Merge branch 'net-stmmac-Some-improvements-and-a-fix'

Jose Abreu says:

====================
net: stmmac: Some improvements and a fix

Some performace improvements (01/03 and 03/03) and a fix (02/03), all for -next.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/stmicro/stmmac/Kconfig

@@ -3,6 +3,7 @@ config STMMAC_ETH
 	tristate "STMicroelectronics Multi-Gigabit Ethernet driver"
 	depends on HAS_IOMEM && HAS_DMA
 	select MII
+	select PAGE_POOL
 	select PHYLINK
 	select CRC32
 	imply PTP_1588_CLOCK

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

@@ -252,6 +252,7 @@ struct stmmac_safety_stats {
 #define STMMAC_MAX_COAL_TX_TICK	100000
 #define STMMAC_TX_MAX_FRAMES	256
 #define STMMAC_TX_FRAMES	1
+#define STMMAC_RX_FRAMES	25
 
 /* Packets types */
 enum packets_types {

drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c

@@ -289,18 +289,18 @@ static void sun8i_dwmac_dma_init(void __iomem *ioaddr,
 
 static void sun8i_dwmac_dma_init_rx(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_rx_phy, u32 chan)
+				    dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* Write RX descriptors address */
-	writel(dma_rx_phy, ioaddr + EMAC_RX_DESC_LIST);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + EMAC_RX_DESC_LIST);
 }
 
 static void sun8i_dwmac_dma_init_tx(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 chan)
+				    dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* Write TX descriptors address */
-	writel(dma_tx_phy, ioaddr + EMAC_TX_DESC_LIST);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + EMAC_TX_DESC_LIST);
 }
 
 /* sun8i_dwmac_dump_regs() - Dump EMAC address space

drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c

@@ -112,18 +112,18 @@ static void dwmac1000_dma_init(void __iomem *ioaddr,
 
 static void dwmac1000_dma_init_rx(void __iomem *ioaddr,
 				  struct stmmac_dma_cfg *dma_cfg,
-				  u32 dma_rx_phy, u32 chan)
+				  dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* RX descriptor base address list must be written into DMA CSR3 */
-	writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
 }
 
 static void dwmac1000_dma_init_tx(void __iomem *ioaddr,
 				  struct stmmac_dma_cfg *dma_cfg,
-				  u32 dma_tx_phy, u32 chan)
+				  dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* TX descriptor base address list must be written into DMA CSR4 */
-	writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
 }
 
 static u32 dwmac1000_configure_fc(u32 csr6, int rxfifosz)

drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c

@@ -31,18 +31,18 @@ static void dwmac100_dma_init(void __iomem *ioaddr,
 
 static void dwmac100_dma_init_rx(void __iomem *ioaddr,
 				 struct stmmac_dma_cfg *dma_cfg,
-				 u32 dma_rx_phy, u32 chan)
+				 dma_addr_t dma_rx_phy, u32 chan)
 {
 	/* RX descriptor base addr lists must be written into DMA CSR3 */
-	writel(dma_rx_phy, ioaddr + DMA_RCV_BASE_ADDR);
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_RCV_BASE_ADDR);
 }
 
 static void dwmac100_dma_init_tx(void __iomem *ioaddr,
 				 struct stmmac_dma_cfg *dma_cfg,
-				 u32 dma_tx_phy, u32 chan)
+				 dma_addr_t dma_tx_phy, u32 chan)
 {
 	/* TX descriptor base addr lists must be written into DMA CSR4 */
-	writel(dma_tx_phy, ioaddr + DMA_TX_BASE_ADDR);
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_TX_BASE_ADDR);
 }
 
 /* Store and Forward capability is not used at all.

drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c

@@ -70,7 +70,7 @@ static void dwmac4_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
 
 static void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_rx_phy, u32 chan)
+				    dma_addr_t dma_rx_phy, u32 chan)
 {
 	u32 value;
 	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
@@ -79,12 +79,12 @@ static void dwmac4_dma_init_rx_chan(void __iomem *ioaddr,
 	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));
+	writel(lower_32_bits(dma_rx_phy), ioaddr + DMA_CHAN_RX_BASE_ADDR(chan));
 }
 
 static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
 				    struct stmmac_dma_cfg *dma_cfg,
-				    u32 dma_tx_phy, u32 chan)
+				    dma_addr_t dma_tx_phy, u32 chan)
 {
 	u32 value;
 	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
@@ -97,7 +97,7 @@ static void dwmac4_dma_init_tx_chan(void __iomem *ioaddr,
 
