--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -7,9 +7,12 @@ Required properties:
 - interrupt-parent: Should be the phandle for the interrupt controller
   that services interrupts for this device
 - interrupts: Should contain the STMMAC interrupts
-- interrupt-names: Should contain the interrupt names "macirq"
-  "eth_wake_irq" if this interrupt is supported in the "interrupts"
-  property
+- interrupt-names: Should contain a list of interrupt names corresponding to
+	the interrupts in the interrupts property, if available.
+	Valid interrupt names are:
+  - "macirq" (combined signal for various interrupt events)
+  - "eth_wake_irq" (the interrupt to manage the remote wake-up packet detection)
+  - "eth_lpi" (the interrupt that occurs when Tx or Rx enters/exits LPI state)
 - phy-mode: See ethernet.txt file in the same directory.
 - snps,reset-gpio 	gpio number for phy reset.
 - snps,reset-active-low boolean flag to indicate if phy reset is active low.
@@ -28,9 +31,9 @@ Optional properties:
   clocks may be specified in derived bindings.
 - clock-names: One name for each entry in the clocks property, the
   first one should be "stmmaceth" and the second one should be "pclk".
-- clk_ptp_ref: this is the PTP reference clock; in case of the PTP is
-  available this clock is used for programming the Timestamp Addend Register.
-  If not passed then the system clock will be used and this is fine on some
+- ptp_ref: this is the PTP reference clock; in case of the PTP is available
+  this clock is used for programming the Timestamp Addend Register. If not
+  passed then the system clock will be used and this is fine on some
   platforms.
 - tx-fifo-depth: See ethernet.txt file in the same directory
 - rx-fifo-depth: See ethernet.txt file in the same directory
@@ -72,7 +75,45 @@ Optional properties:
 	- snps,mb: mixed-burst
 	- snps,rb: rebuild INCRx Burst
 - mdio: with compatible = "snps,dwmac-mdio", create and register mdio bus.
-
+- Multiple RX Queues parameters: below the list of all the parameters to
+				 configure the multiple RX queues:
+	- snps,rx-queues-to-use: number of RX queues to be used in the driver
+	- Choose one of these RX scheduling algorithms:
+		- snps,rx-sched-sp: Strict priority
+		- snps,rx-sched-wsp: Weighted Strict priority
+	- For each RX queue
+		- Choose one of these modes:
+			- snps,dcb-algorithm: Queue to be enabled as DCB
+			- snps,avb-algorithm: Queue to be enabled as AVB
+		- snps,map-to-dma-channel: Channel to map
+		- Specifiy specific packet routing:
+			- snps,route-avcp: AV Untagged Control packets
+			- snps,route-ptp: PTP Packets
+			- snps,route-dcbcp: DCB Control Packets
+			- snps,route-up: Untagged Packets
+			- snps,route-multi-broad: Multicast & Broadcast Packets
+		- snps,priority: RX queue priority (Range: 0x0 to 0xF)
+- Multiple TX Queues parameters: below the list of all the parameters to
+				 configure the multiple TX queues:
+	- snps,tx-queues-to-use: number of TX queues to be used in the driver
+	- Choose one of these TX scheduling algorithms:
+		- snps,tx-sched-wrr: Weighted Round Robin
+		- snps,tx-sched-wfq: Weighted Fair Queuing
+		- snps,tx-sched-dwrr: Deficit Weighted Round Robin
+		- snps,tx-sched-sp: Strict priority
+	- For each TX queue
+		- snps,weight: TX queue weight (if using a DCB weight algorithm)
+		- Choose one of these modes:
+			- snps,dcb-algorithm: TX queue will be working in DCB
+			- snps,avb-algorithm: TX queue will be working in AVB
+			  [Attention] Queue 0 is reserved for legacy traffic
+			  and so no AVB is available in this queue.
+		- Configure Credit Base Shaper (if AVB Mode selected):
+			- snps,send_slope: enable Low Power Interface
+			- snps,idle_slope: unlock on WoL
+			- snps,high_credit: max write outstanding req. limit
+			- snps,low_credit: max read outstanding req. limit
+		- snps,priority: TX queue priority (Range: 0x0 to 0xF)
 Examples:
 
 	stmmac_axi_setup: stmmac-axi-config {
@@ -81,12 +122,41 @@ Examples:
 		snps,blen = <256 128 64 32 0 0 0>;
 	};
 
+	mtl_rx_setup: rx-queues-config {
+		snps,rx-queues-to-use = <1>;
+		snps,rx-sched-sp;
+		queue0 {
+			snps,dcb-algorithm;
+			snps,map-to-dma-channel = <0x0>;
+			snps,priority = <0x0>;
+		};
+	};
+
+	mtl_tx_setup: tx-queues-config {
+		snps,tx-queues-to-use = <2>;
+		snps,tx-sched-wrr;
+		queue0 {
+			snps,weight = <0x10>;
+			snps,dcb-algorithm;
+			snps,priority = <0x0>;
+		};
+
+		queue1 {
+			snps,avb-algorithm;
+			snps,send_slope = <0x1000>;
+			snps,idle_slope = <0x1000>;
+			snps,high_credit = <0x3E800>;
+			snps,low_credit = <0xFFC18000>;
+			snps,priority = <0x1>;
+		};
+	};
+
 	gmac0: ethernet@e0800000 {
 		compatible = "st,spear600-gmac";
 		reg = <0xe0800000 0x8000>;
 		interrupt-parent = <&vic1>;
-		interrupts = <24 23>;
-		interrupt-names = "macirq", "eth_wake_irq";
+		interrupts = <24 23 22>;
+		interrupt-names = "macirq", "eth_wake_irq", "eth_lpi";
 		mac-address = [000000000000]; /* Filled in by U-Boot */
 		max-frame-size = <3800>;
 		phy-mode = "gmii";
@@ -104,4 +174,6 @@ Examples:
 			phy1: ethernet-phy@0 {
 			};
 		};
+		snps,mtl-rx-config = <&mtl_rx_setup>;
+		snps,mtl-tx-config = <&mtl_tx_setup>;
 	};
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
@@ -37,6 +37,7 @@
 #define TSE_PCS_CONTROL_AN_EN_MASK			BIT(12)
 #define TSE_PCS_CONTROL_REG				0x00
 #define TSE_PCS_CONTROL_RESTART_AN_MASK			BIT(9)
+#define TSE_PCS_CTRL_AUTONEG_SGMII			0x1140
 #define TSE_PCS_IF_MODE_REG				0x28
 #define TSE_PCS_LINK_TIMER_0_REG			0x24
 #define TSE_PCS_LINK_TIMER_1_REG			0x26
@@ -65,6 +66,7 @@
 #define TSE_PCS_SW_RESET_TIMEOUT			100
 #define TSE_PCS_USE_SGMII_AN_MASK			BIT(1)
 #define TSE_PCS_USE_SGMII_ENA				BIT(0)
+#define TSE_PCS_IF_USE_SGMII				0x03
 
 #define SGMII_ADAPTER_CTRL_REG				0x00
 #define SGMII_ADAPTER_DISABLE				0x0001
@@ -101,7 +103,9 @@ int tse_pcs_init(void __iomem *base, str
 {
 	int ret = 0;
 
-	writew(TSE_PCS_USE_SGMII_ENA, base + TSE_PCS_IF_MODE_REG);
+	writew(TSE_PCS_IF_USE_SGMII, base + TSE_PCS_IF_MODE_REG);
+
+	writew(TSE_PCS_CTRL_AUTONEG_SGMII, base + TSE_PCS_CONTROL_REG);
 
 	writew(TSE_PCS_SGMII_LINK_TIMER_0, base + TSE_PCS_LINK_TIMER_0_REG);
 	writew(TSE_PCS_SGMII_LINK_TIMER_1, base + TSE_PCS_LINK_TIMER_1_REG);
--- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c
@@ -26,12 +26,15 @@
 
 static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)p;
-	unsigned int entry = priv->cur_tx;
-	struct dma_desc *desc = priv->dma_tx + entry;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p;
 	unsigned int nopaged_len = skb_headlen(skb);
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->cur_tx;
 	unsigned int bmax, des2;
 	unsigned int i = 1, len;
+	struct dma_desc *desc;
+
+	desc = tx_q->dma_tx + entry;
 
 	if (priv->plat->enh_desc)
 		bmax = BUF_SIZE_8KiB;
@@ -45,16 +48,16 @@ static int stmmac_jumbo_frm(void *p, str
 	desc->des2 = cpu_to_le32(des2);
 	if (dma_mapping_error(priv->device, des2))
 		return -1;
-	priv->tx_skbuff_dma[entry].buf = des2;
-	priv->tx_skbuff_dma[entry].len = bmax;
+	tx_q->tx_skbuff_dma[entry].buf = des2;
+	tx_q->tx_skbuff_dma[entry].len = bmax;
 	/* do not close the descriptor and do not set own bit */
 	priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE,
-					0, false);
+					0, false, skb->len);
 
 	while (len != 0) {
-		priv->tx_skbuff[entry] = NULL;
+		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
-		desc = priv->dma_tx + entry;
+		desc = tx_q->dma_tx + entry;
 
 		if (len > bmax) {
 			des2 = dma_map_single(priv->device,
@@ -63,11 +66,11 @@ static int stmmac_jumbo_frm(void *p, str
 			desc->des2 = cpu_to_le32(des2);
 			if (dma_mapping_error(priv->device, des2))
 				return -1;
-			priv->tx_skbuff_dma[entry].buf = des2;
-			priv->tx_skbuff_dma[entry].len = bmax;
+			tx_q->tx_skbuff_dma[entry].buf = des2;
+			tx_q->tx_skbuff_dma[entry].len = bmax;
 			priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum,
 							STMMAC_CHAIN_MODE, 1,
-							false);
+							false, skb->len);
 			len -= bmax;
 			i++;
 		} else {
@@ -77,17 +80,17 @@ static int stmmac_jumbo_frm(void *p, str
 			desc->des2 = cpu_to_le32(des2);
 			if (dma_mapping_error(priv->device, des2))
 				return -1;
-			priv->tx_skbuff_dma[entry].buf = des2;
-			priv->tx_skbuff_dma[entry].len = len;
+			tx_q->tx_skbuff_dma[entry].buf = des2;
+			tx_q->tx_skbuff_dma[entry].len = len;
 			/* last descriptor can be set now */
 			priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
 							STMMAC_CHAIN_MODE, 1,
-							true);
+							true, skb->len);
 			len = 0;
 		}
 	}
 
-	priv->cur_tx = entry;
+	tx_q->cur_tx = entry;
 
 	return entry;
 }
@@ -136,32 +139,34 @@ static void stmmac_init_dma_chain(void *
 
 static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
+	struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)priv_ptr;
+	struct stmmac_priv *priv = rx_q->priv_data;
 
 	if (priv->hwts_rx_en && !priv->extend_desc)
 		/* NOTE: Device will overwrite des3 with timestamp value if
 		 * 1588-2002 time stamping is enabled, hence reinitialize it
 		 * to keep explicit chaining in the descriptor.
 		 */
-		p->des3 = cpu_to_le32((unsigned int)(priv->dma_rx_phy +
-				      (((priv->dirty_rx) + 1) %
+		p->des3 = cpu_to_le32((unsigned int)(rx_q->dma_rx_phy +
+				      (((rx_q->dirty_rx) + 1) %
 				       DMA_RX_SIZE) *
 				      sizeof(struct dma_desc)));
 }
 
 static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
-	unsigned int entry = priv->dirty_tx;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr;
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->dirty_tx;
 
-	if (priv->tx_skbuff_dma[entry].last_segment && !priv->extend_desc &&
+	if (tx_q->tx_skbuff_dma[entry].last_segment && !priv->extend_desc &&
 	    priv->hwts_tx_en)
 		/* NOTE: Device will overwrite des3 with timestamp value if
 		 * 1588-2002 time stamping is enabled, hence reinitialize it
 		 * to keep explicit chaining in the descriptor.
 		 */
-		p->des3 = cpu_to_le32((unsigned int)((priv->dma_tx_phy +
-				      ((priv->dirty_tx + 1) % DMA_TX_SIZE))
+		p->des3 = cpu_to_le32((unsigned int)((tx_q->dma_tx_phy +
+				      ((tx_q->dirty_tx + 1) % DMA_TX_SIZE))
 				      * sizeof(struct dma_desc)));
 }
 
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -246,6 +246,15 @@ struct stmmac_extra_stats {
 #define STMMAC_TX_MAX_FRAMES	256
 #define STMMAC_TX_FRAMES	64
 
+/* Packets types */
+enum packets_types {
+	PACKET_AVCPQ = 0x1, /* AV Untagged Control packets */
+	PACKET_PTPQ = 0x2, /* PTP Packets */
+	PACKET_DCBCPQ = 0x3, /* DCB Control Packets */
+	PACKET_UPQ = 0x4, /* Untagged Packets */
+	PACKET_MCBCQ = 0x5, /* Multicast & Broadcast Packets */
+};
+
 /* Rx IPC status */
 enum rx_frame_status {
 	good_frame = 0x0,
@@ -324,6 +333,9 @@ struct dma_features {
 	unsigned int number_tx_queues;
 	/* Alternate (enhanced) DESC mode */
 	unsigned int enh_desc;
+	/* TX and RX FIFO sizes */
+	unsigned int tx_fifo_size;
+	unsigned int rx_fifo_size;
 };
 
 /* GMAC TX FIFO is 8K, Rx FIFO is 16K */
@@ -361,7 +373,7 @@ struct stmmac_desc_ops {
 	/* Invoked by the xmit function to prepare the tx descriptor */
 	void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len,
 				 bool csum_flag, int mode, bool tx_own,
-				 bool ls);
+				 bool ls, unsigned int tot_pkt_len);
 	void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1,
 				    int len2, bool tx_own, bool ls,
 				    unsigned int tcphdrlen,
@@ -413,6 +425,14 @@ struct stmmac_dma_ops {
 	int (*reset)(void __iomem *ioaddr);
 	void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg,
 		     u32 dma_tx, u32 dma_rx, int atds);
+	void (*init_chan)(void __iomem *ioaddr,
+			  struct stmmac_dma_cfg *dma_cfg, u32 chan);
+	void (*init_rx_chan)(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_rx_phy, u32 chan);
+	void (*init_tx_chan)(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_tx_phy, u32 chan);
 	/* Configure the AXI Bus Mode Register */
 	void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
 	/* Dump DMA registers */
@@ -421,25 +441,28 @@ struct stmmac_dma_ops {
 	 * An invalid value enables the store-and-forward mode */
 	void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode,
 			 int rxfifosz);
+	void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel,
+			    int fifosz);
+	void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel);
 	/* To track extra statistic (if supported) */
 	void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x,
 				   void __iomem *ioaddr);
 	void (*enable_dma_transmission) (void __iomem *ioaddr);
-	void (*enable_dma_irq) (void __iomem *ioaddr);
-	void (*disable_dma_irq) (void __iomem *ioaddr);
-	void (*start_tx) (void __iomem *ioaddr);
-	void (*stop_tx) (void __iomem *ioaddr);
-	void (*start_rx) (void __iomem *ioaddr);
-	void (*stop_rx) (void __iomem *ioaddr);
+	void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan);
+	void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan);
+	void (*start_tx)(void __iomem *ioaddr, u32 chan);
+	void (*stop_tx)(void __iomem *ioaddr, u32 chan);
+	void (*start_rx)(void __iomem *ioaddr, u32 chan);
+	void (*stop_rx)(void __iomem *ioaddr, u32 chan);
 	int (*dma_interrupt) (void __iomem *ioaddr,
-			      struct stmmac_extra_stats *x);
+			      struct stmmac_extra_stats *x, u32 chan);
 	/* If supported then get the optional core features */
 	void (*get_hw_feature)(void __iomem *ioaddr,
 			       struct dma_features *dma_cap);
 	/* Program the HW RX Watchdog */
-	void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt);
-	void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len);
-	void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len);
+	void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan);
+	void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
+	void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan);
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
@@ -451,20 +474,44 @@ struct mac_device_info;
 struct stmmac_ops {
 	/* MAC core initialization */
 	void (*core_init)(struct mac_device_info *hw, int mtu);
+	/* Enable the MAC RX/TX */
+	void (*set_mac)(void __iomem *ioaddr, bool enable);
 	/* Enable and verify that the IPC module is supported */
 	int (*rx_ipc)(struct mac_device_info *hw);
 	/* Enable RX Queues */
-	void (*rx_queue_enable)(struct mac_device_info *hw, u32 queue);
+	void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue);
+	/* RX Queues Priority */
+	void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+	/* TX Queues Priority */
+	void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue);
+	/* RX Queues Routing */
+	void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet,
+				 u32 queue);
+	/* Program RX Algorithms */
+	void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg);
+	/* Program TX Algorithms */
+	void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg);
+	/* Set MTL TX queues weight */
+	void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw,
+					u32 weight, u32 queue);
+	/* RX MTL queue to RX dma mapping */
+	void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan);
+	/* Configure AV Algorithm */
+	void (*config_cbs)(struct mac_device_info *hw, u32 send_slope,
+			   u32 idle_slope, u32 high_credit, u32 low_credit,
+			   u32 queue);
 	/* Dump MAC registers */
 	void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space);
 	/* Handle extra events on specific interrupts hw dependent */
 	int (*host_irq_status)(struct mac_device_info *hw,
 			       struct stmmac_extra_stats *x);
+	/* Handle MTL interrupts */
+	int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan);
 	/* Multicast filter setting */
 	void (*set_filter)(struct mac_device_info *hw, struct net_device *dev);
 	/* Flow control setting */
 	void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex,
-			  unsigned int fc, unsigned int pause_time);
+			  unsigned int fc, unsigned int pause_time, u32 tx_cnt);
 	/* Set power management mode (e.g. magic frame) */
 	void (*pmt)(struct mac_device_info *hw, unsigned long mode);
 	/* Set/Get Unicast MAC addresses */
@@ -477,7 +524,8 @@ struct stmmac_ops {
 	void (*reset_eee_mode)(struct mac_device_info *hw);
 	void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
 	void (*set_eee_pls)(struct mac_device_info *hw, int link);
-	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+	void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+		      u32 rx_queues, u32 tx_queues);
 	/* PCS calls */
 	void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral,
 			     bool loopback);
@@ -547,6 +595,11 @@ struct mac_device_info {
 	unsigned int ps;
 };
 
+struct stmmac_rx_routing {
+	u32 reg_mask;
+	u32 reg_shift;
+};
+
 struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
 					int perfect_uc_entries,
 					int *synopsys_id);
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -14,16 +14,34 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/device.h>
+#include <linux/gpio/consumer.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
 #include <linux/of_net.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
+#include <linux/reset.h>
 #include <linux/stmmac.h>
 
 #include "stmmac_platform.h"
+#include "dwmac4.h"
+
+struct tegra_eqos {
+	struct device *dev;
+	void __iomem *regs;
+
+	struct reset_control *rst;
+	struct clk *clk_master;
+	struct clk *clk_slave;
+	struct clk *clk_tx;
+	struct clk *clk_rx;
+
+	struct gpio_desc *reset;
+};
 
 static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 				   struct plat_stmmacenet_data *plat_dat)
@@ -106,13 +124,309 @@ static int dwc_eth_dwmac_config_dt(struc
 	return 0;
 }
 
+static void *dwc_qos_probe(struct platform_device *pdev,
+			   struct plat_stmmacenet_data *plat_dat,
+			   struct stmmac_resources *stmmac_res)
+{
+	int err;
+
+	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
+	if (IS_ERR(plat_dat->stmmac_clk)) {
+		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
+		return ERR_CAST(plat_dat->stmmac_clk);
+	}
+
+	err = clk_prepare_enable(plat_dat->stmmac_clk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
+			err);
+		return ERR_PTR(err);
+	}
+
+	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
+	if (IS_ERR(plat_dat->pclk)) {
+		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
+		err = PTR_ERR(plat_dat->pclk);
+		goto disable;
+	}
+
+	err = clk_prepare_enable(plat_dat->pclk);
+	if (err < 0) {
+		dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n",
+			err);
+		goto disable;
+	}
+
+	return NULL;
+
+disable:
+	clk_disable_unprepare(plat_dat->stmmac_clk);
+	return ERR_PTR(err);
+}
+
+static int dwc_qos_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	clk_disable_unprepare(priv->plat->pclk);
+	clk_disable_unprepare(priv->plat->stmmac_clk);
+
+	return 0;
+}
+
+#define SDMEMCOMPPADCTRL 0x8800
+#define  SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD BIT(31)
+
+#define AUTO_CAL_CONFIG 0x8804
+#define  AUTO_CAL_CONFIG_START BIT(31)
+#define  AUTO_CAL_CONFIG_ENABLE BIT(29)
+
+#define AUTO_CAL_STATUS 0x880c
+#define  AUTO_CAL_STATUS_ACTIVE BIT(31)
+
+static void tegra_eqos_fix_speed(void *priv, unsigned int speed)
+{
+	struct tegra_eqos *eqos = priv;
+	unsigned long rate = 125000000;
+	bool needs_calibration = false;
+	u32 value;
+	int err;
+
+	switch (speed) {
+	case SPEED_1000:
+		needs_calibration = true;
+		rate = 125000000;
+		break;
+
+	case SPEED_100:
+		needs_calibration = true;
+		rate = 25000000;
+		break;
+
+	case SPEED_10:
+		rate = 2500000;
+		break;
+
+	default:
+		dev_err(eqos->dev, "invalid speed %u\n", speed);
+		break;
+	}
+
+	if (needs_calibration) {
+		/* calibrate */
+		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+		value |= SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+
+		udelay(1);
+
+		value = readl(eqos->regs + AUTO_CAL_CONFIG);
+		value |= AUTO_CAL_CONFIG_START | AUTO_CAL_CONFIG_ENABLE;
+		writel(value, eqos->regs + AUTO_CAL_CONFIG);
+
+		err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+						value,
+						value & AUTO_CAL_STATUS_ACTIVE,
+						1, 10);
+		if (err < 0) {
+			dev_err(eqos->dev, "calibration did not start\n");
+			goto failed;
+		}
+
+		err = readl_poll_timeout_atomic(eqos->regs + AUTO_CAL_STATUS,
+						value,
+						(value & AUTO_CAL_STATUS_ACTIVE) == 0,
+						20, 200);
+		if (err < 0) {
+			dev_err(eqos->dev, "calibration didn't finish\n");
+			goto failed;
+		}
+
+	failed:
+		value = readl(eqos->regs + SDMEMCOMPPADCTRL);
+		value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD;
+		writel(value, eqos->regs + SDMEMCOMPPADCTRL);
+	} else {
+		value = readl(eqos->regs + AUTO_CAL_CONFIG);
+		value &= ~AUTO_CAL_CONFIG_ENABLE;
+		writel(value, eqos->regs + AUTO_CAL_CONFIG);
+	}
+
+	err = clk_set_rate(eqos->clk_tx, rate);
+	if (err < 0)
+		dev_err(eqos->dev, "failed to set TX rate: %d\n", err);
+}
+
+static int tegra_eqos_init(struct platform_device *pdev, void *priv)
+{
+	struct tegra_eqos *eqos = priv;
+	unsigned long rate;
+	u32 value;
+
+	rate = clk_get_rate(eqos->clk_slave);
+
+	value = (rate / 1000000) - 1;
+	writel(value, eqos->regs + GMAC_1US_TIC_COUNTER);
+
+	return 0;
+}
+
+static void *tegra_eqos_probe(struct platform_device *pdev,
+			      struct plat_stmmacenet_data *data,
+			      struct stmmac_resources *res)
+{
+	struct tegra_eqos *eqos;
+	int err;
+
+	eqos = devm_kzalloc(&pdev->dev, sizeof(*eqos), GFP_KERNEL);
+	if (!eqos) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	eqos->dev = &pdev->dev;
+	eqos->regs = res->addr;
+
+	eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus");
+	if (IS_ERR(eqos->clk_master)) {
+		err = PTR_ERR(eqos->clk_master);
+		goto error;
+	}
+
+	err = clk_prepare_enable(eqos->clk_master);
+	if (err < 0)
+		goto error;
+
+	eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus");
+	if (IS_ERR(eqos->clk_slave)) {
+		err = PTR_ERR(eqos->clk_slave);
+		goto disable_master;
+	}
+
+	data->stmmac_clk = eqos->clk_slave;
+
+	err = clk_prepare_enable(eqos->clk_slave);
+	if (err < 0)
+		goto disable_master;
+
+	eqos->clk_rx = devm_clk_get(&pdev->dev, "rx");
+	if (IS_ERR(eqos->clk_rx)) {
+		err = PTR_ERR(eqos->clk_rx);
+		goto disable_slave;
+	}
+
+	err = clk_prepare_enable(eqos->clk_rx);
+	if (err < 0)
+		goto disable_slave;
+
+	eqos->clk_tx = devm_clk_get(&pdev->dev, "tx");
+	if (IS_ERR(eqos->clk_tx)) {
+		err = PTR_ERR(eqos->clk_tx);
+		goto disable_rx;
+	}
+
+	err = clk_prepare_enable(eqos->clk_tx);
+	if (err < 0)
+		goto disable_rx;
+
+	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(eqos->reset)) {
+		err = PTR_ERR(eqos->reset);
+		goto disable_tx;
+	}
+
+	usleep_range(2000, 4000);
+	gpiod_set_value(eqos->reset, 0);
+
+	eqos->rst = devm_reset_control_get(&pdev->dev, "eqos");
+	if (IS_ERR(eqos->rst)) {
+		err = PTR_ERR(eqos->rst);
+		goto reset_phy;
+	}
+
+	err = reset_control_assert(eqos->rst);
+	if (err < 0)
+		goto reset_phy;
+
+	usleep_range(2000, 4000);
+
+	err = reset_control_deassert(eqos->rst);
+	if (err < 0)
+		goto reset_phy;
+
+	usleep_range(2000, 4000);
+
+	data->fix_mac_speed = tegra_eqos_fix_speed;
+	data->init = tegra_eqos_init;
+	data->bsp_priv = eqos;
+
+	err = tegra_eqos_init(pdev, eqos);
+	if (err < 0)
+		goto reset;
+
+out:
+	return eqos;
+
+reset:
+	reset_control_assert(eqos->rst);
+reset_phy:
+	gpiod_set_value(eqos->reset, 1);
+disable_tx:
+	clk_disable_unprepare(eqos->clk_tx);
+disable_rx:
+	clk_disable_unprepare(eqos->clk_rx);
+disable_slave:
+	clk_disable_unprepare(eqos->clk_slave);
+disable_master:
+	clk_disable_unprepare(eqos->clk_master);
+error:
+	eqos = ERR_PTR(err);
+	goto out;
+}
+
+static int tegra_eqos_remove(struct platform_device *pdev)
+{
+	struct tegra_eqos *eqos = get_stmmac_bsp_priv(&pdev->dev);
+
+	reset_control_assert(eqos->rst);
+	gpiod_set_value(eqos->reset, 1);
+	clk_disable_unprepare(eqos->clk_tx);
+	clk_disable_unprepare(eqos->clk_rx);
+	clk_disable_unprepare(eqos->clk_slave);
+	clk_disable_unprepare(eqos->clk_master);
+
+	return 0;
+}
+
+struct dwc_eth_dwmac_data {
+	void *(*probe)(struct platform_device *pdev,
+		       struct plat_stmmacenet_data *data,
+		       struct stmmac_resources *res);
+	int (*remove)(struct platform_device *pdev);
+};
+
+static const struct dwc_eth_dwmac_data dwc_qos_data = {
+	.probe = dwc_qos_probe,
+	.remove = dwc_qos_remove,
+};
+
+static const struct dwc_eth_dwmac_data tegra_eqos_data = {
+	.probe = tegra_eqos_probe,
+	.remove = tegra_eqos_remove,
+};
+
 static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 {
+	const struct dwc_eth_dwmac_data *data;
 	struct plat_stmmacenet_data *plat_dat;
 	struct stmmac_resources stmmac_res;
 	struct resource *res;
+	void *priv;
 	int ret;
 
