diff mbox

[1/2,v2] spi: overhaul davinci spi driver to correct multiple errors

Message ID 1268422520-22642-2-git-send-email-bniebuhr@efjohnson.com (mailing list archive)
State Rejected
Headers show

Commit Message

Brian Niebuhr March 12, 2010, 7:35 p.m. UTC
None
diff mbox

Patch

diff --git a/arch/arm/mach-davinci/include/mach/spi.h b/arch/arm/mach-davinci/include/mach/spi.h
index 7b54926..10c39d8 100644
--- a/arch/arm/mach-davinci/include/mach/spi.h
+++ b/arch/arm/mach-davinci/include/mach/spi.h
@@ -34,18 +34,24 @@  enum {
 struct davinci_spi_platform_data {
 	u8	version;
 	u16	num_chipselect;
-	u32	wdelay;
-	u32	odd_parity;
-	u32	parity_enable;
-	u32	wait_enable;
-	u32	timer_disable;
-	u32	clk_internal;
-	u32	cs_hold;
-	u32	intr_level;
-	u32	poll_mode;
-	u32	use_dma;
-	u8	c2tdelay;
-	u8	t2cdelay;
+	u8	*chip_sel;
+};
+
+struct davinci_spi_config {
+	u32     odd_parity:1;
+	u32     parity_enable:1;
+	u32     intr_level:1;
+	u32     io_type:2;
+#define SPI_IO_TYPE_INTR    0
+#define SPI_IO_TYPE_POLL    1
+#define SPI_IO_TYPE_DMA     2
+	u32     bytes_per_word:2;
+	u32     wdelay:6;
+	u32     timer_disable:1;
+	u8      c2t_delay;
+	u8      t2c_delay;
+	u8      t2e_delay;
+	u8      c2e_delay;
 };
 
 #endif	/* __ARCH_ARM_DAVINCI_SPI_H */
diff --git a/drivers/spi/davinci_spi.c b/drivers/spi/davinci_spi.c
index 956f617..0bed840 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
@@ -33,43 +34,45 @@ 
 
 #include "davinci_spi.h"
 
-static unsigned use_dma;
-
 #define	DAVINCI_SPI_NO_RESOURCE		((resource_size_t)-1)
 
 static void davinci_spi_rx_buf_u8(u32 data, struct davinci_spi *davinci_spi)
 {
-	u8 *rx = davinci_spi->rx;
-
-	*rx++ = (u8)data;
-	davinci_spi->rx = rx;
+	if (davinci_spi->rx) {
+		u8 *rx = davinci_spi->rx;
+		*rx++ = (u8)data;
+		davinci_spi->rx = rx;
+	}
 }
 
 static void davinci_spi_rx_buf_u16(u32 data, struct davinci_spi *davinci_spi)
 {
-	u16 *rx = davinci_spi->rx;
-
-	*rx++ = (u16)data;
-	davinci_spi->rx = rx;
+	if (davinci_spi->rx) {
+		u16 *rx = davinci_spi->rx;
+		*rx++ = (u16)data;
+		davinci_spi->rx = rx;
+	}
 }
 
 static u32 davinci_spi_tx_buf_u8(struct davinci_spi *davinci_spi)
 {
-	u32 data;
-	const u8 *tx = davinci_spi->tx;
-
-	data = *tx++;
-	davinci_spi->tx = tx;
+	u32 data = 0;
+	if (davinci_spi->tx) {
+		const u8 *tx = davinci_spi->tx;
+		data = *tx++;
+		davinci_spi->tx = tx;
+	}
 	return data;
 }
 
 static u32 davinci_spi_tx_buf_u16(struct davinci_spi *davinci_spi)
 {
-	u32 data;
-	const u16 *tx = davinci_spi->tx;
-
-	data = *tx++;
-	davinci_spi->tx = tx;
+	u32 data = 0;
+	if (davinci_spi->tx) {
+		const u16 *tx = davinci_spi->tx;
+		data = *tx++;
+		davinci_spi->tx = tx;
+	}
 	return data;
 }
 
@@ -89,26 +92,6 @@  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
  */
@@ -116,25 +99,54 @@  static void davinci_spi_chipselect(struct spi_device *spi, int value)
 {
 	struct davinci_spi *davinci_spi;
 	struct davinci_spi_platform_data *pdata;
-	u32 data1_reg_val = 0;
+	u8 i, chip_sel = spi->chip_select;
+	u32 spidat1;
+	u16 spidat1_cfg;
 
 	davinci_spi = spi_master_get_devdata(spi->master);
 	pdata = davinci_spi->pdata;
 
-	/*
-	 * Board specific chip select logic decides the polarity and cs
-	 * line for the controller
-	 */
-	if (value == BITBANG_CS_INACTIVE) {
-		set_io_bits(davinci_spi->base + SPIDEF, CS_DEFAULT);
-
-		data1_reg_val |= CS_DEFAULT << SPIDAT1_CSNR_SHIFT;
-		iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
+	spidat1 = SPIDAT1_CSNR_MASK;
+	if (value == BITBANG_CS_ACTIVE)
+		spidat1 |= SPIDAT1_CSHOLD_MASK;
+	else
+		spidat1 |= SPIDAT1_WDEL_MASK;
 
-		while ((ioread32(davinci_spi->base + SPIBUF)
-					& SPIBUF_RXEMPTY_MASK) == 0)
-			cpu_relax();
+	if (pdata->chip_sel == NULL) {
+		if (value == BITBANG_CS_ACTIVE)
+			spidat1 &= ~((0x1 << chip_sel) << SPIDAT1_CSNR_SHIFT);
+	} else {
+		for (i = 0; i < pdata->num_chipselect; i++) {
+			if (pdata->chip_sel[i] == SPI_INTERN_CS) {
+				if ((i == chip_sel) &&
+				    (value == BITBANG_CS_ACTIVE)) {
+					spidat1 &= ~((0x1 << chip_sel)
+						<< SPIDAT1_CSNR_SHIFT);
+				}
+			} else {
+				if (value == BITBANG_CS_INACTIVE)
+					gpio_set_value(pdata->chip_sel[i], 1);
+				else if (i == chip_sel)
+					gpio_set_value(pdata->chip_sel[i], 0);
+			}
+		}
 	}
+
+	spidat1_cfg = spidat1 >> SPIDAT1_CSNR_SHIFT;
+	iowrite16(spidat1_cfg, davinci_spi->base + SPIDAT1 + 2);
+}
+
+/*
+ * davinci_spi_get_prescale - Calculates the correct prescale value
+ * @max_speed_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
+ */
+static inline u32 davinci_spi_get_prescale(struct davinci_spi *davinci_spi,
+						u32 max_speed_hz)
+{
+	return ((clk_get_rate(davinci_spi->clk) - 1) / max_speed_hz) & 0xff;
 }
 
