Merge branch 'for-grant' of git://arago-project.org/git/projects/linux-davinci into spi/next

* 'for-grant' of git://arago-project.org/git/projects/linux-davinci into spi/next
   spi: davinci: fix checkpatch errors
   spi: davinci: whitespace cleanup
   spi: davinci: remove unused variable 'pdata'
   spi: davinci: set chip-select mode in SPIDEF only once
   spi: davinci: enable both activation and deactivation of chip-selects
   spi: davinci: remove unnecessary data transmit on CS disable
   spi: davinci: enable GPIO lines to be used as chip selects
   spi: davinci: simplify prescalar calculation
   spi: davinci: remove 'wait_enable' platform data member
   spi: davinci: make chip-slect specific parameters really chip-select specific
   spi: davinci: consolidate setup of SPIFMTn in one function
   spi: davinci: setup chip-select timers values only if timer enabled
   spi: davinci: add support for wait enable timeouts
   spi: davinci: remove unused members of davinci_spi_slave
   spi: davinci: eliminate the single member structure davinci_spi_slave
   spi: davinci: eliminate unnecessary update of davinci_spi->count
   spi: davinci: simplify calculation of edma acount value
   spi: davinci: check for NULL buffer pointer before using it
   spi: davinci: remove unnecessary disable of SPI
   spi: davinci: remove unnecessary 'count' variable in driver private data
   spi: davinci: remove unnecessary completion variable initialization
   spi: davinci: remove non-useful interrupt mode support
   spi: davinci: simplify poll mode transfers
   spi: davinci: add support for interrupt mode
   spi: davinci: configure the invariable bits in spipc0 only once
   spi: davinci: remove unnecessary function davinci_spi_bufs_prep()
   spi: davinci: remove unnecessary call to davinci_spi_setup_transfer()
   spi: davinci: do not store DMA channel information per chip select
   spi: davinci: always start transmit DMA
   spi: davinci: do not use temporary buffer if no transmit data provided
   spi: davinci: always start receive DMA
   spi: davinci: use edma_write_slot() to setup EDMA PaRAM slot
   spi: davinci: fix DMA event generation stoppage
   spi: davinci: fix EDMA CC errors at end of transfers
   spi: davinci: handle DMA completion errors correctly
   spi: davinci: remove usage of additional completion variables for DMA
   spi: davinci: let DMA operation be specified on per-device basis
   spi: davinci: remove non-useful "clk_internal" platform data
   spi: davinci: enable and power-up SPI only when required
   spi: davinci: setup the driver owner
   spi: davinci: add additional comments
   spi: davinci: add EF Johnson Technologies copyright
   spi: davinci: removed unused #defines
   spi: davinci: remove unnecessary typecast
   spi: davinci: do not treat Tx interrupt being set as error
   spi: davinci: do not allocate DMA channels during SPI device setup
   spi: davinci: remove unnecessary private data member 'region_size'
   spi: davinci: shorten variable names
   spi: davinci: kconfig: add manufacturer name to prompt string

5 files changed, 587 insertions, 799 deletions

diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 2652af124ac..a5f8a80c1f2 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -412,12 +412,7 @@ static struct resource dm355_spi0_resources[] = {
 static struct davinci_spi_platform_data dm355_spi0_pdata = {
 	.version 	= SPI_VERSION_1,
 	.num_chipselect = 2,
-	.clk_internal	= 1,
-	.cs_hold	= 1,
-	.intr_level	= 0,
-	.poll_mode	= 1,	/* 0 -> interrupt mode 1-> polling mode */
-	.c2tdelay	= 0,
-	.t2cdelay	= 0,
+	.cshold_bug	= true,
 };
 static struct platform_device dm355_spi0_device = {
 	.name = "spi_davinci",
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index c466d710d3c..02d2cc380df 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -625,12 +625,6 @@ static u64 dm365_spi0_dma_mask = DMA_BIT_MASK(32);
 static struct davinci_spi_platform_data dm365_spi0_pdata = {
 	.version 	= SPI_VERSION_1,
 	.num_chipselect = 2,
-	.clk_internal	= 1,
-	.cs_hold	= 1,
-	.intr_level	= 0,
-	.poll_mode	= 1,	/* 0 -> interrupt mode 1-> polling mode */
-	.c2tdelay	= 0,
-	.t2cdelay	= 0,
 };
 
 static struct resource dm365_spi0_resources[] = {
diff --git a/arch/arm/mach-davinci/include/mach/spi.h b/arch/arm/mach-davinci/include/mach/spi.h
index 910efbf099c..38f4da5ca13 100644
--- a/arch/arm/mach-davinci/include/mach/spi.h
+++ b/arch/arm/mach-davinci/include/mach/spi.h
@@ -19,26 +19,66 @@
 #ifndef __ARCH_ARM_DAVINCI_SPI_H
 #define __ARCH_ARM_DAVINCI_SPI_H
 
+#define SPI_INTERN_CS	0xFF
+
 enum {
 	SPI_VERSION_1, /* For DM355/DM365/DM6467 */
 	SPI_VERSION_2, /* For DA8xx */
 };
 
+/**
+ * davinci_spi_platform_data - Platform data for SPI master device on DaVinci
+ *
+ * @version:	version of the SPI IP. Different DaVinci devices have slightly
+ *		varying versions of the same IP.
+ * @num_chipselect: number of chipselects supported by this SPI master
+ * @intr_line:	interrupt line used to connect the SPI IP to the ARM interrupt
+ *		controller withn the SoC. Possible values are 0 and 1.
+ * @chip_sel:	list of GPIOs which can act as chip-selects for the SPI.
+ *		SPI_INTERN_CS denotes internal SPI chip-select. Not necessary
+ *		to populate if all chip-selects are internal.
+ * @cshold_bug:	set this to true if the SPI controller on your chip requires
+ *		a write to CSHOLD bit in between transfers (like in DM355).
+ */
 struct davinci_spi_platform_data {
 	u8	version;
 	u8	num_chipselect;
+	u8	intr_line;
+	u8	*chip_sel;
+	bool	cshold_bug;
+};
+
+/**
+ * davinci_spi_config - Per-chip-select configuration for SPI slave devices
+ *
+ * @wdelay:	amount of delay between transmissions. Measured in number of
+ *		SPI module clocks.
+ * @odd_parity:	polarity of parity flag at the end of transmit data stream.
+ *		0 - odd parity, 1 - even parity.
+ * @parity_enable: enable transmission of parity at end of each transmit
+ *		data stream.
+ * @io_type:	type of IO transfer. Choose between polled, interrupt and DMA.
+ * @timer_disable: disable chip-select timers (setup and hold)
+ * @c2tdelay:	chip-select setup time. Measured in number of SPI module clocks.
+ * @t2cdelay:	chip-select hold time. Measured in number of SPI module clocks.
+ * @t2edelay:	transmit data finished to SPI ENAn pin inactive time. Measured
+ *		in number of SPI clocks.
+ * @c2edelay:	chip-select active to SPI ENAn signal active time. Measured in
+ *		number of SPI clocks.
+ */
+struct davinci_spi_config {
 	u8	wdelay;
 	u8	odd_parity;
 	u8	parity_enable;
-	u8	wait_enable;
+#define SPI_IO_TYPE_INTR	0
+#define SPI_IO_TYPE_POLL	1
+#define SPI_IO_TYPE_DMA		2
+	u8	io_type;
 	u8	timer_disable;
-	u8	clk_internal;
-	u8	cs_hold;
-	u8	intr_level;
-	u8	poll_mode;
-	u8	use_dma;
 	u8	c2tdelay;
 	u8	t2cdelay;
+	u8	t2edelay;
+	u8	c2edelay;
 };
 
 #endif	/* __ARCH_ARM_DAVINCI_SPI_H */
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index caa2e84cc0a..6efac5fd439 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -111,11 +111,14 @@ config SPI_COLDFIRE_QSPI
 	  will be called coldfire_qspi.
 
 config SPI_DAVINCI
-	tristate "SPI controller driver for DaVinci/DA8xx SoC's"
+	tristate "Texas Instruments DaVinci/DA8x/OMAP-L/AM1x SoC SPI controller"
 	depends on SPI_MASTER && ARCH_DAVINCI
 	select SPI_BITBANG
 	help
-	  SPI master controller for DaVinci and DA8xx SPI modules.
+	  SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules.
+
+	  This driver can also be built as a module. The module will be called
+	  davinci_spi.
 
 config SPI_EP93XX
 	tristate "Cirrus Logic EP93xx SPI controller"
diff --git a/drivers/spi/davinci_spi.c b/drivers/spi/davinci_spi.c
index b85090caf7c..6beab99bf95 100644
--- a/drivers/spi/davinci_spi.c
+++ b/drivers/spi/davinci_spi.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (C) 2009 Texas Instruments.
+ * Copyright (C) 2010 EF Johnson Technologies
  *
  * 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
@@ -38,11 +39,6 @@
 
 #define CS_DEFAULT	0xFF
 
-#define SPI_BUFSIZ	(SMP_CACHE_BYTES + 1)
-#define DAVINCI_DMA_DATA_TYPE_S8	0x01
-#define DAVINCI_DMA_DATA_TYPE_S16	0x02
-#define DAVINCI_DMA_DATA_TYPE_S32	0x04
-
 #define SPIFMT_PHASE_MASK	BIT(16)
 #define SPIFMT_POLARITY_MASK	BIT(17)
 #define SPIFMT_DISTIMER_MASK	BIT(18)
@@ -52,34 +48,43 @@
 #define SPIFMT_ODD_PARITY_MASK	BIT(23)
 #define SPIFMT_WDELAY_MASK	0x3f000000u
 #define SPIFMT_WDELAY_SHIFT	24
-#define SPIFMT_CHARLEN_MASK	0x0000001Fu
-
-/* SPIGCR1 */
-#define SPIGCR1_SPIENA_MASK	0x01000000u
+#define SPIFMT_PRESCALE_SHIFT	8
 
