diff --git a/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt
new file mode 100644
index 0000000000000000000000000000000000000000..8a18d71e68791fbf29256716d5c83d31eed0701d
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/adi,axi-spi-engine.txt
@@ -0,0 +1,31 @@
+Analog Devices AXI SPI Engine controller Device Tree Bindings
+
+Required properties:
+- compatible		: Must be "adi,axi-spi-engine-1.00.a""
+- reg			: Physical base address and size of the register map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- clock-names		: List of input clock names - "s_axi_aclk", "spi_clk"
+- clocks		: Clock phandles and specifiers (See clock bindings for
+			  details on clock-names and clocks).
+- #address-cells	: Must be <1>
+- #size-cells		: Must be <0>
+
+Optional subnodes:
+	Subnodes are use to represent the SPI slave devices connected to the SPI
+	master. They follow the generic SPI bindings as outlined in spi-bus.txt.
+
+Example:
+
+    spi@@44a00000 {
+		compatible = "adi,axi-spi-engine-1.00.a";
+		reg = <0x44a00000 0x1000>;
+		interrupts = <0 56 4>;
+		clocks = <&clkc 15 &clkc 15>;
+		clock-names = "s_axi_aclk", "spi_clk";
+
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		/* SPI devices */
+    };
diff --git a/Documentation/devicetree/bindings/spi/icpdas-lp8841-spi-rtc.txt b/Documentation/devicetree/bindings/spi/icpdas-lp8841-spi-rtc.txt
new file mode 100644
index 0000000000000000000000000000000000000000..852b651f3bc5b619662232676b082ad9e593d42d
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/icpdas-lp8841-spi-rtc.txt
@@ -0,0 +1,54 @@
+* ICP DAS LP-8841 SPI Controller for RTC
+
+ICP DAS LP-8841 contains a DS-1302 RTC. RTC is connected to an IO
+memory register, which acts as an SPI master device.
+
+The device uses the standard MicroWire half-duplex transfer timing.
+Master output is set on low clock and sensed by the RTC on the rising
+edge. Master input is set by the RTC on the trailing edge and is sensed
+by the master on low clock.
+
+Required properties:
+
+- #address-cells: should be 1
+
+- #size-cells: should be 0
+
+- compatible: should be "icpdas,lp8841-spi-rtc"
+
+- reg: should provide IO memory address
+
+Requirements to SPI slave nodes:
+
+- There can be only one slave device.
+
+- The spi slave node should claim the following flags which are
+  required by the spi controller.
+
+  - spi-3wire: The master itself has only 3 wire. It cannor work in
+    full duplex mode.
+
+  - spi-cs-high: DS-1302 has active high chip select line. The master
+    doesn't support active low.
+
+  - spi-lsb-first: DS-1302 requires least significant bit first
+    transfers. The master only support this type of bit ordering.
+
+
+Example:
+
+spi@901c {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "icpdas,lp8841-spi-rtc";
+	reg = <0x901c 0x1>;
+
+	rtc@0 {
+		compatible = "maxim,ds1302";
+		reg = <0>;
+		spi-max-frequency = <500000>;
+		spi-3wire;
+		spi-lsb-first;
+		spi-cs-high;
+	};
+};
diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
index 0c491bda4c65f9bace70c051fc06389261d82cad..1b14d69d8903a448a1138e38bf8332828bfd551e 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
@@ -9,6 +9,7 @@ Required Properties:
     "rockchip,rk3066-spi" for rk3066.
     "rockchip,rk3188-spi", "rockchip,rk3066-spi" for rk3188.
     "rockchip,rk3288-spi", "rockchip,rk3066-spi" for rk3288.
+    "rockchip,rk3399-spi", "rockchip,rk3066-spi" for rk3399.
 - reg: physical base address of the controller and length of memory mapped
        region.
 - interrupts: The interrupt number to the cpu. The interrupt specifier format
diff --git a/Documentation/devicetree/bindings/spi/spi-xilinx.txt b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
new file mode 100644
index 0000000000000000000000000000000000000000..c7b7856bd5281aed0f4a6e5d6bd633386733f763
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
@@ -0,0 +1,22 @@
+Xilinx SPI controller Device Tree Bindings
+-------------------------------------------------
+
+Required properties:
+- compatible		: Should be "xlnx,xps-spi-2.00.a" or "xlnx,xps-spi-2.00.b"
+- reg			: Physical base address and size of SPI registers map.
+- interrupts		: Property with a value describing the interrupt
+			  number.
+- interrupt-parent	: Must be core interrupt controller
+
+Optional properties:
+- xlnx,num-ss-bits	: Number of chip selects used.
+
+Example:
+	axi_quad_spi@41e00000 {
+			compatible = "xlnx,xps-spi-2.00.a";
+			interrupt-parent = <&intc>;
+			interrupts = <0 31 1>;
+			reg = <0x41e00000 0x10000>;
+			xlnx,num-ss-bits = <0x1>;
+	};
+
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 77064160dd762c26f6c1fd184b252b24360163e3..9d8c84bb15446a75153d64f94a5900ab165193ac 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -75,11 +75,26 @@ config SPI_ATMEL
 	  This selects a driver for the Atmel SPI Controller, present on
 	  many AT32 (AVR32) and AT91 (ARM) chips.
 
+config SPI_AU1550
+	tristate "Au1550/Au1200/Au1300 SPI Controller"
+	depends on MIPS_ALCHEMY
+	select SPI_BITBANG
+	help
+	  If you say yes to this option, support will be included for the
+	  PSC SPI controller found on Au1550, Au1200 and Au1300 series.
+
+config SPI_AXI_SPI_ENGINE
+	tristate "Analog Devices AXI SPI Engine controller"
+	depends on HAS_IOMEM
+	help
+	  This enables support for the Analog Devices AXI SPI Engine SPI controller.
+	  It is part of the SPI Engine framework that is used in some Analog Devices
+	  reference designs for FPGAs.
+
 config SPI_BCM2835
 	tristate "BCM2835 SPI controller"
 	depends on GPIOLIB
 	depends on ARCH_BCM2835 || COMPILE_TEST
-	depends on GPIOLIB
 	help
 	  This selects a driver for the Broadcom BCM2835 SPI master.
 
@@ -90,8 +105,7 @@ config SPI_BCM2835
 
 config SPI_BCM2835AUX
 	tristate "BCM2835 SPI auxiliary controller"
-	depends on ARCH_BCM2835 || COMPILE_TEST
-	depends on GPIOLIB
+	depends on (ARCH_BCM2835 && GPIOLIB) || COMPILE_TEST
 	help
 	  This selects a driver for the Broadcom BCM2835 SPI aux master.
 
@@ -118,14 +132,6 @@ config SPI_BFIN_SPORT
 	help
 	  Enable support for a SPI bus via the Blackfin SPORT peripheral.
 
-config SPI_AU1550
-	tristate "Au1550/Au1200/Au1300 SPI Controller"
-	depends on MIPS_ALCHEMY
-	select SPI_BITBANG
-	help
-	  If you say yes to this option, support will be included for the
-	  PSC SPI controller found on Au1550, Au1200 and Au1300 series.
-
 config SPI_BCM53XX
 	tristate "Broadcom BCM53xx SPI controller"
 	depends on ARCH_BCM_5301X
@@ -197,6 +203,23 @@ config SPI_DAVINCI
 	help
 	  SPI master controller for DaVinci/DA8x/OMAP-L/AM1x SPI modules.
 
+config SPI_DESIGNWARE
+	tristate "DesignWare SPI controller core support"
+	help
+	  general driver for SPI controller core from DesignWare
+
+config SPI_DW_PCI
+	tristate "PCI interface driver for DW SPI core"
+	depends on SPI_DESIGNWARE && PCI
+
+config SPI_DW_MID_DMA
+	bool "DMA support for DW SPI controller on Intel MID platform"
+	depends on SPI_DW_PCI && DW_DMAC_PCI
+
+config SPI_DW_MMIO
+	tristate "Memory-mapped io interface driver for DW SPI core"
+	depends on SPI_DESIGNWARE
+
 config SPI_DLN2
        tristate "Diolan DLN-2 USB SPI adapter"
        depends on MFD_DLN2
@@ -271,6 +294,16 @@ config SPI_LM70_LLP
 	  which interfaces to an LM70 temperature sensor using
 	  a parallel port.
 
+config SPI_LP8841_RTC
+	tristate "ICP DAS LP-8841 SPI Controller for RTC"
+	depends on MACH_PXA27X_DT || COMPILE_TEST
+	help
+	  This driver provides an SPI master device to drive Maxim
+	  DS-1302 real time clock.
+
+	  Say N here unless you plan to run the kernel on an ICP DAS
+	  LP-8x4x industrial computer.
+
 config SPI_MPC52xx
 	tristate "Freescale MPC52xx SPI (non-PSC) controller support"
 	depends on PPC_MPC52xx
@@ -346,6 +379,13 @@ config SPI_MT65XX
 	  say Y or M here.If you are not sure, say N.
 	  SPI drivers for Mediatek MT65XX and MT81XX series ARM SoCs.
 
+config SPI_NUC900
+	tristate "Nuvoton NUC900 series SPI"
+	depends on ARCH_W90X900
+	select SPI_BITBANG
+	help
+	  SPI driver for Nuvoton NUC900 series ARM SoCs
+
 config SPI_OC_TINY
 	tristate "OpenCores tiny SPI"
 	depends on GPIOLIB || COMPILE_TEST
@@ -415,10 +455,6 @@ config SPI_PPC4xx
 	help
 	  This selects a driver for the PPC4xx SPI Controller.
 
-config SPI_PXA2XX_DMA
-	def_bool y
-	depends on SPI_PXA2XX
-
 config SPI_PXA2XX
 	tristate "PXA2xx SSP SPI master"
 	depends on (ARCH_PXA || PCI || ACPI)
@@ -451,7 +487,7 @@ config SPI_RB4XX
 
 config SPI_RSPI
 	tristate "Renesas RSPI/QSPI controller"
-	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
+	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for Renesas RSPI and QSPI blocks.
 
@@ -501,7 +537,7 @@ config SPI_SC18IS602
 config SPI_SH_MSIOF
 	tristate "SuperH MSIOF SPI controller"
 	depends on HAVE_CLK && HAS_DMA
-	depends on SUPERH || ARCH_SHMOBILE || COMPILE_TEST
+	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for SuperH and SH Mobile MSIOF blocks.
 
@@ -520,7 +556,7 @@ config SPI_SH_SCI
 
 config SPI_SH_HSPI
 	tristate "SuperH HSPI controller"
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	help
 	  SPI driver for SuperH HSPI blocks.
 
@@ -647,34 +683,10 @@ config SPI_ZYNQMP_GQSPI
 	help
 	  Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC.
 
-config SPI_NUC900
-	tristate "Nuvoton NUC900 series SPI"
-	depends on ARCH_W90X900
-	select SPI_BITBANG
-	help
-	  SPI driver for Nuvoton NUC900 series ARM SoCs
-
 #
 # Add new SPI master controllers in alphabetical order above this line
 #
 
