These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

14 files changed, 901 insertions, 814 deletions

diff --git a/kernel/drivers/net/ethernet/freescale/Kconfig b/kernel/drivers/net/ethernet/freescale/Kconfig
index 25e342572..bee32a9d9 100644
--- a/kernel/drivers/net/ethernet/freescale/Kconfig
+++ b/kernel/drivers/net/ethernet/freescale/Kconfig
@@ -7,11 +7,10 @@ config NET_VENDOR_FREESCALE
 	default y
 	depends on FSL_SOC || QUICC_ENGINE || CPM1 || CPM2 || PPC_MPC512x || \
 		   M523x || M527x || M5272 || M528x || M520x || M532x || \
-		   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM)
+		   ARCH_MXC || ARCH_MXS || (PPC_MPC52xx && PPC_BESTCOMM) || \
+		   ARCH_LAYERSCAPE
 	---help---
-	  If you have a network (Ethernet) card belonging to this class, say Y
-	  and read the Ethernet-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  If you have a network (Ethernet) card belonging to this class, say Y.
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
@@ -85,12 +84,12 @@ config UGETH_TX_ON_DEMAND
 
 config GIANFAR
 	tristate "Gianfar Ethernet"
-	depends on FSL_SOC
 	select FSL_PQ_MDIO
 	select PHYLIB
 	select CRC32
 	---help---
 	  This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx,
-	  and MPC86xx family of chips, and the FEC on the 8540.
+	  and MPC86xx family of chips, the eTSEC on LS1021A and the FEC
+	  on the 8540.
 
 endif # NET_VENDOR_FREESCALE
diff --git a/kernel/drivers/net/ethernet/freescale/fec.h b/kernel/drivers/net/ethernet/freescale/fec.h
index a86af8a74..99d33e2d3 100644
--- a/kernel/drivers/net/ethernet/freescale/fec.h
+++ b/kernel/drivers/net/ethernet/freescale/fec.h
@@ -428,6 +428,8 @@ struct bufdesc_ex {
 #define FEC_QUIRK_BUG_CAPTURE		(1 << 10)
 /* Controller has only one MDIO bus */
 #define FEC_QUIRK_SINGLE_MDIO		(1 << 11)
+/* Controller supports RACC register */
+#define FEC_QUIRK_HAS_RACC		(1 << 12)
 
 struct fec_enet_priv_tx_q {
 	int index;
@@ -560,6 +562,7 @@ struct fec_enet_private {
 };
 
 void fec_ptp_init(struct platform_device *pdev);
+void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
diff --git a/kernel/drivers/net/ethernet/freescale/fec_main.c b/kernel/drivers/net/ethernet/freescale/fec_main.c
index 570390b5c..b2a32209f 100644
--- a/kernel/drivers/net/ethernet/freescale/fec_main.c
+++ b/kernel/drivers/net/ethernet/freescale/fec_main.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/pm_runtime.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
@@ -77,6 +78,7 @@ static void fec_enet_itr_coal_init(struct net_device *ndev);
 #define FEC_ENET_RAEM_V	0x8
 #define FEC_ENET_RAFL_V	0x8
 #define FEC_ENET_OPD_V	0xFFF0
+#define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -85,28 +87,30 @@ static struct platform_device_id fec_devtype[] = {
 		.driver_data = 0,
 	}, {
 		.name = "imx25-fec",
-		.driver_data = FEC_QUIRK_USE_GASKET,
+		.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx27-fec",
-		.driver_data = 0,
+		.driver_data = FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx28-fec",
 		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
-				FEC_QUIRK_SINGLE_MDIO,
+				FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "imx6q-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_ERR006358,
+				FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
+				FEC_QUIRK_HAS_RACC,
 	}, {
 		.name = "mvf600-fec",
-		.driver_data = FEC_QUIRK_ENET_MAC,
+		.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
 	}, {
 		.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 | FEC_QUIRK_BUG_CAPTURE,
+				FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
+				FEC_QUIRK_HAS_RACC,
 	}, {
 		/* sentinel */
 	}
@@ -360,7 +364,7 @@ fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
 	return 0;
 }
 
-static int
+static struct bufdesc *
 fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq,
 			     struct sk_buff *skb,
 			     struct net_device *ndev)
@@ -435,10 +439,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq,
 		bdp->cbd_sc = status;
 	}
 
-	txq->cur_tx = bdp;
-
-	return 0;
-
+	return bdp;
 dma_mapping_error:
 	bdp = txq->cur_tx;
 	for (i = 0; i < frag; i++) {
@@ -446,7 +447,7 @@ dma_mapping_error:
 		dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
 				bdp->cbd_datlen, DMA_TO_DEVICE);
 	}
-	return NETDEV_TX_OK;
+	return ERR_PTR(-ENOMEM);
 }
 
 static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
@@ -463,7 +464,6 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 	unsigned int estatus = 0;
 	unsigned int index;
 	int entries_free;
-	int ret;
 
 	entries_free = fec_enet_get_free_txdesc_num(fep, txq);
 	if (entries_free < MAX_SKB_FRAGS + 1) {
@@ -481,6 +481,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	/* Fill in a Tx ring entry */
 	bdp = txq->cur_tx;
+	last_bdp = bdp;
 	status = bdp->cbd_sc;
 	status &= ~BD_ENET_TX_STATS;
 
@@ -509,9 +510,9 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 	}
 
 	if (nr_frags) {
-		ret = fec_enet_txq_submit_frag_skb(txq, skb, ndev);
-		if (ret)
-			return ret;
+		last_bdp = fec_enet_txq_submit_frag_skb(txq, skb, ndev);
+		if (IS_ERR(last_bdp))
+			return NETDEV_TX_OK;
 	} else {
 		status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
 		if (fep->bufdesc_ex) {
@@ -540,7 +541,6 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 		ebdp->cbd_esc = estatus;
 	}
 
-	last_bdp = txq->cur_tx;
 	index = fec_enet_get_bd_index(txq->tx_bd_base, last_bdp, fep);
 	/* Save skb pointer */
 	txq->tx_skbuff[index] = skb;
@@ -559,6 +559,10 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
 
 	skb_tx_timestamp(skb);
 
+	/* Make sure the update to bdp and tx_skbuff are performed before
+	 * cur_tx.
+	 */
+	wmb();
 	txq->cur_tx = bdp;
 
 	/* Trigger transmission start */
@@ -970,13 +974,15 @@ fec_restart(struct net_device *ndev)
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 
 #if !defined(CONFIG_M5272)
-	/* set RX checksum */
-	val = readl(fep->hwp + FEC_RACC);
-	if (fep->csum_flags & FLAG_RX_CSUM_ENABLED)
-		val |= FEC_RACC_OPTIONS;
-	else
-		val &= ~FEC_RACC_OPTIONS;
-	writel(val, fep->hwp + FEC_RACC);
+	if (fep->quirks & FEC_QUIRK_HAS_RACC) {
+		/* set RX checksum */
+		val = readl(fep->hwp + FEC_RACC);
+		if (fep->csum_flags & FLAG_RX_CSUM_ENABLED)
+			val |= FEC_RACC_OPTIONS;
+		else
+			val &= ~FEC_RACC_OPTIONS;
+		writel(val, fep->hwp + FEC_RACC);
+	}
 #endif
 
 	/*
@@ -1212,10 +1218,11 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 	/* get next bdp of dirty_tx */
 	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 == txq->cur_tx)
+	while (bdp != READ_ONCE(txq->cur_tx)) {
+		/* Order the load of cur_tx and cbd_sc */
+		rmb();
+		status = READ_ONCE(bdp->cbd_sc);
+		if (status & BD_ENET_TX_READY)
 			break;
 
 		index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
@@ -1269,6 +1276,10 @@ fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
 		/* Free the sk buffer associated with this last transmit */
 		dev_kfree_skb_any(skb);
 
+		/* Make sure the update to bdp and tx_skbuff are performed
+		 * before dirty_tx
+		 */
+		wmb();
 		txq->dirty_tx = bdp;
 
 		/* Update pointer to next buffer descriptor to be transmitted */
@@ -1764,10 +1775,16 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		return ret;
 
 	fep->mii_timeout = 0;
-	init_completion(&fep->mdio_done);
+	reinit_completion(&fep->mdio_done);
 
 	/* start a read op */
 	writel(FEC_MMFR_ST | FEC_MMFR_OP_READ |
@@ -1780,21 +1797,35 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO read timeout\n");
-		return -ETIMEDOUT;
+		ret = -ETIMEDOUT;
+		goto out;
 	}
 
-	/* return value */
-	return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+	ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+
+out:
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			   u16 value)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0)
+		return ret;
+	else
+		ret = 0;
 
 	fep->mii_timeout = 0;
-	init_completion(&fep->mdio_done);
+	reinit_completion(&fep->mdio_done);
 
 	/* start a write op */
 	writel(FEC_MMFR_ST | FEC_MMFR_OP_WRITE |
@@ -1808,10 +1839,13 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO write timeout\n");
-		return -ETIMEDOUT;
+		ret  = -ETIMEDOUT;
 	}
 
-	return 0;
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
@@ -1823,9 +1857,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 		ret = clk_prepare_enable(fep->clk_ahb);
 		if (ret)
 			return ret;
-		ret = clk_prepare_enable(fep->clk_ipg);
-		if (ret)
-			goto failed_clk_ipg;
 		if (fep->clk_enet_out) {
 			ret = clk_prepare_enable(fep->clk_enet_out);
 			if (ret)
@@ -1849,7 +1880,6 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
 		}
 	} else {
 		clk_disable_unprepare(fep->clk_ahb);
-		clk_disable_unprepare(fep->clk_ipg);
 		if (fep->clk_enet_out)
 			clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
@@ -1871,8 +1901,6 @@ failed_clk_ptp:
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
 failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
 		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
@@ -2119,6 +2147,82 @@ static void fec_enet_get_drvinfo(struct net_device *ndev,
 	strlcpy(info->bus_info, dev_name(&ndev->dev), sizeof(info->bus_info));
 }
 
+static int fec_enet_get_regs_len(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	struct resource *r;
+	int s = 0;
+
+	r = platform_get_resource(fep->pdev, IORESOURCE_MEM, 0);
+	if (r)
+		s = resource_size(r);
+
+	return s;
+}
+
+/* List of registers that can be safety be read to dump them with ethtool */
+#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
+	defined(CONFIG_M520x) || defined(CONFIG_M532x) ||		\
+	defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28)
+static u32 fec_enet_register_offset[] = {
+	FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
+	FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
+	FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_TXIC1,
+	FEC_TXIC2, FEC_RXIC0, FEC_RXIC1, FEC_RXIC2, FEC_HASH_TABLE_HIGH,
+	FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH, FEC_GRP_HASH_TABLE_LOW,
+	FEC_X_WMRK, FEC_R_BOUND, FEC_R_FSTART, FEC_R_DES_START_1,
+	FEC_X_DES_START_1, FEC_R_BUFF_SIZE_1, FEC_R_DES_START_2,
+	FEC_X_DES_START_2, FEC_R_BUFF_SIZE_2, FEC_R_DES_START_0,
+	FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM,
+	FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC, FEC_RCMR_1, FEC_RCMR_2,
+	FEC_DMA_CFG_1, FEC_DMA_CFG_2, FEC_R_DES_ACTIVE_1, FEC_X_DES_ACTIVE_1,
+	FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_2, FEC_QOS_SCHEME,
+	RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT,
+	RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG,
+	RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255,
+	RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047,
+	RMON_T_P_GTE2048, RMON_T_OCTETS,
+	IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF,
+	IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE,
+	IEEE_T_FDXFC, IEEE_T_OCTETS_OK,
+	RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN,
+	RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB,
+	RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255,
+	RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047,
+	RMON_R_P_GTE2048, RMON_R_OCTETS,
+	IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
+	IEEE_R_FDXFC, IEEE_R_OCTETS_OK
+};
+#else
+static u32 fec_enet_register_offset[] = {
+	FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0,
+	FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0,
+	FEC_X_DES_ACTIVE_1, FEC_X_DES_ACTIVE_2, FEC_MII_DATA, FEC_MII_SPEED,
+	FEC_R_BOUND, FEC_R_FSTART, FEC_X_WMRK, FEC_X_FSTART, FEC_R_CNTRL,
+	FEC_MAX_FRM_LEN, FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH,
+	FEC_GRP_HASH_TABLE_HIGH, FEC_GRP_HASH_TABLE_LOW, FEC_R_DES_START_0,
+	FEC_R_DES_START_1, FEC_R_DES_START_2, FEC_X_DES_START_0,
+	FEC_X_DES_START_1, FEC_X_DES_START_2, FEC_R_BUFF_SIZE_0,
+	FEC_R_BUFF_SIZE_1, FEC_R_BUFF_SIZE_2
+};
+#endif
+
+static void fec_enet_get_regs(struct net_device *ndev,
+			      struct ethtool_regs *regs, void *regbuf)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+	u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
+	u32 *buf = (u32 *)regbuf;
+	u32 i, off;
+
+	memset(buf, 0, regs->len);
+
+	for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
+		off = fec_enet_register_offset[i] / 4;
+		buf[off] = readl(&theregs[off]);
+	}
+}
+
 static int fec_enet_get_ts_info(struct net_device *ndev,
 				struct ethtool_ts_info *info)
 {
@@ -2516,6 +2620,8 @@ 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,
+	.get_regs_len		= fec_enet_get_regs_len,
+	.get_regs		= fec_enet_get_regs,
 	.nway_reset		= fec_enet_nway_reset,
 	.get_link		= ethtool_op_get_link,
 	.get_coalesce		= fec_enet_get_coalesce,
@@ -2766,10 +2872,14 @@ fec_enet_open(struct net_device *ndev)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int ret;
 
+	ret = pm_runtime_get_sync(&fep->pdev->dev);
+	if (ret < 0)
+		return ret;
+
 	pinctrl_pm_select_default_state(&fep->pdev->dev);
 	ret = fec_enet_clk_enable(ndev, true);
 	if (ret)
-		return ret;
+		goto clk_enable;
 
 	/* I should reset the ring buffers here, but I don't yet know
 	 * a simple way to do that.
@@ -2779,12 +2889,14 @@ fec_enet_open(struct net_device *ndev)
 	if (ret)
 		goto err_enet_alloc;
 
