Merge tag 'spi-nor/for-4.11-v2' of git://github.com/spi-nor/linux

From Cyrille:

"""
This pull request contains the following notable changes:
- add support to the 4-byte address instruction set.
- add support to new memory parts.
- add support to S3AN memories.
- add support to the Intel SPI controller.
- add support to the Aspeed AST2400 and AST2550 controllers.
- fix max SPI transfer and message sizes in m25p80_read().
- fix the Candence QSPI driver.
- fix the Freescale QSPI driver.
"""

9 files changed, 1913 insertions, 67 deletions

diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index 4a682ee0f632..7252087ef407 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -29,6 +29,16 @@ config MTD_SPI_NOR_USE_4K_SECTORS
 	  Please note that some tools/drivers/filesystems may not work with
 	  4096 B erase size (e.g. UBIFS requires 15 KiB as a minimum).
 
+config SPI_ASPEED_SMC
+	tristate "Aspeed flash controllers in SPI mode"
+	depends on ARCH_ASPEED || COMPILE_TEST
+	depends on HAS_IOMEM && OF
+	help
+	  This enables support for the Firmware Memory controller (FMC)
+	  in the Aspeed AST2500/AST2400 SoCs when attached to SPI NOR chips,
+	  and support for the SPI flash memory controller (SPI) for
+	  the host firmware. The implementation only supports SPI NOR.
+
 config SPI_ATMEL_QUADSPI
 	tristate "Atmel Quad SPI Controller"
 	depends on ARCH_AT91 || (ARM && COMPILE_TEST)
@@ -40,7 +50,7 @@ config SPI_ATMEL_QUADSPI
 
 config SPI_CADENCE_QUADSPI
 	tristate "Cadence Quad SPI controller"
-	depends on OF && ARM
+	depends on OF && (ARM || COMPILE_TEST)
 	help
 	  Enable support for the Cadence Quad SPI Flash controller.
 
@@ -76,4 +86,24 @@ config SPI_NXP_SPIFI
 	  Flash. Enable this option if you have a device with a SPIFI
 	  controller and want to access the Flash as a mtd device.
 
