Merge git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

19 files changed, 1287 insertions, 102 deletions

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index ce96c091f01..2fda0b61524 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -80,6 +80,23 @@ config MTD_NAND_OMAP2
 	help
           Support for NAND flash on Texas Instruments OMAP2 and OMAP3 platforms.
 
+config MTD_NAND_OMAP_PREFETCH
+	bool "GPMC prefetch support for NAND Flash device"
+	depends on MTD_NAND && MTD_NAND_OMAP2
+	default y
+	help
+	 The NAND device can be accessed for Read/Write using GPMC PREFETCH engine
+	 to improve the performance.
+
+config MTD_NAND_OMAP_PREFETCH_DMA
+	depends on MTD_NAND_OMAP_PREFETCH
+	bool "DMA mode"
+	default n
+	help
+	 The GPMC PREFETCH engine can be configured eigther in MPU interrupt mode
+	 or in DMA interrupt mode.
+	 Say y for DMA mode or MPU mode will be used
+
 config MTD_NAND_TS7250
 	tristate "NAND Flash device on TS-7250 board"
 	depends on MACH_TS72XX
@@ -426,6 +443,12 @@ config MTD_NAND_MXC
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
 
+config MTD_NAND_NOMADIK
+	tristate "ST Nomadik 8815 NAND support"
+	depends on ARCH_NOMADIK
+	help
+	  Driver for the NAND flash controller on the Nomadik, with ECC.
+
 config MTD_NAND_SH_FLCTL
 	tristate "Support for NAND on Renesas SuperH FLCTL"
 	depends on MTD_NAND && SUPERH && CPU_SUBTYPE_SH7723
@@ -452,4 +475,11 @@ config MTD_NAND_SOCRATES
 	help
 	  Enables support for NAND Flash chips wired onto Socrates board.
 
+config MTD_NAND_W90P910
+	tristate "Support for NAND on w90p910 evaluation board."
+	depends on ARCH_W90X900 && MTD_PARTITIONS
+	help
+	  This enables the driver for the NAND Flash on evaluation board based
+	  on w90p910.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index f3a786b3cff..6950d3dabf1 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -40,5 +40,7 @@ obj-$(CONFIG_MTD_NAND_SH_FLCTL)		+= sh_flctl.o
 obj-$(CONFIG_MTD_NAND_MXC)		+= mxc_nand.o
 obj-$(CONFIG_MTD_NAND_SOCRATES)		+= socrates_nand.o
 obj-$(CONFIG_MTD_NAND_TXX9NDFMC)	+= txx9ndfmc.o
+obj-$(CONFIG_MTD_NAND_W90P910)		+= w90p910_nand.o
+obj-$(CONFIG_MTD_NAND_NOMADIK)		+= nomadik_nand.o
 
 nand-objs := nand_base.o nand_bbt.o
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 20c828ba940..f8e9975c86e 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -218,7 +218,7 @@ static int atmel_nand_calculate(struct mtd_info *mtd,
  * buf:        buffer to store read data
  */
 static int atmel_nand_read_page(struct mtd_info *mtd,
-		struct nand_chip *chip, uint8_t *buf)
+		struct nand_chip *chip, uint8_t *buf, int page)
 {
 	int eccsize = chip->ecc.size;
 	int eccbytes = chip->ecc.bytes;
diff --git a/drivers/mtd/nand/cafe_nand.c b/drivers/mtd/nand/cafe_nand.c
index 29acd06b1c3..c828d9ac7bd 100644
--- a/drivers/mtd/nand/cafe_nand.c
+++ b/drivers/mtd/nand/cafe_nand.c
@@ -381,7 +381,7 @@ static int cafe_nand_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
  * we need a special oob layout and handling.
  */
 static int cafe_nand_read_page(struct mtd_info *mtd, struct nand_chip *chip,
-			       uint8_t *buf)
+			       uint8_t *buf, int page)
 {
 	struct cafe_priv *cafe = mtd->priv;
 
@@ -903,12 +903,12 @@ static struct pci_driver cafe_nand_pci_driver = {
 	.resume = cafe_nand_resume,
 };
 
-static int cafe_nand_init(void)
+static int __init cafe_nand_init(void)
 {
 	return pci_register_driver(&cafe_nand_pci_driver);
 }
 
-static void cafe_nand_exit(void)
+static void __exit cafe_nand_exit(void)
 {
 	pci_unregister_driver(&cafe_nand_pci_driver);
 }
diff --git a/drivers/mtd/nand/cmx270_nand.c b/drivers/mtd/nand/cmx270_nand.c
index 10081e656a6..826cacffcef 100644
--- a/drivers/mtd/nand/cmx270_nand.c
+++ b/drivers/mtd/nand/cmx270_nand.c
@@ -147,7 +147,7 @@ static int cmx270_device_ready(struct mtd_info *mtd)
 /*
  * Main initialization routine
  */
-static int cmx270_init(void)
+static int __init cmx270_init(void)
 {
 	struct nand_chip *this;
 	const char *part_type;
@@ -261,7 +261,7 @@ module_init(cmx270_init);
 /*
  * Clean up routine
  */
-static void cmx270_cleanup(void)
+static void __exit cmx270_cleanup(void)
 {
 	/* Release resources, unregister device */
 	nand_release(cmx270_nand_mtd);
diff --git a/drivers/mtd/nand/davinci_nand.c b/drivers/mtd/nand/davinci_nand.c
index 0fad6487e6f..f13f5b9afaf 100644
--- a/drivers/mtd/nand/davinci_nand.c
+++ b/drivers/mtd/nand/davinci_nand.c
@@ -348,6 +348,12 @@ compare:
 	if (!(syndrome[0] | syndrome[1] | syndrome[2] | syndrome[3]))
 		return 0;
 
+	/*
+	 * Clear any previous address calculation by doing a dummy read of an
+	 * error address register.
+	 */
+	davinci_nand_readl(info, NAND_ERR_ADD1_OFFSET);
+
 	/* Start address calculation, and wait for it to complete.
 	 * We _could_ start reading more data while this is working,
 	 * to speed up the overall page read.
@@ -359,8 +365,10 @@ compare:
 
 		switch ((fsr >> 8) & 0x0f) {
 		case 0:		/* no error, should not happen */
+			davinci_nand_readl(info, NAND_ERR_ERRVAL1_OFFSET);
 			return 0;
 		case 1:		/* five or more errors detected */
+			davinci_nand_readl(info, NAND_ERR_ERRVAL1_OFFSET);
 			return -EIO;
 		case 2:		/* error addresses computed */
 		case 3:
@@ -500,6 +508,26 @@ static struct nand_ecclayout hwecc4_small __initconst = {
 	},
 };
 
+/* An ECC layout for using 4-bit ECC with large-page (2048bytes) flash,
+ * storing ten ECC bytes plus the manufacturer's bad block marker byte,
+ * and not overlapping the default BBT markers.
+ */
+static struct nand_ecclayout hwecc4_2048 __initconst = {
+	.eccbytes = 40,
+	.eccpos = {
+		/* at the end of spare sector */
+		24, 25, 26, 27, 28, 29,	30, 31, 32, 33,
+		34, 35, 36, 37, 38, 39,	40, 41, 42, 43,
+		44, 45, 46, 47, 48, 49, 50, 51, 52, 53,
+		54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+		},
+	.oobfree = {
+		/* 2 bytes at offset 0 hold manufacturer badblock markers */
+		{.offset = 2, .length = 22, },
+		/* 5 bytes at offset 8 hold BBT markers */
+		/* 8 bytes at offset 16 hold JFFS2 clean markers */
+	},
+};
 
 static int __init nand_davinci_probe(struct platform_device *pdev)
 {
@@ -690,15 +718,20 @@ static int __init nand_davinci_probe(struct platform_device *pdev)
 				info->mtd.oobsize - 16;
 			goto syndrome_done;
 		}
+		if (chunks == 4) {
+			info->ecclayout = hwecc4_2048;
+			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
+			goto syndrome_done;
+		}
 
-		/* For large page chips we'll be wanting to use a
-		 * not-yet-implemented mode that reads OOB data
-		 * before reading the body of the page, to avoid
-		 * the "infix OOB" model of NAND_ECC_HW_SYNDROME
-		 * (and preserve manufacturer badblock markings).
+		/* 4KiB page chips are not yet supported. The eccpos from
+		 * nand_ecclayout cannot hold 80 bytes and change to eccpos[]
+		 * breaks userspace ioctl interface with mtd-utils. Once we
+		 * resolve this issue, NAND_ECC_HW_OOB_FIRST mode can be used
+		 * for the 4KiB page chips.
 		 */
 		dev_warn(&pdev->dev, "no 4-bit ECC support yet "
-				"for large page NAND\n");
+				"for 4KiB-page NAND\n");
 		ret = -EIO;
 		goto err_scan;
 
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 1f6eb257871..ddd37d2554e 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -739,7 +739,8 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 
 static int fsl_elbc_read_page(struct mtd_info *mtd,
                               struct nand_chip *chip,
-                              uint8_t *buf)
+			      uint8_t *buf,
+			      int page)
 {
 	fsl_elbc_read_buf(mtd, buf, mtd->writesize);
 	fsl_elbc_read_buf(mtd, chip->oob_poi, mtd->oobsize);
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index 76beea40d2c..65b26d5a5c0 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -857,6 +857,17 @@ static void mxc_nand_command(struct mtd_info *mtd, unsigned command,
 	}
 }
 
