diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 3b8d6d19ff05..671d080105a7 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -221,7 +221,7 @@ struct bufdesc_ex {
 #define BD_ENET_TX_RCMASK       ((ushort)0x003c)
 #define BD_ENET_TX_UN           ((ushort)0x0002)
 #define BD_ENET_TX_CSL          ((ushort)0x0001)
-#define BD_ENET_TX_STATS        ((ushort)0x03ff)        /* All status bits */
+#define BD_ENET_TX_STATS        ((ushort)0x0fff)        /* All status bits */
 
 /*enhanced buffer descriptor control/status used by Ethernet transmit*/
 #define BD_ENET_TX_INT          0x40000000
@@ -246,8 +246,8 @@ struct bufdesc_ex {
 #define RX_RING_SIZE		(FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
 #define FEC_ENET_TX_FRSIZE	2048
 #define FEC_ENET_TX_FRPPG	(PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE		16	/* Must be power of two */
-#define TX_RING_MOD_MASK	15	/*   for this to work */
+#define TX_RING_SIZE		512	/* Must be power of two */
+#define TX_RING_MOD_MASK	511	/*   for this to work */
 
 #define BD_ENET_RX_INT          0x00800000
 #define BD_ENET_RX_PTP          ((ushort)0x0400)
@@ -296,8 +296,15 @@ struct fec_enet_private {
 	/* The ring entries to be free()ed */
 	struct bufdesc	*dirty_tx;
 
+	unsigned short bufdesc_size;
 	unsigned short tx_ring_size;
 	unsigned short rx_ring_size;
+	unsigned short tx_stop_threshold;
+	unsigned short tx_wake_threshold;
+
+	/* Software TSO */
+	char *tso_hdrs;
+	dma_addr_t tso_hdrs_dma;
 
 	struct	platform_device *pdev;
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 802be17285b6..38d9d276ab8b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -36,6 +36,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <net/ip.h>
+#include <net/tso.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/icmp.h>
@@ -173,10 +174,6 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #endif
 #endif /* CONFIG_M5272 */
 
-#if (((RX_RING_SIZE + TX_RING_SIZE) * 32) > PAGE_SIZE)
-#error "FEC: descriptor ring size constants too large"
-#endif
-
 /* Interrupt events/masks. */
 #define FEC_ENET_HBERR	((uint)0x80000000)	/* Heartbeat error */
 #define FEC_ENET_BABR	((uint)0x40000000)	/* Babbling receiver */
@@ -232,6 +229,15 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_PAUSE_FLAG_AUTONEG	0x1
 #define FEC_PAUSE_FLAG_ENABLE	0x2
 
+#define TSO_HEADER_SIZE		128
+/* Max number of allowed TCP segments for software TSO */
+#define FEC_MAX_TSO_SEGS	100
+#define FEC_MAX_SKB_DESCS	(FEC_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
+
+#define IS_TSO_HEADER(txq, addr) \
+	((addr >= txq->tso_hdrs_dma) && \
+	(addr < txq->tso_hdrs_dma + txq->tx_ring_size * TSO_HEADER_SIZE))
+
 static int mii_cnt;
 
 static inline
@@ -287,6 +293,22 @@ struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, struct fec_enet_priva
 		return (new_bd < base) ? (new_bd + ring_size) : new_bd;
 }
 
+static int fec_enet_get_bd_index(struct bufdesc *base, struct bufdesc *bdp,
+				struct fec_enet_private *fep)
+{
+	return ((const char *)bdp - (const char *)base) / fep->bufdesc_size;
+}
+
+static int fec_enet_get_free_txdesc_num(struct fec_enet_private *fep)
+{
+	int entries;
+
+	entries = ((const char *)fep->dirty_tx -
+			(const char *)fep->cur_tx) / fep->bufdesc_size - 1;
+
+	return entries > 0 ? entries : entries + fep->tx_ring_size;
+}
+
 static void *swap_buffer(void *bufaddr, int len)
 {
 	int i;
@@ -308,115 +330,18 @@ fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
 	if (unlikely(skb_cow_head(skb, 0)))
 		return -1;
 
