, 3) u8 *nfp_pr_et(u8 *data, const char *fmt, ...);
 
@@ -106,6 +106,8 @@ int
 nfp_port_set_features(struct net_device *netdev, netdev_features_t features);
 
 struct nfp_port *nfp_port_from_netdev(struct net_device *netdev);
+int nfp_port_get_port_parent_id(struct net_device *netdev,
+				struct netdev_phys_item_id *ppid);
 struct nfp_port *
 nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id);
 struct nfp_eth_table_port *__nfp_port_get_eth_port(struct nfp_port *port);
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c
index 814360ed3a20..ea2e3f829aba 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c
@@ -48,6 +48,7 @@ int nfp_shared_buf_pool_get(struct nfp_pf *pf, unsigned int sb, u16 pool_index,
 	pool_info->pool_type = le32_to_cpu(get_data.pool_type);
 	pool_info->threshold_type = le32_to_cpu(get_data.threshold_type);
 	pool_info->size = le32_to_cpu(get_data.size) * unit_size;
+	pool_info->cell_size = unit_size;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
index ce1577bbbd2a..3a4e224a64b7 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c
@@ -7,11 +7,13 @@
  *         Jason McMullan <jason.mcmullan@netronome.com>
  */
 
+#include <asm/unaligned.h>
 #include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/firmware.h>
 #include <linux/kernel.h>
 #include <linux/kthread.h>
+#include <linux/overflow.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
 
@@ -36,6 +38,7 @@
 #define NSP_COMMAND		0x08
 #define   NSP_COMMAND_OPTION	GENMASK_ULL(63, 32)
 #define   NSP_COMMAND_CODE	GENMASK_ULL(31, 16)
+#define   NSP_COMMAND_DMA_BUF	BIT_ULL(1)
 #define   NSP_COMMAND_START	BIT_ULL(0)
 
 /* CPP address to retrieve the data from */
@@ -48,8 +51,12 @@
 #define   NSP_DFLT_BUFFER_ADDRESS	GENMASK_ULL(39, 0)
 
 #define NSP_DFLT_BUFFER_CONFIG	0x20
+#define   NSP_DFLT_BUFFER_DMA_CHUNK_ORDER	GENMASK_ULL(63, 58)
+#define   NSP_DFLT_BUFFER_SIZE_4KB	GENMASK_ULL(15, 8)
 #define   NSP_DFLT_BUFFER_SIZE_MB	GENMASK_ULL(7, 0)
 
+#define NFP_CAP_CMD_DMA_SG	0x28
+
 #define NSP_MAGIC		0xab10
 #define NSP_MAJOR		0
 #define NSP_MINOR		8
@@ -62,6 +69,16 @@
 
 #define NFP_HWINFO_LOOKUP_SIZE	GENMASK(11, 0)
 
+#define NFP_VERSIONS_SIZE	GENMASK(11, 0)
+#define NFP_VERSIONS_CNT_OFF	0
+#define NFP_VERSIONS_BSP_OFF	2
+#define NFP_VERSIONS_CPLD_OFF	6
+#define NFP_VERSIONS_APP_OFF	10
+#define NFP_VERSIONS_BUNDLE_OFF	14
+#define NFP_VERSIONS_UNDI_OFF	18
+#define NFP_VERSIONS_NCSI_OFF	22
+#define NFP_VERSIONS_CFGR_OFF	26
+
 enum nfp_nsp_cmd {
 	SPCODE_NOOP		= 0, /* No operation */
 	SPCODE_SOFT_RESET	= 1, /* Soft reset the NFP */
@@ -77,6 +94,17 @@ enum nfp_nsp_cmd {
 	SPCODE_NSP_IDENTIFY	= 13, /* Read NSP version */
 	SPCODE_FW_STORED	= 16, /* If no FW loaded, load flash app FW */
 	SPCODE_HWINFO_LOOKUP	= 17, /* Lookup HWinfo with overwrites etc. */
+	SPCODE_VERSIONS		= 21, /* Report FW versions */
+};
+
+struct nfp_nsp_dma_buf {
+	__le32 chunk_cnt;
+	__le32 reserved[3];
+	struct {
+		__le32 size;
+		__le32 reserved;
+		__le64 addr;
+	} descs[];
 };
 
 static const struct {
@@ -107,18 +135,18 @@ struct nfp_nsp {
 /**
  * struct nfp_nsp_command_arg - NFP command argument structure
  * @code:	NFP SP Command Code
+ * @dma:	@buf points to a host buffer, not NSP buffer
  * @timeout_sec:Timeout value to wait for completion in seconds
  * @option:	NFP SP Command Argument
- * @buff_cpp:	NFP SP Buffer CPP Address info
- * @buff_addr:	NFP SP Buffer Host address
+ * @buf:	NFP SP Buffer Address
  * @error_cb:	Callback for interpreting option if error occurred
  */
 struct nfp_nsp_command_arg {
 	u16 code;
+	bool dma;
 	unsigned int timeout_sec;
 	u32 option;
-	u32 buff_cpp;
-	u64 buff_addr;
+	u64 buf;
 	void (*error_cb)(struct nfp_nsp *state, u32 ret_val);
 };
 
@@ -332,22 +360,14 @@ __nfp_nsp_command(struct nfp_nsp *state, const struct nfp_nsp_command_arg *arg)
 	if (err)
 		return err;
 
-	if (!FIELD_FIT(NSP_BUFFER_CPP, arg->buff_cpp >> 8) ||
-	    !FIELD_FIT(NSP_BUFFER_ADDRESS, arg->buff_addr)) {
-		nfp_err(cpp, "Host buffer out of reach %08x %016llx\n",
-			arg->buff_cpp, arg->buff_addr);
-		return -EINVAL;
-	}
-
-	err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_buffer,
-			     FIELD_PREP(NSP_BUFFER_CPP, arg->buff_cpp >> 8) |
-			     FIELD_PREP(NSP_BUFFER_ADDRESS, arg->buff_addr));
+	err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_buffer, arg->buf);
 	if (err < 0)
 		return err;
 
 	err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_command,
 			     FIELD_PREP(NSP_COMMAND_OPTION, arg->option) |
 			     FIELD_PREP(NSP_COMMAND_CODE, arg->code) |
+			     FIELD_PREP(NSP_COMMAND_DMA_BUF, arg->dma) |
 			     FIELD_PREP(NSP_COMMAND_START, 1));
 	if (err < 0)
 		return err;
@@ -399,36 +419,14 @@ static int nfp_nsp_command(struct nfp_nsp *state, u16 code)
 }
 
 static int
-nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
+nfp_nsp_command_buf_def(struct nfp_nsp *nsp,
+			struct nfp_nsp_command_buf_arg *arg)
 {
 	struct nfp_cpp *cpp = nsp->cpp;
-	unsigned int max_size;
 	u64 reg, cpp_buf;
-	int ret, err;
+	int err, ret;
 	u32 cpp_id;
 
-	if (nsp->ver.minor < 13) {
-		nfp_err(cpp, "NSP: Code 0x%04x with buffer not supported (ABI %hu.%hu)\n",
-			arg->arg.code, nsp->ver.major, nsp->ver.minor);
-		return -EOPNOTSUPP;
-	}
-
-	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
-			    nfp_resource_address(nsp->res) +
-			    NSP_DFLT_BUFFER_CONFIG,
-			    &reg);
-	if (err < 0)
-		return err;
-
-	max_size = max(arg->in_size, arg->out_size);
-	if (FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M < max_size) {
-		nfp_err(cpp, "NSP: default buffer too small for command 0x%04x (%llu < %u)\n",
-			arg->arg.code,
-			FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M,
-			max_size);
-		return -EINVAL;
-	}
-
 	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
 			    nfp_resource_address(nsp->res) +
 			    NSP_DFLT_BUFFER,
@@ -447,15 +445,21 @@ nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
 	}
 	/* Zero out remaining part of the buffer */
 	if (arg->out_buf && arg->out_size && arg->out_size > arg->in_size) {
-		memset(arg->out_buf, 0, arg->out_size - arg->in_size);
 		err = nfp_cpp_write(cpp, cpp_id, cpp_buf + arg->in_size,
 				    arg->out_buf, arg->out_size - arg->in_size);
 		if (err < 0)
 			return err;
 	}
 
-	arg->arg.buff_cpp = cpp_id;
-	arg->arg.buff_addr = cpp_buf;
+	if (!FIELD_FIT(NSP_BUFFER_CPP, cpp_id >> 8) ||
+	    !FIELD_FIT(NSP_BUFFER_ADDRESS, cpp_buf)) {
+		nfp_err(cpp, "Buffer out of reach %08x %016llx\n",
+			cpp_id, cpp_buf);
+		return -EINVAL;
+	}
+
+	arg->arg.buf = FIELD_PREP(NSP_BUFFER_CPP, cpp_id >> 8) |
+		       FIELD_PREP(NSP_BUFFER_ADDRESS, cpp_buf);
 	ret = __nfp_nsp_command(nsp, &arg->arg);
 	if (ret < 0)
 		return ret;
@@ -470,6 +474,210 @@ nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
 	return ret;
 }
 
+static int
+nfp_nsp_command_buf_dma_sg(struct nfp_nsp *nsp,
+			   struct nfp_nsp_command_buf_arg *arg,
+			   unsigned int max_size, unsigned int chunk_order,
+			   unsigned int dma_order)
+{
+	struct nfp_cpp *cpp = nsp->cpp;
+	struct nfp_nsp_dma_buf *desc;
+	struct {
+		dma_addr_t dma_addr;
+		unsigned long len;
+		void *chunk;
+	} *chunks;
+	size_t chunk_size, dma_size;
+	dma_addr_t dma_desc;
+	struct device *dev;
+	unsigned long off;
+	int i, ret, nseg;
+	size_t desc_sz;
+
+	chunk_size = BIT_ULL(chunk_order);
+	dma_size = BIT_ULL(dma_order);
+	nseg = DIV_ROUND_UP(max_size, chunk_size);
+
+	chunks = kzalloc(array_size(sizeof(*chunks), nseg), GFP_KERNEL);
+	if (!chunks)
+		return -ENOMEM;
+
+	off = 0;
+	ret = -ENOMEM;
+	for (i = 0; i < nseg; i++) {
+		unsigned long coff;
+
+		chunks[i].chunk = kmalloc(chunk_size,
+					  GFP_KERNEL | __GFP_NOWARN);
+		if (!chunks[i].chunk)
+			goto exit_free_prev;
+
+		chunks[i].len = min_t(u64, chunk_size, max_size - off);
+
+		coff = 0;
+		if (arg->in_size > off) {
+			coff = min_t(u64, arg->in_size - off, chunk_size);
+			memcpy(chunks[i].chunk, arg->in_buf + off, coff);
+		}
+		memset(chunks[i].chunk + coff, 0, chunk_size - coff);
+
+		off += chunks[i].len;
+	}
+
+	dev = nfp_cpp_device(cpp)->parent;
+
+	for (i = 0; i < nseg; i++) {
+		dma_addr_t addr;
+
+		addr = dma_map_single(dev, chunks[i].chunk, chunks[i].len,
+				      DMA_BIDIRECTIONAL);
+		chunks[i].dma_addr = addr;
+
+		ret = dma_mapping_error(dev, addr);
+		if (ret)
+			goto exit_unmap_prev;
+
+		if (WARN_ONCE(round_down(addr, dma_size) !=
+			      round_down(addr + chunks[i].len - 1, dma_size),
+			      "unaligned DMA address: %pad %lu %zd\n",
+			      &addr, chunks[i].len, dma_size)) {
+			ret = -EFAULT;
+			i++;
+			goto exit_unmap_prev;
+		}
+	}
+
+	desc_sz = struct_size(desc, descs, nseg);
+	desc = kmalloc(desc_sz, GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto exit_unmap_all;
+	}
+
+	desc->chunk_cnt = cpu_to_le32(nseg);
+	for (i = 0; i < nseg; i++) {
+		desc->descs[i].size = cpu_to_le32(chunks[i].len);
+		desc->descs[i].addr = cpu_to_le64(chunks[i].dma_addr);
+	}
+
+	dma_desc = dma_map_single(dev, desc, desc_sz, DMA_TO_DEVICE);
+	ret = dma_mapping_error(dev, dma_desc);
+	if (ret)
+		goto exit_free_desc;
+
+	arg->arg.dma = true;
+	arg->arg.buf = dma_desc;
+	ret = __nfp_nsp_command(nsp, &arg->arg);
+	if (ret < 0)
+		goto exit_unmap_desc;
+
+	i = 0;
+	off = 0;
+	while (off < arg->out_size) {
+		unsigned int len;
+
+		len = min_t(u64, chunks[i].len, arg->out_size - off);
+		memcpy(arg->out_buf + off, chunks[i].chunk, len);
+		off += len;
+		i++;
+	}
+
+exit_unmap_desc:
+	dma_unmap_single(dev, dma_desc, desc_sz, DMA_TO_DEVICE);
+exit_free_desc:
+	kfree(desc);
+exit_unmap_all:
+	i = nseg;
+exit_unmap_prev:
+	while (--i >= 0)
+		dma_unmap_single(dev, chunks[i].dma_addr, chunks[i].len,
+				 DMA_BIDIRECTIONAL);
+	i = nseg;
+exit_free_prev:
+	while (--i >= 0)
+		kfree(chunks[i].chunk);
+	kfree(chunks);
+	if (ret < 0)
+		nfp_err(cpp, "NSP: SG DMA failed for command 0x%04x: %d (sz:%d cord:%d)\n",
+			arg->arg.code, ret, max_size, chunk_order);
+	return ret;
+}
+
+static int
+nfp_nsp_command_buf_dma(struct nfp_nsp *nsp,
+			struct nfp_nsp_command_buf_arg *arg,
+			unsigned int max_size, unsigned int dma_order)
+{
+	unsigned int chunk_order, buf_order;
+	struct nfp_cpp *cpp = nsp->cpp;
+	bool sg_ok;
+	u64 reg;
+	int err;
+
+	buf_order = order_base_2(roundup_pow_of_two(max_size));
+
+	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
+			    nfp_resource_address(nsp->res) + NFP_CAP_CMD_DMA_SG,
+			    &reg);
+	if (err < 0)
+		return err;
+	sg_ok = reg & BIT_ULL(arg->arg.code - 1);
+
+	if (!sg_ok) {
+		if (buf_order > dma_order) {
+			nfp_err(cpp, "NSP: can't service non-SG DMA for command 0x%04x\n",
+				arg->arg.code);
+			return -ENOMEM;
+		}
+		chunk_order = buf_order;
+	} else {
+		chunk_order = min_t(unsigned int, dma_order, PAGE_SHIFT);
+	}
+
+	return nfp_nsp_command_buf_dma_sg(nsp, arg, max_size, chunk_order,
+					  dma_order);
+}
+
+static int
+nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg)
+{
+	unsigned int dma_order, def_size, max_size;
+	struct nfp_cpp *cpp = nsp->cpp;
+	u64 reg;
+	int err;
+
+	if (nsp->ver.minor < 13) {
+		nfp_err(cpp, "NSP: Code 0x%04x with buffer not supported (ABI %hu.%hu)\n",
+			arg->arg.code, nsp->ver.major, nsp->ver.minor);
+		return -EOPNOTSUPP;
+	}
+
+	err = nfp_cpp_readq(cpp, nfp_resource_cpp_id(nsp->res),
+			    nfp_resource_address(nsp->res) +
+			    NSP_DFLT_BUFFER_CONFIG,
+			    &reg);
+	if (err < 0)
+		return err;
+
+	/* Zero out undefined part of the out buffer */
+	if (arg->out_buf && arg->out_size && arg->out_size > arg->in_size)
+		memset(arg->out_buf, 0, arg->out_size - arg->in_size);
+
+	max_size = max(arg->in_size, arg->out_size);
+	def_size = FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M +
+		   FIELD_GET(NSP_DFLT_BUFFER_SIZE_4KB, reg) * SZ_4K;
+	dma_order = FIELD_GET(NSP_DFLT_BUFFER_DMA_CHUNK_ORDER, reg);
+	if (def_size >= max_size) {
+		return nfp_nsp_command_buf_def(nsp, arg);
+	} else if (!dma_order) {
+		nfp_err(cpp, "NSP: default buffer too small for command 0x%04x (%u < %u)\n",
+			arg->arg.code, def_size, max_size);
+		return -EINVAL;
+	}
+
+	return nfp_nsp_command_buf_dma(nsp, arg, max_size, dma_order);
+}
+
 int nfp_nsp_wait(struct nfp_nsp *state)
 {
 	const unsigned long wait_until = jiffies + NFP_NSP_TIMEOUT_BOOT * HZ;
@@ -591,10 +799,7 @@ int nfp_nsp_write_flash(struct nfp_nsp *state, const struct firmware *fw)
 		{
 			.code		= SPCODE_NSP_WRITE_FLASH,
 			.option		= fw->size,
-			/* The flash time is specified to take a maximum of 70s
-			 * so we add an additional factor to this spec time.
-			 */
-			.timeout_sec	= 2.5 * 70,
+			.timeout_sec	= 900,
 		},
 		.in_buf		= fw->data,
 		.in_size	= fw->size,
@@ -711,3 +916,52 @@ int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size)
 
 	return 0;
 }
+
+int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size)
+{
+	struct nfp_nsp_command_buf_arg versions = {
+		{
+			.code		= SPCODE_VERSIONS,
+			.option		= min_t(u32, size, NFP_VERSIONS_SIZE),
+		},
+		.out_buf	= buf,
+		.out_size	= min_t(u32, size, NFP_VERSIONS_SIZE),
+	};
+
+	return nfp_nsp_command_buf(state, &versions);
+}
+
+const char *nfp_nsp_versions_get(enum nfp_nsp_versions id, bool flash,
+				 const u8 *buf, unsigned int size)
+{
+	static const u32 id2off[] = {
+		[NFP_VERSIONS_BSP] =	NFP_VERSIONS_BSP_OFF,
+		[NFP_VERSIONS_CPLD] =	NFP_VERSIONS_CPLD_OFF,
+		[NFP_VERSIONS_APP] =	NFP_VERSIONS_APP_OFF,
+		[NFP_VERSIONS_BUNDLE] =	NFP_VERSIONS_BUNDLE_OFF,
+		[NFP_VERSIONS_UNDI] =	NFP_VERSIONS_UNDI_OFF,
+		[NFP_VERSIONS_NCSI] =	NFP_VERSIONS_NCSI_OFF,
+		[NFP_VERSIONS_CFGR] =	NFP_VERSIONS_CFGR_OFF,
+	};
+	unsigned int field, buf_field_cnt, buf_off;
+
+	if (id >= ARRAY_SIZE(id2off) || !id2off[id])
+		return ERR_PTR(-EINVAL);
+
+	field = id * 2 + flash;
+
+	buf_field_cnt = get_unaligned_le16(buf);
+	if (buf_field_cnt <= field)
+		return ERR_PTR(-ENOENT);
+
+	buf_off = get_unaligned_le16(buf + id2off[id] + flash * 2);
+	if (!buf_off)
+		return ERR_PTR(-ENOENT);
+
+	if (buf_off >= size)
+		return ERR_PTR(-EINVAL);
+	if (strnlen(&buf[buf_off], size - buf_off) == size - buf_off)
+		return ERR_PTR(-EINVAL);
+
+	return (const char *)&buf[buf_off];
+}
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
index ff33ac54097a..bd9c358c646f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h
@@ -38,12 +38,18 @@ static inline bool nfp_nsp_has_hwinfo_lookup(struct nfp_nsp *state)
 	return nfp_nsp_get_abi_ver_minor(state) > 24;
 }
 
+static inline bool nfp_nsp_has_versions(struct nfp_nsp *state)
+{
+	return nfp_nsp_get_abi_ver_minor(state) > 27;
+}
+
 enum nfp_eth_interface {
 	NFP_INTERFACE_NONE	= 0,
 	NFP_INTERFACE_SFP	= 1,
 	NFP_INTERFACE_SFPP	= 10,
 	NFP_INTERFACE_SFP28	= 28,
 	NFP_INTERFACE_QSFP	= 40,
+	NFP_INTERFACE_RJ45	= 45,
 	NFP_INTERFACE_CXP	= 100,
 	NFP_INTERFACE_QSFP28	= 112,
 };
@@ -208,4 +214,19 @@ enum nfp_nsp_sensor_id {
 int nfp_hwmon_read_sensor(struct nfp_cpp *cpp, enum nfp_nsp_sensor_id id,
 			  long *val);
 
+#define NFP_NSP_VERSION_BUFSZ	1024 /* reasonable size, not in the ABI */
+
+enum nfp_nsp_versions {
+	NFP_VERSIONS_BSP,
+	NFP_VERSIONS_CPLD,
+	NFP_VERSIONS_APP,
+	NFP_VERSIONS_BUNDLE,
+	NFP_VERSIONS_UNDI,
+	NFP_VERSIONS_NCSI,
+	NFP_VERSIONS_CFGR,
+};
+
+int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size);
+const char *nfp_nsp_versions_get(enum nfp_nsp_versions id, bool flash,
+				 const u8 *buf, unsigned int size);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
index 802c9224bb32..311a5be25acb 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c
@@ -206,6 +206,9 @@ nfp_eth_calc_port_type(struct nfp_cpp *cpp, struct nfp_eth_table_port *entry)
 	if (entry->interface == NFP_INTERFACE_NONE) {
 		entry->port_type = PORT_NONE;
 		return;
+	} else if (entry->interface == NFP_INTERFACE_RJ45) {
+		entry->port_type = PORT_TP;
+		return;
 	}
 
 	if (entry->media == NFP_MEDIA_FIBRE)
@@ -269,8 +272,7 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp)
 		goto err;
 	}
 
-	table = kzalloc(sizeof(*table) +
-			sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL);
+	table = kzalloc(struct_size(table, ports, cnt), GFP_KERNEL);
 	if (!table)
 		goto err;
 
diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 0611f2335b4a..96f7a9818294 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -105,6 +105,12 @@
 #define NIXGE_MAX_JUMBO_FRAME_SIZE \
 	(NIXGE_JUMBO_MTU + NIXGE_HDR_SIZE + NIXGE_TRL_SIZE)
 
+enum nixge_version {
+	NIXGE_V2,
+	NIXGE_V3,
+	NIXGE_VERSION_COUNT
+};
+
 struct nixge_hw_dma_bd {
 	u32 next_lo;
 	u32 next_hi;
@@ -287,9 +293,9 @@ static int nixge_hw_dma_bd_init(struct net_device *ndev)
 	priv->rx_bd_ci = 0;
 
 	/* Allocate the Tx and Rx buffer descriptors. */
-	priv->tx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					    sizeof(*priv->tx_bd_v) * TX_BD_NUM,
-					    &priv->tx_bd_p, GFP_KERNEL);
+	priv->tx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					   sizeof(*priv->tx_bd_v) * TX_BD_NUM,
+					   &priv->tx_bd_p, GFP_KERNEL);
 	if (!priv->tx_bd_v)
 		goto out;
 
@@ -299,9 +305,9 @@ static int nixge_hw_dma_bd_init(struct net_device *ndev)
 	if (!priv->tx_skb)
 		goto out;
 
-	priv->rx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					    sizeof(*priv->rx_bd_v) * RX_BD_NUM,
-					    &priv->rx_bd_p, GFP_KERNEL);
+	priv->rx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					   sizeof(*priv->rx_bd_v) * RX_BD_NUM,
+					   &priv->rx_bd_p, GFP_KERNEL);
 	if (!priv->rx_bd_v)
 		goto out;
 
@@ -1225,11 +1231,60 @@ static void *nixge_get_nvmem_address(struct device *dev)
 	return mac;
 }
 
+/* Match table for of_platform binding */
+static const struct of_device_id nixge_dt_ids[] = {
+	{ .compatible = "ni,xge-enet-2.00", .data = (void *)NIXGE_V2 },
+	{ .compatible = "ni,xge-enet-3.00", .data = (void *)NIXGE_V3 },
+	{},
+};
+MODULE_DEVICE_TABLE(of, nixge_dt_ids);
+
+static int nixge_of_get_resources(struct platform_device *pdev)
+{
+	const struct of_device_id *of_id;
+	enum nixge_version version;
+	struct resource *ctrlres;
+	struct resource *dmares;
+	struct net_device *ndev;
+	struct nixge_priv *priv;
+
+	ndev = platform_get_drvdata(pdev);
+	priv = netdev_priv(ndev);
+	of_id = of_match_node(nixge_dt_ids, pdev->dev.of_node);
+	if (!of_id)
+		return -ENODEV;
+
+	version = (enum nixge_version)of_id->data;
+	if (version <= NIXGE_V2)
+		dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	else
+		dmares = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						      "dma");
+
+	priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares);
+	if (IS_ERR(priv->dma_regs)) {
+		netdev_err(ndev, "failed to map dma regs\n");
+		return PTR_ERR(priv->dma_regs);
+	}
+	if (version <= NIXGE_V2) {
+		priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET;
+	} else {
+		ctrlres = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						       "ctrl");
+		priv->ctrl_regs = devm_ioremap_resource(&pdev->dev, ctrlres);
+	}
+	if (IS_ERR(priv->ctrl_regs)) {
+		netdev_err(ndev, "failed to map ctrl regs\n");
+		return PTR_ERR(priv->ctrl_regs);
+	}
+	return 0;
+}
+
 static int nixge_probe(struct platform_device *pdev)
 {
+	struct device_node *mn, *phy_node;
 	struct nixge_priv *priv;
 	struct net_device *ndev;
-	struct resource *dmares;
 	const u8 *mac_addr;
 	int err;
 
@@ -1261,14 +1316,9 @@ static int nixge_probe(struct platform_device *pdev)
 	priv->dev = &pdev->dev;
 
 	netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT);
-
-	dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares);
-	if (IS_ERR(priv->dma_regs)) {
-		netdev_err(ndev, "failed to map dma regs\n");
-		return PTR_ERR(priv->dma_regs);
-	}
-	priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET;
+	err = nixge_of_get_resources(pdev);
+	if (err)
+		return err;
 	__nixge_hw_set_mac_address(ndev);
 
 	priv->tx_irq = platform_get_irq_byname(pdev, "tx");
@@ -1286,10 +1336,14 @@ static int nixge_probe(struct platform_device *pdev)
 	priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
 	priv->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
 
-	err = nixge_mdio_setup(priv, pdev->dev.of_node);
-	if (err) {
-		netdev_err(ndev, "error registering mdio bus");
-		goto free_netdev;
+	mn = of_get_child_by_name(pdev->dev.of_node, "mdio");
+	if (mn) {
+		err = nixge_mdio_setup(priv, mn);
+		of_node_put(mn);
+		if (err) {
+			netdev_err(ndev, "error registering mdio bus");
+			goto free_netdev;
+		}
 	}
 
 	priv->phy_mode = of_get_phy_mode(pdev->dev.of_node);
@@ -1299,23 +1353,33 @@ static int nixge_probe(struct platform_device *pdev)
 		goto unregister_mdio;
 	}
 
-	priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
-	if (!priv->phy_node) {
-		netdev_err(ndev, "not find \"phy-handle\" property\n");
-		err = -EINVAL;
-		goto unregister_mdio;
+	phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
+	if (!phy_node && of_phy_is_fixed_link(pdev->dev.of_node)) {
+		err = of_phy_register_fixed_link(pdev->dev.of_node);
+		if (err < 0) {
+			netdev_err(ndev, "broken fixed-link specification\n");
+			goto unregister_mdio;
+		}
+		phy_node = of_node_get(pdev->dev.of_node);
 	}
+	priv->phy_node = phy_node;
 
 	err = register_netdev(priv->ndev);
 	if (err) {
 		netdev_err(ndev, "register_netdev() error (%i)\n", err);
-		goto unregister_mdio;
+		goto free_phy;
 	}
 
 	return 0;
 
+free_phy:
+	if (of_phy_is_fixed_link(pdev->dev.of_node))
+		of_phy_deregister_fixed_link(pdev->dev.of_node);
+	of_node_put(phy_node);
+
 unregister_mdio:
-	mdiobus_unregister(priv->mii_bus);
+	if (priv->mii_bus)
+		mdiobus_unregister(priv->mii_bus);
 
 free_netdev:
 	free_netdev(ndev);
@@ -1330,20 +1394,18 @@ static int nixge_remove(struct platform_device *pdev)
 
 	unregister_netdev(ndev);
 
-	mdiobus_unregister(priv->mii_bus);
+	if (of_phy_is_fixed_link(pdev->dev.of_node))
+		of_phy_deregister_fixed_link(pdev->dev.of_node);
+	of_node_put(priv->phy_node);
+
+	if (priv->mii_bus)
+		mdiobus_unregister(priv->mii_bus);
 
 	free_netdev(ndev);
 
 	return 0;
 }
 
-/* Match table for of_platform binding */
-static const struct of_device_id nixge_dt_ids[] = {
-	{ .compatible = "ni,xge-enet-2.00", },
-	{},
-};
-MODULE_DEVICE_TABLE(of, nixge_dt_ids);
-
 static struct platform_driver nixge_driver = {
 	.probe		= nixge_probe,
 	.remove		= nixge_remove,
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index c662c6f5bee3..67bf02b0763a 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -630,7 +630,7 @@ static int w90p910_ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	if (!(w90p910_send_frame(dev, skb->data, skb->len))) {
 		ether->skb = skb;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		return 0;
 	}
 	return -EAGAIN;
diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c
index 25382f8fbb70..89d17399fb5a 100644
--- a/drivers/net/ethernet/nxp/lpc_eth.c
+++ b/drivers/net/ethernet/nxp/lpc_eth.c
@@ -280,7 +280,7 @@
 #define LPC_FCCR_MIRRORCOUNTERCURRENT(n)	((n) & 0xFFFF)
 
 /*
- * rxfliterctrl, rxfilterwolstatus, and rxfilterwolclear shared
+ * rxfilterctrl, rxfilterwolstatus, and rxfilterwolclear shared
  * register definitions
  */
 #define LPC_RXFLTRW_ACCEPTUNICAST		(1 << 0)
@@ -291,7 +291,7 @@
 #define LPC_RXFLTRW_ACCEPTPERFECT		(1 << 5)
 
 /*
- * rxfliterctrl register definitions
+ * rxfilterctrl register definitions
  */
 #define LPC_RXFLTRWSTS_MAGICPACKETENWOL		(1 << 12)
 #define LPC_RXFLTRWSTS_RXFILTERENWOL		(1 << 13)
@@ -783,8 +783,6 @@ static int lpc_mii_probe(struct net_device *ndev)
 
 	phy_set_max_speed(phydev, SPEED_100);
 
-	phydev->advertising = phydev->supported;
-
 	pldat->link = 0;
 	pldat->speed = 0;
 	pldat->duplex = -1;
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 43c0c10dfeb7..528f6b4fd16a 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -27,7 +27,6 @@
 #define DRV_VERSION     "1.01"
 const char pch_driver_version[] = DRV_VERSION;
 
-#define PCI_DEVICE_ID_INTEL_IOH1_GBE	0x8802		/* Pci device ID */
 #define PCH_GBE_MAR_ENTRIES		16
 #define PCH_GBE_SHORT_PKT		64
 #define DSC_INIT16			0xC000
@@ -37,11 +36,9 @@ const char pch_driver_version[] = DRV_VERSION;
 #define PCH_GBE_PCI_BAR			1
 #define PCH_GBE_RESERVE_MEMORY		0x200000	/* 2MB */
 
-/* Macros for ML7223 */
-#define PCI_VENDOR_ID_ROHM			0x10db
-#define PCI_DEVICE_ID_ROHM_ML7223_GBE		0x8013
+#define PCI_DEVICE_ID_INTEL_IOH1_GBE		0x8802
 
-/* Macros for ML7831 */
+#define PCI_DEVICE_ID_ROHM_ML7223_GBE		0x8013
 #define PCI_DEVICE_ID_ROHM_ML7831_GBE		0x8802
 
 #define PCH_GBE_TX_WEIGHT         64
@@ -1440,8 +1437,8 @@ pch_gbe_alloc_rx_buffers_pool(struct pch_gbe_adapter *adapter,
 
 	size = rx_ring->count * bufsz + PCH_GBE_RESERVE_MEMORY;
 	rx_ring->rx_buff_pool =
-		dma_zalloc_coherent(&pdev->dev, size,
-				    &rx_ring->rx_buff_pool_logic, GFP_KERNEL);
+		dma_alloc_coherent(&pdev->dev, size,
+				   &rx_ring->rx_buff_pool_logic, GFP_KERNEL);
 	if (!rx_ring->rx_buff_pool)
 		return -ENOMEM;
 
@@ -1755,8 +1752,8 @@ int pch_gbe_setup_tx_resources(struct pch_gbe_adapter *adapter,
 
 	tx_ring->size = tx_ring->count * (int)sizeof(struct pch_gbe_tx_desc);
 
-	tx_ring->desc = dma_zalloc_coherent(&pdev->dev, tx_ring->size,
-					    &tx_ring->dma, GFP_KERNEL);
+	tx_ring->desc = dma_alloc_coherent(&pdev->dev, tx_ring->size,
+					   &tx_ring->dma, GFP_KERNEL);
 	if (!tx_ring->desc) {
 		vfree(tx_ring->buffer_info);
 		return -ENOMEM;
@@ -1798,8 +1795,8 @@ int pch_gbe_setup_rx_resources(struct pch_gbe_adapter *adapter,
 		return -ENOMEM;
 
 	rx_ring->size = rx_ring->count * (int)sizeof(struct pch_gbe_rx_desc);
-	rx_ring->desc =	dma_zalloc_coherent(&pdev->dev, rx_ring->size,
-					    &rx_ring->dma, GFP_KERNEL);
+	rx_ring->desc =	dma_alloc_coherent(&pdev->dev, rx_ring->size,
+						  &rx_ring->dma, GFP_KERNEL);
 	if (!rx_ring->desc) {
 		vfree(rx_ring->buffer_info);
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c
index c9529c29a0a7..eee883a2aa8d 100644
--- a/drivers/net/ethernet/packetengines/hamachi.c
+++ b/drivers/net/ethernet/packetengines/hamachi.c
@@ -1337,7 +1337,7 @@ static irqreturn_t hamachi_interrupt(int irq, void *dev_instance)
 							leXX_to_cpu(hmp->tx_ring[entry].addr),
 							skb->len,
 							PCI_DMA_TODEVICE);
-						dev_kfree_skb_irq(skb);
+						dev_consume_skb_irq(skb);
 						hmp->tx_skbuff[entry] = NULL;
 					}
 					hmp->tx_ring[entry].status_n_length = 0;
diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c
index 54224d1822e3..6f8d6584f809 100644
--- a/drivers/net/ethernet/packetengines/yellowfin.c
+++ b/drivers/net/ethernet/packetengines/yellowfin.c
@@ -925,7 +925,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance)
 			/* Free the original skb. */
 			pci_unmap_single(yp->pci_dev, le32_to_cpu(yp->tx_ring[entry].addr),
 				skb->len, PCI_DMA_TODEVICE);
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 			yp->tx_skbuff[entry] = NULL;
 		}
 		if (yp->tx_full &&
@@ -983,7 +983,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance)
 				pci_unmap_single(yp->pci_dev,
 					yp->tx_ring[entry<<1].addr, skb->len,
 					PCI_DMA_TODEVICE);
-				dev_kfree_skb_irq(skb);
+				dev_consume_skb_irq(skb);
 				yp->tx_skbuff[entry] = 0;
 				/* Mark status as empty. */
 				yp->tx_status[entry].tx_errs = 0;
diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c
index 8a31a02c9f47..a5bf46310f60 100644
--- a/drivers/net/ethernet/pasemi/pasemi_mac.c
+++ b/drivers/net/ethernet/pasemi/pasemi_mac.c
@@ -401,9 +401,9 @@ static int pasemi_mac_setup_rx_resources(const struct net_device *dev)
 	if (pasemi_dma_alloc_ring(&ring->chan, RX_RING_SIZE))
 		goto out_ring_desc;
 
-	ring->buffers = dma_zalloc_coherent(&mac->dma_pdev->dev,
-					    RX_RING_SIZE * sizeof(u64),
-					    &ring->buf_dma, GFP_KERNEL);
+	ring->buffers = dma_alloc_coherent(&mac->dma_pdev->dev,
+					   RX_RING_SIZE * sizeof(u64),
+					   &ring->buf_dma, GFP_KERNEL);
 	if (!ring->buffers)
 		goto out_ring_desc;
 
@@ -1716,6 +1716,7 @@ pasemi_mac_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		err = -ENODEV;
 		goto out;
 	}
+	dma_set_mask(&mac->dma_pdev->dev, DMA_BIT_MASK(64));
 
 	mac->iob_pdev = pci_get_device(PCI_VENDOR_ID_PASEMI, 0xa001, NULL);
 	if (!mac->iob_pdev) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index d9a03aba0e02..127c89b22ef0 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -53,7 +53,7 @@
 extern const struct qed_common_ops qed_common_ops_pass;
 
 #define QED_MAJOR_VERSION		8
-#define QED_MINOR_VERSION		33
+#define QED_MINOR_VERSION		37
 #define QED_REVISION_VERSION		0
 #define QED_ENGINEERING_VERSION		20
 
@@ -296,6 +296,12 @@ enum qed_wol_support {
 	QED_WOL_SUPPORT_PME,
 };
 
+enum qed_db_rec_exec {
+	DB_REC_DRY_RUN,
+	DB_REC_REAL_DEAL,
+	DB_REC_ONCE,
+};
+
 struct qed_hw_info {
 	/* PCI personality */
 	enum qed_pci_personality personality;
@@ -425,6 +431,18 @@ struct qed_qm_info {
 	u8 num_pf_rls;
 };
 
+#define QED_OVERFLOW_BIT	1
+
+struct qed_db_recovery_info {
+	struct list_head list;
+
+	/* Lock to protect the doorbell recovery mechanism list */
+	spinlock_t lock;
+	bool dorq_attn;
+	u32 db_recovery_counter;
+	unsigned long overflow;
+};
+
 struct storm_stats {
 	u32     address;
 	u32     len;
@@ -522,6 +540,7 @@ struct qed_simd_fp_handler {
 
 enum qed_slowpath_wq_flag {
 	QED_SLOWPATH_MFW_TLV_REQ,
+	QED_SLOWPATH_PERIODIC_DB_REC,
 };
 
 struct qed_hwfn {
@@ -539,7 +558,6 @@ struct qed_hwfn {
 	u8				dp_level;
 	char				name[NAME_SIZE];
 
-	bool				first_on_engine;
 	bool				hw_init_done;
 
 	u8				num_funcs_on_engine;
@@ -640,6 +658,9 @@ struct qed_hwfn {
 	/* L2-related */
 	struct qed_l2_info *p_l2_info;
 
+	/* Mechanism for recovering from doorbell drop */
+	struct qed_db_recovery_info db_recovery_info;
+
 	/* Nvm images number and attributes */
 	struct qed_nvm_image_info nvm_info;
 
@@ -652,11 +673,12 @@ struct qed_hwfn {
 	struct delayed_work iov_task;
 	unsigned long iov_task_flags;
 #endif
-
-	struct z_stream_s		*stream;
+	struct z_stream_s *stream;
+	bool slowpath_wq_active;
 	struct workqueue_struct *slowpath_wq;
 	struct delayed_work slowpath_task;
 	unsigned long slowpath_task_flags;
+	u32 periodic_db_rec_count;
 };
 
 struct pci_params {
@@ -735,6 +757,7 @@ struct qed_dev {
 #define CHIP_BOND_ID_SHIFT              0
 
 	u8				num_engines;
+	u8				num_ports;
 	u8				num_ports_in_engine;
 	u8				num_funcs_in_port;
 
@@ -786,6 +809,9 @@ struct qed_dev {
 
 	u32				mcp_nvm_resp;
 
+	/* Recovery */
+	bool recov_in_prog;
+
 	/* Linux specific here */
 	struct  qede_dev		*edev;
 	struct  pci_dev			*pdev;
@@ -871,7 +897,6 @@ void qed_configure_vp_wfq_on_link_change(struct qed_dev *cdev,
 
 void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 int qed_device_num_engines(struct qed_dev *cdev);
-int qed_device_get_port_id(struct qed_dev *cdev);
 void qed_set_fw_mac_addr(__le16 *fw_msb,
 			 __le16 *fw_mid, __le16 *fw_lsb, u8 *mac);
 
@@ -897,6 +922,11 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
+/* doorbell recovery mechanism */
+void qed_db_recovery_dp(struct qed_hwfn *p_hwfn);
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn);
+bool qed_edpm_enabled(struct qed_hwfn *p_hwfn);
+
 /* Other Linux specific common definitions */
 #define DP_NAME(cdev) ((cdev)->name)
 
@@ -912,6 +942,10 @@ u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 	writel((u32)val, (void __iomem *)((u8 __iomem *)\
 					  (cdev->doorbells) + (db_addr)))
 
+#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %			  \
+				  qed_device_num_ports((_p_hwfn)->cdev))
+int qed_device_num_ports(struct qed_dev *cdev);
+
 /* Prototypes */
 int qed_fill_dev_info(struct qed_dev *cdev,
 		      struct qed_dev_info *dev_info);
@@ -919,6 +953,7 @@ void qed_link_update(struct qed_hwfn *hwfn, struct qed_ptt *ptt);
 u32 qed_unzip_data(struct qed_hwfn *p_hwfn,
 		   u32 input_len, u8 *input_buf,
 		   u32 max_size, u8 *unzip_buf);
+void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn);
 void qed_get_protocol_stats(struct qed_dev *cdev,
 			    enum qed_mcp_protocol_type type,
 			    union qed_mcp_protocol_stats *stats);
@@ -931,4 +966,6 @@ int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn,
 			  union qed_mfw_tlv_data *tlv_data);
 
 void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc);
+
+void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn);
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index dc1c1b616084..e61d1d905415 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -936,9 +936,9 @@ static int qed_cxt_src_t2_alloc(struct qed_hwfn *p_hwfn)
 		u32 size = min_t(u32, total_size, psz);
 		void **p_virt = &p_mngr->t2[i].p_virt;
 
-		*p_virt = dma_zalloc_coherent(&p_hwfn->cdev->pdev->dev,
-					      size, &p_mngr->t2[i].p_phys,
-					      GFP_KERNEL);
+		*p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, size,
+					     &p_mngr->t2[i].p_phys,
+					     GFP_KERNEL);
 		if (!p_mngr->t2[i].p_virt) {
 			rc = -ENOMEM;
 			goto t2_fail;
@@ -1054,8 +1054,8 @@ static int qed_ilt_blk_alloc(struct qed_hwfn *p_hwfn,
 		u32 size;
 
 		size = min_t(u32, sz_left, p_blk->real_size_in_page);
-		p_virt = dma_zalloc_coherent(&p_hwfn->cdev->pdev->dev, size,
-					     &p_phys, GFP_KERNEL);
+		p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev, size,
+					    &p_phys, GFP_KERNEL);
 		if (!p_virt)
 			return -ENOMEM;
 
@@ -2129,17 +2129,18 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks)
 					       rdma_tasks);
 		/* no need for break since RoCE coexist with Ethernet */
 	}
+	/* fall through */
 	case QED_PCI_ETH:
 	{
 		struct qed_eth_pf_params *p_params =
 		    &p_hwfn->pf_params.eth_pf_params;
 
-			if (!p_params->num_vf_cons)
-				p_params->num_vf_cons =
-				    ETH_PF_PARAMS_VF_CONS_DEFAULT;
-			qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
-						    p_params->num_cons,
-						    p_params->num_vf_cons);
+		if (!p_params->num_vf_cons)
+			p_params->num_vf_cons =
+			    ETH_PF_PARAMS_VF_CONS_DEFAULT;
+		qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH,
+					    p_params->num_cons,
+					    p_params->num_vf_cons);
 		p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters;
 		break;
 	}
@@ -2306,9 +2307,9 @@ qed_cxt_dynamic_ilt_alloc(struct qed_hwfn *p_hwfn,
 		goto out0;
 	}
 
-	p_virt = dma_zalloc_coherent(&p_hwfn->cdev->pdev->dev,
-				     p_blk->real_size_in_page, &p_phys,
-				     GFP_KERNEL);
+	p_virt = dma_alloc_coherent(&p_hwfn->cdev->pdev->dev,
+				    p_blk->real_size_in_page, &p_phys,
+				    GFP_KERNEL);
 	if (!p_virt) {
 		rc = -ENOMEM;
 		goto out1;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 88a8576ca9ce..866cdc86a3f2 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -66,6 +66,301 @@
 
 static DEFINE_SPINLOCK(qm_lock);
 
+/******************** Doorbell Recovery *******************/
+/* The doorbell recovery mechanism consists of a list of entries which represent
+ * doorbelling entities (l2 queues, roce sq/rq/cqs, the slowpath spq, etc). Each
+ * entity needs to register with the mechanism and provide the parameters
+ * describing it's doorbell, including a location where last used doorbell data
+ * can be found. The doorbell execute function will traverse the list and
+ * doorbell all of the registered entries.
+ */
+struct qed_db_recovery_entry {
+	struct list_head list_entry;
+	void __iomem *db_addr;
+	void *db_data;
+	enum qed_db_rec_width db_width;
+	enum qed_db_rec_space db_space;
+	u8 hwfn_idx;
+};
+
+/* Display a single doorbell recovery entry */
+static void qed_db_recovery_dp_entry(struct qed_hwfn *p_hwfn,
+				     struct qed_db_recovery_entry *db_entry,
+				     char *action)
+{
+	DP_VERBOSE(p_hwfn,
+		   QED_MSG_SPQ,
+		   "(%s: db_entry %p, addr %p, data %p, width %s, %s space, hwfn %d)\n",
+		   action,
+		   db_entry,
+		   db_entry->db_addr,
+		   db_entry->db_data,
+		   db_entry->db_width == DB_REC_WIDTH_32B ? "32b" : "64b",
+		   db_entry->db_space == DB_REC_USER ? "user" : "kernel",
+		   db_entry->hwfn_idx);
+}
+
+/* Doorbell address sanity (address within doorbell bar range) */
+static bool qed_db_rec_sanity(struct qed_dev *cdev,
+			      void __iomem *db_addr,
+			      enum qed_db_rec_width db_width,
+			      void *db_data)
+{
+	u32 width = (db_width == DB_REC_WIDTH_32B) ? 32 : 64;
+
+	/* Make sure doorbell address is within the doorbell bar */
+	if (db_addr < cdev->doorbells ||
+	    (u8 __iomem *)db_addr + width >
+	    (u8 __iomem *)cdev->doorbells + cdev->db_size) {
+		WARN(true,
+		     "Illegal doorbell address: %p. Legal range for doorbell addresses is [%p..%p]\n",
+		     db_addr,
+		     cdev->doorbells,
+		     (u8 __iomem *)cdev->doorbells + cdev->db_size);
+		return false;
+	}
+
+	/* ake sure doorbell data pointer is not null */
+	if (!db_data) {
+		WARN(true, "Illegal doorbell data pointer: %p", db_data);
+		return false;
+	}
+
+	return true;
+}
+
+/* Find hwfn according to the doorbell address */
+static struct qed_hwfn *qed_db_rec_find_hwfn(struct qed_dev *cdev,
+					     void __iomem *db_addr)
+{
+	struct qed_hwfn *p_hwfn;
+
+	/* In CMT doorbell bar is split down the middle between engine 0 and enigne 1 */
+	if (cdev->num_hwfns > 1)
+		p_hwfn = db_addr < cdev->hwfns[1].doorbells ?
+		    &cdev->hwfns[0] : &cdev->hwfns[1];
+	else
+		p_hwfn = QED_LEADING_HWFN(cdev);
+
+	return p_hwfn;
+}
+
+/* Add a new entry to the doorbell recovery mechanism */
+int qed_db_recovery_add(struct qed_dev *cdev,
+			void __iomem *db_addr,
+			void *db_data,
+			enum qed_db_rec_width db_width,
+			enum qed_db_rec_space db_space)
+{
+	struct qed_db_recovery_entry *db_entry;
+	struct qed_hwfn *p_hwfn;
+
+	/* Shortcircuit VFs, for now */
+	if (IS_VF(cdev)) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV, "db recovery - skipping VF doorbell\n");
+		return 0;
+	}
+
+	/* Sanitize doorbell address */
+	if (!qed_db_rec_sanity(cdev, db_addr, db_width, db_data))
+		return -EINVAL;
+
+	/* Obtain hwfn from doorbell address */
+	p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
+
+	/* Create entry */
+	db_entry = kzalloc(sizeof(*db_entry), GFP_KERNEL);
+	if (!db_entry) {
+		DP_NOTICE(cdev, "Failed to allocate a db recovery entry\n");
+		return -ENOMEM;
+	}
+
+	/* Populate entry */
+	db_entry->db_addr = db_addr;
+	db_entry->db_data = db_data;
+	db_entry->db_width = db_width;
+	db_entry->db_space = db_space;
+	db_entry->hwfn_idx = p_hwfn->my_id;
+
+	/* Display */
+	qed_db_recovery_dp_entry(p_hwfn, db_entry, "Adding");
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_add_tail(&db_entry->list_entry, &p_hwfn->db_recovery_info.list);
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+
+	return 0;
+}
+
+/* Remove an entry from the doorbell recovery mechanism */
+int qed_db_recovery_del(struct qed_dev *cdev,
+			void __iomem *db_addr, void *db_data)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+	struct qed_hwfn *p_hwfn;
+	int rc = -EINVAL;
+
+	/* Shortcircuit VFs, for now */
+	if (IS_VF(cdev)) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV, "db recovery - skipping VF doorbell\n");
+		return 0;
+	}
+
+	/* Obtain hwfn from doorbell address */
+	p_hwfn = qed_db_rec_find_hwfn(cdev, db_addr);
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_for_each_entry(db_entry,
+			    &p_hwfn->db_recovery_info.list, list_entry) {
+		/* search according to db_data addr since db_addr is not unique (roce) */
+		if (db_entry->db_data == db_data) {
+			qed_db_recovery_dp_entry(p_hwfn, db_entry, "Deleting");
+			list_del(&db_entry->list_entry);
+			rc = 0;
+			break;
+		}
+	}
+
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+
+	if (rc == -EINVAL)
+
+		DP_NOTICE(p_hwfn,
+			  "Failed to find element in list. Key (db_data addr) was %p. db_addr was %p\n",
+			  db_data, db_addr);
+	else
+		kfree(db_entry);
+
+	return rc;
+}
+
+/* Initialize the doorbell recovery mechanism */
+static int qed_db_recovery_setup(struct qed_hwfn *p_hwfn)
+{
+	DP_VERBOSE(p_hwfn, QED_MSG_SPQ, "Setting up db recovery\n");
+
+	/* Make sure db_size was set in cdev */
+	if (!p_hwfn->cdev->db_size) {
+		DP_ERR(p_hwfn->cdev, "db_size not set\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&p_hwfn->db_recovery_info.list);
+	spin_lock_init(&p_hwfn->db_recovery_info.lock);
+	p_hwfn->db_recovery_info.db_recovery_counter = 0;
+
+	return 0;
+}
+
+/* Destroy the doorbell recovery mechanism */
+static void qed_db_recovery_teardown(struct qed_hwfn *p_hwfn)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SPQ, "Tearing down db recovery\n");
+	if (!list_empty(&p_hwfn->db_recovery_info.list)) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SPQ,
+			   "Doorbell Recovery teardown found the doorbell recovery list was not empty (Expected in disorderly driver unload (e.g. recovery) otherwise this probably means some flow forgot to db_recovery_del). Prepare to purge doorbell recovery list...\n");
+		while (!list_empty(&p_hwfn->db_recovery_info.list)) {
+			db_entry =
+			    list_first_entry(&p_hwfn->db_recovery_info.list,
+					     struct qed_db_recovery_entry,
+					     list_entry);
+			qed_db_recovery_dp_entry(p_hwfn, db_entry, "Purging");
+			list_del(&db_entry->list_entry);
+			kfree(db_entry);
+		}
+	}
+	p_hwfn->db_recovery_info.db_recovery_counter = 0;
+}
+
+/* Print the content of the doorbell recovery mechanism */
+void qed_db_recovery_dp(struct qed_hwfn *p_hwfn)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+
+	DP_NOTICE(p_hwfn,
+		  "Displaying doorbell recovery database. Counter was %d\n",
+		  p_hwfn->db_recovery_info.db_recovery_counter);
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_for_each_entry(db_entry,
+			    &p_hwfn->db_recovery_info.list, list_entry) {
+		qed_db_recovery_dp_entry(p_hwfn, db_entry, "Printing");
+	}
+
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+}
+
+/* Ring the doorbell of a single doorbell recovery entry */
+static void qed_db_recovery_ring(struct qed_hwfn *p_hwfn,
+				 struct qed_db_recovery_entry *db_entry)
+{
+	/* Print according to width */
+	if (db_entry->db_width == DB_REC_WIDTH_32B) {
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "ringing doorbell address %p data %x\n",
+			   db_entry->db_addr,
+			   *(u32 *)db_entry->db_data);
+	} else {
+		DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
+			   "ringing doorbell address %p data %llx\n",
+			   db_entry->db_addr,
+			   *(u64 *)(db_entry->db_data));
+	}
+
+	/* Sanity */
+	if (!qed_db_rec_sanity(p_hwfn->cdev, db_entry->db_addr,
+			       db_entry->db_width, db_entry->db_data))
+		return;
+
+	/* Flush the write combined buffer. Since there are multiple doorbelling
+	 * entities using the same address, if we don't flush, a transaction
+	 * could be lost.
+	 */
+	wmb();
+
+	/* Ring the doorbell */
+	if (db_entry->db_width == DB_REC_WIDTH_32B)
+		DIRECT_REG_WR(db_entry->db_addr,
+			      *(u32 *)(db_entry->db_data));
+	else
+		DIRECT_REG_WR64(db_entry->db_addr,
+				*(u64 *)(db_entry->db_data));
+
+	/* Flush the write combined buffer. Next doorbell may come from a
+	 * different entity to the same address...
+	 */
+	wmb();
+}
+
+/* Traverse the doorbell recovery entry list and ring all the doorbells */
+void qed_db_recovery_execute(struct qed_hwfn *p_hwfn)
+{
+	struct qed_db_recovery_entry *db_entry = NULL;
+
+	DP_NOTICE(p_hwfn, "Executing doorbell recovery. Counter was %d\n",
+		  p_hwfn->db_recovery_info.db_recovery_counter);
+
+	/* Track amount of times recovery was executed */
+	p_hwfn->db_recovery_info.db_recovery_counter++;
+
+	/* Protect the list */
+	spin_lock_bh(&p_hwfn->db_recovery_info.lock);
+	list_for_each_entry(db_entry,
+			    &p_hwfn->db_recovery_info.list, list_entry)
+		qed_db_recovery_ring(p_hwfn, db_entry);
+	spin_unlock_bh(&p_hwfn->db_recovery_info.lock);
+}
+
+/******************** Doorbell Recovery end ****************/
+
 #define QED_MIN_DPIS            (4)
 #define QED_MIN_PWM_REGION      (QED_WID_SIZE * QED_MIN_DPIS)
 
@@ -194,6 +489,9 @@ void qed_resc_free(struct qed_dev *cdev)
 		qed_dmae_info_free(p_hwfn);
 		qed_dcbx_info_free(p_hwfn);
 		qed_dbg_user_data_free(p_hwfn);
+
+		/* Destroy doorbell recovery mechanism */
+		qed_db_recovery_teardown(p_hwfn);
 	}
 }
 
@@ -480,19 +778,19 @@ static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
 
 /* get pq index according to PQ_FLAGS */
 static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
-					   u32 pq_flags)
+					   unsigned long pq_flags)
 {
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
 
 	/* Can't have multiple flags set here */
-	if (bitmap_weight((unsigned long *)&pq_flags,
+	if (bitmap_weight(&pq_flags,
 			  sizeof(pq_flags) * BITS_PER_BYTE) > 1) {
-		DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags);
+		DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags);
 		goto err;
 	}
 
 	if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) {
-		DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags);
+		DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags);
 		goto err;
 	}
 
@@ -969,6 +1267,11 @@ int qed_resc_alloc(struct qed_dev *cdev)
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
 		u32 n_eqes, num_cons;
 
+		/* Initialize the doorbell recovery mechanism */
+		rc = qed_db_recovery_setup(p_hwfn);
+		if (rc)
+			goto alloc_err;
+
 		/* First allocate the context manager structure */
 		rc = qed_cxt_mngr_alloc(p_hwfn);
 		if (rc)
@@ -1468,6 +1771,14 @@ enum QED_ROCE_EDPM_MODE {
 	QED_ROCE_EDPM_MODE_DISABLE = 2,
 };
 
+bool qed_edpm_enabled(struct qed_hwfn *p_hwfn)
+{
+	if (p_hwfn->dcbx_no_edpm || p_hwfn->db_bar_no_edpm)
+		return false;
+
+	return true;
+}
+
 static int
 qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
@@ -1537,13 +1848,13 @@ qed_hw_init_pf_doorbell_bar(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	p_hwfn->wid_count = (u16) n_cpus;
 
 	DP_INFO(p_hwfn,
-		"doorbell bar: normal_region_size=%d, pwm_region_size=%d, dpi_size=%d, dpi_count=%d, roce_edpm=%s\n",
+		"doorbell bar: normal_region_size=%d, pwm_region_size=%d, dpi_size=%d, dpi_count=%d, roce_edpm=%s, page_size=%lu\n",
 		norm_regsize,
 		pwm_regsize,
 		p_hwfn->dpi_size,
 		p_hwfn->dpi_count,
-		((p_hwfn->dcbx_no_edpm) || (p_hwfn->db_bar_no_edpm)) ?
-		"disabled" : "enabled");
+		(!qed_edpm_enabled(p_hwfn)) ?
+		"disabled" : "enabled", PAGE_SIZE);
 
 	if (rc) {
 		DP_ERR(p_hwfn,
@@ -1631,11 +1942,6 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 		     (p_hwfn->hw_info.personality == QED_PCI_FCOE) ? 1 : 0);
 	STORE_RT_REG(p_hwfn, PRS_REG_SEARCH_ROCE_RT_OFFSET, 0);
 
-	/* Cleanup chip from previous driver if such remains exist */
-	rc = qed_final_cleanup(p_hwfn, p_ptt, rel_pf_id, false);
-	if (rc)
-		return rc;
-
 	/* Sanity check before the PF init sequence that uses DMAE */
 	rc = qed_dmae_sanity(p_hwfn, p_ptt, "pf_phase");
 	if (rc)
@@ -1679,17 +1985,15 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-static int qed_change_pci_hwfn(struct qed_hwfn *p_hwfn,
-			       struct qed_ptt *p_ptt,
-			       u8 enable)
+int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt, bool b_enable)
 {
-	u32 delay_idx = 0, val, set_val = enable ? 1 : 0;
+	u32 delay_idx = 0, val, set_val = b_enable ? 1 : 0;
 
-	/* Change PF in PXP */
-	qed_wr(p_hwfn, p_ptt,
-	       PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
+	/* Configure the PF's internal FID_enable for master transactions */
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER, set_val);
 
-	/* wait until value is set - try for 1 second every 50us */
+	/* Wait until value is set - try for 1 second every 50us */
 	for (delay_idx = 0; delay_idx < 20000; delay_idx++) {
 		val = qed_rd(p_hwfn, p_ptt,
 			     PGLUE_B_REG_INTERNAL_PFID_ENABLE_MASTER);
@@ -1743,13 +2047,19 @@ static int qed_vf_start(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+static void qed_pglueb_clear_err(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR,
+	       BIT(p_hwfn->abs_pf_id));
+}
+
 int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 {
 	struct qed_load_req_params load_req_params;
 	u32 load_code, resp, param, drv_mb_param;
 	bool b_default_mtu = true;
 	struct qed_hwfn *p_hwfn;
-	int rc = 0, mfw_rc, i;
+	int rc = 0, i;
 	u16 ether_type;
 
 	if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) {
@@ -1764,7 +2074,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 	}
 
 	for_each_hwfn(cdev, i) {
-		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
+		p_hwfn = &cdev->hwfns[i];
 
 		/* If management didn't provide a default, set one of our own */
 		if (!p_hwfn->hw_info.mtu) {
@@ -1777,9 +2087,6 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			continue;
 		}
 
-		/* Enable DMAE in PXP */
-		rc = qed_change_pci_hwfn(p_hwfn, p_hwfn->p_main_ptt, true);
-
 		rc = qed_calc_hw_mode(p_hwfn);
 		if (rc)
 			return rc;
@@ -1816,12 +2123,43 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			   "Load request was sent. Load code: 0x%x\n",
 			   load_code);
 
+		/* Only relevant for recovery:
+		 * Clear the indication after LOAD_REQ is responded by the MFW.
+		 */
+		cdev->recov_in_prog = false;
+
 		qed_mcp_set_capabilities(p_hwfn, p_hwfn->p_main_ptt);
 
 		qed_reset_mb_shadow(p_hwfn, p_hwfn->p_main_ptt);
 
-		p_hwfn->first_on_engine = (load_code ==
-					   FW_MSG_CODE_DRV_LOAD_ENGINE);
+		/* Clean up chip from previous driver if such remains exist.
+		 * This is not needed when the PF is the first one on the
+		 * engine, since afterwards we are going to init the FW.
+		 */
+		if (load_code != FW_MSG_CODE_DRV_LOAD_ENGINE) {
+			rc = qed_final_cleanup(p_hwfn, p_hwfn->p_main_ptt,
+					       p_hwfn->rel_pf_id, false);
+			if (rc) {
+				DP_NOTICE(p_hwfn, "Final cleanup failed\n");
+				goto load_err;
+			}
+		}
+
+		/* Log and clear previous pglue_b errors if such exist */
+		qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_main_ptt);
+
+		/* Enable the PF's internal FID_enable in the PXP */
+		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_hwfn->p_main_ptt,
+						true);
+		if (rc)
+			goto load_err;
+
+		/* Clear the pglue_b was_error indication.
+		 * In E4 it must be done after the BME and the internal
+		 * FID_enable for the PF are set, since VDMs may cause the
+		 * indication to be set again.
+		 */
+		qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
 
 		switch (load_code) {
 		case FW_MSG_CODE_DRV_LOAD_ENGINE:
@@ -1852,39 +2190,29 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 			break;
 		}
 
-		if (rc)
+		if (rc) {
 			DP_NOTICE(p_hwfn,
 				  "init phase failed for loadcode 0x%x (rc %d)\n",
-				   load_code, rc);
+				  load_code, rc);
+			goto load_err;
+		}
 
-		/* ACK mfw regardless of success or failure of initialization */
-		mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				     DRV_MSG_CODE_LOAD_DONE,
-				     0, &load_code, &param);
+		rc = qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			return rc;
-		if (mfw_rc) {
-			DP_NOTICE(p_hwfn, "Failed sending LOAD_DONE command\n");
-			return mfw_rc;
-		}
-
-		/* Check if there is a DID mismatch between nvm-cfg/efuse */
-		if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
-			DP_NOTICE(p_hwfn,
-				  "warning: device configuration is not supported on this board type. The device may not function as expected.\n");
 
