net: ethernet: mediatek: modify to use the PDMA instead of the QDMA for Ethernet RX

Because the PDMA has richer features than the QDMA for Ethernet RX
(such as multiple RX rings, HW LRO, etc.),
the patch modifies to use the PDMA to handle Ethernet RX.
Acked-by: John Crispin <john@phrozen.org>
Signed-off-by: Nelson Chang <nelson.chang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mediatek/mtk_eth_soc.c

@@ -342,25 +342,27 @@ static void mtk_mdio_cleanup(struct mtk_eth *eth)
 	mdiobus_free(eth->mii_bus);
 }
 
-static inline void mtk_irq_disable(struct mtk_eth *eth, u32 mask)
+static inline void mtk_irq_disable(struct mtk_eth *eth,
+				   unsigned reg, u32 mask)
 {
 	unsigned long flags;
 	u32 val;
 
 	spin_lock_irqsave(&eth->irq_lock, flags);
-	val = mtk_r32(eth, MTK_QDMA_INT_MASK);
-	mtk_w32(eth, val & ~mask, MTK_QDMA_INT_MASK);
+	val = mtk_r32(eth, reg);
+	mtk_w32(eth, val & ~mask, reg);
 	spin_unlock_irqrestore(&eth->irq_lock, flags);
 }
 
-static inline void mtk_irq_enable(struct mtk_eth *eth, u32 mask)
+static inline void mtk_irq_enable(struct mtk_eth *eth,
+				  unsigned reg, u32 mask)
 {
 	unsigned long flags;
 	u32 val;
 
 	spin_lock_irqsave(&eth->irq_lock, flags);
-	val = mtk_r32(eth, MTK_QDMA_INT_MASK);
-	mtk_w32(eth, val | mask, MTK_QDMA_INT_MASK);
+	val = mtk_r32(eth, reg);
+	mtk_w32(eth, val | mask, reg);
 	spin_unlock_irqrestore(&eth->irq_lock, flags);
 }
 
@@ -897,12 +899,12 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		 * we continue
 		 */
 		wmb();
-		mtk_w32(eth, ring->calc_idx, MTK_QRX_CRX_IDX0);
+		mtk_w32(eth, ring->calc_idx, MTK_PRX_CRX_IDX0);
 		done++;
 	}
 
 	if (done < budget)
-		mtk_w32(eth, MTK_RX_DONE_INT, MTK_QMTK_INT_STATUS);
+		mtk_w32(eth, MTK_RX_DONE_INT, MTK_PDMA_INT_STATUS);
 
 	return done;
 }
@@ -1012,7 +1014,7 @@ static int mtk_napi_tx(struct napi_struct *napi, int budget)
 		return budget;
 
 	napi_complete(napi);
-	mtk_irq_enable(eth, MTK_TX_DONE_INT);
+	mtk_irq_enable(eth, MTK_QDMA_INT_MASK, MTK_TX_DONE_INT);
 
 	return tx_done;
 }
@@ -1024,12 +1026,12 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget)
 	int rx_done = 0;
 
 	mtk_handle_status_irq(eth);
-	mtk_w32(eth, MTK_RX_DONE_INT, MTK_QMTK_INT_STATUS);
+	mtk_w32(eth, MTK_RX_DONE_INT, MTK_PDMA_INT_STATUS);
 	rx_done = mtk_poll_rx(napi, budget, eth);
 
 	if (unlikely(netif_msg_intr(eth))) {
-		status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
-		mask = mtk_r32(eth, MTK_QDMA_INT_MASK);
+		status = mtk_r32(eth, MTK_PDMA_INT_STATUS);
+		mask = mtk_r32(eth, MTK_PDMA_INT_MASK);
 		dev_info(eth->dev,
 			 "done rx %d, intr 0x%08x/0x%x\n",
 			 rx_done, status, mask);
@@ -1038,12 +1040,12 @@ static int mtk_napi_rx(struct napi_struct *napi, int budget)
 	if (rx_done == budget)
 		return budget;
 
-	status = mtk_r32(eth, MTK_QMTK_INT_STATUS);
+	status = mtk_r32(eth, MTK_PDMA_INT_STATUS);
 	if (status & MTK_RX_DONE_INT)
 		return budget;
 
 	napi_complete(napi);
-	mtk_irq_enable(eth, MTK_RX_DONE_INT);
+	mtk_irq_enable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 
 	return rx_done;
 }
@@ -1092,6 +1094,7 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	mtk_w32(eth,
 		ring->phys + ((MTK_DMA_SIZE - 1) * sz),
 		MTK_QTX_DRX_PTR);
+	mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0));
 
 	return 0;
 
