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 78f9fd02c1b2..1906840c1113 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 8bc1a5abac1f..3a42463c92a4 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 fb3d1b31772d..a2a5921c730a 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 b85090caf7cf..6beab99bf95b 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),
 };
 
diff --git a/drivers/spi/dw_spi.c b/drivers/spi/dw_spi.c
index 0838c79861e4..22af77f98816 100644
--- a/drivers/spi/dw_spi.c
+++ b/drivers/spi/dw_spi.c
@@ -164,20 +164,23 @@ static inline void mrst_spi_debugfs_remove(struct dw_spi *dws)
 
 static void wait_till_not_busy(struct dw_spi *dws)
 {
-	unsigned long end = jiffies + 1 + usecs_to_jiffies(1000);
+	unsigned long end = jiffies + 1 + usecs_to_jiffies(5000);
 
 	while (time_before(jiffies, end)) {
 		if (!(dw_readw(dws, sr) & SR_BUSY))
 			return;
+		cpu_relax();
 	}
 	dev_err(&dws->master->dev,
-		"DW SPI: Status keeps busy for 1000us after a read/write!\n");
+		"DW SPI: Status keeps busy for 5000us after a read/write!\n");
 }
 
 static void flush(struct dw_spi *dws)
 {
-	while (dw_readw(dws, sr) & SR_RF_NOT_EMPT)
+	while (dw_readw(dws, sr) & SR_RF_NOT_EMPT) {
 		dw_readw(dws, dr);
+		cpu_relax();
+	}
 
 	wait_till_not_busy(dws);
 }
@@ -285,8 +288,10 @@ static void *next_transfer(struct dw_spi *dws)
  */
 static int map_dma_buffers(struct dw_spi *dws)
 {
-	if (!dws->cur_msg->is_dma_mapped || !dws->dma_inited
-		|| !dws->cur_chip->enable_dma)
+	if (!dws->cur_msg->is_dma_mapped
+		|| !dws->dma_inited
+		|| !dws->cur_chip->enable_dma
+		|| !dws->dma_ops)
 		return 0;
 
 	if (dws->cur_transfer->tx_dma)
@@ -338,7 +343,7 @@ static void int_error_stop(struct dw_spi *dws, const char *msg)
 	tasklet_schedule(&dws->pump_transfers);
 }
 
-static void transfer_complete(struct dw_spi *dws)
+void dw_spi_xfer_done(struct dw_spi *dws)
 {
 	/* Update total byte transfered return count actual bytes read */
 	dws->cur_msg->actual_length += dws->len;
@@ -353,6 +358,7 @@ static void transfer_complete(struct dw_spi *dws)
 	} else
 		tasklet_schedule(&dws->pump_transfers);
 }
+EXPORT_SYMBOL_GPL(dw_spi_xfer_done);
 
 static irqreturn_t interrupt_transfer(struct dw_spi *dws)
 {
@@ -384,7 +390,7 @@ static irqreturn_t interrupt_transfer(struct dw_spi *dws)
 		if (dws->tx_end > dws->tx)
 			spi_umask_intr(dws, SPI_INT_TXEI);
 		else
-			transfer_complete(dws);
+			dw_spi_xfer_done(dws);
 	}
 
 	return IRQ_HANDLED;
@@ -419,11 +425,7 @@ static void poll_transfer(struct dw_spi *dws)
 	 */
 	dws->read(dws);
 
-	transfer_complete(dws);
-}
-
-static void dma_transfer(struct dw_spi *dws, int cs_change)
-{
+	dw_spi_xfer_done(dws);
 }
 
 static void pump_transfers(unsigned long data)
@@ -592,7 +594,7 @@ static void pump_transfers(unsigned long data)
 		spi_set_clk(dws, clk_div ? clk_div : chip->clk_div);
 		spi_chip_sel(dws, spi->chip_select);
 
-		/* Set the interrupt mask, for poll mode just diable all int */
+		/* Set the interrupt mask, for poll mode just disable all int */
 		spi_mask_intr(dws, 0xff);
 		if (imask)
 			spi_umask_intr(dws, imask);
@@ -605,7 +607,7 @@ static void pump_transfers(unsigned long data)
 	}
 
 	if (dws->dma_mapped)
-		dma_transfer(dws, cs_change);
+		dws->dma_ops->dma_transfer(dws, cs_change);
 
 	if (chip->poll_mode)
 		poll_transfer(dws);
@@ -901,11 +903,17 @@ int __devinit dw_spi_add_host(struct dw_spi *dws)
 	master->setup = dw_spi_setup;
 	master->transfer = dw_spi_transfer;
 
-	dws->dma_inited = 0;
-
 	/* Basic HW init */
 	spi_hw_init(dws);
 
+	if (dws->dma_ops && dws->dma_ops->dma_init) {
+		ret = dws->dma_ops->dma_init(dws);
+		if (ret) {
+			dev_warn(&master->dev, "DMA init failed\n");
+			dws->dma_inited = 0;
+		}
+	}
+
 	/* Initial and start queue */
 	ret = init_queue(dws);
 	if (ret) {
@@ -930,6 +938,8 @@ int __devinit dw_spi_add_host(struct dw_spi *dws)
 
 err_queue_alloc:
 	destroy_queue(dws);
+	if (dws->dma_ops && dws->dma_ops->dma_exit)
+		dws->dma_ops->dma_exit(dws);
 err_diable_hw:
 	spi_enable_chip(dws, 0);
 	free_irq(dws->irq, dws);
@@ -938,7 +948,7 @@ err_free_master:
 exit:
 	return ret;
 }
-EXPORT_SYMBOL(dw_spi_add_host);
+EXPORT_SYMBOL_GPL(dw_spi_add_host);
 
 void __devexit dw_spi_remove_host(struct dw_spi *dws)
 {
@@ -954,6 +964,8 @@ void __devexit dw_spi_remove_host(struct dw_spi *dws)
 		dev_err(&dws->master->dev, "dw_spi_remove: workqueue will not "
 			"complete, message memory not freed\n");
 
+	if (dws->dma_ops && dws->dma_ops->dma_exit)
+		dws->dma_ops->dma_exit(dws);
 	spi_enable_chip(dws, 0);
 	/* Disable clk */
 	spi_set_clk(dws, 0);
@@ -962,7 +974,7 @@ void __devexit dw_spi_remove_host(struct dw_spi *dws)
 	/* Disconnect from the SPI framework */
 	spi_unregister_master(dws->master);
 }
-EXPORT_SYMBOL(dw_spi_remove_host);
+EXPORT_SYMBOL_GPL(dw_spi_remove_host);
 
 int dw_spi_suspend_host(struct dw_spi *dws)
 {
@@ -975,7 +987,7 @@ int dw_spi_suspend_host(struct dw_spi *dws)
 	spi_set_clk(dws, 0);
 	return ret;
 }
-EXPORT_SYMBOL(dw_spi_suspend_host);
+EXPORT_SYMBOL_GPL(dw_spi_suspend_host);
 
 int dw_spi_resume_host(struct dw_spi *dws)
 {
@@ -987,7 +999,7 @@ int dw_spi_resume_host(struct dw_spi *dws)
 		dev_err(&dws->master->dev, "fail to start queue (%d)\n", ret);
 	return ret;
 }
-EXPORT_SYMBOL(dw_spi_resume_host);
+EXPORT_SYMBOL_GPL(dw_spi_resume_host);
 
