Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Most notable changes in here:

   1) By far the biggest accomplishment, thanks to a large range of
      contributors, is the addition of multi-send for transmit.  This is
      the result of discussions back in Chicago, and the hard work of
      several individuals.

      Now, when the ->ndo_start_xmit() method of a driver sees
      skb->xmit_more as true, it can choose to defer the doorbell
      telling the driver to start processing the new TX queue entires.

      skb->xmit_more means that the generic networking is guaranteed to
      call the driver immediately with another SKB to send.

      There is logic added to the qdisc layer to dequeue multiple
      packets at a time, and the handling mis-predicted offloads in
      software is now done with no locks held.

      Finally, pktgen is extended to have a "burst" parameter that can
      be used to test a multi-send implementation.

      Several drivers have xmit_more support: i40e, igb, ixgbe, mlx4,
      virtio_net

      Adding support is almost trivial, so export more drivers to
      support this optimization soon.

      I want to thank, in no particular or implied order, Jesper
      Dangaard Brouer, Eric Dumazet, Alexander Duyck, Tom Herbert, Jamal
      Hadi Salim, John Fastabend, Florian Westphal, Daniel Borkmann,
      David Tat, Hannes Frederic Sowa, and Rusty Russell.

   2) PTP and timestamping support in bnx2x, from Michal Kalderon.

   3) Allow adjusting the rx_copybreak threshold for a driver via
      ethtool, and add rx_copybreak support to enic driver.  From
      Govindarajulu Varadarajan.

   4) Significant enhancements to the generic PHY layer and the bcm7xxx
      driver in particular (EEE support, auto power down, etc.) from
      Florian Fainelli.

   5) Allow raw buffers to be used for flow dissection, allowing drivers
      to determine the optimal "linear pull" size for devices that DMA
      into pools of pages.  The objective is to get exactly the
      necessary amount of headers into the linear SKB area pre-pulled,
      but no more.  The new interface drivers use is eth_get_headlen().
      From WANG Cong, with driver conversions (several had their own
      by-hand duplicated implementations) by Alexander Duyck and Eric
      Dumazet.

   6) Support checksumming more smoothly and efficiently for
      encapsulations, and add "foo over UDP" facility.  From Tom
      Herbert.

   7) Add Broadcom SF2 switch driver to DSA layer, from Florian
      Fainelli.

   8) eBPF now can load programs via a system call and has an extensive
      testsuite.  Alexei Starovoitov and Daniel Borkmann.

   9) Major overhaul of the packet scheduler to use RCU in several major
      areas such as the classifiers and rate estimators.  From John
      Fastabend.

  10) Add driver for Intel FM10000 Ethernet Switch, from Alexander
      Duyck.

  11) Rearrange TCP_SKB_CB() to reduce cache line misses, from Eric
      Dumazet.

  12) Add Datacenter TCP congestion control algorithm support, From
      Florian Westphal.

  13) Reorganize sk_buff so that __copy_skb_header() is significantly
      faster.  From Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1558 commits)
  netlabel: directly return netlbl_unlabel_genl_init()
  net: add netdev_txq_bql_{enqueue, complete}_prefetchw() helpers
  net: description of dma_cookie cause make xmldocs warning
  cxgb4: clean up a type issue
  cxgb4: potential shift wrapping bug
  i40e: skb->xmit_more support
  net: fs_enet: Add NAPI TX
  net: fs_enet: Remove non NAPI RX
  r8169:add support for RTL8168EP
  net_sched: copy exts->type in tcf_exts_change()
  wimax: convert printk to pr_foo()
  af_unix: remove 0 assignment on static
  ipv6: Do not warn for informational ICMP messages, regardless of type.
  Update Intel Ethernet Driver maintainers list
  bridge: Save frag_max_size between PRE_ROUTING and POST_ROUTING
  tipc: fix bug in multicast congestion handling
  net: better IFF_XMIT_DST_RELEASE support
  net/mlx4_en: remove NETDEV_TX_BUSY
  3c59x: fix bad split of cpu_to_le32(pci_map_single())
  net: bcmgenet: fix Tx ring priority programming
  ...

1 files changed, 920 insertions, 298 deletions

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 89355a719625..87975b5dda94 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -57,21 +57,19 @@
 #include <linux/regulator/consumer.h>
 #include <linux/if_vlan.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/prefetch.h>
 
 #include <asm/cacheflush.h>
 
 #include "fec.h"
 
 static void set_multicast_list(struct net_device *ndev);
-
-#if defined(CONFIG_ARM)
-#define FEC_ALIGNMENT	0xf
-#else
-#define FEC_ALIGNMENT	0x3
-#endif
+static void fec_enet_itr_coal_init(struct net_device *ndev);
 
 #define DRIVER_NAME	"fec"
 
+#define FEC_ENET_GET_QUQUE(_x) ((_x == 0) ? 1 : ((_x == 1) ? 2 : 0))
+
 /* Pause frame feild and FIFO threshold */
 #define FEC_ENET_FCE	(1 << 5)
 #define FEC_ENET_RSEM_V	0x84
@@ -104,6 +102,22 @@ static void set_multicast_list(struct net_device *ndev);
  * ENET_TDAR[TDAR].
  */
 #define FEC_QUIRK_ERR006358            (1 << 7)
+/* ENET IP hw AVB
+ *
+ * i.MX6SX ENET IP add Audio Video Bridging (AVB) feature support.
+ * - Two class indicators on receive with configurable priority
+ * - Two class indicators and line speed timer on transmit allowing
+ *   implementation class credit based shapers externally
+ * - Additional DMA registers provisioned to allow managing up to 3
+ *   independent rings
+ */
+#define FEC_QUIRK_HAS_AVB		(1 << 8)
+/* There is a TDAR race condition for mutliQ when the software sets TDAR
+ * and the UDMA clears TDAR simultaneously or in a small window (2-4 cycles).
+ * This will cause the udma_tx and udma_tx_arbiter state machines to hang.
+ * The issue exist at i.MX6SX enet IP.
+ */
+#define FEC_QUIRK_ERR007885		(1 << 9)
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -128,6 +142,12 @@ static struct platform_device_id fec_devtype[] = {
 		.name = "mvf600-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC,
 	}, {
+		.name = "imx6sx-fec",
+		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+				FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
+				FEC_QUIRK_ERR007885,
+	}, {
 		/* sentinel */
 	}
 };
@@ -139,6 +159,7 @@ enum imx_fec_type {
 	IMX28_FEC,
 	IMX6Q_FEC,
 	MVF600_FEC,
+	IMX6SX_FEC,
 };
 
 static const struct of_device_id fec_dt_ids[] = {
@@ -147,6 +168,7 @@ static const struct of_device_id fec_dt_ids[] = {
 	{ .compatible = "fsl,imx28-fec", .data = &fec_devtype[IMX28_FEC], },
 	{ .compatible = "fsl,imx6q-fec", .data = &fec_devtype[IMX6Q_FEC], },
 	{ .compatible = "fsl,mvf600-fec", .data = &fec_devtype[MVF600_FEC], },
+	{ .compatible = "fsl,imx6sx-fec", .data = &fec_devtype[IMX6SX_FEC], },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fec_dt_ids);
@@ -175,21 +197,6 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #endif
 #endif /* CONFIG_M5272 */
 
-/* Interrupt events/masks. */
-#define FEC_ENET_HBERR	((uint)0x80000000)	/* Heartbeat error */
-#define FEC_ENET_BABR	((uint)0x40000000)	/* Babbling receiver */
-#define FEC_ENET_BABT	((uint)0x20000000)	/* Babbling transmitter */
-#define FEC_ENET_GRA	((uint)0x10000000)	/* Graceful stop complete */
-#define FEC_ENET_TXF	((uint)0x08000000)	/* Full frame transmitted */
-#define FEC_ENET_TXB	((uint)0x04000000)	/* A buffer was transmitted */
-#define FEC_ENET_RXF	((uint)0x02000000)	/* Full frame received */
-#define FEC_ENET_RXB	((uint)0x01000000)	/* A buffer was received */
-#define FEC_ENET_MII	((uint)0x00800000)	/* MII interrupt */
-#define FEC_ENET_EBERR	((uint)0x00400000)	/* SDMA bus error */
-
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
-#define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
-
 /* The FEC stores dest/src/type/vlan, data, and checksum for receive packets.
  */
 #define PKT_MAXBUF_SIZE		1522
@@ -230,6 +237,8 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #define FEC_PAUSE_FLAG_AUTONEG	0x1
 #define FEC_PAUSE_FLAG_ENABLE	0x2
 
+#define COPYBREAK_DEFAULT	256
+
 #define TSO_HEADER_SIZE		128
 /* Max number of allowed TCP segments for software TSO */
 #define FEC_MAX_TSO_SEGS	100
@@ -242,22 +251,26 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 static int mii_cnt;
 
 static inline
-struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, struct fec_enet_private *fep)
+struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp,
+				      struct fec_enet_private *fep,
+				      int queue_id)
 {
 	struct bufdesc *new_bd = bdp + 1;
 	struct bufdesc_ex *ex_new_bd = (struct bufdesc_ex *)bdp + 1;
+	struct fec_enet_priv_tx_q *txq = fep->tx_queue[queue_id];
+	struct fec_enet_priv_rx_q *rxq = fep->rx_queue[queue_id];
 	struct bufdesc_ex *ex_base;
 	struct bufdesc *base;
 	int ring_size;
 
