RE: [PATCH v7 3/9] spi: Add a driver for the Freescale/NXP QuadSPI controller

[Yogesh Narayan Gaur <yogeshnarayan.gaur@xxxxxxx>]

Hi Frieder,

> -----Original Message-----
> From: Schrempf Frieder [mailto:frieder.schrempf@xxxxxxxxxx]
> Sent: Tuesday, December 4, 2018 7:45 PM
> To: linux-mtd@xxxxxxxxxxxxxxxxxxx; boris.brezillon@xxxxxxxxxxx; linux-
> spi@xxxxxxxxxxxxxxx; Marek Vasut <marek.vasut@xxxxxxxxx>; Mark Brown
> <broonie@xxxxxxxxxx>; Han Xu <han.xu@xxxxxxx>
> Cc: dwmw2@xxxxxxxxxxxxx; computersforpeace@xxxxxxxxx; richard@xxxxxx;
> miquel.raynal@xxxxxxxxxxx; David Wolfe <david.wolfe@xxxxxxx>; Fabio
> Estevam <fabio.estevam@xxxxxxx>; Prabhakar Kushwaha
> <prabhakar.kushwaha@xxxxxxx>; Yogesh Narayan Gaur
> <yogeshnarayan.gaur@xxxxxxx>; shawnguo@xxxxxxxxxx; Schrempf Frieder
> <frieder.schrempf@xxxxxxxxxx>; linux-kernel@xxxxxxxxxxxxxxx
> Subject: [PATCH v7 3/9] spi: Add a driver for the Freescale/NXP QuadSPI
> controller
> 
> From: Frieder Schrempf <frieder.schrempf@xxxxxxxxxx>
> 
> This driver is derived from the SPI NOR driver at mtd/spi-nor/fsl-quadspi.c. It
> uses the new SPI memory interface of the SPI framework to issue flash memory
> operations to up to four connected flash chips (2 buses with 2 CS each).
> 
> The controller does not support generic SPI messages.
> 
> This patch also disables the build of the "old" driver and reuses its Kconfig option
> CONFIG_SPI_FSL_QUADSPI to replace it.
> 
> Signed-off-by: Frieder Schrempf <frieder.schrempf@xxxxxxxxxx>
> ---
>  drivers/mtd/spi-nor/Kconfig  |   9 -
>  drivers/mtd/spi-nor/Makefile |   1 -
>  drivers/spi/Kconfig          |  11 +
>  drivers/spi/Makefile         |   1 +
>  drivers/spi/spi-fsl-qspi.c   | 966 ++++++++++++++++++++++++++++++++++++++
>  5 files changed, 978 insertions(+), 10 deletions(-)
> 
> diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig index
> 6cc9c92..d1ca307 100644
> --- a/drivers/mtd/spi-nor/Kconfig
> +++ b/drivers/mtd/spi-nor/Kconfig
> @@ -59,15 +59,6 @@ config SPI_CADENCE_QUADSPI
>  	  device with a Cadence QSPI controller and want to access the
>  	  Flash as an MTD device.
> 
> -config SPI_FSL_QUADSPI
> -	tristate "Freescale Quad SPI controller"
> -	depends on ARCH_MXC || SOC_LS1021A || ARCH_LAYERSCAPE ||
> COMPILE_TEST
> -	depends on HAS_IOMEM
> -	help
> -	  This enables support for the Quad SPI controller in master mode.
> -	  This controller does not support generic SPI. It only supports
> -	  SPI NOR.
