Merge branch 'next-spi' of git://git.secretlab.ca/git/linux-2.6

* 'next-spi' of git://git.secretlab.ca/git/linux-2.6: (31 commits)
  spi: Correct SPI clock frequency setting in spi_mpc8xxx
  spi/spi_s3c64xx.c: Fix continuation line formats
  spi/dw_spi: Fix dw_spi_mmio to depend on HAVE_CLK
  spi/dw_spi: Allow dw_spi.c to be a module
  spi/dw_spi: mmio code style fixups
  Memory-mapped dw_spi driver
  spi/dw_spi: fix missing export of dw_spi_remove_host
  spi/dw_spi: conditional transfer mode changes
  spi/dw_spi: remove conditional from 'poll_transfer'.
  spi/dw_spi: fixed a spelling typo in a warning message.
  spi/dw_spi: add return value to empty mrst_spi_debugfs_init()
  spi/dw_spi: enable platform specific chipselect.
  spi/dw_spi: add a FIFO depth detection
  spi/dw_spi: fix __init/__devinit section mismatch
  spi: xilinx_spi: Fix up I/O routine wrapping bogosity.
  spi/spi_imx: add device information by switching pr_debug() to dev_dbg()
  spi: update MSIOF includes
  spi/dw_spi: refine the IRQ mode working flow
  spi/dw_spi: add a missed dw_spi_remove_host() in exit sequence
  spi/dw_spi: bug fix in wait_till_not_busy()
  ...

18 files changed, 2225 insertions, 100 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index f55eb010733..0fee95cd9a4 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -100,6 +100,23 @@ config SPI_BUTTERFLY
 	  inexpensive battery powered microcontroller evaluation board.
 	  This same cable can be used to flash new firmware.
 
+config SPI_COLDFIRE_QSPI
+	tristate "Freescale Coldfire QSPI controller"
+	depends on (M520x || M523x || M5249 || M527x || M528x || M532x)
+	help
+	  This enables support for the Coldfire QSPI controller in master
+	  mode.
+
+	  This driver can also be built as a module.  If so, the module
+	  will be called coldfire_qspi.
+
+config SPI_DAVINCI
+	tristate "SPI controller driver for DaVinci/DA8xx SoC's"
+	depends on SPI_MASTER && ARCH_DAVINCI
+	select SPI_BITBANG
+	help
+	  SPI master controller for DaVinci and DA8xx SPI modules.
+
 config SPI_GPIO
 	tristate "GPIO-based bitbanging SPI Master"
 	depends on GENERIC_GPIO
@@ -308,7 +325,7 @@ config SPI_NUC900
 #
 
 config SPI_DESIGNWARE
-	bool "DesignWare SPI controller core support"
+	tristate "DesignWare SPI controller core support"
 	depends on SPI_MASTER
 	help
 	  general driver for SPI controller core from DesignWare
@@ -317,6 +334,10 @@ config SPI_DW_PCI
 	tristate "PCI interface driver for DW SPI core"
 	depends on SPI_DESIGNWARE && PCI
 