+	/* Init MAC prior to mii bus probe */
+	fec_restart(ndev);
+
 	/* Probe and connect to PHY when open the interface */
 	ret = fec_enet_mii_probe(ndev);
 	if (ret)
 		goto err_enet_mii_probe;
 
-	fec_restart(ndev);
 	napi_enable(&fep->napi);
 	phy_start(fep->phy_dev);
 	netif_tx_start_all_queues(ndev);
@@ -2798,6 +2910,9 @@ err_enet_mii_probe:
 	fec_enet_free_buffers(ndev);
 err_enet_alloc:
 	fec_enet_clk_enable(ndev, false);
+clk_enable:
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	return ret;
 }
@@ -2820,6 +2935,9 @@ fec_enet_close(struct net_device *ndev)
 
 	fec_enet_clk_enable(ndev, false);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
+
 	fec_enet_free_buffers(ndev);
 
 	return 0;
@@ -2913,6 +3031,14 @@ fec_set_mac_address(struct net_device *ndev, void *p)
 		memcpy(ndev->dev_addr, addr->sa_data, ndev->addr_len);
 	}
 
+	/* Add netif status check here to avoid system hang in below case:
+	 * ifconfig ethx down; ifconfig ethx hw ether xx:xx:xx:xx:xx:xx;
+	 * After ethx down, fec all clocks are gated off and then register
+	 * access causes system hang.
+	 */
+	if (!netif_running(ndev))
+		return 0;
+
 	writel(ndev->dev_addr[3] | (ndev->dev_addr[2] << 8) |
 		(ndev->dev_addr[1] << 16) | (ndev->dev_addr[0] << 24),
 		fep->hwp + FEC_ADDR_LOW);
@@ -2944,7 +3070,6 @@ static void fec_poll_controller(struct net_device *dev)
 }
 #endif
 
-#define FEATURES_NEED_QUIESCE NETIF_F_RXCSUM
 static inline void fec_enet_set_netdev_features(struct net_device *netdev,
 	netdev_features_t features)
 {
@@ -2968,7 +3093,7 @@ static int fec_set_features(struct net_device *netdev,
 	struct fec_enet_private *fep = netdev_priv(netdev);
 	netdev_features_t changed = features ^ netdev->features;
 
-	if (netif_running(netdev) && changed & FEATURES_NEED_QUIESCE) {
+	if (netif_running(netdev) && changed & NETIF_F_RXCSUM) {
 		napi_disable(&fep->napi);
 		netif_tx_lock_bh(netdev);
 		fec_stop(netdev);
@@ -3032,8 +3157,8 @@ static int fec_enet_init(struct net_device *ndev)
 			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
-				      GFP_KERNEL);
+	cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
+				       GFP_KERNEL);
 	if (!cbd_base) {
 		return -ENOMEM;
 	}
@@ -3136,7 +3261,7 @@ static void fec_reset_phy(struct platform_device *pdev)
 		return;
 	}
 	msleep(msec);
-	gpio_set_value(phy_reset, 1);
+	gpio_set_value_cansleep(phy_reset, 1);
 }
 #else /* CONFIG_OF */
 static void fec_reset_phy(struct platform_device *pdev)
@@ -3305,6 +3430,10 @@ fec_probe(struct platform_device *pdev)
 	if (ret)
 		goto failed_clk;
 
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
 	fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
 		ret = regulator_enable(fep->reg_phy);
@@ -3317,6 +3446,12 @@ fec_probe(struct platform_device *pdev)
 		fep->reg_phy = NULL;
 	}
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	fec_reset_phy(pdev);
 
 	if (fep->bufdesc_ex)
@@ -3364,6 +3499,10 @@ fec_probe(struct platform_device *pdev)
 
 	fep->rx_copybreak = COPYBREAK_DEFAULT;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
 	return 0;
 
 failed_register:
@@ -3371,9 +3510,12 @@ failed_register:
 failed_mii_init:
 failed_irq:
 failed_init:
+	fec_ptp_stop(pdev);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
 failed_phy:
@@ -3390,14 +3532,12 @@ fec_drv_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
-	cancel_delayed_work_sync(&fep->time_keep);
 	cancel_work_sync(&fep->tx_timeout_work);
+	fec_ptp_stop(pdev);
 	unregister_netdev(ndev);
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
-	if (fep->ptp_clock)
-		ptp_clock_unregister(fep->ptp_clock);
 	of_node_put(fep->phy_node);
 	free_netdev(ndev);
 
@@ -3485,7 +3625,28 @@ failed_clk:
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume);
+static int __maybe_unused fec_runtime_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	clk_disable_unprepare(fep->clk_ipg);
+
+	return 0;
+}
+
+static int __maybe_unused fec_runtime_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return clk_prepare_enable(fep->clk_ipg);
+}
+
+static const struct dev_pm_ops fec_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
+	SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
+};
 
 static struct platform_driver fec_driver = {
 	.driver	= {
diff --git a/kernel/drivers/net/ethernet/freescale/fec_ptp.c b/kernel/drivers/net/ethernet/freescale/fec_ptp.c
index a583d89b1..f9e74461b 100644
--- a/kernel/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/kernel/drivers/net/ethernet/freescale/fec_ptp.c
@@ -112,9 +112,8 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 	unsigned long flags;
 	u32 val, tempval;
 	int inc;
-	struct timespec ts;
+	struct timespec64 ts;
 	u64 ns;
-	u32 remainder;
 	val = 0;
 
 	if (!(fep->hwts_tx_en || fep->hwts_rx_en)) {
@@ -163,8 +162,7 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 		tempval = readl(fep->hwp + FEC_ATIME);
 		/* Convert the ptp local counter to 1588 timestamp */
 		ns = timecounter_cyc2time(&fep->tc, tempval);
-		ts.tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder);
-		ts.tv_nsec = remainder;
+		ts = ns_to_timespec64(ns);
 
 		/* The tempval is  less than 3 seconds, and  so val is less than
 		 * 4 seconds. No overflow for 32bit calculation.
@@ -353,6 +351,7 @@ static int fec_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
 	tmp = readl(fep->hwp + FEC_ATIME_INC) & FEC_T_INC_MASK;
 	tmp |= corr_ns << FEC_T_INC_CORR_OFFSET;
 	writel(tmp, fep->hwp + FEC_ATIME_INC);
+	corr_period = corr_period > 1 ? corr_period - 1 : corr_period;
 	writel(corr_period, fep->hwp + FEC_ATIME_CORR);
 	/* dummy read to update the timer. */
 	timecounter_read(&fep->tc);
@@ -505,12 +504,6 @@ int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr)
 		break;
 
 	default:
-		/*
-		 * register RXMTRL must be set in order to do V1 packets,
-		 * therefore it is not possible to time stamp both V1 Sync and
-		 * Delay_Req messages and hardware does not support
-		 * timestamping all packets => return error
-		 */
 		fep->hwts_rx_en = 1;
 		config.rx_filter = HWTSTAMP_FILTER_ALL;
 		break;
@@ -603,6 +596,16 @@ void fec_ptp_init(struct platform_device *pdev)
 	schedule_delayed_work(&fep->time_keep, HZ);
 }
 
+void fec_ptp_stop(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	cancel_delayed_work_sync(&fep->time_keep);
+	if (fep->ptp_clock)
+		ptp_clock_unregister(fep->ptp_clock);
+}
+
 /**
  * fec_ptp_check_pps_event
  * @fep: the fec_enet_private structure handle
diff --git a/kernel/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/kernel/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 9b3639eae..cf8e54652 100644
--- a/kernel/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/kernel/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -86,7 +86,7 @@ static int fs_enet_rx_napi(struct napi_struct *napi, int budget)
 	struct net_device *dev = fep->ndev;
 	const struct fs_platform_info *fpi = fep->fpi;
 	cbd_t __iomem *bdp;
-	struct sk_buff *skb, *skbn, *skbt;
+	struct sk_buff *skb, *skbn;
 	int received = 0;
 	u16 pkt_len, sc;
 	int curidx;
@@ -161,10 +161,7 @@ static int fs_enet_rx_napi(struct napi_struct *napi, int budget)
 					skb_reserve(skbn, 2);	/* align IP header */
 					skb_copy_from_linear_data(skb,
 						      skbn->data, pkt_len);
-					/* swap */
-					skbt = skb;
-					skb = skbn;
-					skbn = skbt;
+					swap(skb, skbn);
 				}
 			} else {
 				skbn = netdev_alloc_skb(dev, ENET_RX_FRSIZE);
@@ -490,6 +487,9 @@ static struct sk_buff *tx_skb_align_workaround(struct net_device *dev,
 {
 	struct sk_buff *new_skb;
 
+	if (skb_linearize(skb))
+		return NULL;
+
 	/* Alloc new skb */
 	new_skb = netdev_alloc_skb(dev, skb->len + 4);
 	if (!new_skb)
@@ -515,12 +515,27 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	cbd_t __iomem *bdp;
 	int curidx;
 	u16 sc;
-	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int nr_frags;
 	skb_frag_t *frag;
 	int len;
-
 #ifdef CONFIG_FS_ENET_MPC5121_FEC
-	if (((unsigned long)skb->data) & 0x3) {
+	int is_aligned = 1;
+	int i;
+
+	if (!IS_ALIGNED((unsigned long)skb->data, 4)) {
+		is_aligned = 0;
+	} else {
+		nr_frags = skb_shinfo(skb)->nr_frags;
+		frag = skb_shinfo(skb)->frags;
+		for (i = 0; i < nr_frags; i++, frag++) {
+			if (!IS_ALIGNED(frag->page_offset, 4)) {
+				is_aligned = 0;
+				break;
+			}
+		}
+	}
+
+	if (!is_aligned) {
 		skb = tx_skb_align_workaround(dev, skb);
 		if (!skb) {
 			/*
@@ -532,6 +547,7 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 #endif
+
 	spin_lock(&fep->tx_lock);
 
 	/*
@@ -539,6 +555,7 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	bdp = fep->cur_tx;
 
+	nr_frags = skb_shinfo(skb)->nr_frags;
 	if (fep->tx_free <= nr_frags || (CBDR_SC(bdp) & BD_ENET_TX_READY)) {
 		netif_stop_queue(dev);
 		spin_unlock(&fep->tx_lock);
@@ -569,7 +586,8 @@ static int fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	frag = skb_shinfo(skb)->frags;
 	while (nr_frags) {
 		CBDC_SC(bdp,
-			BD_ENET_TX_STATS | BD_ENET_TX_LAST | BD_ENET_TX_TC);
+			BD_ENET_TX_STATS | BD_ENET_TX_INTR | BD_ENET_TX_LAST |
+			BD_ENET_TX_TC);
 		CBDS_SC(bdp, BD_ENET_TX_READY);
 
 		if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0)
diff --git a/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c b/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
index 08f5b911d..52e0091b4 100644
--- a/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
+++ b/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fcc.c
@@ -552,7 +552,7 @@ static void tx_restart(struct net_device *dev)
 	cbd_t __iomem *prev_bd;
 	cbd_t __iomem *last_tx_bd;
 
-	last_tx_bd = fep->tx_bd_base + (fpi->tx_ring * sizeof(cbd_t));
+	last_tx_bd = fep->tx_bd_base + ((fpi->tx_ring - 1) * sizeof(cbd_t));
 
 	/* get the current bd held in TBPTR  and scan back from this point */
 	recheck_bd = curr_tbptr = (cbd_t __iomem *)
diff --git a/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index b34214e2d..016743e35 100644
--- a/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/kernel/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -110,7 +110,7 @@ static int do_pd_setup(struct fs_enet_private *fep)
 }
 
 #define FEC_NAPI_RX_EVENT_MSK	(FEC_ENET_RXF | FEC_ENET_RXB)
-#define FEC_NAPI_TX_EVENT_MSK	(FEC_ENET_TXF | FEC_ENET_TXB)
+#define FEC_NAPI_TX_EVENT_MSK	(FEC_ENET_TXF)
 #define FEC_RX_EVENT		(FEC_ENET_RXF)
 #define FEC_TX_EVENT		(FEC_ENET_TXF)
 #define FEC_ERR_EVENT_MSK	(FEC_ENET_HBERR | FEC_ENET_BABR | \
diff --git a/kernel/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/kernel/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 3c40f6b99..40071dad1 100644
--- a/kernel/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/kernel/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -198,11 +198,13 @@ static int fsl_pq_mdio_reset(struct mii_bus *bus)
 
 #if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
 /*
+ * Return the TBIPA address, starting from the address
+ * of the mapped GFAR MDIO registers (struct gfar)
  * This is mildly evil, but so is our hardware for doing this.
  * Also, we have to cast back to struct gfar because of
  * definition weirdness done in gianfar.h.
  */
-static uint32_t __iomem *get_gfar_tbipa(void __iomem *p)
+static uint32_t __iomem *get_gfar_tbipa_from_mdio(void __iomem *p)
 {
 	struct gfar __iomem *enet_regs = p;
 
@@ -210,6 +212,15 @@ static uint32_t __iomem *get_gfar_tbipa(void __iomem *p)
 }
 
 /*
+ * Return the TBIPA address, starting from the address
+ * of the mapped GFAR MII registers (gfar_mii_regs[] within struct gfar)
+ */
+static uint32_t __iomem *get_gfar_tbipa_from_mii(void __iomem *p)
+{
+	return get_gfar_tbipa_from_mdio(container_of(p, struct gfar, gfar_mii_regs));
+}
+
+/*
  * Return the TBIPAR address for an eTSEC2 node
  */
 static uint32_t __iomem *get_etsec_tbipa(void __iomem *p)
@@ -220,11 +231,12 @@ static uint32_t __iomem *get_etsec_tbipa(void __iomem *p)
 