+config SPI_INTEL_SPI
+	tristate
+
+config SPI_INTEL_SPI_PLATFORM
+	tristate "Intel PCH/PCU SPI flash platform driver" if EXPERT
+	depends on X86
+	select SPI_INTEL_SPI
+	help
+	  This enables platform support for the Intel PCH/PCU SPI
+	  controller in master mode. This controller is present in modern
+	  Intel hardware and is used to hold BIOS and other persistent
+	  settings. Using this driver it is possible to upgrade BIOS
+	  directly from Linux.
+
+	  Say N here unless you know what you are doing. Overwriting the
+	  SPI flash may render the system unbootable.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called intel-spi-platform.
+
 endif # MTD_SPI_NOR
diff --git a/drivers/mtd/spi-nor/Makefile b/drivers/mtd/spi-nor/Makefile
index 121695e83542..72238a793198 100644
--- a/drivers/mtd/spi-nor/Makefile
+++ b/drivers/mtd/spi-nor/Makefile
@@ -1,7 +1,10 @@
 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
+obj-$(CONFIG_SPI_INTEL_SPI)	+= intel-spi.o
+obj-$(CONFIG_SPI_INTEL_SPI_PLATFORM)	+= intel-spi-platform.o
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
new file mode 100644
index 000000000000..7c86099450be
--- /dev/null
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -0,0 +1,758 @@
+/*
+ * ASPEED Static Memory Controller driver
+ *
+ * Copyright (c) 2015-2016, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bug.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/sysfs.h>
+
+#define DEVICE_NAME	"aspeed-smc"
+
+/*
+ * The driver only support SPI flash
+ */
+enum aspeed_smc_flash_type {
+	smc_type_nor  = 0,
+	smc_type_nand = 1,
+	smc_type_spi  = 2,
+};
+
+struct aspeed_smc_chip;
+
+struct aspeed_smc_info {
+	u32 maxsize;		/* maximum size of chip window */
+	u8 nce;			/* number of chip enables */
+	bool hastype;		/* flash type field exists in config reg */
+	u8 we0;			/* shift for write enable bit for CE0 */
+	u8 ctl0;		/* offset in regs of ctl for CE0 */
+
+	void (*set_4b)(struct aspeed_smc_chip *chip);
+};
+
+static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip);
+static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip);
+
+static const struct aspeed_smc_info fmc_2400_info = {
+	.maxsize = 64 * 1024 * 1024,
+	.nce = 5,
+	.hastype = true,
+	.we0 = 16,
+	.ctl0 = 0x10,
+	.set_4b = aspeed_smc_chip_set_4b,
+};
+
+static const struct aspeed_smc_info spi_2400_info = {
+	.maxsize = 64 * 1024 * 1024,
+	.nce = 1,
+	.hastype = false,
+	.we0 = 0,
+	.ctl0 = 0x04,
+	.set_4b = aspeed_smc_chip_set_4b_spi_2400,
+};
+
+static const struct aspeed_smc_info fmc_2500_info = {
+	.maxsize = 256 * 1024 * 1024,
+	.nce = 3,
+	.hastype = true,
+	.we0 = 16,
+	.ctl0 = 0x10,
+	.set_4b = aspeed_smc_chip_set_4b,
+};
+
+static const struct aspeed_smc_info spi_2500_info = {
+	.maxsize = 128 * 1024 * 1024,
+	.nce = 2,
+	.hastype = false,
+	.we0 = 16,
+	.ctl0 = 0x10,
+	.set_4b = aspeed_smc_chip_set_4b,
+};
+
+enum aspeed_smc_ctl_reg_value {
+	smc_base,		/* base value without mode for other commands */
+	smc_read,		/* command reg for (maybe fast) reads */
+	smc_write,		/* command reg for writes */
+	smc_max,
+};
+
+struct aspeed_smc_controller;
+
+struct aspeed_smc_chip {
+	int cs;
+	struct aspeed_smc_controller *controller;
+	void __iomem *ctl;			/* control register */
+	void __iomem *ahb_base;			/* base of chip window */
+	u32 ctl_val[smc_max];			/* control settings */
+	enum aspeed_smc_flash_type type;	/* what type of flash */
+	struct spi_nor nor;
+};
+
+struct aspeed_smc_controller {
+	struct device *dev;
+
+	struct mutex mutex;			/* controller access mutex */
+	const struct aspeed_smc_info *info;	/* type info of controller */
+	void __iomem *regs;			/* controller registers */
+	void __iomem *ahb_base;			/* per-chip windows resource */
+
+	struct aspeed_smc_chip *chips[0];	/* pointers to attached chips */
+};
+
+/*
+ * SPI Flash Configuration Register (AST2500 SPI)
+ *     or
+ * Type setting Register (AST2500 FMC).
+ * CE0 and CE1 can only be of type SPI. CE2 can be of type NOR but the
+ * driver does not support it.
+ */
+#define CONFIG_REG			0x0
+#define CONFIG_DISABLE_LEGACY		BIT(31) /* 1 */
+
+#define CONFIG_CE2_WRITE		BIT(18)
+#define CONFIG_CE1_WRITE		BIT(17)
+#define CONFIG_CE0_WRITE		BIT(16)
+
+#define CONFIG_CE2_TYPE			BIT(4) /* AST2500 FMC only */
+#define CONFIG_CE1_TYPE			BIT(2) /* AST2500 FMC only */
+#define CONFIG_CE0_TYPE			BIT(0) /* AST2500 FMC only */
+
+/*
+ * CE Control Register
+ */
+#define CE_CONTROL_REG			0x4
+
+/*
+ * CEx Control Register
+ */
+#define CONTROL_AAF_MODE		BIT(31)
+#define CONTROL_IO_MODE_MASK		GENMASK(30, 28)
+#define CONTROL_IO_DUAL_DATA		BIT(29)
+#define CONTROL_IO_DUAL_ADDR_DATA	(BIT(29) | BIT(28))
+#define CONTROL_IO_QUAD_DATA		BIT(30)
+#define CONTROL_IO_QUAD_ADDR_DATA	(BIT(30) | BIT(28))
+#define CONTROL_CE_INACTIVE_SHIFT	24
+#define CONTROL_CE_INACTIVE_MASK	GENMASK(27, \
+					CONTROL_CE_INACTIVE_SHIFT)
+/* 0 = 16T ... 15 = 1T   T=HCLK */
+#define CONTROL_COMMAND_SHIFT		16
+#define CONTROL_DUMMY_COMMAND_OUT	BIT(15)
+#define CONTROL_IO_DUMMY_HI		BIT(14)
+#define CONTROL_IO_DUMMY_HI_SHIFT	14
+#define CONTROL_CLK_DIV4		BIT(13) /* others */
+#define CONTROL_IO_ADDRESS_4B		BIT(13) /* AST2400 SPI */
+#define CONTROL_RW_MERGE		BIT(12)
+#define CONTROL_IO_DUMMY_LO_SHIFT	6
+#define CONTROL_IO_DUMMY_LO		GENMASK(7, \
+						CONTROL_IO_DUMMY_LO_SHIFT)
+#define CONTROL_IO_DUMMY_MASK		(CONTROL_IO_DUMMY_HI | \
+					 CONTROL_IO_DUMMY_LO)
+#define CONTROL_IO_DUMMY_SET(dummy)				 \
+	(((((dummy) >> 2) & 0x1) << CONTROL_IO_DUMMY_HI_SHIFT) | \
+	 (((dummy) & 0x3) << CONTROL_IO_DUMMY_LO_SHIFT))
+
+#define CONTROL_CLOCK_FREQ_SEL_SHIFT	8
+#define CONTROL_CLOCK_FREQ_SEL_MASK	GENMASK(11, \
+						CONTROL_CLOCK_FREQ_SEL_SHIFT)
+#define CONTROL_LSB_FIRST		BIT(5)
+#define CONTROL_CLOCK_MODE_3		BIT(4)
+#define CONTROL_IN_DUAL_DATA		BIT(3)
+#define CONTROL_CE_STOP_ACTIVE_CONTROL	BIT(2)
+#define CONTROL_COMMAND_MODE_MASK	GENMASK(1, 0)
+#define CONTROL_COMMAND_MODE_NORMAL	0
+#define CONTROL_COMMAND_MODE_FREAD	1
+#define CONTROL_COMMAND_MODE_WRITE	2
+#define CONTROL_COMMAND_MODE_USER	3
+
+#define CONTROL_KEEP_MASK						\
+	(CONTROL_AAF_MODE | CONTROL_CE_INACTIVE_MASK | CONTROL_CLK_DIV4 | \
+	 CONTROL_IO_DUMMY_MASK | CONTROL_CLOCK_FREQ_SEL_MASK |		\
+	 CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3)
+
+/*
+ * The Segment Register uses a 8MB unit to encode the start address
+ * and the end address of the mapping window of a flash SPI slave :
+ *
+ *        | byte 1 | byte 2 | byte 3 | byte 4 |
+ *        +--------+--------+--------+--------+
+ *        |  end   |  start |   0    |   0    |
+ */
+#define SEGMENT_ADDR_REG0		0x30
+#define SEGMENT_ADDR_START(_r)		((((_r) >> 16) & 0xFF) << 23)
+#define SEGMENT_ADDR_END(_r)		((((_r) >> 24) & 0xFF) << 23)
+
+/*
+ * In user mode all data bytes read or written to the chip decode address
+ * range are transferred to or from the SPI bus. The range is treated as a
+ * fifo of arbitratry 1, 2, or 4 byte width but each write has to be aligned
+ * to its size. The address within the multiple 8kB range is ignored when
+ * sending bytes to the SPI bus.
+ *
+ * On the arm architecture, as of Linux version 4.3, memcpy_fromio and
+ * memcpy_toio on little endian targets use the optimized memcpy routines
+ * that were designed for well behavied memory storage. These routines
+ * have a stutter if the source and destination are not both word aligned,
+ * once with a duplicate access to the source after aligning to the
+ * destination to a word boundary, and again with a duplicate access to
+ * the source when the final byte count is not word aligned.
+ *
+ * When writing or reading the fifo this stutter discards data or sends
+ * too much data to the fifo and can not be used by this driver.
+ *
+ * While the low level io string routines that implement the insl family do
+ * the desired accesses and memory increments, the cross architecture io
+ * macros make them essentially impossible to use on a memory mapped address
+ * instead of a a token from the call to iomap of an io port.
+ *
+ * These fifo routines use readl and friends to a constant io port and update
+ * the memory buffer pointer and count via explicit code. The final updates
+ * to len are optimistically suppressed.
+ */
+static int aspeed_smc_read_from_ahb(void *buf, void __iomem *src, size_t len)
+{
+	size_t offset = 0;
+
+	if (IS_ALIGNED((uintptr_t)src, sizeof(uintptr_t)) &&
+	    IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) {
+		ioread32_rep(src, buf, len >> 2);
+		offset = len & ~0x3;
+		len -= offset;
+	}
+	ioread8_rep(src, (u8 *)buf + offset, len);
+	return 0;
+}
+
+static int aspeed_smc_write_to_ahb(void __iomem *dst, const void *buf,
+				   size_t len)
+{
+	size_t offset = 0;
+
+	if (IS_ALIGNED((uintptr_t)dst, sizeof(uintptr_t)) &&
+	    IS_ALIGNED((uintptr_t)buf, sizeof(uintptr_t))) {
+		iowrite32_rep(dst, buf, len >> 2);
+		offset = len & ~0x3;
+		len -= offset;
+	}
+	iowrite8_rep(dst, (const u8 *)buf + offset, len);
+	return 0;
+}
+
+static inline u32 aspeed_smc_chip_write_bit(struct aspeed_smc_chip *chip)
+{
+	return BIT(chip->controller->info->we0 + chip->cs);
+}
+
+static void aspeed_smc_chip_check_config(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	reg = readl(controller->regs + CONFIG_REG);
+
+	if (reg & aspeed_smc_chip_write_bit(chip))
+		return;
+
+	dev_dbg(controller->dev, "config write is not set ! @%p: 0x%08x\n",
+		controller->regs + CONFIG_REG, reg);
+	reg |= aspeed_smc_chip_write_bit(chip);
+	writel(reg, controller->regs + CONFIG_REG);
+}
+
+static void aspeed_smc_start_user(struct spi_nor *nor)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+	u32 ctl = chip->ctl_val[smc_base];
+
+	/*
+	 * When the chip is controlled in user mode, we need write
+	 * access to send the opcodes to it. So check the config.
+	 */
+	aspeed_smc_chip_check_config(chip);
+
+	ctl |= CONTROL_COMMAND_MODE_USER |
+		CONTROL_CE_STOP_ACTIVE_CONTROL;
+	writel(ctl, chip->ctl);
+
+	ctl &= ~CONTROL_CE_STOP_ACTIVE_CONTROL;
+	writel(ctl, chip->ctl);
+}
+
+static void aspeed_smc_stop_user(struct spi_nor *nor)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	u32 ctl = chip->ctl_val[smc_read];
+	u32 ctl2 = ctl | CONTROL_COMMAND_MODE_USER |
+		CONTROL_CE_STOP_ACTIVE_CONTROL;
+
+	writel(ctl2, chip->ctl);	/* stop user CE control */
+	writel(ctl, chip->ctl);		/* default to fread or read mode */
+}
+
+static int aspeed_smc_prep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	mutex_lock(&chip->controller->mutex);
+	return 0;
+}
+
+static void aspeed_smc_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	mutex_unlock(&chip->controller->mutex);
+}
+
+static int aspeed_smc_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1);
+	aspeed_smc_read_from_ahb(buf, chip->ahb_base, len);
+	aspeed_smc_stop_user(nor);
+	return 0;
+}
+
+static int aspeed_smc_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
+				int len)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_write_to_ahb(chip->ahb_base, &opcode, 1);
+	aspeed_smc_write_to_ahb(chip->ahb_base, buf, len);
+	aspeed_smc_stop_user(nor);
+	return 0;
+}
+
+static void aspeed_smc_send_cmd_addr(struct spi_nor *nor, u8 cmd, u32 addr)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+	__be32 temp;
+	u32 cmdaddr;
+
+	switch (nor->addr_width) {
+	default:
+		WARN_ONCE(1, "Unexpected address width %u, defaulting to 3\n",
+			  nor->addr_width);
+		/* FALLTHROUGH */
