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

16 files changed, 1035 insertions, 40 deletions

diff --git a/drivers/Makefile b/drivers/Makefile
index 5d03f37a18..b23076f614 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -14,3 +14,4 @@ obj-y += twserial/
 obj-y += video/
 obj-y += watchdog/
 obj-$(CONFIG_QE) += qe/
+obj-y += memory/
diff --git a/drivers/block/dwc_ahsata.c b/drivers/block/dwc_ahsata.c
index 3569214297..15d65d77f3 100644
--- a/drivers/block/dwc_ahsata.c
+++ b/drivers/block/dwc_ahsata.c
@@ -17,6 +17,7 @@
 #include <asm/io.h>
 #include <linux/bitops.h>
 #include <asm/arch/clock.h>
+#include <asm/arch/sys_proto.h>
 #include "dwc_ahsata.h"
 
 struct sata_port_regs {
@@ -558,6 +559,10 @@ int init_sata(int dev)
 	u32 linkmap;
 	struct ahci_probe_ent *probe_ent = NULL;
 
+#if defined(CONFIG_MX6)
+	if (!is_cpu_type(MXC_CPU_MX6Q) && !is_cpu_type(MXC_CPU_MX6D))
+		return 1;
+#endif
 	if (dev < 0 || dev > (CONFIG_SYS_SATA_MAX_DEVICE - 1)) {
 		printf("The sata index %d is out of ranges\n\r", dev);
 		return -1;
diff --git a/drivers/memory/Makefile b/drivers/memory/Makefile
new file mode 100644
index 0000000000..9bfb9c785d
--- /dev/null
+++ b/drivers/memory/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_TI_AEMIF) += ti-aemif.o
diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c
new file mode 100644
index 0000000000..f821daea4e
--- /dev/null
+++ b/drivers/memory/ti-aemif.c
@@ -0,0 +1,80 @@
+/*
+ * Keystone2: Asynchronous EMIF Configuration
+ *
+ * (C) Copyright 2012-2014
+ *     Texas Instruments Incorporated, <www.ti.com>
+ *
+ * SPDX-License-Identifier:     GPL-2.0+
+ */
+
+#include <common.h>
+#include <asm/ti-common/ti-aemif.h>
+
+#define AEMIF_WAITCYCLE_CONFIG		(CONFIG_AEMIF_CNTRL_BASE + 0x4)
+#define AEMIF_NAND_CONTROL		(CONFIG_AEMIF_CNTRL_BASE + 0x60)
+#define AEMIF_ONENAND_CONTROL		(CONFIG_AEMIF_CNTRL_BASE + 0x5c)
+#define AEMIF_CONFIG(cs)		(CONFIG_AEMIF_CNTRL_BASE + 0x10 \
+					 + (cs * 4))
+
+#define AEMIF_CFG_SELECT_STROBE(v)	((v) ? 1 << 31 : 0)
+#define AEMIF_CFG_EXTEND_WAIT(v)	((v) ? 1 << 30 : 0)
+#define AEMIF_CFG_WR_SETUP(v)		(((v) & 0x0f) << 26)
+#define AEMIF_CFG_WR_STROBE(v)		(((v) & 0x3f) << 20)
+#define AEMIF_CFG_WR_HOLD(v)		(((v) & 0x07) << 17)
+#define AEMIF_CFG_RD_SETUP(v)		(((v) & 0x0f) << 13)
+#define AEMIF_CFG_RD_STROBE(v)		(((v) & 0x3f) << 7)
+#define AEMIF_CFG_RD_HOLD(v)		(((v) & 0x07) << 4)
+#define AEMIF_CFG_TURN_AROUND(v)	(((v) & 0x03) << 2)
+#define AEMIF_CFG_WIDTH(v)		(((v) & 0x03) << 0)
+
+#define set_config_field(reg, field, val)			\
+	do {							\
+		if (val != -1) {				\
+			reg &= ~AEMIF_CFG_##field(0xffffffff);	\
+			reg |=	AEMIF_CFG_##field(val);		\
+		}						\
+	} while (0)
+
+static void aemif_configure(int cs, struct aemif_config *cfg)
+{
+	unsigned long tmp;
+
+	if (cfg->mode == AEMIF_MODE_NAND) {
+		tmp = __raw_readl(AEMIF_NAND_CONTROL);
+		tmp |= (1 << cs);
+		__raw_writel(tmp, AEMIF_NAND_CONTROL);
+
+	} else if (cfg->mode == AEMIF_MODE_ONENAND) {
+		tmp = __raw_readl(AEMIF_ONENAND_CONTROL);
+		tmp |= (1 << cs);
+		__raw_writel(tmp, AEMIF_ONENAND_CONTROL);
+	}
+
+	tmp = __raw_readl(AEMIF_CONFIG(cs));
+
+	set_config_field(tmp, SELECT_STROBE,	cfg->select_strobe);
+	set_config_field(tmp, EXTEND_WAIT,	cfg->extend_wait);
+	set_config_field(tmp, WR_SETUP,		cfg->wr_setup);
+	set_config_field(tmp, WR_STROBE,	cfg->wr_strobe);
+	set_config_field(tmp, WR_HOLD,		cfg->wr_hold);
+	set_config_field(tmp, RD_SETUP,		cfg->rd_setup);
+	set_config_field(tmp, RD_STROBE,	cfg->rd_strobe);
+	set_config_field(tmp, RD_HOLD,		cfg->rd_hold);
+	set_config_field(tmp, TURN_AROUND,	cfg->turn_around);
+	set_config_field(tmp, WIDTH,		cfg->width);
+
+	__raw_writel(tmp, AEMIF_CONFIG(cs));
+}
+
+void aemif_init(int num_cs, struct aemif_config *config)
+{
+	int cs;
+
+	if (num_cs > AEMIF_NUM_CS) {
+		num_cs = AEMIF_NUM_CS;
+		printf("AEMIF: csnum has to be <= 5");
+	}
+
+	for (cs = 0; cs < num_cs; cs++)
+		aemif_configure(cs, config + cs);
+}
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 4eb354da93..bf1312a373 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -68,5 +68,6 @@ else  # minimal SPL drivers
 obj-$(CONFIG_NAND_FSL_ELBC) += fsl_elbc_spl.o
 obj-$(CONFIG_NAND_FSL_IFC) += fsl_ifc_spl.o
 obj-$(CONFIG_NAND_MXC) += mxc_nand_spl.o
+obj-$(CONFIG_NAND_MXS) += mxs_nand_spl.o mxs_nand.o
 
 endif # drivers
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 75b03a74b6..5d425092f4 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -32,8 +32,7 @@
 #include <common.h>
 #include <asm/io.h>
 #include <nand.h>
-#include <asm/arch/nand_defs.h>
-#include <asm/arch/emif_defs.h>
+#include <asm/ti-common/davinci_nand.h>
 
