Merge tag 'spi-v3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi

Pull spi updates from Mark Brown:
 "A quiet release, more bug fixes than anything else.  A few things do
  stand out though:

   - updates to several drivers to move towards the standard GPIO chip
     select handling in the core.
   - DMA support for the SH MSIOF driver.
   - support for Rockchip SPI controllers (their first mainline
     submission)"

* tag 'spi-v3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi: (64 commits)
  spi: davinci: use spi_device.cs_gpio to store gpio cs per spi device
  spi: davinci: add support to configure gpio cs through dt
  spi/pl022: Explicitly truncate large bitmask
  spi/atmel: Fix pointer to int conversion warnings on 64 bit builds
  spi: davinci: fix to support more than 2 chip selects
  spi: topcliff-pch: don't hardcode PCI slot to get DMA device
  spi: orion: fix incorrect handling of cell-index DT property
  spi: orion: Fix error return code in orion_spi_probe()
  spi/rockchip: fix error return code in rockchip_spi_probe()
  spi/rockchip: remove redundant dev_err call in rockchip_spi_probe()
  spi/rockchip: remove duplicated include from spi-rockchip.c
  ARM: dts: fix the chip select gpios definition in the SPI nodes
  spi: s3c64xx: Update binding documentation
  spi: s3c64xx: use the generic SPI "cs-gpios" property
  spi: s3c64xx: Revert "spi: s3c64xx: Added provision for dedicated cs pin"
  spi: atmel: Use dmaengine_prep_slave_sg() API
  spi: topcliff-pch: Update error messages for dmaengine_prep_slave_sg() API
  spi: sh-msiof: Use correct device for DMA mapping with IOMMU
  spi: sh-msiof: Handle dmaengine_prep_slave_single() failures gracefully
  spi: rspi: Handle dmaengine_prep_slave_sg() failures gracefully
  ...

Documentation/devicetree/bindings/spi/efm32-spi.txt

@@ -10,11 +10,12 @@ Required properties:
 - cs-gpios: see spi-bus.txt
 
 Recommended properties :
-- efm32,location: Value to write to the ROUTE register's LOCATION bitfield to
+- energymicro,location: Value to write to the ROUTE register's LOCATION
-                  configure the pinmux for the device, see datasheet for values.
+                        bitfield to configure the pinmux for the device, see
-                  If "efm32,location" property is not provided, keeping what is
+                        datasheet for values.
-                  already configured in the hardware, so its either the reset
+                        If this property is not provided, keeping what is
-                  default 0 or whatever the bootloader did.
+                        already configured in the hardware, so its either the
+                        reset default 0 or whatever the bootloader did.
 
 Example:
 
@@ -26,7 +27,7 @@ spi1: spi@0x4000c400 { /* USART1 */
 	interrupts = <15 16>;
 	clocks = <&cmu 20>;
 	cs-gpios = <&gpio 51 1>; // D3
-	efm32,location = <1>;
+	energymicro,location = <1>;
 	status = "ok";
 
 	ks8851@0 {

Documentation/devicetree/bindings/spi/qcom,spi-qup.txt

@@ -7,7 +7,11 @@ SPI in master mode supports up to 50MHz, up to four chip selects, programmable
 data path from 4 bits to 32 bits and numerous protocol variants.
 
 Required properties:
-- compatible:     Should contain "qcom,spi-qup-v2.1.1" or "qcom,spi-qup-v2.2.1"
+- compatible:     Should contain:
+		  "qcom,spi-qup-v1.1.1" for 8660, 8960 and 8064.
+		  "qcom,spi-qup-v2.1.1" for 8974 and later
+		  "qcom,spi-qup-v2.2.1" for 8974 v2 and later.
+
 - reg:            Should contain base register location and length
 - interrupts:     Interrupt number used by this controller
 

Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt

@@ -0,0 +1,28 @@
+Synopsys DesignWare AMBA 2.0 Synchronous Serial Interface.
+
+Required properties:
+- compatible : "snps,dw-apb-ssi"
+- reg : The register base for the controller.
+- interrupts : One interrupt, used by the controller.
+- #address-cells : <1>, as required by generic SPI binding.
+- #size-cells : <0>, also as required by generic SPI binding.
+
+Optional properties:
+- cs-gpios : Specifies the gpio pis to be used for chipselects.
+- num-cs : The number of chipselects. If omitted, this will default to 4.
+
+Child nodes as per the generic SPI binding.
+
+Example:
+
+	spi@fff00000 {
+		compatible = "snps,dw-apb-ssi";
+		reg = <0xfff00000 0x1000>;
+		interrupts = <0 154 4>;
+		#address-cells = <1>;
+		#size-cells = <0>;
+		num-cs = <2>;
+		cs-gpios = <&gpio0 13 0>,
+			   <&gpio0 14 0>;
+	};
+

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

@@ -8,7 +8,8 @@ Required properties:
 	- "ti,dm6441-spi" for SPI used similar to that on DM644x SoC family
 	- "ti,da830-spi" for SPI used similar to that on DA8xx SoC family
 - reg: Offset and length of SPI controller register space
-- num-cs: Number of chip selects
+- num-cs: Number of chip selects. This includes internal as well as
+	GPIO chip selects.
 - ti,davinci-spi-intr-line: interrupt line used to connect the SPI
 	IP to the interrupt controller within the SoC. Possible values
 	are 0 and 1. Manual says one of the two possible interrupt
@@ -17,6 +18,12 @@ Required properties:
 - interrupts: interrupt number mapped to CPU.
 - clocks: spi clk phandle
 
+Optional:
+- cs-gpios: gpio chip selects
+	For example to have 3 internal CS and 2 GPIO CS, user could define
+	cs-gpios = <0>, <0>, <0>, <&gpio1 30 0>, <&gpio1 31 0>;
+	where first three are internal CS and last two are GPIO CS.
+
 Example of a NOR flash slave device (n25q032) connected to DaVinci
 SPI controller device over the SPI bus.
 

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

@@ -0,0 +1,37 @@
+* Rockchip SPI Controller
+
+The Rockchip SPI controller is used to interface with various devices such as flash
+and display controllers using the SPI communication interface.
+
+Required Properties:
+
+- compatible: should be one of the following.
+    "rockchip,rk3066-spi" for rk3066.
+    "rockchip,rk3188-spi", "rockchip,rk3066-spi" for rk3188.
+    "rockchip,rk3288-spi", "rockchip,rk3066-spi" for rk3288.
+- reg: physical base address of the controller and length of memory mapped
+       region.
+- interrupts: The interrupt number to the cpu. The interrupt specifier format
+              depends on the interrupt controller.
+- clocks: Must contain an entry for each entry in clock-names.
+- clock-names: Shall be "spiclk" for the transfer-clock, and "apb_pclk" for
+			   the peripheral clock.
+- 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.
+- #address-cells: should be 1.
+- #size-cells: should be 0.
+
+Example:
+
+	spi0: spi@ff110000 {
+		compatible = "rockchip,rk3066-spi";
+		reg = <0xff110000 0x1000>;
+		dmas = <&pdma1 11>, <&pdma1 12>;
+		dma-names = "tx", "rx";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru SCLK_SPI0>, <&cru PCLK_SPI0>;
+		clock-names = "spiclk", "apb_pclk";
+	};

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

@@ -18,14 +18,11 @@ Required SoC Specific Properties:
 - interrupts: The interrupt number to the cpu. The interrupt specifier format
   depends on the interrupt controller.
 
-[PRELIMINARY: the dma channel allocation will change once there are
+- dmas : Two or more DMA channel specifiers following the convention outlined
-official DMA bindings]
+  in bindings/dma/dma.txt
 
-- tx-dma-channel: The dma channel specifier for tx operations. The format of
+- dma-names: Names for the dma channels. There must be at least one channel
-  the dma specifier depends on the dma controller.
+  named "tx" for transmit and named "rx" for receive.
-
-- rx-dma-channel: The dma channel specifier for rx operations. The format of
-  the dma specifier depends on the dma controller.
 
 Required Board Specific Properties:
 
@@ -42,15 +39,13 @@ Optional Board Specific Properties:
 - num-cs: Specifies the number of chip select lines supported. If
   not specified, the default number of chip select lines is set to 1.
 
+- cs-gpios: should specify GPIOs used for chipselects (see spi-bus.txt)
+
 SPI Controller specific data in SPI slave nodes:
 
 - The spi slave nodes should provide the following information which is required
   by the spi controller.
 
-  - cs-gpio: A gpio specifier that specifies the gpio line used as
-    the slave select line by the spi controller. The format of the gpio
-    specifier depends on the gpio controller.
-
   - samsung,spi-feedback-delay: The sampling phase shift to be applied on the
     miso line (to account for any lag in the miso line). The following are the
     valid values.
@@ -74,8 +69,11 @@ Example:
 		compatible = "samsung,exynos4210-spi";
 		reg = <0x12d20000 0x100>;
 		interrupts = <0 66 0>;
-		tx-dma-channel = <&pdma0 5>;
+		dmas = <&pdma0 5
-		rx-dma-channel = <&pdma0 4>;
+			&pdma0 4>;
+		dma-names = "tx", "rx";
+		#address-cells = <1>;
+		#size-cells = <0>;
 	};
 
 - Board Specific Portion:
@@ -85,6 +83,7 @@ Example:
 		#size-cells = <0>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi0_bus>;
+		cs-gpios = <&gpa2 5 0>;
 
 		w25q80bw@0 {
 			#address-cells = <1>;
@@ -94,7 +93,6 @@ Example:
 			spi-max-frequency = <10000>;
 
 			controller-data {
-				cs-gpio = <&gpa2 5 1 0 3>;
 				samsung,spi-feedback-delay = <0>;
 			};
 

arch/arm/boot/dts/exynos4210-smdkv310.dts

@@ -168,6 +168,7 @@
 	};
 
 	spi_2: spi@13940000 {
+		cs-gpios = <&gpc1 2 0>;
 		status = "okay";
 
 		w25x80@0 {
@@ -178,7 +179,6 @@
 			spi-max-frequency = <1000000>;
 
 			controller-data {
-				cs-gpio = <&gpc1 2 0>;
 				samsung,spi-feedback-delay = <0>;
 			};
 

arch/arm/boot/dts/exynos4412-trats2.dts

@@ -589,6 +589,7 @@
 	spi_1: spi@13930000 {
 		pinctrl-names = "default";
 		pinctrl-0 = <&spi1_bus>;
+		cs-gpios = <&gpb 5 0>;
 		status = "okay";
 
 		s5c73m3_spi: s5c73m3 {
@@ -596,7 +597,6 @@
 			spi-max-frequency = <50000000>;
 			reg = <0>;
 			controller-data {
-				cs-gpio = <&gpb 5 0>;
 				samsung,spi-feedback-delay = <2>;
 			};
 		};

arch/arm/boot/dts/exynos5250-smdk5250.dts

@@ -316,6 +316,7 @@
 	};
 
 	spi_1: spi@12d30000 {
+		cs-gpios = <&gpa2 5 0>;
 		status = "okay";
 
 		w25q80bw@0 {
@@ -326,7 +327,6 @@
 			spi-max-frequency = <1000000>;
 
 			controller-data {
-				cs-gpio = <&gpa2 5 0>;
 				samsung,spi-feedback-delay = <0>;
 			};
 

drivers/spi/Kconfig

@@ -382,9 +382,21 @@ config SPI_PXA2XX
 config SPI_PXA2XX_PCI
 	def_tristate SPI_PXA2XX && PCI
 
+config SPI_ROCKCHIP
+	tristate "Rockchip SPI controller driver"
+	depends on ARM || ARM64 || AVR32 || HEXAGON || MIPS || SUPERH
+	help
+	  This selects a driver for Rockchip SPI controller.
+
+	  If you say yes to this option, support will be included for
+	  RK3066, RK3188 and RK3288 families of SPI controller.
+	  Rockchip SPI controller support DMA transport and PIO mode.
+	  The main usecase of this controller is to use spi flash as boot
+	  device.
+
 config SPI_RSPI
 	tristate "Renesas RSPI/QSPI controller"
-	depends on (SUPERH && SH_DMAE_BASE) || ARCH_SHMOBILE
+	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
 	help
 	  SPI driver for Renesas RSPI and QSPI blocks.
 
@@ -434,7 +446,7 @@ config SPI_SC18IS602
 
 config SPI_SH_MSIOF
 	tristate "SuperH MSIOF SPI controller"
-	depends on HAVE_CLK
+	depends on HAVE_CLK && HAS_DMA
 	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
 	help
 	  SPI driver for SuperH and SH Mobile MSIOF blocks.

drivers/spi/Makefile

@@ -61,6 +61,7 @@ spi-pxa2xx-platform-$(CONFIG_SPI_PXA2XX_DMA)	+= spi-pxa2xx-dma.o
 obj-$(CONFIG_SPI_PXA2XX)		+= spi-pxa2xx-platform.o
 obj-$(CONFIG_SPI_PXA2XX_PCI)		+= spi-pxa2xx-pci.o
 obj-$(CONFIG_SPI_QUP)			+= spi-qup.o
+obj-$(CONFIG_SPI_ROCKCHIP)		+= spi-rockchip.o
 obj-$(CONFIG_SPI_RSPI)			+= spi-rspi.o
 obj-$(CONFIG_SPI_S3C24XX)		+= spi-s3c24xx-hw.o
 spi-s3c24xx-hw-y			:= spi-s3c24xx.o

drivers/spi/spi-adi-v3.c

@@ -660,10 +660,9 @@ static int adi_spi_setup(struct spi_device *spi)
 		struct adi_spi3_chip *chip_info = spi->controller_data;
 
 		chip = kzalloc(sizeof(*chip), GFP_KERNEL);
-		if (!chip) {
+		if (!chip)
-			dev_err(&spi->dev, "can not allocate chip data\n");
 			return -ENOMEM;
-		}
+
 		if (chip_info) {
 			if (chip_info->control & ~ctl_reg) {
 				dev_err(&spi->dev,

drivers/spi/spi-atmel.c

@@ -597,21 +597,15 @@ static int atmel_spi_next_xfer_dma_submit(struct spi_master *master,
 		goto err_exit;
 
 	/* Send both scatterlists */
-	rxdesc = rxchan->device->device_prep_slave_sg(rxchan,
+	rxdesc = dmaengine_prep_slave_sg(rxchan, &as->dma.sgrx, 1,
-					&as->dma.sgrx,
-					1,
 					 DMA_FROM_DEVICE,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK,
+					 DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-					NULL);
 	if (!rxdesc)
 		goto err_dma;
 
-	txdesc = txchan->device->device_prep_slave_sg(txchan,
+	txdesc = dmaengine_prep_slave_sg(txchan, &as->dma.sgtx, 1,
-					&as->dma.sgtx,
-					1,
 					 DMA_TO_DEVICE,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK,
+					 DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-					NULL);
 	if (!txdesc)
 		goto err_dma;
 
