Merge remote-tracking branches 'spi/topic/fsl-dspi', 'spi/topic/imx',...

Merge remote-tracking branches 'spi/topic/fsl-dspi', 'spi/topic/imx', 'spi/topic/mxs', 'spi/topic/omap-100k' and 'spi/topic/orion' into spi-next

Documentation/devicetree/bindings/regmap/regmap.txt

+Device-Tree binding for regmap
+
+The endianness mode of CPU & Device scenarios:
+Index     Device     Endianness properties
+---------------------------------------------------
+1         BE         'big-endian'
+2         LE         'little-endian'
+
+For one device driver, which will run in different scenarios above
+on different SoCs using the devicetree, we need one way to simplify
+this.
+
+Required properties:
+- {big,little}-endian: these are boolean properties, if absent
+  meaning that the CPU and the Device are in the same endianness mode,
+  these properties are for register values and all the buffers only.
+
+Examples:
+Scenario 1 : CPU in LE mode & device in LE mode.
+dev: dev@40031000 {
+	      compatible = "name";
+	      reg = <0x40031000 0x1000>;
+	      ...
+};
+
+Scenario 2 : CPU in LE mode & device in BE mode.
+dev: dev@40031000 {
+	      compatible = "name";
+	      reg = <0x40031000 0x1000>;
+	      ...
+	      big-endian;
+};
+
+Scenario 3 : CPU in BE mode & device in BE mode.
+dev: dev@40031000 {
+	      compatible = "name";
+	      reg = <0x40031000 0x1000>;
+	      ...
+};
+
+Scenario 4 : CPU in BE mode & device in LE mode.
+dev: dev@40031000 {
+	      compatible = "name";
+	      reg = <0x40031000 0x1000>;
+	      ...
+	      little-endian;
+};

Documentation/devicetree/bindings/spi/fsl-imx-cspi.txt

@@ -7,6 +7,9 @@ Required properties:
 - interrupts : Should contain CSPI/eCSPI interrupt
 - fsl,spi-num-chipselects : Contains the number of the chipselect
 - cs-gpios : Specifies the gpio pins to be used for chipselects.
+- dmas: DMA specifiers for tx and rx dma. See the DMA client binding,
+		Documentation/devicetree/bindings/dma/dma.txt
+- dma-names: DMA request names should include "tx" and "rx" if present.
 
 Example:
 
@@ -19,4 +22,6 @@ ecspi@70010000 {
 	fsl,spi-num-chipselects = <2>;
 	cs-gpios = <&gpio3 24 0>, /* GPIO3_24 */
 		   <&gpio3 25 0>; /* GPIO3_25 */
+	dmas = <&sdma 3 7 1>, <&sdma 4 7 2>;
+	dma-names = "rx", "tx";
 };

Documentation/devicetree/bindings/spi/spi-fsl-dspi.txt

@@ -10,7 +10,12 @@ Required properties:
 - pinctrl-names: must contain a "default" entry.
 - spi-num-chipselects : the number of the chipselect signals.
 - bus-num : the slave chip chipselect signal number.
-- big-endian : if DSPI modudle is big endian, the bool will be set in node.
+
+Optional property:
+- big-endian: If present the dspi device's registers are implemented
+  in big endian mode, otherwise in native mode(same with CPU), for more
+  detail please see: Documentation/devicetree/bindings/regmap/regmap.txt.
+
 Example:
 
 dspi0@4002c000 {

Documentation/devicetree/bindings/spi/spi-orion.txt

 Marvell Orion SPI device
 
 Required properties:
-- compatible : should be "marvell,orion-spi".
+- compatible : should be "marvell,orion-spi" or "marvell,armada-370-spi".
 - reg : offset and length of the register set for the device
 - cell-index : Which of multiple SPI controllers is this.
 Optional properties:

drivers/base/regmap/regmap-i2c.c

@@ -168,6 +168,8 @@ static struct regmap_bus regmap_i2c = {
 	.write = regmap_i2c_write,
 	.gather_write = regmap_i2c_gather_write,
 	.read = regmap_i2c_read,
+	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
+	.val_format_endian_default = REGMAP_ENDIAN_BIG,
 };
 
 static const struct regmap_bus *regmap_get_i2c_bus(struct i2c_client *i2c,

drivers/base/regmap/regmap-spi.c

@@ -109,6 +109,8 @@ static struct regmap_bus regmap_spi = {
 	.async_alloc = regmap_spi_async_alloc,
 	.read = regmap_spi_read,
 	.read_flag_mask = 0x80,
+	.reg_format_endian_default = REGMAP_ENDIAN_BIG,
+	.val_format_endian_default = REGMAP_ENDIAN_BIG,
 };
 
 /**

drivers/base/regmap/regmap.c

@@ -15,6 +15,7 @@
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/err.h>
+#include <linux/of.h>
 #include <linux/rbtree.h>
 #include <linux/sched.h>
 
@@ -448,6 +449,66 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 }
 EXPORT_SYMBOL_GPL(regmap_attach_dev);
 
+static enum regmap_endian regmap_get_reg_endian(const struct regmap_bus *bus,
+					const struct regmap_config *config)
+{
+	enum regmap_endian endian;
+
+	/* Retrieve the endianness specification from the regmap config */
+	endian = config->reg_format_endian;
+
+	/* If the regmap config specified a non-default value, use that */
+	if (endian != REGMAP_ENDIAN_DEFAULT)
+		return endian;
+
+	/* Retrieve the endianness specification from the bus config */
+	if (bus && bus->reg_format_endian_default)
+		endian = bus->reg_format_endian_default;
+
+	/* If the bus specified a non-default value, use that */
+	if (endian != REGMAP_ENDIAN_DEFAULT)
+		return endian;
+
+	/* Use this if no other value was found */
+	return REGMAP_ENDIAN_BIG;
+}
+
+static enum regmap_endian regmap_get_val_endian(struct device *dev,
+					const struct regmap_bus *bus,
+					const struct regmap_config *config)
+{
+	struct device_node *np = dev->of_node;
+	enum regmap_endian endian;
+
+	/* Retrieve the endianness specification from the regmap config */
+	endian = config->val_format_endian;
+
+	/* If the regmap config specified a non-default value, use that */
+	if (endian != REGMAP_ENDIAN_DEFAULT)
+		return endian;
+
+	/* Parse the device's DT node for an endianness specification */
+	if (of_property_read_bool(np, "big-endian"))
+		endian = REGMAP_ENDIAN_BIG;
+	else if (of_property_read_bool(np, "little-endian"))
+		endian = REGMAP_ENDIAN_LITTLE;
+
+	/* If the endianness was specified in DT, use that */
+	if (endian != REGMAP_ENDIAN_DEFAULT)
+		return endian;
+
+	/* Retrieve the endianness specification from the bus config */
+	if (bus && bus->val_format_endian_default)
+		endian = bus->val_format_endian_default;
+
+	/* If the bus specified a non-default value, use that */
+	if (endian != REGMAP_ENDIAN_DEFAULT)
+		return endian;
+
+	/* Use this if no other value was found */
+	return REGMAP_ENDIAN_BIG;
+}
+
 /**
  * regmap_init(): Initialise register map
  *
@@ -551,17 +612,8 @@ struct regmap *regmap_init(struct device *dev,
 		map->reg_read  = _regmap_bus_read;
 	}
 
