Merge remote-tracking branch 'spi/for-5.9' into spi-next

53 files changed, 2532 insertions, 758 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 8f1f8fca79e3..c3008e423f59 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -59,6 +59,7 @@ comment "SPI Master Controller Drivers"
 
 config SPI_ALTERA
 	tristate "Altera SPI Controller"
+	select REGMAP_MMIO
 	help
 	  This is the driver for the Altera SPI Controller.
 
@@ -102,7 +103,7 @@ config SPI_AT91_USART
 
 config SPI_ATMEL_QUADSPI
 	tristate "Atmel Quad SPI Controller"
-	depends on ARCH_AT91 || (ARM && COMPILE_TEST && !ARCH_EBSA110)
+	depends on ARCH_AT91 || COMPILE_TEST
 	depends on OF && HAS_IOMEM
 	help
 	  This enables support for the Quad SPI controller in master mode.
@@ -149,13 +150,13 @@ config SPI_BCM2835AUX
 
 config SPI_BCM63XX
 	tristate "Broadcom BCM63xx SPI controller"
-	depends on BCM63XX || COMPILE_TEST
+	depends on BCM63XX || BMIPS_GENERIC || COMPILE_TEST
 	help
 	  Enable support for the SPI controller on the Broadcom BCM63xx SoCs.
 
 config SPI_BCM63XX_HSSPI
 	tristate "Broadcom BCM63XX HS SPI controller driver"
-	depends on BCM63XX || ARCH_BCM_63XX || COMPILE_TEST
+	depends on BCM63XX || BMIPS_GENERIC || ARCH_BCM_63XX || COMPILE_TEST
 	help
 	  This enables support for the High Speed SPI controller present on
 	  newer Broadcom BCM63XX SoCs.
@@ -168,7 +169,7 @@ config SPI_BCM_QSPI
 	help
 	  Enables support for the Broadcom SPI flash and MSPI controller.
 	  Select this option for any one of BRCMSTB, iProc NSP and NS2 SoCs
-	  based platforms. This driver works for both SPI master for spi-nor
+	  based platforms. This driver works for both SPI master for SPI NOR
 	  flash device as well as MSPI device.
 
 config SPI_BITBANG
@@ -200,6 +201,17 @@ config SPI_CADENCE
 	  This selects the Cadence SPI controller master driver
 	  used by Xilinx Zynq and ZynqMP.
 
+config SPI_CADENCE_QUADSPI
+	tristate "Cadence Quad SPI controller"
+	depends on OF && (ARM || ARM64 || COMPILE_TEST)
+	help
+	  Enable support for the Cadence Quad SPI Flash controller.
+
+	  Cadence QSPI is a specialized controller for connecting an SPI
+	  Flash over 1/2/4-bit wide bus. Enable this option if you have a
+	  device with a Cadence QSPI controller and want to access the
+	  Flash as an MTD device.
+
 config SPI_CLPS711X
 	tristate "CLPS711X host SPI controller"
 	depends on ARCH_CLPS711X || COMPILE_TEST
@@ -299,11 +311,11 @@ config SPI_FSL_QUADSPI
 	  supports the high-level SPI memory interface.
 
 config SPI_HISI_SFC_V3XX
-	tristate "HiSilicon SPI-NOR Flash Controller for Hi16XX chipsets"
+	tristate "HiSilicon SPI NOR Flash Controller for Hi16XX chipsets"
 	depends on (ARM64 && ACPI) || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
-	  This enables support for HiSilicon v3xx SPI-NOR flash controller
+	  This enables support for HiSilicon v3xx SPI NOR flash controller
 	  found in hi16xx chipsets.
 
 config SPI_NXP_FLEXSPI
@@ -465,9 +477,9 @@ config SPI_MTK_NOR
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	help
 	  This enables support for SPI NOR controller found on MediaTek
-	  ARM SoCs. This is a controller specifically for SPI-NOR flash.
+	  ARM SoCs. This is a controller specifically for SPI NOR flash.
 	  It can perform generic SPI transfers up to 6 bytes via generic
-	  SPI interface as well as several SPI-NOR specific instructions
+	  SPI interface as well as several SPI NOR specific instructions
 	  via SPI MEM interface.
 
 config SPI_NPCM_FIU
@@ -489,11 +501,11 @@ config SPI_NPCM_PSPI
 
 config SPI_LANTIQ_SSC
 	tristate "Lantiq SSC SPI controller"
-	depends on LANTIQ || COMPILE_TEST
+	depends on LANTIQ || X86 || COMPILE_TEST
 	help
 	  This driver supports the Lantiq SSC SPI controller in master
 	  mode. This controller is found on Intel (former Lantiq) SoCs like
-	  the Danube, Falcon, xRX200, xRX300.
+	  the Danube, Falcon, xRX200, xRX300, Lightning Mountain.
 
 config SPI_OC_TINY
 	tristate "OpenCores tiny SPI"
@@ -605,6 +617,12 @@ config SPI_RB4XX
 	help
 	  SPI controller driver for the Mikrotik RB4xx series boards.
 
+config SPI_RPCIF
+	tristate "Renesas RPC-IF SPI driver"
+	depends on RENESAS_RPCIF
+	help
+	  SPI driver for Renesas R-Car Gen3 RPC-IF.
+
 config SPI_RSPI
 	tristate "Renesas RSPI/QSPI controller"
 	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index d2e41d3d464a..cf955ea803cd 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_SPI_BCM_QSPI)		+= spi-iproc-qspi.o spi-brcmstb-qspi.o spi-bcm-qspi.
 obj-$(CONFIG_SPI_BITBANG)		+= spi-bitbang.o
 obj-$(CONFIG_SPI_BUTTERFLY)		+= spi-butterfly.o
 obj-$(CONFIG_SPI_CADENCE)		+= spi-cadence.o
+obj-$(CONFIG_SPI_CADENCE_QUADSPI)	+= spi-cadence-quadspi.o
 obj-$(CONFIG_SPI_CLPS711X)		+= spi-clps711x.o
 obj-$(CONFIG_SPI_COLDFIRE_QSPI)		+= spi-coldfire-qspi.o
 obj-$(CONFIG_SPI_DAVINCI)		+= spi-davinci.o
@@ -92,6 +93,7 @@ obj-$(CONFIG_SPI_QCOM_QSPI)		+= spi-qcom-qspi.o
 obj-$(CONFIG_SPI_QUP)			+= spi-qup.o
 obj-$(CONFIG_SPI_ROCKCHIP)		+= spi-rockchip.o
 obj-$(CONFIG_SPI_RB4XX)			+= spi-rb4xx.o
+obj-$(CONFIG_SPI_RPCIF)			+= spi-rpc-if.o
 obj-$(CONFIG_SPI_RSPI)			+= spi-rspi.o
 obj-$(CONFIG_SPI_S3C24XX)		+= spi-s3c24xx-hw.o
 spi-s3c24xx-hw-y			:= spi-s3c24xx.o
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index cb44d1e169aa..8c009c175f2c 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -285,6 +285,12 @@ static bool atmel_qspi_supports_op(struct spi_mem *mem,
 		op->dummy.nbytes == 0)
 		return false;
 
+	/* DTR ops not supported. */
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		return false;
+	if (op->cmd.nbytes != 1)
+		return false;
+
 	return true;
 }
 
@@ -424,11 +430,11 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 
 		/* Send/Receive data */
 		if (op->data.dir == SPI_MEM_DATA_IN)
-			_memcpy_fromio(op->data.buf.in, aq->mem + offset,
-				       op->data.nbytes);
+			memcpy_fromio(op->data.buf.in, aq->mem + offset,
+				      op->data.nbytes);
 		else
-			_memcpy_toio(aq->mem + offset, op->data.buf.out,
-				     op->data.nbytes);
+			memcpy_toio(aq->mem + offset, op->data.buf.out,
+				    op->data.nbytes);
 
 		/* Release the chip-select */
 		atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR);
diff --git a/drivers/spi/spi-altera.c b/drivers/spi/spi-altera.c
index 41d71ba7fd32..809bfff3690a 100644
--- a/drivers/spi/spi-altera.c
+++ b/drivers/spi/spi-altera.c
@@ -14,6 +14,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/spi/altera.h>
 #include <linux/spi/spi.h>
 #include <linux/io.h>
 #include <linux/of.h>
@@ -40,19 +41,61 @@
 #define ALTERA_SPI_CONTROL_IE_MSK	0x100
 #define ALTERA_SPI_CONTROL_SSO_MSK	0x400
 
+#define ALTERA_SPI_MAX_CS		32
+
+enum altera_spi_type {
+	ALTERA_SPI_TYPE_UNKNOWN,
+	ALTERA_SPI_TYPE_SUBDEV,
+};
+
 struct altera_spi {
-	void __iomem *base;
 	int irq;
 	int len;
 	int count;
 	int bytes_per_word;
-	unsigned long imr;
+	u32 imr;
 
 	/* data buffers */
 	const unsigned char *tx;
 	unsigned char *rx;
+
+	struct regmap *regmap;
+	u32 regoff;
+	struct device *dev;
+};
+
+static const struct regmap_config spi_altera_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
 };
 
+static int altr_spi_writel(struct altera_spi *hw, unsigned int reg,
+			   unsigned int val)
+{
+	int ret;
+
+	ret = regmap_write(hw->regmap, hw->regoff + reg, val);
+	if (ret)
+		dev_err(hw->dev, "fail to write reg 0x%x val 0x%x: %d\n",
+			reg, val, ret);
+
+	return ret;
+}
+
+static int altr_spi_readl(struct altera_spi *hw, unsigned int reg,
+			  unsigned int *val)
+{
+	int ret;
+
+	ret = regmap_read(hw->regmap, hw->regoff + reg, val);
+	if (ret)
+		dev_err(hw->dev, "fail to read reg 0x%x: %d\n", reg, ret);
+
+	return ret;
+}
+
 static inline struct altera_spi *altera_spi_to_hw(struct spi_device *sdev)
 {
 	return spi_master_get_devdata(sdev->master);
@@ -64,12 +107,13 @@ static void altera_spi_set_cs(struct spi_device *spi, bool is_high)
 
 	if (is_high) {
 		hw->imr &= ~ALTERA_SPI_CONTROL_SSO_MSK;
-		writel(hw->imr, hw->base + ALTERA_SPI_CONTROL);
-		writel(0, hw->base + ALTERA_SPI_SLAVE_SEL);
+		altr_spi_writel(hw, ALTERA_SPI_CONTROL, hw->imr);
+		altr_spi_writel(hw, ALTERA_SPI_SLAVE_SEL, 0);
 	} else {
-		writel(BIT(spi->chip_select), hw->base + ALTERA_SPI_SLAVE_SEL);
+		altr_spi_writel(hw, ALTERA_SPI_SLAVE_SEL,
+				BIT(spi->chip_select));
 		hw->imr |= ALTERA_SPI_CONTROL_SSO_MSK;
-		writel(hw->imr, hw->base + ALTERA_SPI_CONTROL);
+		altr_spi_writel(hw, ALTERA_SPI_CONTROL, hw->imr);
 	}
 }
 
@@ -86,17 +130,24 @@ static void altera_spi_tx_word(struct altera_spi *hw)
 			txd = (hw->tx[hw->count * 2]
 				| (hw->tx[hw->count * 2 + 1] << 8));
 			break;
+		case 4:
+			txd = (hw->tx[hw->count * 4]
+				| (hw->tx[hw->count * 4 + 1] << 8)
+				| (hw->tx[hw->count * 4 + 2] << 16)
+				| (hw->tx[hw->count * 4 + 3] << 24));
+			break;
+
 		}
 	}
 
-	writel(txd, hw->base + ALTERA_SPI_TXDATA);
+	altr_spi_writel(hw, ALTERA_SPI_TXDATA, txd);
 }
 
 static void altera_spi_rx_word(struct altera_spi *hw)
 {
 	unsigned int rxd;
 
-	rxd = readl(hw->base + ALTERA_SPI_RXDATA);
+	altr_spi_readl(hw, ALTERA_SPI_RXDATA, &rxd);
 	if (hw->rx) {
 		switch (hw->bytes_per_word) {
 		case 1:
@@ -106,6 +157,13 @@ static void altera_spi_rx_word(struct altera_spi *hw)
 			hw->rx[hw->count * 2] = rxd;
 			hw->rx[hw->count * 2 + 1] = rxd >> 8;
 			break;
+		case 4:
+			hw->rx[hw->count * 4] = rxd;
+			hw->rx[hw->count * 4 + 1] = rxd >> 8;
+			hw->rx[hw->count * 4 + 2] = rxd >> 16;
+			hw->rx[hw->count * 4 + 3] = rxd >> 24;
+			break;
+
 		}
 	}
 
@@ -116,6 +174,7 @@ static int altera_spi_txrx(struct spi_master *master,
 	struct spi_device *spi, struct spi_transfer *t)
 {
 	struct altera_spi *hw = spi_master_get_devdata(master);
+	u32 val;
 
 	hw->tx = t->tx_buf;
 	hw->rx = t->rx_buf;
@@ -126,7 +185,7 @@ static int altera_spi_txrx(struct spi_master *master,
 	if (hw->irq >= 0) {
 		/* enable receive interrupt */
 		hw->imr |= ALTERA_SPI_CONTROL_IRRDY_MSK;
-		writel(hw->imr, hw->base + ALTERA_SPI_CONTROL);
+		altr_spi_writel(hw, ALTERA_SPI_CONTROL, hw->imr);
 
 		/* send the first byte */
 		altera_spi_tx_word(hw);
@@ -134,9 +193,13 @@ static int altera_spi_txrx(struct spi_master *master,
 		while (hw->count < hw->len) {
 			altera_spi_tx_word(hw);
 
-			while (!(readl(hw->base + ALTERA_SPI_STATUS) &
-				 ALTERA_SPI_STATUS_RRDY_MSK))
+			for (;;) {
+				altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
+				if (val & ALTERA_SPI_STATUS_RRDY_MSK)
+					break;
+
 				cpu_relax();
+			}
 
 			altera_spi_rx_word(hw);
 		}
@@ -158,7 +221,7 @@ static irqreturn_t altera_spi_irq(int irq, void *dev)
 	} else {
 		/* disable receive interrupt */
 		hw->imr &= ~ALTERA_SPI_CONTROL_IRRDY_MSK;
-		writel(hw->imr, hw->base + ALTERA_SPI_CONTROL);
+		altr_spi_writel(hw, ALTERA_SPI_CONTROL, hw->imr);
 
 		spi_finalize_current_transfer(master);
 	}
@@ -168,9 +231,14 @@ static irqreturn_t altera_spi_irq(int irq, void *dev)
 
 static int altera_spi_probe(struct platform_device *pdev)
 {
+	const struct platform_device_id *platid = platform_get_device_id(pdev);
+	struct altera_spi_platform_data *pdata = dev_get_platdata(&pdev->dev);
+	enum altera_spi_type type = ALTERA_SPI_TYPE_UNKNOWN;
 	struct altera_spi *hw;
 	struct spi_master *master;
 	int err = -ENODEV;
+	u32 val;
+	u16 i;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(struct altera_spi));
 	if (!master)
@@ -178,27 +246,72 @@ static int altera_spi_probe(struct platform_device *pdev)
 
 	/* setup the master state. */
 	master->bus_num = pdev->id;
-	master->num_chipselect = 16;
-	master->mode_bits = SPI_CS_HIGH;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 16);
+
+	if (pdata) {
+		if (pdata->num_chipselect > ALTERA_SPI_MAX_CS) {
+			dev_err(&pdev->dev,
+				"Invalid number of chipselect: %hu\n",
+				pdata->num_chipselect);
+			return -EINVAL;
+		}
+
+		master->num_chipselect = pdata->num_chipselect;
+		master->mode_bits = pdata->mode_bits;
+		master->bits_per_word_mask = pdata->bits_per_word_mask;
+	} else {
+		master->num_chipselect = 16;
+		master->mode_bits = SPI_CS_HIGH;
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 16);
+	}
+
 	master->dev.of_node = pdev->dev.of_node;
 	master->transfer_one = altera_spi_txrx;
 	master->set_cs = altera_spi_set_cs;
 
 	hw = spi_master_get_devdata(master);
+	hw->dev = &pdev->dev;
+
+	if (platid)
+		type = platid->driver_data;
 
 	/* find and map our resources */
-	hw->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(hw->base)) {
-		err = PTR_ERR(hw->base);
-		goto exit;
+	if (type == ALTERA_SPI_TYPE_SUBDEV) {
+		struct resource *regoff;
+
+		hw->regmap = dev_get_regmap(pdev->dev.parent, NULL);
+		if (!hw->regmap) {
+			dev_err(&pdev->dev, "get regmap failed\n");
+			goto exit;
+		}
+
+		regoff = platform_get_resource(pdev, IORESOURCE_REG, 0);
+		if (regoff)
+			hw->regoff = regoff->start;
+	} else {
+		void __iomem *res;
+
+		res = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(res)) {
+			err = PTR_ERR(res);
+			goto exit;
+		}
+
+		hw->regmap = devm_regmap_init_mmio(&pdev->dev, res,
+						   &spi_altera_config);
+		if (IS_ERR(hw->regmap)) {
+			dev_err(&pdev->dev, "regmap mmio init failed\n");
+			err = PTR_ERR(hw->regmap);
+			goto exit;
+		}
 	}
+
 	/* program defaults into the registers */
 	hw->imr = 0;		/* disable spi interrupts */
-	writel(hw->imr, hw->base + ALTERA_SPI_CONTROL);
-	writel(0, hw->base + ALTERA_SPI_STATUS);	/* clear status reg */
-	if (readl(hw->base + ALTERA_SPI_STATUS) & ALTERA_SPI_STATUS_RRDY_MSK)
-		readl(hw->base + ALTERA_SPI_RXDATA);	/* flush rxdata */
+	altr_spi_writel(hw, ALTERA_SPI_CONTROL, hw->imr);
+	altr_spi_writel(hw, ALTERA_SPI_STATUS, 0);	/* clear status reg */
+	altr_spi_readl(hw, ALTERA_SPI_STATUS, &val);
+	if (val & ALTERA_SPI_STATUS_RRDY_MSK)
+		altr_spi_readl(hw, ALTERA_SPI_RXDATA, &val); /* flush rxdata */
 	/* irq is optional */
 	hw->irq = platform_get_irq(pdev, 0);
 	if (hw->irq >= 0) {
@@ -211,7 +324,17 @@ static int altera_spi_probe(struct platform_device *pdev)
 	err = devm_spi_register_master(&pdev->dev, master);
 	if (err)
 		goto exit;
-	dev_info(&pdev->dev, "base %p, irq %d\n", hw->base, hw->irq);
+
+	if (pdata) {
+		for (i = 0; i < pdata->num_devices; i++) {
+			if (!spi_new_device(master, pdata->devices + i))
+				dev_warn(&pdev->dev,
+					 "unable to create SPI device: %s\n",
+					 pdata->devices[i].modalias);
+		}
+	}
+
+	dev_info(&pdev->dev, "regoff %u, irq %d\n", hw->regoff, hw->irq);
 
 	return 0;
 exit:
@@ -228,6 +351,13 @@ static const struct of_device_id altera_spi_match[] = {
 MODULE_DEVICE_TABLE(of, altera_spi_match);
 #endif /* CONFIG_OF */
 
+static const struct platform_device_id altera_spi_ids[] = {
+	{ DRV_NAME,		ALTERA_SPI_TYPE_UNKNOWN },
+	{ "subdev_spi_altera",	ALTERA_SPI_TYPE_SUBDEV },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, altera_spi_ids);
+
 static struct platform_driver altera_spi_driver = {
 	.probe = altera_spi_probe,
 	.driver = {
@@ -235,6 +365,7 @@ static struct platform_driver altera_spi_driver = {
 		.pm = NULL,
 		.of_match_table = of_match_ptr(altera_spi_match),
 	},
+	.id_table	= altera_spi_ids,
 };
 module_platform_driver(altera_spi_driver);
 
diff --git a/drivers/spi/spi-amd.c b/drivers/spi/spi-amd.c
index d0aacd4de1b9..7f629544060d 100644
--- a/drivers/spi/spi-amd.c
+++ b/drivers/spi/spi-amd.c
@@ -294,11 +294,13 @@ err_free_master:
 	return err;
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id spi_acpi_match[] = {
 	{ "AMDI0061", 0 },
 	{},
 };
 MODULE_DEVICE_TABLE(acpi, spi_acpi_match);
+#endif
 
 static struct platform_driver amd_spi_driver = {
 	.driver = {
diff --git a/drivers/spi/spi-at91-usart.c b/drivers/spi/spi-at91-usart.c
index 88033422a42a..8c8352625d23 100644
--- a/drivers/spi/spi-at91-usart.c
+++ b/drivers/spi/spi-at91-usart.c
@@ -681,13 +681,6 @@ static const struct dev_pm_ops at91_usart_spi_pm_ops = {
 			   at91_usart_spi_runtime_resume, NULL)
 };
 
-static const struct of_device_id at91_usart_spi_dt_ids[] = {
-	{ .compatible = "microchip,at91sam9g45-usart-spi"},
-	{ /* sentinel */}
-};
-
-MODULE_DEVICE_TABLE(of, at91_usart_spi_dt_ids);
-
 static struct platform_driver at91_usart_spi_driver = {
 	.driver = {
 		.name = "at91_usart_spi",
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index 57ee8c3b7972..2cfe6253a784 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1546,10 +1546,9 @@ static int atmel_spi_probe(struct platform_device *pdev)
 		return PTR_ERR(clk);
 
 	/* setup spi core then atmel-specific driver state */
-	ret = -ENOMEM;
 	master = spi_alloc_master(&pdev->dev, sizeof(*as));
 	if (!master)
-		goto out_free;
+		return -ENOMEM;
 
 	/* the spi->mode bits understood by this driver: */
 	master->use_gpio_descriptors = true;
@@ -1678,7 +1677,6 @@ out_free_dma:
 	clk_disable_unprepare(clk);
 out_free_irq:
 out_unmap_regs:
-out_free:
 	spi_master_put(master);
 	return ret;
 }
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 237bd306c268..c45d76c848c8 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -86,6 +86,7 @@ MODULE_PARM_DESC(polling_limit_us,
  * @clk: core clock, divided to calculate serial clock
  * @irq: interrupt, signals TX FIFO empty or RX FIFO ¾ full
  * @tfr: SPI transfer currently processed
+ * @ctlr: SPI controller reverse lookup
  * @tx_buf: pointer whence next transmitted byte is read
  * @rx_buf: pointer where next received byte is written
  * @tx_len: remaining bytes to transmit
@@ -125,6 +126,7 @@ struct bcm2835_spi {
 	struct clk *clk;
 	int irq;
 	struct spi_transfer *tfr;
+	struct spi_controller *ctlr;
 	const u8 *tx_buf;
 	u8 *rx_buf;
 	int tx_len;
@@ -243,13 +245,13 @@ static inline void bcm2835_rd_fifo_count(struct bcm2835_spi *bs, int count)
 
 	bs->rx_len -= count;
 
-	while (count > 0) {
+	do {
 		val = bcm2835_rd(bs, BCM2835_SPI_FIFO);
 		len = min(count, 4);
 		memcpy(bs->rx_buf, &val, len);
 		bs->rx_buf += len;
 		count -= 4;
-	}
+	} while (count > 0);
 }
 
 /**
@@ -269,7 +271,7 @@ static inline void bcm2835_wr_fifo_count(struct bcm2835_spi *bs, int count)
 
 	bs->tx_len -= count;
 
-	while (count > 0) {
+	do {
 		if (bs->tx_buf) {
 			len = min(count, 4);
 			memcpy(&val, bs->tx_buf, len);
@@ -279,7 +281,7 @@ static inline void bcm2835_wr_fifo_count(struct bcm2835_spi *bs, int count)
 		}
 		bcm2835_wr(bs, BCM2835_SPI_FIFO, val);
 		count -= 4;
-	}
+	} while (count > 0);
 }
 
 /**
@@ -308,12 +310,11 @@ static inline void bcm2835_rd_fifo_blind(struct bcm2835_spi *bs, int count)
 	count = min(count, bs->rx_len);
 	bs->rx_len -= count;
 
-	while (count) {
+	do {
 		val = bcm2835_rd(bs, BCM2835_SPI_FIFO);
 		if (bs->rx_buf)
 			*bs->rx_buf++ = val;
-		count--;
-	}
+	} while (--count);
 }
 
 /**
@@ -328,16 +329,14 @@ static inline void bcm2835_wr_fifo_blind(struct bcm2835_spi *bs, int count)
 	count = min(count, bs->tx_len);
 	bs->tx_len -= count;
 
-	while (count) {
+	do {
 		val = bs->tx_buf ? *bs->tx_buf++ : 0;
 		bcm2835_wr(bs, BCM2835_SPI_FIFO, val);
-		count--;
-	}
+	} while (--count);
 }
 
-static void bcm2835_spi_reset_hw(struct spi_controller *ctlr)
+static void bcm2835_spi_reset_hw(struct bcm2835_spi *bs)
 {
-	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 
 	/* Disable SPI interrupts and transfer */
@@ -363,8 +362,7 @@ static void bcm2835_spi_reset_hw(struct spi_controller *ctlr)
 
 static irqreturn_t bcm2835_spi_interrupt(int irq, void *dev_id)
 {
-	struct spi_controller *ctlr = dev_id;
-	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
+	struct bcm2835_spi *bs = dev_id;
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 
 	/*
@@ -386,9 +384,9 @@ static irqreturn_t bcm2835_spi_interrupt(int irq, void *dev_id)
 
 	if (!bs->rx_len) {
 		/* Transfer complete - reset SPI HW */
-		bcm2835_spi_reset_hw(ctlr);
+		bcm2835_spi_reset_hw(bs);
 		/* wake up the framework */
-		complete(&ctlr->xfer_completion);
+		complete(&bs->ctlr->xfer_completion);
 	}
 
 	return IRQ_HANDLED;
@@ -607,7 +605,7 @@ static void bcm2835_spi_dma_rx_done(void *data)
 	bcm2835_spi_undo_prologue(bs);
 
 	/* reset fifo and HW */
-	bcm2835_spi_reset_hw(ctlr);
+	bcm2835_spi_reset_hw(bs);
 
 	/* and mark as completed */;
 	complete(&ctlr->xfer_completion);
@@ -641,7 +639,7 @@ static void bcm2835_spi_dma_tx_done(void *data)
 		dmaengine_terminate_async(ctlr->dma_rx);
 
 	bcm2835_spi_undo_prologue(bs);
-	bcm2835_spi_reset_hw(ctlr);
+	bcm2835_spi_reset_hw(bs);
 	complete(&ctlr->xfer_completion);
 }
 
@@ -825,14 +823,14 @@ static int bcm2835_spi_transfer_one_dma(struct spi_controller *ctlr,
 	if (!bs->rx_buf && !bs->tx_dma_active &&
 	    cmpxchg(&bs->rx_dma_active, true, false)) {
 		dmaengine_terminate_async(ctlr->dma_rx);
-		bcm2835_spi_reset_hw(ctlr);
+		bcm2835_spi_reset_hw(bs);
 	}
 
 	/* wait for wakeup in framework */
 	return 1;
 
 err_reset_hw:
-	bcm2835_spi_reset_hw(ctlr);
+	bcm2835_spi_reset_hw(bs);
 	bcm2835_spi_undo_prologue(bs);
 	return ret;
 }
@@ -1074,7 +1072,7 @@ static int bcm2835_spi_transfer_one_poll(struct spi_controller *ctlr,
 	}
 
 	/* Transfer complete - reset SPI HW */
-	bcm2835_spi_reset_hw(ctlr);
+	bcm2835_spi_reset_hw(bs);
 	/* and return without waiting for completion */
 	return 0;
 }
@@ -1084,7 +1082,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
 				    struct spi_transfer *tfr)
 {
 	struct bcm2835_spi *bs = spi_controller_get_devdata(ctlr);
-	unsigned long spi_hz, clk_hz, cdiv, spi_used_hz;
+	unsigned long spi_hz, clk_hz, cdiv;
 	unsigned long hz_per_byte, byte_limit;
 	u32 cs = bs->prepare_cs[spi->chip_select];
 
