Merge tag 'v3.7-rc8' into spi/next

Linux 3.7-rc8
diff --git a/Documentation/devicetree/bindings/spi/nvidia,tegra20-sflash.txt b/Documentation/devicetree/bindings/spi/nvidia,tegra20-sflash.txt
new file mode 100644
index 0000000..8cf24f6
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/nvidia,tegra20-sflash.txt
@@ -0,0 +1,26 @@
+NVIDIA Tegra20 SFLASH controller.
+
+Required properties:
+- compatible : should be "nvidia,tegra20-sflash".
+- reg: Should contain SFLASH registers location and length.
+- interrupts: Should contain SFLASH interrupts.
+- nvidia,dma-request-selector : The Tegra DMA controller's phandle and
+  request selector for this SFLASH controller.
+
+Recommended properties:
+- spi-max-frequency: Definition as per
+                     Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Example:
+
+spi@7000d600 {
+	compatible = "nvidia,tegra20-sflash";
+	reg = <0x7000c380 0x80>;
+	interrupts = <0 39 0x04>;
+	nvidia,dma-request-selector = <&apbdma 16>;
+	spi-max-frequency = <25000000>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "disabled";
+};
+
diff --git a/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt b/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt
new file mode 100644
index 0000000..f5b1ad1
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/nvidia,tegra20-slink.txt
@@ -0,0 +1,26 @@
+NVIDIA Tegra20/Tegra30 SLINK controller.
+
+Required properties:
+- compatible : should be "nvidia,tegra20-slink", "nvidia,tegra30-slink".
+- reg: Should contain SLINK registers location and length.
+- interrupts: Should contain SLINK interrupts.
+- nvidia,dma-request-selector : The Tegra DMA controller's phandle and
+  request selector for this SLINK controller.
+
+Recommended properties:
+- spi-max-frequency: Definition as per
+                     Documentation/devicetree/bindings/spi/spi-bus.txt
+
+Example:
+
+slink@7000d600 {
+	compatible = "nvidia,tegra20-slink";
+	reg = <0x7000d600 0x200>;
+	interrupts = <0 82 0x04>;
+	nvidia,dma-request-selector = <&apbdma 16>;
+	spi-max-frequency = <25000000>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	status = "disabled";
+};
+
diff --git a/Documentation/devicetree/bindings/spi/omap-spi.txt b/Documentation/devicetree/bindings/spi/omap-spi.txt
index 81df374..938809c 100644
--- a/Documentation/devicetree/bindings/spi/omap-spi.txt
+++ b/Documentation/devicetree/bindings/spi/omap-spi.txt
@@ -6,7 +6,9 @@
   - "ti,omap4-spi" for OMAP4+.
 - ti,spi-num-cs : Number of chipselect supported  by the instance.
 - ti,hwmods: Name of the hwmod associated to the McSPI
-
+- ti,pindir-d0-out-d1-in: Select the D0 pin as output and D1 as
+			  input. The default is D0 as input and
+			  D1 as output.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/spi/spi-bus.txt b/Documentation/devicetree/bindings/spi/spi-bus.txt
index d2c33d0..296015e 100644
--- a/Documentation/devicetree/bindings/spi/spi-bus.txt
+++ b/Documentation/devicetree/bindings/spi/spi-bus.txt
@@ -12,6 +12,7 @@
 - #size-cells     - should be zero.
 - compatible      - name of SPI bus controller following generic names
     		recommended practice.
+- cs-gpios	  - (optional) gpios chip select.
 No other properties are required in the SPI bus node.  It is assumed
 that a driver for an SPI bus device will understand that it is an SPI bus.
 However, the binding does not attempt to define the specific method for
@@ -24,6 +25,22 @@
 Optional property:
 - num-cs : total number of chipselects
 
+If cs-gpios is used the number of chip select will automatically increased
+with max(cs-gpios > hw cs)
+
+So if for example the controller has 2 CS lines, and the cs-gpios
+property looks like this:
+
+cs-gpios = <&gpio1 0 0> <0> <&gpio1 1 0> <&gpio1 2 0>;
+
+Then it should be configured so that num_chipselect = 4 with the
+following mapping:
+
+cs0 : &gpio1 0 0
+cs1 : native
+cs2 : &gpio1 1 0
+cs3 : &gpio1 2 0
+
 SPI slave nodes must be children of the SPI master node and can
 contain the following properties.
 - reg             - (required) chip select address of device.
@@ -36,6 +53,11 @@
     		shifted clock phase (CPHA) mode
 - spi-cs-high     - (optional) Empty property indicating device requires
     		chip select active high
+- spi-3wire       - (optional) Empty property indicating device requires
+    		    3-wire mode.
+
+If a gpio chipselect is used for the SPI slave the gpio number will be passed
+via the cs_gpio
 
 SPI example for an MPC5200 SPI bus:
 	spi@f00 {
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 1acae35..2e188e1 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -123,6 +123,13 @@
 	  inexpensive battery powered microcontroller evaluation board.
 	  This same cable can be used to flash new firmware.
 
+config SPI_CLPS711X
+	tristate "CLPS711X host SPI controller"
+	depends on ARCH_CLPS711X
+	help
+	  This enables dedicated general purpose SPI/Microwire1-compatible
+	  master mode interface (SSI1) for CLPS711X-based CPUs.
+
 config SPI_COLDFIRE_QSPI
 	tristate "Freescale Coldfire QSPI controller"
 	depends on (M520x || M523x || M5249 || M525x || M527x || M528x || M532x)
@@ -341,10 +348,10 @@
 
 config SPI_SH_MSIOF
 	tristate "SuperH MSIOF SPI controller"
-	depends on SUPERH && HAVE_CLK
+	depends on (SUPERH || ARCH_SHMOBILE) && HAVE_CLK
 	select SPI_BITBANG
 	help
-	  SPI driver for SuperH MSIOF blocks.
+	  SPI driver for SuperH and SH Mobile MSIOF blocks.
 
 config SPI_SH
 	tristate "SuperH SPI controller"
@@ -372,12 +379,6 @@
 	help
 	  SPI driver for CSR SiRFprimaII SoCs
 
-config SPI_STMP3XXX
-	tristate "Freescale STMP37xx/378x SPI/SSP controller"
-	depends on ARCH_STMP3XXX
-	help
-	  SPI driver for Freescale STMP37xx/378x SoC SSP interface
-
 config SPI_MXS
 	tristate "Freescale MXS SPI controller"
 	depends on ARCH_MXS
@@ -385,6 +386,20 @@
 	help
 	  SPI driver for Freescale MXS devices.
 
+config SPI_TEGRA20_SFLASH
+	tristate "Nvidia Tegra20 Serial flash Controller"
+	depends on ARCH_TEGRA
+	help
+	  SPI driver for Nvidia Tegra20 Serial flash Controller interface.
+	  The main usecase of this controller is to use spi flash as boot
+	  device.
+
+config SPI_TEGRA20_SLINK
+	tristate "Nvidia Tegra20/Tegra30 SLINK Controller"
+	depends on ARCH_TEGRA && TEGRA20_APB_DMA
+	help
+	  SPI driver for Nvidia Tegra20/Tegra30 SLINK Controller interface.
+
 config SPI_TI_SSP
 	tristate "TI Sequencer Serial Port - SPI Support"
 	depends on MFD_TI_SSP
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index c48df47..64e970b 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -19,6 +19,7 @@
 obj-$(CONFIG_SPI_BFIN_SPORT)		+= spi-bfin-sport.o
 obj-$(CONFIG_SPI_BITBANG)		+= spi-bitbang.o
 obj-$(CONFIG_SPI_BUTTERFLY)		+= spi-butterfly.o
+obj-$(CONFIG_SPI_CLPS711X)		+= spi-clps711x.o
 obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= spi-coldfire-qspi.o
 obj-$(CONFIG_SPI_DAVINCI)		+= spi-davinci.o
 obj-$(CONFIG_SPI_DESIGNWARE)		+= spi-dw.o
@@ -59,11 +60,11 @@
 obj-$(CONFIG_SPI_SH_MSIOF)		+= spi-sh-msiof.o
 obj-$(CONFIG_SPI_SH_SCI)		+= spi-sh-sci.o
 obj-$(CONFIG_SPI_SIRF)		+= spi-sirf.o
-obj-$(CONFIG_SPI_STMP3XXX)		+= spi-stmp.o
+obj-$(CONFIG_SPI_TEGRA20_SFLASH)	+= spi-tegra20-sflash.o
+obj-$(CONFIG_SPI_TEGRA20_SLINK)		+= spi-tegra20-slink.o
 obj-$(CONFIG_SPI_TI_SSP)		+= spi-ti-ssp.o
 obj-$(CONFIG_SPI_TLE62X0)		+= spi-tle62x0.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi-topcliff-pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi-txx9.o
 obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
-
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index a9f4049..6d97047 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -36,7 +36,6 @@
 #include <bcm63xx_dev_spi.h>
 
 #define PFX		KBUILD_MODNAME
-#define DRV_VER		"0.1.2"
 
 struct bcm63xx_spi {
 	struct completion	done;
@@ -170,13 +169,6 @@
 		return -EINVAL;
 	}
 
-	ret = bcm63xx_spi_check_transfer(spi, NULL);
-	if (ret < 0) {
-		dev_err(&spi->dev, "setup: unsupported mode bits %x\n",
-			spi->mode & ~MODEBITS);
-		return ret;
-	}
-
 	dev_dbg(&spi->dev, "%s, mode %d, %u bits/w, %u nsec/bit\n",
 		__func__, spi->mode & MODEBITS, spi->bits_per_word, 0);
 
@@ -441,8 +433,8 @@
 		goto out_clk_disable;
 	}
 
-	dev_info(dev, "at 0x%08x (irq %d, FIFOs size %d) v%s\n",
-		 r->start, irq, bs->fifo_size, DRV_VER);
+	dev_info(dev, "at 0x%08x (irq %d, FIFOs size %d)\n",
+		 r->start, irq, bs->fifo_size);
 
 	return 0;
 
@@ -485,6 +477,8 @@
 			platform_get_drvdata(to_platform_device(dev));
 	struct bcm63xx_spi *bs = spi_master_get_devdata(master);
 
+	spi_master_suspend(master);
+
 	clk_disable(bs->clk);
 
 	return 0;
@@ -498,6 +492,8 @@
 
 	clk_enable(bs->clk);
 
+	spi_master_resume(master);
+
 	return 0;
 }
 
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index aef59b1..8b3d8ef 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -260,11 +260,11 @@
 	struct spi_bitbang	*bitbang =
 		container_of(work, struct spi_bitbang, work);
 	unsigned long		flags;
+	struct spi_message	*m, *_m;
 
 	spin_lock_irqsave(&bitbang->lock, flags);
 	bitbang->busy = 1;
-	while (!list_empty(&bitbang->queue)) {
-		struct spi_message	*m;
+	list_for_each_entry_safe(m, _m, &bitbang->queue, queue) {
 		struct spi_device	*spi;
 		unsigned		nsecs;
 		struct spi_transfer	*t = NULL;
@@ -273,9 +273,7 @@
 		int			status;
 		int			do_setup = -1;
 
-		m = container_of(bitbang->queue.next, struct spi_message,
-				queue);
-		list_del_init(&m->queue);
+		list_del(&m->queue);
 		spin_unlock_irqrestore(&bitbang->lock, flags);
 
 		/* FIXME this is made-up ... the correct value is known to
@@ -346,17 +344,14 @@
 			if (t->delay_usecs)
 				udelay(t->delay_usecs);
 
-			if (!cs_change)
-				continue;
-			if (t->transfer_list.next == &m->transfers)
-				break;
-
-			/* sometimes a short mid-message deselect of the chip
-			 * may be needed to terminate a mode or command
-			 */
-			ndelay(nsecs);
-			bitbang->chipselect(spi, BITBANG_CS_INACTIVE);
-			ndelay(nsecs);
+			if (cs_change && !list_is_last(&t->transfer_list, &m->transfers)) {
+				/* sometimes a short mid-message deselect of the chip
+				 * may be needed to terminate a mode or command
+				 */
+				ndelay(nsecs);
+				bitbang->chipselect(spi, BITBANG_CS_INACTIVE);
+				ndelay(nsecs);
+			}
 		}
 
 		m->status = status;
diff --git a/drivers/spi/spi-clps711x.c b/drivers/spi/spi-clps711x.c
new file mode 100644
index 0000000..59677eb
--- /dev/null
+++ b/drivers/spi/spi-clps711x.c
@@ -0,0 +1,296 @@
+/*
+ *  CLPS711X SPI bus driver
+ *
+ *  Copyright (C) 2012 Alexander Shiyan <shc_work@mail.ru>
+ *
+ * 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.
+ */
+
+#include <linux/io.h>
+#include <linux/clk.h>
+#include <linux/init.h>
+#include <linux/gpio.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/platform_data/spi-clps711x.h>
+
+#include <mach/hardware.h>
+
+#define DRIVER_NAME	"spi-clps711x"
+
+struct spi_clps711x_data {
+	struct completion	done;
+
+	struct clk		*spi_clk;
+	u32			max_speed_hz;
+
+	u8			*tx_buf;
+	u8			*rx_buf;
+	int			count;
+	int			len;
+
+	int			chipselect[0];
+};
+
+static int spi_clps711x_setup(struct spi_device *spi)
+{
+	struct spi_clps711x_data *hw = spi_master_get_devdata(spi->master);
+
+	if (spi->bits_per_word != 8) {
+		dev_err(&spi->dev, "Unsupported master bus width %i\n",
+			spi->bits_per_word);
+		return -EINVAL;
+	}
+
+	/* We are expect that SPI-device is not selected */
+	gpio_direction_output(hw->chipselect[spi->chip_select],
+			      !(spi->mode & SPI_CS_HIGH));
+
+	return 0;
+}
+
+static void spi_clps711x_setup_mode(struct spi_device *spi)
+{
+	/* Setup edge for transfer */
+	if (spi->mode & SPI_CPHA)
+		clps_writew(clps_readw(SYSCON3) | SYSCON3_ADCCKNSEN, SYSCON3);
+	else
+		clps_writew(clps_readw(SYSCON3) & ~SYSCON3_ADCCKNSEN, SYSCON3);
+}
+
+static int spi_clps711x_setup_xfer(struct spi_device *spi,
+				   struct spi_transfer *xfer)
+{
+	u32 speed = xfer->speed_hz ? : spi->max_speed_hz;
+	u8 bpw = xfer->bits_per_word ? : spi->bits_per_word;
+	struct spi_clps711x_data *hw = spi_master_get_devdata(spi->master);
+
+	if (bpw != 8) {
+		dev_err(&spi->dev, "Unsupported master bus width %i\n", bpw);
+		return -EINVAL;
+	}
+
+	/* Setup SPI frequency divider */
+	if (!speed || (speed >= hw->max_speed_hz))
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(3), SYSCON1);
+	else if (speed >= (hw->max_speed_hz / 2))
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(2), SYSCON1);
+	else if (speed >= (hw->max_speed_hz / 8))
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(1), SYSCON1);
+	else
+		clps_writel((clps_readl(SYSCON1) & ~SYSCON1_ADCKSEL_MASK) |
+			    SYSCON1_ADCKSEL(0), SYSCON1);
+
+	return 0;
+}
+
+static int spi_clps711x_transfer_one_message(struct spi_master *master,
+					     struct spi_message *msg)
+{
+	struct spi_clps711x_data *hw = spi_master_get_devdata(master);
+	struct spi_transfer *xfer;
+	int status = 0, cs = hw->chipselect[msg->spi->chip_select];
+	u32 data;
+
+	spi_clps711x_setup_mode(msg->spi);
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (spi_clps711x_setup_xfer(msg->spi, xfer)) {
+			status = -EINVAL;
+			goto out_xfr;
+		}
+
+		gpio_set_value(cs, !!(msg->spi->mode & SPI_CS_HIGH));
+
+		INIT_COMPLETION(hw->done);
+
+		hw->count = 0;
+		hw->len = xfer->len;
+		hw->tx_buf = (u8 *)xfer->tx_buf;
+		hw->rx_buf = (u8 *)xfer->rx_buf;
+
+		/* Initiate transfer */
+		data = hw->tx_buf ? hw->tx_buf[hw->count] : 0;
+		clps_writel(data | SYNCIO_FRMLEN(8) | SYNCIO_TXFRMEN, SYNCIO);
+
+		wait_for_completion(&hw->done);
+
+		if (xfer->delay_usecs)
+			udelay(xfer->delay_usecs);
+
+		if (xfer->cs_change ||
+		    list_is_last(&xfer->transfer_list, &msg->transfers))
+			gpio_set_value(cs, !(msg->spi->mode & SPI_CS_HIGH));
+
+		msg->actual_length += xfer->len;
+	}
+
+out_xfr:
+	msg->status = status;
+	spi_finalize_current_message(master);
+
+	return 0;
+}
+
+static irqreturn_t spi_clps711x_isr(int irq, void *dev_id)
+{
+	struct spi_clps711x_data *hw = (struct spi_clps711x_data *)dev_id;
+	u32 data;
+
+	/* Handle RX */
+	data = clps_readb(SYNCIO);
+	if (hw->rx_buf)
+		hw->rx_buf[hw->count] = (u8)data;
+
+	hw->count++;
+
+	/* Handle TX */
+	if (hw->count < hw->len) {
+		data = hw->tx_buf ? hw->tx_buf[hw->count] : 0;
+		clps_writel(data | SYNCIO_FRMLEN(8) | SYNCIO_TXFRMEN, SYNCIO);
+	} else
+		complete(&hw->done);
+
+	return IRQ_HANDLED;
+}
+
+static int __devinit spi_clps711x_probe(struct platform_device *pdev)
+{
+	int i, ret;
+	struct spi_master *master;
+	struct spi_clps711x_data *hw;
+	struct spi_clps711x_pdata *pdata = dev_get_platdata(&pdev->dev);
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data supplied\n");
+		return -EINVAL;
+	}
+
+	if (pdata->num_chipselect < 1) {
+		dev_err(&pdev->dev, "At least one CS must be defined\n");
+		return -EINVAL;
+	}
+
+	master = spi_alloc_master(&pdev->dev,
+				  sizeof(struct spi_clps711x_data) +
+				  sizeof(int) * pdata->num_chipselect);
+	if (!master) {
+		dev_err(&pdev->dev, "SPI allocating memory error\n");
+		return -ENOMEM;
+	}
+
+	master->bus_num = pdev->id;
+	master->mode_bits = SPI_CPHA | SPI_CS_HIGH;
+	master->num_chipselect = pdata->num_chipselect;
+	master->setup = spi_clps711x_setup;
+	master->transfer_one_message = spi_clps711x_transfer_one_message;
+
+	hw = spi_master_get_devdata(master);
+
+	for (i = 0; i < master->num_chipselect; i++) {
+		hw->chipselect[i] = pdata->chipselect[i];
+		if (!gpio_is_valid(hw->chipselect[i])) {
+			dev_err(&pdev->dev, "Invalid CS GPIO %i\n", i);
+			ret = -EINVAL;
+			goto err_out;
+		}
+		if (gpio_request(hw->chipselect[i], DRIVER_NAME)) {
+			dev_err(&pdev->dev, "Can't get CS GPIO %i\n", i);
+			ret = -EINVAL;
+			goto err_out;
+		}
+	}
+
+	hw->spi_clk = devm_clk_get(&pdev->dev, "spi");
+	if (IS_ERR(hw->spi_clk)) {
+		dev_err(&pdev->dev, "Can't get clocks\n");
+		ret = PTR_ERR(hw->spi_clk);
+		goto err_out;
+	}
+	hw->max_speed_hz = clk_get_rate(hw->spi_clk);
+
+	init_completion(&hw->done);
+	platform_set_drvdata(pdev, master);
+
+	/* Disable extended mode due hardware problems */
+	clps_writew(clps_readw(SYSCON3) & ~SYSCON3_ADCCON, SYSCON3);
+
+	/* Clear possible pending interrupt */
+	clps_readl(SYNCIO);
+
+	ret = devm_request_irq(&pdev->dev, IRQ_SSEOTI, spi_clps711x_isr, 0,
+			       dev_name(&pdev->dev), hw);
+	if (ret) {
+		dev_err(&pdev->dev, "Can't request IRQ\n");
+		clk_put(hw->spi_clk);
+		goto clk_out;
+	}
+
+	ret = spi_register_master(master);
+	if (!ret) {
+		dev_info(&pdev->dev,
+			 "SPI bus driver initialized. Master clock %u Hz\n",
+			 hw->max_speed_hz);
+		return 0;
+	}
+
+	dev_err(&pdev->dev, "Failed to register master\n");
+	devm_free_irq(&pdev->dev, IRQ_SSEOTI, hw);
+
+clk_out:
+	devm_clk_put(&pdev->dev, hw->spi_clk);
+
+err_out:
+	while (--i >= 0)
+		if (gpio_is_valid(hw->chipselect[i]))
+			gpio_free(hw->chipselect[i]);
+
+	platform_set_drvdata(pdev, NULL);
+	spi_master_put(master);
+	kfree(master);
+
+	return ret;
+}
+
+static int __devexit spi_clps711x_remove(struct platform_device *pdev)
+{
+	int i;
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_clps711x_data *hw = spi_master_get_devdata(master);
+
+	devm_free_irq(&pdev->dev, IRQ_SSEOTI, hw);
+
+	for (i = 0; i < master->num_chipselect; i++)
+		if (gpio_is_valid(hw->chipselect[i]))
+			gpio_free(hw->chipselect[i]);
+
+	devm_clk_put(&pdev->dev, hw->spi_clk);
+	platform_set_drvdata(pdev, NULL);
+	spi_unregister_master(master);
+	kfree(master);
+
+	return 0;
+}
+
+static struct platform_driver clps711x_spi_driver = {
+	.driver	= {
+		.name	= DRIVER_NAME,
+		.owner	= THIS_MODULE,
+	},
+	.probe	= spi_clps711x_probe,
+	.remove	= __devexit_p(spi_clps711x_remove),
+};
+module_platform_driver(clps711x_spi_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Alexander Shiyan <shc_work@mail.ru>");
+MODULE_DESCRIPTION("CLPS711X SPI bus driver");
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 3542fdc..8501384 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -39,7 +39,6 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
-#include <linux/err.h>
 