-	if (bdp >= fep->tx_bd_base) {
-		base = fep->tx_bd_base;
-		ring_size = fep->tx_ring_size;
-		ex_base = (struct bufdesc_ex *)fep->tx_bd_base;
+	if (bdp >= txq->tx_bd_base) {
+		base = txq->tx_bd_base;
+		ring_size = txq->tx_ring_size;
+		ex_base = (struct bufdesc_ex *)txq->tx_bd_base;
 	} else {
-		base = fep->rx_bd_base;
-		ring_size = fep->rx_ring_size;
-		ex_base = (struct bufdesc_ex *)fep->rx_bd_base;
+		base = rxq->rx_bd_base;
+		ring_size = rxq->rx_ring_size;
+		ex_base = (struct bufdesc_ex *)rxq->rx_bd_base;
 	}
 
 	if (fep->bufdesc_ex)
@@ -269,22 +282,26 @@ struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, struct fec_enet_priva
 }
 
 static inline
-struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, struct fec_enet_private *fep)
+struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp,
+				      struct fec_enet_private *fep,
+				      int queue_id)
 {
 	struct bufdesc *new_bd = bdp - 1;
 	struct bufdesc_ex *ex_new_bd = (struct bufdesc_ex *)bdp - 1;
+	struct fec_enet_priv_tx_q *txq = fep->tx_queue[queue_id];
+	struct fec_enet_priv_rx_q *rxq = fep->rx_queue[queue_id];
 	struct bufdesc_ex *ex_base;
 	struct bufdesc *base;
 	int ring_size;
 
-	if (bdp >= fep->tx_bd_base) {
-		base = fep->tx_bd_base;
-		ring_size = fep->tx_ring_size;
-		ex_base = (struct bufdesc_ex *)fep->tx_bd_base;
+	if (bdp >= txq->tx_bd_base) {
+		base = txq->tx_bd_base;
+		ring_size = txq->tx_ring_size;
+		ex_base = (struct bufdesc_ex *)txq->tx_bd_base;
 	} else {
-		base = fep->rx_bd_base;
-		ring_size = fep->rx_ring_size;
-		ex_base = (struct bufdesc_ex *)fep->rx_bd_base;
+		base = rxq->rx_bd_base;
+		ring_size = rxq->rx_ring_size;
+		ex_base = (struct bufdesc_ex *)rxq->rx_bd_base;
 	}
 
 	if (fep->bufdesc_ex)
@@ -300,14 +317,15 @@ static int fec_enet_get_bd_index(struct bufdesc *base, struct bufdesc *bdp,
 	return ((const char *)bdp - (const char *)base) / fep->bufdesc_size;
 }
 
-static int fec_enet_get_free_txdesc_num(struct fec_enet_private *fep)
+static int fec_enet_get_free_txdesc_num(struct fec_enet_private *fep,
+					struct fec_enet_priv_tx_q *txq)
 {
 	int entries;
 
-	entries = ((const char *)fep->dirty_tx -
-			(const char *)fep->cur_tx) / fep->bufdesc_size - 1;
+	entries = ((const char *)txq->dirty_tx -
+			(const char *)txq->cur_tx) / fep->bufdesc_size - 1;
 
-	return entries > 0 ? entries : entries + fep->tx_ring_size;
+	return entries > 0 ? entries : entries + txq->tx_ring_size;
 }
 
 static void *swap_buffer(void *bufaddr, int len)
@@ -324,22 +342,26 @@ static void *swap_buffer(void *bufaddr, int len)
 static void fec_dump(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
-	struct bufdesc *bdp = fep->tx_bd_base;
-	unsigned int index = 0;
+	struct bufdesc *bdp;
+	struct fec_enet_priv_tx_q *txq;
+	int index = 0;
 
 	netdev_info(ndev, "TX ring dump\n");
 	pr_info("Nr     SC     addr       len  SKB\n");
 
+	txq = fep->tx_queue[0];
+	bdp = txq->tx_bd_base;
+
 	do {
 		pr_info("%3u %c%c 0x%04x 0x%08lx %4u %p\n",
 			index,
-			bdp == fep->cur_tx ? 'S' : ' ',
-			bdp == fep->dirty_tx ? 'H' : ' ',
+			bdp == txq->cur_tx ? 'S' : ' ',
+			bdp == txq->dirty_tx ? 'H' : ' ',
 			bdp->cbd_sc, bdp->cbd_bufaddr, bdp->cbd_datlen,
-			fep->tx_skbuff[index]);
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+			txq->tx_skbuff[index]);
+		bdp = fec_enet_get_nextdesc(bdp, fep, 0);
 		index++;
-	} while (bdp != fep->tx_bd_base);
+	} while (bdp != txq->tx_bd_base);
 }
 
 static inline bool is_ipv4_pkt(struct sk_buff *skb)
@@ -365,14 +387,17 @@ fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
 }
 
 static int
-fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
+fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq,
+			     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 *bdp = txq->cur_tx;
 	struct bufdesc_ex *ebdp;
 	int nr_frags = skb_shinfo(skb)->nr_frags;
+	unsigned short queue = skb_get_queue_mapping(skb);
 	int frag, frag_len;
 	unsigned short status;
 	unsigned int estatus = 0;
@@ -384,7 +409,7 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
 
 	for (frag = 0; frag < nr_frags; frag++) {
 		this_frag = &skb_shinfo(skb)->frags[frag];
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue);
 		ebdp = (struct bufdesc_ex *)bdp;
 
 		status = bdp->cbd_sc;
@@ -404,6 +429,8 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
 		}
 
 		if (fep->bufdesc_ex) {
+			if (id_entry->driver_data & FEC_QUIRK_HAS_AVB)
+				estatus |= FEC_TX_BD_FTYPE(queue);
 			if (skb->ip_summed == CHECKSUM_PARTIAL)
 				estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
 			ebdp->cbd_bdu = 0;
@@ -412,11 +439,11 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
 
 		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 ||
+		index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
+		if (((unsigned long) bufaddr) & fep->tx_align ||
 			id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
-			memcpy(fep->tx_bounce[index], bufaddr, frag_len);
-			bufaddr = fep->tx_bounce[index];
+			memcpy(txq->tx_bounce[index], bufaddr, frag_len);
+			bufaddr = txq->tx_bounce[index];
 
 			if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
 				swap_buffer(bufaddr, frag_len);
@@ -436,21 +463,22 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
 		bdp->cbd_sc = status;
 	}
 
-	fep->cur_tx = bdp;
+	txq->cur_tx = bdp;
 
 	return 0;
 
 dma_mapping_error:
-	bdp = fep->cur_tx;
+	bdp = txq->cur_tx;
 	for (i = 0; i < frag; i++) {
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue);
 		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)
+static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
+				   struct sk_buff *skb, struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	const struct platform_device_id *id_entry =
@@ -461,12 +489,13 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 	dma_addr_t addr;
 	unsigned short status;
 	unsigned short buflen;
+	unsigned short queue;
 	unsigned int estatus = 0;
 	unsigned int index;
 	int entries_free;
 	int ret;
 
-	entries_free = fec_enet_get_free_txdesc_num(fep);
+	entries_free = fec_enet_get_free_txdesc_num(fep, txq);
 	if (entries_free < MAX_SKB_FRAGS + 1) {
 		dev_kfree_skb_any(skb);
 		if (net_ratelimit())
@@ -481,7 +510,7 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 	}
 
 	/* Fill in a Tx ring entry */
-	bdp = fep->cur_tx;
+	bdp = txq->cur_tx;
 	status = bdp->cbd_sc;
 	status &= ~BD_ENET_TX_STATS;
 
@@ -489,11 +518,12 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 	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 ||
+	queue = skb_get_queue_mapping(skb);
+	index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
+	if (((unsigned long) bufaddr) & fep->tx_align ||
 		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
-		memcpy(fep->tx_bounce[index], skb->data, buflen);
-		bufaddr = fep->tx_bounce[index];
+		memcpy(txq->tx_bounce[index], skb->data, buflen);
+		bufaddr = txq->tx_bounce[index];
 
 		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
 			swap_buffer(bufaddr, buflen);
@@ -509,7 +539,7 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 	}
 
 	if (nr_frags) {
-		ret = fec_enet_txq_submit_frag_skb(skb, ndev);
+		ret = fec_enet_txq_submit_frag_skb(txq, skb, ndev);
 		if (ret)
 			return ret;
 	} else {
@@ -530,6 +560,9 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 			fep->hwts_tx_en))
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 
+		if (id_entry->driver_data & FEC_QUIRK_HAS_AVB)
+			estatus |= FEC_TX_BD_FTYPE(queue);
+
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
 