 /* SPIPC0 */
 #define SPIPC0_DIFUN_MASK	BIT(11)		/* MISO */
 #define SPIPC0_DOFUN_MASK	BIT(10)		/* MOSI */
 #define SPIPC0_CLKFUN_MASK	BIT(9)		/* CLK */
 #define SPIPC0_SPIENA_MASK	BIT(8)		/* nREADY */
-#define SPIPC0_EN1FUN_MASK	BIT(1)
-#define SPIPC0_EN0FUN_MASK	BIT(0)
 
 #define SPIINT_MASKALL		0x0101035F
-#define SPI_INTLVL_1		0x000001FFu
-#define SPI_INTLVL_0		0x00000000u
+#define SPIINT_MASKINT		0x0000015F
+#define SPI_INTLVL_1		0x000001FF
+#define SPI_INTLVL_0		0x00000000
 
-/* SPIDAT1 */
-#define SPIDAT1_CSHOLD_SHIFT	28
-#define SPIDAT1_CSNR_SHIFT	16
+/* SPIDAT1 (upper 16 bit defines) */
+#define SPIDAT1_CSHOLD_MASK	BIT(12)
+
+/* SPIGCR1 */
 #define SPIGCR1_CLKMOD_MASK	BIT(1)
 #define SPIGCR1_MASTER_MASK     BIT(0)
+#define SPIGCR1_POWERDOWN_MASK	BIT(8)
 #define SPIGCR1_LOOPBACK_MASK	BIT(16)
+#define SPIGCR1_SPIENA_MASK	BIT(24)
 
 /* SPIBUF */
 #define SPIBUF_TXFULL_MASK	BIT(29)
 #define SPIBUF_RXEMPTY_MASK	BIT(31)
 
+/* SPIDELAY */
+#define SPIDELAY_C2TDELAY_SHIFT 24
+#define SPIDELAY_C2TDELAY_MASK  (0xFF << SPIDELAY_C2TDELAY_SHIFT)
+#define SPIDELAY_T2CDELAY_SHIFT 16
+#define SPIDELAY_T2CDELAY_MASK  (0xFF << SPIDELAY_T2CDELAY_SHIFT)
+#define SPIDELAY_T2EDELAY_SHIFT 8
+#define SPIDELAY_T2EDELAY_MASK  (0xFF << SPIDELAY_T2EDELAY_SHIFT)
+#define SPIDELAY_C2EDELAY_SHIFT 0
+#define SPIDELAY_C2EDELAY_MASK  0xFF
+
 /* Error Masks */
 #define SPIFLG_DLEN_ERR_MASK		BIT(0)
 #define SPIFLG_TIMEOUT_MASK		BIT(1)
@@ -87,29 +92,13 @@
 #define SPIFLG_DESYNC_MASK		BIT(3)
 #define SPIFLG_BITERR_MASK		BIT(4)
 #define SPIFLG_OVRRUN_MASK		BIT(6)
-#define SPIFLG_RX_INTR_MASK		BIT(8)
-#define SPIFLG_TX_INTR_MASK		BIT(9)
 #define SPIFLG_BUF_INIT_ACTIVE_MASK	BIT(24)
-#define SPIFLG_MASK			(SPIFLG_DLEN_ERR_MASK \
+#define SPIFLG_ERROR_MASK		(SPIFLG_DLEN_ERR_MASK \
 				| SPIFLG_TIMEOUT_MASK | SPIFLG_PARERR_MASK \
 				| SPIFLG_DESYNC_MASK | SPIFLG_BITERR_MASK \
-				| SPIFLG_OVRRUN_MASK | SPIFLG_RX_INTR_MASK \
-				| SPIFLG_TX_INTR_MASK \
-				| SPIFLG_BUF_INIT_ACTIVE_MASK)
-
-#define SPIINT_DLEN_ERR_INTR	BIT(0)
-#define SPIINT_TIMEOUT_INTR	BIT(1)
-#define SPIINT_PARERR_INTR	BIT(2)
-#define SPIINT_DESYNC_INTR	BIT(3)
-#define SPIINT_BITERR_INTR	BIT(4)
-#define SPIINT_OVRRUN_INTR	BIT(6)
-#define SPIINT_RX_INTR		BIT(8)
-#define SPIINT_TX_INTR		BIT(9)
-#define SPIINT_DMA_REQ_EN	BIT(16)
-#define SPIINT_ENABLE_HIGHZ	BIT(24)
+				| SPIFLG_OVRRUN_MASK)
 
-#define SPI_T2CDELAY_SHIFT	16
-#define SPI_C2TDELAY_SHIFT	24
+#define SPIINT_DMA_REQ_EN	BIT(16)
 
 /* SPI Controller registers */
 #define SPIGCR0		0x00
@@ -118,44 +107,18 @@
 #define SPILVL		0x0c
 #define SPIFLG		0x10
 #define SPIPC0		0x14
-#define SPIPC1		0x18
-#define SPIPC2		0x1c
-#define SPIPC3		0x20
-#define SPIPC4		0x24
-#define SPIPC5		0x28
-#define SPIPC6		0x2c
-#define SPIPC7		0x30
-#define SPIPC8		0x34
-#define SPIDAT0		0x38
 #define SPIDAT1		0x3c
 #define SPIBUF		0x40
-#define SPIEMU		0x44
 #define SPIDELAY	0x48
 #define SPIDEF		0x4c
 #define SPIFMT0		0x50
-#define SPIFMT1		0x54
-#define SPIFMT2		0x58
-#define SPIFMT3		0x5c
-#define TGINTVEC0	0x60
-#define TGINTVEC1	0x64
-
-struct davinci_spi_slave {
-	u32	cmd_to_write;
-	u32	clk_ctrl_to_write;
-	u32	bytes_per_word;
-	u8	active_cs;
-};
 
 /* We have 2 DMA channels per CS, one for RX and one for TX */
 struct davinci_spi_dma {
-	int			dma_tx_channel;
-	int			dma_rx_channel;
-	int			dma_tx_sync_dev;
-	int			dma_rx_sync_dev;
+	int			tx_channel;
+	int			rx_channel;
+	int			dummy_param_slot;
 	enum dma_event_q	eventq;
-
-	struct completion	dma_tx_completion;
-	struct completion	dma_rx_completion;
 };
 
 /* SPI Controller driver's private data. */
@@ -166,58 +129,63 @@ struct davinci_spi {
 	u8			version;
 	resource_size_t		pbase;
 	void __iomem		*base;
-	size_t			region_size;
 	u32			irq;
 	struct completion	done;
 
 	const void		*tx;
 	void			*rx;
-	u8			*tmp_buf;
-	int			count;
-	struct davinci_spi_dma	*dma_channels;
-	struct			davinci_spi_platform_data *pdata;
+#define SPI_TMP_BUFSZ	(SMP_CACHE_BYTES + 1)
+	u8			rx_tmp_buf[SPI_TMP_BUFSZ];
+	int			rcount;
+	int			wcount;
+	struct davinci_spi_dma	dma;
+	struct davinci_spi_platform_data *pdata;
 
 	void			(*get_rx)(u32 rx_data, struct davinci_spi *);
 	u32			(*get_tx)(struct davinci_spi *);
 
-	struct davinci_spi_slave slave[SPI_MAX_CHIPSELECT];
+	u8			bytes_per_word[SPI_MAX_CHIPSELECT];
 };
 
-static unsigned use_dma;
+static struct davinci_spi_config davinci_spi_default_cfg;
 
-static void davinci_spi_rx_buf_u8(u32 data, struct davinci_spi *davinci_spi)
+static void davinci_spi_rx_buf_u8(u32 data, struct davinci_spi *dspi)
 {
-	u8 *rx = davinci_spi->rx;
-
-	*rx++ = (u8)data;
-	davinci_spi->rx = rx;
+	if (dspi->rx) {
+		u8 *rx = dspi->rx;
+		*rx++ = (u8)data;
+		dspi->rx = rx;
+	}
 }
 
-static void davinci_spi_rx_buf_u16(u32 data, struct davinci_spi *davinci_spi)
+static void davinci_spi_rx_buf_u16(u32 data, struct davinci_spi *dspi)
 {
-	u16 *rx = davinci_spi->rx;
-
-	*rx++ = (u16)data;
-	davinci_spi->rx = rx;
+	if (dspi->rx) {
+		u16 *rx = dspi->rx;
+		*rx++ = (u16)data;
+		dspi->rx = rx;
+	}
 }
 
-static u32 davinci_spi_tx_buf_u8(struct davinci_spi *davinci_spi)
+static u32 davinci_spi_tx_buf_u8(struct davinci_spi *dspi)
 {
-	u32 data;
-	const u8 *tx = davinci_spi->tx;
-
-	data = *tx++;
-	davinci_spi->tx = tx;
+	u32 data = 0;
+	if (dspi->tx) {
+		const u8 *tx = dspi->tx;
+		data = *tx++;
+		dspi->tx = tx;
+	}
 	return data;
 }
 
-static u32 davinci_spi_tx_buf_u16(struct davinci_spi *davinci_spi)
+static u32 davinci_spi_tx_buf_u16(struct davinci_spi *dspi)
 {
-	u32 data;
-	const u16 *tx = davinci_spi->tx;
-
-	data = *tx++;
-	davinci_spi->tx = tx;
+	u32 data = 0;
+	if (dspi->tx) {
+		const u16 *tx = dspi->tx;
+		data = *tx++;
+		dspi->tx = tx;
+	}
 	return data;
 }
 
@@ -237,55 +205,67 @@ static inline void clear_io_bits(void __iomem *addr, u32 bits)
 	iowrite32(v, addr);
 }
 