 #if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
 /*
- * Return the TBIPAR address for a QE MDIO node
+ * Return the TBIPAR address for a QE MDIO node, starting from the address
+ * of the mapped MII registers (struct fsl_pq_mii)
  */
 static uint32_t __iomem *get_ucc_tbipa(void __iomem *p)
 {
-	struct fsl_pq_mdio __iomem *mdio = p;
+	struct fsl_pq_mdio __iomem *mdio = container_of(p, struct fsl_pq_mdio, mii);
 
 	return &mdio->utbipar;
 }
@@ -300,14 +312,14 @@ static const struct of_device_id fsl_pq_mdio_match[] = {
 		.compatible = "fsl,gianfar-tbi",
 		.data = &(struct fsl_pq_mdio_data) {
 			.mii_offset = 0,
-			.get_tbipa = get_gfar_tbipa,
+			.get_tbipa = get_gfar_tbipa_from_mii,
 		},
 	},
 	{
 		.compatible = "fsl,gianfar-mdio",
 		.data = &(struct fsl_pq_mdio_data) {
 			.mii_offset = 0,
-			.get_tbipa = get_gfar_tbipa,
+			.get_tbipa = get_gfar_tbipa_from_mii,
 		},
 	},
 	{
@@ -315,7 +327,7 @@ static const struct of_device_id fsl_pq_mdio_match[] = {
 		.compatible = "gianfar",
 		.data = &(struct fsl_pq_mdio_data) {
 			.mii_offset = offsetof(struct fsl_pq_mdio, mii),
-			.get_tbipa = get_gfar_tbipa,
+			.get_tbipa = get_gfar_tbipa_from_mdio,
 		},
 	},
 	{
@@ -445,6 +457,16 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev)
 
 			tbipa = data->get_tbipa(priv->map);
 
+			/*
+			 * Add consistency check to make sure TBI is contained
+			 * within the mapped range (not because we would get a
+			 * segfault, rather to catch bugs in computing TBI
+			 * address). Print error message but continue anyway.
+			 */
+			if ((void *)tbipa > priv->map + resource_size(&res) - 4)
+				dev_err(&pdev->dev, "invalid register map (should be at least 0x%04zx to contain TBI address)\n",
+					((void *)tbipa - priv->map) + 4);
+
 			iowrite32be(be32_to_cpup(prop), tbipa);
 		}
 	}
diff --git a/kernel/drivers/net/ethernet/freescale/gianfar.c b/kernel/drivers/net/ethernet/freescale/gianfar.c
index e616b71d5..3e233d924 100644
--- a/kernel/drivers/net/ethernet/freescale/gianfar.c
+++ b/kernel/drivers/net/ethernet/freescale/gianfar.c
@@ -107,17 +107,17 @@
 
 #include "gianfar.h"
 
-#define TX_TIMEOUT      (1*HZ)
+#define TX_TIMEOUT      (5*HZ)
 
-const char gfar_driver_version[] = "1.3";
+const char gfar_driver_version[] = "2.0";
 
 static int gfar_enet_open(struct net_device *dev);
 static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev);
 static void gfar_reset_task(struct work_struct *work);
 static void gfar_timeout(struct net_device *dev);
 static int gfar_close(struct net_device *dev);
-static struct sk_buff *gfar_new_skb(struct net_device *dev,
-				    dma_addr_t *bufaddr);
+static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue,
+				int alloc_cnt);
 static int gfar_set_mac_address(struct net_device *dev);
 static int gfar_change_mtu(struct net_device *dev, int new_mtu);
 static irqreturn_t gfar_error(int irq, void *dev_id);
@@ -141,8 +141,7 @@ static void gfar_netpoll(struct net_device *dev);
 #endif
 int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit);
 static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue);
-static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
-			       int amount_pull, struct napi_struct *napi);
+static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb);
 static void gfar_halt_nodisable(struct gfar_private *priv);
 static void gfar_clear_exact_match(struct net_device *dev);
 static void gfar_set_mac_for_addr(struct net_device *dev, int num,
@@ -169,17 +168,15 @@ static void gfar_init_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp,
 	bdp->lstatus = cpu_to_be32(lstatus);
 }
 
-static int gfar_init_bds(struct net_device *ndev)
+static void gfar_init_bds(struct net_device *ndev)
 {
 	struct gfar_private *priv = netdev_priv(ndev);
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
 	struct gfar_priv_tx_q *tx_queue = NULL;
 	struct gfar_priv_rx_q *rx_queue = NULL;
 	struct txbd8 *txbdp;
-	struct rxbd8 *rxbdp;
 	u32 __iomem *rfbptr;
 	int i, j;
-	dma_addr_t bufaddr;
 
 	for (i = 0; i < priv->num_tx_queues; i++) {
 		tx_queue = priv->tx_queue[i];
@@ -207,40 +204,26 @@ static int gfar_init_bds(struct net_device *ndev)
 	rfbptr = &regs->rfbptr0;
 	for (i = 0; i < priv->num_rx_queues; i++) {
 		rx_queue = priv->rx_queue[i];
-		rx_queue->cur_rx = rx_queue->rx_bd_base;
-		rx_queue->skb_currx = 0;
-		rxbdp = rx_queue->rx_bd_base;
 
-		for (j = 0; j < rx_queue->rx_ring_size; j++) {
-			struct sk_buff *skb = rx_queue->rx_skbuff[j];
+		rx_queue->next_to_clean = 0;
+		rx_queue->next_to_use = 0;
+		rx_queue->next_to_alloc = 0;
 
-			if (skb) {
-				bufaddr = be32_to_cpu(rxbdp->bufPtr);
-			} else {
-				skb = gfar_new_skb(ndev, &bufaddr);
-				if (!skb) {
-					netdev_err(ndev, "Can't allocate RX buffers\n");
-					return -ENOMEM;
-				}
-				rx_queue->rx_skbuff[j] = skb;
-			}
-
-			gfar_init_rxbdp(rx_queue, rxbdp, bufaddr);
-			rxbdp++;
-		}
+		/* make sure next_to_clean != next_to_use after this
+		 * by leaving at least 1 unused descriptor
+		 */
+		gfar_alloc_rx_buffs(rx_queue, gfar_rxbd_unused(rx_queue));
 
 		rx_queue->rfbptr = rfbptr;
 		rfbptr += 2;
 	}
-
-	return 0;
 }
 
 static int gfar_alloc_skb_resources(struct net_device *ndev)
 {
 	void *vaddr;
 	dma_addr_t addr;
-	int i, j, k;
+	int i, j;
 	struct gfar_private *priv = netdev_priv(ndev);
 	struct device *dev = priv->dev;
 	struct gfar_priv_tx_q *tx_queue = NULL;
@@ -279,7 +262,8 @@ static int gfar_alloc_skb_resources(struct net_device *ndev)
 		rx_queue = priv->rx_queue[i];
 		rx_queue->rx_bd_base = vaddr;
 		rx_queue->rx_bd_dma_base = addr;
-		rx_queue->dev = ndev;
+		rx_queue->ndev = ndev;
+		rx_queue->dev = dev;
 		addr  += sizeof(struct rxbd8) * rx_queue->rx_ring_size;
 		vaddr += sizeof(struct rxbd8) * rx_queue->rx_ring_size;
 	}
@@ -294,25 +278,20 @@ static int gfar_alloc_skb_resources(struct net_device *ndev)
 		if (!tx_queue->tx_skbuff)
 			goto cleanup;
 
-		for (k = 0; k < tx_queue->tx_ring_size; k++)
-			tx_queue->tx_skbuff[k] = NULL;
+		for (j = 0; j < tx_queue->tx_ring_size; j++)
+			tx_queue->tx_skbuff[j] = NULL;
 	}
 
 	for (i = 0; i < priv->num_rx_queues; i++) {
 		rx_queue = priv->rx_queue[i];
-		rx_queue->rx_skbuff =
-			kmalloc_array(rx_queue->rx_ring_size,
-				      sizeof(*rx_queue->rx_skbuff),
-				      GFP_KERNEL);
-		if (!rx_queue->rx_skbuff)
+		rx_queue->rx_buff = kcalloc(rx_queue->rx_ring_size,
+					    sizeof(*rx_queue->rx_buff),
+					    GFP_KERNEL);
+		if (!rx_queue->rx_buff)
 			goto cleanup;
-
-		for (j = 0; j < rx_queue->rx_ring_size; j++)
-			rx_queue->rx_skbuff[j] = NULL;
 	}
 
-	if (gfar_init_bds(ndev))
-		goto cleanup;
+	gfar_init_bds(ndev);
 
 	return 0;
 
@@ -354,28 +333,16 @@ static void gfar_init_rqprm(struct gfar_private *priv)
 	}
 }
 
-static void gfar_rx_buff_size_config(struct gfar_private *priv)
+static void gfar_rx_offload_en(struct gfar_private *priv)
 {
-	int frame_size = priv->ndev->mtu + ETH_HLEN + ETH_FCS_LEN;
-
 	/* set this when rx hw offload (TOE) functions are being used */
 	priv->uses_rxfcb = 0;
 
 	if (priv->ndev->features & (NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX))
 		priv->uses_rxfcb = 1;
 
-	if (priv->hwts_rx_en)
+	if (priv->hwts_rx_en || priv->rx_filer_enable)
 		priv->uses_rxfcb = 1;
-
-	if (priv->uses_rxfcb)
-		frame_size += GMAC_FCB_LEN;
-
-	frame_size += priv->padding;
-
-	frame_size = (frame_size & ~(INCREMENTAL_BUFFER_SIZE - 1)) +
-		     INCREMENTAL_BUFFER_SIZE;
-
-	priv->rx_buffer_size = frame_size;
 }
 
 static void gfar_mac_rx_config(struct gfar_private *priv)
@@ -384,7 +351,7 @@ static void gfar_mac_rx_config(struct gfar_private *priv)
 	u32 rctrl = 0;
 
 	if (priv->rx_filer_enable) {
-		rctrl |= RCTRL_FILREN;
+		rctrl |= RCTRL_FILREN | RCTRL_PRSDEP_INIT;
 		/* Program the RIR0 reg with the required distribution */
 		if (priv->poll_mode == GFAR_SQ_POLLING)
 			gfar_write(&regs->rir0, DEFAULT_2RXQ_RIR0);
@@ -516,6 +483,15 @@ static struct net_device_stats *gfar_get_stats(struct net_device *dev)
 	return &dev->stats;
 }
 
+static int gfar_set_mac_addr(struct net_device *dev, void *p)
+{
+	eth_mac_addr(dev, p);
+
+	gfar_set_mac_for_addr(dev, 0, dev->dev_addr);
+
+	return 0;
+}
+
 static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_open = gfar_enet_open,
 	.ndo_start_xmit = gfar_start_xmit,
@@ -526,7 +502,7 @@ static const struct net_device_ops gfar_netdev_ops = {
 	.ndo_tx_timeout = gfar_timeout,
 	.ndo_do_ioctl = gfar_ioctl,
 	.ndo_get_stats = gfar_get_stats,
-	.ndo_set_mac_address = eth_mac_addr,
+	.ndo_set_mac_address = gfar_set_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = gfar_netpoll,
@@ -556,22 +532,6 @@ static void gfar_ints_enable(struct gfar_private *priv)
 	}
 }
 
-static void lock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_lock(&priv->tx_queue[i]->txlock);
-}
-
-static void unlock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_unlock(&priv->tx_queue[i]->txlock);
-}
-
 static int gfar_alloc_tx_queues(struct gfar_private *priv)
 {
 	int i;
@@ -600,9 +560,8 @@ static int gfar_alloc_rx_queues(struct gfar_private *priv)
 		if (!priv->rx_queue[i])
 			return -ENOMEM;
 
-		priv->rx_queue[i]->rx_skbuff = NULL;
 		priv->rx_queue[i]->qindex = i;
-		priv->rx_queue[i]->dev = priv->ndev;
+		priv->rx_queue[i]->ndev = priv->ndev;
 	}
 	return 0;
 }
@@ -688,9 +647,9 @@ static int gfar_parse_group(struct device_node *np,
 	if (model && strcasecmp(model, "FEC")) {
 		gfar_irq(grp, RX)->irq = irq_of_parse_and_map(np, 1);
 		gfar_irq(grp, ER)->irq = irq_of_parse_and_map(np, 2);
-		if (gfar_irq(grp, TX)->irq == NO_IRQ ||
-		    gfar_irq(grp, RX)->irq == NO_IRQ ||
-		    gfar_irq(grp, ER)->irq == NO_IRQ)
+		if (!gfar_irq(grp, TX)->irq ||
+		    !gfar_irq(grp, RX)->irq ||
+		    !gfar_irq(grp, ER)->irq)
 			return -EINVAL;
 	}
 
@@ -935,7 +894,8 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 				     FSL_GIANFAR_DEV_HAS_VLAN |
 				     FSL_GIANFAR_DEV_HAS_MAGIC_PACKET |
 				     FSL_GIANFAR_DEV_HAS_EXTENDED_HASH |
-				     FSL_GIANFAR_DEV_HAS_TIMER;
+				     FSL_GIANFAR_DEV_HAS_TIMER |
+				     FSL_GIANFAR_DEV_HAS_RX_FILER;
 
 	err = of_property_read_string(np, "phy-connection-type", &ctype);
 
@@ -948,6 +908,9 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 	if (of_find_property(np, "fsl,magic-packet", NULL))
 		priv->device_flags |= FSL_GIANFAR_DEV_HAS_MAGIC_PACKET;
 
+	if (of_get_property(np, "fsl,wake-on-filer", NULL))
+		priv->device_flags |= FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER;
+
 	priv->phy_node = of_parse_phandle(np, "phy-handle", 0);
 
 	/* In the case of a fixed PHY, the DT node associated
@@ -1194,12 +1157,11 @@ void gfar_mac_reset(struct gfar_private *priv)
 
 	udelay(3);
 
-	/* Compute rx_buff_size based on config flags */
-	gfar_rx_buff_size_config(priv);
+	gfar_rx_offload_en(priv);
 
 	/* Initialize the max receive frame/buffer lengths */
-	gfar_write(&regs->maxfrm, priv->rx_buffer_size);
-	gfar_write(&regs->mrblr, priv->rx_buffer_size);
+	gfar_write(&regs->maxfrm, GFAR_JUMBO_FRAME_SIZE);
+	gfar_write(&regs->mrblr, GFAR_RXB_SIZE);
 
 	/* Initialize the Minimum Frame Length Register */
 	gfar_write(&regs->minflr, MINFLR_INIT_SETTINGS);
@@ -1207,12 +1169,11 @@ void gfar_mac_reset(struct gfar_private *priv)
 	/* Initialize MACCFG2. */
 	tempval = MACCFG2_INIT_SETTINGS;
 