 #include <linux/spi/spi.h>
 
@@ -130,6 +129,7 @@
 	struct omap2_mcspi_dma	*dma_channels;
 	struct device		*dev;
 	struct omap2_mcspi_regs ctx;
+	unsigned int		pin_dir:1;
 };
 
 struct omap2_mcspi_cs {
@@ -323,19 +323,11 @@
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_dma  *mcspi_dma;
 	unsigned int		count;
-	u8			* rx;
-	const u8		* tx;
-	void __iomem		*chstat_reg;
-	struct omap2_mcspi_cs	*cs = spi->controller_state;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
 	count = xfer->len;
 
-	rx = xfer->rx_buf;
-	tx = xfer->tx_buf;
-	chstat_reg = cs->base + OMAP2_MCSPI_CHSTAT0;
-
 	if (mcspi_dma->dma_tx) {
 		struct dma_async_tx_descriptor *tx;
 		struct scatterlist sg;
@@ -359,19 +351,6 @@
 	dma_async_issue_pending(mcspi_dma->dma_tx);
 	omap2_mcspi_set_dma_req(spi, 0, 1);
 
-	wait_for_completion(&mcspi_dma->dma_tx_completion);
-	dma_unmap_single(mcspi->dev, xfer->tx_dma, count,
-			 DMA_TO_DEVICE);
-
-	/* for TX_ONLY mode, be sure all words have shifted out */
-	if (rx == NULL) {
-		if (mcspi_wait_for_reg_bit(chstat_reg,
-					OMAP2_MCSPI_CHSTAT_TXS) < 0)
-			dev_err(&spi->dev, "TXS timed out\n");
-		else if (mcspi_wait_for_reg_bit(chstat_reg,
-					OMAP2_MCSPI_CHSTAT_EOT) < 0)
-			dev_err(&spi->dev, "EOT timed out\n");
-	}
 }
 
 static unsigned
@@ -492,6 +471,7 @@
 	struct dma_slave_config	cfg;
 	enum dma_slave_buswidth width;
 	unsigned es;
+	void __iomem		*chstat_reg;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
@@ -526,8 +506,24 @@
 		omap2_mcspi_tx_dma(spi, xfer, cfg);
 
 	if (rx != NULL)
-		return omap2_mcspi_rx_dma(spi, xfer, cfg, es);
+		count = omap2_mcspi_rx_dma(spi, xfer, cfg, es);
 
+	if (tx != NULL) {
+		chstat_reg = cs->base + OMAP2_MCSPI_CHSTAT0;
+		wait_for_completion(&mcspi_dma->dma_tx_completion);
+		dma_unmap_single(mcspi->dev, xfer->tx_dma, xfer->len,
+				 DMA_TO_DEVICE);
+
+		/* for TX_ONLY mode, be sure all words have shifted out */
+		if (rx == NULL) {
+			if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_TXS) < 0)
+				dev_err(&spi->dev, "TXS timed out\n");
+			else if (mcspi_wait_for_reg_bit(chstat_reg,
+						OMAP2_MCSPI_CHSTAT_EOT) < 0)
+				dev_err(&spi->dev, "EOT timed out\n");
+		}
+	}
 	return count;
 }
 
@@ -765,8 +761,15 @@
 	/* standard 4-wire master mode:  SCK, MOSI/out, MISO/in, nCS
 	 * REVISIT: this controller could support SPI_3WIRE mode.
 	 */
-	l &= ~(OMAP2_MCSPI_CHCONF_IS|OMAP2_MCSPI_CHCONF_DPE1);
-	l |= OMAP2_MCSPI_CHCONF_DPE0;
+	if (mcspi->pin_dir == MCSPI_PINDIR_D0_IN_D1_OUT) {
+		l &= ~OMAP2_MCSPI_CHCONF_IS;
+		l &= ~OMAP2_MCSPI_CHCONF_DPE1;
+		l |= OMAP2_MCSPI_CHCONF_DPE0;
+	} else {
+		l |= OMAP2_MCSPI_CHCONF_IS;
+		l |= OMAP2_MCSPI_CHCONF_DPE1;
+		l &= ~OMAP2_MCSPI_CHCONF_DPE0;
+	}
 
 	/* wordlength */
 	l &= ~OMAP2_MCSPI_CHCONF_WL_MASK;
@@ -1167,6 +1170,11 @@
 	master->cleanup = omap2_mcspi_cleanup;
 	master->dev.of_node = node;
 
+	dev_set_drvdata(&pdev->dev, master);
+
+	mcspi = spi_master_get_devdata(master);
+	mcspi->master = master;
+
 	match = of_match_device(omap_mcspi_of_match, &pdev->dev);
 	if (match) {
 		u32 num_cs = 1; /* default number of chipselect */
@@ -1175,19 +1183,17 @@
 		of_property_read_u32(node, "ti,spi-num-cs", &num_cs);
 		master->num_chipselect = num_cs;
 		master->bus_num = bus_num++;
+		if (of_get_property(node, "ti,pindir-d0-out-d1-in", NULL))
+			mcspi->pin_dir = MCSPI_PINDIR_D0_OUT_D1_IN;
 	} else {
 		pdata = pdev->dev.platform_data;
 		master->num_chipselect = pdata->num_cs;
 		if (pdev->id != -1)
 			master->bus_num = pdev->id;
+		mcspi->pin_dir = pdata->pin_dir;
 	}
 	regs_offset = pdata->regs_offset;
 
-	dev_set_drvdata(&pdev->dev, master);
-
-	mcspi = spi_master_get_devdata(master);
-	mcspi->master = master;
-
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (r == NULL) {
 		status = -ENODEV;
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index b17c09c..011186d 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -32,8 +32,12 @@
 #define ORION_SPI_DATA_IN_REG		0x0c
 #define ORION_SPI_INT_CAUSE_REG		0x10
 
+#define ORION_SPI_MODE_CPOL		(1 << 11)
+#define ORION_SPI_MODE_CPHA		(1 << 12)
 #define ORION_SPI_IF_8_16_BIT_MODE	(1 << 5)
 #define ORION_SPI_CLK_PRESCALE_MASK	0x1F
+#define ORION_SPI_MODE_MASK		(ORION_SPI_MODE_CPOL | \
+					 ORION_SPI_MODE_CPHA)
 
 struct orion_spi {
 	struct spi_master	*master;
@@ -123,6 +127,23 @@
 	return 0;
 }
 
+static void
+orion_spi_mode_set(struct spi_device *spi)
+{
+	u32 reg;
+	struct orion_spi *orion_spi;
+
+	orion_spi = spi_master_get_devdata(spi->master);
+
+	reg = readl(spi_reg(orion_spi, ORION_SPI_IF_CONFIG_REG));
+	reg &= ~ORION_SPI_MODE_MASK;
+	if (spi->mode & SPI_CPOL)
+		reg |= ORION_SPI_MODE_CPOL;
+	if (spi->mode & SPI_CPHA)
+		reg |= ORION_SPI_MODE_CPHA;
+	writel(reg, spi_reg(orion_spi, ORION_SPI_IF_CONFIG_REG));
+}
+
 /*
  * called only when no transfer is active on the bus
  */
@@ -142,6 +163,8 @@
 	if ((t != NULL) && t->bits_per_word)
 		bits_per_word = t->bits_per_word;
 
+	orion_spi_mode_set(spi);
+
 	rc = orion_spi_baudrate_set(spi, speed);
 	if (rc)
 		return rc;
@@ -399,7 +422,7 @@
 	}
 
 	/* we support only mode 0, and no options */
-	master->mode_bits = 0;
+	master->mode_bits = SPI_CPHA | SPI_CPOL;
 
 	master->setup = orion_spi_setup;
 	master->transfer_one_message = orion_spi_transfer_one_message;
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index a1db91a..1361868 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -371,6 +371,7 @@
 	/* Two optional pin states - default & sleep */
 	struct pinctrl			*pinctrl;
 	struct pinctrl_state		*pins_default;
+	struct pinctrl_state		*pins_idle;
 	struct pinctrl_state		*pins_sleep;
 	struct spi_master		*master;
 	struct pl022_ssp_controller	*master_info;
@@ -2116,6 +2117,11 @@
 	} else
 		dev_err(dev, "could not get default pinstate\n");
 
+	pl022->pins_idle = pinctrl_lookup_state(pl022->pinctrl,
+					      PINCTRL_STATE_IDLE);
+	if (IS_ERR(pl022->pins_idle))
+		dev_dbg(dev, "could not get idle pinstate\n");
+
 	pl022->pins_sleep = pinctrl_lookup_state(pl022->pinctrl,
 					       PINCTRL_STATE_SLEEP);
 	if (IS_ERR(pl022->pins_sleep))
@@ -2246,10 +2252,9 @@
 		pm_runtime_set_autosuspend_delay(dev,
 			platform_info->autosuspend_delay);
 		pm_runtime_use_autosuspend(dev);
-		pm_runtime_put_autosuspend(dev);
-	} else {
-		pm_runtime_put(dev);
 	}
+	pm_runtime_put(dev);
+
 	return 0;
 
  err_spi_register:
@@ -2303,35 +2308,47 @@
  * the runtime counterparts to handle external resources like
  * clocks, pins and regulators when going to sleep.
  */
-static void pl022_suspend_resources(struct pl022 *pl022)
+static void pl022_suspend_resources(struct pl022 *pl022, bool runtime)
 {
 	int ret;
+	struct pinctrl_state *pins_state;
 
 	clk_disable(pl022->clk);
 
+	pins_state = runtime ? pl022->pins_idle : pl022->pins_sleep;
 	/* Optionally let pins go into sleep states */
-	if (!IS_ERR(pl022->pins_sleep)) {
-		ret = pinctrl_select_state(pl022->pinctrl,
-					   pl022->pins_sleep);
+	if (!IS_ERR(pins_state)) {
+		ret = pinctrl_select_state(pl022->pinctrl, pins_state);
 		if (ret)
-			dev_err(&pl022->adev->dev,
-				"could not set pins to sleep state\n");
+			dev_err(&pl022->adev->dev, "could not set %s pins\n",
+				runtime ? "idle" : "sleep");
 	}
 }
 
-static void pl022_resume_resources(struct pl022 *pl022)
+static void pl022_resume_resources(struct pl022 *pl022, bool runtime)
 {
 	int ret;
 
 	/* Optionaly enable pins to be muxed in and configured */
+	/* First go to the default state */
 	if (!IS_ERR(pl022->pins_default)) {
-		ret = pinctrl_select_state(pl022->pinctrl,
-					   pl022->pins_default);
+		ret = pinctrl_select_state(pl022->pinctrl, pl022->pins_default);
 		if (ret)
 			dev_err(&pl022->adev->dev,
 				"could not set default pins\n");
 	}
 
+	if (!runtime) {
+		/* Then let's idle the pins until the next transfer happens */
+		if (!IS_ERR(pl022->pins_idle)) {
+			ret = pinctrl_select_state(pl022->pinctrl,
+					pl022->pins_idle);
+		if (ret)
+			dev_err(&pl022->adev->dev,
+				"could not set idle pins\n");
+		}
+	}
+
 	clk_enable(pl022->clk);
 }
 #endif
@@ -2347,7 +2364,9 @@
 		dev_warn(dev, "cannot suspend master\n");
 		return ret;
 	}
-	pl022_suspend_resources(pl022);
+
+	pm_runtime_get_sync(dev);
+	pl022_suspend_resources(pl022, false);
 
 	dev_dbg(dev, "suspended\n");
 	return 0;
@@ -2358,7 +2377,8 @@
 	struct pl022 *pl022 = dev_get_drvdata(dev);
 	int ret;
 
-	pl022_resume_resources(pl022);
+	pl022_resume_resources(pl022, false);
+	pm_runtime_put(dev);
 
 	/* Start the queue running */
 	ret = spi_master_resume(pl022->master);
@@ -2376,7 +2396,7 @@
 {
 	struct pl022 *pl022 = dev_get_drvdata(dev);
 
-	pl022_suspend_resources(pl022);
+	pl022_suspend_resources(pl022, true);
 	return 0;
 }
 
@@ -2384,7 +2404,7 @@
 {
 	struct pl022 *pl022 = dev_get_drvdata(dev);
 
-	pl022_resume_resources(pl022);
+	pl022_resume_resources(pl022, true);
 	return 0;
 }
 #endif
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 6e7a805..57900a8 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -516,7 +516,7 @@
 
 	/* Disable Clock */
 	if (sdd->port_conf->clk_from_cmu) {
-		clk_disable(sdd->src_clk);
+		clk_disable_unprepare(sdd->src_clk);
 	} else {
 		val = readl(regs + S3C64XX_SPI_CLK_CFG);
 		val &= ~S3C64XX_SPI_ENCLK_ENABLE;
@@ -564,7 +564,7 @@
 		/* There is half-multiplier before the SPI */
 		clk_set_rate(sdd->src_clk, sdd->cur_speed * 2);
 		/* Enable Clock */
-		clk_enable(sdd->src_clk);
+		clk_prepare_enable(sdd->src_clk);
 	} else {
 		/* Configure Clock */
 		val = readl(regs + S3C64XX_SPI_CLK_CFG);
@@ -1112,7 +1112,7 @@
 			dev_err(dev, "invalid gpio[%d]: %d\n", idx, gpio);
 			goto free_gpio;
 		}
-
+		sdd->gpios[idx] = gpio;
 		ret = gpio_request(gpio, "spi-bus");
 		if (ret) {
 			dev_err(dev, "gpio [%d] request failed: %d\n",
@@ -1302,7 +1302,7 @@
 		goto err3;
 	}
 
-	if (clk_enable(sdd->clk)) {
+	if (clk_prepare_enable(sdd->clk)) {
 		dev_err(&pdev->dev, "Couldn't enable clock 'spi'\n");
 		ret = -EBUSY;
 		goto err4;
@@ -1317,7 +1317,7 @@
 		goto err5;
 	}
 
-	if (clk_enable(sdd->src_clk)) {
+	if (clk_prepare_enable(sdd->src_clk)) {
 		dev_err(&pdev->dev, "Couldn't enable clock '%s'\n", clk_name);
 		ret = -EBUSY;
 		goto err6;
@@ -1361,11 +1361,11 @@
 err8:
 	free_irq(irq, sdd);
 err7:
-	clk_disable(sdd->src_clk);
+	clk_disable_unprepare(sdd->src_clk);
 err6:
 	clk_put(sdd->src_clk);
 err5:
-	clk_disable(sdd->clk);
+	clk_disable_unprepare(sdd->clk);
 err4:
 	clk_put(sdd->clk);
 err3:
@@ -1393,10 +1393,10 @@
 
 	free_irq(platform_get_irq(pdev, 0), sdd);
 
-	clk_disable(sdd->src_clk);
+	clk_disable_unprepare(sdd->src_clk);
 	clk_put(sdd->src_clk);
 
-	clk_disable(sdd->clk);
+	clk_disable_unprepare(sdd->clk);
 	clk_put(sdd->clk);
 
 	if (!sdd->cntrlr_info->cfg_gpio && pdev->dev.of_node)
@@ -1417,8 +1417,8 @@
 	spi_master_suspend(master);
 