-static inline void set_fmt_bits(void __iomem *addr, u32 bits, int cs_num)
-{
-	set_io_bits(addr + SPIFMT0 + (0x4 * cs_num), bits);
-}
-
-static inline void clear_fmt_bits(void __iomem *addr, u32 bits, int cs_num)
-{
-	clear_io_bits(addr + SPIFMT0 + (0x4 * cs_num), bits);
-}
-
-static void davinci_spi_set_dma_req(const struct spi_device *spi, int enable)
-{
-	struct davinci_spi *davinci_spi = spi_master_get_devdata(spi->master);
-
-	if (enable)
-		set_io_bits(davinci_spi->base + SPIINT, SPIINT_DMA_REQ_EN);
-	else
-		clear_io_bits(davinci_spi->base + SPIINT, SPIINT_DMA_REQ_EN);
-}
-
 /*
  * Interface to control the chip select signal
  */
 static void davinci_spi_chipselect(struct spi_device *spi, int value)
 {
-	struct davinci_spi *davinci_spi;
+	struct davinci_spi *dspi;
 	struct davinci_spi_platform_data *pdata;
-	u32 data1_reg_val = 0;
+	u8 chip_sel = spi->chip_select;
+	u16 spidat1 = CS_DEFAULT;
+	bool gpio_chipsel = false;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	pdata = davinci_spi->pdata;
+	dspi = spi_master_get_devdata(spi->master);
+	pdata = dspi->pdata;
+
+	if (pdata->chip_sel && chip_sel < pdata->num_chipselect &&
+				pdata->chip_sel[chip_sel] != SPI_INTERN_CS)
+		gpio_chipsel = true;
 
 	/*
 	 * Board specific chip select logic decides the polarity and cs
 	 * line for the controller
 	 */
-	if (value == BITBANG_CS_INACTIVE) {
-		set_io_bits(davinci_spi->base + SPIDEF, CS_DEFAULT);
-
-		data1_reg_val |= CS_DEFAULT << SPIDAT1_CSNR_SHIFT;
-		iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
+	if (gpio_chipsel) {
+		if (value == BITBANG_CS_ACTIVE)
+			gpio_set_value(pdata->chip_sel[chip_sel], 0);
+		else
+			gpio_set_value(pdata->chip_sel[chip_sel], 1);
+	} else {
+		if (value == BITBANG_CS_ACTIVE) {
+			spidat1 |= SPIDAT1_CSHOLD_MASK;
+			spidat1 &= ~(0x1 << chip_sel);
+		}
 
-		while ((ioread32(davinci_spi->base + SPIBUF)
-					& SPIBUF_RXEMPTY_MASK) == 0)
-			cpu_relax();
+		iowrite16(spidat1, dspi->base + SPIDAT1 + 2);
 	}
 }
 
 /**
+ * davinci_spi_get_prescale - Calculates the correct prescale value
+ * @maxspeed_hz: the maximum rate the SPI clock can run at
+ *
+ * This function calculates the prescale value that generates a clock rate
+ * less than or equal to the specified maximum.
+ *
+ * Returns: calculated prescale - 1 for easy programming into SPI registers
+ * or negative error number if valid prescalar cannot be updated.
+ */
+static inline int davinci_spi_get_prescale(struct davinci_spi *dspi,
+							u32 max_speed_hz)
+{
+	int ret;
+
+	ret = DIV_ROUND_UP(clk_get_rate(dspi->clk), max_speed_hz);
+
+	if (ret < 3 || ret > 256)
+		return -EINVAL;
+
+	return ret - 1;
+}
+
+/**
  * davinci_spi_setup_transfer - This functions will determine transfer method
  * @spi: spi device on which data transfer to be done
  * @t: spi transfer in which transfer info is filled
@@ -298,13 +278,15 @@ static int davinci_spi_setup_transfer(struct spi_device *spi,
 		struct spi_transfer *t)
 {
 
-	struct davinci_spi *davinci_spi;
-	struct davinci_spi_platform_data *pdata;
+	struct davinci_spi *dspi;
+	struct davinci_spi_config *spicfg;
 	u8 bits_per_word = 0;
-	u32 hz = 0, prescale = 0, clkspeed;
+	u32 hz = 0, spifmt = 0, prescale = 0;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	pdata = davinci_spi->pdata;
+	dspi = spi_master_get_devdata(spi->master);
+	spicfg = (struct davinci_spi_config *)spi->controller_data;
+	if (!spicfg)
+		spicfg = &davinci_spi_default_cfg;
 
 	if (t) {
 		bits_per_word = t->bits_per_word;
@@ -320,111 +302,83 @@ static int davinci_spi_setup_transfer(struct spi_device *spi,
 	 * 8bit, 16bit or 32bit transfer
 	 */
 	if (bits_per_word <= 8 && bits_per_word >= 2) {
-		davinci_spi->get_rx = davinci_spi_rx_buf_u8;
-		davinci_spi->get_tx = davinci_spi_tx_buf_u8;
-		davinci_spi->slave[spi->chip_select].bytes_per_word = 1;
+		dspi->get_rx = davinci_spi_rx_buf_u8;
+		dspi->get_tx = davinci_spi_tx_buf_u8;
+		dspi->bytes_per_word[spi->chip_select] = 1;
 	} else if (bits_per_word <= 16 && bits_per_word >= 2) {
-		davinci_spi->get_rx = davinci_spi_rx_buf_u16;
-		davinci_spi->get_tx = davinci_spi_tx_buf_u16;
-		davinci_spi->slave[spi->chip_select].bytes_per_word = 2;
+		dspi->get_rx = davinci_spi_rx_buf_u16;
+		dspi->get_tx = davinci_spi_tx_buf_u16;
+		dspi->bytes_per_word[spi->chip_select] = 2;
 	} else
 		return -EINVAL;
 
 	if (!hz)
 		hz = spi->max_speed_hz;
 
-	clear_fmt_bits(davinci_spi->base, SPIFMT_CHARLEN_MASK,
-			spi->chip_select);
-	set_fmt_bits(davinci_spi->base, bits_per_word & 0x1f,
-			spi->chip_select);
+	/* Set up SPIFMTn register, unique to this chipselect. */
 
-	clkspeed = clk_get_rate(davinci_spi->clk);
-	if (hz > clkspeed / 2)
-		prescale = 1 << 8;
-	if (hz < clkspeed / 256)
-		prescale = 255 << 8;
-	if (!prescale)
-		prescale = ((clkspeed / hz - 1) << 8) & 0x0000ff00;
+	prescale = davinci_spi_get_prescale(dspi, hz);
+	if (prescale < 0)
+		return prescale;
 
-	clear_fmt_bits(davinci_spi->base, 0x0000ff00, spi->chip_select);
-	set_fmt_bits(davinci_spi->base, prescale, spi->chip_select);
+	spifmt = (prescale << SPIFMT_PRESCALE_SHIFT) | (bits_per_word & 0x1f);
 
-	return 0;
-}
+	if (spi->mode & SPI_LSB_FIRST)
+		spifmt |= SPIFMT_SHIFTDIR_MASK;
 
-static void davinci_spi_dma_rx_callback(unsigned lch, u16 ch_status, void *data)
-{
-	struct spi_device *spi = (struct spi_device *)data;
-	struct davinci_spi *davinci_spi;
-	struct davinci_spi_dma *davinci_spi_dma;
-	struct davinci_spi_platform_data *pdata;
+	if (spi->mode & SPI_CPOL)
+		spifmt |= SPIFMT_POLARITY_MASK;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	davinci_spi_dma = &(davinci_spi->dma_channels[spi->chip_select]);
-	pdata = davinci_spi->pdata;
+	if (!(spi->mode & SPI_CPHA))
+		spifmt |= SPIFMT_PHASE_MASK;
 
-	if (ch_status == DMA_COMPLETE)
-		edma_stop(davinci_spi_dma->dma_rx_channel);
-	else
-		edma_clean_channel(davinci_spi_dma->dma_rx_channel);
+	/*
+	 * Version 1 hardware supports two basic SPI modes:
+	 *  - Standard SPI mode uses 4 pins, with chipselect
+	 *  - 3 pin SPI is a 4 pin variant without CS (SPI_NO_CS)
+	 *	(distinct from SPI_3WIRE, with just one data wire;
+	 *	or similar variants without MOSI or without MISO)
+	 *
+	 * Version 2 hardware supports an optional handshaking signal,
+	 * so it can support two more modes:
+	 *  - 5 pin SPI variant is standard SPI plus SPI_READY
+	 *  - 4 pin with enable is (SPI_READY | SPI_NO_CS)
+	 */
 
-	complete(&davinci_spi_dma->dma_rx_completion);
-	/* We must disable the DMA RX request */
-	davinci_spi_set_dma_req(spi, 0);
-}
+	if (dspi->version == SPI_VERSION_2) {
 
-static void davinci_spi_dma_tx_callback(unsigned lch, u16 ch_status, void *data)
-{
-	struct spi_device *spi = (struct spi_device *)data;
-	struct davinci_spi *davinci_spi;
-	struct davinci_spi_dma *davinci_spi_dma;
-	struct davinci_spi_platform_data *pdata;
+		u32 delay = 0;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	davinci_spi_dma = &(davinci_spi->dma_channels[spi->chip_select]);
-	pdata = davinci_spi->pdata;
+		spifmt |= ((spicfg->wdelay << SPIFMT_WDELAY_SHIFT)
+							& SPIFMT_WDELAY_MASK);
 
-	if (ch_status == DMA_COMPLETE)
-		edma_stop(davinci_spi_dma->dma_tx_channel);
-	else
-		edma_clean_channel(davinci_spi_dma->dma_tx_channel);
+		if (spicfg->odd_parity)
+			spifmt |= SPIFMT_ODD_PARITY_MASK;
 
-	complete(&davinci_spi_dma->dma_tx_completion);
-	/* We must disable the DMA TX request */
-	davinci_spi_set_dma_req(spi, 0);
-}
+		if (spicfg->parity_enable)
+			spifmt |= SPIFMT_PARITYENA_MASK;
 