+/* Define some generic bad / good block scan pattern which are used
+ * while scanning a device for factory marked good / bad blocks. */
+static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
+
+static struct nand_bbt_descr smallpage_memorybased = {
+	.options = NAND_BBT_SCAN2NDPAGE,
+	.offs = 5,
+	.len = 1,
+	.pattern = scan_ff_pattern
+};
+
 static int __init mxcnd_probe(struct platform_device *pdev)
 {
 	struct nand_chip *this;
@@ -973,7 +984,10 @@ static int __init mxcnd_probe(struct platform_device *pdev)
 		goto escan;
 	}
 
-	host->pagesize_2k = (mtd->writesize == 2048) ? 1 : 0;
+	if (mtd->writesize == 2048) {
+		host->pagesize_2k = 1;
+		this->badblock_pattern = &smallpage_memorybased;
+	}
 
 	if (this->ecc.mode == NAND_ECC_HW) {
 		switch (mtd->oobsize) {
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 8c21b89d2d0..2957cc70da3 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -688,8 +688,7 @@ nand_get_device(struct nand_chip *chip, struct mtd_info *mtd, int new_state)
  retry:
 	spin_lock(lock);
 
-	/* Hardware controller shared among independend devices */
-	/* Hardware controller shared among independend devices */
+	/* Hardware controller shared among independent devices */
 	if (!chip->controller->active)
 		chip->controller->active = chip;
 
@@ -762,11 +761,12 @@ static int nand_wait(struct mtd_info *mtd, struct nand_chip *chip)
  * @mtd:	mtd info structure
  * @chip:	nand chip info structure
  * @buf:	buffer to store read data
+ * @page:	page number to read
  *
  * 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)
+			      uint8_t *buf, int page)
 {
 	chip->read_buf(mtd, buf, mtd->writesize);
 	chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
@@ -778,11 +778,12 @@ static int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
  * @mtd:	mtd info structure
  * @chip:	nand chip info structure
  * @buf:	buffer to store read data
+ * @page:	page number to read
  *
  * We need a special oob layout and handling even when OOB isn't used.
  */
 static int nand_read_page_raw_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
-			      uint8_t *buf)
+			      uint8_t *buf, int page)
 {
 	int eccsize = chip->ecc.size;
 	int eccbytes = chip->ecc.bytes;
@@ -819,9 +820,10 @@ static int nand_read_page_raw_syndrome(struct mtd_info *mtd, struct nand_chip *c
  * @mtd:	mtd info structure
  * @chip:	nand chip info structure
  * @buf:	buffer to store read data
+ * @page:	page number to read
  */
 static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
-				uint8_t *buf)
+				uint8_t *buf, int page)
 {
 	int i, eccsize = chip->ecc.size;
 	int eccbytes = chip->ecc.bytes;
@@ -831,7 +833,7 @@ static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
 	uint8_t *ecc_code = chip->buffers->ecccode;
 	uint32_t *eccpos = chip->ecc.layout->eccpos;
 
-	chip->ecc.read_page_raw(mtd, chip, buf);
+	chip->ecc.read_page_raw(mtd, chip, buf, page);
 
 	for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize)
 		chip->ecc.calculate(mtd, p, &ecc_calc[i]);
@@ -940,11 +942,12 @@ static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip, uint3
  * @mtd:	mtd info structure
  * @chip:	nand chip info structure
  * @buf:	buffer to store read data
+ * @page:	page number to read
  *
  * Not for syndrome calculating ecc controllers which need a special oob layout
  */
 static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
-				uint8_t *buf)
+				uint8_t *buf, int page)
 {
 	int i, eccsize = chip->ecc.size;
 	int eccbytes = chip->ecc.bytes;
@@ -980,16 +983,66 @@ static int nand_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 }
 
 /**
+ * nand_read_page_hwecc_oob_first - [REPLACABLE] hw ecc, read oob first
+ * @mtd:	mtd info structure
+ * @chip:	nand chip info structure
+ * @buf:	buffer to store read data
+ * @page:	page number to read
+ *
+ * Hardware ECC for large page chips, require OOB to be read first.
+ * For this ECC mode, the write_page method is re-used from ECC_HW.
+ * These methods read/write ECC from the OOB area, unlike the
+ * ECC_HW_SYNDROME support with multiple ECC steps, follows the
+ * "infix ECC" scheme and reads/writes ECC from the data area, by
+ * overwriting the NAND manufacturer bad block markings.
+ */
+static int nand_read_page_hwecc_oob_first(struct mtd_info *mtd,
+	struct nand_chip *chip, uint8_t *buf, int page)
+{
+	int i, eccsize = chip->ecc.size;
+	int eccbytes = chip->ecc.bytes;
+	int eccsteps = chip->ecc.steps;
+	uint8_t *p = buf;
+	uint8_t *ecc_code = chip->buffers->ecccode;
+	uint32_t *eccpos = chip->ecc.layout->eccpos;
+	uint8_t *ecc_calc = chip->buffers->ecccalc;
+
+	/* Read the OOB area first */
+	chip->cmdfunc(mtd, NAND_CMD_READOOB, 0, page);
+	chip->read_buf(mtd, chip->oob_poi, mtd->oobsize);
+	chip->cmdfunc(mtd, NAND_CMD_READ0, 0, page);
+
+	for (i = 0; i < chip->ecc.total; i++)
+		ecc_code[i] = chip->oob_poi[eccpos[i]];
+
+	for (i = 0; eccsteps; eccsteps--, i += eccbytes, p += eccsize) {
+		int stat;
+
+		chip->ecc.hwctl(mtd, NAND_ECC_READ);
+		chip->read_buf(mtd, p, eccsize);
+		chip->ecc.calculate(mtd, p, &ecc_calc[i]);
+
+		stat = chip->ecc.correct(mtd, p, &ecc_code[i], NULL);
+		if (stat < 0)
+			mtd->ecc_stats.failed++;
+		else
+			mtd->ecc_stats.corrected += stat;
+	}
+	return 0;
+}
+
+/**
  * nand_read_page_syndrome - [REPLACABLE] hardware ecc syndrom based page read
  * @mtd:	mtd info structure
  * @chip:	nand chip info structure
  * @buf:	buffer to store read data
+ * @page:	page number to read
  *
  * The hw generator calculates the error syndrome automatically. Therefor
  * we need a special oob layout and handling.
  */
 static int nand_read_page_syndrome(struct mtd_info *mtd, struct nand_chip *chip,
-				   uint8_t *buf)
+				   uint8_t *buf, int page)
 {
 	int i, eccsize = chip->ecc.size;
 	int eccbytes = chip->ecc.bytes;
@@ -1131,11 +1184,13 @@ static int nand_do_read_ops(struct mtd_info *mtd, loff_t from,
 
 			/* Now read the page into the buffer */
 			if (unlikely(ops->mode == MTD_OOB_RAW))
-				ret = chip->ecc.read_page_raw(mtd, chip, bufpoi);
+				ret = chip->ecc.read_page_raw(mtd, chip,
+							      bufpoi, page);
 			else if (!aligned && NAND_SUBPAGE_READ(chip) && !oob)
 				ret = chip->ecc.read_subpage(mtd, chip, col, bytes, bufpoi);
 			else
-				ret = chip->ecc.read_page(mtd, chip, bufpoi);
+				ret = chip->ecc.read_page(mtd, chip, bufpoi,
+							  page);
 			if (ret < 0)
 				break;
 
@@ -1413,8 +1468,8 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from,
 	int len;
 	uint8_t *buf = ops->oobbuf;
 
-	DEBUG(MTD_DEBUG_LEVEL3, "nand_read_oob: from = 0x%08Lx, len = %i\n",
-	      (unsigned long long)from, readlen);
+	DEBUG(MTD_DEBUG_LEVEL3, "%s: from = 0x%08Lx, len = %i\n",
+			__func__, (unsigned long long)from, readlen);
 
 	if (ops->mode == MTD_OOB_AUTO)
 		len = chip->ecc.layout->oobavail;
@@ -1422,8 +1477,8 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from,
 		len = mtd->oobsize;
 
 	if (unlikely(ops->ooboffs >= len)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_read_oob: "
-			"Attempt to start read outside oob\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt to start read "
+					"outside oob\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1431,8 +1486,8 @@ static int nand_do_read_oob(struct mtd_info *mtd, loff_t from,
 	if (unlikely(from >= mtd->size ||
 		     ops->ooboffs + readlen > ((mtd->size >> chip->page_shift) -
 					(from >> chip->page_shift)) * len)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_read_oob: "
-			"Attempt read beyond end of device\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt read beyond end "
+					"of device\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1506,8 +1561,8 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
 
 	/* Do not allow reads past end of device */
 	if (ops->datbuf && (from + ops->len) > mtd->size) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_read_oob: "
-		      "Attempt read beyond end of device\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt read "
+				"beyond end of device\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1816,8 +1871,8 @@ static int nand_do_write_ops(struct mtd_info *mtd, loff_t to,
 
 	/* reject writes, which are not page aligned */
 	if (NOTALIGNED(to) || NOTALIGNED(ops->len)) {
-		printk(KERN_NOTICE "nand_write: "
-		       "Attempt to write not page aligned data\n");
+		printk(KERN_NOTICE "%s: Attempt to write not "
+				"page aligned data\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1944,8 +1999,8 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
 	int chipnr, page, status, len;
 	struct nand_chip *chip = mtd->priv;
 
-	DEBUG(MTD_DEBUG_LEVEL3, "nand_write_oob: to = 0x%08x, len = %i\n",
-	      (unsigned int)to, (int)ops->ooblen);
+	DEBUG(MTD_DEBUG_LEVEL3, "%s: to = 0x%08x, len = %i\n",
+			 __func__, (unsigned int)to, (int)ops->ooblen);
 
 	if (ops->mode == MTD_OOB_AUTO)
 		len = chip->ecc.layout->oobavail;
@@ -1954,14 +2009,14 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
 