@@ -537,10 +570,10 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 		ebdp->cbd_esc = estatus;
 	}
 
-	last_bdp = fep->cur_tx;
-	index = fec_enet_get_bd_index(fep->tx_bd_base, last_bdp, fep);
+	last_bdp = txq->cur_tx;
+	index = fec_enet_get_bd_index(txq->tx_bd_base, last_bdp, fep);
 	/* Save skb pointer */
-	fep->tx_skbuff[index] = skb;
+	txq->tx_skbuff[index] = skb;
 
 	bdp->cbd_datlen = buflen;
 	bdp->cbd_bufaddr = addr;
@@ -552,27 +585,29 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
 	bdp->cbd_sc = status;
 
 	/* If this was the last BD in the ring, start at the beginning again. */
-	bdp = fec_enet_get_nextdesc(last_bdp, fep);
+	bdp = fec_enet_get_nextdesc(last_bdp, fep, queue);
 
 	skb_tx_timestamp(skb);
 
-	fep->cur_tx = bdp;
+	txq->cur_tx = bdp;
 
 	/* Trigger transmission start */
-	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+	writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue));
 
 	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)
+fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, 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;
+	struct bufdesc_ex *ebdp = container_of(bdp, struct bufdesc_ex, desc);
+	unsigned short queue = skb_get_queue_mapping(skb);
 	unsigned short status;
 	unsigned int estatus = 0;
 	dma_addr_t addr;
@@ -582,10 +617,10 @@ fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
 
 	status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
 
-	if (((unsigned long) data) & FEC_ALIGNMENT ||
+	if (((unsigned long) data) & fep->tx_align ||
 		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
-		memcpy(fep->tx_bounce[index], data, size);
-		data = fep->tx_bounce[index];
+		memcpy(txq->tx_bounce[index], data, size);
+		data = txq->tx_bounce[index];
 
 		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
 			swap_buffer(data, size);
@@ -603,6 +638,8 @@ fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
 	bdp->cbd_bufaddr = addr;
 
 	if (fep->bufdesc_ex) {
+		if (id_entry->driver_data & FEC_QUIRK_HAS_AVB)
+			estatus |= FEC_TX_BD_FTYPE(queue);
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
 		ebdp->cbd_bdu = 0;
@@ -624,14 +661,16 @@ fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
 }
 
 static int
-fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
-			struct bufdesc *bdp, int index)
+fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq,
+			 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;
+	struct bufdesc_ex *ebdp = container_of(bdp, struct bufdesc_ex, desc);
+	unsigned short queue = skb_get_queue_mapping(skb);
 	void *bufaddr;
 	unsigned long dmabuf;
 	unsigned short status;
@@ -641,12 +680,12 @@ fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
 	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 ||
+	bufaddr = txq->tso_hdrs + index * TSO_HEADER_SIZE;
+	dmabuf = txq->tso_hdrs_dma + index * TSO_HEADER_SIZE;
+	if (((unsigned long)bufaddr) & fep->tx_align ||
 		id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
-		memcpy(fep->tx_bounce[index], skb->data, hdr_len);
-		bufaddr = fep->tx_bounce[index];
+		memcpy(txq->tx_bounce[index], skb->data, hdr_len);
+		bufaddr = txq->tx_bounce[index];
 
 		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
 			swap_buffer(bufaddr, hdr_len);
@@ -665,6 +704,8 @@ fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
 	bdp->cbd_datlen = hdr_len;
 
 	if (fep->bufdesc_ex) {
+		if (id_entry->driver_data & FEC_QUIRK_HAS_AVB)
+			estatus |= FEC_TX_BD_FTYPE(queue);
 		if (skb->ip_summed == CHECKSUM_PARTIAL)
 			estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
 		ebdp->cbd_bdu = 0;
@@ -676,17 +717,22 @@ fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
 	return 0;
 }
 
-static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
+static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
+				   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 bufdesc *bdp = txq->cur_tx;
+	unsigned short queue = skb_get_queue_mapping(skb);
 	struct tso_t tso;
 	unsigned int index = 0;
 	int ret;
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
 
-	if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep)) {
+	if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep, txq)) {
 		dev_kfree_skb_any(skb);
 		if (net_ratelimit())
 			netdev_err(ndev, "NOT enough BD for TSO!\n");
@@ -706,14 +752,14 @@ static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
 	while (total_len > 0) {
 		char *hdr;
 
-		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+		index = fec_enet_get_bd_index(txq->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;
+		hdr = txq->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);
+		ret = fec_enet_txq_put_hdr_tso(txq, skb, ndev, bdp, index);
 		if (ret)
 			goto err_release;
 
@@ -721,10 +767,13 @@ static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
 			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,
+			bdp = fec_enet_get_nextdesc(bdp, fep, queue);
+			index = fec_enet_get_bd_index(txq->tx_bd_base,
+						      bdp, fep);
+			ret = fec_enet_txq_put_data_tso(txq, skb, ndev,
+							bdp, index,
+							tso.data, size,
+							size == data_left,
 							total_len == 0);
 			if (ret)
 				goto err_release;
@@ -733,17 +782,22 @@ static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
 			tso_build_data(skb, &tso, size);
 		}
 
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue);
 	}
 
 	/* Save skb pointer */
-	fep->tx_skbuff[index] = skb;
+	txq->tx_skbuff[index] = skb;
 
 	skb_tx_timestamp(skb);
-	fep->cur_tx = bdp;
+	txq->cur_tx = bdp;
 
 	/* Trigger transmission start */
-	writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+	if (!(id_entry->driver_data & FEC_QUIRK_ERR007885) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)) ||
+	    !readl(fep->hwp + FEC_X_DES_ACTIVE(queue)))
+		writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue));
 
 	return 0;
 
@@ -757,18 +811,25 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int entries_free;
+	unsigned short queue;
+	struct fec_enet_priv_tx_q *txq;
+	struct netdev_queue *nq;
 	int ret;
 
+	queue = skb_get_queue_mapping(skb);
+	txq = fep->tx_queue[queue];
+	nq = netdev_get_tx_queue(ndev, queue);
+
 	if (skb_is_gso(skb))
-		ret = fec_enet_txq_submit_tso(skb, ndev);
+		ret = fec_enet_txq_submit_tso(txq, skb, ndev);
 	else
-		ret = fec_enet_txq_submit_skb(skb, ndev);
+		ret = fec_enet_txq_submit_skb(txq, 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);
+	entries_free = fec_enet_get_free_txdesc_num(fep, txq);
+	if (entries_free <= txq->tx_stop_threshold)
+		netif_tx_stop_queue(nq);
 
 	return NETDEV_TX_OK;
 }
@@ -778,46 +839,111 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 static void fec_enet_bd_init(struct net_device *dev)
 {
 	struct fec_enet_private *fep = netdev_priv(dev);
+	struct fec_enet_priv_tx_q *txq;
+	struct fec_enet_priv_rx_q *rxq;
 	struct bufdesc *bdp;
 	unsigned int i;
+	unsigned int q;
 
-	/* Initialize the receive buffer descriptors. */
-	bdp = fep->rx_bd_base;
-	for (i = 0; i < fep->rx_ring_size; i++) {
+	for (q = 0; q < fep->num_rx_queues; q++) {
+		/* Initialize the receive buffer descriptors. */
+		rxq = fep->rx_queue[q];
+		bdp = rxq->rx_bd_base;
 
-		/* Initialize the BD for every fragment in the page. */
-		if (bdp->cbd_bufaddr)
-			bdp->cbd_sc = BD_ENET_RX_EMPTY;
-		else
+		for (i = 0; i < rxq->rx_ring_size; i++) {
+
+			/* Initialize the BD for every fragment in the page. */
+			if (bdp->cbd_bufaddr)
+				bdp->cbd_sc = BD_ENET_RX_EMPTY;
+			else
+				bdp->cbd_sc = 0;
+			bdp = fec_enet_get_nextdesc(bdp, fep, q);
+		}
+
+		/* Set the last buffer to wrap */
+		bdp = fec_enet_get_prevdesc(bdp, fep, q);
+		bdp->cbd_sc |= BD_SC_WRAP;
+
+		rxq->cur_rx = rxq->rx_bd_base;
+	}
+
+	for (q = 0; q < fep->num_tx_queues; q++) {
+		/* ...and the same for transmit */
+		txq = fep->tx_queue[q];
+		bdp = txq->tx_bd_base;
+		txq->cur_tx = bdp;
+
+		for (i = 0; i < txq->tx_ring_size; i++) {
+			/* Initialize the BD for every fragment in the page. */
 			bdp->cbd_sc = 0;
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+			if (txq->tx_skbuff[i]) {
+				dev_kfree_skb_any(txq->tx_skbuff[i]);
+				txq->tx_skbuff[i] = NULL;
+			}
+			bdp->cbd_bufaddr = 0;
+			bdp = fec_enet_get_nextdesc(bdp, fep, q);
+		}
+
+		/* Set the last buffer to wrap */
+		bdp = fec_enet_get_prevdesc(bdp, fep, q);
+		bdp->cbd_sc |= BD_SC_WRAP;
+		txq->dirty_tx = bdp;
 	}
+}
 