-	/* If the mtu is larger than the max size for standard
-	 * ethernet frames (ie, a jumbo frame), then set maccfg2
-	 * to allow huge frames, and to check the length
+	/* eTSEC74 erratum: Rx frames of length MAXFRM or MAXFRM-1
+	 * are marked as truncated.  Avoid this by MACCFG2[Huge Frame]=1,
+	 * and by checking RxBD[LG] and discarding larger than MAXFRM.
 	 */
-	if (priv->rx_buffer_size > DEFAULT_RX_BUFFER_SIZE ||
-	    gfar_has_errata(priv, GFAR_ERRATA_74))
+	if (gfar_has_errata(priv, GFAR_ERRATA_74))
 		tempval |= MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK;
 
 	gfar_write(&regs->maccfg2, tempval);
@@ -1367,7 +1328,6 @@ static int gfar_probe(struct platform_device *ofdev)
 	priv->dev = &ofdev->dev;
 	SET_NETDEV_DEV(dev, &ofdev->dev);
 
-	spin_lock_init(&priv->bflock);
 	INIT_WORK(&priv->reset_task, gfar_reset_task);
 
 	platform_set_drvdata(ofdev, priv);
@@ -1411,6 +1371,8 @@ static int gfar_probe(struct platform_device *ofdev)
 		dev->features |= NETIF_F_HW_VLAN_CTAG_RX;
 	}
 
+	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+
 	gfar_init_addr_hash_table(priv);
 
 	/* Insert receive time stamps into padding alignment bytes */
@@ -1421,8 +1383,6 @@ static int gfar_probe(struct platform_device *ofdev)
 	    priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)
 		dev->needed_headroom = GMAC_FCB_LEN;
 
-	priv->rx_buffer_size = DEFAULT_RX_BUFFER_SIZE;
-
 	/* Initializing some of the rx/tx queue level parameters */
 	for (i = 0; i < priv->num_tx_queues; i++) {
 		priv->tx_queue[i]->tx_ring_size = DEFAULT_TX_RING_SIZE;
@@ -1437,8 +1397,9 @@ static int gfar_probe(struct platform_device *ofdev)
 		priv->rx_queue[i]->rxic = DEFAULT_RXIC;
 	}
 
-	/* always enable rx filer */
-	priv->rx_filer_enable = 1;
+	/* Always enable rx filer if available */
+	priv->rx_filer_enable =
+	    (priv->device_flags & FSL_GIANFAR_DEV_HAS_RX_FILER) ? 1 : 0;
 	/* Enable most messages by default */
 	priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1;
 	/* use pritority h/w tx queue scheduling for single queue devices */
@@ -1459,9 +1420,14 @@ static int gfar_probe(struct platform_device *ofdev)
 		goto register_fail;
 	}
 
-	device_init_wakeup(&dev->dev,
-			   priv->device_flags &
-			   FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET)
+		priv->wol_supported |= GFAR_WOL_MAGIC;
+
+	if ((priv->device_flags & FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER) &&
+	    priv->rx_filer_enable)
+		priv->wol_supported |= GFAR_WOL_FILER_UCAST;
+
+	device_set_wakeup_capable(&ofdev->dev, priv->wol_supported);
 
 	/* fill out IRQ number and name fields */
 	for (i = 0; i < priv->num_grps; i++) {
@@ -1524,53 +1490,153 @@ static int gfar_remove(struct platform_device *ofdev)
 
 #ifdef CONFIG_PM
 
+static void __gfar_filer_disable(struct gfar_private *priv)
+{
+	struct gfar __iomem *regs = priv->gfargrp[0].regs;
+	u32 temp;
+
+	temp = gfar_read(&regs->rctrl);
+	temp &= ~(RCTRL_FILREN | RCTRL_PRSDEP_INIT);
+	gfar_write(&regs->rctrl, temp);
+}
+
+static void __gfar_filer_enable(struct gfar_private *priv)
+{
+	struct gfar __iomem *regs = priv->gfargrp[0].regs;
+	u32 temp;
+
+	temp = gfar_read(&regs->rctrl);
+	temp |= RCTRL_FILREN | RCTRL_PRSDEP_INIT;
+	gfar_write(&regs->rctrl, temp);
+}
+
+/* Filer rules implementing wol capabilities */
+static void gfar_filer_config_wol(struct gfar_private *priv)
+{
+	unsigned int i;
+	u32 rqfcr;
+
+	__gfar_filer_disable(priv);
+
+	/* clear the filer table, reject any packet by default */
+	rqfcr = RQFCR_RJE | RQFCR_CMP_MATCH;
+	for (i = 0; i <= MAX_FILER_IDX; i++)
+		gfar_write_filer(priv, i, rqfcr, 0);
+
+	i = 0;
+	if (priv->wol_opts & GFAR_WOL_FILER_UCAST) {
+		/* unicast packet, accept it */
+		struct net_device *ndev = priv->ndev;
+		/* get the default rx queue index */
+		u8 qindex = (u8)priv->gfargrp[0].rx_queue->qindex;
+		u32 dest_mac_addr = (ndev->dev_addr[0] << 16) |
+				    (ndev->dev_addr[1] << 8) |
+				     ndev->dev_addr[2];
+
+		rqfcr = (qindex << 10) | RQFCR_AND |
+			RQFCR_CMP_EXACT | RQFCR_PID_DAH;
+
+		gfar_write_filer(priv, i++, rqfcr, dest_mac_addr);
+
+		dest_mac_addr = (ndev->dev_addr[3] << 16) |
+				(ndev->dev_addr[4] << 8) |
+				 ndev->dev_addr[5];
+		rqfcr = (qindex << 10) | RQFCR_GPI |
+			RQFCR_CMP_EXACT | RQFCR_PID_DAL;
+		gfar_write_filer(priv, i++, rqfcr, dest_mac_addr);
+	}
+
+	__gfar_filer_enable(priv);
+}
+
+static void gfar_filer_restore_table(struct gfar_private *priv)
+{
+	u32 rqfcr, rqfpr;
+	unsigned int i;
+
+	__gfar_filer_disable(priv);
+
+	for (i = 0; i <= MAX_FILER_IDX; i++) {
+		rqfcr = priv->ftp_rqfcr[i];
+		rqfpr = priv->ftp_rqfpr[i];
+		gfar_write_filer(priv, i, rqfcr, rqfpr);
+	}
+
+	__gfar_filer_enable(priv);
+}
+
+/* gfar_start() for Rx only and with the FGPI filer interrupt enabled */
+static void gfar_start_wol_filer(struct gfar_private *priv)
+{
+	struct gfar __iomem *regs = priv->gfargrp[0].regs;
+	u32 tempval;
+	int i = 0;
+
+	/* Enable Rx hw queues */
+	gfar_write(&regs->rqueue, priv->rqueue);
+
+	/* Initialize DMACTRL to have WWR and WOP */
+	tempval = gfar_read(&regs->dmactrl);
+	tempval |= DMACTRL_INIT_SETTINGS;
+	gfar_write(&regs->dmactrl, tempval);
+
+	/* Make sure we aren't stopped */
+	tempval = gfar_read(&regs->dmactrl);
+	tempval &= ~DMACTRL_GRS;
+	gfar_write(&regs->dmactrl, tempval);
+
+	for (i = 0; i < priv->num_grps; i++) {
+		regs = priv->gfargrp[i].regs;
+		/* Clear RHLT, so that the DMA starts polling now */
+		gfar_write(&regs->rstat, priv->gfargrp[i].rstat);
+		/* enable the Filer General Purpose Interrupt */
+		gfar_write(&regs->imask, IMASK_FGPI);
+	}
+
+	/* Enable Rx DMA */
+	tempval = gfar_read(&regs->maccfg1);
+	tempval |= MACCFG1_RX_EN;
+	gfar_write(&regs->maccfg1, tempval);
+}
+
 static int gfar_suspend(struct device *dev)
 {
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
+	u16 wol = priv->wol_opts;
 
-	int magic_packet = priv->wol_en &&
-			   (priv->device_flags &
-			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+	if (!netif_running(ndev))
+		return 0;
 
+	disable_napi(priv);
+	netif_tx_lock(ndev);
 	netif_device_detach(ndev);
+	netif_tx_unlock(ndev);
 
-	if (netif_running(ndev)) {
+	gfar_halt(priv);
 
-		local_irq_save_nort(flags);
-		lock_tx_qs(priv);
+	if (wol & GFAR_WOL_MAGIC) {
+		/* Enable interrupt on Magic Packet */
+		gfar_write(&regs->imask, IMASK_MAG);
 
-		gfar_halt_nodisable(priv);
+		/* Enable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval |= MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
 
-		/* Disable Tx, and Rx if wake-on-LAN is disabled. */
+		/* re-enable the Rx block */
 		tempval = gfar_read(&regs->maccfg1);
-
-		tempval &= ~MACCFG1_TX_EN;
-
-		if (!magic_packet)
-			tempval &= ~MACCFG1_RX_EN;
-
+		tempval |= MACCFG1_RX_EN;
 		gfar_write(&regs->maccfg1, tempval);
 
-		unlock_tx_qs(priv);
-		local_irq_restore_nort(flags);
-
-		disable_napi(priv);
-
-		if (magic_packet) {
-			/* Enable interrupt on Magic Packet */
-			gfar_write(&regs->imask, IMASK_MAG);
+	} else if (wol & GFAR_WOL_FILER_UCAST) {
+		gfar_filer_config_wol(priv);
+		gfar_start_wol_filer(priv);
 
-			/* Enable Magic Packet mode */
-			tempval = gfar_read(&regs->maccfg2);
-			tempval |= MACCFG2_MPEN;
-			gfar_write(&regs->maccfg2, tempval);
-		} else {
-			phy_stop(priv->phydev);
-		}
+	} else {
+		phy_stop(priv->phydev);
 	}
 
 	return 0;
@@ -1581,37 +1647,30 @@ static int gfar_resume(struct device *dev)
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
-	int magic_packet = priv->wol_en &&
-			   (priv->device_flags &
-			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+	u16 wol = priv->wol_opts;
 
-	if (!netif_running(ndev)) {
-		netif_device_attach(ndev);
+	if (!netif_running(ndev))
 		return 0;
-	}
 
-	if (!magic_packet && priv->phydev)
-		phy_start(priv->phydev);
+	if (wol & GFAR_WOL_MAGIC) {
+		/* Disable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval &= ~MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
 
-	/* Disable Magic Packet mode, in case something
-	 * else woke us up.
-	 */
-	local_irq_save_nort(flags);
-	lock_tx_qs(priv);
+	} else if (wol & GFAR_WOL_FILER_UCAST) {
+		/* need to stop rx only, tx is already down */
+		gfar_halt(priv);
+		gfar_filer_restore_table(priv);
 
-	tempval = gfar_read(&regs->maccfg2);
-	tempval &= ~MACCFG2_MPEN;
-	gfar_write(&regs->maccfg2, tempval);
+	} else {
+		phy_start(priv->phydev);
+	}
 
 	gfar_start(priv);
 
-	unlock_tx_qs(priv);
-	local_irq_restore_nort(flags);
-
 	netif_device_attach(ndev);
-
 	enable_napi(priv);
 
 	return 0;
@@ -1628,10 +1687,7 @@ static int gfar_restore(struct device *dev)
 		return 0;
 	}
 
-	if (gfar_init_bds(ndev)) {
-		free_skb_resources(priv);
-		return -ENOMEM;
-	}
+	gfar_init_bds(ndev);
 
 	gfar_mac_reset(priv);
 
@@ -1780,8 +1836,10 @@ static void gfar_configure_serdes(struct net_device *dev)
 	 * everything for us?  Resetting it takes the link down and requires
 	 * several seconds for it to come back.
 	 */
-	if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS)
+	if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) {
+		put_device(&tbiphy->dev);
 		return;
+	}
 
 	/* Single clk mode, mii mode off(for serdes communication) */
 	phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT);
@@ -1793,6 +1851,8 @@ static void gfar_configure_serdes(struct net_device *dev)
 	phy_write(tbiphy, MII_BMCR,
 		  BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX |
 		  BMCR_SPEED1000);
+
+	put_device(&tbiphy->dev);
 }
 
 static int __gfar_is_rx_idle(struct gfar_private *priv)
@@ -1922,26 +1982,32 @@ static void free_skb_tx_queue(struct gfar_priv_tx_q *tx_queue)
 
 static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue)
 {
-	struct rxbd8 *rxbdp;
-	struct gfar_private *priv = netdev_priv(rx_queue->dev);
 	int i;
 
-	rxbdp = rx_queue->rx_bd_base;
+	struct rxbd8 *rxbdp = rx_queue->rx_bd_base;
+
+	if (rx_queue->skb)
+		dev_kfree_skb(rx_queue->skb);
 
 	for (i = 0; i < rx_queue->rx_ring_size; i++) {
-		if (rx_queue->rx_skbuff[i]) {
-			dma_unmap_single(priv->dev, be32_to_cpu(rxbdp->bufPtr),
-					 priv->rx_buffer_size,
-					 DMA_FROM_DEVICE);
-			dev_kfree_skb_any(rx_queue->rx_skbuff[i]);
-			rx_queue->rx_skbuff[i] = NULL;
-		}
+		struct	gfar_rx_buff *rxb = &rx_queue->rx_buff[i];
+
 		rxbdp->lstatus = 0;
 		rxbdp->bufPtr = 0;
 		rxbdp++;
+
+		if (!rxb->page)
+			continue;
+
+		dma_unmap_single(rx_queue->dev, rxb->dma,
+				 PAGE_SIZE, DMA_FROM_DEVICE);
+		__free_page(rxb->page);
+
+		rxb->page = NULL;
 	}
-	kfree(rx_queue->rx_skbuff);
-	rx_queue->rx_skbuff = NULL;
+
+	kfree(rx_queue->rx_buff);
+	rx_queue->rx_buff = NULL;
 }
 