+	data = of_device_get_match_data(&pdev->dev);
+
 	memset(&stmmac_res, 0, sizeof(struct stmmac_resources));
 
 	/**
@@ -138,39 +452,26 @@ static int dwc_eth_dwmac_probe(struct pl
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
-	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
-	if (IS_ERR(plat_dat->stmmac_clk)) {
-		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
-		ret = PTR_ERR(plat_dat->stmmac_clk);
-		plat_dat->stmmac_clk = NULL;
-		goto err_remove_config_dt;
+	priv = data->probe(pdev, plat_dat, &stmmac_res);
+	if (IS_ERR(priv)) {
+		ret = PTR_ERR(priv);
+		dev_err(&pdev->dev, "failed to probe subdriver: %d\n", ret);
+		goto remove_config;
 	}
-	clk_prepare_enable(plat_dat->stmmac_clk);
-
-	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
-	if (IS_ERR(plat_dat->pclk)) {
-		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
-		ret = PTR_ERR(plat_dat->pclk);
-		plat_dat->pclk = NULL;
-		goto err_out_clk_dis_phy;
-	}
-	clk_prepare_enable(plat_dat->pclk);
 
 	ret = dwc_eth_dwmac_config_dt(pdev, plat_dat);
 	if (ret)
-		goto err_out_clk_dis_aper;
+		goto remove;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 	if (ret)
-		goto err_out_clk_dis_aper;
+		goto remove;
 
-	return 0;
+	return ret;
 
-err_out_clk_dis_aper:
-	clk_disable_unprepare(plat_dat->pclk);
-err_out_clk_dis_phy:
-	clk_disable_unprepare(plat_dat->stmmac_clk);
-err_remove_config_dt:
+remove:
+	data->remove(pdev);
+remove_config:
 	stmmac_remove_config_dt(pdev, plat_dat);
 
 	return ret;
@@ -178,11 +479,29 @@ err_remove_config_dt:
 
 static int dwc_eth_dwmac_remove(struct platform_device *pdev)
 {
-	return stmmac_pltfr_remove(pdev);
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	const struct dwc_eth_dwmac_data *data;
+	int err;
+
+	data = of_device_get_match_data(&pdev->dev);
+
+	err = stmmac_dvr_remove(&pdev->dev);
+	if (err < 0)
+		dev_err(&pdev->dev, "failed to remove platform: %d\n", err);
+
+	err = data->remove(pdev);
+	if (err < 0)
+		dev_err(&pdev->dev, "failed to remove subdriver: %d\n", err);
+
+	stmmac_remove_config_dt(pdev, priv->plat);
+
+	return err;
 }
 
 static const struct of_device_id dwc_eth_dwmac_match[] = {
-	{ .compatible = "snps,dwc-qos-ethernet-4.10", },
+	{ .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data },
+	{ .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match);
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -74,6 +74,10 @@ struct rk_priv_data {
 #define GRF_BIT(nr)	(BIT(nr) | BIT(nr+16))
 #define GRF_CLR_BIT(nr)	(BIT(nr+16))
 
+#define DELAY_ENABLE(soc, tx, rx) \
+	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
+	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
+
 #define RK3228_GRF_MAC_CON0	0x0900
 #define RK3228_GRF_MAC_CON1	0x0904
 
@@ -115,8 +119,7 @@ static void rk3228_set_to_rgmii(struct r
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3228_GMAC_RMII_MODE_CLR |
-		     RK3228_GMAC_RXCLK_DLY_ENABLE |
-		     RK3228_GMAC_TXCLK_DLY_ENABLE);
+		     DELAY_ENABLE(RK3228, tx_delay, rx_delay));
 
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON0,
 		     RK3228_GMAC_CLK_RX_DL_CFG(rx_delay) |
@@ -232,8 +235,7 @@ static void rk3288_set_to_rgmii(struct r
 		     RK3288_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3288_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3,
-		     RK3288_GMAC_RXCLK_DLY_ENABLE |
-		     RK3288_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3288, tx_delay, rx_delay) |
 		     RK3288_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3288_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -460,8 +462,7 @@ static void rk3366_set_to_rgmii(struct r
 		     RK3366_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3366_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON7,
-		     RK3366_GMAC_RXCLK_DLY_ENABLE |
-		     RK3366_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3366, tx_delay, rx_delay) |
 		     RK3366_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3366_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -572,8 +573,7 @@ static void rk3368_set_to_rgmii(struct r
 		     RK3368_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3368_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16,
-		     RK3368_GMAC_RXCLK_DLY_ENABLE |
-		     RK3368_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3368, tx_delay, rx_delay) |
 		     RK3368_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3368_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -684,8 +684,7 @@ static void rk3399_set_to_rgmii(struct r
 		     RK3399_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3399_GMAC_RMII_MODE_CLR);
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON6,
-		     RK3399_GMAC_RXCLK_DLY_ENABLE |
-		     RK3399_GMAC_TXCLK_DLY_ENABLE |
+		     DELAY_ENABLE(RK3399, tx_delay, rx_delay) |
 		     RK3399_GMAC_CLK_RX_DL_CFG(rx_delay) |
 		     RK3399_GMAC_CLK_TX_DL_CFG(tx_delay));
 }
@@ -985,14 +984,29 @@ static int rk_gmac_powerup(struct rk_pri
 		return ret;
 
 	/*rmii or rgmii*/
-	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII) {
+	switch (bsp_priv->phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
 		dev_info(dev, "init for RGMII\n");
 		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay,
 					    bsp_priv->rx_delay);
-	} else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII) {
+		break;
+	case PHY_INTERFACE_MODE_RGMII_ID:
+		dev_info(dev, "init for RGMII_ID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, 0, 0);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		dev_info(dev, "init for RGMII_RXID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, bsp_priv->tx_delay, 0);
+		break;
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+		dev_info(dev, "init for RGMII_TXID\n");
+		bsp_priv->ops->set_to_rgmii(bsp_priv, 0, bsp_priv->rx_delay);
+		break;
+	case PHY_INTERFACE_MODE_RMII:
 		dev_info(dev, "init for RMII\n");
 		bsp_priv->ops->set_to_rmii(bsp_priv);
-	} else {
+		break;
+	default:
 		dev_err(dev, "NO interface defined!\n");
 	}
 
@@ -1022,12 +1036,19 @@ static void rk_fix_speed(void *priv, uns
 	struct rk_priv_data *bsp_priv = priv;
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RGMII)
+	switch (bsp_priv->phy_iface) {
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
 		bsp_priv->ops->set_rgmii_speed(bsp_priv, speed);
-	else if (bsp_priv->phy_iface == PHY_INTERFACE_MODE_RMII)
+		break;
+	case PHY_INTERFACE_MODE_RMII:
 		bsp_priv->ops->set_rmii_speed(bsp_priv, speed);
-	else
+		break;
+	default:
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
+	}
 }
 
 static int rk_gmac_probe(struct platform_device *pdev)
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct
 
 
 static void dwmac1000_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-				unsigned int fc, unsigned int pause_time)
+				unsigned int fc, unsigned int pause_time,
+				u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	/* Set flow such that DZPQ in Mac Register 6 is 0,
@@ -412,7 +413,8 @@ static void dwmac1000_get_adv_lp(void __
 	dwmac_get_adv_lp(ioaddr, GMAC_PCS_BASE, adv);
 }
 
-static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			    u32 rx_queues, u32 tx_queues)
 {
 	u32 value = readl(ioaddr + GMAC_DEBUG);
 
@@ -488,6 +490,7 @@ static void dwmac1000_debug(void __iomem
 
 static const struct stmmac_ops dwmac1000_ops = {
 	.core_init = dwmac1000_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac1000_rx_ipc_enable,
 	.dump_regs = dwmac1000_dump_regs,
 	.host_irq_status = dwmac1000_irq_status,
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -247,7 +247,8 @@ static void dwmac1000_get_hw_feature(voi
 	dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
 }
 
-static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt,
+				  u32 number_chan)
 {
 	writel(riwt, ioaddr + DMA_RX_WATCHDOG);
 }
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct m
 }
 
 static void dwmac100_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-			       unsigned int fc, unsigned int pause_time)
+			       unsigned int fc, unsigned int pause_time,
+			       u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	unsigned int flow = MAC_FLOW_CTRL_ENABLE;
@@ -149,6 +150,7 @@ static void dwmac100_pmt(struct mac_devi
 
 static const struct stmmac_ops dwmac100_ops = {
 	.core_init = dwmac100_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac100_rx_ipc_enable,
 	.dump_regs = dwmac100_dump_mac_regs,
 	.host_irq_status = dwmac100_irq_status,
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -22,9 +22,15 @@
 #define GMAC_HASH_TAB_32_63		0x00000014
 #define GMAC_RX_FLOW_CTRL		0x00000090
 #define GMAC_QX_TX_FLOW_CTRL(x)		(0x70 + x * 4)
+#define GMAC_TXQ_PRTY_MAP0		0x98
+#define GMAC_TXQ_PRTY_MAP1		0x9C
 #define GMAC_RXQ_CTRL0			0x000000a0
+#define GMAC_RXQ_CTRL1			0x000000a4
+#define GMAC_RXQ_CTRL2			0x000000a8
+#define GMAC_RXQ_CTRL3			0x000000ac
 #define GMAC_INT_STATUS			0x000000b0
 #define GMAC_INT_EN			0x000000b4
+#define GMAC_1US_TIC_COUNTER		0x000000dc
 #define GMAC_PCS_BASE			0x000000e0
 #define GMAC_PHYIF_CONTROL_STATUS	0x000000f8
 #define GMAC_PMT			0x000000c0
@@ -38,6 +44,22 @@
 #define GMAC_ADDR_HIGH(reg)		(0x300 + reg * 8)
 #define GMAC_ADDR_LOW(reg)		(0x304 + reg * 8)
 
+/* RX Queues Routing */
+#define GMAC_RXQCTRL_AVCPQ_MASK		GENMASK(2, 0)
+#define GMAC_RXQCTRL_AVCPQ_SHIFT	0
+#define GMAC_RXQCTRL_PTPQ_MASK		GENMASK(6, 4)
+#define GMAC_RXQCTRL_PTPQ_SHIFT		4
+#define GMAC_RXQCTRL_DCBCPQ_MASK	GENMASK(10, 8)
+#define GMAC_RXQCTRL_DCBCPQ_SHIFT	8
+#define GMAC_RXQCTRL_UPQ_MASK		GENMASK(14, 12)
+#define GMAC_RXQCTRL_UPQ_SHIFT		12
+#define GMAC_RXQCTRL_MCBCQ_MASK		GENMASK(18, 16)
+#define GMAC_RXQCTRL_MCBCQ_SHIFT	16
+#define GMAC_RXQCTRL_MCBCQEN		BIT(20)
+#define GMAC_RXQCTRL_MCBCQEN_SHIFT	20
+#define GMAC_RXQCTRL_TACPQE		BIT(21)
+#define GMAC_RXQCTRL_TACPQE_SHIFT	21
+
 /* MAC Packet Filtering */
 #define GMAC_PACKET_FILTER_PR		BIT(0)
 #define GMAC_PACKET_FILTER_HMC		BIT(2)
@@ -53,6 +75,14 @@
 /* MAC Flow Control RX */
 #define GMAC_RX_FLOW_CTRL_RFE		BIT(0)
 
+/* RX Queues Priorities */
+#define GMAC_RXQCTRL_PSRQX_MASK(x)	GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_RXQCTRL_PSRQX_SHIFT(x)	((x) * 8)
+
+/* TX Queues Priorities */
+#define GMAC_TXQCTRL_PSTQX_MASK(x)	GENMASK(7 + ((x) * 8), 0 + ((x) * 8))
+#define GMAC_TXQCTRL_PSTQX_SHIFT(x)	((x) * 8)
+
 /* MAC Flow Control TX */
 #define GMAC_TX_FLOW_CTRL_TFE		BIT(1)
 #define GMAC_TX_FLOW_CTRL_PT_SHIFT	16
@@ -148,6 +178,8 @@ enum power_event {
 /* MAC HW features1 bitmap */
 #define GMAC_HW_FEAT_AVSEL		BIT(20)
 #define GMAC_HW_TSOEN			BIT(18)
+#define GMAC_HW_TXFIFOSIZE		GENMASK(10, 6)
+#define GMAC_HW_RXFIFOSIZE		GENMASK(4, 0)
 
 /* MAC HW features2 bitmap */
 #define GMAC_HW_FEAT_TXCHCNT		GENMASK(21, 18)
@@ -161,8 +193,25 @@ enum power_event {
 #define GMAC_HI_REG_AE			BIT(31)
 
 /*  MTL registers */
+#define MTL_OPERATION_MODE		0x00000c00
+#define MTL_OPERATION_SCHALG_MASK	GENMASK(6, 5)
+#define MTL_OPERATION_SCHALG_WRR	(0x0 << 5)
+#define MTL_OPERATION_SCHALG_WFQ	(0x1 << 5)
+#define MTL_OPERATION_SCHALG_DWRR	(0x2 << 5)
+#define MTL_OPERATION_SCHALG_SP		(0x3 << 5)
+#define MTL_OPERATION_RAA		BIT(2)
+#define MTL_OPERATION_RAA_SP		(0x0 << 2)
+#define MTL_OPERATION_RAA_WSP		(0x1 << 2)
+
 #define MTL_INT_STATUS			0x00000c20
-#define MTL_INT_Q0			BIT(0)
+#define MTL_INT_QX(x)			BIT(x)
+
+#define MTL_RXQ_DMA_MAP0		0x00000c30 /* queue 0 to 3 */
+#define MTL_RXQ_DMA_MAP1		0x00000c34 /* queue 4 to 7 */
+#define MTL_RXQ_DMA_Q04MDMACH_MASK	GENMASK(3, 0)
+#define MTL_RXQ_DMA_Q04MDMACH(x)	((x) << 0)
+#define MTL_RXQ_DMA_QXMDMACH_MASK(x)	GENMASK(11 + (8 * ((x) - 1)), 8 * (x))
+#define MTL_RXQ_DMA_QXMDMACH(chan, q)	((chan) << (8 * (q)))
 
 #define MTL_CHAN_BASE_ADDR		0x00000d00
 #define MTL_CHAN_BASE_OFFSET		0x40
@@ -180,6 +229,7 @@ enum power_event {
 #define MTL_OP_MODE_TSF			BIT(1)
 
 #define MTL_OP_MODE_TQS_MASK		GENMASK(24, 16)
+#define MTL_OP_MODE_TQS_SHIFT		16
 
 #define MTL_OP_MODE_TTC_MASK		0x70
 #define MTL_OP_MODE_TTC_SHIFT		4
@@ -193,6 +243,17 @@ enum power_event {
 #define MTL_OP_MODE_TTC_384		(6 << MTL_OP_MODE_TTC_SHIFT)
 #define MTL_OP_MODE_TTC_512		(7 << MTL_OP_MODE_TTC_SHIFT)
 
+#define MTL_OP_MODE_RQS_MASK		GENMASK(29, 20)
+#define MTL_OP_MODE_RQS_SHIFT		20
+
+#define MTL_OP_MODE_RFD_MASK		GENMASK(19, 14)
+#define MTL_OP_MODE_RFD_SHIFT		14
+
+#define MTL_OP_MODE_RFA_MASK		GENMASK(13, 8)
+#define MTL_OP_MODE_RFA_SHIFT		8
+
+#define MTL_OP_MODE_EHFC		BIT(7)
+
 #define MTL_OP_MODE_RTC_MASK		0x18
 #define MTL_OP_MODE_RTC_SHIFT		3
 
@@ -201,6 +262,46 @@ enum power_event {
 #define MTL_OP_MODE_RTC_96		(2 << MTL_OP_MODE_RTC_SHIFT)
 #define MTL_OP_MODE_RTC_128		(3 << MTL_OP_MODE_RTC_SHIFT)
 
+/* MTL ETS Control register */
+#define MTL_ETS_CTRL_BASE_ADDR		0x00000d10
+#define MTL_ETS_CTRL_BASE_OFFSET	0x40
+#define MTL_ETSX_CTRL_BASE_ADDR(x)	(MTL_ETS_CTRL_BASE_ADDR + \
+					((x) * MTL_ETS_CTRL_BASE_OFFSET))
+
+#define MTL_ETS_CTRL_CC			BIT(3)
+#define MTL_ETS_CTRL_AVALG		BIT(2)
+
+/* MTL Queue Quantum Weight */
+#define MTL_TXQ_WEIGHT_BASE_ADDR	0x00000d18
+#define MTL_TXQ_WEIGHT_BASE_OFFSET	0x40
+#define MTL_TXQX_WEIGHT_BASE_ADDR(x)	(MTL_TXQ_WEIGHT_BASE_ADDR + \
+					((x) * MTL_TXQ_WEIGHT_BASE_OFFSET))
+#define MTL_TXQ_WEIGHT_ISCQW_MASK	GENMASK(20, 0)
+
+/* MTL sendSlopeCredit register */
+#define MTL_SEND_SLP_CRED_BASE_ADDR	0x00000d1c
+#define MTL_SEND_SLP_CRED_OFFSET	0x40
+#define MTL_SEND_SLP_CREDX_BASE_ADDR(x)	(MTL_SEND_SLP_CRED_BASE_ADDR + \
+					((x) * MTL_SEND_SLP_CRED_OFFSET))
+
+#define MTL_SEND_SLP_CRED_SSC_MASK	GENMASK(13, 0)
+
+/* MTL hiCredit register */
+#define MTL_HIGH_CRED_BASE_ADDR		0x00000d20
+#define MTL_HIGH_CRED_OFFSET		0x40
+#define MTL_HIGH_CREDX_BASE_ADDR(x)	(MTL_HIGH_CRED_BASE_ADDR + \
+					((x) * MTL_HIGH_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_HC_MASK		GENMASK(28, 0)
+
+/* MTL loCredit register */
+#define MTL_LOW_CRED_BASE_ADDR		0x00000d24
+#define MTL_LOW_CRED_OFFSET		0x40
+#define MTL_LOW_CREDX_BASE_ADDR(x)	(MTL_LOW_CRED_BASE_ADDR + \
+					((x) * MTL_LOW_CRED_OFFSET))
+
+#define MTL_HIGH_CRED_LC_MASK		GENMASK(28, 0)
+
 /*  MTL debug */
 #define MTL_DEBUG_TXSTSFSTS		BIT(5)
 #define MTL_DEBUG_TXFSTS		BIT(4)
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -59,17 +59,211 @@ static void dwmac4_core_init(struct mac_
 	writel(value, ioaddr + GMAC_INT_EN);
 }
 
-static void dwmac4_rx_queue_enable(struct mac_device_info *hw, u32 queue)
+static void dwmac4_rx_queue_enable(struct mac_device_info *hw,
+				   u8 mode, u32 queue)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value = readl(ioaddr + GMAC_RXQ_CTRL0);
 
 	value &= GMAC_RX_QUEUE_CLEAR(queue);
-	value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+	if (mode == MTL_QUEUE_AVB)
+		value |= GMAC_RX_AV_QUEUE_ENABLE(queue);
+	else if (mode == MTL_QUEUE_DCB)
+		value |= GMAC_RX_DCB_QUEUE_ENABLE(queue);
 
 	writel(value, ioaddr + GMAC_RXQ_CTRL0);
 }
 
+static void dwmac4_rx_queue_priority(struct mac_device_info *hw,
+				     u32 prio, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 base_register;
+	u32 value;
+
+	base_register = (queue < 4) ? GMAC_RXQ_CTRL2 : GMAC_RXQ_CTRL3;
+
+	value = readl(ioaddr + base_register);
+
+	value &= ~GMAC_RXQCTRL_PSRQX_MASK(queue);
+	value |= (prio << GMAC_RXQCTRL_PSRQX_SHIFT(queue)) &
+						GMAC_RXQCTRL_PSRQX_MASK(queue);
+	writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_priority(struct mac_device_info *hw,
+				     u32 prio, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 base_register;
+	u32 value;
+
+	base_register = (queue < 4) ? GMAC_TXQ_PRTY_MAP0 : GMAC_TXQ_PRTY_MAP1;
+
+	value = readl(ioaddr + base_register);
+
+	value &= ~GMAC_TXQCTRL_PSTQX_MASK(queue);
+	value |= (prio << GMAC_TXQCTRL_PSTQX_SHIFT(queue)) &
+						GMAC_TXQCTRL_PSTQX_MASK(queue);
+
+	writel(value, ioaddr + base_register);
+}
+
+static void dwmac4_tx_queue_routing(struct mac_device_info *hw,
+				    u8 packet, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	const struct stmmac_rx_routing route_possibilities[] = {
+		{ GMAC_RXQCTRL_AVCPQ_MASK, GMAC_RXQCTRL_AVCPQ_SHIFT },
+		{ GMAC_RXQCTRL_PTPQ_MASK, GMAC_RXQCTRL_PTPQ_SHIFT },
+		{ GMAC_RXQCTRL_DCBCPQ_MASK, GMAC_RXQCTRL_DCBCPQ_SHIFT },
+		{ GMAC_RXQCTRL_UPQ_MASK, GMAC_RXQCTRL_UPQ_SHIFT },
+		{ GMAC_RXQCTRL_MCBCQ_MASK, GMAC_RXQCTRL_MCBCQ_SHIFT },
+	};
+
+	value = readl(ioaddr + GMAC_RXQ_CTRL1);
+
+	/* routing configuration */
+	value &= ~route_possibilities[packet - 1].reg_mask;
+	value |= (queue << route_possibilities[packet-1].reg_shift) &
+		 route_possibilities[packet - 1].reg_mask;
+
+	/* some packets require extra ops */
+	if (packet == PACKET_AVCPQ) {
+		value &= ~GMAC_RXQCTRL_TACPQE;
+		value |= 0x1 << GMAC_RXQCTRL_TACPQE_SHIFT;
+	} else if (packet == PACKET_MCBCQ) {
+		value &= ~GMAC_RXQCTRL_MCBCQEN;
+		value |= 0x1 << GMAC_RXQCTRL_MCBCQEN_SHIFT;
+	}
+
+	writel(value, ioaddr + GMAC_RXQ_CTRL1);
+}
+
+static void dwmac4_prog_mtl_rx_algorithms(struct mac_device_info *hw,
+					  u32 rx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+	value &= ~MTL_OPERATION_RAA;
+	switch (rx_alg) {
+	case MTL_RX_ALGORITHM_SP:
+		value |= MTL_OPERATION_RAA_SP;
+		break;
+	case MTL_RX_ALGORITHM_WSP:
+		value |= MTL_OPERATION_RAA_WSP;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + MTL_OPERATION_MODE);
+}
+
+static void dwmac4_prog_mtl_tx_algorithms(struct mac_device_info *hw,
+					  u32 tx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_OPERATION_MODE);
+
+	value &= ~MTL_OPERATION_SCHALG_MASK;
+	switch (tx_alg) {
+	case MTL_TX_ALGORITHM_WRR:
+		value |= MTL_OPERATION_SCHALG_WRR;
+		break;
+	case MTL_TX_ALGORITHM_WFQ:
+		value |= MTL_OPERATION_SCHALG_WFQ;
+		break;
+	case MTL_TX_ALGORITHM_DWRR:
+		value |= MTL_OPERATION_SCHALG_DWRR;
+		break;
+	case MTL_TX_ALGORITHM_SP:
+		value |= MTL_OPERATION_SCHALG_SP;
+		break;
+	default:
+		break;
+	}
+}
+
+static void dwmac4_set_mtl_tx_queue_weight(struct mac_device_info *hw,
+					   u32 weight, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value = readl(ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+
+	value &= ~MTL_TXQ_WEIGHT_ISCQW_MASK;
+	value |= weight & MTL_TXQ_WEIGHT_ISCQW_MASK;
+	writel(value, ioaddr + MTL_TXQX_WEIGHT_BASE_ADDR(queue));
+}
+
+static void dwmac4_map_mtl_dma(struct mac_device_info *hw, u32 queue, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	if (queue < 4)
+		value = readl(ioaddr + MTL_RXQ_DMA_MAP0);
+	else
+		value = readl(ioaddr + MTL_RXQ_DMA_MAP1);
+
+	if (queue == 0 || queue == 4) {
+		value &= ~MTL_RXQ_DMA_Q04MDMACH_MASK;
+		value |= MTL_RXQ_DMA_Q04MDMACH(chan);
+	} else {
+		value &= ~MTL_RXQ_DMA_QXMDMACH_MASK(queue);
+		value |= MTL_RXQ_DMA_QXMDMACH(chan, queue);
+	}
+
+	if (queue < 4)
+		writel(value, ioaddr + MTL_RXQ_DMA_MAP0);
+	else
+		writel(value, ioaddr + MTL_RXQ_DMA_MAP1);
+}
+
+static void dwmac4_config_cbs(struct mac_device_info *hw,
+			      u32 send_slope, u32 idle_slope,
+			      u32 high_credit, u32 low_credit, u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	pr_debug("Queue %d configured as AVB. Parameters:\n", queue);
+	pr_debug("\tsend_slope: 0x%08x\n", send_slope);
+	pr_debug("\tidle_slope: 0x%08x\n", idle_slope);
+	pr_debug("\thigh_credit: 0x%08x\n", high_credit);
+	pr_debug("\tlow_credit: 0x%08x\n", low_credit);
+
+	/* enable AV algorithm */
+	value = readl(ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+	value |= MTL_ETS_CTRL_AVALG;
+	value |= MTL_ETS_CTRL_CC;
+	writel(value, ioaddr + MTL_ETSX_CTRL_BASE_ADDR(queue));
+
+	/* configure send slope */
+	value = readl(ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_SEND_SLP_CRED_SSC_MASK;
+	value |= send_slope & MTL_SEND_SLP_CRED_SSC_MASK;
+	writel(value, ioaddr + MTL_SEND_SLP_CREDX_BASE_ADDR(queue));
+
+	/* configure idle slope (same register as tx weight) */
+	dwmac4_set_mtl_tx_queue_weight(hw, idle_slope, queue);
+
+	/* configure high credit */
+	value = readl(ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_HIGH_CRED_HC_MASK;
+	value |= high_credit & MTL_HIGH_CRED_HC_MASK;
+	writel(value, ioaddr + MTL_HIGH_CREDX_BASE_ADDR(queue));
+
+	/* configure high credit */
+	value = readl(ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+	value &= ~MTL_HIGH_CRED_LC_MASK;
+	value |= low_credit & MTL_HIGH_CRED_LC_MASK;
+	writel(value, ioaddr + MTL_LOW_CREDX_BASE_ADDR(queue));
+}
+
 static void dwmac4_dump_regs(struct mac_device_info *hw, u32 *reg_space)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -251,11 +445,12 @@ static void dwmac4_set_filter(struct mac
 }
 
 static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
-			     unsigned int fc, unsigned int pause_time)
+			     unsigned int fc, unsigned int pause_time,
+			     u32 tx_cnt)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 channel = STMMAC_CHAN0;	/* FIXME */
 	unsigned int flow = 0;
+	u32 queue = 0;
 
 	pr_debug("GMAC Flow-Control:\n");
 	if (fc & FLOW_RX) {
@@ -265,13 +460,18 @@ static void dwmac4_flow_ctrl(struct mac_
 	}
 	if (fc & FLOW_TX) {
 		pr_debug("\tTransmit Flow-Control ON\n");
-		flow |= GMAC_TX_FLOW_CTRL_TFE;
-		writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
 