 /*
@@ -149,14 +161,15 @@  static void davinci_spi_chipselect(struct spi_device *spi, int value)
 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_config *spi_cfg;
 	u8 bits_per_word = 0;
-	u32 hz = 0, prescale;
+	u32 hz = 0, spifmt = 0, prescale, delay = 0;
 
 	davinci_spi = spi_master_get_devdata(spi->master);
 	pdata = davinci_spi->pdata;
+	spi_cfg = spi->controller_data;
 
 	if (t) {
 		bits_per_word = t->bits_per_word;
@@ -174,72 +187,112 @@  static int davinci_spi_setup_transfer(struct spi_device *spi,
 	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;
+		spi_cfg->bytes_per_word = 1;
 	} else if (bits_per_word <= 16 && bits_per_word >= 2) {
 		davinci_spi->get_rx = davinci_spi_rx_buf_u16;
 		davinci_spi->get_tx = davinci_spi_tx_buf_u16;
-		davinci_spi->slave[spi->chip_select].bytes_per_word = 2;
+		spi_cfg->bytes_per_word = 2;
 	} else
 		return -EINVAL;
 
 	if (!hz)
 		hz = spi->max_speed_hz;
 
-	clear_fmt_bits(davinci_spi->base, SPIFMT_CHARLEN_MASK,
-			spi->chip_select);
-	set_fmt_bits(davinci_spi->base, bits_per_word & 0x1f,
-			spi->chip_select);
+	prescale = davinci_spi_get_prescale(davinci_spi, hz);
+	spifmt |= (prescale << SPIFMT_PRESCALE_SHIFT);
+
+	spifmt |= (bits_per_word & 0x1f);
+
+	if (spi->mode & SPI_LSB_FIRST)
+		spifmt |= SPIFMT_SHIFTDIR_MASK;
+
+	if (spi->mode & SPI_CPOL)
+		spifmt |= SPIFMT_POLARITY_MASK;
+
+	if (!(spi->mode & SPI_CPHA))
+		spifmt |= SPIFMT_PHASE_MASK;
 
-	prescale = ((clk_get_rate(davinci_spi->clk) / hz) - 1) & 0xff;
+	if (davinci_spi->version == SPI_VERSION_2) {
+		spifmt |= ((spi_cfg->wdelay << SPIFMT_WDELAY_SHIFT)
+				& SPIFMT_WDELAY_MASK);
+
+		if (spi_cfg->odd_parity)
+			spifmt |= SPIFMT_ODD_PARITY_MASK;
+
+		if (spi_cfg->parity_enable)
+			spifmt |= SPIFMT_PARITYENA_MASK;
+
+		if (spi->mode & SPI_READY) {
+			spifmt |= SPIFMT_WAITENA_MASK;
+			delay |= (spi_cfg->t2e_delay
+					<< SPIDELAY_T2EDELAY_SHIFT)
+						& SPIDELAY_T2EDELAY_MASK;
+			delay |= (spi_cfg->c2e_delay
+					<< SPIDELAY_C2EDELAY_SHIFT)
+						& SPIDELAY_C2EDELAY_MASK;
+		}
 
-	clear_fmt_bits(davinci_spi->base, 0x0000ff00, spi->chip_select);
-	set_fmt_bits(davinci_spi->base, prescale << 8, spi->chip_select);
+		if (spi_cfg->timer_disable) {
+			spifmt |= SPIFMT_DISTIMER_MASK;
+		} else {
+			delay |= (spi_cfg->c2t_delay
+					<< SPIDELAY_C2TDELAY_SHIFT)
+						& SPIDELAY_C2TDELAY_MASK;
+			delay |= (spi_cfg->t2c_delay
+					<< SPIDELAY_T2CDELAY_SHIFT)
+						& SPIDELAY_T2CDELAY_MASK;
+		}
+
+		iowrite32(delay, davinci_spi->base + SPIDELAY);
+	}
+
+	iowrite32(spifmt, davinci_spi->base + SPIFMT0);
+
+	if (spi_cfg->intr_level)
+		iowrite32(SPI_INTLVL_1, davinci_spi->base + SPILVL);
+	else
+		iowrite32(SPI_INTLVL_0, davinci_spi->base + SPILVL);
+
+	if (spi->mode & SPI_LOOP)
+		set_io_bits(davinci_spi->base + SPIGCR1,
+				SPIGCR1_LOOPBACK_MASK);
+	else
+		clear_io_bits(davinci_spi->base + SPIGCR1,
+				SPIGCR1_LOOPBACK_MASK);
 
 	return 0;
 }
 
 static 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 *davinci_spi = (struct davinci_spi *)data;
 	struct davinci_spi_dma *davinci_spi_dma;
 	struct davinci_spi_platform_data *pdata;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	davinci_spi_dma = &(davinci_spi->dma_channels[spi->chip_select]);
+	davinci_spi_dma = &(davinci_spi->dma_channels);
 	pdata = davinci_spi->pdata;
 
-	if (ch_status == DMA_COMPLETE)
-		edma_stop(davinci_spi_dma->dma_rx_channel);
-	else
-		edma_clean_channel(davinci_spi_dma->dma_rx_channel);
+	edma_stop(davinci_spi_dma->dma_rx_channel);
 
