Merge branch 'spi-5.7' into spi-next

24 files changed, 2968 insertions, 574 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index d6ed0c355954..efce98e9844e 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -62,6 +62,13 @@ config SPI_ALTERA
 	help
 	  This is the driver for the Altera SPI Controller.
 
+config SPI_AR934X
+	tristate "Qualcomm Atheros AR934X/QCA95XX SPI controller driver"
+	depends on ATH79 || COMPILE_TEST
+	help
+	  This enables support for the SPI controller present on the
+	  Qualcomm Atheros AR934X/QCA95XX SoCs.
+
 config SPI_ATH79
 	tristate "Atheros AR71XX/AR724X/AR913X SPI controller driver"
 	depends on ATH79 || COMPILE_TEST
@@ -264,6 +271,13 @@ config SPI_FALCON
 	  has only been tested with m25p80 type chips. The hardware has no
 	  support for other types of SPI peripherals.
 
+config SPI_FSI
+	tristate "FSI SPI driver"
+	depends on FSI
+	help
+	  This enables support for the driver for FSI bus attached SPI
+	  controllers.
+
 config SPI_FSL_LPSPI
 	tristate "Freescale i.MX LPSPI controller"
 	depends on ARCH_MXC || COMPILE_TEST
@@ -285,7 +299,6 @@ config SPI_HISI_SFC_V3XX
 	tristate "HiSilicon SPI-NOR Flash Controller for Hi16XX chipsets"
 	depends on (ARM64 && ACPI) || COMPILE_TEST
 	depends on HAS_IOMEM
-	select CONFIG_MTD_SPI_NOR
 	help
 	  This enables support for HiSilicon v3xx SPI-NOR flash controller
 	  found in hi16xx chipsets.
@@ -415,6 +428,7 @@ config SPI_FSL_ESPI
 
 config SPI_MESON_SPICC
 	tristate "Amlogic Meson SPICC controller"
+	depends on COMMON_CLK
 	depends on ARCH_MESON || COMPILE_TEST
 	help
 	  This enables master mode support for the SPICC (SPI communication
@@ -443,6 +457,16 @@ config SPI_MT7621
 	help
 	  This selects a driver for the MediaTek MT7621 SPI Controller.
 
+config SPI_MTK_NOR
+	tristate "MediaTek SPI NOR controller"
+	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.
+	  It can perform generic SPI transfers up to 6 bytes via generic
+	  SPI interface as well as several SPI-NOR specific instructions
+	  via SPI MEM interface.
+
 config SPI_NPCM_FIU
 	tristate "Nuvoton NPCM FLASH Interface Unit"
 	depends on ARCH_NPCM || COMPILE_TEST
@@ -890,6 +914,17 @@ config SPI_ZYNQMP_GQSPI
 # Add new SPI master controllers in alphabetical order above this line
 #
 
+comment "SPI Multiplexer support"
+
+config SPI_MUX
+	tristate "SPI multiplexer support"
+	select MULTIPLEXER
+	help
+	  This adds support for SPI multiplexers. Each SPI mux will be
+	  accessible as a SPI controller, the devices behind the mux will appear
+	  to be chip selects on this controller. It is still necessary to
+	  select one or more specific mux-controller drivers.
+
 #
 # There are lots of SPI device types, with sensors and memory
 # being probably the most widely used ones.
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 9b65ec5afc5e..28f601327f8c 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -9,11 +9,13 @@ ccflags-$(CONFIG_SPI_DEBUG) := -DDEBUG
 # config declarations into driver model code
 obj-$(CONFIG_SPI_MASTER)		+= spi.o
 obj-$(CONFIG_SPI_MEM)			+= spi-mem.o
+obj-$(CONFIG_SPI_MUX)			+= spi-mux.o
 obj-$(CONFIG_SPI_SPIDEV)		+= spidev.o
 obj-$(CONFIG_SPI_LOOPBACK_TEST)		+= spi-loopback-test.o
 
 # SPI master controller drivers (bus)
 obj-$(CONFIG_SPI_ALTERA)		+= spi-altera.o
+obj-$(CONFIG_SPI_AR934X)		+= spi-ar934x.o
 obj-$(CONFIG_SPI_ARMADA_3700)		+= spi-armada-3700.o
 obj-$(CONFIG_SPI_ATMEL)			+= spi-atmel.o
 obj-$(CONFIG_SPI_ATMEL_QUADSPI)		+= atmel-quadspi.o
@@ -40,6 +42,7 @@ spi-dw-midpci-objs			:= spi-dw-pci.o spi-dw-mid.o
 obj-$(CONFIG_SPI_EFM32)			+= spi-efm32.o
 obj-$(CONFIG_SPI_EP93XX)		+= spi-ep93xx.o
 obj-$(CONFIG_SPI_FALCON)		+= spi-falcon.o
+obj-$(CONFIG_SPI_FSI)			+= spi-fsi.o
 obj-$(CONFIG_SPI_FSL_CPM)		+= spi-fsl-cpm.o
 obj-$(CONFIG_SPI_FSL_DSPI)		+= spi-fsl-dspi.o
 obj-$(CONFIG_SPI_FSL_LIB)		+= spi-fsl-lib.o
@@ -62,6 +65,7 @@ obj-$(CONFIG_SPI_MPC52xx_PSC)		+= spi-mpc52xx-psc.o
 obj-$(CONFIG_SPI_MPC52xx)		+= spi-mpc52xx.o
 obj-$(CONFIG_SPI_MT65XX)                += spi-mt65xx.o
 obj-$(CONFIG_SPI_MT7621)		+= spi-mt7621.o
+obj-$(CONFIG_SPI_MTK_NOR)		+= spi-mtk-nor.o
 obj-$(CONFIG_SPI_MXIC)			+= spi-mxic.o
 obj-$(CONFIG_SPI_MXS)			+= spi-mxs.o
 obj-$(CONFIG_SPI_NPCM_FIU)		+= spi-npcm-fiu.o
diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index 13def7f78b9e..cb44d1e169aa 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -173,6 +173,81 @@ static const struct atmel_qspi_mode atmel_qspi_modes[] = {
 	{ 4, 4, 4, QSPI_IFR_WIDTH_QUAD_CMD },
 };
 
+#ifdef VERBOSE_DEBUG
+static const char *atmel_qspi_reg_name(u32 offset, char *tmp, size_t sz)
+{
+	switch (offset) {
+	case QSPI_CR:
+		return "CR";
+	case QSPI_MR:
+		return "MR";
+	case QSPI_RD:
+		return "MR";
+	case QSPI_TD:
+		return "TD";
+	case QSPI_SR:
+		return "SR";
+	case QSPI_IER:
+		return "IER";
+	case QSPI_IDR:
+		return "IDR";
+	case QSPI_IMR:
+		return "IMR";
+	case QSPI_SCR:
+		return "SCR";
+	case QSPI_IAR:
+		return "IAR";
+	case QSPI_ICR:
+		return "ICR/WICR";
+	case QSPI_IFR:
+		return "IFR";
+	case QSPI_RICR:
+		return "RICR";
+	case QSPI_SMR:
+		return "SMR";
+	case QSPI_SKR:
+		return "SKR";
+	case QSPI_WPMR:
+		return "WPMR";
+	case QSPI_WPSR:
+		return "WPSR";
+	case QSPI_VERSION:
+		return "VERSION";
+	default:
+		snprintf(tmp, sz, "0x%02x", offset);
+		break;
+	}
+
+	return tmp;
+}
+#endif /* VERBOSE_DEBUG */
+
+static u32 atmel_qspi_read(struct atmel_qspi *aq, u32 offset)
+{
+	u32 value = readl_relaxed(aq->regs + offset);
+
+#ifdef VERBOSE_DEBUG
+	char tmp[8];
+
+	dev_vdbg(&aq->pdev->dev, "read 0x%08x from %s\n", value,
+		 atmel_qspi_reg_name(offset, tmp, sizeof(tmp)));
+#endif /* VERBOSE_DEBUG */
+
+	return value;
+}
+
+static void atmel_qspi_write(u32 value, struct atmel_qspi *aq, u32 offset)
+{
+#ifdef VERBOSE_DEBUG
+	char tmp[8];
+
+	dev_vdbg(&aq->pdev->dev, "write 0x%08x into %s\n", value,
+		 atmel_qspi_reg_name(offset, tmp, sizeof(tmp)));
+#endif /* VERBOSE_DEBUG */
+
+	writel_relaxed(value, aq->regs + offset);
+}
+
 static inline bool atmel_qspi_is_compatible(const struct spi_mem_op *op,
 					    const struct atmel_qspi_mode *mode)
 {
@@ -293,32 +368,32 @@ static int atmel_qspi_set_cfg(struct atmel_qspi *aq,
 	 * Serial Memory Mode (SMM).
 	 */
 	if (aq->mr != QSPI_MR_SMM) {
-		writel_relaxed(QSPI_MR_SMM, aq->regs + QSPI_MR);
+		atmel_qspi_write(QSPI_MR_SMM, aq, QSPI_MR);
 		aq->mr = QSPI_MR_SMM;
 	}
 
 	/* Clear pending interrupts */
-	(void)readl_relaxed(aq->regs + QSPI_SR);
+	(void)atmel_qspi_read(aq, QSPI_SR);
 
 	if (aq->caps->has_ricr) {
 		if (!op->addr.nbytes && op->data.dir == SPI_MEM_DATA_IN)
 			ifr |= QSPI_IFR_APBTFRTYP_READ;
 
 		/* Set QSPI Instruction Frame registers */
-		writel_relaxed(iar, aq->regs + QSPI_IAR);
+		atmel_qspi_write(iar, aq, QSPI_IAR);
 		if (op->data.dir == SPI_MEM_DATA_IN)
-			writel_relaxed(icr, aq->regs + QSPI_RICR);
+			atmel_qspi_write(icr, aq, QSPI_RICR);
 		else
-			writel_relaxed(icr, aq->regs + QSPI_WICR);
-		writel_relaxed(ifr, aq->regs + QSPI_IFR);
+			atmel_qspi_write(icr, aq, QSPI_WICR);
+		atmel_qspi_write(ifr, aq, QSPI_IFR);
 	} else {
 		if (op->data.dir == SPI_MEM_DATA_OUT)
 			ifr |= QSPI_IFR_SAMA5D2_WRITE_TRSFR;
 
 		/* Set QSPI Instruction Frame registers */
-		writel_relaxed(iar, aq->regs + QSPI_IAR);
-		writel_relaxed(icr, aq->regs + QSPI_ICR);
-		writel_relaxed(ifr, aq->regs + QSPI_IFR);
+		atmel_qspi_write(iar, aq, QSPI_IAR);
+		atmel_qspi_write(icr, aq, QSPI_ICR);
+		atmel_qspi_write(ifr, aq, QSPI_IFR);
 	}
 
 	return 0;
@@ -345,7 +420,7 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	/* Skip to the final steps if there is no data */
 	if (op->data.nbytes) {
 		/* Dummy read of QSPI_IFR to synchronize APB and AHB accesses */
-		(void)readl_relaxed(aq->regs + QSPI_IFR);
+		(void)atmel_qspi_read(aq, QSPI_IFR);
 
 		/* Send/Receive data */
 		if (op->data.dir == SPI_MEM_DATA_IN)
@@ -356,22 +431,22 @@ static int atmel_qspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 				     op->data.nbytes);
 
 		/* Release the chip-select */
-		writel_relaxed(QSPI_CR_LASTXFER, aq->regs + QSPI_CR);
+		atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR);
 	}
 
 	/* Poll INSTRuction End status */
-	sr = readl_relaxed(aq->regs + QSPI_SR);
+	sr = atmel_qspi_read(aq, QSPI_SR);
 	if ((sr & QSPI_SR_CMD_COMPLETED) == QSPI_SR_CMD_COMPLETED)
 		return err;
 
 	/* Wait for INSTRuction End interrupt */
 	reinit_completion(&aq->cmd_completion);
 	aq->pending = sr & QSPI_SR_CMD_COMPLETED;
-	writel_relaxed(QSPI_SR_CMD_COMPLETED, aq->regs + QSPI_IER);
+	atmel_qspi_write(QSPI_SR_CMD_COMPLETED, aq, QSPI_IER);
 	if (!wait_for_completion_timeout(&aq->cmd_completion,
 					 msecs_to_jiffies(1000)))
 		err = -ETIMEDOUT;
-	writel_relaxed(QSPI_SR_CMD_COMPLETED, aq->regs + QSPI_IDR);
+	atmel_qspi_write(QSPI_SR_CMD_COMPLETED, aq, QSPI_IDR);
 
 	return err;
 }
@@ -410,7 +485,7 @@ static int atmel_qspi_setup(struct spi_device *spi)
 		scbr--;
 
 	aq->scr = QSPI_SCR_SCBR(scbr);
-	writel_relaxed(aq->scr, aq->regs + QSPI_SCR);
+	atmel_qspi_write(aq->scr, aq, QSPI_SCR);
 
 	return 0;
 }
@@ -418,14 +493,14 @@ static int atmel_qspi_setup(struct spi_device *spi)
 static void atmel_qspi_init(struct atmel_qspi *aq)
 {
 	/* Reset the QSPI controller */
-	writel_relaxed(QSPI_CR_SWRST, aq->regs + QSPI_CR);
+	atmel_qspi_write(QSPI_CR_SWRST, aq, QSPI_CR);
 
 	/* Set the QSPI controller by default in Serial Memory Mode */
-	writel_relaxed(QSPI_MR_SMM, aq->regs + QSPI_MR);
+	atmel_qspi_write(QSPI_MR_SMM, aq, QSPI_MR);
 	aq->mr = QSPI_MR_SMM;
 
 	/* Enable the QSPI controller */
-	writel_relaxed(QSPI_CR_QSPIEN, aq->regs + QSPI_CR);
+	atmel_qspi_write(QSPI_CR_QSPIEN, aq, QSPI_CR);
 }
 
 static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
@@ -433,8 +508,8 @@ static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
 	struct atmel_qspi *aq = dev_id;
 	u32 status, mask, pending;
 
-	status = readl_relaxed(aq->regs + QSPI_SR);
-	mask = readl_relaxed(aq->regs + QSPI_IMR);
+	status = atmel_qspi_read(aq, QSPI_SR);
+	mask = atmel_qspi_read(aq, QSPI_IMR);
 	pending = status & mask;
 
 	if (!pending)
@@ -569,7 +644,7 @@ static int atmel_qspi_remove(struct platform_device *pdev)
 	struct atmel_qspi *aq = spi_controller_get_devdata(ctrl);
 
 	spi_unregister_controller(ctrl);
-	writel_relaxed(QSPI_CR_QSPIDIS, aq->regs + QSPI_CR);
+	atmel_qspi_write(QSPI_CR_QSPIDIS, aq, QSPI_CR);
 	clk_disable_unprepare(aq->qspick);
 	clk_disable_unprepare(aq->pclk);
 	return 0;
@@ -596,7 +671,7 @@ static int __maybe_unused atmel_qspi_resume(struct device *dev)
 
 	atmel_qspi_init(aq);
 
-	writel_relaxed(aq->scr, aq->regs + QSPI_SCR);
+	atmel_qspi_write(aq->scr, aq, QSPI_SCR);
 
 	return 0;
 }
diff --git a/drivers/spi/spi-ar934x.c b/drivers/spi/spi-ar934x.c
new file mode 100644
index 000000000000..d08dec09d423
--- /dev/null
+++ b/drivers/spi/spi-ar934x.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// SPI controller driver for Qualcomm Atheros AR934x/QCA95xx SoCs
+//
+// Copyright (C) 2020 Chuanhong Guo <gch981213@gmail.com>
+//
+// Based on spi-mt7621.c:
+// Copyright (C) 2011 Sergiy <piratfm@gmail.com>
+// Copyright (C) 2011-2013 Gabor Juhos <juhosg@openwrt.org>
+// Copyright (C) 2014-2015 Felix Fietkau <nbd@nbd.name>
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+
+#define DRIVER_NAME "spi-ar934x"
+
+#define AR934X_SPI_REG_FS		0x00
+#define AR934X_SPI_ENABLE		BIT(0)
+
+#define AR934X_SPI_REG_IOC		0x08
+#define AR934X_SPI_IOC_INITVAL		0x70000
+
+#define AR934X_SPI_REG_CTRL		0x04
+#define AR934X_SPI_CLK_MASK		GENMASK(5, 0)
+
+#define AR934X_SPI_DATAOUT		0x10
+
+#define AR934X_SPI_REG_SHIFT_CTRL	0x14
+#define AR934X_SPI_SHIFT_EN		BIT(31)
+#define AR934X_SPI_SHIFT_CS(n)		BIT(28 + (n))
+#define AR934X_SPI_SHIFT_TERM		26
+#define AR934X_SPI_SHIFT_VAL(cs, term, count)			\
+	(AR934X_SPI_SHIFT_EN | AR934X_SPI_SHIFT_CS(cs) |	\
+	(term) << AR934X_SPI_SHIFT_TERM | (count))
+
+#define AR934X_SPI_DATAIN 0x18
+
+struct ar934x_spi {
+	struct spi_controller *ctlr;
+	void __iomem *base;
+	struct clk *clk;
+	unsigned int clk_freq;
+};
+
+static inline int ar934x_spi_clk_div(struct ar934x_spi *sp, unsigned int freq)
+{
+	int div = DIV_ROUND_UP(sp->clk_freq, freq * 2) - 1;
+
+	if (div < 0)
+		return 0;
+	else if (div > AR934X_SPI_CLK_MASK)
+		return -EINVAL;
+	else
+		return div;
+}
+
+static int ar934x_spi_setup(struct spi_device *spi)
+{
+	struct ar934x_spi *sp = spi_controller_get_devdata(spi->master);
+
+	if ((spi->max_speed_hz == 0) ||
+	    (spi->max_speed_hz > (sp->clk_freq / 2))) {
+		spi->max_speed_hz = sp->clk_freq / 2;
+	} else if (spi->max_speed_hz < (sp->clk_freq / 128)) {
+		dev_err(&spi->dev, "spi clock is too low\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ar934x_spi_transfer_one_message(struct spi_controller *master,
+					   struct spi_message *m)
+{
+	struct ar934x_spi *sp = spi_controller_get_devdata(master);
+	struct spi_transfer *t = NULL;
+	struct spi_device *spi = m->spi;
+	unsigned long trx_done, trx_cur;
+	int stat = 0;
+	u8 term = 0;
+	int div, i;
+	u32 reg;
+	const u8 *tx_buf;
+	u8 *buf;
+
+	m->actual_length = 0;
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		if (t->speed_hz)
+			div = ar934x_spi_clk_div(sp, t->speed_hz);
+		else
+			div = ar934x_spi_clk_div(sp, spi->max_speed_hz);
+		if (div < 0) {
+			stat = -EIO;
+			goto msg_done;
+		}
+
+		reg = ioread32(sp->base + AR934X_SPI_REG_CTRL);
+		reg &= ~AR934X_SPI_CLK_MASK;
+		reg |= div;
+		iowrite32(reg, sp->base + AR934X_SPI_REG_CTRL);
+		iowrite32(0, sp->base + AR934X_SPI_DATAOUT);
+
+		for (trx_done = 0; trx_done < t->len; trx_done += 4) {
+			trx_cur = t->len - trx_done;
+			if (trx_cur > 4)
+				trx_cur = 4;
+			else if (list_is_last(&t->transfer_list, &m->transfers))
+				term = 1;
+
+			if (t->tx_buf) {
+				tx_buf = t->tx_buf + trx_done;
+				reg = tx_buf[0];
+				for (i = 1; i < trx_cur; i++)
+					reg = reg << 8 | tx_buf[i];
+				iowrite32(reg, sp->base + AR934X_SPI_DATAOUT);
+			}
+
+			reg = AR934X_SPI_SHIFT_VAL(spi->chip_select, term,
+						   trx_cur * 8);
+			iowrite32(reg, sp->base + AR934X_SPI_REG_SHIFT_CTRL);
+			stat = readl_poll_timeout(
+				sp->base + AR934X_SPI_REG_SHIFT_CTRL, reg,
+				!(reg & AR934X_SPI_SHIFT_EN), 0, 5);
+			if (stat < 0)
+				goto msg_done;
+
+			if (t->rx_buf) {
+				reg = ioread32(sp->base + AR934X_SPI_DATAIN);
+				buf = t->rx_buf + trx_done;
+				for (i = 0; i < trx_cur; i++) {
+					buf[trx_cur - i - 1] = reg & 0xff;
+					reg >>= 8;
+				}
+			}
+		}
+		m->actual_length += t->len;
+	}
+
+msg_done:
+	m->status = stat;
+	spi_finalize_current_message(master);
+
+	return 0;
+}
+
+static const struct of_device_id ar934x_spi_match[] = {
+	{ .compatible = "qca,ar934x-spi" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, ar934x_spi_match);
+
+static int ar934x_spi_probe(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr;
+	struct ar934x_spi *sp;
+	void __iomem *base;
+	struct clk *clk;
+	int ret;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(&pdev->dev, "failed to get clock\n");
+		return PTR_ERR(clk);
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
+	ctlr = spi_alloc_master(&pdev->dev, sizeof(*sp));
+	if (!ctlr) {
+		dev_info(&pdev->dev, "failed to allocate spi controller\n");
+		return -ENOMEM;
+	}
+
+	/* disable flash mapping and expose spi controller registers */
+	iowrite32(AR934X_SPI_ENABLE, base + AR934X_SPI_REG_FS);
+	/* restore pins to default state: CSn=1 DO=CLK=0 */
+	iowrite32(AR934X_SPI_IOC_INITVAL, base + AR934X_SPI_REG_IOC);
+
+	ctlr->mode_bits = SPI_LSB_FIRST;
+	ctlr->setup = ar934x_spi_setup;
+	ctlr->transfer_one_message = ar934x_spi_transfer_one_message;
+	ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
+	ctlr->dev.of_node = pdev->dev.of_node;
+	ctlr->num_chipselect = 3;
+
+	dev_set_drvdata(&pdev->dev, ctlr);
+
+	sp = spi_controller_get_devdata(ctlr);
+	sp->base = base;
+	sp->clk = clk;
+	sp->clk_freq = clk_get_rate(clk);
+	sp->ctlr = ctlr;
+
+	return devm_spi_register_controller(&pdev->dev, ctlr);
+}
+
+static int ar934x_spi_remove(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr;
+	struct ar934x_spi *sp;
+
+	ctlr = dev_get_drvdata(&pdev->dev);
+	sp = spi_controller_get_devdata(ctlr);
+
+	clk_disable_unprepare(sp->clk);
+
+	return 0;
+}
+
+static struct platform_driver ar934x_spi_driver = {
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = ar934x_spi_match,
+	},
+	.probe = ar934x_spi_probe,
+	.remove = ar934x_spi_remove,
+};
+
+module_platform_driver(ar934x_spi_driver);
+
+MODULE_DESCRIPTION("SPI controller driver for Qualcomm Atheros AR934x/QCA95xx");
+MODULE_AUTHOR("Chuanhong Guo <gch981213@gmail.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/spi-efm32.c b/drivers/spi/spi-efm32.c
index 64d4c441b641..ea6e4a7b3feb 100644
--- a/drivers/spi/spi-efm32.c
+++ b/drivers/spi/spi-efm32.c
@@ -6,14 +6,13 @@
 #include <linux/io.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/spi_bitbang.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/module.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_data/efm32-spi.h>
+#include <linux/of.h>
 
 #define DRIVER_NAME "efm32-spi"
 
@@ -82,9 +81,6 @@ struct efm32_spi_ddata {
 	const u8 *tx_buf;
 	u8 *rx_buf;
 	unsigned tx_len, rx_len;
-
-	/* chip selects */
-	unsigned csgpio[];
 };
 
 #define ddata_to_dev(ddata)	(&(ddata->bitbang.master->dev))
@@ -102,14 +98,6 @@ static u32 efm32_spi_read32(struct efm32_spi_ddata *ddata, unsigned offset)
 	return readl_relaxed(ddata->base + offset);
 }
 
-static void efm32_spi_chipselect(struct spi_device *spi, int is_on)
-{
-	struct efm32_spi_ddata *ddata = spi_master_get_devdata(spi->master);
-	int value = !(spi->mode & SPI_CS_HIGH) == !(is_on == BITBANG_CS_ACTIVE);
-
-	gpio_set_value(ddata->csgpio[spi->chip_select], value);
-}
-
 static int efm32_spi_setup_transfer(struct spi_device *spi,
 		struct spi_transfer *t)
 {
@@ -320,17 +308,11 @@ static int efm32_spi_probe(struct platform_device *pdev)
 	int ret;
 	struct spi_master *master;
 	struct device_node *np = pdev->dev.of_node;
-	int num_cs, i;
 
 	if (!np)
 		return -EINVAL;
 
-	num_cs = of_gpio_named_count(np, "cs-gpios");
-	if (num_cs < 0)
-		return num_cs;
-
-	master = spi_alloc_master(&pdev->dev,
-			sizeof(*ddata) + num_cs * sizeof(unsigned));
+	master = spi_alloc_master(&pdev->dev, sizeof(*ddata));
 	if (!master) {
 		dev_dbg(&pdev->dev,
 				"failed to allocate spi master controller\n");
@@ -340,14 +322,13 @@ static int efm32_spi_probe(struct platform_device *pdev)
 
 	master->dev.of_node = pdev->dev.of_node;
 
