Merge branch 'next' of https://source.denx.de/u-boot/custodians/u-boot-spi into next

- xSPI Octal DTR support (Pratyush Yadav)
- MXIC SPI driver (Zhengxun)

9 files changed, 1004 insertions, 43 deletions

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 1494c91763..e317d8a2c6 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -255,6 +255,13 @@ config MXS_SPI
 	  Enable the MXS SPI controller driver. This driver can be used
 	  on the i.MX23 and i.MX28 SoCs.
 
+config SPI_MXIC
+	bool "Macronix MX25F0A SPI controller"
+	help
+	  Enable the Macronix MX25F0A SPI controller driver. This driver
+	  can be used to access the SPI flash on platforms embedding
+	  this Macronix IP core.
+
 config NXP_FSPI
 	bool "NXP FlexSPI driver"
 	depends on SPI_MEM
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index cfe4fae1d4..3dc83089b8 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -51,6 +51,7 @@ obj-$(CONFIG_OMAP3_SPI) += omap3_spi.o
 obj-$(CONFIG_PIC32_SPI) += pic32_spi.o
 obj-$(CONFIG_PL022_SPI) += pl022_spi.o
 obj-$(CONFIG_SPI_QUP) += spi-qup.o
+obj-$(CONFIG_SPI_MXIC) += spi-mxic.o
 obj-$(CONFIG_RENESAS_RPC_SPI) += renesas_rpc_spi.o
 obj-$(CONFIG_ROCKCHIP_SPI) += rk_spi.o
 obj-$(CONFIG_SANDBOX_SPI) += sandbox_spi.o
diff --git a/drivers/spi/cadence_qspi.c b/drivers/spi/cadence_qspi.c
index 67980431ba..d1b3808c4d 100644
--- a/drivers/spi/cadence_qspi.c
+++ b/drivers/spi/cadence_qspi.c
@@ -20,6 +20,8 @@
 #include <linux/sizes.h>
 #include "cadence_qspi.h"
 
+#define NSEC_PER_SEC			1000000000L
+
 #define CQSPI_STIG_READ			0
 #define CQSPI_STIG_WRITE		1
 #define CQSPI_READ			2
@@ -41,20 +43,22 @@ static int cadence_spi_write_speed(struct udevice *bus, uint hz)
 	return 0;
 }
 
-static int cadence_spi_read_id(void *reg_base, u8 len, u8 *idcode)
+static int cadence_spi_read_id(struct cadence_spi_plat *plat, u8 len,
+			       u8 *idcode)
 {
 	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0x9F, 1),
 					  SPI_MEM_OP_NO_ADDR,
 					  SPI_MEM_OP_NO_DUMMY,
 					  SPI_MEM_OP_DATA_IN(len, idcode, 1));
 
-	return cadence_qspi_apb_command_read(reg_base, &op);
+	return cadence_qspi_apb_command_read(plat, &op);
 }
 
 /* Calibration sequence to determine the read data capture delay register */
 static int spi_calibration(struct udevice *bus, uint hz)
 {
 	struct cadence_spi_priv *priv = dev_get_priv(bus);
+	struct cadence_spi_plat *plat = dev_get_plat(bus);
 	void *base = priv->regbase;
 	unsigned int idcode = 0, temp = 0;
 	int err = 0, i, range_lo = -1, range_hi = -1;
@@ -69,7 +73,7 @@ static int spi_calibration(struct udevice *bus, uint hz)
 	cadence_qspi_apb_controller_enable(base);
 
 	/* read the ID which will be our golden value */
-	err = cadence_spi_read_id(base, 3, (u8 *)&idcode);
+	err = cadence_spi_read_id(plat, 3, (u8 *)&idcode);
 	if (err) {
 		puts("SF: Calibration failed (read)\n");
 		return err;
@@ -88,7 +92,7 @@ static int spi_calibration(struct udevice *bus, uint hz)
 		cadence_qspi_apb_controller_enable(base);
 
 		/* issue a RDID to get the ID value */
-		err = cadence_spi_read_id(base, 3, (u8 *)&temp);
+		err = cadence_spi_read_id(plat, 3, (u8 *)&temp);
 		if (err) {
 			puts("SF: Calibration failed (read)\n");
 			return err;
@@ -141,12 +145,20 @@ static int cadence_spi_set_speed(struct udevice *bus, uint hz)
 	cadence_qspi_apb_controller_disable(priv->regbase);
 
 	/*
-	 * Calibration required for different current SCLK speed, requested
-	 * SCLK speed or chip select
+	 * If the device tree already provides a read delay value, use that
+	 * instead of calibrating.
 	 */
-	if (priv->previous_hz != hz ||
-	    priv->qspi_calibrated_hz != hz ||
-	    priv->qspi_calibrated_cs != spi_chip_select(bus)) {
+	if (plat->read_delay >= 0) {
+		cadence_spi_write_speed(bus, hz);
+		cadence_qspi_apb_readdata_capture(priv->regbase, 1,
+						  plat->read_delay);
+	} else if (priv->previous_hz != hz ||
+		   priv->qspi_calibrated_hz != hz ||
+		   priv->qspi_calibrated_cs != spi_chip_select(bus)) {
+		/*
+		 * Calibration required for different current SCLK speed,
+		 * requested SCLK speed or chip select
+		 */
 		err = spi_calibration(bus, hz);
 		if (err)
 			return err;
@@ -200,6 +212,8 @@ static int cadence_spi_probe(struct udevice *bus)
 		priv->qspi_is_init = 1;
 	}
 
+	plat->wr_delay = 50 * DIV_ROUND_UP(NSEC_PER_SEC, plat->ref_clk_hz);
+
 	return 0;
 }
 
@@ -259,10 +273,14 @@ static int cadence_spi_mem_exec_op(struct spi_slave *spi,
 
 	switch (mode) {
 	case CQSPI_STIG_READ:
-		err = cadence_qspi_apb_command_read(base, op);
+		err = cadence_qspi_apb_command_read_setup(plat, op);
+		if (!err)
+			err = cadence_qspi_apb_command_read(plat, op);
 		break;
 	case CQSPI_STIG_WRITE:
-		err = cadence_qspi_apb_command_write(base, op);
+		err = cadence_qspi_apb_command_write_setup(plat, op);
+		if (!err)
+			err = cadence_qspi_apb_command_write(plat, op);
 		break;
 	case CQSPI_READ:
 		err = cadence_qspi_apb_read_setup(plat, op);
@@ -282,6 +300,26 @@ static int cadence_spi_mem_exec_op(struct spi_slave *spi,
 	return err;
 }
 