-	reg_endian = config->reg_format_endian;
-	if (reg_endian == REGMAP_ENDIAN_DEFAULT)
-		reg_endian = bus->reg_format_endian_default;
-	if (reg_endian == REGMAP_ENDIAN_DEFAULT)
-		reg_endian = REGMAP_ENDIAN_BIG;
-
-	val_endian = config->val_format_endian;
-	if (val_endian == REGMAP_ENDIAN_DEFAULT)
-		val_endian = bus->val_format_endian_default;
-	if (val_endian == REGMAP_ENDIAN_DEFAULT)
-		val_endian = REGMAP_ENDIAN_BIG;
+	reg_endian = regmap_get_reg_endian(bus, config);
+	val_endian = regmap_get_val_endian(dev, bus, config);
 
 	switch (config->reg_bits + map->reg_shift) {
 	case 2:

drivers/spi/spi-fsl-dspi.c

@@ -493,9 +493,6 @@ static int dspi_probe(struct platform_device *pdev)
 	}
 
 	dspi_regmap_config.lock_arg = dspi;
-	dspi_regmap_config.val_format_endian =
-		of_property_read_bool(np, "big-endian")
-			? REGMAP_ENDIAN_BIG : REGMAP_ENDIAN_DEFAULT;
 	dspi->regmap = devm_regmap_init_mmio_clk(&pdev->dev, "dspi", base,
 						&dspi_regmap_config);
 	if (IS_ERR(dspi->regmap)) {
@@ -535,7 +532,6 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_clk_put;
 	}
 
-	pr_info(KERN_INFO "Freescale DSPI master initialized\n");
 	return ret;
 
 out_clk_put:

drivers/spi/spi-imx.c

@@ -21,6 +21,8 @@
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
+#include <linux/dmaengine.h>
+#include <linux/dma-mapping.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
@@ -37,6 +39,7 @@
 #include <linux/of_device.h>
 #include <linux/of_gpio.h>
 
+#include <linux/platform_data/dma-imx.h>
 #include <linux/platform_data/spi-imx.h>
 
 #define DRIVER_NAME "spi_imx"
@@ -51,6 +54,9 @@
 #define MXC_INT_RR	(1 << 0) /* Receive data ready interrupt */
 #define MXC_INT_TE	(1 << 1) /* Transmit FIFO empty interrupt */
 
+/* The maximum  bytes that a sdma BD can transfer.*/
+#define MAX_SDMA_BD_BYTES  (1 << 15)
+#define IMX_DMA_TIMEOUT (msecs_to_jiffies(3000))
 struct spi_imx_config {
 	unsigned int speed_hz;
 	unsigned int bpw;
@@ -95,6 +101,16 @@ struct spi_imx_data {
 	const void *tx_buf;
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
 
+	/* DMA */
+	unsigned int dma_is_inited;
+	unsigned int dma_finished;
+	bool usedma;
+	u32 rx_wml;
+	u32 tx_wml;
+	u32 rxt_wml;
+	struct completion dma_rx_completion;
+	struct completion dma_tx_completion;
+
 	const struct spi_imx_devtype_data *devtype_data;
 	int chipselect[0];
 };
@@ -181,9 +197,21 @@ static unsigned int spi_imx_clkdiv_2(unsigned int fin,
 	return 7;
 }
 
+static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
+			 struct spi_transfer *transfer)
+{
+	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
+
+	if (spi_imx->dma_is_inited && (transfer->len > spi_imx->rx_wml)
+	    && (transfer->len > spi_imx->tx_wml))
+		return true;
+	return false;
+}
+
 #define MX51_ECSPI_CTRL		0x08
 #define MX51_ECSPI_CTRL_ENABLE		(1 <<  0)
 #define MX51_ECSPI_CTRL_XCH		(1 <<  2)
+#define MX51_ECSPI_CTRL_SMC		(1 << 3)
 #define MX51_ECSPI_CTRL_MODE_MASK	(0xf << 4)
 #define MX51_ECSPI_CTRL_POSTDIV_OFFSET	8
 #define MX51_ECSPI_CTRL_PREDIV_OFFSET	12
@@ -201,6 +229,18 @@ static unsigned int spi_imx_clkdiv_2(unsigned int fin,
 #define MX51_ECSPI_INT_TEEN		(1 <<  0)
 #define MX51_ECSPI_INT_RREN		(1 <<  3)
 