@@ -1104,7 +1102,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
 	} else {
 		cdiv = 0; /* 0 is the slowest we can go */
 	}
-	spi_used_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536);
+	tfr->effective_speed_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536);
 	bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);
 
 	/* handle all the 3-wire mode */
@@ -1124,7 +1122,7 @@ static int bcm2835_spi_transfer_one(struct spi_controller *ctlr,
 	 * per 300,000 Hz of bus clock.
 	 */
 	hz_per_byte = polling_limit_us ? (9 * 1000000) / polling_limit_us : 0;
-	byte_limit = hz_per_byte ? spi_used_hz / hz_per_byte : 1;
+	byte_limit = hz_per_byte ? tfr->effective_speed_hz / hz_per_byte : 1;
 
 	/* run in polling mode for short transfers */
 	if (tfr->len < byte_limit)
@@ -1182,7 +1180,7 @@ static void bcm2835_spi_handle_err(struct spi_controller *ctlr,
 	bcm2835_spi_undo_prologue(bs);
 
 	/* and reset */
-	bcm2835_spi_reset_hw(ctlr);
+	bcm2835_spi_reset_hw(bs);
 }
 
 static int chip_match_name(struct gpio_chip *chip, void *data)
@@ -1311,6 +1309,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
 	ctlr->dev.of_node = pdev->dev.of_node;
 
 	bs = spi_controller_get_devdata(ctlr);
+	bs->ctlr = ctlr;
 
 	bs->regs = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(bs->regs)) {
@@ -1345,7 +1344,7 @@ static int bcm2835_spi_probe(struct platform_device *pdev)
 		   BCM2835_SPI_CS_CLEAR_RX | BCM2835_SPI_CS_CLEAR_TX);
 
 	err = devm_request_irq(&pdev->dev, bs->irq, bcm2835_spi_interrupt, 0,
-			       dev_name(&pdev->dev), ctlr);
+			       dev_name(&pdev->dev), bs);
 	if (err) {
 		dev_err(&pdev->dev, "could not request IRQ: %d\n", err);
 		goto out_dma_release;
diff --git a/drivers/spi/spi-bcm2835aux.c b/drivers/spi/spi-bcm2835aux.c
index c331efd6e86b..2f717812c766 100644
--- a/drivers/spi/spi-bcm2835aux.c
+++ b/drivers/spi/spi-bcm2835aux.c
@@ -345,7 +345,7 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 				       struct spi_transfer *tfr)
 {
 	struct bcm2835aux_spi *bs = spi_master_get_devdata(master);
-	unsigned long spi_hz, clk_hz, speed, spi_used_hz;
+	unsigned long spi_hz, clk_hz, speed;
 	unsigned long hz_per_byte, byte_limit;
 
 	/* calculate the registers to handle
@@ -374,7 +374,7 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	/* set the new speed */
 	bs->cntl[0] |= speed << BCM2835_AUX_SPI_CNTL0_SPEED_SHIFT;
 
-	spi_used_hz = clk_hz / (2 * (speed + 1));
+	tfr->effective_speed_hz = clk_hz / (2 * (speed + 1));
 
 	/* set transmit buffers and length */
 	bs->tx_buf = tfr->tx_buf;
@@ -391,7 +391,7 @@ static int bcm2835aux_spi_transfer_one(struct spi_master *master,
 	 * 30 µs per 300,000 Hz of bus clock.
 	 */
 	hz_per_byte = polling_limit_us ? (9 * 1000000) / polling_limit_us : 0;
-	byte_limit = hz_per_byte ? spi_used_hz / hz_per_byte : 1;
+	byte_limit = hz_per_byte ? tfr->effective_speed_hz / hz_per_byte : 1;
 
 	/* run in polling mode for short transfers */
 	if (tfr->len < byte_limit)
diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
index 6c235306c0e4..9909b18f3c5a 100644
--- a/drivers/spi/spi-bcm63xx-hsspi.c
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -20,6 +20,7 @@
 #include <linux/spi/spi.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
+#include <linux/reset.h>
 
 #define HSSPI_GLOBAL_CTRL_REG			0x0
 #define GLOBAL_CTRL_CS_POLARITY_SHIFT		0
@@ -334,6 +335,7 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev)
 	struct clk *clk, *pll_clk = NULL;
 	int irq, ret;
 	u32 reg, rate, num_cs = HSSPI_SPI_MAX_CS;
+	struct reset_control *reset;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
@@ -348,10 +350,20 @@ static int bcm63xx_hsspi_probe(struct platform_device *pdev)
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
+	reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	if (IS_ERR(reset))
+		return PTR_ERR(reset);
+
 	ret = clk_prepare_enable(clk);
 	if (ret)
 		return ret;
 
+	ret = reset_control_reset(reset);
+	if (ret) {
+		dev_err(dev, "unable to reset device: %d\n", ret);
+		goto out_disable_clk;
+	}
+
 	rate = clk_get_rate(clk);
 	if (!rate) {
 		pll_clk = devm_clk_get(dev, "pll");
diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
index 0f1b10a4ef0c..96d075e633f4 100644
--- a/drivers/spi/spi-bcm63xx.c
+++ b/drivers/spi/spi-bcm63xx.c
@@ -18,6 +18,7 @@
 #include <linux/err.h>
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
+#include <linux/reset.h>
 
 /* BCM 6338/6348 SPI core */
 #define SPI_6348_RSET_SIZE		64
@@ -493,6 +494,7 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 	struct bcm63xx_spi *bs;
 	int ret;
 	u32 num_cs = BCM63XX_SPI_MAX_CS;
+	struct reset_control *reset;
 
 	if (dev->of_node) {
 		const struct of_device_id *match;
@@ -529,6 +531,10 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 		return PTR_ERR(clk);
 	}
 
+	reset = devm_reset_control_get_optional_exclusive(dev, NULL);
+	if (IS_ERR(reset))
+		return PTR_ERR(reset);
+
 	master = spi_alloc_master(dev, sizeof(*bs));
 	if (!master) {
 		dev_err(dev, "out of memory\n");
@@ -579,6 +585,12 @@ static int bcm63xx_spi_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_err;
 
+	ret = reset_control_reset(reset);
+	if (ret) {
+		dev_err(dev, "unable to reset device: %d\n", ret);
+		goto out_clk_disable;
+	}
+
 	bcm_spi_writeb(bs, SPI_INTR_CLEAR_ALL, SPI_INT_STATUS);
 
 	/* register and we are done */
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index 68491a8bf7b5..1a7352abd878 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -174,7 +174,7 @@ int spi_bitbang_setup_transfer(struct spi_device *spi, struct spi_transfer *t)
 }
 EXPORT_SYMBOL_GPL(spi_bitbang_setup_transfer);
 
-/**
+/*
  * spi_bitbang_setup - default setup for per-word I/O loops
  */
 int spi_bitbang_setup(struct spi_device *spi)
@@ -208,7 +208,7 @@ int spi_bitbang_setup(struct spi_device *spi)
 }
 EXPORT_SYMBOL_GPL(spi_bitbang_setup);
 
-/**
+/*
  * spi_bitbang_cleanup - default cleanup for per-word I/O loops
  */
 void spi_bitbang_cleanup(struct spi_device *spi)
@@ -427,7 +427,7 @@ int spi_bitbang_start(struct spi_bitbang *bitbang)
 }
 EXPORT_SYMBOL_GPL(spi_bitbang_start);
 