+	ip_hdr(skb)->check = 0;
 	*(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) = 0;
 
 	return 0;
 }
 
-static netdev_tx_t
-fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static void
+fec_enet_submit_work(struct bufdesc *bdp, struct fec_enet_private *fep)
 {
-	struct fec_enet_private *fep = netdev_priv(ndev);
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
-	struct bufdesc *bdp, *bdp_pre;
-	void *bufaddr;
-	unsigned short	status;
-	unsigned int index;
-
-	/* Fill in a Tx ring entry */
-	bdp = fep->cur_tx;
-
-	status = bdp->cbd_sc;
-
-	if (status & BD_ENET_TX_READY) {
-		/* Ooops.  All transmit buffers are full.  Bail out.
-		 * This should not happen, since ndev->tbusy should be set.
-		 */
-		netdev_err(ndev, "tx queue full!\n");
-		return NETDEV_TX_BUSY;
-	}
-
-	/* Protocol checksum off-load for TCP and UDP. */
-	if (fec_enet_clear_csum(skb, ndev)) {
-		dev_kfree_skb_any(skb);
-		return NETDEV_TX_OK;
-	}
-
-	/* Clear all of the status flags */
-	status &= ~BD_ENET_TX_STATS;
-
-	/* Set buffer length and buffer pointer */
-	bufaddr = skb->data;
-	bdp->cbd_datlen = skb->len;
-
-	/*
-	 * On some FEC implementations data must be aligned on
-	 * 4-byte boundaries. Use bounce buffers to copy data
-	 * and get it aligned. Ugh.
-	 */
-	if (fep->bufdesc_ex)
-		index = (struct bufdesc_ex *)bdp -
-			(struct bufdesc_ex *)fep->tx_bd_base;
-	else
-		index = bdp - fep->tx_bd_base;
-
-	if (((unsigned long) bufaddr) & FEC_ALIGNMENT) {
-		memcpy(fep->tx_bounce[index], skb->data, skb->len);
-		bufaddr = fep->tx_bounce[index];
-	}
-
-	/*
-	 * Some design made an incorrect assumption on endian mode of
-	 * the system that it's running on. As the result, driver has to
-	 * swap every frame going to and coming from the controller.
-	 */
-	if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
-		swap_buffer(bufaddr, skb->len);
-
-	/* Save skb pointer */
-	fep->tx_skbuff[index] = skb;
-
-	/* Push the data cache so the CPM does not get stale memory
-	 * data.
-	 */
-	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr,
-			skb->len, DMA_TO_DEVICE);
-	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
-		bdp->cbd_bufaddr = 0;
-		fep->tx_skbuff[index] = NULL;
-		dev_kfree_skb_any(skb);
-		if (net_ratelimit())
-			netdev_err(ndev, "Tx DMA memory map failed\n");
-		return NETDEV_TX_OK;
-	}
-
-	if (fep->bufdesc_ex) {
-
-		struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
-		ebdp->cbd_bdu = 0;
-		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
-			fep->hwts_tx_en)) {
-			ebdp->cbd_esc = (BD_ENET_TX_TS | BD_ENET_TX_INT);
-			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
-		} else {
-			ebdp->cbd_esc = BD_ENET_TX_INT;
-
-			/* Enable protocol checksum flags
-			 * We do not bother with the IP Checksum bits as they
-			 * are done by the kernel
-			 */
-			if (skb->ip_summed == CHECKSUM_PARTIAL)
-				ebdp->cbd_esc |= BD_ENET_TX_PINS;
-		}
-	}
-
-	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
-	 * it's the last BD of the frame, and to put the CRC on the end.
-	 */
-	status |= (BD_ENET_TX_READY | BD_ENET_TX_INTR
-			| BD_ENET_TX_LAST | BD_ENET_TX_TC);
-	bdp->cbd_sc = status;
+	struct bufdesc *bdp_pre;
 