-	master->num_chipselect = num_cs;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+	master->use_gpio_descriptors = true;
 
 	ddata = spi_master_get_devdata(master);
 
 	ddata->bitbang.master = master;
-	ddata->bitbang.chipselect = efm32_spi_chipselect;
 	ddata->bitbang.setup_transfer = efm32_spi_setup_transfer;
 	ddata->bitbang.txrx_bufs = efm32_spi_txrx_bufs;
 
@@ -361,25 +342,6 @@ static int efm32_spi_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	for (i = 0; i < num_cs; ++i) {
-		ret = of_get_named_gpio(np, "cs-gpios", i);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "failed to get csgpio#%u (%d)\n",
-					i, ret);
-			goto err;
-		}
-		ddata->csgpio[i] = ret;
-		dev_dbg(&pdev->dev, "csgpio#%u = %u\n", i, ddata->csgpio[i]);
-		ret = devm_gpio_request_one(&pdev->dev, ddata->csgpio[i],
-				GPIOF_OUT_INIT_LOW, DRIVER_NAME);
-		if (ret < 0) {
-			dev_err(&pdev->dev,
-					"failed to configure csgpio#%u (%d)\n",
-					i, ret);
-			goto err;
-		}
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
 		ret = -ENODEV;
diff --git a/drivers/spi/spi-fsi.c b/drivers/spi/spi-fsi.c
new file mode 100644
index 000000000000..37a3e0f8e752
--- /dev/null
+++ b/drivers/spi/spi-fsi.c
@@ -0,0 +1,558 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+// Copyright (C) IBM Corporation 2020
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/fsi.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+#define FSI_ENGID_SPI			0x23
+#define FSI_MBOX_ROOT_CTRL_8		0x2860
+
+#define FSI2SPI_DATA0			0x00
+#define FSI2SPI_DATA1			0x04
+#define FSI2SPI_CMD			0x08
+#define  FSI2SPI_CMD_WRITE		 BIT(31)
+#define FSI2SPI_RESET			0x18
+#define FSI2SPI_STATUS			0x1c
+#define  FSI2SPI_STATUS_ANY_ERROR	 BIT(31)
+#define FSI2SPI_IRQ			0x20
+
+#define SPI_FSI_BASE			0x70000
+#define SPI_FSI_INIT_TIMEOUT_MS		1000
+#define SPI_FSI_MAX_TRANSFER_SIZE	2048
+
+#define SPI_FSI_ERROR			0x0
+#define SPI_FSI_COUNTER_CFG		0x1
+#define  SPI_FSI_COUNTER_CFG_LOOPS(x)	 (((u64)(x) & 0xffULL) << 32)
+#define SPI_FSI_CFG1			0x2
+#define SPI_FSI_CLOCK_CFG		0x3
+#define  SPI_FSI_CLOCK_CFG_MM_ENABLE	 BIT_ULL(32)
+#define  SPI_FSI_CLOCK_CFG_ECC_DISABLE	 (BIT_ULL(35) | BIT_ULL(33))
+#define  SPI_FSI_CLOCK_CFG_RESET1	 (BIT_ULL(36) | BIT_ULL(38))
+#define  SPI_FSI_CLOCK_CFG_RESET2	 (BIT_ULL(37) | BIT_ULL(39))
+#define  SPI_FSI_CLOCK_CFG_MODE		 (BIT_ULL(41) | BIT_ULL(42))
+#define  SPI_FSI_CLOCK_CFG_SCK_RECV_DEL	 GENMASK_ULL(51, 44)
+#define   SPI_FSI_CLOCK_CFG_SCK_NO_DEL	  BIT_ULL(51)
+#define  SPI_FSI_CLOCK_CFG_SCK_DIV	 GENMASK_ULL(63, 52)
+#define SPI_FSI_MMAP			0x4
+#define SPI_FSI_DATA_TX			0x5
+#define SPI_FSI_DATA_RX			0x6
+#define SPI_FSI_SEQUENCE		0x7
+#define  SPI_FSI_SEQUENCE_STOP		 0x00
+#define  SPI_FSI_SEQUENCE_SEL_SLAVE(x)	 (0x10 | ((x) & 0xf))
+#define  SPI_FSI_SEQUENCE_SHIFT_OUT(x)	 (0x30 | ((x) & 0xf))
+#define  SPI_FSI_SEQUENCE_SHIFT_IN(x)	 (0x40 | ((x) & 0xf))
+#define  SPI_FSI_SEQUENCE_COPY_DATA_TX	 0xc0
+#define  SPI_FSI_SEQUENCE_BRANCH(x)	 (0xe0 | ((x) & 0xf))
+#define SPI_FSI_STATUS			0x8
+#define  SPI_FSI_STATUS_ERROR		 \
+	(GENMASK_ULL(31, 21) | GENMASK_ULL(15, 12))
+#define  SPI_FSI_STATUS_SEQ_STATE	 GENMASK_ULL(55, 48)
+#define   SPI_FSI_STATUS_SEQ_STATE_IDLE	  BIT_ULL(48)
+#define  SPI_FSI_STATUS_TDR_UNDERRUN	 BIT_ULL(57)
+#define  SPI_FSI_STATUS_TDR_OVERRUN	 BIT_ULL(58)
+#define  SPI_FSI_STATUS_TDR_FULL	 BIT_ULL(59)
+#define  SPI_FSI_STATUS_RDR_UNDERRUN	 BIT_ULL(61)
+#define  SPI_FSI_STATUS_RDR_OVERRUN	 BIT_ULL(62)
+#define  SPI_FSI_STATUS_RDR_FULL	 BIT_ULL(63)
+#define  SPI_FSI_STATUS_ANY_ERROR	 \
+	(SPI_FSI_STATUS_ERROR | SPI_FSI_STATUS_TDR_UNDERRUN | \
+	 SPI_FSI_STATUS_TDR_OVERRUN | SPI_FSI_STATUS_RDR_UNDERRUN | \
+	 SPI_FSI_STATUS_RDR_OVERRUN)
+#define SPI_FSI_PORT_CTRL		0x9
+
+struct fsi_spi {
+	struct device *dev;	/* SPI controller device */
+	struct fsi_device *fsi;	/* FSI2SPI CFAM engine device */
+	u32 base;
+};
+
+struct fsi_spi_sequence {
+	int bit;
+	u64 data;
+};
+
+static int fsi_spi_check_status(struct fsi_spi *ctx)
+{
+	int rc;
+	u32 sts;
+	__be32 sts_be;
+
+	rc = fsi_device_read(ctx->fsi, FSI2SPI_STATUS, &sts_be,
+			     sizeof(sts_be));
+	if (rc)
+		return rc;
+
+	sts = be32_to_cpu(sts_be);
+	if (sts & FSI2SPI_STATUS_ANY_ERROR) {
+		dev_err(ctx->dev, "Error with FSI2SPI interface: %08x.\n", sts);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int fsi_spi_read_reg(struct fsi_spi *ctx, u32 offset, u64 *value)
+{
+	int rc;
+	__be32 cmd_be;
+	__be32 data_be;
+	u32 cmd = offset + ctx->base;
+
+	*value = 0ULL;
+
+	if (cmd & FSI2SPI_CMD_WRITE)
+		return -EINVAL;
+
+	cmd_be = cpu_to_be32(cmd);
+	rc = fsi_device_write(ctx->fsi, FSI2SPI_CMD, &cmd_be, sizeof(cmd_be));
+	if (rc)
+		return rc;
+
+	rc = fsi_spi_check_status(ctx);
+	if (rc)
+		return rc;
+
+	rc = fsi_device_read(ctx->fsi, FSI2SPI_DATA0, &data_be,
+			     sizeof(data_be));
+	if (rc)
+		return rc;
+
+	*value |= (u64)be32_to_cpu(data_be) << 32;
+
+	rc = fsi_device_read(ctx->fsi, FSI2SPI_DATA1, &data_be,
+			     sizeof(data_be));
+	if (rc)
+		return rc;
+
+	*value |= (u64)be32_to_cpu(data_be);
+	dev_dbg(ctx->dev, "Read %02x[%016llx].\n", offset, *value);
+
+	return 0;
+}
+
+static int fsi_spi_write_reg(struct fsi_spi *ctx, u32 offset, u64 value)
+{
+	int rc;
+	__be32 cmd_be;
+	__be32 data_be;
+	u32 cmd = offset + ctx->base;
+
+	if (cmd & FSI2SPI_CMD_WRITE)
+		return -EINVAL;
+
+	dev_dbg(ctx->dev, "Write %02x[%016llx].\n", offset, value);
+
+	data_be = cpu_to_be32(upper_32_bits(value));
+	rc = fsi_device_write(ctx->fsi, FSI2SPI_DATA0, &data_be,
+			      sizeof(data_be));
+	if (rc)
+		return rc;
+
+	data_be = cpu_to_be32(lower_32_bits(value));
+	rc = fsi_device_write(ctx->fsi, FSI2SPI_DATA1, &data_be,
+			      sizeof(data_be));
+	if (rc)
+		return rc;
+
+	cmd_be = cpu_to_be32(cmd | FSI2SPI_CMD_WRITE);
+	rc = fsi_device_write(ctx->fsi, FSI2SPI_CMD, &cmd_be, sizeof(cmd_be));
+	if (rc)
+		return rc;
+
+	return fsi_spi_check_status(ctx);
+}
+
+static int fsi_spi_data_in(u64 in, u8 *rx, int len)
+{
+	int i;
+	int num_bytes = min(len, 8);
+
+	for (i = 0; i < num_bytes; ++i)
+		rx[i] = (u8)(in >> (8 * ((num_bytes - 1) - i)));
+
+	return num_bytes;
+}
+
+static int fsi_spi_data_out(u64 *out, const u8 *tx, int len)
+{
+	int i;
+	int num_bytes = min(len, 8);
+	u8 *out_bytes = (u8 *)out;
+
+	/* Unused bytes of the tx data should be 0. */
+	*out = 0ULL;
+
+	for (i = 0; i < num_bytes; ++i)
+		out_bytes[8 - (i + 1)] = tx[i];
+
+	return num_bytes;
+}
+
+static int fsi_spi_reset(struct fsi_spi *ctx)
+{
+	int rc;
+
+	dev_dbg(ctx->dev, "Resetting SPI controller.\n");
+
+	rc = fsi_spi_write_reg(ctx, SPI_FSI_CLOCK_CFG,
+			       SPI_FSI_CLOCK_CFG_RESET1);
+	if (rc)
+		return rc;
+
+	return fsi_spi_write_reg(ctx, SPI_FSI_CLOCK_CFG,
+				 SPI_FSI_CLOCK_CFG_RESET2);
+}
+
+static int fsi_spi_sequence_add(struct fsi_spi_sequence *seq, u8 val)
+{
+	/*
+	 * Add the next byte of instruction to the 8-byte sequence register.
+	 * Then decrement the counter so that the next instruction will go in
+	 * the right place. Return the number of "slots" left in the sequence
+	 * register.
+	 */
+	seq->data |= (u64)val << seq->bit;
+	seq->bit -= 8;
+
+	return ((64 - seq->bit) / 8) - 2;
+}
+
+static void fsi_spi_sequence_init(struct fsi_spi_sequence *seq)
+{
+	seq->bit = 56;
+	seq->data = 0ULL;
+}
+
+static int fsi_spi_sequence_transfer(struct fsi_spi *ctx,
+				     struct fsi_spi_sequence *seq,
+				     struct spi_transfer *transfer)
+{
+	int loops;
+	int idx;
+	int rc;
+	u8 len = min(transfer->len, 8U);
+	u8 rem = transfer->len % len;
+
+	loops = transfer->len / len;
+
+	if (transfer->tx_buf) {
+		idx = fsi_spi_sequence_add(seq,
+					   SPI_FSI_SEQUENCE_SHIFT_OUT(len));
+		if (rem)
+			rem = SPI_FSI_SEQUENCE_SHIFT_OUT(rem);
+	} else if (transfer->rx_buf) {
+		idx = fsi_spi_sequence_add(seq,
+					   SPI_FSI_SEQUENCE_SHIFT_IN(len));
+		if (rem)
+			rem = SPI_FSI_SEQUENCE_SHIFT_IN(rem);
+	} else {
+		return -EINVAL;
+	}
+
+	if (loops > 1) {
+		fsi_spi_sequence_add(seq, SPI_FSI_SEQUENCE_BRANCH(idx));
+
+		if (rem)
+			fsi_spi_sequence_add(seq, rem);
+
+		rc = fsi_spi_write_reg(ctx, SPI_FSI_COUNTER_CFG,
+				       SPI_FSI_COUNTER_CFG_LOOPS(loops - 1));
+		if (rc)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int fsi_spi_transfer_data(struct fsi_spi *ctx,
+				 struct spi_transfer *transfer)
+{
+	int rc = 0;
+	u64 status = 0ULL;
+
+	if (transfer->tx_buf) {
+		int nb;
+		int sent = 0;
+		u64 out = 0ULL;
+		const u8 *tx = transfer->tx_buf;
+
+		while (transfer->len > sent) {
+			nb = fsi_spi_data_out(&out, &tx[sent],
+					      (int)transfer->len - sent);
+
+			rc = fsi_spi_write_reg(ctx, SPI_FSI_DATA_TX, out);
+			if (rc)
+				return rc;
+
+			do {
+				rc = fsi_spi_read_reg(ctx, SPI_FSI_STATUS,
+						      &status);
+				if (rc)
+					return rc;
+
+				if (status & SPI_FSI_STATUS_ANY_ERROR) {
+					rc = fsi_spi_reset(ctx);
+					if (rc)
+						return rc;
+
+					return -EREMOTEIO;
+				}
+			} while (status & SPI_FSI_STATUS_TDR_FULL);
+
+			sent += nb;
+		}
+	} else if (transfer->rx_buf) {
+		int recv = 0;
+		u64 in = 0ULL;
+		u8 *rx = transfer->rx_buf;
+
+		while (transfer->len > recv) {
+			do {
+				rc = fsi_spi_read_reg(ctx, SPI_FSI_STATUS,
+						      &status);
+				if (rc)
+					return rc;
+
+				if (status & SPI_FSI_STATUS_ANY_ERROR) {
+					rc = fsi_spi_reset(ctx);
+					if (rc)
+						return rc;
+
+					return -EREMOTEIO;
+				}
+			} while (!(status & SPI_FSI_STATUS_RDR_FULL));
+
+			rc = fsi_spi_read_reg(ctx, SPI_FSI_DATA_RX, &in);
+			if (rc)
+				return rc;
+
+			recv += fsi_spi_data_in(in, &rx[recv],
+						(int)transfer->len - recv);
+		}
+	}
+
+	return 0;
+}
+
+static int fsi_spi_transfer_init(struct fsi_spi *ctx)
+{
+	int rc;
+	bool reset = false;
+	unsigned long end;
+	u64 seq_state;
+	u64 clock_cfg = 0ULL;
+	u64 status = 0ULL;
+	u64 wanted_clock_cfg = SPI_FSI_CLOCK_CFG_ECC_DISABLE |
+		SPI_FSI_CLOCK_CFG_SCK_NO_DEL |
+		FIELD_PREP(SPI_FSI_CLOCK_CFG_SCK_DIV, 4);
+
+	end = jiffies + msecs_to_jiffies(SPI_FSI_INIT_TIMEOUT_MS);
+	do {
+		if (time_after(jiffies, end))
+			return -ETIMEDOUT;
+
+		rc = fsi_spi_read_reg(ctx, SPI_FSI_STATUS, &status);
+		if (rc)
+			return rc;
+
+		seq_state = status & SPI_FSI_STATUS_SEQ_STATE;
+
+		if (status & (SPI_FSI_STATUS_ANY_ERROR |
+			      SPI_FSI_STATUS_TDR_FULL |
+			      SPI_FSI_STATUS_RDR_FULL)) {
+			if (reset)
+				return -EIO;
+
+			rc = fsi_spi_reset(ctx);
+			if (rc)
+				return rc;
+
+			reset = true;
+			continue;
+		}
+	} while (seq_state && (seq_state != SPI_FSI_STATUS_SEQ_STATE_IDLE));
+
+	rc = fsi_spi_read_reg(ctx, SPI_FSI_CLOCK_CFG, &clock_cfg);
+	if (rc)
+		return rc;
+
+	if ((clock_cfg & (SPI_FSI_CLOCK_CFG_MM_ENABLE |
+			  SPI_FSI_CLOCK_CFG_ECC_DISABLE |
+			  SPI_FSI_CLOCK_CFG_MODE |
+			  SPI_FSI_CLOCK_CFG_SCK_RECV_DEL |
+			  SPI_FSI_CLOCK_CFG_SCK_DIV)) != wanted_clock_cfg)
+		rc = fsi_spi_write_reg(ctx, SPI_FSI_CLOCK_CFG,
+				       wanted_clock_cfg);
+
+	return rc;
+}
+
+static int fsi_spi_transfer_one_message(struct spi_controller *ctlr,
+					struct spi_message *mesg)
+{
+	int rc = 0;
+	u8 seq_slave = SPI_FSI_SEQUENCE_SEL_SLAVE(mesg->spi->chip_select + 1);
+	struct spi_transfer *transfer;
+	struct fsi_spi *ctx = spi_controller_get_devdata(ctlr);
+
+	list_for_each_entry(transfer, &mesg->transfers, transfer_list) {
+		struct fsi_spi_sequence seq;
+		struct spi_transfer *next = NULL;
+
+		/* Sequencer must do shift out (tx) first. */
+		if (!transfer->tx_buf ||
+		    transfer->len > SPI_FSI_MAX_TRANSFER_SIZE) {
+			rc = -EINVAL;
+			goto error;
+		}
+
+		dev_dbg(ctx->dev, "Start tx of %d bytes.\n", transfer->len);
+
+		rc = fsi_spi_transfer_init(ctx);
+		if (rc < 0)
+			goto error;
+
+		fsi_spi_sequence_init(&seq);
+		fsi_spi_sequence_add(&seq, seq_slave);
+
+		rc = fsi_spi_sequence_transfer(ctx, &seq, transfer);
+		if (rc)
+			goto error;
+
+		if (!list_is_last(&transfer->transfer_list,
+				  &mesg->transfers)) {
+			next = list_next_entry(transfer, transfer_list);
+
+			/* Sequencer can only do shift in (rx) after tx. */
+			if (next->rx_buf) {
+				if (next->len > SPI_FSI_MAX_TRANSFER_SIZE) {
+					rc = -EINVAL;
+					goto error;
+				}
+
+				dev_dbg(ctx->dev, "Sequence rx of %d bytes.\n",
+					next->len);
+
+				rc = fsi_spi_sequence_transfer(ctx, &seq,
+							       next);
+				if (rc)
+					goto error;
+			} else {
+				next = NULL;
+			}
+		}
+
+		fsi_spi_sequence_add(&seq, SPI_FSI_SEQUENCE_SEL_SLAVE(0));
+
+		rc = fsi_spi_write_reg(ctx, SPI_FSI_SEQUENCE, seq.data);
+		if (rc)
+			goto error;
+
+		rc = fsi_spi_transfer_data(ctx, transfer);
+		if (rc)
+			goto error;
+
+		if (next) {
+			rc = fsi_spi_transfer_data(ctx, next);
+			if (rc)
+				goto error;
+
+			transfer = next;
+		}
+	}
+
+error:
+	mesg->status = rc;
+	spi_finalize_current_message(ctlr);
+
+	return rc;
+}
+
+static size_t fsi_spi_max_transfer_size(struct spi_device *spi)
+{
+	return SPI_FSI_MAX_TRANSFER_SIZE;
+}
+
+static int fsi_spi_probe(struct device *dev)
+{
+	int rc;
+	u32 root_ctrl_8;
+	struct device_node *np;
+	int num_controllers_registered = 0;
+	struct fsi_device *fsi = to_fsi_dev(dev);
+
+	/*
+	 * Check the SPI mux before attempting to probe. If the mux isn't set
+	 * then the SPI controllers can't access their slave devices.
+	 */
+	rc = fsi_slave_read(fsi->slave, FSI_MBOX_ROOT_CTRL_8, &root_ctrl_8,
+			    sizeof(root_ctrl_8));
+	if (rc)
+		return rc;
+
+	if (!root_ctrl_8) {
+		dev_dbg(dev, "SPI mux not set, aborting probe.\n");
+		return -ENODEV;
+	}
+
+	for_each_available_child_of_node(dev->of_node, np) {
+		u32 base;
+		struct fsi_spi *ctx;
+		struct spi_controller *ctlr;
+
+		if (of_property_read_u32(np, "reg", &base))
+			continue;
+
+		ctlr = spi_alloc_master(dev, sizeof(*ctx));
+		if (!ctlr)
+			break;
+
+		ctlr->dev.of_node = np;
+		ctlr->num_chipselect = of_get_available_child_count(np) ?: 1;
+		ctlr->flags = SPI_CONTROLLER_HALF_DUPLEX;
+		ctlr->max_transfer_size = fsi_spi_max_transfer_size;
+		ctlr->transfer_one_message = fsi_spi_transfer_one_message;
+
+		ctx = spi_controller_get_devdata(ctlr);
+		ctx->dev = &ctlr->dev;
+		ctx->fsi = fsi;
+		ctx->base = base + SPI_FSI_BASE;
+
+		rc = devm_spi_register_controller(dev, ctlr);
+		if (rc)
+			spi_controller_put(ctlr);
+		else
+			num_controllers_registered++;
+	}
+
+	if (!num_controllers_registered)
+		return -ENODEV;
+
+	return 0;
+}
+
+static const struct fsi_device_id fsi_spi_ids[] = {
+	{ FSI_ENGID_SPI, FSI_VERSION_ANY },
+	{ }
+};
+MODULE_DEVICE_TABLE(fsi, fsi_spi_ids);
+
+static struct fsi_driver fsi_spi_driver = {
+	.id_table = fsi_spi_ids,
+	.drv = {
+		.name = "spi-fsi",
+		.bus = &fsi_bus_type,
+		.probe = fsi_spi_probe,
+	},
+};
+module_fsi_driver(fsi_spi_driver);
+
+MODULE_AUTHOR("Eddie James <eajames@linux.ibm.com>");
+MODULE_DESCRIPTION("FSI attached SPI controller");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 6ec2dcb8c57a..50e41f66a2d7 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -20,16 +20,9 @@
 
 #define DRIVER_NAME			"fsl-dspi"
 
-#ifdef CONFIG_M5441x
-#define DSPI_FIFO_SIZE			16
-#else
-#define DSPI_FIFO_SIZE			4
-#endif
-#define DSPI_DMA_BUFSIZE		(DSPI_FIFO_SIZE * 1024)
-
 #define SPI_MCR				0x00
 #define SPI_MCR_MASTER			BIT(31)
-#define SPI_MCR_PCSIS			(0x3F << 16)
+#define SPI_MCR_PCSIS(x)		((x) << 16)
 #define SPI_MCR_CLR_TXF			BIT(11)
 #define SPI_MCR_CLR_RXF			BIT(10)
 #define SPI_MCR_XSPI			BIT(3)
@@ -79,6 +72,7 @@
 #define SPI_RSER			0x30
 #define SPI_RSER_TCFQE			BIT(31)
 #define SPI_RSER_EOQFE			BIT(28)
+#define SPI_RSER_CMDTCFE		BIT(23)
 
 #define SPI_PUSHR			0x34
 #define SPI_PUSHR_CMD_CONT		BIT(15)
@@ -109,57 +103,95 @@
 #define SPI_FRAME_BITS(bits)		SPI_CTAR_FMSZ((bits) - 1)
 #define SPI_FRAME_EBITS(bits)		SPI_CTARE_FMSZE(((bits) - 1) >> 4)
 
-/* Register offsets for regmap_pushr */
-#define PUSHR_CMD			0x0
-#define PUSHR_TX			0x2
-
 #define DMA_COMPLETION_TIMEOUT		msecs_to_jiffies(3000)
 
 struct chip_data {
 	u32			ctar_val;
-	u16			void_write_data;
 };
 
 enum dspi_trans_mode {
 	DSPI_EOQ_MODE = 0,
-	DSPI_TCFQ_MODE,
+	DSPI_XSPI_MODE,
 	DSPI_DMA_MODE,
 };
 
 struct fsl_dspi_devtype_data {
 	enum dspi_trans_mode	trans_mode;
 	u8			max_clock_factor;
-	bool			ptp_sts_supported;
-	bool			xspi_mode;
-};
-
-static const struct fsl_dspi_devtype_data vf610_data = {
-	.trans_mode		= DSPI_DMA_MODE,
-	.max_clock_factor	= 2,
-};
-
-static const struct fsl_dspi_devtype_data ls1021a_v1_data = {
-	.trans_mode		= DSPI_TCFQ_MODE,
-	.max_clock_factor	= 8,
-	.ptp_sts_supported	= true,
-	.xspi_mode		= true,
+	int			fifo_size;
 };
 