@@ -1018,7 +1012,7 @@ static int atmel_spi_setup(struct spi_device *spi)
 	csr |= SPI_BF(DLYBCT, 0);
 
 	/* chipselect must have been muxed as GPIO (e.g. in board setup) */
-	npcs_pin = (unsigned int)spi->controller_data;
+	npcs_pin = (unsigned long)spi->controller_data;
 
 	if (gpio_is_valid(spi->cs_gpio))
 		npcs_pin = spi->cs_gpio;
@@ -1253,7 +1247,7 @@ msg_done:
 static void atmel_spi_cleanup(struct spi_device *spi)
 {
 	struct atmel_spi_device	*asd = spi->controller_state;
-	unsigned		gpio = (unsigned) spi->controller_data;
+	unsigned		gpio = (unsigned long) spi->controller_data;
 
 	if (!asd)
 		return;

drivers/spi/spi-au1550.c

@@ -925,8 +925,7 @@ err_no_txdma:
 	iounmap((void __iomem *)hw->regs);
 
 err_ioremap:
-	release_resource(hw->ioarea);
+	release_mem_region(r->start, sizeof(psc_spi_t));
-	kfree(hw->ioarea);
 
 err_no_iores:
 err_no_pdata:
@@ -946,8 +945,7 @@ static int au1550_spi_remove(struct platform_device *pdev)
 	spi_bitbang_stop(&hw->bitbang);
 	free_irq(hw->irq, hw);
 	iounmap((void __iomem *)hw->regs);
-	release_resource(hw->ioarea);
+	release_mem_region(r->start, sizeof(psc_spi_t));
-	kfree(hw->ioarea);
 
 	if (hw->usedma) {
 		au1550_spi_dma_rxtmp_free(hw);

drivers/spi/spi-cadence.c

@@ -205,18 +205,30 @@ static void cdns_spi_chipselect(struct spi_device *spi, bool is_high)
 static void cdns_spi_config_clock_mode(struct spi_device *spi)
 {
 	struct cdns_spi *xspi = spi_master_get_devdata(spi->master);
-	u32 ctrl_reg;
+	u32 ctrl_reg, new_ctrl_reg;
 
-	ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR_OFFSET);
+	new_ctrl_reg = ctrl_reg = cdns_spi_read(xspi, CDNS_SPI_CR_OFFSET);
 
 	/* Set the SPI clock phase and clock polarity */
-	ctrl_reg &= ~(CDNS_SPI_CR_CPHA_MASK | CDNS_SPI_CR_CPOL_MASK);
+	new_ctrl_reg &= ~(CDNS_SPI_CR_CPHA_MASK | CDNS_SPI_CR_CPOL_MASK);
 	if (spi->mode & SPI_CPHA)
-		ctrl_reg |= CDNS_SPI_CR_CPHA_MASK;
+		new_ctrl_reg |= CDNS_SPI_CR_CPHA_MASK;
 	if (spi->mode & SPI_CPOL)
-		ctrl_reg |= CDNS_SPI_CR_CPOL_MASK;
+		new_ctrl_reg |= CDNS_SPI_CR_CPOL_MASK;
 
-	cdns_spi_write(xspi, CDNS_SPI_CR_OFFSET, ctrl_reg);
+	if (new_ctrl_reg != ctrl_reg) {
+		/*
+		 * Just writing the CR register does not seem to apply the clock
+		 * setting changes. This is problematic when changing the clock
+		 * polarity as it will cause the SPI slave to see spurious clock
+		 * transitions. To workaround the issue toggle the ER register.
+		 */
+		cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
+				   CDNS_SPI_ER_DISABLE_MASK);
+		cdns_spi_write(xspi, CDNS_SPI_CR_OFFSET, new_ctrl_reg);
+		cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
+				   CDNS_SPI_ER_ENABLE_MASK);
+	}
 }
 
 /**
@@ -370,6 +382,12 @@ static irqreturn_t cdns_spi_irq(int irq, void *dev_id)
 
 	return status;
 }
+static int cdns_prepare_message(struct spi_master *master,
+				struct spi_message *msg)
+{
+	cdns_spi_config_clock_mode(msg->spi);
+	return 0;
+}
 
 /**
  * cdns_transfer_one - Initiates the SPI transfer
@@ -416,8 +434,6 @@ static int cdns_prepare_transfer_hardware(struct spi_master *master)
 {
 	struct cdns_spi *xspi = spi_master_get_devdata(master);
 
-	cdns_spi_config_clock_mode(master->cur_msg->spi);
-
 	cdns_spi_write(xspi, CDNS_SPI_ER_OFFSET,
 		       CDNS_SPI_ER_ENABLE_MASK);
 
@@ -532,6 +548,7 @@ static int cdns_spi_probe(struct platform_device *pdev)
 		xspi->is_decoded_cs = 0;
 
 	master->prepare_transfer_hardware = cdns_prepare_transfer_hardware;
+	master->prepare_message = cdns_prepare_message;
 	master->transfer_one = cdns_transfer_one;
 	master->unprepare_transfer_hardware = cdns_unprepare_transfer_hardware;
 	master->set_cs = cdns_spi_chipselect;
@@ -647,7 +664,7 @@ static int __maybe_unused cdns_spi_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(cdns_spi_dev_pm_ops, cdns_spi_suspend,
 			 cdns_spi_resume);
 
-static struct of_device_id cdns_spi_of_match[] = {
+static const struct of_device_id cdns_spi_of_match[] = {
 	{ .compatible = "xlnx,zynq-spi-r1p6" },
 	{ .compatible = "cdns,spi-r1p6" },
 	{ /* end of table */ }

drivers/spi/spi-clps711x.c

@@ -184,8 +184,6 @@ static int spi_clps711x_probe(struct platform_device *pdev)
 	}
 	master->max_speed_hz = clk_get_rate(hw->spi_clk);
 
-	platform_set_drvdata(pdev, master);
-
 	hw->syscon = syscon_regmap_lookup_by_pdevname("syscon.3");
 	if (IS_ERR(hw->syscon)) {
 		ret = PTR_ERR(hw->syscon);

drivers/spi/spi-davinci.c

@@ -30,6 +30,7 @@
 #include <linux/edma.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/slab.h>
@@ -38,8 +39,6 @@
 
 #define SPI_NO_RESOURCE		((resource_size_t)-1)
 
-#define SPI_MAX_CHIPSELECT	2
-
 #define CS_DEFAULT	0xFF
 
 #define SPIFMT_PHASE_MASK	BIT(16)
@@ -142,7 +141,7 @@ struct davinci_spi {
 	void			(*get_rx)(u32 rx_data, struct davinci_spi *);
 	u32			(*get_tx)(struct davinci_spi *);
 
-	u8			bytes_per_word[SPI_MAX_CHIPSELECT];
+	u8			*bytes_per_word;
 };
 
 static struct davinci_spi_config davinci_spi_default_cfg;
@@ -213,13 +212,16 @@ static void davinci_spi_chipselect(struct spi_device *spi, int value)
 	u8 chip_sel = spi->chip_select;
 	u16 spidat1 = CS_DEFAULT;
 	bool gpio_chipsel = false;
+	int gpio;
 
 	dspi = spi_master_get_devdata(spi->master);
 	pdata = &dspi->pdata;
 
-	if (pdata->chip_sel && chip_sel < pdata->num_chipselect &&
+	if (spi->cs_gpio >= 0) {
-				pdata->chip_sel[chip_sel] != SPI_INTERN_CS)
+		/* SPI core parse and update master->cs_gpio */
 		gpio_chipsel = true;
+		gpio = spi->cs_gpio;
+	}
 
 	/*
 	 * Board specific chip select logic decides the polarity and cs
@@ -227,9 +229,9 @@ static void davinci_spi_chipselect(struct spi_device *spi, int value)
 	 */
 	if (gpio_chipsel) {
 		if (value == BITBANG_CS_ACTIVE)
-			gpio_set_value(pdata->chip_sel[chip_sel], 0);
+			gpio_set_value(gpio, spi->mode & SPI_CS_HIGH);
 		else
-			gpio_set_value(pdata->chip_sel[chip_sel], 1);
+			gpio_set_value(gpio, !(spi->mode & SPI_CS_HIGH));
 	} else {
 		if (value == BITBANG_CS_ACTIVE) {
 			spidat1 |= SPIDAT1_CSHOLD_MASK;
@@ -392,16 +394,39 @@ static int davinci_spi_setup(struct spi_device *spi)
 	int retval = 0;
 	struct davinci_spi *dspi;
 	struct davinci_spi_platform_data *pdata;
+	struct spi_master *master = spi->master;
+	struct device_node *np = spi->dev.of_node;
+	bool internal_cs = true;
+	unsigned long flags = GPIOF_DIR_OUT;
 
 	dspi = spi_master_get_devdata(spi->master);
 	pdata = &dspi->pdata;
 
-	if (!(spi->mode & SPI_NO_CS)) {
+	flags |= (spi->mode & SPI_CS_HIGH) ? GPIOF_INIT_LOW : GPIOF_INIT_HIGH;
-		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_NO_CS)) {
+		if (np && (master->cs_gpios != NULL) && (spi->cs_gpio >= 0)) {
+			retval = gpio_request_one(spi->cs_gpio,
+						  flags, dev_name(&spi->dev));
+			internal_cs = false;
+		} else if (pdata->chip_sel &&
+			   spi->chip_select < pdata->num_chipselect &&
+			   pdata->chip_sel[spi->chip_select] != SPI_INTERN_CS) {
+			spi->cs_gpio = pdata->chip_sel[spi->chip_select];
+			retval = gpio_request_one(spi->cs_gpio,
+						  flags, dev_name(&spi->dev));
+			internal_cs = false;
 		}
+	}
+
+	if (retval) {
+		dev_err(&spi->dev, "GPIO %d setup failed (%d)\n",
+			spi->cs_gpio, retval);
+		return retval;
+	}
+
+	if (internal_cs)
+		set_io_bits(dspi->base + SPIPC0, 1 << spi->chip_select);
 
 	if (spi->mode & SPI_READY)
 		set_io_bits(dspi->base + SPIPC0, SPIPC0_SPIENA_MASK);
@@ -414,6 +439,12 @@ static int davinci_spi_setup(struct spi_device *spi)
 	return retval;
 }
 
+static void davinci_spi_cleanup(struct spi_device *spi)
+{
+	if (spi->cs_gpio >= 0)
+		gpio_free(spi->cs_gpio);
+}
+
 static int davinci_spi_check_error(struct davinci_spi *dspi, int int_status)
 {
 	struct device *sdev = dspi->bitbang.master->dev.parent;
@@ -812,6 +843,8 @@ static int spi_davinci_get_pdata(struct platform_device *pdev,
 
 	/*
 	 * default num_cs is 1 and all chipsel are internal to the chip
+	 * indicated by chip_sel being NULL or cs_gpios being NULL or
+	 * set to -ENOENT. num-cs includes internal as well as gpios.
 	 * indicated by chip_sel being NULL. GPIO based CS is not
 	 * supported yet in DT bindings.
 	 */
@@ -850,7 +883,7 @@ static int davinci_spi_probe(struct platform_device *pdev)
 	struct resource *r;
 	resource_size_t dma_rx_chan = SPI_NO_RESOURCE;
 	resource_size_t	dma_tx_chan = SPI_NO_RESOURCE;
-	int i = 0, ret = 0;
+	int ret = 0;
 	u32 spipc0;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct davinci_spi));
@@ -876,6 +909,14 @@ static int davinci_spi_probe(struct platform_device *pdev)
 	/* pdata in dspi is now updated and point pdata to that */
 	pdata = &dspi->pdata;
 
+	dspi->bytes_per_word = devm_kzalloc(&pdev->dev,
+					    sizeof(*dspi->bytes_per_word) *
+					    pdata->num_chipselect, GFP_KERNEL);
+	if (dspi->bytes_per_word == NULL) {
+		ret = -ENOMEM;
+		goto free_master;
+	}
+
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (r == NULL) {
 		ret = -ENOENT;
@@ -915,6 +956,7 @@ static int davinci_spi_probe(struct platform_device *pdev)
 	master->num_chipselect = pdata->num_chipselect;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(2, 16);
 	master->setup = davinci_spi_setup;
+	master->cleanup = davinci_spi_cleanup;
 
 	dspi->bitbang.chipselect = davinci_spi_chipselect;
 	dspi->bitbang.setup_transfer = davinci_spi_setup_transfer;
@@ -962,14 +1004,6 @@ static int davinci_spi_probe(struct platform_device *pdev)
 	spipc0 = SPIPC0_DIFUN_MASK | SPIPC0_DOFUN_MASK | SPIPC0_CLKFUN_MASK;
 	iowrite32(spipc0, dspi->base + SPIPC0);
 
-	/* 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 (pdata->intr_line)
 		iowrite32(SPI_INTLVL_1, dspi->base + SPILVL);
 	else

drivers/spi/spi-dw-mmio.c

@@ -16,7 +16,9 @@
 #include <linux/spi/spi.h>
 #include <linux/scatterlist.h>
 #include <linux/module.h>
+#include <linux/of.h>
 #include <linux/of_gpio.h>
+#include <linux/of_platform.h>
 
 #include "spi-dw.h"
 
@@ -33,6 +35,7 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 	struct dw_spi *dws;
 	struct resource *mem;
 	int ret;
+	int num_cs;
 
 	dwsmmio = devm_kzalloc(&pdev->dev, sizeof(struct dw_spi_mmio),
 			GFP_KERNEL);
@@ -68,9 +71,16 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 		return ret;
 
 	dws->bus_num = pdev->id;
-	dws->num_cs = 4;
+
 	dws->max_freq = clk_get_rate(dwsmmio->clk);
 
+	num_cs = 4;
+
+	if (pdev->dev.of_node)
+		of_property_read_u32(pdev->dev.of_node, "num-cs", &num_cs);
+
+	dws->num_cs = num_cs;
+
 	if (pdev->dev.of_node) {
 		int i;
 
@@ -114,12 +124,19 @@ static int dw_spi_mmio_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id dw_spi_mmio_of_match[] = {
+	{ .compatible = "snps,dw-apb-ssi", },
+	{ /* end of table */}
+};
+MODULE_DEVICE_TABLE(of, dw_spi_mmio_of_match);
+
 static struct platform_driver dw_spi_mmio_driver = {
 	.probe		= dw_spi_mmio_probe,
 	.remove		= dw_spi_mmio_remove,
 	.driver		= {
 		.name	= DRIVER_NAME,
 		.owner	= THIS_MODULE,
+		.of_match_table = dw_spi_mmio_of_match,
 	},
 };
 module_platform_driver(dw_spi_mmio_driver);

drivers/spi/spi-efm32.c

@@ -294,10 +294,16 @@ static void efm32_spi_probe_dt(struct platform_device *pdev,
 	u32 location;
 	int ret;
 