 /* If there are any tx skbs or rx skbs still around, free them.
@@ -1966,7 +2032,7 @@ static void free_skb_resources(struct gfar_private *priv)
 
 	for (i = 0; i < priv->num_rx_queues; i++) {
 		rx_queue = priv->rx_queue[i];
-		if (rx_queue->rx_skbuff)
+		if (rx_queue->rx_buff)
 			free_skb_rx_queue(rx_queue);
 	}
 
@@ -2042,6 +2108,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 
 			goto err_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, ER)->irq);
+
 		err = request_irq(gfar_irq(grp, TX)->irq, gfar_transmit, 0,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
@@ -2056,6 +2124,8 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 				  gfar_irq(grp, RX)->irq);
 			goto rx_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, RX)->irq);
+
 	} else {
 		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
 				  gfar_irq(grp, TX)->name, grp);
@@ -2064,6 +2134,7 @@ static int register_grp_irqs(struct gfar_priv_grp *grp)
 				  gfar_irq(grp, TX)->irq);
 			goto err_irq_fail;
 		}
+		enable_irq_wake(gfar_irq(grp, TX)->irq);
 	}
 
 	return 0;
@@ -2129,6 +2200,11 @@ int startup_gfar(struct net_device *ndev)
 	/* Start Rx/Tx DMA and enable the interrupts */
 	gfar_start(priv);
 
+	/* force link state update after mac reset */
+	priv->oldlink = 0;
+	priv->oldspeed = 0;
+	priv->oldduplex = -1;
+
 	phy_start(priv->phydev);
 
 	enable_napi(priv);
@@ -2158,8 +2234,6 @@ static int gfar_enet_open(struct net_device *dev)
 	if (err)
 		return err;
 
-	device_set_wakeup_enable(&dev->dev, priv->wol_en);
-
 	return err;
 }
 
@@ -2254,7 +2328,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	int i, rq = 0;
 	int do_tstamp, do_csum, do_vlan;
 	u32 bufaddr;
-	unsigned long flags;
 	unsigned int nr_frags, nr_txbds, bytes_sent, fcb_len = 0;
 
 	rq = skb->queue_mapping;
@@ -2434,19 +2507,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	netdev_tx_sent_queue(txq, bytes_sent);
 
-	/* We can work in parallel with gfar_clean_tx_ring(), except
-	 * when modifying num_txbdfree. Note that we didn't grab the lock
-	 * when we were reading the num_txbdfree and checking for available
-	 * space, that's because outside of this function it can only grow,
-	 * and once we've got needed space, it cannot suddenly disappear.
-	 *
-	 * The lock also protects us from gfar_error(), which can modify
-	 * regs->tstat and thus retrigger the transfers, which is why we
-	 * also must grab the lock before setting ready bit for the first
-	 * to be transmitted BD.
-	 */
-	spin_lock_irqsave(&tx_queue->txlock, flags);
-
 	gfar_wmb();
 
 	txbdp_start->lstatus = cpu_to_be32(lstatus);
@@ -2463,8 +2523,15 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	tx_queue->cur_tx = next_txbd(txbdp, base, tx_queue->tx_ring_size);
 
+	/* We can work in parallel with gfar_clean_tx_ring(), except
+	 * when modifying num_txbdfree. Note that we didn't grab the lock
+	 * when we were reading the num_txbdfree and checking for available
+	 * space, that's because outside of this function it can only grow.
+	 */
+	spin_lock_bh(&tx_queue->txlock);
 	/* reduce TxBD free count */
 	tx_queue->num_txbdfree -= (nr_txbds);
+	spin_unlock_bh(&tx_queue->txlock);
 
 	/* If the next BD still needs to be cleaned up, then the bds
 	 * are full.  We need to tell the kernel to stop sending us stuff.
@@ -2478,9 +2545,6 @@ static int gfar_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Tell the DMA to go go go */
 	gfar_write(&regs->tstat, TSTAT_CLEAR_THALT >> tx_queue->qindex);
 
-	/* Unlock priv */
-	spin_unlock_irqrestore(&tx_queue->txlock, flags);
-
 	return NETDEV_TX_OK;
 
 dma_map_err:
@@ -2534,7 +2598,7 @@ static int gfar_change_mtu(struct net_device *dev, int new_mtu)
 	struct gfar_private *priv = netdev_priv(dev);
 	int frame_size = new_mtu + ETH_HLEN;
 
-	if ((frame_size < 64) || (frame_size > JUMBO_FRAME_SIZE)) {
+	if ((frame_size < 64) || (frame_size > GFAR_JUMBO_FRAME_SIZE)) {
 		netif_err(priv, drv, dev, "Invalid MTU setting\n");
 		return -EINVAL;
 	}
@@ -2588,15 +2652,6 @@ static void gfar_timeout(struct net_device *dev)
 	schedule_work(&priv->reset_task);
 }
 
-static void gfar_align_skb(struct sk_buff *skb)
-{
-	/* We need the data buffer to be aligned properly.  We will reserve
-	 * as many bytes as needed to align the data properly
-	 */
-	skb_reserve(skb, RXBUF_ALIGNMENT -
-		    (((unsigned long) skb->data) & (RXBUF_ALIGNMENT - 1)));
-}
-
 /* Interrupt Handler for Transmit complete */
 static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 {
@@ -2622,7 +2677,6 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 	skb_dirtytx = tx_queue->skb_dirtytx;
 
 	while ((skb = tx_queue->tx_skbuff[skb_dirtytx])) {
-		unsigned long flags;
 
 		frags = skb_shinfo(skb)->nr_frags;
 
@@ -2655,7 +2709,8 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 
 		if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
 			struct skb_shared_hwtstamps shhwtstamps;
-			u64 *ns = (u64*) (((u32)skb->data + 0x10) & ~0x7);
+			u64 *ns = (u64 *)(((uintptr_t)skb->data + 0x10) &
+					  ~0x7UL);
 
 			memset(&shhwtstamps, 0, sizeof(shhwtstamps));
 			shhwtstamps.hwtstamp = ns_to_ktime(*ns);
@@ -2686,9 +2741,9 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 			      TX_RING_MOD_MASK(tx_ring_size);
 
 		howmany++;
-		spin_lock_irqsave(&tx_queue->txlock, flags);
+		spin_lock(&tx_queue->txlock);
 		tx_queue->num_txbdfree += nr_txbds;
-		spin_unlock_irqrestore(&tx_queue->txlock, flags);
+		spin_unlock(&tx_queue->txlock);
 	}
 
 	/* If we freed a buffer, we can restart transmission, if necessary */
@@ -2704,49 +2759,85 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue)
 	netdev_tx_completed_queue(txq, howmany, bytes_sent);
 }
 
-static struct sk_buff *gfar_alloc_skb(struct net_device *dev)
+static bool gfar_new_page(struct gfar_priv_rx_q *rxq, struct gfar_rx_buff *rxb)
 {
-	struct gfar_private *priv = netdev_priv(dev);
-	struct sk_buff *skb;
+	struct page *page;
+	dma_addr_t addr;
 
-	skb = netdev_alloc_skb(dev, priv->rx_buffer_size + RXBUF_ALIGNMENT);
-	if (!skb)
-		return NULL;
+	page = dev_alloc_page();
+	if (unlikely(!page))
+		return false;
 
-	gfar_align_skb(skb);
+	addr = dma_map_page(rxq->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(rxq->dev, addr))) {
+		__free_page(page);
 
-	return skb;
+		return false;
+	}
+
+	rxb->dma = addr;
+	rxb->page = page;
+	rxb->page_offset = 0;
+
+	return true;
 }
 
-static struct sk_buff *gfar_new_skb(struct net_device *dev, dma_addr_t *bufaddr)
+static void gfar_rx_alloc_err(struct gfar_priv_rx_q *rx_queue)
 {
-	struct gfar_private *priv = netdev_priv(dev);
-	struct sk_buff *skb;
-	dma_addr_t addr;
+	struct gfar_private *priv = netdev_priv(rx_queue->ndev);
+	struct gfar_extra_stats *estats = &priv->extra_stats;
 
-	skb = gfar_alloc_skb(dev);
-	if (!skb)
-		return NULL;
+	netdev_err(rx_queue->ndev, "Can't alloc RX buffers\n");
+	atomic64_inc(&estats->rx_alloc_err);
+}
 
-	addr = dma_map_single(priv->dev, skb->data,
-			      priv->rx_buffer_size, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(priv->dev, addr))) {
-		dev_kfree_skb_any(skb);
-		return NULL;
+static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue,
+				int alloc_cnt)
+{
+	struct rxbd8 *bdp;
+	struct gfar_rx_buff *rxb;
+	int i;
+
+	i = rx_queue->next_to_use;
+	bdp = &rx_queue->rx_bd_base[i];
+	rxb = &rx_queue->rx_buff[i];
+
+	while (alloc_cnt--) {
+		/* try reuse page */
+		if (unlikely(!rxb->page)) {
+			if (unlikely(!gfar_new_page(rx_queue, rxb))) {
+				gfar_rx_alloc_err(rx_queue);
+				break;
+			}
+		}
+
+		/* Setup the new RxBD */
+		gfar_init_rxbdp(rx_queue, bdp,
+				rxb->dma + rxb->page_offset + RXBUF_ALIGNMENT);
+
+		/* Update to the next pointer */
+		bdp++;
+		rxb++;
+
+		if (unlikely(++i == rx_queue->rx_ring_size)) {
+			i = 0;
+			bdp = rx_queue->rx_bd_base;
+			rxb = rx_queue->rx_buff;
+		}
 	}
 
-	*bufaddr = addr;
-	return skb;
+	rx_queue->next_to_use = i;
+	rx_queue->next_to_alloc = i;
 }
 
-static inline void count_errors(unsigned short status, struct net_device *dev)
+static void count_errors(u32 lstatus, struct net_device *ndev)
 {
-	struct gfar_private *priv = netdev_priv(dev);
-	struct net_device_stats *stats = &dev->stats;
+	struct gfar_private *priv = netdev_priv(ndev);
+	struct net_device_stats *stats = &ndev->stats;
 	struct gfar_extra_stats *estats = &priv->extra_stats;
 
 	/* If the packet was truncated, none of the other errors matter */
-	if (status & RXBD_TRUNCATED) {
+	if (lstatus & BD_LFLAG(RXBD_TRUNCATED)) {
 		stats->rx_length_errors++;
 
 		atomic64_inc(&estats->rx_trunc);
@@ -2754,25 +2845,25 @@ static inline void count_errors(unsigned short status, struct net_device *dev)
 		return;
 	}
 	/* Count the errors, if there were any */
-	if (status & (RXBD_LARGE | RXBD_SHORT)) {
+	if (lstatus & BD_LFLAG(RXBD_LARGE | RXBD_SHORT)) {
 		stats->rx_length_errors++;
 
-		if (status & RXBD_LARGE)
+		if (lstatus & BD_LFLAG(RXBD_LARGE))
 			atomic64_inc(&estats->rx_large);
 		else
 			atomic64_inc(&estats->rx_short);
 	}
-	if (status & RXBD_NONOCTET) {
+	if (lstatus & BD_LFLAG(RXBD_NONOCTET)) {
 		stats->rx_frame_errors++;
 		atomic64_inc(&estats->rx_nonoctet);
 	}
-	if (status & RXBD_CRCERR) {
+	if (lstatus & BD_LFLAG(RXBD_CRCERR)) {
 		atomic64_inc(&estats->rx_crcerr);
 		stats->rx_crc_errors++;
 	}
-	if (status & RXBD_OVERRUN) {
+	if (lstatus & BD_LFLAG(RXBD_OVERRUN)) {
 		atomic64_inc(&estats->rx_overrun);
-		stats->rx_crc_errors++;
+		stats->rx_over_errors++;
 	}
 }
 
@@ -2780,7 +2871,14 @@ irqreturn_t gfar_receive(int irq, void *grp_id)
 {
 	struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id;
 	unsigned long flags;
-	u32 imask;
+	u32 imask, ievent;
+
+	ievent = gfar_read(&grp->regs->ievent);
+
+	if (unlikely(ievent & IEVENT_FGPI)) {
+		gfar_write(&grp->regs->ievent, IEVENT_FGPI);
+		return IRQ_HANDLED;
+	}
 
 	if (likely(napi_schedule_prep(&grp->napi_rx))) {
 		spin_lock_irqsave(&grp->grplock, flags);
@@ -2823,6 +2921,93 @@ static irqreturn_t gfar_transmit(int irq, void *grp_id)
 	return IRQ_HANDLED;
 }
 
+static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
+			     struct sk_buff *skb, bool first)
+{
+	unsigned int size = lstatus & BD_LENGTH_MASK;
+	struct page *page = rxb->page;
+
+	/* Remove the FCS from the packet length */
+	if (likely(lstatus & BD_LFLAG(RXBD_LAST)))
+		size -= ETH_FCS_LEN;
+
+	if (likely(first))
+		skb_put(skb, size);
+	else
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+				rxb->page_offset + RXBUF_ALIGNMENT,
+				size, GFAR_RXB_TRUESIZE);
+
+	/* try reuse page */
+	if (unlikely(page_count(page) != 1))
+		return false;
+
+	/* change offset to the other half */
+	rxb->page_offset ^= GFAR_RXB_TRUESIZE;
+
+	atomic_inc(&page->_count);
+
+	return true;
+}
+
+static void gfar_reuse_rx_page(struct gfar_priv_rx_q *rxq,
+			       struct gfar_rx_buff *old_rxb)
+{
+	struct gfar_rx_buff *new_rxb;
+	u16 nta = rxq->next_to_alloc;
+
+	new_rxb = &rxq->rx_buff[nta];
+
+	/* find next buf that can reuse a page */
+	nta++;
+	rxq->next_to_alloc = (nta < rxq->rx_ring_size) ? nta : 0;
+
+	/* copy page reference */
+	*new_rxb = *old_rxb;
+
+	/* sync for use by the device */
+	dma_sync_single_range_for_device(rxq->dev, old_rxb->dma,
+					 old_rxb->page_offset,
+					 GFAR_RXB_TRUESIZE, DMA_FROM_DEVICE);
+}
+
+static struct sk_buff *gfar_get_next_rxbuff(struct gfar_priv_rx_q *rx_queue,
+					    u32 lstatus, struct sk_buff *skb)
+{
+	struct gfar_rx_buff *rxb = &rx_queue->rx_buff[rx_queue->next_to_clean];
+	struct page *page = rxb->page;
+	bool first = false;
+
+	if (likely(!skb)) {
+		void *buff_addr = page_address(page) + rxb->page_offset;
+
+		skb = build_skb(buff_addr, GFAR_SKBFRAG_SIZE);
+		if (unlikely(!skb)) {
+			gfar_rx_alloc_err(rx_queue);
+			return NULL;
+		}
+		skb_reserve(skb, RXBUF_ALIGNMENT);
+		first = true;
+	}
+
+	dma_sync_single_range_for_cpu(rx_queue->dev, rxb->dma, rxb->page_offset,
+				      GFAR_RXB_TRUESIZE, DMA_FROM_DEVICE);
+
+	if (gfar_add_rx_frag(rxb, lstatus, skb, first)) {
+		/* reuse the free half of the page */
+		gfar_reuse_rx_page(rx_queue, rxb);
+	} else {
+		/* page cannot be reused, unmap it */
+		dma_unmap_page(rx_queue->dev, rxb->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+	}
+
+	/* clear rxb content */
+	rxb->page = NULL;
+
+	return skb;
+}
+
 static inline void gfar_rx_checksum(struct sk_buff *skb, struct rxfcb *fcb)
 {
 	/* If valid headers were found, and valid sums
@@ -2837,10 +3022,9 @@ static inline void gfar_rx_checksum(struct sk_buff *skb, struct rxfcb *fcb)
 }
 