 	writel(value, ioaddr + DMA_CHAN_TX_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
+	writel(lower_32_bits(dma_tx_phy), ioaddr + DMA_CHAN_TX_BASE_ADDR(chan));
 }
 
 static void dwmac4_dma_init_channel(void __iomem *ioaddr,

drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h

@@ -199,7 +199,9 @@
 #define XGMAC_RxPBL			GENMASK(21, 16)
 #define XGMAC_RxPBL_SHIFT		16
 #define XGMAC_RXST			BIT(0)
+#define XGMAC_DMA_CH_TxDESC_HADDR(x)	(0x00003110 + (0x80 * (x)))
 #define XGMAC_DMA_CH_TxDESC_LADDR(x)	(0x00003114 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_HADDR(x)	(0x00003118 + (0x80 * (x)))
 #define XGMAC_DMA_CH_RxDESC_LADDR(x)	(0x0000311c + (0x80 * (x)))
 #define XGMAC_DMA_CH_TxDESC_TAIL_LPTR(x)	(0x00003124 + (0x80 * (x)))
 #define XGMAC_DMA_CH_RxDESC_TAIL_LPTR(x)	(0x0000312c + (0x80 * (x)))

drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c

@@ -44,7 +44,7 @@ static void dwxgmac2_dma_init_chan(void __iomem *ioaddr,
 
 static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
 				      struct stmmac_dma_cfg *dma_cfg,
-				      u32 dma_rx_phy, u32 chan)
+				      dma_addr_t phy, u32 chan)
 {
 	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
 	u32 value;
@@ -54,12 +54,13 @@ static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
 	value |= (rxpbl << XGMAC_RxPBL_SHIFT) & XGMAC_RxPBL;
 	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
 
-	writel(dma_rx_phy, ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
+	writel(upper_32_bits(phy), ioaddr + XGMAC_DMA_CH_RxDESC_HADDR(chan));
+	writel(lower_32_bits(phy), ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
 }
 
 static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
 				      struct stmmac_dma_cfg *dma_cfg,
-				      u32 dma_tx_phy, u32 chan)
+				      dma_addr_t phy, u32 chan)
 {
 	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
 	u32 value;
@@ -70,7 +71,8 @@ static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
 	value |= XGMAC_OSP;
 	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
 
-	writel(dma_tx_phy, ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
+	writel(upper_32_bits(phy), ioaddr + XGMAC_DMA_CH_TxDESC_HADDR(chan));
+	writel(lower_32_bits(phy), ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
 }
 
 static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)

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

@@ -150,10 +150,10 @@ struct stmmac_dma_ops {
 			  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);
+			     dma_addr_t phy, u32 chan);
 	void (*init_tx_chan)(void __iomem *ioaddr,
 			     struct stmmac_dma_cfg *dma_cfg,
-			     u32 dma_tx_phy, u32 chan);
+			     dma_addr_t phy, u32 chan);
 	/* Configure the AXI Bus Mode Register */
 	void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi);
 	/* Dump DMA registers */

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

@@ -20,6 +20,7 @@
 #include <linux/ptp_clock_kernel.h>
 #include <linux/net_tstamp.h>
 #include <linux/reset.h>
+#include <net/page_pool.h>
 
 struct stmmac_resources {
 	void __iomem *addr;
@@ -54,13 +55,19 @@ struct stmmac_tx_queue {
 	u32 mss;
 };
 
+struct stmmac_rx_buffer {
+	struct page *page;
+	dma_addr_t addr;
+};
+
 struct stmmac_rx_queue {
+	u32 rx_count_frames;
 	u32 queue_index;
+	struct page_pool *page_pool;
+	struct stmmac_rx_buffer *buf_pool;
 	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;
@@ -110,6 +117,7 @@ struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames;
 	u32 tx_coal_timer;
+	u32 rx_coal_frames;
 
 	int tx_coalesce;
 	int hwts_tx_en;

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

@@ -701,8 +701,10 @@ static int stmmac_get_coalesce(struct net_device *dev,
 	ec->tx_coalesce_usecs = priv->tx_coal_timer;
 	ec->tx_max_coalesced_frames = priv->tx_coal_frames;
 