+	ret = of_property_read_u32(np, "energymicro,location", &location);
+
+	if (ret)
+		/* fall back to wrongly namespaced property */
 		ret = of_property_read_u32(np, "efm32,location", &location);
+
 	if (ret)
 		/* fall back to old and (wrongly) generic property "location" */
 		ret = of_property_read_u32(np, "location", &location);
+
 	if (!ret) {
 		dev_dbg(&pdev->dev, "using location %u\n", location);
 	} else {

drivers/spi/spi-falcon.c

@@ -425,8 +425,6 @@ static int falcon_sflash_probe(struct platform_device *pdev)
 	master->unprepare_transfer_hardware = falcon_sflash_unprepare_xfer;
 	master->dev.of_node = pdev->dev.of_node;
 
-	platform_set_drvdata(pdev, priv);
-
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret)
 		spi_master_put(master);

drivers/spi/spi-fsl-lib.c

@@ -196,7 +196,7 @@ int of_mpc8xxx_spi_probe(struct platform_device *ofdev)
 
 	pinfo = devm_kzalloc(&ofdev->dev, sizeof(*pinfo), GFP_KERNEL);
 	if (!pinfo)
-		return -ENOMEM;
+		return ret;
 
 	pdata = &pinfo->pdata;
 	dev->platform_data = pdata;

drivers/spi/spi-fsl-spi.c

@@ -58,7 +58,7 @@ static struct fsl_spi_match_data of_fsl_spi_grlib_config = {
 	.type = TYPE_GRLIB,
 };
 
-static struct of_device_id of_fsl_spi_match[] = {
+static const struct of_device_id of_fsl_spi_match[] = {
 	{
 		.compatible = "fsl,spi",
 		.data = &of_fsl_spi_fsl_config,

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

@@ -420,8 +420,6 @@ static int omap1_spi100k_probe(struct platform_device *pdev)
 	master->min_speed_hz = OMAP1_SPI100K_MAX_FREQ/(1<<16);
 	master->max_speed_hz = OMAP1_SPI100K_MAX_FREQ;
 
-	platform_set_drvdata(pdev, master);
-
 	spi100k = spi_master_get_devdata(master);
 
 	/*

drivers/spi/spi-omap-uwire.c

@@ -41,14 +41,15 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/slab.h>
+#include <linux/device.h>
 
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/module.h>
+#include <linux/io.h>
 
 #include <asm/irq.h>
 #include <mach/hardware.h>
-#include <asm/io.h>
 #include <asm/mach-types.h>
 
 #include <mach/mux.h>
@@ -447,7 +448,6 @@ static void uwire_off(struct uwire_spi *uwire)
 {
 	uwire_write_reg(UWIRE_SR3, 0);
 	clk_disable(uwire->ck);
-	clk_put(uwire->ck);
 	spi_master_put(uwire->bitbang.master);
 }
 
@@ -463,7 +463,7 @@ static int uwire_probe(struct platform_device *pdev)
 
 	uwire = spi_master_get_devdata(master);
 
-	uwire_base = ioremap(UWIRE_BASE_PHYS, UWIRE_IO_SIZE);
+	uwire_base = devm_ioremap(&pdev->dev, UWIRE_BASE_PHYS, UWIRE_IO_SIZE);
 	if (!uwire_base) {
 		dev_dbg(&pdev->dev, "can't ioremap UWIRE\n");
 		spi_master_put(master);
@@ -472,12 +472,11 @@ static int uwire_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, uwire);
 
-	uwire->ck = clk_get(&pdev->dev, "fck");
+	uwire->ck = devm_clk_get(&pdev->dev, "fck");
 	if (IS_ERR(uwire->ck)) {
 		status = PTR_ERR(uwire->ck);
 		dev_dbg(&pdev->dev, "no functional clock?\n");
 		spi_master_put(master);
-		iounmap(uwire_base);
 		return status;
 	}
 	clk_enable(uwire->ck);
@@ -507,7 +506,6 @@ static int uwire_probe(struct platform_device *pdev)
 	status = spi_bitbang_start(&uwire->bitbang);
 	if (status < 0) {
 		uwire_off(uwire);
-		iounmap(uwire_base);
 	}
 	return status;
 }
@@ -520,7 +518,6 @@ static int uwire_remove(struct platform_device *pdev)
 
 	spi_bitbang_stop(&uwire->bitbang);
 	uwire_off(uwire);
-	iounmap(uwire_base);
 	return 0;
 }
 

drivers/spi/spi-omap2-mcspi.c

@@ -149,6 +149,7 @@ struct omap2_mcspi_cs {
 	void __iomem		*base;
 	unsigned long		phys;
 	int			word_len;
+	u16			mode;
 	struct list_head	node;
 	/* Context save and restore shadow register */
 	u32			chconf0, chctrl0;
@@ -926,6 +927,8 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 
 	mcspi_write_chconf0(spi, l);
 
+	cs->mode = spi->mode;
+
 	dev_dbg(&spi->dev, "setup: speed %d, sample %s edge, clk %s\n",
 			speed_hz,
 			(spi->mode & SPI_CPHA) ? "trailing" : "leading",
@@ -998,6 +1001,7 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 			return -ENOMEM;
 		cs->base = mcspi->base + spi->chip_select * 0x14;
 		cs->phys = mcspi->phys + spi->chip_select * 0x14;
+		cs->mode = 0;
 		cs->chconf0 = 0;
 		cs->chctrl0 = 0;
 		spi->controller_state = cs;
@@ -1079,6 +1083,16 @@ static void omap2_mcspi_work(struct omap2_mcspi *mcspi, struct spi_message *m)
 	cs = spi->controller_state;
 	cd = spi->controller_data;
 
+	/*
+	 * The slave driver could have changed spi->mode in which case
+	 * it will be different from cs->mode (the current hardware setup).
+	 * If so, set par_override (even though its not a parity issue) so
+	 * omap2_mcspi_setup_transfer will be called to configure the hardware
+	 * with the correct mode on the first iteration of the loop below.
+	 */
+	if (spi->mode != cs->mode)
+		par_override = 1;
+
 	omap2_mcspi_set_enable(spi, 0);
 	list_for_each_entry(t, &m->transfers, transfer_list) {
 		if (t->tx_buf == NULL && t->rx_buf == NULL && t->len) {

drivers/spi/spi-orion.c

@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/spi/spi.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 #include <linux/of.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
@@ -23,6 +24,9 @@
 
 #define DRIVER_NAME			"orion_spi"
 
+/* Runtime PM autosuspend timeout: PM is fairly light on this driver */
+#define SPI_AUTOSUSPEND_TIMEOUT		200
+
 #define ORION_NUM_CHIPSELECTS		1 /* only one slave is supported*/
 #define ORION_SPI_WAIT_RDY_MAX_LOOP	2000 /* in usec */
 
@@ -277,7 +281,6 @@ out:
 	return xfer->len - count;
 }
 
-
 static int orion_spi_transfer_one_message(struct spi_master *master,
 					   struct spi_message *m)
 {
@@ -346,8 +349,6 @@ static int orion_spi_probe(struct platform_device *pdev)
 	struct resource *r;
 	unsigned long tclk_hz;
 	int status = 0;
-	const u32 *iprop;
-	int size;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*spi));
 	if (master == NULL) {
@@ -358,10 +359,10 @@ static int orion_spi_probe(struct platform_device *pdev)
 	if (pdev->id != -1)
 		master->bus_num = pdev->id;
 	if (pdev->dev.of_node) {
-		iprop = of_get_property(pdev->dev.of_node, "cell-index",
+		u32 cell_index;
-					&size);
+		if (!of_property_read_u32(pdev->dev.of_node, "cell-index",
-		if (iprop && size == sizeof(*iprop))
+					  &cell_index))
-			master->bus_num = *iprop;
+			master->bus_num = cell_index;
 	}
 
 	/* we support only mode 0, and no options */
@@ -370,6 +371,7 @@ static int orion_spi_probe(struct platform_device *pdev)
 	master->transfer_one_message = orion_spi_transfer_one_message;
 	master->num_chipselect = ORION_NUM_CHIPSELECTS;
 	master->bits_per_word_mask = SPI_BPW_MASK(8) | SPI_BPW_MASK(16);
+	master->auto_runtime_pm = true;
 
 	platform_set_drvdata(pdev, master);
 
@@ -382,8 +384,10 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out;
 	}
 
-	clk_prepare(spi->clk);
+	status = clk_prepare_enable(spi->clk);
-	clk_enable(spi->clk);
+	if (status)
+		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);
@@ -395,16 +399,27 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out_rel_clk;
 	}
 
-	if (orion_spi_reset(spi) < 0)
+	pm_runtime_set_active(&pdev->dev);
-		goto out_rel_clk;
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, SPI_AUTOSUSPEND_TIMEOUT);
+	pm_runtime_enable(&pdev->dev);
+
+	status = orion_spi_reset(spi);
+	if (status < 0)
+		goto out_rel_pm;
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
 
 	master->dev.of_node = pdev->dev.of_node;
-	status = devm_spi_register_master(&pdev->dev, master);
+	status = spi_register_master(master);
 	if (status < 0)
-		goto out_rel_clk;
+		goto out_rel_pm;
 
 	return status;
 
+out_rel_pm:
+	pm_runtime_disable(&pdev->dev);
 out_rel_clk:
 	clk_disable_unprepare(spi->clk);
 out:
@@ -415,19 +430,45 @@ out:
 
 static int orion_spi_remove(struct platform_device *pdev)
 {
-	struct spi_master *master;
+	struct spi_master *master = platform_get_drvdata(pdev);
-	struct orion_spi *spi;
+	struct orion_spi *spi = spi_master_get_devdata(master);
-
-	master = platform_get_drvdata(pdev);
-	spi = spi_master_get_devdata(master);
 
+	pm_runtime_get_sync(&pdev->dev);
 	clk_disable_unprepare(spi->clk);
 
+	spi_unregister_master(master);
+	pm_runtime_disable(&pdev->dev);
+
 	return 0;
 }
 
 MODULE_ALIAS("platform:" DRIVER_NAME);
 
+#ifdef CONFIG_PM_RUNTIME
+static int orion_spi_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct orion_spi *spi = spi_master_get_devdata(master);
+
+	clk_disable_unprepare(spi->clk);
+	return 0;
+}
+
+static int orion_spi_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct orion_spi *spi = spi_master_get_devdata(master);
+
+	return clk_prepare_enable(spi->clk);
+}
+#endif
+
+static const struct dev_pm_ops orion_spi_pm_ops = {
+	SET_RUNTIME_PM_OPS(orion_spi_runtime_suspend,
+			   orion_spi_runtime_resume,
+			   NULL)
+};
+
 static const struct of_device_id orion_spi_of_match_table[] = {
 	{ .compatible = "marvell,orion-spi", },
 	{}
@@ -438,6 +479,7 @@ static struct platform_driver orion_spi_driver = {
 	.driver = {
 		.name	= DRIVER_NAME,
 		.owner	= THIS_MODULE,
+		.pm	= &orion_spi_pm_ops,
 		.of_match_table = of_match_ptr(orion_spi_of_match_table),
 	},
 	.probe		= orion_spi_probe,

drivers/spi/spi-pl022.c

@@ -1417,7 +1417,7 @@ static void do_interrupt_dma_transfer(struct pl022 *pl022)
 	 * Default is to enable all interrupts except RX -
 	 * this will be enabled once TX is complete
 	 */
-	u32 irqflags = ENABLE_ALL_INTERRUPTS & ~SSP_IMSC_MASK_RXIM;
+	u32 irqflags = (u32)(ENABLE_ALL_INTERRUPTS & ~SSP_IMSC_MASK_RXIM);
 
 	/* Enable target chip, if not already active */
 	if (!pl022->next_msg_cs_active)

drivers/spi/spi-qup.c

@@ -142,6 +142,7 @@ struct spi_qup {
 	int			w_size;	/* bytes per SPI word */
 	int			tx_bytes;
 	int			rx_bytes;
+	int			qup_v1;
 };
 
 
@@ -420,6 +421,8 @@ static int spi_qup_io_config(struct spi_device *spi, struct spi_transfer *xfer)
 	config |= QUP_CONFIG_SPI_MODE;
 	writel_relaxed(config, controller->base + QUP_CONFIG);
 
+	/* only write to OPERATIONAL_MASK when register is present */
+	if (!controller->qup_v1)
 		writel_relaxed(0, controller->base + QUP_OPERATIONAL_MASK);
 	return 0;
 }
@@ -486,7 +489,7 @@ static int spi_qup_probe(struct platform_device *pdev)
 	struct resource *res;
 	struct device *dev;
 	void __iomem *base;
-	u32 data, max_freq, iomode;
+	u32 max_freq, iomode;
 	int ret, irq, size;
 
 	dev = &pdev->dev;
@@ -529,15 +532,6 @@ static int spi_qup_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	data = readl_relaxed(base + QUP_HW_VERSION);
-
-	if (data < QUP_HW_VERSION_2_1_1) {
-		clk_disable_unprepare(cclk);
-		clk_disable_unprepare(iclk);
-		dev_err(dev, "v.%08x is not supported\n", data);
-		return -ENXIO;
-	}
-
 	master = spi_alloc_master(dev, sizeof(struct spi_qup));
 	if (!master) {
 		clk_disable_unprepare(cclk);
@@ -570,6 +564,10 @@ static int spi_qup_probe(struct platform_device *pdev)
 	controller->cclk = cclk;
 	controller->irq = irq;
 
+	/* set v1 flag if device is version 1 */
+	if (of_device_is_compatible(dev->of_node, "qcom,spi-qup-v1.1.1"))
+		controller->qup_v1 = 1;
+
 	spin_lock_init(&controller->lock);
 	init_completion(&controller->done);
 
@@ -593,8 +591,8 @@ static int spi_qup_probe(struct platform_device *pdev)
 	size = QUP_IO_M_INPUT_FIFO_SIZE(iomode);
 	controller->in_fifo_sz = controller->in_blk_sz * (2 << size);
 