-/**
+/*
  * spi_bitbang_stop - stops the task providing spi communication
  */
 void spi_bitbang_stop(struct spi_bitbang *bitbang)
diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
new file mode 100644
index 000000000000..1c1a9d17eec0
--- /dev/null
+++ b/drivers/spi/spi-cadence-quadspi.c
@@ -0,0 +1,1419 @@
+// SPDX-License-Identifier: GPL-2.0-only
+//
+// Driver for Cadence QSPI Controller
+//
+// Copyright Altera Corporation (C) 2012-2014. All rights reserved.
+// Copyright Intel Corporation (C) 2019-2020. All rights reserved.
+// Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+#include <linux/sched.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+#include <linux/timer.h>
+
+#define CQSPI_NAME			"cadence-qspi"
+#define CQSPI_MAX_CHIPSELECT		16
+
+/* Quirks */
+#define CQSPI_NEEDS_WR_DELAY		BIT(0)
+#define CQSPI_DISABLE_DAC_MODE		BIT(1)
+
+/* Capabilities */
+#define CQSPI_SUPPORTS_OCTAL		BIT(0)
+
+struct cqspi_st;
+
+struct cqspi_flash_pdata {
+	struct cqspi_st	*cqspi;
+	u32		clk_rate;
+	u32		read_delay;
+	u32		tshsl_ns;
+	u32		tsd2d_ns;
+	u32		tchsh_ns;
+	u32		tslch_ns;
+	u8		inst_width;
+	u8		addr_width;
+	u8		data_width;
+	u8		cs;
+};
+
+struct cqspi_st {
+	struct platform_device	*pdev;
+
+	struct clk		*clk;
+	unsigned int		sclk;
+
+	void __iomem		*iobase;
+	void __iomem		*ahb_base;
+	resource_size_t		ahb_size;
+	struct completion	transfer_complete;
+
+	struct dma_chan		*rx_chan;
+	struct completion	rx_dma_complete;
+	dma_addr_t		mmap_phys_base;
+
+	int			current_cs;
+	unsigned long		master_ref_clk_hz;
+	bool			is_decoded_cs;
+	u32			fifo_depth;
+	u32			fifo_width;
+	bool			rclk_en;
+	u32			trigger_address;
+	u32			wr_delay;
+	bool			use_direct_mode;
+	struct cqspi_flash_pdata f_pdata[CQSPI_MAX_CHIPSELECT];
+};
+
+struct cqspi_driver_platdata {
+	u32 hwcaps_mask;
+	u8 quirks;
+};
+
+/* Operation timeout value */
+#define CQSPI_TIMEOUT_MS			500
+#define CQSPI_READ_TIMEOUT_MS			10
+
+/* Instruction type */
+#define CQSPI_INST_TYPE_SINGLE			0
+#define CQSPI_INST_TYPE_DUAL			1
+#define CQSPI_INST_TYPE_QUAD			2
+#define CQSPI_INST_TYPE_OCTAL			3
+
+#define CQSPI_DUMMY_CLKS_PER_BYTE		8
+#define CQSPI_DUMMY_BYTES_MAX			4
+#define CQSPI_DUMMY_CLKS_MAX			31
+
+#define CQSPI_STIG_DATA_LEN_MAX			8
+
+/* Register map */
+#define CQSPI_REG_CONFIG			0x00
+#define CQSPI_REG_CONFIG_ENABLE_MASK		BIT(0)
+#define CQSPI_REG_CONFIG_ENB_DIR_ACC_CTRL	BIT(7)
+#define CQSPI_REG_CONFIG_DECODE_MASK		BIT(9)
+#define CQSPI_REG_CONFIG_CHIPSELECT_LSB		10
+#define CQSPI_REG_CONFIG_DMA_MASK		BIT(15)
+#define CQSPI_REG_CONFIG_BAUD_LSB		19
+#define CQSPI_REG_CONFIG_IDLE_LSB		31
+#define CQSPI_REG_CONFIG_CHIPSELECT_MASK	0xF
+#define CQSPI_REG_CONFIG_BAUD_MASK		0xF
+
+#define CQSPI_REG_RD_INSTR			0x04
+#define CQSPI_REG_RD_INSTR_OPCODE_LSB		0
+#define CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB	8
+#define CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB	12
+#define CQSPI_REG_RD_INSTR_TYPE_DATA_LSB	16
+#define CQSPI_REG_RD_INSTR_MODE_EN_LSB		20
+#define CQSPI_REG_RD_INSTR_DUMMY_LSB		24
+#define CQSPI_REG_RD_INSTR_TYPE_INSTR_MASK	0x3
+#define CQSPI_REG_RD_INSTR_TYPE_ADDR_MASK	0x3
+#define CQSPI_REG_RD_INSTR_TYPE_DATA_MASK	0x3
+#define CQSPI_REG_RD_INSTR_DUMMY_MASK		0x1F
+
+#define CQSPI_REG_WR_INSTR			0x08
+#define CQSPI_REG_WR_INSTR_OPCODE_LSB		0
+#define CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB	12
+#define CQSPI_REG_WR_INSTR_TYPE_DATA_LSB	16
+
+#define CQSPI_REG_DELAY				0x0C
+#define CQSPI_REG_DELAY_TSLCH_LSB		0
+#define CQSPI_REG_DELAY_TCHSH_LSB		8
+#define CQSPI_REG_DELAY_TSD2D_LSB		16
+#define CQSPI_REG_DELAY_TSHSL_LSB		24
+#define CQSPI_REG_DELAY_TSLCH_MASK		0xFF
+#define CQSPI_REG_DELAY_TCHSH_MASK		0xFF
+#define CQSPI_REG_DELAY_TSD2D_MASK		0xFF
+#define CQSPI_REG_DELAY_TSHSL_MASK		0xFF
+
+#define CQSPI_REG_READCAPTURE			0x10
+#define CQSPI_REG_READCAPTURE_BYPASS_LSB	0
+#define CQSPI_REG_READCAPTURE_DELAY_LSB		1
+#define CQSPI_REG_READCAPTURE_DELAY_MASK	0xF
+
+#define CQSPI_REG_SIZE				0x14
+#define CQSPI_REG_SIZE_ADDRESS_LSB		0
+#define CQSPI_REG_SIZE_PAGE_LSB			4
+#define CQSPI_REG_SIZE_BLOCK_LSB		16
+#define CQSPI_REG_SIZE_ADDRESS_MASK		0xF
+#define CQSPI_REG_SIZE_PAGE_MASK		0xFFF
+#define CQSPI_REG_SIZE_BLOCK_MASK		0x3F
+
+#define CQSPI_REG_SRAMPARTITION			0x18
+#define CQSPI_REG_INDIRECTTRIGGER		0x1C
+
+#define CQSPI_REG_DMA				0x20
+#define CQSPI_REG_DMA_SINGLE_LSB		0
+#define CQSPI_REG_DMA_BURST_LSB			8
+#define CQSPI_REG_DMA_SINGLE_MASK		0xFF
+#define CQSPI_REG_DMA_BURST_MASK		0xFF
+
+#define CQSPI_REG_REMAP				0x24
+#define CQSPI_REG_MODE_BIT			0x28
+
+#define CQSPI_REG_SDRAMLEVEL			0x2C
+#define CQSPI_REG_SDRAMLEVEL_RD_LSB		0
+#define CQSPI_REG_SDRAMLEVEL_WR_LSB		16
+#define CQSPI_REG_SDRAMLEVEL_RD_MASK		0xFFFF
+#define CQSPI_REG_SDRAMLEVEL_WR_MASK		0xFFFF
+
+#define CQSPI_REG_IRQSTATUS			0x40
+#define CQSPI_REG_IRQMASK			0x44
+
+#define CQSPI_REG_INDIRECTRD			0x60
+#define CQSPI_REG_INDIRECTRD_START_MASK		BIT(0)
+#define CQSPI_REG_INDIRECTRD_CANCEL_MASK	BIT(1)
+#define CQSPI_REG_INDIRECTRD_DONE_MASK		BIT(5)
+
+#define CQSPI_REG_INDIRECTRDWATERMARK		0x64
+#define CQSPI_REG_INDIRECTRDSTARTADDR		0x68
+#define CQSPI_REG_INDIRECTRDBYTES		0x6C
+
+#define CQSPI_REG_CMDCTRL			0x90
+#define CQSPI_REG_CMDCTRL_EXECUTE_MASK		BIT(0)
+#define CQSPI_REG_CMDCTRL_INPROGRESS_MASK	BIT(1)
+#define CQSPI_REG_CMDCTRL_WR_BYTES_LSB		12
+#define CQSPI_REG_CMDCTRL_WR_EN_LSB		15
+#define CQSPI_REG_CMDCTRL_ADD_BYTES_LSB		16
+#define CQSPI_REG_CMDCTRL_ADDR_EN_LSB		19
+#define CQSPI_REG_CMDCTRL_RD_BYTES_LSB		20
+#define CQSPI_REG_CMDCTRL_RD_EN_LSB		23
+#define CQSPI_REG_CMDCTRL_OPCODE_LSB		24
+#define CQSPI_REG_CMDCTRL_WR_BYTES_MASK		0x7
+#define CQSPI_REG_CMDCTRL_ADD_BYTES_MASK	0x3
+#define CQSPI_REG_CMDCTRL_RD_BYTES_MASK		0x7
+
+#define CQSPI_REG_INDIRECTWR			0x70
+#define CQSPI_REG_INDIRECTWR_START_MASK		BIT(0)
+#define CQSPI_REG_INDIRECTWR_CANCEL_MASK	BIT(1)
+#define CQSPI_REG_INDIRECTWR_DONE_MASK		BIT(5)
+
+#define CQSPI_REG_INDIRECTWRWATERMARK		0x74
+#define CQSPI_REG_INDIRECTWRSTARTADDR		0x78
+#define CQSPI_REG_INDIRECTWRBYTES		0x7C
+
+#define CQSPI_REG_CMDADDRESS			0x94
+#define CQSPI_REG_CMDREADDATALOWER		0xA0
+#define CQSPI_REG_CMDREADDATAUPPER		0xA4
+#define CQSPI_REG_CMDWRITEDATALOWER		0xA8
+#define CQSPI_REG_CMDWRITEDATAUPPER		0xAC
+
+/* Interrupt status bits */
+#define CQSPI_REG_IRQ_MODE_ERR			BIT(0)
+#define CQSPI_REG_IRQ_UNDERFLOW			BIT(1)
+#define CQSPI_REG_IRQ_IND_COMP			BIT(2)
+#define CQSPI_REG_IRQ_IND_RD_REJECT		BIT(3)
+#define CQSPI_REG_IRQ_WR_PROTECTED_ERR		BIT(4)
+#define CQSPI_REG_IRQ_ILLEGAL_AHB_ERR		BIT(5)
+#define CQSPI_REG_IRQ_WATERMARK			BIT(6)
+#define CQSPI_REG_IRQ_IND_SRAM_FULL		BIT(12)
+
+#define CQSPI_IRQ_MASK_RD		(CQSPI_REG_IRQ_WATERMARK	| \
+					 CQSPI_REG_IRQ_IND_SRAM_FULL	| \
+					 CQSPI_REG_IRQ_IND_COMP)
+
+#define CQSPI_IRQ_MASK_WR		(CQSPI_REG_IRQ_IND_COMP		| \
+					 CQSPI_REG_IRQ_WATERMARK	| \
+					 CQSPI_REG_IRQ_UNDERFLOW)
+
+#define CQSPI_IRQ_STATUS_MASK		0x1FFFF
+
+static int cqspi_wait_for_bit(void __iomem *reg, const u32 mask, bool clr)
+{
+	u32 val;
+
+	return readl_relaxed_poll_timeout(reg, val,
+					  (((clr ? ~val : val) & mask) == mask),
+					  10, CQSPI_TIMEOUT_MS * 1000);
+}
+
+static bool cqspi_is_idle(struct cqspi_st *cqspi)
+{
+	u32 reg = readl(cqspi->iobase + CQSPI_REG_CONFIG);
+
+	return reg & (1 << CQSPI_REG_CONFIG_IDLE_LSB);
+}
+
+static u32 cqspi_get_rd_sram_level(struct cqspi_st *cqspi)
+{
+	u32 reg = readl(cqspi->iobase + CQSPI_REG_SDRAMLEVEL);
+
+	reg >>= CQSPI_REG_SDRAMLEVEL_RD_LSB;
+	return reg & CQSPI_REG_SDRAMLEVEL_RD_MASK;
+}
+
+static irqreturn_t cqspi_irq_handler(int this_irq, void *dev)
+{
+	struct cqspi_st *cqspi = dev;
+	unsigned int irq_status;
+
+	/* Read interrupt status */
+	irq_status = readl(cqspi->iobase + CQSPI_REG_IRQSTATUS);
+
+	/* Clear interrupt */
+	writel(irq_status, cqspi->iobase + CQSPI_REG_IRQSTATUS);
+
+	irq_status &= CQSPI_IRQ_MASK_RD | CQSPI_IRQ_MASK_WR;
+
+	if (irq_status)
+		complete(&cqspi->transfer_complete);
+
+	return IRQ_HANDLED;
+}
+
+static unsigned int cqspi_calc_rdreg(struct cqspi_flash_pdata *f_pdata)
+{
+	u32 rdreg = 0;
+
+	rdreg |= f_pdata->inst_width << CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB;
+	rdreg |= f_pdata->addr_width << CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB;
+	rdreg |= f_pdata->data_width << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB;
+
+	return rdreg;
+}
+
+static int cqspi_wait_idle(struct cqspi_st *cqspi)
+{
+	const unsigned int poll_idle_retry = 3;
+	unsigned int count = 0;
+	unsigned long timeout;
+
+	timeout = jiffies + msecs_to_jiffies(CQSPI_TIMEOUT_MS);
+	while (1) {
+		/*
+		 * Read few times in succession to ensure the controller
+		 * is indeed idle, that is, the bit does not transition
+		 * low again.
+		 */
+		if (cqspi_is_idle(cqspi))
+			count++;
+		else
+			count = 0;
+
+		if (count >= poll_idle_retry)
+			return 0;
+
+		if (time_after(jiffies, timeout)) {
+			/* Timeout, in busy mode. */
+			dev_err(&cqspi->pdev->dev,
+				"QSPI is still busy after %dms timeout.\n",
+				CQSPI_TIMEOUT_MS);
+			return -ETIMEDOUT;
+		}
+
+		cpu_relax();
+	}
+}
+
+static int cqspi_exec_flash_cmd(struct cqspi_st *cqspi, unsigned int reg)
+{
+	void __iomem *reg_base = cqspi->iobase;
+	int ret;
+
+	/* Write the CMDCTRL without start execution. */
+	writel(reg, reg_base + CQSPI_REG_CMDCTRL);
+	/* Start execute */
+	reg |= CQSPI_REG_CMDCTRL_EXECUTE_MASK;
+	writel(reg, reg_base + CQSPI_REG_CMDCTRL);
+
+	/* Polling for completion. */
+	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_CMDCTRL,
+				 CQSPI_REG_CMDCTRL_INPROGRESS_MASK, 1);
+	if (ret) {
+		dev_err(&cqspi->pdev->dev,
+			"Flash command execution timed out.\n");
+		return ret;
+	}
+
+	/* Polling QSPI idle status. */
+	return cqspi_wait_idle(cqspi);
+}
+
+static int cqspi_command_read(struct cqspi_flash_pdata *f_pdata,
+			      const struct spi_mem_op *op)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	u8 *rxbuf = op->data.buf.in;
+	u8 opcode = op->cmd.opcode;
+	size_t n_rx = op->data.nbytes;
+	unsigned int rdreg;
+	unsigned int reg;
+	size_t read_len;
+	int status;
+
+	if (!n_rx || n_rx > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) {
+		dev_err(&cqspi->pdev->dev,
+			"Invalid input argument, len %zu rxbuf 0x%p\n",
+			n_rx, rxbuf);
+		return -EINVAL;
+	}
+
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+
+	rdreg = cqspi_calc_rdreg(f_pdata);
+	writel(rdreg, reg_base + CQSPI_REG_RD_INSTR);
+
+	reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB);
+
+	/* 0 means 1 byte. */
+	reg |= (((n_rx - 1) & CQSPI_REG_CMDCTRL_RD_BYTES_MASK)
+		<< CQSPI_REG_CMDCTRL_RD_BYTES_LSB);
+	status = cqspi_exec_flash_cmd(cqspi, reg);
+	if (status)
+		return status;
+
+	reg = readl(reg_base + CQSPI_REG_CMDREADDATALOWER);
+
+	/* Put the read value into rx_buf */
+	read_len = (n_rx > 4) ? 4 : n_rx;
+	memcpy(rxbuf, &reg, read_len);
+	rxbuf += read_len;
+
+	if (n_rx > 4) {
+		reg = readl(reg_base + CQSPI_REG_CMDREADDATAUPPER);
+
+		read_len = n_rx - read_len;
+		memcpy(rxbuf, &reg, read_len);
+	}
+
+	return 0;
+}
+
+static int cqspi_command_write(struct cqspi_flash_pdata *f_pdata,
+			       const struct spi_mem_op *op)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	const u8 opcode = op->cmd.opcode;
+	const u8 *txbuf = op->data.buf.out;
+	size_t n_tx = op->data.nbytes;
+	unsigned int reg;
+	unsigned int data;
+	size_t write_len;
+
+	if (n_tx > CQSPI_STIG_DATA_LEN_MAX || (n_tx && !txbuf)) {
+		dev_err(&cqspi->pdev->dev,
+			"Invalid input argument, cmdlen %zu txbuf 0x%p\n",
+			n_tx, txbuf);
+		return -EINVAL;
+	}
+
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+
+	if (op->addr.nbytes) {
+		reg |= (0x1 << CQSPI_REG_CMDCTRL_ADDR_EN_LSB);
+		reg |= ((op->addr.nbytes - 1) &
+			CQSPI_REG_CMDCTRL_ADD_BYTES_MASK)
+			<< CQSPI_REG_CMDCTRL_ADD_BYTES_LSB;
+
+		writel(op->addr.val, reg_base + CQSPI_REG_CMDADDRESS);
+	}
+
+	if (n_tx) {
+		reg |= (0x1 << CQSPI_REG_CMDCTRL_WR_EN_LSB);
+		reg |= ((n_tx - 1) & CQSPI_REG_CMDCTRL_WR_BYTES_MASK)
+			<< CQSPI_REG_CMDCTRL_WR_BYTES_LSB;
+		data = 0;
+		write_len = (n_tx > 4) ? 4 : n_tx;
+		memcpy(&data, txbuf, write_len);
+		txbuf += write_len;
+		writel(data, reg_base + CQSPI_REG_CMDWRITEDATALOWER);
+
+		if (n_tx > 4) {
+			data = 0;
+			write_len = n_tx - 4;
+			memcpy(&data, txbuf, write_len);
+			writel(data, reg_base + CQSPI_REG_CMDWRITEDATAUPPER);
+		}
+	}
+
+	return cqspi_exec_flash_cmd(cqspi, reg);
+}
+
+static int cqspi_read_setup(struct cqspi_flash_pdata *f_pdata,
+			    const struct spi_mem_op *op)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int dummy_clk = 0;
+	unsigned int reg;
+
+	reg = op->cmd.opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
+	reg |= cqspi_calc_rdreg(f_pdata);
+
+	/* Setup dummy clock cycles */
+	dummy_clk = op->dummy.nbytes * 8;
+	if (dummy_clk > CQSPI_DUMMY_CLKS_MAX)
+		dummy_clk = CQSPI_DUMMY_CLKS_MAX;
+
+	if (dummy_clk)
+		reg |= (dummy_clk & CQSPI_REG_RD_INSTR_DUMMY_MASK)
+		       << CQSPI_REG_RD_INSTR_DUMMY_LSB;
+
+	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
+
+	/* Set address width */
+	reg = readl(reg_base + CQSPI_REG_SIZE);
+	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
+	reg |= (op->addr.nbytes - 1);
+	writel(reg, reg_base + CQSPI_REG_SIZE);
+	return 0;
+}
+
+static int cqspi_indirect_read_execute(struct cqspi_flash_pdata *f_pdata,
+				       u8 *rxbuf, loff_t from_addr,
+				       const size_t n_rx)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	struct device *dev = &cqspi->pdev->dev;
+	void __iomem *reg_base = cqspi->iobase;
+	void __iomem *ahb_base = cqspi->ahb_base;
+	unsigned int remaining = n_rx;
+	unsigned int mod_bytes = n_rx % 4;
+	unsigned int bytes_to_read = 0;
+	u8 *rxbuf_end = rxbuf + n_rx;
+	int ret = 0;
+
+	writel(from_addr, reg_base + CQSPI_REG_INDIRECTRDSTARTADDR);
+	writel(remaining, reg_base + CQSPI_REG_INDIRECTRDBYTES);
+
+	/* Clear all interrupts. */
+	writel(CQSPI_IRQ_STATUS_MASK, reg_base + CQSPI_REG_IRQSTATUS);
+
+	writel(CQSPI_IRQ_MASK_RD, reg_base + CQSPI_REG_IRQMASK);
+
+	reinit_completion(&cqspi->transfer_complete);
+	writel(CQSPI_REG_INDIRECTRD_START_MASK,
+	       reg_base + CQSPI_REG_INDIRECTRD);
+
+	while (remaining > 0) {
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+						 msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
+			ret = -ETIMEDOUT;
+
+		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
+
+		if (ret && bytes_to_read == 0) {
+			dev_err(dev, "Indirect read timeout, no bytes\n");
+			goto failrd;
+		}
+
+		while (bytes_to_read != 0) {
+			unsigned int word_remain = round_down(remaining, 4);
+
+			bytes_to_read *= cqspi->fifo_width;
+			bytes_to_read = bytes_to_read > remaining ?
+					remaining : bytes_to_read;
+			bytes_to_read = round_down(bytes_to_read, 4);
+			/* Read 4 byte word chunks then single bytes */
+			if (bytes_to_read) {
+				ioread32_rep(ahb_base, rxbuf,
+					     (bytes_to_read / 4));
+			} else if (!word_remain && mod_bytes) {
+				unsigned int temp = ioread32(ahb_base);
+
+				bytes_to_read = mod_bytes;
+				memcpy(rxbuf, &temp, min((unsigned int)
+							 (rxbuf_end - rxbuf),
+							 bytes_to_read));
+			}
+			rxbuf += bytes_to_read;
+			remaining -= bytes_to_read;
+			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
+		}
+
+		if (remaining > 0)
+			reinit_completion(&cqspi->transfer_complete);
+	}
+
+	/* Check indirect done status */
+	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_INDIRECTRD,
+				 CQSPI_REG_INDIRECTRD_DONE_MASK, 0);
+	if (ret) {
+		dev_err(dev, "Indirect read completion error (%i)\n", ret);
+		goto failrd;
+	}
+
+	/* Disable interrupt */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Clear indirect completion status */
+	writel(CQSPI_REG_INDIRECTRD_DONE_MASK, reg_base + CQSPI_REG_INDIRECTRD);
+
+	return 0;
+
+failrd:
+	/* Disable interrupt */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Cancel the indirect read */
+	writel(CQSPI_REG_INDIRECTWR_CANCEL_MASK,
+	       reg_base + CQSPI_REG_INDIRECTRD);
+	return ret;
+}
+
+static int cqspi_write_setup(struct cqspi_flash_pdata *f_pdata,
+			     const struct spi_mem_op *op)
+{
+	unsigned int reg;
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+
+	/* Set opcode. */
+	reg = op->cmd.opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
+	writel(reg, reg_base + CQSPI_REG_WR_INSTR);
+	reg = cqspi_calc_rdreg(f_pdata);
+	writel(reg, reg_base + CQSPI_REG_RD_INSTR);
+
+	reg = readl(reg_base + CQSPI_REG_SIZE);
+	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
+	reg |= (op->addr.nbytes - 1);
+	writel(reg, reg_base + CQSPI_REG_SIZE);
+	return 0;
+}
+
+static int cqspi_indirect_write_execute(struct cqspi_flash_pdata *f_pdata,
+					loff_t to_addr, const u8 *txbuf,
+					const size_t n_tx)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	struct device *dev = &cqspi->pdev->dev;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int remaining = n_tx;
+	unsigned int write_bytes;
+	int ret;
+
+	writel(to_addr, reg_base + CQSPI_REG_INDIRECTWRSTARTADDR);
+	writel(remaining, reg_base + CQSPI_REG_INDIRECTWRBYTES);
+
+	/* Clear all interrupts. */
+	writel(CQSPI_IRQ_STATUS_MASK, reg_base + CQSPI_REG_IRQSTATUS);
+
+	writel(CQSPI_IRQ_MASK_WR, reg_base + CQSPI_REG_IRQMASK);
+
+	reinit_completion(&cqspi->transfer_complete);
+	writel(CQSPI_REG_INDIRECTWR_START_MASK,
+	       reg_base + CQSPI_REG_INDIRECTWR);
+	/*
+	 * As per 66AK2G02 TRM SPRUHY8F section 11.15.5.3 Indirect Access
+	 * Controller programming sequence, couple of cycles of
+	 * QSPI_REF_CLK delay is required for the above bit to
+	 * be internally synchronized by the QSPI module. Provide 5
+	 * cycles of delay.
+	 */
+	if (cqspi->wr_delay)
+		ndelay(cqspi->wr_delay);
+
+	while (remaining > 0) {
+		size_t write_words, mod_bytes;
+
+		write_bytes = remaining;
+		write_words = write_bytes / 4;
+		mod_bytes = write_bytes % 4;
+		/* Write 4 bytes at a time then single bytes. */
+		if (write_words) {
+			iowrite32_rep(cqspi->ahb_base, txbuf, write_words);
+			txbuf += (write_words * 4);
+		}
+		if (mod_bytes) {
+			unsigned int temp = 0xFFFFFFFF;
+
+			memcpy(&temp, txbuf, mod_bytes);
+			iowrite32(temp, cqspi->ahb_base);
+			txbuf += mod_bytes;
+		}
+
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+						 msecs_to_jiffies(CQSPI_TIMEOUT_MS))) {
+			dev_err(dev, "Indirect write timeout\n");
+			ret = -ETIMEDOUT;
+			goto failwr;
+		}
+
+		remaining -= write_bytes;
+
+		if (remaining > 0)
+			reinit_completion(&cqspi->transfer_complete);
+	}
+
+	/* Check indirect done status */
+	ret = cqspi_wait_for_bit(reg_base + CQSPI_REG_INDIRECTWR,
+				 CQSPI_REG_INDIRECTWR_DONE_MASK, 0);
+	if (ret) {
+		dev_err(dev, "Indirect write completion error (%i)\n", ret);
+		goto failwr;
+	}
+
+	/* Disable interrupt. */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Clear indirect completion status */
+	writel(CQSPI_REG_INDIRECTWR_DONE_MASK, reg_base + CQSPI_REG_INDIRECTWR);
+
+	cqspi_wait_idle(cqspi);
+
+	return 0;
+
+failwr:
+	/* Disable interrupt. */
+	writel(0, reg_base + CQSPI_REG_IRQMASK);
+
+	/* Cancel the indirect write */
+	writel(CQSPI_REG_INDIRECTWR_CANCEL_MASK,
+	       reg_base + CQSPI_REG_INDIRECTWR);
+	return ret;
+}
+
+static void cqspi_chipselect(struct cqspi_flash_pdata *f_pdata)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int chip_select = f_pdata->cs;
+	unsigned int reg;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+	if (cqspi->is_decoded_cs) {
+		reg |= CQSPI_REG_CONFIG_DECODE_MASK;
+	} else {
+		reg &= ~CQSPI_REG_CONFIG_DECODE_MASK;
+
+		/* Convert CS if without decoder.
+		 * CS0 to 4b'1110
+		 * CS1 to 4b'1101
+		 * CS2 to 4b'1011
+		 * CS3 to 4b'0111
+		 */
+		chip_select = 0xF & ~(1 << chip_select);
+	}
+
+	reg &= ~(CQSPI_REG_CONFIG_CHIPSELECT_MASK
+		 << CQSPI_REG_CONFIG_CHIPSELECT_LSB);
+	reg |= (chip_select & CQSPI_REG_CONFIG_CHIPSELECT_MASK)
+	    << CQSPI_REG_CONFIG_CHIPSELECT_LSB;
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+}
+
+static unsigned int calculate_ticks_for_ns(const unsigned int ref_clk_hz,
+					   const unsigned int ns_val)
+{
+	unsigned int ticks;
+
+	ticks = ref_clk_hz / 1000;	/* kHz */
+	ticks = DIV_ROUND_UP(ticks * ns_val, 1000000);
+
+	return ticks;
+}
+
+static void cqspi_delay(struct cqspi_flash_pdata *f_pdata)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	void __iomem *iobase = cqspi->iobase;
+	const unsigned int ref_clk_hz = cqspi->master_ref_clk_hz;
+	unsigned int tshsl, tchsh, tslch, tsd2d;
+	unsigned int reg;
+	unsigned int tsclk;
+
+	/* calculate the number of ref ticks for one sclk tick */
+	tsclk = DIV_ROUND_UP(ref_clk_hz, cqspi->sclk);
+
+	tshsl = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tshsl_ns);
+	/* this particular value must be at least one sclk */
+	if (tshsl < tsclk)
+		tshsl = tsclk;
+
+	tchsh = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tchsh_ns);
+	tslch = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tslch_ns);
+	tsd2d = calculate_ticks_for_ns(ref_clk_hz, f_pdata->tsd2d_ns);
+
+	reg = (tshsl & CQSPI_REG_DELAY_TSHSL_MASK)
+	       << CQSPI_REG_DELAY_TSHSL_LSB;
+	reg |= (tchsh & CQSPI_REG_DELAY_TCHSH_MASK)
+		<< CQSPI_REG_DELAY_TCHSH_LSB;
+	reg |= (tslch & CQSPI_REG_DELAY_TSLCH_MASK)
+		<< CQSPI_REG_DELAY_TSLCH_LSB;
+	reg |= (tsd2d & CQSPI_REG_DELAY_TSD2D_MASK)
+		<< CQSPI_REG_DELAY_TSD2D_LSB;
+	writel(reg, iobase + CQSPI_REG_DELAY);
+}
+
+static void cqspi_config_baudrate_div(struct cqspi_st *cqspi)
+{
+	const unsigned int ref_clk_hz = cqspi->master_ref_clk_hz;
+	void __iomem *reg_base = cqspi->iobase;
+	u32 reg, div;
+
+	/* Recalculate the baudrate divisor based on QSPI specification. */
+	div = DIV_ROUND_UP(ref_clk_hz, 2 * cqspi->sclk) - 1;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+	reg &= ~(CQSPI_REG_CONFIG_BAUD_MASK << CQSPI_REG_CONFIG_BAUD_LSB);
+	reg |= (div & CQSPI_REG_CONFIG_BAUD_MASK) << CQSPI_REG_CONFIG_BAUD_LSB;
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+}
+
+static void cqspi_readdata_capture(struct cqspi_st *cqspi,
+				   const bool bypass,
+				   const unsigned int delay)
+{
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+
+	reg = readl(reg_base + CQSPI_REG_READCAPTURE);
+
+	if (bypass)
+		reg |= (1 << CQSPI_REG_READCAPTURE_BYPASS_LSB);
+	else
+		reg &= ~(1 << CQSPI_REG_READCAPTURE_BYPASS_LSB);
+
+	reg &= ~(CQSPI_REG_READCAPTURE_DELAY_MASK
+		 << CQSPI_REG_READCAPTURE_DELAY_LSB);
+
+	reg |= (delay & CQSPI_REG_READCAPTURE_DELAY_MASK)
+		<< CQSPI_REG_READCAPTURE_DELAY_LSB;
+
+	writel(reg, reg_base + CQSPI_REG_READCAPTURE);
+}
+
+static void cqspi_controller_enable(struct cqspi_st *cqspi, bool enable)
+{
+	void __iomem *reg_base = cqspi->iobase;
+	unsigned int reg;
+
+	reg = readl(reg_base + CQSPI_REG_CONFIG);
+
+	if (enable)
+		reg |= CQSPI_REG_CONFIG_ENABLE_MASK;
+	else
+		reg &= ~CQSPI_REG_CONFIG_ENABLE_MASK;
+
+	writel(reg, reg_base + CQSPI_REG_CONFIG);
+}
+
+static void cqspi_configure(struct cqspi_flash_pdata *f_pdata,
+			    unsigned long sclk)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	int switch_cs = (cqspi->current_cs != f_pdata->cs);
+	int switch_ck = (cqspi->sclk != sclk);
+
+	if (switch_cs || switch_ck)
+		cqspi_controller_enable(cqspi, 0);
+
+	/* Switch chip select. */
+	if (switch_cs) {
+		cqspi->current_cs = f_pdata->cs;
+		cqspi_chipselect(f_pdata);
+	}
+
+	/* Setup baudrate divisor and delays */
+	if (switch_ck) {
+		cqspi->sclk = sclk;
+		cqspi_config_baudrate_div(cqspi);
+		cqspi_delay(f_pdata);
+		cqspi_readdata_capture(cqspi, !cqspi->rclk_en,
+				       f_pdata->read_delay);
+	}
+
+	if (switch_cs || switch_ck)
+		cqspi_controller_enable(cqspi, 1);
+}
+
+static int cqspi_set_protocol(struct cqspi_flash_pdata *f_pdata,
+			      const struct spi_mem_op *op)
+{
+	f_pdata->inst_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->addr_width = CQSPI_INST_TYPE_SINGLE;
+	f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
+
+	if (op->data.dir == SPI_MEM_DATA_IN) {
+		switch (op->data.buswidth) {
+		case 1:
+			f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
+			break;
+		case 2:
+			f_pdata->data_width = CQSPI_INST_TYPE_DUAL;
+			break;
+		case 4:
+			f_pdata->data_width = CQSPI_INST_TYPE_QUAD;
+			break;
+		case 8:
+			f_pdata->data_width = CQSPI_INST_TYPE_OCTAL;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static ssize_t cqspi_write(struct cqspi_flash_pdata *f_pdata,
+			   const struct spi_mem_op *op)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	loff_t to = op->addr.val;
+	size_t len = op->data.nbytes;
+	const u_char *buf = op->data.buf.out;
+	int ret;
+
+	ret = cqspi_set_protocol(f_pdata, op);
+	if (ret)
+		return ret;
+
+	ret = cqspi_write_setup(f_pdata, op);
+	if (ret)
+		return ret;
+
+	if (cqspi->use_direct_mode && ((to + len) <= cqspi->ahb_size)) {
+		memcpy_toio(cqspi->ahb_base + to, buf, len);
+		return cqspi_wait_idle(cqspi);
+	}
+
+	return cqspi_indirect_write_execute(f_pdata, to, buf, len);
+}
+
+static void cqspi_rx_dma_callback(void *param)
+{
+	struct cqspi_st *cqspi = param;
+
+	complete(&cqspi->rx_dma_complete);
+}
+
+static int cqspi_direct_read_execute(struct cqspi_flash_pdata *f_pdata,
+				     u_char *buf, loff_t from, size_t len)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	struct device *dev = &cqspi->pdev->dev;
+	enum dma_ctrl_flags flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
+	dma_addr_t dma_src = (dma_addr_t)cqspi->mmap_phys_base + from;
+	int ret = 0;
+	struct dma_async_tx_descriptor *tx;
+	dma_cookie_t cookie;
+	dma_addr_t dma_dst;
+
+	if (!cqspi->rx_chan || !virt_addr_valid(buf)) {
+		memcpy_fromio(buf, cqspi->ahb_base + from, len);
+		return 0;
+	}
+
+	dma_dst = dma_map_single(dev, buf, len, DMA_FROM_DEVICE);
+	if (dma_mapping_error(dev, dma_dst)) {
+		dev_err(dev, "dma mapping failed\n");
+		return -ENOMEM;
+	}
+	tx = dmaengine_prep_dma_memcpy(cqspi->rx_chan, dma_dst, dma_src,
+				       len, flags);
+	if (!tx) {
+		dev_err(dev, "device_prep_dma_memcpy error\n");
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	tx->callback = cqspi_rx_dma_callback;
+	tx->callback_param = cqspi;
+	cookie = tx->tx_submit(tx);
+	reinit_completion(&cqspi->rx_dma_complete);
+
+	ret = dma_submit_error(cookie);
+	if (ret) {
+		dev_err(dev, "dma_submit_error %d\n", cookie);
+		ret = -EIO;
+		goto err_unmap;
+	}
+
+	dma_async_issue_pending(cqspi->rx_chan);
+	if (!wait_for_completion_timeout(&cqspi->rx_dma_complete,
+					 msecs_to_jiffies(len))) {
+		dmaengine_terminate_sync(cqspi->rx_chan);
+		dev_err(dev, "DMA wait_for_completion_timeout\n");
+		ret = -ETIMEDOUT;
+		goto err_unmap;
+	}
+
+err_unmap:
+	dma_unmap_single(dev, dma_dst, len, DMA_FROM_DEVICE);
+
+	return ret;
+}
+
+static ssize_t cqspi_read(struct cqspi_flash_pdata *f_pdata,
+			  const struct spi_mem_op *op)
+{
+	struct cqspi_st *cqspi = f_pdata->cqspi;
+	loff_t from = op->addr.val;
+	size_t len = op->data.nbytes;
+	u_char *buf = op->data.buf.in;
+	int ret;
+
+	ret = cqspi_set_protocol(f_pdata, op);
+	if (ret)
+		return ret;
+
+	ret = cqspi_read_setup(f_pdata, op);
+	if (ret)
+		return ret;
+
+	if (cqspi->use_direct_mode && ((from + len) <= cqspi->ahb_size))
+		return cqspi_direct_read_execute(f_pdata, buf, from, len);
+
+	return cqspi_indirect_read_execute(f_pdata, buf, from, len);
+}
+
+static int cqspi_mem_process(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+	struct cqspi_st *cqspi = spi_master_get_devdata(mem->spi->master);
+	struct cqspi_flash_pdata *f_pdata;
+
+	f_pdata = &cqspi->f_pdata[mem->spi->chip_select];
+	cqspi_configure(f_pdata, mem->spi->max_speed_hz);
+
+	if (op->data.dir == SPI_MEM_DATA_IN && op->data.buf.in) {
+		if (!op->addr.nbytes)
+			return cqspi_command_read(f_pdata, op);
+
+		return cqspi_read(f_pdata, op);
+	}
+
+	if (!op->addr.nbytes || !op->data.buf.out)
+		return cqspi_command_write(f_pdata, op);
+
+	return cqspi_write(f_pdata, op);
+}
+
+static int cqspi_exec_mem_op(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+	int ret;
+
+	ret = cqspi_mem_process(mem, op);
+	if (ret)
+		dev_err(&mem->spi->dev, "operation failed with %d\n", ret);
+
+	return ret;
+}
+
+static int cqspi_of_get_flash_pdata(struct platform_device *pdev,
+				    struct cqspi_flash_pdata *f_pdata,
+				    struct device_node *np)
+{
+	if (of_property_read_u32(np, "cdns,read-delay", &f_pdata->read_delay)) {
+		dev_err(&pdev->dev, "couldn't determine read-delay\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tshsl-ns", &f_pdata->tshsl_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tshsl-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tsd2d-ns", &f_pdata->tsd2d_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tsd2d-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tchsh-ns", &f_pdata->tchsh_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tchsh-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,tslch-ns", &f_pdata->tslch_ns)) {
+		dev_err(&pdev->dev, "couldn't determine tslch-ns\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "spi-max-frequency", &f_pdata->clk_rate)) {
+		dev_err(&pdev->dev, "couldn't determine spi-max-frequency\n");
+		return -ENXIO;
+	}
+
+	return 0;
+}
+
+static int cqspi_of_get_pdata(struct cqspi_st *cqspi)
+{
+	struct device *dev = &cqspi->pdev->dev;
+	struct device_node *np = dev->of_node;
+
+	cqspi->is_decoded_cs = of_property_read_bool(np, "cdns,is-decoded-cs");
+
+	if (of_property_read_u32(np, "cdns,fifo-depth", &cqspi->fifo_depth)) {
+		dev_err(dev, "couldn't determine fifo-depth\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,fifo-width", &cqspi->fifo_width)) {
+		dev_err(dev, "couldn't determine fifo-width\n");
+		return -ENXIO;
+	}
+
+	if (of_property_read_u32(np, "cdns,trigger-address",
+				 &cqspi->trigger_address)) {
+		dev_err(dev, "couldn't determine trigger-address\n");
+		return -ENXIO;
+	}
+
+	cqspi->rclk_en = of_property_read_bool(np, "cdns,rclk-en");
+
+	return 0;
+}
+
+static void cqspi_controller_init(struct cqspi_st *cqspi)
+{
+	u32 reg;
+
+	cqspi_controller_enable(cqspi, 0);
+
+	/* Configure the remap address register, no remap */
+	writel(0, cqspi->iobase + CQSPI_REG_REMAP);
+
+	/* Disable all interrupts. */
+	writel(0, cqspi->iobase + CQSPI_REG_IRQMASK);
+
+	/* Configure the SRAM split to 1:1 . */
+	writel(cqspi->fifo_depth / 2, cqspi->iobase + CQSPI_REG_SRAMPARTITION);
+
+	/* Load indirect trigger address. */
+	writel(cqspi->trigger_address,
+	       cqspi->iobase + CQSPI_REG_INDIRECTTRIGGER);
+
+	/* Program read watermark -- 1/2 of the FIFO. */
+	writel(cqspi->fifo_depth * cqspi->fifo_width / 2,
+	       cqspi->iobase + CQSPI_REG_INDIRECTRDWATERMARK);
+	/* Program write watermark -- 1/8 of the FIFO. */
+	writel(cqspi->fifo_depth * cqspi->fifo_width / 8,
+	       cqspi->iobase + CQSPI_REG_INDIRECTWRWATERMARK);
+
+	/* Enable Direct Access Controller */
+	reg = readl(cqspi->iobase + CQSPI_REG_CONFIG);
+	reg |= CQSPI_REG_CONFIG_ENB_DIR_ACC_CTRL;
+	writel(reg, cqspi->iobase + CQSPI_REG_CONFIG);
+
+	cqspi_controller_enable(cqspi, 1);
+}
+
+static int cqspi_request_mmap_dma(struct cqspi_st *cqspi)
+{
+	dma_cap_mask_t mask;
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_MEMCPY, mask);
+
+	cqspi->rx_chan = dma_request_chan_by_mask(&mask);
+	if (IS_ERR(cqspi->rx_chan)) {
+		int ret = PTR_ERR(cqspi->rx_chan);
+
+		if (ret != -EPROBE_DEFER)
+			dev_err(&cqspi->pdev->dev, "No Rx DMA available\n");
+		cqspi->rx_chan = NULL;
+		return ret;
+	}
+	init_completion(&cqspi->rx_dma_complete);
+
+	return 0;
+}
+
+static const struct spi_controller_mem_ops cqspi_mem_ops = {
+	.exec_op = cqspi_exec_mem_op,
+};
+
+static int cqspi_setup_flash(struct cqspi_st *cqspi)
+{
+	struct platform_device *pdev = cqspi->pdev;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct cqspi_flash_pdata *f_pdata;
+	unsigned int cs;
+	int ret;
+
+	/* Get flash device data */
+	for_each_available_child_of_node(dev->of_node, np) {
+		ret = of_property_read_u32(np, "reg", &cs);
+		if (ret) {
+			dev_err(dev, "Couldn't determine chip select.\n");
+			return ret;
+		}
+
+		if (cs >= CQSPI_MAX_CHIPSELECT) {
+			dev_err(dev, "Chip select %d out of range.\n", cs);
+			return -EINVAL;
+		}
+
+		f_pdata = &cqspi->f_pdata[cs];
+		f_pdata->cqspi = cqspi;
+		f_pdata->cs = cs;
+
+		ret = cqspi_of_get_flash_pdata(pdev, f_pdata, np);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int cqspi_probe(struct platform_device *pdev)
+{
+	const struct cqspi_driver_platdata *ddata;
+	struct reset_control *rstc, *rstc_ocp;
+	struct device *dev = &pdev->dev;
+	struct spi_master *master;
+	struct resource *res_ahb;
+	struct cqspi_st *cqspi;
+	struct resource *res;
+	int ret;
+	int irq;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*cqspi));
+	if (!master) {
+		dev_err(&pdev->dev, "spi_alloc_master failed\n");
+		return -ENOMEM;
+	}
+	master->mode_bits = SPI_RX_QUAD | SPI_RX_DUAL;
+	master->mem_ops = &cqspi_mem_ops;
+	master->dev.of_node = pdev->dev.of_node;
+
+	cqspi = spi_master_get_devdata(master);
+
+	cqspi->pdev = pdev;
+
+	/* Obtain configuration from OF. */
+	ret = cqspi_of_get_pdata(cqspi);
+	if (ret) {
+		dev_err(dev, "Cannot get mandatory OF data.\n");
+		ret = -ENODEV;
+		goto probe_master_put;
+	}
+
+	/* Obtain QSPI clock. */
+	cqspi->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(cqspi->clk)) {
+		dev_err(dev, "Cannot claim QSPI clock.\n");
+		ret = PTR_ERR(cqspi->clk);
+		goto probe_master_put;
+	}
+
+	/* Obtain and remap controller address. */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cqspi->iobase = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cqspi->iobase)) {
+		dev_err(dev, "Cannot remap controller address.\n");
+		ret = PTR_ERR(cqspi->iobase);
+		goto probe_master_put;
+	}
+
+	/* Obtain and remap AHB address. */
+	res_ahb = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	cqspi->ahb_base = devm_ioremap_resource(dev, res_ahb);
+	if (IS_ERR(cqspi->ahb_base)) {
+		dev_err(dev, "Cannot remap AHB address.\n");
+		ret = PTR_ERR(cqspi->ahb_base);
+		goto probe_master_put;
+	}
+	cqspi->mmap_phys_base = (dma_addr_t)res_ahb->start;
+	cqspi->ahb_size = resource_size(res_ahb);
+
+	init_completion(&cqspi->transfer_complete);
+
+	/* Obtain IRQ line. */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		ret = -ENXIO;
+		goto probe_master_put;
+	}
+
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(dev);
+		goto probe_master_put;
+	}
+
+	ret = clk_prepare_enable(cqspi->clk);
+	if (ret) {
+		dev_err(dev, "Cannot enable QSPI clock.\n");
+		goto probe_clk_failed;
+	}
+
+	/* Obtain QSPI reset control */
+	rstc = devm_reset_control_get_optional_exclusive(dev, "qspi");
+	if (IS_ERR(rstc)) {
+		dev_err(dev, "Cannot get QSPI reset.\n");
+		goto probe_reset_failed;
+	}
+
+	rstc_ocp = devm_reset_control_get_optional_exclusive(dev, "qspi-ocp");
+	if (IS_ERR(rstc_ocp)) {
+		dev_err(dev, "Cannot get QSPI OCP reset.\n");
+		goto probe_reset_failed;
+	}
+
+	reset_control_assert(rstc);
+	reset_control_deassert(rstc);
+
+	reset_control_assert(rstc_ocp);
+	reset_control_deassert(rstc_ocp);
+
+	cqspi->master_ref_clk_hz = clk_get_rate(cqspi->clk);
+	ddata  = of_device_get_match_data(dev);
+	if (ddata) {
+		if (ddata->quirks & CQSPI_NEEDS_WR_DELAY)
+			cqspi->wr_delay = 5 * DIV_ROUND_UP(NSEC_PER_SEC,
+						cqspi->master_ref_clk_hz);
+		if (ddata->hwcaps_mask & CQSPI_SUPPORTS_OCTAL)
+			master->mode_bits |= SPI_RX_OCTAL;
+		if (!(ddata->quirks & CQSPI_DISABLE_DAC_MODE))
+			cqspi->use_direct_mode = true;
+	}
+
+	ret = devm_request_irq(dev, irq, cqspi_irq_handler, 0,
+			       pdev->name, cqspi);
+	if (ret) {
+		dev_err(dev, "Cannot request IRQ.\n");
+		goto probe_reset_failed;
+	}
+
+	cqspi_wait_idle(cqspi);
+	cqspi_controller_init(cqspi);
+	cqspi->current_cs = -1;
+	cqspi->sclk = 0;
+
+	ret = cqspi_setup_flash(cqspi);
+	if (ret) {
+		dev_err(dev, "failed to setup flash parameters %d\n", ret);
+		goto probe_setup_failed;
+	}
+
+	if (cqspi->use_direct_mode) {
+		ret = cqspi_request_mmap_dma(cqspi);
+		if (ret == -EPROBE_DEFER)
+			goto probe_setup_failed;
+	}
+
+	ret = devm_spi_register_master(dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register SPI ctlr %d\n", ret);
+		goto probe_setup_failed;
+	}
+
+	return 0;
+probe_setup_failed:
+	cqspi_controller_enable(cqspi, 0);
+probe_reset_failed:
+	clk_disable_unprepare(cqspi->clk);
+probe_clk_failed:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+probe_master_put:
+	spi_master_put(master);
+	return ret;
+}
+
+static int cqspi_remove(struct platform_device *pdev)
+{
+	struct cqspi_st *cqspi = platform_get_drvdata(pdev);
+
+	cqspi_controller_enable(cqspi, 0);
+
+	if (cqspi->rx_chan)
+		dma_release_channel(cqspi->rx_chan);
+
+	clk_disable_unprepare(cqspi->clk);
+
+	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_disable(&pdev->dev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int cqspi_suspend(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	cqspi_controller_enable(cqspi, 0);
+	return 0;
+}
+
+static int cqspi_resume(struct device *dev)
+{
+	struct cqspi_st *cqspi = dev_get_drvdata(dev);
+
+	cqspi_controller_enable(cqspi, 1);
+	return 0;
+}
+
+static const struct dev_pm_ops cqspi__dev_pm_ops = {
+	.suspend = cqspi_suspend,
+	.resume = cqspi_resume,
+};
+
+#define CQSPI_DEV_PM_OPS	(&cqspi__dev_pm_ops)
+#else
+#define CQSPI_DEV_PM_OPS	NULL
+#endif
+
+static const struct cqspi_driver_platdata cdns_qspi = {
+	.quirks = CQSPI_DISABLE_DAC_MODE,
+};
+
+static const struct cqspi_driver_platdata k2g_qspi = {
+	.quirks = CQSPI_NEEDS_WR_DELAY,
+};
+
+static const struct cqspi_driver_platdata am654_ospi = {
+	.hwcaps_mask = CQSPI_SUPPORTS_OCTAL,
+	.quirks = CQSPI_NEEDS_WR_DELAY,
+};
+
+static const struct of_device_id cqspi_dt_ids[] = {
+	{
+		.compatible = "cdns,qspi-nor",
+		.data = &cdns_qspi,
+	},
+	{
+		.compatible = "ti,k2g-qspi",
+		.data = &k2g_qspi,
+	},
+	{
+		.compatible = "ti,am654-ospi",
+		.data = &am654_ospi,
+	},
+	{ /* end of table */ }
+};
+
+MODULE_DEVICE_TABLE(of, cqspi_dt_ids);
+
+static struct platform_driver cqspi_platform_driver = {
+	.probe = cqspi_probe,
+	.remove = cqspi_remove,
+	.driver = {
+		.name = CQSPI_NAME,
+		.pm = CQSPI_DEV_PM_OPS,
+		.of_match_table = cqspi_dt_ids,
+	},
+};
+
+module_platform_driver(cqspi_platform_driver);
+
+MODULE_DESCRIPTION("Cadence QSPI Controller Driver");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:" CQSPI_NAME);
+MODULE_AUTHOR("Ley Foon Tan <lftan@altera.com>");
+MODULE_AUTHOR("Graham Moore <grmoore@opensource.altera.com>");
+MODULE_AUTHOR("Vadivel Murugan R <vadivel.muruganx.ramuthevar@intel.com>");
+MODULE_AUTHOR("Vignesh Raghavendra <vigneshr@ti.com>");
diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index 82a0ee09cbe1..2b6b9c1ad9d0 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -556,7 +556,7 @@ static int cdns_spi_probe(struct platform_device *pdev)
 	master->unprepare_transfer_hardware = cdns_unprepare_transfer_hardware;
 	master->set_cs = cdns_spi_chipselect;
 	master->auto_runtime_pm = true;
-	master->mode_bits = SPI_CPOL | SPI_CPHA;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 
 	/* Set to default valid value */
 	master->max_speed_hz = clk_get_rate(xspi->ref_clk) / 4;
diff --git a/drivers/spi/spi-cavium-thunderx.c b/drivers/spi/spi-cavium-thunderx.c
index fd6b9caffaf0..60c0d6934654 100644
--- a/drivers/spi/spi-cavium-thunderx.c
+++ b/drivers/spi/spi-cavium-thunderx.c
@@ -64,6 +64,7 @@ static int thunderx_spi_probe(struct pci_dev *pdev,
 		p->sys_freq = SYS_FREQ_DEFAULT;
 	dev_info(dev, "Set system clock to %u\n", p->sys_freq);
 