+static bool cadence_spi_mem_supports_op(struct spi_slave *slave,
+					const struct spi_mem_op *op)
+{
+	bool all_true, all_false;
+
+	all_true = op->cmd.dtr && op->addr.dtr && op->dummy.dtr &&
+		   op->data.dtr;
+	all_false = !op->cmd.dtr && !op->addr.dtr && !op->dummy.dtr &&
+		    !op->data.dtr;
+
+	/* Mixed DTR modes not supported. */
+	if (!(all_true || all_false))
+		return false;
+
+	if (all_true)
+		return spi_mem_dtr_supports_op(slave, op);
+	else
+		return spi_mem_default_supports_op(slave, op);
+}
+
 static int cadence_spi_of_to_plat(struct udevice *bus)
 {
 	struct cadence_spi_plat *plat = dev_get_plat(bus);
@@ -320,6 +358,14 @@ static int cadence_spi_of_to_plat(struct udevice *bus)
 						 255);
 	plat->tchsh_ns = ofnode_read_u32_default(subnode, "cdns,tchsh-ns", 20);
 	plat->tslch_ns = ofnode_read_u32_default(subnode, "cdns,tslch-ns", 20);
+	/*
+	 * Read delay should be an unsigned value but we use a signed integer
+	 * so that negative values can indicate that the device tree did not
+	 * specify any signed values and we need to perform the calibration
+	 * sequence to find it out.
+	 */
+	plat->read_delay = ofnode_read_s32_default(subnode, "cdns,read-delay",
+						   -1);
 
 	debug("%s: regbase=%p ahbbase=%p max-frequency=%d page-size=%d\n",
 	      __func__, plat->regbase, plat->ahbbase, plat->max_hz,
@@ -330,6 +376,7 @@ static int cadence_spi_of_to_plat(struct udevice *bus)
 
 static const struct spi_controller_mem_ops cadence_spi_mem_ops = {
 	.exec_op = cadence_spi_mem_exec_op,
+	.supports_op = cadence_spi_mem_supports_op,
 };
 
 static const struct dm_spi_ops cadence_spi_ops = {
diff --git a/drivers/spi/cadence_qspi.h b/drivers/spi/cadence_qspi.h
index 64c5867609..49b401168f 100644
--- a/drivers/spi/cadence_qspi.h
+++ b/drivers/spi/cadence_qspi.h
@@ -26,6 +26,8 @@ struct cadence_spi_plat {
 	u32		trigger_address;
 	fdt_addr_t	ahbsize;
 	bool		use_dac_mode;
+	int		read_delay;
+	u32		wr_delay;
 
 	/* Flash parameters */
 	u32		page_size;
@@ -34,6 +36,12 @@ struct cadence_spi_plat {
 	u32		tsd2d_ns;
 	u32		tchsh_ns;
 	u32		tslch_ns;
+
+	/* Transaction protocol parameters. */
+	u8		inst_width;
+	u8		addr_width;
+	u8		data_width;
+	bool		dtr;
 };
 
 struct cadence_spi_priv {
@@ -57,9 +65,13 @@ void cadence_qspi_apb_controller_enable(void *reg_base_addr);
 void cadence_qspi_apb_controller_disable(void *reg_base_addr);
 void cadence_qspi_apb_dac_mode_enable(void *reg_base);
 
-int cadence_qspi_apb_command_read(void *reg_base_addr,
+int cadence_qspi_apb_command_read_setup(struct cadence_spi_plat *plat,
+					const struct spi_mem_op *op);
+int cadence_qspi_apb_command_read(struct cadence_spi_plat *plat,
 				  const struct spi_mem_op *op);
-int cadence_qspi_apb_command_write(void *reg_base_addr,
+int cadence_qspi_apb_command_write_setup(struct cadence_spi_plat *plat,
+					 const struct spi_mem_op *op);
+int cadence_qspi_apb_command_write(struct cadence_spi_plat *plat,
 				   const struct spi_mem_op *op);
 
 int cadence_qspi_apb_read_setup(struct cadence_spi_plat *plat,
diff --git a/drivers/spi/cadence_qspi_apb.c b/drivers/spi/cadence_qspi_apb.c
index b051f462ed..c36a652211 100644
--- a/drivers/spi/cadence_qspi_apb.c
+++ b/drivers/spi/cadence_qspi_apb.c
@@ -51,7 +51,7 @@
 #define CQSPI_STIG_DATA_LEN_MAX			8
 
 #define CQSPI_DUMMY_CLKS_PER_BYTE		8
-#define CQSPI_DUMMY_BYTES_MAX			4
+#define CQSPI_DUMMY_CLKS_MAX			31
 
 /****************************************************************************
  * Controller's configuration and status register (offset from QSPI_BASE)
@@ -65,6 +65,8 @@
 #define	CQSPI_REG_CONFIG_XIP_IMM		BIT(18)
 #define	CQSPI_REG_CONFIG_CHIPSELECT_LSB		10
 #define	CQSPI_REG_CONFIG_BAUD_LSB		19
+#define CQSPI_REG_CONFIG_DTR_PROTO		BIT(24)
+#define CQSPI_REG_CONFIG_DUAL_OPCODE		BIT(30)
 #define	CQSPI_REG_CONFIG_IDLE_LSB		31
 #define	CQSPI_REG_CONFIG_CHIPSELECT_MASK	0xF
 #define	CQSPI_REG_CONFIG_BAUD_MASK		0xF
@@ -83,6 +85,7 @@
 
 #define	CQSPI_REG_WR_INSTR			0x08
 #define	CQSPI_REG_WR_INSTR_OPCODE_LSB		0
+#define CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB	12
 #define	CQSPI_REG_WR_INSTR_TYPE_DATA_LSB	16
 
 #define	CQSPI_REG_DELAY				0x0C
@@ -120,6 +123,9 @@
 #define	CQSPI_REG_SDRAMLEVEL_RD_MASK		0xFFFF
 #define	CQSPI_REG_SDRAMLEVEL_WR_MASK		0xFFFF
 
+#define CQSPI_REG_WR_COMPLETION_CTRL		0x38
+#define CQSPI_REG_WR_DISABLE_AUTO_POLL		BIT(14)
+
 #define	CQSPI_REG_IRQSTATUS			0x40
 #define	CQSPI_REG_IRQMASK			0x44
 
@@ -166,6 +172,11 @@
 #define	CQSPI_REG_CMDWRITEDATALOWER		0xA8
 #define	CQSPI_REG_CMDWRITEDATAUPPER		0xAC
 
+#define CQSPI_REG_OP_EXT_LOWER			0xE0
+#define CQSPI_REG_OP_EXT_READ_LSB		24
+#define CQSPI_REG_OP_EXT_WRITE_LSB		16
+#define CQSPI_REG_OP_EXT_STIG_LSB		0
+
 #define CQSPI_REG_IS_IDLE(base)					\
 	((readl(base + CQSPI_REG_CONFIG) >>		\
 		CQSPI_REG_CONFIG_IDLE_LSB) & 0x1)
@@ -203,6 +214,75 @@ void cadence_qspi_apb_dac_mode_enable(void *reg_base)
 	writel(reg, reg_base + CQSPI_REG_CONFIG);
 }
 