-	complete(&davinci_spi_dma->dma_rx_completion);
-	/* We must disable the DMA RX request */
-	davinci_spi_set_dma_req(spi, 0);
+	if (ch_status == DMA_COMPLETE)
+		davinci_spi->rcount = 0;
 
+	complete(&davinci_spi->done);
 }
 
 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 *davinci_spi = (struct davinci_spi *)data;
 	struct davinci_spi_dma *davinci_spi_dma;
 	struct davinci_spi_platform_data *pdata;
 
-	davinci_spi = spi_master_get_devdata(spi->master);
-	davinci_spi_dma = &(davinci_spi->dma_channels[spi->chip_select]);
+	davinci_spi_dma = &(davinci_spi->dma_channels);
 	pdata = davinci_spi->pdata;
 
-	if (ch_status == DMA_COMPLETE)
-		edma_stop(davinci_spi_dma->dma_tx_channel);
-	else
-		edma_clean_channel(davinci_spi_dma->dma_tx_channel);
-
-	complete(&davinci_spi_dma->dma_tx_completion);
-	/* We must disable the DMA TX request */
-	davinci_spi_set_dma_req(spi, 0);
+	edma_stop(davinci_spi_dma->dma_tx_channel);
 
+	if (ch_status == DMA_COMPLETE)
+		davinci_spi->wcount = 0;
 }
 
 static int davinci_spi_request_dma(struct spi_device *spi)
@@ -251,30 +304,51 @@  static int davinci_spi_request_dma(struct spi_device *spi)
 	int r;
 
 	davinci_spi = spi_master_get_devdata(spi->master);
-	davinci_spi_dma = &davinci_spi->dma_channels[spi->chip_select];
+	davinci_spi_dma = &davinci_spi->dma_channels;
 	pdata = davinci_spi->pdata;
 	sdev = davinci_spi->bitbang.master->dev.parent;
 
 	r = edma_alloc_channel(davinci_spi_dma->dma_rx_sync_dev,
-				davinci_spi_dma_rx_callback, spi,
+				davinci_spi_dma_rx_callback, davinci_spi,
 				davinci_spi_dma->eventq);
 	if (r < 0) {
 		dev_dbg(sdev, "Unable to request DMA channel for MibSPI RX\n");
-		return -EAGAIN;
+		r =  -EAGAIN;
+		goto rx_dma_failed;
 	}
 	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_tx_callback, davinci_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 MibSPI TX\n");
-		return -EAGAIN;
+		r = -EAGAIN;
+		goto tx_dma_failed;
 	}
 	davinci_spi_dma->dma_tx_channel = r;
 
+	r = edma_alloc_slot(EDMA_CTLR(davinci_spi_dma->dma_tx_sync_dev),
+				EDMA_SLOT_ANY);
+	if (r < 0) {
+		dev_dbg(sdev, "Unable to request SPI DMA param slot\n");
+		r = -EAGAIN;
+		goto param_failed;
+	}
+	davinci_spi_dma->dummy_param_slot = r;
+	edma_link(davinci_spi_dma->dummy_param_slot,
+		  davinci_spi_dma->dummy_param_slot);
+
 	return 0;
+
+param_failed:
+	edma_free_channel(davinci_spi_dma->dma_tx_channel);
+	davinci_spi_dma->dma_tx_channel = -1;
+tx_dma_failed:
+	edma_free_channel(davinci_spi_dma->dma_rx_channel);
+	davinci_spi_dma->dma_rx_channel = -1;
+rx_dma_failed:
+	return r;
 }
 
 /*
@@ -286,124 +360,51 @@  static int davinci_spi_request_dma(struct spi_device *spi)
 
 static int davinci_spi_setup(struct spi_device *spi)
 {
-	int retval;
+	int retval = 0;
 	struct davinci_spi *davinci_spi;
-	struct davinci_spi_dma *davinci_spi_dma;
+	struct davinci_spi_dma *davinci_dma;
+	struct davinci_spi_platform_data *pdata;
+	struct davinci_spi_config *spi_cfg;
+	u32 prescale;
 
 	davinci_spi = spi_master_get_devdata(spi->master);
+	pdata = davinci_spi->pdata;
+	spi_cfg = (struct davinci_spi_config *)spi->controller_data;
+	davinci_dma = &(davinci_spi->dma_channels);
 
 	/* 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 (!(spi->mode & SPI_NO_CS)) {
+		if ((pdata->chip_sel == NULL) ||
+		    (pdata->chip_sel[spi->chip_select] == SPI_INTERN_CS))
+			set_io_bits(davinci_spi->base + SPIPC0,
+					1 << 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)
-		return -EINVAL;
+	if (spi->mode & SPI_READY)
+		set_io_bits(davinci_spi->base + SPIPC0, SPIPC0_SPIENA_MASK);
 
-	/*
-	 * 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_cfg->io_type == SPI_IO_TYPE_DMA) {
+		davinci_dma = &(davinci_spi->dma_channels);
 
-	if (spi->mode & SPI_CPOL)
-		set_fmt_bits(davinci_spi->base, SPIFMT_POLARITY_MASK,
-				spi->chip_select);
-	else
-		clear_fmt_bits(davinci_spi->base, SPIFMT_POLARITY_MASK,
-				spi->chip_select);
-
-	if (!(spi->mode & SPI_CPHA))
-		set_fmt_bits(davinci_spi->base, SPIFMT_PHASE_MASK,
-				spi->chip_select);
-	else
-		clear_fmt_bits(davinci_spi->base, SPIFMT_PHASE_MASK,
-				spi->chip_select);
+		if ((davinci_dma->dma_tx_sync_dev == DAVINCI_SPI_NO_RESOURCE) ||
+		    (davinci_dma->dma_rx_sync_dev == DAVINCI_SPI_NO_RESOURCE) ||
+		    (davinci_dma->eventq == DAVINCI_SPI_NO_RESOURCE))
+			spi_cfg->io_type = SPI_IO_TYPE_INTR;
+		else if ((davinci_dma->dma_rx_channel == -1) ||
+			 (davinci_dma->dma_tx_channel == -1))
+			retval = davinci_spi_request_dma(spi);
+	}
 