 /* Definitions for 4-bit hardware ECC */
 #define NAND_TIMEOUT			10240
diff --git a/drivers/mtd/nand/mxs_nand_spl.c b/drivers/mtd/nand/mxs_nand_spl.c
new file mode 100644
index 0000000000..0e7c364a22
--- /dev/null
+++ b/drivers/mtd/nand/mxs_nand_spl.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright (C) 2014 Gateworks Corporation
+ * Author: Tim Harvey <tharvey@gateworks.com>
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+#include <common.h>
+#include <nand.h>
+#include <malloc.h>
+
+static nand_info_t mtd;
+static struct nand_chip nand_chip;
+
+static void mxs_nand_command(struct mtd_info *mtd, unsigned int command,
+			     int column, int page_addr)
+{
+	register struct nand_chip *chip = mtd->priv;
+	u32 timeo, time_start;
+
+	/* write out the command to the device */
+	chip->cmd_ctrl(mtd, command, NAND_CLE);
+
+	/* Serially input address */
+	if (column != -1) {
+		chip->cmd_ctrl(mtd, column, NAND_ALE);
+		chip->cmd_ctrl(mtd, column >> 8, NAND_ALE);
+	}
+	if (page_addr != -1) {
+		chip->cmd_ctrl(mtd, page_addr, NAND_ALE);
+		chip->cmd_ctrl(mtd, page_addr >> 8, NAND_ALE);
+		/* One more address cycle for devices > 128MiB */
+		if (chip->chipsize > (128 << 20))
+			chip->cmd_ctrl(mtd, page_addr >> 16, NAND_ALE);
+	}
+	chip->cmd_ctrl(mtd, NAND_CMD_NONE, 0);
+
+	if (command == NAND_CMD_READ0) {
+		chip->cmd_ctrl(mtd, NAND_CMD_READSTART, NAND_CLE);
+		chip->cmd_ctrl(mtd, NAND_CMD_NONE, 0);
+	}
+
+	/* wait for nand ready */
+	ndelay(100);
+	timeo = (CONFIG_SYS_HZ * 20) / 1000;
+	time_start = get_timer(0);
+	while (get_timer(time_start) < timeo) {
+		if (chip->dev_ready(mtd))
+			break;
+	}
+}
+
+static int mxs_flash_ident(struct mtd_info *mtd)
+{
+	register struct nand_chip *chip = mtd->priv;
+	int i;
+	u8 mfg_id, dev_id;
+	u8 id_data[8];
+	struct nand_onfi_params *p = &chip->onfi_params;
+
+	/* Reset the chip */
+	chip->cmdfunc(mtd, NAND_CMD_RESET, -1, -1);
+
+	/* Send the command for reading device ID */
+	chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
+
+	/* Read manufacturer and device IDs */
+	mfg_id = chip->read_byte(mtd);
+	dev_id = chip->read_byte(mtd);
+
+	/* Try again to make sure */
+	chip->cmdfunc(mtd, NAND_CMD_READID, 0x00, -1);
+	for (i = 0; i < 8; i++)
+		id_data[i] = chip->read_byte(mtd);
+	if (id_data[0] != mfg_id || id_data[1] != dev_id) {
+		printf("second ID read did not match");
+		return -1;
+	}
+	debug("0x%02x:0x%02x ", mfg_id, dev_id);
+
+	/* read ONFI */
+	chip->onfi_version = 0;
+	chip->cmdfunc(mtd, NAND_CMD_READID, 0x20, -1);
+	if (chip->read_byte(mtd) != 'O' || chip->read_byte(mtd) != 'N' ||
+	    chip->read_byte(mtd) != 'F' || chip->read_byte(mtd) != 'I') {
+		return -2;
+	}
+
+	/* we have ONFI, probe it */
+	chip->cmdfunc(mtd, NAND_CMD_PARAM, 0, -1);
+	chip->read_buf(mtd, (uint8_t *)p, sizeof(*p));
+	mtd->name = p->model;
+	mtd->writesize = le32_to_cpu(p->byte_per_page);
+	mtd->erasesize = le32_to_cpu(p->pages_per_block) * mtd->writesize;
+	mtd->oobsize = le16_to_cpu(p->spare_bytes_per_page);
+	chip->chipsize = le32_to_cpu(p->blocks_per_lun);
+	chip->chipsize *= (uint64_t)mtd->erasesize * p->lun_count;
+	/* Calculate the address shift from the page size */
+	chip->page_shift = ffs(mtd->writesize) - 1;
+	chip->phys_erase_shift = ffs(mtd->erasesize) - 1;
+	/* Convert chipsize to number of pages per chip -1 */
+	chip->pagemask = (chip->chipsize >> chip->page_shift) - 1;
+	chip->badblockbits = 8;
+
+	debug("erasesize=%d (>>%d)\n", mtd->erasesize, chip->phys_erase_shift);
+	debug("writesize=%d (>>%d)\n", mtd->writesize, chip->page_shift);
+	debug("oobsize=%d\n", mtd->oobsize);
+	debug("chipsize=%lld\n", chip->chipsize);
+
+	return 0;
+}
+
+static int mxs_read_page_ecc(struct mtd_info *mtd, void *buf, unsigned int page)
+{
+	register struct nand_chip *chip = mtd->priv;
+	int ret;
+
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0x0, page);
+	ret = nand_chip.ecc.read_page(mtd, chip, buf, 1, page);
+	if (ret < 0) {
+		printf("read_page failed %d\n", ret);
+		return -1;
+	}
+	return 0;
+}
+
+static int is_badblock(struct mtd_info *mtd, loff_t offs, int allowbbt)
+{
+	register struct nand_chip *chip = mtd->priv;
+	unsigned int block = offs >> chip->phys_erase_shift;
+	unsigned int page = offs >> chip->page_shift;
+
+	debug("%s offs=0x%08x block:%d page:%d\n", __func__, (int)offs, block,
+	      page);
+	chip->cmdfunc(mtd, NAND_CMD_READ0, mtd->writesize, page);
+	memset(chip->oob_poi, 0, mtd->oobsize);
+	chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+	return chip->oob_poi[0] != 0xff;
+}
+
+/* setup mtd and nand structs and init mxs_nand driver */
+static int mxs_nand_init(void)
+{
+	/* return if already initalized */
+	if (nand_chip.numchips)
+		return 0;
+
+	/* init mxs nand driver */
+	board_nand_init(&nand_chip);
+	mtd.priv = &nand_chip;
+	/* set mtd functions */
+	nand_chip.cmdfunc = mxs_nand_command;
+	nand_chip.numchips = 1;
+
+	/* identify flash device */
+	puts("NAND : ");
+	if (mxs_flash_ident(&mtd)) {
+		printf("Failed to identify\n");
+		return -1;
+	}
+
+	/* allocate and initialize buffers */
+	nand_chip.buffers = memalign(ARCH_DMA_MINALIGN,
+				     sizeof(*nand_chip.buffers));
+	nand_chip.oob_poi = nand_chip.buffers->databuf + mtd.writesize;
+	/* setup flash layout (does not scan as we override that) */
+	mtd.size = nand_chip.chipsize;
+	nand_chip.scan_bbt(&mtd);
+
+	printf("%llu MiB\n", (mtd.size / (1024 * 1024)));
+	return 0;
+}
+
+int nand_spl_load_image(uint32_t offs, unsigned int size, void *buf)
+{
+	struct nand_chip *chip;
+	unsigned int page;
+	unsigned int nand_page_per_block;
+	unsigned int sz = 0;
+
+	if (mxs_nand_init())
+		return -ENODEV;
+	chip = mtd.priv;
+	page = offs >> chip->page_shift;
+	nand_page_per_block = mtd.erasesize / mtd.writesize;
+
+	debug("%s offset:0x%08x len:%d page:%d\n", __func__, offs, size, page);
+
+	size = roundup(size, mtd.writesize);
+	while (sz < size) {
+		if (mxs_read_page_ecc(&mtd, buf, page) < 0)
+			return -1;
+		sz += mtd.writesize;
+		offs += mtd.writesize;
+		page++;
+		buf += mtd.writesize;
+
+		/*
+		 * Check if we have crossed a block boundary, and if so
+		 * check for bad block.
+		 */
+		if (!(page % nand_page_per_block)) {
+			/*
+			 * Yes, new block. See if this block is good. If not,
+			 * loop until we find a good block.
+			 */
+			while (is_badblock(&mtd, offs, 1)) {
+				page = page + nand_page_per_block;
+				/* Check i we've reached the end of flash. */
+				if (page >= mtd.size >> chip->page_shift)
+					return -ENOMEM;
+			}
+		}
+	}
+
+	return 0;
+}
+
+int nand_default_bbt(struct mtd_info *mtd)
+{
+	return 0;
+}
+
+void nand_init(void)
+{
+}
+
+void nand_deselect(void)
+{
+}
+
diff --git a/drivers/net/macb.c b/drivers/net/macb.c
index 781a272cff..01a94a4c4d 100644
--- a/drivers/net/macb.c
+++ b/drivers/net/macb.c
@@ -40,17 +40,21 @@
 