 		/* send DCBX attention request command */
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_DCB,
 			   "sending phony dcbx set command to trigger DCBx attention handling\n");
-		mfw_rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
-				     DRV_MSG_CODE_SET_DCBX,
-				     1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
-				     &load_code, &param);
-		if (mfw_rc) {
+		rc = qed_mcp_cmd(p_hwfn, p_hwfn->p_main_ptt,
+				 DRV_MSG_CODE_SET_DCBX,
+				 1 << DRV_MB_PARAM_DCBX_NOTIFY_SHIFT,
+				 &resp, &param);
+		if (rc) {
 			DP_NOTICE(p_hwfn,
 				  "Failed to send DCBX attention request\n");
-			return mfw_rc;
+			return rc;
 		}
 
 		p_hwfn->hw_init_done = true;
@@ -1933,6 +2261,12 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 	}
 
 	return 0;
+
+load_err:
+	/* The MFW load lock should be released also when initialization fails.
+	 */
+	qed_mcp_load_done(p_hwfn, p_hwfn->p_main_ptt);
+	return rc;
 }
 
 #define QED_HW_STOP_RETRY_LIMIT (10)
@@ -1945,6 +2279,9 @@ static void qed_hw_timers_stop(struct qed_dev *cdev,
 	qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_CONN, 0x0);
 	qed_wr(p_hwfn, p_ptt, TM_REG_PF_ENABLE_TASK, 0x0);
 
+	if (cdev->recov_in_prog)
+		return;
+
 	for (i = 0; i < QED_HW_STOP_RETRY_LIMIT; i++) {
 		if ((!qed_rd(p_hwfn, p_ptt,
 			     TM_REG_PF_SCAN_ACTIVE_CONN)) &&
@@ -2007,12 +2344,14 @@ int qed_hw_stop(struct qed_dev *cdev)
 		p_hwfn->hw_init_done = false;
 
 		/* Send unload command to MCP */
-		rc = qed_mcp_unload_req(p_hwfn, p_ptt);
-		if (rc) {
-			DP_NOTICE(p_hwfn,
-				  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
-				  rc);
-			rc2 = -EINVAL;
+		if (!cdev->recov_in_prog) {
+			rc = qed_mcp_unload_req(p_hwfn, p_ptt);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "Failed sending a UNLOAD_REQ command. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 		}
 
 		qed_slowpath_irq_sync(p_hwfn);
@@ -2054,27 +2393,31 @@ int qed_hw_stop(struct qed_dev *cdev)
 		qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_DB_ENABLE, 0);
 		qed_wr(p_hwfn, p_ptt, QM_REG_PF_EN, 0);
 
-		qed_mcp_unload_done(p_hwfn, p_ptt);
-		if (rc) {
-			DP_NOTICE(p_hwfn,
-				  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
-				  rc);
-			rc2 = -EINVAL;
+		if (!cdev->recov_in_prog) {
+			rc = qed_mcp_unload_done(p_hwfn, p_ptt);
+			if (rc) {
+				DP_NOTICE(p_hwfn,
+					  "Failed sending a UNLOAD_DONE command. rc = %d.\n",
+					  rc);
+				rc2 = -EINVAL;
+			}
 		}
 	}
 
-	if (IS_PF(cdev)) {
+	if (IS_PF(cdev) && !cdev->recov_in_prog) {
 		p_hwfn = QED_LEADING_HWFN(cdev);
 		p_ptt = QED_LEADING_HWFN(cdev)->p_main_ptt;
 
-		/* Disable DMAE in PXP - in CMT, this should only be done for
-		 * first hw-function, and only after all transactions have
-		 * stopped for all active hw-functions.
+		/* Clear the PF's internal FID_enable in the PXP.
+		 * In CMT this should only be done for first hw-function, and
+		 * only after all transactions have stopped for all active
+		 * hw-functions.
 		 */
-		rc = qed_change_pci_hwfn(p_hwfn, p_ptt, false);
+		rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
 		if (rc) {
 			DP_NOTICE(p_hwfn,
-				  "qed_change_pci_hwfn failed. rc = %d.\n", rc);
+				  "qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
+				  rc);
 			rc2 = -EINVAL;
 		}
 	}
@@ -2174,9 +2517,8 @@ static void qed_hw_hwfn_prepare(struct qed_hwfn *p_hwfn)
 		       PGLUE_B_REG_PGL_ADDR_94_F0_BB, 0);
 	}
 
-	/* Clean Previous errors if such exist */
-	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
-	       PGLUE_B_REG_WAS_ERROR_PF_31_0_CLR, 1 << p_hwfn->abs_pf_id);
+	/* Clean previous pglue_b errors if such exist */
+	qed_pglueb_clear_err(p_hwfn, p_hwfn->p_main_ptt);
 
 	/* enable internal target-read */
 	qed_wr(p_hwfn, p_hwfn->p_main_ptt,
@@ -2910,55 +3252,43 @@ static void qed_get_num_funcs(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		   p_hwfn->enabled_func_idx, p_hwfn->num_funcs_on_engine);
 }
 
-static void qed_hw_info_port_num_bb(struct qed_hwfn *p_hwfn,
-				    struct qed_ptt *p_ptt)
-{
-	u32 port_mode;
-
-	port_mode = qed_rd(p_hwfn, p_ptt, CNIG_REG_NW_PORT_MODE_BB);
-
-	if (port_mode < 3) {
-		p_hwfn->cdev->num_ports_in_engine = 1;
-	} else if (port_mode <= 5) {
-		p_hwfn->cdev->num_ports_in_engine = 2;
-	} else {
-		DP_NOTICE(p_hwfn, "PORT MODE: %d not supported\n",
-			  p_hwfn->cdev->num_ports_in_engine);
-
-		/* Default num_ports_in_engine to something */
-		p_hwfn->cdev->num_ports_in_engine = 1;
-	}
-}
-
-static void qed_hw_info_port_num_ah(struct qed_hwfn *p_hwfn,
-				    struct qed_ptt *p_ptt)
+static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
-	u32 port;
-	int i;
-
-	p_hwfn->cdev->num_ports_in_engine = 0;
+	u32 addr, global_offsize, global_addr, port_mode;
+	struct qed_dev *cdev = p_hwfn->cdev;
 
-	for (i = 0; i < MAX_NUM_PORTS_K2; i++) {
-		port = qed_rd(p_hwfn, p_ptt,
-			      CNIG_REG_NIG_PORT0_CONF_K2 + (i * 4));
-		if (port & 1)
-			p_hwfn->cdev->num_ports_in_engine++;
+	/* In CMT there is always only one port */
+	if (cdev->num_hwfns > 1) {
+		cdev->num_ports_in_engine = 1;
+		cdev->num_ports = 1;
+		return;
 	}
 
-	if (!p_hwfn->cdev->num_ports_in_engine) {
-		DP_NOTICE(p_hwfn, "All NIG ports are inactive\n");
-
-		/* Default num_ports_in_engine to something */
-		p_hwfn->cdev->num_ports_in_engine = 1;
+	/* Determine the number of ports per engine */
+	port_mode = qed_rd(p_hwfn, p_ptt, MISC_REG_PORT_MODE);
+	switch (port_mode) {
+	case 0x0:
+		cdev->num_ports_in_engine = 1;
+		break;
+	case 0x1:
+		cdev->num_ports_in_engine = 2;
+		break;
+	case 0x2:
+		cdev->num_ports_in_engine = 4;
+		break;
+	default:
+		DP_NOTICE(p_hwfn, "Unknown port mode 0x%08x\n", port_mode);
+		cdev->num_ports_in_engine = 1;	/* Default to something */
+		break;
 	}
-}
 
-static void qed_hw_info_port_num(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
-{
-	if (QED_IS_BB(p_hwfn->cdev))
-		qed_hw_info_port_num_bb(p_hwfn, p_ptt);
-	else
-		qed_hw_info_port_num_ah(p_hwfn, p_ptt);
+	/* Get the total number of ports of the device */
+	addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base,
+				    PUBLIC_GLOBAL);
+	global_offsize = qed_rd(p_hwfn, p_ptt, addr);
+	global_addr = SECTION_ADDR(global_offsize, 0);
+	addr = global_addr + offsetof(struct public_global, max_ports);
+	cdev->num_ports = (u8)qed_rd(p_hwfn, p_ptt, addr);
 }
 
 static void qed_get_eee_caps(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
@@ -2996,7 +3326,8 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 			return rc;
 	}
 
-	qed_hw_info_port_num(p_hwfn, p_ptt);
+	if (IS_LEAD_HWFN(p_hwfn))
+		qed_hw_info_port_num(p_hwfn, p_ptt);
 
 	qed_mcp_get_capabilities(p_hwfn, p_ptt);
 
@@ -3112,6 +3443,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 				 void __iomem *p_doorbells,
 				 enum qed_pci_personality personality)
 {
+	struct qed_dev *cdev = p_hwfn->cdev;
 	int rc = 0;
 
 	/* Split PCI bars evenly between hwfns */
@@ -3164,7 +3496,7 @@ static int qed_hw_prepare_single(struct qed_hwfn *p_hwfn,
 	/* Sending a mailbox to the MFW should be done after qed_get_hw_info()
 	 * is called as it sets the ports number in an engine.
 	 */
-	if (IS_LEAD_HWFN(p_hwfn)) {
+	if (IS_LEAD_HWFN(p_hwfn) && !cdev->recov_in_prog) {
 		rc = qed_mcp_initiate_pf_flr(p_hwfn, p_hwfn->p_main_ptt);
 		if (rc)
 			DP_NOTICE(p_hwfn, "Failed to initiate PF FLR\n");
@@ -4400,23 +4732,9 @@ void qed_clean_wfq_db(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	       sizeof(*p_hwfn->qm_info.wfq_data) * p_hwfn->qm_info.num_vports);
 }
 
-int qed_device_num_engines(struct qed_dev *cdev)
-{
-	return QED_IS_BB(cdev) ? 2 : 1;
-}
-
-static int qed_device_num_ports(struct qed_dev *cdev)
-{
-	/* in CMT always only one port */
-	if (cdev->num_hwfns > 1)
-		return 1;
-
-	return cdev->num_ports_in_engine * qed_device_num_engines(cdev);
-}
-
-int qed_device_get_port_id(struct qed_dev *cdev)
+int qed_device_num_ports(struct qed_dev *cdev)
 {
-	return (QED_LEADING_HWFN(cdev)->abs_pf_id) % qed_device_num_ports(cdev);
+	return cdev->num_ports;
 }
 
 void qed_set_fw_mac_addr(__le16 *fw_msb,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
index defdda1ffaa2..e4b4e3b78e8a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev_api.h
@@ -472,6 +472,46 @@ int qed_get_queue_coalesce(struct qed_hwfn *p_hwfn, u16 *coal, void *handle);
 int
 qed_set_queue_coalesce(u16 rx_coal, u16 tx_coal, void *p_handle);
 
+/**
+ * @brief qed_pglueb_set_pfid_enable - Enable or disable PCI BUS MASTER
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ * @param b_enable - true/false
+ *
+ * @return int
+ */
+int qed_pglueb_set_pfid_enable(struct qed_hwfn *p_hwfn,
+			       struct qed_ptt *p_ptt, bool b_enable);
+
+/**
+ * @brief db_recovery_add - add doorbell information to the doorbell
+ * recovery mechanism.
+ *
+ * @param cdev
+ * @param db_addr - doorbell address
+ * @param db_data - address of where db_data is stored
+ * @param db_width - doorbell is 32b pr 64b
+ * @param db_space - doorbell recovery addresses are user or kernel space
+ */
+int qed_db_recovery_add(struct qed_dev *cdev,
+			void __iomem *db_addr,
+			void *db_data,
+			enum qed_db_rec_width db_width,
+			enum qed_db_rec_space db_space);
+
+/**
+ * @brief db_recovery_del - remove doorbell information from the doorbell
+ * recovery mechanism. db_data serves as key (db_addr is not unique).
+ *
+ * @param cdev
+ * @param db_addr - doorbell address
+ * @param db_data - address where db_data is stored. Serves as key for the
+ *                  entry to delete.
+ */
+int qed_db_recovery_del(struct qed_dev *cdev,
+			void __iomem *db_addr, void *db_data);
+
 
 const char *qed_hw_get_resc_name(enum qed_resources res_id);
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index b38e12c9de9d..37edaa847512 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12655,6 +12655,7 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_DCBX_NOTIFY_MASK		0x000000FF
 #define DRV_MB_PARAM_DCBX_NOTIFY_SHIFT		3
 
+#define DRV_MB_PARAM_NVM_PUT_FILE_BEGIN_MBI     0x3
 #define DRV_MB_PARAM_NVM_LEN_OFFSET		24
 
 #define DRV_MB_PARAM_CFG_VF_MSIX_VF_ID_SHIFT	0
@@ -12795,6 +12796,7 @@ struct public_drv_mb {
 #define FW_MB_PARAM_GET_PF_RDMA_BOTH		0x3
 
 /* get MFW feature support response */
+#define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ	0x00000001
 #define FW_MB_PARAM_FEATURE_SUPPORT_EEE		0x00000002
 #define FW_MB_PARAM_FEATURE_SUPPORT_VLINK	0x00010000
 
@@ -12814,6 +12816,11 @@ struct public_drv_mb {
 	union drv_union_data union_data;
 };
 
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET_MASK	0x00ffffff
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET_SHIFT	0
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_SIZE_MASK		0xff000000
+#define FW_MB_PARAM_NVM_PUT_FILE_REQ_SIZE_SHIFT		24
+
 enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_LINK_CHANGE,
 	MFW_DRV_MSG_FLR_FW_ACK_FAILED,
@@ -12821,7 +12828,7 @@ enum MFW_DRV_MSG_TYPE {
 	MFW_DRV_MSG_LLDP_DATA_UPDATED,
 	MFW_DRV_MSG_DCBX_REMOTE_MIB_UPDATED,
 	MFW_DRV_MSG_DCBX_OPERATIONAL_MIB_UPDATED,
-	MFW_DRV_MSG_RESERVED4,
+	MFW_DRV_MSG_ERROR_RECOVERY,
 	MFW_DRV_MSG_BW_UPDATE,
 	MFW_DRV_MSG_S_TAG_UPDATE,
 	MFW_DRV_MSG_GET_LAN_STATS,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_hw.c b/drivers/net/ethernet/qlogic/qed/qed_hw.c
index 70504dcf4087..72ec1c6bdf70 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hw.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_hw.c
@@ -703,6 +703,17 @@ static int qed_dmae_execute_command(struct qed_hwfn *p_hwfn,
 	int qed_status = 0;
 	u32 offset = 0;
 
+	if (p_hwfn->cdev->recov_in_prog) {
+		DP_VERBOSE(p_hwfn,
+			   NETIF_MSG_HW,
+			   "Recovery is in progress. Avoid DMAE transaction [{src: addr 0x%llx, type %d}, {dst: addr 0x%llx, type %d}, size %d].\n",
+			   src_addr, src_type, dst_addr, dst_type,
+			   size_in_dwords);
+
+		/* Let the flow complete w/o any error handling */
+		return 0;
+	}
+
 	qed_dmae_opcode(p_hwfn,
 			(src_type == QED_DMAE_ADDRESS_GRC),
 			(dst_type == QED_DMAE_ADDRESS_GRC),
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c
index b22f464ea3fa..8848d5bed6e5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.c
@@ -255,138 +255,298 @@ out:
 #define PGLUE_ATTENTION_ICPL_VALID		(1 << 23)
 #define PGLUE_ATTENTION_ZLR_VALID		(1 << 25)
 #define PGLUE_ATTENTION_ILT_VALID		(1 << 23)
-static int qed_pglub_rbc_attn_cb(struct qed_hwfn *p_hwfn)
+
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt)
 {
 	u32 tmp;
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_WR_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_VALID) {
 		u32 addr_lo, addr_hi, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_WR_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"Illegal write by chip to [%08x:%08x] blocked.\n"
-			"Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			"Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			addr_hi, addr_lo, details,
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			GET_FIELD(details,
-				  PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			tmp,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			GET_FIELD(tmp,
-				  PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
+		DP_NOTICE(p_hwfn,
+			  "Illegal write by chip to [%08x:%08x] blocked.\n"
+			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
+			  addr_hi, addr_lo, details,
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			  GET_FIELD(details,
+				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
+			  tmp,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_RD_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_RD_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_RD_VALID) {
 		u32 addr_lo, addr_hi, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_TX_ERR_RD_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"Illegal read by chip from [%08x:%08x] blocked.\n"
-			" Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
-			" Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
-			addr_hi, addr_lo, details,
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
-			(u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
-			GET_FIELD(details,
-				  PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
-			tmp,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1
-									 : 0,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
-			GET_FIELD(tmp, PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1
-									: 0);
+		DP_NOTICE(p_hwfn,
+			  "Illegal read by chip from [%08x:%08x] blocked.\n"
+			  "Details: %08x [PFID %02x, VFID %02x, VF_VALID %02x]\n"
+			  "Details2 %08x [Was_error %02x BME deassert %02x FID_enable deassert %02x]\n",
+			  addr_hi, addr_lo, details,
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_PFID),
+			  (u8)GET_FIELD(details, PGLUE_ATTENTION_DETAILS_VFID),
+			  GET_FIELD(details,
+				    PGLUE_ATTENTION_DETAILS_VF_VALID) ? 1 : 0,
+			  tmp,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_WAS_ERR) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_BME) ? 1 : 0,
+			  GET_FIELD(tmp,
+				    PGLUE_ATTENTION_DETAILS2_FID_EN) ? 1 : 0);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_TX_ERR_WR_DETAILS_ICPL);
 	if (tmp & PGLUE_ATTENTION_ICPL_VALID)
-		DP_INFO(p_hwfn, "ICPL error - %08x\n", tmp);
+		DP_NOTICE(p_hwfn, "ICPL error - %08x\n", tmp);
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_MASTER_ZLR_ERR_DETAILS);
 	if (tmp & PGLUE_ATTENTION_ZLR_VALID) {
 		u32 addr_hi, addr_lo;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_MASTER_ZLR_ERR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_MASTER_ZLR_ERR_ADD_63_32);
 
-		DP_INFO(p_hwfn, "ZLR eror - %08x [Address %08x:%08x]\n",
-			tmp, addr_hi, addr_lo);
+		DP_NOTICE(p_hwfn, "ZLR error - %08x [Address %08x:%08x]\n",
+			  tmp, addr_hi, addr_lo);
 	}
 
-	tmp = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-		     PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
+	tmp = qed_rd(p_hwfn, p_ptt, PGLUE_B_REG_VF_ILT_ERR_DETAILS2);
 	if (tmp & PGLUE_ATTENTION_ILT_VALID) {
 		u32 addr_hi, addr_lo, details;
 
-		addr_lo = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_lo = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_ADD_31_0);
-		addr_hi = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		addr_hi = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_ADD_63_32);
-		details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
+		details = qed_rd(p_hwfn, p_ptt,
 				 PGLUE_B_REG_VF_ILT_ERR_DETAILS);
 
-		DP_INFO(p_hwfn,
-			"ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
-			details, tmp, addr_hi, addr_lo);
+		DP_NOTICE(p_hwfn,
+			  "ILT error - Details %08x Details2 %08x [Address %08x:%08x]\n",
+			  details, tmp, addr_hi, addr_lo);
 	}
 
 	/* Clear the indications */
-	qed_wr(p_hwfn, p_hwfn->p_dpc_ptt,
-	       PGLUE_B_REG_LATCHED_ERRORS_CLR, (1 << 2));
+	qed_wr(p_hwfn, p_ptt, PGLUE_B_REG_LATCHED_ERRORS_CLR, BIT(2));
 
 	return 0;
 }
 
-#define QED_DORQ_ATTENTION_REASON_MASK	(0xfffff)
-#define QED_DORQ_ATTENTION_OPAQUE_MASK (0xffff)
-#define QED_DORQ_ATTENTION_SIZE_MASK	(0x7f)
-#define QED_DORQ_ATTENTION_SIZE_SHIFT	(16)
-static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+static int qed_pglueb_rbc_attn_cb(struct qed_hwfn *p_hwfn)
 {
-	u32 reason;
+	return qed_pglueb_rbc_attn_handler(p_hwfn, p_hwfn->p_dpc_ptt);
+}
 
-	reason = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt, DORQ_REG_DB_DROP_REASON) &
-			QED_DORQ_ATTENTION_REASON_MASK;
-	if (reason) {
-		u32 details = qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-				     DORQ_REG_DB_DROP_DETAILS);
+#define QED_DORQ_ATTENTION_REASON_MASK  (0xfffff)
+#define QED_DORQ_ATTENTION_OPAQUE_MASK  (0xffff)
+#define QED_DORQ_ATTENTION_OPAQUE_SHIFT (0x0)
+#define QED_DORQ_ATTENTION_SIZE_MASK            (0x7f)
+#define QED_DORQ_ATTENTION_SIZE_SHIFT           (16)
 
-		DP_INFO(p_hwfn->cdev,
-			"DORQ db_drop: address 0x%08x Opaque FID 0x%04x Size [bytes] 0x%08x Reason: 0x%08x\n",
-			qed_rd(p_hwfn, p_hwfn->p_dpc_ptt,
-			       DORQ_REG_DB_DROP_DETAILS_ADDRESS),
-			(u16)(details & QED_DORQ_ATTENTION_OPAQUE_MASK),
-			GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
-			reason);
+#define QED_DB_REC_COUNT                        1000
+#define QED_DB_REC_INTERVAL                     100
+
+static int qed_db_rec_flush_queue(struct qed_hwfn *p_hwfn,
+				  struct qed_ptt *p_ptt)
+{
+	u32 count = QED_DB_REC_COUNT;
+	u32 usage = 1;
+
+	/* Flush any pending (e)dpms as they may never arrive */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_DPM_FORCE_ABORT, 0x1);
+
+	/* wait for usage to zero or count to run out. This is necessary since
+	 * EDPM doorbell transactions can take multiple 64b cycles, and as such
+	 * can "split" over the pci. Possibly, the doorbell drop can happen with
+	 * half an EDPM in the queue and other half dropped. Another EDPM
+	 * doorbell to the same address (from doorbell recovery mechanism or
+	 * from the doorbelling entity) could have first half dropped and second
+	 * half interpreted as continuation of the first. To prevent such
+	 * malformed doorbells from reaching the device, flush the queue before
+	 * releasing the overflow sticky indication.
+	 */
+	while (count-- && usage) {
+		usage = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_USAGE_CNT);
+		udelay(QED_DB_REC_INTERVAL);
+	}
+
+	/* should have been depleted by now */
+	if (usage) {
+		DP_NOTICE(p_hwfn->cdev,
+			  "DB recovery: doorbell usage failed to zero after %d usec. usage was %x\n",
+			  QED_DB_REC_INTERVAL * QED_DB_REC_COUNT, usage);
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 attn_ovfl, cur_ovfl;
+	int rc;
+
+	attn_ovfl = test_and_clear_bit(QED_OVERFLOW_BIT,
+				       &p_hwfn->db_recovery_info.overflow);
+	cur_ovfl = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!cur_ovfl && !attn_ovfl)
+		return 0;
+
+	DP_NOTICE(p_hwfn, "PF Overflow sticky: attn %u current %u\n",
+		  attn_ovfl, cur_ovfl);
+
+	if (cur_ovfl && !p_hwfn->db_bar_no_edpm) {
+		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+		if (rc)
+			return rc;
 	}
 
+	/* Release overflow sticky indication (stop silently dropping everything) */
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+
+	/* Repeat all last doorbells (doorbell drop recovery) */
+	qed_db_recovery_execute(p_hwfn);
+
+	return 0;
+}
+
+static void qed_dorq_attn_overflow(struct qed_hwfn *p_hwfn)
+{
+	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+	u32 overflow;
+	int rc;
+
+	overflow = qed_rd(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY);
+	if (!overflow)
+		goto out;
+
+	/* Run PF doorbell recovery in next periodic handler */
+	set_bit(QED_OVERFLOW_BIT, &p_hwfn->db_recovery_info.overflow);
+
+	if (!p_hwfn->db_bar_no_edpm) {
+		rc = qed_db_rec_flush_queue(p_hwfn, p_ptt);
+		if (rc)
+			goto out;
+	}
+
+	qed_wr(p_hwfn, p_ptt, DORQ_REG_PF_OVFL_STICKY, 0x0);
+out:
+	/* Schedule the handler even if overflow was not detected */
+	qed_periodic_db_rec_start(p_hwfn);
+}
+
+static int qed_dorq_attn_int_sts(struct qed_hwfn *p_hwfn)
+{
+	u32 int_sts, first_drop_reason, details, address, all_drops_reason;
+	struct qed_ptt *p_ptt = p_hwfn->p_dpc_ptt;
+
+	/* int_sts may be zero since all PFs were interrupted for doorbell
+	 * overflow but another one already handled it. Can abort here. If
+	 * This PF also requires overflow recovery we will be interrupted again.
+	 * The masked almost full indication may also be set. Ignoring.
+	 */
+	int_sts = qed_rd(p_hwfn, p_ptt, DORQ_REG_INT_STS);
+	if (!(int_sts & ~DORQ_REG_INT_STS_DORQ_FIFO_AFULL))
+		return 0;
+
+	DP_NOTICE(p_hwfn->cdev, "DORQ attention. int_sts was %x\n", int_sts);
+
+	/* check if db_drop or overflow happened */
+	if (int_sts & (DORQ_REG_INT_STS_DB_DROP |
+		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR)) {
+		/* Obtain data about db drop/overflow */
+		first_drop_reason = qed_rd(p_hwfn, p_ptt,
+					   DORQ_REG_DB_DROP_REASON) &
+		    QED_DORQ_ATTENTION_REASON_MASK;
+		details = qed_rd(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS);
+		address = qed_rd(p_hwfn, p_ptt,
+				 DORQ_REG_DB_DROP_DETAILS_ADDRESS);
+		all_drops_reason = qed_rd(p_hwfn, p_ptt,
+					  DORQ_REG_DB_DROP_DETAILS_REASON);
+
+		/* Log info */
+		DP_NOTICE(p_hwfn->cdev,
+			  "Doorbell drop occurred\n"
+			  "Address\t\t0x%08x\t(second BAR address)\n"
+			  "FID\t\t0x%04x\t\t(Opaque FID)\n"
+			  "Size\t\t0x%04x\t\t(in bytes)\n"
+			  "1st drop reason\t0x%08x\t(details on first drop since last handling)\n"
+			  "Sticky reasons\t0x%08x\t(all drop reasons since last handling)\n",
+			  address,
+			  GET_FIELD(details, QED_DORQ_ATTENTION_OPAQUE),
+			  GET_FIELD(details, QED_DORQ_ATTENTION_SIZE) * 4,
+			  first_drop_reason, all_drops_reason);
+
+		/* Clear the doorbell drop details and prepare for next drop */
+		qed_wr(p_hwfn, p_ptt, DORQ_REG_DB_DROP_DETAILS_REL, 0);
+
+		/* Mark interrupt as handled (note: even if drop was due to a different
+		 * reason than overflow we mark as handled)
+		 */
+		qed_wr(p_hwfn,
+		       p_ptt,
+		       DORQ_REG_INT_STS_WR,
+		       DORQ_REG_INT_STS_DB_DROP |
+		       DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR);
+
+		/* If there are no indications other than drop indications, success */
+		if ((int_sts & ~(DORQ_REG_INT_STS_DB_DROP |
+				 DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR |
+				 DORQ_REG_INT_STS_DORQ_FIFO_AFULL)) == 0)
+			return 0;
+	}
+
+	/* Some other indication was present - non recoverable */
+	DP_INFO(p_hwfn, "DORQ fatal attention\n");
+
 	return -EINVAL;
 }
 
+static int qed_dorq_attn_cb(struct qed_hwfn *p_hwfn)
+{
+	p_hwfn->db_recovery_info.dorq_attn = true;
+	qed_dorq_attn_overflow(p_hwfn);
+
+	return qed_dorq_attn_int_sts(p_hwfn);
+}
+
+static void qed_dorq_attn_handler(struct qed_hwfn *p_hwfn)
+{
+	if (p_hwfn->db_recovery_info.dorq_attn)
+		goto out;
+
+	/* Call DORQ callback if the attention was missed */
+	qed_dorq_attn_cb(p_hwfn);
+out:
+	p_hwfn->db_recovery_info.dorq_attn = false;
+}
+
 /* Instead of major changes to the data-structure, we have a some 'special'
  * identifiers for sources that changed meaning between adapters.
  */
@@ -422,7 +582,7 @@ static struct aeu_invert_reg aeu_descs[NUM_ATTN_REGS] = {
 			{"PGLUE misc_flr", ATTENTION_SINGLE,
 			 NULL, MAX_BLOCK_ID},
 			{"PGLUE B RBC", ATTENTION_PAR_INT,
-			 qed_pglub_rbc_attn_cb, BLOCK_PGLUE_B},
+			 qed_pglueb_rbc_attn_cb, BLOCK_PGLUE_B},
 			{"PGLUE misc_mctp", ATTENTION_SINGLE,
 			 NULL, MAX_BLOCK_ID},
 			{"Flash event", ATTENTION_SINGLE, NULL, MAX_BLOCK_ID},
@@ -960,6 +1120,9 @@ static int qed_int_deassertion(struct qed_hwfn  *p_hwfn,
 		}
 	}
 
+	/* Handle missed DORQ attention */
+	qed_dorq_attn_handler(p_hwfn);
+
 	/* Clear IGU indication for the deasserted bits */
 	DIRECT_REG_WR((u8 __iomem *)p_hwfn->regview +
 				    GTT_BAR0_MAP_REG_IGU_CMD +
diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.h b/drivers/net/ethernet/qlogic/qed/qed_int.h
index 54b4ee0acfd7..d473b522afc5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_int.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_int.h
@@ -190,6 +190,16 @@ void qed_int_get_num_sbs(struct qed_hwfn	*p_hwfn,
  */
 void qed_int_disable_post_isr_release(struct qed_dev *cdev);
 
+/**
+ * @brief - Doorbell Recovery handler.
+ *          Run doorbell recovery in case of PF overflow (and flush DORQ if
+ *          needed).
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ */
+int qed_db_rec_handler(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
 #define QED_CAU_DEF_RX_TIMER_RES 0
 #define QED_CAU_DEF_TX_TIMER_RES 0
 
@@ -421,4 +431,7 @@ int qed_int_set_timer_res(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
 
 #define QED_MAPPING_MEMORY_SIZE(dev)	(NUM_OF_SBS(dev))
 
+int qed_pglueb_rbc_attn_handler(struct qed_hwfn *p_hwfn,
+				struct qed_ptt *p_ptt);
+
 #endif
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index beb8e5d6401a..ded556b7bab5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -1688,6 +1688,15 @@ qed_iwarp_parse_rx_pkt(struct qed_hwfn *p_hwfn,
 
 	eth_hlen = ETH_HLEN + (vlan_valid ? sizeof(u32) : 0);
 
+	if (!ether_addr_equal(ethh->h_dest,
+			      p_hwfn->p_rdma_info->iwarp.mac_addr)) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_RDMA,
+			   "Got unexpected mac %pM instead of %pM\n",
+			   ethh->h_dest, p_hwfn->p_rdma_info->iwarp.mac_addr);
+		return -EINVAL;
+	}
+
 	ether_addr_copy(remote_mac_addr, ethh->h_source);
 	ether_addr_copy(local_mac_addr, ethh->h_dest);
 
@@ -2605,7 +2614,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	struct qed_iwarp_info *iwarp_info;
 	struct qed_ll2_acquire_data data;
 	struct qed_ll2_cbs cbs;
-	u32 mpa_buff_size;
+	u32 buff_size;
 	u16 n_ooo_bufs;
 	int rc = 0;
 	int i;
@@ -2632,7 +2641,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 
 	memset(&data, 0, sizeof(data));
 	data.input.conn_type = QED_LL2_TYPE_IWARP;
-	data.input.mtu = QED_IWARP_MAX_SYN_PKT_SIZE;
+	data.input.mtu = params->max_mtu;
 	data.input.rx_num_desc = QED_IWARP_LL2_SYN_RX_SIZE;
 	data.input.tx_num_desc = QED_IWARP_LL2_SYN_TX_SIZE;
 	data.input.tx_max_bds_per_packet = 1;	/* will never be fragmented */
@@ -2654,9 +2663,10 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 		goto err;
 	}
 
+	buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu);
 	rc = qed_iwarp_ll2_alloc_buffers(p_hwfn,
 					 QED_IWARP_LL2_SYN_RX_SIZE,
-					 QED_IWARP_MAX_SYN_PKT_SIZE,
+					 buff_size,
 					 iwarp_info->ll2_syn_handle);
 	if (rc)
 		goto err;
@@ -2710,10 +2720,9 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 	if (rc)
 		goto err;
 
-	mpa_buff_size = QED_IWARP_MAX_BUF_SIZE(params->max_mtu);
 	rc = qed_iwarp_ll2_alloc_buffers(p_hwfn,
 					 data.input.rx_num_desc,
-					 mpa_buff_size,
+					 buff_size,
 					 iwarp_info->ll2_mpa_handle);
 	if (rc)
 		goto err;
@@ -2726,7 +2735,7 @@ qed_iwarp_ll2_start(struct qed_hwfn *p_hwfn,
 
 	iwarp_info->max_num_partial_fpdus = (u16)p_hwfn->p_rdma_info->num_qps;
 
-	iwarp_info->mpa_intermediate_buf = kzalloc(mpa_buff_size, GFP_KERNEL);
+	iwarp_info->mpa_intermediate_buf = kzalloc(buff_size, GFP_KERNEL);
 	if (!iwarp_info->mpa_intermediate_buf)
 		goto err;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
index b8f612d00241..7ac959038324 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.h
@@ -46,7 +46,6 @@ enum qed_iwarp_qp_state qed_roce2iwarp_state(enum qed_roce_qp_state state);
 
 #define QED_IWARP_LL2_SYN_TX_SIZE       (128)
 #define QED_IWARP_LL2_SYN_RX_SIZE       (256)
-#define QED_IWARP_MAX_SYN_PKT_SIZE      (128)
 
 #define QED_IWARP_LL2_OOO_DEF_TX_SIZE   (256)
 #define QED_IWARP_MAX_OOO		(16)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 67c02ea93906..57641728df69 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -609,6 +609,10 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn,
 			  (!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) &&
 			   !!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED)));
 
+		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_BCAST_ACCEPT_ALL,
 			  !!(accept_filter & QED_ACCEPT_BCAST));
 
@@ -744,6 +748,11 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn,
 		return rc;
 	}
 
+	if (p_params->update_ctl_frame_check) {
+		p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en;
+		p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en;
+	}
+
 	/* Update mcast bins for VFs, PF doesn't use this functionality */
 	qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params);
 
@@ -1889,6 +1898,7 @@ static void _qed_get_vport_stats(struct qed_dev *cdev,
 		struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
 		struct qed_ptt *p_ptt = IS_PF(cdev) ? qed_ptt_acquire(p_hwfn)
 						    :  NULL;
+		bool b_get_port_stats;
 
 		if (IS_PF(cdev)) {
 			/* The main vport index is relative first */
@@ -1903,8 +1913,9 @@ static void _qed_get_vport_stats(struct qed_dev *cdev,
 			continue;
 		}
 
+		b_get_port_stats = IS_PF(cdev) && IS_LEAD_HWFN(p_hwfn);
 		__qed_get_vport_stats(p_hwfn, p_ptt, stats, fw_vport,
-				      IS_PF(cdev) ? true : false);
+				      b_get_port_stats);
 
 out:
 		if (IS_PF(cdev) && p_ptt)
@@ -2207,7 +2218,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 			u16 num_queues = 0;
 
 			/* Since the feature controls only queue-zones,
-			 * make sure we have the contexts [rx, tx, xdp] to
+			 * make sure we have the contexts [rx, xdp, tcs] to
 			 * match.
 			 */
 			for_each_hwfn(cdev, i) {
@@ -2217,7 +2228,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 				u16 cids;
 
 				cids = hwfn->pf_params.eth_pf_params.num_cons;
-				num_queues += min_t(u16, l2_queues, cids / 3);
+				cids /= (2 + info->num_tc);
+				num_queues += min_t(u16, l2_queues, cids);
 			}
 
 			/* queues might theoretically be >256, but interrupts'
@@ -2688,7 +2700,8 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev,
 	if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) {
 		accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED |
 						 QED_ACCEPT_MCAST_UNMATCHED;
-		accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
+		accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED |
+						 QED_ACCEPT_MCAST_UNMATCHED;
 	} else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) {
 		accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
 		accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED;
@@ -2860,7 +2873,8 @@ static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle)
 	p_hwfn = p_cid->p_owner;
 	rc = qed_get_queue_coalesce(p_hwfn, coal, handle);
 	if (rc)
-		DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n");
+		DP_VERBOSE(cdev, QED_MSG_DEBUG,
+			   "Unable to read queue coalescing\n");
 
 	return rc;
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h
index 8d80f1095d17..7127d5aaac42 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h
@@ -219,6 +219,9 @@ struct qed_sp_vport_update_params {
 	struct qed_rss_params		*rss_params;
 	struct qed_filter_accept_flags	accept_flags;
 	struct qed_sge_tpa_params	*sge_tpa_params;
+	u8				update_ctl_frame_check;
+	u8				mac_chk_en;
+	u8				ethtype_chk_en;
 };
 
 int qed_sp_vport_update(struct qed_hwfn *p_hwfn,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index c6f4bab67a5f..b5f419b71287 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -1085,7 +1085,14 @@ static int qed_sp_ll2_tx_queue_start(struct qed_hwfn *p_hwfn,
 
 	p_ramrod->gsi_offload_flag = p_ll2_conn->input.gsi_enable;
 
-	return qed_spq_post(p_hwfn, p_ent, NULL);
+	rc = qed_spq_post(p_hwfn, p_ent, NULL);
+	if (rc)
+		return rc;
+
+	rc = qed_db_recovery_add(p_hwfn->cdev, p_tx->doorbell_addr,
+				 &p_tx->db_msg, DB_REC_WIDTH_32B,
+				 DB_REC_KERNEL);
+	return rc;
 }
 
 static int qed_sp_ll2_rx_queue_stop(struct qed_hwfn *p_hwfn,
@@ -1119,9 +1126,11 @@ static int qed_sp_ll2_rx_queue_stop(struct qed_hwfn *p_hwfn,
 static int qed_sp_ll2_tx_queue_stop(struct qed_hwfn *p_hwfn,
 				    struct qed_ll2_info *p_ll2_conn)
 {
+	struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue;
 	struct qed_spq_entry *p_ent = NULL;
 	struct qed_sp_init_data init_data;
 	int rc = -EINVAL;
+	qed_db_recovery_del(p_hwfn->cdev, p_tx->doorbell_addr, &p_tx->db_msg);
 
 	/* Get SPQ entry */
 	memset(&init_data, 0, sizeof(init_data));
@@ -1542,6 +1551,13 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle)
 	p_tx->doorbell_addr = (u8 __iomem *)p_hwfn->doorbells +
 					    qed_db_addr(p_ll2_conn->cid,
 							DQ_DEMS_LEGACY);
+	/* prepare db data */
+	SET_FIELD(p_tx->db_msg.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
+	SET_FIELD(p_tx->db_msg.params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_SET);
+	SET_FIELD(p_tx->db_msg.params, CORE_DB_DATA_AGG_VAL_SEL,
+		  DQ_XCM_CORE_TX_BD_PROD_CMD);
+	p_tx->db_msg.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
+
 
 	rc = qed_ll2_establish_connection_rx(p_hwfn, p_ll2_conn);
 	if (rc)
@@ -1603,6 +1619,10 @@ static void qed_ll2_post_rx_buffer_notify_fw(struct qed_hwfn *p_hwfn,
 	cq_prod = qed_chain_get_prod_idx(&p_rx->rcq_chain);
 	rx_prod.bd_prod = cpu_to_le16(bd_prod);
 	rx_prod.cqe_prod = cpu_to_le16(cq_prod);
+
+	/* Make sure chain element is updated before ringing the doorbell */
+	dma_wmb();
+
 	DIRECT_REG_WR(p_rx->set_prod_addr, *((u32 *)&rx_prod));
 }
 
@@ -1780,7 +1800,6 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
 	bool b_notify = p_ll2_conn->tx_queue.cur_send_packet->notify_fw;
 	struct qed_ll2_tx_queue *p_tx = &p_ll2_conn->tx_queue;
 	struct qed_ll2_tx_packet *p_pkt = NULL;
-	struct core_db_data db_msg = { 0, 0, 0 };
 	u16 bd_prod;
 
 	/* If there are missing BDs, don't do anything now */
@@ -1809,24 +1828,19 @@ static void qed_ll2_tx_packet_notify(struct qed_hwfn *p_hwfn,
 		list_move_tail(&p_pkt->list_entry, &p_tx->active_descq);
 	}
 
-	SET_FIELD(db_msg.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
-	SET_FIELD(db_msg.params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_SET);
-	SET_FIELD(db_msg.params, CORE_DB_DATA_AGG_VAL_SEL,
-		  DQ_XCM_CORE_TX_BD_PROD_CMD);
-	db_msg.agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
-	db_msg.spq_prod = cpu_to_le16(bd_prod);
+	p_tx->db_msg.spq_prod = cpu_to_le16(bd_prod);
 
 	/* Make sure the BDs data is updated before ringing the doorbell */
 	wmb();
 
-	DIRECT_REG_WR(p_tx->doorbell_addr, *((u32 *)&db_msg));
+	DIRECT_REG_WR(p_tx->doorbell_addr, *((u32 *)&p_tx->db_msg));
 
 	DP_VERBOSE(p_hwfn,
 		   (NETIF_MSG_TX_QUEUED | QED_MSG_LL2),
 		   "LL2 [q 0x%02x cid 0x%08x type 0x%08x] Doorbelled [producer 0x%04x]\n",
 		   p_ll2_conn->queue_id,
 		   p_ll2_conn->cid,
-		   p_ll2_conn->input.conn_type, db_msg.spq_prod);
+		   p_ll2_conn->input.conn_type, p_tx->db_msg.spq_prod);
 }
 
 int qed_ll2_prepare_tx_packet(void *cxt,
@@ -2437,19 +2451,24 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 {
 	struct qed_ll2_tx_pkt_info pkt;
 	const skb_frag_t *frag;
+	u8 flags = 0, nr_frags;
 	int rc = -EINVAL, i;
 	dma_addr_t mapping;
 	u16 vlan = 0;
-	u8 flags = 0;
 
 	if (unlikely(skb->ip_summed != CHECKSUM_NONE)) {
 		DP_INFO(cdev, "Cannot transmit a checksummed packet\n");
 		return -EINVAL;
 	}
 
-	if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) {
+	/* Cache number of fragments from SKB since SKB may be freed by
+	 * the completion routine after calling qed_ll2_prepare_tx_packet()
+	 */
+	nr_frags = skb_shinfo(skb)->nr_frags;
+
+	if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) {
 		DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n",
-		       1 + skb_shinfo(skb)->nr_frags);
+		       1 + nr_frags);
 		return -EINVAL;
 	}
 
@@ -2471,7 +2490,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 	}
 
 	memset(&pkt, 0, sizeof(pkt));
-	pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags;
+	pkt.num_of_bds = 1 + nr_frags;
 	pkt.vlan = vlan;
 	pkt.bd_flags = flags;
 	pkt.tx_dest = QED_LL2_TX_DEST_NW;
@@ -2482,12 +2501,17 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb,
 	    test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags))
 		pkt.remove_stag = true;
 
+	/* qed_ll2_prepare_tx_packet() may actually send the packet if
+	 * there are no fragments in the skb and subsequently the completion
+	 * routine may run and free the SKB, so no dereferencing the SKB
+	 * beyond this point unless skb has any fragments.
+	 */
 	rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle,
 				       &pkt, 1);
 	if (rc)
 		goto err;
 
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+	for (i = 0; i < nr_frags; i++) {
 		frag = &skb_shinfo(skb)->frags[i];
 
 		mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.h b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
index 1a5c1ae01474..5f01fbd3c073 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.h
@@ -103,6 +103,7 @@ struct qed_ll2_tx_queue {
 	struct qed_ll2_tx_packet cur_completing_packet;
 	u16 cur_completing_bd_idx;
 	void __iomem *doorbell_addr;
+	struct core_db_data db_msg;
 	u16 bds_idx;
 	u16 cur_send_frag_num;
 	u16 cur_completing_frag_num;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index fff7f04d4525..6de23b56b294 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -281,6 +281,8 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 		if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME)
 			dev_info->wol_support = true;
 
+		dev_info->smart_an = qed_mcp_is_smart_an_supported(p_hwfn);
+
 		dev_info->abs_pf_id = QED_LEADING_HWFN(cdev)->abs_pf_id;
 	} else {
 		qed_vf_get_fw_version(&cdev->hwfns[0], &dev_info->fw_major,
@@ -359,6 +361,8 @@ static struct qed_dev *qed_probe(struct pci_dev *pdev,
 
 	qed_init_dp(cdev, params->dp_module, params->dp_level);
 
+	cdev->recov_in_prog = params->recov_in_prog;
+
 	rc = qed_init_pci(cdev, pdev);
 	if (rc) {
 		DP_ERR(cdev, "init pci failed\n");
@@ -966,9 +970,47 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 	}
 }
 
+#define QED_PERIODIC_DB_REC_COUNT		10
+#define QED_PERIODIC_DB_REC_INTERVAL_MS		100
+#define QED_PERIODIC_DB_REC_INTERVAL \
+	msecs_to_jiffies(QED_PERIODIC_DB_REC_INTERVAL_MS)
+#define QED_PERIODIC_DB_REC_WAIT_COUNT		10
+#define QED_PERIODIC_DB_REC_WAIT_INTERVAL \
+	(QED_PERIODIC_DB_REC_INTERVAL_MS / QED_PERIODIC_DB_REC_WAIT_COUNT)
+
+static int qed_slowpath_delayed_work(struct qed_hwfn *hwfn,
+				     enum qed_slowpath_wq_flag wq_flag,
+				     unsigned long delay)
+{
+	if (!hwfn->slowpath_wq_active)
+		return -EINVAL;
+
+	/* Memory barrier for setting atomic bit */
+	smp_mb__before_atomic();
+	set_bit(wq_flag, &hwfn->slowpath_task_flags);
+	smp_mb__after_atomic();
+	queue_delayed_work(hwfn->slowpath_wq, &hwfn->slowpath_task, delay);
+
+	return 0;
+}
+
+void qed_periodic_db_rec_start(struct qed_hwfn *p_hwfn)
+{
+	/* Reset periodic Doorbell Recovery counter */
+	p_hwfn->periodic_db_rec_count = QED_PERIODIC_DB_REC_COUNT;
+
+	/* Don't schedule periodic Doorbell Recovery if already scheduled */
+	if (test_bit(QED_SLOWPATH_PERIODIC_DB_REC,
+		     &p_hwfn->slowpath_task_flags))
+		return;
+
+	qed_slowpath_delayed_work(p_hwfn, QED_SLOWPATH_PERIODIC_DB_REC,
+				  QED_PERIODIC_DB_REC_INTERVAL);
+}
+
 static void qed_slowpath_wq_stop(struct qed_dev *cdev)
 {
-	int i;
+	int i, sleep_count = QED_PERIODIC_DB_REC_WAIT_COUNT;
 
 	if (IS_VF(cdev))
 		return;
@@ -977,6 +1019,15 @@ static void qed_slowpath_wq_stop(struct qed_dev *cdev)
 		if (!cdev->hwfns[i].slowpath_wq)
 			continue;
 
+		/* Stop queuing new delayed works */
+		cdev->hwfns[i].slowpath_wq_active = false;
+
+		/* Wait until the last periodic doorbell recovery is executed */
+		while (test_bit(QED_SLOWPATH_PERIODIC_DB_REC,
+				&cdev->hwfns[i].slowpath_task_flags) &&
+		       sleep_count--)
+			msleep(QED_PERIODIC_DB_REC_WAIT_INTERVAL);
+
 		flush_workqueue(cdev->hwfns[i].slowpath_wq);
 		destroy_workqueue(cdev->hwfns[i].slowpath_wq);
 	}
@@ -989,7 +1040,10 @@ static void qed_slowpath_task(struct work_struct *work)
 	struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
 
 	if (!ptt) {
-		queue_delayed_work(hwfn->slowpath_wq, &hwfn->slowpath_task, 0);
+		if (hwfn->slowpath_wq_active)
+			queue_delayed_work(hwfn->slowpath_wq,
+					   &hwfn->slowpath_task, 0);
+
 		return;
 	}
 
@@ -997,6 +1051,15 @@ static void qed_slowpath_task(struct work_struct *work)
 			       &hwfn->slowpath_task_flags))
 		qed_mfw_process_tlv_req(hwfn, ptt);
 
+	if (test_and_clear_bit(QED_SLOWPATH_PERIODIC_DB_REC,
+			       &hwfn->slowpath_task_flags)) {
+		qed_db_rec_handler(hwfn, ptt);
+		if (hwfn->periodic_db_rec_count--)
+			qed_slowpath_delayed_work(hwfn,
+						  QED_SLOWPATH_PERIODIC_DB_REC,
+						  QED_PERIODIC_DB_REC_INTERVAL);
+	}
+
 	qed_ptt_release(hwfn, ptt);
 }
 
@@ -1023,6 +1086,7 @@ static int qed_slowpath_wq_start(struct qed_dev *cdev)
 		}
 
 		INIT_DELAYED_WORK(&hwfn->slowpath_task, qed_slowpath_task);
+		hwfn->slowpath_wq_active = true;
 	}
 
 	return 0;
@@ -1939,21 +2003,30 @@ exit:
  * 0B  |                       0x3 [command index]                            |
  * 4B  | b'0: check_response?   | b'1-31  reserved                            |
  * 8B  | File-type |                   reserved                               |
+ * 12B |                    Image length in bytes                             |
  *     \----------------------------------------------------------------------/
  *     Start a new file of the provided type
  */
 static int qed_nvm_flash_image_file_start(struct qed_dev *cdev,
 					  const u8 **data, bool *check_resp)
 {
+	u32 file_type, file_size = 0;
 	int rc;
 
 	*data += 4;
 	*check_resp = !!(**data & BIT(0));
 	*data += 4;
+	file_type = **data;
 
 	DP_VERBOSE(cdev, NETIF_MSG_DRV,
-		   "About to start a new file of type %02x\n", **data);
-	rc = qed_mcp_nvm_put_file_begin(cdev, **data);
+		   "About to start a new file of type %02x\n", file_type);
+	if (file_type == DRV_MB_PARAM_NVM_PUT_FILE_BEGIN_MBI) {
+		*data += 4;
+		file_size = *((u32 *)(*data));
+	}
+
+	rc = qed_mcp_nvm_write(cdev, QED_PUT_FILE_BEGIN, file_type,
+			       (u8 *)(&file_size), 4);
 	*data += 4;
 
 	return rc;
@@ -2134,6 +2207,15 @@ static int qed_nvm_get_image(struct qed_dev *cdev, enum qed_nvm_images type,
 	return qed_mcp_get_nvm_image(hwfn, type, buf, len);
 }
 
+void qed_schedule_recovery_handler(struct qed_hwfn *p_hwfn)
+{
+	struct qed_common_cb_ops *ops = p_hwfn->cdev->protocol_ops.common;
+	void *cookie = p_hwfn->cdev->ops_cookie;
+
+	if (ops && ops->schedule_recovery_handler)
+		ops->schedule_recovery_handler(cookie);
+}
+
 static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal,
 			    void *handle)
 {
@@ -2157,6 +2239,23 @@ static int qed_set_led(struct qed_dev *cdev, enum qed_led_mode mode)
 	return status;
 }
 
+static int qed_recovery_process(struct qed_dev *cdev)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt;
+	int rc = 0;
+
+	p_ptt = qed_ptt_acquire(p_hwfn);
+	if (!p_ptt)
+		return -EAGAIN;
+
+	rc = qed_start_recovery_process(p_hwfn, p_ptt);
+
+	qed_ptt_release(p_hwfn, p_ptt);
+
+	return rc;
+}
+
 static int qed_update_wol(struct qed_dev *cdev, bool enabled)
 {
 	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
@@ -2311,10 +2410,14 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.nvm_get_image = &qed_nvm_get_image,
 	.set_coalesce = &qed_set_coalesce,
 	.set_led = &qed_set_led,
+	.recovery_process = &qed_recovery_process,
+	.recovery_prolog = &qed_recovery_prolog,
 	.update_drv_state = &qed_update_drv_state,
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,
 	.update_wol = &qed_update_wol,
+	.db_recovery_add = &qed_db_recovery_add,
+	.db_recovery_del = &qed_db_recovery_del,
 	.read_module_eeprom = &qed_read_module_eeprom,
 };
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index a96364df4320..cc27fd60d689 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1070,6 +1070,27 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	u32 resp = 0, param = 0;
+	int rc;
+
+	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_LOAD_DONE, 0, &resp,
+			 &param);
+	if (rc) {
+		DP_NOTICE(p_hwfn,
+			  "Failed to send a LOAD_DONE command, rc = %d\n", rc);
+		return rc;
+	}
+
+	/* Check if there is a DID mismatch between nvm-cfg/efuse */
+	if (param & FW_MB_PARAM_LOAD_DONE_DID_EFUSE_ERROR)
+		DP_NOTICE(p_hwfn,
+			  "warning: device configuration is not supported on this board type. The device may not function as expected.\n");
+
+	return 0;
+}
+
 int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	struct qed_mcp_mb_params mb_params;
@@ -1528,6 +1549,60 @@ int qed_mcp_set_link(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, bool b_up)
 	return 0;
 }
 
+u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn,
+				 struct qed_ptt *p_ptt)
+{
+	u32 path_offsize_addr, path_offsize, path_addr, proc_kill_cnt;
+
+	if (IS_VF(p_hwfn->cdev))
+		return -EINVAL;
+
+	path_offsize_addr = SECTION_OFFSIZE_ADDR(p_hwfn->mcp_info->public_base,
+						 PUBLIC_PATH);
+	path_offsize = qed_rd(p_hwfn, p_ptt, path_offsize_addr);
+	path_addr = SECTION_ADDR(path_offsize, QED_PATH_ID(p_hwfn));
+
+	proc_kill_cnt = qed_rd(p_hwfn, p_ptt,
+			       path_addr +
+			       offsetof(struct public_path, process_kill)) &
+			PROCESS_KILL_COUNTER_MASK;
+
+	return proc_kill_cnt;
+}
+
+static void qed_mcp_handle_process_kill(struct qed_hwfn *p_hwfn,
+					struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+	u32 proc_kill_cnt;
+
+	/* Prevent possible attentions/interrupts during the recovery handling
+	 * and till its load phase, during which they will be re-enabled.
+	 */
+	qed_int_igu_disable_int(p_hwfn, p_ptt);
+
+	DP_NOTICE(p_hwfn, "Received a process kill indication\n");
+
+	/* The following operations should be done once, and thus in CMT mode
+	 * are carried out by only the first HW function.
+	 */
+	if (p_hwfn != QED_LEADING_HWFN(cdev))
+		return;
+
+	if (cdev->recov_in_prog) {
+		DP_NOTICE(p_hwfn,
+			  "Ignoring the indication since a recovery process is already in progress\n");
+		return;
+	}
+
+	cdev->recov_in_prog = true;
+
+	proc_kill_cnt = qed_get_process_kill_counter(p_hwfn, p_ptt);
+	DP_NOTICE(p_hwfn, "Process kill counter: %d\n", proc_kill_cnt);
+
+	qed_schedule_recovery_handler(p_hwfn);
+}
+
 static void qed_mcp_send_protocol_stats(struct qed_hwfn *p_hwfn,
 					struct qed_ptt *p_ptt,
 					enum MFW_DRV_MSG_TYPE type)
@@ -1619,7 +1694,7 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		qed_sp_pf_update_stag(p_hwfn);
 	}
 
-	DP_VERBOSE(p_hwfn, QED_MSG_SP, "ovlan  = %d hw_mode = 0x%x\n",
+	DP_VERBOSE(p_hwfn, QED_MSG_SP, "ovlan = %d hw_mode = 0x%x\n",
 		   p_hwfn->mcp_info->func_info.ovlan, p_hwfn->hw_info.hw_mode);
 
 	/* Acknowledge the MFW */
@@ -1641,7 +1716,9 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	val = (port_cfg & OEM_CFG_CHANNEL_TYPE_MASK) >>
 		OEM_CFG_CHANNEL_TYPE_OFFSET;
 	if (val != OEM_CFG_CHANNEL_TYPE_STAGGED)
-		DP_NOTICE(p_hwfn, "Incorrect UFP Channel type  %d\n", val);
+		DP_NOTICE(p_hwfn,
+			  "Incorrect UFP Channel type  %d port_id 0x%02x\n",
+			  val, MFW_PORT(p_hwfn));
 
 	val = (port_cfg & OEM_CFG_SCHED_TYPE_MASK) >> OEM_CFG_SCHED_TYPE_OFFSET;
 	if (val == OEM_CFG_SCHED_TYPE_ETS) {
@@ -1650,7 +1727,9 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		p_hwfn->ufp_info.mode = QED_UFP_MODE_VNIC_BW;
 	} else {
 		p_hwfn->ufp_info.mode = QED_UFP_MODE_UNKNOWN;
-		DP_NOTICE(p_hwfn, "Unknown UFP scheduling mode %d\n", val);
+		DP_NOTICE(p_hwfn,
+			  "Unknown UFP scheduling mode %d port_id 0x%02x\n",
+			  val, MFW_PORT(p_hwfn));
 	}
 
 	qed_mcp_get_shmem_func(p_hwfn, p_ptt, &shmem_info, MCP_PF_ID(p_hwfn));
@@ -1665,13 +1744,15 @@ void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 		p_hwfn->ufp_info.pri_type = QED_UFP_PRI_OS;
 	} else {
 		p_hwfn->ufp_info.pri_type = QED_UFP_PRI_UNKNOWN;
-		DP_NOTICE(p_hwfn, "Unknown Host priority control %d\n", val);
+		DP_NOTICE(p_hwfn,
+			  "Unknown Host priority control %d port_id 0x%02x\n",
+			  val, MFW_PORT(p_hwfn));
 	}
 
 	DP_NOTICE(p_hwfn,
-		  "UFP shmem config: mode = %d tc = %d pri_type = %d\n",
-		  p_hwfn->ufp_info.mode,
-		  p_hwfn->ufp_info.tc, p_hwfn->ufp_info.pri_type);
+		  "UFP shmem config: mode = %d tc = %d pri_type = %d port_id 0x%02x\n",
+		  p_hwfn->ufp_info.mode, p_hwfn->ufp_info.tc,
+		  p_hwfn->ufp_info.pri_type, MFW_PORT(p_hwfn));
 }
 
 static int
@@ -1752,6 +1833,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn,
 		case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE:
 			qed_mcp_handle_transceiver_change(p_hwfn, p_ptt);
 			break;
+		case MFW_DRV_MSG_ERROR_RECOVERY:
+			qed_mcp_handle_process_kill(p_hwfn, p_ptt);
+			break;
 		case MFW_DRV_MSG_GET_LAN_STATS:
 		case MFW_DRV_MSG_GET_FCOE_STATS:
 		case MFW_DRV_MSG_GET_ISCSI_STATS:
@@ -2297,6 +2381,43 @@ int qed_mcp_get_flash_size(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
+int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
+{
+	struct qed_dev *cdev = p_hwfn->cdev;
+
+	if (cdev->recov_in_prog) {
+		DP_NOTICE(p_hwfn,
+			  "Avoid triggering a recovery since such a process is already in progress\n");
+		return -EAGAIN;
+	}
+
+	DP_NOTICE(p_hwfn, "Triggering a recovery process\n");
+	qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_GENERAL_ATTN_35, 0x1);
+
+	return 0;
+}
+
+#define QED_RECOVERY_PROLOG_SLEEP_MS    100
+
+int qed_recovery_prolog(struct qed_dev *cdev)
+{
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *p_ptt = p_hwfn->p_main_ptt;
+	int rc;
+
+	/* Allow ongoing PCIe transactions to complete */
+	msleep(QED_RECOVERY_PROLOG_SLEEP_MS);
+
+	/* Clear the PF's internal FID_enable in the PXP */
+	rc = qed_pglueb_set_pfid_enable(p_hwfn, p_ptt, false);
+	if (rc)
+		DP_NOTICE(p_hwfn,
+			  "qed_pglueb_set_pfid_enable() failed. rc = %d.\n",
+			  rc);
+
+	return rc;
+}
+
 static int
 qed_mcp_config_vf_msix_bb(struct qed_hwfn *p_hwfn,
 			  struct qed_ptt *p_ptt, u8 vf_id, u8 num)
@@ -2739,24 +2860,6 @@ int qed_mcp_nvm_resp(struct qed_dev *cdev, u8 *p_buf)
 	return 0;
 }
 
-int qed_mcp_nvm_put_file_begin(struct qed_dev *cdev, u32 addr)
-{
-	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
-	struct qed_ptt *p_ptt;
-	u32 resp, param;
-	int rc;
-
-	p_ptt = qed_ptt_acquire(p_hwfn);
-	if (!p_ptt)
-		return -EBUSY;
-	rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_NVM_PUT_FILE_BEGIN, addr,
-			 &resp, &param);
-	cdev->mcp_nvm_resp = resp;
-	qed_ptt_release(p_hwfn, p_ptt);
-
-	return rc;
-}
-
 int qed_mcp_nvm_write(struct qed_dev *cdev,
 		      u32 cmd, u32 addr, u8 *p_buf, u32 len)
 {
@@ -2770,6 +2873,9 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		return -EBUSY;
 
 	switch (cmd) {
+	case QED_PUT_FILE_BEGIN:
+		nvm_cmd = DRV_MSG_CODE_NVM_PUT_FILE_BEGIN;
+		break;
 	case QED_PUT_FILE_DATA:
 		nvm_cmd = DRV_MSG_CODE_NVM_PUT_FILE_DATA;
 		break;
@@ -2782,10 +2888,14 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		goto out;
 	}
 
+	buf_size = min_t(u32, (len - buf_idx), MCP_DRV_NVM_BUF_LEN);
 	while (buf_idx < len) {
-		buf_size = min_t(u32, (len - buf_idx), MCP_DRV_NVM_BUF_LEN);
-		nvm_offset = ((buf_size << DRV_MB_PARAM_NVM_LEN_OFFSET) |
-			      addr) + buf_idx;
+		if (cmd == QED_PUT_FILE_BEGIN)
+			nvm_offset = addr;
+		else
+			nvm_offset = ((buf_size <<
+				       DRV_MB_PARAM_NVM_LEN_OFFSET) | addr) +
+				       buf_idx;
 		rc = qed_mcp_nvm_wr_cmd(p_hwfn, p_ptt, nvm_cmd, nvm_offset,
 					&resp, &param, buf_size,
 					(u32 *)&p_buf[buf_idx]);
@@ -2810,7 +2920,19 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		if (buf_idx % 0x1000 > (buf_idx + buf_size) % 0x1000)
 			usleep_range(1000, 2000);
 