+static unsigned int cadence_qspi_calc_dummy(const struct spi_mem_op *op,
+					    bool dtr)
+{
+	unsigned int dummy_clk;
+
+	dummy_clk = op->dummy.nbytes * (8 / op->dummy.buswidth);
+	if (dtr)
+		dummy_clk /= 2;
+
+	return dummy_clk;
+}
+
+static u32 cadence_qspi_calc_rdreg(struct cadence_spi_plat *plat)
+{
+	u32 rdreg = 0;
+
+	rdreg |= plat->inst_width << CQSPI_REG_RD_INSTR_TYPE_INSTR_LSB;
+	rdreg |= plat->addr_width << CQSPI_REG_RD_INSTR_TYPE_ADDR_LSB;
+	rdreg |= plat->data_width << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB;
+
+	return rdreg;
+}
+
+static int cadence_qspi_buswidth_to_inst_type(u8 buswidth)
+{
+	switch (buswidth) {
+	case 0:
+	case 1:
+		return CQSPI_INST_TYPE_SINGLE;
+
+	case 2:
+		return CQSPI_INST_TYPE_DUAL;
+
+	case 4:
+		return CQSPI_INST_TYPE_QUAD;
+
+	case 8:
+		return CQSPI_INST_TYPE_OCTAL;
+
+	default:
+		return -ENOTSUPP;
+	}
+}
+
+static int cadence_qspi_set_protocol(struct cadence_spi_plat *plat,
+				     const struct spi_mem_op *op)
+{
+	int ret;
+
+	plat->dtr = op->data.dtr && op->cmd.dtr && op->addr.dtr;
+
+	ret = cadence_qspi_buswidth_to_inst_type(op->cmd.buswidth);
+	if (ret < 0)
+		return ret;
+	plat->inst_width = ret;
+
+	ret = cadence_qspi_buswidth_to_inst_type(op->addr.buswidth);
+	if (ret < 0)
+		return ret;
+	plat->addr_width = ret;
+
+	ret = cadence_qspi_buswidth_to_inst_type(op->data.buswidth);
+	if (ret < 0)
+		return ret;
+	plat->data_width = ret;
+
+	return 0;
+}
+
 /* Return 1 if idle, otherwise return 0 (busy). */
 static unsigned int cadence_qspi_wait_idle(void *reg_base)
 {
@@ -434,21 +514,109 @@ static int cadence_qspi_apb_exec_flash_cmd(void *reg_base,
 	return 0;
 }
 
+static int cadence_qspi_setup_opcode_ext(struct cadence_spi_plat *plat,
+					 const struct spi_mem_op *op,
+					 unsigned int shift)
+{
+	unsigned int reg;
+	u8 ext;
+
+	if (op->cmd.nbytes != 2)
+		return -EINVAL;
+
+	/* Opcode extension is the LSB. */
+	ext = op->cmd.opcode & 0xff;
+
+	reg = readl(plat->regbase + CQSPI_REG_OP_EXT_LOWER);
+	reg &= ~(0xff << shift);
+	reg |= ext << shift;
+	writel(reg, plat->regbase + CQSPI_REG_OP_EXT_LOWER);
+
+	return 0;
+}
+
+static int cadence_qspi_enable_dtr(struct cadence_spi_plat *plat,
+				   const struct spi_mem_op *op,
+				   unsigned int shift,
+				   bool enable)
+{
+	unsigned int reg;
+	int ret;
+
+	reg = readl(plat->regbase + CQSPI_REG_CONFIG);
+
+	if (enable) {
+		reg |= CQSPI_REG_CONFIG_DTR_PROTO;
+		reg |= CQSPI_REG_CONFIG_DUAL_OPCODE;
+
+		/* Set up command opcode extension. */
+		ret = cadence_qspi_setup_opcode_ext(plat, op, shift);
+		if (ret)
+			return ret;
+	} else {
+		reg &= ~CQSPI_REG_CONFIG_DTR_PROTO;
+		reg &= ~CQSPI_REG_CONFIG_DUAL_OPCODE;
+	}
+
+	writel(reg, plat->regbase + CQSPI_REG_CONFIG);
+
+	return 0;
+}
+
+int cadence_qspi_apb_command_read_setup(struct cadence_spi_plat *plat,
+					const struct spi_mem_op *op)
+{
+	int ret;
+	unsigned int reg;
+
+	ret = cadence_qspi_set_protocol(plat, op);
+	if (ret)
+		return ret;
+
+	ret = cadence_qspi_enable_dtr(plat, op, CQSPI_REG_OP_EXT_STIG_LSB,
+				      plat->dtr);
+	if (ret)
+		return ret;
+
+	reg = cadence_qspi_calc_rdreg(plat);
+	writel(reg, plat->regbase + CQSPI_REG_RD_INSTR);
+
+	return 0;
+}
+
 /* For command RDID, RDSR. */
-int cadence_qspi_apb_command_read(void *reg_base, const struct spi_mem_op *op)
+int cadence_qspi_apb_command_read(struct cadence_spi_plat *plat,
+				  const struct spi_mem_op *op)
 {
+	void *reg_base = plat->regbase;
 	unsigned int reg;
 	unsigned int read_len;
 	int status;
 	unsigned int rxlen = op->data.nbytes;
 	void *rxbuf = op->data.buf.in;
+	unsigned int dummy_clk;
+	u8 opcode;
 
 	if (rxlen > CQSPI_STIG_DATA_LEN_MAX || !rxbuf) {
 		printf("QSPI: Invalid input arguments rxlen %u\n", rxlen);
 		return -EINVAL;
 	}
 
-	reg = op->cmd.opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+	if (plat->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
+
+	reg = opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+
+	/* Set up dummy cycles. */
+	dummy_clk = cadence_qspi_calc_dummy(op, plat->dtr);
+	if (dummy_clk > CQSPI_DUMMY_CLKS_MAX)
+		return -ENOTSUPP;
+
+	if (dummy_clk)
+		reg |= (dummy_clk & CQSPI_REG_CMDCTRL_DUMMY_MASK)
+		     << CQSPI_REG_CMDCTRL_DUMMY_LSB;
 
 	reg |= (0x1 << CQSPI_REG_CMDCTRL_RD_EN_LSB);
 
@@ -475,15 +643,39 @@ int cadence_qspi_apb_command_read(void *reg_base, const struct spi_mem_op *op)
 	return 0;
 }
 
+int cadence_qspi_apb_command_write_setup(struct cadence_spi_plat *plat,
+					 const struct spi_mem_op *op)
+{
+	int ret;
+	unsigned int reg;
+
+	ret = cadence_qspi_set_protocol(plat, op);
+	if (ret)
+		return ret;
+
+	ret = cadence_qspi_enable_dtr(plat, op, CQSPI_REG_OP_EXT_STIG_LSB,
+				      plat->dtr);
+	if (ret)
+		return ret;
+
+	reg = cadence_qspi_calc_rdreg(plat);
+	writel(reg, plat->regbase + CQSPI_REG_RD_INSTR);
+
+	return 0;
+}
+
 /* For commands: WRSR, WREN, WRDI, CHIP_ERASE, BE, etc. */
-int cadence_qspi_apb_command_write(void *reg_base, const struct spi_mem_op *op)
+int cadence_qspi_apb_command_write(struct cadence_spi_plat *plat,
+				   const struct spi_mem_op *op)
 {
 	unsigned int reg = 0;
 	unsigned int wr_data;
 	unsigned int wr_len;
 	unsigned int txlen = op->data.nbytes;
 	const void *txbuf = op->data.buf.out;
+	void *reg_base = plat->regbase;
 	u32 addr;
+	u8 opcode;
 