 #include "macb.h"
 
-#define CONFIG_SYS_MACB_RX_BUFFER_SIZE		4096
-#define CONFIG_SYS_MACB_RX_RING_SIZE		(CONFIG_SYS_MACB_RX_BUFFER_SIZE / 128)
-#define CONFIG_SYS_MACB_TX_RING_SIZE		16
-#define CONFIG_SYS_MACB_TX_TIMEOUT		1000
-#define CONFIG_SYS_MACB_AUTONEG_TIMEOUT	5000000
+#define MACB_RX_BUFFER_SIZE		4096
+#define MACB_RX_RING_SIZE		(MACB_RX_BUFFER_SIZE / 128)
+#define MACB_TX_RING_SIZE		16
+#define MACB_TX_TIMEOUT		1000
+#define MACB_AUTONEG_TIMEOUT	5000000
 
 struct macb_dma_desc {
 	u32	addr;
 	u32	ctrl;
 };
 
+#define DMA_DESC_BYTES(n)	(n * sizeof(struct macb_dma_desc))
+#define MACB_TX_DMA_DESC_SIZE	(DMA_DESC_BYTES(MACB_TX_RING_SIZE))
+#define MACB_RX_DMA_DESC_SIZE	(DMA_DESC_BYTES(MACB_RX_RING_SIZE))
+
 #define RXADDR_USED		0x00000001
 #define RXADDR_WRAP		0x00000002
 
@@ -170,7 +174,7 @@ int macb_miiphy_read(const char *devname, u8 phy_adr, u8 reg, u16 *value)
 	struct eth_device *dev = eth_get_dev_by_name(devname);
 	struct macb_device *macb = to_macb(dev);
 
-	if ( macb->phy_addr != phy_adr )
+	if (macb->phy_addr != phy_adr)
 		return -1;
 
 	arch_get_mdio_control(devname);
@@ -184,7 +188,7 @@ int macb_miiphy_write(const char *devname, u8 phy_adr, u8 reg, u16 value)
 	struct eth_device *dev = eth_get_dev_by_name(devname);
 	struct macb_device *macb = to_macb(dev);
 
-	if ( macb->phy_addr != phy_adr )
+	if (macb->phy_addr != phy_adr)
 		return -1;
 
 	arch_get_mdio_control(devname);
@@ -194,6 +198,39 @@ int macb_miiphy_write(const char *devname, u8 phy_adr, u8 reg, u16 value)
 }
 #endif
 
+#define RX	1
+#define TX	0
+static inline void macb_invalidate_ring_desc(struct macb_device *macb, bool rx)
+{
+	if (rx)
+		invalidate_dcache_range(macb->rx_ring_dma, macb->rx_ring_dma +
+			MACB_RX_DMA_DESC_SIZE);
+	else
+		invalidate_dcache_range(macb->tx_ring_dma, macb->tx_ring_dma +
+			MACB_TX_DMA_DESC_SIZE);
+}
+
+static inline void macb_flush_ring_desc(struct macb_device *macb, bool rx)
+{
+	if (rx)
+		flush_dcache_range(macb->rx_ring_dma, macb->rx_ring_dma +
+			MACB_RX_DMA_DESC_SIZE);
+	else
+		flush_dcache_range(macb->tx_ring_dma, macb->tx_ring_dma +
+			MACB_TX_DMA_DESC_SIZE);
+}
+
+static inline void macb_flush_rx_buffer(struct macb_device *macb)
+{
+	flush_dcache_range(macb->rx_buffer_dma, macb->rx_buffer_dma +
+				MACB_RX_BUFFER_SIZE);
+}
+
+static inline void macb_invalidate_rx_buffer(struct macb_device *macb)
+{
+	invalidate_dcache_range(macb->rx_buffer_dma, macb->rx_buffer_dma +
+				MACB_RX_BUFFER_SIZE);
+}
 
 #if defined(CONFIG_CMD_NET)
 
@@ -208,23 +245,28 @@ static int macb_send(struct eth_device *netdev, void *packet, int length)
 
 	ctrl = length & TXBUF_FRMLEN_MASK;
 	ctrl |= TXBUF_FRAME_END;
-	if (tx_head == (CONFIG_SYS_MACB_TX_RING_SIZE - 1)) {
+	if (tx_head == (MACB_TX_RING_SIZE - 1)) {
 		ctrl |= TXBUF_WRAP;
 		macb->tx_head = 0;
-	} else
+	} else {
 		macb->tx_head++;
+	}
 
 	macb->tx_ring[tx_head].ctrl = ctrl;
 	macb->tx_ring[tx_head].addr = paddr;
 	barrier();
+	macb_flush_ring_desc(macb, TX);
+	/* Do we need check paddr and length is dcache line aligned? */
+	flush_dcache_range(paddr, paddr + length);
 	macb_writel(macb, NCR, MACB_BIT(TE) | MACB_BIT(RE) | MACB_BIT(TSTART));
 
 	/*
 	 * I guess this is necessary because the networking core may
 	 * re-use the transmit buffer as soon as we return...
 	 */
-	for (i = 0; i <= CONFIG_SYS_MACB_TX_TIMEOUT; i++) {
+	for (i = 0; i <= MACB_TX_TIMEOUT; i++) {
 		barrier();
+		macb_invalidate_ring_desc(macb, TX);
 		ctrl = macb->tx_ring[tx_head].ctrl;
 		if (ctrl & TXBUF_USED)
 			break;
@@ -233,7 +275,7 @@ static int macb_send(struct eth_device *netdev, void *packet, int length)
 
 	dma_unmap_single(packet, length, paddr);
 
-	if (i <= CONFIG_SYS_MACB_TX_TIMEOUT) {
+	if (i <= MACB_TX_TIMEOUT) {
 		if (ctrl & TXBUF_UNDERRUN)
 			printf("%s: TX underrun\n", netdev->name);
 		if (ctrl & TXBUF_EXHAUSTED)
@@ -253,10 +295,12 @@ static void reclaim_rx_buffers(struct macb_device *macb,
 	unsigned int i;
 
 	i = macb->rx_tail;
+
+	macb_invalidate_ring_desc(macb, RX);
 	while (i > new_tail) {
 		macb->rx_ring[i].addr &= ~RXADDR_USED;
 		i++;
-		if (i > CONFIG_SYS_MACB_RX_RING_SIZE)
+		if (i > MACB_RX_RING_SIZE)
 			i = 0;
 	}
 
@@ -266,6 +310,7 @@ static void reclaim_rx_buffers(struct macb_device *macb,
 	}
 
 	barrier();
+	macb_flush_ring_desc(macb, RX);
 	macb->rx_tail = new_tail;
 }
 
@@ -279,6 +324,8 @@ static int macb_recv(struct eth_device *netdev)
 	u32 status;
 
 	for (;;) {
+		macb_invalidate_ring_desc(macb, RX);
+
 		if (!(macb->rx_ring[rx_tail].addr & RXADDR_USED))
 			return -1;
 