@@ -1162,11 +1165,10 @@ static int mtk_rx_alloc(struct mtk_eth *eth)
 	 */
 	wmb();
 
-	mtk_w32(eth, eth->rx_ring.phys, MTK_QRX_BASE_PTR0);
-	mtk_w32(eth, MTK_DMA_SIZE, MTK_QRX_MAX_CNT0);
-	mtk_w32(eth, eth->rx_ring.calc_idx, MTK_QRX_CRX_IDX0);
-	mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_QDMA_RST_IDX);
-	mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0));
+	mtk_w32(eth, eth->rx_ring.phys, MTK_PRX_BASE_PTR0);
+	mtk_w32(eth, MTK_DMA_SIZE, MTK_PRX_MAX_CNT0);
+	mtk_w32(eth, eth->rx_ring.calc_idx, MTK_PRX_CRX_IDX0);
+	mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_PDMA_RST_IDX);
 
 	return 0;
 }
@@ -1285,7 +1287,7 @@ static irqreturn_t mtk_handle_irq_rx(int irq, void *_eth)
 
 	if (likely(napi_schedule_prep(&eth->rx_napi))) {
 		__napi_schedule(&eth->rx_napi);
-		mtk_irq_disable(eth, MTK_RX_DONE_INT);
+		mtk_irq_disable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 	}
 
 	return IRQ_HANDLED;
@@ -1297,7 +1299,7 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth)
 
 	if (likely(napi_schedule_prep(&eth->tx_napi))) {
 		__napi_schedule(&eth->tx_napi);
-		mtk_irq_disable(eth, MTK_TX_DONE_INT);
+		mtk_irq_disable(eth, MTK_QDMA_INT_MASK, MTK_TX_DONE_INT);
 	}
 
 	return IRQ_HANDLED;
@@ -1308,11 +1310,12 @@ static void mtk_poll_controller(struct net_device *dev)
 {
 	struct mtk_mac *mac = netdev_priv(dev);
 	struct mtk_eth *eth = mac->hw;
-	u32 int_mask = MTK_TX_DONE_INT | MTK_RX_DONE_INT;
 
-	mtk_irq_disable(eth, int_mask);
+	mtk_irq_disable(eth, MTK_QDMA_INT_MASK, MTK_TX_DONE_INT);
+	mtk_irq_disable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 	mtk_handle_irq_rx(eth->irq[2], dev);
-	mtk_irq_enable(eth, int_mask);
+	mtk_irq_enable(eth, MTK_QDMA_INT_MASK, MTK_TX_DONE_INT);
+	mtk_irq_enable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 }
 #endif
 
@@ -1327,11 +1330,15 @@ static int mtk_start_dma(struct mtk_eth *eth)
 	}
 
 	mtk_w32(eth,
-		MTK_TX_WB_DDONE | MTK_RX_DMA_EN | MTK_TX_DMA_EN |
-		MTK_RX_2B_OFFSET | MTK_DMA_SIZE_16DWORDS |
-		MTK_RX_BT_32DWORDS | MTK_NDP_CO_PRO,
+		MTK_TX_WB_DDONE | MTK_TX_DMA_EN |
+		MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO,
 		MTK_QDMA_GLO_CFG);
 
+	mtk_w32(eth,
+		MTK_RX_DMA_EN | MTK_RX_2B_OFFSET |
+		MTK_RX_BT_32DWORDS | MTK_MULTI_EN,
+		MTK_PDMA_GLO_CFG);
+
 	return 0;
 }
 
@@ -1349,7 +1356,8 @@ static int mtk_open(struct net_device *dev)
 
 		napi_enable(&eth->tx_napi);
 		napi_enable(&eth->rx_napi);
-		mtk_irq_enable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+		mtk_irq_enable(eth, MTK_QDMA_INT_MASK, MTK_TX_DONE_INT);
+		mtk_irq_enable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 	}
 	atomic_inc(&eth->dma_refcnt);
 
@@ -1394,7 +1402,8 @@ static int mtk_stop(struct net_device *dev)
 	if (!atomic_dec_and_test(&eth->dma_refcnt))
 		return 0;
 