-static int davinci_spi_request_dma(struct spi_device *spi)
-{
-	struct davinci_spi *davinci_spi;
-	struct davinci_spi_dma *davinci_spi_dma;
-	struct davinci_spi_platform_data *pdata;
-	struct device *sdev;
-	int r;
+		if (spicfg->timer_disable) {
+			spifmt |= SPIFMT_DISTIMER_MASK;
+		} else {
+			delay |= (spicfg->c2tdelay << SPIDELAY_C2TDELAY_SHIFT)
+						& SPIDELAY_C2TDELAY_MASK;
+			delay |= (spicfg->t2cdelay << SPIDELAY_T2CDELAY_SHIFT)
+						& SPIDELAY_T2CDELAY_MASK;
+		}
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
-	pdata = davinci_spi->pdata;
-	sdev = davinci_spi->bitbang.master->dev.parent;
+		if (spi->mode & SPI_READY) {
+			spifmt |= SPIFMT_WAITENA_MASK;
+			delay |= (spicfg->t2edelay << SPIDELAY_T2EDELAY_SHIFT)
+						& SPIDELAY_T2EDELAY_MASK;
+			delay |= (spicfg->c2edelay << SPIDELAY_C2EDELAY_SHIFT)
+						& SPIDELAY_C2EDELAY_MASK;
+		}
 
-	r = edma_alloc_channel(davinci_spi_dma->dma_rx_sync_dev,
-				davinci_spi_dma_rx_callback, spi,
-				davinci_spi_dma->eventq);
-	if (r < 0) {
-		dev_dbg(sdev, "Unable to request DMA channel for SPI RX\n");
-		return -EAGAIN;
+		iowrite32(delay, dspi->base + SPIDELAY);
 	}
-	davinci_spi_dma->dma_rx_channel = r;
-	r = edma_alloc_channel(davinci_spi_dma->dma_tx_sync_dev,
-				davinci_spi_dma_tx_callback, spi,
-				davinci_spi_dma->eventq);
-	if (r < 0) {
-		edma_free_channel(davinci_spi_dma->dma_rx_channel);
-		davinci_spi_dma->dma_rx_channel = -1;
-		dev_dbg(sdev, "Unable to request DMA channel for SPI TX\n");
-		return -EAGAIN;
-	}
-	davinci_spi_dma->dma_tx_channel = r;
+
+	iowrite32(spifmt, dspi->base + SPIFMT0);
 
 	return 0;
 }
@@ -435,190 +389,40 @@ static int davinci_spi_request_dma(struct spi_device *spi)
  *
  * This functions sets the default transfer method.
  */
-
 static int davinci_spi_setup(struct spi_device *spi)
 {
-	int retval;
-	struct davinci_spi *davinci_spi;
-	struct davinci_spi_dma *davinci_spi_dma;
-	struct device *sdev;
+	int retval = 0;
+	struct davinci_spi *dspi;
+	struct davinci_spi_platform_data *pdata;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	sdev = davinci_spi->bitbang.master->dev.parent;
+	dspi = spi_master_get_devdata(spi->master);
+	pdata = dspi->pdata;
 
 	/* if bits per word length is zero then set it default 8 */
 	if (!spi->bits_per_word)
 		spi->bits_per_word = 8;
 
-	davinci_spi->slave[spi->chip_select].cmd_to_write = 0;
-
-	if (use_dma && davinci_spi->dma_channels) {
-		davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
-
-		if ((davinci_spi_dma->dma_rx_channel == -1)
-				|| (davinci_spi_dma->dma_tx_channel == -1)) {
-			retval = davinci_spi_request_dma(spi);
-			if (retval < 0)
-				return retval;
-		}
-	}
-
-	/*
-	 * SPI in DaVinci and DA8xx operate between
-	 * 600 KHz and 50 MHz
-	 */
-	if (spi->max_speed_hz < 600000 || spi->max_speed_hz > 50000000) {
-		dev_dbg(sdev, "Operating frequency is not in acceptable "
-				"range\n");
-		return -EINVAL;
-	}
-
-	/*
-	 * Set up SPIFMTn register, unique to this chipselect.
-	 *
-	 * NOTE: we could do all of these with one write.  Also, some
-	 * of the "version 2" features are found in chips that don't
-	 * support all of them...
-	 */
-	if (spi->mode & SPI_LSB_FIRST)
-		set_fmt_bits(davinci_spi->base, SPIFMT_SHIFTDIR_MASK,
-				spi->chip_select);
-	else
-		clear_fmt_bits(davinci_spi->base, SPIFMT_SHIFTDIR_MASK,
-				spi->chip_select);
-
-	if (spi->mode & SPI_CPOL)
-		set_fmt_bits(davinci_spi->base, SPIFMT_POLARITY_MASK,
-				spi->chip_select);
-	else
-		clear_fmt_bits(davinci_spi->base, SPIFMT_POLARITY_MASK,
-				spi->chip_select);
+	if (!(spi->mode & SPI_NO_CS)) {
+		if ((pdata->chip_sel == NULL) ||
+		    (pdata->chip_sel[spi->chip_select] == SPI_INTERN_CS))
+			set_io_bits(dspi->base + SPIPC0, 1 << spi->chip_select);
 
-	if (!(spi->mode & SPI_CPHA))
-		set_fmt_bits(davinci_spi->base, SPIFMT_PHASE_MASK,
-				spi->chip_select);
-	else
-		clear_fmt_bits(davinci_spi->base, SPIFMT_PHASE_MASK,
-				spi->chip_select);
-
-	/*
-	 * Version 1 hardware supports two basic SPI modes:
-	 *  - Standard SPI mode uses 4 pins, with chipselect
-	 *  - 3 pin SPI is a 4 pin variant without CS (SPI_NO_CS)
-	 *	(distinct from SPI_3WIRE, with just one data wire;
-	 *	or similar variants without MOSI or without MISO)
-	 *
-	 * Version 2 hardware supports an optional handshaking signal,
-	 * so it can support two more modes:
-	 *  - 5 pin SPI variant is standard SPI plus SPI_READY
-	 *  - 4 pin with enable is (SPI_READY | SPI_NO_CS)
-	 */
-
-	if (davinci_spi->version == SPI_VERSION_2) {
-		clear_fmt_bits(davinci_spi->base, SPIFMT_WDELAY_MASK,
-				spi->chip_select);
-		set_fmt_bits(davinci_spi->base,
-				(davinci_spi->pdata->wdelay
-						<< SPIFMT_WDELAY_SHIFT)
-					& SPIFMT_WDELAY_MASK,
-				spi->chip_select);
-
-		if (davinci_spi->pdata->odd_parity)
-			set_fmt_bits(davinci_spi->base,
-					SPIFMT_ODD_PARITY_MASK,
-					spi->chip_select);
-		else
-			clear_fmt_bits(davinci_spi->base,
-					SPIFMT_ODD_PARITY_MASK,
-					spi->chip_select);
-
-		if (davinci_spi->pdata->parity_enable)
-			set_fmt_bits(davinci_spi->base,
-					SPIFMT_PARITYENA_MASK,
-					spi->chip_select);
-		else
-			clear_fmt_bits(davinci_spi->base,
-					SPIFMT_PARITYENA_MASK,
-					spi->chip_select);
-
-		if (davinci_spi->pdata->wait_enable)
-			set_fmt_bits(davinci_spi->base,
-					SPIFMT_WAITENA_MASK,
-					spi->chip_select);
-		else
-			clear_fmt_bits(davinci_spi->base,
-					SPIFMT_WAITENA_MASK,
-					spi->chip_select);
-
-		if (davinci_spi->pdata->timer_disable)
-			set_fmt_bits(davinci_spi->base,
-					SPIFMT_DISTIMER_MASK,
-					spi->chip_select);
-		else
-			clear_fmt_bits(davinci_spi->base,
-					SPIFMT_DISTIMER_MASK,
-					spi->chip_select);
 	}
 
-	retval = davinci_spi_setup_transfer(spi, NULL);
-
-	return retval;
-}
-
-static void davinci_spi_cleanup(struct spi_device *spi)
-{
-	struct davinci_spi *davinci_spi = spi_master_get_devdata(spi->master);
-	struct davinci_spi_dma *davinci_spi_dma;
-
-	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
-
-	if (use_dma && davinci_spi->dma_channels) {
-		davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
-
-		if ((davinci_spi_dma->dma_rx_channel != -1)
-				&& (davinci_spi_dma->dma_tx_channel != -1)) {
-			edma_free_channel(davinci_spi_dma->dma_tx_channel);
-			edma_free_channel(davinci_spi_dma->dma_rx_channel);
-		}
-	}
-}
-
-static int davinci_spi_bufs_prep(struct spi_device *spi,
-				 struct davinci_spi *davinci_spi)
-{
-	int op_mode = 0;
-
-	/*
-	 * REVISIT  unless devices disagree about SPI_LOOP or
-	 * SPI_READY (SPI_NO_CS only allows one device!), this
-	 * should not need to be done before each message...
-	 * optimize for both flags staying cleared.
-	 */
-
-	op_mode = SPIPC0_DIFUN_MASK
-		| SPIPC0_DOFUN_MASK
-		| SPIPC0_CLKFUN_MASK;
-	if (!(spi->mode & SPI_NO_CS))
-		op_mode |= 1 << spi->chip_select;
 	if (spi->mode & SPI_READY)
-		op_mode |= SPIPC0_SPIENA_MASK;
-
-	iowrite32(op_mode, davinci_spi->base + SPIPC0);
+		set_io_bits(dspi->base + SPIPC0, SPIPC0_SPIENA_MASK);
 
 	if (spi->mode & SPI_LOOP)
-		set_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_LOOPBACK_MASK);
+		set_io_bits(dspi->base + SPIGCR1, SPIGCR1_LOOPBACK_MASK);
 	else
-		clear_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_LOOPBACK_MASK);
+		clear_io_bits(dspi->base + SPIGCR1, SPIGCR1_LOOPBACK_MASK);
 