@@ -292,10 +339,12 @@ static int macb_recv(struct eth_device *netdev)
 		if (status & RXBUF_FRAME_END) {
 			buffer = macb->rx_buffer + 128 * macb->rx_tail;
 			length = status & RXBUF_FRMLEN_MASK;
+
+			macb_invalidate_rx_buffer(macb);
 			if (wrapped) {
 				unsigned int headlen, taillen;
 
-				headlen = 128 * (CONFIG_SYS_MACB_RX_RING_SIZE
+				headlen = 128 * (MACB_RX_RING_SIZE
 						 - macb->rx_tail);
 				taillen = length - headlen;
 				memcpy((void *)NetRxPackets[0],
@@ -306,11 +355,11 @@ static int macb_recv(struct eth_device *netdev)
 			}
 
 			NetReceive(buffer, length);
-			if (++rx_tail >= CONFIG_SYS_MACB_RX_RING_SIZE)
+			if (++rx_tail >= MACB_RX_RING_SIZE)
 				rx_tail = 0;
 			reclaim_rx_buffers(macb, rx_tail);
 		} else {
-			if (++rx_tail >= CONFIG_SYS_MACB_RX_RING_SIZE) {
+			if (++rx_tail >= MACB_RX_RING_SIZE) {
 				wrapped = 1;
 				rx_tail = 0;
 			}
@@ -333,7 +382,7 @@ static void macb_phy_reset(struct macb_device *macb)
 	macb_mdio_write(macb, MII_BMCR, (BMCR_ANENABLE
 					 | BMCR_ANRESTART));
 
-	for (i = 0; i < CONFIG_SYS_MACB_AUTONEG_TIMEOUT / 100; i++) {
+	for (i = 0; i < MACB_AUTONEG_TIMEOUT / 100; i++) {
 		status = macb_mdio_read(macb, MII_BMSR);
 		if (status & BMSR_ANEGCOMPLETE)
 			break;
@@ -385,9 +434,8 @@ static int macb_phy_init(struct macb_device *macb)
 	arch_get_mdio_control(netdev->name);
 #ifdef CONFIG_MACB_SEARCH_PHY
 	/* Auto-detect phy_addr */
-	if (!macb_phy_find(macb)) {
+	if (!macb_phy_find(macb))
 		return 0;
-	}
 #endif /* CONFIG_MACB_SEARCH_PHY */
 
 	/* Check if the PHY is up to snuff... */
@@ -414,7 +462,7 @@ static int macb_phy_init(struct macb_device *macb)
 		/* Try to re-negotiate if we don't have link already. */
 		macb_phy_reset(macb);
 
-		for (i = 0; i < CONFIG_SYS_MACB_AUTONEG_TIMEOUT / 100; i++) {
+		for (i = 0; i < MACB_AUTONEG_TIMEOUT / 100; i++) {
 			status = macb_mdio_read(macb, MII_BMSR);
 			if (status & BMSR_LSTATUS)
 				break;
@@ -499,21 +547,28 @@ static int macb_init(struct eth_device *netdev, bd_t *bd)
 
 	/* initialize DMA descriptors */
 	paddr = macb->rx_buffer_dma;
-	for (i = 0; i < CONFIG_SYS_MACB_RX_RING_SIZE; i++) {
-		if (i == (CONFIG_SYS_MACB_RX_RING_SIZE - 1))
+	for (i = 0; i < MACB_RX_RING_SIZE; i++) {
+		if (i == (MACB_RX_RING_SIZE - 1))
 			paddr |= RXADDR_WRAP;
 		macb->rx_ring[i].addr = paddr;
 		macb->rx_ring[i].ctrl = 0;
 		paddr += 128;
 	}
-	for (i = 0; i < CONFIG_SYS_MACB_TX_RING_SIZE; i++) {
+	macb_flush_ring_desc(macb, RX);
+	macb_flush_rx_buffer(macb);
+
+	for (i = 0; i < MACB_TX_RING_SIZE; i++) {
 		macb->tx_ring[i].addr = 0;
-		if (i == (CONFIG_SYS_MACB_TX_RING_SIZE - 1))
+		if (i == (MACB_TX_RING_SIZE - 1))
 			macb->tx_ring[i].ctrl = TXBUF_USED | TXBUF_WRAP;
 		else
 			macb->tx_ring[i].ctrl = TXBUF_USED;
 	}
-	macb->rx_tail = macb->tx_head = macb->tx_tail = 0;
+	macb_flush_ring_desc(macb, TX);
+
+	macb->rx_tail = 0;
+	macb->tx_head = 0;
+	macb->tx_tail = 0;
 
 	macb_writel(macb, RBQP, macb->rx_ring_dma);
 	macb_writel(macb, TBQP, macb->tx_ring_dma);
@@ -654,15 +709,15 @@ int macb_eth_initialize(int id, void *regs, unsigned int phy_addr)
 
 	netdev = &macb->netdev;
 
-	macb->rx_buffer = dma_alloc_coherent(CONFIG_SYS_MACB_RX_BUFFER_SIZE,
+	macb->rx_buffer = dma_alloc_coherent(MACB_RX_BUFFER_SIZE,
 					     &macb->rx_buffer_dma);
-	macb->rx_ring = dma_alloc_coherent(CONFIG_SYS_MACB_RX_RING_SIZE
-					   * sizeof(struct macb_dma_desc),
+	macb->rx_ring = dma_alloc_coherent(MACB_RX_DMA_DESC_SIZE,
 					   &macb->rx_ring_dma);
-	macb->tx_ring = dma_alloc_coherent(CONFIG_SYS_MACB_TX_RING_SIZE
-					   * sizeof(struct macb_dma_desc),
+	macb->tx_ring = dma_alloc_coherent(MACB_TX_DMA_DESC_SIZE,
 					   &macb->tx_ring_dma);
 
+	/* TODO: we need check the rx/tx_ring_dma is dcache line aligned */
+
 	macb->regs = regs;
 	macb->phy_addr = phy_addr;
 
diff --git a/drivers/power/pmic/pmic_max77686.c b/drivers/power/pmic/pmic_max77686.c
index d4c430e22e..df1fd91de3 100644
--- a/drivers/power/pmic/pmic_max77686.c
+++ b/drivers/power/pmic/pmic_max77686.c
@@ -210,6 +210,10 @@ int pmic_init(unsigned char bus)
 {
 	static const char name[] = "MAX77686_PMIC";
 	struct pmic *p = pmic_alloc();
+#ifdef CONFIG_OF_CONTROL
+	const void *blob = gd->fdt_blob;
+	int node, parent, tmp;
+#endif
 
 	if (!p) {
 		printf("%s: POWER allocation error!\n", __func__);
@@ -217,9 +221,6 @@ int pmic_init(unsigned char bus)
 	}
 
 #ifdef CONFIG_OF_CONTROL
-	const void *blob = gd->fdt_blob;
-	int node, parent;
-
 	node = fdtdec_next_compatible(blob, 0, COMPAT_MAXIM_MAX77686_PMIC);
 	if (node < 0) {
 		debug("PMIC: No node for PMIC Chip in device tree\n");
@@ -233,11 +234,13 @@ int pmic_init(unsigned char bus)
 		return -1;
 	}
 