-		if (duplex) {
+		if (duplex)
 			pr_debug("\tduplex mode: PAUSE %d\n", pause_time);
-			flow |= (pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
-			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(channel));
+
+		for (queue = 0; queue < tx_cnt; queue++) {
+			flow |= GMAC_TX_FLOW_CTRL_TFE;
+
+			if (duplex)
+				flow |=
+				(pause_time << GMAC_TX_FLOW_CTRL_PT_SHIFT);
+
+			writel(flow, ioaddr + GMAC_QX_TX_FLOW_CTRL(queue));
 		}
 	}
 }
@@ -325,11 +525,34 @@ static void dwmac4_phystatus(void __iome
 	}
 }
 
+static int dwmac4_irq_mtl_status(struct mac_device_info *hw, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 mtl_int_qx_status;
+	int ret = 0;
+
+	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
+
+	/* Check MTL Interrupt */
+	if (mtl_int_qx_status & MTL_INT_QX(chan)) {
+		/* read Queue x Interrupt status */
+		u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(chan));
+
+		if (status & MTL_RX_OVERFLOW_INT) {
+			/*  clear Interrupt */
+			writel(status | MTL_RX_OVERFLOW_INT,
+			       ioaddr + MTL_CHAN_INT_CTRL(chan));
+			ret = CORE_IRQ_MTL_RX_OVERFLOW;
+		}
+	}
+
+	return ret;
+}
+
 static int dwmac4_irq_status(struct mac_device_info *hw,
 			     struct stmmac_extra_stats *x)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 mtl_int_qx_status;
 	u32 intr_status;
 	int ret = 0;
 
@@ -348,20 +571,6 @@ static int dwmac4_irq_status(struct mac_
 		x->irq_receive_pmt_irq_n++;
 	}
 
-	mtl_int_qx_status = readl(ioaddr + MTL_INT_STATUS);
-	/* Check MTL Interrupt: Currently only one queue is used: Q0. */
-	if (mtl_int_qx_status & MTL_INT_Q0) {
-		/* read Queue 0 Interrupt status */
-		u32 status = readl(ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-
-		if (status & MTL_RX_OVERFLOW_INT) {
-			/*  clear Interrupt */
-			writel(status | MTL_RX_OVERFLOW_INT,
-			       ioaddr + MTL_CHAN_INT_CTRL(STMMAC_CHAN0));
-			ret = CORE_IRQ_MTL_RX_OVERFLOW;
-		}
-	}
-
 	dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x);
 	if (intr_status & PCS_RGSMIIIS_IRQ)
 		dwmac4_phystatus(ioaddr, x);
@@ -369,64 +578,69 @@ static int dwmac4_irq_status(struct mac_
 	return ret;
 }
 
-static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
+static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			 u32 rx_queues, u32 tx_queues)
 {
 	u32 value;
+	u32 queue;
 
-	/*  Currently only channel 0 is supported */
-	value = readl(ioaddr + MTL_CHAN_TX_DEBUG(STMMAC_CHAN0));
+	for (queue = 0; queue < tx_queues; queue++) {
+		value = readl(ioaddr + MTL_CHAN_TX_DEBUG(queue));
 
-	if (value & MTL_DEBUG_TXSTSFSTS)
-		x->mtl_tx_status_fifo_full++;
-	if (value & MTL_DEBUG_TXFSTS)
-		x->mtl_tx_fifo_not_empty++;
-	if (value & MTL_DEBUG_TWCSTS)
-		x->mmtl_fifo_ctrl++;
-	if (value & MTL_DEBUG_TRCSTS_MASK) {
-		u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
-			     >> MTL_DEBUG_TRCSTS_SHIFT;
-		if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
-			x->mtl_tx_fifo_read_ctrl_write++;
-		else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
-			x->mtl_tx_fifo_read_ctrl_wait++;
-		else if (trcsts == MTL_DEBUG_TRCSTS_READ)
-			x->mtl_tx_fifo_read_ctrl_read++;
-		else
-			x->mtl_tx_fifo_read_ctrl_idle++;
+		if (value & MTL_DEBUG_TXSTSFSTS)
+			x->mtl_tx_status_fifo_full++;
+		if (value & MTL_DEBUG_TXFSTS)
+			x->mtl_tx_fifo_not_empty++;
+		if (value & MTL_DEBUG_TWCSTS)
+			x->mmtl_fifo_ctrl++;
+		if (value & MTL_DEBUG_TRCSTS_MASK) {
+			u32 trcsts = (value & MTL_DEBUG_TRCSTS_MASK)
+				     >> MTL_DEBUG_TRCSTS_SHIFT;
+			if (trcsts == MTL_DEBUG_TRCSTS_WRITE)
+				x->mtl_tx_fifo_read_ctrl_write++;
+			else if (trcsts == MTL_DEBUG_TRCSTS_TXW)
+				x->mtl_tx_fifo_read_ctrl_wait++;
+			else if (trcsts == MTL_DEBUG_TRCSTS_READ)
+				x->mtl_tx_fifo_read_ctrl_read++;
+			else
+				x->mtl_tx_fifo_read_ctrl_idle++;
+		}
+		if (value & MTL_DEBUG_TXPAUSED)
+			x->mac_tx_in_pause++;
 	}
-	if (value & MTL_DEBUG_TXPAUSED)
-		x->mac_tx_in_pause++;
 
-	value = readl(ioaddr + MTL_CHAN_RX_DEBUG(STMMAC_CHAN0));
+	for (queue = 0; queue < rx_queues; queue++) {
+		value = readl(ioaddr + MTL_CHAN_RX_DEBUG(queue));
 
-	if (value & MTL_DEBUG_RXFSTS_MASK) {
-		u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
-			     >> MTL_DEBUG_RRCSTS_SHIFT;
-
-		if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
-			x->mtl_rx_fifo_fill_level_full++;
-		else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
-			x->mtl_rx_fifo_fill_above_thresh++;
-		else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
-			x->mtl_rx_fifo_fill_below_thresh++;
-		else
-			x->mtl_rx_fifo_fill_level_empty++;
-	}
-	if (value & MTL_DEBUG_RRCSTS_MASK) {
-		u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
-			     MTL_DEBUG_RRCSTS_SHIFT;
-
-		if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
-			x->mtl_rx_fifo_read_ctrl_flush++;
-		else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
-			x->mtl_rx_fifo_read_ctrl_read_data++;
-		else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
-			x->mtl_rx_fifo_read_ctrl_status++;
-		else
-			x->mtl_rx_fifo_read_ctrl_idle++;
+		if (value & MTL_DEBUG_RXFSTS_MASK) {
+			u32 rxfsts = (value & MTL_DEBUG_RXFSTS_MASK)
+				     >> MTL_DEBUG_RRCSTS_SHIFT;
+
+			if (rxfsts == MTL_DEBUG_RXFSTS_FULL)
+				x->mtl_rx_fifo_fill_level_full++;
+			else if (rxfsts == MTL_DEBUG_RXFSTS_AT)
+				x->mtl_rx_fifo_fill_above_thresh++;
+			else if (rxfsts == MTL_DEBUG_RXFSTS_BT)
+				x->mtl_rx_fifo_fill_below_thresh++;
+			else
+				x->mtl_rx_fifo_fill_level_empty++;
+		}
+		if (value & MTL_DEBUG_RRCSTS_MASK) {
+			u32 rrcsts = (value & MTL_DEBUG_RRCSTS_MASK) >>
+				     MTL_DEBUG_RRCSTS_SHIFT;
+
+			if (rrcsts == MTL_DEBUG_RRCSTS_FLUSH)
+				x->mtl_rx_fifo_read_ctrl_flush++;
+			else if (rrcsts == MTL_DEBUG_RRCSTS_RSTAT)
+				x->mtl_rx_fifo_read_ctrl_read_data++;
+			else if (rrcsts == MTL_DEBUG_RRCSTS_RDATA)
+				x->mtl_rx_fifo_read_ctrl_status++;
+			else
+				x->mtl_rx_fifo_read_ctrl_idle++;
+		}
+		if (value & MTL_DEBUG_RWCSTS)
+			x->mtl_rx_fifo_ctrl_active++;
 	}
-	if (value & MTL_DEBUG_RWCSTS)
-		x->mtl_rx_fifo_ctrl_active++;
 
 	/* GMAC debug */
 	value = readl(ioaddr + GMAC_DEBUG);
@@ -455,10 +669,51 @@ static void dwmac4_debug(void __iomem *i
 
 static const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
+	.set_mac = stmmac_set_mac,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.rx_queue_prio = dwmac4_rx_queue_priority,
+	.tx_queue_prio = dwmac4_tx_queue_priority,
+	.rx_queue_routing = dwmac4_tx_queue_routing,
+	.prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+	.map_mtl_to_dma = dwmac4_map_mtl_dma,
+	.config_cbs = dwmac4_config_cbs,
 	.dump_regs = dwmac4_dump_regs,
 	.host_irq_status = dwmac4_irq_status,
+	.host_mtl_irq_status = dwmac4_irq_mtl_status,
+	.flow_ctrl = dwmac4_flow_ctrl,
+	.pmt = dwmac4_pmt,
+	.set_umac_addr = dwmac4_set_umac_addr,
+	.get_umac_addr = dwmac4_get_umac_addr,
+	.set_eee_mode = dwmac4_set_eee_mode,
+	.reset_eee_mode = dwmac4_reset_eee_mode,
+	.set_eee_timer = dwmac4_set_eee_timer,
+	.set_eee_pls = dwmac4_set_eee_pls,
+	.pcs_ctrl_ane = dwmac4_ctrl_ane,
+	.pcs_rane = dwmac4_rane,
+	.pcs_get_adv_lp = dwmac4_get_adv_lp,
+	.debug = dwmac4_debug,
+	.set_filter = dwmac4_set_filter,
+};
+
+static const struct stmmac_ops dwmac410_ops = {
+	.core_init = dwmac4_core_init,
+	.set_mac = stmmac_dwmac4_set_mac,
+	.rx_ipc = dwmac4_rx_ipc_enable,
+	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.rx_queue_prio = dwmac4_rx_queue_priority,
+	.tx_queue_prio = dwmac4_tx_queue_priority,
+	.rx_queue_routing = dwmac4_tx_queue_routing,
+	.prog_mtl_rx_algorithms = dwmac4_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwmac4_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = dwmac4_set_mtl_tx_queue_weight,
+	.map_mtl_to_dma = dwmac4_map_mtl_dma,
+	.config_cbs = dwmac4_config_cbs,
+	.dump_regs = dwmac4_dump_regs,
+	.host_irq_status = dwmac4_irq_status,
+	.host_mtl_irq_status = dwmac4_irq_mtl_status,
 	.flow_ctrl = dwmac4_flow_ctrl,
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
@@ -492,8 +747,6 @@ struct mac_device_info *dwmac4_setup(voi
 	if (mac->multicast_filter_bins)
 		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
 
-	mac->mac = &dwmac4_ops;
-
 	mac->link.port = GMAC_CONFIG_PS;
 	mac->link.duplex = GMAC_CONFIG_DM;
 	mac->link.speed = GMAC_CONFIG_FES;
@@ -514,5 +767,10 @@ struct mac_device_info *dwmac4_setup(voi
 	else
 		mac->dma = &dwmac4_dma_ops;
 
+	if (*synopsys_id >= DWMAC_CORE_4_00)
+		mac->mac = &dwmac410_ops;
+	else
+		mac->mac = &dwmac4_ops;
+
 	return mac;
 }
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -214,13 +214,13 @@ static int dwmac4_wrback_get_tx_timestam
 {
 	/* Context type from W/B descriptor must be zero */
 	if (le32_to_cpu(p->des3) & TDES3_CONTEXT_TYPE)
-		return -EINVAL;
+		return 0;
 
 	/* Tx Timestamp Status is 1 so des0 and des1'll have valid values */
 	if (le32_to_cpu(p->des3) & TDES3_TIMESTAMP_STATUS)
-		return 0;
+		return 1;
 
-	return 1;
+	return 0;
 }
 
 static inline u64 dwmac4_get_timestamp(void *desc, u32 ats)
@@ -282,7 +282,10 @@ static int dwmac4_wrback_get_rx_timestam
 		}
 	}
 exit:
-	return ret;
+	if (likely(ret == 0))
+		return 1;
+
+	return 0;
 }
 
 static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
@@ -304,12 +307,13 @@ static void dwmac4_rd_init_tx_desc(struc
 
 static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				      bool csum_flag, int mode, bool tx_own,
-				      bool ls)
+				      bool ls, unsigned int tot_pkt_len)
 {
 	unsigned int tdes3 = le32_to_cpu(p->des3);
 
 	p->des2 |= cpu_to_le32(len & TDES2_BUFFER1_SIZE_MASK);
 
+	tdes3 |= tot_pkt_len & TDES3_PACKET_SIZE_MASK;
 	if (is_fs)
 		tdes3 |= TDES3_FIRST_DESCRIPTOR;
 	else
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -71,36 +71,48 @@ static void dwmac4_dma_axi(void __iomem
 	writel(value, ioaddr + DMA_SYS_BUS_MODE);
 }
 
-static void dwmac4_dma_init_channel(void __iomem *ioaddr,
-				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 dma_rx_phy,
-				    u32 channel)
+void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_rx_phy, u32 chan)
 {
 	u32 value;
-	int txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
-	int rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
 
-	/* set PBL for each channels. Currently we affect same configuration
-	 * on each channel
-	 */
-	value = readl(ioaddr + DMA_CHAN_CONTROL(channel));
-	if (dma_cfg->pblx8)
-		value = value | DMA_BUS_MODE_PBL;
-	writel(value, ioaddr + DMA_CHAN_CONTROL(channel));
+	value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
+	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
+
+	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
+}
 
-	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(channel));
+void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg,
+			     u32 dma_tx_phy, u32 chan)
+{
+	u32 value;
+	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+
+	value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 	value = value | (txpbl << DMA_BUS_MODE_PBL_SHIFT);
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(channel));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
-	value = readl(ioaddr + DMA_CHAN_RX_CONTROL(channel));
-	value = value | (rxpbl << DMA_BUS_MODE_RPBL_SHIFT);
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(channel));
+	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+}
 
-	/* Mask interrupts by writing to CSR7 */
-	writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr + DMA_CHAN_INTR_ENA(channel));
+void dwmac4_dma_init_channel(void __iomem *ioaddr,
+			     struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+	u32 value;
+
+	/* common channel control register config */
+	value = readl(ioaddr + DMA_CHAN_CONTROL(chan));
+	if (dma_cfg->pblx8)
+		value = value | DMA_BUS_MODE_PBL;
+	writel(value, ioaddr + DMA_CHAN_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(channel));
-	writel(dma_rx_phy, ioaddr + DMA_CHAN_RX_BASE_ADDR(channel));
+	/* Mask interrupts by writing to CSR7 */
+	writel(DMA_CHAN_INTR_DEFAULT_MASK,
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 static void dwmac4_dma_init(void __iomem *ioaddr,
@@ -108,7 +120,6 @@ static void dwmac4_dma_init(void __iomem
 			    u32 dma_tx, u32 dma_rx, int atds)
 {
 	u32 value = readl(ioaddr + DMA_SYS_BUS_MODE);
-	int i;
 
 	/* Set the Fixed burst mode */
 	if (dma_cfg->fixed_burst)
@@ -122,9 +133,6 @@ static void dwmac4_dma_init(void __iomem
 		value |= DMA_SYS_BUS_AAL;
 
 	writel(value, ioaddr + DMA_SYS_BUS_MODE);
-
-	for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
-		dwmac4_dma_init_channel(ioaddr, dma_cfg, dma_tx, dma_rx, i);
 }
 
 static void _dwmac4_dump_dma_regs(void __iomem *ioaddr, u32 channel,
@@ -174,46 +182,121 @@ static void dwmac4_dump_dma_regs(void __
 		_dwmac4_dump_dma_regs(ioaddr, i, reg_space);
 }
 
-static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt)
+static void dwmac4_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 number_chan)
 {
-	int i;
+	u32 chan;
 
-	for (i = 0; i < DMA_CHANNEL_NB_MAX; i++)
-		writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(i));
+	for (chan = 0; chan < number_chan; chan++)
+		writel(riwt, ioaddr + DMA_CHAN_RX_WATCHDOG(chan));
 }
 
-static void dwmac4_dma_chan_op_mode(void __iomem *ioaddr, int txmode,
-				    int rxmode, u32 channel)
+static void dwmac4_dma_rx_chan_op_mode(void __iomem *ioaddr, int mode,
+				       u32 channel, int fifosz)
 {
-	u32 mtl_tx_op, mtl_rx_op, mtl_rx_int;
+	unsigned int rqs = fifosz / 256 - 1;
+	u32 mtl_rx_op, mtl_rx_int;
 
-	/* Following code only done for channel 0, other channels not yet
-	 * supported.
-	 */
-	mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+	if (mode == SF_DMA_MODE) {
+		pr_debug("GMAC: enable RX store and forward mode\n");
+		mtl_rx_op |= MTL_OP_MODE_RSF;
+	} else {
+		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", mode);
+		mtl_rx_op &= ~MTL_OP_MODE_RSF;
+		mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
+		if (mode <= 32)
+			mtl_rx_op |= MTL_OP_MODE_RTC_32;
+		else if (mode <= 64)
+			mtl_rx_op |= MTL_OP_MODE_RTC_64;
+		else if (mode <= 96)
+			mtl_rx_op |= MTL_OP_MODE_RTC_96;
+		else
+			mtl_rx_op |= MTL_OP_MODE_RTC_128;
+	}
+
+	mtl_rx_op &= ~MTL_OP_MODE_RQS_MASK;
+	mtl_rx_op |= rqs << MTL_OP_MODE_RQS_SHIFT;
+
+	/* enable flow control only if each channel gets 4 KiB or more FIFO */
+	if (fifosz >= 4096) {
+		unsigned int rfd, rfa;
+
+		mtl_rx_op |= MTL_OP_MODE_EHFC;
+
+		/* Set Threshold for Activating Flow Control to min 2 frames,
+		 * i.e. 1500 * 2 = 3000 bytes.
+		 *
+		 * Set Threshold for Deactivating Flow Control to min 1 frame,
+		 * i.e. 1500 bytes.
+		 */
+		switch (fifosz) {
+		case 4096:
+			/* This violates the above formula because of FIFO size
+			 * limit therefore overflow may occur in spite of this.
+			 */
+			rfd = 0x03; /* Full-2.5K */
+			rfa = 0x01; /* Full-1.5K */
+			break;
+
+		case 8192:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x0a; /* Full-6K */
+			break;
+
+		case 16384:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x12; /* Full-10K */
+			break;
+
+		default:
+			rfd = 0x06; /* Full-4K */
+			rfa = 0x1e; /* Full-16K */
+			break;
+		}
 
-	if (txmode == SF_DMA_MODE) {
+		mtl_rx_op &= ~MTL_OP_MODE_RFD_MASK;
+		mtl_rx_op |= rfd << MTL_OP_MODE_RFD_SHIFT;
+
+		mtl_rx_op &= ~MTL_OP_MODE_RFA_MASK;
+		mtl_rx_op |= rfa << MTL_OP_MODE_RFA_SHIFT;
+	}
+
+	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
+
+	/* Enable MTL RX overflow */
+	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
+	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
+	       ioaddr + MTL_CHAN_INT_CTRL(channel));
+}
+
+static void dwmac4_dma_tx_chan_op_mode(void __iomem *ioaddr, int mode,
+				       u32 channel)
+{
+	u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+	if (mode == SF_DMA_MODE) {
 		pr_debug("GMAC: enable TX store and forward mode\n");
 		/* Transmit COE type 2 cannot be done in cut-through mode. */
 		mtl_tx_op |= MTL_OP_MODE_TSF;
 	} else {
-		pr_debug("GMAC: disabling TX SF (threshold %d)\n", txmode);
+		pr_debug("GMAC: disabling TX SF (threshold %d)\n", mode);
 		mtl_tx_op &= ~MTL_OP_MODE_TSF;
 		mtl_tx_op &= MTL_OP_MODE_TTC_MASK;
 		/* Set the transmit threshold */
-		if (txmode <= 32)
+		if (mode <= 32)
 			mtl_tx_op |= MTL_OP_MODE_TTC_32;
-		else if (txmode <= 64)
+		else if (mode <= 64)
 			mtl_tx_op |= MTL_OP_MODE_TTC_64;
-		else if (txmode <= 96)
+		else if (mode <= 96)
 			mtl_tx_op |= MTL_OP_MODE_TTC_96;
-		else if (txmode <= 128)
+		else if (mode <= 128)
 			mtl_tx_op |= MTL_OP_MODE_TTC_128;
-		else if (txmode <= 192)
+		else if (mode <= 192)
 			mtl_tx_op |= MTL_OP_MODE_TTC_192;
-		else if (txmode <= 256)
+		else if (mode <= 256)
 			mtl_tx_op |= MTL_OP_MODE_TTC_256;
-		else if (txmode <= 384)
+		else if (mode <= 384)
 			mtl_tx_op |= MTL_OP_MODE_TTC_384;
 		else
 			mtl_tx_op |= MTL_OP_MODE_TTC_512;
@@ -230,39 +313,6 @@ static void dwmac4_dma_chan_op_mode(void
 	 */
 	mtl_tx_op |= MTL_OP_MODE_TXQEN | MTL_OP_MODE_TQS_MASK;
 	writel(mtl_tx_op, ioaddr +  MTL_CHAN_TX_OP_MODE(channel));
-
-	mtl_rx_op = readl(ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	if (rxmode == SF_DMA_MODE) {
-		pr_debug("GMAC: enable RX store and forward mode\n");
-		mtl_rx_op |= MTL_OP_MODE_RSF;
-	} else {
-		pr_debug("GMAC: disable RX SF mode (threshold %d)\n", rxmode);
-		mtl_rx_op &= ~MTL_OP_MODE_RSF;
-		mtl_rx_op &= MTL_OP_MODE_RTC_MASK;
-		if (rxmode <= 32)
-			mtl_rx_op |= MTL_OP_MODE_RTC_32;
-		else if (rxmode <= 64)
-			mtl_rx_op |= MTL_OP_MODE_RTC_64;
-		else if (rxmode <= 96)
-			mtl_rx_op |= MTL_OP_MODE_RTC_96;
-		else
-			mtl_rx_op |= MTL_OP_MODE_RTC_128;
-	}
-
-	writel(mtl_rx_op, ioaddr + MTL_CHAN_RX_OP_MODE(channel));
-
-	/* Enable MTL RX overflow */
-	mtl_rx_int = readl(ioaddr + MTL_CHAN_INT_CTRL(channel));
-	writel(mtl_rx_int | MTL_RX_OVERFLOW_INT_EN,
-	       ioaddr + MTL_CHAN_INT_CTRL(channel));
-}
-
-static void dwmac4_dma_operation_mode(void __iomem *ioaddr, int txmode,
-				      int rxmode, int rxfifosz)
-{
-	/* Only Channel 0 is actually configured and used */
-	dwmac4_dma_chan_op_mode(ioaddr, txmode, rxmode, 0);
 }
 
 static void dwmac4_get_hw_feature(void __iomem *ioaddr,
@@ -294,6 +344,11 @@ static void dwmac4_get_hw_feature(void _
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE1);
 	dma_cap->av = (hw_cap & GMAC_HW_FEAT_AVSEL) >> 20;
 	dma_cap->tsoen = (hw_cap & GMAC_HW_TSOEN) >> 18;
+	/* RX and TX FIFO sizes are encoded as log2(n / 128). Undo that by
+	 * shifting and store the sizes in bytes.
+	 */
+	dma_cap->tx_fifo_size = 128 << ((hw_cap & GMAC_HW_TXFIFOSIZE) >> 6);
+	dma_cap->rx_fifo_size = 128 << ((hw_cap & GMAC_HW_RXFIFOSIZE) >> 0);
 	/* MAC HW feature2 */
 	hw_cap = readl(ioaddr + GMAC_HW_FEATURE2);
 	/* TX and RX number of channels */
@@ -332,9 +387,13 @@ static void dwmac4_enable_tso(void __iom
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
+	.init_chan = dwmac4_dma_init_channel,
+	.init_rx_chan = dwmac4_dma_init_rx_chan,
+	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,
 	.dump_regs = dwmac4_dump_dma_regs,
-	.dma_mode = dwmac4_dma_operation_mode,
+	.dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+	.dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
 	.enable_dma_irq = dwmac4_enable_dma_irq,
 	.disable_dma_irq = dwmac4_disable_dma_irq,
 	.start_tx = dwmac4_dma_start_tx,
@@ -354,9 +413,13 @@ const struct stmmac_dma_ops dwmac4_dma_o
 const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
+	.init_chan = dwmac4_dma_init_channel,
+	.init_rx_chan = dwmac4_dma_init_rx_chan,
+	.init_tx_chan = dwmac4_dma_init_tx_chan,
 	.axi = dwmac4_dma_axi,
 	.dump_regs = dwmac4_dump_dma_regs,
-	.dma_mode = dwmac4_dma_operation_mode,
+	.dma_rx_mode = dwmac4_dma_rx_chan_op_mode,
+	.dma_tx_mode = dwmac4_dma_tx_chan_op_mode,
 	.enable_dma_irq = dwmac410_enable_dma_irq,
 	.disable_dma_irq = dwmac4_disable_dma_irq,
 	.start_tx = dwmac4_dma_start_tx,
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
@@ -185,17 +185,17 @@
 
 int dwmac4_dma_reset(void __iomem *ioaddr);
 void dwmac4_enable_dma_transmission(void __iomem *ioaddr, u32 tail_ptr);
-void dwmac4_enable_dma_irq(void __iomem *ioaddr);
-void dwmac410_enable_dma_irq(void __iomem *ioaddr);
-void dwmac4_disable_dma_irq(void __iomem *ioaddr);
-void dwmac4_dma_start_tx(void __iomem *ioaddr);
-void dwmac4_dma_stop_tx(void __iomem *ioaddr);
-void dwmac4_dma_start_rx(void __iomem *ioaddr);
-void dwmac4_dma_stop_rx(void __iomem *ioaddr);
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan);
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
-			 struct stmmac_extra_stats *x);
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len);
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len);
+			 struct stmmac_extra_stats *x, u32 chan);
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan);
 void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
@@ -37,96 +37,96 @@ int dwmac4_dma_reset(void __iomem *ioadd
 
 void dwmac4_set_rx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
 {
-	writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(0));
+	writel(tail_ptr, ioaddr + DMA_CHAN_RX_END_ADDR(chan));
 }
 
 void dwmac4_set_tx_tail_ptr(void __iomem *ioaddr, u32 tail_ptr, u32 chan)
 {
-	writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(0));
+	writel(tail_ptr, ioaddr + DMA_CHAN_TX_END_ADDR(chan));
 }
 