 	/*
-	 * 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)
+	 * Validate desired clock rate
 	 */
-
-	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);
+	prescale = davinci_spi_get_prescale(davinci_spi, spi->max_speed_hz);
+	if ((prescale < 2) || (prescale > 255))
+		return -EINVAL;
 
 	return retval;
 }
@@ -412,50 +413,19 @@  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;
+	struct davinci_spi_platform_data *pdata;
 
-	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;
+	davinci_spi_dma = &davinci_spi->dma_channels;
+	pdata = davinci_spi->pdata;
 
-	iowrite32(op_mode, davinci_spi->base + SPIPC0);
+	if (davinci_spi_dma->dma_rx_channel != -1)
+		edma_free_channel(davinci_spi_dma->dma_rx_channel);
 
-	if (spi->mode & SPI_LOOP)
-		set_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_LOOPBACK_MASK);
-	else
-		clear_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_LOOPBACK_MASK);
+	if (davinci_spi_dma->dma_tx_channel != -1)
+		edma_free_channel(davinci_spi_dma->dma_tx_channel);
 
-	return 0;
+	if (davinci_spi_dma->dummy_param_slot != -1)
+		edma_free_slot(davinci_spi_dma->dummy_param_slot);
 }
 
 static int davinci_spi_check_error(struct davinci_spi *davinci_spi,
@@ -503,329 +473,190 @@  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
+ * @davinci_spi - 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 *davinci_spi)
 {
-	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 bbased on bits_per_word */
-	conv = davinci_spi->slave[spi->chip_select].bytes_per_word;
-	davinci_spi->count = t->len / conv;
-
-	INIT_COMPLETION(davinci_spi->done);
-
-	ret = davinci_spi_bufs_prep(spi, davinci_spi);
-	if (ret)
-		return ret;
-
-	/* Enable SPI */
-	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
-
-	iowrite32(0 | (pdata->c2tdelay << SPI_C2TDELAY_SHIFT) |
-			(pdata->t2cdelay << SPI_T2CDELAY_SHIFT),
-			davinci_spi->base + SPIDELAY);
-
-	count = davinci_spi->count;
-	data1_reg_val = pdata->cs_hold << SPIDAT1_CSHOLD_SHIFT;
-	tmp = ~(0x1 << spi->chip_select);
-
-	clear_io_bits(davinci_spi->base + SPIDEF, ~tmp);
-
-	data1_reg_val |= tmp << SPIDAT1_CSNR_SHIFT;
-
-	while ((ioread32(davinci_spi->base + SPIBUF)
-				& SPIBUF_RXEMPTY_MASK) == 0)
-		cpu_relax();
-
-	/* Determine the command to execute READ or WRITE */
-	if (t->tx_buf) {
-		clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
-
-		while (1) {
-			tx_data = davinci_spi->get_tx(davinci_spi);
-
-			data1_reg_val &= ~(0xFFFF);
-			data1_reg_val |= (0xFFFF & tx_data);
-
-			buf_val = ioread32(davinci_spi->base + SPIBUF);
-			if ((buf_val & SPIBUF_TXFULL_MASK) == 0) {
-				iowrite32(data1_reg_val,
-						davinci_spi->base + SPIDAT1);
-
-				count--;
-			}
-			while (ioread32(davinci_spi->base + SPIBUF)
-					& SPIBUF_RXEMPTY_MASK)
-				cpu_relax();
-
-			/* getting the returned byte */
-			if (t->rx_buf) {
-				buf_val = ioread32(davinci_spi->base + SPIBUF);
-				davinci_spi->get_rx(buf_val, davinci_spi);
-			}
-			if (count <= 0)
-				break;
-		}
-	} else {
-		if (pdata->poll_mode) {
-			while (1) {
-				/* keeps the serial clock going */
-				if ((ioread32(davinci_spi->base + SPIBUF)
-						& SPIBUF_TXFULL_MASK) == 0)
-					iowrite32(data1_reg_val,
-						davinci_spi->base + SPIDAT1);
-
-				while (ioread32(davinci_spi->base + SPIBUF) &
-						SPIBUF_RXEMPTY_MASK)
-					cpu_relax();
-
-				flg_val = ioread32(davinci_spi->base + SPIFLG);
-				buf_val = ioread32(davinci_spi->base + SPIBUF);
-
-				davinci_spi->get_rx(buf_val, davinci_spi);
-
-				count--;
-				if (count <= 0)
-					break;
-			}
-		} else {	/* Receive in Interrupt mode */
-			int i;
-
-			for (i = 0; i < davinci_spi->count; i++) {
-				set_io_bits(davinci_spi->base + SPIINT,
-						SPIINT_BITERR_INTR
-						| SPIINT_OVRRUN_INTR
-						| SPIINT_RX_INTR);
-
-				iowrite32(data1_reg_val,
-						davinci_spi->base + SPIDAT1);
-
-				while (ioread32(davinci_spi->base + SPIINT) &
-						SPIINT_RX_INTR)
-					cpu_relax();
-			}
-			iowrite32((data1_reg_val & 0x0ffcffff),
-					davinci_spi->base + SPIDAT1);
-		}
+	u32 status, tx_data, rx_data, spidat1;
+	u8 tx_word = 0;
+
+	status = ioread32(davinci_spi->base + SPIFLG);
+
+	if ((davinci_spi->version == SPI_VERSION_2) &&
+	    (likely(status & SPIFLG_TX_INTR_MASK)) &&
+	    (likely(davinci_spi->wcount > 0)))
+		tx_word = 1;
+
+	if (likely(status & SPIFLG_RX_INTR_MASK)) {
+		rx_data = ioread32(davinci_spi->base + SPIBUF) & 0xFFFF;
+		davinci_spi->get_rx(rx_data, davinci_spi);
+		davinci_spi->rcount--;
+		if ((davinci_spi->version != SPI_VERSION_2) &&
+		    (likely(davinci_spi->wcount > 0)))
+			tx_word = 1;
 	}
 
