1 files changed, 254 insertions, 75 deletions

diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index ec09fcece711..538544a7c642 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -32,19 +32,28 @@
 #include <linux/of_gpio.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
-
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
 #include "macb.h"
 
 #define MACB_RX_BUFFER_SIZE	128
 #define RX_BUFFER_MULTIPLE	64  /* bytes */
-#define RX_RING_SIZE		512 /* must be power of 2 */
-#define RX_RING_BYTES		(sizeof(struct macb_dma_desc) * RX_RING_SIZE)
 
-#define TX_RING_SIZE		128 /* must be power of 2 */
-#define TX_RING_BYTES		(sizeof(struct macb_dma_desc) * TX_RING_SIZE)
+#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)	(sizeof(struct macb_dma_desc)	\
+				 * (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)	(sizeof(struct macb_dma_desc)	\
+				 * (bp)->tx_ring_size)
 
 /* level of occupied TX descriptors under which we wake up TX process */
-#define MACB_TX_WAKEUP_THRESH	(3 * TX_RING_SIZE / 4)
+#define MACB_TX_WAKEUP_THRESH(bp)	(3 * (bp)->tx_ring_size / 4)
 
 #define MACB_RX_INT_FLAGS	(MACB_BIT(RCOMP) | MACB_BIT(RXUBR)	\
 				 | MACB_BIT(ISR_ROVR))
@@ -53,10 +62,13 @@
 					| MACB_BIT(TXERR))
 #define MACB_TX_INT_FLAGS	(MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP))
 
-#define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1))
-#define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1))
+/* Max length of transmit frame must be a multiple of 8 bytes */
+#define MACB_TX_LEN_ALIGN	8
+#define MACB_MAX_TX_LEN		((unsigned int)((1 << MACB_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
+#define GEM_MAX_TX_LEN		((unsigned int)((1 << GEM_TX_FRMLEN_SIZE) - 1) & ~((unsigned int)(MACB_TX_LEN_ALIGN - 1)))
 
-#define GEM_MTU_MIN_SIZE	68
+#define GEM_MTU_MIN_SIZE	ETH_MIN_MTU
+#define MACB_NETIF_LSO		(NETIF_F_TSO | NETIF_F_UFO)
 
 #define MACB_WOL_HAS_MAGIC_PACKET	(0x1 << 0)
 #define MACB_WOL_ENABLED		(0x1 << 1)
@@ -67,45 +79,47 @@
 #define MACB_HALT_TIMEOUT	1230
 
 /* Ring buffer accessors */
-static unsigned int macb_tx_ring_wrap(unsigned int index)
+static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index)
 {
-	return index & (TX_RING_SIZE - 1);
+	return index & (bp->tx_ring_size - 1);
 }
 
 static struct macb_dma_desc *macb_tx_desc(struct macb_queue *queue,
 					  unsigned int index)
 {
-	return &queue->tx_ring[macb_tx_ring_wrap(index)];
+	return &queue->tx_ring[macb_tx_ring_wrap(queue->bp, index)];
 }
 
 static struct macb_tx_skb *macb_tx_skb(struct macb_queue *queue,
 				       unsigned int index)
 {
-	return &queue->tx_skb[macb_tx_ring_wrap(index)];
+	return &queue->tx_skb[macb_tx_ring_wrap(queue->bp, index)];
 }
 
 static dma_addr_t macb_tx_dma(struct macb_queue *queue, unsigned int index)
 {
 	dma_addr_t offset;
 
-	offset = macb_tx_ring_wrap(index) * sizeof(struct macb_dma_desc);
+	offset = macb_tx_ring_wrap(queue->bp, index) *
+		 sizeof(struct macb_dma_desc);
 
 	return queue->tx_ring_dma + offset;
 }
 
-static unsigned int macb_rx_ring_wrap(unsigned int index)
+static unsigned int macb_rx_ring_wrap(struct macb *bp, unsigned int index)
 {
-	return index & (RX_RING_SIZE - 1);
+	return index & (bp->rx_ring_size - 1);
 }
 
 static struct macb_dma_desc *macb_rx_desc(struct macb *bp, unsigned int index)
 {
-	return &bp->rx_ring[macb_rx_ring_wrap(index)];
+	return &bp->rx_ring[macb_rx_ring_wrap(bp, index)];
 }
 
 static void *macb_rx_buffer(struct macb *bp, unsigned int index)
 {
-	return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
+	return bp->rx_buffers + bp->rx_buffer_size *
+	       macb_rx_ring_wrap(bp, index);
 }
 