-config SPI_DESIGNWARE
-	tristate "DesignWare SPI controller core support"
-	help
-	  general driver for SPI controller core from DesignWare
-
-config SPI_DW_PCI
-	tristate "PCI interface driver for DW SPI core"
-	depends on SPI_DESIGNWARE && PCI
-
-config SPI_DW_MID_DMA
-	bool "DMA support for DW SPI controller on Intel MID platform"
-	depends on SPI_DW_PCI && DW_DMAC_PCI
-
-config SPI_DW_MMIO
-	tristate "Memory-mapped io interface driver for DW SPI core"
-	depends on SPI_DESIGNWARE
-
 #
 # There are lots of SPI device types, with sensors and memory
 # being probably the most widely used ones.
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 8991ffce6e12d66682dcbbbcdbecf86f9f08dc3c..fbb255c5a608d270ccdb10f1d7ea8f2bd3e24c45 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_SPI_ALTERA)		+= spi-altera.o
 obj-$(CONFIG_SPI_ATMEL)			+= spi-atmel.o
 obj-$(CONFIG_SPI_ATH79)			+= spi-ath79.o
 obj-$(CONFIG_SPI_AU1550)		+= spi-au1550.o
+obj-$(CONFIG_SPI_AXI_SPI_ENGINE)	+= spi-axi-spi-engine.o
 obj-$(CONFIG_SPI_BCM2835)		+= spi-bcm2835.o
 obj-$(CONFIG_SPI_BCM2835AUX)		+= spi-bcm2835aux.o
 obj-$(CONFIG_SPI_BCM53XX)		+= spi-bcm53xx.o
@@ -46,6 +47,7 @@ obj-$(CONFIG_SPI_GPIO)			+= spi-gpio.o
 obj-$(CONFIG_SPI_IMG_SPFI)		+= spi-img-spfi.o
 obj-$(CONFIG_SPI_IMX)			+= spi-imx.o
 obj-$(CONFIG_SPI_LM70_LLP)		+= spi-lm70llp.o
+obj-$(CONFIG_SPI_LP8841_RTC)		+= spi-lp8841-rtc.o
 obj-$(CONFIG_SPI_MESON_SPIFC)		+= spi-meson-spifc.o
 obj-$(CONFIG_SPI_MPC512x_PSC)		+= spi-mpc512x-psc.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= spi-mpc52xx-psc.o
@@ -62,8 +64,7 @@ obj-$(CONFIG_SPI_TI_QSPI)		+= spi-ti-qspi.o
 obj-$(CONFIG_SPI_ORION)			+= spi-orion.o
 obj-$(CONFIG_SPI_PL022)			+= spi-pl022.o
 obj-$(CONFIG_SPI_PPC4xx)		+= spi-ppc4xx.o
-spi-pxa2xx-platform-objs		:= spi-pxa2xx.o
-spi-pxa2xx-platform-$(CONFIG_SPI_PXA2XX_DMA)	+= spi-pxa2xx-dma.o
+spi-pxa2xx-platform-objs		:= spi-pxa2xx.o spi-pxa2xx-dma.o
 obj-$(CONFIG_SPI_PXA2XX)		+= spi-pxa2xx-platform.o
 obj-$(CONFIG_SPI_PXA2XX_PCI)		+= spi-pxa2xx-pci.o
 obj-$(CONFIG_SPI_QUP)			+= spi-qup.o
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
new file mode 100644
index 0000000000000000000000000000000000000000..c968ab210a5157482f199f23328d7fb22c27e0c7
--- /dev/null
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -0,0 +1,591 @@
+/*
+ * SPI-Engine SPI controller driver
+ * Copyright 2015 Analog Devices Inc.
+ *  Author: Lars-Peter Clausen <lars@metafoo.de>
+ *
+ * Licensed under the GPL-2.
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+#define SPI_ENGINE_VERSION_MAJOR(x)	((x >> 16) & 0xff)
+#define SPI_ENGINE_VERSION_MINOR(x)	((x >> 8) & 0xff)
+#define SPI_ENGINE_VERSION_PATCH(x)	(x & 0xff)
+
+#define SPI_ENGINE_REG_VERSION			0x00
+
+#define SPI_ENGINE_REG_RESET			0x40
+
+#define SPI_ENGINE_REG_INT_ENABLE		0x80
+#define SPI_ENGINE_REG_INT_PENDING		0x84
+#define SPI_ENGINE_REG_INT_SOURCE		0x88
+
+#define SPI_ENGINE_REG_SYNC_ID			0xc0
+
+#define SPI_ENGINE_REG_CMD_FIFO_ROOM		0xd0
+#define SPI_ENGINE_REG_SDO_FIFO_ROOM		0xd4
+#define SPI_ENGINE_REG_SDI_FIFO_LEVEL		0xd8
+
+#define SPI_ENGINE_REG_CMD_FIFO			0xe0
+#define SPI_ENGINE_REG_SDO_DATA_FIFO		0xe4
+#define SPI_ENGINE_REG_SDI_DATA_FIFO		0xe8
+#define SPI_ENGINE_REG_SDI_DATA_FIFO_PEEK	0xec
+
+#define SPI_ENGINE_INT_CMD_ALMOST_EMPTY		BIT(0)
+#define SPI_ENGINE_INT_SDO_ALMOST_EMPTY		BIT(1)
+#define SPI_ENGINE_INT_SDI_ALMOST_FULL		BIT(2)
+#define SPI_ENGINE_INT_SYNC			BIT(3)
+
+#define SPI_ENGINE_CONFIG_CPHA			BIT(0)
+#define SPI_ENGINE_CONFIG_CPOL			BIT(1)
+#define SPI_ENGINE_CONFIG_3WIRE			BIT(2)
+
+#define SPI_ENGINE_INST_TRANSFER		0x0
+#define SPI_ENGINE_INST_ASSERT			0x1
+#define SPI_ENGINE_INST_WRITE			0x2
+#define SPI_ENGINE_INST_MISC			0x3
+
+#define SPI_ENGINE_CMD_REG_CLK_DIV		0x0
+#define SPI_ENGINE_CMD_REG_CONFIG		0x1
+
+#define SPI_ENGINE_MISC_SYNC			0x0
+#define SPI_ENGINE_MISC_SLEEP			0x1
+
+#define SPI_ENGINE_TRANSFER_WRITE		0x1
+#define SPI_ENGINE_TRANSFER_READ		0x2
+
+#define SPI_ENGINE_CMD(inst, arg1, arg2) \
+	(((inst) << 12) | ((arg1) << 8) | (arg2))
+
+#define SPI_ENGINE_CMD_TRANSFER(flags, n) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_TRANSFER, (flags), (n))
+#define SPI_ENGINE_CMD_ASSERT(delay, cs) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_ASSERT, (delay), (cs))
+#define SPI_ENGINE_CMD_WRITE(reg, val) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_WRITE, (reg), (val))
+#define SPI_ENGINE_CMD_SLEEP(delay) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_MISC, SPI_ENGINE_MISC_SLEEP, (delay))
+#define SPI_ENGINE_CMD_SYNC(id) \
+	SPI_ENGINE_CMD(SPI_ENGINE_INST_MISC, SPI_ENGINE_MISC_SYNC, (id))
+
+struct spi_engine_program {
+	unsigned int length;
+	uint16_t instructions[];
+};
+
+struct spi_engine {
+	struct clk *clk;
+	struct clk *ref_clk;
+
+	spinlock_t lock;
+
+	void __iomem *base;
+
+	struct spi_message *msg;
+	struct spi_engine_program *p;
+	unsigned cmd_length;
+	const uint16_t *cmd_buf;
+
+	struct spi_transfer *tx_xfer;
+	unsigned int tx_length;
+	const uint8_t *tx_buf;
+
+	struct spi_transfer *rx_xfer;
+	unsigned int rx_length;
+	uint8_t *rx_buf;
+
+	unsigned int sync_id;
+	unsigned int completed_id;
+
+	unsigned int int_enable;
+};
+
+static void spi_engine_program_add_cmd(struct spi_engine_program *p,
+	bool dry, uint16_t cmd)
+{
+	if (!dry)
+		p->instructions[p->length] = cmd;
+	p->length++;
+}
+
+static unsigned int spi_engine_get_config(struct spi_device *spi)
+{
+	unsigned int config = 0;
+
+	if (spi->mode & SPI_CPOL)
+		config |= SPI_ENGINE_CONFIG_CPOL;
+	if (spi->mode & SPI_CPHA)
+		config |= SPI_ENGINE_CONFIG_CPHA;
+	if (spi->mode & SPI_3WIRE)
+		config |= SPI_ENGINE_CONFIG_3WIRE;
+
+	return config;
+}
+
+static unsigned int spi_engine_get_clk_div(struct spi_engine *spi_engine,
+	struct spi_device *spi, struct spi_transfer *xfer)
+{
+	unsigned int clk_div;
+
+	clk_div = DIV_ROUND_UP(clk_get_rate(spi_engine->ref_clk),
+		xfer->speed_hz * 2);
+	if (clk_div > 255)
+		clk_div = 255;
+	else if (clk_div > 0)
+		clk_div -= 1;
+
+	return clk_div;
+}
+
+static void spi_engine_gen_xfer(struct spi_engine_program *p, bool dry,
+	struct spi_transfer *xfer)
+{
+	unsigned int len = xfer->len;
+
+	while (len) {
+		unsigned int n = min(len, 256U);
+		unsigned int flags = 0;
+
+		if (xfer->tx_buf)
+			flags |= SPI_ENGINE_TRANSFER_WRITE;
+		if (xfer->rx_buf)
+			flags |= SPI_ENGINE_TRANSFER_READ;
+
+		spi_engine_program_add_cmd(p, dry,
+			SPI_ENGINE_CMD_TRANSFER(flags, n - 1));
+		len -= n;
+	}
+}
+
+static void spi_engine_gen_sleep(struct spi_engine_program *p, bool dry,
+	struct spi_engine *spi_engine, unsigned int clk_div, unsigned int delay)
+{
+	unsigned int spi_clk = clk_get_rate(spi_engine->ref_clk);
+	unsigned int t;
+
+	if (delay == 0)
+		return;
+
+	t = DIV_ROUND_UP(delay * spi_clk, (clk_div + 1) * 2);
+	while (t) {
+		unsigned int n = min(t, 256U);
+
+		spi_engine_program_add_cmd(p, dry, SPI_ENGINE_CMD_SLEEP(n - 1));
+		t -= n;
+	}
+}
+
+static void spi_engine_gen_cs(struct spi_engine_program *p, bool dry,
+		struct spi_device *spi, bool assert)
+{
+	unsigned int mask = 0xff;
+
+	if (assert)
+		mask ^= BIT(spi->chip_select);
+
+	spi_engine_program_add_cmd(p, dry, SPI_ENGINE_CMD_ASSERT(1, mask));
+}
+
+static int spi_engine_compile_message(struct spi_engine *spi_engine,
+	struct spi_message *msg, bool dry, struct spi_engine_program *p)
+{
+	struct spi_device *spi = msg->spi;
+	struct spi_transfer *xfer;
+	int clk_div, new_clk_div;
+	bool cs_change = true;
+
+	clk_div = -1;
+
+	spi_engine_program_add_cmd(p, dry,
+		SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CONFIG,
+			spi_engine_get_config(spi)));
+
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		new_clk_div = spi_engine_get_clk_div(spi_engine, spi, xfer);
+		if (new_clk_div != clk_div) {
+			clk_div = new_clk_div;
+			spi_engine_program_add_cmd(p, dry,
+				SPI_ENGINE_CMD_WRITE(SPI_ENGINE_CMD_REG_CLK_DIV,
+					clk_div));
+		}
+
+		if (cs_change)
+			spi_engine_gen_cs(p, dry, spi, true);
+
+		spi_engine_gen_xfer(p, dry, xfer);
+		spi_engine_gen_sleep(p, dry, spi_engine, clk_div,
+			xfer->delay_usecs);
+
+		cs_change = xfer->cs_change;
+		if (list_is_last(&xfer->transfer_list, &msg->transfers))
+			cs_change = !cs_change;
+
+		if (cs_change)
+			spi_engine_gen_cs(p, dry, spi, false);
+	}
+
+	return 0;
+}
+
+static void spi_engine_xfer_next(struct spi_engine *spi_engine,
+	struct spi_transfer **_xfer)
+{
+	struct spi_message *msg = spi_engine->msg;
+	struct spi_transfer *xfer = *_xfer;
+
+	if (!xfer) {
+		xfer = list_first_entry(&msg->transfers,
+			struct spi_transfer, transfer_list);
+	} else if (list_is_last(&xfer->transfer_list, &msg->transfers)) {
+		xfer = NULL;
+	} else {
+		xfer = list_next_entry(xfer, transfer_list);
+	}
+
+	*_xfer = xfer;
+}
+
+static void spi_engine_tx_next(struct spi_engine *spi_engine)
+{
+	struct spi_transfer *xfer = spi_engine->tx_xfer;
+
+	do {
+		spi_engine_xfer_next(spi_engine, &xfer);
+	} while (xfer && !xfer->tx_buf);
+
+	spi_engine->tx_xfer = xfer;
+	if (xfer) {
+		spi_engine->tx_length = xfer->len;
+		spi_engine->tx_buf = xfer->tx_buf;
+	} else {
+		spi_engine->tx_buf = NULL;
+	}
+}
+
+static void spi_engine_rx_next(struct spi_engine *spi_engine)
+{
+	struct spi_transfer *xfer = spi_engine->rx_xfer;
+
+	do {
+		spi_engine_xfer_next(spi_engine, &xfer);
+	} while (xfer && !xfer->rx_buf);
+
+	spi_engine->rx_xfer = xfer;
+	if (xfer) {
+		spi_engine->rx_length = xfer->len;
+		spi_engine->rx_buf = xfer->rx_buf;
+	} else {
+		spi_engine->rx_buf = NULL;
+	}
+}
+
+static bool spi_engine_write_cmd_fifo(struct spi_engine *spi_engine)
+{
+	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_CMD_FIFO;
+	unsigned int n, m, i;
+	const uint16_t *buf;
+
+	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_CMD_FIFO_ROOM);
+	while (n && spi_engine->cmd_length) {
+		m = min(n, spi_engine->cmd_length);
+		buf = spi_engine->cmd_buf;
+		for (i = 0; i < m; i++)
+			writel_relaxed(buf[i], addr);
+		spi_engine->cmd_buf += m;
+		spi_engine->cmd_length -= m;
+		n -= m;
+	}
+
+	return spi_engine->cmd_length != 0;
+}
+
+static bool spi_engine_write_tx_fifo(struct spi_engine *spi_engine)
+{
+	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDO_DATA_FIFO;
+	unsigned int n, m, i;
+	const uint8_t *buf;
+
+	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDO_FIFO_ROOM);
+	while (n && spi_engine->tx_length) {
+		m = min(n, spi_engine->tx_length);
+		buf = spi_engine->tx_buf;
+		for (i = 0; i < m; i++)
+			writel_relaxed(buf[i], addr);
+		spi_engine->tx_buf += m;
+		spi_engine->tx_length -= m;
+		n -= m;
+		if (spi_engine->tx_length == 0)
+			spi_engine_tx_next(spi_engine);
+	}
+
+	return spi_engine->tx_length != 0;
+}
+
+static bool spi_engine_read_rx_fifo(struct spi_engine *spi_engine)
+{
+	void __iomem *addr = spi_engine->base + SPI_ENGINE_REG_SDI_DATA_FIFO;
+	unsigned int n, m, i;
+	uint8_t *buf;
+
+	n = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_SDI_FIFO_LEVEL);
+	while (n && spi_engine->rx_length) {
+		m = min(n, spi_engine->rx_length);
+		buf = spi_engine->rx_buf;
+		for (i = 0; i < m; i++)
+			buf[i] = readl_relaxed(addr);
+		spi_engine->rx_buf += m;
+		spi_engine->rx_length -= m;
+		n -= m;
+		if (spi_engine->rx_length == 0)
+			spi_engine_rx_next(spi_engine);
+	}
+
+	return spi_engine->rx_length != 0;
+}
+
+static irqreturn_t spi_engine_irq(int irq, void *devid)
+{
+	struct spi_master *master = devid;
+	struct spi_engine *spi_engine = spi_master_get_devdata(master);
+	unsigned int disable_int = 0;
+	unsigned int pending;
+
+	pending = readl_relaxed(spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+
+	if (pending & SPI_ENGINE_INT_SYNC) {
+		writel_relaxed(SPI_ENGINE_INT_SYNC,
+			spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+		spi_engine->completed_id = readl_relaxed(
+			spi_engine->base + SPI_ENGINE_REG_SYNC_ID);
+	}
+
+	spin_lock(&spi_engine->lock);
+
+	if (pending & SPI_ENGINE_INT_CMD_ALMOST_EMPTY) {
+		if (!spi_engine_write_cmd_fifo(spi_engine))
+			disable_int |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY;
+	}
+
+	if (pending & SPI_ENGINE_INT_SDO_ALMOST_EMPTY) {
+		if (!spi_engine_write_tx_fifo(spi_engine))
+			disable_int |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY;
+	}
+
+	if (pending & (SPI_ENGINE_INT_SDI_ALMOST_FULL | SPI_ENGINE_INT_SYNC)) {
+		if (!spi_engine_read_rx_fifo(spi_engine))
+			disable_int |= SPI_ENGINE_INT_SDI_ALMOST_FULL;
+	}
+
+	if (pending & SPI_ENGINE_INT_SYNC) {
+		if (spi_engine->msg &&
+		    spi_engine->completed_id == spi_engine->sync_id) {
+			struct spi_message *msg = spi_engine->msg;
+
+			kfree(spi_engine->p);
+			msg->status = 0;
+			msg->actual_length = msg->frame_length;
+			spi_engine->msg = NULL;
+			spi_finalize_current_message(master);
+			disable_int |= SPI_ENGINE_INT_SYNC;
+		}
+	}
+
+	if (disable_int) {
+		spi_engine->int_enable &= ~disable_int;
+		writel_relaxed(spi_engine->int_enable,
+			spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	}
+
+	spin_unlock(&spi_engine->lock);
+
+	return IRQ_HANDLED;
+}
+
+static int spi_engine_transfer_one_message(struct spi_master *master,
+	struct spi_message *msg)
+{
+	struct spi_engine_program p_dry, *p;
+	struct spi_engine *spi_engine = spi_master_get_devdata(master);
+	unsigned int int_enable = 0;
+	unsigned long flags;
+	size_t size;
+
+	p_dry.length = 0;
+	spi_engine_compile_message(spi_engine, msg, true, &p_dry);
+
+	size = sizeof(*p->instructions) * (p_dry.length + 1);
+	p = kzalloc(sizeof(*p) + size, GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+	spi_engine_compile_message(spi_engine, msg, false, p);
+
+	spin_lock_irqsave(&spi_engine->lock, flags);
+	spi_engine->sync_id = (spi_engine->sync_id + 1) & 0xff;
+	spi_engine_program_add_cmd(p, false,
+		SPI_ENGINE_CMD_SYNC(spi_engine->sync_id));
+
+	spi_engine->msg = msg;
+	spi_engine->p = p;
+
+	spi_engine->cmd_buf = p->instructions;
+	spi_engine->cmd_length = p->length;
+	if (spi_engine_write_cmd_fifo(spi_engine))
+		int_enable |= SPI_ENGINE_INT_CMD_ALMOST_EMPTY;
+
+	spi_engine_tx_next(spi_engine);
+	if (spi_engine_write_tx_fifo(spi_engine))
+		int_enable |= SPI_ENGINE_INT_SDO_ALMOST_EMPTY;
+
+	spi_engine_rx_next(spi_engine);
+	if (spi_engine->rx_length != 0)
+		int_enable |= SPI_ENGINE_INT_SDI_ALMOST_FULL;
+
+	int_enable |= SPI_ENGINE_INT_SYNC;
+
+	writel_relaxed(int_enable,
+		spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	spi_engine->int_enable = int_enable;
+	spin_unlock_irqrestore(&spi_engine->lock, flags);
+
+	return 0;
+}
+
+static int spi_engine_probe(struct platform_device *pdev)
+{
+	struct spi_engine *spi_engine;
+	struct spi_master *master;
+	unsigned int version;
+	struct resource *res;
+	int irq;
+	int ret;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0)
+		return -ENXIO;
+
+	spi_engine = devm_kzalloc(&pdev->dev, sizeof(*spi_engine), GFP_KERNEL);
+	if (!spi_engine)
+		return -ENOMEM;
+
+	master = spi_alloc_master(&pdev->dev, 0);
+	if (!master)
+		return -ENOMEM;
+
+	spi_master_set_devdata(master, spi_engine);
+
+	spin_lock_init(&spi_engine->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	spi_engine->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(spi_engine->base)) {
+		ret = PTR_ERR(spi_engine->base);
+		goto err_put_master;
+	}
+
+	version = readl(spi_engine->base + SPI_ENGINE_REG_VERSION);
+	if (SPI_ENGINE_VERSION_MAJOR(version) != 1) {
+		dev_err(&pdev->dev, "Unsupported peripheral version %u.%u.%c\n",
+			SPI_ENGINE_VERSION_MAJOR(version),
+			SPI_ENGINE_VERSION_MINOR(version),
+			SPI_ENGINE_VERSION_PATCH(version));
+		return -ENODEV;
+	}
+
+	spi_engine->clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
+	if (IS_ERR(spi_engine->clk)) {
+		ret = PTR_ERR(spi_engine->clk);
+		goto err_put_master;
+	}
+
+	spi_engine->ref_clk = devm_clk_get(&pdev->dev, "spi_clk");
+	if (IS_ERR(spi_engine->ref_clk)) {
+		ret = PTR_ERR(spi_engine->ref_clk);
+		goto err_put_master;
+	}
+
+	ret = clk_prepare_enable(spi_engine->clk);
+	if (ret)
+		goto err_put_master;
+
+	ret = clk_prepare_enable(spi_engine->ref_clk);
+	if (ret)
+		goto err_clk_disable;
+
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_RESET);
+	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+
+	ret = request_irq(irq, spi_engine_irq, 0, pdev->name, master);
+	if (ret)
+		goto err_ref_clk_disable;
+
+	master->dev.parent = &pdev->dev;
+	master->dev.of_node = pdev->dev.of_node;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_3WIRE;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+	master->max_speed_hz = clk_get_rate(spi_engine->ref_clk) / 2;
+	master->transfer_one_message = spi_engine_transfer_one_message;
+	master->num_chipselect = 8;
+
+	ret = spi_register_master(master);
+	if (ret)
+		goto err_free_irq;
+
+	platform_set_drvdata(pdev, master);
+
+	return 0;
+err_free_irq:
+	free_irq(irq, master);
+err_ref_clk_disable:
+	clk_disable_unprepare(spi_engine->ref_clk);
+err_clk_disable:
+	clk_disable_unprepare(spi_engine->clk);
+err_put_master:
+	spi_master_put(master);
+	return ret;
+}
+
+static int spi_engine_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct spi_engine *spi_engine = spi_master_get_devdata(master);
+	int irq = platform_get_irq(pdev, 0);
+
+	spi_unregister_master(master);
+
+	free_irq(irq, master);
+
+	writel_relaxed(0xff, spi_engine->base + SPI_ENGINE_REG_INT_PENDING);
+	writel_relaxed(0x00, spi_engine->base + SPI_ENGINE_REG_INT_ENABLE);
+	writel_relaxed(0x01, spi_engine->base + SPI_ENGINE_REG_RESET);
+
+	clk_disable_unprepare(spi_engine->ref_clk);
+	clk_disable_unprepare(spi_engine->clk);
+
+	return 0;
+}
+
+static const struct of_device_id spi_engine_match_table[] = {
+	{ .compatible = "adi,axi-spi-engine-1.00.a" },
+	{ },
+};
+
+static struct platform_driver spi_engine_driver = {
+	.probe = spi_engine_probe,
+	.remove = spi_engine_remove,
+	.driver = {
+		.name = "spi-engine",
+		.of_match_table = spi_engine_match_table,
+	},
+};
+module_platform_driver(spi_engine_driver);
+
+MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
+MODULE_DESCRIPTION("Analog Devices SPI engine peripheral driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index cf04960cc3e6ca1f5a87ad24f3d88cdbcfaa8a36..f35cc10772f6670397ea923ad30158270dd68578 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -727,11 +727,6 @@ static int bcm2835_spi_setup(struct spi_device *spi)
 			spi->chip_select, spi->cs_gpio, err);
 		return err;
 	}
-	/* the implementation of pinctrl-bcm2835 currently does not
-	 * set the GPIO value when using gpio_direction_output
-	 * so we are setting it here explicitly
-	 */
-	gpio_set_value(spi->cs_gpio, (spi->mode & SPI_CS_HIGH) ? 0 : 1);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index ecc73c0a97cf5ebf0d2a6c623cf3ce1ac311e62b..7428091d3f5b8ffa77ed2a3be65a114720cb4bfa 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -64,9 +64,9 @@
 #define BCM2835_AUX_SPI_CNTL0_VAR_WIDTH	0x00004000
 #define BCM2835_AUX_SPI_CNTL0_DOUTHOLD	0x00003000
 #define BCM2835_AUX_SPI_CNTL0_ENABLE	0x00000800
-#define BCM2835_AUX_SPI_CNTL0_CPHA_IN	0x00000400
+#define BCM2835_AUX_SPI_CNTL0_IN_RISING	0x00000400
 #define BCM2835_AUX_SPI_CNTL0_CLEARFIFO	0x00000200
-#define BCM2835_AUX_SPI_CNTL0_CPHA_OUT	0x00000100
+#define BCM2835_AUX_SPI_CNTL0_OUT_RISING	0x00000100
 #define BCM2835_AUX_SPI_CNTL0_CPOL	0x00000080
 #define BCM2835_AUX_SPI_CNTL0_MSBF_OUT	0x00000040
 #define BCM2835_AUX_SPI_CNTL0_SHIFTLEN	0x0000003F
@@ -92,9 +92,6 @@
 #define BCM2835_AUX_SPI_POLLING_LIMIT_US	30
 #define BCM2835_AUX_SPI_POLLING_JIFFIES		2
 