-	dev_info(dev, "v.%08x IN:block:%d, fifo:%d, OUT:block:%d, fifo:%d\n",
+	dev_info(dev, "IN:block:%d, fifo:%d, OUT:block:%d, fifo:%d\n",
-		 data, controller->in_blk_sz, controller->in_fifo_sz,
+		 controller->in_blk_sz, controller->in_fifo_sz,
 		 controller->out_blk_sz, controller->out_fifo_sz);
 
 	writel_relaxed(1, base + QUP_SW_RESET);
@@ -607,10 +605,19 @@ static int spi_qup_probe(struct platform_device *pdev)
 
 	writel_relaxed(0, base + QUP_OPERATIONAL);
 	writel_relaxed(0, base + QUP_IO_M_MODES);
+
+	if (!controller->qup_v1)
 		writel_relaxed(0, base + QUP_OPERATIONAL_MASK);
+
 	writel_relaxed(SPI_ERROR_CLK_UNDER_RUN | SPI_ERROR_CLK_OVER_RUN,
 		       base + SPI_ERROR_FLAGS_EN);
 
+	/* if earlier version of the QUP, disable INPUT_OVERRUN */
+	if (controller->qup_v1)
+		writel_relaxed(QUP_ERROR_OUTPUT_OVER_RUN |
+			QUP_ERROR_INPUT_UNDER_RUN | QUP_ERROR_OUTPUT_UNDER_RUN,
+			base + QUP_ERROR_FLAGS_EN);
+
 	writel_relaxed(0, base + SPI_CONFIG);
 	writel_relaxed(SPI_IO_C_NO_TRI_STATE, base + SPI_IO_CONTROL);
 
@@ -732,6 +739,7 @@ static int spi_qup_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id spi_qup_dt_match[] = {
+	{ .compatible = "qcom,spi-qup-v1.1.1", },
 	{ .compatible = "qcom,spi-qup-v2.1.1", },
 	{ .compatible = "qcom,spi-qup-v2.2.1", },
 	{ }