 /* I/O accessors */
@@ -608,7 +622,8 @@ static void macb_tx_error_task(struct work_struct *work)
 			 */
 			if (!(ctrl & MACB_BIT(TX_BUF_EXHAUSTED))) {
 				netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n",
-					    macb_tx_ring_wrap(tail), skb->data);
+					    macb_tx_ring_wrap(bp, tail),
+					    skb->data);
 				bp->stats.tx_packets++;
 				bp->stats.tx_bytes += skb->len;
 			}
@@ -700,7 +715,8 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 			/* First, update TX stats if needed */
 			if (skb) {
 				netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
-					    macb_tx_ring_wrap(tail), skb->data);
+					    macb_tx_ring_wrap(bp, tail),
+					    skb->data);
 				bp->stats.tx_packets++;
 				bp->stats.tx_bytes += skb->len;
 			}
@@ -720,7 +736,7 @@ static void macb_tx_interrupt(struct macb_queue *queue)
 	queue->tx_tail = tail;
 	if (__netif_subqueue_stopped(bp->dev, queue_index) &&
 	    CIRC_CNT(queue->tx_head, queue->tx_tail,
-		     TX_RING_SIZE) <= MACB_TX_WAKEUP_THRESH)
+		     bp->tx_ring_size) <= MACB_TX_WAKEUP_THRESH(bp))
 		netif_wake_subqueue(bp->dev, queue_index);
 }
 
@@ -731,8 +747,8 @@ static void gem_rx_refill(struct macb *bp)
 	dma_addr_t		paddr;
 
 	while (CIRC_SPACE(bp->rx_prepared_head, bp->rx_tail,
-			  RX_RING_SIZE) > 0) {
-		entry = macb_rx_ring_wrap(bp->rx_prepared_head);
+			  bp->rx_ring_size) > 0) {
+		entry = macb_rx_ring_wrap(bp, bp->rx_prepared_head);
 
 		/* Make hw descriptor updates visible to CPU */
 		rmb();
@@ -759,7 +775,7 @@ static void gem_rx_refill(struct macb *bp)
 
 			bp->rx_skbuff[entry] = skb;
 
-			if (entry == RX_RING_SIZE - 1)
+			if (entry == bp->rx_ring_size - 1)
 				paddr |= MACB_BIT(RX_WRAP);
 			macb_set_addr(&(bp->rx_ring[entry]), paddr);
 			bp->rx_ring[entry].ctrl = 0;
@@ -813,7 +829,7 @@ static int gem_rx(struct macb *bp, int budget)
 		dma_addr_t addr;
 		bool rxused;
 
-		entry = macb_rx_ring_wrap(bp->rx_tail);
+		entry = macb_rx_ring_wrap(bp, bp->rx_tail);
 		desc = &bp->rx_ring[entry];
 
 		/* Make hw descriptor updates visible to CPU */
@@ -895,8 +911,8 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
 	len = desc->ctrl & bp->rx_frm_len_mask;
 
 	netdev_vdbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n",
-		    macb_rx_ring_wrap(first_frag),
-		    macb_rx_ring_wrap(last_frag), len);
+		macb_rx_ring_wrap(bp, first_frag),
+		macb_rx_ring_wrap(bp, last_frag), len);
 
 	/* The ethernet header starts NET_IP_ALIGN bytes into the
 	 * first buffer. Since the header is 14 bytes, this makes the
@@ -969,12 +985,12 @@ static inline void macb_init_rx_ring(struct macb *bp)
 	int i;
 
 	addr = bp->rx_buffers_dma;
-	for (i = 0; i < RX_RING_SIZE; i++) {
+	for (i = 0; i < bp->rx_ring_size; i++) {
 		bp->rx_ring[i].addr = addr;
 		bp->rx_ring[i].ctrl = 0;
 		addr += bp->rx_buffer_size;
 	}
-	bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP);
+	bp->rx_ring[bp->rx_ring_size - 1].addr |= MACB_BIT(RX_WRAP);
 	bp->rx_tail = 0;
 }
 