-void dwmac4_dma_start_tx(void __iomem *ioaddr)
+void dwmac4_dma_start_tx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value |= DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value |= GMAC_CONFIG_TE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_stop_tx(void __iomem *ioaddr)
+void dwmac4_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value &= ~DMA_CONTROL_ST;
-	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value &= ~GMAC_CONFIG_TE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_start_rx(void __iomem *ioaddr)
+void dwmac4_dma_start_rx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value |= DMA_CONTROL_SR;
 
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value |= GMAC_CONFIG_RE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_dma_stop_rx(void __iomem *ioaddr)
+void dwmac4_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 {
-	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	u32 value = readl(ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value &= ~DMA_CONTROL_SR;
-	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(STMMAC_CHAN0));
+	writel(value, ioaddr + DMA_CHAN_RX_CONTROL(chan));
 
 	value = readl(ioaddr + GMAC_CONFIG);
 	value &= ~GMAC_CONFIG_RE;
 	writel(value, ioaddr + GMAC_CONFIG);
 }
 
-void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
 {
-	writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(STMMAC_CHAN0));
+	writel(len, ioaddr + DMA_CHAN_TX_RING_LEN(chan));
 }
 
-void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len)
+void dwmac4_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
 {
-	writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(STMMAC_CHAN0));
+	writel(len, ioaddr + DMA_CHAN_RX_RING_LEN(chan));
 }
 
-void dwmac4_enable_dma_irq(void __iomem *ioaddr)
+void dwmac4_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_CHAN_INTR_DEFAULT_MASK, ioaddr +
-	       DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	       DMA_CHAN_INTR_ENA(chan));
 }
 
-void dwmac410_enable_dma_irq(void __iomem *ioaddr)
+void dwmac410_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_CHAN_INTR_DEFAULT_MASK_4_10,
-	       ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	       ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
-void dwmac4_disable_dma_irq(void __iomem *ioaddr)
+void dwmac4_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
-	writel(0, ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+	writel(0, ioaddr + DMA_CHAN_INTR_ENA(chan));
 }
 
 int dwmac4_dma_interrupt(void __iomem *ioaddr,
-			 struct stmmac_extra_stats *x)
+			 struct stmmac_extra_stats *x, u32 chan)
 {
 	int ret = 0;
 
-	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(0));
+	u32 intr_status = readl(ioaddr + DMA_CHAN_STATUS(chan));
 
 	/* ABNORMAL interrupts */
 	if (unlikely(intr_status & DMA_CHAN_STATUS_AIS)) {
@@ -153,7 +153,7 @@ int dwmac4_dma_interrupt(void __iomem *i
 		if (likely(intr_status & DMA_CHAN_STATUS_RI)) {
 			u32 value;
 
-			value = readl(ioaddr + DMA_CHAN_INTR_ENA(STMMAC_CHAN0));
+			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++;
@@ -172,7 +172,7 @@ int dwmac4_dma_interrupt(void __iomem *i
 	 * status [21-0] expect reserved bits [5-3]
 	 */
 	writel((intr_status & 0x3fffc7),
-	       ioaddr + DMA_CHAN_STATUS(STMMAC_CHAN0));
+	       ioaddr + DMA_CHAN_STATUS(chan));
 
 	return ret;
 }
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -137,13 +137,14 @@
 #define DMA_CONTROL_FTF		0x00100000	/* Flush transmit FIFO */
 
 void dwmac_enable_dma_transmission(void __iomem *ioaddr);
-void dwmac_enable_dma_irq(void __iomem *ioaddr);
-void dwmac_disable_dma_irq(void __iomem *ioaddr);
-void dwmac_dma_start_tx(void __iomem *ioaddr);
-void dwmac_dma_stop_tx(void __iomem *ioaddr);
-void dwmac_dma_start_rx(void __iomem *ioaddr);
-void dwmac_dma_stop_rx(void __iomem *ioaddr);
-int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x);
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan);
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan);
+int dwmac_dma_interrupt(void __iomem *ioaddr, struct stmmac_extra_stats *x,
+			u32 chan);
 int dwmac_dma_reset(void __iomem *ioaddr);
 
 #endif /* __DWMAC_DMA_H__ */
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_lib.c
@@ -47,38 +47,38 @@ void dwmac_enable_dma_transmission(void
 	writel(1, ioaddr + DMA_XMT_POLL_DEMAND);
 }
 
-void dwmac_enable_dma_irq(void __iomem *ioaddr)
+void dwmac_enable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(DMA_INTR_DEFAULT_MASK, ioaddr + DMA_INTR_ENA);
 }
 
-void dwmac_disable_dma_irq(void __iomem *ioaddr)
+void dwmac_disable_dma_irq(void __iomem *ioaddr, u32 chan)
 {
 	writel(0, ioaddr + DMA_INTR_ENA);
 }
 
-void dwmac_dma_start_tx(void __iomem *ioaddr)
+void dwmac_dma_start_tx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value |= DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_stop_tx(void __iomem *ioaddr)
+void dwmac_dma_stop_tx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value &= ~DMA_CONTROL_ST;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_start_rx(void __iomem *ioaddr)
+void dwmac_dma_start_rx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value |= DMA_CONTROL_SR;
 	writel(value, ioaddr + DMA_CONTROL);
 }
 
-void dwmac_dma_stop_rx(void __iomem *ioaddr)
+void dwmac_dma_stop_rx(void __iomem *ioaddr, u32 chan)
 {
 	u32 value = readl(ioaddr + DMA_CONTROL);
 	value &= ~DMA_CONTROL_SR;
@@ -156,7 +156,7 @@ static void show_rx_process_state(unsign
 #endif
 
 int dwmac_dma_interrupt(void __iomem *ioaddr,
-			struct stmmac_extra_stats *x)
+			struct stmmac_extra_stats *x, u32 chan)
 {
 	int ret = 0;
 	/* read the status register (CSR5) */
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -315,7 +315,7 @@ static void enh_desc_release_tx_desc(str
 
 static void enh_desc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				     bool csum_flag, int mode, bool tx_own,
-				     bool ls)
+				     bool ls, unsigned int tot_pkt_len)
 {
 	unsigned int tdes0 = le32_to_cpu(p->des0);
 
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -191,7 +191,7 @@ static void ndesc_release_tx_desc(struct
 
 static void ndesc_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
 				  bool csum_flag, int mode, bool tx_own,
-				  bool ls)
+				  bool ls, unsigned int tot_pkt_len)
 {
 	unsigned int tdes1 = le32_to_cpu(p->des1);
 
--- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
+++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c
@@ -26,16 +26,17 @@
 
 static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)p;
-	unsigned int entry = priv->cur_tx;
-	struct dma_desc *desc;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p;
 	unsigned int nopaged_len = skb_headlen(skb);
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->cur_tx;
 	unsigned int bmax, len, des2;
+	struct dma_desc *desc;
 
 	if (priv->extend_desc)
-		desc = (struct dma_desc *)(priv->dma_etx + entry);
+		desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 	else
-		desc = priv->dma_tx + entry;
+		desc = tx_q->dma_tx + entry;
 
 	if (priv->plat->enh_desc)
 		bmax = BUF_SIZE_8KiB;
@@ -52,48 +53,51 @@ static int stmmac_jumbo_frm(void *p, str
 		if (dma_mapping_error(priv->device, des2))
 			return -1;
 
-		priv->tx_skbuff_dma[entry].buf = des2;
-		priv->tx_skbuff_dma[entry].len = bmax;
-		priv->tx_skbuff_dma[entry].is_jumbo = true;
+		tx_q->tx_skbuff_dma[entry].buf = des2;
+		tx_q->tx_skbuff_dma[entry].len = bmax;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum,
-						STMMAC_RING_MODE, 0, false);
-		priv->tx_skbuff[entry] = NULL;
+						STMMAC_RING_MODE, 0,
+						false, skb->len);
+		tx_q->tx_skbuff[entry] = NULL;
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
 		if (priv->extend_desc)
-			desc = (struct dma_desc *)(priv->dma_etx + entry);
+			desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 		else
-			desc = priv->dma_tx + entry;
+			desc = tx_q->dma_tx + entry;
 
 		des2 = dma_map_single(priv->device, skb->data + bmax, len,
 				      DMA_TO_DEVICE);
 		desc->des2 = cpu_to_le32(des2);
 		if (dma_mapping_error(priv->device, des2))
 			return -1;
-		priv->tx_skbuff_dma[entry].buf = des2;
-		priv->tx_skbuff_dma[entry].len = len;
-		priv->tx_skbuff_dma[entry].is_jumbo = true;
+		tx_q->tx_skbuff_dma[entry].buf = des2;
+		tx_q->tx_skbuff_dma[entry].len = len;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum,
-						STMMAC_RING_MODE, 1, true);
+						STMMAC_RING_MODE, 1,
+						true, skb->len);
 	} else {
 		des2 = dma_map_single(priv->device, skb->data,
 				      nopaged_len, DMA_TO_DEVICE);
 		desc->des2 = cpu_to_le32(des2);
 		if (dma_mapping_error(priv->device, des2))
 			return -1;
-		priv->tx_skbuff_dma[entry].buf = des2;
-		priv->tx_skbuff_dma[entry].len = nopaged_len;
-		priv->tx_skbuff_dma[entry].is_jumbo = true;
+		tx_q->tx_skbuff_dma[entry].buf = des2;
+		tx_q->tx_skbuff_dma[entry].len = nopaged_len;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = true;
 		desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB);
 		priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum,
-						STMMAC_RING_MODE, 0, true);
+						STMMAC_RING_MODE, 0,
+						true, skb->len);
 	}
 
-	priv->cur_tx = entry;
+	tx_q->cur_tx = entry;
 
 	return entry;
 }
@@ -125,12 +129,13 @@ static void stmmac_init_desc3(struct dma
 
 static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p)
 {
-	struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr;
-	unsigned int entry = priv->dirty_tx;
+	struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr;
+	struct stmmac_priv *priv = tx_q->priv_data;
+	unsigned int entry = tx_q->dirty_tx;
 
 	/* des3 is only used for jumbo frames tx or time stamping */
-	if (unlikely(priv->tx_skbuff_dma[entry].is_jumbo ||
-		     (priv->tx_skbuff_dma[entry].last_segment &&
+	if (unlikely(tx_q->tx_skbuff_dma[entry].is_jumbo ||
+		     (tx_q->tx_skbuff_dma[entry].last_segment &&
 		      !priv->extend_desc && priv->hwts_tx_en)))
 		p->des3 = 0;
 }
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -46,38 +46,51 @@ struct stmmac_tx_info {
 	bool is_jumbo;
 };
 
-struct stmmac_priv {
-	/* Frequently used values are kept adjacent for cache effect */
+/* Frequently used values are kept adjacent for cache effect */
+struct stmmac_tx_queue {
+	u32 queue_index;
+	struct stmmac_priv *priv_data;
 	struct dma_extended_desc *dma_etx ____cacheline_aligned_in_smp;
 	struct dma_desc *dma_tx;
 	struct sk_buff **tx_skbuff;
+	struct stmmac_tx_info *tx_skbuff_dma;
 	unsigned int cur_tx;
 	unsigned int dirty_tx;
+	dma_addr_t dma_tx_phy;
+	u32 tx_tail_addr;
+};
+
+struct stmmac_rx_queue {
+	u32 queue_index;
+	struct stmmac_priv *priv_data;
+	struct dma_extended_desc *dma_erx;
+	struct dma_desc *dma_rx ____cacheline_aligned_in_smp;
+	struct sk_buff **rx_skbuff;
+	dma_addr_t *rx_skbuff_dma;
+	unsigned int cur_rx;
+	unsigned int dirty_rx;
+	u32 rx_zeroc_thresh;
+	dma_addr_t dma_rx_phy;
+	u32 rx_tail_addr;
+	struct napi_struct napi ____cacheline_aligned_in_smp;
+};
+
+struct stmmac_priv {
+	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_count_frames;
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
-	struct stmmac_tx_info *tx_skbuff_dma;
-	dma_addr_t dma_tx_phy;
+
 	int tx_coalesce;
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
 	struct timer_list txtimer;
 	bool tso;
 
-	struct dma_desc *dma_rx	____cacheline_aligned_in_smp;
-	struct dma_extended_desc *dma_erx;
-	struct sk_buff **rx_skbuff;
-	unsigned int cur_rx;
-	unsigned int dirty_rx;
 	unsigned int dma_buf_sz;
 	unsigned int rx_copybreak;
-	unsigned int rx_zeroc_thresh;
 	u32 rx_riwt;
 	int hwts_rx_en;
-	dma_addr_t *rx_skbuff_dma;
-	dma_addr_t dma_rx_phy;
-
-	struct napi_struct napi ____cacheline_aligned_in_smp;
 
 	void __iomem *ioaddr;
 	struct net_device *dev;
@@ -85,6 +98,12 @@ struct stmmac_priv {
 	struct mac_device_info *hw;
 	spinlock_t lock;
 
+	/* RX Queue */
+	struct stmmac_rx_queue rx_queue[MTL_MAX_RX_QUEUES];
+
+	/* TX Queue */
+	struct stmmac_tx_queue tx_queue[MTL_MAX_TX_QUEUES];
+
 	int oldlink;
 	int speed;
 	int oldduplex;
@@ -119,8 +138,6 @@ struct stmmac_priv {
 	spinlock_t ptp_lock;
 	void __iomem *mmcaddr;
 	void __iomem *ptpaddr;
-	u32 rx_tail_addr;
-	u32 tx_tail_addr;
 	u32 mss;
 
 #ifdef CONFIG_DEBUG_FS
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device
 		      struct ethtool_pauseparam *pause)
 {
 	struct stmmac_priv *priv = netdev_priv(netdev);
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	struct phy_device *phy = netdev->phydev;
 	int new_pause = FLOW_OFF;
 
@@ -511,7 +512,7 @@ stmmac_set_pauseparam(struct net_device
 	}
 
 	priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl,
-				 priv->pause);
+				 priv->pause, tx_cnt);
 	return 0;
 }
 
@@ -519,6 +520,8 @@ static void stmmac_get_ethtool_stats(str
 				 struct ethtool_stats *dummy, u64 *data)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
 	int i, j = 0;
 
 	/* Update the DMA HW counters for dwmac10/100 */
@@ -549,7 +552,8 @@ static void stmmac_get_ethtool_stats(str
 		if ((priv->hw->mac->debug) &&
 		    (priv->synopsys_id >= DWMAC_CORE_3_50))
 			priv->hw->mac->debug(priv->ioaddr,
-					     (void *)&priv->xstats);
+					     (void *)&priv->xstats,
+					     rx_queues_count, tx_queues_count);
 	}
 	for (i = 0; i < STMMAC_STATS_LEN; i++) {
 		char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset;
@@ -726,6 +730,7 @@ static int stmmac_set_coalesce(struct ne
 			       struct ethtool_coalesce *ec)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
 	unsigned int rx_riwt;
 
 	/* Check not supported parameters  */
@@ -764,7 +769,7 @@ static int stmmac_set_coalesce(struct ne
 	priv->tx_coal_frames = ec->tx_max_coalesced_frames;
 	priv->tx_coal_timer = ec->tx_coalesce_usecs;
 	priv->rx_riwt = rx_riwt;
-	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt);
+	priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt);
 
 	return 0;
 }
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -139,6 +139,64 @@ static void stmmac_verify_args(void)
 }
 
 /**
+ * stmmac_disable_all_queues - Disable all queues
+ * @priv: driver private structure
+ */
+static void stmmac_disable_all_queues(struct stmmac_priv *priv)
+{
+	u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < rx_queues_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		napi_disable(&rx_q->napi);
+	}
+}
+
+/**
+ * stmmac_enable_all_queues - Enable all queues
+ * @priv: driver private structure
+ */
+static void stmmac_enable_all_queues(struct stmmac_priv *priv)
+{
+	u32 rx_queues_cnt = priv->plat->rx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < rx_queues_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		napi_enable(&rx_q->napi);
+	}
+}
+
+/**
+ * stmmac_stop_all_queues - Stop all queues
+ * @priv: driver private structure
+ */
+static void stmmac_stop_all_queues(struct stmmac_priv *priv)
+{
+	u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_cnt; queue++)
+		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
+}
+
+/**
+ * stmmac_start_all_queues - Start all queues
+ * @priv: driver private structure
+ */
+static void stmmac_start_all_queues(struct stmmac_priv *priv)
+{
+	u32 tx_queues_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_cnt; queue++)
+		netif_tx_start_queue(netdev_get_tx_queue(priv->dev, queue));
+}
+
+/**
  * stmmac_clk_csr_set - dynamically set the MDC clock
  * @priv: driver private structure
  * Description: this is to dynamically set the MDC clock according to the csr
@@ -185,26 +243,33 @@ static void print_pkt(unsigned char *buf
 	print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, buf, len);
 }
 
-static inline u32 stmmac_tx_avail(struct stmmac_priv *priv)
+static inline u32 stmmac_tx_avail(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	u32 avail;
 
-	if (priv->dirty_tx > priv->cur_tx)
-		avail = priv->dirty_tx - priv->cur_tx - 1;
+	if (tx_q->dirty_tx > tx_q->cur_tx)
+		avail = tx_q->dirty_tx - tx_q->cur_tx - 1;
 	else
-		avail = DMA_TX_SIZE - priv->cur_tx + priv->dirty_tx - 1;
+		avail = DMA_TX_SIZE - tx_q->cur_tx + tx_q->dirty_tx - 1;
 
 	return avail;
 }
 
-static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv)
+/**
+ * stmmac_rx_dirty - Get RX queue dirty
+ * @priv: driver private structure
+ * @queue: RX queue index
+ */
+static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	u32 dirty;
 
-	if (priv->dirty_rx <= priv->cur_rx)
-		dirty = priv->cur_rx - priv->dirty_rx;
+	if (rx_q->dirty_rx <= rx_q->cur_rx)
+		dirty = rx_q->cur_rx - rx_q->dirty_rx;
 	else
-		dirty = DMA_RX_SIZE - priv->dirty_rx + priv->cur_rx;
+		dirty = DMA_RX_SIZE - rx_q->dirty_rx + rx_q->cur_rx;
 
 	return dirty;
 }
@@ -232,9 +297,19 @@ static inline void stmmac_hw_fix_mac_spe
  */
 static void stmmac_enable_eee_mode(struct stmmac_priv *priv)
 {
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	/* check if all TX queues have the work finished */
+	for (queue = 0; queue < tx_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		if (tx_q->dirty_tx != tx_q->cur_tx)
+			return; /* still unfinished work */
+	}
+
 	/* Check and enter in LPI mode */
-	if ((priv->dirty_tx == priv->cur_tx) &&
-	    (priv->tx_path_in_lpi_mode == false))
+	if (!priv->tx_path_in_lpi_mode)
 		priv->hw->mac->set_eee_mode(priv->hw,
 					    priv->plat->en_tx_lpi_clockgating);
 }
@@ -365,14 +440,14 @@ static void stmmac_get_tx_hwtstamp(struc
 		return;
 
 	/* check tx tstamp status */
-	if (!priv->hw->desc->get_tx_timestamp_status(p)) {
+	if (priv->hw->desc->get_tx_timestamp_status(p)) {
 		/* get the valid tstamp */
 		ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
 
 		memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
 		shhwtstamp.hwtstamp = ns_to_ktime(ns);
 
-		netdev_info(priv->dev, "get valid TX hw timestamp %llu\n", ns);
+		netdev_dbg(priv->dev, "get valid TX hw timestamp %llu\n", ns);
 		/* pass tstamp to stack */
 		skb_tstamp_tx(skb, &shhwtstamp);
 	}
@@ -399,19 +474,19 @@ static void stmmac_get_rx_hwtstamp(struc
 		return;
 
 	/* Check if timestamp is available */
-	if (!priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) {
+	if (priv->hw->desc->get_rx_timestamp_status(p, priv->adv_ts)) {
 		/* For GMAC4, the valid timestamp is from CTX next desc. */
 		if (priv->plat->has_gmac4)
 			ns = priv->hw->desc->get_timestamp(np, priv->adv_ts);
 		else
 			ns = priv->hw->desc->get_timestamp(p, priv->adv_ts);
 
-		netdev_info(priv->dev, "get valid RX hw timestamp %llu\n", ns);
+		netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns);
 		shhwtstamp = skb_hwtstamps(skb);
 		memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps));
 		shhwtstamp->hwtstamp = ns_to_ktime(ns);
 	} else  {
-		netdev_err(priv->dev, "cannot get RX hw timestamp\n");
+		netdev_dbg(priv->dev, "cannot get RX hw timestamp\n");
 	}
 }
 
@@ -688,6 +763,19 @@ static void stmmac_release_ptp(struct st
 }
 
 /**
+ *  stmmac_mac_flow_ctrl - Configure flow control in all queues
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the flow control in all queues
+ */
+static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+
+	priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl,
+				 priv->pause, tx_cnt);
+}
+
+/**
  * stmmac_adjust_link - adjusts the link parameters
  * @dev: net device structure
  * Description: this is the helper called by the physical abstraction layer
@@ -702,7 +790,6 @@ static void stmmac_adjust_link(struct ne
 	struct phy_device *phydev = dev->phydev;
 	unsigned long flags;
 	int new_state = 0;
-	unsigned int fc = priv->flow_ctrl, pause_time = priv->pause;
 
 	if (!phydev)
 		return;
@@ -724,8 +811,7 @@ static void stmmac_adjust_link(struct ne
 		}
 		/* Flow Control operation */
 		if (phydev->pause)
-			priv->hw->mac->flow_ctrl(priv->hw, phydev->duplex,
-						 fc, pause_time);
+			stmmac_mac_flow_ctrl(priv, phydev->duplex);
 
 		if (phydev->speed != priv->speed) {
 			new_state = 1;
@@ -893,22 +979,56 @@ static int stmmac_init_phy(struct net_de
 	return 0;
 }
 
-static void stmmac_display_rings(struct stmmac_priv *priv)
+static void stmmac_display_rx_rings(struct stmmac_priv *priv)
 {
-	void *head_rx, *head_tx;
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	void *head_rx;
+	u32 queue;
 
-	if (priv->extend_desc) {
-		head_rx = (void *)priv->dma_erx;
-		head_tx = (void *)priv->dma_etx;
-	} else {
-		head_rx = (void *)priv->dma_rx;
-		head_tx = (void *)priv->dma_tx;
+	/* Display RX rings */
+	for (queue = 0; queue < rx_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		pr_info("\tRX Queue %u rings\n", queue);
+
+		if (priv->extend_desc)
+			head_rx = (void *)rx_q->dma_erx;
+		else
+			head_rx = (void *)rx_q->dma_rx;
+
+		/* Display RX ring */
+		priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
+	}
+}
+
+static void stmmac_display_tx_rings(struct stmmac_priv *priv)
+{
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	void *head_tx;
+	u32 queue;
+
+	/* Display TX rings */
+	for (queue = 0; queue < tx_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		pr_info("\tTX Queue %d rings\n", queue);
+
+		if (priv->extend_desc)
+			head_tx = (void *)tx_q->dma_etx;
+		else
+			head_tx = (void *)tx_q->dma_tx;
+
+		priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
 	}
+}
+
+static void stmmac_display_rings(struct stmmac_priv *priv)
+{
+	/* Display RX ring */
+	stmmac_display_rx_rings(priv);
 
-	/* Display Rx ring */
-	priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
-	/* Display Tx ring */
-	priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
+	/* Display TX ring */
+	stmmac_display_tx_rings(priv);
 }
 
 static int stmmac_set_bfsize(int mtu, int bufsize)
@@ -928,48 +1048,88 @@ static int stmmac_set_bfsize(int mtu, in
 }
 