 	/* Reorder address to SPI bus order if only transferring address */
 	if (!txlen) {
@@ -499,7 +691,12 @@ int cadence_qspi_apb_command_write(void *reg_base, const struct spi_mem_op *op)
 		return -EINVAL;
 	}
 
-	reg |= op->cmd.opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
+	if (plat->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
+
+	reg |= opcode << CQSPI_REG_CMDCTRL_OPCODE_LSB;
 
 	if (txlen) {
 		/* writing data = yes */
@@ -533,29 +730,39 @@ int cadence_qspi_apb_read_setup(struct cadence_spi_plat *plat,
 	unsigned int rd_reg;
 	unsigned int dummy_clk;
 	unsigned int dummy_bytes = op->dummy.nbytes;
+	int ret;
+	u8 opcode;
+
+	ret = cadence_qspi_set_protocol(plat, op);
+	if (ret)
+		return ret;
+
+	ret = cadence_qspi_enable_dtr(plat, op, CQSPI_REG_OP_EXT_READ_LSB,
+				      plat->dtr);
+	if (ret)
+		return ret;
 
 	/* Setup the indirect trigger address */
 	writel(plat->trigger_address,
 	       plat->regbase + CQSPI_REG_INDIRECTTRIGGER);
 
 	/* Configure the opcode */
-	rd_reg = op->cmd.opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
+	if (plat->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
 
-	if (op->data.buswidth == 8)
-		/* Instruction and address at DQ0, data at DQ0-7. */
-		rd_reg |= CQSPI_INST_TYPE_OCTAL << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB;
-	else if (op->data.buswidth == 4)
-		/* Instruction and address at DQ0, data at DQ0-3. */
-		rd_reg |= CQSPI_INST_TYPE_QUAD << CQSPI_REG_RD_INSTR_TYPE_DATA_LSB;
+	rd_reg = opcode << CQSPI_REG_RD_INSTR_OPCODE_LSB;
+	rd_reg |= cadence_qspi_calc_rdreg(plat);
 
 	writel(op->addr.val, plat->regbase + CQSPI_REG_INDIRECTRDSTARTADDR);
 
 	if (dummy_bytes) {
-		if (dummy_bytes > CQSPI_DUMMY_BYTES_MAX)
-			dummy_bytes = CQSPI_DUMMY_BYTES_MAX;
-
 		/* Convert to clock cycles. */
-		dummy_clk = dummy_bytes * CQSPI_DUMMY_CLKS_PER_BYTE;
+		dummy_clk = cadence_qspi_calc_dummy(op, plat->dtr);
+
+		if (dummy_clk > CQSPI_DUMMY_CLKS_MAX)
+			return -ENOTSUPP;
 
 		if (dummy_clk)
 			rd_reg |= (dummy_clk & CQSPI_REG_RD_INSTR_DUMMY_MASK)
@@ -682,17 +889,52 @@ int cadence_qspi_apb_write_setup(struct cadence_spi_plat *plat,
 				 const struct spi_mem_op *op)
 {
 	unsigned int reg;
+	int ret;
+	u8 opcode;
+
+	ret = cadence_qspi_set_protocol(plat, op);
+	if (ret)
+		return ret;
+
+	ret = cadence_qspi_enable_dtr(plat, op, CQSPI_REG_OP_EXT_WRITE_LSB,
+				      plat->dtr);
+	if (ret)
+		return ret;
 
 	/* Setup the indirect trigger address */
 	writel(plat->trigger_address,
 	       plat->regbase + CQSPI_REG_INDIRECTTRIGGER);
 
 	/* Configure the opcode */
-	reg = op->cmd.opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
+	if (plat->dtr)
+		opcode = op->cmd.opcode >> 8;
+	else
+		opcode = op->cmd.opcode;
+
+	reg = opcode << CQSPI_REG_WR_INSTR_OPCODE_LSB;
+	reg |= plat->data_width << CQSPI_REG_WR_INSTR_TYPE_DATA_LSB;
+	reg |= plat->addr_width << CQSPI_REG_WR_INSTR_TYPE_ADDR_LSB;
 	writel(reg, plat->regbase + CQSPI_REG_WR_INSTR);
 
+	reg = cadence_qspi_calc_rdreg(plat);
+	writel(reg, plat->regbase + CQSPI_REG_RD_INSTR);
+
 	writel(op->addr.val, plat->regbase + CQSPI_REG_INDIRECTWRSTARTADDR);
 
+	if (plat->dtr) {
+		/*
+		 * Some flashes like the cypress Semper flash expect a 4-byte
+		 * dummy address with the Read SR command in DTR mode, but this
+		 * controller does not support sending address with the Read SR
+		 * command. So, disable write completion polling on the
+		 * controller's side. spi-nor will take care of polling the
+		 * status register.
+		 */
+		reg = readl(plat->regbase + CQSPI_REG_WR_COMPLETION_CTRL);
+		reg |= CQSPI_REG_WR_DISABLE_AUTO_POLL;
+		writel(reg, plat->regbase + CQSPI_REG_WR_COMPLETION_CTRL);
+	}
+
 	reg = readl(plat->regbase + CQSPI_REG_SIZE);
 	reg &= ~CQSPI_REG_SIZE_ADDRESS_MASK;
 	reg |= (op->addr.nbytes - 1);
@@ -730,6 +972,12 @@ cadence_qspi_apb_indirect_write_execute(struct cadence_spi_plat *plat,
 	writel(CQSPI_REG_INDIRECTWR_START,
 	       plat->regbase + CQSPI_REG_INDIRECTWR);
 
+	/*
+	 * Some delay is required for the above bit to be internally
+	 * synchronized by the QSPI module.
+	 */
+	ndelay(plat->wr_delay);
+
 	while (remaining > 0) {
 		write_bytes = remaining > page_size ? page_size : remaining;
 		writesl(plat->ahbbase, bb_txbuf, write_bytes >> 2);
@@ -781,7 +1029,15 @@ int cadence_qspi_apb_write_execute(struct cadence_spi_plat *plat,
 	const void *buf = op->data.buf.out;
 	size_t len = op->data.nbytes;
 
-	if (plat->use_dac_mode && (to + len < plat->ahbsize)) {
+	/*
+	 * Some flashes like the Cypress Semper flash expect a dummy 4-byte
+	 * address (all 0s) with the read status register command in DTR mode.
+	 * But this controller does not support sending dummy address bytes to
+	 * the flash when it is polling the write completion register in DTR
+	 * mode. So, we can not use direct mode when in DTR mode for writing
+	 * data.
+	 */
+	if (!plat->dtr && plat->use_dac_mode && (to + len < plat->ahbsize)) {
 		memcpy_toio(plat->ahbbase + to, buf, len);
 		if (!cadence_qspi_wait_idle(plat->regbase))
 			return -EIO;
diff --git a/drivers/spi/mtk_snfi_spi.c b/drivers/spi/mtk_snfi_spi.c
index b6ab5fa3ad..65d0ce0981 100644
--- a/drivers/spi/mtk_snfi_spi.c
+++ b/drivers/spi/mtk_snfi_spi.c
@@ -64,8 +64,7 @@ static int mtk_snfi_adjust_op_size(struct spi_slave *slave,
 	 * or the output+input data must not exceed the GPRAM size.
 	 */
 