 	bdp_pre = fec_enet_get_prevdesc(bdp, fep);
 	if ((id_entry->driver_data & FEC_QUIRK_ERR006358) &&
@@ -425,20 +350,415 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		schedule_delayed_work(&(fep->delay_work.delay_work),
 					msecs_to_jiffies(1));
 	}
+}
+
+static int
+fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	struct bufdesc *bdp = fep->cur_tx;
+	struct bufdesc_ex *ebdp;
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int frag, frag_len;
+	unsigned short status;
+	unsigned int estatus = 0;
+	skb_frag_t *this_frag;
+	unsigned int index;
+	void *bufaddr;
+	int i;
+
+	for (frag = 0; frag < nr_frags; frag++) {
+		this_frag = &skb_shinfo(skb)->frags[frag];
+		bdp = fec_enet_get_nextdesc(bdp, fep);
+		ebdp = (struct bufdesc_ex *)bdp;
+
+		status = bdp->cbd_sc;
+		status &= ~BD_ENET_TX_STATS;
+		status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
+		frag_len = skb_shinfo(skb)->frags[frag].size;
+
+		/* Handle the last BD specially */
+		if (frag == nr_frags - 1) {
+			status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
+			if (fep->bufdesc_ex) {
+				estatus |= BD_ENET_TX_INT;
+				if (unlikely(skb_shinfo(skb)->tx_flags &
+					SKBTX_HW_TSTAMP && fep->hwts_tx_en))
+					estatus |= BD_ENET_TX_TS;
+			}
+		}
+
+		if (fep->bufdesc_ex) {
+			if (skb->ip_summed == CHECKSUM_PARTIAL)
+				estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+			ebdp->cbd_bdu = 0;
+			ebdp->cbd_esc = estatus;
+		}
+
+		bufaddr = page_address(this_frag->page.p) + this_frag->page_offset;
+
+		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+		if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+			id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+			memcpy(fep->tx_bounce[index], bufaddr, frag_len);
+			bufaddr = fep->tx_bounce[index];
+
+			if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+				swap_buffer(bufaddr, frag_len);
+		}
+
+		bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr,
+						frag_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+			dev_kfree_skb_any(skb);
+			if (net_ratelimit())
+				netdev_err(ndev, "Tx DMA memory map failed\n");
+			goto dma_mapping_error;
+		}
+
+		bdp->cbd_datlen = frag_len;
+		bdp->cbd_sc = status;
+	}
+
+	fep->cur_tx = bdp;
+
+	return 0;
+
+dma_mapping_error:
+	bdp = fep->cur_tx;
+	for (i = 0; i < frag; i++) {
+		bdp = fec_enet_get_nextdesc(bdp, fep);
+		dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+				bdp->cbd_datlen, DMA_TO_DEVICE);
+	}
+	return NETDEV_TX_OK;
+}
+
+static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	struct bufdesc *bdp, *last_bdp;
+	void *bufaddr;
+	unsigned short status;
+	unsigned short buflen;
+	unsigned int estatus = 0;
+	unsigned int index;
+	int entries_free;
+	int ret;
+
+	entries_free = fec_enet_get_free_txdesc_num(fep);
+	if (entries_free < MAX_SKB_FRAGS + 1) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "NOT enough BD for SG!\n");
+		return NETDEV_TX_OK;
+	}
+
+	/* Protocol checksum off-load for TCP and UDP. */
+	if (fec_enet_clear_csum(skb, ndev)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Fill in a Tx ring entry */
+	bdp = fep->cur_tx;
+	status = bdp->cbd_sc;
+	status &= ~BD_ENET_TX_STATS;
+
+	/* Set buffer length and buffer pointer */
+	bufaddr = skb->data;
+	buflen = skb_headlen(skb);
+
+	index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+	if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+		memcpy(fep->tx_bounce[index], skb->data, buflen);
+		bufaddr = fep->tx_bounce[index];
+
+		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+			swap_buffer(bufaddr, buflen);
+	}
+
+	/* Push the data cache so the CPM does not get stale memory
+	 * data.
+	 */
+	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, bufaddr,
+					buflen, DMA_TO_DEVICE);
+	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "Tx DMA memory map failed\n");
+		return NETDEV_TX_OK;
+	}
+
+	if (nr_frags) {
+		ret = fec_enet_txq_submit_frag_skb(skb, ndev);
+		if (ret)
+			return ret;
+	} else {
+		status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
+		if (fep->bufdesc_ex) {
+			estatus = BD_ENET_TX_INT;
+			if (unlikely(skb_shinfo(skb)->tx_flags &
+				SKBTX_HW_TSTAMP && fep->hwts_tx_en))
+				estatus |= BD_ENET_TX_TS;
+		}
+	}
+
+	if (fep->bufdesc_ex) {
+
+		struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+
+		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+			fep->hwts_tx_en))
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = estatus;
+	}
+
+	last_bdp = fep->cur_tx;
+	index = fec_enet_get_bd_index(fep->tx_bd_base, last_bdp, fep);
+	/* Save skb pointer */
+	fep->tx_skbuff[index] = skb;
+
+	bdp->cbd_datlen = buflen;
+
+	/* Send it on its way.  Tell FEC it's ready, interrupt when done,
+	 * it's the last BD of the frame, and to put the CRC on the end.
+	 */
+	status |= (BD_ENET_TX_READY | BD_ENET_TX_TC);
+	bdp->cbd_sc = status;
+
+	fec_enet_submit_work(bdp, fep);
 