-static const struct fsl_dspi_devtype_data ls2085a_data = {
-	.trans_mode		= DSPI_TCFQ_MODE,
-	.max_clock_factor	= 8,
-	.ptp_sts_supported	= true,
+enum {
+	LS1021A,
+	LS1012A,
+	LS1028A,
+	LS1043A,
+	LS1046A,
+	LS2080A,
+	LS2085A,
+	LX2160A,
+	MCF5441X,
+	VF610,
 };
 
-static const struct fsl_dspi_devtype_data coldfire_data = {
-	.trans_mode		= DSPI_EOQ_MODE,
-	.max_clock_factor	= 8,
+static const struct fsl_dspi_devtype_data devtype_data[] = {
+	[VF610] = {
+		.trans_mode		= DSPI_DMA_MODE,
+		.max_clock_factor	= 2,
+		.fifo_size		= 4,
+	},
+	[LS1021A] = {
+		/* Has A-011218 DMA erratum */
+		.trans_mode		= DSPI_XSPI_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 4,
+	},
+	[LS1012A] = {
+		/* Has A-011218 DMA erratum */
+		.trans_mode		= DSPI_XSPI_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 16,
+	},
+	[LS1028A] = {
+		.trans_mode		= DSPI_XSPI_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 4,
+	},
+	[LS1043A] = {
+		/* Has A-011218 DMA erratum */
+		.trans_mode		= DSPI_XSPI_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 16,
+	},
+	[LS1046A] = {
+		/* Has A-011218 DMA erratum */
+		.trans_mode		= DSPI_XSPI_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 16,
+	},
+	[LS2080A] = {
+		.trans_mode		= DSPI_DMA_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 4,
+	},
+	[LS2085A] = {
+		.trans_mode		= DSPI_DMA_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 4,
+	},
+	[LX2160A] = {
+		.trans_mode		= DSPI_DMA_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 4,
+	},
+	[MCF5441X] = {
+		.trans_mode		= DSPI_EOQ_MODE,
+		.max_clock_factor	= 8,
+		.fifo_size		= 16,
+	},
 };
 
 struct fsl_dspi_dma {
-	/* Length of transfer in words of DSPI_FIFO_SIZE */
-	u32					curr_xfer_len;
-
 	u32					*tx_dma_buf;
 	struct dma_chan				*chan_tx;
 	dma_addr_t				tx_dma_phys;
@@ -189,36 +221,99 @@ struct fsl_dspi {
 	size_t					len;
 	const void				*tx;
 	void					*rx;
-	void					*rx_end;
-	u16					void_write_data;
 	u16					tx_cmd;
-	u8					bits_per_word;
-	u8					bytes_per_word;
 	const struct fsl_dspi_devtype_data	*devtype_data;
 
-	wait_queue_head_t			waitq;
-	u32					waitflags;
+	struct completion			xfer_done;
 
 	struct fsl_dspi_dma			*dma;
+
+	int					oper_word_size;
+	int					oper_bits_per_word;
+
+	int					words_in_flight;
+
+	/*
+	 * Offsets for CMD and TXDATA within SPI_PUSHR when accessed
+	 * individually (in XSPI mode)
+	 */
+	int					pushr_cmd;
+	int					pushr_tx;
+
+	void (*host_to_dev)(struct fsl_dspi *dspi, u32 *txdata);
+	void (*dev_to_host)(struct fsl_dspi *dspi, u32 rxdata);
 };
 
+static void dspi_native_host_to_dev(struct fsl_dspi *dspi, u32 *txdata)
+{
+	memcpy(txdata, dspi->tx, dspi->oper_word_size);
+	dspi->tx += dspi->oper_word_size;
+}
+
+static void dspi_native_dev_to_host(struct fsl_dspi *dspi, u32 rxdata)
+{
+	memcpy(dspi->rx, &rxdata, dspi->oper_word_size);
+	dspi->rx += dspi->oper_word_size;
+}
+
+static void dspi_8on32_host_to_dev(struct fsl_dspi *dspi, u32 *txdata)
+{
+	*txdata = cpu_to_be32(*(u32 *)dspi->tx);
+	dspi->tx += sizeof(u32);
+}
+
+static void dspi_8on32_dev_to_host(struct fsl_dspi *dspi, u32 rxdata)
+{
+	*(u32 *)dspi->rx = be32_to_cpu(rxdata);
+	dspi->rx += sizeof(u32);
+}
+
+static void dspi_8on16_host_to_dev(struct fsl_dspi *dspi, u32 *txdata)
+{
+	*txdata = cpu_to_be16(*(u16 *)dspi->tx);
+	dspi->tx += sizeof(u16);
+}
+
+static void dspi_8on16_dev_to_host(struct fsl_dspi *dspi, u32 rxdata)
+{
+	*(u16 *)dspi->rx = be16_to_cpu(rxdata);
+	dspi->rx += sizeof(u16);
+}
+
+static void dspi_16on32_host_to_dev(struct fsl_dspi *dspi, u32 *txdata)
+{
+	u16 hi = *(u16 *)dspi->tx;
+	u16 lo = *(u16 *)(dspi->tx + 2);
+
+	*txdata = (u32)hi << 16 | lo;
+	dspi->tx += sizeof(u32);
+}
+
+static void dspi_16on32_dev_to_host(struct fsl_dspi *dspi, u32 rxdata)
+{
+	u16 hi = rxdata & 0xffff;
+	u16 lo = rxdata >> 16;
+
+	*(u16 *)dspi->rx = lo;
+	*(u16 *)(dspi->rx + 2) = hi;
+	dspi->rx += sizeof(u32);
+}
+
+/*
+ * Pop one word from the TX buffer for pushing into the
+ * PUSHR register (TX FIFO)
+ */
 static u32 dspi_pop_tx(struct fsl_dspi *dspi)
 {
 	u32 txdata = 0;
 
-	if (dspi->tx) {
-		if (dspi->bytes_per_word == 1)
-			txdata = *(u8 *)dspi->tx;
-		else if (dspi->bytes_per_word == 2)
-			txdata = *(u16 *)dspi->tx;
-		else  /* dspi->bytes_per_word == 4 */
-			txdata = *(u32 *)dspi->tx;
-		dspi->tx += dspi->bytes_per_word;
-	}
-	dspi->len -= dspi->bytes_per_word;
+	if (dspi->tx)
+		dspi->host_to_dev(dspi, &txdata);
+	dspi->len -= dspi->oper_word_size;
 	return txdata;
 }
 
+/* Prepare one TX FIFO entry (txdata plus cmd) */
 static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 {
 	u16 cmd = dspi->tx_cmd, data = dspi_pop_tx(dspi);
@@ -231,21 +326,12 @@ static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 	return cmd << 16 | data;
 }
 
+/* Push one word to the RX buffer from the POPR register (RX FIFO) */
 static void dspi_push_rx(struct fsl_dspi *dspi, u32 rxdata)
 {
 	if (!dspi->rx)
 		return;
-
-	/* Mask off undefined bits */
-	rxdata &= (1 << dspi->bits_per_word) - 1;
-
-	if (dspi->bytes_per_word == 1)
-		*(u8 *)dspi->rx = rxdata;
-	else if (dspi->bytes_per_word == 2)
-		*(u16 *)dspi->rx = rxdata;
-	else /* dspi->bytes_per_word == 4 */
-		*(u32 *)dspi->rx = rxdata;
-	dspi->rx += dspi->bytes_per_word;
+	dspi->dev_to_host(dspi, rxdata);
 }
 
 static void dspi_tx_dma_callback(void *arg)
@@ -263,7 +349,7 @@ static void dspi_rx_dma_callback(void *arg)
 	int i;
 
 	if (dspi->rx) {
-		for (i = 0; i < dma->curr_xfer_len; i++)
+		for (i = 0; i < dspi->words_in_flight; i++)
 			dspi_push_rx(dspi, dspi->dma->rx_dma_buf[i]);
 	}
 
@@ -277,12 +363,12 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	int time_left;
 	int i;
 
-	for (i = 0; i < dma->curr_xfer_len; i++)
+	for (i = 0; i < dspi->words_in_flight; i++)
 		dspi->dma->tx_dma_buf[i] = dspi_pop_tx_pushr(dspi);
 
 	dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
 					dma->tx_dma_phys,
-					dma->curr_xfer_len *
+					dspi->words_in_flight *
 					DMA_SLAVE_BUSWIDTH_4_BYTES,
 					DMA_MEM_TO_DEV,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
@@ -300,7 +386,7 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 
 	dma->rx_desc = dmaengine_prep_slave_single(dma->chan_rx,
 					dma->rx_dma_phys,
-					dma->curr_xfer_len *
+					dspi->words_in_flight *
 					DMA_SLAVE_BUSWIDTH_4_BYTES,
 					DMA_DEV_TO_MEM,
 					DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
@@ -348,45 +434,42 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	return 0;
 }
 
+static void dspi_setup_accel(struct fsl_dspi *dspi);
+
 static int dspi_dma_xfer(struct fsl_dspi *dspi)
 {
 	struct spi_message *message = dspi->cur_msg;
 	struct device *dev = &dspi->pdev->dev;
-	struct fsl_dspi_dma *dma = dspi->dma;
-	int curr_remaining_bytes;
-	int bytes_per_buffer;
 	int ret = 0;
 
-	curr_remaining_bytes = dspi->len;
-	bytes_per_buffer = DSPI_DMA_BUFSIZE / DSPI_FIFO_SIZE;
-	while (curr_remaining_bytes) {
-		/* Check if current transfer fits the DMA buffer */
-		dma->curr_xfer_len = curr_remaining_bytes
-			/ dspi->bytes_per_word;
-		if (dma->curr_xfer_len > bytes_per_buffer)
-			dma->curr_xfer_len = bytes_per_buffer;
+	/*
+	 * dspi->len gets decremented by dspi_pop_tx_pushr in
+	 * dspi_next_xfer_dma_submit
+	 */
+	while (dspi->len) {
+		/* Figure out operational bits-per-word for this chunk */
+		dspi_setup_accel(dspi);
+
+		dspi->words_in_flight = dspi->len / dspi->oper_word_size;
+		if (dspi->words_in_flight > dspi->devtype_data->fifo_size)
+			dspi->words_in_flight = dspi->devtype_data->fifo_size;
+
+		message->actual_length += dspi->words_in_flight *
+					  dspi->oper_word_size;
 
 		ret = dspi_next_xfer_dma_submit(dspi);
 		if (ret) {
 			dev_err(dev, "DMA transfer failed\n");
-			goto exit;
-
-		} else {
-			const int len =
-				dma->curr_xfer_len * dspi->bytes_per_word;
-			curr_remaining_bytes -= len;
-			message->actual_length += len;
-			if (curr_remaining_bytes < 0)
-				curr_remaining_bytes = 0;
+			break;
 		}
 	}
 
-exit:
 	return ret;
 }
 
 static int dspi_request_dma(struct fsl_dspi *dspi, phys_addr_t phy_addr)
 {
+	int dma_bufsize = dspi->devtype_data->fifo_size * 2;
 	struct device *dev = &dspi->pdev->dev;
 	struct dma_slave_config cfg;
 	struct fsl_dspi_dma *dma;
@@ -410,15 +493,17 @@ static int dspi_request_dma(struct fsl_dspi *dspi, phys_addr_t phy_addr)
 		goto err_tx_channel;
 	}
 
-	dma->tx_dma_buf = dma_alloc_coherent(dev, DSPI_DMA_BUFSIZE,
-					     &dma->tx_dma_phys, GFP_KERNEL);
+	dma->tx_dma_buf = dma_alloc_coherent(dma->chan_tx->device->dev,
+					     dma_bufsize, &dma->tx_dma_phys,
+					     GFP_KERNEL);
 	if (!dma->tx_dma_buf) {
 		ret = -ENOMEM;
 		goto err_tx_dma_buf;
 	}
 
-	dma->rx_dma_buf = dma_alloc_coherent(dev, DSPI_DMA_BUFSIZE,
-					     &dma->rx_dma_phys, GFP_KERNEL);
+	dma->rx_dma_buf = dma_alloc_coherent(dma->chan_rx->device->dev,
+					     dma_bufsize, &dma->rx_dma_phys,
+					     GFP_KERNEL);
 	if (!dma->rx_dma_buf) {
 		ret = -ENOMEM;
 		goto err_rx_dma_buf;
@@ -454,11 +539,11 @@ static int dspi_request_dma(struct fsl_dspi *dspi, phys_addr_t phy_addr)
 	return 0;
 
 err_slave_config:
-	dma_free_coherent(dev, DSPI_DMA_BUFSIZE,
-			dma->rx_dma_buf, dma->rx_dma_phys);
+	dma_free_coherent(dma->chan_rx->device->dev,
+			  dma_bufsize, dma->rx_dma_buf, dma->rx_dma_phys);
 err_rx_dma_buf:
-	dma_free_coherent(dev, DSPI_DMA_BUFSIZE,
-			dma->tx_dma_buf, dma->tx_dma_phys);
+	dma_free_coherent(dma->chan_tx->device->dev,
+			  dma_bufsize, dma->tx_dma_buf, dma->tx_dma_phys);
 err_tx_dma_buf:
 	dma_release_channel(dma->chan_tx);
 err_tx_channel:
@@ -472,21 +557,21 @@ err_tx_channel:
 
 static void dspi_release_dma(struct fsl_dspi *dspi)
 {
+	int dma_bufsize = dspi->devtype_data->fifo_size * 2;
 	struct fsl_dspi_dma *dma = dspi->dma;
-	struct device *dev = &dspi->pdev->dev;
 
 	if (!dma)
 		return;
 
 	if (dma->chan_tx) {
-		dma_unmap_single(dev, dma->tx_dma_phys,
-				 DSPI_DMA_BUFSIZE, DMA_TO_DEVICE);
+		dma_unmap_single(dma->chan_tx->device->dev, dma->tx_dma_phys,
+				 dma_bufsize, DMA_TO_DEVICE);
 		dma_release_channel(dma->chan_tx);
 	}
 
 	if (dma->chan_rx) {
-		dma_unmap_single(dev, dma->rx_dma_phys,
-				 DSPI_DMA_BUFSIZE, DMA_FROM_DEVICE);
+		dma_unmap_single(dma->chan_rx->device->dev, dma->rx_dma_phys,
+				 dma_bufsize, DMA_FROM_DEVICE);
 		dma_release_channel(dma->chan_rx);
 	}
 }
@@ -562,124 +647,220 @@ static void ns_delay_scale(char *psc, char *sc, int delay_ns,
 	}
 }
 
-static void fifo_write(struct fsl_dspi *dspi)
+static void dspi_pushr_write(struct fsl_dspi *dspi)
 {
 	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pop_tx_pushr(dspi));
 }
 
-static void cmd_fifo_write(struct fsl_dspi *dspi)
+static void dspi_pushr_cmd_write(struct fsl_dspi *dspi, u16 cmd)
 {
-	u16 cmd = dspi->tx_cmd;
-
-	if (dspi->len > 0)
+	/*
+	 * The only time when the PCS doesn't need continuation after this word
+	 * is when it's last. We need to look ahead, because we actually call
+	 * dspi_pop_tx (the function that decrements dspi->len) _after_
+	 * dspi_pushr_cmd_write with XSPI mode. As for how much in advance? One
+	 * word is enough. If there's more to transmit than that,
+	 * dspi_xspi_write will know to split the FIFO writes in 2, and
+	 * generate a new PUSHR command with the final word that will have PCS
+	 * deasserted (not continued) here.
+	 */
+	if (dspi->len > dspi->oper_word_size)
 		cmd |= SPI_PUSHR_CMD_CONT;
-	regmap_write(dspi->regmap_pushr, PUSHR_CMD, cmd);
+	regmap_write(dspi->regmap_pushr, dspi->pushr_cmd, cmd);
 }
 
-static void tx_fifo_write(struct fsl_dspi *dspi, u16 txdata)
+static void dspi_pushr_txdata_write(struct fsl_dspi *dspi, u16 txdata)
 {
-	regmap_write(dspi->regmap_pushr, PUSHR_TX, txdata);
+	regmap_write(dspi->regmap_pushr, dspi->pushr_tx, txdata);
 }
 
-static void dspi_tcfq_write(struct fsl_dspi *dspi)
+static void dspi_xspi_fifo_write(struct fsl_dspi *dspi, int num_words)
 {
-	/* Clear transfer count */
-	dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
+	int num_bytes = num_words * dspi->oper_word_size;
+	u16 tx_cmd = dspi->tx_cmd;
 
-	if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) {
-		/* Write the CMD FIFO entry first, and then the two
-		 * corresponding TX FIFO entries.
-		 */
-		u32 data = dspi_pop_tx(dspi);
+	/*
+	 * If the PCS needs to de-assert (i.e. we're at the end of the buffer
+	 * and cs_change does not want the PCS to stay on), then we need a new
+	 * PUSHR command, since this one (for the body of the buffer)
+	 * necessarily has the CONT bit set.
+	 * So send one word less during this go, to force a split and a command
+	 * with a single word next time, when CONT will be unset.
+	 */
+	if (!(dspi->tx_cmd & SPI_PUSHR_CMD_CONT) && num_bytes == dspi->len)
+		tx_cmd |= SPI_PUSHR_CMD_EOQ;
 
-		cmd_fifo_write(dspi);
-		tx_fifo_write(dspi, data & 0xFFFF);
-		tx_fifo_write(dspi, data >> 16);
-	} else {
-		/* Write one entry to both TX FIFO and CMD FIFO
-		 * simultaneously.
-		 */
-		fifo_write(dspi);
-	}
-}
+	/* Update CTARE */
+	regmap_write(dspi->regmap, SPI_CTARE(0),
+		     SPI_FRAME_EBITS(dspi->oper_bits_per_word) |
+		     SPI_CTARE_DTCP(num_words));
 
-static u32 fifo_read(struct fsl_dspi *dspi)
-{
-	u32 rxdata = 0;
+	/*
+	 * Write the CMD FIFO entry first, and then the two
+	 * corresponding TX FIFO entries (or one...).
+	 */
+	dspi_pushr_cmd_write(dspi, tx_cmd);
 
-	regmap_read(dspi->regmap, SPI_POPR, &rxdata);
-	return rxdata;
-}
+	/* Fill TX FIFO with as many transfers as possible */
+	while (num_words--) {
+		u32 data = dspi_pop_tx(dspi);
 
-static void dspi_tcfq_read(struct fsl_dspi *dspi)
-{
-	dspi_push_rx(dspi, fifo_read(dspi));
+		dspi_pushr_txdata_write(dspi, data & 0xFFFF);
+		if (dspi->oper_bits_per_word > 16)
+			dspi_pushr_txdata_write(dspi, data >> 16);
+	}
 }
 
-static void dspi_eoq_write(struct fsl_dspi *dspi)
+static void dspi_eoq_fifo_write(struct fsl_dspi *dspi, int num_words)
 {
-	int fifo_size = DSPI_FIFO_SIZE;
 	u16 xfer_cmd = dspi->tx_cmd;
 
 	/* Fill TX FIFO with as many transfers as possible */
-	while (dspi->len && fifo_size--) {
+	while (num_words--) {
 		dspi->tx_cmd = xfer_cmd;
 		/* Request EOQF for last transfer in FIFO */
-		if (dspi->len == dspi->bytes_per_word || fifo_size == 0)
+		if (num_words == 0)
 			dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ;
-		/* Clear transfer count for first transfer in FIFO */
-		if (fifo_size == (DSPI_FIFO_SIZE - 1))
-			dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
 		/* Write combined TX FIFO and CMD FIFO entry */
-		fifo_write(dspi);
+		dspi_pushr_write(dspi);
 	}
 }
 
-static void dspi_eoq_read(struct fsl_dspi *dspi)
+static u32 dspi_popr_read(struct fsl_dspi *dspi)
 {
-	int fifo_size = DSPI_FIFO_SIZE;
+	u32 rxdata = 0;
+
+	regmap_read(dspi->regmap, SPI_POPR, &rxdata);
+	return rxdata;
+}
+
+static void dspi_fifo_read(struct fsl_dspi *dspi)
+{
+	int num_fifo_entries = dspi->words_in_flight;
 
 	/* Read one FIFO entry and push to rx buffer */
-	while ((dspi->rx < dspi->rx_end) && fifo_size--)
-		dspi_push_rx(dspi, fifo_read(dspi));
+	while (num_fifo_entries--)
+		dspi_push_rx(dspi, dspi_popr_read(dspi));
 }
 
-static int dspi_rxtx(struct fsl_dspi *dspi)
+static void dspi_setup_accel(struct fsl_dspi *dspi)
 {
+	struct spi_transfer *xfer = dspi->cur_transfer;
+	bool odd = !!(dspi->len & 1);
+
+	/* No accel for frames not multiple of 8 bits at the moment */
+	if (xfer->bits_per_word % 8)
+		goto no_accel;
+
+	if (!odd && dspi->len <= dspi->devtype_data->fifo_size * 2) {
+		dspi->oper_bits_per_word = 16;
+	} else if (odd && dspi->len <= dspi->devtype_data->fifo_size) {
+		dspi->oper_bits_per_word = 8;
+	} else {
+		/* Start off with maximum supported by hardware */
+		if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
+			dspi->oper_bits_per_word = 32;
+		else
+			dspi->oper_bits_per_word = 16;
+
+		/*
+		 * And go down only if the buffer can't be sent with
+		 * words this big
+		 */
+		do {
+			if (dspi->len >= DIV_ROUND_UP(dspi->oper_bits_per_word, 8))
+				break;
+
+			dspi->oper_bits_per_word /= 2;
+		} while (dspi->oper_bits_per_word > 8);
+	}
+
+	if (xfer->bits_per_word == 8 && dspi->oper_bits_per_word == 32) {
+		dspi->dev_to_host = dspi_8on32_dev_to_host;
+		dspi->host_to_dev = dspi_8on32_host_to_dev;
+	} else if (xfer->bits_per_word == 8 && dspi->oper_bits_per_word == 16) {
+		dspi->dev_to_host = dspi_8on16_dev_to_host;
+		dspi->host_to_dev = dspi_8on16_host_to_dev;
+	} else if (xfer->bits_per_word == 16 && dspi->oper_bits_per_word == 32) {
+		dspi->dev_to_host = dspi_16on32_dev_to_host;
+		dspi->host_to_dev = dspi_16on32_host_to_dev;
+	} else {
+no_accel:
+		dspi->dev_to_host = dspi_native_dev_to_host;
+		dspi->host_to_dev = dspi_native_host_to_dev;
+		dspi->oper_bits_per_word = xfer->bits_per_word;
+	}
+
+	dspi->oper_word_size = DIV_ROUND_UP(dspi->oper_bits_per_word, 8);
+
+	/*
+	 * Update CTAR here (code is common for EOQ, XSPI and DMA modes).
+	 * We will update CTARE in the portion specific to XSPI, when we
+	 * also know the preload value (DTCP).
+	 */
+	regmap_write(dspi->regmap, SPI_CTAR(0),
+		     dspi->cur_chip->ctar_val |
+		     SPI_FRAME_BITS(dspi->oper_bits_per_word));
+}
+
+static void dspi_fifo_write(struct fsl_dspi *dspi)
+{
+	int num_fifo_entries = dspi->devtype_data->fifo_size;
+	struct spi_transfer *xfer = dspi->cur_transfer;
 	struct spi_message *msg = dspi->cur_msg;
-	enum dspi_trans_mode trans_mode;
-	u16 spi_tcnt;
-	u32 spi_tcr;
+	int num_words, num_bytes;
 
-	spi_take_timestamp_post(dspi->ctlr, dspi->cur_transfer,
-				dspi->progress, !dspi->irq);
+	dspi_setup_accel(dspi);
+
+	/* In XSPI mode each 32-bit word occupies 2 TX FIFO entries */
+	if (dspi->oper_word_size == 4)
+		num_fifo_entries /= 2;
 
-	/* Get transfer counter (in number of SPI transfers). It was
-	 * reset to 0 when transfer(s) were started.
+	/*
+	 * Integer division intentionally trims off odd (or non-multiple of 4)
+	 * numbers of bytes at the end of the buffer, which will be sent next
+	 * time using a smaller oper_word_size.
 	 */
-	regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
-	spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
+	num_words = dspi->len / dspi->oper_word_size;
+	if (num_words > num_fifo_entries)
+		num_words = num_fifo_entries;
+
 	/* Update total number of bytes that were transferred */
-	msg->actual_length += spi_tcnt * dspi->bytes_per_word;
-	dspi->progress += spi_tcnt;
+	num_bytes = num_words * dspi->oper_word_size;
+	msg->actual_length += num_bytes;
+	dspi->progress += num_bytes / DIV_ROUND_UP(xfer->bits_per_word, 8);
 