 MODULE_AUTHOR("Feng Tang <feng.tang@intel.com>");
 MODULE_DESCRIPTION("Driver for DesignWare SPI controller core");
diff --git a/drivers/spi/dw_spi_mid.c b/drivers/spi/dw_spi_mid.c
new file mode 100644
index 000000000000..c91c966e0717
--- /dev/null
+++ b/drivers/spi/dw_spi_mid.c
@@ -0,0 +1,223 @@
+/*
+ * dw_spi_mid.c - special handling for DW core on Intel MID platform
+ *
+ * Copyright (c) 2009, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation,
+ * Inc., 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/dw_spi.h>
+
+#ifdef CONFIG_SPI_DW_MID_DMA
+#include <linux/intel_mid_dma.h>
+#include <linux/pci.h>
+
+struct mid_dma {
+	struct intel_mid_dma_slave	dmas_tx;
+	struct intel_mid_dma_slave	dmas_rx;
+};
+
+static bool mid_spi_dma_chan_filter(struct dma_chan *chan, void *param)
+{
+	struct dw_spi *dws = param;
+
+	return dws->dmac && (&dws->dmac->dev == chan->device->dev);
+}
+
+static int mid_spi_dma_init(struct dw_spi *dws)
+{
+	struct mid_dma *dw_dma = dws->dma_priv;
+	struct intel_mid_dma_slave *rxs, *txs;
+	dma_cap_mask_t mask;
+
+	/*
+	 * Get pci device for DMA controller, currently it could only
+	 * be the DMA controller of either Moorestown or Medfield
+	 */
+	dws->dmac = pci_get_device(PCI_VENDOR_ID_INTEL, 0x0813, NULL);
+	if (!dws->dmac)
+		dws->dmac = pci_get_device(PCI_VENDOR_ID_INTEL, 0x0827, NULL);
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	/* 1. Init rx channel */
+	dws->rxchan = dma_request_channel(mask, mid_spi_dma_chan_filter, dws);
+	if (!dws->rxchan)
+		goto err_exit;
+	rxs = &dw_dma->dmas_rx;
+	rxs->hs_mode = LNW_DMA_HW_HS;
+	rxs->cfg_mode = LNW_DMA_PER_TO_MEM;
+	dws->rxchan->private = rxs;
+
+	/* 2. Init tx channel */
+	dws->txchan = dma_request_channel(mask, mid_spi_dma_chan_filter, dws);
+	if (!dws->txchan)
+		goto free_rxchan;
+	txs = &dw_dma->dmas_tx;
+	txs->hs_mode = LNW_DMA_HW_HS;
+	txs->cfg_mode = LNW_DMA_MEM_TO_PER;
+	dws->txchan->private = txs;
+
+	dws->dma_inited = 1;
+	return 0;
+
+free_rxchan:
+	dma_release_channel(dws->rxchan);
+err_exit:
+	return -1;
+
+}
+
+static void mid_spi_dma_exit(struct dw_spi *dws)
+{
+	dma_release_channel(dws->txchan);
+	dma_release_channel(dws->rxchan);
+}
+
+/*
+ * dws->dma_chan_done is cleared before the dma transfer starts,
+ * callback for rx/tx channel will each increment it by 1.
+ * Reaching 2 means the whole spi transaction is done.
+ */
+static void dw_spi_dma_done(void *arg)
+{
+	struct dw_spi *dws = arg;
+
+	if (++dws->dma_chan_done != 2)
+		return;
+	dw_spi_xfer_done(dws);
+}
+
+static int mid_spi_dma_transfer(struct dw_spi *dws, int cs_change)
+{
+	struct dma_async_tx_descriptor *txdesc = NULL, *rxdesc = NULL;
+	struct dma_chan *txchan, *rxchan;
+	struct dma_slave_config txconf, rxconf;
+	u16 dma_ctrl = 0;
+
+	/* 1. setup DMA related registers */
+	if (cs_change) {
+		spi_enable_chip(dws, 0);
+		dw_writew(dws, dmardlr, 0xf);
+		dw_writew(dws, dmatdlr, 0x10);
+		if (dws->tx_dma)
+			dma_ctrl |= 0x2;
+		if (dws->rx_dma)
+			dma_ctrl |= 0x1;
+		dw_writew(dws, dmacr, dma_ctrl);
+		spi_enable_chip(dws, 1);
+	}
+
+	dws->dma_chan_done = 0;
+	txchan = dws->txchan;
+	rxchan = dws->rxchan;
+
+	/* 2. Prepare the TX dma transfer */
+	txconf.direction = DMA_TO_DEVICE;
+	txconf.dst_addr = dws->dma_addr;
+	txconf.dst_maxburst = LNW_DMA_MSIZE_16;
+	txconf.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	txconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+
+	txchan->device->device_control(txchan, DMA_SLAVE_CONFIG,
+				       (unsigned long) &txconf);
+
+	memset(&dws->tx_sgl, 0, sizeof(dws->tx_sgl));
+	dws->tx_sgl.dma_address = dws->tx_dma;
+	dws->tx_sgl.length = dws->len;
+
+	txdesc = txchan->device->device_prep_slave_sg(txchan,
+				&dws->tx_sgl,
+				1,
+				DMA_TO_DEVICE,
+				DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+	txdesc->callback = dw_spi_dma_done;
+	txdesc->callback_param = dws;
+
+	/* 3. Prepare the RX dma transfer */
+	rxconf.direction = DMA_FROM_DEVICE;
+	rxconf.src_addr = dws->dma_addr;
+	rxconf.src_maxburst = LNW_DMA_MSIZE_16;
+	rxconf.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
+	rxconf.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
+
+	rxchan->device->device_control(rxchan, DMA_SLAVE_CONFIG,
+				       (unsigned long) &rxconf);
+
+	memset(&dws->rx_sgl, 0, sizeof(dws->rx_sgl));
+	dws->rx_sgl.dma_address = dws->rx_dma;
+	dws->rx_sgl.length = dws->len;
+
+	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+				&dws->rx_sgl,
+				1,
+				DMA_FROM_DEVICE,
+				DMA_PREP_INTERRUPT | DMA_COMPL_SKIP_DEST_UNMAP);
+	rxdesc->callback = dw_spi_dma_done;
+	rxdesc->callback_param = dws;
+
+	/* rx must be started before tx due to spi instinct */
+	rxdesc->tx_submit(rxdesc);
+	txdesc->tx_submit(txdesc);
+	return 0;
+}
+
+static struct dw_spi_dma_ops mid_dma_ops = {
+	.dma_init	= mid_spi_dma_init,
+	.dma_exit	= mid_spi_dma_exit,
+	.dma_transfer	= mid_spi_dma_transfer,
+};
+#endif
+
+/* Some specific info for SPI0 controller on Moorestown */
+
+/* HW info for MRST CLk Control Unit, one 32b reg */
+#define MRST_SPI_CLK_BASE	100000000	/* 100m */
+#define MRST_CLK_SPI0_REG	0xff11d86c
+#define CLK_SPI_BDIV_OFFSET	0
+#define CLK_SPI_BDIV_MASK	0x00000007
+#define CLK_SPI_CDIV_OFFSET	9
+#define CLK_SPI_CDIV_MASK	0x00000e00
+#define CLK_SPI_DISABLE_OFFSET	8
+
+int dw_spi_mid_init(struct dw_spi *dws)
+{
+	u32 *clk_reg, clk_cdiv;
+
+	clk_reg = ioremap_nocache(MRST_CLK_SPI0_REG, 16);
+	if (!clk_reg)
+		return -ENOMEM;
+
+	/* get SPI controller operating freq info */
+	clk_cdiv  = (readl(clk_reg) & CLK_SPI_CDIV_MASK) >> CLK_SPI_CDIV_OFFSET;
+	dws->max_freq = MRST_SPI_CLK_BASE / (clk_cdiv + 1);
+	iounmap(clk_reg);
+
+	dws->num_cs = 16;
+	dws->fifo_len = 40;	/* FIFO has 40 words buffer */
+
+#ifdef CONFIG_SPI_DW_MID_DMA
+	dws->dma_priv = kzalloc(sizeof(struct mid_dma), GFP_KERNEL);
+	if (!dws->dma_priv)
+		return -ENOMEM;
+	dws->dma_ops = &mid_dma_ops;
+#endif
+	return 0;
+}
diff --git a/drivers/spi/dw_spi_pci.c b/drivers/spi/dw_spi_pci.c
index 1f52755dc878..49ec3aa1219f 100644
--- a/drivers/spi/dw_spi_pci.c
+++ b/drivers/spi/dw_spi_pci.c
@@ -1,5 +1,5 @@
 /*
- * mrst_spi_pci.c - PCI interface driver for DW SPI Core
+ * dw_spi_pci.c - PCI interface driver for DW SPI Core
  *
  * Copyright (c) 2009, Intel Corporation.
  *
@@ -26,8 +26,8 @@
 #define DRIVER_NAME "dw_spi_pci"
 
 struct dw_spi_pci {
-	struct pci_dev		*pdev;
-	struct dw_spi		dws;
+	struct pci_dev	*pdev;
+	struct dw_spi	dws;
 };
 
 static int __devinit spi_pci_probe(struct pci_dev *pdev,
@@ -72,9 +72,17 @@ static int __devinit spi_pci_probe(struct pci_dev *pdev,
 	dws->parent_dev = &pdev->dev;
 	dws->bus_num = 0;
 	dws->num_cs = 4;
-	dws->max_freq = 25000000;	/* for Moorestwon */
 	dws->irq = pdev->irq;
-	dws->fifo_len = 40;		/* FIFO has 40 words buffer */
+
+	/*
+	 * Specific handling for Intel MID paltforms, like dma setup,
+	 * clock rate, FIFO depth.
+	 */
+	if (pdev->device == 0x0800) {
+		ret = dw_spi_mid_init(dws);
+		if (ret)
+			goto err_unmap;
+	}
 
 	ret = dw_spi_add_host(dws);
 	if (ret)
@@ -140,7 +148,7 @@ static int spi_resume(struct pci_dev *pdev)
 #endif
 
 static const struct pci_device_id pci_ids[] __devinitdata = {
-	/* Intel Moorestown platform SPI controller 0 */
+	/* Intel MID platform SPI controller 0 */
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0800) },
 	{},
 };
diff --git a/drivers/spi/mpc52xx_psc_spi.c b/drivers/spi/mpc52xx_psc_spi.c
index 983fbbfce76e..8a904c1c8485 100644
--- a/drivers/spi/mpc52xx_psc_spi.c
+++ b/drivers/spi/mpc52xx_psc_spi.c
@@ -363,7 +363,7 @@ static irqreturn_t mpc52xx_psc_spi_isr(int irq, void *dev_id)
 }
 