+	case 3:
+		cmdaddr = addr & 0xFFFFFF;
+		cmdaddr |= cmd << 24;
+
+		temp = cpu_to_be32(cmdaddr);
+		aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4);
+		break;
+	case 4:
+		temp = cpu_to_be32(addr);
+		aspeed_smc_write_to_ahb(chip->ahb_base, &cmd, 1);
+		aspeed_smc_write_to_ahb(chip->ahb_base, &temp, 4);
+		break;
+	}
+}
+
+static ssize_t aspeed_smc_read_user(struct spi_nor *nor, loff_t from,
+				    size_t len, u_char *read_buf)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+	int i;
+	u8 dummy = 0xFF;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_send_cmd_addr(nor, nor->read_opcode, from);
+	for (i = 0; i < chip->nor.read_dummy / 8; i++)
+		aspeed_smc_write_to_ahb(chip->ahb_base, &dummy, sizeof(dummy));
+
+	aspeed_smc_read_from_ahb(read_buf, chip->ahb_base, len);
+	aspeed_smc_stop_user(nor);
+	return len;
+}
+
+static ssize_t aspeed_smc_write_user(struct spi_nor *nor, loff_t to,
+				     size_t len, const u_char *write_buf)
+{
+	struct aspeed_smc_chip *chip = nor->priv;
+
+	aspeed_smc_start_user(nor);
+	aspeed_smc_send_cmd_addr(nor, nor->program_opcode, to);
+	aspeed_smc_write_to_ahb(chip->ahb_base, write_buf, len);
+	aspeed_smc_stop_user(nor);
+	return len;
+}
+
+static int aspeed_smc_unregister(struct aspeed_smc_controller *controller)
+{
+	struct aspeed_smc_chip *chip;
+	int n;
+
+	for (n = 0; n < controller->info->nce; n++) {
+		chip = controller->chips[n];
+		if (chip)
+			mtd_device_unregister(&chip->nor.mtd);
+	}
+
+	return 0;
+}
+
+static int aspeed_smc_remove(struct platform_device *dev)
+{
+	return aspeed_smc_unregister(platform_get_drvdata(dev));
+}
+
+static const struct of_device_id aspeed_smc_matches[] = {
+	{ .compatible = "aspeed,ast2400-fmc", .data = &fmc_2400_info },
+	{ .compatible = "aspeed,ast2400-spi", .data = &spi_2400_info },
+	{ .compatible = "aspeed,ast2500-fmc", .data = &fmc_2500_info },
+	{ .compatible = "aspeed,ast2500-spi", .data = &spi_2500_info },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, aspeed_smc_matches);
+
+/*
+ * Each chip has a mapping window defined by a segment address
+ * register defining a start and an end address on the AHB bus. These
+ * addresses can be configured to fit the chip size and offer a
+ * contiguous memory region across chips. For the moment, we only
+ * check that each chip segment is valid.
+ */
+static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip,
+					  struct resource *res)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 offset = 0;
+	u32 reg;
+
+	if (controller->info->nce > 1) {
+		reg = readl(controller->regs + SEGMENT_ADDR_REG0 +
+			    chip->cs * 4);
+
+		if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg))
+			return NULL;
+
+		offset = SEGMENT_ADDR_START(reg) - res->start;
+	}
+
+	return controller->ahb_base + offset;
+}
+
+static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	reg = readl(controller->regs + CONFIG_REG);
+
+	reg |= aspeed_smc_chip_write_bit(chip);
+	writel(reg, controller->regs + CONFIG_REG);
+}
+
+static void aspeed_smc_chip_set_type(struct aspeed_smc_chip *chip, int type)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	chip->type = type;
+
+	reg = readl(controller->regs + CONFIG_REG);
+	reg &= ~(3 << (chip->cs * 2));
+	reg |= chip->type << (chip->cs * 2);
+	writel(reg, controller->regs + CONFIG_REG);
+}
+
+/*
+ * The AST2500 FMC flash controller should be strapped by hardware, or
+ * autodetected, but the AST2500 SPI flash needs to be set.
+ */
+static void aspeed_smc_chip_set_4b(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 reg;
+
+	if (chip->controller->info == &spi_2500_info) {
+		reg = readl(controller->regs + CE_CONTROL_REG);
+		reg |= 1 << chip->cs;
+		writel(reg, controller->regs + CE_CONTROL_REG);
+	}
+}
+
+/*
+ * The AST2400 SPI flash controller does not have a CE Control
+ * register. It uses the CE0 control register to set 4Byte mode at the
+ * controller level.
+ */
+static void aspeed_smc_chip_set_4b_spi_2400(struct aspeed_smc_chip *chip)
+{
+	chip->ctl_val[smc_base] |= CONTROL_IO_ADDRESS_4B;
+	chip->ctl_val[smc_read] |= CONTROL_IO_ADDRESS_4B;
+}
+
+static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip,
+				      struct resource *res)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	const struct aspeed_smc_info *info = controller->info;
+	u32 reg, base_reg;
+
+	/*
+	 * Always turn on the write enable bit to allow opcodes to be
+	 * sent in user mode.
+	 */
+	aspeed_smc_chip_enable_write(chip);
+
+	/* The driver only supports SPI type flash */
+	if (info->hastype)
+		aspeed_smc_chip_set_type(chip, smc_type_spi);
+
+	/*
+	 * Configure chip base address in memory
+	 */
+	chip->ahb_base = aspeed_smc_chip_base(chip, res);
+	if (!chip->ahb_base) {
+		dev_warn(chip->nor.dev, "CE segment window closed.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Get value of the inherited control register. U-Boot usually
+	 * does some timing calibration on the FMC chip, so it's good
+	 * to keep them. In the future, we should handle calibration
+	 * from Linux.
+	 */
+	reg = readl(chip->ctl);
+	dev_dbg(controller->dev, "control register: %08x\n", reg);
+
+	base_reg = reg & CONTROL_KEEP_MASK;
+	if (base_reg != reg) {
+		dev_dbg(controller->dev,
+			"control register changed to: %08x\n",
+			base_reg);
+	}
+	chip->ctl_val[smc_base] = base_reg;
+
+	/*
+	 * Retain the prior value of the control register as the
+	 * default if it was normal access mode. Otherwise start with
+	 * the sanitized base value set to read mode.
+	 */
+	if ((reg & CONTROL_COMMAND_MODE_MASK) ==
+	    CONTROL_COMMAND_MODE_NORMAL)
+		chip->ctl_val[smc_read] = reg;
+	else
+		chip->ctl_val[smc_read] = chip->ctl_val[smc_base] |
+			CONTROL_COMMAND_MODE_NORMAL;
+
+	dev_dbg(controller->dev, "default control register: %08x\n",
+		chip->ctl_val[smc_read]);
+	return 0;
+}
+
+static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	const struct aspeed_smc_info *info = controller->info;
+	u32 cmd;
+
+	if (chip->nor.addr_width == 4 && info->set_4b)
+		info->set_4b(chip);
+
+	/*
+	 * base mode has not been optimized yet. use it for writes.
+	 */
+	chip->ctl_val[smc_write] = chip->ctl_val[smc_base] |
+		chip->nor.program_opcode << CONTROL_COMMAND_SHIFT |
+		CONTROL_COMMAND_MODE_WRITE;
+
+	dev_dbg(controller->dev, "write control register: %08x\n",
+		chip->ctl_val[smc_write]);
+
+	/*
+	 * TODO: Adjust clocks if fast read is supported and interpret
+	 * SPI-NOR flags to adjust controller settings.
+	 */
+	switch (chip->nor.flash_read) {
+	case SPI_NOR_NORMAL:
+		cmd = CONTROL_COMMAND_MODE_NORMAL;
+		break;
+	case SPI_NOR_FAST:
+		cmd = CONTROL_COMMAND_MODE_FREAD;
+		break;
+	default:
+		dev_err(chip->nor.dev, "unsupported SPI read mode\n");
+		return -EINVAL;
+	}
+
+	chip->ctl_val[smc_read] |= cmd |
+		CONTROL_IO_DUMMY_SET(chip->nor.read_dummy / 8);
+
+	dev_dbg(controller->dev, "base control register: %08x\n",
+		chip->ctl_val[smc_read]);
+	return 0;
+}
+
+static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
+				  struct device_node *np, struct resource *r)
+{
+	const struct aspeed_smc_info *info = controller->info;
+	struct device *dev = controller->dev;
+	struct device_node *child;
+	unsigned int cs;
+	int ret = -ENODEV;
+
+	for_each_available_child_of_node(np, child) {
+		struct aspeed_smc_chip *chip;
+		struct spi_nor *nor;
+		struct mtd_info *mtd;
+
+		/* This driver does not support NAND or NOR flash devices. */
+		if (!of_device_is_compatible(child, "jedec,spi-nor"))
+			continue;
+
+		ret = of_property_read_u32(child, "reg", &cs);
+		if (ret) {
+			dev_err(dev, "Couldn't not read chip select.\n");
+			break;
+		}
+
+		if (cs >= info->nce) {
+			dev_err(dev, "Chip select %d out of range.\n",
+				cs);
+			ret = -ERANGE;
+			break;
+		}
+
+		if (controller->chips[cs]) {
+			dev_err(dev, "Chip select %d already in use by %s\n",
+				cs, dev_name(controller->chips[cs]->nor.dev));
+			ret = -EBUSY;
+			break;
+		}
+
+		chip = devm_kzalloc(controller->dev, sizeof(*chip), GFP_KERNEL);
+		if (!chip) {
+			ret = -ENOMEM;
+			break;
+		}
+
+		chip->controller = controller;
+		chip->ctl = controller->regs + info->ctl0 + cs * 4;
+		chip->cs = cs;
+
+		nor = &chip->nor;
+		mtd = &nor->mtd;
+
+		nor->dev = dev;
+		nor->priv = chip;
+		spi_nor_set_flash_node(nor, child);
+		nor->read = aspeed_smc_read_user;
+		nor->write = aspeed_smc_write_user;
+		nor->read_reg = aspeed_smc_read_reg;
+		nor->write_reg = aspeed_smc_write_reg;
+		nor->prepare = aspeed_smc_prep;
+		nor->unprepare = aspeed_smc_unprep;
+
+		ret = aspeed_smc_chip_setup_init(chip, r);
+		if (ret)
+			break;
+
+		/*
+		 * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL
+		 * attach when board support is present as determined
+		 * by of property.
+		 */
+		ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL);
+		if (ret)
+			break;
+
+		ret = aspeed_smc_chip_setup_finish(chip);
+		if (ret)
+			break;
+
+		ret = mtd_device_register(mtd, NULL, 0);
+		if (ret)
+			break;
+
+		controller->chips[cs] = chip;
+	}
+
+	if (ret)
+		aspeed_smc_unregister(controller);
+
+	return ret;
+}
+
+static int aspeed_smc_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct device *dev = &pdev->dev;
+	struct aspeed_smc_controller *controller;
+	const struct of_device_id *match;
+	const struct aspeed_smc_info *info;
+	struct resource *res;
+	int ret;
+
+	match = of_match_device(aspeed_smc_matches, &pdev->dev);
+	if (!match || !match->data)
+		return -ENODEV;
+	info = match->data;
+
+	controller = devm_kzalloc(&pdev->dev, sizeof(*controller) +
+		info->nce * sizeof(controller->chips[0]), GFP_KERNEL);
+	if (!controller)
+		return -ENOMEM;
+	controller->info = info;
+	controller->dev = dev;
+
+	mutex_init(&controller->mutex);
+	platform_set_drvdata(pdev, controller);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	controller->regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(controller->regs)) {
+		dev_err(dev, "Cannot remap controller address.\n");
+		return PTR_ERR(controller->regs);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	controller->ahb_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(controller->ahb_base)) {
+		dev_err(dev, "Cannot remap controller address.\n");
+		return PTR_ERR(controller->ahb_base);
+	}
+
+	ret = aspeed_smc_setup_flash(controller, np, res);
+	if (ret)
+		dev_err(dev, "Aspeed SMC probe failed %d\n", ret);
+
+	return ret;
+}
+
+static struct platform_driver aspeed_smc_driver = {
+	.probe = aspeed_smc_probe,
+	.remove = aspeed_smc_remove,
+	.driver = {
+		.name = DEVICE_NAME,
+		.of_match_table = aspeed_smc_matches,
+	}
+};
+
+module_platform_driver(aspeed_smc_driver);
+
+MODULE_DESCRIPTION("ASPEED Static Memory Controller Driver");
+MODULE_AUTHOR("Cedric Le Goater <clg@kaod.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index d489fbd07c12..9f8102de1b16 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -526,7 +526,8 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor,
 			bytes_to_read *= cqspi->fifo_width;
 			bytes_to_read = bytes_to_read > remaining ?
 					remaining : bytes_to_read;
-			readsl(ahb_base, rxbuf, DIV_ROUND_UP(bytes_to_read, 4));
+			ioread32_rep(ahb_base, rxbuf,
+				     DIV_ROUND_UP(bytes_to_read, 4));
 			rxbuf += bytes_to_read;
 			remaining -= bytes_to_read;
 			bytes_to_read = cqspi_get_rd_sram_level(cqspi);
@@ -610,7 +611,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor,
 