 /* gfar_process_frame() -- handle one incoming packet if skb isn't NULL. */
-static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
-			       int amount_pull, struct napi_struct *napi)
+static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb)
 {
-	struct gfar_private *priv = netdev_priv(dev);
+	struct gfar_private *priv = netdev_priv(ndev);
 	struct rxfcb *fcb = NULL;
 
 	/* fcb is at the beginning if exists */
@@ -2849,10 +3033,8 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
 	/* Remove the FCB from the skb
 	 * Remove the padded bytes, if there are any
 	 */
-	if (amount_pull) {
-		skb_record_rx_queue(skb, fcb->rq);
-		skb_pull(skb, amount_pull);
-	}
+	if (priv->uses_rxfcb)
+		skb_pull(skb, GMAC_FCB_LEN);
 
 	/* Get receive timestamp from the skb */
 	if (priv->hwts_rx_en) {
@@ -2866,24 +3048,20 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
 	if (priv->padding)
 		skb_pull(skb, priv->padding);
 
-	if (dev->features & NETIF_F_RXCSUM)
+	if (ndev->features & NETIF_F_RXCSUM)
 		gfar_rx_checksum(skb, fcb);
 
 	/* Tell the skb what kind of packet this is */
-	skb->protocol = eth_type_trans(skb, dev);
+	skb->protocol = eth_type_trans(skb, ndev);
 
 	/* There's need to check for NETIF_F_HW_VLAN_CTAG_RX here.
 	 * Even if vlan rx accel is disabled, on some chips
 	 * RXFCB_VLN is pseudo randomly set.
 	 */
-	if (dev->features & NETIF_F_HW_VLAN_CTAG_RX &&
+	if (ndev->features & NETIF_F_HW_VLAN_CTAG_RX &&
 	    be16_to_cpu(fcb->flags) & RXFCB_VLN)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q),
 				       be16_to_cpu(fcb->vlctl));
-
-	/* Send the packet up the stack */
-	napi_gro_receive(napi, skb);
-
 }
 
 /* gfar_clean_rx_ring() -- Processes each frame in the rx ring
@@ -2892,91 +3070,89 @@ static void gfar_process_frame(struct net_device *dev, struct sk_buff *skb,
  */
 int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit)
 {
-	struct net_device *dev = rx_queue->dev;
-	struct rxbd8 *bdp, *base;
-	struct sk_buff *skb;
-	int pkt_len;
-	int amount_pull;
-	int howmany = 0;
-	struct gfar_private *priv = netdev_priv(dev);
+	struct net_device *ndev = rx_queue->ndev;
+	struct gfar_private *priv = netdev_priv(ndev);
+	struct rxbd8 *bdp;
+	int i, howmany = 0;
+	struct sk_buff *skb = rx_queue->skb;
+	int cleaned_cnt = gfar_rxbd_unused(rx_queue);
+	unsigned int total_bytes = 0, total_pkts = 0;
 
 	/* Get the first full descriptor */
-	bdp = rx_queue->cur_rx;
-	base = rx_queue->rx_bd_base;
+	i = rx_queue->next_to_clean;
+
+	while (rx_work_limit--) {
+		u32 lstatus;
 
-	amount_pull = priv->uses_rxfcb ? GMAC_FCB_LEN : 0;
+		if (cleaned_cnt >= GFAR_RX_BUFF_ALLOC) {
+			gfar_alloc_rx_buffs(rx_queue, cleaned_cnt);
+			cleaned_cnt = 0;
+		}
 
-	while (!(be16_to_cpu(bdp->status) & RXBD_EMPTY) && rx_work_limit--) {
-		struct sk_buff *newskb;
-		dma_addr_t bufaddr;
+		bdp = &rx_queue->rx_bd_base[i];
+		lstatus = be32_to_cpu(bdp->lstatus);
+		if (lstatus & BD_LFLAG(RXBD_EMPTY))
+			break;
 
+		/* order rx buffer descriptor reads */
 		rmb();
 
-		/* Add another skb for the future */
-		newskb = gfar_new_skb(dev, &bufaddr);
+		/* fetch next to clean buffer from the ring */
+		skb = gfar_get_next_rxbuff(rx_queue, lstatus, skb);
+		if (unlikely(!skb))
+			break;
 
-		skb = rx_queue->rx_skbuff[rx_queue->skb_currx];
+		cleaned_cnt++;
+		howmany++;
 
-		dma_unmap_single(priv->dev, be32_to_cpu(bdp->bufPtr),
-				 priv->rx_buffer_size, DMA_FROM_DEVICE);
-
-		if (unlikely(!(be16_to_cpu(bdp->status) & RXBD_ERR) &&
-			     be16_to_cpu(bdp->length) > priv->rx_buffer_size))
-			bdp->status = cpu_to_be16(RXBD_LARGE);
-
-		/* We drop the frame if we failed to allocate a new buffer */
-		if (unlikely(!newskb ||
-			     !(be16_to_cpu(bdp->status) & RXBD_LAST) ||
-			     be16_to_cpu(bdp->status) & RXBD_ERR)) {
-			count_errors(be16_to_cpu(bdp->status), dev);
-
-			if (unlikely(!newskb)) {
-				newskb = skb;
-				bufaddr = be32_to_cpu(bdp->bufPtr);
-			} else if (skb)
-				dev_kfree_skb(skb);
-		} else {
-			/* Increment the number of packets */
-			rx_queue->stats.rx_packets++;
-			howmany++;
-
-			if (likely(skb)) {
-				pkt_len = be16_to_cpu(bdp->length) -
-					  ETH_FCS_LEN;
-				/* Remove the FCS from the packet length */
-				skb_put(skb, pkt_len);
-				rx_queue->stats.rx_bytes += pkt_len;
-				skb_record_rx_queue(skb, rx_queue->qindex);
-				gfar_process_frame(dev, skb, amount_pull,
-						   &rx_queue->grp->napi_rx);
+		if (unlikely(++i == rx_queue->rx_ring_size))
+			i = 0;
 
-			} else {
-				netif_warn(priv, rx_err, dev, "Missing skb!\n");
-				rx_queue->stats.rx_dropped++;
-				atomic64_inc(&priv->extra_stats.rx_skbmissing);
-			}
+		rx_queue->next_to_clean = i;
+
+		/* fetch next buffer if not the last in frame */
+		if (!(lstatus & BD_LFLAG(RXBD_LAST)))
+			continue;
 
+		if (unlikely(lstatus & BD_LFLAG(RXBD_ERR))) {
+			count_errors(lstatus, ndev);
+
+			/* discard faulty buffer */
+			dev_kfree_skb(skb);
+			skb = NULL;
+			rx_queue->stats.rx_dropped++;
+			continue;
 		}
 
-		rx_queue->rx_skbuff[rx_queue->skb_currx] = newskb;
+		/* Increment the number of packets */
+		total_pkts++;
+		total_bytes += skb->len;
 
-		/* Setup the new bdp */
-		gfar_init_rxbdp(rx_queue, bdp, bufaddr);
+		skb_record_rx_queue(skb, rx_queue->qindex);
 
-		/* Update Last Free RxBD pointer for LFC */
-		if (unlikely(rx_queue->rfbptr && priv->tx_actual_en))
-			gfar_write(rx_queue->rfbptr, (u32)bdp);
+		gfar_process_frame(ndev, skb);
 
-		/* Update to the next pointer */
-		bdp = next_bd(bdp, base, rx_queue->rx_ring_size);
+		/* Send the packet up the stack */
+		napi_gro_receive(&rx_queue->grp->napi_rx, skb);
 
-		/* update to point at the next skb */
-		rx_queue->skb_currx = (rx_queue->skb_currx + 1) &
-				      RX_RING_MOD_MASK(rx_queue->rx_ring_size);
+		skb = NULL;
 	}
 
-	/* Update the current rxbd pointer to be the next one */
-	rx_queue->cur_rx = bdp;
+	/* Store incomplete frames for completion */
+	rx_queue->skb = skb;
+
+	rx_queue->stats.rx_packets += total_pkts;
+	rx_queue->stats.rx_bytes += total_bytes;
+
+	if (cleaned_cnt)
+		gfar_alloc_rx_buffs(rx_queue, cleaned_cnt);
+
+	/* Update Last Free RxBD pointer for LFC */
+	if (unlikely(priv->tx_actual_en)) {
+		u32 bdp_dma = gfar_rxbd_dma_lastfree(rx_queue);
+
+		gfar_write(rx_queue->rfbptr, bdp_dma);
+	}
 
 	return howmany;
 }
@@ -3411,30 +3587,19 @@ static irqreturn_t gfar_error(int irq, void *grp_id)
 		if (events & IEVENT_CRL)
 			dev->stats.tx_aborted_errors++;
 		if (events & IEVENT_XFUN) {
-			unsigned long flags;
-
 			netif_dbg(priv, tx_err, dev,
 				  "TX FIFO underrun, packet dropped\n");
 			dev->stats.tx_dropped++;
 			atomic64_inc(&priv->extra_stats.tx_underrun);
 
-			local_irq_save_nort(flags);
-			lock_tx_qs(priv);
-
-			/* Reactivate the Tx Queues */
-			gfar_write(&regs->tstat, gfargrp->tstat);
-
-			unlock_tx_qs(priv);
-			local_irq_restore_nort(flags);
+			schedule_work(&priv->reset_task);
 		}
 		netif_dbg(priv, tx_err, dev, "Transmit Error\n");
 	}
 	if (events & IEVENT_BSY) {
-		dev->stats.rx_errors++;
+		dev->stats.rx_over_errors++;
 		atomic64_inc(&priv->extra_stats.rx_bsy);
 
-		gfar_receive(irq, grp_id);
-
 		netif_dbg(priv, rx_err, dev, "busy error (rstat: %x)\n",
 			  gfar_read(&regs->rstat));
 	}
@@ -3503,7 +3668,6 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 	struct phy_device *phydev = priv->phydev;
 	struct gfar_priv_rx_q *rx_queue = NULL;
 	int i;
-	struct rxbd8 *bdp;
 
 	if (unlikely(test_bit(GFAR_RESETTING, &priv->state)))
 		return;
@@ -3560,15 +3724,11 @@ static noinline void gfar_update_link_state(struct gfar_private *priv)
 		/* Turn last free buffer recording on */
 		if ((tempval1 & MACCFG1_TX_FLOW) && !tx_flow_oldval) {
 			for (i = 0; i < priv->num_rx_queues; i++) {
+				u32 bdp_dma;
+
 				rx_queue = priv->rx_queue[i];
-				bdp = rx_queue->cur_rx;
-				/* skip to previous bd */
-				bdp = skip_bd(bdp, rx_queue->rx_ring_size - 1,
-					      rx_queue->rx_bd_base,
-					      rx_queue->rx_ring_size);
-
-				if (rx_queue->rfbptr)
-					gfar_write(rx_queue->rfbptr, (u32)bdp);
+				bdp_dma = gfar_rxbd_dma_lastfree(rx_queue);
+				gfar_write(rx_queue->rfbptr, bdp_dma);
 			}
 
 			priv->tx_actual_en = 1;
diff --git a/kernel/drivers/net/ethernet/freescale/gianfar.h b/kernel/drivers/net/ethernet/freescale/gianfar.h
index daa1d37de..cb7766797 100644
--- a/kernel/drivers/net/ethernet/freescale/gianfar.h
+++ b/kernel/drivers/net/ethernet/freescale/gianfar.h
@@ -71,11 +71,6 @@ struct ethtool_rx_list {
 /* Number of bytes to align the rx bufs to */
 #define RXBUF_ALIGNMENT 64
 
-/* The number of bytes which composes a unit for the purpose of
- * allocating data buffers.  ie-for any given MTU, the data buffer
- * will be the next highest multiple of 512 bytes. */
-#define INCREMENTAL_BUFFER_SIZE 512
-
 #define PHY_INIT_TIMEOUT 100000
 
 #define DRV_NAME "gfar-enet"
@@ -92,6 +87,8 @@ extern const char gfar_driver_version[];
 #define DEFAULT_TX_RING_SIZE	256
 #define DEFAULT_RX_RING_SIZE	256
 
+#define GFAR_RX_BUFF_ALLOC	16
+
 #define GFAR_RX_MAX_RING_SIZE   256
 #define GFAR_TX_MAX_RING_SIZE   256
 
@@ -103,11 +100,14 @@ extern const char gfar_driver_version[];
 #define DEFAULT_RX_LFC_THR  16
 #define DEFAULT_LFC_PTVVAL  4
 