+config SPI_DW_MMIO
+	tristate "Memory-mapped io interface driver for DW SPI core"
+	depends on SPI_DESIGNWARE && HAVE_CLK
+
 #
 # There are lots of SPI device types, with sensors and memory
 # being probably the most widely used ones.
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index f3d2810ba11..d7d0f89b797 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -16,8 +16,11 @@ obj-$(CONFIG_SPI_BFIN)			+= spi_bfin5xx.o
 obj-$(CONFIG_SPI_BITBANG)		+= spi_bitbang.o
 obj-$(CONFIG_SPI_AU1550)		+= au1550_spi.o
 obj-$(CONFIG_SPI_BUTTERFLY)		+= spi_butterfly.o
+obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= coldfire_qspi.o
+obj-$(CONFIG_SPI_DAVINCI)		+= davinci_spi.o
 obj-$(CONFIG_SPI_DESIGNWARE)		+= dw_spi.o
 obj-$(CONFIG_SPI_DW_PCI)		+= dw_spi_pci.o
+obj-$(CONFIG_SPI_DW_MMIO)		+= dw_spi_mmio.o
 obj-$(CONFIG_SPI_GPIO)			+= spi_gpio.o
 obj-$(CONFIG_SPI_IMX)			+= spi_imx.o
 obj-$(CONFIG_SPI_LM70_LLP)		+= spi_lm70llp.o
diff --git a/drivers/spi/coldfire_qspi.c b/drivers/spi/coldfire_qspi.c
new file mode 100644
index 00000000000..59be3efe063
--- /dev/null
+++ b/drivers/spi/coldfire_qspi.c
@@ -0,0 +1,640 @@
+/*
+ * Freescale/Motorola Coldfire Queued SPI driver
+ *
+ * Copyright 2010 Steven King <sfking@fdwdc.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA
+ *
+*/
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/platform_device.h>
+#include <linux/workqueue.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/spi/spi.h>
+
+#include <asm/coldfire.h>
+#include <asm/mcfqspi.h>
+
+#define	DRIVER_NAME "mcfqspi"
+
+#define	MCFQSPI_BUSCLK			(MCF_BUSCLK / 2)
+
+#define	MCFQSPI_QMR			0x00
+#define		MCFQSPI_QMR_MSTR	0x8000
+#define		MCFQSPI_QMR_CPOL	0x0200
+#define		MCFQSPI_QMR_CPHA	0x0100
+#define	MCFQSPI_QDLYR			0x04
+#define		MCFQSPI_QDLYR_SPE	0x8000
+#define	MCFQSPI_QWR			0x08
+#define		MCFQSPI_QWR_HALT	0x8000
+#define		MCFQSPI_QWR_WREN	0x4000
+#define		MCFQSPI_QWR_CSIV	0x1000
+#define	MCFQSPI_QIR			0x0C
+#define		MCFQSPI_QIR_WCEFB	0x8000
+#define		MCFQSPI_QIR_ABRTB	0x4000
+#define		MCFQSPI_QIR_ABRTL	0x1000
+#define		MCFQSPI_QIR_WCEFE	0x0800
+#define		MCFQSPI_QIR_ABRTE	0x0400
+#define		MCFQSPI_QIR_SPIFE	0x0100
+#define		MCFQSPI_QIR_WCEF	0x0008
+#define		MCFQSPI_QIR_ABRT	0x0004
+#define		MCFQSPI_QIR_SPIF	0x0001
+#define	MCFQSPI_QAR			0x010
+#define		MCFQSPI_QAR_TXBUF	0x00
+#define		MCFQSPI_QAR_RXBUF	0x10
+#define		MCFQSPI_QAR_CMDBUF	0x20
+#define	MCFQSPI_QDR			0x014
+#define	MCFQSPI_QCR			0x014
+#define		MCFQSPI_QCR_CONT	0x8000
+#define		MCFQSPI_QCR_BITSE	0x4000
+#define		MCFQSPI_QCR_DT		0x2000
+
+struct mcfqspi {
+	void __iomem *iobase;
+	int irq;
+	struct clk *clk;
+	struct mcfqspi_cs_control *cs_control;
+
+	wait_queue_head_t waitq;
+
+	struct work_struct work;
+	struct workqueue_struct *workq;
+	spinlock_t lock;
+	struct list_head msgq;
+};
+
+static void mcfqspi_wr_qmr(struct mcfqspi *mcfqspi, u16 val)
+{
+	writew(val, mcfqspi->iobase + MCFQSPI_QMR);
+}
+
+static void mcfqspi_wr_qdlyr(struct mcfqspi *mcfqspi, u16 val)
+{
+	writew(val, mcfqspi->iobase + MCFQSPI_QDLYR);
+}
+
+static u16 mcfqspi_rd_qdlyr(struct mcfqspi *mcfqspi)
+{
+	return readw(mcfqspi->iobase + MCFQSPI_QDLYR);
+}
+
+static void mcfqspi_wr_qwr(struct mcfqspi *mcfqspi, u16 val)
+{
+	writew(val, mcfqspi->iobase + MCFQSPI_QWR);
+}
+
+static void mcfqspi_wr_qir(struct mcfqspi *mcfqspi, u16 val)
+{
+	writew(val, mcfqspi->iobase + MCFQSPI_QIR);
+}
+
+static void mcfqspi_wr_qar(struct mcfqspi *mcfqspi, u16 val)
+{
+	writew(val, mcfqspi->iobase + MCFQSPI_QAR);
+}
+
+static void mcfqspi_wr_qdr(struct mcfqspi *mcfqspi, u16 val)
+{
+	writew(val, mcfqspi->iobase + MCFQSPI_QDR);
+}
+
+static u16 mcfqspi_rd_qdr(struct mcfqspi *mcfqspi)
+{
+	return readw(mcfqspi->iobase + MCFQSPI_QDR);
+}
+
+static void mcfqspi_cs_select(struct mcfqspi *mcfqspi, u8 chip_select,
+			    bool cs_high)
+{
+	mcfqspi->cs_control->select(mcfqspi->cs_control, chip_select, cs_high);
+}
+
+static void mcfqspi_cs_deselect(struct mcfqspi *mcfqspi, u8 chip_select,
+				bool cs_high)
+{
+	mcfqspi->cs_control->deselect(mcfqspi->cs_control, chip_select, cs_high);
+}
+
+static int mcfqspi_cs_setup(struct mcfqspi *mcfqspi)
+{
+	return (mcfqspi->cs_control && mcfqspi->cs_control->setup) ?
+		mcfqspi->cs_control->setup(mcfqspi->cs_control) : 0;
+}
+
+static void mcfqspi_cs_teardown(struct mcfqspi *mcfqspi)
+{
+	if (mcfqspi->cs_control && mcfqspi->cs_control->teardown)
+		mcfqspi->cs_control->teardown(mcfqspi->cs_control);
+}
+
+static u8 mcfqspi_qmr_baud(u32 speed_hz)
+{
+	return clamp((MCFQSPI_BUSCLK + speed_hz - 1) / speed_hz, 2u, 255u);
+}
+
+static bool mcfqspi_qdlyr_spe(struct mcfqspi *mcfqspi)
+{
+	return mcfqspi_rd_qdlyr(mcfqspi) & MCFQSPI_QDLYR_SPE;
+}
+
+static irqreturn_t mcfqspi_irq_handler(int this_irq, void *dev_id)
+{
+	struct mcfqspi *mcfqspi = dev_id;
+
+	/* clear interrupt */
+	mcfqspi_wr_qir(mcfqspi, MCFQSPI_QIR_SPIFE | MCFQSPI_QIR_SPIF);
+	wake_up(&mcfqspi->waitq);
+
+	return IRQ_HANDLED;
+}
+
+static void mcfqspi_transfer_msg8(struct mcfqspi *mcfqspi, unsigned count,
+				  const u8 *txbuf, u8 *rxbuf)
+{
+	unsigned i, n, offset = 0;
+
+	n = min(count, 16u);
+
+	mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_CMDBUF);
+	for (i = 0; i < n; ++i)
+		mcfqspi_wr_qdr(mcfqspi, MCFQSPI_QCR_BITSE);
+
+	mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_TXBUF);
+	if (txbuf)
+		for (i = 0; i < n; ++i)
+			mcfqspi_wr_qdr(mcfqspi, *txbuf++);
+	else
+		for (i = 0; i < count; ++i)
+			mcfqspi_wr_qdr(mcfqspi, 0);
+
+	count -= n;
+	if (count) {
+		u16 qwr = 0xf08;
+		mcfqspi_wr_qwr(mcfqspi, 0x700);
+		mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+
+		do {
+			wait_event(mcfqspi->waitq, !mcfqspi_qdlyr_spe(mcfqspi));
+			mcfqspi_wr_qwr(mcfqspi, qwr);
+			mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+			if (rxbuf) {
+				mcfqspi_wr_qar(mcfqspi,
+					       MCFQSPI_QAR_RXBUF + offset);
+				for (i = 0; i < 8; ++i)
+					*rxbuf++ = mcfqspi_rd_qdr(mcfqspi);
+			}
+			n = min(count, 8u);
+			if (txbuf) {
+				mcfqspi_wr_qar(mcfqspi,
+					       MCFQSPI_QAR_TXBUF + offset);
+				for (i = 0; i < n; ++i)
+					mcfqspi_wr_qdr(mcfqspi, *txbuf++);
+			}
+			qwr = (offset ? 0x808 : 0) + ((n - 1) << 8);
+			offset ^= 8;
+			count -= n;
+		} while (count);
+		wait_event(mcfqspi->waitq, !mcfqspi_qdlyr_spe(mcfqspi));
+		mcfqspi_wr_qwr(mcfqspi, qwr);
+		mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+		if (rxbuf) {
+			mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_RXBUF + offset);
+			for (i = 0; i < 8; ++i)
+				*rxbuf++ = mcfqspi_rd_qdr(mcfqspi);
+			offset ^= 8;
+		}
+	} else {
+		mcfqspi_wr_qwr(mcfqspi, (n - 1) << 8);
+		mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+	}
+	wait_event(mcfqspi->waitq, !mcfqspi_qdlyr_spe(mcfqspi));
+	if (rxbuf) {
+		mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_RXBUF + offset);
+		for (i = 0; i < n; ++i)
+			*rxbuf++ = mcfqspi_rd_qdr(mcfqspi);
+	}
+}
+
+static void mcfqspi_transfer_msg16(struct mcfqspi *mcfqspi, unsigned count,
+				   const u16 *txbuf, u16 *rxbuf)
+{
+	unsigned i, n, offset = 0;
+
+	n = min(count, 16u);
+
+	mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_CMDBUF);
+	for (i = 0; i < n; ++i)
+		mcfqspi_wr_qdr(mcfqspi, MCFQSPI_QCR_BITSE);
+
+	mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_TXBUF);
+	if (txbuf)
+		for (i = 0; i < n; ++i)
+			mcfqspi_wr_qdr(mcfqspi, *txbuf++);
+	else
+		for (i = 0; i < count; ++i)
+			mcfqspi_wr_qdr(mcfqspi, 0);
+
+	count -= n;
+	if (count) {
+		u16 qwr = 0xf08;
+		mcfqspi_wr_qwr(mcfqspi, 0x700);
+		mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+
+		do {
+			wait_event(mcfqspi->waitq, !mcfqspi_qdlyr_spe(mcfqspi));
+			mcfqspi_wr_qwr(mcfqspi, qwr);
+			mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+			if (rxbuf) {
+				mcfqspi_wr_qar(mcfqspi,
+					       MCFQSPI_QAR_RXBUF + offset);
+				for (i = 0; i < 8; ++i)
+					*rxbuf++ = mcfqspi_rd_qdr(mcfqspi);
+			}
+			n = min(count, 8u);
+			if (txbuf) {
+				mcfqspi_wr_qar(mcfqspi,
+					       MCFQSPI_QAR_TXBUF + offset);
+				for (i = 0; i < n; ++i)
+					mcfqspi_wr_qdr(mcfqspi, *txbuf++);
+			}
+			qwr = (offset ? 0x808 : 0x000) + ((n - 1) << 8);
+			offset ^= 8;
+			count -= n;
+		} while (count);
+		wait_event(mcfqspi->waitq, !mcfqspi_qdlyr_spe(mcfqspi));
+		mcfqspi_wr_qwr(mcfqspi, qwr);
+		mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+		if (rxbuf) {
+			mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_RXBUF + offset);
+			for (i = 0; i < 8; ++i)
+				*rxbuf++ = mcfqspi_rd_qdr(mcfqspi);
+			offset ^= 8;
+		}
+	} else {
+		mcfqspi_wr_qwr(mcfqspi, (n - 1) << 8);
+		mcfqspi_wr_qdlyr(mcfqspi, MCFQSPI_QDLYR_SPE);
+	}
+	wait_event(mcfqspi->waitq, !mcfqspi_qdlyr_spe(mcfqspi));
+	if (rxbuf) {
+		mcfqspi_wr_qar(mcfqspi, MCFQSPI_QAR_RXBUF + offset);
+		for (i = 0; i < n; ++i)
+			*rxbuf++ = mcfqspi_rd_qdr(mcfqspi);
+	}
+}
+
+static void mcfqspi_work(struct work_struct *work)
+{
+	struct mcfqspi *mcfqspi = container_of(work, struct mcfqspi, work);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mcfqspi->lock, flags);
+	while (!list_empty(&mcfqspi->msgq)) {
+		struct spi_message *msg;
+		struct spi_device *spi;
+		struct spi_transfer *xfer;
+		int status = 0;
+
+		msg = container_of(mcfqspi->msgq.next, struct spi_message,
+				   queue);
+
+		list_del_init(&mcfqspi->msgq);
+		spin_unlock_irqrestore(&mcfqspi->lock, flags);
+
+		spi = msg->spi;
+
+		list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+			bool cs_high = spi->mode & SPI_CS_HIGH;
+			u16 qmr = MCFQSPI_QMR_MSTR;
+
+			if (xfer->bits_per_word)
+				qmr |= xfer->bits_per_word << 10;
+			else
+				qmr |= spi->bits_per_word << 10;
+			if (spi->mode & SPI_CPHA)
+				qmr |= MCFQSPI_QMR_CPHA;
+			if (spi->mode & SPI_CPOL)
+				qmr |= MCFQSPI_QMR_CPOL;
+			if (xfer->speed_hz)
+				qmr |= mcfqspi_qmr_baud(xfer->speed_hz);
+			else
+				qmr |= mcfqspi_qmr_baud(spi->max_speed_hz);
+			mcfqspi_wr_qmr(mcfqspi, qmr);
+
+			mcfqspi_cs_select(mcfqspi, spi->chip_select, cs_high);
+
+			mcfqspi_wr_qir(mcfqspi, MCFQSPI_QIR_SPIFE);
+			if ((xfer->bits_per_word ? xfer->bits_per_word :
+						spi->bits_per_word) == 8)
+				mcfqspi_transfer_msg8(mcfqspi, xfer->len,
+						      xfer->tx_buf,
+						      xfer->rx_buf);
+			else
+				mcfqspi_transfer_msg16(mcfqspi, xfer->len / 2,
+						       xfer->tx_buf,
+						       xfer->rx_buf);
+			mcfqspi_wr_qir(mcfqspi, 0);
+
+			if (xfer->delay_usecs)
+				udelay(xfer->delay_usecs);
+			if (xfer->cs_change) {
+				if (!list_is_last(&xfer->transfer_list,
+						  &msg->transfers))
+					mcfqspi_cs_deselect(mcfqspi,
+							    spi->chip_select,
+							    cs_high);
+			} else {
+				if (list_is_last(&xfer->transfer_list,
+						 &msg->transfers))
+					mcfqspi_cs_deselect(mcfqspi,
+							    spi->chip_select,
+							    cs_high);
+			}
+			msg->actual_length += xfer->len;
+		}
+		msg->status = status;
+		msg->complete(msg->context);
+
+		spin_lock_irqsave(&mcfqspi->lock, flags);
+	}
+	spin_unlock_irqrestore(&mcfqspi->lock, flags);
+}
+
+static int mcfqspi_transfer(struct spi_device *spi, struct spi_message *msg)
+{
+	struct mcfqspi *mcfqspi;
+	struct spi_transfer *xfer;
+	unsigned long flags;
+
+	mcfqspi = spi_master_get_devdata(spi->master);
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (xfer->bits_per_word && ((xfer->bits_per_word < 8)
+					|| (xfer->bits_per_word > 16))) {
+			dev_dbg(&spi->dev,
+				"%d bits per word is not supported\n",
+				xfer->bits_per_word);
+			goto fail;
+		}
+		if (xfer->speed_hz) {
+			u32 real_speed = MCFQSPI_BUSCLK /
+				mcfqspi_qmr_baud(xfer->speed_hz);
+			if (real_speed != xfer->speed_hz)
+				dev_dbg(&spi->dev,
+					"using speed %d instead of %d\n",
+					real_speed, xfer->speed_hz);
+		}
+	}
+	msg->status = -EINPROGRESS;
+	msg->actual_length = 0;
+
+	spin_lock_irqsave(&mcfqspi->lock, flags);
+	list_add_tail(&msg->queue, &mcfqspi->msgq);
+	queue_work(mcfqspi->workq, &mcfqspi->work);
+	spin_unlock_irqrestore(&mcfqspi->lock, flags);
+
+	return 0;
+fail:
+	msg->status = -EINVAL;
+	return -EINVAL;
+}
+
+static int mcfqspi_setup(struct spi_device *spi)
+{
+	if ((spi->bits_per_word < 8) || (spi->bits_per_word > 16)) {
+		dev_dbg(&spi->dev, "%d bits per word is not supported\n",
+			spi->bits_per_word);
+		return -EINVAL;
+	}
+	if (spi->chip_select >= spi->master->num_chipselect) {
+		dev_dbg(&spi->dev, "%d chip select is out of range\n",
+			spi->chip_select);
+		return -EINVAL;
+	}
+
+	mcfqspi_cs_deselect(spi_master_get_devdata(spi->master),
+			    spi->chip_select, spi->mode & SPI_CS_HIGH);
+
+	dev_dbg(&spi->dev,
+			"bits per word %d, chip select %d, speed %d KHz\n",
+			spi->bits_per_word, spi->chip_select,
+			(MCFQSPI_BUSCLK / mcfqspi_qmr_baud(spi->max_speed_hz))
+			/ 1000);
+
+	return 0;
+}
+
+static int __devinit mcfqspi_probe(struct platform_device *pdev)
+{
+	struct spi_master *master;
+	struct mcfqspi *mcfqspi;
+	struct resource *res;
+	struct mcfqspi_platform_data *pdata;
+	int status;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*mcfqspi));