-		buf_idx += buf_size;
+		/* For MBI upgrade, MFW response includes the next buffer offset
+		 * to be delivered to MFW.
+		 */
+		if (param && cmd == QED_PUT_FILE_DATA) {
+			buf_idx = QED_MFW_GET_FIELD(param,
+					FW_MB_PARAM_NVM_PUT_FILE_REQ_OFFSET);
+			buf_size = QED_MFW_GET_FIELD(param,
+					 FW_MB_PARAM_NVM_PUT_FILE_REQ_SIZE);
+		} else {
+			buf_idx += buf_size;
+			buf_size = min_t(u32, (len - buf_idx),
+					 MCP_DRV_NVM_BUF_LEN);
+		}
 	}
 
 	cdev->mcp_nvm_resp = resp;
@@ -3532,6 +3654,12 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock,
 	}
 }
 
+bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn)
+{
+	return !!(p_hwfn->mcp_info->capabilities &
+		  FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ);
+}
+
 int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u32 mcp_resp;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 1adfe52b3905..261c1a392e2c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -441,6 +441,38 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn,
 			 struct qed_mcp_drv_version *p_ver);
 
 /**
+ * @brief Read the MFW process kill counter
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return u32
+ */
+u32 qed_get_process_kill_counter(struct qed_hwfn *p_hwfn,
+				 struct qed_ptt *p_ptt);
+
+/**
+ * @brief Trigger a recovery process
+ *
+ *  @param p_hwfn
+ *  @param p_ptt
+ *
+ * @return int
+ */
+int qed_start_recovery_process(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
+ * @brief A recovery handler must call this function as its first step.
+ *        It is assumed that the handler is not run from an interrupt context.
+ *
+ *  @param cdev
+ *  @param p_ptt
+ *
+ * @return int
+ */
+int qed_recovery_prolog(struct qed_dev *cdev);
+
+/**
  * @brief Notify MFW about the change in base device properties
  *
  *  @param p_hwfn
@@ -543,16 +575,6 @@ int qed_mcp_nvm_write(struct qed_dev *cdev,
 		      u32 cmd, u32 addr, u8 *p_buf, u32 len);
 
 /**
- * @brief Put file begin
- *
- *  @param cdev
- *  @param addr - nvm offset
- *
- * @return int - 0 - operation was successful.
- */
-int qed_mcp_nvm_put_file_begin(struct qed_dev *cdev, u32 addr);
-
-/**
  * @brief Check latest response
  *
  *  @param cdev
@@ -669,10 +691,6 @@ int qed_mfw_process_tlv_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
 					    rel_pfid)
 #define MCP_PF_ID(p_hwfn) MCP_PF_ID_BY_REL(p_hwfn, (p_hwfn)->rel_pf_id)
 
-#define MFW_PORT(_p_hwfn)       ((_p_hwfn)->abs_pf_id %			  \
-				 ((_p_hwfn)->cdev->num_ports_in_engine * \
-				  qed_device_num_engines((_p_hwfn)->cdev)))
-
 struct qed_mcp_info {
 	/* List for mailbox commands which were sent and wait for a response */
 	struct list_head			cmd_list;
@@ -811,6 +829,16 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn,
 		     struct qed_load_req_params *p_params);
 
 /**
+ * @brief Sends a LOAD_DONE message to the MFW
+ *
+ * @param p_hwfn
+ * @param p_ptt
+ *
+ * @return int - 0 - Operation was successful.
+ */
+int qed_mcp_load_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt);
+
+/**
  * @brief Sends a UNLOAD_REQ message to the MFW
  *
  * @param p_hwfn
@@ -1116,6 +1144,16 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock,
 				    struct qed_resc_unlock_params *p_unlock,
 				    enum qed_resc_lock
 				    resource, bool b_is_permanent);
+
+/**
+ * @brief - Return whether management firmware support smart AN
+ *
+ * @param p_hwfn
+ *
+ * @return bool - true if feature is supported.
+ */
+bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn);
+
 /**
  * @brief Learn of supported MFW features; To be done during early init
  *
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ptp.c b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
index 5a90d69dc2f8..1302b308bd87 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ptp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ptp.c
@@ -47,7 +47,7 @@
 
 static enum qed_resc_lock qed_ptcdev_to_resc(struct qed_hwfn *p_hwfn)
 {
-	switch (qed_device_get_port_id(p_hwfn->cdev)) {
+	switch (MFW_PORT(p_hwfn)) {
 	case 0:
 		return QED_RESC_LOCK_PTP_PORT0;
 	case 1:
diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
index 2440970882c4..5ce825ca5f24 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h
@@ -518,6 +518,8 @@
 	0x180824UL
 #define  MISC_REG_AEU_GENERAL_ATTN_0 \
 	0x008400UL
+#define MISC_REG_AEU_GENERAL_ATTN_35 \
+	0x00848cUL
 #define  CAU_REG_SB_ADDR_MEMORY \
 	0x1c8000UL
 #define  CAU_REG_SB_VAR_MEMORY \
@@ -1243,6 +1245,56 @@
 	0x1701534UL
 #define TSEM_REG_DBG_FORCE_FRAME \
 	0x1701538UL
+#define DORQ_REG_PF_USAGE_CNT \
+	0x1009c0UL
+#define DORQ_REG_PF_OVFL_STICKY	\
+	0x1009d0UL
+#define DORQ_REG_DPM_FORCE_ABORT \
+	0x1009d8UL
+#define DORQ_REG_INT_STS \
+	0x100180UL
+#define DORQ_REG_INT_STS_ADDRESS_ERROR \
+	(0x1UL << 0)
+#define DORQ_REG_INT_STS_WR \
+	0x100188UL
+#define DORQ_REG_DB_DROP_DETAILS_REL \
+	0x100a28UL
+#define DORQ_REG_INT_STS_ADDRESS_ERROR_SHIFT \
+	0
+#define DORQ_REG_INT_STS_DB_DROP \
+		(0x1UL << 1)
+#define DORQ_REG_INT_STS_DB_DROP_SHIFT \
+	1
+#define DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR \
+		(0x1UL << 2)
+#define DORQ_REG_INT_STS_DORQ_FIFO_OVFL_ERR_SHIFT \
+	2
+#define DORQ_REG_INT_STS_DORQ_FIFO_AFULL\
+		(0x1UL << 3)
+#define DORQ_REG_INT_STS_DORQ_FIFO_AFULL_SHIFT \
+	3
+#define DORQ_REG_INT_STS_CFC_BYP_VALIDATION_ERR \
+		(0x1UL << 4)
+#define DORQ_REG_INT_STS_CFC_BYP_VALIDATION_ERR_SHIFT \
+	4
+#define DORQ_REG_INT_STS_CFC_LD_RESP_ERR \
+		(0x1UL << 5)
+#define DORQ_REG_INT_STS_CFC_LD_RESP_ERR_SHIFT \
+	5
+#define DORQ_REG_INT_STS_XCM_DONE_CNT_ERR \
+		(0x1UL << 6)
+#define DORQ_REG_INT_STS_XCM_DONE_CNT_ERR_SHIFT	\
+	6
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_OVFL_ERR \
+		(0x1UL << 7)
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_OVFL_ERR_SHIFT	\
+	7
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_UNDER_ERR \
+		(0x1UL << 8)
+#define DORQ_REG_INT_STS_CFC_LD_REQ_FIFO_UNDER_ERR_SHIFT \
+	8
+#define DORQ_REG_DB_DROP_DETAILS_REASON	\
+	0x100a20UL
 #define MSEM_REG_DBG_SELECT \
 	0x1801528UL
 #define MSEM_REG_DBG_DWORD_ENABLE \
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h
index 3157c0d99441..96ab77ae6af5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h
@@ -227,7 +227,9 @@ struct qed_spq {
 	u32			comp_count;
 
 	u32			cid;
-	qed_spq_async_comp_cb async_comp_cb[MAX_PROTOCOL_TYPE];
+	u32			db_addr_offset;
+	struct core_db_data	db_data;
+	qed_spq_async_comp_cb	async_comp_cb[MAX_PROTOCOL_TYPE];
 };
 
 /**
@@ -380,6 +382,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn);
  * @param p_hwfn
  */
 void qed_consq_free(struct qed_hwfn *p_hwfn);
+int qed_spq_pend_post(struct qed_hwfn *p_hwfn);
 
 /**
  * @file
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
index 888274fa208b..5a495fda9e9d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c
@@ -604,6 +604,9 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn)
 
 	p_ent->ramrod.pf_update.update_mf_vlan_flag = true;
 	p_ent->ramrod.pf_update.mf_vlan = cpu_to_le16(p_hwfn->hw_info.ovlan);
+	if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits))
+		p_ent->ramrod.pf_update.mf_vlan |=
+			cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13));
 
 	return qed_spq_post(p_hwfn, p_ent, NULL);
 }
diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c
index 0a9c5bb0fa48..79b311b86f66 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_spq.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c
@@ -252,9 +252,9 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 			   struct qed_spq *p_spq, struct qed_spq_entry *p_ent)
 {
 	struct qed_chain *p_chain = &p_hwfn->p_spq->chain;
+	struct core_db_data *p_db_data = &p_spq->db_data;
 	u16 echo = qed_chain_get_prod_idx(p_chain);
 	struct slow_path_element	*elem;
-	struct core_db_data		db;
 
 	p_ent->elem.hdr.echo	= cpu_to_le16(echo);
 	elem = qed_chain_produce(p_chain);
@@ -266,27 +266,22 @@ static int qed_spq_hw_post(struct qed_hwfn *p_hwfn,
 	*elem = p_ent->elem; /* struct assignment */
 
 	/* send a doorbell on the slow hwfn session */
-	memset(&db, 0, sizeof(db));
-	SET_FIELD(db.params, CORE_DB_DATA_DEST, DB_DEST_XCM);
-	SET_FIELD(db.params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_SET);
-	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;
-	db.spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
+	p_db_data->spq_prod = cpu_to_le16(qed_chain_get_prod_idx(p_chain));
 
 	/* make sure the SPQE is updated before the doorbell */
 	wmb();
 
-	DOORBELL(p_hwfn, qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY), *(u32 *)&db);
+	DOORBELL(p_hwfn, p_spq->db_addr_offset, *(u32 *)p_db_data);
 
 	/* make sure doorbell is rang */
 	wmb();
 
 	DP_VERBOSE(p_hwfn, QED_MSG_SPQ,
 		   "Doorbelled [0x%08x, CID 0x%08x] with Flags: %02x agg_params: %02x, prod: %04x\n",
-		   qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY),
-		   p_spq->cid, db.params, db.agg_flags,
-		   qed_chain_get_prod_idx(p_chain));
+		   p_spq->db_addr_offset,
+		   p_spq->cid,
+		   p_db_data->params,
+		   p_db_data->agg_flags, qed_chain_get_prod_idx(p_chain));
 
 	return 0;
 }
@@ -402,6 +397,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie)
 
 	qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain));
 
+	/* Attempt to post pending requests */
+	spin_lock_bh(&p_hwfn->p_spq->lock);
+	rc = qed_spq_pend_post(p_hwfn);
+	spin_unlock_bh(&p_hwfn->p_spq->lock);
+
 	return rc;
 }
 
@@ -490,8 +490,11 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq *p_spq = p_hwfn->p_spq;
 	struct qed_spq_entry *p_virt = NULL;
+	struct core_db_data *p_db_data;
+	void __iomem *db_addr;
 	dma_addr_t p_phys = 0;
 	u32 i, capacity;
+	int rc;
 
 	INIT_LIST_HEAD(&p_spq->pending);
 	INIT_LIST_HEAD(&p_spq->completion_pending);
@@ -528,6 +531,25 @@ void qed_spq_setup(struct qed_hwfn *p_hwfn)
 
 	/* reset the chain itself */
 	qed_chain_reset(&p_spq->chain);
+
+	/* Initialize the address/data of the SPQ doorbell */
+	p_spq->db_addr_offset = qed_db_addr(p_spq->cid, DQ_DEMS_LEGACY);
+	p_db_data = &p_spq->db_data;
+	memset(p_db_data, 0, sizeof(*p_db_data));
+	SET_FIELD(p_db_data->params, CORE_DB_DATA_DEST, DB_DEST_XCM);
+	SET_FIELD(p_db_data->params, CORE_DB_DATA_AGG_CMD, DB_AGG_CMD_MAX);
+	SET_FIELD(p_db_data->params, CORE_DB_DATA_AGG_VAL_SEL,
+		  DQ_XCM_CORE_SPQ_PROD_CMD);
+	p_db_data->agg_flags = DQ_XCM_CORE_DQ_CF_CMD;
+
+	/* Register the SPQ doorbell with the doorbell recovery mechanism */
+	db_addr = (void __iomem *)((u8 __iomem *)p_hwfn->doorbells +
+				   p_spq->db_addr_offset);
+	rc = qed_db_recovery_add(p_hwfn->cdev, db_addr, &p_spq->db_data,
+				 DB_REC_WIDTH_32B, DB_REC_KERNEL);
+	if (rc)
+		DP_INFO(p_hwfn,
+			"Failed to register the SPQ doorbell with the doorbell recovery mechanism\n");
 }
 
 int qed_spq_alloc(struct qed_hwfn *p_hwfn)
@@ -575,11 +597,17 @@ spq_allocate_fail:
 void qed_spq_free(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq *p_spq = p_hwfn->p_spq;
+	void __iomem *db_addr;
 	u32 capacity;
 
 	if (!p_spq)
 		return;
 
+	/* Delete the SPQ doorbell from the doorbell recovery mechanism */
+	db_addr = (void __iomem *)((u8 __iomem *)p_hwfn->doorbells +
+				   p_spq->db_addr_offset);
+	qed_db_recovery_del(p_hwfn->cdev, db_addr, &p_spq->db_data);
+
 	if (p_spq->p_virt) {
 		capacity = qed_chain_get_capacity(&p_spq->chain);
 		dma_free_coherent(&p_hwfn->cdev->pdev->dev,
@@ -744,7 +772,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
-static int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
+int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
 {
 	struct qed_spq *p_spq = p_hwfn->p_spq;
 	struct qed_spq_entry *p_ent = NULL;
@@ -767,6 +795,17 @@ static int qed_spq_pend_post(struct qed_hwfn *p_hwfn)
 				 SPQ_HIGH_PRI_RESERVE_DEFAULT);
 }
 
+static void qed_spq_recov_set_ret_code(struct qed_spq_entry *p_ent,
+				       u8 *fw_return_code)
+{
+	if (!fw_return_code)
+		return;
+
+	if (p_ent->elem.hdr.protocol_id == PROTOCOLID_ROCE ||
+	    p_ent->elem.hdr.protocol_id == PROTOCOLID_IWARP)
+		*fw_return_code = RDMA_RETURN_OK;
+}
+
 /* Avoid overriding of SPQ entries when getting out-of-order completions, by
  * marking the completions in a bitmap and increasing the chain consumer only
  * for the first successive completed entries.
@@ -802,6 +841,17 @@ int qed_spq_post(struct qed_hwfn *p_hwfn,
 		return -EINVAL;
 	}
 
+	if (p_hwfn->cdev->recov_in_prog) {
+		DP_VERBOSE(p_hwfn,
+			   QED_MSG_SPQ,
+			   "Recovery is in progress. Skip spq post [cmd %02x protocol %02x]\n",
+			   p_ent->elem.hdr.cmd_id, p_ent->elem.hdr.protocol_id);
+
+		/* Let the flow complete w/o any error handling */
+		qed_spq_recov_set_ret_code(p_ent, fw_return_code);
+		return 0;
+	}
+
 	/* Complete the entry */
 	rc = qed_spq_fill_entry(p_hwfn, p_ent);
 
@@ -882,7 +932,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 	struct qed_spq_entry	*p_ent = NULL;
 	struct qed_spq_entry	*tmp;
 	struct qed_spq_entry	*found = NULL;
-	int			rc;
 
 	if (!p_hwfn)
 		return -EINVAL;
@@ -940,12 +989,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn,
 		 */
 		qed_spq_return_entry(p_hwfn, found);
 
-	/* Attempt to post pending requests */
-	spin_lock_bh(&p_spq->lock);
-	rc = qed_spq_pend_post(p_hwfn);
-	spin_unlock_bh(&p_spq->lock);
-
-	return rc;
+	return 0;
 }
 
 int qed_consq_alloc(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index ca6290fa0f30..2f318aaf2b05 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -1591,7 +1591,7 @@ static void qed_iov_vf_mbx_acquire(struct qed_hwfn *p_hwfn,
 			p_vfdev->eth_fp_hsi_minor = ETH_HSI_VER_NO_PKT_LEN_TUNN;
 		} else {
 			DP_INFO(p_hwfn,
-				"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's faspath HSI %02x.%02x\n",
+				"VF[%d] needs fastpath HSI %02x.%02x, which is incompatible with loaded FW's fastpath HSI %02x.%02x\n",
 				vf->abs_vf_id,
 				req->vfdev_info.eth_fp_hsi_major,
 				req->vfdev_info.eth_fp_hsi_minor,
@@ -1969,7 +1969,9 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn,
 	params.vport_id = vf->vport_id;
 	params.max_buffers_per_cqe = start->max_buffers_per_cqe;
 	params.mtu = vf->mtu;
-	params.check_mac = true;
+
+	/* Non trusted VFs should enable control frame filtering */
+	params.check_mac = !vf->p_vf_info.is_trusted_configured;
 
 	rc = qed_sp_eth_vport_start(p_hwfn, &params);
 	if (rc) {
@@ -4447,6 +4449,13 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 	if (cdev->p_iov_info && cdev->p_iov_info->num_vfs && pci_enabled)
 		pci_disable_sriov(cdev->pdev);
 
+	if (cdev->recov_in_prog) {
+		DP_VERBOSE(cdev,
+			   QED_MSG_IOV,
+			   "Skip SRIOV disable operations in the device since a recovery is in progress\n");
+		goto out;
+	}
+
 	for_each_hwfn(cdev, i) {
 		struct qed_hwfn *hwfn = &cdev->hwfns[i];
 		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
@@ -4486,7 +4495,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 
 		qed_ptt_release(hwfn, ptt);
 	}
-
+out:
 	qed_iov_set_vfs_to_disable(cdev, false);
 
 	return 0;
@@ -5130,6 +5139,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn)
 		params.opaque_fid = vf->opaque_fid;
 		params.vport_id = vf->vport_id;
 
+		params.update_ctl_frame_check = 1;
+		params.mac_chk_en = !vf_info->is_trusted_configured;
+
 		if (vf_info->rx_accept_mode & mask) {
 			flags->update_rx_mode_config = 1;
 			flags->rx_accept_filter = vf_info->rx_accept_mode;
@@ -5147,7 +5159,8 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn)
 		}
 
 		if (flags->update_rx_mode_config ||
-		    flags->update_tx_mode_config)
+		    flags->update_tx_mode_config ||
+		    params.update_ctl_frame_check)
 			qed_sp_vport_update(hwfn, &params,
 					    QED_SPQ_MODE_EBLOCK, NULL);
 	}
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index b6cccf44bf40..5dda547772c1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -261,6 +261,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 	struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp;
 	struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
 	struct vf_pf_resc_request *p_resc;
+	u8 retry_cnt = VF_ACQUIRE_THRESH;
 	bool resources_acquired = false;
 	struct vfpf_acquire_tlv *req;
 	int rc = 0, attempts = 0;
@@ -314,6 +315,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
 
 		/* send acquire request */
 		rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+
+		/* Re-try acquire in case of vf-pf hw channel timeout */
+		if (retry_cnt && rc == -EBUSY) {
+			DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+				   "VF retrying to acquire due to VPC timeout\n");
+			retry_cnt--;
+			continue;
+		}
+
 		if (rc)
 			goto exit;
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index de98a974673b..63a78162cfaf 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -56,7 +56,7 @@
 #include <net/tc_act/tc_gact.h>
 
 #define QEDE_MAJOR_VERSION		8
-#define QEDE_MINOR_VERSION		33
+#define QEDE_MINOR_VERSION		37
 #define QEDE_REVISION_VERSION		0
 #define QEDE_ENGINEERING_VERSION	20
 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "."	\
@@ -162,12 +162,20 @@ struct qede_rdma_dev {
 	struct list_head entry;
 	struct list_head rdma_event_list;
 	struct workqueue_struct *rdma_wq;
+	bool exp_recovery;
 };
 
 struct qede_ptp;
 
 #define QEDE_RFS_MAX_FLTR	256
 
+enum qede_flags_bit {
+	QEDE_FLAGS_IS_VF = 0,
+	QEDE_FLAGS_LINK_REQUESTED,
+	QEDE_FLAGS_PTP_TX_IN_PRORGESS,
+	QEDE_FLAGS_TX_TIMESTAMPING_EN
+};
+
 struct qede_dev {
 	struct qed_dev			*cdev;
 	struct net_device		*ndev;
@@ -177,10 +185,7 @@ struct qede_dev {
 	u8				dp_level;
 
 	unsigned long flags;
-#define QEDE_FLAG_IS_VF			BIT(0)
-#define IS_VF(edev)	(!!((edev)->flags & QEDE_FLAG_IS_VF))
-#define QEDE_TX_TIMESTAMPING_EN		BIT(1)
-#define QEDE_FLAGS_PTP_TX_IN_PRORGESS	BIT(2)
+#define IS_VF(edev)	(test_bit(QEDE_FLAGS_IS_VF, &(edev)->flags))
 
 	const struct qed_eth_ops	*ops;
 	struct qede_ptp			*ptp;
@@ -260,6 +265,7 @@ struct qede_dev {
 enum QEDE_STATE {
 	QEDE_STATE_CLOSED,
 	QEDE_STATE_OPEN,
+	QEDE_STATE_RECOVERY,
 };
 
 #define HILO_U64(hi, lo)		((((u64)(hi)) << 32) + (lo))
@@ -377,6 +383,7 @@ struct qede_tx_queue {
 
 	u64 xmit_pkts;
 	u64 stopped_cnt;
+	u64 tx_mem_alloc_err;
 
 	__le16 *hw_cons_ptr;
 
@@ -457,6 +464,7 @@ struct qede_fastpath {
 #define QEDE_CSUM_UNNECESSARY		BIT(1)
 #define QEDE_TUNN_CSUM_UNNECESSARY	BIT(2)
 
+#define QEDE_SP_RECOVERY		0
 #define QEDE_SP_RX_MODE			1
 
 #ifdef CONFIG_RFS_ACCEL
@@ -489,6 +497,9 @@ struct qede_reload_args {
 
 /* Datapath functions definition */
 netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev);
+u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
+		      struct net_device *sb_dev,
+		      select_queue_fallback_t fallback);
 netdev_features_t qede_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 8cbbd628fd73..b4c8949933f1 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -73,6 +73,7 @@ static const struct {
 } qede_tqstats_arr[] = {
 	QEDE_TQSTAT(xmit_pkts),
 	QEDE_TQSTAT(stopped_cnt),
+	QEDE_TQSTAT(tx_mem_alloc_err),
 };
 
 #define QEDE_STAT_OFFSET(stat_name, type, base) \
@@ -185,11 +186,13 @@ static const struct {
 
 enum {
 	QEDE_PRI_FLAG_CMT,
+	QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */
 	QEDE_PRI_FLAG_LEN,
 };
 
 static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = {
 	"Coupled-Function",
+	"SmartAN capable",
 };
 
 enum qede_ethtool_tests {
@@ -403,8 +406,15 @@ static int qede_get_sset_count(struct net_device *dev, int stringset)
 static u32 qede_get_priv_flags(struct net_device *dev)
 {
 	struct qede_dev *edev = netdev_priv(dev);
+	u32 flags = 0;
 
-	return (!!(edev->dev_info.common.num_hwfns > 1)) << QEDE_PRI_FLAG_CMT;
+	if (edev->dev_info.common.num_hwfns > 1)
+		flags |= BIT(QEDE_PRI_FLAG_CMT);
+
+	if (edev->dev_info.common.smart_an)
+		flags |= BIT(QEDE_PRI_FLAG_SMART_AN_SUPPORT);
+
+	return flags;
 }
 
 struct qede_link_mode_mapping {
@@ -1653,8 +1663,11 @@ static int qede_selftest_run_loopback(struct qede_dev *edev, u32 loopback_mode)
 	/* Wait for loopback configuration to apply */
 	msleep_interruptible(500);
 
-	/* prepare the loopback packet */
-	pkt_size = edev->ndev->mtu + ETH_HLEN;
+	/* Setting max packet size to 1.5K to avoid data being split over
+	 * multiple BDs in cases where MTU > PAGE_SIZE.
+	 */
+	pkt_size = (((edev->ndev->mtu < ETH_DATA_LEN) ?
+		     edev->ndev->mtu : ETH_DATA_LEN) + ETH_HLEN);
 
 	skb = netdev_alloc_skb(edev->ndev, pkt_size);
 	if (!skb) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b16ce7d93caf..add922b93d2c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1665,198 +1665,6 @@ static int qede_set_v6_tuple_to_profile(struct qede_dev *edev,
 	return 0;
 }
 
-static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
-					       struct qede_arfs_tuple *t,
-					       struct ethtool_rx_flow_spec *fs)
-{
-	if ((fs->h_u.tcp_ip4_spec.ip4src &
-	     fs->m_u.tcp_ip4_spec.ip4src) != fs->h_u.tcp_ip4_spec.ip4src) {
-		DP_INFO(edev, "Don't support IP-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip4_spec.ip4dst &
-	     fs->m_u.tcp_ip4_spec.ip4dst) != fs->h_u.tcp_ip4_spec.ip4dst) {
-		DP_INFO(edev, "Don't support IP-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip4_spec.psrc &
-	     fs->m_u.tcp_ip4_spec.psrc) != fs->h_u.tcp_ip4_spec.psrc) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip4_spec.pdst &
-	     fs->m_u.tcp_ip4_spec.pdst) != fs->h_u.tcp_ip4_spec.pdst) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (fs->h_u.tcp_ip4_spec.tos) {
-		DP_INFO(edev, "Don't support tos\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->eth_proto = htons(ETH_P_IP);
-	t->src_ipv4 = fs->h_u.tcp_ip4_spec.ip4src;
-	t->dst_ipv4 = fs->h_u.tcp_ip4_spec.ip4dst;
-	t->src_port = fs->h_u.tcp_ip4_spec.psrc;
-	t->dst_port = fs->h_u.tcp_ip4_spec.pdst;
-
-	return qede_set_v4_tuple_to_profile(edev, t);
-}
-
-static int qede_flow_spec_to_tuple_tcpv4(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_TCP;
-
-	if (qede_flow_spec_to_tuple_ipv4_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple_udpv4(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_UDP;
-
-	if (qede_flow_spec_to_tuple_ipv4_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
-					       struct qede_arfs_tuple *t,
-					       struct ethtool_rx_flow_spec *fs)
-{
-	struct in6_addr zero_addr;
-
-	memset(&zero_addr, 0, sizeof(zero_addr));
-
-	if ((fs->h_u.tcp_ip6_spec.psrc &
-	     fs->m_u.tcp_ip6_spec.psrc) != fs->h_u.tcp_ip6_spec.psrc) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((fs->h_u.tcp_ip6_spec.pdst &
-	     fs->m_u.tcp_ip6_spec.pdst) != fs->h_u.tcp_ip6_spec.pdst) {
-		DP_INFO(edev, "Don't support port-masks\n");
-		return -EOPNOTSUPP;
-	}
-
-	if (fs->h_u.tcp_ip6_spec.tclass) {
-		DP_INFO(edev, "Don't support tclass\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->eth_proto = htons(ETH_P_IPV6);
-	memcpy(&t->src_ipv6, &fs->h_u.tcp_ip6_spec.ip6src,
-	       sizeof(struct in6_addr));
-	memcpy(&t->dst_ipv6, &fs->h_u.tcp_ip6_spec.ip6dst,
-	       sizeof(struct in6_addr));
-	t->src_port = fs->h_u.tcp_ip6_spec.psrc;
-	t->dst_port = fs->h_u.tcp_ip6_spec.pdst;
-
-	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
-}
-
-static int qede_flow_spec_to_tuple_tcpv6(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_TCP;
-
-	if (qede_flow_spec_to_tuple_ipv6_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple_udpv6(struct qede_dev *edev,
-					 struct qede_arfs_tuple *t,
-					 struct ethtool_rx_flow_spec *fs)
-{
-	t->ip_proto = IPPROTO_UDP;
-
-	if (qede_flow_spec_to_tuple_ipv6_common(edev, t, fs))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int qede_flow_spec_to_tuple(struct qede_dev *edev,
-				   struct qede_arfs_tuple *t,
-				   struct ethtool_rx_flow_spec *fs)
-{
-	memset(t, 0, sizeof(*t));
-
-	if (qede_flow_spec_validate_unused(edev, fs))
-		return -EOPNOTSUPP;
-
-	switch ((fs->flow_type & ~FLOW_EXT)) {
-	case TCP_V4_FLOW:
-		return qede_flow_spec_to_tuple_tcpv4(edev, t, fs);
-	case UDP_V4_FLOW:
-		return qede_flow_spec_to_tuple_udpv4(edev, t, fs);
-	case TCP_V6_FLOW:
-		return qede_flow_spec_to_tuple_tcpv6(edev, t, fs);
-	case UDP_V6_FLOW:
-		return qede_flow_spec_to_tuple_udpv6(edev, t, fs);
-	default:
-		DP_VERBOSE(edev, NETIF_MSG_IFUP,
-			   "Can't support flow of type %08x\n", fs->flow_type);
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int qede_flow_spec_validate(struct qede_dev *edev,
-				   struct ethtool_rx_flow_spec *fs,
-				   struct qede_arfs_tuple *t)
-{
-	if (fs->location >= QEDE_RFS_MAX_FLTR) {
-		DP_INFO(edev, "Location out-of-bounds\n");
-		return -EINVAL;
-	}
-
-	/* Check location isn't already in use */
-	if (test_bit(fs->location, edev->arfs->arfs_fltr_bmap)) {
-		DP_INFO(edev, "Location already in use\n");
-		return -EINVAL;
-	}
-
-	/* Check if the filtering-mode could support the filter */
-	if (edev->arfs->filter_count &&
-	    edev->arfs->mode != t->mode) {
-		DP_INFO(edev,
-			"flow_spec would require filtering mode %08x, but %08x is configured\n",
-			t->mode, edev->arfs->filter_count);
-		return -EINVAL;
-	}
-
-	/* If drop requested then no need to validate other data */
-	if (fs->ring_cookie == RX_CLS_FLOW_DISC)
-		return 0;
-
-	if (ethtool_get_flow_spec_ring_vf(fs->ring_cookie))
-		return 0;
-
-	if (fs->ring_cookie >= QEDE_RSS_COUNT(edev)) {
-		DP_INFO(edev, "Queue out-of-bounds\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 /* Must be called while qede lock is held */
 static struct qede_arfs_fltr_node *
 qede_flow_find_fltr(struct qede_dev *edev, struct qede_arfs_tuple *t)
@@ -1896,72 +1704,6 @@ static void qede_flow_set_destination(struct qede_dev *edev,
 			   "Configuring N-tuple for VF 0x%02x\n", n->vfid - 1);
 }
 
-int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
-{
-	struct ethtool_rx_flow_spec *fsp = &info->fs;
-	struct qede_arfs_fltr_node *n;
-	struct qede_arfs_tuple t;
-	int min_hlen, rc;
-
-	__qede_lock(edev);
-
-	if (!edev->arfs) {
-		rc = -EPERM;
-		goto unlock;
-	}
-
-	/* Translate the flow specification into something fittign our DB */
-	rc = qede_flow_spec_to_tuple(edev, &t, fsp);
-	if (rc)
-		goto unlock;
-
-	/* Make sure location is valid and filter isn't already set */
-	rc = qede_flow_spec_validate(edev, fsp, &t);
-	if (rc)
-		goto unlock;
-
-	if (qede_flow_find_fltr(edev, &t)) {
-		rc = -EINVAL;
-		goto unlock;
-	}
-
-	n = kzalloc(sizeof(*n), GFP_KERNEL);
-	if (!n) {
-		rc = -ENOMEM;
-		goto unlock;
-	}
-
-	min_hlen = qede_flow_get_min_header_size(&t);
-	n->data = kzalloc(min_hlen, GFP_KERNEL);
-	if (!n->data) {
-		kfree(n);
-		rc = -ENOMEM;
-		goto unlock;
-	}
-
-	n->sw_id = fsp->location;
-	set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap);
-	n->buf_len = min_hlen;
-
-	memcpy(&n->tuple, &t, sizeof(n->tuple));
-
-	qede_flow_set_destination(edev, n, fsp);
-
-	/* Build a minimal header according to the flow */
-	n->tuple.build_hdr(&n->tuple, n->data);
-
-	rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0);
-	if (rc)
-		goto unlock;
-
-	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
-	rc = qede_poll_arfs_filter_config(edev, n);
-unlock:
-	__qede_unlock(edev);
-
-	return rc;
-}
-
 int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie)
 {
 	struct qede_arfs_fltr_node *fltr = NULL;
@@ -2004,190 +1746,172 @@ unlock:
 }
 
 static int qede_parse_actions(struct qede_dev *edev,
-			      struct tcf_exts *exts)
+			      struct flow_action *flow_action)
 {
-	int rc = -EINVAL, num_act = 0, i;
-	const struct tc_action *a;
-	bool is_drop = false;
+	const struct flow_action_entry *act;
+	int i;
 
-	if (!tcf_exts_has_actions(exts)) {
-		DP_NOTICE(edev, "No tc actions received\n");
-		return rc;
+	if (!flow_action_has_entries(flow_action)) {
+		DP_NOTICE(edev, "No actions received\n");
+		return -EINVAL;
 	}
 
-	tcf_exts_for_each_action(i, a, exts) {
-		num_act++;
+	flow_action_for_each(i, act, flow_action) {
+		switch (act->id) {
+		case FLOW_ACTION_DROP:
+			break;
+		case FLOW_ACTION_QUEUE:
+			if (act->queue.vf)
+				break;
 
-		if (is_tcf_gact_shot(a))
-			is_drop = true;
+			if (act->queue.index >= QEDE_RSS_COUNT(edev)) {
+				DP_INFO(edev, "Queue out-of-bounds\n");
+				return -EINVAL;
+			}
+			break;
+		default:
+			return -EINVAL;
+		}
 	}
 
-	if (num_act == 1 && is_drop)
-		return 0;
-
-	return rc;
+	return 0;
 }
 
 static int
-qede_tc_parse_ports(struct qede_dev *edev,
-		    struct tc_cls_flower_offload *f,
-		    struct qede_arfs_tuple *t)
-{
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
-		struct flow_dissector_key_ports *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_PORTS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_PORTS,
-						 f->mask);
-
-		if ((key->src && mask->src != U16_MAX) ||
-		    (key->dst && mask->dst != U16_MAX)) {
+qede_flow_parse_ports(struct qede_dev *edev, struct flow_rule *rule,
+		      struct qede_arfs_tuple *t)
+{
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports match;
+
+		flow_rule_match_ports(rule, &match);
+		if ((match.key->src && match.mask->src != U16_MAX) ||
+		    (match.key->dst && match.mask->dst != U16_MAX)) {
 			DP_NOTICE(edev, "Do not support ports masks\n");
 			return -EINVAL;
 		}
 
-		t->src_port = key->src;
-		t->dst_port = key->dst;
+		t->src_port = match.key->src;
+		t->dst_port = match.key->dst;
 	}
 
 	return 0;
 }
 
 static int
-qede_tc_parse_v6_common(struct qede_dev *edev,
-			struct tc_cls_flower_offload *f,
-			struct qede_arfs_tuple *t)
+qede_flow_parse_v6_common(struct qede_dev *edev, struct flow_rule *rule,
+			  struct qede_arfs_tuple *t)
 {
 	struct in6_addr zero_addr, addr;
 
 	memset(&zero_addr, 0, sizeof(addr));
 	memset(&addr, 0xff, sizeof(addr));
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
-		struct flow_dissector_key_ipv6_addrs *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_IPV6_ADDRS,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_match_ipv6_addrs match;
 
-		if ((memcmp(&key->src, &zero_addr, sizeof(addr)) &&
-		     memcmp(&mask->src, &addr, sizeof(addr))) ||
-		    (memcmp(&key->dst, &zero_addr, sizeof(addr)) &&
-		     memcmp(&mask->dst, &addr, sizeof(addr)))) {
+		flow_rule_match_ipv6_addrs(rule, &match);
+		if ((memcmp(&match.key->src, &zero_addr, sizeof(addr)) &&
+		     memcmp(&match.mask->src, &addr, sizeof(addr))) ||
+		    (memcmp(&match.key->dst, &zero_addr, sizeof(addr)) &&
+		     memcmp(&match.mask->dst, &addr, sizeof(addr)))) {
 			DP_NOTICE(edev,
 				  "Do not support IPv6 address prefix/mask\n");
 			return -EINVAL;
 		}
 
-		memcpy(&t->src_ipv6, &key->src, sizeof(addr));
-		memcpy(&t->dst_ipv6, &key->dst, sizeof(addr));
+		memcpy(&t->src_ipv6, &match.key->src, sizeof(addr));
+		memcpy(&t->dst_ipv6, &match.key->dst, sizeof(addr));
 	}
 
-	if (qede_tc_parse_ports(edev, f, t))
+	if (qede_flow_parse_ports(edev, rule, t))
 		return -EINVAL;
 
 	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
 }
 
 static int
-qede_tc_parse_v4_common(struct qede_dev *edev,
-			struct tc_cls_flower_offload *f,
+qede_flow_parse_v4_common(struct qede_dev *edev, struct flow_rule *rule,
 			struct qede_arfs_tuple *t)
 {
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
-		struct flow_dissector_key_ipv4_addrs *key, *mask;
-
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						f->key);
-		mask = skb_flow_dissector_target(f->dissector,
-						 FLOW_DISSECTOR_KEY_IPV4_ADDRS,
-						 f->mask);
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_match_ipv4_addrs match;
 
-		if ((key->src && mask->src != U32_MAX) ||
-		    (key->dst && mask->dst != U32_MAX)) {
+		flow_rule_match_ipv4_addrs(rule, &match);
+		if ((match.key->src && match.mask->src != U32_MAX) ||
+		    (match.key->dst && match.mask->dst != U32_MAX)) {
 			DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n");
 			return -EINVAL;
 		}
 
-		t->src_ipv4 = key->src;
-		t->dst_ipv4 = key->dst;
+		t->src_ipv4 = match.key->src;
+		t->dst_ipv4 = match.key->dst;
 	}
 
-	if (qede_tc_parse_ports(edev, f, t))
+	if (qede_flow_parse_ports(edev, rule, t))
 		return -EINVAL;
 
 	return qede_set_v4_tuple_to_profile(edev, t);
 }
 
 static int
-qede_tc_parse_tcp_v6(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_tcp_v6(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_TCP;
 	tuple->eth_proto = htons(ETH_P_IPV6);
 
-	return qede_tc_parse_v6_common(edev, f, tuple);
+	return qede_flow_parse_v6_common(edev, rule, tuple);
 }
 
 static int
-qede_tc_parse_tcp_v4(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_tcp_v4(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_TCP;
 	tuple->eth_proto = htons(ETH_P_IP);
 
-	return qede_tc_parse_v4_common(edev, f, tuple);
+	return qede_flow_parse_v4_common(edev, rule, tuple);
 }
 
 static int
-qede_tc_parse_udp_v6(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_udp_v6(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_UDP;
 	tuple->eth_proto = htons(ETH_P_IPV6);
 
-	return qede_tc_parse_v6_common(edev, f, tuple);
+	return qede_flow_parse_v6_common(edev, rule, tuple);
 }
 
 static int
-qede_tc_parse_udp_v4(struct qede_dev *edev,
-		     struct tc_cls_flower_offload *f,
+qede_flow_parse_udp_v4(struct qede_dev *edev, struct flow_rule *rule,
 		     struct qede_arfs_tuple *tuple)
 {
 	tuple->ip_proto = IPPROTO_UDP;
 	tuple->eth_proto = htons(ETH_P_IP);
 
-	return qede_tc_parse_v4_common(edev, f, tuple);
+	return qede_flow_parse_v4_common(edev, rule, tuple);
 }
 
 static int
-qede_parse_flower_attr(struct qede_dev *edev, __be16 proto,
-		       struct tc_cls_flower_offload *f,
-		       struct qede_arfs_tuple *tuple)
+qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
+		     struct flow_rule *rule, struct qede_arfs_tuple *tuple)
 {
+	struct flow_dissector *dissector = rule->match.dissector;
 	int rc = -EINVAL;
 	u8 ip_proto = 0;
 
 	memset(tuple, 0, sizeof(*tuple));
 
-	if (f->dissector->used_keys &
+	if (dissector->used_keys &
 	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
 		DP_NOTICE(edev, "Unsupported key set:0x%x\n",
-			  f->dissector->used_keys);
+			  dissector->used_keys);
 		return -EOPNOTSUPP;
 	}
 
@@ -2197,25 +1921,23 @@ qede_parse_flower_attr(struct qede_dev *edev, __be16 proto,
 		return -EPROTONOSUPPORT;
 	}
 
-	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
-		struct flow_dissector_key_basic *key;
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
 
-		key = skb_flow_dissector_target(f->dissector,
-						FLOW_DISSECTOR_KEY_BASIC,
-						f->key);
-		ip_proto = key->ip_proto;
+		flow_rule_match_basic(rule, &match);
+		ip_proto = match.key->ip_proto;
 	}
 
 	if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP))
-		rc = qede_tc_parse_tcp_v4(edev, f, tuple);
+		rc = qede_flow_parse_tcp_v4(edev, rule, tuple);
 	else if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IPV6))
-		rc = qede_tc_parse_tcp_v6(edev, f, tuple);
+		rc = qede_flow_parse_tcp_v6(edev, rule, tuple);
 	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IP))
-		rc = qede_tc_parse_udp_v4(edev, f, tuple);
+		rc = qede_flow_parse_udp_v4(edev, rule, tuple);
 	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IPV6))
-		rc = qede_tc_parse_udp_v6(edev, f, tuple);
+		rc = qede_flow_parse_udp_v6(edev, rule, tuple);
 	else
-		DP_NOTICE(edev, "Invalid tc protocol request\n");
+		DP_NOTICE(edev, "Invalid protocol request\n");
 
 	return rc;
 }
@@ -2235,7 +1957,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse flower attribute and prepare filter */
-	if (qede_parse_flower_attr(edev, proto, f, &t))
+	if (qede_parse_flow_attr(edev, proto, f->rule, &t))
 		goto unlock;
 
 	/* Validate profile mode and number of filters */
@@ -2248,7 +1970,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
 	}
 
 	/* parse tc actions and get the vf_id */
-	if (qede_parse_actions(edev, f->exts))
+	if (qede_parse_actions(edev, &f->rule->action))
 		goto unlock;
 
 	if (qede_flow_find_fltr(edev, &t)) {
@@ -2290,3 +2012,141 @@ unlock:
 	__qede_unlock(edev);
 	return rc;
 }
+
+static int qede_flow_spec_validate(struct qede_dev *edev,
+				   struct flow_action *flow_action,
+				   struct qede_arfs_tuple *t,
+				   __u32 location)
+{
+	if (location >= QEDE_RFS_MAX_FLTR) {
+		DP_INFO(edev, "Location out-of-bounds\n");
+		return -EINVAL;
+	}
+
+	/* Check location isn't already in use */
+	if (test_bit(location, edev->arfs->arfs_fltr_bmap)) {
+		DP_INFO(edev, "Location already in use\n");
+		return -EINVAL;
+	}
+
+	/* Check if the filtering-mode could support the filter */
+	if (edev->arfs->filter_count &&
+	    edev->arfs->mode != t->mode) {
+		DP_INFO(edev,
+			"flow_spec would require filtering mode %08x, but %08x is configured\n",
+			t->mode, edev->arfs->filter_count);
+		return -EINVAL;
+	}
+
+	if (qede_parse_actions(edev, flow_action))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int qede_flow_spec_to_rule(struct qede_dev *edev,
+				  struct qede_arfs_tuple *t,
+				  struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_rx_flow_spec_input input = {};
+	struct ethtool_rx_flow_rule *flow;
+	__be16 proto;
+	int err = 0;
+
+	if (qede_flow_spec_validate_unused(edev, fs))
+		return -EOPNOTSUPP;
+
+	switch ((fs->flow_type & ~FLOW_EXT)) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+		proto = htons(ETH_P_IP);
+		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		proto = htons(ETH_P_IPV6);
+		break;
+	default:
+		DP_VERBOSE(edev, NETIF_MSG_IFUP,
+			   "Can't support flow of type %08x\n", fs->flow_type);
+		return -EOPNOTSUPP;
+	}
+
+	input.fs = fs;
+	flow = ethtool_rx_flow_rule_create(&input);
+	if (IS_ERR(flow))
+		return PTR_ERR(flow);
+
+	if (qede_parse_flow_attr(edev, proto, flow->rule, t)) {
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	/* Make sure location is valid and filter isn't already set */
+	err = qede_flow_spec_validate(edev, &flow->rule->action, t,
+				      fs->location);
+err_out:
+	ethtool_rx_flow_rule_destroy(flow);
+	return err;
+
+}
+
+int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
+{
+	struct ethtool_rx_flow_spec *fsp = &info->fs;
+	struct qede_arfs_fltr_node *n;
+	struct qede_arfs_tuple t;
+	int min_hlen, rc;
+
+	__qede_lock(edev);
+
+	if (!edev->arfs) {
+		rc = -EPERM;
+		goto unlock;
+	}
+
+	/* Translate the flow specification into something fittign our DB */
+	rc = qede_flow_spec_to_rule(edev, &t, fsp);
+	if (rc)
+		goto unlock;
+
+	if (qede_flow_find_fltr(edev, &t)) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+
+	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	if (!n) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	min_hlen = qede_flow_get_min_header_size(&t);
+	n->data = kzalloc(min_hlen, GFP_KERNEL);
+	if (!n->data) {
+		kfree(n);
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	n->sw_id = fsp->location;
+	set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap);
+	n->buf_len = min_hlen;
+
+	memcpy(&n->tuple, &t, sizeof(n->tuple));
+
+	qede_flow_set_destination(edev, n, fsp);
+
+	/* Build a minimal header according to the flow */
+	n->tuple.build_hdr(&n->tuple, n->data);
+
+	rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0);
+	if (rc)
+		goto unlock;
+
+	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
+	rc = qede_poll_arfs_filter_config(edev, n);
+unlock:
+	__qede_unlock(edev);
+
+	return rc;
+}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 1a78027de071..31b046e24565 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1466,8 +1466,8 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 #if ((MAX_SKB_FRAGS + 2) > ETH_TX_MAX_BDS_PER_NON_LSO_PACKET)
 	if (qede_pkt_req_lin(skb, xmit_type)) {
 		if (skb_linearize(skb)) {
-			DP_NOTICE(edev,
-				  "SKB linearization failed - silently dropping this SKB\n");
+			txq->tx_mem_alloc_err++;
+
 			dev_kfree_skb_any(skb);
 			return NETDEV_TX_OK;
 		}
@@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NETDEV_TX_OK;
 }
 
+u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb,
+		      struct net_device *sb_dev,
+		      select_queue_fallback_t fallback)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	int total_txq;
+
+	total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc;
+
+	return QEDE_TSS_COUNT(edev) ?
+		fallback(dev, skb, NULL) % total_txq :  0;
+}
+
 /* 8B udp header + 8B base tunnel header + 32B option length */
 #define QEDE_MAX_TUN_HDR_LEN 48
 
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 46d0f2eaa0c0..02a97c659e29 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -133,23 +133,12 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id);
 static void qede_remove(struct pci_dev *pdev);
 static void qede_shutdown(struct pci_dev *pdev);
 static void qede_link_update(void *dev, struct qed_link_output *link);
+static void qede_schedule_recovery_handler(void *dev);
+static void qede_recovery_handler(struct qede_dev *edev);
 static void qede_get_eth_tlv_data(void *edev, void *data);
 static void qede_get_generic_tlv_data(void *edev,
 				      struct qed_generic_tlvs *data);
 
-/* The qede lock is used to protect driver state change and driver flows that
- * are not reentrant.
- */
-void __qede_lock(struct qede_dev *edev)
-{
-	mutex_lock(&edev->qede_lock);
-}
-
-void __qede_unlock(struct qede_dev *edev)
-{
-	mutex_unlock(&edev->qede_lock);
-}
-
 #ifdef CONFIG_QED_SRIOV
 static int qede_set_vf_vlan(struct net_device *ndev, int vf, u16 vlan, u8 qos,
 			    __be16 vlan_proto)
@@ -231,6 +220,7 @@ static struct qed_eth_cb_ops qede_ll_ops = {
 		.arfs_filter_op = qede_arfs_filter_op,
 #endif
 		.link_update = qede_link_update,
+		.schedule_recovery_handler = qede_schedule_recovery_handler,
 		.get_generic_tlv_data = qede_get_generic_tlv_data,
 		.get_protocol_tlv_data = qede_get_eth_tlv_data,
 	},
@@ -631,6 +621,7 @@ static const struct net_device_ops qede_netdev_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
 	.ndo_start_xmit = qede_start_xmit,
+	.ndo_select_queue = qede_select_queue,
 	.ndo_set_rx_mode = qede_set_rx_mode,
 	.ndo_set_mac_address = qede_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
@@ -666,6 +657,7 @@ static const struct net_device_ops qede_netdev_vf_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
 	.ndo_start_xmit = qede_start_xmit,
+	.ndo_select_queue = qede_select_queue,
 	.ndo_set_rx_mode = qede_set_rx_mode,
 	.ndo_set_mac_address = qede_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
@@ -684,6 +676,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
 	.ndo_start_xmit = qede_start_xmit,
+	.ndo_select_queue = qede_select_queue,
 	.ndo_set_rx_mode = qede_set_rx_mode,
 	.ndo_set_mac_address = qede_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
@@ -950,11 +943,57 @@ err:
 	return -ENOMEM;
 }
 
+/* The qede lock is used to protect driver state change and driver flows that
+ * are not reentrant.
+ */
+void __qede_lock(struct qede_dev *edev)
+{
+	mutex_lock(&edev->qede_lock);
+}
+
+void __qede_unlock(struct qede_dev *edev)
+{
+	mutex_unlock(&edev->qede_lock);
+}
+
+/* This version of the lock should be used when acquiring the RTNL lock is also
+ * needed in addition to the internal qede lock.
+ */
+void qede_lock(struct qede_dev *edev)
+{
+	rtnl_lock();
+	__qede_lock(edev);
+}
+
+void qede_unlock(struct qede_dev *edev)
+{
+	__qede_unlock(edev);
+	rtnl_unlock();
+}
+
 static void qede_sp_task(struct work_struct *work)
 {
 	struct qede_dev *edev = container_of(work, struct qede_dev,
 					     sp_task.work);
 
+	/* The locking scheme depends on the specific flag:
+	 * In case of QEDE_SP_RECOVERY, acquiring the RTNL lock is required to
+	 * ensure that ongoing flows are ended and new ones are not started.
+	 * In other cases - only the internal qede lock should be acquired.
+	 */
+
+	if (test_and_clear_bit(QEDE_SP_RECOVERY, &edev->sp_flags)) {
+#ifdef CONFIG_QED_SRIOV
+		/* SRIOV must be disabled outside the lock to avoid a deadlock.
+		 * The recovery of the active VFs is currently not supported.
+		 */
+		qede_sriov_configure(edev->pdev, 0);
+#endif
+		qede_lock(edev);
+		qede_recovery_handler(edev);
+		qede_unlock(edev);
+	}
+
 	__qede_lock(edev);
 
 	if (test_and_clear_bit(QEDE_SP_RX_MODE, &edev->sp_flags))
@@ -1031,6 +1070,7 @@ static void qede_log_probe(struct qede_dev *edev)
 
 enum qede_probe_mode {
 	QEDE_PROBE_NORMAL,
+	QEDE_PROBE_RECOVERY,
 };
 
 static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
@@ -1051,6 +1091,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	probe_params.dp_module = dp_module;
 	probe_params.dp_level = dp_level;
 	probe_params.is_vf = is_vf;
+	probe_params.recov_in_prog = (mode == QEDE_PROBE_RECOVERY);
 	cdev = qed_ops->common->probe(pdev, &probe_params);
 	if (!cdev) {
 		rc = -ENODEV;
@@ -1078,40 +1119,52 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	if (rc)
 		goto err2;
 
-	edev = qede_alloc_etherdev(cdev, pdev, &dev_info, dp_module,
-				   dp_level);
-	if (!edev) {
-		rc = -ENOMEM;
-		goto err2;
+	if (mode != QEDE_PROBE_RECOVERY) {
+		edev = qede_alloc_etherdev(cdev, pdev, &dev_info, dp_module,
+					   dp_level);
+		if (!edev) {
+			rc = -ENOMEM;
+			goto err2;
+		}
+	} else {
+		struct net_device *ndev = pci_get_drvdata(pdev);
+
+		edev = netdev_priv(ndev);
+		edev->cdev = cdev;
+		memset(&edev->stats, 0, sizeof(edev->stats));
+		memcpy(&edev->dev_info, &dev_info, sizeof(dev_info));
 	}
 
 	if (is_vf)
-		edev->flags |= QEDE_FLAG_IS_VF;
+		set_bit(QEDE_FLAGS_IS_VF, &edev->flags);
 
 	qede_init_ndev(edev);
 
-	rc = qede_rdma_dev_add(edev);
+	rc = qede_rdma_dev_add(edev, (mode == QEDE_PROBE_RECOVERY));
 	if (rc)
 		goto err3;
 
-	/* Prepare the lock prior to the registration of the netdev,
-	 * as once it's registered we might reach flows requiring it
-	 * [it's even possible to reach a flow needing it directly
-	 * from there, although it's unlikely].
-	 */
-	INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
-	mutex_init(&edev->qede_lock);
-	rc = register_netdev(edev->ndev);
-	if (rc) {
-		DP_NOTICE(edev, "Cannot register net-device\n");
-		goto err4;
+	if (mode != QEDE_PROBE_RECOVERY) {
+		/* Prepare the lock prior to the registration of the netdev,
+		 * as once it's registered we might reach flows requiring it
+		 * [it's even possible to reach a flow needing it directly
+		 * from there, although it's unlikely].
+		 */
+		INIT_DELAYED_WORK(&edev->sp_task, qede_sp_task);
+		mutex_init(&edev->qede_lock);
+
+		rc = register_netdev(edev->ndev);
+		if (rc) {
+			DP_NOTICE(edev, "Cannot register net-device\n");
+			goto err4;
+		}
 	}
 
 	edev->ops->common->set_name(cdev, edev->ndev->name);
 
 	/* PTP not supported on VFs */
 	if (!is_vf)
-		qede_ptp_enable(edev, true);
+		qede_ptp_enable(edev, (mode == QEDE_PROBE_NORMAL));
 
 	edev->ops->register_ops(cdev, &qede_ll_ops, edev);
 
@@ -1126,7 +1179,7 @@ static int __qede_probe(struct pci_dev *pdev, u32 dp_module, u8 dp_level,
 	return 0;
 
 err4:
-	qede_rdma_dev_remove(edev);
+	qede_rdma_dev_remove(edev, (mode == QEDE_PROBE_RECOVERY));
 err3:
 	free_netdev(edev->ndev);
 err2:
@@ -1162,6 +1215,7 @@ static int qede_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 enum qede_remove_mode {
 	QEDE_REMOVE_NORMAL,
+	QEDE_REMOVE_RECOVERY,
 };
 
 static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
@@ -1172,15 +1226,19 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 
 	DP_INFO(edev, "Starting qede_remove\n");
 
-	qede_rdma_dev_remove(edev);
-	unregister_netdev(ndev);
-	cancel_delayed_work_sync(&edev->sp_task);
+	qede_rdma_dev_remove(edev, (mode == QEDE_REMOVE_RECOVERY));
 
-	qede_ptp_disable(edev);
+	if (mode != QEDE_REMOVE_RECOVERY) {
+		unregister_netdev(ndev);
 
-	edev->ops->common->set_power_state(cdev, PCI_D0);
+		cancel_delayed_work_sync(&edev->sp_task);
 
-	pci_set_drvdata(pdev, NULL);
+		edev->ops->common->set_power_state(cdev, PCI_D0);
+
+		pci_set_drvdata(pdev, NULL);
+	}
+
+	qede_ptp_disable(edev);
 
 	/* Use global ops since we've freed edev */
 	qed_ops->common->slowpath_stop(cdev);
@@ -1194,7 +1252,8 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
 	 * [e.g., QED register callbacks] won't break anything when
 	 * accessing the netdevice.
 	 */
-	 free_netdev(ndev);
+	if (mode != QEDE_REMOVE_RECOVERY)
+		free_netdev(ndev);
 
 	dev_info(&pdev->dev, "Ending qede_remove successfully\n");
 }
@@ -1539,6 +1598,58 @@ static int qede_alloc_mem_load(struct qede_dev *edev)
 	return 0;
 }
 
+static void qede_empty_tx_queue(struct qede_dev *edev,
+				struct qede_tx_queue *txq)
+{
+	unsigned int pkts_compl = 0, bytes_compl = 0;
+	struct netdev_queue *netdev_txq;
+	int rc, len = 0;
+
+	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id);
+
+	while (qed_chain_get_cons_idx(&txq->tx_pbl) !=
+	       qed_chain_get_prod_idx(&txq->tx_pbl)) {
+		DP_VERBOSE(edev, NETIF_MSG_IFDOWN,
+			   "Freeing a packet on tx queue[%d]: chain_cons 0x%x, chain_prod 0x%x\n",
+			   txq->index, qed_chain_get_cons_idx(&txq->tx_pbl),
+			   qed_chain_get_prod_idx(&txq->tx_pbl));
+
+		rc = qede_free_tx_pkt(edev, txq, &len);
+		if (rc) {
+			DP_NOTICE(edev,
+				  "Failed to free a packet on tx queue[%d]: chain_cons 0x%x, chain_prod 0x%x\n",
+				  txq->index,
+				  qed_chain_get_cons_idx(&txq->tx_pbl),
+				  qed_chain_get_prod_idx(&txq->tx_pbl));
+			break;
+		}
+
+		bytes_compl += len;
+		pkts_compl++;
+		txq->sw_tx_cons++;
+	}
+
+	netdev_tx_completed_queue(netdev_txq, pkts_compl, bytes_compl);
+}
+
+static void qede_empty_tx_queues(struct qede_dev *edev)
+{
+	int i;
+
+	for_each_queue(i)
+		if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				struct qede_fastpath *fp;
+
+				fp = &edev->fp_array[i];
+				qede_empty_tx_queue(edev,
+						    &fp->txq[cos]);
+			}
+		}
+}
+
 /* This function inits fp content and resets the SB, RXQ and TXQ structures */
 static void qede_init_fp(struct qede_dev *edev)
 {
@@ -1774,6 +1885,10 @@ static int qede_drain_txq(struct qede_dev *edev,
 static int qede_stop_txq(struct qede_dev *edev,
 			 struct qede_tx_queue *txq, int rss_id)
 {
+	/* delete doorbell from doorbell recovery mechanism */
+	edev->ops->common->db_recovery_del(edev->cdev, txq->doorbell_addr,
+					   &txq->tx_db);
+
 	return edev->ops->q_tx_stop(edev->cdev, rss_id, txq->handle);
 }
 
@@ -1910,6 +2025,11 @@ static int qede_start_txq(struct qede_dev *edev,
 		  DQ_XCM_ETH_TX_BD_PROD_CMD);
 	txq->tx_db.data.agg_flags = DQ_XCM_ETH_DQ_CF_CMD;
 
+	/* register doorbell with doorbell recovery mechanism */
+	rc = edev->ops->common->db_recovery_add(edev->cdev, txq->doorbell_addr,
+						&txq->tx_db, DB_REC_WIDTH_32B,
+						DB_REC_KERNEL);
+
 	return rc;
 }
 
@@ -2044,6 +2164,7 @@ out:
 
 enum qede_unload_mode {
 	QEDE_UNLOAD_NORMAL,
+	QEDE_UNLOAD_RECOVERY,
 };
 
 static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
@@ -2057,7 +2178,10 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	if (!is_locked)
 		__qede_lock(edev);
 
-	edev->state = QEDE_STATE_CLOSED;
+	clear_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags);
+
+	if (mode != QEDE_UNLOAD_RECOVERY)
+		edev->state = QEDE_STATE_CLOSED;
 
 	qede_rdma_dev_event_close(edev);
 
@@ -2065,17 +2189,20 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 	netif_tx_disable(edev->ndev);
 	netif_carrier_off(edev->ndev);
 
-	/* Reset the link */
-	memset(&link_params, 0, sizeof(link_params));
-	link_params.link_up = false;
-	edev->ops->common->set_link(edev->cdev, &link_params);
-	rc = qede_stop_queues(edev);
-	if (rc) {
-		qede_sync_free_irqs(edev);
-		goto out;
-	}
+	if (mode != QEDE_UNLOAD_RECOVERY) {
+		/* Reset the link */
+		memset(&link_params, 0, sizeof(link_params));
+		link_params.link_up = false;
+		edev->ops->common->set_link(edev->cdev, &link_params);
 
-	DP_INFO(edev, "Stopped Queues\n");
+		rc = qede_stop_queues(edev);
+		if (rc) {
+			qede_sync_free_irqs(edev);
+			goto out;
+		}
+
+		DP_INFO(edev, "Stopped Queues\n");
+	}
 
 	qede_vlan_mark_nonconfigured(edev);
 	edev->ops->fastpath_stop(edev->cdev);
@@ -2091,18 +2218,26 @@ static void qede_unload(struct qede_dev *edev, enum qede_unload_mode mode,
 
 	qede_napi_disable_remove(edev);
 
+	if (mode == QEDE_UNLOAD_RECOVERY)
+		qede_empty_tx_queues(edev);
+
 	qede_free_mem_load(edev);
 	qede_free_fp_array(edev);
 
 out:
 	if (!is_locked)
 		__qede_unlock(edev);
+
+	if (mode != QEDE_UNLOAD_RECOVERY)
+		DP_NOTICE(edev, "Link is down\n");
+
 	DP_INFO(edev, "Ending qede unload\n");
 }
 
 enum qede_load_mode {
 	QEDE_LOAD_NORMAL,
 	QEDE_LOAD_RELOAD,
+	QEDE_LOAD_RECOVERY,
 };
 
 static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
@@ -2163,6 +2298,8 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 	/* Program un-configured VLANs */
 	qede_configure_vlan_filters(edev);
 
+	set_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags);
+
 	/* Ask for link-up using current configuration */
 	memset(&link_params, 0, sizeof(link_params));
 	link_params.link_up = true;
@@ -2258,8 +2395,8 @@ static void qede_link_update(void *dev, struct qed_link_output *link)
 {
 	struct qede_dev *edev = dev;
 
-	if (!netif_running(edev->ndev)) {
-		DP_VERBOSE(edev, NETIF_MSG_LINK, "Interface is not running\n");
+	if (!test_bit(QEDE_FLAGS_LINK_REQUESTED, &edev->flags)) {
+		DP_VERBOSE(edev, NETIF_MSG_LINK, "Interface is not ready\n");
 		return;
 	}
 
