Use the page pool allocator for the data buffers and enable skb recycling
support, instead of relying on netdev_alloc_skb allocating the entire skb
during the refill.

The patch also add support for receiving network frames that span multiple
DMA descriptors in the Cadence MACB/GEM Ethernet driver.

The patch removes the requirement that limited frame reception to
a single descriptor (RX_SOF && RX_EOF), also avoiding potential
contiguous multi-page allocation for large frames.

Signed-off-by: Paolo Valerio <redacted>
---
 drivers/net/ethernet/cadence/Kconfig     |   1 +
 drivers/net/ethernet/cadence/macb.h      |   5 +
 drivers/net/ethernet/cadence/macb_main.c | 345 +++++++++++++++--------
 3 files changed, 235 insertions(+), 116 deletions(-)

diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 5b2a461dfd28..ae500f717433 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig

@@ -25,6 +25,7 @@ config MACB
 	depends on PTP_1588_CLOCK_OPTIONAL
 	select PHYLINK
 	select CRC32
+	select PAGE_POOL
 	help
 	  The Cadence MACB ethernet interface is found on many Atmel AT32 and
 	  AT91 parts.  This driver also supports the Cadence GEM (Gigabit

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 3b184e9ac771..45c04157f153 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h

@@ -14,6 +14,8 @@
 #include <linux/interrupt.h>
 #include <linux/phy/phy.h>
 #include <linux/workqueue.h>
+#include <net/page_pool/helpers.h>
+#include <net/xdp.h>

 
 #define MACB_GREGS_NBR 16
 #define MACB_GREGS_VERSION 2

@@ -1266,6 +1268,8 @@ struct macb_queue {
 	void			*rx_buffers;
 	struct napi_struct	napi_rx;
 	struct queue_stats stats;
+	struct page_pool	*page_pool;
+	struct sk_buff		*skb;
 };
 
 struct ethtool_rx_fs_item {

@@ -1289,6 +1293,7 @@ struct macb {
 	struct macb_dma_desc	*rx_ring_tieoff;
 	dma_addr_t		rx_ring_tieoff_dma;
 	size_t			rx_buffer_size;
+	size_t			rx_headroom;
 
 	unsigned int		rx_ring_size;
 	unsigned int		tx_ring_size;

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b4e2444b2e95..9e1efc1f56d8 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c

@@ -1249,14 +1249,22 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 	return packets;
 }
 
-static int gem_rx_refill(struct macb_queue *queue)
+static int gem_total_rx_buffer_size(struct macb *bp)
+{
+	return SKB_HEAD_ALIGN(bp->rx_buffer_size + bp->rx_headroom);
+}

+
+static int gem_rx_refill(struct macb_queue *queue, bool napi)
 {
 	unsigned int		entry;
-	struct sk_buff		*skb;
 	dma_addr_t		paddr;
+	void			*data;
 	struct macb *bp = queue->bp;
 	struct macb_dma_desc *desc;
+	struct page *page;
+	gfp_t gfp_alloc;
 	int err = 0;
+	int offset;
 
 	while (CIRC_SPACE(queue->rx_prepared_head, queue->rx_tail,
 			bp->rx_ring_size) > 0) {

@@ -1268,25 +1276,20 @@ static int gem_rx_refill(struct macb_queue *queue)
 		desc = macb_rx_desc(queue, entry);
 
 		if (!queue->rx_buff[entry]) {
-			/* allocate sk_buff for this free entry in ring */
-			skb = netdev_alloc_skb(bp->dev, bp->rx_buffer_size);
-			if (unlikely(!skb)) {
+			gfp_alloc = napi ? GFP_ATOMIC : GFP_KERNEL;
+			page = page_pool_alloc_frag(queue->page_pool, &offset,
+						    gem_total_rx_buffer_size(bp),
+						    gfp_alloc | __GFP_NOWARN);
+			if (!page) {
 				netdev_err(bp->dev,
-					   "Unable to allocate sk_buff\n");
+					   "Unable to allocate page\n");
 				err = -ENOMEM;
 				break;
 			}
 
-			/* now fill corresponding descriptor entry */
-			paddr = dma_map_single(&bp->pdev->dev, skb->data,
-					       bp->rx_buffer_size,
-					       DMA_FROM_DEVICE);
-			if (dma_mapping_error(&bp->pdev->dev, paddr)) {
-				dev_kfree_skb(skb);
-				break;
-			}
-
-			queue->rx_buff[entry] = skb;
+			paddr = page_pool_get_dma_addr(page) + XDP_PACKET_HEADROOM + offset;
+			data = page_address(page) + offset;
+			queue->rx_buff[entry] = data;
 
 			if (entry == bp->rx_ring_size - 1)
 				paddr |= MACB_BIT(RX_WRAP);

