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

* 'next-spi' of git://git.secretlab.ca/git/linux-2.6: (77 commits)
  spi/omap: Fix DMA API usage in OMAP MCSPI driver
  spi/imx: correct the test on platform_get_irq() return value
  spi/topcliff: Typo fix threhold to threshold
  spi/dw_spi Typo change diable to disable.
  spi/fsl_espi: change the read behaviour of the SPIRF
  spi/mpc52xx-psc-spi: move probe/remove to proper sections
  spi/dw_spi: add DMA support
  spi/dw_spi: change to EXPORT_SYMBOL_GPL for exported APIs
  spi/dw_spi: Fix too short timeout in spi polling loop
  spi/pl022: convert running variable
  spi/pl022: convert busy flag to a bool
  spi/pl022: pass the returned sglen to the DMA engine
  spi/pl022: map the buffers on the DMA engine
  spi/topcliff_pch: Fix data transfer issue
  spi/imx: remove autodetection
  spi/pxa2xx: pass of_node to spi device and set a parent device
  spi/pxa2xx: Modify RX-Tresh instead of busy-loop for the remaining RX bytes.
  spi/pxa2xx: Add chipselect support for Sodaville
  spi/pxa2xx: Consider CE4100's FIFO depth
  spi/pxa2xx: Add CE4100 support
  ...

18 files changed, 1327 insertions, 1265 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 78f9fd02c1b..1906840c111 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"
@@ -267,12 +270,15 @@ config SPI_PPC4xx
 
 config SPI_PXA2XX
 	tristate "PXA2xx SSP SPI master"
-	depends on ARCH_PXA && EXPERIMENTAL
-	select PXA_SSP
+	depends on (ARCH_PXA || (X86_32 && PCI)) && EXPERIMENTAL
+	select PXA_SSP if ARCH_PXA
 	help
-	  This enables using a PXA2xx SSP port as a SPI master controller.
-	  The driver can be configured to use any SSP port and additional
-	  documentation can be found a Documentation/spi/pxa2xx.
+	  This enables using a PXA2xx or Sodaville SSP port as a SPI master
+	  controller. The driver can be configured to use any SSP port and
+	  additional documentation can be found a Documentation/spi/pxa2xx.
+
+config SPI_PXA2XX_PCI
+	def_bool SPI_PXA2XX && X86_32 && PCI
 
 config SPI_S3C24XX
 	tristate "Samsung S3C24XX series SPI"
@@ -353,7 +359,6 @@ config SPI_XILINX
 	tristate "Xilinx SPI controller common module"
 	depends on HAS_IOMEM && EXPERIMENTAL
 	select SPI_BITBANG
-	select SPI_XILINX_OF if (XILINX_VIRTEX || MICROBLAZE)
 	help
 	  This exposes the SPI controller IP from the Xilinx EDK.
 
@@ -362,19 +367,6 @@ config SPI_XILINX
 
 	  Or for the DS570, see "XPS Serial Peripheral Interface (SPI) (v2.00b)"
 
-config SPI_XILINX_OF
-	tristate "Xilinx SPI controller OF device"
-	depends on SPI_XILINX && (XILINX_VIRTEX || MICROBLAZE)
-	help
-	  This is the OF driver for the SPI controller IP from the Xilinx EDK.
-
-config SPI_XILINX_PLTFM
-	tristate "Xilinx SPI controller platform device"
-	depends on SPI_XILINX
-	help
-	  This is the platform driver for the SPI controller IP
-	  from the Xilinx EDK.
-
 config SPI_NUC900
 	tristate "Nuvoton NUC900 series SPI"
 	depends on ARCH_W90X900 && EXPERIMENTAL
@@ -396,6 +388,10 @@ config SPI_DW_PCI
 	tristate "PCI interface driver for DW SPI core"
 	depends on SPI_DESIGNWARE && PCI
 