@@ -1214,7 +1230,8 @@ static void macb_poll_controller(struct net_device *dev)
 
 static unsigned int macb_tx_map(struct macb *bp,
 				struct macb_queue *queue,
-				struct sk_buff *skb)
+				struct sk_buff *skb,
+				unsigned int hdrlen)
 {
 	dma_addr_t mapping;
 	unsigned int len, entry, i, tx_head = queue->tx_head;
@@ -1222,15 +1239,28 @@ static unsigned int macb_tx_map(struct macb *bp,
 	struct macb_dma_desc *desc;
 	unsigned int offset, size, count = 0;
 	unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags;
-	unsigned int eof = 1;
-	u32 ctrl;
+	unsigned int eof = 1, mss_mfs = 0;
+	u32 ctrl, lso_ctrl = 0, seq_ctrl = 0;
+
+	/* LSO */
+	if (skb_shinfo(skb)->gso_size != 0) {
+		if (ip_hdr(skb)->protocol == IPPROTO_UDP)
+			/* UDP - UFO */
+			lso_ctrl = MACB_LSO_UFO_ENABLE;
+		else
+			/* TCP - TSO */
+			lso_ctrl = MACB_LSO_TSO_ENABLE;
+	}
 
 	/* First, map non-paged data */
 	len = skb_headlen(skb);
+
+	/* first buffer length */
+	size = hdrlen;
+
 	offset = 0;
 	while (len) {
-		size = min(len, bp->max_tx_length);
-		entry = macb_tx_ring_wrap(tx_head);
+		entry = macb_tx_ring_wrap(bp, tx_head);
 		tx_skb = &queue->tx_skb[entry];
 
 		mapping = dma_map_single(&bp->pdev->dev,
@@ -1249,6 +1279,8 @@ static unsigned int macb_tx_map(struct macb *bp,
 		offset += size;
 		count++;
 		tx_head++;
+
+		size = min(len, bp->max_tx_length);
 	}
 
 	/* Then, map paged data from fragments */
@@ -1259,7 +1291,7 @@ static unsigned int macb_tx_map(struct macb *bp,
 		offset = 0;
 		while (len) {
 			size = min(len, bp->max_tx_length);
-			entry = macb_tx_ring_wrap(tx_head);
+			entry = macb_tx_ring_wrap(bp, tx_head);
 			tx_skb = &queue->tx_skb[entry];
 
 			mapping = skb_frag_dma_map(&bp->pdev->dev, frag,
@@ -1297,14 +1329,29 @@ static unsigned int macb_tx_map(struct macb *bp,
 	 * to set the end of TX queue
 	 */
 	i = tx_head;
-	entry = macb_tx_ring_wrap(i);
+	entry = macb_tx_ring_wrap(bp, i);
 	ctrl = MACB_BIT(TX_USED);
 	desc = &queue->tx_ring[entry];
 	desc->ctrl = ctrl;
 
+	if (lso_ctrl) {
+		if (lso_ctrl == MACB_LSO_UFO_ENABLE)
+			/* include header and FCS in value given to h/w */
+			mss_mfs = skb_shinfo(skb)->gso_size +
+					skb_transport_offset(skb) +
+					ETH_FCS_LEN;
+		else /* TSO */ {
+			mss_mfs = skb_shinfo(skb)->gso_size;
+			/* TCP Sequence Number Source Select
+			 * can be set only for TSO
+			 */
+			seq_ctrl = 0;
+		}
+	}
+
 	do {
 		i--;
-		entry = macb_tx_ring_wrap(i);
+		entry = macb_tx_ring_wrap(bp, i);
 		tx_skb = &queue->tx_skb[entry];
 		desc = &queue->tx_ring[entry];
 