-	/*
-	 * 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;
+	if (unlikely(status & SPIFLG_ERROR_MASK)) {
+		davinci_spi->errors = (status & SPIFLG_ERROR_MASK);
+		return -1;
+	}
 
-	/* SPI Framework maintains the count only in bytes so convert back */
-	davinci_spi->count *= conv;
+	if (likely(tx_word)) {
+		spidat1 = ioread32(davinci_spi->base + SPIDAT1);
+		davinci_spi->wcount--;
+		tx_data = davinci_spi->get_tx(davinci_spi);
+		spidat1 &= 0xFFFF0000;
+		spidat1 |= (tx_data & 0xFFFF);
+		iowrite32(spidat1, davinci_spi->base + SPIDAT1);
+	}
 
-	return t->len;
+	return 0;
 }
 
-#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_txrx_bufs - function 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_txrx_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct davinci_spi *davinci_spi;
-	int int_status = 0;
-	int 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;
+	int data_type, ret = 0;
+	u32 tx_data, spidat1;
+	u16 tx_buf_count = 0, rx_buf_count = 0;
+	struct davinci_spi_config *spi_cfg;
 	struct davinci_spi_platform_data *pdata;
+	struct davinci_spi_dma *davinci_dma;
 	struct device *sdev;
+	dma_addr_t tx_reg, rx_reg;
+	void *tx_buf, *rx_buf;
+	struct edmacc_param rx_param, tx_param;
 
 	davinci_spi = spi_master_get_devdata(spi->master);
 	pdata = davinci_spi->pdata;
-	sdev = davinci_spi->bitbang.master->dev.parent;
-
-	BUG_ON(davinci_spi->dma_channels == NULL);
-
-	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;
+	spi_cfg = (struct davinci_spi_config *)spi->controller_data;
+	davinci_dma = &(davinci_spi->dma_channels);
 
-	/* used for macro defs */
 	davinci_spi->tx = t->tx_buf;
 	davinci_spi->rx = t->rx_buf;
+	davinci_spi->wcount = t->len / spi_cfg->bytes_per_word;
+	davinci_spi->rcount = davinci_spi->wcount;
+	davinci_spi->errors = 0;
 
-	/* 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;
+	spidat1 = ioread32(davinci_spi->base + SPIDAT1);
 
-	INIT_COMPLETION(davinci_spi->done);
-
-	init_completion(&davinci_spi_dma->dma_rx_completion);
-	init_completion(&davinci_spi_dma->dma_tx_completion);
-
-	word_len = conv * 8;
-
-	if (word_len <= 8)
-		data_type = DAVINCI_DMA_DATA_TYPE_S8;
-	else if (word_len <= 16)
-		data_type = DAVINCI_DMA_DATA_TYPE_S16;
-	else if (word_len <= 32)
-		data_type = DAVINCI_DMA_DATA_TYPE_S32;
-	else
-		return -1;
-
-	ret = davinci_spi_bufs_prep(spi, davinci_spi);
-	if (ret)
-		return ret;
-
-	/* Put delay val if required */
-	iowrite32(0 | (pdata->c2tdelay << SPI_C2TDELAY_SHIFT) |
-			(pdata->t2cdelay << SPI_T2CDELAY_SHIFT),
-			davinci_spi->base + SPIDELAY);
-
-	count = davinci_spi->count;	/* the number of elements */
-	data1_reg_val = pdata->cs_hold << SPIDAT1_CSHOLD_SHIFT;
-
-	/* CD default = 0xFF */
-	tmp = ~(0x1 << spi->chip_select);
-
-	clear_io_bits(davinci_spi->base + SPIDEF, ~tmp);
-
-	data1_reg_val |= tmp << SPIDAT1_CSNR_SHIFT;
-
-	/* disable all interrupts for dma transfers */
-	clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
-	/* Disable SPI to write configuration bits in SPIDAT */
-	clear_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
-	iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
-	/* Enable SPI */
+	clear_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_POWERDOWN_MASK);
 	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
 
-	while ((ioread32(davinci_spi->base + SPIBUF)
-				& SPIBUF_RXEMPTY_MASK) == 0)
-		cpu_relax();
-
+	INIT_COMPLETION(davinci_spi->done);
 