@@ -1296,20 +1299,6 @@ static int gem_rx_refill(struct macb_queue *queue)
 			 */
 			dma_wmb();
 			macb_set_addr(bp, desc, paddr);
-
-			/* Properly align Ethernet header.
-			 *
-			 * Hardware can add dummy bytes if asked using the RBOF
-			 * field inside the NCFGR register. That feature isn't
-			 * available if hardware is RSC capable.
-			 *
-			 * We cannot fallback to doing the 2-byte shift before
-			 * DMA mapping because the address field does not allow
-			 * setting the low 2/3 bits.
-			 * It is 3 bits if HW_DMA_CAP_PTP, else 2 bits.
-			 */
-			if (!(bp->caps & MACB_CAPS_RSC))
-				skb_reserve(skb, NET_IP_ALIGN);
 		} else {
 			desc->ctrl = 0;
 			dma_wmb();

@@ -1353,14 +1342,19 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi,
 	struct macb *bp = queue->bp;
 	unsigned int		len;
 	unsigned int		entry;
-	struct sk_buff		*skb;
 	struct macb_dma_desc	*desc;
+	int			data_len;
 	int			count = 0;
+	void			*buff_head;
+	struct skb_shared_info	*shinfo;
+	struct page		*page;
+	int			nr_frags;

+
 
 	while (count < budget) {
 		u32 ctrl;
 		dma_addr_t addr;
-		bool rxused;
+		bool rxused, first_frame;
 
 		entry = macb_rx_ring_wrap(bp, queue->rx_tail);
 		desc = macb_rx_desc(queue, entry);

@@ -1374,6 +1368,12 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi,
 		if (!rxused)
 			break;
 
+		if (!(bp->caps & MACB_CAPS_RSC))
+			addr += NET_IP_ALIGN;
+
+		dma_sync_single_for_cpu(&bp->pdev->dev,
+					addr, bp->rx_buffer_size,
+					page_pool_get_dma_dir(queue->page_pool));
 		/* Ensure ctrl is at least as up-to-date as rxused */
 		dma_rmb();
 

@@ -1382,58 +1382,118 @@ static int gem_rx(struct macb_queue *queue, struct napi_struct *napi,
 		queue->rx_tail++;
 		count++;
 
-		if (!(ctrl & MACB_BIT(RX_SOF) && ctrl & MACB_BIT(RX_EOF))) {
-			netdev_err(bp->dev,
-				   "not whole frame pointed by descriptor\n");
-			bp->dev->stats.rx_dropped++;
-			queue->stats.rx_dropped++;
-			break;
-		}
-		skb = queue->rx_buff[entry];
-		if (unlikely(!skb)) {
+		buff_head = queue->rx_buff[entry];
+		if (unlikely(!buff_head)) {
 			netdev_err(bp->dev,
 				   "inconsistent Rx descriptor chain\n");
 			bp->dev->stats.rx_dropped++;
 			queue->stats.rx_dropped++;
 			break;
 		}
-		/* now everything is ready for receiving packet */
-		queue->rx_buff[entry] = NULL;
+
+		first_frame = ctrl & MACB_BIT(RX_SOF);
 		len = ctrl & bp->rx_frm_len_mask;
 
-		netdev_vdbg(bp->dev, "gem_rx %u (len %u)\n", entry, len);
+		if (len) {
+			data_len = len;
+			if (!first_frame)
+				data_len -= queue->skb->len;
+		} else {
+			data_len = bp->rx_buffer_size;
+		}

 
-		napi_gro_receive(napi, skb);
+			napi_gro_receive(napi, queue->skb);
+			queue->skb = NULL;
+		}
+
+		continue;
+
+free_frags:
+		if (queue->skb) {
+			dev_kfree_skb(queue->skb);
+			queue->skb = NULL;
+		} else {
+			page_pool_put_full_page(queue->page_pool,
+						virt_to_head_page(buff_head),
+						false);
+		}
+
+		bp->dev->stats.rx_dropped++;
+		queue->stats.rx_dropped++;
+		queue->rx_buff[entry] = NULL;
 	}
 
-	gem_rx_refill(queue);
+	gem_rx_refill(queue, true);
 
 	return count;
 }

@@ -2367,12 +2427,25 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
-static void macb_init_rx_buffer_size(struct macb *bp, size_t size)
+static void macb_init_rx_buffer_size(struct macb *bp, unsigned int mtu)
 {
+	int overhead;