-#define BCM2835_AUX_SPI_MODE_BITS (SPI_CPOL | SPI_CPHA | SPI_CS_HIGH \
-				  | SPI_NO_CS)
-
 struct bcm2835aux_spi {
 	void __iomem *regs;
 	struct clk *clk;
@@ -212,9 +209,15 @@ static irqreturn_t bcm2835aux_spi_interrupt(int irq, void *dev_id)
 		ret = IRQ_HANDLED;
 	}
 
-	/* and if rx_len is 0 then wake up completion and disable spi */
+	if (!bs->tx_len) {
+		/* disable tx fifo empty interrupt */
+		bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1] |
+			BCM2835_AUX_SPI_CNTL1_IDLE);
+	}
+
+	/* and if rx_len is 0 then disable interrupts and wake up completion */
 	if (!bs->rx_len) {
-		bcm2835aux_spi_reset_hw(bs);
+		bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
 		complete(&master->xfer_completion);
 	}
 
@@ -307,9 +310,6 @@ static int bcm2835aux_spi_transfer_one_poll(struct spi_master *master,
 		}
 	}
 
-	/* Transfer complete - reset SPI HW */
-	bcm2835aux_spi_reset_hw(bs);
-
 	/* and return without waiting for completion */
 	return 0;
 }
@@ -330,10 +330,6 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	 * resulting (potentially) in more interrupts when transferring
 	 * more than 12 bytes
 	 */
-	bs->cntl[0] = BCM2835_AUX_SPI_CNTL0_ENABLE |
-		      BCM2835_AUX_SPI_CNTL0_VAR_WIDTH |
-		      BCM2835_AUX_SPI_CNTL0_MSBF_OUT;
-	bs->cntl[1] = BCM2835_AUX_SPI_CNTL1_MSBF_IN;
 
 	/* set clock */
 	spi_hz = tfr->speed_hz;
@@ -348,17 +344,13 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	} else { /* the slowest we can go */
 		speed = BCM2835_AUX_SPI_CNTL0_SPEED_MAX;
 	}
+	/* mask out old speed from previous spi_transfer */
+	bs->cntl[0] &= ~(BCM2835_AUX_SPI_CNTL0_SPEED);
+	/* set the new speed */
 	bs->cntl[0] |= speed << BCM2835_AUX_SPI_CNTL0_SPEED_SHIFT;
 
 	spi_used_hz = clk_hz / (2 * (speed + 1));
 
-	/* handle all the modes */
-	if (spi->mode & SPI_CPOL)
-		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_CPOL;
-	if (spi->mode & SPI_CPHA)
-		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_CPHA_OUT |
-			       BCM2835_AUX_SPI_CNTL0_CPHA_IN;
-
 	/* set transmit buffers and length */
 	bs->tx_buf = tfr->tx_buf;
 	bs->rx_buf = tfr->rx_buf;
@@ -382,6 +374,40 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	return bcm2835aux_spi_transfer_one_irq(master, spi, tfr);
 }
 
+static int bcm2835aux_spi_prepare_message(struct spi_master *master,
+					  struct spi_message *msg)
+{
+	struct spi_device *spi = msg->spi;
+	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
+
+	bs->cntl[0] = BCM2835_AUX_SPI_CNTL0_ENABLE |
+		      BCM2835_AUX_SPI_CNTL0_VAR_WIDTH |
+		      BCM2835_AUX_SPI_CNTL0_MSBF_OUT;
+	bs->cntl[1] = BCM2835_AUX_SPI_CNTL1_MSBF_IN;
+
+	/* handle all the modes */
+	if (spi->mode & SPI_CPOL) {
+		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_CPOL;
+		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_OUT_RISING;
+	} else {
+		bs->cntl[0] |= BCM2835_AUX_SPI_CNTL0_IN_RISING;
+	}
+	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL1, bs->cntl[1]);
+	bcm2835aux_wr(bs, BCM2835_AUX_SPI_CNTL0, bs->cntl[0]);
+
+	return 0;
+}
+
+static int bcm2835aux_spi_unprepare_message(struct spi_master *master,
+					    struct spi_message *msg)
+{
+	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
+
+	bcm2835aux_spi_reset_hw(bs);
+
+	return 0;
+}
+
 static void bcm2835aux_spi_handle_err(struct spi_master *master,
 				      struct spi_message *msg)
 {
@@ -405,11 +431,13 @@ static int bcm2835aux_spi_probe(struct platform_device *pdev)
 	}
 
 	platform_set_drvdata(pdev, master);
-	master->mode_bits = BCM2835_AUX_SPI_MODE_BITS;
+	master->mode_bits = (SPI_CPOL | SPI_CS_HIGH | SPI_NO_CS);
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
 	master->num_chipselect = -1;
 	master->transfer_one = bcm2835aux_spi_transfer_one;
 	master->handle_err = bcm2835aux_spi_handle_err;
+	master->prepare_message = bcm2835aux_spi_prepare_message;
+	master->unprepare_message = bcm2835aux_spi_unprepare_message;
 	master->dev.of_node = pdev->dev.of_node;
 
 	bs = spi_master_get_devdata(master);
diff --git a/drivers/spi/spi-dw-mid.c b/drivers/spi/spi-dw-mid.c
index 9185f6c08459842e68a6292dbae6b6884d53fcde..e31971f91475b1b3d9f1b2011e0b6e4e2ae4697b 100644
--- a/drivers/spi/spi-dw-mid.c
+++ b/drivers/spi/spi-dw-mid.c
@@ -89,10 +89,10 @@ static void mid_spi_dma_exit(struct dw_spi *dws)
 	if (!dws->dma_inited)
 		return;
 
-	dmaengine_terminate_all(dws->txchan);
+	dmaengine_terminate_sync(dws->txchan);
 	dma_release_channel(dws->txchan);
 
-	dmaengine_terminate_all(dws->rxchan);
+	dmaengine_terminate_sync(dws->rxchan);
 	dma_release_channel(dws->rxchan);
 }
 
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index a6d7029a85ac8655ce44423751f2ded3b63b8816..447497e9124c922a4e3ecc20af8ab7ee91062e99 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -47,11 +47,6 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 
 	/* Get basic io resource and map it */
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!mem) {
-		dev_err(&pdev->dev, "no mem resource?\n");
-		return -EINVAL;
-	}
-
 	dws->regs = devm_ioremap_resource(&pdev->dev, mem);
 	if (IS_ERR(dws->regs)) {
 		dev_err(&pdev->dev, "SPI region map failed\n");
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index c688efa95e29b0561ac14be901cc4e4faa5aaf33..e7a19be87c38053f1742c785a7bfbf9d17113bfc 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -56,7 +56,6 @@
 
 /* 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;
@@ -86,12 +85,18 @@ struct spi_imx_devtype_data {
 
 struct spi_imx_data {
 	struct spi_bitbang bitbang;
+	struct device *dev;
 
 	struct completion xfer_done;
 	void __iomem *base;
+	unsigned long base_phys;
+
 	struct clk *clk_per;
 	struct clk *clk_ipg;
 	unsigned long spi_clk;
+	unsigned int spi_bus_clk;
+
+	unsigned int bytes_per_word;
 
 	unsigned int count;
 	void (*tx)(struct spi_imx_data *);
@@ -101,8 +106,6 @@ struct spi_imx_data {
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
 
 	/* DMA */
-	unsigned int dma_is_inited;
-	unsigned int dma_finished;
 	bool usedma;
 	u32 wml;
 	struct completion dma_rx_completion;
@@ -199,15 +202,35 @@ static unsigned int spi_imx_clkdiv_2(unsigned int fin,
 	return 7;
 }
 
+static int spi_imx_bytes_per_word(const int bpw)
+{
+	return DIV_ROUND_UP(bpw, BITS_PER_BYTE);
+}
+
 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);
+	unsigned int bpw = transfer->bits_per_word;
+
+	if (!master->dma_rx)
+		return false;
 
-	if (spi_imx->dma_is_inited && transfer->len >= spi_imx->wml &&
-	    (transfer->len % spi_imx->wml) == 0)
-		return true;
-	return false;
+	if (!bpw)
+		bpw = spi->bits_per_word;
+
+	bpw = spi_imx_bytes_per_word(bpw);
+
+	if (bpw != 1 && bpw != 2 && bpw != 4)
+		return false;
+
+	if (transfer->len < spi_imx->wml * bpw)
+		return false;
+
+	if (transfer->len % (spi_imx->wml * bpw))
+		return false;
+
+	return true;
 }
 
 #define MX51_ECSPI_CTRL		0x08
@@ -232,16 +255,13 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 #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_TX_WML(wml)	((wml) & 0x3f)
+#define MX51_ECSPI_DMA_RX_WML(wml)	(((wml) & 0x3f) << 16)
+#define MX51_ECSPI_DMA_RXT_WML(wml)	(((wml) & 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_DMA_TEDEN		(1 << 7)
+#define MX51_ECSPI_DMA_RXDEN		(1 << 23)
+#define MX51_ECSPI_DMA_RXTDEN		(1 << 31)
 
 #define MX51_ECSPI_STAT		0x18
 #define MX51_ECSPI_STAT_RR		(1 <<  3)
@@ -250,14 +270,15 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 #define MX51_ECSPI_TESTREG_LBC	BIT(31)
 
 /* MX51 eCSPI */
-static unsigned int mx51_ecspi_clkdiv(unsigned int fin, unsigned int fspi,
-				      unsigned int *fres)
+static unsigned int mx51_ecspi_clkdiv(struct spi_imx_data *spi_imx,
+				      unsigned int fspi, unsigned int *fres)
 {
 	/*
 	 * there are two 4-bit dividers, the pre-divider divides by
 	 * $pre, the post-divider by 2^$post
 	 */
 	unsigned int pre, post;
+	unsigned int fin = spi_imx->spi_clk;
 
 	if (unlikely(fspi > fin))
 		return 0;
@@ -270,14 +291,14 @@ static unsigned int mx51_ecspi_clkdiv(unsigned int fin, unsigned int fspi,
 
 	post = max(4U, post) - 4;
 	if (unlikely(post > 0xf)) {
-		pr_err("%s: cannot set clock freq: %u (base freq: %u)\n",
-				__func__, fspi, fin);
+		dev_err(spi_imx->dev, "cannot set clock freq: %u (base freq: %u)\n",
+				fspi, fin);
 		return 0xff;
 	}
 
 	pre = DIV_ROUND_UP(fin, fspi << post) - 1;
 
-	pr_debug("%s: fin: %u, fspi: %u, post: %u, pre: %u\n",
+	dev_dbg(spi_imx->dev, "%s: fin: %u, fspi: %u, post: %u, pre: %u\n",
 			__func__, fin, fspi, post, pre);
 
 	/* Resulting frequency for the SCLK line. */
@@ -302,22 +323,17 @@ 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 = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	u32 reg;
 
-	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;
+	reg = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	reg |= MX51_ECSPI_CTRL_XCH;
 	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, dma = 0;
-	u32 tx_wml_cfg, rx_wml_cfg, rxt_wml_cfg;
+	u32 ctrl = MX51_ECSPI_CTRL_ENABLE, cfg = 0;
 	u32 clk = config->speed_hz, delay, reg;
 
 	/*
@@ -330,7 +346,8 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 	ctrl |= MX51_ECSPI_CTRL_MODE_MASK;
 
 	/* set clock speed */
-	ctrl |= mx51_ecspi_clkdiv(spi_imx->spi_clk, config->speed_hz, &clk);
+	ctrl |= mx51_ecspi_clkdiv(spi_imx, config->speed_hz, &clk);
+	spi_imx->spi_bus_clk = clk;
 