-#define DEFAULT_RX_BUFFER_SIZE  1536
+#define GFAR_RXB_SIZE 1536
+#define GFAR_SKBFRAG_SIZE (RXBUF_ALIGNMENT + GFAR_RXB_SIZE \
+			  + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define GFAR_RXB_TRUESIZE 2048
+
 #define TX_RING_MOD_MASK(size) (size-1)
 #define RX_RING_MOD_MASK(size) (size-1)
-#define JUMBO_BUFFER_SIZE 9728
-#define JUMBO_FRAME_SIZE 9600
+#define GFAR_JUMBO_FRAME_SIZE 9600
 
 #define DEFAULT_FIFO_TX_THR 0x100
 #define DEFAULT_FIFO_TX_STARVE 0x40
@@ -340,6 +340,7 @@ extern const char gfar_driver_version[];
 #define IEVENT_MAG		0x00000800
 #define IEVENT_GRSC		0x00000100
 #define IEVENT_RXF0		0x00000080
+#define IEVENT_FGPI		0x00000010
 #define IEVENT_FIR		0x00000008
 #define IEVENT_FIQ		0x00000004
 #define IEVENT_DPE		0x00000002
@@ -372,6 +373,7 @@ extern const char gfar_driver_version[];
 #define IMASK_MAG		0x00000800
 #define IMASK_GRSC              0x00000100
 #define IMASK_RXFEN0		0x00000080
+#define IMASK_FGPI		0x00000010
 #define IMASK_FIR		0x00000008
 #define IMASK_FIQ		0x00000004
 #define IMASK_DPE		0x00000002
@@ -540,6 +542,9 @@ extern const char gfar_driver_version[];
 
 #define GFAR_INT_NAME_MAX	(IFNAMSIZ + 6)	/* '_g#_xx' */
 
+#define GFAR_WOL_MAGIC		0x00000001
+#define GFAR_WOL_FILER_UCAST	0x00000002
+
 struct txbd8
 {
 	union {
@@ -640,6 +645,7 @@ struct rmon_mib
 };
 
 struct gfar_extra_stats {
+	atomic64_t rx_alloc_err;
 	atomic64_t rx_large;
 	atomic64_t rx_short;
 	atomic64_t rx_nonoctet;
@@ -651,7 +657,6 @@ struct gfar_extra_stats {
 	atomic64_t eberr;
 	atomic64_t tx_babt;
 	atomic64_t tx_underrun;
-	atomic64_t rx_skbmissing;
 	atomic64_t tx_timeout;
 };
 
@@ -917,6 +922,8 @@ struct gfar {
 #define FSL_GIANFAR_DEV_HAS_BD_STASHING		0x00000200
 #define FSL_GIANFAR_DEV_HAS_BUF_STASHING	0x00000400
 #define FSL_GIANFAR_DEV_HAS_TIMER		0x00000800
+#define FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER	0x00001000
+#define FSL_GIANFAR_DEV_HAS_RX_FILER		0x00002000
 
 #if (MAXGROUPS == 2)
 #define DEFAULT_MAPPING 	0xAA
@@ -1012,34 +1019,42 @@ struct rx_q_stats {
 	unsigned long rx_dropped;
 };
 
+struct gfar_rx_buff {
+	dma_addr_t dma;
+	struct page *page;
+	unsigned int page_offset;
+};
+
 /**
  *	struct gfar_priv_rx_q - per rx queue structure
- *	@rx_skbuff: skb pointers
- *	@skb_currx: currently use skb pointer
+ *	@rx_buff: Array of buffer info metadata structs
  *	@rx_bd_base: First rx buffer descriptor
- *	@cur_rx: Next free rx ring entry
+ *	@next_to_use: index of the next buffer to be alloc'd
+ *	@next_to_clean: index of the next buffer to be cleaned
  *	@qindex: index of this queue
- *	@dev: back pointer to the dev structure
+ *	@ndev: back pointer to net_device
  *	@rx_ring_size: Rx ring size
  *	@rxcoalescing: enable/disable rx-coalescing
  *	@rxic: receive interrupt coalescing vlaue
  */
 
 struct gfar_priv_rx_q {
-	struct	sk_buff **rx_skbuff __aligned(SMP_CACHE_BYTES);
-	dma_addr_t rx_bd_dma_base;
+	struct	gfar_rx_buff *rx_buff __aligned(SMP_CACHE_BYTES);
 	struct	rxbd8 *rx_bd_base;
-	struct	rxbd8 *cur_rx;
-	struct	net_device *dev;
-	struct gfar_priv_grp *grp;
+	struct	net_device *ndev;
+	struct	device *dev;
+	u16 rx_ring_size;
+	u16 qindex;
+	struct	gfar_priv_grp *grp;
+	u16 next_to_clean;
+	u16 next_to_use;
+	u16 next_to_alloc;
+	struct	sk_buff *skb;
 	struct rx_q_stats stats;
-	u16	skb_currx;
-	u16	qindex;
-	unsigned int	rx_ring_size;
-	/* RX Coalescing values */
+	u32 __iomem *rfbptr;
 	unsigned char rxcoalescing;
 	unsigned long rxic;
-	u32 __iomem *rfbptr;
+	dma_addr_t rx_bd_dma_base;
 };
 
 enum gfar_irqinfo_id {
@@ -1109,7 +1124,6 @@ struct gfar_private {
 	struct device *dev;
 	struct net_device *ndev;
 	enum gfar_errata errata;
-	unsigned int rx_buffer_size;
 
 	u16 uses_rxfcb;
 	u16 padding;
@@ -1145,9 +1159,6 @@ struct gfar_private {
 	int oldduplex;
 	int oldlink;
 
-	/* Bitfield update lock */
-	spinlock_t bflock;
-
 	uint32_t msg_enable;
 
 	struct work_struct reset_task;
@@ -1157,8 +1168,6 @@ struct gfar_private {
 		extended_hash:1,
 		bd_stash_en:1,
 		rx_filer_enable:1,
-		/* Wake-on-LAN enabled */
-		wol_en:1,
 		/* Enable priorty based Tx scheduling in Hw */
 		prio_sched_en:1,
 		/* Flow control flags */
@@ -1187,6 +1196,10 @@ struct gfar_private {
 	u32 __iomem *hash_regs[16];
 	int hash_width;
 
+	/* wake-on-lan settings */
+	u16 wol_opts;
+	u16 wol_supported;
+
 	/*Filer table*/
 	unsigned int ftp_rqfpr[MAX_FILER_IDX + 1];
 	unsigned int ftp_rqfcr[MAX_FILER_IDX + 1];
@@ -1295,6 +1308,28 @@ static inline void gfar_clear_txbd_status(struct txbd8 *bdp)
 	bdp->lstatus = cpu_to_be32(lstatus);
 }
 
+static inline int gfar_rxbd_unused(struct gfar_priv_rx_q *rxq)
+{
+	if (rxq->next_to_clean > rxq->next_to_use)
+		return rxq->next_to_clean - rxq->next_to_use - 1;
+
+	return rxq->rx_ring_size + rxq->next_to_clean - rxq->next_to_use - 1;
+}
+
+static inline u32 gfar_rxbd_dma_lastfree(struct gfar_priv_rx_q *rxq)
+{
+	struct rxbd8 *bdp;
+	u32 bdp_dma;
+	int i;
+
+	i = rxq->next_to_use ? rxq->next_to_use - 1 : rxq->rx_ring_size - 1;
+	bdp = &rxq->rx_bd_base[i];
+	bdp_dma = lower_32_bits(rxq->rx_bd_dma_base);
+	bdp_dma += (uintptr_t)bdp - (uintptr_t)rxq->rx_bd_base;
+
+	return bdp_dma;
+}
+
 irqreturn_t gfar_receive(int irq, void *dev_id);
 int startup_gfar(struct net_device *dev);
 void stop_gfar(struct net_device *dev);
diff --git a/kernel/drivers/net/ethernet/freescale/gianfar_ethtool.c b/kernel/drivers/net/ethernet/freescale/gianfar_ethtool.c
index fda12fb32..4b0ee855e 100644
--- a/kernel/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/kernel/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -61,6 +61,8 @@ static void gfar_gdrvinfo(struct net_device *dev,
 			  struct ethtool_drvinfo *drvinfo);
 
 static const char stat_gstrings[][ETH_GSTRING_LEN] = {
+	/* extra stats */
+	"rx-allocation-errors",
 	"rx-large-frame-errors",
 	"rx-short-frame-errors",
 	"rx-non-octet-errors",
@@ -72,8 +74,8 @@ static const char stat_gstrings[][ETH_GSTRING_LEN] = {
 	"ethernet-bus-error",
 	"tx-babbling-errors",
 	"tx-underrun-errors",
-	"rx-skb-missing-errors",
 	"tx-timeout-errors",
+	/* rmon stats */
 	"tx-rx-64-frames",
 	"tx-rx-65-127-frames",
 	"tx-rx-128-255-frames",
@@ -180,8 +182,6 @@ static void gfar_gdrvinfo(struct net_device *dev,
 		sizeof(drvinfo->version));
 	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, "N/A", sizeof(drvinfo->bus_info));
-	drvinfo->regdump_len = 0;
-	drvinfo->eedump_len = 0;
 }
 
 
@@ -642,31 +642,49 @@ static void gfar_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct gfar_private *priv = netdev_priv(dev);
 
-	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) {
-		wol->supported = WAKE_MAGIC;
-		wol->wolopts = priv->wol_en ? WAKE_MAGIC : 0;
-	} else {
-		wol->supported = wol->wolopts = 0;
-	}
+	wol->supported = 0;
+	wol->wolopts = 0;
+
+	if (priv->wol_supported & GFAR_WOL_MAGIC)
+		wol->supported |= WAKE_MAGIC;
+
+	if (priv->wol_supported & GFAR_WOL_FILER_UCAST)
+		wol->supported |= WAKE_UCAST;
+
+	if (priv->wol_opts & GFAR_WOL_MAGIC)
+		wol->wolopts |= WAKE_MAGIC;
+
+	if (priv->wol_opts & GFAR_WOL_FILER_UCAST)
+		wol->wolopts |= WAKE_UCAST;
 }
 
 static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct gfar_private *priv = netdev_priv(dev);
-	unsigned long flags;
+	u16 wol_opts = 0;
+	int err;
 
-	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) &&
-	    wol->wolopts != 0)
+	if (!priv->wol_supported && wol->wolopts)
 		return -EINVAL;
 
-	if (wol->wolopts & ~WAKE_MAGIC)
+	if (wol->wolopts & ~(WAKE_MAGIC | WAKE_UCAST))
 		return -EINVAL;
 
-	device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC);
+	if (wol->wolopts & WAKE_MAGIC) {
+		wol_opts |= GFAR_WOL_MAGIC;
+	} else {
+		if (wol->wolopts & WAKE_UCAST)
+			wol_opts |= GFAR_WOL_FILER_UCAST;
+	}
 
-	spin_lock_irqsave(&priv->bflock, flags);
-	priv->wol_en =  !!device_may_wakeup(&dev->dev);
-	spin_unlock_irqrestore(&priv->bflock, flags);
+	wol_opts &= priv->wol_supported;
+	priv->wol_opts = 0;
+
+	err = device_set_wakeup_enable(priv->dev, wol_opts);
+	if (err)
+		return err;
+
+	priv->wol_opts = wol_opts;
 
 	return 0;
 }
@@ -677,14 +695,14 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 	u32 fcr = 0x0, fpr = FPR_FILER_MASK;
 
 	if (ethflow & RXH_L2DA) {
-		fcr = RQFCR_PID_DAH |RQFCR_CMP_NOMATCH |
+		fcr = RQFCR_PID_DAH | RQFCR_CMP_NOMATCH |
 		      RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0;
 		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
 		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
 		gfar_write_filer(priv, priv->cur_filer_idx, fcr, fpr);
 		priv->cur_filer_idx = priv->cur_filer_idx - 1;
 
-		fcr = RQFCR_PID_DAL | RQFCR_AND | RQFCR_CMP_NOMATCH |
+		fcr = RQFCR_PID_DAL | RQFCR_CMP_NOMATCH |
 		      RQFCR_HASH | RQFCR_AND | RQFCR_HASHTBL_0;
 		priv->ftp_rqfpr[priv->cur_filer_idx] = fpr;
 		priv->ftp_rqfcr[priv->cur_filer_idx] = fcr;
@@ -903,27 +921,6 @@ static int gfar_check_filer_hardware(struct gfar_private *priv)
 	return 0;
 }
 
-static int gfar_comp_asc(const void *a, const void *b)
-{
-	return memcmp(a, b, 4);
-}
-
-static int gfar_comp_desc(const void *a, const void *b)
-{
-	return -memcmp(a, b, 4);
-}
-
-static void gfar_swap(void *a, void *b, int size)
-{
-	u32 *_a = a;
-	u32 *_b = b;
-
-	swap(_a[0], _b[0]);
-	swap(_a[1], _b[1]);
-	swap(_a[2], _b[2]);
-	swap(_a[3], _b[3]);
-}
-
 /* Write a mask to filer cache */
 static void gfar_set_mask(u32 mask, struct filer_table *tab)
 {
@@ -1273,310 +1270,6 @@ static int gfar_convert_to_filer(struct ethtool_rx_flow_spec *rule,
 	return 0;
 }
 