 /**
- * stmmac_clear_descriptors - clear descriptors
+ * stmmac_clear_rx_descriptors - clear RX descriptors
  * @priv: driver private structure
- * Description: this function is called to clear the tx and rx descriptors
+ * @queue: RX queue index
+ * Description: this function is called to clear the RX descriptors
  * in case of both basic and extended descriptors are used.
  */
-static void stmmac_clear_descriptors(struct stmmac_priv *priv)
+static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	int i;
 
-	/* Clear the Rx/Tx descriptors */
+	/* Clear the RX descriptors */
 	for (i = 0; i < DMA_RX_SIZE; i++)
 		if (priv->extend_desc)
-			priv->hw->desc->init_rx_desc(&priv->dma_erx[i].basic,
+			priv->hw->desc->init_rx_desc(&rx_q->dma_erx[i].basic,
 						     priv->use_riwt, priv->mode,
 						     (i == DMA_RX_SIZE - 1));
 		else
-			priv->hw->desc->init_rx_desc(&priv->dma_rx[i],
+			priv->hw->desc->init_rx_desc(&rx_q->dma_rx[i],
 						     priv->use_riwt, priv->mode,
 						     (i == DMA_RX_SIZE - 1));
+}
+
+/**
+ * stmmac_clear_tx_descriptors - clear tx descriptors
+ * @priv: driver private structure
+ * @queue: TX queue index.
+ * Description: this function is called to clear the TX descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue)
+{
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+	int i;
+
+	/* Clear the TX descriptors */
 	for (i = 0; i < DMA_TX_SIZE; i++)
 		if (priv->extend_desc)
-			priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic,
+			priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic,
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
 		else
-			priv->hw->desc->init_tx_desc(&priv->dma_tx[i],
+			priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i],
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
 }
 
 /**
+ * stmmac_clear_descriptors - clear descriptors
+ * @priv: driver private structure
+ * Description: this function is called to clear the TX and RX descriptors
+ * in case of both basic and extended descriptors are used.
+ */
+static void stmmac_clear_descriptors(struct stmmac_priv *priv)
+{
+	u32 rx_queue_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_queue_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	/* Clear the RX descriptors */
+	for (queue = 0; queue < rx_queue_cnt; queue++)
+		stmmac_clear_rx_descriptors(priv, queue);
+
+	/* Clear the TX descriptors */
+	for (queue = 0; queue < tx_queue_cnt; queue++)
+		stmmac_clear_tx_descriptors(priv, queue);
+}
+
+/**
  * stmmac_init_rx_buffers - init the RX descriptor buffer.
  * @priv: driver private structure
  * @p: descriptor pointer
  * @i: descriptor index
- * @flags: gfp flag.
+ * @flags: gfp flag
+ * @queue: RX queue index
  * Description: this function is called to allocate a receive buffer, perform
  * the DMA mapping and init the descriptor.
  */
 static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
-				  int i, gfp_t flags)
+				  int i, gfp_t flags, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 	struct sk_buff *skb;
 
 	skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
@@ -978,20 +1138,20 @@ static int stmmac_init_rx_buffers(struct
 			   "%s: Rx init fails; skb is NULL\n", __func__);
 		return -ENOMEM;
 	}
-	priv->rx_skbuff[i] = skb;
-	priv->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
+	rx_q->rx_skbuff[i] = skb;
+	rx_q->rx_skbuff_dma[i] = dma_map_single(priv->device, skb->data,
 						priv->dma_buf_sz,
 						DMA_FROM_DEVICE);
-	if (dma_mapping_error(priv->device, priv->rx_skbuff_dma[i])) {
+	if (dma_mapping_error(priv->device, rx_q->rx_skbuff_dma[i])) {
 		netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
 		dev_kfree_skb_any(skb);
 		return -EINVAL;
 	}
 
 	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		p->des0 = cpu_to_le32(priv->rx_skbuff_dma[i]);
+		p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
 	else
-		p->des2 = cpu_to_le32(priv->rx_skbuff_dma[i]);
+		p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]);
 
 	if ((priv->hw->mode->init_desc3) &&
 	    (priv->dma_buf_sz == BUF_SIZE_16KiB))
@@ -1000,30 +1160,71 @@ static int stmmac_init_rx_buffers(struct
 	return 0;
 }
 
-static void stmmac_free_rx_buffers(struct stmmac_priv *priv, int i)
+/**
+ * stmmac_free_rx_buffer - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ * @i: buffer index.
+ */
+static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i)
 {
-	if (priv->rx_skbuff[i]) {
-		dma_unmap_single(priv->device, priv->rx_skbuff_dma[i],
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+	if (rx_q->rx_skbuff[i]) {
+		dma_unmap_single(priv->device, rx_q->rx_skbuff_dma[i],
 				 priv->dma_buf_sz, DMA_FROM_DEVICE);
-		dev_kfree_skb_any(priv->rx_skbuff[i]);
+		dev_kfree_skb_any(rx_q->rx_skbuff[i]);
 	}
-	priv->rx_skbuff[i] = NULL;
+	rx_q->rx_skbuff[i] = NULL;
 }
 
 /**
- * init_dma_desc_rings - init the RX/TX descriptor rings
+ * stmmac_free_tx_buffer - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ * @i: buffer index.
+ */
+static void stmmac_free_tx_buffer(struct stmmac_priv *priv, u32 queue, int i)
+{
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+	if (tx_q->tx_skbuff_dma[i].buf) {
+		if (tx_q->tx_skbuff_dma[i].map_as_page)
+			dma_unmap_page(priv->device,
+				       tx_q->tx_skbuff_dma[i].buf,
+				       tx_q->tx_skbuff_dma[i].len,
+				       DMA_TO_DEVICE);
+		else
+			dma_unmap_single(priv->device,
+					 tx_q->tx_skbuff_dma[i].buf,
+					 tx_q->tx_skbuff_dma[i].len,
+					 DMA_TO_DEVICE);
+	}
+
+	if (tx_q->tx_skbuff[i]) {
+		dev_kfree_skb_any(tx_q->tx_skbuff[i]);
+		tx_q->tx_skbuff[i] = NULL;
+		tx_q->tx_skbuff_dma[i].buf = 0;
+		tx_q->tx_skbuff_dma[i].map_as_page = false;
+	}
+}
+
+/**
+ * init_dma_rx_desc_rings - init the RX descriptor rings
  * @dev: net device structure
  * @flags: gfp flag.
- * Description: this function initializes the DMA RX/TX descriptors
+ * Description: this function initializes the DMA RX descriptors
  * and allocates the socket buffers. It supports the chained and ring
  * modes.
  */
-static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
+static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags)
 {
-	int i;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_count = priv->plat->rx_queues_to_use;
 	unsigned int bfsize = 0;
 	int ret = -ENOMEM;
+	int queue;
+	int i;
 
 	if (priv->hw->mode->set_16kib_bfsize)
 		bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu);
@@ -1033,257 +1234,516 @@ static int init_dma_desc_rings(struct ne
 
 	priv->dma_buf_sz = bfsize;
 
-	netif_dbg(priv, probe, priv->dev,
-		  "(%s) dma_rx_phy=0x%08x dma_tx_phy=0x%08x\n",
-		  __func__, (u32)priv->dma_rx_phy, (u32)priv->dma_tx_phy);
-
 	/* RX INITIALIZATION */
 	netif_dbg(priv, probe, priv->dev,
 		  "SKB addresses:\nskb\t\tskb data\tdma data\n");
 
-	for (i = 0; i < DMA_RX_SIZE; i++) {
-		struct dma_desc *p;
-		if (priv->extend_desc)
-			p = &((priv->dma_erx + i)->basic);
-		else
-			p = priv->dma_rx + i;
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
 
-		ret = stmmac_init_rx_buffers(priv, p, i, flags);
-		if (ret)
-			goto err_init_rx_buffers;
+		netif_dbg(priv, probe, priv->dev,
+			  "(%s) dma_rx_phy=0x%08x\n", __func__,
+			  (u32)rx_q->dma_rx_phy);
 
-		netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
-			  priv->rx_skbuff[i], priv->rx_skbuff[i]->data,
-			  (unsigned int)priv->rx_skbuff_dma[i]);
+		for (i = 0; i < DMA_RX_SIZE; i++) {
+			struct dma_desc *p;
+
+			if (priv->extend_desc)
+				p = &((rx_q->dma_erx + i)->basic);
+			else
+				p = rx_q->dma_rx + i;
+
+			ret = stmmac_init_rx_buffers(priv, p, i, flags,
+						     queue);
+			if (ret)
+				goto err_init_rx_buffers;
+
+			netif_dbg(priv, probe, priv->dev, "[%p]\t[%p]\t[%x]\n",
+				  rx_q->rx_skbuff[i], rx_q->rx_skbuff[i]->data,
+				  (unsigned int)rx_q->rx_skbuff_dma[i]);
+		}
+
+		rx_q->cur_rx = 0;
+		rx_q->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
+
+		stmmac_clear_rx_descriptors(priv, queue);
+
+		/* Setup the chained descriptor addresses */
+		if (priv->mode == STMMAC_CHAIN_MODE) {
+			if (priv->extend_desc)
+				priv->hw->mode->init(rx_q->dma_erx,
+						     rx_q->dma_rx_phy,
+						     DMA_RX_SIZE, 1);
+			else
+				priv->hw->mode->init(rx_q->dma_rx,
+						     rx_q->dma_rx_phy,
+						     DMA_RX_SIZE, 0);
+		}
 	}
-	priv->cur_rx = 0;
-	priv->dirty_rx = (unsigned int)(i - DMA_RX_SIZE);
+
 	buf_sz = bfsize;
 
-	/* Setup the chained descriptor addresses */
-	if (priv->mode == STMMAC_CHAIN_MODE) {
-		if (priv->extend_desc) {
-			priv->hw->mode->init(priv->dma_erx, priv->dma_rx_phy,
-					     DMA_RX_SIZE, 1);
-			priv->hw->mode->init(priv->dma_etx, priv->dma_tx_phy,
-					     DMA_TX_SIZE, 1);
-		} else {
-			priv->hw->mode->init(priv->dma_rx, priv->dma_rx_phy,
-					     DMA_RX_SIZE, 0);
-			priv->hw->mode->init(priv->dma_tx, priv->dma_tx_phy,
-					     DMA_TX_SIZE, 0);
-		}
+	return 0;
+
+err_init_rx_buffers:
+	while (queue >= 0) {
+		while (--i >= 0)
+			stmmac_free_rx_buffer(priv, queue, i);
+
+		if (queue == 0)
+			break;
+
+		i = DMA_RX_SIZE;
+		queue--;
 	}
 
-	/* TX INITIALIZATION */
-	for (i = 0; i < DMA_TX_SIZE; i++) {
-		struct dma_desc *p;
-		if (priv->extend_desc)
-			p = &((priv->dma_etx + i)->basic);
-		else
-			p = priv->dma_tx + i;
+	return ret;
+}
 
-		if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-			p->des0 = 0;
-			p->des1 = 0;
-			p->des2 = 0;
-			p->des3 = 0;
-		} else {
-			p->des2 = 0;
+/**
+ * init_dma_tx_desc_rings - init the TX descriptor rings
+ * @dev: net device structure.
+ * Description: this function initializes the DMA TX descriptors
+ * and allocates the socket buffers. It supports the chained and ring
+ * modes.
+ */
+static int init_dma_tx_desc_rings(struct net_device *dev)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_queue_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+	int i;
+
+	for (queue = 0; queue < tx_queue_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		netif_dbg(priv, probe, priv->dev,
+			  "(%s) dma_tx_phy=0x%08x\n", __func__,
+			 (u32)tx_q->dma_tx_phy);
+
+		/* Setup the chained descriptor addresses */
+		if (priv->mode == STMMAC_CHAIN_MODE) {
+			if (priv->extend_desc)
+				priv->hw->mode->init(tx_q->dma_etx,
+						     tx_q->dma_tx_phy,
+						     DMA_TX_SIZE, 1);
+			else
+				priv->hw->mode->init(tx_q->dma_tx,
+						     tx_q->dma_tx_phy,
+						     DMA_TX_SIZE, 0);
+		}
+
+		for (i = 0; i < DMA_TX_SIZE; i++) {
+			struct dma_desc *p;
+			if (priv->extend_desc)
+				p = &((tx_q->dma_etx + i)->basic);
+			else
+				p = tx_q->dma_tx + i;
+
+			if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+				p->des0 = 0;
+				p->des1 = 0;
+				p->des2 = 0;
+				p->des3 = 0;
+			} else {
+				p->des2 = 0;
+			}
+
+			tx_q->tx_skbuff_dma[i].buf = 0;
+			tx_q->tx_skbuff_dma[i].map_as_page = false;
+			tx_q->tx_skbuff_dma[i].len = 0;
+			tx_q->tx_skbuff_dma[i].last_segment = false;
+			tx_q->tx_skbuff[i] = NULL;
 		}
 
-		priv->tx_skbuff_dma[i].buf = 0;
-		priv->tx_skbuff_dma[i].map_as_page = false;
-		priv->tx_skbuff_dma[i].len = 0;
-		priv->tx_skbuff_dma[i].last_segment = false;
-		priv->tx_skbuff[i] = NULL;
+		tx_q->dirty_tx = 0;
+		tx_q->cur_tx = 0;
+
+		netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
-	priv->dirty_tx = 0;
-	priv->cur_tx = 0;
-	netdev_reset_queue(priv->dev);
+	return 0;
+}
+
+/**
+ * init_dma_desc_rings - init the RX/TX descriptor rings
+ * @dev: net device structure
+ * @flags: gfp flag.
+ * Description: this function initializes the DMA RX/TX descriptors
+ * and allocates the socket buffers. It supports the chained and ring
+ * modes.
+ */
+static int init_dma_desc_rings(struct net_device *dev, gfp_t flags)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+	int ret;
+
+	ret = init_dma_rx_desc_rings(dev, flags);
+	if (ret)
+		return ret;
+
+	ret = init_dma_tx_desc_rings(dev);
 
 	stmmac_clear_descriptors(priv);
 
 	if (netif_msg_hw(priv))
 		stmmac_display_rings(priv);
 
-	return 0;
-err_init_rx_buffers:
-	while (--i >= 0)
-		stmmac_free_rx_buffers(priv, i);
 	return ret;
 }
 
-static void dma_free_rx_skbufs(struct stmmac_priv *priv)
+/**
+ * dma_free_rx_skbufs - free RX dma buffers
+ * @priv: private structure
+ * @queue: RX queue index
+ */
+static void dma_free_rx_skbufs(struct stmmac_priv *priv, u32 queue)
 {
 	int i;
 
 	for (i = 0; i < DMA_RX_SIZE; i++)
-		stmmac_free_rx_buffers(priv, i);
+		stmmac_free_rx_buffer(priv, queue, i);
 }
 
-static void dma_free_tx_skbufs(struct stmmac_priv *priv)
+/**
+ * dma_free_tx_skbufs - free TX dma buffers
+ * @priv: private structure
+ * @queue: TX queue index
+ */
+static void dma_free_tx_skbufs(struct stmmac_priv *priv, u32 queue)
 {
 	int i;
 
-	for (i = 0; i < DMA_TX_SIZE; i++) {
-		if (priv->tx_skbuff_dma[i].buf) {
-			if (priv->tx_skbuff_dma[i].map_as_page)
-				dma_unmap_page(priv->device,
-					       priv->tx_skbuff_dma[i].buf,
-					       priv->tx_skbuff_dma[i].len,
-					       DMA_TO_DEVICE);
-			else
-				dma_unmap_single(priv->device,
-						 priv->tx_skbuff_dma[i].buf,
-						 priv->tx_skbuff_dma[i].len,
-						 DMA_TO_DEVICE);
+	for (i = 0; i < DMA_TX_SIZE; i++)
+		stmmac_free_tx_buffer(priv, queue, i);
+}
+
+/**
+ * free_dma_rx_desc_resources - free RX dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
+{
+	u32 rx_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+
+	/* Free RX queue resources */
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		/* Release the DMA RX socket buffers */
+		dma_free_rx_skbufs(priv, queue);
+
+		/* Free DMA regions of consistent memory previously allocated */
+		if (!priv->extend_desc)
+			dma_free_coherent(priv->device,
+					  DMA_RX_SIZE * sizeof(struct dma_desc),
+					  rx_q->dma_rx, rx_q->dma_rx_phy);
+		else
+			dma_free_coherent(priv->device, DMA_RX_SIZE *
+					  sizeof(struct dma_extended_desc),
+					  rx_q->dma_erx, rx_q->dma_rx_phy);
+
+		kfree(rx_q->rx_skbuff_dma);
+		kfree(rx_q->rx_skbuff);
+	}
+}
+
+/**
+ * free_dma_tx_desc_resources - free TX dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_tx_desc_resources(struct stmmac_priv *priv)
+{
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 queue = 0;
+
+	/* Free TX queue resources */
+	for (queue = 0; queue < tx_count; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		/* Release the DMA TX socket buffers */
+		dma_free_tx_skbufs(priv, queue);
+
+		/* Free DMA regions of consistent memory previously allocated */
+		if (!priv->extend_desc)
+			dma_free_coherent(priv->device,
+					  DMA_TX_SIZE * sizeof(struct dma_desc),
+					  tx_q->dma_tx, tx_q->dma_tx_phy);
+		else
+			dma_free_coherent(priv->device, DMA_TX_SIZE *
+					  sizeof(struct dma_extended_desc),
+					  tx_q->dma_etx, tx_q->dma_tx_phy);
+
+		kfree(tx_q->tx_skbuff_dma);
+		kfree(tx_q->tx_skbuff);
+	}
+}
+
+/**
+ * alloc_dma_rx_desc_resources - alloc RX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
+{
+	u32 rx_count = priv->plat->rx_queues_to_use;
+	int ret = -ENOMEM;
+	u32 queue;
+
+	/* RX queues buffers and DMA */
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		rx_q->queue_index = queue;
+		rx_q->priv_data = priv;
+
+		rx_q->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE,
+						    sizeof(dma_addr_t),
+						    GFP_KERNEL);
+		if (!rx_q->rx_skbuff_dma)
+			return -ENOMEM;
+
+		rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE,
+						sizeof(struct sk_buff *),
+						GFP_KERNEL);
+		if (!rx_q->rx_skbuff)
+			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);
+			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);
+			if (!rx_q->dma_rx)
+				goto err_dma;
+		}
+	}
+
+	return 0;
+
+err_dma:
+	free_dma_rx_desc_resources(priv);
+
+	return ret;
+}
+
+/**
+ * alloc_dma_tx_desc_resources - alloc TX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_tx_desc_resources(struct stmmac_priv *priv)
+{
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	int ret = -ENOMEM;
+	u32 queue;
+
+	/* TX queues buffers and DMA */
+	for (queue = 0; queue < tx_count; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		tx_q->queue_index = queue;
+		tx_q->priv_data = priv;
+
+		tx_q->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
+						    sizeof(*tx_q->tx_skbuff_dma),
+						    GFP_KERNEL);
+		if (!tx_q->tx_skbuff_dma)
+			return -ENOMEM;
+
+		tx_q->tx_skbuff = kmalloc_array(DMA_TX_SIZE,
+						sizeof(struct sk_buff *),
+						GFP_KERNEL);
+		if (!tx_q->tx_skbuff)
+			goto err_dma_buffers;
+
+		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);
+			if (!tx_q->dma_etx)
+				goto err_dma_buffers;
+		} else {
+			tx_q->dma_tx = dma_zalloc_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_buffers;
 		}
+	}
+
+	return 0;
+
+err_dma_buffers:
+	free_dma_tx_desc_resources(priv);
+
+	return ret;
+}
+
+/**
+ * alloc_dma_desc_resources - alloc TX/RX resources.
+ * @priv: private structure
+ * Description: according to which descriptor can be used (extend or basic)
+ * this function allocates the resources for TX and RX paths. In case of
+ * reception, for example, it pre-allocated the RX socket buffer in order to
+ * allow zero-copy mechanism.
+ */
+static int alloc_dma_desc_resources(struct stmmac_priv *priv)
+{
+	/* RX Allocation */
+	int ret = alloc_dma_rx_desc_resources(priv);
+
+	if (ret)
+		return ret;
+
+	ret = alloc_dma_tx_desc_resources(priv);
+
+	return ret;
+}
+
+/**
+ * free_dma_desc_resources - free dma desc resources
+ * @priv: private structure
+ */
+static void free_dma_desc_resources(struct stmmac_priv *priv)
+{
+	/* Release the DMA RX socket buffers */
+	free_dma_rx_desc_resources(priv);
+
+	/* Release the DMA TX socket buffers */
+	free_dma_tx_desc_resources(priv);
+}
+
+/**
+ *  stmmac_mac_enable_rx_queues - Enable MAC rx queues
+ *  @priv: driver private structure
+ *  Description: It is used for enabling the rx queues in the MAC
+ */
+static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	int queue;
+	u8 mode;
 
-		if (priv->tx_skbuff[i]) {
-			dev_kfree_skb_any(priv->tx_skbuff[i]);
-			priv->tx_skbuff[i] = NULL;
-			priv->tx_skbuff_dma[i].buf = 0;
-			priv->tx_skbuff_dma[i].map_as_page = false;
-		}
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		mode = priv->plat->rx_queues_cfg[queue].mode_to_use;
+		priv->hw->mac->rx_queue_enable(priv->hw, mode, queue);
 	}
 }
 
 /**
- * alloc_dma_desc_resources - alloc TX/RX resources.
- * @priv: private structure
- * Description: according to which descriptor can be used (extend or basic)
- * this function allocates the resources for TX and RX paths. In case of
- * reception, for example, it pre-allocated the RX socket buffer in order to
- * allow zero-copy mechanism.
+ * stmmac_start_rx_dma - start RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This starts a RX DMA channel
  */
-static int alloc_dma_desc_resources(struct stmmac_priv *priv)
+static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan)
 {
-	int ret = -ENOMEM;
-
-	priv->rx_skbuff_dma = kmalloc_array(DMA_RX_SIZE, sizeof(dma_addr_t),
-					    GFP_KERNEL);
-	if (!priv->rx_skbuff_dma)
-		return -ENOMEM;
-
-	priv->rx_skbuff = kmalloc_array(DMA_RX_SIZE, sizeof(struct sk_buff *),
-					GFP_KERNEL);
-	if (!priv->rx_skbuff)
-		goto err_rx_skbuff;
-
-	priv->tx_skbuff_dma = kmalloc_array(DMA_TX_SIZE,
-					    sizeof(*priv->tx_skbuff_dma),
-					    GFP_KERNEL);
-	if (!priv->tx_skbuff_dma)
-		goto err_tx_skbuff_dma;
-
-	priv->tx_skbuff = kmalloc_array(DMA_TX_SIZE, sizeof(struct sk_buff *),
-					GFP_KERNEL);
-	if (!priv->tx_skbuff)
-		goto err_tx_skbuff;
-
-	if (priv->extend_desc) {
-		priv->dma_erx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE *
-						    sizeof(struct
-							   dma_extended_desc),
-						    &priv->dma_rx_phy,
-						    GFP_KERNEL);
-		if (!priv->dma_erx)
-			goto err_dma;
-
-		priv->dma_etx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE *
-						    sizeof(struct
-							   dma_extended_desc),
-						    &priv->dma_tx_phy,
-						    GFP_KERNEL);
-		if (!priv->dma_etx) {
-			dma_free_coherent(priv->device, DMA_RX_SIZE *
-					  sizeof(struct dma_extended_desc),
-					  priv->dma_erx, priv->dma_rx_phy);
-			goto err_dma;
-		}
-	} else {
-		priv->dma_rx = dma_zalloc_coherent(priv->device, DMA_RX_SIZE *
-						   sizeof(struct dma_desc),
-						   &priv->dma_rx_phy,
-						   GFP_KERNEL);
-		if (!priv->dma_rx)
-			goto err_dma;
+	netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan);
+	priv->hw->dma->start_rx(priv->ioaddr, chan);
+}
 
-		priv->dma_tx = dma_zalloc_coherent(priv->device, DMA_TX_SIZE *
-						   sizeof(struct dma_desc),
-						   &priv->dma_tx_phy,
-						   GFP_KERNEL);
-		if (!priv->dma_tx) {
-			dma_free_coherent(priv->device, DMA_RX_SIZE *
-					  sizeof(struct dma_desc),
-					  priv->dma_rx, priv->dma_rx_phy);
-			goto err_dma;
-		}
-	}
+/**
+ * stmmac_start_tx_dma - start TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This starts a TX DMA channel
+ */
+static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan);
+	priv->hw->dma->start_tx(priv->ioaddr, chan);
+}
 
-	return 0;
+/**
+ * stmmac_stop_rx_dma - stop RX DMA channel
+ * @priv: driver private structure
+ * @chan: RX channel index
+ * Description:
+ * This stops a RX DMA channel
+ */
+static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan);
+	priv->hw->dma->stop_rx(priv->ioaddr, chan);
+}
 
-err_dma:
-	kfree(priv->tx_skbuff);
-err_tx_skbuff:
-	kfree(priv->tx_skbuff_dma);
-err_tx_skbuff_dma:
-	kfree(priv->rx_skbuff);
-err_rx_skbuff:
-	kfree(priv->rx_skbuff_dma);
-	return ret;
+/**
+ * stmmac_stop_tx_dma - stop TX DMA channel
+ * @priv: driver private structure
+ * @chan: TX channel index
+ * Description:
+ * This stops a TX DMA channel
+ */
+static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan)
+{
+	netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan);
+	priv->hw->dma->stop_tx(priv->ioaddr, chan);
 }
 