-	nbytes = sizeof(op->cmd.opcode) + op->addr.nbytes +
-		op->dummy.nbytes;
+	nbytes = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 	if (nbytes + op->data.nbytes <= SNFI_GPRAM_SIZE)
 		return 0;
diff --git a/drivers/spi/spi-mem-nodm.c b/drivers/spi/spi-mem-nodm.c
index 765f05fe54..a228c808c7 100644
--- a/drivers/spi/spi-mem-nodm.c
+++ b/drivers/spi/spi-mem-nodm.c
@@ -27,7 +27,7 @@ int spi_mem_exec_op(struct spi_slave *slave,
 			tx_buf = op->data.buf.out;
 	}
 
-	op_len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
+	op_len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 	op_buf = calloc(1, op_len);
 
 	ret = spi_claim_bus(slave);
@@ -89,7 +89,7 @@ int spi_mem_adjust_op_size(struct spi_slave *slave,
 {
 	unsigned int len;
 
-	len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
+	len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 	if (slave->max_write_size && len > slave->max_write_size)
 		return -EINVAL;
 
@@ -105,3 +105,65 @@ int spi_mem_adjust_op_size(struct spi_slave *slave,
 
 	return 0;
 }
+
+static int spi_check_buswidth_req(struct spi_slave *slave, u8 buswidth, bool tx)
+{
+	u32 mode = slave->mode;
+
+	switch (buswidth) {
+	case 1:
+		return 0;
+
+	case 2:
+		if ((tx && (mode & (SPI_TX_DUAL | SPI_TX_QUAD))) ||
+		    (!tx && (mode & (SPI_RX_DUAL | SPI_RX_QUAD))))
+			return 0;
+
+		break;
+
+	case 4:
+		if ((tx && (mode & SPI_TX_QUAD)) ||
+		    (!tx && (mode & SPI_RX_QUAD)))
+			return 0;
+
+		break;
+	case 8:
+		if ((tx && (mode & SPI_TX_OCTAL)) ||
+		    (!tx && (mode & SPI_RX_OCTAL)))
+			return 0;
+
+		break;
+
+	default:
+		break;
+	}
+
+	return -ENOTSUPP;
+}
+
+bool spi_mem_supports_op(struct spi_slave *slave, const struct spi_mem_op *op)
+{
+	if (spi_check_buswidth_req(slave, op->cmd.buswidth, true))
+		return false;
+
+	if (op->addr.nbytes &&
+	    spi_check_buswidth_req(slave, op->addr.buswidth, true))
+		return false;
+
+	if (op->dummy.nbytes &&
+	    spi_check_buswidth_req(slave, op->dummy.buswidth, true))
+		return false;
+
+	if (op->data.nbytes &&
+	    spi_check_buswidth_req(slave, op->data.buswidth,
+				   op->data.dir == SPI_MEM_DATA_OUT))
+		return false;
+
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		return false;
+
+	if (op->cmd.nbytes != 1)
+		return false;
+
+	return true;
+}
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index c095ae9505..9c1ede1b61 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -145,8 +145,8 @@ static int spi_check_buswidth_req(struct spi_slave *slave, u8 buswidth, bool tx)
 	return -ENOTSUPP;
 }
 
-bool spi_mem_default_supports_op(struct spi_slave *slave,
-				 const struct spi_mem_op *op)
+static bool spi_mem_check_buswidth(struct spi_slave *slave,
+				   const struct spi_mem_op *op)
 {
 	if (spi_check_buswidth_req(slave, op->cmd.buswidth, true))
 		return false;
@@ -166,6 +166,38 @@ bool spi_mem_default_supports_op(struct spi_slave *slave,
 
 	return true;
 }
+
+bool spi_mem_dtr_supports_op(struct spi_slave *slave,
+			     const struct spi_mem_op *op)
+{
+	if (op->cmd.buswidth == 8 && op->cmd.nbytes % 2)
+		return false;
+
+	if (op->addr.nbytes && op->addr.buswidth == 8 && op->addr.nbytes % 2)
+		return false;
+
+	if (op->dummy.nbytes && op->dummy.buswidth == 8 && op->dummy.nbytes % 2)
+		return false;
+
+	if (op->data.dir != SPI_MEM_NO_DATA &&
+	    op->dummy.buswidth == 8 && op->data.nbytes % 2)
+		return false;
+
+	return spi_mem_check_buswidth(slave, op);
+}
+EXPORT_SYMBOL_GPL(spi_mem_dtr_supports_op);
+
+bool spi_mem_default_supports_op(struct spi_slave *slave,
+				 const struct spi_mem_op *op)
+{
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		return false;
+
+	if (op->cmd.nbytes != 1)
+		return false;
+
+	return spi_mem_check_buswidth(slave, op);
+}
 EXPORT_SYMBOL_GPL(spi_mem_default_supports_op);
 
 /**
@@ -270,8 +302,7 @@ int spi_mem_exec_op(struct spi_slave *slave, const struct spi_mem_op *op)
 	}
 
 #ifndef __UBOOT__
-	tmpbufsize = sizeof(op->cmd.opcode) + op->addr.nbytes +
-		     op->dummy.nbytes;
+	tmpbufsize = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 	/*
 	 * Allocate a buffer to transmit the CMD, ADDR cycles with kmalloc() so
@@ -286,7 +317,7 @@ int spi_mem_exec_op(struct spi_slave *slave, const struct spi_mem_op *op)
 
 	tmpbuf[0] = op->cmd.opcode;
 	xfers[xferpos].tx_buf = tmpbuf;
-	xfers[xferpos].len = sizeof(op->cmd.opcode);
+	xfers[xferpos].len = op->cmd.nbytes;
 	xfers[xferpos].tx_nbits = op->cmd.buswidth;
 	spi_message_add_tail(&xfers[xferpos], &msg);
 	xferpos++;
@@ -350,7 +381,7 @@ int spi_mem_exec_op(struct spi_slave *slave, const struct spi_mem_op *op)
 			tx_buf = op->data.buf.out;
 	}
 
-	op_len = sizeof(op->cmd.opcode) + op->addr.nbytes + op->dummy.nbytes;
+	op_len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 
 	/*
 	 * Avoid using malloc() here so that we can use this code in SPL where
@@ -439,8 +470,7 @@ int spi_mem_adjust_op_size(struct spi_slave *slave, struct spi_mem_op *op)
 	if (!ops->mem_ops || !ops->mem_ops->exec_op) {
 		unsigned int len;
 