+	if (master == NULL) {
+		dev_dbg(&pdev->dev, "spi_alloc_master failed\n");
+		return -ENOMEM;
+	}
+
+	mcfqspi = spi_master_get_devdata(master);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_dbg(&pdev->dev, "platform_get_resource failed\n");
+		status = -ENXIO;
+		goto fail0;
+	}
+
+	if (!request_mem_region(res->start, resource_size(res), pdev->name)) {
+		dev_dbg(&pdev->dev, "request_mem_region failed\n");
+		status = -EBUSY;
+		goto fail0;
+	}
+
+	mcfqspi->iobase = ioremap(res->start, resource_size(res));
+	if (!mcfqspi->iobase) {
+		dev_dbg(&pdev->dev, "ioremap failed\n");
+		status = -ENOMEM;
+		goto fail1;
+	}
+
+	mcfqspi->irq = platform_get_irq(pdev, 0);
+	if (mcfqspi->irq < 0) {
+		dev_dbg(&pdev->dev, "platform_get_irq failed\n");
+		status = -ENXIO;
+		goto fail2;
+	}
+
+	status = request_irq(mcfqspi->irq, mcfqspi_irq_handler, IRQF_DISABLED,
+			     pdev->name, mcfqspi);
+	if (status) {
+		dev_dbg(&pdev->dev, "request_irq failed\n");
+		goto fail2;
+	}
+
+	mcfqspi->clk = clk_get(&pdev->dev, "qspi_clk");
+	if (IS_ERR(mcfqspi->clk)) {
+		dev_dbg(&pdev->dev, "clk_get failed\n");
+		status = PTR_ERR(mcfqspi->clk);
+		goto fail3;
+	}
+	clk_enable(mcfqspi->clk);
+
+	mcfqspi->workq = create_singlethread_workqueue(dev_name(master->dev.parent));
+	if (!mcfqspi->workq) {
+		dev_dbg(&pdev->dev, "create_workqueue failed\n");
+		status = -ENOMEM;
+		goto fail4;
+	}
+	INIT_WORK(&mcfqspi->work, mcfqspi_work);
+	spin_lock_init(&mcfqspi->lock);
+	INIT_LIST_HEAD(&mcfqspi->msgq);
+	init_waitqueue_head(&mcfqspi->waitq);
+
+	pdata = pdev->dev.platform_data;
+	if (!pdata) {
+		dev_dbg(&pdev->dev, "platform data is missing\n");
+		goto fail5;
+	}
+	master->bus_num = pdata->bus_num;
+	master->num_chipselect = pdata->num_chipselect;
+
+	mcfqspi->cs_control = pdata->cs_control;
+	status = mcfqspi_cs_setup(mcfqspi);
+	if (status) {
+		dev_dbg(&pdev->dev, "error initializing cs_control\n");
+		goto fail5;
+	}
+
+	master->mode_bits = SPI_CS_HIGH | SPI_CPOL | SPI_CPHA;
+	master->setup = mcfqspi_setup;
+	master->transfer = mcfqspi_transfer;
+
+	platform_set_drvdata(pdev, master);
+
+	status = spi_register_master(master);
+	if (status) {
+		dev_dbg(&pdev->dev, "spi_register_master failed\n");
+		goto fail6;
+	}
+	dev_info(&pdev->dev, "Coldfire QSPI bus driver\n");
+
+	return 0;
+
+fail6:
+	mcfqspi_cs_teardown(mcfqspi);
+fail5:
+	destroy_workqueue(mcfqspi->workq);
+fail4:
+	clk_disable(mcfqspi->clk);
+	clk_put(mcfqspi->clk);
+fail3:
+	free_irq(mcfqspi->irq, mcfqspi);
+fail2:
+	iounmap(mcfqspi->iobase);
+fail1:
+	release_mem_region(res->start, resource_size(res));
+fail0:
+	spi_master_put(master);
+
+	dev_dbg(&pdev->dev, "Coldfire QSPI probe failed\n");
+
+	return status;
+}
+
+static int __devexit mcfqspi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct mcfqspi *mcfqspi = spi_master_get_devdata(master);
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	/* disable the hardware (set the baud rate to 0) */
+	mcfqspi_wr_qmr(mcfqspi, MCFQSPI_QMR_MSTR);
+
+	platform_set_drvdata(pdev, NULL);
+	mcfqspi_cs_teardown(mcfqspi);
+	destroy_workqueue(mcfqspi->workq);
+	clk_disable(mcfqspi->clk);
+	clk_put(mcfqspi->clk);
+	free_irq(mcfqspi->irq, mcfqspi);
+	iounmap(mcfqspi->iobase);
+	release_mem_region(res->start, resource_size(res));
+	spi_unregister_master(master);
+	spi_master_put(master);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+
+static int mcfqspi_suspend(struct device *dev)
+{
+	struct mcfqspi *mcfqspi = platform_get_drvdata(to_platform_device(dev));
+
+	clk_disable(mcfqspi->clk);
+
+	return 0;
+}
+
+static int mcfqspi_resume(struct device *dev)
+{
+	struct mcfqspi *mcfqspi = platform_get_drvdata(to_platform_device(dev));
+
+	clk_enable(mcfqspi->clk);
+
+	return 0;
+}
+
+static struct dev_pm_ops mcfqspi_dev_pm_ops = {
+	.suspend	= mcfqspi_suspend,
+	.resume		= mcfqspi_resume,
+};
+
+#define	MCFQSPI_DEV_PM_OPS	(&mcfqspi_dev_pm_ops)
+#else
+#define	MCFQSPI_DEV_PM_OPS	NULL
+#endif
+
+static struct platform_driver mcfqspi_driver = {
+	.driver.name	= DRIVER_NAME,
+	.driver.owner	= THIS_MODULE,
+	.driver.pm	= MCFQSPI_DEV_PM_OPS,
+	.remove		= __devexit_p(mcfqspi_remove),
+};
+
+static int __init mcfqspi_init(void)
+{
+	return platform_driver_probe(&mcfqspi_driver, mcfqspi_probe);
+}
+module_init(mcfqspi_init);
+
+static void __exit mcfqspi_exit(void)
+{
+	platform_driver_unregister(&mcfqspi_driver);
+}
+module_exit(mcfqspi_exit);
+
+MODULE_AUTHOR("Steven King <sfking@fdwdc.com>");
+MODULE_DESCRIPTION("Coldfire QSPI Controller Driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/davinci_spi.c b/drivers/spi/davinci_spi.c
new file mode 100644
index 00000000000..225ab60b02c
--- /dev/null
+++ b/drivers/spi/davinci_spi.c
@@ -0,0 +1,1255 @@
+/*
+ * Copyright (C) 2009 Texas Instruments.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi_bitbang.h>
+
+#include <mach/spi.h>
+#include <mach/edma.h>
+
+#define SPI_NO_RESOURCE		((resource_size_t)-1)
+
+#define SPI_MAX_CHIPSELECT	2
+
+#define CS_DEFAULT	0xFF
+
+#define SPI_BUFSIZ	(SMP_CACHE_BYTES + 1)
+#define DAVINCI_DMA_DATA_TYPE_S8	0x01
+#define DAVINCI_DMA_DATA_TYPE_S16	0x02
+#define DAVINCI_DMA_DATA_TYPE_S32	0x04
+
+#define SPIFMT_PHASE_MASK	BIT(16)
+#define SPIFMT_POLARITY_MASK	BIT(17)
+#define SPIFMT_DISTIMER_MASK	BIT(18)
+#define SPIFMT_SHIFTDIR_MASK	BIT(20)
+#define SPIFMT_WAITENA_MASK	BIT(21)
+#define SPIFMT_PARITYENA_MASK	BIT(22)
+#define SPIFMT_ODD_PARITY_MASK	BIT(23)
+#define SPIFMT_WDELAY_MASK	0x3f000000u
+#define SPIFMT_WDELAY_SHIFT	24
+#define SPIFMT_CHARLEN_MASK	0x0000001Fu
+
+/* SPIGCR1 */
+#define SPIGCR1_SPIENA_MASK	0x01000000u
+
+/* SPIPC0 */
+#define SPIPC0_DIFUN_MASK	BIT(11)		/* MISO */
+#define SPIPC0_DOFUN_MASK	BIT(10)		/* MOSI */
+#define SPIPC0_CLKFUN_MASK	BIT(9)		/* CLK */
+#define SPIPC0_SPIENA_MASK	BIT(8)		/* nREADY */
+#define SPIPC0_EN1FUN_MASK	BIT(1)
+#define SPIPC0_EN0FUN_MASK	BIT(0)
+
+#define SPIINT_MASKALL		0x0101035F
+#define SPI_INTLVL_1		0x000001FFu
+#define SPI_INTLVL_0		0x00000000u
+
+/* SPIDAT1 */
+#define SPIDAT1_CSHOLD_SHIFT	28
+#define SPIDAT1_CSNR_SHIFT	16
+#define SPIGCR1_CLKMOD_MASK	BIT(1)
+#define SPIGCR1_MASTER_MASK     BIT(0)
+#define SPIGCR1_LOOPBACK_MASK	BIT(16)
+
+/* SPIBUF */
+#define SPIBUF_TXFULL_MASK	BIT(29)
+#define SPIBUF_RXEMPTY_MASK	BIT(31)
+
+/* Error Masks */
+#define SPIFLG_DLEN_ERR_MASK		BIT(0)
+#define SPIFLG_TIMEOUT_MASK		BIT(1)
+#define SPIFLG_PARERR_MASK		BIT(2)
+#define SPIFLG_DESYNC_MASK		BIT(3)
+#define SPIFLG_BITERR_MASK		BIT(4)
+#define SPIFLG_OVRRUN_MASK		BIT(6)
+#define SPIFLG_RX_INTR_MASK		BIT(8)
+#define SPIFLG_TX_INTR_MASK		BIT(9)
+#define SPIFLG_BUF_INIT_ACTIVE_MASK	BIT(24)
+#define SPIFLG_MASK			(SPIFLG_DLEN_ERR_MASK \
+				| SPIFLG_TIMEOUT_MASK | SPIFLG_PARERR_MASK \
+				| SPIFLG_DESYNC_MASK | SPIFLG_BITERR_MASK \
+				| SPIFLG_OVRRUN_MASK | SPIFLG_RX_INTR_MASK \
+				| SPIFLG_TX_INTR_MASK \
+				| SPIFLG_BUF_INIT_ACTIVE_MASK)
+
+#define SPIINT_DLEN_ERR_INTR	BIT(0)
+#define SPIINT_TIMEOUT_INTR	BIT(1)
+#define SPIINT_PARERR_INTR	BIT(2)
+#define SPIINT_DESYNC_INTR	BIT(3)
+#define SPIINT_BITERR_INTR	BIT(4)
+#define SPIINT_OVRRUN_INTR	BIT(6)
+#define SPIINT_RX_INTR		BIT(8)
+#define SPIINT_TX_INTR		BIT(9)
+#define SPIINT_DMA_REQ_EN	BIT(16)
+#define SPIINT_ENABLE_HIGHZ	BIT(24)
+
+#define SPI_T2CDELAY_SHIFT	16
+#define SPI_C2TDELAY_SHIFT	24
+
+/* SPI Controller registers */
+#define SPIGCR0		0x00
+#define SPIGCR1		0x04
+#define SPIINT		0x08
+#define SPILVL		0x0c
+#define SPIFLG		0x10
+#define SPIPC0		0x14
+#define SPIPC1		0x18
+#define SPIPC2		0x1c
+#define SPIPC3		0x20
+#define SPIPC4		0x24
+#define SPIPC5		0x28
+#define SPIPC6		0x2c
+#define SPIPC7		0x30
+#define SPIPC8		0x34
+#define SPIDAT0		0x38
+#define SPIDAT1		0x3c
+#define SPIBUF		0x40
+#define SPIEMU		0x44
+#define SPIDELAY	0x48
+#define SPIDEF		0x4c
+#define SPIFMT0		0x50
+#define SPIFMT1		0x54
+#define SPIFMT2		0x58
+#define SPIFMT3		0x5c
+#define TGINTVEC0	0x60
+#define TGINTVEC1	0x64
+
+struct davinci_spi_slave {
+	u32	cmd_to_write;
+	u32	clk_ctrl_to_write;
+	u32	bytes_per_word;
+	u8	active_cs;
+};
+
+/* We have 2 DMA channels per CS, one for RX and one for TX */
+struct davinci_spi_dma {
+	int			dma_tx_channel;
+	int			dma_rx_channel;
+	int			dma_tx_sync_dev;
+	int			dma_rx_sync_dev;
+	enum dma_event_q	eventq;
+
+	struct completion	dma_tx_completion;
+	struct completion	dma_rx_completion;
+};
+
+/* SPI Controller driver's private data. */
+struct davinci_spi {
+	struct spi_bitbang	bitbang;
+	struct clk		*clk;
+
+	u8			version;
+	resource_size_t		pbase;
+	void __iomem		*base;
+	size_t			region_size;
+	u32			irq;
+	struct completion	done;
+
+	const void		*tx;
+	void			*rx;
+	u8			*tmp_buf;
+	int			count;
+	struct davinci_spi_dma	*dma_channels;
+	struct			davinci_spi_platform_data *pdata;
+
+	void			(*get_rx)(u32 rx_data, struct davinci_spi *);
+	u32			(*get_tx)(struct davinci_spi *);
+
+	struct davinci_spi_slave slave[SPI_MAX_CHIPSELECT];
+};
+
+static unsigned use_dma;
+
+static void davinci_spi_rx_buf_u8(u32 data, struct davinci_spi *davinci_spi)
+{
+	u8 *rx = davinci_spi->rx;
+
+	*rx++ = (u8)data;
+	davinci_spi->rx = rx;
+}
+
+static void davinci_spi_rx_buf_u16(u32 data, struct davinci_spi *davinci_spi)
+{
+	u16 *rx = davinci_spi->rx;
+
+	*rx++ = (u16)data;
+	davinci_spi->rx = rx;
+}
+
+static u32 davinci_spi_tx_buf_u8(struct davinci_spi *davinci_spi)
+{
+	u32 data;
+	const u8 *tx = davinci_spi->tx;
+
+	data = *tx++;
+	davinci_spi->tx = tx;
+	return data;
+}
+
+static u32 davinci_spi_tx_buf_u16(struct davinci_spi *davinci_spi)
+{
+	u32 data;
+	const u16 *tx = davinci_spi->tx;
+
+	data = *tx++;
+	davinci_spi->tx = tx;
+	return data;
+}
+
+static inline void set_io_bits(void __iomem *addr, u32 bits)
+{
+	u32 v = ioread32(addr);
+
+	v |= bits;
+	iowrite32(v, addr);
+}
+
+static inline void clear_io_bits(void __iomem *addr, u32 bits)
+{
+	u32 v = ioread32(addr);
+
+	v &= ~bits;
+	iowrite32(v, addr);
+}
+
+static inline void set_fmt_bits(void __iomem *addr, u32 bits, int cs_num)
+{
+	set_io_bits(addr + SPIFMT0 + (0x4 * cs_num), bits);
+}
+
+static inline void clear_fmt_bits(void __iomem *addr, u32 bits, int cs_num)
+{
+	clear_io_bits(addr + SPIFMT0 + (0x4 * cs_num), bits);
+}
+
+static void davinci_spi_set_dma_req(const struct spi_device *spi, int enable)
+{
+	struct davinci_spi *davinci_spi = spi_master_get_devdata(spi->master);
+
+	if (enable)
+		set_io_bits(davinci_spi->base + SPIINT, SPIINT_DMA_REQ_EN);
+	else
+		clear_io_bits(davinci_spi->base + SPIINT, SPIINT_DMA_REQ_EN);
+}
+
+/*
+ * Interface to control the chip select signal
+ */
+static void davinci_spi_chipselect(struct spi_device *spi, int value)
+{
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_platform_data *pdata;
+	u32 data1_reg_val = 0;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	pdata = davinci_spi->pdata;
+
+	/*
+	 * Board specific chip select logic decides the polarity and cs
+	 * line for the controller
+	 */
+	if (value == BITBANG_CS_INACTIVE) {
+		set_io_bits(davinci_spi->base + SPIDEF, CS_DEFAULT);
+
+		data1_reg_val |= CS_DEFAULT << SPIDAT1_CSNR_SHIFT;
+		iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
+
+		while ((ioread32(davinci_spi->base + SPIBUF)
+					& SPIBUF_RXEMPTY_MASK) == 0)
+			cpu_relax();
+	}
+}
+
+/**
+ * davinci_spi_setup_transfer - This functions will determine transfer method
+ * @spi: spi device on which data transfer to be done
+ * @t: spi transfer in which transfer info is filled
+ *
+ * This function determines data transfer method (8/16/32 bit transfer).
+ * It will also set the SPI Clock Control register according to
+ * SPI slave device freq.
+ */
+static int davinci_spi_setup_transfer(struct spi_device *spi,
+		struct spi_transfer *t)
+{
+
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_platform_data *pdata;
+	u8 bits_per_word = 0;
+	u32 hz = 0, prescale;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	pdata = davinci_spi->pdata;
+
+	if (t) {
+		bits_per_word = t->bits_per_word;
+		hz = t->speed_hz;
+	}
+
+	/* if bits_per_word is not set then set it default */
+	if (!bits_per_word)
+		bits_per_word = spi->bits_per_word;
+
+	/*
+	 * Assign function pointer to appropriate transfer method
+	 * 8bit, 16bit or 32bit transfer
+	 */
+	if (bits_per_word <= 8 && bits_per_word >= 2) {
+		davinci_spi->get_rx = davinci_spi_rx_buf_u8;
+		davinci_spi->get_tx = davinci_spi_tx_buf_u8;
+		davinci_spi->slave[spi->chip_select].bytes_per_word = 1;
+	} else if (bits_per_word <= 16 && bits_per_word >= 2) {
+		davinci_spi->get_rx = davinci_spi_rx_buf_u16;
+		davinci_spi->get_tx = davinci_spi_tx_buf_u16;
+		davinci_spi->slave[spi->chip_select].bytes_per_word = 2;
+	} else
+		return -EINVAL;
+
+	if (!hz)
+		hz = spi->max_speed_hz;
+
+	clear_fmt_bits(davinci_spi->base, SPIFMT_CHARLEN_MASK,
+			spi->chip_select);
+	set_fmt_bits(davinci_spi->base, bits_per_word & 0x1f,
+			spi->chip_select);
+
+	prescale = ((clk_get_rate(davinci_spi->clk) / hz) - 1) & 0xff;
+
+	clear_fmt_bits(davinci_spi->base, 0x0000ff00, spi->chip_select);
+	set_fmt_bits(davinci_spi->base, prescale << 8, spi->chip_select);
