Merge branch 'master' of git://git.denx.de/u-boot-net

19 files changed, 473 insertions, 193 deletions

diff --git a/drivers/net/designware.c b/drivers/net/designware.c
index 8413d57767..22155b4d94 100644
--- a/drivers/net/designware.c
+++ b/drivers/net/designware.c
@@ -96,7 +96,7 @@ static int mac_reset(struct eth_device *dev)
 	ulong start;
 	int timeout = CONFIG_MACRESET_TIMEOUT;
 
-	writel(DMAMAC_SRST, &dma_p->busmode);
+	writel(readl(&dma_p->busmode) | DMAMAC_SRST, &dma_p->busmode);
 
 	if (priv->interface != PHY_INTERFACE_MODE_RGMII)
 		writel(MII_PORTSELECT, &mac_p->conf);
diff --git a/drivers/net/designware.h b/drivers/net/designware.h
index e80002a0e4..5440c9215f 100644
--- a/drivers/net/designware.h
+++ b/drivers/net/designware.h
@@ -112,7 +112,7 @@ struct dmamacdescr {
 	u32 dmamac_cntl;
 	void *dmamac_addr;
 	struct dmamacdescr *dmamac_next;
-};
+} __aligned(16);
 
 /*
  * txrx_status definitions
@@ -224,8 +224,7 @@ struct dw_eth_dev {
 	u32 tx_currdescnum;
 	u32 rx_currdescnum;
 	u32 phy_configured;
-	int link_printed;
-	u32 padding;
+	u32 link_printed;
 
 	struct dmamacdescr tx_mac_descrtable[CONFIG_TX_DESCR_NUM];
 	struct dmamacdescr rx_mac_descrtable[CONFIG_RX_DESCR_NUM];
@@ -237,7 +236,7 @@ struct dw_eth_dev {
 	struct eth_dma_regs *dma_regs_p;
 
 	struct eth_device *dev;
-} __attribute__ ((aligned(8)));
+};
 
 /* Speed specific definitions */
 #define SPEED_10M		1
diff --git a/drivers/net/dm9000x.c b/drivers/net/dm9000x.c
index f7170e0554..b68d808c74 100644
--- a/drivers/net/dm9000x.c
+++ b/drivers/net/dm9000x.c
@@ -342,6 +342,15 @@ static int dm9000_init(struct eth_device *dev, bd_t *bd)
 	DM9000_iow(DM9000_ISR, ISR_ROOS | ISR_ROS | ISR_PTS | ISR_PRS);
 
 	printf("MAC: %pM\n", dev->enetaddr);
+	if (!is_valid_ether_addr(dev->enetaddr)) {
+#ifdef CONFIG_RANDOM_MACADDR
+		printf("Bad MAC address (uninitialized EEPROM?), randomizing\n");
+		eth_random_enetaddr(dev->enetaddr);
+		printf("MAC: %pM\n", dev->enetaddr);
+#else
+		printf("WARNING: Bad MAC address (uninitialized EEPROM?)\n");
+#endif
+	}
 
 	/* fill device MAC address registers */
 	for (i = 0, oft = DM9000_PAR; i < 6; i++, oft++)
diff --git a/drivers/net/e1000.c b/drivers/net/e1000.c
index 57aa53dbae..9a66e68ae0 100644
--- a/drivers/net/e1000.c
+++ b/drivers/net/e1000.c
@@ -114,12 +114,13 @@ static int e1000_write_phy_reg(struct e1000_hw *hw, uint32_t reg_addr,
 static int32_t e1000_phy_hw_reset(struct e1000_hw *hw);
 static int e1000_phy_reset(struct e1000_hw *hw);
 static int e1000_detect_gig_phy(struct e1000_hw *hw);
-static void e1000_put_hw_eeprom_semaphore(struct e1000_hw *hw);
 static void e1000_set_media_type(struct e1000_hw *hw);
 
 static int32_t e1000_swfw_sync_acquire(struct e1000_hw *hw, uint16_t mask);
 static int32_t e1000_check_phy_reset_block(struct e1000_hw *hw);
 
+#ifndef CONFIG_E1000_NO_NVM
+static void e1000_put_hw_eeprom_semaphore(struct e1000_hw *hw);
 static int32_t e1000_read_eeprom(struct e1000_hw *hw, uint16_t offset,
 		uint16_t words,
 		uint16_t *data);
@@ -885,6 +886,7 @@ static int e1000_validate_eeprom_checksum(struct e1000_hw *hw)
 
 	return -E1000_ERR_EEPROM;
 }
+#endif /* CONFIG_E1000_NO_NVM */
 
 /*****************************************************************************
  * Set PHY to class A mode
@@ -897,6 +899,7 @@ static int e1000_validate_eeprom_checksum(struct e1000_hw *hw)
 static int32_t
 e1000_set_phy_mode(struct e1000_hw *hw)
 {
+#ifndef CONFIG_E1000_NO_NVM
 	int32_t ret_val;
 	uint16_t eeprom_data;
 
@@ -923,10 +926,11 @@ e1000_set_phy_mode(struct e1000_hw *hw)
 			hw->phy_reset_disable = false;
 		}
 	}
-
+#endif
 	return E1000_SUCCESS;
 }
 
+#ifndef CONFIG_E1000_NO_NVM
 /***************************************************************************
  *
  * Obtaining software semaphore bit (SMBI) before resetting PHY.
@@ -965,6 +969,7 @@ e1000_get_software_semaphore(struct e1000_hw *hw)
 
 	return E1000_SUCCESS;
 }
+#endif
 
 /***************************************************************************
  * This function clears HW semaphore bits.
@@ -977,6 +982,7 @@ e1000_get_software_semaphore(struct e1000_hw *hw)
 static void
 e1000_put_hw_eeprom_semaphore(struct e1000_hw *hw)
 {
+#ifndef CONFIG_E1000_NO_NVM
 	 uint32_t swsm;
 
 	DEBUGFUNC();
@@ -991,6 +997,7 @@ e1000_put_hw_eeprom_semaphore(struct e1000_hw *hw)
 	} else
 		swsm &= ~(E1000_SWSM_SWESMBI);
 	E1000_WRITE_REG(hw, SWSM, swsm);
+#endif
 }
 
 /***************************************************************************
@@ -1007,6 +1014,7 @@ e1000_put_hw_eeprom_semaphore(struct e1000_hw *hw)
 static int32_t
 e1000_get_hw_eeprom_semaphore(struct e1000_hw *hw)
 {
+#ifndef CONFIG_E1000_NO_NVM
 	int32_t timeout;
 	uint32_t swsm;
 
@@ -1043,7 +1051,7 @@ e1000_get_hw_eeprom_semaphore(struct e1000_hw *hw)
 				"SWESMBI bit is set.\n");
 		return -E1000_ERR_EEPROM;
 	}
-
+#endif
 	return E1000_SUCCESS;
 }
 
@@ -1097,6 +1105,7 @@ static bool e1000_is_second_port(struct e1000_hw *hw)
 	}
 }
 
+#ifndef CONFIG_E1000_NO_NVM
 /******************************************************************************
  * Reads the adapter's MAC address from the EEPROM and inverts the LSB for the
  * second function of dual function devices
@@ -1136,6 +1145,7 @@ e1000_read_mac_addr(struct eth_device *nic)
 #endif
 	return 0;
 }
+#endif
 
 /******************************************************************************
  * Initializes receive address filters.
@@ -1764,9 +1774,11 @@ static int
 e1000_setup_link(struct eth_device *nic)
 {
 	struct e1000_hw *hw = nic->priv;
-	uint32_t ctrl_ext;
 	int32_t ret_val;
+#ifndef CONFIG_E1000_NO_NVM
+	uint32_t ctrl_ext;
 	uint16_t eeprom_data;
+#endif
 
 	DEBUGFUNC();
 
@@ -1775,6 +1787,7 @@ e1000_setup_link(struct eth_device *nic)
 	if (e1000_check_phy_reset_block(hw))
 		return E1000_SUCCESS;
 
+#ifndef CONFIG_E1000_NO_NVM
 	/* Read and store word 0x0F of the EEPROM. This word contains bits
 	 * that determine the hardware's default PAUSE (flow control) mode,
 	 * a bit that determines whether the HW defaults to enabling or
@@ -1788,7 +1801,7 @@ e1000_setup_link(struct eth_device *nic)
 		DEBUGOUT("EEPROM Read Error\n");
 		return -E1000_ERR_EEPROM;
 	}
-
+#endif
 	if (hw->fc == e1000_fc_default) {
 		switch (hw->mac_type) {
 		case e1000_ich8lan:
@@ -1797,6 +1810,7 @@ e1000_setup_link(struct eth_device *nic)
 			hw->fc = e1000_fc_full;
 			break;
 		default:
+#ifndef CONFIG_E1000_NO_NVM
 			ret_val = e1000_read_eeprom(hw,
 				EEPROM_INIT_CONTROL2_REG, 1, &eeprom_data);
 			if (ret_val) {
@@ -1809,6 +1823,7 @@ e1000_setup_link(struct eth_device *nic)
 				    EEPROM_WORD0F_ASM_DIR)
 				hw->fc = e1000_fc_tx_pause;
 			else
+#endif
 				hw->fc = e1000_fc_full;
 			break;
 		}
@@ -1828,6 +1843,7 @@ e1000_setup_link(struct eth_device *nic)
 
 	DEBUGOUT("After fix-ups FlowControl is now = %x\n", hw->fc);
 
