Merge tag 'for-linus-20170713' of git://git.infradead.org/linux-mtd

Pull MTD updates from Brian Norris:
 "General updates:
   - Cleanups and additional flash support for "dataflash" driver
   - new driver for mchp23k256 SPI SRAM device
   - improve handling of MTDs without eraseblocks (i.e., MTD_NO_ERASE)
   - refactor and improve "sub-partition" handling with TRX partition
     parser; partitions can now be created as sub-partitions of another
     partition

  SPINOR updates, from Cyrille Pitchen and Marek Vasut:
   - introduce support to the SPI 1-2-2 and 1-4-4 protocols.
   - introduce support to the Double Data Rate (DDR) mode.
   - introduce support to the Octo SPI protocols.
   - add support to new memory parts for Spansion, Macronix and Winbond.
   - add fixes for the Aspeed, STM32 and Cadence QSPI controler drivers.
   - clean up the st_spi_fsm driver.

  NAND updates, from Boris Brezillon:
   - addition of on-die ECC support to Micron driver
   - addition of helpers to help drivers choose most appropriate ECC
     settings
   - deletion of dead-code (cached programming and ->errstat() hook)
   - make sure drivers that do not support the SET/GET FEATURES command
     return ENOTSUPP use a dummy ->set/get_features implementation
     returning -ENOTSUPP (required for Micron on-die ECC)
   - change the semantic of ecc->write_page() for drivers setting the
     NAND_ECC_CUSTOM_PAGE_ACCESS flag
   - support exiting 'GET STATUS' command in default ->cmdfunc()
     implementations
   - change the prototype of ->setup_data_interface()

  A bunch of driver related changes:
   - various cleanup, fixes and improvements of the MTK driver
   - OMAP DT bindings fixes
   - support for ->setup_data_interface() in the fsmc driver
   - support for imx7 in the gpmi driver
   - finalization of the denali driver rework (thanks to Masahiro for
     the work he's done on this driver)
   - fix "bitflips in erased pages" handling in the ifc driver
   - addition of PM ops and dynamic timing configuration to the atmel
     driver"

* tag 'for-linus-20170713' of git://git.infradead.org/linux-mtd: (118 commits)
  Documentation: ABI: mtd: describe "offset" more precisely
  mtd: Fix check in mtd_unpoint()
  mtd: nand: mtk: release lock on error path
  mtd: st_spi_fsm: remove SPINOR_OP_RDSR2 and use SPINOR_OP_RDCR instead
  mtd: spi-nor: cqspi: remove duplicate const
  mtd: spi-nor: Add support for Spansion S25FL064L
  mtd: spi-nor: Add support for mx66u51235f
  mtd: nand: mtk: add ->setup_data_interface() hook
  mtd: nand: mtk: remove unneeded mtk_ecc_hw_init from mtk_ecc_resume
  mtd: nand: mtk: remove unneeded mtk_nfc_hw_init from mtk_nfc_resume
  mtd: nand: mtk: disable ecc irq when writing page with hwecc
  mtd: nand: mtk: fix incorrect register setting order about ecc irq
  mtd: partitions: fixup some allocate_partition() whitespace
  mtd: parsers: trx: fix pr_err format for printing offset
  MAINTAINERS: Update SPI NOR subsystem git repositories
  mtd: extract TRX parser out of bcm47xxpart into a separated module
  mtd: partitions: add support for partition parsers
  mtd: partitions: add support for subpartitions
  mtd: partitions: rename "master" to the "parent" where appropriate
  mtd: partitions: remove sysfs files when deleting all master's partitions
  ...

62 files changed, 3948 insertions, 2169 deletions

diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index e83a279f1217..5a2d71729b9a 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -155,6 +155,10 @@ config MTD_BCM47XX_PARTS
 	  This provides partitions parser for devices based on BCM47xx
 	  boards.
 
+menu "Partition parsers"
+source "drivers/mtd/parsers/Kconfig"
+endmenu
+
 comment "User Modules And Translation Layers"
 
 #
diff --git a/drivers/mtd/Makefile b/drivers/mtd/Makefile
index 99bb9a1f6e16..151d60df303a 100644
--- a/drivers/mtd/Makefile
+++ b/drivers/mtd/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_MTD_AFS_PARTS)	+= afs.o
 obj-$(CONFIG_MTD_AR7_PARTS)	+= ar7part.o
 obj-$(CONFIG_MTD_BCM63XX_PARTS)	+= bcm63xxpart.o
 obj-$(CONFIG_MTD_BCM47XX_PARTS)	+= bcm47xxpart.o
+obj-y				+= parsers/
 
 # 'Users' - code which presents functionality to userspace.
 obj-$(CONFIG_MTD_BLKDEVS)	+= mtd_blkdevs.o
diff --git a/drivers/mtd/bcm47xxpart.c b/drivers/mtd/bcm47xxpart.c
index d10fa6c8f074..fe2581d9d882 100644
--- a/drivers/mtd/bcm47xxpart.c
+++ b/drivers/mtd/bcm47xxpart.c
@@ -43,7 +43,8 @@
 #define ML_MAGIC2			0x26594131
 #define TRX_MAGIC			0x30524448
 #define SHSQ_MAGIC			0x71736873	/* shsq (weird ZTE H218N endianness) */
-#define UBI_EC_MAGIC			0x23494255	/* UBI# */
+
+static const char * const trx_types[] = { "trx", NULL };
 
 struct trx_header {
 	uint32_t magic;
@@ -62,89 +63,6 @@ static void bcm47xxpart_add_part(struct mtd_partition *part, const char *name,
 	part->mask_flags = mask_flags;
 }
 
-static const char *bcm47xxpart_trx_data_part_name(struct mtd_info *master,
-						  size_t offset)
-{
-	uint32_t buf;
-	size_t bytes_read;
-	int err;
-
-	err  = mtd_read(master, offset, sizeof(buf), &bytes_read,
-			(uint8_t *)&buf);
-	if (err && !mtd_is_bitflip(err)) {
-		pr_err("mtd_read error while parsing (offset: 0x%X): %d\n",
-			offset, err);
-		goto out_default;
-	}
-
-	if (buf == UBI_EC_MAGIC)
-		return "ubi";
-
-out_default:
-	return "rootfs";
-}
-
-static int bcm47xxpart_parse_trx(struct mtd_info *master,
-				 struct mtd_partition *trx,
-				 struct mtd_partition *parts,
-				 size_t parts_len)
-{
-	struct trx_header header;
-	size_t bytes_read;
-	int curr_part = 0;
-	int i, err;
-
-	if (parts_len < 3) {
-		pr_warn("No enough space to add TRX partitions!\n");
-		return -ENOMEM;
-	}
-
-	err = mtd_read(master, trx->offset, sizeof(header), &bytes_read,
-		       (uint8_t *)&header);
-	if (err && !mtd_is_bitflip(err)) {
-		pr_err("mtd_read error while reading TRX header: %d\n", err);
-		return err;
-	}
-
-	i = 0;
-
-	/* We have LZMA loader if offset[2] points to sth */
-	if (header.offset[2]) {
-		bcm47xxpart_add_part(&parts[curr_part++], "loader",
-				     trx->offset + header.offset[i], 0);
-		i++;
-	}
-
-	if (header.offset[i]) {
-		bcm47xxpart_add_part(&parts[curr_part++], "linux",
-				     trx->offset + header.offset[i], 0);
-		i++;
-	}
-
-	if (header.offset[i]) {
-		size_t offset = trx->offset + header.offset[i];
-		const char *name = bcm47xxpart_trx_data_part_name(master,
-								  offset);
-
-		bcm47xxpart_add_part(&parts[curr_part++], name, offset, 0);
-		i++;
-	}
-
-	/*
-	 * Assume that every partition ends at the beginning of the one it is
-	 * followed by.
-	 */
-	for (i = 0; i < curr_part; i++) {
-		u64 next_part_offset = (i < curr_part - 1) ?
-					parts[i + 1].offset :
-					trx->offset + trx->size;
-
-		parts[i].size = next_part_offset - parts[i].offset;
-	}
-
-	return curr_part;
-}
-
 /**
  * bcm47xxpart_bootpartition - gets index of TRX partition used by bootloader
  *
@@ -362,17 +280,10 @@ static int bcm47xxpart_parse(struct mtd_info *master,
 	for (i = 0; i < trx_num; i++) {
 		struct mtd_partition *trx = &parts[trx_parts[i]];
 
-		if (i == bcm47xxpart_bootpartition()) {
-			int num_parts;
-
-			num_parts = bcm47xxpart_parse_trx(master, trx,
-							  parts + curr_part,
-							  BCM47XXPART_MAX_PARTS - curr_part);
-			if (num_parts > 0)
-				curr_part += num_parts;
-		} else {
+		if (i == bcm47xxpart_bootpartition())
+			trx->types = trx_types;
+		else
 			trx->name = "failsafe";
-		}
 	}
 
 	*pparts = parts;
diff --git a/drivers/mtd/chips/cfi_cmdset_0020.c b/drivers/mtd/chips/cfi_cmdset_0020.c
index 94d3eb42c4d5..7d342965f392 100644
--- a/drivers/mtd/chips/cfi_cmdset_0020.c
+++ b/drivers/mtd/chips/cfi_cmdset_0020.c
@@ -666,7 +666,7 @@ cfi_staa_writev(struct mtd_info *mtd, const struct kvec *vecs,
 	size_t	 totlen = 0, thislen;
 	int	 ret = 0;
 	size_t	 buflen = 0;
-	static char *buffer;
+	char *buffer;
 
 	if (!ECCBUF_SIZE) {
 		/* We should fall back to a general writev implementation.
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 58329d2dacd1..6def5445e03e 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -95,6 +95,16 @@ config MTD_M25P80
 	  if you want to specify device partitioning or to use a device which
 	  doesn't support the JEDEC ID instruction.
 
+config MTD_MCHP23K256
+	tristate "Microchip 23K256 SRAM"
+	depends on SPI_MASTER
+	help
+	  This enables access to Microchip 23K256 SRAM chips, using SPI.
+
+	  Set up your spi devices with the right board-specific
+	  platform data, or a device tree description if you want to
+	  specify device partitioning
+
 config MTD_SPEAR_SMI
 	tristate "SPEAR MTD NOR Support through SMI controller"
 	depends on PLAT_SPEAR
diff --git a/drivers/mtd/devices/Makefile b/drivers/mtd/devices/Makefile
index 7912d3a0ee34..f0f767624cc6 100644
--- a/drivers/mtd/devices/Makefile
+++ b/drivers/mtd/devices/Makefile
@@ -12,6 +12,7 @@ obj-$(CONFIG_MTD_LART)		+= lart.o
 obj-$(CONFIG_MTD_BLOCK2MTD)	+= block2mtd.o
 obj-$(CONFIG_MTD_DATAFLASH)	+= mtd_dataflash.o
 obj-$(CONFIG_MTD_M25P80)	+= m25p80.o
+obj-$(CONFIG_MTD_MCHP23K256)	+= mchp23k256.o
 obj-$(CONFIG_MTD_SPEAR_SMI)	+= spear_smi.o
 obj-$(CONFIG_MTD_SST25L)	+= sst25l.o
 obj-$(CONFIG_MTD_BCM47XXSFLASH)	+= bcm47xxsflash.o
diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index c4df3b1bded0..00eea6fd379c 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -78,11 +78,17 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 {
 	struct m25p *flash = nor->priv;
 	struct spi_device *spi = flash->spi;
-	struct spi_transfer t[2] = {};
+	unsigned int inst_nbits, addr_nbits, data_nbits, data_idx;
+	struct spi_transfer t[3] = {};
 	struct spi_message m;
 	int cmd_sz = m25p_cmdsz(nor);
 	ssize_t ret;
 
+	/* get transfer protocols. */
+	inst_nbits = spi_nor_get_protocol_inst_nbits(nor->write_proto);
+	addr_nbits = spi_nor_get_protocol_addr_nbits(nor->write_proto);
+	data_nbits = spi_nor_get_protocol_data_nbits(nor->write_proto);
+
 	spi_message_init(&m);
 
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
@@ -92,12 +98,27 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	m25p_addr2cmd(nor, to, flash->command);
 
 	t[0].tx_buf = flash->command;
+	t[0].tx_nbits = inst_nbits;
 	t[0].len = cmd_sz;
 	spi_message_add_tail(&t[0], &m);
 
-	t[1].tx_buf = buf;
-	t[1].len = len;
-	spi_message_add_tail(&t[1], &m);
+	/* split the op code and address bytes into two transfers if needed. */
+	data_idx = 1;
+	if (addr_nbits != inst_nbits) {
+		t[0].len = 1;
+
+		t[1].tx_buf = &flash->command[1];
+		t[1].tx_nbits = addr_nbits;
+		t[1].len = cmd_sz - 1;
+		spi_message_add_tail(&t[1], &m);
+
+		data_idx = 2;
+	}
+
+	t[data_idx].tx_buf = buf;
+	t[data_idx].tx_nbits = data_nbits;
+	t[data_idx].len = len;
+	spi_message_add_tail(&t[data_idx], &m);
 
 	ret = spi_sync(spi, &m);
 	if (ret)
@@ -109,18 +130,6 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	return ret;
 }
 
-static inline unsigned int m25p80_rx_nbits(struct spi_nor *nor)
-{
-	switch (nor->flash_read) {
-	case SPI_NOR_DUAL:
-		return 2;
-	case SPI_NOR_QUAD:
-		return 4;
-	default:
-		return 0;
-	}
-}
-
 /*
  * Read an address range from the nor chip.  The address range
  * may be any size provided it is within the physical boundaries.
@@ -130,13 +139,20 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 {
 	struct m25p *flash = nor->priv;
 	struct spi_device *spi = flash->spi;
-	struct spi_transfer t[2];
+	unsigned int inst_nbits, addr_nbits, data_nbits, data_idx;
+	struct spi_transfer t[3];
 	struct spi_message m;
 	unsigned int dummy = nor->read_dummy;
 	ssize_t ret;
+	int cmd_sz;
+
+	/* get transfer protocols. */
+	inst_nbits = spi_nor_get_protocol_inst_nbits(nor->read_proto);
+	addr_nbits = spi_nor_get_protocol_addr_nbits(nor->read_proto);
+	data_nbits = spi_nor_get_protocol_data_nbits(nor->read_proto);
 
 	/* convert the dummy cycles to the number of bytes */
-	dummy /= 8;
+	dummy = (dummy * addr_nbits) / 8;
 
 	if (spi_flash_read_supported(spi)) {
 		struct spi_flash_read_message msg;
@@ -149,10 +165,9 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 		msg.read_opcode = nor->read_opcode;
 		msg.addr_width = nor->addr_width;
 		msg.dummy_bytes = dummy;
-		/* TODO: Support other combinations */
-		msg.opcode_nbits = SPI_NBITS_SINGLE;
-		msg.addr_nbits = SPI_NBITS_SINGLE;
-		msg.data_nbits = m25p80_rx_nbits(nor);
+		msg.opcode_nbits = inst_nbits;
+		msg.addr_nbits = addr_nbits;
+		msg.data_nbits = data_nbits;
 
 		ret = spi_flash_read(spi, &msg);
 		if (ret < 0)
@@ -167,20 +182,45 @@ static ssize_t m25p80_read(struct spi_nor *nor, loff_t from, size_t len,
 	m25p_addr2cmd(nor, from, flash->command);
 
 	t[0].tx_buf = flash->command;
+	t[0].tx_nbits = inst_nbits;
 	t[0].len = m25p_cmdsz(nor) + dummy;
 	spi_message_add_tail(&t[0], &m);
 
-	t[1].rx_buf = buf;
-	t[1].rx_nbits = m25p80_rx_nbits(nor);
-	t[1].len = min3(len, spi_max_transfer_size(spi),
-			spi_max_message_size(spi) - t[0].len);
-	spi_message_add_tail(&t[1], &m);
+	/*
+	 * Set all dummy/mode cycle bits to avoid sending some manufacturer
+	 * specific pattern, which might make the memory enter its Continuous
+	 * Read mode by mistake.
+	 * Based on the different mode cycle bit patterns listed and described
+	 * in the JESD216B specification, the 0xff value works for all memories
+	 * and all manufacturers.
+	 */
+	cmd_sz = t[0].len;
+	memset(flash->command + cmd_sz - dummy, 0xff, dummy);
+
+	/* split the op code and address bytes into two transfers if needed. */
+	data_idx = 1;
+	if (addr_nbits != inst_nbits) {
+		t[0].len = 1;
+
+		t[1].tx_buf = &flash->command[1];
+		t[1].tx_nbits = addr_nbits;
+		t[1].len = cmd_sz - 1;
+		spi_message_add_tail(&t[1], &m);
+
+		data_idx = 2;
+	}
+
+	t[data_idx].rx_buf = buf;
+	t[data_idx].rx_nbits = data_nbits;
+	t[data_idx].len = min3(len, spi_max_transfer_size(spi),
+			       spi_max_message_size(spi) - cmd_sz);
+	spi_message_add_tail(&t[data_idx], &m);
 
 	ret = spi_sync(spi, &m);
 	if (ret)
 		return ret;
 
-	ret = m.actual_length - m25p_cmdsz(nor) - dummy;
+	ret = m.actual_length - cmd_sz;
 	if (ret < 0)
 		return -EIO;
 	return ret;
@@ -196,7 +236,11 @@ static int m25p_probe(struct spi_device *spi)
 	struct flash_platform_data	*data;
 	struct m25p *flash;
 	struct spi_nor *nor;
-	enum read_mode mode = SPI_NOR_NORMAL;
+	struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	char *flash_name;
 	int ret;
 
@@ -221,10 +265,19 @@ static int m25p_probe(struct spi_device *spi)
 	spi_set_drvdata(spi, flash);
 	flash->spi = spi;
 
-	if (spi->mode & SPI_RX_QUAD)
-		mode = SPI_NOR_QUAD;
-	else if (spi->mode & SPI_RX_DUAL)
-		mode = SPI_NOR_DUAL;
+	if (spi->mode & SPI_RX_QUAD) {
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
+
+		if (spi->mode & SPI_TX_QUAD)
+			hwcaps.mask |= (SNOR_HWCAPS_READ_1_4_4 |
+					SNOR_HWCAPS_PP_1_1_4 |
+					SNOR_HWCAPS_PP_1_4_4);
+	} else if (spi->mode & SPI_RX_DUAL) {
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
+
+		if (spi->mode & SPI_TX_DUAL)
+			hwcaps.mask |= SNOR_HWCAPS_READ_1_2_2;
+	}
 
 	if (data && data->name)
 		nor->mtd.name = data->name;
@@ -241,7 +294,7 @@ static int m25p_probe(struct spi_device *spi)
 	else
 		flash_name = spi->modalias;
 
-	ret = spi_nor_scan(nor, flash_name, mode);
+	ret = spi_nor_scan(nor, flash_name, &hwcaps);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/devices/mchp23k256.c b/drivers/mtd/devices/mchp23k256.c
new file mode 100644
index 000000000000..8956b7dcc984
--- /dev/null
+++ b/drivers/mtd/devices/mchp23k256.c
@@ -0,0 +1,236 @@
+/*
+ * mchp23k256.c
+ *
+ * Driver for Microchip 23k256 SPI RAM chips
+ *
+ * Copyright © 2016 Andrew Lunn <andrew@lunn.ch>
+ *
+ * This code 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/device.h>
+#include <linux/module.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+#include <linux/spi/flash.h>
+#include <linux/spi/spi.h>
+#include <linux/of_device.h>
+
+#define MAX_CMD_SIZE		4
+
+struct mchp23_caps {
+	u8 addr_width;
+	unsigned int size;
+};
+
+struct mchp23k256_flash {
+	struct spi_device	*spi;
+	struct mutex		lock;
+	struct mtd_info		mtd;
+	const struct mchp23_caps	*caps;
+};
+
+#define MCHP23K256_CMD_WRITE_STATUS	0x01
+#define MCHP23K256_CMD_WRITE		0x02
+#define MCHP23K256_CMD_READ		0x03
+#define MCHP23K256_MODE_SEQ		BIT(6)
+
+#define to_mchp23k256_flash(x) container_of(x, struct mchp23k256_flash, mtd)
+
+static void mchp23k256_addr2cmd(struct mchp23k256_flash *flash,
+				unsigned int addr, u8 *cmd)
+{
+	int i;
+
+	/*
+	 * Address is sent in big endian (MSB first) and we skip
+	 * the first entry of the cmd array which contains the cmd
+	 * opcode.
+	 */
+	for (i = flash->caps->addr_width; i > 0; i--, addr >>= 8)
+		cmd[i] = addr;
+}
+
+static int mchp23k256_cmdsz(struct mchp23k256_flash *flash)
+{
+	return 1 + flash->caps->addr_width;
+}
+
+static int mchp23k256_write(struct mtd_info *mtd, loff_t to, size_t len,
+			    size_t *retlen, const unsigned char *buf)
+{
+	struct mchp23k256_flash *flash = to_mchp23k256_flash(mtd);
+	struct spi_transfer transfer[2] = {};
+	struct spi_message message;
+	unsigned char command[MAX_CMD_SIZE];
+
+	spi_message_init(&message);
+
+	command[0] = MCHP23K256_CMD_WRITE;
+	mchp23k256_addr2cmd(flash, to, command);
+
+	transfer[0].tx_buf = command;
+	transfer[0].len = mchp23k256_cmdsz(flash);
+	spi_message_add_tail(&transfer[0], &message);
+
+	transfer[1].tx_buf = buf;
+	transfer[1].len = len;
+	spi_message_add_tail(&transfer[1], &message);
+
+	mutex_lock(&flash->lock);
+
+	spi_sync(flash->spi, &message);
+
+	if (retlen && message.actual_length > sizeof(command))
+		*retlen += message.actual_length - sizeof(command);
+
+	mutex_unlock(&flash->lock);
+	return 0;
+}
+
+static int mchp23k256_read(struct mtd_info *mtd, loff_t from, size_t len,
+			   size_t *retlen, unsigned char *buf)
+{
+	struct mchp23k256_flash *flash = to_mchp23k256_flash(mtd);
+	struct spi_transfer transfer[2] = {};
+	struct spi_message message;
+	unsigned char command[MAX_CMD_SIZE];
+
+	spi_message_init(&message);
+
+	memset(&transfer, 0, sizeof(transfer));
+	command[0] = MCHP23K256_CMD_READ;
+	mchp23k256_addr2cmd(flash, from, command);
+
+	transfer[0].tx_buf = command;
+	transfer[0].len = mchp23k256_cmdsz(flash);
+	spi_message_add_tail(&transfer[0], &message);
+
+	transfer[1].rx_buf = buf;
+	transfer[1].len = len;
+	spi_message_add_tail(&transfer[1], &message);
+
+	mutex_lock(&flash->lock);
+
+	spi_sync(flash->spi, &message);
+
+	if (retlen && message.actual_length > sizeof(command))
+		*retlen += message.actual_length - sizeof(command);
+
+	mutex_unlock(&flash->lock);
+	return 0;
+}
+
+/*
+ * Set the device into sequential mode. This allows read/writes to the
+ * entire SRAM in a single operation
+ */
+static int mchp23k256_set_mode(struct spi_device *spi)
+{
+	struct spi_transfer transfer = {};
+	struct spi_message message;
+	unsigned char command[2];
+
+	spi_message_init(&message);
+
+	command[0] = MCHP23K256_CMD_WRITE_STATUS;
+	command[1] = MCHP23K256_MODE_SEQ;
+
+	transfer.tx_buf = command;
+	transfer.len = sizeof(command);
+	spi_message_add_tail(&transfer, &message);
+
+	return spi_sync(spi, &message);
+}
+
+static const struct mchp23_caps mchp23k256_caps = {
+	.size = SZ_32K,
+	.addr_width = 2,
+};
+
+static const struct mchp23_caps mchp23lcv1024_caps = {
+	.size = SZ_128K,
+	.addr_width = 3,
+};
+
+static int mchp23k256_probe(struct spi_device *spi)
+{
+	struct mchp23k256_flash *flash;
+	struct flash_platform_data *data;
+	int err;
+
+	flash = devm_kzalloc(&spi->dev, sizeof(*flash), GFP_KERNEL);
+	if (!flash)
+		return -ENOMEM;
+
+	flash->spi = spi;
+	mutex_init(&flash->lock);
+	spi_set_drvdata(spi, flash);
+
+	err = mchp23k256_set_mode(spi);
+	if (err)
+		return err;
+
+	data = dev_get_platdata(&spi->dev);
+
+	flash->caps = of_device_get_match_data(&spi->dev);
+	if (!flash->caps)
+		flash->caps = &mchp23k256_caps;
+
+	mtd_set_of_node(&flash->mtd, spi->dev.of_node);
+	flash->mtd.dev.parent	= &spi->dev;
+	flash->mtd.type		= MTD_RAM;
+	flash->mtd.flags	= MTD_CAP_RAM;
+	flash->mtd.writesize	= 1;
+	flash->mtd.size		= flash->caps->size;
+	flash->mtd._read	= mchp23k256_read;
+	flash->mtd._write	= mchp23k256_write;
+
+	err = mtd_device_register(&flash->mtd, data ? data->parts : NULL,
+				  data ? data->nr_parts : 0);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int mchp23k256_remove(struct spi_device *spi)
+{
+	struct mchp23k256_flash *flash = spi_get_drvdata(spi);
+
+	return mtd_device_unregister(&flash->mtd);
+}
+
+static const struct of_device_id mchp23k256_of_table[] = {
+	{
+		.compatible = "microchip,mchp23k256",
+		.data = &mchp23k256_caps,
+	},
+	{
+		.compatible = "microchip,mchp23lcv1024",
+		.data = &mchp23lcv1024_caps,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, mchp23k256_of_table);
+
+static struct spi_driver mchp23k256_driver = {
+	.driver = {
+		.name	= "mchp23k256",
+		.of_match_table = of_match_ptr(mchp23k256_of_table),
+	},
+	.probe		= mchp23k256_probe,
+	.remove		= mchp23k256_remove,
+};
+
+module_spi_driver(mchp23k256_driver);
+
+MODULE_DESCRIPTION("MTD SPI driver for MCHP23K256 RAM chips");
+MODULE_AUTHOR("Andrew Lunn <andre@lunn.ch>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("spi:mchp23k256");
diff --git a/drivers/mtd/devices/mtd_dataflash.c b/drivers/mtd/devices/mtd_dataflash.c
index f9e9bd1cfaa0..5dc8bd042cc5 100644
--- a/drivers/mtd/devices/mtd_dataflash.c
+++ b/drivers/mtd/devices/mtd_dataflash.c
@@ -82,9 +82,13 @@
 #define OP_WRITE_SECURITY_REVC	0x9A
 #define OP_WRITE_SECURITY	0x9B	/* revision D */
 
+#define CFI_MFR_ATMEL		0x1F
+
+#define DATAFLASH_SHIFT_EXTID	24
+#define DATAFLASH_SHIFT_ID	40
 
 struct dataflash {
-	uint8_t			command[4];
+	u8			command[4];
 	char			name[24];
 
 	unsigned short		page_offset;	/* offset in flash address */
@@ -129,8 +133,7 @@ static int dataflash_waitready(struct spi_device *spi)
 	for (;;) {
 		status = dataflash_status(spi);
 		if (status < 0) {
-			pr_debug("%s: status %d?\n",
-					dev_name(&spi->dev), status);
+			dev_dbg(&spi->dev, "status %d?\n", status);
 			status = 0;
 		}
 
@@ -153,12 +156,11 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr)
 	struct spi_transfer	x = { };
 	struct spi_message	msg;
 	unsigned		blocksize = priv->page_size << 3;
-	uint8_t			*command;
-	uint32_t		rem;
+	u8			*command;
+	u32			rem;
 
-	pr_debug("%s: erase addr=0x%llx len 0x%llx\n",
-	      dev_name(&spi->dev), (long long)instr->addr,
-	      (long long)instr->len);
+	dev_dbg(&spi->dev, "erase addr=0x%llx len 0x%llx\n",
+		(long long)instr->addr, (long long)instr->len);
 
 	div_u64_rem(instr->len, priv->page_size, &rem);
 	if (rem)
@@ -187,11 +189,11 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr)
 		pageaddr = pageaddr << priv->page_offset;
 
 		command[0] = do_block ? OP_ERASE_BLOCK : OP_ERASE_PAGE;
-		command[1] = (uint8_t)(pageaddr >> 16);
-		command[2] = (uint8_t)(pageaddr >> 8);
+		command[1] = (u8)(pageaddr >> 16);
+		command[2] = (u8)(pageaddr >> 8);
 		command[3] = 0;
 
-		pr_debug("ERASE %s: (%x) %x %x %x [%i]\n",
+		dev_dbg(&spi->dev, "ERASE %s: (%x) %x %x %x [%i]\n",
 			do_block ? "block" : "page",
 			command[0], command[1], command[2], command[3],
 			pageaddr);
@@ -200,8 +202,8 @@ static int dataflash_erase(struct mtd_info *mtd, struct erase_info *instr)
 		(void) dataflash_waitready(spi);
 
 		if (status < 0) {
-			printk(KERN_ERR "%s: erase %x, err %d\n",
-				dev_name(&spi->dev), pageaddr, status);
+			dev_err(&spi->dev, "erase %x, err %d\n",
+				pageaddr, status);
 			/* REVISIT:  can retry instr->retries times; or
 			 * giveup and instr->fail_addr = instr->addr;
 			 */
@@ -239,11 +241,11 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct spi_transfer	x[2] = { };
 	struct spi_message	msg;
 	unsigned int		addr;
-	uint8_t			*command;
+	u8			*command;
 	int			status;
 
-	pr_debug("%s: read 0x%x..0x%x\n", dev_name(&priv->spi->dev),
-			(unsigned)from, (unsigned)(from + len));
+	dev_dbg(&priv->spi->dev, "read 0x%x..0x%x\n",
+		  (unsigned int)from, (unsigned int)(from + len));
 
 	/* Calculate flash page/byte address */
 	addr = (((unsigned)from / priv->page_size) << priv->page_offset)
@@ -251,7 +253,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 
 	command = priv->command;
 
-	pr_debug("READ: (%x) %x %x %x\n",
+	dev_dbg(&priv->spi->dev, "READ: (%x) %x %x %x\n",
 		command[0], command[1], command[2], command[3]);
 
 	spi_message_init(&msg);
@@ -271,9 +273,9 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 	 * fewer "don't care" bytes.  Both buffers stay unchanged.
 	 */
 	command[0] = OP_READ_CONTINUOUS;
-	command[1] = (uint8_t)(addr >> 16);
-	command[2] = (uint8_t)(addr >> 8);
-	command[3] = (uint8_t)(addr >> 0);
+	command[1] = (u8)(addr >> 16);
+	command[2] = (u8)(addr >> 8);
+	command[3] = (u8)(addr >> 0);
 	/* plus 4 "don't care" bytes */
 
 	status = spi_sync(priv->spi, &msg);
@@ -283,8 +285,7 @@ static int dataflash_read(struct mtd_info *mtd, loff_t from, size_t len,
 		*retlen = msg.actual_length - 8;
 		status = 0;
 	} else
-		pr_debug("%s: read %x..%x --> %d\n",
-			dev_name(&priv->spi->dev),
+		dev_dbg(&priv->spi->dev, "read %x..%x --> %d\n",
 			(unsigned)from, (unsigned)(from + len),
 			status);
 	return status;
@@ -308,10 +309,10 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 	size_t			remaining = len;
 	u_char			*writebuf = (u_char *) buf;
 	int			status = -EINVAL;
-	uint8_t			*command;
+	u8			*command;
 
-	pr_debug("%s: write 0x%x..0x%x\n",
-		dev_name(&spi->dev), (unsigned)to, (unsigned)(to + len));
+	dev_dbg(&spi->dev, "write 0x%x..0x%x\n",
+		(unsigned int)to, (unsigned int)(to + len));
 
 	spi_message_init(&msg);
 
@@ -328,7 +329,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 
 	mutex_lock(&priv->lock);
 	while (remaining > 0) {
-		pr_debug("write @ %i:%i len=%i\n",
+		dev_dbg(&spi->dev, "write @ %i:%i len=%i\n",
 			pageaddr, offset, writelen);
 
 		/* REVISIT:
@@ -356,13 +357,13 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 			command[2] = (addr & 0x0000FF00) >> 8;
 			command[3] = 0;
 
-			pr_debug("TRANSFER: (%x) %x %x %x\n",
+			dev_dbg(&spi->dev, "TRANSFER: (%x) %x %x %x\n",
 				command[0], command[1], command[2], command[3]);
 
 			status = spi_sync(spi, &msg);
 			if (status < 0)
-				pr_debug("%s: xfer %u -> %d\n",
-					dev_name(&spi->dev), addr, status);
+				dev_dbg(&spi->dev, "xfer %u -> %d\n",
+					addr, status);
 
 			(void) dataflash_waitready(priv->spi);
 		}
@@ -374,7 +375,7 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 		command[2] = (addr & 0x0000FF00) >> 8;
 		command[3] = (addr & 0x000000FF);
 
-		pr_debug("PROGRAM: (%x) %x %x %x\n",
+		dev_dbg(&spi->dev, "PROGRAM: (%x) %x %x %x\n",
 			command[0], command[1], command[2], command[3]);
 
 		x[1].tx_buf = writebuf;
@@ -383,8 +384,8 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 		status = spi_sync(spi, &msg);
 		spi_transfer_del(x + 1);
 		if (status < 0)
-			pr_debug("%s: pgm %u/%u -> %d\n",
-				dev_name(&spi->dev), addr, writelen, status);
+			dev_dbg(&spi->dev, "pgm %u/%u -> %d\n",
+				addr, writelen, status);
 
 		(void) dataflash_waitready(priv->spi);
 
@@ -398,20 +399,20 @@ static int dataflash_write(struct mtd_info *mtd, loff_t to, size_t len,
 		command[2] = (addr & 0x0000FF00) >> 8;
 		command[3] = 0;
 
-		pr_debug("COMPARE: (%x) %x %x %x\n",
+		dev_dbg(&spi->dev, "COMPARE: (%x) %x %x %x\n",
 			command[0], command[1], command[2], command[3]);
 
 		status = spi_sync(spi, &msg);
 		if (status < 0)
-			pr_debug("%s: compare %u -> %d\n",
-				dev_name(&spi->dev), addr, status);
+			dev_dbg(&spi->dev, "compare %u -> %d\n",
+				addr, status);
 
 		status = dataflash_waitready(priv->spi);
 
 		/* Check result of the compare operation */
 		if (status & (1 << 6)) {
-			printk(KERN_ERR "%s: compare page %u, err %d\n",
-				dev_name(&spi->dev), pageaddr, status);
+			dev_err(&spi->dev, "compare page %u, err %d\n",
+				pageaddr, status);
 			remaining = 0;
 			status = -EIO;
 			break;
@@ -455,11 +456,11 @@ static int dataflash_get_otp_info(struct mtd_info *mtd, size_t len,
 }
 
 static ssize_t otp_read(struct spi_device *spi, unsigned base,
-		uint8_t *buf, loff_t off, size_t len)
+		u8 *buf, loff_t off, size_t len)
 {
 	struct spi_message	m;
 	size_t			l;
-	uint8_t			*scratch;
+	u8			*scratch;
 	struct spi_transfer	t;
 	int			status;
 
@@ -538,7 +539,7 @@ static int dataflash_write_user_otp(struct mtd_info *mtd,
 {
 	struct spi_message	m;
 	const size_t		l = 4 + 64;
-	uint8_t			*scratch;
+	u8			*scratch;
 	struct spi_transfer	t;
 	struct dataflash	*priv = mtd->priv;
 	int			status;
@@ -689,14 +690,15 @@ struct flash_info {
 	/* JEDEC id has a high byte of zero plus three data bytes:
 	 * the manufacturer id, then a two byte device id.
 	 */
-	uint32_t	jedec_id;
+	u64		jedec_id;
 
 	/* The size listed here is what works with OP_ERASE_PAGE. */
 	unsigned	nr_pages;
-	uint16_t	pagesize;
-	uint16_t	pageoffset;
+	u16		pagesize;
+	u16		pageoffset;
 
-	uint16_t	flags;
+	u16		flags;
+#define SUP_EXTID	0x0004		/* supports extended ID data */
 #define SUP_POW2PS	0x0002		/* supports 2^N byte pages */
 #define IS_POW2PS	0x0001		/* uses 2^N byte pages */
 };
@@ -734,54 +736,32 @@ static struct flash_info dataflash_data[] = {
 
 	{ "AT45DB642x",  0x1f2800, 8192, 1056, 11, SUP_POW2PS},
 	{ "at45db642d",  0x1f2800, 8192, 1024, 10, SUP_POW2PS | IS_POW2PS},
+
+	{ "AT45DB641E",  0x1f28000100, 32768, 264, 9, SUP_EXTID | SUP_POW2PS},
+	{ "at45db641e",  0x1f28000100, 32768, 256, 8, SUP_EXTID | SUP_POW2PS | IS_POW2PS},
 };
 
-static struct flash_info *jedec_probe(struct spi_device *spi)
+static struct flash_info *jedec_lookup(struct spi_device *spi,
+				       u64 jedec, bool use_extid)
 {
-	int			tmp;
-	uint8_t			code = OP_READ_ID;
-	uint8_t			id[3];
-	uint32_t		jedec;
-	struct flash_info	*info;
+	struct flash_info *info;
 	int status;
 
-	/* JEDEC also defines an optional "extended device information"
-	 * string for after vendor-specific data, after the three bytes
-	 * we use here.  Supporting some chips might require using it.
-	 *
-	 * If the vendor ID isn't Atmel's (0x1f), assume this call failed.
-	 * That's not an error; only rev C and newer chips handle it, and
-	 * only Atmel sells these chips.
-	 */
-	tmp = spi_write_then_read(spi, &code, 1, id, 3);
-	if (tmp < 0) {
-		pr_debug("%s: error %d reading JEDEC ID\n",
-			dev_name(&spi->dev), tmp);
-		return ERR_PTR(tmp);
-	}
-	if (id[0] != 0x1f)
-		return NULL;
-
-	jedec = id[0];
-	jedec = jedec << 8;
-	jedec |= id[1];
-	jedec = jedec << 8;
-	jedec |= id[2];
+	for (info = dataflash_data;
+	     info < dataflash_data + ARRAY_SIZE(dataflash_data);
+	     info++) {
+		if (use_extid && !(info->flags & SUP_EXTID))
+			continue;
 
-	for (tmp = 0, info = dataflash_data;
-			tmp < ARRAY_SIZE(dataflash_data);
-			tmp++, info++) {
 		if (info->jedec_id == jedec) {
-			pr_debug("%s: OTP, sector protect%s\n",
-				dev_name(&spi->dev),
-				(info->flags & SUP_POW2PS)
-					? ", binary pagesize" : ""
-				);
+			dev_dbg(&spi->dev, "OTP, sector protect%s\n",
+				(info->flags & SUP_POW2PS) ?
+				", binary pagesize" : "");
 			if (info->flags & SUP_POW2PS) {
 				status = dataflash_status(spi);
 				if (status < 0) {
-					pr_debug("%s: status error %d\n",
-						dev_name(&spi->dev), status);
+					dev_dbg(&spi->dev, "status error %d\n",
+						status);
 					return ERR_PTR(status);
 				}
 				if (status & 0x1) {
@@ -796,12 +776,58 @@ static struct flash_info *jedec_probe(struct spi_device *spi)
 		}
 	}
 
+	return ERR_PTR(-ENODEV);
+}
+
+static struct flash_info *jedec_probe(struct spi_device *spi)
+{
+	int ret;
+	u8 code = OP_READ_ID;
+	u64 jedec;
+	u8 id[sizeof(jedec)] = {0};
+	const unsigned int id_size = 5;
+	struct flash_info *info;
+
+	/*
+	 * JEDEC also defines an optional "extended device information"
+	 * string for after vendor-specific data, after the three bytes
+	 * we use here.  Supporting some chips might require using it.
+	 *
+	 * If the vendor ID isn't Atmel's (0x1f), assume this call failed.
+	 * That's not an error; only rev C and newer chips handle it, and
+	 * only Atmel sells these chips.
+	 */
+	ret = spi_write_then_read(spi, &code, 1, id, id_size);
+	if (ret < 0) {
+		dev_dbg(&spi->dev, "error %d reading JEDEC ID\n", ret);
+		return ERR_PTR(ret);
+	}
+
+	if (id[0] != CFI_MFR_ATMEL)
+		return NULL;
+
+	jedec = be64_to_cpup((__be64 *)id);
+
+	/*
+	 * First, try to match device using extended device
+	 * information
+	 */
+	info = jedec_lookup(spi, jedec >> DATAFLASH_SHIFT_EXTID, true);
+	if (!IS_ERR(info))
+		return info;
+	/*
+	 * If that fails, make another pass using regular ID
+	 * information
+	 */
+	info = jedec_lookup(spi, jedec >> DATAFLASH_SHIFT_ID, false);
+	if (!IS_ERR(info))
+		return info;
 	/*
 	 * Treat other chips as errors ... we won't know the right page
 	 * size (it might be binary) even when we can tell which density
 	 * class is involved (legacy chip id scheme).
 	 */
-	dev_warn(&spi->dev, "JEDEC id %06x not handled\n", jedec);
+	dev_warn(&spi->dev, "JEDEC id %016llx not handled\n", jedec);
 	return ERR_PTR(-ENODEV);
 }
 
@@ -845,8 +871,7 @@ static int dataflash_probe(struct spi_device *spi)
 	 */
 	status = dataflash_status(spi);
 	if (status <= 0 || status == 0xff) {
-		pr_debug("%s: status error %d\n",
-				dev_name(&spi->dev), status);
+		dev_dbg(&spi->dev, "status error %d\n", status);
 		if (status == 0 || status == 0xff)
 			status = -ENODEV;
 		return status;
@@ -887,8 +912,7 @@ static int dataflash_probe(struct spi_device *spi)
 	}
 
 	if (status < 0)
-		pr_debug("%s: add_dataflash --> %d\n", dev_name(&spi->dev),
-				status);
+		dev_dbg(&spi->dev, "add_dataflash --> %d\n", status);
 
 	return status;
 }
@@ -898,7 +922,7 @@ static int dataflash_remove(struct spi_device *spi)
 	struct dataflash	*flash = spi_get_drvdata(spi);
 	int			status;
 
-	pr_debug("%s: remove\n", dev_name(&spi->dev));
+	dev_dbg(&spi->dev, "remove\n");
 
 	status = mtd_device_unregister(&flash->mtd);
 	if (status == 0)
diff --git a/drivers/mtd/devices/serial_flash_cmds.h b/drivers/mtd/devices/serial_flash_cmds.h
index 8b81e15105dd..eba125c9f23f 100644
--- a/drivers/mtd/devices/serial_flash_cmds.h
+++ b/drivers/mtd/devices/serial_flash_cmds.h
@@ -13,7 +13,6 @@
 #define _MTD_SERIAL_FLASH_CMDS_H
 
 /* Generic Flash Commands/OPCODEs */
-#define SPINOR_OP_RDSR2		0x35
 #define SPINOR_OP_WRVCR		0x81
 #define SPINOR_OP_RDVCR		0x85
 
diff --git a/drivers/mtd/devices/st_spi_fsm.c b/drivers/mtd/devices/st_spi_fsm.c
index 804313a33f2b..21afd94cd904 100644
--- a/drivers/mtd/devices/st_spi_fsm.c
+++ b/drivers/mtd/devices/st_spi_fsm.c
@@ -1445,7 +1445,7 @@ static int stfsm_s25fl_config(struct stfsm *fsm)
 	}
 
 	/* Check status of 'QE' bit, update if required. */
-	stfsm_read_status(fsm, SPINOR_OP_RDSR2, &cr1, 1);
+	stfsm_read_status(fsm, SPINOR_OP_RDCR, &cr1, 1);
 	data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1;
 	if (data_pads == 4) {
 		if (!(cr1 & STFSM_S25FL_CONFIG_QE)) {
@@ -1490,7 +1490,7 @@ static int stfsm_w25q_config(struct stfsm *fsm)
 		return ret;
 
 	/* Check status of 'QE' bit, update if required. */
-	stfsm_read_status(fsm, SPINOR_OP_RDSR2, &sr2, 1);
+	stfsm_read_status(fsm, SPINOR_OP_RDCR, &sr2, 1);
 	data_pads = ((fsm->stfsm_seq_read.seq_cfg >> 16) & 0x3) + 1;
 	if (data_pads == 4) {
 		if (!(sr2 & W25Q_STATUS_QE)) {
diff --git a/drivers/mtd/maps/physmap_of_gemini.c b/drivers/mtd/maps/physmap_of_gemini.c
index 9d371cd728ea..05b286b5289f 100644
--- a/drivers/mtd/maps/physmap_of_gemini.c
+++ b/drivers/mtd/maps/physmap_of_gemini.c
@@ -59,7 +59,7 @@ int of_flash_probe_gemini(struct platform_device *pdev,
 			  struct device_node *np,
 			  struct map_info *map)
 {
-	static struct regmap *rmap;
+	struct regmap *rmap;
 	struct device *dev = &pdev->dev;
 	u32 val;
 	int ret;
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 1517da3ddd7d..956382cea256 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -991,7 +991,7 @@ EXPORT_SYMBOL_GPL(mtd_point);
 /* We probably shouldn't allow XIP if the unpoint isn't a NULL */
 int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
-	if (!mtd->_point)
+	if (!mtd->_unpoint)
 		return -EOPNOTSUPP;
 	if (from < 0 || from >= mtd->size || len > mtd->size - from)
 		return -EINVAL;
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index ea5e5307f667..5736b0c90b33 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -37,10 +37,16 @@
 static LIST_HEAD(mtd_partitions);
 static DEFINE_MUTEX(mtd_partitions_mutex);
 