+
+	return 0;
+}
+
+static void davinci_spi_dma_rx_callback(unsigned lch, u16 ch_status, void *data)
+{
+	struct spi_device *spi = (struct spi_device *)data;
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_dma *davinci_spi_dma;
+	struct davinci_spi_platform_data *pdata;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	davinci_spi_dma = &(davinci_spi->dma_channels[spi->chip_select]);
+	pdata = davinci_spi->pdata;
+
+	if (ch_status == DMA_COMPLETE)
+		edma_stop(davinci_spi_dma->dma_rx_channel);
+	else
+		edma_clean_channel(davinci_spi_dma->dma_rx_channel);
+
+	complete(&davinci_spi_dma->dma_rx_completion);
+	/* We must disable the DMA RX request */
+	davinci_spi_set_dma_req(spi, 0);
+}
+
+static void davinci_spi_dma_tx_callback(unsigned lch, u16 ch_status, void *data)
+{
+	struct spi_device *spi = (struct spi_device *)data;
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_dma *davinci_spi_dma;
+	struct davinci_spi_platform_data *pdata;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	davinci_spi_dma = &(davinci_spi->dma_channels[spi->chip_select]);
+	pdata = davinci_spi->pdata;
+
+	if (ch_status == DMA_COMPLETE)
+		edma_stop(davinci_spi_dma->dma_tx_channel);
+	else
+		edma_clean_channel(davinci_spi_dma->dma_tx_channel);
+
+	complete(&davinci_spi_dma->dma_tx_completion);
+	/* We must disable the DMA TX request */
+	davinci_spi_set_dma_req(spi, 0);
+}
+
+static int davinci_spi_request_dma(struct spi_device *spi)
+{
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_dma *davinci_spi_dma;
+	struct davinci_spi_platform_data *pdata;
+	struct device *sdev;
+	int r;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
+	pdata = davinci_spi->pdata;
+	sdev = davinci_spi->bitbang.master->dev.parent;
+
+	r = edma_alloc_channel(davinci_spi_dma->dma_rx_sync_dev,
+				davinci_spi_dma_rx_callback, spi,
+				davinci_spi_dma->eventq);
+	if (r < 0) {
+		dev_dbg(sdev, "Unable to request DMA channel for SPI RX\n");
+		return -EAGAIN;
+	}
+	davinci_spi_dma->dma_rx_channel = r;
+	r = edma_alloc_channel(davinci_spi_dma->dma_tx_sync_dev,
+				davinci_spi_dma_tx_callback, spi,
+				davinci_spi_dma->eventq);
+	if (r < 0) {
+		edma_free_channel(davinci_spi_dma->dma_rx_channel);
+		davinci_spi_dma->dma_rx_channel = -1;
+		dev_dbg(sdev, "Unable to request DMA channel for SPI TX\n");
+		return -EAGAIN;
+	}
+	davinci_spi_dma->dma_tx_channel = r;
+
+	return 0;
+}
+
+/**
+ * davinci_spi_setup - This functions will set default transfer method
+ * @spi: spi device on which data transfer to be done
+ *
+ * This functions sets the default transfer method.
+ */
+
+static int davinci_spi_setup(struct spi_device *spi)
+{
+	int retval;
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_dma *davinci_spi_dma;
+	struct device *sdev;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	sdev = davinci_spi->bitbang.master->dev.parent;
+
+	/* if bits per word length is zero then set it default 8 */
+	if (!spi->bits_per_word)
+		spi->bits_per_word = 8;
+
+	davinci_spi->slave[spi->chip_select].cmd_to_write = 0;
+
+	if (use_dma && davinci_spi->dma_channels) {
+		davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
+
+		if ((davinci_spi_dma->dma_rx_channel == -1)
+				|| (davinci_spi_dma->dma_tx_channel == -1)) {
+			retval = davinci_spi_request_dma(spi);
+			if (retval < 0)
+				return retval;
+		}
+	}
+
+	/*
+	 * SPI in DaVinci and DA8xx operate between
+	 * 600 KHz and 50 MHz
+	 */
+	if (spi->max_speed_hz < 600000 || spi->max_speed_hz > 50000000) {
+		dev_dbg(sdev, "Operating frequency is not in acceptable "
+				"range\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Set up SPIFMTn register, unique to this chipselect.
+	 *
+	 * NOTE: we could do all of these with one write.  Also, some
+	 * of the "version 2" features are found in chips that don't
+	 * support all of them...
+	 */
+	if (spi->mode & SPI_LSB_FIRST)
+		set_fmt_bits(davinci_spi->base, SPIFMT_SHIFTDIR_MASK,
+				spi->chip_select);
+	else
+		clear_fmt_bits(davinci_spi->base, SPIFMT_SHIFTDIR_MASK,
+				spi->chip_select);
+
+	if (spi->mode & SPI_CPOL)
+		set_fmt_bits(davinci_spi->base, SPIFMT_POLARITY_MASK,
+				spi->chip_select);
+	else
+		clear_fmt_bits(davinci_spi->base, SPIFMT_POLARITY_MASK,
+				spi->chip_select);
+
+	if (!(spi->mode & SPI_CPHA))
+		set_fmt_bits(davinci_spi->base, SPIFMT_PHASE_MASK,
+				spi->chip_select);
+	else
+		clear_fmt_bits(davinci_spi->base, SPIFMT_PHASE_MASK,
+				spi->chip_select);
+
+	/*
+	 * Version 1 hardware supports two basic SPI modes:
+	 *  - Standard SPI mode uses 4 pins, with chipselect
+	 *  - 3 pin SPI is a 4 pin variant without CS (SPI_NO_CS)
+	 *	(distinct from SPI_3WIRE, with just one data wire;
+	 *	or similar variants without MOSI or without MISO)
+	 *
+	 * Version 2 hardware supports an optional handshaking signal,
+	 * so it can support two more modes:
+	 *  - 5 pin SPI variant is standard SPI plus SPI_READY
+	 *  - 4 pin with enable is (SPI_READY | SPI_NO_CS)
+	 */
+
+	if (davinci_spi->version == SPI_VERSION_2) {
+		clear_fmt_bits(davinci_spi->base, SPIFMT_WDELAY_MASK,
+				spi->chip_select);
+		set_fmt_bits(davinci_spi->base,
+				(davinci_spi->pdata->wdelay
+						<< SPIFMT_WDELAY_SHIFT)
+					& SPIFMT_WDELAY_MASK,
+				spi->chip_select);
+
+		if (davinci_spi->pdata->odd_parity)
+			set_fmt_bits(davinci_spi->base,
+					SPIFMT_ODD_PARITY_MASK,
+					spi->chip_select);
+		else
+			clear_fmt_bits(davinci_spi->base,
+					SPIFMT_ODD_PARITY_MASK,
+					spi->chip_select);
+
+		if (davinci_spi->pdata->parity_enable)
+			set_fmt_bits(davinci_spi->base,
+					SPIFMT_PARITYENA_MASK,
+					spi->chip_select);
+		else
+			clear_fmt_bits(davinci_spi->base,
+					SPIFMT_PARITYENA_MASK,
+					spi->chip_select);
+
+		if (davinci_spi->pdata->wait_enable)
+			set_fmt_bits(davinci_spi->base,
+					SPIFMT_WAITENA_MASK,
+					spi->chip_select);
+		else
+			clear_fmt_bits(davinci_spi->base,
+					SPIFMT_WAITENA_MASK,
+					spi->chip_select);
+
+		if (davinci_spi->pdata->timer_disable)
+			set_fmt_bits(davinci_spi->base,
+					SPIFMT_DISTIMER_MASK,
+					spi->chip_select);
+		else
+			clear_fmt_bits(davinci_spi->base,
+					SPIFMT_DISTIMER_MASK,
+					spi->chip_select);
+	}
+
+	retval = davinci_spi_setup_transfer(spi, NULL);
+
+	return retval;
+}
+
+static void davinci_spi_cleanup(struct spi_device *spi)
+{
+	struct davinci_spi *davinci_spi = spi_master_get_devdata(spi->master);
+	struct davinci_spi_dma *davinci_spi_dma;
+
+	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
+
+	if (use_dma && davinci_spi->dma_channels) {
+		davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
+
+		if ((davinci_spi_dma->dma_rx_channel != -1)
+				&& (davinci_spi_dma->dma_tx_channel != -1)) {
+			edma_free_channel(davinci_spi_dma->dma_tx_channel);
+			edma_free_channel(davinci_spi_dma->dma_rx_channel);
+		}
+	}
+}
+
+static int davinci_spi_bufs_prep(struct spi_device *spi,
+				 struct davinci_spi *davinci_spi)
+{
+	int op_mode = 0;
+
+	/*
+	 * REVISIT  unless devices disagree about SPI_LOOP or
+	 * SPI_READY (SPI_NO_CS only allows one device!), this
+	 * should not need to be done before each message...
+	 * optimize for both flags staying cleared.
+	 */
+
+	op_mode = SPIPC0_DIFUN_MASK
+		| SPIPC0_DOFUN_MASK
+		| SPIPC0_CLKFUN_MASK;
+	if (!(spi->mode & SPI_NO_CS))
+		op_mode |= 1 << spi->chip_select;
+	if (spi->mode & SPI_READY)
+		op_mode |= SPIPC0_SPIENA_MASK;
+
+	iowrite32(op_mode, davinci_spi->base + SPIPC0);
+
+	if (spi->mode & SPI_LOOP)
+		set_io_bits(davinci_spi->base + SPIGCR1,
+				SPIGCR1_LOOPBACK_MASK);
+	else
+		clear_io_bits(davinci_spi->base + SPIGCR1,
+				SPIGCR1_LOOPBACK_MASK);
+
+	return 0;
+}
+
+static int davinci_spi_check_error(struct davinci_spi *davinci_spi,
+				   int int_status)
+{
+	struct device *sdev = davinci_spi->bitbang.master->dev.parent;
+
+	if (int_status & SPIFLG_TIMEOUT_MASK) {
+		dev_dbg(sdev, "SPI Time-out Error\n");
+		return -ETIMEDOUT;
+	}
+	if (int_status & SPIFLG_DESYNC_MASK) {
+		dev_dbg(sdev, "SPI Desynchronization Error\n");
+		return -EIO;
+	}
+	if (int_status & SPIFLG_BITERR_MASK) {
+		dev_dbg(sdev, "SPI Bit error\n");
+		return -EIO;
+	}
+
+	if (davinci_spi->version == SPI_VERSION_2) {
+		if (int_status & SPIFLG_DLEN_ERR_MASK) {
+			dev_dbg(sdev, "SPI Data Length Error\n");
+			return -EIO;
+		}
+		if (int_status & SPIFLG_PARERR_MASK) {
+			dev_dbg(sdev, "SPI Parity Error\n");
+			return -EIO;
+		}
+		if (int_status & SPIFLG_OVRRUN_MASK) {
+			dev_dbg(sdev, "SPI Data Overrun error\n");
+			return -EIO;
+		}
+		if (int_status & SPIFLG_TX_INTR_MASK) {
+			dev_dbg(sdev, "SPI TX intr bit set\n");
+			return -EIO;
+		}
+		if (int_status & SPIFLG_BUF_INIT_ACTIVE_MASK) {
+			dev_dbg(sdev, "SPI Buffer Init Active\n");
+			return -EBUSY;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * davinci_spi_bufs - functions which will handle transfer data
+ * @spi: spi device on which data transfer to be done
+ * @t: spi transfer in which transfer info is filled
+ *
+ * This function will put data to be transferred into data register
+ * of SPI controller and then wait until the completion will be marked
+ * by the IRQ Handler.
+ */
+static int davinci_spi_bufs_pio(struct spi_device *spi, struct spi_transfer *t)
+{
+	struct davinci_spi *davinci_spi;
+	int int_status, count, ret;
+	u8 conv, tmp;
+	u32 tx_data, data1_reg_val;
+	u32 buf_val, flg_val;
+	struct davinci_spi_platform_data *pdata;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	pdata = davinci_spi->pdata;
+
+	davinci_spi->tx = t->tx_buf;
+	davinci_spi->rx = t->rx_buf;
+
+	/* convert len to words based on bits_per_word */
+	conv = davinci_spi->slave[spi->chip_select].bytes_per_word;
+	davinci_spi->count = t->len / conv;
+
+	INIT_COMPLETION(davinci_spi->done);
+
+	ret = davinci_spi_bufs_prep(spi, davinci_spi);
+	if (ret)
+		return ret;
+
+	/* Enable SPI */
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
+
+	iowrite32(0 | (pdata->c2tdelay << SPI_C2TDELAY_SHIFT) |
+			(pdata->t2cdelay << SPI_T2CDELAY_SHIFT),
+			davinci_spi->base + SPIDELAY);
+
+	count = davinci_spi->count;
+	data1_reg_val = pdata->cs_hold << SPIDAT1_CSHOLD_SHIFT;
+	tmp = ~(0x1 << spi->chip_select);
+
+	clear_io_bits(davinci_spi->base + SPIDEF, ~tmp);
+
+	data1_reg_val |= tmp << SPIDAT1_CSNR_SHIFT;
+
+	while ((ioread32(davinci_spi->base + SPIBUF)
+				& SPIBUF_RXEMPTY_MASK) == 0)
+		cpu_relax();
+
+	/* Determine the command to execute READ or WRITE */
+	if (t->tx_buf) {
+		clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
+
+		while (1) {
+			tx_data = davinci_spi->get_tx(davinci_spi);
+
+			data1_reg_val &= ~(0xFFFF);
+			data1_reg_val |= (0xFFFF & tx_data);
+
+			buf_val = ioread32(davinci_spi->base + SPIBUF);
+			if ((buf_val & SPIBUF_TXFULL_MASK) == 0) {
+				iowrite32(data1_reg_val,
+						davinci_spi->base + SPIDAT1);
+
+				count--;
+			}
+			while (ioread32(davinci_spi->base + SPIBUF)
+					& SPIBUF_RXEMPTY_MASK)
+				cpu_relax();
+
+			/* getting the returned byte */
+			if (t->rx_buf) {
+				buf_val = ioread32(davinci_spi->base + SPIBUF);
+				davinci_spi->get_rx(buf_val, davinci_spi);
+			}
+			if (count <= 0)
+				break;
+		}
+	} else {
+		if (pdata->poll_mode) {
+			while (1) {
+				/* keeps the serial clock going */
+				if ((ioread32(davinci_spi->base + SPIBUF)
+						& SPIBUF_TXFULL_MASK) == 0)
+					iowrite32(data1_reg_val,
+						davinci_spi->base + SPIDAT1);
+
+				while (ioread32(davinci_spi->base + SPIBUF) &
+						SPIBUF_RXEMPTY_MASK)
+					cpu_relax();
+
+				flg_val = ioread32(davinci_spi->base + SPIFLG);
+				buf_val = ioread32(davinci_spi->base + SPIBUF);
+
+				davinci_spi->get_rx(buf_val, davinci_spi);
+
+				count--;
+				if (count <= 0)
+					break;
+			}
+		} else {	/* Receive in Interrupt mode */
+			int i;
+
+			for (i = 0; i < davinci_spi->count; i++) {
+				set_io_bits(davinci_spi->base + SPIINT,
+						SPIINT_BITERR_INTR
+						| SPIINT_OVRRUN_INTR
+						| SPIINT_RX_INTR);
+
+				iowrite32(data1_reg_val,
+						davinci_spi->base + SPIDAT1);
+
+				while (ioread32(davinci_spi->base + SPIINT) &
+						SPIINT_RX_INTR)
+					cpu_relax();
+			}
+			iowrite32((data1_reg_val & 0x0ffcffff),
+					davinci_spi->base + SPIDAT1);
+		}
+	}
+
+	/*
+	 * Check for bit error, desync error,parity error,timeout error and
+	 * receive overflow errors
+	 */
+	int_status = ioread32(davinci_spi->base + SPIFLG);
+
+	ret = davinci_spi_check_error(davinci_spi, int_status);
+	if (ret != 0)
+		return ret;
+
+	/* SPI Framework maintains the count only in bytes so convert back */
+	davinci_spi->count *= conv;
+
+	return t->len;
+}
+
+#define DAVINCI_DMA_DATA_TYPE_S8	0x01
+#define DAVINCI_DMA_DATA_TYPE_S16	0x02
+#define DAVINCI_DMA_DATA_TYPE_S32	0x04
+
+static int davinci_spi_bufs_dma(struct spi_device *spi, struct spi_transfer *t)
+{
+	struct davinci_spi *davinci_spi;
+	int int_status = 0;
+	int count, temp_count;
+	u8 conv = 1;
+	u8 tmp;
+	u32 data1_reg_val;
+	struct davinci_spi_dma *davinci_spi_dma;
+	int word_len, data_type, ret;
+	unsigned long tx_reg, rx_reg;