@@ -1313,9 +1360,19 @@ static unsigned int macb_tx_map(struct macb *bp,
 			ctrl |= MACB_BIT(TX_LAST);
 			eof = 0;
 		}
-		if (unlikely(entry == (TX_RING_SIZE - 1)))
+		if (unlikely(entry == (bp->tx_ring_size - 1)))
 			ctrl |= MACB_BIT(TX_WRAP);
 
+		/* First descriptor is header descriptor */
+		if (i == queue->tx_head) {
+			ctrl |= MACB_BF(TX_LSO, lso_ctrl);
+			ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl);
+		} else
+			/* Only set MSS/MFS on payload descriptors
+			 * (second or later descriptor)
+			 */
+			ctrl |= MACB_BF(MSS_MFS, mss_mfs);
+
 		/* Set TX buffer descriptor */
 		macb_set_addr(desc, tx_skb->mapping);
 		/* desc->addr must be visible to hardware before clearing
@@ -1341,6 +1398,43 @@ dma_error:
 	return 0;
 }
 
+static netdev_features_t macb_features_check(struct sk_buff *skb,
+					     struct net_device *dev,
+					     netdev_features_t features)
+{
+	unsigned int nr_frags, f;
+	unsigned int hdrlen;
+
+	/* Validate LSO compatibility */
+
+	/* there is only one buffer */
+	if (!skb_is_nonlinear(skb))
+		return features;
+
+	/* length of header */
+	hdrlen = skb_transport_offset(skb);
+	if (ip_hdr(skb)->protocol == IPPROTO_TCP)
+		hdrlen += tcp_hdrlen(skb);
+
+	/* For LSO:
+	 * When software supplies two or more payload buffers all payload buffers
+	 * apart from the last must be a multiple of 8 bytes in size.
+	 */
+	if (!IS_ALIGNED(skb_headlen(skb) - hdrlen, MACB_TX_LEN_ALIGN))
+		return features & ~MACB_NETIF_LSO;
+
+	nr_frags = skb_shinfo(skb)->nr_frags;
+	/* No need to check last fragment */
+	nr_frags--;
+	for (f = 0; f < nr_frags; f++) {
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+
+		if (!IS_ALIGNED(skb_frag_size(frag), MACB_TX_LEN_ALIGN))
+			return features & ~MACB_NETIF_LSO;
+	}
+	return features;
+}
+
 static inline int macb_clear_csum(struct sk_buff *skb)
 {
 	/* no change for packets without checksum offloading */
@@ -1365,7 +1459,28 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct macb *bp = netdev_priv(dev);
 	struct macb_queue *queue = &bp->queues[queue_index];
 	unsigned long flags;
-	unsigned int count, nr_frags, frag_size, f;
+	unsigned int desc_cnt, nr_frags, frag_size, f;
+	unsigned int hdrlen;
+	bool is_lso, is_udp = 0;
+
+	is_lso = (skb_shinfo(skb)->gso_size != 0);
+
+	if (is_lso) {
+		is_udp = !!(ip_hdr(skb)->protocol == IPPROTO_UDP);
+
+		/* length of headers */
+		if (is_udp)
+			/* only queue eth + ip headers separately for UDP */
+			hdrlen = skb_transport_offset(skb);
+		else
+			hdrlen = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		if (skb_headlen(skb) < hdrlen) {
+			netdev_err(bp->dev, "Error - LSO headers fragmented!!!\n");
+			/* if this is required, would need to copy to single buffer */
+			return NETDEV_TX_BUSY;
+		}
+	} else
+		hdrlen = min(skb_headlen(skb), bp->max_tx_length);
 
 #if defined(DEBUG) && defined(VERBOSE_DEBUG)
 	netdev_vdbg(bp->dev,
@@ -1380,17 +1495,22 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 * socket buffer: skb fragments of jumbo frames may need to be
 	 * split into many buffer descriptors.
 	 */
-	count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
+	if (is_lso && (skb_headlen(skb) > hdrlen))
+		/* extra header descriptor if also payload in first buffer */
+		desc_cnt = DIV_ROUND_UP((skb_headlen(skb) - hdrlen), bp->max_tx_length) + 1;
+	else
+		desc_cnt = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
 		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
-		count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
+		desc_cnt += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
 	spin_lock_irqsave(&bp->lock, flags);
 