 	while (remaining > 0) {
 		write_bytes = remaining > page_size ? page_size : remaining;
-		writesl(cqspi->ahb_base, txbuf, DIV_ROUND_UP(write_bytes, 4));
+		iowrite32_rep(cqspi->ahb_base, txbuf,
+			      DIV_ROUND_UP(write_bytes, 4));
 
 		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
 						  msecs_to_jiffies
@@ -891,7 +893,7 @@ static ssize_t cqspi_write(struct spi_nor *nor, loff_t to,
 	if (ret)
 		return ret;
 
-	return (ret < 0) ? ret : len;
+	return len;
 }
 
 static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
@@ -911,7 +913,7 @@ static ssize_t cqspi_read(struct spi_nor *nor, loff_t from,
 	if (ret)
 		return ret;
 
-	return (ret < 0) ? ret : len;
+	return len;
 }
 
 static int cqspi_erase(struct spi_nor *nor, loff_t offs)
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index b4d8953fb30a..1476135e0d50 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -193,7 +193,7 @@
 #define QUADSPI_LUT_NUM		64
 
 /* SEQID -- we can have 16 seqids at most. */
-#define SEQID_QUAD_READ		0
+#define SEQID_READ		0
 #define SEQID_WREN		1
 #define SEQID_WRDI		2
 #define SEQID_RDSR		3
@@ -373,32 +373,26 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	void __iomem *base = q->iobase;
 	int rxfifo = q->devtype_data->rxfifo;
 	u32 lut_base;
-	u8 cmd, addrlen, dummy;
 	int i;
 
+	struct spi_nor *nor = &q->nor[0];
+	u8 addrlen = (nor->addr_width == 3) ? ADDR24BIT : ADDR32BIT;
+	u8 read_op = nor->read_opcode;
+	u8 read_dm = nor->read_dummy;
+
 	fsl_qspi_unlock_lut(q);
 
 	/* Clear all the LUT table */
 	for (i = 0; i < QUADSPI_LUT_NUM; i++)
 		qspi_writel(q, 0, base + QUADSPI_LUT_BASE + i * 4);
 
-	/* Quad Read */
-	lut_base = SEQID_QUAD_READ * 4;
-
-	if (q->nor_size <= SZ_16M) {
-		cmd = SPINOR_OP_READ_1_1_4;
-		addrlen = ADDR24BIT;
-		dummy = 8;
-	} else {
-		/* use the 4-byte address */
-		cmd = SPINOR_OP_READ_1_1_4;
-		addrlen = ADDR32BIT;
-		dummy = 8;
-	}
+	/* Read */
+	lut_base = SEQID_READ * 4;
 
-	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, read_op) | LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
-	qspi_writel(q, LUT0(DUMMY, PAD1, dummy) | LUT1(FSL_READ, PAD4, rxfifo),
+	qspi_writel(q, LUT0(DUMMY, PAD1, read_dm) |
+		    LUT1(FSL_READ, PAD4, rxfifo),
 			base + QUADSPI_LUT(lut_base + 1));
 
 	/* Write enable */
@@ -409,16 +403,8 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	/* Page Program */
 	lut_base = SEQID_PP * 4;
 
-	if (q->nor_size <= SZ_16M) {
-		cmd = SPINOR_OP_PP;
-		addrlen = ADDR24BIT;
-	} else {
-		/* use the 4-byte address */
-		cmd = SPINOR_OP_PP;
-		addrlen = ADDR32BIT;
-	}
-
-	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, nor->program_opcode) |
+		    LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
 	qspi_writel(q, LUT0(FSL_WRITE, PAD1, 0),
 			base + QUADSPI_LUT(lut_base + 1));
@@ -432,10 +418,8 @@ static void fsl_qspi_init_lut(struct fsl_qspi *q)
 	/* Erase a sector */
 	lut_base = SEQID_SE * 4;
 
-	cmd = q->nor[0].erase_opcode;
-	addrlen = q->nor_size <= SZ_16M ? ADDR24BIT : ADDR32BIT;
-
-	qspi_writel(q, LUT0(CMD, PAD1, cmd) | LUT1(ADDR, PAD1, addrlen),
+	qspi_writel(q, LUT0(CMD, PAD1, nor->erase_opcode) |
+		    LUT1(ADDR, PAD1, addrlen),
 			base + QUADSPI_LUT(lut_base));
 