 /* bus_num is used only for the case dev->platform_data == NULL */
-static int __init mpc52xx_psc_spi_do_probe(struct device *dev, u32 regaddr,
+static int __devinit mpc52xx_psc_spi_do_probe(struct device *dev, u32 regaddr,
 				u32 size, unsigned int irq, s16 bus_num)
 {
 	struct fsl_spi_platform_data *pdata = dev->platform_data;
@@ -450,22 +450,7 @@ free_master:
 	return ret;
 }
 
-static int __exit mpc52xx_psc_spi_do_remove(struct device *dev)
-{
-	struct spi_master *master = dev_get_drvdata(dev);
-	struct mpc52xx_psc_spi *mps = spi_master_get_devdata(master);
-
-	flush_workqueue(mps->workqueue);
-	destroy_workqueue(mps->workqueue);
-	spi_unregister_master(master);
-	free_irq(mps->irq, mps);
-	if (mps->psc)
-		iounmap(mps->psc);
-
-	return 0;
-}
-
-static int __init mpc52xx_psc_spi_of_probe(struct platform_device *op,
+static int __devinit mpc52xx_psc_spi_of_probe(struct platform_device *op,
 	const struct of_device_id *match)
 {
 	const u32 *regaddr_p;
@@ -495,9 +480,19 @@ static int __init mpc52xx_psc_spi_of_probe(struct platform_device *op,
 				irq_of_parse_and_map(op->dev.of_node, 0), id);
 }
 
-static int __exit mpc52xx_psc_spi_of_remove(struct platform_device *op)
+static int __devexit mpc52xx_psc_spi_of_remove(struct platform_device *op)
 {
-	return mpc52xx_psc_spi_do_remove(&op->dev);
+	struct spi_master *master = dev_get_drvdata(&op->dev);
+	struct mpc52xx_psc_spi *mps = spi_master_get_devdata(master);
+
+	flush_workqueue(mps->workqueue);
+	destroy_workqueue(mps->workqueue);
+	spi_unregister_master(master);
+	free_irq(mps->irq, mps);
+	if (mps->psc)
+		iounmap(mps->psc);
+
+	return 0;
 }
 
 static const struct of_device_id mpc52xx_psc_spi_of_match[] = {
@@ -510,7 +505,7 @@ MODULE_DEVICE_TABLE(of, mpc52xx_psc_spi_of_match);
 
 static struct of_platform_driver mpc52xx_psc_spi_of_driver = {
 	.probe = mpc52xx_psc_spi_of_probe,
-	.remove = __exit_p(mpc52xx_psc_spi_of_remove),
+	.remove = __devexit_p(mpc52xx_psc_spi_of_remove),
 	.driver = {
 		.name = "mpc52xx-psc-spi",
 		.owner = THIS_MODULE,
diff --git a/drivers/spi/omap2_mcspi.c b/drivers/spi/omap2_mcspi.c
index 951a160fc27f..abb1ffbf3d20 100644
--- a/drivers/spi/omap2_mcspi.c
+++ b/drivers/spi/omap2_mcspi.c
@@ -397,7 +397,7 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 
 	if (tx != NULL) {
 		wait_for_completion(&mcspi_dma->dma_tx_completion);
-		dma_unmap_single(NULL, xfer->tx_dma, count, DMA_TO_DEVICE);
+		dma_unmap_single(&spi->dev, xfer->tx_dma, count, DMA_TO_DEVICE);
 
 		/* for TX_ONLY mode, be sure all words have shifted out */
 		if (rx == NULL) {
@@ -412,7 +412,7 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 
 	if (rx != NULL) {
 		wait_for_completion(&mcspi_dma->dma_rx_completion);
-		dma_unmap_single(NULL, xfer->rx_dma, count, DMA_FROM_DEVICE);
+		dma_unmap_single(&spi->dev, xfer->rx_dma, count, DMA_FROM_DEVICE);
 		omap2_mcspi_set_enable(spi, 0);
 
 		if (l & OMAP2_MCSPI_CHCONF_TURBO) {
@@ -1025,11 +1025,6 @@ static int omap2_mcspi_transfer(struct spi_device *spi, struct spi_message *m)
 		if (m->is_dma_mapped || len < DMA_MIN_BYTES)
 			continue;
 
-		/* Do DMA mapping "early" for better error reporting and
-		 * dcache use.  Note that if dma_unmap_single() ever starts
-		 * to do real work on ARM, we'd need to clean up mappings
-		 * for previous transfers on *ALL* exits of this loop...
-		 */
 		if (tx_buf != NULL) {
 			t->tx_dma = dma_map_single(&spi->dev, (void *) tx_buf,
 					len, DMA_TO_DEVICE);
@@ -1046,7 +1041,7 @@ static int omap2_mcspi_transfer(struct spi_device *spi, struct spi_message *m)
 				dev_dbg(&spi->dev, "dma %cX %d bytes error\n",
 						'R', len);
 				if (tx_buf != NULL)
-					dma_unmap_single(NULL, t->tx_dma,
+					dma_unmap_single(&spi->dev, t->tx_dma,
 							len, DMA_TO_DEVICE);
 				return -EINVAL;
 			}
diff --git a/drivers/spi/pxa2xx_spi.c b/drivers/spi/pxa2xx_spi.c
index e76b1afafe07..95928833855b 100644
--- a/drivers/spi/pxa2xx_spi.c
+++ b/drivers/spi/pxa2xx_spi.c
@@ -23,11 +23,11 @@
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/spi/pxa2xx_spi.h>
 #include <linux/dma-mapping.h>
 #include <linux/spi/spi.h>
 #include <linux/workqueue.h>
 #include <linux/delay.h>
-#include <linux/clk.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
 
@@ -35,9 +35,6 @@
 #include <asm/irq.h>
 #include <asm/delay.h>
 
-#include <mach/dma.h>
-#include <plat/ssp.h>
-#include <mach/pxa2xx_spi.h>
 
 MODULE_AUTHOR("Stephen Street");
 MODULE_DESCRIPTION("PXA2xx SSP SPI Controller");
@@ -46,8 +43,6 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 
 #define MAX_BUSES 3
 
-#define RX_THRESH_DFLT 	8
-#define TX_THRESH_DFLT 	8
 #define TIMOUT_DFLT		1000
 
 #define DMA_INT_MASK		(DCSR_ENDINTR | DCSR_STARTINTR | DCSR_BUSERR)
@@ -168,7 +163,10 @@ struct chip_data {
 	u8 enable_dma;
 	u8 bits_per_word;
 	u32 speed_hz;
-	int gpio_cs;
+	union {
+		int gpio_cs;
+		unsigned int frm;
+	};
 	int gpio_cs_inverted;
 	int (*write)(struct driver_data *drv_data);
 	int (*read)(struct driver_data *drv_data);
@@ -181,6 +179,11 @@ static void cs_assert(struct driver_data *drv_data)
 {
 	struct chip_data *chip = drv_data->cur_chip;
 
+	if (drv_data->ssp_type == CE4100_SSP) {
+		write_SSSR(drv_data->cur_chip->frm, drv_data->ioaddr);
+		return;
+	}
+
 	if (chip->cs_control) {
 		chip->cs_control(PXA2XX_CS_ASSERT);
 		return;
@@ -194,6 +197,9 @@ static void cs_deassert(struct driver_data *drv_data)
 {
 	struct chip_data *chip = drv_data->cur_chip;
 
+	if (drv_data->ssp_type == CE4100_SSP)
+		return;
+
 	if (chip->cs_control) {
 		chip->cs_control(PXA2XX_CS_DEASSERT);
 		return;
@@ -203,6 +209,25 @@ static void cs_deassert(struct driver_data *drv_data)
 		gpio_set_value(chip->gpio_cs, !chip->gpio_cs_inverted);
 }
 