 	/* Do not allow write past end of page */
 	if ((ops->ooboffs + ops->ooblen) > len) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_write_oob: "
-		      "Attempt to write past end of page\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt to write "
+				"past end of page\n", __func__);
 		return -EINVAL;
 	}
 
 	if (unlikely(ops->ooboffs >= len)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_do_write_oob: "
-			"Attempt to start write outside oob\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt to start "
+				"write outside oob\n", __func__);
 		return -EINVAL;
 	}
 
@@ -1970,8 +2025,8 @@ static int nand_do_write_oob(struct mtd_info *mtd, loff_t to,
 		     ops->ooboffs + ops->ooblen >
 			((mtd->size >> chip->page_shift) -
 			 (to >> chip->page_shift)) * len)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_do_write_oob: "
-			"Attempt write beyond end of device\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt write beyond "
+				"end of device\n", __func__);
 		return -EINVAL;
 	}
 
@@ -2026,8 +2081,8 @@ static int nand_write_oob(struct mtd_info *mtd, loff_t to,
 
 	/* Do not allow writes past end of device */
 	if (ops->datbuf && (to + ops->len) > mtd->size) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_write_oob: "
-		      "Attempt write beyond end of device\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Attempt write beyond "
+				"end of device\n", __func__);
 		return -EINVAL;
 	}
 
@@ -2117,26 +2172,27 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 	unsigned int bbt_masked_page = 0xffffffff;
 	loff_t len;
 
-	DEBUG(MTD_DEBUG_LEVEL3, "nand_erase: start = 0x%012llx, len = %llu\n",
-	      (unsigned long long)instr->addr, (unsigned long long)instr->len);
+	DEBUG(MTD_DEBUG_LEVEL3, "%s: start = 0x%012llx, len = %llu\n",
+				__func__, (unsigned long long)instr->addr,
+				(unsigned long long)instr->len);
 
 	/* Start address must align on block boundary */
 	if (instr->addr & ((1 << chip->phys_erase_shift) - 1)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_erase: Unaligned address\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Unaligned address\n", __func__);
 		return -EINVAL;
 	}
 
 	/* Length must align on block boundary */
 	if (instr->len & ((1 << chip->phys_erase_shift) - 1)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_erase: "
-		      "Length not block aligned\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Length not block aligned\n",
+					__func__);
 		return -EINVAL;
 	}
 
 	/* Do not allow erase past end of device */
 	if ((instr->len + instr->addr) > mtd->size) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_erase: "
-		      "Erase past end of device\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Erase past end of device\n",
+					__func__);
 		return -EINVAL;
 	}
 
@@ -2157,8 +2213,8 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 
 	/* Check, if it is write protected */
 	if (nand_check_wp(mtd)) {
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_erase: "
-		      "Device is write protected!!!\n");
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: Device is write protected!!!\n",
+					__func__);
 		instr->state = MTD_ERASE_FAILED;
 		goto erase_exit;
 	}
@@ -2183,8 +2239,8 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		 */
 		if (nand_block_checkbad(mtd, ((loff_t) page) <<
 					chip->page_shift, 0, allowbbt)) {
-			printk(KERN_WARNING "nand_erase: attempt to erase a "
-			       "bad block at page 0x%08x\n", page);
+			printk(KERN_WARNING "%s: attempt to erase a bad block "
+					"at page 0x%08x\n", __func__, page);
 			instr->state = MTD_ERASE_FAILED;
 			goto erase_exit;
 		}
@@ -2211,8 +2267,8 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 
 		/* See if block erase succeeded */
 		if (status & NAND_STATUS_FAIL) {
-			DEBUG(MTD_DEBUG_LEVEL0, "nand_erase: "
-			      "Failed erase, page 0x%08x\n", page);
+			DEBUG(MTD_DEBUG_LEVEL0, "%s: Failed erase, "
+					"page 0x%08x\n", __func__, page);
 			instr->state = MTD_ERASE_FAILED;
 			instr->fail_addr =
 				((loff_t)page << chip->page_shift);
@@ -2272,9 +2328,9 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		if (!rewrite_bbt[chipnr])
 			continue;
 		/* update the BBT for chip */
-		DEBUG(MTD_DEBUG_LEVEL0, "nand_erase_nand: nand_update_bbt "
-		      "(%d:0x%0llx 0x%0x)\n", chipnr, rewrite_bbt[chipnr],
-		      chip->bbt_td->pages[chipnr]);
+		DEBUG(MTD_DEBUG_LEVEL0, "%s: nand_update_bbt "
+			"(%d:0x%0llx 0x%0x)\n", __func__, chipnr,
+			rewrite_bbt[chipnr], chip->bbt_td->pages[chipnr]);
 		nand_update_bbt(mtd, rewrite_bbt[chipnr]);
 	}
 
@@ -2292,7 +2348,7 @@ static void nand_sync(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd->priv;
 
-	DEBUG(MTD_DEBUG_LEVEL3, "nand_sync: called\n");
+	DEBUG(MTD_DEBUG_LEVEL3, "%s: called\n", __func__);
 
 	/* Grab the lock and see if the device is available */
 	nand_get_device(chip, mtd, FL_SYNCING);
@@ -2356,8 +2412,8 @@ static void nand_resume(struct mtd_info *mtd)
 	if (chip->state == FL_PM_SUSPENDED)
 		nand_release_device(mtd);
 	else
-		printk(KERN_ERR "nand_resume() called for a chip which is not "
-		       "in suspended state\n");
+		printk(KERN_ERR "%s called for a chip which is not "
+		       "in suspended state\n", __func__);
 }
 
 /*
@@ -2671,6 +2727,17 @@ int nand_scan_tail(struct mtd_info *mtd)
 	 */
 
 	switch (chip->ecc.mode) {
+	case NAND_ECC_HW_OOB_FIRST:
+		/* Similar to NAND_ECC_HW, but a separate read_page handle */
+		if (!chip->ecc.calculate || !chip->ecc.correct ||
+		     !chip->ecc.hwctl) {
+			printk(KERN_WARNING "No ECC functions supplied; "
+			       "Hardware ECC not possible\n");
+			BUG();
+		}
+		if (!chip->ecc.read_page)
+			chip->ecc.read_page = nand_read_page_hwecc_oob_first;
+
 	case NAND_ECC_HW:
 		/* Use standard hwecc read page function ? */
 		if (!chip->ecc.read_page)
@@ -2693,7 +2760,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		     chip->ecc.read_page == nand_read_page_hwecc ||
 		     !chip->ecc.write_page ||
 		     chip->ecc.write_page == nand_write_page_hwecc)) {
-			printk(KERN_WARNING "No ECC functions supplied, "
+			printk(KERN_WARNING "No ECC functions supplied; "
 			       "Hardware ECC not possible\n");
 			BUG();
 		}
@@ -2728,7 +2795,8 @@ int nand_scan_tail(struct mtd_info *mtd)
 		chip->ecc.write_page_raw = nand_write_page_raw;
 		chip->ecc.read_oob = nand_read_oob_std;
 		chip->ecc.write_oob = nand_write_oob_std;
-		chip->ecc.size = 256;
+		if (!chip->ecc.size)
+			chip->ecc.size = 256;
 		chip->ecc.bytes = 3;
 		break;
 
@@ -2858,7 +2926,8 @@ int nand_scan(struct mtd_info *mtd, int maxchips)
 
 	/* Many callers got this wrong, so check for it for a while... */
 	if (!mtd->owner && caller_is_module()) {
-		printk(KERN_CRIT "nand_scan() called with NULL mtd->owner!\n");
+		printk(KERN_CRIT "%s called with NULL mtd->owner!\n",
+				__func__);
 		BUG();
 	}
 
diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c
index c0cb87d6d16..db7ae9d6a29 100644
--- a/drivers/mtd/nand/nand_ecc.c
+++ b/drivers/mtd/nand/nand_ecc.c
@@ -417,22 +417,22 @@ int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf,
 EXPORT_SYMBOL(nand_calculate_ecc);
 
 /**
- * nand_correct_data - [NAND Interface] Detect and correct bit error(s)
- * @mtd:	MTD block structure
+ * __nand_correct_data - [NAND Interface] Detect and correct bit error(s)
  * @buf:	raw data read from the chip
  * @read_ecc:	ECC from the chip
  * @calc_ecc:	the ECC calculated from raw data
+ * @eccsize:	data bytes per ecc step (256 or 512)
  *
- * Detect and correct a 1 bit error for 256/512 byte block
+ * Detect and correct a 1 bit error for eccsize byte block
  */
-int nand_correct_data(struct mtd_info *mtd, unsigned char *buf,
-		      unsigned char *read_ecc, unsigned char *calc_ecc)
+int __nand_correct_data(unsigned char *buf,
+			unsigned char *read_ecc, unsigned char *calc_ecc,
+			unsigned int eccsize)
 {
 	unsigned char b0, b1, b2, bit_addr;
 	unsigned int byte_addr;
 	/* 256 or 512 bytes/ecc  */
-	const uint32_t eccsize_mult =
-			(((struct nand_chip *)mtd->priv)->ecc.size) >> 8;
+	const uint32_t eccsize_mult = eccsize >> 8;
 