-static void free_dma_desc_resources(struct stmmac_priv *priv)
+/**
+ * stmmac_start_all_dma - start all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This starts all the RX and TX DMA channels
+ */
+static void stmmac_start_all_dma(struct stmmac_priv *priv)
 {
-	/* Release the DMA TX/RX socket buffers */
-	dma_free_rx_skbufs(priv);
-	dma_free_tx_skbufs(priv);
-
-	/* Free DMA regions of consistent memory previously allocated */
-	if (!priv->extend_desc) {
-		dma_free_coherent(priv->device,
-				  DMA_TX_SIZE * sizeof(struct dma_desc),
-				  priv->dma_tx, priv->dma_tx_phy);
-		dma_free_coherent(priv->device,
-				  DMA_RX_SIZE * sizeof(struct dma_desc),
-				  priv->dma_rx, priv->dma_rx_phy);
-	} else {
-		dma_free_coherent(priv->device, DMA_TX_SIZE *
-				  sizeof(struct dma_extended_desc),
-				  priv->dma_etx, priv->dma_tx_phy);
-		dma_free_coherent(priv->device, DMA_RX_SIZE *
-				  sizeof(struct dma_extended_desc),
-				  priv->dma_erx, priv->dma_rx_phy);
-	}
-	kfree(priv->rx_skbuff_dma);
-	kfree(priv->rx_skbuff);
-	kfree(priv->tx_skbuff_dma);
-	kfree(priv->tx_skbuff);
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan = 0;
+
+	for (chan = 0; chan < rx_channels_count; chan++)
+		stmmac_start_rx_dma(priv, chan);
+
+	for (chan = 0; chan < tx_channels_count; chan++)
+		stmmac_start_tx_dma(priv, chan);
 }
 
 /**
- *  stmmac_mac_enable_rx_queues - Enable MAC rx queues
- *  @priv: driver private structure
- *  Description: It is used for enabling the rx queues in the MAC
+ * stmmac_stop_all_dma - stop all RX and TX DMA channels
+ * @priv: driver private structure
+ * Description:
+ * This stops the RX and TX DMA channels
  */
-static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
+static void stmmac_stop_all_dma(struct stmmac_priv *priv)
 {
-	int rx_count = priv->dma_cap.number_rx_queues;
-	int queue = 0;
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan = 0;
 
-	/* If GMAC does not have multiple queues, then this is not necessary*/
-	if (rx_count == 1)
-		return;
+	for (chan = 0; chan < rx_channels_count; chan++)
+		stmmac_stop_rx_dma(priv, chan);
 
-	/**
-	 *  If the core is synthesized with multiple rx queues / multiple
-	 *  dma channels, then rx queues will be disabled by default.
-	 *  For now only rx queue 0 is enabled.
-	 */
-	priv->hw->mac->rx_queue_enable(priv->hw, queue);
+	for (chan = 0; chan < tx_channels_count; chan++)
+		stmmac_stop_tx_dma(priv, chan);
 }
 
 /**
@@ -1294,11 +1754,20 @@ static void stmmac_mac_enable_rx_queues(
  */
 static void stmmac_dma_operation_mode(struct stmmac_priv *priv)
 {
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
 	int rxfifosz = priv->plat->rx_fifo_size;
-
-	if (priv->plat->force_thresh_dma_mode)
-		priv->hw->dma->dma_mode(priv->ioaddr, tc, tc, rxfifosz);
-	else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
+	u32 txmode = 0;
+	u32 rxmode = 0;
+	u32 chan = 0;
+
+	if (rxfifosz == 0)
+		rxfifosz = priv->dma_cap.rx_fifo_size;
+
+	if (priv->plat->force_thresh_dma_mode) {
+		txmode = tc;
+		rxmode = tc;
+	} else if (priv->plat->force_sf_dma_mode || priv->plat->tx_coe) {
 		/*
 		 * In case of GMAC, SF mode can be enabled
 		 * to perform the TX COE in HW. This depends on:
@@ -1306,37 +1775,53 @@ static void stmmac_dma_operation_mode(st
 		 * 2) There is no bugged Jumbo frame support
 		 *    that needs to not insert csum in the TDES.
 		 */
-		priv->hw->dma->dma_mode(priv->ioaddr, SF_DMA_MODE, SF_DMA_MODE,
-					rxfifosz);
+		txmode = SF_DMA_MODE;
+		rxmode = SF_DMA_MODE;
 		priv->xstats.threshold = SF_DMA_MODE;
-	} else
-		priv->hw->dma->dma_mode(priv->ioaddr, tc, SF_DMA_MODE,
+	} else {
+		txmode = tc;
+		rxmode = SF_DMA_MODE;
+	}
+
+	/* configure all channels */
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		for (chan = 0; chan < rx_channels_count; chan++)
+			priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+						   rxfifosz);
+
+		for (chan = 0; chan < tx_channels_count; chan++)
+			priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+	} else {
+		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
 					rxfifosz);
+	}
 }
 
 /**
  * stmmac_tx_clean - to manage the transmission completion
  * @priv: driver private structure
+ * @queue: TX queue index
  * Description: it reclaims the transmit resources after transmission completes.
  */
-static void stmmac_tx_clean(struct stmmac_priv *priv)
+static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	unsigned int bytes_compl = 0, pkts_compl = 0;
-	unsigned int entry = priv->dirty_tx;
+	unsigned int entry = tx_q->dirty_tx;
 
 	netif_tx_lock(priv->dev);
 
 	priv->xstats.tx_clean++;
 
-	while (entry != priv->cur_tx) {
-		struct sk_buff *skb = priv->tx_skbuff[entry];
+	while (entry != tx_q->cur_tx) {
+		struct sk_buff *skb = tx_q->tx_skbuff[entry];
 		struct dma_desc *p;
 		int status;
 
 		if (priv->extend_desc)
-			p = (struct dma_desc *)(priv->dma_etx + entry);
+			p = (struct dma_desc *)(tx_q->dma_etx + entry);
 		else
-			p = priv->dma_tx + entry;
+			p = tx_q->dma_tx + entry;
 
 		status = priv->hw->desc->tx_status(&priv->dev->stats,
 						      &priv->xstats, p,
@@ -1357,48 +1842,51 @@ static void stmmac_tx_clean(struct stmma
 			stmmac_get_tx_hwtstamp(priv, p, skb);
 		}
 
-		if (likely(priv->tx_skbuff_dma[entry].buf)) {
-			if (priv->tx_skbuff_dma[entry].map_as_page)
+		if (likely(tx_q->tx_skbuff_dma[entry].buf)) {
+			if (tx_q->tx_skbuff_dma[entry].map_as_page)
 				dma_unmap_page(priv->device,
-					       priv->tx_skbuff_dma[entry].buf,
-					       priv->tx_skbuff_dma[entry].len,
+					       tx_q->tx_skbuff_dma[entry].buf,
+					       tx_q->tx_skbuff_dma[entry].len,
 					       DMA_TO_DEVICE);
 			else
 				dma_unmap_single(priv->device,
-						 priv->tx_skbuff_dma[entry].buf,
-						 priv->tx_skbuff_dma[entry].len,
+						 tx_q->tx_skbuff_dma[entry].buf,
+						 tx_q->tx_skbuff_dma[entry].len,
 						 DMA_TO_DEVICE);
-			priv->tx_skbuff_dma[entry].buf = 0;
-			priv->tx_skbuff_dma[entry].len = 0;
-			priv->tx_skbuff_dma[entry].map_as_page = false;
+			tx_q->tx_skbuff_dma[entry].buf = 0;
+			tx_q->tx_skbuff_dma[entry].len = 0;
+			tx_q->tx_skbuff_dma[entry].map_as_page = false;
 		}
 
 		if (priv->hw->mode->clean_desc3)
-			priv->hw->mode->clean_desc3(priv, p);
+			priv->hw->mode->clean_desc3(tx_q, p);
 
-		priv->tx_skbuff_dma[entry].last_segment = false;
-		priv->tx_skbuff_dma[entry].is_jumbo = false;
+		tx_q->tx_skbuff_dma[entry].last_segment = false;
+		tx_q->tx_skbuff_dma[entry].is_jumbo = false;
 
 		if (likely(skb != NULL)) {
 			pkts_compl++;
 			bytes_compl += skb->len;
 			dev_consume_skb_any(skb);
-			priv->tx_skbuff[entry] = NULL;
+			tx_q->tx_skbuff[entry] = NULL;
 		}
 
 		priv->hw->desc->release_tx_desc(p, priv->mode);
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 	}
-	priv->dirty_tx = entry;
+	tx_q->dirty_tx = entry;
+
+	netdev_tx_completed_queue(netdev_get_tx_queue(priv->dev, queue),
+				  pkts_compl, bytes_compl);
 
-	netdev_completed_queue(priv->dev, pkts_compl, bytes_compl);
+	if (unlikely(netif_tx_queue_stopped(netdev_get_tx_queue(priv->dev,
+								queue))) &&
+	    stmmac_tx_avail(priv, queue) > STMMAC_TX_THRESH) {
 
-	if (unlikely(netif_queue_stopped(priv->dev) &&
-	    stmmac_tx_avail(priv) > STMMAC_TX_THRESH)) {
 		netif_dbg(priv, tx_done, priv->dev,
 			  "%s: restart transmit\n", __func__);
-		netif_wake_queue(priv->dev);
+		netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
 	if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
@@ -1408,45 +1896,76 @@ static void stmmac_tx_clean(struct stmma
 	netif_tx_unlock(priv->dev);
 }
 
-static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan)
 {
-	priv->hw->dma->enable_dma_irq(priv->ioaddr);
+	priv->hw->dma->enable_dma_irq(priv->ioaddr, chan);
 }
 
-static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv)
+static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan)
 {
-	priv->hw->dma->disable_dma_irq(priv->ioaddr);
+	priv->hw->dma->disable_dma_irq(priv->ioaddr, chan);
 }
 
 /**
  * stmmac_tx_err - to manage the tx error
  * @priv: driver private structure
+ * @chan: channel index
  * Description: it cleans the descriptors and restarts the transmission
  * in case of transmission errors.
  */
-static void stmmac_tx_err(struct stmmac_priv *priv)
+static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
 	int i;
-	netif_stop_queue(priv->dev);
 
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	dma_free_tx_skbufs(priv);
+	netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, chan));
+
+	stmmac_stop_tx_dma(priv, chan);
+	dma_free_tx_skbufs(priv, chan);
 	for (i = 0; i < DMA_TX_SIZE; i++)
 		if (priv->extend_desc)
-			priv->hw->desc->init_tx_desc(&priv->dma_etx[i].basic,
+			priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic,
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
 		else
-			priv->hw->desc->init_tx_desc(&priv->dma_tx[i],
+			priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i],
 						     priv->mode,
 						     (i == DMA_TX_SIZE - 1));
-	priv->dirty_tx = 0;
-	priv->cur_tx = 0;
-	netdev_reset_queue(priv->dev);
-	priv->hw->dma->start_tx(priv->ioaddr);
+	tx_q->dirty_tx = 0;
+	tx_q->cur_tx = 0;
+	netdev_tx_reset_queue(netdev_get_tx_queue(priv->dev, chan));
+	stmmac_start_tx_dma(priv, chan);
 
 	priv->dev->stats.tx_errors++;
-	netif_wake_queue(priv->dev);
+	netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, chan));
+}
+
+/**
+ *  stmmac_set_dma_operation_mode - Set DMA operation mode by channel
+ *  @priv: driver private structure
+ *  @txmode: TX operating mode
+ *  @rxmode: RX operating mode
+ *  @chan: channel index
+ *  Description: it is used for configuring of the DMA operation mode in
+ *  runtime in order to program the tx/rx DMA thresholds or Store-And-Forward
+ *  mode.
+ */
+static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode,
+					  u32 rxmode, u32 chan)
+{
+	int rxfifosz = priv->plat->rx_fifo_size;
+
+	if (rxfifosz == 0)
+		rxfifosz = priv->dma_cap.rx_fifo_size;
+
+	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+		priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan,
+					   rxfifosz);
+		priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan);
+	} else {
+		priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode,
+					rxfifosz);
+	}
 }
 
 /**
@@ -1458,31 +1977,43 @@ static void stmmac_tx_err(struct stmmac_
  */
 static void stmmac_dma_interrupt(struct stmmac_priv *priv)
 {
+	u32 tx_channel_count = priv->plat->tx_queues_to_use;
 	int status;
-	int rxfifosz = priv->plat->rx_fifo_size;
+	u32 chan;
+
+	for (chan = 0; chan < tx_channel_count; chan++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];
 
-	status = priv->hw->dma->dma_interrupt(priv->ioaddr, &priv->xstats);
-	if (likely((status & handle_rx)) || (status & handle_tx)) {
-		if (likely(napi_schedule_prep(&priv->napi))) {
-			stmmac_disable_dma_irq(priv);
-			__napi_schedule(&priv->napi);
+		status = priv->hw->dma->dma_interrupt(priv->ioaddr,
+						      &priv->xstats, chan);
+		if (likely((status & handle_rx)) || (status & handle_tx)) {
+			if (likely(napi_schedule_prep(&rx_q->napi))) {
+				stmmac_disable_dma_irq(priv, chan);
+				__napi_schedule(&rx_q->napi);
+			}
 		}
-	}
-	if (unlikely(status & tx_hard_error_bump_tc)) {
-		/* Try to bump up the dma threshold on this failure */
-		if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
-		    (tc <= 256)) {
-			tc += 64;
-			if (priv->plat->force_thresh_dma_mode)
-				priv->hw->dma->dma_mode(priv->ioaddr, tc, tc,
-							rxfifosz);
-			else
-				priv->hw->dma->dma_mode(priv->ioaddr, tc,
-							SF_DMA_MODE, rxfifosz);
-			priv->xstats.threshold = tc;
+
+		if (unlikely(status & tx_hard_error_bump_tc)) {
+			/* Try to bump up the dma threshold on this failure */
+			if (unlikely(priv->xstats.threshold != SF_DMA_MODE) &&
+			    (tc <= 256)) {
+				tc += 64;
+				if (priv->plat->force_thresh_dma_mode)
+					stmmac_set_dma_operation_mode(priv,
+								      tc,
+								      tc,
+								      chan);
+				else
+					stmmac_set_dma_operation_mode(priv,
+								    tc,
+								    SF_DMA_MODE,
+								    chan);
+				priv->xstats.threshold = tc;
+			}
+		} else if (unlikely(status == tx_hard_error)) {
+			stmmac_tx_err(priv, chan);
 		}
-	} else if (unlikely(status == tx_hard_error))
-		stmmac_tx_err(priv);
+	}
 }
 
 /**
@@ -1589,6 +2120,13 @@ static void stmmac_check_ether_addr(stru
  */
 static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 {
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	struct stmmac_rx_queue *rx_q;
+	struct stmmac_tx_queue *tx_q;
+	u32 dummy_dma_rx_phy = 0;
+	u32 dummy_dma_tx_phy = 0;
+	u32 chan = 0;
 	int atds = 0;
 	int ret = 0;
 
@@ -1606,19 +2144,49 @@ static int stmmac_init_dma_engine(struct
 		return ret;
 	}
 
-	priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
-			    priv->dma_tx_phy, priv->dma_rx_phy, atds);
-
 	if (priv->synopsys_id >= DWMAC_CORE_4_00) {
-		priv->rx_tail_addr = priv->dma_rx_phy +
-			    (DMA_RX_SIZE * sizeof(struct dma_desc));
-		priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, priv->rx_tail_addr,
-					       STMMAC_CHAN0);
-
-		priv->tx_tail_addr = priv->dma_tx_phy +
-			    (DMA_TX_SIZE * sizeof(struct dma_desc));
-		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-					       STMMAC_CHAN0);
+		/* DMA Configuration */
+		priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+				    dummy_dma_tx_phy, dummy_dma_rx_phy, atds);
+
+		/* DMA RX Channel Configuration */
+		for (chan = 0; chan < rx_channels_count; chan++) {
+			rx_q = &priv->rx_queue[chan];
+
+			priv->hw->dma->init_rx_chan(priv->ioaddr,
+						    priv->plat->dma_cfg,
+						    rx_q->dma_rx_phy, chan);
+
+			rx_q->rx_tail_addr = rx_q->dma_rx_phy +
+				    (DMA_RX_SIZE * sizeof(struct dma_desc));
+			priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+						       rx_q->rx_tail_addr,
+						       chan);
+		}
+
+		/* DMA TX Channel Configuration */
+		for (chan = 0; chan < tx_channels_count; chan++) {
+			tx_q = &priv->tx_queue[chan];
+
+			priv->hw->dma->init_chan(priv->ioaddr,
+						 priv->plat->dma_cfg,
+						 chan);
+
+			priv->hw->dma->init_tx_chan(priv->ioaddr,
+						    priv->plat->dma_cfg,
+						    tx_q->dma_tx_phy, chan);
+
+			tx_q->tx_tail_addr = tx_q->dma_tx_phy +
+				    (DMA_TX_SIZE * sizeof(struct dma_desc));
+			priv->hw->dma->set_tx_tail_ptr(priv->ioaddr,
+						       tx_q->tx_tail_addr,
+						       chan);
+		}
+	} else {
+		rx_q = &priv->rx_queue[chan];
+		tx_q = &priv->tx_queue[chan];
+		priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg,
+				    tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds);
 	}
 
 	if (priv->plat->axi && priv->hw->dma->axi)
@@ -1636,8 +2204,12 @@ static int stmmac_init_dma_engine(struct
 static void stmmac_tx_timer(unsigned long data)
 {
 	struct stmmac_priv *priv = (struct stmmac_priv *)data;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue;
 
-	stmmac_tx_clean(priv);
+	/* let's scan all the tx queues */
+	for (queue = 0; queue < tx_queues_count; queue++)
+		stmmac_tx_clean(priv, queue);
 }
 
 /**
@@ -1659,6 +2231,196 @@ static void stmmac_init_tx_coalesce(stru
 	add_timer(&priv->txtimer);
 }
 
+static void stmmac_set_rings_length(struct stmmac_priv *priv)
+{
+	u32 rx_channels_count = priv->plat->rx_queues_to_use;
+	u32 tx_channels_count = priv->plat->tx_queues_to_use;
+	u32 chan;
+
+	/* set TX ring length */
+	if (priv->hw->dma->set_tx_ring_len) {
+		for (chan = 0; chan < tx_channels_count; chan++)
+			priv->hw->dma->set_tx_ring_len(priv->ioaddr,
+						       (DMA_TX_SIZE - 1), chan);
+	}
+
+	/* set RX ring length */
+	if (priv->hw->dma->set_rx_ring_len) {
+		for (chan = 0; chan < rx_channels_count; chan++)
+			priv->hw->dma->set_rx_ring_len(priv->ioaddr,
+						       (DMA_RX_SIZE - 1), chan);
+	}
+}
+
+/**
+ *  stmmac_set_tx_queue_weight - Set TX queue weight
+ *  @priv: driver private structure
+ *  Description: It is used for setting TX queues weight
+ */
+static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 weight;
+	u32 queue;
+
+	for (queue = 0; queue < tx_queues_count; queue++) {
+		weight = priv->plat->tx_queues_cfg[queue].weight;
+		priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue);
+	}
+}
+
+/**
+ *  stmmac_configure_cbs - Configure CBS in TX queue
+ *  @priv: driver private structure
+ *  Description: It is used for configuring CBS in AVB TX queues
+ */
+static void stmmac_configure_cbs(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 mode_to_use;
+	u32 queue;
+
+	/* queue 0 is reserved for legacy traffic */
+	for (queue = 1; queue < tx_queues_count; queue++) {
+		mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+		if (mode_to_use == MTL_QUEUE_DCB)
+			continue;
+
+		priv->hw->mac->config_cbs(priv->hw,
+				priv->plat->tx_queues_cfg[queue].send_slope,
+				priv->plat->tx_queues_cfg[queue].idle_slope,
+				priv->plat->tx_queues_cfg[queue].high_credit,
+				priv->plat->tx_queues_cfg[queue].low_credit,
+				queue);
+	}
+}
+
+/**
+ *  stmmac_rx_queue_dma_chan_map - Map RX queue to RX dma channel
+ *  @priv: driver private structure
+ *  Description: It is used for mapping RX queues to RX dma channels
+ */
+static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u32 chan;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		chan = priv->plat->rx_queues_cfg[queue].chan;
+		priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan);
+	}
+}
+
+/**
+ *  stmmac_mac_config_rx_queues_prio - Configure RX Queue priority
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the RX Queue Priority
+ */
+static void stmmac_mac_config_rx_queues_prio(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u32 prio;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		if (!priv->plat->rx_queues_cfg[queue].use_prio)
+			continue;
+
+		prio = priv->plat->rx_queues_cfg[queue].prio;
+		priv->hw->mac->rx_queue_prio(priv->hw, prio, queue);
+	}
+}
+
+/**
+ *  stmmac_mac_config_tx_queues_prio - Configure TX Queue priority
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the TX Queue Priority
+ */
+static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue;
+	u32 prio;
+
+	for (queue = 0; queue < tx_queues_count; queue++) {
+		if (!priv->plat->tx_queues_cfg[queue].use_prio)
+			continue;
+
+		prio = priv->plat->tx_queues_cfg[queue].prio;
+		priv->hw->mac->tx_queue_prio(priv->hw, prio, queue);
+	}
+}
+
+/**
+ *  stmmac_mac_config_rx_queues_routing - Configure RX Queue Routing
+ *  @priv: driver private structure
+ *  Description: It is used for configuring the RX queue routing
+ */
+static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 queue;
+	u8 packet;
+
+	for (queue = 0; queue < rx_queues_count; queue++) {
+		/* no specific packet type routing specified for the queue */
+		if (priv->plat->rx_queues_cfg[queue].pkt_route == 0x0)
+			continue;
+
+		packet = priv->plat->rx_queues_cfg[queue].pkt_route;
+		priv->hw->mac->rx_queue_prio(priv->hw, packet, queue);
+	}
+}
+
+/**
+ *  stmmac_mtl_configuration - Configure MTL
+ *  @priv: driver private structure
+ *  Description: It is used for configurring MTL
+ */
+static void stmmac_mtl_configuration(struct stmmac_priv *priv)
+{
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+
+	if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight)
+		stmmac_set_tx_queue_weight(priv);
+
+	/* Configure MTL RX algorithms */
+	if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms)
+		priv->hw->mac->prog_mtl_rx_algorithms(priv->hw,
+						priv->plat->rx_sched_algorithm);
+
+	/* Configure MTL TX algorithms */
+	if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms)
+		priv->hw->mac->prog_mtl_tx_algorithms(priv->hw,
+						priv->plat->tx_sched_algorithm);
+
+	/* Configure CBS in AVB TX queues */
+	if (tx_queues_count > 1 && priv->hw->mac->config_cbs)
+		stmmac_configure_cbs(priv);
+
+	/* Map RX MTL to DMA channels */
+	if (priv->hw->mac->map_mtl_to_dma)
+		stmmac_rx_queue_dma_chan_map(priv);
+
+	/* Enable MAC RX Queues */
+	if (priv->hw->mac->rx_queue_enable)
+		stmmac_mac_enable_rx_queues(priv);
+
+	/* Set RX priorities */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_prio)
+		stmmac_mac_config_rx_queues_prio(priv);
+
+	/* Set TX priorities */
+	if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio)
+		stmmac_mac_config_tx_queues_prio(priv);
+
+	/* Set RX routing */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_routing)
+		stmmac_mac_config_rx_queues_routing(priv);
+}
+
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
@@ -1674,6 +2436,9 @@ static void stmmac_init_tx_coalesce(stru
 static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 chan;
 	int ret;
 
 	/* DMA initialization and SW reset */
@@ -1703,9 +2468,9 @@ static int stmmac_hw_setup(struct net_de
 	/* Initialize the MAC Core */
 	priv->hw->mac->core_init(priv->hw, dev->mtu);
 
-	/* Initialize MAC RX Queues */
-	if (priv->hw->mac->rx_queue_enable)
-		stmmac_mac_enable_rx_queues(priv);
+	/* Initialize MTL*/
+	if (priv->synopsys_id >= DWMAC_CORE_4_00)
+		stmmac_mtl_configuration(priv);
 
 	ret = priv->hw->mac->rx_ipc(priv->hw);
 	if (!ret) {
@@ -1715,10 +2480,7 @@ static int stmmac_hw_setup(struct net_de
 	}
 
 	/* Enable the MAC Rx/Tx */
-	if (priv->synopsys_id >= DWMAC_CORE_4_00)
-		stmmac_dwmac4_set_mac(priv->ioaddr, true);
-	else
-		stmmac_set_mac(priv->ioaddr, true);
+	priv->hw->mac->set_mac(priv->ioaddr, true);
 
 	/* Set the HW DMA mode and the COE */
 	stmmac_dma_operation_mode(priv);
@@ -1726,6 +2488,10 @@ static int stmmac_hw_setup(struct net_de
 	stmmac_mmc_setup(priv);
 
 	if (init_ptp) {
+		ret = clk_prepare_enable(priv->plat->clk_ptp_ref);
+		if (ret < 0)
+			netdev_warn(priv->dev, "failed to enable PTP reference clock: %d\n", ret);
+
 		ret = stmmac_init_ptp(priv);
 		if (ret == -EOPNOTSUPP)
 			netdev_warn(priv->dev, "PTP not supported by HW\n");
@@ -1740,35 +2506,37 @@ static int stmmac_hw_setup(struct net_de
 			    __func__);
 #endif
 	/* Start the ball rolling... */
-	netdev_dbg(priv->dev, "DMA RX/TX processes started...\n");
-	priv->hw->dma->start_tx(priv->ioaddr);
-	priv->hw->dma->start_rx(priv->ioaddr);
+	stmmac_start_all_dma(priv);
 
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) {
 		priv->rx_riwt = MAX_DMA_RIWT;
-		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT);
+		priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt);
 	}
 
 	if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane)
 		priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0);
 
-	/*  set TX ring length */
-	if (priv->hw->dma->set_tx_ring_len)
-		priv->hw->dma->set_tx_ring_len(priv->ioaddr,
-					       (DMA_TX_SIZE - 1));
-	/*  set RX ring length */
-	if (priv->hw->dma->set_rx_ring_len)
-		priv->hw->dma->set_rx_ring_len(priv->ioaddr,
-					       (DMA_RX_SIZE - 1));
+	/* set TX and RX rings length */
+	stmmac_set_rings_length(priv);
+
 	/* Enable TSO */
-	if (priv->tso)
-		priv->hw->dma->enable_tso(priv->ioaddr, 1, STMMAC_CHAN0);
+	if (priv->tso) {
+		for (chan = 0; chan < tx_cnt; chan++)
+			priv->hw->dma->enable_tso(priv->ioaddr, 1, chan);
+	}
 
 	return 0;
 }
 
+static void stmmac_hw_teardown(struct net_device *dev)
+{
+	struct stmmac_priv *priv = netdev_priv(dev);
+
+	clk_disable_unprepare(priv->plat->clk_ptp_ref);
+}
+
 /**
  *  stmmac_open - open entry point of the driver
  *  @dev : pointer to the device structure.
@@ -1837,7 +2605,7 @@ static int stmmac_open(struct net_device
 		netdev_err(priv->dev,
 			   "%s: ERROR: allocating the IRQ %d (error: %d)\n",
 			   __func__, dev->irq, ret);
-		goto init_error;
+		goto irq_error;
 	}
 