-	return 0;
+	return retval;
 }
 
-static int davinci_spi_check_error(struct davinci_spi *davinci_spi,
-				   int int_status)
+static int davinci_spi_check_error(struct davinci_spi *dspi, int int_status)
 {
-	struct device *sdev = davinci_spi->bitbang.master->dev.parent;
+	struct device *sdev = dspi->bitbang.master->dev.parent;
 
 	if (int_status & SPIFLG_TIMEOUT_MASK) {
 		dev_dbg(sdev, "SPI Time-out Error\n");
@@ -633,7 +437,7 @@ static int davinci_spi_check_error(struct davinci_spi *davinci_spi,
 		return -EIO;
 	}
 
-	if (davinci_spi->version == SPI_VERSION_2) {
+	if (dspi->version == SPI_VERSION_2) {
 		if (int_status & SPIFLG_DLEN_ERR_MASK) {
 			dev_dbg(sdev, "SPI Data Length Error\n");
 			return -EIO;
@@ -646,10 +450,6 @@ static int davinci_spi_check_error(struct davinci_spi *davinci_spi,
 			dev_dbg(sdev, "SPI Data Overrun error\n");
 			return -EIO;
 		}
-		if (int_status & SPIFLG_TX_INTR_MASK) {
-			dev_dbg(sdev, "SPI TX intr bit set\n");
-			return -EIO;
-		}
 		if (int_status & SPIFLG_BUF_INIT_ACTIVE_MASK) {
 			dev_dbg(sdev, "SPI Buffer Init Active\n");
 			return -EBUSY;
@@ -660,366 +460,339 @@ static int davinci_spi_check_error(struct davinci_spi *davinci_spi,
 }
 
 /**
- * davinci_spi_bufs - functions which will handle transfer data
- * @spi: spi device on which data transfer to be done
- * @t: spi transfer in which transfer info is filled
+ * davinci_spi_process_events - check for and handle any SPI controller events
+ * @dspi: the controller data
  *
- * This function will put data to be transferred into data register
- * of SPI controller and then wait until the completion will be marked
- * by the IRQ Handler.
+ * This function will check the SPIFLG register and handle any events that are
+ * detected there
  */
-static int davinci_spi_bufs_pio(struct spi_device *spi, struct spi_transfer *t)
+static int davinci_spi_process_events(struct davinci_spi *dspi)
 {
-	struct davinci_spi *davinci_spi;
-	int int_status, count, ret;
-	u8 conv, tmp;
-	u32 tx_data, data1_reg_val;
-	u32 buf_val, flg_val;
-	struct davinci_spi_platform_data *pdata;
-
-	davinci_spi = spi_master_get_devdata(spi->master);
-	pdata = davinci_spi->pdata;
-
-	davinci_spi->tx = t->tx_buf;
-	davinci_spi->rx = t->rx_buf;
-
-	/* convert len to words based on bits_per_word */
-	conv = davinci_spi->slave[spi->chip_select].bytes_per_word;
-	davinci_spi->count = t->len / conv;
-
-	INIT_COMPLETION(davinci_spi->done);
-
-	ret = davinci_spi_bufs_prep(spi, davinci_spi);
-	if (ret)
-		return ret;
-
-	/* Enable SPI */
-	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
-
-	iowrite32(0 | (pdata->c2tdelay << SPI_C2TDELAY_SHIFT) |
-			(pdata->t2cdelay << SPI_T2CDELAY_SHIFT),
-			davinci_spi->base + SPIDELAY);
-
-	count = davinci_spi->count;
-	data1_reg_val = pdata->cs_hold << SPIDAT1_CSHOLD_SHIFT;
-	tmp = ~(0x1 << spi->chip_select);
-
-	clear_io_bits(davinci_spi->base + SPIDEF, ~tmp);
-
-	data1_reg_val |= tmp << SPIDAT1_CSNR_SHIFT;
+	u32 buf, status, errors = 0, spidat1;
 
-	while ((ioread32(davinci_spi->base + SPIBUF)
-				& SPIBUF_RXEMPTY_MASK) == 0)
-		cpu_relax();
+	buf = ioread32(dspi->base + SPIBUF);
 
-	/* Determine the command to execute READ or WRITE */
-	if (t->tx_buf) {
-		clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
+	if (dspi->rcount > 0 && !(buf & SPIBUF_RXEMPTY_MASK)) {
+		dspi->get_rx(buf & 0xFFFF, dspi);
+		dspi->rcount--;
+	}
 
-		while (1) {
-			tx_data = davinci_spi->get_tx(davinci_spi);
+	status = ioread32(dspi->base + SPIFLG);
 
-			data1_reg_val &= ~(0xFFFF);
-			data1_reg_val |= (0xFFFF & tx_data);
+	if (unlikely(status & SPIFLG_ERROR_MASK)) {
+		errors = status & SPIFLG_ERROR_MASK;
+		goto out;
+	}
 
-			buf_val = ioread32(davinci_spi->base + SPIBUF);
-			if ((buf_val & SPIBUF_TXFULL_MASK) == 0) {
-				iowrite32(data1_reg_val,
-						davinci_spi->base + SPIDAT1);
+	if (dspi->wcount > 0 && !(buf & SPIBUF_TXFULL_MASK)) {
+		spidat1 = ioread32(dspi->base + SPIDAT1);
+		dspi->wcount--;
+		spidat1 &= ~0xFFFF;
+		spidat1 |= 0xFFFF & dspi->get_tx(dspi);
+		iowrite32(spidat1, dspi->base + SPIDAT1);
+	}
 
-				count--;
-			}
-			while (ioread32(davinci_spi->base + SPIBUF)
-					& SPIBUF_RXEMPTY_MASK)
-				cpu_relax();
-
-			/* getting the returned byte */
-			if (t->rx_buf) {
-				buf_val = ioread32(davinci_spi->base + SPIBUF);
-				davinci_spi->get_rx(buf_val, davinci_spi);
-			}
-			if (count <= 0)
-				break;
-		}
-	} else {
-		if (pdata->poll_mode) {
-			while (1) {
-				/* keeps the serial clock going */
-				if ((ioread32(davinci_spi->base + SPIBUF)
-						& SPIBUF_TXFULL_MASK) == 0)
-					iowrite32(data1_reg_val,
-						davinci_spi->base + SPIDAT1);
-
-				while (ioread32(davinci_spi->base + SPIBUF) &
-						SPIBUF_RXEMPTY_MASK)
-					cpu_relax();
-
-				flg_val = ioread32(davinci_spi->base + SPIFLG);
-				buf_val = ioread32(davinci_spi->base + SPIBUF);
-
-				davinci_spi->get_rx(buf_val, davinci_spi);
-
-				count--;
-				if (count <= 0)
-					break;
-			}
-		} else {	/* Receive in Interrupt mode */
-			int i;
+out:
+	return errors;
+}
 
-			for (i = 0; i < davinci_spi->count; i++) {
-				set_io_bits(davinci_spi->base + SPIINT,
-						SPIINT_BITERR_INTR
-						| SPIINT_OVRRUN_INTR
-						| SPIINT_RX_INTR);
+static void davinci_spi_dma_callback(unsigned lch, u16 status, void *data)
+{
+	struct davinci_spi *dspi = data;
+	struct davinci_spi_dma *dma = &dspi->dma;
 
-				iowrite32(data1_reg_val,
-						davinci_spi->base + SPIDAT1);
+	edma_stop(lch);
 
-				while (ioread32(davinci_spi->base + SPIINT) &
-						SPIINT_RX_INTR)
-					cpu_relax();
-			}
-			iowrite32((data1_reg_val & 0x0ffcffff),
-					davinci_spi->base + SPIDAT1);
-		}
+	if (status == DMA_COMPLETE) {
+		if (lch == dma->rx_channel)
+			dspi->rcount = 0;
+		if (lch == dma->tx_channel)
+			dspi->wcount = 0;
 	}
 
-	/*
-	 * Check for bit error, desync error,parity error,timeout error and
-	 * receive overflow errors
-	 */
-	int_status = ioread32(davinci_spi->base + SPIFLG);
-
-	ret = davinci_spi_check_error(davinci_spi, int_status);
-	if (ret != 0)
-		return ret;
-
-	/* SPI Framework maintains the count only in bytes so convert back */
-	davinci_spi->count *= conv;
-
-	return t->len;
+	if ((!dspi->wcount && !dspi->rcount) || (status != DMA_COMPLETE))
+		complete(&dspi->done);
 }
 
-#define DAVINCI_DMA_DATA_TYPE_S8	0x01
-#define DAVINCI_DMA_DATA_TYPE_S16	0x02
-#define DAVINCI_DMA_DATA_TYPE_S32	0x04
-
-static int davinci_spi_bufs_dma(struct spi_device *spi, struct spi_transfer *t)
+/**
+ * davinci_spi_bufs - functions which will handle transfer data
+ * @spi: spi device on which data transfer to be done
+ * @t: spi transfer in which transfer info is filled
+ *
+ * This function will put data to be transferred into data register
+ * of SPI controller and then wait until the completion will be marked
+ * by the IRQ Handler.
+ */
+static int davinci_spi_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
-	struct davinci_spi *davinci_spi;
-	int int_status = 0;
-	int count, temp_count;
-	u8 conv = 1;
-	u8 tmp;
-	u32 data1_reg_val;
-	struct davinci_spi_dma *davinci_spi_dma;
-	int word_len, data_type, ret;
-	unsigned long tx_reg, rx_reg;
+	struct davinci_spi *dspi;
+	int data_type, ret;
+	u32 tx_data, spidat1;
+	u32 errors = 0;
+	struct davinci_spi_config *spicfg;
 	struct davinci_spi_platform_data *pdata;
+	unsigned uninitialized_var(rx_buf_count);
 	struct device *sdev;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	pdata = davinci_spi->pdata;
-	sdev = davinci_spi->bitbang.master->dev.parent;
-
-	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
-
-	tx_reg = (unsigned long)davinci_spi->pbase + SPIDAT1;
-	rx_reg = (unsigned long)davinci_spi->pbase + SPIBUF;
-
-	davinci_spi->tx = t->tx_buf;
-	davinci_spi->rx = t->rx_buf;
+	dspi = spi_master_get_devdata(spi->master);
+	pdata = dspi->pdata;
+	spicfg = (struct davinci_spi_config *)spi->controller_data;
+	if (!spicfg)
+		spicfg = &davinci_spi_default_cfg;
+	sdev = dspi->bitbang.master->dev.parent;
 