-	trans_mode = dspi->devtype_data->trans_mode;
-	if (trans_mode == DSPI_EOQ_MODE)
-		dspi_eoq_read(dspi);
-	else if (trans_mode == DSPI_TCFQ_MODE)
-		dspi_tcfq_read(dspi);
+	/*
+	 * Update shared variable for use in the next interrupt (both in
+	 * dspi_fifo_read and in dspi_fifo_write).
+	 */
+	dspi->words_in_flight = num_words;
+
+	spi_take_timestamp_pre(dspi->ctlr, xfer, dspi->progress, !dspi->irq);
+
+	if (dspi->devtype_data->trans_mode == DSPI_EOQ_MODE)
+		dspi_eoq_fifo_write(dspi, num_words);
+	else
+		dspi_xspi_fifo_write(dspi, num_words);
+	/*
+	 * Everything after this point is in a potential race with the next
+	 * interrupt, so we must never use dspi->words_in_flight again since it
+	 * might already be modified by the next dspi_fifo_write.
+	 */
+
+	spi_take_timestamp_post(dspi->ctlr, dspi->cur_transfer,
+				dspi->progress, !dspi->irq);
+}
+
+static int dspi_rxtx(struct fsl_dspi *dspi)
+{
+	dspi_fifo_read(dspi);
 
 	if (!dspi->len)
 		/* Success! */
 		return 0;
 
-	spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer,
-			       dspi->progress, !dspi->irq);
-
-	if (trans_mode == DSPI_EOQ_MODE)
-		dspi_eoq_write(dspi);
-	else if (trans_mode == DSPI_TCFQ_MODE)
-		dspi_tcfq_write(dspi);
+	dspi_fifo_write(dspi);
 
 	return -EINPROGRESS;
 }
@@ -693,7 +874,7 @@ static int dspi_poll(struct fsl_dspi *dspi)
 		regmap_read(dspi->regmap, SPI_SR, &spi_sr);
 		regmap_write(dspi->regmap, SPI_SR, spi_sr);
 
-		if (spi_sr & (SPI_SR_EOQF | SPI_SR_TCFQF))
+		if (spi_sr & (SPI_SR_EOQF | SPI_SR_CMDTCF))
 			break;
 	} while (--tries);
 
@@ -711,13 +892,11 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 	regmap_read(dspi->regmap, SPI_SR, &spi_sr);
 	regmap_write(dspi->regmap, SPI_SR, spi_sr);
 
-	if (!(spi_sr & SPI_SR_EOQF))
+	if (!(spi_sr & (SPI_SR_EOQF | SPI_SR_CMDTCF)))
 		return IRQ_NONE;
 
-	if (dspi_rxtx(dspi) == 0) {
-		dspi->waitflags = 1;
-		wake_up_interruptible(&dspi->waitq);
-	}
+	if (dspi_rxtx(dspi) == 0)
+		complete(&dspi->xfer_done);
 
 	return IRQ_HANDLED;
 }
@@ -727,7 +906,6 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 {
 	struct fsl_dspi *dspi = spi_controller_get_devdata(ctlr);
 	struct spi_device *spi = message->spi;
-	enum dspi_trans_mode trans_mode;
 	struct spi_transfer *transfer;
 	int status = 0;
 
@@ -757,76 +935,38 @@ static int dspi_transfer_one_message(struct spi_controller *ctlr,
 				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
 		}
 
-		dspi->void_write_data = dspi->cur_chip->void_write_data;
-
 		dspi->tx = transfer->tx_buf;
 		dspi->rx = transfer->rx_buf;
-		dspi->rx_end = dspi->rx + transfer->len;
 		dspi->len = transfer->len;
 		dspi->progress = 0;
-		/* Validated transfer specific frame size (defaults applied) */
-		dspi->bits_per_word = transfer->bits_per_word;
-		if (transfer->bits_per_word <= 8)
-			dspi->bytes_per_word = 1;
-		else if (transfer->bits_per_word <= 16)
-			dspi->bytes_per_word = 2;
-		else
-			dspi->bytes_per_word = 4;
 
 		regmap_update_bits(dspi->regmap, SPI_MCR,
 				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
 				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
-		regmap_write(dspi->regmap, SPI_CTAR(0),
-			     dspi->cur_chip->ctar_val |
-			     SPI_FRAME_BITS(transfer->bits_per_word));
-		if (dspi->devtype_data->xspi_mode)
-			regmap_write(dspi->regmap, SPI_CTARE(0),
-				     SPI_FRAME_EBITS(transfer->bits_per_word) |
-				     SPI_CTARE_DTCP(1));
 
 		spi_take_timestamp_pre(dspi->ctlr, dspi->cur_transfer,
 				       dspi->progress, !dspi->irq);
 
-		trans_mode = dspi->devtype_data->trans_mode;
-		switch (trans_mode) {
-		case DSPI_EOQ_MODE:
-			regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_EOQFE);
-			dspi_eoq_write(dspi);
-			break;
-		case DSPI_TCFQ_MODE:
-			regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_TCFQE);
-			dspi_tcfq_write(dspi);
-			break;
-		case DSPI_DMA_MODE:
-			regmap_write(dspi->regmap, SPI_RSER,
-				     SPI_RSER_TFFFE | SPI_RSER_TFFFD |
-				     SPI_RSER_RFDFE | SPI_RSER_RFDFD);
+		if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
 			status = dspi_dma_xfer(dspi);
-			break;
-		default:
-			dev_err(&dspi->pdev->dev, "unsupported trans_mode %u\n",
-				trans_mode);
-			status = -EINVAL;
-			goto out;
-		}
-
-		if (!dspi->irq) {
-			do {
-				status = dspi_poll(dspi);
-			} while (status == -EINPROGRESS);
-		} else if (trans_mode != DSPI_DMA_MODE) {
-			status = wait_event_interruptible(dspi->waitq,
-							  dspi->waitflags);
-			dspi->waitflags = 0;
+		} else {
+			dspi_fifo_write(dspi);
+
+			if (dspi->irq) {
+				wait_for_completion(&dspi->xfer_done);
+				reinit_completion(&dspi->xfer_done);
+			} else {
+				do {
+					status = dspi_poll(dspi);
+				} while (status == -EINPROGRESS);
+			}
 		}
 		if (status)
-			dev_err(&dspi->pdev->dev,
-				"Waiting for transfer to complete failed!\n");
+			break;
 
 		spi_transfer_delay_exec(transfer);
 	}
 
-out:
 	message->status = status;
 	spi_finalize_current_message(ctlr);
 
@@ -864,8 +1004,6 @@ static int dspi_setup(struct spi_device *spi)
 		sck_cs_delay = pdata->sck_cs_delay;
 	}
 
-	chip->void_write_data = 0;
-
 	clkrate = clk_get_rate(dspi->clk);
 	hz_to_spi_baud(&pbr, &br, spi->max_speed_hz, clkrate);
 
@@ -909,9 +1047,34 @@ static void dspi_cleanup(struct spi_device *spi)
 }
 
 static const struct of_device_id fsl_dspi_dt_ids[] = {
-	{ .compatible = "fsl,vf610-dspi", .data = &vf610_data, },
-	{ .compatible = "fsl,ls1021a-v1.0-dspi", .data = &ls1021a_v1_data, },
-	{ .compatible = "fsl,ls2085a-dspi", .data = &ls2085a_data, },
+	{
+		.compatible = "fsl,vf610-dspi",
+		.data = &devtype_data[VF610],
+	}, {
+		.compatible = "fsl,ls1021a-v1.0-dspi",
+		.data = &devtype_data[LS1021A],
+	}, {
+		.compatible = "fsl,ls1012a-dspi",
+		.data = &devtype_data[LS1012A],
+	}, {
+		.compatible = "fsl,ls1028a-dspi",
+		.data = &devtype_data[LS1028A],
+	}, {
+		.compatible = "fsl,ls1043a-dspi",
+		.data = &devtype_data[LS1043A],
+	}, {
+		.compatible = "fsl,ls1046a-dspi",
+		.data = &devtype_data[LS1046A],
+	}, {
+		.compatible = "fsl,ls2080a-dspi",
+		.data = &devtype_data[LS2080A],
+	}, {
+		.compatible = "fsl,ls2085a-dspi",
+		.data = &devtype_data[LS2085A],
+	}, {
+		.compatible = "fsl,lx2160a-dspi",
+		.data = &devtype_data[LX2160A],
+	},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, fsl_dspi_dt_ids);
@@ -997,20 +1160,40 @@ static const struct regmap_config dspi_xspi_regmap_config[] = {
 	},
 };
 
-static void dspi_init(struct fsl_dspi *dspi)
+static int dspi_init(struct fsl_dspi *dspi)
 {
-	unsigned int mcr = SPI_MCR_PCSIS;
+	unsigned int mcr;
+
+	/* Set idle states for all chip select signals to high */
+	mcr = SPI_MCR_PCSIS(GENMASK(dspi->ctlr->num_chipselect - 1, 0));
 
-	if (dspi->devtype_data->xspi_mode)
+	if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
 		mcr |= SPI_MCR_XSPI;
 	if (!spi_controller_is_slave(dspi->ctlr))
 		mcr |= SPI_MCR_MASTER;
 
 	regmap_write(dspi->regmap, SPI_MCR, mcr);
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
-	if (dspi->devtype_data->xspi_mode)
-		regmap_write(dspi->regmap, SPI_CTARE(0),
-			     SPI_CTARE_FMSZE(0) | SPI_CTARE_DTCP(1));
+
+	switch (dspi->devtype_data->trans_mode) {
+	case DSPI_EOQ_MODE:
+		regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_EOQFE);
+		break;
+	case DSPI_XSPI_MODE:
+		regmap_write(dspi->regmap, SPI_RSER, SPI_RSER_CMDTCFE);
+		break;
+	case DSPI_DMA_MODE:
+		regmap_write(dspi->regmap, SPI_RSER,
+			     SPI_RSER_TFFFE | SPI_RSER_TFFFD |
+			     SPI_RSER_RFDFE | SPI_RSER_RFDFD);
+		break;
+	default:
+		dev_err(&dspi->pdev->dev, "unsupported trans_mode %u\n",
+			dspi->devtype_data->trans_mode);
+		return -EINVAL;
+	}
+
+	return 0;
 }
 
 static int dspi_slave_abort(struct spi_master *master)
@@ -1021,8 +1204,10 @@ static int dspi_slave_abort(struct spi_master *master)
 	 * Terminate all pending DMA transactions for the SPI working
 	 * in SLAVE mode.
 	 */
-	dmaengine_terminate_sync(dspi->dma->chan_rx);
-	dmaengine_terminate_sync(dspi->dma->chan_tx);
+	if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
+		dmaengine_terminate_sync(dspi->dma->chan_rx);
+		dmaengine_terminate_sync(dspi->dma->chan_tx);
+	}
 
 	/* Clear the internal DSPI RX and TX FIFO buffers */
 	regmap_update_bits(dspi->regmap, SPI_MCR,
@@ -1032,16 +1217,33 @@ static int dspi_slave_abort(struct spi_master *master)
 	return 0;
 }
 
+/*
+ * EOQ mode will inevitably deassert its PCS signal on last word in a queue
+ * (hardware limitation), so we need to inform the spi_device that larger
+ * buffers than the FIFO size are going to have the chip select randomly
+ * toggling, so it has a chance to adapt its message sizes.
+ */
+static size_t dspi_max_message_size(struct spi_device *spi)
+{
+	struct fsl_dspi *dspi = spi_controller_get_devdata(spi->controller);
+
+	if (dspi->devtype_data->trans_mode == DSPI_EOQ_MODE)
+		return dspi->devtype_data->fifo_size;
+
+	return SIZE_MAX;
+}
+
 static int dspi_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node;
 	const struct regmap_config *regmap_config;
 	struct fsl_dspi_platform_data *pdata;
 	struct spi_controller *ctlr;
-	int ret, cs_num, bus_num;
+	int ret, cs_num, bus_num = -1;
 	struct fsl_dspi *dspi;
 	struct resource *res;
 	void __iomem *base;
+	bool big_endian;
 
 	ctlr = spi_alloc_master(&pdev->dev, sizeof(struct fsl_dspi));
 	if (!ctlr)
@@ -1053,6 +1255,7 @@ static int dspi_probe(struct platform_device *pdev)
 
 	ctlr->setup = dspi_setup;
 	ctlr->transfer_one_message = dspi_transfer_one_message;
+	ctlr->max_message_size = dspi_max_message_size;
 	ctlr->dev.of_node = pdev->dev.of_node;
 
 	ctlr->cleanup = dspi_cleanup;
@@ -1064,7 +1267,9 @@ static int dspi_probe(struct platform_device *pdev)
 		ctlr->num_chipselect = pdata->cs_num;
 		ctlr->bus_num = pdata->bus_num;
 
-		dspi->devtype_data = &coldfire_data;
+		/* Only Coldfire uses platform data */
+		dspi->devtype_data = &devtype_data[MCF5441X];
+		big_endian = true;
 	} else {
 
 		ret = of_property_read_u32(np, "spi-num-chipselects", &cs_num);
@@ -1074,11 +1279,7 @@ static int dspi_probe(struct platform_device *pdev)
 		}
 		ctlr->num_chipselect = cs_num;
 
-		ret = of_property_read_u32(np, "bus-num", &bus_num);
-		if (ret < 0) {
-			dev_err(&pdev->dev, "can't get bus-num\n");
-			goto out_ctlr_put;
-		}
+		of_property_read_u32(np, "bus-num", &bus_num);
 		ctlr->bus_num = bus_num;
 
 		if (of_property_read_bool(np, "spi-slave"))
@@ -1090,9 +1291,18 @@ static int dspi_probe(struct platform_device *pdev)
 			ret = -EFAULT;
 			goto out_ctlr_put;
 		}
+
+		big_endian = of_device_is_big_endian(np);
+	}
+	if (big_endian) {
+		dspi->pushr_cmd = 0;
+		dspi->pushr_tx = 2;
+	} else {
+		dspi->pushr_cmd = 2;
+		dspi->pushr_tx = 0;
 	}
 
-	if (dspi->devtype_data->xspi_mode)
+	if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
 		ctlr->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	else
 		ctlr->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
@@ -1104,7 +1314,7 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_ctlr_put;
 	}
 
-	if (dspi->devtype_data->xspi_mode)
+	if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE)
 		regmap_config = &dspi_xspi_regmap_config[0];
 	else
 		regmap_config = &dspi_regmap_config;
@@ -1116,7 +1326,7 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_ctlr_put;
 	}
 
-	if (dspi->devtype_data->xspi_mode) {
+	if (dspi->devtype_data->trans_mode == DSPI_XSPI_MODE) {
 		dspi->regmap_pushr = devm_regmap_init_mmio(
 			&pdev->dev, base + SPI_PUSHR,
 			&dspi_xspi_regmap_config[1]);
@@ -1139,10 +1349,9 @@ static int dspi_probe(struct platform_device *pdev)
 	if (ret)
 		goto out_ctlr_put;
 
-	dspi_init(dspi);
-
-	if (dspi->devtype_data->trans_mode == DSPI_TCFQ_MODE)
-		goto poll_mode;
+	ret = dspi_init(dspi);
+	if (ret)
+		goto out_clk_put;
 
 	dspi->irq = platform_get_irq(pdev, 0);
 	if (dspi->irq <= 0) {
@@ -1159,7 +1368,7 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_clk_put;
 	}
 
-	init_waitqueue_head(&dspi->waitq);
+	init_completion(&dspi->xfer_done);
 
 poll_mode:
 
@@ -1174,7 +1383,8 @@ poll_mode:
 	ctlr->max_speed_hz =
 		clk_get_rate(dspi->clk) / dspi->devtype_data->max_clock_factor;
 
-	ctlr->ptp_sts_supported = dspi->devtype_data->ptp_sts_supported;
+	if (dspi->devtype_data->trans_mode != DSPI_DMA_MODE)
+		ctlr->ptp_sts_supported = true;
 
 	platform_set_drvdata(pdev, ctlr);
 
diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
index d0b8cc741a24..8b41b70f6f5c 100644
--- a/drivers/spi/spi-fsl-lpspi.c
+++ b/drivers/spi/spi-fsl-lpspi.c
@@ -86,8 +86,6 @@
 #define TCR_RXMSK	BIT(19)
 #define TCR_TXMSK	BIT(18)
 
-static int clkdivs[] = {1, 2, 4, 8, 16, 32, 64, 128};
-
 struct lpspi_config {
 	u8 bpw;
 	u8 chip_select;
@@ -125,7 +123,7 @@ struct fsl_lpspi_data {
 	struct completion dma_rx_completion;
 	struct completion dma_tx_completion;
 
-	int chipselect[0];
+	int chipselect[];
 };
 
 static const struct of_device_id fsl_lpspi_dt_ids[] = {
@@ -331,15 +329,14 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
 	}
 
 	for (prescale = 0; prescale < 8; prescale++) {
-		scldiv = perclk_rate /
-			 (clkdivs[prescale] * config.speed_hz) - 2;
+		scldiv = perclk_rate / config.speed_hz / (1 << prescale) - 2;
 		if (scldiv < 256) {
 			fsl_lpspi->config.prescale = prescale;
 			break;
 		}
 	}
 
-	if (prescale == 8 && scldiv >= 256)
+	if (scldiv >= 256)
 		return -EINVAL;
 
 	writel(scldiv | (scldiv << 8) | ((scldiv >> 1) << 16),
diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
index 6f3d64a1a2b3..c3972424af71 100644
--- a/drivers/spi/spi-geni-qcom.c
+++ b/drivers/spi/spi-geni-qcom.c
@@ -6,7 +6,6 @@
 #include <linux/io.h>
 #include <linux/log2.h>
 #include <linux/module.h>
-#include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/qcom-geni-se.h>
@@ -536,6 +535,7 @@ static int spi_geni_probe(struct platform_device *pdev)
 	struct spi_geni_master *mas;
 	void __iomem *base;
 	struct clk *clk;
+	struct device *dev = &pdev->dev;
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0)
@@ -545,28 +545,25 @@ static int spi_geni_probe(struct platform_device *pdev)
 	if (IS_ERR(base))
 		return PTR_ERR(base);
 
-	clk = devm_clk_get(&pdev->dev, "se");
-	if (IS_ERR(clk)) {
-		dev_err(&pdev->dev, "Err getting SE Core clk %ld\n",
-						PTR_ERR(clk));
+	clk = devm_clk_get(dev, "se");
+	if (IS_ERR(clk))
 		return PTR_ERR(clk);
-	}
 
-	spi = spi_alloc_master(&pdev->dev, sizeof(*mas));
+	spi = spi_alloc_master(dev, sizeof(*mas));
 	if (!spi)
 		return -ENOMEM;
 
 	platform_set_drvdata(pdev, spi);
 	mas = spi_master_get_devdata(spi);
 	mas->irq = irq;
-	mas->dev = &pdev->dev;
-	mas->se.dev = &pdev->dev;
-	mas->se.wrapper = dev_get_drvdata(pdev->dev.parent);
+	mas->dev = dev;
+	mas->se.dev = dev;
+	mas->se.wrapper = dev_get_drvdata(dev->parent);
 	mas->se.base = base;
 	mas->se.clk = clk;
 
 	spi->bus_num = -1;
-	spi->dev.of_node = pdev->dev.of_node;
+	spi->dev.of_node = dev->of_node;
 	spi->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LOOP | SPI_CS_HIGH;
 	spi->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
 	spi->num_chipselect = 4;
@@ -579,14 +576,13 @@ static int spi_geni_probe(struct platform_device *pdev)
 
 	init_completion(&mas->xfer_done);
 	spin_lock_init(&mas->lock);
-	pm_runtime_enable(&pdev->dev);
+	pm_runtime_enable(dev);
 
 	ret = spi_geni_init(mas);
 	if (ret)
 		goto spi_geni_probe_runtime_disable;
 
-	ret = request_irq(mas->irq, geni_spi_isr,
-			IRQF_TRIGGER_HIGH, "spi_geni", spi);
+	ret = request_irq(mas->irq, geni_spi_isr, 0, dev_name(dev), spi);
 	if (ret)
 		goto spi_geni_probe_runtime_disable;
 
@@ -598,7 +594,7 @@ static int spi_geni_probe(struct platform_device *pdev)
 spi_geni_probe_free_irq:
 	free_irq(mas->irq, spi);
 spi_geni_probe_runtime_disable:
-	pm_runtime_disable(&pdev->dev);
+	pm_runtime_disable(dev);
 	spi_master_put(spi);
 	return ret;
 }
diff --git a/drivers/spi/spi-hisi-sfc-v3xx.c b/drivers/spi/spi-hisi-sfc-v3xx.c
index 4cf8fc80a7b7..e3b57252d075 100644
--- a/drivers/spi/spi-hisi-sfc-v3xx.c
+++ b/drivers/spi/spi-hisi-sfc-v3xx.c
@@ -7,6 +7,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bitops.h>
+#include <linux/dmi.h>
 #include <linux/iopoll.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
@@ -17,6 +18,12 @@
 #define HISI_SFC_V3XX_VERSION (0x1f8)
 
 #define HISI_SFC_V3XX_CMD_CFG (0x300)
+#define HISI_SFC_V3XX_CMD_CFG_DUAL_IN_DUAL_OUT (1 << 17)
+#define HISI_SFC_V3XX_CMD_CFG_DUAL_IO (2 << 17)
+#define HISI_SFC_V3XX_CMD_CFG_FULL_DIO (3 << 17)
+#define HISI_SFC_V3XX_CMD_CFG_QUAD_IN_QUAD_OUT (5 << 17)
+#define HISI_SFC_V3XX_CMD_CFG_QUAD_IO (6 << 17)
+#define HISI_SFC_V3XX_CMD_CFG_FULL_QIO (7 << 17)
 #define HISI_SFC_V3XX_CMD_CFG_DATA_CNT_OFF 9
 #define HISI_SFC_V3XX_CMD_CFG_RW_MSK BIT(8)
 #define HISI_SFC_V3XX_CMD_CFG_DATA_EN_MSK BIT(7)
@@ -161,6 +168,43 @@ static int hisi_sfc_v3xx_generic_exec_op(struct hisi_sfc_v3xx_host *host,
 	if (op->addr.nbytes)
 		config |= HISI_SFC_V3XX_CMD_CFG_ADDR_EN_MSK;
 
+	switch (op->data.buswidth) {
+	case 0 ... 1:
+		break;
+	case 2:
+		if (op->addr.buswidth <= 1) {
+			config |= HISI_SFC_V3XX_CMD_CFG_DUAL_IN_DUAL_OUT;
+		} else if (op->addr.buswidth == 2) {
+			if (op->cmd.buswidth <= 1) {
+				config |= HISI_SFC_V3XX_CMD_CFG_DUAL_IO;
+			} else if (op->cmd.buswidth == 2) {
+				config |= HISI_SFC_V3XX_CMD_CFG_FULL_DIO;
+			} else {
+				return -EIO;
+			}
+		} else {
+			return -EIO;
+		}
+		break;
+	case 4:
+		if (op->addr.buswidth <= 1) {
+			config |= HISI_SFC_V3XX_CMD_CFG_QUAD_IN_QUAD_OUT;
+		} else if (op->addr.buswidth == 4) {
+			if (op->cmd.buswidth <= 1) {
+				config |= HISI_SFC_V3XX_CMD_CFG_QUAD_IO;
+			} else if (op->cmd.buswidth == 4) {
+				config |= HISI_SFC_V3XX_CMD_CFG_FULL_QIO;
+			} else {
+				return -EIO;
+			}
+		} else {
+			return -EIO;
+		}
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	if (op->data.dir != SPI_MEM_NO_DATA) {
 		config |= (len - 1) << HISI_SFC_V3XX_CMD_CFG_DATA_CNT_OFF;
 		config |= HISI_SFC_V3XX_CMD_CFG_DATA_EN_MSK;
@@ -207,6 +251,44 @@ static const struct spi_controller_mem_ops hisi_sfc_v3xx_mem_ops = {
 	.exec_op = hisi_sfc_v3xx_exec_op,
 };
 
+static int hisi_sfc_v3xx_buswidth_override_bits;
+
+/*
+ * ACPI FW does not allow us to currently set the device buswidth, so quirk it
+ * depending on the board.
+ */
+static int __init hisi_sfc_v3xx_dmi_quirk(const struct dmi_system_id *d)
+{
+	hisi_sfc_v3xx_buswidth_override_bits = SPI_RX_QUAD | SPI_TX_QUAD;
+
+	return 0;
+}
+
+static const struct dmi_system_id hisi_sfc_v3xx_dmi_quirk_table[]  = {
+	{
+	.callback = hisi_sfc_v3xx_dmi_quirk,
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Huawei"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "D06"),
+	},
+	},
+	{
+	.callback = hisi_sfc_v3xx_dmi_quirk,
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Huawei"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "TaiShan 2280 V2"),
+	},
+	},
+	{
+	.callback = hisi_sfc_v3xx_dmi_quirk,
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "Huawei"),
+		DMI_MATCH(DMI_PRODUCT_NAME, "TaiShan 200 (Model 2280)"),
+	},
+	},
+	{}
+};
+
 static int hisi_sfc_v3xx_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -222,6 +304,8 @@ static int hisi_sfc_v3xx_probe(struct platform_device *pdev)
 	ctlr->mode_bits = SPI_RX_DUAL | SPI_RX_QUAD |
 			  SPI_TX_DUAL | SPI_TX_QUAD;
 
+	ctlr->buswidth_override_bits = hisi_sfc_v3xx_buswidth_override_bits;
+
 	host = spi_controller_get_devdata(ctlr);
 	host->dev = dev;
 