 	/*
 	 * b0 to b2 indicate which bit is faulty (if any)
@@ -495,6 +495,23 @@ int nand_correct_data(struct mtd_info *mtd, unsigned char *buf,
 	printk(KERN_ERR "uncorrectable error : ");
 	return -1;
 }
+EXPORT_SYMBOL(__nand_correct_data);
+
+/**
+ * nand_correct_data - [NAND Interface] Detect and correct bit error(s)
+ * @mtd:	MTD block structure
+ * @buf:	raw data read from the chip
+ * @read_ecc:	ECC from the chip
+ * @calc_ecc:	the ECC calculated from raw data
+ *
+ * Detect and correct a 1 bit error for 256/512 byte block
+ */
+int nand_correct_data(struct mtd_info *mtd, unsigned char *buf,
+		      unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	return __nand_correct_data(buf, read_ecc, calc_ecc,
+				   ((struct nand_chip *)mtd->priv)->ecc.size);
+}
 EXPORT_SYMBOL(nand_correct_data);
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c
index 89bf85af642..40b5658bdbe 100644
--- a/drivers/mtd/nand/ndfc.c
+++ b/drivers/mtd/nand/ndfc.c
@@ -102,8 +102,8 @@ static int ndfc_calculate_ecc(struct mtd_info *mtd,
 	wmb();
 	ecc = in_be32(ndfc->ndfcbase + NDFC_ECC);
 	/* The NDFC uses Smart Media (SMC) bytes order */
-	ecc_code[0] = p[2];
-	ecc_code[1] = p[1];
+	ecc_code[0] = p[1];
+	ecc_code[1] = p[2];
 	ecc_code[2] = p[3];
 
 	return 0;
diff --git a/drivers/mtd/nand/nomadik_nand.c b/drivers/mtd/nand/nomadik_nand.c
new file mode 100644
index 00000000000..7c302d55910
--- /dev/null
+++ b/drivers/mtd/nand/nomadik_nand.c
@@ -0,0 +1,250 @@
+/*
+ *  drivers/mtd/nand/nomadik_nand.c
+ *
+ *  Overview:
+ *  	Driver for on-board NAND flash on Nomadik Platforms
+ *
+ * Copyright © 2007 STMicroelectronics Pvt. Ltd.
+ * Author: Sachin Verma <sachin.verma@st.com>
+ *
+ * Copyright © 2009 Alessandro Rubini
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/nand_ecc.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/partitions.h>
+#include <linux/io.h>
+#include <mach/nand.h>
+#include <mach/fsmc.h>
+
+#include <mtd/mtd-abi.h>
+
+struct nomadik_nand_host {
+	struct mtd_info		mtd;
+	struct nand_chip	nand;
+	void __iomem *data_va;
+	void __iomem *cmd_va;
+	void __iomem *addr_va;
+	struct nand_bbt_descr *bbt_desc;
+};
+
+static struct nand_ecclayout nomadik_ecc_layout = {
+	.eccbytes = 3 * 4,
+	.eccpos = { /* each subpage has 16 bytes: pos 2,3,4 hosts ECC */
+		0x02, 0x03, 0x04,
+		0x12, 0x13, 0x14,
+		0x22, 0x23, 0x24,
+		0x32, 0x33, 0x34},
+	/* let's keep bytes 5,6,7 for us, just in case we change ECC algo */
+	.oobfree = { {0x08, 0x08}, {0x18, 0x08}, {0x28, 0x08}, {0x38, 0x08} },
+};
+
+static void nomadik_ecc_control(struct mtd_info *mtd, int mode)
+{
+	/* No need to enable hw ecc, it's on by default */
+}
+
+static void nomadik_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
+{
+	struct nand_chip *nand = mtd->priv;
+	struct nomadik_nand_host *host = nand->priv;
+
+	if (cmd == NAND_CMD_NONE)
+		return;
+
+	if (ctrl & NAND_CLE)
+		writeb(cmd, host->cmd_va);
+	else
+		writeb(cmd, host->addr_va);
+}
+
+static int nomadik_nand_probe(struct platform_device *pdev)
+{
+	struct nomadik_nand_platform_data *pdata = pdev->dev.platform_data;
+	struct nomadik_nand_host *host;
+	struct mtd_info *mtd;
+	struct nand_chip *nand;
+	struct resource *res;
+	int ret = 0;
+
+	/* Allocate memory for the device structure (and zero it) */
+	host = kzalloc(sizeof(struct nomadik_nand_host), GFP_KERNEL);
+	if (!host) {
+		dev_err(&pdev->dev, "Failed to allocate device structure.\n");
+		return -ENOMEM;
+	}
+
+	/* Call the client's init function, if any */
+	if (pdata->init)
+		ret = pdata->init();
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Init function failed\n");
+		goto err;
+	}
+
+	/* ioremap three regions */
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_addr");
+	if (!res) {
+		ret = -EIO;
+		goto err_unmap;
+	}
+	host->addr_va = ioremap(res->start, res->end - res->start + 1);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
+	if (!res) {
+		ret = -EIO;
+		goto err_unmap;
+	}
+	host->data_va = ioremap(res->start, res->end - res->start + 1);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_cmd");
+	if (!res) {
+		ret = -EIO;
+		goto err_unmap;
+	}
+	host->cmd_va = ioremap(res->start, res->end - res->start + 1);
+
+	if (!host->addr_va || !host->data_va || !host->cmd_va) {
+		ret = -ENOMEM;
+		goto err_unmap;
+	}
+
+	/* Link all private pointers */
+	mtd = &host->mtd;
+	nand = &host->nand;
+	mtd->priv = nand;
+	nand->priv = host;
+
+	host->mtd.owner = THIS_MODULE;
+	nand->IO_ADDR_R = host->data_va;
+	nand->IO_ADDR_W = host->data_va;
+	nand->cmd_ctrl = nomadik_cmd_ctrl;
+
+	/*
+	 * This stanza declares ECC_HW but uses soft routines. It's because
+	 * HW claims to make the calculation but not the correction. However,
+	 * I haven't managed to get the desired data out of it until now.
+	 */
+	nand->ecc.mode = NAND_ECC_SOFT;
+	nand->ecc.layout = &nomadik_ecc_layout;
+	nand->ecc.hwctl = nomadik_ecc_control;
+	nand->ecc.size = 512;
+	nand->ecc.bytes = 3;
+
+	nand->options = pdata->options;
+
+	/*
+	 * Scan to find existance of the device
+	 */
+	if (nand_scan(&host->mtd, 1)) {
+		ret = -ENXIO;
+		goto err_unmap;
+	}
+
+#ifdef CONFIG_MTD_PARTITIONS
+	add_mtd_partitions(&host->mtd, pdata->parts, pdata->nparts);
+#else
+	pr_info("Registering %s as whole device\n", mtd->name);
+	add_mtd_device(mtd);
+#endif
+
+	platform_set_drvdata(pdev, host);
+	return 0;
+
+ err_unmap:
+	if (host->cmd_va)
+		iounmap(host->cmd_va);
+	if (host->data_va)
+		iounmap(host->data_va);
+	if (host->addr_va)
+		iounmap(host->addr_va);
+ err:
+	kfree(host);
+	return ret;
+}
+
+/*
+ * Clean up routine
+ */
+static int nomadik_nand_remove(struct platform_device *pdev)
+{
+	struct nomadik_nand_host *host = platform_get_drvdata(pdev);
+	struct nomadik_nand_platform_data *pdata = pdev->dev.platform_data;
+
+	if (pdata->exit)
+		pdata->exit();
+
+	if (host) {
+		iounmap(host->cmd_va);
+		iounmap(host->data_va);
+		iounmap(host->addr_va);
+		kfree(host);
+	}
+	return 0;
+}
+
+static int nomadik_nand_suspend(struct device *dev)
+{
+	struct nomadik_nand_host *host = dev_get_drvdata(dev);
+	int ret = 0;
+	if (host)
+		ret = host->mtd.suspend(&host->mtd);
+	return ret;
+}
+
+static int nomadik_nand_resume(struct device *dev)
+{
+	struct nomadik_nand_host *host = dev_get_drvdata(dev);
+	if (host)
+		host->mtd.resume(&host->mtd);
+	return 0;
+}
+
+static struct dev_pm_ops nomadik_nand_pm_ops = {
+	.suspend = nomadik_nand_suspend,
+	.resume = nomadik_nand_resume,
+};
+
+static struct platform_driver nomadik_nand_driver = {
+	.probe = nomadik_nand_probe,
+	.remove = nomadik_nand_remove,
+	.driver = {
+		.owner = THIS_MODULE,
+		.name = "nomadik_nand",
+		.pm = &nomadik_nand_pm_ops,
+	},
+};
+
+static int __init nand_nomadik_init(void)
+{
+	pr_info("Nomadik NAND driver\n");
+	return platform_driver_register(&nomadik_nand_driver);
+}
+
+static void __exit nand_nomadik_exit(void)
+{
+	platform_driver_unregister(&nomadik_nand_driver);
+}
+
+module_init(nand_nomadik_init);
+module_exit(nand_nomadik_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("ST Microelectronics (sachin.verma@st.com)");
+MODULE_DESCRIPTION("NAND driver for Nomadik Platform");
diff --git a/drivers/mtd/nand/omap2.c b/drivers/mtd/nand/omap2.c
index ebd07e95b81..090ab87086b 100644
--- a/drivers/mtd/nand/omap2.c
+++ b/drivers/mtd/nand/omap2.c
@@ -18,8 +18,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
 
-#include <asm/dma.h>
-
+#include <mach/dma.h>
 #include <mach/gpmc.h>
 #include <mach/nand.h>
 
@@ -112,6 +111,27 @@
 static const char *part_probes[] = { "cmdlinepart", NULL };
 #endif
 