 	/* convert len to words based on bits_per_word */
-	conv = davinci_spi->slave[spi->chip_select].bytes_per_word;
-	davinci_spi->count = t->len / conv;
-
-	INIT_COMPLETION(davinci_spi->done);
+	data_type = dspi->bytes_per_word[spi->chip_select];
 
-	init_completion(&davinci_spi_dma->dma_rx_completion);
-	init_completion(&davinci_spi_dma->dma_tx_completion);
+	dspi->tx = t->tx_buf;
+	dspi->rx = t->rx_buf;
+	dspi->wcount = t->len / data_type;
+	dspi->rcount = dspi->wcount;
 
-	word_len = conv * 8;
-
-	if (word_len <= 8)
-		data_type = DAVINCI_DMA_DATA_TYPE_S8;
-	else if (word_len <= 16)
-		data_type = DAVINCI_DMA_DATA_TYPE_S16;
-	else if (word_len <= 32)
-		data_type = DAVINCI_DMA_DATA_TYPE_S32;
-	else
-		return -EINVAL;
-
-	ret = davinci_spi_bufs_prep(spi, davinci_spi);
-	if (ret)
-		return ret;
+	spidat1 = ioread32(dspi->base + SPIDAT1);
 
-	/* Put delay val if required */
-	iowrite32(0 | (pdata->c2tdelay << SPI_C2TDELAY_SHIFT) |
-			(pdata->t2cdelay << SPI_T2CDELAY_SHIFT),
-			davinci_spi->base + SPIDELAY);
+	clear_io_bits(dspi->base + SPIGCR1, SPIGCR1_POWERDOWN_MASK);
+	set_io_bits(dspi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
 
-	count = davinci_spi->count;	/* the number of elements */
-	data1_reg_val = pdata->cs_hold << SPIDAT1_CSHOLD_SHIFT;
+	INIT_COMPLETION(dspi->done);
 
-	/* CS default = 0xFF */
-	tmp = ~(0x1 << spi->chip_select);
+	if (spicfg->io_type == SPI_IO_TYPE_INTR)
+		set_io_bits(dspi->base + SPIINT, SPIINT_MASKINT);
 
-	clear_io_bits(davinci_spi->base + SPIDEF, ~tmp);
-
-	data1_reg_val |= tmp << SPIDAT1_CSNR_SHIFT;
-
-	/* disable all interrupts for dma transfers */
-	clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
-	/* Disable SPI to write configuration bits in SPIDAT */
-	clear_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
-	iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
-	/* Enable SPI */
-	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
-
-	while ((ioread32(davinci_spi->base + SPIBUF)
-				& SPIBUF_RXEMPTY_MASK) == 0)
-		cpu_relax();
-
-
-	if (t->tx_buf) {
-		t->tx_dma = dma_map_single(&spi->dev, (void *)t->tx_buf, count,
-				DMA_TO_DEVICE);
-		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
-			dev_dbg(sdev, "Unable to DMA map a %d bytes"
-				" TX buffer\n", count);
-			return -ENOMEM;
-		}
-		temp_count = count;
+	if (spicfg->io_type != SPI_IO_TYPE_DMA) {
+		/* start the transfer */
+		dspi->wcount--;
+		tx_data = dspi->get_tx(dspi);
+		spidat1 &= 0xFFFF0000;
+		spidat1 |= tx_data & 0xFFFF;
+		iowrite32(spidat1, dspi->base + SPIDAT1);
 	} else {
-		/* We need TX clocking for RX transaction */
-		t->tx_dma = dma_map_single(&spi->dev,
-				(void *)davinci_spi->tmp_buf, count + 1,
-				DMA_TO_DEVICE);
-		if (dma_mapping_error(&spi->dev, t->tx_dma)) {
-			dev_dbg(sdev, "Unable to DMA map a %d bytes"
-				" TX tmp buffer\n", count);
-			return -ENOMEM;
+		struct davinci_spi_dma *dma;
+		unsigned long tx_reg, rx_reg;
+		struct edmacc_param param;
+		void *rx_buf;
+
+		dma = &dspi->dma;
+
+		tx_reg = (unsigned long)dspi->pbase + SPIDAT1;
+		rx_reg = (unsigned long)dspi->pbase + SPIBUF;
+
+		/*
+		 * Transmit DMA setup
+		 *
+		 * If there is transmit data, map the transmit buffer, set it
+		 * as the source of data and set the source B index to data
+		 * size. If there is no transmit data, set the transmit register
+		 * as the source of data, and set the source B index to zero.
+		 *
+		 * The destination is always the transmit register itself. And
+		 * the destination never increments.
+		 */
+
+		if (t->tx_buf) {
+			t->tx_dma = dma_map_single(&spi->dev, (void *)t->tx_buf,
+						dspi->wcount, DMA_TO_DEVICE);
+			if (dma_mapping_error(&spi->dev, t->tx_dma)) {
+				dev_dbg(sdev, "Unable to DMA map %d bytes"
+						"TX buffer\n", dspi->wcount);
+				return -ENOMEM;
+			}
 		}
-		temp_count = count + 1;
-	}
 
-	edma_set_transfer_params(davinci_spi_dma->dma_tx_channel,
-					data_type, temp_count, 1, 0, ASYNC);
-	edma_set_dest(davinci_spi_dma->dma_tx_channel, tx_reg, INCR, W8BIT);
-	edma_set_src(davinci_spi_dma->dma_tx_channel, t->tx_dma, INCR, W8BIT);
-	edma_set_src_index(davinci_spi_dma->dma_tx_channel, data_type, 0);
-	edma_set_dest_index(davinci_spi_dma->dma_tx_channel, 0, 0);
-
-	if (t->rx_buf) {
-		/* initiate transaction */
-		iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
+		param.opt = TCINTEN | EDMA_TCC(dma->tx_channel);
+		param.src = t->tx_buf ? t->tx_dma : tx_reg;
+		param.a_b_cnt = dspi->wcount << 16 | data_type;
+		param.dst = tx_reg;
+		param.src_dst_bidx = t->tx_buf ? data_type : 0;
+		param.link_bcntrld = 0xffff;
+		param.src_dst_cidx = 0;
+		param.ccnt = 1;
+		edma_write_slot(dma->tx_channel, &param);
+		edma_link(dma->tx_channel, dma->dummy_param_slot);
+
+		/*
+		 * Receive DMA setup
+		 *
+		 * If there is receive buffer, use it to receive data. If there
+		 * is none provided, use a temporary receive buffer. Set the
+		 * destination B index to 0 so effectively only one byte is used
+		 * in the temporary buffer (address does not increment).
+		 *
+		 * The source of receive data is the receive data register. The
+		 * source address never increments.
+		 */
+
+		if (t->rx_buf) {
+			rx_buf = t->rx_buf;
+			rx_buf_count = dspi->rcount;
+		} else {
+			rx_buf = dspi->rx_tmp_buf;
+			rx_buf_count = sizeof(dspi->rx_tmp_buf);
+		}
 
-		t->rx_dma = dma_map_single(&spi->dev, (void *)t->rx_buf, count,
-				DMA_FROM_DEVICE);
+		t->rx_dma = dma_map_single(&spi->dev, rx_buf, rx_buf_count,
+							DMA_FROM_DEVICE);
 		if (dma_mapping_error(&spi->dev, t->rx_dma)) {
 			dev_dbg(sdev, "Couldn't DMA map a %d bytes RX buffer\n",
-					count);
-			if (t->tx_buf != NULL)
-				dma_unmap_single(NULL, t->tx_dma,
-						 count, DMA_TO_DEVICE);
+								rx_buf_count);
+			if (t->tx_buf)
+				dma_unmap_single(NULL, t->tx_dma, dspi->wcount,
+								DMA_TO_DEVICE);
 			return -ENOMEM;
 		}
-		edma_set_transfer_params(davinci_spi_dma->dma_rx_channel,
-				data_type, count, 1, 0, ASYNC);
-		edma_set_src(davinci_spi_dma->dma_rx_channel,
-				rx_reg, INCR, W8BIT);
-		edma_set_dest(davinci_spi_dma->dma_rx_channel,
-				t->rx_dma, INCR, W8BIT);
-		edma_set_src_index(davinci_spi_dma->dma_rx_channel, 0, 0);
-		edma_set_dest_index(davinci_spi_dma->dma_rx_channel,
-				data_type, 0);
-	}
 
-	if ((t->tx_buf) || (t->rx_buf))
-		edma_start(davinci_spi_dma->dma_tx_channel);
+		param.opt = TCINTEN | EDMA_TCC(dma->rx_channel);
+		param.src = rx_reg;
+		param.a_b_cnt = dspi->rcount << 16 | data_type;
+		param.dst = t->rx_dma;
+		param.src_dst_bidx = (t->rx_buf ? data_type : 0) << 16;
+		param.link_bcntrld = 0xffff;
+		param.src_dst_cidx = 0;
+		param.ccnt = 1;
+		edma_write_slot(dma->rx_channel, &param);
+
+		if (pdata->cshold_bug)
+			iowrite16(spidat1 >> 16, dspi->base + SPIDAT1 + 2);
+
+		edma_start(dma->rx_channel);
+		edma_start(dma->tx_channel);
+		set_io_bits(dspi->base + SPIINT, SPIINT_DMA_REQ_EN);
+	}
 