@@ -277,7 +361,20 @@ static struct platform_driver hisi_sfc_v3xx_spi_driver = {
 	.probe	= hisi_sfc_v3xx_probe,
 };
 
-module_platform_driver(hisi_sfc_v3xx_spi_driver);
+static int __init hisi_sfc_v3xx_spi_init(void)
+{
+	dmi_check_system(hisi_sfc_v3xx_dmi_quirk_table);
+
+	return platform_driver_register(&hisi_sfc_v3xx_spi_driver);
+}
+
+static void __exit hisi_sfc_v3xx_spi_exit(void)
+{
+	platform_driver_unregister(&hisi_sfc_v3xx_spi_driver);
+}
+
+module_init(hisi_sfc_v3xx_spi_init);
+module_exit(hisi_sfc_v3xx_spi_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("John Garry <john.garry@huawei.com>");
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index e5a46f0eb93b..adaa0c49f966 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -418,12 +418,13 @@ int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
 	struct spi_controller *ctlr = mem->spi->controller;
 	size_t len;
 
-	len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
-
 	if (ctlr->mem_ops && ctlr->mem_ops->adjust_op_size)
 		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;
+
 		if (len > spi_max_transfer_size(mem->spi))
 			return -EINVAL;
 
@@ -487,7 +488,7 @@ static ssize_t spi_mem_no_dirmap_write(struct spi_mem_dirmap_desc *desc,
  * This function is creating a direct mapping descriptor which can then be used
  * to access the memory using spi_mem_dirmap_read() or spi_mem_dirmap_write().
  * If the SPI controller driver does not support direct mapping, this function
- * fallback to an implementation using spi_mem_exec_op(), so that the caller
+ * falls back to an implementation using spi_mem_exec_op(), so that the caller
  * doesn't have to bother implementing a fallback on his own.
  *
  * Return: a valid pointer in case of success, and ERR_PTR() otherwise.
diff --git a/drivers/spi/spi-meson-spicc.c b/drivers/spi/spi-meson-spicc.c
index 7f5680fe2568..77f7d0e0e46a 100644
--- a/drivers/spi/spi-meson-spicc.c
+++ b/drivers/spi/spi-meson-spicc.c
@@ -9,11 +9,13 @@
 
 #include <linux/bitfield.h>
 #include <linux/clk.h>
+#include <linux/clk-provider.h>
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 #include <linux/types.h>
@@ -33,7 +35,6 @@
  *   to have a CS go down over the full transfer
  */
 
-#define SPICC_MAX_FREQ	30000000
 #define SPICC_MAX_BURST	128
 
 /* Register Map */
@@ -105,7 +106,21 @@
 #define SPICC_SWAP_RO		BIT(14) /* RX FIFO Data Swap Read-Only */
 #define SPICC_SWAP_W1		BIT(15) /* RX FIFO Data Swap Write-Only */
 #define SPICC_DLYCTL_RO_MASK	GENMASK(20, 15) /* Delay Control Read-Only */
-#define SPICC_DLYCTL_W1_MASK	GENMASK(21, 16) /* Delay Control Write-Only */
+#define SPICC_MO_DELAY_MASK	GENMASK(17, 16) /* Master Output Delay */
+#define SPICC_MO_NO_DELAY	0
+#define SPICC_MO_DELAY_1_CYCLE	1
+#define SPICC_MO_DELAY_2_CYCLE	2
+#define SPICC_MO_DELAY_3_CYCLE	3
+#define SPICC_MI_DELAY_MASK	GENMASK(19, 18) /* Master Input Delay */
+#define SPICC_MI_NO_DELAY	0
+#define SPICC_MI_DELAY_1_CYCLE	1
+#define SPICC_MI_DELAY_2_CYCLE	2
+#define SPICC_MI_DELAY_3_CYCLE	3
+#define SPICC_MI_CAP_DELAY_MASK	GENMASK(21, 20) /* Master Capture Delay */
+#define SPICC_CAP_AHEAD_2_CYCLE	0
+#define SPICC_CAP_AHEAD_1_CYCLE	1
+#define SPICC_CAP_NO_DELAY	2
+#define SPICC_CAP_DELAY_1_CYCLE	3
 #define SPICC_FIFORST_RO_MASK	GENMASK(22, 21) /* FIFO Softreset Read-Only */
 #define SPICC_FIFORST_W1_MASK	GENMASK(23, 22) /* FIFO Softreset Write-Only */
 
@@ -113,31 +128,59 @@
 
 #define SPICC_DWADDR	0x24	/* Write Address of DMA */
 
+#define SPICC_ENH_CTL0	0x38	/* Enhanced Feature */
+#define SPICC_ENH_CLK_CS_DELAY_MASK	GENMASK(15, 0)
+#define SPICC_ENH_DATARATE_MASK		GENMASK(23, 16)
+#define SPICC_ENH_DATARATE_EN		BIT(24)
+#define SPICC_ENH_MOSI_OEN		BIT(25)
+#define SPICC_ENH_CLK_OEN		BIT(26)
+#define SPICC_ENH_CS_OEN		BIT(27)
+#define SPICC_ENH_CLK_CS_DELAY_EN	BIT(28)
+#define SPICC_ENH_MAIN_CLK_AO		BIT(29)
+
 #define writel_bits_relaxed(mask, val, addr) \
 	writel_relaxed((readl_relaxed(addr) & ~(mask)) | (val), addr)
 
-#define SPICC_BURST_MAX	16
-#define SPICC_FIFO_HALF 10
+struct meson_spicc_data {
+	unsigned int			max_speed_hz;
+	unsigned int			min_speed_hz;
+	unsigned int			fifo_size;
+	bool				has_oen;
+	bool				has_enhance_clk_div;
+	bool				has_pclk;
+};
 
 struct meson_spicc_device {
 	struct spi_master		*master;
 	struct platform_device		*pdev;
 	void __iomem			*base;
 	struct clk			*core;
+	struct clk			*pclk;
+	struct clk			*clk;
 	struct spi_message		*message;
 	struct spi_transfer		*xfer;
+	const struct meson_spicc_data	*data;
 	u8				*tx_buf;
 	u8				*rx_buf;
 	unsigned int			bytes_per_word;
 	unsigned long			tx_remain;
-	unsigned long			txb_remain;
 	unsigned long			rx_remain;
-	unsigned long			rxb_remain;
 	unsigned long			xfer_remain;
-	bool				is_burst_end;
-	bool				is_last_burst;
 };
 
+static void meson_spicc_oen_enable(struct meson_spicc_device *spicc)
+{
+	u32 conf;
+
+	if (!spicc->data->has_oen)
+		return;
+
+	conf = readl_relaxed(spicc->base + SPICC_ENH_CTL0) |
+		SPICC_ENH_MOSI_OEN | SPICC_ENH_CLK_OEN | SPICC_ENH_CS_OEN;
+
+	writel_relaxed(conf, spicc->base + SPICC_ENH_CTL0);
+}
+
 static inline bool meson_spicc_txfull(struct meson_spicc_device *spicc)
 {
 	return !!FIELD_GET(SPICC_TF,
@@ -146,7 +189,7 @@ static inline bool meson_spicc_txfull(struct meson_spicc_device *spicc)
 
 static inline bool meson_spicc_rxready(struct meson_spicc_device *spicc)
 {
-	return FIELD_GET(SPICC_RH | SPICC_RR | SPICC_RF_EN,
+	return FIELD_GET(SPICC_RH | SPICC_RR | SPICC_RF,
 			 readl_relaxed(spicc->base + SPICC_STATREG));
 }
 
@@ -201,34 +244,22 @@ static inline void meson_spicc_tx(struct meson_spicc_device *spicc)
 			       spicc->base + SPICC_TXDATA);
 }
 
-static inline u32 meson_spicc_setup_rx_irq(struct meson_spicc_device *spicc,
-					   u32 irq_ctrl)
+static inline void meson_spicc_setup_burst(struct meson_spicc_device *spicc)
 {
-	if (spicc->rx_remain > SPICC_FIFO_HALF)
-		irq_ctrl |= SPICC_RH_EN;
-	else
-		irq_ctrl |= SPICC_RR_EN;
-
-	return irq_ctrl;
-}
 
-static inline void meson_spicc_setup_burst(struct meson_spicc_device *spicc,
-					   unsigned int burst_len)
-{
+	unsigned int burst_len = min_t(unsigned int,
+				       spicc->xfer_remain /
+				       spicc->bytes_per_word,
+				       spicc->data->fifo_size);
 	/* Setup Xfer variables */
 	spicc->tx_remain = burst_len;
 	spicc->rx_remain = burst_len;
 	spicc->xfer_remain -= burst_len * spicc->bytes_per_word;
-	spicc->is_burst_end = false;
-	if (burst_len < SPICC_BURST_MAX || !spicc->xfer_remain)
-		spicc->is_last_burst = true;
-	else
-		spicc->is_last_burst = false;
 
 	/* Setup burst length */
 	writel_bits_relaxed(SPICC_BURSTLENGTH_MASK,
 			FIELD_PREP(SPICC_BURSTLENGTH_MASK,
-				burst_len),
+				burst_len - 1),
 			spicc->base + SPICC_CONREG);
 
 	/* Fill TX FIFO */
@@ -238,97 +269,71 @@ static inline void meson_spicc_setup_burst(struct meson_spicc_device *spicc,
 static irqreturn_t meson_spicc_irq(int irq, void *data)
 {
 	struct meson_spicc_device *spicc = (void *) data;
-	u32 ctrl = readl_relaxed(spicc->base + SPICC_INTREG);
-	u32 stat = readl_relaxed(spicc->base + SPICC_STATREG) & ctrl;
 
-	ctrl &= ~(SPICC_RH_EN | SPICC_RR_EN);
+	writel_bits_relaxed(SPICC_TC, SPICC_TC, spicc->base + SPICC_STATREG);
 
 	/* Empty RX FIFO */
 	meson_spicc_rx(spicc);
 
-	/* Enable TC interrupt since we transferred everything */
-	if (!spicc->tx_remain && !spicc->rx_remain) {
-		spicc->is_burst_end = true;
-
-		/* Enable TC interrupt */
-		ctrl |= SPICC_TC_EN;
+	if (!spicc->xfer_remain) {
+		/* Disable all IRQs */
+		writel(0, spicc->base + SPICC_INTREG);
 
-		/* Reload IRQ status */
-		stat = readl_relaxed(spicc->base + SPICC_STATREG) & ctrl;
-	}
-
-	/* Check transfer complete */
-	if ((stat & SPICC_TC) && spicc->is_burst_end) {
-		unsigned int burst_len;
-
-		/* Clear TC bit */
-		writel_relaxed(SPICC_TC, spicc->base + SPICC_STATREG);
-
-		/* Disable TC interrupt */
-		ctrl &= ~SPICC_TC_EN;
-
-		if (spicc->is_last_burst) {
-			/* Disable all IRQs */
-			writel(0, spicc->base + SPICC_INTREG);
-
-			spi_finalize_current_transfer(spicc->master);
-
-			return IRQ_HANDLED;
-		}
-
-		burst_len = min_t(unsigned int,
-				  spicc->xfer_remain / spicc->bytes_per_word,
-				  SPICC_BURST_MAX);
+		spi_finalize_current_transfer(spicc->master);
 
-		/* Setup burst */
-		meson_spicc_setup_burst(spicc, burst_len);
-
-		/* Restart burst */
-		writel_bits_relaxed(SPICC_XCH, SPICC_XCH,
-				    spicc->base + SPICC_CONREG);
+		return IRQ_HANDLED;
 	}
 
-	/* Setup RX interrupt trigger */
-	ctrl = meson_spicc_setup_rx_irq(spicc, ctrl);
+	/* Setup burst */
+	meson_spicc_setup_burst(spicc);
 
-	/* Reconfigure interrupts */
-	writel(ctrl, spicc->base + SPICC_INTREG);
+	/* Start burst */
+	writel_bits_relaxed(SPICC_XCH, SPICC_XCH, spicc->base + SPICC_CONREG);
 
 	return IRQ_HANDLED;
 }
 
-static u32 meson_spicc_setup_speed(struct meson_spicc_device *spicc, u32 conf,
-				   u32 speed)
+static void meson_spicc_auto_io_delay(struct meson_spicc_device *spicc)
 {
-	unsigned long parent, value;
-	unsigned int i, div;
-
-	parent = clk_get_rate(spicc->core);
-
-	/* Find closest inferior/equal possible speed */
-	for (i = 0 ; i < 7 ; ++i) {
-		/* 2^(data_rate+2) */
-		value = parent >> (i + 2);
-
-		if (value <= speed)
-			break;
+	u32 div, hz;
+	u32 mi_delay, cap_delay;
+	u32 conf;
+
+	if (spicc->data->has_enhance_clk_div) {
+		div = FIELD_GET(SPICC_ENH_DATARATE_MASK,
+				readl_relaxed(spicc->base + SPICC_ENH_CTL0));
+		div++;
+		div <<= 1;
+	} else {
+		div = FIELD_GET(SPICC_DATARATE_MASK,
+				readl_relaxed(spicc->base + SPICC_CONREG));
+		div += 2;
+		div = 1 << div;
 	}
 
-	/* If provided speed it lower than max divider, use max divider */
-	if (i > 7) {
-		div = 7;
-		dev_warn_once(&spicc->pdev->dev, "unable to get close to speed %u\n",
-			      speed);
-	} else
-		div = i;
-
-	dev_dbg(&spicc->pdev->dev, "parent %lu, speed %u -> %lu (%u)\n",
-		parent, speed, value, div);
-
-	conf &= ~SPICC_DATARATE_MASK;
-	conf |= FIELD_PREP(SPICC_DATARATE_MASK, div);
-
-	return conf;
+	mi_delay = SPICC_MI_NO_DELAY;
+	cap_delay = SPICC_CAP_AHEAD_2_CYCLE;
+	hz = clk_get_rate(spicc->clk);
+
+	if (hz >= 100000000)
+		cap_delay = SPICC_CAP_DELAY_1_CYCLE;
+	else if (hz >= 80000000)
+		cap_delay = SPICC_CAP_NO_DELAY;
+	else if (hz >= 40000000)
+		cap_delay = SPICC_CAP_AHEAD_1_CYCLE;
+	else if (div >= 16)
+		mi_delay = SPICC_MI_DELAY_3_CYCLE;
+	else if (div >= 8)
+		mi_delay = SPICC_MI_DELAY_2_CYCLE;
+	else if (div >= 6)
+		mi_delay = SPICC_MI_DELAY_1_CYCLE;
+
+	conf = readl_relaxed(spicc->base + SPICC_TESTREG);
+	conf &= ~(SPICC_MO_DELAY_MASK | SPICC_MI_DELAY_MASK
+		  | SPICC_MI_CAP_DELAY_MASK);
+	conf |= FIELD_PREP(SPICC_MI_DELAY_MASK, mi_delay);
+	conf |= FIELD_PREP(SPICC_MI_CAP_DELAY_MASK, cap_delay);
+	writel_relaxed(conf, spicc->base + SPICC_TESTREG);
 }
 
 static void meson_spicc_setup_xfer(struct meson_spicc_device *spicc,
@@ -339,9 +344,6 @@ static void meson_spicc_setup_xfer(struct meson_spicc_device *spicc,
 	/* Read original configuration */
 	conf = conf_orig = readl_relaxed(spicc->base + SPICC_CONREG);
 
-	/* Select closest divider */
-	conf = meson_spicc_setup_speed(spicc, conf, xfer->speed_hz);
-
 	/* Setup word width */
 	conf &= ~SPICC_BITLENGTH_MASK;
 	conf |= FIELD_PREP(SPICC_BITLENGTH_MASK,
@@ -350,6 +352,32 @@ static void meson_spicc_setup_xfer(struct meson_spicc_device *spicc,
 	/* Ignore if unchanged */
 	if (conf != conf_orig)
 		writel_relaxed(conf, spicc->base + SPICC_CONREG);
+
+	clk_set_rate(spicc->clk, xfer->speed_hz);
+
+	meson_spicc_auto_io_delay(spicc);
+
+	writel_relaxed(0, spicc->base + SPICC_DMAREG);
+}
+
+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,
+				    spicc->base + SPICC_ENH_CTL0);
+
+	writel_bits_relaxed(SPICC_FIFORST_W1_MASK, SPICC_FIFORST_W1_MASK,
+			    spicc->base + SPICC_TESTREG);
+
+	while (meson_spicc_rxready(spicc))
+		data = readl_relaxed(spicc->base + SPICC_RXDATA);
+
+	if (spicc->data->has_oen)
+		writel_bits_relaxed(SPICC_ENH_MAIN_CLK_AO, 0,
+				    spicc->base + SPICC_ENH_CTL0);
 }
 
 static int meson_spicc_transfer_one(struct spi_master *master,
@@ -357,8 +385,6 @@ static int meson_spicc_transfer_one(struct spi_master *master,
 				    struct spi_transfer *xfer)
 {
 	struct meson_spicc_device *spicc = spi_master_get_devdata(master);
-	unsigned int burst_len;
-	u32 irq = 0;
 
 	/* Store current transfer */
 	spicc->xfer = xfer;
@@ -372,22 +398,22 @@ static int meson_spicc_transfer_one(struct spi_master *master,
 	spicc->bytes_per_word =
 	   DIV_ROUND_UP(spicc->xfer->bits_per_word, 8);
 
+	if (xfer->len % spicc->bytes_per_word)
+		return -EINVAL;
+
 	/* Setup transfer parameters */
 	meson_spicc_setup_xfer(spicc, xfer);
 
-	burst_len = min_t(unsigned int,
-			  spicc->xfer_remain / spicc->bytes_per_word,
-			  SPICC_BURST_MAX);
+	meson_spicc_reset_fifo(spicc);
 
-	meson_spicc_setup_burst(spicc, burst_len);
-
-	irq = meson_spicc_setup_rx_irq(spicc, irq);
+	/* Setup burst */
+	meson_spicc_setup_burst(spicc);
 
 	/* Start burst */
 	writel_bits_relaxed(SPICC_XCH, SPICC_XCH, spicc->base + SPICC_CONREG);
 
 	/* Enable interrupts */
-	writel_relaxed(irq, spicc->base + SPICC_INTREG);
+	writel_relaxed(SPICC_TC_EN, spicc->base + SPICC_INTREG);
 
 	return 1;
 }
@@ -444,7 +470,7 @@ static int meson_spicc_prepare_message(struct spi_master *master,
 	/* Setup no wait cycles by default */
 	writel_relaxed(0, spicc->base + SPICC_PERIODREG);
 
-	writel_bits_relaxed(BIT(24), BIT(24), spicc->base + SPICC_TESTREG);
+	writel_bits_relaxed(SPICC_LBC_W1, 0, spicc->base + SPICC_TESTREG);
 
 	return 0;
 }
@@ -456,9 +482,6 @@ static int meson_spicc_unprepare_transfer(struct spi_master *master)
 	/* Disable all IRQs */
 	writel(0, spicc->base + SPICC_INTREG);
 
-	/* Disable controller */
-	writel_bits_relaxed(SPICC_ENABLE, 0, spicc->base + SPICC_CONREG);
-
 	device_reset_optional(&spicc->pdev->dev);
 
 	return 0;
@@ -477,11 +500,167 @@ static void meson_spicc_cleanup(struct spi_device *spi)
 	spi->controller_state = NULL;
 }
 
+/*
+ * The Clock Mux
+ *            x-----------------x   x------------x    x------\
+ *        |---| pow2 fixed div  |---| pow2 div   |----|      |
+ *        |   x-----------------x   x------------x    |      |
+ * src ---|                                           | mux  |-- out
+ *        |   x-----------------x   x------------x    |      |
+ *        |---| enh fixed div   |---| enh div    |0---|      |
+ *            x-----------------x   x------------x    x------/
+ *
+ * Clk path for GX series:
+ *    src -> pow2 fixed div -> pow2 div -> out
+ *
+ * Clk path for AXG series:
+ *    src -> pow2 fixed div -> pow2 div -> mux -> out
+ *    src -> enh fixed div -> enh div -> mux -> out
+ *
+ * Clk path for G12A series:
+ *    pclk -> pow2 fixed div -> pow2 div -> mux -> out
+ *    pclk -> enh fixed div -> enh div -> mux -> out
+ */
+
+static int meson_spicc_clk_init(struct meson_spicc_device *spicc)
+{
+	struct device *dev = &spicc->pdev->dev;
+	struct clk_fixed_factor *pow2_fixed_div, *enh_fixed_div;
+	struct clk_divider *pow2_div, *enh_div;
+	struct clk_mux *mux;
+	struct clk_init_data init;
+	struct clk *clk;
+	struct clk_parent_data parent_data[2];
+	char name[64];
+
+	memset(&init, 0, sizeof(init));
+	memset(&parent_data, 0, sizeof(parent_data));
+
+	init.parent_data = parent_data;
+
+	/* algorithm for pow2 div: rate = freq / 4 / (2 ^ N) */
+
+	pow2_fixed_div = devm_kzalloc(dev, sizeof(*pow2_fixed_div), GFP_KERNEL);
+	if (!pow2_fixed_div)
+		return -ENOMEM;
+
+	snprintf(name, sizeof(name), "%s#pow2_fixed_div", dev_name(dev));
+	init.name = name;
+	init.ops = &clk_fixed_factor_ops;
+	init.flags = 0;
+	if (spicc->data->has_pclk)
+		parent_data[0].hw = __clk_get_hw(spicc->pclk);
+	else
+		parent_data[0].hw = __clk_get_hw(spicc->core);
+	init.num_parents = 1;
+
+	pow2_fixed_div->mult = 1,
+	pow2_fixed_div->div = 4,
+	pow2_fixed_div->hw.init = &init;
+
+	clk = devm_clk_register(dev, &pow2_fixed_div->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return PTR_ERR(clk);
+
+	pow2_div = devm_kzalloc(dev, sizeof(*pow2_div), GFP_KERNEL);
+	if (!pow2_div)
+		return -ENOMEM;
+
+	snprintf(name, sizeof(name), "%s#pow2_div", dev_name(dev));
+	init.name = name;
+	init.ops = &clk_divider_ops;
+	init.flags = CLK_SET_RATE_PARENT;
+	parent_data[0].hw = &pow2_fixed_div->hw;
+	init.num_parents = 1;
+
+	pow2_div->shift = 16,
+	pow2_div->width = 3,
+	pow2_div->flags = CLK_DIVIDER_POWER_OF_TWO,
+	pow2_div->reg = spicc->base + SPICC_CONREG;
+	pow2_div->hw.init = &init;
+
+	clk = devm_clk_register(dev, &pow2_div->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return PTR_ERR(clk);
+
+	if (!spicc->data->has_enhance_clk_div) {
+		spicc->clk = clk;
+		return 0;
+	}
+
+	/* algorithm for enh div: rate = freq / 2 / (N + 1) */
+
+	enh_fixed_div = devm_kzalloc(dev, sizeof(*enh_fixed_div), GFP_KERNEL);
+	if (!enh_fixed_div)
+		return -ENOMEM;
+
+	snprintf(name, sizeof(name), "%s#enh_fixed_div", dev_name(dev));
+	init.name = name;
+	init.ops = &clk_fixed_factor_ops;
+	init.flags = 0;
+	if (spicc->data->has_pclk)
+		parent_data[0].hw = __clk_get_hw(spicc->pclk);
+	else
+		parent_data[0].hw = __clk_get_hw(spicc->core);
+	init.num_parents = 1;
+
+	enh_fixed_div->mult = 1,
+	enh_fixed_div->div = 2,
+	enh_fixed_div->hw.init = &init;
+
+	clk = devm_clk_register(dev, &enh_fixed_div->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return PTR_ERR(clk);
+
+	enh_div = devm_kzalloc(dev, sizeof(*enh_div), GFP_KERNEL);
+	if (!enh_div)
+		return -ENOMEM;
+
+	snprintf(name, sizeof(name), "%s#enh_div", dev_name(dev));
+	init.name = name;
+	init.ops = &clk_divider_ops;
+	init.flags = CLK_SET_RATE_PARENT;
+	parent_data[0].hw = &enh_fixed_div->hw;
+	init.num_parents = 1;
+
+	enh_div->shift	= 16,
+	enh_div->width	= 8,
+	enh_div->reg = spicc->base + SPICC_ENH_CTL0;
+	enh_div->hw.init = &init;
+
+	clk = devm_clk_register(dev, &enh_div->hw);
+	if (WARN_ON(IS_ERR(clk)))
+		return PTR_ERR(clk);
+
+	mux = devm_kzalloc(dev, sizeof(*mux), GFP_KERNEL);
+	if (!mux)
+		return -ENOMEM;
+
+	snprintf(name, sizeof(name), "%s#sel", dev_name(dev));
+	init.name = name;
+	init.ops = &clk_mux_ops;
+	parent_data[0].hw = &pow2_div->hw;
+	parent_data[1].hw = &enh_div->hw;
+	init.num_parents = 2;
+	init.flags = CLK_SET_RATE_PARENT;
+
+	mux->mask = 0x1,
+	mux->shift = 24,
+	mux->reg = spicc->base + SPICC_ENH_CTL0;
+	mux->hw.init = &init;
+
+	spicc->clk = devm_clk_register(dev, &mux->hw);
+	if (WARN_ON(IS_ERR(spicc->clk)))
+		return PTR_ERR(spicc->clk);
+
+	return 0;
+}
+
 static int meson_spicc_probe(struct platform_device *pdev)
 {
 	struct spi_master *master;
 	struct meson_spicc_device *spicc;
-	int ret, irq, rate;
+	int ret, irq;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*spicc));
 	if (!master) {
@@ -491,6 +670,13 @@ static int meson_spicc_probe(struct platform_device *pdev)
 	spicc = spi_master_get_devdata(master);
 	spicc->master = master;
 