 	/* This is a hard error, log it. */
-	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, TX_RING_SIZE) < count) {
+	if (CIRC_SPACE(queue->tx_head, queue->tx_tail,
+		       bp->tx_ring_size) < desc_cnt) {
 		netif_stop_subqueue(dev, queue_index);
 		spin_unlock_irqrestore(&bp->lock, flags);
 		netdev_dbg(bp->dev, "tx_head = %u, tx_tail = %u\n",
@@ -1404,7 +1524,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	/* Map socket buffer for DMA transfer */
-	if (!macb_tx_map(bp, queue, skb)) {
+	if (!macb_tx_map(bp, queue, skb, hdrlen)) {
 		dev_kfree_skb_any(skb);
 		goto unlock;
 	}
@@ -1416,7 +1536,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
 
-	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, TX_RING_SIZE) < 1)
+	if (CIRC_SPACE(queue->tx_head, queue->tx_tail, bp->tx_ring_size) < 1)
 		netif_stop_subqueue(dev, queue_index);
 
 unlock:
@@ -1455,7 +1575,7 @@ static void gem_free_rx_buffers(struct macb *bp)
 	if (!bp->rx_skbuff)
 		return;
 
-	for (i = 0; i < RX_RING_SIZE; i++) {
+	for (i = 0; i < bp->rx_ring_size; i++) {
 		skb = bp->rx_skbuff[i];
 
 		if (!skb)
@@ -1480,7 +1600,7 @@ static void macb_free_rx_buffers(struct macb *bp)
 {
 	if (bp->rx_buffers) {
 		dma_free_coherent(&bp->pdev->dev,
-				  RX_RING_SIZE * bp->rx_buffer_size,
+				  bp->rx_ring_size * bp->rx_buffer_size,
 				  bp->rx_buffers, bp->rx_buffers_dma);
 		bp->rx_buffers = NULL;
 	}
@@ -1493,7 +1613,7 @@ static void macb_free_consistent(struct macb *bp)
 
 	bp->macbgem_ops.mog_free_rx_buffers(bp);
 	if (bp->rx_ring) {
-		dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES,
+		dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES(bp),
 				  bp->rx_ring, bp->rx_ring_dma);
 		bp->rx_ring = NULL;
 	}
@@ -1502,7 +1622,7 @@ static void macb_free_consistent(struct macb *bp)
 		kfree(queue->tx_skb);
 		queue->tx_skb = NULL;
 		if (queue->tx_ring) {
-			dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES,
+			dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES(bp),
 					  queue->tx_ring, queue->tx_ring_dma);
 			queue->tx_ring = NULL;
 		}
@@ -1513,14 +1633,14 @@ static int gem_alloc_rx_buffers(struct macb *bp)
 {
 	int size;
 
-	size = RX_RING_SIZE * sizeof(struct sk_buff *);
+	size = bp->rx_ring_size * sizeof(struct sk_buff *);
 	bp->rx_skbuff = kzalloc(size, GFP_KERNEL);
 	if (!bp->rx_skbuff)
 		return -ENOMEM;
-
-	netdev_dbg(bp->dev,
-		   "Allocated %d RX struct sk_buff entries at %p\n",
-		   RX_RING_SIZE, bp->rx_skbuff);
+	else
+		netdev_dbg(bp->dev,
+			   "Allocated %d RX struct sk_buff entries at %p\n",
+			   bp->rx_ring_size, bp->rx_skbuff);
 	return 0;
 }
 
@@ -1528,7 +1648,7 @@ static int macb_alloc_rx_buffers(struct macb *bp)
 {
 	int size;
 
-	size = RX_RING_SIZE * bp->rx_buffer_size;
+	size = bp->rx_ring_size * bp->rx_buffer_size;
 	bp->rx_buffers = dma_alloc_coherent(&bp->pdev->dev, size,
 					    &bp->rx_buffers_dma, GFP_KERNEL);
 	if (!bp->rx_buffers)
@@ -1547,7 +1667,7 @@ static int macb_alloc_consistent(struct macb *bp)
 	int size;
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		size = TX_RING_BYTES;
+		size = TX_RING_BYTES(bp);
 		queue->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
 						    &queue->tx_ring_dma,
 						    GFP_KERNEL);
@@ -1558,13 +1678,13 @@ static int macb_alloc_consistent(struct macb *bp)
 			   q, size, (unsigned long)queue->tx_ring_dma,
 			   queue->tx_ring);
 