 	/* Disable the clock */
-	clk_disable(sdd->src_clk);
-	clk_disable(sdd->clk);
+	clk_disable_unprepare(sdd->src_clk);
+	clk_disable_unprepare(sdd->clk);
 
 	if (!sdd->cntrlr_info->cfg_gpio && dev->of_node)
 		s3c64xx_spi_dt_gpio_free(sdd);
@@ -1440,8 +1440,8 @@
 		sci->cfg_gpio();
 
 	/* Enable the clock */
-	clk_enable(sdd->src_clk);
-	clk_enable(sdd->clk);
+	clk_prepare_enable(sdd->src_clk);
+	clk_prepare_enable(sdd->clk);
 
 	s3c64xx_spi_hwinit(sdd, sdd->port_id);
 
@@ -1457,8 +1457,8 @@
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
 
-	clk_disable(sdd->clk);
-	clk_disable(sdd->src_clk);
+	clk_disable_unprepare(sdd->clk);
+	clk_disable_unprepare(sdd->src_clk);
 
 	return 0;
 }
@@ -1468,8 +1468,8 @@
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct s3c64xx_spi_driver_data *sdd = spi_master_get_devdata(master);
 
-	clk_enable(sdd->src_clk);
-	clk_enable(sdd->clk);
+	clk_prepare_enable(sdd->src_clk);
+	clk_prepare_enable(sdd->clk);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-sh-hspi.c b/drivers/spi/spi-sh-hspi.c
index 796c077..47c4bee 100644
--- a/drivers/spi/spi-sh-hspi.c
+++ b/drivers/spi/spi-sh-hspi.c
@@ -68,6 +68,16 @@
 	return ioread32(hspi->addr + reg);
 }
 
+static void hspi_bit_set(struct hspi_priv *hspi, int reg, u32 mask, u32 set)
+{
+	u32 val = hspi_read(hspi, reg);
+
+	val &= ~mask;
+	val |= set & mask;
+
+	hspi_write(hspi, reg, val);
+}
+
 /*
  *		transfer function
  */
@@ -105,6 +115,13 @@
 	return 0;
 }
 
+#define hspi_hw_cs_enable(hspi)		hspi_hw_cs_ctrl(hspi, 0)
+#define hspi_hw_cs_disable(hspi)	hspi_hw_cs_ctrl(hspi, 1)
+static void hspi_hw_cs_ctrl(struct hspi_priv *hspi, int hi)
+{
+	hspi_bit_set(hspi, SPSCR, (1 << 6), (hi) << 6);
+}
+
 static void hspi_hw_setup(struct hspi_priv *hspi,
 			  struct spi_message *msg,
 			  struct spi_transfer *t)
@@ -155,7 +172,7 @@
 
 	hspi_write(hspi, SPCR, spcr);
 	hspi_write(hspi, SPSR, 0x0);
-	hspi_write(hspi, SPSCR, 0x1);	/* master mode */
+	hspi_write(hspi, SPSCR, 0x21);	/* master mode / CS control */
 }
 
 static int hspi_transfer_one_message(struct spi_master *master,
@@ -166,12 +183,21 @@
 	u32 tx;
 	u32 rx;
 	int ret, i;
+	unsigned int cs_change;
+	const int nsecs = 50;
 
 	dev_dbg(hspi->dev, "%s\n", __func__);
 
+	cs_change = 1;
 	ret = 0;
 	list_for_each_entry(t, &msg->transfers, transfer_list) {
-		hspi_hw_setup(hspi, msg, t);
+
+		if (cs_change) {
+			hspi_hw_setup(hspi, msg, t);
+			hspi_hw_cs_enable(hspi);
+			ndelay(nsecs);
+		}
+		cs_change = t->cs_change;
 
 		for (i = 0; i < t->len; i++) {
 
@@ -198,9 +224,22 @@
 		}
 
 		msg->actual_length += t->len;
+
+		if (t->delay_usecs)
+			udelay(t->delay_usecs);
+
+		if (cs_change) {
+			ndelay(nsecs);
+			hspi_hw_cs_disable(hspi);
+			ndelay(nsecs);
+		}
 	}
 
 	msg->status = ret;
+	if (!cs_change) {
+		ndelay(nsecs);
+		hspi_hw_cs_disable(hspi);
+	}
 	spi_finalize_current_message(master);
 
 	return ret;
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 1f466bc..96358d0 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -597,7 +597,6 @@
 	struct resource	*r;
 	struct spi_master *master;
 	struct sh_msiof_spi_priv *p;
-	char clk_name[16];
 	int i;
 	int ret;
 
@@ -614,10 +613,9 @@
 	p->info = pdev->dev.platform_data;
 	init_completion(&p->done);
 