 	/* If this was the last BD in the ring, start at the beginning again. */
-	bdp = fec_enet_get_nextdesc(bdp, fep);
+	bdp = fec_enet_get_nextdesc(last_bdp, fep);
 
 	skb_tx_timestamp(skb);
 
 	fep->cur_tx = bdp;
 
-	if (fep->cur_tx == fep->dirty_tx)
-		netif_stop_queue(ndev);
+	/* Trigger transmission start */
+	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+
+	return 0;
+}
+
+static int
+fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
+			struct bufdesc *bdp, int index, char *data,
+			int size, bool last_tcp, bool is_last)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+	unsigned short status;
+	unsigned int estatus = 0;
+
+	status = bdp->cbd_sc;
+	status &= ~BD_ENET_TX_STATS;
+
+	status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
+	bdp->cbd_datlen = size;
+
+	if (((unsigned long) data) & FEC_ALIGNMENT ||
+		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+		memcpy(fep->tx_bounce[index], data, size);
+		data = fep->tx_bounce[index];
+
+		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+			swap_buffer(data, size);
+	}
+
+	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, data,
+					size, DMA_TO_DEVICE);
+	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "Tx DMA memory map failed\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	if (fep->bufdesc_ex) {
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = estatus;
+	}
+
+	/* Handle the last BD specially */
+	if (last_tcp)
+		status |= (BD_ENET_TX_LAST | BD_ENET_TX_TC);
+	if (is_last) {
+		status |= BD_ENET_TX_INTR;
+		if (fep->bufdesc_ex)
+			ebdp->cbd_esc |= BD_ENET_TX_INT;
+	}
+
+	bdp->cbd_sc = status;
+
+	return 0;
+}
+
+static int
+fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
+			struct bufdesc *bdp, int index)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
+	void *bufaddr;
+	unsigned long dmabuf;
+	unsigned short status;
+	unsigned int estatus = 0;
+
+	status = bdp->cbd_sc;
+	status &= ~BD_ENET_TX_STATS;
+	status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
+
+	bufaddr = fep->tso_hdrs + index * TSO_HEADER_SIZE;
+	dmabuf = fep->tso_hdrs_dma + index * TSO_HEADER_SIZE;
+	if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
+		memcpy(fep->tx_bounce[index], skb->data, hdr_len);
+		bufaddr = fep->tx_bounce[index];
+
+		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
+			swap_buffer(bufaddr, hdr_len);
+
+		dmabuf = dma_map_single(&fep->pdev->dev, bufaddr,
+					hdr_len, DMA_TO_DEVICE);
+		if (dma_mapping_error(&fep->pdev->dev, dmabuf)) {
+			dev_kfree_skb_any(skb);
+			if (net_ratelimit())
+				netdev_err(ndev, "Tx DMA memory map failed\n");
+			return NETDEV_TX_BUSY;
+		}
+	}
+
+	bdp->cbd_bufaddr = dmabuf;
+	bdp->cbd_datlen = hdr_len;
+
+	if (fep->bufdesc_ex) {
+		if (skb->ip_summed == CHECKSUM_PARTIAL)
+			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
+		ebdp->cbd_bdu = 0;
+		ebdp->cbd_esc = estatus;
+	}
+
+	bdp->cbd_sc = status;
+
+	return 0;
+}
+
+static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int total_len, data_left;
+	struct bufdesc *bdp = fep->cur_tx;
+	struct tso_t tso;
+	unsigned int index = 0;
+	int ret;
+
+	if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep)) {
+		dev_kfree_skb_any(skb);
+		if (net_ratelimit())
+			netdev_err(ndev, "NOT enough BD for TSO!\n");
+		return NETDEV_TX_OK;
+	}
+
+	/* Protocol checksum off-load for TCP and UDP. */
+	if (fec_enet_clear_csum(skb, ndev)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* Initialize the TSO handler, and prepare the first payload */
+	tso_start(skb, &tso);
+
+	total_len = skb->len - hdr_len;
+	while (total_len > 0) {
+		char *hdr;
+
+		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+		data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
+		total_len -= data_left;
+
+		/* prepare packet headers: MAC + IP + TCP */
+		hdr = fep->tso_hdrs + index * TSO_HEADER_SIZE;
+		tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
+		ret = fec_enet_txq_put_hdr_tso(skb, ndev, bdp, index);
+		if (ret)
+			goto err_release;
+
+		while (data_left > 0) {
+			int size;
+
+			size = min_t(int, tso.size, data_left);
+			bdp = fec_enet_get_nextdesc(bdp, fep);
+			index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+			ret = fec_enet_txq_put_data_tso(skb, ndev, bdp, index, tso.data,
+							size, size == data_left,
+							total_len == 0);
+			if (ret)
+				goto err_release;
+
+			data_left -= size;
+			tso_build_data(skb, &tso, size);
+		}
+
+		bdp = fec_enet_get_nextdesc(bdp, fep);
+	}
+
+	/* Save skb pointer */
+	fep->tx_skbuff[index] = skb;
+
+	fec_enet_submit_work(bdp, fep);
+
+	skb_tx_timestamp(skb);
+	fep->cur_tx = bdp;
 