+	struct davinci_spi_platform_data *pdata;
+	struct device *sdev;
+
+	davinci_spi = spi_master_get_devdata(spi->master);
+	pdata = davinci_spi->pdata;
+	sdev = davinci_spi->bitbang.master->dev.parent;
+
+	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
+
+	tx_reg = (unsigned long)davinci_spi->pbase + SPIDAT1;
+	rx_reg = (unsigned long)davinci_spi->pbase + SPIBUF;
+
+	davinci_spi->tx = t->tx_buf;
+	davinci_spi->rx = t->rx_buf;
+
+	/* convert len to words based on bits_per_word */
+	conv = davinci_spi->slave[spi->chip_select].bytes_per_word;
+	davinci_spi->count = t->len / conv;
+
+	INIT_COMPLETION(davinci_spi->done);
+
+	init_completion(&davinci_spi_dma->dma_rx_completion);
+	init_completion(&davinci_spi_dma->dma_tx_completion);
+
+	word_len = conv * 8;
+
+	if (word_len <= 8)
+		data_type = DAVINCI_DMA_DATA_TYPE_S8;
+	else if (word_len <= 16)
+		data_type = DAVINCI_DMA_DATA_TYPE_S16;
+	else if (word_len <= 32)
+		data_type = DAVINCI_DMA_DATA_TYPE_S32;
+	else
+		return -EINVAL;
+
+	ret = davinci_spi_bufs_prep(spi, davinci_spi);
+	if (ret)
+		return ret;
+
+	/* Put delay val if required */
+	iowrite32(0 | (pdata->c2tdelay << SPI_C2TDELAY_SHIFT) |
+			(pdata->t2cdelay << SPI_T2CDELAY_SHIFT),
+			davinci_spi->base + SPIDELAY);
+
+	count = davinci_spi->count;	/* the number of elements */
+	data1_reg_val = pdata->cs_hold << SPIDAT1_CSHOLD_SHIFT;
+
+	/* CS default = 0xFF */
+	tmp = ~(0x1 << spi->chip_select);
+
+	clear_io_bits(davinci_spi->base + SPIDEF, ~tmp);
+
+	data1_reg_val |= tmp << SPIDAT1_CSNR_SHIFT;
+
+	/* disable all interrupts for dma transfers */
+	clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
+	/* Disable SPI to write configuration bits in SPIDAT */
+	clear_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
+	iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
+	/* Enable SPI */
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
+
+	while ((ioread32(davinci_spi->base + SPIBUF)
+				& SPIBUF_RXEMPTY_MASK) == 0)
+		cpu_relax();
+
+
+	if (t->tx_buf) {
+		t->tx_dma = dma_map_single(&spi->dev, (void *)t->tx_buf, count,
+				DMA_TO_DEVICE);
+		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
+			dev_dbg(sdev, "Unable to DMA map a %d bytes"
+				" TX buffer\n", count);
+			return -ENOMEM;
+		}
+		temp_count = count;
+	} else {
+		/* We need TX clocking for RX transaction */
+		t->tx_dma = dma_map_single(&spi->dev,
+				(void *)davinci_spi->tmp_buf, count + 1,
+				DMA_TO_DEVICE);
+		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
+			dev_dbg(sdev, "Unable to DMA map a %d bytes"
+				" TX tmp buffer\n", count);
+			return -ENOMEM;
+		}
+		temp_count = count + 1;
+	}
+
+	edma_set_transfer_params(davinci_spi_dma->dma_tx_channel,
+					data_type, temp_count, 1, 0, ASYNC);
+	edma_set_dest(davinci_spi_dma->dma_tx_channel, tx_reg, INCR, W8BIT);
+	edma_set_src(davinci_spi_dma->dma_tx_channel, t->tx_dma, INCR, W8BIT);
+	edma_set_src_index(davinci_spi_dma->dma_tx_channel, data_type, 0);
+	edma_set_dest_index(davinci_spi_dma->dma_tx_channel, 0, 0);
+
+	if (t->rx_buf) {
+		/* initiate transaction */
+		iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
+
+		t->rx_dma = dma_map_single(&spi->dev, (void *)t->rx_buf, count,
+				DMA_FROM_DEVICE);
+		if (dma_mapping_error(&spi->dev, t->rx_dma)) {
+			dev_dbg(sdev, "Couldn't DMA map a %d bytes RX buffer\n",
+					count);
+			if (t->tx_buf != NULL)
+				dma_unmap_single(NULL, t->tx_dma,
+						 count, DMA_TO_DEVICE);
+			return -ENOMEM;
+		}
+		edma_set_transfer_params(davinci_spi_dma->dma_rx_channel,
+				data_type, count, 1, 0, ASYNC);
+		edma_set_src(davinci_spi_dma->dma_rx_channel,
+				rx_reg, INCR, W8BIT);
+		edma_set_dest(davinci_spi_dma->dma_rx_channel,
+				t->rx_dma, INCR, W8BIT);
+		edma_set_src_index(davinci_spi_dma->dma_rx_channel, 0, 0);
+		edma_set_dest_index(davinci_spi_dma->dma_rx_channel,
+				data_type, 0);
+	}
+
+	if ((t->tx_buf) || (t->rx_buf))
+		edma_start(davinci_spi_dma->dma_tx_channel);
+
+	if (t->rx_buf)
+		edma_start(davinci_spi_dma->dma_rx_channel);
+
+	if ((t->rx_buf) || (t->tx_buf))
+		davinci_spi_set_dma_req(spi, 1);
+
+	if (t->tx_buf)
+		wait_for_completion_interruptible(
+				&davinci_spi_dma->dma_tx_completion);
+
+	if (t->rx_buf)
+		wait_for_completion_interruptible(
+				&davinci_spi_dma->dma_rx_completion);
+
+	dma_unmap_single(NULL, t->tx_dma, temp_count, DMA_TO_DEVICE);
+
+	if (t->rx_buf)
+		dma_unmap_single(NULL, t->rx_dma, count, DMA_FROM_DEVICE);
+
+	/*
+	 * Check for bit error, desync error,parity error,timeout error and
+	 * receive overflow errors
+	 */
+	int_status = ioread32(davinci_spi->base + SPIFLG);
+
+	ret = davinci_spi_check_error(davinci_spi, int_status);
+	if (ret != 0)
+		return ret;
+
+	/* SPI Framework maintains the count only in bytes so convert back */
+	davinci_spi->count *= conv;
+
+	return t->len;
+}
+
+/**
+ * davinci_spi_irq - IRQ handler for DaVinci SPI
+ * @irq: IRQ number for this SPI Master
+ * @context_data: structure for SPI Master controller davinci_spi
+ */
+static irqreturn_t davinci_spi_irq(s32 irq, void *context_data)
+{
+	struct davinci_spi *davinci_spi = context_data;
+	u32 int_status, rx_data = 0;
+	irqreturn_t ret = IRQ_NONE;
+
+	int_status = ioread32(davinci_spi->base + SPIFLG);
+
+	while ((int_status & SPIFLG_RX_INTR_MASK)) {
+		if (likely(int_status & SPIFLG_RX_INTR_MASK)) {
+			ret = IRQ_HANDLED;
+
+			rx_data = ioread32(davinci_spi->base + SPIBUF);
+			davinci_spi->get_rx(rx_data, davinci_spi);
+
+			/* Disable Receive Interrupt */
+			iowrite32(~(SPIINT_RX_INTR | SPIINT_TX_INTR),
+					davinci_spi->base + SPIINT);
+		} else
+			(void)davinci_spi_check_error(davinci_spi, int_status);
+
+		int_status = ioread32(davinci_spi->base + SPIFLG);
+	}
+
+	return ret;
+}
+
+/**
+ * davinci_spi_probe - probe function for SPI Master Controller
+ * @pdev: platform_device structure which contains plateform specific data
+ */
+static int davinci_spi_probe(struct platform_device *pdev)
+{
+	struct spi_master *master;
+	struct davinci_spi *davinci_spi;
+	struct davinci_spi_platform_data *pdata;
+	struct resource *r, *mem;
+	resource_size_t dma_rx_chan = SPI_NO_RESOURCE;
+	resource_size_t	dma_tx_chan = SPI_NO_RESOURCE;
+	resource_size_t	dma_eventq = SPI_NO_RESOURCE;
+	int i = 0, ret = 0;
+
+	pdata = pdev->dev.platform_data;
+	if (pdata == NULL) {
+		ret = -ENODEV;
+		goto err;
+	}
+
+	master = spi_alloc_master(&pdev->dev, sizeof(struct davinci_spi));
+	if (master == NULL) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	dev_set_drvdata(&pdev->dev, master);
+
+	davinci_spi = spi_master_get_devdata(master);
+	if (davinci_spi == NULL) {
+		ret = -ENOENT;
+		goto free_master;
+	}
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (r == NULL) {
+		ret = -ENOENT;
+		goto free_master;
+	}
+
+	davinci_spi->pbase = r->start;
+	davinci_spi->region_size = resource_size(r);
+	davinci_spi->pdata = pdata;
+
+	mem = request_mem_region(r->start, davinci_spi->region_size,
+					pdev->name);
+	if (mem == NULL) {
+		ret = -EBUSY;
+		goto free_master;
+	}
+
+	davinci_spi->base = (struct davinci_spi_reg __iomem *)
+			ioremap(r->start, davinci_spi->region_size);
+	if (davinci_spi->base == NULL) {
+		ret = -ENOMEM;
+		goto release_region;
+	}
+
+	davinci_spi->irq = platform_get_irq(pdev, 0);
+	if (davinci_spi->irq <= 0) {
+		ret = -EINVAL;
+		goto unmap_io;
+	}
+
+	ret = request_irq(davinci_spi->irq, davinci_spi_irq, IRQF_DISABLED,
+			  dev_name(&pdev->dev), davinci_spi);
+	if (ret)
+		goto unmap_io;
+
+	/* Allocate tmp_buf for tx_buf */
+	davinci_spi->tmp_buf = kzalloc(SPI_BUFSIZ, GFP_KERNEL);
+	if (davinci_spi->tmp_buf == NULL) {
+		ret = -ENOMEM;
+		goto irq_free;
+	}
+
+	davinci_spi->bitbang.master = spi_master_get(master);
+	if (davinci_spi->bitbang.master == NULL) {
+		ret = -ENODEV;
+		goto free_tmp_buf;
+	}
+
+	davinci_spi->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(davinci_spi->clk)) {
+		ret = -ENODEV;
+		goto put_master;
+	}
+	clk_enable(davinci_spi->clk);
+
+
+	master->bus_num = pdev->id;
+	master->num_chipselect = pdata->num_chipselect;
+	master->setup = davinci_spi_setup;
+	master->cleanup = davinci_spi_cleanup;
+
+	davinci_spi->bitbang.chipselect = davinci_spi_chipselect;
+	davinci_spi->bitbang.setup_transfer = davinci_spi_setup_transfer;
+
+	davinci_spi->version = pdata->version;
+	use_dma = pdata->use_dma;
+
+	davinci_spi->bitbang.flags = SPI_NO_CS | SPI_LSB_FIRST | SPI_LOOP;
+	if (davinci_spi->version == SPI_VERSION_2)
+		davinci_spi->bitbang.flags |= SPI_READY;
+
+	if (use_dma) {
+			r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+			if (r)
+				dma_rx_chan = r->start;
+			r = platform_get_resource(pdev, IORESOURCE_DMA, 1);
+			if (r)
+				dma_tx_chan = r->start;
+			r = platform_get_resource(pdev, IORESOURCE_DMA, 2);
+			if (r)
+				dma_eventq = r->start;
+	}
+
+	if (!use_dma ||
+	    dma_rx_chan == SPI_NO_RESOURCE ||
+	    dma_tx_chan == SPI_NO_RESOURCE ||
+	    dma_eventq	== SPI_NO_RESOURCE) {
+		davinci_spi->bitbang.txrx_bufs = davinci_spi_bufs_pio;
+		use_dma = 0;
+	} else {
+		davinci_spi->bitbang.txrx_bufs = davinci_spi_bufs_dma;
+		davinci_spi->dma_channels = kzalloc(master->num_chipselect
+				* sizeof(struct davinci_spi_dma), GFP_KERNEL);
+		if (davinci_spi->dma_channels == NULL) {
+			ret = -ENOMEM;
+			goto free_clk;
+		}
+
+		for (i = 0; i < master->num_chipselect; i++) {
+			davinci_spi->dma_channels[i].dma_rx_channel = -1;
+			davinci_spi->dma_channels[i].dma_rx_sync_dev =
+				dma_rx_chan;
+			davinci_spi->dma_channels[i].dma_tx_channel = -1;
+			davinci_spi->dma_channels[i].dma_tx_sync_dev =
+				dma_tx_chan;
+			davinci_spi->dma_channels[i].eventq = dma_eventq;
+		}
+		dev_info(&pdev->dev, "DaVinci SPI driver in EDMA mode\n"
+				"Using RX channel = %d , TX channel = %d and "
+				"event queue = %d", dma_rx_chan, dma_tx_chan,
+				dma_eventq);
+	}
+
+	davinci_spi->get_rx = davinci_spi_rx_buf_u8;
+	davinci_spi->get_tx = davinci_spi_tx_buf_u8;
+
+	init_completion(&davinci_spi->done);
+
+	/* Reset In/OUT SPI module */
+	iowrite32(0, davinci_spi->base + SPIGCR0);
+	udelay(100);
+	iowrite32(1, davinci_spi->base + SPIGCR0);
+
+	/* Clock internal */
+	if (davinci_spi->pdata->clk_internal)
+		set_io_bits(davinci_spi->base + SPIGCR1,
+				SPIGCR1_CLKMOD_MASK);
+	else
+		clear_io_bits(davinci_spi->base + SPIGCR1,
+				SPIGCR1_CLKMOD_MASK);
+
+	/* master mode default */
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_MASTER_MASK);
+
+	if (davinci_spi->pdata->intr_level)
+		iowrite32(SPI_INTLVL_1, davinci_spi->base + SPILVL);
+	else
+		iowrite32(SPI_INTLVL_0, davinci_spi->base + SPILVL);
+
+	ret = spi_bitbang_start(&davinci_spi->bitbang);
+	if (ret)
+		goto free_clk;
+
+	dev_info(&pdev->dev, "Controller at 0x%p \n", davinci_spi->base);
+
+	if (!pdata->poll_mode)
+		dev_info(&pdev->dev, "Operating in interrupt mode"
+			" using IRQ %d\n", davinci_spi->irq);
+
+	return ret;
+
+free_clk:
+	clk_disable(davinci_spi->clk);
+	clk_put(davinci_spi->clk);
+put_master:
+	spi_master_put(master);
+free_tmp_buf:
+	kfree(davinci_spi->tmp_buf);
+irq_free:
+	free_irq(davinci_spi->irq, davinci_spi);
+unmap_io:
+	iounmap(davinci_spi->base);
+release_region:
+	release_mem_region(davinci_spi->pbase, davinci_spi->region_size);
+free_master:
+	kfree(master);
+err:
+	return ret;
+}
+
+/**
+ * davinci_spi_remove - remove function for SPI Master Controller
+ * @pdev: platform_device structure which contains plateform specific data
+ *
+ * This function will do the reverse action of davinci_spi_probe function
+ * It will free the IRQ and SPI controller's memory region.
+ * It will also call spi_bitbang_stop to destroy the work queue which was
+ * created by spi_bitbang_start.
+ */
+static int __exit davinci_spi_remove(struct platform_device *pdev)
+{
+	struct davinci_spi *davinci_spi;
+	struct spi_master *master;
+
+	master = dev_get_drvdata(&pdev->dev);
+	davinci_spi = spi_master_get_devdata(master);
+
+	spi_bitbang_stop(&davinci_spi->bitbang);
+
+	clk_disable(davinci_spi->clk);
+	clk_put(davinci_spi->clk);
+	spi_master_put(master);
+	kfree(davinci_spi->tmp_buf);
+	free_irq(davinci_spi->irq, davinci_spi);
+	iounmap(davinci_spi->base);
+	release_mem_region(davinci_spi->pbase, davinci_spi->region_size);
+
+	return 0;
+}
+
+static struct platform_driver davinci_spi_driver = {
+	.driver.name = "spi_davinci",
+	.remove = __exit_p(davinci_spi_remove),
+};
+
+static int __init davinci_spi_init(void)
+{
+	return platform_driver_probe(&davinci_spi_driver, davinci_spi_probe);
+}
+module_init(davinci_spi_init);
+
+static void __exit davinci_spi_exit(void)
+{
+	platform_driver_unregister(&davinci_spi_driver);
+}
+module_exit(davinci_spi_exit);
+
+MODULE_DESCRIPTION("TI DaVinci SPI Master Controller Driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c
index 31620fae77b..8ed38f1d6c1 100644
--- a/drivers/spi/dw_spi.c
+++ b/drivers/spi/dw_spi.c
@@ -152,6 +152,7 @@ static void mrst_spi_debugfs_remove(struct dw_spi *dws)
 #else
 static inline int mrst_spi_debugfs_init(struct dw_spi *dws)
 {
+	return 0;
 }
 