-		len = sizeof(op->cmd.opcode) + op->addr.nbytes +
-			op->dummy.nbytes;
+		len = op->cmd.nbytes + op->addr.nbytes + op->dummy.nbytes;
 		if (slave->max_write_size && len > slave->max_write_size)
 			return -EINVAL;
 
diff --git a/drivers/spi/spi-mxic.c b/drivers/spi/spi-mxic.c
new file mode 100644
index 0000000000..6aae9f7955
--- /dev/null
+++ b/drivers/spi/spi-mxic.c
@@ -0,0 +1,547 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 Macronix International Co., Ltd.
+ *
+ * Authors:
+ *	zhengxunli <zhengxunli@mxic.com.tw>
+ */
+
+#include <common.h>
+#include <clk.h>
+#include <dm.h>
+#include <errno.h>
+#include <asm/io.h>
+#include <malloc.h>
+#include <spi.h>
+#include <spi-mem.h>
+#include <linux/bug.h>
+#include <linux/iopoll.h>
+
+#define HC_CFG			0x0
+#define HC_CFG_IF_CFG(x)	((x) << 27)
+#define HC_CFG_DUAL_SLAVE	BIT(31)
+#define HC_CFG_INDIVIDUAL	BIT(30)
+#define HC_CFG_NIO(x)		(((x) / 4) << 27)
+#define HC_CFG_TYPE(s, t)	((t) << (23 + ((s) * 2)))
+#define HC_CFG_TYPE_SPI_NOR	0
+#define HC_CFG_TYPE_SPI_NAND	1
+#define HC_CFG_TYPE_SPI_RAM	2
+#define HC_CFG_TYPE_RAW_NAND	3
+#define HC_CFG_SLV_ACT(x)	((x) << 21)
+#define HC_CFG_CLK_PH_EN	BIT(20)
+#define HC_CFG_CLK_POL_INV	BIT(19)
+#define HC_CFG_BIG_ENDIAN	BIT(18)
+#define HC_CFG_DATA_PASS	BIT(17)
+#define HC_CFG_IDLE_SIO_LVL(x)	((x) << 16)
+#define HC_CFG_MAN_START_EN	BIT(3)
+#define HC_CFG_MAN_START	BIT(2)
+#define HC_CFG_MAN_CS_EN	BIT(1)
+#define HC_CFG_MAN_CS_ASSERT	BIT(0)
+
+#define INT_STS			0x4
+#define INT_STS_EN		0x8
+#define INT_SIG_EN		0xc
+#define INT_STS_ALL		GENMASK(31, 0)
+#define INT_RDY_PIN		BIT(26)
+#define INT_RDY_SR		BIT(25)
+#define INT_LNR_SUSP		BIT(24)
+#define INT_ECC_ERR		BIT(17)
+#define INT_CRC_ERR		BIT(16)
+#define INT_LWR_DIS		BIT(12)
+#define INT_LRD_DIS		BIT(11)
+#define INT_SDMA_INT		BIT(10)
+#define INT_DMA_FINISH		BIT(9)
+#define INT_RX_NOT_FULL		BIT(3)
+#define INT_RX_NOT_EMPTY	BIT(2)
+#define INT_TX_NOT_FULL		BIT(1)
+#define INT_TX_EMPTY		BIT(0)
+
+#define HC_EN			0x10
+#define HC_EN_BIT		BIT(0)
+
+#define TXD(x)			(0x14 + ((x) * 4))
+#define RXD			0x24
+
+#define SS_CTRL(s)		(0x30 + ((s) * 4))
+#define LRD_CFG			0x44
+#define LWR_CFG			0x80
+#define RWW_CFG			0x70
+#define OP_READ			BIT(23)
+#define OP_DUMMY_CYC(x)		((x) << 17)
+#define OP_ADDR_BYTES(x)	((x) << 14)
+#define OP_CMD_BYTES(x)		(((x) - 1) << 13)
+#define OP_OCTA_CRC_EN		BIT(12)
+#define OP_DQS_EN		BIT(11)
+#define OP_ENHC_EN		BIT(10)
+#define OP_PREAMBLE_EN		BIT(9)
+#define OP_DATA_DDR		BIT(8)
+#define OP_DATA_BUSW(x)		((x) << 6)
+#define OP_ADDR_DDR		BIT(5)
+#define OP_ADDR_BUSW(x)		((x) << 3)
+#define OP_CMD_DDR		BIT(2)
+#define OP_CMD_BUSW(x)		(x)
+#define OP_BUSW_1		0
+#define OP_BUSW_2		1
+#define OP_BUSW_4		2
+#define OP_BUSW_8		3
+
+#define OCTA_CRC		0x38
+#define OCTA_CRC_IN_EN(s)	BIT(3 + ((s) * 16))
+#define OCTA_CRC_CHUNK(s, x)	((fls((x) / 32)) << (1 + ((s) * 16)))
+#define OCTA_CRC_OUT_EN(s)	BIT(0 + ((s) * 16))
+
+#define ONFI_DIN_CNT(s)		(0x3c + (s))
+
+#define LRD_CTRL		0x48
+#define RWW_CTRL		0x74
+#define LWR_CTRL		0x84
+#define LMODE_EN		BIT(31)
+#define LMODE_SLV_ACT(x)	((x) << 21)
+#define LMODE_CMD1(x)		((x) << 8)
+#define LMODE_CMD0(x)		(x)
+
+#define LRD_ADDR		0x4c
+#define LWR_ADDR		0x88
+#define LRD_RANGE		0x50
+#define LWR_RANGE		0x8c
+
+#define AXI_SLV_ADDR		0x54
+
+#define DMAC_RD_CFG		0x58
+#define DMAC_WR_CFG		0x94
+#define DMAC_CFG_PERIPH_EN	BIT(31)
+#define DMAC_CFG_ALLFLUSH_EN	BIT(30)
+#define DMAC_CFG_LASTFLUSH_EN	BIT(29)
+#define DMAC_CFG_QE(x)		(((x) + 1) << 16)
+#define DMAC_CFG_BURST_LEN(x)	(((x) + 1) << 12)
+#define DMAC_CFG_BURST_SZ(x)	((x) << 8)
+#define DMAC_CFG_DIR_READ	BIT(1)
+#define DMAC_CFG_START		BIT(0)
+
+#define DMAC_RD_CNT		0x5c
+#define DMAC_WR_CNT		0x98
+
+#define SDMA_ADDR		0x60
+
+#define DMAM_CFG		0x64
+#define DMAM_CFG_START		BIT(31)
+#define DMAM_CFG_CONT		BIT(30)
+#define DMAM_CFG_SDMA_GAP(x)	(fls((x) / 8192) << 2)
+#define DMAM_CFG_DIR_READ	BIT(1)
+#define DMAM_CFG_EN		BIT(0)
+
+#define DMAM_CNT		0x68
+
+#define LNR_TIMER_TH		0x6c
+
+#define RDM_CFG0		0x78
+#define RDM_CFG0_POLY(x)	(x)
+
+#define RDM_CFG1		0x7c
+#define RDM_CFG1_RDM_EN		BIT(31)
+#define RDM_CFG1_SEED(x)	(x)
+
+#define LWR_SUSP_CTRL		0x90
+#define LWR_SUSP_CTRL_EN	BIT(31)
+
+#define DMAS_CTRL		0x9c
+#define DMAS_CTRL_EN		BIT(31)
+#define DMAS_CTRL_DIR_READ	BIT(30)
+
+#define DATA_STROB		0xa0
+#define DATA_STROB_EDO_EN	BIT(2)
+#define DATA_STROB_INV_POL	BIT(1)
+#define DATA_STROB_DELAY_2CYC	BIT(0)
+
+#define IDLY_CODE(x)		(0xa4 + ((x) * 4))
+#define IDLY_CODE_VAL(x, v)	((v) << (((x) % 4) * 8))
+
+#define GPIO			0xc4
+#define GPIO_PT(x)		BIT(3 + ((x) * 16))
+#define GPIO_RESET(x)		BIT(2 + ((x) * 16))
+#define GPIO_HOLDB(x)		BIT(1 + ((x) * 16))