+#ifdef CONFIG_MTD_NAND_OMAP_PREFETCH
+static int use_prefetch = 1;
+
+/* "modprobe ... use_prefetch=0" etc */
+module_param(use_prefetch, bool, 0);
+MODULE_PARM_DESC(use_prefetch, "enable/disable use of PREFETCH");
+
+#ifdef CONFIG_MTD_NAND_OMAP_PREFETCH_DMA
+static int use_dma = 1;
+
+/* "modprobe ... use_dma=0" etc */
+module_param(use_dma, bool, 0);
+MODULE_PARM_DESC(use_dma, "enable/disable use of DMA");
+#else
+const int use_dma;
+#endif
+#else
+const int use_prefetch;
+const int use_dma;
+#endif
+
 struct omap_nand_info {
 	struct nand_hw_control		controller;
 	struct omap_nand_platform_data	*pdata;
@@ -124,6 +144,9 @@ struct omap_nand_info {
 	unsigned long			phys_base;
 	void __iomem			*gpmc_cs_baseaddr;
 	void __iomem			*gpmc_baseaddr;
+	void __iomem			*nand_pref_fifo_add;
+	struct completion		comp;
+	int				dma_ch;
 };
 
 /**
@@ -189,6 +212,38 @@ static void omap_hwcontrol(struct mtd_info *mtd, int cmd, unsigned int ctrl)
 }
 
 /**
+ * omap_read_buf8 - read data from NAND controller into buffer
+ * @mtd: MTD device structure
+ * @buf: buffer to store date
+ * @len: number of bytes to read
+ */
+static void omap_read_buf8(struct mtd_info *mtd, u_char *buf, int len)
+{
+	struct nand_chip *nand = mtd->priv;
+
+	ioread8_rep(nand->IO_ADDR_R, buf, len);
+}
+
+/**
+ * omap_write_buf8 - write buffer to NAND controller
+ * @mtd: MTD device structure
+ * @buf: data buffer
+ * @len: number of bytes to write
+ */
+static void omap_write_buf8(struct mtd_info *mtd, const u_char *buf, int len)
+{
+	struct omap_nand_info *info = container_of(mtd,
+						struct omap_nand_info, mtd);
+	u_char *p = (u_char *)buf;
+
+	while (len--) {
+		iowrite8(*p++, info->nand.IO_ADDR_W);
+		while (GPMC_BUF_EMPTY == (readl(info->gpmc_baseaddr +
+						GPMC_STATUS) & GPMC_BUF_FULL));
+	}
+}
+
+/**
  * omap_read_buf16 - read data from NAND controller into buffer
  * @mtd: MTD device structure
  * @buf: buffer to store date
@@ -198,7 +253,7 @@ static void omap_read_buf16(struct mtd_info *mtd, u_char *buf, int len)
 {
 	struct nand_chip *nand = mtd->priv;
 
-	__raw_readsw(nand->IO_ADDR_R, buf, len / 2);
+	ioread16_rep(nand->IO_ADDR_R, buf, len / 2);
 }
 
 /**
@@ -217,13 +272,242 @@ static void omap_write_buf16(struct mtd_info *mtd, const u_char * buf, int len)
 	len >>= 1;
 
 	while (len--) {
-		writew(*p++, info->nand.IO_ADDR_W);
+		iowrite16(*p++, info->nand.IO_ADDR_W);
 
 		while (GPMC_BUF_EMPTY == (readl(info->gpmc_baseaddr +
 						GPMC_STATUS) & GPMC_BUF_FULL))
 			;
 	}
 }
+
+/**
+ * omap_read_buf_pref - read data from NAND controller into buffer
+ * @mtd: MTD device structure
+ * @buf: buffer to store date
+ * @len: number of bytes to read
+ */
+static void omap_read_buf_pref(struct mtd_info *mtd, u_char *buf, int len)
+{
+	struct omap_nand_info *info = container_of(mtd,
+						struct omap_nand_info, mtd);
+	uint32_t pfpw_status = 0, r_count = 0;
+	int ret = 0;
+	u32 *p = (u32 *)buf;
+
+	/* take care of subpage reads */
+	for (; len % 4 != 0; ) {
+		*buf++ = __raw_readb(info->nand.IO_ADDR_R);
+		len--;
+	}
+	p = (u32 *) buf;
+
+	/* configure and start prefetch transfer */
+	ret = gpmc_prefetch_enable(info->gpmc_cs, 0x0, len, 0x0);
+	if (ret) {
+		/* PFPW engine is busy, use cpu copy method */
+		if (info->nand.options & NAND_BUSWIDTH_16)
+			omap_read_buf16(mtd, buf, len);
+		else
+			omap_read_buf8(mtd, buf, len);
+	} else {
+		do {
+			pfpw_status = gpmc_prefetch_status();
+			r_count = ((pfpw_status >> 24) & 0x7F) >> 2;
+			ioread32_rep(info->nand_pref_fifo_add, p, r_count);
+			p += r_count;
+			len -= r_count << 2;
+		} while (len);
+
+		/* disable and stop the PFPW engine */
+		gpmc_prefetch_reset();
+	}
+}
+
+/**
+ * omap_write_buf_pref - write buffer to NAND controller
+ * @mtd: MTD device structure
+ * @buf: data buffer
+ * @len: number of bytes to write
+ */
+static void omap_write_buf_pref(struct mtd_info *mtd,
+					const u_char *buf, int len)
+{
+	struct omap_nand_info *info = container_of(mtd,
+						struct omap_nand_info, mtd);
+	uint32_t pfpw_status = 0, w_count = 0;
+	int i = 0, ret = 0;
+	u16 *p = (u16 *) buf;
+
+	/* take care of subpage writes */
+	if (len % 2 != 0) {
+		writeb(*buf, info->nand.IO_ADDR_R);
+		p = (u16 *)(buf + 1);
+		len--;
+	}
+
+	/*  configure and start prefetch transfer */
+	ret = gpmc_prefetch_enable(info->gpmc_cs, 0x0, len, 0x1);
+	if (ret) {
+		/* PFPW engine is busy, use cpu copy method */
+		if (info->nand.options & NAND_BUSWIDTH_16)
+			omap_write_buf16(mtd, buf, len);
+		else
+			omap_write_buf8(mtd, buf, len);
+	} else {
+		pfpw_status = gpmc_prefetch_status();
+		while (pfpw_status & 0x3FFF) {
+			w_count = ((pfpw_status >> 24) & 0x7F) >> 1;
+			for (i = 0; (i < w_count) && len; i++, len -= 2)
+				iowrite16(*p++, info->nand_pref_fifo_add);
+			pfpw_status = gpmc_prefetch_status();
+		}
+
+		/* disable and stop the PFPW engine */
+		gpmc_prefetch_reset();
+	}
+}
+
+#ifdef CONFIG_MTD_NAND_OMAP_PREFETCH_DMA
+/*
+ * omap_nand_dma_cb: callback on the completion of dma transfer
+ * @lch: logical channel
+ * @ch_satuts: channel status
+ * @data: pointer to completion data structure
+ */
+static void omap_nand_dma_cb(int lch, u16 ch_status, void *data)
+{
+	complete((struct completion *) data);
+}
+
+/*
+ * omap_nand_dma_transfer: configer and start dma transfer
+ * @mtd: MTD device structure
+ * @addr: virtual address in RAM of source/destination
+ * @len: number of data bytes to be transferred
+ * @is_write: flag for read/write operation
+ */
+static inline int omap_nand_dma_transfer(struct mtd_info *mtd, void *addr,
+					unsigned int len, int is_write)
+{
+	struct omap_nand_info *info = container_of(mtd,
+					struct omap_nand_info, mtd);
+	uint32_t prefetch_status = 0;
+	enum dma_data_direction dir = is_write ? DMA_TO_DEVICE :
+							DMA_FROM_DEVICE;
+	dma_addr_t dma_addr;
+	int ret;
+
+	/* The fifo depth is 64 bytes. We have a sync at each frame and frame
+	 * length is 64 bytes.
+	 */
+	int buf_len = len >> 6;
+
+	if (addr >= high_memory) {
+		struct page *p1;
+
+		if (((size_t)addr & PAGE_MASK) !=
+			((size_t)(addr + len - 1) & PAGE_MASK))
+			goto out_copy;
+		p1 = vmalloc_to_page(addr);
+		if (!p1)
+			goto out_copy;
+		addr = page_address(p1) + ((size_t)addr & ~PAGE_MASK);
+	}
+
+	dma_addr = dma_map_single(&info->pdev->dev, addr, len, dir);
+	if (dma_mapping_error(&info->pdev->dev, dma_addr)) {
+		dev_err(&info->pdev->dev,
+			"Couldn't DMA map a %d byte buffer\n", len);
+		goto out_copy;
+	}
+
+	if (is_write) {
+	    omap_set_dma_dest_params(info->dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
+						info->phys_base, 0, 0);
+	    omap_set_dma_src_params(info->dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
+							dma_addr, 0, 0);
+	    omap_set_dma_transfer_params(info->dma_ch, OMAP_DMA_DATA_TYPE_S32,
+					0x10, buf_len, OMAP_DMA_SYNC_FRAME,
+					OMAP24XX_DMA_GPMC, OMAP_DMA_DST_SYNC);
+	} else {
+	    omap_set_dma_src_params(info->dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
+						info->phys_base, 0, 0);
+	    omap_set_dma_dest_params(info->dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
+							dma_addr, 0, 0);
+	    omap_set_dma_transfer_params(info->dma_ch, OMAP_DMA_DATA_TYPE_S32,
+					0x10, buf_len, OMAP_DMA_SYNC_FRAME,
+					OMAP24XX_DMA_GPMC, OMAP_DMA_SRC_SYNC);
+	}
+	/*  configure and start prefetch transfer */
+	ret = gpmc_prefetch_enable(info->gpmc_cs, 0x1, len, is_write);
+	if (ret)
+		/* PFPW engine is busy, use cpu copy methode */
+		goto out_copy;
+
+	init_completion(&info->comp);
+
+	omap_start_dma(info->dma_ch);
+
+	/* setup and start DMA using dma_addr */
+	wait_for_completion(&info->comp);
+
+	while (0x3fff & (prefetch_status = gpmc_prefetch_status()))
+		;
+	/* disable and stop the PFPW engine */
+	gpmc_prefetch_reset();
+
+	dma_unmap_single(&info->pdev->dev, dma_addr, len, dir);
+	return 0;
+
+out_copy:
+	if (info->nand.options & NAND_BUSWIDTH_16)
+		is_write == 0 ? omap_read_buf16(mtd, (u_char *) addr, len)
+			: omap_write_buf16(mtd, (u_char *) addr, len);
+	else
+		is_write == 0 ? omap_read_buf8(mtd, (u_char *) addr, len)
+			: omap_write_buf8(mtd, (u_char *) addr, len);
+	return 0;
+}
+#else
+static void omap_nand_dma_cb(int lch, u16 ch_status, void *data) {}
+static inline int omap_nand_dma_transfer(struct mtd_info *mtd, void *addr,
+					unsigned int len, int is_write)
+{
+	return 0;
+}
+#endif
+
+/**
+ * omap_read_buf_dma_pref - read data from NAND controller into buffer
+ * @mtd: MTD device structure
+ * @buf: buffer to store date
+ * @len: number of bytes to read
+ */
+static void omap_read_buf_dma_pref(struct mtd_info *mtd, u_char *buf, int len)
+{
+	if (len <= mtd->oobsize)
+		omap_read_buf_pref(mtd, buf, len);
+	else
+		/* start transfer in DMA mode */
+		omap_nand_dma_transfer(mtd, buf, len, 0x0);
+}
+
+/**
+ * omap_write_buf_dma_pref - write buffer to NAND controller
+ * @mtd: MTD device structure
+ * @buf: data buffer
+ * @len: number of bytes to write
+ */
+static void omap_write_buf_dma_pref(struct mtd_info *mtd,
+					const u_char *buf, int len)
+{
+	if (len <= mtd->oobsize)
+		omap_write_buf_pref(mtd, buf, len);
+	else
+		/* start transfer in DMA mode */
+		omap_nand_dma_transfer(mtd, buf, len, 0x1);
+}
+
 /**
  * omap_verify_buf - Verify chip data against buffer
  * @mtd: MTD device structure
@@ -658,17 +942,12 @@ static int __devinit omap_nand_probe(struct platform_device *pdev)
 		err = -ENOMEM;
 		goto out_release_mem_region;
 	}
+
 	info->nand.controller = &info->controller;
 