+#define MX51_ECSPI_DMA      0x14
+#define MX51_ECSPI_DMA_TX_WML_OFFSET	0
+#define MX51_ECSPI_DMA_TX_WML_MASK	0x3F
+#define MX51_ECSPI_DMA_RX_WML_OFFSET	16
+#define MX51_ECSPI_DMA_RX_WML_MASK	(0x3F << 16)
+#define MX51_ECSPI_DMA_RXT_WML_OFFSET	24
+#define MX51_ECSPI_DMA_RXT_WML_MASK	(0x3F << 24)
+
+#define MX51_ECSPI_DMA_TEDEN_OFFSET	7
+#define MX51_ECSPI_DMA_RXDEN_OFFSET	23
+#define MX51_ECSPI_DMA_RXTDEN_OFFSET	31
+
 #define MX51_ECSPI_STAT		0x18
 #define MX51_ECSPI_STAT_RR		(1 <<  3)
 
@@ -257,17 +297,22 @@ static void __maybe_unused mx51_ecspi_intctrl(struct spi_imx_data *spi_imx, int
 
 static void __maybe_unused mx51_ecspi_trigger(struct spi_imx_data *spi_imx)
 {
-	u32 reg;
+	u32 reg = readl(spi_imx->base + MX51_ECSPI_CTRL);
 
-	reg = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	if (!spi_imx->usedma)
 		reg |= MX51_ECSPI_CTRL_XCH;
+	else if (!spi_imx->dma_finished)
+		reg |= MX51_ECSPI_CTRL_SMC;
+	else
+		reg &= ~MX51_ECSPI_CTRL_SMC;
 	writel(reg, spi_imx->base + MX51_ECSPI_CTRL);
 }
 
 static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 		struct spi_imx_config *config)
 {
-	u32 ctrl = MX51_ECSPI_CTRL_ENABLE, cfg = 0;
+	u32 ctrl = MX51_ECSPI_CTRL_ENABLE, cfg = 0, dma = 0;
+	u32 tx_wml_cfg, rx_wml_cfg, rxt_wml_cfg;
 	u32 clk = config->speed_hz, delay;
 
 	/*
@@ -319,6 +364,30 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 	else			/* SCLK is _very_ slow */
 		usleep_range(delay, delay + 10);
 
+	/*
+	 * Configure the DMA register: setup the watermark
+	 * and enable DMA request.
+	 */
+	if (spi_imx->dma_is_inited) {
+		dma = readl(spi_imx->base + MX51_ECSPI_DMA);
+
+		spi_imx->tx_wml = spi_imx_get_fifosize(spi_imx) / 2;
+		spi_imx->rx_wml = spi_imx_get_fifosize(spi_imx) / 2;
+		spi_imx->rxt_wml = spi_imx_get_fifosize(spi_imx) / 2;
+		rx_wml_cfg = spi_imx->rx_wml << MX51_ECSPI_DMA_RX_WML_OFFSET;
+		tx_wml_cfg = spi_imx->tx_wml << MX51_ECSPI_DMA_TX_WML_OFFSET;
+		rxt_wml_cfg = spi_imx->rxt_wml << MX51_ECSPI_DMA_RXT_WML_OFFSET;
+		dma = (dma & ~MX51_ECSPI_DMA_TX_WML_MASK
+			   & ~MX51_ECSPI_DMA_RX_WML_MASK
+			   & ~MX51_ECSPI_DMA_RXT_WML_MASK)
+			   | rx_wml_cfg | tx_wml_cfg | rxt_wml_cfg
+			   |(1 << MX51_ECSPI_DMA_TEDEN_OFFSET)
+			   |(1 << MX51_ECSPI_DMA_RXDEN_OFFSET)
+			   |(1 << MX51_ECSPI_DMA_RXTDEN_OFFSET);
+
+		writel(dma, spi_imx->base + MX51_ECSPI_DMA);
+	}
+
 	return 0;
 }
 