-/* Our partition node structure */
+/**
+ * struct mtd_part - our partition node structure
+ *
+ * @mtd: struct holding partition details
+ * @parent: parent mtd - flash device or another partition
+ * @offset: partition offset relative to the *flash device*
+ */
 struct mtd_part {
 	struct mtd_info mtd;
-	struct mtd_info *master;
+	struct mtd_info *parent;
 	uint64_t offset;
 	struct list_head list;
 };
@@ -67,15 +73,15 @@ static int part_read(struct mtd_info *mtd, loff_t from, size_t len,
 	struct mtd_ecc_stats stats;
 	int res;
 
-	stats = part->master->ecc_stats;
-	res = part->master->_read(part->master, from + part->offset, len,
+	stats = part->parent->ecc_stats;
+	res = part->parent->_read(part->parent, from + part->offset, len,
 				  retlen, buf);
 	if (unlikely(mtd_is_eccerr(res)))
 		mtd->ecc_stats.failed +=
-			part->master->ecc_stats.failed - stats.failed;
+			part->parent->ecc_stats.failed - stats.failed;
 	else
 		mtd->ecc_stats.corrected +=
-			part->master->ecc_stats.corrected - stats.corrected;
+			part->parent->ecc_stats.corrected - stats.corrected;
 	return res;
 }
 
@@ -84,7 +90,7 @@ static int part_point(struct mtd_info *mtd, loff_t from, size_t len,
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 
-	return part->master->_point(part->master, from + part->offset, len,
+	return part->parent->_point(part->parent, from + part->offset, len,
 				    retlen, virt, phys);
 }
 
@@ -92,7 +98,7 @@ static int part_unpoint(struct mtd_info *mtd, loff_t from, size_t len)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 
-	return part->master->_unpoint(part->master, from + part->offset, len);
+	return part->parent->_unpoint(part->parent, from + part->offset, len);
 }
 
 static unsigned long part_get_unmapped_area(struct mtd_info *mtd,
@@ -103,7 +109,7 @@ static unsigned long part_get_unmapped_area(struct mtd_info *mtd,
 	struct mtd_part *part = mtd_to_part(mtd);
 
 	offset += part->offset;
-	return part->master->_get_unmapped_area(part->master, len, offset,
+	return part->parent->_get_unmapped_area(part->parent, len, offset,
 						flags);
 }
 
@@ -132,7 +138,7 @@ static int part_read_oob(struct mtd_info *mtd, loff_t from,
 			return -EINVAL;
 	}
 
-	res = part->master->_read_oob(part->master, from + part->offset, ops);
+	res = part->parent->_read_oob(part->parent, from + part->offset, ops);
 	if (unlikely(res)) {
 		if (mtd_is_bitflip(res))
 			mtd->ecc_stats.corrected++;
@@ -146,7 +152,7 @@ static int part_read_user_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len, size_t *retlen, u_char *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_read_user_prot_reg(part->master, from, len,
+	return part->parent->_read_user_prot_reg(part->parent, from, len,
 						 retlen, buf);
 }
 
@@ -154,7 +160,7 @@ static int part_get_user_prot_info(struct mtd_info *mtd, size_t len,
 				   size_t *retlen, struct otp_info *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_get_user_prot_info(part->master, len, retlen,
+	return part->parent->_get_user_prot_info(part->parent, len, retlen,
 						 buf);
 }
 
@@ -162,7 +168,7 @@ static int part_read_fact_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len, size_t *retlen, u_char *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_read_fact_prot_reg(part->master, from, len,
+	return part->parent->_read_fact_prot_reg(part->parent, from, len,
 						 retlen, buf);
 }
 
@@ -170,7 +176,7 @@ static int part_get_fact_prot_info(struct mtd_info *mtd, size_t len,
 				   size_t *retlen, struct otp_info *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_get_fact_prot_info(part->master, len, retlen,
+	return part->parent->_get_fact_prot_info(part->parent, len, retlen,
 						 buf);
 }
 
@@ -178,7 +184,7 @@ static int part_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_write(part->master, to + part->offset, len,
+	return part->parent->_write(part->parent, to + part->offset, len,
 				    retlen, buf);
 }
 
@@ -186,7 +192,7 @@ static int part_panic_write(struct mtd_info *mtd, loff_t to, size_t len,
 		size_t *retlen, const u_char *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_panic_write(part->master, to + part->offset, len,
+	return part->parent->_panic_write(part->parent, to + part->offset, len,
 					  retlen, buf);
 }
 
@@ -199,14 +205,14 @@ static int part_write_oob(struct mtd_info *mtd, loff_t to,
 		return -EINVAL;
 	if (ops->datbuf && to + ops->len > mtd->size)
 		return -EINVAL;
-	return part->master->_write_oob(part->master, to + part->offset, ops);
+	return part->parent->_write_oob(part->parent, to + part->offset, ops);
 }
 
 static int part_write_user_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len, size_t *retlen, u_char *buf)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_write_user_prot_reg(part->master, from, len,
+	return part->parent->_write_user_prot_reg(part->parent, from, len,
 						  retlen, buf);
 }
 
@@ -214,14 +220,14 @@ static int part_lock_user_prot_reg(struct mtd_info *mtd, loff_t from,
 		size_t len)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_lock_user_prot_reg(part->master, from, len);
+	return part->parent->_lock_user_prot_reg(part->parent, from, len);
 }
 
 static int part_writev(struct mtd_info *mtd, const struct kvec *vecs,
 		unsigned long count, loff_t to, size_t *retlen)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_writev(part->master, vecs, count,
+	return part->parent->_writev(part->parent, vecs, count,
 				     to + part->offset, retlen);
 }
 
@@ -231,7 +237,7 @@ static int part_erase(struct mtd_info *mtd, struct erase_info *instr)
 	int ret;
 
 	instr->addr += part->offset;
-	ret = part->master->_erase(part->master, instr);
+	ret = part->parent->_erase(part->parent, instr);
 	if (ret) {
 		if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN)
 			instr->fail_addr -= part->offset;
@@ -257,51 +263,51 @@ EXPORT_SYMBOL_GPL(mtd_erase_callback);
 static int part_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_lock(part->master, ofs + part->offset, len);
+	return part->parent->_lock(part->parent, ofs + part->offset, len);
 }
 
 static int part_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_unlock(part->master, ofs + part->offset, len);
+	return part->parent->_unlock(part->parent, ofs + part->offset, len);
 }
 
 static int part_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_is_locked(part->master, ofs + part->offset, len);
+	return part->parent->_is_locked(part->parent, ofs + part->offset, len);
 }
 
 static void part_sync(struct mtd_info *mtd)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	part->master->_sync(part->master);
+	part->parent->_sync(part->parent);
 }
 
 static int part_suspend(struct mtd_info *mtd)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_suspend(part->master);
+	return part->parent->_suspend(part->parent);
 }
 
 static void part_resume(struct mtd_info *mtd)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	part->master->_resume(part->master);
+	part->parent->_resume(part->parent);
 }
 
 static int part_block_isreserved(struct mtd_info *mtd, loff_t ofs)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 	ofs += part->offset;
-	return part->master->_block_isreserved(part->master, ofs);
+	return part->parent->_block_isreserved(part->parent, ofs);
 }
 
 static int part_block_isbad(struct mtd_info *mtd, loff_t ofs)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 	ofs += part->offset;
-	return part->master->_block_isbad(part->master, ofs);
+	return part->parent->_block_isbad(part->parent, ofs);
 }
 
 static int part_block_markbad(struct mtd_info *mtd, loff_t ofs)
@@ -310,7 +316,7 @@ static int part_block_markbad(struct mtd_info *mtd, loff_t ofs)
 	int res;
 
 	ofs += part->offset;
-	res = part->master->_block_markbad(part->master, ofs);
+	res = part->parent->_block_markbad(part->parent, ofs);
 	if (!res)
 		mtd->ecc_stats.badblocks++;
 	return res;
@@ -319,13 +325,13 @@ static int part_block_markbad(struct mtd_info *mtd, loff_t ofs)
 static int part_get_device(struct mtd_info *mtd)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	return part->master->_get_device(part->master);
+	return part->parent->_get_device(part->parent);
 }
 
 static void part_put_device(struct mtd_info *mtd)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
-	part->master->_put_device(part->master);
+	part->parent->_put_device(part->parent);
 }
 
 static int part_ooblayout_ecc(struct mtd_info *mtd, int section,
@@ -333,7 +339,7 @@ static int part_ooblayout_ecc(struct mtd_info *mtd, int section,
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 
-	return mtd_ooblayout_ecc(part->master, section, oobregion);
+	return mtd_ooblayout_ecc(part->parent, section, oobregion);
 }
 
 static int part_ooblayout_free(struct mtd_info *mtd, int section,
@@ -341,7 +347,7 @@ static int part_ooblayout_free(struct mtd_info *mtd, int section,
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 
-	return mtd_ooblayout_free(part->master, section, oobregion);
+	return mtd_ooblayout_free(part->parent, section, oobregion);
 }
 
 static const struct mtd_ooblayout_ops part_ooblayout_ops = {
@@ -353,7 +359,7 @@ static int part_max_bad_blocks(struct mtd_info *mtd, loff_t ofs, size_t len)
 {
 	struct mtd_part *part = mtd_to_part(mtd);
 
-	return part->master->_max_bad_blocks(part->master,
+	return part->parent->_max_bad_blocks(part->parent,
 					     ofs + part->offset, len);
 }
 
@@ -363,63 +369,70 @@ static inline void free_partition(struct mtd_part *p)
 	kfree(p);
 }
 
-/*
- * This function unregisters and destroy all slave MTD objects which are
- * attached to the given master MTD object.
+/**
+ * mtd_parse_part - parse MTD partition looking for subpartitions
+ *
+ * @slave: part that is supposed to be a container and should be parsed
+ * @types: NULL-terminated array with names of partition parsers to try
+ *
+ * Some partitions are kind of containers with extra subpartitions (volumes).
+ * There can be various formats of such containers. This function tries to use
+ * specified parsers to analyze given partition and registers found
+ * subpartitions on success.
  */
-
-int del_mtd_partitions(struct mtd_info *master)
+static int mtd_parse_part(struct mtd_part *slave, const char *const *types)
 {
-	struct mtd_part *slave, *next;
-	int ret, err = 0;
+	struct mtd_partitions parsed;
+	int err;
 
-	mutex_lock(&mtd_partitions_mutex);
-	list_for_each_entry_safe(slave, next, &mtd_partitions, list)
-		if (slave->master == master) {
-			ret = del_mtd_device(&slave->mtd);
-			if (ret < 0) {
-				err = ret;
-				continue;
-			}
-			list_del(&slave->list);
-			free_partition(slave);
-		}
-	mutex_unlock(&mtd_partitions_mutex);
+	err = parse_mtd_partitions(&slave->mtd, types, &parsed, NULL);
+	if (err)
+		return err;
+	else if (!parsed.nr_parts)
+		return -ENOENT;
+
+	err = add_mtd_partitions(&slave->mtd, parsed.parts, parsed.nr_parts);
+
+	mtd_part_parser_cleanup(&parsed);
 
 	return err;
 }
 
-static struct mtd_part *allocate_partition(struct mtd_info *master,
+static struct mtd_part *allocate_partition(struct mtd_info *parent,
 			const struct mtd_partition *part, int partno,
 			uint64_t cur_offset)
 {
+	int wr_alignment = (parent->flags & MTD_NO_ERASE) ? parent->writesize :
+							    parent->erasesize;
 	struct mtd_part *slave;
+	u32 remainder;
 	char *name;
+	u64 tmp;
 
 	/* allocate the partition structure */
 	slave = kzalloc(sizeof(*slave), GFP_KERNEL);
 	name = kstrdup(part->name, GFP_KERNEL);
 	if (!name || !slave) {
 		printk(KERN_ERR"memory allocation error while creating partitions for \"%s\"\n",
-		       master->name);
+		       parent->name);
 		kfree(name);
 		kfree(slave);
 		return ERR_PTR(-ENOMEM);
 	}
 
 	/* set up the MTD object for this partition */
-	slave->mtd.type = master->type;
-	slave->mtd.flags = master->flags & ~part->mask_flags;
+	slave->mtd.type = parent->type;
+	slave->mtd.flags = parent->flags & ~part->mask_flags;
 	slave->mtd.size = part->size;
-	slave->mtd.writesize = master->writesize;
-	slave->mtd.writebufsize = master->writebufsize;
-	slave->mtd.oobsize = master->oobsize;
-	slave->mtd.oobavail = master->oobavail;
-	slave->mtd.subpage_sft = master->subpage_sft;
-	slave->mtd.pairing = master->pairing;
+	slave->mtd.writesize = parent->writesize;
+	slave->mtd.writebufsize = parent->writebufsize;
+	slave->mtd.oobsize = parent->oobsize;
+	slave->mtd.oobavail = parent->oobavail;
+	slave->mtd.subpage_sft = parent->subpage_sft;
+	slave->mtd.pairing = parent->pairing;
 
 	slave->mtd.name = name;
-	slave->mtd.owner = master->owner;
+	slave->mtd.owner = parent->owner;
 
 	/* NOTE: Historically, we didn't arrange MTDs as a tree out of
 	 * concern for showing the same data in multiple partitions.
@@ -429,80 +442,81 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 	 * parent conditional on that option. Note, this is a way to
 	 * distinguish between the master and the partition in sysfs.
 	 */
-	slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) ?
-				&master->dev :
-				master->dev.parent;
+	slave->mtd.dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) || mtd_is_partition(parent) ?
+				&parent->dev :
+				parent->dev.parent;
 	slave->mtd.dev.of_node = part->of_node;
 
 	slave->mtd._read = part_read;
 	slave->mtd._write = part_write;
 
-	if (master->_panic_write)
+	if (parent->_panic_write)
 		slave->mtd._panic_write = part_panic_write;
 
-	if (master->_point && master->_unpoint) {
+	if (parent->_point && parent->_unpoint) {
 		slave->mtd._point = part_point;
 		slave->mtd._unpoint = part_unpoint;
 	}
 
-	if (master->_get_unmapped_area)
+	if (parent->_get_unmapped_area)
 		slave->mtd._get_unmapped_area = part_get_unmapped_area;
-	if (master->_read_oob)
+	if (parent->_read_oob)
 		slave->mtd._read_oob = part_read_oob;
-	if (master->_write_oob)
+	if (parent->_write_oob)
 		slave->mtd._write_oob = part_write_oob;
-	if (master->_read_user_prot_reg)
+	if (parent->_read_user_prot_reg)
 		slave->mtd._read_user_prot_reg = part_read_user_prot_reg;
-	if (master->_read_fact_prot_reg)
+	if (parent->_read_fact_prot_reg)
 		slave->mtd._read_fact_prot_reg = part_read_fact_prot_reg;
-	if (master->_write_user_prot_reg)
+	if (parent->_write_user_prot_reg)
 		slave->mtd._write_user_prot_reg = part_write_user_prot_reg;
-	if (master->_lock_user_prot_reg)
+	if (parent->_lock_user_prot_reg)
 		slave->mtd._lock_user_prot_reg = part_lock_user_prot_reg;
-	if (master->_get_user_prot_info)
+	if (parent->_get_user_prot_info)
 		slave->mtd._get_user_prot_info = part_get_user_prot_info;
-	if (master->_get_fact_prot_info)
+	if (parent->_get_fact_prot_info)
 		slave->mtd._get_fact_prot_info = part_get_fact_prot_info;
-	if (master->_sync)
+	if (parent->_sync)
 		slave->mtd._sync = part_sync;
-	if (!partno && !master->dev.class && master->_suspend &&
-	    master->_resume) {
-			slave->mtd._suspend = part_suspend;
-			slave->mtd._resume = part_resume;
+	if (!partno && !parent->dev.class && parent->_suspend &&
+	    parent->_resume) {
+		slave->mtd._suspend = part_suspend;
+		slave->mtd._resume = part_resume;
 	}
-	if (master->_writev)
+	if (parent->_writev)
 		slave->mtd._writev = part_writev;
-	if (master->_lock)
+	if (parent->_lock)
 		slave->mtd._lock = part_lock;
-	if (master->_unlock)
+	if (parent->_unlock)
 		slave->mtd._unlock = part_unlock;
-	if (master->_is_locked)
+	if (parent->_is_locked)
 		slave->mtd._is_locked = part_is_locked;
-	if (master->_block_isreserved)
+	if (parent->_block_isreserved)
 		slave->mtd._block_isreserved = part_block_isreserved;
-	if (master->_block_isbad)
+	if (parent->_block_isbad)
 		slave->mtd._block_isbad = part_block_isbad;
-	if (master->_block_markbad)
+	if (parent->_block_markbad)
 		slave->mtd._block_markbad = part_block_markbad;
-	if (master->_max_bad_blocks)
+	if (parent->_max_bad_blocks)
 		slave->mtd._max_bad_blocks = part_max_bad_blocks;
 
-	if (master->_get_device)
+	if (parent->_get_device)
 		slave->mtd._get_device = part_get_device;
-	if (master->_put_device)
+	if (parent->_put_device)
 		slave->mtd._put_device = part_put_device;
 
 	slave->mtd._erase = part_erase;
-	slave->master = master;
+	slave->parent = parent;
 	slave->offset = part->offset;
 
 	if (slave->offset == MTDPART_OFS_APPEND)
 		slave->offset = cur_offset;
 	if (slave->offset == MTDPART_OFS_NXTBLK) {
+		tmp = cur_offset;
 		slave->offset = cur_offset;
-		if (mtd_mod_by_eb(cur_offset, master) != 0) {
-			/* Round up to next erasesize */
-			slave->offset = (mtd_div_by_eb(cur_offset, master) + 1) * master->erasesize;
+		remainder = do_div(tmp, wr_alignment);
+		if (remainder) {
+			slave->offset += wr_alignment - remainder;
 			printk(KERN_NOTICE "Moving partition %d: "
 			       "0x%012llx -> 0x%012llx\n", partno,
 			       (unsigned long long)cur_offset, (unsigned long long)slave->offset);
@@ -510,25 +524,25 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 	}
 	if (slave->offset == MTDPART_OFS_RETAIN) {
 		slave->offset = cur_offset;
-		if (master->size - slave->offset >= slave->mtd.size) {
-			slave->mtd.size = master->size - slave->offset
+		if (parent->size - slave->offset >= slave->mtd.size) {
+			slave->mtd.size = parent->size - slave->offset
 							- slave->mtd.size;
 		} else {
 			printk(KERN_ERR "mtd partition \"%s\" doesn't have enough space: %#llx < %#llx, disabled\n",
-				part->name, master->size - slave->offset,
+				part->name, parent->size - slave->offset,
 				slave->mtd.size);
 			/* register to preserve ordering */
 			goto out_register;
 		}
 	}
 	if (slave->mtd.size == MTDPART_SIZ_FULL)
-		slave->mtd.size = master->size - slave->offset;
+		slave->mtd.size = parent->size - slave->offset;
 
 	printk(KERN_NOTICE "0x%012llx-0x%012llx : \"%s\"\n", (unsigned long long)slave->offset,
 		(unsigned long long)(slave->offset + slave->mtd.size), slave->mtd.name);
 
 	/* let's do some sanity checks */
-	if (slave->offset >= master->size) {
+	if (slave->offset >= parent->size) {
 		/* let's register it anyway to preserve ordering */
 		slave->offset = 0;
 		slave->mtd.size = 0;
@@ -536,16 +550,16 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 			part->name);
 		goto out_register;
 	}
-	if (slave->offset + slave->mtd.size > master->size) {
-		slave->mtd.size = master->size - slave->offset;
+	if (slave->offset + slave->mtd.size > parent->size) {
+		slave->mtd.size = parent->size - slave->offset;
 		printk(KERN_WARNING"mtd: partition \"%s\" extends beyond the end of device \"%s\" -- size truncated to %#llx\n",
-			part->name, master->name, (unsigned long long)slave->mtd.size);
+			part->name, parent->name, (unsigned long long)slave->mtd.size);
 	}
-	if (master->numeraseregions > 1) {
+	if (parent->numeraseregions > 1) {
 		/* Deal with variable erase size stuff */
-		int i, max = master->numeraseregions;
+		int i, max = parent->numeraseregions;
 		u64 end = slave->offset + slave->mtd.size;
-		struct mtd_erase_region_info *regions = master->eraseregions;
+		struct mtd_erase_region_info *regions = parent->eraseregions;
 
 		/* Find the first erase regions which is part of this
 		 * partition. */
@@ -564,37 +578,40 @@ static struct mtd_part *allocate_partition(struct mtd_info *master,
 		BUG_ON(slave->mtd.erasesize == 0);
 	} else {
 		/* Single erase size */
-		slave->mtd.erasesize = master->erasesize;
+		slave->mtd.erasesize = parent->erasesize;
 	}
 
-	if ((slave->mtd.flags & MTD_WRITEABLE) &&
-	    mtd_mod_by_eb(slave->offset, &slave->mtd)) {
+	tmp = slave->offset;
+	remainder = do_div(tmp, wr_alignment);
+	if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) {
 		/* Doesn't start on a boundary of major erase size */
 		/* FIXME: Let it be writable if it is on a boundary of
 		 * _minor_ erase size though */
 		slave->mtd.flags &= ~MTD_WRITEABLE;
-		printk(KERN_WARNING"mtd: partition \"%s\" doesn't start on an erase block boundary -- force read-only\n",
+		printk(KERN_WARNING"mtd: partition \"%s\" doesn't start on an erase/write block boundary -- force read-only\n",
 			part->name);
 	}
-	if ((slave->mtd.flags & MTD_WRITEABLE) &&
-	    mtd_mod_by_eb(slave->mtd.size, &slave->mtd)) {
+
+	tmp = slave->mtd.size;
+	remainder = do_div(tmp, wr_alignment);
+	if ((slave->mtd.flags & MTD_WRITEABLE) && remainder) {
 		slave->mtd.flags &= ~MTD_WRITEABLE;
-		printk(KERN_WARNING"mtd: partition \"%s\" doesn't end on an erase block -- force read-only\n",
+		printk(KERN_WARNING"mtd: partition \"%s\" doesn't end on an erase/write block -- force read-only\n",
 			part->name);
 	}
 
 	mtd_set_ooblayout(&slave->mtd, &part_ooblayout_ops);
-	slave->mtd.ecc_step_size = master->ecc_step_size;
-	slave->mtd.ecc_strength = master->ecc_strength;
-	slave->mtd.bitflip_threshold = master->bitflip_threshold;
+	slave->mtd.ecc_step_size = parent->ecc_step_size;
+	slave->mtd.ecc_strength = parent->ecc_strength;
+	slave->mtd.bitflip_threshold = parent->bitflip_threshold;
 
-	if (master->_block_isbad) {
+	if (parent->_block_isbad) {
 		uint64_t offs = 0;
 
 		while (offs < slave->mtd.size) {
-			if (mtd_block_isreserved(master, offs + slave->offset))
+			if (mtd_block_isreserved(parent, offs + slave->offset))
 				slave->mtd.ecc_stats.bbtblocks++;
-			else if (mtd_block_isbad(master, offs + slave->offset))
+			else if (mtd_block_isbad(parent, offs + slave->offset))
 				slave->mtd.ecc_stats.badblocks++;
 			offs += slave->mtd.erasesize;
 		}
@@ -628,7 +645,7 @@ static int mtd_add_partition_attrs(struct mtd_part *new)
 	return ret;
 }
 
-int mtd_add_partition(struct mtd_info *master, const char *name,
+int mtd_add_partition(struct mtd_info *parent, const char *name,
 		      long long offset, long long length)
 {
 	struct mtd_partition part;
@@ -641,7 +658,7 @@ int mtd_add_partition(struct mtd_info *master, const char *name,
 		return -EINVAL;
 
 	if (length == MTDPART_SIZ_FULL)
-		length = master->size - offset;
+		length = parent->size - offset;
 
 	if (length <= 0)
 		return -EINVAL;
@@ -651,7 +668,7 @@ int mtd_add_partition(struct mtd_info *master, const char *name,
 	part.size = length;
 	part.offset = offset;
 
-	new = allocate_partition(master, &part, -1, offset);
+	new = allocate_partition(parent, &part, -1, offset);
 	if (IS_ERR(new))
 		return PTR_ERR(new);
 
@@ -667,23 +684,69 @@ int mtd_add_partition(struct mtd_info *master, const char *name,
 }
 EXPORT_SYMBOL_GPL(mtd_add_partition);
 
-int mtd_del_partition(struct mtd_info *master, int partno)
+/**
+ * __mtd_del_partition - delete MTD partition
+ *
+ * @priv: internal MTD struct for partition to be deleted
+ *
+ * This function must be called with the partitions mutex locked.
+ */
+static int __mtd_del_partition(struct mtd_part *priv)
+{
+	struct mtd_part *child, *next;
+	int err;
+
+	list_for_each_entry_safe(child, next, &mtd_partitions, list) {
+		if (child->parent == &priv->mtd) {
+			err = __mtd_del_partition(child);
+			if (err)
+				return err;
+		}
+	}
+
+	sysfs_remove_files(&priv->mtd.dev.kobj, mtd_partition_attrs);
+
+	err = del_mtd_device(&priv->mtd);
+	if (err)
+		return err;
+
+	list_del(&priv->list);
+	free_partition(priv);
+
+	return 0;
+}
+
+/*
+ * This function unregisters and destroy all slave MTD objects which are
+ * attached to the given MTD object.
+ */
+int del_mtd_partitions(struct mtd_info *mtd)
 {
 	struct mtd_part *slave, *next;
-	int ret = -EINVAL;
+	int ret, err = 0;
 
 	mutex_lock(&mtd_partitions_mutex);
 	list_for_each_entry_safe(slave, next, &mtd_partitions, list)
-		if ((slave->master == master) &&
-		    (slave->mtd.index == partno)) {
-			sysfs_remove_files(&slave->mtd.dev.kobj,
-					   mtd_partition_attrs);
-			ret = del_mtd_device(&slave->mtd);
+		if (slave->parent == mtd) {
+			ret = __mtd_del_partition(slave);
 			if (ret < 0)
-				break;
+				err = ret;
+		}
+	mutex_unlock(&mtd_partitions_mutex);
+
+	return err;
+}
+
+int mtd_del_partition(struct mtd_info *mtd, int partno)
+{
+	struct mtd_part *slave, *next;
+	int ret = -EINVAL;
 
-			list_del(&slave->list);
-			free_partition(slave);
+	mutex_lock(&mtd_partitions_mutex);
+	list_for_each_entry_safe(slave, next, &mtd_partitions, list)
+		if ((slave->parent == mtd) &&
+		    (slave->mtd.index == partno)) {
+			ret = __mtd_del_partition(slave);
 			break;
 		}
 	mutex_unlock(&mtd_partitions_mutex);
@@ -724,6 +787,8 @@ int add_mtd_partitions(struct mtd_info *master,
 
 		add_mtd_device(&slave->mtd);
 		mtd_add_partition_attrs(slave);
+		if (parts[i].types)
+			mtd_parse_part(slave, parts[i].types);
 
 		cur_offset = slave->offset + slave->mtd.size;
 	}
@@ -799,6 +864,27 @@ static const char * const default_mtd_part_types[] = {
 	NULL
 };
 
+static int mtd_part_do_parse(struct mtd_part_parser *parser,
+			     struct mtd_info *master,
+			     struct mtd_partitions *pparts,
+			     struct mtd_part_parser_data *data)
+{
+	int ret;
+
+	ret = (*parser->parse_fn)(master, &pparts->parts, data);
+	pr_debug("%s: parser %s: %i\n", master->name, parser->name, ret);
+	if (ret <= 0)
+		return ret;
+
+	pr_notice("%d %s partitions found on MTD device %s\n", ret,
+		  parser->name, master->name);
+
+	pparts->nr_parts = ret;
+	pparts->parser = parser;
+
+	return ret;
+}
+
 /**
  * parse_mtd_partitions - parse MTD partitions
  * @master: the master partition (describes whole MTD device)
@@ -839,16 +925,10 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 			 parser ? parser->name : NULL);
 		if (!parser)
 			continue;
-		ret = (*parser->parse_fn)(master, &pparts->parts, data);
-		pr_debug("%s: parser %s: %i\n",
-			 master->name, parser->name, ret);
-		if (ret > 0) {
-			printk(KERN_NOTICE "%d %s partitions found on MTD device %s\n",
-			       ret, parser->name, master->name);
-			pparts->nr_parts = ret;
-			pparts->parser = parser;
+		ret = mtd_part_do_parse(parser, master, pparts, data);
+		/* Found partitions! */
+		if (ret > 0)
 			return 0;
-		}
 		mtd_part_parser_put(parser);
 		/*
 		 * Stash the first error we see; only report it if no parser
@@ -899,6 +979,6 @@ uint64_t mtd_get_device_size(const struct mtd_info *mtd)
 	if (!mtd_is_partition(mtd))
 		return mtd->size;
 
-	return mtd_to_part(mtd)->master->size;
+	return mtd_get_device_size(mtd_to_part(mtd)->parent);
 }
 EXPORT_SYMBOL_GPL(mtd_get_device_size);
diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index c3029528063b..dbfa72d61d5a 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -308,6 +308,7 @@ config MTD_NAND_CS553X
 config MTD_NAND_ATMEL
 	tristate "Support for NAND Flash / SmartMedia on AT91"
 	depends on ARCH_AT91
+	select MFD_ATMEL_SMC
 	help
 	  Enables support for NAND Flash / Smart Media Card interface
 	  on Atmel AT91 processors.
@@ -542,6 +543,7 @@ config MTD_NAND_SUNXI
 
 config MTD_NAND_HISI504
 	tristate "Support for NAND controller on Hisilicon SoC Hip04"
+	depends on ARCH_HISI || COMPILE_TEST
 	depends on HAS_DMA
 	help
 	  Enables support for NAND controller on Hisilicon SoC Hip04.
@@ -555,6 +557,7 @@ config MTD_NAND_QCOM
 
 config MTD_NAND_MTK
 	tristate "Support for NAND controller on MTK SoCs"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
 	depends on HAS_DMA
 	help
 	  Enables support for NAND controller on MTK SoCs.
diff --git a/drivers/mtd/nand/atmel/nand-controller.c b/drivers/mtd/nand/atmel/nand-controller.c
index 3b2446896147..d922a88e407f 100644
--- a/drivers/mtd/nand/atmel/nand-controller.c
+++ b/drivers/mtd/nand/atmel/nand-controller.c
@@ -57,6 +57,7 @@
 #include <linux/interrupt.h>
 #include <linux/mfd/syscon.h>
 #include <linux/mfd/syscon/atmel-matrix.h>
+#include <linux/mfd/syscon/atmel-smc.h>
 #include <linux/module.h>
 #include <linux/mtd/nand.h>
 #include <linux/of_address.h>
@@ -64,7 +65,6 @@
 #include <linux/of_platform.h>
 #include <linux/iopoll.h>
 #include <linux/platform_device.h>
-#include <linux/platform_data/atmel.h>
 #include <linux/regmap.h>
 
 #include "pmecc.h"
@@ -151,6 +151,8 @@ struct atmel_nand_cs {
 		void __iomem *virt;
 		dma_addr_t dma;
 	} io;
+
+	struct atmel_smc_cs_conf smcconf;
 };
 
 struct atmel_nand {
@@ -196,6 +198,8 @@ struct atmel_nand_controller_ops {
 	void (*nand_init)(struct atmel_nand_controller *nc,
 			  struct atmel_nand *nand);
 	int (*ecc_init)(struct atmel_nand *nand);
+	int (*setup_data_interface)(struct atmel_nand *nand, int csline,
+				    const struct nand_data_interface *conf);
 };
 
 struct atmel_nand_controller_caps {
@@ -912,7 +916,7 @@ static int atmel_hsmc_nand_pmecc_write_pg(struct nand_chip *chip,
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct atmel_nand *nand = to_atmel_nand(chip);
 	struct atmel_hsmc_nand_controller *nc;
-	int ret;
+	int ret, status;
 
 	nc = to_hsmc_nand_controller(chip->controller);
 
@@ -954,6 +958,10 @@ static int atmel_hsmc_nand_pmecc_write_pg(struct nand_chip *chip,
 		dev_err(nc->base.dev, "Failed to program NAND page (err = %d)\n",
 			ret);
 
+	status = chip->waitfunc(mtd, chip);
+	if (status & NAND_STATUS_FAIL)
+		return -EIO;
+
 	return ret;
 }
 
@@ -1175,6 +1183,295 @@ static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand)
 	return 0;
 }
 
+static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand,
+					const struct nand_data_interface *conf,
+					struct atmel_smc_cs_conf *smcconf)
+{
+	u32 ncycles, totalcycles, timeps, mckperiodps;
+	struct atmel_nand_controller *nc;
+	int ret;
+
+	nc = to_nand_controller(nand->base.controller);
+
+	/* DDR interface not supported. */
+	if (conf->type != NAND_SDR_IFACE)
+		return -ENOTSUPP;
+
+	/*
+	 * tRC < 30ns implies EDO mode. This controller does not support this
+	 * mode.
+	 */
+	if (conf->timings.sdr.tRC_min < 30)
+		return -ENOTSUPP;
+
+	atmel_smc_cs_conf_init(smcconf);
+
+	mckperiodps = NSEC_PER_SEC / clk_get_rate(nc->mck);
+	mckperiodps *= 1000;
+
+	/*
+	 * Set write pulse timing. This one is easy to extract:
+	 *
+	 * NWE_PULSE = tWP
+	 */
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tWP_min, mckperiodps);
+	totalcycles = ncycles;
+	ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NWE_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/*
+	 * The write setup timing depends on the operation done on the NAND.
+	 * All operations goes through the same data bus, but the operation
+	 * type depends on the address we are writing to (ALE/CLE address
+	 * lines).
+	 * Since we have no way to differentiate the different operations at
+	 * the SMC level, we must consider the worst case (the biggest setup
+	 * time among all operation types):
+	 *
+	 * NWE_SETUP = max(tCLS, tCS, tALS, tDS) - NWE_PULSE
+	 */
+	timeps = max3(conf->timings.sdr.tCLS_min, conf->timings.sdr.tCS_min,
+		      conf->timings.sdr.tALS_min);
+	timeps = max(timeps, conf->timings.sdr.tDS_min);
+	ncycles = DIV_ROUND_UP(timeps, mckperiodps);
+	ncycles = ncycles > totalcycles ? ncycles - totalcycles : 0;
+	totalcycles += ncycles;
+	ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NWE_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/*
+	 * As for the write setup timing, the write hold timing depends on the
+	 * operation done on the NAND:
+	 *
+	 * NWE_HOLD = max(tCLH, tCH, tALH, tDH, tWH)
+	 */
+	timeps = max3(conf->timings.sdr.tCLH_min, conf->timings.sdr.tCH_min,
+		      conf->timings.sdr.tALH_min);
+	timeps = max3(timeps, conf->timings.sdr.tDH_min,
+		      conf->timings.sdr.tWH_min);
+	ncycles = DIV_ROUND_UP(timeps, mckperiodps);
+	totalcycles += ncycles;
+
+	/*
+	 * The write cycle timing is directly matching tWC, but is also
+	 * dependent on the other timings on the setup and hold timings we
+	 * calculated earlier, which gives:
+	 *
+	 * NWE_CYCLE = max(tWC, NWE_SETUP + NWE_PULSE + NWE_HOLD)
+	 */
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tWC_min, mckperiodps);
+	ncycles = max(totalcycles, ncycles);
+	ret = atmel_smc_cs_conf_set_cycle(smcconf, ATMEL_SMC_NWE_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/*
+	 * We don't want the CS line to be toggled between each byte/word
+	 * transfer to the NAND. The only way to guarantee that is to have the
+	 * NCS_{WR,RD}_{SETUP,HOLD} timings set to 0, which in turn means:
+	 *
+	 * NCS_WR_PULSE = NWE_CYCLE
+	 */
+	ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NCS_WR_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/*
+	 * As for the write setup timing, the read hold timing depends on the
+	 * operation done on the NAND:
+	 *
+	 * NRD_HOLD = max(tREH, tRHOH)
+	 */
+	timeps = max(conf->timings.sdr.tREH_min, conf->timings.sdr.tRHOH_min);
+	ncycles = DIV_ROUND_UP(timeps, mckperiodps);
+	totalcycles = ncycles;
+
+	/*
+	 * TDF = tRHZ - NRD_HOLD
+	 */
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tRHZ_max, mckperiodps);
+	ncycles -= totalcycles;
+
+	/*
+	 * In ONFI 4.0 specs, tRHZ has been increased to support EDO NANDs and
+	 * we might end up with a config that does not fit in the TDF field.
+	 * Just take the max value in this case and hope that the NAND is more
+	 * tolerant than advertised.
+	 */
+	if (ncycles > ATMEL_SMC_MODE_TDF_MAX)
+		ncycles = ATMEL_SMC_MODE_TDF_MAX;
+	else if (ncycles < ATMEL_SMC_MODE_TDF_MIN)
+		ncycles = ATMEL_SMC_MODE_TDF_MIN;
+
+	smcconf->mode |= ATMEL_SMC_MODE_TDF(ncycles) |
+			 ATMEL_SMC_MODE_TDFMODE_OPTIMIZED;
+
+	/*
+	 * Read pulse timing directly matches tRP:
+	 *
+	 * NRD_PULSE = tRP
+	 */
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tRP_min, mckperiodps);
+	totalcycles += ncycles;
+	ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NRD_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/*
+	 * The write cycle timing is directly matching tWC, but is also
+	 * dependent on the setup and hold timings we calculated earlier,
+	 * which gives:
+	 *
+	 * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD)
+	 *
+	 * NRD_SETUP is always 0.
+	 */
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps);
+	ncycles = max(totalcycles, ncycles);
+	ret = atmel_smc_cs_conf_set_cycle(smcconf, ATMEL_SMC_NRD_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/*
+	 * We don't want the CS line to be toggled between each byte/word
+	 * transfer from the NAND. The only way to guarantee that is to have
+	 * the NCS_{WR,RD}_{SETUP,HOLD} timings set to 0, which in turn means:
+	 *
+	 * NCS_RD_PULSE = NRD_CYCLE
+	 */
+	ret = atmel_smc_cs_conf_set_pulse(smcconf, ATMEL_SMC_NCS_RD_SHIFT,
+					  ncycles);
+	if (ret)
+		return ret;
+
+	/* Txxx timings are directly matching tXXX ones. */
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tCLR_min, mckperiodps);
+	ret = atmel_smc_cs_conf_set_timing(smcconf,
+					   ATMEL_HSMC_TIMINGS_TCLR_SHIFT,
+					   ncycles);
+	if (ret)
+		return ret;
+
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tADL_min, mckperiodps);
+	ret = atmel_smc_cs_conf_set_timing(smcconf,
+					   ATMEL_HSMC_TIMINGS_TADL_SHIFT,
+					   ncycles);
+	if (ret)
+		return ret;
+
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tAR_min, mckperiodps);
+	ret = atmel_smc_cs_conf_set_timing(smcconf,
+					   ATMEL_HSMC_TIMINGS_TAR_SHIFT,
+					   ncycles);
+	if (ret)
+		return ret;
+
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tRR_min, mckperiodps);
+	ret = atmel_smc_cs_conf_set_timing(smcconf,
+					   ATMEL_HSMC_TIMINGS_TRR_SHIFT,
+					   ncycles);
+	if (ret)
+		return ret;
+
+	ncycles = DIV_ROUND_UP(conf->timings.sdr.tWB_max, mckperiodps);
+	ret = atmel_smc_cs_conf_set_timing(smcconf,
+					   ATMEL_HSMC_TIMINGS_TWB_SHIFT,
+					   ncycles);
+	if (ret)
+		return ret;
+
+	/* Attach the CS line to the NFC logic. */
+	smcconf->timings |= ATMEL_HSMC_TIMINGS_NFSEL;
+
+	/* Set the appropriate data bus width. */
+	if (nand->base.options & NAND_BUSWIDTH_16)
+		smcconf->mode |= ATMEL_SMC_MODE_DBW_16;
+
+	/* Operate in NRD/NWE READ/WRITEMODE. */
+	smcconf->mode |= ATMEL_SMC_MODE_READMODE_NRD |
+			 ATMEL_SMC_MODE_WRITEMODE_NWE;
+
+	return 0;
+}
+
+static int atmel_smc_nand_setup_data_interface(struct atmel_nand *nand,
+					int csline,
+					const struct nand_data_interface *conf)
+{
+	struct atmel_nand_controller *nc;
+	struct atmel_smc_cs_conf smcconf;
+	struct atmel_nand_cs *cs;
+	int ret;
+
+	nc = to_nand_controller(nand->base.controller);
+
+	ret = atmel_smc_nand_prepare_smcconf(nand, conf, &smcconf);
+	if (ret)
+		return ret;
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	cs = &nand->cs[csline];
+	cs->smcconf = smcconf;
+	atmel_smc_cs_conf_apply(nc->smc, cs->id, &cs->smcconf);
+
+	return 0;
+}
+
+static int atmel_hsmc_nand_setup_data_interface(struct atmel_nand *nand,
+					int csline,
+					const struct nand_data_interface *conf)
+{
+	struct atmel_nand_controller *nc;
+	struct atmel_smc_cs_conf smcconf;
+	struct atmel_nand_cs *cs;
+	int ret;
+
+	nc = to_nand_controller(nand->base.controller);
+
+	ret = atmel_smc_nand_prepare_smcconf(nand, conf, &smcconf);
+	if (ret)
+		return ret;
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	cs = &nand->cs[csline];
+	cs->smcconf = smcconf;
+
+	if (cs->rb.type == ATMEL_NAND_NATIVE_RB)
+		cs->smcconf.timings |= ATMEL_HSMC_TIMINGS_RBNSEL(cs->rb.id);
+
+	atmel_hsmc_cs_conf_apply(nc->smc, cs->id, &cs->smcconf);
+
+	return 0;
+}
+
+static int atmel_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct atmel_nand *nand = to_atmel_nand(chip);
+	struct atmel_nand_controller *nc;
+
+	nc = to_nand_controller(nand->base.controller);
+
+	if (csline >= nand->numcs ||
+	    (csline < 0 && csline != NAND_DATA_IFACE_CHECK_ONLY))
+		return -EINVAL;
+
+	return nc->caps->ops->setup_data_interface(nand, csline, conf);
+}
+
 static void atmel_nand_init(struct atmel_nand_controller *nc,
 			    struct atmel_nand *nand)
 {
@@ -1192,6 +1489,9 @@ static void atmel_nand_init(struct atmel_nand_controller *nc,
 	chip->write_buf = atmel_nand_write_buf;
 	chip->select_chip = atmel_nand_select_chip;
 
+	if (nc->mck && nc->caps->ops->setup_data_interface)
+		chip->setup_data_interface = atmel_nand_setup_data_interface;
+
 	/* Some NANDs require a longer delay than the default one (20us). */
 	chip->chip_delay = 40;
 
@@ -1677,6 +1977,12 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 	if (nc->caps->legacy_of_bindings)
 		return 0;
 
+	nc->mck = of_clk_get(dev->parent->of_node, 0);
+	if (IS_ERR(nc->mck)) {
+		dev_err(dev, "Failed to retrieve MCK clk\n");
+		return PTR_ERR(nc->mck);
+	}
+
 	np = of_parse_phandle(dev->parent->of_node, "atmel,smc", 0);
 	if (!np) {
 		dev_err(dev, "Missing or invalid atmel,smc property\n");
@@ -1983,6 +2289,7 @@ static const struct atmel_nand_controller_ops atmel_hsmc_nc_ops = {
 	.remove = atmel_hsmc_nand_controller_remove,
 	.ecc_init = atmel_hsmc_nand_ecc_init,
 	.nand_init = atmel_hsmc_nand_init,
+	.setup_data_interface = atmel_hsmc_nand_setup_data_interface,
 };
 
 static const struct atmel_nand_controller_caps atmel_sama5_nc_caps = {
@@ -2037,7 +2344,14 @@ atmel_smc_nand_controller_remove(struct atmel_nand_controller *nc)
 	return 0;
 }
 
-static const struct atmel_nand_controller_ops atmel_smc_nc_ops = {
+/*
+ * The SMC reg layout of at91rm9200 is completely different which prevents us
+ * from re-using atmel_smc_nand_setup_data_interface() for the
+ * ->setup_data_interface() hook.
+ * At this point, there's no support for the at91rm9200 SMC IP, so we leave
+ * ->setup_data_interface() unassigned.
+ */
+static const struct atmel_nand_controller_ops at91rm9200_nc_ops = {
 	.probe = atmel_smc_nand_controller_probe,
 	.remove = atmel_smc_nand_controller_remove,
 	.ecc_init = atmel_nand_ecc_init,
@@ -2047,6 +2361,20 @@ static const struct atmel_nand_controller_ops atmel_smc_nc_ops = {
 static const struct atmel_nand_controller_caps atmel_rm9200_nc_caps = {
 	.ale_offs = BIT(21),
 	.cle_offs = BIT(22),
+	.ops = &at91rm9200_nc_ops,
+};
+
+static const struct atmel_nand_controller_ops atmel_smc_nc_ops = {
+	.probe = atmel_smc_nand_controller_probe,
+	.remove = atmel_smc_nand_controller_remove,
+	.ecc_init = atmel_nand_ecc_init,
+	.nand_init = atmel_smc_nand_init,
+	.setup_data_interface = atmel_smc_nand_setup_data_interface,
+};
+
+static const struct atmel_nand_controller_caps atmel_sam9260_nc_caps = {
+	.ale_offs = BIT(21),
+	.cle_offs = BIT(22),
 	.ops = &atmel_smc_nc_ops,
 };
 
@@ -2093,7 +2421,7 @@ static const struct of_device_id atmel_nand_controller_of_ids[] = {
 	},
 	{
 		.compatible = "atmel,at91sam9260-nand-controller",
-		.data = &atmel_rm9200_nc_caps,
+		.data = &atmel_sam9260_nc_caps,
 	},
 	{
 		.compatible = "atmel,at91sam9261-nand-controller",
@@ -2181,6 +2509,24 @@ static int atmel_nand_controller_remove(struct platform_device *pdev)
 	return nc->caps->ops->remove(nc);
 }
 