-	if (priv->use_riwt)
+	if (priv->use_riwt) {
+		ec->rx_max_coalesced_frames = priv->rx_coal_frames;
 		ec->rx_coalesce_usecs = stmmac_riwt2usec(priv->rx_riwt, priv);
+	}
 
 	return 0;
 }
@@ -715,7 +717,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 	unsigned int rx_riwt;
 
 	/* Check not supported parameters  */
-	if ((ec->rx_max_coalesced_frames) || (ec->rx_coalesce_usecs_irq) ||
+	if ((ec->rx_coalesce_usecs_irq) ||
 	    (ec->rx_max_coalesced_frames_irq) || (ec->tx_coalesce_usecs_irq) ||
 	    (ec->use_adaptive_rx_coalesce) || (ec->use_adaptive_tx_coalesce) ||
 	    (ec->pkt_rate_low) || (ec->rx_coalesce_usecs_low) ||
@@ -749,6 +751,7 @@ static int stmmac_set_coalesce(struct net_device *dev,
 	/* Only copy relevant parameters, ignore all others. */
 	priv->tx_coal_frames = ec->tx_max_coalesced_frames;
 	priv->tx_coal_timer = ec->tx_coalesce_usecs;
+	priv->rx_coal_frames = ec->rx_max_coalesced_frames;
 	priv->rx_riwt = rx_riwt;
 	stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt);
 

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

@@ -1197,26 +1197,14 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 				  int i, gfp_t flags, u32 queue)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
-	struct sk_buff *skb;
+	struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
 
-	skb = __netdev_alloc_skb_ip_align(priv->dev, priv->dma_buf_sz, flags);
-	if (!skb) {
-		netdev_err(priv->dev,
-			   "%s: Rx init fails; skb is NULL\n", __func__);
+	buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+	if (!buf->page)
 		return -ENOMEM;
-	}
-	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, rx_q->rx_skbuff_dma[i])) {
-		netdev_err(priv->dev, "%s: DMA mapping error\n", __func__);
-		dev_kfree_skb_any(skb);
-		return -EINVAL;
-	}
-
-	stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[i]);
 
+	buf->addr = page_pool_get_dma_addr(buf->page);
+	stmmac_set_desc_addr(priv, p, buf->addr);
 	if (priv->dma_buf_sz == BUF_SIZE_16KiB)
 		stmmac_init_desc3(priv, p);
 
@@ -1232,13 +1220,11 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p,
 static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i)
 {
 	struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+	struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i];
 
-	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(rx_q->rx_skbuff[i]);
-	}
-	rx_q->rx_skbuff[i] = NULL;
+	if (buf->page)
+		page_pool_put_page(rx_q->page_pool, buf->page, false);
+	buf->page = NULL;
 }
 
 /**
@@ -1321,10 +1307,6 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t 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;
@@ -1498,8 +1480,11 @@ static void free_dma_rx_desc_resources(struct stmmac_priv *priv)
 					  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);
+		kfree(rx_q->buf_pool);
+		if (rx_q->page_pool) {
+			page_pool_request_shutdown(rx_q->page_pool);
+			page_pool_destroy(rx_q->page_pool);
+		}
 	}
 }
 
@@ -1551,20 +1536,29 @@ static int alloc_dma_rx_desc_resources(struct stmmac_priv *priv)
 	/* RX queues buffers and DMA */
 	for (queue = 0; queue < rx_count; queue++) {
 		struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue];
+		struct page_pool_params pp_params = { 0 };
 
 		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)
+		pp_params.flags = PP_FLAG_DMA_MAP;
+		pp_params.pool_size = DMA_RX_SIZE;
+		pp_params.order = DIV_ROUND_UP(priv->dma_buf_sz, PAGE_SIZE);
+		pp_params.nid = dev_to_node(priv->device);
+		pp_params.dev = priv->device;
+		pp_params.dma_dir = DMA_FROM_DEVICE;
+
+		rx_q->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(rx_q->page_pool)) {
+			ret = PTR_ERR(rx_q->page_pool);
+			rx_q->page_pool = NULL;
 			goto err_dma;
+		}
 
-		rx_q->rx_skbuff = kmalloc_array(DMA_RX_SIZE,
-						sizeof(struct sk_buff *),
-						GFP_KERNEL);
-		if (!rx_q->rx_skbuff)
+		rx_q->buf_pool = kmalloc_array(DMA_RX_SIZE,
+					       sizeof(*rx_q->buf_pool),
+					       GFP_KERNEL);
+		if (!rx_q->buf_pool)
 			goto err_dma;
 
 		if (priv->extend_desc) {
@@ -2268,20 +2262,21 @@ static void stmmac_tx_timer(struct timer_list *t)
 }
 