 static inline void mrst_spi_debugfs_remove(struct dw_spi *dws)
@@ -161,14 +162,14 @@ static inline void mrst_spi_debugfs_remove(struct dw_spi *dws)
 
 static void wait_till_not_busy(struct dw_spi *dws)
 {
-	unsigned long end = jiffies + usecs_to_jiffies(1000);
+	unsigned long end = jiffies + 1 + usecs_to_jiffies(1000);
 
 	while (time_before(jiffies, end)) {
 		if (!(dw_readw(dws, sr) & SR_BUSY))
 			return;
 	}
 	dev_err(&dws->master->dev,
-		"DW SPI: Stutus keeps busy for 1000us after a read/write!\n");
+		"DW SPI: Status keeps busy for 1000us after a read/write!\n");
 }
 
 static void flush(struct dw_spi *dws)
@@ -358,6 +359,8 @@ static void transfer_complete(struct dw_spi *dws)
 static irqreturn_t interrupt_transfer(struct dw_spi *dws)
 {
 	u16 irq_status, irq_mask = 0x3f;
+	u32 int_level = dws->fifo_len / 2;
+	u32 left;
 
 	irq_status = dw_readw(dws, isr) & irq_mask;
 	/* Error handling */
@@ -369,22 +372,23 @@ static irqreturn_t interrupt_transfer(struct dw_spi *dws)
 		return IRQ_HANDLED;
 	}
 
-	/* INT comes from tx */
-	if (dws->tx && (irq_status & SPI_INT_TXEI)) {
-		while (dws->tx < dws->tx_end)
+	if (irq_status & SPI_INT_TXEI) {
+		spi_mask_intr(dws, SPI_INT_TXEI);
+
+		left = (dws->tx_end - dws->tx) / dws->n_bytes;
+		left = (left > int_level) ? int_level : left;
+
+		while (left--)
 			dws->write(dws);
+		dws->read(dws);
 
-		if (dws->tx == dws->tx_end) {
-			spi_mask_intr(dws, SPI_INT_TXEI);
+		/* Re-enable the IRQ if there is still data left to tx */
+		if (dws->tx_end > dws->tx)
+			spi_umask_intr(dws, SPI_INT_TXEI);
+		else
 			transfer_complete(dws);
-		}
 	}
 
-	/* INT comes from rx */
-	if (dws->rx && (irq_status & SPI_INT_RXFI)) {
-		if (dws->read(dws))
-			transfer_complete(dws);
-	}
 	return IRQ_HANDLED;
 }
 
@@ -404,12 +408,9 @@ static irqreturn_t dw_spi_irq(int irq, void *dev_id)
 /* Must be called inside pump_transfers() */
 static void poll_transfer(struct dw_spi *dws)
 {
-	if (dws->tx) {
-		while (dws->write(dws))
-			dws->read(dws);
-	}
+	while (dws->write(dws))
+		dws->read(dws);
 
-	dws->read(dws);
 	transfer_complete(dws);
 }
 
@@ -428,6 +429,7 @@ static void pump_transfers(unsigned long data)
 	u8 bits = 0;
 	u8 imask = 0;
 	u8 cs_change = 0;
+	u16 txint_level = 0;
 	u16 clk_div = 0;
 	u32 speed = 0;
 	u32 cr0 = 0;
@@ -438,6 +440,9 @@ static void pump_transfers(unsigned long data)
 	chip = dws->cur_chip;
 	spi = message->spi;
 
+	if (unlikely(!chip->clk_div))
+		chip->clk_div = dws->max_freq / chip->speed_hz;
+
 	if (message->state == ERROR_STATE) {
 		message->status = -EIO;
 		goto early_exit;
@@ -492,7 +497,7 @@ static void pump_transfers(unsigned long data)
 
 			/* clk_div doesn't support odd number */
 			clk_div = dws->max_freq / speed;
-			clk_div = (clk_div >> 1) << 1;
+			clk_div = (clk_div + 1) & 0xfffe;
 
 			chip->speed_hz = speed;
 			chip->clk_div = clk_div;
@@ -532,14 +537,35 @@ static void pump_transfers(unsigned long data)
 	}
 	message->state = RUNNING_STATE;
 
+	/*
+	 * Adjust transfer mode if necessary. Requires platform dependent
+	 * chipselect mechanism.
+	 */
+	if (dws->cs_control) {
+		if (dws->rx && dws->tx)
+			chip->tmode = 0x00;
+		else if (dws->rx)
+			chip->tmode = 0x02;
+		else
+			chip->tmode = 0x01;
+
+		cr0 &= ~(0x3 << SPI_MODE_OFFSET);
+		cr0 |= (chip->tmode << SPI_TMOD_OFFSET);
+	}
+
 	/* Check if current transfer is a DMA transaction */
 	dws->dma_mapped = map_dma_buffers(dws);
 
+	/*
+	 * Interrupt mode
+	 * we only need set the TXEI IRQ, as TX/RX always happen syncronizely
+	 */
 	if (!dws->dma_mapped && !chip->poll_mode) {
-		if (dws->rx)
-			imask |= SPI_INT_RXFI;
-		if (dws->tx)
-			imask |= SPI_INT_TXEI;
+		int templen = dws->len / dws->n_bytes;
+		txint_level = dws->fifo_len / 2;
+		txint_level = (templen > txint_level) ? txint_level : templen;
+
+		imask |= SPI_INT_TXEI;
 		dws->transfer_handler = interrupt_transfer;
 	}
 
@@ -549,21 +575,23 @@ static void pump_transfers(unsigned long data)
 	 *	2. clk_div is changed
 	 *	3. control value changes
 	 */
-	if (dw_readw(dws, ctrl0) != cr0 || cs_change || clk_div) {
+	if (dw_readw(dws, ctrl0) != cr0 || cs_change || clk_div || imask) {
 		spi_enable_chip(dws, 0);
 
 		if (dw_readw(dws, ctrl0) != cr0)
 			dw_writew(dws, ctrl0, cr0);
 
+		spi_set_clk(dws, clk_div ? clk_div : chip->clk_div);
+		spi_chip_sel(dws, spi->chip_select);
+
 		/* Set the interrupt mask, for poll mode just diable all int */
 		spi_mask_intr(dws, 0xff);
-		if (!chip->poll_mode)
+		if (imask)
 			spi_umask_intr(dws, imask);
+		if (txint_level)
+			dw_writew(dws, txfltr, txint_level);
 
-		spi_set_clk(dws, clk_div ? clk_div : chip->clk_div);
-		spi_chip_sel(dws, spi->chip_select);
 		spi_enable_chip(dws, 1);
-
 		if (cs_change)
 			dws->prev_chip = chip;
 	}
@@ -712,11 +740,11 @@ static int dw_spi_setup(struct spi_device *spi)
 	}
 	chip->bits_per_word = spi->bits_per_word;
 
+	if (!spi->max_speed_hz) {
+		dev_err(&spi->dev, "No max speed HZ parameter\n");
+		return -EINVAL;
+	}
 	chip->speed_hz = spi->max_speed_hz;
-	if (chip->speed_hz)
-		chip->clk_div = 25000000 / chip->speed_hz;
-	else
-		chip->clk_div = 8;	/* default value */
 
 	chip->tmode = 0; /* Tx & Rx */
 	/* Default SPI mode is SCPOL = 0, SCPH = 0 */
@@ -735,7 +763,7 @@ static void dw_spi_cleanup(struct spi_device *spi)
 	kfree(chip);
 }
 