+#ifndef CONFIG_E1000_NO_NVM
 	/* Take the 4 bits from EEPROM word 0x0F that determine the initial
 	 * polarity value for the SW controlled pins, and setup the
 	 * Extended Device Control reg with that info.
@@ -1840,6 +1856,7 @@ e1000_setup_link(struct eth_device *nic)
 			    SWDPIO__EXT_SHIFT);
 		E1000_WRITE_REG(hw, CTRL_EXT, ctrl_ext);
 	}
+#endif
 
 	/* Call the necessary subroutine to configure the link. */
 	ret_val = (hw->media_type == e1000_media_type_fiber) ?
@@ -5196,6 +5213,7 @@ e1000_initialize(bd_t * bis)
 		e1000_reset_hw(hw);
 		list_add_tail(&hw->list_node, &e1000_hw_list);
 
+#ifndef CONFIG_E1000_NO_NVM
 		/* Validate the EEPROM and get chipset information */
 #if !defined(CONFIG_MVBC_1G)
 		if (e1000_init_eeprom_params(hw)) {
@@ -5206,11 +5224,17 @@ e1000_initialize(bd_t * bis)
 			continue;
 #endif
 		e1000_read_mac_addr(nic);
+#endif
 		e1000_get_bus_type(hw);
 
+#ifndef CONFIG_E1000_NO_NVM
 		printf("e1000: %02x:%02x:%02x:%02x:%02x:%02x\n       ",
 		       nic->enetaddr[0], nic->enetaddr[1], nic->enetaddr[2],
 		       nic->enetaddr[3], nic->enetaddr[4], nic->enetaddr[5]);
+#else
+		memset(nic->enetaddr, 0, 6);
+		printf("e1000: no NVM\n");
+#endif
 
 		/* Set up the function pointers and register the device */
 		nic->init = e1000_init;
diff --git a/drivers/net/e1000.h b/drivers/net/e1000.h
index 25884f5bc5..ff87af2ef8 100644
--- a/drivers/net/e1000.h
+++ b/drivers/net/e1000.h
@@ -63,11 +63,14 @@ struct e1000_hw_stats;
 
 /* Internal E1000 helper functions */
 struct e1000_hw *e1000_find_card(unsigned int cardnum);
+
+#ifndef CONFIG_E1000_NO_NVM
 int32_t e1000_acquire_eeprom(struct e1000_hw *hw);
 void e1000_standby_eeprom(struct e1000_hw *hw);
 void e1000_release_eeprom(struct e1000_hw *hw);
 void e1000_raise_ee_clk(struct e1000_hw *hw, uint32_t *eecd);
 void e1000_lower_ee_clk(struct e1000_hw *hw, uint32_t *eecd);
+#endif
 
 #ifdef CONFIG_E1000_SPI
 int do_e1000_spi(cmd_tbl_t *cmdtp, struct e1000_hw *hw,
@@ -1019,6 +1022,7 @@ struct e1000_hw_stats {
 	uint64_t tsctfc;
 };
 
+#ifndef CONFIG_E1000_NO_NVM
 struct e1000_eeprom_info {
 e1000_eeprom_type type;
 	uint16_t word_size;
@@ -1029,6 +1033,7 @@ e1000_eeprom_type type;
 	bool use_eerd;
 	bool use_eewr;
 };
+#endif
 
 typedef enum {
     e1000_smart_speed_default = 0,
@@ -1081,10 +1086,14 @@ struct e1000_hw {
 	uint32_t io_base;
 #endif
 	uint32_t		asf_firmware_present;
+#ifndef CONFIG_E1000_NO_NVM
 	uint32_t		eeprom_semaphore_present;
+#endif
 	uint32_t		swfw_sync_present;
 	uint32_t		swfwhw_semaphore_present;
+#ifndef CONFIG_E1000_NO_NVM
 	struct e1000_eeprom_info eeprom;
+#endif
 	e1000_ms_type		master_slave;
 	e1000_ms_type		original_master_slave;
 	e1000_ffe_config	ffe_config_state;
diff --git a/drivers/net/fsl_mdio.c b/drivers/net/fsl_mdio.c
index ce36bd7a34..1d88e6504b 100644
--- a/drivers/net/fsl_mdio.c
+++ b/drivers/net/fsl_mdio.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2009-2010 Freescale Semiconductor, Inc.
+ * Copyright 2009-2010, 2013 Freescale Semiconductor, Inc.
  *	Jun-jie Zhang <b18070@freescale.com>
  *	Mingkai Hu <Mingkai.hu@freescale.com>
  *
@@ -13,7 +13,7 @@
 #include <asm/errno.h>
 #include <asm/fsl_enet.h>
 
-void tsec_local_mdio_write(struct tsec_mii_mng *phyregs, int port_addr,
+void tsec_local_mdio_write(struct tsec_mii_mng __iomem *phyregs, int port_addr,
 		int dev_addr, int regnum, int value)
 {
 	int timeout = 1000000;
@@ -26,7 +26,7 @@ void tsec_local_mdio_write(struct tsec_mii_mng *phyregs, int port_addr,
 		;
 }
 
-int tsec_local_mdio_read(struct tsec_mii_mng *phyregs, int port_addr,
+int tsec_local_mdio_read(struct tsec_mii_mng __iomem *phyregs, int port_addr,
 		int dev_addr, int regnum)
 {
 	int value;
@@ -57,7 +57,8 @@ int tsec_local_mdio_read(struct tsec_mii_mng *phyregs, int port_addr,
 
 static int fsl_pq_mdio_reset(struct mii_dev *bus)
 {
-	struct tsec_mii_mng *regs = bus->priv;
+	struct tsec_mii_mng __iomem *regs =
+		(struct tsec_mii_mng __iomem *)bus->priv;
 
 	/* Reset MII (due to new addresses) */
 	out_be32(&regs->miimcfg, MIIMCFG_RESET_MGMT);
@@ -72,7 +73,8 @@ static int fsl_pq_mdio_reset(struct mii_dev *bus)
 
 int tsec_phy_read(struct mii_dev *bus, int addr, int dev_addr, int regnum)
 {
-	struct tsec_mii_mng *phyregs = bus->priv;
+	struct tsec_mii_mng __iomem *phyregs =
+		(struct tsec_mii_mng __iomem *)bus->priv;
 
 	return tsec_local_mdio_read(phyregs, addr, dev_addr, regnum);
 }
@@ -80,7 +82,8 @@ int tsec_phy_read(struct mii_dev *bus, int addr, int dev_addr, int regnum)
 int tsec_phy_write(struct mii_dev *bus, int addr, int dev_addr, int regnum,
 			u16 value)
 {
-	struct tsec_mii_mng *phyregs = bus->priv;
+	struct tsec_mii_mng __iomem *phyregs =
+		(struct tsec_mii_mng __iomem *)bus->priv;
 
 	tsec_local_mdio_write(phyregs, addr, dev_addr, regnum, value);
 
@@ -101,7 +104,7 @@ int fsl_pq_mdio_init(bd_t *bis, struct fsl_pq_mdio_info *info)
 	bus->reset = fsl_pq_mdio_reset;
 	sprintf(bus->name, info->name);
 
-	bus->priv = info->regs;
+	bus->priv = (void *)info->regs;
 
 	return mdio_register(bus);
 }
diff --git a/drivers/net/mvgbe.c b/drivers/net/mvgbe.c
index 6c901d1eaa..0cd06b6a69 100644
--- a/drivers/net/mvgbe.c
+++ b/drivers/net/mvgbe.c
@@ -420,8 +420,9 @@ static int mvgbe_init(struct eth_device *dev)
 {
 	struct mvgbe_device *dmvgbe = to_mvgbe(dev);
 	struct mvgbe_registers *regs = dmvgbe->regs;
-#if (defined (CONFIG_MII) || defined (CONFIG_CMD_MII)) \
-	 && defined (CONFIG_SYS_FAULT_ECHO_LINK_DOWN)
+#if (defined(CONFIG_MII) || defined(CONFIG_CMD_MII)) &&  \
+	!defined(CONFIG_PHYLIB) &&			 \
+	defined(CONFIG_SYS_FAULT_ECHO_LINK_DOWN)
 	int i;
 #endif
 	/* setup RX rings */
diff --git a/drivers/net/phy/atheros.c b/drivers/net/phy/atheros.c
index 0f2dfd6126..b20b4df981 100644
--- a/drivers/net/phy/atheros.c
+++ b/drivers/net/phy/atheros.c
@@ -40,7 +40,7 @@ static int ar8035_config(struct phy_device *phydev)
 static struct phy_driver AR8021_driver =  {
 	.name = "AR8021",
 	.uid = 0x4dd040,
-	.mask = 0xfffff0,
+	.mask = 0x4fffff,
 	.features = PHY_GBIT_FEATURES,
 	.config = ar8021_config,
 	.startup = genphy_startup,
@@ -48,11 +48,11 @@ static struct phy_driver AR8021_driver =  {
 };
 
 static struct phy_driver AR8031_driver =  {
-	.name = "AR8031",
+	.name = "AR8031/AR8033",
 	.uid = 0x4dd074,
-	.mask = 0xfffff0,
+	.mask = 0x4fffff,
 	.features = PHY_GBIT_FEATURES,
-	.config = genphy_config,
+	.config = ar8021_config,
 	.startup = genphy_startup,
 	.shutdown = genphy_shutdown,
 };
diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index a7450f8326..5d7e3be52e 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -100,6 +100,19 @@ int ksz9021_phy_extended_read(struct phy_device *phydev, int regnum)
 	return phy_read(phydev, MDIO_DEVAD_NONE, MII_KSZ9021_EXTENDED_DATAR);
 }
 