-	/* Set the last buffer to wrap */
-	bdp = fec_enet_get_prevdesc(bdp, fep);
-	bdp->cbd_sc |= BD_SC_WRAP;
+static void fec_enet_active_rxring(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int i;
 
-	fep->cur_rx = fep->rx_bd_base;
+	for (i = 0; i < fep->num_rx_queues; i++)
+		writel(0, fep->hwp + FEC_R_DES_ACTIVE(i));
+}
 
-	/* ...and the same for transmit */
-	bdp = fep->tx_bd_base;
-	fep->cur_tx = bdp;
-	for (i = 0; i < fep->tx_ring_size; i++) {
+static void fec_enet_enable_ring(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct fec_enet_priv_tx_q *txq;
+	struct fec_enet_priv_rx_q *rxq;
+	int i;
 
-		/* Initialize the BD for every fragment in the page. */
-		bdp->cbd_sc = 0;
-		if (fep->tx_skbuff[i]) {
-			dev_kfree_skb_any(fep->tx_skbuff[i]);
-			fep->tx_skbuff[i] = NULL;
-		}
-		bdp->cbd_bufaddr = 0;
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+	for (i = 0; i < fep->num_rx_queues; i++) {
+		rxq = fep->rx_queue[i];
+		writel(rxq->bd_dma, fep->hwp + FEC_R_DES_START(i));
+
+		/* enable DMA1/2 */
+		if (i)
+			writel(RCMR_MATCHEN | RCMR_CMP(i),
+			       fep->hwp + FEC_RCMR(i));
 	}
 
-	/* Set the last buffer to wrap */
-	bdp = fec_enet_get_prevdesc(bdp, fep);
-	bdp->cbd_sc |= BD_SC_WRAP;
-	fep->dirty_tx = bdp;
+	for (i = 0; i < fep->num_tx_queues; i++) {
+		txq = fep->tx_queue[i];
+		writel(txq->bd_dma, fep->hwp + FEC_X_DES_START(i));
+
+		/* enable DMA1/2 */
+		if (i)
+			writel(DMA_CLASS_EN | IDLE_SLOPE(i),
+			       fep->hwp + FEC_DMA_CFG(i));
+	}
+}
+
+static void fec_enet_reset_skb(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct fec_enet_priv_tx_q *txq;
+	int i, j;
+
+	for (i = 0; i < fep->num_tx_queues; i++) {
+		txq = fep->tx_queue[i];
+
+		for (j = 0; j < txq->tx_ring_size; j++) {
+			if (txq->tx_skbuff[j]) {
+				dev_kfree_skb_any(txq->tx_skbuff[j]);
+				txq->tx_skbuff[j] = NULL;
+			}
+		}
+	}
 }
 
 /*
@@ -831,15 +957,21 @@ fec_restart(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 i;
 	u32 val;
 	u32 temp_mac[2];
 	u32 rcntl = OPT_FRAME_SIZE | 0x04;
 	u32 ecntl = 0x2; /* ETHEREN */
 
-	/* Whack a reset.  We should wait for this. */
-	writel(1, fep->hwp + FEC_ECNTRL);
-	udelay(10);
+	/* Whack a reset.  We should wait for this.
+	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+	 * instead of reset MAC itself.
+	 */
+	if (id_entry && id_entry->driver_data & FEC_QUIRK_HAS_AVB) {
+		writel(0, fep->hwp + FEC_ECNTRL);
+	} else {
+		writel(1, fep->hwp + FEC_ECNTRL);
+		udelay(10);
+	}
 
 	/*
 	 * enet-mac reset will reset mac address registers too,
@@ -859,22 +991,10 @@ fec_restart(struct net_device *ndev)
 
 	fec_enet_bd_init(ndev);
 
-	/* Set receive and transmit descriptor base. */
-	writel(fep->bd_dma, fep->hwp + FEC_R_DES_START);
-	if (fep->bufdesc_ex)
-		writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc_ex)
-			* fep->rx_ring_size, fep->hwp + FEC_X_DES_START);
-	else
-		writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc)
-			* fep->rx_ring_size,	fep->hwp + FEC_X_DES_START);
-
+	fec_enet_enable_ring(ndev);
 
-	for (i = 0; i <= TX_RING_MOD_MASK; i++) {
-		if (fep->tx_skbuff[i]) {
-			dev_kfree_skb_any(fep->tx_skbuff[i]);
-			fep->tx_skbuff[i] = NULL;
-		}
-	}
+	/* Reset tx SKB buffers. */
+	fec_enet_reset_skb(ndev);
 
 	/* Enable MII mode */
 	if (fep->full_duplex == DUPLEX_FULL) {
@@ -996,13 +1116,17 @@ fec_restart(struct net_device *ndev)
 
 	/* And last, enable the transmit and receive processing */
 	writel(ecntl, fep->hwp + FEC_ECNTRL);
-	writel(0, fep->hwp + FEC_R_DES_ACTIVE);
+	fec_enet_active_rxring(ndev);
 
 	if (fep->bufdesc_ex)
 		fec_ptp_start_cyclecounter(ndev);
 
 	/* Enable interrupts we wish to service */
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
+
+	/* Init the interrupt coalescing */
+	fec_enet_itr_coal_init(ndev);
+
 }
 
 static void
@@ -1021,9 +1145,16 @@ fec_stop(struct net_device *ndev)
 			netdev_err(ndev, "Graceful transmit stop did not complete!\n");
 	}
 
-	/* Whack a reset.  We should wait for this. */
-	writel(1, fep->hwp + FEC_ECNTRL);
-	udelay(10);
+	/* Whack a reset.  We should wait for this.
+	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+	 * instead of reset MAC itself.
+	 */
+	if (id_entry && id_entry->driver_data & FEC_QUIRK_HAS_AVB) {
+		writel(0, fep->hwp + FEC_ECNTRL);
+	} else {
+		writel(1, fep->hwp + FEC_ECNTRL);
+		udelay(10);
+	}
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 
@@ -1081,37 +1212,45 @@ fec_enet_hwtstamp(struct fec_enet_private *fep, unsigned ts,
 }
 
 static void
-fec_enet_tx(struct net_device *ndev)
+fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 {
 	struct	fec_enet_private *fep;
 	struct bufdesc *bdp;
 	unsigned short status;
 	struct	sk_buff	*skb;
+	struct fec_enet_priv_tx_q *txq;
+	struct netdev_queue *nq;
 	int	index = 0;
 	int	entries_free;
 
 	fep = netdev_priv(ndev);
-	bdp = fep->dirty_tx;
+
+	queue_id = FEC_ENET_GET_QUQUE(queue_id);
+
+	txq = fep->tx_queue[queue_id];
+	/* get next bdp of dirty_tx */
+	nq = netdev_get_tx_queue(ndev, queue_id);
+	bdp = txq->dirty_tx;
 
 	/* get next bdp of dirty_tx */
-	bdp = fec_enet_get_nextdesc(bdp, fep);
+	bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
 
 	while (((status = bdp->cbd_sc) & BD_ENET_TX_READY) == 0) {
 
 		/* current queue is empty */
-		if (bdp == fep->cur_tx)
+		if (bdp == txq->cur_tx)
 			break;
 
-		index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+		index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
 
-		skb = fep->tx_skbuff[index];
-		fep->tx_skbuff[index] = NULL;
-		if (!IS_TSO_HEADER(fep, bdp->cbd_bufaddr))
+		skb = txq->tx_skbuff[index];
+		txq->tx_skbuff[index] = NULL;
+		if (!IS_TSO_HEADER(txq, 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);
+			bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
 			continue;
 		}
 
@@ -1153,23 +1292,81 @@ fec_enet_tx(struct net_device *ndev)
 		/* Free the sk buffer associated with this last transmit */
 		dev_kfree_skb_any(skb);
 
-		fep->dirty_tx = bdp;
+		txq->dirty_tx = bdp;
 
 		/* Update pointer to next buffer descriptor to be transmitted */
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
 
 		/* Since we have freed up a buffer, the ring is no longer full
 		 */
 		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);
+			entries_free = fec_enet_get_free_txdesc_num(fep, txq);
+			if (entries_free >= txq->tx_wake_threshold)
+				netif_tx_wake_queue(nq);
 		}
 	}
 