 	/* Erase the whole chip */
@@ -484,7 +468,7 @@ static int fsl_qspi_get_seqid(struct fsl_qspi *q, u8 cmd)
 {
 	switch (cmd) {
 	case SPINOR_OP_READ_1_1_4:
-		return SEQID_QUAD_READ;
+		return SEQID_READ;
 	case SPINOR_OP_WREN:
 		return SEQID_WREN;
 	case SPINOR_OP_WRDI:
diff --git a/drivers/mtd/spi-nor/intel-spi-platform.c b/drivers/mtd/spi-nor/intel-spi-platform.c
new file mode 100644
index 000000000000..5c943df9398f
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi-platform.c
@@ -0,0 +1,57 @@
+/*
+ * Intel PCH/PCU SPI flash platform driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+#include "intel-spi.h"
+
+static int intel_spi_platform_probe(struct platform_device *pdev)
+{
+	struct intel_spi_boardinfo *info;
+	struct intel_spi *ispi;
+	struct resource *mem;
+
+	info = dev_get_platdata(&pdev->dev);
+	if (!info)
+		return -EINVAL;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ispi = intel_spi_probe(&pdev->dev, mem, info);
+	if (IS_ERR(ispi))
+		return PTR_ERR(ispi);
+
+	platform_set_drvdata(pdev, ispi);
+	return 0;
+}
+
+static int intel_spi_platform_remove(struct platform_device *pdev)
+{
+	struct intel_spi *ispi = platform_get_drvdata(pdev);
+
+	return intel_spi_remove(ispi);
+}
+
+static struct platform_driver intel_spi_platform_driver = {
+	.probe = intel_spi_platform_probe,
+	.remove = intel_spi_platform_remove,
+	.driver = {
+		.name = "intel-spi",
+	},
+};
+
+module_platform_driver(intel_spi_platform_driver);
+
+MODULE_DESCRIPTION("Intel PCH/PCU SPI flash platform driver");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:intel-spi");
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
new file mode 100644
index 000000000000..a10f6027b386
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -0,0 +1,777 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/spi-nor.h>
+#include <linux/platform_data/intel-spi.h>
+
+#include "intel-spi.h"
+
+/* Offsets are from @ispi->base */
+#define BFPREG				0x00
+
+#define HSFSTS_CTL			0x04
+#define HSFSTS_CTL_FSMIE		BIT(31)
+#define HSFSTS_CTL_FDBC_SHIFT		24
+#define HSFSTS_CTL_FDBC_MASK		(0x3f << HSFSTS_CTL_FDBC_SHIFT)
+
+#define HSFSTS_CTL_FCYCLE_SHIFT		17
+#define HSFSTS_CTL_FCYCLE_MASK		(0x0f << HSFSTS_CTL_FCYCLE_SHIFT)
+/* HW sequencer opcodes */
+#define HSFSTS_CTL_FCYCLE_READ		(0x00 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_WRITE		(0x02 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_ERASE		(0x03 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_ERASE_64K	(0x04 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_RDID		(0x06 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_WRSR		(0x07 << HSFSTS_CTL_FCYCLE_SHIFT)
+#define HSFSTS_CTL_FCYCLE_RDSR		(0x08 << HSFSTS_CTL_FCYCLE_SHIFT)
+
+#define HSFSTS_CTL_FGO			BIT(16)
+#define HSFSTS_CTL_FLOCKDN		BIT(15)
+#define HSFSTS_CTL_FDV			BIT(14)
+#define HSFSTS_CTL_SCIP			BIT(5)
+#define HSFSTS_CTL_AEL			BIT(2)
+#define HSFSTS_CTL_FCERR		BIT(1)
+#define HSFSTS_CTL_FDONE		BIT(0)
+
+#define FADDR				0x08
+#define DLOCK				0x0c
+#define FDATA(n)			(0x10 + ((n) * 4))
+
+#define FRACC				0x50
+
+#define FREG(n)				(0x54 + ((n) * 4))
+#define FREG_BASE_MASK			0x3fff
+#define FREG_LIMIT_SHIFT		16
+#define FREG_LIMIT_MASK			(0x03fff << FREG_LIMIT_SHIFT)
+
+/* Offset is from @ispi->pregs */
+#define PR(n)				((n) * 4)
+#define PR_WPE				BIT(31)
+#define PR_LIMIT_SHIFT			16
+#define PR_LIMIT_MASK			(0x3fff << PR_LIMIT_SHIFT)
+#define PR_RPE				BIT(15)
+#define PR_BASE_MASK			0x3fff
+/* Last PR is GPR0 */
+#define PR_NUM				(5 + 1)
+
+/* Offsets are from @ispi->sregs */
+#define SSFSTS_CTL			0x00
+#define SSFSTS_CTL_FSMIE		BIT(23)
+#define SSFSTS_CTL_DS			BIT(22)
+#define SSFSTS_CTL_DBC_SHIFT		16
+#define SSFSTS_CTL_SPOP			BIT(11)
+#define SSFSTS_CTL_ACS			BIT(10)
+#define SSFSTS_CTL_SCGO			BIT(9)
+#define SSFSTS_CTL_COP_SHIFT		12
+#define SSFSTS_CTL_FRS			BIT(7)
+#define SSFSTS_CTL_DOFRS		BIT(6)
+#define SSFSTS_CTL_AEL			BIT(4)
+#define SSFSTS_CTL_FCERR		BIT(3)
+#define SSFSTS_CTL_FDONE		BIT(2)
+#define SSFSTS_CTL_SCIP			BIT(0)
+
+#define PREOP_OPTYPE			0x04
+#define OPMENU0				0x08
+#define OPMENU1				0x0c
+
+/* CPU specifics */
+#define BYT_PR				0x74
+#define BYT_SSFSTS_CTL			0x90
+#define BYT_BCR				0xfc
+#define BYT_BCR_WPD			BIT(0)
+#define BYT_FREG_NUM			5
+
+#define LPT_PR				0x74
+#define LPT_SSFSTS_CTL			0x90
+#define LPT_FREG_NUM			5
+
+#define BXT_PR				0x84
+#define BXT_SSFSTS_CTL			0xa0
+#define BXT_FREG_NUM			12
+
+#define INTEL_SPI_TIMEOUT		5000 /* ms */
+#define INTEL_SPI_FIFO_SZ		64
+
+/**
+ * struct intel_spi - Driver private data
+ * @dev: Device pointer
+ * @info: Pointer to board specific info
+ * @nor: SPI NOR layer structure
+ * @base: Beginning of MMIO space
+ * @pregs: Start of protection registers
+ * @sregs: Start of software sequencer registers
+ * @nregions: Maximum number of regions
+ * @writeable: Is the chip writeable
+ * @swseq: Use SW sequencer in register reads/writes
+ * @erase_64k: 64k erase supported
+ * @opcodes: Opcodes which are supported. This are programmed by BIOS
+ *           before it locks down the controller.
+ * @preopcodes: Preopcodes which are supported.
+ */
+struct intel_spi {
+	struct device *dev;
+	const struct intel_spi_boardinfo *info;
+	struct spi_nor nor;
+	void __iomem *base;
+	void __iomem *pregs;
+	void __iomem *sregs;
+	size_t nregions;
+	bool writeable;
+	bool swseq;
+	bool erase_64k;
+	u8 opcodes[8];
+	u8 preopcodes[2];
+};
+
+static bool writeable;
+module_param(writeable, bool, 0);
+MODULE_PARM_DESC(writeable, "Enable write access to SPI flash chip (default=0)");
+
+static void intel_spi_dump_regs(struct intel_spi *ispi)
+{
+	u32 value;
+	int i;
+
+	dev_dbg(ispi->dev, "BFPREG=0x%08x\n", readl(ispi->base + BFPREG));
+
+	value = readl(ispi->base + HSFSTS_CTL);
+	dev_dbg(ispi->dev, "HSFSTS_CTL=0x%08x\n", value);
+	if (value & HSFSTS_CTL_FLOCKDN)
+		dev_dbg(ispi->dev, "-> Locked\n");
+
+	dev_dbg(ispi->dev, "FADDR=0x%08x\n", readl(ispi->base + FADDR));
+	dev_dbg(ispi->dev, "DLOCK=0x%08x\n", readl(ispi->base + DLOCK));
+
+	for (i = 0; i < 16; i++)
+		dev_dbg(ispi->dev, "FDATA(%d)=0x%08x\n",
+			i, readl(ispi->base + FDATA(i)));
+
+	dev_dbg(ispi->dev, "FRACC=0x%08x\n", readl(ispi->base + FRACC));
+
+	for (i = 0; i < ispi->nregions; i++)
+		dev_dbg(ispi->dev, "FREG(%d)=0x%08x\n", i,
+			readl(ispi->base + FREG(i)));
+	for (i = 0; i < PR_NUM; i++)
+		dev_dbg(ispi->dev, "PR(%d)=0x%08x\n", i,
+			readl(ispi->pregs + PR(i)));
+
+	value = readl(ispi->sregs + SSFSTS_CTL);
+	dev_dbg(ispi->dev, "SSFSTS_CTL=0x%08x\n", value);
+	dev_dbg(ispi->dev, "PREOP_OPTYPE=0x%08x\n",
+		readl(ispi->sregs + PREOP_OPTYPE));
+	dev_dbg(ispi->dev, "OPMENU0=0x%08x\n", readl(ispi->sregs + OPMENU0));
+	dev_dbg(ispi->dev, "OPMENU1=0x%08x\n", readl(ispi->sregs + OPMENU1));
+
+	if (ispi->info->type == INTEL_SPI_BYT)
+		dev_dbg(ispi->dev, "BCR=0x%08x\n", readl(ispi->base + BYT_BCR));
+
+	dev_dbg(ispi->dev, "Protected regions:\n");
+	for (i = 0; i < PR_NUM; i++) {
+		u32 base, limit;
+
+		value = readl(ispi->pregs + PR(i));
+		if (!(value & (PR_WPE | PR_RPE)))
+			continue;
+
+		limit = (value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT;
+		base = value & PR_BASE_MASK;
+
+		dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x [%c%c]\n",
+			 i, base << 12, (limit << 12) | 0xfff,
+			 value & PR_WPE ? 'W' : '.',
+			 value & PR_RPE ? 'R' : '.');
+	}
+
+	dev_dbg(ispi->dev, "Flash regions:\n");
+	for (i = 0; i < ispi->nregions; i++) {
+		u32 region, base, limit;
+
+		region = readl(ispi->base + FREG(i));
+		base = region & FREG_BASE_MASK;
+		limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT;
+
+		if (base >= limit || (i > 0 && limit == 0))
+			dev_dbg(ispi->dev, " %02d disabled\n", i);
+		else
+			dev_dbg(ispi->dev, " %02d base: 0x%08x limit: 0x%08x\n",
+				 i, base << 12, (limit << 12) | 0xfff);
+	}
+
+	dev_dbg(ispi->dev, "Using %cW sequencer for register access\n",
+		ispi->swseq ? 'S' : 'H');
+}
+
+/* Reads max INTEL_SPI_FIFO_SZ bytes from the device fifo */
+static int intel_spi_read_block(struct intel_spi *ispi, void *buf, size_t size)
+{
+	size_t bytes;
+	int i = 0;
+
+	if (size > INTEL_SPI_FIFO_SZ)
+		return -EINVAL;
+
+	while (size > 0) {
+		bytes = min_t(size_t, size, 4);
+		memcpy_fromio(buf, ispi->base + FDATA(i), bytes);
+		size -= bytes;
+		buf += bytes;
+		i++;
+	}
+
+	return 0;
+}
+
+/* Writes max INTEL_SPI_FIFO_SZ bytes to the device fifo */
+static int intel_spi_write_block(struct intel_spi *ispi, const void *buf,
+				 size_t size)
+{
+	size_t bytes;
+	int i = 0;
+
+	if (size > INTEL_SPI_FIFO_SZ)
+		return -EINVAL;
+
+	while (size > 0) {
+		bytes = min_t(size_t, size, 4);
+		memcpy_toio(ispi->base + FDATA(i), buf, bytes);
+		size -= bytes;
+		buf += bytes;
+		i++;
+	}
+
+	return 0;
+}
+
+static int intel_spi_wait_hw_busy(struct intel_spi *ispi)
+{
+	u32 val;
+
+	return readl_poll_timeout(ispi->base + HSFSTS_CTL, val,
+				  !(val & HSFSTS_CTL_SCIP), 0,
+				  INTEL_SPI_TIMEOUT * 1000);
+}
+
+static int intel_spi_wait_sw_busy(struct intel_spi *ispi)
+{
+	u32 val;
+
+	return readl_poll_timeout(ispi->sregs + SSFSTS_CTL, val,
+				  !(val & SSFSTS_CTL_SCIP), 0,
+				  INTEL_SPI_TIMEOUT * 1000);
+}
+
+static int intel_spi_init(struct intel_spi *ispi)
+{
+	u32 opmenu0, opmenu1, val;
+	int i;
+
+	switch (ispi->info->type) {
+	case INTEL_SPI_BYT:
+		ispi->sregs = ispi->base + BYT_SSFSTS_CTL;
+		ispi->pregs = ispi->base + BYT_PR;
+		ispi->nregions = BYT_FREG_NUM;
+
+		if (writeable) {
+			/* Disable write protection */
+			val = readl(ispi->base + BYT_BCR);
+			if (!(val & BYT_BCR_WPD)) {
+				val |= BYT_BCR_WPD;
+				writel(val, ispi->base + BYT_BCR);
+				val = readl(ispi->base + BYT_BCR);
+			}
+
+			ispi->writeable = !!(val & BYT_BCR_WPD);
+		}
+
+		break;
+
+	case INTEL_SPI_LPT:
+		ispi->sregs = ispi->base + LPT_SSFSTS_CTL;
+		ispi->pregs = ispi->base + LPT_PR;
+		ispi->nregions = LPT_FREG_NUM;
+		break;
+
+	case INTEL_SPI_BXT:
+		ispi->sregs = ispi->base + BXT_SSFSTS_CTL;
+		ispi->pregs = ispi->base + BXT_PR;
+		ispi->nregions = BXT_FREG_NUM;
+		ispi->erase_64k = true;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	/* Disable #SMI generation */
+	val = readl(ispi->base + HSFSTS_CTL);
+	val &= ~HSFSTS_CTL_FSMIE;
+	writel(val, ispi->base + HSFSTS_CTL);
+
+	/*
+	 * BIOS programs allowed opcodes and then locks down the register.
+	 * So read back what opcodes it decided to support. That's the set
+	 * we are going to support as well.
+	 */
+	opmenu0 = readl(ispi->sregs + OPMENU0);
+	opmenu1 = readl(ispi->sregs + OPMENU1);
+
+	/*
+	 * Some controllers can only do basic operations using hardware
+	 * sequencer. All other operations are supposed to be carried out
+	 * using software sequencer. If we find that BIOS has programmed
+	 * opcodes for the software sequencer we use that over the hardware
+	 * sequencer.
+	 */
+	if (opmenu0 && opmenu1) {
+		for (i = 0; i < ARRAY_SIZE(ispi->opcodes) / 2; i++) {
+			ispi->opcodes[i] = opmenu0 >> i * 8;
+			ispi->opcodes[i + 4] = opmenu1 >> i * 8;
+		}
+
+		val = readl(ispi->sregs + PREOP_OPTYPE);
+		ispi->preopcodes[0] = val;
+		ispi->preopcodes[1] = val >> 8;
+