-static int __init init_queue(struct dw_spi *dws)
+static int __devinit init_queue(struct dw_spi *dws)
 {
 	INIT_LIST_HEAD(&dws->queue);
 	spin_lock_init(&dws->lock);
@@ -817,6 +845,22 @@ static void spi_hw_init(struct dw_spi *dws)
 	spi_mask_intr(dws, 0xff);
 	spi_enable_chip(dws, 1);
 	flush(dws);
+
+	/*
+	 * Try to detect the FIFO depth if not set by interface driver,
+	 * the depth could be from 2 to 256 from HW spec
+	 */
+	if (!dws->fifo_len) {
+		u32 fifo;
+		for (fifo = 2; fifo <= 257; fifo++) {
+			dw_writew(dws, txfltr, fifo);
+			if (fifo != dw_readw(dws, txfltr))
+				break;
+		}
+
+		dws->fifo_len = (fifo == 257) ? 0 : fifo;
+		dw_writew(dws, txfltr, 0);
+	}
 }
 
 int __devinit dw_spi_add_host(struct dw_spi *dws)
@@ -913,6 +957,7 @@ void __devexit dw_spi_remove_host(struct dw_spi *dws)
 	/* Disconnect from the SPI framework */
 	spi_unregister_master(dws->master);
 }
+EXPORT_SYMBOL(dw_spi_remove_host);
 
 int dw_spi_suspend_host(struct dw_spi *dws)
 {
diff --git a/drivers/spi/dw_spi_mmio.c b/drivers/spi/dw_spi_mmio.c
new file mode 100644
index 00000000000..e35b45ac517
--- /dev/null
+++ b/drivers/spi/dw_spi_mmio.c
@@ -0,0 +1,147 @@
+/*
+ * dw_spi_mmio.c - Memory-mapped interface driver for DW SPI Core
+ *
+ * Copyright (c) 2010, Octasic semiconductor.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/spi/dw_spi.h>
+#include <linux/spi/spi.h>
+
+#define DRIVER_NAME "dw_spi_mmio"
+
+struct dw_spi_mmio {
+	struct dw_spi  dws;
+	struct clk     *clk;
+};
+
+static int __devinit dw_spi_mmio_probe(struct platform_device *pdev)
+{
+	struct dw_spi_mmio *dwsmmio;
+	struct dw_spi *dws;
+	struct resource *mem, *ioarea;
+	int ret;
+
+	dwsmmio = kzalloc(sizeof(struct dw_spi_mmio), GFP_KERNEL);
+	if (!dwsmmio) {
+		ret = -ENOMEM;
+		goto err_end;
+	}
+
+	dws = &dwsmmio->dws;
+
+	/* Get basic io resource and map it */
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!mem) {
+		dev_err(&pdev->dev, "no mem resource?\n");
+		ret = -EINVAL;
+		goto err_kfree;
+	}
+
+	ioarea = request_mem_region(mem->start, resource_size(mem),
+			pdev->name);
+	if (!ioarea) {
+		dev_err(&pdev->dev, "SPI region already claimed\n");
+		ret = -EBUSY;
+		goto err_kfree;
+	}
+
+	dws->regs = ioremap_nocache(mem->start, resource_size(mem));
+	if (!dws->regs) {
+		dev_err(&pdev->dev, "SPI region already mapped\n");
+		ret = -ENOMEM;
+		goto err_release_reg;
+	}
+
+	dws->irq = platform_get_irq(pdev, 0);
+	if (dws->irq < 0) {
+		dev_err(&pdev->dev, "no irq resource?\n");
+		ret = dws->irq; /* -ENXIO */
+		goto err_unmap;
+	}
+
+	dwsmmio->clk = clk_get(&pdev->dev, NULL);
+	if (!dwsmmio->clk) {
+		ret = -ENODEV;
+		goto err_irq;
+	}
+	clk_enable(dwsmmio->clk);
+
+	dws->parent_dev = &pdev->dev;
+	dws->bus_num = 0;
+	dws->num_cs = 4;
+	dws->max_freq = clk_get_rate(dwsmmio->clk);
+
+	ret = dw_spi_add_host(dws);
+	if (ret)
+		goto err_clk;
+
+	platform_set_drvdata(pdev, dwsmmio);
+	return 0;
+
+err_clk:
+	clk_disable(dwsmmio->clk);
+	clk_put(dwsmmio->clk);
+	dwsmmio->clk = NULL;
+err_irq:
+	free_irq(dws->irq, dws);
+err_unmap:
+	iounmap(dws->regs);
+err_release_reg:
+	release_mem_region(mem->start, resource_size(mem));
+err_kfree:
+	kfree(dwsmmio);
+err_end:
+	return ret;
+}
+
+static int __devexit dw_spi_mmio_remove(struct platform_device *pdev)
+{
+	struct dw_spi_mmio *dwsmmio = platform_get_drvdata(pdev);
+	struct resource *mem;
+
+	platform_set_drvdata(pdev, NULL);
+
+	clk_disable(dwsmmio->clk);
+	clk_put(dwsmmio->clk);
+	dwsmmio->clk = NULL;
+
+	free_irq(dwsmmio->dws.irq, &dwsmmio->dws);
+	dw_spi_remove_host(&dwsmmio->dws);
+	iounmap(dwsmmio->dws.regs);
+	kfree(dwsmmio);
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(mem->start, resource_size(mem));
+	return 0;
+}
+
+static struct platform_driver dw_spi_mmio_driver = {
+	.remove		= __devexit_p(dw_spi_mmio_remove),
+	.driver		= {
+		.name	= DRIVER_NAME,
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init dw_spi_mmio_init(void)
+{
+	return platform_driver_probe(&dw_spi_mmio_driver, dw_spi_mmio_probe);
+}
+module_init(dw_spi_mmio_init);
+
+static void __exit dw_spi_mmio_exit(void)
+{
+	platform_driver_unregister(&dw_spi_mmio_driver);
+}
+module_exit(dw_spi_mmio_exit);
+
+MODULE_AUTHOR("Jean-Hugues Deschenes <jean-hugues.deschenes@octasic.com>");
+MODULE_DESCRIPTION("Memory-mapped I/O interface driver for DW SPI Core");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/dw_spi_pci.c b/drivers/spi/dw_spi_pci.c
index 34ba6916173..1f0735f9cc7 100644
--- a/drivers/spi/dw_spi_pci.c
+++ b/drivers/spi/dw_spi_pci.c
@@ -73,6 +73,7 @@ static int __devinit spi_pci_probe(struct pci_dev *pdev,
 	dws->num_cs = 4;
 	dws->max_freq = 25000000;	/* for Moorestwon */
 	dws->irq = pdev->irq;
+	dws->fifo_len = 40;		/* FIFO has 40 words buffer */
 
 	ret = dw_spi_add_host(dws);
 	if (ret)
@@ -98,6 +99,7 @@ static void __devexit spi_pci_remove(struct pci_dev *pdev)
 	struct dw_spi_pci *dwpci = pci_get_drvdata(pdev);
 
 	pci_set_drvdata(pdev, NULL);
+	dw_spi_remove_host(&dwpci->dws);
 	iounmap(dwpci->dws.regs);
 	pci_release_region(pdev, 0);
 	kfree(dwpci);
diff --git a/drivers/spi/mpc52xx_psc_spi.c b/drivers/spi/mpc52xx_psc_spi.c
index f50c81df336..04747868d6c 100644
--- a/drivers/spi/mpc52xx_psc_spi.c
+++ b/drivers/spi/mpc52xx_psc_spi.c
@@ -503,7 +503,7 @@ static int __exit mpc52xx_psc_spi_of_remove(struct of_device *op)
 	return mpc52xx_psc_spi_do_remove(&op->dev);
 }
 
-static struct of_device_id mpc52xx_psc_spi_of_match[] = {
+static const struct of_device_id mpc52xx_psc_spi_of_match[] = {
 	{ .compatible = "fsl,mpc5200-psc-spi", },
 	{ .compatible = "mpc5200-psc-spi", }, /* old */
 	{}
diff --git a/drivers/spi/mpc52xx_spi.c b/drivers/spi/mpc52xx_spi.c
index 45bfe645817..6eab46537a0 100644
--- a/drivers/spi/mpc52xx_spi.c
+++ b/drivers/spi/mpc52xx_spi.c
@@ -550,7 +550,7 @@ static int __devexit mpc52xx_spi_remove(struct of_device *op)
 	return 0;
 }
 
-static struct of_device_id mpc52xx_spi_match[] __devinitdata = {
+static const struct of_device_id mpc52xx_spi_match[] __devinitconst = {
 	{ .compatible = "fsl,mpc5200-spi", },
 	{}
 };
diff --git a/drivers/spi/spi_imx.c b/drivers/spi/spi_imx.c
index 1893f1e96dc..0ddbbe45e83 100644
--- a/drivers/spi/spi_imx.c
+++ b/drivers/spi/spi_imx.c
@@ -469,7 +469,7 @@ static int spi_imx_setup(struct spi_device *spi)
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
 	int gpio = spi_imx->chipselect[spi->chip_select];
 
-	pr_debug("%s: mode %d, %u bpw, %d hz\n", __func__,
+	dev_dbg(&spi->dev, "%s: mode %d, %u bpw, %d hz\n", __func__,
 		 spi->mode, spi->bits_per_word, spi->max_speed_hz);
 
 	if (gpio >= 0)
diff --git a/drivers/spi/spi_mpc8xxx.c b/drivers/spi/spi_mpc8xxx.c
index 1fb2a6ea328..4f0cc9d457e 100644
--- a/drivers/spi/spi_mpc8xxx.c
+++ b/drivers/spi/spi_mpc8xxx.c
@@ -365,7 +365,7 @@ int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 
 	if ((mpc8xxx_spi->spibrg / hz) > 64) {
 		cs->hw_mode |= SPMODE_DIV16;
-		pm = mpc8xxx_spi->spibrg / (hz * 64);
+		pm = (mpc8xxx_spi->spibrg - 1) / (hz * 64) + 1;
 
 		WARN_ONCE(pm > 16, "%s: Requested speed is too low: %d Hz. "
 			  "Will use %d Hz instead.\n", dev_name(&spi->dev),
@@ -373,7 +373,7 @@ int mpc8xxx_spi_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 		if (pm > 16)
 			pm = 16;
 	} else
-		pm = mpc8xxx_spi->spibrg / (hz * 4);
+		pm = (mpc8xxx_spi->spibrg - 1) / (hz * 4) + 1;
 	if (pm)
 		pm--;
 
@@ -1328,7 +1328,7 @@ static struct of_platform_driver of_mpc8xxx_spi_driver = {
 static int __devinit plat_mpc8xxx_spi_probe(struct platform_device *pdev)
 {
 	struct resource *mem;
-	unsigned int irq;
+	int irq;
 	struct spi_master *master;
 
 	if (!pdev->dev.platform_data)
@@ -1339,7 +1339,7 @@ static int __devinit plat_mpc8xxx_spi_probe(struct platform_device *pdev)
 		return -EINVAL;
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq)
+	if (irq <= 0)
 		return -EINVAL;
 
 	master = mpc8xxx_spi_probe(&pdev->dev, mem, irq);
diff --git a/drivers/spi/spi_ppc4xx.c b/drivers/spi/spi_ppc4xx.c
index 140a18d6cf3..6d8d4026a07 100644
--- a/drivers/spi/spi_ppc4xx.c
+++ b/drivers/spi/spi_ppc4xx.c
@@ -578,7 +578,7 @@ static int __exit spi_ppc4xx_of_remove(struct of_device *op)
 	return 0;
 }
 
-static struct of_device_id spi_ppc4xx_of_match[] = {
+static const struct of_device_id spi_ppc4xx_of_match[] = {
 	{ .compatible = "ibm,ppc4xx-spi", },
 	{},
 };
diff --git a/drivers/spi/spi_s3c64xx.c b/drivers/spi/spi_s3c64xx.c
index 88a456dba96..97365815a72 100644
--- a/drivers/spi/spi_s3c64xx.c
+++ b/drivers/spi/spi_s3c64xx.c
@@ -28,7 +28,7 @@
 #include <linux/spi/spi.h>
 
 #include <mach/dma.h>
-#include <plat/spi.h>
+#include <plat/s3c64xx-spi.h>
 
 /* Registers and bit-fields */
 
@@ -137,6 +137,7 @@
 /**
  * struct s3c64xx_spi_driver_data - Runtime info holder for SPI driver.
  * @clk: Pointer to the spi clock.
+ * @src_clk: Pointer to the clock used to generate SPI signals.
  * @master: Pointer to the SPI Protocol master.
  * @workqueue: Work queue for the SPI xfer requests.
  * @cntrlr_info: Platform specific data for the controller this driver manages.
@@ -157,10 +158,11 @@
 struct s3c64xx_spi_driver_data {
 	void __iomem                    *regs;
 	struct clk                      *clk;
+	struct clk                      *src_clk;
 	struct platform_device          *pdev;
 	struct spi_master               *master;
 	struct workqueue_struct	        *workqueue;
-	struct s3c64xx_spi_cntrlr_info  *cntrlr_info;
+	struct s3c64xx_spi_info  *cntrlr_info;
 	struct spi_device               *tgl_spi;
 	struct work_struct              work;
 	struct list_head                queue;
@@ -180,7 +182,7 @@ static struct s3c2410_dma_client s3c64xx_spi_dma_client = {
 
 static void flush_fifo(struct s3c64xx_spi_driver_data *sdd)
 {
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
 	unsigned long loops;
 	u32 val;
@@ -225,7 +227,7 @@ static void enable_datapath(struct s3c64xx_spi_driver_data *sdd,
 				struct spi_device *spi,
 				struct spi_transfer *xfer, int dma_mode)
 {
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
 	u32 modecfg, chcfg;
 
@@ -298,19 +300,20 @@ static inline void enable_cs(struct s3c64xx_spi_driver_data *sdd,
 		if (sdd->tgl_spi != spi) { /* if last mssg on diff device */
 			/* Deselect the last toggled device */
 			cs = sdd->tgl_spi->controller_data;
-			cs->set_level(spi->mode & SPI_CS_HIGH ? 0 : 1);
+			cs->set_level(cs->line,
+					spi->mode & SPI_CS_HIGH ? 0 : 1);
 		}
 		sdd->tgl_spi = NULL;
 	}
 
 	cs = spi->controller_data;
-	cs->set_level(spi->mode & SPI_CS_HIGH ? 1 : 0);
+	cs->set_level(cs->line, spi->mode & SPI_CS_HIGH ? 1 : 0);
 }
 
 static int wait_for_xfer(struct s3c64xx_spi_driver_data *sdd,
 				struct spi_transfer *xfer, int dma_mode)
 {
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
 	unsigned long val;
 	int ms;
@@ -384,12 +387,11 @@ static inline void disable_cs(struct s3c64xx_spi_driver_data *sdd,
 	if (sdd->tgl_spi == spi)
 		sdd->tgl_spi = NULL;
 