+static __maybe_unused int atmel_nand_controller_resume(struct device *dev)
+{
+	struct atmel_nand_controller *nc = dev_get_drvdata(dev);
+	struct atmel_nand *nand;
+
+	list_for_each_entry(nand, &nc->chips, node) {
+		int i;
+
+		for (i = 0; i < nand->numcs; i++)
+			nand_reset(&nand->base, i);
+	}
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(atmel_nand_controller_pm_ops, NULL,
+			 atmel_nand_controller_resume);
+
 static struct platform_driver atmel_nand_controller_driver = {
 	.driver = {
 		.name = "atmel-nand-controller",
diff --git a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
index f1da4ea88f2c..54bac5b73f0a 100644
--- a/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
+++ b/drivers/mtd/nand/bcm47xxnflash/ops_bcm4706.c
@@ -392,6 +392,8 @@ int bcm47xxnflash_ops_bcm4706_init(struct bcm47xxnflash *b47n)
 	b47n->nand_chip.read_byte = bcm47xxnflash_ops_bcm4706_read_byte;
 	b47n->nand_chip.read_buf = bcm47xxnflash_ops_bcm4706_read_buf;
 	b47n->nand_chip.write_buf = bcm47xxnflash_ops_bcm4706_write_buf;
+	b47n->nand_chip.onfi_set_features = nand_onfi_get_set_features_notsupp;
+	b47n->nand_chip.onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	nand_chip->chip_delay = 50;
 	b47n->nand_chip.bbt_options = NAND_BBT_USE_FLASH;
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index d40c32d311d8..2fd733eba0a3 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -654,6 +654,8 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	cafe->nand.read_buf = cafe_read_buf;
 	cafe->nand.write_buf = cafe_write_buf;
 	cafe->nand.select_chip = cafe_select_chip;
+	cafe->nand.onfi_set_features = nand_onfi_get_set_features_notsupp;
+	cafe->nand.onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	cafe->nand.chip_delay = 0;
 
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 531c51991e57..7b26e53b95b1 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -771,11 +771,14 @@ static int nand_davinci_probe(struct platform_device *pdev)
 			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
 			info->chip.ecc.bytes = 10;
 			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
+			info->chip.ecc.algo = NAND_ECC_BCH;
 		} else {
+			/* 1bit ecc hamming */
 			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
 			info->chip.ecc.correct = nand_davinci_correct_1bit;
 			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
 			info->chip.ecc.bytes = 3;
+			info->chip.ecc.algo = NAND_ECC_HAMMING;
 		}
 		info->chip.ecc.size = 512;
 		info->chip.ecc.strength = pdata->ecc_bits;
diff --git a/drivers/mtd/nand/denali.c b/drivers/mtd/nand/denali.c
index 16634df2e39a..d723be352148 100644
--- a/drivers/mtd/nand/denali.c
+++ b/drivers/mtd/nand/denali.c
@@ -23,50 +23,43 @@
 #include <linux/mutex.h>
 #include <linux/mtd/mtd.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 
 #include "denali.h"
 
 MODULE_LICENSE("GPL");
 
-/*
- * We define a module parameter that allows the user to override
- * the hardware and decide what timing mode should be used.
- */
-#define NAND_DEFAULT_TIMINGS	-1
+#define DENALI_NAND_NAME    "denali-nand"
 
-static int onfi_timing_mode = NAND_DEFAULT_TIMINGS;
-module_param(onfi_timing_mode, int, S_IRUGO);
-MODULE_PARM_DESC(onfi_timing_mode,
-	   "Overrides default ONFI setting. -1 indicates use default timings");
+/* Host Data/Command Interface */
+#define DENALI_HOST_ADDR	0x00
+#define DENALI_HOST_DATA	0x10
 
-#define DENALI_NAND_NAME    "denali-nand"
+#define DENALI_MAP00		(0 << 26)	/* direct access to buffer */
+#define DENALI_MAP01		(1 << 26)	/* read/write pages in PIO */
+#define DENALI_MAP10		(2 << 26)	/* high-level control plane */
+#define DENALI_MAP11		(3 << 26)	/* direct controller access */
 
-/*
- * We define a macro here that combines all interrupts this driver uses into
- * a single constant value, for convenience.
- */
-#define DENALI_IRQ_ALL	(INTR__DMA_CMD_COMP | \
-			INTR__ECC_TRANSACTION_DONE | \
-			INTR__ECC_ERR | \
-			INTR__PROGRAM_FAIL | \
-			INTR__LOAD_COMP | \
-			INTR__PROGRAM_COMP | \
-			INTR__TIME_OUT | \
-			INTR__ERASE_FAIL | \
-			INTR__RST_COMP | \
-			INTR__ERASE_COMP)
+/* MAP11 access cycle type */
+#define DENALI_MAP11_CMD	((DENALI_MAP11) | 0)	/* command cycle */
+#define DENALI_MAP11_ADDR	((DENALI_MAP11) | 1)	/* address cycle */
+#define DENALI_MAP11_DATA	((DENALI_MAP11) | 2)	/* data cycle */
 
-/*
- * indicates whether or not the internal value for the flash bank is
- * valid or not
- */
-#define CHIP_SELECT_INVALID	-1
+/* MAP10 commands */
+#define DENALI_ERASE		0x01
+
+#define DENALI_BANK(denali)	((denali)->active_bank << 24)
+
+#define DENALI_INVALID_BANK	-1
+#define DENALI_NR_BANKS		4
 
 /*
- * This macro divides two integers and rounds fractional values up
- * to the nearest integer value.
+ * The bus interface clock, clk_x, is phase aligned with the core clock.  The
+ * clk_x is an integral multiple N of the core clk.  The value N is configured
+ * at IP delivery time, and its available value is 4, 5, or 6.  We need to align
+ * to the largest value to make it work with any possible configuration.
  */
-#define CEIL_DIV(X, Y) (((X)%(Y)) ? ((X)/(Y)+1) : ((X)/(Y)))
+#define DENALI_CLK_X_MULT	6
 
 /*
  * this macro allows us to convert from an MTD structure to our own
@@ -77,339 +70,11 @@ static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd)
 	return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand);
 }
 
-/*
- * These constants are defined by the driver to enable common driver
- * configuration options.
- */
-#define SPARE_ACCESS		0x41
-#define MAIN_ACCESS		0x42
-#define MAIN_SPARE_ACCESS	0x43
-
-#define DENALI_READ	0
-#define DENALI_WRITE	0x100
-
-/*
- * this is a helper macro that allows us to
- * format the bank into the proper bits for the controller
- */
-#define BANK(x) ((x) << 24)
-
-/* forward declarations */
-static void clear_interrupts(struct denali_nand_info *denali);
-static uint32_t wait_for_irq(struct denali_nand_info *denali,
-							uint32_t irq_mask);
-static void denali_irq_enable(struct denali_nand_info *denali,
-							uint32_t int_mask);
-static uint32_t read_interrupt_status(struct denali_nand_info *denali);
-
-/*
- * Certain operations for the denali NAND controller use an indexed mode to
- * read/write data. The operation is performed by writing the address value
- * of the command to the device memory followed by the data. This function
- * abstracts this common operation.
- */
-static void index_addr(struct denali_nand_info *denali,
-				uint32_t address, uint32_t data)
-{
-	iowrite32(address, denali->flash_mem);
-	iowrite32(data, denali->flash_mem + 0x10);
-}
-
-/* Perform an indexed read of the device */
-static void index_addr_read_data(struct denali_nand_info *denali,
-				 uint32_t address, uint32_t *pdata)
-{
-	iowrite32(address, denali->flash_mem);
-	*pdata = ioread32(denali->flash_mem + 0x10);
-}
-
-/*
- * We need to buffer some data for some of the NAND core routines.
- * The operations manage buffering that data.
- */
-static void reset_buf(struct denali_nand_info *denali)
-{
-	denali->buf.head = denali->buf.tail = 0;
-}
-
-static void write_byte_to_buf(struct denali_nand_info *denali, uint8_t byte)
-{
-	denali->buf.buf[denali->buf.tail++] = byte;
-}
-
-/* reads the status of the device */
-static void read_status(struct denali_nand_info *denali)
-{
-	uint32_t cmd;
-
-	/* initialize the data buffer to store status */
-	reset_buf(denali);
-
-	cmd = ioread32(denali->flash_reg + WRITE_PROTECT);
-	if (cmd)
-		write_byte_to_buf(denali, NAND_STATUS_WP);
-	else
-		write_byte_to_buf(denali, 0);
-}
-
-/* resets a specific device connected to the core */
-static void reset_bank(struct denali_nand_info *denali)
-{
-	uint32_t irq_status;
-	uint32_t irq_mask = INTR__RST_COMP | INTR__TIME_OUT;
-
-	clear_interrupts(denali);
-
-	iowrite32(1 << denali->flash_bank, denali->flash_reg + DEVICE_RESET);
-
-	irq_status = wait_for_irq(denali, irq_mask);
-
-	if (irq_status & INTR__TIME_OUT)
-		dev_err(denali->dev, "reset bank failed.\n");
-}
-
-/* Reset the flash controller */
-static uint16_t denali_nand_reset(struct denali_nand_info *denali)
-{
-	int i;
-
-	for (i = 0; i < denali->max_banks; i++)
-		iowrite32(INTR__RST_COMP | INTR__TIME_OUT,
-		denali->flash_reg + INTR_STATUS(i));
-
-	for (i = 0; i < denali->max_banks; i++) {
-		iowrite32(1 << i, denali->flash_reg + DEVICE_RESET);
-		while (!(ioread32(denali->flash_reg + INTR_STATUS(i)) &
-			(INTR__RST_COMP | INTR__TIME_OUT)))
-			cpu_relax();
-		if (ioread32(denali->flash_reg + INTR_STATUS(i)) &
-			INTR__TIME_OUT)
-			dev_dbg(denali->dev,
-			"NAND Reset operation timed out on bank %d\n", i);
-	}
-
-	for (i = 0; i < denali->max_banks; i++)
-		iowrite32(INTR__RST_COMP | INTR__TIME_OUT,
-			  denali->flash_reg + INTR_STATUS(i));
-
-	return PASS;
-}
-
-/*
- * this routine calculates the ONFI timing values for a given mode and
- * programs the clocking register accordingly. The mode is determined by
- * the get_onfi_nand_para routine.
- */
-static void nand_onfi_timing_set(struct denali_nand_info *denali,
-								uint16_t mode)
-{
-	uint16_t Trea[6] = {40, 30, 25, 20, 20, 16};
-	uint16_t Trp[6] = {50, 25, 17, 15, 12, 10};
-	uint16_t Treh[6] = {30, 15, 15, 10, 10, 7};
-	uint16_t Trc[6] = {100, 50, 35, 30, 25, 20};
-	uint16_t Trhoh[6] = {0, 15, 15, 15, 15, 15};
-	uint16_t Trloh[6] = {0, 0, 0, 0, 5, 5};
-	uint16_t Tcea[6] = {100, 45, 30, 25, 25, 25};
-	uint16_t Tadl[6] = {200, 100, 100, 100, 70, 70};
-	uint16_t Trhw[6] = {200, 100, 100, 100, 100, 100};
-	uint16_t Trhz[6] = {200, 100, 100, 100, 100, 100};
-	uint16_t Twhr[6] = {120, 80, 80, 60, 60, 60};
-	uint16_t Tcs[6] = {70, 35, 25, 25, 20, 15};
-
-	uint16_t data_invalid_rhoh, data_invalid_rloh, data_invalid;
-	uint16_t dv_window = 0;
-	uint16_t en_lo, en_hi;
-	uint16_t acc_clks;
-	uint16_t addr_2_data, re_2_we, re_2_re, we_2_re, cs_cnt;
-
-	en_lo = CEIL_DIV(Trp[mode], CLK_X);
-	en_hi = CEIL_DIV(Treh[mode], CLK_X);
-#if ONFI_BLOOM_TIME
-	if ((en_hi * CLK_X) < (Treh[mode] + 2))
-		en_hi++;
-#endif
-
-	if ((en_lo + en_hi) * CLK_X < Trc[mode])
-		en_lo += CEIL_DIV((Trc[mode] - (en_lo + en_hi) * CLK_X), CLK_X);
-
-	if ((en_lo + en_hi) < CLK_MULTI)
-		en_lo += CLK_MULTI - en_lo - en_hi;
-
-	while (dv_window < 8) {
-		data_invalid_rhoh = en_lo * CLK_X + Trhoh[mode];
-
-		data_invalid_rloh = (en_lo + en_hi) * CLK_X + Trloh[mode];
-
-		data_invalid = data_invalid_rhoh < data_invalid_rloh ?
-					data_invalid_rhoh : data_invalid_rloh;
-
-		dv_window = data_invalid - Trea[mode];
-
-		if (dv_window < 8)
-			en_lo++;
-	}
-
-	acc_clks = CEIL_DIV(Trea[mode], CLK_X);
-
-	while (acc_clks * CLK_X - Trea[mode] < 3)
-		acc_clks++;
-
-	if (data_invalid - acc_clks * CLK_X < 2)
-		dev_warn(denali->dev, "%s, Line %d: Warning!\n",
-			 __FILE__, __LINE__);
-
-	addr_2_data = CEIL_DIV(Tadl[mode], CLK_X);
-	re_2_we = CEIL_DIV(Trhw[mode], CLK_X);
-	re_2_re = CEIL_DIV(Trhz[mode], CLK_X);
-	we_2_re = CEIL_DIV(Twhr[mode], CLK_X);
-	cs_cnt = CEIL_DIV((Tcs[mode] - Trp[mode]), CLK_X);
-	if (cs_cnt == 0)
-		cs_cnt = 1;
-
-	if (Tcea[mode]) {
-		while (cs_cnt * CLK_X + Trea[mode] < Tcea[mode])
-			cs_cnt++;
-	}
-
-#if MODE5_WORKAROUND
-	if (mode == 5)
-		acc_clks = 5;
-#endif
-
-	/* Sighting 3462430: Temporary hack for MT29F128G08CJABAWP:B */
-	if (ioread32(denali->flash_reg + MANUFACTURER_ID) == 0 &&
-		ioread32(denali->flash_reg + DEVICE_ID) == 0x88)
-		acc_clks = 6;
-
-	iowrite32(acc_clks, denali->flash_reg + ACC_CLKS);
-	iowrite32(re_2_we, denali->flash_reg + RE_2_WE);
-	iowrite32(re_2_re, denali->flash_reg + RE_2_RE);
-	iowrite32(we_2_re, denali->flash_reg + WE_2_RE);
-	iowrite32(addr_2_data, denali->flash_reg + ADDR_2_DATA);
-	iowrite32(en_lo, denali->flash_reg + RDWR_EN_LO_CNT);
-	iowrite32(en_hi, denali->flash_reg + RDWR_EN_HI_CNT);
-	iowrite32(cs_cnt, denali->flash_reg + CS_SETUP_CNT);
-}
-
-/* queries the NAND device to see what ONFI modes it supports. */
-static uint16_t get_onfi_nand_para(struct denali_nand_info *denali)
+static void denali_host_write(struct denali_nand_info *denali,
+			      uint32_t addr, uint32_t data)
 {
-	int i;
-
-	/*
-	 * we needn't to do a reset here because driver has already
-	 * reset all the banks before
-	 */
-	if (!(ioread32(denali->flash_reg + ONFI_TIMING_MODE) &
-		ONFI_TIMING_MODE__VALUE))
-		return FAIL;
-
-	for (i = 5; i > 0; i--) {
-		if (ioread32(denali->flash_reg + ONFI_TIMING_MODE) &
-			(0x01 << i))
-			break;
-	}
-
-	nand_onfi_timing_set(denali, i);
-
-	/*
-	 * By now, all the ONFI devices we know support the page cache
-	 * rw feature. So here we enable the pipeline_rw_ahead feature
-	 */
-	/* iowrite32(1, denali->flash_reg + CACHE_WRITE_ENABLE); */
-	/* iowrite32(1, denali->flash_reg + CACHE_READ_ENABLE);  */
-
-	return PASS;
-}
-
-static void get_samsung_nand_para(struct denali_nand_info *denali,
-							uint8_t device_id)
-{
-	if (device_id == 0xd3) { /* Samsung K9WAG08U1A */
-		/* Set timing register values according to datasheet */
-		iowrite32(5, denali->flash_reg + ACC_CLKS);
-		iowrite32(20, denali->flash_reg + RE_2_WE);
-		iowrite32(12, denali->flash_reg + WE_2_RE);
-		iowrite32(14, denali->flash_reg + ADDR_2_DATA);
-		iowrite32(3, denali->flash_reg + RDWR_EN_LO_CNT);
-		iowrite32(2, denali->flash_reg + RDWR_EN_HI_CNT);
-		iowrite32(2, denali->flash_reg + CS_SETUP_CNT);
-	}
-}
-
-static void get_toshiba_nand_para(struct denali_nand_info *denali)
-{
-	/*
-	 * Workaround to fix a controller bug which reports a wrong
-	 * spare area size for some kind of Toshiba NAND device
-	 */
-	if ((ioread32(denali->flash_reg + DEVICE_MAIN_AREA_SIZE) == 4096) &&
-		(ioread32(denali->flash_reg + DEVICE_SPARE_AREA_SIZE) == 64))
-		iowrite32(216, denali->flash_reg + DEVICE_SPARE_AREA_SIZE);
-}
-
-static void get_hynix_nand_para(struct denali_nand_info *denali,
-							uint8_t device_id)
-{
-	switch (device_id) {
-	case 0xD5: /* Hynix H27UAG8T2A, H27UBG8U5A or H27UCG8VFA */
-	case 0xD7: /* Hynix H27UDG8VEM, H27UCG8UDM or H27UCG8V5A */
-		iowrite32(128, denali->flash_reg + PAGES_PER_BLOCK);
-		iowrite32(4096, denali->flash_reg + DEVICE_MAIN_AREA_SIZE);
-		iowrite32(224, denali->flash_reg + DEVICE_SPARE_AREA_SIZE);
-		iowrite32(0, denali->flash_reg + DEVICE_WIDTH);
-		break;
-	default:
-		dev_warn(denali->dev,
-			 "Unknown Hynix NAND (Device ID: 0x%x).\n"
-			 "Will use default parameter values instead.\n",
-			 device_id);
-	}
-}
-
-/*
- * determines how many NAND chips are connected to the controller. Note for
- * Intel CE4100 devices we don't support more than one device.
- */
-static void find_valid_banks(struct denali_nand_info *denali)
-{
-	uint32_t id[denali->max_banks];
-	int i;
-
-	denali->total_used_banks = 1;
-	for (i = 0; i < denali->max_banks; i++) {
-		index_addr(denali, MODE_11 | (i << 24) | 0, 0x90);
-		index_addr(denali, MODE_11 | (i << 24) | 1, 0);
-		index_addr_read_data(denali, MODE_11 | (i << 24) | 2, &id[i]);
-
-		dev_dbg(denali->dev,
-			"Return 1st ID for bank[%d]: %x\n", i, id[i]);
-
-		if (i == 0) {
-			if (!(id[i] & 0x0ff))
-				break; /* WTF? */
-		} else {
-			if ((id[i] & 0x0ff) == (id[0] & 0x0ff))
-				denali->total_used_banks++;
-			else
-				break;
-		}
-	}
-
-	if (denali->platform == INTEL_CE4100) {
-		/*
-		 * Platform limitations of the CE4100 device limit
-		 * users to a single chip solution for NAND.
-		 * Multichip support is not enabled.
-		 */
-		if (denali->total_used_banks != 1) {
-			dev_err(denali->dev,
-				"Sorry, Intel CE4100 only supports a single NAND device.\n");
-			BUG();
-		}
-	}
-	dev_dbg(denali->dev,
-		"denali->total_used_banks: %d\n", denali->total_used_banks);
+	iowrite32(addr, denali->host + DENALI_HOST_ADDR);
+	iowrite32(data, denali->host + DENALI_HOST_DATA);
 }
 
 /*
@@ -418,7 +83,7 @@ static void find_valid_banks(struct denali_nand_info *denali)
  */
 static void detect_max_banks(struct denali_nand_info *denali)
 {
-	uint32_t features = ioread32(denali->flash_reg + FEATURES);
+	uint32_t features = ioread32(denali->reg + FEATURES);
 
 	denali->max_banks = 1 << (features & FEATURES__N_BANKS);
 
@@ -427,227 +92,120 @@ static void detect_max_banks(struct denali_nand_info *denali)
 		denali->max_banks <<= 1;
 }
 
-static uint16_t denali_nand_timing_set(struct denali_nand_info *denali)
+static void denali_enable_irq(struct denali_nand_info *denali)
 {
-	uint16_t status = PASS;
-	uint32_t id_bytes[8], addr;
-	uint8_t maf_id, device_id;
 	int i;
 
-	/*
-	 * Use read id method to get device ID and other params.
-	 * For some NAND chips, controller can't report the correct
-	 * device ID by reading from DEVICE_ID register
-	 */
-	addr = MODE_11 | BANK(denali->flash_bank);
-	index_addr(denali, addr | 0, 0x90);
-	index_addr(denali, addr | 1, 0);
-	for (i = 0; i < 8; i++)
-		index_addr_read_data(denali, addr | 2, &id_bytes[i]);
-	maf_id = id_bytes[0];
-	device_id = id_bytes[1];
-
-	if (ioread32(denali->flash_reg + ONFI_DEVICE_NO_OF_LUNS) &
-		ONFI_DEVICE_NO_OF_LUNS__ONFI_DEVICE) { /* ONFI 1.0 NAND */
-		if (FAIL == get_onfi_nand_para(denali))
-			return FAIL;
-	} else if (maf_id == 0xEC) { /* Samsung NAND */
-		get_samsung_nand_para(denali, device_id);
-	} else if (maf_id == 0x98) { /* Toshiba NAND */
-		get_toshiba_nand_para(denali);
-	} else if (maf_id == 0xAD) { /* Hynix NAND */
-		get_hynix_nand_para(denali, device_id);
-	}
-
-	dev_info(denali->dev,
-			"Dump timing register values:\n"
-			"acc_clks: %d, re_2_we: %d, re_2_re: %d\n"
-			"we_2_re: %d, addr_2_data: %d, rdwr_en_lo_cnt: %d\n"
-			"rdwr_en_hi_cnt: %d, cs_setup_cnt: %d\n",
-			ioread32(denali->flash_reg + ACC_CLKS),
-			ioread32(denali->flash_reg + RE_2_WE),
-			ioread32(denali->flash_reg + RE_2_RE),
-			ioread32(denali->flash_reg + WE_2_RE),
-			ioread32(denali->flash_reg + ADDR_2_DATA),
-			ioread32(denali->flash_reg + RDWR_EN_LO_CNT),
-			ioread32(denali->flash_reg + RDWR_EN_HI_CNT),
-			ioread32(denali->flash_reg + CS_SETUP_CNT));
-
-	find_valid_banks(denali);
-
-	/*
-	 * If the user specified to override the default timings
-	 * with a specific ONFI mode, we apply those changes here.
-	 */
-	if (onfi_timing_mode != NAND_DEFAULT_TIMINGS)
-		nand_onfi_timing_set(denali, onfi_timing_mode);
-
-	return status;
+	for (i = 0; i < DENALI_NR_BANKS; i++)
+		iowrite32(U32_MAX, denali->reg + INTR_EN(i));
+	iowrite32(GLOBAL_INT_EN_FLAG, denali->reg + GLOBAL_INT_ENABLE);
 }
 
-static void denali_set_intr_modes(struct denali_nand_info *denali,
-					uint16_t INT_ENABLE)
+static void denali_disable_irq(struct denali_nand_info *denali)
 {
-	if (INT_ENABLE)
-		iowrite32(1, denali->flash_reg + GLOBAL_INT_ENABLE);
-	else
-		iowrite32(0, denali->flash_reg + GLOBAL_INT_ENABLE);
-}
-
-/*
- * validation function to verify that the controlling software is making
- * a valid request
- */
-static inline bool is_flash_bank_valid(int flash_bank)
-{
-	return flash_bank >= 0 && flash_bank < 4;
-}
-
-static void denali_irq_init(struct denali_nand_info *denali)
-{
-	uint32_t int_mask;
 	int i;
 
-	/* Disable global interrupts */
-	denali_set_intr_modes(denali, false);
-
-	int_mask = DENALI_IRQ_ALL;
-
-	/* Clear all status bits */
-	for (i = 0; i < denali->max_banks; ++i)
-		iowrite32(0xFFFF, denali->flash_reg + INTR_STATUS(i));
-
-	denali_irq_enable(denali, int_mask);
+	for (i = 0; i < DENALI_NR_BANKS; i++)
+		iowrite32(0, denali->reg + INTR_EN(i));
+	iowrite32(0, denali->reg + GLOBAL_INT_ENABLE);
 }
 
-static void denali_irq_cleanup(int irqnum, struct denali_nand_info *denali)
+static void denali_clear_irq(struct denali_nand_info *denali,
+			     int bank, uint32_t irq_status)
 {
-	denali_set_intr_modes(denali, false);
+	/* write one to clear bits */
+	iowrite32(irq_status, denali->reg + INTR_STATUS(bank));
 }
 
-static void denali_irq_enable(struct denali_nand_info *denali,
-							uint32_t int_mask)
+static void denali_clear_irq_all(struct denali_nand_info *denali)
 {
 	int i;
 
-	for (i = 0; i < denali->max_banks; ++i)
-		iowrite32(int_mask, denali->flash_reg + INTR_EN(i));
+	for (i = 0; i < DENALI_NR_BANKS; i++)
+		denali_clear_irq(denali, i, U32_MAX);
 }
 
-/*
- * This function only returns when an interrupt that this driver cares about
- * occurs. This is to reduce the overhead of servicing interrupts
- */
-static inline uint32_t denali_irq_detected(struct denali_nand_info *denali)
+static irqreturn_t denali_isr(int irq, void *dev_id)
 {
-	return read_interrupt_status(denali) & DENALI_IRQ_ALL;
-}
+	struct denali_nand_info *denali = dev_id;
+	irqreturn_t ret = IRQ_NONE;
+	uint32_t irq_status;
+	int i;
 
-/* Interrupts are cleared by writing a 1 to the appropriate status bit */
-static inline void clear_interrupt(struct denali_nand_info *denali,
-							uint32_t irq_mask)
-{
-	uint32_t intr_status_reg;
+	spin_lock(&denali->irq_lock);
 
-	intr_status_reg = INTR_STATUS(denali->flash_bank);
+	for (i = 0; i < DENALI_NR_BANKS; i++) {
+		irq_status = ioread32(denali->reg + INTR_STATUS(i));
+		if (irq_status)
+			ret = IRQ_HANDLED;
 
-	iowrite32(irq_mask, denali->flash_reg + intr_status_reg);
-}
+		denali_clear_irq(denali, i, irq_status);
 
-static void clear_interrupts(struct denali_nand_info *denali)
-{
-	uint32_t status;
+		if (i != denali->active_bank)
+			continue;
 
-	spin_lock_irq(&denali->irq_lock);
+		denali->irq_status |= irq_status;
 
-	status = read_interrupt_status(denali);
-	clear_interrupt(denali, status);
+		if (denali->irq_status & denali->irq_mask)
+			complete(&denali->complete);
+	}
+
+	spin_unlock(&denali->irq_lock);
 
-	denali->irq_status = 0x0;
-	spin_unlock_irq(&denali->irq_lock);
+	return ret;
 }
 
-static uint32_t read_interrupt_status(struct denali_nand_info *denali)
+static void denali_reset_irq(struct denali_nand_info *denali)
 {
-	uint32_t intr_status_reg;
-
-	intr_status_reg = INTR_STATUS(denali->flash_bank);
+	unsigned long flags;
 
-	return ioread32(denali->flash_reg + intr_status_reg);
+	spin_lock_irqsave(&denali->irq_lock, flags);
+	denali->irq_status = 0;
+	denali->irq_mask = 0;
+	spin_unlock_irqrestore(&denali->irq_lock, flags);
 }
 
-/*
- * This is the interrupt service routine. It handles all interrupts
- * sent to this device. Note that on CE4100, this is a shared interrupt.
- */
-static irqreturn_t denali_isr(int irq, void *dev_id)
+static uint32_t denali_wait_for_irq(struct denali_nand_info *denali,
+				    uint32_t irq_mask)
 {
-	struct denali_nand_info *denali = dev_id;
+	unsigned long time_left, flags;
 	uint32_t irq_status;
-	irqreturn_t result = IRQ_NONE;
 
-	spin_lock(&denali->irq_lock);
+	spin_lock_irqsave(&denali->irq_lock, flags);
 
-	/* check to see if a valid NAND chip has been selected. */
-	if (is_flash_bank_valid(denali->flash_bank)) {
-		/*
-		 * check to see if controller generated the interrupt,
-		 * since this is a shared interrupt
-		 */
-		irq_status = denali_irq_detected(denali);
-		if (irq_status != 0) {
-			/* handle interrupt */
-			/* first acknowledge it */
-			clear_interrupt(denali, irq_status);
-			/*
-			 * store the status in the device context for someone
-			 * to read
-			 */
-			denali->irq_status |= irq_status;
-			/* notify anyone who cares that it happened */
-			complete(&denali->complete);
-			/* tell the OS that we've handled this */
-			result = IRQ_HANDLED;
-		}
+	irq_status = denali->irq_status;
+
+	if (irq_mask & irq_status) {
+		/* return immediately if the IRQ has already happened. */
+		spin_unlock_irqrestore(&denali->irq_lock, flags);
+		return irq_status;
 	}
-	spin_unlock(&denali->irq_lock);
-	return result;
-}
 
-static uint32_t wait_for_irq(struct denali_nand_info *denali, uint32_t irq_mask)
-{
-	unsigned long comp_res;
-	uint32_t intr_status;
-	unsigned long timeout = msecs_to_jiffies(1000);
+	denali->irq_mask = irq_mask;
+	reinit_completion(&denali->complete);
+	spin_unlock_irqrestore(&denali->irq_lock, flags);
 
-	do {
-		comp_res =
-			wait_for_completion_timeout(&denali->complete, timeout);
-		spin_lock_irq(&denali->irq_lock);
-		intr_status = denali->irq_status;
-
-		if (intr_status & irq_mask) {
-			denali->irq_status &= ~irq_mask;
-			spin_unlock_irq(&denali->irq_lock);
-			/* our interrupt was detected */
-			break;
-		}
+	time_left = wait_for_completion_timeout(&denali->complete,
+						msecs_to_jiffies(1000));
+	if (!time_left) {
+		dev_err(denali->dev, "timeout while waiting for irq 0x%x\n",
+			denali->irq_mask);
+		return 0;
+	}
 
-		/*
-		 * these are not the interrupts you are looking for -
-		 * need to wait again
-		 */
-		spin_unlock_irq(&denali->irq_lock);
-	} while (comp_res != 0);
+	return denali->irq_status;
+}
+
+static uint32_t denali_check_irq(struct denali_nand_info *denali)
+{
+	unsigned long flags;
+	uint32_t irq_status;
 
-	if (comp_res == 0) {
-		/* timeout */
-		pr_err("timeout occurred, status = 0x%x, mask = 0x%x\n",
-				intr_status, irq_mask);
+	spin_lock_irqsave(&denali->irq_lock, flags);
+	irq_status = denali->irq_status;
+	spin_unlock_irqrestore(&denali->irq_lock, flags);
 
-		intr_status = 0;
-	}
-	return intr_status;
+	return irq_status;
 }
 
 /*
@@ -664,153 +222,111 @@ static void setup_ecc_for_xfer(struct denali_nand_info *denali, bool ecc_en,
 	transfer_spare_flag = transfer_spare ? TRANSFER_SPARE_REG__FLAG : 0;
 
 	/* Enable spare area/ECC per user's request. */
-	iowrite32(ecc_en_flag, denali->flash_reg + ECC_ENABLE);
-	iowrite32(transfer_spare_flag, denali->flash_reg + TRANSFER_SPARE_REG);
+	iowrite32(ecc_en_flag, denali->reg + ECC_ENABLE);
+	iowrite32(transfer_spare_flag, denali->reg + TRANSFER_SPARE_REG);
 }
 
-/*
- * sends a pipeline command operation to the controller. See the Denali NAND
- * controller's user guide for more information (section 4.2.3.6).
- */
-static int denali_send_pipeline_cmd(struct denali_nand_info *denali,
-				    bool ecc_en, bool transfer_spare,
-				    int access_type, int op)
+static void denali_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
-	int status = PASS;
-	uint32_t addr, cmd;
-
-	setup_ecc_for_xfer(denali, ecc_en, transfer_spare);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	int i;
 
-	clear_interrupts(denali);
+	iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali),
+		  denali->host + DENALI_HOST_ADDR);
 
-	addr = BANK(denali->flash_bank) | denali->page;
+	for (i = 0; i < len; i++)
+		buf[i] = ioread32(denali->host + DENALI_HOST_DATA);
+}
 
-	if (op == DENALI_WRITE && access_type != SPARE_ACCESS) {
-		cmd = MODE_01 | addr;
-		iowrite32(cmd, denali->flash_mem);
-	} else if (op == DENALI_WRITE && access_type == SPARE_ACCESS) {
-		/* read spare area */
-		cmd = MODE_10 | addr;
-		index_addr(denali, cmd, access_type);
+static void denali_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
+{
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	int i;
 
-		cmd = MODE_01 | addr;
-		iowrite32(cmd, denali->flash_mem);
-	} else if (op == DENALI_READ) {
-		/* setup page read request for access type */
-		cmd = MODE_10 | addr;
-		index_addr(denali, cmd, access_type);
+	iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali),
+		  denali->host + DENALI_HOST_ADDR);
 
-		cmd = MODE_01 | addr;
-		iowrite32(cmd, denali->flash_mem);
-	}
-	return status;
+	for (i = 0; i < len; i++)
+		iowrite32(buf[i], denali->host + DENALI_HOST_DATA);
 }
 
-/* helper function that simply writes a buffer to the flash */
-static int write_data_to_flash_mem(struct denali_nand_info *denali,
-				   const uint8_t *buf, int len)
+static void denali_read_buf16(struct mtd_info *mtd, uint8_t *buf, int len)
 {
-	uint32_t *buf32;
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	uint16_t *buf16 = (uint16_t *)buf;
 	int i;
 
-	/*
-	 * verify that the len is a multiple of 4.
-	 * see comment in read_data_from_flash_mem()
-	 */
-	BUG_ON((len % 4) != 0);
+	iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali),
+		  denali->host + DENALI_HOST_ADDR);
 
-	/* write the data to the flash memory */
-	buf32 = (uint32_t *)buf;
-	for (i = 0; i < len / 4; i++)
-		iowrite32(*buf32++, denali->flash_mem + 0x10);
-	return i * 4; /* intent is to return the number of bytes read */
+	for (i = 0; i < len / 2; i++)
+		buf16[i] = ioread32(denali->host + DENALI_HOST_DATA);
 }
 
-/* helper function that simply reads a buffer from the flash */
-static int read_data_from_flash_mem(struct denali_nand_info *denali,
-				    uint8_t *buf, int len)
+static void denali_write_buf16(struct mtd_info *mtd, const uint8_t *buf,
+			       int len)
 {
-	uint32_t *buf32;
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	const uint16_t *buf16 = (const uint16_t *)buf;
 	int i;
 
-	/*
-	 * we assume that len will be a multiple of 4, if not it would be nice
-	 * to know about it ASAP rather than have random failures...
-	 * This assumption is based on the fact that this function is designed
-	 * to be used to read flash pages, which are typically multiples of 4.
-	 */
-	BUG_ON((len % 4) != 0);
+	iowrite32(DENALI_MAP11_DATA | DENALI_BANK(denali),
+		  denali->host + DENALI_HOST_ADDR);
 
-	/* transfer the data from the flash */
-	buf32 = (uint32_t *)buf;
-	for (i = 0; i < len / 4; i++)
-		*buf32++ = ioread32(denali->flash_mem + 0x10);
-	return i * 4; /* intent is to return the number of bytes read */
+	for (i = 0; i < len / 2; i++)
+		iowrite32(buf16[i], denali->host + DENALI_HOST_DATA);
 }
 
-/* writes OOB data to the device */
-static int write_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
+static uint8_t denali_read_byte(struct mtd_info *mtd)
 {
-	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint32_t irq_status;
-	uint32_t irq_mask = INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL;
-	int status = 0;
+	uint8_t byte;
 
-	denali->page = page;
+	denali_read_buf(mtd, &byte, 1);
 
-	if (denali_send_pipeline_cmd(denali, false, false, SPARE_ACCESS,
-							DENALI_WRITE) == PASS) {
-		write_data_to_flash_mem(denali, buf, mtd->oobsize);
+	return byte;
+}
 
-		/* wait for operation to complete */
-		irq_status = wait_for_irq(denali, irq_mask);
+static void denali_write_byte(struct mtd_info *mtd, uint8_t byte)
+{
+	denali_write_buf(mtd, &byte, 1);
+}
 
-		if (irq_status == 0) {
-			dev_err(denali->dev, "OOB write failed\n");
-			status = -EIO;
-		}
-	} else {
-		dev_err(denali->dev, "unable to send pipeline command\n");
-		status = -EIO;
-	}
-	return status;
+static uint16_t denali_read_word(struct mtd_info *mtd)
+{
+	uint16_t word;
+
+	denali_read_buf16(mtd, (uint8_t *)&word, 2);
+
+	return word;
 }
 
-/* reads OOB data from the device */
-static void read_oob_data(struct mtd_info *mtd, uint8_t *buf, int page)
+static void denali_cmd_ctrl(struct mtd_info *mtd, int dat, unsigned int ctrl)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint32_t irq_mask = INTR__LOAD_COMP;
-	uint32_t irq_status, addr, cmd;
+	uint32_t type;
 
-	denali->page = page;
+	if (ctrl & NAND_CLE)
+		type = DENALI_MAP11_CMD;
+	else if (ctrl & NAND_ALE)
+		type = DENALI_MAP11_ADDR;
+	else
+		return;
 
-	if (denali_send_pipeline_cmd(denali, false, true, SPARE_ACCESS,
-							DENALI_READ) == PASS) {
-		read_data_from_flash_mem(denali, buf, mtd->oobsize);
+	/*
+	 * Some commands are followed by chip->dev_ready or chip->waitfunc.
+	 * irq_status must be cleared here to catch the R/B# interrupt later.
+	 */
+	if (ctrl & NAND_CTRL_CHANGE)
+		denali_reset_irq(denali);
 
-		/*
-		 * wait for command to be accepted
-		 * can always use status0 bit as the
-		 * mask is identical for each bank.
-		 */
-		irq_status = wait_for_irq(denali, irq_mask);
+	denali_host_write(denali, DENALI_BANK(denali) | type, dat);
+}
 
-		if (irq_status == 0)
-			dev_err(denali->dev, "page on OOB timeout %d\n",
-					denali->page);
+static int denali_dev_ready(struct mtd_info *mtd)
+{
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
 
-		/*
-		 * We set the device back to MAIN_ACCESS here as I observed
-		 * instability with the controller if you do a block erase
-		 * and the last transaction was a SPARE_ACCESS. Block erase
-		 * is reliable (according to the MTD test infrastructure)
-		 * if you are in MAIN_ACCESS.
-		 */
-		addr = BANK(denali->flash_bank) | denali->page;
-		cmd = MODE_10 | addr;
-		index_addr(denali, cmd, MAIN_ACCESS);
-	}
+	return !!(denali_check_irq(denali) & INTR__INT_ACT);
 }
 
 static int denali_check_erased_page(struct mtd_info *mtd,
@@ -856,11 +372,11 @@ static int denali_hw_ecc_fixup(struct mtd_info *mtd,
 			       unsigned long *uncor_ecc_flags)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
-	int bank = denali->flash_bank;
+	int bank = denali->active_bank;
 	uint32_t ecc_cor;
 	unsigned int max_bitflips;
 
-	ecc_cor = ioread32(denali->flash_reg + ECC_COR_INFO(bank));
+	ecc_cor = ioread32(denali->reg + ECC_COR_INFO(bank));
 	ecc_cor >>= ECC_COR_INFO__SHIFT(bank);
 
 	if (ecc_cor & ECC_COR_INFO__UNCOR_ERR) {
@@ -886,8 +402,6 @@ static int denali_hw_ecc_fixup(struct mtd_info *mtd,
 	return max_bitflips;
 }
 
-#define ECC_SECTOR_SIZE 512
-
 #define ECC_SECTOR(x)	(((x) & ECC_ERROR_ADDRESS__SECTOR_NR) >> 12)
 #define ECC_BYTE(x)	(((x) & ECC_ERROR_ADDRESS__OFFSET))
 #define ECC_CORRECTION_VALUE(x) ((x) & ERR_CORRECTION_INFO__BYTEMASK)
@@ -899,22 +413,23 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd,
 			       struct denali_nand_info *denali,
 			       unsigned long *uncor_ecc_flags, uint8_t *buf)
 {
+	unsigned int ecc_size = denali->nand.ecc.size;
 	unsigned int bitflips = 0;
 	unsigned int max_bitflips = 0;
 	uint32_t err_addr, err_cor_info;
 	unsigned int err_byte, err_sector, err_device;
 	uint8_t err_cor_value;
 	unsigned int prev_sector = 0;
+	uint32_t irq_status;
 
-	/* read the ECC errors. we'll ignore them for now */
-	denali_set_intr_modes(denali, false);
+	denali_reset_irq(denali);
 
 	do {
-		err_addr = ioread32(denali->flash_reg + ECC_ERROR_ADDRESS);
+		err_addr = ioread32(denali->reg + ECC_ERROR_ADDRESS);
 		err_sector = ECC_SECTOR(err_addr);
 		err_byte = ECC_BYTE(err_addr);
 
-		err_cor_info = ioread32(denali->flash_reg + ERR_CORRECTION_INFO);
+		err_cor_info = ioread32(denali->reg + ERR_CORRECTION_INFO);
 		err_cor_value = ECC_CORRECTION_VALUE(err_cor_info);
 		err_device = ECC_ERR_DEVICE(err_cor_info);
 
@@ -928,9 +443,9 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd,
 			 * an erased sector.
 			 */
 			*uncor_ecc_flags |= BIT(err_sector);
-		} else if (err_byte < ECC_SECTOR_SIZE) {
+		} else if (err_byte < ecc_size) {
 			/*
-			 * If err_byte is larger than ECC_SECTOR_SIZE, means error
+			 * If err_byte is larger than ecc_size, means error
 			 * happened in OOB, so we ignore it. It's no need for
 			 * us to correct it err_device is represented the NAND
 			 * error bits are happened in if there are more than
@@ -939,8 +454,8 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd,
 			int offset;
 			unsigned int flips_in_byte;
 
-			offset = (err_sector * ECC_SECTOR_SIZE + err_byte) *
-						denali->devnum + err_device;
+			offset = (err_sector * ecc_size + err_byte) *
+					denali->devs_per_cs + err_device;
 
 			/* correct the ECC error */
 			flips_in_byte = hweight8(buf[offset] ^ err_cor_value);
@@ -959,10 +474,9 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd,
 	 * ECC_TRANSACTION_DONE interrupt, so here just wait for
 	 * a while for this interrupt
 	 */
-	while (!(read_interrupt_status(denali) & INTR__ECC_TRANSACTION_DONE))
-		cpu_relax();
-	clear_interrupts(denali);
-	denali_set_intr_modes(denali, true);
+	irq_status = denali_wait_for_irq(denali, INTR__ECC_TRANSACTION_DONE);
+	if (!(irq_status & INTR__ECC_TRANSACTION_DONE))
+		return -EIO;
 
 	return max_bitflips;
 }
@@ -970,17 +484,17 @@ static int denali_sw_ecc_fixup(struct mtd_info *mtd,
 /* programs the controller to either enable/disable DMA transfers */
 static void denali_enable_dma(struct denali_nand_info *denali, bool en)
 {
-	iowrite32(en ? DMA_ENABLE__FLAG : 0, denali->flash_reg + DMA_ENABLE);
-	ioread32(denali->flash_reg + DMA_ENABLE);
+	iowrite32(en ? DMA_ENABLE__FLAG : 0, denali->reg + DMA_ENABLE);
+	ioread32(denali->reg + DMA_ENABLE);
 }
 
-static void denali_setup_dma64(struct denali_nand_info *denali, int op)
+static void denali_setup_dma64(struct denali_nand_info *denali,
+			       dma_addr_t dma_addr, int page, int write)
 {
 	uint32_t mode;
 	const int page_count = 1;
-	uint64_t addr = denali->buf.dma_buf;
 
-	mode = MODE_10 | BANK(denali->flash_bank) | denali->page;
+	mode = DENALI_MAP10 | DENALI_BANK(denali) | page;
 
 	/* DMA is a three step process */
 
@@ -988,191 +502,354 @@ static void denali_setup_dma64(struct denali_nand_info *denali, int op)
 	 * 1. setup transfer type, interrupt when complete,
 	 *    burst len = 64 bytes, the number of pages
 	 */
-	index_addr(denali, mode, 0x01002000 | (64 << 16) | op | page_count);
+	denali_host_write(denali, mode,
+			  0x01002000 | (64 << 16) | (write << 8) | page_count);
 
 	/* 2. set memory low address */
-	index_addr(denali, mode, addr);
+	denali_host_write(denali, mode, dma_addr);
 
 	/* 3. set memory high address */
-	index_addr(denali, mode, addr >> 32);
+	denali_host_write(denali, mode, (uint64_t)dma_addr >> 32);
 }
 
-static void denali_setup_dma32(struct denali_nand_info *denali, int op)
+static void denali_setup_dma32(struct denali_nand_info *denali,
+			       dma_addr_t dma_addr, int page, int write)
 {
 	uint32_t mode;
 	const int page_count = 1;
-	uint32_t addr = denali->buf.dma_buf;
 
-	mode = MODE_10 | BANK(denali->flash_bank);
+	mode = DENALI_MAP10 | DENALI_BANK(denali);
 
 	/* DMA is a four step process */
 
 	/* 1. setup transfer type and # of pages */
-	index_addr(denali, mode | denali->page, 0x2000 | op | page_count);
+	denali_host_write(denali, mode | page,
+			  0x2000 | (write << 8) | page_count);
 