+
+static int ksz9021_phy_extread(struct phy_device *phydev, int addr, int devaddr,
+			      int regnum)
+{
+	return ksz9021_phy_extended_read(phydev, regnum);
+}
+
+static int ksz9021_phy_extwrite(struct phy_device *phydev, int addr,
+			       int devaddr, int regnum, u16 val)
+{
+	return ksz9021_phy_extended_write(phydev, regnum, val);
+}
+
 /* Micrel ksz9021 */
 static int ksz9021_config(struct phy_device *phydev)
 {
@@ -131,6 +144,8 @@ static struct phy_driver ksz9021_driver = {
 	.config = &ksz9021_config,
 	.startup = &ksz90xx_startup,
 	.shutdown = &genphy_shutdown,
+	.writeext = &ksz9021_phy_extwrite,
+	.readext = &ksz9021_phy_extread,
 };
 #endif
 
@@ -171,14 +186,31 @@ int ksz9031_phy_extended_read(struct phy_device *phydev, int devaddr,
 	return phy_read(phydev, MDIO_DEVAD_NONE, MII_KSZ9031_MMD_REG_DATA);
 }
 
+static int ksz9031_phy_extread(struct phy_device *phydev, int addr, int devaddr,
+			       int regnum)
+{
+	return ksz9031_phy_extended_read(phydev, devaddr, regnum,
+					 MII_KSZ9031_MOD_DATA_NO_POST_INC);
+};
+
+static int ksz9031_phy_extwrite(struct phy_device *phydev, int addr,
+				int devaddr, int regnum, u16 val)
+{
+	return ksz9031_phy_extended_write(phydev, devaddr, regnum,
+					 MII_KSZ9031_MOD_DATA_POST_INC_RW, val);
+};
+
+
 static struct phy_driver ksz9031_driver = {
 	.name = "Micrel ksz9031",
 	.uid  = 0x221620,
-	.mask = 0xfffffe,
+	.mask = 0xfffff0,
 	.features = PHY_GBIT_FEATURES,
 	.config   = &genphy_config,
 	.startup  = &ksz90xx_startup,
 	.shutdown = &genphy_shutdown,
+	.writeext = &ksz9031_phy_extwrite,
+	.readext = &ksz9031_phy_extread,
 };
 
 int phy_micrel_init(void)
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 62925bb286..c691fbbbc6 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -275,13 +275,14 @@ int genphy_parse_link(struct phy_device *phydev)
 	int mii_reg = phy_read(phydev, MDIO_DEVAD_NONE, MII_BMSR);
 
 	/* We're using autonegotiation */
-	if (mii_reg & BMSR_ANEGCAPABLE) {
+	if (phydev->supported & SUPPORTED_Autoneg) {
 		u32 lpa = 0;
 		int gblpa = 0;
 		u32 estatus = 0;
 
 		/* Check for gigabit capability */
-		if (mii_reg & BMSR_ERCAP) {
+		if (phydev->supported & (SUPPORTED_1000baseT_Full |
+					SUPPORTED_1000baseT_Half)) {
 			/* We want a list of states supported by
 			 * both PHYs in the link
 			 */
diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index ddbbc35e27..a3ace68526 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -102,7 +102,7 @@ static int rtl8211x_startup(struct phy_device *phydev)
 static struct phy_driver RTL8211B_driver = {
 	.name = "RealTek RTL8211B",
 	.uid = 0x1cc910,
-	.mask = 0xfffff0,
+	.mask = 0xffffff,
 	.features = PHY_GBIT_FEATURES,
 	.config = &rtl8211x_config,
 	.startup = &rtl8211x_startup,
@@ -113,7 +113,7 @@ static struct phy_driver RTL8211B_driver = {
 static struct phy_driver RTL8211E_driver = {
 	.name = "RealTek RTL8211E",
 	.uid = 0x1cc915,
-	.mask = 0xfffff0,
+	.mask = 0xffffff,
 	.features = PHY_GBIT_FEATURES,
 	.config = &rtl8211x_config,
 	.startup = &rtl8211x_startup,
@@ -124,7 +124,7 @@ static struct phy_driver RTL8211E_driver = {
 static struct phy_driver RTL8211DN_driver = {
 	.name = "RealTek RTL8211DN",
 	.uid = 0x1cc914,
-	.mask = 0xfffff0,
+	.mask = 0xffffff,
 	.features = PHY_GBIT_FEATURES,
 	.config = &rtl8211x_config,
 	.startup = &rtl8211x_startup,
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index 60ed92d203..bfd9815abf 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -12,6 +12,7 @@
  */
 #include <miiphy.h>
 
+/* This code does not check the partner abilities. */
 static int smsc_parse_status(struct phy_device *phydev)
 {
 	int mii_reg;
@@ -64,7 +65,7 @@ static struct phy_driver lan8710_driver = {
 	.mask = 0xffff0,
 	.features = PHY_BASIC_FEATURES,
 	.config = &genphy_config_aneg,
-	.startup = &smsc_startup,
+	.startup = &genphy_startup,
 	.shutdown = &genphy_shutdown,
 };
 
diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index 5cf103e5a1..c555979661 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -49,6 +49,15 @@
 #define MIIM_VSC8574_18G_QSGMII		0x80e0
 #define MIIM_VSC8574_18G_CMDSTAT	0x8000
 
+/* Vitesse VSC8514 control register */
+#define MIIM_VSC8514_GENERAL18		0x12
+#define MIIM_VSC8514_GENERAL19		0x13
+#define MIIM_VSC8514_GENERAL23		0x17
+
+/* Vitesse VSC8514 gerenal purpose register 18 */
+#define MIIM_VSC8514_18G_QSGMII		0x80e0
+#define MIIM_VSC8514_18G_CMDSTAT	0x8000
+
 /* CIS8201 */
 static int vitesse_config(struct phy_device *phydev)
 {
@@ -148,7 +157,7 @@ static int vsc8601_config(struct phy_device *phydev)
 static int vsc8574_config(struct phy_device *phydev)
 {
 	u32 val;
-	/* configure regiser 19G for MAC */
+	/* configure register 19G for MAC */
 	phy_write(phydev, MDIO_DEVAD_NONE, PHY_EXT_PAGE_ACCESS,
 		  PHY_EXT_PAGE_ACCESS_GENERAL);
 
@@ -188,6 +197,53 @@ static int vsc8574_config(struct phy_device *phydev)
 	return 0;
 }
 
+static int vsc8514_config(struct phy_device *phydev)
+{
+	u32 val;
+	int timeout = 1000000;
+
+	/* configure register to access 19G */
+	phy_write(phydev, MDIO_DEVAD_NONE, PHY_EXT_PAGE_ACCESS,
+		  PHY_EXT_PAGE_ACCESS_GENERAL);
+
+	val = phy_read(phydev, MDIO_DEVAD_NONE, MIIM_VSC8514_GENERAL19);
+	if (phydev->interface == PHY_INTERFACE_MODE_QSGMII) {
+		/* set bit 15:14 to '01' for QSGMII mode */
+		val = (val & 0x3fff) | (1 << 14);
+		phy_write(phydev, MDIO_DEVAD_NONE,
+			  MIIM_VSC8514_GENERAL19, val);
+		/* Enable 4 ports MAC QSGMII */
+		phy_write(phydev, MDIO_DEVAD_NONE, MIIM_VSC8514_GENERAL18,
+			  MIIM_VSC8514_18G_QSGMII);
+	} else {
+		/*TODO Add SGMII functionality once spec sheet
+		 * for VSC8514 defines complete functionality
+		 */
+	}
+
+	val = phy_read(phydev, MDIO_DEVAD_NONE, MIIM_VSC8514_GENERAL18);
+	/* When bit 15 is cleared the command has completed */
+	while ((val & MIIM_VSC8514_18G_CMDSTAT) && timeout--)
+		val = phy_read(phydev, MDIO_DEVAD_NONE, MIIM_VSC8514_GENERAL18);
+
+	if (0 == timeout) {
+		printf("PHY 8514 config failed\n");
+		return -1;
+	}
+
+	phy_write(phydev, MDIO_DEVAD_NONE, PHY_EXT_PAGE_ACCESS, 0);
+
+	/* configure register to access 23 */
+	val = phy_read(phydev, MDIO_DEVAD_NONE, MIIM_VSC8514_GENERAL23);
+	/* set bits 10:8 to '000' */
+	val = (val & 0xf8ff);
+	phy_write(phydev, MDIO_DEVAD_NONE, MIIM_VSC8514_GENERAL23, val);
+
+	genphy_config_aneg(phydev);
+
+	return 0;
+}
+
 static struct phy_driver VSC8211_driver = {
 	.name	= "Vitesse VSC8211",
 	.uid	= 0xfc4b0,
@@ -238,6 +294,16 @@ static struct phy_driver VSC8574_driver = {
 	.shutdown = &genphy_shutdown,
 };
 