+	spicc->data = of_device_get_match_data(&pdev->dev);
+	if (!spicc->data) {
+		dev_err(&pdev->dev, "failed to get match data\n");
+		ret = -EINVAL;
+		goto out_master;
+	}
+
 	spicc->pdev = pdev;
 	platform_set_drvdata(pdev, spicc);
 
@@ -501,6 +687,10 @@ static int meson_spicc_probe(struct platform_device *pdev)
 		goto out_master;
 	}
 
+	/* Set master mode and enable controller */
+	writel_relaxed(SPICC_ENABLE | SPICC_MODE_MASTER,
+		       spicc->base + SPICC_CONREG);
+
 	/* Disable all IRQs */
 	writel_relaxed(0, spicc->base + SPICC_INTREG);
 
@@ -519,12 +709,26 @@ static int meson_spicc_probe(struct platform_device *pdev)
 		goto out_master;
 	}
 
+	if (spicc->data->has_pclk) {
+		spicc->pclk = devm_clk_get(&pdev->dev, "pclk");
+		if (IS_ERR(spicc->pclk)) {
+			dev_err(&pdev->dev, "pclk clock request failed\n");
+			ret = PTR_ERR(spicc->pclk);
+			goto out_master;
+		}
+	}
+
 	ret = clk_prepare_enable(spicc->core);
 	if (ret) {
 		dev_err(&pdev->dev, "core clock enable failed\n");
 		goto out_master;
 	}
-	rate = clk_get_rate(spicc->core);
+
+	ret = clk_prepare_enable(spicc->pclk);
+	if (ret) {
+		dev_err(&pdev->dev, "pclk clock enable failed\n");
+		goto out_master;
+	}
 
 	device_reset_optional(&pdev->dev);
 
@@ -536,7 +740,8 @@ static int meson_spicc_probe(struct platform_device *pdev)
 				     SPI_BPW_MASK(16) |
 				     SPI_BPW_MASK(8);
 	master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX);
-	master->min_speed_hz = rate >> 9;
+	master->min_speed_hz = spicc->data->min_speed_hz;
+	master->max_speed_hz = spicc->data->max_speed_hz;
 	master->setup = meson_spicc_setup;
 	master->cleanup = meson_spicc_cleanup;
 	master->prepare_message = meson_spicc_prepare_message;
@@ -544,11 +749,13 @@ static int meson_spicc_probe(struct platform_device *pdev)
 	master->transfer_one = meson_spicc_transfer_one;
 	master->use_gpio_descriptors = true;
 
-	/* Setup max rate according to the Meson GX datasheet */
-	if ((rate >> 2) > SPICC_MAX_FREQ)
-		master->max_speed_hz = SPICC_MAX_FREQ;
-	else
-		master->max_speed_hz = rate >> 2;
+	meson_spicc_oen_enable(spicc);
+
+	ret = meson_spicc_clk_init(spicc);
+	if (ret) {
+		dev_err(&pdev->dev, "clock registration failed\n");
+		goto out_master;
+	}
 
 	ret = devm_spi_register_master(&pdev->dev, master);
 	if (ret) {
@@ -560,6 +767,7 @@ static int meson_spicc_probe(struct platform_device *pdev)
 
 out_clk:
 	clk_disable_unprepare(spicc->core);
+	clk_disable_unprepare(spicc->pclk);
 
 out_master:
 	spi_master_put(master);
@@ -575,13 +783,47 @@ static int meson_spicc_remove(struct platform_device *pdev)
 	writel(0, spicc->base + SPICC_CONREG);
 
 	clk_disable_unprepare(spicc->core);
+	clk_disable_unprepare(spicc->pclk);
 
 	return 0;
 }
 
+static const struct meson_spicc_data meson_spicc_gx_data = {
+	.max_speed_hz		= 30000000,
+	.min_speed_hz		= 325000,
+	.fifo_size		= 16,
+};
+
+static const struct meson_spicc_data meson_spicc_axg_data = {
+	.max_speed_hz		= 80000000,
+	.min_speed_hz		= 325000,
+	.fifo_size		= 16,
+	.has_oen		= true,
+	.has_enhance_clk_div	= true,
+};
+
+static const struct meson_spicc_data meson_spicc_g12a_data = {
+	.max_speed_hz		= 166666666,
+	.min_speed_hz		= 50000,
+	.fifo_size		= 15,
+	.has_oen		= true,
+	.has_enhance_clk_div	= true,
+	.has_pclk		= true,
+};
+
 static const struct of_device_id meson_spicc_of_match[] = {
-	{ .compatible = "amlogic,meson-gx-spicc", },
-	{ .compatible = "amlogic,meson-axg-spicc", },
+	{
+		.compatible	= "amlogic,meson-gx-spicc",
+		.data		= &meson_spicc_gx_data,
+	},
+	{
+		.compatible = "amlogic,meson-axg-spicc",
+		.data		= &meson_spicc_axg_data,
+	},
+	{
+		.compatible = "amlogic,meson-g12a-spicc",
+		.data		= &meson_spicc_g12a_data,
+	},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, meson_spicc_of_match);
diff --git a/drivers/spi/spi-mtk-nor.c b/drivers/spi/spi-mtk-nor.c
new file mode 100644
index 000000000000..c15a9910549f
--- /dev/null
+++ b/drivers/spi/spi-mtk-nor.c
@@ -0,0 +1,689 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Mediatek SPI NOR controller driver
+//
+// Copyright (C) 2020 Chuanhong Guo <gch981213@gmail.com>
+
+#include <linux/bits.h>
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+#include <linux/string.h>
+
+#define DRIVER_NAME "mtk-spi-nor"
+
+#define MTK_NOR_REG_CMD			0x00
+#define MTK_NOR_CMD_WRITE		BIT(4)
+#define MTK_NOR_CMD_PROGRAM		BIT(2)
+#define MTK_NOR_CMD_READ		BIT(0)
+#define MTK_NOR_CMD_MASK		GENMASK(5, 0)
+
+#define MTK_NOR_REG_PRG_CNT		0x04
+#define MTK_NOR_REG_RDATA		0x0c
+
+#define MTK_NOR_REG_RADR0		0x10
+#define MTK_NOR_REG_RADR(n)		(MTK_NOR_REG_RADR0 + 4 * (n))
+#define MTK_NOR_REG_RADR3		0xc8
+
+#define MTK_NOR_REG_WDATA		0x1c
+
+#define MTK_NOR_REG_PRGDATA0		0x20
+#define MTK_NOR_REG_PRGDATA(n)		(MTK_NOR_REG_PRGDATA0 + 4 * (n))
+#define MTK_NOR_REG_PRGDATA_MAX		5
+
+#define MTK_NOR_REG_SHIFT0		0x38
+#define MTK_NOR_REG_SHIFT(n)		(MTK_NOR_REG_SHIFT0 + 4 * (n))
+#define MTK_NOR_REG_SHIFT_MAX		9
+
+#define MTK_NOR_REG_CFG1		0x60
+#define MTK_NOR_FAST_READ		BIT(0)
+
+#define MTK_NOR_REG_CFG2		0x64
+#define MTK_NOR_WR_CUSTOM_OP_EN		BIT(4)
+#define MTK_NOR_WR_BUF_EN		BIT(0)
+
+#define MTK_NOR_REG_PP_DATA		0x98
+
+#define MTK_NOR_REG_IRQ_STAT		0xa8
+#define MTK_NOR_REG_IRQ_EN		0xac
+#define MTK_NOR_IRQ_DMA			BIT(7)
+#define MTK_NOR_IRQ_MASK		GENMASK(7, 0)
+
+#define MTK_NOR_REG_CFG3		0xb4
+#define MTK_NOR_DISABLE_WREN		BIT(7)
+#define MTK_NOR_DISABLE_SR_POLL		BIT(5)
+
+#define MTK_NOR_REG_WP			0xc4
+#define MTK_NOR_ENABLE_SF_CMD		0x30
+
+#define MTK_NOR_REG_BUSCFG		0xcc
+#define MTK_NOR_4B_ADDR			BIT(4)
+#define MTK_NOR_QUAD_ADDR		BIT(3)
+#define MTK_NOR_QUAD_READ		BIT(2)
+#define MTK_NOR_DUAL_ADDR		BIT(1)
+#define MTK_NOR_DUAL_READ		BIT(0)
+#define MTK_NOR_BUS_MODE_MASK		GENMASK(4, 0)
+
+#define MTK_NOR_REG_DMA_CTL		0x718
+#define MTK_NOR_DMA_START		BIT(0)
+
+#define MTK_NOR_REG_DMA_FADR		0x71c
+#define MTK_NOR_REG_DMA_DADR		0x720
+#define MTK_NOR_REG_DMA_END_DADR	0x724
+
+#define MTK_NOR_PRG_MAX_SIZE		6
+// Reading DMA src/dst addresses have to be 16-byte aligned
+#define MTK_NOR_DMA_ALIGN		16
+#define MTK_NOR_DMA_ALIGN_MASK		(MTK_NOR_DMA_ALIGN - 1)
+// and we allocate a bounce buffer if destination address isn't aligned.
+#define MTK_NOR_BOUNCE_BUF_SIZE		PAGE_SIZE
+
+// Buffered page program can do one 128-byte transfer
+#define MTK_NOR_PP_SIZE			128
+
+#define CLK_TO_US(sp, clkcnt)		((clkcnt) * 1000000 / sp->spi_freq)
+
+struct mtk_nor {
+	struct spi_controller *ctlr;
+	struct device *dev;
+	void __iomem *base;
+	u8 *buffer;
+	struct clk *spi_clk;
+	struct clk *ctlr_clk;
+	unsigned int spi_freq;
+	bool wbuf_en;
+	bool has_irq;
+	struct completion op_done;
+};
+
+static inline void mtk_nor_rmw(struct mtk_nor *sp, u32 reg, u32 set, u32 clr)
+{
+	u32 val = readl(sp->base + reg);
+
+	val &= ~clr;
+	val |= set;
+	writel(val, sp->base + reg);
+}
+
+static inline int mtk_nor_cmd_exec(struct mtk_nor *sp, u32 cmd, ulong clk)
+{
+	ulong delay = CLK_TO_US(sp, clk);
+	u32 reg;
+	int ret;
+
+	writel(cmd, sp->base + MTK_NOR_REG_CMD);
+	ret = readl_poll_timeout(sp->base + MTK_NOR_REG_CMD, reg, !(reg & cmd),
+				 delay / 3, (delay + 1) * 200);
+	if (ret < 0)
+		dev_err(sp->dev, "command %u timeout.\n", cmd);
+	return ret;
+}
+
+static void mtk_nor_set_addr(struct mtk_nor *sp, const struct spi_mem_op *op)
+{
+	u32 addr = op->addr.val;
+	int i;
+
+	for (i = 0; i < 3; i++) {
+		writeb(addr & 0xff, sp->base + MTK_NOR_REG_RADR(i));
+		addr >>= 8;
+	}
+	if (op->addr.nbytes == 4) {
+		writeb(addr & 0xff, sp->base + MTK_NOR_REG_RADR3);
+		mtk_nor_rmw(sp, MTK_NOR_REG_BUSCFG, MTK_NOR_4B_ADDR, 0);
+	} else {
+		mtk_nor_rmw(sp, MTK_NOR_REG_BUSCFG, 0, MTK_NOR_4B_ADDR);
+	}
+}
+
+static bool mtk_nor_match_read(const struct spi_mem_op *op)
+{
+	int dummy = 0;
+
+	if (op->dummy.buswidth)
+		dummy = op->dummy.nbytes * BITS_PER_BYTE / op->dummy.buswidth;
+
+	if ((op->data.buswidth == 2) || (op->data.buswidth == 4)) {
+		if (op->addr.buswidth == 1)
+			return dummy == 8;
+		else if (op->addr.buswidth == 2)
+			return dummy == 4;
+		else if (op->addr.buswidth == 4)
+			return dummy == 6;
+	} else if ((op->addr.buswidth == 1) && (op->data.buswidth == 1)) {
+		if (op->cmd.opcode == 0x03)
+			return dummy == 0;
+		else if (op->cmd.opcode == 0x0b)
+			return dummy == 8;
+	}
+	return false;
+}
+
+static int mtk_nor_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op)
+{
+	size_t len;
+
+	if (!op->data.nbytes)
+		return 0;
+
+	if ((op->addr.nbytes == 3) || (op->addr.nbytes == 4)) {
+		if ((op->data.dir == SPI_MEM_DATA_IN) &&
+		    mtk_nor_match_read(op)) {
+			if ((op->addr.val & MTK_NOR_DMA_ALIGN_MASK) ||
+			    (op->data.nbytes < MTK_NOR_DMA_ALIGN))
+				op->data.nbytes = 1;
+			else if (!((ulong)(op->data.buf.in) &
+				   MTK_NOR_DMA_ALIGN_MASK))
+				op->data.nbytes &= ~MTK_NOR_DMA_ALIGN_MASK;
+			else if (op->data.nbytes > MTK_NOR_BOUNCE_BUF_SIZE)
+				op->data.nbytes = MTK_NOR_BOUNCE_BUF_SIZE;
+			return 0;
+		} else if (op->data.dir == SPI_MEM_DATA_OUT) {
+			if (op->data.nbytes >= MTK_NOR_PP_SIZE)
+				op->data.nbytes = MTK_NOR_PP_SIZE;
+			else
+				op->data.nbytes = 1;
+			return 0;
+		}
+	}
+
+	len = MTK_NOR_PRG_MAX_SIZE - sizeof(op->cmd.opcode) - op->addr.nbytes -
+	      op->dummy.nbytes;
+	if (op->data.nbytes > len)
+		op->data.nbytes = len;
+
+	return 0;
+}
+
+static bool mtk_nor_supports_op(struct spi_mem *mem,
+				const struct spi_mem_op *op)
+{
+	size_t len;
+
+	if (op->cmd.buswidth != 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;
+		else if (op->data.dir == SPI_MEM_DATA_OUT)
+			return (op->addr.buswidth == 1) &&
+			       (op->dummy.buswidth == 0) &&
+			       (op->data.buswidth == 1);
+	}
+	len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
+	if ((len > MTK_NOR_PRG_MAX_SIZE) ||
+	    ((op->data.nbytes) && (len == MTK_NOR_PRG_MAX_SIZE)))
+		return false;
+	return true;
+}
+
+static void mtk_nor_setup_bus(struct mtk_nor *sp, const struct spi_mem_op *op)
+{
+	u32 reg = 0;
+
+	if (op->addr.nbytes == 4)
+		reg |= MTK_NOR_4B_ADDR;
+
+	if (op->data.buswidth == 4) {
+		reg |= MTK_NOR_QUAD_READ;
+		writeb(op->cmd.opcode, sp->base + MTK_NOR_REG_PRGDATA(4));
+		if (op->addr.buswidth == 4)
+			reg |= MTK_NOR_QUAD_ADDR;
+	} else if (op->data.buswidth == 2) {
+		reg |= MTK_NOR_DUAL_READ;
+		writeb(op->cmd.opcode, sp->base + MTK_NOR_REG_PRGDATA(3));
+		if (op->addr.buswidth == 2)
+			reg |= MTK_NOR_DUAL_ADDR;
+	} else {
+		if (op->cmd.opcode == 0x0b)
+			mtk_nor_rmw(sp, MTK_NOR_REG_CFG1, MTK_NOR_FAST_READ, 0);
+		else
+			mtk_nor_rmw(sp, MTK_NOR_REG_CFG1, 0, MTK_NOR_FAST_READ);
+	}
+	mtk_nor_rmw(sp, MTK_NOR_REG_BUSCFG, reg, MTK_NOR_BUS_MODE_MASK);
+}
+
+static int mtk_nor_read_dma(struct mtk_nor *sp, u32 from, unsigned int length,
+			    u8 *buffer)
+{
+	int ret = 0;
+	ulong delay;
+	u32 reg;
+	dma_addr_t dma_addr;
+
+	dma_addr = dma_map_single(sp->dev, buffer, length, DMA_FROM_DEVICE);
+	if (dma_mapping_error(sp->dev, dma_addr)) {
+		dev_err(sp->dev, "failed to map dma buffer.\n");
+		return -EINVAL;
+	}
+
+	writel(from, sp->base + MTK_NOR_REG_DMA_FADR);
+	writel(dma_addr, sp->base + MTK_NOR_REG_DMA_DADR);
+	writel(dma_addr + length, sp->base + MTK_NOR_REG_DMA_END_DADR);
+
+	if (sp->has_irq) {
+		reinit_completion(&sp->op_done);
+		mtk_nor_rmw(sp, MTK_NOR_REG_IRQ_EN, MTK_NOR_IRQ_DMA, 0);
+	}
+
+	mtk_nor_rmw(sp, MTK_NOR_REG_DMA_CTL, MTK_NOR_DMA_START, 0);
+
+	delay = CLK_TO_US(sp, (length + 5) * BITS_PER_BYTE);
+
+	if (sp->has_irq) {
+		if (!wait_for_completion_timeout(&sp->op_done,
+						 (delay + 1) * 100))
+			ret = -ETIMEDOUT;
+	} else {
+		ret = readl_poll_timeout(sp->base + MTK_NOR_REG_DMA_CTL, reg,
+					 !(reg & MTK_NOR_DMA_START), delay / 3,
+					 (delay + 1) * 100);
+	}
+
+	dma_unmap_single(sp->dev, dma_addr, length, DMA_FROM_DEVICE);
+	if (ret < 0)
+		dev_err(sp->dev, "dma read timeout.\n");
+
+	return ret;
+}
+
+static int mtk_nor_read_bounce(struct mtk_nor *sp, u32 from,
+			       unsigned int length, u8 *buffer)
+{
+	unsigned int rdlen;
+	int ret;
+
+	if (length & MTK_NOR_DMA_ALIGN_MASK)
+		rdlen = (length + MTK_NOR_DMA_ALIGN) & ~MTK_NOR_DMA_ALIGN_MASK;
+	else
+		rdlen = length;
+
+	ret = mtk_nor_read_dma(sp, from, rdlen, sp->buffer);
+	if (ret)
+		return ret;
+
+	memcpy(buffer, sp->buffer, length);
+	return 0;
+}
+
+static int mtk_nor_read_pio(struct mtk_nor *sp, const struct spi_mem_op *op)
+{
+	u8 *buf = op->data.buf.in;
+	int ret;
+
+	ret = mtk_nor_cmd_exec(sp, MTK_NOR_CMD_READ, 6 * BITS_PER_BYTE);
+	if (!ret)
+		buf[0] = readb(sp->base + MTK_NOR_REG_RDATA);
+	return ret;
+}
+
+static int mtk_nor_write_buffer_enable(struct mtk_nor *sp)
+{
+	int ret;
+	u32 val;
+
+	if (sp->wbuf_en)
+		return 0;
+
+	val = readl(sp->base + MTK_NOR_REG_CFG2);
+	writel(val | MTK_NOR_WR_BUF_EN, sp->base + MTK_NOR_REG_CFG2);
+	ret = readl_poll_timeout(sp->base + MTK_NOR_REG_CFG2, val,
+				 val & MTK_NOR_WR_BUF_EN, 0, 10000);
+	if (!ret)
+		sp->wbuf_en = true;
+	return ret;
+}
+
+static int mtk_nor_write_buffer_disable(struct mtk_nor *sp)
+{
+	int ret;
+	u32 val;
+
+	if (!sp->wbuf_en)
+		return 0;
+	val = readl(sp->base + MTK_NOR_REG_CFG2);
+	writel(val & ~MTK_NOR_WR_BUF_EN, sp->base + MTK_NOR_REG_CFG2);
+	ret = readl_poll_timeout(sp->base + MTK_NOR_REG_CFG2, val,
+				 !(val & MTK_NOR_WR_BUF_EN), 0, 10000);
+	if (!ret)
+		sp->wbuf_en = false;
+	return ret;
+}
+
+static int mtk_nor_pp_buffered(struct mtk_nor *sp, const struct spi_mem_op *op)
+{
+	const u8 *buf = op->data.buf.out;
+	u32 val;
+	int ret, i;
+
+	ret = mtk_nor_write_buffer_enable(sp);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < op->data.nbytes; i += 4) {
+		val = buf[i + 3] << 24 | buf[i + 2] << 16 | buf[i + 1] << 8 |
+		      buf[i];
+		writel(val, sp->base + MTK_NOR_REG_PP_DATA);
+	}
+	return mtk_nor_cmd_exec(sp, MTK_NOR_CMD_WRITE,
+				(op->data.nbytes + 5) * BITS_PER_BYTE);
+}
+
+static int mtk_nor_pp_unbuffered(struct mtk_nor *sp,
+				 const struct spi_mem_op *op)
+{
+	const u8 *buf = op->data.buf.out;
+	int ret;
+
+	ret = mtk_nor_write_buffer_disable(sp);
+	if (ret < 0)
+		return ret;
+	writeb(buf[0], sp->base + MTK_NOR_REG_WDATA);
+	return mtk_nor_cmd_exec(sp, MTK_NOR_CMD_WRITE, 6 * BITS_PER_BYTE);
+}
+
+int mtk_nor_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
+{
+	struct mtk_nor *sp = spi_controller_get_devdata(mem->spi->master);
+	int ret;
+
+	if ((op->data.nbytes == 0) ||
+	    ((op->addr.nbytes != 3) && (op->addr.nbytes != 4)))
+		return -ENOTSUPP;
+
+	if (op->data.dir == SPI_MEM_DATA_OUT) {
+		mtk_nor_set_addr(sp, op);
+		writeb(op->cmd.opcode, sp->base + MTK_NOR_REG_PRGDATA0);
+		if (op->data.nbytes == MTK_NOR_PP_SIZE)
+			return mtk_nor_pp_buffered(sp, op);
+		return mtk_nor_pp_unbuffered(sp, op);
+	}
+
+	if ((op->data.dir == SPI_MEM_DATA_IN) && mtk_nor_match_read(op)) {
+		ret = mtk_nor_write_buffer_disable(sp);
+		if (ret < 0)
+			return ret;
+		mtk_nor_setup_bus(sp, op);
+		if (op->data.nbytes == 1) {
+			mtk_nor_set_addr(sp, op);
+			return mtk_nor_read_pio(sp, op);
+		} else if (((ulong)(op->data.buf.in) &
+			    MTK_NOR_DMA_ALIGN_MASK)) {
+			return mtk_nor_read_bounce(sp, op->addr.val,
+						   op->data.nbytes,
+						   op->data.buf.in);
+		} else {
+			return mtk_nor_read_dma(sp, op->addr.val,
+						op->data.nbytes,
+						op->data.buf.in);
+		}
+	}
+
+	return -ENOTSUPP;
+}
+
+static int mtk_nor_setup(struct spi_device *spi)
+{
+	struct mtk_nor *sp = spi_controller_get_devdata(spi->master);
+
+	if (spi->max_speed_hz && (spi->max_speed_hz < sp->spi_freq)) {
+		dev_err(&spi->dev, "spi clock should be %u Hz.\n",
+			sp->spi_freq);
+		return -EINVAL;
+	}
+	spi->max_speed_hz = sp->spi_freq;
+
+	return 0;
+}
+
+static int mtk_nor_transfer_one_message(struct spi_controller *master,
+					struct spi_message *m)
+{
+	struct mtk_nor *sp = spi_controller_get_devdata(master);
+	struct spi_transfer *t = NULL;
+	unsigned long trx_len = 0;
+	int stat = 0;
+	int reg_offset = MTK_NOR_REG_PRGDATA_MAX;
+	void __iomem *reg;
+	const u8 *txbuf;
+	u8 *rxbuf;
+	int i;
+
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		txbuf = t->tx_buf;
+		for (i = 0; i < t->len; i++, reg_offset--) {
+			reg = sp->base + MTK_NOR_REG_PRGDATA(reg_offset);
+			if (txbuf)
+				writeb(txbuf[i], reg);
+			else
+				writeb(0, reg);
+		}
+		trx_len += t->len;
+	}
+
+	writel(trx_len * BITS_PER_BYTE, sp->base + MTK_NOR_REG_PRG_CNT);
+
+	stat = mtk_nor_cmd_exec(sp, MTK_NOR_CMD_PROGRAM,
+				trx_len * BITS_PER_BYTE);
+	if (stat < 0)
+		goto msg_done;
+
+	reg_offset = trx_len - 1;
+	list_for_each_entry(t, &m->transfers, transfer_list) {
+		rxbuf = t->rx_buf;
+		for (i = 0; i < t->len; i++, reg_offset--) {
+			reg = sp->base + MTK_NOR_REG_SHIFT(reg_offset);
+			if (rxbuf)
+				rxbuf[i] = readb(reg);
+		}
+	}
+
+	m->actual_length = trx_len;
+msg_done:
+	m->status = stat;
+	spi_finalize_current_message(master);
+
+	return 0;
+}
+
+static void mtk_nor_disable_clk(struct mtk_nor *sp)
+{
+	clk_disable_unprepare(sp->spi_clk);
+	clk_disable_unprepare(sp->ctlr_clk);
+}
+
+static int mtk_nor_enable_clk(struct mtk_nor *sp)
+{
+	int ret;
+
+	ret = clk_prepare_enable(sp->spi_clk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(sp->ctlr_clk);
+	if (ret) {
+		clk_disable_unprepare(sp->spi_clk);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int mtk_nor_init(struct mtk_nor *sp)
+{
+	int ret;
+
+	ret = mtk_nor_enable_clk(sp);
+	if (ret)
+		return ret;
+
+	sp->spi_freq = clk_get_rate(sp->spi_clk);
+
+	writel(MTK_NOR_ENABLE_SF_CMD, sp->base + MTK_NOR_REG_WP);
+	mtk_nor_rmw(sp, MTK_NOR_REG_CFG2, MTK_NOR_WR_CUSTOM_OP_EN, 0);
+	mtk_nor_rmw(sp, MTK_NOR_REG_CFG3,
+		    MTK_NOR_DISABLE_WREN | MTK_NOR_DISABLE_SR_POLL, 0);
+
+	return ret;
+}
+
+static irqreturn_t mtk_nor_irq_handler(int irq, void *data)
+{
+	struct mtk_nor *sp = data;
+	u32 irq_status, irq_enabled;
+
+	irq_status = readl(sp->base + MTK_NOR_REG_IRQ_STAT);
+	irq_enabled = readl(sp->base + MTK_NOR_REG_IRQ_EN);
+	// write status back to clear interrupt
+	writel(irq_status, sp->base + MTK_NOR_REG_IRQ_STAT);
+
+	if (!(irq_status & irq_enabled))
+		return IRQ_NONE;
+
+	if (irq_status & MTK_NOR_IRQ_DMA) {
+		complete(&sp->op_done);
+		writel(0, sp->base + MTK_NOR_REG_IRQ_EN);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static size_t mtk_max_msg_size(struct spi_device *spi)
+{
+	return MTK_NOR_PRG_MAX_SIZE;
+}
+
+static const struct spi_controller_mem_ops mtk_nor_mem_ops = {
+	.adjust_op_size = mtk_nor_adjust_op_size,
+	.supports_op = mtk_nor_supports_op,
+	.exec_op = mtk_nor_exec_op
+};
+
+static const struct of_device_id mtk_nor_match[] = {
+	{ .compatible = "mediatek,mt8173-nor" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, mtk_nor_match);
+
+static int mtk_nor_probe(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr;
+	struct mtk_nor *sp;
+	void __iomem *base;
+	u8 *buffer;
+	struct clk *spi_clk, *ctlr_clk;
+	int ret, irq;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	spi_clk = devm_clk_get(&pdev->dev, "spi");
+	if (IS_ERR(spi_clk))
+		return PTR_ERR(spi_clk);
+
+	ctlr_clk = devm_clk_get(&pdev->dev, "sf");
+	if (IS_ERR(ctlr_clk))
+		return PTR_ERR(ctlr_clk);
+
+	buffer = devm_kmalloc(&pdev->dev,
+			      MTK_NOR_BOUNCE_BUF_SIZE + MTK_NOR_DMA_ALIGN,
+			      GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	if ((ulong)buffer & MTK_NOR_DMA_ALIGN_MASK)
+		buffer = (u8 *)(((ulong)buffer + MTK_NOR_DMA_ALIGN) &
+				~MTK_NOR_DMA_ALIGN_MASK);
+
+	ctlr = spi_alloc_master(&pdev->dev, sizeof(*sp));
+	if (!ctlr) {
+		dev_err(&pdev->dev, "failed to allocate spi controller\n");
+		return -ENOMEM;
+	}
+
+	ctlr->bits_per_word_mask = SPI_BPW_MASK(8);
+	ctlr->dev.of_node = pdev->dev.of_node;
+	ctlr->max_message_size = mtk_max_msg_size;
+	ctlr->mem_ops = &mtk_nor_mem_ops;
+	ctlr->mode_bits = SPI_RX_DUAL | SPI_RX_QUAD | SPI_TX_DUAL | SPI_TX_QUAD;
+	ctlr->num_chipselect = 1;
+	ctlr->setup = mtk_nor_setup;
+	ctlr->transfer_one_message = mtk_nor_transfer_one_message;
+
+	dev_set_drvdata(&pdev->dev, ctlr);
+
+	sp = spi_controller_get_devdata(ctlr);
+	sp->base = base;
+	sp->buffer = buffer;
+	sp->has_irq = false;
+	sp->wbuf_en = false;
+	sp->ctlr = ctlr;
+	sp->dev = &pdev->dev;
+	sp->spi_clk = spi_clk;
+	sp->ctlr_clk = ctlr_clk;
+
+	irq = platform_get_irq_optional(pdev, 0);
+	if (irq < 0) {
+		dev_warn(sp->dev, "IRQ not available.");
+	} else {
+		writel(MTK_NOR_IRQ_MASK, base + MTK_NOR_REG_IRQ_STAT);
+		writel(0, base + MTK_NOR_REG_IRQ_EN);
+		ret = devm_request_irq(sp->dev, irq, mtk_nor_irq_handler, 0,
+				       pdev->name, sp);
+		if (ret < 0) {
+			dev_warn(sp->dev, "failed to request IRQ.");
+		} else {
+			init_completion(&sp->op_done);
+			sp->has_irq = true;
+		}
+	}
+
+	ret = mtk_nor_init(sp);
+	if (ret < 0) {
+		kfree(ctlr);
+		return ret;
+	}
+
+	dev_info(&pdev->dev, "spi frequency: %d Hz\n", sp->spi_freq);
+
+	return devm_spi_register_controller(&pdev->dev, ctlr);
+}
+
+static int mtk_nor_remove(struct platform_device *pdev)
+{
+	struct spi_controller *ctlr;
+	struct mtk_nor *sp;
+
+	ctlr = dev_get_drvdata(&pdev->dev);
+	sp = spi_controller_get_devdata(ctlr);
+
+	mtk_nor_disable_clk(sp);
+
+	return 0;
+}
+
+static struct platform_driver mtk_nor_driver = {
+	.driver = {
+		.name = DRIVER_NAME,
+		.of_match_table = mtk_nor_match,
+	},
+	.probe = mtk_nor_probe,
+	.remove = mtk_nor_remove,
+};
+
+module_platform_driver(mtk_nor_driver);
+
+MODULE_DESCRIPTION("Mediatek SPI NOR controller driver");
+MODULE_AUTHOR("Chuanhong Guo <gch981213@gmail.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/spi/spi-mux.c b/drivers/spi/spi-mux.c
new file mode 100644
index 000000000000..4f94c9127fc1
--- /dev/null
+++ b/drivers/spi/spi-mux.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// General Purpose SPI multiplexer
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mux/consumer.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+
+#define SPI_MUX_NO_CS	((unsigned int)-1)
+
+/**
+ * DOC: Driver description
+ *
+ * This driver supports a MUX on an SPI bus. This can be useful when you need
+ * more chip selects than the hardware peripherals support, or than are
+ * available in a particular board setup.
+ *
+ * The driver will create an additional SPI controller. Devices added under the
+ * mux will be handled as 'chip selects' on this controller.
+ */
+
+/**
+ * struct spi_mux_priv - the basic spi_mux structure
+ * @spi:		pointer to the device struct attached to the parent
+ *			spi controller
+ * @current_cs:		The current chip select set in the mux
+ * @child_msg_complete: The mux replaces the complete callback in the child's
+ *			message to its own callback; this field is used by the
+ *			driver to store the child's callback during a transfer
+ * @child_msg_context:	Used to store the child's context to the callback
+ * @child_msg_dev:	Used to store the spi_device pointer to the child
+ * @mux:		mux_control structure used to provide chip selects for
+ *			downstream spi devices
+ */
+struct spi_mux_priv {
+	struct spi_device	*spi;
+	unsigned int		current_cs;
+
+	void			(*child_msg_complete)(void *context);
+	void			*child_msg_context;
+	struct spi_device	*child_msg_dev;
+	struct mux_control	*mux;
+};
+
+/* should not get called when the parent controller is doing a transfer */
+static int spi_mux_select(struct spi_device *spi)
+{
+	struct spi_mux_priv *priv = spi_controller_get_devdata(spi->controller);
+	int ret;
+
+	if (priv->current_cs == spi->chip_select)
+		return 0;
+
+	dev_dbg(&priv->spi->dev, "setting up the mux for cs %d\n",
+		spi->chip_select);
+
+	/* copy the child device's settings except for the cs */
+	priv->spi->max_speed_hz = spi->max_speed_hz;
+	priv->spi->mode = spi->mode;
+	priv->spi->bits_per_word = spi->bits_per_word;
+
+	ret = mux_control_select(priv->mux, spi->chip_select);
+	if (ret)
+		return ret;
+
+	priv->current_cs = spi->chip_select;
+
+	return 0;
+}
+
+static int spi_mux_setup(struct spi_device *spi)
+{
+	struct spi_mux_priv *priv = spi_controller_get_devdata(spi->controller);
+
+	/*
+	 * can be called multiple times, won't do a valid setup now but we will
+	 * change the settings when we do a transfer (necessary because we
+	 * can't predict from which device it will be anyway)
+	 */
+	return spi_setup(priv->spi);
+}
+
+static void spi_mux_complete_cb(void *context)
+{
+	struct spi_mux_priv *priv = (struct spi_mux_priv *)context;
+	struct spi_controller *ctlr = spi_get_drvdata(priv->spi);
+	struct spi_message *m = ctlr->cur_msg;
+
+	m->complete = priv->child_msg_complete;
+	m->context = priv->child_msg_context;
+	m->spi = priv->child_msg_dev;
+	spi_finalize_current_message(ctlr);
+	mux_control_deselect(priv->mux);
+}
+
+static int spi_mux_transfer_one_message(struct spi_controller *ctlr,
+						struct spi_message *m)
+{
+	struct spi_mux_priv *priv = spi_controller_get_devdata(ctlr);
+	struct spi_device *spi = m->spi;
+	int ret;
+
+	ret = spi_mux_select(spi);
+	if (ret)
+		return ret;
+
+	/*
+	 * Replace the complete callback, context and spi_device with our own
+	 * pointers. Save originals
+	 */
+	priv->child_msg_complete = m->complete;
+	priv->child_msg_context = m->context;
+	priv->child_msg_dev = m->spi;
+
+	m->complete = spi_mux_complete_cb;
+	m->context = priv;
+	m->spi = priv->spi;
+
+	/* do the transfer */
+	return spi_async(priv->spi, m);
+}
+
+static int spi_mux_probe(struct spi_device *spi)
+{
+	struct spi_controller *ctlr;
+	struct spi_mux_priv *priv;
+	int ret;
+
+	ctlr = spi_alloc_master(&spi->dev, sizeof(*priv));
+	if (!ctlr)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, ctlr);
+	priv = spi_controller_get_devdata(ctlr);
+	priv->spi = spi;
+
+	priv->mux = devm_mux_control_get(&spi->dev, NULL);
+	if (IS_ERR(priv->mux)) {
+		ret = PTR_ERR(priv->mux);
+		if (ret != -EPROBE_DEFER)
+			dev_err(&spi->dev, "failed to get control-mux\n");
+		goto err_put_ctlr;
+	}
+
+	priv->current_cs = SPI_MUX_NO_CS;
+
+	/* supported modes are the same as our parent's */
+	ctlr->mode_bits = spi->controller->mode_bits;
+	ctlr->flags = spi->controller->flags;
+	ctlr->transfer_one_message = spi_mux_transfer_one_message;
+	ctlr->setup = spi_mux_setup;
+	ctlr->num_chipselect = mux_control_states(priv->mux);
+	ctlr->bus_num = -1;
+	ctlr->dev.of_node = spi->dev.of_node;
+
+	ret = devm_spi_register_controller(&spi->dev, ctlr);
+	if (ret)
+		goto err_put_ctlr;
+
+	return 0;
+
+err_put_ctlr:
+	spi_controller_put(ctlr);
+
+	return ret;
+}
+
+static const struct of_device_id spi_mux_of_match[] = {
+	{ .compatible = "spi-mux" },
+	{ }
+};
+
+static struct spi_driver spi_mux_driver = {
+	.probe  = spi_mux_probe,
+	.driver = {
+		.name   = "spi-mux",
+		.of_match_table = spi_mux_of_match,
+	},
+};
+
+module_spi_driver(spi_mux_driver);
+
+MODULE_DESCRIPTION("SPI multiplexer");
+MODULE_LICENSE("GPL");
diff --git a/drivers/spi/spi-mxs.c b/drivers/spi/spi-mxs.c
index dce85ee07cd0..918918a9e049 100644
--- a/drivers/spi/spi-mxs.c
+++ b/drivers/spi/spi-mxs.c
@@ -22,7 +22,6 @@
 #include <linux/ioport.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
@@ -32,7 +31,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/completion.h>
-#include <linux/gpio.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/regulator/consumer.h>
 #include <linux/pm_runtime.h>
 #include <linux/module.h>
diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c
index 8c5084a3a617..1ccda82da206 100644
--- a/drivers/spi/spi-nxp-fspi.c
+++ b/drivers/spi/spi-nxp-fspi.c
@@ -307,6 +307,7 @@
 
