Merge branch 'stmmac-multiqueue-mac-prep'

Joao Pinto says:

====================
prepare mac operations for multiple queues

As agreed with David Miller, this patch-set is the first of 3 to enable
multiple queues in stmmac.

This first one concentrates on mac operations adding functionalities as:
a) Configuration through DT
b) RX and TX scheduling algorithms programming
b) TX queues weight programming (essential in weightes algorithms)
c) RX enable as DCB or AVB (preparing for future AVB support)
d) Mapping RX queue to DMA channel
e) IRQ treatment prepared for multiple queues
f) Debug dump prepared for multiple queues
g) CBS configuration

In v3 patch-set version I included a new patch to enable CBS configuration
(Patch 9).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/devicetree/bindings/net/stmmac.txt

@@ -72,7 +72,35 @@ 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
+- 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
+		- 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
 Examples:
 
 	stmmac_axi_setup: stmmac-axi-config {
@@ -81,6 +109,32 @@ 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>;
+		};
+	};
+
+	mtl_tx_setup: tx-queues-config {
+		snps,tx-queues-to-use = <2>;
+		snps,tx-sched-wrr;
+		queue0 {
+			snps,weight = <0x10>;
+			snps,dcb-algorithm;
+		};
+
+		queue1 {
+			snps,avb-algorithm;
+			snps,send_slope = <0x1000>;
+			snps,idle_slope = <0x1000>;
+			snps,high_credit = <0x3E800>;
+			snps,low_credit = <0xFFC18000>;
+		};
+	};
+
 	gmac0: ethernet@e0800000 {
 		compatible = "st,spear600-gmac";
 		reg = <0xe0800000 0x8000>;
@@ -104,4 +158,6 @@ Examples:
 			phy1: ethernet-phy@0 {
 			};
 		};
+		snps,mtl-rx-config = <&mtl_rx_setup>;
+		snps,mtl-tx-config = <&mtl_tx_setup>;
 	};

drivers/net/ethernet/stmicro/stmmac/common.h

@@ -457,17 +457,32 @@ struct stmmac_ops {
 	/* 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);
+	/* 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 */
@@ -480,7 +495,8 @@ 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);

drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c

@@ -216,7 +216,8 @@ static void dwmac1000_set_filter(struct mac_device_info *hw,
 
 
 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 __iomem *ioaddr, struct rgmii_adv *adv)
 	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);
 

drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c

@@ -131,7 +131,8 @@ static void dwmac100_set_filter(struct mac_device_info *hw,
 }
 
 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;

drivers/net/ethernet/stmicro/stmmac/dwmac4.h

@@ -164,8 +164,25 @@ 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
@@ -216,6 +233,46 @@ 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)

drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c

@@ -59,17 +59,143 @@ static void dwmac4_core_init(struct mac_device_info *hw, int mtu)
 	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);
+	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_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 +377,12 @@ static void dwmac4_set_filter(struct mac_device_info *hw,
 }
 
 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 +392,18 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
 	}
 	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 +457,34 @@ static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 	}
 }
 
+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 +503,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		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);
@@ -369,12 +510,14 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 	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++;
@@ -396,8 +539,10 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 		}
 		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)
@@ -427,6 +572,7 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x)
 		}
 		if (value & MTL_DEBUG_RWCSTS)
 			x->mtl_rx_fifo_ctrl_active++;
+	}
 
 	/* GMAC debug */
 	value = readl(ioaddr + GMAC_DEBUG);
@@ -457,8 +603,14 @@ static const struct stmmac_ops dwmac4_ops = {
 	.core_init = dwmac4_core_init,
 	.rx_ipc = dwmac4_rx_ipc_enable,
 	.rx_queue_enable = dwmac4_rx_queue_enable,
+	.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,

drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c

@@ -481,6 +481,7 @@ stmmac_set_pauseparam(struct net_device *netdev,
 		      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 *netdev,
 	}
 
 	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(struct net_device *dev,
 				 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(struct net_device *dev,
 		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;

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -672,6 +672,19 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
 	stmmac_ptp_unregister(priv);
 }
 
+/**
+ *  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
@@ -687,7 +700,6 @@ static void stmmac_adjust_link(struct net_device *dev)
 	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;
@@ -709,8 +721,7 @@ static void stmmac_adjust_link(struct net_device *dev)
 		}
 		/* 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;
@@ -1256,19 +1267,14 @@ static void free_dma_desc_resources(struct stmmac_priv *priv)
  */
 static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv)
 {
-	int rx_count = priv->dma_cap.number_rx_queues;
-	int queue = 0;
+	u32 rx_queues_count = priv->plat->rx_queues_to_use;
+	int queue;
+	u8 mode;
 
-	/* If GMAC does not have multiple queues, then this is not necessary*/
-	if (rx_count == 1)
-		return;
-
-	/**
-	 *  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 (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);
+	}
 }
 
 /**
@@ -1647,6 +1653,101 @@ static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
 	add_timer(&priv->txtimer);
 }
 
+/**
+ *  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;
+
+	for (queue = 0; 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_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 (rx_queues_count > 1 && priv->hw->mac->map_mtl_to_dma)
+		stmmac_rx_queue_dma_chan_map(priv);
+
+	/* Enable MAC RX Queues */
+	if (rx_queues_count > 1 && priv->hw->mac->rx_queue_enable)
+		stmmac_mac_enable_rx_queues(priv);
+}
+
 /**
  * stmmac_hw_setup - setup mac in a usable state.
  *  @dev : pointer to the device structure.
@@ -1691,9 +1792,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 	/* 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) {
@@ -2829,6 +2930,11 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
 		int status = priv->hw->mac->host_irq_status(priv->hw,
 							    &priv->xstats);
+
+		if (priv->synopsys_id >= DWMAC_CORE_4_00)
+			status |= priv->hw->mac->host_mtl_irq_status(priv->hw,
+								STMMAC_CHAN0);
+
 		if (unlikely(status)) {
 			/* For LPI we need to save the tx status */
 			if (status & CORE_IRQ_TX_PATH_IN_LPI_MODE)

drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c

@@ -131,6 +131,118 @@ static struct stmmac_axi *stmmac_axi_setup(struct platform_device *pdev)
 	return axi;
 }
 
+/**
+ * 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;
+
+	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 */
+
+		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;
+		}
+
+		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
@@ -340,6 +452,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 
 	plat->axi = stmmac_axi_setup(pdev);
 
+	stmmac_mtl_setup(pdev, plat);
+
 	/* clock setup */
 	plat->stmmac_clk = devm_clk_get(&pdev->dev,
 					STMMAC_RESOURCE_NAME);

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_DCB		0x0
+#define MTL_QUEUE_AVB		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 +124,21 @@ struct stmmac_axi {
 	bool axi_rb;
 };
 
+struct stmmac_rxq_cfg {
+	u8 mode_to_use;
+	u8 chan;
+};
+
+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;
+};
+
 struct plat_stmmacenet_data {
 	int bus_id;
 	int phy_addr;
@@ -133,6 +163,12 @@ 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);