+static struct phy_driver VSC8514_driver = {
+	.name = "Vitesse VSC8514",
+	.uid = 0x70570,
+	.mask = 0xffff0,
+	.features = PHY_GBIT_FEATURES,
+	.config = &vsc8514_config,
+	.startup = &vitesse_startup,
+	.shutdown = &genphy_shutdown,
+};
+
 static struct phy_driver VSC8601_driver = {
 	.name = "Vitesse VSC8601",
 	.uid = 0x70420,
@@ -298,6 +364,7 @@ int phy_vitesse_init(void)
 	phy_register(&VSC8211_driver);
 	phy_register(&VSC8221_driver);
 	phy_register(&VSC8574_driver);
+	phy_register(&VSC8514_driver);
 	phy_register(&VSC8662_driver);
 	phy_register(&cis8201_driver);
 	phy_register(&cis8204_driver);
diff --git a/drivers/net/rtl8139.c b/drivers/net/rtl8139.c
index 4186699ff9..208ce5ccc4 100644
--- a/drivers/net/rtl8139.c
+++ b/drivers/net/rtl8139.c
@@ -188,7 +188,7 @@ static int rtl_transmit(struct eth_device *dev, void *packet, int length);
 static int rtl_poll(struct eth_device *dev);
 static void rtl_disable(struct eth_device *dev);
 #ifdef CONFIG_MCAST_TFTP/*  This driver already accepts all b/mcast */
-static int rtl_bcast_addr (struct eth_device *dev, u8 bcast_mac, u8 set)
+static int rtl_bcast_addr(struct eth_device *dev, const u8 *bcast_mac, u8 set)
 {
 	return (0);
 }
diff --git a/drivers/net/rtl8169.c b/drivers/net/rtl8169.c
index 13fa9c02fe..d040ab171b 100644
--- a/drivers/net/rtl8169.c
+++ b/drivers/net/rtl8169.c
@@ -246,6 +246,8 @@ static struct {
 	{"RTL-8169sc/8110sc",	0x18, 0xff7e1880,},
 	{"RTL-8168b/8111sb",	0x30, 0xff7e1880,},
 	{"RTL-8168b/8111sb",	0x38, 0xff7e1880,},
+	{"RTL-8168d/8111d",	0x28, 0xff7e1880,},
+	{"RTL-8168evl/8111evl",	0x2e, 0xff7e1880,},
 	{"RTL-8101e",		0x34, 0xff7e1880,},
 	{"RTL-8100e",		0x32, 0xff7e1880,},
 };
@@ -314,6 +316,7 @@ static const unsigned int rtl8169_rx_config =
 
 static struct pci_device_id supported[] = {
 	{PCI_VENDOR_ID_REALTEK, 0x8167},
+	{PCI_VENDOR_ID_REALTEK, 0x8168},
 	{PCI_VENDOR_ID_REALTEK, 0x8169},
 	{}
 };
@@ -394,6 +397,50 @@ match:
 	return 0;
 }
 
+/*
+ * Cache maintenance functions. These are simple wrappers around the more
+ * general purpose flush_cache() and invalidate_dcache_range() functions.
+ */
+
+static void rtl_inval_rx_desc(struct RxDesc *desc)
+{
+	unsigned long start = (unsigned long)desc & ~(ARCH_DMA_MINALIGN - 1);
+	unsigned long end = ALIGN(start + sizeof(*desc), ARCH_DMA_MINALIGN);
+
+	invalidate_dcache_range(start, end);
+}
+
+static void rtl_flush_rx_desc(struct RxDesc *desc)
+{
+	flush_cache((unsigned long)desc, sizeof(*desc));
+}
+
+static void rtl_inval_tx_desc(struct TxDesc *desc)
+{
+	unsigned long start = (unsigned long)desc & ~(ARCH_DMA_MINALIGN - 1);
+	unsigned long end = ALIGN(start + sizeof(*desc), ARCH_DMA_MINALIGN);
+
+	invalidate_dcache_range(start, end);
+}
+
+static void rtl_flush_tx_desc(struct TxDesc *desc)
+{
+	flush_cache((unsigned long)desc, sizeof(*desc));
+}
+
+static void rtl_inval_buffer(void *buf, size_t size)
+{
+	unsigned long start = (unsigned long)buf & ~(ARCH_DMA_MINALIGN - 1);
+	unsigned long end = ALIGN(start + size, ARCH_DMA_MINALIGN);
+
+	invalidate_dcache_range(start, end);
+}
+
+static void rtl_flush_buffer(void *buf, size_t size)
+{
+	flush_cache((unsigned long)buf, size);
+}
+
 /**************************************************************************
 RECV - Receive a frame
 ***************************************************************************/
@@ -411,14 +458,16 @@ static int rtl_recv(struct eth_device *dev)
 	ioaddr = dev->iobase;
 
 	cur_rx = tpc->cur_rx;
-	flush_cache((unsigned long)&tpc->RxDescArray[cur_rx],
-			sizeof(struct RxDesc));
+
+	rtl_inval_rx_desc(&tpc->RxDescArray[cur_rx]);
+
 	if ((le32_to_cpu(tpc->RxDescArray[cur_rx].status) & OWNbit) == 0) {
 		if (!(le32_to_cpu(tpc->RxDescArray[cur_rx].status) & RxRES)) {
 			unsigned char rxdata[RX_BUF_LEN];
 			length = (int) (le32_to_cpu(tpc->RxDescArray[cur_rx].
 						status) & 0x00001FFF) - 4;
 
+			rtl_inval_buffer(tpc->RxBufferRing[cur_rx], length);
 			memcpy(rxdata, tpc->RxBufferRing[cur_rx], length);
 			NetReceive(rxdata, length);
 
@@ -430,8 +479,7 @@ static int rtl_recv(struct eth_device *dev)
 					cpu_to_le32(OWNbit + RX_BUF_SIZE);
 			tpc->RxDescArray[cur_rx].buf_addr =
 				cpu_to_le32(bus_to_phys(tpc->RxBufferRing[cur_rx]));
-			flush_cache((unsigned long)tpc->RxBufferRing[cur_rx],
-					RX_BUF_SIZE);
+			rtl_flush_rx_desc(&tpc->RxDescArray[cur_rx]);
 		} else {
 			puts("Error Rx");
 		}
@@ -473,7 +521,7 @@ static int rtl_send(struct eth_device *dev, void *packet, int length)
 	/* point to the current txb incase multiple tx_rings are used */
 	ptxb = tpc->Tx_skbuff[entry * MAX_ETH_FRAME_SIZE];
 	memcpy(ptxb, (char *)packet, (int)length);
-	flush_cache((unsigned long)ptxb, length);
+	rtl_flush_buffer(ptxb, length);
 
 	while (len < ETH_ZLEN)
 		ptxb[len++] = '\0';
@@ -489,20 +537,20 @@ static int rtl_send(struct eth_device *dev, void *packet, int length)
 			cpu_to_le32((OWNbit | EORbit | FSbit | LSbit) |
 				    ((len > ETH_ZLEN) ? len : ETH_ZLEN));
 	}
+	rtl_flush_tx_desc(&tpc->TxDescArray[entry]);
 	RTL_W8(TxPoll, 0x40);	/* set polling bit */
 
 	tpc->cur_tx++;
 	to = currticks() + TX_TIMEOUT;
 	do {
-		flush_cache((unsigned long)&tpc->TxDescArray[entry],
-				sizeof(struct TxDesc));
+		rtl_inval_tx_desc(&tpc->TxDescArray[entry]);
 	} while ((le32_to_cpu(tpc->TxDescArray[entry].status) & OWNbit)
 				&& (currticks() < to));	/* wait */
 
 	if (currticks() >= to) {
 #ifdef DEBUG_RTL8169_TX
-		puts ("tx timeout/error\n");
-		printf ("%s elapsed time : %d\n", __FUNCTION__, currticks()-stime);
+		puts("tx timeout/error\n");
+		printf("%s elapsed time : %lu\n", __func__, currticks()-stime);
 #endif
 		ret = 0;
 	} else {
@@ -604,7 +652,7 @@ static void rtl8169_hw_start(struct eth_device *dev)
 	RTL_W16(MultiIntr, RTL_R16(MultiIntr) & 0xF000);
 
 #ifdef DEBUG_RTL8169
-	printf ("%s elapsed time : %d\n", __FUNCTION__, currticks()-stime);
+	printf("%s elapsed time : %lu\n", __func__, currticks()-stime);
 #endif
 }
 
@@ -638,11 +686,11 @@ static void rtl8169_init_ring(struct eth_device *dev)
 		tpc->RxBufferRing[i] = &rxb[i * RX_BUF_SIZE];
 		tpc->RxDescArray[i].buf_addr =
 			cpu_to_le32(bus_to_phys(tpc->RxBufferRing[i]));
-		flush_cache((unsigned long)tpc->RxBufferRing[i], RX_BUF_SIZE);
+		rtl_flush_rx_desc(&tpc->RxDescArray[i]);
 	}
 
 #ifdef DEBUG_RTL8169
-	printf ("%s elapsed time : %d\n", __FUNCTION__, currticks()-stime);
+	printf("%s elapsed time : %lu\n", __func__, currticks()-stime);
 #endif
 }
 
@@ -683,7 +731,7 @@ static int rtl_reset(struct eth_device *dev, bd_t *bis)
 	txb[5] = dev->enetaddr[5];
 
 #ifdef DEBUG_RTL8169
-	printf ("%s elapsed time : %d\n", __FUNCTION__, currticks()-stime);
+	printf("%s elapsed time : %lu\n", __func__, currticks()-stime);
 #endif
 	return 0;
 }
@@ -869,11 +917,25 @@ int rtl8169_initialize(bd_t *bis)
 	int idx=0;
 
 	while(1){
+		unsigned int region;
+		u16 device;
+
 		/* Find RTL8169 */
 		if ((devno = pci_find_devices(supported, idx++)) < 0)
 			break;
 