 	/* set chip select to use */
 	ctrl |= MX51_ECSPI_CTRL_CS(config->cs);
@@ -341,20 +358,16 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 
 	if (config->mode & SPI_CPHA)
 		cfg |= MX51_ECSPI_CONFIG_SCLKPHA(config->cs);
-	else
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKPHA(config->cs);
 
 	if (config->mode & SPI_CPOL) {
 		cfg |= MX51_ECSPI_CONFIG_SCLKPOL(config->cs);
 		cfg |= MX51_ECSPI_CONFIG_SCLKCTL(config->cs);
-	} else {
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKPOL(config->cs);
-		cfg &= ~MX51_ECSPI_CONFIG_SCLKCTL(config->cs);
 	}
 	if (config->mode & SPI_CS_HIGH)
 		cfg |= MX51_ECSPI_CONFIG_SSBPOL(config->cs);
-	else
-		cfg &= ~MX51_ECSPI_CONFIG_SSBPOL(config->cs);
+
+	if (spi_imx->usedma)
+		ctrl |= MX51_ECSPI_CTRL_SMC;
 
 	/* CTRL register always go first to bring out controller from reset */
 	writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
@@ -389,22 +402,12 @@ static int __maybe_unused mx51_ecspi_config(struct spi_imx_data *spi_imx,
 	 * 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);
-
-		rx_wml_cfg = spi_imx->wml << MX51_ECSPI_DMA_RX_WML_OFFSET;
-		tx_wml_cfg = spi_imx->wml << MX51_ECSPI_DMA_TX_WML_OFFSET;
-		rxt_wml_cfg = spi_imx->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);
-	}
+
+	writel(MX51_ECSPI_DMA_RX_WML(spi_imx->wml) |
+		MX51_ECSPI_DMA_TX_WML(spi_imx->wml) |
+		MX51_ECSPI_DMA_RXT_WML(spi_imx->wml) |
+		MX51_ECSPI_DMA_TEDEN | MX51_ECSPI_DMA_RXDEN |
+		MX51_ECSPI_DMA_RXTDEN, spi_imx->base + MX51_ECSPI_DMA);
 
 	return 0;
 }
@@ -784,11 +787,63 @@ static irqreturn_t spi_imx_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int spi_imx_dma_configure(struct spi_master *master,
+				 int bytes_per_word)
+{
+	int ret;
+	enum dma_slave_buswidth buswidth;
+	struct dma_slave_config rx = {}, tx = {};
+	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
+
+	if (bytes_per_word == spi_imx->bytes_per_word)
+		/* Same as last time */
+		return 0;
+
+	switch (bytes_per_word) {
+	case 4:
+		buswidth = DMA_SLAVE_BUSWIDTH_4_BYTES;
+		break;
+	case 2:
+		buswidth = DMA_SLAVE_BUSWIDTH_2_BYTES;
+		break;
+	case 1:
+		buswidth = DMA_SLAVE_BUSWIDTH_1_BYTE;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	tx.direction = DMA_MEM_TO_DEV;
+	tx.dst_addr = spi_imx->base_phys + MXC_CSPITXDATA;
+	tx.dst_addr_width = buswidth;
+	tx.dst_maxburst = spi_imx->wml;
+	ret = dmaengine_slave_config(master->dma_tx, &tx);
+	if (ret) {
+		dev_err(spi_imx->dev, "TX dma configuration failed with %d\n", ret);
+		return ret;
+	}
+
+	rx.direction = DMA_DEV_TO_MEM;
+	rx.src_addr = spi_imx->base_phys + MXC_CSPIRXDATA;
+	rx.src_addr_width = buswidth;
+	rx.src_maxburst = spi_imx->wml;
+	ret = dmaengine_slave_config(master->dma_rx, &rx);
+	if (ret) {
+		dev_err(spi_imx->dev, "RX dma configuration failed with %d\n", ret);
+		return ret;
+	}
+
+	spi_imx->bytes_per_word = bytes_per_word;
+
+	return 0;
+}
+
 static int spi_imx_setupxfer(struct spi_device *spi,
 				 struct spi_transfer *t)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
 	struct spi_imx_config config;
+	int ret;
 
 	config.bpw = t ? t->bits_per_word : spi->bits_per_word;
 	config.speed_hz  = t ? t->speed_hz : spi->max_speed_hz;
@@ -812,6 +867,18 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 		spi_imx->tx = spi_imx_buf_tx_u32;
 	}
 
+	if (spi_imx_can_dma(spi_imx->bitbang.master, spi, t))
+		spi_imx->usedma = 1;
+	else
+		spi_imx->usedma = 0;
+
+	if (spi_imx->usedma) {
+		ret = spi_imx_dma_configure(spi->master,
+					    spi_imx_bytes_per_word(config.bpw));
+		if (ret)
+			return ret;
+	}
+
 	spi_imx->devtype_data->config(spi_imx, &config);
 
 	return 0;
@@ -830,15 +897,11 @@ static void spi_imx_sdma_exit(struct spi_imx_data *spi_imx)
 		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 spi_master *master)
 {
-	struct dma_slave_config slave_config = {};
 	int ret;
 
 	/* use pio mode for i.mx6dl chip TKT238285 */
@@ -856,16 +919,6 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 		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->wml;
-	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_reason(dev, "rx");
 	if (IS_ERR(master->dma_rx)) {
@@ -875,15 +928,7 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 		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->wml;
-	ret = dmaengine_slave_config(master->dma_rx, &slave_config);
-	if (ret) {
-		dev_err(dev, "error in RX dma configuration.\n");
-		goto err;
-	}
+	spi_imx_dma_configure(master, 1);
 
 	init_completion(&spi_imx->dma_rx_completion);
 	init_completion(&spi_imx->dma_tx_completion);
@@ -891,7 +936,6 @@ static int spi_imx_sdma_init(struct device *dev, struct spi_imx_data *spi_imx,
 	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:
@@ -913,95 +957,81 @@ static void spi_imx_dma_tx_callback(void *cookie)
 	complete(&spi_imx->dma_tx_completion);
 }
 
+static int spi_imx_calculate_timeout(struct spi_imx_data *spi_imx, int size)
+{
+	unsigned long timeout = 0;
+
+	/* Time with actual data transfer and CS change delay related to HW */
+	timeout = (8 + 4) * size / spi_imx->spi_bus_clk;
+
+	/* Add extra second for scheduler related activities */
+	timeout += 1;
+
+	/* Double calculated timeout */
+	return msecs_to_jiffies(2 * timeout * MSEC_PER_SEC);
+}
+
 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;
+	struct dma_async_tx_descriptor *desc_tx, *desc_rx;
+	unsigned long transfer_timeout;
 	unsigned long timeout;
 	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_MEM_TO_DEV,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-		if (!desc_tx)
-			goto tx_nodma;
-
-		desc_tx->callback = spi_imx_dma_tx_callback;
-		desc_tx->callback_param = (void *)spi_imx;
-		dmaengine_submit(desc_tx);
-	}
+	/*
+	 * The TX DMA setup starts the transfer, so make sure RX is configured
+	 * before TX.
+	 */
+	desc_rx = dmaengine_prep_slave_sg(master->dma_rx,
+				rx->sgl, rx->nents, DMA_DEV_TO_MEM,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_rx)
+		return -EINVAL;
 
-	if (rx) {
-		desc_rx = dmaengine_prep_slave_sg(master->dma_rx,
-					rx->sgl, rx->nents, DMA_DEV_TO_MEM,
-					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
-		if (!desc_rx)
-			goto rx_nodma;
+	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);
+	dma_async_issue_pending(master->dma_rx);
 
-		desc_rx->callback = spi_imx_dma_rx_callback;
-		desc_rx->callback_param = (void *)spi_imx;
-		dmaengine_submit(desc_rx);
+	desc_tx = dmaengine_prep_slave_sg(master->dma_tx,
+				tx->sgl, tx->nents, DMA_MEM_TO_DEV,
+				DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
+	if (!desc_tx) {
+		dmaengine_terminate_all(master->dma_tx);
+		return -EINVAL;
 	}
 
-	reinit_completion(&spi_imx->dma_rx_completion);
+	desc_tx->callback = spi_imx_dma_tx_callback;
+	desc_tx->callback_param = (void *)spi_imx;
+	dmaengine_submit(desc_tx);
 	reinit_completion(&spi_imx->dma_tx_completion);
-
-	/* Trigger the cspi module. */
-	spi_imx->dma_finished = 0;
-
-	/*
-	 * Set these order to avoid potential RX overflow. The overflow may
-	 * happen if we enable SPI HW before starting RX DMA due to rescheduling
-	 * for another task and/or interrupt.
-	 * So RX DMA enabled first to make sure data would be read out from FIFO
-	 * ASAP. TX DMA enabled next to start filling TX FIFO with new data.
-	 * And finaly SPI HW enabled to start actual data transfer.
-	 */
-	dma_async_issue_pending(master->dma_rx);
 	dma_async_issue_pending(master->dma_tx);
-	spi_imx->devtype_data->trigger(spi_imx);
+
+	transfer_timeout = spi_imx_calculate_timeout(spi_imx, transfer->len);
 
 	/* Wait SDMA to finish the data transfer.*/
 	timeout = wait_for_completion_timeout(&spi_imx->dma_tx_completion,
-						IMX_DMA_TIMEOUT);
+						transfer_timeout);
 	if (!timeout) {
-		pr_warn("%s %s: I/O Error in DMA TX\n",
-			dev_driver_string(&master->dev),
-			dev_name(&master->dev));
+		dev_err(spi_imx->dev, "I/O Error in DMA TX\n");
 		dmaengine_terminate_all(master->dma_tx);
 		dmaengine_terminate_all(master->dma_rx);
-	} else {
-		timeout = wait_for_completion_timeout(
-				&spi_imx->dma_rx_completion, IMX_DMA_TIMEOUT);
-		if (!timeout) {
-			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);
-		}
+		return -ETIMEDOUT;
 	}
 
-	spi_imx->dma_finished = 1;
-	spi_imx->devtype_data->trigger(spi_imx);
-
-	if (!timeout)
-		ret = -ETIMEDOUT;
-	else
-		ret = transfer->len;
-
-	return ret;
+	timeout = wait_for_completion_timeout(&spi_imx->dma_rx_completion,
+					      transfer_timeout);
+	if (!timeout) {
+		dev_err(&master->dev, "I/O Error in DMA RX\n");
+		spi_imx->devtype_data->reset(spi_imx);
+		dmaengine_terminate_all(master->dma_rx);
+		return -ETIMEDOUT;
+	}
 
-rx_nodma:
-	dmaengine_terminate_all(master->dma_tx);
-tx_nodma:
-	pr_warn_once("%s %s: DMA not available, falling back to PIO\n",
-		     dev_driver_string(&master->dev),
-		     dev_name(&master->dev));
-	return -EAGAIN;
+	return transfer->len;
 }
 
 static int spi_imx_pio_transfer(struct spi_device *spi,
@@ -1028,19 +1058,12 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 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);
+	if (spi_imx->usedma)
+		return spi_imx_dma_transfer(spi_imx, transfer);
+	else
+		return spi_imx_pio_transfer(spi, transfer);
 }
 
 static int spi_imx_setup(struct spi_device *spi)
@@ -1130,6 +1153,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 
 	spi_imx = spi_master_get_devdata(master);
 	spi_imx->bitbang.master = master;
+	spi_imx->dev = &pdev->dev;
 
 	spi_imx->devtype_data = of_id ? of_id->data :
 		(struct spi_imx_devtype_data *)pdev->id_entry->driver_data;
@@ -1170,6 +1194,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 		ret = PTR_ERR(spi_imx->base);
 		goto out_master_put;
 	}
+	spi_imx->base_phys = res->start;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
@@ -1210,7 +1235,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 	 * other chips.
 	 */
 	if (is_imx51_ecspi(spi_imx)) {
-		ret = spi_imx_sdma_init(&pdev->dev, spi_imx, master, res);
+		ret = spi_imx_sdma_init(&pdev->dev, spi_imx, master);
 		if (ret == -EPROBE_DEFER)
 			goto out_clk_put;
 
diff --git a/drivers/spi/spi-lp8841-rtc.c b/drivers/spi/spi-lp8841-rtc.c
new file mode 100644
index 0000000000000000000000000000000000000000..faa577d282c08a9e58c569b60d2c65683864d2cd
--- /dev/null
+++ b/drivers/spi/spi-lp8841-rtc.c
@@ -0,0 +1,256 @@
+/*
+ * SPI master driver for ICP DAS LP-8841 RTC
+ *
+ * Copyright (C) 2016 Sergei Ianovich
+ *
+ * based on
+ *
+ * Dallas DS1302 RTC Support
+ * Copyright (C) 2002 David McCullough
+ * Copyright (C) 2003 - 2007 Paul Mundt
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+
+#define DRIVER_NAME	"spi_lp8841_rtc"
+
+#define SPI_LP8841_RTC_CE	0x01
+#define SPI_LP8841_RTC_CLK	0x02
+#define SPI_LP8841_RTC_nWE	0x04
+#define SPI_LP8841_RTC_MOSI	0x08
+#define SPI_LP8841_RTC_MISO	0x01
+
+/*
+ * REVISIT If there is support for SPI_3WIRE and SPI_LSB_FIRST in SPI
+ * GPIO driver, this SPI driver can be replaced by a simple GPIO driver
+ * providing 3 GPIO pins.
+ */
+
+struct spi_lp8841_rtc {
+	void		*iomem;
+	unsigned long	state;
+};
+
+static inline void
+setsck(struct spi_lp8841_rtc *data, int is_on)
+{
+	if (is_on)
+		data->state |= SPI_LP8841_RTC_CLK;
+	else
+		data->state &= ~SPI_LP8841_RTC_CLK;
+	writeb(data->state, data->iomem);
+}
+
+static inline void
+setmosi(struct spi_lp8841_rtc *data, int is_on)
+{
+	if (is_on)
+		data->state |= SPI_LP8841_RTC_MOSI;
+	else
+		data->state &= ~SPI_LP8841_RTC_MOSI;
+	writeb(data->state, data->iomem);
+}
+
+static inline int
+getmiso(struct spi_lp8841_rtc *data)
+{
+	return ioread8(data->iomem) & SPI_LP8841_RTC_MISO;
+}
+
+static inline u32
+bitbang_txrx_be_cpha0_lsb(struct spi_lp8841_rtc *data,
+		unsigned usecs, unsigned cpol, unsigned flags,
+		u32 word, u8 bits)
+{
+	/* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */
+
+	u32 shift = 32 - bits;
+	/* clock starts at inactive polarity */
+	for (; likely(bits); bits--) {
+
+		/* setup LSB (to slave) on leading edge */
+		if ((flags & SPI_MASTER_NO_TX) == 0)
+			setmosi(data, (word & 1));
+
+		usleep_range(usecs, usecs + 1);	/* T(setup) */
+
+		/* sample LSB (from slave) on trailing edge */
+		word >>= 1;
+		if ((flags & SPI_MASTER_NO_RX) == 0)
+			word |= (getmiso(data) << 31);
+
+		setsck(data, !cpol);
+		usleep_range(usecs, usecs + 1);
+
+		setsck(data, cpol);
+	}
+
+	word >>= shift;
+	return word;
+}
+
+static int
+spi_lp8841_rtc_transfer_one(struct spi_master *master,
+			    struct spi_device *spi,
+			    struct spi_transfer *t)
+{
+	struct spi_lp8841_rtc	*data = spi_master_get_devdata(master);
+	unsigned		count = t->len;
+	const u8		*tx = t->tx_buf;
+	u8			*rx = t->rx_buf;
+	u8			word = 0;
+	int			ret = 0;
+
+	if (tx) {
+		data->state &= ~SPI_LP8841_RTC_nWE;
+		writeb(data->state, data->iomem);
+		while (likely(count > 0)) {
+			word = *tx++;
+			bitbang_txrx_be_cpha0_lsb(data, 1, 0,
+					SPI_MASTER_NO_RX, word, 8);
+			count--;
+		}
+	} else if (rx) {
+		data->state |= SPI_LP8841_RTC_nWE;
+		writeb(data->state, data->iomem);
+		while (likely(count > 0)) {
+			word = bitbang_txrx_be_cpha0_lsb(data, 1, 0,
+					SPI_MASTER_NO_TX, word, 8);
+			*rx++ = word;
+			count--;
+		}
+	} else {
+		ret = -EINVAL;
+	}
+
+	spi_finalize_current_transfer(master);
+
+	return ret;
+}
+
+static void
+spi_lp8841_rtc_set_cs(struct spi_device *spi, bool enable)
+{
+	struct spi_lp8841_rtc *data = spi_master_get_devdata(spi->master);
+
+	data->state = 0;
+	writeb(data->state, data->iomem);
+	if (enable) {
+		usleep_range(4, 5);
+		data->state |= SPI_LP8841_RTC_CE;
+		writeb(data->state, data->iomem);
+		usleep_range(4, 5);
+	}
+}
+
+static int
+spi_lp8841_rtc_setup(struct spi_device *spi)
+{
+	if ((spi->mode & SPI_CS_HIGH) == 0) {
+		dev_err(&spi->dev, "unsupported active low chip select\n");
+		return -EINVAL;
+	}
+
+	if ((spi->mode & SPI_LSB_FIRST) == 0) {
+		dev_err(&spi->dev, "unsupported MSB first mode\n");
+		return -EINVAL;
+	}
+
+	if ((spi->mode & SPI_3WIRE) == 0) {
+		dev_err(&spi->dev, "unsupported wiring. 3 wires required\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id spi_lp8841_rtc_dt_ids[] = {
+	{ .compatible = "icpdas,lp8841-spi-rtc" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, spi_lp8841_rtc_dt_ids);
+#endif
+
+static int
+spi_lp8841_rtc_probe(struct platform_device *pdev)
+{
+	int				ret;
+	struct spi_master		*master;
+	struct spi_lp8841_rtc		*data;
+	void				*iomem;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*data));
+	if (!master)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, master);
+
+	master->flags = SPI_MASTER_HALF_DUPLEX;
+	master->mode_bits = SPI_CS_HIGH | SPI_3WIRE | SPI_LSB_FIRST;
+
+	master->bus_num = pdev->id;
+	master->num_chipselect = 1;
+	master->setup = spi_lp8841_rtc_setup;
+	master->set_cs = spi_lp8841_rtc_set_cs;
+	master->transfer_one = spi_lp8841_rtc_transfer_one;
+	master->bits_per_word_mask = SPI_BPW_MASK(8);
+#ifdef CONFIG_OF
+	master->dev.of_node = pdev->dev.of_node;
+#endif
+
+	data = spi_master_get_devdata(master);
+
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	data->iomem = devm_ioremap_resource(&pdev->dev, iomem);
+	ret = PTR_ERR_OR_ZERO(data->iomem);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to get IO address\n");
+		goto err_put_master;
+	}
+
+	/* register with the SPI framework */
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "cannot register spi master\n");
+		goto err_put_master;
+	}
+
+	return ret;
+
+
+err_put_master:
+	spi_master_put(master);
+
+	return ret;
+}
+
+MODULE_ALIAS("platform:" DRIVER_NAME);
+
+static struct platform_driver spi_lp8841_rtc_driver = {
+	.driver = {
+		.name	= DRIVER_NAME,
+		.of_match_table = of_match_ptr(spi_lp8841_rtc_dt_ids),
+	},
+	.probe		= spi_lp8841_rtc_probe,
+};
+module_platform_driver(spi_lp8841_rtc_driver);
+
+MODULE_DESCRIPTION("SPI master driver for ICP DAS LP-8841 RTC");
+MODULE_AUTHOR("Sergei Ianovich");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 5e5fd77e27119d6ceb8d64f657884ab4ef9f3759..f7f7ba17b40e97597ae76d2f7e58fae3844ec6ef 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -346,13 +346,6 @@ struct vendor_data {
  * @clk: outgoing clock "SPICLK" for the SPI bus
  * @master: SPI framework hookup
  * @master_info: controller-specific data from machine setup
- * @kworker: thread struct for message pump
- * @kworker_task: pointer to task for message pump kworker thread
- * @pump_messages: work struct for scheduling work to the message pump
- * @queue_lock: spinlock to syncronise access to message queue
- * @queue: message queue
- * @busy: message pump is busy
- * @running: message pump is running
  * @pump_transfers: Tasklet used in Interrupt Transfer mode
  * @cur_msg: Pointer to current spi_message being processed
  * @cur_transfer: Pointer to current spi_transfer
diff --git a/drivers/spi/spi-pxa2xx-dma.c b/drivers/spi/spi-pxa2xx-dma.c
index bd8b369a343c98e0c98141295c9f73d63d65ce72..365fc22c35729372e22dee90271dc3a37820d27c 100644
--- a/drivers/spi/spi-pxa2xx-dma.c
+++ b/drivers/spi/spi-pxa2xx-dma.c
@@ -254,8 +254,8 @@ irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data)
 	if (status & SSSR_ROR) {
 		dev_err(&drv_data->pdev->dev, "FIFO overrun\n");
 