-		size = TX_RING_SIZE * sizeof(struct macb_tx_skb);
+		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;
+	size = RX_RING_BYTES(bp);
 	bp->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
 					 &bp->rx_ring_dma, GFP_KERNEL);
 	if (!bp->rx_ring)
@@ -1590,11 +1710,11 @@ static void gem_init_rings(struct macb *bp)
 	int i;
 
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
-		for (i = 0; i < TX_RING_SIZE; i++) {
-			macb_set_addr(&(queue->tx_ring[i]), 0);
+		for (i = 0; i < bp->tx_ring_size; i++) {
+			queue->tx_ring[i].addr = 0;
 			queue->tx_ring[i].ctrl = MACB_BIT(TX_USED);
 		}
-		queue->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
+		queue->tx_ring[bp->tx_ring_size - 1].ctrl |= MACB_BIT(TX_WRAP);
 		queue->tx_head = 0;
 		queue->tx_tail = 0;
 	}
@@ -1611,13 +1731,13 @@ static void macb_init_rings(struct macb *bp)
 
 	macb_init_rx_ring(bp);
 
-	for (i = 0; i < TX_RING_SIZE; i++) {
+	for (i = 0; i < bp->tx_ring_size; i++) {
 		bp->queues[0].tx_ring[i].addr = 0;
 		bp->queues[0].tx_ring[i].ctrl = MACB_BIT(TX_USED);
 	}
 	bp->queues[0].tx_head = 0;
 	bp->queues[0].tx_tail = 0;
-	bp->queues[0].tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
+	bp->queues[0].tx_ring[bp->tx_ring_size - 1].ctrl |= MACB_BIT(TX_WRAP);
 }
 
 static void macb_reset_hw(struct macb *bp)
@@ -1986,19 +2106,9 @@ static int macb_close(struct net_device *dev)
 
 static int macb_change_mtu(struct net_device *dev, int new_mtu)
 {
-	struct macb *bp = netdev_priv(dev);
-	u32 max_mtu;
-
 	if (netif_running(dev))
 		return -EBUSY;
 
-	max_mtu = ETH_DATA_LEN;
-	if (bp->caps & MACB_CAPS_JUMBO)
-		max_mtu = gem_readl(bp, JML) - ETH_HLEN - ETH_FCS_LEN;
-
-	if ((new_mtu > max_mtu) || (new_mtu < GEM_MTU_MIN_SIZE))
-		return -EINVAL;
-
 	dev->mtu = new_mtu;
 
 	return 0;
@@ -2158,8 +2268,8 @@ static void macb_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 	regs->version = (macb_readl(bp, MID) & ((1 << MACB_REV_SIZE) - 1))
 			| MACB_GREGS_VERSION;
 
-	tail = macb_tx_ring_wrap(bp->queues[0].tx_tail);
-	head = macb_tx_ring_wrap(bp->queues[0].tx_head);
+	tail = macb_tx_ring_wrap(bp, bp->queues[0].tx_tail);
+	head = macb_tx_ring_wrap(bp, bp->queues[0].tx_head);
 
 	regs_buff[0]  = macb_readl(bp, NCR);
 	regs_buff[1]  = macb_or_gem_readl(bp, NCFGR);
@@ -2214,6 +2324,56 @@ static int macb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol)
 	return 0;
 }
 