+static void write_SSSR_CS(struct driver_data *drv_data, u32 val)
+{
+	void __iomem *reg = drv_data->ioaddr;
+
+	if (drv_data->ssp_type == CE4100_SSP)
+		val |= read_SSSR(reg) & SSSR_ALT_FRM_MASK;
+
+	write_SSSR(val, reg);
+}
+
+static int pxa25x_ssp_comp(struct driver_data *drv_data)
+{
+	if (drv_data->ssp_type == PXA25x_SSP)
+		return 1;
+	if (drv_data->ssp_type == CE4100_SSP)
+		return 1;
+	return 0;
+}
+
 static int flush(struct driver_data *drv_data)
 {
 	unsigned long limit = loops_per_jiffy << 1;
@@ -214,7 +239,7 @@ static int flush(struct driver_data *drv_data)
 			read_SSDR(reg);
 		}
 	} while ((read_SSSR(reg) & SSSR_BSY) && --limit);
-	write_SSSR(SSSR_ROR, reg);
+	write_SSSR_CS(drv_data, SSSR_ROR);
 
 	return limit;
 }
@@ -224,7 +249,7 @@ static int null_writer(struct driver_data *drv_data)
 	void __iomem *reg = drv_data->ioaddr;
 	u8 n_bytes = drv_data->n_bytes;
 
-	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
+	if (((read_SSSR(reg) & SSSR_TFL_MASK) == SSSR_TFL_MASK)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
@@ -252,7 +277,7 @@ static int u8_writer(struct driver_data *drv_data)
 {
 	void __iomem *reg = drv_data->ioaddr;
 
-	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
+	if (((read_SSSR(reg) & SSSR_TFL_MASK) == SSSR_TFL_MASK)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
@@ -279,7 +304,7 @@ static int u16_writer(struct driver_data *drv_data)
 {
 	void __iomem *reg = drv_data->ioaddr;
 
-	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
+	if (((read_SSSR(reg) & SSSR_TFL_MASK) == SSSR_TFL_MASK)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
@@ -306,7 +331,7 @@ static int u32_writer(struct driver_data *drv_data)
 {
 	void __iomem *reg = drv_data->ioaddr;
 
-	if (((read_SSSR(reg) & 0x00000f00) == 0x00000f00)
+	if (((read_SSSR(reg) & SSSR_TFL_MASK) == SSSR_TFL_MASK)
 		|| (drv_data->tx == drv_data->tx_end))
 		return 0;
 
@@ -507,9 +532,9 @@ static void dma_error_stop(struct driver_data *drv_data, const char *msg)
 	/* Stop and reset */
 	DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL;
 	DCSR(drv_data->tx_channel) = RESET_DMA_CHANNEL;
-	write_SSSR(drv_data->clear_sr, reg);
+	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg);
-	if (drv_data->ssp_type != PXA25x_SSP)
+	if (!pxa25x_ssp_comp(drv_data))
 		write_SSTO(0, reg);
 	flush(drv_data);
 	write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
@@ -529,7 +554,7 @@ static void dma_transfer_complete(struct driver_data *drv_data)
 
 	/* Clear and disable interrupts on SSP and DMA channels*/
 	write_SSCR1(read_SSCR1(reg) & ~drv_data->dma_cr1, reg);
-	write_SSSR(drv_data->clear_sr, reg);
+	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	DCSR(drv_data->tx_channel) = RESET_DMA_CHANNEL;
 	DCSR(drv_data->rx_channel) = RESET_DMA_CHANNEL;
 
@@ -622,7 +647,7 @@ static irqreturn_t dma_transfer(struct driver_data *drv_data)
 
 		/* Clear and disable timeout interrupt, do the rest in
 		 * dma_transfer_complete */
-		if (drv_data->ssp_type != PXA25x_SSP)
+		if (!pxa25x_ssp_comp(drv_data))
 			write_SSTO(0, reg);
 
 		/* finish this transfer, start the next */
@@ -635,14 +660,26 @@ static irqreturn_t dma_transfer(struct driver_data *drv_data)
 	return IRQ_NONE;
 }
 
+static void reset_sccr1(struct driver_data *drv_data)
+{
+	void __iomem *reg = drv_data->ioaddr;
+	struct chip_data *chip = drv_data->cur_chip;
+	u32 sccr1_reg;
+
+	sccr1_reg = read_SSCR1(reg) & ~drv_data->int_cr1;
+	sccr1_reg &= ~SSCR1_RFT;
+	sccr1_reg |= chip->threshold;
+	write_SSCR1(sccr1_reg, reg);
+}
+
 static void int_error_stop(struct driver_data *drv_data, const char* msg)
 {
 	void __iomem *reg = drv_data->ioaddr;
 
 	/* Stop and reset SSP */
-	write_SSSR(drv_data->clear_sr, reg);
-	write_SSCR1(read_SSCR1(reg) & ~drv_data->int_cr1, reg);
-	if (drv_data->ssp_type != PXA25x_SSP)
+	write_SSSR_CS(drv_data, drv_data->clear_sr);
+	reset_sccr1(drv_data);
+	if (!pxa25x_ssp_comp(drv_data))
 		write_SSTO(0, reg);
 	flush(drv_data);
 	write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
@@ -658,9 +695,9 @@ static void int_transfer_complete(struct driver_data *drv_data)
 	void __iomem *reg = drv_data->ioaddr;
 
 	/* Stop SSP */
-	write_SSSR(drv_data->clear_sr, reg);
-	write_SSCR1(read_SSCR1(reg) & ~drv_data->int_cr1, reg);
-	if (drv_data->ssp_type != PXA25x_SSP)
+	write_SSSR_CS(drv_data, drv_data->clear_sr);
+	reset_sccr1(drv_data);
+	if (!pxa25x_ssp_comp(drv_data))
 		write_SSTO(0, reg);
 
 	/* Update total byte transfered return count actual bytes read */
@@ -714,24 +751,34 @@ static irqreturn_t interrupt_transfer(struct driver_data *drv_data)
 	}
 
 	if (drv_data->tx == drv_data->tx_end) {
-		write_SSCR1(read_SSCR1(reg) & ~SSCR1_TIE, reg);
-		/* PXA25x_SSP has no timeout, read trailing bytes */
-		if (drv_data->ssp_type == PXA25x_SSP) {
-			if (!wait_ssp_rx_stall(reg))
-			{
-				int_error_stop(drv_data, "interrupt_transfer: "
-						"rx stall failed");
-				return IRQ_HANDLED;
-			}
-			if (!drv_data->read(drv_data))
-			{
-				int_error_stop(drv_data,
-						"interrupt_transfer: "
-						"trailing byte read failed");
-				return IRQ_HANDLED;
+		u32 bytes_left;
+		u32 sccr1_reg;
+
+		sccr1_reg = read_SSCR1(reg);
+		sccr1_reg &= ~SSCR1_TIE;
+
+		/*
+		 * PXA25x_SSP has no timeout, set up rx threshould for the
+		 * remaing RX bytes.
+		 */
+		if (pxa25x_ssp_comp(drv_data)) {
+
+			sccr1_reg &= ~SSCR1_RFT;
+
+			bytes_left = drv_data->rx_end - drv_data->rx;
+			switch (drv_data->n_bytes) {
+			case 4:
+				bytes_left >>= 1;
+			case 2:
+				bytes_left >>= 1;
 			}
-			int_transfer_complete(drv_data);
+
+			if (bytes_left > RX_THRESH_DFLT)
+				bytes_left = RX_THRESH_DFLT;
+
+			sccr1_reg |= SSCR1_RxTresh(bytes_left);
 		}
+		write_SSCR1(sccr1_reg, reg);
 	}
 
 	/* We did something */
@@ -742,14 +789,26 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 {
 	struct driver_data *drv_data = dev_id;
 	void __iomem *reg = drv_data->ioaddr;
+	u32 sccr1_reg = read_SSCR1(reg);
+	u32 mask = drv_data->mask_sr;
+	u32 status;
+
+	status = read_SSSR(reg);
+
+	/* Ignore possible writes if we don't need to write */
+	if (!(sccr1_reg & SSCR1_TIE))
+		mask &= ~SSSR_TFS;
+
+	if (!(status & mask))
+		return IRQ_NONE;
 
 	if (!drv_data->cur_msg) {
 
 		write_SSCR0(read_SSCR0(reg) & ~SSCR0_SSE, reg);
 		write_SSCR1(read_SSCR1(reg) & ~drv_data->int_cr1, reg);
-		if (drv_data->ssp_type != PXA25x_SSP)
+		if (!pxa25x_ssp_comp(drv_data))
 			write_SSTO(0, reg);
-		write_SSSR(drv_data->clear_sr, reg);
+		write_SSSR_CS(drv_data, drv_data->clear_sr);
 
 		dev_err(&drv_data->pdev->dev, "bad message state "
 			"in interrupt handler\n");
@@ -862,7 +921,7 @@ static unsigned int ssp_get_clk_div(struct ssp_device *ssp, int rate)
 {
 	unsigned long ssp_clk = clk_get_rate(ssp->clk);
 