 	/* 2. set memory high address bits 23:8 */
-	index_addr(denali, mode | ((addr >> 16) << 8), 0x2200);
+	denali_host_write(denali, mode | ((dma_addr >> 16) << 8), 0x2200);
 
 	/* 3. set memory low address bits 23:8 */
-	index_addr(denali, mode | ((addr & 0xffff) << 8), 0x2300);
+	denali_host_write(denali, mode | ((dma_addr & 0xffff) << 8), 0x2300);
 
 	/* 4. interrupt when complete, burst len = 64 bytes */
-	index_addr(denali, mode | 0x14000, 0x2400);
+	denali_host_write(denali, mode | 0x14000, 0x2400);
 }
 
-static void denali_setup_dma(struct denali_nand_info *denali, int op)
+static void denali_setup_dma(struct denali_nand_info *denali,
+			     dma_addr_t dma_addr, int page, int write)
 {
 	if (denali->caps & DENALI_CAP_DMA_64BIT)
-		denali_setup_dma64(denali, op);
+		denali_setup_dma64(denali, dma_addr, page, write);
 	else
-		denali_setup_dma32(denali, op);
+		denali_setup_dma32(denali, dma_addr, page, write);
 }
 
-/*
- * writes a page. user specifies type, and this function handles the
- * configuration details.
- */
-static int write_page(struct mtd_info *mtd, struct nand_chip *chip,
-			const uint8_t *buf, bool raw_xfer)
+static int denali_pio_read(struct denali_nand_info *denali, void *buf,
+			   size_t size, int page, int raw)
 {
-	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dma_addr_t addr = denali->buf.dma_buf;
-	size_t size = mtd->writesize + mtd->oobsize;
+	uint32_t addr = DENALI_BANK(denali) | page;
+	uint32_t *buf32 = (uint32_t *)buf;
+	uint32_t irq_status, ecc_err_mask;
+	int i;
+
+	if (denali->caps & DENALI_CAP_HW_ECC_FIXUP)
+		ecc_err_mask = INTR__ECC_UNCOR_ERR;
+	else
+		ecc_err_mask = INTR__ECC_ERR;
+
+	denali_reset_irq(denali);
+
+	iowrite32(DENALI_MAP01 | addr, denali->host + DENALI_HOST_ADDR);
+	for (i = 0; i < size / 4; i++)
+		*buf32++ = ioread32(denali->host + DENALI_HOST_DATA);
+
+	irq_status = denali_wait_for_irq(denali, INTR__PAGE_XFER_INC);
+	if (!(irq_status & INTR__PAGE_XFER_INC))
+		return -EIO;
+
+	if (irq_status & INTR__ERASED_PAGE)
+		memset(buf, 0xff, size);
+
+	return irq_status & ecc_err_mask ? -EBADMSG : 0;
+}
+
+static int denali_pio_write(struct denali_nand_info *denali,
+			    const void *buf, size_t size, int page, int raw)
+{
+	uint32_t addr = DENALI_BANK(denali) | page;
+	const uint32_t *buf32 = (uint32_t *)buf;
 	uint32_t irq_status;
-	uint32_t irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL;
+	int i;
 
-	/*
-	 * if it is a raw xfer, we want to disable ecc and send the spare area.
-	 * !raw_xfer - enable ecc
-	 * raw_xfer - transfer spare
-	 */
-	setup_ecc_for_xfer(denali, !raw_xfer, raw_xfer);
+	denali_reset_irq(denali);
 
-	/* copy buffer into DMA buffer */
-	memcpy(denali->buf.buf, buf, mtd->writesize);
+	iowrite32(DENALI_MAP01 | addr, denali->host + DENALI_HOST_ADDR);
+	for (i = 0; i < size / 4; i++)
+		iowrite32(*buf32++, denali->host + DENALI_HOST_DATA);
 
-	if (raw_xfer) {
-		/* transfer the data to the spare area */
-		memcpy(denali->buf.buf + mtd->writesize,
-			chip->oob_poi,
-			mtd->oobsize);
+	irq_status = denali_wait_for_irq(denali,
+				INTR__PROGRAM_COMP | INTR__PROGRAM_FAIL);
+	if (!(irq_status & INTR__PROGRAM_COMP))
+		return -EIO;
+
+	return 0;
+}
+
+static int denali_pio_xfer(struct denali_nand_info *denali, void *buf,
+			   size_t size, int page, int raw, int write)
+{
+	if (write)
+		return denali_pio_write(denali, buf, size, page, raw);
+	else
+		return denali_pio_read(denali, buf, size, page, raw);
+}
+
+static int denali_dma_xfer(struct denali_nand_info *denali, void *buf,
+			   size_t size, int page, int raw, int write)
+{
+	dma_addr_t dma_addr;
+	uint32_t irq_mask, irq_status, ecc_err_mask;
+	enum dma_data_direction dir = write ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
+	int ret = 0;
+
+	dma_addr = dma_map_single(denali->dev, buf, size, dir);
+	if (dma_mapping_error(denali->dev, dma_addr)) {
+		dev_dbg(denali->dev, "Failed to DMA-map buffer. Trying PIO.\n");
+		return denali_pio_xfer(denali, buf, size, page, raw, write);
 	}
 
-	dma_sync_single_for_device(denali->dev, addr, size, DMA_TO_DEVICE);
+	if (write) {
+		/*
+		 * INTR__PROGRAM_COMP is never asserted for the DMA transfer.
+		 * We can use INTR__DMA_CMD_COMP instead.  This flag is asserted
+		 * when the page program is completed.
+		 */
+		irq_mask = INTR__DMA_CMD_COMP | INTR__PROGRAM_FAIL;
+		ecc_err_mask = 0;
+	} else if (denali->caps & DENALI_CAP_HW_ECC_FIXUP) {
+		irq_mask = INTR__DMA_CMD_COMP;
+		ecc_err_mask = INTR__ECC_UNCOR_ERR;
+	} else {
+		irq_mask = INTR__DMA_CMD_COMP;
+		ecc_err_mask = INTR__ECC_ERR;
+	}
 
-	clear_interrupts(denali);
 	denali_enable_dma(denali, true);
 
-	denali_setup_dma(denali, DENALI_WRITE);
+	denali_reset_irq(denali);
+	denali_setup_dma(denali, dma_addr, page, write);
 
 	/* wait for operation to complete */
-	irq_status = wait_for_irq(denali, irq_mask);
-
-	if (irq_status == 0) {
-		dev_err(denali->dev, "timeout on write_page (type = %d)\n",
-			raw_xfer);
-		denali->status = NAND_STATUS_FAIL;
-	}
+	irq_status = denali_wait_for_irq(denali, irq_mask);
+	if (!(irq_status & INTR__DMA_CMD_COMP))
+		ret = -EIO;
+	else if (irq_status & ecc_err_mask)
+		ret = -EBADMSG;
 
 	denali_enable_dma(denali, false);
-	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_TO_DEVICE);
+	dma_unmap_single(denali->dev, dma_addr, size, dir);
 
-	return 0;
-}
+	if (irq_status & INTR__ERASED_PAGE)
+		memset(buf, 0xff, size);
 
-/* NAND core entry points */
+	return ret;
+}
 
-/*
- * this is the callback that the NAND core calls to write a page. Since
- * writing a page with ECC or without is similar, all the work is done
- * by write_page above.
- */
-static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip,
-				const uint8_t *buf, int oob_required, int page)
+static int denali_data_xfer(struct denali_nand_info *denali, void *buf,
+			    size_t size, int page, int raw, int write)
 {
-	/*
-	 * for regular page writes, we let HW handle all the ECC
-	 * data written to the device.
-	 */
-	return write_page(mtd, chip, buf, false);
+	setup_ecc_for_xfer(denali, !raw, raw);
+
+	if (denali->dma_avail)
+		return denali_dma_xfer(denali, buf, size, page, raw, write);
+	else
+		return denali_pio_xfer(denali, buf, size, page, raw, write);
 }
 
-/*
- * This is the callback that the NAND core calls to write a page without ECC.
- * raw access is similar to ECC page writes, so all the work is done in the
- * write_page() function above.
- */
-static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
-				 const uint8_t *buf, int oob_required,
-				 int page)
+static void denali_oob_xfer(struct mtd_info *mtd, struct nand_chip *chip,
+			    int page, int write)
 {
-	/*
-	 * for raw page writes, we want to disable ECC and simply write
-	 * whatever data is in the buffer.
-	 */
-	return write_page(mtd, chip, buf, true);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	unsigned int start_cmd = write ? NAND_CMD_SEQIN : NAND_CMD_READ0;
+	unsigned int rnd_cmd = write ? NAND_CMD_RNDIN : NAND_CMD_RNDOUT;
+	int writesize = mtd->writesize;
+	int oobsize = mtd->oobsize;
+	uint8_t *bufpoi = chip->oob_poi;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	int oob_skip = denali->oob_skip_bytes;
+	size_t size = writesize + oobsize;
+	int i, pos, len;
+
+	/* BBM at the beginning of the OOB area */
+	chip->cmdfunc(mtd, start_cmd, writesize, page);
+	if (write)
+		chip->write_buf(mtd, bufpoi, oob_skip);
+	else
+		chip->read_buf(mtd, bufpoi, oob_skip);
+	bufpoi += oob_skip;
+
+	/* OOB ECC */
+	for (i = 0; i < ecc_steps; i++) {
+		pos = ecc_size + i * (ecc_size + ecc_bytes);
+		len = ecc_bytes;
+
+		if (pos >= writesize)
+			pos += oob_skip;
+		else if (pos + len > writesize)
+			len = writesize - pos;
+
+		chip->cmdfunc(mtd, rnd_cmd, pos, -1);
+		if (write)
+			chip->write_buf(mtd, bufpoi, len);
+		else
+			chip->read_buf(mtd, bufpoi, len);
+		bufpoi += len;
+		if (len < ecc_bytes) {
+			len = ecc_bytes - len;
+			chip->cmdfunc(mtd, rnd_cmd, writesize + oob_skip, -1);
+			if (write)
+				chip->write_buf(mtd, bufpoi, len);
+			else
+				chip->read_buf(mtd, bufpoi, len);
+			bufpoi += len;
+		}
+	}
+
+	/* OOB free */
+	len = oobsize - (bufpoi - chip->oob_poi);
+	chip->cmdfunc(mtd, rnd_cmd, size - len, -1);
+	if (write)
+		chip->write_buf(mtd, bufpoi, len);
+	else
+		chip->read_buf(mtd, bufpoi, len);
 }
 
-static int denali_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
-			    int page)
+static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				uint8_t *buf, int oob_required, int page)
 {
-	return write_oob_data(mtd, chip->oob_poi, page);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	int writesize = mtd->writesize;
+	int oobsize = mtd->oobsize;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	void *dma_buf = denali->buf;
+	int oob_skip = denali->oob_skip_bytes;
+	size_t size = writesize + oobsize;
+	int ret, i, pos, len;
+
+	ret = denali_data_xfer(denali, dma_buf, size, page, 1, 0);
+	if (ret)
+		return ret;
+
+	/* Arrange the buffer for syndrome payload/ecc layout */
+	if (buf) {
+		for (i = 0; i < ecc_steps; i++) {
+			pos = i * (ecc_size + ecc_bytes);
+			len = ecc_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(buf, dma_buf + pos, len);
+			buf += len;
+			if (len < ecc_size) {
+				len = ecc_size - len;
+				memcpy(buf, dma_buf + writesize + oob_skip,
+				       len);
+				buf += len;
+			}
+		}
+	}
+
+	if (oob_required) {
+		uint8_t *oob = chip->oob_poi;
+
+		/* BBM at the beginning of the OOB area */
+		memcpy(oob, dma_buf + writesize, oob_skip);
+		oob += oob_skip;
+
+		/* OOB ECC */
+		for (i = 0; i < ecc_steps; i++) {
+			pos = ecc_size + i * (ecc_size + ecc_bytes);
+			len = ecc_bytes;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(oob, dma_buf + pos, len);
+			oob += len;
+			if (len < ecc_bytes) {
+				len = ecc_bytes - len;
+				memcpy(oob, dma_buf + writesize + oob_skip,
+				       len);
+				oob += len;
+			}
+		}
+
+		/* OOB free */
+		len = oobsize - (oob - chip->oob_poi);
+		memcpy(oob, dma_buf + size - len, len);
+	}
+
+	return 0;
 }
 
 static int denali_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 			   int page)
 {
-	read_oob_data(mtd, chip->oob_poi, page);
+	denali_oob_xfer(mtd, chip, page, 0);
 
 	return 0;
 }
 
-static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
-			    uint8_t *buf, int oob_required, int page)
+static int denali_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
+			    int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dma_addr_t addr = denali->buf.dma_buf;
-	size_t size = mtd->writesize + mtd->oobsize;
-	uint32_t irq_status;
-	uint32_t irq_mask = denali->caps & DENALI_CAP_HW_ECC_FIXUP ?
-				INTR__DMA_CMD_COMP | INTR__ECC_UNCOR_ERR :
-				INTR__ECC_TRANSACTION_DONE | INTR__ECC_ERR;
-	unsigned long uncor_ecc_flags = 0;
-	int stat = 0;
+	int status;
 
-	if (page != denali->page) {
-		dev_err(denali->dev,
-			"IN %s: page %d is not equal to denali->page %d",
-			__func__, page, denali->page);
-		BUG();
-	}
+	denali_reset_irq(denali);
 
-	setup_ecc_for_xfer(denali, true, false);
+	denali_oob_xfer(mtd, chip, page, 1);
 
-	denali_enable_dma(denali, true);
-	dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE);
+	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+	status = chip->waitfunc(mtd, chip);
 
-	clear_interrupts(denali);
-	denali_setup_dma(denali, DENALI_READ);
-
-	/* wait for operation to complete */
-	irq_status = wait_for_irq(denali, irq_mask);
+	return status & NAND_STATUS_FAIL ? -EIO : 0;
+}
 
-	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE);
+static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
+			    uint8_t *buf, int oob_required, int page)
+{
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	unsigned long uncor_ecc_flags = 0;
+	int stat = 0;
+	int ret;
 
-	memcpy(buf, denali->buf.buf, mtd->writesize);
+	ret = denali_data_xfer(denali, buf, mtd->writesize, page, 0, 0);
+	if (ret && ret != -EBADMSG)
+		return ret;
 
 	if (denali->caps & DENALI_CAP_HW_ECC_FIXUP)
 		stat = denali_hw_ecc_fixup(mtd, denali, &uncor_ecc_flags);
-	else if (irq_status & INTR__ECC_ERR)
+	else if (ret == -EBADMSG)
 		stat = denali_sw_ecc_fixup(mtd, denali, &uncor_ecc_flags, buf);
-	denali_enable_dma(denali, false);
 
 	if (stat < 0)
 		return stat;
 
 	if (uncor_ecc_flags) {
-		read_oob_data(mtd, chip->oob_poi, denali->page);
+		ret = denali_read_oob(mtd, chip, page);
+		if (ret)
+			return ret;
 
 		stat = denali_check_erased_page(mtd, chip, buf,
 						uncor_ecc_flags, stat);
@@ -1181,137 +858,266 @@ static int denali_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return stat;
 }
 
-static int denali_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
-				uint8_t *buf, int oob_required, int page)
+static int denali_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+				 const uint8_t *buf, int oob_required, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	dma_addr_t addr = denali->buf.dma_buf;
-	size_t size = mtd->writesize + mtd->oobsize;
-	uint32_t irq_mask = INTR__DMA_CMD_COMP;
-
-	if (page != denali->page) {
-		dev_err(denali->dev,
-			"IN %s: page %d is not equal to denali->page %d",
-			__func__, page, denali->page);
-		BUG();
-	}
-
-	setup_ecc_for_xfer(denali, false, true);
-	denali_enable_dma(denali, true);
-
-	dma_sync_single_for_device(denali->dev, addr, size, DMA_FROM_DEVICE);
-
-	clear_interrupts(denali);
-	denali_setup_dma(denali, DENALI_READ);
-
-	/* wait for operation to complete */
-	wait_for_irq(denali, irq_mask);
+	int writesize = mtd->writesize;
+	int oobsize = mtd->oobsize;
+	int ecc_steps = chip->ecc.steps;
+	int ecc_size = chip->ecc.size;
+	int ecc_bytes = chip->ecc.bytes;
+	void *dma_buf = denali->buf;
+	int oob_skip = denali->oob_skip_bytes;
+	size_t size = writesize + oobsize;
+	int i, pos, len;
 
-	dma_sync_single_for_cpu(denali->dev, addr, size, DMA_FROM_DEVICE);
+	/*
+	 * Fill the buffer with 0xff first except the full page transfer.
+	 * This simplifies the logic.
+	 */
+	if (!buf || !oob_required)
+		memset(dma_buf, 0xff, size);
+
+	/* Arrange the buffer for syndrome payload/ecc layout */
+	if (buf) {
+		for (i = 0; i < ecc_steps; i++) {
+			pos = i * (ecc_size + ecc_bytes);
+			len = ecc_size;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(dma_buf + pos, buf, len);
+			buf += len;
+			if (len < ecc_size) {
+				len = ecc_size - len;
+				memcpy(dma_buf + writesize + oob_skip, buf,
+				       len);
+				buf += len;
+			}
+		}
+	}
 
-	denali_enable_dma(denali, false);
+	if (oob_required) {
+		const uint8_t *oob = chip->oob_poi;
+
+		/* BBM at the beginning of the OOB area */
+		memcpy(dma_buf + writesize, oob, oob_skip);
+		oob += oob_skip;
+
+		/* OOB ECC */
+		for (i = 0; i < ecc_steps; i++) {
+			pos = ecc_size + i * (ecc_size + ecc_bytes);
+			len = ecc_bytes;
+
+			if (pos >= writesize)
+				pos += oob_skip;
+			else if (pos + len > writesize)
+				len = writesize - pos;
+
+			memcpy(dma_buf + pos, oob, len);
+			oob += len;
+			if (len < ecc_bytes) {
+				len = ecc_bytes - len;
+				memcpy(dma_buf + writesize + oob_skip, oob,
+				       len);
+				oob += len;
+			}
+		}
 
-	memcpy(buf, denali->buf.buf, mtd->writesize);
-	memcpy(chip->oob_poi, denali->buf.buf + mtd->writesize, mtd->oobsize);
+		/* OOB free */
+		len = oobsize - (oob - chip->oob_poi);
+		memcpy(dma_buf + size - len, oob, len);
+	}
 
-	return 0;
+	return denali_data_xfer(denali, dma_buf, size, page, 1, 1);
 }
 
-static uint8_t denali_read_byte(struct mtd_info *mtd)
+static int denali_write_page(struct mtd_info *mtd, struct nand_chip *chip,
+			     const uint8_t *buf, int oob_required, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint8_t result = 0xff;
-
-	if (denali->buf.head < denali->buf.tail)
-		result = denali->buf.buf[denali->buf.head++];
 
-	return result;
+	return denali_data_xfer(denali, (void *)buf, mtd->writesize,
+				page, 0, 1);
 }
 
 static void denali_select_chip(struct mtd_info *mtd, int chip)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 
-	spin_lock_irq(&denali->irq_lock);
-	denali->flash_bank = chip;
-	spin_unlock_irq(&denali->irq_lock);
+	denali->active_bank = chip;
 }
 
 static int denali_waitfunc(struct mtd_info *mtd, struct nand_chip *chip)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	int status = denali->status;
+	uint32_t irq_status;
 
-	denali->status = 0;
+	/* R/B# pin transitioned from low to high? */
+	irq_status = denali_wait_for_irq(denali, INTR__INT_ACT);
 
-	return status;
+	return irq_status & INTR__INT_ACT ? 0 : NAND_STATUS_FAIL;
 }
 
 static int denali_erase(struct mtd_info *mtd, int page)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
+	uint32_t irq_status;
 
-	uint32_t cmd, irq_status;
-
-	clear_interrupts(denali);
+	denali_reset_irq(denali);
 
-	/* setup page read request for access type */
-	cmd = MODE_10 | BANK(denali->flash_bank) | page;
-	index_addr(denali, cmd, 0x1);
+	denali_host_write(denali, DENALI_MAP10 | DENALI_BANK(denali) | page,
+			  DENALI_ERASE);
 
 	/* wait for erase to complete or failure to occur */
-	irq_status = wait_for_irq(denali, INTR__ERASE_COMP | INTR__ERASE_FAIL);
+	irq_status = denali_wait_for_irq(denali,
+					 INTR__ERASE_COMP | INTR__ERASE_FAIL);
 
-	return irq_status & INTR__ERASE_FAIL ? NAND_STATUS_FAIL : PASS;
+	return irq_status & INTR__ERASE_COMP ? 0 : NAND_STATUS_FAIL;
 }
 
-static void denali_cmdfunc(struct mtd_info *mtd, unsigned int cmd, int col,
-			   int page)
+#define DIV_ROUND_DOWN_ULL(ll, d) \
+	({ unsigned long long _tmp = (ll); do_div(_tmp, d); _tmp; })
+
+static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
+				       const struct nand_data_interface *conf)
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
-	uint32_t addr, id;
+	const struct nand_sdr_timings *timings;
+	unsigned long t_clk;
+	int acc_clks, re_2_we, re_2_re, we_2_re, addr_2_data;
+	int rdwr_en_lo, rdwr_en_hi, rdwr_en_lo_hi, cs_setup;
+	int addr_2_data_mask;
+	uint32_t tmp;
+
+	timings = nand_get_sdr_timings(conf);
+	if (IS_ERR(timings))
+		return PTR_ERR(timings);
+
+	/* clk_x period in picoseconds */
+	t_clk = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
+	if (!t_clk)
+		return -EINVAL;
+
+	if (chipnr == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	/* tREA -> ACC_CLKS */
+	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk);
+	acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE);
+
+	tmp = ioread32(denali->reg + ACC_CLKS);
+	tmp &= ~ACC_CLKS__VALUE;
+	tmp |= acc_clks;
+	iowrite32(tmp, denali->reg + ACC_CLKS);
+
+	/* tRWH -> RE_2_WE */
+	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk);
+	re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE);
+
+	tmp = ioread32(denali->reg + RE_2_WE);
+	tmp &= ~RE_2_WE__VALUE;
+	tmp |= re_2_we;
+	iowrite32(tmp, denali->reg + RE_2_WE);
+
+	/* tRHZ -> RE_2_RE */
+	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk);
+	re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE);
+
+	tmp = ioread32(denali->reg + RE_2_RE);
+	tmp &= ~RE_2_RE__VALUE;
+	tmp |= re_2_re;
+	iowrite32(tmp, denali->reg + RE_2_RE);
+
+	/* tWHR -> WE_2_RE */
+	we_2_re = DIV_ROUND_UP(timings->tWHR_min, t_clk);
+	we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE);
+
+	tmp = ioread32(denali->reg + TWHR2_AND_WE_2_RE);
+	tmp &= ~TWHR2_AND_WE_2_RE__WE_2_RE;
+	tmp |= we_2_re;
+	iowrite32(tmp, denali->reg + TWHR2_AND_WE_2_RE);
+
+	/* tADL -> ADDR_2_DATA */
+
+	/* for older versions, ADDR_2_DATA is only 6 bit wide */
+	addr_2_data_mask = TCWAW_AND_ADDR_2_DATA__ADDR_2_DATA;
+	if (denali->revision < 0x0501)
+		addr_2_data_mask >>= 1;
+
+	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk);
+	addr_2_data = min_t(int, addr_2_data, addr_2_data_mask);
+
+	tmp = ioread32(denali->reg + TCWAW_AND_ADDR_2_DATA);
+	tmp &= ~addr_2_data_mask;
+	tmp |= addr_2_data;
+	iowrite32(tmp, denali->reg + TCWAW_AND_ADDR_2_DATA);
+
+	/* tREH, tWH -> RDWR_EN_HI_CNT */
+	rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min),
+				  t_clk);
+	rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE);
+
+	tmp = ioread32(denali->reg + RDWR_EN_HI_CNT);
+	tmp &= ~RDWR_EN_HI_CNT__VALUE;
+	tmp |= rdwr_en_hi;
+	iowrite32(tmp, denali->reg + RDWR_EN_HI_CNT);
+
+	/* tRP, tWP -> RDWR_EN_LO_CNT */
+	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min),
+				  t_clk);
+	rdwr_en_lo_hi = DIV_ROUND_UP(max(timings->tRC_min, timings->tWC_min),
+				     t_clk);
+	rdwr_en_lo_hi = max(rdwr_en_lo_hi, DENALI_CLK_X_MULT);
+	rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi);
+	rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE);
+
+	tmp = ioread32(denali->reg + RDWR_EN_LO_CNT);
+	tmp &= ~RDWR_EN_LO_CNT__VALUE;
+	tmp |= rdwr_en_lo;
+	iowrite32(tmp, denali->reg + RDWR_EN_LO_CNT);
+
+	/* tCS, tCEA -> CS_SETUP_CNT */
+	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo,
+			(int)DIV_ROUND_UP(timings->tCEA_max, t_clk) - acc_clks,
+			0);
+	cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE);
+
+	tmp = ioread32(denali->reg + CS_SETUP_CNT);
+	tmp &= ~CS_SETUP_CNT__VALUE;
+	tmp |= cs_setup;
+	iowrite32(tmp, denali->reg + CS_SETUP_CNT);
+
+	return 0;
+}
+
+static void denali_reset_banks(struct denali_nand_info *denali)
+{
+	u32 irq_status;
 	int i;
 
-	switch (cmd) {
-	case NAND_CMD_PAGEPROG:
-		break;
-	case NAND_CMD_STATUS:
-		read_status(denali);
-		break;
-	case NAND_CMD_READID:
-	case NAND_CMD_PARAM:
-		reset_buf(denali);
-		/*
-		 * sometimes ManufactureId read from register is not right
-		 * e.g. some of Micron MT29F32G08QAA MLC NAND chips
-		 * So here we send READID cmd to NAND insteand
-		 */
-		addr = MODE_11 | BANK(denali->flash_bank);
-		index_addr(denali, addr | 0, 0x90);
-		index_addr(denali, addr | 1, col);
-		for (i = 0; i < 8; i++) {
-			index_addr_read_data(denali, addr | 2, &id);
-			write_byte_to_buf(denali, id);
-		}
-		break;
-	case NAND_CMD_READ0:
-	case NAND_CMD_SEQIN:
-		denali->page = page;
-		break;
-	case NAND_CMD_RESET:
-		reset_bank(denali);
-		break;
-	case NAND_CMD_READOOB:
-		/* TODO: Read OOB data */
-		break;
-	default:
-		pr_err(": unsupported command received 0x%x\n", cmd);
-		break;
+	for (i = 0; i < denali->max_banks; i++) {
+		denali->active_bank = i;
+
+		denali_reset_irq(denali);
+
+		iowrite32(DEVICE_RESET__BANK(i),
+			  denali->reg + DEVICE_RESET);
+
+		irq_status = denali_wait_for_irq(denali,
+			INTR__RST_COMP | INTR__INT_ACT | INTR__TIME_OUT);
+		if (!(irq_status & INTR__INT_ACT))
+			break;
 	}
+
+	dev_dbg(denali->dev, "%d chips connected\n", i);
+	denali->max_banks = i;
 }
-/* end NAND core entry points */
 
-/* Initialization code to bring the device up to a known good state */
 static void denali_hw_init(struct denali_nand_info *denali)
 {
 	/*
@@ -1319,8 +1125,7 @@ static void denali_hw_init(struct denali_nand_info *denali)
 	 * override it.
 	 */
 	if (!denali->revision)
-		denali->revision =
-				swab16(ioread32(denali->flash_reg + REVISION));
+		denali->revision = swab16(ioread32(denali->reg + REVISION));
 
 	/*
 	 * tell driver how many bit controller will skip before
@@ -1328,30 +1133,51 @@ static void denali_hw_init(struct denali_nand_info *denali)
 	 * set by firmware. So we read this value out.
 	 * if this value is 0, just let it be.
 	 */
-	denali->bbtskipbytes = ioread32(denali->flash_reg +
-						SPARE_AREA_SKIP_BYTES);
+	denali->oob_skip_bytes = ioread32(denali->reg + SPARE_AREA_SKIP_BYTES);
 	detect_max_banks(denali);
-	denali_nand_reset(denali);
-	iowrite32(0x0F, denali->flash_reg + RB_PIN_ENABLED);
-	iowrite32(CHIP_EN_DONT_CARE__FLAG,
-			denali->flash_reg + CHIP_ENABLE_DONT_CARE);
+	iowrite32(0x0F, denali->reg + RB_PIN_ENABLED);
+	iowrite32(CHIP_EN_DONT_CARE__FLAG, denali->reg + CHIP_ENABLE_DONT_CARE);
 
-	iowrite32(0xffff, denali->flash_reg + SPARE_AREA_MARKER);
+	iowrite32(0xffff, denali->reg + SPARE_AREA_MARKER);
 
 	/* Should set value for these registers when init */
-	iowrite32(0, denali->flash_reg + TWO_ROW_ADDR_CYCLES);
-	iowrite32(1, denali->flash_reg + ECC_ENABLE);
-	denali_nand_timing_set(denali);
-	denali_irq_init(denali);
+	iowrite32(0, denali->reg + TWO_ROW_ADDR_CYCLES);
+	iowrite32(1, denali->reg + ECC_ENABLE);
 }
 
-/*
- * Althogh controller spec said SLC ECC is forceb to be 4bit,
- * but denali controller in MRST only support 15bit and 8bit ECC
- * correction
- */
-#define ECC_8BITS	14
-#define ECC_15BITS	26
+int denali_calc_ecc_bytes(int step_size, int strength)
+{
+	/* BCH code.  Denali requires ecc.bytes to be multiple of 2 */
+	return DIV_ROUND_UP(strength * fls(step_size * 8), 16) * 2;
+}
+EXPORT_SYMBOL(denali_calc_ecc_bytes);
+
+static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip,
+			    struct denali_nand_info *denali)
+{
+	int oobavail = mtd->oobsize - denali->oob_skip_bytes;
+	int ret;
+
+	/*
+	 * If .size and .strength are already set (usually by DT),
+	 * check if they are supported by this controller.
+	 */
+	if (chip->ecc.size && chip->ecc.strength)
+		return nand_check_ecc_caps(chip, denali->ecc_caps, oobavail);
+
+	/*
+	 * We want .size and .strength closest to the chip's requirement
+	 * unless NAND_ECC_MAXIMIZE is requested.
+	 */
+	if (!(chip->ecc.options & NAND_ECC_MAXIMIZE)) {
+		ret = nand_match_ecc_req(chip, denali->ecc_caps, oobavail);
+		if (!ret)
+			return 0;
+	}
+
+	/* Max ECC strength is the last thing we can do */
+	return nand_maximize_ecc(chip, denali->ecc_caps, oobavail);
+}
 
 static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
 				struct mtd_oob_region *oobregion)
@@ -1362,7 +1188,7 @@ static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
 	if (section)
 		return -ERANGE;
 
-	oobregion->offset = denali->bbtskipbytes;
+	oobregion->offset = denali->oob_skip_bytes;
 	oobregion->length = chip->ecc.total;
 
 	return 0;
@@ -1377,7 +1203,7 @@ static int denali_ooblayout_free(struct mtd_info *mtd, int section,
 	if (section)
 		return -ERANGE;
 
-	oobregion->offset = chip->ecc.total + denali->bbtskipbytes;
+	oobregion->offset = chip->ecc.total + denali->oob_skip_bytes;
 	oobregion->length = mtd->oobsize - oobregion->offset;
 
 	return 0;
@@ -1388,29 +1214,6 @@ static const struct mtd_ooblayout_ops denali_ooblayout_ops = {
 	.free = denali_ooblayout_free,
 };
 
-static uint8_t bbt_pattern[] = {'B', 'b', 't', '0' };
-static uint8_t mirror_pattern[] = {'1', 't', 'b', 'B' };
-
-static struct nand_bbt_descr bbt_main_descr = {
-	.options = NAND_BBT_LASTBLOCK | NAND_BBT_CREATE | NAND_BBT_WRITE
-		| NAND_BBT_2BIT | NAND_BBT_VERSION | NAND_BBT_PERCHIP,
-	.offs =	8,
-	.len = 4,
-	.veroffs = 12,
-	.maxblocks = 4,
-	.pattern = bbt_pattern,
-};
-
-static struct nand_bbt_descr bbt_mirror_descr = {
-	.options = NAND_BBT_LASTBLOCK | NAND_BBT_CREATE | NAND_BBT_WRITE
-		| NAND_BBT_2BIT | NAND_BBT_VERSION | NAND_BBT_PERCHIP,
-	.offs =	8,
-	.len = 4,
-	.veroffs = 12,
-	.maxblocks = 4,
-	.pattern = mirror_pattern,
-};
-
 /* initialize driver data structures */
 static void denali_drv_init(struct denali_nand_info *denali)
 {
@@ -1425,12 +1228,6 @@ static void denali_drv_init(struct denali_nand_info *denali)
 	 * element that might be access shared data (interrupt status)
 	 */
 	spin_lock_init(&denali->irq_lock);
-
-	/* indicate that MTD has not selected a valid bank yet */
-	denali->flash_bank = CHIP_SELECT_INVALID;
-
-	/* initialize our irq_status variable to indicate no interrupts */
-	denali->irq_status = 0;
 }
 
 static int denali_multidev_fixup(struct denali_nand_info *denali)
@@ -1445,23 +1242,23 @@ static int denali_multidev_fixup(struct denali_nand_info *denali)
 	 * In this case, the core framework knows nothing about this fact,
 	 * so we should tell it the _logical_ pagesize and anything necessary.
 	 */
-	denali->devnum = ioread32(denali->flash_reg + DEVICES_CONNECTED);
+	denali->devs_per_cs = ioread32(denali->reg + DEVICES_CONNECTED);
 
 	/*
 	 * On some SoCs, DEVICES_CONNECTED is not auto-detected.
 	 * For those, DEVICES_CONNECTED is left to 0.  Set 1 if it is the case.
 	 */
-	if (denali->devnum == 0) {
-		denali->devnum = 1;
-		iowrite32(1, denali->flash_reg + DEVICES_CONNECTED);
+	if (denali->devs_per_cs == 0) {
+		denali->devs_per_cs = 1;
+		iowrite32(1, denali->reg + DEVICES_CONNECTED);
 	}
 
-	if (denali->devnum == 1)
+	if (denali->devs_per_cs == 1)
 		return 0;
 
-	if (denali->devnum != 2) {
+	if (denali->devs_per_cs != 2) {
 		dev_err(denali->dev, "unsupported number of devices %d\n",
-			denali->devnum);
+			denali->devs_per_cs);
 		return -EINVAL;
 	}
 
@@ -1479,7 +1276,7 @@ static int denali_multidev_fixup(struct denali_nand_info *denali)
 	chip->ecc.size <<= 1;
 	chip->ecc.bytes <<= 1;
 	chip->ecc.strength <<= 1;
-	denali->bbtskipbytes <<= 1;
+	denali->oob_skip_bytes <<= 1;
 
 	return 0;
 }
@@ -1490,27 +1287,12 @@ int denali_init(struct denali_nand_info *denali)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
-	if (denali->platform == INTEL_CE4100) {
-		/*
-		 * Due to a silicon limitation, we can only support
-		 * ONFI timing mode 1 and below.
-		 */
-		if (onfi_timing_mode < -1 || onfi_timing_mode > 1) {
-			pr_err("Intel CE4100 only supports ONFI timing mode 1 or below\n");
-			return -EINVAL;
-		}
-	}
-
-	/* allocate a temporary buffer for nand_scan_ident() */
-	denali->buf.buf = devm_kzalloc(denali->dev, PAGE_SIZE,
-					GFP_DMA | GFP_KERNEL);
-	if (!denali->buf.buf)
-		return -ENOMEM;
-
 	mtd->dev.parent = denali->dev;
 	denali_hw_init(denali);
 	denali_drv_init(denali);
 
+	denali_clear_irq_all(denali);
+
 	/* Request IRQ after all the hardware initialization is finished */
 	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
 			       IRQF_SHARED, DENALI_NAND_NAME, denali);
@@ -1519,8 +1301,11 @@ int denali_init(struct denali_nand_info *denali)
 		return ret;
 	}
 
-	/* now that our ISR is registered, we can enable interrupts */
-	denali_set_intr_modes(denali, true);
+	denali_enable_irq(denali);
+	denali_reset_banks(denali);
+
+	denali->active_bank = DENALI_INVALID_BANK;
+
 	nand_set_flash_node(chip, denali->dev->of_node);
 	/* Fallback to the default name if DT did not give "label" property */
 	if (!mtd->name)
@@ -1528,10 +1313,17 @@ int denali_init(struct denali_nand_info *denali)
 
 	/* register the driver with the NAND core subsystem */
 	chip->select_chip = denali_select_chip;
-	chip->cmdfunc = denali_cmdfunc;
 	chip->read_byte = denali_read_byte;
+	chip->write_byte = denali_write_byte;
+	chip->read_word = denali_read_word;
+	chip->cmd_ctrl = denali_cmd_ctrl;
+	chip->dev_ready = denali_dev_ready;
 	chip->waitfunc = denali_waitfunc;
 
+	/* clk rate info is needed for setup_data_interface */
+	if (denali->clk_x_rate)
+		chip->setup_data_interface = denali_setup_data_interface;
+
 	/*
 	 * scan for NAND devices attached to the controller
 	 * this is the first stage in a two step process to register
@@ -1539,33 +1331,25 @@ int denali_init(struct denali_nand_info *denali)
 	 */
 	ret = nand_scan_ident(mtd, denali->max_banks, NULL);
 	if (ret)
-		goto failed_req_irq;
-
-	/* allocate the right size buffer now */
-	devm_kfree(denali->dev, denali->buf.buf);
-	denali->buf.buf = devm_kzalloc(denali->dev,
-			     mtd->writesize + mtd->oobsize,
-			     GFP_KERNEL);
-	if (!denali->buf.buf) {
-		ret = -ENOMEM;
-		goto failed_req_irq;
-	}
+		goto disable_irq;
 
-	ret = dma_set_mask(denali->dev,
-			   DMA_BIT_MASK(denali->caps & DENALI_CAP_DMA_64BIT ?
-					64 : 32));
-	if (ret) {
-		dev_err(denali->dev, "No usable DMA configuration\n");
-		goto failed_req_irq;
+	if (ioread32(denali->reg + FEATURES) & FEATURES__DMA)
+		denali->dma_avail = 1;
+
+	if (denali->dma_avail) {
+		int dma_bit = denali->caps & DENALI_CAP_DMA_64BIT ? 64 : 32;
+
+		ret = dma_set_mask(denali->dev, DMA_BIT_MASK(dma_bit));
+		if (ret) {
+			dev_info(denali->dev,
+				 "Failed to set DMA mask. Disabling DMA.\n");
+			denali->dma_avail = 0;
+		}
 	}
 
-	denali->buf.dma_buf = dma_map_single(denali->dev, denali->buf.buf,
-			     mtd->writesize + mtd->oobsize,
-			     DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(denali->dev, denali->buf.dma_buf)) {
-		dev_err(denali->dev, "Failed to map DMA buffer\n");
-		ret = -EIO;
-		goto failed_req_irq;
+	if (denali->dma_avail) {
+		chip->options |= NAND_USE_BOUNCE_BUFFER;
+		chip->buf_align = 16;
 	}
 
 	/*
@@ -1574,46 +1358,49 @@ int denali_init(struct denali_nand_info *denali)
 	 * bad block management.
 	 */
 
-	/* Bad block management */
-	chip->bbt_td = &bbt_main_descr;
-	chip->bbt_md = &bbt_mirror_descr;
-
-	/* skip the scan for now until we have OOB read and write support */
 	chip->bbt_options |= NAND_BBT_USE_FLASH;
-	chip->options |= NAND_SKIP_BBTSCAN;
+	chip->bbt_options |= NAND_BBT_NO_OOB;
+
 	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
 
 	/* no subpage writes on denali */
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	/*
-	 * Denali Controller only support 15bit and 8bit ECC in MRST,
-	 * so just let controller do 15bit ECC for MLC and 8bit ECC for
-	 * SLC if possible.
-	 * */
-	if (!nand_is_slc(chip) &&
-			(mtd->oobsize > (denali->bbtskipbytes +
-			ECC_15BITS * (mtd->writesize /
-			ECC_SECTOR_SIZE)))) {
-		/* if MLC OOB size is large enough, use 15bit ECC*/
-		chip->ecc.strength = 15;
-		chip->ecc.bytes = ECC_15BITS;
-		iowrite32(15, denali->flash_reg + ECC_CORRECTION);
-	} else if (mtd->oobsize < (denali->bbtskipbytes +
-			ECC_8BITS * (mtd->writesize /
-			ECC_SECTOR_SIZE))) {
-		pr_err("Your NAND chip OOB is not large enough to contain 8bit ECC correction codes");
-		goto failed_req_irq;
-	} else {
-		chip->ecc.strength = 8;
-		chip->ecc.bytes = ECC_8BITS;
-		iowrite32(8, denali->flash_reg + ECC_CORRECTION);
+	ret = denali_ecc_setup(mtd, chip, denali);
+	if (ret) {
+		dev_err(denali->dev, "Failed to setup ECC settings.\n");
+		goto disable_irq;
 	}
 
+	dev_dbg(denali->dev,
+		"chosen ECC settings: step=%d, strength=%d, bytes=%d\n",
+		chip->ecc.size, chip->ecc.strength, chip->ecc.bytes);
+
+	iowrite32(MAKE_ECC_CORRECTION(chip->ecc.strength, 1),
+		  denali->reg + ECC_CORRECTION);
+	iowrite32(mtd->erasesize / mtd->writesize,
+		  denali->reg + PAGES_PER_BLOCK);
+	iowrite32(chip->options & NAND_BUSWIDTH_16 ? 1 : 0,
+		  denali->reg + DEVICE_WIDTH);
+	iowrite32(mtd->writesize, denali->reg + DEVICE_MAIN_AREA_SIZE);
+	iowrite32(mtd->oobsize, denali->reg + DEVICE_SPARE_AREA_SIZE);
+
+	iowrite32(chip->ecc.size, denali->reg + CFG_DATA_BLOCK_SIZE);
+	iowrite32(chip->ecc.size, denali->reg + CFG_LAST_DATA_BLOCK_SIZE);
+	/* chip->ecc.steps is set by nand_scan_tail(); not available here */
+	iowrite32(mtd->writesize / chip->ecc.size,
+		  denali->reg + CFG_NUM_DATA_BLOCKS);
+
 	mtd_set_ooblayout(mtd, &denali_ooblayout_ops);
 
-	/* override the default read operations */
-	chip->ecc.size = ECC_SECTOR_SIZE;
+	if (chip->options & NAND_BUSWIDTH_16) {
+		chip->read_buf = denali_read_buf16;
+		chip->write_buf = denali_write_buf16;
+	} else {
+		chip->read_buf = denali_read_buf;
+		chip->write_buf = denali_write_buf;
+	}
+	chip->ecc.options |= NAND_ECC_CUSTOM_PAGE_ACCESS;
 	chip->ecc.read_page = denali_read_page;
 	chip->ecc.read_page_raw = denali_read_page_raw;
 	chip->ecc.write_page = denali_write_page;
@@ -1624,21 +1411,34 @@ int denali_init(struct denali_nand_info *denali)
 
 	ret = denali_multidev_fixup(denali);
 	if (ret)
-		goto failed_req_irq;
+		goto disable_irq;
+
+	/*
+	 * This buffer is DMA-mapped by denali_{read,write}_page_raw.  Do not
+	 * use devm_kmalloc() because the memory allocated by devm_ does not
+	 * guarantee DMA-safe alignment.
+	 */
+	denali->buf = kmalloc(mtd->writesize + mtd->oobsize, GFP_KERNEL);
+	if (!denali->buf) {
+		ret = -ENOMEM;
+		goto disable_irq;
+	}
 
 	ret = nand_scan_tail(mtd);
 	if (ret)
-		goto failed_req_irq;
+		goto free_buf;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(denali->dev, "Failed to register MTD: %d\n", ret);
-		goto failed_req_irq;
+		goto free_buf;
 	}
 	return 0;
 
-failed_req_irq:
-	denali_irq_cleanup(denali->irq, denali);
+free_buf:
+	kfree(denali->buf);
+disable_irq:
+	denali_disable_irq(denali);
 
 	return ret;
 }
@@ -1648,16 +1448,9 @@ EXPORT_SYMBOL(denali_init);
 void denali_remove(struct denali_nand_info *denali)
 {
 	struct mtd_info *mtd = nand_to_mtd(&denali->nand);
-	/*
-	 * Pre-compute DMA buffer size to avoid any problems in case
-	 * nand_release() ever changes in a way that mtd->writesize and
-	 * mtd->oobsize are not reliable after this call.
-	 */
-	int bufsize = mtd->writesize + mtd->oobsize;
 
 	nand_release(mtd);
-	denali_irq_cleanup(denali->irq, denali);
-	dma_unmap_single(denali->dev, denali->buf.dma_buf, bufsize,
-			 DMA_BIDIRECTIONAL);
+	kfree(denali->buf);
+	denali_disable_irq(denali);
 }
 EXPORT_SYMBOL(denali_remove);
diff --git a/drivers/mtd/nand/denali.h b/drivers/mtd/nand/denali.h
index ec004850652a..237cc706b0fb 100644
--- a/drivers/mtd/nand/denali.h
+++ b/drivers/mtd/nand/denali.h
@@ -24,330 +24,315 @@
 #include <linux/mtd/nand.h>
 
 #define DEVICE_RESET				0x0
-#define     DEVICE_RESET__BANK0				0x0001
-#define     DEVICE_RESET__BANK1				0x0002
-#define     DEVICE_RESET__BANK2				0x0004
-#define     DEVICE_RESET__BANK3				0x0008
+#define     DEVICE_RESET__BANK(bank)			BIT(bank)
 