-	snprintf(clk_name, sizeof(clk_name), "msiof%d", pdev->id);
-	p->clk = clk_get(&pdev->dev, clk_name);
+	p->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(p->clk)) {
-		dev_err(&pdev->dev, "cannot get clock \"%s\"\n", clk_name);
+		dev_err(&pdev->dev, "cannot get clock\n");
 		ret = PTR_ERR(p->clk);
 		goto err1;
 	}
diff --git a/drivers/spi/spi-stmp.c b/drivers/spi/spi-stmp.c
deleted file mode 100644
index 911e904..0000000
--- a/drivers/spi/spi-stmp.c
+++ /dev/null
@@ -1,664 +0,0 @@
-/*
- * Freescale STMP378X SPI master driver
- *
- * Author: dmitry pervushin <dimka@embeddedalley.com>
- *
- * Copyright 2008 Freescale Semiconductor, Inc. All Rights Reserved.
- * Copyright 2008 Embedded Alley Solutions, Inc All Rights Reserved.
- */
-
-/*
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
- *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
- */
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/spi/spi.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/dma-mapping.h>
-#include <linux/delay.h>
-
-#include <mach/platform.h>
-#include <mach/stmp3xxx.h>
-#include <mach/dma.h>
-#include <mach/regs-ssp.h>
-#include <mach/regs-apbh.h>
-
-
-/* 0 means DMA mode(recommended, default), !0 - PIO mode */
-static int pio;
-static int clock;
-
-/* default timeout for busy waits is 2 seconds */
-#define STMP_SPI_TIMEOUT	(2 * HZ)
-
-struct stmp_spi {
-	int		id;
-
-	void *  __iomem regs;	/* vaddr of the control registers */
-
-	int		irq, err_irq;
-	u32		dma;
-	struct stmp3xxx_dma_descriptor d;
-
-	u32		speed_khz;
-	u32		saved_timings;
-	u32		divider;
-
-	struct clk	*clk;
-	struct device	*master_dev;
-
-	struct work_struct work;
-	struct workqueue_struct *workqueue;
-
-	/* lock protects queue access */
-	spinlock_t lock;
-	struct list_head queue;
-
-	struct completion done;
-};
-
-#define busy_wait(cond)							\
-	({								\
-	unsigned long end_jiffies = jiffies + STMP_SPI_TIMEOUT;		\
-	bool succeeded = false;						\
-	do {								\
-		if (cond) {						\
-			succeeded = true;				\
-			break;						\
-		}							\
-		cpu_relax();						\
-	} while (time_before(jiffies, end_jiffies));			\
-	succeeded;							\
-	})
-
-/**
- * stmp_spi_init_hw
- * Initialize the SSP port
- */
-static int stmp_spi_init_hw(struct stmp_spi *ss)
-{
-	int err = 0;
-	void *pins = ss->master_dev->platform_data;
-
-	err = stmp3xxx_request_pin_group(pins, dev_name(ss->master_dev));
-	if (err)
-		goto out;
-
-	ss->clk = clk_get(NULL, "ssp");
-	if (IS_ERR(ss->clk)) {
-		err = PTR_ERR(ss->clk);
-		goto out_free_pins;
-	}
-	clk_enable(ss->clk);
-
-	stmp3xxx_reset_block(ss->regs, false);
-	stmp3xxx_dma_reset_channel(ss->dma);
-
-	return 0;
-
-out_free_pins:
-	stmp3xxx_release_pin_group(pins, dev_name(ss->master_dev));
-out:
-	return err;
-}
-
-static void stmp_spi_release_hw(struct stmp_spi *ss)
-{
-	void *pins = ss->master_dev->platform_data;
-
-	if (ss->clk && !IS_ERR(ss->clk)) {
-		clk_disable(ss->clk);
-		clk_put(ss->clk);
-	}
-	stmp3xxx_release_pin_group(pins, dev_name(ss->master_dev));
-}
-
-static int stmp_spi_setup_transfer(struct spi_device *spi,
-		struct spi_transfer *t)
-{
-	u8 bits_per_word;
-	u32 hz;
-	struct stmp_spi *ss = spi_master_get_devdata(spi->master);
-	u16 rate;
-
-	bits_per_word = spi->bits_per_word;
-	if (t && t->bits_per_word)
-		bits_per_word = t->bits_per_word;
-
-	/*
-	 * Calculate speed:
-	 *	- by default, use maximum speed from ssp clk
-	 *	- if device overrides it, use it
-	 *	- if transfer specifies other speed, use transfer's one
-	 */
-	hz = 1000 * ss->speed_khz / ss->divider;
-	if (spi->max_speed_hz)
-		hz = min(hz, spi->max_speed_hz);
-	if (t && t->speed_hz)
-		hz = min(hz, t->speed_hz);
-
-	if (hz == 0) {
-		dev_err(&spi->dev, "Cannot continue with zero clock\n");
-		return -EINVAL;
-	}
-
-	if (bits_per_word != 8) {
-		dev_err(&spi->dev, "%s, unsupported bits_per_word=%d\n",
-			__func__, bits_per_word);
-		return -EINVAL;
-	}
-
-	dev_dbg(&spi->dev, "Requested clk rate = %uHz, max = %uHz/%d = %uHz\n",
-		hz, ss->speed_khz, ss->divider,
-		ss->speed_khz * 1000 / ss->divider);
-
-	if (ss->speed_khz * 1000 / ss->divider < hz) {
-		dev_err(&spi->dev, "%s, unsupported clock rate %uHz\n",
-			__func__, hz);
-		return -EINVAL;
-	}
-
-	rate = 1000 * ss->speed_khz/ss->divider/hz;
-
-	writel(BF(ss->divider, SSP_TIMING_CLOCK_DIVIDE)		|
-	       BF(rate - 1, SSP_TIMING_CLOCK_RATE),
-	       HW_SSP_TIMING + ss->regs);
-
-	writel(BF(1 /* mode SPI */, SSP_CTRL1_SSP_MODE)		|
-	       BF(4 /* 8 bits   */, SSP_CTRL1_WORD_LENGTH)	|
-	       ((spi->mode & SPI_CPOL) ? BM_SSP_CTRL1_POLARITY : 0) |
-	       ((spi->mode & SPI_CPHA) ? BM_SSP_CTRL1_PHASE : 0) |
-	       (pio ? 0 : BM_SSP_CTRL1_DMA_ENABLE),
-	       ss->regs + HW_SSP_CTRL1);
-
-	return 0;
-}
-
-static int stmp_spi_setup(struct spi_device *spi)
-{
-	/* spi_setup() does basic checks,
-	 * stmp_spi_setup_transfer() does more later
-	 */
-	if (spi->bits_per_word != 8) {
-		dev_err(&spi->dev, "%s, unsupported bits_per_word=%d\n",
-			__func__, spi->bits_per_word);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static inline u32 stmp_spi_cs(unsigned cs)
-{
-	return  ((cs & 1) ? BM_SSP_CTRL0_WAIT_FOR_CMD : 0) |
-		((cs & 2) ? BM_SSP_CTRL0_WAIT_FOR_IRQ : 0);
-}
-
-static int stmp_spi_txrx_dma(struct stmp_spi *ss, int cs,
-		unsigned char *buf, dma_addr_t dma_buf, int len,
-		int first, int last, bool write)
-{
-	u32 c0 = 0;
-	dma_addr_t spi_buf_dma = dma_buf;
-	int status = 0;
-	enum dma_data_direction dir = write ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
-
-	c0 |= (first ? BM_SSP_CTRL0_LOCK_CS : 0);
-	c0 |= (last ? BM_SSP_CTRL0_IGNORE_CRC : 0);
-	c0 |= (write ? 0 : BM_SSP_CTRL0_READ);
-	c0 |= BM_SSP_CTRL0_DATA_XFER;
-
-	c0 |= stmp_spi_cs(cs);
-
-	c0 |= BF(len, SSP_CTRL0_XFER_COUNT);
-
-	if (!dma_buf)
-		spi_buf_dma = dma_map_single(ss->master_dev, buf, len, dir);
-
-	ss->d.command->cmd =
-		BF(len, APBH_CHn_CMD_XFER_COUNT)	|
-		BF(1, APBH_CHn_CMD_CMDWORDS)		|
-		BM_APBH_CHn_CMD_WAIT4ENDCMD		|
-		BM_APBH_CHn_CMD_IRQONCMPLT		|
-		BF(write ? BV_APBH_CHn_CMD_COMMAND__DMA_READ :
-			   BV_APBH_CHn_CMD_COMMAND__DMA_WRITE,
-		   APBH_CHn_CMD_COMMAND);
-	ss->d.command->pio_words[0] = c0;
-	ss->d.command->buf_ptr = spi_buf_dma;
-
-	stmp3xxx_dma_reset_channel(ss->dma);
-	stmp3xxx_dma_clear_interrupt(ss->dma);
-	stmp3xxx_dma_enable_interrupt(ss->dma);
-	init_completion(&ss->done);
-	stmp3xxx_dma_go(ss->dma, &ss->d, 1);
-	wait_for_completion(&ss->done);
-
-	if (!busy_wait(readl(ss->regs + HW_SSP_CTRL0) & BM_SSP_CTRL0_RUN))
-		status = -ETIMEDOUT;
-
-	if (!dma_buf)
-		dma_unmap_single(ss->master_dev, spi_buf_dma, len, dir);
-
-	return status;
-}
-
-static inline void stmp_spi_enable(struct stmp_spi *ss)
-{
-	stmp3xxx_setl(BM_SSP_CTRL0_LOCK_CS, ss->regs + HW_SSP_CTRL0);
-	stmp3xxx_clearl(BM_SSP_CTRL0_IGNORE_CRC, ss->regs + HW_SSP_CTRL0);
-}
-
-static inline void stmp_spi_disable(struct stmp_spi *ss)
-{
-	stmp3xxx_clearl(BM_SSP_CTRL0_LOCK_CS, ss->regs + HW_SSP_CTRL0);
-	stmp3xxx_setl(BM_SSP_CTRL0_IGNORE_CRC, ss->regs + HW_SSP_CTRL0);
-}
-
-static int stmp_spi_txrx_pio(struct stmp_spi *ss, int cs,
-		unsigned char *buf, int len,
-		bool first, bool last, bool write)
-{
-	if (first)
-		stmp_spi_enable(ss);
-
-	stmp3xxx_setl(stmp_spi_cs(cs), ss->regs + HW_SSP_CTRL0);
-
-	while (len--) {
-		if (last && len <= 0)
-			stmp_spi_disable(ss);
-
-		stmp3xxx_clearl(BM_SSP_CTRL0_XFER_COUNT,
-				ss->regs + HW_SSP_CTRL0);
-		stmp3xxx_setl(1, ss->regs + HW_SSP_CTRL0);
-
-		if (write)
-			stmp3xxx_clearl(BM_SSP_CTRL0_READ,
-					ss->regs + HW_SSP_CTRL0);
-		else
-			stmp3xxx_setl(BM_SSP_CTRL0_READ,
-					ss->regs + HW_SSP_CTRL0);
-
-		/* Run! */
-		stmp3xxx_setl(BM_SSP_CTRL0_RUN, ss->regs + HW_SSP_CTRL0);
-
-		if (!busy_wait(readl(ss->regs + HW_SSP_CTRL0) &
-				BM_SSP_CTRL0_RUN))
-			break;
-
-		if (write)
-			writel(*buf, ss->regs + HW_SSP_DATA);
-
-		/* Set TRANSFER */
-		stmp3xxx_setl(BM_SSP_CTRL0_DATA_XFER, ss->regs + HW_SSP_CTRL0);
-
-		if (!write) {
-			if (busy_wait((readl(ss->regs + HW_SSP_STATUS) &
-					BM_SSP_STATUS_FIFO_EMPTY)))
-				break;
-			*buf = readl(ss->regs + HW_SSP_DATA) & 0xFF;
-		}
-
-		if (!busy_wait(readl(ss->regs + HW_SSP_CTRL0) &
-					BM_SSP_CTRL0_RUN))
-			break;
-
-		/* advance to the next byte */
-		buf++;
-	}
-
-	return len < 0 ? 0 : -ETIMEDOUT;
-}
-
-static int stmp_spi_handle_message(struct stmp_spi *ss, struct spi_message *m)
-{
-	bool first, last;
-	struct spi_transfer *t, *tmp_t;
-	int status = 0;
-	int cs;
-
-	cs = m->spi->chip_select;
-
-	list_for_each_entry_safe(t, tmp_t, &m->transfers, transfer_list) {
-
-		first = (&t->transfer_list == m->transfers.next);
-		last = (&t->transfer_list == m->transfers.prev);
-
-		if (first || t->speed_hz || t->bits_per_word)
-			stmp_spi_setup_transfer(m->spi, t);
-
-		/* reject "not last" transfers which request to change cs */
-		if (t->cs_change && !last) {
-			dev_err(&m->spi->dev,
-				"Message with t->cs_change has been skipped\n");
-			continue;
-		}
-
-		if (t->tx_buf) {
-			status = pio ?
-			   stmp_spi_txrx_pio(ss, cs, (void *)t->tx_buf,
-				   t->len, first, last, true) :
-			   stmp_spi_txrx_dma(ss, cs, (void *)t->tx_buf,
-				   t->tx_dma, t->len, first, last, true);
-#ifdef DEBUG
-			if (t->len < 0x10)
-				print_hex_dump_bytes("Tx ",
-					DUMP_PREFIX_OFFSET,
-					t->tx_buf, t->len);
-			else
-				pr_debug("Tx: %d bytes\n", t->len);
-#endif
-		}
-		if (t->rx_buf) {
-			status = pio ?
-			   stmp_spi_txrx_pio(ss, cs, t->rx_buf,
-				   t->len, first, last, false) :
-			   stmp_spi_txrx_dma(ss, cs, t->rx_buf,
-				   t->rx_dma, t->len, first, last, false);
-#ifdef DEBUG
-			if (t->len < 0x10)
-				print_hex_dump_bytes("Rx ",
-					DUMP_PREFIX_OFFSET,
-					t->rx_buf, t->len);
-			else
-				pr_debug("Rx: %d bytes\n", t->len);
-#endif
-		}
-
-		if (t->delay_usecs)
-			udelay(t->delay_usecs);
-
-		if (status)
-			break;
-
-	}
-	return status;
-}
-
-/**
- * stmp_spi_handle - handle messages from the queue
- */
-static void stmp_spi_handle(struct work_struct *w)
-{
-	struct stmp_spi *ss = container_of(w, struct stmp_spi, work);
-	unsigned long flags;
-	struct spi_message *m;
-
-	spin_lock_irqsave(&ss->lock, flags);
-	while (!list_empty(&ss->queue)) {
-		m = list_entry(ss->queue.next, struct spi_message, queue);
-		list_del_init(&m->queue);
-		spin_unlock_irqrestore(&ss->lock, flags);
-
-		m->status = stmp_spi_handle_message(ss, m);
-		m->complete(m->context);
-
-		spin_lock_irqsave(&ss->lock, flags);
-	}
-	spin_unlock_irqrestore(&ss->lock, flags);
-
-	return;
-}
-
-/**
- * stmp_spi_transfer - perform message transfer.
- * Called indirectly from spi_async, queues all the messages to
- * spi_handle_message.
- * @spi: spi device
- * @m: message to be queued
- */
-static int stmp_spi_transfer(struct spi_device *spi, struct spi_message *m)
-{
-	struct stmp_spi *ss = spi_master_get_devdata(spi->master);
-	unsigned long flags;
-
-	m->status = -EINPROGRESS;
-	spin_lock_irqsave(&ss->lock, flags);
-	list_add_tail(&m->queue, &ss->queue);
-	queue_work(ss->workqueue, &ss->work);
-	spin_unlock_irqrestore(&ss->lock, flags);
-	return 0;
-}
-
-static irqreturn_t stmp_spi_irq(int irq, void *dev_id)
-{
-	struct stmp_spi *ss = dev_id;
-
-	stmp3xxx_dma_clear_interrupt(ss->dma);
-	complete(&ss->done);
-	return IRQ_HANDLED;
-}
-
-static irqreturn_t stmp_spi_irq_err(int irq, void *dev_id)
-{
-	struct stmp_spi *ss = dev_id;
-	u32 c1, st;
-
-	c1 = readl(ss->regs + HW_SSP_CTRL1);
-	st = readl(ss->regs + HW_SSP_STATUS);
-	dev_err(ss->master_dev, "%s: status = 0x%08X, c1 = 0x%08X\n",
-		__func__, st, c1);
-	stmp3xxx_clearl(c1 & 0xCCCC0000, ss->regs + HW_SSP_CTRL1);
-
-	return IRQ_HANDLED;
-}
-
-static int __devinit stmp_spi_probe(struct platform_device *dev)
-{
-	int err = 0;
-	struct spi_master *master;
-	struct stmp_spi *ss;
-	struct resource *r;
-
-	master = spi_alloc_master(&dev->dev, sizeof(struct stmp_spi));
-	if (master == NULL) {
-		err = -ENOMEM;
-		goto out0;
-	}
-	master->flags = SPI_MASTER_HALF_DUPLEX;
-
-	ss = spi_master_get_devdata(master);
-	platform_set_drvdata(dev, master);
-
-	/* Get resources(memory, IRQ) associated with the device */
-	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (r == NULL) {
-		err = -ENODEV;
-		goto out_put_master;
-	}
-	ss->regs = ioremap(r->start, resource_size(r));
-	if (!ss->regs) {
-		err = -EINVAL;
-		goto out_put_master;
-	}
-
-	ss->master_dev = &dev->dev;
-	ss->id = dev->id;
-
-	INIT_WORK(&ss->work, stmp_spi_handle);
-	INIT_LIST_HEAD(&ss->queue);
-	spin_lock_init(&ss->lock);
-
-	ss->workqueue = create_singlethread_workqueue(dev_name(&dev->dev));
-	if (!ss->workqueue) {
-		err = -ENXIO;
-		goto out_put_master;
-	}
-	master->transfer = stmp_spi_transfer;
-	master->setup = stmp_spi_setup;
-
-	/* the spi->mode bits understood by this driver: */
-	master->mode_bits = SPI_CPOL | SPI_CPHA;
-
-	ss->irq = platform_get_irq(dev, 0);
-	if (ss->irq < 0) {
-		err = ss->irq;
-		goto out_put_master;
-	}
-	ss->err_irq = platform_get_irq(dev, 1);
-	if (ss->err_irq < 0) {
-		err = ss->err_irq;
-		goto out_put_master;
-	}
-
-	r = platform_get_resource(dev, IORESOURCE_DMA, 0);
-	if (r == NULL) {
-		err = -ENODEV;
-		goto out_put_master;
-	}
-
-	ss->dma = r->start;
-	err = stmp3xxx_dma_request(ss->dma, &dev->dev, dev_name(&dev->dev));
-	if (err)
-		goto out_put_master;
-
-	err = stmp3xxx_dma_allocate_command(ss->dma, &ss->d);
-	if (err)
-		goto out_free_dma;
-
-	master->bus_num = dev->id;
-	master->num_chipselect = 1;
-
-	/* SPI controller initializations */
-	err = stmp_spi_init_hw(ss);
-	if (err) {
-		dev_dbg(&dev->dev, "cannot initialize hardware\n");
-		goto out_free_dma_desc;
-	}
-
-	if (clock) {
-		dev_info(&dev->dev, "clock rate forced to %d\n", clock);
-		clk_set_rate(ss->clk, clock);
-	}
-	ss->speed_khz = clk_get_rate(ss->clk);
-	ss->divider = 2;
-	dev_info(&dev->dev, "max possible speed %d = %ld/%d kHz\n",
-		ss->speed_khz, clk_get_rate(ss->clk), ss->divider);
-
-	/* Register for SPI interrupt */
-	err = request_irq(ss->irq, stmp_spi_irq, 0,
-			  dev_name(&dev->dev), ss);
-	if (err) {
-		dev_dbg(&dev->dev, "request_irq failed, %d\n", err);
-		goto out_release_hw;
-	}
-
-	/* ..and shared interrupt for all SSP controllers */
-	err = request_irq(ss->err_irq, stmp_spi_irq_err, IRQF_SHARED,
-			  dev_name(&dev->dev), ss);
-	if (err) {
-		dev_dbg(&dev->dev, "request_irq(error) failed, %d\n", err);
-		goto out_free_irq;
-	}
-
-	err = spi_register_master(master);
-	if (err) {
-		dev_dbg(&dev->dev, "cannot register spi master, %d\n", err);
-		goto out_free_irq_2;
-	}
-	dev_info(&dev->dev, "at (mapped) 0x%08X, irq=%d, bus %d, %s mode\n",
-			(u32)ss->regs, ss->irq, master->bus_num,
-			pio ? "PIO" : "DMA");
-	return 0;
-
-out_free_irq_2:
-	free_irq(ss->err_irq, ss);
-out_free_irq:
-	free_irq(ss->irq, ss);
-out_free_dma_desc:
-	stmp3xxx_dma_free_command(ss->dma, &ss->d);
-out_free_dma:
-	stmp3xxx_dma_release(ss->dma);
-out_release_hw:
-	stmp_spi_release_hw(ss);
-out_put_master:
-	if (ss->workqueue)
-		destroy_workqueue(ss->workqueue);
-	if (ss->regs)
-		iounmap(ss->regs);
-	platform_set_drvdata(dev, NULL);
-	spi_master_put(master);
-out0:
-	return err;
-}
-
-static int __devexit stmp_spi_remove(struct platform_device *dev)
-{
-	struct stmp_spi *ss;
-	struct spi_master *master;
-
-	master = spi_master_get(platform_get_drvdata(dev));
-	ss = spi_master_get_devdata(master);
-
-	spi_unregister_master(master);
-
-	free_irq(ss->err_irq, ss);
-	free_irq(ss->irq, ss);
-	stmp3xxx_dma_free_command(ss->dma, &ss->d);
-	stmp3xxx_dma_release(ss->dma);
-	stmp_spi_release_hw(ss);
-	destroy_workqueue(ss->workqueue);
-	iounmap(ss->regs);
-	spi_master_put(master);
-	return 0;
-}
-
-#ifdef CONFIG_PM
-static int stmp_spi_suspend(struct platform_device *pdev, pm_message_t pmsg)
-{
-	struct stmp_spi *ss;
-	struct spi_master *master;
-
-	master = platform_get_drvdata(pdev);
-	ss = spi_master_get_devdata(master);
-
-	ss->saved_timings = readl(HW_SSP_TIMING + ss->regs);
-	clk_disable(ss->clk);
-
-	return 0;
-}
-
-static int stmp_spi_resume(struct platform_device *pdev)
-{
-	struct stmp_spi *ss;
-	struct spi_master *master;
-
-	master = platform_get_drvdata(pdev);
-	ss = spi_master_get_devdata(master);
-
-	clk_enable(ss->clk);
-	stmp3xxx_reset_block(ss->regs, false);
-	writel(ss->saved_timings, ss->regs + HW_SSP_TIMING);
-
-	return 0;
-}
-
-#else
-#define stmp_spi_suspend NULL
-#define stmp_spi_resume  NULL
-#endif
-
-static struct platform_driver stmp_spi_driver = {
-	.probe	= stmp_spi_probe,
-	.remove	= __devexit_p(stmp_spi_remove),
-	.driver = {
-		.name = "stmp3xxx_ssp",
-		.owner = THIS_MODULE,
-	},
-	.suspend = stmp_spi_suspend,
-	.resume  = stmp_spi_resume,
-};
-module_platform_driver(stmp_spi_driver);
-
-module_param(pio, int, S_IRUGO);
-module_param(clock, int, S_IRUGO);
-MODULE_AUTHOR("dmitry pervushin <dpervushin@embeddedalley.com>");
-MODULE_DESCRIPTION("STMP3xxx SPI/SSP driver");
-MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-tegra20-sflash.c b/drivers/spi/spi-tegra20-sflash.c
new file mode 100644
index 0000000..54eb948
--- /dev/null
+++ b/drivers/spi/spi-tegra20-sflash.c
@@ -0,0 +1,665 @@
+/*
+ * SPI driver for Nvidia's Tegra20 Serial Flash Controller.
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * Author: Laxman Dewangan <ldewangan@nvidia.com>
+ *
+ * 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.
+ *
+ * This program is distributed in the hope 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-tegra.h>
+#include <mach/clk.h>
+
+#define SPI_COMMAND				0x000
+#define SPI_GO					BIT(30)
+#define SPI_M_S					BIT(28)
+#define SPI_ACTIVE_SCLK_MASK			(0x3 << 26)
+#define SPI_ACTIVE_SCLK_DRIVE_LOW		(0 << 26)
+#define SPI_ACTIVE_SCLK_DRIVE_HIGH		(1 << 26)
+#define SPI_ACTIVE_SCLK_PULL_LOW		(2 << 26)
+#define SPI_ACTIVE_SCLK_PULL_HIGH		(3 << 26)
+
+#define SPI_CK_SDA_FALLING			(1 << 21)
+#define SPI_CK_SDA_RISING			(0 << 21)
+#define SPI_CK_SDA_MASK				(1 << 21)
+#define SPI_ACTIVE_SDA				(0x3 << 18)
+#define SPI_ACTIVE_SDA_DRIVE_LOW		(0 << 18)
+#define SPI_ACTIVE_SDA_DRIVE_HIGH		(1 << 18)
+#define SPI_ACTIVE_SDA_PULL_LOW			(2 << 18)
+#define SPI_ACTIVE_SDA_PULL_HIGH		(3 << 18)
+
+#define SPI_CS_POL_INVERT			BIT(16)
+#define SPI_TX_EN				BIT(15)