+	master->flags = SPI_MASTER_HALF_DUPLEX;
 	master->num_chipselect = 4;
 	master->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH |
 			    SPI_LSB_FIRST | SPI_3WIRE;
diff --git a/drivers/spi/spi-coldfire-qspi.c b/drivers/spi/spi-coldfire-qspi.c
index f80e06c87fbe..8996115ce736 100644
--- a/drivers/spi/spi-coldfire-qspi.c
+++ b/drivers/spi/spi-coldfire-qspi.c
@@ -387,7 +387,7 @@ static int mcfqspi_probe(struct platform_device *pdev)
 		status = PTR_ERR(mcfqspi->clk);
 		goto fail0;
 	}
-	clk_enable(mcfqspi->clk);
+	clk_prepare_enable(mcfqspi->clk);
 
 	master->bus_num = pdata->bus_num;
 	master->num_chipselect = pdata->num_chipselect;
@@ -425,7 +425,7 @@ fail2:
 	pm_runtime_disable(&pdev->dev);
 	mcfqspi_cs_teardown(mcfqspi);
 fail1:
-	clk_disable(mcfqspi->clk);
+	clk_disable_unprepare(mcfqspi->clk);
 fail0:
 	spi_master_put(master);
 
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index f71c497393a6..c329a27c16ac 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -236,7 +236,8 @@ static void davinci_spi_chipselect(struct spi_device *spi, int value)
 
 /**
  * davinci_spi_get_prescale - Calculates the correct prescale value
- * @maxspeed_hz: the maximum rate the SPI clock can run at
+ * @dspi: the controller data
+ * @max_speed_hz: the maximum rate the SPI clock can run at
  *
  * This function calculates the prescale value that generates a clock rate
  * less than or equal to the specified maximum.
@@ -711,7 +712,7 @@ err_desc:
 /**
  * dummy_thread_fn - dummy thread function
  * @irq: IRQ number for this SPI Master
- * @context_data: structure for SPI Master controller davinci_spi
+ * @data: structure for SPI Master controller davinci_spi
  *
  * This is to satisfy the request_threaded_irq() API so that the irq
  * handler is called in interrupt context.
@@ -724,7 +725,7 @@ static irqreturn_t dummy_thread_fn(s32 irq, void *data)
 /**
  * davinci_spi_irq - Interrupt handler for SPI Master Controller
  * @irq: IRQ number for this SPI Master
- * @context_data: structure for SPI Master controller davinci_spi
+ * @data: structure for SPI Master controller davinci_spi
  *
  * ISR will determine that interrupt arrives either for READ or WRITE command.
  * According to command it will do the appropriate action. It will check
diff --git a/drivers/spi/spi-ep93xx.c b/drivers/spi/spi-ep93xx.c
index 8c854b187b1d..aa676559d273 100644
--- a/drivers/spi/spi-ep93xx.c
+++ b/drivers/spi/spi-ep93xx.c
@@ -10,7 +10,7 @@
  *
  * For more information about the SPI controller see documentation on Cirrus
  * Logic web site:
- *     http://www.cirrus.com/en/pubs/manual/EP93xx_Users_Guide_UM1.pdf
+ *     https://www.cirrus.com/en/pubs/manual/EP93xx_Users_Guide_UM1.pdf
  */
 
 #include <linux/io.h>
@@ -214,7 +214,7 @@ static void ep93xx_do_read(struct spi_master *master)
 
 /**
  * ep93xx_spi_read_write() - perform next RX/TX transfer
- * @espi: ep93xx SPI controller struct
+ * @master: SPI master
  *
  * This function transfers next bytes (or half-words) to/from RX/TX FIFOs. If
  * called several times, the whole transfer will be completed. Returns
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index 1552b28b9515..85a5c952389a 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -11,7 +11,6 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
@@ -19,11 +18,9 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/dma-imx.h>
-#include <linux/platform_data/spi-imx.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
@@ -101,6 +98,7 @@ struct fsl_lpspi_data {
 	struct clk *clk_ipg;
 	struct clk *clk_per;
 	bool is_slave;
+	bool is_only_cs1;
 	bool is_first_byte;
 
 	void *rx_buf;
@@ -122,8 +120,6 @@ struct fsl_lpspi_data {
 	bool usedma;
 	struct completion dma_rx_completion;
 	struct completion dma_tx_completion;
-
-	int chipselect[];
 };
 
 static const struct of_device_id fsl_lpspi_dt_ids[] = {
@@ -224,20 +220,6 @@ static int lpspi_unprepare_xfer_hardware(struct spi_controller *controller)
 	return 0;
 }
 
-static int fsl_lpspi_prepare_message(struct spi_controller *controller,
-				     struct spi_message *msg)
-{
-	struct fsl_lpspi_data *fsl_lpspi =
-					spi_controller_get_devdata(controller);
-	struct spi_device *spi = msg->spi;
-	int gpio = fsl_lpspi->chipselect[spi->chip_select];
-
-	if (gpio_is_valid(gpio))
-		gpio_direction_output(gpio, spi->mode & SPI_CS_HIGH ? 0 : 1);
-
-	return 0;
-}
-
 static void fsl_lpspi_write_tx_fifo(struct fsl_lpspi_data *fsl_lpspi)
 {
 	u8 txfifo_cnt;
@@ -276,10 +258,9 @@ static void fsl_lpspi_set_cmd(struct fsl_lpspi_data *fsl_lpspi)
 
 	temp |= fsl_lpspi->config.bpw - 1;
 	temp |= (fsl_lpspi->config.mode & 0x3) << 30;
+	temp |= (fsl_lpspi->config.chip_select & 0x3) << 24;
 	if (!fsl_lpspi->is_slave) {
 		temp |= fsl_lpspi->config.prescale << 27;
-		temp |= (fsl_lpspi->config.chip_select & 0x3) << 24;
-
 		/*
 		 * Set TCR_CONT will keep SS asserted after current transfer.
 		 * For the first transfer, clear TCR_CONTC to assert SS.
@@ -440,7 +421,10 @@ static int fsl_lpspi_setup_transfer(struct spi_controller *controller,
 	fsl_lpspi->config.mode = spi->mode;
 	fsl_lpspi->config.bpw = t->bits_per_word;
 	fsl_lpspi->config.speed_hz = t->speed_hz;
-	fsl_lpspi->config.chip_select = spi->chip_select;
+	if (fsl_lpspi->is_only_cs1)
+		fsl_lpspi->config.chip_select = 1;
+	else
+		fsl_lpspi->config.chip_select = spi->chip_select;
 
 	if (!fsl_lpspi->config.speed_hz)
 		fsl_lpspi->config.speed_hz = spi->max_speed_hz;
@@ -831,13 +815,10 @@ static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
 
 static int fsl_lpspi_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
 	struct fsl_lpspi_data *fsl_lpspi;
 	struct spi_controller *controller;
-	struct spi_imx_master *lpspi_platform_info =
-		dev_get_platdata(&pdev->dev);
 	struct resource *res;
-	int i, ret, irq;
+	int ret, irq;
 	u32 temp;
 	bool is_slave;
 
@@ -857,6 +838,8 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	fsl_lpspi = spi_controller_get_devdata(controller);
 	fsl_lpspi->dev = &pdev->dev;
 	fsl_lpspi->is_slave = is_slave;
+	fsl_lpspi->is_only_cs1 = of_property_read_bool((&pdev->dev)->of_node,
+						"fsl,spi-only-use-cs1-sel");
 
 	controller->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 32);
 	controller->transfer_one = fsl_lpspi_transfer_one;
@@ -867,35 +850,8 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	controller->dev.of_node = pdev->dev.of_node;
 	controller->bus_num = pdev->id;
 	controller->slave_abort = fsl_lpspi_slave_abort;
-
-	ret = devm_spi_register_controller(&pdev->dev, controller);
-	if (ret < 0) {
-		dev_err(&pdev->dev, "spi_register_controller error.\n");
-		goto out_controller_put;
-	}
-
-	if (!fsl_lpspi->is_slave) {
-		for (i = 0; i < controller->num_chipselect; i++) {
-			int cs_gpio = of_get_named_gpio(np, "cs-gpios", i);
-
-			if (!gpio_is_valid(cs_gpio) && lpspi_platform_info)
-				cs_gpio = lpspi_platform_info->chipselect[i];
-
-			fsl_lpspi->chipselect[i] = cs_gpio;
-			if (!gpio_is_valid(cs_gpio))
-				continue;
-
-			ret = devm_gpio_request(&pdev->dev,
-						fsl_lpspi->chipselect[i],
-						DRIVER_NAME);
-			if (ret) {
-				dev_err(&pdev->dev, "can't get cs gpios\n");
-				goto out_controller_put;
-			}
-		}
-		controller->cs_gpios = fsl_lpspi->chipselect;
-		controller->prepare_message = fsl_lpspi_prepare_message;
-	}
+	if (!fsl_lpspi->is_slave)
+		controller->use_gpio_descriptors = true;
 
 	init_completion(&fsl_lpspi->xfer_done);
 
@@ -954,10 +910,21 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
 	if (ret < 0)
 		dev_err(&pdev->dev, "dma setup error %d, use pio\n", ret);
 
+	ret = devm_spi_register_controller(&pdev->dev, controller);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "spi_register_controller error.\n");
+		goto out_pm_get;
+	}
+
+	pm_runtime_mark_last_busy(fsl_lpspi->dev);
+	pm_runtime_put_autosuspend(fsl_lpspi->dev);
+
 	return 0;
 
 out_pm_get:
-	pm_runtime_put_noidle(fsl_lpspi->dev);
+	pm_runtime_dont_use_autosuspend(fsl_lpspi->dev);
+	pm_runtime_put_sync(fsl_lpspi->dev);
+	pm_runtime_disable(fsl_lpspi->dev);
 out_controller_put:
 	spi_controller_put(controller);
 
diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c
index 6766262d7e75..9851551ebbe0 100644
--- a/drivers/spi/spi-fsl-qspi.c
+++ b/drivers/spi/spi-fsl-qspi.c
@@ -15,7 +15,7 @@
  *     Yogesh Gaur <yogeshnarayan.gaur@nxp.com>
  *     Suresh Gupta <suresh.gupta@nxp.com>
  *
- * Based on the original fsl-quadspi.c spi-nor driver:
+ * Based on the original fsl-quadspi.c SPI NOR driver:
  * Author: Freescale Semiconductor, Inc.
  *
  */
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 67f022b8c81d..299e9870cf58 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -90,7 +90,7 @@ static void fsl_spi_change_mode(struct spi_device *spi)
 {
 	struct mpc8xxx_spi *mspi = spi_master_get_devdata(spi->master);
 	struct spi_mpc8xxx_cs *cs = spi->controller_state;
-	struct fsl_spi_reg *reg_base = mspi->reg_base;
+	struct fsl_spi_reg __iomem *reg_base = mspi->reg_base;
 	__be32 __iomem *mode = &reg_base->mode;
 	unsigned long flags;
 
@@ -291,7 +291,7 @@ static int fsl_spi_cpu_bufs(struct mpc8xxx_spi *mspi,
 				struct spi_transfer *t, unsigned int len)
 {
 	u32 word;
-	struct fsl_spi_reg *reg_base = mspi->reg_base;
+	struct fsl_spi_reg __iomem *reg_base = mspi->reg_base;
 
 	mspi->count = len;
 
@@ -309,7 +309,7 @@ static int fsl_spi_bufs(struct spi_device *spi, struct spi_transfer *t,
 			    bool is_dma_mapped)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
-	struct fsl_spi_reg *reg_base;
+	struct fsl_spi_reg __iomem *reg_base;
 	unsigned int len = t->len;
 	u8 bits_per_word;
 	int ret;
@@ -440,7 +440,7 @@ static int fsl_spi_do_one_msg(struct spi_master *master,
 static int fsl_spi_setup(struct spi_device *spi)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi;
-	struct fsl_spi_reg *reg_base;
+	struct fsl_spi_reg __iomem *reg_base;
 	int retval;
 	u32 hw_mode;
 	struct spi_mpc8xxx_cs *cs = spi_get_ctldata(spi);
@@ -495,7 +495,7 @@ static void fsl_spi_cleanup(struct spi_device *spi)
 
 static void fsl_spi_cpu_irq(struct mpc8xxx_spi *mspi, u32 events)
 {
-	struct fsl_spi_reg *reg_base = mspi->reg_base;
+	struct fsl_spi_reg __iomem *reg_base = mspi->reg_base;
 
 	/* We need handle RX first */
 	if (events & SPIE_NE) {
@@ -530,7 +530,7 @@ static irqreturn_t fsl_spi_irq(s32 irq, void *context_data)
 	struct mpc8xxx_spi *mspi = context_data;
 	irqreturn_t ret = IRQ_NONE;
 	u32 events;
-	struct fsl_spi_reg *reg_base = mspi->reg_base;
+	struct fsl_spi_reg __iomem *reg_base = mspi->reg_base;
 
 	/* Get interrupt events(tx/rx) */
 	events = mpc8xxx_spi_read_reg(&reg_base->event);
@@ -550,7 +550,7 @@ static irqreturn_t fsl_spi_irq(s32 irq, void *context_data)
 static void fsl_spi_grlib_cs_control(struct spi_device *spi, bool on)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
-	struct fsl_spi_reg *reg_base = mpc8xxx_spi->reg_base;
+	struct fsl_spi_reg __iomem *reg_base = mpc8xxx_spi->reg_base;
 	u32 slvsel;
 	u16 cs = spi->chip_select;
 
@@ -568,7 +568,7 @@ static void fsl_spi_grlib_probe(struct device *dev)
 	struct fsl_spi_platform_data *pdata = dev_get_platdata(dev);
 	struct spi_master *master = dev_get_drvdata(dev);
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
-	struct fsl_spi_reg *reg_base = mpc8xxx_spi->reg_base;
+	struct fsl_spi_reg __iomem *reg_base = mpc8xxx_spi->reg_base;
 	int mbits;
 	u32 capabilities;
 
@@ -594,7 +594,7 @@ static struct spi_master *fsl_spi_probe(struct device *dev,
 	struct fsl_spi_platform_data *pdata = dev_get_platdata(dev);
 	struct spi_master *master;
 	struct mpc8xxx_spi *mpc8xxx_spi;
-	struct fsl_spi_reg *reg_base;
+	struct fsl_spi_reg __iomem *reg_base;
 	u32 regval;
 	int ret = 0;
 
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index c3972424af71..1d96a7f32fda 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -51,7 +51,6 @@
 /* M_CMD OP codes for SPI */
 #define SPI_TX_ONLY		1
 #define SPI_RX_ONLY		2
-#define SPI_FULL_DUPLEX		3
 #define SPI_TX_RX		7
 #define SPI_CS_ASSERT		8
 #define SPI_CS_DEASSERT		9
@@ -63,13 +62,6 @@
 #define TIMESTAMP_AFTER		BIT(3)
 #define POST_CMD_DELAY		BIT(4)
 
-enum spi_m_cmd_opcode {
-	CMD_NONE,
-	CMD_XFER,
-	CMD_CS,
-	CMD_CANCEL,
-};
-
 struct spi_geni_master {
 	struct geni_se se;
 	struct device *dev;
@@ -81,11 +73,13 @@ struct spi_geni_master {
 	unsigned int tx_rem_bytes;
 	unsigned int rx_rem_bytes;
 	const struct spi_transfer *cur_xfer;
-	struct completion xfer_done;
+	struct completion cs_done;
+	struct completion cancel_done;
+	struct completion abort_done;
 	unsigned int oversampling;
 	spinlock_t lock;
-	enum spi_m_cmd_opcode cur_mcmd;
 	int irq;
+	bool cs_flag;
 };
 
 static int get_spi_clk_cfg(unsigned int speed_hz,
@@ -122,24 +116,26 @@ static void handle_fifo_timeout(struct spi_master *spi,
 				struct spi_message *msg)
 {
 	struct spi_geni_master *mas = spi_master_get_devdata(spi);
-	unsigned long time_left, flags;
+	unsigned long time_left;
 	struct geni_se *se = &mas->se;
 
-	spin_lock_irqsave(&mas->lock, flags);
-	reinit_completion(&mas->xfer_done);
-	mas->cur_mcmd = CMD_CANCEL;
-	geni_se_cancel_m_cmd(se);
+	spin_lock_irq(&mas->lock);
+	reinit_completion(&mas->cancel_done);
 	writel(0, se->base + SE_GENI_TX_WATERMARK_REG);
-	spin_unlock_irqrestore(&mas->lock, flags);
-	time_left = wait_for_completion_timeout(&mas->xfer_done, HZ);
+	mas->cur_xfer = NULL;
+	geni_se_cancel_m_cmd(se);
+	spin_unlock_irq(&mas->lock);
+
+	time_left = wait_for_completion_timeout(&mas->cancel_done, HZ);
 	if (time_left)
 		return;
 
-	spin_lock_irqsave(&mas->lock, flags);
-	reinit_completion(&mas->xfer_done);
+	spin_lock_irq(&mas->lock);
+	reinit_completion(&mas->abort_done);
 	geni_se_abort_m_cmd(se);
-	spin_unlock_irqrestore(&mas->lock, flags);
-	time_left = wait_for_completion_timeout(&mas->xfer_done, HZ);
+	spin_unlock_irq(&mas->lock);
+
+	time_left = wait_for_completion_timeout(&mas->abort_done, HZ);
 	if (!time_left)
 		dev_err(mas->dev, "Failed to cancel/abort m_cmd\n");
 }
@@ -151,18 +147,24 @@ static void spi_geni_set_cs(struct spi_device *slv, bool set_flag)
 	struct geni_se *se = &mas->se;
 	unsigned long time_left;
 
-	reinit_completion(&mas->xfer_done);
-	pm_runtime_get_sync(mas->dev);
 	if (!(slv->mode & SPI_CS_HIGH))
 		set_flag = !set_flag;
 
-	mas->cur_mcmd = CMD_CS;
+	if (set_flag == mas->cs_flag)
+		return;
+
+	mas->cs_flag = set_flag;
+
+	pm_runtime_get_sync(mas->dev);
+	spin_lock_irq(&mas->lock);
+	reinit_completion(&mas->cs_done);
 	if (set_flag)
 		geni_se_setup_m_cmd(se, SPI_CS_ASSERT, 0);
 	else
 		geni_se_setup_m_cmd(se, SPI_CS_DEASSERT, 0);
+	spin_unlock_irq(&mas->lock);
 
-	time_left = wait_for_completion_timeout(&mas->xfer_done, HZ);
+	time_left = wait_for_completion_timeout(&mas->cs_done, HZ);
 	if (!time_left)
 		handle_fifo_timeout(spi, NULL);
 
@@ -283,7 +285,7 @@ static int spi_geni_init(struct spi_geni_master *mas)
 	 * Hardware programming guide suggests to configure
 	 * RX FIFO RFR level to fifo_depth-2.
 	 */
-	geni_se_init(se, 0x0, mas->tx_fifo_depth - 2);
+	geni_se_init(se, mas->tx_fifo_depth / 2, mas->tx_fifo_depth - 2);
 	/* Transmit an entire FIFO worth of data per IRQ */
 	mas->tx_wm = 1;
 	ver = geni_se_get_qup_hw_version(se);
@@ -307,6 +309,21 @@ static void setup_fifo_xfer(struct spi_transfer *xfer,
 	u32 spi_tx_cfg, len;
 	struct geni_se *se = &mas->se;
 
+	/*
+	 * Ensure that our interrupt handler isn't still running from some
+	 * prior command before we start messing with the hardware behind
+	 * its back.  We don't need to _keep_ the lock here since we're only
+	 * worried about racing with out interrupt handler.  The SPI core
+	 * already handles making sure that we're not trying to do two
+	 * transfers at once or setting a chip select and doing a transfer
+	 * concurrently.
+	 *
+	 * NOTE: we actually _can't_ hold the lock here because possibly we
+	 * might call clk_set_rate() which needs to be able to sleep.
+	 */
+	spin_lock_irq(&mas->lock);
+	spin_unlock_irq(&mas->lock);
+
 	spi_tx_cfg = readl(se->base + SE_SPI_TRANS_CFG);
 	if (xfer->bits_per_word != mas->cur_bits_per_word) {
 		spi_setup_word_len(mas, mode, xfer->bits_per_word);
@@ -340,12 +357,6 @@ static void setup_fifo_xfer(struct spi_transfer *xfer,
 
 	mas->tx_rem_bytes = 0;
 	mas->rx_rem_bytes = 0;
-	if (xfer->tx_buf && xfer->rx_buf)
-		m_cmd = SPI_FULL_DUPLEX;
-	else if (xfer->tx_buf)
-		m_cmd = SPI_TX_ONLY;
-	else if (xfer->rx_buf)
-		m_cmd = SPI_RX_ONLY;
 
 	spi_tx_cfg &= ~CS_TOGGLE;
 
@@ -356,17 +367,24 @@ static void setup_fifo_xfer(struct spi_transfer *xfer,
 	len &= TRANS_LEN_MSK;
 
 	mas->cur_xfer = xfer;
-	if (m_cmd & SPI_TX_ONLY) {
+	if (xfer->tx_buf) {
+		m_cmd |= SPI_TX_ONLY;
 		mas->tx_rem_bytes = xfer->len;
 		writel(len, se->base + SE_SPI_TX_TRANS_LEN);
 	}
 
-	if (m_cmd & SPI_RX_ONLY) {
+	if (xfer->rx_buf) {
+		m_cmd |= SPI_RX_ONLY;
 		writel(len, se->base + SE_SPI_RX_TRANS_LEN);
 		mas->rx_rem_bytes = xfer->len;
 	}
 	writel(spi_tx_cfg, se->base + SE_SPI_TRANS_CFG);
-	mas->cur_mcmd = CMD_XFER;
+
+	/*
+	 * Lock around right before we start the transfer since our
+	 * interrupt could come in at any time now.
+	 */
+	spin_lock_irq(&mas->lock);
 	geni_se_setup_m_cmd(se, m_cmd, FRAGMENTATION);
 
 	/*
@@ -376,6 +394,7 @@ static void setup_fifo_xfer(struct spi_transfer *xfer,
 	 */
 	if (m_cmd & SPI_TX_ONLY)
 		writel(mas->tx_wm, se->base + SE_GENI_TX_WATERMARK_REG);
+	spin_unlock_irq(&mas->lock);
 }
 
 static int spi_geni_transfer_one(struct spi_master *spi,
@@ -477,13 +496,17 @@ static irqreturn_t geni_spi_isr(int irq, void *data)
 	struct spi_geni_master *mas = spi_master_get_devdata(spi);
 	struct geni_se *se = &mas->se;
 	u32 m_irq;
-	unsigned long flags;
 
-	if (mas->cur_mcmd == CMD_NONE)
+	m_irq = readl(se->base + SE_GENI_M_IRQ_STATUS);
+	if (!m_irq)
 		return IRQ_NONE;
 