> -
>  config SPI_HISI_SFC
>  	tristate "Hisilicon SPI-NOR Flash Controller(SFC)"
>  	depends on ARCH_HISI || COMPILE_TEST
> diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile index
> f4c61d2..3f160c2e3 100644
> --- a/drivers/mtd/spi-nor/Makefile
> +++ b/drivers/mtd/spi-nor/Makefile
> @@ -3,7 +3,6 @@ obj-$(CONFIG_MTD_SPI_NOR)	+= spi-nor.o
>  obj-$(CONFIG_SPI_ASPEED_SMC)	+= aspeed-smc.o
>  obj-$(CONFIG_SPI_ATMEL_QUADSPI)	+= atmel-quadspi.o
>  obj-$(CONFIG_SPI_CADENCE_QUADSPI)	+= cadence-quadspi.o
> -obj-$(CONFIG_SPI_FSL_QUADSPI)	+= fsl-quadspi.o
>  obj-$(CONFIG_SPI_HISI_SFC)	+= hisi-sfc.o
>  obj-$(CONFIG_MTD_MT81xx_NOR)    += mtk-quadspi.o
>  obj-$(CONFIG_SPI_NXP_SPIFI)	+= nxp-spifi.o
> diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig index 7d3a5c9..8c84186
> 100644
> --- a/drivers/spi/Kconfig
> +++ b/drivers/spi/Kconfig
> @@ -259,6 +259,17 @@ config SPI_FSL_LPSPI
>  	help
>  	  This enables Freescale i.MX LPSPI controllers in master mode.
> 
> +config SPI_FSL_QUADSPI
> +	tristate "Freescale QSPI controller"
> +	depends on ARCH_MXC || SOC_LS1021A || ARCH_LAYERSCAPE ||
> COMPILE_TEST
> +	depends on HAS_IOMEM
> +	help
> +	  This enables support for the Quad SPI controller in master mode.
> +	  Up to four flash chips can be connected on two buses with two
> +	  chipselects each.
> +	  This controller does not support generic SPI messages. It only
> +	  supports the high-level SPI memory interface.
> +
>  config SPI_GPIO
>  	tristate "GPIO-based bitbanging SPI Master"
>  	depends on GPIOLIB || COMPILE_TEST
> diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile index 3575205..5377e61
> 100644
> --- a/drivers/spi/Makefile
> +++ b/drivers/spi/Makefile
> @@ -44,6 +44,7 @@ obj-$(CONFIG_SPI_FSL_DSPI)		+= spi-fsl-
> dspi.o
>  obj-$(CONFIG_SPI_FSL_LIB)		+= spi-fsl-lib.o
>  obj-$(CONFIG_SPI_FSL_ESPI)		+= spi-fsl-espi.o
>  obj-$(CONFIG_SPI_FSL_LPSPI)		+= spi-fsl-lpspi.o
> +obj-$(CONFIG_SPI_FSL_QUADSPI)		+= spi-fsl-qspi.o
>  obj-$(CONFIG_SPI_FSL_SPI)		+= spi-fsl-spi.o
>  obj-$(CONFIG_SPI_GPIO)			+= spi-gpio.o
>  obj-$(CONFIG_SPI_IMG_SPFI)		+= spi-img-spfi.o
> diff --git a/drivers/spi/spi-fsl-qspi.c b/drivers/spi/spi-fsl-qspi.c new file mode
> 100644 index 0000000..f0a3400
> --- /dev/null
> +++ b/drivers/spi/spi-fsl-qspi.c
> @@ -0,0 +1,966 @@
> +// SPDX-License-Identifier: GPL-2.0+
> +
> +/*
> + * Freescale QuadSPI driver.
> + *
> + * Copyright (C) 2013 Freescale Semiconductor, Inc.
> + * Copyright (C) 2018 Bootlin
> + * Copyright (C) 2018 exceet electronics GmbH
> + * Copyright (C) 2018 Kontron Electronics GmbH
> + *
> + * Transition to SPI MEM interface:
> + * Authors:
> + *     Boris Brezillion <boris.brezillon@xxxxxxxxxxx>
> + *     Frieder Schrempf <frieder.schrempf@xxxxxxxxxx>
> + *     Yogesh Gaur <yogeshnarayan.gaur@xxxxxxx>
> + *     Suresh Gupta <suresh.gupta@xxxxxxx>
> + *
> + * Based on the original fsl-quadspi.c spi-nor driver:
> + * Author: Freescale Semiconductor, Inc.