 	info->nand.IO_ADDR_W = info->nand.IO_ADDR_R;
 	info->nand.cmd_ctrl  = omap_hwcontrol;
 
-	/* REVISIT:  only supports 16-bit NAND flash */
-
-	info->nand.read_buf   = omap_read_buf16;
-	info->nand.write_buf  = omap_write_buf16;
-	info->nand.verify_buf = omap_verify_buf;
-
 	/*
 	 * If RDY/BSY line is connected to OMAP then use the omap ready
 	 * funcrtion and the generic nand_wait function which reads the status
@@ -689,6 +968,40 @@ static int __devinit omap_nand_probe(struct platform_device *pdev)
 								== 0x1000)
 		info->nand.options  |= NAND_BUSWIDTH_16;
 
+	if (use_prefetch) {
+		/* copy the virtual address of nand base for fifo access */
+		info->nand_pref_fifo_add = info->nand.IO_ADDR_R;
+
+		info->nand.read_buf   = omap_read_buf_pref;
+		info->nand.write_buf  = omap_write_buf_pref;
+		if (use_dma) {
+			err = omap_request_dma(OMAP24XX_DMA_GPMC, "NAND",
+				omap_nand_dma_cb, &info->comp, &info->dma_ch);
+			if (err < 0) {
+				info->dma_ch = -1;
+				printk(KERN_WARNING "DMA request failed."
+					" Non-dma data transfer mode\n");
+			} else {
+				omap_set_dma_dest_burst_mode(info->dma_ch,
+						OMAP_DMA_DATA_BURST_16);
+				omap_set_dma_src_burst_mode(info->dma_ch,
+						OMAP_DMA_DATA_BURST_16);
+
+				info->nand.read_buf   = omap_read_buf_dma_pref;
+				info->nand.write_buf  = omap_write_buf_dma_pref;
+			}
+		}
+	} else {
+		if (info->nand.options & NAND_BUSWIDTH_16) {
+			info->nand.read_buf   = omap_read_buf16;
+			info->nand.write_buf  = omap_write_buf16;
+		} else {
+			info->nand.read_buf   = omap_read_buf8;
+			info->nand.write_buf  = omap_write_buf8;
+		}
+	}
+	info->nand.verify_buf = omap_verify_buf;
+
 #ifdef CONFIG_MTD_NAND_OMAP_HWECC
 	info->nand.ecc.bytes		= 3;
 	info->nand.ecc.size		= 512;
@@ -744,9 +1057,12 @@ static int omap_nand_remove(struct platform_device *pdev)
 	struct omap_nand_info *info = mtd->priv;
 
 	platform_set_drvdata(pdev, NULL);
+	if (use_dma)
+		omap_free_dma(info->dma_ch);
+
 	/* Release NAND device, its internal structures and partitions */
 	nand_release(&info->mtd);
-	iounmap(info->nand.IO_ADDR_R);
+	iounmap(info->nand_pref_fifo_add);
 	kfree(&info->mtd);
 	return 0;
 }
@@ -763,6 +1079,15 @@ static struct platform_driver omap_nand_driver = {
 static int __init omap_nand_init(void)
 {
 	printk(KERN_INFO "%s driver initializing\n", DRIVER_NAME);
+
+	/* This check is required if driver is being
+	 * loaded run time as a module
+	 */
+	if ((1 == use_dma) && (0 == use_prefetch)) {
+		printk(KERN_INFO"Wrong parameters: 'use_dma' can not be 1 "
+				"without use_prefetch'. Prefetch will not be"
+				" used in either mode (mpu or dma)\n");
+	}
 	return platform_driver_register(&omap_nand_driver);
 }
 
diff --git a/drivers/mtd/nand/orion_nand.c b/drivers/mtd/nand/orion_nand.c
index 0d9d4bc9c76..f59c07427af 100644
--- a/drivers/mtd/nand/orion_nand.c
+++ b/drivers/mtd/nand/orion_nand.c
@@ -171,7 +171,6 @@ static int __devexit orion_nand_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver orion_nand_driver = {
-	.probe		= orion_nand_probe,
 	.remove		= __devexit_p(orion_nand_remove),
 	.driver		= {
 		.name	= "orion_nand",
@@ -181,7 +180,7 @@ static struct platform_driver orion_nand_driver = {
 
 static int __init orion_nand_init(void)
 {
-	return platform_driver_register(&orion_nand_driver);
+	return platform_driver_probe(&orion_nand_driver, orion_nand_probe);
 }
 
 static void __exit orion_nand_exit(void)
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 30a8ce6d3e6..6ea520ae241 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -102,6 +102,7 @@ enum {
 	ERR_SENDCMD	= -2,
 	ERR_DBERR	= -3,
 	ERR_BBERR	= -4,
+	ERR_SBERR	= -5,
 };
 
 enum {
@@ -564,11 +565,13 @@ static irqreturn_t pxa3xx_nand_irq(int irq, void *devid)
 
 	status = nand_readl(info, NDSR);
 
-	if (status & (NDSR_RDDREQ | NDSR_DBERR)) {
+	if (status & (NDSR_RDDREQ | NDSR_DBERR | NDSR_SBERR)) {
 		if (status & NDSR_DBERR)
 			info->retcode = ERR_DBERR;
+		else if (status & NDSR_SBERR)
+			info->retcode = ERR_SBERR;
 
-		disable_int(info, NDSR_RDDREQ | NDSR_DBERR);
+		disable_int(info, NDSR_RDDREQ | NDSR_DBERR | NDSR_SBERR);
 
 		if (info->use_dma) {
 			info->state = STATE_DMA_READING;
@@ -670,7 +673,7 @@ static void pxa3xx_nand_cmdfunc(struct mtd_info *mtd, unsigned command,
 		if (prepare_read_prog_cmd(info, cmdset->read1, column, page_addr))
 			break;
 
-		pxa3xx_nand_do_cmd(info, NDSR_RDDREQ | NDSR_DBERR);
+		pxa3xx_nand_do_cmd(info, NDSR_RDDREQ | NDSR_DBERR | NDSR_SBERR);
 
 		/* We only are OOB, so if the data has error, does not matter */
 		if (info->retcode == ERR_DBERR)
@@ -687,7 +690,7 @@ static void pxa3xx_nand_cmdfunc(struct mtd_info *mtd, unsigned command,
 		if (prepare_read_prog_cmd(info, cmdset->read1, column, page_addr))
 			break;
 