-	if (ssp->type == PXA25x_SSP)
+	if (ssp->type == PXA25x_SSP || ssp->type == CE4100_SSP)
 		return ((ssp_clk / (2 * rate) - 1) & 0xff) << 8;
 	else
 		return ((ssp_clk / rate - 1) & 0xfff) << 8;
@@ -1088,7 +1147,7 @@ static void pump_transfers(unsigned long data)
 
 		/* Clear status  */
 		cr1 = chip->cr1 | chip->threshold | drv_data->int_cr1;
-		write_SSSR(drv_data->clear_sr, reg);
+		write_SSSR_CS(drv_data, drv_data->clear_sr);
 	}
 
 	/* see if we need to reload the config registers */
@@ -1098,7 +1157,7 @@ static void pump_transfers(unsigned long data)
 
 		/* stop the SSP, and update the other bits */
 		write_SSCR0(cr0 & ~SSCR0_SSE, reg);
-		if (drv_data->ssp_type != PXA25x_SSP)
+		if (!pxa25x_ssp_comp(drv_data))
 			write_SSTO(chip->timeout, reg);
 		/* first set CR1 without interrupt and service enables */
 		write_SSCR1(cr1 & SSCR1_CHANGE_MASK, reg);
@@ -1106,7 +1165,7 @@ static void pump_transfers(unsigned long data)
 		write_SSCR0(cr0, reg);
 
 	} else {
-		if (drv_data->ssp_type != PXA25x_SSP)
+		if (!pxa25x_ssp_comp(drv_data))
 			write_SSTO(chip->timeout, reg);
 	}
 
@@ -1233,14 +1292,13 @@ static int setup(struct spi_device *spi)
 	uint tx_thres = TX_THRESH_DFLT;
 	uint rx_thres = RX_THRESH_DFLT;
 
-	if (drv_data->ssp_type != PXA25x_SSP
+	if (!pxa25x_ssp_comp(drv_data)
 		&& (spi->bits_per_word < 4 || spi->bits_per_word > 32)) {
 		dev_err(&spi->dev, "failed setup: ssp_type=%d, bits/wrd=%d "
 				"b/w not 4-32 for type non-PXA25x_SSP\n",
 				drv_data->ssp_type, spi->bits_per_word);
 		return -EINVAL;
-	}
-	else if (drv_data->ssp_type == PXA25x_SSP
+	} else if (pxa25x_ssp_comp(drv_data)
 			&& (spi->bits_per_word < 4
 				|| spi->bits_per_word > 16)) {
 		dev_err(&spi->dev, "failed setup: ssp_type=%d, bits/wrd=%d "
@@ -1259,7 +1317,17 @@ static int setup(struct spi_device *spi)
 			return -ENOMEM;
 		}
 
-		chip->gpio_cs = -1;
+		if (drv_data->ssp_type == CE4100_SSP) {
+			if (spi->chip_select > 4) {
+				dev_err(&spi->dev, "failed setup: "
+				"cs number must not be > 4.\n");
+				kfree(chip);
+				return -EINVAL;
+			}
+
+			chip->frm = spi->chip_select;
+		} else
+			chip->gpio_cs = -1;
 		chip->enable_dma = 0;
 		chip->timeout = TIMOUT_DFLT;
 		chip->dma_burst_size = drv_data->master_info->enable_dma ?
@@ -1315,7 +1383,7 @@ static int setup(struct spi_device *spi)
 			| (((spi->mode & SPI_CPOL) != 0) ? SSCR1_SPO : 0);
 
 	/* NOTE:  PXA25x_SSP _could_ use external clocking ... */
-	if (drv_data->ssp_type != PXA25x_SSP)
+	if (!pxa25x_ssp_comp(drv_data))
 		dev_dbg(&spi->dev, "%ld Hz actual, %s\n",
 			clk_get_rate(ssp->clk)
 				/ (1 + ((chip->cr0 & SSCR0_SCR(0xfff)) >> 8)),
@@ -1350,23 +1418,27 @@ static int setup(struct spi_device *spi)
 
 	spi_set_ctldata(spi, chip);
 
+	if (drv_data->ssp_type == CE4100_SSP)
+		return 0;
+
 	return setup_cs(spi, chip, chip_info);
 }
 
 static void cleanup(struct spi_device *spi)
 {
 	struct chip_data *chip = spi_get_ctldata(spi);
+	struct driver_data *drv_data = spi_master_get_devdata(spi->master);
 
 	if (!chip)
 		return;
 
-	if (gpio_is_valid(chip->gpio_cs))
+	if (drv_data->ssp_type != CE4100_SSP && gpio_is_valid(chip->gpio_cs))
 		gpio_free(chip->gpio_cs);
 
 	kfree(chip);
 }
 
-static int __init init_queue(struct driver_data *drv_data)
+static int __devinit init_queue(struct driver_data *drv_data)
 {
 	INIT_LIST_HEAD(&drv_data->queue);
 	spin_lock_init(&drv_data->lock);
@@ -1454,7 +1526,7 @@ static int destroy_queue(struct driver_data *drv_data)
 	return 0;
 }
 
-static int __init pxa2xx_spi_probe(struct platform_device *pdev)
+static int __devinit pxa2xx_spi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct pxa2xx_spi_master *platform_info;
@@ -1484,6 +1556,10 @@ static int __init pxa2xx_spi_probe(struct platform_device *pdev)
 	drv_data->pdev = pdev;
 	drv_data->ssp = ssp;
 
+	master->dev.parent = &pdev->dev;
+#ifdef CONFIG_OF
+	master->dev.of_node = pdev->dev.of_node;
+#endif
 	/* the spi->mode bits understood by this driver: */
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 
@@ -1500,7 +1576,7 @@ static int __init pxa2xx_spi_probe(struct platform_device *pdev)
 
 	drv_data->ioaddr = ssp->mmio_base;
 	drv_data->ssdr_physical = ssp->phys_base + SSDR;
-	if (ssp->type == PXA25x_SSP) {
+	if (pxa25x_ssp_comp(drv_data)) {
 		drv_data->int_cr1 = SSCR1_TIE | SSCR1_RIE;
 		drv_data->dma_cr1 = 0;
 		drv_data->clear_sr = SSSR_ROR;
@@ -1512,7 +1588,8 @@ static int __init pxa2xx_spi_probe(struct platform_device *pdev)
 		drv_data->mask_sr = SSSR_TINT | SSSR_RFS | SSSR_TFS | SSSR_ROR;
 	}
 
-	status = request_irq(ssp->irq, ssp_int, 0, dev_name(dev), drv_data);
+	status = request_irq(ssp->irq, ssp_int, IRQF_SHARED, dev_name(dev),
+			drv_data);
 	if (status < 0) {
 		dev_err(&pdev->dev, "cannot get IRQ %d\n", ssp->irq);
 		goto out_error_master_alloc;
@@ -1561,7 +1638,7 @@ static int __init pxa2xx_spi_probe(struct platform_device *pdev)
 			| SSCR0_Motorola
 			| SSCR0_DataSize(8),
 			drv_data->ioaddr);
-	if (drv_data->ssp_type != PXA25x_SSP)
+	if (!pxa25x_ssp_comp(drv_data))
 		write_SSTO(0, drv_data->ioaddr);
 	write_SSPSP(0, drv_data->ioaddr);
 