 #define POLL_TOUT		5000
 #define NXP_FSPI_MAX_CHIPSELECT		4
+#define NXP_FSPI_MIN_IOMAP	SZ_4M
 
 struct nxp_fspi_devtype_data {
 	unsigned int rxfifo;
@@ -324,11 +325,29 @@ static const struct nxp_fspi_devtype_data lx2160a_data = {
 	.little_endian = true,  /* little-endian    */
 };
 
+static const struct nxp_fspi_devtype_data imx8mm_data = {
+	.rxfifo = SZ_512,       /* (64  * 64 bits)  */
+	.txfifo = SZ_1K,        /* (128 * 64 bits)  */
+	.ahb_buf_size = SZ_2K,  /* (256 * 64 bits)  */
+	.quirks = 0,
+	.little_endian = true,  /* little-endian    */
+};
+
+static const struct nxp_fspi_devtype_data imx8qxp_data = {
+	.rxfifo = SZ_512,       /* (64  * 64 bits)  */
+	.txfifo = SZ_1K,        /* (128 * 64 bits)  */
+	.ahb_buf_size = SZ_2K,  /* (256 * 64 bits)  */
+	.quirks = 0,
+	.little_endian = true,  /* little-endian    */
+};
+
 struct nxp_fspi {
 	void __iomem *iobase;
 	void __iomem *ahb_addr;
 	u32 memmap_phy;
 	u32 memmap_phy_size;
+	u32 memmap_start;
+	u32 memmap_len;
 	struct clk *clk, *clk_en;
 	struct device *dev;
 	struct completion c;
@@ -641,12 +660,35 @@ static void nxp_fspi_select_mem(struct nxp_fspi *f, struct spi_device *spi)
 	f->selected = spi->chip_select;
 }
 
-static void nxp_fspi_read_ahb(struct nxp_fspi *f, const struct spi_mem_op *op)
+static int nxp_fspi_read_ahb(struct nxp_fspi *f, const struct spi_mem_op *op)
 {
+	u32 start = op->addr.val;
 	u32 len = op->data.nbytes;
 
+	/* if necessary, ioremap before AHB read */
+	if ((!f->ahb_addr) || start < f->memmap_start ||
+	     start + len > f->memmap_start + f->memmap_len) {
+		if (f->ahb_addr)
+			iounmap(f->ahb_addr);
+
+		f->memmap_start = start;
+		f->memmap_len = len > NXP_FSPI_MIN_IOMAP ?
+				len : NXP_FSPI_MIN_IOMAP;
+
+		f->ahb_addr = ioremap_wc(f->memmap_phy + f->memmap_start,
+					 f->memmap_len);
+
+		if (!f->ahb_addr) {
+			dev_err(f->dev, "failed to alloc memory\n");
+			return -ENOMEM;
+		}
+	}
+
 	/* Read out the data directly from the AHB buffer. */
-	memcpy_fromio(op->data.buf.in, (f->ahb_addr + op->addr.val), len);
+	memcpy_fromio(op->data.buf.in,
+		      f->ahb_addr + start - f->memmap_start, len);
+
+	return 0;
 }
 
 static void nxp_fspi_fill_txfifo(struct nxp_fspi *f,
@@ -806,7 +848,7 @@ static int nxp_fspi_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 	 */
 	if (op->data.nbytes > (f->devtype_data->rxfifo - 4) &&
 	    op->data.dir == SPI_MEM_DATA_IN) {
-		nxp_fspi_read_ahb(f, op);
+		err = nxp_fspi_read_ahb(f, op);
 	} else {
 		if (op->data.nbytes && op->data.dir == SPI_MEM_DATA_OUT)
 			nxp_fspi_fill_txfifo(f, op);
@@ -871,8 +913,9 @@ static int nxp_fspi_default_setup(struct nxp_fspi *f)
 	fspi_writel(f, FSPI_DLLBCR_OVRDEN, base + FSPI_DLLBCR);
 
 	/* enable module */
-	fspi_writel(f, FSPI_MCR0_AHB_TIMEOUT(0xFF) | FSPI_MCR0_IP_TIMEOUT(0xFF),
-		 base + FSPI_MCR0);
+	fspi_writel(f, FSPI_MCR0_AHB_TIMEOUT(0xFF) |
+		    FSPI_MCR0_IP_TIMEOUT(0xFF) | (u32) FSPI_MCR0_OCTCOMB_EN,
+		    base + FSPI_MCR0);
 
 	/*
 	 * Disable same device enable bit and configure all slave devices
@@ -976,9 +1019,8 @@ static int nxp_fspi_probe(struct platform_device *pdev)
 
 	/* find the resources - controller memory mapped space */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fspi_mmap");
-	f->ahb_addr = devm_ioremap_resource(dev, res);
-	if (IS_ERR(f->ahb_addr)) {
-		ret = PTR_ERR(f->ahb_addr);
+	if (!res) {
+		ret = -ENODEV;
 		goto err_put_ctrl;
 	}
 
@@ -1057,6 +1099,9 @@ static int nxp_fspi_remove(struct platform_device *pdev)
 
 	mutex_destroy(&f->lock);
 
+	if (f->ahb_addr)
+		iounmap(f->ahb_addr);
+
 	return 0;
 }
 
@@ -1076,6 +1121,8 @@ static int nxp_fspi_resume(struct device *dev)
 
 static const struct of_device_id nxp_fspi_dt_ids[] = {
 	{ .compatible = "nxp,lx2160a-fspi", .data = (void *)&lx2160a_data, },
+	{ .compatible = "nxp,imx8mm-fspi", .data = (void *)&imx8mm_data, },
+	{ .compatible = "nxp,imx8qxp-fspi", .data = (void *)&imx8qxp_data, },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, nxp_fspi_dt_ids);
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 2e318158fca9..73d2a65d0b6e 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -192,6 +192,11 @@ static bool is_quark_x1000_ssp(const struct driver_data *drv_data)
 	return drv_data->ssp_type == QUARK_X1000_SSP;
 }
 
+static bool is_mmp2_ssp(const struct driver_data *drv_data)
+{
+	return drv_data->ssp_type == MMP2_SSP;
+}
+
 static u32 pxa2xx_spi_get_ssrc1_change_mask(const struct driver_data *drv_data)
 {
 	switch (drv_data->ssp_type) {
@@ -486,8 +491,8 @@ int pxa2xx_spi_flush(struct driver_data *drv_data)
 
 static void pxa2xx_spi_off(struct driver_data *drv_data)
 {
-	/* On MMP, disabling SSE seems to corrupt the rx fifo */
-	if (drv_data->ssp_type == MMP2_SSP)
+	/* On MMP, disabling SSE seems to corrupt the Rx FIFO */
+	if (is_mmp2_ssp(drv_data))
 		return;
 
 	pxa2xx_spi_write(drv_data, SSCR0,
@@ -1093,7 +1098,7 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 	    || (pxa2xx_spi_read(drv_data, SSCR1) & change_mask)
 	    != (cr1 & change_mask)) {
 		/* stop the SSP, and update the other bits */
-		if (drv_data->ssp_type != MMP2_SSP)
+		if (!is_mmp2_ssp(drv_data))
 			pxa2xx_spi_write(drv_data, SSCR0, cr0 & ~SSCR0_SSE);
 		if (!pxa25x_ssp_comp(drv_data))
 			pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
@@ -1107,7 +1112,7 @@ static int pxa2xx_spi_transfer_one(struct spi_controller *controller,
 			pxa2xx_spi_write(drv_data, SSTO, chip->timeout);
 	}
 
-	if (drv_data->ssp_type == MMP2_SSP) {
+	if (is_mmp2_ssp(drv_data)) {
 		u8 tx_level = (pxa2xx_spi_read(drv_data, SSSR)
 					& SSSR_TFL_MASK) >> 8;
 
@@ -1571,18 +1576,18 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 	else if (pcidev_id)
 		type = (enum pxa_ssp_type)pcidev_id->driver_data;
 	else
-		return NULL;
+		return ERR_PTR(-EINVAL);
 
 	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	ssp = &pdata->ssp;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ssp->mmio_base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(ssp->mmio_base))
-		return NULL;
+		return ERR_CAST(ssp->mmio_base);
 
 	ssp->phys_base = res->start;
 
@@ -1596,11 +1601,11 @@ pxa2xx_spi_init_pdata(struct platform_device *pdev)
 
 	ssp->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(ssp->clk))
-		return NULL;
+		return ERR_CAST(ssp->clk);
 
 	ssp->irq = platform_get_irq(pdev, 0);
 	if (ssp->irq < 0)
-		return NULL;
+		return ERR_PTR(ssp->irq);
 
 	ssp->type = type;
 	ssp->dev = &pdev->dev;
@@ -1657,9 +1662,9 @@ static int pxa2xx_spi_probe(struct platform_device *pdev)
 	platform_info = dev_get_platdata(dev);
 	if (!platform_info) {
 		platform_info = pxa2xx_spi_init_pdata(pdev);
-		if (!platform_info) {
+		if (IS_ERR(platform_info)) {
 			dev_err(&pdev->dev, "missing platform data\n");
-			return -ENODEV;
+			return PTR_ERR(platform_info);
 		}
 	}
 
@@ -1907,11 +1912,7 @@ out_error_controller_alloc:
 static int pxa2xx_spi_remove(struct platform_device *pdev)
 {
 	struct driver_data *drv_data = platform_get_drvdata(pdev);
-	struct ssp_device *ssp;
-
-	if (!drv_data)
-		return 0;
-	ssp = drv_data->ssp;
+	struct ssp_device *ssp = drv_data->ssp;
 
 	pm_runtime_get_sync(&pdev->dev);
 
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 2cc6d9951b52..70ef63e0b6b8 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -843,14 +843,17 @@ static const struct dev_pm_ops rockchip_spi_pm = {
 };
 
 static const struct of_device_id rockchip_spi_dt_match[] = {
-	{ .compatible = "rockchip,rv1108-spi", },
+	{ .compatible = "rockchip,px30-spi", },
 	{ .compatible = "rockchip,rk3036-spi", },
 	{ .compatible = "rockchip,rk3066-spi", },
 	{ .compatible = "rockchip,rk3188-spi", },
 	{ .compatible = "rockchip,rk3228-spi", },
 	{ .compatible = "rockchip,rk3288-spi", },
+	{ .compatible = "rockchip,rk3308-spi", },
+	{ .compatible = "rockchip,rk3328-spi", },
 	{ .compatible = "rockchip,rk3368-spi", },
 	{ .compatible = "rockchip,rk3399-spi", },
+	{ .compatible = "rockchip,rv1108-spi", },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, rockchip_spi_dt_match);
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index 85575d45901c..06192c9ea813 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -24,6 +24,7 @@
 #include <linux/sh_dma.h>
 #include <linux/spi/spi.h>
 #include <linux/spi/rspi.h>
+#include <linux/spinlock.h>
 
 #define RSPI_SPCR		0x00	/* Control Register */
 #define RSPI_SSLP		0x01	/* Slave Select Polarity Register */
@@ -79,8 +80,7 @@
 #define SPCR_BSWAP		0x01	/* Byte Swap of read-data for DMAC */
 
 /* SSLP - Slave Select Polarity Register */
-#define SSLP_SSL1P		0x02	/* SSL1 Signal Polarity Setting */
-#define SSLP_SSL0P		0x01	/* SSL0 Signal Polarity Setting */
+#define SSLP_SSLP(i)		BIT(i)	/* SSLi Signal Polarity Setting */
 