-	p->bus = i2c_get_bus_num_fdt(parent);
-	if (p->bus < 0) {
+	/* tmp since p->bus is unsigned */
+	tmp = i2c_get_bus_num_fdt(parent);
+	if (tmp < 0) {
 		debug("%s: Cannot find I2C bus\n", __func__);
 		return -1;
 	}
+	p->bus = tmp;
 	p->hw.i2c.addr = fdtdec_get_int(blob, node, "reg", 9);
 #else
 	p->bus = bus;
diff --git a/drivers/serial/serial_mxc.c b/drivers/serial/serial_mxc.c
index 56bee55208..313d560afc 100644
--- a/drivers/serial/serial_mxc.c
+++ b/drivers/serial/serial_mxc.c
@@ -77,7 +77,7 @@
 #define  UCR3_DSR        (1<<10) /* Data set ready */
 #define  UCR3_DCD        (1<<9)  /* Data carrier detect */
 #define  UCR3_RI         (1<<8)  /* Ring indicator */
-#define  UCR3_TIMEOUTEN  (1<<7)  /* Timeout interrupt enable */
+#define  UCR3_ADNIMP     (1<<7)  /* Autobaud Detection Not Improved */
 #define  UCR3_RXDSEN	 (1<<6)  /* Receive status interrupt enable */
 #define  UCR3_AIRINTEN   (1<<5)  /* Async IR wake interrupt enable */
 #define  UCR3_AWAKEN	 (1<<4)  /* Async wake interrupt enable */
@@ -186,7 +186,7 @@ static int mxc_serial_init(void)
 
 	while (!(__REG(UART_PHYS + UCR2) & UCR2_SRST));
 