-		dmaengine_terminate_all(drv_data->rx_chan);
-		dmaengine_terminate_all(drv_data->tx_chan);
+		dmaengine_terminate_async(drv_data->rx_chan);
+		dmaengine_terminate_async(drv_data->tx_chan);
 
 		pxa2xx_spi_dma_transfer_complete(drv_data, true);
 		return IRQ_HANDLED;
@@ -331,13 +331,13 @@ int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
 void pxa2xx_spi_dma_release(struct driver_data *drv_data)
 {
 	if (drv_data->rx_chan) {
-		dmaengine_terminate_all(drv_data->rx_chan);
+		dmaengine_terminate_sync(drv_data->rx_chan);
 		dma_release_channel(drv_data->rx_chan);
 		sg_free_table(&drv_data->rx_sgt);
 		drv_data->rx_chan = NULL;
 	}
 	if (drv_data->tx_chan) {
-		dmaengine_terminate_all(drv_data->tx_chan);
+		dmaengine_terminate_sync(drv_data->tx_chan);
 		dma_release_channel(drv_data->tx_chan);
 		sg_free_table(&drv_data->tx_sgt);
 		drv_data->tx_chan = NULL;
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index d19d7f28aecb3c5ac9ca6409fc9c8e2e5f7fc180..520ed1dd57804320859bbef42fa5e15f6a487213 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -19,6 +19,7 @@ enum {
 	PORT_BSW1,
 	PORT_BSW2,
 	PORT_QUARK_X1000,
+	PORT_LPT,
 };
 
 struct pxa_spi_info {
@@ -42,6 +43,9 @@ static struct dw_dma_slave bsw1_rx_param = { .src_id = 7 };
 static struct dw_dma_slave bsw2_tx_param = { .dst_id = 8 };
 static struct dw_dma_slave bsw2_rx_param = { .src_id = 9 };
 
+static struct dw_dma_slave lpt_tx_param = { .dst_id = 0 };
+static struct dw_dma_slave lpt_rx_param = { .src_id = 1 };
+
 static bool lpss_dma_filter(struct dma_chan *chan, void *param)
 {
 	struct dw_dma_slave *dws = param;
@@ -98,6 +102,14 @@ static struct pxa_spi_info spi_info_configs[] = {
 		.num_chipselect = 1,
 		.max_clk_rate = 50000000,
 	},
+	[PORT_LPT] = {
+		.type = LPSS_LPT_SSP,
+		.port_id = 0,
+		.num_chipselect = 1,
+		.max_clk_rate = 50000000,
+		.tx_param = &lpt_tx_param,
+		.rx_param = &lpt_rx_param,
+	},
 };
 
 static int pxa2xx_spi_pci_probe(struct pci_dev *dev,
@@ -202,6 +214,7 @@ static const struct pci_device_id pxa2xx_spi_pci_devices[] = {
 	{ PCI_VDEVICE(INTEL, 0x228e), PORT_BSW0 },
 	{ PCI_VDEVICE(INTEL, 0x2290), PORT_BSW1 },
 	{ PCI_VDEVICE(INTEL, 0x22ac), PORT_BSW2 },
+	{ PCI_VDEVICE(INTEL, 0x9ce6), PORT_LPT },
 	{ },
 };
 MODULE_DEVICE_TABLE(pci, pxa2xx_spi_pci_devices);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index ab9914ad8365a6b1fb31f107dab21dac4ef94b17..85e59a406a4c01fabef55679c5ffb9b9583bd852 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -65,8 +65,6 @@ MODULE_ALIAS("platform:pxa2xx-spi");
 #define LPSS_GENERAL_REG_RXTO_HOLDOFF_DISABLE	BIT(24)
 #define LPSS_CS_CONTROL_SW_MODE			BIT(0)
 #define LPSS_CS_CONTROL_CS_HIGH			BIT(1)
-#define LPSS_CS_CONTROL_CS_SEL_SHIFT		8
-#define LPSS_CS_CONTROL_CS_SEL_MASK		(3 << LPSS_CS_CONTROL_CS_SEL_SHIFT)
 #define LPSS_CAPS_CS_EN_SHIFT			9
 #define LPSS_CAPS_CS_EN_MASK			(0xf << LPSS_CAPS_CS_EN_SHIFT)
 
@@ -82,6 +80,10 @@ struct lpss_config {
 	u32 rx_threshold;
 	u32 tx_threshold_lo;
 	u32 tx_threshold_hi;
+	/* Chip select control */
+	unsigned cs_sel_shift;
+	unsigned cs_sel_mask;
+	unsigned cs_num;
 };
 
 /* Keep these sorted with enum pxa_ssp_type */
@@ -106,6 +108,19 @@ static const struct lpss_config lpss_platforms[] = {
 		.tx_threshold_lo = 160,
 		.tx_threshold_hi = 224,
 	},
+	{	/* LPSS_BSW_SSP */
+		.offset = 0x400,
+		.reg_general = 0x08,
+		.reg_ssp = 0x0c,
+		.reg_cs_ctrl = 0x18,
+		.reg_capabilities = -1,
+		.rx_threshold = 64,
+		.tx_threshold_lo = 160,
+		.tx_threshold_hi = 224,
+		.cs_sel_shift = 2,
+		.cs_sel_mask = 1 << 2,
+		.cs_num = 2,
+	},
 	{	/* LPSS_SPT_SSP */
 		.offset = 0x200,
 		.reg_general = -1,
@@ -125,6 +140,8 @@ static const struct lpss_config lpss_platforms[] = {
 		.rx_threshold = 1,
 		.tx_threshold_lo = 16,
 		.tx_threshold_hi = 48,
+		.cs_sel_shift = 8,
+		.cs_sel_mask = 3 << 8,
 	},
 };
 
@@ -139,6 +156,7 @@ static bool is_lpss_ssp(const struct driver_data *drv_data)
 	switch (drv_data->ssp_type) {
 	case LPSS_LPT_SSP:
 	case LPSS_BYT_SSP:
+	case LPSS_BSW_SSP:
 	case LPSS_SPT_SSP:
 	case LPSS_BXT_SSP:
 		return true;
@@ -288,37 +306,50 @@ static void lpss_ssp_setup(struct driver_data *drv_data)
 	}
 }
 
+static void lpss_ssp_select_cs(struct driver_data *drv_data,
+			       const struct lpss_config *config)
+{
+	u32 value, cs;
+
+	if (!config->cs_sel_mask)
+		return;
+
+	value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
+
+	cs = drv_data->cur_msg->spi->chip_select;
+	cs <<= config->cs_sel_shift;
+	if (cs != (value & config->cs_sel_mask)) {
+		/*
+		 * When switching another chip select output active the
+		 * output must be selected first and wait 2 ssp_clk cycles
+		 * before changing state to active. Otherwise a short
+		 * glitch will occur on the previous chip select since
+		 * output select is latched but state control is not.
+		 */
+		value &= ~config->cs_sel_mask;
+		value |= cs;
+		__lpss_ssp_write_priv(drv_data,
+				      config->reg_cs_ctrl, value);
+		ndelay(1000000000 /
+		       (drv_data->master->max_speed_hz / 2));
+	}
+}
+
 static void lpss_ssp_cs_control(struct driver_data *drv_data, bool enable)
 {
 	const struct lpss_config *config;
-	u32 value, cs;
+	u32 value;
 
 	config = lpss_get_config(drv_data);
 
+	if (enable)
+		lpss_ssp_select_cs(drv_data, config);
+
 	value = __lpss_ssp_read_priv(drv_data, config->reg_cs_ctrl);
-	if (enable) {
-		cs = drv_data->cur_msg->spi->chip_select;
-		cs <<= LPSS_CS_CONTROL_CS_SEL_SHIFT;
-		if (cs != (value & LPSS_CS_CONTROL_CS_SEL_MASK)) {
-			/*
-			 * When switching another chip select output active
-			 * the output must be selected first and wait 2 ssp_clk
-			 * cycles before changing state to active. Otherwise
-			 * a short glitch will occur on the previous chip
-			 * select since output select is latched but state
-			 * control is not.
-			 */
-			value &= ~LPSS_CS_CONTROL_CS_SEL_MASK;
-			value |= cs;
-			__lpss_ssp_write_priv(drv_data,
-					      config->reg_cs_ctrl, value);
-			ndelay(1000000000 /
-			       (drv_data->master->max_speed_hz / 2));
-		}
+	if (enable)
 		value &= ~LPSS_CS_CONTROL_CS_HIGH;
-	} else {
+	else
 		value |= LPSS_CS_CONTROL_CS_HIGH;
-	}
 	__lpss_ssp_write_priv(drv_data, config->reg_cs_ctrl, value);
 }
 
@@ -496,6 +527,7 @@ static void giveback(struct driver_data *drv_data)
 {
 	struct spi_transfer* last_transfer;
 	struct spi_message *msg;
+	unsigned long timeout;
 
 	msg = drv_data->cur_msg;
 	drv_data->cur_msg = NULL;
@@ -508,6 +540,12 @@ static void giveback(struct driver_data *drv_data)
 	if (last_transfer->delay_usecs)
 		udelay(last_transfer->delay_usecs);
 
+	/* Wait until SSP becomes idle before deasserting the CS */
+	timeout = jiffies + msecs_to_jiffies(10);
+	while (pxa2xx_spi_read(drv_data, SSSR) & SSSR_BSY &&
+	       !time_after(jiffies, timeout))
+		cpu_relax();
+
 	/* Drop chip select UNLESS cs_change is true or we are returning
 	 * a message with an error, or next message is for another chip
 	 */
@@ -572,7 +610,7 @@ static void int_error_stop(struct driver_data *drv_data, const char* msg)
 
 static void int_transfer_complete(struct driver_data *drv_data)
 {
-	/* Stop SSP */
+	/* Clear and disable interrupts */
 	write_SSSR_CS(drv_data, drv_data->clear_sr);
 	reset_sccr1(drv_data);
 	if (!pxa25x_ssp_comp(drv_data))
@@ -957,8 +995,6 @@ static void pump_transfers(unsigned long data)
 	drv_data->tx_end = drv_data->tx + transfer->len;
 	drv_data->rx = transfer->rx_buf;
 	drv_data->rx_end = drv_data->rx + transfer->len;
-	drv_data->rx_dma = transfer->rx_dma;
-	drv_data->tx_dma = transfer->tx_dma;
 	drv_data->len = transfer->len;
 	drv_data->write = drv_data->tx ? chip->write : null_writer;
 	drv_data->read = drv_data->rx ? chip->read : null_reader;
@@ -1001,19 +1037,6 @@ static void pump_transfers(unsigned long data)
 					     "pump_transfers: DMA burst size reduced to match bits_per_word\n");
 	}
 
-	/* NOTE:  PXA25x_SSP _could_ use external clocking ... */
-	cr0 = pxa2xx_configure_sscr0(drv_data, clk_div, bits);
-	if (!pxa25x_ssp_comp(drv_data))
-		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
-			drv_data->master->max_speed_hz
-				/ (1 + ((cr0 & SSCR0_SCR(0xfff)) >> 8)),
-			chip->enable_dma ? "DMA" : "PIO");
-	else
-		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
-			drv_data->master->max_speed_hz / 2
-				/ (1 + ((cr0 & SSCR0_SCR(0x0ff)) >> 8)),
-			chip->enable_dma ? "DMA" : "PIO");
-
 	message->state = RUNNING_STATE;
 
 	drv_data->dma_mapped = 0;
@@ -1040,6 +1063,19 @@ static void pump_transfers(unsigned long data)
 		write_SSSR_CS(drv_data, drv_data->clear_sr);
 	}
 