-	cs->set_level(spi->mode & SPI_CS_HIGH ? 0 : 1);
+	cs->set_level(cs->line, spi->mode & SPI_CS_HIGH ? 0 : 1);
 }
 
 static void s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd)
 {
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
 	u32 val;
 
@@ -435,7 +437,7 @@ static void s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd)
 	/* Configure Clock */
 	val = readl(regs + S3C64XX_SPI_CLK_CFG);
 	val &= ~S3C64XX_SPI_PSR_MASK;
-	val |= ((clk_get_rate(sci->src_clk) / sdd->cur_speed / 2 - 1)
+	val |= ((clk_get_rate(sdd->src_clk) / sdd->cur_speed / 2 - 1)
 			& S3C64XX_SPI_PSR_MASK);
 	writel(val, regs + S3C64XX_SPI_CLK_CFG);
 
@@ -558,7 +560,7 @@ static void s3c64xx_spi_unmap_mssg(struct s3c64xx_spi_driver_data *sdd,
 static void handle_msg(struct s3c64xx_spi_driver_data *sdd,
 					struct spi_message *msg)
 {
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	struct spi_device *spi = msg->spi;
 	struct s3c64xx_spi_csinfo *cs = spi->controller_data;
 	struct spi_transfer *xfer;
@@ -632,8 +634,8 @@ static void handle_msg(struct s3c64xx_spi_driver_data *sdd,
 		S3C64XX_SPI_DEACT(sdd);
 
 		if (status) {
-			dev_err(&spi->dev, "I/O Error: \
-				rx-%d tx-%d res:rx-%c tx-%c len-%d\n",
+			dev_err(&spi->dev, "I/O Error: "
+				"rx-%d tx-%d res:rx-%c tx-%c len-%d\n",
 				xfer->rx_buf ? 1 : 0, xfer->tx_buf ? 1 : 0,
 				(sdd->state & RXBUSY) ? 'f' : 'p',
 				(sdd->state & TXBUSY) ? 'f' : 'p',
@@ -786,7 +788,7 @@ static int s3c64xx_spi_setup(struct spi_device *spi)
 {
 	struct s3c64xx_spi_csinfo *cs = spi->controller_data;
 	struct s3c64xx_spi_driver_data *sdd;
-	struct s3c64xx_spi_cntrlr_info *sci;
+	struct s3c64xx_spi_info *sci;
 	struct spi_message *msg;
 	u32 psr, speed;
 	unsigned long flags;
@@ -831,17 +833,17 @@ static int s3c64xx_spi_setup(struct spi_device *spi)
 	}
 
 	/* Check if we can provide the requested rate */
-	speed = clk_get_rate(sci->src_clk) / 2 / (0 + 1); /* Max possible */
+	speed = clk_get_rate(sdd->src_clk) / 2 / (0 + 1); /* Max possible */
 
 	if (spi->max_speed_hz > speed)
 		spi->max_speed_hz = speed;
 
-	psr = clk_get_rate(sci->src_clk) / 2 / spi->max_speed_hz - 1;
+	psr = clk_get_rate(sdd->src_clk) / 2 / spi->max_speed_hz - 1;
 	psr &= S3C64XX_SPI_PSR_MASK;
 	if (psr == S3C64XX_SPI_PSR_MASK)
 		psr--;
 
-	speed = clk_get_rate(sci->src_clk) / 2 / (psr + 1);
+	speed = clk_get_rate(sdd->src_clk) / 2 / (psr + 1);
 	if (spi->max_speed_hz < speed) {
 		if (psr+1 < S3C64XX_SPI_PSR_MASK) {
 			psr++;
@@ -851,7 +853,7 @@ static int s3c64xx_spi_setup(struct spi_device *spi)
 		}
 	}
 
-	speed = clk_get_rate(sci->src_clk) / 2 / (psr + 1);
+	speed = clk_get_rate(sdd->src_clk) / 2 / (psr + 1);
 	if (spi->max_speed_hz >= speed)
 		spi->max_speed_hz = speed;
 	else
@@ -867,7 +869,7 @@ setup_exit:
 
 static void s3c64xx_spi_hwinit(struct s3c64xx_spi_driver_data *sdd, int channel)
 {
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	void __iomem *regs = sdd->regs;
 	unsigned int val;
 
@@ -902,7 +904,7 @@ static int __init s3c64xx_spi_probe(struct platform_device *pdev)
 {
 	struct resource	*mem_res, *dmatx_res, *dmarx_res;
 	struct s3c64xx_spi_driver_data *sdd;
-	struct s3c64xx_spi_cntrlr_info *sci;
+	struct s3c64xx_spi_info *sci;
 	struct spi_master *master;
 	int ret;
 
@@ -1000,18 +1002,15 @@ static int __init s3c64xx_spi_probe(struct platform_device *pdev)
 		goto err4;
 	}
 
-	if (sci->src_clk_nr == S3C64XX_SPI_SRCCLK_PCLK)
-		sci->src_clk = sdd->clk;
-	else
-		sci->src_clk = clk_get(&pdev->dev, sci->src_clk_name);
-	if (IS_ERR(sci->src_clk)) {
+	sdd->src_clk = clk_get(&pdev->dev, sci->src_clk_name);
+	if (IS_ERR(sdd->src_clk)) {
 		dev_err(&pdev->dev,
 			"Unable to acquire clock '%s'\n", sci->src_clk_name);
-		ret = PTR_ERR(sci->src_clk);
+		ret = PTR_ERR(sdd->src_clk);
 		goto err5;
 	}
 
-	if (sci->src_clk != sdd->clk && clk_enable(sci->src_clk)) {
+	if (clk_enable(sdd->src_clk)) {
 		dev_err(&pdev->dev, "Couldn't enable clock '%s'\n",
 							sci->src_clk_name);
 		ret = -EBUSY;
@@ -1040,11 +1039,10 @@ static int __init s3c64xx_spi_probe(struct platform_device *pdev)
 		goto err8;
 	}
 
-	dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d \
-					with %d Slaves attached\n",
+	dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d "
+					"with %d Slaves attached\n",
 					pdev->id, master->num_chipselect);
-	dev_dbg(&pdev->dev, "\tIOmem=[0x%x-0x%x]\
-					\tDMA=[Rx-%d, Tx-%d]\n",
+	dev_dbg(&pdev->dev, "\tIOmem=[0x%x-0x%x]\tDMA=[Rx-%d, Tx-%d]\n",
 					mem_res->end, mem_res->start,
 					sdd->rx_dmach, sdd->tx_dmach);
 
@@ -1053,11 +1051,9 @@ static int __init s3c64xx_spi_probe(struct platform_device *pdev)
 err8:
 	destroy_workqueue(sdd->workqueue);
 err7:
-	if (sci->src_clk != sdd->clk)
-		clk_disable(sci->src_clk);
+	clk_disable(sdd->src_clk);
 err6:
-	if (sci->src_clk != sdd->clk)
-		clk_put(sci->src_clk);
+	clk_put(sdd->src_clk);
 err5:
 	clk_disable(sdd->clk);
 err4:
@@ -1078,7 +1074,6 @@ static int s3c64xx_spi_remove(struct platform_device *pdev)
 {
 	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
 	struct resource	*mem_res;
 	unsigned long flags;
 
@@ -1093,11 +1088,8 @@ static int s3c64xx_spi_remove(struct platform_device *pdev)
 
 	destroy_workqueue(sdd->workqueue);
 
-	if (sci->src_clk != sdd->clk)
-		clk_disable(sci->src_clk);
-
-	if (sci->src_clk != sdd->clk)
-		clk_put(sci->src_clk);
+	clk_disable(sdd->src_clk);
+	clk_put(sdd->src_clk);
 
 	clk_disable(sdd->clk);
 	clk_put(sdd->clk);
@@ -1105,7 +1097,8 @@ static int s3c64xx_spi_remove(struct platform_device *pdev)
 	iounmap((void *) sdd->regs);
 
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(mem_res->start, resource_size(mem_res));
+	if (mem_res != NULL)
+		release_mem_region(mem_res->start, resource_size(mem_res));
 
 	platform_set_drvdata(pdev, NULL);
 	spi_master_put(master);
@@ -1118,8 +1111,6 @@ static int s3c64xx_spi_suspend(struct platform_device *pdev, pm_message_t state)
 {
 	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
-	struct s3c64xx_spi_csinfo *cs;
 	unsigned long flags;
 
 	spin_lock_irqsave(&sdd->lock, flags);
@@ -1130,9 +1121,7 @@ static int s3c64xx_spi_suspend(struct platform_device *pdev, pm_message_t state)
 		msleep(10);
 
 	/* Disable the clock */
-	if (sci->src_clk != sdd->clk)
-		clk_disable(sci->src_clk);
-
+	clk_disable(sdd->src_clk);
 	clk_disable(sdd->clk);
 
 	sdd->cur_speed = 0; /* Output Clock is stopped */
@@ -1144,15 +1133,13 @@ static int s3c64xx_spi_resume(struct platform_device *pdev)
 {
 	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
-	struct s3c64xx_spi_cntrlr_info *sci = sdd->cntrlr_info;
+	struct s3c64xx_spi_info *sci = sdd->cntrlr_info;
 	unsigned long flags;
 
 	sci->cfg_gpio(pdev);
 
 	/* Enable the clock */
-	if (sci->src_clk != sdd->clk)
-		clk_enable(sci->src_clk);
-
+	clk_enable(sdd->src_clk);
 	clk_enable(sdd->clk);
 
 	s3c64xx_spi_hwinit(sdd, pdev->id);
diff --git a/drivers/spi/spi_sh_msiof.c b/drivers/spi/spi_sh_msiof.c
index 30973ec16a9..d93b66743ba 100644
--- a/drivers/spi/spi_sh_msiof.c
+++ b/drivers/spi/spi_sh_msiof.c
@@ -20,12 +20,12 @@
 #include <linux/bitmap.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/err.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/spi/sh_msiof.h>
 
-#include <asm/spi.h>
 #include <asm/unaligned.h>
 
 struct sh_msiof_spi_priv {
diff --git a/drivers/spi/spi_stmp.c b/drivers/spi/spi_stmp.c
index 2552bb36400..fadff76eb7e 100644
--- a/drivers/spi/spi_stmp.c
+++ b/drivers/spi/spi_stmp.c
@@ -76,7 +76,7 @@ struct stmp_spi {
 			break;						\
 		}							\
 		cpu_relax();						\
-	} while (time_before(end_jiffies, jiffies));			\
+	} while (time_before(jiffies, end_jiffies));			\
 	succeeded;							\
 	})
 
diff --git a/drivers/spi/xilinx_spi.c b/drivers/spi/xilinx_spi.c
index 9f386379c16..1b47363cb73 100644
--- a/drivers/spi/xilinx_spi.c
+++ b/drivers/spi/xilinx_spi.c
@@ -93,6 +93,26 @@ struct xilinx_spi {
 	void (*rx_fn) (struct xilinx_spi *);
 };
 
+static void xspi_write32(u32 val, void __iomem *addr)
+{
+	iowrite32(val, addr);
+}
+
+static unsigned int xspi_read32(void __iomem *addr)
+{
+	return ioread32(addr);
+}
+
+static void xspi_write32_be(u32 val, void __iomem *addr)
+{
+	iowrite32be(val, addr);
+}
+
+static unsigned int xspi_read32_be(void __iomem *addr)
+{
+	return ioread32be(addr);
+}
+
 static void xspi_tx8(struct xilinx_spi *xspi)
 {
 	xspi->write_fn(*xspi->tx_ptr, xspi->regs + XSPI_TXD_OFFSET);
@@ -374,11 +394,11 @@ struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
 	xspi->mem = *mem;
 	xspi->irq = irq;
 	if (pdata->little_endian) {
-		xspi->read_fn = ioread32;
-		xspi->write_fn = iowrite32;
+		xspi->read_fn = xspi_read32;
+		xspi->write_fn = xspi_write32;
 	} else {
-		xspi->read_fn = ioread32be;
-		xspi->write_fn = iowrite32be;
+		xspi->read_fn = xspi_read32_be;
+		xspi->write_fn = xspi_write32_be;
 	}
 	xspi->bits_per_word = pdata->bits_per_word;
 	if (xspi->bits_per_word == 8) {
diff --git a/drivers/spi/xilinx_spi_of.c b/drivers/spi/xilinx_spi_of.c
index 71dc3adc049..ed34a8d419c 100644
--- a/drivers/spi/xilinx_spi_of.c
+++ b/drivers/spi/xilinx_spi_of.c
@@ -99,7 +99,7 @@ static int __exit xilinx_spi_of_remove(struct of_device *op)
 	return xilinx_spi_remove(op);
 }
 
-static struct of_device_id xilinx_spi_of_match[] = {
+static const struct of_device_id xilinx_spi_of_match[] = {
 	{ .compatible = "xlnx,xps-spi-2.00.a", },
 	{ .compatible = "xlnx,xps-spi-2.00.b", },
 	{}
diff --git a/include/linux/spi/dw_spi.h b/include/linux/spi/dw_spi.h
index 51b3e771a9a..cc813f95a2f 100644
--- a/include/linux/spi/dw_spi.h
+++ b/include/linux/spi/dw_spi.h
@@ -90,6 +90,7 @@ struct dw_spi {
 	unsigned long		paddr;
 	u32			iolen;
 	int			irq;
+	u32			fifo_len;	/* depth of the FIFO buffer */
 	u32			max_freq;	/* max bus freq supported */
 
 	u16			bus_num;
@@ -171,6 +172,10 @@ static inline void spi_chip_sel(struct dw_spi *dws, u16 cs)
 {
 	if (cs > dws->num_cs)
 		return;
+
+	if (dws->cs_control)
+		dws->cs_control(1);
+
 	dw_writel(dws, ser, 1 << cs);
 }