-	if (t->tx_buf != NULL) {
-		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, "Couldn't DMA map a %d bytes TX buffer\n",
-					count);
-			return -1;
+	if ((spi_cfg->io_type == SPI_IO_TYPE_INTR) ||
+	    (spi_cfg->io_type == SPI_IO_TYPE_POLL)) {
+
+		if (spi_cfg->io_type == SPI_IO_TYPE_INTR)
+			set_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKINT);
+
+		/* start the transfer */
+		davinci_spi->wcount--;
+		tx_data = davinci_spi->get_tx(davinci_spi);
+		spidat1 &= 0xFFFF0000;
+		spidat1 |= (tx_data & 0xFFFF);
+		iowrite32(spidat1, davinci_spi->base + SPIDAT1);
+
+	} else if (spi_cfg->io_type == SPI_IO_TYPE_DMA) {
+		data_type = spi_cfg->bytes_per_word;
+		tx_reg = (dma_addr_t)davinci_spi->pbase + SPIDAT1;
+		rx_reg = (dma_addr_t)davinci_spi->pbase + SPIBUF;
+
+		if (t->tx_buf) {
+			tx_buf = ((void *)t->tx_buf);
+			tx_buf_count = davinci_spi->wcount;
+		} else {
+			tx_buf = (void *)davinci_spi->tmp_buf;
+			tx_buf_count = SPI_BUFSIZ;
 		}
-		edma_set_transfer_params(davinci_spi_dma->dma_tx_channel, data_type,
-			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);
-	} 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, "Couldn't DMA map a %d bytes TX tmp buffer\n",
-					count);
-			return -1;
+		if (t->rx_buf) {
+			rx_buf = (void *)t->rx_buf;
+			rx_buf_count = davinci_spi->rcount;
+		} else {
+			rx_buf = (void *)davinci_spi->tmp_buf;
+			rx_buf_count = SPI_BUFSIZ;
 		}
-		edma_set_transfer_params(davinci_spi_dma->dma_tx_channel,
-				data_type, count + 1, 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);
+
+		t->tx_dma = dma_map_single(&spi->dev, tx_buf,
+						tx_buf_count, DMA_TO_DEVICE);
+		t->rx_dma = dma_map_single(&spi->dev, rx_buf,
+						rx_buf_count, DMA_FROM_DEVICE);
+
+		tx_param.opt = TCINTEN | EDMA_TCC(davinci_dma->dma_tx_channel);
+		tx_param.src = t->tx_buf ? t->tx_dma : tx_reg;
+		tx_param.a_b_cnt = davinci_spi->wcount << 16 | data_type;
+		tx_param.dst = tx_reg;
+		tx_param.src_dst_bidx = t->tx_buf ? data_type : 0;
+		tx_param.link_bcntrld = 0xffff;
+		tx_param.src_dst_cidx = 0;
+		tx_param.ccnt = 1;
+		edma_write_slot(davinci_dma->dma_tx_channel, &tx_param);
+		edma_link(davinci_dma->dma_tx_channel,
+			  davinci_dma->dummy_param_slot);
+
+		rx_param.opt = TCINTEN | EDMA_TCC(davinci_dma->dma_rx_channel);
+		rx_param.src = rx_reg;
+		rx_param.a_b_cnt = davinci_spi->rcount << 16 | data_type;
+		rx_param.dst = t->rx_dma;
+		rx_param.src_dst_bidx = (t->rx_buf ? data_type : 0) << 16;
+		rx_param.link_bcntrld = 0xffff;
+		rx_param.src_dst_cidx = 0;
+		rx_param.ccnt = 1;
+		edma_write_slot(davinci_dma->dma_rx_channel, &rx_param);
+
+		iowrite16(spidat1 >> SPIDAT1_CSNR_SHIFT,
+				davinci_spi->base + SPIDAT1 + 2);
+
+		edma_start(davinci_dma->dma_rx_channel);
+		edma_start(davinci_dma->dma_tx_channel);
+		set_io_bits(davinci_spi->base + SPIINT, SPIINT_DMA_REQ_EN);
 	}
 
-	if (t->rx_buf != NULL) {
-		/* initiate transaction */
-		iowrite32(data1_reg_val, davinci_spi->base + SPIDAT1);
-
-		t->rx_dma = dma_map_single(&spi->dev, (void *)t->rx_buf, count,
-				DMA_FROM_DEVICE);
-		if (dma_mapping_error(&spi->dev, t->rx_dma)) {
-			dev_dbg(sdev, "Couldn't DMA map a %d bytes RX buffer\n",
-					count);
-			if (t->tx_buf != NULL)
-				dma_unmap_single(NULL, t->tx_dma,
-						 count, DMA_TO_DEVICE);
-			return -1;
+	/* Wait for the transfer to complete */
+	if (spi_cfg->io_type != SPI_IO_TYPE_POLL) {
+		wait_for_completion_interruptible(&(davinci_spi->done));
+	} else {
+		while ((davinci_spi->rcount > 0) && (ret == 0)) {
+			ret = davinci_spi_process_events(davinci_spi);
+			cpu_relax();
 		}
-		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 != NULL) || (t->rx_buf != NULL))
-		edma_start(davinci_spi_dma->dma_tx_channel);
-
-	if (t->rx_buf != NULL)
-		edma_start(davinci_spi_dma->dma_rx_channel);
-
-	if ((t->rx_buf != NULL) || (t->tx_buf != NULL))
-		davinci_spi_set_dma_req(spi, 1);
-
-	if (t->tx_buf != NULL)
-		wait_for_completion_interruptible(
-				&davinci_spi_dma->dma_tx_completion);
-
-	if (t->rx_buf != NULL)
-		wait_for_completion_interruptible(
-				&davinci_spi_dma->dma_rx_completion);
-
-	if (t->tx_buf != NULL)
-		dma_unmap_single(NULL, t->tx_dma, count, DMA_TO_DEVICE);
-	else
-		dma_unmap_single(NULL, t->tx_dma, count + 1, DMA_TO_DEVICE);
-
-	if (t->rx_buf != NULL)
-		dma_unmap_single(NULL, t->rx_dma, count, DMA_FROM_DEVICE);
-
-	/*
-	 * Check for bit error, desync error,parity error,timeout error and
-	 * receive overflow errors
-	 */
-	int_status = ioread32(davinci_spi->base + SPIFLG);
+	clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKALL);
+	if (spi_cfg->io_type == SPI_IO_TYPE_DMA) {
+		dma_unmap_single(NULL, t->tx_dma, tx_buf_count,
+					DMA_TO_DEVICE);
+		dma_unmap_single(NULL, t->rx_dma, rx_buf_count,
+					DMA_FROM_DEVICE);
+	}
 
-	ret = davinci_spi_check_error(davinci_spi, int_status);
-	if (ret != 0)
-		return ret;
+	clear_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_SPIENA_MASK);
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_POWERDOWN_MASK);
 
-	/* SPI Framework maintains the count only in bytes so convert back */
-	davinci_spi->count *= conv;
+	if (davinci_spi->errors) {
+		ret = davinci_spi_check_error(davinci_spi, davinci_spi->errors);
+		if (ret != 0)
+			return ret;
+	}
+	if ((davinci_spi->rcount != 0) || (davinci_spi->wcount != 0)) {
+		sdev = davinci_spi->bitbang.master->dev.parent;
+		dev_info(sdev, "SPI data transfer error\n");
+		return -EIO;
+	}
 
 	return t->len;
 }
@@ -844,28 +675,16 @@  static int davinci_spi_bufs_dma(struct spi_device *spi, struct spi_transfer *t)
 static irqreturn_t davinci_spi_irq(s32 irq, void *context_data)
 {
 	struct davinci_spi *davinci_spi = context_data;
-	u32 int_status, rx_data = 0;
-	irqreturn_t ret = IRQ_NONE;
+	int status;
 
