diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index 5aaa7f541ea1..bb77f750e75a 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -27,6 +27,7 @@
 #include <linux/of_device.h>
 #include <linux/of_mtd.h>
 #include "gpmi-nand.h"
+#include "bch-regs.h"
 
 /* Resource names for the GPMI NAND driver. */
 #define GPMI_NAND_GPMI_REGS_ADDR_RES_NAME  "gpmi-nand"
@@ -1049,6 +1050,90 @@ static int gpmi_ecc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return max_bitflips;
 }
 
+/* Fake a virtual small page for the subpage read */
+static int gpmi_ecc_read_subpage(struct mtd_info *mtd, struct nand_chip *chip,
+			uint32_t offs, uint32_t len, uint8_t *buf, int page)
+{
+	struct gpmi_nand_data *this = chip->priv;
+	void __iomem *bch_regs = this->resources.bch_regs;
+	struct bch_geometry old_geo = this->bch_geometry;
+	struct bch_geometry *geo = &this->bch_geometry;
+	int size = chip->ecc.size; /* ECC chunk size */
+	int meta, n, page_size;
+	u32 r1_old, r2_old, r1_new, r2_new;
+	unsigned int max_bitflips;
+	int first, last, marker_pos;
+	int ecc_parity_size;
+	int col = 0;
+
+	/* The size of ECC parity */
+	ecc_parity_size = geo->gf_len * geo->ecc_strength / 8;
+
+	/* Align it with the chunk size */
+	first = offs / size;
+	last = (offs + len - 1) / size;
+
+	/*
+	 * Find the chunk which contains the Block Marker. If this chunk is
+	 * in the range of [first, last], we have to read out the whole page.
+	 * Why? since we had swapped the data at the position of Block Marker
+	 * to the metadata which is bound with the chunk 0.
+	 */
+	marker_pos = geo->block_mark_byte_offset / size;
+	if (last >= marker_pos && first <= marker_pos) {
+		dev_dbg(this->dev, "page:%d, first:%d, last:%d, marker at:%d\n",
+				page, first, last, marker_pos);
+		return gpmi_ecc_read_page(mtd, chip, buf, 0, page);
+	}
+
+	meta = geo->metadata_size;
+	if (first) {
+		col = meta + (size + ecc_parity_size) * first;
+		chip->cmdfunc(mtd, NAND_CMD_RNDOUT, col, -1);
+
+		meta = 0;
+		buf = buf + first * size;
+	}
+
+	/* Save the old environment */
+	r1_old = r1_new = readl(bch_regs + HW_BCH_FLASH0LAYOUT0);
+	r2_old = r2_new = readl(bch_regs + HW_BCH_FLASH0LAYOUT1);
+
+	/* change the BCH registers and bch_geometry{} */
+	n = last - first + 1;
+	page_size = meta + (size + ecc_parity_size) * n;
+
+	r1_new &= ~(BM_BCH_FLASH0LAYOUT0_NBLOCKS |
+			BM_BCH_FLASH0LAYOUT0_META_SIZE);
+	r1_new |= BF_BCH_FLASH0LAYOUT0_NBLOCKS(n - 1)
+			| BF_BCH_FLASH0LAYOUT0_META_SIZE(meta);
+	writel(r1_new, bch_regs + HW_BCH_FLASH0LAYOUT0);
+
+	r2_new &= ~BM_BCH_FLASH0LAYOUT1_PAGE_SIZE;
+	r2_new |= BF_BCH_FLASH0LAYOUT1_PAGE_SIZE(page_size);
+	writel(r2_new, bch_regs + HW_BCH_FLASH0LAYOUT1);
+
+	geo->ecc_chunk_count = n;
+	geo->payload_size = n * size;
+	geo->page_size = page_size;
+	geo->auxiliary_status_offset = ALIGN(meta, 4);
+
+	dev_dbg(this->dev, "page:%d(%d:%d)%d, chunk:(%d:%d), BCH PG size:%d\n",
+		page, offs, len, col, first, n, page_size);
+
+	/* Read the subpage now */
+	this->swap_block_mark = false;
+	max_bitflips = gpmi_ecc_read_page(mtd, chip, buf, 0, page);
+
+	/* Restore */
+	writel(r1_old, bch_regs + HW_BCH_FLASH0LAYOUT0);
+	writel(r2_old, bch_regs + HW_BCH_FLASH0LAYOUT1);
+	this->bch_geometry = old_geo;
+	this->swap_block_mark = true;
+
+	return max_bitflips;
+}
+
 static int gpmi_ecc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 				const uint8_t *buf, int oob_required)
 {
@@ -1565,6 +1650,17 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	ecc->strength	= bch_geo->ecc_strength;
 	ecc->layout	= &gpmi_hw_ecclayout;
 
+	/*
+	 * We only enable the subpage read when:
+	 *  (1) the chip is imx6, and
+	 *  (2) the size of the ECC parity is byte aligned.
+	 */
+	if (GPMI_IS_MX6Q(this) &&
+		((bch_geo->gf_len * bch_geo->ecc_strength) % 8) == 0) {
+		ecc->read_subpage = gpmi_ecc_read_subpage;
+		chip->options |= NAND_SUBPAGE_READ;
+	}
+
 	/*
 	 * Can we enable the extra features? such as EDO or Sync mode.
 	 *