> + *
> + */
> +
> +#include <linux/bitops.h>
> +#include <linux/clk.h>
> +#include <linux/completion.h>
> +#include <linux/delay.h>
> +#include <linux/err.h>
> +#include <linux/errno.h>
> +#include <linux/interrupt.h>
> +#include <linux/io.h>
> +#include <linux/iopoll.h>
> +#include <linux/jiffies.h>
> +#include <linux/kernel.h>
> +#include <linux/module.h>
> +#include <linux/mutex.h>
> +#include <linux/of.h>
> +#include <linux/of_device.h>
> +#include <linux/platform_device.h>
> +#include <linux/pm_qos.h>
> +#include <linux/sizes.h>
> +
> +#include <linux/spi/spi.h>
> +#include <linux/spi/spi-mem.h>
> +
> +/*
> + * The driver only uses one single LUT entry, that is updated on
> + * each call of exec_op(). Index 0 is preset at boot with a basic
> + * read operation, so let's use the last entry (15).
> + */
> +#define	SEQID_LUT			15
> +
> +/* Registers used by the driver */
> +#define QUADSPI_MCR			0x00
> +#define QUADSPI_MCR_RESERVED_MASK	GENMASK(19, 16)
> +#define QUADSPI_MCR_MDIS_MASK		BIT(14)
> +#define QUADSPI_MCR_CLR_TXF_MASK	BIT(11)
> +#define QUADSPI_MCR_CLR_RXF_MASK	BIT(10)
> +#define QUADSPI_MCR_DDR_EN_MASK		BIT(7)
> +#define QUADSPI_MCR_END_CFG_MASK	GENMASK(3, 2)
> +#define QUADSPI_MCR_SWRSTHD_MASK	BIT(1)
> +#define QUADSPI_MCR_SWRSTSD_MASK	BIT(0)
> +
> +#define QUADSPI_IPCR			0x08
> +#define QUADSPI_IPCR_SEQID(x)		((x) << 24)
> +
> +#define QUADSPI_BUF3CR			0x1c
> +#define QUADSPI_BUF3CR_ALLMST_MASK	BIT(31)
> +#define QUADSPI_BUF3CR_ADATSZ(x)	((x) << 8)
> +#define QUADSPI_BUF3CR_ADATSZ_MASK	GENMASK(15, 8)
> +
> +#define QUADSPI_BFGENCR			0x20
> +#define QUADSPI_BFGENCR_SEQID(x)	((x) << 12)
> +
> +#define QUADSPI_BUF0IND			0x30
> +#define QUADSPI_BUF1IND			0x34
> +#define QUADSPI_BUF2IND			0x38
> +#define QUADSPI_SFAR			0x100
> +
> +#define QUADSPI_SMPR			0x108
> +#define QUADSPI_SMPR_DDRSMP_MASK	GENMASK(18, 16)
> +#define QUADSPI_SMPR_FSDLY_MASK		BIT(6)
> +#define QUADSPI_SMPR_FSPHS_MASK		BIT(5)
> +#define QUADSPI_SMPR_HSENA_MASK		BIT(0)
> +
> +#define QUADSPI_RBCT			0x110
> +#define QUADSPI_RBCT_WMRK_MASK		GENMASK(4, 0)
> +#define QUADSPI_RBCT_RXBRD_USEIPS	BIT(8)
> +
> +#define QUADSPI_TBDR			0x154
> +
> +#define QUADSPI_SR			0x15c
> +#define QUADSPI_SR_IP_ACC_MASK		BIT(1)
> +#define QUADSPI_SR_AHB_ACC_MASK		BIT(2)
> +
> +#define QUADSPI_FR			0x160