+		/* Disable #SMI generation from SW sequencer */
+		val = readl(ispi->sregs + SSFSTS_CTL);
+		val &= ~SSFSTS_CTL_FSMIE;
+		writel(val, ispi->sregs + SSFSTS_CTL);
+
+		ispi->swseq = true;
+	}
+
+	intel_spi_dump_regs(ispi);
+
+	return 0;
+}
+
+static int intel_spi_opcode_index(struct intel_spi *ispi, u8 opcode)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ispi->opcodes); i++)
+		if (ispi->opcodes[i] == opcode)
+			return i;
+	return -EINVAL;
+}
+
+static int intel_spi_hw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
+			      int len)
+{
+	u32 val, status;
+	int ret;
+
+	val = readl(ispi->base + HSFSTS_CTL);
+	val &= ~(HSFSTS_CTL_FCYCLE_MASK | HSFSTS_CTL_FDBC_MASK);
+
+	switch (opcode) {
+	case SPINOR_OP_RDID:
+		val |= HSFSTS_CTL_FCYCLE_RDID;
+		break;
+	case SPINOR_OP_WRSR:
+		val |= HSFSTS_CTL_FCYCLE_WRSR;
+		break;
+	case SPINOR_OP_RDSR:
+		val |= HSFSTS_CTL_FCYCLE_RDSR;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	val |= (len - 1) << HSFSTS_CTL_FDBC_SHIFT;
+	val |= HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+	val |= HSFSTS_CTL_FGO;
+	writel(val, ispi->base + HSFSTS_CTL);
+
+	ret = intel_spi_wait_hw_busy(ispi);
+	if (ret)
+		return ret;
+
+	status = readl(ispi->base + HSFSTS_CTL);
+	if (status & HSFSTS_CTL_FCERR)
+		return -EIO;
+	else if (status & HSFSTS_CTL_AEL)
+		return -EACCES;
+
+	return 0;
+}
+
+static int intel_spi_sw_cycle(struct intel_spi *ispi, u8 opcode, u8 *buf,
+			      int len)
+{
+	u32 val, status;
+	int ret;
+
+	ret = intel_spi_opcode_index(ispi, opcode);
+	if (ret < 0)
+		return ret;
+
+	val = (len << SSFSTS_CTL_DBC_SHIFT) | SSFSTS_CTL_DS;
+	val |= ret << SSFSTS_CTL_COP_SHIFT;
+	val |= SSFSTS_CTL_FCERR | SSFSTS_CTL_FDONE;
+	val |= SSFSTS_CTL_SCGO;
+	writel(val, ispi->sregs + SSFSTS_CTL);
+
+	ret = intel_spi_wait_sw_busy(ispi);
+	if (ret)
+		return ret;
+
+	status = readl(ispi->base + SSFSTS_CTL);
+	if (status & SSFSTS_CTL_FCERR)
+		return -EIO;
+	else if (status & SSFSTS_CTL_AEL)
+		return -EACCES;
+
+	return 0;
+}
+
+static int intel_spi_read_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	struct intel_spi *ispi = nor->priv;
+	int ret;
+
+	/* Address of the first chip */
+	writel(0, ispi->base + FADDR);
+
+	if (ispi->swseq)
+		ret = intel_spi_sw_cycle(ispi, opcode, buf, len);
+	else
+		ret = intel_spi_hw_cycle(ispi, opcode, buf, len);
+
+	if (ret)
+		return ret;
+
+	return intel_spi_read_block(ispi, buf, len);
+}
+
+static int intel_spi_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf, int len)
+{
+	struct intel_spi *ispi = nor->priv;
+	int ret;
+
+	/*
+	 * This is handled with atomic operation and preop code in Intel
+	 * controller so skip it here now.
+	 */
+	if (opcode == SPINOR_OP_WREN)
+		return 0;
+
+	writel(0, ispi->base + FADDR);
+
+	/* Write the value beforehand */
+	ret = intel_spi_write_block(ispi, buf, len);
+	if (ret)
+		return ret;
+
+	if (ispi->swseq)
+		return intel_spi_sw_cycle(ispi, opcode, buf, len);
+	return intel_spi_hw_cycle(ispi, opcode, buf, len);
+}
+
+static ssize_t intel_spi_read(struct spi_nor *nor, loff_t from, size_t len,
+			      u_char *read_buf)
+{
+	struct intel_spi *ispi = nor->priv;
+	size_t block_size, retlen = 0;
+	u32 val, status;
+	ssize_t ret;
+
+	switch (nor->read_opcode) {
+	case SPINOR_OP_READ:
+	case SPINOR_OP_READ_FAST:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	while (len > 0) {
+		block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+
+		writel(from, ispi->base + FADDR);
+
+		val = readl(ispi->base + HSFSTS_CTL);
+		val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+		val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+		val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
+		val |= HSFSTS_CTL_FCYCLE_READ;
+		val |= HSFSTS_CTL_FGO;
+		writel(val, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_wait_hw_busy(ispi);
+		if (ret)
+			return ret;
+
+		status = readl(ispi->base + HSFSTS_CTL);
+		if (status & HSFSTS_CTL_FCERR)
+			ret = -EIO;
+		else if (status & HSFSTS_CTL_AEL)
+			ret = -EACCES;
+
+		if (ret < 0) {
+			dev_err(ispi->dev, "read error: %llx: %#x\n", from,
+				status);
+			return ret;
+		}
+
+		ret = intel_spi_read_block(ispi, read_buf, block_size);
+		if (ret)
+			return ret;
+
+		len -= block_size;
+		from += block_size;
+		retlen += block_size;
+		read_buf += block_size;
+	}
+
+	return retlen;
+}
+
+static ssize_t intel_spi_write(struct spi_nor *nor, loff_t to, size_t len,
+			       const u_char *write_buf)
+{
+	struct intel_spi *ispi = nor->priv;
+	size_t block_size, retlen = 0;
+	u32 val, status;
+	ssize_t ret;
+
+	while (len > 0) {
+		block_size = min_t(size_t, len, INTEL_SPI_FIFO_SZ);
+
+		writel(to, ispi->base + FADDR);
+
+		val = readl(ispi->base + HSFSTS_CTL);
+		val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+		val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+		val |= (block_size - 1) << HSFSTS_CTL_FDBC_SHIFT;
+		val |= HSFSTS_CTL_FCYCLE_WRITE;
+
+		/* Write enable */
+		if (ispi->preopcodes[1] == SPINOR_OP_WREN)
+			val |= SSFSTS_CTL_SPOP;
+		val |= SSFSTS_CTL_ACS;
+		writel(val, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_write_block(ispi, write_buf, block_size);
+		if (ret) {
+			dev_err(ispi->dev, "failed to write block\n");
+			return ret;
+		}
+
+		/* Start the write now */
+		val = readl(ispi->base + HSFSTS_CTL);
+		writel(val | HSFSTS_CTL_FGO, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_wait_hw_busy(ispi);
+		if (ret) {
+			dev_err(ispi->dev, "timeout\n");
+			return ret;
+		}
+
+		status = readl(ispi->base + HSFSTS_CTL);
+		if (status & HSFSTS_CTL_FCERR)
+			ret = -EIO;
+		else if (status & HSFSTS_CTL_AEL)
+			ret = -EACCES;
+
+		if (ret < 0) {
+			dev_err(ispi->dev, "write error: %llx: %#x\n", to,
+				status);
+			return ret;
+		}
+
+		len -= block_size;
+		to += block_size;
+		retlen += block_size;
+		write_buf += block_size;
+	}
+
+	return retlen;
+}
+
+static int intel_spi_erase(struct spi_nor *nor, loff_t offs)
+{
+	size_t erase_size, len = nor->mtd.erasesize;
+	struct intel_spi *ispi = nor->priv;
+	u32 val, status, cmd;
+	int ret;
+
+	/* If the hardware can do 64k erase use that when possible */
+	if (len >= SZ_64K && ispi->erase_64k) {
+		cmd = HSFSTS_CTL_FCYCLE_ERASE_64K;
+		erase_size = SZ_64K;
+	} else {
+		cmd = HSFSTS_CTL_FCYCLE_ERASE;
+		erase_size = SZ_4K;
+	}
+
+	while (len > 0) {
+		writel(offs, ispi->base + FADDR);
+
+		val = readl(ispi->base + HSFSTS_CTL);
+		val &= ~(HSFSTS_CTL_FDBC_MASK | HSFSTS_CTL_FCYCLE_MASK);
+		val |= HSFSTS_CTL_AEL | HSFSTS_CTL_FCERR | HSFSTS_CTL_FDONE;
+		val |= cmd;
+		val |= HSFSTS_CTL_FGO;
+		writel(val, ispi->base + HSFSTS_CTL);
+
+		ret = intel_spi_wait_hw_busy(ispi);
+		if (ret)
+			return ret;
+
+		status = readl(ispi->base + HSFSTS_CTL);
+		if (status & HSFSTS_CTL_FCERR)
+			return -EIO;
+		else if (status & HSFSTS_CTL_AEL)
+			return -EACCES;
+
+		offs += erase_size;
+		len -= erase_size;
+	}
+
+	return 0;
+}
+
+static bool intel_spi_is_protected(const struct intel_spi *ispi,
+				   unsigned int base, unsigned int limit)
+{
+	int i;
+
+	for (i = 0; i < PR_NUM; i++) {
+		u32 pr_base, pr_limit, pr_value;
+
+		pr_value = readl(ispi->pregs + PR(i));
+		if (!(pr_value & (PR_WPE | PR_RPE)))
+			continue;
+
+		pr_limit = (pr_value & PR_LIMIT_MASK) >> PR_LIMIT_SHIFT;
+		pr_base = pr_value & PR_BASE_MASK;
+
+		if (pr_base >= base && pr_limit <= limit)
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * There will be a single partition holding all enabled flash regions. We
+ * call this "BIOS".
+ */
+static void intel_spi_fill_partition(struct intel_spi *ispi,
+				     struct mtd_partition *part)
+{
+	u64 end;
+	int i;
+
+	memset(part, 0, sizeof(*part));
+
+	/* Start from the mandatory descriptor region */
+	part->size = 4096;
+	part->name = "BIOS";
+
+	/*
+	 * Now try to find where this partition ends based on the flash
+	 * region registers.
+	 */
+	for (i = 1; i < ispi->nregions; i++) {
+		u32 region, base, limit;
+
+		region = readl(ispi->base + FREG(i));
+		base = region & FREG_BASE_MASK;
+		limit = (region & FREG_LIMIT_MASK) >> FREG_LIMIT_SHIFT;
+
+		if (base >= limit || limit == 0)
+			continue;
+
+		/*
+		 * If any of the regions have protection bits set, make the
+		 * whole partition read-only to be on the safe side.
+		 */
+		if (intel_spi_is_protected(ispi, base, limit))
+			ispi->writeable = 0;
+
+		end = (limit << 12) + 4096;
+		if (end > part->size)
+			part->size = end;
+	}
+}
+
+struct intel_spi *intel_spi_probe(struct device *dev,
+	struct resource *mem, const struct intel_spi_boardinfo *info)
+{
+	struct mtd_partition part;
+	struct intel_spi *ispi;
+	int ret;
+
+	if (!info || !mem)
+		return ERR_PTR(-EINVAL);
+
+	ispi = devm_kzalloc(dev, sizeof(*ispi), GFP_KERNEL);
+	if (!ispi)
+		return ERR_PTR(-ENOMEM);
+
+	ispi->base = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(ispi->base))
+		return ispi->base;
+
+	ispi->dev = dev;
+	ispi->info = info;
+	ispi->writeable = info->writeable;
+
+	ret = intel_spi_init(ispi);
+	if (ret)
+		return ERR_PTR(ret);
+
+	ispi->nor.dev = ispi->dev;
+	ispi->nor.priv = ispi;
+	ispi->nor.read_reg = intel_spi_read_reg;
+	ispi->nor.write_reg = intel_spi_write_reg;
+	ispi->nor.read = intel_spi_read;
+	ispi->nor.write = intel_spi_write;
+	ispi->nor.erase = intel_spi_erase;
+
+	ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL);
+	if (ret) {
+		dev_info(dev, "failed to locate the chip\n");
+		return ERR_PTR(ret);
+	}
+
+	intel_spi_fill_partition(ispi, &part);
+
+	/* Prevent writes if not explicitly enabled */
+	if (!ispi->writeable || !writeable)
+		ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
+
+	ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return ispi;
+}
+EXPORT_SYMBOL_GPL(intel_spi_probe);
+
+int intel_spi_remove(struct intel_spi *ispi)
+{
+	return mtd_device_unregister(&ispi->nor.mtd);
+}
+EXPORT_SYMBOL_GPL(intel_spi_remove);
+
+MODULE_DESCRIPTION("Intel PCH/PCU SPI flash core driver");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/mtd/spi-nor/intel-spi.h b/drivers/mtd/spi-nor/intel-spi.h
new file mode 100644
index 000000000000..5ab7dc250050
--- /dev/null
+++ b/drivers/mtd/spi-nor/intel-spi.h
@@ -0,0 +1,24 @@
+/*
+ * Intel PCH/PCU SPI flash driver.
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef INTEL_SPI_H
+#define INTEL_SPI_H
+
+#include <linux/platform_data/intel-spi.h>
+
+struct intel_spi;
+struct resource;
+
+struct intel_spi *intel_spi_probe(struct device *dev,
+	struct resource *mem, const struct intel_spi_boardinfo *info);
+int intel_spi_remove(struct intel_spi *ispi);
+
+#endif /* INTEL_SPI_H */
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index f6bde5578459..1ae872bfc3ba 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -75,6 +75,16 @@ struct flash_info {
 					 * bit. Must be used with
 					 * SPI_NOR_HAS_LOCK.
 					 */
+#define	SPI_S3AN		BIT(10)	/*
+					 * Xilinx Spartan 3AN In-System Flash
+					 * (MFR cannot be used for probing
+					 * because it has the same value as
+					 * ATMEL flashes)
+					 */
+#define SPI_NOR_4B_OPCODES	BIT(11)	/*
+					 * Use dedicated 4byte address op codes
+					 * to support memory size above 128Mib.
+					 */
 };
 