+	/* NOTE:  PXA25x_SSP _could_ use external clocking ... */
+	cr0 = pxa2xx_configure_sscr0(drv_data, clk_div, bits);
+	if (!pxa25x_ssp_comp(drv_data))
+		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
+			drv_data->master->max_speed_hz
+				/ (1 + ((cr0 & SSCR0_SCR(0xfff)) >> 8)),
+			drv_data->dma_mapped ? "DMA" : "PIO");
+	else
+		dev_dbg(&message->spi->dev, "%u Hz actual, %s\n",
+			drv_data->master->max_speed_hz / 2
+				/ (1 + ((cr0 & SSCR0_SCR(0x0ff)) >> 8)),
+			drv_data->dma_mapped ? "DMA" : "PIO");
+
 	if (is_lpss_ssp(drv_data)) {
 		if ((pxa2xx_spi_read(drv_data, SSIRF) & 0xff)
 		    != chip->lpss_rx_threshold)
@@ -1166,6 +1202,7 @@ static int setup(struct spi_device *spi)
 		break;
 	case LPSS_LPT_SSP:
 	case LPSS_BYT_SSP:
+	case LPSS_BSW_SSP:
 	case LPSS_SPT_SSP:
 	case LPSS_BXT_SSP:
 		config = lpss_get_config(drv_data);
@@ -1313,7 +1350,7 @@ static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{ "INT3430", LPSS_LPT_SSP },
 	{ "INT3431", LPSS_LPT_SSP },
 	{ "80860F0E", LPSS_BYT_SSP },
-	{ "8086228E", LPSS_BYT_SSP },
+	{ "8086228E", LPSS_BSW_SSP },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match);
@@ -1347,10 +1384,14 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	/* SPT-H */
 	{ PCI_VDEVICE(INTEL, 0xa129), LPSS_SPT_SSP },
 	{ PCI_VDEVICE(INTEL, 0xa12a), LPSS_SPT_SSP },
-	/* BXT */
+	/* BXT A-Step */
 	{ PCI_VDEVICE(INTEL, 0x0ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x0ac4), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x0ac6), LPSS_BXT_SSP },
+	/* BXT B-Step */
+	{ PCI_VDEVICE(INTEL, 0x1ac2), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x1ac4), LPSS_BXT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x1ac6), LPSS_BXT_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
@@ -1438,6 +1479,29 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 }
 #endif
 
+static int pxa2xx_spi_fw_translate_cs(struct spi_master *master, unsigned cs)
+{
+	struct driver_data *drv_data = spi_master_get_devdata(master);
+
+	if (has_acpi_companion(&drv_data->pdev->dev)) {
+		switch (drv_data->ssp_type) {
+		/*
+		 * For Atoms the ACPI DeviceSelection used by the Windows
+		 * driver starts from 1 instead of 0 so translate it here
+		 * to match what Linux expects.
+		 */
+		case LPSS_BYT_SSP:
+		case LPSS_BSW_SSP:
+			return cs - 1;
+
+		default:
+			break;
+		}
+	}
+
+	return cs;
+}
+
 static int pxa2xx_spi_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1490,6 +1554,7 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	master->setup = setup;
 	master->transfer_one_message = pxa2xx_spi_transfer_one_message;
 	master->unprepare_transfer_hardware = pxa2xx_spi_unprepare_transfer;
+	master->fw_translate_cs = pxa2xx_spi_fw_translate_cs;
 	master->auto_runtime_pm = true;
 
 	drv_data->ssp_type = ssp->type;
@@ -1576,6 +1641,8 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 			tmp &= LPSS_CAPS_CS_EN_MASK;
 			tmp >>= LPSS_CAPS_CS_EN_SHIFT;
 			platform_info->num_chipselect = ffz(tmp);
+		} else if (config->cs_num) {
+			platform_info->num_chipselect = config->cs_num;
 		}
 	}
 	master->num_chipselect = platform_info->num_chipselect;
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 58efa98313aa0bf5c2aca5d8458032fac566a0eb..a1ef889481447fd4eeeca749bba063014bddc3f6 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -69,8 +69,6 @@ struct driver_data {
 	void *rx;
 	void *rx_end;
 	int dma_mapped;
-	dma_addr_t rx_dma;
-	dma_addr_t tx_dma;
 	size_t rx_map_len;
 	size_t tx_map_len;
 	u8 n_bytes;
@@ -147,20 +145,9 @@ static inline void write_SSSR_CS(struct driver_data *drv_data, u32 val)
 extern int pxa2xx_spi_flush(struct driver_data *drv_data);
 extern void *pxa2xx_spi_next_transfer(struct driver_data *drv_data);
 
-/*
- * Select the right DMA implementation.
- */
-#if defined(CONFIG_SPI_PXA2XX_DMA)
-#define SPI_PXA2XX_USE_DMA	1
 #define MAX_DMA_LEN		SZ_64K
 #define DEFAULT_DMA_CR1		(SSCR1_TSRE | SSCR1_RSRE | SSCR1_TRAIL)
-#else
-#undef SPI_PXA2XX_USE_DMA
-#define MAX_DMA_LEN		0
-#define DEFAULT_DMA_CR1		0
-#endif
 
-#ifdef SPI_PXA2XX_USE_DMA
 extern bool pxa2xx_spi_dma_is_possible(size_t len);
 extern int pxa2xx_spi_map_dma_buffers(struct driver_data *drv_data);
 extern irqreturn_t pxa2xx_spi_dma_transfer(struct driver_data *drv_data);
@@ -173,29 +160,5 @@ extern int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
 						  u8 bits_per_word,
 						  u32 *burst_code,
 						  u32 *threshold);
-#else
-static inline bool pxa2xx_spi_dma_is_possible(size_t len) { return false; }
-static inline int pxa2xx_spi_map_dma_buffers(struct driver_data *drv_data)
-{
-	return 0;
-}
-#define pxa2xx_spi_dma_transfer NULL
-static inline void pxa2xx_spi_dma_prepare(struct driver_data *drv_data,
-					  u32 dma_burst) {}
-static inline void pxa2xx_spi_dma_start(struct driver_data *drv_data) {}
-static inline int pxa2xx_spi_dma_setup(struct driver_data *drv_data)
-{
-	return 0;
-}
-static inline void pxa2xx_spi_dma_release(struct driver_data *drv_data) {}
-static inline int pxa2xx_spi_set_dma_burst_and_threshold(struct chip_data *chip,
-							 struct spi_device *spi,
-							 u8 bits_per_word,
-							 u32 *burst_code,
-							 u32 *threshold)
-{
-	return -ENODEV;
-}
-#endif
 
 #endif /* SPI_PXA2XX_H */
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 7cb1b2d710c10f7aab6c245a31d34e5439dfcbf0..26e2688c104ec9e6ba314264b63318a65048596f 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -13,20 +13,14 @@
  *
  */
 
-#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/dmaengine.h>
+#include <linux/module.h>
+#include <linux/of.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>
+#include <linux/scatterlist.h>
 
 #define DRIVER_NAME "rockchip-spi"
 
@@ -179,7 +173,7 @@ struct rockchip_spi {
 	u8 tmode;
 	u8 bpw;
 	u8 n_bytes;
-	u8 rsd_nsecs;
+	u32 rsd_nsecs;
 	unsigned len;
 	u32 speed;
 
@@ -192,8 +186,6 @@ struct rockchip_spi {
 	/* protect state */
 	spinlock_t lock;
 
-	struct completion xfer_completion;
-
 	u32 use_dma;
 	struct sg_table tx_sg;
 	struct sg_table rx_sg;
@@ -265,7 +257,10 @@ static inline u32 rx_max(struct rockchip_spi *rs)
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	u32 ser;
-	struct rockchip_spi *rs = spi_master_get_devdata(spi->master);
+	struct spi_master *master = spi->master;
+	struct rockchip_spi *rs = spi_master_get_devdata(master);
+
+	pm_runtime_get_sync(rs->dev);
 
 	ser = readl_relaxed(rs->regs + ROCKCHIP_SPI_SER) & SER_MASK;
 
@@ -290,6 +285,8 @@ static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
 		ser &= ~(1 << spi->chip_select);
 
 	writel_relaxed(ser, rs->regs + ROCKCHIP_SPI_SER);
+
+	pm_runtime_put_sync(rs->dev);
 }
 
 static int rockchip_spi_prepare_message(struct spi_master *master,
@@ -319,12 +316,12 @@ static void rockchip_spi_handle_err(struct spi_master *master,
 	 */
 	if (rs->use_dma) {
 		if (rs->state & RXBUSY) {
-			dmaengine_terminate_all(rs->dma_rx.ch);
+			dmaengine_terminate_async(rs->dma_rx.ch);
 			flush_fifo(rs);
 		}
 
 		if (rs->state & TXBUSY)
-			dmaengine_terminate_all(rs->dma_tx.ch);
+			dmaengine_terminate_async(rs->dma_tx.ch);
 	}
 
 	spin_unlock_irqrestore(&rs->lock, flags);
@@ -433,7 +430,7 @@ static void rockchip_spi_dma_txcb(void *data)
 	spin_unlock_irqrestore(&rs->lock, flags);
 }
 
-static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
+static int rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 {
 	unsigned long flags;
 	struct dma_slave_config rxconf, txconf;
@@ -456,6 +453,8 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 				rs->dma_rx.ch,
 				rs->rx_sg.sgl, rs->rx_sg.nents,
 				rs->dma_rx.direction, DMA_PREP_INTERRUPT);
+		if (!rxdesc)
+			return -EINVAL;
 
 		rxdesc->callback = rockchip_spi_dma_rxcb;
 		rxdesc->callback_param = rs;
@@ -473,6 +472,11 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 				rs->dma_tx.ch,
 				rs->tx_sg.sgl, rs->tx_sg.nents,
 				rs->dma_tx.direction, DMA_PREP_INTERRUPT);
+		if (!txdesc) {
+			if (rxdesc)
+				dmaengine_terminate_sync(rs->dma_rx.ch);
+			return -EINVAL;
+		}
 
 		txdesc->callback = rockchip_spi_dma_txcb;
 		txdesc->callback_param = rs;
@@ -494,6 +498,8 @@ static void rockchip_spi_prepare_dma(struct rockchip_spi *rs)
 		dmaengine_submit(txdesc);
 		dma_async_issue_pending(rs->dma_tx.ch);
 	}
+
+	return 0;
 }
 
 static void rockchip_spi_config(struct rockchip_spi *rs)
@@ -503,7 +509,8 @@ static void rockchip_spi_config(struct rockchip_spi *rs)
 	int rsd = 0;
 
 	u32 cr0 = (CR0_BHT_8BIT << CR0_BHT_OFFSET)
-		| (CR0_SSD_ONE << CR0_SSD_OFFSET);
+		| (CR0_SSD_ONE << CR0_SSD_OFFSET)
+		| (CR0_EM_BIG << CR0_EM_OFFSET);
 
 	cr0 |= (rs->n_bytes << CR0_DFS_OFFSET);
 	cr0 |= ((rs->mode & 0x3) << CR0_SCPH_OFFSET);
@@ -606,12 +613,12 @@ static int rockchip_spi_transfer_one(
 	if (rs->use_dma) {
 		if (rs->tmode == CR0_XFM_RO) {
 			/* rx: dma must be prepared first */
-			rockchip_spi_prepare_dma(rs);
+			ret = rockchip_spi_prepare_dma(rs);
 			spi_enable_chip(rs, 1);
 		} else {
 			/* tx or tr: spi must be enabled first */
 			spi_enable_chip(rs, 1);
-			rockchip_spi_prepare_dma(rs);
+			ret = rockchip_spi_prepare_dma(rs);
 		}
 	} else {
 		spi_enable_chip(rs, 1);
@@ -717,8 +724,14 @@ static int rockchip_spi_probe(struct platform_device *pdev)
 	master->handle_err = rockchip_spi_handle_err;
 
 	rs->dma_tx.ch = dma_request_slave_channel(rs->dev, "tx");
-	if (!rs->dma_tx.ch)
+	if (IS_ERR_OR_NULL(rs->dma_tx.ch)) {
+		/* Check tx to see if we need defer probing driver */
+		if (PTR_ERR(rs->dma_tx.ch) == -EPROBE_DEFER) {
+			ret = -EPROBE_DEFER;
+			goto err_get_fifo_len;
+		}
 		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) {
@@ -871,6 +884,7 @@ static const struct of_device_id rockchip_spi_dt_match[] = {
 	{ .compatible = "rockchip,rk3066-spi", },
 	{ .compatible = "rockchip,rk3188-spi", },
 	{ .compatible = "rockchip,rk3288-spi", },
+	{ .compatible = "rockchip,rk3399-spi", },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, rockchip_spi_dt_match);
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 64318fcfacf275c989ebe19d157eb8ff9e523ebf..eac3c960b2decb8c4aa73f73894b16ac3021beba 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -31,6 +31,8 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/pinctrl/consumer.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include <linux/spi/spi.h>
 
@@ -44,8 +46,9 @@ struct ti_qspi {
 
 	struct spi_master	*master;
 	void __iomem            *base;
-	void __iomem            *ctrl_base;
 	void __iomem            *mmap_base;
+	struct regmap		*ctrl_base;
+	unsigned int		ctrl_reg;
 	struct clk		*fclk;
 	struct device           *dev;
 
@@ -55,7 +58,7 @@ struct ti_qspi {
 	u32 cmd;
 	u32 dc;
 
-	bool ctrl_mod;
+	bool mmap_enabled;
 };
 
 #define QSPI_PID			(0x0)
@@ -65,11 +68,8 @@ struct ti_qspi {
 #define QSPI_SPI_CMD_REG		(0x48)
 #define QSPI_SPI_STATUS_REG		(0x4c)
 #define QSPI_SPI_DATA_REG		(0x50)
-#define QSPI_SPI_SETUP0_REG		(0x54)
+#define QSPI_SPI_SETUP_REG(n)		((0x54 + 4 * n))
 #define QSPI_SPI_SWITCH_REG		(0x64)
-#define QSPI_SPI_SETUP1_REG		(0x58)
-#define QSPI_SPI_SETUP2_REG		(0x5c)
-#define QSPI_SPI_SETUP3_REG		(0x60)
 #define QSPI_SPI_DATA_REG_1		(0x68)
 #define QSPI_SPI_DATA_REG_2		(0x6c)
 #define QSPI_SPI_DATA_REG_3		(0x70)
@@ -109,6 +109,17 @@ struct ti_qspi {
 
 #define QSPI_AUTOSUSPEND_TIMEOUT         2000
 
+#define MEM_CS_EN(n)			((n + 1) << 8)
+#define MEM_CS_MASK			(7 << 8)
+
+#define MM_SWITCH			0x1
+
+#define QSPI_SETUP_RD_NORMAL		(0x0 << 12)
+#define QSPI_SETUP_RD_DUAL		(0x1 << 12)
+#define QSPI_SETUP_RD_QUAD		(0x3 << 12)
+#define QSPI_SETUP_ADDR_SHIFT		8
+#define QSPI_SETUP_DUMMY_SHIFT		10
+
 static inline unsigned long ti_qspi_read(struct ti_qspi *qspi,
 		unsigned long reg)
 {
@@ -366,6 +377,72 @@ static int qspi_transfer_msg(struct ti_qspi *qspi, struct spi_transfer *t)
 	return 0;
 }
 
+static void ti_qspi_enable_memory_map(struct spi_device *spi)
+{
+	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+
+	ti_qspi_write(qspi, MM_SWITCH, QSPI_SPI_SWITCH_REG);
+	if (qspi->ctrl_base) {
+		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
+				   MEM_CS_EN(spi->chip_select),
+				   MEM_CS_MASK);
+	}
+	qspi->mmap_enabled = true;
+}
+
+static void ti_qspi_disable_memory_map(struct spi_device *spi)
+{
+	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+
+	ti_qspi_write(qspi, 0, QSPI_SPI_SWITCH_REG);
+	if (qspi->ctrl_base)
+		regmap_update_bits(qspi->ctrl_base, qspi->ctrl_reg,
+				   0, MEM_CS_MASK);
+	qspi->mmap_enabled = false;
+}
+
+static void ti_qspi_setup_mmap_read(struct spi_device *spi,
+				    struct spi_flash_read_message *msg)
+{
+	struct ti_qspi  *qspi = spi_master_get_devdata(spi->master);
+	u32 memval = msg->read_opcode;
+
+	switch (msg->data_nbits) {
+	case SPI_NBITS_QUAD:
+		memval |= QSPI_SETUP_RD_QUAD;
+		break;
+	case SPI_NBITS_DUAL:
+		memval |= QSPI_SETUP_RD_DUAL;
+		break;
+	default:
+		memval |= QSPI_SETUP_RD_NORMAL;
+		break;
+	}
+	memval |= ((msg->addr_width - 1) << QSPI_SETUP_ADDR_SHIFT |
+		   msg->dummy_bytes << QSPI_SETUP_DUMMY_SHIFT);
+	ti_qspi_write(qspi, memval,
+		      QSPI_SPI_SETUP_REG(spi->chip_select));
+}
+
+static int ti_qspi_spi_flash_read(struct  spi_device *spi,
+				  struct spi_flash_read_message *msg)
+{
+	struct ti_qspi *qspi = spi_master_get_devdata(spi->master);
+	int ret = 0;
+
+	mutex_lock(&qspi->list_lock);
+
+	if (!qspi->mmap_enabled)
+		ti_qspi_enable_memory_map(spi);
+	ti_qspi_setup_mmap_read(spi, msg);
+	memcpy_fromio(msg->buf, qspi->mmap_base + msg->from, msg->len);
+	msg->retlen = msg->len;
+
+	mutex_unlock(&qspi->list_lock);
+
+	return ret;
+}
+
 static int ti_qspi_start_transfer_one(struct spi_master *master,
 		struct spi_message *m)
 {
@@ -398,6 +475,9 @@ static int ti_qspi_start_transfer_one(struct spi_master *master,
 
 	mutex_lock(&qspi->list_lock);
 