+#define GPIO_WPB(x)		BIT((x) * 16)
+
+#define HC_VER			0xd0
+
+#define HW_TEST(x)		(0xe0 + ((x) * 4))
+
+struct mxic_spi_priv {
+	struct clk *send_clk;
+	struct clk *send_dly_clk;
+	void __iomem *regs;
+	u32 cur_speed_hz;
+};
+
+static int mxic_spi_clk_enable(struct mxic_spi_priv *priv)
+{
+	int ret;
+
+	ret = clk_prepare_enable(priv->send_clk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(priv->send_dly_clk);
+	if (ret)
+		goto err_send_dly_clk;
+
+	return ret;
+
+err_send_dly_clk:
+	clk_disable_unprepare(priv->send_clk);
+
+	return ret;
+}
+
+static void mxic_spi_clk_disable(struct mxic_spi_priv *priv)
+{
+	clk_disable_unprepare(priv->send_clk);
+	clk_disable_unprepare(priv->send_dly_clk);
+}
+
+static void mxic_spi_set_input_delay_dqs(struct mxic_spi_priv *priv,
+					 u8 idly_code)
+{
+	writel(IDLY_CODE_VAL(0, idly_code) |
+	       IDLY_CODE_VAL(1, idly_code) |
+	       IDLY_CODE_VAL(2, idly_code) |
+	       IDLY_CODE_VAL(3, idly_code),
+	       priv->regs + IDLY_CODE(0));
+	writel(IDLY_CODE_VAL(4, idly_code) |
+	       IDLY_CODE_VAL(5, idly_code) |
+	       IDLY_CODE_VAL(6, idly_code) |
+	       IDLY_CODE_VAL(7, idly_code),
+	       priv->regs + IDLY_CODE(1));
+}
+
+static int mxic_spi_clk_setup(struct mxic_spi_priv *priv, uint freq)
+{
+	int ret;
+
+	ret = clk_set_rate(priv->send_clk, freq);
+	if (ret)
+		return ret;
+
+	ret = clk_set_rate(priv->send_dly_clk, freq);
+	if (ret)
+		return ret;
+
+	/*
+	 * A constant delay range from 0x0 ~ 0x1F for input delay,
+	 * the unit is 78 ps, the max input delay is 2.418 ns.
+	 */
+	mxic_spi_set_input_delay_dqs(priv, 0xf);
+
+	return 0;
+}
+
+static int mxic_spi_set_speed(struct udevice *bus, uint freq)
+{
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+	int ret;
+
+	if (priv->cur_speed_hz == freq)
+		return 0;
+
+	mxic_spi_clk_disable(priv);
+	ret = mxic_spi_clk_setup(priv, freq);
+	if (ret)
+		return ret;
+
+	ret = mxic_spi_clk_enable(priv);
+	if (ret)
+		return ret;
+
+	priv->cur_speed_hz = freq;
+
+	return 0;
+}
+
+static int mxic_spi_set_mode(struct udevice *bus, uint mode)
+{
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+	u32 hc_config = 0;
+
+	if (mode & SPI_CPHA)
+		hc_config |= HC_CFG_CLK_PH_EN;
+	if (mode & SPI_CPOL)
+		hc_config |= HC_CFG_CLK_POL_INV;
+
+	writel(hc_config, priv->regs + HC_CFG);
+
+	return 0;
+}
+
+static void mxic_spi_hw_init(struct mxic_spi_priv *priv)
+{
+	writel(0, priv->regs + DATA_STROB);
+	writel(INT_STS_ALL, priv->regs + INT_STS_EN);
+	writel(0, priv->regs + HC_EN);
+	writel(0, priv->regs + LRD_CFG);
+	writel(0, priv->regs + LRD_CTRL);
+	writel(HC_CFG_NIO(1) | HC_CFG_TYPE(0, HC_CFG_TYPE_SPI_NOR) |
+	       HC_CFG_SLV_ACT(0) | HC_CFG_MAN_CS_EN | HC_CFG_IDLE_SIO_LVL(1),
+	       priv->regs + HC_CFG);
+}
+
+static int mxic_spi_data_xfer(struct mxic_spi_priv *priv, const void *txbuf,
+			      void *rxbuf, unsigned int len)
+{
+	unsigned int pos = 0;
+
+	while (pos < len) {
+		unsigned int nbytes = len - pos;
+		u32 data = 0xffffffff;
+		u32 sts;
+		int ret;
+
+		if (nbytes > 4)
+			nbytes = 4;
+
+		if (txbuf)
+			memcpy(&data, txbuf + pos, nbytes);
+
+		ret = readl_poll_timeout(priv->regs + INT_STS, sts,
+					 sts & INT_TX_EMPTY, 1000000);
+		if (ret)
+			return ret;
+
+		writel(data, priv->regs + TXD(nbytes % 4));
+
+		if (rxbuf) {
+			ret = readl_poll_timeout(priv->regs + INT_STS, sts,
+						 sts & INT_TX_EMPTY,
+						 1000000);
+			if (ret)
+				return ret;
+
+			ret = readl_poll_timeout(priv->regs + INT_STS, sts,
+						 sts & INT_RX_NOT_EMPTY,
+						 1000000);
+			if (ret)
+				return ret;
+
+			data = readl(priv->regs + RXD);
+			data >>= (8 * (4 - nbytes));
+			memcpy(rxbuf + pos, &data, nbytes);
+			WARN_ON(readl(priv->regs + INT_STS) & INT_RX_NOT_EMPTY);
+		} else {
+			readl(priv->regs + RXD);
+		}
+		WARN_ON(readl(priv->regs + INT_STS) & INT_RX_NOT_EMPTY);
+
+		pos += nbytes;
+	}
+
+	return 0;
+}
+
+static bool mxic_spi_mem_supports_op(struct spi_slave *slave,
+				     const struct spi_mem_op *op)
+{
+	if (op->data.buswidth > 8 || op->addr.buswidth > 8 ||
+	    op->dummy.buswidth > 8 || op->cmd.buswidth > 8)
+		return false;
+
+	if (op->addr.nbytes > 7)
+		return false;
+
+	return spi_mem_default_supports_op(slave, op);
+}
+
+static int mxic_spi_mem_exec_op(struct spi_slave *slave,
+				const struct spi_mem_op *op)
+{
+	struct dm_spi_slave_plat *slave_plat = dev_get_parent_plat(slave->dev);
+	struct udevice *bus = slave->dev->parent;
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+	int nio = 1, i, ret;
+	u32 ss_ctrl;
+	u8 addr[8], dummy_bytes = 0;
+
+	if (slave->mode & (SPI_TX_OCTAL | SPI_RX_OCTAL))
+		nio = 8;
+	else if (slave->mode & (SPI_TX_QUAD | SPI_RX_QUAD))
+		nio = 4;
+	else if (slave->mode & (SPI_TX_DUAL | SPI_RX_DUAL))
+		nio = 2;