> +#define QUADSPI_FR_TFF_MASK		BIT(0)
> +
> +#define QUADSPI_SPTRCLR			0x16c
> +#define QUADSPI_SPTRCLR_IPPTRC		BIT(8)
> +#define QUADSPI_SPTRCLR_BFPTRC		BIT(0)
> +
> +#define QUADSPI_SFA1AD			0x180
> +#define QUADSPI_SFA2AD			0x184
> +#define QUADSPI_SFB1AD			0x188
> +#define QUADSPI_SFB2AD			0x18c
> +#define QUADSPI_RBDR(x)			(0x200 + ((x) * 4))
> +
> +#define QUADSPI_LUTKEY			0x300
> +#define QUADSPI_LUTKEY_VALUE		0x5AF05AF0
> +
> +#define QUADSPI_LCKCR			0x304
> +#define QUADSPI_LCKER_LOCK		BIT(0)
> +#define QUADSPI_LCKER_UNLOCK		BIT(1)
> +
> +#define QUADSPI_RSER			0x164
> +#define QUADSPI_RSER_TFIE		BIT(0)
> +
> +#define QUADSPI_LUT_BASE		0x310
> +#define QUADSPI_LUT_OFFSET		(SEQID_LUT * 4 * 4)
> +#define QUADSPI_LUT_REG(idx) \
> +	(QUADSPI_LUT_BASE + QUADSPI_LUT_OFFSET + (idx) * 4)
> +
> +/* Instruction set for the LUT register */
> +#define LUT_STOP		0
> +#define LUT_CMD			1
> +#define LUT_ADDR		2
> +#define LUT_DUMMY		3
> +#define LUT_MODE		4
> +#define LUT_MODE2		5
> +#define LUT_MODE4		6
> +#define LUT_FSL_READ		7
> +#define LUT_FSL_WRITE		8
> +#define LUT_JMP_ON_CS		9
> +#define LUT_ADDR_DDR		10
> +#define LUT_MODE_DDR		11
> +#define LUT_MODE2_DDR		12
> +#define LUT_MODE4_DDR		13
> +#define LUT_FSL_READ_DDR	14
> +#define LUT_FSL_WRITE_DDR	15
> +#define LUT_DATA_LEARN		16
> +
> +/*
> + * The PAD definitions for LUT register.
> + *
> + * The pad stands for the number of IO lines [0:3].
> + * For example, the quad read needs four IO lines,
> + * so you should use LUT_PAD(4).
> + */
> +#define LUT_PAD(x) (fls(x) - 1)
> +
> +/*
> + * Macro for constructing the LUT entries with the following
> + * register layout:
> + *
> + *  ---------------------------------------------------
> + *  | INSTR1 | PAD1 | OPRND1 | INSTR0 | PAD0 | OPRND0 |
> + *  ---------------------------------------------------
> + */
> +#define LUT_DEF(idx, ins, pad, opr)					\
> +	((((ins) << 10) | ((pad) << 8) | (opr)) << (((idx) % 2) * 16))
> +
> +/* Controller needs driver to swap endianness */
> +#define QUADSPI_QUIRK_SWAP_ENDIAN	BIT(0)
> +
> +/* Controller needs 4x internal clock */
> +#define QUADSPI_QUIRK_4X_INT_CLK	BIT(1)
> +
> +/*
> + * TKT253890, the controller needs the driver to fill the txfifo with
> + * 16 bytes at least to trigger a data transfer, even though the extra
> + * data won't be transferred.