 /**
- * stmmac_init_tx_coalesce - init tx mitigation options.
+ * stmmac_init_coalesce - init mitigation options.
  * @priv: driver private structure
  * Description:
- * This inits the transmit coalesce parameters: i.e. timer rate,
+ * This inits the coalesce parameters: i.e. timer rate,
  * timer handler and default threshold used for enabling the
  * interrupt on completion bit.
  */
-static void stmmac_init_tx_coalesce(struct stmmac_priv *priv)
+static void stmmac_init_coalesce(struct stmmac_priv *priv)
 {
 	u32 tx_channel_count = priv->plat->tx_queues_to_use;
 	u32 chan;
 
 	priv->tx_coal_frames = STMMAC_TX_FRAMES;
 	priv->tx_coal_timer = STMMAC_COAL_TX_TIMER;
+	priv->rx_coal_frames = STMMAC_RX_FRAMES;
 
 	for (chan = 0; chan < tx_channel_count; chan++) {
 		struct stmmac_tx_queue *tx_q = &priv->tx_queue[chan];
@@ -2651,7 +2646,7 @@ static int stmmac_open(struct net_device *dev)
 		goto init_error;
 	}
 
-	stmmac_init_tx_coalesce(priv);
+	stmmac_init_coalesce(priv);
 
 	phylink_start(priv->phylink);
 
@@ -3285,55 +3280,32 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 	int dirty = stmmac_rx_dirty(priv, queue);
 	unsigned int entry = rx_q->dirty_rx;
 
-	int bfsize = priv->dma_buf_sz;
-
 	while (dirty-- > 0) {
+		struct stmmac_rx_buffer *buf = &rx_q->buf_pool[entry];
 		struct dma_desc *p;
+		bool use_rx_wd;
 
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(rx_q->dma_erx + entry);
 		else
 			p = rx_q->dma_rx + entry;
 
-		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! */
-				rx_q->rx_zeroc_thresh = STMMAC_RX_THRESH;
-				if (unlikely(net_ratelimit()))
-					dev_err(priv->device,
-						"fail to alloc skb entry %d\n",
-						entry);
-				break;
-			}
-
-			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,
-					      rx_q->rx_skbuff_dma[entry])) {
-				netdev_err(priv->dev, "Rx DMA map failed\n");
-				dev_kfree_skb(skb);
+		if (!buf->page) {
+			buf->page = page_pool_dev_alloc_pages(rx_q->page_pool);
+			if (!buf->page)
 				break;
-			}
-
-			stmmac_set_desc_addr(priv, p, rx_q->rx_skbuff_dma[entry]);
-			stmmac_refill_desc3(priv, rx_q, p);
-
-			if (rx_q->rx_zeroc_thresh > 0)
-				rx_q->rx_zeroc_thresh--;
-
-			netif_dbg(priv, rx_status, priv->dev,
-				  "refill entry #%d\n", entry);
 		}
-		dma_wmb();
 
-		stmmac_set_rx_owner(priv, p, priv->use_riwt);
+		buf->addr = page_pool_get_dma_addr(buf->page);
+		stmmac_set_desc_addr(priv, p, buf->addr);
+		stmmac_refill_desc3(priv, rx_q, p);
+
+		rx_q->rx_count_frames++;
+		rx_q->rx_count_frames %= priv->rx_coal_frames;
+		use_rx_wd = priv->use_riwt && rx_q->rx_count_frames;
 
 		dma_wmb();
+		stmmac_set_rx_owner(priv, p, use_rx_wd);
 
 		entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
 	}
@@ -3358,9 +3330,6 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	unsigned int next_entry = rx_q->cur_rx;
 	int coe = priv->hw->rx_csum;
 	unsigned int count = 0;
-	bool xmac;
-
-	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
@@ -3374,11 +3343,12 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 		stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true);
 	}
 	while (count < limit) {
+		struct stmmac_rx_buffer *buf;
+		struct dma_desc *np, *p;
 		int entry, status;
-		struct dma_desc *p;
-		struct dma_desc *np;
 
 		entry = next_entry;
+		buf = &rx_q->buf_pool[entry];
 