+config SPI_DW_MID_DMA
+	bool "DMA support for DW SPI controller on Intel Moorestown platform"
+	depends on SPI_DW_PCI && INTEL_MID_DMAC
+
 config SPI_DW_MMIO
 	tristate "Memory-mapped io interface driver for DW SPI core"
 	depends on SPI_DESIGNWARE && HAVE_CLK
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 8bc1a5abac1..3a42463c92a 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -17,13 +17,15 @@ obj-$(CONFIG_SPI_BUTTERFLY)		+= spi_butterfly.o
 obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= coldfire_qspi.o
 obj-$(CONFIG_SPI_DAVINCI)		+= davinci_spi.o
 obj-$(CONFIG_SPI_DESIGNWARE)		+= dw_spi.o
-obj-$(CONFIG_SPI_DW_PCI)		+= dw_spi_pci.o
+obj-$(CONFIG_SPI_DW_PCI)		+= dw_spi_midpci.o
+dw_spi_midpci-objs			:= dw_spi_pci.o dw_spi_mid.o
 obj-$(CONFIG_SPI_DW_MMIO)		+= dw_spi_mmio.o
 obj-$(CONFIG_SPI_EP93XX)		+= ep93xx_spi.o
 obj-$(CONFIG_SPI_GPIO)			+= spi_gpio.o
 obj-$(CONFIG_SPI_IMX)			+= spi_imx.o
 obj-$(CONFIG_SPI_LM70_LLP)		+= spi_lm70llp.o
 obj-$(CONFIG_SPI_PXA2XX)		+= pxa2xx_spi.o
+obj-$(CONFIG_SPI_PXA2XX_PCI)		+= pxa2xx_spi_pci.o
 obj-$(CONFIG_SPI_OMAP_UWIRE)		+= omap_uwire.o
 obj-$(CONFIG_SPI_OMAP24XX)		+= omap2_mcspi.o
 obj-$(CONFIG_SPI_OMAP_100K)		+= omap_spi_100k.o
@@ -43,8 +45,6 @@ obj-$(CONFIG_SPI_TEGRA)			+= spi_tegra.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi_topcliff_pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi_txx9.o
 obj-$(CONFIG_SPI_XILINX)		+= xilinx_spi.o
-obj-$(CONFIG_SPI_XILINX_OF)		+= xilinx_spi_of.o
-obj-$(CONFIG_SPI_XILINX_PLTFM)		+= xilinx_spi_pltfm.o
 obj-$(CONFIG_SPI_SH_SCI)		+= spi_sh_sci.o
 obj-$(CONFIG_SPI_SH_MSIOF)		+= spi_sh_msiof.o
 obj-$(CONFIG_SPI_STMP3XXX)		+= spi_stmp.o
diff --git a/drivers/spi/amba-pl022.c b/drivers/spi/amba-pl022.c
index fb3d1b31772..a2a5921c730 100644
--- a/drivers/spi/amba-pl022.c
+++ b/drivers/spi/amba-pl022.c
@@ -253,11 +253,6 @@
 #define STATE_ERROR			((void *) -1)
 
 /*
- * Queue State
- */
-#define QUEUE_RUNNING			(0)
-#define QUEUE_STOPPED			(1)
-/*
  * SSP State - Whether Enabled or Disabled
  */
 #define SSP_DISABLED			(0)
@@ -344,7 +339,7 @@ struct vendor_data {
  * @lock: spinlock to syncronise access to driver data
  * @workqueue: a workqueue on which any spi_message request is queued
  * @busy: workqueue is busy
- * @run: workqueue is running
+ * @running: workqueue is running
  * @pump_transfers: Tasklet used in Interrupt Transfer mode
  * @cur_msg: Pointer to current spi_message being processed
  * @cur_transfer: Pointer to current spi_transfer
@@ -369,8 +364,8 @@ struct pl022 {
 	struct work_struct		pump_messages;
 	spinlock_t			queue_lock;
 	struct list_head		queue;
-	int				busy;
-	int				run;
+	bool				busy;
+	bool				running;
 	/* Message transfer pump */
 	struct tasklet_struct		pump_transfers;
 	struct spi_message		*cur_msg;
@@ -782,9 +777,9 @@ static void *next_transfer(struct pl022 *pl022)
 static void unmap_free_dma_scatter(struct pl022 *pl022)
 {
 	/* Unmap and free the SG tables */
-	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_tx.sgl,
+	dma_unmap_sg(pl022->dma_tx_channel->device->dev, pl022->sgt_tx.sgl,
 		     pl022->sgt_tx.nents, DMA_TO_DEVICE);
-	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_rx.sgl,
+	dma_unmap_sg(pl022->dma_rx_channel->device->dev, pl022->sgt_rx.sgl,
 		     pl022->sgt_rx.nents, DMA_FROM_DEVICE);
 	sg_free_table(&pl022->sgt_rx);
 	sg_free_table(&pl022->sgt_tx);
@@ -917,7 +912,7 @@ static int configure_dma(struct pl022 *pl022)
 	};
 	unsigned int pages;
 	int ret;
-	int sglen;
+	int rx_sglen, tx_sglen;
 	struct dma_chan *rxchan = pl022->dma_rx_channel;
 	struct dma_chan *txchan = pl022->dma_tx_channel;
 	struct dma_async_tx_descriptor *rxdesc;
@@ -956,7 +951,7 @@ static int configure_dma(struct pl022 *pl022)
 		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 		break;
 	case WRITING_U32:
-		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;;
+		tx_conf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
 		break;
 	}
 
@@ -991,20 +986,20 @@ static int configure_dma(struct pl022 *pl022)
 			  pl022->cur_transfer->len, &pl022->sgt_tx);
 
 	/* Map DMA buffers */
-	sglen = dma_map_sg(&pl022->adev->dev, pl022->sgt_rx.sgl,
+	rx_sglen = dma_map_sg(rxchan->device->dev, pl022->sgt_rx.sgl,
 			   pl022->sgt_rx.nents, DMA_FROM_DEVICE);
-	if (!sglen)
+	if (!rx_sglen)
 		goto err_rx_sgmap;
 