@@ -730,7 +799,186 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	return 0;
 }
 
-static int spi_imx_transfer(struct spi_device *spi,
+static void spi_imx_sdma_exit(struct spi_imx_data *spi_imx)
+{
+	struct spi_master *master = spi_imx->bitbang.master;
+
+	if (master->dma_rx) {
+		dma_release_channel(master->dma_rx);
+		master->dma_rx = NULL;
+	}
+
+	if (master->dma_tx) {
+		dma_release_channel(master->dma_tx);
+		master->dma_tx = NULL;
+	}
+
+	spi_imx->dma_is_inited = 0;
+}
+
+static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
+			     struct spi_master *master,
+			     const struct resource *res)
+{
+	struct dma_slave_config slave_config = {};
+	int ret;
+
+	/* Prepare for TX DMA: */
+	master->dma_tx = dma_request_slave_channel(dev, "tx");
+	if (!master->dma_tx) {
+		dev_err(dev, "cannot get the TX DMA channel!\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	slave_config.direction = DMA_MEM_TO_DEV;
+	slave_config.dst_addr = res->start + MXC_CSPITXDATA;
+	slave_config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	slave_config.dst_maxburst = spi_imx_get_fifosize(spi_imx) / 2;
+	ret = dmaengine_slave_config(master->dma_tx, &slave_config);
+	if (ret) {
+		dev_err(dev, "error in TX dma configuration.\n");
+		goto err;
+	}
+
+	/* Prepare for RX : */
+	master->dma_rx = dma_request_slave_channel(dev, "rx");
+	if (!master->dma_rx) {
+		dev_dbg(dev, "cannot get the DMA channel.\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	slave_config.direction = DMA_DEV_TO_MEM;
+	slave_config.src_addr = res->start + MXC_CSPIRXDATA;
+	slave_config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
+	slave_config.src_maxburst = spi_imx_get_fifosize(spi_imx) / 2;
+	ret = dmaengine_slave_config(master->dma_rx, &slave_config);
+	if (ret) {
+		dev_err(dev, "error in RX dma configuration.\n");
+		goto err;
+	}
+
+	init_completion(&spi_imx->dma_rx_completion);
+	init_completion(&spi_imx->dma_tx_completion);
+	master->can_dma = spi_imx_can_dma;
+	master->max_dma_len = MAX_SDMA_BD_BYTES;
+	spi_imx->bitbang.master->flags = SPI_MASTER_MUST_RX |
+					 SPI_MASTER_MUST_TX;
+	spi_imx->dma_is_inited = 1;
+
+	return 0;
+err:
+	spi_imx_sdma_exit(spi_imx);
+	return ret;
+}
+
+static void spi_imx_dma_rx_callback(void *cookie)
+{
+	struct spi_imx_data *spi_imx = (struct spi_imx_data *)cookie;
+
+	complete(&spi_imx->dma_rx_completion);
+}
+
+static void spi_imx_dma_tx_callback(void *cookie)
+{
+	struct spi_imx_data *spi_imx = (struct spi_imx_data *)cookie;
+
+	complete(&spi_imx->dma_tx_completion);
+}
+
+static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
+				struct spi_transfer *transfer)
+{
+	struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL;
+	int ret;