 #define TRANSFER_SPARE_REG			0x10
-#define     TRANSFER_SPARE_REG__FLAG			0x0001
+#define     TRANSFER_SPARE_REG__FLAG			BIT(0)
 
 #define LOAD_WAIT_CNT				0x20
-#define     LOAD_WAIT_CNT__VALUE			0xffff
+#define     LOAD_WAIT_CNT__VALUE			GENMASK(15, 0)
 
 #define PROGRAM_WAIT_CNT			0x30
-#define     PROGRAM_WAIT_CNT__VALUE			0xffff
+#define     PROGRAM_WAIT_CNT__VALUE			GENMASK(15, 0)
 
 #define ERASE_WAIT_CNT				0x40
-#define     ERASE_WAIT_CNT__VALUE			0xffff
+#define     ERASE_WAIT_CNT__VALUE			GENMASK(15, 0)
 
 #define INT_MON_CYCCNT				0x50
-#define     INT_MON_CYCCNT__VALUE			0xffff
+#define     INT_MON_CYCCNT__VALUE			GENMASK(15, 0)
 
 #define RB_PIN_ENABLED				0x60
-#define     RB_PIN_ENABLED__BANK0			0x0001
-#define     RB_PIN_ENABLED__BANK1			0x0002
-#define     RB_PIN_ENABLED__BANK2			0x0004
-#define     RB_PIN_ENABLED__BANK3			0x0008
+#define     RB_PIN_ENABLED__BANK(bank)			BIT(bank)
 
 #define MULTIPLANE_OPERATION			0x70
-#define     MULTIPLANE_OPERATION__FLAG			0x0001
+#define     MULTIPLANE_OPERATION__FLAG			BIT(0)
 
 #define MULTIPLANE_READ_ENABLE			0x80
-#define     MULTIPLANE_READ_ENABLE__FLAG		0x0001
+#define     MULTIPLANE_READ_ENABLE__FLAG		BIT(0)
 
 #define COPYBACK_DISABLE			0x90
-#define     COPYBACK_DISABLE__FLAG			0x0001
+#define     COPYBACK_DISABLE__FLAG			BIT(0)
 
 #define CACHE_WRITE_ENABLE			0xa0
-#define     CACHE_WRITE_ENABLE__FLAG			0x0001
+#define     CACHE_WRITE_ENABLE__FLAG			BIT(0)
 
 #define CACHE_READ_ENABLE			0xb0
-#define     CACHE_READ_ENABLE__FLAG			0x0001
+#define     CACHE_READ_ENABLE__FLAG			BIT(0)
 
 #define PREFETCH_MODE				0xc0
-#define     PREFETCH_MODE__PREFETCH_EN			0x0001
-#define     PREFETCH_MODE__PREFETCH_BURST_LENGTH	0xfff0
+#define     PREFETCH_MODE__PREFETCH_EN			BIT(0)
+#define     PREFETCH_MODE__PREFETCH_BURST_LENGTH	GENMASK(15, 4)
 
 #define CHIP_ENABLE_DONT_CARE			0xd0
-#define     CHIP_EN_DONT_CARE__FLAG			0x01
+#define     CHIP_EN_DONT_CARE__FLAG			BIT(0)
 
 #define ECC_ENABLE				0xe0
-#define     ECC_ENABLE__FLAG				0x0001
+#define     ECC_ENABLE__FLAG				BIT(0)
 
 #define GLOBAL_INT_ENABLE			0xf0
-#define     GLOBAL_INT_EN_FLAG				0x01
+#define     GLOBAL_INT_EN_FLAG				BIT(0)
 
-#define WE_2_RE					0x100
-#define     WE_2_RE__VALUE				0x003f
+#define TWHR2_AND_WE_2_RE			0x100
+#define     TWHR2_AND_WE_2_RE__WE_2_RE			GENMASK(5, 0)
+#define     TWHR2_AND_WE_2_RE__TWHR2			GENMASK(13, 8)
 
-#define ADDR_2_DATA				0x110
-#define     ADDR_2_DATA__VALUE				0x003f
+#define TCWAW_AND_ADDR_2_DATA			0x110
+/* The width of ADDR_2_DATA is 6 bit for old IP, 7 bit for new IP */
+#define     TCWAW_AND_ADDR_2_DATA__ADDR_2_DATA		GENMASK(6, 0)
+#define     TCWAW_AND_ADDR_2_DATA__TCWAW		GENMASK(13, 8)
 
 #define RE_2_WE					0x120
-#define     RE_2_WE__VALUE				0x003f
+#define     RE_2_WE__VALUE				GENMASK(5, 0)
 
 #define ACC_CLKS				0x130
-#define     ACC_CLKS__VALUE				0x000f
+#define     ACC_CLKS__VALUE				GENMASK(3, 0)
 
 #define NUMBER_OF_PLANES			0x140
-#define     NUMBER_OF_PLANES__VALUE			0x0007
+#define     NUMBER_OF_PLANES__VALUE			GENMASK(2, 0)
 
 #define PAGES_PER_BLOCK				0x150
-#define     PAGES_PER_BLOCK__VALUE			0xffff
+#define     PAGES_PER_BLOCK__VALUE			GENMASK(15, 0)
 
 #define DEVICE_WIDTH				0x160
-#define     DEVICE_WIDTH__VALUE				0x0003
+#define     DEVICE_WIDTH__VALUE				GENMASK(1, 0)
 
 #define DEVICE_MAIN_AREA_SIZE			0x170
-#define     DEVICE_MAIN_AREA_SIZE__VALUE		0xffff
+#define     DEVICE_MAIN_AREA_SIZE__VALUE		GENMASK(15, 0)
 
 #define DEVICE_SPARE_AREA_SIZE			0x180
-#define     DEVICE_SPARE_AREA_SIZE__VALUE		0xffff
+#define     DEVICE_SPARE_AREA_SIZE__VALUE		GENMASK(15, 0)
 
 #define TWO_ROW_ADDR_CYCLES			0x190
-#define     TWO_ROW_ADDR_CYCLES__FLAG			0x0001
+#define     TWO_ROW_ADDR_CYCLES__FLAG			BIT(0)
 
 #define MULTIPLANE_ADDR_RESTRICT		0x1a0
-#define     MULTIPLANE_ADDR_RESTRICT__FLAG		0x0001
+#define     MULTIPLANE_ADDR_RESTRICT__FLAG		BIT(0)
 
 #define ECC_CORRECTION				0x1b0
-#define     ECC_CORRECTION__VALUE			0x001f
+#define     ECC_CORRECTION__VALUE			GENMASK(4, 0)
+#define     ECC_CORRECTION__ERASE_THRESHOLD		GENMASK(31, 16)
+#define     MAKE_ECC_CORRECTION(val, thresh)		\
+			(((val) & (ECC_CORRECTION__VALUE)) | \
+			(((thresh) << 16) & (ECC_CORRECTION__ERASE_THRESHOLD)))
 
 #define READ_MODE				0x1c0
-#define     READ_MODE__VALUE				0x000f
+#define     READ_MODE__VALUE				GENMASK(3, 0)
 
 #define WRITE_MODE				0x1d0
-#define     WRITE_MODE__VALUE				0x000f
+#define     WRITE_MODE__VALUE				GENMASK(3, 0)
 
 #define COPYBACK_MODE				0x1e0
-#define     COPYBACK_MODE__VALUE			0x000f
+#define     COPYBACK_MODE__VALUE			GENMASK(3, 0)
 
 #define RDWR_EN_LO_CNT				0x1f0
-#define     RDWR_EN_LO_CNT__VALUE			0x001f
+#define     RDWR_EN_LO_CNT__VALUE			GENMASK(4, 0)
 
 #define RDWR_EN_HI_CNT				0x200
-#define     RDWR_EN_HI_CNT__VALUE			0x001f
+#define     RDWR_EN_HI_CNT__VALUE			GENMASK(4, 0)
 
 #define MAX_RD_DELAY				0x210
-#define     MAX_RD_DELAY__VALUE				0x000f
+#define     MAX_RD_DELAY__VALUE				GENMASK(3, 0)
 
 #define CS_SETUP_CNT				0x220
-#define     CS_SETUP_CNT__VALUE				0x001f
+#define     CS_SETUP_CNT__VALUE				GENMASK(4, 0)
+#define     CS_SETUP_CNT__TWB				GENMASK(17, 12)
 
 #define SPARE_AREA_SKIP_BYTES			0x230
-#define     SPARE_AREA_SKIP_BYTES__VALUE		0x003f
+#define     SPARE_AREA_SKIP_BYTES__VALUE		GENMASK(5, 0)
 
 #define SPARE_AREA_MARKER			0x240
-#define     SPARE_AREA_MARKER__VALUE			0xffff
+#define     SPARE_AREA_MARKER__VALUE			GENMASK(15, 0)
 
 #define DEVICES_CONNECTED			0x250
-#define     DEVICES_CONNECTED__VALUE			0x0007
+#define     DEVICES_CONNECTED__VALUE			GENMASK(2, 0)
 
 #define DIE_MASK				0x260
-#define     DIE_MASK__VALUE				0x00ff
+#define     DIE_MASK__VALUE				GENMASK(7, 0)
 
 #define FIRST_BLOCK_OF_NEXT_PLANE		0x270
-#define     FIRST_BLOCK_OF_NEXT_PLANE__VALUE		0xffff
+#define     FIRST_BLOCK_OF_NEXT_PLANE__VALUE		GENMASK(15, 0)
 
 #define WRITE_PROTECT				0x280
-#define     WRITE_PROTECT__FLAG				0x0001
+#define     WRITE_PROTECT__FLAG				BIT(0)
 
 #define RE_2_RE					0x290
-#define     RE_2_RE__VALUE				0x003f
+#define     RE_2_RE__VALUE				GENMASK(5, 0)
 
 #define MANUFACTURER_ID				0x300
-#define     MANUFACTURER_ID__VALUE			0x00ff
+#define     MANUFACTURER_ID__VALUE			GENMASK(7, 0)
 
 #define DEVICE_ID				0x310
-#define     DEVICE_ID__VALUE				0x00ff
+#define     DEVICE_ID__VALUE				GENMASK(7, 0)
 
 #define DEVICE_PARAM_0				0x320
-#define     DEVICE_PARAM_0__VALUE			0x00ff
+#define     DEVICE_PARAM_0__VALUE			GENMASK(7, 0)
 
 #define DEVICE_PARAM_1				0x330
-#define     DEVICE_PARAM_1__VALUE			0x00ff
+#define     DEVICE_PARAM_1__VALUE			GENMASK(7, 0)
 
 #define DEVICE_PARAM_2				0x340
-#define     DEVICE_PARAM_2__VALUE			0x00ff
+#define     DEVICE_PARAM_2__VALUE			GENMASK(7, 0)
 
 #define LOGICAL_PAGE_DATA_SIZE			0x350
-#define     LOGICAL_PAGE_DATA_SIZE__VALUE		0xffff
+#define     LOGICAL_PAGE_DATA_SIZE__VALUE		GENMASK(15, 0)
 
 #define LOGICAL_PAGE_SPARE_SIZE			0x360
-#define     LOGICAL_PAGE_SPARE_SIZE__VALUE		0xffff
+#define     LOGICAL_PAGE_SPARE_SIZE__VALUE		GENMASK(15, 0)
 
 #define REVISION				0x370
-#define     REVISION__VALUE				0xffff
+#define     REVISION__VALUE				GENMASK(15, 0)
 
 #define ONFI_DEVICE_FEATURES			0x380
-#define     ONFI_DEVICE_FEATURES__VALUE			0x003f
+#define     ONFI_DEVICE_FEATURES__VALUE			GENMASK(5, 0)
 
 #define ONFI_OPTIONAL_COMMANDS			0x390
-#define     ONFI_OPTIONAL_COMMANDS__VALUE		0x003f
+#define     ONFI_OPTIONAL_COMMANDS__VALUE		GENMASK(5, 0)
 
 #define ONFI_TIMING_MODE			0x3a0
-#define     ONFI_TIMING_MODE__VALUE			0x003f
+#define     ONFI_TIMING_MODE__VALUE			GENMASK(5, 0)
 
 #define ONFI_PGM_CACHE_TIMING_MODE		0x3b0
-#define     ONFI_PGM_CACHE_TIMING_MODE__VALUE		0x003f
+#define     ONFI_PGM_CACHE_TIMING_MODE__VALUE		GENMASK(5, 0)
 
 #define ONFI_DEVICE_NO_OF_LUNS			0x3c0
-#define     ONFI_DEVICE_NO_OF_LUNS__NO_OF_LUNS		0x00ff
-#define     ONFI_DEVICE_NO_OF_LUNS__ONFI_DEVICE		0x0100
+#define     ONFI_DEVICE_NO_OF_LUNS__NO_OF_LUNS		GENMASK(7, 0)
+#define     ONFI_DEVICE_NO_OF_LUNS__ONFI_DEVICE		BIT(8)
 
 #define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_L	0x3d0
-#define     ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_L__VALUE	0xffff
+#define     ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_L__VALUE	GENMASK(15, 0)
 
 #define ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_U	0x3e0
-#define     ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_U__VALUE	0xffff
-
-#define FEATURES					0x3f0
-#define     FEATURES__N_BANKS				0x0003
-#define     FEATURES__ECC_MAX_ERR			0x003c
-#define     FEATURES__DMA				0x0040
-#define     FEATURES__CMD_DMA				0x0080
-#define     FEATURES__PARTITION				0x0100
-#define     FEATURES__XDMA_SIDEBAND			0x0200
-#define     FEATURES__GPREG				0x0400
-#define     FEATURES__INDEX_ADDR			0x0800
+#define     ONFI_DEVICE_NO_OF_BLOCKS_PER_LUN_U__VALUE	GENMASK(15, 0)
+
+#define FEATURES				0x3f0
+#define     FEATURES__N_BANKS				GENMASK(1, 0)
+#define     FEATURES__ECC_MAX_ERR			GENMASK(5, 2)
+#define     FEATURES__DMA				BIT(6)
+#define     FEATURES__CMD_DMA				BIT(7)
+#define     FEATURES__PARTITION				BIT(8)
+#define     FEATURES__XDMA_SIDEBAND			BIT(9)
+#define     FEATURES__GPREG				BIT(10)
+#define     FEATURES__INDEX_ADDR			BIT(11)
 
 #define TRANSFER_MODE				0x400
-#define     TRANSFER_MODE__VALUE			0x0003
+#define     TRANSFER_MODE__VALUE			GENMASK(1, 0)
 
-#define INTR_STATUS(__bank)	(0x410 + ((__bank) * 0x50))
-#define INTR_EN(__bank)		(0x420 + ((__bank) * 0x50))
+#define INTR_STATUS(bank)			(0x410 + (bank) * 0x50)
+#define INTR_EN(bank)				(0x420 + (bank) * 0x50)
 /* bit[1:0] is used differently depending on IP version */
-#define     INTR__ECC_UNCOR_ERR				0x0001	/* new IP */
-#define     INTR__ECC_TRANSACTION_DONE			0x0001	/* old IP */
-#define     INTR__ECC_ERR				0x0002	/* old IP */
-#define     INTR__DMA_CMD_COMP				0x0004
-#define     INTR__TIME_OUT				0x0008
-#define     INTR__PROGRAM_FAIL				0x0010
-#define     INTR__ERASE_FAIL				0x0020
-#define     INTR__LOAD_COMP				0x0040
-#define     INTR__PROGRAM_COMP				0x0080
-#define     INTR__ERASE_COMP				0x0100
-#define     INTR__PIPE_CPYBCK_CMD_COMP			0x0200
-#define     INTR__LOCKED_BLK				0x0400
-#define     INTR__UNSUP_CMD				0x0800
-#define     INTR__INT_ACT				0x1000
-#define     INTR__RST_COMP				0x2000
-#define     INTR__PIPE_CMD_ERR				0x4000
-#define     INTR__PAGE_XFER_INC				0x8000
-
-#define PAGE_CNT(__bank)	(0x430 + ((__bank) * 0x50))
-#define ERR_PAGE_ADDR(__bank)	(0x440 + ((__bank) * 0x50))
-#define ERR_BLOCK_ADDR(__bank)	(0x450 + ((__bank) * 0x50))
+#define     INTR__ECC_UNCOR_ERR				BIT(0)	/* new IP */
+#define     INTR__ECC_TRANSACTION_DONE			BIT(0)	/* old IP */
+#define     INTR__ECC_ERR				BIT(1)	/* old IP */
+#define     INTR__DMA_CMD_COMP				BIT(2)
+#define     INTR__TIME_OUT				BIT(3)
+#define     INTR__PROGRAM_FAIL				BIT(4)
+#define     INTR__ERASE_FAIL				BIT(5)
+#define     INTR__LOAD_COMP				BIT(6)
+#define     INTR__PROGRAM_COMP				BIT(7)
+#define     INTR__ERASE_COMP				BIT(8)
+#define     INTR__PIPE_CPYBCK_CMD_COMP			BIT(9)
+#define     INTR__LOCKED_BLK				BIT(10)
+#define     INTR__UNSUP_CMD				BIT(11)
+#define     INTR__INT_ACT				BIT(12)
+#define     INTR__RST_COMP				BIT(13)
+#define     INTR__PIPE_CMD_ERR				BIT(14)
+#define     INTR__PAGE_XFER_INC				BIT(15)
+#define     INTR__ERASED_PAGE				BIT(16)
+
+#define PAGE_CNT(bank)				(0x430 + (bank) * 0x50)
+#define ERR_PAGE_ADDR(bank)			(0x440 + (bank) * 0x50)
+#define ERR_BLOCK_ADDR(bank)			(0x450 + (bank) * 0x50)
 
 #define ECC_THRESHOLD				0x600
-#define     ECC_THRESHOLD__VALUE			0x03ff
+#define     ECC_THRESHOLD__VALUE			GENMASK(9, 0)
 
 #define ECC_ERROR_BLOCK_ADDRESS			0x610
-#define     ECC_ERROR_BLOCK_ADDRESS__VALUE		0xffff
+#define     ECC_ERROR_BLOCK_ADDRESS__VALUE		GENMASK(15, 0)
 
 #define ECC_ERROR_PAGE_ADDRESS			0x620
-#define     ECC_ERROR_PAGE_ADDRESS__VALUE		0x0fff
-#define     ECC_ERROR_PAGE_ADDRESS__BANK		0xf000
+#define     ECC_ERROR_PAGE_ADDRESS__VALUE		GENMASK(11, 0)
+#define     ECC_ERROR_PAGE_ADDRESS__BANK		GENMASK(15, 12)
 
 #define ECC_ERROR_ADDRESS			0x630
-#define     ECC_ERROR_ADDRESS__OFFSET			0x0fff
-#define     ECC_ERROR_ADDRESS__SECTOR_NR		0xf000
+#define     ECC_ERROR_ADDRESS__OFFSET			GENMASK(11, 0)
+#define     ECC_ERROR_ADDRESS__SECTOR_NR		GENMASK(15, 12)
 
 #define ERR_CORRECTION_INFO			0x640
-#define     ERR_CORRECTION_INFO__BYTEMASK		0x00ff
-#define     ERR_CORRECTION_INFO__DEVICE_NR		0x0f00
-#define     ERR_CORRECTION_INFO__ERROR_TYPE		0x4000
-#define     ERR_CORRECTION_INFO__LAST_ERR_INFO		0x8000
+#define     ERR_CORRECTION_INFO__BYTEMASK		GENMASK(7, 0)
+#define     ERR_CORRECTION_INFO__DEVICE_NR		GENMASK(11, 8)
+#define     ERR_CORRECTION_INFO__ERROR_TYPE		BIT(14)
+#define     ERR_CORRECTION_INFO__LAST_ERR_INFO		BIT(15)
 
 #define ECC_COR_INFO(bank)			(0x650 + (bank) / 2 * 0x10)
 #define     ECC_COR_INFO__SHIFT(bank)			((bank) % 2 * 8)
-#define     ECC_COR_INFO__MAX_ERRORS			0x007f
-#define     ECC_COR_INFO__UNCOR_ERR			0x0080
+#define     ECC_COR_INFO__MAX_ERRORS			GENMASK(6, 0)
+#define     ECC_COR_INFO__UNCOR_ERR			BIT(7)
+
+#define CFG_DATA_BLOCK_SIZE			0x6b0
+
+#define CFG_LAST_DATA_BLOCK_SIZE		0x6c0
+
+#define CFG_NUM_DATA_BLOCKS			0x6d0
+
+#define CFG_META_DATA_SIZE			0x6e0
 
 #define DMA_ENABLE				0x700
-#define     DMA_ENABLE__FLAG				0x0001
+#define     DMA_ENABLE__FLAG				BIT(0)
 
 #define IGNORE_ECC_DONE				0x710
-#define     IGNORE_ECC_DONE__FLAG			0x0001
+#define     IGNORE_ECC_DONE__FLAG			BIT(0)
 
 #define DMA_INTR				0x720
 #define DMA_INTR_EN				0x730
-#define     DMA_INTR__TARGET_ERROR			0x0001
-#define     DMA_INTR__DESC_COMP_CHANNEL0		0x0002
-#define     DMA_INTR__DESC_COMP_CHANNEL1		0x0004
-#define     DMA_INTR__DESC_COMP_CHANNEL2		0x0008
-#define     DMA_INTR__DESC_COMP_CHANNEL3		0x0010
-#define     DMA_INTR__MEMCOPY_DESC_COMP			0x0020
+#define     DMA_INTR__TARGET_ERROR			BIT(0)
+#define     DMA_INTR__DESC_COMP_CHANNEL0		BIT(1)
+#define     DMA_INTR__DESC_COMP_CHANNEL1		BIT(2)
+#define     DMA_INTR__DESC_COMP_CHANNEL2		BIT(3)
+#define     DMA_INTR__DESC_COMP_CHANNEL3		BIT(4)
+#define     DMA_INTR__MEMCOPY_DESC_COMP			BIT(5)
 
 #define TARGET_ERR_ADDR_LO			0x740
-#define     TARGET_ERR_ADDR_LO__VALUE			0xffff
+#define     TARGET_ERR_ADDR_LO__VALUE			GENMASK(15, 0)
 
 #define TARGET_ERR_ADDR_HI			0x750
-#define     TARGET_ERR_ADDR_HI__VALUE			0xffff
+#define     TARGET_ERR_ADDR_HI__VALUE			GENMASK(15, 0)
 
 #define CHNL_ACTIVE				0x760
-#define     CHNL_ACTIVE__CHANNEL0			0x0001
-#define     CHNL_ACTIVE__CHANNEL1			0x0002
-#define     CHNL_ACTIVE__CHANNEL2			0x0004
-#define     CHNL_ACTIVE__CHANNEL3			0x0008
-
-#define FAIL 1                  /*failed flag*/
-#define PASS 0                  /*success flag*/
-
-#define CLK_X  5
-#define CLK_MULTI 4
-
-#define ONFI_BLOOM_TIME         1
-#define MODE5_WORKAROUND        0
-
-
-#define MODE_00    0x00000000
-#define MODE_01    0x04000000
-#define MODE_10    0x08000000
-#define MODE_11    0x0C000000
-
-#define ECC_SECTOR_SIZE     512
-
-struct nand_buf {
-	int head;
-	int tail;
-	uint8_t *buf;
-	dma_addr_t dma_buf;
-};
-
-#define INTEL_CE4100	1
-#define INTEL_MRST	2
-#define DT		3
+#define     CHNL_ACTIVE__CHANNEL0			BIT(0)
+#define     CHNL_ACTIVE__CHANNEL1			BIT(1)
+#define     CHNL_ACTIVE__CHANNEL2			BIT(2)
+#define     CHNL_ACTIVE__CHANNEL3			BIT(3)
 
 struct denali_nand_info {
 	struct nand_chip nand;
-	int flash_bank; /* currently selected chip */
-	int status;
-	int platform;
-	struct nand_buf buf;
+	unsigned long clk_x_rate;	/* bus interface clock rate */
+	int active_bank;		/* currently selected bank */
 	struct device *dev;
-	int total_used_banks;
-	int page;
-	void __iomem *flash_reg;	/* Register Interface */
-	void __iomem *flash_mem;	/* Host Data/Command Interface */
+	void __iomem *reg;		/* Register Interface */
+	void __iomem *host;		/* Host Data/Command Interface */
 
 	/* elements used by ISR */
 	struct completion complete;
 	spinlock_t irq_lock;
+	uint32_t irq_mask;
 	uint32_t irq_status;
 	int irq;
 
-	int devnum;	/* represent how many nands connected */
-	int bbtskipbytes;
+	void *buf;
+	dma_addr_t dma_addr;
+	int dma_avail;
+	int devs_per_cs;		/* devices connected in parallel */
+	int oob_skip_bytes;
 	int max_banks;
 	unsigned int revision;
 	unsigned int caps;
+	const struct nand_ecc_caps *ecc_caps;
 };
 
 #define DENALI_CAP_HW_ECC_FIXUP			BIT(0)
 #define DENALI_CAP_DMA_64BIT			BIT(1)
 
+int denali_calc_ecc_bytes(int step_size, int strength);
 extern int denali_init(struct denali_nand_info *denali);
 extern void denali_remove(struct denali_nand_info *denali);
 
diff --git a/drivers/mtd/nand/denali_dt.c b/drivers/mtd/nand/denali_dt.c
index df9ef36cc2ce..47f398edf18f 100644
--- a/drivers/mtd/nand/denali_dt.c
+++ b/drivers/mtd/nand/denali_dt.c
@@ -32,10 +32,31 @@ struct denali_dt {
 struct denali_dt_data {
 	unsigned int revision;
 	unsigned int caps;
+	const struct nand_ecc_caps *ecc_caps;
 };
 
+NAND_ECC_CAPS_SINGLE(denali_socfpga_ecc_caps, denali_calc_ecc_bytes,
+		     512, 8, 15);
 static const struct denali_dt_data denali_socfpga_data = {
 	.caps = DENALI_CAP_HW_ECC_FIXUP,
+	.ecc_caps = &denali_socfpga_ecc_caps,
+};
+
+NAND_ECC_CAPS_SINGLE(denali_uniphier_v5a_ecc_caps, denali_calc_ecc_bytes,
+		     1024, 8, 16, 24);
+static const struct denali_dt_data denali_uniphier_v5a_data = {
+	.caps = DENALI_CAP_HW_ECC_FIXUP |
+		DENALI_CAP_DMA_64BIT,
+	.ecc_caps = &denali_uniphier_v5a_ecc_caps,
+};
+
+NAND_ECC_CAPS_SINGLE(denali_uniphier_v5b_ecc_caps, denali_calc_ecc_bytes,
+		     1024, 8, 16);
+static const struct denali_dt_data denali_uniphier_v5b_data = {
+	.revision = 0x0501,
+	.caps = DENALI_CAP_HW_ECC_FIXUP |
+		DENALI_CAP_DMA_64BIT,
+	.ecc_caps = &denali_uniphier_v5b_ecc_caps,
 };
 
 static const struct of_device_id denali_nand_dt_ids[] = {
@@ -43,13 +64,21 @@ static const struct of_device_id denali_nand_dt_ids[] = {
 		.compatible = "altr,socfpga-denali-nand",
 		.data = &denali_socfpga_data,
 	},
+	{
+		.compatible = "socionext,uniphier-denali-nand-v5a",
+		.data = &denali_uniphier_v5a_data,
+	},
+	{
+		.compatible = "socionext,uniphier-denali-nand-v5b",
+		.data = &denali_uniphier_v5b_data,
+	},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
 
 static int denali_dt_probe(struct platform_device *pdev)
 {
-	struct resource *denali_reg, *nand_data;
+	struct resource *res;
 	struct denali_dt *dt;
 	const struct denali_dt_data *data;
 	struct denali_nand_info *denali;
@@ -64,9 +93,9 @@ static int denali_dt_probe(struct platform_device *pdev)
 	if (data) {
 		denali->revision = data->revision;
 		denali->caps = data->caps;
+		denali->ecc_caps = data->ecc_caps;
 	}
 
-	denali->platform = DT;
 	denali->dev = &pdev->dev;
 	denali->irq = platform_get_irq(pdev, 0);
 	if (denali->irq < 0) {
@@ -74,17 +103,15 @@ static int denali_dt_probe(struct platform_device *pdev)
 		return denali->irq;
 	}
 
-	denali_reg = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						  "denali_reg");
-	denali->flash_reg = devm_ioremap_resource(&pdev->dev, denali_reg);
-	if (IS_ERR(denali->flash_reg))
-		return PTR_ERR(denali->flash_reg);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
+	denali->reg = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(denali->reg))
+		return PTR_ERR(denali->reg);
 
-	nand_data = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-						 "nand_data");
-	denali->flash_mem = devm_ioremap_resource(&pdev->dev, nand_data);
-	if (IS_ERR(denali->flash_mem))
-		return PTR_ERR(denali->flash_mem);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
+	denali->host = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(denali->host))
+		return PTR_ERR(denali->host);
 
 	dt->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(dt->clk)) {
@@ -93,6 +120,8 @@ static int denali_dt_probe(struct platform_device *pdev)
 	}
 	clk_prepare_enable(dt->clk);
 
+	denali->clk_x_rate = clk_get_rate(dt->clk);
+
 	ret = denali_init(denali);
 	if (ret)
 		goto out_disable_clk;
diff --git a/drivers/mtd/nand/denali_pci.c b/drivers/mtd/nand/denali_pci.c
index ac843238b77e..81370c79aa48 100644
--- a/drivers/mtd/nand/denali_pci.c
+++ b/drivers/mtd/nand/denali_pci.c
@@ -19,6 +19,9 @@
 
 #define DENALI_NAND_NAME    "denali-nand-pci"
 
+#define INTEL_CE4100	1
+#define INTEL_MRST	2
+
 /* List of platforms this NAND controller has be integrated into */
 static const struct pci_device_id denali_pci_ids[] = {
 	{ PCI_VDEVICE(INTEL, 0x0701), INTEL_CE4100 },
@@ -27,6 +30,8 @@ static const struct pci_device_id denali_pci_ids[] = {
 };
 MODULE_DEVICE_TABLE(pci, denali_pci_ids);
 
+NAND_ECC_CAPS_SINGLE(denali_pci_ecc_caps, denali_calc_ecc_bytes, 512, 8, 15);
+
 static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
 	int ret;
@@ -45,13 +50,11 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	if (id->driver_data == INTEL_CE4100) {
-		denali->platform = INTEL_CE4100;
 		mem_base = pci_resource_start(dev, 0);
 		mem_len = pci_resource_len(dev, 1);
 		csr_base = pci_resource_start(dev, 1);
 		csr_len = pci_resource_len(dev, 1);
 	} else {
-		denali->platform = INTEL_MRST;
 		csr_base = pci_resource_start(dev, 0);
 		csr_len = pci_resource_len(dev, 0);
 		mem_base = pci_resource_start(dev, 1);
@@ -65,6 +68,9 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	pci_set_master(dev);
 	denali->dev = &dev->dev;
 	denali->irq = dev->irq;
+	denali->ecc_caps = &denali_pci_ecc_caps;
+	denali->nand.ecc.options |= NAND_ECC_MAXIMIZE;
+	denali->clk_x_rate = 200000000;		/* 200 MHz */
 
 	ret = pci_request_regions(dev, DENALI_NAND_NAME);
 	if (ret) {
@@ -72,14 +78,14 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 		return ret;
 	}
 
-	denali->flash_reg = ioremap_nocache(csr_base, csr_len);
-	if (!denali->flash_reg) {
+	denali->reg = ioremap_nocache(csr_base, csr_len);
+	if (!denali->reg) {
 		dev_err(&dev->dev, "Spectra: Unable to remap memory region\n");
 		return -ENOMEM;
 	}
 
-	denali->flash_mem = ioremap_nocache(mem_base, mem_len);
-	if (!denali->flash_mem) {
+	denali->host = ioremap_nocache(mem_base, mem_len);
+	if (!denali->host) {
 		dev_err(&dev->dev, "Spectra: ioremap_nocache failed!");
 		ret = -ENOMEM;
 		goto failed_remap_reg;
@@ -94,9 +100,9 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	return 0;
 
 failed_remap_mem:
-	iounmap(denali->flash_mem);
+	iounmap(denali->host);
 failed_remap_reg:
-	iounmap(denali->flash_reg);
+	iounmap(denali->reg);
 	return ret;
 }
 
@@ -106,8 +112,8 @@ static void denali_pci_remove(struct pci_dev *dev)
 	struct denali_nand_info *denali = pci_get_drvdata(dev);
 
 	denali_remove(denali);
-	iounmap(denali->flash_reg);
-	iounmap(denali->flash_mem);
+	iounmap(denali->reg);
+	iounmap(denali->host);
 }
 
 static struct pci_driver denali_pci_driver = {
diff --git a/drivers/mtd/nand/docg4.c b/drivers/mtd/nand/docg4.c
index 7af2a3cd949e..a27a84fbfb84 100644
--- a/drivers/mtd/nand/docg4.c
+++ b/drivers/mtd/nand/docg4.c
@@ -1260,6 +1260,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->read_buf = docg4_read_buf;
 	nand->write_buf = docg4_write_buf16;
 	nand->erase = docg4_erase_block;
+	nand->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	nand->onfi_get_features = nand_onfi_get_set_features_notsupp;
 	nand->ecc.read_page = docg4_read_page;
 	nand->ecc.write_page = docg4_write_page;
 	nand->ecc.read_page_raw = docg4_read_page_raw;
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 113f76e59937..b9ac16f05057 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -775,6 +775,8 @@ static int fsl_elbc_chip_init(struct fsl_elbc_mtd *priv)
 	chip->select_chip = fsl_elbc_select_chip;
 	chip->cmdfunc = fsl_elbc_cmdfunc;
 	chip->waitfunc = fsl_elbc_wait;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	chip->bbt_td = &bbt_main_descr;
 	chip->bbt_md = &bbt_mirror_descr;
diff --git a/drivers/mtd/nand/fsl_ifc_nand.c b/drivers/mtd/nand/fsl_ifc_nand.c
index d1570f512f0b..59408ec2c69f 100644
--- a/drivers/mtd/nand/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/fsl_ifc_nand.c
@@ -171,34 +171,6 @@ static void set_addr(struct mtd_info *mtd, int column, int page_addr, int oob)
 		ifc_nand_ctrl->index += mtd->writesize;
 }
 
-static int is_blank(struct mtd_info *mtd, unsigned int bufnum)
-{
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
-	u8 __iomem *addr = priv->vbase + bufnum * (mtd->writesize * 2);
-	u32 __iomem *mainarea = (u32 __iomem *)addr;
-	u8 __iomem *oob = addr + mtd->writesize;
-	struct mtd_oob_region oobregion = { };
-	int i, section = 0;
-
-	for (i = 0; i < mtd->writesize / 4; i++) {
-		if (__raw_readl(&mainarea[i]) != 0xffffffff)
-			return 0;
-	}
-
-	mtd_ooblayout_ecc(mtd, section++, &oobregion);
-	while (oobregion.length) {
-		for (i = 0; i < oobregion.length; i++) {
-			if (__raw_readb(&oob[oobregion.offset + i]) != 0xff)
-				return 0;
-		}
-
-		mtd_ooblayout_ecc(mtd, section++, &oobregion);
-	}
-
-	return 1;
-}
-
 /* returns nonzero if entire page is blank */
 static int check_read_ecc(struct mtd_info *mtd, struct fsl_ifc_ctrl *ctrl,
 			  u32 *eccstat, unsigned int bufnum)
@@ -274,16 +246,14 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
 			if (errors == 15) {
 				/*
 				 * Uncorrectable error.
-				 * OK only if the whole page is blank.
+				 * We'll check for blank pages later.
 				 *
 				 * We disable ECCER reporting due to...
 				 * erratum IFC-A002770 -- so report it now if we
 				 * see an uncorrectable error in ECCSTAT.
 				 */
-				if (!is_blank(mtd, bufnum))
-					ctrl->nand_stat |=
-						IFC_NAND_EVTER_STAT_ECCER;
-				break;
+				ctrl->nand_stat |= IFC_NAND_EVTER_STAT_ECCER;
+				continue;
 			}
 
 			mtd->ecc_stats.corrected += errors;
@@ -678,6 +648,39 @@ static int fsl_ifc_wait(struct mtd_info *mtd, struct nand_chip *chip)
 	return nand_fsr | NAND_STATUS_WP;
 }
 
+/*
+ * The controller does not check for bitflips in erased pages,
+ * therefore software must check instead.
+ */
+static int check_erased_page(struct nand_chip *chip, u8 *buf)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u8 *ecc = chip->oob_poi;
+	const int ecc_size = chip->ecc.bytes;
+	const int pkt_size = chip->ecc.size;
+	int i, res, bitflips = 0;
+	struct mtd_oob_region oobregion = { };
+
+	mtd_ooblayout_ecc(mtd, 0, &oobregion);
+	ecc += oobregion.offset;
+
+	for (i = 0; i < chip->ecc.steps; ++i) {
+		res = nand_check_erased_ecc_chunk(buf, pkt_size, ecc, ecc_size,
+						  NULL, 0,
+						  chip->ecc.strength);
+		if (res < 0)
+			mtd->ecc_stats.failed++;
+		else
+			mtd->ecc_stats.corrected += res;
+
+		bitflips = max(res, bitflips);
+		buf += pkt_size;
+		ecc += ecc_size;
+	}
+
+	return bitflips;
+}
+
 static int fsl_ifc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 			     uint8_t *buf, int oob_required, int page)
 {
@@ -689,8 +692,12 @@ static int fsl_ifc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	if (oob_required)
 		fsl_ifc_read_buf(mtd, chip->oob_poi, mtd->oobsize);
 
-	if (ctrl->nand_stat & IFC_NAND_EVTER_STAT_ECCER)
-		dev_err(priv->dev, "NAND Flash ECC Uncorrectable Error\n");
+	if (ctrl->nand_stat & IFC_NAND_EVTER_STAT_ECCER) {
+		if (!oob_required)
+			fsl_ifc_read_buf(mtd, chip->oob_poi, mtd->oobsize);
+
+		return check_erased_page(chip, buf);
+	}
 
 	if (ctrl->nand_stat != IFC_NAND_EVTER_STAT_OPC)
 		mtd->ecc_stats.failed++;
@@ -831,6 +838,8 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 	chip->select_chip = fsl_ifc_select_chip;
 	chip->cmdfunc = fsl_ifc_cmdfunc;
 	chip->waitfunc = fsl_ifc_wait;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	chip->bbt_td = &bbt_main_descr;
 	chip->bbt_md = &bbt_mirror_descr;
@@ -904,7 +913,7 @@ static int fsl_ifc_chip_init(struct fsl_ifc_mtd *priv)
 		chip->ecc.algo = NAND_ECC_HAMMING;
 	}
 
-	if (ctrl->version == FSL_IFC_VERSION_1_1_0)
+	if (ctrl->version >= FSL_IFC_VERSION_1_1_0)
 		fsl_ifc_sram_init(priv);
 
 	return 0;
diff --git a/drivers/mtd/nand/fsmc_nand.c b/drivers/mtd/nand/fsmc_nand.c
index cea50d2f218c..9d8b051d3187 100644
--- a/drivers/mtd/nand/fsmc_nand.c
+++ b/drivers/mtd/nand/fsmc_nand.c
@@ -302,25 +302,13 @@ static void fsmc_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
  * This routine initializes timing parameters related to NAND memory access in
  * FSMC registers
  */
-static void fsmc_nand_setup(void __iomem *regs, uint32_t bank,
-			   uint32_t busw, struct fsmc_nand_timings *timings)
+static void fsmc_nand_setup(struct fsmc_nand_data *host,
+			    struct fsmc_nand_timings *tims)
 {
 	uint32_t value = FSMC_DEVTYPE_NAND | FSMC_ENABLE | FSMC_WAITON;
 	uint32_t tclr, tar, thiz, thold, twait, tset;
-	struct fsmc_nand_timings *tims;
-	struct fsmc_nand_timings default_timings = {
-		.tclr	= FSMC_TCLR_1,
-		.tar	= FSMC_TAR_1,
-		.thiz	= FSMC_THIZ_1,
-		.thold	= FSMC_THOLD_4,
-		.twait	= FSMC_TWAIT_6,
-		.tset	= FSMC_TSET_0,
-	};
-
-	if (timings)
-		tims = timings;
-	else
-		tims = &default_timings;
+	unsigned int bank = host->bank;
+	void __iomem *regs = host->regs_va;
 
 	tclr = (tims->tclr & FSMC_TCLR_MASK) << FSMC_TCLR_SHIFT;
 	tar = (tims->tar & FSMC_TAR_MASK) << FSMC_TAR_SHIFT;
@@ -329,7 +317,7 @@ static void fsmc_nand_setup(void __iomem *regs, uint32_t bank,
 	twait = (tims->twait & FSMC_TWAIT_MASK) << FSMC_TWAIT_SHIFT;
 	tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT;
 
-	if (busw)
+	if (host->nand.options & NAND_BUSWIDTH_16)
 		writel_relaxed(value | FSMC_DEVWID_16,
 				FSMC_NAND_REG(regs, bank, PC));
 	else
@@ -344,6 +332,87 @@ static void fsmc_nand_setup(void __iomem *regs, uint32_t bank,
 			FSMC_NAND_REG(regs, bank, ATTRIB));
 }
 
+static int fsmc_calc_timings(struct fsmc_nand_data *host,
+			     const struct nand_sdr_timings *sdrt,
+			     struct fsmc_nand_timings *tims)
+{
+	unsigned long hclk = clk_get_rate(host->clk);
+	unsigned long hclkn = NSEC_PER_SEC / hclk;
+	uint32_t thiz, thold, twait, tset;
+
+	if (sdrt->tRC_min < 30000)
+		return -EOPNOTSUPP;
+
+	tims->tar = DIV_ROUND_UP(sdrt->tAR_min / 1000, hclkn) - 1;
+	if (tims->tar > FSMC_TAR_MASK)
+		tims->tar = FSMC_TAR_MASK;
+	tims->tclr = DIV_ROUND_UP(sdrt->tCLR_min / 1000, hclkn) - 1;
+	if (tims->tclr > FSMC_TCLR_MASK)
+		tims->tclr = FSMC_TCLR_MASK;
+
+	thiz = sdrt->tCS_min - sdrt->tWP_min;
+	tims->thiz = DIV_ROUND_UP(thiz / 1000, hclkn);
+
+	thold = sdrt->tDH_min;
+	if (thold < sdrt->tCH_min)
+		thold = sdrt->tCH_min;
+	if (thold < sdrt->tCLH_min)
+		thold = sdrt->tCLH_min;
+	if (thold < sdrt->tWH_min)
+		thold = sdrt->tWH_min;
+	if (thold < sdrt->tALH_min)
+		thold = sdrt->tALH_min;
+	if (thold < sdrt->tREH_min)
+		thold = sdrt->tREH_min;
+	tims->thold = DIV_ROUND_UP(thold / 1000, hclkn);
+	if (tims->thold == 0)
+		tims->thold = 1;
+	else if (tims->thold > FSMC_THOLD_MASK)
+		tims->thold = FSMC_THOLD_MASK;
+
+	twait = max(sdrt->tRP_min, sdrt->tWP_min);
+	tims->twait = DIV_ROUND_UP(twait / 1000, hclkn) - 1;
+	if (tims->twait == 0)
+		tims->twait = 1;
+	else if (tims->twait > FSMC_TWAIT_MASK)
+		tims->twait = FSMC_TWAIT_MASK;
+
+	tset = max(sdrt->tCS_min - sdrt->tWP_min,
+		   sdrt->tCEA_max - sdrt->tREA_max);
+	tims->tset = DIV_ROUND_UP(tset / 1000, hclkn) - 1;
+	if (tims->tset == 0)
+		tims->tset = 1;
+	else if (tims->tset > FSMC_TSET_MASK)
+		tims->tset = FSMC_TSET_MASK;
+
+	return 0;
+}
+
+static int fsmc_setup_data_interface(struct mtd_info *mtd, int csline,
+				     const struct nand_data_interface *conf)
+{
+	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct fsmc_nand_data *host = nand_get_controller_data(nand);
+	struct fsmc_nand_timings tims;
+	const struct nand_sdr_timings *sdrt;
+	int ret;
+
+	sdrt = nand_get_sdr_timings(conf);
+	if (IS_ERR(sdrt))
+		return PTR_ERR(sdrt);
+
+	ret = fsmc_calc_timings(host, sdrt, &tims);
+	if (ret)
+		return ret;
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	fsmc_nand_setup(host, &tims);
+
+	return 0;
+}
+
 /*
  * fsmc_enable_hwecc - Enables Hardware ECC through FSMC registers
  */
@@ -796,10 +865,8 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 		return -ENOMEM;
 	ret = of_property_read_u8_array(np, "timings", (u8 *)host->dev_timings,
 						sizeof(*host->dev_timings));
-	if (ret) {
-		dev_info(&pdev->dev, "No timings in dts specified, using default timings!\n");
+	if (ret)
 		host->dev_timings = NULL;
-	}
 
 	/* Set default NAND bank to 0 */
 	host->bank = 0;
@@ -933,9 +1000,10 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 		break;
 	}
 
-	fsmc_nand_setup(host->regs_va, host->bank,
-			nand->options & NAND_BUSWIDTH_16,
-			host->dev_timings);
+	if (host->dev_timings)
+		fsmc_nand_setup(host, host->dev_timings);
+	else
+		nand->setup_data_interface = fsmc_setup_data_interface;
 
 	if (AMBA_REV_BITS(host->pid) >= 8) {
 		nand->ecc.read_page = fsmc_read_page_hwecc;
@@ -986,6 +1054,9 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 				break;
 			}
 
+		case NAND_ECC_ON_DIE:
+			break;
+
 		default:
 			dev_err(&pdev->dev, "Unsupported ECC mode!\n");
 			goto err_probe;
@@ -1073,9 +1144,8 @@ static int fsmc_nand_resume(struct device *dev)
 	struct fsmc_nand_data *host = dev_get_drvdata(dev);
 	if (host) {
 		clk_prepare_enable(host->clk);
-		fsmc_nand_setup(host->regs_va, host->bank,
-				host->nand.options & NAND_BUSWIDTH_16,
-				host->dev_timings);
+		if (host->dev_timings)
+			fsmc_nand_setup(host, host->dev_timings);
 	}
 	return 0;
 }
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
index 141bd70a49c2..97787246af41 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-lib.c
@@ -26,7 +26,7 @@
 #include "gpmi-regs.h"
 #include "bch-regs.h"
 