-	__REG(UART_PHYS + UCR3) = 0x0704;
+	__REG(UART_PHYS + UCR3) = 0x0704 | UCR3_ADNIMP;
 	__REG(UART_PHYS + UCR4) = 0x8000;
 	__REG(UART_PHYS + UESC) = 0x002b;
 	__REG(UART_PHYS + UTIM) = 0x0;
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 81b6af6694..b587308c84 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -40,3 +40,4 @@ obj-$(CONFIG_TEGRA114_SPI) += tegra114_spi.o
 obj-$(CONFIG_TI_QSPI) += ti_qspi.o
 obj-$(CONFIG_XILINX_SPI) += xilinx_spi.o
 obj-$(CONFIG_ZYNQ_SPI) += zynq_spi.o
+obj-$(CONFIG_FSL_QSPI) += fsl_qspi.o
diff --git a/drivers/spi/davinci_spi.c b/drivers/spi/davinci_spi.c
index 28fb3a2e9f..0ec5b9d859 100644
--- a/drivers/spi/davinci_spi.c
+++ b/drivers/spi/davinci_spi.c
@@ -41,7 +41,7 @@ struct spi_slave *spi_setup_slave(unsigned int bus, unsigned int cs,
 		break;
 #ifdef CONFIG_SYS_SPI1
 	case SPI1_BUS:
-		ds->regs = (struct davinci_spi_regs *)SPI0_BASE;
+		ds->regs = (struct davinci_spi_regs *)SPI1_BASE;
 		break;
 #endif
 #ifdef CONFIG_SYS_SPI2
diff --git a/drivers/spi/exynos_spi.c b/drivers/spi/exynos_spi.c
index 4d5def2d31..c92276fdf7 100644
--- a/drivers/spi/exynos_spi.c
+++ b/drivers/spi/exynos_spi.c
@@ -302,7 +302,10 @@ static int spi_rx_tx(struct exynos_spi_slave *spi_slave, int todo,
 					}
 				} else {
 					if (rxp || stopping) {
-						*rxp = temp;
+						if (step == 4)
+							*(uint32_t *)rxp = temp;
+						else
+							*rxp = temp;
 						rxp += step;
 					}
 					in_bytes -= step;
diff --git a/drivers/spi/fsl_qspi.c b/drivers/spi/fsl_qspi.c
new file mode 100644
index 0000000000..ba20beff4f
--- /dev/null
+++ b/drivers/spi/fsl_qspi.c
@@ -0,0 +1,482 @@
+/*
+ * Copyright 2013-2014 Freescale Semiconductor, Inc.
+ *
+ * Freescale Quad Serial Peripheral Interface (QSPI) driver
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <malloc.h>
+#include <spi.h>
+#include <asm/io.h>
+#include <linux/sizes.h>
+#include "fsl_qspi.h"
+
+#define RX_BUFFER_SIZE		0x80
+#define TX_BUFFER_SIZE		0x40
+
+#define OFFSET_BITS_MASK	0x00ffffff
+
+#define FLASH_STATUS_WEL	0x02
+
+/* SEQID */
+#define SEQID_WREN		1
+#define SEQID_FAST_READ		2
+#define SEQID_RDSR		3
+#define SEQID_SE		4
+#define SEQID_CHIP_ERASE	5
+#define SEQID_PP		6
+#define SEQID_RDID		7
+
+/* Flash opcodes */
+#define OPCODE_PP		0x02	/* Page program (up to 256 bytes) */
+#define OPCODE_RDSR		0x05	/* Read status register */
+#define OPCODE_WREN		0x06	/* Write enable */
+#define OPCODE_FAST_READ	0x0b	/* Read data bytes (high frequency) */
+#define OPCODE_CHIP_ERASE	0xc7	/* Erase whole flash chip */
+#define OPCODE_SE		0xd8	/* Sector erase (usually 64KiB) */
+#define OPCODE_RDID		0x9f	/* Read JEDEC ID */
+
+/* 4-byte address opcodes - used on Spansion and some Macronix flashes */
+#define OPCODE_FAST_READ_4B	0x0c    /* Read data bytes (high frequency) */
+#define OPCODE_PP_4B		0x12    /* Page program (up to 256 bytes) */
+#define OPCODE_SE_4B		0xdc    /* Sector erase (usually 64KiB) */
+
+#ifdef CONFIG_SYS_FSL_QSPI_LE
+#define qspi_read32		in_le32
+#define qspi_write32		out_le32
+#elif defined(CONFIG_SYS_FSL_QSPI_BE)
+#define qspi_read32		in_be32
+#define qspi_write32		out_be32
+#endif
+
+static unsigned long spi_bases[] = {
+	QSPI0_BASE_ADDR,
+};
+
+static unsigned long amba_bases[] = {
+	QSPI0_AMBA_BASE,
+};
+
+struct fsl_qspi {
+	struct spi_slave slave;
+	unsigned long reg_base;
+	unsigned long amba_base;
+	u32 sf_addr;
+	u8 cur_seqid;
+};
+
+/* QSPI support swapping the flash read/write data
+ * in hardware for LS102xA, but not for VF610 */
+static inline u32 qspi_endian_xchg(u32 data)
+{
+#ifdef CONFIG_VF610
+	return swab32(data);
+#else
+	return data;
+#endif
+}
+
+static inline struct fsl_qspi *to_qspi_spi(struct spi_slave *slave)
+{
+	return container_of(slave, struct fsl_qspi, slave);
+}
+
+static void qspi_set_lut(struct fsl_qspi *qspi)
+{
+	struct fsl_qspi_regs *regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	u32 lut_base;
+
+	/* Unlock the LUT */
+	qspi_write32(&regs->lutkey, LUT_KEY_VALUE);
+	qspi_write32(&regs->lckcr, QSPI_LCKCR_UNLOCK);
+
+	/* Write Enable */
+	lut_base = SEQID_WREN * 4;
+	qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_WREN) |
+		PAD0(LUT_PAD1) | INSTR0(LUT_CMD));
+	qspi_write32(&regs->lut[lut_base + 1], 0);
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* Fast Read */
+	lut_base = SEQID_FAST_READ * 4;
+	if (FSL_QSPI_FLASH_SIZE  <= SZ_16M)
+		qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_FAST_READ) |
+			PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
+			PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	else
+		qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_FAST_READ_4B) |
+			PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR32BIT) |
+			PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	qspi_write32(&regs->lut[lut_base + 1], OPRND0(8) | PAD0(LUT_PAD1) |
+		INSTR0(LUT_DUMMY) | OPRND1(RX_BUFFER_SIZE) | PAD1(LUT_PAD1) |
+		INSTR1(LUT_READ));
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* Read Status */
+	lut_base = SEQID_RDSR * 4;
+	qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_RDSR) |
+		PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(1) |
+		PAD1(LUT_PAD1) | INSTR1(LUT_READ));
+	qspi_write32(&regs->lut[lut_base + 1], 0);
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* Erase a sector */
+	lut_base = SEQID_SE * 4;
+	if (FSL_QSPI_FLASH_SIZE  <= SZ_16M)
+		qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_SE) |
+			PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
+			PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	else
+		qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_SE_4B) |
+			PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR32BIT) |
+			PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	qspi_write32(&regs->lut[lut_base + 1], 0);
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* Erase the whole chip */
+	lut_base = SEQID_CHIP_ERASE * 4;
+	qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_CHIP_ERASE) |
+		PAD0(LUT_PAD1) | INSTR0(LUT_CMD));
+	qspi_write32(&regs->lut[lut_base + 1], 0);
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* Page Program */
+	lut_base = SEQID_PP * 4;
+	if (FSL_QSPI_FLASH_SIZE  <= SZ_16M)
+		qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_PP) |
+			PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR24BIT) |
+			PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	else
+		qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_PP_4B) |
+			PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(ADDR32BIT) |
+			PAD1(LUT_PAD1) | INSTR1(LUT_ADDR));
+	qspi_write32(&regs->lut[lut_base + 1], OPRND0(TX_BUFFER_SIZE) |