-		pci_read_config_dword(devno, PCI_BASE_ADDRESS_1, &iobase);
+		pci_read_config_word(devno, PCI_DEVICE_ID, &device);
+		switch (device) {
+		case 0x8168:
+			region = 2;
+			break;
+
+		default:
+			region = 1;
+			break;
+		}
+
+		pci_read_config_dword(devno, PCI_BASE_ADDRESS_0 + (region * 4), &iobase);
 		iobase &= ~0xf;
 
 		debug ("rtl8169: REALTEK RTL8169 @0x%x\n", iobase);
diff --git a/drivers/net/sh_eth.c b/drivers/net/sh_eth.c
index d5a83e0bf5..5e132f2b53 100644
--- a/drivers/net/sh_eth.c
+++ b/drivers/net/sh_eth.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2008, 2011 Renesas Solutions Corp.
  * Copyright (c) 2008, 2011 Nobuhiro Iwamatsu
  * Copyright (c) 2007 Carlos Munoz <carlos@kenati.com>
+ * Copyright (C) 2013  Renesas Electronics Corporation
  *
  * SPDX-License-Identifier:	GPL-2.0+
  */
@@ -25,13 +26,31 @@
 #ifndef CONFIG_SH_ETHER_PHY_ADDR
 # error "Please define CONFIG_SH_ETHER_PHY_ADDR"
 #endif
-#ifdef CONFIG_SH_ETHER_CACHE_WRITEBACK
-#define flush_cache_wback(addr, len)	\
-			dcache_wback_range((u32)addr, (u32)(addr + len - 1))
+
+#if defined(CONFIG_SH_ETHER_CACHE_WRITEBACK) && !defined(CONFIG_SYS_DCACHE_OFF)
+#define flush_cache_wback(addr, len)    \
+		flush_dcache_range((u32)addr, (u32)(addr + len - 1))
 #else
 #define flush_cache_wback(...)
 #endif
 
+#if defined(CONFIG_SH_ETHER_CACHE_INVALIDATE) && defined(CONFIG_ARM)
+#define invalidate_cache(addr, len)		\
+	{	\
+		u32 line_size = CONFIG_SH_ETHER_ALIGNE_SIZE;	\
+		u32 start, end;	\
+		\
+		start = (u32)addr;	\
+		end = start + len;	\
+		start &= ~(line_size - 1);	\
+		end = ((end + line_size - 1) & ~(line_size - 1));	\
+		\
+		invalidate_dcache_range(start, end);	\
+	}
+#else
+#define invalidate_cache(...)
+#endif
+
 #define TIMEOUT_CNT 1000
 
 int sh_eth_send(struct eth_device *dev, void *packet, int len)
@@ -69,8 +88,11 @@ int sh_eth_send(struct eth_device *dev, void *packet, int len)
 
 	/* Wait until packet is transmitted */
 	timeout = TIMEOUT_CNT;
-	while (port_info->tx_desc_cur->td0 & TD_TACT && timeout--)
+	do {
+		invalidate_cache(port_info->tx_desc_cur,
+				 sizeof(struct tx_desc_s));
 		udelay(100);
+	} while (port_info->tx_desc_cur->td0 & TD_TACT && timeout--);
 
 	if (timeout < 0) {
 		printf(SHETHER_NAME ": transmit timeout\n");
@@ -94,12 +116,14 @@ int sh_eth_recv(struct eth_device *dev)
 	uchar *packet;
 
 	/* Check if the rx descriptor is ready */
+	invalidate_cache(port_info->rx_desc_cur, sizeof(struct rx_desc_s));
 	if (!(port_info->rx_desc_cur->rd0 & RD_RACT)) {
 		/* Check for errors */
 		if (!(port_info->rx_desc_cur->rd0 & RD_RFE)) {
 			len = port_info->rx_desc_cur->rd1 & 0xffff;
 			packet = (uchar *)
 				ADDR_TO_P2(port_info->rx_desc_cur->rd2);
+			invalidate_cache(packet, len);
 			NetReceive(packet, len);
 		}
 
@@ -108,7 +132,6 @@ int sh_eth_recv(struct eth_device *dev)
 			port_info->rx_desc_cur->rd0 = RD_RACT | RD_RDLE;
 		else
 			port_info->rx_desc_cur->rd0 = RD_RACT;
-
 		/* Point to the next descriptor */
 		port_info->rx_desc_cur++;
 		if (port_info->rx_desc_cur >=
@@ -237,15 +260,17 @@ static int sh_eth_rx_desc_init(struct sh_eth_dev *eth)
 	 * Allocate rx data buffers. They must be 32 bytes aligned  and in
 	 * P2 area
 	 */
-	port_info->rx_buf_malloc = malloc(NUM_RX_DESC * MAX_BUF_SIZE + 31);
+	port_info->rx_buf_malloc = malloc(
+		NUM_RX_DESC * MAX_BUF_SIZE + RX_BUF_ALIGNE_SIZE - 1);
 	if (!port_info->rx_buf_malloc) {
 		printf(SHETHER_NAME ": malloc failed\n");
 		ret = -ENOMEM;
 		goto err_buf_malloc;
 	}
 
-	tmp_addr = (u32)(((int)port_info->rx_buf_malloc + (32 - 1)) &
-			  ~(32 - 1));
+	tmp_addr = (u32)(((int)port_info->rx_buf_malloc
+			  + (RX_BUF_ALIGNE_SIZE - 1)) &
+			  ~(RX_BUF_ALIGNE_SIZE - 1));
 	port_info->rx_buf_base = (u8 *)ADDR_TO_P2(tmp_addr);
 
 	/* Initialize all descriptors */
@@ -351,8 +376,9 @@ static int sh_eth_config(struct sh_eth_dev *eth, bd_t *bd)
 	struct phy_device *phy;
 
 	/* Configure e-dmac registers */
-	sh_eth_write(eth, (sh_eth_read(eth, EDMR) & ~EMDR_DESC_R) | EDMR_EL,
-		     EDMR);
+	sh_eth_write(eth, (sh_eth_read(eth, EDMR) & ~EMDR_DESC_R) |
+			(EMDR_DESC | EDMR_EL), EDMR);
+
 	sh_eth_write(eth, 0, EESIPR);
 	sh_eth_write(eth, 0, TRSCER);
 	sh_eth_write(eth, 0, TFTR);
@@ -384,6 +410,8 @@ static int sh_eth_config(struct sh_eth_dev *eth, bd_t *bd)
 
 #if defined(CONFIG_CPU_SH7734) || defined(CONFIG_R8A7740)
 	sh_eth_write(eth, CONFIG_SH_ETHER_SH7734_MII, RMII_MII);
+#elif defined(CONFIG_R8A7790) || defined(CONFIG_R8A7791)
+	sh_eth_write(eth, sh_eth_read(eth, RMIIMR) | 0x1, RMIIMR);
 #endif
 	/* Configure phy */
 	ret = sh_eth_phy_config(eth);
@@ -407,7 +435,8 @@ static int sh_eth_config(struct sh_eth_dev *eth, bd_t *bd)
 		sh_eth_write(eth, GECMR_100B, GECMR);
 #elif defined(CONFIG_CPU_SH7757) || defined(CONFIG_CPU_SH7752)
 		sh_eth_write(eth, 1, RTRATE);
-#elif defined(CONFIG_CPU_SH7724)
+#elif defined(CONFIG_CPU_SH7724) || defined(CONFIG_R8A7790) || \
+		defined(CONFIG_R8A7791)
 		val = ECMR_RTM;
 #endif
 	} else if (phy->speed == 10) {
diff --git a/drivers/net/sh_eth.h b/drivers/net/sh_eth.h
index 9ad800e427..8aa71098cb 100644
--- a/drivers/net/sh_eth.h
+++ b/drivers/net/sh_eth.h
@@ -31,6 +31,11 @@
 #define ADDR_TO_P2(addr)	(addr)
 #endif /* defined(CONFIG_SH) */
 
+/* base padding size is 16 */
+#ifndef CONFIG_SH_ETHER_ALIGNE_SIZE
+#define CONFIG_SH_ETHER_ALIGNE_SIZE 16
+#endif
+
 /* Number of supported ports */
 #define MAX_PORT_NUM	2
 
@@ -45,15 +50,16 @@
 
 /* The size of the tx descriptor is determined by how much padding is used.
    4, 20, or 52 bytes of padding can be used */
-#define TX_DESC_PADDING		4
-#define TX_DESC_SIZE		(12 + TX_DESC_PADDING)
+#define TX_DESC_PADDING	(CONFIG_SH_ETHER_ALIGNE_SIZE - 12)
+/* same as CONFIG_SH_ETHER_ALIGNE_SIZE */
+#define TX_DESC_SIZE	(12 + TX_DESC_PADDING)
 
 /* Tx descriptor. We always use 3 bytes of padding */
 struct tx_desc_s {
 	volatile u32 td0;
 	u32 td1;
 	u32 td2;		/* Buffer start */
-	u32 padding;
+	u8 padding[TX_DESC_PADDING];	/* aligned cache line size */
 };
 
 /* There is no limitation in the number of rx descriptors */
@@ -61,15 +67,18 @@ struct tx_desc_s {
 
 /* The size of the rx descriptor is determined by how much padding is used.
    4, 20, or 52 bytes of padding can be used */
-#define RX_DESC_PADDING		4
+#define RX_DESC_PADDING	(CONFIG_SH_ETHER_ALIGNE_SIZE - 12)
+/* same as CONFIG_SH_ETHER_ALIGNE_SIZE */
 #define RX_DESC_SIZE		(12 + RX_DESC_PADDING)
+/* aligned cache line size */
+#define RX_BUF_ALIGNE_SIZE	(CONFIG_SH_ETHER_ALIGNE_SIZE > 32 ? 64 : 32)
 