-	spin_lock_irqsave(&mas->lock, flags);
-	m_irq = readl(se->base + SE_GENI_M_IRQ_STATUS);
+	if (m_irq & (M_CMD_OVERRUN_EN | M_ILLEGAL_CMD_EN | M_CMD_FAILURE_EN |
+		     M_RX_FIFO_RD_ERR_EN | M_RX_FIFO_WR_ERR_EN |
+		     M_TX_FIFO_RD_ERR_EN | M_TX_FIFO_WR_ERR_EN))
+		dev_warn(mas->dev, "Unexpected IRQ err status %#010x\n", m_irq);
+
+	spin_lock(&mas->lock);
 
 	if ((m_irq & M_RX_FIFO_WATERMARK_EN) || (m_irq & M_RX_FIFO_LAST_EN))
 		geni_spi_handle_rx(mas);
@@ -492,39 +515,57 @@ static irqreturn_t geni_spi_isr(int irq, void *data)
 		geni_spi_handle_tx(mas);
 
 	if (m_irq & M_CMD_DONE_EN) {
-		if (mas->cur_mcmd == CMD_XFER)
+		if (mas->cur_xfer) {
 			spi_finalize_current_transfer(spi);
-		else if (mas->cur_mcmd == CMD_CS)
-			complete(&mas->xfer_done);
-		mas->cur_mcmd = CMD_NONE;
-		/*
-		 * If this happens, then a CMD_DONE came before all the Tx
-		 * buffer bytes were sent out. This is unusual, log this
-		 * condition and disable the WM interrupt to prevent the
-		 * system from stalling due an interrupt storm.
-		 * If this happens when all Rx bytes haven't been received, log
-		 * the condition.
-		 * The only known time this can happen is if bits_per_word != 8
-		 * and some registers that expect xfer lengths in num spi_words
-		 * weren't written correctly.
-		 */
-		if (mas->tx_rem_bytes) {
-			writel(0, se->base + SE_GENI_TX_WATERMARK_REG);
-			dev_err(mas->dev, "Premature done. tx_rem = %d bpw%d\n",
-				mas->tx_rem_bytes, mas->cur_bits_per_word);
+			mas->cur_xfer = NULL;
+			/*
+			 * If this happens, then a CMD_DONE came before all the
+			 * Tx buffer bytes were sent out. This is unusual, log
+			 * this condition and disable the WM interrupt to
+			 * prevent the system from stalling due an interrupt
+			 * storm.
+			 *
+			 * If this happens when all Rx bytes haven't been
+			 * received, log the condition. The only known time
+			 * this can happen is if bits_per_word != 8 and some
+			 * registers that expect xfer lengths in num spi_words
+			 * weren't written correctly.
+			 */
+			if (mas->tx_rem_bytes) {
+				writel(0, se->base + SE_GENI_TX_WATERMARK_REG);
+				dev_err(mas->dev, "Premature done. tx_rem = %d bpw%d\n",
+					mas->tx_rem_bytes, mas->cur_bits_per_word);
+			}
+			if (mas->rx_rem_bytes)
+				dev_err(mas->dev, "Premature done. rx_rem = %d bpw%d\n",
+					mas->rx_rem_bytes, mas->cur_bits_per_word);
+		} else {
+			complete(&mas->cs_done);
 		}
-		if (mas->rx_rem_bytes)
-			dev_err(mas->dev, "Premature done. rx_rem = %d bpw%d\n",
-				mas->rx_rem_bytes, mas->cur_bits_per_word);
 	}
 
-	if ((m_irq & M_CMD_CANCEL_EN) || (m_irq & M_CMD_ABORT_EN)) {
-		mas->cur_mcmd = CMD_NONE;
-		complete(&mas->xfer_done);
-	}
+	if (m_irq & M_CMD_CANCEL_EN)
+		complete(&mas->cancel_done);
+	if (m_irq & M_CMD_ABORT_EN)
+		complete(&mas->abort_done);
 
+	/*
+	 * It's safe or a good idea to Ack all of our our interrupts at the
+	 * end of the function. Specifically:
+	 * - M_CMD_DONE_EN / M_RX_FIFO_LAST_EN: Edge triggered interrupts and
+	 *   clearing Acks. Clearing at the end relies on nobody else having
+	 *   started a new transfer yet or else we could be clearing _their_
+	 *   done bit, but everyone grabs the spinlock before starting a new
+	 *   transfer.
+	 * - M_RX_FIFO_WATERMARK_EN / M_TX_FIFO_WATERMARK_EN: These appear
+	 *   to be "latched level" interrupts so it's important to clear them
+	 *   _after_ you've handled the condition and always safe to do so
+	 *   since they'll re-assert if they're still happening.
+	 */
 	writel(m_irq, se->base + SE_GENI_M_IRQ_CLEAR);
-	spin_unlock_irqrestore(&mas->lock, flags);
+
+	spin_unlock(&mas->lock);
+
 	return IRQ_HANDLED;
 }
 
@@ -574,8 +615,12 @@ static int spi_geni_probe(struct platform_device *pdev)
 	spi->handle_err = handle_fifo_timeout;
 	spi->set_cs = spi_geni_set_cs;
 
-	init_completion(&mas->xfer_done);
+	init_completion(&mas->cs_done);
+	init_completion(&mas->cancel_done);
+	init_completion(&mas->abort_done);
 	spin_lock_init(&mas->lock);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_autosuspend_delay(&pdev->dev, 250);
 	pm_runtime_enable(dev);
 
 	ret = spi_geni_init(mas);
diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c
index 8543f5ed1099..b068537375d6 100644
--- a/drivers/spi/spi-img-spfi.c
+++ b/drivers/spi/spi-img-spfi.c
@@ -9,7 +9,6 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
@@ -102,10 +101,6 @@ struct img_spfi {
 	bool rx_dma_busy;
 };
 
-struct img_spfi_device_data {
-	bool gpio_requested;
-};
-
 static inline u32 spfi_readl(struct img_spfi *spfi, u32 reg)
 {
 	return readl(spfi->regs + reg);
@@ -442,54 +437,6 @@ static int img_spfi_unprepare(struct spi_master *master,
 	return 0;
 }
 
-static int img_spfi_setup(struct spi_device *spi)
-{
-	int ret = -EINVAL;
-	struct img_spfi_device_data *spfi_data = spi_get_ctldata(spi);
-
-	if (!spfi_data) {
-		spfi_data = kzalloc(sizeof(*spfi_data), GFP_KERNEL);
-		if (!spfi_data)
-			return -ENOMEM;
-		spfi_data->gpio_requested = false;
-		spi_set_ctldata(spi, spfi_data);
-	}
-	if (!spfi_data->gpio_requested) {
-		ret = gpio_request_one(spi->cs_gpio,
-				       (spi->mode & SPI_CS_HIGH) ?
-				       GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH,
-				       dev_name(&spi->dev));
-		if (ret)
-			dev_err(&spi->dev, "can't request chipselect gpio %d\n",
-				spi->cs_gpio);
-		else
-			spfi_data->gpio_requested = true;
-	} else {
-		if (gpio_is_valid(spi->cs_gpio)) {
-			int mode = ((spi->mode & SPI_CS_HIGH) ?
-				    GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH);
-
-			ret = gpio_direction_output(spi->cs_gpio, mode);
-			if (ret)
-				dev_err(&spi->dev, "chipselect gpio %d setup failed (%d)\n",
-					spi->cs_gpio, ret);
-		}
-	}
-	return ret;
-}
-
-static void img_spfi_cleanup(struct spi_device *spi)
-{
-	struct img_spfi_device_data *spfi_data = spi_get_ctldata(spi);
-
-	if (spfi_data) {
-		if (spfi_data->gpio_requested)
-			gpio_free(spi->cs_gpio);
-		kfree(spfi_data);
-		spi_set_ctldata(spi, NULL);
-	}
-}
-
 static void img_spfi_config(struct spi_master *master, struct spi_device *spi,
 			    struct spi_transfer *xfer)
 {
@@ -659,12 +606,11 @@ static int img_spfi_probe(struct platform_device *pdev)
 			master->max_speed_hz = max_speed_hz;
 	}
 
-	master->setup = img_spfi_setup;
-	master->cleanup = img_spfi_cleanup;
 	master->transfer_one = img_spfi_transfer_one;
 	master->prepare_message = img_spfi_prepare;
 	master->unprepare_message = img_spfi_unprepare;
 	master->handle_err = img_spfi_handle_err;
+	master->use_gpio_descriptors = true;
 
 	spfi->tx_ch = dma_request_chan(spfi->dev, "tx");
 	if (IS_ERR(spfi->tx_ch)) {
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index b7a85e3fe1c1..38a5f1304cec 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -8,23 +8,23 @@
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 #include <linux/types.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
+#include <linux/property.h>
 
 #include <linux/platform_data/dma-imx.h>
-#include <linux/platform_data/spi-imx.h>
 
 #define DRIVER_NAME "spi_imx"
 
@@ -32,6 +32,8 @@ static bool use_dma = true;
 module_param(use_dma, bool, 0644);
 MODULE_PARM_DESC(use_dma, "Enable usage of DMA when available (default)");
 
+#define MXC_RPM_TIMEOUT		2000 /* 2000ms */
+
 #define MXC_CSPIRXDATA		0x00
 #define MXC_CSPITXDATA		0x04
 #define MXC_CSPICTRL		0x08
@@ -224,7 +226,7 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 
-	if (!use_dma)
+	if (!use_dma || master->fallback)
 		return false;
 
 	if (!master->dma_rx)
@@ -723,7 +725,7 @@ static int mx31_prepare_transfer(struct spi_imx_data *spi_imx,
 		reg |= MX31_CSPICTRL_POL;
 	if (spi->mode & SPI_CS_HIGH)
 		reg |= MX31_CSPICTRL_SSPOL;
-	if (!gpio_is_valid(spi->cs_gpio))
+	if (!spi->cs_gpiod)
 		reg |= (spi->chip_select) <<
 			(is_imx35_cspi(spi_imx) ? MX35_CSPICTRL_CS_SHIFT :
 						  MX31_CSPICTRL_CS_SHIFT);
@@ -824,7 +826,7 @@ static int mx21_prepare_transfer(struct spi_imx_data *spi_imx,
 		reg |= MX21_CSPICTRL_POL;
 	if (spi->mode & SPI_CS_HIGH)
 		reg |= MX21_CSPICTRL_SSPOL;
-	if (!gpio_is_valid(spi->cs_gpio))
+	if (!spi->cs_gpiod)
 		reg |= spi->chip_select << MX21_CSPICTRL_CS_SHIFT;
 
 	writel(reg, spi_imx->base + MXC_CSPICTRL);
@@ -1056,20 +1058,6 @@ static const struct of_device_id spi_imx_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, spi_imx_dt_ids);
 
-static void spi_imx_chipselect(struct spi_device *spi, int is_active)
-{
-	int active = is_active != BITBANG_CS_INACTIVE;
-	int dev_is_lowactive = !(spi->mode & SPI_CS_HIGH);
-
-	if (spi->mode & SPI_NO_CS)
-		return;
-
-	if (!gpio_is_valid(spi->cs_gpio))
-		return;
-
-	gpio_set_value(spi->cs_gpio, dev_is_lowactive ^ active);
-}
-
 static void spi_imx_set_burst_len(struct spi_imx_data *spi_imx, int n_bits)
 {
 	u32 ctrl;
@@ -1364,11 +1352,12 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 
 	ret = spi_imx_dma_configure(master);
 	if (ret)
-		return ret;
+		goto dma_failure_no_start;
 
 	if (!spi_imx->devtype_data->setup_wml) {
 		dev_err(spi_imx->dev, "No setup_wml()?\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto dma_failure_no_start;
 	}
 	spi_imx->devtype_data->setup_wml(spi_imx);
 
@@ -1379,8 +1368,10 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 	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 (!desc_rx) {
+		ret = -EINVAL;
+		goto dma_failure_no_start;
+	}
 
 	desc_rx->callback = spi_imx_dma_rx_callback;
 	desc_rx->callback_param = (void *)spi_imx;
@@ -1425,6 +1416,10 @@ static int spi_imx_dma_transfer(struct spi_imx_data *spi_imx,
 	}
 
 	return transfer->len;
+/* fallback to pio */
+dma_failure_no_start:
+	transfer->error |= SPI_TRANS_FAIL_NO_START;
+	return ret;
 }
 
 static int spi_imx_pio_transfer(struct spi_device *spi,
@@ -1507,7 +1502,6 @@ static int spi_imx_transfer(struct spi_device *spi,
 				struct spi_transfer *transfer)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(spi->master);
-	int ret;
 
 	/* flush rxfifo before transfer */
 	while (spi_imx->devtype_data->rx_available(spi_imx))
@@ -1516,21 +1510,8 @@ static int spi_imx_transfer(struct spi_device *spi,
 	if (spi_imx->slave_mode)
 		return spi_imx_pio_transfer_slave(spi, transfer);
 
-	/*
-	 * fallback PIO mode if dma setup error happen, for example sdma
-	 * firmware may not be updated as ERR009165 required.
-	 */
-	if (spi_imx->usedma) {
-		ret = spi_imx_dma_transfer(spi_imx, transfer);
-		if (ret != -EINVAL)
-			return ret;
-
-		spi_imx->devtype_data->disable_dma(spi_imx);
-
-		spi_imx->usedma = false;
-		spi_imx->dynamic_burst = spi_imx->devtype_data->dynamic_burst;
-		dev_dbg(&spi->dev, "Fallback to PIO mode\n");
-	}
+	if (spi_imx->usedma)
+		return spi_imx_dma_transfer(spi_imx, transfer);
 
 	return spi_imx_pio_transfer(spi, transfer);
 }
@@ -1540,15 +1521,6 @@ static int spi_imx_setup(struct spi_device *spi)
 	dev_dbg(&spi->dev, "%s: mode %d, %u bpw, %d hz\n", __func__,
 		 spi->mode, spi->bits_per_word, spi->max_speed_hz);
 
-	if (spi->mode & SPI_NO_CS)
-		return 0;
-
-	if (gpio_is_valid(spi->cs_gpio))
-		gpio_direction_output(spi->cs_gpio,
-				      spi->mode & SPI_CS_HIGH ? 0 : 1);
-
-	spi_imx_chipselect(spi, BITBANG_CS_INACTIVE);
-
 	return 0;
 }
 
@@ -1562,20 +1534,16 @@ spi_imx_prepare_message(struct spi_master *master, struct spi_message *msg)
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 	int ret;
 
-	ret = clk_enable(spi_imx->clk_per);
-	if (ret)
-		return ret;
-
-	ret = clk_enable(spi_imx->clk_ipg);
-	if (ret) {
-		clk_disable(spi_imx->clk_per);
+	ret = pm_runtime_get_sync(spi_imx->dev);
+	if (ret < 0) {
+		dev_err(spi_imx->dev, "failed to enable clock\n");
 		return ret;
 	}
 
 	ret = spi_imx->devtype_data->prepare_message(spi_imx, msg);
 	if (ret) {
-		clk_disable(spi_imx->clk_ipg);
-		clk_disable(spi_imx->clk_per);
+		pm_runtime_mark_last_busy(spi_imx->dev);
+		pm_runtime_put_autosuspend(spi_imx->dev);
 	}
 
 	return ret;
@@ -1586,8 +1554,8 @@ spi_imx_unprepare_message(struct spi_master *master, struct spi_message *msg)
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 
-	clk_disable(spi_imx->clk_ipg);
-	clk_disable(spi_imx->clk_per);
+	pm_runtime_mark_last_busy(spi_imx->dev);
+	pm_runtime_put_autosuspend(spi_imx->dev);
 	return 0;
 }
 
@@ -1606,20 +1574,14 @@ static int spi_imx_probe(struct platform_device *pdev)
 	struct device_node *np = pdev->dev.of_node;
 	const struct of_device_id *of_id =
 			of_match_device(spi_imx_dt_ids, &pdev->dev);
-	struct spi_imx_master *mxc_platform_info =
-			dev_get_platdata(&pdev->dev);
 	struct spi_master *master;
 	struct spi_imx_data *spi_imx;
 	struct resource *res;
-	int i, ret, irq, spi_drctl;
+	int ret, irq, spi_drctl;
 	const struct spi_imx_devtype_data *devtype_data = of_id ? of_id->data :
 		(struct spi_imx_devtype_data *)pdev->id_entry->driver_data;
 	bool slave_mode;
-
-	if (!np && !mxc_platform_info) {
-		dev_err(&pdev->dev, "can't get the platform data\n");
-		return -EINVAL;
-	}
+	u32 val;
 
 	slave_mode = devtype_data->has_slavemode &&
 			of_property_read_bool(np, "spi-slave");
@@ -1642,6 +1604,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
 	master->bus_num = np ? -1 : pdev->id;
+	master->use_gpio_descriptors = true;
 
 	spi_imx = spi_master_get_devdata(master);
 	spi_imx->bitbang.master = master;
@@ -1650,28 +1613,17 @@ static int spi_imx_probe(struct platform_device *pdev)
 
 	spi_imx->devtype_data = devtype_data;
 
-	/* Get number of chip selects, either platform data or OF */
-	if (mxc_platform_info) {
-		master->num_chipselect = mxc_platform_info->num_chipselect;
-		if (mxc_platform_info->chipselect) {
-			master->cs_gpios = devm_kcalloc(&master->dev,
-				master->num_chipselect, sizeof(int),
-				GFP_KERNEL);
-			if (!master->cs_gpios)
-				return -ENOMEM;
-
-			for (i = 0; i < master->num_chipselect; i++)
-				master->cs_gpios[i] = mxc_platform_info->chipselect[i];
-		}
-	} else {
-		u32 num_cs;
-
-		if (!of_property_read_u32(np, "num-cs", &num_cs))
-			master->num_chipselect = num_cs;
-		/* If not preset, default value of 1 is used */
-	}
+	/*
+	 * Get number of chip selects from device properties. This can be
+	 * coming from device tree or boardfiles, if it is not defined,
+	 * a default value of 3 chip selects will be used, as all the legacy
+	 * board files have <= 3 chip selects.
+	 */
+	if (!device_property_read_u32(&pdev->dev, "num-cs", &val))
+		master->num_chipselect = val;
+	else
+		master->num_chipselect = 3;
 
-	spi_imx->bitbang.chipselect = spi_imx_chipselect;
 	spi_imx->bitbang.setup_transfer = spi_imx_setupxfer;
 	spi_imx->bitbang.txrx_bufs = spi_imx_transfer;
 	spi_imx->bitbang.master->setup = spi_imx_setup;
@@ -1722,13 +1674,15 @@ static int spi_imx_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
-	ret = clk_prepare_enable(spi_imx->clk_per);
-	if (ret)
-		goto out_master_put;
+	pm_runtime_enable(spi_imx->dev);
+	pm_runtime_set_autosuspend_delay(spi_imx->dev, MXC_RPM_TIMEOUT);
+	pm_runtime_use_autosuspend(spi_imx->dev);
 
-	ret = clk_prepare_enable(spi_imx->clk_ipg);
-	if (ret)
-		goto out_put_per;
+	ret = pm_runtime_get_sync(spi_imx->dev);
+	if (ret < 0) {
+		dev_err(spi_imx->dev, "failed to enable clock\n");
+		goto out_runtime_pm_put;
+	}
 
 	spi_imx->spi_clk = clk_get_rate(spi_imx->clk_per);
 	/*
@@ -1738,7 +1692,7 @@ static int spi_imx_probe(struct platform_device *pdev)
 	if (spi_imx->devtype_data->has_dmamode) {
 		ret = spi_imx_sdma_init(&pdev->dev, spi_imx, master);
 		if (ret == -EPROBE_DEFER)
-			goto out_clk_put;
+			goto out_runtime_pm_put;
 
 		if (ret < 0)
 			dev_err(&pdev->dev, "dma setup error %d, use pio\n",
@@ -1753,38 +1707,20 @@ static int spi_imx_probe(struct platform_device *pdev)
 	ret = spi_bitbang_start(&spi_imx->bitbang);
 	if (ret) {
 		dev_err(&pdev->dev, "bitbang start failed with %d\n", ret);
-		goto out_clk_put;
-	}
-
-	/* Request GPIO CS lines, if any */
-	if (!spi_imx->slave_mode && master->cs_gpios) {
-		for (i = 0; i < master->num_chipselect; i++) {
-			if (!gpio_is_valid(master->cs_gpios[i]))
-				continue;
-
-			ret = devm_gpio_request(&pdev->dev,
-						master->cs_gpios[i],
-						DRIVER_NAME);
-			if (ret) {
-				dev_err(&pdev->dev, "Can't get CS GPIO %i\n",
-					master->cs_gpios[i]);
-				goto out_spi_bitbang;
-			}
-		}
+		goto out_runtime_pm_put;
 	}
 
 	dev_info(&pdev->dev, "probed\n");
 
-	clk_disable(spi_imx->clk_ipg);
-	clk_disable(spi_imx->clk_per);
+	pm_runtime_mark_last_busy(spi_imx->dev);
+	pm_runtime_put_autosuspend(spi_imx->dev);
+
 	return ret;
 
-out_spi_bitbang:
-	spi_bitbang_stop(&spi_imx->bitbang);
-out_clk_put:
-	clk_disable_unprepare(spi_imx->clk_ipg);
-out_put_per:
-	clk_disable_unprepare(spi_imx->clk_per);
+out_runtime_pm_put:
+	pm_runtime_dont_use_autosuspend(spi_imx->dev);
+	pm_runtime_put_sync(spi_imx->dev);
+	pm_runtime_disable(spi_imx->dev);
 out_master_put:
 	spi_master_put(master);
 
@@ -1799,30 +1735,82 @@ static int spi_imx_remove(struct platform_device *pdev)
 
 	spi_bitbang_stop(&spi_imx->bitbang);
 
-	ret = clk_enable(spi_imx->clk_per);
+	ret = pm_runtime_get_sync(spi_imx->dev);
+	if (ret < 0) {
+		dev_err(spi_imx->dev, "failed to enable clock\n");
+		return ret;
+	}
+
+	writel(0, spi_imx->base + MXC_CSPICTRL);
+
+	pm_runtime_dont_use_autosuspend(spi_imx->dev);
+	pm_runtime_put_sync(spi_imx->dev);
+	pm_runtime_disable(spi_imx->dev);
+
+	spi_imx_sdma_exit(spi_imx);
+	spi_master_put(master);
+
+	return 0;
+}
+
+static int __maybe_unused spi_imx_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_imx_data *spi_imx;
+	int ret;
+
+	spi_imx = spi_master_get_devdata(master);
+
+	ret = clk_prepare_enable(spi_imx->clk_per);
 	if (ret)
 		return ret;
 
-	ret = clk_enable(spi_imx->clk_ipg);
+	ret = clk_prepare_enable(spi_imx->clk_ipg);
 	if (ret) {
-		clk_disable(spi_imx->clk_per);
+		clk_disable_unprepare(spi_imx->clk_per);
 		return ret;
 	}
 
-	writel(0, spi_imx->base + MXC_CSPICTRL);
-	clk_disable_unprepare(spi_imx->clk_ipg);
+	return 0;
+}
+
+static int __maybe_unused spi_imx_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct spi_imx_data *spi_imx;
+
+	spi_imx = spi_master_get_devdata(master);
+
 	clk_disable_unprepare(spi_imx->clk_per);
-	spi_imx_sdma_exit(spi_imx);
-	spi_master_put(master);
+	clk_disable_unprepare(spi_imx->clk_ipg);
+
+	return 0;
+}
+
+static int __maybe_unused spi_imx_suspend(struct device *dev)
+{
+	pinctrl_pm_select_sleep_state(dev);
+	return 0;
+}
 
+static int __maybe_unused spi_imx_resume(struct device *dev)
+{
+	pinctrl_pm_select_default_state(dev);
 	return 0;
 }
 
+static const struct dev_pm_ops imx_spi_pm = {
+	SET_RUNTIME_PM_OPS(spi_imx_runtime_suspend,
+				spi_imx_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(spi_imx_suspend, spi_imx_resume)
+};
+
 static struct platform_driver spi_imx_driver = {
 	.driver = {
 		   .name = DRIVER_NAME,
 		   .of_match_table = spi_imx_dt_ids,
-		   },
+		   .pm = &imx_spi_pm,
+	},
 	.id_table = spi_imx_devtype,
 	.probe = spi_imx_probe,
 	.remove = spi_imx_remove,
diff --git a/drivers/spi/spi-lantiq-ssc.c b/drivers/spi/spi-lantiq-ssc.c
index 1fd7ee53d451..dccef1dcea32 100644
--- a/drivers/spi/spi-lantiq-ssc.c
+++ b/drivers/spi/spi-lantiq-ssc.c
@@ -15,7 +15,6 @@
 #include <linux/completion.h>
 #include <linux/spinlock.h>
 #include <linux/err.h>
-#include <linux/gpio.h>
 #include <linux/pm_runtime.h>
 #include <linux/spi/spi.h>
 
@@ -50,8 +49,6 @@
 #define LTQ_SPI_RXCNT		0x84
 #define LTQ_SPI_DMACON		0xec
 #define LTQ_SPI_IRNEN		0xf4
-#define LTQ_SPI_IRNICR		0xf8
-#define LTQ_SPI_IRNCR		0xfc
 
 #define LTQ_SPI_CLC_SMC_S	16	/* Clock divider for sleep mode */
 #define LTQ_SPI_CLC_SMC_M	(0xFF << LTQ_SPI_CLC_SMC_S)
@@ -61,9 +58,7 @@
 #define LTQ_SPI_CLC_DISR	BIT(0)	/* Disable request bit */
 
 #define LTQ_SPI_ID_TXFS_S	24	/* Implemented TX FIFO size */
-#define LTQ_SPI_ID_TXFS_M	(0x3F << LTQ_SPI_ID_TXFS_S)
 #define LTQ_SPI_ID_RXFS_S	16	/* Implemented RX FIFO size */
-#define LTQ_SPI_ID_RXFS_M	(0x3F << LTQ_SPI_ID_RXFS_S)
 #define LTQ_SPI_ID_MOD_S	8	/* Module ID */
 #define LTQ_SPI_ID_MOD_M	(0xff << LTQ_SPI_ID_MOD_S)
 #define LTQ_SPI_ID_CFG_S	5	/* DMA interface support */
@@ -126,19 +121,15 @@
 					 LTQ_SPI_WHBSTATE_CLRTUE)
 
 #define LTQ_SPI_RXFCON_RXFITL_S	8	/* FIFO interrupt trigger level */
-#define LTQ_SPI_RXFCON_RXFITL_M	(0x3F << LTQ_SPI_RXFCON_RXFITL_S)
 #define LTQ_SPI_RXFCON_RXFLU	BIT(1)	/* FIFO flush */
 #define LTQ_SPI_RXFCON_RXFEN	BIT(0)	/* FIFO enable */
 
 #define LTQ_SPI_TXFCON_TXFITL_S	8	/* FIFO interrupt trigger level */
-#define LTQ_SPI_TXFCON_TXFITL_M	(0x3F << LTQ_SPI_TXFCON_TXFITL_S)
 #define LTQ_SPI_TXFCON_TXFLU	BIT(1)	/* FIFO flush */
 #define LTQ_SPI_TXFCON_TXFEN	BIT(0)	/* FIFO enable */
 
 #define LTQ_SPI_FSTAT_RXFFL_S	0
-#define LTQ_SPI_FSTAT_RXFFL_M	(0x3f << LTQ_SPI_FSTAT_RXFFL_S)
 #define LTQ_SPI_FSTAT_TXFFL_S	8
-#define LTQ_SPI_FSTAT_TXFFL_M	(0x3f << LTQ_SPI_FSTAT_TXFFL_S)
 
 #define LTQ_SPI_GPOCON_ISCSBN_S	8
 #define LTQ_SPI_GPOCON_INVOUTN_S	0
@@ -158,9 +149,16 @@
 #define LTQ_SPI_IRNEN_T_XRX	BIT(0)	/* Receive end interrupt request */
 #define LTQ_SPI_IRNEN_ALL	0x1F
 