drivers/spi/spi-rockchip.c

@@ -0,0 +1,837 @@
+/*
+ * Copyright (c) 2014, Fuzhou Rockchip Electronics Co., Ltd
+ * Author: Addy Ke <addy.ke@rock-chips.com>
+ *
+ * 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.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/scatterlist.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/io.h>
+#include <linux/dmaengine.h>
+
+#define DRIVER_NAME "rockchip-spi"
+
+/* SPI register offsets */
+#define ROCKCHIP_SPI_CTRLR0			0x0000
+#define ROCKCHIP_SPI_CTRLR1			0x0004
+#define ROCKCHIP_SPI_SSIENR			0x0008
+#define ROCKCHIP_SPI_SER			0x000c
+#define ROCKCHIP_SPI_BAUDR			0x0010
+#define ROCKCHIP_SPI_TXFTLR			0x0014
+#define ROCKCHIP_SPI_RXFTLR			0x0018
+#define ROCKCHIP_SPI_TXFLR			0x001c
+#define ROCKCHIP_SPI_RXFLR			0x0020
+#define ROCKCHIP_SPI_SR				0x0024
+#define ROCKCHIP_SPI_IPR			0x0028
+#define ROCKCHIP_SPI_IMR			0x002c
+#define ROCKCHIP_SPI_ISR			0x0030
+#define ROCKCHIP_SPI_RISR			0x0034
+#define ROCKCHIP_SPI_ICR			0x0038
+#define ROCKCHIP_SPI_DMACR			0x003c
+#define ROCKCHIP_SPI_DMATDLR		0x0040
+#define ROCKCHIP_SPI_DMARDLR		0x0044
+#define ROCKCHIP_SPI_TXDR			0x0400
+#define ROCKCHIP_SPI_RXDR			0x0800
+
+/* Bit fields in CTRLR0 */
+#define CR0_DFS_OFFSET				0
+
+#define CR0_CFS_OFFSET				2
+
+#define CR0_SCPH_OFFSET				6
+
+#define CR0_SCPOL_OFFSET			7
+
+#define CR0_CSM_OFFSET				8
+#define CR0_CSM_KEEP				0x0
+/* ss_n be high for half sclk_out cycles */
+#define CR0_CSM_HALF				0X1
+/* ss_n be high for one sclk_out cycle */
+#define CR0_CSM_ONE					0x2
+
+/* ss_n to sclk_out delay */
+#define CR0_SSD_OFFSET				10
+/*
+ * The period between ss_n active and
+ * sclk_out active is half sclk_out cycles
+ */
+#define CR0_SSD_HALF				0x0
+/*
+ * The period between ss_n active and
+ * sclk_out active is one sclk_out cycle
+ */
+#define CR0_SSD_ONE					0x1
+
+#define CR0_EM_OFFSET				11
+#define CR0_EM_LITTLE				0x0
+#define CR0_EM_BIG					0x1
+
+#define CR0_FBM_OFFSET				12
+#define CR0_FBM_MSB					0x0
+#define CR0_FBM_LSB					0x1
+
+#define CR0_BHT_OFFSET				13
+#define CR0_BHT_16BIT				0x0
+#define CR0_BHT_8BIT				0x1
+
+#define CR0_RSD_OFFSET				14
+
+#define CR0_FRF_OFFSET				16
+#define CR0_FRF_SPI					0x0
+#define CR0_FRF_SSP					0x1
+#define CR0_FRF_MICROWIRE			0x2
+
+#define CR0_XFM_OFFSET				18
+#define CR0_XFM_MASK				(0x03 << SPI_XFM_OFFSET)
+#define CR0_XFM_TR					0x0
+#define CR0_XFM_TO					0x1
+#define CR0_XFM_RO					0x2
+
+#define CR0_OPM_OFFSET				20
+#define CR0_OPM_MASTER				0x0
+#define CR0_OPM_SLAVE				0x1
+
+#define CR0_MTM_OFFSET				0x21
+
+/* Bit fields in SER, 2bit */
+#define SER_MASK					0x3
+
+/* Bit fields in SR, 5bit */
+#define SR_MASK						0x1f
+#define SR_BUSY						(1 << 0)
+#define SR_TF_FULL					(1 << 1)
+#define SR_TF_EMPTY					(1 << 2)
+#define SR_RF_EMPTY					(1 << 3)
+#define SR_RF_FULL					(1 << 4)
+
+/* Bit fields in ISR, IMR, ISR, RISR, 5bit */
+#define INT_MASK					0x1f
+#define INT_TF_EMPTY				(1 << 0)
+#define INT_TF_OVERFLOW				(1 << 1)
+#define INT_RF_UNDERFLOW			(1 << 2)
+#define INT_RF_OVERFLOW				(1 << 3)
+#define INT_RF_FULL					(1 << 4)
+
+/* Bit fields in ICR, 4bit */
+#define ICR_MASK					0x0f
+#define ICR_ALL						(1 << 0)
+#define ICR_RF_UNDERFLOW			(1 << 1)
+#define ICR_RF_OVERFLOW				(1 << 2)
+#define ICR_TF_OVERFLOW				(1 << 3)
+
+/* Bit fields in DMACR */
+#define RF_DMA_EN					(1 << 0)
+#define TF_DMA_EN					(1 << 1)
+
+#define RXBUSY						(1 << 0)
+#define TXBUSY						(1 << 1)
+
+enum rockchip_ssi_type {
+	SSI_MOTO_SPI = 0,
+	SSI_TI_SSP,
+	SSI_NS_MICROWIRE,
+};
+
+struct rockchip_spi_dma_data {
+	struct dma_chan *ch;
+	enum dma_transfer_direction direction;
+	dma_addr_t addr;
+};
+
+struct rockchip_spi {
+	struct device *dev;
+	struct spi_master *master;
+
+	struct clk *spiclk;
+	struct clk *apb_pclk;
+
+	void __iomem *regs;
+	/*depth of the FIFO buffer */
+	u32 fifo_len;
+	/* max bus freq supported */
+	u32 max_freq;
+	/* supported slave numbers */
+	enum rockchip_ssi_type type;
+
+	u16 mode;
+	u8 tmode;
+	u8 bpw;
+	u8 n_bytes;
+	unsigned len;
+	u32 speed;
+
+	const void *tx;
+	const void *tx_end;
+	void *rx;
+	void *rx_end;
+
+	u32 state;
+	/* protect state */
+	spinlock_t lock;
+
+	struct completion xfer_completion;
+
+	u32 use_dma;
+	struct sg_table tx_sg;
+	struct sg_table rx_sg;
+	struct rockchip_spi_dma_data dma_rx;
+	struct rockchip_spi_dma_data dma_tx;
+};
+
+static inline void spi_enable_chip(struct rockchip_spi *rs, int enable)
+{
+	writel_relaxed((enable ? 1 : 0), rs->regs + ROCKCHIP_SPI_SSIENR);
+}
+
+static inline void spi_set_clk(struct rockchip_spi *rs, u16 div)
+{
+	writel_relaxed(div, rs->regs + ROCKCHIP_SPI_BAUDR);
+}
+
+static inline void flush_fifo(struct rockchip_spi *rs)
+{
+	while (readl_relaxed(rs->regs + ROCKCHIP_SPI_RXFLR))
+		readl_relaxed(rs->regs + ROCKCHIP_SPI_RXDR);
+}
+
+static inline void wait_for_idle(struct rockchip_spi *rs)
+{
+	unsigned long timeout = jiffies + msecs_to_jiffies(5);
+
+	do {
+		if (!(readl_relaxed(rs->regs + ROCKCHIP_SPI_SR) & SR_BUSY))
+			return;
+	} while (time_before(jiffies, timeout));
+
+	dev_warn(rs->dev, "spi controller is in busy state!\n");
+}
+
+static u32 get_fifo_len(struct rockchip_spi *rs)
+{
+	u32 fifo;
+
+	for (fifo = 2; fifo < 32; fifo++) {
+		writel_relaxed(fifo, rs->regs + ROCKCHIP_SPI_TXFTLR);
+		if (fifo != readl_relaxed(rs->regs + ROCKCHIP_SPI_TXFTLR))
+			break;
+	}
+
+	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_TXFTLR);
+
+	return (fifo == 31) ? 0 : fifo;
+}
+
+static inline u32 tx_max(struct rockchip_spi *rs)
+{
+	u32 tx_left, tx_room;
+
+	tx_left = (rs->tx_end - rs->tx) / rs->n_bytes;
+	tx_room = rs->fifo_len - readl_relaxed(rs->regs + ROCKCHIP_SPI_TXFLR);
+
+	return min(tx_left, tx_room);
+}
+
+static inline u32 rx_max(struct rockchip_spi *rs)
+{
+	u32 rx_left = (rs->rx_end - rs->rx) / rs->n_bytes;
+	u32 rx_room = (u32)readl_relaxed(rs->regs + ROCKCHIP_SPI_RXFLR);
+
+	return min(rx_left, rx_room);
+}
+
+static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	u32 ser;
+	struct rockchip_spi *rs = spi_master_get_devdata(spi->master);
+
+	ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK;
+
+	/*
+	 * drivers/spi/spi.c:
+	 * static void spi_set_cs(struct spi_device *spi, bool enable)
+	 * {
+	 *		if (spi->mode & SPI_CS_HIGH)
+	 *			enable = !enable;
+	 *
+	 *		if (spi->cs_gpio >= 0)
+	 *			gpio_set_value(spi->cs_gpio, !enable);
+	 *		else if (spi->master->set_cs)
+	 *		spi->master->set_cs(spi, !enable);
+	 * }
+	 *
+	 * Note: enable(rockchip_spi_set_cs) = !enable(spi_set_cs)
+	 */
+	if (!enable)
+		ser |= 1 << spi->chip_select;
+	else
+		ser &= ~(1 << spi->chip_select);
+
+	writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER);
+}
+
+static int rockchip_spi_prepare_message(struct spi_master *master,
+					struct spi_message *msg)
+{
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+	struct spi_device *spi = msg->spi;
+
+	rs->mode = spi->mode;
+
+	return 0;
+}
+
+static int rockchip_spi_unprepare_message(struct spi_master *master,
+					  struct spi_message *msg)
+{
+	unsigned long flags;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	spin_lock_irqsave(&rs->lock, flags);
+
+	/*
+	 * For DMA mode, we need terminate DMA channel and flush
+	 * fifo for the next transfer if DMA thansfer timeout.
+	 * unprepare_message() was called by core if transfer complete
+	 * or timeout. Maybe it is reasonable for error handling here.
+	 */
+	if (rs->use_dma) {
+		if (rs->state & RXBUSY) {
+			dmaengine_terminate_all(rs->dma_rx.ch);
+			flush_fifo(rs);
+		}
+
+		if (rs->state & TXBUSY)
+			dmaengine_terminate_all(rs->dma_tx.ch);
+	}
+
+	spin_unlock_irqrestore(&rs->lock, flags);
+
+	return 0;
+}
+
+static void rockchip_spi_pio_writer(struct rockchip_spi *rs)
+{
+	u32 max = tx_max(rs);
+	u32 txw = 0;
+
+	while (max--) {
+		if (rs->n_bytes == 1)
+			txw = *(u8 *)(rs->tx);
+		else
+			txw = *(u16 *)(rs->tx);
+
+		writel_relaxed(txw, rs->regs + ROCKCHIP_SPI_TXDR);
+		rs->tx += rs->n_bytes;
+	}
+}
+
+static void rockchip_spi_pio_reader(struct rockchip_spi *rs)
+{
+	u32 max = rx_max(rs);
+	u32 rxw;
+
+	while (max--) {
+		rxw = readl_relaxed(rs->regs + ROCKCHIP_SPI_RXDR);
+		if (rs->n_bytes == 1)
+			*(u8 *)(rs->rx) = (u8)rxw;
+		else
+			*(u16 *)(rs->rx) = (u16)rxw;
+		rs->rx += rs->n_bytes;
+	}
+}
+
+static int rockchip_spi_pio_transfer(struct rockchip_spi *rs)
+{
+	int remain = 0;
+
+	do {
+		if (rs->tx) {
+			remain = rs->tx_end - rs->tx;
+			rockchip_spi_pio_writer(rs);
+		}
+
+		if (rs->rx) {
+			remain = rs->rx_end - rs->rx;
+			rockchip_spi_pio_reader(rs);
+		}
+
+		cpu_relax();
+	} while (remain);
+
+	/* If tx, wait until the FIFO data completely. */
+	if (rs->tx)
+		wait_for_idle(rs);
+
+	return 0;
+}
+
+static void rockchip_spi_dma_rxcb(void *data)
+{
+	unsigned long flags;
+	struct rockchip_spi *rs = data;
+
+	spin_lock_irqsave(&rs->lock, flags);
+
+	rs->state &= ~RXBUSY;
+	if (!(rs->state & TXBUSY))
+		spi_finalize_current_transfer(rs->master);
+
+	spin_unlock_irqrestore(&rs->lock, flags);
+}
+
+static void rockchip_spi_dma_txcb(void *data)
+{
+	unsigned long flags;
+	struct rockchip_spi *rs = data;
+
+	/* Wait until the FIFO data completely. */
+	wait_for_idle(rs);
+
+	spin_lock_irqsave(&rs->lock, flags);
+
+	rs->state &= ~TXBUSY;
+	if (!(rs->state & RXBUSY))
+		spi_finalize_current_transfer(rs->master);
+
+	spin_unlock_irqrestore(&rs->lock, flags);
+}
+
+static int rockchip_spi_dma_transfer(struct rockchip_spi *rs)
+{
+	unsigned long flags;
+	struct dma_slave_config rxconf, txconf;
+	struct dma_async_tx_descriptor *rxdesc, *txdesc;
+
+	spin_lock_irqsave(&rs->lock, flags);
+	rs->state &= ~RXBUSY;
+	rs->state &= ~TXBUSY;
+	spin_unlock_irqrestore(&rs->lock, flags);
+
+	if (rs->rx) {
+		rxconf.direction = rs->dma_rx.direction;
+		rxconf.src_addr = rs->dma_rx.addr;
+		rxconf.src_addr_width = rs->n_bytes;
+		rxconf.src_maxburst = rs->n_bytes;
+		dmaengine_slave_config(rs->dma_rx.ch, &rxconf);
+
+		rxdesc = dmaengine_prep_slave_sg(
+				rs->dma_rx.ch,
+				rs->rx_sg.sgl, rs->rx_sg.nents,
+				rs->dma_rx.direction, DMA_PREP_INTERRUPT);
+
+		rxdesc->callback = rockchip_spi_dma_rxcb;
+		rxdesc->callback_param = rs;
+	}
+
+	if (rs->tx) {
+		txconf.direction = rs->dma_tx.direction;
+		txconf.dst_addr = rs->dma_tx.addr;
+		txconf.dst_addr_width = rs->n_bytes;
+		txconf.dst_maxburst = rs->n_bytes;
+		dmaengine_slave_config(rs->dma_tx.ch, &txconf);
+
+		txdesc = dmaengine_prep_slave_sg(
+				rs->dma_tx.ch,
+				rs->tx_sg.sgl, rs->tx_sg.nents,
+				rs->dma_tx.direction, DMA_PREP_INTERRUPT);
+
+		txdesc->callback = rockchip_spi_dma_txcb;
+		txdesc->callback_param = rs;
+	}
+
+	/* rx must be started before tx due to spi instinct */
+	if (rs->rx) {
+		spin_lock_irqsave(&rs->lock, flags);
+		rs->state |= RXBUSY;
+		spin_unlock_irqrestore(&rs->lock, flags);
+		dmaengine_submit(rxdesc);
+		dma_async_issue_pending(rs->dma_rx.ch);
+	}
+
+	if (rs->tx) {
+		spin_lock_irqsave(&rs->lock, flags);
+		rs->state |= TXBUSY;
+		spin_unlock_irqrestore(&rs->lock, flags);
+		dmaengine_submit(txdesc);
+		dma_async_issue_pending(rs->dma_tx.ch);
+	}
+
+	return 1;
+}
+
+static void rockchip_spi_config(struct rockchip_spi *rs)
+{
+	u32 div = 0;
+	u32 dmacr = 0;
+
+	u32 cr0 = (CR0_BHT_8BIT << CR0_BHT_OFFSET)
+		| (CR0_SSD_ONE << CR0_SSD_OFFSET);
+
+	cr0 |= (rs->n_bytes << CR0_DFS_OFFSET);
+	cr0 |= ((rs->mode & 0x3) << CR0_SCPH_OFFSET);
+	cr0 |= (rs->tmode << CR0_XFM_OFFSET);
+	cr0 |= (rs->type << CR0_FRF_OFFSET);
+
+	if (rs->use_dma) {
+		if (rs->tx)
+			dmacr |= TF_DMA_EN;
+		if (rs->rx)
+			dmacr |= RF_DMA_EN;
+	}
+
+	/* div doesn't support odd number */
+	div = rs->max_freq / rs->speed;
+	div = (div + 1) & 0xfffe;
+
+	spi_enable_chip(rs, 0);
+
+	writel_relaxed(cr0, rs->regs + ROCKCHIP_SPI_CTRLR0);
+
+	writel_relaxed(rs->len - 1, rs->regs + ROCKCHIP_SPI_CTRLR1);
+	writel_relaxed(rs->fifo_len / 2 - 1, rs->regs + ROCKCHIP_SPI_TXFTLR);
+	writel_relaxed(rs->fifo_len / 2 - 1, rs->regs + ROCKCHIP_SPI_RXFTLR);
+
+	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_DMATDLR);
+	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_DMARDLR);
+	writel_relaxed(dmacr, rs->regs + ROCKCHIP_SPI_DMACR);
+
+	spi_set_clk(rs, div);
+
+	dev_dbg(rs->dev, "cr0 0x%x, div %d\n", cr0, div);
+
+	spi_enable_chip(rs, 1);
+}
+
+static int rockchip_spi_transfer_one(
+		struct spi_master *master,
+		struct spi_device *spi,
+		struct spi_transfer *xfer)
+{
+	int ret = 0;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	WARN_ON((readl_relaxed(rs->regs + ROCKCHIP_SPI_SR) & SR_BUSY));
+
+	if (!xfer->tx_buf && !xfer->rx_buf) {
+		dev_err(rs->dev, "No buffer for transfer\n");
+		return -EINVAL;
+	}
+
+	rs->speed = xfer->speed_hz;
+	rs->bpw = xfer->bits_per_word;
+	rs->n_bytes = rs->bpw >> 3;
+
+	rs->tx = xfer->tx_buf;
+	rs->tx_end = rs->tx + xfer->len;
+	rs->rx = xfer->rx_buf;
+	rs->rx_end = rs->rx + xfer->len;
+	rs->len = xfer->len;
+
+	rs->tx_sg = xfer->tx_sg;
+	rs->rx_sg = xfer->rx_sg;
+
+	if (rs->tx && rs->rx)
+		rs->tmode = CR0_XFM_TR;
+	else if (rs->tx)
+		rs->tmode = CR0_XFM_TO;
+	else if (rs->rx)
+		rs->tmode = CR0_XFM_RO;
+
+	if (master->can_dma && master->can_dma(master, spi, xfer))
+		rs->use_dma = 1;
+	else
+		rs->use_dma = 0;
+
+	rockchip_spi_config(rs);
+
+	if (rs->use_dma)
+		ret = rockchip_spi_dma_transfer(rs);
+	else
+		ret = rockchip_spi_pio_transfer(rs);
+
+	return ret;
+}
+
+static bool rockchip_spi_can_dma(struct spi_master *master,
+				 struct spi_device *spi,
+				 struct spi_transfer *xfer)
+{
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	return (xfer->len > rs->fifo_len);
+}
+
+static int rockchip_spi_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	struct rockchip_spi *rs;
+	struct spi_master *master;
+	struct resource *mem;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(struct rockchip_spi));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+
+	rs = spi_master_get_devdata(master);
+	memset(rs, 0, sizeof(struct rockchip_spi));
+
+	/* Get basic io resource and map it */
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rs->regs = devm_ioremap_resource(&pdev->dev, mem);
+	if (IS_ERR(rs->regs)) {
+		ret =  PTR_ERR(rs->regs);
+		goto err_ioremap_resource;
+	}
+
+	rs->apb_pclk = devm_clk_get(&pdev->dev, "apb_pclk");
+	if (IS_ERR(rs->apb_pclk)) {
+		dev_err(&pdev->dev, "Failed to get apb_pclk\n");
+		ret = PTR_ERR(rs->apb_pclk);
+		goto err_ioremap_resource;
+	}
+
+	rs->spiclk = devm_clk_get(&pdev->dev, "spiclk");
+	if (IS_ERR(rs->spiclk)) {
+		dev_err(&pdev->dev, "Failed to get spi_pclk\n");
+		ret = PTR_ERR(rs->spiclk);
+		goto err_ioremap_resource;
+	}
+
+	ret = clk_prepare_enable(rs->apb_pclk);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to enable apb_pclk\n");
+		goto err_ioremap_resource;
+	}
+
+	ret = clk_prepare_enable(rs->spiclk);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to enable spi_clk\n");
+		goto err_spiclk_enable;
+	}
+
+	spi_enable_chip(rs, 0);
+
+	rs->type = SSI_MOTO_SPI;
+	rs->master = master;
+	rs->dev = &pdev->dev;
+	rs->max_freq = clk_get_rate(rs->spiclk);
+
+	rs->fifo_len = get_fifo_len(rs);
+	if (!rs->fifo_len) {
+		dev_err(&pdev->dev, "Failed to get fifo length\n");
+		ret = -EINVAL;
+		goto err_get_fifo_len;
+	}
+
+	spin_lock_init(&rs->lock);
+
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
+	master->auto_runtime_pm = true;
+	master->bus_num = pdev->id;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LOOP;
+	master->num_chipselect = 2;
+	master->dev.of_node = pdev->dev.of_node;
+	master->bits_per_word_mask = SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
+
+	master->set_cs = rockchip_spi_set_cs;
+	master->prepare_message = rockchip_spi_prepare_message;
+	master->unprepare_message = rockchip_spi_unprepare_message;
+	master->transfer_one = rockchip_spi_transfer_one;
+
+	rs->dma_tx.ch = dma_request_slave_channel(rs->dev, "tx");
+	if (!rs->dma_tx.ch)
+		dev_warn(rs->dev, "Failed to request TX DMA channel\n");
+
+	rs->dma_rx.ch = dma_request_slave_channel(rs->dev, "rx");
+	if (!rs->dma_rx.ch) {
+		if (rs->dma_tx.ch) {
+			dma_release_channel(rs->dma_tx.ch);
+			rs->dma_tx.ch = NULL;
+		}
+		dev_warn(rs->dev, "Failed to request RX DMA channel\n");
+	}
+
+	if (rs->dma_tx.ch && rs->dma_rx.ch) {
+		rs->dma_tx.addr = (dma_addr_t)(mem->start + ROCKCHIP_SPI_TXDR);
+		rs->dma_rx.addr = (dma_addr_t)(mem->start + ROCKCHIP_SPI_RXDR);
+		rs->dma_tx.direction = DMA_MEM_TO_DEV;
+		rs->dma_tx.direction = DMA_DEV_TO_MEM;
+
+		master->can_dma = rockchip_spi_can_dma;
+		master->dma_tx = rs->dma_tx.ch;
+		master->dma_rx = rs->dma_rx.ch;
+	}
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to register master\n");
+		goto err_register_master;
+	}
+
+	return 0;
+
+err_register_master:
+	if (rs->dma_tx.ch)
+		dma_release_channel(rs->dma_tx.ch);
+	if (rs->dma_rx.ch)
+		dma_release_channel(rs->dma_rx.ch);
+err_get_fifo_len:
+	clk_disable_unprepare(rs->spiclk);
+err_spiclk_enable:
+	clk_disable_unprepare(rs->apb_pclk);
+err_ioremap_resource:
+	spi_master_put(master);
+
+	return ret;
+}
+
+static int rockchip_spi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = spi_master_get(platform_get_drvdata(pdev));
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	pm_runtime_disable(&pdev->dev);
+
+	clk_disable_unprepare(rs->spiclk);
+	clk_disable_unprepare(rs->apb_pclk);
+
+	if (rs->dma_tx.ch)
+		dma_release_channel(rs->dma_tx.ch);
+	if (rs->dma_rx.ch)
+		dma_release_channel(rs->dma_rx.ch);
+
+	spi_master_put(master);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int rockchip_spi_suspend(struct device *dev)
+{
+	int ret = 0;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	ret = spi_master_suspend(rs->master);
+	if (ret)
+		return ret;
+
+	if (!pm_runtime_suspended(dev)) {
+		clk_disable_unprepare(rs->spiclk);
+		clk_disable_unprepare(rs->apb_pclk);
+	}
+
+	return ret;
+}
+
+static int rockchip_spi_resume(struct device *dev)
+{
+	int ret = 0;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	if (!pm_runtime_suspended(dev)) {
+		ret = clk_prepare_enable(rs->apb_pclk);
+		if (ret < 0)
+			return ret;
+
+		ret = clk_prepare_enable(rs->spiclk);
+		if (ret < 0) {
+			clk_disable_unprepare(rs->apb_pclk);
+			return ret;
+		}
+	}
+
+	ret = spi_master_resume(rs->master);
+	if (ret < 0) {
+		clk_disable_unprepare(rs->spiclk);
+		clk_disable_unprepare(rs->apb_pclk);
+	}
+
+	return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM_RUNTIME
+static int rockchip_spi_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	clk_disable_unprepare(rs->spiclk);
+	clk_disable_unprepare(rs->apb_pclk);
+
+	return 0;
+}
+
+static int rockchip_spi_runtime_resume(struct device *dev)
+{
+	int ret;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	ret = clk_prepare_enable(rs->apb_pclk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(rs->spiclk);
+	if (ret)
+		clk_disable_unprepare(rs->apb_pclk);
+
+	return ret;
+}
+#endif /* CONFIG_PM_RUNTIME */
+
+static const struct dev_pm_ops rockchip_spi_pm = {
+	SET_SYSTEM_SLEEP_PM_OPS(rockchip_spi_suspend, rockchip_spi_resume)
+	SET_RUNTIME_PM_OPS(rockchip_spi_runtime_suspend,
+			   rockchip_spi_runtime_resume, NULL)
+};
+
+static const struct of_device_id rockchip_spi_dt_match[] = {
+	{ .compatible = "rockchip,rk3066-spi", },
+	{ .compatible = "rockchip,rk3188-spi", },
+	{ .compatible = "rockchip,rk3288-spi", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, rockchip_spi_dt_match);
+
+static struct platform_driver rockchip_spi_driver = {
+	.driver = {
+		.name	= DRIVER_NAME,
+		.owner = THIS_MODULE,
+		.pm = &rockchip_spi_pm,
+		.of_match_table = of_match_ptr(rockchip_spi_dt_match),
+	},
+	.probe = rockchip_spi_probe,
+	.remove = rockchip_spi_remove,
+};
+
+module_platform_driver(rockchip_spi_driver);
+
+MODULE_AUTHOR("Addy Ke <addy.ke@rock-chips.com>");
+MODULE_DESCRIPTION("ROCKCHIP SPI Controller Driver");
+MODULE_LICENSE("GPL v2");

drivers/spi/spi-rspi.c

@@ -477,7 +477,7 @@ static int rspi_dma_transfer(struct rspi_data *rspi, struct sg_table *tx,
 					tx->sgl, tx->nents, DMA_TO_DEVICE,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (!desc_tx)
-			return -EIO;
+			goto no_dma;
 
 		irq_mask |= SPCR_SPTIE;
 	}
@@ -486,7 +486,7 @@ static int rspi_dma_transfer(struct rspi_data *rspi, struct sg_table *tx,
 					rx->sgl, rx->nents, DMA_FROM_DEVICE,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 		if (!desc_rx)
-			return -EIO;
+			goto no_dma;
 
 		irq_mask |= SPCR_SPRIE;
 	}
@@ -540,6 +540,12 @@ static int rspi_dma_transfer(struct rspi_data *rspi, struct sg_table *tx,
 		enable_irq(rspi->rx_irq);
 
 	return ret;
+
+no_dma:
+	pr_warn_once("%s %s: DMA not available, falling back to PIO\n",
+		     dev_driver_string(&rspi->master->dev),
+		     dev_name(&rspi->master->dev));
+	return -EAGAIN;
 }
 
 static void rspi_receive_init(const struct rspi_data *rspi)
@@ -593,8 +599,10 @@ static int rspi_common_transfer(struct rspi_data *rspi,
 