@@ -1723,13 +1800,14 @@ static struct platform_driver driver = {
 		.pm	= &pxa2xx_spi_pm_ops,
 #endif
 	},
+	.probe = pxa2xx_spi_probe,
 	.remove = pxa2xx_spi_remove,
 	.shutdown = pxa2xx_spi_shutdown,
 };
 
 static int __init pxa2xx_spi_init(void)
 {
-	return platform_driver_probe(&driver, pxa2xx_spi_probe);
+	return platform_driver_register(&driver);
 }
 subsys_initcall(pxa2xx_spi_init);
 
diff --git a/drivers/spi/pxa2xx_spi_pci.c b/drivers/spi/pxa2xx_spi_pci.c
new file mode 100644
index 000000000000..351d8a375b57
--- /dev/null
+++ b/drivers/spi/pxa2xx_spi_pci.c
@@ -0,0 +1,201 @@
+/*
+ * CE4100's SPI device is more or less the same one as found on PXA
+ *
+ */
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/of_device.h>
+#include <linux/spi/pxa2xx_spi.h>
+
+struct awesome_struct {
+	struct ssp_device ssp;
+	struct platform_device spi_pdev;
+	struct pxa2xx_spi_master spi_pdata;
+};
+
+static DEFINE_MUTEX(ssp_lock);
+static LIST_HEAD(ssp_list);
+
+struct ssp_device *pxa_ssp_request(int port, const char *label)
+{
+	struct ssp_device *ssp = NULL;
+
+	mutex_lock(&ssp_lock);
+
+	list_for_each_entry(ssp, &ssp_list, node) {
+		if (ssp->port_id == port && ssp->use_count == 0) {
+			ssp->use_count++;
+			ssp->label = label;
+			break;
+		}
+	}
+
+	mutex_unlock(&ssp_lock);
+
+	if (&ssp->node == &ssp_list)
+		return NULL;
+
+	return ssp;
+}
+EXPORT_SYMBOL_GPL(pxa_ssp_request);
+
+void pxa_ssp_free(struct ssp_device *ssp)
+{
+	mutex_lock(&ssp_lock);
+	if (ssp->use_count) {
+		ssp->use_count--;
+		ssp->label = NULL;
+	} else
+		dev_err(&ssp->pdev->dev, "device already free\n");
+	mutex_unlock(&ssp_lock);
+}
+EXPORT_SYMBOL_GPL(pxa_ssp_free);
+
+static void plat_dev_release(struct device *dev)
+{
+	struct awesome_struct *as = container_of(dev,
+			struct awesome_struct, spi_pdev.dev);
+
+	of_device_node_put(&as->spi_pdev.dev);
+}
+
+static int __devinit ce4100_spi_probe(struct pci_dev *dev,
+		const struct pci_device_id *ent)
+{
+	int ret;
+	resource_size_t phys_beg;
+	resource_size_t phys_len;
+	struct awesome_struct *spi_info;
+	struct platform_device *pdev;
+	struct pxa2xx_spi_master *spi_pdata;
+	struct ssp_device *ssp;
+
+	ret = pci_enable_device(dev);
+	if (ret)
+		return ret;
+
+	phys_beg = pci_resource_start(dev, 0);
+	phys_len = pci_resource_len(dev, 0);
+
+	if (!request_mem_region(phys_beg, phys_len,
+				"CE4100 SPI")) {
+		dev_err(&dev->dev, "Can't request register space.\n");
+		ret = -EBUSY;
+		return ret;
+	}
+
+	spi_info = kzalloc(sizeof(*spi_info), GFP_KERNEL);
+	if (!spi_info) {
+		ret = -ENOMEM;
+		goto err_kz;
+	}
+	ssp = &spi_info->ssp;
+	pdev = &spi_info->spi_pdev;
+	spi_pdata =  &spi_info->spi_pdata;
+
+	pdev->name = "pxa2xx-spi";
+	pdev->id = dev->devfn;
+	pdev->dev.parent = &dev->dev;
+	pdev->dev.platform_data = &spi_info->spi_pdata;
+
+#ifdef CONFIG_OF
+	pdev->dev.of_node = dev->dev.of_node;
+#endif
+	pdev->dev.release = plat_dev_release;
+
+	spi_pdata->num_chipselect = dev->devfn;
+
+	ssp->phys_base = pci_resource_start(dev, 0);
+	ssp->mmio_base = ioremap(phys_beg, phys_len);
+	if (!ssp->mmio_base) {
+		dev_err(&pdev->dev, "failed to ioremap() registers\n");
+		ret = -EIO;
+		goto err_remap;
+	}
+	ssp->irq = dev->irq;
+	ssp->port_id = pdev->id;
+	ssp->type = PXA25x_SSP;
+
+	mutex_lock(&ssp_lock);
+	list_add(&ssp->node, &ssp_list);
+	mutex_unlock(&ssp_lock);
+
+	pci_set_drvdata(dev, spi_info);
+
+	ret = platform_device_register(pdev);
+	if (ret)
+		goto err_dev_add;
+
+	return ret;
+
+err_dev_add:
+	pci_set_drvdata(dev, NULL);
+	mutex_lock(&ssp_lock);
+	list_del(&ssp->node);
+	mutex_unlock(&ssp_lock);
+	iounmap(ssp->mmio_base);
+
+err_remap:
+	kfree(spi_info);
+
+err_kz:
+	release_mem_region(phys_beg, phys_len);
+
+	return ret;
+}
+
+static void __devexit ce4100_spi_remove(struct pci_dev *dev)
+{
+	struct awesome_struct *spi_info;
+	struct platform_device *pdev;
+	struct ssp_device *ssp;
+
+	spi_info = pci_get_drvdata(dev);
+
+	ssp = &spi_info->ssp;
+	pdev = &spi_info->spi_pdev;
+
+	platform_device_unregister(pdev);
+
+	iounmap(ssp->mmio_base);
+	release_mem_region(pci_resource_start(dev, 0),
+			pci_resource_len(dev, 0));
+
+	mutex_lock(&ssp_lock);
+	list_del(&ssp->node);
+	mutex_unlock(&ssp_lock);
+
+	pci_set_drvdata(dev, NULL);
+	pci_disable_device(dev);
+	kfree(spi_info);
+}
+
+static struct pci_device_id ce4100_spi_devices[] __devinitdata = {
+
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2e6a) },
+	{ },
+};
+MODULE_DEVICE_TABLE(pci, ce4100_spi_devices);
+
+static struct pci_driver ce4100_spi_driver = {
+	.name           = "ce4100_spi",
+	.id_table       = ce4100_spi_devices,
+	.probe          = ce4100_spi_probe,
+	.remove         = __devexit_p(ce4100_spi_remove),
+};
+
+static int __init ce4100_spi_init(void)
+{
+	return pci_register_driver(&ce4100_spi_driver);
+}
+module_init(ce4100_spi_init);
+
+static void __exit ce4100_spi_exit(void)
+{
+	pci_unregister_driver(&ce4100_spi_driver);
+}
+module_exit(ce4100_spi_exit);
+
+MODULE_DESCRIPTION("CE4100 PCI-SPI glue code for PXA's driver");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Sebastian Andrzej Siewior <bigeasy@linutronix.de>");
diff --git a/drivers/spi/spi_imx.c b/drivers/spi/spi_imx.c
index 55a38e2c6c13..9469564e6888 100644
--- a/drivers/spi/spi_imx.c
+++ b/drivers/spi/spi_imx.c
@@ -66,7 +66,6 @@ enum spi_imx_devtype {
 	SPI_IMX_VER_0_5,
 	SPI_IMX_VER_0_7,
 	SPI_IMX_VER_2_3,
-	SPI_IMX_VER_AUTODETECT,
 };
 
 struct spi_imx_data;
@@ -720,9 +719,6 @@ static void spi_imx_cleanup(struct spi_device *spi)
 
 static struct platform_device_id spi_imx_devtype[] = {
 	{
-		.name = DRIVER_NAME,
-		.driver_data = SPI_IMX_VER_AUTODETECT,
-	}, {
 		.name = "imx1-cspi",
 		.driver_data = SPI_IMX_VER_IMX1,
 	}, {
@@ -802,30 +798,8 @@ static int __devinit spi_imx_probe(struct platform_device *pdev)
 
 	init_completion(&spi_imx->xfer_done);
 