 	/* Trigger transmission start */
 	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
 
+	return 0;
+
+err_release:
+	/* TODO: Release all used data descriptors for TSO */
+	return ret;
+}
+
+static netdev_tx_t
+fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int entries_free;
+	int ret;
+
+	if (skb_is_gso(skb))
+		ret = fec_enet_txq_submit_tso(skb, ndev);
+	else
+		ret = fec_enet_txq_submit_skb(skb, ndev);
+	if (ret)
+		return ret;
+
+	entries_free = fec_enet_get_free_txdesc_num(fep);
+	if (entries_free <= fep->tx_stop_threshold)
+		netif_stop_queue(ndev);
+
 	return NETDEV_TX_OK;
 }
 
@@ -757,6 +1077,7 @@ fec_enet_tx(struct net_device *ndev)
 	unsigned short status;
 	struct	sk_buff	*skb;
 	int	index = 0;
+	int	entries_free;
 
 	fep = netdev_priv(ndev);
 	bdp = fep->dirty_tx;
@@ -770,16 +1091,17 @@ fec_enet_tx(struct net_device *ndev)
 		if (bdp == fep->cur_tx)
 			break;
 
-		if (fep->bufdesc_ex)
-			index = (struct bufdesc_ex *)bdp -
-				(struct bufdesc_ex *)fep->tx_bd_base;
-		else
-			index = bdp - fep->tx_bd_base;
+		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
 
 		skb = fep->tx_skbuff[index];
-		dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr, skb->len,
-				DMA_TO_DEVICE);
+		if (!IS_TSO_HEADER(fep, bdp->cbd_bufaddr))
+			dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+					bdp->cbd_datlen, DMA_TO_DEVICE);
 		bdp->cbd_bufaddr = 0;
+		if (!skb) {
+			bdp = fec_enet_get_nextdesc(bdp, fep);
+			continue;
+		}
 
 		/* Check for errors. */
 		if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
@@ -798,7 +1120,7 @@ fec_enet_tx(struct net_device *ndev)
 				ndev->stats.tx_carrier_errors++;
 		} else {
 			ndev->stats.tx_packets++;
-			ndev->stats.tx_bytes += bdp->cbd_datlen;
+			ndev->stats.tx_bytes += skb->len;
 		}
 
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) &&
@@ -835,15 +1157,15 @@ fec_enet_tx(struct net_device *ndev)
 