+
+	writel(HC_CFG_NIO(nio) |
+	       HC_CFG_TYPE(slave_plat->cs, HC_CFG_TYPE_SPI_NOR) |
+	       HC_CFG_SLV_ACT(slave_plat->cs) | HC_CFG_IDLE_SIO_LVL(1) |
+	       HC_CFG_MAN_CS_EN,
+	       priv->regs + HC_CFG);
+	writel(HC_EN_BIT, priv->regs + HC_EN);
+
+	ss_ctrl = OP_CMD_BYTES(1) | OP_CMD_BUSW(fls(op->cmd.buswidth) - 1);
+
+	if (op->addr.nbytes)
+		ss_ctrl |= OP_ADDR_BYTES(op->addr.nbytes) |
+			   OP_ADDR_BUSW(fls(op->addr.buswidth) - 1);
+
+	/*
+	 * Since the SPI MXIC dummy buswidth is aligned with the data buswidth,
+	 * the dummy byte needs to be recalculated to send out the correct
+	 * dummy cycle.
+	 */
+	if (op->dummy.nbytes) {
+		dummy_bytes = op->dummy.nbytes /
+			      op->addr.buswidth *
+			      op->data.buswidth;
+		ss_ctrl |= OP_DUMMY_CYC(dummy_bytes);
+	}
+
+	if (op->data.nbytes) {
+		ss_ctrl |= OP_DATA_BUSW(fls(op->data.buswidth) - 1);
+		if (op->data.dir == SPI_MEM_DATA_IN)
+			ss_ctrl |= OP_READ;
+	}
+
+	writel(ss_ctrl, priv->regs + SS_CTRL(slave_plat->cs));
+
+	writel(readl(priv->regs + HC_CFG) | HC_CFG_MAN_CS_ASSERT,
+	       priv->regs + HC_CFG);
+
+	ret = mxic_spi_data_xfer(priv, &op->cmd.opcode, NULL, 1);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < op->addr.nbytes; i++)
+		addr[i] = op->addr.val >> (8 * (op->addr.nbytes - i - 1));
+
+	ret = mxic_spi_data_xfer(priv, addr, NULL, op->addr.nbytes);
+	if (ret)
+		goto out;
+
+	ret = mxic_spi_data_xfer(priv, NULL, NULL, dummy_bytes);
+	if (ret)
+		goto out;
+
+	ret = mxic_spi_data_xfer(priv,
+				 op->data.dir == SPI_MEM_DATA_OUT ?
+				 op->data.buf.out : NULL,
+				 op->data.dir == SPI_MEM_DATA_IN ?
+				 op->data.buf.in : NULL,
+				 op->data.nbytes);
+
+out:
+	writel(readl(priv->regs + HC_CFG) & ~HC_CFG_MAN_CS_ASSERT,
+	       priv->regs + HC_CFG);
+	writel(0, priv->regs + HC_EN);
+
+	return ret;
+}
+
+static const struct spi_controller_mem_ops mxic_spi_mem_ops = {
+	.supports_op = mxic_spi_mem_supports_op,
+	.exec_op = mxic_spi_mem_exec_op,
+};
+
+static int mxic_spi_claim_bus(struct udevice *dev)
+{
+	struct udevice *bus = dev_get_parent(dev);
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+
+	writel(readl(priv->regs + HC_CFG) | HC_CFG_MAN_CS_EN,
+	       priv->regs + HC_CFG);
+	writel(HC_EN_BIT, priv->regs + HC_EN);
+	writel(readl(priv->regs + HC_CFG) | HC_CFG_MAN_CS_ASSERT,
+	       priv->regs + HC_CFG);
+
+	return 0;
+}
+
+static int mxic_spi_release_bus(struct udevice *dev)
+{
+	struct udevice *bus = dev_get_parent(dev);
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+
+	writel(readl(priv->regs + HC_CFG) & ~HC_CFG_MAN_CS_ASSERT,
+	       priv->regs + HC_CFG);
+	writel(0, priv->regs + HC_EN);
+
+	return 0;
+}
+
+static int mxic_spi_xfer(struct udevice *dev, unsigned int bitlen,
+			 const void *dout, void *din, unsigned long flags)
+{
+	struct udevice *bus = dev_get_parent(dev);
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+	struct spi_slave *slave = dev_get_parent_priv(dev);
+	unsigned int busw = OP_BUSW_1;
+	unsigned int len = bitlen / 8;
+	int ret;
+
+	if (dout && din) {
+		if (((slave->mode & SPI_TX_QUAD) &&
+		     !(slave->mode & SPI_RX_QUAD)) ||
+		    ((slave->mode & SPI_TX_DUAL) &&
+		     !(slave->mode & SPI_RX_DUAL)))
+			return -ENOTSUPP;
+	}
+
+	if (din) {
+		if (slave->mode & SPI_TX_QUAD)
+			busw = OP_BUSW_4;
+		else if (slave->mode & SPI_TX_DUAL)
+			busw = OP_BUSW_2;
+	} else if (dout) {
+		if (slave->mode & SPI_RX_QUAD)
+			busw = OP_BUSW_4;
+		else if (slave->mode & SPI_RX_DUAL)
+			busw = OP_BUSW_2;
+	}
+
+	writel(OP_CMD_BYTES(1) | OP_CMD_BUSW(busw) |
+	       OP_DATA_BUSW(busw) | (din ? OP_READ : 0),
+	       priv->regs + SS_CTRL(0));
+
+	ret = mxic_spi_data_xfer(priv, dout, din, len);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mxic_spi_probe(struct udevice *bus)
+{
+	struct mxic_spi_priv *priv = dev_get_priv(bus);
+
+	priv->regs = (void *)dev_read_addr(bus);
+
+	priv->send_clk = devm_clk_get(bus, "send_clk");
+	if (IS_ERR(priv->send_clk))
+		return PTR_ERR(priv->send_clk);
+
+	priv->send_dly_clk = devm_clk_get(bus, "send_dly_clk");
+	if (IS_ERR(priv->send_dly_clk))
+		return PTR_ERR(priv->send_dly_clk);
+
+	mxic_spi_hw_init(priv);
+
+	return 0;
+}
+
+static const struct dm_spi_ops mxic_spi_ops = {
+	.claim_bus	= mxic_spi_claim_bus,
+	.release_bus	= mxic_spi_release_bus,
+	.xfer		= mxic_spi_xfer,
+	.set_speed	= mxic_spi_set_speed,
+	.set_mode	= mxic_spi_set_mode,
+	.mem_ops	= &mxic_spi_mem_ops,
+};
+
+static const struct udevice_id mxic_spi_ids[] = {
+	{ .compatible = "mxicy,mx25f0a-spi", },
+	{ }
+};
+
+U_BOOT_DRIVER(mxic_spi) = {
+	.name	= "mxic_spi",
+	.id	= UCLASS_SPI,
+	.of_match = mxic_spi_ids,
+	.ops	= &mxic_spi_ops,
+	.priv_auto = sizeof(struct mxic_spi_priv),
+	.probe	= mxic_spi_probe,
+};