> + */
> +#define QUADSPI_QUIRK_TKT253890		BIT(2)
> +
> +/* TKT245618, the controller cannot wake up from wait mode */
> +#define QUADSPI_QUIRK_TKT245618		BIT(3)
> +
> +/*
> + * Controller adds QSPI_AMBA_BASE (base address of the mapped memory)
> + * internally. No need to add it when setting SFXXAD and SFAR registers
> +*/
> +#define QUADSPI_QUIRK_BASE_INTERNAL	BIT(4)
> +
> +struct fsl_qspi_devtype_data {
> +	unsigned int rxfifo;
> +	unsigned int txfifo;
> +	unsigned int ahb_buf_size;
> +	unsigned int quirks;
> +	bool little_endian;
> +};
> +
> +static const struct fsl_qspi_devtype_data vybrid_data = {
> +	.rxfifo = SZ_128,
> +	.txfifo = SZ_64,
> +	.ahb_buf_size = SZ_1K,
> +	.quirks = QUADSPI_QUIRK_SWAP_ENDIAN,
> +	.little_endian = true,
> +};
> +
> +static const struct fsl_qspi_devtype_data imx6sx_data = {
> +	.rxfifo = SZ_128,
> +	.txfifo = SZ_512,
> +	.ahb_buf_size = SZ_1K,
> +	.quirks = QUADSPI_QUIRK_4X_INT_CLK | QUADSPI_QUIRK_TKT245618,
> +	.little_endian = true,
> +};
> +
> +static const struct fsl_qspi_devtype_data imx7d_data = {
> +	.rxfifo = SZ_512,
> +	.txfifo = SZ_512,
> +	.ahb_buf_size = SZ_1K,
> +	.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK,
> +	.little_endian = true,
> +};
> +
> +static const struct fsl_qspi_devtype_data imx6ul_data = {
> +	.rxfifo = SZ_128,
> +	.txfifo = SZ_512,
> +	.ahb_buf_size = SZ_1K,
> +	.quirks = QUADSPI_QUIRK_TKT253890 | QUADSPI_QUIRK_4X_INT_CLK,
> +	.little_endian = true,
> +};
> +
> +static const struct fsl_qspi_devtype_data ls1021a_data = {
> +	.rxfifo = SZ_128,
> +	.txfifo = SZ_64,
> +	.ahb_buf_size = SZ_1K,
> +	.quirks = 0,
> +	.little_endian = false,
> +};
> +
> +static const struct fsl_qspi_devtype_data ls2080a_data = {
> +	.rxfifo = SZ_128,
> +	.txfifo = SZ_64,
> +	.ahb_buf_size = SZ_1K,
> +	.quirks = QUADSPI_QUIRK_TKT253890 |
> QUADSPI_QUIRK_BASE_INTERNAL,
> +	.little_endian = true,
> +};
> +
> +struct fsl_qspi {
> +	void __iomem *iobase;
> +	void __iomem *ahb_addr;
> +	u32 memmap_phy;
> +	struct clk *clk, *clk_en;
> +	struct device *dev;
> +	struct completion c;
> +	const struct fsl_qspi_devtype_data *devtype_data;
> +	struct mutex lock;
> +	struct pm_qos_request pm_qos_req;
> +	int selected;
> +};
> +
> +static inline int needs_swap_endian(struct fsl_qspi *q) {
> +	return q->devtype_data->quirks & QUADSPI_QUIRK_SWAP_ENDIAN; }
> +
> +static inline int needs_4x_clock(struct fsl_qspi *q) {
> +	return q->devtype_data->quirks & QUADSPI_QUIRK_4X_INT_CLK; }
> +
> +static inline int needs_fill_txfifo(struct fsl_qspi *q) {
> +	return q->devtype_data->quirks & QUADSPI_QUIRK_TKT253890; }
> +
> +static inline int needs_wakeup_wait_mode(struct fsl_qspi *q) {
> +	return q->devtype_data->quirks & QUADSPI_QUIRK_TKT245618; }
> +
> +static inline int needs_amba_base_offset(struct fsl_qspi *q) {
> +	return !(q->devtype_data->quirks &
> QUADSPI_QUIRK_BASE_INTERNAL); }
> +
> +/*
> + * An IC bug makes it necessary to rearrange the 32-bit data.
> + * Later chips, such as IMX6SLX, have fixed this bug.
> + */
> +static inline u32 fsl_qspi_endian_xchg(struct fsl_qspi *q, u32 a) {
> +	return needs_swap_endian(q) ? __swab32(a) : a; }
> +
> +/*
> + * R/W functions for big- or little-endian registers:
> + * The QSPI controller's endianness is independent of
> + * the CPU core's endianness. So far, although the CPU
> + * core is little-endian the QSPI controller can use
> + * big-endian or little-endian.