 	/* ERR006538: Keep the transmitter going */
-	if (bdp != fep->cur_tx && readl(fep->hwp + FEC_X_DES_ACTIVE) == 0)
-		writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+	if (bdp != txq->cur_tx &&
+	    readl(fep->hwp + FEC_X_DES_ACTIVE(queue_id)) == 0)
+		writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue_id));
+}
+
+static void
+fec_enet_tx(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	u16 queue_id;
+	/* First process class A queue, then Class B and Best Effort queue */
+	for_each_set_bit(queue_id, &fep->work_tx, FEC_ENET_MAX_TX_QS) {
+		clear_bit(queue_id, &fep->work_tx);
+		fec_enet_tx_queue(ndev, queue_id);
+	}
+	return;
+}
+
+static int
+fec_enet_new_rxbdp(struct net_device *ndev, struct bufdesc *bdp, struct sk_buff *skb)
+{
+	struct  fec_enet_private *fep = netdev_priv(ndev);
+	int off;
+
+	off = ((unsigned long)skb->data) & fep->rx_align;
+	if (off)
+		skb_reserve(skb, fep->rx_align + 1 - off);
+
+	bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data,
+					  FEC_ENET_RX_FRSIZE - fep->rx_align,
+					  DMA_FROM_DEVICE);
+	if (dma_mapping_error(&fep->pdev->dev, bdp->cbd_bufaddr)) {
+		if (net_ratelimit())
+			netdev_err(ndev, "Rx DMA memory map failed\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static bool fec_enet_copybreak(struct net_device *ndev, struct sk_buff **skb,
+			       struct bufdesc *bdp, u32 length)
+{
+	struct  fec_enet_private *fep = netdev_priv(ndev);
+	struct sk_buff *new_skb;
+
+	if (length > fep->rx_copybreak)
+		return false;
+
+	new_skb = netdev_alloc_skb(ndev, length);
+	if (!new_skb)
+		return false;
+
+	dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
+				FEC_ENET_RX_FRSIZE - fep->rx_align,
+				DMA_FROM_DEVICE);
+	memcpy(new_skb->data, (*skb)->data, length);
+	*skb = new_skb;
+
+	return true;
 }
 
 /* During a receive, the cur_rx points to the current incoming buffer.
@@ -1178,14 +1375,16 @@ fec_enet_tx(struct net_device *ndev)
  * effectively tossing the packet.
  */
 static int
-fec_enet_rx(struct net_device *ndev, int budget)
+fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
+	struct fec_enet_priv_rx_q *rxq;
 	struct bufdesc *bdp;
 	unsigned short status;
-	struct	sk_buff	*skb;
+	struct  sk_buff *skb_new = NULL;
+	struct  sk_buff *skb;
 	ushort	pkt_len;
 	__u8 *data;
 	int	pkt_received = 0;
@@ -1193,15 +1392,18 @@ fec_enet_rx(struct net_device *ndev, int budget)
 	bool	vlan_packet_rcvd = false;
 	u16	vlan_tag;
 	int	index = 0;
+	bool	is_copybreak;
 
 #ifdef CONFIG_M532x
 	flush_cache_all();
 #endif
+	queue_id = FEC_ENET_GET_QUQUE(queue_id);
+	rxq = fep->rx_queue[queue_id];
 
 	/* First, grab all of the stats for the incoming packet.
 	 * These get messed up if we get called due to a busy condition.
 	 */
-	bdp = fep->cur_rx;
+	bdp = rxq->cur_rx;
 
 	while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) {
 
@@ -1215,7 +1417,6 @@ fec_enet_rx(struct net_device *ndev, int budget)
 		if ((status & BD_ENET_RX_LAST) == 0)
 			netdev_err(ndev, "rcv is not +last\n");
 
-		writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
 
 		/* Check for errors. */
 		if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
@@ -1248,11 +1449,28 @@ fec_enet_rx(struct net_device *ndev, int budget)
 		pkt_len = bdp->cbd_datlen;
 		ndev->stats.rx_bytes += pkt_len;
 
-		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);
+		index = fec_enet_get_bd_index(rxq->rx_bd_base, bdp, fep);
+		skb = rxq->rx_skbuff[index];
+
+		/* The packet length includes FCS, but we don't want to
+		 * include that when passing upstream as it messes up
+		 * bridging applications.
+		 */
+		is_copybreak = fec_enet_copybreak(ndev, &skb, bdp, pkt_len - 4);
+		if (!is_copybreak) {
+			skb_new = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
+			if (unlikely(!skb_new)) {
+				ndev->stats.rx_dropped++;
+				goto rx_processing_done;
+			}
+			dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
+					 FEC_ENET_RX_FRSIZE - fep->rx_align,
+					 DMA_FROM_DEVICE);
+		}
 
+		prefetch(skb->data - NET_IP_ALIGN);
+		skb_put(skb, pkt_len - 4);
+		data = skb->data;
 		if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
 			swap_buffer(data, pkt_len);
 
@@ -1264,66 +1482,53 @@ fec_enet_rx(struct net_device *ndev, int budget)
 		/* If this is a VLAN packet remove the VLAN Tag */
 		vlan_packet_rcvd = false;
 		if ((ndev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
-		    fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) {
+			fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) {
 			/* Push and remove the vlan tag */
 			struct vlan_hdr *vlan_header =
 					(struct vlan_hdr *) (data + ETH_HLEN);
 			vlan_tag = ntohs(vlan_header->h_vlan_TCI);
-			pkt_len -= VLAN_HLEN;
 
 			vlan_packet_rcvd = true;
+
+			skb_copy_to_linear_data_offset(skb, VLAN_HLEN,
+						       data, (2 * ETH_ALEN));
+			skb_pull(skb, VLAN_HLEN);
 		}
 
-		/* This does 16 byte alignment, exactly what we need.
-		 * The packet length includes FCS, but we don't want to
-		 * include that when passing upstream as it messes up
-		 * bridging applications.
-		 */
-		skb = netdev_alloc_skb(ndev, pkt_len - 4 + NET_IP_ALIGN);
+		skb->protocol = eth_type_trans(skb, ndev);
 
-		if (unlikely(!skb)) {
-			ndev->stats.rx_dropped++;
-		} else {
-			int payload_offset = (2 * ETH_ALEN);
-			skb_reserve(skb, NET_IP_ALIGN);
-			skb_put(skb, pkt_len - 4);	/* Make room */
-
-			/* Extract the frame data without the VLAN header. */
-			skb_copy_to_linear_data(skb, data, (2 * ETH_ALEN));
-			if (vlan_packet_rcvd)
-				payload_offset = (2 * ETH_ALEN) + VLAN_HLEN;
-			skb_copy_to_linear_data_offset(skb, (2 * ETH_ALEN),
-						       data + payload_offset,
-						       pkt_len - 4 - (2 * ETH_ALEN));
-
-			skb->protocol = eth_type_trans(skb, ndev);
-
-			/* Get receive timestamp from the skb */
-			if (fep->hwts_rx_en && fep->bufdesc_ex)
-				fec_enet_hwtstamp(fep, ebdp->ts,
-						  skb_hwtstamps(skb));
-
-			if (fep->bufdesc_ex &&
-			    (fep->csum_flags & FLAG_RX_CSUM_ENABLED)) {
-				if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) {
-					/* don't check it */
-					skb->ip_summed = CHECKSUM_UNNECESSARY;
-				} else {
-					skb_checksum_none_assert(skb);
-				}
+		/* Get receive timestamp from the skb */
+		if (fep->hwts_rx_en && fep->bufdesc_ex)
+			fec_enet_hwtstamp(fep, ebdp->ts,
+					  skb_hwtstamps(skb));
+
+		if (fep->bufdesc_ex &&
+		    (fep->csum_flags & FLAG_RX_CSUM_ENABLED)) {
+			if (!(ebdp->cbd_esc & FLAG_RX_CSUM_ERROR)) {
+				/* don't check it */
+				skb->ip_summed = CHECKSUM_UNNECESSARY;
+			} else {
+				skb_checksum_none_assert(skb);
 			}
+		}
+
+		/* Handle received VLAN packets */
+		if (vlan_packet_rcvd)
+			__vlan_hwaccel_put_tag(skb,
+					       htons(ETH_P_8021Q),
+					       vlan_tag);
 
-			/* Handle received VLAN packets */
-			if (vlan_packet_rcvd)
-				__vlan_hwaccel_put_tag(skb,
-						       htons(ETH_P_8021Q),
-						       vlan_tag);
+		napi_gro_receive(&fep->napi, skb);
 
-			napi_gro_receive(&fep->napi, skb);
+		if (is_copybreak) {
+			dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr,
+						   FEC_ENET_RX_FRSIZE - fep->rx_align,
+						   DMA_FROM_DEVICE);
+		} else {
+			rxq->rx_skbuff[index] = skb_new;
+			fec_enet_new_rxbdp(ndev, bdp, skb_new);
 		}
 
-		dma_sync_single_for_device(&fep->pdev->dev, bdp->cbd_bufaddr,
-					FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
 rx_processing_done:
 		/* Clear the status flags for this buffer */
 		status &= ~BD_ENET_RX_STATS;
@@ -1341,19 +1546,56 @@ rx_processing_done:
 		}
 
 		/* Update BD pointer to next entry */
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
 