-	int_status = ioread32(davinci_spi->base + SPIFLG);
+	status = davinci_spi_process_events(davinci_spi);
+	if (unlikely(status != 0))
+		clear_io_bits(davinci_spi->base + SPIINT, SPIINT_MASKINT);
 
-	while ((int_status & SPIFLG_RX_INTR_MASK)) {
-		if (likely(int_status & SPIFLG_RX_INTR_MASK)) {
-			ret = IRQ_HANDLED;
+	if ((davinci_spi->rcount == 0) || (status != 0))
+		complete(&(davinci_spi->done));
 
-			rx_data = ioread32(davinci_spi->base + SPIBUF);
-			davinci_spi->get_rx(rx_data, davinci_spi);
-
-			/* Disable Receive Interrupt */
-			iowrite32(~(SPIINT_RX_INTR | SPIINT_TX_INTR),
-					davinci_spi->base + SPIINT);
-		} else
-			(void)davinci_spi_check_error(davinci_spi, int_status);
-
-		int_status = ioread32(davinci_spi->base + SPIFLG);
-	}
-
-	return ret;
+	return IRQ_HANDLED;
 }
 
 resource_size_t davinci_spi_get_dma_by_flag(struct platform_device *dev,
@@ -906,6 +725,7 @@  static int davinci_spi_probe(struct platform_device *pdev)
 	resource_size_t	dma_tx_chan = DAVINCI_SPI_NO_RESOURCE;
 	resource_size_t	dma_eventq = DAVINCI_SPI_NO_RESOURCE;
 	int i = 0, ret = 0;
+	u32 spipc0;
 
 	pdata = pdev->dev.platform_data;
 	if (pdata == NULL) {
@@ -992,52 +812,23 @@  static int davinci_spi_probe(struct platform_device *pdev)
 
 	davinci_spi->bitbang.chipselect = davinci_spi_chipselect;
 	davinci_spi->bitbang.setup_transfer = davinci_spi_setup_transfer;
+	davinci_spi->bitbang.txrx_bufs = davinci_spi_txrx_bufs;
 
 	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) {
-		dma_rx_chan = davinci_spi_get_dma_by_flag(pdev,
-						IORESOURCE_DMA_RX_CHAN);
-		dma_tx_chan = davinci_spi_get_dma_by_flag(pdev,
-						IORESOURCE_DMA_TX_CHAN);
-		dma_eventq  = davinci_spi_get_dma_by_flag(pdev,
-						IORESOURCE_DMA_EVENT_Q);
-	}
-
-	if (!use_dma ||
-	    dma_rx_chan == DAVINCI_SPI_NO_RESOURCE ||
-	    dma_tx_chan == DAVINCI_SPI_NO_RESOURCE ||
-	    dma_eventq	== DAVINCI_SPI_NO_RESOURCE) {
-		davinci_spi->bitbang.txrx_bufs = davinci_spi_bufs_pio;
-		use_dma = 0;
-	} else {
-		davinci_spi->bitbang.txrx_bufs = davinci_spi_bufs_dma;
-		davinci_spi->dma_channels = kzalloc(master->num_chipselect
-				* sizeof(struct davinci_spi_dma), GFP_KERNEL);
-		if (davinci_spi->dma_channels == NULL) {
-			ret = -ENOMEM;
-			goto free_clk;
-		}
-
-		for (i = 0; i < master->num_chipselect; i++) {
-			davinci_spi->dma_channels[i].dma_rx_channel = -1;
-			davinci_spi->dma_channels[i].dma_rx_sync_dev =
-				dma_rx_chan;
-			davinci_spi->dma_channels[i].dma_tx_channel = -1;
-			davinci_spi->dma_channels[i].dma_tx_sync_dev =
-				dma_tx_chan;
-			davinci_spi->dma_channels[i].eventq = dma_eventq;
-		}
-		dev_info(&pdev->dev, "DaVinci SPI driver in EDMA mode\n"
-				"Using RX channel = %d , TX channel = %d and "
-				"event queue = %d", dma_rx_chan, dma_tx_chan,
-				dma_eventq);
-	}
+	dma_rx_chan = davinci_spi_get_dma_by_flag(pdev, IORESOURCE_DMA_RX_CHAN);
+	dma_tx_chan = davinci_spi_get_dma_by_flag(pdev, IORESOURCE_DMA_TX_CHAN);
+	dma_eventq  = davinci_spi_get_dma_by_flag(pdev, IORESOURCE_DMA_EVENT_Q);
+	davinci_spi->dma_channels.dma_rx_channel = -1;
+	davinci_spi->dma_channels.dma_rx_sync_dev = dma_rx_chan;
+	davinci_spi->dma_channels.dma_tx_channel = -1;
+	davinci_spi->dma_channels.dma_tx_sync_dev = dma_tx_chan;
+	davinci_spi->dma_channels.dummy_param_slot = -1;
+	davinci_spi->dma_channels.eventq = dma_eventq;
 
 	davinci_spi->get_rx = davinci_spi_rx_buf_u8;
 	davinci_spi->get_tx = davinci_spi_tx_buf_u8;
@@ -1049,21 +840,22 @@  static int davinci_spi_probe(struct platform_device *pdev)
 	udelay(100);
 	iowrite32(1, davinci_spi->base + SPIGCR0);
 
-	/* Clock internal */
-	if (davinci_spi->pdata->clk_internal)
-		set_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_CLKMOD_MASK);
-	else
-		clear_io_bits(davinci_spi->base + SPIGCR1,
-				SPIGCR1_CLKMOD_MASK);
+	/* 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, davinci_spi->base + SPIPC0);
 
-	/* master mode default */
-	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_MASTER_MASK);
+	/* initialize chip selects */
+	if (pdata->chip_sel != NULL) {
+		for (i = 0; i < pdata->num_chipselect; i++) {
+			if (pdata->chip_sel[i] != SPI_INTERN_CS)
+				gpio_direction_output(pdata->chip_sel[i], 1);
+		}
+	}
+	iowrite32(SPIDEF_CSDEF_MASK, davinci_spi->base + SPIDEF);
 