+static void macb_get_ringparam(struct net_device *netdev,
+			       struct ethtool_ringparam *ring)
+{
+	struct macb *bp = netdev_priv(netdev);
+
+	ring->rx_max_pending = MAX_RX_RING_SIZE;
+	ring->tx_max_pending = MAX_TX_RING_SIZE;
+
+	ring->rx_pending = bp->rx_ring_size;
+	ring->tx_pending = bp->tx_ring_size;
+}
+
+static int macb_set_ringparam(struct net_device *netdev,
+			      struct ethtool_ringparam *ring)
+{
+	struct macb *bp = netdev_priv(netdev);
+	u32 new_rx_size, new_tx_size;
+	unsigned int reset = 0;
+
+	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
+		return -EINVAL;
+
+	new_rx_size = clamp_t(u32, ring->rx_pending,
+			      MIN_RX_RING_SIZE, MAX_RX_RING_SIZE);
+	new_rx_size = roundup_pow_of_two(new_rx_size);
+
+	new_tx_size = clamp_t(u32, ring->tx_pending,
+			      MIN_TX_RING_SIZE, MAX_TX_RING_SIZE);
+	new_tx_size = roundup_pow_of_two(new_tx_size);
+
+	if ((new_tx_size == bp->tx_ring_size) &&
+	    (new_rx_size == bp->rx_ring_size)) {
+		/* nothing to do */
+		return 0;
+	}
+
+	if (netif_running(bp->dev)) {
+		reset = 1;
+		macb_close(bp->dev);
+	}
+
+	bp->rx_ring_size = new_rx_size;
+	bp->tx_ring_size = new_tx_size;
+
+	if (reset)
+		macb_open(bp->dev);
+
+	return 0;
+}
+
 static const struct ethtool_ops macb_ethtool_ops = {
 	.get_regs_len		= macb_get_regs_len,
 	.get_regs		= macb_get_regs,
@@ -2223,6 +2383,8 @@ static const struct ethtool_ops macb_ethtool_ops = {
 	.set_wol		= macb_set_wol,
 	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
+	.get_ringparam		= macb_get_ringparam,
+	.set_ringparam		= macb_set_ringparam,
 };
 
 static const struct ethtool_ops gem_ethtool_ops = {
@@ -2235,6 +2397,8 @@ static const struct ethtool_ops gem_ethtool_ops = {
 	.get_sset_count		= gem_get_sset_count,
 	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
+	.get_ringparam		= macb_get_ringparam,
+	.set_ringparam		= macb_set_ringparam,
 };
 
 static int macb_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
@@ -2298,6 +2462,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_poll_controller	= macb_poll_controller,
 #endif
 	.ndo_set_features	= macb_set_features,
+	.ndo_features_check	= macb_features_check,
 };
 
 /* Configure peripheral capabilities according to device tree
@@ -2429,6 +2594,9 @@ static int macb_init(struct platform_device *pdev)
 	int err;
 	u32 val;
 
+	bp->tx_ring_size = DEFAULT_TX_RING_SIZE;
+	bp->rx_ring_size = DEFAULT_RX_RING_SIZE;
+
 	/* set the queue register mapping once for all: queue0 has a special
 	 * register mapping but we don't want to test the queue index then
 	 * compute the corresponding register offset at run time.
@@ -2501,6 +2669,11 @@ static int macb_init(struct platform_device *pdev)
 
 	/* Set features */
 	dev->hw_features = NETIF_F_SG;
+
+	/* Check LSO capability */
+	if (GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6)))
+		dev->hw_features |= MACB_NETIF_LSO;
+
 	/* Checksum offload is only available on gem with packet buffer */
 	if (macb_is_gem(bp) && !(bp->caps & MACB_CAPS_FIFO_MODE))
 		dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
@@ -2800,7 +2973,6 @@ static const struct net_device_ops at91ether_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_do_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_change_mtu		= eth_change_mtu,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= at91ether_poll_controller,
 #endif
@@ -3035,6 +3207,13 @@ static int macb_probe(struct platform_device *pdev)
 		goto err_out_free_netdev;
 	}
 
+	/* MTU range: 68 - 1500 or 10240 */
+	dev->min_mtu = GEM_MTU_MIN_SIZE;
+	if (bp->caps & MACB_CAPS_JUMBO)
+		dev->max_mtu = gem_readl(bp, JML) - ETH_HLEN - ETH_FCS_LEN;
+	else
+		dev->max_mtu = ETH_DATA_LEN;
+
 	mac = of_get_mac_address(np);
 	if (mac)
 		ether_addr_copy(bp->dev->dev_addr, mac);