 /* Rx descriptor. We always use 4 bytes of padding */
 struct rx_desc_s {
 	volatile u32 rd0;
 	volatile u32 rd1;
 	u32 rd2;		/* Buffer start */
-	u32 padding;
+	u8 padding[TX_DESC_PADDING];	/* aligned cache line size */
 };
 
 struct sh_eth_info {
@@ -157,6 +166,7 @@ enum {
 	TLFRCR,
 	CERCR,
 	CEECR,
+	RMIIMR, /* R8A7790 */
 	MAFCR,
 	RTRATE,
 	CSMR,
@@ -263,6 +273,7 @@ static const u16 sh_eth_offset_fast_sh4[SH_ETH_MAX_REGISTER_OFFSET] = {
 	[RMCR]	= 0x0058,
 	[TFUCR]	= 0x0064,
 	[RFOCR]	= 0x0068,
+	[RMIIMR] = 0x006C,
 	[FCFTR]	= 0x0070,
 	[RPADIR]	= 0x0078,
 	[TRIMD]	= 0x007c,
@@ -290,6 +301,9 @@ static const u16 sh_eth_offset_fast_sh4[SH_ETH_MAX_REGISTER_OFFSET] = {
 #elif defined(CONFIG_R8A7740)
 #define SH_ETH_TYPE_GETHER
 #define BASE_IO_ADDR	0xE9A00000
+#elif defined(CONFIG_R8A7790) || defined(CONFIG_R8A7791)
+#define SH_ETH_TYPE_ETHER
+#define BASE_IO_ADDR	0xEE700200
 #endif
 
 /*
@@ -320,6 +334,14 @@ enum DMAC_M_BIT {
 #endif
 };
 
+#if CONFIG_SH_ETHER_ALIGNE_SIZE == 64
+# define EMDR_DESC EDMR_DL1
+#elif CONFIG_SH_ETHER_ALIGNE_SIZE == 32
+# define EMDR_DESC EDMR_DL0
+#elif CONFIG_SH_ETHER_ALIGNE_SIZE == 16 /* Default */
+# define EMDR_DESC 0
+#endif
+
 /* RFLR */
 #define RFLR_RFL_MIN	0x05EE	/* Recv Frame length 1518 byte */
 
@@ -485,6 +507,8 @@ enum FELIC_MODE_BIT {
 	ECMR_PRM = 0x00000001,
 #ifdef CONFIG_CPU_SH7724
 	ECMR_RTM = 0x00000010,
+#elif defined(CONFIG_R8A7790) || defined(CONFIG_R8A7791)
+	ECMR_RTM = 0x00000004,
 #endif
 
 };
diff --git a/drivers/net/tsec.c b/drivers/net/tsec.c
index f5e314b9ee..e9138f0338 100644
--- a/drivers/net/tsec.c
+++ b/drivers/net/tsec.c
@@ -5,7 +5,7 @@
  * terms of the GNU Public License, Version 2, incorporated
  * herein by reference.
  *
- * Copyright 2004-2011 Freescale Semiconductor, Inc.
+ * Copyright 2004-2011, 2013 Freescale Semiconductor, Inc.
  * (C) Copyright 2003, Motorola, Inc.
  * author Andy Fleming
  *
@@ -25,21 +25,13 @@ DECLARE_GLOBAL_DATA_PTR;
 
 #define TX_BUF_CNT		2
 
-static uint rxIdx;		/* index of the current RX buffer */
-static uint txIdx;		/* index of the current TX buffer */
-
-typedef volatile struct rtxbd {
-	txbd8_t txbd[TX_BUF_CNT];
-	rxbd8_t rxbd[PKTBUFSRX];
-} RTXBD;
-
-#define MAXCONTROLLERS	(8)
-
-static struct tsec_private *privlist[MAXCONTROLLERS];
-static int num_tsecs = 0;
+static uint rx_idx;		/* index of the current RX buffer */
+static uint tx_idx;		/* index of the current TX buffer */
 
 #ifdef __GNUC__
-static RTXBD rtx __attribute__ ((aligned(8)));
+static struct txbd8 __iomem txbd[TX_BUF_CNT] __aligned(8);
+static struct rxbd8 __iomem rxbd[PKTBUFSRX] __aligned(8);
+
 #else
 #error "rtx must be 64-bit aligned"
 #endif
@@ -57,7 +49,7 @@ static struct tsec_info_struct tsec_info[] = {
 #endif
 #ifdef CONFIG_MPC85XX_FEC
 	{
-		.regs = (tsec_t *)(TSEC_BASE_ADDR + 0x2000),
+		.regs = TSEC_GET_REGS(2, 0x2000),
 		.devname = CONFIG_MPC85XX_FEC_NAME,
 		.phyaddr = FEC_PHY_ADDR,
 		.flags = FEC_FLAGS,
@@ -113,32 +105,31 @@ static void tsec_configure_serdes(struct tsec_private *priv)
  * result.
  * 2) Use the 8 most significant bits as a hash into a 256-entry
  * table.  The table is controlled through 8 32-bit registers:
- * gaddr0-7.  gaddr0's MSB is entry 0, and gaddr7's LSB is
- * gaddr7.  This means that the 3 most significant bits in the
+ * gaddr0-7.  gaddr0's MSB is entry 0, and gaddr7's LSB is entry
+ * 255.  This means that the 3 most significant bits in the
  * hash index which gaddr register to use, and the 5 other bits
  * indicate which bit (assuming an IBM numbering scheme, which
- * for PowerPC (tm) is usually the case) in the tregister holds
+ * for PowerPC (tm) is usually the case) in the register holds
  * the entry. */
 static int
-tsec_mcast_addr (struct eth_device *dev, u8 mcast_mac, u8 set)
+tsec_mcast_addr(struct eth_device *dev, const u8 *mcast_mac, u8 set)
 {
-	struct tsec_private *priv = privlist[1];
-	volatile tsec_t *regs = priv->regs;
-	volatile u32  *reg_array, value;
-	u8 result, whichbit, whichreg;
-
-	result = (u8)((ether_crc(MAC_ADDR_LEN,mcast_mac) >> 24) & 0xff);
-	whichbit = result & 0x1f;	/* the 5 LSB = which bit to set */
-	whichreg = result >> 5;		/* the 3 MSB = which reg to set it in */
-	value = (1 << (31-whichbit));
-
-	reg_array = &(regs->hash.gaddr0);
-
-	if (set) {
-		reg_array[whichreg] |= value;
-	} else {
-		reg_array[whichreg] &= ~value;
-	}
+	struct tsec_private *priv = (struct tsec_private *)dev->priv;
+	struct tsec __iomem *regs = priv->regs;
+	u32 result, value;
+	u8 whichbit, whichreg;
+
+	result = ether_crc(MAC_ADDR_LEN, mcast_mac);
+	whichbit = (result >> 24) & 0x1f; /* the 5 LSB = which bit to set */
+	whichreg = result >> 29; /* the 3 MSB = which reg to set it in */
+
+	value = 1 << (31-whichbit);
+
+	if (set)
+		setbits_be32(&regs->hash.gaddr0 + whichreg, value);
+	else
+		clrbits_be32(&regs->hash.gaddr0 + whichreg, value);
+
 	return 0;
 }
 #endif /* Multicast TFTP ? */
@@ -147,7 +138,7 @@ tsec_mcast_addr (struct eth_device *dev, u8 mcast_mac, u8 set)
  * those we don't care about (unless zero is bad, in which case,
  * choose a more appropriate value)
  */
-static void init_registers(tsec_t *regs)
+static void init_registers(struct tsec __iomem *regs)
 {
 	/* Clear IEVENT */
 	out_be32(&regs->ievent, IEVENT_INIT_CLEAR);
@@ -175,7 +166,7 @@ static void init_registers(tsec_t *regs)
 	out_be32(&regs->rctrl, 0x00000000);
 
 	/* Init RMON mib registers */
-	memset((void *)&(regs->rmon), 0, sizeof(rmon_mib_t));
+	memset((void *)&regs->rmon, 0, sizeof(regs->rmon));
 
 	out_be32(&regs->rmon.cam1, 0xffffffff);
 	out_be32(&regs->rmon.cam2, 0xffffffff);
@@ -194,7 +185,7 @@ static void init_registers(tsec_t *regs)
  */
 static void adjust_link(struct tsec_private *priv, struct phy_device *phydev)
 {
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
 	u32 ecntrl, maccfg2;
 
 	if (!phydev->link) {
@@ -248,7 +239,7 @@ static void adjust_link(struct tsec_private *priv, struct phy_device *phydev)
 void redundant_init(struct eth_device *dev)
 {
 	struct tsec_private *priv = dev->priv;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
 	uint t, count = 0;
 	int fail = 1;
 	static const u8 pkt[] = {
@@ -281,23 +272,26 @@ void redundant_init(struct eth_device *dev)
 	clrbits_be32(&regs->dmactrl, DMACTRL_GRS | DMACTRL_GTS);
 
 	do {
+		uint16_t status;
 		tsec_send(dev, (void *)pkt, sizeof(pkt));
 
 		/* Wait for buffer to be received */
-		for (t = 0; rtx.rxbd[rxIdx].status & RXBD_EMPTY; t++) {
+		for (t = 0; in_be16(&rxbd[rx_idx].status) & RXBD_EMPTY; t++) {
 			if (t >= 10 * TOUT_LOOP) {
 				printf("%s: tsec: rx error\n", dev->name);
 				break;
 			}
 		}
 
-		if (!memcmp(pkt, (void *)NetRxPackets[rxIdx], sizeof(pkt)))
+		if (!memcmp(pkt, (void *)NetRxPackets[rx_idx], sizeof(pkt)))
 			fail = 0;
 
-		rtx.rxbd[rxIdx].length = 0;
-		rtx.rxbd[rxIdx].status =
-		    RXBD_EMPTY | (((rxIdx + 1) == PKTBUFSRX) ? RXBD_WRAP : 0);
-		rxIdx = (rxIdx + 1) % PKTBUFSRX;
+		out_be16(&rxbd[rx_idx].length, 0);
+		status = RXBD_EMPTY;
+		if ((rx_idx + 1) == PKTBUFSRX)
+			status |= RXBD_WRAP;
+		out_be16(&rxbd[rx_idx].status, status);
+		rx_idx = (rx_idx + 1) % PKTBUFSRX;
 
 		if (in_be32(&regs->ievent) & IEVENT_BSY) {
 			out_be32(&regs->ievent, IEVENT_BSY);
@@ -325,36 +319,39 @@ void redundant_init(struct eth_device *dev)
  */
 static void startup_tsec(struct eth_device *dev)
 {
-	int i;
 	struct tsec_private *priv = (struct tsec_private *)dev->priv;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
+	uint16_t status;
+	int i;
 