-	sglen = dma_map_sg(&pl022->adev->dev, pl022->sgt_tx.sgl,
+	tx_sglen = dma_map_sg(txchan->device->dev, pl022->sgt_tx.sgl,
 			   pl022->sgt_tx.nents, DMA_TO_DEVICE);
-	if (!sglen)
+	if (!tx_sglen)
 		goto err_tx_sgmap;
 
 	/* Send both scatterlists */
 	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
 				      pl022->sgt_rx.sgl,
-				      pl022->sgt_rx.nents,
+				      rx_sglen,
 				      DMA_FROM_DEVICE,
 				      DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!rxdesc)
@@ -1012,7 +1007,7 @@ static int configure_dma(struct pl022 *pl022)
 
 	txdesc = txchan->device->device_prep_slave_sg(txchan,
 				      pl022->sgt_tx.sgl,
-				      pl022->sgt_tx.nents,
+				      tx_sglen,
 				      DMA_TO_DEVICE,
 				      DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!txdesc)
@@ -1040,10 +1035,10 @@ err_txdesc:
 	txchan->device->device_control(txchan, DMA_TERMINATE_ALL, 0);
 err_rxdesc:
 	rxchan->device->device_control(rxchan, DMA_TERMINATE_ALL, 0);
-	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_tx.sgl,
+	dma_unmap_sg(txchan->device->dev, pl022->sgt_tx.sgl,
 		     pl022->sgt_tx.nents, DMA_TO_DEVICE);
 err_tx_sgmap:
-	dma_unmap_sg(&pl022->adev->dev, pl022->sgt_rx.sgl,
+	dma_unmap_sg(rxchan->device->dev, pl022->sgt_rx.sgl,
 		     pl022->sgt_tx.nents, DMA_FROM_DEVICE);
 err_rx_sgmap:
 	sg_free_table(&pl022->sgt_tx);
@@ -1460,8 +1455,8 @@ static void pump_messages(struct work_struct *work)
 
 	/* Lock queue and check for queue work */
 	spin_lock_irqsave(&pl022->queue_lock, flags);
-	if (list_empty(&pl022->queue) || pl022->run == QUEUE_STOPPED) {
-		pl022->busy = 0;
+	if (list_empty(&pl022->queue) || !pl022->running) {
+		pl022->busy = false;
 		spin_unlock_irqrestore(&pl022->queue_lock, flags);
 		return;
 	}
@@ -1475,7 +1470,7 @@ static void pump_messages(struct work_struct *work)
 	    list_entry(pl022->queue.next, struct spi_message, queue);
 
 	list_del_init(&pl022->cur_msg->queue);
-	pl022->busy = 1;
+	pl022->busy = true;
 	spin_unlock_irqrestore(&pl022->queue_lock, flags);
 
 	/* Initial message state */
@@ -1507,8 +1502,8 @@ static int __init init_queue(struct pl022 *pl022)
 	INIT_LIST_HEAD(&pl022->queue);
 	spin_lock_init(&pl022->queue_lock);
 
-	pl022->run = QUEUE_STOPPED;
-	pl022->busy = 0;
+	pl022->running = false;
+	pl022->busy = false;
 
 	tasklet_init(&pl022->pump_transfers,
 			pump_transfers,	(unsigned long)pl022);
@@ -1529,12 +1524,12 @@ static int start_queue(struct pl022 *pl022)
 
 	spin_lock_irqsave(&pl022->queue_lock, flags);
 
-	if (pl022->run == QUEUE_RUNNING || pl022->busy) {
+	if (pl022->running || pl022->busy) {
 		spin_unlock_irqrestore(&pl022->queue_lock, flags);
 		return -EBUSY;
 	}
 
-	pl022->run = QUEUE_RUNNING;
+	pl022->running = true;
 	pl022->cur_msg = NULL;
 	pl022->cur_transfer = NULL;
 	pl022->cur_chip = NULL;
@@ -1566,7 +1561,8 @@ static int stop_queue(struct pl022 *pl022)
 
 	if (!list_empty(&pl022->queue) || pl022->busy)
 		status = -EBUSY;
-	else pl022->run = QUEUE_STOPPED;
+	else
+		pl022->running = false;
 
 	spin_unlock_irqrestore(&pl022->queue_lock, flags);
 
@@ -1684,7 +1680,7 @@ static int pl022_transfer(struct spi_device *spi, struct spi_message *msg)
 
 	spin_lock_irqsave(&pl022->queue_lock, flags);
 
-	if (pl022->run == QUEUE_STOPPED) {
+	if (!pl022->running) {
 		spin_unlock_irqrestore(&pl022->queue_lock, flags);
 		return -ESHUTDOWN;
 	}
@@ -1693,7 +1689,7 @@ static int pl022_transfer(struct spi_device *spi, struct spi_message *msg)
 	msg->state = STATE_START;
 
 	list_add_tail(&msg->queue, &pl022->queue);
-	if (pl022->run == QUEUE_RUNNING && !pl022->busy)
+	if (pl022->running && !pl022->busy)
 		queue_work(pl022->workqueue, &pl022->pump_messages);
 
 	spin_unlock_irqrestore(&pl022->queue_lock, flags);
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))