 #define JEDEC_MFR(info)	((info)->id[0])
@@ -188,6 +198,78 @@ static inline struct spi_nor *mtd_to_spi_nor(struct mtd_info *mtd)
 	return mtd->priv;
 }
 
+
+static u8 spi_nor_convert_opcode(u8 opcode, const u8 table[][2], size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (table[i][0] == opcode)
+			return table[i][1];
+
+	/* No conversion found, keep input op code. */
+	return opcode;
+}
+
+static inline u8 spi_nor_convert_3to4_read(u8 opcode)
+{
+	static const u8 spi_nor_3to4_read[][2] = {
+		{ SPINOR_OP_READ,	SPINOR_OP_READ_4B },
+		{ SPINOR_OP_READ_FAST,	SPINOR_OP_READ_FAST_4B },
+		{ SPINOR_OP_READ_1_1_2,	SPINOR_OP_READ_1_1_2_4B },
+		{ SPINOR_OP_READ_1_2_2,	SPINOR_OP_READ_1_2_2_4B },
+		{ SPINOR_OP_READ_1_1_4,	SPINOR_OP_READ_1_1_4_4B },
+		{ SPINOR_OP_READ_1_4_4,	SPINOR_OP_READ_1_4_4_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
+				      ARRAY_SIZE(spi_nor_3to4_read));
+}
+
+static inline u8 spi_nor_convert_3to4_program(u8 opcode)
+{
+	static const u8 spi_nor_3to4_program[][2] = {
+		{ SPINOR_OP_PP,		SPINOR_OP_PP_4B },
+		{ SPINOR_OP_PP_1_1_4,	SPINOR_OP_PP_1_1_4_4B },
+		{ SPINOR_OP_PP_1_4_4,	SPINOR_OP_PP_1_4_4_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_program,
+				      ARRAY_SIZE(spi_nor_3to4_program));
+}
+
+static inline u8 spi_nor_convert_3to4_erase(u8 opcode)
+{
+	static const u8 spi_nor_3to4_erase[][2] = {
+		{ SPINOR_OP_BE_4K,	SPINOR_OP_BE_4K_4B },
+		{ SPINOR_OP_BE_32K,	SPINOR_OP_BE_32K_4B },
+		{ SPINOR_OP_SE,		SPINOR_OP_SE_4B },
+	};
+
+	return spi_nor_convert_opcode(opcode, spi_nor_3to4_erase,
+				      ARRAY_SIZE(spi_nor_3to4_erase));
+}
+
+static void spi_nor_set_4byte_opcodes(struct spi_nor *nor,
+				      const struct flash_info *info)
+{
+	/* Do some manufacturer fixups first */
+	switch (JEDEC_MFR(info)) {
+	case SNOR_MFR_SPANSION:
+		/* No small sector erase for 4-byte command set */
+		nor->erase_opcode = SPINOR_OP_SE;
+		nor->mtd.erasesize = info->sector_size;
+		break;
+
+	default:
+		break;
+	}
+
+	nor->read_opcode = spi_nor_convert_3to4_read(nor->read_opcode);
+	nor->program_opcode = spi_nor_convert_3to4_program(nor->program_opcode);
+	nor->erase_opcode = spi_nor_convert_3to4_erase(nor->erase_opcode);
+}
+
 /* Enable/disable 4-byte addressing mode. */
 static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info,
 			    int enable)
@@ -217,6 +299,21 @@ static inline int set_4byte(struct spi_nor *nor, const struct flash_info *info,
 		return nor->write_reg(nor, SPINOR_OP_BRWR, nor->cmd_buf, 1);
 	}
 }
+
+static int s3an_sr_ready(struct spi_nor *nor)
+{
+	int ret;
+	u8 val;
+
+	ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1);
+	if (ret < 0) {
+		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+		return ret;
+	}
+
+	return !!(val & XSR_RDY);
+}
+
 static inline int spi_nor_sr_ready(struct spi_nor *nor)
 {
 	int sr = read_sr(nor);
@@ -238,7 +335,11 @@ static inline int spi_nor_fsr_ready(struct spi_nor *nor)
 static int spi_nor_ready(struct spi_nor *nor)
 {
 	int sr, fsr;
-	sr = spi_nor_sr_ready(nor);
+
+	if (nor->flags & SNOR_F_READY_XSR_RDY)
+		sr = s3an_sr_ready(nor);
+	else
+		sr = spi_nor_sr_ready(nor);
 	if (sr < 0)
 		return sr;
 	fsr = nor->flags & SNOR_F_USE_FSR ? spi_nor_fsr_ready(nor) : 1;
@@ -320,6 +421,27 @@ static void spi_nor_unlock_and_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 }
 
 /*
+ * This code converts an address to the Default Address Mode, that has non
+ * power of two page sizes. We must support this mode because it is the default
+ * mode supported by Xilinx tools, it can access the whole flash area and
+ * changing over to the Power-of-two mode is irreversible and corrupts the
+ * original data.
+ * Addr can safely be unsigned int, the biggest S3AN device is smaller than
+ * 4 MiB.
+ */
+static loff_t spi_nor_s3an_addr_convert(struct spi_nor *nor, unsigned int addr)
+{
+	unsigned int offset;
+	unsigned int page;
+
+	offset = addr % nor->page_size;
+	page = addr / nor->page_size;
+	page <<= (nor->page_size > 512) ? 10 : 9;
+
+	return page | offset;
+}
+
+/*
  * Initiate the erasure of a single sector
  */
 static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
@@ -327,6 +449,9 @@ static int spi_nor_erase_sector(struct spi_nor *nor, u32 addr)
 	u8 buf[SPI_NOR_MAX_ADDR_WIDTH];
 	int i;
 