+	u32 dma;
+	int left;
+	struct spi_master *master = spi_imx->bitbang.master;
+	struct sg_table *tx = &transfer->tx_sg, *rx = &transfer->rx_sg;
+
+	if (tx) {
+		desc_tx = dmaengine_prep_slave_sg(master->dma_tx,
+					tx->sgl, tx->nents, DMA_TO_DEVICE,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!desc_tx)
+			goto no_dma;
+
+		desc_tx->callback = spi_imx_dma_tx_callback;
+		desc_tx->callback_param = (void *)spi_imx;
+		dmaengine_submit(desc_tx);
+	}
+
+	if (rx) {
+		desc_rx = dmaengine_prep_slave_sg(master->dma_rx,
+					rx->sgl, rx->nents, DMA_FROM_DEVICE,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!desc_rx)
+			goto no_dma;
+
+		desc_rx->callback = spi_imx_dma_rx_callback;
+		desc_rx->callback_param = (void *)spi_imx;
+		dmaengine_submit(desc_rx);
+	}
+
+	reinit_completion(&spi_imx->dma_rx_completion);
+	reinit_completion(&spi_imx->dma_tx_completion);
+
+	/* Trigger the cspi module. */
+	spi_imx->dma_finished = 0;
+
+	dma = readl(spi_imx->base + MX51_ECSPI_DMA);
+	dma = dma & (~MX51_ECSPI_DMA_RXT_WML_MASK);
+	/* Change RX_DMA_LENGTH trigger dma fetch tail data */
+	left = transfer->len % spi_imx->rxt_wml;
+	if (left)
+		writel(dma | (left << MX51_ECSPI_DMA_RXT_WML_OFFSET),
+				spi_imx->base + MX51_ECSPI_DMA);
+	spi_imx->devtype_data->trigger(spi_imx);
+
+	dma_async_issue_pending(master->dma_tx);
+	dma_async_issue_pending(master->dma_rx);
+	/* Wait SDMA to finish the data transfer.*/
+	ret = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
+						IMX_DMA_TIMEOUT);
+	if (!ret) {
+		pr_warn("%s %s: I/O Error in DMA TX\n",
+			dev_driver_string(&master->dev),
+			dev_name(&master->dev));
+		dmaengine_terminate_all(master->dma_tx);
+	} else {
+		ret = wait_for_completion_timeout(&spi_imx->dma_rx_completion,
+				IMX_DMA_TIMEOUT);
+		if (!ret) {
+			pr_warn("%s %s: I/O Error in DMA RX\n",
+				dev_driver_string(&master->dev),
+				dev_name(&master->dev));
+			spi_imx->devtype_data->reset(spi_imx);
+			dmaengine_terminate_all(master->dma_rx);
+		}
+		writel(dma |
+		       spi_imx->rxt_wml << MX51_ECSPI_DMA_RXT_WML_OFFSET,
+		       spi_imx->base + MX51_ECSPI_DMA);
+	}
+
+	spi_imx->dma_finished = 1;
+	spi_imx->devtype_data->trigger(spi_imx);
+
+	if (!ret)
+		ret = -ETIMEDOUT;
+	else if (ret > 0)
+		ret = transfer->len;
+
+	return ret;
+
+no_dma:
+	pr_warn_once("%s %s: DMA not available, falling back to PIO\n",
+		     dev_driver_string(&master->dev),
+		     dev_name(&master->dev));
+	return -EAGAIN;
+}
+
+static int spi_imx_pio_transfer(struct spi_device *spi,
 				struct spi_transfer *transfer)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
@@ -751,6 +999,24 @@ static int spi_imx_transfer(struct spi_device *spi,
 	return transfer->len;
 }
 