> + */
> +static void qspi_writel(struct fsl_qspi *q, u32 val, void __iomem
> +*addr) {
> +	if (q->devtype_data->little_endian)
> +		iowrite32(val, addr);
> +	else
> +		iowrite32be(val, addr);
> +}
> +
> +static u32 qspi_readl(struct fsl_qspi *q, void __iomem *addr) {
> +	if (q->devtype_data->little_endian)
> +		return ioread32(addr);
> +
> +	return ioread32be(addr);
> +}
> +
> +static irqreturn_t fsl_qspi_irq_handler(int irq, void *dev_id) {
> +	struct fsl_qspi *q = dev_id;
> +	u32 reg;
> +
> +	/* clear interrupt */
> +	reg = qspi_readl(q, q->iobase + QUADSPI_FR);
> +	qspi_writel(q, reg, q->iobase + QUADSPI_FR);
> +
> +	if (reg & QUADSPI_FR_TFF_MASK)
> +		complete(&q->c);
> +
> +	dev_dbg(q->dev, "QUADSPI_FR : 0x%.8x:0x%.8x\n", 0, reg);
> +	return IRQ_HANDLED;
> +}
> +
> +static int fsl_qspi_check_buswidth(struct fsl_qspi *q, u8 width) {
> +	switch (width) {
> +	case 1:
> +	case 2:
> +	case 4:
> +		return 0;
> +	}
> +
> +	return -ENOTSUPP;
> +}
> +
> +static bool fsl_qspi_supports_op(struct spi_mem *mem,
> +				 const struct spi_mem_op *op)
> +{
> +	struct fsl_qspi *q = spi_controller_get_devdata(mem->spi->master);
> +	int ret;
> +
> +	ret = fsl_qspi_check_buswidth(q, op->cmd.buswidth);
> +
> +	if (op->addr.nbytes)
> +		ret |= fsl_qspi_check_buswidth(q, op->addr.buswidth);
> +
> +	if (op->dummy.nbytes)
> +		ret |= fsl_qspi_check_buswidth(q, op->dummy.buswidth);
> +
> +	if (op->data.nbytes)
> +		ret |= fsl_qspi_check_buswidth(q, op->data.buswidth);
> +
> +	if (ret)
> +		return false;
> +
> +	/*
> +	 * The number of instructions needed for the op, needs
> +	 * to fit into a single LUT entry.
> +	 */
> +	if (op->addr.nbytes +
> +	   (op->dummy.nbytes ? 1:0) +
> +	   (op->data.nbytes ? 1:0) > 6)
> +		return false;
> +
> +	/* Max 64 dummy clock cycles supported */
> +	if (op->dummy.nbytes &&
> +	    (op->dummy.nbytes * 8 / op->dummy.buswidth > 64))
> +		return false;
> +
> +	/* Max data length, check controller limits and alignment */
> +	if (op->data.dir == SPI_MEM_DATA_IN &&
> +	    (op->data.nbytes > q->devtype_data->ahb_buf_size ||
> +	     (op->data.nbytes > q->devtype_data->rxfifo - 4 &&
> +	      !IS_ALIGNED(op->data.nbytes, 8))))
> +		return false;
> +
> +	if (op->data.dir == SPI_MEM_DATA_OUT &&
> +	    op->data.nbytes > q->devtype_data->txfifo)
> +		return false;
> +
> +	return true;
> +}
> +
> +static void fsl_qspi_prepare_lut(struct fsl_qspi *q,
> +				 const struct spi_mem_op *op)
> +{
> +	void __iomem *base = q->iobase;
> +	u32 lutval[4] = {};
> +	int lutidx = 1, i;
> +
> +	lutval[0] |= LUT_DEF(0, LUT_CMD, LUT_PAD(op->cmd.buswidth),
> +			     op->cmd.opcode);
> +
> +	/*
> +	 * For some unknown reason, using LUT_ADDR doesn't work in some
> +	 * cases (at least with only one byte long addresses), so
> +	 * let's use LUT_MODE to write the address bytes one by one
> +	 */
> +	for (i = 0; i < op->addr.nbytes; i++) {
> +		u8 addrbyte = op->addr.val >> (8 * (op->addr.nbytes - i - 1));
> +
> +		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_MODE,
> +					      LUT_PAD(op->addr.buswidth),
> +					      addrbyte);
> +		lutidx++;
> +	}
> +
> +	if (op->dummy.nbytes) {
> +		lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_DUMMY,
> +					      LUT_PAD(op->dummy.buswidth),
> +					      op->dummy.nbytes * 8 /
> +					      op->dummy.buswidth);
> +		lutidx++;
> +	}
> +
> +	if (op->data.nbytes) {
> +		lutval[lutidx / 2] |= LUT_DEF(lutidx,
> +					      op->data.dir ==
> SPI_MEM_DATA_IN ?