-	mtk_irq_disable(eth, MTK_TX_DONE_INT | MTK_RX_DONE_INT);
+	mtk_irq_disable(eth, MTK_QDMA_INT_MASK, MTK_TX_DONE_INT);
+	mtk_irq_disable(eth, MTK_PDMA_INT_MASK, MTK_RX_DONE_INT);
 	napi_disable(&eth->tx_napi);
 	napi_disable(&eth->rx_napi);
 
@@ -1448,7 +1457,9 @@ static int __init mtk_hw_init(struct mtk_eth *eth)
 
 	/* disable delay and normal interrupt */
 	mtk_w32(eth, 0, MTK_QDMA_DELAY_INT);
-	mtk_irq_disable(eth, ~0);
+	mtk_w32(eth, 0, MTK_PDMA_DELAY_INT);
+	mtk_irq_disable(eth, MTK_QDMA_INT_MASK, ~0);
+	mtk_irq_disable(eth, MTK_PDMA_INT_MASK, ~0);
 	mtk_w32(eth, RST_GL_PSE, MTK_RST_GL);
 	mtk_w32(eth, 0, MTK_RST_GL);
 
@@ -1504,7 +1515,8 @@ static void mtk_uninit(struct net_device *dev)
 
 	phy_disconnect(mac->phy_dev);
 	mtk_mdio_cleanup(eth);
-	mtk_irq_disable(eth, ~0);
+	mtk_irq_disable(eth, MTK_QDMA_INT_MASK, ~0);
+	mtk_irq_disable(eth, MTK_PDMA_INT_MASK, ~0);
 	free_irq(eth->irq[1], dev);
 	free_irq(eth->irq[2], dev);
 }
@@ -1683,7 +1695,7 @@ static void mtk_get_ethtool_stats(struct net_device *dev,
 	}
 
 	do {
-		data_src = (u64*)hwstats;
+		data_src = (u64 *)hwstats;
 		data_dst = data;
 		start = u64_stats_fetch_begin_irq(&hwstats->syncp);
 

drivers/net/ethernet/mediatek/mtk_eth_soc.h

@@ -68,6 +68,32 @@
 /* Unicast Filter MAC Address Register - High */
 #define MTK_GDMA_MAC_ADRH(x)	(0x50C + (x * 0x1000))
 
+/* PDMA RX Base Pointer Register */
+#define MTK_PRX_BASE_PTR0	0x900
+
+/* PDMA RX Maximum Count Register */
+#define MTK_PRX_MAX_CNT0	0x904
+
+/* PDMA RX CPU Pointer Register */
+#define MTK_PRX_CRX_IDX0	0x908
+
+/* PDMA Global Configuration Register */
+#define MTK_PDMA_GLO_CFG	0xa04
+#define MTK_MULTI_EN		BIT(10)
+
+/* PDMA Reset Index Register */
+#define MTK_PDMA_RST_IDX	0xa08
+#define MTK_PST_DRX_IDX0	BIT(16)
+
+/* PDMA Delay Interrupt Register */
+#define MTK_PDMA_DELAY_INT	0xa0c
+
+/* PDMA Interrupt Status Register */
+#define MTK_PDMA_INT_STATUS	0xa20
+
+/* PDMA Interrupt Mask Register */
+#define MTK_PDMA_INT_MASK	0xa28
+
 /* PDMA Interrupt grouping registers */
 #define MTK_PDMA_INT_GRP1	0xa50
 #define MTK_PDMA_INT_GRP2	0xa54
@@ -119,13 +145,16 @@
 
 /* QDMA Interrupt Status Register */
 #define MTK_QMTK_INT_STATUS	0x1A18
+#define MTK_RX_DONE_INT3	BIT(19)
+#define MTK_RX_DONE_INT2	BIT(18)
 #define MTK_RX_DONE_INT1	BIT(17)
 #define MTK_RX_DONE_INT0	BIT(16)
 #define MTK_TX_DONE_INT3	BIT(3)
 #define MTK_TX_DONE_INT2	BIT(2)
 #define MTK_TX_DONE_INT1	BIT(1)
 #define MTK_TX_DONE_INT0	BIT(0)
-#define MTK_RX_DONE_INT		(MTK_RX_DONE_INT0 | MTK_RX_DONE_INT1)
+#define MTK_RX_DONE_INT		(MTK_RX_DONE_INT0 | MTK_RX_DONE_INT1 | \
+				 MTK_RX_DONE_INT2 | MTK_RX_DONE_INT3)
 #define MTK_TX_DONE_INT		(MTK_TX_DONE_INT0 | MTK_TX_DONE_INT1 | \
 				 MTK_TX_DONE_INT2 | MTK_TX_DONE_INT3)