 	/* reset the indices to zero */
-	rxIdx = 0;
-	txIdx = 0;
+	rx_idx = 0;
+	tx_idx = 0;
 #ifdef CONFIG_SYS_FSL_ERRATUM_NMG_ETSEC129
 	uint svr;
 #endif
 
 	/* Point to the buffer descriptors */
-	out_be32(&regs->tbase, (unsigned int)(&rtx.txbd[txIdx]));
-	out_be32(&regs->rbase, (unsigned int)(&rtx.rxbd[rxIdx]));
+	out_be32(&regs->tbase, (u32)&txbd[0]);
+	out_be32(&regs->rbase, (u32)&rxbd[0]);
 
 	/* Initialize the Rx Buffer descriptors */
 	for (i = 0; i < PKTBUFSRX; i++) {
-		rtx.rxbd[i].status = RXBD_EMPTY;
-		rtx.rxbd[i].length = 0;
-		rtx.rxbd[i].bufPtr = (uint) NetRxPackets[i];
+		out_be16(&rxbd[i].status, RXBD_EMPTY);
+		out_be16(&rxbd[i].length, 0);
+		out_be32(&rxbd[i].bufptr, (u32)NetRxPackets[i]);
 	}
-	rtx.rxbd[PKTBUFSRX - 1].status |= RXBD_WRAP;
+	status = in_be16(&rxbd[PKTBUFSRX - 1].status);
+	out_be16(&rxbd[PKTBUFSRX - 1].status, status | RXBD_WRAP);
 
 	/* Initialize the TX Buffer Descriptors */
 	for (i = 0; i < TX_BUF_CNT; i++) {
-		rtx.txbd[i].status = 0;
-		rtx.txbd[i].length = 0;
-		rtx.txbd[i].bufPtr = 0;
+		out_be16(&txbd[i].status, 0);
+		out_be16(&txbd[i].length, 0);
+		out_be32(&txbd[i].bufptr, 0);
 	}
-	rtx.txbd[TX_BUF_CNT - 1].status |= TXBD_WRAP;
+	status = in_be16(&txbd[TX_BUF_CNT - 1].status);
+	out_be16(&txbd[TX_BUF_CNT - 1].status, status | TXBD_WRAP);
 
 #ifdef CONFIG_SYS_FSL_ERRATUM_NMG_ETSEC129
 	svr = get_svr();
@@ -378,66 +375,67 @@ static void startup_tsec(struct eth_device *dev)
  */
 static int tsec_send(struct eth_device *dev, void *packet, int length)
 {
-	int i;
-	int result = 0;
 	struct tsec_private *priv = (struct tsec_private *)dev->priv;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
+	uint16_t status;
+	int result = 0;
+	int i;
 
 	/* Find an empty buffer descriptor */
-	for (i = 0; rtx.txbd[txIdx].status & TXBD_READY; i++) {
+	for (i = 0; in_be16(&txbd[tx_idx].status) & TXBD_READY; i++) {
 		if (i >= TOUT_LOOP) {
 			debug("%s: tsec: tx buffers full\n", dev->name);
 			return result;
 		}
 	}
 
-	rtx.txbd[txIdx].bufPtr = (uint) packet;
-	rtx.txbd[txIdx].length = length;
-	rtx.txbd[txIdx].status |=
-	    (TXBD_READY | TXBD_LAST | TXBD_CRC | TXBD_INTERRUPT);
+	out_be32(&txbd[tx_idx].bufptr, (u32)packet);
+	out_be16(&txbd[tx_idx].length, length);
+	status = in_be16(&txbd[tx_idx].status);
+	out_be16(&txbd[tx_idx].status, status |
+		(TXBD_READY | TXBD_LAST | TXBD_CRC | TXBD_INTERRUPT));
 
 	/* Tell the DMA to go */
 	out_be32(&regs->tstat, TSTAT_CLEAR_THALT);
 
 	/* Wait for buffer to be transmitted */
-	for (i = 0; rtx.txbd[txIdx].status & TXBD_READY; i++) {
+	for (i = 0; in_be16(&txbd[tx_idx].status) & TXBD_READY; i++) {
 		if (i >= TOUT_LOOP) {
 			debug("%s: tsec: tx error\n", dev->name);
 			return result;
 		}
 	}
 
-	txIdx = (txIdx + 1) % TX_BUF_CNT;
-	result = rtx.txbd[txIdx].status & TXBD_STATS;
+	tx_idx = (tx_idx + 1) % TX_BUF_CNT;
+	result = in_be16(&txbd[tx_idx].status) & TXBD_STATS;
 
 	return result;
 }
 
 static int tsec_recv(struct eth_device *dev)
 {
-	int length;
 	struct tsec_private *priv = (struct tsec_private *)dev->priv;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
 
-	while (!(rtx.rxbd[rxIdx].status & RXBD_EMPTY)) {
-
-		length = rtx.rxbd[rxIdx].length;
+	while (!(in_be16(&rxbd[rx_idx].status) & RXBD_EMPTY)) {
+		int length = in_be16(&rxbd[rx_idx].length);
+		uint16_t status = in_be16(&rxbd[rx_idx].status);
 
 		/* Send the packet up if there were no errors */
-		if (!(rtx.rxbd[rxIdx].status & RXBD_STATS)) {
-			NetReceive(NetRxPackets[rxIdx], length - 4);
-		} else {
-			printf("Got error %x\n",
-			       (rtx.rxbd[rxIdx].status & RXBD_STATS));
-		}
+		if (!(status & RXBD_STATS))
+			NetReceive(NetRxPackets[rx_idx], length - 4);
+		else
+			printf("Got error %x\n", (status & RXBD_STATS));
 
-		rtx.rxbd[rxIdx].length = 0;
+		out_be16(&rxbd[rx_idx].length, 0);
 
+		status = RXBD_EMPTY;
 		/* Set the wrap bit if this is the last element in the list */
-		rtx.rxbd[rxIdx].status =
-		    RXBD_EMPTY | (((rxIdx + 1) == PKTBUFSRX) ? RXBD_WRAP : 0);
+		if ((rx_idx + 1) == PKTBUFSRX)
+			status |= RXBD_WRAP;
+		out_be16(&rxbd[rx_idx].status, status);
 
-		rxIdx = (rxIdx + 1) % PKTBUFSRX;
+		rx_idx = (rx_idx + 1) % PKTBUFSRX;
 	}
 
 	if (in_be32(&regs->ievent) & IEVENT_BSY) {
@@ -453,7 +451,7 @@ static int tsec_recv(struct eth_device *dev)
 static void tsec_halt(struct eth_device *dev)
 {
 	struct tsec_private *priv = (struct tsec_private *)dev->priv;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
 
 	clrbits_be32(&regs->dmactrl, DMACTRL_GRS | DMACTRL_GTS);
 	setbits_be32(&regs->dmactrl, DMACTRL_GRS | DMACTRL_GTS);
@@ -475,11 +473,9 @@ static void tsec_halt(struct eth_device *dev)
  */
 static int tsec_init(struct eth_device *dev, bd_t * bd)
 {
-	uint tempval;
-	char tmpbuf[MAC_ADDR_LEN];
-	int i;
 	struct tsec_private *priv = (struct tsec_private *)dev->priv;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
+	u32 tempval;
 	int ret;
 
 	/* Make sure the controller is stopped */
@@ -492,16 +488,16 @@ static int tsec_init(struct eth_device *dev, bd_t * bd)
 	out_be32(&regs->ecntrl, ECNTRL_INIT_SETTINGS);
 
 	/* Copy the station address into the address registers.
-	 * Backwards, because little endian MACS are dumb */
-	for (i = 0; i < MAC_ADDR_LEN; i++)
-		tmpbuf[MAC_ADDR_LEN - 1 - i] = dev->enetaddr[i];
-
-	tempval = (tmpbuf[0] << 24) | (tmpbuf[1] << 16) | (tmpbuf[2] << 8) |
-		  tmpbuf[3];
+	 * For a station address of 0x12345678ABCD in transmission
+	 * order (BE), MACnADDR1 is set to 0xCDAB7856 and
+	 * MACnADDR2 is set to 0x34120000.
+	 */
+	tempval = (dev->enetaddr[5] << 24) | (dev->enetaddr[4] << 16) |
+		  (dev->enetaddr[3] << 8)  |  dev->enetaddr[2];
 
 	out_be32(&regs->macstnaddr1, tempval);
 
-	tempval = *((uint *) (tmpbuf + 4));
+	tempval = (dev->enetaddr[1] << 24) | (dev->enetaddr[0] << 16);
 
 	out_be32(&regs->macstnaddr2, tempval);
 
@@ -527,7 +523,7 @@ static int tsec_init(struct eth_device *dev, bd_t * bd)
 
 static phy_interface_t tsec_get_interface(struct tsec_private *priv)
 {
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
 	u32 ecntrl;
 
 	ecntrl = in_be32(&regs->ecntrl);
@@ -576,7 +572,7 @@ static int init_phy(struct eth_device *dev)
 {
 	struct tsec_private *priv = (struct tsec_private *)dev->priv;
 	struct phy_device *phydev;
-	tsec_t *regs = priv->regs;
+	struct tsec __iomem *regs = priv->regs;
 	u32 supported = (SUPPORTED_10baseT_Half |
 			SUPPORTED_10baseT_Full |
 			SUPPORTED_100baseT_Half |
@@ -626,7 +622,6 @@ static int tsec_initialize(bd_t *bis, struct tsec_info_struct *tsec_info)
 	if (NULL == priv)
 		return 0;
 