+	if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+		addr = spi_nor_s3an_addr_convert(nor, addr);
+
 	if (nor->erase)
 		return nor->erase(nor, addr);
 
@@ -368,7 +493,7 @@ static int spi_nor_erase(struct mtd_info *mtd, struct erase_info *instr)
 		return ret;
 
 	/* whole-chip erase? */
-	if (len == mtd->size) {
+	if (len == mtd->size && !(nor->flags & SNOR_F_NO_OP_CHIP_ERASE)) {
 		unsigned long timeout;
 
 		write_enable(nor);
@@ -782,6 +907,19 @@ static int spi_nor_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 		.addr_width = (_addr_width),				\
 		.flags = (_flags),
 
+#define S3AN_INFO(_jedec_id, _n_sectors, _page_size)			\
+		.id = {							\
+			((_jedec_id) >> 16) & 0xff,			\
+			((_jedec_id) >> 8) & 0xff,			\
+			(_jedec_id) & 0xff				\
+			},						\
+		.id_len = 3,						\
+		.sector_size = (8*_page_size),				\
+		.n_sectors = (_n_sectors),				\
+		.page_size = _page_size,				\
+		.addr_width = 3,					\
+		.flags = SPI_NOR_NO_FR | SPI_S3AN,
+
 /* NOTE: double check command sets and memory organization when you add
  * more nor chips.  This current list focusses on newer chips, which
  * have been converging on command sets which including JEDEC ID.
@@ -821,7 +959,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "en25s64",	INFO(0x1c3817, 0, 64 * 1024,  128, SECT_4K) },
 
 	/* ESMT */
-	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K) },
+	{ "f25l32pa", INFO(0x8c2016, 0, 64 * 1024, 64, SECT_4K | SPI_NOR_HAS_LOCK) },
 
 	/* Everspin */
 	{ "mr25h256", CAT25_INFO( 32 * 1024, 1, 256, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
@@ -833,6 +971,11 @@ static const struct flash_info spi_nor_ids[] = {
 
 	/* GigaDevice */
 	{
+		"gd25q16", INFO(0xc84015, 0, 64 * 1024,  32,
+			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
+			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
+	},
+	{
 		"gd25q32", INFO(0xc84016, 0, 64 * 1024,  64,
 			SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ |
 			SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB)
@@ -1014,6 +1157,13 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "cat25c09", CAT25_INFO( 128, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "cat25c17", CAT25_INFO( 256, 8, 32, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
 	{ "cat25128", CAT25_INFO(2048, 8, 64, 2, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
+
+	/* Xilinx S3AN Internal Flash */
+	{ "3S50AN", S3AN_INFO(0x1f2200, 64, 264) },
+	{ "3S200AN", S3AN_INFO(0x1f2400, 256, 264) },
+	{ "3S400AN", S3AN_INFO(0x1f2400, 256, 264) },
+	{ "3S700AN", S3AN_INFO(0x1f2500, 512, 264) },
+	{ "3S1400AN", S3AN_INFO(0x1f2600, 512, 528) },
 	{ },
 };
 
@@ -1054,7 +1204,12 @@ static int spi_nor_read(struct mtd_info *mtd, loff_t from, size_t len,
 		return ret;
 
 	while (len) {
-		ret = nor->read(nor, from, len, buf);
+		loff_t addr = from;
+
+		if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+			addr = spi_nor_s3an_addr_convert(nor, addr);
+
+		ret = nor->read(nor, addr, len, buf);
 		if (ret == 0) {
 			/* We shouldn't see 0-length reads */
 			ret = -EIO;
@@ -1175,17 +1330,32 @@ static int spi_nor_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 	for (i = 0; i < len; ) {
 		ssize_t written;
+		loff_t addr = to + i;
+
+		/*
+		 * If page_size is a power of two, the offset can be quickly
+		 * calculated with an AND operation. On the other cases we
+		 * need to do a modulus operation (more expensive).
+		 * Power of two numbers have only one bit set and we can use
+		 * the instruction hweight32 to detect if we need to do a
+		 * modulus (do_div()) or not.
+		 */
+		if (hweight32(nor->page_size) == 1) {
+			page_offset = addr & (nor->page_size - 1);
+		} else {
+			uint64_t aux = addr;
 
-		page_offset = (to + i) & (nor->page_size - 1);
-		WARN_ONCE(page_offset,
-			  "Writing at offset %zu into a NOR page. Writing partial pages may decrease reliability and increase wear of NOR flash.",
-			  page_offset);
+			page_offset = do_div(aux, nor->page_size);
+		}
 		/* the size of data remaining on the first page */
 		page_remain = min_t(size_t,
 				    nor->page_size - page_offset, len - i);
 
+		if (nor->flags & SNOR_F_S3AN_ADDR_DEFAULT)
+			addr = spi_nor_s3an_addr_convert(nor, addr);
+
 		write_enable(nor);
-		ret = nor->write(nor, to + i, page_remain, buf + i);
+		ret = nor->write(nor, addr, page_remain, buf + i);
 		if (ret < 0)
 			goto write_err;
 		written = ret;
@@ -1216,6 +1386,9 @@ static int macronix_quad_enable(struct spi_nor *nor)
 	val = read_sr(nor);
 	if (val < 0)
 		return val;
+	if (val & SR_QUAD_EN_MX)
+		return 0;
+
 	write_enable(nor);
 
 	write_sr(nor, val | SR_QUAD_EN_MX);
@@ -1312,6 +1485,47 @@ static int spi_nor_check(struct spi_nor *nor)
 	return 0;
 }
 
+static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor)
+{
+	int ret;
+	u8 val;
+
+	ret = nor->read_reg(nor, SPINOR_OP_XRDSR, &val, 1);
+	if (ret < 0) {
+		dev_err(nor->dev, "error %d reading XRDSR\n", (int) ret);
+		return ret;
+	}
+
+	nor->erase_opcode = SPINOR_OP_XSE;
+	nor->program_opcode = SPINOR_OP_XPP;
+	nor->read_opcode = SPINOR_OP_READ;
+	nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
+
+	/*
+	 * This flashes have a page size of 264 or 528 bytes (known as
+	 * Default addressing mode). It can be changed to a more standard
+	 * Power of two mode where the page size is 256/512. This comes
+	 * with a price: there is 3% less of space, the data is corrupted
+	 * and the page size cannot be changed back to default addressing
+	 * mode.
+	 *
+	 * The current addressing mode can be read from the XRDSR register
+	 * and should not be changed, because is a destructive operation.
+	 */
+	if (val & XSR_PAGESIZE) {
+		/* Flash in Power of 2 mode */
+		nor->page_size = (nor->page_size == 264) ? 256 : 512;
+		nor->mtd.writebufsize = nor->page_size;
+		nor->mtd.size = 8 * nor->page_size * info->n_sectors;
+		nor->mtd.erasesize = 8 * nor->page_size;
+	} else {
+		/* Flash in Default addressing mode */
+		nor->flags |= SNOR_F_S3AN_ADDR_DEFAULT;
+	}
+
+	return 0;
+}
+
 int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 {
 	const struct flash_info *info = NULL;
@@ -1360,6 +1574,14 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	mutex_init(&nor->lock);
 
 	/*
+	 * Make sure the XSR_RDY flag is set before calling
+	 * spi_nor_wait_till_ready(). Xilinx S3AN share MFR
+	 * with Atmel spi-nor
+	 */
+	if (info->flags & SPI_S3AN)
+		nor->flags |=  SNOR_F_READY_XSR_RDY;
+
+	/*
 	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
 	 * with the software protection bits set
 	 */
@@ -1483,27 +1705,10 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	else if (mtd->size > 0x1000000) {
 		/* enable 4-byte addressing if the device exceeds 16MiB */
 		nor->addr_width = 4;
-		if (JEDEC_MFR(info) == SNOR_MFR_SPANSION) {
-			/* Dedicated 4-byte command set */
-			switch (nor->flash_read) {
-			case SPI_NOR_QUAD:
-				nor->read_opcode = SPINOR_OP_READ4_1_1_4;
-				break;
-			case SPI_NOR_DUAL:
-				nor->read_opcode = SPINOR_OP_READ4_1_1_2;
-				break;
-			case SPI_NOR_FAST:
-				nor->read_opcode = SPINOR_OP_READ4_FAST;
-				break;
-			case SPI_NOR_NORMAL:
-				nor->read_opcode = SPINOR_OP_READ4;
-				break;
-			}
-			nor->program_opcode = SPINOR_OP_PP_4B;
-			/* No small sector erase for 4-byte command set */
-			nor->erase_opcode = SPINOR_OP_SE_4B;
-			mtd->erasesize = info->sector_size;
-		} else
+		if (JEDEC_MFR(info) == SNOR_MFR_SPANSION ||
+		    info->flags & SPI_NOR_4B_OPCODES)
+			spi_nor_set_4byte_opcodes(nor, info);
+		else
 			set_4byte(nor, info, 1);
 	} else {
 		nor->addr_width = 3;
@@ -1517,6 +1722,12 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 
 	nor->read_dummy = spi_nor_read_dummy_cycles(nor);
 
+	if (info->flags & SPI_S3AN) {
+		ret = s3an_nor_scan(info, nor);
+		if (ret)
+			return ret;
+	}
+
 	dev_info(dev, "%s (%lld Kbytes)\n", info->name,
 			(long long)mtd->size >> 10);