 		/* Doing this here will keep the FEC running while we process
 		 * incoming frames.  On a heavily loaded network, we should be
 		 * able to keep up at the expense of system resources.
 		 */
-		writel(0, fep->hwp + FEC_R_DES_ACTIVE);
+		writel(0, fep->hwp + FEC_R_DES_ACTIVE(queue_id));
 	}
-	fep->cur_rx = bdp;
+	rxq->cur_rx = bdp;
+	return pkt_received;
+}
 
+static int
+fec_enet_rx(struct net_device *ndev, int budget)
+{
+	int     pkt_received = 0;
+	u16	queue_id;
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
+		clear_bit(queue_id, &fep->work_rx);
+		pkt_received += fec_enet_rx_queue(ndev,
+					budget - pkt_received, queue_id);
+	}
 	return pkt_received;
 }
 
+static bool
+fec_enet_collect_events(struct fec_enet_private *fep, uint int_events)
+{
+	if (int_events == 0)
+		return false;
+
+	if (int_events & FEC_ENET_RXF)
+		fep->work_rx |= (1 << 2);
+	if (int_events & FEC_ENET_RXF_1)
+		fep->work_rx |= (1 << 0);
+	if (int_events & FEC_ENET_RXF_2)
+		fep->work_rx |= (1 << 1);
+
+	if (int_events & FEC_ENET_TXF)
+		fep->work_tx |= (1 << 2);
+	if (int_events & FEC_ENET_TXF_1)
+		fep->work_tx |= (1 << 0);
+	if (int_events & FEC_ENET_TXF_2)
+		fep->work_tx |= (1 << 1);
+
+	return true;
+}
+
 static irqreturn_t
 fec_enet_interrupt(int irq, void *dev_id)
 {
@@ -1365,6 +1607,7 @@ fec_enet_interrupt(int irq, void *dev_id)
 
 	int_events = readl(fep->hwp + FEC_IEVENT);
 	writel(int_events & ~napi_mask, fep->hwp + FEC_IEVENT);
+	fec_enet_collect_events(fep, int_events);
 
 	if (int_events & napi_mask) {
 		ret = IRQ_HANDLED;
@@ -1621,6 +1864,11 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 			}
 			mutex_unlock(&fep->ptp_clk_mutex);
 		}
+		if (fep->clk_ref) {
+			ret = clk_prepare_enable(fep->clk_ref);
+			if (ret)
+				goto failed_clk_ref;
+		}
 	} else {
 		clk_disable_unprepare(fep->clk_ahb);
 		clk_disable_unprepare(fep->clk_ipg);
@@ -1632,9 +1880,15 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 			fep->ptp_clk_on = false;
 			mutex_unlock(&fep->ptp_clk_mutex);
 		}
+		if (fep->clk_ref)
+			clk_disable_unprepare(fep->clk_ref);
 	}
 
 	return 0;
+
+failed_clk_ref:
+	if (fep->clk_ref)
+		clk_disable_unprepare(fep->clk_ref);
 failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
@@ -1674,13 +1928,13 @@ static int fec_enet_mii_probe(struct net_device *ndev)
 				continue;
 			if (dev_id--)
 				continue;
-			strncpy(mdio_bus_id, fep->mii_bus->id, MII_BUS_ID_SIZE);
+			strlcpy(mdio_bus_id, fep->mii_bus->id, MII_BUS_ID_SIZE);
 			break;
 		}
 
 		if (phy_id >= PHY_MAX_ADDR) {
 			netdev_info(ndev, "no PHY, assuming direct connection to switch\n");
-			strncpy(mdio_bus_id, "fixed-0", MII_BUS_ID_SIZE);
+			strlcpy(mdio_bus_id, "fixed-0", MII_BUS_ID_SIZE);
 			phy_id = 0;
 		}
 
@@ -2062,12 +2316,179 @@ static int fec_enet_nway_reset(struct net_device *dev)
 	return genphy_restart_aneg(phydev);
 }
 
+/* ITR clock source is enet system clock (clk_ahb).
+ * TCTT unit is cycle_ns * 64 cycle
+ * So, the ICTT value = X us / (cycle_ns * 64)
+ */
+static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return us * (fep->itr_clk_rate / 64000) / 1000;
+}
+
+/* Set threshold for interrupt coalescing */
+static void fec_enet_itr_coal_set(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 rx_itr, tx_itr;
+
+	if (!(id_entry->driver_data & FEC_QUIRK_HAS_AVB))
+		return;
+
+	/* Must be greater than zero to avoid unpredictable behavior */
+	if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
+	    !fep->tx_time_itr || !fep->tx_pkts_itr)
+		return;
+
+	/* Select enet system clock as Interrupt Coalescing
+	 * timer Clock Source
+	 */
+	rx_itr = FEC_ITR_CLK_SEL;
+	tx_itr = FEC_ITR_CLK_SEL;
+
+	/* set ICFT and ICTT */
+	rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
+	rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr));
+	tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
+	tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr));
+
+	rx_itr |= FEC_ITR_EN;
+	tx_itr |= FEC_ITR_EN;
+
+	writel(tx_itr, fep->hwp + FEC_TXIC0);
+	writel(rx_itr, fep->hwp + FEC_RXIC0);
+	writel(tx_itr, fep->hwp + FEC_TXIC1);
+	writel(rx_itr, fep->hwp + FEC_RXIC1);
+	writel(tx_itr, fep->hwp + FEC_TXIC2);
+	writel(rx_itr, fep->hwp + FEC_RXIC2);
+}
+
+static int
+fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+
+	if (!(id_entry->driver_data & FEC_QUIRK_HAS_AVB))
+		return -EOPNOTSUPP;
+
+	ec->rx_coalesce_usecs = fep->rx_time_itr;
+	ec->rx_max_coalesced_frames = fep->rx_pkts_itr;
+
+	ec->tx_coalesce_usecs = fep->tx_time_itr;
+	ec->tx_max_coalesced_frames = fep->tx_pkts_itr;
+
+	return 0;
+}
+
+static int
+fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	const struct platform_device_id *id_entry =
+				platform_get_device_id(fep->pdev);
+
+	unsigned int cycle;
+
+	if (!(id_entry->driver_data & FEC_QUIRK_HAS_AVB))
+		return -EOPNOTSUPP;
+
+	if (ec->rx_max_coalesced_frames > 255) {
+		pr_err("Rx coalesced frames exceed hardware limiation");
+		return -EINVAL;
+	}
+
+	if (ec->tx_max_coalesced_frames > 255) {
+		pr_err("Tx coalesced frame exceed hardware limiation");
+		return -EINVAL;
+	}
+
+	cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
+	if (cycle > 0xFFFF) {
+		pr_err("Rx coalesed usec exceeed hardware limiation");
+		return -EINVAL;
+	}
+
+	cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
+	if (cycle > 0xFFFF) {
+		pr_err("Rx coalesed usec exceeed hardware limiation");
+		return -EINVAL;
+	}
+
+	fep->rx_time_itr = ec->rx_coalesce_usecs;
+	fep->rx_pkts_itr = ec->rx_max_coalesced_frames;
+
+	fep->tx_time_itr = ec->tx_coalesce_usecs;
+	fep->tx_pkts_itr = ec->tx_max_coalesced_frames;
+
+	fec_enet_itr_coal_set(ndev);
+
+	return 0;
+}
+
+static void fec_enet_itr_coal_init(struct net_device *ndev)
+{
+	struct ethtool_coalesce ec;
+
+	ec.rx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
+	ec.rx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
+
+	ec.tx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
+	ec.tx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
+
+	fec_enet_set_coalesce(ndev, &ec);
+}
+
+static int fec_enet_get_tunable(struct net_device *netdev,
+				const struct ethtool_tunable *tuna,
+				void *data)
+{
+	struct fec_enet_private *fep = netdev_priv(netdev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		*(u32 *)data = fep->rx_copybreak;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int fec_enet_set_tunable(struct net_device *netdev,
+				const struct ethtool_tunable *tuna,
+				const void *data)
+{
+	struct fec_enet_private *fep = netdev_priv(netdev);
+	int ret = 0;
+
+	switch (tuna->id) {
+	case ETHTOOL_RX_COPYBREAK:
+		fep->rx_copybreak = *(u32 *)data;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
 static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_settings		= fec_enet_get_settings,
 	.set_settings		= fec_enet_set_settings,
 	.get_drvinfo		= fec_enet_get_drvinfo,
 	.nway_reset		= fec_enet_nway_reset,
 	.get_link		= ethtool_op_get_link,
+	.get_coalesce		= fec_enet_get_coalesce,
+	.set_coalesce		= fec_enet_set_coalesce,
 #ifndef CONFIG_M5272
 	.get_pauseparam		= fec_enet_get_pauseparam,
 	.set_pauseparam		= fec_enet_set_pauseparam,
@@ -2076,6 +2497,8 @@ static const struct ethtool_ops fec_enet_ethtool_ops = {
 	.get_sset_count		= fec_enet_get_sset_count,
 #endif
 	.get_ts_info		= fec_enet_get_ts_info,
+	.get_tunable		= fec_enet_get_tunable,
+	.set_tunable		= fec_enet_set_tunable,
 };
 
 static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
@@ -2105,55 +2528,136 @@ static void fec_enet_free_buffers(struct net_device *ndev)
 	unsigned int i;
 	struct sk_buff *skb;
 	struct bufdesc	*bdp;
+	struct fec_enet_priv_tx_q *txq;
+	struct fec_enet_priv_rx_q *rxq;
+	unsigned int q;
+
+	for (q = 0; q < fep->num_rx_queues; q++) {
+		rxq = fep->rx_queue[q];
+		bdp = rxq->rx_bd_base;
+		for (i = 0; i < rxq->rx_ring_size; i++) {
+			skb = rxq->rx_skbuff[i];
+			rxq->rx_skbuff[i] = NULL;
+			if (skb) {
+				dma_unmap_single(&fep->pdev->dev,
+						 bdp->cbd_bufaddr,
+						 FEC_ENET_RX_FRSIZE - fep->rx_align,
+						 DMA_FROM_DEVICE);
+				dev_kfree_skb(skb);
+			}
+			bdp = fec_enet_get_nextdesc(bdp, fep, q);
+		}
+	}
 
