Merge branch 'net-macb-various-fixes'

Théo Lebrun says:

====================
net: macb: various fixes

Fix a few disparate topics in MACB:

[PATCH net v6 1/5] dt-bindings: net: cdns,macb: allow tsu_clk without tx_clk
[PATCH net v6 2/5] net: macb: remove illusion about TBQPH/RBQPH being per-queue
[PATCH net v6 3/5] net: macb: move ring size computation to functions
[PATCH net v6 4/5] net: macb: single dma_alloc_coherent() for DMA descriptors
[PATCH net v6 5/5] net: macb: avoid dealing with endianness in macb_set_hwaddr()

Patch 3/5 is a rework that simplifies patch 4/5. It is the only non-fix.

Pending series on MACB are: (1) many cleanup patches, (2) patches for
EyeQ5 support and (3) XDP work. Those will be sent targeting
net-next/main once this series lands there, aiming to minimise merge
conflicts. Old version of(1) and (2) are visible in the V2 revision [0].

[0]: https://lore.kernel.org/lkml/[email protected]/
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

Documentation/devicetree/bindings/net/cdns,macb.yaml

@@ -85,7 +85,7 @@ properties:
     items:
       - enum: [ ether_clk, hclk, pclk ]
       - enum: [ hclk, pclk ]
-      - const: tx_clk
+      - enum: [ tx_clk, tsu_clk ]
       - enum: [ rx_clk, tsu_clk ]
       - const: tsu_clk
 

drivers/net/ethernet/cadence/macb.h

@@ -213,10 +213,8 @@
 
 #define GEM_ISR(hw_q)		(0x0400 + ((hw_q) << 2))
 #define GEM_TBQP(hw_q)		(0x0440 + ((hw_q) << 2))
-#define GEM_TBQPH(hw_q)		(0x04C8)
 #define GEM_RBQP(hw_q)		(0x0480 + ((hw_q) << 2))
 #define GEM_RBQS(hw_q)		(0x04A0 + ((hw_q) << 2))
-#define GEM_RBQPH(hw_q)		(0x04D4)
 #define GEM_IER(hw_q)		(0x0600 + ((hw_q) << 2))
 #define GEM_IDR(hw_q)		(0x0620 + ((hw_q) << 2))
 #define GEM_IMR(hw_q)		(0x0640 + ((hw_q) << 2))
@@ -1214,10 +1212,8 @@ struct macb_queue {
 	unsigned int		IDR;
 	unsigned int		IMR;
 	unsigned int		TBQP;
-	unsigned int		TBQPH;
 	unsigned int		RBQS;
 	unsigned int		RBQP;
-	unsigned int		RBQPH;
 
 	/* Lock to protect tx_head and tx_tail */
 	spinlock_t		tx_ptr_lock;

drivers/net/ethernet/cadence/macb_main.c

@@ -51,14 +51,10 @@ struct sifive_fu540_macb_mgmt {
 #define DEFAULT_RX_RING_SIZE	512 /* must be power of 2 */
 #define MIN_RX_RING_SIZE	64
 #define MAX_RX_RING_SIZE	8192
-#define RX_RING_BYTES(bp)	(macb_dma_desc_get_size(bp)	\
-				 * (bp)->rx_ring_size)
 
 #define DEFAULT_TX_RING_SIZE	512 /* must be power of 2 */
 #define MIN_TX_RING_SIZE	64
 #define MAX_TX_RING_SIZE	4096
-#define TX_RING_BYTES(bp)	(macb_dma_desc_get_size(bp)	\
-				 * (bp)->tx_ring_size)
 
 /* level of occupied TX descriptors under which we wake up TX process */
 #define MACB_TX_WAKEUP_THRESH(bp)	(3 * (bp)->tx_ring_size / 4)
@@ -278,9 +274,9 @@ static void macb_set_hwaddr(struct macb *bp)
 	u32 bottom;
 	u16 top;
 
-	bottom = cpu_to_le32(*((u32 *)bp->dev->dev_addr));
+	bottom = get_unaligned_le32(bp->dev->dev_addr);
 	macb_or_gem_writel(bp, SA1B, bottom);
-	top = cpu_to_le16(*((u16 *)(bp->dev->dev_addr + 4)));
+	top = get_unaligned_le16(bp->dev->dev_addr + 4);
 	macb_or_gem_writel(bp, SA1T, top);
 
 	if (gem_has_ptp(bp)) {
@@ -495,19 +491,19 @@ static void macb_init_buffers(struct macb *bp)
 	struct macb_queue *queue;
 	unsigned int q;
 