 		/* Since we have freed up a buffer, the ring is no longer full
 		 */
-		if (fep->dirty_tx != fep->cur_tx) {
-			if (netif_queue_stopped(ndev))
+		if (netif_queue_stopped(ndev)) {
+			entries_free = fec_enet_get_free_txdesc_num(fep);
+			if (entries_free >= fep->tx_wake_threshold)
 				netif_wake_queue(ndev);
 		}
 	}
 	return;
 }
 
-
 /* During a receive, the cur_rx points to the current incoming buffer.
  * When we update through the ring, if the next incoming buffer has
  * not been given to the system, we just set the empty indicator,
@@ -921,11 +1243,7 @@ fec_enet_rx(struct net_device *ndev, int budget)
 		pkt_len = bdp->cbd_datlen;
 		ndev->stats.rx_bytes += pkt_len;
 
-		if (fep->bufdesc_ex)
-			index = (struct bufdesc_ex *)bdp -
-				(struct bufdesc_ex *)fep->rx_bd_base;
-		else
-			index = bdp - fep->rx_bd_base;
+		index = fec_enet_get_bd_index(fep->rx_bd_base, bdp, fep);
 		data = fep->rx_skbuff[index]->data;
 		dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
 					FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
@@ -2039,13 +2357,35 @@ static int fec_enet_init(struct net_device *ndev)
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
 	struct bufdesc *cbd_base;
+	int bd_size;
+
+	/* init the tx & rx ring size */
+	fep->tx_ring_size = TX_RING_SIZE;
+	fep->rx_ring_size = RX_RING_SIZE;
+
+	fep->tx_stop_threshold = FEC_MAX_SKB_DESCS;
+	fep->tx_wake_threshold = (fep->tx_ring_size - fep->tx_stop_threshold) / 2;
+
+	if (fep->bufdesc_ex)
+		fep->bufdesc_size = sizeof(struct bufdesc_ex);
+	else
+		fep->bufdesc_size = sizeof(struct bufdesc);
+	bd_size = (fep->tx_ring_size + fep->rx_ring_size) *
+			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, PAGE_SIZE, &fep->bd_dma,
+	cbd_base = dma_alloc_coherent(NULL, bd_size, &fep->bd_dma,
 				      GFP_KERNEL);
 	if (!cbd_base)
 		return -ENOMEM;
 
+	fep->tso_hdrs = dma_alloc_coherent(NULL, fep->tx_ring_size * TSO_HEADER_SIZE,
+						&fep->tso_hdrs_dma, GFP_KERNEL);
+	if (!fep->tso_hdrs) {
+		dma_free_coherent(NULL, bd_size, cbd_base, fep->bd_dma);
+		return -ENOMEM;
+	}
+
 	memset(cbd_base, 0, PAGE_SIZE);
 
 	fep->netdev = ndev;
@@ -2055,10 +2395,6 @@ static int fec_enet_init(struct net_device *ndev)
 	/* make sure MAC we just acquired is programmed into the hw */
 	fec_set_mac_address(ndev, NULL);
 
-	/* init the tx & rx ring size */
-	fep->tx_ring_size = TX_RING_SIZE;
-	fep->rx_ring_size = RX_RING_SIZE;
-
 	/* Set receive and transmit descriptor base. */
 	fep->rx_bd_base = cbd_base;
 	if (fep->bufdesc_ex)
@@ -2075,21 +2411,21 @@ static int fec_enet_init(struct net_device *ndev)
 	writel(FEC_RX_DISABLED_IMASK, fep->hwp + FEC_IMASK);
 	netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, NAPI_POLL_WEIGHT);
 
-	if (id_entry->driver_data & FEC_QUIRK_HAS_VLAN) {
+	if (id_entry->driver_data & FEC_QUIRK_HAS_VLAN)
 		/* enable hw VLAN support */
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_RX;
-		ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX;
-	}
 
 	if (id_entry->driver_data & FEC_QUIRK_HAS_CSUM) {
+		ndev->gso_max_segs = FEC_MAX_TSO_SEGS;
+
 		/* enable hw accelerator */
 		ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-				| NETIF_F_RXCSUM);
-		ndev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
-				| NETIF_F_RXCSUM);
+				| NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO);
 		fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
 	}
 
+	ndev->hw_features = ndev->features;
+
 	fec_restart(ndev, 0);
 
 	return 0;