-	bdp = fep->rx_bd_base;
-	for (i = 0; i < fep->rx_ring_size; i++) {
-		skb = fep->rx_skbuff[i];
-		fep->rx_skbuff[i] = NULL;
-		if (skb) {
-			dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
-					FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
+	for (q = 0; q < fep->num_tx_queues; q++) {
+		txq = fep->tx_queue[q];
+		bdp = txq->tx_bd_base;
+		for (i = 0; i < txq->tx_ring_size; i++) {
+			kfree(txq->tx_bounce[i]);
+			txq->tx_bounce[i] = NULL;
+			skb = txq->tx_skbuff[i];
+			txq->tx_skbuff[i] = NULL;
 			dev_kfree_skb(skb);
 		}
-		bdp = fec_enet_get_nextdesc(bdp, fep);
 	}
+}
 
-	bdp = fep->tx_bd_base;
-	for (i = 0; i < fep->tx_ring_size; i++) {
-		kfree(fep->tx_bounce[i]);
-		fep->tx_bounce[i] = NULL;
-		skb = fep->tx_skbuff[i];
-		fep->tx_skbuff[i] = NULL;
-		dev_kfree_skb(skb);
+static void fec_enet_free_queue(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int i;
+	struct fec_enet_priv_tx_q *txq;
+
+	for (i = 0; i < fep->num_tx_queues; i++)
+		if (fep->tx_queue[i] && fep->tx_queue[i]->tso_hdrs) {
+			txq = fep->tx_queue[i];
+			dma_free_coherent(NULL,
+					  txq->tx_ring_size * TSO_HEADER_SIZE,
+					  txq->tso_hdrs,
+					  txq->tso_hdrs_dma);
+		}
+
+	for (i = 0; i < fep->num_rx_queues; i++)
+		if (fep->rx_queue[i])
+			kfree(fep->rx_queue[i]);
+
+	for (i = 0; i < fep->num_tx_queues; i++)
+		if (fep->tx_queue[i])
+			kfree(fep->tx_queue[i]);
+}
+
+static int fec_enet_alloc_queue(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	int i;
+	int ret = 0;
+	struct fec_enet_priv_tx_q *txq;
+
+	for (i = 0; i < fep->num_tx_queues; i++) {
+		txq = kzalloc(sizeof(*txq), GFP_KERNEL);
+		if (!txq) {
+			ret = -ENOMEM;
+			goto alloc_failed;
+		}
+
+		fep->tx_queue[i] = txq;
+		txq->tx_ring_size = TX_RING_SIZE;
+		fep->total_tx_ring_size += fep->tx_queue[i]->tx_ring_size;
+
+		txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
+		txq->tx_wake_threshold =
+				(txq->tx_ring_size - txq->tx_stop_threshold) / 2;
+
+		txq->tso_hdrs = dma_alloc_coherent(NULL,
+					txq->tx_ring_size * TSO_HEADER_SIZE,
+					&txq->tso_hdrs_dma,
+					GFP_KERNEL);
+		if (!txq->tso_hdrs) {
+			ret = -ENOMEM;
+			goto alloc_failed;
+		}
+	}
+
+	for (i = 0; i < fep->num_rx_queues; i++) {
+		fep->rx_queue[i] = kzalloc(sizeof(*fep->rx_queue[i]),
+					   GFP_KERNEL);
+		if (!fep->rx_queue[i]) {
+			ret = -ENOMEM;
+			goto alloc_failed;
+		}
+
+		fep->rx_queue[i]->rx_ring_size = RX_RING_SIZE;
+		fep->total_rx_ring_size += fep->rx_queue[i]->rx_ring_size;
 	}
+	return ret;
+
+alloc_failed:
+	fec_enet_free_queue(ndev);
+	return ret;
 }
 
-static int fec_enet_alloc_buffers(struct net_device *ndev)
+static int
+fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	unsigned int i;
 	struct sk_buff *skb;
 	struct bufdesc	*bdp;
+	struct fec_enet_priv_rx_q *rxq;
 
-	bdp = fep->rx_bd_base;
-	for (i = 0; i < fep->rx_ring_size; i++) {
-		dma_addr_t addr;
-
+	rxq = fep->rx_queue[queue];
+	bdp = rxq->rx_bd_base;
+	for (i = 0; i < rxq->rx_ring_size; i++) {
 		skb = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
 		if (!skb)
 			goto err_alloc;
 
-		addr = dma_map_single(&fep->pdev->dev, skb->data,
-				FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
-		if (dma_mapping_error(&fep->pdev->dev, addr)) {
+		if (fec_enet_new_rxbdp(ndev, bdp, skb)) {
 			dev_kfree_skb(skb);
-			if (net_ratelimit())
-				netdev_err(ndev, "Rx DMA memory map failed\n");
 			goto err_alloc;
 		}
 
-		fep->rx_skbuff[i] = skb;
-		bdp->cbd_bufaddr = addr;
+		rxq->rx_skbuff[i] = skb;
 		bdp->cbd_sc = BD_ENET_RX_EMPTY;
 
 		if (fep->bufdesc_ex) {
@@ -2161,17 +2665,32 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
 			ebdp->cbd_esc = BD_ENET_RX_INT;
 		}
 
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue);
 	}
 
 	/* Set the last buffer to wrap. */
-	bdp = fec_enet_get_prevdesc(bdp, fep);
+	bdp = fec_enet_get_prevdesc(bdp, fep, queue);
 	bdp->cbd_sc |= BD_SC_WRAP;
+	return 0;
 
-	bdp = fep->tx_bd_base;
-	for (i = 0; i < fep->tx_ring_size; i++) {
-		fep->tx_bounce[i] = kmalloc(FEC_ENET_TX_FRSIZE, GFP_KERNEL);
-		if (!fep->tx_bounce[i])
+ err_alloc:
+	fec_enet_free_buffers(ndev);
+	return -ENOMEM;
+}
+
+static int
+fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	unsigned int i;
+	struct bufdesc  *bdp;
+	struct fec_enet_priv_tx_q *txq;
+
+	txq = fep->tx_queue[queue];
+	bdp = txq->tx_bd_base;
+	for (i = 0; i < txq->tx_ring_size; i++) {
+		txq->tx_bounce[i] = kmalloc(FEC_ENET_TX_FRSIZE, GFP_KERNEL);
+		if (!txq->tx_bounce[i])
 			goto err_alloc;
 
 		bdp->cbd_sc = 0;
@@ -2182,11 +2701,11 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
 			ebdp->cbd_esc = BD_ENET_TX_INT;
 		}
 
-		bdp = fec_enet_get_nextdesc(bdp, fep);
+		bdp = fec_enet_get_nextdesc(bdp, fep, queue);
 	}
 
 	/* Set the last buffer to wrap. */
-	bdp = fec_enet_get_prevdesc(bdp, fep);
+	bdp = fec_enet_get_prevdesc(bdp, fep, queue);
 	bdp->cbd_sc |= BD_SC_WRAP;
 
 	return 0;
@@ -2196,6 +2715,21 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
 	return -ENOMEM;
 }
 
+static int fec_enet_alloc_buffers(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	unsigned int i;
+
+	for (i = 0; i < fep->num_rx_queues; i++)
+		if (fec_enet_alloc_rxq_buffers(ndev, i))
+			return -ENOMEM;
+
+	for (i = 0; i < fep->num_tx_queues; i++)
+		if (fec_enet_alloc_txq_buffers(ndev, i))
+			return -ENOMEM;
+	return 0;
+}
+
 static int
 fec_enet_open(struct net_device *ndev)
 {
@@ -2213,20 +2747,26 @@ fec_enet_open(struct net_device *ndev)
 
 	ret = fec_enet_alloc_buffers(ndev);
 	if (ret)
-		return ret;
+		goto err_enet_alloc;
 