+	if (qspi->mmap_enabled)
+		ti_qspi_disable_memory_map(spi);
+
 	list_for_each_entry(t, &m->transfers, transfer_list) {
 		qspi->cmd |= QSPI_WLEN(t->bits_per_word);
 
@@ -441,7 +521,7 @@ static int ti_qspi_probe(struct platform_device *pdev)
 {
 	struct  ti_qspi *qspi;
 	struct spi_master *master;
-	struct resource         *r, *res_ctrl, *res_mmap;
+	struct resource         *r, *res_mmap;
 	struct device_node *np = pdev->dev.of_node;
 	u32 max_freq;
 	int ret = 0, num_cs, irq;
@@ -487,16 +567,6 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		}
 	}
 
-	res_ctrl = platform_get_resource_byname(pdev,
-			IORESOURCE_MEM, "qspi_ctrlmod");
-	if (res_ctrl == NULL) {
-		res_ctrl = platform_get_resource(pdev, IORESOURCE_MEM, 2);
-		if (res_ctrl == NULL) {
-			dev_dbg(&pdev->dev,
-				"control module resources not required\n");
-		}
-	}
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "no irq resource?\n");
@@ -511,20 +581,31 @@ static int ti_qspi_probe(struct platform_device *pdev)
 		goto free_master;
 	}
 
-	if (res_ctrl) {
-		qspi->ctrl_mod = true;
-		qspi->ctrl_base = devm_ioremap_resource(&pdev->dev, res_ctrl);
-		if (IS_ERR(qspi->ctrl_base)) {
-			ret = PTR_ERR(qspi->ctrl_base);
-			goto free_master;
-		}
-	}
-
 	if (res_mmap) {
-		qspi->mmap_base = devm_ioremap_resource(&pdev->dev, res_mmap);
+		qspi->mmap_base = devm_ioremap_resource(&pdev->dev,
+							res_mmap);
+		master->spi_flash_read = ti_qspi_spi_flash_read;
 		if (IS_ERR(qspi->mmap_base)) {
-			ret = PTR_ERR(qspi->mmap_base);
-			goto free_master;
+			dev_err(&pdev->dev,
+				"falling back to PIO mode\n");
+			master->spi_flash_read = NULL;
+		}
+	}
+	qspi->mmap_enabled = false;
+
+	if (of_property_read_bool(np, "syscon-chipselects")) {
+		qspi->ctrl_base =
+		syscon_regmap_lookup_by_phandle(np,
+						"syscon-chipselects");
+		if (IS_ERR(qspi->ctrl_base))
+			return PTR_ERR(qspi->ctrl_base);
+		ret = of_property_read_u32_index(np,
+						 "syscon-chipselects",
+						 1, &qspi->ctrl_reg);
+		if (ret) {
+			dev_err(&pdev->dev,
+				"couldn't get ctrl_mod reg index\n");
+			return ret;
 		}
 	}
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 47eff8012a7715c362eb3ac3e706f8a9ea6e71c2..de2f2f90d7995a52ce4f803cf41ba32992e2664b 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -144,6 +144,8 @@ SPI_STATISTICS_TRANSFER_BYTES_HISTO(14, "16384-32767");
 SPI_STATISTICS_TRANSFER_BYTES_HISTO(15, "32768-65535");
 SPI_STATISTICS_TRANSFER_BYTES_HISTO(16, "65536+");
 
+SPI_STATISTICS_SHOW(transfers_split_maxsize, "%lu");
+
 static struct attribute *spi_dev_attrs[] = {
 	&dev_attr_modalias.attr,
 	NULL,
@@ -181,6 +183,7 @@ static struct attribute *spi_device_statistics_attrs[] = {
 	&dev_attr_spi_device_transfer_bytes_histo14.attr,
 	&dev_attr_spi_device_transfer_bytes_histo15.attr,
 	&dev_attr_spi_device_transfer_bytes_histo16.attr,
+	&dev_attr_spi_device_transfers_split_maxsize.attr,
 	NULL,
 };
 
@@ -223,6 +226,7 @@ static struct attribute *spi_master_statistics_attrs[] = {
 	&dev_attr_spi_master_transfer_bytes_histo14.attr,
 	&dev_attr_spi_master_transfer_bytes_histo15.attr,
 	&dev_attr_spi_master_transfer_bytes_histo16.attr,
+	&dev_attr_spi_master_transfers_split_maxsize.attr,
 	NULL,
 };
 
@@ -702,6 +706,7 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 		       enum dma_data_direction dir)
 {
 	const bool vmalloced_buf = is_vmalloc_addr(buf);
+	unsigned int max_seg_size = dma_get_max_seg_size(dev);
 	int desc_len;
 	int sgs;
 	struct page *vm_page;
@@ -710,10 +715,10 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 	int i, ret;
 
 	if (vmalloced_buf) {
-		desc_len = PAGE_SIZE;
+		desc_len = min_t(int, max_seg_size, PAGE_SIZE);
 		sgs = DIV_ROUND_UP(len + offset_in_page(buf), desc_len);
 	} else {
-		desc_len = master->max_dma_len;
+		desc_len = min_t(int, max_seg_size, master->max_dma_len);
 		sgs = DIV_ROUND_UP(len, desc_len);
 	}
 
@@ -739,7 +744,6 @@ static int spi_map_buf(struct spi_master *master, struct device *dev,
 			sg_set_buf(&sgt->sgl[i], sg_buf, min);
 		}
 
-
 		buf += min;
 		len -= min;
 	}
@@ -1024,6 +1028,8 @@ static int spi_transfer_one_message(struct spi_master *master,
 	if (msg->status && master->handle_err)
 		master->handle_err(master, msg);
 
+	spi_res_release(master, msg);
+
 	spi_finalize_current_message(master);
 
 	return ret;
@@ -1047,6 +1053,7 @@ EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
  * __spi_pump_messages - function which processes spi message queue
  * @master: master to process queue for
  * @in_kthread: true if we are in the context of the message pump thread
+ * @bus_locked: true if the bus mutex is held when calling this function
  *
  * This function checks if there is any spi message in the queue that
  * needs processing and if so call out to the driver to initialize hardware
@@ -1056,7 +1063,8 @@ EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
  * inside spi_sync(); the queue extraction handling at the top of the
  * function should deal with this safely.
  */
-static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
+static void __spi_pump_messages(struct spi_master *master, bool in_kthread,
+				bool bus_locked)
 {
 	unsigned long flags;
 	bool was_busy = false;
@@ -1152,6 +1160,9 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 		}
 	}
 
+	if (!bus_locked)
+		mutex_lock(&master->bus_lock_mutex);
+
 	trace_spi_message_start(master->cur_msg);
 
 	if (master->prepare_message) {
@@ -1161,7 +1172,7 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 				"failed to prepare message: %d\n", ret);
 			master->cur_msg->status = ret;
 			spi_finalize_current_message(master);
-			return;
+			goto out;
 		}
 		master->cur_msg_prepared = true;
 	}
@@ -1170,15 +1181,23 @@ static void __spi_pump_messages(struct spi_master *master, bool in_kthread)
 	if (ret) {
 		master->cur_msg->status = ret;
 		spi_finalize_current_message(master);
-		return;
+		goto out;
 	}
 
 	ret = master->transfer_one_message(master, master->cur_msg);
 	if (ret) {
 		dev_err(&master->dev,
 			"failed to transfer one message from queue\n");
-		return;
+		goto out;
 	}
+
+out:
+	if (!bus_locked)
+		mutex_unlock(&master->bus_lock_mutex);
+
+	/* Prod the scheduler in case transfer_one() was busy waiting */
+	if (!ret)
+		cond_resched();
 }
 
 /**
@@ -1190,7 +1209,7 @@ static void spi_pump_messages(struct kthread_work *work)
 	struct spi_master *master =
 		container_of(work, struct spi_master, pump_messages);
 
-	__spi_pump_messages(master, true);
+	__spi_pump_messages(master, true, false);
 }
 
 static int spi_init_queue(struct spi_master *master)
@@ -1581,13 +1600,30 @@ static void of_register_spi_devices(struct spi_master *master) { }
 static int acpi_spi_add_resource(struct acpi_resource *ares, void *data)
 {
 	struct spi_device *spi = data;
+	struct spi_master *master = spi->master;
 
 	if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) {
 		struct acpi_resource_spi_serialbus *sb;
 
 		sb = &ares->data.spi_serial_bus;
 		if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_SPI) {
-			spi->chip_select = sb->device_selection;
+			/*
+			 * ACPI DeviceSelection numbering is handled by the
+			 * host controller driver in Windows and can vary
+			 * from driver to driver. In Linux we always expect
+			 * 0 .. max - 1 so we need to ask the driver to
+			 * translate between the two schemes.
+			 */
+			if (master->fw_translate_cs) {
+				int cs = master->fw_translate_cs(master,
+						sb->device_selection);
+				if (cs < 0)
+					return cs;
+				spi->chip_select = cs;
+			} else {
+				spi->chip_select = sb->device_selection;
+			}
+
 			spi->max_speed_hz = sb->connection_speed;
 
 			if (sb->clock_phase == ACPI_SPI_SECOND_PHASE)
@@ -2013,6 +2049,336 @@ struct spi_master *spi_busnum_to_master(u16 bus_num)
 }
 EXPORT_SYMBOL_GPL(spi_busnum_to_master);
 
+/*-------------------------------------------------------------------------*/
+
+/* Core methods for SPI resource management */
+
+/**
+ * spi_res_alloc - allocate a spi resource that is life-cycle managed
+ *                 during the processing of a spi_message while using
+ *                 spi_transfer_one
+ * @spi:     the spi device for which we allocate memory
+ * @release: the release code to execute for this resource
+ * @size:    size to alloc and return
+ * @gfp:     GFP allocation flags
+ *
+ * Return: the pointer to the allocated data
+ *
+ * This may get enhanced in the future to allocate from a memory pool
+ * of the @spi_device or @spi_master to avoid repeated allocations.
+ */
+void *spi_res_alloc(struct spi_device *spi,
+		    spi_res_release_t release,
+		    size_t size, gfp_t gfp)
+{
+	struct spi_res *sres;
+
+	sres = kzalloc(sizeof(*sres) + size, gfp);
+	if (!sres)
+		return NULL;
+
+	INIT_LIST_HEAD(&sres->entry);
+	sres->release = release;
+
+	return sres->data;
+}
+EXPORT_SYMBOL_GPL(spi_res_alloc);
+
+/**
+ * spi_res_free - free an spi resource
+ * @res: pointer to the custom data of a resource
+ *
+ */
+void spi_res_free(void *res)
+{
+	struct spi_res *sres = container_of(res, struct spi_res, data);
+
+	if (!res)
+		return;
+
+	WARN_ON(!list_empty(&sres->entry));
+	kfree(sres);
+}
+EXPORT_SYMBOL_GPL(spi_res_free);
+
+/**
+ * spi_res_add - add a spi_res to the spi_message
+ * @message: the spi message
+ * @res:     the spi_resource
+ */
+void spi_res_add(struct spi_message *message, void *res)
+{
+	struct spi_res *sres = container_of(res, struct spi_res, data);
+
+	WARN_ON(!list_empty(&sres->entry));
+	list_add_tail(&sres->entry, &message->resources);
+}
+EXPORT_SYMBOL_GPL(spi_res_add);
+
+/**
+ * spi_res_release - release all spi resources for this message
+ * @master:  the @spi_master
+ * @message: the @spi_message
+ */
+void spi_res_release(struct spi_master *master,
+		     struct spi_message *message)
+{
+	struct spi_res *res;
+
+	while (!list_empty(&message->resources)) {
+		res = list_last_entry(&message->resources,
+				      struct spi_res, entry);
+
+		if (res->release)
+			res->release(master, message, res->data);
+
+		list_del(&res->entry);
+
+		kfree(res);
+	}
+}
+EXPORT_SYMBOL_GPL(spi_res_release);
+
+/*-------------------------------------------------------------------------*/
+
+/* Core methods for spi_message alterations */
+
+static void __spi_replace_transfers_release(struct spi_master *master,
+					    struct spi_message *msg,
+					    void *res)
+{
+	struct spi_replaced_transfers *rxfer = res;
+	size_t i;
+
+	/* call extra callback if requested */
+	if (rxfer->release)
+		rxfer->release(master, msg, res);
+
+	/* insert replaced transfers back into the message */
+	list_splice(&rxfer->replaced_transfers, rxfer->replaced_after);
+
+	/* remove the formerly inserted entries */
+	for (i = 0; i < rxfer->inserted; i++)
+		list_del(&rxfer->inserted_transfers[i].transfer_list);
+}
+
+/**
+ * spi_replace_transfers - replace transfers with several transfers
+ *                         and register change with spi_message.resources
+ * @msg:           the spi_message we work upon
+ * @xfer_first:    the first spi_transfer we want to replace
+ * @remove:        number of transfers to remove
+ * @insert:        the number of transfers we want to insert instead
+ * @release:       extra release code necessary in some circumstances
+ * @extradatasize: extra data to allocate (with alignment guarantees
+ *                 of struct @spi_transfer)
+ * @gfp:           gfp flags
+ *
+ * Returns: pointer to @spi_replaced_transfers,
+ *          PTR_ERR(...) in case of errors.
+ */
+struct spi_replaced_transfers *spi_replace_transfers(
+	struct spi_message *msg,
+	struct spi_transfer *xfer_first,
+	size_t remove,
+	size_t insert,
+	spi_replaced_release_t release,
+	size_t extradatasize,
+	gfp_t gfp)
+{
+	struct spi_replaced_transfers *rxfer;
+	struct spi_transfer *xfer;
+	size_t i;
+
+	/* allocate the structure using spi_res */
+	rxfer = spi_res_alloc(msg->spi, __spi_replace_transfers_release,
+			      insert * sizeof(struct spi_transfer)
+			      + sizeof(struct spi_replaced_transfers)
+			      + extradatasize,
+			      gfp);
+	if (!rxfer)
+		return ERR_PTR(-ENOMEM);
+
+	/* the release code to invoke before running the generic release */
+	rxfer->release = release;
+
+	/* assign extradata */
+	if (extradatasize)
+		rxfer->extradata =
+			&rxfer->inserted_transfers[insert];
+
+	/* init the replaced_transfers list */
+	INIT_LIST_HEAD(&rxfer->replaced_transfers);
+
+	/* assign the list_entry after which we should reinsert
+	 * the @replaced_transfers - it may be spi_message.messages!
+	 */
+	rxfer->replaced_after = xfer_first->transfer_list.prev;
+
+	/* remove the requested number of transfers */
+	for (i = 0; i < remove; i++) {
+		/* if the entry after replaced_after it is msg->transfers
+		 * then we have been requested to remove more transfers
+		 * than are in the list
+		 */
+		if (rxfer->replaced_after->next == &msg->transfers) {
+			dev_err(&msg->spi->dev,
+				"requested to remove more spi_transfers than are available\n");
+			/* insert replaced transfers back into the message */
+			list_splice(&rxfer->replaced_transfers,
+				    rxfer->replaced_after);
+
+			/* free the spi_replace_transfer structure */
+			spi_res_free(rxfer);
+
+			/* and return with an error */
+			return ERR_PTR(-EINVAL);
+		}
+
+		/* remove the entry after replaced_after from list of
+		 * transfers and add it to list of replaced_transfers
+		 */
+		list_move_tail(rxfer->replaced_after->next,
+			       &rxfer->replaced_transfers);
+	}
+
+	/* create copy of the given xfer with identical settings
+	 * based on the first transfer to get removed
+	 */
+	for (i = 0; i < insert; i++) {
+		/* we need to run in reverse order */
+		xfer = &rxfer->inserted_transfers[insert - 1 - i];
+
+		/* copy all spi_transfer data */
+		memcpy(xfer, xfer_first, sizeof(*xfer));
+
+		/* add to list */
+		list_add(&xfer->transfer_list, rxfer->replaced_after);
+
+		/* clear cs_change and delay_usecs for all but the last */
+		if (i) {
+			xfer->cs_change = false;
+			xfer->delay_usecs = 0;
+		}
+	}
+
+	/* set up inserted */
+	rxfer->inserted = insert;
+
+	/* and register it with spi_res/spi_message */
+	spi_res_add(msg, rxfer);
+
+	return rxfer;
+}
+EXPORT_SYMBOL_GPL(spi_replace_transfers);
+
+static int __spi_split_transfer_maxsize(struct spi_master *master,
+					struct spi_message *msg,
+					struct spi_transfer **xferp,
+					size_t maxsize,
+					gfp_t gfp)
+{
+	struct spi_transfer *xfer = *xferp, *xfers;
+	struct spi_replaced_transfers *srt;
+	size_t offset;
+	size_t count, i;
+
+	/* warn once about this fact that we are splitting a transfer */
+	dev_warn_once(&msg->spi->dev,
+		      "spi_transfer of length %i exceed max length of %zu - needed to split transfers\n",
+		      xfer->len, maxsize);
+
+	/* calculate how many we have to replace */
+	count = DIV_ROUND_UP(xfer->len, maxsize);
+
+	/* create replacement */
+	srt = spi_replace_transfers(msg, xfer, 1, count, NULL, 0, gfp);
+	if (IS_ERR(srt))
+		return PTR_ERR(srt);
+	xfers = srt->inserted_transfers;
+
+	/* now handle each of those newly inserted spi_transfers
+	 * note that the replacements spi_transfers all are preset
+	 * to the same values as *xferp, so tx_buf, rx_buf and len
+	 * are all identical (as well as most others)
+	 * so we just have to fix up len and the pointers.
+	 *
+	 * this also includes support for the depreciated
+	 * spi_message.is_dma_mapped interface
+	 */
+
+	/* the first transfer just needs the length modified, so we
+	 * run it outside the loop
+	 */
+	xfers[0].len = min_t(size_t, maxsize, xfer[0].len);
+
+	/* all the others need rx_buf/tx_buf also set */
+	for (i = 1, offset = maxsize; i < count; offset += maxsize, i++) {
+		/* update rx_buf, tx_buf and dma */
+		if (xfers[i].rx_buf)
+			xfers[i].rx_buf += offset;
+		if (xfers[i].rx_dma)
+			xfers[i].rx_dma += offset;
+		if (xfers[i].tx_buf)
+			xfers[i].tx_buf += offset;
+		if (xfers[i].tx_dma)
+			xfers[i].tx_dma += offset;
+
+		/* update length */
+		xfers[i].len = min(maxsize, xfers[i].len - offset);
+	}
+
+	/* we set up xferp to the last entry we have inserted,
+	 * so that we skip those already split transfers
+	 */
+	*xferp = &xfers[count - 1];
+
+	/* increment statistics counters */
+	SPI_STATISTICS_INCREMENT_FIELD(&master->statistics,
+				       transfers_split_maxsize);
+	SPI_STATISTICS_INCREMENT_FIELD(&msg->spi->statistics,
+				       transfers_split_maxsize);
+
+	return 0;
+}
+
+/**
+ * spi_split_tranfers_maxsize - split spi transfers into multiple transfers
+ *                              when an individual transfer exceeds a
+ *                              certain size
+ * @master:    the @spi_master for this transfer
+ * @msg:   the @spi_message to transform
+ * @maxsize:  the maximum when to apply this
+ * @gfp: GFP allocation flags
+ *
+ * Return: status of transformation
+ */
+int spi_split_transfers_maxsize(struct spi_master *master,
+				struct spi_message *msg,
+				size_t maxsize,
+				gfp_t gfp)
+{
+	struct spi_transfer *xfer;
+	int ret;
+
+	/* iterate over the transfer_list,
+	 * but note that xfer is advanced to the last transfer inserted
+	 * to avoid checking sizes again unnecessarily (also xfer does
+	 * potentiall belong to a different list by the time the
+	 * replacement has happened
+	 */
+	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
+		if (xfer->len > maxsize) {
+			ret = __spi_split_transfer_maxsize(
+				master, msg, &xfer, maxsize, gfp);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(spi_split_transfers_maxsize);
 
