diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 1d9bf48..75c2c06 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -29,4 +29,14 @@
 
 endif
 
+if SPL_BUILD
+
+config SPL_NAND_DENALI
+	bool "Support Denali NAND controller for SPL"
+	help
+	  This is a small implementation of the Denali NAND controller
+	  for use on SPL.
+
+endif
+
 endmenu
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index f298f84..47eb34f 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -12,6 +12,7 @@
 endif
 
 obj-$(CONFIG_SPL_NAND_AM33XX_BCH) += am335x_spl_bch.o
+obj-$(CONFIG_SPL_NAND_DENALI) += denali_spl.o
 obj-$(CONFIG_SPL_NAND_DOCG4) += docg4_spl.o
 obj-$(CONFIG_SPL_NAND_SIMPLE) += nand_spl_simple.o
 obj-$(CONFIG_SPL_NAND_LOAD) += nand_spl_load.o
diff --git a/drivers/mtd/nand/denali_spl.c b/drivers/mtd/nand/denali_spl.c
new file mode 100644
index 0000000..65fdde8
--- /dev/null
+++ b/drivers/mtd/nand/denali_spl.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright (C) 2014       Panasonic Corporation
+ *
+ * SPDX-License-Identifier:	GPL-2.0+
+ */
+
+#include <common.h>
+#include <asm/io.h>
+#include <asm/unaligned.h>
+#include <linux/mtd/nand.h>
+#include "denali.h"
+
+#define SPARE_ACCESS		0x41
+#define MAIN_ACCESS		0x42
+#define PIPELINE_ACCESS		0x2000
+
+#define BANK(x) ((x) << 24)
+
+static void __iomem *denali_flash_mem =
+			(void __iomem *)CONFIG_SYS_NAND_DATA_BASE;
+static void __iomem *denali_flash_reg =
+			(void __iomem *)CONFIG_SYS_NAND_REGS_BASE;
+
+static const int flash_bank;
+static uint8_t page_buffer[NAND_MAX_PAGESIZE];
+static int page_size, oob_size, pages_per_block;
+
+static void index_addr(uint32_t address, uint32_t data)
+{
+	writel(address, denali_flash_mem + INDEX_CTRL_REG);
+	writel(data, denali_flash_mem + INDEX_DATA_REG);
+}
+
+static int wait_for_irq(uint32_t irq_mask)
+{
+	unsigned long timeout = 1000000;
+	uint32_t intr_status;
+
+	do {
+		intr_status = readl(denali_flash_reg + INTR_STATUS(flash_bank));
+
+		if (intr_status & INTR_STATUS__ECC_UNCOR_ERR) {
+			debug("Uncorrected ECC detected\n");
+			return -EIO;
+		}
+
+		if (intr_status & irq_mask)
+			break;
+
+		udelay(1);
+		timeout--;
+	} while (timeout);
+
+	if (!timeout) {
+		debug("Timeout with interrupt status %08x\n", intr_status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void read_data_from_flash_mem(uint8_t *buf, int len)
+{
+	int i;
+	uint32_t *buf32;
+
+	/* transfer the data from the flash */
+	buf32 = (uint32_t *)buf;
+
+	/*
+	 * Let's take care of unaligned access although it rarely happens.
+	 * Avoid put_unaligned() for the normal use cases since it leads to
+	 * a bit performance regression.
+	 */
+	if ((unsigned long)buf32 % 4) {
+		for (i = 0; i < len / 4; i++)
+			put_unaligned(readl(denali_flash_mem + INDEX_DATA_REG),
+				      buf32++);
+	} else {
+		for (i = 0; i < len / 4; i++)
+			*buf32++ = readl(denali_flash_mem + INDEX_DATA_REG);
+	}
+
+	if (len % 4) {
+		u32 tmp;
+
+		tmp = cpu_to_le32(readl(denali_flash_mem + INDEX_DATA_REG));