-/* Copy size filer entries */
-static void gfar_copy_filer_entries(struct gfar_filer_entry dst[0],
-				    struct gfar_filer_entry src[0], s32 size)
-{
-	while (size > 0) {
-		size--;
-		dst[size].ctrl = src[size].ctrl;
-		dst[size].prop = src[size].prop;
-	}
-}
-
-/* Delete the contents of the filer-table between start and end
- * and collapse them
- */
-static int gfar_trim_filer_entries(u32 begin, u32 end, struct filer_table *tab)
-{
-	int length;
-
-	if (end > MAX_FILER_CACHE_IDX || end < begin)
-		return -EINVAL;
-
-	end++;
-	length = end - begin;
-
-	/* Copy */
-	while (end < tab->index) {
-		tab->fe[begin].ctrl = tab->fe[end].ctrl;
-		tab->fe[begin++].prop = tab->fe[end++].prop;
-
-	}
-	/* Fill up with don't cares */
-	while (begin < tab->index) {
-		tab->fe[begin].ctrl = 0x60;
-		tab->fe[begin].prop = 0xFFFFFFFF;
-		begin++;
-	}
-
-	tab->index -= length;
-	return 0;
-}
-
-/* Make space on the wanted location */
-static int gfar_expand_filer_entries(u32 begin, u32 length,
-				     struct filer_table *tab)
-{
-	if (length == 0 || length + tab->index > MAX_FILER_CACHE_IDX ||
-	    begin > MAX_FILER_CACHE_IDX)
-		return -EINVAL;
-
-	gfar_copy_filer_entries(&(tab->fe[begin + length]), &(tab->fe[begin]),
-				tab->index - length + 1);
-
-	tab->index += length;
-	return 0;
-}
-
-static int gfar_get_next_cluster_start(int start, struct filer_table *tab)
-{
-	for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1);
-	     start++) {
-		if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) ==
-		    (RQFCR_AND | RQFCR_CLE))
-			return start;
-	}
-	return -1;
-}
-
-static int gfar_get_next_cluster_end(int start, struct filer_table *tab)
-{
-	for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1);
-	     start++) {
-		if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) ==
-		    (RQFCR_CLE))
-			return start;
-	}
-	return -1;
-}
-
-/* Uses hardwares clustering option to reduce
- * the number of filer table entries
- */
-static void gfar_cluster_filer(struct filer_table *tab)
-{
-	s32 i = -1, j, iend, jend;
-
-	while ((i = gfar_get_next_cluster_start(++i, tab)) != -1) {
-		j = i;
-		while ((j = gfar_get_next_cluster_start(++j, tab)) != -1) {
-			/* The cluster entries self and the previous one
-			 * (a mask) must be identical!
-			 */
-			if (tab->fe[i].ctrl != tab->fe[j].ctrl)
-				break;
-			if (tab->fe[i].prop != tab->fe[j].prop)
-				break;
-			if (tab->fe[i - 1].ctrl != tab->fe[j - 1].ctrl)
-				break;
-			if (tab->fe[i - 1].prop != tab->fe[j - 1].prop)
-				break;
-			iend = gfar_get_next_cluster_end(i, tab);
-			jend = gfar_get_next_cluster_end(j, tab);
-			if (jend == -1 || iend == -1)
-				break;
-
-			/* First we make some free space, where our cluster
-			 * element should be. Then we copy it there and finally
-			 * delete in from its old location.
-			 */
-			if (gfar_expand_filer_entries(iend, (jend - j), tab) ==
-			    -EINVAL)
-				break;
-
-			gfar_copy_filer_entries(&(tab->fe[iend + 1]),
-						&(tab->fe[jend + 1]), jend - j);
-
-			if (gfar_trim_filer_entries(jend - 1,
-						    jend + (jend - j),
-						    tab) == -EINVAL)
-				return;
-
-			/* Mask out cluster bit */
-			tab->fe[iend].ctrl &= ~(RQFCR_CLE);
-		}
-	}
-}
-
-/* Swaps the masked bits of a1<>a2 and b1<>b2 */
-static void gfar_swap_bits(struct gfar_filer_entry *a1,
-			   struct gfar_filer_entry *a2,
-			   struct gfar_filer_entry *b1,
-			   struct gfar_filer_entry *b2, u32 mask)
-{
-	u32 temp[4];
-	temp[0] = a1->ctrl & mask;
-	temp[1] = a2->ctrl & mask;
-	temp[2] = b1->ctrl & mask;
-	temp[3] = b2->ctrl & mask;
-
-	a1->ctrl &= ~mask;
-	a2->ctrl &= ~mask;
-	b1->ctrl &= ~mask;
-	b2->ctrl &= ~mask;
-
-	a1->ctrl |= temp[1];
-	a2->ctrl |= temp[0];
-	b1->ctrl |= temp[3];
-	b2->ctrl |= temp[2];
-}
-
-/* Generate a list consisting of masks values with their start and
- * end of validity and block as indicator for parts belonging
- * together (glued by ANDs) in mask_table
- */
-static u32 gfar_generate_mask_table(struct gfar_mask_entry *mask_table,
-				    struct filer_table *tab)
-{
-	u32 i, and_index = 0, block_index = 1;
-
-	for (i = 0; i < tab->index; i++) {
-
-		/* LSByte of control = 0 sets a mask */
-		if (!(tab->fe[i].ctrl & 0xF)) {
-			mask_table[and_index].mask = tab->fe[i].prop;
-			mask_table[and_index].start = i;
-			mask_table[and_index].block = block_index;
-			if (and_index >= 1)
-				mask_table[and_index - 1].end = i - 1;
-			and_index++;
-		}
-		/* cluster starts and ends will be separated because they should
-		 * hold their position
-		 */
-		if (tab->fe[i].ctrl & RQFCR_CLE)
-			block_index++;
-		/* A not set AND indicates the end of a depended block */
-		if (!(tab->fe[i].ctrl & RQFCR_AND))
-			block_index++;
-	}
-
-	mask_table[and_index - 1].end = i - 1;
-
-	return and_index;
-}
-
-/* Sorts the entries of mask_table by the values of the masks.
- * Important: The 0xFF80 flags of the first and last entry of a
- * block must hold their position (which queue, CLusterEnable, ReJEct,
- * AND)
- */
-static void gfar_sort_mask_table(struct gfar_mask_entry *mask_table,
-				 struct filer_table *temp_table, u32 and_index)
-{
-	/* Pointer to compare function (_asc or _desc) */
-	int (*gfar_comp)(const void *, const void *);
-
-	u32 i, size = 0, start = 0, prev = 1;
-	u32 old_first, old_last, new_first, new_last;
-
-	gfar_comp = &gfar_comp_desc;
-
-	for (i = 0; i < and_index; i++) {
-		if (prev != mask_table[i].block) {
-			old_first = mask_table[start].start + 1;
-			old_last = mask_table[i - 1].end;
-			sort(mask_table + start, size,
-			     sizeof(struct gfar_mask_entry),
-			     gfar_comp, &gfar_swap);
-
-			/* Toggle order for every block. This makes the
-			 * thing more efficient!
-			 */
-			if (gfar_comp == gfar_comp_desc)
-				gfar_comp = &gfar_comp_asc;
-			else
-				gfar_comp = &gfar_comp_desc;
-
-			new_first = mask_table[start].start + 1;
-			new_last = mask_table[i - 1].end;
-
-			gfar_swap_bits(&temp_table->fe[new_first],
-				       &temp_table->fe[old_first],
-				       &temp_table->fe[new_last],
-				       &temp_table->fe[old_last],
-				       RQFCR_QUEUE | RQFCR_CLE |
-				       RQFCR_RJE | RQFCR_AND);
-
-			start = i;
-			size = 0;
-		}
-		size++;
-		prev = mask_table[i].block;
-	}
-}
-
-/* Reduces the number of masks needed in the filer table to save entries
- * This is done by sorting the masks of a depended block. A depended block is
- * identified by gluing ANDs or CLE. The sorting order toggles after every
- * block. Of course entries in scope of a mask must change their location with
- * it.
- */
-static int gfar_optimize_filer_masks(struct filer_table *tab)
-{
-	struct filer_table *temp_table;
-	struct gfar_mask_entry *mask_table;
-
-	u32 and_index = 0, previous_mask = 0, i = 0, j = 0, size = 0;
-	s32 ret = 0;
-
-	/* We need a copy of the filer table because
-	 * we want to change its order
-	 */
-	temp_table = kmemdup(tab, sizeof(*temp_table), GFP_KERNEL);
-	if (temp_table == NULL)
-		return -ENOMEM;
-
-	mask_table = kcalloc(MAX_FILER_CACHE_IDX / 2 + 1,
-			     sizeof(struct gfar_mask_entry), GFP_KERNEL);
-
-	if (mask_table == NULL) {
-		ret = -ENOMEM;
-		goto end;
-	}
-
-	and_index = gfar_generate_mask_table(mask_table, tab);
-
-	gfar_sort_mask_table(mask_table, temp_table, and_index);
-
-	/* Now we can copy the data from our duplicated filer table to
-	 * the real one in the order the mask table says
-	 */
-	for (i = 0; i < and_index; i++) {
-		size = mask_table[i].end - mask_table[i].start + 1;
-		gfar_copy_filer_entries(&(tab->fe[j]),
-				&(temp_table->fe[mask_table[i].start]), size);
-		j += size;
-	}
-
-	/* And finally we just have to check for duplicated masks and drop the
-	 * second ones
-	 */
-	for (i = 0; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) {
-		if (tab->fe[i].ctrl == 0x80) {
-			previous_mask = i++;
-			break;
-		}
-	}
-	for (; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) {
-		if (tab->fe[i].ctrl == 0x80) {
-			if (tab->fe[i].prop == tab->fe[previous_mask].prop) {
-				/* Two identical ones found!
-				 * So drop the second one!
-				 */
-				gfar_trim_filer_entries(i, i, tab);
-			} else
-				/* Not identical! */
-				previous_mask = i;
-		}
-	}
-
-	kfree(mask_table);
-end:	kfree(temp_table);
-	return ret;
-}
-
 /* Write the bit-pattern from software's buffer to hardware registers */
 static int gfar_write_filer_table(struct gfar_private *priv,
 				  struct filer_table *tab)
@@ -1586,11 +1279,10 @@ static int gfar_write_filer_table(struct gfar_private *priv,
 		return -EBUSY;
 
 	/* Fill regular entries */
-	for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop);
-	     i++)
+	for (; i < MAX_FILER_IDX && (tab->fe[i].ctrl | tab->fe[i].prop); i++)
 		gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop);
 	/* Fill the rest with fall-troughs */
-	for (; i < MAX_FILER_IDX - 1; i++)
+	for (; i < MAX_FILER_IDX; i++)
 		gfar_write_filer(priv, i, 0x60, 0xFFFFFFFF);
 	/* Last entry must be default accept
 	 * because that's what people expect
@@ -1624,7 +1316,6 @@ static int gfar_process_filer_changes(struct gfar_private *priv)
 {
 	struct ethtool_flow_spec_container *j;
 	struct filer_table *tab;
-	s32 i = 0;
 	s32 ret = 0;
 
 	/* So index is set to zero, too! */
@@ -1649,17 +1340,6 @@ static int gfar_process_filer_changes(struct gfar_private *priv)
 		}
 	}
 
-	i = tab->index;
-
-	/* Optimizations to save entries */
-	gfar_cluster_filer(tab);
-	gfar_optimize_filer_masks(tab);
-
-	pr_debug("\tSummary:\n"
-		 "\tData on hardware: %d\n"
-		 "\tCompression rate: %d%%\n",
-		 tab->index, 100 - (100 * tab->index) / i);
-
 	/* Write everything to hardware */
 	ret = gfar_write_filer_table(priv, tab);
 	if (ret == -EBUSY) {
@@ -1725,13 +1405,14 @@ static int gfar_add_cls(struct gfar_private *priv,
 	}
 
 process:
+	priv->rx_list.count++;
 	ret = gfar_process_filer_changes(priv);
 	if (ret)
 		goto clean_list;
-	priv->rx_list.count++;
 	return ret;
 
 clean_list:
+	priv->rx_list.count--;
 	list_del(&temp->list);
 clean_mem:
 	kfree(temp);
diff --git a/kernel/drivers/net/ethernet/freescale/gianfar_ptp.c b/kernel/drivers/net/ethernet/freescale/gianfar_ptp.c
index 8e3cd77aa..b40fba929 100644
--- a/kernel/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/kernel/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -467,7 +467,7 @@ static int gianfar_ptp_probe(struct platform_device *dev)
 
 	etsects->irq = platform_get_irq(dev, 0);
 
-	if (etsects->irq == NO_IRQ) {
+	if (etsects->irq < 0) {
 		pr_err("irq not in device tree\n");
 		goto no_node;
 	}
@@ -557,6 +557,7 @@ static const struct of_device_id match_table[] = {
 	{ .compatible = "fsl,etsec-ptp" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, match_table);
 
 static struct platform_driver gianfar_ptp_driver = {
 	.driver = {
diff --git a/kernel/drivers/net/ethernet/freescale/ucc_geth.c b/kernel/drivers/net/ethernet/freescale/ucc_geth.c
index 4dd40e057..650f7888e 100644
--- a/kernel/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/kernel/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1384,6 +1384,8 @@ static int adjust_enet_interface(struct ucc_geth_private *ugeth)
 		value = phy_read(tbiphy, ENET_TBI_MII_CR);
 		value &= ~0x1000;	/* Turn off autonegotiation */
 		phy_write(tbiphy, ENET_TBI_MII_CR, value);
+
+		put_device(&tbiphy->dev);
 	}
 
 	init_check_frame_length_mode(ug_info->lengthCheckRx, &ug_regs->maccfg2);
@@ -1702,8 +1704,10 @@ static void uec_configure_serdes(struct net_device *dev)
 	 * everything for us?  Resetting it takes the link down and requires
 	 * several seconds for it to come back.
 	 */
-	if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS)
+	if (phy_read(tbiphy, ENET_TBI_MII_SR) & TBISR_LSTATUS) {
+		put_device(&tbiphy->dev);
 		return;
+	}
 
 	/* Single clk mode, mii mode off(for serdes communication) */
 	phy_write(tbiphy, ENET_TBI_MII_ANA, TBIANA_SETTINGS);
@@ -1711,6 +1715,8 @@ static void uec_configure_serdes(struct net_device *dev)
 	phy_write(tbiphy, ENET_TBI_MII_TBICON, TBICON_CLK_SELECT);
 
 	phy_write(tbiphy, ENET_TBI_MII_CR, TBICR_SETTINGS);
+
+	put_device(&tbiphy->dev);
 }
 
 /* Configure the PHY for dev.
diff --git a/kernel/drivers/net/ethernet/freescale/ucc_geth_ethtool.c b/kernel/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
index cc83350d5..89714f5e0 100644
--- a/kernel/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
+++ b/kernel/drivers/net/ethernet/freescale/ucc_geth_ethtool.c
@@ -351,8 +351,6 @@ uec_get_drvinfo(struct net_device *netdev,
 	strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
 	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, "QUICC ENGINE", sizeof(drvinfo->bus_info));
-	drvinfo->eedump_len = 0;
-	drvinfo->regdump_len = uec_get_regs_len(netdev);
 }
 
 #ifdef CONFIG_PM