 /*-------------------------------------------------------------------------*/
 
@@ -2351,6 +2717,46 @@ int spi_async_locked(struct spi_device *spi, struct spi_message *message)
 EXPORT_SYMBOL_GPL(spi_async_locked);
 
 
+int spi_flash_read(struct spi_device *spi,
+		   struct spi_flash_read_message *msg)
+
+{
+	struct spi_master *master = spi->master;
+	int ret;
+
+	if ((msg->opcode_nbits == SPI_NBITS_DUAL ||
+	     msg->addr_nbits == SPI_NBITS_DUAL) &&
+	    !(spi->mode & (SPI_TX_DUAL | SPI_TX_QUAD)))
+		return -EINVAL;
+	if ((msg->opcode_nbits == SPI_NBITS_QUAD ||
+	     msg->addr_nbits == SPI_NBITS_QUAD) &&
+	    !(spi->mode & SPI_TX_QUAD))
+		return -EINVAL;
+	if (msg->data_nbits == SPI_NBITS_DUAL &&
+	    !(spi->mode & (SPI_RX_DUAL | SPI_RX_QUAD)))
+		return -EINVAL;
+	if (msg->data_nbits == SPI_NBITS_QUAD &&
+	    !(spi->mode &  SPI_RX_QUAD))
+		return -EINVAL;
+
+	if (master->auto_runtime_pm) {
+		ret = pm_runtime_get_sync(master->dev.parent);
+		if (ret < 0) {
+			dev_err(&master->dev, "Failed to power device: %d\n",
+				ret);
+			return ret;
+		}
+	}
+	mutex_lock(&master->bus_lock_mutex);
+	ret = master->spi_flash_read(spi, msg);
+	mutex_unlock(&master->bus_lock_mutex);
+	if (master->auto_runtime_pm)
+		pm_runtime_put(master->dev.parent);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(spi_flash_read);
+
 /*-------------------------------------------------------------------------*/
 
 /* Utility methods for SPI master protocol drivers, layered on
@@ -2414,7 +2820,7 @@ static int __spi_sync(struct spi_device *spi, struct spi_message *message,
 						       spi_sync_immediate);
 			SPI_STATISTICS_INCREMENT_FIELD(&spi->statistics,
 						       spi_sync_immediate);
-			__spi_pump_messages(master, false);
+			__spi_pump_messages(master, false, bus_locked);
 		}
 
 		wait_for_completion(&done);
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index c2f2574ff61ceebbe4729df6d577722b391d0600..2a097d176ba964faae345a245f516c447701553c 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -197,6 +197,7 @@ enum pxa_ssp_type {
 	QUARK_X1000_SSP,
 	LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */
 	LPSS_BYT_SSP,
+	LPSS_BSW_SSP,
 	LPSS_SPT_SSP,
 	LPSS_BXT_SSP,
 };
diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 53be3a4c60cbe4d53388a18ef7ca96d3204b26cc..857a9a1d82b58ad3569c7daeb9fffb17f690926a 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -25,6 +25,7 @@
 struct dma_chan;
 struct spi_master;
 struct spi_transfer;
+struct spi_flash_read_message;
 
 /*
  * INTERFACES between SPI master-side drivers and SPI infrastructure.
@@ -53,6 +54,10 @@ extern struct bus_type spi_bus_type;
  *
  * @transfer_bytes_histo:
  *                 transfer bytes histogramm
+ *
+ * @transfers_split_maxsize:
+ *                 number of transfers that have been split because of
+ *                 maxsize limit
  */
 struct spi_statistics {
 	spinlock_t		lock; /* lock for the whole structure */
@@ -72,6 +77,8 @@ struct spi_statistics {
 
 #define SPI_STATISTICS_HISTO_SIZE 17
 	unsigned long transfer_bytes_histo[SPI_STATISTICS_HISTO_SIZE];
+
+	unsigned long transfers_split_maxsize;
 };
 
 void spi_statistics_add_transfer_stats(struct spi_statistics *stats,
@@ -303,6 +310,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @min_speed_hz: Lowest supported transfer speed
  * @max_speed_hz: Highest supported transfer speed
  * @flags: other constraints relevant to this driver
+ * @max_transfer_size: function that returns the max transfer size for
+ *	a &spi_device; may be %NULL, so the default %SIZE_MAX will be used.
  * @bus_lock_spinlock: spinlock for SPI bus locking
  * @bus_lock_mutex: mutex for SPI bus locking
  * @bus_lock_flag: indicates that the SPI bus is locked for exclusive use
@@ -361,6 +370,8 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @handle_err: the subsystem calls the driver to handle an error that occurs
  *		in the generic implementation of transfer_one_message().
  * @unprepare_message: undo any work done by prepare_message().
+ * @spi_flash_read: to support spi-controller hardwares that provide
+ *                  accelerated interface to read from flash devices.
  * @cs_gpios: Array of GPIOs to use as chip select lines; one per CS
  *	number. Any individual value may be -ENOENT for CS lines that
  *	are not GPIOs (driven by the SPI controller itself).
@@ -369,6 +380,9 @@ static inline void spi_unregister_driver(struct spi_driver *sdrv)
  * @dma_rx: DMA receive channel
  * @dummy_rx: dummy receive buffer for full-duplex devices
  * @dummy_tx: dummy transmit buffer for full-duplex devices
+ * @fw_translate_cs: If the boot firmware uses different numbering scheme
+ *	what Linux expects, this optional hook can be used to translate
+ *	between the two.
  *
  * Each SPI master controller can communicate with one or more @spi_device
  * children.  These make a small bus, sharing MOSI, MISO and SCK signals
@@ -513,6 +527,8 @@ struct spi_master {
 			       struct spi_message *message);
 	int (*unprepare_message)(struct spi_master *master,
 				 struct spi_message *message);
+	int (*spi_flash_read)(struct  spi_device *spi,
+			      struct spi_flash_read_message *msg);
 
 	/*
 	 * These hooks are for drivers that use a generic implementation
@@ -537,6 +553,8 @@ struct spi_master {
 	/* dummy data for full duplex devices */
 	void			*dummy_rx;
 	void			*dummy_tx;
+
+	int (*fw_translate_cs)(struct spi_master *master, unsigned cs);
 };
 
 static inline void *spi_master_get_devdata(struct spi_master *master)
@@ -582,6 +600,38 @@ extern void spi_unregister_master(struct spi_master *master);
 
 extern struct spi_master *spi_busnum_to_master(u16 busnum);
 
+/*
+ * SPI resource management while processing a SPI message
+ */
+
+typedef void (*spi_res_release_t)(struct spi_master *master,
+				  struct spi_message *msg,
+				  void *res);
+
+/**
+ * struct spi_res - spi resource management structure
+ * @entry:   list entry
+ * @release: release code called prior to freeing this resource
+ * @data:    extra data allocated for the specific use-case
+ *
+ * this is based on ideas from devres, but focused on life-cycle
+ * management during spi_message processing
+ */
+struct spi_res {
+	struct list_head        entry;
+	spi_res_release_t       release;
+	unsigned long long      data[]; /* guarantee ull alignment */
+};
+
+extern void *spi_res_alloc(struct spi_device *spi,
+			   spi_res_release_t release,
+			   size_t size, gfp_t gfp);
+extern void spi_res_add(struct spi_message *message, void *res);
+extern void spi_res_free(void *res);
+
+extern void spi_res_release(struct spi_master *master,
+			    struct spi_message *message);
+
 /*---------------------------------------------------------------------------*/
 
 /*
@@ -720,6 +770,7 @@ struct spi_transfer {
  * @status: zero for success, else negative errno
  * @queue: for use by whichever driver currently owns the message
  * @state: for use by whichever driver currently owns the message
+ * @resources: for resource management when the spi message is processed
  *
  * A @spi_message is used to execute an atomic sequence of data transfers,
  * each represented by a struct spi_transfer.  The sequence is "atomic"
@@ -766,11 +817,15 @@ struct spi_message {
 	 */
 	struct list_head	queue;
 	void			*state;
+
+	/* list of spi_res reources when the spi message is processed */
+	struct list_head        resources;
 };
 
 static inline void spi_message_init_no_memset(struct spi_message *m)
 {
 	INIT_LIST_HEAD(&m->transfers);
+	INIT_LIST_HEAD(&m->resources);
 }
 
 static inline void spi_message_init(struct spi_message *m)
@@ -854,6 +909,60 @@ spi_max_transfer_size(struct spi_device *spi)
 
 /*---------------------------------------------------------------------------*/
 
+/* SPI transfer replacement methods which make use of spi_res */
+
+struct spi_replaced_transfers;
+typedef void (*spi_replaced_release_t)(struct spi_master *master,
+				       struct spi_message *msg,
+				       struct spi_replaced_transfers *res);
+/**
+ * struct spi_replaced_transfers - structure describing the spi_transfer
+ *                                 replacements that have occurred
+ *                                 so that they can get reverted
+ * @release:            some extra release code to get executed prior to
+ *                      relasing this structure
+ * @extradata:          pointer to some extra data if requested or NULL
+ * @replaced_transfers: transfers that have been replaced and which need
+ *                      to get restored
+ * @replaced_after:     the transfer after which the @replaced_transfers
+ *                      are to get re-inserted
+ * @inserted:           number of transfers inserted
+ * @inserted_transfers: array of spi_transfers of array-size @inserted,
+ *                      that have been replacing replaced_transfers
+ *
+ * note: that @extradata will point to @inserted_transfers[@inserted]
+ * if some extra allocation is requested, so alignment will be the same
+ * as for spi_transfers
+ */
+struct spi_replaced_transfers {
+	spi_replaced_release_t release;
+	void *extradata;
+	struct list_head replaced_transfers;
+	struct list_head *replaced_after;
+	size_t inserted;
+	struct spi_transfer inserted_transfers[];
+};
+
+extern struct spi_replaced_transfers *spi_replace_transfers(
+	struct spi_message *msg,
+	struct spi_transfer *xfer_first,
+	size_t remove,
+	size_t insert,
+	spi_replaced_release_t release,
+	size_t extradatasize,
+	gfp_t gfp);
+
+/*---------------------------------------------------------------------------*/
+
+/* SPI transfer transformation methods */
+
+extern int spi_split_transfers_maxsize(struct spi_master *master,
+				       struct spi_message *msg,
+				       size_t maxsize,
+				       gfp_t gfp);
+
+/*---------------------------------------------------------------------------*/
+
 /* All these synchronous SPI transfer routines are utilities layered
  * over the core async transfer primitive.  Here, "synchronous" means
  * they will sleep uninterruptibly until the async transfer completes.
@@ -1019,6 +1128,42 @@ static inline ssize_t spi_w8r16be(struct spi_device *spi, u8 cmd)
 	return be16_to_cpu(result);
 }
 
+/**
+ * struct spi_flash_read_message - flash specific information for
+ * spi-masters that provide accelerated flash read interfaces
+ * @buf: buffer to read data
+ * @from: offset within the flash from where data is to be read
+ * @len: length of data to be read
+ * @retlen: actual length of data read
+ * @read_opcode: read_opcode to be used to communicate with flash
+ * @addr_width: number of address bytes
+ * @dummy_bytes: number of dummy bytes
+ * @opcode_nbits: number of lines to send opcode
+ * @addr_nbits: number of lines to send address
+ * @data_nbits: number of lines for data
+ */
+struct spi_flash_read_message {
+	void *buf;
+	loff_t from;
+	size_t len;
+	size_t retlen;
+	u8 read_opcode;
+	u8 addr_width;
+	u8 dummy_bytes;
+	u8 opcode_nbits;
+	u8 addr_nbits;
+	u8 data_nbits;
+};
+
+/* SPI core interface for flash read support */
+static inline bool spi_flash_read_supported(struct spi_device *spi)
+{
+	return spi->master->spi_flash_read ? true : false;
+}
+
+int spi_flash_read(struct spi_device *spi,
+		   struct spi_flash_read_message *msg);
+
 /*---------------------------------------------------------------------------*/
 
 /*