@@ -2280,6 +2417,77 @@ static void qede_link_update(void *dev, struct qed_link_output *link)
 	}
 }
 
+static void qede_schedule_recovery_handler(void *dev)
+{
+	struct qede_dev *edev = dev;
+
+	if (edev->state == QEDE_STATE_RECOVERY) {
+		DP_NOTICE(edev,
+			  "Avoid scheduling a recovery handling since already in recovery state\n");
+		return;
+	}
+
+	set_bit(QEDE_SP_RECOVERY, &edev->sp_flags);
+	schedule_delayed_work(&edev->sp_task, 0);
+
+	DP_INFO(edev, "Scheduled a recovery handler\n");
+}
+
+static void qede_recovery_failed(struct qede_dev *edev)
+{
+	netdev_err(edev->ndev, "Recovery handling has failed. Power cycle is needed.\n");
+
+	netif_device_detach(edev->ndev);
+
+	if (edev->cdev)
+		edev->ops->common->set_power_state(edev->cdev, PCI_D3hot);
+}
+
+static void qede_recovery_handler(struct qede_dev *edev)
+{
+	u32 curr_state = edev->state;
+	int rc;
+
+	DP_NOTICE(edev, "Starting a recovery process\n");
+
+	/* No need to acquire first the qede_lock since is done by qede_sp_task
+	 * before calling this function.
+	 */
+	edev->state = QEDE_STATE_RECOVERY;
+
+	edev->ops->common->recovery_prolog(edev->cdev);
+
+	if (curr_state == QEDE_STATE_OPEN)
+		qede_unload(edev, QEDE_UNLOAD_RECOVERY, true);
+
+	__qede_remove(edev->pdev, QEDE_REMOVE_RECOVERY);
+
+	rc = __qede_probe(edev->pdev, edev->dp_module, edev->dp_level,
+			  IS_VF(edev), QEDE_PROBE_RECOVERY);
+	if (rc) {
+		edev->cdev = NULL;
+		goto err;
+	}
+
+	if (curr_state == QEDE_STATE_OPEN) {
+		rc = qede_load(edev, QEDE_LOAD_RECOVERY, true);
+		if (rc)
+			goto err;
+
+		qede_config_rx_mode(edev->ndev);
+		udp_tunnel_get_rx_info(edev->ndev);
+	}
+
+	edev->state = curr_state;
+
+	DP_NOTICE(edev, "Recovery handling is done\n");
+
+	return;
+
+err:
+	qede_recovery_failed(edev);
+}
+
 static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	struct netdev_queue *netdev_txq;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 013ff567283c..bddb2b5982dc 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -223,12 +223,12 @@ static int qede_ptp_cfg_filters(struct qede_dev *edev)
 
 	switch (ptp->tx_type) {
 	case HWTSTAMP_TX_ON:
-		edev->flags |= QEDE_TX_TIMESTAMPING_EN;
+		set_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags);
 		tx_type = QED_PTP_HWTSTAMP_TX_ON;
 		break;
 
 	case HWTSTAMP_TX_OFF:
-		edev->flags &= ~QEDE_TX_TIMESTAMPING_EN;
+		clear_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags);
 		tx_type = QED_PTP_HWTSTAMP_TX_OFF;
 		break;
 
@@ -490,18 +490,17 @@ int qede_ptp_enable(struct qede_dev *edev, bool init_tc)
 
 	ptp->clock = ptp_clock_register(&ptp->clock_info, &edev->pdev->dev);
 	if (IS_ERR(ptp->clock)) {
-		rc = -EINVAL;
 		DP_ERR(edev, "PTP clock registration failed\n");
+		qede_ptp_disable(edev);
+		rc = -EINVAL;
 		goto err2;
 	}
 
 	return 0;
 
-err2:
-	qede_ptp_disable(edev);
-	ptp->clock = NULL;
 err1:
 	kfree(ptp);
+err2:
 	edev->ptp = NULL;
 
 	return rc;
@@ -518,7 +517,7 @@ void qede_ptp_tx_ts(struct qede_dev *edev, struct sk_buff *skb)
 	if (test_and_set_bit_lock(QEDE_FLAGS_PTP_TX_IN_PRORGESS, &edev->flags))
 		return;
 
-	if (unlikely(!(edev->flags & QEDE_TX_TIMESTAMPING_EN))) {
+	if (unlikely(!test_bit(QEDE_FLAGS_TX_TIMESTAMPING_EN, &edev->flags))) {
 		DP_NOTICE(edev,
 			  "Tx timestamping was not enabled, this packet will not be timestamped\n");
 	} else if (unlikely(ptp->tx_skb)) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
index 1900bf7e67d1..ffabc2d2f082 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c
@@ -50,6 +50,8 @@ static void _qede_rdma_dev_add(struct qede_dev *edev)
 	if (!qedr_drv)
 		return;
 
+	/* Leftovers from previous error recovery */
+	edev->rdma_info.exp_recovery = false;
 	edev->rdma_info.qedr_dev = qedr_drv->add(edev->cdev, edev->pdev,
 						 edev->ndev);
 }
@@ -87,21 +89,26 @@ static void qede_rdma_destroy_wq(struct qede_dev *edev)
 	destroy_workqueue(edev->rdma_info.rdma_wq);
 }
 
-int qede_rdma_dev_add(struct qede_dev *edev)
+int qede_rdma_dev_add(struct qede_dev *edev, bool recovery)
 {
-	int rc = 0;
+	int rc;
 
-	if (qede_rdma_supported(edev)) {
-		rc = qede_rdma_create_wq(edev);
-		if (rc)
-			return rc;
+	if (!qede_rdma_supported(edev))
+		return 0;
 
-		INIT_LIST_HEAD(&edev->rdma_info.entry);
-		mutex_lock(&qedr_dev_list_lock);
-		list_add_tail(&edev->rdma_info.entry, &qedr_dev_list);
-		_qede_rdma_dev_add(edev);
-		mutex_unlock(&qedr_dev_list_lock);
-	}
+	/* Cannot start qedr while recovering since it wasn't fully stopped */
+	if (recovery)
+		return 0;
+
+	rc = qede_rdma_create_wq(edev);
+	if (rc)
+		return rc;
+
+	INIT_LIST_HEAD(&edev->rdma_info.entry);
+	mutex_lock(&qedr_dev_list_lock);
+	list_add_tail(&edev->rdma_info.entry, &qedr_dev_list);
+	_qede_rdma_dev_add(edev);
+	mutex_unlock(&qedr_dev_list_lock);
 
 	return rc;
 }
@@ -110,19 +117,30 @@ static void _qede_rdma_dev_remove(struct qede_dev *edev)
 {
 	if (qedr_drv && qedr_drv->remove && edev->rdma_info.qedr_dev)
 		qedr_drv->remove(edev->rdma_info.qedr_dev);
-	edev->rdma_info.qedr_dev = NULL;
 }
 
-void qede_rdma_dev_remove(struct qede_dev *edev)
+void qede_rdma_dev_remove(struct qede_dev *edev, bool recovery)
 {
 	if (!qede_rdma_supported(edev))
 		return;
 
-	qede_rdma_destroy_wq(edev);
-	mutex_lock(&qedr_dev_list_lock);
-	_qede_rdma_dev_remove(edev);
-	list_del(&edev->rdma_info.entry);
-	mutex_unlock(&qedr_dev_list_lock);
+	/* Cannot remove qedr while recovering since it wasn't fully stopped */
+	if (!recovery) {
+		qede_rdma_destroy_wq(edev);
+		mutex_lock(&qedr_dev_list_lock);
+		if (!edev->rdma_info.exp_recovery)
+			_qede_rdma_dev_remove(edev);
+		edev->rdma_info.qedr_dev = NULL;
+		list_del(&edev->rdma_info.entry);
+		mutex_unlock(&qedr_dev_list_lock);
+	} else {
+		if (!edev->rdma_info.exp_recovery) {
+			mutex_lock(&qedr_dev_list_lock);
+			_qede_rdma_dev_remove(edev);
+			mutex_unlock(&qedr_dev_list_lock);
+		}
+		edev->rdma_info.exp_recovery = true;
+	}
 }
 
 static void _qede_rdma_dev_open(struct qede_dev *edev)
@@ -204,7 +222,8 @@ void qede_rdma_unregister_driver(struct qedr_driver *drv)
 
 	mutex_lock(&qedr_dev_list_lock);
 	list_for_each_entry(edev, &qedr_dev_list, rdma_info.entry) {
-		if (edev->rdma_info.qedr_dev)
+		/* If device has experienced recovery it was already removed */
+		if (edev->rdma_info.qedr_dev && !edev->rdma_info.exp_recovery)
 			_qede_rdma_dev_remove(edev);
 	}
 	qedr_drv = NULL;
@@ -284,6 +303,10 @@ static void qede_rdma_add_event(struct qede_dev *edev,
 {
 	struct qede_rdma_event_work *event_node;
 
+	/* If a recovery was experienced avoid adding the event */
+	if (edev->rdma_info.exp_recovery)
+		return;
+
 	if (!edev->rdma_info.qedr_dev)
 		return;
 
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index 10b075bc5959..b61b88cbc0c7 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -3886,6 +3886,12 @@ static int ql3xxx_probe(struct pci_dev *pdev,
 	netif_stop_queue(ndev);
 
 	qdev->workqueue = create_singlethread_workqueue(ndev->name);
+	if (!qdev->workqueue) {
+		unregister_netdev(ndev);
+		err = -ENOMEM;
+		goto err_out_iounmap;
+	}
+
 	INIT_DELAYED_WORK(&qdev->reset_work, ql_reset_work);
 	INIT_DELAYED_WORK(&qdev->tx_timeout_work, ql_tx_timeout_work);
 	INIT_DELAYED_WORK(&qdev->link_state_work, ql_link_state_machine_work);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 0c443ea98479..374a4d4371f9 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -497,7 +497,7 @@ struct qlcnic_hardware_context {
 	u16 board_type;
 	u16 supported_type;
 
-	u16 link_speed;
+	u32 link_speed;
 	u16 link_duplex;
 	u16 link_autoneg;
 	u16 module_type;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
index d344e9d43832..af38d3d73291 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c
@@ -434,14 +434,14 @@ int qlcnic_82xx_fw_cmd_create_tx_ctx(struct qlcnic_adapter *adapter,
 	*(tx_ring->hw_consumer) = 0;
 
 	rq_size = SIZEOF_HOSTRQ_TX(struct qlcnic_hostrq_tx_ctx);
-	rq_addr = dma_zalloc_coherent(&adapter->pdev->dev, rq_size,
-				      &rq_phys_addr, GFP_KERNEL);
+	rq_addr = dma_alloc_coherent(&adapter->pdev->dev, rq_size,
+				     &rq_phys_addr, GFP_KERNEL);
 	if (!rq_addr)
 		return -ENOMEM;
 
 	rsp_size = SIZEOF_CARDRSP_TX(struct qlcnic_cardrsp_tx_ctx);
-	rsp_addr = dma_zalloc_coherent(&adapter->pdev->dev, rsp_size,
-				       &rsp_phys_addr, GFP_KERNEL);
+	rsp_addr = dma_alloc_coherent(&adapter->pdev->dev, rsp_size,
+				      &rsp_phys_addr, GFP_KERNEL);
 	if (!rsp_addr) {
 		err = -ENOMEM;
 		goto out_free_rq;
@@ -855,8 +855,8 @@ int qlcnic_82xx_get_nic_info(struct qlcnic_adapter *adapter,
 	struct qlcnic_cmd_args cmd;
 	size_t  nic_size = sizeof(struct qlcnic_info_le);
 
-	nic_info_addr = dma_zalloc_coherent(&adapter->pdev->dev, nic_size,
-					    &nic_dma_t, GFP_KERNEL);
+	nic_info_addr = dma_alloc_coherent(&adapter->pdev->dev, nic_size,
+					   &nic_dma_t, GFP_KERNEL);
 	if (!nic_info_addr)
 		return -ENOMEM;
 
@@ -909,8 +909,8 @@ int qlcnic_82xx_set_nic_info(struct qlcnic_adapter *adapter,
 	if (adapter->ahw->op_mode != QLCNIC_MGMT_FUNC)
 		return err;
 
-	nic_info_addr = dma_zalloc_coherent(&adapter->pdev->dev, nic_size,
-					    &nic_dma_t, GFP_KERNEL);
+	nic_info_addr = dma_alloc_coherent(&adapter->pdev->dev, nic_size,
+					   &nic_dma_t, GFP_KERNEL);
 	if (!nic_info_addr)
 		return -ENOMEM;
 
@@ -964,8 +964,8 @@ int qlcnic_82xx_get_pci_info(struct qlcnic_adapter *adapter,
 	void *pci_info_addr;
 	int err = 0, i;
 
-	pci_info_addr = dma_zalloc_coherent(&adapter->pdev->dev, pci_size,
-					    &pci_info_dma_t, GFP_KERNEL);
+	pci_info_addr = dma_alloc_coherent(&adapter->pdev->dev, pci_size,
+					   &pci_info_dma_t, GFP_KERNEL);
 	if (!pci_info_addr)
 		return -ENOMEM;
 
@@ -1078,8 +1078,8 @@ int qlcnic_get_port_stats(struct qlcnic_adapter *adapter, const u8 func,
 		return -EIO;
 	}
 
-	stats_addr = dma_zalloc_coherent(&adapter->pdev->dev, stats_size,
-					 &stats_dma_t, GFP_KERNEL);
+	stats_addr = dma_alloc_coherent(&adapter->pdev->dev, stats_size,
+					&stats_dma_t, GFP_KERNEL);
 	if (!stats_addr)
 		return -ENOMEM;
 
@@ -1134,8 +1134,8 @@ int qlcnic_get_mac_stats(struct qlcnic_adapter *adapter,
 	if (mac_stats == NULL)
 		return -ENOMEM;
 
-	stats_addr = dma_zalloc_coherent(&adapter->pdev->dev, stats_size,
-					 &stats_dma_t, GFP_KERNEL);
+	stats_addr = dma_alloc_coherent(&adapter->pdev->dev, stats_size,
+					&stats_dma_t, GFP_KERNEL);
 	if (!stats_addr)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 3b0adda7cc9c..a4cd6f2cfb86 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -1048,6 +1048,8 @@ int qlcnic_do_lb_test(struct qlcnic_adapter *adapter, u8 mode)
 
 	for (i = 0; i < QLCNIC_NUM_ILB_PKT; i++) {
 		skb = netdev_alloc_skb(adapter->netdev, QLCNIC_ILB_PKT_SIZE);
+		if (!skb)
+			break;
 		qlcnic_create_loopback_buff(skb->data, adapter->mac_addr);
 		skb_put(skb, QLCNIC_ILB_PKT_SIZE);
 		adapter->ahw->diag_cnt = 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index d42ba2293d8c..7a873002e626 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -396,7 +396,8 @@ static int qlcnic_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 
 static int qlcnic_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 			struct net_device *netdev,
-			const unsigned char *addr, u16 vid, u16 flags)
+			const unsigned char *addr, u16 vid, u16 flags,
+			struct netlink_ext_ack *extack)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	int err = 0;
@@ -2993,10 +2994,8 @@ int qlcnic_check_temp(struct qlcnic_adapter *adapter)
 static inline void dump_tx_ring_desc(struct qlcnic_host_tx_ring *tx_ring)
 {
 	int i;
-	struct cmd_desc_type0 *tx_desc_info;
 
 	for (i = 0; i < tx_ring->num_desc; i++) {
-		tx_desc_info = &tx_ring->desc_head[i];
 		pr_info("TX Desc: %d\n", i);
 		print_hex_dump(KERN_INFO, "TX: ", DUMP_PREFIX_OFFSET, 16, 1,
 			       &tx_ring->desc_head[i],
@@ -4008,19 +4007,12 @@ int qlcnic_validate_rings(struct qlcnic_adapter *adapter, __u32 ring_cnt,
 			  int queue_type)
 {
 	struct net_device *netdev = adapter->netdev;
-	u8 max_hw_rings = 0;
 	char buf[8];
-	int cur_rings;
 
-	if (queue_type == QLCNIC_RX_QUEUE) {
-		max_hw_rings = adapter->max_sds_rings;
-		cur_rings = adapter->drv_sds_rings;
+	if (queue_type == QLCNIC_RX_QUEUE)
 		strcpy(buf, "SDS");
-	} else if (queue_type == QLCNIC_TX_QUEUE) {
-		max_hw_rings = adapter->max_tx_rings;
-		cur_rings = adapter->drv_tx_rings;
+	else
 		strcpy(buf, "Tx");
-	}
 
 	if (!is_power_of_2(ring_cnt)) {
 		netdev_err(netdev, "%s rings value should be a power of 2\n",
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
index 50eaafa3eaba..af3b037fa442 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c
@@ -1067,9 +1067,6 @@ static int qlcnic_sriov_pf_cfg_ip_cmd(struct qlcnic_bc_trans *trans,
 	struct qlcnic_vf_info *vf = trans->vf;
 	struct qlcnic_adapter *adapter = vf->adapter;
 	int err = -EIO;
-	u8 op;
-
-	op =  cmd->req.arg[1] & 0xff;
 
 	cmd->req.arg[1] |= vf->vp->handle << 16;
 	cmd->req.arg[1] |= BIT_31;
@@ -1339,14 +1336,13 @@ static int qlcnic_sriov_pf_get_acl_cmd(struct qlcnic_bc_trans *trans,
 {
 	struct qlcnic_vf_info *vf = trans->vf;
 	struct qlcnic_vport *vp = vf->vp;
-	u8 cmd_op, mode = vp->vlan_mode;
+	u8 mode = vp->vlan_mode;
 	struct qlcnic_adapter *adapter;
 	struct qlcnic_sriov *sriov;
 
 	adapter = vf->adapter;
 	sriov = adapter->ahw->sriov;
 
-	cmd_op = trans->req_hdr->cmd_op;
 	cmd->rsp.arg[0] |= 1 << 25;
 
 	/* For 84xx adapter in case of PVID , PFD should send vlan mode as
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
index 5edbd532127d..a6886cc5654c 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
@@ -249,8 +249,8 @@ static void ql_update_stats(struct ql_adapter *qdev)
 
 	spin_lock(&qdev->stats_lock);
 	if (ql_sem_spinlock(qdev, qdev->xg_sem_mask)) {
-			netif_err(qdev, drv, qdev->ndev,
-				  "Couldn't get xgmac sem.\n");
+		netif_err(qdev, drv, qdev->ndev,
+			  "Couldn't get xgmac sem.\n");
 		goto quit;
 	}
 	/*
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 059ba9429e51..07e1c623048e 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -1159,10 +1159,10 @@ static void ql_update_lbq(struct ql_adapter *qdev, struct rx_ring *rx_ring)
 
 			map = lbq_desc->p.pg_chunk.map +
 				lbq_desc->p.pg_chunk.offset;
-				dma_unmap_addr_set(lbq_desc, mapaddr, map);
+			dma_unmap_addr_set(lbq_desc, mapaddr, map);
 			dma_unmap_len_set(lbq_desc, maplen,
 					rx_ring->lbq_buf_size);
-				*lbq_desc->addr = cpu_to_le64(map);
+			*lbq_desc->addr = cpu_to_le64(map);
 
 			pci_dma_sync_single_for_device(qdev->pdev, map,
 						rx_ring->lbq_buf_size,
@@ -4681,6 +4681,11 @@ static int ql_init_device(struct pci_dev *pdev, struct net_device *ndev,
 	 */
 	qdev->workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM,
 						  ndev->name);
+	if (!qdev->workqueue) {
+		err = -ENOMEM;
+		goto err_out2;
+	}
+
 	INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work);
 	INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work);
diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
index 031f6e6ee9c1..20d2400ad300 100644
--- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c
+++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c
@@ -776,7 +776,7 @@ int emac_mac_rx_tx_rings_alloc_all(struct emac_adapter *adpt)
 			    8 + 2 * 8; /* 8 byte per one Tx and two Rx rings */
 
 	ring_header->used = 0;
-	ring_header->v_addr = dma_zalloc_coherent(dev, ring_header->size,
+	ring_header->v_addr = dma_alloc_coherent(dev, ring_header->size,
 						 &ring_header->dma_addr,
 						 GFP_KERNEL);
 	if (!ring_header->v_addr)
@@ -1204,7 +1204,7 @@ void emac_mac_tx_process(struct emac_adapter *adpt, struct emac_tx_queue *tx_q)
 		if (tpbuf->skb) {
 			pkts_compl++;
 			bytes_compl += tpbuf->skb->len;
-			dev_kfree_skb_irq(tpbuf->skb);
+			dev_consume_skb_irq(tpbuf->skb);
 			tpbuf->skb = NULL;
 		}
 
diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c
index a9f1bc013364..bcb890b18a94 100644
--- a/drivers/net/ethernet/qualcomm/qca_debug.c
+++ b/drivers/net/ethernet/qualcomm/qca_debug.c
@@ -61,6 +61,7 @@ static const char qcaspi_gstrings_stats[][ETH_GSTRING_LEN] = {
 	"Transmit ring full",
 	"SPI errors",
 	"Write verify errors",
+	"Buffer available errors",
 };
 
 #ifdef CONFIG_DEBUG_FS
@@ -125,19 +126,7 @@ qcaspi_info_show(struct seq_file *s, void *what)
 
 	return 0;
 }
-
-static int
-qcaspi_info_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, qcaspi_info_show, inode->i_private);
-}
-
-static const struct file_operations qcaspi_info_ops = {
-	.open = qcaspi_info_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(qcaspi_info);
 
 void
 qcaspi_init_device_debugfs(struct qcaspi *qca)
@@ -153,7 +142,7 @@ qcaspi_init_device_debugfs(struct qcaspi *qca)
 		return;
 	}
 	debugfs_create_file("info", S_IFREG | 0444, device_root, qca,
-			    &qcaspi_info_ops);
+			    &qcaspi_info_fops);
 }
 
 void
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index d5310504f436..97f92953bdb9 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -289,6 +289,14 @@ qcaspi_transmit(struct qcaspi *qca)
 
 	qcaspi_read_register(qca, SPI_REG_WRBUF_SPC_AVA, &available);
 
+	if (available > QCASPI_HW_BUF_LEN) {
+		/* This could only happen by interferences on the SPI line.
+		 * So retry later ...
+		 */
+		qca->stats.buf_avail_err++;
+		return -1;
+	}
+
 	while (qca->txr.skb[qca->txr.head]) {
 		pkt_len = qca->txr.skb[qca->txr.head]->len + QCASPI_HW_PKT_LEN;
 
@@ -355,7 +363,13 @@ qcaspi_receive(struct qcaspi *qca)
 	netdev_dbg(net_dev, "qcaspi_receive: SPI_REG_RDBUF_BYTE_AVA: Value: %08x\n",
 		   available);
 
-	if (available == 0) {
+	if (available > QCASPI_HW_BUF_LEN) {
+		/* This could only happen by interferences on the SPI line.
+		 * So retry later ...
+		 */
+		qca->stats.buf_avail_err++;
+		return -1;
+	} else if (available == 0) {
 		netdev_dbg(net_dev, "qcaspi_receive called without any data being available!\n");
 		return -1;
 	}
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h
index 2d2c49726492..eb9af45fcc5e 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.h
+++ b/drivers/net/ethernet/qualcomm/qca_spi.h
@@ -74,6 +74,7 @@ struct qcaspi_stats {
 	u64 ring_full;
 	u64 spi_err;
 	u64 write_verify_failed;
+	u64 buf_avail_err;
 };
 
 struct qcaspi {
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 5f4e447c5dce..b8bbee645f51 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -301,10 +301,13 @@ static int rmnet_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct rmnet_port *port;
 	u16 mux_id;
 
+	if (!dev)
+		return -ENODEV;
+
 	real_dev = __dev_get_by_index(dev_net(dev),
 				      nla_get_u32(tb[IFLA_LINK]));
 
-	if (!real_dev || !dev || !rmnet_is_real_dev_registered(real_dev))
+	if (!real_dev || !rmnet_is_real_dev_registered(real_dev))
 		return -ENODEV;
 
 	port = rmnet_get_port_rtnl(real_dev);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
index 3ee8ae9b6838..f6cf59aee212 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_map_command.c
@@ -20,17 +20,12 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
 				    struct rmnet_port *port,
 				    int enable)
 {
-	struct rmnet_map_control_command *cmd;
 	struct rmnet_endpoint *ep;
 	struct net_device *vnd;
-	u16 ip_family;
-	u16 fc_seq;
-	u32 qos_id;
 	u8 mux_id;
 	int r;
 
 	mux_id = RMNET_MAP_GET_MUX_ID(skb);
-	cmd = RMNET_MAP_GET_CMD_START(skb);
 
 	if (mux_id >= RMNET_MAX_LOGICAL_EP) {
 		kfree_skb(skb);
@@ -45,10 +40,6 @@ static u8 rmnet_map_do_flow_control(struct sk_buff *skb,
 
 	vnd = ep->egress_dev;
 
-	ip_family = cmd->flow_control.ip_family;
-	fc_seq = ntohs(cmd->flow_control.flow_control_seq_num);
-	qos_id = ntohl(cmd->flow_control.qos_id);
-
 	/* Ignore the ip family and pass the sequence number for both v4 and v6
 	 * sequence. User space does not support creating dedicated flows for
 	 * the 2 protocols
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index 44f6e4873aad..4f910c4f67b0 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -691,7 +691,7 @@ static void cp_tx (struct cp_private *cp)
 			}
 			bytes_compl += skb->len;
 			pkts_compl++;
-			dev_kfree_skb_irq(skb);
+			dev_consume_skb_irq(skb);
 		}
 
 		cp->tx_skb[tx_tail] = NULL;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index ffd68a7bc9e1..55d01266e615 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -258,6 +258,7 @@ static const struct pci_device_id rtl8139_pci_tbl[] = {
 	{0x126c, 0x1211, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
 	{0x1743, 0x8139, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
 	{0x021b, 0x8139, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
+	{0x16ec, 0xab06, PCI_ANY_ID, PCI_ANY_ID, 0, 0, RTL8139 },
 
 #ifdef CONFIG_SH_SECUREEDGE5410
 	/* Bogus 8139 silicon reports 8129 without external PROM :-( */
@@ -1661,7 +1662,7 @@ static void rtl8139_tx_timeout_task (struct work_struct *work)
 
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
-	synchronize_sched();
+	synchronize_rcu();
 
 	netdev_dbg(dev, "Transmit timeout, status %02x %04x %04x media %02x\n",
 		   RTL_R8(ChipCmd), RTL_R16(IntrStatus),
diff --git a/drivers/net/ethernet/realtek/atp.c b/drivers/net/ethernet/realtek/atp.c
index 7e011c1c1e6e..58e0ca9093d3 100644
--- a/drivers/net/ethernet/realtek/atp.c
+++ b/drivers/net/ethernet/realtek/atp.c
@@ -454,14 +454,14 @@ static void hardware_init(struct net_device *dev)
 {
 	struct net_local *lp = netdev_priv(dev);
 	long ioaddr = dev->base_addr;
-    int i;
+	int i;
 
 	/* Turn off the printer multiplexer on the 8012. */
 	for (i = 0; i < 8; i++)
 		outb(mux_8012[i], ioaddr + PAR_DATA);
 	write_reg_high(ioaddr, CMR1, CMR1h_RESET);
 
-    for (i = 0; i < 6; i++)
+	for (i = 0; i < 6; i++)
 		write_reg_byte(ioaddr, PAR0 + i, dev->dev_addr[i]);
 
 	write_reg_high(ioaddr, CMR2, lp->addr_mode);
@@ -471,18 +471,18 @@ static void hardware_init(struct net_device *dev)
 			   (read_nibble(ioaddr, CMR2_h) >> 3) & 0x0f);
 	}
 
-    write_reg(ioaddr, CMR2, CMR2_IRQOUT);
-    write_reg_high(ioaddr, CMR1, CMR1h_RxENABLE | CMR1h_TxENABLE);
+	write_reg(ioaddr, CMR2, CMR2_IRQOUT);
+	write_reg_high(ioaddr, CMR1, CMR1h_RxENABLE | CMR1h_TxENABLE);
 
 	/* Enable the interrupt line from the serial port. */
 	outb(Ctrl_SelData + Ctrl_IRQEN, ioaddr + PAR_CONTROL);
 
 	/* Unmask the interesting interrupts. */
-    write_reg(ioaddr, IMR, ISR_RxOK | ISR_TxErr | ISR_TxOK);
-    write_reg_high(ioaddr, IMR, ISRh_RxErr);
+	write_reg(ioaddr, IMR, ISR_RxOK | ISR_TxErr | ISR_TxOK);
+	write_reg_high(ioaddr, IMR, ISRh_RxErr);
 
 	lp->tx_unit_busy = 0;
-    lp->pac_cnt_in_tx_buf = 0;
+	lp->pac_cnt_in_tx_buf = 0;
 	lp->saved_tx_size = 0;
 }
 
@@ -610,10 +610,12 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 	write_reg(ioaddr, CMR2, CMR2_NULL);
 	write_reg(ioaddr, IMR, 0);
 
-	if (net_debug > 5) printk(KERN_DEBUG "%s: In interrupt ", dev->name);
-    while (--boguscount > 0) {
+	if (net_debug > 5)
+		printk(KERN_DEBUG "%s: In interrupt ", dev->name);
+	while (--boguscount > 0) {
 		int status = read_nibble(ioaddr, ISR);
-		if (net_debug > 5) printk("loop status %02x..", status);
+		if (net_debug > 5)
+			printk("loop status %02x..", status);
 
 		if (status & (ISR_RxOK<<3)) {
 			handled = 1;
@@ -640,7 +642,8 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 			} while (--boguscount > 0);
 		} else if (status & ((ISR_TxErr + ISR_TxOK)<<3)) {
 			handled = 1;
-			if (net_debug > 6)  printk("handling Tx done..");
+			if (net_debug > 6)
+				printk("handling Tx done..");
 			/* Clear the Tx interrupt.  We should check for too many failures
 			   and reinitialize the adapter. */
 			write_reg(ioaddr, ISR, ISR_TxErr + ISR_TxOK);
@@ -680,7 +683,7 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 			break;
 		} else
 			break;
-    }
+	}
 
 	/* This following code fixes a rare (and very difficult to track down)
 	   problem where the adapter forgets its ethernet address. */
@@ -694,7 +697,7 @@ static irqreturn_t atp_interrupt(int irq, void *dev_instance)
 	}
 
 	/* Tell the adapter that it can go back to using the output line as IRQ. */
-    write_reg(ioaddr, CMR2, CMR2_IRQOUT);
+	write_reg(ioaddr, CMR2, CMR2_IRQOUT);
 	/* Enable the physical interrupt line, which is sure to be low until.. */
 	outb(Ctrl_SelData + Ctrl_IRQEN, ioaddr + PAR_CONTROL);
 	/* .. we enable the interrupt sources. */
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 209566f8097b..ed651dde6ef9 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -28,6 +28,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/firmware.h>
 #include <linux/prefetch.h>
+#include <linux/pci-aspm.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
@@ -56,13 +57,6 @@
 #define R8169_MSG_DEFAULT \
 	(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
 
-#define TX_SLOTS_AVAIL(tp) \
-	(tp->dirty_tx + NUM_TX_DESC - tp->cur_tx)
-
-/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
-#define TX_FRAGS_READY_FOR(tp,nr_frags) \
-	(TX_SLOTS_AVAIL(tp) >= (nr_frags + 1))
-
 /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast).
    The RTL chips use a 64 element hash table based on the Ethernet CRC. */
 static const int multicast_filter_limit = 32;
@@ -212,29 +206,30 @@ enum cfg_version {
 };
 
 static const struct pci_device_id rtl8169_pci_tbl[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8129), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8136), 0, 0, RTL_CFG_2 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8161), 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8167), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8168), 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_NCUBE,	0x8168), 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_REALTEK,	0x8169), 0, 0, RTL_CFG_0 },
-	{ PCI_VENDOR_ID_DLINK,			0x4300,
-		PCI_VENDOR_ID_DLINK, 0x4b10,		 0, 0, RTL_CFG_1 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4300), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_DLINK,	0x4302), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(PCI_VENDOR_ID_AT,		0xc107), 0, 0, RTL_CFG_0 },
-	{ PCI_DEVICE(0x16ec,			0x0116), 0, 0, RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x2502), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x2600), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x8129), RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x8136), RTL_CFG_2 },
+	{ PCI_VDEVICE(REALTEK,	0x8161), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x8167), RTL_CFG_0 },
+	{ PCI_VDEVICE(REALTEK,	0x8168), RTL_CFG_1 },
+	{ PCI_VDEVICE(NCUBE,	0x8168), RTL_CFG_1 },
+	{ PCI_VDEVICE(REALTEK,	0x8169), RTL_CFG_0 },
+	{ PCI_VENDOR_ID_DLINK,	0x4300,
+		PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 },
+	{ PCI_VDEVICE(DLINK,	0x4300), RTL_CFG_0 },
+	{ PCI_VDEVICE(DLINK,	0x4302), RTL_CFG_0 },
+	{ PCI_VDEVICE(AT,	0xc107), RTL_CFG_0 },
+	{ PCI_VDEVICE(USR,	0x0116), RTL_CFG_0 },
 	{ PCI_VENDOR_ID_LINKSYS,		0x1032,
 		PCI_ANY_ID, 0x0024, 0, 0, RTL_CFG_0 },
 	{ 0x0001,				0x8168,
 		PCI_ANY_ID, 0x2410, 0, 0, RTL_CFG_2 },
-	{0,},
+	{}
 };
 
 MODULE_DEVICE_TABLE(pci, rtl8169_pci_tbl);
 
-static int use_dac = -1;
 static struct {
 	u32 msg_enable;
 } debug = { -1 };
@@ -603,7 +598,6 @@ struct RxDesc {
 struct ring_info {
 	struct sk_buff	*skb;
 	u32		len;
-	u8		__pad[sizeof(void *) - sizeof(u32)];
 };
 
 struct rtl8169_counters {
@@ -645,6 +639,7 @@ struct rtl8169_private {
 	void __iomem *mmio_addr;	/* memory map physical address */
 	struct pci_dev *pci_dev;
 	struct net_device *dev;
+	struct phy_device *phydev;
 	struct napi_struct napi;
 	u32 msg_enable;
 	u16 mac_version;
@@ -661,7 +656,7 @@ struct rtl8169_private {
 	struct ring_info tx_skb[NUM_TX_DESC];	/* Tx data buffers */
 	u16 cp_cmd;
 
-	u16 event_slow;
+	u16 irq_mask;
 	const struct rtl_coalesce_info *coalesce_info;
 	struct clk *clk;
 
@@ -684,13 +679,14 @@ struct rtl8169_private {
 		struct work_struct work;
 	} wk;
 
+	unsigned irq_enabled:1;
 	unsigned supports_gmii:1;
-	struct mii_bus *mii_bus;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
 	u32 saved_wolopts;
 
+	const char *fw_name;
 	struct rtl_fw {
 		const struct firmware *fw;
 
@@ -703,17 +699,15 @@ struct rtl8169_private {
 			size_t size;
 		} phy_action;
 	} *rtl_fw;
-#define RTL_FIRMWARE_UNKNOWN	ERR_PTR(-EAGAIN)
 
 	u32 ocp_base;
 };
 
 MODULE_AUTHOR("Realtek and the Linux r8169 crew <netdev@vger.kernel.org>");
 MODULE_DESCRIPTION("RealTek RTL-8169 Gigabit Ethernet driver");
-module_param(use_dac, int, 0);
-MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
+MODULE_SOFTDEP("pre: realtek");
 MODULE_LICENSE("GPL");
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
 MODULE_FIRMWARE(FIRMWARE_8168D_2);
@@ -750,6 +744,16 @@ static void rtl_unlock_work(struct rtl8169_private *tp)
 	mutex_unlock(&tp->wk.mutex);
 }
 
+static void rtl_lock_config_regs(struct rtl8169_private *tp)
+{
+	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+}
+
+static void rtl_unlock_config_regs(struct rtl8169_private *tp)
+{
+	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+}
+
 static void rtl_tx_performance_tweak(struct rtl8169_private *tp, u16 force)
 {
 	pcie_capability_clear_and_set_word(tp->pci_dev, PCI_EXP_DEVCTL,
@@ -1102,23 +1106,6 @@ static u32 r8168ep_ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
 	return rtl_eri_read(tp, reg, ERIAR_OOB);
 }
 
-static u32 ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_27:
-	case RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		return r8168dp_ocp_read(tp, mask, reg);
-	case RTL_GIGA_MAC_VER_49:
-	case RTL_GIGA_MAC_VER_50:
-	case RTL_GIGA_MAC_VER_51:
-		return r8168ep_ocp_read(tp, mask, reg);
-	default:
-		BUG();
-		return ~0;
-	}
-}
-
 static void r8168dp_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 			      u32 data)
 {
@@ -1134,30 +1121,11 @@ static void r8168ep_ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg,
 		      data, ERIAR_OOB);
 }
 
-static void ocp_write(struct rtl8169_private *tp, u8 mask, u16 reg, u32 data)
-{
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_27:
-	case RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		r8168dp_ocp_write(tp, mask, reg, data);
-		break;
-	case RTL_GIGA_MAC_VER_49:
-	case RTL_GIGA_MAC_VER_50:
-	case RTL_GIGA_MAC_VER_51:
-		r8168ep_ocp_write(tp, mask, reg, data);
-		break;
-	default:
-		BUG();
-		break;
-	}
-}
-
-static void rtl8168_oob_notify(struct rtl8169_private *tp, u8 cmd)
+static void r8168dp_oob_notify(struct rtl8169_private *tp, u8 cmd)
 {
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_0001, cmd, ERIAR_EXGMAC);
 
-	ocp_write(tp, 0x1, 0x30, 0x00000001);
+	r8168dp_ocp_write(tp, 0x1, 0x30, 0x00000001);
 }
 
 #define OOB_CMD_RESET		0x00
@@ -1169,18 +1137,18 @@ static u16 rtl8168_get_ocp_reg(struct rtl8169_private *tp)
 	return (tp->mac_version == RTL_GIGA_MAC_VER_31) ? 0xb8 : 0x10;
 }
 
-DECLARE_RTL_COND(rtl_ocp_read_cond)
+DECLARE_RTL_COND(rtl_dp_ocp_read_cond)
 {
 	u16 reg;
 
 	reg = rtl8168_get_ocp_reg(tp);
 
-	return ocp_read(tp, 0x0f, reg) & 0x00000800;
+	return r8168dp_ocp_read(tp, 0x0f, reg) & 0x00000800;
 }
 
 DECLARE_RTL_COND(rtl_ep_ocp_read_cond)
 {
-	return ocp_read(tp, 0x0f, 0x124) & 0x00000001;
+	return r8168ep_ocp_read(tp, 0x0f, 0x124) & 0x00000001;
 }
 
 DECLARE_RTL_COND(rtl_ocp_tx_cond)
@@ -1198,14 +1166,15 @@ static void rtl8168ep_stop_cmac(struct rtl8169_private *tp)
 
 static void rtl8168dp_driver_start(struct rtl8169_private *tp)
 {
-	rtl8168_oob_notify(tp, OOB_CMD_DRIVER_START);
-	rtl_msleep_loop_wait_high(tp, &rtl_ocp_read_cond, 10, 10);
+	r8168dp_oob_notify(tp, OOB_CMD_DRIVER_START);
+	rtl_msleep_loop_wait_high(tp, &rtl_dp_ocp_read_cond, 10, 10);
 }
 
 static void rtl8168ep_driver_start(struct rtl8169_private *tp)
 {
-	ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
-	ocp_write(tp, 0x01, 0x30, ocp_read(tp, 0x01, 0x30) | 0x01);
+	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_START);
+	r8168ep_ocp_write(tp, 0x01, 0x30,
+			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
 	rtl_msleep_loop_wait_high(tp, &rtl_ep_ocp_read_cond, 10, 10);
 }
 
@@ -1230,15 +1199,16 @@ static void rtl8168_driver_start(struct rtl8169_private *tp)
 
 static void rtl8168dp_driver_stop(struct rtl8169_private *tp)
 {
-	rtl8168_oob_notify(tp, OOB_CMD_DRIVER_STOP);
-	rtl_msleep_loop_wait_low(tp, &rtl_ocp_read_cond, 10, 10);
+	r8168dp_oob_notify(tp, OOB_CMD_DRIVER_STOP);
+	rtl_msleep_loop_wait_low(tp, &rtl_dp_ocp_read_cond, 10, 10);
 }
 
 static void rtl8168ep_driver_stop(struct rtl8169_private *tp)
 {
 	rtl8168ep_stop_cmac(tp);
-	ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
-	ocp_write(tp, 0x01, 0x30, ocp_read(tp, 0x01, 0x30) | 0x01);
+	r8168ep_ocp_write(tp, 0x01, 0x180, OOB_CMD_DRIVER_STOP);
+	r8168ep_ocp_write(tp, 0x01, 0x30,
+			  r8168ep_ocp_read(tp, 0x01, 0x30) | 0x01);
 	rtl_msleep_loop_wait_low(tp, &rtl_ep_ocp_read_cond, 10, 10);
 }
 
@@ -1265,12 +1235,12 @@ static bool r8168dp_check_dash(struct rtl8169_private *tp)
 {
 	u16 reg = rtl8168_get_ocp_reg(tp);
 
-	return !!(ocp_read(tp, 0x0f, reg) & 0x00008000);
+	return !!(r8168dp_ocp_read(tp, 0x0f, reg) & 0x00008000);
 }
 
 static bool r8168ep_check_dash(struct rtl8169_private *tp)
 {
-	return !!(ocp_read(tp, 0x0f, 0x128) & 0x00000001);
+	return !!(r8168ep_ocp_read(tp, 0x0f, 0x128) & 0x00000001);
 }
 
 static bool r8168_check_dash(struct rtl8169_private *tp)
@@ -1317,35 +1287,25 @@ static u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr)
 		RTL_R32(tp, EFUSEAR) & EFUSEAR_DATA_MASK : ~0;
 }
 
-static u16 rtl_get_events(struct rtl8169_private *tp)
-{
-	return RTL_R16(tp, IntrStatus);
-}
-
 static void rtl_ack_events(struct rtl8169_private *tp, u16 bits)
 {
 	RTL_W16(tp, IntrStatus, bits);
-	mmiowb();
 }
 
 static void rtl_irq_disable(struct rtl8169_private *tp)
 {
 	RTL_W16(tp, IntrMask, 0);
-	mmiowb();
-}
-
-static void rtl_irq_enable(struct rtl8169_private *tp, u16 bits)
-{
-	RTL_W16(tp, IntrMask, bits);
+	tp->irq_enabled = 0;
 }
 
 #define RTL_EVENT_NAPI_RX	(RxOK | RxErr)
 #define RTL_EVENT_NAPI_TX	(TxOK | TxErr)
 #define RTL_EVENT_NAPI		(RTL_EVENT_NAPI_RX | RTL_EVENT_NAPI_TX)
 
-static void rtl_irq_enable_all(struct rtl8169_private *tp)
+static void rtl_irq_enable(struct rtl8169_private *tp)
 {
-	rtl_irq_enable(tp, RTL_EVENT_NAPI | tp->event_slow);
+	tp->irq_enabled = 1;
+	RTL_W16(tp, IntrMask, tp->irq_mask);
 }
 
 static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
@@ -1359,7 +1319,7 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 static void rtl_link_chg_patch(struct rtl8169_private *tp)
 {
 	struct net_device *dev = tp->dev;
-	struct phy_device *phydev = dev->phydev;
+	struct phy_device *phydev = tp->phydev;
 
 	if (!netif_running(dev))
 		return;
@@ -1415,41 +1375,6 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 
 #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
 
-static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
-{
-	u8 options;
-	u32 wolopts = 0;
-
-	options = RTL_R8(tp, Config1);
-	if (!(options & PMEnable))
-		return 0;
-
-	options = RTL_R8(tp, Config3);
-	if (options & LinkUp)
-		wolopts |= WAKE_PHY;
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
-		if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2)
-			wolopts |= WAKE_MAGIC;
-		break;
-	default:
-		if (options & MagicPacket)
-			wolopts |= WAKE_MAGIC;
-		break;
-	}
-
-	options = RTL_R8(tp, Config5);
-	if (options & UWF)
-		wolopts |= WAKE_UCAST;
-	if (options & BWF)
-		wolopts |= WAKE_BCAST;
-	if (options & MWF)
-		wolopts |= WAKE_MCAST;
-
-	return wolopts;
-}
-
 static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
@@ -1477,7 +1402,7 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 	};
 	u8 options;
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	rtl_unlock_config_regs(tp);
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38:
@@ -1525,7 +1450,9 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
 		break;
 	}
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	rtl_lock_config_regs(tp);
+
+	device_set_wakeup_enable(tp_to_dev(tp), wolopts);
 }
 
 static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -1547,18 +1474,11 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	rtl_unlock_work(tp);
 
-	device_set_wakeup_enable(d, tp->saved_wolopts);
-
 	pm_runtime_put_noidle(d);
 
 	return 0;
 }
 
-static const char *rtl_lookup_firmware_name(struct rtl8169_private *tp)
-{
-	return rtl_chip_infos[tp->mac_version].fw_name;
-}
-
 static void rtl8169_get_drvinfo(struct net_device *dev,
 				struct ethtool_drvinfo *info)
 {
@@ -1568,7 +1488,7 @@ static void rtl8169_get_drvinfo(struct net_device *dev,
 	strlcpy(info->driver, MODULENAME, sizeof(info->driver));
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
-	if (!IS_ERR_OR_NULL(rtl_fw))
+	if (rtl_fw)
 		strlcpy(info->fw_version, rtl_fw->version,
 			sizeof(info->fw_version));
 }
@@ -1728,11 +1648,13 @@ static bool rtl8169_reset_counters(struct rtl8169_private *tp)
 
 static bool rtl8169_update_counters(struct rtl8169_private *tp)
 {
+	u8 val = RTL_R8(tp, ChipCmd);
+
 	/*
 	 * Some chips are unable to dump tally counters when the receiver
-	 * is disabled.
+	 * is disabled. If 0xff chip may be in a PCI power-save state.
 	 */
-	if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0)
+	if (!(val & CmdRxEnb) || val == 0xff)
 		return true;
 
 	return rtl8169_do_counters(tp, CounterDump);
@@ -2031,6 +1953,196 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec)
 	return 0;
 }
 
+static int rtl_get_eee_supp(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		phy_write(phydev, 0x1f, 0x0a5c);
+		ret = phy_read(phydev, 0x12);
+		phy_write(phydev, 0x1f, 0x0000);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl_get_eee_lpadv(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		phy_write(phydev, 0x1f, 0x0a5d);
+		ret = phy_read(phydev, 0x11);
+		phy_write(phydev, 0x1f, 0x0000);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl_get_eee_adv(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		phy_write(phydev, 0x1f, 0x0a5d);
+		ret = phy_read(phydev, 0x10);
+		phy_write(phydev, 0x1f, 0x0000);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl_set_eee_adv(struct rtl8169_private *tp, int val)
+{
+	struct phy_device *phydev = tp->phydev;
+	int ret = 0;
+
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_34:
+	case RTL_GIGA_MAC_VER_35:
+	case RTL_GIGA_MAC_VER_36:
+	case RTL_GIGA_MAC_VER_38:
+		ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, val);
+		break;
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		phy_write(phydev, 0x1f, 0x0a5d);
+		phy_write(phydev, 0x10, val);
+		phy_write(phydev, 0x1f, 0x0000);
+		break;
+	default:
+		ret = -EPROTONOSUPPORT;
+		break;
+	}
+
+	return ret;
+}
+
+static int rtl8169_get_eee(struct net_device *dev, struct ethtool_eee *data)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct device *d = tp_to_dev(tp);
+	int ret;
+
+	pm_runtime_get_noresume(d);
+
+	if (!pm_runtime_active(d)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	/* Get Supported EEE */
+	ret = rtl_get_eee_supp(tp);
+	if (ret < 0)
+		goto out;
+	data->supported = mmd_eee_cap_to_ethtool_sup_t(ret);
+
+	/* Get advertisement EEE */
+	ret = rtl_get_eee_adv(tp);
+	if (ret < 0)
+		goto out;
+	data->advertised = mmd_eee_adv_to_ethtool_adv_t(ret);
+	data->eee_enabled = !!data->advertised;
+
+	/* Get LP advertisement EEE */
+	ret = rtl_get_eee_lpadv(tp);
+	if (ret < 0)
+		goto out;
+	data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(ret);
+	data->eee_active = !!(data->advertised & data->lp_advertised);
+out:
+	pm_runtime_put_noidle(d);
+	return ret < 0 ? ret : 0;
+}
+
+static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data)
+{
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct device *d = tp_to_dev(tp);
+	int old_adv, adv = 0, cap, ret;
+
+	pm_runtime_get_noresume(d);
+
+	if (!dev->phydev || !pm_runtime_active(d)) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (dev->phydev->autoneg == AUTONEG_DISABLE ||
+	    dev->phydev->duplex != DUPLEX_FULL) {
+		ret = -EPROTONOSUPPORT;
+		goto out;
+	}
+
+	/* Get Supported EEE */
+	ret = rtl_get_eee_supp(tp);
+	if (ret < 0)
+		goto out;
+	cap = ret;
+
+	ret = rtl_get_eee_adv(tp);
+	if (ret < 0)
+		goto out;
+	old_adv = ret;
+
+	if (data->eee_enabled) {
+		adv = !data->advertised ? cap :
+		      ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap;
+		/* Mask prohibited EEE modes */
+		adv &= ~dev->phydev->eee_broken_modes;
+	}
+
+	if (old_adv != adv) {
+		ret = rtl_set_eee_adv(tp, adv);
+		if (ret < 0)
+			goto out;
+
+		/* Restart autonegotiation so the new modes get sent to the
+		 * link partner.
+		 */
+		ret = phy_restart_aneg(dev->phydev);
+	}
+
+out:
+	pm_runtime_put_noidle(d);
+	return ret < 0 ? ret : 0;
+}
+
 static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_drvinfo		= rtl8169_get_drvinfo,
 	.get_regs_len		= rtl8169_get_regs_len,
@@ -2047,12 +2159,21 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.nway_reset		= phy_ethtool_nway_reset,
+	.get_eee		= rtl8169_get_eee,
+	.set_eee		= rtl8169_set_eee,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
-static void rtl8169_get_mac_version(struct rtl8169_private *tp,
-				    u8 default_version)
+static void rtl_enable_eee(struct rtl8169_private *tp)
+{
+	int supported = rtl_get_eee_supp(tp);
+
+	if (supported > 0)
+		rtl_set_eee_adv(tp, supported);
+}
+
+static void rtl8169_get_mac_version(struct rtl8169_private *tp)
 {
 	/*
 	 * The driver currently handles the 8168Bf and the 8168Be identically
@@ -2066,120 +2187,107 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 	 * (RTL_R32(tp, TxConfig) & 0x700000) == 0x200000 ? 8101Eb : 8101Ec
 	 */
 	static const struct rtl_mac_info {
-		u32 mask;
-		u32 val;
-		int mac_version;
+		u16 mask;
+		u16 val;
+		u16 mac_version;
 	} mac_info[] = {
 		/* 8168EP family. */
-		{ 0x7cf00000, 0x50200000,	RTL_GIGA_MAC_VER_51 },
-		{ 0x7cf00000, 0x50100000,	RTL_GIGA_MAC_VER_50 },
-		{ 0x7cf00000, 0x50000000,	RTL_GIGA_MAC_VER_49 },
+		{ 0x7cf, 0x502,	RTL_GIGA_MAC_VER_51 },
+		{ 0x7cf, 0x501,	RTL_GIGA_MAC_VER_50 },
+		{ 0x7cf, 0x500,	RTL_GIGA_MAC_VER_49 },
 
 		/* 8168H family. */
-		{ 0x7cf00000, 0x54100000,	RTL_GIGA_MAC_VER_46 },
-		{ 0x7cf00000, 0x54000000,	RTL_GIGA_MAC_VER_45 },
+		{ 0x7cf, 0x541,	RTL_GIGA_MAC_VER_46 },
+		{ 0x7cf, 0x540,	RTL_GIGA_MAC_VER_45 },
 
 		/* 8168G family. */
-		{ 0x7cf00000, 0x5c800000,	RTL_GIGA_MAC_VER_44 },
-		{ 0x7cf00000, 0x50900000,	RTL_GIGA_MAC_VER_42 },
-		{ 0x7cf00000, 0x4c100000,	RTL_GIGA_MAC_VER_41 },
-		{ 0x7cf00000, 0x4c000000,	RTL_GIGA_MAC_VER_40 },
+		{ 0x7cf, 0x5c8,	RTL_GIGA_MAC_VER_44 },
+		{ 0x7cf, 0x509,	RTL_GIGA_MAC_VER_42 },
+		{ 0x7cf, 0x4c1,	RTL_GIGA_MAC_VER_41 },
+		{ 0x7cf, 0x4c0,	RTL_GIGA_MAC_VER_40 },
 
 		/* 8168F family. */
-		{ 0x7c800000, 0x48800000,	RTL_GIGA_MAC_VER_38 },
-		{ 0x7cf00000, 0x48100000,	RTL_GIGA_MAC_VER_36 },
-		{ 0x7cf00000, 0x48000000,	RTL_GIGA_MAC_VER_35 },
+		{ 0x7c8, 0x488,	RTL_GIGA_MAC_VER_38 },
+		{ 0x7cf, 0x481,	RTL_GIGA_MAC_VER_36 },
+		{ 0x7cf, 0x480,	RTL_GIGA_MAC_VER_35 },
 
 		/* 8168E family. */
-		{ 0x7c800000, 0x2c800000,	RTL_GIGA_MAC_VER_34 },
-		{ 0x7cf00000, 0x2c100000,	RTL_GIGA_MAC_VER_32 },
-		{ 0x7c800000, 0x2c000000,	RTL_GIGA_MAC_VER_33 },
+		{ 0x7c8, 0x2c8,	RTL_GIGA_MAC_VER_34 },
+		{ 0x7cf, 0x2c1,	RTL_GIGA_MAC_VER_32 },
+		{ 0x7c8, 0x2c0,	RTL_GIGA_MAC_VER_33 },
 
 		/* 8168D family. */
-		{ 0x7cf00000, 0x28100000,	RTL_GIGA_MAC_VER_25 },
-		{ 0x7c800000, 0x28000000,	RTL_GIGA_MAC_VER_26 },
+		{ 0x7cf, 0x281,	RTL_GIGA_MAC_VER_25 },
+		{ 0x7c8, 0x280,	RTL_GIGA_MAC_VER_26 },
 
 		/* 8168DP family. */
-		{ 0x7cf00000, 0x28800000,	RTL_GIGA_MAC_VER_27 },
-		{ 0x7cf00000, 0x28a00000,	RTL_GIGA_MAC_VER_28 },
-		{ 0x7cf00000, 0x28b00000,	RTL_GIGA_MAC_VER_31 },
+		{ 0x7cf, 0x288,	RTL_GIGA_MAC_VER_27 },
+		{ 0x7cf, 0x28a,	RTL_GIGA_MAC_VER_28 },
+		{ 0x7cf, 0x28b,	RTL_GIGA_MAC_VER_31 },
 
 		/* 8168C family. */
-		{ 0x7cf00000, 0x3c900000,	RTL_GIGA_MAC_VER_23 },
-		{ 0x7cf00000, 0x3c800000,	RTL_GIGA_MAC_VER_18 },
-		{ 0x7c800000, 0x3c800000,	RTL_GIGA_MAC_VER_24 },
-		{ 0x7cf00000, 0x3c000000,	RTL_GIGA_MAC_VER_19 },
-		{ 0x7cf00000, 0x3c200000,	RTL_GIGA_MAC_VER_20 },
-		{ 0x7cf00000, 0x3c300000,	RTL_GIGA_MAC_VER_21 },
-		{ 0x7c800000, 0x3c000000,	RTL_GIGA_MAC_VER_22 },
+		{ 0x7cf, 0x3c9,	RTL_GIGA_MAC_VER_23 },
+		{ 0x7cf, 0x3c8,	RTL_GIGA_MAC_VER_18 },
+		{ 0x7c8, 0x3c8,	RTL_GIGA_MAC_VER_24 },
+		{ 0x7cf, 0x3c0,	RTL_GIGA_MAC_VER_19 },
+		{ 0x7cf, 0x3c2,	RTL_GIGA_MAC_VER_20 },
+		{ 0x7cf, 0x3c3,	RTL_GIGA_MAC_VER_21 },
+		{ 0x7c8, 0x3c0,	RTL_GIGA_MAC_VER_22 },
 
 		/* 8168B family. */
-		{ 0x7cf00000, 0x38000000,	RTL_GIGA_MAC_VER_12 },
-		{ 0x7c800000, 0x38000000,	RTL_GIGA_MAC_VER_17 },
-		{ 0x7c800000, 0x30000000,	RTL_GIGA_MAC_VER_11 },
+		{ 0x7cf, 0x380,	RTL_GIGA_MAC_VER_12 },
+		{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17 },
+		{ 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
 
 		/* 8101 family. */
-		{ 0x7c800000, 0x44800000,	RTL_GIGA_MAC_VER_39 },
-		{ 0x7c800000, 0x44000000,	RTL_GIGA_MAC_VER_37 },
-		{ 0x7cf00000, 0x40900000,	RTL_GIGA_MAC_VER_29 },
-		{ 0x7c800000, 0x40800000,	RTL_GIGA_MAC_VER_30 },
-		{ 0x7cf00000, 0x34900000,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf00000, 0x24900000,	RTL_GIGA_MAC_VER_08 },
-		{ 0x7cf00000, 0x34800000,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf00000, 0x24800000,	RTL_GIGA_MAC_VER_07 },
-		{ 0x7cf00000, 0x34000000,	RTL_GIGA_MAC_VER_13 },
-		{ 0x7cf00000, 0x34300000,	RTL_GIGA_MAC_VER_10 },
-		{ 0x7cf00000, 0x34200000,	RTL_GIGA_MAC_VER_16 },
-		{ 0x7c800000, 0x34800000,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c800000, 0x24800000,	RTL_GIGA_MAC_VER_09 },
-		{ 0x7c800000, 0x34000000,	RTL_GIGA_MAC_VER_16 },
+		{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39 },
+		{ 0x7c8, 0x440,	RTL_GIGA_MAC_VER_37 },
+		{ 0x7cf, 0x409,	RTL_GIGA_MAC_VER_29 },
+		{ 0x7c8, 0x408,	RTL_GIGA_MAC_VER_30 },
+		{ 0x7cf, 0x349,	RTL_GIGA_MAC_VER_08 },
+		{ 0x7cf, 0x249,	RTL_GIGA_MAC_VER_08 },
+		{ 0x7cf, 0x348,	RTL_GIGA_MAC_VER_07 },
+		{ 0x7cf, 0x248,	RTL_GIGA_MAC_VER_07 },
+		{ 0x7cf, 0x340,	RTL_GIGA_MAC_VER_13 },
+		{ 0x7cf, 0x343,	RTL_GIGA_MAC_VER_10 },
+		{ 0x7cf, 0x342,	RTL_GIGA_MAC_VER_16 },
+		{ 0x7c8, 0x348,	RTL_GIGA_MAC_VER_09 },
+		{ 0x7c8, 0x248,	RTL_GIGA_MAC_VER_09 },
+		{ 0x7c8, 0x340,	RTL_GIGA_MAC_VER_16 },
 		/* FIXME: where did these entries come from ? -- FR */
-		{ 0xfc800000, 0x38800000,	RTL_GIGA_MAC_VER_15 },
-		{ 0xfc800000, 0x30800000,	RTL_GIGA_MAC_VER_14 },
+		{ 0xfc8, 0x388,	RTL_GIGA_MAC_VER_15 },
+		{ 0xfc8, 0x308,	RTL_GIGA_MAC_VER_14 },
 
 		/* 8110 family. */
-		{ 0xfc800000, 0x98000000,	RTL_GIGA_MAC_VER_06 },
-		{ 0xfc800000, 0x18000000,	RTL_GIGA_MAC_VER_05 },
-		{ 0xfc800000, 0x10000000,	RTL_GIGA_MAC_VER_04 },
-		{ 0xfc800000, 0x04000000,	RTL_GIGA_MAC_VER_03 },
-		{ 0xfc800000, 0x00800000,	RTL_GIGA_MAC_VER_02 },
-		{ 0xfc800000, 0x00000000,	RTL_GIGA_MAC_VER_01 },
+		{ 0xfc8, 0x980,	RTL_GIGA_MAC_VER_06 },
+		{ 0xfc8, 0x180,	RTL_GIGA_MAC_VER_05 },
+		{ 0xfc8, 0x100,	RTL_GIGA_MAC_VER_04 },
+		{ 0xfc8, 0x040,	RTL_GIGA_MAC_VER_03 },
+		{ 0xfc8, 0x008,	RTL_GIGA_MAC_VER_02 },
+		{ 0xfc8, 0x000,	RTL_GIGA_MAC_VER_01 },
 
 		/* Catch-all */
-		{ 0x00000000, 0x00000000,	RTL_GIGA_MAC_NONE   }
+		{ 0x000, 0x000,	RTL_GIGA_MAC_NONE   }
 	};
 	const struct rtl_mac_info *p = mac_info;
-	u32 reg;
+	u16 reg = RTL_R32(tp, TxConfig) >> 20;
 
-	reg = RTL_R32(tp, TxConfig);
 	while ((reg & p->mask) != p->val)
 		p++;
 	tp->mac_version = p->mac_version;
 
 	if (tp->mac_version == RTL_GIGA_MAC_NONE) {
-		dev_notice(tp_to_dev(tp),
-			   "unknown MAC, using family default\n");
-		tp->mac_version = default_version;
-	} else if (tp->mac_version == RTL_GIGA_MAC_VER_42) {
-		tp->mac_version = tp->supports_gmii ?
-				  RTL_GIGA_MAC_VER_42 :
-				  RTL_GIGA_MAC_VER_43;
-	} else if (tp->mac_version == RTL_GIGA_MAC_VER_45) {
-		tp->mac_version = tp->supports_gmii ?
-				  RTL_GIGA_MAC_VER_45 :
-				  RTL_GIGA_MAC_VER_47;
-	} else if (tp->mac_version == RTL_GIGA_MAC_VER_46) {
-		tp->mac_version = tp->supports_gmii ?
-				  RTL_GIGA_MAC_VER_46 :
-				  RTL_GIGA_MAC_VER_48;
+		dev_err(tp_to_dev(tp), "unknown chip XID %03x\n", reg & 0xfcf);
+	} else if (!tp->supports_gmii) {
+		if (tp->mac_version == RTL_GIGA_MAC_VER_42)
+			tp->mac_version = RTL_GIGA_MAC_VER_43;
+		else if (tp->mac_version == RTL_GIGA_MAC_VER_45)
+			tp->mac_version = RTL_GIGA_MAC_VER_47;
+		else if (tp->mac_version == RTL_GIGA_MAC_VER_46)
+			tp->mac_version = RTL_GIGA_MAC_VER_48;
 	}
 }
 