+		PAD0(LUT_PAD1) | INSTR0(LUT_WRITE));
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* READ ID */
+	lut_base = SEQID_RDID * 4;
+	qspi_write32(&regs->lut[lut_base], OPRND0(OPCODE_RDID) |
+		PAD0(LUT_PAD1) | INSTR0(LUT_CMD) | OPRND1(8) |
+		PAD1(LUT_PAD1) | INSTR1(LUT_READ));
+	qspi_write32(&regs->lut[lut_base + 1], 0);
+	qspi_write32(&regs->lut[lut_base + 2], 0);
+	qspi_write32(&regs->lut[lut_base + 3], 0);
+
+	/* Lock the LUT */
+	qspi_write32(&regs->lutkey, LUT_KEY_VALUE);
+	qspi_write32(&regs->lckcr, QSPI_LCKCR_LOCK);
+}
+
+void spi_init()
+{
+	/* do nothing */
+}
+
+struct spi_slave *spi_setup_slave(unsigned int bus, unsigned int cs,
+		unsigned int max_hz, unsigned int mode)
+{
+	struct fsl_qspi *qspi;
+	struct fsl_qspi_regs *regs;
+	u32 reg_val, smpr_val;
+	u32 total_size, seq_id;
+
+	if (bus >= ARRAY_SIZE(spi_bases))
+		return NULL;
+
+	qspi = spi_alloc_slave(struct fsl_qspi, bus, cs);
+	if (!qspi)
+		return NULL;
+
+	qspi->reg_base = spi_bases[bus];
+	qspi->amba_base = amba_bases[bus];
+
+	qspi->slave.max_write_size = TX_BUFFER_SIZE;
+
+	regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	qspi_write32(&regs->mcr, QSPI_MCR_RESERVED_MASK | QSPI_MCR_MDIS_MASK);
+
+	smpr_val = qspi_read32(&regs->smpr);
+	qspi_write32(&regs->smpr, smpr_val & ~(QSPI_SMPR_FSDLY_MASK |
+		QSPI_SMPR_FSPHS_MASK | QSPI_SMPR_HSENA_MASK));
+	qspi_write32(&regs->mcr, QSPI_MCR_RESERVED_MASK);
+
+	total_size = FSL_QSPI_FLASH_SIZE * FSL_QSPI_FLASH_NUM;
+	qspi_write32(&regs->sfa1ad, FSL_QSPI_FLASH_SIZE | qspi->amba_base);
+	qspi_write32(&regs->sfa2ad, FSL_QSPI_FLASH_SIZE | qspi->amba_base);
+	qspi_write32(&regs->sfb1ad, total_size | qspi->amba_base);
+	qspi_write32(&regs->sfb2ad, total_size | qspi->amba_base);
+
+	qspi_set_lut(qspi);
+
+	smpr_val = qspi_read32(&regs->smpr);
+	smpr_val &= ~QSPI_SMPR_DDRSMP_MASK;
+	qspi_write32(&regs->smpr, smpr_val);
+	qspi_write32(&regs->mcr, QSPI_MCR_RESERVED_MASK);
+
+	seq_id = 0;
+	reg_val = qspi_read32(&regs->bfgencr);
+	reg_val &= ~QSPI_BFGENCR_SEQID_MASK;
+	reg_val |= (seq_id << QSPI_BFGENCR_SEQID_SHIFT);
+	reg_val &= ~QSPI_BFGENCR_PAR_EN_MASK;
+	qspi_write32(&regs->bfgencr, reg_val);
+
+	return &qspi->slave;
+}
+
+void spi_free_slave(struct spi_slave *slave)
+{
+	struct fsl_qspi *qspi = to_qspi_spi(slave);
+
+	free(qspi);
+}
+
+int spi_claim_bus(struct spi_slave *slave)
+{
+	return 0;
+}
+
+static void qspi_op_rdid(struct fsl_qspi *qspi, u32 *rxbuf, u32 len)
+{
+	struct fsl_qspi_regs *regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	u32 mcr_reg, rbsr_reg, data;
+	int i, size;
+
+	mcr_reg = qspi_read32(&regs->mcr);
+	qspi_write32(&regs->mcr, QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
+		QSPI_MCR_RESERVED_MASK | QSPI_MCR_END_CFD_LE);
+	qspi_write32(&regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
+
+	qspi_write32(&regs->sfar, qspi->amba_base);
+
+	qspi_write32(&regs->ipcr, (SEQID_RDID << QSPI_IPCR_SEQID_SHIFT) | 0);
+	while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+		;
+
+	i = 0;
+	size = len;
+	while ((RX_BUFFER_SIZE >= size) && (size > 0)) {
+		rbsr_reg = qspi_read32(&regs->rbsr);
+		if (rbsr_reg & QSPI_RBSR_RDBFL_MASK) {
+			data = qspi_read32(&regs->rbdr[i]);
+			data = qspi_endian_xchg(data);
+			memcpy(rxbuf, &data, 4);
+			rxbuf++;
+			size -= 4;
+			i++;
+		}
+	}
+
+	qspi_write32(&regs->mcr, mcr_reg);
+}
+
+static void qspi_op_read(struct fsl_qspi *qspi, u32 *rxbuf, u32 len)
+{
+	struct fsl_qspi_regs *regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	u32 mcr_reg, data;
+	int i, size;
+	u32 to_or_from;
+
+	mcr_reg = qspi_read32(&regs->mcr);
+	qspi_write32(&regs->mcr, QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
+		QSPI_MCR_RESERVED_MASK | QSPI_MCR_END_CFD_LE);
+	qspi_write32(&regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
+
+	to_or_from = qspi->sf_addr + qspi->amba_base;
+
+	while (len > 0) {
+		qspi_write32(&regs->sfar, to_or_from);
+
+		size = (len > RX_BUFFER_SIZE) ?
+			RX_BUFFER_SIZE : len;
+
+		qspi_write32(&regs->ipcr,
+			(SEQID_FAST_READ << QSPI_IPCR_SEQID_SHIFT) | size);
+		while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+			;
+
+		to_or_from += size;
+		len -= size;
+
+		i = 0;
+		while ((RX_BUFFER_SIZE >= size) && (size > 0)) {
+			data = qspi_read32(&regs->rbdr[i]);
+			data = qspi_endian_xchg(data);
+			memcpy(rxbuf, &data, 4);
+			rxbuf++;
+			size -= 4;
+			i++;
+		}
+		qspi_write32(&regs->mcr, qspi_read32(&regs->mcr) |
+			QSPI_MCR_CLR_RXF_MASK);
+	}
+
+	qspi_write32(&regs->mcr, mcr_reg);
+}
+
+static void qspi_op_pp(struct fsl_qspi *qspi, u32 *txbuf, u32 len)
+{
+	struct fsl_qspi_regs *regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	u32 mcr_reg, data, reg, status_reg;
+	int i, size, tx_size;
+	u32 to_or_from = 0;
+
+	mcr_reg = qspi_read32(&regs->mcr);
+	qspi_write32(&regs->mcr, QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
+		QSPI_MCR_RESERVED_MASK | QSPI_MCR_END_CFD_LE);
+	qspi_write32(&regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
+
+	status_reg = 0;
+	while ((status_reg & FLASH_STATUS_WEL) != FLASH_STATUS_WEL) {
+		qspi_write32(&regs->ipcr,
+			(SEQID_WREN << QSPI_IPCR_SEQID_SHIFT) | 0);
+		while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+			;
+
+		qspi_write32(&regs->ipcr,
+			(SEQID_RDSR << QSPI_IPCR_SEQID_SHIFT) | 1);
+		while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+			;
+
+		reg = qspi_read32(&regs->rbsr);
+		if (reg & QSPI_RBSR_RDBFL_MASK) {
+			status_reg = qspi_read32(&regs->rbdr[0]);
+			status_reg = qspi_endian_xchg(status_reg);
+		}
+		qspi_write32(&regs->mcr,
+			qspi_read32(&regs->mcr) | QSPI_MCR_CLR_RXF_MASK);
+	}
+
+	to_or_from = qspi->sf_addr + qspi->amba_base;
+	qspi_write32(&regs->sfar, to_or_from);
+
+	tx_size = (len > TX_BUFFER_SIZE) ?
+		TX_BUFFER_SIZE : len;
+
+	size = (tx_size + 3) / 4;
+
+	for (i = 0; i < size; i++) {
+		data = qspi_endian_xchg(*txbuf);
+		qspi_write32(&regs->tbdr, data);
+		txbuf++;
+	}
+
+	qspi_write32(&regs->ipcr,
+		(SEQID_PP << QSPI_IPCR_SEQID_SHIFT) | tx_size);
+	while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+		;
+
+	qspi_write32(&regs->mcr, mcr_reg);
+}
+
+static void qspi_op_rdsr(struct fsl_qspi *qspi, u32 *rxbuf)
+{
+	struct fsl_qspi_regs *regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	u32 mcr_reg, reg, data;
+
+	mcr_reg = qspi_read32(&regs->mcr);
+	qspi_write32(&regs->mcr, QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
+		QSPI_MCR_RESERVED_MASK | QSPI_MCR_END_CFD_LE);
+	qspi_write32(&regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
+
+	qspi_write32(&regs->sfar, qspi->amba_base);
+