-	if (pdev->id_entry->driver_data == SPI_IMX_VER_AUTODETECT) {
-		if (cpu_is_mx25() || cpu_is_mx35())
-			spi_imx->devtype_data =
-				spi_imx_devtype_data[SPI_IMX_VER_0_7];
-		else if (cpu_is_mx25() || cpu_is_mx31() || cpu_is_mx35())
-			spi_imx->devtype_data =
-				spi_imx_devtype_data[SPI_IMX_VER_0_4];
-		else if (cpu_is_mx27() || cpu_is_mx21())
-			spi_imx->devtype_data =
-				spi_imx_devtype_data[SPI_IMX_VER_0_0];
-		else if (cpu_is_mx1())
-			spi_imx->devtype_data =
-				spi_imx_devtype_data[SPI_IMX_VER_IMX1];
-		else
-			BUG();
-	} else
-		spi_imx->devtype_data =
-			spi_imx_devtype_data[pdev->id_entry->driver_data];
-
-	if (!spi_imx->devtype_data.intctrl) {
-		dev_err(&pdev->dev, "no support for this device compiled in\n");
-		ret = -ENODEV;
-		goto out_gpio_free;
-	}
+	spi_imx->devtype_data =
+		spi_imx_devtype_data[pdev->id_entry->driver_data];
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
@@ -847,7 +821,7 @@ static int __devinit spi_imx_probe(struct platform_device *pdev)
 	}
 
 	spi_imx->irq = platform_get_irq(pdev, 0);
-	if (spi_imx->irq <= 0) {
+	if (spi_imx->irq < 0) {
 		ret = -EINVAL;
 		goto out_iounmap;
 	}
diff --git a/drivers/spi/spi_nuc900.c b/drivers/spi/spi_nuc900.c
index dff63be0d0a8..d5be18b3078c 100644
--- a/drivers/spi/spi_nuc900.c
+++ b/drivers/spi/spi_nuc900.c
@@ -449,7 +449,7 @@ err_iomap:
 	release_mem_region(hw->res->start, resource_size(hw->res));
 	kfree(hw->ioarea);
 err_pdata:
-	spi_master_put(hw->master);;
+	spi_master_put(hw->master);
 
 err_nomem:
 	return err;
diff --git a/drivers/spi/spi_topcliff_pch.c b/drivers/spi/spi_topcliff_pch.c
index 58e187f45ec7..79e48d451137 100644
--- a/drivers/spi/spi_topcliff_pch.c
+++ b/drivers/spi/spi_topcliff_pch.c
@@ -267,7 +267,7 @@ static void pch_spi_handler_sub(struct pch_spi_data *data, u32 reg_spsr_val,
 	if (reg_spsr_val & SPSR_FI_BIT) {
 		/* disable FI & RFI interrupts */
 		pch_spi_setclr_reg(data->master, PCH_SPCR, 0,
-				   SPCR_FIE_BIT | SPCR_TFIE_BIT);
+				   SPCR_FIE_BIT | SPCR_RFIE_BIT);
 
 		/* transfer is completed;inform pch_spi_process_messages */
 		data->transfer_complete = true;
@@ -677,15 +677,15 @@ static void pch_spi_set_ir(struct pch_spi_data *data)
 {
 	/* enable interrupts */
 	if ((data->bpw_len) > PCH_MAX_FIFO_DEPTH) {
-		/* set receive threhold to PCH_RX_THOLD */
+		/* set receive threshold to PCH_RX_THOLD */
 		pch_spi_setclr_reg(data->master, PCH_SPCR,
-				   PCH_RX_THOLD << SPCR_TFIC_FIELD,
-				   ~MASK_TFIC_SPCR_BITS);
+				   PCH_RX_THOLD << SPCR_RFIC_FIELD,
+				   ~MASK_RFIC_SPCR_BITS);
 		/* enable FI and RFI interrupts */
 		pch_spi_setclr_reg(data->master, PCH_SPCR,
-				   SPCR_RFIE_BIT | SPCR_TFIE_BIT, 0);
+				   SPCR_RFIE_BIT | SPCR_FIE_BIT, 0);
 	} else {
-		/* set receive threhold to maximum */
+		/* set receive threshold to maximum */
 		pch_spi_setclr_reg(data->master, PCH_SPCR,
 				   PCH_RX_THOLD_MAX << SPCR_TFIC_FIELD,
 				   ~MASK_TFIC_SPCR_BITS);
diff --git a/drivers/spi/xilinx_spi.c b/drivers/spi/xilinx_spi.c
index 80f2db5bcfd6..7adaef62a991 100644
--- a/drivers/spi/xilinx_spi.c
+++ b/drivers/spi/xilinx_spi.c
@@ -1,26 +1,27 @@
 /*
- * xilinx_spi.c
- *
  * Xilinx SPI controller driver (master mode only)
  *
  * Author: MontaVista Software, Inc.
  *	source@mvista.com
  *
- * 2002-2007 (c) MontaVista Software, Inc.  This file is licensed under the
- * terms of the GNU General Public License version 2.  This program is licensed
- * "as is" without any warranty of any kind, whether express or implied.
+ * Copyright (c) 2010 Secret Lab Technologies, Ltd.
+ * Copyright (c) 2009 Intel Corporation
+ * 2002-2007 (c) MontaVista Software, Inc.
+
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
-
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
-#include <linux/io.h>
-
-#include "xilinx_spi.h"
 #include <linux/spi/xilinx_spi.h>
+#include <linux/io.h>
 
 #define XILINX_SPI_NAME "xilinx_spi"
 
@@ -350,19 +351,22 @@ static irqreturn_t xilinx_spi_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id xilinx_spi_of_match[] = {
+	{ .compatible = "xlnx,xps-spi-2.00.a", },
+	{ .compatible = "xlnx,xps-spi-2.00.b", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, xilinx_spi_of_match);
+#endif
+
 struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
-	u32 irq, s16 bus_num)
+	u32 irq, s16 bus_num, int num_cs, int little_endian, int bits_per_word)
 {
 	struct spi_master *master;
 	struct xilinx_spi *xspi;
-	struct xspi_platform_data *pdata = dev->platform_data;
 	int ret;
 
-	if (!pdata) {
-		dev_err(dev, "No platform data attached\n");
-		return NULL;
-	}
-
 	master = spi_alloc_master(dev, sizeof(struct xilinx_spi));
 	if (!master)
 		return NULL;
@@ -389,21 +393,21 @@ struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
 	}
 
 	master->bus_num = bus_num;
-	master->num_chipselect = pdata->num_chipselect;
+	master->num_chipselect = num_cs;
 #ifdef CONFIG_OF
 	master->dev.of_node = dev->of_node;
 #endif
 
 	xspi->mem = *mem;
 	xspi->irq = irq;
-	if (pdata->little_endian) {
+	if (little_endian) {
 		xspi->read_fn = xspi_read32;
 		xspi->write_fn = xspi_write32;
 	} else {
 		xspi->read_fn = xspi_read32_be;
 		xspi->write_fn = xspi_write32_be;
 	}
-	xspi->bits_per_word = pdata->bits_per_word;
+	xspi->bits_per_word = bits_per_word;
 	if (xspi->bits_per_word == 8) {
 		xspi->tx_fn = xspi_tx8;
 		xspi->rx_fn = xspi_rx8;
@@ -462,6 +466,97 @@ void xilinx_spi_deinit(struct spi_master *master)
 }
 EXPORT_SYMBOL(xilinx_spi_deinit);
 