-static void rtl8169_print_mac_version(struct rtl8169_private *tp)
-{
-	netif_dbg(tp, drv, tp->dev, "mac_version = 0x%02x\n", tp->mac_version);
-}
-
 struct phy_reg {
 	u16 reg;
 	u16 val;
@@ -2257,7 +2365,7 @@ static bool rtl_fw_format_ok(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
 		if (fw->size % FW_OPCODE_SIZE)
 			goto out;
 
-		strlcpy(version, rtl_lookup_firmware_name(tp), RTL_VER_SIZE);
+		strlcpy(version, tp->fw_name, RTL_VER_SIZE);
 
 		pa->code = (__le32 *)fw->data;
 		pa->size = fw->size / FW_OPCODE_SIZE;
@@ -2432,20 +2540,18 @@ static void rtl_phy_write_fw(struct rtl8169_private *tp, struct rtl_fw *rtl_fw)
 
 static void rtl_release_firmware(struct rtl8169_private *tp)
 {
-	if (!IS_ERR_OR_NULL(tp->rtl_fw)) {
+	if (tp->rtl_fw) {
 		release_firmware(tp->rtl_fw->fw);
 		kfree(tp->rtl_fw);
+		tp->rtl_fw = NULL;
 	}
-	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 }
 
 static void rtl_apply_firmware(struct rtl8169_private *tp)
 {
-	struct rtl_fw *rtl_fw = tp->rtl_fw;
-
 	/* TODO: release firmware once rtl_phy_write_fw signals failures. */
-	if (!IS_ERR_OR_NULL(rtl_fw))
-		rtl_phy_write_fw(tp, rtl_fw);
+	if (tp->rtl_fw)
+		rtl_phy_write_fw(tp, tp->rtl_fw);
 }
 
 static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val)
@@ -2456,6 +2562,33 @@ static void rtl_apply_firmware_cond(struct rtl8169_private *tp, u8 reg, u16 val)
 		rtl_apply_firmware(tp);
 }
 
+static void rtl8168_config_eee_mac(struct rtl8169_private *tp)
+{
+	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_1111, 0x0003, 0x0000, ERIAR_EXGMAC);
+}
+
+static void rtl8168f_config_eee_phy(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+
+	phy_write(phydev, 0x1f, 0x0007);
+	phy_write(phydev, 0x1e, 0x0020);
+	phy_set_bits(phydev, 0x15, BIT(8));
+
+	phy_write(phydev, 0x1f, 0x0005);
+	phy_write(phydev, 0x05, 0x8b85);
+	phy_set_bits(phydev, 0x06, BIT(13));
+
+	phy_write(phydev, 0x1f, 0x0000);
+}
+
+static void rtl8168g_config_eee_phy(struct rtl8169_private *tp)
+{
+	phy_write(tp->phydev, 0x1f, 0x0a43);
+	phy_set_bits(tp->phydev, 0x11, BIT(4));
+	phy_write(tp->phydev, 0x1f, 0x0000);
+}
+
 static void rtl8169s_hw_phy_config(struct rtl8169_private *tp)
 {
 	static const struct phy_reg phy_reg_init[] = {
@@ -3223,22 +3356,8 @@ static void rtl8168e_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x06, 0x4000, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* EEE setting */
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_1111, 0x0003, 0x0000, ERIAR_EXGMAC);
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b85);
-	rtl_w0w1_phy(tp, 0x06, 0x2000, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0004);
-	rtl_writephy(tp, 0x1f, 0x0007);
-	rtl_writephy(tp, 0x1e, 0x0020);
-	rtl_w0w1_phy(tp, 0x15, 0x0100, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0002);
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_writephy(tp, 0x0d, 0x0007);
-	rtl_writephy(tp, 0x0e, 0x003c);
-	rtl_writephy(tp, 0x0d, 0x4007);
-	rtl_writephy(tp, 0x0e, 0x0006);
-	rtl_writephy(tp, 0x0d, 0x0000);
+	rtl8168f_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 
 	/* Green feature */
 	rtl_writephy(tp, 0x1f, 0x0003);
@@ -3273,6 +3392,9 @@ static void rtl8168f_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x05, 0x8b86);
 	rtl_w0w1_phy(tp, 0x06, 0x0001, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
+
+	rtl8168f_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168f_1_hw_phy_config(struct rtl8169_private *tp)
@@ -3406,22 +3528,6 @@ static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x06, 0x8000, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* eee setting */
-	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0001, 0x00, 0x03, ERIAR_EXGMAC);
-	rtl_writephy(tp, 0x1f, 0x0005);
-	rtl_writephy(tp, 0x05, 0x8b85);
-	rtl_w0w1_phy(tp, 0x06, 0x0000, 0x2000);
-	rtl_writephy(tp, 0x1f, 0x0004);
-	rtl_writephy(tp, 0x1f, 0x0007);
-	rtl_writephy(tp, 0x1e, 0x0020);
-	rtl_w0w1_phy(tp, 0x15, 0x0000, 0x0100);
-	rtl_writephy(tp, 0x1f, 0x0000);
-	rtl_writephy(tp, 0x0d, 0x0007);
-	rtl_writephy(tp, 0x0e, 0x003c);
-	rtl_writephy(tp, 0x0d, 0x4007);
-	rtl_writephy(tp, 0x0e, 0x0000);
-	rtl_writephy(tp, 0x0d, 0x0000);
-
 	/* Green feature */
 	rtl_writephy(tp, 0x1f, 0x0003);
 	rtl_w0w1_phy(tp, 0x19, 0x0000, 0x0001);
@@ -3429,6 +3535,30 @@ static void rtl8411_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0000);
 }
 
+static void rtl8168g_disable_aldps(struct rtl8169_private *tp)
+{
+	phy_write(tp->phydev, 0x1f, 0x0a43);
+	phy_clear_bits(tp->phydev, 0x10, BIT(2));
+}
+
+static void rtl8168g_phy_adjust_10m_aldps(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = tp->phydev;
+
+	phy_write(phydev, 0x1f, 0x0bcc);
+	phy_clear_bits(phydev, 0x14, BIT(8));
+
+	phy_write(phydev, 0x1f, 0x0a44);
+	phy_set_bits(phydev, 0x11, BIT(7) | BIT(6));
+
+	phy_write(phydev, 0x1f, 0x0a43);
+	phy_write(phydev, 0x13, 0x8084);
+	phy_clear_bits(phydev, 0x14, BIT(14) | BIT(13));
+	phy_set_bits(phydev, 0x10, BIT(12) | BIT(1) | BIT(0));
+
+	phy_write(phydev, 0x1f, 0x0000);
+}
+
 static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
 {
 	rtl_apply_firmware(tp);
@@ -3455,14 +3585,7 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x1f, 0x0a44);
 	rtl_w0w1_phy(tp, 0x11, 0x000c, 0x0000);
 
-	rtl_writephy(tp, 0x1f, 0x0bcc);
-	rtl_w0w1_phy(tp, 0x14, 0x0100, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x00c0, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	rtl_writephy(tp, 0x13, 0x8084);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x6000);
-	rtl_w0w1_phy(tp, 0x10, 0x1003, 0x0000);
+	rtl8168g_phy_adjust_10m_aldps(tp);
 
 	/* EEE auto-fallback function */
 	rtl_writephy(tp, 0x1f, 0x0a4b);
@@ -3487,17 +3610,16 @@ static void rtl8168g_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x14, 0x9065);
 	rtl_writephy(tp, 0x14, 0x1065);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168g_2_hw_phy_config(struct rtl8169_private *tp)
 {
 	rtl_apply_firmware(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp)
@@ -3602,12 +3724,9 @@ static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x11, 0x0000, 0x0080);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp)
@@ -3675,12 +3794,9 @@ static void rtl8168h_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x11, 0x0000, 0x0080);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp)
@@ -3690,16 +3806,7 @@ static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x11, 0x000c, 0x0000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* patch 10M & ALDPS */
-	rtl_writephy(tp, 0x1f, 0x0bcc);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x0100);
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x00c0, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	rtl_writephy(tp, 0x13, 0x8084);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x6000);
-	rtl_w0w1_phy(tp, 0x10, 0x1003, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_phy_adjust_10m_aldps(tp);
 
 	/* Enable EEE auto-fallback function */
 	rtl_writephy(tp, 0x1f, 0x0a4b);
@@ -3717,26 +3824,14 @@ static void rtl8168ep_1_hw_phy_config(struct rtl8169_private *tp)
 	rtl_w0w1_phy(tp, 0x11, 0x4000, 0x2000);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp)
 {
-	/* patch 10M & ALDPS */
-	rtl_writephy(tp, 0x1f, 0x0bcc);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x0100);
-	rtl_writephy(tp, 0x1f, 0x0a44);
-	rtl_w0w1_phy(tp, 0x11, 0x00c0, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	rtl_writephy(tp, 0x13, 0x8084);
-	rtl_w0w1_phy(tp, 0x14, 0x0000, 0x6000);
-	rtl_w0w1_phy(tp, 0x10, 0x1003, 0x0000);
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_phy_adjust_10m_aldps(tp);
 
 	/* Enable UC LPF tune function */
 	rtl_writephy(tp, 0x1f, 0x0a43);
@@ -3808,12 +3903,9 @@ static void rtl8168ep_2_hw_phy_config(struct rtl8169_private *tp)
 	rtl_writephy(tp, 0x14, 0x1065);
 	rtl_writephy(tp, 0x1f, 0x0000);
 
-	/* Check ALDPS bit, disable it if enabled */
-	rtl_writephy(tp, 0x1f, 0x0a43);
-	if (rtl_readphy(tp, 0x10) & 0x0004)
-		rtl_w0w1_phy(tp, 0x10, 0x0000, 0x0004);
-
-	rtl_writephy(tp, 0x1f, 0x0000);
+	rtl8168g_disable_aldps(tp);
+	rtl8168g_config_eee_phy(tp);
+	rtl_enable_eee(tp);
 }
 
 static void rtl8102e_hw_phy_config(struct rtl8169_private *tp)
@@ -3902,8 +3994,6 @@ static void rtl_hw_phy_config(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	rtl8169_print_mac_version(tp);
-
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_01:
 		break;
@@ -4054,24 +4144,24 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 	}
 
 	/* We may have called phy_speed_down before */
-	phy_speed_up(dev->phydev);
+	phy_speed_up(tp->phydev);
 
-	genphy_soft_reset(dev->phydev);
+	genphy_soft_reset(tp->phydev);
 
 	/* It was reported that several chips end up with 10MBit/Half on a
 	 * 1GBit link after resuming from S3. For whatever reason the PHY on
 	 * these chips doesn't properly start a renegotiation when soft-reset.
 	 * Explicitly requesting a renegotiation fixes this.
 	 */
-	if (dev->phydev->autoneg == AUTONEG_ENABLE)
-		phy_restart_aneg(dev->phydev);
+	if (tp->phydev->autoneg == AUTONEG_ENABLE)
+		phy_restart_aneg(tp->phydev);
 }
 
 static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
 {
 	rtl_lock_work(tp);
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	rtl_unlock_config_regs(tp);
 
 	RTL_W32(tp, MAC4, addr[4] | addr[5] << 8);
 	RTL_R32(tp, MAC4);
@@ -4082,7 +4172,7 @@ static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
 	if (tp->mac_version == RTL_GIGA_MAC_VER_34)
 		rtl_rar_exgmac_set(tp, addr);
 
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	rtl_lock_config_regs(tp);
 
 	rtl_unlock_work(tp);
 }
@@ -4109,10 +4199,12 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
 
 static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
+	struct rtl8169_private *tp = netdev_priv(dev);
+
 	if (!netif_running(dev))
 		return -ENODEV;
 
-	return phy_mii_ioctl(dev->phydev, ifr, cmd);
+	return phy_mii_ioctl(tp->phydev, ifr, cmd);
 }
 
 static void rtl_init_mdio_ops(struct rtl8169_private *tp)
@@ -4159,22 +4251,6 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 	}
 }
 
-static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
-{
-	struct phy_device *phydev;
-
-	if (!__rtl8169_get_wol(tp))
-		return false;
-
-	/* phydev may not be attached to netdevice */
-	phydev = mdiobus_get_phy(tp->mii_bus, 0);
-
-	phy_speed_down(phydev, false);
-	rtl_wol_suspend_quirk(tp);
-
-	return true;
-}
-
 static void r8168_pll_power_down(struct rtl8169_private *tp)
 {
 	if (r8168_check_dash(tp))
@@ -4184,8 +4260,11 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
 	    tp->mac_version == RTL_GIGA_MAC_VER_33)
 		rtl_ephy_write(tp, 0x19, 0xff64);
 
-	if (rtl_wol_pll_power_down(tp))
+	if (device_may_wakeup(tp_to_dev(tp))) {
+		phy_speed_down(tp->phydev, false);
+		rtl_wol_suspend_quirk(tp);
 		return;
+	}
 
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
@@ -4238,7 +4317,7 @@ static void r8168_pll_power_up(struct rtl8169_private *tp)
 		break;
 	}
 
-	phy_resume(tp->dev->phydev);
+	phy_resume(tp->phydev);
 	/* give MAC/PHY some time to resume */
 	msleep(20);
 }
@@ -4294,18 +4373,18 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp)
 static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
 {
 	if (tp->jumbo_ops.enable) {
-		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+		rtl_unlock_config_regs(tp);
 		tp->jumbo_ops.enable(tp);
-		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+		rtl_lock_config_regs(tp);
 	}
 }
 
 static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
 {
 	if (tp->jumbo_ops.disable) {
-		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+		rtl_unlock_config_regs(tp);
 		tp->jumbo_ops.disable(tp);
-		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+		rtl_lock_config_regs(tp);
 	}
 }
 
@@ -4438,21 +4517,20 @@ static void rtl_hw_reset(struct rtl8169_private *tp)
 	rtl_udelay_loop_wait_low(tp, &rtl_chipcmd_cond, 100, 100);
 }
 
-static void rtl_request_uncached_firmware(struct rtl8169_private *tp)
+static void rtl_request_firmware(struct rtl8169_private *tp)
 {
 	struct rtl_fw *rtl_fw;
-	const char *name;
 	int rc = -ENOMEM;
 
-	name = rtl_lookup_firmware_name(tp);
-	if (!name)
-		goto out_no_firmware;
+	/* firmware loaded already or no firmware available */
+	if (tp->rtl_fw || !tp->fw_name)
+		return;
 
 	rtl_fw = kzalloc(sizeof(*rtl_fw), GFP_KERNEL);
 	if (!rtl_fw)
 		goto err_warn;
 
-	rc = request_firmware(&rtl_fw->fw, name, tp_to_dev(tp));
+	rc = request_firmware(&rtl_fw->fw, tp->fw_name, tp_to_dev(tp));
 	if (rc < 0)
 		goto err_free;
 
@@ -4461,7 +4539,7 @@ static void rtl_request_uncached_firmware(struct rtl8169_private *tp)
 		goto err_release_firmware;
 
 	tp->rtl_fw = rtl_fw;
-out:
+
 	return;
 
 err_release_firmware:
@@ -4470,16 +4548,7 @@ err_free:
 	kfree(rtl_fw);
 err_warn:
 	netif_warn(tp, ifup, tp->dev, "unable to load firmware patch %s (%d)\n",
-		   name, rc);
-out_no_firmware:
-	tp->rtl_fw = NULL;
-	goto out;
-}
-
-static void rtl_request_firmware(struct rtl8169_private *tp)
-{
-	if (IS_ERR(tp->rtl_fw))
-		rtl_request_uncached_firmware(tp);
+		   tp->fw_name, rc);
 }
 
 static void rtl_rx_close(struct rtl8169_private *tp)
@@ -4626,13 +4695,13 @@ static void rtl_set_rx_mode(struct net_device *dev)
 
 static void rtl_hw_start(struct  rtl8169_private *tp)
 {
-	RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+	rtl_unlock_config_regs(tp);
 
 	tp->hw_start(tp);
 
 	rtl_set_rx_max_size(tp);
 	rtl_set_rx_tx_desc_registers(tp);
-	RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+	rtl_lock_config_regs(tp);
 
 	/* Initially a 10 us delay. Turned it into a PCI commit. - FR */
 	RTL_R8(tp, IntrMask);
@@ -4643,7 +4712,7 @@ static void rtl_hw_start(struct  rtl8169_private *tp)
 	rtl_set_rx_mode(tp->dev);
 	/* no early-rx interrupts */
 	RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000);
-	rtl_irq_enable_all(tp);
+	rtl_irq_enable(tp);
 }
 
 static void rtl_hw_start_8169(struct rtl8169_private *tp)
@@ -4756,18 +4825,10 @@ static void rtl_enable_clock_request(struct rtl8169_private *tp)
 				 PCI_EXP_LNKCTL_CLKREQ_EN);
 }
 
-static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable)
+static void rtl_pcie_state_l2l3_disable(struct rtl8169_private *tp)
 {
-	u8 data;
-
-	data = RTL_R8(tp, Config3);
-
-	if (enable)
-		data |= Rdy_to_L23;
-	else
-		data &= ~Rdy_to_L23;
-
-	RTL_W8(tp, Config3, data);
+	/* work around an issue when PCI reset occurs during L2/L3 state */
+	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Rdy_to_L23);
 }
 
 static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
@@ -5025,6 +5086,8 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	/* Adjust EEE LED frequency */
 	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
 
+	rtl8168_config_eee_mac(tp);
+
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
 	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
@@ -5057,6 +5120,8 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
 	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+
+	rtl8168_config_eee_mac(tp);
 }
 
 static void rtl_hw_start_8168f_1(struct rtl8169_private *tp)
@@ -5088,7 +5153,7 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp)
 	};
 
 	rtl_hw_start_8168f(tp);
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 
 	rtl_ephy_init(tp, e_info_8168f_1, ARRAY_SIZE(e_info_8168f_1));
 
@@ -5119,10 +5184,12 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 	/* Adjust EEE LED frequency */
 	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
 
+	rtl8168_config_eee_mac(tp);
+
 	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC);
 	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
@@ -5221,6 +5288,8 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	/* Adjust EEE LED frequency */
 	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
 
+	rtl8168_config_eee_mac(tp);
+
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 	RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN);
 
@@ -5228,7 +5297,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 
 	rtl_w0w1_eri(tp, 0x1b0, ERIAR_MASK_0011, 0x0000, 0x1000, ERIAR_EXGMAC);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 
 	rtl_writephy(tp, 0x1f, 0x0c42);
 	rg_saw_cnt = (rtl_readphy(tp, 0x13) & 0x3fff);
@@ -5301,11 +5370,13 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 	/* Adjust EEE LED frequency */
 	RTL_W8(tp, EEE_LED, RTL_R8(tp, EEE_LED) & ~0x07);
 
+	rtl8168_config_eee_mac(tp);
+
 	rtl_w0w1_eri(tp, 0x2fc, ERIAR_MASK_0001, 0x01, 0x06, ERIAR_EXGMAC);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~TX_10M_PS_EN);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp)
@@ -5390,12 +5461,12 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 	tp->cp_cmd |= PktCntrDisable | INTT_1;
 	RTL_W16(tp, CPlusCmd, tp->cp_cmd);
 
-	RTL_W16(tp, IntrMitigate, 0x5151);
+	RTL_W16(tp, IntrMitigate, 0x5100);
 
 	/* Work around for RxFIFO overflow. */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
-		tp->event_slow |= RxFIFOOver | PCSTimeout;
-		tp->event_slow &= ~RxOverflow;
+		tp->irq_mask |= RxFIFOOver;
+		tp->irq_mask &= ~RxOverflow;
 	}
 
 	switch (tp->mac_version) {
@@ -5576,7 +5647,7 @@ static void rtl_hw_start_8105e_1(struct rtl8169_private *tp)
 
 	rtl_ephy_init(tp, e_info_8105e_1, ARRAY_SIZE(e_info_8105e_1));
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8105e_2(struct rtl8169_private *tp)
@@ -5611,7 +5682,7 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC);
 	rtl_w0w1_eri(tp, 0x0d4, ERIAR_MASK_0011, 0x0e00, 0xff00, ERIAR_EXGMAC);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 }
 
 static void rtl_hw_start_8106(struct rtl8169_private *tp)
@@ -5625,14 +5696,14 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp)
 	RTL_W8(tp, MCU, RTL_R8(tp, MCU) | EN_NDP | EN_OOB_RESET);
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 
-	rtl_pcie_state_l2l3_enable(tp, false);
+	rtl_pcie_state_l2l3_disable(tp);
 	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8101(struct rtl8169_private *tp)
 {
 	if (tp->mac_version >= RTL_GIGA_MAC_VER_30)
-		tp->event_slow &= ~RxFIFOOver;
+		tp->irq_mask &= ~RxFIFOOver;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_13 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_16)
@@ -5725,11 +5796,6 @@ static inline void rtl8169_mark_to_asic(struct RxDesc *desc)
 	desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE);
 }
 
-static inline void *rtl8169_align(void *data)
-{
-	return (void *)ALIGN((long)data, 16);
-}
-
 static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp,
 					     struct RxDesc *desc)
 {
@@ -5742,15 +5808,13 @@ static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp,
 	if (!data)
 		return NULL;
 
-	if (rtl8169_align(data) != data) {
-		kfree(data);
-		data = kmalloc_node(R8169_RX_BUF_SIZE + 15, GFP_KERNEL, node);
-		if (!data)
-			return NULL;
+	/* Memory should be properly aligned, but better check. */
+	if (!IS_ALIGNED((unsigned long)data, 8)) {
+		netdev_err_once(tp->dev, "RX buffer not 8-byte-aligned\n");
+		goto err_out;
 	}
 
-	mapping = dma_map_single(d, rtl8169_align(data), R8169_RX_BUF_SIZE,
-				 DMA_FROM_DEVICE);
+	mapping = dma_map_single(d, data, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(d, mapping))) {
 		if (net_ratelimit())
 			netif_err(tp, drv, tp->dev, "Failed to map RX DMA!\n");
@@ -5866,7 +5930,7 @@ static void rtl_reset_work(struct rtl8169_private *tp)
 
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
-	synchronize_sched();
+	synchronize_rcu();
 
 	rtl8169_hw_reset(tp);
 
@@ -5888,6 +5952,16 @@ static void rtl8169_tx_timeout(struct net_device *dev)
 	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
+static __le32 rtl8169_get_txd_opts1(u32 opts0, u32 len, unsigned int entry)
+{
+	u32 status = opts0 | len;
+
+	if (entry == NUM_TX_DESC - 1)
+		status |= RingEnd;
+
+	return cpu_to_le32(status);
+}
+
 static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 			      u32 *opts)
 {
@@ -5900,7 +5974,7 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 	for (cur_frag = 0; cur_frag < info->nr_frags; cur_frag++) {
 		const skb_frag_t *frag = info->frags + cur_frag;
 		dma_addr_t mapping;
-		u32 status, len;
+		u32 len;
 		void *addr;
 
 		entry = (entry + 1) % NUM_TX_DESC;
@@ -5916,11 +5990,7 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb,
 			goto err_out;
 		}
 
-		/* Anti gcc 2.95.3 bugware (sic) */
-		status = opts[0] | len |
-			(RingEnd * !((entry + 1) % NUM_TX_DESC));
-
-		txd->opts1 = cpu_to_le32(status);
+		txd->opts1 = rtl8169_get_txd_opts1(opts[0], len, entry);
 		txd->opts2 = cpu_to_le32(opts[1]);
 		txd->addr = cpu_to_le64(mapping);
 
@@ -6108,6 +6178,15 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp,
 	return true;
 }
 
+static bool rtl_tx_slots_avail(struct rtl8169_private *tp,
+			       unsigned int nr_frags)
+{
+	unsigned int slots_avail = tp->dirty_tx + NUM_TX_DESC - tp->cur_tx;
+
+	/* A skbuff with nr_frags needs nr_frags+1 entries in the tx queue */
+	return slots_avail > nr_frags;
+}
+
 static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
@@ -6116,11 +6195,10 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	struct TxDesc *txd = tp->TxDescArray + entry;
 	struct device *d = tp_to_dev(tp);
 	dma_addr_t mapping;
-	u32 status, len;
-	u32 opts[2];
+	u32 opts[2], len;
 	int frags;
 
-	if (unlikely(!TX_FRAGS_READY_FOR(tp, skb_shinfo(skb)->nr_frags))) {
+	if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) {
 		netif_err(tp, drv, dev, "BUG! Tx Ring full when queue awake!\n");
 		goto err_stop_0;
 	}
@@ -6166,9 +6244,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 	/* Force memory writes to complete before releasing descriptor */
 	dma_wmb();
 
-	/* Anti gcc 2.95.3 bugware (sic) */
-	status = opts[0] | len | (RingEnd * !((entry + 1) % NUM_TX_DESC));
-	txd->opts1 = cpu_to_le32(status);
+	txd->opts1 = rtl8169_get_txd_opts1(opts[0], len, entry);
 
 	/* Force all memory writes to complete before notifying device */
 	wmb();
@@ -6177,9 +6253,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 
 	RTL_W8(tp, TxPoll, NPQ);
 
-	mmiowb();
-
-	if (!TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) {
+	if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
 		/* Avoid wrongly optimistic queue wake-up: rtl_tx thread must
 		 * not miss a ring update when it notices a stopped queue.
 		 */
@@ -6193,7 +6267,7 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
 		 * can't.
 		 */
 		smp_mb();
-		if (TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS))
+		if (rtl_tx_slots_avail(tp, MAX_SKB_FRAGS))
 			netif_wake_queue(dev);
 	}
 
@@ -6244,20 +6318,11 @@ static void rtl8169_pcierr_interrupt(struct net_device *dev)
 		PCI_STATUS_SIG_SYSTEM_ERROR | PCI_STATUS_REC_MASTER_ABORT |
 		PCI_STATUS_REC_TARGET_ABORT | PCI_STATUS_SIG_TARGET_ABORT));
 
-	/* The infamous DAC f*ckup only happens at boot time */
-	if ((tp->cp_cmd & PCIDAC) && !tp->cur_rx) {
-		netif_info(tp, intr, dev, "disabling PCI DAC\n");
-		tp->cp_cmd &= ~PCIDAC;
-		RTL_W16(tp, CPlusCmd, tp->cp_cmd);
-		dev->features &= ~NETIF_F_HIGHDMA;
-	}
-
-	rtl8169_hw_reset(tp);
-
 	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
-static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
+static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp,
+		   int budget)
 {
 	unsigned int dirty_tx, tx_left, bytes_compl = 0, pkts_compl = 0;
 
@@ -6285,7 +6350,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 		if (status & LastFrag) {
 			pkts_compl++;
 			bytes_compl += tx_skb->skb->len;
-			dev_consume_skb_any(tx_skb->skb);
+			napi_consume_skb(tx_skb->skb, budget);
 			tx_skb->skb = NULL;
 		}
 		dirty_tx++;
@@ -6310,7 +6375,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp)
 		 */
 		smp_mb();
 		if (netif_queue_stopped(dev) &&
-		    TX_FRAGS_READY_FOR(tp, MAX_SKB_FRAGS)) {
+		    rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) {
 			netif_wake_queue(dev);
 		}
 		/*
@@ -6348,7 +6413,6 @@ static struct sk_buff *rtl8169_try_rx_copy(void *data,
 	struct sk_buff *skb;
 	struct device *d = tp_to_dev(tp);
 
-	data = rtl8169_align(data);
 	dma_sync_single_for_cpu(d, addr, pkt_size, DMA_FROM_DEVICE);
 	prefetch(data);
 	skb = napi_alloc_skb(&tp->napi, pkt_size);
@@ -6459,9 +6523,9 @@ release_descriptor:
 static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 {
 	struct rtl8169_private *tp = dev_instance;
-	u16 status = rtl_get_events(tp);
+	u16 status = RTL_R16(tp, IntrStatus);
 
-	if (status == 0xffff || !(status & (RTL_EVENT_NAPI | tp->event_slow)))
+	if (!tp->irq_enabled || status == 0xffff || !(status & tp->irq_mask))
 		return IRQ_NONE;
 
 	if (unlikely(status & SYSErr)) {
@@ -6469,8 +6533,8 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		goto out;
 	}
 
-	if (status & LinkChg && tp->dev->phydev)
-		phy_mac_interrupt(tp->dev->phydev);
+	if (status & LinkChg)
+		phy_mac_interrupt(tp->phydev);
 
 	if (unlikely(status & RxFIFOOver &&
 	    tp->mac_version == RTL_GIGA_MAC_VER_11)) {
@@ -6479,7 +6543,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 		set_bit(RTL_FLAG_TASK_RESET_PENDING, tp->wk.flags);
 	}
 
-	if (status & RTL_EVENT_NAPI) {
+	if (status & (RTL_EVENT_NAPI | LinkChg)) {
 		rtl_irq_disable(tp);
 		napi_schedule_irqoff(&tp->napi);
 	}
@@ -6528,13 +6592,11 @@ static int rtl8169_poll(struct napi_struct *napi, int budget)
 
 	work_done = rtl_rx(dev, tp, (u32) budget);
 
-	rtl_tx(dev, tp);
+	rtl_tx(dev, tp, budget);
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-
-		rtl_irq_enable_all(tp);
-		mmiowb();
+		rtl_irq_enable(tp);
 	}
 
 	return work_done;
@@ -6563,12 +6625,12 @@ static void r8169_phylink_handler(struct net_device *ndev)
 	}
 
 	if (net_ratelimit())
-		phy_print_status(ndev->phydev);
+		phy_print_status(tp->phydev);
 }
 
 static int r8169_phy_connect(struct rtl8169_private *tp)
 {
-	struct phy_device *phydev = mdiobus_get_phy(tp->mii_bus, 0);
+	struct phy_device *phydev = tp->phydev;
 	phy_interface_t phy_mode;
 	int ret;
 
@@ -6584,7 +6646,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 		phy_set_max_speed(phydev, SPEED_100);
 
 	/* Ensure to advertise everything, incl. pause */
-	phydev->advertising = phydev->supported;
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	phy_attached_info(phydev);
 
@@ -6595,7 +6657,7 @@ static void rtl8169_down(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	phy_stop(dev->phydev);
+	phy_stop(tp->phydev);
 
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
@@ -6609,7 +6671,7 @@ static void rtl8169_down(struct net_device *dev)
 	rtl8169_rx_missed(dev);
 
 	/* Give a racing hard_start_xmit a few cycles to complete. */
-	synchronize_sched();
+	synchronize_rcu();
 
 	rtl8169_tx_clear(tp);
 
@@ -6637,7 +6699,7 @@ static int rtl8169_close(struct net_device *dev)
 
 	cancel_work_sync(&tp->wk.work);
 
-	phy_disconnect(dev->phydev);
+	phy_disconnect(tp->phydev);
 
 	pci_free_irq(pdev, 0, tp);
 
@@ -6688,10 +6750,6 @@ static int rtl_open(struct net_device *dev)
 	if (retval < 0)
 		goto err_free_rx_1;
 
-	INIT_WORK(&tp->wk.work, rtl_task);
-
-	smp_mb();
-
 	rtl_request_firmware(tp);
 
 	retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, tp,
@@ -6718,7 +6776,7 @@ static int rtl_open(struct net_device *dev)
 	if (!rtl8169_init_counter_offsets(tp))
 		netif_warn(tp, hw, dev, "counter reset/update failed\n");
 
-	phy_start(dev->phydev);
+	phy_start(tp->phydev);
 	netif_start_queue(dev);
 
 	rtl_unlock_work(tp);
@@ -6807,7 +6865,7 @@ static void rtl8169_net_suspend(struct net_device *dev)
 	if (!netif_running(dev))
 		return;
 
-	phy_stop(dev->phydev);
+	phy_stop(tp->phydev);
 	netif_device_detach(dev);
 
 	rtl_lock_work(tp);
@@ -6824,8 +6882,7 @@ static void rtl8169_net_suspend(struct net_device *dev)
 
 static int rtl8169_suspend(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	rtl8169_net_suspend(dev);
@@ -6843,20 +6900,18 @@ static void __rtl8169_resume(struct net_device *dev)
 	rtl_pll_power_up(tp);
 	rtl8169_init_phy(dev, tp);
 
-	phy_start(tp->dev->phydev);
+	phy_start(tp->phydev);
 
 	rtl_lock_work(tp);
 	napi_enable(&tp->napi);
 	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
+	rtl_reset_work(tp);
 	rtl_unlock_work(tp);
-
-	rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING);
 }
 
 static int rtl8169_resume(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	clk_prepare_enable(tp->clk);
@@ -6869,8 +6924,7 @@ static int rtl8169_resume(struct device *device)
 
 static int rtl8169_runtime_suspend(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
 	if (!tp->TxDescArray)
@@ -6891,8 +6945,7 @@ static int rtl8169_runtime_suspend(struct device *device)
 
 static int rtl8169_runtime_resume(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 	struct rtl8169_private *tp = netdev_priv(dev);
 	rtl_rar_set(tp, dev->dev_addr);
 
@@ -6910,8 +6963,7 @@ static int rtl8169_runtime_resume(struct device *device)
 
 static int rtl8169_runtime_idle(struct device *device)
 {
-	struct pci_dev *pdev = to_pci_dev(device);
-	struct net_device *dev = pci_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(device);
 
 	if (!netif_running(dev) || !netif_carrier_ok(dev))
 		pm_schedule_suspend(device, 10000);
@@ -6991,7 +7043,7 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	netif_napi_del(&tp->napi);
 
 	unregister_netdev(dev);
-	mdiobus_unregister(tp->mii_bus);
+	mdiobus_unregister(tp->phydev->mdio.bus);
 
 	rtl_release_firmware(tp);
 
@@ -7023,31 +7075,26 @@ static const struct net_device_ops rtl_netdev_ops = {
 
 static const struct rtl_cfg_info {
 	void (*hw_start)(struct rtl8169_private *tp);
-	u16 event_slow;
+	u16 irq_mask;
 	unsigned int has_gmii:1;
 	const struct rtl_coalesce_info *coalesce_info;
-	u8 default_ver;
 } rtl_cfg_infos [] = {
 	[RTL_CFG_0] = {
 		.hw_start	= rtl_hw_start_8169,
-		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
+		.irq_mask	= SYSErr | LinkChg | RxOverflow | RxFIFOOver,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8169,
-		.default_ver	= RTL_GIGA_MAC_VER_01,
 	},
 	[RTL_CFG_1] = {
 		.hw_start	= rtl_hw_start_8168,
-		.event_slow	= SYSErr | LinkChg | RxOverflow,
+		.irq_mask	= LinkChg | RxOverflow,
 		.has_gmii	= 1,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
-		.default_ver	= RTL_GIGA_MAC_VER_11,
 	},
 	[RTL_CFG_2] = {
 		.hw_start	= rtl_hw_start_8101,
-		.event_slow	= SYSErr | LinkChg | RxOverflow | RxFIFOOver |
-				  PCSTimeout,
+		.irq_mask	= LinkChg | RxOverflow | RxFIFOOver,
 		.coalesce_info	= rtl_coalesce_info_8168_8136,
-		.default_ver	= RTL_GIGA_MAC_VER_13,
 	}
 };
 
@@ -7056,9 +7103,9 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 	unsigned int flags;
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
-		RTL_W8(tp, Cfg9346, Cfg9346_Unlock);
+		rtl_unlock_config_regs(tp);
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
-		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
+		rtl_lock_config_regs(tp);
 		flags = PCI_IRQ_LEGACY;
 	} else {
 		flags = PCI_IRQ_ALL_TYPES;
@@ -7067,6 +7114,30 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 	return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags);
 }
 
+static void rtl_read_mac_address(struct rtl8169_private *tp,
+				 u8 mac_addr[ETH_ALEN])
+{
+	u32 value;
+
+	/* Get MAC address */
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38:
+	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
+		value = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC);
+		mac_addr[0] = (value >>  0) & 0xff;
+		mac_addr[1] = (value >>  8) & 0xff;
+		mac_addr[2] = (value >> 16) & 0xff;
+		mac_addr[3] = (value >> 24) & 0xff;
+
+		value = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC);
+		mac_addr[4] = (value >>  0) & 0xff;
+		mac_addr[5] = (value >>  8) & 0xff;
+		break;
+	default:
+		break;
+	}
+}
+
 DECLARE_RTL_COND(rtl_link_list_ready_cond)
 {
 	return RTL_R8(tp, MCU) & LINK_LIST_RDY;
@@ -7103,7 +7174,6 @@ static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
 static int r8169_mdio_register(struct rtl8169_private *tp)
 {
 	struct pci_dev *pdev = tp->pci_dev;
-	struct phy_device *phydev;
 	struct mii_bus *new_bus;
 	int ret;
 
@@ -7125,16 +7195,14 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	if (ret)
 		return ret;
 
-	phydev = mdiobus_get_phy(new_bus, 0);
-	if (!phydev) {
+	tp->phydev = mdiobus_get_phy(new_bus, 0);
+	if (!tp->phydev) {
 		mdiobus_unregister(new_bus);
 		return -ENODEV;
 	}
 
 	/* PHY will be woken up in rtl_open() */
-	phy_suspend(phydev);
-
-	tp->mii_bus = new_bus;
+	phy_suspend(tp->phydev);
 
 	return 0;
 }
@@ -7232,9 +7300,37 @@ static void rtl_disable_clk(void *data)
 	clk_disable_unprepare(data);
 }
 
+static int rtl_get_ether_clk(struct rtl8169_private *tp)
+{
+	struct device *d = tp_to_dev(tp);
+	struct clk *clk;
+	int rc;
+
+	clk = devm_clk_get(d, "ether_clk");
+	if (IS_ERR(clk)) {
+		rc = PTR_ERR(clk);
+		if (rc == -ENOENT)
+			/* clk-core allows NULL (for suspend / resume) */
+			rc = 0;
+		else if (rc != -EPROBE_DEFER)
+			dev_err(d, "failed to get clk: %d\n", rc);
+	} else {
+		tp->clk = clk;
+		rc = clk_prepare_enable(clk);
+		if (rc)
+			dev_err(d, "failed to enable clk: %d\n", rc);
+		else
+			rc = devm_add_action_or_reset(d, rtl_disable_clk, clk);
+	}
+
+	return rc;
+}
+
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
+	/* align to u16 for is_valid_ether_addr() */
+	u8 mac_addr[ETH_ALEN] __aligned(2) = {};
 	struct rtl8169_private *tp;
 	struct net_device *dev;
 	int chipset, region, i;
@@ -7253,30 +7349,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->supports_gmii = cfg->has_gmii;
 
 	/* Get the *optional* external "ether_clk" used on some boards */
-	tp->clk = devm_clk_get(&pdev->dev, "ether_clk");
-	if (IS_ERR(tp->clk)) {
-		rc = PTR_ERR(tp->clk);
-		if (rc == -ENOENT) {
-			/* clk-core allows NULL (for suspend / resume) */
-			tp->clk = NULL;
-		} else if (rc == -EPROBE_DEFER) {
-			return rc;
-		} else {
-			dev_err(&pdev->dev, "failed to get clk: %d\n", rc);
-			return rc;
-		}
-	} else {
-		rc = clk_prepare_enable(tp->clk);
-		if (rc) {
-			dev_err(&pdev->dev, "failed to enable clk: %d\n", rc);
-			return rc;
-		}
+	rc = rtl_get_ether_clk(tp);
+	if (rc)
+		return rc;
 
-		rc = devm_add_action_or_reset(&pdev->dev, rtl_disable_clk,
-					      tp->clk);
-		if (rc)
-			return rc;
-	}
+	/* Disable ASPM completely as that cause random device stop working
+	 * problems as well as full system hangs for some PCIe devices users.
+	 */
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1);
 
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
@@ -7309,11 +7389,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->mmio_addr = pcim_iomap_table(pdev)[region];
 
-	if (!pci_is_pcie(pdev))
-		dev_info(&pdev->dev, "not PCI Express\n");
-
 	/* Identify chip attached to board */
-	rtl8169_get_mac_version(tp, cfg->default_ver);
+	rtl8169_get_mac_version(tp);
+	if (tp->mac_version == RTL_GIGA_MAC_NONE)
+		return -ENODEV;
 
 	if (rtl_tbi_enabled(tp)) {
 		dev_err(&pdev->dev, "TBI fiber mode not supported\n");
@@ -7322,13 +7401,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd);
 
-	if (sizeof(dma_addr_t) > 4 && (use_dac == 1 || (use_dac == -1 &&
-	    tp->mac_version >= RTL_GIGA_MAC_VER_18)) &&
+	if (sizeof(dma_addr_t) > 4 && tp->mac_version >= RTL_GIGA_MAC_VER_18 &&
 	    !dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) {
-
-		/* CPlusCmd Dual Access Cycle is only needed for non-PCIe */
-		if (!pci_is_pcie(pdev))
-			tp->cp_cmd |= PCIDAC;
 		dev->features |= NETIF_F_HIGHDMA;
 	} else {
 		rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
@@ -7351,8 +7425,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	rtl_init_mdio_ops(tp);
 	rtl_init_jumbo_ops(tp);
 
-	rtl8169_print_mac_version(tp);
-
 	chipset = tp->mac_version;
 
 	rc = rtl_alloc_irq(tp);
@@ -7361,26 +7433,19 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return rc;
 	}
 
-	tp->saved_wolopts = __rtl8169_get_wol(tp);
-
 	mutex_init(&tp->wk.mutex);
+	INIT_WORK(&tp->wk.work, rtl_task);
 	u64_stats_init(&tp->rx_stats.syncp);
 	u64_stats_init(&tp->tx_stats.syncp);
 
-	/* Get MAC address */
-	switch (tp->mac_version) {
-		u8 mac_addr[ETH_ALEN] __aligned(4);
-	case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38:
-	case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51:
-		*(u32 *)&mac_addr[0] = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC);
-		*(u16 *)&mac_addr[4] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC);
+	/* get MAC address */
+	rc = eth_platform_get_mac_address(&pdev->dev, mac_addr);
+	if (rc)
+		rtl_read_mac_address(tp, mac_addr);
+
+	if (is_valid_ether_addr(mac_addr))
+		rtl_rar_set(tp, mac_addr);
 
-		if (is_valid_ether_addr(mac_addr))
-			rtl_rar_set(tp, mac_addr);
-		break;
-	default:
-		break;
-	}
 	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = RTL_R8(tp, MAC0 + i);
 
@@ -7426,10 +7491,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	dev->max_mtu = jumbo_max;
 
 	tp->hw_start = cfg->hw_start;
-	tp->event_slow = cfg->event_slow;
+	tp->irq_mask = RTL_EVENT_NAPI | cfg->irq_mask;
 	tp->coalesce_info = cfg->coalesce_info;
 
-	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
+	tp->fw_name = rtl_chip_infos[chipset].fw_name;
 
 	tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
 					    &tp->counters_phys_addr,
@@ -7450,9 +7515,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto err_mdio_unregister;
 
-	netif_info(tp, probe, dev, "%s, %pM, XID %08x, IRQ %d\n",
+	netif_info(tp, probe, dev, "%s, %pM, XID %03x, IRQ %d\n",
 		   rtl_chip_infos[chipset].name, dev->dev_addr,
-		   (u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff),
+		   (RTL_R32(tp, TxConfig) >> 20) & 0xfcf,
 		   pci_irq_vector(pdev, 0));
 
 	if (jumbo_max > JUMBO_1K)
@@ -7470,7 +7535,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	return 0;
 
 err_mdio_unregister:
-	mdiobus_unregister(tp->mii_bus);
+	mdiobus_unregister(tp->phydev->mdio.bus);
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h
index 1c6e4df94f01..ac9195add811 100644
--- a/drivers/net/ethernet/renesas/ravb.h
+++ b/drivers/net/ethernet/renesas/ravb.h
@@ -1032,7 +1032,6 @@ struct ravb_private {
 	phy_interface_t phy_interface;
 	int msg_enable;
 	int speed;
-	int duplex;
 	int emac_irq;
 	enum ravb_chip_id chip_id;
 	int rx_irqs[NUM_RX_QUEUE];
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index defed0d0c51d..8154b38c08f7 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -82,13 +82,6 @@ static int ravb_config(struct net_device *ndev)
 	return error;
 }
 
-static void ravb_set_duplex(struct net_device *ndev)
-{
-	struct ravb_private *priv = netdev_priv(ndev);
-
-	ravb_modify(ndev, ECMR, ECMR_DM, priv->duplex ? ECMR_DM : 0);
-}
-
 static void ravb_set_rate(struct net_device *ndev)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
@@ -350,7 +343,7 @@ static int ravb_ring_init(struct net_device *ndev, int q)
 	int i;
 
 	priv->rx_buf_sz = (ndev->mtu <= 1492 ? PKT_BUF_SZ : ndev->mtu) +
-		ETH_HLEN + VLAN_HLEN;
+		ETH_HLEN + VLAN_HLEN + sizeof(__sum16);
 
 	/* Allocate RX and TX skb rings */
 	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -406,13 +399,11 @@ error:
 /* E-MAC init function */
 static void ravb_emac_init(struct net_device *ndev)
 {
-	struct ravb_private *priv = netdev_priv(ndev);
-
 	/* Receive frame limit set register */
 	ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
 
 	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
-	ravb_write(ndev, ECMR_ZPF | (priv->duplex ? ECMR_DM : 0) |
+	ravb_write(ndev, ECMR_ZPF | ECMR_DM |
 		   (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
 		   ECMR_TE | ECMR_RE, ECMR);
 
@@ -467,7 +458,7 @@ static int ravb_dmac_init(struct net_device *ndev)
 		   RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR);
 
 	/* Set FIFO size */
-	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00222200, TGC);
+	ravb_write(ndev, TGC_TQP_AVBMODE1 | 0x00112200, TGC);
 
 	/* Timestamp enable */
 	ravb_write(ndev, TCCR_TFEN, TCCR);
@@ -533,13 +524,15 @@ static void ravb_rx_csum(struct sk_buff *skb)
 {
 	u8 *hw_csum;
 
-	/* The hardware checksum is 2 bytes appended to packet data */
-	if (unlikely(skb->len < 2))
+	/* The hardware checksum is contained in sizeof(__sum16) (2) bytes
+	 * appended to packet data
+	 */
+	if (unlikely(skb->len < sizeof(__sum16)))
 		return;
-	hw_csum = skb_tail_pointer(skb) - 2;
+	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
 	skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
 	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb_trim(skb, skb->len - 2);
+	skb_trim(skb, skb->len - sizeof(__sum16));
 }
 
 /* Packet receive function for Ethernet AVB */
@@ -995,12 +988,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 		ravb_rcv_snd_disable(ndev);
 
 	if (phydev->link) {
-		if (phydev->duplex != priv->duplex) {
-			new_state = true;
-			priv->duplex = phydev->duplex;
-			ravb_set_duplex(ndev);
-		}
-
 		if (phydev->speed != priv->speed) {
 			new_state = true;
 			priv->speed = phydev->speed;
@@ -1015,7 +1002,6 @@ static void ravb_adjust_link(struct net_device *ndev)
 		new_state = true;
 		priv->link = 0;
 		priv->speed = 0;
-		priv->duplex = -1;
 	}
 
 	/* Enable TX and RX right over here, if E-MAC change is ignored */
@@ -1045,7 +1031,6 @@ static int ravb_phy_init(struct net_device *ndev)
 
 	priv->link = 0;
 	priv->speed = 0;
-	priv->duplex = -1;
 
 	/* Try connecting to PHY */
 	pn = of_parse_phandle(np, "phy-handle", 0);
@@ -1088,6 +1073,10 @@ static int ravb_phy_init(struct net_device *ndev)
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_Pause_BIT);
 	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT);
 
+	/* Half Duplex is not supported */
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+
 	phy_attached_info(phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index f27a0dc8c563..e33af371b169 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -555,7 +555,7 @@ static int sh_eth_soft_reset_gether(struct net_device *ndev)
 	sh_eth_write(ndev, 0, RDFFR);
 
 	/* Reset HW CRC register */
-	if (mdp->cd->hw_checksum)
+	if (mdp->cd->csmr)
 		sh_eth_write(ndev, 0, CSMR);
 
 	/* Select MII mode */
@@ -619,7 +619,8 @@ static struct sh_eth_cpu_data r7s72100_data = {
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.tsu		= 1,
 	.no_tx_cntrs	= 1,
 };
@@ -668,7 +669,8 @@ static struct sh_eth_cpu_data r8a7740_data = {
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.tsu		= 1,
 	.select_mii	= 1,
 	.magic		= 1,
@@ -793,7 +795,8 @@ static struct sh_eth_cpu_data r8a77980_data = {
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.select_mii	= 1,
 	.magic		= 1,
 	.cexcr		= 1,
@@ -1045,7 +1048,8 @@ static struct sh_eth_cpu_data sh7734_data = {
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
 	.tsu		= 1,
-	.hw_checksum	= 1,
+	.csmr		= 1,
+	.rx_csum	= 1,
 	.select_mii	= 1,
 	.magic		= 1,
 	.cexcr		= 1,
@@ -1088,6 +1092,7 @@ static struct sh_eth_cpu_data sh7763_data = {
 	.irq_flags	= IRQF_SHARED,
 	.magic		= 1,
 	.cexcr		= 1,
+	.rx_csum	= 1,
 	.dual_port	= 1,
 };
 
@@ -1532,8 +1537,9 @@ static int sh_eth_dev_init(struct net_device *ndev)
 	mdp->irq_enabled = true;
 	sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR);
 
-	/* PAUSE Prohibition */
+	/* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
 	sh_eth_write(ndev, ECMR_ZPF | (mdp->duplex ? ECMR_DM : 0) |
+		     (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) |
 		     ECMR_TE | ECMR_RE, ECMR);
 
 	if (mdp->cd->set_rate)
@@ -1592,6 +1598,19 @@ static void sh_eth_dev_exit(struct net_device *ndev)
 	update_mac_address(ndev);
 }
 
+static void sh_eth_rx_csum(struct sk_buff *skb)
+{
+	u8 *hw_csum;
+
+	/* The hardware checksum is 2 bytes appended to packet data */
+	if (unlikely(skb->len < sizeof(__sum16)))
+		return;
+	hw_csum = skb_tail_pointer(skb) - sizeof(__sum16);
+	skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum));
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb_trim(skb, skb->len - sizeof(__sum16));
+}
+
 /* Packet receive function */
 static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 {
@@ -1633,7 +1652,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 		 * the RFS bits are from bit 25 to bit 16. So, the
 		 * driver needs right shifting by 16.
 		 */
-		if (mdp->cd->hw_checksum)
+		if (mdp->cd->csmr)
 			desc_status >>= 16;
 
 		skb = mdp->rx_skbuff[entry];
@@ -1666,6 +1685,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota)
 					 DMA_FROM_DEVICE);
 			skb_put(skb, pkt_len);
 			skb->protocol = eth_type_trans(skb, ndev);
+			if (ndev->features & NETIF_F_RXCSUM)
+				sh_eth_rx_csum(skb);
 			netif_receive_skb(skb);
 			ndev->stats.rx_packets++;
 			ndev->stats.rx_bytes += pkt_len;
@@ -2173,7 +2194,7 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf)
 	add_reg(MAFCR);
 	if (cd->rtrate)
 		add_reg(RTRATE);
-	if (cd->hw_checksum)
+	if (cd->csmr)
 		add_reg(CSMR);
 	if (cd->select_mii)
 		add_reg(RMII_MII);
@@ -2921,6 +2942,39 @@ static void sh_eth_set_rx_mode(struct net_device *ndev)
 	spin_unlock_irqrestore(&mdp->lock, flags);
 }
 
+static void sh_eth_set_rx_csum(struct net_device *ndev, bool enable)
+{
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mdp->lock, flags);
+
+	/* Disable TX and RX */
+	sh_eth_rcv_snd_disable(ndev);
+
+	/* Modify RX Checksum setting */
+	sh_eth_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0);
+
+	/* Enable TX and RX */
+	sh_eth_rcv_snd_enable(ndev);
+
+	spin_unlock_irqrestore(&mdp->lock, flags);
+}
+
+static int sh_eth_set_features(struct net_device *ndev,
+			       netdev_features_t features)
+{
+	netdev_features_t changed = ndev->features ^ features;
+	struct sh_eth_private *mdp = netdev_priv(ndev);
+
+	if (changed & NETIF_F_RXCSUM && mdp->cd->rx_csum)
+		sh_eth_set_rx_csum(ndev, features & NETIF_F_RXCSUM);
+
+	ndev->features = features;
+
+	return 0;
+}
+
 static int sh_eth_get_vtag_index(struct sh_eth_private *mdp)
 {
 	if (!mdp->port)
@@ -3102,6 +3156,7 @@ static const struct net_device_ops sh_eth_netdev_ops = {
 	.ndo_change_mtu		= sh_eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_set_features	= sh_eth_set_features,
 };
 
 static const struct net_device_ops sh_eth_netdev_ops_tsu = {
@@ -3117,6 +3172,7 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = {
 	.ndo_change_mtu		= sh_eth_change_mtu,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= eth_mac_addr,
+	.ndo_set_features	= sh_eth_set_features,
 };
 
 #ifdef CONFIG_OF
@@ -3125,12 +3181,16 @@ static struct sh_eth_plat_data *sh_eth_parse_dt(struct device *dev)
 	struct device_node *np = dev->of_node;
 	struct sh_eth_plat_data *pdata;
 	const char *mac_addr;
+	int ret;
 
 	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return NULL;
 
-	pdata->phy_interface = of_get_phy_mode(np);
+	ret = of_get_phy_mode(np);
+	if (ret < 0)
+		return NULL;
+	pdata->phy_interface = ret;
 
 	mac_addr = of_get_mac_address(np);
 	if (mac_addr)
@@ -3245,6 +3305,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 	ndev->max_mtu = 2000 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN);
 	ndev->min_mtu = ETH_MIN_MTU;
 
+	if (mdp->cd->rx_csum) {
+		ndev->features = NETIF_F_RXCSUM;
+		ndev->hw_features = NETIF_F_RXCSUM;
+	}
+
 	/* set function */
 	if (mdp->cd->tsu)
 		ndev->netdev_ops = &sh_eth_netdev_ops_tsu;
@@ -3294,7 +3359,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev)
 			goto out_release;
 		}
 		mdp->port = port;
-		ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER;
+		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
 		/* Need to init only the first port of the two sharing a TSU */
 		if (port == 0) {
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 0c18650bbfe6..850726301e1c 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -499,7 +499,8 @@ struct sh_eth_cpu_data {
 	unsigned no_ade:1;	/* E-DMAC DOES NOT have ADE bit in EESR */
 	unsigned no_xdfar:1;	/* E-DMAC DOES NOT have RDFAR/TDFAR */
 	unsigned xdfar_rw:1;	/* E-DMAC has writeable RDFAR/TDFAR */
-	unsigned hw_checksum:1;	/* E-DMAC has CSMR */
+	unsigned csmr:1;	/* E-DMAC has CSMR */
+	unsigned rx_csum:1;	/* EtherC has ECMR.RCSC */
 	unsigned select_mii:1;	/* EtherC has RMII_MII (MII select register) */
 	unsigned rmiimode:1;	/* EtherC has RMIIMODE register */
 	unsigned rtrate:1;	/* EtherC has RTRATE register */
diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h
index 748fb12260a6..2b2e1c4f0dc3 100644
--- a/drivers/net/ethernet/rocker/rocker.h
+++ b/drivers/net/ethernet/rocker/rocker.h
@@ -109,8 +109,6 @@ struct rocker_world_ops {
 	int (*port_attr_bridge_flags_set)(struct rocker_port *rocker_port,
 					  unsigned long brport_flags,
 					  struct switchdev_trans *trans);
-	int (*port_attr_bridge_flags_get)(const struct rocker_port *rocker_port,
-					  unsigned long *p_brport_flags);
 	int (*port_attr_bridge_flags_support_get)(const struct rocker_port *
 						  rocker_port,
 						  unsigned long *
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index beb06628f22d..a71c900ca04f 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -1566,45 +1566,57 @@ static int rocker_world_port_attr_stp_state_set(struct rocker_port *rocker_port,
 }
 
 static int
-rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
-					unsigned long brport_flags,
-					struct switchdev_trans *trans)
+rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port *
+						rocker_port,
+						unsigned long *
+						p_brport_flags_support)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
-	if (!wops->port_attr_bridge_flags_set)
+	if (!wops->port_attr_bridge_flags_support_get)
 		return -EOPNOTSUPP;
-
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
-
-	return wops->port_attr_bridge_flags_set(rocker_port, brport_flags,
-						trans);
+	return wops->port_attr_bridge_flags_support_get(rocker_port,
+							p_brport_flags_support);
 }
 
 static int
-rocker_world_port_attr_bridge_flags_get(const struct rocker_port *rocker_port,
-					unsigned long *p_brport_flags)
+rocker_world_port_attr_pre_bridge_flags_set(struct rocker_port *rocker_port,
+					    unsigned long brport_flags,
+					    struct switchdev_trans *trans)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
+	unsigned long brport_flags_s;
+	int err;
 
-	if (!wops->port_attr_bridge_flags_get)
+	if (!wops->port_attr_bridge_flags_set)
 		return -EOPNOTSUPP;
-	return wops->port_attr_bridge_flags_get(rocker_port, p_brport_flags);
+
+	err = rocker_world_port_attr_bridge_flags_support_get(rocker_port,
+							      &brport_flags_s);
+	if (err)
+		return err;
+
+	if (brport_flags & ~brport_flags_s)
+		return -EINVAL;
+
+	return 0;
 }
 
 static int
-rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port *
-						rocker_port,
-						unsigned long *
-						p_brport_flags_support)
+rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
+					unsigned long brport_flags,
+					struct switchdev_trans *trans)
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
-	if (!wops->port_attr_bridge_flags_support_get)
+	if (!wops->port_attr_bridge_flags_set)
 		return -EOPNOTSUPP;
-	return wops->port_attr_bridge_flags_support_get(rocker_port,
-							p_brport_flags_support);
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	return wops->port_attr_bridge_flags_set(rocker_port, brport_flags,
+						trans);
 }
 
 static int
@@ -1632,9 +1644,6 @@ rocker_world_port_obj_vlan_add(struct rocker_port *rocker_port,
 {
 	struct rocker_world_ops *wops = rocker_port->rocker->wops;
 
-	if (netif_is_bridge_master(vlan->obj.orig_dev))
-		return -EOPNOTSUPP;
-
 	if (!wops->port_obj_vlan_add)
 		return -EOPNOTSUPP;
 
@@ -2029,6 +2038,18 @@ static void rocker_port_neigh_destroy(struct net_device *dev,
 			    err);
 }
 
+static int rocker_port_get_port_parent_id(struct net_device *dev,
+					  struct netdev_phys_item_id *ppid)
+{
+	const struct rocker_port *rocker_port = netdev_priv(dev);
+	const struct rocker *rocker = rocker_port->rocker;
+
+	ppid->id_len = sizeof(rocker->hw.id);
+	memcpy(&ppid->id, &rocker->hw.id, ppid->id_len);
+
+	return 0;
+}
+
 static const struct net_device_ops rocker_port_netdev_ops = {
 	.ndo_open			= rocker_port_open,
 	.ndo_stop			= rocker_port_stop,
@@ -2038,39 +2059,13 @@ static const struct net_device_ops rocker_port_netdev_ops = {
 	.ndo_get_phys_port_name		= rocker_port_get_phys_port_name,
 	.ndo_change_proto_down		= rocker_port_change_proto_down,
 	.ndo_neigh_destroy		= rocker_port_neigh_destroy,
+	.ndo_get_port_parent_id		= rocker_port_get_port_parent_id,
 };
 
 /********************
  * swdev interface
  ********************/
 
-static int rocker_port_attr_get(struct net_device *dev,
-				struct switchdev_attr *attr)
-{
-	const struct rocker_port *rocker_port = netdev_priv(dev);
-	const struct rocker *rocker = rocker_port->rocker;
-	int err = 0;
-
-	switch (attr->id) {
-	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(rocker->hw.id);
-		memcpy(&attr->u.ppid.id, &rocker->hw.id, attr->u.ppid.id_len);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
-		err = rocker_world_port_attr_bridge_flags_get(rocker_port,
-							      &attr->u.brport_flags);
-		break;
-	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT:
-		err = rocker_world_port_attr_bridge_flags_support_get(rocker_port,
-								      &attr->u.brport_flags_support);
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return err;
-}
-
 static int rocker_port_attr_set(struct net_device *dev,
 				const struct switchdev_attr *attr,
 				struct switchdev_trans *trans)
@@ -2084,6 +2079,11 @@ static int rocker_port_attr_set(struct net_device *dev,
 							   attr->u.stp_state,
 							   trans);
 		break;
+	case SWITCHDEV_ATTR_ID_PORT_PRE_BRIDGE_FLAGS:
+		err = rocker_world_port_attr_pre_bridge_flags_set(rocker_port,
+							      attr->u.brport_flags,
+							      trans);
+		break;
 	case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS:
 		err = rocker_world_port_attr_bridge_flags_set(rocker_port,
 							      attr->u.brport_flags,
@@ -2142,13 +2142,6 @@ static int rocker_port_obj_del(struct net_device *dev,
 	return err;
 }
 
-static const struct switchdev_ops rocker_port_switchdev_ops = {
-	.switchdev_port_attr_get	= rocker_port_attr_get,
-	.switchdev_port_attr_set	= rocker_port_attr_set,
-	.switchdev_port_obj_add		= rocker_port_obj_add,
-	.switchdev_port_obj_del		= rocker_port_obj_del,
-};
-
 struct rocker_fib_event_work {
 	struct work_struct work;
 	union {
@@ -2602,7 +2595,6 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	rocker_port_dev_addr_init(rocker_port);
 	dev->netdev_ops = &rocker_port_netdev_ops;
 	dev->ethtool_ops = &rocker_port_ethtool_ops;
-	dev->switchdev_ops = &rocker_port_switchdev_ops;
 	netif_tx_napi_add(dev, &rocker_port->napi_tx, rocker_port_poll_tx,
 			  NAPI_POLL_WEIGHT);
 	netif_napi_add(dev, &rocker_port->napi_rx, rocker_port_poll_rx,
@@ -2713,6 +2705,19 @@ static bool rocker_port_dev_check(const struct net_device *dev)
 	return dev->netdev_ops == &rocker_port_netdev_ops;
 }
 
+static int
+rocker_switchdev_port_attr_set_event(struct net_device *netdev,
+		struct switchdev_notifier_port_attr_info *port_attr_info)
+{
+	int err;
+
+	err = rocker_port_attr_set(netdev, port_attr_info->attr,
+				   port_attr_info->trans);
+
+	port_attr_info->handled = true;
+	return notifier_from_errno(err);
+}
+
 struct rocker_switchdev_event_work {
 	struct work_struct work;
 	struct switchdev_notifier_fdb_info fdb_info;
@@ -2730,7 +2735,7 @@ rocker_fdb_offload_notify(struct rocker_port *rocker_port,
 	info.vid = recv_info->vid;
 	info.offloaded = true;
 	call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED,
-				 rocker_port->dev, &info.info);
+				 rocker_port->dev, &info.info, NULL);
 }
 
 static void rocker_switchdev_event_work(struct work_struct *work)
@@ -2782,6 +2787,9 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 	if (!rocker_port_dev_check(dev))
 		return NOTIFY_DONE;
 
