diff --git a/Documentation/ABI/testing/sysfs-class-mtd b/Documentation/ABI/testing/sysfs-class-mtd
index db1ad7e..938ef71 100644
--- a/Documentation/ABI/testing/sysfs-class-mtd
+++ b/Documentation/ABI/testing/sysfs-class-mtd
@@ -142,13 +142,14 @@
 Contact:	linux-mtd@lists.infradead.org
 Description:
 		This allows the user to examine and adjust the criteria by which
-		mtd returns -EUCLEAN from mtd_read().  If the maximum number of
-		bit errors that were corrected on any single region comprising
-		an ecc step (as reported by the driver) equals or exceeds this
-		value, -EUCLEAN is returned.  Otherwise, absent an error, 0 is
-		returned.  Higher layers (e.g., UBI) use this return code as an
-		indication that an erase block may be degrading and should be
-		scrutinized as a candidate for being marked as bad.
+		mtd returns -EUCLEAN from mtd_read() and mtd_read_oob().  If the
+		maximum number of bit errors that were corrected on any single
+		region comprising an ecc step (as reported by the driver) equals
+		or exceeds this value, -EUCLEAN is returned.  Otherwise, absent
+		an error, 0 is returned.  Higher layers (e.g., UBI) use this
+		return code as an indication that an erase block may be
+		degrading and should be scrutinized as a candidate for being
+		marked as bad.
 
 		The initial value may be specified by the flash device driver.
 		If not, then the default value is ecc_strength.
@@ -167,7 +168,7 @@
 		block degradation, but high enough to avoid the consequences of
 		a persistent return value of -EUCLEAN on devices where sticky
 		bitflips occur.  Note that if bitflip_threshold exceeds
-		ecc_strength, -EUCLEAN is never returned by mtd_read().
+		ecc_strength, -EUCLEAN is never returned by the read operations.
 		Conversely, if bitflip_threshold is zero, -EUCLEAN is always
 		returned, absent a hard error.
 
diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
index a05b7b4..a6cad5c 100644
--- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c
@@ -920,12 +920,12 @@
 		 */
 		memset(chip->oob_poi, ~0, mtd->oobsize);
 		chip->oob_poi[0] = ((uint8_t *) auxiliary_virt)[0];
-
-		read_page_swap_end(this, buf, mtd->writesize,
-				this->payload_virt, this->payload_phys,
-				nfc_geo->payload_size,
-				payload_virt, payload_phys);
 	}
+
+	read_page_swap_end(this, buf, mtd->writesize,
+			this->payload_virt, this->payload_phys,
+			nfc_geo->payload_size,
+			payload_virt, payload_phys);
 exit_nfc:
 	return ret;
 }
diff --git a/drivers/mtd/nand/mxc_nand.c b/drivers/mtd/nand/mxc_nand.c
index c58e6a9..6acc790 100644
--- a/drivers/mtd/nand/mxc_nand.c
+++ b/drivers/mtd/nand/mxc_nand.c
@@ -273,6 +273,26 @@
 
 static const char *part_probes[] = { "RedBoot", "cmdlinepart", "ofpart", NULL };
 
+static void memcpy32_fromio(void *trg, const void __iomem  *src, size_t size)
+{
+	int i;
+	u32 *t = trg;
+	const __iomem u32 *s = src;
+
+	for (i = 0; i < (size >> 2); i++)
+		*t++ = __raw_readl(s++);
+}
+
+static void memcpy32_toio(void __iomem *trg, const void *src, int size)
+{
+	int i;
+	u32 __iomem *t = trg;
+	const u32 *s = src;
+
+	for (i = 0; i < (size >> 2); i++)
+		__raw_writel(*s++, t++);
+}
+
 static int check_int_v3(struct mxc_nand_host *host)
 {
 	uint32_t tmp;
@@ -519,7 +539,7 @@
 
 	wait_op_done(host, true);
 
-	memcpy_fromio(host->data_buf, host->main_area0, 16);
+	memcpy32_fromio(host->data_buf, host->main_area0, 16);
 }
 