-static struct timing_threshod timing_default_threshold = {
+static struct timing_threshold timing_default_threshold = {
 	.max_data_setup_cycles       = (BM_GPMI_TIMING0_DATA_SETUP >>
 						BP_GPMI_TIMING0_DATA_SETUP),
 	.internal_data_setup_in_ns   = 0,
@@ -329,7 +329,7 @@ static unsigned int ns_to_cycles(unsigned int time,
 static int gpmi_nfc_compute_hardware_timing(struct gpmi_nand_data *this,
 					struct gpmi_nfc_hardware_timing *hw)
 {
-	struct timing_threshod *nfc = &timing_default_threshold;
+	struct timing_threshold *nfc = &timing_default_threshold;
 	struct resources *r = &this->resources;
 	struct nand_chip *nand = &this->nand;
 	struct nand_timing target = this->timing;
@@ -932,7 +932,7 @@ static int enable_edo_mode(struct gpmi_nand_data *this, int mode)
 
 	nand->select_chip(mtd, 0);
 
-	/* [1] send SET FEATURE commond to NAND */
+	/* [1] send SET FEATURE command to NAND */
 	feature[0] = mode;
 	ret = nand->onfi_set_features(mtd, nand,
 				ONFI_FEATURE_ADDR_TIMING_MODE, feature);
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index d52139635b67..50f8d4a1b983 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -82,6 +82,10 @@ static int gpmi_ooblayout_free(struct mtd_info *mtd, int section,
 	return 0;
 }
 
+static const char * const gpmi_clks_for_mx2x[] = {
+	"gpmi_io",
+};
+
 static const struct mtd_ooblayout_ops gpmi_ooblayout_ops = {
 	.ecc = gpmi_ooblayout_ecc,
 	.free = gpmi_ooblayout_free,
@@ -91,24 +95,48 @@ static const struct gpmi_devdata gpmi_devdata_imx23 = {
 	.type = IS_MX23,
 	.bch_max_ecc_strength = 20,
 	.max_chain_delay = 16,
+	.clks = gpmi_clks_for_mx2x,
+	.clks_count = ARRAY_SIZE(gpmi_clks_for_mx2x),
 };
 
 static const struct gpmi_devdata gpmi_devdata_imx28 = {
 	.type = IS_MX28,
 	.bch_max_ecc_strength = 20,
 	.max_chain_delay = 16,
+	.clks = gpmi_clks_for_mx2x,
+	.clks_count = ARRAY_SIZE(gpmi_clks_for_mx2x),
+};
+
+static const char * const gpmi_clks_for_mx6[] = {
+	"gpmi_io", "gpmi_apb", "gpmi_bch", "gpmi_bch_apb", "per1_bch",
 };
 
 static const struct gpmi_devdata gpmi_devdata_imx6q = {
 	.type = IS_MX6Q,
 	.bch_max_ecc_strength = 40,
 	.max_chain_delay = 12,
+	.clks = gpmi_clks_for_mx6,
+	.clks_count = ARRAY_SIZE(gpmi_clks_for_mx6),
 };
 
 static const struct gpmi_devdata gpmi_devdata_imx6sx = {
 	.type = IS_MX6SX,
 	.bch_max_ecc_strength = 62,
 	.max_chain_delay = 12,
+	.clks = gpmi_clks_for_mx6,
+	.clks_count = ARRAY_SIZE(gpmi_clks_for_mx6),
+};
+
+static const char * const gpmi_clks_for_mx7d[] = {
+	"gpmi_io", "gpmi_bch_apb",
+};
+
+static const struct gpmi_devdata gpmi_devdata_imx7d = {
+	.type = IS_MX7D,
+	.bch_max_ecc_strength = 62,
+	.max_chain_delay = 12,
+	.clks = gpmi_clks_for_mx7d,
+	.clks_count = ARRAY_SIZE(gpmi_clks_for_mx7d),
 };
 
 static irqreturn_t bch_irq(int irq, void *cookie)
@@ -599,35 +627,14 @@ acquire_err:
 	return -EINVAL;
 }
 
-static char *extra_clks_for_mx6q[GPMI_CLK_MAX] = {
-	"gpmi_apb", "gpmi_bch", "gpmi_bch_apb", "per1_bch",
-};
-
 static int gpmi_get_clks(struct gpmi_nand_data *this)
 {
 	struct resources *r = &this->resources;
-	char **extra_clks = NULL;
 	struct clk *clk;
 	int err, i;
 
-	/* The main clock is stored in the first. */
-	r->clock[0] = devm_clk_get(this->dev, "gpmi_io");
-	if (IS_ERR(r->clock[0])) {
-		err = PTR_ERR(r->clock[0]);
-		goto err_clock;
-	}
-
-	/* Get extra clocks */
-	if (GPMI_IS_MX6(this))
-		extra_clks = extra_clks_for_mx6q;
-	if (!extra_clks)
-		return 0;
-
-	for (i = 1; i < GPMI_CLK_MAX; i++) {
-		if (extra_clks[i - 1] == NULL)
-			break;
-
-		clk = devm_clk_get(this->dev, extra_clks[i - 1]);
+	for (i = 0; i < this->devdata->clks_count; i++) {
+		clk = devm_clk_get(this->dev, this->devdata->clks[i]);
 		if (IS_ERR(clk)) {
 			err = PTR_ERR(clk);
 			goto err_clock;
@@ -1929,12 +1936,6 @@ static int gpmi_set_geometry(struct gpmi_nand_data *this)
 	return gpmi_alloc_dma_buffer(this);
 }
 
-static void gpmi_nand_exit(struct gpmi_nand_data *this)
-{
-	nand_release(nand_to_mtd(&this->nand));
-	gpmi_free_dma_buffer(this);
-}
-
 static int gpmi_init_last(struct gpmi_nand_data *this)
 {
 	struct nand_chip *chip = &this->nand;
@@ -2048,18 +2049,20 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 
 	ret = nand_boot_init(this);
 	if (ret)
-		goto err_out;
+		goto err_nand_cleanup;
 	ret = chip->scan_bbt(mtd);
 	if (ret)
-		goto err_out;
+		goto err_nand_cleanup;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret)
-		goto err_out;
+		goto err_nand_cleanup;
 	return 0;
 
+err_nand_cleanup:
+	nand_cleanup(chip);
 err_out:
-	gpmi_nand_exit(this);
+	gpmi_free_dma_buffer(this);
 	return ret;
 }
 
@@ -2076,6 +2079,9 @@ static const struct of_device_id gpmi_nand_id_table[] = {
 	}, {
 		.compatible = "fsl,imx6sx-gpmi-nand",
 		.data = &gpmi_devdata_imx6sx,
+	}, {
+		.compatible = "fsl,imx7d-gpmi-nand",
+		.data = &gpmi_devdata_imx7d,
 	}, {}
 };
 MODULE_DEVICE_TABLE(of, gpmi_nand_id_table);
@@ -2129,7 +2135,8 @@ static int gpmi_nand_remove(struct platform_device *pdev)
 {
 	struct gpmi_nand_data *this = platform_get_drvdata(pdev);
 
-	gpmi_nand_exit(this);
+	nand_release(nand_to_mtd(&this->nand));
+	gpmi_free_dma_buffer(this);
 	release_resources(this);
 	return 0;
 }
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
index 4e49a1f5fa27..9df0ad64e7e0 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.h
@@ -123,13 +123,16 @@ enum gpmi_type {
 	IS_MX23,
 	IS_MX28,
 	IS_MX6Q,
-	IS_MX6SX
+	IS_MX6SX,
+	IS_MX7D,
 };
 
 struct gpmi_devdata {
 	enum gpmi_type type;
 	int bch_max_ecc_strength;
 	int max_chain_delay; /* See the async EDO mode */
+	const char * const *clks;
+	const int clks_count;
 };
 
 struct gpmi_nand_data {
@@ -231,7 +234,7 @@ struct gpmi_nfc_hardware_timing {
 };
 
 /**
- * struct timing_threshod - Timing threshold
+ * struct timing_threshold - Timing threshold
  * @max_data_setup_cycles:       The maximum number of data setup cycles that
  *                               can be expressed in the hardware.
  * @internal_data_setup_in_ns:   The time, in ns, that the NFC hardware requires
@@ -253,7 +256,7 @@ struct gpmi_nfc_hardware_timing {
  *                               progress, this is the clock frequency during
  *                               the most recent I/O transaction.
  */
-struct timing_threshod {
+struct timing_threshold {
 	const unsigned int      max_chip_count;
 	const unsigned int      max_data_setup_cycles;
 	const unsigned int      internal_data_setup_in_ns;
@@ -305,6 +308,8 @@ void gpmi_copy_bits(u8 *dst, size_t dst_bit_off,
 #define GPMI_IS_MX28(x)		((x)->devdata->type == IS_MX28)
 #define GPMI_IS_MX6Q(x)		((x)->devdata->type == IS_MX6Q)
 #define GPMI_IS_MX6SX(x)	((x)->devdata->type == IS_MX6SX)
+#define GPMI_IS_MX7D(x)		((x)->devdata->type == IS_MX7D)
 
-#define GPMI_IS_MX6(x)		(GPMI_IS_MX6Q(x) || GPMI_IS_MX6SX(x))
+#define GPMI_IS_MX6(x)		(GPMI_IS_MX6Q(x) || GPMI_IS_MX6SX(x) || \
+				 GPMI_IS_MX7D(x))
 #endif
diff --git a/drivers/mtd/nand/hisi504_nand.c b/drivers/mtd/nand/hisi504_nand.c
index e40364eeb556..530caa80b1b6 100644
--- a/drivers/mtd/nand/hisi504_nand.c
+++ b/drivers/mtd/nand/hisi504_nand.c
@@ -764,6 +764,8 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 	chip->write_buf		= hisi_nfc_write_buf;
 	chip->read_buf		= hisi_nfc_read_buf;
 	chip->chip_delay	= HINFC504_CHIP_DELAY;
+	chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 
 	hisi_nfc_host_init(host);
 
diff --git a/drivers/mtd/nand/jz4780_nand.c b/drivers/mtd/nand/jz4780_nand.c
index a39bb70175ee..8bc835f71b26 100644
--- a/drivers/mtd/nand/jz4780_nand.c
+++ b/drivers/mtd/nand/jz4780_nand.c
@@ -205,7 +205,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 		return -EINVAL;
 	}
 
-	mtd->ooblayout = &nand_ooblayout_lp_ops;
+	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/mpc5121_nfc.c b/drivers/mtd/nand/mpc5121_nfc.c
index 6d6eaed2d20c..0e86fb6277c3 100644
--- a/drivers/mtd/nand/mpc5121_nfc.c
+++ b/drivers/mtd/nand/mpc5121_nfc.c
@@ -708,6 +708,8 @@ static int mpc5121_nfc_probe(struct platform_device *op)
 	chip->read_buf = mpc5121_nfc_read_buf;
 	chip->write_buf = mpc5121_nfc_write_buf;
 	chip->select_chip = mpc5121_nfc_select_chip;
+	chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 	chip->bbt_options = NAND_BBT_USE_FLASH;
 	chip->ecc.mode = NAND_ECC_SOFT;
 	chip->ecc.algo = NAND_ECC_HAMMING;
diff --git a/drivers/mtd/nand/mtk_ecc.c b/drivers/mtd/nand/mtk_ecc.c
index dbf256217b3e..6c3a4aab0b48 100644
--- a/drivers/mtd/nand/mtk_ecc.c
+++ b/drivers/mtd/nand/mtk_ecc.c
@@ -28,36 +28,16 @@
 
 #define ECC_IDLE_MASK		BIT(0)
 #define ECC_IRQ_EN		BIT(0)
+#define ECC_PG_IRQ_SEL		BIT(1)
 #define ECC_OP_ENABLE		(1)
 #define ECC_OP_DISABLE		(0)
 
 #define ECC_ENCCON		(0x00)
 #define ECC_ENCCNFG		(0x04)
-#define		ECC_CNFG_4BIT		(0)
-#define		ECC_CNFG_6BIT		(1)
-#define		ECC_CNFG_8BIT		(2)
-#define		ECC_CNFG_10BIT		(3)
-#define		ECC_CNFG_12BIT		(4)
-#define		ECC_CNFG_14BIT		(5)
-#define		ECC_CNFG_16BIT		(6)
-#define		ECC_CNFG_18BIT		(7)
-#define		ECC_CNFG_20BIT		(8)
-#define		ECC_CNFG_22BIT		(9)
-#define		ECC_CNFG_24BIT		(0xa)
-#define		ECC_CNFG_28BIT		(0xb)
-#define		ECC_CNFG_32BIT		(0xc)
-#define		ECC_CNFG_36BIT		(0xd)
-#define		ECC_CNFG_40BIT		(0xe)
-#define		ECC_CNFG_44BIT		(0xf)
-#define		ECC_CNFG_48BIT		(0x10)
-#define		ECC_CNFG_52BIT		(0x11)
-#define		ECC_CNFG_56BIT		(0x12)
-#define		ECC_CNFG_60BIT		(0x13)
 #define		ECC_MODE_SHIFT		(5)
 #define		ECC_MS_SHIFT		(16)
 #define ECC_ENCDIADDR		(0x08)
 #define ECC_ENCIDLE		(0x0C)
-#define ECC_ENCPAR(x)		(0x10 + (x) * sizeof(u32))
 #define ECC_ENCIRQ_EN		(0x80)
 #define ECC_ENCIRQ_STA		(0x84)
 #define ECC_DECCON		(0x100)
@@ -66,7 +46,6 @@
 #define		DEC_CNFG_CORRECT	(0x3 << 12)
 #define ECC_DECIDLE		(0x10C)
 #define ECC_DECENUM0		(0x114)
-#define		ERR_MASK		(0x3f)
 #define ECC_DECDONE		(0x124)
 #define ECC_DECIRQ_EN		(0x200)
 #define ECC_DECIRQ_STA		(0x204)
@@ -78,8 +57,17 @@
 #define ECC_IRQ_REG(op)		((op) == ECC_ENCODE ? \
 					ECC_ENCIRQ_EN : ECC_DECIRQ_EN)
 
+struct mtk_ecc_caps {
+	u32 err_mask;
+	const u8 *ecc_strength;
+	u8 num_ecc_strength;
+	u32 encode_parity_reg0;
+	int pg_irq_sel;
+};
+
 struct mtk_ecc {
 	struct device *dev;
+	const struct mtk_ecc_caps *caps;
 	void __iomem *regs;
 	struct clk *clk;
 
@@ -87,7 +75,18 @@ struct mtk_ecc {
 	struct mutex lock;
 	u32 sectors;
 
-	u8 eccdata[112];
+	u8 *eccdata;
+};
+
+/* ecc strength that each IP supports */
+static const u8 ecc_strength_mt2701[] = {
+	4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
+	40, 44, 48, 52, 56, 60
+};
+
+static const u8 ecc_strength_mt2712[] = {
+	4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
+	40, 44, 48, 52, 56, 60, 68, 72, 80
 };
 
 static inline void mtk_ecc_wait_idle(struct mtk_ecc *ecc,
@@ -136,77 +135,24 @@ static irqreturn_t mtk_ecc_irq(int irq, void *id)
 	return IRQ_HANDLED;
 }
 
-static void mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
+static int mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
 {
-	u32 ecc_bit = ECC_CNFG_4BIT, dec_sz, enc_sz;
-	u32 reg;
-
-	switch (config->strength) {
-	case 4:
-		ecc_bit = ECC_CNFG_4BIT;
-		break;
-	case 6:
-		ecc_bit = ECC_CNFG_6BIT;
-		break;
-	case 8:
-		ecc_bit = ECC_CNFG_8BIT;
-		break;
-	case 10:
-		ecc_bit = ECC_CNFG_10BIT;
-		break;
-	case 12:
-		ecc_bit = ECC_CNFG_12BIT;
-		break;
-	case 14:
-		ecc_bit = ECC_CNFG_14BIT;
-		break;
-	case 16:
-		ecc_bit = ECC_CNFG_16BIT;
-		break;
-	case 18:
-		ecc_bit = ECC_CNFG_18BIT;
-		break;
-	case 20:
-		ecc_bit = ECC_CNFG_20BIT;
-		break;
-	case 22:
-		ecc_bit = ECC_CNFG_22BIT;
-		break;
-	case 24:
-		ecc_bit = ECC_CNFG_24BIT;
-		break;
-	case 28:
-		ecc_bit = ECC_CNFG_28BIT;
-		break;
-	case 32:
-		ecc_bit = ECC_CNFG_32BIT;
-		break;
-	case 36:
-		ecc_bit = ECC_CNFG_36BIT;
-		break;
-	case 40:
-		ecc_bit = ECC_CNFG_40BIT;
-		break;
-	case 44:
-		ecc_bit = ECC_CNFG_44BIT;
-		break;
-	case 48:
-		ecc_bit = ECC_CNFG_48BIT;
-		break;
-	case 52:
-		ecc_bit = ECC_CNFG_52BIT;
-		break;
-	case 56:
-		ecc_bit = ECC_CNFG_56BIT;
-		break;
-	case 60:
-		ecc_bit = ECC_CNFG_60BIT;
-		break;
-	default:
-		dev_err(ecc->dev, "invalid strength %d, default to 4 bits\n",
+	u32 ecc_bit, dec_sz, enc_sz;
+	u32 reg, i;
+
+	for (i = 0; i < ecc->caps->num_ecc_strength; i++) {
+		if (ecc->caps->ecc_strength[i] == config->strength)
+			break;
+	}
+
+	if (i == ecc->caps->num_ecc_strength) {
+		dev_err(ecc->dev, "invalid ecc strength %d\n",
 			config->strength);
+		return -EINVAL;
 	}
 
+	ecc_bit = i;
+
 	if (config->op == ECC_ENCODE) {
 		/* configure ECC encoder (in bits) */
 		enc_sz = config->len << 3;
@@ -232,6 +178,8 @@ static void mtk_ecc_config(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
 		if (config->sectors)
 			ecc->sectors = 1 << (config->sectors - 1);
 	}
+
+	return 0;
 }
 
 void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats,
@@ -247,8 +195,8 @@ void mtk_ecc_get_stats(struct mtk_ecc *ecc, struct mtk_ecc_stats *stats,
 		offset = (i >> 2) << 2;
 		err = readl(ecc->regs + ECC_DECENUM0 + offset);
 		err = err >> ((i % 4) * 8);
-		err &= ERR_MASK;
-		if (err == ERR_MASK) {
+		err &= ecc->caps->err_mask;
+		if (err == ecc->caps->err_mask) {
 			/* uncorrectable errors */
 			stats->failed++;
 			continue;
@@ -313,6 +261,7 @@ EXPORT_SYMBOL(of_mtk_ecc_get);
 int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
 {
 	enum mtk_ecc_operation op = config->op;
+	u16 reg_val;
 	int ret;
 
 	ret = mutex_lock_interruptible(&ecc->lock);
@@ -322,11 +271,27 @@ int mtk_ecc_enable(struct mtk_ecc *ecc, struct mtk_ecc_config *config)
 	}
 
 	mtk_ecc_wait_idle(ecc, op);
-	mtk_ecc_config(ecc, config);
-	writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op));
 
-	init_completion(&ecc->done);
-	writew(ECC_IRQ_EN, ecc->regs + ECC_IRQ_REG(op));
+	ret = mtk_ecc_config(ecc, config);
+	if (ret) {
+		mutex_unlock(&ecc->lock);
+		return ret;
+	}
+
+	if (config->mode != ECC_NFI_MODE || op != ECC_ENCODE) {
+		init_completion(&ecc->done);
+		reg_val = ECC_IRQ_EN;
+		/*
+		 * For ECC_NFI_MODE, if ecc->caps->pg_irq_sel is 1, then it
+		 * means this chip can only generate one ecc irq during page
+		 * read / write. If is 0, generate one ecc irq each ecc step.
+		 */
+		if (ecc->caps->pg_irq_sel && config->mode == ECC_NFI_MODE)
+			reg_val |= ECC_PG_IRQ_SEL;
+		writew(reg_val, ecc->regs + ECC_IRQ_REG(op));
+	}
+
+	writew(ECC_OP_ENABLE, ecc->regs + ECC_CTL_REG(op));
 
 	return 0;
 }
@@ -396,7 +361,9 @@ int mtk_ecc_encode(struct mtk_ecc *ecc, struct mtk_ecc_config *config,
 	len = (config->strength * ECC_PARITY_BITS + 7) >> 3;
 
 	/* write the parity bytes generated by the ECC back to temp buffer */
-	__ioread32_copy(ecc->eccdata, ecc->regs + ECC_ENCPAR(0), round_up(len, 4));
+	__ioread32_copy(ecc->eccdata,
+			ecc->regs + ecc->caps->encode_parity_reg0,
+			round_up(len, 4));
 
 	/* copy into possibly unaligned OOB region with actual length */
 	memcpy(data + bytes, ecc->eccdata, len);
@@ -409,37 +376,79 @@ timeout:
 }
 EXPORT_SYMBOL(mtk_ecc_encode);
 
-void mtk_ecc_adjust_strength(u32 *p)
+void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p)
 {
-	u32 ecc[] = {4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 28, 32, 36,
-			40, 44, 48, 52, 56, 60};
+	const u8 *ecc_strength = ecc->caps->ecc_strength;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(ecc); i++) {
-		if (*p <= ecc[i]) {
+	for (i = 0; i < ecc->caps->num_ecc_strength; i++) {
+		if (*p <= ecc_strength[i]) {
 			if (!i)
-				*p = ecc[i];
-			else if (*p != ecc[i])
-				*p = ecc[i - 1];
+				*p = ecc_strength[i];
+			else if (*p != ecc_strength[i])
+				*p = ecc_strength[i - 1];
 			return;
 		}
 	}
 
-	*p = ecc[ARRAY_SIZE(ecc) - 1];
+	*p = ecc_strength[ecc->caps->num_ecc_strength - 1];
 }
 EXPORT_SYMBOL(mtk_ecc_adjust_strength);
 
+static const struct mtk_ecc_caps mtk_ecc_caps_mt2701 = {
+	.err_mask = 0x3f,
+	.ecc_strength = ecc_strength_mt2701,
+	.num_ecc_strength = 20,
+	.encode_parity_reg0 = 0x10,
+	.pg_irq_sel = 0,
+};
+
+static const struct mtk_ecc_caps mtk_ecc_caps_mt2712 = {
+	.err_mask = 0x7f,
+	.ecc_strength = ecc_strength_mt2712,
+	.num_ecc_strength = 23,
+	.encode_parity_reg0 = 0x300,
+	.pg_irq_sel = 1,
+};
+
+static const struct of_device_id mtk_ecc_dt_match[] = {
+	{
+		.compatible = "mediatek,mt2701-ecc",
+		.data = &mtk_ecc_caps_mt2701,
+	}, {
+		.compatible = "mediatek,mt2712-ecc",
+		.data = &mtk_ecc_caps_mt2712,
+	},
+	{},
+};
+
 static int mtk_ecc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct mtk_ecc *ecc;
 	struct resource *res;
+	const struct of_device_id *of_ecc_id = NULL;
+	u32 max_eccdata_size;
 	int irq, ret;
 
 	ecc = devm_kzalloc(dev, sizeof(*ecc), GFP_KERNEL);
 	if (!ecc)
 		return -ENOMEM;
 
+	of_ecc_id = of_match_device(mtk_ecc_dt_match, &pdev->dev);
+	if (!of_ecc_id)
+		return -ENODEV;
+
+	ecc->caps = of_ecc_id->data;
+
+	max_eccdata_size = ecc->caps->num_ecc_strength - 1;
+	max_eccdata_size = ecc->caps->ecc_strength[max_eccdata_size];
+	max_eccdata_size = (max_eccdata_size * ECC_PARITY_BITS + 7) >> 3;
+	max_eccdata_size = round_up(max_eccdata_size, 4);
+	ecc->eccdata = devm_kzalloc(dev, max_eccdata_size, GFP_KERNEL);
+	if (!ecc->eccdata)
+		return -ENOMEM;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ecc->regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(ecc->regs)) {
@@ -500,19 +509,12 @@ static int mtk_ecc_resume(struct device *dev)
 		return ret;
 	}
 
-	mtk_ecc_hw_init(ecc);
-
 	return 0;
 }
 
 static SIMPLE_DEV_PM_OPS(mtk_ecc_pm_ops, mtk_ecc_suspend, mtk_ecc_resume);
 #endif
 
-static const struct of_device_id mtk_ecc_dt_match[] = {
-	{ .compatible = "mediatek,mt2701-ecc" },
-	{},
-};
-
 MODULE_DEVICE_TABLE(of, mtk_ecc_dt_match);
 
 static struct platform_driver mtk_ecc_driver = {
diff --git a/drivers/mtd/nand/mtk_ecc.h b/drivers/mtd/nand/mtk_ecc.h
index cbeba5cd1c13..d245c14f1b80 100644
--- a/drivers/mtd/nand/mtk_ecc.h
+++ b/drivers/mtd/nand/mtk_ecc.h
@@ -42,7 +42,7 @@ void mtk_ecc_get_stats(struct mtk_ecc *, struct mtk_ecc_stats *, int);
 int mtk_ecc_wait_done(struct mtk_ecc *, enum mtk_ecc_operation);
 int mtk_ecc_enable(struct mtk_ecc *, struct mtk_ecc_config *);
 void mtk_ecc_disable(struct mtk_ecc *);
-void mtk_ecc_adjust_strength(u32 *);
+void mtk_ecc_adjust_strength(struct mtk_ecc *ecc, u32 *p);
 
 struct mtk_ecc *of_mtk_ecc_get(struct device_node *);
 void mtk_ecc_release(struct mtk_ecc *);
diff --git a/drivers/mtd/nand/mtk_nand.c b/drivers/mtd/nand/mtk_nand.c
index 6c517c682939..f7ae99464375 100644
--- a/drivers/mtd/nand/mtk_nand.c
+++ b/drivers/mtd/nand/mtk_nand.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/iopoll.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include "mtk_ecc.h"
 
 /* NAND controller register definition */
@@ -38,23 +39,6 @@
 #define NFI_PAGEFMT		(0x04)
 #define		PAGEFMT_FDM_ECC_SHIFT	(12)
 #define		PAGEFMT_FDM_SHIFT	(8)
-#define		PAGEFMT_SPARE_16	(0)
-#define		PAGEFMT_SPARE_26	(1)
-#define		PAGEFMT_SPARE_27	(2)
-#define		PAGEFMT_SPARE_28	(3)
-#define		PAGEFMT_SPARE_32	(4)
-#define		PAGEFMT_SPARE_36	(5)
-#define		PAGEFMT_SPARE_40	(6)
-#define		PAGEFMT_SPARE_44	(7)
-#define		PAGEFMT_SPARE_48	(8)
-#define		PAGEFMT_SPARE_49	(9)
-#define		PAGEFMT_SPARE_50	(0xa)
-#define		PAGEFMT_SPARE_51	(0xb)
-#define		PAGEFMT_SPARE_52	(0xc)
-#define		PAGEFMT_SPARE_62	(0xd)
-#define		PAGEFMT_SPARE_63	(0xe)
-#define		PAGEFMT_SPARE_64	(0xf)
-#define		PAGEFMT_SPARE_SHIFT	(4)
 #define		PAGEFMT_SEC_SEL_512	BIT(2)
 #define		PAGEFMT_512_2K		(0)
 #define		PAGEFMT_2K_4K		(1)
@@ -115,6 +99,17 @@
 #define MTK_RESET_TIMEOUT	(1000000)
 #define MTK_MAX_SECTOR		(16)
 #define MTK_NAND_MAX_NSELS	(2)
+#define MTK_NFC_MIN_SPARE	(16)
+#define ACCTIMING(tpoecs, tprecs, tc2r, tw2r, twh, twst, trlt) \
+	((tpoecs) << 28 | (tprecs) << 22 | (tc2r) << 16 | \
+	(tw2r) << 12 | (twh) << 8 | (twst) << 4 | (trlt))
+
+struct mtk_nfc_caps {
+	const u8 *spare_size;
+	u8 num_spare_size;
+	u8 pageformat_spare_shift;
+	u8 nfi_clk_div;
+};
 
 struct mtk_nfc_bad_mark_ctl {
 	void (*bm_swap)(struct mtd_info *, u8 *buf, int raw);
@@ -155,6 +150,7 @@ struct mtk_nfc {
 	struct mtk_ecc *ecc;
 
 	struct device *dev;
+	const struct mtk_nfc_caps *caps;
 	void __iomem *regs;
 
 	struct completion done;
@@ -163,6 +159,20 @@ struct mtk_nfc {
 	u8 *buffer;
 };
 
+/*
+ * supported spare size of each IP.
+ * order should be the same with the spare size bitfiled defination of
+ * register NFI_PAGEFMT.
+ */
+static const u8 spare_size_mt2701[] = {
+	16, 26, 27, 28, 32, 36, 40, 44,	48, 49, 50, 51, 52, 62, 63, 64
+};
+
+static const u8 spare_size_mt2712[] = {
+	16, 26, 27, 28, 32, 36, 40, 44, 48, 49, 50, 51, 52, 62, 61, 63, 64, 67,
+	74
+};
+
 static inline struct mtk_nfc_nand_chip *to_mtk_nand(struct nand_chip *nand)
 {
 	return container_of(nand, struct mtk_nfc_nand_chip, nand);
@@ -308,7 +318,7 @@ static int mtk_nfc_hw_runtime_config(struct mtd_info *mtd)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
 	struct mtk_nfc *nfc = nand_get_controller_data(chip);
-	u32 fmt, spare;
+	u32 fmt, spare, i;
 
 	if (!mtd->writesize)
 		return 0;
@@ -352,63 +362,21 @@ static int mtk_nfc_hw_runtime_config(struct mtd_info *mtd)
 	if (chip->ecc.size == 1024)
 		spare >>= 1;
 
-	switch (spare) {
-	case 16:
-		fmt |= (PAGEFMT_SPARE_16 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 26:
-		fmt |= (PAGEFMT_SPARE_26 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 27:
-		fmt |= (PAGEFMT_SPARE_27 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 28:
-		fmt |= (PAGEFMT_SPARE_28 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 32:
-		fmt |= (PAGEFMT_SPARE_32 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 36:
-		fmt |= (PAGEFMT_SPARE_36 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 40:
-		fmt |= (PAGEFMT_SPARE_40 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 44:
-		fmt |= (PAGEFMT_SPARE_44 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 48:
-		fmt |= (PAGEFMT_SPARE_48 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 49:
-		fmt |= (PAGEFMT_SPARE_49 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 50:
-		fmt |= (PAGEFMT_SPARE_50 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 51:
-		fmt |= (PAGEFMT_SPARE_51 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 52:
-		fmt |= (PAGEFMT_SPARE_52 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 62:
-		fmt |= (PAGEFMT_SPARE_62 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 63:
-		fmt |= (PAGEFMT_SPARE_63 << PAGEFMT_SPARE_SHIFT);
-		break;
-	case 64:
-		fmt |= (PAGEFMT_SPARE_64 << PAGEFMT_SPARE_SHIFT);
-		break;
-	default:
-		dev_err(nfc->dev, "invalid spare per sector %d\n", spare);
+	for (i = 0; i < nfc->caps->num_spare_size; i++) {
+		if (nfc->caps->spare_size[i] == spare)
+			break;
+	}
+
+	if (i == nfc->caps->num_spare_size) {
+		dev_err(nfc->dev, "invalid spare size %d\n", spare);
 		return -EINVAL;
 	}
 
+	fmt |= i << nfc->caps->pageformat_spare_shift;
+
 	fmt |= mtk_nand->fdm.reg_size << PAGEFMT_FDM_SHIFT;
 	fmt |= mtk_nand->fdm.ecc_size << PAGEFMT_FDM_ECC_SHIFT;
-	nfi_writew(nfc, fmt, NFI_PAGEFMT);
+	nfi_writel(nfc, fmt, NFI_PAGEFMT);
 
 	nfc->ecc_cfg.strength = chip->ecc.strength;
 	nfc->ecc_cfg.len = chip->ecc.size + mtk_nand->fdm.ecc_size;
@@ -531,6 +499,74 @@ static void mtk_nfc_write_buf(struct mtd_info *mtd, const u8 *buf, int len)
 		mtk_nfc_write_byte(mtd, buf[i]);
 }
 
+static int mtk_nfc_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
+{
+	struct mtk_nfc *nfc = nand_get_controller_data(mtd_to_nand(mtd));
+	const struct nand_sdr_timings *timings;
+	u32 rate, tpoecs, tprecs, tc2r, tw2r, twh, twst, trlt;
+
+	timings = nand_get_sdr_timings(conf);
+	if (IS_ERR(timings))
+		return -ENOTSUPP;
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	rate = clk_get_rate(nfc->clk.nfi_clk);
+	/* There is a frequency divider in some IPs */
+	rate /= nfc->caps->nfi_clk_div;
+
+	/* turn clock rate into KHZ */
+	rate /= 1000;
+
+	tpoecs = max(timings->tALH_min, timings->tCLH_min) / 1000;
+	tpoecs = DIV_ROUND_UP(tpoecs * rate, 1000000);
+	tpoecs &= 0xf;
+
+	tprecs = max(timings->tCLS_min, timings->tALS_min) / 1000;
+	tprecs = DIV_ROUND_UP(tprecs * rate, 1000000);
+	tprecs &= 0x3f;
+
+	/* sdr interface has no tCR which means CE# low to RE# low */
+	tc2r = 0;
+
+	tw2r = timings->tWHR_min / 1000;
+	tw2r = DIV_ROUND_UP(tw2r * rate, 1000000);
+	tw2r = DIV_ROUND_UP(tw2r - 1, 2);
+	tw2r &= 0xf;
+
+	twh = max(timings->tREH_min, timings->tWH_min) / 1000;
+	twh = DIV_ROUND_UP(twh * rate, 1000000) - 1;
+	twh &= 0xf;
+
+	twst = timings->tWP_min / 1000;
+	twst = DIV_ROUND_UP(twst * rate, 1000000) - 1;
+	twst &= 0xf;
+
+	trlt = max(timings->tREA_max, timings->tRP_min) / 1000;
+	trlt = DIV_ROUND_UP(trlt * rate, 1000000) - 1;
+	trlt &= 0xf;
+
+	/*
+	 * ACCON: access timing control register
+	 * -------------------------------------
+	 * 31:28: tpoecs, minimum required time for CS post pulling down after
+	 *        accessing the device
+	 * 27:22: tprecs, minimum required time for CS pre pulling down before
+	 *        accessing the device
+	 * 21:16: tc2r, minimum required time from NCEB low to NREB low
+	 * 15:12: tw2r, minimum required time from NWEB high to NREB low.
+	 * 11:08: twh, write enable hold time
+	 * 07:04: twst, write wait states
+	 * 03:00: trlt, read wait states
+	 */
+	trlt = ACCTIMING(tpoecs, tprecs, tc2r, tw2r, twh, twst, trlt);
+	nfi_writel(nfc, trlt, NFI_ACCCON);
+
+	return 0;
+}
+
 static int mtk_nfc_sector_encode(struct nand_chip *chip, u8 *data)
 {
 	struct mtk_nfc *nfc = nand_get_controller_data(chip);
@@ -988,28 +1024,13 @@ static int mtk_nfc_read_oob_std(struct mtd_info *mtd, struct nand_chip *chip,
 static inline void mtk_nfc_hw_init(struct mtk_nfc *nfc)
 {
 	/*
-	 * ACCON: access timing control register
-	 * -------------------------------------
-	 * 31:28: minimum required time for CS post pulling down after accessing
-	 *	the device
-	 * 27:22: minimum required time for CS pre pulling down before accessing
-	 *	the device
-	 * 21:16: minimum required time from NCEB low to NREB low
-	 * 15:12: minimum required time from NWEB high to NREB low.
-	 * 11:08: write enable hold time
-	 * 07:04: write wait states
-	 * 03:00: read wait states
-	 */
-	nfi_writel(nfc, 0x10804211, NFI_ACCCON);
-
-	/*
 	 * CNRNB: nand ready/busy register
 	 * -------------------------------
 	 * 7:4: timeout register for polling the NAND busy/ready signal
 	 * 0  : poll the status of the busy/ready signal after [7:4]*16 cycles.
 	 */
 	nfi_writew(nfc, 0xf1, NFI_CNRNB);
-	nfi_writew(nfc, PAGEFMT_8K_16K, NFI_PAGEFMT);
+	nfi_writel(nfc, PAGEFMT_8K_16K, NFI_PAGEFMT);
 
 	mtk_nfc_hw_reset(nfc);
 
@@ -1131,12 +1152,12 @@ static void mtk_nfc_set_bad_mark_ctl(struct mtk_nfc_bad_mark_ctl *bm_ctl,
 	}
 }
 
-static void mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd)
+static int mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
-	u32 spare[] = {16, 26, 27, 28, 32, 36, 40, 44,
-			48, 49, 50, 51, 52, 62, 63, 64};
-	u32 eccsteps, i;
+	struct mtk_nfc *nfc = nand_get_controller_data(nand);
+	const u8 *spare = nfc->caps->spare_size;
+	u32 eccsteps, i, closest_spare = 0;
 
 	eccsteps = mtd->writesize / nand->ecc.size;
 	*sps = mtd->oobsize / eccsteps;
@@ -1144,28 +1165,31 @@ static void mtk_nfc_set_spare_per_sector(u32 *sps, struct mtd_info *mtd)
 	if (nand->ecc.size == 1024)
 		*sps >>= 1;
 
-	for (i = 0; i < ARRAY_SIZE(spare); i++) {
-		if (*sps <= spare[i]) {
-			if (!i)
-				*sps = spare[i];
-			else if (*sps != spare[i])
-				*sps = spare[i - 1];
-			break;
+	if (*sps < MTK_NFC_MIN_SPARE)
+		return -EINVAL;
+
+	for (i = 0; i < nfc->caps->num_spare_size; i++) {
+		if (*sps >= spare[i] && spare[i] >= spare[closest_spare]) {
+			closest_spare = i;
+			if (*sps == spare[i])
+				break;
 		}
 	}
 
-	if (i >= ARRAY_SIZE(spare))
-		*sps = spare[ARRAY_SIZE(spare) - 1];
+	*sps = spare[closest_spare];
 
 	if (nand->ecc.size == 1024)
 		*sps <<= 1;
+
+	return 0;
 }
 
 static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtk_nfc *nfc = nand_get_controller_data(nand);
 	u32 spare;
-	int free;
+	int free, ret;
 
 	/* support only ecc hw mode */
 	if (nand->ecc.mode != NAND_ECC_HW) {
@@ -1194,7 +1218,9 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 			nand->ecc.size = 1024;
 		}
 
-		mtk_nfc_set_spare_per_sector(&spare, mtd);
+		ret = mtk_nfc_set_spare_per_sector(&spare, mtd);
+		if (ret)
+			return ret;
 
 		/* calculate oob bytes except ecc parity data */
 		free = ((nand->ecc.strength * ECC_PARITY_BITS) + 7) >> 3;
@@ -1214,7 +1240,7 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 		}
 	}
 
-	mtk_ecc_adjust_strength(&nand->ecc.strength);
+	mtk_ecc_adjust_strength(nfc->ecc, &nand->ecc.strength);
 
 	dev_info(dev, "eccsize %d eccstrength %d\n",
 		 nand->ecc.size, nand->ecc.strength);
@@ -1271,6 +1297,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 	nand->read_byte = mtk_nfc_read_byte;
 	nand->read_buf = mtk_nfc_read_buf;
 	nand->cmd_ctrl = mtk_nfc_cmd_ctrl;
+	nand->setup_data_interface = mtk_nfc_setup_data_interface;
 
 	/* set default mode in case dt entry is missing */
 	nand->ecc.mode = NAND_ECC_HW;
@@ -1312,7 +1339,10 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 		return -EINVAL;
 	}
 
-	mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
+	ret = mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
+	if (ret)
+		return ret;
+
 	mtk_nfc_set_fdm(&chip->fdm, mtd);
 	mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd);
 
@@ -1354,12 +1384,39 @@ static int mtk_nfc_nand_chips_init(struct device *dev, struct mtk_nfc *nfc)
 	return 0;
 }
 
+static const struct mtk_nfc_caps mtk_nfc_caps_mt2701 = {
+	.spare_size = spare_size_mt2701,
+	.num_spare_size = 16,
+	.pageformat_spare_shift = 4,
+	.nfi_clk_div = 1,
+};
+
+static const struct mtk_nfc_caps mtk_nfc_caps_mt2712 = {
+	.spare_size = spare_size_mt2712,
+	.num_spare_size = 19,
+	.pageformat_spare_shift = 16,
+	.nfi_clk_div = 2,
+};
+
+static const struct of_device_id mtk_nfc_id_table[] = {
+	{
+		.compatible = "mediatek,mt2701-nfc",
+		.data = &mtk_nfc_caps_mt2701,
+	}, {
+		.compatible = "mediatek,mt2712-nfc",
+		.data = &mtk_nfc_caps_mt2712,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, mtk_nfc_id_table);
+
 static int mtk_nfc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct mtk_nfc *nfc;
 	struct resource *res;
+	const struct of_device_id *of_nfc_id = NULL;
 	int ret, irq;
 
 	nfc = devm_kzalloc(dev, sizeof(*nfc), GFP_KERNEL);
@@ -1423,6 +1480,14 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
+	of_nfc_id = of_match_device(mtk_nfc_id_table, &pdev->dev);
+	if (!of_nfc_id) {
+		ret = -ENODEV;
+		goto clk_disable;
+	}
+
+	nfc->caps = of_nfc_id->data;
+
 	platform_set_drvdata(pdev, nfc);
 
 	ret = mtk_nfc_nand_chips_init(dev, nfc);
@@ -1485,8 +1550,6 @@ static int mtk_nfc_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	mtk_nfc_hw_init(nfc);
-
 	/* reset NAND chip if VCC was powered off */
 	list_for_each_entry(chip, &nfc->chips, node) {
 		nand = &chip->nand;
@@ -1503,12 +1566,6 @@ static int mtk_nfc_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(mtk_nfc_pm_ops, mtk_nfc_suspend, mtk_nfc_resume);
 #endif
 
-static const struct of_device_id mtk_nfc_id_table[] = {
-	{ .compatible = "mediatek,mt2701-nfc" },
-	{}
-};
-MODULE_DEVICE_TABLE(of, mtk_nfc_id_table);
-
 static struct platform_driver mtk_nfc_driver = {
 	.probe  = mtk_nfc_probe,
 	.remove = mtk_nfc_remove,
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 61ca020c5272..a764d5ca7536 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -152,9 +152,8 @@ struct mxc_nand_devtype_data {
 	void (*select_chip)(struct mtd_info *mtd, int chip);
 	int (*correct_data)(struct mtd_info *mtd, u_char *dat,
 			u_char *read_ecc, u_char *calc_ecc);
-	int (*setup_data_interface)(struct mtd_info *mtd,
-				    const struct nand_data_interface *conf,
-				    bool check_only);
+	int (*setup_data_interface)(struct mtd_info *mtd, int csline,
+				    const struct nand_data_interface *conf);
 
 	/*
 	 * On i.MX21 the CONFIG2:INT bit cannot be read if interrupts are masked
@@ -1015,9 +1014,8 @@ static void preset_v1(struct mtd_info *mtd)
 	writew(0x4, NFC_V1_V2_WRPROT);
 }
 
-static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd,
-					const struct nand_data_interface *conf,
-					bool check_only)
+static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
 {
 	struct nand_chip *nand_chip = mtd_to_nand(mtd);
 	struct mxc_nand_host *host = nand_get_controller_data(nand_chip);
@@ -1075,7 +1073,7 @@ static int mxc_nand_v2_setup_data_interface(struct mtd_info *mtd,
 		return -EINVAL;
 	}
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	ret = clk_set_rate(host->clk, rate);
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index bf8486c406d3..5fa5ddc94834 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -755,6 +755,16 @@ static void nand_command(struct mtd_info *mtd, unsigned int command,
 		return;
 
 		/* This applies to read commands */
+	case NAND_CMD_READ0:
+		/*
+		 * READ0 is sometimes used to exit GET STATUS mode. When this
+		 * is the case no address cycles are requested, and we can use
+		 * this information to detect that we should not wait for the
+		 * device to be ready.
+		 */
+		if (column == -1 && page_addr == -1)
+			return;
+
 	default:
 		/*
 		 * If we don't have access to the busy pin, we apply the given
@@ -889,6 +899,15 @@ static void nand_command_lp(struct mtd_info *mtd, unsigned int command,
 		return;
 
 	case NAND_CMD_READ0:
+		/*
+		 * READ0 is sometimes used to exit GET STATUS mode. When this
+		 * is the case no address cycles are requested, and we can use
+		 * this information to detect that READSTART should not be
+		 * issued.
+		 */
+		if (column == -1 && page_addr == -1)
+			return;
+
 		chip->cmd_ctrl(mtd, NAND_CMD_READSTART,
 			       NAND_NCE | NAND_CLE | NAND_CTRL_CHANGE);
 		chip->cmd_ctrl(mtd, NAND_CMD_NONE,
@@ -1044,12 +1063,13 @@ static int nand_wait(struct mtd_info *mtd, struct nand_chip *chip)
 /**
  * nand_reset_data_interface - Reset data interface and timings
  * @chip: The NAND chip
+ * @chipnr: Internal die id
  *
  * Reset the Data interface and timings to ONFI mode 0.
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_reset_data_interface(struct nand_chip *chip)
+static int nand_reset_data_interface(struct nand_chip *chip, int chipnr)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_data_interface *conf;
@@ -1073,7 +1093,7 @@ static int nand_reset_data_interface(struct nand_chip *chip)
 	 */
 
 	conf = nand_get_default_data_interface();
-	ret = chip->setup_data_interface(mtd, conf, false);
+	ret = chip->setup_data_interface(mtd, chipnr, conf);
 	if (ret)
 		pr_err("Failed to configure data interface to SDR timing mode 0\n");
 