-	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		queue_writel(queue, RBQP, lower_32_bits(queue->rx_ring_dma));
 #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		if (bp->hw_dma_cap & HW_DMA_CAP_64B)
-			queue_writel(queue, RBQPH,
-				     upper_32_bits(queue->rx_ring_dma));
+	/* Single register for all queues' high 32 bits. */
+	if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
+		macb_writel(bp, RBQPH,
+			    upper_32_bits(bp->queues[0].rx_ring_dma));
+		macb_writel(bp, TBQPH,
+			    upper_32_bits(bp->queues[0].tx_ring_dma));
+	}
 #endif
+
+	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
+		queue_writel(queue, RBQP, lower_32_bits(queue->rx_ring_dma));
 		queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-		if (bp->hw_dma_cap & HW_DMA_CAP_64B)
-			queue_writel(queue, TBQPH,
-				     upper_32_bits(queue->tx_ring_dma));
-#endif
 	}
 }
 
@@ -1166,10 +1162,6 @@ static void macb_tx_error_task(struct work_struct *work)
 
 	/* Reinitialize the TX desc queue */
 	queue_writel(queue, TBQP, lower_32_bits(queue->tx_ring_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-	if (bp->hw_dma_cap & HW_DMA_CAP_64B)
-		queue_writel(queue, TBQPH, upper_32_bits(queue->tx_ring_dma));
-#endif
 	/* Make TX ring reflect state of hardware */
 	queue->tx_head = 0;
 	queue->tx_tail = 0;
@@ -2474,35 +2466,42 @@ static void macb_free_rx_buffers(struct macb *bp)
 	}
 }
 
+static unsigned int macb_tx_ring_size_per_queue(struct macb *bp)
+{
+	return macb_dma_desc_get_size(bp) * bp->tx_ring_size + bp->tx_bd_rd_prefetch;
+}
+
+static unsigned int macb_rx_ring_size_per_queue(struct macb *bp)
+{
+	return macb_dma_desc_get_size(bp) * bp->rx_ring_size + bp->rx_bd_rd_prefetch;
+}
+
 static void macb_free_consistent(struct macb *bp)
 {
+	struct device *dev = &bp->pdev->dev;
 	struct macb_queue *queue;
 	unsigned int q;
-	int size;
+	size_t size;
 
 	if (bp->rx_ring_tieoff) {
-		dma_free_coherent(&bp->pdev->dev, macb_dma_desc_get_size(bp),
+		dma_free_coherent(dev, macb_dma_desc_get_size(bp),
 				  bp->rx_ring_tieoff, bp->rx_ring_tieoff_dma);
 		bp->rx_ring_tieoff = NULL;
 	}
 
 	bp->macbgem_ops.mog_free_rx_buffers(bp);
 
+	size = bp->num_queues * macb_tx_ring_size_per_queue(bp);
+	dma_free_coherent(dev, size, bp->queues[0].tx_ring, bp->queues[0].tx_ring_dma);
+
+	size = bp->num_queues * macb_rx_ring_size_per_queue(bp);
+	dma_free_coherent(dev, size, bp->queues[0].rx_ring, bp->queues[0].rx_ring_dma);
+
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		kfree(queue->tx_skb);
 		queue->tx_skb = NULL;
-		if (queue->tx_ring) {
-			size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
-			dma_free_coherent(&bp->pdev->dev, size,
-					  queue->tx_ring, queue->tx_ring_dma);
-			queue->tx_ring = NULL;
-		}
-		if (queue->rx_ring) {
-			size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
-			dma_free_coherent(&bp->pdev->dev, size,
-					  queue->rx_ring, queue->rx_ring_dma);
-			queue->rx_ring = NULL;
-		}
+		queue->tx_ring = NULL;
+		queue->rx_ring = NULL;
 	}
 }
 
@@ -2544,35 +2543,45 @@ static int macb_alloc_rx_buffers(struct macb *bp)
 