+	if (event == SWITCHDEV_PORT_ATTR_SET)
+		return rocker_switchdev_port_attr_set_event(dev, ptr);
+
 	rocker_port = netdev_priv(dev);
 	switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC);
 	if (WARN_ON(!switchdev_work))
@@ -2797,6 +2805,11 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 		memcpy(&switchdev_work->fdb_info, ptr,
 		       sizeof(switchdev_work->fdb_info));
 		switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
+		if (unlikely(!switchdev_work->fdb_info.addr)) {
+			kfree(switchdev_work);
+			return NOTIFY_BAD;
+		}
+
 		ether_addr_copy((u8 *)switchdev_work->fdb_info.addr,
 				fdb_info->addr);
 		/* Take a reference on the rocker device */
@@ -2812,12 +2825,56 @@ static int rocker_switchdev_event(struct notifier_block *unused,
 	return NOTIFY_DONE;
 }
 
+static int
+rocker_switchdev_port_obj_event(unsigned long event, struct net_device *netdev,
+			struct switchdev_notifier_port_obj_info *port_obj_info)
+{
+	int err = -EOPNOTSUPP;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+		err = rocker_port_obj_add(netdev, port_obj_info->obj,
+					  port_obj_info->trans);
+		break;
+	case SWITCHDEV_PORT_OBJ_DEL:
+		err = rocker_port_obj_del(netdev, port_obj_info->obj);
+		break;
+	}
+
+	port_obj_info->handled = true;
+	return notifier_from_errno(err);
+}
+
+static int rocker_switchdev_blocking_event(struct notifier_block *unused,
+					   unsigned long event, void *ptr)
+{
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+
+	if (!rocker_port_dev_check(dev))
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case SWITCHDEV_PORT_OBJ_ADD:
+	case SWITCHDEV_PORT_OBJ_DEL:
+		return rocker_switchdev_port_obj_event(event, dev, ptr);
+	case SWITCHDEV_PORT_ATTR_SET:
+		return rocker_switchdev_port_attr_set_event(dev, ptr);
+	}
+
+	return NOTIFY_DONE;
+}
+
 static struct notifier_block rocker_switchdev_notifier = {
 	.notifier_call = rocker_switchdev_event,
 };
 
+static struct notifier_block rocker_switchdev_blocking_notifier = {
+	.notifier_call = rocker_switchdev_blocking_event,
+};
+
 static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
+	struct notifier_block *nb;
 	struct rocker *rocker;
 	int err;
 
@@ -2933,6 +2990,13 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto err_register_switchdev_notifier;
 	}
 
+	nb = &rocker_switchdev_blocking_notifier;
+	err = register_switchdev_blocking_notifier(nb);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to register switchdev blocking notifier\n");
+		goto err_register_switchdev_blocking_notifier;
+	}
+
 	rocker->hw.id = rocker_read64(rocker, SWITCH_ID);
 
 	dev_info(&pdev->dev, "Rocker switch with id %*phN\n",
@@ -2940,6 +3004,8 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+err_register_switchdev_blocking_notifier:
+	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 err_register_switchdev_notifier:
 	unregister_fib_notifier(&rocker->fib_nb);
 err_register_fib_notifier:
@@ -2971,6 +3037,10 @@ err_pci_enable_device:
 static void rocker_remove(struct pci_dev *pdev)
 {
 	struct rocker *rocker = pci_get_drvdata(pdev);
+	struct notifier_block *nb;
+
+	nb = &rocker_switchdev_blocking_notifier;
+	unregister_switchdev_blocking_notifier(nb);
 
 	unregister_switchdev_notifier(&rocker_switchdev_notifier);
 	unregister_fib_notifier(&rocker->fib_nb);
diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c
index 6473cc68c2d5..fa296a7c255d 100644
--- a/drivers/net/ethernet/rocker/rocker_ofdpa.c
+++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c
@@ -1833,10 +1833,10 @@ static void ofdpa_port_fdb_learn_work(struct work_struct *work)
 	rtnl_lock();
 	if (learned && removing)
 		call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE,
-					 lw->ofdpa_port->dev, &info.info);
+					 lw->ofdpa_port->dev, &info.info, NULL);
 	else if (learned && !removing)
 		call_switchdev_notifiers(SWITCHDEV_FDB_ADD_TO_BRIDGE,
-					 lw->ofdpa_port->dev, &info.info);
+					 lw->ofdpa_port->dev, &info.info, NULL);
 	rtnl_unlock();
 
 	kfree(work);
@@ -2512,16 +2512,6 @@ static int ofdpa_port_attr_bridge_flags_set(struct rocker_port *rocker_port,
 }
 
 static int
-ofdpa_port_attr_bridge_flags_get(const struct rocker_port *rocker_port,
-				 unsigned long *p_brport_flags)
-{
-	const struct ofdpa_port *ofdpa_port = rocker_port->wpriv;
-
-	*p_brport_flags = ofdpa_port->brport_flags;
-	return 0;
-}
-
-static int
 ofdpa_port_attr_bridge_flags_support_get(const struct rocker_port *
 					 rocker_port,
 					 unsigned long *
@@ -2823,7 +2813,6 @@ struct rocker_world_ops rocker_ofdpa_ops = {
 	.port_stop = ofdpa_port_stop,
 	.port_attr_stp_state_set = ofdpa_port_attr_stp_state_set,
 	.port_attr_bridge_flags_set = ofdpa_port_attr_bridge_flags_set,
-	.port_attr_bridge_flags_get = ofdpa_port_attr_bridge_flags_get,
 	.port_attr_bridge_flags_support_get = ofdpa_port_attr_bridge_flags_support_get,
 	.port_attr_bridge_ageing_time_set = ofdpa_port_attr_bridge_ageing_time_set,
 	.port_obj_vlan_add = ofdpa_port_obj_vlan_add,
diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
index 690aee88f0eb..6d22dd500790 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c
@@ -400,9 +400,9 @@ static int init_tx_ring(struct device *dev, u8 queue_no,
 	}
 
 	/* allocate memory for TX descriptors */
-	tx_ring->dma_tx = dma_zalloc_coherent(dev,
-					      tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
-					      &tx_ring->dma_tx_phy, GFP_KERNEL);
+	tx_ring->dma_tx = dma_alloc_coherent(dev,
+					     tx_rsize * sizeof(struct sxgbe_tx_norm_desc),
+					     &tx_ring->dma_tx_phy, GFP_KERNEL);
 	if (!tx_ring->dma_tx)
 		return -ENOMEM;
 
@@ -479,9 +479,9 @@ static int init_rx_ring(struct net_device *dev, u8 queue_no,
 	rx_ring->queue_no = queue_no;
 
 	/* allocate memory for RX descriptors */
-	rx_ring->dma_rx = dma_zalloc_coherent(priv->device,
-					      rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
-					      &rx_ring->dma_rx_phy, GFP_KERNEL);
+	rx_ring->dma_rx = dma_alloc_coherent(priv->device,
+					     rx_rsize * sizeof(struct sxgbe_rx_norm_desc),
+					     &rx_ring->dma_rx_phy, GFP_KERNEL);
 
 	if (rx_ring->dma_rx == NULL)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 7eeac3d6cfe8..e888b479c596 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -6041,23 +6041,33 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = {
 	{ NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3, 0,   3, "sfc_exp_rom_cfg" },
 	{ NVRAM_PARTITION_TYPE_LICENSE,		   0,    0, "sfc_license" },
 	{ NVRAM_PARTITION_TYPE_PHY_MIN,		   0xff, 0, "sfc_phy_fw" },
+	{ NVRAM_PARTITION_TYPE_MUM_FIRMWARE,	   0,    0, "sfc_mumfw" },
+	{ NVRAM_PARTITION_TYPE_EXPANSION_UEFI,	   0,    0, "sfc_uefi" },
+	{ NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS, 0,    0, "sfc_dynamic_cfg_dflt" },
+	{ NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS, 0,    0, "sfc_exp_rom_cfg_dflt" },
+	{ NVRAM_PARTITION_TYPE_STATUS,		   0,    0, "sfc_status" },
+	{ NVRAM_PARTITION_TYPE_BUNDLE,		   0,    0, "sfc_bundle" },
+	{ NVRAM_PARTITION_TYPE_BUNDLE_METADATA,	   0,    0, "sfc_bundle_metadata" },
 };
+#define EF10_NVRAM_PARTITION_COUNT	ARRAY_SIZE(efx_ef10_nvram_types)
 
 static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 					struct efx_mcdi_mtd_partition *part,
-					unsigned int type)
+					unsigned int type,
+					unsigned long *found)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_METADATA_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_METADATA_OUT_LENMAX);
 	const struct efx_ef10_nvram_type_info *info;
 	size_t size, erase_size, outlen;
+	int type_idx = 0;
 	bool protected;
 	int rc;
 
-	for (info = efx_ef10_nvram_types; ; info++) {
-		if (info ==
-		    efx_ef10_nvram_types + ARRAY_SIZE(efx_ef10_nvram_types))
+	for (type_idx = 0; ; type_idx++) {
+		if (type_idx == EF10_NVRAM_PARTITION_COUNT)
 			return -ENODEV;
+		info = efx_ef10_nvram_types + type_idx;
 		if ((type & ~info->type_mask) == info->type)
 			break;
 	}
@@ -6067,8 +6077,22 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
 	if (rc)
 		return rc;
+	if (protected &&
+	    (type != NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS &&
+	     type != NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS))
+		/* Hide protected partitions that don't provide defaults. */
+		return -ENODEV;
+
 	if (protected)
-		return -ENODEV; /* hide it */
+		/* Protected partitions are read only. */
+		erase_size = 0;
+
+	/* If we've already exposed a partition of this type, hide this
+	 * duplicate.  All operations on MTDs are keyed by the type anyway,
+	 * so we can't act on the duplicate.
+	 */
+	if (__test_and_set_bit(type_idx, found))
+		return -EEXIST;
 
 	part->nvram_type = type;
 
@@ -6091,6 +6115,9 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	part->common.mtd.flags = MTD_CAP_NORFLASH;
 	part->common.mtd.size = size;
 	part->common.mtd.erasesize = erase_size;
+	/* sfc_status is read-only */
+	if (!erase_size)
+		part->common.mtd.flags |= MTD_NO_ERASE;
 
 	return 0;
 }
@@ -6098,6 +6125,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 static int efx_ef10_mtd_probe(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
+	DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 };
 	struct efx_mcdi_mtd_partition *parts;
 	size_t outlen, n_parts_total, i, n_parts;
 	unsigned int type;
@@ -6126,11 +6154,13 @@ static int efx_ef10_mtd_probe(struct efx_nic *efx)
 	for (i = 0; i < n_parts_total; i++) {
 		type = MCDI_ARRAY_DWORD(outbuf, NVRAM_PARTITIONS_OUT_TYPE_ID,
 					i);
-		rc = efx_ef10_mtd_probe_partition(efx, &parts[n_parts], type);
-		if (rc == 0)
-			n_parts++;
-		else if (rc != -ENODEV)
+		rc = efx_ef10_mtd_probe_partition(efx, &parts[n_parts], type,
+						  found);
+		if (rc == -EEXIST || rc == -ENODEV)
+			continue;
+		if (rc)
 			goto fail;
+		n_parts++;
 	}
 
 	rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts));
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 98fe7e762e17..bc655ffc9e02 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -915,7 +915,7 @@ rollback:
 
 void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
 {
-	mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100));
+	mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(10));
 }
 
 static bool efx_default_channel_want_txqs(struct efx_channel *channel)
@@ -3167,7 +3167,7 @@ struct hlist_head *efx_rps_hash_bucket(struct efx_nic *efx,
 {
 	u32 hash = efx_filter_spec_hash(spec);
 
-	WARN_ON(!spin_is_locked(&efx->rps_hash_lock));
+	lockdep_assert_held(&efx->rps_hash_lock);
 	if (!efx->rps_hash_table)
 		return NULL;
 	return &efx->rps_hash_table[hash % EFX_ARFS_HASH_TABLE_SIZE];
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 3143588ffd77..600d7b895cf2 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -539,7 +539,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
 	/* We need rx buffers and interrupts. */
 	already_up = (efx->net_dev->flags & IFF_UP);
 	if (!already_up) {
-		rc = dev_open(efx->net_dev);
+		rc = dev_open(efx->net_dev, NULL);
 		if (rc) {
 			netif_err(efx, drv, efx->net_dev,
 				  "failed opening device.\n");
diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 1ccdb7a82e2a..72cedec945c1 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -517,7 +517,7 @@ static void ef4_ethtool_self_test(struct net_device *net_dev,
 	/* We need rx buffers and interrupts. */
 	already_up = (efx->net_dev->flags & IFF_UP);
 	if (!already_up) {
-		rc = dev_open(efx->net_dev);
+		rc = dev_open(efx->net_dev, NULL);
 		if (rc) {
 			netif_err(efx, drv, efx->net_dev,
 				  "failed opening device.\n");
diff --git a/drivers/net/ethernet/sfc/falcon/nic.c b/drivers/net/ethernet/sfc/falcon/nic.c
index a8ecb33390da..9c07b5175581 100644
--- a/drivers/net/ethernet/sfc/falcon/nic.c
+++ b/drivers/net/ethernet/sfc/falcon/nic.c
@@ -33,8 +33,8 @@
 int ef4_nic_alloc_buffer(struct ef4_nic *efx, struct ef4_buffer *buffer,
 			 unsigned int len, gfp_t gfp_flags)
 {
-	buffer->addr = dma_zalloc_coherent(&efx->pci_dev->dev, len,
-					   &buffer->dma_addr, gfp_flags);
+	buffer->addr = dma_alloc_coherent(&efx->pci_dev->dev, len,
+					  &buffer->dma_addr, gfp_flags);
 	if (!buffer->addr)
 		return -ENOMEM;
 	buffer->len = len;
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index dfad93fca0a6..295ec1787b9f 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -2074,22 +2074,26 @@ fail:
 
 static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
 {
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_IN_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_V2_IN_LEN);
 	int rc;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_START_IN_TYPE, type);
+	MCDI_POPULATE_DWORD_1(inbuf, NVRAM_UPDATE_START_V2_IN_FLAGS,
+			      NVRAM_UPDATE_START_V2_IN_FLAG_REPORT_VERIFY_RESULT,
+			      1);
 
 	BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_START_OUT_LEN != 0);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_START, inbuf, sizeof(inbuf),
 			  NULL, 0, NULL);
+
 	return rc;
 }
 
 static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 			       loff_t offset, u8 *buffer, size_t length)
 {
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_READ_IN_LEN);
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_READ_IN_V2_LEN);
 	MCDI_DECLARE_BUF(outbuf,
 			 MC_CMD_NVRAM_READ_OUT_LEN(EFX_MCDI_NVRAM_LEN_MAX));
 	size_t outlen;
@@ -2098,6 +2102,8 @@ static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_TYPE, type);
 	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_OFFSET, offset);
 	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_LENGTH, length);
+	MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_V2_MODE,
+		       MC_CMD_NVRAM_READ_IN_V2_DEFAULT);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_READ, inbuf, sizeof(inbuf),
 			  outbuf, sizeof(outbuf), &outlen);
@@ -2147,15 +2153,51 @@ static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
 
 static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 {
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN);
-	int rc;
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN);
+	size_t outlen;
+	int rc, rc2;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type);
-
-	BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN != 0);
+	/* Always set this flag. Old firmware ignores it */
+	MCDI_POPULATE_DWORD_1(inbuf, NVRAM_UPDATE_FINISH_V2_IN_FLAGS,
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_REPORT_VERIFY_RESULT,
+			      1);
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf),
-			  NULL, 0, NULL);
+			  outbuf, sizeof(outbuf), &outlen);
+	if (!rc && outlen >= MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN) {
+		rc2 = MCDI_DWORD(outbuf, NVRAM_UPDATE_FINISH_V2_OUT_RESULT_CODE);
+		if (rc2 != MC_CMD_NVRAM_VERIFY_RC_SUCCESS)
+			netif_err(efx, drv, efx->net_dev,
+				  "NVRAM update failed verification with code 0x%x\n",
+				  rc2);
+		switch (rc2) {
+		case MC_CMD_NVRAM_VERIFY_RC_SUCCESS:
+			break;
+		case MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_TRUSTED_APPROVERS_CHECK_FAILED:
+		case MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHAIN_CHECK_FAILED:
+			rc = -EIO;
+			break;
+		case MC_CMD_NVRAM_VERIFY_RC_INVALID_CMS_FORMAT:
+		case MC_CMD_NVRAM_VERIFY_RC_BAD_MESSAGE_DIGEST:
+			rc = -EINVAL;
+			break;
+		case MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES:
+		case MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS:
+		case MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH:
+			rc = -EPERM;
+			break;
+		default:
+			netif_err(efx, drv, efx->net_dev,
+				  "Unknown response to NVRAM_UPDATE_FINISH\n");
+			rc = -EIO;
+		}
+	}
+
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 3839eec783ea..20a5523bf9f3 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -6784,6 +6784,14 @@
  * subset of the information stored in this partition.
  */
 #define          NVRAM_PARTITION_TYPE_FRU_INFORMATION 0x1d00
+/* enum: Bundle image partition */
+#define          NVRAM_PARTITION_TYPE_BUNDLE 0x1e00
+/* enum: Bundle metadata partition that holds additional information related to
+ * a bundle update in TLV format
+ */
+#define          NVRAM_PARTITION_TYPE_BUNDLE_METADATA 0x1e01
+/* enum: Bundle update non-volatile log output partition */
+#define          NVRAM_PARTITION_TYPE_BUNDLE_LOG 0x1e02
 /* enum: Start of reserved value range (firmware may use for any purpose) */
 #define          NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00
 /* enum: End of reserved value range (firmware may use for any purpose) */
diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c
index 4ac30b6e5dab..0d03e0577d85 100644
--- a/drivers/net/ethernet/sfc/mtd.c
+++ b/drivers/net/ethernet/sfc/mtd.c
@@ -66,6 +66,9 @@ int efx_mtd_add(struct efx_nic *efx, struct efx_mtd_partition *parts,
 
 		part->mtd.writesize = 1;
 
+		if (!(part->mtd.flags & MTD_NO_ERASE))
+			part->mtd.flags |= MTD_WRITEABLE;
+
 		part->mtd.owner = THIS_MODULE;
 		part->mtd.priv = efx;
 		part->mtd.name = part->name;
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index aa1945a858d5..c2d45a40eb48 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -34,8 +34,8 @@
 int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer,
 			 unsigned int len, gfp_t gfp_flags)
 {
-	buffer->addr = dma_zalloc_coherent(&efx->pci_dev->dev, len,
-					   &buffer->dma_addr, gfp_flags);
+	buffer->addr = dma_alloc_coherent(&efx->pci_dev->dev, len,
+					  &buffer->dma_addr, gfp_flags);
 	if (!buffer->addr)
 		return -ENOMEM;
 	buffer->len = len;
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 396ff01298cd..8702ab44d80b 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -360,8 +360,7 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic)
 		rc = efx_init_rx_buffers(rx_queue, atomic);
 		if (unlikely(rc)) {
 			/* Ensure that we don't leave the rx queue empty */
-			if (rx_queue->added_count == rx_queue->removed_count)
-				efx_schedule_slow_fill(rx_queue);
+			efx_schedule_slow_fill(rx_queue);
 			goto out;
 		}
 	} while ((space -= batch_size) >= batch_size);
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index c3ad564ac4c0..06c8f282263f 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -471,7 +471,7 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue,
 	if (IS_ERR(segments))
 		return PTR_ERR(segments);
 
-	dev_kfree_skb_any(skb);
+	dev_consume_skb_any(skb);
 	skb = segments;
 
 	while (skb) {
@@ -553,13 +553,10 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	if (!data_mapped && (efx_tx_map_data(tx_queue, skb, segments)))
 		goto err;
 
-	/* Update BQL */
-	netdev_tx_sent_queue(tx_queue->core_txq, skb_len);
-
 	efx_tx_maybe_stop_queue(tx_queue);
 
 	/* Pass off to hardware */
-	if (!xmit_more || netif_xmit_stopped(tx_queue->core_txq)) {
+	if (__netdev_tx_sent_queue(tx_queue->core_txq, skb_len, xmit_more)) {
 		struct efx_tx_queue *txq2 = efx_tx_queue_partner(tx_queue);
 
 		/* There could be packets left on the partner queue if those
diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c
index 3140999642ba..358e66b81926 100644
--- a/drivers/net/ethernet/sgi/ioc3-eth.c
+++ b/drivers/net/ethernet/sgi/ioc3-eth.c
@@ -666,7 +666,7 @@ static inline void ioc3_tx(struct net_device *dev)
 		packets++;
 		skb = ip->tx_skbs[o_entry];
 		bytes += skb->len;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		ip->tx_skbs[o_entry] = NULL;
 
 		o_entry = (o_entry + 1) & 127;		/* Next */
diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c
index 703fbbefea44..f1271402ca21 100644
--- a/drivers/net/ethernet/sgi/meth.c
+++ b/drivers/net/ethernet/sgi/meth.c
@@ -68,6 +68,8 @@ module_param(timeout, int, 0);
  * packets in and out, so there is place for a packet
  */
 struct meth_private {
+	struct platform_device *pdev;
+
 	/* in-memory copy of MAC Control register */
 	u64 mac_ctrl;
 
@@ -211,8 +213,8 @@ static void meth_check_link(struct net_device *dev)
 static int meth_init_tx_ring(struct meth_private *priv)
 {
 	/* Init TX ring */
-	priv->tx_ring = dma_zalloc_coherent(NULL, TX_RING_BUFFER_SIZE,
-					    &priv->tx_ring_dma, GFP_ATOMIC);
+	priv->tx_ring = dma_alloc_coherent(&priv->pdev->dev,
+			TX_RING_BUFFER_SIZE, &priv->tx_ring_dma, GFP_ATOMIC);
 	if (!priv->tx_ring)
 		return -ENOMEM;
 
@@ -236,7 +238,7 @@ static int meth_init_rx_ring(struct meth_private *priv)
 		priv->rx_ring[i]=(rx_packet*)(priv->rx_skbs[i]->head);
 		/* I'll need to re-sync it after each RX */
 		priv->rx_ring_dmas[i] =
-			dma_map_single(NULL, priv->rx_ring[i],
+			dma_map_single(&priv->pdev->dev, priv->rx_ring[i],
 				       METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		mace->eth.rx_fifo = priv->rx_ring_dmas[i];
 	}
@@ -253,7 +255,7 @@ static void meth_free_tx_ring(struct meth_private *priv)
 			dev_kfree_skb(priv->tx_skbs[i]);
 		priv->tx_skbs[i] = NULL;
 	}
-	dma_free_coherent(NULL, TX_RING_BUFFER_SIZE, priv->tx_ring,
+	dma_free_coherent(&priv->pdev->dev, TX_RING_BUFFER_SIZE, priv->tx_ring,
 	                  priv->tx_ring_dma);
 }
 
@@ -263,7 +265,7 @@ static void meth_free_rx_ring(struct meth_private *priv)
 	int i;
 
 	for (i = 0; i < RX_RING_ENTRIES; i++) {
-		dma_unmap_single(NULL, priv->rx_ring_dmas[i],
+		dma_unmap_single(&priv->pdev->dev, priv->rx_ring_dmas[i],
 				 METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		priv->rx_ring[i] = 0;
 		priv->rx_ring_dmas[i] = 0;
@@ -393,7 +395,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status)
 		fifo_rptr = (fifo_rptr - 1) & 0x0f;
 	}
 	while (priv->rx_write != fifo_rptr) {
-		dma_unmap_single(NULL, priv->rx_ring_dmas[priv->rx_write],
+		dma_unmap_single(&priv->pdev->dev,
+				 priv->rx_ring_dmas[priv->rx_write],
 				 METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		status = priv->rx_ring[priv->rx_write]->status.raw;
 #if MFE_DEBUG
@@ -454,7 +457,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status)
 		priv->rx_ring[priv->rx_write] = (rx_packet*)skb->head;
 		priv->rx_ring[priv->rx_write]->status.raw = 0;
 		priv->rx_ring_dmas[priv->rx_write] =
-			dma_map_single(NULL, priv->rx_ring[priv->rx_write],
+			dma_map_single(&priv->pdev->dev,
+				       priv->rx_ring[priv->rx_write],
 				       METH_RX_BUFF_SIZE, DMA_FROM_DEVICE);
 		mace->eth.rx_fifo = priv->rx_ring_dmas[priv->rx_write];
 		ADVANCE_RX_PTR(priv->rx_write);
@@ -521,7 +525,7 @@ static void meth_tx_cleanup(struct net_device* dev, unsigned long int_status)
 			DPRINTK("RPTR points us here, but packet not done?\n");
 			break;
 		}
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		priv->tx_skbs[priv->tx_read] = NULL;
 		priv->tx_ring[priv->tx_read].header.raw = 0;
 		priv->tx_read = (priv->tx_read+1)&(TX_RING_ENTRIES-1);
@@ -637,7 +641,7 @@ static void meth_tx_1page_prepare(struct meth_private *priv,
 	}
 
 	/* first page */
-	catbuf = dma_map_single(NULL, buffer_data, buffer_len,
+	catbuf = dma_map_single(&priv->pdev->dev, buffer_data, buffer_len,
 				DMA_TO_DEVICE);
 	desc->data.cat_buf[0].form.start_addr = catbuf >> 3;
 	desc->data.cat_buf[0].form.len = buffer_len - 1;
@@ -663,12 +667,12 @@ static void meth_tx_2page_prepare(struct meth_private *priv,
 	}
 
 	/* first page */
-	catbuf1 = dma_map_single(NULL, buffer1_data, buffer1_len,
+	catbuf1 = dma_map_single(&priv->pdev->dev, buffer1_data, buffer1_len,
 				 DMA_TO_DEVICE);
 	desc->data.cat_buf[0].form.start_addr = catbuf1 >> 3;
 	desc->data.cat_buf[0].form.len = buffer1_len - 1;
 	/* second page */
-	catbuf2 = dma_map_single(NULL, buffer2_data, buffer2_len,
+	catbuf2 = dma_map_single(&priv->pdev->dev, buffer2_data, buffer2_len,
 				 DMA_TO_DEVICE);
 	desc->data.cat_buf[1].form.start_addr = catbuf2 >> 3;
 	desc->data.cat_buf[1].form.len = buffer2_len - 1;
@@ -840,6 +844,7 @@ static int meth_probe(struct platform_device *pdev)
 	memcpy(dev->dev_addr, o2meth_eaddr, ETH_ALEN);
 
 	priv = netdev_priv(dev);
+	priv->pdev = pdev;
 	spin_lock_init(&priv->meth_lock);
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index c2c50522b96d..5b351beb78cb 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -714,7 +714,7 @@ static void sis190_tx_interrupt(struct net_device *dev,
 
 		sis190_unmap_tx_skb(tp->pci_dev, skb, txd);
 		tp->Tx_skbuff[entry] = NULL;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 
 	if (tp->dirty_tx != dirty_tx) {
@@ -1142,7 +1142,7 @@ static void sis190_down(struct net_device *dev)
 		if (!poll_locked)
 			poll_locked++;
 
-		synchronize_sched();
+		synchronize_rcu();
 
 	} while (SIS_R32(IntrMask));
 
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index 4bb89f74742c..67f9bb6e941b 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -730,10 +730,10 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 		status = mdio_read(net_dev, phy->phy_addr, MII_STATUS);
 
 		/* Link ON & Not select default PHY & not ghost PHY */
-		 if ((status & MII_STAT_LINK) && !default_phy &&
-					(phy->phy_types != UNKNOWN))
-		 	default_phy = phy;
-		 else {
+		if ((status & MII_STAT_LINK) && !default_phy &&
+		    (phy->phy_types != UNKNOWN)) {
+			default_phy = phy;
+		} else {
 			status = mdio_read(net_dev, phy->phy_addr, MII_CONTROL);
 			mdio_write(net_dev, phy->phy_addr, MII_CONTROL,
 				status | MII_CNTL_AUTO | MII_CNTL_ISOLATE);
@@ -741,7 +741,7 @@ static u16 sis900_default_phy(struct net_device * net_dev)
 				phy_home = phy;
 			else if(phy->phy_types == LAN)
 				phy_lan = phy;
-		 }
+		}
 	}
 
 	if (!default_phy && phy_home)
@@ -1927,7 +1927,7 @@ static void sis900_finish_xmit (struct net_device *net_dev)
 		pci_unmap_single(sis_priv->pci_dev,
 			sis_priv->tx_ring[entry].bufptr, skb->len,
 			PCI_DMA_TODEVICE);
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		sis_priv->tx_skbuff[entry] = NULL;
 		sis_priv->tx_ring[entry].bufptr = 0;
 		sis_priv->tx_ring[entry].cmdsts = 0;
diff --git a/drivers/net/ethernet/smsc/Kconfig b/drivers/net/ethernet/smsc/Kconfig
index 358820282ef0..79612060d0ba 100644
--- a/drivers/net/ethernet/smsc/Kconfig
+++ b/drivers/net/ethernet/smsc/Kconfig
@@ -27,7 +27,7 @@ config SMC9194
 	  option if you have a DELL laptop with the docking station, or
 	  another SMC9192/9194 based chipset.  Say Y if you want it compiled
 	  into the kernel, and read the file
-	  <file:Documentation/networking/smc9.txt>.
+	  <file:Documentation/networking/device_drivers/smsc/smc9.txt>.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called smc9194.
@@ -43,7 +43,7 @@ config SMC91X
 	  This is a driver for SMC's 91x series of Ethernet chipsets,
 	  including the SMC91C94 and the SMC91C111. Say Y if you want it
 	  compiled into the kernel, and read the file
-	  <file:Documentation/networking/smc9.txt>.
+	  <file:Documentation/networking/device_drivers/smsc/smc9.txt>.
 
 	  This driver is also available as a module ( = code which can be
 	  inserted in and removed from the running kernel whenever you want).
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 15c62c160953..be47d864f8b9 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1037,7 +1037,7 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep)
 		skb = ep->tx_skbuff[entry];
 		pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr,
 				 skb->len, PCI_DMA_TODEVICE);
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		ep->tx_skbuff[entry] = NULL;
 	}
 
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 8355dfbb8ec3..b550e624500d 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -1188,7 +1188,7 @@ smc911x_tx_dma_irq(void *data)
 
 	DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "TX DMA irq handler\n");
 	BUG_ON(skb == NULL);
-	dma_unmap_single(NULL, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE);
+	dma_unmap_single(lp->dev, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE);
 	netif_trans_update(dev);
 	dev_kfree_skb_irq(skb);
 	lp->current_tx_skb = NULL;
@@ -1219,7 +1219,7 @@ smc911x_rx_dma_irq(void *data)
 
 	DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__);
 	DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, "RX DMA irq handler\n");
-	dma_unmap_single(NULL, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE);
+	dma_unmap_single(lp->dev, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE);
 	BUG_ON(skb == NULL);
 	lp->current_rx_skb = NULL;
 	PRINT_PKT(skb->data, skb->len);
diff --git a/drivers/net/ethernet/smsc/smsc911x.h b/drivers/net/ethernet/smsc/smsc911x.h
index 8d75508acd2b..51b2fc1a395f 100644
--- a/drivers/net/ethernet/smsc/smsc911x.h
+++ b/drivers/net/ethernet/smsc/smsc911x.h
@@ -67,7 +67,7 @@
 
 #ifdef CONFIG_DEBUG_SPINLOCK
 #define SMSC_ASSERT_MAC_LOCK(pdata) \
-		WARN_ON_SMP(!spin_is_locked(&pdata->mac_lock))
+		lockdep_assert_held(&pdata->mac_lock)
 #else
 #define SMSC_ASSERT_MAC_LOCK(pdata) do {} while (0)
 #endif				/* CONFIG_DEBUG_SPINLOCK */
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index d9d0d03e4ce7..cba5881b2746 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -234,6 +234,9 @@
 
 #define DESC_NUM	256
 
+#define NETSEC_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN)
+#define NETSEC_RX_BUF_SZ 1536
+
 #define DESC_SZ	sizeof(struct netsec_de)
 
 #define NETSEC_F_NETSEC_VER_MAJOR_NUM(x)	((x) & 0xffff0000)
@@ -254,7 +257,6 @@ struct netsec_desc_ring {
 	dma_addr_t desc_dma;
 	struct netsec_desc *desc;
 	void *vaddr;
-	u16 pkt_cnt;
 	u16 head, tail;
 };
 
@@ -571,34 +573,10 @@ static const struct ethtool_ops netsec_ethtool_ops = {
 
 /************* NETDEV_OPS FOLLOW *************/
 
-static struct sk_buff *netsec_alloc_skb(struct netsec_priv *priv,
-					struct netsec_desc *desc)
-{
-	struct sk_buff *skb;
-
-	if (device_get_dma_attr(priv->dev) == DEV_DMA_COHERENT) {
-		skb = netdev_alloc_skb_ip_align(priv->ndev, desc->len);
-	} else {
-		desc->len = L1_CACHE_ALIGN(desc->len);
-		skb = netdev_alloc_skb(priv->ndev, desc->len);
-	}
-	if (!skb)
-		return NULL;
-
-	desc->addr = skb->data;
-	desc->dma_addr = dma_map_single(priv->dev, desc->addr, desc->len,
-					DMA_FROM_DEVICE);
-	if (dma_mapping_error(priv->dev, desc->dma_addr)) {
-		dev_kfree_skb_any(skb);
-		return NULL;
-	}
-	return skb;
-}
 
 static void netsec_set_rx_de(struct netsec_priv *priv,
 			     struct netsec_desc_ring *dring, u16 idx,
-			     const struct netsec_desc *desc,
-			     struct sk_buff *skb)
+			     const struct netsec_desc *desc)
 {
 	struct netsec_de *de = dring->vaddr + DESC_SZ * idx;
 	u32 attr = (1 << NETSEC_RX_PKT_OWN_FIELD) |
@@ -617,88 +595,28 @@ static void netsec_set_rx_de(struct netsec_priv *priv,
 	dring->desc[idx].dma_addr = desc->dma_addr;
 	dring->desc[idx].addr = desc->addr;
 	dring->desc[idx].len = desc->len;
-	dring->desc[idx].skb = skb;
-}
-
-static struct sk_buff *netsec_get_rx_de(struct netsec_priv *priv,
-					struct netsec_desc_ring *dring,
-					u16 idx,
-					struct netsec_rx_pkt_info *rxpi,
-					struct netsec_desc *desc, u16 *len)
-{
-	struct netsec_de de = {};
-
-	memcpy(&de, dring->vaddr + DESC_SZ * idx, DESC_SZ);
-
-	*len = de.buf_len_info >> 16;
-
-	rxpi->err_flag = (de.attr >> NETSEC_RX_PKT_ER_FIELD) & 1;
-	rxpi->rx_cksum_result = (de.attr >> NETSEC_RX_PKT_CO_FIELD) & 3;
-	rxpi->err_code = (de.attr >> NETSEC_RX_PKT_ERR_FIELD) &
-							NETSEC_RX_PKT_ERR_MASK;
-	*desc = dring->desc[idx];
-	return desc->skb;
-}
-
-static struct sk_buff *netsec_get_rx_pkt_data(struct netsec_priv *priv,
-					      struct netsec_rx_pkt_info *rxpi,
-					      struct netsec_desc *desc,
-					      u16 *len)
-{
-	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	struct sk_buff *tmp_skb, *skb = NULL;
-	struct netsec_desc td;
-	int tail;
-
-	*rxpi = (struct netsec_rx_pkt_info){};
-
-	td.len = priv->ndev->mtu + 22;
-
-	tmp_skb = netsec_alloc_skb(priv, &td);
-
-	tail = dring->tail;
-
-	if (!tmp_skb) {
-		netsec_set_rx_de(priv, dring, tail, &dring->desc[tail],
-				 dring->desc[tail].skb);
-	} else {
-		skb = netsec_get_rx_de(priv, dring, tail, rxpi, desc, len);
-		netsec_set_rx_de(priv, dring, tail, &td, tmp_skb);
-	}
-
-	/* move tail ahead */
-	dring->tail = (dring->tail + 1) % DESC_NUM;
-
-	return skb;
 }
 
-static int netsec_clean_tx_dring(struct netsec_priv *priv, int budget)
+static bool netsec_clean_tx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
 	unsigned int pkts, bytes;
-
-	dring->pkt_cnt += netsec_read(priv, NETSEC_REG_NRM_TX_DONE_PKTCNT);
-
-	if (dring->pkt_cnt < budget)
-		budget = dring->pkt_cnt;
+	struct netsec_de *entry;
+	int tail = dring->tail;
+	int cnt = 0;
 
 	pkts = 0;
 	bytes = 0;
+	entry = dring->vaddr + DESC_SZ * tail;
 
-	while (pkts < budget) {
+	while (!(entry->attr & (1U << NETSEC_TX_SHIFT_OWN_FIELD)) &&
+	       cnt < DESC_NUM) {
 		struct netsec_desc *desc;
-		struct netsec_de *entry;
-		int tail, eop;
-
-		tail = dring->tail;
-
-		/* move tail ahead */
-		dring->tail = (tail + 1) % DESC_NUM;
+		int eop;
 
 		desc = &dring->desc[tail];
-		entry = dring->vaddr + DESC_SZ * tail;
-
 		eop = (entry->attr >> NETSEC_TX_LAST) & 1;
+		dma_rmb();
 
 		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
 				 DMA_TO_DEVICE);
@@ -707,33 +625,95 @@ static int netsec_clean_tx_dring(struct netsec_priv *priv, int budget)
 			bytes += desc->skb->len;
 			dev_kfree_skb(desc->skb);
 		}
+		/* clean up so netsec_uninit_pkt_dring() won't free the skb
+		 * again
+		 */
 		*desc = (struct netsec_desc){};
+
+		/* entry->attr is not going to be accessed by the NIC until
+		 * netsec_set_tx_de() is called. No need for a dma_wmb() here
+		 */
+		entry->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
+		/* move tail ahead */
+		dring->tail = (tail + 1) % DESC_NUM;
+
+		tail = dring->tail;
+		entry = dring->vaddr + DESC_SZ * tail;
+		cnt++;
 	}
-	dring->pkt_cnt -= budget;
 
-	priv->ndev->stats.tx_packets += budget;
+	if (!cnt)
+		return false;
+
+	/* reading the register clears the irq */
+	netsec_read(priv, NETSEC_REG_NRM_TX_DONE_PKTCNT);
+
+	priv->ndev->stats.tx_packets += cnt;
 	priv->ndev->stats.tx_bytes += bytes;
 
-	netdev_completed_queue(priv->ndev, budget, bytes);
+	netdev_completed_queue(priv->ndev, cnt, bytes);
 
-	return budget;
+	return true;
 }
 
-static int netsec_process_tx(struct netsec_priv *priv, int budget)
+static void netsec_process_tx(struct netsec_priv *priv)
 {
 	struct net_device *ndev = priv->ndev;
-	int new, done = 0;
+	bool cleaned;
 
-	do {
-		new = netsec_clean_tx_dring(priv, budget);
-		done += new;
-		budget -= new;
-	} while (new);
+	cleaned = netsec_clean_tx_dring(priv);
 
-	if (done && netif_queue_stopped(ndev))
+	if (cleaned && netif_queue_stopped(ndev)) {
+		/* Make sure we update the value, anyone stopping the queue
+		 * after this will read the proper consumer idx
+		 */
+		smp_wmb();
 		netif_wake_queue(ndev);
+	}
+}
 
-	return done;
+static void *netsec_alloc_rx_data(struct netsec_priv *priv,
+				  dma_addr_t *dma_handle, u16 *desc_len,
+				  bool napi)
+{
+	size_t total_len = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	size_t payload_len = NETSEC_RX_BUF_SZ;
+	dma_addr_t mapping;
+	void *buf;
+
+	total_len += SKB_DATA_ALIGN(payload_len + NETSEC_SKB_PAD);
+
+	buf = napi ? napi_alloc_frag(total_len) : netdev_alloc_frag(total_len);
+	if (!buf)
+		return NULL;
+
+	mapping = dma_map_single(priv->dev, buf + NETSEC_SKB_PAD, payload_len,
+				 DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(priv->dev, mapping)))
+		goto err_out;
+
+	*dma_handle = mapping;
+	*desc_len = payload_len;
+
+	return buf;
+
+err_out:
+	skb_free_frag(buf);
+	return NULL;
+}
+
+static void netsec_rx_fill(struct netsec_priv *priv, u16 from, u16 num)
+{
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
+	u16 idx = from;
+
+	while (num) {
+		netsec_set_rx_de(priv, dring, idx, &dring->desc[idx]);
+		idx++;
+		if (idx >= DESC_NUM)
+			idx = 0;
+		num--;
+	}
 }
 
 static int netsec_process_rx(struct netsec_priv *priv, int budget)
@@ -741,14 +721,17 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
 	struct net_device *ndev = priv->ndev;
 	struct netsec_rx_pkt_info rx_info;
-	int done = 0;
-	struct netsec_desc desc;
 	struct sk_buff *skb;
-	u16 len;
+	int done = 0;
 
 	while (done < budget) {
 		u16 idx = dring->tail;
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
+		struct netsec_desc *desc = &dring->desc[idx];
+		u16 pkt_len, desc_len;
+		dma_addr_t dma_handle;
+		void *buf_addr;
+		u32 truesize;
 
 		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD)) {
 			/* reading the register clears the irq */
@@ -762,18 +745,60 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		 */
 		dma_rmb();
 		done++;
-		skb = netsec_get_rx_pkt_data(priv, &rx_info, &desc, &len);
-		if (unlikely(!skb) || rx_info.err_flag) {
+
+		pkt_len = de->buf_len_info >> 16;
+		rx_info.err_code = (de->attr >> NETSEC_RX_PKT_ERR_FIELD) &
+			NETSEC_RX_PKT_ERR_MASK;
+		rx_info.err_flag = (de->attr >> NETSEC_RX_PKT_ER_FIELD) & 1;
+		if (rx_info.err_flag) {
 			netif_err(priv, drv, priv->ndev,
-				  "%s: rx fail err(%d)\n",
-				  __func__, rx_info.err_code);
+				  "%s: rx fail err(%d)\n", __func__,
+				  rx_info.err_code);
 			ndev->stats.rx_dropped++;
+			dring->tail = (dring->tail + 1) % DESC_NUM;
+			/* reuse buffer page frag */
+			netsec_rx_fill(priv, idx, 1);
 			continue;
 		}
+		rx_info.rx_cksum_result =
+			(de->attr >> NETSEC_RX_PKT_CO_FIELD) & 3;
 
-		dma_unmap_single(priv->dev, desc.dma_addr, desc.len,
-				 DMA_FROM_DEVICE);
-		skb_put(skb, len);
+		/* allocate a fresh buffer and map it to the hardware.
+		 * This will eventually replace the old buffer in the hardware
+		 */
+		buf_addr = netsec_alloc_rx_data(priv, &dma_handle, &desc_len,
+						true);
+		if (unlikely(!buf_addr))
+			break;
+
+		dma_sync_single_for_cpu(priv->dev, desc->dma_addr, pkt_len,
+					DMA_FROM_DEVICE);
+		prefetch(desc->addr);
+
+		truesize = SKB_DATA_ALIGN(desc->len + NETSEC_SKB_PAD) +
+			SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		skb = build_skb(desc->addr, truesize);
+		if (unlikely(!skb)) {
+			/* free the newly allocated buffer, we are not going to
+			 * use it
+			 */
+			dma_unmap_single(priv->dev, dma_handle, desc_len,
+					 DMA_FROM_DEVICE);
+			skb_free_frag(buf_addr);
+			netif_err(priv, drv, priv->ndev,
+				  "rx failed to build skb\n");
+			break;
+		}
+		dma_unmap_single_attrs(priv->dev, desc->dma_addr, desc->len,
+				       DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+
+		/* Update the descriptor with the new buffer we allocated */
+		desc->len = desc_len;
+		desc->dma_addr = dma_handle;
+		desc->addr = buf_addr;
+
+		skb_reserve(skb, NETSEC_SKB_PAD);
+		skb_put(skb, pkt_len);
 		skb->protocol = eth_type_trans(skb, priv->ndev);
 
 		if (priv->rx_cksum_offload_flag &&
@@ -782,8 +807,11 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 
 		if (napi_gro_receive(&priv->napi, skb) != GRO_DROP) {
 			ndev->stats.rx_packets++;
-			ndev->stats.rx_bytes += len;
+			ndev->stats.rx_bytes += pkt_len;
 		}
+
+		netsec_rx_fill(priv, idx, 1);
+		dring->tail = (dring->tail + 1) % DESC_NUM;
 	}
 
 	return done;
@@ -792,24 +820,17 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 static int netsec_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct netsec_priv *priv;
-	int tx, rx, done, todo;
+	int rx, done, todo;
 
 	priv = container_of(napi, struct netsec_priv, napi);
 
+	netsec_process_tx(priv);
+
 	todo = budget;
 	do {
-		if (!todo)
-			break;
-
-		tx = netsec_process_tx(priv, todo);
-		todo -= tx;
-
-		if (!todo)
-			break;
-
 		rx = netsec_process_rx(priv, todo);
 		todo -= rx;
-	} while (rx || tx);
+	} while (rx);
 
 	done = budget - todo;
 
@@ -861,6 +882,41 @@ static void netsec_set_tx_de(struct netsec_priv *priv,
 	dring->head = (dring->head + 1) % DESC_NUM;
 }
 
+static int netsec_desc_used(struct netsec_desc_ring *dring)
+{
+	int used;
+
+	if (dring->head >= dring->tail)
+		used = dring->head - dring->tail;
+	else
+		used = dring->head + DESC_NUM - dring->tail;
+
+	return used;
+}
+
+static int netsec_check_stop_tx(struct netsec_priv *priv, int used)
+{
+	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_TX];
+
+	/* keep tail from touching the queue */
+	if (DESC_NUM - used < 2) {
+		netif_stop_queue(priv->ndev);
+
+		/* Make sure we read the updated value in case
+		 * descriptors got freed
+		 */
+		smp_rmb();
+
+		used = netsec_desc_used(dring);
+		if (DESC_NUM - used < 2)
+			return NETDEV_TX_BUSY;
+
+		netif_wake_queue(priv->ndev);
+	}
+
+	return 0;
+}
+
 static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 					    struct net_device *ndev)
 {
@@ -871,16 +927,10 @@ static netdev_tx_t netsec_netdev_start_xmit(struct sk_buff *skb,
 	u16 tso_seg_len = 0;
 	int filled;
 
-	/* differentiate between full/emtpy ring */
-	if (dring->head >= dring->tail)
-		filled = dring->head - dring->tail;
-	else
-		filled = dring->head + DESC_NUM - dring->tail;
-
-	if (DESC_NUM - filled < 2) { /* if less than 2 available */
-		netif_err(priv, drv, priv->ndev, "%s: TxQFull!\n", __func__);
-		netif_stop_queue(priv->ndev);
-		dma_wmb();
+	filled = netsec_desc_used(dring);
+	if (netsec_check_stop_tx(priv, filled)) {
+		net_warn_ratelimited("%s %s Tx queue full\n",
+				     dev_name(priv->dev), ndev->name);
 		return NETDEV_TX_BUSY;
 	}
 
@@ -946,7 +996,10 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 		dma_unmap_single(priv->dev, desc->dma_addr, desc->len,
 				 id == NETSEC_RING_RX ? DMA_FROM_DEVICE :
 							      DMA_TO_DEVICE);
-		dev_kfree_skb(desc->skb);
+		if (id == NETSEC_RING_RX)
+			skb_free_frag(desc->addr);
+		else if (id == NETSEC_RING_TX)
+			dev_kfree_skb(desc->skb);
 	}
 
 	memset(dring->desc, 0, sizeof(struct netsec_desc) * DESC_NUM);
@@ -954,7 +1007,6 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
 
 	dring->head = 0;
 	dring->tail = 0;
-	dring->pkt_cnt = 0;
 
 	if (id == NETSEC_RING_TX)
 		netdev_reset_queue(priv->ndev);
@@ -977,47 +1029,65 @@ static void netsec_free_dring(struct netsec_priv *priv, int id)
 static int netsec_alloc_dring(struct netsec_priv *priv, enum ring_id id)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[id];
-	int ret = 0;
+	int i;
 
-	dring->vaddr = dma_zalloc_coherent(priv->dev, DESC_SZ * DESC_NUM,
-					   &dring->desc_dma, GFP_KERNEL);
-	if (!dring->vaddr) {
-		ret = -ENOMEM;
+	dring->vaddr = dma_alloc_coherent(priv->dev, DESC_SZ * DESC_NUM,
+					  &dring->desc_dma, GFP_KERNEL);
+	if (!dring->vaddr)
 		goto err;
-	}
 
 	dring->desc = kcalloc(DESC_NUM, sizeof(*dring->desc), GFP_KERNEL);
-	if (!dring->desc) {
-		ret = -ENOMEM;
+	if (!dring->desc)
 		goto err;
+
+	if (id == NETSEC_RING_TX) {
+		for (i = 0; i < DESC_NUM; i++) {
+			struct netsec_de *de;
+
+			de = dring->vaddr + (DESC_SZ * i);
+			/* de->attr is not going to be accessed by the NIC
+			 * until netsec_set_tx_de() is called.
+			 * No need for a dma_wmb() here
+			 */
+			de->attr = 1U << NETSEC_TX_SHIFT_OWN_FIELD;
+		}
 	}
 
 	return 0;
 err:
 	netsec_free_dring(priv, id);
 
-	return ret;
+	return -ENOMEM;
 }
 
 static int netsec_setup_rx_dring(struct netsec_priv *priv)
 {
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
-	struct netsec_desc desc;
-	struct sk_buff *skb;
-	int n;
+	int i;
 
-	desc.len = priv->ndev->mtu + 22;
+	for (i = 0; i < DESC_NUM; i++) {
+		struct netsec_desc *desc = &dring->desc[i];
+		dma_addr_t dma_handle;
+		void *buf;
+		u16 len;
 
-	for (n = 0; n < DESC_NUM; n++) {
-		skb = netsec_alloc_skb(priv, &desc);
-		if (!skb) {
+		buf = netsec_alloc_rx_data(priv, &dma_handle, &len,
+					   false);
+		if (!buf) {
 			netsec_uninit_pkt_dring(priv, NETSEC_RING_RX);
-			return -ENOMEM;
+			goto err_out;
 		}
-		netsec_set_rx_de(priv, dring, n, &desc, skb);
+		desc->dma_addr = dma_handle;
+		desc->addr = buf;
+		desc->len = len;
 	}
 
+	netsec_rx_fill(priv, 0, DESC_NUM);
+
 	return 0;
+
+err_out:
+	return -ENOMEM;
 }
 
 static int netsec_netdev_load_ucode_region(struct netsec_priv *priv, u32 reg,
@@ -1377,6 +1447,8 @@ static int netsec_netdev_init(struct net_device *ndev)
 	int ret;
 	u16 data;
 
+	BUILD_BUG_ON_NOT_POWER_OF_2(DESC_NUM);
+
 	ret = netsec_alloc_dring(priv, NETSEC_RING_TX);
 	if (ret)
 		return ret;
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
index 7c7cd9d94bcc..bb6d5fb73035 100644
--- a/drivers/net/ethernet/socionext/sni_ave.c
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -262,6 +262,7 @@ struct ave_private {
 	struct regmap		*regmap;
 	unsigned int		pinmode_mask;
 	unsigned int		pinmode_val;
+	u32			wolopts;
 
 	/* stats */
 	struct ave_stats	stats_rx;
@@ -1119,7 +1120,7 @@ static void ave_phy_adjust_link(struct net_device *ndev)
 		if (phydev->asym_pause)
 			rmt_adv |= LPA_PAUSE_ASYM;
 
-		lcl_adv = ethtool_adv_to_lcl_adv_t(phydev->advertising);
+		lcl_adv = linkmode_adv_to_lcl_adv_t(phydev->advertising);
 		cap = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
 		if (cap & FLOW_CTRL_TX)
 			txcr |= AVE_TXCR_FLOCTR;
@@ -1210,9 +1211,13 @@ static int ave_init(struct net_device *ndev)
 
 	priv->phydev = phydev;
 
-	phy_ethtool_get_wol(phydev, &wol);
+	ave_ethtool_get_wol(ndev, &wol);
 	device_set_wakeup_capable(&ndev->dev, !!wol.supported);
 
+	/* set wol initial state disabled */
+	wol.wolopts = 0;
+	ave_ethtool_set_wol(ndev, &wol);
+
 	if (!phy_interface_is_rgmii(phydev))
 		phy_set_max_speed(phydev, SPEED_100);
 
@@ -1737,6 +1742,58 @@ static int ave_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int ave_suspend(struct device *dev)
+{
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct ave_private *priv = netdev_priv(ndev);
+	int ret = 0;
+
+	if (netif_running(ndev)) {
+		ret = ave_stop(ndev);
+		netif_device_detach(ndev);
+	}
+
+	ave_ethtool_get_wol(ndev, &wol);
+	priv->wolopts = wol.wolopts;
+
+	return ret;
+}
+
+static int ave_resume(struct device *dev)
+{
+	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct ave_private *priv = netdev_priv(ndev);
+	int ret = 0;
+
+	ave_global_reset(ndev);
+
+	ave_ethtool_get_wol(ndev, &wol);
+	wol.wolopts = priv->wolopts;
+	ave_ethtool_set_wol(ndev, &wol);
+
+	if (ndev->phydev) {
+		ret = phy_resume(ndev->phydev);
+		if (ret)
+			return ret;
+	}
+
+	if (netif_running(ndev)) {
+		ret = ave_open(ndev);
+		netif_device_attach(ndev);
+	}
+
+	return ret;
+}
+
+static SIMPLE_DEV_PM_OPS(ave_pm_ops, ave_suspend, ave_resume);
+#define AVE_PM_OPS	(&ave_pm_ops)
+#else
+#define AVE_PM_OPS	NULL
+#endif
+
 static int ave_pro4_get_pinmode(struct ave_private *priv,
 				phy_interface_t phy_mode, u32 arg)
 {
@@ -1911,6 +1968,7 @@ static struct platform_driver ave_driver = {
 	.remove = ave_remove,
 	.driver	= {
 		.name = "ave",
+		.pm   = AVE_PM_OPS,
 		.of_match_table	= of_ave_match,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 324049eebb9b..f194235153f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -75,6 +75,14 @@ config DWMAC_LPC18XX
 	---help---
 	  Support for NXP LPC18xx/43xx DWMAC Ethernet.
 
+config DWMAC_MEDIATEK
+	tristate "MediaTek MT27xx GMAC support"
+	depends on OF && (ARCH_MEDIATEK || COMPILE_TEST)
+	help
+	  Support for MediaTek GMAC Ethernet controller.
+
+	  This selects the MT2712 SoC support for the stmmac driver.
+
 config DWMAC_MESON
 	tristate "Amlogic Meson dwmac support"
 	default ARCH_MESON
@@ -97,6 +105,16 @@ config DWMAC_OXNAS
 	  This selects the Oxford Semiconductor OXNASSoC glue layer support for
 	  the stmmac device driver. This driver is used for OX820.
 