+static int __devinit xilinx_spi_probe(struct platform_device *dev)
+{
+	struct xspi_platform_data *pdata;
+	struct resource *r;
+	int irq, num_cs = 0, little_endian = 0, bits_per_word = 8;
+	struct spi_master *master;
+	u8 i;
+
+	pdata = dev->dev.platform_data;
+	if (pdata) {
+		num_cs = pdata->num_chipselect;
+		little_endian = pdata->little_endian;
+		bits_per_word = pdata->bits_per_word;
+	}
+
+#ifdef CONFIG_OF
+	if (dev->dev.of_node) {
+		const __be32 *prop;
+		int len;
+
+		/* number of slave select bits is required */
+		prop = of_get_property(dev->dev.of_node, "xlnx,num-ss-bits",
+				       &len);
+		if (prop && len >= sizeof(*prop))
+			num_cs = __be32_to_cpup(prop);
+	}
+#endif
+
+	if (!num_cs) {
+		dev_err(&dev->dev, "Missing slave select configuration data\n");
+		return -EINVAL;
+	}
+
+
+	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!r)
+		return -ENODEV;
+
+	irq = platform_get_irq(dev, 0);
+	if (irq < 0)
+		return -ENXIO;
+
+	master = xilinx_spi_init(&dev->dev, r, irq, dev->id, num_cs,
+				 little_endian, bits_per_word);
+	if (!master)
+		return -ENODEV;
+
+	if (pdata) {
+		for (i = 0; i < pdata->num_devices; i++)
+			spi_new_device(master, pdata->devices + i);
+	}
+
+	platform_set_drvdata(dev, master);
+	return 0;
+}
+
+static int __devexit xilinx_spi_remove(struct platform_device *dev)
+{
+	xilinx_spi_deinit(platform_get_drvdata(dev));
+	platform_set_drvdata(dev, 0);
+
+	return 0;
+}
+
+/* work with hotplug and coldplug */
+MODULE_ALIAS("platform:" XILINX_SPI_NAME);
+
+static struct platform_driver xilinx_spi_driver = {
+	.probe = xilinx_spi_probe,
+	.remove = __devexit_p(xilinx_spi_remove),
+	.driver = {
+		.name = XILINX_SPI_NAME,
+		.owner = THIS_MODULE,
+#ifdef CONFIG_OF
+		.of_match_table = xilinx_spi_of_match,
+#endif
+	},
+};
+
+static int __init xilinx_spi_pltfm_init(void)
+{
+	return platform_driver_register(&xilinx_spi_driver);
+}
+module_init(xilinx_spi_pltfm_init);
+
+static void __exit xilinx_spi_pltfm_exit(void)
+{
+	platform_driver_unregister(&xilinx_spi_driver);
+}
+module_exit(xilinx_spi_pltfm_exit);
+
 MODULE_AUTHOR("MontaVista Software, Inc. <source@mvista.com>");
 MODULE_DESCRIPTION("Xilinx SPI driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/spi/xilinx_spi.h b/drivers/spi/xilinx_spi.h
deleted file mode 100644
index d211accf68d2..000000000000
--- a/drivers/spi/xilinx_spi.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/*
- * Xilinx SPI device driver API and platform data header file
- *
- * Copyright (c) 2009 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef _XILINX_SPI_H_
-#define _XILINX_SPI_H_
-
-#include <linux/spi/spi.h>
-#include <linux/spi/spi_bitbang.h>
-
-#define XILINX_SPI_NAME "xilinx_spi"
-
-struct spi_master *xilinx_spi_init(struct device *dev, struct resource *mem,
-	u32 irq, s16 bus_num);
-
-void xilinx_spi_deinit(struct spi_master *master);
-#endif
diff --git a/drivers/spi/xilinx_spi_of.c b/drivers/spi/xilinx_spi_of.c
deleted file mode 100644
index b66c2dbf20a5..000000000000
--- a/drivers/spi/xilinx_spi_of.c
+++ /dev/null
@@ -1,133 +0,0 @@
-/*
- * Xilinx SPI OF device driver
- *
- * Copyright (c) 2009 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/* Supports:
- * Xilinx SPI devices as OF devices
- *
- * Inspired by xilinx_spi.c, 2002-2007 (c) MontaVista Software, Inc.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-
-#include <linux/of_address.h>
-#include <linux/of_platform.h>
-#include <linux/of_device.h>
-#include <linux/of_spi.h>
-
-#include <linux/spi/xilinx_spi.h>
-#include "xilinx_spi.h"
-
-
-static int __devinit xilinx_spi_of_probe(struct platform_device *ofdev,
-	const struct of_device_id *match)
-{
-	struct spi_master *master;
-	struct xspi_platform_data *pdata;
-	struct resource r_mem;
-	struct resource r_irq;
-	int rc = 0;
-	const u32 *prop;
-	int len;
-
-	rc = of_address_to_resource(ofdev->dev.of_node, 0, &r_mem);
-	if (rc) {
-		dev_warn(&ofdev->dev, "invalid address\n");
-		return rc;
-	}
-
-	rc = of_irq_to_resource(ofdev->dev.of_node, 0, &r_irq);
-	if (rc == NO_IRQ) {
-		dev_warn(&ofdev->dev, "no IRQ found\n");
-		return -ENODEV;
-	}
-
-	ofdev->dev.platform_data =
-		kzalloc(sizeof(struct xspi_platform_data), GFP_KERNEL);
-	pdata = ofdev->dev.platform_data;
-	if (!pdata)
-		return -ENOMEM;
-
-	/* number of slave select bits is required */
-	prop = of_get_property(ofdev->dev.of_node, "xlnx,num-ss-bits", &len);
-	if (!prop || len < sizeof(*prop)) {
-		dev_warn(&ofdev->dev, "no 'xlnx,num-ss-bits' property\n");
-		return -EINVAL;
-	}
-	pdata->num_chipselect = *prop;
-	pdata->bits_per_word = 8;
-	master = xilinx_spi_init(&ofdev->dev, &r_mem, r_irq.start, -1);
-	if (!master)
-		return -ENODEV;
-
-	dev_set_drvdata(&ofdev->dev, master);
-
-	return 0;
-}
-
-static int __devexit xilinx_spi_remove(struct platform_device *ofdev)
-{
-	xilinx_spi_deinit(dev_get_drvdata(&ofdev->dev));
-	dev_set_drvdata(&ofdev->dev, 0);
-	kfree(ofdev->dev.platform_data);
-	ofdev->dev.platform_data = NULL;
-	return 0;
-}
-
-static int __exit xilinx_spi_of_remove(struct platform_device *op)
-{
-	return xilinx_spi_remove(op);
-}
-
-static const struct of_device_id xilinx_spi_of_match[] = {
-	{ .compatible = "xlnx,xps-spi-2.00.a", },
-	{ .compatible = "xlnx,xps-spi-2.00.b", },
-	{}
-};
-
-MODULE_DEVICE_TABLE(of, xilinx_spi_of_match);
-
-static struct of_platform_driver xilinx_spi_of_driver = {
-	.probe = xilinx_spi_of_probe,
-	.remove = __exit_p(xilinx_spi_of_remove),
-	.driver = {
-		.name = "xilinx-xps-spi",
-		.owner = THIS_MODULE,
-		.of_match_table = xilinx_spi_of_match,
-	},
-};
-
-static int __init xilinx_spi_of_init(void)
-{
-	return of_register_platform_driver(&xilinx_spi_of_driver);
-}
-module_init(xilinx_spi_of_init);
-
-static void __exit xilinx_spi_of_exit(void)
-{
-	of_unregister_platform_driver(&xilinx_spi_of_driver);
-}
-module_exit(xilinx_spi_of_exit);
-
-MODULE_AUTHOR("Mocean Laboratories <info@mocean-labs.com>");
-MODULE_DESCRIPTION("Xilinx SPI platform driver");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/xilinx_spi_pltfm.c b/drivers/spi/xilinx_spi_pltfm.c
deleted file mode 100644
index 24debac646a9..000000000000
--- a/drivers/spi/xilinx_spi_pltfm.c
+++ /dev/null
@@ -1,102 +0,0 @@
-/*
- * Support for Xilinx SPI platform devices
- * Copyright (c) 2009 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/* Supports:
- * Xilinx SPI devices as platform devices
- *
- * Inspired by xilinx_spi.c, 2002-2007 (c) MontaVista Software, Inc.
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/platform_device.h>
-
-#include <linux/spi/spi.h>
-#include <linux/spi/spi_bitbang.h>
-#include <linux/spi/xilinx_spi.h>
-
-#include "xilinx_spi.h"
-
-static int __devinit xilinx_spi_probe(struct platform_device *dev)
-{
-	struct xspi_platform_data *pdata;
-	struct resource *r;
-	int irq;
-	struct spi_master *master;
-	u8 i;
-
-	pdata = dev->dev.platform_data;
-	if (!pdata)
-		return -ENODEV;
-
-	r = platform_get_resource(dev, IORESOURCE_MEM, 0);
-	if (!r)
-		return -ENODEV;
-
-	irq = platform_get_irq(dev, 0);
-	if (irq < 0)
-		return -ENXIO;
-
-	master = xilinx_spi_init(&dev->dev, r, irq, dev->id);
-	if (!master)
-		return -ENODEV;
-
-	for (i = 0; i < pdata->num_devices; i++)
-		spi_new_device(master, pdata->devices + i);
-
-	platform_set_drvdata(dev, master);
-	return 0;
-}
-
-static int __devexit xilinx_spi_remove(struct platform_device *dev)
-{
-	xilinx_spi_deinit(platform_get_drvdata(dev));
-	platform_set_drvdata(dev, 0);
-
-	return 0;
-}
-
-/* work with hotplug and coldplug */
-MODULE_ALIAS("platform:" XILINX_SPI_NAME);
-
-static struct platform_driver xilinx_spi_driver = {
-	.probe	= xilinx_spi_probe,
-	.remove	= __devexit_p(xilinx_spi_remove),
-	.driver = {
-		.name = XILINX_SPI_NAME,
-		.owner = THIS_MODULE,
-	},
-};
-
-static int __init xilinx_spi_pltfm_init(void)
-{
-	return platform_driver_register(&xilinx_spi_driver);
-}
-module_init(xilinx_spi_pltfm_init);
-
-static void __exit xilinx_spi_pltfm_exit(void)
-{
-	platform_driver_unregister(&xilinx_spi_driver);
-}
-module_exit(xilinx_spi_pltfm_exit);
-
-MODULE_AUTHOR("Mocean Laboratories <info@mocean-labs.com>");
-MODULE_DESCRIPTION("Xilinx SPI platform driver");
-MODULE_LICENSE("GPL v2");