+		buf = (uint8_t *)buf32;
+		for (i = 0; i < len % 4; i++) {
+			*buf++ = tmp;
+			tmp >>= 8;
+		}
+	}
+}
+
+int denali_send_pipeline_cmd(int page, int ecc_en, int access_type)
+{
+	uint32_t addr, cmd;
+	static uint32_t page_count = 1;
+
+	writel(ecc_en, denali_flash_reg + ECC_ENABLE);
+
+	/* clear all bits of intr_status. */
+	writel(0xffff, denali_flash_reg + INTR_STATUS(flash_bank));
+
+	addr = BANK(flash_bank) | page;
+
+	/* setup the acccess type */
+	cmd = MODE_10 | addr;
+	index_addr(cmd, access_type);
+
+	/* setup the pipeline command */
+	index_addr(cmd, PIPELINE_ACCESS | page_count);
+
+	cmd = MODE_01 | addr;
+	writel(cmd, denali_flash_mem + INDEX_CTRL_REG);
+
+	return wait_for_irq(INTR_STATUS__LOAD_COMP);
+}
+
+static int nand_read_oob(void *buf, int page)
+{
+	int ret;
+
+	ret = denali_send_pipeline_cmd(page, 0, SPARE_ACCESS);
+	if (ret < 0)
+		return ret;
+
+	read_data_from_flash_mem(buf, oob_size);
+
+	return 0;
+}
+
+static int nand_read_page(void *buf, int page)
+{
+	int ret;
+
+	ret = denali_send_pipeline_cmd(page, 1, MAIN_ACCESS);
+	if (ret < 0)
+		return ret;
+
+	read_data_from_flash_mem(buf, page_size);
+
+	return 0;
+}
+
+static int nand_block_isbad(int block)
+{
+	int ret;
+
+	ret = nand_read_oob(page_buffer, block * pages_per_block);
+	if (ret < 0)
+		return ret;
+
+	return page_buffer[CONFIG_SYS_NAND_BAD_BLOCK_POS] != 0xff;
+}
+
+/* nand_init() - initialize data to make nand usable by SPL */
+void nand_init(void)
+{
+	/* access to main area */
+	writel(0, denali_flash_reg + TRANSFER_SPARE_REG);
+
+	/*
+	 * These registers are expected to be already set by the hardware
+	 * or earlier boot code.  So we read these values out.
+	 */
+	page_size = readl(denali_flash_reg + DEVICE_MAIN_AREA_SIZE);
+	oob_size = readl(denali_flash_reg + DEVICE_SPARE_AREA_SIZE);
+	pages_per_block = readl(denali_flash_reg + PAGES_PER_BLOCK);
+}
+
+int nand_spl_load_image(uint32_t offs, unsigned int size, void *dst)
+{
+	int block, page, column, readlen;
+	int ret;
+	int force_bad_block_check = 1;
+
+	page = offs / page_size;
+	column = offs % page_size;
+
+	block = page / pages_per_block;
+	page = page % pages_per_block;
+
+	while (size) {
+		if (force_bad_block_check || page == 0) {
+			ret = nand_block_isbad(block);
+			if (ret < 0)
+				return ret;
+
+			if (ret) {
+				block++;
+				continue;
+			}
+		}
+
+		force_bad_block_check = 0;
+
+		if (unlikely(column || size < page_size)) {
+			/* Partial page read */
+			ret = nand_read_page(page_buffer,
+					     block * pages_per_block + page);
+			if (ret < 0)
+				return ret;
+
+			readlen = min(page_size - column, size);
+			memcpy(dst, page_buffer, readlen);
+
+			column = 0;
+		} else {
+			ret = nand_read_page(dst,
+					     block * pages_per_block + page);
+			if (ret < 0)
+				return ret;
+
+			readlen = page_size;
+		}
+
+		size -= readlen;
+		dst += readlen;
+		page++;
+		if (page == pages_per_block) {
+			block++;
+			page = 0;
+		}
+	}
+
+	return 0;
+}
+
+void nand_deselect(void) {}