+#define SPI_RX_EN				BIT(14)
+#define SPI_CS_VAL_HIGH				BIT(13)
+#define SPI_CS_VAL_LOW				0x0
+#define SPI_CS_SW				BIT(12)
+#define SPI_CS_HW				0x0
+#define SPI_CS_DELAY_MASK			(7 << 9)
+#define SPI_CS3_EN				BIT(8)
+#define SPI_CS2_EN				BIT(7)
+#define SPI_CS1_EN				BIT(6)
+#define SPI_CS0_EN				BIT(5)
+
+#define SPI_CS_MASK			(SPI_CS3_EN | SPI_CS2_EN |	\
+					SPI_CS1_EN | SPI_CS0_EN)
+#define SPI_BIT_LENGTH(x)		(((x) & 0x1f) << 0)
+
+#define SPI_MODES			(SPI_ACTIVE_SCLK_MASK | SPI_CK_SDA_MASK)
+
+#define SPI_STATUS			0x004
+#define SPI_BSY				BIT(31)
+#define SPI_RDY				BIT(30)
+#define SPI_TXF_FLUSH			BIT(29)
+#define SPI_RXF_FLUSH			BIT(28)
+#define SPI_RX_UNF			BIT(27)
+#define SPI_TX_OVF			BIT(26)
+#define SPI_RXF_EMPTY			BIT(25)
+#define SPI_RXF_FULL			BIT(24)
+#define SPI_TXF_EMPTY			BIT(23)
+#define SPI_TXF_FULL			BIT(22)
+#define SPI_BLK_CNT(count)		(((count) & 0xffff) + 1)
+
+#define SPI_FIFO_ERROR			(SPI_RX_UNF | SPI_TX_OVF)
+#define SPI_FIFO_EMPTY			(SPI_TX_EMPTY | SPI_RX_EMPTY)
+
+#define SPI_RX_CMP			0x8
+#define SPI_DMA_CTL			0x0C
+#define SPI_DMA_EN			BIT(31)
+#define SPI_IE_RXC			BIT(27)
+#define SPI_IE_TXC			BIT(26)
+#define SPI_PACKED			BIT(20)
+#define SPI_RX_TRIG_MASK		(0x3 << 18)
+#define SPI_RX_TRIG_1W			(0x0 << 18)
+#define SPI_RX_TRIG_4W			(0x1 << 18)
+#define SPI_TX_TRIG_MASK		(0x3 << 16)
+#define SPI_TX_TRIG_1W			(0x0 << 16)
+#define SPI_TX_TRIG_4W			(0x1 << 16)
+#define SPI_DMA_BLK_COUNT(count)	(((count) - 1) & 0xFFFF);
+
+#define SPI_TX_FIFO			0x10
+#define SPI_RX_FIFO			0x20
+
+#define DATA_DIR_TX			(1 << 0)
+#define DATA_DIR_RX			(1 << 1)
+
+#define MAX_CHIP_SELECT			4
+#define SPI_FIFO_DEPTH			4
+#define SPI_DMA_TIMEOUT               (msecs_to_jiffies(1000))
+
+struct tegra_sflash_data {
+	struct device				*dev;
+	struct spi_master			*master;
+	spinlock_t				lock;
+
+	struct clk				*clk;
+	void __iomem				*base;
+	unsigned				irq;
+	u32					spi_max_frequency;
+	u32					cur_speed;
+
+	struct spi_device			*cur_spi;
+	unsigned				cur_pos;
+	unsigned				cur_len;
+	unsigned				bytes_per_word;
+	unsigned				cur_direction;
+	unsigned				curr_xfer_words;
+
+	unsigned				cur_rx_pos;
+	unsigned				cur_tx_pos;
+
+	u32					tx_status;
+	u32					rx_status;
+	u32					status_reg;
+
+	u32					def_command_reg;
+	u32					command_reg;
+	u32					dma_control_reg;
+
+	struct completion			xfer_completion;
+	struct spi_transfer			*curr_xfer;
+};
+
+static int tegra_sflash_runtime_suspend(struct device *dev);
+static int tegra_sflash_runtime_resume(struct device *dev);
+
+static inline unsigned long tegra_sflash_readl(struct tegra_sflash_data *tsd,
+		unsigned long reg)
+{
+	return readl(tsd->base + reg);
+}
+
+static inline void tegra_sflash_writel(struct tegra_sflash_data *tsd,
+		unsigned long val, unsigned long reg)
+{
+	writel(val, tsd->base + reg);
+}
+
+static void tegra_sflash_clear_status(struct tegra_sflash_data *tsd)
+{
+	/* Write 1 to clear status register */
+	tegra_sflash_writel(tsd, SPI_RDY | SPI_FIFO_ERROR, SPI_STATUS);
+}
+
+static unsigned tegra_sflash_calculate_curr_xfer_param(
+	struct spi_device *spi, struct tegra_sflash_data *tsd,
+	struct spi_transfer *t)
+{
+	unsigned remain_len = t->len - tsd->cur_pos;
+	unsigned max_word;
+
+	tsd->bytes_per_word = (t->bits_per_word - 1) / 8 + 1;
+	max_word = remain_len / tsd->bytes_per_word;
+	if (max_word > SPI_FIFO_DEPTH)
+		max_word = SPI_FIFO_DEPTH;
+	tsd->curr_xfer_words = max_word;
+	return max_word;
+}
+
+static unsigned tegra_sflash_fill_tx_fifo_from_client_txbuf(
+	struct tegra_sflash_data *tsd, struct spi_transfer *t)
+{
+	unsigned nbytes;
+	unsigned long status;
+	unsigned max_n_32bit = tsd->curr_xfer_words;
+	u8 *tx_buf = (u8 *)t->tx_buf + tsd->cur_tx_pos;
+
+	if (max_n_32bit > SPI_FIFO_DEPTH)
+		max_n_32bit = SPI_FIFO_DEPTH;
+	nbytes = max_n_32bit * tsd->bytes_per_word;
+
+	status = tegra_sflash_readl(tsd, SPI_STATUS);
+	while (!(status & SPI_TXF_FULL)) {
+		int i;
+		unsigned int x = 0;
+
+		for (i = 0; nbytes && (i < tsd->bytes_per_word);
+							i++, nbytes--)
+				x |= ((*tx_buf++) << i*8);
+		tegra_sflash_writel(tsd, x, SPI_TX_FIFO);
+		if (!nbytes)
+			break;
+
+		status = tegra_sflash_readl(tsd, SPI_STATUS);
+	}
+	tsd->cur_tx_pos += max_n_32bit * tsd->bytes_per_word;
+	return max_n_32bit;
+}
+
+static int tegra_sflash_read_rx_fifo_to_client_rxbuf(
+		struct tegra_sflash_data *tsd, struct spi_transfer *t)
+{
+	unsigned long status;
+	unsigned int read_words = 0;
+	u8 *rx_buf = (u8 *)t->rx_buf + tsd->cur_rx_pos;
+
+	status = tegra_sflash_readl(tsd, SPI_STATUS);
+	while (!(status & SPI_RXF_EMPTY)) {
+		int i;
+		unsigned long x;
+
+		x = tegra_sflash_readl(tsd, SPI_RX_FIFO);
+		for (i = 0; (i < tsd->bytes_per_word); i++)
+			*rx_buf++ = (x >> (i*8)) & 0xFF;
+		read_words++;
+		status = tegra_sflash_readl(tsd, SPI_STATUS);
+	}
+	tsd->cur_rx_pos += read_words * tsd->bytes_per_word;
+	return 0;
+}
+
+static int tegra_sflash_start_cpu_based_transfer(
+		struct tegra_sflash_data *tsd, struct spi_transfer *t)
+{
+	unsigned long val = 0;
+	unsigned cur_words;
+
+	if (tsd->cur_direction & DATA_DIR_TX)
+		val |= SPI_IE_TXC;
+
+	if (tsd->cur_direction & DATA_DIR_RX)
+		val |= SPI_IE_RXC;
+
+	tegra_sflash_writel(tsd, val, SPI_DMA_CTL);
+	tsd->dma_control_reg = val;
+
+	if (tsd->cur_direction & DATA_DIR_TX)
+		cur_words = tegra_sflash_fill_tx_fifo_from_client_txbuf(tsd, t);
+	else
+		cur_words = tsd->curr_xfer_words;
+	val |= SPI_DMA_BLK_COUNT(cur_words);
+	tegra_sflash_writel(tsd, val, SPI_DMA_CTL);
+	tsd->dma_control_reg = val;
+	val |= SPI_DMA_EN;
+	tegra_sflash_writel(tsd, val, SPI_DMA_CTL);
+	return 0;
+}
+
+static int tegra_sflash_start_transfer_one(struct spi_device *spi,
+		struct spi_transfer *t, bool is_first_of_msg,
+		bool is_single_xfer)
+{
+	struct tegra_sflash_data *tsd = spi_master_get_devdata(spi->master);
+	u32 speed;
+	unsigned long command;
+
+	speed = t->speed_hz ? t->speed_hz : spi->max_speed_hz;
+	if (!speed)
+		speed = tsd->spi_max_frequency;
+	if (speed != tsd->cur_speed) {
+		clk_set_rate(tsd->clk, speed);
+		tsd->cur_speed = speed;
+	}
+
+	tsd->cur_spi = spi;
+	tsd->cur_pos = 0;
+	tsd->cur_rx_pos = 0;
+	tsd->cur_tx_pos = 0;
+	tsd->curr_xfer = t;
+	tegra_sflash_calculate_curr_xfer_param(spi, tsd, t);
+	if (is_first_of_msg) {
+		command = tsd->def_command_reg;
+		command |= SPI_BIT_LENGTH(t->bits_per_word - 1);
+		command |= SPI_CS_VAL_HIGH;
+
+		command &= ~SPI_MODES;
+		if (spi->mode & SPI_CPHA)
+			command |= SPI_CK_SDA_FALLING;
+
+		if (spi->mode & SPI_CPOL)
+			command |= SPI_ACTIVE_SCLK_DRIVE_HIGH;
+		else
+			command |= SPI_ACTIVE_SCLK_DRIVE_LOW;
+		command |= SPI_CS0_EN << spi->chip_select;
+	} else {
+		command = tsd->command_reg;
+		command &= ~SPI_BIT_LENGTH(~0);
+		command |= SPI_BIT_LENGTH(t->bits_per_word - 1);
+		command &= ~(SPI_RX_EN | SPI_TX_EN);
+	}
+
+	tsd->cur_direction = 0;
+	if (t->rx_buf) {
+		command |= SPI_RX_EN;
+		tsd->cur_direction |= DATA_DIR_RX;
+	}
+	if (t->tx_buf) {
+		command |= SPI_TX_EN;
+		tsd->cur_direction |= DATA_DIR_TX;
+	}
+	tegra_sflash_writel(tsd, command, SPI_COMMAND);
+	tsd->command_reg = command;
+
+	return  tegra_sflash_start_cpu_based_transfer(tsd, t);
+}
+
+static int tegra_sflash_transfer_one_message(struct spi_master *master,
+			struct spi_message *msg)
+{
+	bool is_first_msg = true;
+	int single_xfer;
+	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	struct spi_transfer *xfer;
+	struct spi_device *spi = msg->spi;
+	int ret;
+
+	ret = pm_runtime_get_sync(tsd->dev);
+	if (ret < 0) {
+		dev_err(tsd->dev, "pm_runtime_get() failed, err = %d\n", ret);
+		return ret;
+	}
+
+	msg->status = 0;
+	msg->actual_length = 0;
+	single_xfer = list_is_singular(&msg->transfers);
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		INIT_COMPLETION(tsd->xfer_completion);
+		ret = tegra_sflash_start_transfer_one(spi, xfer,
+					is_first_msg, single_xfer);
+		if (ret < 0) {
+			dev_err(tsd->dev,
+				"spi can not start transfer, err %d\n", ret);
+			goto exit;
+		}
+		is_first_msg = false;
+		ret = wait_for_completion_timeout(&tsd->xfer_completion,
+						SPI_DMA_TIMEOUT);
+		if (WARN_ON(ret == 0)) {
+			dev_err(tsd->dev,
+				"spi trasfer timeout, err %d\n", ret);
+			ret = -EIO;
+			goto exit;
+		}
+
+		if (tsd->tx_status ||  tsd->rx_status) {
+			dev_err(tsd->dev, "Error in Transfer\n");
+			ret = -EIO;
+			goto exit;
+		}
+		msg->actual_length += xfer->len;
+		if (xfer->cs_change && xfer->delay_usecs) {
+			tegra_sflash_writel(tsd, tsd->def_command_reg,
+					SPI_COMMAND);
+			udelay(xfer->delay_usecs);
+		}
+	}
+	ret = 0;
+exit:
+	tegra_sflash_writel(tsd, tsd->def_command_reg, SPI_COMMAND);
+	msg->status = ret;
+	spi_finalize_current_message(master);
+	pm_runtime_put(tsd->dev);
+	return ret;
+}
+
+static irqreturn_t handle_cpu_based_xfer(struct tegra_sflash_data *tsd)
+{
+	struct spi_transfer *t = tsd->curr_xfer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tsd->lock, flags);
+	if (tsd->tx_status || tsd->rx_status || (tsd->status_reg & SPI_BSY)) {
+		dev_err(tsd->dev,
+			"CpuXfer ERROR bit set 0x%x\n", tsd->status_reg);
+		dev_err(tsd->dev,
+			"CpuXfer 0x%08x:0x%08x\n", tsd->command_reg,
+				tsd->dma_control_reg);
+		tegra_periph_reset_assert(tsd->clk);
+		udelay(2);
+		tegra_periph_reset_deassert(tsd->clk);
+		complete(&tsd->xfer_completion);
+		goto exit;
+	}
+
+	if (tsd->cur_direction & DATA_DIR_RX)
+		tegra_sflash_read_rx_fifo_to_client_rxbuf(tsd, t);
+
+	if (tsd->cur_direction & DATA_DIR_TX)
+		tsd->cur_pos = tsd->cur_tx_pos;
+	else
+		tsd->cur_pos = tsd->cur_rx_pos;
+
+	if (tsd->cur_pos == t->len) {
+		complete(&tsd->xfer_completion);
+		goto exit;
+	}
+
+	tegra_sflash_calculate_curr_xfer_param(tsd->cur_spi, tsd, t);
+	tegra_sflash_start_cpu_based_transfer(tsd, t);
+exit:
+	spin_unlock_irqrestore(&tsd->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t tegra_sflash_isr(int irq, void *context_data)
+{
+	struct tegra_sflash_data *tsd = context_data;
+
+	tsd->status_reg = tegra_sflash_readl(tsd, SPI_STATUS);
+	if (tsd->cur_direction & DATA_DIR_TX)
+		tsd->tx_status = tsd->status_reg & SPI_TX_OVF;
+
+	if (tsd->cur_direction & DATA_DIR_RX)
+		tsd->rx_status = tsd->status_reg & SPI_RX_UNF;
+	tegra_sflash_clear_status(tsd);
+
+	return handle_cpu_based_xfer(tsd);
+}
+
+static struct tegra_spi_platform_data *tegra_sflash_parse_dt(
+		struct platform_device *pdev)
+{
+	struct tegra_spi_platform_data *pdata;
+	struct device_node *np = pdev->dev.of_node;
+	u32 max_freq;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Memory alloc for pdata failed\n");
+		return NULL;
+	}
+
+	if (!of_property_read_u32(np, "spi-max-frequency", &max_freq))
+		pdata->spi_max_frequency = max_freq;
+
+	return pdata;
+}
+
+static struct of_device_id tegra_sflash_of_match[] __devinitconst = {
+	{ .compatible = "nvidia,tegra20-sflash", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, tegra_sflash_of_match);
+
+static int __devinit tegra_sflash_probe(struct platform_device *pdev)
+{
+	struct spi_master	*master;
+	struct tegra_sflash_data	*tsd;
+	struct resource		*r;
+	struct tegra_spi_platform_data *pdata = pdev->dev.platform_data;
+	int ret;
+	const struct of_device_id *match;
+
+	match = of_match_device(of_match_ptr(tegra_sflash_of_match),
+					&pdev->dev);
+	if (!match) {
+		dev_err(&pdev->dev, "Error: No device match found\n");
+		return -ENODEV;
+	}
+
+	if (!pdata && pdev->dev.of_node)
+		pdata = tegra_sflash_parse_dt(pdev);
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data, exiting\n");
+		return -ENODEV;
+	}
+
+	if (!pdata->spi_max_frequency)
+		pdata->spi_max_frequency = 25000000; /* 25MHz */
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*tsd));
+	if (!master) {
+		dev_err(&pdev->dev, "master allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* the spi->mode bits understood by this driver: */
+	master->mode_bits = SPI_CPOL | SPI_CPHA;
+	master->transfer_one_message = tegra_sflash_transfer_one_message;
+	master->num_chipselect = MAX_CHIP_SELECT;
+	master->bus_num = -1;
+
+	dev_set_drvdata(&pdev->dev, master);
+	tsd = spi_master_get_devdata(master);
+	tsd->master = master;
+	tsd->dev = &pdev->dev;
+	spin_lock_init(&tsd->lock);
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "No IO memory resource\n");
+		ret = -ENODEV;
+		goto exit_free_master;
+	}
+	tsd->base = devm_request_and_ioremap(&pdev->dev, r);
+	if (!tsd->base) {
+		dev_err(&pdev->dev,
+			"Cannot request memregion/iomap dma address\n");
+		ret = -EADDRNOTAVAIL;
+		goto exit_free_master;
+	}
+
+	tsd->irq = platform_get_irq(pdev, 0);
+	ret = request_irq(tsd->irq, tegra_sflash_isr, 0,
+			dev_name(&pdev->dev), tsd);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
+					tsd->irq);
+		goto exit_free_master;
+	}
+
+	tsd->clk = devm_clk_get(&pdev->dev, "spi");
+	if (IS_ERR(tsd->clk)) {
+		dev_err(&pdev->dev, "can not get clock\n");
+		ret = PTR_ERR(tsd->clk);
+		goto exit_free_irq;
+	}
+
+	tsd->spi_max_frequency = pdata->spi_max_frequency;
+	init_completion(&tsd->xfer_completion);
+	pm_runtime_enable(&pdev->dev);
+	if (!pm_runtime_enabled(&pdev->dev)) {
+		ret = tegra_sflash_runtime_resume(&pdev->dev);
+		if (ret)
+			goto exit_pm_disable;
+	}
+
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
+		goto exit_pm_disable;
+	}
+
+	/* Reset controller */
+	tegra_periph_reset_assert(tsd->clk);
+	udelay(2);
+	tegra_periph_reset_deassert(tsd->clk);
+
+	tsd->def_command_reg  = SPI_M_S | SPI_CS_SW;
+	tegra_sflash_writel(tsd, tsd->def_command_reg, SPI_COMMAND);
+	pm_runtime_put(&pdev->dev);
+
+	master->dev.of_node = pdev->dev.of_node;
+	ret = spi_register_master(master);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
+		goto exit_pm_disable;
+	}
+	return ret;
+
+exit_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_sflash_runtime_suspend(&pdev->dev);
+exit_free_irq:
+	free_irq(tsd->irq, tsd);
+exit_free_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int __devexit tegra_sflash_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = dev_get_drvdata(&pdev->dev);
+	struct tegra_sflash_data	*tsd = spi_master_get_devdata(master);
+
+	free_irq(tsd->irq, tsd);
+	spi_unregister_master(master);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_sflash_runtime_suspend(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int tegra_sflash_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+
+	return spi_master_suspend(master);
+}
+
+static int tegra_sflash_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm runtime failed, e = %d\n", ret);
+		return ret;
+	}
+	tegra_sflash_writel(tsd, tsd->command_reg, SPI_COMMAND);
+	pm_runtime_put(dev);
+
+	return spi_master_resume(master);
+}
+#endif
+
+static int tegra_sflash_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+
+	/* Flush all write which are in PPSB queue by reading back */
+	tegra_sflash_readl(tsd, SPI_COMMAND);
+
+	clk_disable_unprepare(tsd->clk);
+	return 0;
+}
+
+static int tegra_sflash_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_sflash_data *tsd = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(tsd->clk);
+	if (ret < 0) {
+		dev_err(tsd->dev, "clk_prepare failed: %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static const struct dev_pm_ops slink_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_sflash_runtime_suspend,
+		tegra_sflash_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tegra_sflash_suspend, tegra_sflash_resume)
+};
+static struct platform_driver tegra_sflash_driver = {
+	.driver = {
+		.name		= "spi-tegra-sflash",
+		.owner		= THIS_MODULE,
+		.pm		= &slink_pm_ops,
+		.of_match_table	= of_match_ptr(tegra_sflash_of_match),
+	},
+	.probe =	tegra_sflash_probe,
+	.remove =	__devexit_p(tegra_sflash_remove),
+};
+module_platform_driver(tegra_sflash_driver);
+
+MODULE_ALIAS("platform:spi-tegra-sflash");
+MODULE_DESCRIPTION("NVIDIA Tegra20 Serial Flash Controller Driver");
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-tegra20-slink.c b/drivers/spi/spi-tegra20-slink.c
new file mode 100644
index 0000000..7882b50
--- /dev/null
+++ b/drivers/spi/spi-tegra20-slink.c
@@ -0,0 +1,1358 @@
+/*
+ * SPI driver for Nvidia's Tegra20/Tegra30 SLINK Controller.
+ *
+ * Copyright (c) 2012, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope 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, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-tegra.h>
+#include <mach/clk.h>
+
+#define SLINK_COMMAND			0x000
+#define SLINK_BIT_LENGTH(x)		(((x) & 0x1f) << 0)
+#define SLINK_WORD_SIZE(x)		(((x) & 0x1f) << 5)
+#define SLINK_BOTH_EN			(1 << 10)
+#define SLINK_CS_SW			(1 << 11)
+#define SLINK_CS_VALUE			(1 << 12)
+#define SLINK_CS_POLARITY		(1 << 13)
+#define SLINK_IDLE_SDA_DRIVE_LOW	(0 << 16)
+#define SLINK_IDLE_SDA_DRIVE_HIGH	(1 << 16)
+#define SLINK_IDLE_SDA_PULL_LOW		(2 << 16)
+#define SLINK_IDLE_SDA_PULL_HIGH	(3 << 16)
+#define SLINK_IDLE_SDA_MASK		(3 << 16)
+#define SLINK_CS_POLARITY1		(1 << 20)
+#define SLINK_CK_SDA			(1 << 21)
+#define SLINK_CS_POLARITY2		(1 << 22)
+#define SLINK_CS_POLARITY3		(1 << 23)
+#define SLINK_IDLE_SCLK_DRIVE_LOW	(0 << 24)
+#define SLINK_IDLE_SCLK_DRIVE_HIGH	(1 << 24)
+#define SLINK_IDLE_SCLK_PULL_LOW	(2 << 24)
+#define SLINK_IDLE_SCLK_PULL_HIGH	(3 << 24)
+#define SLINK_IDLE_SCLK_MASK		(3 << 24)
+#define SLINK_M_S			(1 << 28)
+#define SLINK_WAIT			(1 << 29)
+#define SLINK_GO			(1 << 30)
+#define SLINK_ENB			(1 << 31)
+
+#define SLINK_MODES			(SLINK_IDLE_SCLK_MASK | SLINK_CK_SDA)
+
+#define SLINK_COMMAND2			0x004
+#define SLINK_LSBFE			(1 << 0)
+#define SLINK_SSOE			(1 << 1)
+#define SLINK_SPIE			(1 << 4)
+#define SLINK_BIDIROE			(1 << 6)
+#define SLINK_MODFEN			(1 << 7)
+#define SLINK_INT_SIZE(x)		(((x) & 0x1f) << 8)
+#define SLINK_CS_ACTIVE_BETWEEN		(1 << 17)
+#define SLINK_SS_EN_CS(x)		(((x) & 0x3) << 18)
+#define SLINK_SS_SETUP(x)		(((x) & 0x3) << 20)
+#define SLINK_FIFO_REFILLS_0		(0 << 22)
+#define SLINK_FIFO_REFILLS_1		(1 << 22)
+#define SLINK_FIFO_REFILLS_2		(2 << 22)
+#define SLINK_FIFO_REFILLS_3		(3 << 22)
+#define SLINK_FIFO_REFILLS_MASK		(3 << 22)
+#define SLINK_WAIT_PACK_INT(x)		(((x) & 0x7) << 26)
+#define SLINK_SPC0			(1 << 29)
+#define SLINK_TXEN			(1 << 30)
+#define SLINK_RXEN			(1 << 31)
+
+#define SLINK_STATUS			0x008