+	qspi_write32(&regs->ipcr,
+		(SEQID_RDSR << QSPI_IPCR_SEQID_SHIFT) | 0);
+	while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+		;
+
+	while (1) {
+		reg = qspi_read32(&regs->rbsr);
+		if (reg & QSPI_RBSR_RDBFL_MASK) {
+			data = qspi_read32(&regs->rbdr[0]);
+			data = qspi_endian_xchg(data);
+			memcpy(rxbuf, &data, 4);
+			qspi_write32(&regs->mcr, qspi_read32(&regs->mcr) |
+				QSPI_MCR_CLR_RXF_MASK);
+			break;
+		}
+	}
+
+	qspi_write32(&regs->mcr, mcr_reg);
+}
+
+static void qspi_op_se(struct fsl_qspi *qspi)
+{
+	struct fsl_qspi_regs *regs = (struct fsl_qspi_regs *)qspi->reg_base;
+	u32 mcr_reg;
+	u32 to_or_from = 0;
+
+	mcr_reg = qspi_read32(&regs->mcr);
+	qspi_write32(&regs->mcr, QSPI_MCR_CLR_RXF_MASK | QSPI_MCR_CLR_TXF_MASK |
+		QSPI_MCR_RESERVED_MASK | QSPI_MCR_END_CFD_LE);
+	qspi_write32(&regs->rbct, QSPI_RBCT_RXBRD_USEIPS);
+
+	to_or_from = qspi->sf_addr + qspi->amba_base;
+	qspi_write32(&regs->sfar, to_or_from);
+
+	qspi_write32(&regs->ipcr,
+		(SEQID_WREN << QSPI_IPCR_SEQID_SHIFT) | 0);
+	while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+		;
+
+	qspi_write32(&regs->ipcr,
+		(SEQID_SE << QSPI_IPCR_SEQID_SHIFT) | 0);
+	while (qspi_read32(&regs->sr) & QSPI_SR_BUSY_MASK)
+		;
+
+	qspi_write32(&regs->mcr, mcr_reg);
+}
+
+int spi_xfer(struct spi_slave *slave, unsigned int bitlen,
+		const void *dout, void *din, unsigned long flags)
+{
+	struct fsl_qspi *qspi = to_qspi_spi(slave);
+	u32 bytes = DIV_ROUND_UP(bitlen, 8);
+	static u32 pp_sfaddr;
+	u32 txbuf;
+
+	if (dout) {
+		memcpy(&txbuf, dout, 4);
+		qspi->cur_seqid = *(u8 *)dout;
+
+		if (flags == SPI_XFER_END) {
+			qspi->sf_addr = pp_sfaddr;
+			qspi_op_pp(qspi, (u32 *)dout, bytes);
+			return 0;
+		}
+
+		if (qspi->cur_seqid == OPCODE_FAST_READ) {
+			qspi->sf_addr = swab32(txbuf) & OFFSET_BITS_MASK;
+		} else if (qspi->cur_seqid == OPCODE_SE) {
+			qspi->sf_addr = swab32(txbuf) & OFFSET_BITS_MASK;
+			qspi_op_se(qspi);
+		} else if (qspi->cur_seqid == OPCODE_PP) {
+			pp_sfaddr = swab32(txbuf) & OFFSET_BITS_MASK;
+		}
+	}
+
+	if (din) {
+		if (qspi->cur_seqid == OPCODE_FAST_READ)
+			qspi_op_read(qspi, din, bytes);
+		else if (qspi->cur_seqid == OPCODE_RDID)
+			qspi_op_rdid(qspi, din, bytes);
+		else if (qspi->cur_seqid == OPCODE_RDSR)
+			qspi_op_rdsr(qspi, din);
+	}
+
+	return 0;
+}
+
+void spi_release_bus(struct spi_slave *slave)
+{
+	/* Nothing to do */
+}
diff --git a/drivers/spi/fsl_qspi.h b/drivers/spi/fsl_qspi.h
new file mode 100644
index 0000000000..db400e66b5
--- /dev/null
+++ b/drivers/spi/fsl_qspi.h
@@ -0,0 +1,127 @@
+/*
+ * Copyright 2013-2014 Freescale Semiconductor, Inc.
+ *
+ * Register definitions for Freescale QSPI
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#ifndef _FSL_QSPI_H_
+#define _FSL_QSPI_H_
+
+struct fsl_qspi_regs {
+	u32 mcr;
+	u32 rsvd0[1];
+	u32 ipcr;
+	u32 flshcr;
+	u32 buf0cr;
+	u32 buf1cr;
+	u32 buf2cr;
+	u32 buf3cr;
+	u32 bfgencr;
+	u32 soccr;
+	u32 rsvd1[2];
+	u32 buf0ind;
+	u32 buf1ind;
+	u32 buf2ind;
+	u32 rsvd2[49];
+	u32 sfar;
+	u32 rsvd3[1];
+	u32 smpr;
+	u32 rbsr;
+	u32 rbct;
+	u32 rsvd4[15];
+	u32 tbsr;
+	u32 tbdr;
+	u32 rsvd5[1];
+	u32 sr;
+	u32 fr;
+	u32 rser;
+	u32 spndst;
+	u32 sptrclr;
+	u32 rsvd6[4];
+	u32 sfa1ad;
+	u32 sfa2ad;
+	u32 sfb1ad;
+	u32 sfb2ad;
+	u32 rsvd7[28];
+	u32 rbdr[32];
+	u32 rsvd8[32];
+	u32 lutkey;
+	u32 lckcr;
+	u32 rsvd9[2];
+	u32 lut[64];
+};
+
+#define QSPI_IPCR_SEQID_SHIFT		24
+#define QSPI_IPCR_SEQID_MASK		(0xf << QSPI_IPCR_SEQID_SHIFT)
+
+#define QSPI_MCR_END_CFD_SHIFT		2
+#define QSPI_MCR_END_CFD_MASK		(3 << QSPI_MCR_END_CFD_SHIFT)
+#define QSPI_MCR_END_CFD_LE		(1 << QSPI_MCR_END_CFD_SHIFT)
+#define QSPI_MCR_DDR_EN_SHIFT		7
+#define QSPI_MCR_DDR_EN_MASK		(1 << QSPI_MCR_DDR_EN_SHIFT)
+#define QSPI_MCR_CLR_RXF_SHIFT		10
+#define QSPI_MCR_CLR_RXF_MASK		(1 << QSPI_MCR_CLR_RXF_SHIFT)
+#define QSPI_MCR_CLR_TXF_SHIFT		11
+#define QSPI_MCR_CLR_TXF_MASK		(1 << QSPI_MCR_CLR_TXF_SHIFT)
+#define QSPI_MCR_MDIS_SHIFT		14
+#define QSPI_MCR_MDIS_MASK		(1 << QSPI_MCR_MDIS_SHIFT)
+#define QSPI_MCR_RESERVED_SHIFT		16
+#define QSPI_MCR_RESERVED_MASK		(0xf << QSPI_MCR_RESERVED_SHIFT)
+
+#define QSPI_SMPR_HSENA_SHIFT		0
+#define QSPI_SMPR_HSENA_MASK		(1 << QSPI_SMPR_HSENA_SHIFT)
+#define QSPI_SMPR_FSPHS_SHIFT		5
+#define QSPI_SMPR_FSPHS_MASK		(1 << QSPI_SMPR_FSPHS_SHIFT)
+#define QSPI_SMPR_FSDLY_SHIFT		6
+#define QSPI_SMPR_FSDLY_MASK		(1 << QSPI_SMPR_FSDLY_SHIFT)
+#define QSPI_SMPR_DDRSMP_SHIFT		16
+#define QSPI_SMPR_DDRSMP_MASK		(7 << QSPI_SMPR_DDRSMP_SHIFT)
+
+#define QSPI_BFGENCR_SEQID_SHIFT	12
+#define QSPI_BFGENCR_SEQID_MASK		(0xf << QSPI_BFGENCR_SEQID_SHIFT)
+#define QSPI_BFGENCR_PAR_EN_SHIFT	16
+#define QSPI_BFGENCR_PAR_EN_MASK	(1 << QSPI_BFGENCR_PAR_EN_SHIFT)
+
+#define QSPI_RBSR_RDBFL_SHIFT		8
+#define QSPI_RBSR_RDBFL_MASK		(0x3f << QSPI_RBSR_RDBFL_SHIFT)
+
+#define QSPI_RBCT_RXBRD_SHIFT		8
+#define QSPI_RBCT_RXBRD_USEIPS		(1 << QSPI_RBCT_RXBRD_SHIFT)
+
+#define QSPI_SR_BUSY_SHIFT		0
+#define QSPI_SR_BUSY_MASK		(1 << QSPI_SR_BUSY_SHIFT)
+
+#define QSPI_LCKCR_LOCK			0x1
+#define QSPI_LCKCR_UNLOCK		0x2
+
+#define LUT_KEY_VALUE			0x5af05af0
+
+#define OPRND0_SHIFT			0
+#define OPRND0(x)			((x) << OPRND0_SHIFT)
+#define PAD0_SHIFT			8
+#define PAD0(x)				((x) << PAD0_SHIFT)
+#define INSTR0_SHIFT			10
+#define INSTR0(x)			((x) << INSTR0_SHIFT)
+#define OPRND1_SHIFT			16
+#define OPRND1(x)			((x) << OPRND1_SHIFT)
+#define PAD1_SHIFT			24
+#define PAD1(x)				((x) << PAD1_SHIFT)
+#define INSTR1_SHIFT			26
+#define INSTR1(x)			((x) << INSTR1_SHIFT)
+
+#define LUT_CMD				1
+#define LUT_ADDR			2
+#define LUT_DUMMY			3
+#define LUT_READ			7
+#define LUT_WRITE			8
+
+#define LUT_PAD1			0
+#define LUT_PAD2			1
+#define LUT_PAD4			2
+
+#define ADDR24BIT			0x18
+#define ADDR32BIT			0x20
+
+#endif /* _FSL_QSPI_H_ */
diff --git a/drivers/video/atmel_hlcdfb.c b/drivers/video/atmel_hlcdfb.c
index bb4d7d8c14..935ae42a9c 100644
--- a/drivers/video/atmel_hlcdfb.c
+++ b/drivers/video/atmel_hlcdfb.c
@@ -171,6 +171,9 @@ void lcd_ctrl_init(void *lcdbase)
 			| LCDC_BASECTRL_DMAIEN | LCDC_BASECTRL_DFETCH;
 	desc->next = (u32)desc;
 
+	/* Flush the DMA descriptor if we enabled dcache */
+	flush_dcache_range((u32)desc, (u32)desc + sizeof(*desc));
+
 	lcdc_writel(&regs->lcdc_baseaddr, desc->address);
 	lcdc_writel(&regs->lcdc_basectrl, desc->control);
 	lcdc_writel(&regs->lcdc_basenext, desc->next);
@@ -194,4 +197,7 @@ void lcd_ctrl_init(void *lcdbase)
 	lcdc_writel(&regs->lcdc_lcden, value | LCDC_LCDEN_PWMEN);
 	while (!(lcdc_readl(&regs->lcdc_lcdsr) & LCDC_LCDSR_PWMSTS))
 		udelay(1);
+
+	/* Enable flushing if we enabled dcache */
+	lcd_set_flush_dcache(1);
 }