-	if (t->rx_buf)
-		edma_start(davinci_spi_dma->dma_rx_channel);
+	/* Wait for the transfer to complete */
+	if (spicfg->io_type != SPI_IO_TYPE_POLL) {
+		wait_for_completion_interruptible(&(dspi->done));
+	} else {
+		while (dspi->rcount > 0 || dspi->wcount > 0) {
+			errors = davinci_spi_process_events(dspi);
+			if (errors)
+				break;
+			cpu_relax();
+		}
+	}
 
-	if ((t->rx_buf) || (t->tx_buf))
-		davinci_spi_set_dma_req(spi, 1);
+	clear_io_bits(dspi->base + SPIINT, SPIINT_MASKALL);
+	if (spicfg->io_type == SPI_IO_TYPE_DMA) {
 
-	if (t->tx_buf)
-		wait_for_completion_interruptible(
-				&davinci_spi_dma->dma_tx_completion);
+		if (t->tx_buf)
+			dma_unmap_single(NULL, t->tx_dma, dspi->wcount,
+								DMA_TO_DEVICE);
 
-	if (t->rx_buf)
-		wait_for_completion_interruptible(
-				&davinci_spi_dma->dma_rx_completion);
+		dma_unmap_single(NULL, t->rx_dma, rx_buf_count,
+							DMA_FROM_DEVICE);
 
-	dma_unmap_single(NULL, t->tx_dma, temp_count, DMA_TO_DEVICE);
+		clear_io_bits(dspi->base + SPIINT, SPIINT_DMA_REQ_EN);
+	}
 
-	if (t->rx_buf)
-		dma_unmap_single(NULL, t->rx_dma, count, DMA_FROM_DEVICE);
+	clear_io_bits(dspi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
+	set_io_bits(dspi->base + SPIGCR1, SPIGCR1_POWERDOWN_MASK);
 
 	/*
 	 * Check for bit error, desync error,parity error,timeout error and
 	 * receive overflow errors
 	 */
-	int_status = ioread32(davinci_spi->base + SPIFLG);
-
-	ret = davinci_spi_check_error(davinci_spi, int_status);
-	if (ret != 0)
+	if (errors) {
+		ret = davinci_spi_check_error(dspi, errors);
+		WARN(!ret, "%s: error reported but no error found!\n",
+							dev_name(&spi->dev));
 		return ret;
+	}
 
-	/* SPI Framework maintains the count only in bytes so convert back */
-	davinci_spi->count *= conv;
+	if (dspi->rcount != 0 || dspi->wcount != 0) {
+		dev_err(sdev, "SPI data transfer error\n");
+		return -EIO;
+	}
 
 	return t->len;
 }
 
 /**
- * davinci_spi_irq - IRQ handler for DaVinci SPI
+ * davinci_spi_irq - Interrupt handler for SPI Master Controller
  * @irq: IRQ number for this SPI Master
  * @context_data: structure for SPI Master controller davinci_spi
+ *
+ * ISR will determine that interrupt arrives either for READ or WRITE command.
+ * According to command it will do the appropriate action. It will check
+ * transfer length and if it is not zero then dispatch transfer command again.
+ * If transfer length is zero then it will indicate the COMPLETION so that
+ * davinci_spi_bufs function can go ahead.
  */
-static irqreturn_t davinci_spi_irq(s32 irq, void *context_data)
+static irqreturn_t davinci_spi_irq(s32 irq, void *data)
 {
-	struct davinci_spi *davinci_spi = context_data;
-	u32 int_status, rx_data = 0;
-	irqreturn_t ret = IRQ_NONE;
+	struct davinci_spi *dspi = data;
+	int status;
 
-	int_status = ioread32(davinci_spi->base + SPIFLG);
+	status = davinci_spi_process_events(dspi);
+	if (unlikely(status != 0))
+		clear_io_bits(dspi->base + SPIINT, SPIINT_MASKINT);
 
-	while ((int_status & SPIFLG_RX_INTR_MASK)) {
-		if (likely(int_status & SPIFLG_RX_INTR_MASK)) {
-			ret = IRQ_HANDLED;
+	if ((!dspi->rcount && !dspi->wcount) || status)
+		complete(&dspi->done);
 
-			rx_data = ioread32(davinci_spi->base + SPIBUF);
-			davinci_spi->get_rx(rx_data, davinci_spi);
+	return IRQ_HANDLED;
+}
 
-			/* Disable Receive Interrupt */
-			iowrite32(~(SPIINT_RX_INTR | SPIINT_TX_INTR),
-					davinci_spi->base + SPIINT);
-		} else
-			(void)davinci_spi_check_error(davinci_spi, int_status);
+static int davinci_spi_request_dma(struct davinci_spi *dspi)
+{
+	int r;
+	struct davinci_spi_dma *dma = &dspi->dma;
 
-		int_status = ioread32(davinci_spi->base + SPIFLG);
+	r = edma_alloc_channel(dma->rx_channel, davinci_spi_dma_callback, dspi,
+								dma->eventq);
+	if (r < 0) {
+		pr_err("Unable to request DMA channel for SPI RX\n");
+		r = -EAGAIN;
+		goto rx_dma_failed;
 	}
 
-	return ret;
+	r = edma_alloc_channel(dma->tx_channel, davinci_spi_dma_callback, dspi,
+								dma->eventq);
+	if (r < 0) {
+		pr_err("Unable to request DMA channel for SPI TX\n");
+		r = -EAGAIN;
+		goto tx_dma_failed;
+	}
+
+	r = edma_alloc_slot(EDMA_CTLR(dma->tx_channel), EDMA_SLOT_ANY);
+	if (r < 0) {
+		pr_err("Unable to request SPI TX DMA param slot\n");
+		r = -EAGAIN;
+		goto param_failed;
+	}
+	dma->dummy_param_slot = r;
+	edma_link(dma->dummy_param_slot, dma->dummy_param_slot);
+
+	return 0;
+param_failed:
+	edma_free_channel(dma->tx_channel);
+tx_dma_failed:
+	edma_free_channel(dma->rx_channel);
+rx_dma_failed:
+	return r;
 }
 
 /**
  * davinci_spi_probe - probe function for SPI Master Controller
  * @pdev: platform_device structure which contains plateform specific data
+ *
+ * According to Linux Device Model this function will be invoked by Linux
+ * with platform_device struct which contains the device specific info.
+ * This function will map the SPI controller's memory, register IRQ,
+ * Reset SPI controller and setting its registers to default value.
+ * It will invoke spi_bitbang_start to create work queue so that client driver
+ * can register transfer method to work queue.
  */
 static int davinci_spi_probe(struct platform_device *pdev)
 {
 	struct spi_master *master;
-	struct davinci_spi *davinci_spi;
+	struct davinci_spi *dspi;
 	struct davinci_spi_platform_data *pdata;
 	struct resource *r, *mem;
 	resource_size_t dma_rx_chan = SPI_NO_RESOURCE;
 	resource_size_t	dma_tx_chan = SPI_NO_RESOURCE;
 	resource_size_t	dma_eventq = SPI_NO_RESOURCE;
 	int i = 0, ret = 0;
+	u32 spipc0;
 
 	pdata = pdev->dev.platform_data;
 	if (pdata == NULL) {
@@ -1035,8 +808,8 @@ static int davinci_spi_probe(struct platform_device *pdev)
 
 	dev_set_drvdata(&pdev->dev, master);
 
-	davinci_spi = spi_master_get_devdata(master);
-	if (davinci_spi == NULL) {
+	dspi = spi_master_get_devdata(master);
+	if (dspi == NULL) {
 		ret = -ENOENT;
 		goto free_master;
 	}
@@ -1047,164 +820,143 @@ static int davinci_spi_probe(struct platform_device *pdev)
 		goto free_master;
 	}
 
-	davinci_spi->pbase = r->start;
-	davinci_spi->region_size = resource_size(r);
-	davinci_spi->pdata = pdata;
+	dspi->pbase = r->start;
+	dspi->pdata = pdata;
 
-	mem = request_mem_region(r->start, davinci_spi->region_size,
-					pdev->name);
+	mem = request_mem_region(r->start, resource_size(r), pdev->name);
 	if (mem == NULL) {
 		ret = -EBUSY;
 		goto free_master;
 	}
 
-	davinci_spi->base = (struct davinci_spi_reg __iomem *)
-			ioremap(r->start, davinci_spi->region_size);
-	if (davinci_spi->base == NULL) {
+	dspi->base = ioremap(r->start, resource_size(r));
+	if (dspi->base == NULL) {
 		ret = -ENOMEM;
 		goto release_region;
 	}
 
-	davinci_spi->irq = platform_get_irq(pdev, 0);
-	if (davinci_spi->irq <= 0) {
+	dspi->irq = platform_get_irq(pdev, 0);
+	if (dspi->irq <= 0) {
 		ret = -EINVAL;
 		goto unmap_io;
 	}
 
-	ret = request_irq(davinci_spi->irq, davinci_spi_irq, IRQF_DISABLED,
-			  dev_name(&pdev->dev), davinci_spi);
+	ret = request_irq(dspi->irq, davinci_spi_irq, 0, dev_name(&pdev->dev),
+									dspi);
 	if (ret)
 		goto unmap_io;
 
-	/* Allocate tmp_buf for tx_buf */
-	davinci_spi->tmp_buf = kzalloc(SPI_BUFSIZ, GFP_KERNEL);
-	if (davinci_spi->tmp_buf == NULL) {
-		ret = -ENOMEM;
-		goto irq_free;
-	}
-
-	davinci_spi->bitbang.master = spi_master_get(master);
-	if (davinci_spi->bitbang.master == NULL) {
+	dspi->bitbang.master = spi_master_get(master);
+	if (dspi->bitbang.master == NULL) {
 		ret = -ENODEV;
-		goto free_tmp_buf;
+		goto irq_free;
 	}
 