+#define SLINK_COUNT(val)		(((val) >> 0) & 0x1f)
+#define SLINK_WORD(val)			(((val) >> 5) & 0x1f)
+#define SLINK_BLK_CNT(val)		(((val) >> 0) & 0xffff)
+#define SLINK_MODF			(1 << 16)
+#define SLINK_RX_UNF			(1 << 18)
+#define SLINK_TX_OVF			(1 << 19)
+#define SLINK_TX_FULL			(1 << 20)
+#define SLINK_TX_EMPTY			(1 << 21)
+#define SLINK_RX_FULL			(1 << 22)
+#define SLINK_RX_EMPTY			(1 << 23)
+#define SLINK_TX_UNF			(1 << 24)
+#define SLINK_RX_OVF			(1 << 25)
+#define SLINK_TX_FLUSH			(1 << 26)
+#define SLINK_RX_FLUSH			(1 << 27)
+#define SLINK_SCLK			(1 << 28)
+#define SLINK_ERR			(1 << 29)
+#define SLINK_RDY			(1 << 30)
+#define SLINK_BSY			(1 << 31)
+#define SLINK_FIFO_ERROR		(SLINK_TX_OVF | SLINK_RX_UNF |	\
+					SLINK_TX_UNF | SLINK_RX_OVF)
+
+#define SLINK_FIFO_EMPTY		(SLINK_TX_EMPTY | SLINK_RX_EMPTY)
+
+#define SLINK_MAS_DATA			0x010
+#define SLINK_SLAVE_DATA		0x014
+
+#define SLINK_DMA_CTL			0x018
+#define SLINK_DMA_BLOCK_SIZE(x)		(((x) & 0xffff) << 0)
+#define SLINK_TX_TRIG_1			(0 << 16)
+#define SLINK_TX_TRIG_4			(1 << 16)
+#define SLINK_TX_TRIG_8			(2 << 16)
+#define SLINK_TX_TRIG_16		(3 << 16)
+#define SLINK_TX_TRIG_MASK		(3 << 16)
+#define SLINK_RX_TRIG_1			(0 << 18)
+#define SLINK_RX_TRIG_4			(1 << 18)
+#define SLINK_RX_TRIG_8			(2 << 18)
+#define SLINK_RX_TRIG_16		(3 << 18)
+#define SLINK_RX_TRIG_MASK		(3 << 18)
+#define SLINK_PACKED			(1 << 20)
+#define SLINK_PACK_SIZE_4		(0 << 21)
+#define SLINK_PACK_SIZE_8		(1 << 21)
+#define SLINK_PACK_SIZE_16		(2 << 21)
+#define SLINK_PACK_SIZE_32		(3 << 21)
+#define SLINK_PACK_SIZE_MASK		(3 << 21)
+#define SLINK_IE_TXC			(1 << 26)
+#define SLINK_IE_RXC			(1 << 27)
+#define SLINK_DMA_EN			(1 << 31)
+
+#define SLINK_STATUS2			0x01c
+#define SLINK_TX_FIFO_EMPTY_COUNT(val)	(((val) & 0x3f) >> 0)
+#define SLINK_RX_FIFO_FULL_COUNT(val)	(((val) & 0x3f0000) >> 16)
+#define SLINK_SS_HOLD_TIME(val)		(((val) & 0xF) << 6)
+
+#define SLINK_TX_FIFO			0x100
+#define SLINK_RX_FIFO			0x180
+
+#define DATA_DIR_TX			(1 << 0)
+#define DATA_DIR_RX			(1 << 1)
+
+#define SLINK_DMA_TIMEOUT		(msecs_to_jiffies(1000))
+
+#define DEFAULT_SPI_DMA_BUF_LEN		(16*1024)
+#define TX_FIFO_EMPTY_COUNT_MAX		SLINK_TX_FIFO_EMPTY_COUNT(0x20)
+#define RX_FIFO_FULL_COUNT_ZERO		SLINK_RX_FIFO_FULL_COUNT(0)
+
+#define SLINK_STATUS2_RESET \
+	(TX_FIFO_EMPTY_COUNT_MAX | RX_FIFO_FULL_COUNT_ZERO << 16)
+
+#define MAX_CHIP_SELECT			4
+#define SLINK_FIFO_DEPTH		32
+
+struct tegra_slink_chip_data {
+	bool cs_hold_time;
+};
+
+struct tegra_slink_data {
+	struct device				*dev;
+	struct spi_master			*master;
+	const struct tegra_slink_chip_data	*chip_data;
+	spinlock_t				lock;
+
+	struct clk				*clk;
+	void __iomem				*base;
+	phys_addr_t				phys;
+	unsigned				irq;
+	int					dma_req_sel;
+	u32					spi_max_frequency;
+	u32					cur_speed;
+
+	struct spi_device			*cur_spi;
+	unsigned				cur_pos;
+	unsigned				cur_len;
+	unsigned				words_per_32bit;
+	unsigned				bytes_per_word;
+	unsigned				curr_dma_words;
+	unsigned				cur_direction;
+
+	unsigned				cur_rx_pos;
+	unsigned				cur_tx_pos;
+
+	unsigned				dma_buf_size;
+	unsigned				max_buf_size;
+	bool					is_curr_dma_xfer;
+	bool					is_hw_based_cs;
+
+	struct completion			rx_dma_complete;
+	struct completion			tx_dma_complete;
+
+	u32					tx_status;
+	u32					rx_status;
+	u32					status_reg;
+	bool					is_packed;
+	unsigned long				packed_size;
+
+	u32					command_reg;
+	u32					command2_reg;
+	u32					dma_control_reg;
+	u32					def_command_reg;
+	u32					def_command2_reg;
+
+	struct completion			xfer_completion;
+	struct spi_transfer			*curr_xfer;
+	struct dma_chan				*rx_dma_chan;
+	u32					*rx_dma_buf;
+	dma_addr_t				rx_dma_phys;
+	struct dma_async_tx_descriptor		*rx_dma_desc;
+
+	struct dma_chan				*tx_dma_chan;
+	u32					*tx_dma_buf;
+	dma_addr_t				tx_dma_phys;
+	struct dma_async_tx_descriptor		*tx_dma_desc;
+};
+
+static int tegra_slink_runtime_suspend(struct device *dev);
+static int tegra_slink_runtime_resume(struct device *dev);
+
+static inline unsigned long tegra_slink_readl(struct tegra_slink_data *tspi,
+		unsigned long reg)
+{
+	return readl(tspi->base + reg);
+}
+
+static inline void tegra_slink_writel(struct tegra_slink_data *tspi,
+		unsigned long val, unsigned long reg)
+{
+	writel(val, tspi->base + reg);
+
+	/* Read back register to make sure that register writes completed */
+	if (reg != SLINK_TX_FIFO)
+		readl(tspi->base + SLINK_MAS_DATA);
+}
+
+static void tegra_slink_clear_status(struct tegra_slink_data *tspi)
+{
+	unsigned long val;
+	unsigned long val_write = 0;
+
+	val = tegra_slink_readl(tspi, SLINK_STATUS);
+
+	/* Write 1 to clear status register */
+	val_write = SLINK_RDY | SLINK_FIFO_ERROR;
+	tegra_slink_writel(tspi, val_write, SLINK_STATUS);
+}
+
+static unsigned long tegra_slink_get_packed_size(struct tegra_slink_data *tspi,
+				  struct spi_transfer *t)
+{
+	unsigned long val;
+
+	switch (tspi->bytes_per_word) {
+	case 0:
+		val = SLINK_PACK_SIZE_4;
+		break;
+	case 1:
+		val = SLINK_PACK_SIZE_8;
+		break;
+	case 2:
+		val = SLINK_PACK_SIZE_16;
+		break;
+	case 4:
+		val = SLINK_PACK_SIZE_32;
+		break;
+	default:
+		val = 0;
+	}
+	return val;
+}
+
+static unsigned tegra_slink_calculate_curr_xfer_param(
+	struct spi_device *spi, struct tegra_slink_data *tspi,
+	struct spi_transfer *t)
+{
+	unsigned remain_len = t->len - tspi->cur_pos;
+	unsigned max_word;
+	unsigned bits_per_word ;
+	unsigned max_len;
+	unsigned total_fifo_words;
+
+	bits_per_word = t->bits_per_word ? t->bits_per_word :
+						spi->bits_per_word;
+	tspi->bytes_per_word = (bits_per_word - 1) / 8 + 1;
+
+	if (bits_per_word == 8 || bits_per_word == 16) {
+		tspi->is_packed = 1;
+		tspi->words_per_32bit = 32/bits_per_word;
+	} else {
+		tspi->is_packed = 0;
+		tspi->words_per_32bit = 1;
+	}
+	tspi->packed_size = tegra_slink_get_packed_size(tspi, t);
+
+	if (tspi->is_packed) {
+		max_len = min(remain_len, tspi->max_buf_size);
+		tspi->curr_dma_words = max_len/tspi->bytes_per_word;
+		total_fifo_words = max_len/4;
+	} else {
+		max_word = (remain_len - 1) / tspi->bytes_per_word + 1;
+		max_word = min(max_word, tspi->max_buf_size/4);
+		tspi->curr_dma_words = max_word;
+		total_fifo_words = max_word;
+	}
+	return total_fifo_words;
+}
+
+static unsigned tegra_slink_fill_tx_fifo_from_client_txbuf(
+	struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned nbytes;
+	unsigned tx_empty_count;
+	unsigned long fifo_status;
+	unsigned max_n_32bit;
+	unsigned i, count;
+	unsigned long x;
+	unsigned int written_words;
+	unsigned fifo_words_left;
+	u8 *tx_buf = (u8 *)t->tx_buf + tspi->cur_tx_pos;
+
+	fifo_status = tegra_slink_readl(tspi, SLINK_STATUS2);
+	tx_empty_count = SLINK_TX_FIFO_EMPTY_COUNT(fifo_status);
+
+	if (tspi->is_packed) {
+		fifo_words_left = tx_empty_count * tspi->words_per_32bit;
+		written_words = min(fifo_words_left, tspi->curr_dma_words);
+		nbytes = written_words * tspi->bytes_per_word;
+		max_n_32bit = DIV_ROUND_UP(nbytes, 4);
+		for (count = 0; count < max_n_32bit; count++) {
+			x = 0;
+			for (i = 0; (i < 4) && nbytes; i++, nbytes--)
+				x |= (*tx_buf++) << (i*8);
+			tegra_slink_writel(tspi, x, SLINK_TX_FIFO);
+		}
+	} else {
+		max_n_32bit = min(tspi->curr_dma_words,  tx_empty_count);
+		written_words = max_n_32bit;
+		nbytes = written_words * tspi->bytes_per_word;
+		for (count = 0; count < max_n_32bit; count++) {
+			x = 0;
+			for (i = 0; nbytes && (i < tspi->bytes_per_word);
+							i++, nbytes--)
+				x |= ((*tx_buf++) << i*8);
+			tegra_slink_writel(tspi, x, SLINK_TX_FIFO);
+		}
+	}
+	tspi->cur_tx_pos += written_words * tspi->bytes_per_word;
+	return written_words;
+}
+
+static unsigned int tegra_slink_read_rx_fifo_to_client_rxbuf(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned rx_full_count;
+	unsigned long fifo_status;
+	unsigned i, count;
+	unsigned long x;
+	unsigned int read_words = 0;
+	unsigned len;
+	u8 *rx_buf = (u8 *)t->rx_buf + tspi->cur_rx_pos;
+
+	fifo_status = tegra_slink_readl(tspi, SLINK_STATUS2);
+	rx_full_count = SLINK_RX_FIFO_FULL_COUNT(fifo_status);
+	if (tspi->is_packed) {
+		len = tspi->curr_dma_words * tspi->bytes_per_word;
+		for (count = 0; count < rx_full_count; count++) {
+			x = tegra_slink_readl(tspi, SLINK_RX_FIFO);
+			for (i = 0; len && (i < 4); i++, len--)
+				*rx_buf++ = (x >> i*8) & 0xFF;
+		}
+		tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
+		read_words += tspi->curr_dma_words;
+	} else {
+		unsigned int bits_per_word;
+
+		bits_per_word = t->bits_per_word ? t->bits_per_word :
+						tspi->cur_spi->bits_per_word;
+		for (count = 0; count < rx_full_count; count++) {
+			x = tegra_slink_readl(tspi, SLINK_RX_FIFO);
+			for (i = 0; (i < tspi->bytes_per_word); i++)
+				*rx_buf++ = (x >> (i*8)) & 0xFF;
+		}
+		tspi->cur_rx_pos += rx_full_count * tspi->bytes_per_word;
+		read_words += rx_full_count;
+	}
+	return read_words;
+}
+
+static void tegra_slink_copy_client_txbuf_to_spi_txbuf(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned len;
+
+	/* Make the dma buffer to read by cpu */
+	dma_sync_single_for_cpu(tspi->dev, tspi->tx_dma_phys,
+				tspi->dma_buf_size, DMA_TO_DEVICE);
+
+	if (tspi->is_packed) {
+		len = tspi->curr_dma_words * tspi->bytes_per_word;
+		memcpy(tspi->tx_dma_buf, t->tx_buf + tspi->cur_pos, len);
+	} else {
+		unsigned int i;
+		unsigned int count;
+		u8 *tx_buf = (u8 *)t->tx_buf + tspi->cur_tx_pos;
+		unsigned consume = tspi->curr_dma_words * tspi->bytes_per_word;
+		unsigned int x;
+
+		for (count = 0; count < tspi->curr_dma_words; count++) {
+			x = 0;
+			for (i = 0; consume && (i < tspi->bytes_per_word);
+							i++, consume--)
+				x |= ((*tx_buf++) << i * 8);
+			tspi->tx_dma_buf[count] = x;
+		}
+	}
+	tspi->cur_tx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
+
+	/* Make the dma buffer to read by dma */
+	dma_sync_single_for_device(tspi->dev, tspi->tx_dma_phys,
+				tspi->dma_buf_size, DMA_TO_DEVICE);
+}
+
+static void tegra_slink_copy_spi_rxbuf_to_client_rxbuf(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned len;
+
+	/* Make the dma buffer to read by cpu */
+	dma_sync_single_for_cpu(tspi->dev, tspi->rx_dma_phys,
+		tspi->dma_buf_size, DMA_FROM_DEVICE);
+
+	if (tspi->is_packed) {
+		len = tspi->curr_dma_words * tspi->bytes_per_word;
+		memcpy(t->rx_buf + tspi->cur_rx_pos, tspi->rx_dma_buf, len);
+	} else {
+		unsigned int i;
+		unsigned int count;
+		unsigned char *rx_buf = t->rx_buf + tspi->cur_rx_pos;
+		unsigned int x;
+		unsigned int rx_mask, bits_per_word;
+
+		bits_per_word = t->bits_per_word ? t->bits_per_word :
+						tspi->cur_spi->bits_per_word;
+		rx_mask = (1 << bits_per_word) - 1;
+		for (count = 0; count < tspi->curr_dma_words; count++) {
+			x = tspi->rx_dma_buf[count];
+			x &= rx_mask;
+			for (i = 0; (i < tspi->bytes_per_word); i++)
+				*rx_buf++ = (x >> (i*8)) & 0xFF;
+		}
+	}
+	tspi->cur_rx_pos += tspi->curr_dma_words * tspi->bytes_per_word;
+
+	/* Make the dma buffer to read by dma */
+	dma_sync_single_for_device(tspi->dev, tspi->rx_dma_phys,
+		tspi->dma_buf_size, DMA_FROM_DEVICE);
+}
+
+static void tegra_slink_dma_complete(void *args)
+{
+	struct completion *dma_complete = args;
+
+	complete(dma_complete);
+}
+
+static int tegra_slink_start_tx_dma(struct tegra_slink_data *tspi, int len)
+{
+	INIT_COMPLETION(tspi->tx_dma_complete);
+	tspi->tx_dma_desc = dmaengine_prep_slave_single(tspi->tx_dma_chan,
+				tspi->tx_dma_phys, len, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);
+	if (!tspi->tx_dma_desc) {
+		dev_err(tspi->dev, "Not able to get desc for Tx\n");
+		return -EIO;
+	}
+
+	tspi->tx_dma_desc->callback = tegra_slink_dma_complete;
+	tspi->tx_dma_desc->callback_param = &tspi->tx_dma_complete;
+
+	dmaengine_submit(tspi->tx_dma_desc);
+	dma_async_issue_pending(tspi->tx_dma_chan);
+	return 0;
+}
+
+static int tegra_slink_start_rx_dma(struct tegra_slink_data *tspi, int len)
+{
+	INIT_COMPLETION(tspi->rx_dma_complete);
+	tspi->rx_dma_desc = dmaengine_prep_slave_single(tspi->rx_dma_chan,
+				tspi->rx_dma_phys, len, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);
+	if (!tspi->rx_dma_desc) {
+		dev_err(tspi->dev, "Not able to get desc for Rx\n");
+		return -EIO;
+	}
+
+	tspi->rx_dma_desc->callback = tegra_slink_dma_complete;
+	tspi->rx_dma_desc->callback_param = &tspi->rx_dma_complete;
+
+	dmaengine_submit(tspi->rx_dma_desc);
+	dma_async_issue_pending(tspi->rx_dma_chan);
+	return 0;
+}
+
+static int tegra_slink_start_dma_based_transfer(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned long val;
+	unsigned long test_val;
+	unsigned int len;
+	int ret = 0;
+	unsigned long status;
+
+	/* Make sure that Rx and Tx fifo are empty */
+	status = tegra_slink_readl(tspi, SLINK_STATUS);
+	if ((status & SLINK_FIFO_EMPTY) != SLINK_FIFO_EMPTY) {
+		dev_err(tspi->dev,
+			"Rx/Tx fifo are not empty status 0x%08lx\n", status);
+		return -EIO;
+	}
+
+	val = SLINK_DMA_BLOCK_SIZE(tspi->curr_dma_words - 1);
+	val |= tspi->packed_size;
+	if (tspi->is_packed)
+		len = DIV_ROUND_UP(tspi->curr_dma_words * tspi->bytes_per_word,
+					4) * 4;
+	else
+		len = tspi->curr_dma_words * 4;
+
+	/* Set attention level based on length of transfer */
+	if (len & 0xF)
+		val |= SLINK_TX_TRIG_1 | SLINK_RX_TRIG_1;
+	else if (((len) >> 4) & 0x1)
+		val |= SLINK_TX_TRIG_4 | SLINK_RX_TRIG_4;
+	else
+		val |= SLINK_TX_TRIG_8 | SLINK_RX_TRIG_8;
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		val |= SLINK_IE_TXC;
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		val |= SLINK_IE_RXC;
+
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	tspi->dma_control_reg = val;
+
+	if (tspi->cur_direction & DATA_DIR_TX) {
+		tegra_slink_copy_client_txbuf_to_spi_txbuf(tspi, t);
+		wmb();
+		ret = tegra_slink_start_tx_dma(tspi, len);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"Starting tx dma failed, err %d\n", ret);
+			return ret;
+		}
+
+		/* Wait for tx fifo to be fill before starting slink */
+		test_val = tegra_slink_readl(tspi, SLINK_STATUS);
+		while (!(test_val & SLINK_TX_FULL))
+			test_val = tegra_slink_readl(tspi, SLINK_STATUS);
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX) {
+		/* Make the dma buffer to read by dma */
+		dma_sync_single_for_device(tspi->dev, tspi->rx_dma_phys,
+				tspi->dma_buf_size, DMA_FROM_DEVICE);
+
+		ret = tegra_slink_start_rx_dma(tspi, len);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"Starting rx dma failed, err %d\n", ret);
+			if (tspi->cur_direction & DATA_DIR_TX)
+				dmaengine_terminate_all(tspi->tx_dma_chan);
+			return ret;
+		}
+	}
+	tspi->is_curr_dma_xfer = true;
+	if (tspi->is_packed) {
+		val |= SLINK_PACKED;
+		tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+		/* HW need small delay after settign Packed mode */
+		udelay(1);
+	}
+	tspi->dma_control_reg = val;
+
+	val |= SLINK_DMA_EN;
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	return ret;
+}
+
+static int tegra_slink_start_cpu_based_transfer(
+		struct tegra_slink_data *tspi, struct spi_transfer *t)
+{
+	unsigned long val;
+	unsigned cur_words;
+
+	val = tspi->packed_size;
+	if (tspi->cur_direction & DATA_DIR_TX)
+		val |= SLINK_IE_TXC;
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		val |= SLINK_IE_RXC;
+
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	tspi->dma_control_reg = val;
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		cur_words = tegra_slink_fill_tx_fifo_from_client_txbuf(tspi, t);
+	else
+		cur_words = tspi->curr_dma_words;
+	val |= SLINK_DMA_BLOCK_SIZE(cur_words - 1);
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	tspi->dma_control_reg = val;
+
+	tspi->is_curr_dma_xfer = false;
+	if (tspi->is_packed) {
+		val |= SLINK_PACKED;
+		tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+		udelay(1);
+		wmb();
+	}
+	tspi->dma_control_reg = val;
+	val |= SLINK_DMA_EN;
+	tegra_slink_writel(tspi, val, SLINK_DMA_CTL);
+	return 0;
+}
+
+static int tegra_slink_init_dma_param(struct tegra_slink_data *tspi,
+			bool dma_to_memory)
+{
+	struct dma_chan *dma_chan;
+	u32 *dma_buf;
+	dma_addr_t dma_phys;
+	int ret;
+	struct dma_slave_config dma_sconfig;
+	dma_cap_mask_t mask;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	dma_chan = dma_request_channel(mask, NULL, NULL);
+	if (!dma_chan) {
+		dev_err(tspi->dev,
+			"Dma channel is not available, will try later\n");
+		return -EPROBE_DEFER;
+	}
+
+	dma_buf = dma_alloc_coherent(tspi->dev, tspi->dma_buf_size,
+				&dma_phys, GFP_KERNEL);
+	if (!dma_buf) {
+		dev_err(tspi->dev, " Not able to allocate the dma buffer\n");
+		dma_release_channel(dma_chan);
+		return -ENOMEM;
+	}
+
+	dma_sconfig.slave_id = tspi->dma_req_sel;
+	if (dma_to_memory) {
+		dma_sconfig.src_addr = tspi->phys + SLINK_RX_FIFO;
+		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.src_maxburst = 0;
+	} else {
+		dma_sconfig.dst_addr = tspi->phys + SLINK_TX_FIFO;
+		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		dma_sconfig.dst_maxburst = 0;
+	}
+
+	ret = dmaengine_slave_config(dma_chan, &dma_sconfig);
+	if (ret)
+		goto scrub;
+	if (dma_to_memory) {
+		tspi->rx_dma_chan = dma_chan;
+		tspi->rx_dma_buf = dma_buf;
+		tspi->rx_dma_phys = dma_phys;
+	} else {
+		tspi->tx_dma_chan = dma_chan;
+		tspi->tx_dma_buf = dma_buf;
+		tspi->tx_dma_phys = dma_phys;
+	}
+	return 0;
+
+scrub:
+	dma_free_coherent(tspi->dev, tspi->dma_buf_size, dma_buf, dma_phys);
+	dma_release_channel(dma_chan);
+	return ret;
+}
+
+static void tegra_slink_deinit_dma_param(struct tegra_slink_data *tspi,
+	bool dma_to_memory)
+{
+	u32 *dma_buf;
+	dma_addr_t dma_phys;
+	struct dma_chan *dma_chan;
+
+	if (dma_to_memory) {
+		dma_buf = tspi->rx_dma_buf;
+		dma_chan = tspi->rx_dma_chan;
+		dma_phys = tspi->rx_dma_phys;
+		tspi->rx_dma_chan = NULL;
+		tspi->rx_dma_buf = NULL;
+	} else {
+		dma_buf = tspi->tx_dma_buf;
+		dma_chan = tspi->tx_dma_chan;
+		dma_phys = tspi->tx_dma_phys;
+		tspi->tx_dma_buf = NULL;
+		tspi->tx_dma_chan = NULL;
+	}
+	if (!dma_chan)
+		return;
+
+	dma_free_coherent(tspi->dev, tspi->dma_buf_size, dma_buf, dma_phys);
+	dma_release_channel(dma_chan);
+}
+
+static int tegra_slink_start_transfer_one(struct spi_device *spi,
+		struct spi_transfer *t, bool is_first_of_msg,
+		bool is_single_xfer)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(spi->master);