-		pxa3xx_nand_do_cmd(info, NDSR_RDDREQ | NDSR_DBERR);
+		pxa3xx_nand_do_cmd(info, NDSR_RDDREQ | NDSR_DBERR | NDSR_SBERR);
 
 		if (info->retcode == ERR_DBERR) {
 			/* for blank page (all 0xff), HW will calculate its ECC as
@@ -861,8 +864,12 @@ static int pxa3xx_nand_ecc_correct(struct mtd_info *mtd,
 	 * consider it as a ecc error which will tell the caller the
 	 * read fail We have distinguish all the errors, but the
 	 * nand_read_ecc only check this function return value
+	 *
+	 * Corrected (single-bit) errors must also be noted.
 	 */
-	if (info->retcode != ERR_NONE)
+	if (info->retcode == ERR_SBERR)
+		return 1;
+	else if (info->retcode != ERR_NONE)
 		return -1;
 
 	return 0;
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
index 2bc896623e2..02bef21f2e4 100644
--- a/drivers/mtd/nand/sh_flctl.c
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -329,7 +329,7 @@ static void set_cmd_regs(struct mtd_info *mtd, uint32_t cmd, uint32_t flcmcdr_va
 }
 
 static int flctl_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
-				uint8_t *buf)
+				uint8_t *buf, int page)
 {
 	int i, eccsize = chip->ecc.size;
 	int eccbytes = chip->ecc.bytes;
@@ -857,7 +857,6 @@ static int __exit flctl_remove(struct platform_device *pdev)
 }
 
 static struct platform_driver flctl_driver = {
-	.probe		= flctl_probe,
 	.remove		= flctl_remove,
 	.driver = {
 		.name	= "sh_flctl",
@@ -867,7 +866,7 @@ static struct platform_driver flctl_driver = {
 
 static int __init flctl_nand_init(void)
 {
-	return platform_driver_register(&flctl_driver);
+	return platform_driver_probe(&flctl_driver, flctl_probe);
 }
 
 static void __exit flctl_nand_cleanup(void)
diff --git a/drivers/mtd/nand/tmio_nand.c b/drivers/mtd/nand/tmio_nand.c
index daa6a4c3b8c..92c73344a66 100644
--- a/drivers/mtd/nand/tmio_nand.c
+++ b/drivers/mtd/nand/tmio_nand.c
@@ -301,6 +301,21 @@ static int tmio_nand_calculate_ecc(struct mtd_info *mtd, const u_char *dat,
 	return 0;
 }
 
+static int tmio_nand_correct_data(struct mtd_info *mtd, unsigned char *buf,
+		unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	int r0, r1;
+
+	/* assume ecc.size = 512 and ecc.bytes = 6 */
+	r0 = __nand_correct_data(buf, read_ecc, calc_ecc, 256);
+	if (r0 < 0)
+		return r0;
+	r1 = __nand_correct_data(buf + 256, read_ecc + 3, calc_ecc + 3, 256);
+	if (r1 < 0)
+		return r1;
+	return r0 + r1;
+}
+
 static int tmio_hw_init(struct platform_device *dev, struct tmio_nand *tmio)
 {
 	struct mfd_cell *cell = (struct mfd_cell *)dev->dev.platform_data;
@@ -424,7 +439,7 @@ static int tmio_probe(struct platform_device *dev)
 	nand_chip->ecc.bytes = 6;
 	nand_chip->ecc.hwctl = tmio_nand_enable_hwecc;
 	nand_chip->ecc.calculate = tmio_nand_calculate_ecc;
-	nand_chip->ecc.correct = nand_correct_data;
+	nand_chip->ecc.correct = tmio_nand_correct_data;
 
 	if (data)
 		nand_chip->badblock_pattern = data->badblock_pattern;
diff --git a/drivers/mtd/nand/txx9ndfmc.c b/drivers/mtd/nand/txx9ndfmc.c
index 488088eff2c..73af8324d0d 100644
--- a/drivers/mtd/nand/txx9ndfmc.c
+++ b/drivers/mtd/nand/txx9ndfmc.c
@@ -189,18 +189,43 @@ static int txx9ndfmc_calculate_ecc(struct mtd_info *mtd, const uint8_t *dat,
 				   uint8_t *ecc_code)
 {
 	struct platform_device *dev = mtd_to_platdev(mtd);
+	struct nand_chip *chip = mtd->priv;
+	int eccbytes;
 	u32 mcr = txx9ndfmc_read(dev, TXX9_NDFMCR);
 
 	mcr &= ~TXX9_NDFMCR_ECC_ALL;
 	txx9ndfmc_write(dev, mcr | TXX9_NDFMCR_ECC_OFF, TXX9_NDFMCR);
 	txx9ndfmc_write(dev, mcr | TXX9_NDFMCR_ECC_READ, TXX9_NDFMCR);
-	ecc_code[1] = txx9ndfmc_read(dev, TXX9_NDFDTR);
-	ecc_code[0] = txx9ndfmc_read(dev, TXX9_NDFDTR);
-	ecc_code[2] = txx9ndfmc_read(dev, TXX9_NDFDTR);
+	for (eccbytes = chip->ecc.bytes; eccbytes > 0; eccbytes -= 3) {
+		ecc_code[1] = txx9ndfmc_read(dev, TXX9_NDFDTR);
+		ecc_code[0] = txx9ndfmc_read(dev, TXX9_NDFDTR);
+		ecc_code[2] = txx9ndfmc_read(dev, TXX9_NDFDTR);
+		ecc_code += 3;
+	}
 	txx9ndfmc_write(dev, mcr | TXX9_NDFMCR_ECC_OFF, TXX9_NDFMCR);
 	return 0;
 }
 
+static int txx9ndfmc_correct_data(struct mtd_info *mtd, unsigned char *buf,
+		unsigned char *read_ecc, unsigned char *calc_ecc)
+{
+	struct nand_chip *chip = mtd->priv;
+	int eccsize;
+	int corrected = 0;
+	int stat;
+
+	for (eccsize = chip->ecc.size; eccsize > 0; eccsize -= 256) {
+		stat = __nand_correct_data(buf, read_ecc, calc_ecc, 256);
+		if (stat < 0)
+			return stat;
+		corrected += stat;
+		buf += 256;
+		read_ecc += 3;
+		calc_ecc += 3;
+	}
+	return corrected;
+}
+
 static void txx9ndfmc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	struct platform_device *dev = mtd_to_platdev(mtd);
@@ -244,6 +269,22 @@ static void txx9ndfmc_initialize(struct platform_device *dev)
 #define TXX9NDFMC_NS_TO_CYC(gbusclk, ns) \
 	DIV_ROUND_UP((ns) * DIV_ROUND_UP(gbusclk, 1000), 1000000)
 
+static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
+{
+	struct nand_chip *chip = mtd->priv;
+	int ret;
+
+	ret = nand_scan_ident(mtd, 1);
+	if (!ret) {
+		if (mtd->writesize >= 512) {
+			chip->ecc.size = mtd->writesize;
+			chip->ecc.bytes = 3 * (mtd->writesize / 256);
+		}
+		ret = nand_scan_tail(mtd);
+	}
+	return ret;
+}
+
 static int __init txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev->dev.platform_data;
@@ -321,9 +362,10 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->cmd_ctrl = txx9ndfmc_cmd_ctrl;
 		chip->dev_ready = txx9ndfmc_dev_ready;
 		chip->ecc.calculate = txx9ndfmc_calculate_ecc;
-		chip->ecc.correct = nand_correct_data;
+		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
 		chip->ecc.mode = NAND_ECC_HW;
+		/* txx9ndfmc_nand_scan will overwrite ecc.size and ecc.bytes */
 		chip->ecc.size = 256;
 		chip->ecc.bytes = 3;
 		chip->chip_delay = 100;
@@ -349,7 +391,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		if (plat->wide_mask & (1 << i))
 			chip->options |= NAND_BUSWIDTH_16;
 