> +					      LUT_FSL_READ : LUT_FSL_WRITE,
> +					      LUT_PAD(op->data.buswidth),
> +					      0);
> +		lutidx++;
> +	}
> +
> +	lutval[lutidx / 2] |= LUT_DEF(lutidx, LUT_STOP, 0, 0);
> +
> +	/* unlock LUT */
> +	qspi_writel(q, QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
> +	qspi_writel(q, QUADSPI_LCKER_UNLOCK, q->iobase + QUADSPI_LCKCR);
> +
> +	/* fill LUT */
> +	for (i = 0; i < ARRAY_SIZE(lutval); i++)
> +		qspi_writel(q, lutval[i], base + QUADSPI_LUT_REG(i));
> +
> +	/* lock LUT */
> +	qspi_writel(q, QUADSPI_LUTKEY_VALUE, q->iobase + QUADSPI_LUTKEY);
> +	qspi_writel(q, QUADSPI_LCKER_LOCK, q->iobase + QUADSPI_LCKCR); }
> +
> +static int fsl_qspi_clk_prep_enable(struct fsl_qspi *q) {
> +	int ret;
> +
> +	ret = clk_prepare_enable(q->clk_en);
> +	if (ret)
> +		return ret;
> +
> +	ret = clk_prepare_enable(q->clk);
> +	if (ret) {
> +		clk_disable_unprepare(q->clk_en);
> +		return ret;
> +	}
> +
> +	if (needs_wakeup_wait_mode(q))
> +		pm_qos_add_request(&q->pm_qos_req,
> PM_QOS_CPU_DMA_LATENCY, 0);
> +
> +	return 0;
> +}
> +
> +static void fsl_qspi_clk_disable_unprep(struct fsl_qspi *q) {
> +	if (needs_wakeup_wait_mode(q))
> +		pm_qos_remove_request(&q->pm_qos_req);
> +
> +	clk_disable_unprepare(q->clk);
> +	clk_disable_unprepare(q->clk_en);
> +}
> +
> +/*
> + * If we have changed the content of the flash by writing or erasing,
> +or if we
> + * read from flash with a different offset into the page buffer, we
> +need to
> + * invalidate the AHB buffer. If we do not do so, we may read out the
> +wrong
> + * data. The spec tells us reset the AHB domain and Serial Flash domain
> +at
> + * the same time.
> + */
> +static void fsl_qspi_invalidate(struct fsl_qspi *q) {
> +	u32 reg;
> +
> +	reg = qspi_readl(q, q->iobase + QUADSPI_MCR);
> +	reg |= QUADSPI_MCR_SWRSTHD_MASK |
> QUADSPI_MCR_SWRSTSD_MASK;
> +	qspi_writel(q, reg, q->iobase + QUADSPI_MCR);
> +
> +	/*
> +	 * The minimum delay : 1 AHB + 2 SFCK clocks.
> +	 * Delay 1 us is enough.