 	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer)) {
 		/* rx_buf can be NULL on RSPI on SH in TX-only Mode */
-		return rspi_dma_transfer(rspi, &xfer->tx_sg,
+		ret = rspi_dma_transfer(rspi, &xfer->tx_sg,
 					xfer->rx_buf ? &xfer->rx_sg : NULL);
+		if (ret != -EAGAIN)
+			return ret;
 	}
 
 	ret = rspi_pio_transfer(rspi, xfer->tx_buf, xfer->rx_buf, xfer->len);
@@ -630,7 +638,6 @@ static int rspi_rz_transfer_one(struct spi_master *master,
 				struct spi_transfer *xfer)
 {
 	struct rspi_data *rspi = spi_master_get_devdata(master);
-	int ret;
 
 	rspi_rz_receive_init(rspi);
 
@@ -649,8 +656,11 @@ static int qspi_transfer_out(struct rspi_data *rspi, struct spi_transfer *xfer)
 {
 	int ret;
 
-	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer))
+	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer)) {
-		return rspi_dma_transfer(rspi, &xfer->tx_sg, NULL);
+		ret = rspi_dma_transfer(rspi, &xfer->tx_sg, NULL);
+		if (ret != -EAGAIN)
+			return ret;
+	}
 
 	ret = rspi_pio_transfer(rspi, xfer->tx_buf, NULL, xfer->len);
 	if (ret < 0)
@@ -664,8 +674,11 @@ static int qspi_transfer_out(struct rspi_data *rspi, struct spi_transfer *xfer)
 
 static int qspi_transfer_in(struct rspi_data *rspi, struct spi_transfer *xfer)
 {
-	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer))
+	if (rspi->master->can_dma && __rspi_can_dma(rspi, xfer)) {
-		return rspi_dma_transfer(rspi, NULL, &xfer->rx_sg);
+		int ret = rspi_dma_transfer(rspi, NULL, &xfer->rx_sg);
+		if (ret != -EAGAIN)
+			return ret;
+	}
 
 	return rspi_pio_transfer(rspi, NULL, xfer->rx_buf, xfer->len);
 }
@@ -927,19 +940,19 @@ static int rspi_request_dma(struct device *dev, struct spi_master *master,
 	return 0;
 }
 
-static void rspi_release_dma(struct rspi_data *rspi)
+static void rspi_release_dma(struct spi_master *master)
 {
-	if (rspi->master->dma_tx)
+	if (master->dma_tx)
-		dma_release_channel(rspi->master->dma_tx);
+		dma_release_channel(master->dma_tx);
-	if (rspi->master->dma_rx)
+	if (master->dma_rx)
-		dma_release_channel(rspi->master->dma_rx);
+		dma_release_channel(master->dma_rx);
 }
 
 static int rspi_remove(struct platform_device *pdev)
 {
 	struct rspi_data *rspi = platform_get_drvdata(pdev);
 
-	rspi_release_dma(rspi);
+	rspi_release_dma(rspi->master);
 	pm_runtime_disable(&pdev->dev);
 
 	return 0;
@@ -1141,7 +1154,7 @@ static int rspi_probe(struct platform_device *pdev)
 	return 0;
 
 error3:
-	rspi_release_dma(rspi);
+	rspi_release_dma(master);
 error2:
 	pm_runtime_disable(&pdev->dev);
 error1:

drivers/spi/spi-s3c64xx.c

@@ -197,7 +197,6 @@ struct s3c64xx_spi_driver_data {
 	struct s3c64xx_spi_dma_data	tx_dma;
 	struct s3c64xx_spi_port_config	*port_conf;
 	unsigned int			port_id;
-	bool				cs_gpio;
 };
 
 static void flush_fifo(struct s3c64xx_spi_driver_data *sdd)
@@ -754,10 +753,8 @@ static struct s3c64xx_spi_csinfo *s3c64xx_get_slave_ctrldata(
 {
 	struct s3c64xx_spi_csinfo *cs;
 	struct device_node *slave_np, *data_np = NULL;
-	struct s3c64xx_spi_driver_data *sdd;
 	u32 fb_delay = 0;
 
-	sdd = spi_master_get_devdata(spi->master);
 	slave_np = spi->dev.of_node;
 	if (!slave_np) {
 		dev_err(&spi->dev, "device node not found\n");
@@ -776,17 +773,6 @@ static struct s3c64xx_spi_csinfo *s3c64xx_get_slave_ctrldata(
 		return ERR_PTR(-ENOMEM);
 	}
 
-	/* The CS line is asserted/deasserted by the gpio pin */
-	if (sdd->cs_gpio)
-		cs->line = of_get_named_gpio(data_np, "cs-gpio", 0);
-
-	if (!gpio_is_valid(cs->line)) {
-		dev_err(&spi->dev, "chip select gpio is not specified or invalid\n");
-		kfree(cs);
-		of_node_put(data_np);
-		return ERR_PTR(-EINVAL);
-	}
-
 	of_property_read_u32(data_np, "samsung,spi-feedback-delay", &fb_delay);
 	cs->fb_delay = fb_delay;
 	of_node_put(data_np);
@@ -807,9 +793,16 @@ static int s3c64xx_spi_setup(struct spi_device *spi)
 	int err;
 
 	sdd = spi_master_get_devdata(spi->master);
-	if (!cs && spi->dev.of_node) {
+	if (spi->dev.of_node) {
 		cs = s3c64xx_get_slave_ctrldata(spi);
 		spi->controller_data = cs;
+	} else if (cs) {
+		/* On non-DT platforms the SPI core will set spi->cs_gpio
+		 * to -ENOENT. The GPIO pin used to drive the chip select
+		 * is defined by using platform data so spi->cs_gpio value
+		 * has to be override to have the proper GPIO pin number.
+		 */
+		spi->cs_gpio = cs->line;
 	}
 
 	if (IS_ERR_OR_NULL(cs)) {
@@ -818,18 +811,15 @@ static int s3c64xx_spi_setup(struct spi_device *spi)
 	}
 
 	if (!spi_get_ctldata(spi)) {
-		/* Request gpio only if cs line is asserted by gpio pins */
+		if (gpio_is_valid(spi->cs_gpio)) {
-		if (sdd->cs_gpio) {
+			err = gpio_request_one(spi->cs_gpio, GPIOF_OUT_INIT_HIGH,
-			err = gpio_request_one(cs->line, GPIOF_OUT_INIT_HIGH,
 					       dev_name(&spi->dev));
 			if (err) {
 				dev_err(&spi->dev,
 					"Failed to get /CS gpio [%d]: %d\n",
-					cs->line, err);
+					spi->cs_gpio, err);
 				goto err_gpio_req;
 			}
-
-			spi->cs_gpio = cs->line;
 		}
 
 		spi_set_ctldata(spi, cs);
@@ -884,7 +874,8 @@ setup_exit:
 	/* setup() returns with device de-selected */
 	writel(S3C64XX_SPI_SLAVE_SIG_INACT, sdd->regs + S3C64XX_SPI_SLAVE_SEL);
 
-	gpio_free(cs->line);
+	if (gpio_is_valid(spi->cs_gpio))
+		gpio_free(spi->cs_gpio);
 	spi_set_ctldata(spi, NULL);
 
 err_gpio_req:
@@ -897,14 +888,21 @@ err_gpio_req:
 static void s3c64xx_spi_cleanup(struct spi_device *spi)
 {
 	struct s3c64xx_spi_csinfo *cs = spi_get_ctldata(spi);
-	struct s3c64xx_spi_driver_data *sdd;
 
-	sdd = spi_master_get_devdata(spi->master);
+	if (gpio_is_valid(spi->cs_gpio)) {
-	if (spi->cs_gpio) {
 		gpio_free(spi->cs_gpio);
 		if (spi->dev.of_node)
 			kfree(cs);
+		else {
+			/* On non-DT platforms, the SPI core sets
+			 * spi->cs_gpio to -ENOENT and .setup()
+			 * overrides it with the GPIO pin value
+			 * passed using platform data.
+			 */
+			spi->cs_gpio = -ENOENT;
 		}
+	}
+
 	spi_set_ctldata(spi, NULL);
 }
 
@@ -1075,11 +1073,7 @@ static int s3c64xx_spi_probe(struct platform_device *pdev)
 	sdd->cntrlr_info = sci;
 	sdd->pdev = pdev;
 	sdd->sfr_start = mem_res->start;
-	sdd->cs_gpio = true;
 	if (pdev->dev.of_node) {
-		if (!of_find_property(pdev->dev.of_node, "cs-gpio", NULL))
-			sdd->cs_gpio = false;
-
 		ret = of_alias_get_id(pdev->dev.of_node, "spi");
 		if (ret < 0) {
 			dev_err(&pdev->dev, "failed to get alias id, errno %d\n",

drivers/spi/spi-sh-hspi.c

@@ -304,7 +304,7 @@ static int hspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static struct of_device_id hspi_of_match[] = {
+static const struct of_device_id hspi_of_match[] = {
 	{ .compatible = "renesas,hspi", },
 	{ /* sentinel */ }
 };

drivers/spi/spi-sh-msiof.c

@@ -2,6 +2,7 @@
  * SuperH MSIOF SPI Master Interface
  *
  * Copyright (c) 2009 Magnus Damm
+ * Copyright (C) 2014 Glider bvba
  *
  * 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
@@ -13,6 +14,8 @@
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/err.h>
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
@@ -23,6 +26,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/sh_dma.h>
 
 #include <linux/spi/sh_msiof.h>
 #include <linux/spi/spi.h>
@@ -37,6 +41,7 @@ struct sh_msiof_chipdata {
 };
 
 struct sh_msiof_spi_priv {
+	struct spi_master *master;
 	void __iomem *mapbase;
 	struct clk *clk;
 	struct platform_device *pdev;
@@ -45,6 +50,10 @@ struct sh_msiof_spi_priv {
 	struct completion done;
 	int tx_fifo_size;
 	int rx_fifo_size;
+	void *tx_dma_page;
+	void *rx_dma_page;
+	dma_addr_t tx_dma_addr;
+	dma_addr_t rx_dma_addr;
 };
 
 #define TMDR1	0x00	/* Transmit Mode Register 1 */
@@ -84,6 +93,8 @@ struct sh_msiof_spi_priv {
 #define MDR2_WDLEN1(i)	(((i) - 1) << 16) /* Word Count (1-64/256 (SH, A1))) */
 #define MDR2_GRPMASK1	0x00000001 /* Group Output Mask 1 (SH, A1) */
 
+#define MAX_WDLEN	256U
+
 /* TSCR and RSCR */
 #define SCR_BRPS_MASK	    0x1f00 /* Prescaler Setting (1-32) */
 #define SCR_BRPS(i)	(((i) - 1) << 8)
@@ -113,9 +124,61 @@ struct sh_msiof_spi_priv {
 #define CTR_TXE		0x00000200 /* Transmit Enable */
 #define CTR_RXE		0x00000100 /* Receive Enable */
 
-/* STR and IER */
+/* FCTR */
+#define FCTR_TFWM_MASK	0xe0000000 /* Transmit FIFO Watermark */
+#define FCTR_TFWM_64	0x00000000 /*  Transfer Request when 64 empty stages */
+#define FCTR_TFWM_32	0x20000000 /*  Transfer Request when 32 empty stages */
+#define FCTR_TFWM_24	0x40000000 /*  Transfer Request when 24 empty stages */
+#define FCTR_TFWM_16	0x60000000 /*  Transfer Request when 16 empty stages */
+#define FCTR_TFWM_12	0x80000000 /*  Transfer Request when 12 empty stages */
+#define FCTR_TFWM_8	0xa0000000 /*  Transfer Request when 8 empty stages */
+#define FCTR_TFWM_4	0xc0000000 /*  Transfer Request when 4 empty stages */
+#define FCTR_TFWM_1	0xe0000000 /*  Transfer Request when 1 empty stage */
+#define FCTR_TFUA_MASK	0x07f00000 /* Transmit FIFO Usable Area */
+#define FCTR_TFUA_SHIFT		20
+#define FCTR_TFUA(i)	((i) << FCTR_TFUA_SHIFT)
+#define FCTR_RFWM_MASK	0x0000e000 /* Receive FIFO Watermark */
+#define FCTR_RFWM_1	0x00000000 /*  Transfer Request when 1 valid stages */
+#define FCTR_RFWM_4	0x00002000 /*  Transfer Request when 4 valid stages */
+#define FCTR_RFWM_8	0x00004000 /*  Transfer Request when 8 valid stages */
+#define FCTR_RFWM_16	0x00006000 /*  Transfer Request when 16 valid stages */
+#define FCTR_RFWM_32	0x00008000 /*  Transfer Request when 32 valid stages */
+#define FCTR_RFWM_64	0x0000a000 /*  Transfer Request when 64 valid stages */
+#define FCTR_RFWM_128	0x0000c000 /*  Transfer Request when 128 valid stages */
+#define FCTR_RFWM_256	0x0000e000 /*  Transfer Request when 256 valid stages */
+#define FCTR_RFUA_MASK	0x00001ff0 /* Receive FIFO Usable Area (0x40 = full) */
+#define FCTR_RFUA_SHIFT		 4
+#define FCTR_RFUA(i)	((i) << FCTR_RFUA_SHIFT)
+
+/* STR */
+#define STR_TFEMP	0x20000000 /* Transmit FIFO Empty */
+#define STR_TDREQ	0x10000000 /* Transmit Data Transfer Request */
 #define STR_TEOF	0x00800000 /* Frame Transmission End */
+#define STR_TFSERR	0x00200000 /* Transmit Frame Synchronization Error */
+#define STR_TFOVF	0x00100000 /* Transmit FIFO Overflow */
+#define STR_TFUDF	0x00080000 /* Transmit FIFO Underflow */
+#define STR_RFFUL	0x00002000 /* Receive FIFO Full */
+#define STR_RDREQ	0x00001000 /* Receive Data Transfer Request */
 #define STR_REOF	0x00000080 /* Frame Reception End */
+#define STR_RFSERR	0x00000020 /* Receive Frame Synchronization Error */
+#define STR_RFUDF	0x00000010 /* Receive FIFO Underflow */
+#define STR_RFOVF	0x00000008 /* Receive FIFO Overflow */
+
+/* IER */
+#define IER_TDMAE	0x80000000 /* Transmit Data DMA Transfer Req. Enable */
+#define IER_TFEMPE	0x20000000 /* Transmit FIFO Empty Enable */
+#define IER_TDREQE	0x10000000 /* Transmit Data Transfer Request Enable */
+#define IER_TEOFE	0x00800000 /* Frame Transmission End Enable */
+#define IER_TFSERRE	0x00200000 /* Transmit Frame Sync Error Enable */
+#define IER_TFOVFE	0x00100000 /* Transmit FIFO Overflow Enable */
+#define IER_TFUDFE	0x00080000 /* Transmit FIFO Underflow Enable */
+#define IER_RDMAE	0x00008000 /* Receive Data DMA Transfer Req. Enable */
+#define IER_RFFULE	0x00002000 /* Receive FIFO Full Enable */
+#define IER_RDREQE	0x00001000 /* Receive Data Transfer Request Enable */
+#define IER_REOFE	0x00000080 /* Frame Reception End Enable */
+#define IER_RFSERRE	0x00000020 /* Receive Frame Sync Error Enable */
+#define IER_RFUDFE	0x00000010 /* Receive FIFO Underflow Enable */
+#define IER_RFOVFE	0x00000008 /* Receive FIFO Overflow Enable */
 