 		if (priv->extend_desc)
 			p = (struct dma_desc *)(rx_q->dma_erx + entry);
@@ -3408,20 +3378,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			stmmac_rx_extended_status(priv, &priv->dev->stats,
 					&priv->xstats, rx_q->dma_erx + entry);
 		if (unlikely(status == discard_frame)) {
+			page_pool_recycle_direct(rx_q->page_pool, buf->page);
 			priv->dev->stats.rx_errors++;
-			if (priv->hwts_rx_en && !priv->extend_desc) {
-				/* DESC2 & DESC3 will be overwritten by device
-				 * with timestamp value, hence reinitialize
-				 * them in stmmac_rx_refill() function so that
-				 * device can reuse it.
-				 */
-				dev_kfree_skb_any(rx_q->rx_skbuff[entry]);
-				rx_q->rx_skbuff[entry] = NULL;
-				dma_unmap_single(priv->device,
-						 rx_q->rx_skbuff_dma[entry],
-						 priv->dma_buf_sz,
-						 DMA_FROM_DEVICE);
-			}
+			buf->page = NULL;
 		} else {
 			struct sk_buff *skb;
 			int frame_len;
@@ -3461,58 +3420,20 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 					   frame_len, status);
 			}
 
-			/* The zero-copy is always used for all the sizes
-			 * in case of GMAC4 because it needs
-			 * to refill the used descriptors, always.
-			 */
-			if (unlikely(!xmac &&
-				     ((frame_len < priv->rx_copybreak) ||
-				     stmmac_rx_threshold_count(rx_q)))) {
-				skb = netdev_alloc_skb_ip_align(priv->dev,
-								frame_len);
-				if (unlikely(!skb)) {
-					if (net_ratelimit())
-						dev_warn(priv->device,
-							 "packet dropped\n");
-					priv->dev->stats.rx_dropped++;
-					continue;
-				}
-
-				dma_sync_single_for_cpu(priv->device,
-							rx_q->rx_skbuff_dma
-							[entry], frame_len,
-							DMA_FROM_DEVICE);
-				skb_copy_to_linear_data(skb,
-							rx_q->
-							rx_skbuff[entry]->data,
-							frame_len);
-
-				skb_put(skb, frame_len);
-				dma_sync_single_for_device(priv->device,
-							   rx_q->rx_skbuff_dma
-							   [entry], frame_len,
-							   DMA_FROM_DEVICE);
-			} else {
-				skb = rx_q->rx_skbuff[entry];
-				if (unlikely(!skb)) {
-					if (net_ratelimit())
-						netdev_err(priv->dev,
-							   "%s: Inconsistent Rx chain\n",
-							   priv->dev->name);
-					priv->dev->stats.rx_dropped++;
-					continue;
-				}
-				prefetch(skb->data - NET_IP_ALIGN);
-				rx_q->rx_skbuff[entry] = NULL;
-				rx_q->rx_zeroc_thresh++;
-
-				skb_put(skb, frame_len);
-				dma_unmap_single(priv->device,
-						 rx_q->rx_skbuff_dma[entry],
-						 priv->dma_buf_sz,
-						 DMA_FROM_DEVICE);
+			skb = netdev_alloc_skb_ip_align(priv->dev, frame_len);
+			if (unlikely(!skb)) {
+				priv->dev->stats.rx_dropped++;
+				continue;
 			}
 
+			dma_sync_single_for_cpu(priv->device, buf->addr,
+						frame_len, DMA_FROM_DEVICE);
+			skb_copy_to_linear_data(skb, page_address(buf->page),
+						frame_len);
+			skb_put(skb, frame_len);
+			dma_sync_single_for_device(priv->device, buf->addr,
+						   frame_len, DMA_FROM_DEVICE);
+
 			if (netif_msg_pktdata(priv)) {
 				netdev_dbg(priv->dev, "frame received (%dbytes)",
 					   frame_len);
@@ -3532,6 +3453,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 
 			napi_gro_receive(&ch->rx_napi, skb);
 
+			/* Data payload copied into SKB, page ready for recycle */
+			page_pool_recycle_direct(rx_q->page_pool, buf->page);
+			buf->page = NULL;
+
 			priv->dev->stats.rx_packets++;
 			priv->dev->stats.rx_bytes += frame_len;
 		}
@@ -4631,7 +4556,7 @@ int stmmac_resume(struct device *dev)
 	stmmac_clear_descriptors(priv);
 
 	stmmac_hw_setup(ndev, false);
-	stmmac_init_tx_coalesce(priv);
+	stmmac_init_coalesce(priv);
 	stmmac_set_rx_mode(ndev);
 
 	stmmac_enable_all_queues(priv);