-		if (nand_scan(mtd, 1)) {
+		if (txx9ndfmc_nand_scan(mtd)) {
 			kfree(txx9_priv->mtdname);
 			kfree(txx9_priv);
 			continue;
diff --git a/drivers/mtd/nand/w90p910_nand.c b/drivers/mtd/nand/w90p910_nand.c
new file mode 100644
index 00000000000..7680e731348
--- /dev/null
+++ b/drivers/mtd/nand/w90p910_nand.c
@@ -0,0 +1,382 @@
+/*
+ * Copyright (c) 2009 Nuvoton technology corporation.
+ *
+ * Wan ZongShun <mcuos.com@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation;version 2 of the License.
+ *
+ */
+
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/delay.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+
+#define REG_FMICSR   	0x00
+#define REG_SMCSR    	0xa0
+#define REG_SMISR    	0xac
+#define REG_SMCMD    	0xb0
+#define REG_SMADDR   	0xb4
+#define REG_SMDATA   	0xb8
+
+#define RESET_FMI	0x01
+#define NAND_EN		0x08
+#define READYBUSY	(0x01 << 18)
+
+#define SWRST		0x01
+#define PSIZE		(0x01 << 3)
+#define DMARWEN		(0x03 << 1)
+#define BUSWID		(0x01 << 4)
+#define ECC4EN		(0x01 << 5)
+#define WP		(0x01 << 24)
+#define NANDCS		(0x01 << 25)
+#define ENDADDR		(0x01 << 31)
+
+#define read_data_reg(dev)		\
+	__raw_readl((dev)->reg + REG_SMDATA)
+
+#define write_data_reg(dev, val)	\
+	__raw_writel((val), (dev)->reg + REG_SMDATA)
+
+#define write_cmd_reg(dev, val)		\
+	__raw_writel((val), (dev)->reg + REG_SMCMD)
+
+#define write_addr_reg(dev, val)	\
+	__raw_writel((val), (dev)->reg + REG_SMADDR)
+
+struct w90p910_nand {
+	struct mtd_info mtd;
+	struct nand_chip chip;
+	void __iomem *reg;
+	struct clk *clk;
+	spinlock_t lock;
+};
+
+static const struct mtd_partition partitions[] = {
+	{
+	 .name = "NAND FS 0",
+	 .offset = 0,
+	 .size = 8 * 1024 * 1024
+	},
+	{
+	 .name = "NAND FS 1",
+	 .offset = MTDPART_OFS_APPEND,
+	 .size = MTDPART_SIZ_FULL
+	}
+};
+
+static unsigned char w90p910_nand_read_byte(struct mtd_info *mtd)
+{
+	unsigned char ret;
+	struct w90p910_nand *nand;
+
+	nand = container_of(mtd, struct w90p910_nand, mtd);
+
+	ret = (unsigned char)read_data_reg(nand);
+
+	return ret;
+}
+
+static void w90p910_nand_read_buf(struct mtd_info *mtd,
+						unsigned char *buf, int len)
+{
+	int i;
+	struct w90p910_nand *nand;
+
+	nand = container_of(mtd, struct w90p910_nand, mtd);
+
+	for (i = 0; i < len; i++)
+		buf[i] = (unsigned char)read_data_reg(nand);
+}
+
+static void w90p910_nand_write_buf(struct mtd_info *mtd,
+					const unsigned char *buf, int len)
+{
+	int i;
+	struct w90p910_nand *nand;
+
+	nand = container_of(mtd, struct w90p910_nand, mtd);
+
+	for (i = 0; i < len; i++)
+		write_data_reg(nand, buf[i]);
+}
+
+static int w90p910_verify_buf(struct mtd_info *mtd,
+					const unsigned char *buf, int len)
+{
+	int i;
+	struct w90p910_nand *nand;
+
+	nand = container_of(mtd, struct w90p910_nand, mtd);
+
+	for (i = 0; i < len; i++) {
+		if (buf[i] != (unsigned char)read_data_reg(nand))
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int w90p910_check_rb(struct w90p910_nand *nand)
+{
+	unsigned int val;
+	spin_lock(&nand->lock);
+	val = __raw_readl(REG_SMISR);
+	val &= READYBUSY;
+	spin_unlock(&nand->lock);
+
+	return val;
+}
+
+static int w90p910_nand_devready(struct mtd_info *mtd)
+{
+	struct w90p910_nand *nand;
+	int ready;
+
+	nand = container_of(mtd, struct w90p910_nand, mtd);
+
+	ready = (w90p910_check_rb(nand)) ? 1 : 0;
+	return ready;
+}
+
+static void w90p910_nand_command_lp(struct mtd_info *mtd,
+			unsigned int command, int column, int page_addr)
+{
+	register struct nand_chip *chip = mtd->priv;
+	struct w90p910_nand *nand;
+
+	nand = container_of(mtd, struct w90p910_nand, mtd);
+
+	if (command == NAND_CMD_READOOB) {
+		column += mtd->writesize;
+		command = NAND_CMD_READ0;
+	}
+
+	write_cmd_reg(nand, command & 0xff);
+
+	if (column != -1 || page_addr != -1) {
+
+		if (column != -1) {
+			if (chip->options & NAND_BUSWIDTH_16)
+				column >>= 1;
+			write_addr_reg(nand, column);
+			write_addr_reg(nand, column >> 8 | ENDADDR);
+		}
+		if (page_addr != -1) {
+			write_addr_reg(nand, page_addr);
+
+			if (chip->chipsize > (128 << 20)) {
+				write_addr_reg(nand, page_addr >> 8);
+				write_addr_reg(nand, page_addr >> 16 | ENDADDR);
+			} else {
+				write_addr_reg(nand, page_addr >> 8 | ENDADDR);
+			}
+		}
+	}
+
+	switch (command) {
+	case NAND_CMD_CACHEDPROG:
+	case NAND_CMD_PAGEPROG:
+	case NAND_CMD_ERASE1:
+	case NAND_CMD_ERASE2:
+	case NAND_CMD_SEQIN:
+	case NAND_CMD_RNDIN:
+	case NAND_CMD_STATUS:
+	case NAND_CMD_DEPLETE1:
+		return;
+
+	case NAND_CMD_STATUS_ERROR:
+	case NAND_CMD_STATUS_ERROR0:
+	case NAND_CMD_STATUS_ERROR1:
+	case NAND_CMD_STATUS_ERROR2:
+	case NAND_CMD_STATUS_ERROR3:
+		udelay(chip->chip_delay);
+		return;
+
+	case NAND_CMD_RESET:
+		if (chip->dev_ready)
+			break;
+		udelay(chip->chip_delay);
+
+		write_cmd_reg(nand, NAND_CMD_STATUS);
+		write_cmd_reg(nand, command);
+
+		while (!w90p910_check_rb(nand))
+			;
+
+		return;
+
+	case NAND_CMD_RNDOUT:
+		write_cmd_reg(nand, NAND_CMD_RNDOUTSTART);
+		return;
+
+	case NAND_CMD_READ0:
+
+		write_cmd_reg(nand, NAND_CMD_READSTART);
+	default:
+
+		if (!chip->dev_ready) {
+			udelay(chip->chip_delay);
+			return;
+		}
+	}
+
+	/* Apply this short delay always to ensure that we do wait tWB in
+	 * any case on any machine. */
+	ndelay(100);
+
+	while (!chip->dev_ready(mtd))
+		;
+}
+
+
+static void w90p910_nand_enable(struct w90p910_nand *nand)
+{
+	unsigned int val;
+	spin_lock(&nand->lock);
+	__raw_writel(RESET_FMI, (nand->reg + REG_FMICSR));
+
+	val = __raw_readl(nand->reg + REG_FMICSR);
+
+	if (!(val & NAND_EN))
+		__raw_writel(val | NAND_EN, REG_FMICSR);
+
+	val = __raw_readl(nand->reg + REG_SMCSR);
+
+	val &= ~(SWRST|PSIZE|DMARWEN|BUSWID|ECC4EN|NANDCS);
+	val |= WP;
+
+	__raw_writel(val, nand->reg + REG_SMCSR);
+
+	spin_unlock(&nand->lock);
+}
+
+static int __devinit w90p910_nand_probe(struct platform_device *pdev)
+{
+	struct w90p910_nand *w90p910_nand;
+	struct nand_chip *chip;
+	int retval;
+	struct resource *res;
+
+	retval = 0;
+
+	w90p910_nand = kzalloc(sizeof(struct w90p910_nand), GFP_KERNEL);
+	if (!w90p910_nand)
+		return -ENOMEM;
+	chip = &(w90p910_nand->chip);
+
+	w90p910_nand->mtd.priv	= chip;
+	w90p910_nand->mtd.owner	= THIS_MODULE;
+	spin_lock_init(&w90p910_nand->lock);
+
+	w90p910_nand->clk = clk_get(&pdev->dev, NULL);
+	if (IS_ERR(w90p910_nand->clk)) {
+		retval = -ENOENT;
+		goto fail1;
+	}
+	clk_enable(w90p910_nand->clk);
+
+	chip->cmdfunc		= w90p910_nand_command_lp;
+	chip->dev_ready		= w90p910_nand_devready;
+	chip->read_byte		= w90p910_nand_read_byte;
+	chip->write_buf		= w90p910_nand_write_buf;
+	chip->read_buf		= w90p910_nand_read_buf;
+	chip->verify_buf	= w90p910_verify_buf;
+	chip->chip_delay	= 50;
+	chip->options		= 0;
+	chip->ecc.mode		= NAND_ECC_SOFT;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		retval = -ENXIO;
+		goto fail1;
+	}
+
+	if (!request_mem_region(res->start, resource_size(res), pdev->name)) {
+		retval = -EBUSY;
+		goto fail1;
+	}
+
+	w90p910_nand->reg = ioremap(res->start, resource_size(res));
+	if (!w90p910_nand->reg) {
+		retval = -ENOMEM;
+		goto fail2;
+	}
+
+	w90p910_nand_enable(w90p910_nand);
+
+	if (nand_scan(&(w90p910_nand->mtd), 1)) {
+		retval = -ENXIO;
+		goto fail3;
+	}
+
+	add_mtd_partitions(&(w90p910_nand->mtd), partitions,
+						ARRAY_SIZE(partitions));
+
+	platform_set_drvdata(pdev, w90p910_nand);
+
+	return retval;
+
+fail3:	iounmap(w90p910_nand->reg);
+fail2:	release_mem_region(res->start, resource_size(res));
+fail1:	kfree(w90p910_nand);
+	return retval;
+}
+
+static int __devexit w90p910_nand_remove(struct platform_device *pdev)
+{
+	struct w90p910_nand *w90p910_nand = platform_get_drvdata(pdev);
+	struct resource *res;
+
+	iounmap(w90p910_nand->reg);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(res->start, resource_size(res));
+
+	clk_disable(w90p910_nand->clk);
+	clk_put(w90p910_nand->clk);
+
+	kfree(w90p910_nand);
+
+	platform_set_drvdata(pdev, NULL);
+
+	return 0;
+}
+
+static struct platform_driver w90p910_nand_driver = {
+	.probe		= w90p910_nand_probe,
+	.remove		= __devexit_p(w90p910_nand_remove),
+	.driver		= {
+		.name	= "w90p910-fmi",
+		.owner	= THIS_MODULE,
+	},
+};
+
+static int __init w90p910_nand_init(void)
+{
+	return platform_driver_register(&w90p910_nand_driver);
+}
+
+static void __exit w90p910_nand_exit(void)
+{
+	platform_driver_unregister(&w90p910_nand_driver);
+}
+
+module_init(w90p910_nand_init);
+module_exit(w90p910_nand_exit);
+
+MODULE_AUTHOR("Wan ZongShun <mcuos.com@gmail.com>");
+MODULE_DESCRIPTION("w90p910 nand driver!");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:w90p910-fmi");