-	privlist[num_tsecs++] = priv;
 	priv->regs = tsec_info->regs;
 	priv->phyregs_sgmii = tsec_info->miiregs_sgmii;
 
@@ -684,7 +679,7 @@ int tsec_standard_init(bd_t *bis)
 {
 	struct fsl_pq_mdio_info info;
 
-	info.regs = (struct tsec_mii_mng *)CONFIG_SYS_MDIO_BASE_ADDR;
+	info.regs = TSEC_GET_MDIO_REGS_BASE(1);
 	info.name = DEFAULT_MII_NAME;
 
 	fsl_pq_mdio_init(bis, &info);
diff --git a/drivers/net/zynq_gem.c b/drivers/net/zynq_gem.c
index 236a75311f..6a017a8102 100644
--- a/drivers/net/zynq_gem.c
+++ b/drivers/net/zynq_gem.c
@@ -43,11 +43,6 @@
 #define ZYNQ_GEM_TXBUF_WRAP_MASK	0x40000000
 #define ZYNQ_GEM_TXBUF_LAST_MASK	0x00008000 /* Last buffer */
 
-#define ZYNQ_GEM_TXSR_HRESPNOK_MASK	0x00000100 /* Transmit hresp not OK */
-#define ZYNQ_GEM_TXSR_URUN_MASK		0x00000040 /* Transmit underrun */
-/* Transmit buffs exhausted mid frame */
-#define ZYNQ_GEM_TXSR_BUFEXH_MASK	0x00000010
-
 #define ZYNQ_GEM_NWCTRL_TXEN_MASK	0x00000008 /* Enable transmit */
 #define ZYNQ_GEM_NWCTRL_RXEN_MASK	0x00000004 /* Enable receive */
 #define ZYNQ_GEM_NWCTRL_MDEN_MASK	0x00000010 /* Enable MDIO port */
@@ -90,6 +85,11 @@
  */
 #define PHY_DETECT_MASK 0x1808
 
+/* TX BD status masks */
+#define ZYNQ_GEM_TXBUF_FRMLEN_MASK	0x000007ff
+#define ZYNQ_GEM_TXBUF_EXHAUSTED	0x08000000
+#define ZYNQ_GEM_TXBUF_UNDERRUN		0x10000000
+
 /* Device registers */
 struct zynq_gem_regs {
 	u32 nwctrl; /* Network Control reg */
@@ -123,12 +123,18 @@ struct emac_bd {
 };
 
 #define RX_BUF 3
+/* Page table entries are set to 1MB, or multiples of 1MB
+ * (not < 1MB). driver uses less bd's so use 1MB bdspace.
+ */
+#define BD_SPACE	0x100000
+/* BD separation space */
+#define BD_SEPRN_SPACE	64
 
 /* Initialized, rxbd_current, rx_first_buf must be 0 after init */
 struct zynq_gem_priv {
-	struct emac_bd tx_bd;
-	struct emac_bd rx_bd[RX_BUF];
-	char rxbuffers[RX_BUF * PKTSIZE_ALIGN];
+	struct emac_bd *tx_bd;
+	struct emac_bd *rx_bd;
+	char *rxbuffers;
 	u32 rxbd_current;
 	u32 rx_first_buf;
 	int phyaddr;
@@ -299,20 +305,18 @@ static int zynq_gem_init(struct eth_device *dev, bd_t * bis)
 			readl(&regs->stat[i]);
 
 		/* Setup RxBD space */
-		memset(&(priv->rx_bd), 0, sizeof(priv->rx_bd));
-		/* Create the RxBD ring */
-		memset(&(priv->rxbuffers), 0, sizeof(priv->rxbuffers));
+		memset(priv->rx_bd, 0, RX_BUF * sizeof(struct emac_bd));
 
 		for (i = 0; i < RX_BUF; i++) {
 			priv->rx_bd[i].status = 0xF0000000;
 			priv->rx_bd[i].addr =
-					(u32)((char *)&(priv->rxbuffers) +
+					((u32)(priv->rxbuffers) +
 							(i * PKTSIZE_ALIGN));
 		}
 		/* WRAP bit to last BD */
 		priv->rx_bd[--i].addr |= ZYNQ_GEM_RXBUF_WRAP_MASK;
 		/* Write RxBDs to IP */
-		writel((u32)&(priv->rx_bd), &regs->rxqbase);
+		writel((u32)priv->rx_bd, &regs->rxqbase);
 
 		/* Setup for DMA Configuration register */
 		writel(ZYNQ_GEM_DMACR_INIT, &regs->dmacr);
@@ -368,32 +372,35 @@ static int zynq_gem_init(struct eth_device *dev, bd_t * bis)
 
 static int zynq_gem_send(struct eth_device *dev, void *ptr, int len)
 {
-	u32 status;
+	u32 addr, size;
 	struct zynq_gem_priv *priv = dev->priv;
 	struct zynq_gem_regs *regs = (struct zynq_gem_regs *)dev->iobase;
-	const u32 mask = ZYNQ_GEM_TXSR_HRESPNOK_MASK | \
-			ZYNQ_GEM_TXSR_URUN_MASK | ZYNQ_GEM_TXSR_BUFEXH_MASK;
 
 	/* setup BD */
-	writel((u32)&(priv->tx_bd), &regs->txqbase);
+	writel((u32)priv->tx_bd, &regs->txqbase);
 
 	/* Setup Tx BD */
-	memset((void *)&(priv->tx_bd), 0, sizeof(struct emac_bd));
+	memset(priv->tx_bd, 0, sizeof(struct emac_bd));
+
+	priv->tx_bd->addr = (u32)ptr;
+	priv->tx_bd->status = (len & ZYNQ_GEM_TXBUF_FRMLEN_MASK) |
+				ZYNQ_GEM_TXBUF_LAST_MASK;
 
-	priv->tx_bd.addr = (u32)ptr;
-	priv->tx_bd.status = len | ZYNQ_GEM_TXBUF_LAST_MASK;
+	addr = (u32) ptr;
+	addr &= ~(ARCH_DMA_MINALIGN - 1);
+	size = roundup(len, ARCH_DMA_MINALIGN);
+	flush_dcache_range(addr, addr + size);
+	barrier();
 
 	/* Start transmit */
 	setbits_le32(&regs->nwctrl, ZYNQ_GEM_NWCTRL_STARTTX_MASK);
 
-	/* Read the stat register to know if the packet has been transmitted */
-	status = readl(&regs->txsr);
-	if (status & mask)
-		printf("Something has gone wrong here!? Status is 0x%x.\n",
-		       status);
+	/* Read TX BD status */
+	if (priv->tx_bd->status & ZYNQ_GEM_TXBUF_UNDERRUN)
+		printf("TX underrun\n");
+	if (priv->tx_bd->status & ZYNQ_GEM_TXBUF_EXHAUSTED)
+		printf("TX buffers exhausted in mid frame\n");
 
-	/* Clear Tx status register before leaving . */
-	writel(status, &regs->txsr);
 	return 0;
 }
 
@@ -416,8 +423,12 @@ static int zynq_gem_recv(struct eth_device *dev)
 
 	frame_len = current_bd->status & ZYNQ_GEM_RXBUF_LEN_MASK;
 	if (frame_len) {
-		NetReceive((u8 *) (current_bd->addr &
-					ZYNQ_GEM_RXBUF_ADD_MASK), frame_len);
+		u32 addr = current_bd->addr & ZYNQ_GEM_RXBUF_ADD_MASK;
+		addr &= ~(ARCH_DMA_MINALIGN - 1);
+		u32 size = roundup(frame_len, ARCH_DMA_MINALIGN);
+		invalidate_dcache_range(addr, addr + size);
+
+		NetReceive((u8 *)addr, frame_len);
 
 		if (current_bd->status & ZYNQ_GEM_RXBUF_SOF_MASK)
 			priv->rx_first_buf = priv->rxbd_current;
@@ -471,6 +482,7 @@ int zynq_gem_initialize(bd_t *bis, int base_addr, int phy_addr, u32 emio)
 {
 	struct eth_device *dev;
 	struct zynq_gem_priv *priv;
+	void *bd_space;
 
 	dev = calloc(1, sizeof(*dev));
 	if (dev == NULL)
@@ -483,6 +495,18 @@ int zynq_gem_initialize(bd_t *bis, int base_addr, int phy_addr, u32 emio)
 	}
 	priv = dev->priv;
 
+	/* Align rxbuffers to ARCH_DMA_MINALIGN */
+	priv->rxbuffers = memalign(ARCH_DMA_MINALIGN, RX_BUF * PKTSIZE_ALIGN);
+	memset(priv->rxbuffers, 0, RX_BUF * PKTSIZE_ALIGN);
+
+	/* Align bd_space to 1MB */
+	bd_space = memalign(1 << MMU_SECTION_SHIFT, BD_SPACE);
+	mmu_set_region_dcache_behaviour((u32)bd_space, BD_SPACE, DCACHE_OFF);
+
+	/* Initialize the bd spaces for tx and rx bd's */
+	priv->tx_bd = (struct emac_bd *)bd_space;
+	priv->rx_bd = (struct emac_bd *)((u32)bd_space + BD_SEPRN_SPACE);
+
 	priv->phyaddr = phy_addr;
 	priv->emio = emio;