@@ -1083,6 +1103,7 @@ static int nand_reset_data_interface(struct nand_chip *chip)
 /**
  * nand_setup_data_interface - Setup the best data interface and timings
  * @chip: The NAND chip
+ * @chipnr: Internal die id
  *
  * Find and configure the best data interface and NAND timings supported by
  * the chip and the driver.
@@ -1092,7 +1113,7 @@ static int nand_reset_data_interface(struct nand_chip *chip)
  *
  * Returns 0 for success or negative error code otherwise.
  */
-static int nand_setup_data_interface(struct nand_chip *chip)
+static int nand_setup_data_interface(struct nand_chip *chip, int chipnr)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
@@ -1116,7 +1137,7 @@ static int nand_setup_data_interface(struct nand_chip *chip)
 			goto err;
 	}
 
-	ret = chip->setup_data_interface(mtd, chip->data_interface, false);
+	ret = chip->setup_data_interface(mtd, chipnr, chip->data_interface);
 err:
 	return ret;
 }
@@ -1167,8 +1188,10 @@ static int nand_init_data_interface(struct nand_chip *chip)
 		if (ret)
 			continue;
 
-		ret = chip->setup_data_interface(mtd, chip->data_interface,
-						 true);
+		/* Pass -1 to only */
+		ret = chip->setup_data_interface(mtd,
+						 NAND_DATA_IFACE_CHECK_ONLY,
+						 chip->data_interface);
 		if (!ret) {
 			chip->onfi_timing_mode_default = mode;
 			break;
@@ -1195,7 +1218,7 @@ int nand_reset(struct nand_chip *chip, int chipnr)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
-	ret = nand_reset_data_interface(chip);
+	ret = nand_reset_data_interface(chip, chipnr);
 	if (ret)
 		return ret;
 
@@ -1208,7 +1231,7 @@ int nand_reset(struct nand_chip *chip, int chipnr)
 	chip->select_chip(mtd, -1);
 
 	chip->select_chip(mtd, chipnr);
-	ret = nand_setup_data_interface(chip);
+	ret = nand_setup_data_interface(chip, chipnr);
 	chip->select_chip(mtd, -1);
 	if (ret)
 		return ret;
@@ -1424,7 +1447,10 @@ static int nand_check_erased_buf(void *buf, int len, int bitflips_threshold)
 
 	for (; len >= sizeof(long);
 	     len -= sizeof(long), bitmap += sizeof(long)) {
-		weight = hweight_long(*((unsigned long *)bitmap));
+		unsigned long d = *((unsigned long *)bitmap);
+		if (d == ~0UL)
+			continue;
+		weight = hweight_long(d);
 		bitflips += BITS_PER_LONG - weight;
 		if (unlikely(bitflips > bitflips_threshold))
 			return -EBADMSG;
@@ -1527,14 +1553,15 @@ EXPORT_SYMBOL(nand_check_erased_ecc_chunk);
  *
  * Not for syndrome calculating ECC controllers, which use a special oob layout.
  */
-static int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
-			      uint8_t *buf, int oob_required, int page)
+int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       uint8_t *buf, int oob_required, int page)
 {
 	chip->read_buf(mtd, buf, mtd->writesize);
 	if (oob_required)
 		chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
 	return 0;
 }
+EXPORT_SYMBOL(nand_read_page_raw);
 
 /**
  * nand_read_page_raw_syndrome - [INTERN] read raw page data without ecc
@@ -2472,8 +2499,8 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
  *
  * Not for syndrome calculating ECC controllers, which use a special oob layout.
  */
-static int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
-			       const uint8_t *buf, int oob_required, int page)
+int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
+			const uint8_t *buf, int oob_required, int page)
 {
 	chip->write_buf(mtd, buf, mtd->writesize);
 	if (oob_required)
@@ -2481,6 +2508,7 @@ static int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 
 	return 0;
 }
+EXPORT_SYMBOL(nand_write_page_raw);
 
 /**
  * nand_write_page_raw_syndrome - [INTERN] raw page write function
@@ -2718,7 +2746,7 @@ static int nand_write_page_syndrome(struct mtd_info *mtd,
  */
 static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 		uint32_t offset, int data_len, const uint8_t *buf,
-		int oob_required, int page, int cached, int raw)
+		int oob_required, int page, int raw)
 {
 	int status, subpage;
 
@@ -2744,30 +2772,12 @@ static int nand_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	if (status < 0)
 		return status;
 
-	/*
-	 * Cached progamming disabled for now. Not sure if it's worth the
-	 * trouble. The speed gain is not very impressive. (2.3->2.6Mib/s).
-	 */
-	cached = 0;
+	if (nand_standard_page_accessors(&chip->ecc)) {
+		chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
 
-	if (!cached || !NAND_HAS_CACHEPROG(chip)) {
-
-		if (nand_standard_page_accessors(&chip->ecc))
-			chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
 		status = chip->waitfunc(mtd, chip);
-		/*
-		 * See if operation failed and additional status checks are
-		 * available.
-		 */
-		if ((status & NAND_STATUS_FAIL) && (chip->errstat))
-			status = chip->errstat(mtd, chip, FL_WRITING, status,
-					       page);
-
 		if (status & NAND_STATUS_FAIL)
 			return -EIO;
-	} else {
-		chip->cmdfunc(mtd, NAND_CMD_CACHEDPROG, -1, -1);
-		status = chip->waitfunc(mtd, chip);
 	}
 
 	return 0;
@@ -2875,7 +2885,6 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 
 	while (1) {
 		int bytes = mtd->writesize;
-		int cached = writelen > bytes && page != blockmask;
 		uint8_t *wbuf = buf;
 		int use_bufpoi;
 		int part_pagewr = (column || writelen < mtd->writesize);
@@ -2893,7 +2902,6 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 		if (use_bufpoi) {
 			pr_debug("%s: using write bounce buffer for buf@%p\n",
 					 __func__, buf);
-			cached = 0;
 			if (part_pagewr)
 				bytes = min_t(int, bytes - column, writelen);
 			chip->pagebuf = -1;
@@ -2912,7 +2920,7 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 		}
 
 		ret = nand_write_page(mtd, chip, column, bytes, wbuf,
-				      oob_required, page, cached,
+				      oob_required, page,
 				      (ops->mode == MTD_OPS_RAW));
 		if (ret)
 			break;
@@ -3228,14 +3236,6 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 
 		status = chip->erase(mtd, page & chip->pagemask);
 
-		/*
-		 * See if operation failed and additional status checks are
-		 * available
-		 */
-		if ((status & NAND_STATUS_FAIL) && (chip->errstat))
-			status = chip->errstat(mtd, chip, FL_ERASING,
-					       status, page);
-
 		/* See if block erase succeeded */
 		if (status & NAND_STATUS_FAIL) {
 			pr_debug("%s: failed erase, page 0x%08x\n",
@@ -3422,6 +3422,25 @@ static int nand_onfi_get_features(struct mtd_info *mtd, struct nand_chip *chip,
 }
 
 /**
+ * nand_onfi_get_set_features_notsupp - set/get features stub returning
+ *					-ENOTSUPP
+ * @mtd: MTD device structure
+ * @chip: nand chip info structure
+ * @addr: feature address.
+ * @subfeature_param: the subfeature parameters, a four bytes array.
+ *
+ * Should be used by NAND controller drivers that do not support the SET/GET
+ * FEATURES operations.
+ */
+int nand_onfi_get_set_features_notsupp(struct mtd_info *mtd,
+				       struct nand_chip *chip, int addr,
+				       u8 *subfeature_param)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_onfi_get_set_features_notsupp);
+
+/**
  * nand_suspend - [MTD Interface] Suspend the NAND flash
  * @mtd: MTD device structure
  */
@@ -4180,6 +4199,7 @@ static const char * const nand_ecc_modes[] = {
 	[NAND_ECC_HW]		= "hw",
 	[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
 	[NAND_ECC_HW_OOB_FIRST]	= "hw_oob_first",
+	[NAND_ECC_ON_DIE]	= "on-die",
 };
 
 static int of_get_nand_ecc_mode(struct device_node *np)
@@ -4374,7 +4394,7 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 	 * For the other dies, nand_reset() will automatically switch to the
 	 * best mode for us.
 	 */
-	ret = nand_setup_data_interface(chip);
+	ret = nand_setup_data_interface(chip, 0);
 	if (ret)
 		goto err_nand_init;
 
@@ -4512,6 +4532,226 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 	}
 }
 
+/**
+ * nand_check_ecc_caps - check the sanity of preset ECC settings
+ * @chip: nand chip info structure
+ * @caps: ECC caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * When ECC step size and strength are already set, check if they are supported
+ * by the controller and the calculated ECC bytes fit within the chip's OOB.
+ * On success, the calculated ECC bytes is set.
+ */
+int nand_check_ecc_caps(struct nand_chip *chip,
+			const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	const struct nand_ecc_step_info *stepinfo;
+	int preset_step = chip->ecc.size;
+	int preset_strength = chip->ecc.strength;
+	int nsteps, ecc_bytes;
+	int i, j;
+
+	if (WARN_ON(oobavail < 0))
+		return -EINVAL;
+
+	if (!preset_step || !preset_strength)
+		return -ENODATA;
+
+	nsteps = mtd->writesize / preset_step;
+
+	for (i = 0; i < caps->nstepinfos; i++) {
+		stepinfo = &caps->stepinfos[i];
+
+		if (stepinfo->stepsize != preset_step)
+			continue;
+
+		for (j = 0; j < stepinfo->nstrengths; j++) {
+			if (stepinfo->strengths[j] != preset_strength)
+				continue;
+
+			ecc_bytes = caps->calc_ecc_bytes(preset_step,
+							 preset_strength);
+			if (WARN_ON_ONCE(ecc_bytes < 0))
+				return ecc_bytes;
+
+			if (ecc_bytes * nsteps > oobavail) {
+				pr_err("ECC (step, strength) = (%d, %d) does not fit in OOB",
+				       preset_step, preset_strength);
+				return -ENOSPC;
+			}
+
+			chip->ecc.bytes = ecc_bytes;
+
+			return 0;
+		}
+	}
+
+	pr_err("ECC (step, strength) = (%d, %d) not supported on this controller",
+	       preset_step, preset_strength);
+
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
+
+/**
+ * nand_match_ecc_req - meet the chip's requirement with least ECC bytes
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * If a chip's ECC requirement is provided, try to meet it with the least
+ * number of ECC bytes (i.e. with the largest number of OOB-free bytes).
+ * On success, the chosen ECC settings are set.
+ */
+int nand_match_ecc_req(struct nand_chip *chip,
+		       const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	const struct nand_ecc_step_info *stepinfo;
+	int req_step = chip->ecc_step_ds;
+	int req_strength = chip->ecc_strength_ds;
+	int req_corr, step_size, strength, nsteps, ecc_bytes, ecc_bytes_total;
+	int best_step, best_strength, best_ecc_bytes;
+	int best_ecc_bytes_total = INT_MAX;
+	int i, j;
+
+	if (WARN_ON(oobavail < 0))
+		return -EINVAL;
+
+	/* No information provided by the NAND chip */
+	if (!req_step || !req_strength)
+		return -ENOTSUPP;
+
+	/* number of correctable bits the chip requires in a page */
+	req_corr = mtd->writesize / req_step * req_strength;
+
+	for (i = 0; i < caps->nstepinfos; i++) {
+		stepinfo = &caps->stepinfos[i];
+		step_size = stepinfo->stepsize;
+
+		for (j = 0; j < stepinfo->nstrengths; j++) {
+			strength = stepinfo->strengths[j];
+
+			/*
+			 * If both step size and strength are smaller than the
+			 * chip's requirement, it is not easy to compare the
+			 * resulted reliability.
+			 */
+			if (step_size < req_step && strength < req_strength)
+				continue;
+
+			if (mtd->writesize % step_size)
+				continue;
+
+			nsteps = mtd->writesize / step_size;
+
+			ecc_bytes = caps->calc_ecc_bytes(step_size, strength);
+			if (WARN_ON_ONCE(ecc_bytes < 0))
+				continue;
+			ecc_bytes_total = ecc_bytes * nsteps;
+
+			if (ecc_bytes_total > oobavail ||
+			    strength * nsteps < req_corr)
+				continue;
+
+			/*
+			 * We assume the best is to meet the chip's requrement
+			 * with the least number of ECC bytes.
+			 */
+			if (ecc_bytes_total < best_ecc_bytes_total) {
+				best_ecc_bytes_total = ecc_bytes_total;
+				best_step = step_size;
+				best_strength = strength;
+				best_ecc_bytes = ecc_bytes;
+			}
+		}
+	}
+
+	if (best_ecc_bytes_total == INT_MAX)
+		return -ENOTSUPP;
+
+	chip->ecc.size = best_step;
+	chip->ecc.strength = best_strength;
+	chip->ecc.bytes = best_ecc_bytes;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nand_match_ecc_req);
+
+/**
+ * nand_maximize_ecc - choose the max ECC strength available
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * Choose the max ECC strength that is supported on the controller, and can fit
+ * within the chip's OOB.  On success, the chosen ECC settings are set.
+ */
+int nand_maximize_ecc(struct nand_chip *chip,
+		      const struct nand_ecc_caps *caps, int oobavail)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	const struct nand_ecc_step_info *stepinfo;
+	int step_size, strength, nsteps, ecc_bytes, corr;
+	int best_corr = 0;
+	int best_step = 0;
+	int best_strength, best_ecc_bytes;
+	int i, j;
+
+	if (WARN_ON(oobavail < 0))
+		return -EINVAL;
+
+	for (i = 0; i < caps->nstepinfos; i++) {
+		stepinfo = &caps->stepinfos[i];
+		step_size = stepinfo->stepsize;
+
+		/* If chip->ecc.size is already set, respect it */
+		if (chip->ecc.size && step_size != chip->ecc.size)
+			continue;
+
+		for (j = 0; j < stepinfo->nstrengths; j++) {
+			strength = stepinfo->strengths[j];
+
+			if (mtd->writesize % step_size)
+				continue;
+
+			nsteps = mtd->writesize / step_size;
+
+			ecc_bytes = caps->calc_ecc_bytes(step_size, strength);
+			if (WARN_ON_ONCE(ecc_bytes < 0))
+				continue;
+
+			if (ecc_bytes * nsteps > oobavail)
+				continue;
+
+			corr = strength * nsteps;
+
+			/*
+			 * If the number of correctable bits is the same,
+			 * bigger step_size has more reliability.
+			 */
+			if (corr > best_corr ||
+			    (corr == best_corr && step_size > best_step)) {
+				best_corr = corr;
+				best_step = step_size;
+				best_strength = strength;
+				best_ecc_bytes = ecc_bytes;
+			}
+		}
+	}
+
+	if (!best_corr)
+		return -ENOTSUPP;
+
+	chip->ecc.size = best_step;
+	chip->ecc.strength = best_strength;
+	chip->ecc.bytes = best_ecc_bytes;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nand_maximize_ecc);
+
 /*
  * Check if the chip configuration meet the datasheet requirements.
 
@@ -4733,6 +4973,18 @@ int nand_scan_tail(struct mtd_info *mtd)
 		}
 		break;
 
+	case NAND_ECC_ON_DIE:
+		if (!ecc->read_page || !ecc->write_page) {
+			WARN(1, "No ECC functions supplied; on-die ECC not possible\n");
+			ret = -EINVAL;
+			goto err_free;
+		}
+		if (!ecc->read_oob)
+			ecc->read_oob = nand_read_oob_std;
+		if (!ecc->write_oob)
+			ecc->write_oob = nand_write_oob_std;
+		break;
+
 	case NAND_ECC_NONE:
 		pr_warn("NAND_ECC_NONE selected by board driver. This is not recommended!\n");
 		ecc->read_page = nand_read_page_raw;
@@ -4773,6 +5025,11 @@ int nand_scan_tail(struct mtd_info *mtd)
 		goto err_free;
 	}
 	ecc->total = ecc->steps * ecc->bytes;
+	if (ecc->total > mtd->oobsize) {
+		WARN(1, "Total number of ECC bytes exceeded oobsize\n");
+		ret = -EINVAL;
+		goto err_free;
+	}
 
 	/*
 	 * The number of bytes available for a client to place data into
diff --git a/drivers/mtd/nand/nand_micron.c b/drivers/mtd/nand/nand_micron.c
index 877011069251..c30ab60f8e1b 100644
--- a/drivers/mtd/nand/nand_micron.c
+++ b/drivers/mtd/nand/nand_micron.c
@@ -17,6 +17,12 @@
 
 #include <linux/mtd/nand.h>
 
+/*
+ * Special Micron status bit that indicates when the block has been
+ * corrected by on-die ECC and should be rewritten
+ */
+#define NAND_STATUS_WRITE_RECOMMENDED	BIT(3)
+
 struct nand_onfi_vendor_micron {
 	u8 two_plane_read;
 	u8 read_cache;
@@ -66,9 +72,197 @@ static int micron_nand_onfi_init(struct nand_chip *chip)
 	return 0;
 }
 
+static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
+					    struct mtd_oob_region *oobregion)
+{
+	if (section >= 4)
+		return -ERANGE;
+
+	oobregion->offset = (section * 16) + 8;
+	oobregion->length = 8;
+
+	return 0;
+}
+
+static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
+					     struct mtd_oob_region *oobregion)
+{
+	if (section >= 4)
+		return -ERANGE;
+
+	oobregion->offset = (section * 16) + 2;
+	oobregion->length = 6;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = {
+	.ecc = micron_nand_on_die_ooblayout_ecc,
+	.free = micron_nand_on_die_ooblayout_free,
+};
+
+static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
+{
+	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+
+	if (enable)
+		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
+
+	return chip->onfi_set_features(nand_to_mtd(chip), chip,
+				       ONFI_FEATURE_ON_DIE_ECC, feature);
+}
+
+static int
+micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
+				 uint8_t *buf, int oob_required,
+				 int page)
+{
+	int status;
+	int max_bitflips = 0;
+
+	micron_nand_on_die_ecc_setup(chip, true);
+
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
+	chip->cmdfunc(mtd, NAND_CMD_STATUS, -1, -1);
+	status = chip->read_byte(mtd);
+	if (status & NAND_STATUS_FAIL)
+		mtd->ecc_stats.failed++;
+	/*
+	 * The internal ECC doesn't tell us the number of bitflips
+	 * that have been corrected, but tells us if it recommends to
+	 * rewrite the block. If it's the case, then we pretend we had
+	 * a number of bitflips equal to the ECC strength, which will
+	 * hint the NAND core to rewrite the block.
+	 */
+	else if (status & NAND_STATUS_WRITE_RECOMMENDED)
+		max_bitflips = chip->ecc.strength;
+
+	chip->cmdfunc(mtd, NAND_CMD_READ0, -1, -1);
+
+	nand_read_page_raw(mtd, chip, buf, oob_required, page);
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	return max_bitflips;
+}
+
+static int
+micron_nand_write_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
+				  const uint8_t *buf, int oob_required,
+				  int page)
+{
+	int status;
+
+	micron_nand_on_die_ecc_setup(chip, true);
+
+	chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page);
+	nand_write_page_raw(mtd, chip, buf, oob_required, page);
+	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+	status = chip->waitfunc(mtd, chip);
+
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	return status & NAND_STATUS_FAIL ? -EIO : 0;
+}
+
+static int
+micron_nand_read_page_raw_on_die_ecc(struct mtd_info *mtd,
+				     struct nand_chip *chip,
+				     uint8_t *buf, int oob_required,
+				     int page)
+{
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0x00, page);
+	nand_read_page_raw(mtd, chip, buf, oob_required, page);
+
+	return 0;
+}
+
+static int
+micron_nand_write_page_raw_on_die_ecc(struct mtd_info *mtd,
+				      struct nand_chip *chip,
+				      const uint8_t *buf, int oob_required,
+				      int page)
+{
+	int status;
+
+	chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0x00, page);
+	nand_write_page_raw(mtd, chip, buf, oob_required, page);
+	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+	status = chip->waitfunc(mtd, chip);
+
+	return status & NAND_STATUS_FAIL ? -EIO : 0;
+}
+
+enum {
+	/* The NAND flash doesn't support on-die ECC */
+	MICRON_ON_DIE_UNSUPPORTED,
+
+	/*
+	 * The NAND flash supports on-die ECC and it can be
+	 * enabled/disabled by a set features command.
+	 */
+	MICRON_ON_DIE_SUPPORTED,
+
+	/*
+	 * The NAND flash supports on-die ECC, and it cannot be
+	 * disabled.
+	 */
+	MICRON_ON_DIE_MANDATORY,
+};
+
+/*
+ * Try to detect if the NAND support on-die ECC. To do this, we enable
+ * the feature, and read back if it has been enabled as expected. We
+ * also check if it can be disabled, because some Micron NANDs do not
+ * allow disabling the on-die ECC and we don't support such NANDs for
+ * now.
+ *
+ * This function also has the side effect of disabling on-die ECC if
+ * it had been left enabled by the firmware/bootloader.
+ */
+static int micron_supports_on_die_ecc(struct nand_chip *chip)
+{
+	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	int ret;
+
+	if (chip->onfi_version == 0)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	if (chip->bits_per_cell != 1)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	ret = micron_nand_on_die_ecc_setup(chip, true);
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	chip->onfi_get_features(nand_to_mtd(chip), chip,
+				ONFI_FEATURE_ON_DIE_ECC, feature);
+	if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	ret = micron_nand_on_die_ecc_setup(chip, false);
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	chip->onfi_get_features(nand_to_mtd(chip), chip,
+				ONFI_FEATURE_ON_DIE_ECC, feature);
+	if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN)
+		return MICRON_ON_DIE_MANDATORY;
+
+	/*
+	 * Some Micron NANDs have an on-die ECC of 4/512, some other
+	 * 8/512. We only support the former.
+	 */
+	if (chip->onfi_params.ecc_bits != 4)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	return MICRON_ON_DIE_SUPPORTED;
+}
+
 static int micron_nand_init(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ondie;
 	int ret;
 
 	ret = micron_nand_onfi_init(chip);
@@ -78,6 +272,34 @@ static int micron_nand_init(struct nand_chip *chip)
 	if (mtd->writesize == 2048)
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
 
+	ondie = micron_supports_on_die_ecc(chip);
+
+	if (ondie == MICRON_ON_DIE_MANDATORY) {
+		pr_err("On-die ECC forcefully enabled, not supported\n");
+		return -EINVAL;
+	}
+
+	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
+		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
+			pr_err("On-die ECC selected but not supported\n");
+			return -EINVAL;
+		}
+
+		chip->ecc.options = NAND_ECC_CUSTOM_PAGE_ACCESS;
+		chip->ecc.bytes = 8;
+		chip->ecc.size = 512;
+		chip->ecc.strength = 4;
+		chip->ecc.algo = NAND_ECC_BCH;
+		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
+		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
+		chip->ecc.read_page_raw =
+			micron_nand_read_page_raw_on_die_ecc;
+		chip->ecc.write_page_raw =
+			micron_nand_write_page_raw_on_die_ecc;
+
+		mtd_set_ooblayout(mtd, &micron_nand_on_die_ooblayout_ops);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index f8e463a97b9e..209170ed2b76 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -166,7 +166,11 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 		}
 	}
 
-	clk_prepare_enable(info->clk);
+	ret = clk_prepare_enable(info->clk);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to prepare clock!\n");
+		return ret;
+	}
 
 	ret = nand_scan(mtd, 1);
 	if (ret)
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 649ba8200832..74dae4bbdac8 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -1812,6 +1812,8 @@ static int alloc_nand_resource(struct platform_device *pdev)
 		chip->write_buf		= pxa3xx_nand_write_buf;
 		chip->options		|= NAND_NO_SUBPAGE_WRITE;
 		chip->cmdfunc		= nand_cmdfunc;
+		chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+		chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 	}
 
 	nand_hw_control_init(chip->controller);
diff --git a/drivers/mtd/nand/qcom_nandc.c b/drivers/mtd/nand/qcom_nandc.c
index 57d483ac5765..88af7145a51a 100644
--- a/drivers/mtd/nand/qcom_nandc.c
+++ b/drivers/mtd/nand/qcom_nandc.c
@@ -2008,6 +2008,8 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
 	chip->read_byte		= qcom_nandc_read_byte;
 	chip->read_buf		= qcom_nandc_read_buf;
 	chip->write_buf		= qcom_nandc_write_buf;
+	chip->onfi_set_features	= nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features	= nand_onfi_get_set_features_notsupp;
 
 	/*
 	 * the bad block marker is readable only when we read the last codeword
diff --git a/drivers/mtd/nand/s3c2410.c b/drivers/mtd/nand/s3c2410.c
index f0b030d44f71..9e0c849607b9 100644
--- a/drivers/mtd/nand/s3c2410.c
+++ b/drivers/mtd/nand/s3c2410.c
@@ -812,9 +812,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 	return -ENODEV;
 }
 
-static int s3c2410_nand_setup_data_interface(struct mtd_info *mtd,
-					const struct nand_data_interface *conf,
-					bool check_only)
+static int s3c2410_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
 {
 	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 	struct s3c2410_platform_nand *pdata = info->platform;
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 442ce619b3b6..891ac7b99305 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -1183,6 +1183,8 @@ static int flctl_probe(struct platform_device *pdev)
 	nand->read_buf = flctl_read_buf;
 	nand->select_chip = flctl_select_chip;
 	nand->cmdfunc = flctl_cmdfunc;
+	nand->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	nand->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	if (pdata->flcmncr_val & SEL_16BIT)
 		nand->options |= NAND_BUSWIDTH_16;
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index 118a26fff368..d0b6f8f9f297 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -1301,7 +1301,6 @@ static int sunxi_nfc_hw_ecc_read_subpage(struct mtd_info *mtd,
 
 	sunxi_nfc_hw_ecc_enable(mtd);
 
-	chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page);
 	for (i = data_offs / ecc->size;
 	     i < DIV_ROUND_UP(data_offs + readlen, ecc->size); i++) {
 		int data_off = i * ecc->size;
@@ -1592,9 +1591,8 @@ static int _sunxi_nand_lookup_timing(const s32 *lut, int lut_size, u32 duration,
 #define sunxi_nand_lookup_timing(l, p, c) \
 			_sunxi_nand_lookup_timing(l, ARRAY_SIZE(l), p, c)
 
-static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd,
-					const struct nand_data_interface *conf,
-					bool check_only)
+static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
 {
 	struct nand_chip *nand = mtd_to_nand(mtd);
 	struct sunxi_nand_chip *chip = to_sunxi_nand(nand);
@@ -1707,7 +1705,7 @@ static int sunxi_nfc_setup_data_interface(struct mtd_info *mtd,
 		return tRHW;
 	}
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	/*
@@ -1922,7 +1920,6 @@ static int sunxi_nand_hw_ecc_ctrl_init(struct mtd_info *mtd,
 	ecc->write_subpage = sunxi_nfc_hw_ecc_write_subpage;
 	ecc->read_oob_raw = nand_read_oob_std;
 	ecc->write_oob_raw = nand_write_oob_std;
-	ecc->read_subpage = sunxi_nfc_hw_ecc_read_subpage;
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/tango_nand.c b/drivers/mtd/nand/tango_nand.c
index 49b286c6c10f..9d40b793b1c4 100644
--- a/drivers/mtd/nand/tango_nand.c
+++ b/drivers/mtd/nand/tango_nand.c
@@ -303,7 +303,7 @@ static int tango_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 			    const u8 *buf, int oob_required, int page)
 {
 	struct tango_nfc *nfc = to_tango_nfc(chip->controller);
-	int err, len = mtd->writesize;
+	int err, status, len = mtd->writesize;
 
 	/* Calling tango_write_oob() would send PAGEPROG twice */
 	if (oob_required)
@@ -314,6 +314,10 @@ static int tango_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	if (err)
 		return err;
 
+	status = chip->waitfunc(mtd, chip);
+	if (status & NAND_STATUS_FAIL)
+		return -EIO;
+
 	return 0;
 }
 
@@ -340,7 +344,7 @@ static void aux_write(struct nand_chip *chip, const u8 **buf, int len, int *pos)
 
 	if (!*buf) {
 		/* skip over "len" bytes */
-		chip->cmdfunc(mtd, NAND_CMD_SEQIN, *pos, -1);
+		chip->cmdfunc(mtd, NAND_CMD_RNDIN, *pos, -1);
 	} else {
 		tango_write_buf(mtd, *buf, len);
 		*buf += len;
@@ -431,9 +435,16 @@ static int tango_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 static int tango_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 				const u8 *buf, int oob_required, int page)
 {
+	int status;
+
 	chip->cmdfunc(mtd, NAND_CMD_SEQIN, 0, page);
 	raw_write(chip, buf, chip->oob_poi);
 	chip->cmdfunc(mtd, NAND_CMD_PAGEPROG, -1, -1);
+
+	status = chip->waitfunc(mtd, chip);
+	if (status & NAND_STATUS_FAIL)
+		return -EIO;
+
 	return 0;
 }
 
@@ -484,9 +495,8 @@ static u32 to_ticks(int kHz, int ps)
 	return DIV_ROUND_UP_ULL((u64)kHz * ps, NSEC_PER_SEC);
 }
 
-static int tango_set_timings(struct mtd_info *mtd,
-			     const struct nand_data_interface *conf,
-			     bool check_only)
+static int tango_set_timings(struct mtd_info *mtd, int csline,
+			     const struct nand_data_interface *conf)
 {
 	const struct nand_sdr_timings *sdr = nand_get_sdr_timings(conf);
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -498,7 +508,7 @@ static int tango_set_timings(struct mtd_info *mtd,
 	if (IS_ERR(sdr))
 		return PTR_ERR(sdr);
 
-	if (check_only)
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	Trdy = to_ticks(kHz, sdr->tCEA_max - sdr->tREA_max);
diff --git a/drivers/mtd/nand/vf610_nfc.c b/drivers/mtd/nand/vf610_nfc.c
index 3ea4bb19e12d..744ab10e8962 100644
--- a/drivers/mtd/nand/vf610_nfc.c
+++ b/drivers/mtd/nand/vf610_nfc.c
@@ -703,6 +703,8 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 	chip->read_buf = vf610_nfc_read_buf;
 	chip->write_buf = vf610_nfc_write_buf;
 	chip->select_chip = vf610_nfc_select_chip;
+	chip->onfi_set_features = nand_onfi_get_set_features_notsupp;
+	chip->onfi_get_features = nand_onfi_get_set_features_notsupp;
 
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
diff --git a/drivers/mtd/parsers/Kconfig b/drivers/mtd/parsers/Kconfig
new file mode 100644
index 000000000000..d206b3c533bc
--- /dev/null
+++ b/drivers/mtd/parsers/Kconfig
@@ -0,0 +1,8 @@
+config MTD_PARSER_TRX
+	tristate "Parser for TRX format partitions"
+	depends on MTD && (BCM47XX || ARCH_BCM_5301X || COMPILE_TEST)
+	help
+	  TRX is a firmware format used by Broadcom on their devices. It
+	  may contain up to 3/4 partitions (depending on the version).
+	  This driver will parse TRX header and report at least two partitions:
+	  kernel and rootfs.
diff --git a/drivers/mtd/parsers/Makefile b/drivers/mtd/parsers/Makefile
new file mode 100644
index 000000000000..4d9024e0be3b
--- /dev/null
+++ b/drivers/mtd/parsers/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_MTD_PARSER_TRX)		+= parser_trx.o
diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c
new file mode 100644
index 000000000000..df360a75e1eb
--- /dev/null
+++ b/drivers/mtd/parsers/parser_trx.c
@@ -0,0 +1,126 @@
+/*
+ * Parser for TRX format partitions
+ *
+ * Copyright (C) 2012 - 2017 Rafał Miłecki <rafal@milecki.pl>
+ *
+ * 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/module.h>
+#include <linux/slab.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+
+#define TRX_PARSER_MAX_PARTS		4
+
+/* Magics */
+#define TRX_MAGIC			0x30524448
+#define UBI_EC_MAGIC			0x23494255	/* UBI# */
+
+struct trx_header {
+	uint32_t magic;
+	uint32_t length;
+	uint32_t crc32;
+	uint16_t flags;
+	uint16_t version;
+	uint32_t offset[3];
+} __packed;
+
+static const char *parser_trx_data_part_name(struct mtd_info *master,
+					     size_t offset)
+{
+	uint32_t buf;
+	size_t bytes_read;
+	int err;
+
+	err  = mtd_read(master, offset, sizeof(buf), &bytes_read,
+			(uint8_t *)&buf);
+	if (err && !mtd_is_bitflip(err)) {
+		pr_err("mtd_read error while parsing (offset: 0x%zX): %d\n",
+			offset, err);
+		goto out_default;
+	}
+
+	if (buf == UBI_EC_MAGIC)
+		return "ubi";
+
+out_default:
+	return "rootfs";
+}
+
+static int parser_trx_parse(struct mtd_info *mtd,
+			    const struct mtd_partition **pparts,
+			    struct mtd_part_parser_data *data)
+{
+	struct mtd_partition *parts;
+	struct mtd_partition *part;
+	struct trx_header trx;
+	size_t bytes_read;
+	uint8_t curr_part = 0, i = 0;
+	int err;
+
+	parts = kzalloc(sizeof(struct mtd_partition) * TRX_PARSER_MAX_PARTS,
+			GFP_KERNEL);
+	if (!parts)
+		return -ENOMEM;
+
+	err = mtd_read(mtd, 0, sizeof(trx), &bytes_read, (uint8_t *)&trx);
+	if (err) {
+		pr_err("MTD reading error: %d\n", err);
+		kfree(parts);
+		return err;
+	}
+
+	if (trx.magic != TRX_MAGIC) {
+		kfree(parts);
+		return -ENOENT;
+	}
+
+	/* We have LZMA loader if there is address in offset[2] */
+	if (trx.offset[2]) {
+		part = &parts[curr_part++];
+		part->name = "loader";
+		part->offset = trx.offset[i];
+		i++;
+	}
+
+	if (trx.offset[i]) {
+		part = &parts[curr_part++];
+		part->name = "linux";
+		part->offset = trx.offset[i];
+		i++;
+	}
+
+	if (trx.offset[i]) {
+		part = &parts[curr_part++];
+		part->name = parser_trx_data_part_name(mtd, trx.offset[i]);
+		part->offset = trx.offset[i];
+		i++;
+	}
+
+	/*
+	 * Assume that every partition ends at the beginning of the one it is
+	 * followed by.
+	 */
+	for (i = 0; i < curr_part; i++) {
+		u64 next_part_offset = (i < curr_part - 1) ?
+				       parts[i + 1].offset : mtd->size;
+
+		parts[i].size = next_part_offset - parts[i].offset;
+	}
+
+	*pparts = parts;
+	return i;
+};
+
+static struct mtd_part_parser mtd_parser_trx = {
+	.parse_fn = parser_trx_parse,
+	.name = "trx",
+};
+module_mtd_part_parser(mtd_parser_trx);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Parser for TRX format partitions");
diff --git a/drivers/mtd/spi-nor/Kconfig b/drivers/mtd/spi-nor/Kconfig
index bfdfb1e72b38..293c8a4d1e49 100644
--- a/drivers/mtd/spi-nor/Kconfig
+++ b/drivers/mtd/spi-nor/Kconfig
@@ -108,7 +108,7 @@ config SPI_INTEL_SPI_PLATFORM
 
 config SPI_STM32_QUADSPI
 	tristate "STM32 Quad SPI controller"
-	depends on ARCH_STM32
+	depends on ARCH_STM32 || COMPILE_TEST
 	help
 	  This enables support for the STM32 Quad SPI controller.
 	  We only connect the NOR to this controller.
diff --git a/drivers/mtd/spi-nor/aspeed-smc.c b/drivers/mtd/spi-nor/aspeed-smc.c
index 56051d30f000..0106357421bd 100644
--- a/drivers/mtd/spi-nor/aspeed-smc.c
+++ b/drivers/mtd/spi-nor/aspeed-smc.c
@@ -19,6 +19,7 @@
 #include <linux/mtd/spi-nor.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/sizes.h>
 #include <linux/sysfs.h>
 
 #define DEVICE_NAME	"aspeed-smc"
@@ -97,6 +98,7 @@ struct aspeed_smc_chip {
 	struct aspeed_smc_controller *controller;
 	void __iomem *ctl;			/* control register */
 	void __iomem *ahb_base;			/* base of chip window */
+	u32 ahb_window_size;			/* chip mapping window size */
 	u32 ctl_val[smc_max];			/* control settings */
 	enum aspeed_smc_flash_type type;	/* what type of flash */
 	struct spi_nor nor;
@@ -109,6 +111,7 @@ struct aspeed_smc_controller {
 	const struct aspeed_smc_info *info;	/* type info of controller */
 	void __iomem *regs;			/* controller registers */
 	void __iomem *ahb_base;			/* per-chip windows resource */
+	u32 ahb_window_size;			/* full mapping window size */
 
 	struct aspeed_smc_chip *chips[0];	/* pointers to attached chips */
 };
@@ -180,8 +183,7 @@ struct aspeed_smc_controller {
 
 #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)
+	 CONTROL_CLOCK_FREQ_SEL_MASK | CONTROL_LSB_FIRST | CONTROL_CLOCK_MODE_3)
 
 /*
  * The Segment Register uses a 8MB unit to encode the start address
@@ -194,6 +196,10 @@ struct aspeed_smc_controller {
 #define SEGMENT_ADDR_REG0		0x30
 #define SEGMENT_ADDR_START(_r)		((((_r) >> 16) & 0xFF) << 23)
 #define SEGMENT_ADDR_END(_r)		((((_r) >> 24) & 0xFF) << 23)
+#define SEGMENT_ADDR_VALUE(start, end)					\
+	(((((start) >> 23) & 0xFF) << 16) | ((((end) >> 23) & 0xFF) << 24))
+#define SEGMENT_ADDR_REG(controller, cs)	\
+	((controller)->regs + SEGMENT_ADDR_REG0 + (cs) * 4)
 
 /*
  * In user mode all data bytes read or written to the chip decode address
@@ -439,8 +445,7 @@ static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip,
 	u32 reg;
 
 	if (controller->info->nce > 1) {
-		reg = readl(controller->regs + SEGMENT_ADDR_REG0 +
-			    chip->cs * 4);
+		reg = readl(SEGMENT_ADDR_REG(controller, chip->cs));
 
 		if (SEGMENT_ADDR_START(reg) >= SEGMENT_ADDR_END(reg))
 			return NULL;
@@ -451,6 +456,146 @@ static void __iomem *aspeed_smc_chip_base(struct aspeed_smc_chip *chip,
 	return controller->ahb_base + offset;
 }
 
+static u32 aspeed_smc_ahb_base_phy(struct aspeed_smc_controller *controller)
+{
+	u32 seg0_val = readl(SEGMENT_ADDR_REG(controller, 0));
+
+	return SEGMENT_ADDR_START(seg0_val);
+}
+
+static u32 chip_set_segment(struct aspeed_smc_chip *chip, u32 cs, u32 start,
+			    u32 size)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	void __iomem *seg_reg;
+	u32 seg_oldval, seg_newval, ahb_base_phy, end;
+
+	ahb_base_phy = aspeed_smc_ahb_base_phy(controller);
+
+	seg_reg = SEGMENT_ADDR_REG(controller, cs);
+	seg_oldval = readl(seg_reg);
+
+	/*
+	 * If the chip size is not specified, use the default segment
+	 * size, but take into account the possible overlap with the
+	 * previous segment
+	 */
+	if (!size)
+		size = SEGMENT_ADDR_END(seg_oldval) - start;
+
+	/*
+	 * The segment cannot exceed the maximum window size of the
+	 * controller.
+	 */
+	if (start + size > ahb_base_phy + controller->ahb_window_size) {
+		size = ahb_base_phy + controller->ahb_window_size - start;
+		dev_warn(chip->nor.dev, "CE%d window resized to %dMB",
+			 cs, size >> 20);
+	}
+
+	end = start + size;
+	seg_newval = SEGMENT_ADDR_VALUE(start, end);
+	writel(seg_newval, seg_reg);
+
+	/*
+	 * Restore default value if something goes wrong. The chip
+	 * might have set some bogus value and we would loose access
+	 * to the chip.
+	 */
+	if (seg_newval != readl(seg_reg)) {
+		dev_err(chip->nor.dev, "CE%d window invalid", cs);
+		writel(seg_oldval, seg_reg);
+		start = SEGMENT_ADDR_START(seg_oldval);
+		end = SEGMENT_ADDR_END(seg_oldval);
+		size = end - start;
+	}
+
+	dev_info(chip->nor.dev, "CE%d window [ 0x%.8x - 0x%.8x ] %dMB",
+		 cs, start, end, size >> 20);
+
+	return size;
+}
+
+/*
+ * The segment register defines the mapping window on the AHB bus and
+ * it needs to be configured depending on the chip size. The segment
+ * register of the following CE also needs to be tuned in order to
+ * provide a contiguous window across multiple chips.
+ *
+ * This is expected to be called in increasing CE order
+ */
+static u32 aspeed_smc_chip_set_segment(struct aspeed_smc_chip *chip)
+{
+	struct aspeed_smc_controller *controller = chip->controller;
+	u32 ahb_base_phy, start;
+	u32 size = chip->nor.mtd.size;
+
+	/*
+	 * Each controller has a chip size limit for direct memory
+	 * access
+	 */
+	if (size > controller->info->maxsize)
+		size = controller->info->maxsize;
+
+	/*
+	 * The AST2400 SPI controller only handles one chip and does
+	 * not have segment registers. Let's use the chip size for the
+	 * AHB window.
+	 */
+	if (controller->info == &spi_2400_info)
+		goto out;
+
+	/*
+	 * The AST2500 SPI controller has a HW bug when the CE0 chip
+	 * size reaches 128MB. Enforce a size limit of 120MB to
+	 * prevent the controller from using bogus settings in the
+	 * segment register.
+	 */
+	if (chip->cs == 0 && controller->info == &spi_2500_info &&
+	    size == SZ_128M) {
+		size = 120 << 20;
+		dev_info(chip->nor.dev,
+			 "CE%d window resized to %dMB (AST2500 HW quirk)",
+			 chip->cs, size >> 20);
+	}
+
+	ahb_base_phy = aspeed_smc_ahb_base_phy(controller);
+
+	/*
+	 * As a start address for the current segment, use the default
+	 * start address if we are handling CE0 or use the previous
+	 * segment ending address
+	 */
+	if (chip->cs) {
+		u32 prev = readl(SEGMENT_ADDR_REG(controller, chip->cs - 1));
+
+		start = SEGMENT_ADDR_END(prev);
+	} else {
+		start = ahb_base_phy;
+	}
+
+	size = chip_set_segment(chip, chip->cs, start, size);
+
+	/* Update chip base address on the AHB bus */
+	chip->ahb_base = controller->ahb_base + (start - ahb_base_phy);
+
+	/*
+	 * Now, make sure the next segment does not overlap with the
+	 * current one we just configured, even if there is no
+	 * available chip. That could break access in Command Mode.
+	 */
+	if (chip->cs < controller->info->nce - 1)
+		chip_set_segment(chip, chip->cs + 1, start + size, 0);
+
+out:
+	if (size < chip->nor.mtd.size)
+		dev_warn(chip->nor.dev,
+			 "CE%d window too small for chip %dMB",
+			 chip->cs, (u32)chip->nor.mtd.size >> 20);
+
+	return size;
+}
+
 static void aspeed_smc_chip_enable_write(struct aspeed_smc_chip *chip)
 {
 	struct aspeed_smc_controller *controller = chip->controller;
@@ -524,7 +669,7 @@ static int aspeed_smc_chip_setup_init(struct aspeed_smc_chip *chip,
 	 */
 	chip->ahb_base = aspeed_smc_chip_base(chip, res);
 	if (!chip->ahb_base) {
-		dev_warn(chip->nor.dev, "CE segment window closed.\n");
+		dev_warn(chip->nor.dev, "CE%d window closed", chip->cs);
 		return -EINVAL;
 	}
 
@@ -571,6 +716,9 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 	if (chip->nor.addr_width == 4 && info->set_4b)
 		info->set_4b(chip);
 
+	/* This is for direct AHB access when using Command Mode. */
+	chip->ahb_window_size = aspeed_smc_chip_set_segment(chip);
+
 	/*
 	 * base mode has not been optimized yet. use it for writes.
 	 */
@@ -585,14 +733,12 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 	 * 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:
+	if (chip->nor.read_proto == SNOR_PROTO_1_1_1) {
+		if (chip->nor.read_dummy == 0)
+			cmd = CONTROL_COMMAND_MODE_NORMAL;
+		else
+			cmd = CONTROL_COMMAND_MODE_FREAD;
+	} else {
 		dev_err(chip->nor.dev, "unsupported SPI read mode\n");
 		return -EINVAL;
 	}
@@ -608,6 +754,11 @@ static int aspeed_smc_chip_setup_finish(struct aspeed_smc_chip *chip)
 static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 				  struct device_node *np, struct resource *r)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	const struct aspeed_smc_info *info = controller->info;
 	struct device *dev = controller->dev;
 	struct device_node *child;
@@ -671,11 +822,11 @@ static int aspeed_smc_setup_flash(struct aspeed_smc_controller *controller,
 			break;
 
 		/*
-		 * TODO: Add support for SPI_NOR_QUAD and SPI_NOR_DUAL
+		 * TODO: Add support for Dual and Quad SPI protocols
 		 * attach when board support is present as determined
 		 * by of property.
 		 */
-		ret = spi_nor_scan(nor, NULL, SPI_NOR_NORMAL);
+		ret = spi_nor_scan(nor, NULL, &hwcaps);
 		if (ret)
 			break;
 