-	davinci_spi->clk = clk_get(&pdev->dev, NULL);
-	if (IS_ERR(davinci_spi->clk)) {
+	dspi->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(dspi->clk)) {
 		ret = -ENODEV;
 		goto put_master;
 	}
-	clk_enable(davinci_spi->clk);
-
+	clk_enable(dspi->clk);
 
 	master->bus_num = pdev->id;
 	master->num_chipselect = pdata->num_chipselect;
 	master->setup = davinci_spi_setup;
-	master->cleanup = davinci_spi_cleanup;
-
-	davinci_spi->bitbang.chipselect = davinci_spi_chipselect;
-	davinci_spi->bitbang.setup_transfer = davinci_spi_setup_transfer;
-
-	davinci_spi->version = pdata->version;
-	use_dma = pdata->use_dma;
-
-	davinci_spi->bitbang.flags = SPI_NO_CS | SPI_LSB_FIRST | SPI_LOOP;
-	if (davinci_spi->version == SPI_VERSION_2)
-		davinci_spi->bitbang.flags |= SPI_READY;
-
-	if (use_dma) {
-			r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-			if (r)
-				dma_rx_chan = r->start;
-			r = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-			if (r)
-				dma_tx_chan = r->start;
-			r = platform_get_resource(pdev, IORESOURCE_DMA, 2);
-			if (r)
-				dma_eventq = r->start;
-	}
 
-	if (!use_dma ||
-	    dma_rx_chan == SPI_NO_RESOURCE ||
-	    dma_tx_chan == SPI_NO_RESOURCE ||
-	    dma_eventq	== SPI_NO_RESOURCE) {
-		davinci_spi->bitbang.txrx_bufs = davinci_spi_bufs_pio;
-		use_dma = 0;
-	} else {
-		davinci_spi->bitbang.txrx_bufs = davinci_spi_bufs_dma;
-		davinci_spi->dma_channels = kzalloc(master->num_chipselect
-				* sizeof(struct davinci_spi_dma), GFP_KERNEL);
-		if (davinci_spi->dma_channels == NULL) {
-			ret = -ENOMEM;
+	dspi->bitbang.chipselect = davinci_spi_chipselect;
+	dspi->bitbang.setup_transfer = davinci_spi_setup_transfer;
+
+	dspi->version = pdata->version;
+
+	dspi->bitbang.flags = SPI_NO_CS | SPI_LSB_FIRST | SPI_LOOP;
+	if (dspi->version == SPI_VERSION_2)
+		dspi->bitbang.flags |= SPI_READY;
+
+	r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
+	if (r)
+		dma_rx_chan = r->start;
+	r = platform_get_resource(pdev, IORESOURCE_DMA, 1);
+	if (r)
+		dma_tx_chan = r->start;
+	r = platform_get_resource(pdev, IORESOURCE_DMA, 2);
+	if (r)
+		dma_eventq = r->start;
+
+	dspi->bitbang.txrx_bufs = davinci_spi_bufs;
+	if (dma_rx_chan != SPI_NO_RESOURCE &&
+	    dma_tx_chan != SPI_NO_RESOURCE &&
+	    dma_eventq != SPI_NO_RESOURCE) {
+		dspi->dma.rx_channel = dma_rx_chan;
+		dspi->dma.tx_channel = dma_tx_chan;
+		dspi->dma.eventq = dma_eventq;
+
+		ret = davinci_spi_request_dma(dspi);
+		if (ret)
 			goto free_clk;
-		}
 
-		for (i = 0; i < master->num_chipselect; i++) {
-			davinci_spi->dma_channels[i].dma_rx_channel = -1;
-			davinci_spi->dma_channels[i].dma_rx_sync_dev =
-				dma_rx_chan;
-			davinci_spi->dma_channels[i].dma_tx_channel = -1;
-			davinci_spi->dma_channels[i].dma_tx_sync_dev =
-				dma_tx_chan;
-			davinci_spi->dma_channels[i].eventq = dma_eventq;
-		}
-		dev_info(&pdev->dev, "DaVinci SPI driver in EDMA mode\n"
-				"Using RX channel = %d , TX channel = %d and "
-				"event queue = %d", dma_rx_chan, dma_tx_chan,
+		dev_info(&pdev->dev, "DMA: supported\n");
+		dev_info(&pdev->dev, "DMA: RX channel: %d, TX channel: %d, "
+				"event queue: %d\n", dma_rx_chan, dma_tx_chan,
 				dma_eventq);
 	}
 
-	davinci_spi->get_rx = davinci_spi_rx_buf_u8;
-	davinci_spi->get_tx = davinci_spi_tx_buf_u8;
+	dspi->get_rx = davinci_spi_rx_buf_u8;
+	dspi->get_tx = davinci_spi_tx_buf_u8;
 
-	init_completion(&davinci_spi->done);
+	init_completion(&dspi->done);
 
 	/* Reset In/OUT SPI module */
-	iowrite32(0, davinci_spi->base + SPIGCR0);
+	iowrite32(0, dspi->base + SPIGCR0);
 	udelay(100);
-	iowrite32(1, davinci_spi->base + SPIGCR0);
+	iowrite32(1, dspi->base + SPIGCR0);
 
-	/* Clock internal */
-	if (davinci_spi->pdata->clk_internal)
-		set_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_CLKMOD_MASK);
-	else
-		clear_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_CLKMOD_MASK);
+	/* Set up SPIPC0.  CS and ENA init is done in davinci_spi_setup */
+	spipc0 = SPIPC0_DIFUN_MASK | SPIPC0_DOFUN_MASK | SPIPC0_CLKFUN_MASK;
+	iowrite32(spipc0, dspi->base + SPIPC0);
 
-	/* master mode default */
-	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_MASTER_MASK);
+	/* initialize chip selects */
+	if (pdata->chip_sel) {
+		for (i = 0; i < pdata->num_chipselect; i++) {
+			if (pdata->chip_sel[i] != SPI_INTERN_CS)
+				gpio_direction_output(pdata->chip_sel[i], 1);
+		}
+	}
 
-	if (davinci_spi->pdata->intr_level)
-		iowrite32(SPI_INTLVL_1, davinci_spi->base + SPILVL);
+	if (pdata->intr_line)
+		iowrite32(SPI_INTLVL_1, dspi->base + SPILVL);
 	else
-		iowrite32(SPI_INTLVL_0, davinci_spi->base + SPILVL);
+		iowrite32(SPI_INTLVL_0, dspi->base + SPILVL);
 
-	ret = spi_bitbang_start(&davinci_spi->bitbang);
-	if (ret)
-		goto free_clk;
+	iowrite32(CS_DEFAULT, dspi->base + SPIDEF);
 
-	dev_info(&pdev->dev, "Controller at 0x%p \n", davinci_spi->base);
+	/* master mode default */
+	set_io_bits(dspi->base + SPIGCR1, SPIGCR1_CLKMOD_MASK);
+	set_io_bits(dspi->base + SPIGCR1, SPIGCR1_MASTER_MASK);
+	set_io_bits(dspi->base + SPIGCR1, SPIGCR1_POWERDOWN_MASK);
+
+	ret = spi_bitbang_start(&dspi->bitbang);
+	if (ret)
+		goto free_dma;
 
-	if (!pdata->poll_mode)
-		dev_info(&pdev->dev, "Operating in interrupt mode"
-			" using IRQ %d\n", davinci_spi->irq);
+	dev_info(&pdev->dev, "Controller at 0x%p\n", dspi->base);
 
 	return ret;
 
+free_dma:
+	edma_free_channel(dspi->dma.tx_channel);
+	edma_free_channel(dspi->dma.rx_channel);
+	edma_free_slot(dspi->dma.dummy_param_slot);
 free_clk:
-	clk_disable(davinci_spi->clk);
-	clk_put(davinci_spi->clk);
+	clk_disable(dspi->clk);
+	clk_put(dspi->clk);
 put_master:
 	spi_master_put(master);
-free_tmp_buf:
-	kfree(davinci_spi->tmp_buf);
 irq_free:
-	free_irq(davinci_spi->irq, davinci_spi);
+	free_irq(dspi->irq, dspi);
 unmap_io:
-	iounmap(davinci_spi->base);
+	iounmap(dspi->base);
 release_region:
-	release_mem_region(davinci_spi->pbase, davinci_spi->region_size);
+	release_mem_region(dspi->pbase, resource_size(r));
 free_master:
 	kfree(master);
 err:
@@ -1222,27 +974,31 @@ err:
  */
 static int __exit davinci_spi_remove(struct platform_device *pdev)
 {
-	struct davinci_spi *davinci_spi;
+	struct davinci_spi *dspi;
 	struct spi_master *master;
+	struct resource *r;
 
 	master = dev_get_drvdata(&pdev->dev);
-	davinci_spi = spi_master_get_devdata(master);
+	dspi = spi_master_get_devdata(master);
 
-	spi_bitbang_stop(&davinci_spi->bitbang);
+	spi_bitbang_stop(&dspi->bitbang);
 
-	clk_disable(davinci_spi->clk);
-	clk_put(davinci_spi->clk);
+	clk_disable(dspi->clk);
+	clk_put(dspi->clk);
 	spi_master_put(master);
-	kfree(davinci_spi->tmp_buf);
-	free_irq(davinci_spi->irq, davinci_spi);
-	iounmap(davinci_spi->base);
-	release_mem_region(davinci_spi->pbase, davinci_spi->region_size);
+	free_irq(dspi->irq, dspi);
+	iounmap(dspi->base);
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(dspi->pbase, resource_size(r));
 
 	return 0;
 }
 
 static struct platform_driver davinci_spi_driver = {
-	.driver.name = "spi_davinci",
+	.driver = {
+		.name = "spi_davinci",
+		.owner = THIS_MODULE,
+	},
 	.remove = __exit_p(davinci_spi_remove),
 };