+	u32 speed;
+	u8 bits_per_word;
+	unsigned total_fifo_words;
+	int ret;
+	struct tegra_spi_device_controller_data *cdata = spi->controller_data;
+	unsigned long command;
+	unsigned long command2;
+
+	bits_per_word = t->bits_per_word;
+	speed = t->speed_hz ? t->speed_hz : spi->max_speed_hz;
+	if (!speed)
+		speed = tspi->spi_max_frequency;
+	if (speed != tspi->cur_speed) {
+		clk_set_rate(tspi->clk, speed * 4);
+		tspi->cur_speed = speed;
+	}
+
+	tspi->cur_spi = spi;
+	tspi->cur_pos = 0;
+	tspi->cur_rx_pos = 0;
+	tspi->cur_tx_pos = 0;
+	tspi->curr_xfer = t;
+	total_fifo_words = tegra_slink_calculate_curr_xfer_param(spi, tspi, t);
+
+	if (is_first_of_msg) {
+		tegra_slink_clear_status(tspi);
+
+		command = tspi->def_command_reg;
+		command |= SLINK_BIT_LENGTH(bits_per_word - 1);
+
+		command2 = tspi->def_command2_reg;
+		command2 |= SLINK_SS_EN_CS(spi->chip_select);
+
+		/* possibly use the hw based chip select */
+		tspi->is_hw_based_cs = false;
+		if (cdata && cdata->is_hw_based_cs && is_single_xfer &&
+			((tspi->curr_dma_words * tspi->bytes_per_word) ==
+						(t->len - tspi->cur_pos))) {
+			int setup_count;
+			int sts2;
+
+			setup_count = cdata->cs_setup_clk_count >> 1;
+			setup_count = max(setup_count, 3);
+			command2 |= SLINK_SS_SETUP(setup_count);
+			if (tspi->chip_data->cs_hold_time) {
+				int hold_count;
+
+				hold_count = cdata->cs_hold_clk_count;
+				hold_count = max(hold_count, 0xF);
+				sts2 = tegra_slink_readl(tspi, SLINK_STATUS2);
+				sts2 &= ~SLINK_SS_HOLD_TIME(0xF);
+				sts2 |= SLINK_SS_HOLD_TIME(hold_count);
+				tegra_slink_writel(tspi, sts2, SLINK_STATUS2);
+			}
+			tspi->is_hw_based_cs = true;
+		}
+
+		if (tspi->is_hw_based_cs)
+			command &= ~SLINK_CS_SW;
+		else
+			command |= SLINK_CS_SW | SLINK_CS_VALUE;
+
+		command &= ~SLINK_MODES;
+		if (spi->mode & SPI_CPHA)
+			command |= SLINK_CK_SDA;
+
+		if (spi->mode & SPI_CPOL)
+			command |= SLINK_IDLE_SCLK_DRIVE_HIGH;
+		else
+			command |= SLINK_IDLE_SCLK_DRIVE_LOW;
+	} else {
+		command = tspi->command_reg;
+		command &= ~SLINK_BIT_LENGTH(~0);
+		command |= SLINK_BIT_LENGTH(bits_per_word - 1);
+
+		command2 = tspi->command2_reg;
+		command2 &= ~(SLINK_RXEN | SLINK_TXEN);
+	}
+
+	tegra_slink_writel(tspi, command, SLINK_COMMAND);
+	tspi->command_reg = command;
+
+	tspi->cur_direction = 0;
+	if (t->rx_buf) {
+		command2 |= SLINK_RXEN;
+		tspi->cur_direction |= DATA_DIR_RX;
+	}
+	if (t->tx_buf) {
+		command2 |= SLINK_TXEN;
+		tspi->cur_direction |= DATA_DIR_TX;
+	}
+	tegra_slink_writel(tspi, command2, SLINK_COMMAND2);
+	tspi->command2_reg = command2;
+
+	if (total_fifo_words > SLINK_FIFO_DEPTH)
+		ret = tegra_slink_start_dma_based_transfer(tspi, t);
+	else
+		ret = tegra_slink_start_cpu_based_transfer(tspi, t);
+	return ret;
+}
+
+static int tegra_slink_setup(struct spi_device *spi)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(spi->master);
+	unsigned long val;
+	unsigned long flags;
+	int ret;
+	unsigned int cs_pol_bit[MAX_CHIP_SELECT] = {
+			SLINK_CS_POLARITY,
+			SLINK_CS_POLARITY1,
+			SLINK_CS_POLARITY2,
+			SLINK_CS_POLARITY3,
+	};
+
+	dev_dbg(&spi->dev, "setup %d bpw, %scpol, %scpha, %dHz\n",
+		spi->bits_per_word,
+		spi->mode & SPI_CPOL ? "" : "~",
+		spi->mode & SPI_CPHA ? "" : "~",
+		spi->max_speed_hz);
+
+	BUG_ON(spi->chip_select >= MAX_CHIP_SELECT);
+
+	ret = pm_runtime_get_sync(tspi->dev);
+	if (ret < 0) {
+		dev_err(tspi->dev, "pm runtime failed, e = %d\n", ret);
+		return ret;
+	}
+
+	spin_lock_irqsave(&tspi->lock, flags);
+	val = tspi->def_command_reg;
+	if (spi->mode & SPI_CS_HIGH)
+		val |= cs_pol_bit[spi->chip_select];
+	else
+		val &= ~cs_pol_bit[spi->chip_select];
+	tspi->def_command_reg = val;
+	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
+	spin_unlock_irqrestore(&tspi->lock, flags);
+
+	pm_runtime_put(tspi->dev);
+	return 0;
+}
+
+static int tegra_slink_prepare_transfer(struct spi_master *master)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+
+	return pm_runtime_get_sync(tspi->dev);
+}
+
+static int tegra_slink_unprepare_transfer(struct spi_master *master)
+{
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+
+	pm_runtime_put(tspi->dev);
+	return 0;
+}
+
+static int tegra_slink_transfer_one_message(struct spi_master *master,
+			struct spi_message *msg)
+{
+	bool is_first_msg = true;
+	int single_xfer;
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	struct spi_transfer *xfer;
+	struct spi_device *spi = msg->spi;
+	int ret;
+
+	msg->status = 0;
+	msg->actual_length = 0;
+	single_xfer = list_is_singular(&msg->transfers);
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		INIT_COMPLETION(tspi->xfer_completion);
+		ret = tegra_slink_start_transfer_one(spi, xfer,
+					is_first_msg, single_xfer);
+		if (ret < 0) {
+			dev_err(tspi->dev,
+				"spi can not start transfer, err %d\n", ret);
+			goto exit;
+		}
+		is_first_msg = false;
+		ret = wait_for_completion_timeout(&tspi->xfer_completion,
+						SLINK_DMA_TIMEOUT);
+		if (WARN_ON(ret == 0)) {
+			dev_err(tspi->dev,
+				"spi trasfer timeout, err %d\n", ret);
+			ret = -EIO;
+			goto exit;
+		}
+
+		if (tspi->tx_status ||  tspi->rx_status) {
+			dev_err(tspi->dev, "Error in Transfer\n");
+			ret = -EIO;
+			goto exit;
+		}
+		msg->actual_length += xfer->len;
+		if (xfer->cs_change && xfer->delay_usecs) {
+			tegra_slink_writel(tspi, tspi->def_command_reg,
+					SLINK_COMMAND);
+			udelay(xfer->delay_usecs);
+		}
+	}
+	ret = 0;
+exit:
+	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
+	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
+	msg->status = ret;
+	spi_finalize_current_message(master);
+	return ret;
+}
+
+static irqreturn_t handle_cpu_based_xfer(struct tegra_slink_data *tspi)
+{
+	struct spi_transfer *t = tspi->curr_xfer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tspi->lock, flags);
+	if (tspi->tx_status ||  tspi->rx_status ||
+				(tspi->status_reg & SLINK_BSY)) {
+		dev_err(tspi->dev,
+			"CpuXfer ERROR bit set 0x%x\n", tspi->status_reg);
+		dev_err(tspi->dev,
+			"CpuXfer 0x%08x:0x%08x:0x%08x\n", tspi->command_reg,
+				tspi->command2_reg, tspi->dma_control_reg);
+		tegra_periph_reset_assert(tspi->clk);
+		udelay(2);
+		tegra_periph_reset_deassert(tspi->clk);
+		complete(&tspi->xfer_completion);
+		goto exit;
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		tegra_slink_read_rx_fifo_to_client_rxbuf(tspi, t);
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		tspi->cur_pos = tspi->cur_tx_pos;
+	else
+		tspi->cur_pos = tspi->cur_rx_pos;
+
+	if (tspi->cur_pos == t->len) {
+		complete(&tspi->xfer_completion);
+		goto exit;
+	}
+
+	tegra_slink_calculate_curr_xfer_param(tspi->cur_spi, tspi, t);
+	tegra_slink_start_cpu_based_transfer(tspi, t);
+exit:
+	spin_unlock_irqrestore(&tspi->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t handle_dma_based_xfer(struct tegra_slink_data *tspi)
+{
+	struct spi_transfer *t = tspi->curr_xfer;
+	long wait_status;
+	int err = 0;
+	unsigned total_fifo_words;
+	unsigned long flags;
+
+	/* Abort dmas if any error */
+	if (tspi->cur_direction & DATA_DIR_TX) {
+		if (tspi->tx_status) {
+			dmaengine_terminate_all(tspi->tx_dma_chan);
+			err += 1;
+		} else {
+			wait_status = wait_for_completion_interruptible_timeout(
+				&tspi->tx_dma_complete, SLINK_DMA_TIMEOUT);
+			if (wait_status <= 0) {
+				dmaengine_terminate_all(tspi->tx_dma_chan);
+				dev_err(tspi->dev, "TxDma Xfer failed\n");
+				err += 1;
+			}
+		}
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX) {
+		if (tspi->rx_status) {
+			dmaengine_terminate_all(tspi->rx_dma_chan);
+			err += 2;
+		} else {
+			wait_status = wait_for_completion_interruptible_timeout(
+				&tspi->rx_dma_complete, SLINK_DMA_TIMEOUT);
+			if (wait_status <= 0) {
+				dmaengine_terminate_all(tspi->rx_dma_chan);
+				dev_err(tspi->dev, "RxDma Xfer failed\n");
+				err += 2;
+			}
+		}
+	}
+
+	spin_lock_irqsave(&tspi->lock, flags);
+	if (err) {
+		dev_err(tspi->dev,
+			"DmaXfer: ERROR bit set 0x%x\n", tspi->status_reg);
+		dev_err(tspi->dev,
+			"DmaXfer 0x%08x:0x%08x:0x%08x\n", tspi->command_reg,
+				tspi->command2_reg, tspi->dma_control_reg);
+		tegra_periph_reset_assert(tspi->clk);
+		udelay(2);
+		tegra_periph_reset_deassert(tspi->clk);
+		complete(&tspi->xfer_completion);
+		spin_unlock_irqrestore(&tspi->lock, flags);
+		return IRQ_HANDLED;
+	}
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		tegra_slink_copy_spi_rxbuf_to_client_rxbuf(tspi, t);
+
+	if (tspi->cur_direction & DATA_DIR_TX)
+		tspi->cur_pos = tspi->cur_tx_pos;
+	else
+		tspi->cur_pos = tspi->cur_rx_pos;
+
+	if (tspi->cur_pos == t->len) {
+		complete(&tspi->xfer_completion);
+		goto exit;
+	}
+
+	/* Continue transfer in current message */
+	total_fifo_words = tegra_slink_calculate_curr_xfer_param(tspi->cur_spi,
+							tspi, t);
+	if (total_fifo_words > SLINK_FIFO_DEPTH)
+		err = tegra_slink_start_dma_based_transfer(tspi, t);
+	else
+		err = tegra_slink_start_cpu_based_transfer(tspi, t);
+
+exit:
+	spin_unlock_irqrestore(&tspi->lock, flags);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t tegra_slink_isr_thread(int irq, void *context_data)
+{
+	struct tegra_slink_data *tspi = context_data;
+
+	if (!tspi->is_curr_dma_xfer)
+		return handle_cpu_based_xfer(tspi);
+	return handle_dma_based_xfer(tspi);
+}
+
+static irqreturn_t tegra_slink_isr(int irq, void *context_data)
+{
+	struct tegra_slink_data *tspi = context_data;
+
+	tspi->status_reg = tegra_slink_readl(tspi, SLINK_STATUS);
+	if (tspi->cur_direction & DATA_DIR_TX)
+		tspi->tx_status = tspi->status_reg &
+					(SLINK_TX_OVF | SLINK_TX_UNF);
+
+	if (tspi->cur_direction & DATA_DIR_RX)
+		tspi->rx_status = tspi->status_reg &
+					(SLINK_RX_OVF | SLINK_RX_UNF);
+	tegra_slink_clear_status(tspi);
+
+	return IRQ_WAKE_THREAD;
+}
+
+static struct tegra_spi_platform_data *tegra_slink_parse_dt(
+		struct platform_device *pdev)
+{
+	struct tegra_spi_platform_data *pdata;
+	const unsigned int *prop;
+	struct device_node *np = pdev->dev.of_node;
+	u32 of_dma[2];
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Memory alloc for pdata failed\n");
+		return NULL;
+	}
+
+	if (of_property_read_u32_array(np, "nvidia,dma-request-selector",
+				of_dma, 2) >= 0)
+		pdata->dma_req_sel = of_dma[1];
+
+	prop = of_get_property(np, "spi-max-frequency", NULL);
+	if (prop)
+		pdata->spi_max_frequency = be32_to_cpup(prop);
+
+	return pdata;
+}
+
+const struct tegra_slink_chip_data tegra30_spi_cdata = {
+	.cs_hold_time = true,
+};
+
+const struct tegra_slink_chip_data tegra20_spi_cdata = {
+	.cs_hold_time = false,
+};
+
+static struct of_device_id tegra_slink_of_match[] __devinitconst = {
+	{ .compatible = "nvidia,tegra30-slink", .data = &tegra30_spi_cdata, },
+	{ .compatible = "nvidia,tegra20-slink", .data = &tegra20_spi_cdata, },
+	{}
+};
+MODULE_DEVICE_TABLE(of, tegra_slink_of_match);
+
+static int __devinit tegra_slink_probe(struct platform_device *pdev)
+{
+	struct spi_master	*master;
+	struct tegra_slink_data	*tspi;
+	struct resource		*r;
+	struct tegra_spi_platform_data *pdata = pdev->dev.platform_data;
+	int ret, spi_irq;
+	const struct tegra_slink_chip_data *cdata = NULL;
+	const struct of_device_id *match;
+
+	match = of_match_device(of_match_ptr(tegra_slink_of_match), &pdev->dev);
+	if (!match) {
+		dev_err(&pdev->dev, "Error: No device match found\n");
+		return -ENODEV;
+	}
+	cdata = match->data;
+	if (!pdata && pdev->dev.of_node)
+		pdata = tegra_slink_parse_dt(pdev);
+
+	if (!pdata) {
+		dev_err(&pdev->dev, "No platform data, exiting\n");
+		return -ENODEV;
+	}
+
+	if (!pdata->spi_max_frequency)
+		pdata->spi_max_frequency = 25000000; /* 25MHz */
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*tspi));
+	if (!master) {
+		dev_err(&pdev->dev, "master allocation failed\n");
+		return -ENOMEM;
+	}
+
+	/* the spi->mode bits understood by this driver: */
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	master->setup = tegra_slink_setup;
+	master->prepare_transfer_hardware = tegra_slink_prepare_transfer;
+	master->transfer_one_message = tegra_slink_transfer_one_message;
+	master->unprepare_transfer_hardware = tegra_slink_unprepare_transfer;
+	master->num_chipselect = MAX_CHIP_SELECT;
+	master->bus_num = -1;
+
+	dev_set_drvdata(&pdev->dev, master);
+	tspi = spi_master_get_devdata(master);
+	tspi->master = master;
+	tspi->dma_req_sel = pdata->dma_req_sel;
+	tspi->dev = &pdev->dev;
+	tspi->chip_data = cdata;
+	spin_lock_init(&tspi->lock);
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!r) {
+		dev_err(&pdev->dev, "No IO memory resource\n");
+		ret = -ENODEV;
+		goto exit_free_master;
+	}
+	tspi->phys = r->start;
+	tspi->base = devm_request_and_ioremap(&pdev->dev, r);
+	if (!tspi->base) {
+		dev_err(&pdev->dev,
+			"Cannot request memregion/iomap dma address\n");
+		ret = -EADDRNOTAVAIL;
+		goto exit_free_master;
+	}
+
+	spi_irq = platform_get_irq(pdev, 0);
+	tspi->irq = spi_irq;
+	ret = request_threaded_irq(tspi->irq, tegra_slink_isr,
+			tegra_slink_isr_thread, IRQF_ONESHOT,
+			dev_name(&pdev->dev), tspi);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Failed to register ISR for IRQ %d\n",
+					tspi->irq);
+		goto exit_free_master;
+	}
+
+	tspi->clk = devm_clk_get(&pdev->dev, "slink");
+	if (IS_ERR(tspi->clk)) {
+		dev_err(&pdev->dev, "can not get clock\n");
+		ret = PTR_ERR(tspi->clk);
+		goto exit_free_irq;
+	}
+
+	tspi->max_buf_size = SLINK_FIFO_DEPTH << 2;
+	tspi->dma_buf_size = DEFAULT_SPI_DMA_BUF_LEN;
+	tspi->spi_max_frequency = pdata->spi_max_frequency;
+
+	if (pdata->dma_req_sel) {
+		ret = tegra_slink_init_dma_param(tspi, true);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "RxDma Init failed, err %d\n", ret);
+			goto exit_free_irq;
+		}
+
+		ret = tegra_slink_init_dma_param(tspi, false);
+		if (ret < 0) {
+			dev_err(&pdev->dev, "TxDma Init failed, err %d\n", ret);
+			goto exit_rx_dma_free;
+		}
+		tspi->max_buf_size = tspi->dma_buf_size;
+		init_completion(&tspi->tx_dma_complete);
+		init_completion(&tspi->rx_dma_complete);
+	}
+
+	init_completion(&tspi->xfer_completion);
+
+	pm_runtime_enable(&pdev->dev);
+	if (!pm_runtime_enabled(&pdev->dev)) {
+		ret = tegra_slink_runtime_resume(&pdev->dev);
+		if (ret)
+			goto exit_pm_disable;
+	}
+
+	ret = pm_runtime_get_sync(&pdev->dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "pm runtime get failed, e = %d\n", ret);
+		goto exit_pm_disable;
+	}
+	tspi->def_command_reg  = SLINK_M_S;
+	tspi->def_command2_reg = SLINK_CS_ACTIVE_BETWEEN;
+	tegra_slink_writel(tspi, tspi->def_command_reg, SLINK_COMMAND);
+	tegra_slink_writel(tspi, tspi->def_command2_reg, SLINK_COMMAND2);
+	pm_runtime_put(&pdev->dev);
+
+	master->dev.of_node = pdev->dev.of_node;
+	ret = spi_register_master(master);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "can not register to master err %d\n", ret);
+		goto exit_pm_disable;
+	}
+	return ret;
+
+exit_pm_disable:
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_slink_runtime_suspend(&pdev->dev);
+	tegra_slink_deinit_dma_param(tspi, false);
+exit_rx_dma_free:
+	tegra_slink_deinit_dma_param(tspi, true);
+exit_free_irq:
+	free_irq(spi_irq, tspi);
+exit_free_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int __devexit tegra_slink_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = dev_get_drvdata(&pdev->dev);
+	struct tegra_slink_data	*tspi = spi_master_get_devdata(master);
+
+	free_irq(tspi->irq, tspi);
+	spi_unregister_master(master);
+
+	if (tspi->tx_dma_chan)
+		tegra_slink_deinit_dma_param(tspi, false);
+
+	if (tspi->rx_dma_chan)
+		tegra_slink_deinit_dma_param(tspi, true);
+
+	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		tegra_slink_runtime_suspend(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int tegra_slink_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+
+	return spi_master_suspend(master);
+}
+
+static int tegra_slink_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm runtime failed, e = %d\n", ret);
+		return ret;
+	}
+	tegra_slink_writel(tspi, tspi->command_reg, SLINK_COMMAND);
+	tegra_slink_writel(tspi, tspi->command2_reg, SLINK_COMMAND2);
+	pm_runtime_put(dev);
+
+	return spi_master_resume(master);
+}
+#endif
+
+static int tegra_slink_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+
+	/* Flush all write which are in PPSB queue by reading back */
+	tegra_slink_readl(tspi, SLINK_MAS_DATA);
+
+	clk_disable_unprepare(tspi->clk);
+	return 0;
+}
+
+static int tegra_slink_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct tegra_slink_data *tspi = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(tspi->clk);
+	if (ret < 0) {
+		dev_err(tspi->dev, "clk_prepare failed: %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static const struct dev_pm_ops slink_pm_ops = {
+	SET_RUNTIME_PM_OPS(tegra_slink_runtime_suspend,
+		tegra_slink_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tegra_slink_suspend, tegra_slink_resume)
+};
+static struct platform_driver tegra_slink_driver = {
+	.driver = {
+		.name		= "spi-tegra-slink",
+		.owner		= THIS_MODULE,
+		.pm		= &slink_pm_ops,
+		.of_match_table	= of_match_ptr(tegra_slink_of_match),
+	},
+	.probe =	tegra_slink_probe,
+	.remove =	__devexit_p(tegra_slink_remove),
+};
+module_platform_driver(tegra_slink_driver);
+
+MODULE_ALIAS("platform:spi-tegra-slink");
+MODULE_DESCRIPTION("NVIDIA Tegra20/Tegra30 SLINK Controller Driver");
+MODULE_AUTHOR("Laxman Dewangan <ldewangan@nvidia.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 84c2861..2ca5f07 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h>
 #include <linux/mod_devicetable.h>
 #include <linux/spi/spi.h>
+#include <linux/of_gpio.h>
 #include <linux/pm_runtime.h>
 #include <linux/export.h>
 #include <linux/sched.h>
@@ -327,6 +328,7 @@
 	spi->dev.parent = &master->dev;
 	spi->dev.bus = &spi_bus_type;
 	spi->dev.release = spidev_release;
+	spi->cs_gpio = -EINVAL;
 	device_initialize(&spi->dev);
 	return spi;
 }
@@ -344,15 +346,16 @@
 int spi_add_device(struct spi_device *spi)
 {
 	static DEFINE_MUTEX(spi_add_lock);
-	struct device *dev = spi->master->dev.parent;
+	struct spi_master *master = spi->master;
+	struct device *dev = master->dev.parent;
 	struct device *d;
 	int status;
 