 
 static u32 sh_msiof_read(struct sh_msiof_spi_priv *p, int reg_offs)
@@ -230,8 +293,6 @@ static void sh_msiof_spi_set_pin_regs(struct sh_msiof_spi_priv *p,
 	 *    1    0         11     11    0    0
 	 *    1    1         11     11    1    1
 	 */
-	sh_msiof_write(p, FCTR, 0);
-
 	tmp = MDR1_SYNCMD_SPI | 1 << MDR1_FLD_SHIFT | MDR1_XXSTP;
 	tmp |= !cs_high << MDR1_SYNCAC_SHIFT;
 	tmp |= lsb_first << MDR1_BITLSB_SHIFT;
@@ -267,8 +328,6 @@ static void sh_msiof_spi_set_mode_regs(struct sh_msiof_spi_priv *p,
 
 	if (rx_buf)
 		sh_msiof_write(p, RMDR2, dr2);
-
-	sh_msiof_write(p, IER, STR_TEOF | STR_REOF);
 }
 
 static void sh_msiof_reset_str(struct sh_msiof_spi_priv *p)
@@ -457,6 +516,40 @@ static int sh_msiof_prepare_message(struct spi_master *master,
 	return 0;
 }
 
+static int sh_msiof_spi_start(struct sh_msiof_spi_priv *p, void *rx_buf)
+{
+	int ret;
+
+	/* setup clock and rx/tx signals */
+	ret = sh_msiof_modify_ctr_wait(p, 0, CTR_TSCKE);
+	if (rx_buf && !ret)
+		ret = sh_msiof_modify_ctr_wait(p, 0, CTR_RXE);
+	if (!ret)
+		ret = sh_msiof_modify_ctr_wait(p, 0, CTR_TXE);
+
+	/* start by setting frame bit */
+	if (!ret)
+		ret = sh_msiof_modify_ctr_wait(p, 0, CTR_TFSE);
+
+	return ret;
+}
+
+static int sh_msiof_spi_stop(struct sh_msiof_spi_priv *p, void *rx_buf)
+{
+	int ret;
+
+	/* shut down frame, rx/tx and clock signals */
+	ret = sh_msiof_modify_ctr_wait(p, CTR_TFSE, 0);
+	if (!ret)
+		ret = sh_msiof_modify_ctr_wait(p, CTR_TXE, 0);
+	if (rx_buf && !ret)
+		ret = sh_msiof_modify_ctr_wait(p, CTR_RXE, 0);
+	if (!ret)
+		ret = sh_msiof_modify_ctr_wait(p, CTR_TSCKE, 0);
+
+	return ret;
+}
+
 static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p,
 				  void (*tx_fifo)(struct sh_msiof_spi_priv *,
 						  const void *, int, int),
@@ -477,29 +570,32 @@ static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p,
 	/* the fifo contents need shifting */
 	fifo_shift = 32 - bits;
 
+	/* default FIFO watermarks for PIO */
+	sh_msiof_write(p, FCTR, 0);
+
 	/* setup msiof transfer mode registers */
 	sh_msiof_spi_set_mode_regs(p, tx_buf, rx_buf, bits, words);
+	sh_msiof_write(p, IER, IER_TEOFE | IER_REOFE);
 
 	/* write tx fifo */
 	if (tx_buf)
 		tx_fifo(p, tx_buf, words, fifo_shift);
 
-	/* setup clock and rx/tx signals */
-	ret = sh_msiof_modify_ctr_wait(p, 0, CTR_TSCKE);
-	if (rx_buf)
-		ret = ret ? ret : sh_msiof_modify_ctr_wait(p, 0, CTR_RXE);
-	ret = ret ? ret : sh_msiof_modify_ctr_wait(p, 0, CTR_TXE);
-
-	/* start by setting frame bit */
 	reinit_completion(&p->done);
-	ret = ret ? ret : sh_msiof_modify_ctr_wait(p, 0, CTR_TFSE);
+
+	ret = sh_msiof_spi_start(p, rx_buf);
 	if (ret) {
 		dev_err(&p->pdev->dev, "failed to start hardware\n");
-		goto err;
+		goto stop_ier;
 	}
 
 	/* wait for tx fifo to be emptied / rx fifo to be filled */
-	wait_for_completion(&p->done);
+	ret = wait_for_completion_timeout(&p->done, HZ);
+	if (!ret) {
+		dev_err(&p->pdev->dev, "PIO timeout\n");
+		ret = -ETIMEDOUT;
+		goto stop_reset;
+	}
 
 	/* read rx fifo */
 	if (rx_buf)
@@ -508,41 +604,248 @@ static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p,
 	/* clear status bits */
 	sh_msiof_reset_str(p);
 
-	/* shut down frame, rx/tx and clock signals */
+	ret = sh_msiof_spi_stop(p, rx_buf);
-	ret = sh_msiof_modify_ctr_wait(p, CTR_TFSE, 0);
-	ret = ret ? ret : sh_msiof_modify_ctr_wait(p, CTR_TXE, 0);
-	if (rx_buf)
-		ret = ret ? ret : sh_msiof_modify_ctr_wait(p, CTR_RXE, 0);
-	ret = ret ? ret : sh_msiof_modify_ctr_wait(p, CTR_TSCKE, 0);
 	if (ret) {
 		dev_err(&p->pdev->dev, "failed to shut down hardware\n");
-		goto err;
+		return ret;
 	}
 
 	return words;
 
- err:
+stop_reset:
+	sh_msiof_reset_str(p);
+	sh_msiof_spi_stop(p, rx_buf);
+stop_ier:
 	sh_msiof_write(p, IER, 0);
 	return ret;
 }
 
+static void sh_msiof_dma_complete(void *arg)
+{
+	struct sh_msiof_spi_priv *p = arg;
+
+	sh_msiof_write(p, IER, 0);
+	complete(&p->done);
+}
+
+static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
+			     void *rx, unsigned int len)
+{
+	u32 ier_bits = 0;
+	struct dma_async_tx_descriptor *desc_tx = NULL, *desc_rx = NULL;
+	dma_cookie_t cookie;
+	int ret;
+
+	if (tx) {
+		ier_bits |= IER_TDREQE | IER_TDMAE;
+		dma_sync_single_for_device(p->master->dma_tx->device->dev,
+					   p->tx_dma_addr, len, DMA_TO_DEVICE);
+		desc_tx = dmaengine_prep_slave_single(p->master->dma_tx,
+					p->tx_dma_addr, len, DMA_TO_DEVICE,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!desc_tx)
+			return -EAGAIN;
+	}
+
+	if (rx) {
+		ier_bits |= IER_RDREQE | IER_RDMAE;
+		desc_rx = dmaengine_prep_slave_single(p->master->dma_rx,
+					p->rx_dma_addr, len, DMA_FROM_DEVICE,
+					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+		if (!desc_rx)
+			return -EAGAIN;
+	}
+
+	/* 1 stage FIFO watermarks for DMA */
+	sh_msiof_write(p, FCTR, FCTR_TFWM_1 | FCTR_RFWM_1);
+
+	/* setup msiof transfer mode registers (32-bit words) */
+	sh_msiof_spi_set_mode_regs(p, tx, rx, 32, len / 4);
+
+	sh_msiof_write(p, IER, ier_bits);
+
+	reinit_completion(&p->done);
+
+	if (rx) {
+		desc_rx->callback = sh_msiof_dma_complete;
+		desc_rx->callback_param = p;
+		cookie = dmaengine_submit(desc_rx);
+		if (dma_submit_error(cookie)) {
+			ret = cookie;
+			goto stop_ier;
+		}
+		dma_async_issue_pending(p->master->dma_rx);
+	}
+
+	if (tx) {
+		if (rx) {
+			/* No callback */
+			desc_tx->callback = NULL;
+		} else {
+			desc_tx->callback = sh_msiof_dma_complete;
+			desc_tx->callback_param = p;
+		}
+		cookie = dmaengine_submit(desc_tx);
+		if (dma_submit_error(cookie)) {
+			ret = cookie;
+			goto stop_rx;
+		}
+		dma_async_issue_pending(p->master->dma_tx);
+	}
+
+	ret = sh_msiof_spi_start(p, rx);
+	if (ret) {
+		dev_err(&p->pdev->dev, "failed to start hardware\n");
+		goto stop_tx;
+	}
+
+	/* wait for tx fifo to be emptied / rx fifo to be filled */
+	ret = wait_for_completion_timeout(&p->done, HZ);
+	if (!ret) {
+		dev_err(&p->pdev->dev, "DMA timeout\n");
+		ret = -ETIMEDOUT;
+		goto stop_reset;
+	}
+
+	/* clear status bits */
+	sh_msiof_reset_str(p);
+
+	ret = sh_msiof_spi_stop(p, rx);
+	if (ret) {
+		dev_err(&p->pdev->dev, "failed to shut down hardware\n");
+		return ret;
+	}
+
+	if (rx)
+		dma_sync_single_for_cpu(p->master->dma_rx->device->dev,
+					p->rx_dma_addr, len,
+					DMA_FROM_DEVICE);
+
+	return 0;
+
+stop_reset:
+	sh_msiof_reset_str(p);
+	sh_msiof_spi_stop(p, rx);
+stop_tx:
+	if (tx)
+		dmaengine_terminate_all(p->master->dma_tx);
+stop_rx:
+	if (rx)
+		dmaengine_terminate_all(p->master->dma_rx);
+stop_ier:
+	sh_msiof_write(p, IER, 0);
+	return ret;
+}
+
+static void copy_bswap32(u32 *dst, const u32 *src, unsigned int words)
+{
+	/* src or dst can be unaligned, but not both */
+	if ((unsigned long)src & 3) {
+		while (words--) {
+			*dst++ = swab32(get_unaligned(src));
+			src++;
+		}
+	} else if ((unsigned long)dst & 3) {
+		while (words--) {
+			put_unaligned(swab32(*src++), dst);
+			dst++;
+		}
+	} else {
+		while (words--)
+			*dst++ = swab32(*src++);
+	}
+}
+
+static void copy_wswap32(u32 *dst, const u32 *src, unsigned int words)
+{
+	/* src or dst can be unaligned, but not both */
+	if ((unsigned long)src & 3) {
+		while (words--) {
+			*dst++ = swahw32(get_unaligned(src));
+			src++;
+		}
+	} else if ((unsigned long)dst & 3) {
+		while (words--) {
+			put_unaligned(swahw32(*src++), dst);
+			dst++;
+		}
+	} else {
+		while (words--)
+			*dst++ = swahw32(*src++);
+	}
+}
+
+static void copy_plain32(u32 *dst, const u32 *src, unsigned int words)
+{
+	memcpy(dst, src, words * 4);
+}
+
 static int sh_msiof_transfer_one(struct spi_master *master,
 				 struct spi_device *spi,
 				 struct spi_transfer *t)
 {
 	struct sh_msiof_spi_priv *p = spi_master_get_devdata(master);
+	void (*copy32)(u32 *, const u32 *, unsigned int);
 	void (*tx_fifo)(struct sh_msiof_spi_priv *, const void *, int, int);
 	void (*rx_fifo)(struct sh_msiof_spi_priv *, void *, int, int);
-	int bits;
+	const void *tx_buf = t->tx_buf;
-	int bytes_per_word;
+	void *rx_buf = t->rx_buf;
-	int bytes_done;
+	unsigned int len = t->len;
-	int words;
+	unsigned int bits = t->bits_per_word;
+	unsigned int bytes_per_word;
+	unsigned int words;
 	int n;
 	bool swab;
+	int ret;
 
-	bits = t->bits_per_word;
+	/* setup clocks (clock already enabled in chipselect()) */
+	sh_msiof_spi_set_clk_regs(p, clk_get_rate(p->clk), t->speed_hz);
 
-	if (bits <= 8 && t->len > 15 && !(t->len & 3)) {
+	while (master->dma_tx && len > 15) {
+		/*
+		 *  DMA supports 32-bit words only, hence pack 8-bit and 16-bit
+		 *  words, with byte resp. word swapping.
+		 */
+		unsigned int l = min(len, MAX_WDLEN * 4);
+
+		if (bits <= 8) {
+			if (l & 3)
+				break;
+			copy32 = copy_bswap32;
+		} else if (bits <= 16) {
+			if (l & 1)
+				break;
+			copy32 = copy_wswap32;
+		} else {
+			copy32 = copy_plain32;
+		}
+
+		if (tx_buf)
+			copy32(p->tx_dma_page, tx_buf, l / 4);
+
+		ret = sh_msiof_dma_once(p, tx_buf, rx_buf, l);
+		if (ret == -EAGAIN) {
+			pr_warn_once("%s %s: DMA not available, falling back to PIO\n",
+				     dev_driver_string(&p->pdev->dev),
+				     dev_name(&p->pdev->dev));
+			break;
+		}
+		if (ret)
+			return ret;
+
+		if (rx_buf) {
+			copy32(rx_buf, p->rx_dma_page, l / 4);
+			rx_buf += l;
+		}
+		if (tx_buf)
+			tx_buf += l;
+
+		len -= l;
+		if (!len)
+			return 0;
+	}
+
+	if (bits <= 8 && len > 15 && !(len & 3)) {
 		bits = 32;
 		swab = true;
 	} else {
@@ -556,57 +859,52 @@ static int sh_msiof_transfer_one(struct spi_master *master,
 		rx_fifo = sh_msiof_spi_read_fifo_8;
 	} else if (bits <= 16) {
 		bytes_per_word = 2;
-		if ((unsigned long)t->tx_buf & 0x01)
+		if ((unsigned long)tx_buf & 0x01)
 			tx_fifo = sh_msiof_spi_write_fifo_16u;
 		else
 			tx_fifo = sh_msiof_spi_write_fifo_16;
 