-	if (davinci_spi->pdata->intr_level)
-		iowrite32(SPI_INTLVL_1, davinci_spi->base + SPILVL);
-	else
-		iowrite32(SPI_INTLVL_0, davinci_spi->base + SPILVL);
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_CLKMOD_MASK);
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_MASTER_MASK);
+	set_io_bits(davinci_spi->base + SPIGCR1, SPIGCR1_POWERDOWN_MASK);
 
 	ret = spi_bitbang_start(&davinci_spi->bitbang);
 	if (ret != 0)
@@ -1071,10 +863,6 @@  static int davinci_spi_probe(struct platform_device *pdev)
 
 	dev_info(&pdev->dev, "Controller at 0x%p \n", davinci_spi->base);
 
-	if (!pdata->poll_mode)
-		dev_info(&pdev->dev, "Operating in interrupt mode"
-			" using IRQ %d\n", davinci_spi->irq);
-
 	return ret;
 
 free_clk:
diff --git a/drivers/spi/davinci_spi.h b/drivers/spi/davinci_spi.h
index 52acf47..462b2a2 100644
--- a/drivers/spi/davinci_spi.h
+++ b/drivers/spi/davinci_spi.h
@@ -19,8 +19,6 @@ 
 #ifndef __DAVINCI_SPI_H
 #define __DAVINCI_SPI_H
 
-#define SPI_MAX_CHIPSELECT	2
-
 #define CS_DEFAULT	0xFF
 #define SCS0_SELECT	0x01
 #define SCS1_SELECT	0x02
@@ -41,9 +39,11 @@ 
 #define SPIFMT_WDELAY_MASK	0x3f000000u
 #define SPIFMT_WDELAY_SHIFT	24
 #define SPIFMT_CHARLEN_MASK	0x0000001Fu
+#define SPIFMT_PRESCALE_SHIFT	8
 
 /* SPIGCR1 */
-#define SPIGCR1_SPIENA_MASK	0x01000000u
+#define SPIGCR1_SPIENA_MASK	BIT(24)
+#define SPIGCR1_POWERDOWN_MASK	BIT(8)
 
 /* SPIPC0 */
 #define SPIPC0_DIFUN_MASK	BIT(11)		/* MISO */
@@ -53,14 +53,16 @@ 
 #define SPIPC0_EN1FUN_MASK	BIT(1)
 #define SPIPC0_EN0FUN_MASK	BIT(0)
 
-#define SPIINT_MASKALL		0x0101035F
+#define SPIINT_MASKALL		0x0101035Fu
+#define SPIINT_MASKINT		0x0000035Fu
 #define SPI_INTLVL_1		0x000001FFu
 #define SPI_INTLVL_0		0x00000000u
 
 /* SPIDAT1 */
 #define SPIDAT1_CSHOLD_MASK	BIT(28)
 #define SPIDAT1_CSHOLD_SHIFT	28
-#define SPIDAT1_CSNR_MASK	(BIT(17 | BIT(16))
+#define SPIDAT1_WDEL_MASK	BIT(26)
+#define SPIDAT1_CSNR_MASK	0x00FF0000u
 #define SPIDAT1_CSNR_SHIFT	16
 #define SPIDAT1_DFSEL_MASK	(BIT(24 | BIT(25))
 #define SPIGCR1_CLKMOD_MASK	BIT(1)
@@ -71,6 +73,19 @@ 
 #define SPIBUF_TXFULL_MASK	BIT(29)
 #define SPIBUF_RXEMPTY_MASK	BIT(31)
 
+/* SPIDELAY */
+#define SPIDELAY_C2TDELAY_MASK	0xFF000000u
+#define SPIDELAY_C2TDELAY_SHIFT	24
+#define SPIDELAY_T2CDELAY_MASK	0x00FF0000u
+#define SPIDELAY_T2CDELAY_SHIFT	16
+#define SPIDELAY_T2EDELAY_MASK	0x0000FF00u
+#define SPIDELAY_T2EDELAY_SHIFT	8
+#define SPIDELAY_C2EDELAY_MASK	0x000000FFu
+#define SPIDELAY_C2EDELAY_SHIFT	0
+
+/* SPIDEF */
+#define SPIDEF_CSDEF_MASK	0x000000FFu
+
 /* Error Masks */
 #define SPIFLG_DLEN_ERR_MASK		BIT(0)
 #define SPIFLG_TIMEOUT_MASK		BIT(1)
@@ -81,11 +96,12 @@ 
 #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_OVRRUN_MASK)
+#define SPIFLG_MASK			(SPIFLG_ERROR_MASK \
+				| SPIFLG_RX_INTR_MASK | SPIFLG_TX_INTR_MASK \
 				| SPIFLG_BUF_INIT_ACTIVE_MASK)
 
 #define SPIINT_DLEN_ERR_INTR	BIT(0)
@@ -130,13 +146,6 @@ 
 #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;
-};
-
 #define SPI_BUFSIZ	(SMP_CACHE_BYTES + 1)
 
 /* We have 2 DMA channels per CS, one for RX and one for TX */
@@ -145,10 +154,8 @@  struct davinci_spi_dma {
 	int			dma_rx_channel;
 	int			dma_tx_sync_dev;
 	int			dma_rx_sync_dev;
+	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. */
@@ -166,14 +173,14 @@  struct davinci_spi {
 	const void		*tx;
 	void			*rx;
 	u8			*tmp_buf;
-	int			count;
-	struct davinci_spi_dma	*dma_channels;
-	struct			davinci_spi_platform_data *pdata;
+	int			rcount;
+	int			wcount;
+	u32			errors;
+	struct davinci_spi_dma	dma_channels;
+	struct davinci_spi_platform_data *pdata;
 
 	void			(*get_rx)(u32 rx_data, struct davinci_spi *);
 	u32			(*get_tx)(struct davinci_spi *);
-
-	struct davinci_spi_slave slave[SPI_MAX_CHIPSELECT];
 };
 
 #endif /* __DAVINCI_SPI_H */