@@ -731,6 +882,8 @@ static int aspeed_smc_probe(struct platform_device *pdev)
 	if (IS_ERR(controller->ahb_base))
 		return PTR_ERR(controller->ahb_base);
 
+	controller->ahb_window_size = resource_size(res);
+
 	ret = aspeed_smc_setup_flash(controller, np, res);
 	if (ret)
 		dev_err(dev, "Aspeed SMC probe failed %d\n", ret);
diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index 47937d9beec6..ba76fa8f2031 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -275,14 +275,48 @@ static void atmel_qspi_debug_command(struct atmel_qspi *aq,
 
 static int atmel_qspi_run_command(struct atmel_qspi *aq,
 				  const struct atmel_qspi_command *cmd,
-				  u32 ifr_tfrtyp, u32 ifr_width)
+				  u32 ifr_tfrtyp, enum spi_nor_protocol proto)
 {
 	u32 iar, icr, ifr, sr;
 	int err = 0;
 
 	iar = 0;
 	icr = 0;
-	ifr = ifr_tfrtyp | ifr_width;
+	ifr = ifr_tfrtyp;
+
+	/* Set the SPI protocol */
+	switch (proto) {
+	case SNOR_PROTO_1_1_1:
+		ifr |= QSPI_IFR_WIDTH_SINGLE_BIT_SPI;
+		break;
+
+	case SNOR_PROTO_1_1_2:
+		ifr |= QSPI_IFR_WIDTH_DUAL_OUTPUT;
+		break;
+
+	case SNOR_PROTO_1_1_4:
+		ifr |= QSPI_IFR_WIDTH_QUAD_OUTPUT;
+		break;
+
+	case SNOR_PROTO_1_2_2:
+		ifr |= QSPI_IFR_WIDTH_DUAL_IO;
+		break;
+
+	case SNOR_PROTO_1_4_4:
+		ifr |= QSPI_IFR_WIDTH_QUAD_IO;
+		break;
+
+	case SNOR_PROTO_2_2_2:
+		ifr |= QSPI_IFR_WIDTH_DUAL_CMD;
+		break;
+
+	case SNOR_PROTO_4_4_4:
+		ifr |= QSPI_IFR_WIDTH_QUAD_CMD;
+		break;
+
+	default:
+		return -EINVAL;
+	}
 
 	/* Compute instruction parameters */
 	if (cmd->enable.bits.instruction) {
@@ -434,7 +468,7 @@ static int atmel_qspi_read_reg(struct spi_nor *nor, u8 opcode,
 	cmd.rx_buf = buf;
 	cmd.buf_len = len;
 	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ,
-				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				      nor->reg_proto);
 }
 
 static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode,
@@ -450,7 +484,7 @@ static int atmel_qspi_write_reg(struct spi_nor *nor, u8 opcode,
 	cmd.tx_buf = buf;
 	cmd.buf_len = len;
 	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE,
-				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				      nor->reg_proto);
 }
 
 static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
@@ -469,7 +503,7 @@ static ssize_t atmel_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
 	cmd.tx_buf = write_buf;
 	cmd.buf_len = len;
 	ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE_MEM,
-				     QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				     nor->write_proto);
 	return (ret < 0) ? ret : len;
 }
 
@@ -484,7 +518,7 @@ static int atmel_qspi_erase(struct spi_nor *nor, loff_t offs)
 	cmd.instruction = nor->erase_opcode;
 	cmd.address = (u32)offs;
 	return atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_WRITE,
-				      QSPI_IFR_WIDTH_SINGLE_BIT_SPI);
+				      nor->reg_proto);
 }
 
 static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
@@ -493,27 +527,8 @@ static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct atmel_qspi *aq = nor->priv;
 	struct atmel_qspi_command cmd;
 	u8 num_mode_cycles, num_dummy_cycles;
-	u32 ifr_width;
 	ssize_t ret;
 
-	switch (nor->flash_read) {
-	case SPI_NOR_NORMAL:
-	case SPI_NOR_FAST:
-		ifr_width = QSPI_IFR_WIDTH_SINGLE_BIT_SPI;
-		break;
-
-	case SPI_NOR_DUAL:
-		ifr_width = QSPI_IFR_WIDTH_DUAL_OUTPUT;
-		break;
-
-	case SPI_NOR_QUAD:
-		ifr_width = QSPI_IFR_WIDTH_QUAD_OUTPUT;
-		break;
-
-	default:
-		return -EINVAL;
-	}
-
 	if (nor->read_dummy >= 2) {
 		num_mode_cycles = 2;
 		num_dummy_cycles = nor->read_dummy - 2;
@@ -536,7 +551,7 @@ static ssize_t atmel_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	cmd.rx_buf = read_buf;
 	cmd.buf_len = len;
 	ret = atmel_qspi_run_command(aq, &cmd, QSPI_IFR_TFRTYP_TRSFR_READ_MEM,
-				     ifr_width);
+				     nor->read_proto);
 	return (ret < 0) ? ret : len;
 }
 
@@ -590,6 +605,20 @@ static irqreturn_t atmel_qspi_interrupt(int irq, void *dev_id)
 
 static int atmel_qspi_probe(struct platform_device *pdev)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_READ_1_2_2 |
+			SNOR_HWCAPS_READ_2_2_2 |
+			SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_READ_1_4_4 |
+			SNOR_HWCAPS_READ_4_4_4 |
+			SNOR_HWCAPS_PP |
+			SNOR_HWCAPS_PP_1_1_4 |
+			SNOR_HWCAPS_PP_1_4_4 |
+			SNOR_HWCAPS_PP_4_4_4,
+	};
 	struct device_node *child, *np = pdev->dev.of_node;
 	struct atmel_qspi *aq;
 	struct resource *res;
@@ -679,7 +708,7 @@ static int atmel_qspi_probe(struct platform_device *pdev)
 	if (err)
 		goto disable_clk;
 
-	err = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+	err = spi_nor_scan(nor, NULL, &hwcaps);
 	if (err)
 		goto disable_clk;
 
diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index 9f8102de1b16..53c7d8e0327a 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -855,15 +855,14 @@ static int cqspi_set_protocol(struct spi_nor *nor, const int read)
 	f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
 
 	if (read) {
-		switch (nor->flash_read) {
-		case SPI_NOR_NORMAL:
-		case SPI_NOR_FAST:
+		switch (nor->read_proto) {
+		case SNOR_PROTO_1_1_1:
 			f_pdata->data_width = CQSPI_INST_TYPE_SINGLE;
 			break;
-		case SPI_NOR_DUAL:
+		case SNOR_PROTO_1_1_2:
 			f_pdata->data_width = CQSPI_INST_TYPE_DUAL;
 			break;
-		case SPI_NOR_QUAD:
+		case SNOR_PROTO_1_1_4:
 			f_pdata->data_width = CQSPI_INST_TYPE_QUAD;
 			break;
 		default:
@@ -1069,6 +1068,13 @@ static void cqspi_controller_init(struct cqspi_st *cqspi)
 
 static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_PP,
+	};
 	struct platform_device *pdev = cqspi->pdev;
 	struct device *dev = &pdev->dev;
 	struct cqspi_flash_pdata *f_pdata;
@@ -1123,7 +1129,7 @@ static int cqspi_setup_flash(struct cqspi_st *cqspi, struct device_node *np)
 			goto err;
 		}
 
-		ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+		ret = spi_nor_scan(nor, NULL, &hwcaps);
 		if (ret)
 			goto err;
 
@@ -1277,7 +1283,7 @@ static const struct dev_pm_ops cqspi__dev_pm_ops = {
 #define CQSPI_DEV_PM_OPS	NULL
 #endif
 
-static struct of_device_id const cqspi_dt_ids[] = {
+static const struct of_device_id cqspi_dt_ids[] = {
 	{.compatible = "cdns,qspi-nor",},
 	{ /* end of table */ }
 };
diff --git a/drivers/mtd/spi-nor/fsl-quadspi.c b/drivers/mtd/spi-nor/fsl-quadspi.c
index 1476135e0d50..f17d22435bfc 100644
--- a/drivers/mtd/spi-nor/fsl-quadspi.c
+++ b/drivers/mtd/spi-nor/fsl-quadspi.c
@@ -957,6 +957,10 @@ static void fsl_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 
 static int fsl_qspi_probe(struct platform_device *pdev)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_PP,
+	};
 	struct device_node *np = pdev->dev.of_node;
 	struct device *dev = &pdev->dev;
 	struct fsl_qspi *q;
@@ -1065,7 +1069,7 @@ static int fsl_qspi_probe(struct platform_device *pdev)
 		/* set the chip address for READID */
 		fsl_qspi_set_base_addr(q, nor);
 
-		ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+		ret = spi_nor_scan(nor, NULL, &hwcaps);
 		if (ret)
 			goto mutex_failed;
 
diff --git a/drivers/mtd/spi-nor/hisi-sfc.c b/drivers/mtd/spi-nor/hisi-sfc.c
index a286350627a6..d1106832b9d5 100644
--- a/drivers/mtd/spi-nor/hisi-sfc.c
+++ b/drivers/mtd/spi-nor/hisi-sfc.c
@@ -120,19 +120,24 @@ static inline int wait_op_finish(struct hifmc_host *host)
 		(reg & FMC_INT_OP_DONE), 0, FMC_WAIT_TIMEOUT);
 }
 
-static int get_if_type(enum read_mode flash_read)
+static int get_if_type(enum spi_nor_protocol proto)
 {
 	enum hifmc_iftype if_type;
 
-	switch (flash_read) {
-	case SPI_NOR_DUAL:
+	switch (proto) {
+	case SNOR_PROTO_1_1_2:
 		if_type = IF_TYPE_DUAL;
 		break;
-	case SPI_NOR_QUAD:
+	case SNOR_PROTO_1_2_2:
+		if_type = IF_TYPE_DIO;
+		break;
+	case SNOR_PROTO_1_1_4:
 		if_type = IF_TYPE_QUAD;
 		break;
-	case SPI_NOR_NORMAL:
-	case SPI_NOR_FAST:
+	case SNOR_PROTO_1_4_4:
+		if_type = IF_TYPE_QIO;
+		break;
+	case SNOR_PROTO_1_1_1:
 	default:
 		if_type = IF_TYPE_STD;
 		break;
@@ -253,7 +258,10 @@ static int hisi_spi_nor_dma_transfer(struct spi_nor *nor, loff_t start_off,
 	writel(FMC_DMA_LEN_SET(len), host->regbase + FMC_DMA_LEN);
 
 	reg = OP_CFG_FM_CS(priv->chipselect);
-	if_type = get_if_type(nor->flash_read);
+	if (op_type == FMC_OP_READ)
+		if_type = get_if_type(nor->read_proto);
+	else
+		if_type = get_if_type(nor->write_proto);
 	reg |= OP_CFG_MEM_IF_TYPE(if_type);
 	if (op_type == FMC_OP_READ)
 		reg |= OP_CFG_DUMMY_NUM(nor->read_dummy >> 3);
@@ -321,6 +329,13 @@ static ssize_t hisi_spi_nor_write(struct spi_nor *nor, loff_t to,
 static int hisi_spi_nor_register(struct device_node *np,
 				struct hifmc_host *host)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_READ_1_1_4 |
+			SNOR_HWCAPS_PP,
+	};
 	struct device *dev = host->dev;
 	struct spi_nor *nor;
 	struct hifmc_priv *priv;
@@ -362,7 +377,7 @@ static int hisi_spi_nor_register(struct device_node *np,
 	nor->read = hisi_spi_nor_read;
 	nor->write = hisi_spi_nor_write;
 	nor->erase = NULL;
-	ret = spi_nor_scan(nor, NULL, SPI_NOR_QUAD);
+	ret = spi_nor_scan(nor, NULL, &hwcaps);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index 986a3d020a3a..8a596bfeddff 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -715,6 +715,11 @@ static void intel_spi_fill_partition(struct intel_spi *ispi,
 struct intel_spi *intel_spi_probe(struct device *dev,
 	struct resource *mem, const struct intel_spi_boardinfo *info)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	struct mtd_partition part;
 	struct intel_spi *ispi;
 	int ret;
@@ -746,7 +751,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 	ispi->nor.write = intel_spi_write;
 	ispi->nor.erase = intel_spi_erase;
 
-	ret = spi_nor_scan(&ispi->nor, NULL, SPI_NOR_NORMAL);
+	ret = spi_nor_scan(&ispi->nor, NULL, &hwcaps);
 	if (ret) {
 		dev_info(dev, "failed to locate the chip\n");
 		return ERR_PTR(ret);
diff --git a/drivers/mtd/spi-nor/mtk-quadspi.c b/drivers/mtd/spi-nor/mtk-quadspi.c
index b6377707ce32..8a20ec4991c8 100644
--- a/drivers/mtd/spi-nor/mtk-quadspi.c
+++ b/drivers/mtd/spi-nor/mtk-quadspi.c
@@ -123,20 +123,20 @@ static void mt8173_nor_set_read_mode(struct mt8173_nor *mt8173_nor)
 {
 	struct spi_nor *nor = &mt8173_nor->nor;
 
-	switch (nor->flash_read) {
-	case SPI_NOR_FAST:
+	switch (nor->read_proto) {
+	case SNOR_PROTO_1_1_1:
 		writeb(nor->read_opcode, mt8173_nor->base +
 		       MTK_NOR_PRGDATA3_REG);
 		writeb(MTK_NOR_FAST_READ, mt8173_nor->base +
 		       MTK_NOR_CFG1_REG);
 		break;
-	case SPI_NOR_DUAL:
+	case SNOR_PROTO_1_1_2:
 		writeb(nor->read_opcode, mt8173_nor->base +
 		       MTK_NOR_PRGDATA3_REG);
 		writeb(MTK_NOR_DUAL_READ_EN, mt8173_nor->base +
 		       MTK_NOR_DUAL_REG);
 		break;
-	case SPI_NOR_QUAD:
+	case SNOR_PROTO_1_1_4:
 		writeb(nor->read_opcode, mt8173_nor->base +
 		       MTK_NOR_PRGDATA4_REG);
 		writeb(MTK_NOR_QUAD_READ_EN, mt8173_nor->base +
@@ -408,6 +408,11 @@ static int mt8173_nor_write_reg(struct spi_nor *nor, u8 opcode, u8 *buf,
 static int mtk_nor_init(struct mt8173_nor *mt8173_nor,
 			struct device_node *flash_node)
 {
+	const struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_READ_1_1_2 |
+			SNOR_HWCAPS_PP,
+	};
 	int ret;
 	struct spi_nor *nor;
 
@@ -426,7 +431,7 @@ static int mtk_nor_init(struct mt8173_nor *mt8173_nor,
 	nor->write_reg = mt8173_nor_write_reg;
 	nor->mtd.name = "mtk_nor";
 	/* initialized with NULL */
-	ret = spi_nor_scan(nor, NULL, SPI_NOR_DUAL);
+	ret = spi_nor_scan(nor, NULL, &hwcaps);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 73a14f40928b..15374216d4d9 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -240,13 +240,12 @@ static int nxp_spifi_erase(struct spi_nor *nor, loff_t offs)
 
 static int nxp_spifi_setup_memory_cmd(struct nxp_spifi *spifi)
 {
-	switch (spifi->nor.flash_read) {
-	case SPI_NOR_NORMAL:
-	case SPI_NOR_FAST:
+	switch (spifi->nor.read_proto) {
+	case SNOR_PROTO_1_1_1:
 		spifi->mcmd = SPIFI_CMD_FIELDFORM_ALL_SERIAL;
 		break;
-	case SPI_NOR_DUAL:
-	case SPI_NOR_QUAD:
+	case SNOR_PROTO_1_1_2:
+	case SNOR_PROTO_1_1_4:
 		spifi->mcmd = SPIFI_CMD_FIELDFORM_QUAD_DUAL_DATA;
 		break;
 	default:
@@ -274,7 +273,11 @@ static void nxp_spifi_dummy_id_read(struct spi_nor *nor)
 static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 				 struct device_node *np)
 {
-	enum read_mode flash_read;
+	struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
 	u32 ctrl, property;
 	u16 mode = 0;
 	int ret;
@@ -308,13 +311,12 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 
 	if (mode & SPI_RX_DUAL) {
 		ctrl |= SPIFI_CTRL_DUAL;
-		flash_read = SPI_NOR_DUAL;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
 	} else if (mode & SPI_RX_QUAD) {
 		ctrl &= ~SPIFI_CTRL_DUAL;
-		flash_read = SPI_NOR_QUAD;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
 	} else {
 		ctrl |= SPIFI_CTRL_DUAL;
-		flash_read = SPI_NOR_NORMAL;
 	}
 
 	switch (mode & (SPI_CPHA | SPI_CPOL)) {
@@ -351,7 +353,7 @@ static int nxp_spifi_setup_flash(struct nxp_spifi *spifi,
 	 */
 	nxp_spifi_dummy_id_read(&spifi->nor);
 
-	ret = spi_nor_scan(&spifi->nor, NULL, flash_read);
+	ret = spi_nor_scan(&spifi->nor, NULL, &hwcaps);
 	if (ret) {
 		dev_err(spifi->dev, "device scan failed\n");
 		return ret;
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index dea8c9cbadf0..1413828ff1fb 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -150,24 +150,6 @@ static int read_cr(struct spi_nor *nor)
 }
 
 /*
- * Dummy Cycle calculation for different type of read.
- * It can be used to support more commands with
- * different dummy cycle requirements.
- */
-static inline int spi_nor_read_dummy_cycles(struct spi_nor *nor)
-{
-	switch (nor->flash_read) {
-	case SPI_NOR_FAST:
-	case SPI_NOR_DUAL:
-	case SPI_NOR_QUAD:
-		return 8;
-	case SPI_NOR_NORMAL:
-		return 0;
-	}
-	return 0;
-}
-
-/*
  * Write status register 1 byte
  * Returns negative if error occurred.
  */
@@ -221,6 +203,10 @@ static inline u8 spi_nor_convert_3to4_read(u8 opcode)
 		{ 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 },
+
+		{ SPINOR_OP_READ_1_1_1_DTR,	SPINOR_OP_READ_1_1_1_DTR_4B },
+		{ SPINOR_OP_READ_1_2_2_DTR,	SPINOR_OP_READ_1_2_2_DTR_4B },
+		{ SPINOR_OP_READ_1_4_4_DTR,	SPINOR_OP_READ_1_4_4_DTR_4B },
 	};
 
 	return spi_nor_convert_opcode(opcode, spi_nor_3to4_read,
@@ -1022,10 +1008,12 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "mx25u6435f",  INFO(0xc22537, 0, 64 * 1024, 128, SECT_4K) },
 	{ "mx25l12805d", INFO(0xc22018, 0, 64 * 1024, 256, 0) },
 	{ "mx25l12855e", INFO(0xc22618, 0, 64 * 1024, 256, 0) },
-	{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, 0) },
+	{ "mx25l25635e", INFO(0xc22019, 0, 64 * 1024, 512, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "mx25u25635f", INFO(0xc22539, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_4B_OPCODES) },
 	{ "mx25l25655e", INFO(0xc22619, 0, 64 * 1024, 512, 0) },
-	{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_QUAD_READ) },
+	{ "mx66l51235l", INFO(0xc2201a, 0, 64 * 1024, 1024, SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "mx66u51235f", INFO(0xc2253a, 0, 64 * 1024, 1024, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
+	{ "mx66l1g45g",  INFO(0xc2201b, 0, 64 * 1024, 2048, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "mx66l1g55g",  INFO(0xc2261b, 0, 64 * 1024, 2048, SPI_NOR_QUAD_READ) },
 
 	/* Micron */
@@ -1036,7 +1024,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "n25q064a",    INFO(0x20bb17, 0, 64 * 1024,  128, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q128a11",  INFO(0x20bb18, 0, 64 * 1024,  256, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q128a13",  INFO(0x20ba18, 0, 64 * 1024,  256, SECT_4K | SPI_NOR_QUAD_READ) },
-	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K | SPI_NOR_QUAD_READ) },
+	{ "n25q256a",    INFO(0x20ba19, 0, 64 * 1024,  512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
 	{ "n25q256ax1",  INFO(0x20bb19, 0, 64 * 1024,  512, SECT_4K | SPI_NOR_QUAD_READ) },
 	{ "n25q512a",    INFO(0x20bb20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
 	{ "n25q512ax3",  INFO(0x20ba20, 0, 64 * 1024, 1024, SECT_4K | USE_FSR | SPI_NOR_QUAD_READ) },
@@ -1076,6 +1064,7 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "s25fl164k",  INFO(0x014017,      0,  64 * 1024, 128, SECT_4K) },
 	{ "s25fl204k",  INFO(0x014013,      0,  64 * 1024,   8, SECT_4K | SPI_NOR_DUAL_READ) },
 	{ "s25fl208k",  INFO(0x014014,      0,  64 * 1024,  16, SECT_4K | SPI_NOR_DUAL_READ) },
+	{ "s25fl064l",  INFO(0x016017,      0,  64 * 1024, 128, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ | SPI_NOR_4B_OPCODES) },
 
 	/* SST -- large erase sizes are "overlays", "sectors" are 4K */
 	{ "sst25vf040b", INFO(0xbf258d, 0, 64 * 1024,  8, SECT_4K | SST_WRITE) },
@@ -1159,7 +1148,9 @@ static const struct flash_info spi_nor_ids[] = {
 	{ "w25q80", INFO(0xef5014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q80bl", INFO(0xef4014, 0, 64 * 1024,  16, SECT_4K) },
 	{ "w25q128", INFO(0xef4018, 0, 64 * 1024, 256, SECT_4K) },
-	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K) },
+	{ "w25q256", INFO(0xef4019, 0, 64 * 1024, 512, SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ) },
+	{ "w25m512jv", INFO(0xef7119, 0, 64 * 1024, 1024,
+			SECT_4K | SPI_NOR_QUAD_READ | SPI_NOR_DUAL_READ) },
 
 	/* Catalyst / On Semiconductor -- non-JEDEC */
 	{ "cat25c11", CAT25_INFO(  16, 8, 16, 1, SPI_NOR_NO_ERASE | SPI_NOR_NO_FR) },
@@ -1403,8 +1394,9 @@ static int macronix_quad_enable(struct spi_nor *nor)
 
 	write_sr(nor, val | SR_QUAD_EN_MX);
 
-	if (spi_nor_wait_till_ready(nor))
-		return 1;
+	ret = spi_nor_wait_till_ready(nor);
+	if (ret)
+		return ret;
 
 	ret = read_sr(nor);
 	if (!(ret > 0 && (ret & SR_QUAD_EN_MX))) {
@@ -1460,30 +1452,6 @@ static int spansion_quad_enable(struct spi_nor *nor)
 	return 0;
 }
 
-static int set_quad_mode(struct spi_nor *nor, const struct flash_info *info)
-{
-	int status;
-
-	switch (JEDEC_MFR(info)) {
-	case SNOR_MFR_MACRONIX:
-		status = macronix_quad_enable(nor);
-		if (status) {
-			dev_err(nor->dev, "Macronix quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
-	case SNOR_MFR_MICRON:
-		return 0;
-	default:
-		status = spansion_quad_enable(nor);
-		if (status) {
-			dev_err(nor->dev, "Spansion quad-read not enabled\n");
-			return -EINVAL;
-		}
-		return status;
-	}
-}
-
 static int spi_nor_check(struct spi_nor *nor)
 {
 	if (!nor->dev || !nor->read || !nor->write ||
@@ -1536,8 +1504,349 @@ static int s3an_nor_scan(const struct flash_info *info, struct spi_nor *nor)
 	return 0;
 }
 
-int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
+struct spi_nor_read_command {
+	u8			num_mode_clocks;
+	u8			num_wait_states;
+	u8			opcode;
+	enum spi_nor_protocol	proto;
+};
+
+struct spi_nor_pp_command {
+	u8			opcode;
+	enum spi_nor_protocol	proto;
+};
+
+enum spi_nor_read_command_index {
+	SNOR_CMD_READ,
+	SNOR_CMD_READ_FAST,
+	SNOR_CMD_READ_1_1_1_DTR,
+
+	/* Dual SPI */
+	SNOR_CMD_READ_1_1_2,
+	SNOR_CMD_READ_1_2_2,
+	SNOR_CMD_READ_2_2_2,
+	SNOR_CMD_READ_1_2_2_DTR,
+
+	/* Quad SPI */
+	SNOR_CMD_READ_1_1_4,
+	SNOR_CMD_READ_1_4_4,
+	SNOR_CMD_READ_4_4_4,
+	SNOR_CMD_READ_1_4_4_DTR,
+
+	/* Octo SPI */
+	SNOR_CMD_READ_1_1_8,
+	SNOR_CMD_READ_1_8_8,
+	SNOR_CMD_READ_8_8_8,
+	SNOR_CMD_READ_1_8_8_DTR,
+
+	SNOR_CMD_READ_MAX
+};
+
+enum spi_nor_pp_command_index {
+	SNOR_CMD_PP,
+
+	/* Quad SPI */
+	SNOR_CMD_PP_1_1_4,
+	SNOR_CMD_PP_1_4_4,
+	SNOR_CMD_PP_4_4_4,
+
+	/* Octo SPI */
+	SNOR_CMD_PP_1_1_8,
+	SNOR_CMD_PP_1_8_8,
+	SNOR_CMD_PP_8_8_8,
+
+	SNOR_CMD_PP_MAX
+};
+
+struct spi_nor_flash_parameter {
+	u64				size;
+	u32				page_size;
+
+	struct spi_nor_hwcaps		hwcaps;
+	struct spi_nor_read_command	reads[SNOR_CMD_READ_MAX];
+	struct spi_nor_pp_command	page_programs[SNOR_CMD_PP_MAX];
+
+	int (*quad_enable)(struct spi_nor *nor);
+};
+
+static void
+spi_nor_set_read_settings(struct spi_nor_read_command *read,
+			  u8 num_mode_clocks,
+			  u8 num_wait_states,
+			  u8 opcode,
+			  enum spi_nor_protocol proto)
 {
+	read->num_mode_clocks = num_mode_clocks;
+	read->num_wait_states = num_wait_states;
+	read->opcode = opcode;
+	read->proto = proto;
+}
+
+static void
+spi_nor_set_pp_settings(struct spi_nor_pp_command *pp,
+			u8 opcode,
+			enum spi_nor_protocol proto)
+{
+	pp->opcode = opcode;
+	pp->proto = proto;
+}
+
+static int spi_nor_init_params(struct spi_nor *nor,
+			       const struct flash_info *info,
+			       struct spi_nor_flash_parameter *params)
+{
+	/* Set legacy flash parameters as default. */
+	memset(params, 0, sizeof(*params));
+
+	/* Set SPI NOR sizes. */
+	params->size = info->sector_size * info->n_sectors;
+	params->page_size = info->page_size;
+
+	/* (Fast) Read settings. */
+	params->hwcaps.mask |= SNOR_HWCAPS_READ;
+	spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ],
+				  0, 0, SPINOR_OP_READ,
+				  SNOR_PROTO_1_1_1);
+
+	if (!(info->flags & SPI_NOR_NO_FR)) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_FAST],
+					  0, 8, SPINOR_OP_READ_FAST,
+					  SNOR_PROTO_1_1_1);
+	}
+
+	if (info->flags & SPI_NOR_DUAL_READ) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_1_1_2],
+					  0, 8, SPINOR_OP_READ_1_1_2,
+					  SNOR_PROTO_1_1_2);
+	}
+
+	if (info->flags & SPI_NOR_QUAD_READ) {
+		params->hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
+		spi_nor_set_read_settings(&params->reads[SNOR_CMD_READ_1_1_4],
+					  0, 8, SPINOR_OP_READ_1_1_4,
+					  SNOR_PROTO_1_1_4);
+	}
+
+	/* Page Program settings. */
+	params->hwcaps.mask |= SNOR_HWCAPS_PP;
+	spi_nor_set_pp_settings(&params->page_programs[SNOR_CMD_PP],
+				SPINOR_OP_PP, SNOR_PROTO_1_1_1);
+
+	/* Select the procedure to set the Quad Enable bit. */
+	if (params->hwcaps.mask & (SNOR_HWCAPS_READ_QUAD |
+				   SNOR_HWCAPS_PP_QUAD)) {
+		switch (JEDEC_MFR(info)) {
+		case SNOR_MFR_MACRONIX:
+			params->quad_enable = macronix_quad_enable;
+			break;
+
+		case SNOR_MFR_MICRON:
+			break;
+
+		default:
+			params->quad_enable = spansion_quad_enable;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int spi_nor_hwcaps2cmd(u32 hwcaps, const int table[][2], size_t size)
+{
+	size_t i;
+
+	for (i = 0; i < size; i++)
+		if (table[i][0] == (int)hwcaps)
+			return table[i][1];
+
+	return -EINVAL;
+}
+
+static int spi_nor_hwcaps_read2cmd(u32 hwcaps)
+{
+	static const int hwcaps_read2cmd[][2] = {
+		{ SNOR_HWCAPS_READ,		SNOR_CMD_READ },
+		{ SNOR_HWCAPS_READ_FAST,	SNOR_CMD_READ_FAST },
+		{ SNOR_HWCAPS_READ_1_1_1_DTR,	SNOR_CMD_READ_1_1_1_DTR },
+		{ SNOR_HWCAPS_READ_1_1_2,	SNOR_CMD_READ_1_1_2 },
+		{ SNOR_HWCAPS_READ_1_2_2,	SNOR_CMD_READ_1_2_2 },
+		{ SNOR_HWCAPS_READ_2_2_2,	SNOR_CMD_READ_2_2_2 },
+		{ SNOR_HWCAPS_READ_1_2_2_DTR,	SNOR_CMD_READ_1_2_2_DTR },
+		{ SNOR_HWCAPS_READ_1_1_4,	SNOR_CMD_READ_1_1_4 },
+		{ SNOR_HWCAPS_READ_1_4_4,	SNOR_CMD_READ_1_4_4 },
+		{ SNOR_HWCAPS_READ_4_4_4,	SNOR_CMD_READ_4_4_4 },
+		{ SNOR_HWCAPS_READ_1_4_4_DTR,	SNOR_CMD_READ_1_4_4_DTR },
+		{ SNOR_HWCAPS_READ_1_1_8,	SNOR_CMD_READ_1_1_8 },
+		{ SNOR_HWCAPS_READ_1_8_8,	SNOR_CMD_READ_1_8_8 },
+		{ SNOR_HWCAPS_READ_8_8_8,	SNOR_CMD_READ_8_8_8 },
+		{ SNOR_HWCAPS_READ_1_8_8_DTR,	SNOR_CMD_READ_1_8_8_DTR },
+	};
+
+	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_read2cmd,
+				  ARRAY_SIZE(hwcaps_read2cmd));
+}
+
+static int spi_nor_hwcaps_pp2cmd(u32 hwcaps)
+{
+	static const int hwcaps_pp2cmd[][2] = {
+		{ SNOR_HWCAPS_PP,		SNOR_CMD_PP },
+		{ SNOR_HWCAPS_PP_1_1_4,		SNOR_CMD_PP_1_1_4 },
+		{ SNOR_HWCAPS_PP_1_4_4,		SNOR_CMD_PP_1_4_4 },
+		{ SNOR_HWCAPS_PP_4_4_4,		SNOR_CMD_PP_4_4_4 },
+		{ SNOR_HWCAPS_PP_1_1_8,		SNOR_CMD_PP_1_1_8 },
+		{ SNOR_HWCAPS_PP_1_8_8,		SNOR_CMD_PP_1_8_8 },
+		{ SNOR_HWCAPS_PP_8_8_8,		SNOR_CMD_PP_8_8_8 },
+	};
+
+	return spi_nor_hwcaps2cmd(hwcaps, hwcaps_pp2cmd,
+				  ARRAY_SIZE(hwcaps_pp2cmd));
+}
+
+static int spi_nor_select_read(struct spi_nor *nor,
+			       const struct spi_nor_flash_parameter *params,
+			       u32 shared_hwcaps)
+{
+	int cmd, best_match = fls(shared_hwcaps & SNOR_HWCAPS_READ_MASK) - 1;
+	const struct spi_nor_read_command *read;
+
+	if (best_match < 0)
+		return -EINVAL;
+
+	cmd = spi_nor_hwcaps_read2cmd(BIT(best_match));
+	if (cmd < 0)
+		return -EINVAL;
+
+	read = &params->reads[cmd];
+	nor->read_opcode = read->opcode;
+	nor->read_proto = read->proto;
+
+	/*
+	 * In the spi-nor framework, we don't need to make the difference
+	 * between mode clock cycles and wait state clock cycles.
+	 * Indeed, the value of the mode clock cycles is used by a QSPI
+	 * flash memory to know whether it should enter or leave its 0-4-4
+	 * (Continuous Read / XIP) mode.
+	 * eXecution In Place is out of the scope of the mtd sub-system.
+	 * Hence we choose to merge both mode and wait state clock cycles
+	 * into the so called dummy clock cycles.
+	 */
+	nor->read_dummy = read->num_mode_clocks + read->num_wait_states;
+	return 0;
+}
+
+static int spi_nor_select_pp(struct spi_nor *nor,
+			     const struct spi_nor_flash_parameter *params,
+			     u32 shared_hwcaps)
+{
+	int cmd, best_match = fls(shared_hwcaps & SNOR_HWCAPS_PP_MASK) - 1;
+	const struct spi_nor_pp_command *pp;
+
+	if (best_match < 0)
+		return -EINVAL;
+
+	cmd = spi_nor_hwcaps_pp2cmd(BIT(best_match));
+	if (cmd < 0)
+		return -EINVAL;
+
+	pp = &params->page_programs[cmd];
+	nor->program_opcode = pp->opcode;
+	nor->write_proto = pp->proto;
+	return 0;
+}
+
+static int spi_nor_select_erase(struct spi_nor *nor,
+				const struct flash_info *info)
+{
+	struct mtd_info *mtd = &nor->mtd;
+
+#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
+	/* prefer "small sector" erase if possible */
+	if (info->flags & SECT_4K) {
+		nor->erase_opcode = SPINOR_OP_BE_4K;
+		mtd->erasesize = 4096;
+	} else if (info->flags & SECT_4K_PMC) {
+		nor->erase_opcode = SPINOR_OP_BE_4K_PMC;
+		mtd->erasesize = 4096;
+	} else
+#endif
+	{
+		nor->erase_opcode = SPINOR_OP_SE;
+		mtd->erasesize = info->sector_size;
+	}
+	return 0;
+}
+
+static int spi_nor_setup(struct spi_nor *nor, const struct flash_info *info,
+			 const struct spi_nor_flash_parameter *params,
+			 const struct spi_nor_hwcaps *hwcaps)
+{
+	u32 ignored_mask, shared_mask;
+	bool enable_quad_io;
+	int err;
+
+	/*
+	 * Keep only the hardware capabilities supported by both the SPI
+	 * controller and the SPI flash memory.
+	 */
+	shared_mask = hwcaps->mask & params->hwcaps.mask;
+
+	/* SPI n-n-n protocols are not supported yet. */
+	ignored_mask = (SNOR_HWCAPS_READ_2_2_2 |
+			SNOR_HWCAPS_READ_4_4_4 |
+			SNOR_HWCAPS_READ_8_8_8 |
+			SNOR_HWCAPS_PP_4_4_4 |
+			SNOR_HWCAPS_PP_8_8_8);
+	if (shared_mask & ignored_mask) {
+		dev_dbg(nor->dev,
+			"SPI n-n-n protocols are not supported yet.\n");
+		shared_mask &= ~ignored_mask;
+	}
+
+	/* Select the (Fast) Read command. */
+	err = spi_nor_select_read(nor, params, shared_mask);
+	if (err) {
+		dev_err(nor->dev,
+			"can't select read settings supported by both the SPI controller and memory.\n");
+		return err;
+	}
+
+	/* Select the Page Program command. */
+	err = spi_nor_select_pp(nor, params, shared_mask);
+	if (err) {
+		dev_err(nor->dev,
+			"can't select write settings supported by both the SPI controller and memory.\n");
+		return err;
+	}
+
+	/* Select the Sector Erase command. */
+	err = spi_nor_select_erase(nor, info);
+	if (err) {
+		dev_err(nor->dev,
+			"can't select erase settings supported by both the SPI controller and memory.\n");
+		return err;
+	}
+
+	/* Enable Quad I/O if needed. */
+	enable_quad_io = (spi_nor_get_protocol_width(nor->read_proto) == 4 ||
+			  spi_nor_get_protocol_width(nor->write_proto) == 4);
+	if (enable_quad_io && params->quad_enable) {
+		err = params->quad_enable(nor);
+		if (err) {
+			dev_err(nor->dev, "quad mode not supported\n");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int spi_nor_scan(struct spi_nor *nor, const char *name,
+		 const struct spi_nor_hwcaps *hwcaps)
+{
+	struct spi_nor_flash_parameter params;
 	const struct flash_info *info = NULL;
 	struct device *dev = nor->dev;
 	struct mtd_info *mtd = &nor->mtd;
@@ -1549,6 +1858,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (ret)
 		return ret;
 
+	/* Reset SPI protocol for all commands. */
+	nor->reg_proto = SNOR_PROTO_1_1_1;
+	nor->read_proto = SNOR_PROTO_1_1_1;
+	nor->write_proto = SNOR_PROTO_1_1_1;
+
 	if (name)
 		info = spi_nor_match_id(name);
 	/* Try to auto-detect if chip name wasn't specified or not found */
@@ -1591,6 +1905,11 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (info->flags & SPI_S3AN)
 		nor->flags |=  SNOR_F_READY_XSR_RDY;
 
+	/* Parse the Serial Flash Discoverable Parameters table. */
+	ret = spi_nor_init_params(nor, info, &params);
+	if (ret)
+		return ret;
+
 	/*
 	 * Atmel, SST, Intel/Numonyx, and others serial NOR tend to power up
 	 * with the software protection bits set
@@ -1611,7 +1930,7 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	mtd->type = MTD_NORFLASH;
 	mtd->writesize = 1;
 	mtd->flags = MTD_CAP_NORFLASH;
-	mtd->size = info->sector_size * info->n_sectors;
+	mtd->size = params.size;
 	mtd->_erase = spi_nor_erase;
 	mtd->_read = spi_nor_read;
 
@@ -1642,75 +1961,38 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 	if (info->flags & NO_CHIP_ERASE)
 		nor->flags |= SNOR_F_NO_OP_CHIP_ERASE;
 
-#ifdef CONFIG_MTD_SPI_NOR_USE_4K_SECTORS
-	/* prefer "small sector" erase if possible */
-	if (info->flags & SECT_4K) {
-		nor->erase_opcode = SPINOR_OP_BE_4K;
-		mtd->erasesize = 4096;
-	} else if (info->flags & SECT_4K_PMC) {
-		nor->erase_opcode = SPINOR_OP_BE_4K_PMC;
-		mtd->erasesize = 4096;
-	} else
-#endif
-	{
-		nor->erase_opcode = SPINOR_OP_SE;
-		mtd->erasesize = info->sector_size;
-	}
-
 	if (info->flags & SPI_NOR_NO_ERASE)
 		mtd->flags |= MTD_NO_ERASE;
 
 	mtd->dev.parent = dev;
-	nor->page_size = info->page_size;
+	nor->page_size = params.page_size;
 	mtd->writebufsize = nor->page_size;
 
 	if (np) {
 		/* If we were instantiated by DT, use it */
 		if (of_property_read_bool(np, "m25p,fast-read"))
-			nor->flash_read = SPI_NOR_FAST;
+			params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 		else
-			nor->flash_read = SPI_NOR_NORMAL;
+			params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
 	} else {
 		/* If we weren't instantiated by DT, default to fast-read */
-		nor->flash_read = SPI_NOR_FAST;
+		params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 	}
 
 	/* Some devices cannot do fast-read, no matter what DT tells us */
 	if (info->flags & SPI_NOR_NO_FR)
-		nor->flash_read = SPI_NOR_NORMAL;
-
-	/* Quad/Dual-read mode takes precedence over fast/normal */
-	if (mode == SPI_NOR_QUAD && info->flags & SPI_NOR_QUAD_READ) {
-		ret = set_quad_mode(nor, info);
-		if (ret) {
-			dev_err(dev, "quad mode not supported\n");
-			return ret;
-		}
-		nor->flash_read = SPI_NOR_QUAD;
-	} else if (mode == SPI_NOR_DUAL && info->flags & SPI_NOR_DUAL_READ) {
-		nor->flash_read = SPI_NOR_DUAL;
-	}
-
-	/* Default commands */
-	switch (nor->flash_read) {
-	case SPI_NOR_QUAD:
-		nor->read_opcode = SPINOR_OP_READ_1_1_4;
-		break;
-	case SPI_NOR_DUAL:
-		nor->read_opcode = SPINOR_OP_READ_1_1_2;
-		break;
-	case SPI_NOR_FAST:
-		nor->read_opcode = SPINOR_OP_READ_FAST;
-		break;
-	case SPI_NOR_NORMAL:
-		nor->read_opcode = SPINOR_OP_READ;
-		break;
-	default:
-		dev_err(dev, "No Read opcode defined\n");
-		return -EINVAL;
-	}
+		params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
 
-	nor->program_opcode = SPINOR_OP_PP;
+	/*
+	 * Configure the SPI memory:
+	 * - select op codes for (Fast) Read, Page Program and Sector Erase.
+	 * - set the number of dummy cycles (mode cycles + wait states).
+	 * - set the SPI protocols for register and memory accesses.
+	 * - set the Quad Enable bit if needed (required by SPI x-y-4 protos).
+	 */
+	ret = spi_nor_setup(nor, info, &params, hwcaps);
+	if (ret)
+		return ret;
 
 	if (info->addr_width)
 		nor->addr_width = info->addr_width;
@@ -1732,8 +2014,6 @@ int spi_nor_scan(struct spi_nor *nor, const char *name, enum read_mode mode)
 		return -EINVAL;
 	}
 
-	nor->read_dummy = spi_nor_read_dummy_cycles(nor);
-
 	if (info->flags & SPI_S3AN) {
 		ret = s3an_nor_scan(info, nor);
 		if (ret)
diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index ae45f81b8cd3..86c0931543c5 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -19,6 +19,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
+#include <linux/sizes.h>
 
 #define QUADSPI_CR		0x00
 #define CR_EN			BIT(0)
@@ -192,15 +193,15 @@ static void stm32_qspi_set_framemode(struct spi_nor *nor,
 	cmd->framemode = CCR_IMODE_1;
 
 	if (read) {
-		switch (nor->flash_read) {
-		case SPI_NOR_NORMAL:
-		case SPI_NOR_FAST:
+		switch (nor->read_proto) {
+		default:
+		case SNOR_PROTO_1_1_1:
 			dmode = CCR_DMODE_1;
 			break;
-		case SPI_NOR_DUAL:
+		case SNOR_PROTO_1_1_2:
 			dmode = CCR_DMODE_2;
 			break;
-		case SPI_NOR_QUAD:
+		case SNOR_PROTO_1_1_4:
 			dmode = CCR_DMODE_4;
 			break;
 		}
@@ -375,7 +376,7 @@ static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct stm32_qspi_cmd cmd;
 	int err;
 
-	dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#x\n",
+	dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#zx\n",
 		nor->read_opcode, buf, (u32)from, len);
 
 	memset(&cmd, 0, sizeof(cmd));
@@ -402,7 +403,7 @@ static ssize_t stm32_qspi_write(struct spi_nor *nor, loff_t to, size_t len,
 	struct stm32_qspi_cmd cmd;
 	int err;
 
-	dev_dbg(dev, "write(%#.2x): buf:%p to:%#.8x len:%#x\n",
+	dev_dbg(dev, "write(%#.2x): buf:%p to:%#.8x len:%#zx\n",
 		nor->program_opcode, buf, (u32)to, len);
 
 	memset(&cmd, 0, sizeof(cmd));
@@ -480,7 +481,12 @@ static void stm32_qspi_unprep(struct spi_nor *nor, enum spi_nor_ops ops)
 static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 				  struct device_node *np)
 {
-	u32 width, flash_read, presc, cs_num, max_rate = 0;
+	struct spi_nor_hwcaps hwcaps = {
+		.mask = SNOR_HWCAPS_READ |
+			SNOR_HWCAPS_READ_FAST |
+			SNOR_HWCAPS_PP,
+	};
+	u32 width, presc, cs_num, max_rate = 0;
 	struct stm32_qspi_flash *flash;
 	struct mtd_info *mtd;
 	int ret;
@@ -499,12 +505,10 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 		width = 1;
 
 	if (width == 4)
-		flash_read = SPI_NOR_QUAD;
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_4;
 	else if (width == 2)
-		flash_read = SPI_NOR_DUAL;
-	else if (width == 1)
-		flash_read = SPI_NOR_NORMAL;
-	else
+		hwcaps.mask |= SNOR_HWCAPS_READ_1_1_2;
+	else if (width != 1)
 		return -EINVAL;
 
 	flash = &qspi->flash[cs_num];
@@ -539,7 +543,7 @@ static int stm32_qspi_flash_setup(struct stm32_qspi *qspi,
 	 */
 	flash->fsize = FSIZE_VAL(SZ_1K);
 
-	ret = spi_nor_scan(&flash->nor, NULL, flash_read);
+	ret = spi_nor_scan(&flash->nor, NULL, &hwcaps);
 	if (ret) {
 		dev_err(qspi->dev, "device scan failed\n");
 		return ret;
diff --git a/drivers/mtd/tests/subpagetest.c b/drivers/mtd/tests/subpagetest.c
index aecc6ce5a9e1..fa2519ad2435 100644
--- a/drivers/mtd/tests/subpagetest.c
+++ b/drivers/mtd/tests/subpagetest.c
@@ -102,7 +102,7 @@ static int write_eraseblock2(int ebnum)
 		if (unlikely(err || written != subpgsize * k)) {
 			pr_err("error: write failed at %#llx\n",
 			       (long long)addr);
-			if (written != subpgsize) {
+			if (written != subpgsize * k) {
 				pr_err("  write size: %#x\n",
 				       subpgsize * k);
 				pr_err("  written: %#08zx\n",