> +	 */
> +	udelay(1);
> +
> +	reg &= ~(QUADSPI_MCR_SWRSTHD_MASK |
> QUADSPI_MCR_SWRSTSD_MASK);
> +	qspi_writel(q, reg, q->iobase + QUADSPI_MCR); }
> +
> +static void fsl_qspi_select_mem(struct fsl_qspi *q, struct spi_device
> +*spi) {
> +	unsigned long rate = spi->max_speed_hz;
> +	int ret;
> +
> +	if (q->selected == spi->chip_select)
> +		return;
> +
> +	if (needs_4x_clock(q))
> +		rate *= 4;
> +
> +	fsl_qspi_clk_disable_unprep(q);
> +
> +	ret = clk_set_rate(q->clk, rate);
> +	if (ret)
> +		return;
> +
> +	ret = fsl_qspi_clk_prep_enable(q);
> +	if (ret)
> +		return;
> +
> +	q->selected = spi->chip_select;
> +
> +	fsl_qspi_invalidate(q);
> +}
> +
> +static void fsl_qspi_read_ahb(struct fsl_qspi *q, const struct
> +spi_mem_op *op) {
> +	memcpy_fromio(op->data.buf.in,
> +		      q->ahb_addr + q->selected * q->devtype_data-
> >ahb_buf_size,
> +		      op->data.nbytes);
> +}
> +
> +static void fsl_qspi_fill_txfifo(struct fsl_qspi *q,
> +				 const struct spi_mem_op *op)
> +{
> +	void __iomem *base = q->iobase;
> +	int i;
> +	u32 val;
> +
> +	for (i = 0; i < ALIGN_DOWN(op->data.nbytes, 4); i += 4) {
> +		memcpy(&val, op->data.buf.out + i, 4);
> +		val = fsl_qspi_endian_xchg(q, val);
> +		qspi_writel(q, val, base + QUADSPI_TBDR);
> +	}
> +
> +	if (i < op->data.nbytes) {
> +		memcpy(&val, op->data.buf.out + i, op->data.nbytes - i);
> +		val = fsl_qspi_endian_xchg(q, val);
> +		qspi_writel(q, val, base + QUADSPI_TBDR);
> +	}
> +
> +	if (needs_fill_txfifo(q)) {
> +		for (i = op->data.nbytes; i < 16; i += 4)
> +			qspi_writel(q, 0, base + QUADSPI_TBDR);
> +	}
> +}
> +
> +static void fsl_qspi_read_rxfifo(struct fsl_qspi *q,
> +			  const struct spi_mem_op *op)
> +{
> +	void __iomem *base = q->iobase;
> +	int i;
> +	u8 *buf = op->data.buf.in;
> +	u32 val;
> +
> +	for (i = 0; i < ALIGN_DOWN(op->data.nbytes, 4); i += 4) {
> +		val = qspi_readl(q, base + QUADSPI_RBDR(i / 4));
> +		val = fsl_qspi_endian_xchg(q, val);
> +		memcpy(buf + i, &val, 4);
> +	}
> +
> +	if (i < op->data.nbytes) {
> +		val = qspi_readl(q, base + QUADSPI_RBDR(i / 4));
> +		val = fsl_qspi_endian_xchg(q, val);
> +		memcpy(buf + i, &val, op->data.nbytes - i);
> +	}
> +}
> +
> +static int fsl_qspi_do_op(struct fsl_qspi *q, const struct spi_mem_op
> +*op) {
> +	void __iomem *base = q->iobase;
> +	int err = 0;
> +
> +	init_completion(&q->c);
> +
> +	/*
> +	 * Always start the sequence at the same index since we update
> +	 * the LUT at each exec_op() call. And also specify the DATA
> +	 * length, since it's has not been specified in the LUT.
> +	 */
> +	qspi_writel(q, op->data.nbytes | QUADSPI_IPCR_SEQID(SEQID_LUT),
> +		    base + QUADSPI_IPCR);
> +
> +	/* Wait for the interrupt. */
> +	if (!wait_for_completion_timeout(&q->c, msecs_to_jiffies(1000)))
> +		err = -ETIMEDOUT;
> +
> +	if (!err && op->data.nbytes && op->data.dir == SPI_MEM_DATA_IN)
> +		fsl_qspi_read_rxfifo(q, op);
> +
> +	return err;
> +}
> +
> +static int fsl_qspi_readl_poll_tout(struct fsl_qspi *q, void __iomem *base,
> +				    u32 mask, u32 delay_us, u32 timeout_us) {
> +	u32 reg;
> +
> +	if (!q->devtype_data->little_endian)
> +		mask = (u32)cpu_to_be32(mask);
> +

reg is being used as an un-initialized variable, didn't it needs to be initialized with some proper value?

> +	return readl_poll_timeout(base, reg, !(reg & mask), delay_us,
> +				  timeout_us);
> +}
> +

--
Regards
Yogesh Gaur.

[...]