 	/* Chipselects are numbered 0..max; validate. */
-	if (spi->chip_select >= spi->master->num_chipselect) {
+	if (spi->chip_select >= master->num_chipselect) {
 		dev_err(dev, "cs%d >= max %d\n",
 			spi->chip_select,
-			spi->master->num_chipselect);
+			master->num_chipselect);
 		return -EINVAL;
 	}
 
@@ -376,6 +379,9 @@
 		goto done;
 	}
 
+	if (master->cs_gpios)
+		spi->cs_gpio = master->cs_gpios[spi->chip_select];
+
 	/* Drivers may modify this initial i/o setup, but will
 	 * normally rely on the device being setup.  Devices
 	 * using SPI_CS_HIGH can't coexist well otherwise...
@@ -855,6 +861,8 @@
 			spi->mode |= SPI_CPOL;
 		if (of_find_property(nc, "spi-cs-high", NULL))
 			spi->mode |= SPI_CS_HIGH;
+		if (of_find_property(nc, "spi-3wire", NULL))
+			spi->mode |= SPI_3WIRE;
 
 		/* Device speed */
 		prop = of_get_property(nc, "spi-max-frequency", &len);
@@ -946,6 +954,44 @@
 }
 EXPORT_SYMBOL_GPL(spi_alloc_master);
 
+#ifdef CONFIG_OF
+static int of_spi_register_master(struct spi_master *master)
+{
+	u16 nb;
+	int i, *cs;
+	struct device_node *np = master->dev.of_node;
+
+	if (!np)
+		return 0;
+
+	nb = of_gpio_named_count(np, "cs-gpios");
+	master->num_chipselect = max(nb, master->num_chipselect);
+
+	if (nb < 1)
+		return 0;
+
+	cs = devm_kzalloc(&master->dev,
+			  sizeof(int) * master->num_chipselect,
+			  GFP_KERNEL);
+	master->cs_gpios = cs;
+
+	if (!master->cs_gpios)
+		return -ENOMEM;
+
+	memset(cs, -EINVAL, master->num_chipselect);
+
+	for (i = 0; i < nb; i++)
+		cs[i] = of_get_named_gpio(np, "cs-gpios", i);
+
+	return 0;
+}
+#else
+static int of_spi_register_master(struct spi_master *master)
+{
+	return 0;
+}
+#endif
+
 /**
  * spi_register_master - register SPI master controller
  * @master: initialized master, originally from spi_alloc_master()
@@ -977,6 +1023,10 @@
 	if (!dev)
 		return -ENODEV;
 
+	status = of_spi_register_master(master);
+	if (status)
+		return status;
+
 	/* even if it's just one always-selected device, there must
 	 * be at least one chipselect
 	 */
@@ -1156,7 +1206,7 @@
 int spi_setup(struct spi_device *spi)
 {
 	unsigned	bad_bits;
-	int		status;
+	int		status = 0;
 
 	/* help drivers fail *cleanly* when they need options
 	 * that aren't supported with their current master
@@ -1171,7 +1221,8 @@
 	if (!spi->bits_per_word)
 		spi->bits_per_word = 8;
 
-	status = spi->master->setup(spi);
+	if (spi->master->setup)
+		status = spi->master->setup(spi);
 
 	dev_dbg(&spi->dev, "setup mode %d, %s%s%s%s"
 				"%u bits/w, %u Hz max --> %d\n",
@@ -1190,6 +1241,7 @@
 static int __spi_async(struct spi_device *spi, struct spi_message *message)
 {
 	struct spi_master *master = spi->master;
+	struct spi_transfer *xfer;
 
 	/* Half-duplex links include original MicroWire, and ones with
 	 * only one data pin like SPI_3WIRE (switches direction) or where
@@ -1198,7 +1250,6 @@
 	 */
 	if ((master->flags & SPI_MASTER_HALF_DUPLEX)
 			|| (spi->mode & SPI_3WIRE)) {
-		struct spi_transfer *xfer;
 		unsigned flags = master->flags;
 
 		list_for_each_entry(xfer, &message->transfers, transfer_list) {
@@ -1211,6 +1262,15 @@
 		}
 	}
 
+	/**
+	 * Set transfer bits_per_word as spi device default if it is not
+	 * set for this transfer.
+	 */
+	list_for_each_entry(xfer, &message->transfers, transfer_list) {
+		if (!xfer->bits_per_word)
+			xfer->bits_per_word = spi->bits_per_word;
+	}
+
 	message->spi = spi;
 	message->status = -EINPROGRESS;
 	return master->transfer(spi, message);
@@ -1487,12 +1547,18 @@
 	struct spi_transfer	x[2];
 	u8			*local_buf;
 
-	/* Use preallocated DMA-safe buffer.  We can't avoid copying here,
-	 * (as a pure convenience thing), but we can keep heap costs
-	 * out of the hot path ...
+	/* Use preallocated DMA-safe buffer if we can.  We can't avoid
+	 * copying here, (as a pure convenience thing), but we can
+	 * keep heap costs out of the hot path unless someone else is
+	 * using the pre-allocated buffer or the transfer is too large.
 	 */
-	if ((n_tx + n_rx) > SPI_BUFSIZ)
-		return -EINVAL;
+	if ((n_tx + n_rx) > SPI_BUFSIZ || !mutex_trylock(&lock)) {
+		local_buf = kmalloc(max((unsigned)SPI_BUFSIZ, n_tx + n_rx), GFP_KERNEL);
+		if (!local_buf)
+			return -ENOMEM;
+	} else {
+		local_buf = buf;
+	}
 
 	spi_message_init(&message);
 	memset(x, 0, sizeof x);
@@ -1505,14 +1571,6 @@
 		spi_message_add_tail(&x[1], &message);
 	}
 
-	/* ... unless someone else is using the pre-allocated buffer */
-	if (!mutex_trylock(&lock)) {
-		local_buf = kmalloc(SPI_BUFSIZ, GFP_KERNEL);
-		if (!local_buf)
-			return -ENOMEM;
-	} else
-		local_buf = buf;
-
 	memcpy(local_buf, txbuf, n_tx);
 	x[0].tx_buf = local_buf;
 	x[1].rx_buf = local_buf + n_tx;
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 830adbe..e44abc9 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -31,6 +31,8 @@
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/compat.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/spidev.h>
@@ -642,10 +644,18 @@
 	return 0;
 }
 
+static const struct of_device_id spidev_dt_ids[] = {
+	{ .compatible = "rohm,dh2228fv" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, spidev_dt_ids);
+
 static struct spi_driver spidev_spi_driver = {
 	.driver = {
 		.name =		"spidev",
 		.owner =	THIS_MODULE,
+		.of_match_table = of_match_ptr(spidev_dt_ids),
 	},
 	.probe =	spidev_probe,
 	.remove =	__devexit_p(spidev_remove),
diff --git a/include/linux/platform_data/spi-clps711x.h b/include/linux/platform_data/spi-clps711x.h
new file mode 100644
index 0000000..301956e
--- /dev/null
+++ b/include/linux/platform_data/spi-clps711x.h
@@ -0,0 +1,21 @@
+/*
+ *  CLPS711X SPI bus driver definitions
+ *
+ *  Copyright (C) 2012 Alexander Shiyan <shc_work@mail.ru>
+ *
+ * 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.
+ */
+
+#ifndef ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H
+#define ____LINUX_PLATFORM_DATA_SPI_CLPS711X_H
+
+/* Board specific platform_data */
+struct spi_clps711x_pdata {
+	int *chipselect;	/* Array of GPIO-numbers */
+	int num_chipselect;	/* Total count of GPIOs */
+};
+
+#endif
diff --git a/include/linux/platform_data/spi-omap2-mcspi.h b/include/linux/platform_data/spi-omap2-mcspi.h
index a357eb2..a65572d 100644
--- a/include/linux/platform_data/spi-omap2-mcspi.h
+++ b/include/linux/platform_data/spi-omap2-mcspi.h
@@ -7,9 +7,13 @@
 
 #define OMAP4_MCSPI_REG_OFFSET 0x100
 
+#define MCSPI_PINDIR_D0_IN_D1_OUT	0
+#define MCSPI_PINDIR_D0_OUT_D1_IN	1
+
 struct omap2_mcspi_platform_config {
 	unsigned short	num_cs;
 	unsigned int regs_offset;
+	unsigned int pin_dir:1;
 };
 
 struct omap2_mcspi_dev_attr {
diff --git a/include/linux/spi/spi-tegra.h b/include/linux/spi/spi-tegra.h
new file mode 100644
index 0000000..786932c
--- /dev/null
+++ b/include/linux/spi/spi-tegra.h
@@ -0,0 +1,40 @@
+/*
+ * spi-tegra.h: SPI interface for Nvidia Tegra20 SLINK controller.
+ *
+ * Copyright (C) 2011 NVIDIA Corporation
+ *
+ * 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 Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#ifndef _LINUX_SPI_TEGRA_H
+#define _LINUX_SPI_TEGRA_H
+
+struct tegra_spi_platform_data {
+	int dma_req_sel;
+	unsigned int spi_max_frequency;
+};
+
+/*
+ * Controller data from device to pass some info like
+ * hw based chip select can be used or not and if yes
+ * then CS hold and setup time.
+ */
+struct tegra_spi_device_controller_data {
+	bool is_hw_based_cs;
+	int cs_setup_clk_count;
+	int cs_hold_clk_count;
+};
+
+#endif /* _LINUX_SPI_TEGRA_H */
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index fa702ae..f629189 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -90,6 +90,7 @@
 	void			*controller_state;
 	void			*controller_data;
 	char			modalias[SPI_NAME_SIZE];
+	int			cs_gpio;	/* chip select gpio */
 
 	/*
 	 * likely need more hooks for more protocol options affecting how
@@ -362,6 +363,8 @@
 	int (*transfer_one_message)(struct spi_master *master,
 				    struct spi_message *mesg);
 	int (*unprepare_transfer_hardware)(struct spi_master *master);
+	/* gpio chip select */
+	int			*cs_gpios;
 };
 
 static inline void *spi_master_get_devdata(struct spi_master *master)