+static int spi_imx_transfer(struct spi_device *spi,
+				struct spi_transfer *transfer)
+{
+	int ret;
+	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
+
+	if (spi_imx->bitbang.master->can_dma &&
+	    spi_imx_can_dma(spi_imx->bitbang.master, spi, transfer)) {
+		spi_imx->usedma = true;
+		ret = spi_imx_dma_transfer(spi_imx, transfer);
+		if (ret != -EAGAIN)
+			return ret;
+	}
+	spi_imx->usedma = false;
+
+	return spi_imx_pio_transfer(spi, transfer);
+}
+
 static int spi_imx_setup(struct spi_device *spi)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
@@ -911,6 +1177,13 @@ static int spi_imx_probe(struct platform_device *pdev)
 		goto out_put_per;
 
 	spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per);
+	/*
+	 * Only validated on i.mx6 now, can remove the constrain if validated on
+	 * other chips.
+	 */
+	if (spi_imx->devtype_data == &imx51_ecspi_devtype_data
+	    && spi_imx_sdma_init(&pdev->dev, spi_imx, master, res))
+		dev_err(&pdev->dev, "dma setup error,use pio instead\n");
 
 	spi_imx->devtype_data->reset(spi_imx);
 
@@ -949,6 +1222,7 @@ static int spi_imx_remove(struct platform_device *pdev)
 	writel(0, spi_imx->base + MXC_CSPICTRL);
 	clk_unprepare(spi_imx->clk_ipg);
 	clk_unprepare(spi_imx->clk_per);
+	spi_imx_sdma_exit(spi_imx);
 	spi_master_put(master);
 
 	return 0;

drivers/spi/spi-mxs.c

@@ -85,7 +85,7 @@ static int mxs_spi_setup_transfer(struct spi_device *dev,
 		mxs_ssp_set_clk_rate(ssp, hz);
 		/*
 		 * Save requested rate, hz, rather than the actual rate,
-		 * ssp->clk_rate.  Otherwise we would set the rate every trasfer
+		 * ssp->clk_rate.  Otherwise we would set the rate every transfer
 		 * when the actual rate is not quite the same as requested rate.
 		 */
 		spi->sck = hz;

drivers/spi/spi-omap-100k.c

@@ -70,10 +70,6 @@
 #define SPI_STATUS_WE                   (1UL << 1)
 #define SPI_STATUS_RD                   (1UL << 0)
 
-#define WRITE 0
-#define READ  1
-
-
 /* use PIO for small transfers, avoiding DMA setup/teardown overhead and
  * cache operations; better heuristics consider wordsize and bitrate.
  */

drivers/spi/spi-orion.c

@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
 #include <asm/unaligned.h>
@@ -40,13 +41,27 @@
 #define ORION_SPI_MODE_CPHA		(1 << 12)
 #define ORION_SPI_IF_8_16_BIT_MODE	(1 << 5)
 #define ORION_SPI_CLK_PRESCALE_MASK	0x1F
+#define ARMADA_SPI_CLK_PRESCALE_MASK	0xDF
 #define ORION_SPI_MODE_MASK		(ORION_SPI_MODE_CPOL | \
 					 ORION_SPI_MODE_CPHA)
 
+enum orion_spi_type {
+	ORION_SPI,
+	ARMADA_SPI,
+};
+
+struct orion_spi_dev {
+	enum orion_spi_type	typ;
+	unsigned int		min_divisor;
+	unsigned int		max_divisor;
+	u32			prescale_mask;
+};
+
 struct orion_spi {
 	struct spi_master	*master;
 	void __iomem		*base;
 	struct clk              *clk;
+	const struct orion_spi_dev *devdata;
 };
 
 static inline void __iomem *spi_reg(struct orion_spi *orion_spi, u32 reg)
@@ -83,11 +98,46 @@ static int orion_spi_baudrate_set(struct spi_device *spi, unsigned int speed)
 	u32 prescale;
 	u32 reg;
 	struct orion_spi *orion_spi;
+	const struct orion_spi_dev *devdata;
 
 	orion_spi = spi_master_get_devdata(spi->master);
+	devdata = orion_spi->devdata;
 
 	tclk_hz = clk_get_rate(orion_spi->clk);
 