 	/* Probe and connect to PHY when open the interface */
 	ret = fec_enet_mii_probe(ndev);
-	if (ret) {
-		fec_enet_free_buffers(ndev);
-		return ret;
-	}
+	if (ret)
+		goto err_enet_mii_probe;
 
 	fec_restart(ndev);
 	napi_enable(&fep->napi);
 	phy_start(fep->phy_dev);
-	netif_start_queue(ndev);
+	netif_tx_start_all_queues(ndev);
+
 	return 0;
+
+err_enet_mii_probe:
+	fec_enet_free_buffers(ndev);
+err_enet_alloc:
+	fec_enet_clk_enable(ndev, false);
+	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+	return ret;
 }
 
 static int
@@ -2399,7 +2939,7 @@ static int fec_set_features(struct net_device *netdev,
 	/* Resume the device after updates */
 	if (netif_running(netdev) && changed & FEATURES_NEED_QUIESCE) {
 		fec_restart(netdev);
-		netif_wake_queue(netdev);
+		netif_tx_wake_all_queues(netdev);
 		netif_tx_unlock_bh(netdev);
 		napi_enable(&fep->napi);
 	}
@@ -2432,39 +2972,38 @@ static int fec_enet_init(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 fec_enet_priv_tx_q *txq;
+	struct fec_enet_priv_rx_q *rxq;
 	struct bufdesc *cbd_base;
+	dma_addr_t bd_dma;
 	int bd_size;
+	unsigned int i;
 
-	/* init the tx & rx ring size */
-	fep->tx_ring_size = TX_RING_SIZE;
-	fep->rx_ring_size = RX_RING_SIZE;
+#if defined(CONFIG_ARM)
+	fep->rx_align = 0xf;
+	fep->tx_align = 0xf;
+#else
+	fep->rx_align = 0x3;
+	fep->tx_align = 0x3;
+#endif
 
-	fep->tx_stop_threshold = FEC_MAX_SKB_DESCS;
-	fep->tx_wake_threshold = (fep->tx_ring_size - fep->tx_stop_threshold) / 2;
+	fec_enet_alloc_queue(ndev);
 
 	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) *
+	bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) *
 			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, bd_size, &fep->bd_dma,
+	cbd_base = dma_alloc_coherent(NULL, bd_size, &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);
+	if (!cbd_base) {
 		return -ENOMEM;
 	}
 
-	memset(cbd_base, 0, PAGE_SIZE);
-
-	fep->netdev = ndev;
+	memset(cbd_base, 0, bd_size);
 
 	/* Get the Ethernet address */
 	fec_get_mac(ndev);
@@ -2472,12 +3011,36 @@ static int fec_enet_init(struct net_device *ndev)
 	fec_set_mac_address(ndev, NULL);
 
 	/* Set receive and transmit descriptor base. */
-	fep->rx_bd_base = cbd_base;
-	if (fep->bufdesc_ex)
-		fep->tx_bd_base = (struct bufdesc *)
-			(((struct bufdesc_ex *)cbd_base) + fep->rx_ring_size);
-	else
-		fep->tx_bd_base = cbd_base + fep->rx_ring_size;
+	for (i = 0; i < fep->num_rx_queues; i++) {
+		rxq = fep->rx_queue[i];
+		rxq->index = i;
+		rxq->rx_bd_base = (struct bufdesc *)cbd_base;
+		rxq->bd_dma = bd_dma;
+		if (fep->bufdesc_ex) {
+			bd_dma += sizeof(struct bufdesc_ex) * rxq->rx_ring_size;
+			cbd_base = (struct bufdesc *)
+				(((struct bufdesc_ex *)cbd_base) + rxq->rx_ring_size);
+		} else {
+			bd_dma += sizeof(struct bufdesc) * rxq->rx_ring_size;
+			cbd_base += rxq->rx_ring_size;
+		}
+	}
+
+	for (i = 0; i < fep->num_tx_queues; i++) {
+		txq = fep->tx_queue[i];
+		txq->index = i;
+		txq->tx_bd_base = (struct bufdesc *)cbd_base;
+		txq->bd_dma = bd_dma;
+		if (fep->bufdesc_ex) {
+			bd_dma += sizeof(struct bufdesc_ex) * txq->tx_ring_size;
+			cbd_base = (struct bufdesc *)
+			 (((struct bufdesc_ex *)cbd_base) + txq->tx_ring_size);
+		} else {
+			bd_dma += sizeof(struct bufdesc) * txq->tx_ring_size;
+			cbd_base += txq->tx_ring_size;
+		}
+	}
+
 
 	/* The FEC Ethernet specific entries in the device structure */
 	ndev->watchdog_timeo = TX_TIMEOUT;
@@ -2500,6 +3063,11 @@ static int fec_enet_init(struct net_device *ndev)
 		fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
 	}
 
+	if (id_entry->driver_data & FEC_QUIRK_HAS_AVB) {
+		fep->tx_align = 0;
+		fep->rx_align = 0x3f;
+	}
+
 	ndev->hw_features = ndev->features;
 
 	fec_restart(ndev);
@@ -2545,6 +3113,42 @@ static void fec_reset_phy(struct platform_device *pdev)
 }
 #endif /* CONFIG_OF */
 
+static void
+fec_enet_get_queue_num(struct platform_device *pdev, int *num_tx, int *num_rx)
+{
+	struct device_node *np = pdev->dev.of_node;
+	int err;
+
+	*num_tx = *num_rx = 1;
+
+	if (!np || !of_device_is_available(np))
+		return;
+
+	/* parse the num of tx and rx queues */
+	err = of_property_read_u32(np, "fsl,num-tx-queues", num_tx);
+	if (err)
+		*num_tx = 1;
+
+	err = of_property_read_u32(np, "fsl,num-rx-queues", num_rx);
+	if (err)
+		*num_rx = 1;
+
+	if (*num_tx < 1 || *num_tx > FEC_ENET_MAX_TX_QS) {
+		dev_warn(&pdev->dev, "Invalid num_tx(=%d), fall back to 1\n",
+			 *num_tx);
+		*num_tx = 1;
+		return;
+	}
+
+	if (*num_rx < 1 || *num_rx > FEC_ENET_MAX_RX_QS) {
+		dev_warn(&pdev->dev, "Invalid num_rx(=%d), fall back to 1\n",
+			 *num_rx);
+		*num_rx = 1;
+		return;
+	}
+
+}
+
 static int
 fec_probe(struct platform_device *pdev)
 {
@@ -2556,13 +3160,18 @@ fec_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id;
 	static int dev_id;
 	struct device_node *np = pdev->dev.of_node, *phy_node;
+	int num_tx_qs;
+	int num_rx_qs;
 
 	of_id = of_match_device(fec_dt_ids, &pdev->dev);
 	if (of_id)
 		pdev->id_entry = of_id->data;
 
+	fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs);
+
 	/* Init network device */
-	ndev = alloc_etherdev(sizeof(struct fec_enet_private));
+	ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private),
+				  num_tx_qs, num_rx_qs);
 	if (!ndev)
 		return -ENOMEM;
 
@@ -2571,6 +3180,9 @@ fec_probe(struct platform_device *pdev)
 	/* setup board info structure */
 	fep = netdev_priv(ndev);
 
+	fep->num_rx_queues = num_rx_qs;
+	fep->num_tx_queues = num_tx_qs;
+
 #if !defined(CONFIG_M5272)
 	/* default enable pause frame auto negotiation */
 	if (pdev->id_entry &&
@@ -2630,6 +3242,8 @@ fec_probe(struct platform_device *pdev)
 		goto failed_clk;
 	}
 
+	fep->itr_clk_rate = clk_get_rate(fep->clk_ahb);
+
 	/* enet_out is optional, depends on board */
 	fep->clk_enet_out = devm_clk_get(&pdev->dev, "enet_out");
 	if (IS_ERR(fep->clk_enet_out))
@@ -2637,6 +3251,12 @@ fec_probe(struct platform_device *pdev)
 
 	fep->ptp_clk_on = false;
 	mutex_init(&fep->ptp_clk_mutex);
+
+	/* clk_ref is optional, depends on board */
+	fep->clk_ref = devm_clk_get(&pdev->dev, "enet_clk_ref");
+	if (IS_ERR(fep->clk_ref))
+		fep->clk_ref = NULL;
+
 	fep->clk_ptp = devm_clk_get(&pdev->dev, "ptp");
 	fep->bufdesc_ex =
 		pdev->id_entry->driver_data & FEC_QUIRK_HAS_BUFDESC_EX;
@@ -2684,6 +3304,7 @@ fec_probe(struct platform_device *pdev)
 			goto failed_irq;
 	}
 
+	init_completion(&fep->mdio_done);
 	ret = fec_enet_mii_init(pdev);
 	if (ret)
 		goto failed_mii_init;
@@ -2700,6 +3321,7 @@ fec_probe(struct platform_device *pdev)
 	if (fep->bufdesc_ex && fep->ptp_clock)
 		netdev_info(ndev, "registered PHC device %d\n", fep->dev_id);
 
+	fep->rx_copybreak = COPYBREAK_DEFAULT;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
 	return 0;