 /* SPPCR - Pin Control Register */
 #define SPPCR_MOIFE		0x20	/* MOSI Idle Value Fixing Enable */
@@ -181,7 +181,9 @@ struct rspi_data {
 	void __iomem *addr;
 	u32 max_speed_hz;
 	struct spi_controller *ctlr;
+	struct platform_device *pdev;
 	wait_queue_head_t wait;
+	spinlock_t lock;		/* Protects RMW-access to RSPI_SSLP */
 	struct clk *clk;
 	u16 spcmd;
 	u8 spsr;
@@ -239,7 +241,7 @@ struct spi_ops {
 	int (*set_config_register)(struct rspi_data *rspi, int access_size);
 	int (*transfer_one)(struct spi_controller *ctlr,
 			    struct spi_device *spi, struct spi_transfer *xfer);
-	u16 mode_bits;
+	u16 extra_mode_bits;
 	u16 flags;
 	u16 fifo_size;
 	u8 num_hw_ss;
@@ -919,6 +921,29 @@ static int qspi_setup_sequencer(struct rspi_data *rspi,
 	return 0;
 }
 
+static int rspi_setup(struct spi_device *spi)
+{
+	struct rspi_data *rspi = spi_controller_get_devdata(spi->controller);
+	u8 sslp;
+
+	if (spi->cs_gpiod)
+		return 0;
+
+	pm_runtime_get_sync(&rspi->pdev->dev);
+	spin_lock_irq(&rspi->lock);
+
+	sslp = rspi_read8(rspi, RSPI_SSLP);
+	if (spi->mode & SPI_CS_HIGH)
+		sslp |= SSLP_SSLP(spi->chip_select);
+	else
+		sslp &= ~SSLP_SSLP(spi->chip_select);
+	rspi_write8(rspi, sslp, RSPI_SSLP);
+
+	spin_unlock_irq(&rspi->lock);
+	pm_runtime_put(&rspi->pdev->dev);
+	return 0;
+}
+
 static int rspi_prepare_message(struct spi_controller *ctlr,
 				struct spi_message *msg)
 {
@@ -933,6 +958,8 @@ static int rspi_prepare_message(struct spi_controller *ctlr,
 		rspi->spcmd |= SPCMD_CPOL;
 	if (spi->mode & SPI_CPHA)
 		rspi->spcmd |= SPCMD_CPHA;
+	if (spi->mode & SPI_LSB_FIRST)
+		rspi->spcmd |= SPCMD_LSBF;
 
 	/* Configure slave signal to assert */
 	rspi->spcmd |= SPCMD_SSLA(spi->cs_gpiod ? rspi->ctlr->unused_native_cs
@@ -1122,7 +1149,6 @@ static int rspi_remove(struct platform_device *pdev)
 static const struct spi_ops rspi_ops = {
 	.set_config_register =	rspi_set_config_register,
 	.transfer_one =		rspi_transfer_one,
-	.mode_bits =		SPI_CPHA | SPI_CPOL | SPI_LOOP,
 	.flags =		SPI_CONTROLLER_MUST_TX,
 	.fifo_size =		8,
 	.num_hw_ss =		2,
@@ -1131,7 +1157,6 @@ static const struct spi_ops rspi_ops = {
 static const struct spi_ops rspi_rz_ops = {
 	.set_config_register =	rspi_rz_set_config_register,
 	.transfer_one =		rspi_rz_transfer_one,
-	.mode_bits =		SPI_CPHA | SPI_CPOL | SPI_LOOP,
 	.flags =		SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX,
 	.fifo_size =		8,	/* 8 for TX, 32 for RX */
 	.num_hw_ss =		1,
@@ -1140,8 +1165,7 @@ static const struct spi_ops rspi_rz_ops = {
 static const struct spi_ops qspi_ops = {
 	.set_config_register =	qspi_set_config_register,
 	.transfer_one =		qspi_transfer_one,
-	.mode_bits =		SPI_CPHA | SPI_CPOL | SPI_LOOP |
-				SPI_TX_DUAL | SPI_TX_QUAD |
+	.extra_mode_bits =	SPI_TX_DUAL | SPI_TX_QUAD |
 				SPI_RX_DUAL | SPI_RX_QUAD,
 	.flags =		SPI_CONTROLLER_MUST_RX | SPI_CONTROLLER_MUST_TX,
 	.fifo_size =		32,
@@ -1249,16 +1273,20 @@ static int rspi_probe(struct platform_device *pdev)
 		goto error1;
 	}
 
+	rspi->pdev = pdev;
 	pm_runtime_enable(&pdev->dev);
 
 	init_waitqueue_head(&rspi->wait);
+	spin_lock_init(&rspi->lock);
 
 	ctlr->bus_num = pdev->id;
+	ctlr->setup = rspi_setup;
 	ctlr->auto_runtime_pm = true;
 	ctlr->transfer_one = ops->transfer_one;
 	ctlr->prepare_message = rspi_prepare_message;
 	ctlr->unprepare_message = rspi_unprepare_message;
-	ctlr->mode_bits = ops->mode_bits;
+	ctlr->mode_bits = SPI_CPHA | SPI_CPOL | SPI_CS_HIGH | SPI_LSB_FIRST |
+			  SPI_LOOP | ops->extra_mode_bits;
 	ctlr->flags = ops->flags;
 	ctlr->dev.of_node = pdev->dev.of_node;
 	ctlr->use_gpio_descriptors = true;
diff --git a/drivers/spi/spi-s3c24xx.c b/drivers/spi/spi-s3c24xx.c
index 2d6e37f25e2d..2cb3b611c294 100644
--- a/drivers/spi/spi-s3c24xx.c
+++ b/drivers/spi/spi-s3c24xx.c
@@ -227,7 +227,7 @@ static inline unsigned int hw_txbyte(struct s3c24xx_spi *hw, int count)
 struct spi_fiq_code {
 	u32	length;
 	u32	ack_offset;
-	u8	data[0];
+	u8	data[];
 };
 
 extern struct spi_fiq_code s3c24xx_spi_fiq_txrx;
diff --git a/drivers/spi/spi-stm32-qspi.c b/drivers/spi/spi-stm32-qspi.c
index 4ef569b47aa6..d066f5144c3e 100644
--- a/drivers/spi/spi-stm32-qspi.c
+++ b/drivers/spi/spi-stm32-qspi.c
@@ -565,7 +565,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	qspi->io_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(qspi->io_base)) {
 		ret = PTR_ERR(qspi->io_base);
-		goto err;
+		goto err_master_put;
 	}
 
 	qspi->phys_base = res->start;
@@ -574,24 +574,26 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	qspi->mm_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(qspi->mm_base)) {
 		ret = PTR_ERR(qspi->mm_base);
-		goto err;
+		goto err_master_put;
 	}
 
 	qspi->mm_size = resource_size(res);
 	if (qspi->mm_size > STM32_QSPI_MAX_MMAP_SZ) {
 		ret = -EINVAL;
-		goto err;
+		goto err_master_put;
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
-		return irq;
+	if (irq < 0) {
+		ret = irq;
+		goto err_master_put;
+	}
 
 	ret = devm_request_irq(dev, irq, stm32_qspi_irq, 0,
 			       dev_name(dev), qspi);
 	if (ret) {
 		dev_err(dev, "failed to request irq\n");
-		goto err;
+		goto err_master_put;
 	}
 
 	init_completion(&qspi->data_completion);
@@ -599,23 +601,27 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	qspi->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(qspi->clk)) {
 		ret = PTR_ERR(qspi->clk);
-		goto err;
+		goto err_master_put;
 	}
 
 	qspi->clk_rate = clk_get_rate(qspi->clk);
 	if (!qspi->clk_rate) {
 		ret = -EINVAL;
-		goto err;
+		goto err_master_put;
 	}
 
 	ret = clk_prepare_enable(qspi->clk);
 	if (ret) {
 		dev_err(dev, "can not enable the clock\n");
-		goto err;
+		goto err_master_put;
 	}
 
 	rstc = devm_reset_control_get_exclusive(dev, NULL);
-	if (!IS_ERR(rstc)) {
+	if (IS_ERR(rstc)) {
+		ret = PTR_ERR(rstc);
+		if (ret == -EPROBE_DEFER)
+			goto err_qspi_release;
+	} else {
 		reset_control_assert(rstc);
 		udelay(2);
 		reset_control_deassert(rstc);
@@ -625,7 +631,7 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, qspi);
 	ret = stm32_qspi_dma_setup(qspi);
 	if (ret)
-		goto err;
+		goto err_qspi_release;
 
 	mutex_init(&qspi->lock);
 
@@ -641,8 +647,9 @@ static int stm32_qspi_probe(struct platform_device *pdev)
 	if (!ret)
 		return 0;
 
-err:
+err_qspi_release:
 	stm32_qspi_release(qspi);
+err_master_put:
 	spi_master_put(qspi->ctrl);
 
 	return ret;
diff --git a/drivers/spi/spi-stm32.c b/drivers/spi/spi-stm32.c
index e041f9c4ec47..44ac6eb3298d 100644
--- a/drivers/spi/spi-stm32.c
+++ b/drivers/spi/spi-stm32.c
@@ -175,7 +175,7 @@
 #define SPI_DMA_MIN_BYTES	16
 
 /**
- * stm32_spi_reg - stm32 SPI register & bitfield desc
+ * struct stm32_spi_reg - stm32 SPI register & bitfield desc
  * @reg:		register offset
  * @mask:		bitfield mask
  * @shift:		left shift
@@ -187,16 +187,16 @@ struct stm32_spi_reg {
 };
 
 /**
- * stm32_spi_regspec - stm32 registers definition, compatible dependent data
- * en: enable register and SPI enable bit
- * dma_rx_en: SPI DMA RX enable register end SPI DMA RX enable bit
- * dma_tx_en: SPI DMA TX enable register end SPI DMA TX enable bit
- * cpol: clock polarity register and polarity bit
- * cpha: clock phase register and phase bit
- * lsb_first: LSB transmitted first register and bit
- * br: baud rate register and bitfields
- * rx: SPI RX data register
- * tx: SPI TX data register
+ * struct stm32_spi_regspec - stm32 registers definition, compatible dependent data
+ * @en: enable register and SPI enable bit
+ * @dma_rx_en: SPI DMA RX enable register end SPI DMA RX enable bit
+ * @dma_tx_en: SPI DMA TX enable register end SPI DMA TX enable bit
+ * @cpol: clock polarity register and polarity bit
+ * @cpha: clock phase register and phase bit
+ * @lsb_first: LSB transmitted first register and bit
+ * @br: baud rate register and bitfields
+ * @rx: SPI RX data register
+ * @tx: SPI TX data register
  */
 struct stm32_spi_regspec {
 	const struct stm32_spi_reg en;
@@ -213,7 +213,7 @@ struct stm32_spi_regspec {
 struct stm32_spi;
 
 /**
- * stm32_spi_cfg - stm32 compatible configuration data
+ * struct stm32_spi_cfg - stm32 compatible configuration data
  * @regs: registers descriptions
  * @get_fifo_size: routine to get fifo size
  * @get_bpw_mask: routine to get bits per word mask
@@ -223,13 +223,13 @@ struct stm32_spi;
  * @set_mode: routine to configure registers to desired mode
  * @set_data_idleness: optional routine to configure registers to desired idle
  * time between frames (if driver has this functionality)
- * set_number_of_data: optional routine to configure registers to desired
+ * @set_number_of_data: optional routine to configure registers to desired
  * number of data (if driver has this functionality)
  * @can_dma: routine to determine if the transfer is eligible for DMA use
  * @transfer_one_dma_start: routine to start transfer a single spi_transfer
  * using DMA
- * @dma_rx cb: routine to call after DMA RX channel operation is complete
- * @dma_tx cb: routine to call after DMA TX channel operation is complete
+ * @dma_rx_cb: routine to call after DMA RX channel operation is complete
+ * @dma_tx_cb: routine to call after DMA TX channel operation is complete
  * @transfer_one_irq: routine to configure interrupts for driver
  * @irq_handler_event: Interrupt handler for SPI controller events
  * @irq_handler_thread: thread of interrupt handler for SPI controller
@@ -587,6 +587,7 @@ static void stm32f4_spi_read_rx(struct stm32_spi *spi)
 /**
  * stm32h7_spi_read_rxfifo - Read bytes in Receive Data Register
  * @spi: pointer to the spi controller data structure
+ * @flush: boolean indicating that FIFO should be flushed
  *
  * Write in rx_buf depends on remaining bytes to avoid to write beyond
  * rx_buf end.
@@ -756,6 +757,9 @@ static void stm32h7_spi_disable(struct stm32_spi *spi)
 
 /**
  * stm32_spi_can_dma - Determine if the transfer is eligible for DMA use
+ * @master: controller master interface
+ * @spi_dev: pointer to the spi device
+ * @transfer: pointer to spi transfer
  *
  * If driver has fifo and the current transfer size is greater than fifo size,
  * use DMA. Otherwise use DMA for transfer longer than defined DMA min bytes.
@@ -974,6 +978,8 @@ static irqreturn_t stm32h7_spi_irq_thread(int irq, void *dev_id)
 
 /**
  * stm32_spi_prepare_msg - set up the controller to transfer a single message
+ * @master: controller master interface
+ * @msg: pointer to spi message
  */
 static int stm32_spi_prepare_msg(struct spi_master *master,
 				 struct spi_message *msg)
@@ -1026,6 +1032,7 @@ static int stm32_spi_prepare_msg(struct spi_master *master,
 
 /**
  * stm32f4_spi_dma_tx_cb - dma callback
+ * @data: pointer to the spi controller data structure
  *
  * DMA callback is called when the transfer is complete for DMA TX channel.
  */
@@ -1041,6 +1048,7 @@ static void stm32f4_spi_dma_tx_cb(void *data)
 
 /**
  * stm32f4_spi_dma_rx_cb - dma callback
+ * @data: pointer to the spi controller data structure
  *
  * DMA callback is called when the transfer is complete for DMA RX channel.
  */
@@ -1054,6 +1062,7 @@ static void stm32f4_spi_dma_rx_cb(void *data)
 
 /**
  * stm32h7_spi_dma_cb - dma callback
+ * @data: pointer to the spi controller data structure
  *
  * DMA callback is called when the transfer is complete or when an error
  * occurs. If the transfer is complete, EOT flag is raised.
@@ -1079,6 +1088,9 @@ static void stm32h7_spi_dma_cb(void *data)
 /**
  * stm32_spi_dma_config - configure dma slave channel depending on current
  *			  transfer bits_per_word.
+ * @spi: pointer to the spi controller data structure
+ * @dma_conf: pointer to the dma_slave_config structure
+ * @dir: direction of the dma transfer
  */
 static void stm32_spi_dma_config(struct stm32_spi *spi,
 				 struct dma_slave_config *dma_conf,
@@ -1126,6 +1138,7 @@ static void stm32_spi_dma_config(struct stm32_spi *spi,
 /**
  * stm32f4_spi_transfer_one_irq - transfer a single spi_transfer using
  *				  interrupts
+ * @spi: pointer to the spi controller data structure
  *
  * It must returns 0 if the transfer is finished or 1 if the transfer is still
  * in progress.
@@ -1166,6 +1179,7 @@ static int stm32f4_spi_transfer_one_irq(struct stm32_spi *spi)
 /**
  * stm32h7_spi_transfer_one_irq - transfer a single spi_transfer using
  *				  interrupts
+ * @spi: pointer to the spi controller data structure
  *
  * It must returns 0 if the transfer is finished or 1 if the transfer is still
  * in progress.
@@ -1207,6 +1221,7 @@ static int stm32h7_spi_transfer_one_irq(struct stm32_spi *spi)
 /**
  * stm32f4_spi_transfer_one_dma_start - Set SPI driver registers to start
  *					transfer using DMA
+ * @spi: pointer to the spi controller data structure
  */
 static void stm32f4_spi_transfer_one_dma_start(struct stm32_spi *spi)
 {
@@ -1227,6 +1242,7 @@ static void stm32f4_spi_transfer_one_dma_start(struct stm32_spi *spi)
 /**
  * stm32h7_spi_transfer_one_dma_start - Set SPI driver registers to start
  *					transfer using DMA
+ * @spi: pointer to the spi controller data structure
  */
 static void stm32h7_spi_transfer_one_dma_start(struct stm32_spi *spi)
 {
@@ -1243,6 +1259,8 @@ static void stm32h7_spi_transfer_one_dma_start(struct stm32_spi *spi)
 
 /**
  * stm32_spi_transfer_one_dma - transfer a single spi_transfer using DMA
+ * @spi: pointer to the spi controller data structure
+ * @xfer: pointer to the spi_transfer structure
  *
  * It must returns 0 if the transfer is finished or 1 if the transfer is still
  * in progress.
@@ -1405,7 +1423,7 @@ static void stm32_spi_set_mbr(struct stm32_spi *spi, u32 mbrdiv)
 /**
  * stm32_spi_communication_type - return transfer communication type
  * @spi_dev: pointer to the spi device
- * transfer: pointer to spi transfer
+ * @transfer: pointer to spi transfer
  */
 static unsigned int stm32_spi_communication_type(struct spi_device *spi_dev,
 						 struct spi_transfer *transfer)
@@ -1522,7 +1540,7 @@ static void stm32h7_spi_data_idleness(struct stm32_spi *spi, u32 len)
 /**
  * stm32h7_spi_number_of_data - configure number of data at current transfer
  * @spi: pointer to the spi controller data structure
- * @len: transfer length
+ * @nb_words: transfer length (in words)
  */
 static int stm32h7_spi_number_of_data(struct stm32_spi *spi, u32 nb_words)
 {
@@ -1546,6 +1564,9 @@ static int stm32h7_spi_number_of_data(struct stm32_spi *spi, u32 nb_words)
  * stm32_spi_transfer_one_setup - common setup to transfer a single
  *				  spi_transfer either using DMA or
  *				  interrupts.
+ * @spi: pointer to the spi controller data structure
+ * @spi_dev: pointer to the spi device
+ * @transfer: pointer to spi transfer
  */
 static int stm32_spi_transfer_one_setup(struct stm32_spi *spi,
 					struct spi_device *spi_dev,
@@ -1625,6 +1646,9 @@ out:
 
 /**
  * stm32_spi_transfer_one - transfer a single spi_transfer
+ * @master: controller master interface
+ * @spi_dev: pointer to the spi device
+ * @transfer: pointer to spi transfer
  *
  * It must return 0 if the transfer is finished or 1 if the transfer is still
  * in progress.
@@ -1658,6 +1682,8 @@ static int stm32_spi_transfer_one(struct spi_master *master,
 
 /**
  * stm32_spi_unprepare_msg - relax the hardware
+ * @master: controller master interface
+ * @msg: pointer to the spi message
  */
 static int stm32_spi_unprepare_msg(struct spi_master *master,
 				   struct spi_message *msg)
@@ -1671,6 +1697,7 @@ static int stm32_spi_unprepare_msg(struct spi_master *master,
 
 /**
  * stm32f4_spi_config - Configure SPI controller as SPI master
+ * @spi: pointer to the spi controller data structure
  */
 static int stm32f4_spi_config(struct stm32_spi *spi)
 {
@@ -1701,6 +1728,7 @@ static int stm32f4_spi_config(struct stm32_spi *spi)
 
 /**
  * stm32h7_spi_config - Configure SPI controller as SPI master
+ * @spi: pointer to the spi controller data structure
  */
 static int stm32h7_spi_config(struct stm32_spi *spi)
 {
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 755221bc3745..c92c89467e7e 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -510,6 +510,7 @@ struct spi_device *spi_alloc_device(struct spi_controller *ctlr)
 	spi->dev.bus = &spi_bus_type;
 	spi->dev.release = spidev_release;
 	spi->cs_gpio = -ENOENT;
+	spi->mode = ctlr->buswidth_override_bits;
 
 	spin_lock_init(&spi->statistics.lock);
 
@@ -1514,17 +1515,15 @@ void spi_take_timestamp_pre(struct spi_controller *ctlr,
 	if (!xfer->ptp_sts)
 		return;
 
-	if (xfer->timestamped_pre)
+	if (xfer->timestamped)
 		return;
 
-	if (progress < xfer->ptp_sts_word_pre)
+	if (progress > xfer->ptp_sts_word_pre)
 		return;
 
 	/* Capture the resolution of the timestamp */
 	xfer->ptp_sts_word_pre = progress;
 
-	xfer->timestamped_pre = true;
-
 	if (irqs_off) {
 		local_irq_save(ctlr->irq_flags);
 		preempt_disable();
@@ -1553,7 +1552,7 @@ void spi_take_timestamp_post(struct spi_controller *ctlr,
 	if (!xfer->ptp_sts)
 		return;
 
-	if (xfer->timestamped_post)
+	if (xfer->timestamped)
 		return;
 
 	if (progress < xfer->ptp_sts_word_post)
@@ -1569,7 +1568,7 @@ void spi_take_timestamp_post(struct spi_controller *ctlr,
 	/* Capture the resolution of the timestamp */
 	xfer->ptp_sts_word_post = progress;
 
-	xfer->timestamped_post = true;
+	xfer->timestamped = true;
 }
 EXPORT_SYMBOL_GPL(spi_take_timestamp_post);
 
@@ -1674,12 +1673,9 @@ void spi_finalize_current_message(struct spi_controller *ctlr)
 		}
 	}
 
-	if (unlikely(ctlr->ptp_sts_supported)) {
-		list_for_each_entry(xfer, &mesg->transfers, transfer_list) {
-			WARN_ON_ONCE(xfer->ptp_sts && !xfer->timestamped_pre);
-			WARN_ON_ONCE(xfer->ptp_sts && !xfer->timestamped_post);
-		}
-	}
+	if (unlikely(ctlr->ptp_sts_supported))
+		list_for_each_entry(xfer, &mesg->transfers, transfer_list)
+			WARN_ON_ONCE(xfer->ptp_sts && !xfer->timestamped);
 
 	spi_unmap_msg(ctlr, mesg);
 
@@ -1955,13 +1951,8 @@ static int of_spi_parse_dt(struct spi_controller *ctlr, struct spi_device *spi,
 		spi->mode |= SPI_CS_HIGH;
 
 	/* Device speed */
-	rc = of_property_read_u32(nc, "spi-max-frequency", &value);
-	if (rc) {
-		dev_err(&ctlr->dev,
-			"%pOF has no valid 'spi-max-frequency' property (%d)\n", nc, rc);
-		return rc;
-	}
-	spi->max_speed_hz = value;
+	if (!of_property_read_u32(nc, "spi-max-frequency", &value))
+		spi->max_speed_hz = value;
 
 	return 0;
 }
@@ -2181,9 +2172,10 @@ static acpi_status acpi_register_spi_device(struct spi_controller *ctlr,
 		return AE_NO_MEMORY;
 	}
 
+
 	ACPI_COMPANION_SET(&spi->dev, adev);
 	spi->max_speed_hz	= lookup.max_speed_hz;
-	spi->mode		= lookup.mode;
+	spi->mode		|= lookup.mode;
 	spi->irq		= lookup.irq;
 	spi->bits_per_word	= lookup.bits_per_word;
 	spi->chip_select	= lookup.chip_select;
@@ -4034,7 +4026,7 @@ static struct spi_device *acpi_spi_find_device_by_adev(struct acpi_device *adev)
 	struct device *dev;
 
 	dev = bus_find_device_by_acpi_dev(&spi_bus_type, adev);
-	return dev ? to_spi_device(dev) : NULL;
+	return to_spi_device(dev);
 }
 
 static int acpi_spi_notify(struct notifier_block *nb, unsigned long value,
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index 2ab6e782f14c..80dd1025b953 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -275,14 +275,14 @@ static int spidev_message(struct spidev_data *spidev,
 #ifdef VERBOSE
 		dev_dbg(&spidev->spi->dev,
 			"  xfer len %u %s%s%s%dbits %u usec %u usec %uHz\n",
-			u_tmp->len,
-			u_tmp->rx_buf ? "rx " : "",
-			u_tmp->tx_buf ? "tx " : "",
-			u_tmp->cs_change ? "cs " : "",
-			u_tmp->bits_per_word ? : spidev->spi->bits_per_word,
-			u_tmp->delay_usecs,
-			u_tmp->word_delay_usecs,
-			u_tmp->speed_hz ? : spidev->spi->max_speed_hz);
+			k_tmp->len,
+			k_tmp->rx_buf ? "rx " : "",
+			k_tmp->tx_buf ? "tx " : "",
+			k_tmp->cs_change ? "cs " : "",
+			k_tmp->bits_per_word ? : spidev->spi->bits_per_word,
+			k_tmp->delay.value,
+			k_tmp->word_delay.value,
+			k_tmp->speed_hz ? : spidev->spi->max_speed_hz);
 #endif
 		spi_message_add_tail(k_tmp, &msg);
 	}
@@ -454,10 +454,11 @@ spidev_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 			spi->max_speed_hz = tmp;
 			retval = spi_setup(spi);
-			if (retval >= 0)
+			if (retval == 0) {
 				spidev->speed_hz = tmp;
-			else
-				dev_dbg(&spi->dev, "%d Hz (max)\n", tmp);
+				dev_dbg(&spi->dev, "%d Hz (max)\n",
+					spidev->speed_hz);
+			}
 			spi->max_speed_hz = save;
 		}
 		break;