 /* Request the NANDFC to perform a read of the NAND device ID. */
@@ -535,7 +555,7 @@
 	/* Wait for operation to complete */
 	wait_op_done(host, true);
 
-	memcpy_fromio(host->data_buf, host->main_area0, 16);
+	memcpy32_fromio(host->data_buf, host->main_area0, 16);
 
 	if (this->options & NAND_BUSWIDTH_16) {
 		/* compress the ID info */
@@ -797,16 +817,16 @@
 
 	if (bfrom) {
 		for (i = 0; i < n - 1; i++)
-			memcpy_fromio(d + i * j, s + i * t, j);
+			memcpy32_fromio(d + i * j, s + i * t, j);
 
 		/* the last section */
-		memcpy_fromio(d + i * j, s + i * t, mtd->oobsize - i * j);
+		memcpy32_fromio(d + i * j, s + i * t, mtd->oobsize - i * j);
 	} else {
 		for (i = 0; i < n - 1; i++)
-			memcpy_toio(&s[i * t], &d[i * j], j);
+			memcpy32_toio(&s[i * t], &d[i * j], j);
 
 		/* the last section */
-		memcpy_toio(&s[i * t], &d[i * j], mtd->oobsize - i * j);
+		memcpy32_toio(&s[i * t], &d[i * j], mtd->oobsize - i * j);
 	}
 }
 
@@ -1070,7 +1090,8 @@
 
 		host->devtype_data->send_page(mtd, NFC_OUTPUT);
 
-		memcpy_fromio(host->data_buf, host->main_area0, mtd->writesize);
+		memcpy32_fromio(host->data_buf, host->main_area0,
+				mtd->writesize);
 		copy_spare(mtd, true);
 		break;
 
@@ -1086,7 +1107,7 @@
 		break;
 
 	case NAND_CMD_PAGEPROG:
-		memcpy_toio(host->main_area0, host->data_buf, mtd->writesize);
+		memcpy32_toio(host->main_area0, host->data_buf, mtd->writesize);
 		copy_spare(mtd, false);
 		host->devtype_data->send_page(mtd, NFC_INPUT);
 		host->devtype_data->send_cmd(host, command, true);
diff --git a/drivers/mtd/nand/nandsim.c b/drivers/mtd/nand/nandsim.c
index 6cc8fbf..cf0cd31 100644
--- a/drivers/mtd/nand/nandsim.c
+++ b/drivers/mtd/nand/nandsim.c
@@ -28,7 +28,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/vmalloc.h>
-#include <asm/div64.h>
+#include <linux/math64.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
 #include <linux/string.h>
@@ -546,12 +546,6 @@
 	return kstrdup(buf, GFP_KERNEL);
 }
 
-static uint64_t divide(uint64_t n, uint32_t d)
-{
-	do_div(n, d);
-	return n;
-}
-
 /*
  * Initialize the nandsim structure.
  *
@@ -580,7 +574,7 @@
 	ns->geom.oobsz    = mtd->oobsize;
 	ns->geom.secsz    = mtd->erasesize;
 	ns->geom.pgszoob  = ns->geom.pgsz + ns->geom.oobsz;
-	ns->geom.pgnum    = divide(ns->geom.totsz, ns->geom.pgsz);
+	ns->geom.pgnum    = div_u64(ns->geom.totsz, ns->geom.pgsz);
 	ns->geom.totszoob = ns->geom.totsz + (uint64_t)ns->geom.pgnum * ns->geom.oobsz;
 	ns->geom.secshift = ffs(ns->geom.secsz) - 1;
 	ns->geom.pgshift  = chip->page_shift;
@@ -921,7 +915,7 @@
 
 	if (!rptwear)
 		return 0;
-	wear_eb_count = divide(mtd->size, mtd->erasesize);
+	wear_eb_count = div_u64(mtd->size, mtd->erasesize);
 	mem = wear_eb_count * sizeof(unsigned long);
 	if (mem / sizeof(unsigned long) != wear_eb_count) {
 		NS_ERR("Too many erase blocks for wear reporting\n");