 	/* Request the Wake IRQ in case of another line is used for WoL */
@@ -1864,8 +2632,8 @@ static int stmmac_open(struct net_device
 		}
 	}
 
-	napi_enable(&priv->napi);
-	netif_start_queue(dev);
+	stmmac_enable_all_queues(priv);
+	stmmac_start_all_queues(priv);
 
 	return 0;
 
@@ -1874,7 +2642,12 @@ lpiirq_error:
 		free_irq(priv->wol_irq, dev);
 wolirq_error:
 	free_irq(dev->irq, dev);
+irq_error:
+	if (dev->phydev)
+		phy_stop(dev->phydev);
 
+	del_timer_sync(&priv->txtimer);
+	stmmac_hw_teardown(dev);
 init_error:
 	free_dma_desc_resources(priv);
 dma_desc_error:
@@ -1903,9 +2676,9 @@ static int stmmac_release(struct net_dev
 		phy_disconnect(dev->phydev);
 	}
 
-	netif_stop_queue(dev);
+	stmmac_stop_all_queues(priv);
 
-	napi_disable(&priv->napi);
+	stmmac_disable_all_queues(priv);
 
 	del_timer_sync(&priv->txtimer);
 
@@ -1917,14 +2690,13 @@ static int stmmac_release(struct net_dev
 		free_irq(priv->lpi_irq, dev);
 
 	/* Stop TX/RX DMA and clear the descriptors */
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	priv->hw->dma->stop_rx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
 	/* Release and free the Rx/Tx resources */
 	free_dma_desc_resources(priv);
 
 	/* Disable the MAC Rx/Tx */
-	stmmac_set_mac(priv->ioaddr, false);
+	priv->hw->mac->set_mac(priv->ioaddr, false);
 
 	netif_carrier_off(dev);
 
@@ -1943,22 +2715,24 @@ static int stmmac_release(struct net_dev
  *  @des: buffer start address
  *  @total_len: total length to fill in descriptors
  *  @last_segmant: condition for the last descriptor
+ *  @queue: TX queue index
  *  Description:
  *  This function fills descriptor and request new descriptors according to
  *  buffer length to fill
  */
 static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des,
-				 int total_len, bool last_segment)
+				 int total_len, bool last_segment, u32 queue)
 {
+	struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
 	struct dma_desc *desc;
-	int tmp_len;
 	u32 buff_size;
+	int tmp_len;
 
 	tmp_len = total_len;
 
 	while (tmp_len > 0) {
-		priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
-		desc = priv->dma_tx + priv->cur_tx;
+		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
+		desc = tx_q->dma_tx + tx_q->cur_tx;
 
 		desc->des0 = cpu_to_le32(des + (total_len - tmp_len));
 		buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ?
@@ -1966,7 +2740,7 @@ static void stmmac_tso_allocator(struct
 
 		priv->hw->desc->prepare_tso_tx_desc(desc, 0, buff_size,
 			0, 1,
-			(last_segment) && (buff_size < TSO_MAX_BUFF_SIZE),
+			(last_segment) && (tmp_len <= TSO_MAX_BUFF_SIZE),
 			0, 0);
 
 		tmp_len -= TSO_MAX_BUFF_SIZE;
@@ -2002,23 +2776,28 @@ static void stmmac_tso_allocator(struct
  */
 static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	u32 pay_len, mss;
-	int tmp_pay_len = 0;
+	struct dma_desc *desc, *first, *mss_desc = NULL;
 	struct stmmac_priv *priv = netdev_priv(dev);
 	int nfrags = skb_shinfo(skb)->nr_frags;
+	u32 queue = skb_get_queue_mapping(skb);
 	unsigned int first_entry, des;
-	struct dma_desc *desc, *first, *mss_desc = NULL;
+	struct stmmac_tx_queue *tx_q;
+	int tmp_pay_len = 0;
+	u32 pay_len, mss;
 	u8 proto_hdr_len;
 	int i;
 
+	tx_q = &priv->tx_queue[queue];
+
 	/* Compute header lengths */
 	proto_hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
 
 	/* Desc availability based on threshold should be enough safe */
-	if (unlikely(stmmac_tx_avail(priv) <
+	if (unlikely(stmmac_tx_avail(priv, queue) <
 		(((skb->len - proto_hdr_len) / TSO_MAX_BUFF_SIZE + 1)))) {
-		if (!netif_queue_stopped(dev)) {
-			netif_stop_queue(dev);
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
+			netif_tx_stop_queue(netdev_get_tx_queue(priv->dev,
+								queue));
 			/* This is a hard error, log it. */
 			netdev_err(priv->dev,
 				   "%s: Tx Ring full when queue awake\n",
@@ -2033,10 +2812,10 @@ static netdev_tx_t stmmac_tso_xmit(struc
 
 	/* set new MSS value if needed */
 	if (mss != priv->mss) {
-		mss_desc = priv->dma_tx + priv->cur_tx;
+		mss_desc = tx_q->dma_tx + tx_q->cur_tx;
 		priv->hw->desc->set_mss(mss_desc, mss);
 		priv->mss = mss;
-		priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
+		tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
 	}
 
 	if (netif_msg_tx_queued(priv)) {
@@ -2046,9 +2825,9 @@ static netdev_tx_t stmmac_tso_xmit(struc
 			skb->data_len);
 	}
 
-	first_entry = priv->cur_tx;
+	first_entry = tx_q->cur_tx;
 
-	desc = priv->dma_tx + first_entry;
+	desc = tx_q->dma_tx + first_entry;
 	first = desc;
 
 	/* first descriptor: fill Headers on Buf1 */
@@ -2057,9 +2836,8 @@ static netdev_tx_t stmmac_tso_xmit(struc
 	if (dma_mapping_error(priv->device, des))
 		goto dma_map_err;
 
-	priv->tx_skbuff_dma[first_entry].buf = des;
-	priv->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
-	priv->tx_skbuff[first_entry] = skb;
+	tx_q->tx_skbuff_dma[first_entry].buf = des;
+	tx_q->tx_skbuff_dma[first_entry].len = skb_headlen(skb);
 
 	first->des0 = cpu_to_le32(des);
 
@@ -2070,7 +2848,7 @@ static netdev_tx_t stmmac_tso_xmit(struc
 	/* If needed take extra descriptors to fill the remaining payload */
 	tmp_pay_len = pay_len - TSO_MAX_BUFF_SIZE;
 
-	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0));
+	stmmac_tso_allocator(priv, des, tmp_pay_len, (nfrags == 0), queue);
 
 	/* Prepare fragments */
 	for (i = 0; i < nfrags; i++) {
@@ -2079,24 +2857,34 @@ static netdev_tx_t stmmac_tso_xmit(struc
 		des = skb_frag_dma_map(priv->device, frag, 0,
 				       skb_frag_size(frag),
 				       DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->device, des))
+			goto dma_map_err;
 
 		stmmac_tso_allocator(priv, des, skb_frag_size(frag),
-				     (i == nfrags - 1));
+				     (i == nfrags - 1), queue);
 
-		priv->tx_skbuff_dma[priv->cur_tx].buf = des;
-		priv->tx_skbuff_dma[priv->cur_tx].len = skb_frag_size(frag);
-		priv->tx_skbuff[priv->cur_tx] = NULL;
-		priv->tx_skbuff_dma[priv->cur_tx].map_as_page = true;
+		tx_q->tx_skbuff_dma[tx_q->cur_tx].buf = des;
+		tx_q->tx_skbuff_dma[tx_q->cur_tx].len = skb_frag_size(frag);
+		tx_q->tx_skbuff[tx_q->cur_tx] = NULL;
+		tx_q->tx_skbuff_dma[tx_q->cur_tx].map_as_page = true;
 	}
 
-	priv->tx_skbuff_dma[priv->cur_tx].last_segment = true;
+	tx_q->tx_skbuff_dma[tx_q->cur_tx].last_segment = true;
+
+	/* Only the last descriptor gets to point to the skb. */
+	tx_q->tx_skbuff[tx_q->cur_tx] = skb;
 
-	priv->cur_tx = STMMAC_GET_ENTRY(priv->cur_tx, DMA_TX_SIZE);
+	/* We've used all descriptors we need for this skb, however,
+	 * advance cur_tx so that it references a fresh descriptor.
+	 * ndo_start_xmit will fill this descriptor the next time it's
+	 * called and stmmac_tx_clean may clean up to this descriptor.
+	 */
+	tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE);
 
-	if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
+	if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) {
 		netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
 			  __func__);
-		netif_stop_queue(dev);
+		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
 	dev->stats.tx_bytes += skb->len;
@@ -2128,7 +2916,7 @@ static netdev_tx_t stmmac_tso_xmit(struc
 	priv->hw->desc->prepare_tso_tx_desc(first, 1,
 			proto_hdr_len,
 			pay_len,
-			1, priv->tx_skbuff_dma[first_entry].last_segment,
+			1, tx_q->tx_skbuff_dma[first_entry].last_segment,
 			tcp_hdrlen(skb) / 4, (skb->len - proto_hdr_len));
 
 	/* If context desc is used to change MSS */
@@ -2143,20 +2931,20 @@ static netdev_tx_t stmmac_tso_xmit(struc
 
 	if (netif_msg_pktdata(priv)) {
 		pr_info("%s: curr=%d dirty=%d f=%d, e=%d, f_p=%p, nfrags %d\n",
-			__func__, priv->cur_tx, priv->dirty_tx, first_entry,
-			priv->cur_tx, first, nfrags);
+			__func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
+			tx_q->cur_tx, first, nfrags);
 
-		priv->hw->desc->display_ring((void *)priv->dma_tx, DMA_TX_SIZE,
+		priv->hw->desc->display_ring((void *)tx_q->dma_tx, DMA_TX_SIZE,
 					     0);
 
 		pr_info(">>> frame to be transmitted: ");
 		print_pkt(skb->data, skb_headlen(skb));
 	}
 
-	netdev_sent_queue(dev, skb->len);
+	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
-	priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-				       STMMAC_CHAN0);
+	priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr,
+				       queue);
 
 	return NETDEV_TX_OK;
 
@@ -2180,21 +2968,27 @@ static netdev_tx_t stmmac_xmit(struct sk
 	struct stmmac_priv *priv = netdev_priv(dev);
 	unsigned int nopaged_len = skb_headlen(skb);
 	int i, csum_insertion = 0, is_jumbo = 0;
+	u32 queue = skb_get_queue_mapping(skb);
 	int nfrags = skb_shinfo(skb)->nr_frags;
-	unsigned int entry, first_entry;
+	int entry;
+	unsigned int first_entry;
 	struct dma_desc *desc, *first;
+	struct stmmac_tx_queue *tx_q;
 	unsigned int enh_desc;
 	unsigned int des;
 
+	tx_q = &priv->tx_queue[queue];
+
 	/* Manage oversized TCP frames for GMAC4 device */
 	if (skb_is_gso(skb) && priv->tso) {
 		if (ip_hdr(skb)->protocol == IPPROTO_TCP)
 			return stmmac_tso_xmit(skb, dev);
 	}
 
-	if (unlikely(stmmac_tx_avail(priv) < nfrags + 1)) {
-		if (!netif_queue_stopped(dev)) {
-			netif_stop_queue(dev);
+	if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) {
+		if (!netif_tx_queue_stopped(netdev_get_tx_queue(dev, queue))) {
+			netif_tx_stop_queue(netdev_get_tx_queue(priv->dev,
+								queue));
 			/* This is a hard error, log it. */
 			netdev_err(priv->dev,
 				   "%s: Tx Ring full when queue awake\n",
@@ -2206,20 +3000,18 @@ static netdev_tx_t stmmac_xmit(struct sk
 	if (priv->tx_path_in_lpi_mode)
 		stmmac_disable_eee_mode(priv);
 
-	entry = priv->cur_tx;
+	entry = tx_q->cur_tx;
 	first_entry = entry;
 
 	csum_insertion = (skb->ip_summed == CHECKSUM_PARTIAL);
 
 	if (likely(priv->extend_desc))
-		desc = (struct dma_desc *)(priv->dma_etx + entry);
+		desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 	else
-		desc = priv->dma_tx + entry;
+		desc = tx_q->dma_tx + entry;
 
 	first = desc;
 
-	priv->tx_skbuff[first_entry] = skb;
-
 	enh_desc = priv->plat->enh_desc;
 	/* To program the descriptors according to the size of the frame */
 	if (enh_desc)
@@ -2227,7 +3019,7 @@ static netdev_tx_t stmmac_xmit(struct sk
 
 	if (unlikely(is_jumbo) && likely(priv->synopsys_id <
 					 DWMAC_CORE_4_00)) {
-		entry = priv->hw->mode->jumbo_frm(priv, skb, csum_insertion);
+		entry = priv->hw->mode->jumbo_frm(tx_q, skb, csum_insertion);
 		if (unlikely(entry < 0))
 			goto dma_map_err;
 	}
@@ -2240,48 +3032,56 @@ static netdev_tx_t stmmac_xmit(struct sk
 		entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
 
 		if (likely(priv->extend_desc))
-			desc = (struct dma_desc *)(priv->dma_etx + entry);
+			desc = (struct dma_desc *)(tx_q->dma_etx + entry);
 		else
-			desc = priv->dma_tx + entry;
+			desc = tx_q->dma_tx + entry;
 
 		des = skb_frag_dma_map(priv->device, frag, 0, len,
 				       DMA_TO_DEVICE);
 		if (dma_mapping_error(priv->device, des))
 			goto dma_map_err; /* should reuse desc w/o issues */
 
-		priv->tx_skbuff[entry] = NULL;
+		tx_q->tx_skbuff[entry] = NULL;
 
-		priv->tx_skbuff_dma[entry].buf = des;
+		tx_q->tx_skbuff_dma[entry].buf = des;
 		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
 			desc->des0 = cpu_to_le32(des);
 		else
 			desc->des2 = cpu_to_le32(des);
 
-		priv->tx_skbuff_dma[entry].map_as_page = true;
-		priv->tx_skbuff_dma[entry].len = len;
-		priv->tx_skbuff_dma[entry].last_segment = last_segment;
+		tx_q->tx_skbuff_dma[entry].map_as_page = true;
+		tx_q->tx_skbuff_dma[entry].len = len;
+		tx_q->tx_skbuff_dma[entry].last_segment = last_segment;
 
 		/* Prepare the descriptor and set the own bit too */
 		priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion,
-						priv->mode, 1, last_segment);
+						priv->mode, 1, last_segment,
+						skb->len);
 	}
 
-	entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
+	/* Only the last descriptor gets to point to the skb. */
+	tx_q->tx_skbuff[entry] = skb;
 
-	priv->cur_tx = entry;
+	/* We've used all descriptors we need for this skb, however,
+	 * advance cur_tx so that it references a fresh descriptor.
+	 * ndo_start_xmit will fill this descriptor the next time it's
+	 * called and stmmac_tx_clean may clean up to this descriptor.
+	 */
+	entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE);
+	tx_q->cur_tx = entry;
 
 	if (netif_msg_pktdata(priv)) {
 		void *tx_head;
 
 		netdev_dbg(priv->dev,
 			   "%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
-			   __func__, priv->cur_tx, priv->dirty_tx, first_entry,
+			   __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry,
 			   entry, first, nfrags);
 
 		if (priv->extend_desc)
-			tx_head = (void *)priv->dma_etx;
+			tx_head = (void *)tx_q->dma_etx;
 		else
-			tx_head = (void *)priv->dma_tx;
+			tx_head = (void *)tx_q->dma_tx;
 
 		priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false);
 
@@ -2289,10 +3089,10 @@ static netdev_tx_t stmmac_xmit(struct sk
 		print_pkt(skb->data, skb->len);
 	}
 
-	if (unlikely(stmmac_tx_avail(priv) <= (MAX_SKB_FRAGS + 1))) {
+	if (unlikely(stmmac_tx_avail(priv, queue) <= (MAX_SKB_FRAGS + 1))) {
 		netif_dbg(priv, hw, priv->dev, "%s: stop transmitted packets\n",
 			  __func__);
-		netif_stop_queue(dev);
+		netif_tx_stop_queue(netdev_get_tx_queue(priv->dev, queue));
 	}
 
 	dev->stats.tx_bytes += skb->len;
@@ -2327,14 +3127,14 @@ static netdev_tx_t stmmac_xmit(struct sk
 		if (dma_mapping_error(priv->device, des))
 			goto dma_map_err;
 
-		priv->tx_skbuff_dma[first_entry].buf = des;
+		tx_q->tx_skbuff_dma[first_entry].buf = des;
 		if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00))
 			first->des0 = cpu_to_le32(des);
 		else
 			first->des2 = cpu_to_le32(des);
 
-		priv->tx_skbuff_dma[first_entry].len = nopaged_len;
-		priv->tx_skbuff_dma[first_entry].last_segment = last_segment;
+		tx_q->tx_skbuff_dma[first_entry].len = nopaged_len;
+		tx_q->tx_skbuff_dma[first_entry].last_segment = last_segment;
 
 		if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 			     priv->hwts_tx_en)) {
@@ -2346,7 +3146,7 @@ static netdev_tx_t stmmac_xmit(struct sk
 		/* Prepare the first descriptor setting the OWN bit too */
 		priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len,
 						csum_insertion, priv->mode, 1,
-						last_segment);
+						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
@@ -2355,13 +3155,13 @@ static netdev_tx_t stmmac_xmit(struct sk
 		dma_wmb();
 	}
 
-	netdev_sent_queue(dev, skb->len);
+	netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len);
 
 	if (priv->synopsys_id < DWMAC_CORE_4_00)
 		priv->hw->dma->enable_dma_transmission(priv->ioaddr);
 	else
-		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, priv->tx_tail_addr,
-					       STMMAC_CHAN0);
+		priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr,
+					       queue);
 
 	return NETDEV_TX_OK;
 
@@ -2389,9 +3189,9 @@ static void stmmac_rx_vlan(struct net_de
 }
 
 
-static inline int stmmac_rx_threshold_count(struct stmmac_priv *priv)
+static inline int stmmac_rx_threshold_count(struct stmmac_rx_queue *rx_q)
 {
-	if (priv->rx_zeroc_thresh < STMMAC_RX_THRESH)
+	if (rx_q->rx_zeroc_thresh < STMMAC_RX_THRESH)
 		return 0;
 
 	return 1;
@@ -2400,30 +3200,33 @@ static inline int stmmac_rx_threshold_co
 /**
  * stmmac_rx_refill - refill used skb preallocated buffers
  * @priv: driver private structure
+ * @queue: RX queue index
  * Description : this is to reallocate the skb for the reception process
  * that is based on zero-copy.
  */
-static inline void stmmac_rx_refill(struct stmmac_priv *priv)
+static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 {
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	int dirty = stmmac_rx_dirty(priv, queue);
+	unsigned int entry = rx_q->dirty_rx;
+
 	int bfsize = priv->dma_buf_sz;
-	unsigned int entry = priv->dirty_rx;
-	int dirty = stmmac_rx_dirty(priv);
 
 	while (dirty-- > 0) {
 		struct dma_desc *p;
 
 		if (priv->extend_desc)
-			p = (struct dma_desc *)(priv->dma_erx + entry);
+			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
-			p = priv->dma_rx + entry;
+			p = rx_q->dma_rx + entry;
 
-		if (likely(priv->rx_skbuff[entry] == NULL)) {
+		if (likely(!rx_q->rx_skbuff[entry])) {
 			struct sk_buff *skb;
 
 			skb = netdev_alloc_skb_ip_align(priv->dev, bfsize);
 			if (unlikely(!skb)) {
 				/* so for a while no zero-copy! */
-				priv->rx_zeroc_thresh = STMMAC_RX_THRESH;
+				rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH;
 				if (unlikely(net_ratelimit()))
 					dev_err(priv->device,
 						"fail to alloc skb entry %d\n",
@@ -2431,28 +3234,28 @@ static inline void stmmac_rx_refill(stru
 				break;
 			}
 
-			priv->rx_skbuff[entry] = skb;
-			priv->rx_skbuff_dma[entry] =
+			rx_q->rx_skbuff[entry] = skb;
+			rx_q->rx_skbuff_dma[entry] =
 			    dma_map_single(priv->device, skb->data, bfsize,
 					   DMA_FROM_DEVICE);
 			if (dma_mapping_error(priv->device,
-					      priv->rx_skbuff_dma[entry])) {
+					      rx_q->rx_skbuff_dma[entry])) {
 				netdev_err(priv->dev, "Rx DMA map failed\n");
 				dev_kfree_skb(skb);
 				break;
 			}
 
 			if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) {
-				p->des0 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
+				p->des0 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
 				p->des1 = 0;
 			} else {
-				p->des2 = cpu_to_le32(priv->rx_skbuff_dma[entry]);
+				p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]);
 			}
 			if (priv->hw->mode->refill_desc3)
-				priv->hw->mode->refill_desc3(priv, p);
+				priv->hw->mode->refill_desc3(rx_q, p);
 
-			if (priv->rx_zeroc_thresh > 0)
-				priv->rx_zeroc_thresh--;
+			if (rx_q->rx_zeroc_thresh > 0)
+				rx_q->rx_zeroc_thresh--;
 
 			netif_dbg(priv, rx_status, priv->dev,
 				  "refill entry #%d\n", entry);
@@ -2468,31 +3271,33 @@ static inline void stmmac_rx_refill(stru
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
 	}
-	priv->dirty_rx = entry;
+	rx_q->dirty_rx = entry;
 }
 
 /**
  * stmmac_rx - manage the receive process
  * @priv: driver private structure
- * @limit: napi bugget.
+ * @limit: napi bugget
+ * @queue: RX queue index.
  * Description :  this the function called by the napi poll method.
  * It gets all the frames inside the ring.
  */
-static int stmmac_rx(struct stmmac_priv *priv, int limit)
+static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 {
-	unsigned int entry = priv->cur_rx;
+	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	unsigned int entry = rx_q->cur_rx;
+	int coe = priv->hw->rx_csum;
 	unsigned int next_entry;
 	unsigned int count = 0;
-	int coe = priv->hw->rx_csum;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
 
 		netdev_dbg(priv->dev, "%s: descriptor ring:\n", __func__);
 		if (priv->extend_desc)
-			rx_head = (void *)priv->dma_erx;
+			rx_head = (void *)rx_q->dma_erx;
 		else
-			rx_head = (void *)priv->dma_rx;
+			rx_head = (void *)rx_q->dma_rx;
 
 		priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true);
 	}
@@ -2502,9 +3307,9 @@ static int stmmac_rx(struct stmmac_priv
 		struct dma_desc *np;
 
 		if (priv->extend_desc)
-			p = (struct dma_desc *)(priv->dma_erx + entry);
+			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
-			p = priv->dma_rx + entry;
+			p = rx_q->dma_rx + entry;
 
 		/* read the status of the incoming frame */
 		status = priv->hw->desc->rx_status(&priv->dev->stats,
@@ -2515,20 +3320,20 @@ static int stmmac_rx(struct stmmac_priv
 
 		count++;
 
-		priv->cur_rx = STMMAC_GET_ENTRY(priv->cur_rx, DMA_RX_SIZE);
-		next_entry = priv->cur_rx;
+		rx_q->cur_rx = STMMAC_GET_ENTRY(rx_q->cur_rx, DMA_RX_SIZE);
+		next_entry = rx_q->cur_rx;
 
 		if (priv->extend_desc)
-			np = (struct dma_desc *)(priv->dma_erx + next_entry);
+			np = (struct dma_desc *)(rx_q->dma_erx + next_entry);
 		else
-			np = priv->dma_rx + next_entry;
+			np = rx_q->dma_rx + next_entry;
 
 		prefetch(np);
 
 		if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status))
 			priv->hw->desc->rx_extended_status(&priv->dev->stats,
 							   &priv->xstats,
-							   priv->dma_erx +
+							   rx_q->dma_erx +
 							   entry);
 		if (unlikely(status == discard_frame)) {
 			priv->dev->stats.rx_errors++;
@@ -2538,9 +3343,9 @@ static int stmmac_rx(struct stmmac_priv
 				 * them in stmmac_rx_refill() function so that
 				 * device can reuse it.
 				 */
-				priv->rx_skbuff[entry] = NULL;
+				rx_q->rx_skbuff[entry] = NULL;
 				dma_unmap_single(priv->device,
-						 priv->rx_skbuff_dma[entry],
+						 rx_q->rx_skbuff_dma[entry],
 						 priv->dma_buf_sz,
 						 DMA_FROM_DEVICE);
 			}
@@ -2588,7 +3393,7 @@ static int stmmac_rx(struct stmmac_priv
 			 */
 			if (unlikely(!priv->plat->has_gmac4 &&
 				     ((frame_len < priv->rx_copybreak) ||
-				     stmmac_rx_threshold_count(priv)))) {
+				     stmmac_rx_threshold_count(rx_q)))) {
 				skb = netdev_alloc_skb_ip_align(priv->dev,
 								frame_len);
 				if (unlikely(!skb)) {
@@ -2600,21 +3405,21 @@ static int stmmac_rx(struct stmmac_priv
 				}
 
 				dma_sync_single_for_cpu(priv->device,
-							priv->rx_skbuff_dma
+							rx_q->rx_skbuff_dma
 							[entry], frame_len,
 							DMA_FROM_DEVICE);
 				skb_copy_to_linear_data(skb,
-							priv->
+							rx_q->
 							rx_skbuff[entry]->data,
 							frame_len);
 
 				skb_put(skb, frame_len);
 				dma_sync_single_for_device(priv->device,
-							   priv->rx_skbuff_dma
+							   rx_q->rx_skbuff_dma
 							   [entry], frame_len,
 							   DMA_FROM_DEVICE);
 			} else {
-				skb = priv->rx_skbuff[entry];
+				skb = rx_q->rx_skbuff[entry];
 				if (unlikely(!skb)) {
 					netdev_err(priv->dev,
 						   "%s: Inconsistent Rx chain\n",
@@ -2623,12 +3428,12 @@ static int stmmac_rx(struct stmmac_priv
 					break;
 				}
 				prefetch(skb->data - NET_IP_ALIGN);
-				priv->rx_skbuff[entry] = NULL;
-				priv->rx_zeroc_thresh++;
+				rx_q->rx_skbuff[entry] = NULL;
+				rx_q->rx_zeroc_thresh++;
 
 				skb_put(skb, frame_len);
 				dma_unmap_single(priv->device,
-						 priv->rx_skbuff_dma[entry],
+						 rx_q->rx_skbuff_dma[entry],
 						 priv->dma_buf_sz,
 						 DMA_FROM_DEVICE);
 			}
@@ -2650,7 +3455,7 @@ static int stmmac_rx(struct stmmac_priv
 			else
 				skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-			napi_gro_receive(&priv->napi, skb);
+			napi_gro_receive(&rx_q->napi, skb);
 