 static int macb_alloc_consistent(struct macb *bp)
 {
+	struct device *dev = &bp->pdev->dev;
+	dma_addr_t tx_dma, rx_dma;
 	struct macb_queue *queue;
 	unsigned int q;
-	int size;
+	void *tx, *rx;
+	size_t size;
+
+	/*
+	 * Upper 32-bits of Tx/Rx DMA descriptor for each queues much match!
+	 * We cannot enforce this guarantee, the best we can do is do a single
+	 * allocation and hope it will land into alloc_pages() that guarantees
+	 * natural alignment of physical addresses.
+	 */
+
+	size = bp->num_queues * macb_tx_ring_size_per_queue(bp);
+	tx = dma_alloc_coherent(dev, size, &tx_dma, GFP_KERNEL);
+	if (!tx || upper_32_bits(tx_dma) != upper_32_bits(tx_dma + size - 1))
+		goto out_err;
+	netdev_dbg(bp->dev, "Allocated %zu bytes for %u TX rings at %08lx (mapped %p)\n",
+		   size, bp->num_queues, (unsigned long)tx_dma, tx);
+
+	size = bp->num_queues * macb_rx_ring_size_per_queue(bp);
+	rx = dma_alloc_coherent(dev, size, &rx_dma, GFP_KERNEL);
+	if (!rx || upper_32_bits(rx_dma) != upper_32_bits(rx_dma + size - 1))
+		goto out_err;
+	netdev_dbg(bp->dev, "Allocated %zu bytes for %u RX rings at %08lx (mapped %p)\n",
+		   size, bp->num_queues, (unsigned long)rx_dma, rx);
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		size = TX_RING_BYTES(bp) + bp->tx_bd_rd_prefetch;
-		queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
-						    &queue->tx_ring_dma,
-						    GFP_KERNEL);
-		if (!queue->tx_ring)
-			goto out_err;
-		netdev_dbg(bp->dev,
-			   "Allocated TX ring for queue %u of %d bytes at %08lx (mapped %p)\n",
-			   q, size, (unsigned long)queue->tx_ring_dma,
-			   queue->tx_ring);
+		queue->tx_ring = tx + macb_tx_ring_size_per_queue(bp) * q;
+		queue->tx_ring_dma = tx_dma + macb_tx_ring_size_per_queue(bp) * q;
+
+		queue->rx_ring = rx + macb_rx_ring_size_per_queue(bp) * q;
+		queue->rx_ring_dma = rx_dma + macb_rx_ring_size_per_queue(bp) * q;
 
 		size = bp->tx_ring_size * sizeof(struct macb_tx_skb);
 		queue->tx_skb = kmalloc(size, GFP_KERNEL);
 		if (!queue->tx_skb)
 			goto out_err;
-
-		size = RX_RING_BYTES(bp) + bp->rx_bd_rd_prefetch;
-		queue->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
-						 &queue->rx_ring_dma, GFP_KERNEL);
-		if (!queue->rx_ring)
-			goto out_err;
-		netdev_dbg(bp->dev,
-			   "Allocated RX ring of %d bytes at %08lx (mapped %p)\n",
-			   size, (unsigned long)queue->rx_ring_dma, queue->rx_ring);
 	}
 	if (bp->macbgem_ops.mog_alloc_rx_buffers(bp))
 		goto out_err;
@@ -4309,12 +4318,6 @@ static int macb_init(struct platform_device *pdev)
 			queue->TBQP = GEM_TBQP(hw_q - 1);
 			queue->RBQP = GEM_RBQP(hw_q - 1);
 			queue->RBQS = GEM_RBQS(hw_q - 1);
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-			if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
-				queue->TBQPH = GEM_TBQPH(hw_q - 1);
-				queue->RBQPH = GEM_RBQPH(hw_q - 1);
-			}
-#endif
 		} else {
 			/* queue0 uses legacy registers */
 			queue->ISR  = MACB_ISR;
@@ -4323,12 +4326,6 @@ static int macb_init(struct platform_device *pdev)
 			queue->IMR  = MACB_IMR;
 			queue->TBQP = MACB_TBQP;
 			queue->RBQP = MACB_RBQP;
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-			if (bp->hw_dma_cap & HW_DMA_CAP_64B) {
-				queue->TBQPH = MACB_TBQPH;
-				queue->RBQPH = MACB_RBQPH;
-			}
-#endif
 		}
 
 		/* get irq: here we use the linux queue index, not the hardware
@@ -5452,6 +5449,11 @@ static int __maybe_unused macb_suspend(struct device *dev)
 		 */
 		tmp = macb_readl(bp, NCR);
 		macb_writel(bp, NCR, tmp & ~(MACB_BIT(TE) | MACB_BIT(RE)));
+#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
+		if (!(bp->caps & MACB_CAPS_QUEUE_DISABLE))
+			macb_writel(bp, RBQPH,
+				    upper_32_bits(bp->rx_ring_tieoff_dma));
+#endif
 		for (q = 0, queue = bp->queues; q < bp->num_queues;
 		     ++q, ++queue) {
 			/* Disable RX queues */
@@ -5461,10 +5463,6 @@ static int __maybe_unused macb_suspend(struct device *dev)
 				/* Tie off RX queues */
 				queue_writel(queue, RBQP,
 					     lower_32_bits(bp->rx_ring_tieoff_dma));
-#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
-				queue_writel(queue, RBQPH,
-					     upper_32_bits(bp->rx_ring_tieoff_dma));
-#endif
 			}
 			/* Disable all interrupts */
 			queue_writel(queue, IDR, -1);