+struct lantiq_ssc_spi;
+
 struct lantiq_ssc_hwcfg {
-	unsigned int irnen_r;
-	unsigned int irnen_t;
+	int (*cfg_irq)(struct platform_device *pdev, struct lantiq_ssc_spi *spi);
+	unsigned int	irnen_r;
+	unsigned int	irnen_t;
+	unsigned int	irncr;
+	unsigned int	irnicr;
+	bool		irq_ack;
+	u32		fifo_size_mask;
 };
 
 struct lantiq_ssc_spi {
@@ -184,6 +182,7 @@ struct lantiq_ssc_spi {
 	unsigned int			tx_fifo_size;
 	unsigned int			rx_fifo_size;
 	unsigned int			base_cs;
+	unsigned int			fdx_tx_level;
 };
 
 static u32 lantiq_ssc_readl(const struct lantiq_ssc_spi *spi, u32 reg)
@@ -209,16 +208,18 @@ static void lantiq_ssc_maskl(const struct lantiq_ssc_spi *spi, u32 clr,
 
 static unsigned int tx_fifo_level(const struct lantiq_ssc_spi *spi)
 {
+	const struct lantiq_ssc_hwcfg *hwcfg = spi->hwcfg;
 	u32 fstat = lantiq_ssc_readl(spi, LTQ_SPI_FSTAT);
 
-	return (fstat & LTQ_SPI_FSTAT_TXFFL_M) >> LTQ_SPI_FSTAT_TXFFL_S;
+	return (fstat >> LTQ_SPI_FSTAT_TXFFL_S) & hwcfg->fifo_size_mask;
 }
 
 static unsigned int rx_fifo_level(const struct lantiq_ssc_spi *spi)
 {
+	const struct lantiq_ssc_hwcfg *hwcfg = spi->hwcfg;
 	u32 fstat = lantiq_ssc_readl(spi, LTQ_SPI_FSTAT);
 
-	return fstat & LTQ_SPI_FSTAT_RXFFL_M;
+	return (fstat >> LTQ_SPI_FSTAT_RXFFL_S) & hwcfg->fifo_size_mask;
 }
 
 static unsigned int tx_fifo_free(const struct lantiq_ssc_spi *spi)
@@ -391,7 +392,7 @@ static int lantiq_ssc_setup(struct spi_device *spidev)
 	u32 gpocon;
 
 	/* GPIOs are used for CS */
-	if (gpio_is_valid(spidev->cs_gpio))
+	if (spidev->cs_gpiod)
 		return 0;
 
 	dev_dbg(spi->dev, "using internal chipselect %u\n", cs);
@@ -481,6 +482,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi)
 	u32 data;
 	unsigned int tx_free = tx_fifo_free(spi);
 
+	spi->fdx_tx_level = 0;
 	while (spi->tx_todo && tx_free) {
 		switch (spi->bits_per_word) {
 		case 2 ... 8:
@@ -509,6 +511,7 @@ static void tx_fifo_write(struct lantiq_ssc_spi *spi)
 
 		lantiq_ssc_writel(spi, data, LTQ_SPI_TB);
 		tx_free--;
+		spi->fdx_tx_level++;
 	}
 }
 
@@ -520,6 +523,13 @@ static void rx_fifo_read_full_duplex(struct lantiq_ssc_spi *spi)
 	u32 data;
 	unsigned int rx_fill = rx_fifo_level(spi);
 
+	/*
+	 * Wait until all expected data to be shifted in.
+	 * Otherwise, rx overrun may occur.
+	 */
+	while (rx_fill != spi->fdx_tx_level)
+		rx_fill = rx_fifo_level(spi);
+
 	while (rx_fill) {
 		data = lantiq_ssc_readl(spi, LTQ_SPI_RB);
 
@@ -613,6 +623,13 @@ static void rx_request(struct lantiq_ssc_spi *spi)
 static irqreturn_t lantiq_ssc_xmit_interrupt(int irq, void *data)
 {
 	struct lantiq_ssc_spi *spi = data;
+	const struct lantiq_ssc_hwcfg *hwcfg = spi->hwcfg;
+	u32 val = lantiq_ssc_readl(spi, hwcfg->irncr);
+	unsigned long flags;
+
+	spin_lock_irqsave(&spi->lock, flags);
+	if (hwcfg->irq_ack)
+		lantiq_ssc_writel(spi, val, hwcfg->irncr);
 
 	if (spi->tx) {
 		if (spi->rx && spi->rx_todo)
@@ -635,10 +652,12 @@ static irqreturn_t lantiq_ssc_xmit_interrupt(int irq, void *data)
 		}
 	}
 
+	spin_unlock_irqrestore(&spi->lock, flags);
 	return IRQ_HANDLED;
 
 completed:
 	queue_work(spi->wq, &spi->work);
+	spin_unlock_irqrestore(&spi->lock, flags);
 
 	return IRQ_HANDLED;
 }
@@ -646,11 +665,18 @@ completed:
 static irqreturn_t lantiq_ssc_err_interrupt(int irq, void *data)
 {
 	struct lantiq_ssc_spi *spi = data;
+	const struct lantiq_ssc_hwcfg *hwcfg = spi->hwcfg;
 	u32 stat = lantiq_ssc_readl(spi, LTQ_SPI_STAT);
+	u32 val = lantiq_ssc_readl(spi, hwcfg->irncr);
+	unsigned long flags;
 
 	if (!(stat & LTQ_SPI_STAT_ERRORS))
 		return IRQ_NONE;
 
+	spin_lock_irqsave(&spi->lock, flags);
+	if (hwcfg->irq_ack)
+		lantiq_ssc_writel(spi, val, hwcfg->irncr);
+
 	if (stat & LTQ_SPI_STAT_RUE)
 		dev_err(spi->dev, "receive underflow error\n");
 	if (stat & LTQ_SPI_STAT_TUE)
@@ -671,6 +697,25 @@ static irqreturn_t lantiq_ssc_err_interrupt(int irq, void *data)
 	if (spi->master->cur_msg)
 		spi->master->cur_msg->status = -EIO;
 	queue_work(spi->wq, &spi->work);
+	spin_unlock_irqrestore(&spi->lock, flags);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t intel_lgm_ssc_isr(int irq, void *data)
+{
+	struct lantiq_ssc_spi *spi = data;
+	const struct lantiq_ssc_hwcfg *hwcfg = spi->hwcfg;
+	u32 val = lantiq_ssc_readl(spi, hwcfg->irncr);
+
+	if (!(val & LTQ_SPI_IRNEN_ALL))
+		return IRQ_NONE;
+
+	if (val & LTQ_SPI_IRNEN_E)
+		return lantiq_ssc_err_interrupt(irq, data);
+
+	if ((val & hwcfg->irnen_t) || (val & hwcfg->irnen_r))
+		return lantiq_ssc_xmit_interrupt(irq, data);
 
 	return IRQ_HANDLED;
 }
@@ -775,20 +820,84 @@ static int lantiq_ssc_transfer_one(struct spi_master *master,
 	return transfer_start(spi, spidev, t);
 }
 
+static int intel_lgm_cfg_irq(struct platform_device *pdev, struct lantiq_ssc_spi *spi)
+{
+	int irq;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	return devm_request_irq(&pdev->dev, irq, intel_lgm_ssc_isr, 0, "spi", spi);
+}
+
+static int lantiq_cfg_irq(struct platform_device *pdev, struct lantiq_ssc_spi *spi)
+{
+	int irq, err;
+
+	irq = platform_get_irq_byname(pdev, LTQ_SPI_RX_IRQ_NAME);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(&pdev->dev, irq, lantiq_ssc_xmit_interrupt,
+			       0, LTQ_SPI_RX_IRQ_NAME, spi);
+	if (err)
+		return err;
+
+	irq = platform_get_irq_byname(pdev, LTQ_SPI_TX_IRQ_NAME);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(&pdev->dev, irq, lantiq_ssc_xmit_interrupt,
+			       0, LTQ_SPI_TX_IRQ_NAME, spi);
+
+	if (err)
+		return err;
+
+	irq = platform_get_irq_byname(pdev, LTQ_SPI_ERR_IRQ_NAME);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(&pdev->dev, irq, lantiq_ssc_err_interrupt,
+			       0, LTQ_SPI_ERR_IRQ_NAME, spi);
+	return err;
+}
+
 static const struct lantiq_ssc_hwcfg lantiq_ssc_xway = {
-	.irnen_r = LTQ_SPI_IRNEN_R_XWAY,
-	.irnen_t = LTQ_SPI_IRNEN_T_XWAY,
+	.cfg_irq	= lantiq_cfg_irq,
+	.irnen_r	= LTQ_SPI_IRNEN_R_XWAY,
+	.irnen_t	= LTQ_SPI_IRNEN_T_XWAY,
+	.irnicr		= 0xF8,
+	.irncr		= 0xFC,
+	.fifo_size_mask	= GENMASK(5, 0),
+	.irq_ack	= false,
 };
 
 static const struct lantiq_ssc_hwcfg lantiq_ssc_xrx = {
-	.irnen_r = LTQ_SPI_IRNEN_R_XRX,
-	.irnen_t = LTQ_SPI_IRNEN_T_XRX,
+	.cfg_irq	= lantiq_cfg_irq,
+	.irnen_r	= LTQ_SPI_IRNEN_R_XRX,
+	.irnen_t	= LTQ_SPI_IRNEN_T_XRX,
+	.irnicr		= 0xF8,
+	.irncr		= 0xFC,
+	.fifo_size_mask	= GENMASK(5, 0),
+	.irq_ack	= false,
+};
+
+static const struct lantiq_ssc_hwcfg intel_ssc_lgm = {
+	.cfg_irq	= intel_lgm_cfg_irq,
+	.irnen_r	= LTQ_SPI_IRNEN_R_XRX,
+	.irnen_t	= LTQ_SPI_IRNEN_T_XRX,
+	.irnicr		= 0xFC,
+	.irncr		= 0xF8,
+	.fifo_size_mask	= GENMASK(7, 0),
+	.irq_ack	= true,
 };
 
 static const struct of_device_id lantiq_ssc_match[] = {
 	{ .compatible = "lantiq,ase-spi", .data = &lantiq_ssc_xway, },
 	{ .compatible = "lantiq,falcon-spi", .data = &lantiq_ssc_xrx, },
 	{ .compatible = "lantiq,xrx100-spi", .data = &lantiq_ssc_xrx, },
+	{ .compatible = "intel,lgm-spi", .data = &intel_ssc_lgm, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, lantiq_ssc_match);
@@ -800,9 +909,9 @@ static int lantiq_ssc_probe(struct platform_device *pdev)
 	struct lantiq_ssc_spi *spi;
 	const struct lantiq_ssc_hwcfg *hwcfg;
 	const struct of_device_id *match;
-	int err, rx_irq, tx_irq, err_irq;
 	u32 id, supports_dma, revision;
 	unsigned int num_cs;
+	int err;
 
 	match = of_match_device(lantiq_ssc_match, dev);
 	if (!match) {
@@ -811,18 +920,6 @@ static int lantiq_ssc_probe(struct platform_device *pdev)
 	}
 	hwcfg = match->data;
 
-	rx_irq = platform_get_irq_byname(pdev, LTQ_SPI_RX_IRQ_NAME);
-	if (rx_irq < 0)
-		return -ENXIO;
-
-	tx_irq = platform_get_irq_byname(pdev, LTQ_SPI_TX_IRQ_NAME);
-	if (tx_irq < 0)
-		return -ENXIO;
-
-	err_irq = platform_get_irq_byname(pdev, LTQ_SPI_ERR_IRQ_NAME);
-	if (err_irq < 0)
-		return -ENXIO;
-
 	master = spi_alloc_master(dev, sizeof(struct lantiq_ssc_spi));
 	if (!master)
 		return -ENOMEM;
@@ -838,18 +935,7 @@ static int lantiq_ssc_probe(struct platform_device *pdev)
 		goto err_master_put;
 	}
 
-	err = devm_request_irq(dev, rx_irq, lantiq_ssc_xmit_interrupt,
-			       0, LTQ_SPI_RX_IRQ_NAME, spi);
-	if (err)
-		goto err_master_put;
-
-	err = devm_request_irq(dev, tx_irq, lantiq_ssc_xmit_interrupt,
-			       0, LTQ_SPI_TX_IRQ_NAME, spi);
-	if (err)
-		goto err_master_put;
-
-	err = devm_request_irq(dev, err_irq, lantiq_ssc_err_interrupt,
-			       0, LTQ_SPI_ERR_IRQ_NAME, spi);
+	err = hwcfg->cfg_irq(pdev, spi);
 	if (err)
 		goto err_master_put;
 
@@ -888,6 +974,7 @@ static int lantiq_ssc_probe(struct platform_device *pdev)
 
 	master->dev.of_node = pdev->dev.of_node;
 	master->num_chipselect = num_cs;
+	master->use_gpio_descriptors = true;
 	master->setup = lantiq_ssc_setup;
 	master->set_cs = lantiq_ssc_set_cs;
 	master->handle_err = lantiq_ssc_handle_err;
@@ -907,8 +994,8 @@ static int lantiq_ssc_probe(struct platform_device *pdev)
 	INIT_WORK(&spi->work, lantiq_ssc_bussy_work);
 
 	id = lantiq_ssc_readl(spi, LTQ_SPI_ID);
-	spi->tx_fifo_size = (id & LTQ_SPI_ID_TXFS_M) >> LTQ_SPI_ID_TXFS_S;
-	spi->rx_fifo_size = (id & LTQ_SPI_ID_RXFS_M) >> LTQ_SPI_ID_RXFS_S;
+	spi->tx_fifo_size = (id >> LTQ_SPI_ID_TXFS_S) & hwcfg->fifo_size_mask;
+	spi->rx_fifo_size = (id >> LTQ_SPI_ID_RXFS_S) & hwcfg->fifo_size_mask;
 	supports_dma = (id & LTQ_SPI_ID_CFG_M) >> LTQ_SPI_ID_CFG_S;
 	revision = id & LTQ_SPI_ID_REV_M;
 
diff --git a/drivers/spi/spi-loopback-test.c b/drivers/spi/spi-loopback-test.c
index b6d79cd156fb..9522d1b5786d 100644
--- a/drivers/spi/spi-loopback-test.c
+++ b/drivers/spi/spi-loopback-test.c
@@ -885,10 +885,10 @@ static int spi_test_run_iter(struct spi_device *spi,
 /**
  * spi_test_execute_msg - default implementation to run a test
  *
- * spi: @spi_device on which to run the @spi_message
- * test: the test to execute, which already contains @msg
- * tx:   the tx buffer allocated for the test sequence
- * rx:   the rx buffer allocated for the test sequence
+ * @spi: @spi_device on which to run the @spi_message
+ * @test: the test to execute, which already contains @msg
+ * @tx:   the tx buffer allocated for the test sequence
+ * @rx:   the rx buffer allocated for the test sequence
  *
  * Returns: error code of spi_sync as well as basic error checking
  */
@@ -957,10 +957,10 @@ EXPORT_SYMBOL_GPL(spi_test_execute_msg);
  *                     including all the relevant iterations on:
  *                     length and buffer alignment
  *
- * spi:  the spi_device to send the messages to
- * test: the test which we need to execute
- * tx:   the tx buffer allocated for the test sequence
- * rx:   the rx buffer allocated for the test sequence
+ * @spi:  the spi_device to send the messages to
+ * @test: the test which we need to execute
+ * @tx:   the tx buffer allocated for the test sequence
+ * @rx:   the rx buffer allocated for the test sequence
  *
  * Returns: status code of spi_sync or other failures
  */
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 9a86cc27fcc0..ef53290b7d24 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -156,6 +156,12 @@ bool spi_mem_default_supports_op(struct spi_mem *mem,
 				   op->data.dir == SPI_MEM_DATA_OUT))
 		return false;
 
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		return false;
+
+	if (op->cmd.nbytes != 1)
+		return false;
+
 	return true;
 }
 EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
@@ -170,7 +176,7 @@ static bool spi_mem_buswidth_is_valid(u8 buswidth)
 
 static int spi_mem_check_op(const struct spi_mem_op *op)
 {
-	if (!op->cmd.buswidth)
+	if (!op->cmd.buswidth || !op->cmd.nbytes)
 		return -EINVAL;
 
 	if ((op->addr.nbytes && !op->addr.buswidth) ||
@@ -306,8 +312,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 			return ret;
 	}
 
-	tmpbufsize = sizeof(op->cmd.opcode) + op->addr.nbytes +
-		     op->dummy.nbytes;
+	tmpbufsize = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 	/*
 	 * Allocate a buffer to transmit the CMD, ADDR cycles with kmalloc() so
@@ -322,7 +327,7 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 
 	tmpbuf[0] = op->cmd.opcode;
 	xfers[xferpos].tx_buf = tmpbuf;
-	xfers[xferpos].len = sizeof(op->cmd.opcode);
+	xfers[xferpos].len = op->cmd.nbytes;
 	xfers[xferpos].tx_nbits = op->cmd.buswidth;
 	spi_message_add_tail(&xfers[xferpos], &msg);
 	xferpos++;
@@ -424,8 +429,7 @@ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 		return ctlr->mem_ops->adjust_op_size(mem, op);
 
 	if (!ctlr->mem_ops || !ctlr->mem_ops->exec_op) {
-		len = sizeof(op->cmd.opcode) + op->addr.nbytes +
-		      op->dummy.nbytes;
+		len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 		if (len > spi_max_transfer_size(mem->spi))
 			return -EINVAL;
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 77f7d0e0e46a..ecba6b4a5d85 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -362,8 +362,6 @@ static void meson_spicc_setup_xfer(struct meson_spicc_device *spicc,
 
 static void meson_spicc_reset_fifo(struct meson_spicc_device *spicc)
 {
-	u32 data;
-
 	if (spicc->data->has_oen)
 		writel_bits_relaxed(SPICC_ENH_MAIN_CLK_AO,
 				    SPICC_ENH_MAIN_CLK_AO,
@@ -373,7 +371,7 @@ static void meson_spicc_reset_fifo(struct meson_spicc_device *spicc)
 			    spicc->base + SPICC_TESTREG);
 
 	while (meson_spicc_rxready(spicc))
-		data = readl_relaxed(spicc->base + SPICC_RXDATA);
+		readl_relaxed(spicc->base + SPICC_RXDATA);
 
 	if (spicc->data->has_oen)
 		writel_bits_relaxed(SPICC_ENH_MAIN_CLK_AO, 0,
diff --git a/drivers/spi/spi-meson-spifc.c b/drivers/spi/spi-meson-spifc.c
index c7b039980291..8eca6f24cb79 100644
--- a/drivers/spi/spi-meson-spifc.c
+++ b/drivers/spi/spi-meson-spifc.c
@@ -70,7 +70,7 @@
  * @master:	the SPI master
  * @regmap:	regmap for device registers
  * @clk:	input clock of the built-in baud rate generator
- * @device:	the device structure
+ * @dev:	the device structure
  */
 struct meson_spifc {
 	struct spi_master *master;
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
index a556795caeef..5d643051bf3d 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -171,6 +171,9 @@ static const struct of_device_id mtk_spi_of_match[] = {
 	{ .compatible = "mediatek,mt8183-spi",
 		.data = (void *)&mt8183_compat,
 	},
+	{ .compatible = "mediatek,mt8192-spi",
+		.data = (void *)&mt6765_compat,
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(of, mtk_spi_of_match);
diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c
index 7bc302b50396..b08d8e9a8ee9 100644
--- a/drivers/spi/spi-mtk-nor.c
+++ b/drivers/spi/spi-mtk-nor.c
@@ -195,7 +195,7 @@ static int mtk_nor_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 		}
 	}
 
-	len = MTK_NOR_PRG_MAX_SIZE - sizeof(op->cmd.opcode) - op->addr.nbytes -
+	len = MTK_NOR_PRG_MAX_SIZE - op->cmd.nbytes - op->addr.nbytes -
 	      op->dummy.nbytes;
 	if (op->data.nbytes > len)
 		op->data.nbytes = len;
@@ -211,6 +211,12 @@ static bool mtk_nor_supports_op(struct spi_mem *mem,
 	if (op->cmd.buswidth != 1)
 		return false;
 
+	/* DTR ops not supported. */
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		return false;
+	if (op->cmd.nbytes != 1)
+		return false;
+
 	if ((op->addr.nbytes == 3) || (op->addr.nbytes == 4)) {
 		if ((op->data.dir == SPI_MEM_DATA_IN) && mtk_nor_match_read(op))
 			return true;
@@ -219,7 +225,7 @@ static bool mtk_nor_supports_op(struct spi_mem *mem,
 			       (op->dummy.buswidth == 0) &&
 			       (op->data.buswidth == 1);
 	}
-	len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
+	len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 	if ((len > MTK_NOR_PRG_MAX_SIZE) ||
 	    ((op->data.nbytes) && (len == MTK_NOR_PRG_MAX_SIZE)))
 		return false;
diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c
index 69491f3a515d..8c630acb0110 100644
--- a/drivers/spi/spi-mxic.c
+++ b/drivers/spi/spi-mxic.c
@@ -356,6 +356,7 @@ static int mxic_spi_mem_exec_op(struct spi_mem *mem,
 	int nio = 1, i, ret;
 	u32 ss_ctrl;
 	u8 addr[8];
+	u8 opcode = op->cmd.opcode;
 
 	ret = mxic_spi_set_freq(mxic, mem->spi->max_speed_hz);
 	if (ret)
@@ -393,7 +394,7 @@ static int mxic_spi_mem_exec_op(struct spi_mem *mem,
 	writel(readl(mxic->regs + HC_CFG) | HC_CFG_MAN_CS_ASSERT,
 	       mxic->regs + HC_CFG);
 
-	ret = mxic_spi_data_xfer(mxic, &op->cmd.opcode, NULL, 1);
+	ret = mxic_spi_data_xfer(mxic, &opcode, NULL, 1);
 	if (ret)
 		goto out;
 
diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c
index d25ee32862e0..9468e71f03ad 100644
--- a/drivers/spi/spi-npcm-fiu.c
+++ b/drivers/spi/spi-npcm-fiu.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Nuvoton Technology corporation.
 
+#include <linux/bits.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/device.h>
@@ -177,7 +178,6 @@ enum {
 #define MAP_SIZE_16MB			0x1000000
 #define MAP_SIZE_8MB			0x800000
 
-#define NUM_BITS_IN_BYTE		8
 #define FIU_DRD_MAX_DUMMY_NUMBER	3
 #define NPCM_MAX_CHIP_NUM		4
 #define CHUNK_SIZE			16
@@ -252,8 +252,8 @@ static void npcm_fiu_set_drd(struct npcm_fiu_spi *fiu,
 	fiu->drd_op.addr.buswidth = op->addr.buswidth;
 	regmap_update_bits(fiu->regmap, NPCM_FIU_DRD_CFG,
 			   NPCM_FIU_DRD_CFG_DBW,
-			   ((op->dummy.nbytes * ilog2(op->addr.buswidth))
-			    / NUM_BITS_IN_BYTE) << NPCM_FIU_DRD_DBW_SHIFT);
+			   ((op->dummy.nbytes * ilog2(op->addr.buswidth)) / BITS_PER_BYTE)
+			   << NPCM_FIU_DRD_DBW_SHIFT);
 	fiu->drd_op.dummy.nbytes = op->dummy.nbytes;
 	regmap_update_bits(fiu->regmap, NPCM_FIU_DRD_CFG,
 			   NPCM_FIU_DRD_CFG_RDCMD, op->cmd.opcode);
diff --git a/drivers/spi/spi-npcm-pspi.c b/drivers/spi/spi-npcm-pspi.c
index 87cd0233c60b..56d10c4511db 100644
--- a/drivers/spi/spi-npcm-pspi.c
+++ b/drivers/spi/spi-npcm-pspi.c
@@ -10,8 +10,6 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
 #include <linux/reset.h>
 
 #include <asm/unaligned.h>
@@ -344,16 +342,9 @@ static int npcm_pspi_probe(struct platform_device *pdev)
 	struct npcm_pspi *priv;
 	struct spi_master *master;
 	unsigned long clk_hz;
-	struct device_node *np = pdev->dev.of_node;
-	int num_cs, i;
-	int csgpio;
 	int irq;
 	int ret;
 
-	num_cs = of_gpio_named_count(np, "cs-gpios");
-	if (num_cs < 0)
-		return num_cs;
-
 	master = spi_alloc_master(&pdev->dev, sizeof(*priv));
 	if (!master)
 		return -ENOMEM;
@@ -418,24 +409,7 @@ static int npcm_pspi_probe(struct platform_device *pdev)
 		npcm_pspi_prepare_transfer_hardware;
 	master->unprepare_transfer_hardware =
 		npcm_pspi_unprepare_transfer_hardware;
-	master->num_chipselect = num_cs;
-
-	for (i = 0; i < num_cs; i++) {
-		csgpio = of_get_named_gpio(np, "cs-gpios", i);
-		if (csgpio < 0) {
-			dev_err(&pdev->dev, "failed to get csgpio#%u\n", i);
-			goto out_disable_clk;
-		}
-		dev_dbg(&pdev->dev, "csgpio#%u = %d\n", i, csgpio);
-		ret = devm_gpio_request_one(&pdev->dev, csgpio,
-					    GPIOF_OUT_INIT_HIGH, DRIVER_NAME);
-		if (ret < 0) {
-			dev_err(&pdev->dev,
-				"failed to configure csgpio#%u %d\n"
-				, i, csgpio);
-			goto out_disable_clk;
-		}
-	}
+	master->use_gpio_descriptors = true;
 
 	/* set to default clock rate */
 	npcm_pspi_set_baudrate(priv, NPCM_PSPI_DEFAULT_CLK);
diff --git a/drivers/spi/spi-oc-tiny.c b/drivers/spi/spi-oc-tiny.c
index 9df7c5979c29..f3843f0ff260 100644
--- a/drivers/spi/spi-oc-tiny.c
+++ b/drivers/spi/spi-oc-tiny.c
@@ -2,7 +2,7 @@
 /*
  * OpenCores tiny SPI master driver
  *
- * http://opencores.org/project,tiny_spi
+ * https://opencores.org/project,tiny_spi
  *
  * Copyright (C) 2011 Thomas Chou <thomas@wytron.com.tw>
  *
diff --git a/drivers/spi/spi-omap-100k.c b/drivers/spi/spi-omap-100k.c
index 5c704ba6d8ea..36a4922a134a 100644
--- a/drivers/spi/spi-omap-100k.c
+++ b/drivers/spi/spi-omap-100k.c
@@ -19,7 +19,6 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
 #include <linux/slab.h>
 
 #include <linux/spi/spi.h>
diff --git a/drivers/spi/spi-omap-uwire.c b/drivers/spi/spi-omap-uwire.c
index ce8dbdbce312..71402f71ddd8 100644
--- a/drivers/spi/spi-omap-uwire.c
+++ b/drivers/spi/spi-omap-uwire.c
@@ -443,7 +443,7 @@ static void uwire_cleanup(struct spi_device *spi)
 static void uwire_off(struct uwire_spi *uwire)
 {
 	uwire_write_reg(UWIRE_SR3, 0);
-	clk_disable(uwire->ck);
+	clk_disable_unprepare(uwire->ck);
 	spi_master_put(uwire->bitbang.master);
 }
 
@@ -475,7 +475,7 @@ static int uwire_probe(struct platform_device *pdev)
 		spi_master_put(master);
 		return status;
 	}
-	clk_enable(uwire->ck);
+	clk_prepare_enable(uwire->ck);
 
 	if (cpu_is_omap7xx())
 		uwire_idx_shift = 1;
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index e9e256718ef4..1c9478e6e5d9 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -27,7 +27,6 @@
 #include <linux/iopoll.h>
 