+	if (devdata->typ == ARMADA_SPI) {
+		unsigned int clk, spr, sppr, sppr2, err;
+		unsigned int best_spr, best_sppr, best_err;
+
+		best_err = speed;
+		best_spr = 0;
+		best_sppr = 0;
+
+		/* Iterate over the valid range looking for best fit */
+		for (sppr = 0; sppr < 8; sppr++) {
+			sppr2 = 0x1 << sppr;
+
+			spr = tclk_hz / sppr2;
+			spr = DIV_ROUND_UP(spr, speed);
+			if ((spr == 0) || (spr > 15))
+				continue;
+
+			clk = tclk_hz / (spr * sppr2);
+			err = speed - clk;
+
+			if (err < best_err) {
+				best_spr = spr;
+				best_sppr = sppr;
+				best_err = err;
+			}
+		}
+
+		if ((best_sppr == 0) && (best_spr == 0))
+			return -EINVAL;
+
+		prescale = ((best_sppr & 0x6) << 5) |
+			((best_sppr & 0x1) << 4) | best_spr;
+	} else {
 		/*
 		 * the supported rates are: 4,6,8...30
 		 * round up as we look for equal or less speed
@@ -104,9 +154,10 @@ static int orion_spi_baudrate_set(struct spi_device *spi, unsigned int speed)
 
 		/* Convert the rate to SPI clock divisor value.	*/
 		prescale = 0x10 + rate/2;
+	}
 
 	reg = readl(spi_reg(orion_spi, ORION_SPI_IF_CONFIG_REG));
-	reg = ((reg & ~ORION_SPI_CLK_PRESCALE_MASK) | prescale);
+	reg = ((reg & ~devdata->prescale_mask) | prescale);
 	writel(reg, spi_reg(orion_spi, ORION_SPI_IF_CONFIG_REG));
 
 	return 0;
@@ -342,8 +393,31 @@ static int orion_spi_reset(struct orion_spi *orion_spi)
 	return 0;
 }
 
+static const struct orion_spi_dev orion_spi_dev_data = {
+	.typ = ORION_SPI,
+	.min_divisor = 4,
+	.max_divisor = 30,
+	.prescale_mask = ORION_SPI_CLK_PRESCALE_MASK,
+};
+
+static const struct orion_spi_dev armada_spi_dev_data = {
+	.typ = ARMADA_SPI,
+	.min_divisor = 1,
+	.max_divisor = 1920,
+	.prescale_mask = ARMADA_SPI_CLK_PRESCALE_MASK,
+};
+
+static const struct of_device_id orion_spi_of_match_table[] = {
+	{ .compatible = "marvell,orion-spi", .data = &orion_spi_dev_data, },
+	{ .compatible = "marvell,armada-370-spi", .data = &armada_spi_dev_data, },
+	{}
+};
+MODULE_DEVICE_TABLE(of, orion_spi_of_match_table);
+
 static int orion_spi_probe(struct platform_device *pdev)
 {
+	const struct of_device_id *of_id;
+	const struct orion_spi_dev *devdata;
 	struct spi_master *master;
 	struct orion_spi *spi;
 	struct resource *r;
@@ -379,6 +453,10 @@ static int orion_spi_probe(struct platform_device *pdev)
 	spi = spi_master_get_devdata(master);
 	spi->master = master;
 
+	of_id = of_match_device(orion_spi_of_match_table, &pdev->dev);
+	devdata = of_id->data;
+	spi->devdata = devdata;
+
 	spi->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(spi->clk)) {
 		status = PTR_ERR(spi->clk);
@@ -390,8 +468,8 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out;
 
 	tclk_hz = clk_get_rate(spi->clk);
-	master->max_speed_hz = DIV_ROUND_UP(tclk_hz, 4);
-	master->min_speed_hz = DIV_ROUND_UP(tclk_hz, 30);
+	master->max_speed_hz = DIV_ROUND_UP(tclk_hz, devdata->min_divisor);
+	master->min_speed_hz = DIV_ROUND_UP(tclk_hz, devdata->max_divisor);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	spi->base = devm_ioremap_resource(&pdev->dev, r);
@@ -470,12 +548,6 @@ static const struct dev_pm_ops orion_spi_pm_ops = {
 			   NULL)
 };
 
-static const struct of_device_id orion_spi_of_match_table[] = {
-	{ .compatible = "marvell,orion-spi", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, orion_spi_of_match_table);
-
 static struct platform_driver orion_spi_driver = {
 	.driver = {
 		.name	= DRIVER_NAME,