+config DWMAC_QCOM_ETHQOS
+	tristate "Qualcomm ETHQOS support"
+	default ARCH_QCOM
+	depends on OF && (ARCH_QCOM || COMPILE_TEST)
+	help
+	  Support for the Qualcomm ETHQOS core.
+
+	  This selects the Qualcomm ETHQOS glue layer support for the
+	  stmmac device driver.
+
 config DWMAC_ROCKCHIP
 	tristate "Rockchip dwmac support"
 	default ARCH_ROCKCHIP
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 99967a80a8c8..c529c21e9bdd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -13,8 +13,10 @@ obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
 obj-$(CONFIG_DWMAC_ANARION)	+= dwmac-anarion.o
 obj-$(CONFIG_DWMAC_IPQ806X)	+= dwmac-ipq806x.o
 obj-$(CONFIG_DWMAC_LPC18XX)	+= dwmac-lpc18xx.o
+obj-$(CONFIG_DWMAC_MEDIATEK)	+= dwmac-mediatek.o
 obj-$(CONFIG_DWMAC_MESON)	+= dwmac-meson.o dwmac-meson8b.o
 obj-$(CONFIG_DWMAC_OXNAS)	+= dwmac-oxnas.o
+obj-$(CONFIG_DWMAC_QCOM_ETHQOS)	+= dwmac-qcom-ethqos.o
 obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
 obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-altr-socfpga.o
 obj-$(CONFIG_DWMAC_STI)		+= dwmac-sti.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/descs_com.h b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
index 40d6356a7e73..3dfb07a78952 100644
--- a/drivers/net/ethernet/stmicro/stmmac/descs_com.h
+++ b/drivers/net/ethernet/stmicro/stmmac/descs_com.h
@@ -29,11 +29,13 @@
 /* Specific functions used for Ring mode */
 
 /* Enhanced descriptors */
-static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ehn_desc_rx_set_on_ring(struct dma_desc *p, int end,
+					   int bfsize)
 {
-	p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
-			<< ERDES1_BUFFER2_SIZE_SHIFT)
-		   & ERDES1_BUFFER2_SIZE_MASK);
+	if (bfsize == BUF_SIZE_16KiB)
+		p->des1 |= cpu_to_le32((BUF_SIZE_8KiB
+				<< ERDES1_BUFFER2_SIZE_SHIFT)
+			   & ERDES1_BUFFER2_SIZE_MASK);
 
 	if (end)
 		p->des1 |= cpu_to_le32(ERDES1_END_RING);
@@ -59,11 +61,15 @@ static inline void enh_set_tx_desc_len_on_ring(struct dma_desc *p, int len)
 }
 
 /* Normal descriptors */
-static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end)
+static inline void ndesc_rx_set_on_ring(struct dma_desc *p, int end, int bfsize)
 {
-	p->des1 |= cpu_to_le32(((BUF_SIZE_2KiB - 1)
-				<< RDES1_BUFFER2_SIZE_SHIFT)
-		    & RDES1_BUFFER2_SIZE_MASK);
+	if (bfsize >= BUF_SIZE_2KiB) {
+		int bfsize2;
+
+		bfsize2 = min(bfsize - BUF_SIZE_2KiB + 1, BUF_SIZE_2KiB - 1);
+		p->des1 |= cpu_to_le32((bfsize2 << RDES1_BUFFER2_SIZE_SHIFT)
+			    & RDES1_BUFFER2_SIZE_MASK);
+	}
 
 	if (end)
 		p->des1 |= cpu_to_le32(RDES1_END_RING);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
new file mode 100644
index 000000000000..bf2562995fc8
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -0,0 +1,390 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 MediaTek Inc.
+ */
+#include <linux/bitfield.h>
+#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_net.h>
+#include <linux/regmap.h>
+#include <linux/stmmac.h>
+
+#include "stmmac.h"
+#include "stmmac_platform.h"
+
+/* Peri Configuration register for mt2712 */
+#define PERI_ETH_PHY_INTF_SEL	0x418
+#define PHY_INTF_MII		0
+#define PHY_INTF_RGMII		1
+#define PHY_INTF_RMII		4
+#define RMII_CLK_SRC_RXC	BIT(4)
+#define RMII_CLK_SRC_INTERNAL	BIT(5)
+
+#define PERI_ETH_DLY	0x428
+#define ETH_DLY_GTXC_INV	BIT(6)
+#define ETH_DLY_GTXC_ENABLE	BIT(5)
+#define ETH_DLY_GTXC_STAGES	GENMASK(4, 0)
+#define ETH_DLY_TXC_INV		BIT(20)
+#define ETH_DLY_TXC_ENABLE	BIT(19)
+#define ETH_DLY_TXC_STAGES	GENMASK(18, 14)
+#define ETH_DLY_RXC_INV		BIT(13)
+#define ETH_DLY_RXC_ENABLE	BIT(12)
+#define ETH_DLY_RXC_STAGES	GENMASK(11, 7)
+
+#define PERI_ETH_DLY_FINE	0x800
+#define ETH_RMII_DLY_TX_INV	BIT(2)
+#define ETH_FINE_DLY_GTXC	BIT(1)
+#define ETH_FINE_DLY_RXC	BIT(0)
+
+struct mac_delay_struct {
+	u32 tx_delay;
+	u32 rx_delay;
+	bool tx_inv;
+	bool rx_inv;
+};
+
+struct mediatek_dwmac_plat_data {
+	const struct mediatek_dwmac_variant *variant;
+	struct mac_delay_struct mac_delay;
+	struct clk_bulk_data *clks;
+	struct device_node *np;
+	struct regmap *peri_regmap;
+	struct device *dev;
+	int phy_mode;
+	bool rmii_rxc;
+};
+
+struct mediatek_dwmac_variant {
+	int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat);
+	int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat);
+
+	/* clock ids to be requested */
+	const char * const *clk_list;
+	int num_clks;
+
+	u32 dma_bit_mask;
+	u32 rx_delay_max;
+	u32 tx_delay_max;
+};
+
+/* list of clocks required for mac */
+static const char * const mt2712_dwmac_clk_l[] = {
+	"axi", "apb", "mac_main", "ptp_ref"
+};
+
+static int mt2712_set_interface(struct mediatek_dwmac_plat_data *plat)
+{
+	int rmii_rxc = plat->rmii_rxc ? RMII_CLK_SRC_RXC : 0;
+	u32 intf_val = 0;
+
+	/* select phy interface in top control domain */
+	switch (plat->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+		intf_val |= PHY_INTF_MII;
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		intf_val |= (PHY_INTF_RMII | rmii_rxc);
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		intf_val |= PHY_INTF_RGMII;
+		break;
+	default:
+		dev_err(plat->dev, "phy interface not supported\n");
+		return -EINVAL;
+	}
+
+	regmap_write(plat->peri_regmap, PERI_ETH_PHY_INTF_SEL, intf_val);
+
+	return 0;
+}
+
+static void mt2712_delay_ps2stage(struct mediatek_dwmac_plat_data *plat)
+{
+	struct mac_delay_struct *mac_delay = &plat->mac_delay;
+
+	switch (plat->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_RMII:
+		/* 550ps per stage for MII/RMII */
+		mac_delay->tx_delay /= 550;
+		mac_delay->rx_delay /= 550;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		/* 170ps per stage for RGMII */
+		mac_delay->tx_delay /= 170;
+		mac_delay->rx_delay /= 170;
+		break;
+	default:
+		dev_err(plat->dev, "phy interface not supported\n");
+		break;
+	}
+}
+
+static int mt2712_set_delay(struct mediatek_dwmac_plat_data *plat)
+{
+	struct mac_delay_struct *mac_delay = &plat->mac_delay;
+	u32 delay_val = 0, fine_val = 0;
+
+	mt2712_delay_ps2stage(plat);
+
+	switch (plat->phy_mode) {
+	case PHY_INTERFACE_MODE_MII:
+		delay_val |= FIELD_PREP(ETH_DLY_TXC_ENABLE, !!mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_TXC_STAGES, mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_TXC_INV, mac_delay->tx_inv);
+
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		break;
+	case PHY_INTERFACE_MODE_RMII:
+		/* the rmii reference clock is from external phy,
+		 * and the property "rmii_rxc" indicates which pin(TXC/RXC)
+		 * the reference clk is connected to. The reference clock is a
+		 * received signal, so rx_delay/rx_inv are used to indicate
+		 * the reference clock timing adjustment
+		 */
+		if (plat->rmii_rxc) {
+			/* the rmii reference clock from outside is connected
+			 * to RXC pin, the reference clock will be adjusted
+			 * by RXC delay macro circuit.
+			 */
+			delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		} else {
+			/* the rmii reference clock from outside is connected
+			 * to TXC pin, the reference clock will be adjusted
+			 * by TXC delay macro circuit.
+			 */
+			delay_val |= FIELD_PREP(ETH_DLY_TXC_ENABLE, !!mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_TXC_STAGES, mac_delay->rx_delay);
+			delay_val |= FIELD_PREP(ETH_DLY_TXC_INV, mac_delay->rx_inv);
+		}
+		/* tx_inv will inverse the tx clock inside mac relateive to
+		 * reference clock from external phy,
+		 * and this bit is located in the same register with fine-tune
+		 */
+		if (mac_delay->tx_inv)
+			fine_val = ETH_RMII_DLY_TX_INV;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		fine_val = ETH_FINE_DLY_GTXC | ETH_FINE_DLY_RXC;
+
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_ENABLE, !!mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_STAGES, mac_delay->tx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_GTXC_INV, mac_delay->tx_inv);
+
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_ENABLE, !!mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_STAGES, mac_delay->rx_delay);
+		delay_val |= FIELD_PREP(ETH_DLY_RXC_INV, mac_delay->rx_inv);
+		break;
+	default:
+		dev_err(plat->dev, "phy interface not supported\n");
+		return -EINVAL;
+	}
+	regmap_write(plat->peri_regmap, PERI_ETH_DLY, delay_val);
+	regmap_write(plat->peri_regmap, PERI_ETH_DLY_FINE, fine_val);
+
+	return 0;
+}
+
+static const struct mediatek_dwmac_variant mt2712_gmac_variant = {
+		.dwmac_set_phy_interface = mt2712_set_interface,
+		.dwmac_set_delay = mt2712_set_delay,
+		.clk_list = mt2712_dwmac_clk_l,
+		.num_clks = ARRAY_SIZE(mt2712_dwmac_clk_l),
+		.dma_bit_mask = 33,
+		.rx_delay_max = 17600,
+		.tx_delay_max = 17600,
+};
+
+static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
+{
+	struct mac_delay_struct *mac_delay = &plat->mac_delay;
+	u32 tx_delay_ps, rx_delay_ps;
+
+	plat->peri_regmap = syscon_regmap_lookup_by_phandle(plat->np, "mediatek,pericfg");
+	if (IS_ERR(plat->peri_regmap)) {
+		dev_err(plat->dev, "Failed to get pericfg syscon\n");
+		return PTR_ERR(plat->peri_regmap);
+	}
+
+	plat->phy_mode = of_get_phy_mode(plat->np);
+	if (plat->phy_mode < 0) {
+		dev_err(plat->dev, "not find phy-mode\n");
+		return -EINVAL;
+	}
+
+	if (!of_property_read_u32(plat->np, "mediatek,tx-delay-ps", &tx_delay_ps)) {
+		if (tx_delay_ps < plat->variant->tx_delay_max) {
+			mac_delay->tx_delay = tx_delay_ps;
+		} else {
+			dev_err(plat->dev, "Invalid TX clock delay: %dps\n", tx_delay_ps);
+			return -EINVAL;
+		}
+	}
+
+	if (!of_property_read_u32(plat->np, "mediatek,rx-delay-ps", &rx_delay_ps)) {
+		if (rx_delay_ps < plat->variant->rx_delay_max) {
+			mac_delay->rx_delay = rx_delay_ps;
+		} else {
+			dev_err(plat->dev, "Invalid RX clock delay: %dps\n", rx_delay_ps);
+			return -EINVAL;
+		}
+	}
+
+	mac_delay->tx_inv = of_property_read_bool(plat->np, "mediatek,txc-inverse");
+	mac_delay->rx_inv = of_property_read_bool(plat->np, "mediatek,rxc-inverse");
+	plat->rmii_rxc = of_property_read_bool(plat->np, "mediatek,rmii-rxc");
+
+	return 0;
+}
+
+static int mediatek_dwmac_clk_init(struct mediatek_dwmac_plat_data *plat)
+{
+	const struct mediatek_dwmac_variant *variant = plat->variant;
+	int i, num = variant->num_clks;
+
+	plat->clks = devm_kcalloc(plat->dev, num, sizeof(*plat->clks), GFP_KERNEL);
+	if (!plat->clks)
+		return -ENOMEM;
+
+	for (i = 0; i < num; i++)
+		plat->clks[i].id = variant->clk_list[i];
+
+	return devm_clk_bulk_get(plat->dev, num, plat->clks);
+}
+
+static int mediatek_dwmac_init(struct platform_device *pdev, void *priv)
+{
+	struct mediatek_dwmac_plat_data *plat = priv;
+	const struct mediatek_dwmac_variant *variant = plat->variant;
+	int ret;
+
+	ret = dma_set_mask_and_coherent(plat->dev, DMA_BIT_MASK(variant->dma_bit_mask));
+	if (ret) {
+		dev_err(plat->dev, "No suitable DMA available, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = variant->dwmac_set_phy_interface(plat);
+	if (ret) {
+		dev_err(plat->dev, "failed to set phy interface, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = variant->dwmac_set_delay(plat);
+	if (ret) {
+		dev_err(plat->dev, "failed to set delay value, err = %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_bulk_prepare_enable(variant->num_clks, plat->clks);
+	if (ret) {
+		dev_err(plat->dev, "failed to enable clks, err = %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mediatek_dwmac_exit(struct platform_device *pdev, void *priv)
+{
+	struct mediatek_dwmac_plat_data *plat = priv;
+	const struct mediatek_dwmac_variant *variant = plat->variant;
+
+	clk_bulk_disable_unprepare(variant->num_clks, plat->clks);
+}
+
+static int mediatek_dwmac_probe(struct platform_device *pdev)
+{
+	struct mediatek_dwmac_plat_data *priv_plat;
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	int ret;
+
+	priv_plat = devm_kzalloc(&pdev->dev, sizeof(*priv_plat), GFP_KERNEL);
+	if (!priv_plat)
+		return -ENOMEM;
+
+	priv_plat->variant = of_device_get_match_data(&pdev->dev);
+	if (!priv_plat->variant) {
+		dev_err(&pdev->dev, "Missing dwmac-mediatek variant\n");
+		return -EINVAL;
+	}
+
+	priv_plat->dev = &pdev->dev;
+	priv_plat->np = pdev->dev.of_node;
+
+	ret = mediatek_dwmac_config_dt(priv_plat);
+	if (ret)
+		return ret;
+
+	ret = mediatek_dwmac_clk_init(priv_plat);
+	if (ret)
+		return ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return PTR_ERR(plat_dat);
+
+	plat_dat->interface = priv_plat->phy_mode;
+	/* clk_csr_i = 250-300MHz & MDC = clk_csr_i/124 */
+	plat_dat->clk_csr = 5;
+	plat_dat->has_gmac4 = 1;
+	plat_dat->has_gmac = 0;
+	plat_dat->pmt = 0;
+	plat_dat->maxmtu = ETH_DATA_LEN;
+	plat_dat->bsp_priv = priv_plat;
+	plat_dat->init = mediatek_dwmac_init;
+	plat_dat->exit = mediatek_dwmac_exit;
+	mediatek_dwmac_init(pdev, priv_plat);
+
+	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	if (ret) {
+		stmmac_remove_config_dt(pdev, plat_dat);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id mediatek_dwmac_match[] = {
+	{ .compatible = "mediatek,mt2712-gmac",
+	  .data = &mt2712_gmac_variant },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, mediatek_dwmac_match);
+
+static struct platform_driver mediatek_dwmac_driver = {
+	.probe  = mediatek_dwmac_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name           = "dwmac-mediatek",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = mediatek_dwmac_match,
+	},
+};
+module_platform_driver(mediatek_dwmac_driver);
+
+MODULE_AUTHOR("Biao Huang <biao.huang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek DWMAC specific glue layer");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
new file mode 100644
index 000000000000..7ec895407d23
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -0,0 +1,545 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018-19, Linaro Limited
+
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include "stmmac.h"
+#include "stmmac_platform.h"
+
+#define RGMII_IO_MACRO_CONFIG		0x0
+#define SDCC_HC_REG_DLL_CONFIG		0x4
+#define SDCC_HC_REG_DDR_CONFIG		0xC
+#define SDCC_HC_REG_DLL_CONFIG2		0x10
+#define SDC4_STATUS			0x14
+#define SDCC_USR_CTL			0x18
+#define RGMII_IO_MACRO_CONFIG2		0x1C
+#define RGMII_IO_MACRO_DEBUG1		0x20
+#define EMAC_SYSTEM_LOW_POWER_DEBUG	0x28
+
+/* RGMII_IO_MACRO_CONFIG fields */
+#define RGMII_CONFIG_FUNC_CLK_EN		BIT(30)
+#define RGMII_CONFIG_POS_NEG_DATA_SEL		BIT(23)
+#define RGMII_CONFIG_GPIO_CFG_RX_INT		GENMASK(21, 20)
+#define RGMII_CONFIG_GPIO_CFG_TX_INT		GENMASK(19, 17)
+#define RGMII_CONFIG_MAX_SPD_PRG_9		GENMASK(16, 8)
+#define RGMII_CONFIG_MAX_SPD_PRG_2		GENMASK(7, 6)
+#define RGMII_CONFIG_INTF_SEL			GENMASK(5, 4)
+#define RGMII_CONFIG_BYPASS_TX_ID_EN		BIT(3)
+#define RGMII_CONFIG_LOOPBACK_EN		BIT(2)
+#define RGMII_CONFIG_PROG_SWAP			BIT(1)
+#define RGMII_CONFIG_DDR_MODE			BIT(0)
+
+/* SDCC_HC_REG_DLL_CONFIG fields */
+#define SDCC_DLL_CONFIG_DLL_RST			BIT(30)
+#define SDCC_DLL_CONFIG_PDN			BIT(29)
+#define SDCC_DLL_CONFIG_MCLK_FREQ		GENMASK(26, 24)
+#define SDCC_DLL_CONFIG_CDR_SELEXT		GENMASK(23, 20)
+#define SDCC_DLL_CONFIG_CDR_EXT_EN		BIT(19)
+#define SDCC_DLL_CONFIG_CK_OUT_EN		BIT(18)
+#define SDCC_DLL_CONFIG_CDR_EN			BIT(17)
+#define SDCC_DLL_CONFIG_DLL_EN			BIT(16)
+#define SDCC_DLL_MCLK_GATING_EN			BIT(5)
+#define SDCC_DLL_CDR_FINE_PHASE			GENMASK(3, 2)
+
+/* SDCC_HC_REG_DDR_CONFIG fields */
+#define SDCC_DDR_CONFIG_PRG_DLY_EN		BIT(31)
+#define SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY	GENMASK(26, 21)
+#define SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE	GENMASK(29, 27)
+#define SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN	BIT(30)
+#define SDCC_DDR_CONFIG_PRG_RCLK_DLY		GENMASK(8, 0)
+
+/* SDCC_HC_REG_DLL_CONFIG2 fields */
+#define SDCC_DLL_CONFIG2_DLL_CLOCK_DIS		BIT(21)
+#define SDCC_DLL_CONFIG2_MCLK_FREQ_CALC		GENMASK(17, 10)
+#define SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SEL	GENMASK(3, 2)
+#define SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW	BIT(1)
+#define SDCC_DLL_CONFIG2_DDR_CAL_EN		BIT(0)
+
+/* SDC4_STATUS bits */
+#define SDC4_STATUS_DLL_LOCK			BIT(7)
+
+/* RGMII_IO_MACRO_CONFIG2 fields */
+#define RGMII_CONFIG2_RSVD_CONFIG15		GENMASK(31, 17)
+#define RGMII_CONFIG2_RGMII_CLK_SEL_CFG		BIT(16)
+#define RGMII_CONFIG2_TX_TO_RX_LOOPBACK_EN	BIT(13)
+#define RGMII_CONFIG2_CLK_DIVIDE_SEL		BIT(12)
+#define RGMII_CONFIG2_RX_PROG_SWAP		BIT(7)
+#define RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL	BIT(6)
+#define RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN	BIT(5)
+
+struct ethqos_emac_por {
+	unsigned int offset;
+	unsigned int value;
+};
+
+struct qcom_ethqos {
+	struct platform_device *pdev;
+	void __iomem *rgmii_base;
+
+	unsigned int rgmii_clk_rate;
+	struct clk *rgmii_clk;
+	unsigned int speed;
+
+	const struct ethqos_emac_por *por;
+	unsigned int num_por;
+};
+
+static int rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset)
+{
+	return readl(ethqos->rgmii_base + offset);
+}
+
+static void rgmii_writel(struct qcom_ethqos *ethqos,
+			 int value, unsigned int offset)
+{
+	writel(value, ethqos->rgmii_base + offset);
+}
+
+static void rgmii_updatel(struct qcom_ethqos *ethqos,
+			  int mask, int val, unsigned int offset)
+{
+	unsigned int temp;
+
+	temp =  rgmii_readl(ethqos, offset);
+	temp = (temp & ~(mask)) | val;
+	rgmii_writel(ethqos, temp, offset);
+}
+
+static void rgmii_dump(struct qcom_ethqos *ethqos)
+{
+	dev_dbg(&ethqos->pdev->dev, "Rgmii register dump\n");
+	dev_dbg(&ethqos->pdev->dev, "RGMII_IO_MACRO_CONFIG: %x\n",
+		rgmii_readl(ethqos, RGMII_IO_MACRO_CONFIG));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_HC_REG_DLL_CONFIG: %x\n",
+		rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_HC_REG_DDR_CONFIG: %x\n",
+		rgmii_readl(ethqos, SDCC_HC_REG_DDR_CONFIG));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_HC_REG_DLL_CONFIG2: %x\n",
+		rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG2));
+	dev_dbg(&ethqos->pdev->dev, "SDC4_STATUS: %x\n",
+		rgmii_readl(ethqos, SDC4_STATUS));
+	dev_dbg(&ethqos->pdev->dev, "SDCC_USR_CTL: %x\n",
+		rgmii_readl(ethqos, SDCC_USR_CTL));
+	dev_dbg(&ethqos->pdev->dev, "RGMII_IO_MACRO_CONFIG2: %x\n",
+		rgmii_readl(ethqos, RGMII_IO_MACRO_CONFIG2));
+	dev_dbg(&ethqos->pdev->dev, "RGMII_IO_MACRO_DEBUG1: %x\n",
+		rgmii_readl(ethqos, RGMII_IO_MACRO_DEBUG1));
+	dev_dbg(&ethqos->pdev->dev, "EMAC_SYSTEM_LOW_POWER_DEBUG: %x\n",
+		rgmii_readl(ethqos, EMAC_SYSTEM_LOW_POWER_DEBUG));
+}
+
+/* Clock rates */
+#define RGMII_1000_NOM_CLK_FREQ			(250 * 1000 * 1000UL)
+#define RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ	 (50 * 1000 * 1000UL)
+#define RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ	  (5 * 1000 * 1000UL)
+
+static void
+ethqos_update_rgmii_clk(struct qcom_ethqos *ethqos, unsigned int speed)
+{
+	switch (speed) {
+	case SPEED_1000:
+		ethqos->rgmii_clk_rate =  RGMII_1000_NOM_CLK_FREQ;
+		break;
+
+	case SPEED_100:
+		ethqos->rgmii_clk_rate =  RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ;
+		break;
+
+	case SPEED_10:
+		ethqos->rgmii_clk_rate =  RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ;
+		break;
+	}
+
+	clk_set_rate(ethqos->rgmii_clk, ethqos->rgmii_clk_rate);
+}
+
+static void ethqos_set_func_clk_en(struct qcom_ethqos *ethqos)
+{
+	rgmii_updatel(ethqos, RGMII_CONFIG_FUNC_CLK_EN,
+		      RGMII_CONFIG_FUNC_CLK_EN, RGMII_IO_MACRO_CONFIG);
+}
+
+static const struct ethqos_emac_por emac_v2_3_0_por[] = {
+	{ .offset = RGMII_IO_MACRO_CONFIG,	.value = 0x00C01343 },
+	{ .offset = SDCC_HC_REG_DLL_CONFIG,	.value = 0x2004642C },
+	{ .offset = SDCC_HC_REG_DDR_CONFIG,	.value = 0x00000000 },
+	{ .offset = SDCC_HC_REG_DLL_CONFIG2,	.value = 0x00200000 },
+	{ .offset = SDCC_USR_CTL,		.value = 0x00010800 },
+	{ .offset = RGMII_IO_MACRO_CONFIG2,	.value = 0x00002060 },
+};
+
+static int ethqos_dll_configure(struct qcom_ethqos *ethqos)
+{
+	unsigned int val;
+	int retry = 1000;
+
+	/* Set CDR_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CDR_EN,
+		      SDCC_DLL_CONFIG_CDR_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Set CDR_EXT_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CDR_EXT_EN,
+		      SDCC_DLL_CONFIG_CDR_EXT_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Clear CK_OUT_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN,
+		      0, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Set DLL_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN,
+		      SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	rgmii_updatel(ethqos, SDCC_DLL_MCLK_GATING_EN,
+		      0, SDCC_HC_REG_DLL_CONFIG);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CDR_FINE_PHASE,
+		      0, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Wait for CK_OUT_EN clear */
+	do {
+		val = rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG);
+		val &= SDCC_DLL_CONFIG_CK_OUT_EN;
+		if (!val)
+			break;
+		mdelay(1);
+		retry--;
+	} while (retry > 0);
+	if (!retry)
+		dev_err(&ethqos->pdev->dev, "Clear CK_OUT_EN timedout\n");
+
+	/* Set CK_OUT_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN,
+		      SDCC_DLL_CONFIG_CK_OUT_EN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Wait for CK_OUT_EN set */
+	retry = 1000;
+	do {
+		val = rgmii_readl(ethqos, SDCC_HC_REG_DLL_CONFIG);
+		val &= SDCC_DLL_CONFIG_CK_OUT_EN;
+		if (val)
+			break;
+		mdelay(1);
+		retry--;
+	} while (retry > 0);
+	if (!retry)
+		dev_err(&ethqos->pdev->dev, "Set CK_OUT_EN timedout\n");
+
+	/* Set DDR_CAL_EN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_CAL_EN,
+		      SDCC_DLL_CONFIG2_DDR_CAL_EN, SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DLL_CLOCK_DIS,
+		      0, SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_MCLK_FREQ_CALC,
+		      0x1A << 10, SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SEL,
+		      BIT(2), SDCC_HC_REG_DLL_CONFIG2);
+
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW,
+		      SDCC_DLL_CONFIG2_DDR_TRAFFIC_INIT_SW,
+		      SDCC_HC_REG_DLL_CONFIG2);
+
+	return 0;
+}
+
+static int ethqos_rgmii_macro_init(struct qcom_ethqos *ethqos)
+{
+	/* Disable loopback mode */
+	rgmii_updatel(ethqos, RGMII_CONFIG2_TX_TO_RX_LOOPBACK_EN,
+		      0, RGMII_IO_MACRO_CONFIG2);
+
+	/* Select RGMII, write 0 to interface select */
+	rgmii_updatel(ethqos, RGMII_CONFIG_INTF_SEL,
+		      0, RGMII_IO_MACRO_CONFIG);
+
+	switch (ethqos->speed) {
+	case SPEED_1000:
+		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
+			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP,
+			      RGMII_CONFIG_PROG_SWAP, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP,
+			      RGMII_CONFIG2_RX_PROG_SWAP,
+			      RGMII_IO_MACRO_CONFIG2);
+
+		/* Set PRG_RCLK_DLY to 57 for 1.8 ns delay */
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_RCLK_DLY,
+			      57, SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_PRG_DLY_EN,
+			      SDCC_DDR_CONFIG_PRG_DLY_EN,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN,
+			      RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG);
+		break;
+
+	case SPEED_100:
+		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
+			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG_MAX_SPD_PRG_2,
+			      BIT(6), RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		/* Write 0x5 to PRG_RCLK_DLY_CODE */
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE,
+			      (BIT(29) | BIT(27)), SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN,
+			      RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG);
+		break;
+
+	case SPEED_10:
+		rgmii_updatel(ethqos, RGMII_CONFIG_DDR_MODE,
+			      RGMII_CONFIG_DDR_MODE, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_CONFIG_BYPASS_TX_ID_EN,
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_POS_NEG_DATA_SEL,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG_MAX_SPD_PRG_9,
+			      BIT(12) | GENMASK(9, 8),
+			      RGMII_IO_MACRO_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RSVD_CONFIG15,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		rgmii_updatel(ethqos, RGMII_CONFIG2_RX_PROG_SWAP,
+			      0, RGMII_IO_MACRO_CONFIG2);
+		/* Write 0x5 to PRG_RCLK_DLY_CODE */
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_CODE,
+			      (BIT(29) | BIT(27)), SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_DDR_CONFIG_EXT_PRG_RCLK_DLY_EN,
+			      SDCC_HC_REG_DDR_CONFIG);
+		rgmii_updatel(ethqos, RGMII_CONFIG_LOOPBACK_EN,
+			      RGMII_CONFIG_LOOPBACK_EN, RGMII_IO_MACRO_CONFIG);
+		break;
+	default:
+		dev_err(&ethqos->pdev->dev,
+			"Invalid speed %d\n", ethqos->speed);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ethqos_configure(struct qcom_ethqos *ethqos)
+{
+	volatile unsigned int dll_lock;
+	unsigned int i, retry = 1000;
+
+	/* Reset to POR values and enable clk */
+	for (i = 0; i < ethqos->num_por; i++)
+		rgmii_writel(ethqos, ethqos->por[i].value,
+			     ethqos->por[i].offset);
+	ethqos_set_func_clk_en(ethqos);
+
+	/* Initialize the DLL first */
+
+	/* Set DLL_RST */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_RST,
+		      SDCC_DLL_CONFIG_DLL_RST, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Set PDN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN,
+		      SDCC_DLL_CONFIG_PDN, SDCC_HC_REG_DLL_CONFIG);
+
+	/* Clear DLL_RST */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_RST, 0,
+		      SDCC_HC_REG_DLL_CONFIG);
+
+	/* Clear PDN */
+	rgmii_updatel(ethqos, SDCC_DLL_CONFIG_PDN, 0,
+		      SDCC_HC_REG_DLL_CONFIG);
+
+	if (ethqos->speed != SPEED_100 && ethqos->speed != SPEED_10) {
+		/* Set DLL_EN */
+		rgmii_updatel(ethqos, SDCC_DLL_CONFIG_DLL_EN,
+			      SDCC_DLL_CONFIG_DLL_EN, SDCC_HC_REG_DLL_CONFIG);
+
+		/* Set CK_OUT_EN */
+		rgmii_updatel(ethqos, SDCC_DLL_CONFIG_CK_OUT_EN,
+			      SDCC_DLL_CONFIG_CK_OUT_EN,
+			      SDCC_HC_REG_DLL_CONFIG);
+
+		/* Set USR_CTL bit 26 with mask of 3 bits */
+		rgmii_updatel(ethqos, GENMASK(26, 24), BIT(26), SDCC_USR_CTL);
+
+		/* wait for DLL LOCK */
+		do {
+			mdelay(1);
+			dll_lock = rgmii_readl(ethqos, SDC4_STATUS);
+			if (dll_lock & SDC4_STATUS_DLL_LOCK)
+				break;
+		} while (retry > 0);
+		if (!retry)
+			dev_err(&ethqos->pdev->dev,
+				"Timeout while waiting for DLL lock\n");
+	}
+
+	if (ethqos->speed == SPEED_1000)
+		ethqos_dll_configure(ethqos);
+
+	ethqos_rgmii_macro_init(ethqos);
+
+	return 0;
+}
+
+static void ethqos_fix_mac_speed(void *priv, unsigned int speed)
+{
+	struct qcom_ethqos *ethqos = priv;
+
+	ethqos->speed = speed;
+	ethqos_update_rgmii_clk(ethqos, speed);
+	ethqos_configure(ethqos);
+}
+
+static int qcom_ethqos_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct qcom_ethqos *ethqos;
+	struct resource *res;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return ret;
+
+	plat_dat = stmmac_probe_config_dt(pdev, &stmmac_res.mac);
+	if (IS_ERR(plat_dat)) {
+		dev_err(&pdev->dev, "dt configuration failed\n");
+		return PTR_ERR(plat_dat);
+	}
+
+	ethqos = devm_kzalloc(&pdev->dev, sizeof(*ethqos), GFP_KERNEL);
+	if (!ethqos) {
+		ret = -ENOMEM;
+		goto err_mem;
+	}
+
+	ethqos->pdev = pdev;
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "rgmii");
+	ethqos->rgmii_base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ethqos->rgmii_base)) {
+		dev_err(&pdev->dev, "Can't get rgmii base\n");
+		ret = PTR_ERR(ethqos->rgmii_base);
+		goto err_mem;
+	}
+
+	ethqos->por = of_device_get_match_data(&pdev->dev);
+
+	ethqos->rgmii_clk = devm_clk_get(&pdev->dev, "rgmii");
+	if (IS_ERR(ethqos->rgmii_clk)) {
+		ret = PTR_ERR(ethqos->rgmii_clk);
+		goto err_mem;
+	}
+
+	ret = clk_prepare_enable(ethqos->rgmii_clk);
+	if (ret)
+		goto err_mem;
+
+	ethqos->speed = SPEED_1000;
+	ethqos_update_rgmii_clk(ethqos, SPEED_1000);
+	ethqos_set_func_clk_en(ethqos);
+
+	plat_dat->bsp_priv = ethqos;
+	plat_dat->fix_mac_speed = ethqos_fix_mac_speed;
+	plat_dat->has_gmac4 = 1;
+	plat_dat->pmt = 1;
+	plat_dat->tso_en = of_property_read_bool(np, "snps,tso");
+
+	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
+	if (ret)
+		goto err_clk;
+
+	rgmii_dump(ethqos);
+
+	return ret;
+
+err_clk:
+	clk_disable_unprepare(ethqos->rgmii_clk);
+
+err_mem:
+	stmmac_remove_config_dt(pdev, plat_dat);
+
+	return ret;
+}
+
+static int qcom_ethqos_remove(struct platform_device *pdev)
+{
+	struct qcom_ethqos *ethqos;
+	int ret;
+
+	ethqos = get_stmmac_bsp_priv(&pdev->dev);
+	if (!ethqos)
+		return -ENODEV;
+
+	ret = stmmac_pltfr_remove(pdev);
+	clk_disable_unprepare(ethqos->rgmii_clk);
+
+	return ret;
+}
+
+static const struct of_device_id qcom_ethqos_match[] = {
+	{ .compatible = "qcom,qcs404-ethqos", .data = &emac_v2_3_0_por},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, qcom_ethqos_match);
+
+static struct platform_driver qcom_ethqos_driver = {
+	.probe  = qcom_ethqos_probe,
+	.remove = qcom_ethqos_remove,
+	.driver = {
+		.name           = "qcom-ethqos",
+		.pm		= &stmmac_pltfr_pm_ops,
+		.of_match_table = of_match_ptr(qcom_ethqos_match),
+	},
+};
+module_platform_driver(qcom_ethqos_driver);
+
+MODULE_DESCRIPTION("Qualcomm ETHQOS driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 7b923362ee55..3b174eae77c1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1342,8 +1342,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 	}
 
 	ret = phy_power_on(bsp_priv, true);
-	if (ret)
+	if (ret) {
+		gmac_clk_enable(bsp_priv, false);
 		return ret;
+	}
 
 	pm_runtime_enable(dev);
 	pm_runtime_get_sync(dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 7e2e79dedebf..21428537e231 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -25,9 +25,24 @@
 
 #define SYSCFG_MCU_ETH_MASK		BIT(23)
 #define SYSCFG_MP1_ETH_MASK		GENMASK(23, 16)
+#define SYSCFG_PMCCLRR_OFFSET		0x40
 
 #define SYSCFG_PMCR_ETH_CLK_SEL		BIT(16)
 #define SYSCFG_PMCR_ETH_REF_CLK_SEL	BIT(17)
+
+/*  Ethernet PHY interface selection in register SYSCFG Configuration
+ *------------------------------------------
+ * src	 |BIT(23)| BIT(22)| BIT(21)|BIT(20)|
+ *------------------------------------------
+ * MII   |   0	 |   0	  |   0    |   1   |
+ *------------------------------------------
+ * GMII  |   0	 |   0	  |   0    |   0   |
+ *------------------------------------------
+ * RGMII |   0	 |   0	  |   1	   |  n/a  |
+ *------------------------------------------
+ * RMII  |   1	 |   0	  |   0	   |  n/a  |
+ *------------------------------------------
+ */
 #define SYSCFG_PMCR_ETH_SEL_MII		BIT(20)
 #define SYSCFG_PMCR_ETH_SEL_RGMII	BIT(21)
 #define SYSCFG_PMCR_ETH_SEL_RMII	BIT(23)
@@ -35,14 +50,54 @@
 #define SYSCFG_MCU_ETH_SEL_MII		0
 #define SYSCFG_MCU_ETH_SEL_RMII		1
 
+/* STM32MP1 register definitions
+ *
+ * Below table summarizes the clock requirement and clock sources for
+ * supported phy interface modes.
+ * __________________________________________________________________________
+ *|PHY_MODE | Normal | PHY wo crystal|   PHY wo crystal   |No 125Mhz from PHY|
+ *|         |        |      25MHz    |        50MHz       |                  |
+ * ---------------------------------------------------------------------------
+ *|  MII    |	 -   |     eth-ck    |	      n/a	  |	  n/a        |
+ *|         |        |		     |                    |		     |
+ * ---------------------------------------------------------------------------
+ *|  GMII   |	 -   |     eth-ck    |	      n/a	  |	  n/a        |
+ *|         |        |               |                    |		     |
+ * ---------------------------------------------------------------------------
+ *| RGMII   |	 -   |     eth-ck    |	      n/a	  |  eth-ck (no pin) |
+ *|         |        |               |                    |  st,eth-clk-sel  |
+ * ---------------------------------------------------------------------------
+ *| RMII    |	 -   |     eth-ck    |	    eth-ck        |	  n/a        |
+ *|         |        |		     | st,eth-ref-clk-sel |		     |
+ * ---------------------------------------------------------------------------
+ *
+ * BIT(17) : set this bit in RMII mode when you have PHY without crystal 50MHz
+ * BIT(16) : set this bit in GMII/RGMII PHY when you do not want use 125Mhz
+ * from PHY
+ *-----------------------------------------------------
+ * src	 |         BIT(17)       |       BIT(16)      |
+ *-----------------------------------------------------
+ * MII   |           n/a	 |         n/a        |
+ *-----------------------------------------------------
+ * GMII  |           n/a         |   st,eth-clk-sel   |
+ *-----------------------------------------------------
+ * RGMII |           n/a         |   st,eth-clk-sel   |
+ *-----------------------------------------------------
+ * RMII  |   st,eth-ref-clk-sel	 |         n/a        |
+ *-----------------------------------------------------
+ *
+ */
+
 struct stm32_dwmac {
 	struct clk *clk_tx;
 	struct clk *clk_rx;
 	struct clk *clk_eth_ck;
 	struct clk *clk_ethstp;
 	struct clk *syscfg_clk;
-	bool int_phyclk;	/* Clock from RCC to drive PHY */
-	u32 mode_reg;		/* MAC glue-logic mode register */
+	int eth_clk_sel_reg;
+	int eth_ref_clk_sel_reg;
+	int irq_pwr_wakeup;
+	u32 mode_reg;		 /* MAC glue-logic mode register */
 	struct regmap *regmap;
 	u32 speed;
 	const struct stm32_ops *ops;
@@ -102,7 +157,7 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare)
 		if (ret)
 			return ret;
 
-		if (dwmac->int_phyclk) {
+		if (dwmac->clk_eth_ck) {
 			ret = clk_prepare_enable(dwmac->clk_eth_ck);
 			if (ret) {
 				clk_disable_unprepare(dwmac->syscfg_clk);
@@ -111,7 +166,7 @@ static int stm32mp1_clk_prepare(struct stm32_dwmac *dwmac, bool prepare)
 		}
 	} else {
 		clk_disable_unprepare(dwmac->syscfg_clk);
-		if (dwmac->int_phyclk)
+		if (dwmac->clk_eth_ck)
 			clk_disable_unprepare(dwmac->clk_eth_ck);
 	}
 	return ret;
@@ -121,7 +176,7 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct stm32_dwmac *dwmac = plat_dat->bsp_priv;
 	u32 reg = dwmac->mode_reg;
-	int val;
+	int val, ret;
 
 	switch (plat_dat->interface) {
 	case PHY_INTERFACE_MODE_MII:
@@ -130,19 +185,22 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 		break;
 	case PHY_INTERFACE_MODE_GMII:
 		val = SYSCFG_PMCR_ETH_SEL_GMII;
-		if (dwmac->int_phyclk)
+		if (dwmac->eth_clk_sel_reg)
 			val |= SYSCFG_PMCR_ETH_CLK_SEL;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_GMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RMII:
 		val = SYSCFG_PMCR_ETH_SEL_RMII;
-		if (dwmac->int_phyclk)
+		if (dwmac->eth_ref_clk_sel_reg)
 			val |= SYSCFG_PMCR_ETH_REF_CLK_SEL;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		val = SYSCFG_PMCR_ETH_SEL_RGMII;
-		if (dwmac->int_phyclk)
+		if (dwmac->eth_clk_sel_reg)
 			val |= SYSCFG_PMCR_ETH_CLK_SEL;
 		pr_debug("SYSCFG init : PHY_INTERFACE_MODE_RGMII\n");
 		break;
@@ -153,6 +211,11 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat)
 		return -EINVAL;
 	}
 
+	/* Need to update PMCCLRR (clear register) */
+	ret = regmap_write(dwmac->regmap, reg + SYSCFG_PMCCLRR_OFFSET,
+			   dwmac->ops->syscfg_eth_mask);
+
+	/* Update PMCSETR (set register) */
 	return regmap_update_bits(dwmac->regmap, reg,
 				 dwmac->ops->syscfg_eth_mask, val);
 }
@@ -180,7 +243,7 @@ static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat)
 	}
 
 	return regmap_update_bits(dwmac->regmap, reg,
-				 dwmac->ops->syscfg_eth_mask, val);
+				 dwmac->ops->syscfg_eth_mask, val << 23);
 }
 
 static void stm32_dwmac_clk_disable(struct stm32_dwmac *dwmac)
@@ -232,24 +295,29 @@ static int stm32_dwmac_parse_data(struct stm32_dwmac *dwmac,
 static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 			       struct device *dev)
 {
+	struct platform_device *pdev = to_platform_device(dev);
 	struct device_node *np = dev->of_node;
+	int err = 0;
 
-	dwmac->int_phyclk = of_property_read_bool(np, "st,int-phyclk");
+	/* Gigabit Ethernet 125MHz clock selection. */
+	dwmac->eth_clk_sel_reg = of_property_read_bool(np, "st,eth-clk-sel");
 
-	/* Check if internal clk from RCC selected */
-	if (dwmac->int_phyclk) {
-		/*  Get ETH_CLK clocks */
-		dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck");
-		if (IS_ERR(dwmac->clk_eth_ck)) {
-			dev_err(dev, "No ETH CK clock provided...\n");
-			return PTR_ERR(dwmac->clk_eth_ck);
-		}
+	/* Ethernet 50Mhz RMII clock selection */
+	dwmac->eth_ref_clk_sel_reg =
+		of_property_read_bool(np, "st,eth-ref-clk-sel");
+
+	/*  Get ETH_CLK clocks */
+	dwmac->clk_eth_ck = devm_clk_get(dev, "eth-ck");
+	if (IS_ERR(dwmac->clk_eth_ck)) {
+		dev_warn(dev, "No phy clock provided...\n");
+		dwmac->clk_eth_ck = NULL;
 	}
 
 	/*  Clock used for low power mode */
 	dwmac->clk_ethstp = devm_clk_get(dev, "ethstp");
 	if (IS_ERR(dwmac->clk_ethstp)) {
-		dev_err(dev, "No ETH peripheral clock provided for CStop mode ...\n");
+		dev_err(dev,
+			"No ETH peripheral clock provided for CStop mode ...\n");
 		return PTR_ERR(dwmac->clk_ethstp);
 	}
 
@@ -260,7 +328,29 @@ static int stm32mp1_parse_data(struct stm32_dwmac *dwmac,
 		return PTR_ERR(dwmac->syscfg_clk);
 	}
 
-	return 0;
+	/* Get IRQ information early to have an ability to ask for deferred
+	 * probe if needed before we went too far with resource allocation.
+	 */
+	dwmac->irq_pwr_wakeup = platform_get_irq_byname(pdev,
+							"stm32_pwr_wakeup");
+	if (dwmac->irq_pwr_wakeup == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	if (!dwmac->clk_eth_ck && dwmac->irq_pwr_wakeup >= 0) {
+		err = device_init_wakeup(&pdev->dev, true);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to init wake up irq\n");
+			return err;
+		}
+		err = dev_pm_set_dedicated_wake_irq(&pdev->dev,
+						    dwmac->irq_pwr_wakeup);
+		if (err) {
+			dev_err(&pdev->dev, "Failed to set wake up irq\n");
+			device_init_wakeup(&pdev->dev, false);
+		}
+		device_set_wakeup_enable(&pdev->dev, false);
+	}
+	return err;
 }
 
 static int stm32_dwmac_probe(struct platform_device *pdev)
@@ -326,9 +416,15 @@ static int stm32_dwmac_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct stmmac_priv *priv = netdev_priv(ndev);
 	int ret = stmmac_dvr_remove(&pdev->dev);
+	struct stm32_dwmac *dwmac = priv->plat->bsp_priv;
 
 	stm32_dwmac_clk_disable(priv->plat->bsp_priv);
 
+	if (dwmac->irq_pwr_wakeup >= 0) {
+		dev_pm_clear_wake_irq(&pdev->dev);
+		device_init_wakeup(&pdev->dev, false);
+	}
+
 	return ret;
 }
 
@@ -342,7 +438,7 @@ static int stm32mp1_suspend(struct stm32_dwmac *dwmac)
 
 	clk_disable_unprepare(dwmac->clk_tx);
 	clk_disable_unprepare(dwmac->syscfg_clk);
-	if (dwmac->int_phyclk)
+	if (dwmac->clk_eth_ck)
 		clk_disable_unprepare(dwmac->clk_eth_ck);
 
 	return ret;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 0f660af01a4b..195669f550f0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1147,7 +1147,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	plat_dat->interface = of_get_phy_mode(dev->of_node);
+	ret = of_get_phy_mode(dev->of_node);
+	if (ret < 0)
+		return -EINVAL;
+	plat_dat->interface = ret;
 
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index d07520fb969e..62ccbd47c1db 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -59,7 +59,9 @@ static int sun7i_gmac_init(struct platform_device *pdev, void *priv)
 		gmac->clk_enabled = 1;
 	} else {
 		clk_set_rate(gmac->tx_clk, SUN7I_GMAC_MII_RATE);
-		clk_prepare(gmac->tx_clk);
+		ret = clk_prepare(gmac->tx_clk);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
index 20299f6f65fc..e061e9f5fad7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -241,15 +241,18 @@ static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts)
 static int dwmac4_rx_check_timestamp(void *desc)
 {
 	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes0 = le32_to_cpu(p->des0);
+	unsigned int rdes1 = le32_to_cpu(p->des1);
+	unsigned int rdes3 = le32_to_cpu(p->des3);
 	u32 own, ctxt;
 	int ret = 1;
 
-	own = p->des3 & RDES3_OWN;
-	ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR)
+	own = rdes3 & RDES3_OWN;
+	ctxt = ((rdes3 & RDES3_CONTEXT_DESCRIPTOR)
 		>> RDES3_CONTEXT_DESCRIPTOR_SHIFT);
 
 	if (likely(!own && ctxt)) {
-		if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff))
+		if ((rdes0 == 0xffffffff) && (rdes1 == 0xffffffff))
 			/* Corrupted value */
 			ret = -EINVAL;
 		else
@@ -268,7 +271,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc,
 	int ret = -EINVAL;
 
 	/* Get the status from normal w/b descriptor */
-	if (likely(p->des3 & TDES3_RS1V)) {
+	if (likely(le32_to_cpu(p->des3) & RDES3_RDES1_VALID)) {
 		if (likely(le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)) {
 			int i = 0;
 
@@ -293,7 +296,7 @@ exit:
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				   int mode, int end)
+				   int mode, int end, int bfsize)
 {
 	dwmac4_set_rx_owner(p, disable_rx_ic);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
index 49f5687879df..545cb9c47433 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -124,9 +124,9 @@ void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
 			 struct stmmac_extra_stats *x, u32 chan)
 {
-	int ret = 0;
-
 	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
+	u32 intr_en = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
+	int ret = 0;
 
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
@@ -151,16 +151,11 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 	if (likely(intr_status & DMA_CHAN_STATUS_NIS)) {
 		x->normal_irq_n++;
 		if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
-			u32 value;
-
-			value = readl(ioaddr + DMA_CHAN_INTR_ENA(chan));
-			/* to schedule NAPI on real RIE event. */
-			if (likely(value & DMA_CHAN_INTR_ENA_RIE)) {
-				x->rx_normal_irq_n++;
-				ret |= handle_rx;
-			}
+			x->rx_normal_irq_n++;
+			ret |= handle_rx;
 		}
-		if (likely(intr_status & DMA_CHAN_STATUS_TI)) {
+		if (likely(intr_status & (DMA_CHAN_STATUS_TI |
+					  DMA_CHAN_STATUS_TBU))) {
 			x->tx_normal_irq_n++;
 			ret |= handle_tx;
 		}
@@ -168,12 +163,7 @@ int dwmac4_dma_interrupt(void __iomem *ioaddr,
 			x->rx_early_irq++;
 	}
 
-	/* Clear the interrupt by writing a logic 1 to the chanX interrupt
-	 * status [21-0] expect reserved bits [5-3]
-	 */
-	writel((intr_status & 0x3fffc7),
-	       ioaddr + DMA_CHAN_STATUS(chan));
-
+	writel(intr_status & intr_en, ioaddr + DMA_CHAN_STATUS(chan));
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index d6bb953685fa..37d5e6fe7473 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -193,9 +193,10 @@
 #define XGMAC_AIE			BIT(14)
 #define XGMAC_RBUE			BIT(7)
 #define XGMAC_RIE			BIT(6)
+#define XGMAC_TBUE			BIT(2)
 #define XGMAC_TIE			BIT(0)
 #define XGMAC_DMA_INT_DEFAULT_EN	(XGMAC_NIE | XGMAC_AIE | XGMAC_RBUE | \
-					XGMAC_RIE | XGMAC_TIE)
+					XGMAC_RIE | XGMAC_TBUE | XGMAC_TIE)
 #define XGMAC_DMA_CH_Rx_WATCHDOG(x)	(0x0000313c + (0x80 * (x)))
 #define XGMAC_RWT			GENMASK(7, 0)
 #define XGMAC_DMA_CH_STATUS(x)		(0x00003160 + (0x80 * (x)))
@@ -204,6 +205,7 @@
 #define XGMAC_FBE			BIT(12)
 #define XGMAC_RBU			BIT(7)
 #define XGMAC_RI			BIT(6)
+#define XGMAC_TBU			BIT(2)
 #define XGMAC_TPS			BIT(1)
 #define XGMAC_TI			BIT(0)
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
index 1d858fdec997..98fa471da7c0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -123,7 +123,7 @@ static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc,
 }
 
 static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				  int mode, int end)
+				  int mode, int end, int bfsize)
 {
 	dwxgmac2_set_rx_owner(p, disable_rx_ic);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
index 6c5092e7771c..2ba712b48a89 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -263,6 +263,7 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
 				  struct stmmac_extra_stats *x, u32 chan)
 {
 	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
+	u32 intr_en = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
 	int ret = 0;
 
 	/* ABNORMAL interrupts */
@@ -282,20 +283,17 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
 		x->normal_irq_n++;
 
 		if (likely(intr_status & XGMAC_RI)) {
-			u32 value = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
-			if (likely(value & XGMAC_RIE)) {
-				x->rx_normal_irq_n++;
-				ret |= handle_rx;
-			}
+			x->rx_normal_irq_n++;
+			ret |= handle_rx;
 		}
-		if (likely(intr_status & XGMAC_TI)) {
+		if (likely(intr_status & (XGMAC_TI | XGMAC_TBU))) {
 			x->tx_normal_irq_n++;
 			ret |= handle_tx;
 		}
 	}
 
 	/* Clear interrupts */
-	writel(~0x0, ioaddr + XGMAC_DMA_CH_STATUS(chan));
+	writel(intr_en & intr_status, ioaddr + XGMAC_DMA_CH_STATUS(chan));
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index 5ef91a790f9d..5202d6ad7919 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -201,6 +201,11 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	if (unlikely(rdes0 & RDES0_OWN))
 		return dma_own;
 
+	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
+		stats->rx_length_errors++;
+		return discard_frame;
+	}
+
 	if (unlikely(rdes0 & RDES0_ERROR_SUMMARY)) {
 		if (unlikely(rdes0 & RDES0_DESCRIPTOR_ERROR)) {
 			x->rx_desc++;
@@ -231,9 +236,10 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 	 * It doesn't match with the information reported into the databook.
 	 * At any rate, we need to understand if the CSUM hw computation is ok
 	 * and report this info to the upper layers. */
-	ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
-				 !!(rdes0 & RDES0_FRAME_TYPE),
-				 !!(rdes0 & ERDES0_RX_MAC_ADDR));
+	if (likely(ret == good_frame))
+		ret = enh_desc_coe_rdes0(!!(rdes0 & RDES0_IPC_CSUM_ERROR),
+					 !!(rdes0 & RDES0_FRAME_TYPE),
+					 !!(rdes0 & ERDES0_RX_MAC_ADDR));
 
 	if (unlikely(rdes0 & RDES0_DRIBBLING))
 		x->dribbling_bit++;
@@ -259,15 +265,19 @@ static int enh_desc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 }
 
 static void enh_desc_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
-				  int mode, int end)
+				  int mode, int end, int bfsize)
 {
+	int bfsize1;
+
 	p->des0 |= cpu_to_le32(RDES0_OWN);
-	p->des1 |= cpu_to_le32(BUF_SIZE_8KiB & ERDES1_BUFFER1_SIZE_MASK);
+
+	bfsize1 = min(bfsize, BUF_SIZE_8KiB);
+	p->des1 |= cpu_to_le32(bfsize1 & ERDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ehn_desc_rx_set_on_chain(p);
 	else
-		ehn_desc_rx_set_on_ring(p, end);
+		ehn_desc_rx_set_on_ring(p, end, bfsize);
 
 	if (disable_rx_ic)
 		p->des1 |= cpu_to_le32(ERDES1_DISABLE_IC);
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 92b8944f26e3..5bb00234d961 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -33,7 +33,7 @@ struct dma_extended_desc;
 struct stmmac_desc_ops {
 	/* DMA RX descriptor ring initialization */
 	void (*init_rx_desc)(struct dma_desc *p, int disable_rx_ic, int mode,
-			int end);
+			int end, int bfsize);
 	/* DMA TX descriptor ring initialization */
 	void (*init_tx_desc)(struct dma_desc *p, int mode, int end);
 	/* Invoked by the xmit function to prepare the tx descriptor */
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index de65bb29feba..6d690678c20e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -91,8 +91,6 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 		return dma_own;
 
 	if (unlikely(!(rdes0 & RDES0_LAST_DESCRIPTOR))) {
-		pr_warn("%s: Oversized frame spanned multiple buffers\n",
-			__func__);
 		stats->rx_length_errors++;
 		return discard_frame;
 	}
@@ -135,15 +133,19 @@ static int ndesc_get_rx_status(void *data, struct stmmac_extra_stats *x,
 }
 
 static void ndesc_init_rx_desc(struct dma_desc *p, int disable_rx_ic, int mode,
-			       int end)
+			       int end, int bfsize)
 {
+	int bfsize1;
+
 	p->des0 |= cpu_to_le32(RDES0_OWN);
-	p->des1 |= cpu_to_le32((BUF_SIZE_2KiB - 1) & RDES1_BUFFER1_SIZE_MASK);
+
+	bfsize1 = min(bfsize, BUF_SIZE_2KiB - 1);
+	p->des1 |= cpu_to_le32(bfsize1 & RDES1_BUFFER1_SIZE_MASK);
 
 	if (mode == STMMAC_CHAIN_MODE)
 		ndesc_rx_set_on_chain(p, end);
 	else
-		ndesc_rx_set_on_ring(p, end);
+		ndesc_rx_set_on_ring(p, end, bfsize);
 
 	if (disable_rx_ic)
 		p->des1 |= cpu_to_le32(RDES1_DISABLE_IC);
diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
index d8c5bc412219..4d9bcb4d0378 100644
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -59,7 +59,7 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum,
-				STMMAC_RING_MODE, 1, false, skb->len);
+				STMMAC_RING_MODE, 0, false, skb->len);
 		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
@@ -79,7 +79,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 0, len, csum,
-				STMMAC_RING_MODE, 1, true, skb->len);
+				STMMAC_RING_MODE, 1, !skb_is_nonlinear(skb),
+				skb->len);
 	} else {
 		des2 = dma_map_single(priv->device, skb->data,
 				      nopaged_len, DMA_TO_DEVICE);
@@ -91,7 +92,8 @@ static int jumbo_frm(void *p, struct sk_buff *skb, int csum)
 		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		stmmac_prepare_tx_desc(priv, desc, 1, nopaged_len, csum,
-				STMMAC_RING_MODE, 1, true, skb->len);
+				STMMAC_RING_MODE, 0, !skb_is_nonlinear(skb),
+				skb->len);
 	}
 
 	tx_q->cur_tx = entry;
@@ -111,10 +113,11 @@ static unsigned int is_jumbo_frm(int len, int enh_desc)
 
 static void refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	/* Fill DES3 in case of RING mode */
-	if (priv->dma_buf_sz >= BUF_SIZE_8KiB)
+	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 63e1064b27a2..dd95d959c1ce 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -28,6 +28,7 @@
 #include <linux/pci.h>
 #include "common.h"
 #include <linux/ptp_clock_kernel.h>
+#include <linux/net_tstamp.h>
 #include <linux/reset.h>
 
 struct stmmac_resources {
@@ -78,11 +79,10 @@ struct stmmac_rx_queue {
 };
 
 struct stmmac_channel {
-	struct napi_struct napi ____cacheline_aligned_in_smp;
+	struct napi_struct rx_napi ____cacheline_aligned_in_smp;
+	struct napi_struct tx_napi ____cacheline_aligned_in_smp;
 	struct stmmac_priv *priv_data;
 	u32 index;
-	int has_rx;
-	int has_tx;
 };
 
 struct stmmac_tc_entry {
@@ -174,6 +174,7 @@ struct stmmac_priv {
 	unsigned int mode;
 	unsigned int chain_mode;
 	int extend_desc;
+	struct hwtstamp_config tstamp_config;
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_ops;
 	unsigned int default_addend;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index 5710864fa809..3c749c327cbd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -458,8 +458,10 @@ stmmac_get_pauseparam(struct net_device *netdev,
 		if (!adv_lp.pause)
 			return;
 	} else {
-		if (!(netdev->phydev->supported & SUPPORTED_Pause) ||
-		    !(netdev->phydev->supported & SUPPORTED_Asym_Pause))
+		if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				       netdev->phydev->supported) ||
+		    linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				      netdev->phydev->supported))
 			return;
 	}
 
@@ -487,8 +489,10 @@ stmmac_set_pauseparam(struct net_device *netdev,
 		if (!adv_lp.pause)
 			return -EOPNOTSUPP;
 	} else {
-		if (!(phy->supported & SUPPORTED_Pause) ||
-		    !(phy->supported & SUPPORTED_Asym_Pause))
+		if (!linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+				       phy->supported) ||
+		    linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+				      phy->supported))
 			return -EOPNOTSUPP;
 	}
 
@@ -692,33 +696,38 @@ static int stmmac_ethtool_op_set_eee(struct net_device *dev,
 				     struct ethtool_eee *edata)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	int ret;
 
-	priv->eee_enabled = edata->eee_enabled;
-
-	if (!priv->eee_enabled)
+	if (!edata->eee_enabled) {
 		stmmac_disable_eee_mode(priv);
-	else {
+	} else {
 		/* We are asking for enabling the EEE but it is safe
 		 * to verify all by invoking the eee_init function.
 		 * In case of failure it will return an error.
 		 */
-		priv->eee_enabled = stmmac_eee_init(priv);
-		if (!priv->eee_enabled)
+		edata->eee_enabled = stmmac_eee_init(priv);
+		if (!edata->eee_enabled)
 			return -EOPNOTSUPP;
-
-		/* Do not change tx_lpi_timer in case of failure */
-		priv->tx_lpi_timer = edata->tx_lpi_timer;
 	}
 
-	return phy_ethtool_set_eee(dev->phydev, edata);
+	ret = phy_ethtool_set_eee(dev->phydev, edata);
+	if (ret)
+		return ret;
+
+	priv->eee_enabled = edata->eee_enabled;
+	priv->tx_lpi_timer = edata->tx_lpi_timer;
+	return 0;
 }
 
 static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv)
 {
 	unsigned long clk = clk_get_rate(priv->plat->stmmac_clk);
 
-	if (!clk)
-		return 0;
+	if (!clk) {
+		clk = priv->plat->clk_ref_rate;
+		if (!clk)
+			return 0;
+	}
 
 	return (usec * (clk / 1000000)) / 256;
 }
@@ -727,8 +736,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv)
 {
 	unsigned long clk = clk_get_rate(priv->plat->stmmac_clk);
 
-	if (!clk)
-		return 0;
+	if (!clk) {
+		clk = priv->plat->clk_ref_rate;
+		if (!clk)
+			return 0;
+	}
 
 	return (riwt * 256) / (clk / 1000000);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c4a35e932f05..48712437d0da 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -155,7 +155,10 @@ static void stmmac_disable_all_queues(struct stmmac_priv *priv)
 	for (queue = 0; queue < maxq; queue++) {
 		struct stmmac_channel *ch = &priv->channel[queue];
 
-		napi_disable(&ch->napi);
+		if (queue < rx_queues_cnt)
+			napi_disable(&ch->rx_napi);
+		if (queue < tx_queues_cnt)
+			napi_disable(&ch->tx_napi);
 	}
 }
 
@@ -173,7 +176,10 @@ static void stmmac_enable_all_queues(struct stmmac_priv *priv)
 	for (queue = 0; queue < maxq; queue++) {
 		struct stmmac_channel *ch = &priv->channel[queue];
 
-		napi_enable(&ch->napi);
+		if (queue < rx_queues_cnt)
+			napi_enable(&ch->rx_napi);
+		if (queue < tx_queues_cnt)
+			napi_enable(&ch->tx_napi);
 	}
 }
 
@@ -474,7 +480,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv,
 				   struct dma_desc *p, struct sk_buff *skb)
 {
 	struct skb_shared_hwtstamps shhwtstamp;
-	u64 ns;
+	u64 ns = 0;
 
 	if (!priv->hwts_tx_en)
 		return;
@@ -513,7 +519,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 {
 	struct skb_shared_hwtstamps *shhwtstamp = NULL;
 	struct dma_desc *desc = p;
-	u64 ns;
+	u64 ns = 0;
 
 	if (!priv->hwts_rx_en)
 		return;
@@ -534,7 +540,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 }
 
 /**
- *  stmmac_hwtstamp_ioctl - control hardware timestamping.
+ *  stmmac_hwtstamp_set - control hardware timestamping.
  *  @dev: device pointer.
  *  @ifr: An IOCTL specific structure, that can contain a pointer to
  *  a proprietary structure used to pass information to the driver.
@@ -544,7 +550,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
  *  Return Value:
  *  0 on success and an appropriate -ve integer on failure.
  */
-static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
+static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config config;
@@ -558,8 +564,8 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	u32 snap_type_sel = 0;
 	u32 ts_master_en = 0;
 	u32 ts_event_en = 0;
+	u32 sec_inc = 0;
 	u32 value = 0;
-	u32 sec_inc;
 	bool xmac;
 
 	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
@@ -573,7 +579,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	}
 
 	if (copy_from_user(&config, ifr->ifr_data,
-			   sizeof(struct hwtstamp_config)))
+			   sizeof(config)))
 		return -EFAULT;
 
 	netdev_dbg(priv->dev, "%s config flags:0x%x, tx_type:0x%x, rx_filter:0x%x\n",
@@ -597,12 +603,13 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 		case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 			/* PTP v1, UDP, any kind of event packet */
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
-			/* take time stamp for all event messages */
-			if (xmac)
-				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
-			else
-				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-
+			/* 'xmac' hardware can support Sync, Pdelay_Req and
+			 * Pdelay_resp by setting bit14 and bits17/16 to 01
+			 * This leaves Delay_Req timestamps out.
+			 * Enable all events *and* general purpose message
+			 * timestamping
+			 */
+			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			break;
@@ -633,10 +640,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
-			if (xmac)
-				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
-			else
-				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
+			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
@@ -669,12 +673,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			/* PTP v2/802.AS1 any layer, any kind of event packet */
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
-			/* take time stamp for all event messages */
-			if (xmac)
-				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
-			else
-				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
-
+			snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
 			ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA;
 			ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA;
 			ptp_over_ethernet = PTP_TCR_TSIPENA;
@@ -765,8 +764,31 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 				(u32)now.tv_sec, now.tv_nsec);
 	}
 
+	memcpy(&priv->tstamp_config, &config, sizeof(config));
+
 	return copy_to_user(ifr->ifr_data, &config,
-			    sizeof(struct hwtstamp_config)) ? -EFAULT : 0;
+			    sizeof(config)) ? -EFAULT : 0;
+}
+
+/**
+ *  stmmac_hwtstamp_get - read hardware timestamping.
+ *  @dev: device pointer.
+ *  @ifr: An IOCTL specific structure, that can contain a pointer to
+ *  a proprietary structure used to pass information to the driver.
+ *  Description:
+ *  This function obtain the current hardware timestamping settings
+    as requested.
+ */
+static int stmmac_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	struct hwtstamp_config *config = &priv->tstamp_config;
+
+	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
+		return -EOPNOTSUPP;
+
+	return copy_to_user(ifr->ifr_data, config,
+			    sizeof(*config)) ? -EFAULT : 0;
 }
 
 /**
@@ -1114,11 +1136,13 @@ static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue)
 		if (priv->extend_desc)
 			stmmac_init_rx_desc(priv, &rx_q->dma_erx[i].basic,
 					priv->use_riwt, priv->mode,
-					(i == DMA_RX_SIZE - 1));
+					(i == DMA_RX_SIZE - 1),
+					priv->dma_buf_sz);
 		else
 			stmmac_init_rx_desc(priv, &rx_q->dma_rx[i],
 					priv->use_riwt, priv->mode,
-					(i == DMA_RX_SIZE - 1));
+					(i == DMA_RX_SIZE - 1),
+					priv->dma_buf_sz);
 }
 
 /**
@@ -1549,22 +1573,18 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
 			goto err_dma;
 
 		if (priv->extend_desc) {
-			rx_q->dma_erx = dma_zalloc_coherent(priv->device,
-							    DMA_RX_SIZE *
-							    sizeof(struct
-							    dma_extended_desc),
-							    &rx_q->dma_rx_phy,
-							    GFP_KERNEL);
+			rx_q->dma_erx = dma_alloc_coherent(priv->device,
+							   DMA_RX_SIZE * sizeof(struct dma_extended_desc),
+							   &rx_q->dma_rx_phy,
+							   GFP_KERNEL);
 			if (!rx_q->dma_erx)
 				goto err_dma;
 
 		} else {
-			rx_q->dma_rx = dma_zalloc_coherent(priv->device,
-							   DMA_RX_SIZE *
-							   sizeof(struct
-							   dma_desc),
-							   &rx_q->dma_rx_phy,
-							   GFP_KERNEL);
+			rx_q->dma_rx = dma_alloc_coherent(priv->device,
+							  DMA_RX_SIZE * sizeof(struct dma_desc),
+							  &rx_q->dma_rx_phy,
+							  GFP_KERNEL);
 			if (!rx_q->dma_rx)
 				goto err_dma;
 		}
@@ -1612,21 +1632,17 @@ static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv)
 			goto err_dma;
 
 		if (priv->extend_desc) {
-			tx_q->dma_etx = dma_zalloc_coherent(priv->device,
-							    DMA_TX_SIZE *
-							    sizeof(struct
-							    dma_extended_desc),
-							    &tx_q->dma_tx_phy,
-							    GFP_KERNEL);
+			tx_q->dma_etx = dma_alloc_coherent(priv->device,
+							   DMA_TX_SIZE * sizeof(struct dma_extended_desc),
+							   &tx_q->dma_tx_phy,
+							   GFP_KERNEL);
 			if (!tx_q->dma_etx)
 				goto err_dma;
 		} else {
-			tx_q->dma_tx = dma_zalloc_coherent(priv->device,
-							   DMA_TX_SIZE *
-							   sizeof(struct
-								  dma_desc),
-							   &tx_q->dma_tx_phy,
-							   GFP_KERNEL);
+			tx_q->dma_tx = dma_alloc_coherent(priv->device,
+							  DMA_TX_SIZE * sizeof(struct dma_desc),
+							  &tx_q->dma_tx_phy,
+							  GFP_KERNEL);
 			if (!tx_q->dma_tx)
 				goto err_dma;
 		}
@@ -1947,6 +1963,10 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue)
 		mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer));
 	}
 
+	/* We still have pending packets, let's call for a new scheduling */
+	if (tx_q->dirty_tx != tx_q->cur_tx)
+		mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(10));
+
 	__netif_tx_unlock_bh(netdev_get_tx_queue(priv->dev, queue));
 
 	return count;
@@ -2037,23 +2057,15 @@ static int stmmac_napi_check(struct stmmac_priv *priv, u32 chan)
 	int status = stmmac_dma_interrupt_status(priv, priv->ioaddr,
 						 &priv->xstats, chan);
 	struct stmmac_channel *ch = &priv->channel[chan];
-	bool needs_work = false;
 
-	if ((status & handle_rx) && ch->has_rx) {
-		needs_work = true;
-	} else {
-		status &= ~handle_rx;
-	}
-
-	if ((status & handle_tx) && ch->has_tx) {
-		needs_work = true;
-	} else {
-		status &= ~handle_tx;
+	if ((status & handle_rx) && (chan < priv->plat->rx_queues_to_use)) {
+		stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
+		napi_schedule_irqoff(&ch->rx_napi);
 	}
 
-	if (needs_work && napi_schedule_prep(&ch->napi)) {
+	if ((status & handle_tx) && (chan < priv->plat->tx_queues_to_use)) {
 		stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
-		__napi_schedule(&ch->napi);
+		napi_schedule_irqoff(&ch->tx_napi);
 	}
 
 	return status;
@@ -2249,8 +2261,14 @@ static void stmmac_tx_timer(struct timer_list *t)
 
 	ch = &priv->channel[tx_q->queue_index];
 