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
 
 #include <linux/platform_data/spi-omap2-mcspi.h>
 
@@ -1043,16 +1042,6 @@ static int omap2_mcspi_setup(struct spi_device *spi)
 		spi->controller_state = cs;
 		/* Link this to context save list */
 		list_add_tail(&cs->node, &ctx->cs);
-
-		if (gpio_is_valid(spi->cs_gpio)) {
-			ret = gpio_request(spi->cs_gpio, dev_name(&spi->dev));
-			if (ret) {
-				dev_err(&spi->dev, "failed to request gpio\n");
-				return ret;
-			}
-			gpio_direction_output(spi->cs_gpio,
-					 !(spi->mode & SPI_CS_HIGH));
-		}
 	}
 
 	ret = pm_runtime_get_sync(mcspi->dev);
@@ -1080,9 +1069,6 @@ static void omap2_mcspi_cleanup(struct spi_device *spi)
 
 		kfree(cs);
 	}
-
-	if (gpio_is_valid(spi->cs_gpio))
-		gpio_free(spi->cs_gpio);
 }
 
 static irqreturn_t omap2_mcspi_irq_handler(int irq, void *data)
@@ -1152,7 +1138,7 @@ static int omap2_mcspi_transfer_one(struct spi_master *master,
 
 	omap2_mcspi_set_enable(spi, 0);
 
-	if (gpio_is_valid(spi->cs_gpio))
+	if (spi->cs_gpiod)
 		omap2_mcspi_set_cs(spi, spi->mode & SPI_CS_HIGH);
 
 	if (par_override ||
@@ -1241,7 +1227,7 @@ out:
 
 	omap2_mcspi_set_enable(spi, 0);
 
-	if (gpio_is_valid(spi->cs_gpio))
+	if (spi->cs_gpiod)
 		omap2_mcspi_set_cs(spi, !(spi->mode & SPI_CS_HIGH));
 
 	if (mcspi->fifo_depth > 0 && t)
@@ -1431,6 +1417,7 @@ static int omap2_mcspi_probe(struct platform_device *pdev)
 	master->dev.of_node = node;
 	master->max_speed_hz = OMAP2_MCSPI_MAX_FREQ;
 	master->min_speed_hz = OMAP2_MCSPI_MAX_FREQ >> 15;
+	master->use_gpio_descriptors = true;
 
 	platform_set_drvdata(pdev, master);
 
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 43f73db22f21..b57b8b3cc26e 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -708,7 +708,7 @@ static int orion_spi_probe(struct platform_device *pdev)
 		/*
 		 * Only map one page for direct access. This is enough for the
 		 * simple TX transfer which only writes to the first word.
-		 * This needs to get extended for the direct SPI-NOR / SPI-NAND
+		 * This needs to get extended for the direct SPI NOR / SPI NAND
 		 * support, once this gets implemented.
 		 */
 		dir_acc = &spi->child[cs].direct_access;
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index 66028ebbc336..d1776fea287e 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -298,7 +298,7 @@ enum ssp_reading {
 	READING_U32
 };
 
-/**
+/*
  * The type of writing going on on this chip
  */
 enum ssp_writing {
@@ -317,6 +317,7 @@ enum ssp_writing {
  * @extended_cr: 32 bit wide control register 0 with extra
  * features and extra features in CR1 as found in the ST variants
  * @pl023: supports a subset of the ST extensions called "PL023"
+ * @loopback: supports loopback mode
  * @internal_cs_ctrl: supports chip select control register
  */
 struct vendor_data {
@@ -353,11 +354,14 @@ struct vendor_data {
  * @read: the type of read currently going on
  * @write: the type of write currently going on
  * @exp_fifo_level: expected FIFO level
+ * @rx_lev_trig: receive FIFO watermark level which triggers IRQ
+ * @tx_lev_trig: transmit FIFO watermark level which triggers IRQ
  * @dma_rx_channel: optional channel for RX DMA
  * @dma_tx_channel: optional channel for TX DMA
  * @sgt_rx: scattertable for the RX transfer
  * @sgt_tx: scattertable for the TX transfer
  * @dummypage: a dummy page used for driving data on the bus with DMA
+ * @dma_running: indicates whether DMA is in operation
  * @cur_cs: current chip select (gpio)
  * @chipselects: list of chipselects (gpios)
  */
@@ -662,7 +666,7 @@ static void load_ssp_default_config(struct pl022 *pl022)
 	writew(CLEAR_ALL_INTERRUPTS, SSP_ICR(pl022->virtbase));
 }
 
-/**
+/*
  * This will write to TX and read from RX according to the parameters
  * set in pl022.
  */
@@ -1237,6 +1241,8 @@ static inline void pl022_dma_remove(struct pl022 *pl022)
 
 /**
  * pl022_interrupt_handler - Interrupt handler for SSP controller
+ * @irq: IRQ number
+ * @dev_id: Local device data
  *
  * This function handles interrupts generated for an interrupt based transfer.
  * If a receive overrun (ROR) interrupt is there then we disable SSP, flag the
@@ -1334,7 +1340,7 @@ static irqreturn_t pl022_interrupt_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-/**
+/*
  * This sets up the pointers to memory for the next message to
  * send out on the SPI bus.
  */
diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
index 0ea2d9a369d9..d8ee363fb714 100644
--- a/drivers/spi/spi-ppc4xx.c
+++ b/drivers/spi/spi-ppc4xx.c
@@ -28,11 +28,9 @@
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
-#include <linux/of_gpio.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
 
-#include <linux/gpio.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
 
@@ -127,8 +125,6 @@ struct ppc4xx_spi {
 	const unsigned char *tx;
 	unsigned char *rx;
 
-	int *gpios;
-
 	struct spi_ppc4xx_regs __iomem *regs; /* pointer to the registers */
 	struct spi_master *master;
 	struct device *dev;
@@ -260,27 +256,6 @@ static int spi_ppc4xx_setup(struct spi_device *spi)
 	return 0;
 }
 
-static void spi_ppc4xx_chipsel(struct spi_device *spi, int value)
-{
-	struct ppc4xx_spi *hw = spi_master_get_devdata(spi->master);
-	unsigned int cs = spi->chip_select;
-	unsigned int cspol;
-
-	/*
-	 * If there are no chip selects at all, or if this is the special
-	 * case of a non-existent (dummy) chip select, do nothing.
-	 */
-
-	if (!hw->master->num_chipselect || hw->gpios[cs] == -EEXIST)
-		return;
-
-	cspol = spi->mode & SPI_CS_HIGH ? 1 : 0;
-	if (value == BITBANG_CS_INACTIVE)
-		cspol = !cspol;
-
-	gpio_set_value(hw->gpios[cs], cspol);
-}
-
 static irqreturn_t spi_ppc4xx_int(int irq, void *dev_id)
 {
 	struct ppc4xx_spi *hw;
@@ -359,19 +334,6 @@ static void spi_ppc4xx_enable(struct ppc4xx_spi *hw)
 	dcri_clrset(SDR0, SDR0_PFC1, 0x80000000 >> 14, 0);
 }
 
-static void free_gpios(struct ppc4xx_spi *hw)
-{
-	if (hw->master->num_chipselect) {
-		int i;
-		for (i = 0; i < hw->master->num_chipselect; i++)
-			if (gpio_is_valid(hw->gpios[i]))
-				gpio_free(hw->gpios[i]);
-
-		kfree(hw->gpios);
-		hw->gpios = NULL;
-	}
-}
-
 /*
  * platform_device layer stuff...
  */
@@ -385,7 +347,6 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 	struct device *dev = &op->dev;
 	struct device_node *opbnp;
 	int ret;
-	int num_gpios;
 	const unsigned int *clk;
 
 	master = spi_alloc_master(dev, sizeof *hw);
@@ -399,74 +360,32 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 
 	init_completion(&hw->done);
 
-	/*
-	 * A count of zero implies a single SPI device without any chip-select.
-	 * Note that of_gpio_count counts all gpios assigned to this spi master.
-	 * This includes both "null" gpio's and real ones.
-	 */
-	num_gpios = of_gpio_count(np);
-	if (num_gpios > 0) {
-		int i;
-
-		hw->gpios = kcalloc(num_gpios, sizeof(*hw->gpios), GFP_KERNEL);
-		if (!hw->gpios) {
-			ret = -ENOMEM;
-			goto free_master;
-		}
-
-		for (i = 0; i < num_gpios; i++) {
-			int gpio;
-			enum of_gpio_flags flags;
-
-			gpio = of_get_gpio_flags(np, i, &flags);
-			hw->gpios[i] = gpio;
-
-			if (gpio_is_valid(gpio)) {
-				/* Real CS - set the initial state. */
-				ret = gpio_request(gpio, np->name);
-				if (ret < 0) {
-					dev_err(dev,
-						"can't request gpio #%d: %d\n",
-						i, ret);
-					goto free_gpios;
-				}
-
-				gpio_direction_output(gpio,
-						!!(flags & OF_GPIO_ACTIVE_LOW));
-			} else if (gpio == -EEXIST) {
-				; /* No CS, but that's OK. */
-			} else {
-				dev_err(dev, "invalid gpio #%d: %d\n", i, gpio);
-				ret = -EINVAL;
-				goto free_gpios;
-			}
-		}
-	}
-
 	/* Setup the state for the bitbang driver */
 	bbp = &hw->bitbang;
 	bbp->master = hw->master;
 	bbp->setup_transfer = spi_ppc4xx_setupxfer;
-	bbp->chipselect = spi_ppc4xx_chipsel;
 	bbp->txrx_bufs = spi_ppc4xx_txrx;
 	bbp->use_dma = 0;
 	bbp->master->setup = spi_ppc4xx_setup;
 	bbp->master->cleanup = spi_ppc4xx_cleanup;
 	bbp->master->bits_per_word_mask = SPI_BPW_MASK(8);
+	bbp->master->use_gpio_descriptors = true;
+	/*
+	 * The SPI core will count the number of GPIO descriptors to figure
+	 * out the number of chip selects available on the platform.
+	 */
+	bbp->master->num_chipselect = 0;
 
 	/* the spi->mode bits understood by this driver: */
 	bbp->master->mode_bits =
 		SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LSB_FIRST;
 
-	/* this many pins in all GPIO controllers */
-	bbp->master->num_chipselect = num_gpios > 0 ? num_gpios : 0;
-
 	/* Get the clock for the OPB */
 	opbnp = of_find_compatible_node(NULL, NULL, "ibm,opb");
 	if (opbnp == NULL) {
 		dev_err(dev, "OPB: cannot find node\n");
 		ret = -ENODEV;
-		goto free_gpios;
+		goto free_master;
 	}
 	/* Get the clock (Hz) for the OPB */
 	clk = of_get_property(opbnp, "clock-frequency", NULL);
@@ -474,7 +393,7 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 		dev_err(dev, "OPB: no clock-frequency property set\n");
 		of_node_put(opbnp);
 		ret = -ENODEV;
-		goto free_gpios;
+		goto free_master;
 	}
 	hw->opb_freq = *clk;
 	hw->opb_freq >>= 2;
@@ -483,7 +402,7 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 	ret = of_address_to_resource(np, 0, &resource);
 	if (ret) {
 		dev_err(dev, "error while parsing device node resource\n");
-		goto free_gpios;
+		goto free_master;
 	}
 	hw->mapbase = resource.start;
 	hw->mapsize = resource_size(&resource);
@@ -492,7 +411,7 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 	if (hw->mapsize < sizeof(struct spi_ppc4xx_regs)) {
 		dev_err(dev, "too small to map registers\n");
 		ret = -EINVAL;
-		goto free_gpios;
+		goto free_master;
 	}
 
 	/* Request IRQ */
@@ -501,7 +420,7 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
 			  0, "spi_ppc4xx_of", (void *)hw);
 	if (ret) {
 		dev_err(dev, "unable to allocate interrupt\n");
-		goto free_gpios;
+		goto free_master;
 	}
 
 	if (!request_mem_region(hw->mapbase, hw->mapsize, DRIVER_NAME)) {
@@ -538,8 +457,6 @@ map_io_error:
 	release_mem_region(hw->mapbase, hw->mapsize);
 request_mem_error:
 	free_irq(hw->irqnum, hw);
-free_gpios:
-	free_gpios(hw);
 free_master:
 	spi_master_put(master);
 
@@ -556,7 +473,6 @@ static int spi_ppc4xx_of_remove(struct platform_device *op)
 	release_mem_region(hw->mapbase, hw->mapsize);
 	free_irq(hw->irqnum, hw);
 	iounmap(hw->regs);
-	free_gpios(hw);
 	spi_master_put(master);
 	return 0;
 }
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 0040362b7162..814268405ab0 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1432,6 +1432,7 @@ static void cleanup(struct spi_device *spi)
 	kfree(chip);
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{ "INT33C0", LPSS_LPT_SSP },
 	{ "INT33C1", LPSS_LPT_SSP },
@@ -1442,6 +1443,7 @@ static const struct acpi_device_id pxa2xx_spi_acpi_match[] = {
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match);
+#endif
 
 /*
  * PCI IDs of compound devices that integrate both host controller and private
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 9b8a5e1233c0..75a8a9428ff8 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -39,8 +39,9 @@
 #define ROCKCHIP_SPI_RISR			0x0034
 #define ROCKCHIP_SPI_ICR			0x0038
 #define ROCKCHIP_SPI_DMACR			0x003c
-#define ROCKCHIP_SPI_DMATDLR		0x0040
-#define ROCKCHIP_SPI_DMARDLR		0x0044
+#define ROCKCHIP_SPI_DMATDLR			0x0040
+#define ROCKCHIP_SPI_DMARDLR			0x0044
+#define ROCKCHIP_SPI_VERSION			0x0048
 #define ROCKCHIP_SPI_TXDR			0x0400
 #define ROCKCHIP_SPI_RXDR			0x0800
 
@@ -156,6 +157,8 @@
 #define ROCKCHIP_SPI_MAX_TRANLEN		0xffff
 
 #define ROCKCHIP_SPI_MAX_CS_NUM			2
+#define ROCKCHIP_SPI_VER2_TYPE1			0x05EC0002
+#define ROCKCHIP_SPI_VER2_TYPE2			0x00110002
 
 struct rockchip_spi {
 	struct device *dev;
@@ -206,17 +209,17 @@ static inline void wait_for_idle(struct rockchip_spi *rs)
 
 static u32 get_fifo_len(struct rockchip_spi *rs)
 {
-	u32 fifo;
+	u32 ver;
 
-	for (fifo = 2; fifo < 32; fifo++) {
-		writel_relaxed(fifo, rs->regs + ROCKCHIP_SPI_TXFTLR);
-		if (fifo != readl_relaxed(rs->regs + ROCKCHIP_SPI_TXFTLR))
-			break;
-	}
-
-	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_TXFTLR);
+	ver = readl_relaxed(rs->regs + ROCKCHIP_SPI_VERSION);
 
-	return (fifo == 31) ? 0 : fifo;
+	switch (ver) {
+	case ROCKCHIP_SPI_VER2_TYPE1:
+	case ROCKCHIP_SPI_VER2_TYPE2:
+		return 64;
+	default:
+		return 32;
+	}
 }
 
 static void rockchip_spi_set_cs(struct spi_device *spi, bool enable)
@@ -288,7 +291,7 @@ static void rockchip_spi_pio_writer(struct rockchip_spi *rs)
 static void rockchip_spi_pio_reader(struct rockchip_spi *rs)
 {
 	u32 words = readl_relaxed(rs->regs + ROCKCHIP_SPI_RXFLR);
-	u32 rx_left = rs->rx_left - words;
+	u32 rx_left = (rs->rx_left > words) ? rs->rx_left - words : 0;
 
 	/* the hardware doesn't allow us to change fifo threshold
 	 * level while spi is enabled, so instead make sure to leave
@@ -384,6 +387,19 @@ static void rockchip_spi_dma_txcb(void *data)
 	spi_finalize_current_transfer(ctlr);
 }
 
+static u32 rockchip_spi_calc_burst_size(u32 data_len)
+{
+	u32 i;
+
+	/* burst size: 1, 2, 4, 8 */
+	for (i = 1; i < 8; i <<= 1) {
+		if (data_len & i)
+			break;
+	}
+
+	return i;
+}
+
 static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 		struct spi_controller *ctlr, struct spi_transfer *xfer)
 {
@@ -397,7 +413,8 @@ static int rockchip_spi_prepare_dma(struct rockchip_spi *rs,
 			.direction = DMA_DEV_TO_MEM,
 			.src_addr = rs->dma_addr_rx,
 			.src_addr_width = rs->n_bytes,
-			.src_maxburst = 1,
+			.src_maxburst = rockchip_spi_calc_burst_size(xfer->len /
+								     rs->n_bytes),
 		};
 
 		dmaengine_slave_config(ctlr->dma_rx, &rxconf);
@@ -525,7 +542,8 @@ static void rockchip_spi_config(struct rockchip_spi *rs,
 		writel_relaxed(rs->fifo_len / 2 - 1, rs->regs + ROCKCHIP_SPI_RXFTLR);
 
 	writel_relaxed(rs->fifo_len / 2, rs->regs + ROCKCHIP_SPI_DMATDLR);
-	writel_relaxed(0, rs->regs + ROCKCHIP_SPI_DMARDLR);
+	writel_relaxed(rockchip_spi_calc_burst_size(xfer->len / rs->n_bytes) - 1,
+		       rs->regs + ROCKCHIP_SPI_DMARDLR);
 	writel_relaxed(dmacr, rs->regs + ROCKCHIP_SPI_DMACR);
 
 	/* the hardware only supports an even clock divisor, so
diff --git a/drivers/spi/spi-rpc-if.c b/drivers/spi/spi-rpc-if.c
new file mode 100644
index 000000000000..ed3e548227f4
--- /dev/null
+++ b/drivers/spi/spi-rpc-if.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// RPC-IF SPI/QSPI/Octa driver
+//
+// Copyright (C) 2018 ~ 2019 Renesas Solutions Corp.
+// Copyright (C) 2019 Macronix International Co., Ltd.
+// Copyright (C) 2019 - 2020 Cogent Embedded, Inc.
+//
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+#include <memory/renesas-rpc-if.h>
+
+#include <asm/unaligned.h>
+
+static void rpcif_spi_mem_prepare(struct spi_device *spi_dev,
+				  const struct spi_mem_op *spi_op,
+				  u64 *offs, size_t *len)
+{
+	struct rpcif *rpc = spi_controller_get_devdata(spi_dev->controller);
+	struct rpcif_op rpc_op = { };
+
+	rpc_op.cmd.opcode = spi_op->cmd.opcode;
+	rpc_op.cmd.buswidth = spi_op->cmd.buswidth;
+
+	if (spi_op->addr.nbytes) {
+		rpc_op.addr.buswidth = spi_op->addr.buswidth;
+		rpc_op.addr.nbytes = spi_op->addr.nbytes;
+		rpc_op.addr.val = spi_op->addr.val;
+	}
+
+	if (spi_op->dummy.nbytes) {
+		rpc_op.dummy.buswidth = spi_op->dummy.buswidth;
+		rpc_op.dummy.ncycles  = spi_op->dummy.nbytes * 8 /
+					spi_op->dummy.buswidth;
+	}
+
+	if (spi_op->data.nbytes || (offs && len)) {
+		rpc_op.data.buswidth = spi_op->data.buswidth;
+		rpc_op.data.nbytes = spi_op->data.nbytes;
+		switch (spi_op->data.dir) {
+		case SPI_MEM_DATA_IN:
+			rpc_op.data.dir = RPCIF_DATA_IN;
+			rpc_op.data.buf.in = spi_op->data.buf.in;
+			break;
+		case SPI_MEM_DATA_OUT:
+			rpc_op.data.dir = RPCIF_DATA_OUT;
+			rpc_op.data.buf.out = spi_op->data.buf.out;
+			break;
+		case SPI_MEM_NO_DATA:
+			rpc_op.data.dir = RPCIF_NO_DATA;
+			break;
+		}
+	} else	{
+		rpc_op.data.dir = RPCIF_NO_DATA;
+	}
+
+	rpcif_prepare(rpc, &rpc_op, offs, len);
+}
+
+static bool rpcif_spi_mem_supports_op(struct spi_mem *mem,
+				      const struct spi_mem_op *op)
+{
+	if (!spi_mem_default_supports_op(mem, op))
+		return false;
+
+	if (op->data.buswidth > 4 || op->addr.buswidth > 4 ||
+	    op->dummy.buswidth > 4 || op->cmd.buswidth > 4 ||
+	    op->addr.nbytes > 4)
+		return false;
+
+	return true;
+}
+
+static ssize_t rpcif_spi_mem_dirmap_read(struct spi_mem_dirmap_desc *desc,
+					 u64 offs, size_t len, void *buf)
+{
+	struct rpcif *rpc =
+		spi_controller_get_devdata(desc->mem->spi->controller);
+
+	if (offs + desc->info.offset + len > U32_MAX)
+		return -EINVAL;
+
+	rpcif_spi_mem_prepare(desc->mem->spi, &desc->info.op_tmpl, &offs, &len);
+
+	return rpcif_dirmap_read(rpc, offs, len, buf);
+}
+
+static int rpcif_spi_mem_dirmap_create(struct spi_mem_dirmap_desc *desc)
+{
+	struct rpcif *rpc =
+		spi_controller_get_devdata(desc->mem->spi->controller);
+
+	if (desc->info.offset + desc->info.length > U32_MAX)
+		return -ENOTSUPP;
+
+	if (!rpcif_spi_mem_supports_op(desc->mem, &desc->info.op_tmpl))
+		return -ENOTSUPP;
+
+	if (!rpc->dirmap && desc->info.op_tmpl.data.dir == SPI_MEM_DATA_IN)
+		return -ENOTSUPP;
+
+	if (desc->info.op_tmpl.data.dir == SPI_MEM_DATA_OUT)
+		return -ENOTSUPP;
+
+	return 0;
+}
+
+static int rpcif_spi_mem_exec_op(struct spi_mem *mem,
+				 const struct spi_mem_op *op)
+{
+	struct rpcif *rpc =
+		spi_controller_get_devdata(mem->spi->controller);
+
+	rpcif_spi_mem_prepare(mem->spi, op, NULL, NULL);
+
+	return rpcif_manual_xfer(rpc);
+}
+
+static const struct spi_controller_mem_ops rpcif_spi_mem_ops = {
+	.supports_op	= rpcif_spi_mem_supports_op,
+	.exec_op	= rpcif_spi_mem_exec_op,
+	.dirmap_create	= rpcif_spi_mem_dirmap_create,
+	.dirmap_read	= rpcif_spi_mem_dirmap_read,
+};
+
+static int rpcif_spi_probe(struct platform_device *pdev)
+{
+	struct device *parent = pdev->dev.parent;
+	struct spi_controller *ctlr;
+	struct rpcif *rpc;
+	int error;
+
+	ctlr = spi_alloc_master(&pdev->dev, sizeof(*rpc));
+	if (!ctlr)
+		return -ENOMEM;
+
+	rpc = spi_controller_get_devdata(ctlr);
+	rpcif_sw_init(rpc, parent);
+
+	platform_set_drvdata(pdev, ctlr);
+
+	ctlr->dev.of_node = parent->of_node;
+
+	rpcif_enable_rpm(rpc);
+
+	ctlr->num_chipselect = 1;
+	ctlr->mem_ops = &rpcif_spi_mem_ops;
+
+	ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
+	ctlr->mode_bits = SPI_CPOL | SPI_CPHA | SPI_TX_QUAD | SPI_RX_QUAD;
+	ctlr->flags = SPI_CONTROLLER_HALF_DUPLEX;
+
+	rpcif_hw_init(rpc, false);
+
+	error = spi_register_controller(ctlr);
+	if (error) {
+		dev_err(&pdev->dev, "spi_register_controller failed\n");
+		goto err_put_ctlr;
+	}
+	return 0;
+
+err_put_ctlr:
+	rpcif_disable_rpm(rpc);
+	spi_controller_put(ctlr);
+
+	return error;
+}
+
+static int rpcif_spi_remove(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr = platform_get_drvdata(pdev);
+	struct rpcif *rpc = spi_controller_get_devdata(ctlr);
+
+	spi_unregister_controller(ctlr);
+	rpcif_disable_rpm(rpc);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int rpcif_spi_suspend(struct device *dev)
+{
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+
+	return spi_controller_suspend(ctlr);
+}
+
+static int rpcif_spi_resume(struct device *dev)
+{
+	struct spi_controller *ctlr = dev_get_drvdata(dev);
+
+	return spi_controller_resume(ctlr);
+}
+
+static SIMPLE_DEV_PM_OPS(rpcif_spi_pm_ops, rpcif_spi_suspend, rpcif_spi_resume);
+#define DEV_PM_OPS	(&rpcif_spi_pm_ops)
+#else
+#define DEV_PM_OPS	NULL
+#endif
+
+static struct platform_driver rpcif_spi_driver = {
+	.probe	= rpcif_spi_probe,
+	.remove	= rpcif_spi_remove,
+	.driver = {
+		.name	= "rpc-if-spi",
+		.pm	= DEV_PM_OPS,
+	},
+};
+module_platform_driver(rpcif_spi_driver);
+
+MODULE_DESCRIPTION("Renesas RPC-IF SPI driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index cf67ea60dc0e..924b24441789 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -130,9 +130,11 @@ struct s3c64xx_spi_dma_data {
  * @fifo_lvl_mask: Bit-mask for {TX|RX}_FIFO_LVL bits in SPI_STATUS register.
  * @rx_lvl_offset: Bit offset of RX_FIFO_LVL bits in SPI_STATUS regiter.
  * @tx_st_done: Bit offset of TX_DONE bit in SPI_STATUS regiter.
+ * @quirks: Bitmask of known quirks
  * @high_speed: True, if the controller supports HIGH_SPEED_EN bit.
  * @clk_from_cmu: True, if the controller does not include a clock mux and
  *	prescaler unit.
+ * @clk_ioclk: True if clock is present on this device
  *
  * The Samsung s3c64xx SPI controller are used on various Samsung SoC's but
  * differ in some aspects such as the size of the fifo and spi bus clock
@@ -154,6 +156,7 @@ struct s3c64xx_spi_port_config {
  * @clk: Pointer to the spi clock.
  * @src_clk: Pointer to the clock used to generate SPI signals.
  * @ioclk: Pointer to the i/o clock between master and slave
+ * @pdev: Pointer to device's platform device data
  * @master: Pointer to the SPI Protocol master.
  * @cntrlr_info: Platform specific data for the controller this driver manages.
  * @lock: Controller specific lock.
@@ -166,7 +169,11 @@ struct s3c64xx_spi_port_config {
  * @xfer_completion: To indicate completion of xfer task.
  * @cur_mode: Stores the active configuration of the controller.
  * @cur_bpw: Stores the active bits per word settings.
- * @cur_speed: Stores the active xfer clock speed.
+ * @cur_speed: Current clock speed
+ * @rx_dma: Local receive DMA data (e.g. chan and direction)
+ * @tx_dma: Local transmit DMA data (e.g. chan and direction)
+ * @port_conf: Local SPI port configuartion data
+ * @port_id: Port identification number
  */
 struct s3c64xx_spi_driver_data {
 	void __iomem                    *regs;
diff --git a/drivers/spi/spi-sun4i.c b/drivers/spi/spi-sun4i.c
index cbfac6596fad..1fdfc6e6691d 100644
--- a/drivers/spi/spi-sun4i.c
+++ b/drivers/spi/spi-sun4i.c
@@ -198,7 +198,7 @@ static void sun4i_spi_set_cs(struct spi_device *spi, bool enable)
 
 static size_t sun4i_spi_max_transfer_size(struct spi_device *spi)
 {
-	return SUN4I_FIFO_DEPTH - 1;
+	return SUN4I_MAX_XFER_SIZE - 1;
 }
 
 static int sun4i_spi_transfer_one(struct spi_master *master,
diff --git a/drivers/spi/spi-sun6i.c b/drivers/spi/spi-sun6i.c
index fa11cc0e809b..19238e1b76b4 100644
--- a/drivers/spi/spi-sun6i.c
+++ b/drivers/spi/spi-sun6i.c
@@ -7,6 +7,7 @@
  * Maxime Ripard <maxime.ripard@free-electrons.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -58,10 +59,8 @@
 #define SUN6I_FIFO_CTL_TF_RST			BIT(31)
 