-		if ((unsigned long)t->rx_buf & 0x01)
+		if ((unsigned long)rx_buf & 0x01)
 			rx_fifo = sh_msiof_spi_read_fifo_16u;
 		else
 			rx_fifo = sh_msiof_spi_read_fifo_16;
 	} else if (swab) {
 		bytes_per_word = 4;
-		if ((unsigned long)t->tx_buf & 0x03)
+		if ((unsigned long)tx_buf & 0x03)
 			tx_fifo = sh_msiof_spi_write_fifo_s32u;
 		else
 			tx_fifo = sh_msiof_spi_write_fifo_s32;
 
-		if ((unsigned long)t->rx_buf & 0x03)
+		if ((unsigned long)rx_buf & 0x03)
 			rx_fifo = sh_msiof_spi_read_fifo_s32u;
 		else
 			rx_fifo = sh_msiof_spi_read_fifo_s32;
 	} else {
 		bytes_per_word = 4;
-		if ((unsigned long)t->tx_buf & 0x03)
+		if ((unsigned long)tx_buf & 0x03)
 			tx_fifo = sh_msiof_spi_write_fifo_32u;
 		else
 			tx_fifo = sh_msiof_spi_write_fifo_32;
 
-		if ((unsigned long)t->rx_buf & 0x03)
+		if ((unsigned long)rx_buf & 0x03)
 			rx_fifo = sh_msiof_spi_read_fifo_32u;
 		else
 			rx_fifo = sh_msiof_spi_read_fifo_32;
 	}
 
-	/* setup clocks (clock already enabled in chipselect()) */
-	sh_msiof_spi_set_clk_regs(p, clk_get_rate(p->clk), t->speed_hz);
-
 	/* transfer in fifo sized chunks */
-	words = t->len / bytes_per_word;
+	words = len / bytes_per_word;
-	bytes_done = 0;
 
-	while (bytes_done < t->len) {
+	while (words > 0) {
-		void *rx_buf = t->rx_buf ? t->rx_buf + bytes_done : NULL;
+		n = sh_msiof_spi_txrx_once(p, tx_fifo, rx_fifo, tx_buf, rx_buf,
-		const void *tx_buf = t->tx_buf ? t->tx_buf + bytes_done : NULL;
-		n = sh_msiof_spi_txrx_once(p, tx_fifo, rx_fifo,
-					   tx_buf,
-					   rx_buf,
 					   words, bits);
 		if (n < 0)
-			break;
+			return n;
 
-		bytes_done += n * bytes_per_word;
+		if (tx_buf)
+			tx_buf += n * bytes_per_word;
+		if (rx_buf)
+			rx_buf += n * bytes_per_word;
 		words -= n;
 	}
 
@@ -663,6 +961,128 @@ static struct sh_msiof_spi_info *sh_msiof_spi_parse_dt(struct device *dev)
 }
 #endif
 
+static struct dma_chan *sh_msiof_request_dma_chan(struct device *dev,
+	enum dma_transfer_direction dir, unsigned int id, dma_addr_t port_addr)
+{
+	dma_cap_mask_t mask;
+	struct dma_chan *chan;
+	struct dma_slave_config cfg;
+	int ret;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+
+	chan = dma_request_channel(mask, shdma_chan_filter,
+				  (void *)(unsigned long)id);
+	if (!chan) {
+		dev_warn(dev, "dma_request_channel failed\n");
+		return NULL;
+	}
+
+	memset(&cfg, 0, sizeof(cfg));
+	cfg.slave_id = id;
+	cfg.direction = dir;
+	if (dir == DMA_MEM_TO_DEV)
+		cfg.dst_addr = port_addr;
+	else
+		cfg.src_addr = port_addr;
+
+	ret = dmaengine_slave_config(chan, &cfg);
+	if (ret) {
+		dev_warn(dev, "dmaengine_slave_config failed %d\n", ret);
+		dma_release_channel(chan);
+		return NULL;
+	}
+
+	return chan;
+}
+
+static int sh_msiof_request_dma(struct sh_msiof_spi_priv *p)
+{
+	struct platform_device *pdev = p->pdev;
+	struct device *dev = &pdev->dev;
+	const struct sh_msiof_spi_info *info = dev_get_platdata(dev);
+	const struct resource *res;
+	struct spi_master *master;
+	struct device *tx_dev, *rx_dev;
+
+	if (!info || !info->dma_tx_id || !info->dma_rx_id)
+		return 0;	/* The driver assumes no error */
+
+	/* The DMA engine uses the second register set, if present */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (!res)
+		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	master = p->master;
+	master->dma_tx = sh_msiof_request_dma_chan(dev, DMA_MEM_TO_DEV,
+						   info->dma_tx_id,
+						   res->start + TFDR);
+	if (!master->dma_tx)
+		return -ENODEV;
+
+	master->dma_rx = sh_msiof_request_dma_chan(dev, DMA_DEV_TO_MEM,
+						   info->dma_rx_id,
+						   res->start + RFDR);
+	if (!master->dma_rx)
+		goto free_tx_chan;
+
+	p->tx_dma_page = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+	if (!p->tx_dma_page)
+		goto free_rx_chan;
+
+	p->rx_dma_page = (void *)__get_free_page(GFP_KERNEL | GFP_DMA);
+	if (!p->rx_dma_page)
+		goto free_tx_page;
+
+	tx_dev = master->dma_tx->device->dev;
+	p->tx_dma_addr = dma_map_single(tx_dev, p->tx_dma_page, PAGE_SIZE,
+					DMA_TO_DEVICE);
+	if (dma_mapping_error(tx_dev, p->tx_dma_addr))
+		goto free_rx_page;
+
+	rx_dev = master->dma_rx->device->dev;
+	p->rx_dma_addr = dma_map_single(rx_dev, p->rx_dma_page, PAGE_SIZE,
+					DMA_FROM_DEVICE);
+	if (dma_mapping_error(rx_dev, p->rx_dma_addr))
+		goto unmap_tx_page;
+
+	dev_info(dev, "DMA available");
+	return 0;
+
+unmap_tx_page:
+	dma_unmap_single(tx_dev, p->tx_dma_addr, PAGE_SIZE, DMA_TO_DEVICE);
+free_rx_page:
+	free_page((unsigned long)p->rx_dma_page);
+free_tx_page:
+	free_page((unsigned long)p->tx_dma_page);
+free_rx_chan:
+	dma_release_channel(master->dma_rx);
+free_tx_chan:
+	dma_release_channel(master->dma_tx);
+	master->dma_tx = NULL;
+	return -ENODEV;
+}
+
+static void sh_msiof_release_dma(struct sh_msiof_spi_priv *p)
+{
+	struct spi_master *master = p->master;
+	struct device *dev;
+
+	if (!master->dma_tx)
+		return;
+
+	dev = &p->pdev->dev;
+	dma_unmap_single(master->dma_rx->device->dev, p->rx_dma_addr,
+			 PAGE_SIZE, DMA_FROM_DEVICE);
+	dma_unmap_single(master->dma_tx->device->dev, p->tx_dma_addr,
+			 PAGE_SIZE, DMA_TO_DEVICE);
+	free_page((unsigned long)p->rx_dma_page);
+	free_page((unsigned long)p->tx_dma_page);
+	dma_release_channel(master->dma_rx);
+	dma_release_channel(master->dma_tx);
+}
+
 static int sh_msiof_spi_probe(struct platform_device *pdev)
 {
 	struct resource	*r;
@@ -681,6 +1101,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	p = spi_master_get_devdata(master);
 
 	platform_set_drvdata(pdev, p);
+	p->master = master;
 
 	of_id = of_match_device(sh_msiof_match, &pdev->dev);
 	if (of_id) {
@@ -751,6 +1172,10 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	master->auto_runtime_pm = true;
 	master->transfer_one = sh_msiof_transfer_one;
 
+	ret = sh_msiof_request_dma(p);
+	if (ret < 0)
+		dev_warn(&pdev->dev, "DMA not available, using PIO\n");
+
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "spi_register_master error.\n");
@@ -760,6 +1185,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	return 0;
 
  err2:
+	sh_msiof_release_dma(p);
 	pm_runtime_disable(&pdev->dev);
  err1:
 	spi_master_put(master);
@@ -768,6 +1194,9 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 
 static int sh_msiof_spi_remove(struct platform_device *pdev)
 {
+	struct sh_msiof_spi_priv *p = platform_get_drvdata(pdev);
+
+	sh_msiof_release_dma(p);
 	pm_runtime_disable(&pdev->dev);
 	return 0;
 }

drivers/spi/spi-sh.c

@@ -432,7 +432,6 @@ static int spi_sh_remove(struct platform_device *pdev)
 	spi_unregister_master(ss->master);
 	destroy_workqueue(ss->workqueue);
 	free_irq(ss->irq, ss);
-	iounmap(ss->addr);
 
 	return 0;
 }
@@ -480,7 +479,7 @@ static int spi_sh_probe(struct platform_device *pdev)
 	}
 	ss->irq = irq;
 	ss->master = master;
-	ss->addr = ioremap(res->start, resource_size(res));
+	ss->addr = devm_ioremap(&pdev->dev, res->start, resource_size(res));
 	if (ss->addr == NULL) {
 		dev_err(&pdev->dev, "ioremap error.\n");
 		ret = -ENOMEM;
@@ -495,13 +494,13 @@ static int spi_sh_probe(struct platform_device *pdev)
 	if (ss->workqueue == NULL) {
 		dev_err(&pdev->dev, "create workqueue error\n");
 		ret = -EBUSY;
-		goto error2;
+		goto error1;
 	}
 
 	ret = request_irq(irq, spi_sh_irq, 0, "spi_sh", ss);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "request_irq error\n");
-		goto error3;
+		goto error2;
 	}
 
 	master->num_chipselect = 2;
@@ -513,17 +512,15 @@ static int spi_sh_probe(struct platform_device *pdev)
 	ret = spi_register_master(master);
 	if (ret < 0) {
 		printk(KERN_ERR "spi_register_master error.\n");
-		goto error4;
+		goto error3;
 	}
 
 	return 0;
 
- error4:
-	free_irq(irq, ss);
  error3:
-	destroy_workqueue(ss->workqueue);
+	free_irq(irq, ss);
  error2:
-	iounmap(ss->addr);
+	destroy_workqueue(ss->workqueue);
  error1:
 	spi_master_put(master);
 

drivers/spi/spi-topcliff-pch.c

@@ -874,8 +874,8 @@ static void pch_spi_request_dma(struct pch_spi_data *data, int bpw)
 	dma_cap_set(DMA_SLAVE, mask);
 
 	/* Get DMA's dev information */
-	dma_dev = pci_get_bus_and_slot(data->board_dat->pdev->bus->number,
+	dma_dev = pci_get_slot(data->board_dat->pdev->bus,
-				       PCI_DEVFN(12, 0));
+			PCI_DEVFN(PCI_SLOT(data->board_dat->pdev->devfn), 0));
 
 	/* Set Tx DMA */
 	param = &dma->param_tx;
@@ -1047,8 +1047,8 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 					num, DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_rx) {
-		dev_err(&data->master->dev, "%s:device_prep_slave_sg Failed\n",
+		dev_err(&data->master->dev,
-			__func__);
+			"%s:dmaengine_prep_slave_sg Failed\n", __func__);
 		return;
 	}
 	dma_sync_sg_for_device(&data->master->dev, sg, num, DMA_FROM_DEVICE);
@@ -1106,8 +1106,8 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 					sg, num, DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
 	if (!desc_tx) {
-		dev_err(&data->master->dev, "%s:device_prep_slave_sg Failed\n",
+		dev_err(&data->master->dev,
-			__func__);
+			"%s:dmaengine_prep_slave_sg Failed\n", __func__);
 		return;
 	}
 	dma_sync_sg_for_device(&data->master->dev, sg, num, DMA_TO_DEVICE);

drivers/spi/spi-xilinx.c

@@ -369,7 +369,7 @@ static int xilinx_spi_probe(struct platform_device *pdev)
 		goto put_master;
 	}
 
-	master->bus_num = pdev->dev.id;
+	master->bus_num = pdev->id;
 	master->num_chipselect = num_cs;
 	master->dev.of_node = pdev->dev.of_node;
 

drivers/spi/spi.c

@@ -350,14 +350,12 @@ static DEFINE_MUTEX(board_lock);
 struct spi_device *spi_alloc_device(struct spi_master *master)
 {
 	struct spi_device	*spi;
-	struct device		*dev = master->dev.parent;
 
 	if (!spi_master_get(master))
 		return NULL;
 
 	spi = kzalloc(sizeof(*spi), GFP_KERNEL);
 	if (!spi) {
-		dev_err(dev, "cannot alloc spi_device\n");
 		spi_master_put(master);
 		return NULL;
 	}
@@ -624,6 +622,8 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 	}
 
 	ret = dma_map_sg(dev, sgt->sgl, sgt->nents, dir);
+	if (!ret)
+		ret = -ENOMEM;
 	if (ret < 0) {
 		sg_free_table(sgt);
 		return ret;
@@ -652,8 +652,8 @@ static int __spi_map_msg(struct spi_master *master, struct spi_message *msg)
 	if (!master->can_dma)
 		return 0;
 
-	tx_dev = &master->dma_tx->dev->device;
+	tx_dev = master->dma_tx->device->dev;
-	rx_dev = &master->dma_rx->dev->device;
+	rx_dev = master->dma_rx->device->dev;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		if (!master->can_dma(master, msg->spi, xfer))
@@ -692,8 +692,8 @@ static int spi_unmap_msg(struct spi_master *master, struct spi_message *msg)
 	if (!master->cur_msg_mapped || !master->can_dma)
 		return 0;
 
-	tx_dev = &master->dma_tx->dev->device;
+	tx_dev = master->dma_tx->device->dev;
-	rx_dev = &master->dma_rx->dev->device;
+	rx_dev = master->dma_rx->device->dev;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		if (!master->can_dma(master, msg->spi, xfer))

include/linux/spi/sh_msiof.h

@@ -5,6 +5,8 @@ struct sh_msiof_spi_info {
 	int tx_fifo_override;
 	int rx_fifo_override;
 	u16 num_chipselect;
+	unsigned int dma_tx_id;
+	unsigned int dma_rx_id;
 };
 
 #endif /* __SPI_SH_MSIOF_H__ */