-	if (likely(napi_schedule_prep(&ch->napi)))
-		__napi_schedule(&ch->napi);
+	/*
+	 * If NAPI is already running we can miss some events. Let's rearm
+	 * the timer and try again.
+	 */
+	if (likely(napi_schedule_prep(&ch->tx_napi)))
+		__napi_schedule(&ch->tx_napi);
+	else
+		mod_timer(&tx_q->txtimer, STMMAC_COAL_TIMER(10));
 }
 
 /**
@@ -2598,8 +2616,6 @@ static int stmmac_open(struct net_device *dev)
 	u32 chan;
 	int ret;
 
-	stmmac_check_ether_addr(priv);
-
 	if (priv->hw->pcs != STMMAC_PCS_RGMII &&
 	    priv->hw->pcs != STMMAC_PCS_TBI &&
 	    priv->hw->pcs != STMMAC_PCS_RTBI) {
@@ -3031,10 +3047,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_q = &priv->tx_queue[queue];
 
+	if (priv->tx_path_in_lpi_mode)
+		stmmac_disable_eee_mode(priv);
+
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
-		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+			/*
+			 * There is no way to determine the number of TSO
+			 * capable Queues. Let's use always the Queue 0
+			 * because if TSO is supported then at least this
+			 * one will be capable.
+			 */
+			skb_set_queue_mapping(skb, 0);
+
 			return stmmac_tso_xmit(skb, dev);
+		}
 	}
 
 	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
@@ -3049,9 +3077,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
-	if (priv->tx_path_in_lpi_mode)
-		stmmac_disable_eee_mode(priv);
-
 	entry = tx_q->cur_tx;
 	first_entry = entry;
 	WARN_ON(tx_q->tx_skbuff[first_entry]);
@@ -3191,14 +3216,16 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
 		stmmac_prepare_tx_desc(priv, first, 1, nopaged_len,
 				csum_insertion, priv->mode, 1, last_segment,
 				skb->len);
-
-		/* The own bit must be the latest setting done when prepare the
-		 * descriptor and then barrier is needed to make sure that
-		 * all is coherent before granting the DMA engine.
-		 */
-		wmb();
+	} else {
+		stmmac_set_tx_owner(priv, first);
 	}
 
+	/* The own bit must be the latest setting done when prepare the
+	 * descriptor and then barrier is needed to make sure that
+	 * all is coherent before granting the DMA engine.
+	 */
+	wmb();
+
 	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	stmmac_enable_dma_transmission(priv, priv->ioaddr);
@@ -3325,9 +3352,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct stmmac_channel *ch = &priv->channel[queue];
-	unsigned int entry = rx_q->cur_rx;
+	unsigned int next_entry = rx_q->cur_rx;
 	int coe = priv->hw->rx_csum;
-	unsigned int next_entry;
 	unsigned int count = 0;
 	bool xmac;
 
@@ -3345,10 +3371,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 		stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
 	}
 	while (count < limit) {
-		int status;
+		int entry, status;
 		struct dma_desc *p;
 		struct dma_desc *np;
 
+		entry = next_entry;
+
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
@@ -3404,11 +3432,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			 *  ignored
 			 */
 			if (frame_len > priv->dma_buf_sz) {
-				netdev_err(priv->dev,
-					   "len %d larger than size (%d)\n",
-					   frame_len, priv->dma_buf_sz);
+				if (net_ratelimit())
+					netdev_err(priv->dev,
+						   "len %d larger than size (%d)\n",
+						   frame_len, priv->dma_buf_sz);
 				priv->dev->stats.rx_length_errors++;
-				break;
+				continue;
 			}
 
 			/* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3
@@ -3443,7 +3472,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 						dev_warn(priv->device,
 							 "packet dropped\n");
 					priv->dev->stats.rx_dropped++;
-					break;
+					continue;
 				}
 
 				dma_sync_single_for_cpu(priv->device,
@@ -3463,11 +3492,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			} else {
 				skb = rx_q->rx_skbuff[entry];
 				if (unlikely(!skb)) {
-					netdev_err(priv->dev,
-						   "%s: Inconsistent Rx chain\n",
-						   priv->dev->name);
+					if (net_ratelimit())
+						netdev_err(priv->dev,
+							   "%s: Inconsistent Rx chain\n",
+							   priv->dev->name);
 					priv->dev->stats.rx_dropped++;
-					break;
+					continue;
 				}
 				prefetch(skb->data - NET_IP_ALIGN);
 				rx_q->rx_skbuff[entry] = NULL;
@@ -3497,12 +3527,11 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			else
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-			napi_gro_receive(&ch->napi, skb);
+			napi_gro_receive(&ch->rx_napi, skb);
 
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
 		}
-		entry = next_entry;
 	}
 
 	stmmac_rx_refill(priv, queue);
@@ -3512,41 +3541,47 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	return count;
 }
 
-/**
- *  stmmac_poll - stmmac poll method (NAPI)
- *  @napi : pointer to the napi structure.
- *  @budget : maximum number of packets that the current CPU can receive from
- *	      all interfaces.
- *  Description :
- *  To look at the incoming frames and clear the tx resources.
- */
-static int stmmac_napi_poll(struct napi_struct *napi, int budget)
+static int stmmac_napi_poll_rx(struct napi_struct *napi, int budget)
 {
 	struct stmmac_channel *ch =
-		container_of(napi, struct stmmac_channel, napi);
+		container_of(napi, struct stmmac_channel, rx_napi);
 	struct stmmac_priv *priv = ch->priv_data;
-	int work_done = 0, work_rem = budget;
 	u32 chan = ch->index;
+	int work_done;
 
 	priv->xstats.napi_poll++;
 
-	if (ch->has_tx) {
-		int done = stmmac_tx_clean(priv, work_rem, chan);
+	work_done = stmmac_rx(priv, budget, chan);
+	if (work_done < budget && napi_complete_done(napi, work_done))
+		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
+	return work_done;
+}
 
-		work_done += done;
-		work_rem -= done;
-	}
+static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget)
+{
+	struct stmmac_channel *ch =
+		container_of(napi, struct stmmac_channel, tx_napi);
+	struct stmmac_priv *priv = ch->priv_data;
+	struct stmmac_tx_queue *tx_q;
+	u32 chan = ch->index;
+	int work_done;
 
-	if (ch->has_rx) {
-		int done = stmmac_rx(priv, work_rem, chan);
+	priv->xstats.napi_poll++;
 
-		work_done += done;
-		work_rem -= done;
-	}
+	work_done = stmmac_tx_clean(priv, DMA_TX_SIZE, chan);
+	work_done = min(work_done, budget);
 
 	if (work_done < budget && napi_complete_done(napi, work_done))
 		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
 
+	/* Force transmission restart */
+	tx_q = &priv->tx_queue[chan];
+	if (tx_q->cur_tx != tx_q->dirty_tx) {
+		stmmac_enable_dma_transmission(priv, priv->ioaddr);
+		stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr,
+				       chan);
+	}
+
 	return work_done;
 }
 
@@ -3774,7 +3809,10 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 		ret = phy_mii_ioctl(dev->phydev, rq, cmd);
 		break;
 	case SIOCSHWTSTAMP:
-		ret = stmmac_hwtstamp_ioctl(dev, rq);
+		ret = stmmac_hwtstamp_set(dev, rq);
+		break;
+	case SIOCGHWTSTAMP:
+		ret = stmmac_hwtstamp_get(dev, rq);
 		break;
 	default:
 		break;
@@ -3881,7 +3919,7 @@ static void sysfs_display_ring(void *head, int size, int extend_desc,
 	}
 }
 
-static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v)
+static int stmmac_rings_status_show(struct seq_file *seq, void *v)
 {
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -3926,23 +3964,9 @@ static int stmmac_sysfs_ring_read(struct seq_file *seq, void *v)
 
 	return 0;
 }
+DEFINE_SHOW_ATTRIBUTE(stmmac_rings_status);
 
-static int stmmac_sysfs_ring_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, stmmac_sysfs_ring_read, inode->i_private);
-}
-
-/* Debugfs files, should appear in /sys/kernel/debug/stmmaceth/eth0 */
-
-static const struct file_operations stmmac_rings_status_fops = {
-	.owner = THIS_MODULE,
-	.open = stmmac_sysfs_ring_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
-static int stmmac_sysfs_dma_cap_read(struct seq_file *seq, void *v)
+static int stmmac_dma_cap_show(struct seq_file *seq, void *v)
 {
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
@@ -4005,19 +4029,7 @@ static int stmmac_sysfs_dma_cap_read(struct seq_file *seq, void *v)
 
 	return 0;
 }
-
-static int stmmac_sysfs_dma_cap_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, stmmac_sysfs_dma_cap_read, inode->i_private);
-}
-
-static const struct file_operations stmmac_dma_cap_fops = {
-	.owner = THIS_MODULE,
-	.open = stmmac_sysfs_dma_cap_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap);
 
 static int stmmac_init_fs(struct net_device *dev)
 {
@@ -4101,7 +4113,7 @@ static void stmmac_reset_subtask(struct stmmac_priv *priv)
 
 	set_bit(STMMAC_DOWN, &priv->state);
 	dev_close(priv->dev);
-	dev_open(priv->dev);
+	dev_open(priv->dev, NULL);
 	clear_bit(STMMAC_DOWN, &priv->state);
 	clear_bit(STMMAC_RESETING, &priv->state);
 	rtnl_unlock();
@@ -4194,6 +4206,18 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
 			return ret;
 	}
 
+	/* Rx Watchdog is available in the COREs newer than the 3.40.
+	 * In some case, for example on bugged HW this feature
+	 * has to be disable and this can be done by passing the
+	 * riwt_off field from the platform.
+	 */
+	if (((priv->synopsys_id >= DWMAC_CORE_3_50) ||
+	    (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) {
+		priv->use_riwt = 1;
+		dev_info(priv->device,
+			 "Enable RX Mitigation via HW Watchdog Timer\n");
+	}
+
 	return 0;
 }
 
@@ -4277,6 +4301,8 @@ int stmmac_dvr_probe(struct device *device,
 	if (ret)
 		goto error_hw_init;
 
+	stmmac_check_ether_addr(priv);
+
 	/* Configure real RX and TX queues */
 	netif_set_real_num_rx_queues(ndev, priv->plat->rx_queues_to_use);
 	netif_set_real_num_tx_queues(ndev, priv->plat->tx_queues_to_use);
@@ -4326,18 +4352,6 @@ int stmmac_dvr_probe(struct device *device,
 	if (flow_ctrl)
 		priv->flow_ctrl = FLOW_AUTO;	/* RX/TX pause on */
 
-	/* Rx Watchdog is available in the COREs newer than the 3.40.
-	 * In some case, for example on bugged HW this feature
-	 * has to be disable and this can be done by passing the
-	 * riwt_off field from the platform.
-	 */
-	if (((priv->synopsys_id >= DWMAC_CORE_3_50) ||
-	    (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) {
-		priv->use_riwt = 1;
-		dev_info(priv->device,
-			 "Enable RX Mitigation via HW Watchdog Timer\n");
-	}
-
 	/* Setup channels NAPI */
 	maxq = max(priv->plat->rx_queues_to_use, priv->plat->tx_queues_to_use);
 
@@ -4347,13 +4361,14 @@ int stmmac_dvr_probe(struct device *device,
 		ch->priv_data = priv;
 		ch->index = queue;
 
-		if (queue < priv->plat->rx_queues_to_use)
-			ch->has_rx = true;
-		if (queue < priv->plat->tx_queues_to_use)
-			ch->has_tx = true;
-
-		netif_napi_add(ndev, &ch->napi, stmmac_napi_poll,
-			       NAPI_POLL_WEIGHT);
+		if (queue < priv->plat->rx_queues_to_use) {
+			netif_napi_add(ndev, &ch->rx_napi, stmmac_napi_poll_rx,
+				       NAPI_POLL_WEIGHT);
+		}
+		if (queue < priv->plat->tx_queues_to_use) {
+			netif_napi_add(ndev, &ch->tx_napi, stmmac_napi_poll_tx,
+				       NAPI_POLL_WEIGHT);
+		}
 	}
 
 	mutex_init(&priv->lock);
@@ -4409,7 +4424,10 @@ error_mdio_register:
 	for (queue = 0; queue < maxq; queue++) {
 		struct stmmac_channel *ch = &priv->channel[queue];
 
-		netif_napi_del(&ch->napi);
+		if (queue < priv->plat->rx_queues_to_use)
+			netif_napi_del(&ch->rx_napi);
+		if (queue < priv->plat->tx_queues_to_use)
+			netif_napi_del(&ch->tx_napi);
 	}
 error_hw_init:
 	destroy_workqueue(priv->wq);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index c54a50dbd5ac..26db6aa002d1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -159,6 +159,12 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 		},
 		.driver_data = (void *)&galileo_stmmac_dmi_data,
 	},
+	/*
+	 * There are 2 types of SIMATIC IOT2000: IOT2020 and IOT2040.
+	 * The asset tag "6ES7647-0AA00-0YA2" is only for IOT2020 which
+	 * has only one pci network device while other asset tags are
+	 * for IOT2040 which has two.
+	 */
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
@@ -170,8 +176,6 @@ static const struct dmi_system_id quark_pci_dmi[] = {
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "SIMATIC IOT2000"),
-			DMI_EXACT_MATCH(DMI_BOARD_ASSET_TAG,
-					"6ES7647-0AA00-1YA2"),
 		},
 		.driver_data = (void *)&iot2040_stmmac_dmi_data,
 	},
@@ -299,7 +303,17 @@ static int stmmac_pci_probe(struct pci_dev *pdev,
  */
 static void stmmac_pci_remove(struct pci_dev *pdev)
 {
+	int i;
+
 	stmmac_dvr_remove(&pdev->dev);
+
+	for (i = 0; i <= PCI_STD_RESOURCE_END; i++) {
+		if (pci_resource_len(pdev, i) == 0)
+			continue;
+		pcim_iounmap_regions(pdev, BIT(i));
+		break;
+	}
+
 	pci_disable_device(pdev);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 2b800ce1d5bf..3031f2bf15d6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -408,6 +408,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 	/* Default to phy auto-detection */
 	plat->phy_addr = -1;
 
+	/* Get clk_csr from device tree */
+	of_property_read_u32(np, "clk_csr", &plat->clk_csr);
+
 	/* "snps,phy-addr" is not a standard property. Mark it as deprecated
 	 * and warn of its use. Remove this when phy node support is added.
 	 */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 2293e21f789f..cc60b3fb0892 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -105,7 +105,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts)
 	struct stmmac_priv *priv =
 	    container_of(ptp, struct stmmac_priv, ptp_clock_ops);
 	unsigned long flags;
-	u64 ns;
+	u64 ns = 0;
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
 	stmmac_get_systime(priv, priv->ptpaddr, &ns);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index ecccf895fd7e..e852821289cf 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -59,9 +59,14 @@
 #define	PTP_TCR_TSEVNTENA	BIT(14)
 /* Enable Snapshot for Messages Relevant to Master */
 #define	PTP_TCR_TSMSTRENA	BIT(15)
-/* Select PTP packets for Taking Snapshots */
+/* Select PTP packets for Taking Snapshots
+ * On gmac4 specifically:
+ * Enable SYNC, Pdelay_Req, Pdelay_Resp when TSEVNTENA is enabled.
+ * or
+ * Enable  SYNC, Follow_Up, Delay_Req, Delay_Resp, Pdelay_Req, Pdelay_Resp,
+ * Pdelay_Resp_Follow_Up if TSEVNTENA is disabled
+ */
 #define	PTP_TCR_SNAPTYPSEL_1	BIT(16)
-#define	PTP_GMAC4_TCR_SNAPTYPSEL_1	GENMASK(17, 16)
 /* Enable MAC address for PTP Frame Filtering */
 #define	PTP_TCR_TSENMACADDR	BIT(18)
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 531294f4978b..58ea18af9813 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -301,6 +301,8 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 	/* Queue 0 is not AVB capable */
 	if (queue <= 0 || queue >= tx_queues_count)
 		return -EINVAL;
+	if (!priv->dma_cap.av)
+		return -EOPNOTSUPP;
 	if (priv->speed != SPEED_100 && priv->speed != SPEED_1000)
 		return -EOPNOTSUPP;
 
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index 9020b084b953..6fc05c106afc 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -1,22 +1,9 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: GPL-2.0+
 /* cassini.c: Sun Microsystems Cassini(+) ethernet driver.
  *
  * Copyright (C) 2004 Sun Microsystems Inc.
  * Copyright (C) 2003 Adrian Sun (asun@darksunrising.com)
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * This driver uses the sungem driver (c) David Miller
  * (davem@redhat.com) as its basis.
  *
@@ -1911,7 +1898,7 @@ static inline void cas_tx_ringN(struct cas *cp, int ring, int limit)
 		cp->net_stats[ring].tx_packets++;
 		cp->net_stats[ring].tx_bytes += skb->len;
 		spin_unlock(&cp->stat_lock[ring]);
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 	}
 	cp->tx_old[ring] = entry;
 
diff --git a/drivers/net/ethernet/sun/cassini.h b/drivers/net/ethernet/sun/cassini.h
index 13f3860496a8..ae5f05f03f88 100644
--- a/drivers/net/ethernet/sun/cassini.h
+++ b/drivers/net/ethernet/sun/cassini.h
@@ -1,23 +1,10 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0+ */
 /* $Id: cassini.h,v 1.16 2004/08/17 21:15:16 zaumen Exp $
  * cassini.h: Definitions for Sun Microsystems Cassini(+) ethernet driver.
  *
  * Copyright (C) 2004 Sun Microsystems Inc.
  * Copyright (c) 2003 Adrian Sun (asun@darksunrising.com)
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- *
  * vendor id: 0x108E (Sun Microsystems, Inc.)
  * device id: 0xabba (Cassini)
  * revision ids: 0x01 = Cassini
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 9319d84bf49f..6f99437a6962 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -7464,6 +7464,7 @@ static int niu_add_ethtool_tcam_entry(struct niu *np,
 					class = CLASS_CODE_USER_PROG4;
 					break;
 				default:
+					class = CLASS_CODE_UNRECOG;
 					break;
 				}
 				ret = tcam_user_ip_class_set(np, class, 0,
@@ -8100,6 +8101,8 @@ static int niu_pci_vpd_scan_props(struct niu *np, u32 start, u32 end)
 		start += 3;
 
 		prop_len = niu_pci_eeprom_read(np, start + 4);
+		if (prop_len < 0)
+			return prop_len;
 		err = niu_pci_vpd_get_propname(np, start + 5, namebuf, 64);
 		if (err < 0)
 			return err;
@@ -8144,8 +8147,12 @@ static int niu_pci_vpd_scan_props(struct niu *np, u32 start, u32 end)
 			netif_printk(np, probe, KERN_DEBUG, np->dev,
 				     "VPD_SCAN: Reading in property [%s] len[%d]\n",
 				     namebuf, prop_len);
-			for (i = 0; i < prop_len; i++)
-				*prop_buf++ = niu_pci_eeprom_read(np, off + i);
+			for (i = 0; i < prop_len; i++) {
+				err = niu_pci_eeprom_read(np, off + i);
+				if (err >= 0)
+					*prop_buf = err;
+				++prop_buf;
+			}
 		}
 
 		start += len;
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 720b7ac77f3b..e9b757b03b56 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -781,7 +781,7 @@ static void bigmac_tx(struct bigmac *bp)
 
 		DTX(("skb(%p) ", skb));
 		bp->tx_skbs[elem] = NULL;
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 
 		elem = NEXT_TX(elem);
 	}
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index b9221fc1674d..3e7631160384 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -2760,7 +2760,7 @@ static void get_gem_mac_nonobp(struct pci_dev *pdev, unsigned char *dev_addr)
 	void __iomem *p = pci_map_rom(pdev, &size);
 
 	if (p) {
-			int found;
+		int found;
 
 		found = readb(p) == 0x55 &&
 			readb(p + 1) == 0xaa &&
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 863fd602fd33..d007dfeba5c3 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -1962,7 +1962,7 @@ static void happy_meal_tx(struct happy_meal *hp)
 			this = &txbase[elem];
 		}
 
-		dev_kfree_skb_irq(skb);
+		dev_consume_skb_irq(skb);
 		dev->stats.tx_packets++;
 	}
 	hp->tx_old = elem;
@@ -2691,7 +2691,7 @@ static int happy_meal_sbus_probe_one(struct platform_device *op, int is_qfe)
 	sbus_dp = op->dev.parent->of_node;
 
 	/* We can match PCI devices too, do not accept those here. */
-	if (strcmp(sbus_dp->name, "sbus") && strcmp(sbus_dp->name, "sbi"))
+	if (!of_node_name_eq(sbus_dp, "sbus") && !of_node_name_eq(sbus_dp, "sbi"))
 		return err;
 
 	if (is_qfe) {
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index dc966ddb6d81..b24c11187017 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1739,7 +1739,7 @@ static void bdx_tx_cleanup(struct bdx_priv *priv)
 		tx_level -= db->rptr->len;	/* '-' koz len is negative */
 
 		/* now should come skb pointer - free it */
-		dev_kfree_skb_irq(db->rptr->addr.skb);
+		dev_consume_skb_irq(db->rptr->addr.skb);
 		bdx_tx_db_inc_rptr(db);
 	}
 
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index f932923f7d56..8b21b40a9fe5 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -49,10 +49,11 @@ config TI_DAVINCI_CPDMA
 	  will be called davinci_cpdma.  This is recommended.
 
 config TI_CPSW_PHY_SEL
-	bool
+	bool "TI CPSW Phy mode Selection (DEPRECATED)"
+	default n
 	---help---
 	  This driver supports configuring of the phy mode connected to
-	  the CPSW.
+	  the CPSW. DEPRECATED: use PHY_TI_GMII_SEL.
 
 config TI_CPSW_ALE
 	tristate "TI CPSW ALE Support"
@@ -64,7 +65,6 @@ config TI_CPSW
 	depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
 	select TI_DAVINCI_CPDMA
 	select TI_DAVINCI_MDIO
-	select TI_CPSW_PHY_SEL
 	select TI_CPSW_ALE
 	select MFD_SYSCON
 	select REGMAP
@@ -121,7 +121,8 @@ config TLAN
 
 	  Devices currently supported by this driver are Compaq Netelligent,
 	  Compaq NetFlex and Olicom cards.  Please read the file
-	  <file:Documentation/networking/tlan.txt> for more details.
+	  <file:Documentation/networking/device_drivers/ti/tlan.txt>
+	  for more details.
 
 	  To compile this driver as a module, choose M here. The module
 	  will be called tlan.
diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c
index 9b8a30bf939b..e2d47b24a869 100644
--- a/drivers/net/ethernet/ti/cpmac.c
+++ b/drivers/net/ethernet/ti/cpmac.c
@@ -608,7 +608,7 @@ static void cpmac_end_xmit(struct net_device *dev, int queue)
 			netdev_dbg(dev, "sent 0x%p, len=%d\n",
 				   desc->skb, desc->skb->len);
 
-		dev_kfree_skb_irq(desc->skb);
+		dev_consume_skb_irq(desc->skb);
 		desc->skb = NULL;
 		if (__netif_subqueue_stopped(dev, queue))
 			netif_wake_subqueue(dev, queue);
@@ -991,7 +991,6 @@ static int cpmac_open(struct net_device *dev)
 	cpmac_hw_start(dev);
 
 	napi_enable(&priv->napi);
-	dev->phydev->state = PHY_CHANGELINK;
 	phy_start(dev->phydev);
 
 	return 0;
diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c
index 396e1cd10667..fec275e2208d 100644
--- a/drivers/net/ethernet/ti/cpsw-phy-sel.c
+++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c
@@ -78,7 +78,7 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv,
 	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
-	};
+	}
 
 	mask = GMII_SEL_MODE_MASK << (slave * 2) | BIT(slave + 6);
 	mask |= BIT(slave + 4);
@@ -133,7 +133,7 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv,
 	case PHY_INTERFACE_MODE_MII:
 		mode = AM33XX_GMII_SEL_MODE_MII;
 		break;
-	};
+	}
 
 	switch (slave) {
 	case 0:
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 500f7ed8c58c..a591583d120e 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -26,6 +26,7 @@
 #include <linux/netdevice.h>
 #include <linux/net_tstamp.h>
 #include <linux/phy.h>
+#include <linux/phy/phy.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
 #include <linux/pm_runtime.h>
@@ -283,7 +284,7 @@ struct cpsw_ss_regs {
 
 #define CTRL_V2_TS_BITS \
 	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
-	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN)
+	 TS_TTL_NONZERO  | TS_ANNEX_D_EN | TS_LTYPE1_EN | VLAN_LTYPE1_EN)
 
 #define CTRL_V2_ALL_TS_MASK (CTRL_V2_TS_BITS | TS_TX_EN | TS_RX_EN)
 #define CTRL_V2_TX_TS_BITS  (CTRL_V2_TS_BITS | TS_TX_EN)
@@ -293,7 +294,7 @@ struct cpsw_ss_regs {
 #define CTRL_V3_TS_BITS \
 	(TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
 	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
-	 TS_LTYPE1_EN)
+	 TS_LTYPE1_EN | VLAN_LTYPE1_EN)
 
 #define CTRL_V3_ALL_TS_MASK (CTRL_V3_TS_BITS | TS_TX_EN | TS_RX_EN)
 #define CTRL_V3_TX_TS_BITS  (CTRL_V3_TS_BITS | TS_TX_EN)
@@ -387,6 +388,7 @@ struct cpsw_slave_data {
 	int		phy_if;
 	u8		mac_addr[ETH_ALEN];
 	u16		dual_emac_res_vlan;	/* Reserved VLAN for DualEMAC */
+	struct phy	*ifphy;
 };
 
 struct cpsw_platform_data {
@@ -466,6 +468,8 @@ struct cpsw_priv {
 	bool				mqprio_hw;
 	int				fifo_bw[CPSW_TC_NUM];
 	int				shp_cfg_speed;
+	int				tx_ts_enabled;
+	int				rx_ts_enabled;
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -565,26 +569,14 @@ static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
 				(func)(slave++, ##arg);			\
 	} while (0)
 
+static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
+				    __be16 proto, u16 vid);
+
 static inline int cpsw_get_slave_port(u32 slave_num)
 {
 	return slave_num + 1;
 }
 
-static void cpsw_add_mcast(struct cpsw_priv *priv, const u8 *addr)
-{
-	struct cpsw_common *cpsw = priv->cpsw;
-
-	if (cpsw->data.dual_emac) {
-		struct cpsw_slave *slave = cpsw->slaves + priv->emac_port;
-
-		cpsw_ale_add_mcast(cpsw->ale, addr, ALE_PORT_HOST,
-				   ALE_VLAN, slave->port_vlan, 0);
-		return;
-	}
-
-	cpsw_ale_add_mcast(cpsw->ale, addr, ALE_ALL_PORTS, 0, 0, 0);
-}
-
 static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -640,7 +632,7 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 
 			/* Clear all mcast from ALE */
 			cpsw_ale_flush_multicast(ale, ALE_ALL_PORTS, -1);
-			__dev_mc_unsync(ndev, NULL);
+			__hw_addr_ref_unsync_dev(&ndev->mc, ndev, NULL);
 
 			/* Flood All Unicast Packets to Host port */
 			cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1);
@@ -661,29 +653,148 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 	}
 }
 
-static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr)
+struct addr_sync_ctx {
+	struct net_device *ndev;
+	const u8 *addr;		/* address to be synched */
+	int consumed;		/* number of address instances */
+	int flush;		/* flush flag */
+};
+
+/**
+ * cpsw_set_mc - adds multicast entry to the table if it's not added or deletes
+ * if it's not deleted
+ * @ndev: device to sync
+ * @addr: address to be added or deleted
+ * @vid: vlan id, if vid < 0 set/unset address for real device
+ * @add: add address if the flag is set or remove otherwise
+ */
+static int cpsw_set_mc(struct net_device *ndev, const u8 *addr,
+		       int vid, int add)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int mask, flags, ret;
+
+	if (vid < 0) {
+		if (cpsw->data.dual_emac)
+			vid = cpsw->slaves[priv->emac_port].port_vlan;
+		else
+			vid = 0;
+	}
+
+	mask = cpsw->data.dual_emac ? ALE_PORT_HOST : ALE_ALL_PORTS;
+	flags = vid ? ALE_VLAN : 0;
+
+	if (add)
+		ret = cpsw_ale_add_mcast(cpsw->ale, addr, mask, flags, vid, 0);
+	else
+		ret = cpsw_ale_del_mcast(cpsw->ale, addr, 0, flags, vid);
+
+	return ret;
+}
+
+static int cpsw_update_vlan_mc(struct net_device *vdev, int vid, void *ctx)
+{
+	struct addr_sync_ctx *sync_ctx = ctx;
+	struct netdev_hw_addr *ha;
+	int found = 0, ret = 0;
+
+	if (!vdev || !(vdev->flags & IFF_UP))
+		return 0;
+
+	/* vlan address is relevant if its sync_cnt != 0 */
+	netdev_for_each_mc_addr(ha, vdev) {
+		if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
+			found = ha->sync_cnt;
+			break;
+		}
+	}
+
+	if (found)
+		sync_ctx->consumed++;
+
+	if (sync_ctx->flush) {
+		if (!found)
+			cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
+		return 0;
+	}
+
+	if (found)
+		ret = cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 1);
+
+	return ret;
+}
+
+static int cpsw_add_mc_addr(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+	int ret;
+
+	sync_ctx.consumed = 0;
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.flush = 0;
+
+	ret = vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed < num && !ret)
+		ret = cpsw_set_mc(ndev, addr, -1, 1);
+
+	return ret;
+}
+
+static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+
+	sync_ctx.consumed = 0;
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.flush = 1;
+
+	vlan_for_each(ndev, cpsw_update_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed == num)
+		cpsw_set_mc(ndev, addr, -1, 0);
 
-	cpsw_add_mcast(priv, addr);
 	return 0;
 }
 
-static int cpsw_del_mc_addr(struct net_device *ndev, const u8 *addr)
+static int cpsw_purge_vlan_mc(struct net_device *vdev, int vid, void *ctx)
 {
-	struct cpsw_priv *priv = netdev_priv(ndev);
-	struct cpsw_common *cpsw = priv->cpsw;
-	int vid, flags;
+	struct addr_sync_ctx *sync_ctx = ctx;
+	struct netdev_hw_addr *ha;
+	int found = 0;
 
-	if (cpsw->data.dual_emac) {
-		vid = cpsw->slaves[priv->emac_port].port_vlan;
-		flags = ALE_VLAN;
-	} else {
-		vid = 0;
-		flags = 0;
+	if (!vdev || !(vdev->flags & IFF_UP))
+		return 0;
+
+	/* vlan address is relevant if its sync_cnt != 0 */
+	netdev_for_each_mc_addr(ha, vdev) {
+		if (ether_addr_equal(ha->addr, sync_ctx->addr)) {
+			found = ha->sync_cnt;
+			break;
+		}
 	}
 
-	cpsw_ale_del_mcast(cpsw->ale, addr, 0, flags, vid);
+	if (!found)
+		return 0;
+
+	sync_ctx->consumed++;
+	cpsw_set_mc(sync_ctx->ndev, sync_ctx->addr, vid, 0);
+	return 0;
+}
+
+static int cpsw_purge_all_mc(struct net_device *ndev, const u8 *addr, int num)
+{
+	struct addr_sync_ctx sync_ctx;
+
+	sync_ctx.addr = addr;
+	sync_ctx.ndev = ndev;
+	sync_ctx.consumed = 0;
+
+	vlan_for_each(ndev, cpsw_purge_vlan_mc, &sync_ctx);
+	if (sync_ctx.consumed < num)
+		cpsw_set_mc(ndev, addr, -1, 0);
+
 	return 0;
 }
 
@@ -704,7 +815,9 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 	/* Restore allmulti on vlans if necessary */
 	cpsw_ale_set_allmulti(cpsw->ale, ndev->flags & IFF_ALLMULTI);
 
-	__dev_mc_sync(ndev, cpsw_add_mc_addr, cpsw_del_mc_addr);
+	/* add/remove mcast address either for real netdev or for vlan */
+	__hw_addr_ref_sync_dev(&ndev->mc, ndev, cpsw_add_mc_addr,
+			       cpsw_del_mc_addr);
 }
 
 static void cpsw_intr_enable(struct cpsw_common *cpsw)
@@ -796,6 +909,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	struct net_device	*ndev = skb->dev;
 	int			ret = 0, port;
 	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
+	struct cpsw_priv	*priv;
 
 	if (cpsw->data.dual_emac) {
 		port = CPDMA_RX_SOURCE_PORT(status);
@@ -830,7 +944,9 @@ static void cpsw_rx_handler(void *token, int len, int status)
 		skb_put(skb, len);
 		if (status & CPDMA_RX_VLAN_ENCAP)
 			cpsw_rx_vlan_encap(skb);
-		cpts_rx_timestamp(cpsw->cpts, skb);
+		priv = netdev_priv(ndev);
+		if (priv->rx_ts_enabled)
+			cpts_rx_timestamp(cpsw->cpts, skb);
 		skb->protocol = eth_type_trans(skb, ndev);
 		netif_receive_skb(skb);
 		ndev->stats.rx_bytes += len;
@@ -1510,7 +1626,12 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
 	phy_start(slave->phy);
 
 	/* Configure GMII_SEL register */
-	cpsw_phy_sel(cpsw->dev, slave->phy->interface, slave->slave_num);
+	if (!IS_ERR(slave->data->ifphy))
+		phy_set_mode_ext(slave->data->ifphy, PHY_MODE_ETHERNET,
+				 slave->data->phy_if);
+	else
+		cpsw_phy_sel(cpsw->dev, slave->phy->interface,
+			     slave->slave_num);
 }
 
 static inline void cpsw_add_default_vlan(struct cpsw_priv *priv)
@@ -1845,9 +1966,23 @@ static void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv)
 	slave_write(slave, tx_prio_map, tx_prio_rg);
 }
 
+static int cpsw_restore_vlans(struct net_device *vdev, int vid, void *arg)
+{
+	struct cpsw_priv *priv = arg;
+
+	if (!vdev)
+		return 0;
+
+	cpsw_ndo_vlan_rx_add_vid(priv->ndev, 0, vid);
+	return 0;
+}
+
 /* restore resources after port reset */
 static void cpsw_restore(struct cpsw_priv *priv)
 {
+	/* restore vlan configurations */
+	vlan_for_each(priv->ndev, cpsw_restore_vlans, priv);
+
 	/* restore MQPRIO offload */
 	for_each_slave(priv, cpsw_mqprio_resume, priv);
 
@@ -1964,7 +2099,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
 	struct cpsw_common *cpsw = priv->cpsw;
 
 	cpsw_info(priv, ifdown, "shutting down cpsw device\n");
-	__dev_mc_unsync(priv->ndev, cpsw_del_mc_addr);
+	__hw_addr_ref_unsync_dev(&ndev->mc, ndev, cpsw_purge_all_mc);
 	netif_tx_stop_all_queues(priv->ndev);
 	netif_carrier_off(priv->ndev);
 
@@ -2003,7 +2138,7 @@ static netdev_tx_t cpsw_ndo_start_xmit(struct sk_buff *skb,
 	}
 
 	if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
-	    cpts_is_tx_enabled(cpts) && cpts_can_timestamp(cpts, skb))
+	    priv->tx_ts_enabled && cpts_can_timestamp(cpts, skb))
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
 	q_idx = skb_get_queue_mapping(skb);
@@ -2047,13 +2182,13 @@ fail:
 
 #if IS_ENABLED(CONFIG_TI_CPTS)
 
-static void cpsw_hwtstamp_v1(struct cpsw_common *cpsw)
+static void cpsw_hwtstamp_v1(struct cpsw_priv *priv)
 {
+	struct cpsw_common *cpsw = priv->cpsw;
 	struct cpsw_slave *slave = &cpsw->slaves[cpsw->data.active_slave];
 	u32 ts_en, seq_id;
 
-	if (!cpts_is_tx_enabled(cpsw->cpts) &&
-	    !cpts_is_rx_enabled(cpsw->cpts)) {
+	if (!priv->tx_ts_enabled && !priv->rx_ts_enabled) {
 		slave_write(slave, 0, CPSW1_TS_CTL);
 		return;
 	}
@@ -2061,10 +2196,10 @@ static void cpsw_hwtstamp_v1(struct cpsw_common *cpsw)
 	seq_id = (30 << CPSW_V1_SEQ_ID_OFS_SHIFT) | ETH_P_1588;
 	ts_en = EVENT_MSG_BITS << CPSW_V1_MSG_TYPE_OFS;
 
-	if (cpts_is_tx_enabled(cpsw->cpts))
+	if (priv->tx_ts_enabled)
 		ts_en |= CPSW_V1_TS_TX_EN;
 
-	if (cpts_is_rx_enabled(cpsw->cpts))
+	if (priv->rx_ts_enabled)
 		ts_en |= CPSW_V1_TS_RX_EN;
 
 	slave_write(slave, ts_en, CPSW1_TS_CTL);
@@ -2084,20 +2219,20 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 	case CPSW_VERSION_2:
 		ctrl &= ~CTRL_V2_ALL_TS_MASK;
 
-		if (cpts_is_tx_enabled(cpsw->cpts))
+		if (priv->tx_ts_enabled)
 			ctrl |= CTRL_V2_TX_TS_BITS;
 
-		if (cpts_is_rx_enabled(cpsw->cpts))
+		if (priv->rx_ts_enabled)
 			ctrl |= CTRL_V2_RX_TS_BITS;
 		break;
 	case CPSW_VERSION_3:
 	default:
 		ctrl &= ~CTRL_V3_ALL_TS_MASK;
 
-		if (cpts_is_tx_enabled(cpsw->cpts))
+		if (priv->tx_ts_enabled)
 			ctrl |= CTRL_V3_TX_TS_BITS;
 
-		if (cpts_is_rx_enabled(cpsw->cpts))
+		if (priv->rx_ts_enabled)
 			ctrl |= CTRL_V3_RX_TS_BITS;
 		break;
 	}
@@ -2107,6 +2242,7 @@ static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
 	slave_write(slave, mtype, CPSW2_TS_SEQ_MTYPE);
 	slave_write(slave, ctrl, CPSW2_CONTROL);
 	writel_relaxed(ETH_P_1588, &cpsw->regs->ts_ltype);
+	writel_relaxed(ETH_P_8021Q, &cpsw->regs->vlan_ltype);
 }
 
 static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
@@ -2114,7 +2250,6 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	struct cpsw_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config cfg;
 	struct cpsw_common *cpsw = priv->cpsw;
-	struct cpts *cpts = cpsw->cpts;
 
 	if (cpsw->version != CPSW_VERSION_1 &&
 	    cpsw->version != CPSW_VERSION_2 &&
@@ -2133,7 +2268,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 
 	switch (cfg.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		cpts_rx_enable(cpts, 0);
+		priv->rx_ts_enabled = 0;
 		break;
 	case HWTSTAMP_FILTER_ALL:
 	case HWTSTAMP_FILTER_NTP_ALL:
@@ -2141,7 +2276,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V1_L4_EVENT);
+		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -2153,18 +2288,18 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V2_EVENT);
+		priv->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
 		return -ERANGE;
 	}
 
-	cpts_tx_enable(cpts, cfg.tx_type == HWTSTAMP_TX_ON);
+	priv->tx_ts_enabled = cfg.tx_type == HWTSTAMP_TX_ON;
 
 	switch (cpsw->version) {
 	case CPSW_VERSION_1:
-		cpsw_hwtstamp_v1(cpsw);
+		cpsw_hwtstamp_v1(priv);
 		break;
 	case CPSW_VERSION_2:
 	case CPSW_VERSION_3:
@@ -2180,7 +2315,7 @@ static int cpsw_hwtstamp_set(struct net_device *dev, struct ifreq *ifr)
 static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(dev);
-	struct cpts *cpts = cpsw->cpts;
+	struct cpsw_priv *priv = netdev_priv(dev);
 	struct hwtstamp_config cfg;
 
 	if (cpsw->version != CPSW_VERSION_1 &&
@@ -2189,10 +2324,8 @@ static int cpsw_hwtstamp_get(struct net_device *dev, struct ifreq *ifr)
 		return -EOPNOTSUPP;
 
 	cfg.flags = 0;
-	cfg.tx_type = cpts_is_tx_enabled(cpts) ?
-		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg.rx_filter = (cpts_is_rx_enabled(cpts) ?
-			 cpts->rx_enable : HWTSTAMP_FILTER_NONE);
+	cfg.tx_type = priv->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg.rx_filter = priv->rx_ts_enabled;
 
 	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
 }
@@ -2415,6 +2548,7 @@ static int cpsw_ndo_vlan_rx_kill_vid(struct net_device *ndev,
 				  HOST_PORT_NUM, ALE_VLAN, vid);
 	ret |= cpsw_ale_del_mcast(cpsw->ale, priv->ndev->broadcast,
 				  0, ALE_VLAN, vid);
+	ret |= cpsw_ale_flush_multicast(cpsw->ale, 0, vid);
 err:
 	pm_runtime_put(cpsw->dev);
 	return ret;
@@ -3144,9 +3278,19 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data,
 		const __be32 *parp;
 
 		/* This is no slave child node, continue */
-		if (strcmp(slave_node->name, "slave"))
+		if (!of_node_name_eq(slave_node, "slave"))
 			continue;
 
+		slave_data->ifphy = devm_of_phy_get(&pdev->dev, slave_node,
+						    NULL);
+		if (!IS_ENABLED(CONFIG_TI_CPSW_PHY_SEL) &&
+		    IS_ERR(slave_data->ifphy)) {
+			ret = PTR_ERR(slave_data->ifphy);
+			dev_err(&pdev->dev,
+				"%d: Error retrieving port phy: %d\n", i, ret);
+			return ret;
+		}
+
 		slave_data->phy_node = of_parse_phandle(slave_node,
 							"phy-handle", 0);
 		parp = of_get_property(slave_node, "phy_id", &lenp);
@@ -3240,7 +3384,7 @@ static void cpsw_remove_dt(struct platform_device *pdev)
 	for_each_available_child_of_node(node, slave_node) {
 		struct cpsw_slave_data *slave_data = &data->slave_data[i];
 
-		if (strcmp(slave_node->name, "slave"))
+		if (!of_node_name_eq(slave_node, "slave"))
 			continue;
 
 		if (of_phy_is_fixed_link(slave_node))
diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h
index cf111db3dc27..907e05fc22e4 100644
--- a/drivers/net/ethernet/ti/cpsw.h
+++ b/drivers/net/ethernet/ti/cpsw.h
@@ -21,7 +21,13 @@
 			 ((mac)[2] << 16) | ((mac)[3] << 24))
 #define mac_lo(mac)	(((mac)[4] << 0) | ((mac)[5] << 8))
 
+#if IS_ENABLED(CONFIG_TI_CPSW_PHY_SEL)
 void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave);
+#else
+static inline
+void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave)
+{}
+#endif
 int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr);
 
 #endif /* __CPSW_H__ */
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index b96b93c686bf..2a9ba4acd7fa 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -86,6 +86,25 @@ static int cpts_purge_events(struct cpts *cpts)
 	return removed ? 0 : -1;
 }
 
+static void cpts_purge_txq(struct cpts *cpts)
+{
+	struct cpts_skb_cb_data *skb_cb;
+	struct sk_buff *skb, *tmp;
+	int removed = 0;
+
+	skb_queue_walk_safe(&cpts->txq, skb, tmp) {
+		skb_cb = (struct cpts_skb_cb_data *)skb->cb;
+		if (time_after(jiffies, skb_cb->tmo)) {
+			__skb_unlink(skb, &cpts->txq);
+			dev_consume_skb_any(skb);
+			++removed;
+		}
+	}
+
+	if (removed)
+		dev_dbg(cpts->dev, "txq cleaned up %d\n", removed);
+}
+
 static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 {
 	struct sk_buff *skb, *tmp;
@@ -119,9 +138,7 @@ static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 
 		if (time_after(jiffies, skb_cb->tmo)) {
 			/* timeout any expired skbs over 1s */
-			dev_dbg(cpts->dev,
-				"expiring tx timestamp mtype %u seqid %04x\n",
-				mtype, seqid);
+			dev_dbg(cpts->dev, "expiring tx timestamp from txq\n");
 			__skb_unlink(skb, &cpts->txq);
 			dev_consume_skb_any(skb);
 		}
@@ -294,8 +311,11 @@ static long cpts_overflow_check(struct ptp_clock_info *ptp)
 	spin_lock_irqsave(&cpts->lock, flags);
 	ts = ns_to_timespec64(timecounter_read(&cpts->tc));
 
-	if (!skb_queue_empty(&cpts->txq))
-		delay = CPTS_SKB_TX_WORK_TIMEOUT;
+	if (!skb_queue_empty(&cpts->txq)) {
+		cpts_purge_txq(cpts);
+		if (!skb_queue_empty(&cpts->txq))
+			delay = CPTS_SKB_TX_WORK_TIMEOUT;
+	}
 	spin_unlock_irqrestore(&cpts->lock, flags);
 
 	pr_debug("cpts overflow check at %lld.%09ld\n",
@@ -410,8 +430,6 @@ void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb)
 	u64 ns;
 	struct skb_shared_hwtstamps *ssh;
 
-	if (!cpts->rx_enable)
-		return;
 	ns = cpts_find_ts(cpts, skb, CPTS_EV_RX);
 	if (!ns)
 		return;
@@ -572,7 +590,9 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 		return ERR_CAST(cpts->refclk);
 	}
 
-	clk_prepare(cpts->refclk);
+	ret = clk_prepare(cpts->refclk);
+	if (ret)
+		return ERR_PTR(ret);
 
 	cpts->cc.read = cpts_systim_read;
 	cpts->cc.mask = CLOCKSOURCE_MASK(32);
diff --git a/drivers/net/ethernet/ti/cpts.h b/drivers/net/ethernet/ti/cpts.h
index 73d73faf0f38..d2c7decd59b6 100644
--- a/drivers/net/ethernet/ti/cpts.h
+++ b/drivers/net/ethernet/ti/cpts.h
@@ -136,26 +136,6 @@ struct cpts *cpts_create(struct device *dev, void __iomem *regs,
 			 struct device_node *node);
 void cpts_release(struct cpts *cpts);
 
-static inline void cpts_rx_enable(struct cpts *cpts, int enable)
-{
-	cpts->rx_enable = enable;
-}
-
-static inline bool cpts_is_rx_enabled(struct cpts *cpts)
-{
-	return !!cpts->rx_enable;
-}
-
-static inline void cpts_tx_enable(struct cpts *cpts, int enable)
-{
-	cpts->tx_enable = enable;
-}
-
-static inline bool cpts_is_tx_enabled(struct cpts *cpts)
-{
-	return !!cpts->tx_enable;
-}
-
 static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
 	unsigned int class = ptp_classify_raw(skb);
@@ -197,24 +177,6 @@ static inline void cpts_unregister(struct cpts *cpts)
 {
 }
 
-static inline void cpts_rx_enable(struct cpts *cpts, int enable)
-{
-}
-
-static inline bool cpts_is_rx_enabled(struct cpts *cpts)
-{
-	return false;
-}
-
-static inline void cpts_tx_enable(struct cpts *cpts, int enable)
-{
-}
-
-static inline bool cpts_is_tx_enabled(struct cpts *cpts)
-{
-	return false;
-}
-
 static inline bool cpts_can_timestamp(struct cpts *cpts, struct sk_buff *skb)
 {
 	return false;
diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c
index 9153db120352..57450b174fc4 100644
--- a/drivers/net/ethernet/ti/davinci_emac.c
+++ b/drivers/net/ethernet/ti/davinci_emac.c
@@ -1912,11 +1912,15 @@ static int davinci_emac_probe(struct platform_device *pdev)
 		ether_addr_copy(ndev->dev_addr, priv->mac_addr);
 
 	if (!is_valid_ether_addr(priv->mac_addr)) {
-		/* Use random MAC if none passed */
-		eth_hw_addr_random(ndev);
-		memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len);
-		dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
-							priv->mac_addr);
+		/* Try nvmem if MAC wasn't passed over pdata or DT. */
+		rc = nvmem_get_mac_address(&pdev->dev, priv->mac_addr);
+		if (rc) {
+			/* Use random MAC if still none obtained. */
+			eth_hw_addr_random(ndev);
+			memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len);
+			dev_warn(&pdev->dev, "using random MAC addr: %pM\n",
+				 priv->mac_addr);
+		}
 	}
 
 	ndev->netdev_ops = &emac_netdev_ops;
@@ -2025,7 +2029,6 @@ static const struct dev_pm_ops davinci_emac_pm_ops = {
 	.resume		= davinci_emac_resume,
 };
 
-#if IS_ENABLED(CONFIG_OF)
 static const struct emac_platform_data am3517_emac_data = {
 	.version		= EMAC_VERSION_2,
 	.hw_ram_addr		= 0x01e20000,
@@ -2042,14 +2045,13 @@ static const struct of_device_id davinci_emac_of_match[] = {
 	{},
 };
 MODULE_DEVICE_TABLE(of, davinci_emac_of_match);
-#endif
 
 /* davinci_emac_driver: EMAC platform driver structure */
 static struct platform_driver davinci_emac_driver = {
 	.driver = {
 		.name	 = "davinci_emac",
 		.pm	 = &davinci_emac_pm_ops,
-		.of_match_table = of_match_ptr(davinci_emac_of_match),
+		.of_match_table = davinci_emac_of_match,
 	},
 	.probe = davinci_emac_probe,
 	.remove = davinci_emac_remove,
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 1f612268c998..d847f672a705 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -259,7 +259,7 @@ static int netcp_module_probe(struct netcp_device *netcp_device,
 		const char *name;
 		char node_name[32];
 
-		if (of_property_read_string(node, "label", &name) < 0) {
+		if (of_property_read_string(child, "label", &name) < 0) {
 			snprintf(node_name, sizeof(node_name), "%pOFn", child);
 			name = node_name;
 		}
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 0397ccb6597e..0a920c5936b2 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -763,6 +763,8 @@ struct gbe_priv {
 
 	int                             cpts_registered;
 	struct cpts                     *cpts;
+	int				rx_ts_enabled;
+	int				tx_ts_enabled;
 };
 
 struct gbe_intf {
@@ -2564,7 +2566,7 @@ static int gbe_txtstamp_mark_pkt(struct gbe_intf *gbe_intf,
 	struct gbe_priv *gbe_dev = gbe_intf->gbe_dev;
 
 	if (!(skb_shinfo(p_info->skb)->tx_flags & SKBTX_HW_TSTAMP) ||
-	    !cpts_is_tx_enabled(gbe_dev->cpts))
+	    !gbe_dev->tx_ts_enabled)
 		return 0;
 
 	/* If phy has the txtstamp api, assume it will do it.
@@ -2598,7 +2600,9 @@ static int gbe_rxtstamp(struct gbe_intf *gbe_intf, struct netcp_packet *p_info)
 		return 0;
 	}
 
-	cpts_rx_timestamp(gbe_dev->cpts, p_info->skb);
+	if (gbe_dev->rx_ts_enabled)
+		cpts_rx_timestamp(gbe_dev->cpts, p_info->skb);
+
 	p_info->rxtstamp_complete = true;
 
 	return 0;
@@ -2614,10 +2618,8 @@ static int gbe_hwtstamp_get(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 		return -EOPNOTSUPP;
 
 	cfg.flags = 0;
-	cfg.tx_type = cpts_is_tx_enabled(cpts) ?
-		      HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
-	cfg.rx_filter = (cpts_is_rx_enabled(cpts) ?
-			 cpts->rx_enable : HWTSTAMP_FILTER_NONE);
+	cfg.tx_type = gbe_dev->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
+	cfg.rx_filter = gbe_dev->rx_ts_enabled;
 
 	return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
 }
@@ -2628,8 +2630,8 @@ static void gbe_hwtstamp(struct gbe_intf *gbe_intf)
 	struct gbe_slave *slave = gbe_intf->slave;
 	u32 ts_en, seq_id, ctl;
 
-	if (!cpts_is_rx_enabled(gbe_dev->cpts) &&
-	    !cpts_is_tx_enabled(gbe_dev->cpts)) {
+	if (!gbe_dev->rx_ts_enabled &&
+	    !gbe_dev->tx_ts_enabled) {
 		writel(0, GBE_REG_ADDR(slave, port_regs, ts_ctl));
 		return;
 	}
@@ -2641,10 +2643,10 @@ static void gbe_hwtstamp(struct gbe_intf *gbe_intf)
 		(slave->ts_ctl.uni ?  TS_UNI_EN :
 			slave->ts_ctl.maddr_map << TS_CTL_MADDR_SHIFT);
 
-	if (cpts_is_tx_enabled(gbe_dev->cpts))
+	if (gbe_dev->tx_ts_enabled)
 		ts_en |= (TS_TX_ANX_ALL_EN | TS_TX_VLAN_LT1_EN);
 
-	if (cpts_is_rx_enabled(gbe_dev->cpts))
+	if (gbe_dev->rx_ts_enabled)
 		ts_en |= (TS_RX_ANX_ALL_EN | TS_RX_VLAN_LT1_EN);
 
 	writel(ts_en,  GBE_REG_ADDR(slave, port_regs, ts_ctl));
@@ -2670,10 +2672,10 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 
 	switch (cfg.tx_type) {
 	case HWTSTAMP_TX_OFF:
-		cpts_tx_enable(cpts, 0);
+		gbe_dev->tx_ts_enabled = 0;
 		break;
 	case HWTSTAMP_TX_ON:
-		cpts_tx_enable(cpts, 1);
+		gbe_dev->tx_ts_enabled = 1;
 		break;
 	default:
 		return -ERANGE;
@@ -2681,12 +2683,12 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 
 	switch (cfg.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		cpts_rx_enable(cpts, 0);
+		gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_NONE;
 		break;
 	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
 	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
 	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V1_L4_EVENT);
+		gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 		break;
 	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
@@ -2698,7 +2700,7 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr)
 	case HWTSTAMP_FILTER_PTP_V2_EVENT:
 	case HWTSTAMP_FILTER_PTP_V2_SYNC:
 	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
-		cpts_rx_enable(cpts, HWTSTAMP_FILTER_PTP_V2_EVENT);
+		gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 		break;
 	default:
@@ -3621,7 +3623,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		return -EINVAL;
 	}
 
-	if (!strcmp(node->name, "gbe")) {
+	if (of_node_name_eq(node, "gbe")) {
 		ret = get_gbe_resource_version(gbe_dev, node);
 		if (ret)
 			return ret;
@@ -3635,7 +3637,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 		else
 			ret = -ENODEV;
 
-	} else if (!strcmp(node->name, "xgbe")) {
+	} else if (of_node_name_eq(node, "xgbe")) {
 		ret = set_xgbe_ethss10_priv(gbe_dev, node);
 		if (ret)
 			return ret;
@@ -3655,12 +3657,16 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev,
 
 	ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
 				gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
-	if (ret)
+	if (ret) {
+		of_node_put(interfaces);
 		return ret;
+	}
 
 	ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
-	if (ret)
+	if (ret) {
+		of_node_put(interfaces);
 		return ret;
+	}
 
 	/* Create network interfaces */
 	INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index 93d142867c2a..b4ab1a5f6cd0 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -69,7 +69,9 @@ MODULE_AUTHOR("Maintainer: Samuel Chessman <chessman@tux.org>");
 MODULE_DESCRIPTION("Driver for TI ThunderLAN based ethernet PCI adapters");
 MODULE_LICENSE("GPL");
 
-/* Turn on debugging. See Documentation/networking/tlan.txt for details */
+/* Turn on debugging.
+ * See Documentation/networking/device_drivers/ti/tlan.txt for details
+ */
 static  int		debug;
 module_param(debug, int, 0);
 MODULE_PARM_DESC(debug, "ThunderLAN debug mask");
diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c
index 6a71c2c0f17d..c50a9772f4af 100644
--- a/drivers/net/ethernet/toshiba/tc35815.c
+++ b/drivers/net/ethernet/toshiba/tc35815.c
@@ -607,9 +607,9 @@ static void tc_handle_link_change(struct net_device *dev)
 
 static int tc_mii_probe(struct net_device *dev)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct tc35815_local *lp = netdev_priv(dev);
 	struct phy_device *phydev;
-	u32 dropmask;
 
 	phydev = phy_find_first(lp->mii_bus);
 	if (!phydev) {
@@ -630,17 +630,22 @@ static int tc_mii_probe(struct net_device *dev)
 
 	/* mask with MAC supported features */
 	phy_set_max_speed(phydev, SPEED_100);
-	dropmask = 0;
-	if (options.speed == 10)
-		dropmask |= SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full;
-	else if (options.speed == 100)
-		dropmask |= SUPPORTED_10baseT_Half | SUPPORTED_10baseT_Full;
-	if (options.duplex == 1)
-		dropmask |= SUPPORTED_10baseT_Full | SUPPORTED_100baseT_Full;
-	else if (options.duplex == 2)
-		dropmask |= SUPPORTED_10baseT_Half | SUPPORTED_100baseT_Half;
-	phydev->supported &= ~dropmask;
-	phydev->advertising = phydev->supported;
+	if (options.speed == 10) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+	} else if (options.speed == 100) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, mask);
+	}
+	if (options.duplex == 1) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, mask);
+	} else if (options.duplex == 2) {
+		linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, mask);
+		linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, mask);
+	}
+	linkmode_and(phydev->supported, phydev->supported, mask);
+	linkmode_copy(phydev->advertising, phydev->supported);
 
 	lp->link = 0;
 	lp->speed = 0;
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index edcd1e60b30d..37925a1d58de 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1311,13 +1311,13 @@ static int tsi108_open(struct net_device *dev)
 		       data->id, dev->irq, dev->name);
 	}
 
-	data->rxring = dma_zalloc_coherent(&data->pdev->dev, rxring_size,
-			&data->rxdma, GFP_KERNEL);
+	data->rxring = dma_alloc_coherent(&data->pdev->dev, rxring_size,
+					  &data->rxdma, GFP_KERNEL);
 	if (!data->rxring)
 		return -ENOMEM;
 
-	data->txring = dma_zalloc_coherent(&data->pdev->dev, txring_size,
-			&data->txdma, GFP_KERNEL);
+	data->txring = dma_alloc_coherent(&data->pdev->dev, txring_size,
+					  &data->txdma, GFP_KERNEL);
 	if (!data->txring) {
 		dma_free_coherent(&data->pdev->dev, rxring_size, data->rxring,
 				    data->rxdma);
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 82412691ee66..27f6cf140845 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -1740,7 +1740,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr,
 		dma_unmap_single(vptr->dev, tdinfo->skb_dma[i],
 				 le16_to_cpu(pktlen), DMA_TO_DEVICE);
 	}
-	dev_kfree_skb_irq(skb);
+	dev_consume_skb_irq(skb);
 	tdinfo->skb = NULL;
 }
 
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index 2241f9897092..44efffbe7970 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -243,15 +243,15 @@ static int temac_dma_bd_init(struct net_device *ndev)
 
 	/* allocate the tx and rx ring buffer descriptors. */
 	/* returns a virtual address and a physical address. */
-	lp->tx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					  sizeof(*lp->tx_bd_v) * TX_BD_NUM,
-					  &lp->tx_bd_p, GFP_KERNEL);
+	lp->tx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					 sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+					 &lp->tx_bd_p, GFP_KERNEL);
 	if (!lp->tx_bd_v)
 		goto out;
 
-	lp->rx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					  sizeof(*lp->rx_bd_v) * RX_BD_NUM,
-					  &lp->rx_bd_p, GFP_KERNEL);
+	lp->rx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					 sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+					 &lp->rx_bd_p, GFP_KERNEL);
 	if (!lp->rx_bd_v)
 		goto out;
 
@@ -630,7 +630,7 @@ static void temac_start_xmit_done(struct net_device *ndev)
 		dma_unmap_single(ndev->dev.parent, cur_p->phys, cur_p->len,
 				 DMA_TO_DEVICE);
 		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *)cur_p->app4);
+			dev_consume_skb_irq((struct sk_buff *)cur_p->app4);
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
 		cur_p->app2 = 0;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 12a14609ec47..4041c75997ba 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -199,15 +199,15 @@ static int axienet_dma_bd_init(struct net_device *ndev)
 	lp->rx_bd_ci = 0;
 
 	/* Allocate the Tx and Rx buffer descriptors. */
-	lp->tx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					  sizeof(*lp->tx_bd_v) * TX_BD_NUM,
-					  &lp->tx_bd_p, GFP_KERNEL);
+	lp->tx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					 sizeof(*lp->tx_bd_v) * TX_BD_NUM,
+					 &lp->tx_bd_p, GFP_KERNEL);
 	if (!lp->tx_bd_v)
 		goto out;
 
-	lp->rx_bd_v = dma_zalloc_coherent(ndev->dev.parent,
-					  sizeof(*lp->rx_bd_v) * RX_BD_NUM,
-					  &lp->rx_bd_p, GFP_KERNEL);
+	lp->rx_bd_v = dma_alloc_coherent(ndev->dev.parent,
+					 sizeof(*lp->rx_bd_v) * RX_BD_NUM,
+					 &lp->rx_bd_p, GFP_KERNEL);
 	if (!lp->rx_bd_v)
 		goto out;
 
@@ -595,7 +595,7 @@ static void axienet_start_xmit_done(struct net_device *ndev)
 				(cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
 				DMA_TO_DEVICE);
 		if (cur_p->app4)
-			dev_kfree_skb_irq((struct sk_buff *)cur_p->app4);
+			dev_consume_skb_irq((struct sk_buff *)cur_p->app4);
 		/*cur_p->phys = 0;*/
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
@@ -1575,12 +1575,14 @@ static int axienet_probe(struct platform_device *pdev)
 	ret = of_address_to_resource(np, 0, &dmares);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to get DMA resource\n");
+		of_node_put(np);
 		goto free_netdev;
 	}
 	lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares);
 	if (IS_ERR(lp->dma_regs)) {
 		dev_err(&pdev->dev, "could not map DMA regs\n");
 		ret = PTR_ERR(lp->dma_regs);
+		of_node_put(np);
 		goto free_netdev;
 	}
 	lp->rx_irq = irq_of_parse_and_map(np, 1);
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 639e3e99af46..b03a417d0073 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -581,7 +581,7 @@ static void xemaclite_tx_handler(struct net_device *dev)
 		return;
 
 	dev->stats.tx_bytes += lp->deferred_skb->len;
-	dev_kfree_skb_irq(lp->deferred_skb);
+	dev_consume_skb_irq(lp->deferred_skb);
 	lp->deferred_skb = NULL;
 	netif_trans_update(dev); /* prevent tx timeout */
 	netif_wake_queue(dev);
diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c
index aee55c03def0..ed6623a9801e 100644
--- a/drivers/net/ethernet/xscale/ixp4xx_eth.c
+++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c
@@ -139,7 +139,7 @@
 #ifdef __ARMEB__
 typedef struct sk_buff buffer_t;
 #define free_buffer dev_kfree_skb
-#define free_buffer_irq dev_kfree_skb_irq
+#define free_buffer_irq dev_consume_skb_irq
 #else
 typedef void buffer_t;
 #define free_buffer kfree