 #define SUN6I_FIFO_STA_REG		0x1c
-#define SUN6I_FIFO_STA_RF_CNT_MASK		0x7f
-#define SUN6I_FIFO_STA_RF_CNT_BITS		0
-#define SUN6I_FIFO_STA_TF_CNT_MASK		0x7f
-#define SUN6I_FIFO_STA_TF_CNT_BITS		16
+#define SUN6I_FIFO_STA_RF_CNT_MASK		GENMASK(7, 0)
+#define SUN6I_FIFO_STA_TF_CNT_MASK		GENMASK(23, 16)
 
 #define SUN6I_CLK_CTL_REG		0x24
 #define SUN6I_CLK_CTL_CDR2_MASK			0xff
@@ -73,13 +72,10 @@
 #define SUN6I_MAX_XFER_SIZE		0xffffff
 
 #define SUN6I_BURST_CNT_REG		0x30
-#define SUN6I_BURST_CNT(cnt)			((cnt) & SUN6I_MAX_XFER_SIZE)
 
 #define SUN6I_XMIT_CNT_REG		0x34
-#define SUN6I_XMIT_CNT(cnt)			((cnt) & SUN6I_MAX_XFER_SIZE)
 
 #define SUN6I_BURST_CTL_CNT_REG		0x38
-#define SUN6I_BURST_CTL_CNT_STC(cnt)		((cnt) & SUN6I_MAX_XFER_SIZE)
 
 #define SUN6I_TXDATA_REG		0x200
 #define SUN6I_RXDATA_REG		0x300
@@ -109,21 +105,18 @@ static inline void sun6i_spi_write(struct sun6i_spi *sspi, u32 reg, u32 value)
 	writel(value, sspi->base_addr + reg);
 }
 
-static inline u32 sun6i_spi_get_tx_fifo_count(struct sun6i_spi *sspi)
+static inline u32 sun6i_spi_get_rx_fifo_count(struct sun6i_spi *sspi)
 {
 	u32 reg = sun6i_spi_read(sspi, SUN6I_FIFO_STA_REG);
 
-	reg >>= SUN6I_FIFO_STA_TF_CNT_BITS;
-
-	return reg & SUN6I_FIFO_STA_TF_CNT_MASK;
+	return FIELD_GET(SUN6I_FIFO_STA_RF_CNT_MASK, reg);
 }
 
-static inline void sun6i_spi_enable_interrupt(struct sun6i_spi *sspi, u32 mask)
+static inline u32 sun6i_spi_get_tx_fifo_count(struct sun6i_spi *sspi)
 {
-	u32 reg = sun6i_spi_read(sspi, SUN6I_INT_CTL_REG);
+	u32 reg = sun6i_spi_read(sspi, SUN6I_FIFO_STA_REG);
 
-	reg |= mask;
-	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, reg);
+	return FIELD_GET(SUN6I_FIFO_STA_TF_CNT_MASK, reg);
 }
 
 static inline void sun6i_spi_disable_interrupt(struct sun6i_spi *sspi, u32 mask)
@@ -134,18 +127,13 @@ static inline void sun6i_spi_disable_interrupt(struct sun6i_spi *sspi, u32 mask)
 	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, reg);
 }
 
-static inline void sun6i_spi_drain_fifo(struct sun6i_spi *sspi, int len)
+static inline void sun6i_spi_drain_fifo(struct sun6i_spi *sspi)
 {
-	u32 reg, cnt;
+	u32 len;
 	u8 byte;
 
 	/* See how much data is available */
-	reg = sun6i_spi_read(sspi, SUN6I_FIFO_STA_REG);
-	reg &= SUN6I_FIFO_STA_RF_CNT_MASK;
-	cnt = reg >> SUN6I_FIFO_STA_RF_CNT_BITS;
-
-	if (len > cnt)
-		len = cnt;
+	len = sun6i_spi_get_rx_fifo_count(sspi);
 
 	while (len--) {
 		byte = readb(sspi->base_addr + SUN6I_RXDATA_REG);
@@ -154,15 +142,16 @@ static inline void sun6i_spi_drain_fifo(struct sun6i_spi *sspi, int len)
 	}
 }
 
-static inline void sun6i_spi_fill_fifo(struct sun6i_spi *sspi, int len)
+static inline void sun6i_spi_fill_fifo(struct sun6i_spi *sspi)
 {
 	u32 cnt;
+	int len;
 	u8 byte;
 
 	/* See how much data we can fit */
 	cnt = sspi->fifo_depth - sun6i_spi_get_tx_fifo_count(sspi);
 
-	len = min3(len, (int)cnt, sspi->len);
+	len = min((int)cnt, sspi->len);
 
 	while (len--) {
 		byte = sspi->tx_buf ? *sspi->tx_buf++ : 0;
@@ -201,7 +190,7 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	unsigned int mclk_rate, div, div_cdr1, div_cdr2, timeout;
 	unsigned int start, end, tx_time;
 	unsigned int trig_level;
-	unsigned int tx_len = 0;
+	unsigned int tx_len = 0, rx_len = 0;
 	int ret = 0;
 	u32 reg;
 
@@ -256,10 +245,12 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	 * If it's a TX only transfer, we don't want to fill the RX
 	 * FIFO with bogus data
 	 */
-	if (sspi->rx_buf)
+	if (sspi->rx_buf) {
 		reg &= ~SUN6I_TFR_CTL_DHB;
-	else
+		rx_len = tfr->len;
+	} else {
 		reg |= SUN6I_TFR_CTL_DHB;
+	}
 
 	/* We want to control the chip select manually */
 	reg |= SUN6I_TFR_CTL_CS_MANUAL;
@@ -291,9 +282,11 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 	div_cdr2 = DIV_ROUND_UP(div_cdr1, 2);
 	if (div_cdr2 <= (SUN6I_CLK_CTL_CDR2_MASK + 1)) {
 		reg = SUN6I_CLK_CTL_CDR2(div_cdr2 - 1) | SUN6I_CLK_CTL_DRS;
+		tfr->effective_speed_hz = mclk_rate / (2 * div_cdr2);
 	} else {
 		div = min(SUN6I_CLK_CTL_CDR1_MASK, order_base_2(div_cdr1));
 		reg = SUN6I_CLK_CTL_CDR1(div);
+		tfr->effective_speed_hz = mclk_rate / (1 << div);
 	}
 
 	sun6i_spi_write(sspi, SUN6I_CLK_CTL_REG, reg);
@@ -303,20 +296,22 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 		tx_len = tfr->len;
 
 	/* Setup the counters */
-	sun6i_spi_write(sspi, SUN6I_BURST_CNT_REG, SUN6I_BURST_CNT(tfr->len));
-	sun6i_spi_write(sspi, SUN6I_XMIT_CNT_REG, SUN6I_XMIT_CNT(tx_len));
-	sun6i_spi_write(sspi, SUN6I_BURST_CTL_CNT_REG,
-			SUN6I_BURST_CTL_CNT_STC(tx_len));
+	sun6i_spi_write(sspi, SUN6I_BURST_CNT_REG, tfr->len);
+	sun6i_spi_write(sspi, SUN6I_XMIT_CNT_REG, tx_len);
+	sun6i_spi_write(sspi, SUN6I_BURST_CTL_CNT_REG, tx_len);
 
 	/* Fill the TX FIFO */
-	sun6i_spi_fill_fifo(sspi, sspi->fifo_depth);
+	sun6i_spi_fill_fifo(sspi);
 
 	/* Enable the interrupts */
-	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, SUN6I_INT_CTL_TC);
-	sun6i_spi_enable_interrupt(sspi, SUN6I_INT_CTL_TC |
-					 SUN6I_INT_CTL_RF_RDY);
+	reg = SUN6I_INT_CTL_TC;
+
+	if (rx_len > sspi->fifo_depth)
+		reg |= SUN6I_INT_CTL_RF_RDY;
 	if (tx_len > sspi->fifo_depth)
-		sun6i_spi_enable_interrupt(sspi, SUN6I_INT_CTL_TF_ERQ);
+		reg |= SUN6I_INT_CTL_TF_ERQ;
+
+	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, reg);
 
 	/* Start the transfer */
 	reg = sun6i_spi_read(sspi, SUN6I_TFR_CTL_REG);
@@ -333,10 +328,8 @@ static int sun6i_spi_transfer_one(struct spi_master *master,
 			 dev_name(&spi->dev), tfr->len, tfr->speed_hz,
 			 jiffies_to_msecs(end - start), tx_time);
 		ret = -ETIMEDOUT;
-		goto out;
 	}
 
-out:
 	sun6i_spi_write(sspi, SUN6I_INT_CTL_REG, 0);
 
 	return ret;
@@ -350,14 +343,14 @@ static irqreturn_t sun6i_spi_handler(int irq, void *dev_id)
 	/* Transfer complete */
 	if (status & SUN6I_INT_CTL_TC) {
 		sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_TC);
-		sun6i_spi_drain_fifo(sspi, sspi->fifo_depth);
+		sun6i_spi_drain_fifo(sspi);
 		complete(&sspi->done);
 		return IRQ_HANDLED;
 	}
 
 	/* Receive FIFO 3/4 full */
 	if (status & SUN6I_INT_CTL_RF_RDY) {
-		sun6i_spi_drain_fifo(sspi, SUN6I_FIFO_DEPTH);
+		sun6i_spi_drain_fifo(sspi);
 		/* Only clear the interrupt _after_ draining the FIFO */
 		sun6i_spi_write(sspi, SUN6I_INT_STA_REG, SUN6I_INT_CTL_RF_RDY);
 		return IRQ_HANDLED;
@@ -365,7 +358,7 @@ static irqreturn_t sun6i_spi_handler(int irq, void *dev_id)
 
 	/* Transmit FIFO 3/4 empty */
 	if (status & SUN6I_INT_CTL_TF_ERQ) {
-		sun6i_spi_fill_fifo(sspi, SUN6I_FIFO_DEPTH);
+		sun6i_spi_fill_fifo(sspi);
 
 		if (!sspi->len)
 			/* nothing left to transmit */
diff --git a/drivers/spi/spi-ti-qspi.c b/drivers/spi/spi-ti-qspi.c
index 366a3e5cca6b..3c41649698a5 100644
--- a/drivers/spi/spi-ti-qspi.c
+++ b/drivers/spi/spi-ti-qspi.c
@@ -2,7 +2,7 @@
 /*
  * TI QSPI driver
  *
- * Copyright (C) 2013 Texas Instruments Incorporated - http://www.ti.com
+ * Copyright (C) 2013 Texas Instruments Incorporated - https://www.ti.com
  * Author: Sourav Poddar <sourav.poddar@ti.com>
  */
 
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index d7ea6af74743..6df2aeff2843 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -122,6 +122,7 @@ struct pch_spi_dma_ctrl {
 /**
  * struct pch_spi_data - Holds the SPI channel specific details
  * @io_remap_addr:		The remapped PCI base address
+ * @io_base_addr:		Base address
  * @master:			Pointer to the SPI master structure
  * @work:			Reference to work queue handler
  * @wait:			Wait queue for waking up upon receiving an
@@ -138,8 +139,8 @@ struct pch_spi_dma_ctrl {
  *				transfer
  * @rx_index:			Receive data count; for bookkeeping during
  *				transfer
- * @tx_buff:			Buffer for data to be transmitted
- * @rx_index:			Buffer for Received data
+ * @pkt_tx_buff:		Buffer for data to be transmitted
+ * @pkt_rx_buff:		Buffer for received data
  * @n_curnt_chip:		The chip number that this SPI driver currently
  *				operates on
  * @current_chip:		Reference to the current chip that this SPI
@@ -151,7 +152,10 @@ struct pch_spi_dma_ctrl {
  * @board_dat:			Reference to the SPI device data structure
  * @plat_dev:			platform_device structure
  * @ch:				SPI channel number
+ * @dma:			Local DMA information
+ * @use_dma:			True if DMA is to be used
  * @irq_reg_sts:		Status of IRQ registration
+ * @save_total_len:		Save length while data is being transferred
  */
 struct pch_spi_data {
 	void __iomem *io_remap_addr;
@@ -1631,64 +1635,37 @@ static void pch_spi_remove(struct pci_dev *pdev)
 	kfree(pd_dev_save);
 }
 
-#ifdef CONFIG_PM
-static int pch_spi_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused pch_spi_suspend(struct device *dev)
 {
-	int retval;
-	struct pch_pd_dev_save *pd_dev_save = pci_get_drvdata(pdev);
+	struct pch_pd_dev_save *pd_dev_save = dev_get_drvdata(dev);
 
-	dev_dbg(&pdev->dev, "%s ENTRY\n", __func__);
+	dev_dbg(dev, "%s ENTRY\n", __func__);
 
 	pd_dev_save->board_dat->suspend_sts = true;
 
-	/* save config space */
-	retval = pci_save_state(pdev);
-	if (retval == 0) {
-		pci_enable_wake(pdev, PCI_D3hot, 0);
-		pci_disable_device(pdev);
-		pci_set_power_state(pdev, PCI_D3hot);
-	} else {
-		dev_err(&pdev->dev, "%s pci_save_state failed\n", __func__);
-	}
-
-	return retval;
+	return 0;
 }
 
-static int pch_spi_resume(struct pci_dev *pdev)
+static int __maybe_unused pch_spi_resume(struct device *dev)
 {
-	int retval;
-	struct pch_pd_dev_save *pd_dev_save = pci_get_drvdata(pdev);
-	dev_dbg(&pdev->dev, "%s ENTRY\n", __func__);
+	struct pch_pd_dev_save *pd_dev_save = dev_get_drvdata(dev);
 
-	pci_set_power_state(pdev, PCI_D0);
-	pci_restore_state(pdev);
+	dev_dbg(dev, "%s ENTRY\n", __func__);
 
-	retval = pci_enable_device(pdev);
-	if (retval < 0) {
-		dev_err(&pdev->dev,
-			"%s pci_enable_device failed\n", __func__);
-	} else {
-		pci_enable_wake(pdev, PCI_D3hot, 0);
-
-		/* set suspend status to false */
-		pd_dev_save->board_dat->suspend_sts = false;
-	}
+	/* set suspend status to false */
+	pd_dev_save->board_dat->suspend_sts = false;
 
-	return retval;
+	return 0;
 }
-#else
-#define pch_spi_suspend NULL
-#define pch_spi_resume NULL
 
-#endif
+static SIMPLE_DEV_PM_OPS(pch_spi_pm_ops, pch_spi_suspend, pch_spi_resume);
 
 static struct pci_driver pch_spi_pcidev_driver = {
 	.name = "pch_spi",
 	.id_table = pch_spi_pcidev_id,
 	.probe = pch_spi_probe,
 	.remove = pch_spi_remove,
-	.suspend = pch_spi_suspend,
-	.resume = pch_spi_resume,
+	.driver.pm = &pch_spi_pm_ops,
 };
 
 static int __init pch_spi_init(void)
diff --git a/drivers/spi/spi-zynq-qspi.c b/drivers/spi/spi-zynq-qspi.c
index 17641157354d..5d8a5ee62fa2 100644
--- a/drivers/spi/spi-zynq-qspi.c
+++ b/drivers/spi/spi-zynq-qspi.c
@@ -119,6 +119,7 @@
 
 /**
  * struct zynq_qspi - Defines qspi driver instance
+ * @dev:		Pointer to the this device's information
  * @regs:		Virtual address of the QSPI controller registers
  * @refclk:		Pointer to the peripheral clock
  * @pclk:		Pointer to the APB clock
@@ -316,7 +317,7 @@ static void zynq_qspi_chipselect(struct spi_device *spi, bool assert)
 /**
  * zynq_qspi_config_op - Configure QSPI controller for specified transfer
  * @xqspi:	Pointer to the zynq_qspi structure
- * @qspi:	Pointer to the spi_device structure
+ * @spi:	Pointer to the spi_device structure
  *
  * Sets the operational mode of QSPI controller for the next QSPI transfer and
  * sets the requested clock frequency.
@@ -527,20 +528,21 @@ static int zynq_qspi_exec_mem_op(struct spi_mem *mem,
 	struct zynq_qspi *xqspi = spi_controller_get_devdata(mem->spi->master);
 	int err = 0, i;
 	u8 *tmpbuf;
+	u8 opcode = op->cmd.opcode;
 
 	dev_dbg(xqspi->dev, "cmd:%#x mode:%d.%d.%d.%d\n",
-		op->cmd.opcode, op->cmd.buswidth, op->addr.buswidth,
+		opcode, op->cmd.buswidth, op->addr.buswidth,
 		op->dummy.buswidth, op->data.buswidth);
 
 	zynq_qspi_chipselect(mem->spi, true);
 	zynq_qspi_config_op(xqspi, mem->spi);
 
-	if (op->cmd.opcode) {
+	if (op->cmd.nbytes) {
 		reinit_completion(&xqspi->data_completion);
-		xqspi->txbuf = (u8 *)&op->cmd.opcode;
+		xqspi->txbuf = &opcode;
 		xqspi->rxbuf = NULL;
-		xqspi->tx_bytes = sizeof(op->cmd.opcode);
-		xqspi->rx_bytes = sizeof(op->cmd.opcode);
+		xqspi->tx_bytes = op->cmd.nbytes;
+		xqspi->rx_bytes = op->cmd.nbytes;
 		zynq_qspi_write_op(xqspi, ZYNQ_QSPI_FIFO_DEPTH, true);
 		zynq_qspi_write(xqspi, ZYNQ_QSPI_IEN_OFFSET,
 				ZYNQ_QSPI_IXR_RXTX_MASK);
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 811c97a7c858..e17a20125255 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -197,8 +197,8 @@ static inline void zynqmp_gqspi_write(struct zynqmp_qspi *xqspi, u32 offset,
 /**
  * zynqmp_gqspi_selectslave:	For selection of slave device
  * @instanceptr:	Pointer to the zynqmp_qspi structure
- * @flashcs:	For chip select
- * @flashbus:	To check which bus is selected- upper or lower
+ * @slavecs:	For chip select
+ * @slavebus:	To check which bus is selected- upper or lower
  */
 static void zynqmp_gqspi_selectslave(struct zynqmp_qspi *instanceptr,
 				     u8 slavecs, u8 slavebus)
@@ -892,7 +892,7 @@ static int zynqmp_qspi_start_transfer(struct spi_master *master,
 
 /**
  * zynqmp_qspi_suspend:	Suspend method for the QSPI driver
- * @_dev:	Address of the platform_device structure
+ * @dev:	Address of the platform_device structure
  *
  * This function stops the QSPI driver queue and disables the QSPI controller
  *
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 8158e281f354..0b260484b4f5 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -778,6 +778,17 @@ static void spi_set_cs(struct spi_device *spi, bool enable)
 {
 	bool enable1 = enable;
 
+	/*
+	 * Avoid calling into the driver (or doing delays) if the chip select
+	 * isn't actually changing from the last time this was called.
+	 */
+	if ((spi->controller->last_cs_enable == enable) &&
+	    (spi->controller->last_cs_mode_high == (spi->mode & SPI_CS_HIGH)))
+		return;
+
+	spi->controller->last_cs_enable = enable;
+	spi->controller->last_cs_mode_high = spi->mode & SPI_CS_HIGH;
+
 	if (!spi->controller->set_cs_timing) {
 		if (enable1)
 			spi_delay_exec(&spi->controller->cs_setup, NULL);
@@ -982,6 +993,8 @@ static int __spi_unmap_msg(struct spi_controller *ctlr, struct spi_message *msg)
 		spi_unmap_buf(ctlr, tx_dev, &xfer->tx_sg, DMA_TO_DEVICE);
 	}
 
+	ctlr->cur_msg_mapped = false;
+
 	return 0;
 }
 #else /* !CONFIG_HAS_DMA */
@@ -1234,8 +1247,17 @@ static int spi_transfer_one_message(struct spi_controller *ctlr,
 		if (xfer->tx_buf || xfer->rx_buf) {
 			reinit_completion(&ctlr->xfer_completion);
 
+fallback_pio:
 			ret = ctlr->transfer_one(ctlr, msg->spi, xfer);
 			if (ret < 0) {
+				if (ctlr->cur_msg_mapped &&
+				   (xfer->error & SPI_TRANS_FAIL_NO_START)) {
+					__spi_unmap_msg(ctlr, msg);
+					ctlr->fallback = true;
+					xfer->error &= ~SPI_TRANS_FAIL_NO_START;
+					goto fallback_pio;
+				}
+
 				SPI_STATISTICS_INCREMENT_FIELD(statm,
 							       errors);
 				SPI_STATISTICS_INCREMENT_FIELD(stats,
@@ -1314,6 +1336,14 @@ void spi_finalize_current_transfer(struct spi_controller *ctlr)
 }
 EXPORT_SYMBOL_GPL(spi_finalize_current_transfer);
 
+static void spi_idle_runtime_pm(struct spi_controller *ctlr)
+{
+	if (ctlr->auto_runtime_pm) {
+		pm_runtime_mark_last_busy(ctlr->dev.parent);
+		pm_runtime_put_autosuspend(ctlr->dev.parent);
+	}
+}
+
 /**
  * __spi_pump_messages - function which processes spi message queue
  * @ctlr: controller to process queue for
@@ -1346,7 +1376,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 
 	/* If another context is idling the device then defer */
 	if (ctlr->idling) {
-		kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+		kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 		spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 		return;
 	}
@@ -1358,10 +1388,17 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 			return;
 		}
 
-		/* Only do teardown in the thread */
+		/* Defer any non-atomic teardown to the thread */
 		if (!in_kthread) {
-			kthread_queue_work(&ctlr->kworker,
-					   &ctlr->pump_messages);
+			if (!ctlr->dummy_rx && !ctlr->dummy_tx &&
+			    !ctlr->unprepare_transfer_hardware) {
+				spi_idle_runtime_pm(ctlr);
+				ctlr->busy = false;
+				trace_spi_controller_idle(ctlr);
+			} else {
+				kthread_queue_work(ctlr->kworker,
+						   &ctlr->pump_messages);
+			}
 			spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 			return;
 		}
@@ -1378,10 +1415,7 @@ static void __spi_pump_messages(struct spi_controller *ctlr, bool in_kthread)
 		    ctlr->unprepare_transfer_hardware(ctlr))
 			dev_err(&ctlr->dev,
 				"failed to unprepare transfer hardware\n");
-		if (ctlr->auto_runtime_pm) {
-			pm_runtime_mark_last_busy(ctlr->dev.parent);
-			pm_runtime_put_autosuspend(ctlr->dev.parent);
-		}
+		spi_idle_runtime_pm(ctlr);
 		trace_spi_controller_idle(ctlr);
 
 		spin_lock_irqsave(&ctlr->queue_lock, flags);
@@ -1596,7 +1630,7 @@ static void spi_set_thread_rt(struct spi_controller *ctlr)
 
 	dev_info(&ctlr->dev,
 		"will run message pump with realtime priority\n");
-	sched_setscheduler(ctlr->kworker_task, SCHED_FIFO, &param);
+	sched_setscheduler(ctlr->kworker->task, SCHED_FIFO, &param);
 }
 
 static int spi_init_queue(struct spi_controller *ctlr)
@@ -1604,13 +1638,12 @@ static int spi_init_queue(struct spi_controller *ctlr)
 	ctlr->running = false;
 	ctlr->busy = false;
 
-	kthread_init_worker(&ctlr->kworker);
-	ctlr->kworker_task = kthread_run(kthread_worker_fn, &ctlr->kworker,
-					 "%s", dev_name(&ctlr->dev));
-	if (IS_ERR(ctlr->kworker_task)) {
-		dev_err(&ctlr->dev, "failed to create message pump task\n");
-		return PTR_ERR(ctlr->kworker_task);
+	ctlr->kworker = kthread_create_worker(0, dev_name(&ctlr->dev));
+	if (IS_ERR(ctlr->kworker)) {
+		dev_err(&ctlr->dev, "failed to create message pump kworker\n");
+		return PTR_ERR(ctlr->kworker);
 	}
+
 	kthread_init_work(&ctlr->pump_messages, spi_pump_messages);
 
 	/*
@@ -1693,7 +1726,8 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 	spin_lock_irqsave(&ctlr->queue_lock, flags);
 	ctlr->cur_msg = NULL;
 	ctlr->cur_msg_prepared = false;
-	kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+	ctlr->fallback = false;
+	kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 
 	trace_spi_message_done(mesg);
@@ -1719,7 +1753,7 @@ static int spi_start_queue(struct spi_controller *ctlr)
 	ctlr->cur_msg = NULL;
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 
-	kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+	kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 
 	return 0;
 }
@@ -1775,8 +1809,7 @@ static int spi_destroy_queue(struct spi_controller *ctlr)
 		return ret;
 	}
 
-	kthread_flush_worker(&ctlr->kworker);
-	kthread_stop(ctlr->kworker_task);
+	kthread_destroy_worker(ctlr->kworker);
 
 	return 0;
 }
@@ -1799,7 +1832,7 @@ static int __spi_queued_transfer(struct spi_device *spi,
 
 	list_add_tail(&msg->queue, &ctlr->queue);
 	if (!ctlr->busy && need_pump)
-		kthread_queue_work(&ctlr->kworker, &ctlr->pump_messages);
+		kthread_queue_work(ctlr->kworker, &ctlr->pump_messages);
 
 	spin_unlock_irqrestore(&ctlr->queue_lock, flags);
 	return 0;
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 59e07675ef86..455e99c4958e 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -224,6 +224,11 @@ static int spidev_message(struct spidev_data *spidev,
 	for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers;
 			n;
 			n--, k_tmp++, u_tmp++) {
+		/* Ensure that also following allocations from rx_buf/tx_buf will meet
+		 * DMA alignment requirements.
+		 */
+		unsigned int len_aligned = ALIGN(u_tmp->len, ARCH_KMALLOC_MINALIGN);
+
 		k_tmp->len = u_tmp->len;
 
 		total += k_tmp->len;
@@ -239,17 +244,17 @@ static int spidev_message(struct spidev_data *spidev,
 
 		if (u_tmp->rx_buf) {
 			/* this transfer needs space in RX bounce buffer */
-			rx_total += k_tmp->len;
+			rx_total += len_aligned;
 			if (rx_total > bufsiz) {
 				status = -EMSGSIZE;
 				goto done;
 			}
 			k_tmp->rx_buf = rx_buf;
-			rx_buf += k_tmp->len;
+			rx_buf += len_aligned;
 		}
 		if (u_tmp->tx_buf) {
 			/* this transfer needs space in TX bounce buffer */
-			tx_total += k_tmp->len;
+			tx_total += len_aligned;
 			if (tx_total > bufsiz) {
 				status = -EMSGSIZE;
 				goto done;
@@ -259,7 +264,7 @@ static int spidev_message(struct spidev_data *spidev,
 						(uintptr_t) u_tmp->tx_buf,
 					u_tmp->len))
 				goto done;
-			tx_buf += k_tmp->len;
+			tx_buf += len_aligned;
 		}
 
 		k_tmp->cs_change = !!u_tmp->cs_change;
@@ -293,16 +298,16 @@ static int spidev_message(struct spidev_data *spidev,
 		goto done;
 
 	/* copy any rx data out of bounce buffer */
-	rx_buf = spidev->rx_buffer;
-	for (n = n_xfers, u_tmp = u_xfers; n; n--, u_tmp++) {
+	for (n = n_xfers, k_tmp = k_xfers, u_tmp = u_xfers;
+			n;
+			n--, k_tmp++, u_tmp++) {
 		if (u_tmp->rx_buf) {
 			if (copy_to_user((u8 __user *)
-					(uintptr_t) u_tmp->rx_buf, rx_buf,
+					(uintptr_t) u_tmp->rx_buf, k_tmp->rx_buf,
 					u_tmp->len)) {
 				status = -EFAULT;
 				goto done;
 			}
-			rx_buf += u_tmp->len;
 		}
 	}
 	status = total;