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
@@ -2658,7 +3463,7 @@ static int stmmac_rx(struct stmmac_priv
 		entry = next_entry;
 	}
 
-	stmmac_rx_refill(priv);
+	stmmac_rx_refill(priv, queue);
 
 	priv->xstats.rx_pkt_n += count;
 
@@ -2675,16 +3480,24 @@ static int stmmac_rx(struct stmmac_priv
  */
 static int stmmac_poll(struct napi_struct *napi, int budget)
 {
-	struct stmmac_priv *priv = container_of(napi, struct stmmac_priv, napi);
+	struct stmmac_rx_queue *rx_q =
+		container_of(napi, struct stmmac_rx_queue, napi);
+	struct stmmac_priv *priv = rx_q->priv_data;
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 chan = rx_q->queue_index;
 	int work_done = 0;
+	u32 queue;
 
 	priv->xstats.napi_poll++;
-	stmmac_tx_clean(priv);
 
-	work_done = stmmac_rx(priv, budget);
+	/* check all the queues */
+	for (queue = 0; queue < tx_count; queue++)
+		stmmac_tx_clean(priv, queue);
+
+	work_done = stmmac_rx(priv, budget, rx_q->queue_index);
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-		stmmac_enable_dma_irq(priv);
+		stmmac_enable_dma_irq(priv, chan);
 	}
 	return work_done;
 }
@@ -2700,9 +3513,12 @@ static int stmmac_poll(struct napi_struc
 static void stmmac_tx_timeout(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 chan;
 
 	/* Clear Tx resources and restart transmitting again */
-	stmmac_tx_err(priv);
+	for (chan = 0; chan < tx_count; chan++)
+		stmmac_tx_err(priv, chan);
 }
 
 /**
@@ -2825,6 +3641,12 @@ static irqreturn_t stmmac_interrupt(int
 {
 	struct net_device *dev = (struct net_device *)dev_id;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queues_count;
+	u32 queue;
+
+	queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt;
 
 	if (priv->irq_wake)
 		pm_wakeup_event(priv->device, 0);
@@ -2838,16 +3660,30 @@ static irqreturn_t stmmac_interrupt(int
 	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
 		int status = priv->hw->mac->host_irq_status(priv->hw,
 							    &priv->xstats);
+
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
 			if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE)
 				priv->tx_path_in_lpi_mode = true;
 			if (status & CORE_IRQ_TX_PATH_EXIT_LPI_MODE)
 				priv->tx_path_in_lpi_mode = false;
-			if (status & CORE_IRQ_MTL_RX_OVERFLOW && priv->hw->dma->set_rx_tail_ptr)
-				priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
-							priv->rx_tail_addr,
-							STMMAC_CHAN0);
+		}
+
+		if (priv->synopsys_id >= DWMAC_CORE_4_00) {
+			for (queue = 0; queue < queues_count; queue++) {
+				struct stmmac_rx_queue *rx_q =
+				&priv->rx_queue[queue];
+
+				status |=
+				priv->hw->mac->host_mtl_irq_status(priv->hw,
+								   queue);
+
+				if (status & CORE_IRQ_MTL_RX_OVERFLOW &&
+				    priv->hw->dma->set_rx_tail_ptr)
+					priv->hw->dma->set_rx_tail_ptr(priv->ioaddr,
+								rx_q->rx_tail_addr,
+								queue);
+			}
 		}
 
 		/* PCS link status */
@@ -2932,7 +3768,7 @@ static void sysfs_display_ring(void *hea
 			ep++;
 		} else {
 			seq_printf(seq, "%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
-				   i, (unsigned int)virt_to_phys(ep),
+				   i, (unsigned int)virt_to_phys(p),
 				   le32_to_cpu(p->des0), le32_to_cpu(p->des1),
 				   le32_to_cpu(p->des2), le32_to_cpu(p->des3));
 			p++;
@@ -2945,17 +3781,40 @@ static int stmmac_sysfs_ring_read(struct
 {
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
+	u32 rx_count = priv->plat->rx_queues_to_use;
+	u32 tx_count = priv->plat->tx_queues_to_use;
+	u32 queue;
 
-	if (priv->extend_desc) {
-		seq_printf(seq, "Extended RX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_erx, DMA_RX_SIZE, 1, seq);
-		seq_printf(seq, "Extended TX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_etx, DMA_TX_SIZE, 1, seq);
-	} else {
-		seq_printf(seq, "RX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_rx, DMA_RX_SIZE, 0, seq);
-		seq_printf(seq, "TX descriptor ring:\n");
-		sysfs_display_ring((void *)priv->dma_tx, DMA_TX_SIZE, 0, seq);
+	for (queue = 0; queue < rx_count; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		seq_printf(seq, "RX Queue %d:\n", queue);
+
+		if (priv->extend_desc) {
+			seq_printf(seq, "Extended descriptor ring:\n");
+			sysfs_display_ring((void *)rx_q->dma_erx,
+					   DMA_RX_SIZE, 1, seq);
+		} else {
+			seq_printf(seq, "Descriptor ring:\n");
+			sysfs_display_ring((void *)rx_q->dma_rx,
+					   DMA_RX_SIZE, 0, seq);
+		}
+	}
+
+	for (queue = 0; queue < tx_count; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		seq_printf(seq, "TX Queue %d:\n", queue);
+
+		if (priv->extend_desc) {
+			seq_printf(seq, "Extended descriptor ring:\n");
+			sysfs_display_ring((void *)tx_q->dma_etx,
+					   DMA_TX_SIZE, 1, seq);
+		} else {
+			seq_printf(seq, "Descriptor ring:\n");
+			sysfs_display_ring((void *)tx_q->dma_tx,
+					   DMA_TX_SIZE, 0, seq);
+		}
 	}
 
 	return 0;
@@ -3238,11 +4097,14 @@ int stmmac_dvr_probe(struct device *devi
 		     struct plat_stmmacenet_data *plat_dat,
 		     struct stmmac_resources *res)
 {
-	int ret = 0;
 	struct net_device *ndev = NULL;
 	struct stmmac_priv *priv;
+	int ret = 0;
+	u32 queue;
 
-	ndev = alloc_etherdev(sizeof(struct stmmac_priv));
+	ndev = alloc_etherdev_mqs(sizeof(struct stmmac_priv),
+				  MTL_MAX_TX_QUEUES,
+				  MTL_MAX_RX_QUEUES);
 	if (!ndev)
 		return -ENOMEM;
 
@@ -3284,6 +4146,10 @@ int stmmac_dvr_probe(struct device *devi
 	if (ret)
 		goto error_hw_init;
 
+	/* 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);
+
 	ndev->netdev_ops = &stmmac_netdev_ops;
 
 	ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -3316,7 +4182,12 @@ int stmmac_dvr_probe(struct device *devi
 			 "Enable RX Mitigation via HW Watchdog Timer\n");
 	}
 
-	netif_napi_add(ndev, &priv->napi, stmmac_poll, 64);
+	for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		netif_napi_add(ndev, &rx_q->napi, stmmac_poll,
+			       (8 * priv->plat->rx_queues_to_use));
+	}
 
 	spin_lock_init(&priv->lock);
 
@@ -3361,7 +4232,11 @@ error_netdev_register:
 	    priv->hw->pcs != STMMAC_PCS_RTBI)
 		stmmac_mdio_unregister(ndev);
 error_mdio_register:
-	netif_napi_del(&priv->napi);
+	for (queue = 0; queue < priv->plat->rx_queues_to_use; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		netif_napi_del(&rx_q->napi);
+	}
 error_hw_init:
 	free_netdev(ndev);
 
@@ -3382,10 +4257,9 @@ int stmmac_dvr_remove(struct device *dev
 
 	netdev_info(priv->dev, "%s: removing driver", __func__);
 
-	priv->hw->dma->stop_rx(priv->ioaddr);
-	priv->hw->dma->stop_tx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
-	stmmac_set_mac(priv->ioaddr, false);
+	priv->hw->mac->set_mac(priv->ioaddr, false);
 	netif_carrier_off(ndev);
 	unregister_netdev(ndev);
 	if (priv->plat->stmmac_rst)
@@ -3424,20 +4298,19 @@ int stmmac_suspend(struct device *dev)
 	spin_lock_irqsave(&priv->lock, flags);
 
 	netif_device_detach(ndev);
-	netif_stop_queue(ndev);
+	stmmac_stop_all_queues(priv);
 
-	napi_disable(&priv->napi);
+	stmmac_disable_all_queues(priv);
 
 	/* Stop TX/RX DMA */
-	priv->hw->dma->stop_tx(priv->ioaddr);
-	priv->hw->dma->stop_rx(priv->ioaddr);
+	stmmac_stop_all_dma(priv);
 
 	/* Enable Power down mode by programming the PMT regs */
 	if (device_may_wakeup(priv->device)) {
 		priv->hw->mac->pmt(priv->hw, priv->wolopts);
 		priv->irq_wake = 1;
 	} else {
-		stmmac_set_mac(priv->ioaddr, false);
+		priv->hw->mac->set_mac(priv->ioaddr, false);
 		pinctrl_pm_select_sleep_state(priv->device);
 		/* Disable clock in case of PWM is off */
 		clk_disable(priv->plat->pclk);
@@ -3453,6 +4326,31 @@ int stmmac_suspend(struct device *dev)
 EXPORT_SYMBOL_GPL(stmmac_suspend);
 
 /**
+ * stmmac_reset_queues_param - reset queue parameters
+ * @dev: device pointer
+ */
+static void stmmac_reset_queues_param(struct stmmac_priv *priv)
+{
+	u32 rx_cnt = priv->plat->rx_queues_to_use;
+	u32 tx_cnt = priv->plat->tx_queues_to_use;
+	u32 queue;
+
+	for (queue = 0; queue < rx_cnt; queue++) {
+		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+
+		rx_q->cur_rx = 0;
+		rx_q->dirty_rx = 0;
+	}
+
+	for (queue = 0; queue < tx_cnt; queue++) {
+		struct stmmac_tx_queue *tx_q = &priv->tx_queue[queue];
+
+		tx_q->cur_tx = 0;
+		tx_q->dirty_tx = 0;
+	}
+}
+
+/**
  * stmmac_resume - resume callback
  * @dev: device pointer
  * Description: when resume this function is invoked to setup the DMA and CORE
@@ -3492,10 +4390,8 @@ int stmmac_resume(struct device *dev)
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	priv->cur_rx = 0;
-	priv->dirty_rx = 0;
-	priv->dirty_tx = 0;
-	priv->cur_tx = 0;
+	stmmac_reset_queues_param(priv);
+
 	/* reset private mss value to force mss context settings at
 	 * next tso xmit (only used for gmac4).
 	 */
@@ -3507,9 +4403,9 @@ int stmmac_resume(struct device *dev)
 	stmmac_init_tx_coalesce(priv);
 	stmmac_set_rx_mode(ndev);
 
-	napi_enable(&priv->napi);
+	stmmac_enable_all_queues(priv);
 
-	netif_start_queue(ndev);
+	stmmac_start_all_queues(priv);
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -32,6 +32,7 @@
  */
 struct stmmac_pci_dmi_data {
 	const char *name;
+	const char *asset_tag;
 	unsigned int func;
 	int phy_addr;
 };
@@ -46,6 +47,7 @@ struct stmmac_pci_info {
 static int stmmac_pci_find_phy_addr(struct stmmac_pci_info *info)
 {
 	const char *name = dmi_get_system_info(DMI_BOARD_NAME);
+	const char *asset_tag = dmi_get_system_info(DMI_BOARD_ASSET_TAG);
 	unsigned int func = PCI_FUNC(info->pdev->devfn);
 	struct stmmac_pci_dmi_data *dmi;
 
@@ -57,18 +59,19 @@ static int stmmac_pci_find_phy_addr(stru
 		return 1;
 
 	for (dmi = info->dmi; dmi->name && *dmi->name; dmi++) {
-		if (!strcmp(dmi->name, name) && dmi->func == func)
+		if (!strcmp(dmi->name, name) && dmi->func == func) {
+			/* If asset tag is provided, match on it as well. */
+			if (dmi->asset_tag && strcmp(dmi->asset_tag, asset_tag))
+				continue;
 			return dmi->phy_addr;
+		}
 	}
 
 	return -ENODEV;
 }
 
-static void stmmac_default_data(struct plat_stmmacenet_data *plat)
+static void common_default_data(struct plat_stmmacenet_data *plat)
 {
-	plat->bus_id = 1;
-	plat->phy_addr = 0;
-	plat->interface = PHY_INTERFACE_MODE_GMII;
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
 	plat->has_gmac = 1;
 	plat->force_sf_dma_mode = 1;
@@ -76,10 +79,6 @@ static void stmmac_default_data(struct p
 	plat->mdio_bus_data->phy_reset = NULL;
 	plat->mdio_bus_data->phy_mask = 0;
 
-	plat->dma_cfg->pbl = 32;
-	plat->dma_cfg->pblx8 = true;
-	/* TODO: AXI */
-
 	/* Set default value for multicast hash bins */
 	plat->multicast_filter_bins = HASH_TABLE_SIZE;
 
@@ -88,6 +87,31 @@ static void stmmac_default_data(struct p
 
 	/* Set the maxmtu to a default of JUMBO_LEN */
 	plat->maxmtu = JUMBO_LEN;
+
+	/* Set default number of RX and TX queues to use */
+	plat->tx_queues_to_use = 1;
+	plat->rx_queues_to_use = 1;
+
+	/* Disable Priority config by default */
+	plat->tx_queues_cfg[0].use_prio = false;
+	plat->rx_queues_cfg[0].use_prio = false;
+
+	/* Disable RX queues routing by default */
+	plat->rx_queues_cfg[0].pkt_route = 0x0;
+}
+
+static void stmmac_default_data(struct plat_stmmacenet_data *plat)
+{
+	/* Set common default data first */
+	common_default_data(plat);
+
+	plat->bus_id = 1;
+	plat->phy_addr = 0;
+	plat->interface = PHY_INTERFACE_MODE_GMII;
+
+	plat->dma_cfg->pbl = 32;
+	plat->dma_cfg->pblx8 = true;
+	/* TODO: AXI */
 }
 
 static int quark_default_data(struct plat_stmmacenet_data *plat,
@@ -96,6 +120,9 @@ static int quark_default_data(struct pla
 	struct pci_dev *pdev = info->pdev;
 	int ret;
 
+	/* Set common default data first */
+	common_default_data(plat);
+
 	/*
 	 * Refuse to load the driver and register net device if MAC controller
 	 * does not connect to any PHY interface.
@@ -107,27 +134,12 @@ static int quark_default_data(struct pla
 	plat->bus_id = PCI_DEVID(pdev->bus->number, pdev->devfn);
 	plat->phy_addr = ret;
 	plat->interface = PHY_INTERFACE_MODE_RMII;
-	plat->clk_csr = 2;
-	plat->has_gmac = 1;
-	plat->force_sf_dma_mode = 1;
-
-	plat->mdio_bus_data->phy_reset = NULL;
-	plat->mdio_bus_data->phy_mask = 0;
 
 	plat->dma_cfg->pbl = 16;
 	plat->dma_cfg->pblx8 = true;
 	plat->dma_cfg->fixed_burst = 1;
 	/* AXI (TODO) */
 
-	/* Set default value for multicast hash bins */
-	plat->multicast_filter_bins = HASH_TABLE_SIZE;
-
-	/* Set default value for unicast filter entries */
-	plat->unicast_filter_entries = 1;
-
-	/* Set the maxmtu to a default of JUMBO_LEN */
-	plat->maxmtu = JUMBO_LEN;
-
 	return 0;
 }
 
@@ -142,6 +154,24 @@ static struct stmmac_pci_dmi_data quark_
 		.func = 6,
 		.phy_addr = 1,
 	},
+	{
+		.name = "SIMATIC IOT2000",
+		.asset_tag = "6ES7647-0AA00-0YA2",
+		.func = 6,
+		.phy_addr = 1,
+	},
+	{
+		.name = "SIMATIC IOT2000",
+		.asset_tag = "6ES7647-0AA00-1YA2",
+		.func = 6,
+		.phy_addr = 1,
+	},
+	{
+		.name = "SIMATIC IOT2000",
+		.asset_tag = "6ES7647-0AA00-1YA2",
+		.func = 7,
+		.phy_addr = 1,
+	},
 	{}
 };
 
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -108,7 +108,7 @@ static struct stmmac_axi *stmmac_axi_set
 	if (!np)
 		return NULL;
 
-	axi = kzalloc(sizeof(*axi), GFP_KERNEL);
+	axi = devm_kzalloc(&pdev->dev, sizeof(*axi), GFP_KERNEL);
 	if (!axi) {
 		of_node_put(np);
 		return ERR_PTR(-ENOMEM);
@@ -132,6 +132,155 @@ static struct stmmac_axi *stmmac_axi_set
 }
 
 /**
+ * stmmac_mtl_setup - parse DT parameters for multiple queues configuration
+ * @pdev: platform device
+ */
+static void stmmac_mtl_setup(struct platform_device *pdev,
+			     struct plat_stmmacenet_data *plat)
+{
+	struct device_node *q_node;
+	struct device_node *rx_node;
+	struct device_node *tx_node;
+	u8 queue = 0;
+
+	/* For backwards-compatibility with device trees that don't have any
+	 * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back
+	 * to one RX and TX queues each.
+	 */
+	plat->rx_queues_to_use = 1;
+	plat->tx_queues_to_use = 1;
+
+	rx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-rx-config", 0);
+	if (!rx_node)
+		return;
+
+	tx_node = of_parse_phandle(pdev->dev.of_node, "snps,mtl-tx-config", 0);
+	if (!tx_node) {
+		of_node_put(rx_node);
+		return;
+	}
+
+	/* Processing RX queues common config */
+	if (of_property_read_u8(rx_node, "snps,rx-queues-to-use",
+				&plat->rx_queues_to_use))
+		plat->rx_queues_to_use = 1;
+
+	if (of_property_read_bool(rx_node, "snps,rx-sched-sp"))
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+	else if (of_property_read_bool(rx_node, "snps,rx-sched-wsp"))
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_WSP;
+	else
+		plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP;
+
+	/* Processing individual RX queue config */
+	for_each_child_of_node(rx_node, q_node) {
+		if (queue >= plat->rx_queues_to_use)
+			break;
+
+		if (of_property_read_bool(q_node, "snps,dcb-algorithm"))
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		else if (of_property_read_bool(q_node, "snps,avb-algorithm"))
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+		else
+			plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+
+		if (of_property_read_u8(q_node, "snps,map-to-dma-channel",
+					&plat->rx_queues_cfg[queue].chan))
+			plat->rx_queues_cfg[queue].chan = queue;
+		/* TODO: Dynamic mapping to be included in the future */
+
+		if (of_property_read_u32(q_node, "snps,priority",
+					&plat->rx_queues_cfg[queue].prio)) {
+			plat->rx_queues_cfg[queue].prio = 0;
+			plat->rx_queues_cfg[queue].use_prio = false;
+		} else {
+			plat->rx_queues_cfg[queue].use_prio = true;
+		}
+
+		/* RX queue specific packet type routing */
+		if (of_property_read_bool(q_node, "snps,route-avcp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_AVCPQ;
+		else if (of_property_read_bool(q_node, "snps,route-ptp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_PTPQ;
+		else if (of_property_read_bool(q_node, "snps,route-dcbcp"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_DCBCPQ;
+		else if (of_property_read_bool(q_node, "snps,route-up"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ;
+		else if (of_property_read_bool(q_node, "snps,route-multi-broad"))
+			plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ;
+		else
+			plat->rx_queues_cfg[queue].pkt_route = 0x0;
+
+		queue++;
+	}
+
+	/* Processing TX queues common config */
+	if (of_property_read_u8(tx_node, "snps,tx-queues-to-use",
+				&plat->tx_queues_to_use))
+		plat->tx_queues_to_use = 1;
+
+	if (of_property_read_bool(tx_node, "snps,tx-sched-wrr"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-wfq"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WFQ;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-dwrr"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_DWRR;
+	else if (of_property_read_bool(tx_node, "snps,tx-sched-sp"))
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+	else
+		plat->tx_sched_algorithm = MTL_TX_ALGORITHM_SP;
+
+	queue = 0;
+
+	/* Processing individual TX queue config */
+	for_each_child_of_node(tx_node, q_node) {
+		if (queue >= plat->tx_queues_to_use)
+			break;
+
+		if (of_property_read_u8(q_node, "snps,weight",
+					&plat->tx_queues_cfg[queue].weight))
+			plat->tx_queues_cfg[queue].weight = 0x10 + queue;
+
+		if (of_property_read_bool(q_node, "snps,dcb-algorithm")) {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		} else if (of_property_read_bool(q_node,
+						 "snps,avb-algorithm")) {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+
+			/* Credit Base Shaper parameters used by AVB */
+			if (of_property_read_u32(q_node, "snps,send_slope",
+				&plat->tx_queues_cfg[queue].send_slope))
+				plat->tx_queues_cfg[queue].send_slope = 0x0;
+			if (of_property_read_u32(q_node, "snps,idle_slope",
+				&plat->tx_queues_cfg[queue].idle_slope))
+				plat->tx_queues_cfg[queue].idle_slope = 0x0;
+			if (of_property_read_u32(q_node, "snps,high_credit",
+				&plat->tx_queues_cfg[queue].high_credit))
+				plat->tx_queues_cfg[queue].high_credit = 0x0;
+			if (of_property_read_u32(q_node, "snps,low_credit",
+				&plat->tx_queues_cfg[queue].low_credit))
+				plat->tx_queues_cfg[queue].low_credit = 0x0;
+		} else {
+			plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB;
+		}
+
+		if (of_property_read_u32(q_node, "snps,priority",
+					&plat->tx_queues_cfg[queue].prio)) {
+			plat->tx_queues_cfg[queue].prio = 0;
+			plat->tx_queues_cfg[queue].use_prio = false;
+		} else {
+			plat->tx_queues_cfg[queue].use_prio = true;
+		}
+
+		queue++;
+	}
+
+	of_node_put(rx_node);
+	of_node_put(tx_node);
+	of_node_put(q_node);
+}
+
+/**
  * stmmac_dt_phy - parse device-tree driver parameters to allocate PHY resources
  * @plat: driver data platform structure
  * @np: device tree node
@@ -340,6 +489,8 @@ stmmac_probe_config_dt(struct platform_d
 
 	plat->axi = stmmac_axi_setup(pdev);
 
+	stmmac_mtl_setup(pdev, plat);
+
 	/* clock setup */
 	plat->stmmac_clk = devm_clk_get(&pdev->dev,
 					STMMAC_RESOURCE_NAME);
@@ -359,13 +510,12 @@ stmmac_probe_config_dt(struct platform_d
 	clk_prepare_enable(plat->pclk);
 
 	/* Fall-back to main clock in case of no PTP ref is passed */
-	plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "clk_ptp_ref");
+	plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref");
 	if (IS_ERR(plat->clk_ptp_ref)) {
 		plat->clk_ptp_rate = clk_get_rate(plat->stmmac_clk);
 		plat->clk_ptp_ref = NULL;
 		dev_warn(&pdev->dev, "PTP uses main clock\n");
 	} else {
-		clk_prepare_enable(plat->clk_ptp_ref);
 		plat->clk_ptp_rate = clk_get_rate(plat->clk_ptp_ref);
 		dev_dbg(&pdev->dev, "PTP rate %d\n", plat->clk_ptp_rate);
 	}
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -28,6 +28,9 @@
 
 #include <linux/platform_device.h>
 
+#define MTL_MAX_RX_QUEUES	8
+#define MTL_MAX_TX_QUEUES	8
+
 #define STMMAC_RX_COE_NONE	0
 #define STMMAC_RX_COE_TYPE1	1
 #define STMMAC_RX_COE_TYPE2	2
@@ -44,6 +47,18 @@
 #define	STMMAC_CSR_150_250M	0x4	/* MDC = clk_scr_i/102 */
 #define	STMMAC_CSR_250_300M	0x5	/* MDC = clk_scr_i/122 */
 
+/* MTL algorithms identifiers */
+#define MTL_TX_ALGORITHM_WRR	0x0
+#define MTL_TX_ALGORITHM_WFQ	0x1
+#define MTL_TX_ALGORITHM_DWRR	0x2
+#define MTL_TX_ALGORITHM_SP	0x3
+#define MTL_RX_ALGORITHM_SP	0x4
+#define MTL_RX_ALGORITHM_WSP	0x5
+
+/* RX/TX Queue Mode */
+#define MTL_QUEUE_AVB		0x0
+#define MTL_QUEUE_DCB		0x1
+
 /* The MDC clock could be set higher than the IEEE 802.3
  * specified frequency limit 0f 2.5 MHz, by programming a clock divider
  * of value different than the above defined values. The resultant MDIO
@@ -109,6 +124,26 @@ struct stmmac_axi {
 	bool axi_rb;
 };
 
+struct stmmac_rxq_cfg {
+	u8 mode_to_use;
+	u8 chan;
+	u8 pkt_route;
+	bool use_prio;
+	u32 prio;
+};
+
+struct stmmac_txq_cfg {
+	u8 weight;
+	u8 mode_to_use;
+	/* Credit Base Shaper parameters */
+	u32 send_slope;
+	u32 idle_slope;
+	u32 high_credit;
+	u32 low_credit;
+	bool use_prio;
+	u32 prio;
+};
+
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
@@ -133,6 +168,12 @@ struct plat_stmmacenet_data {
 	int unicast_filter_entries;
 	int tx_fifo_size;
 	int rx_fifo_size;
+	u8 rx_queues_to_use;
+	u8 tx_queues_to_use;
+	u8 rx_sched_algorithm;
+	u8 tx_sched_algorithm;
+	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
+	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
 	void (*fix_mac_speed)(void *priv, unsigned int speed);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);