diff --git a/arch/sh/include/asm/sections.h b/arch/sh/include/asm/sections.h
index a78701da775b9d6dd2e246c80983562095bf6e54..4a5350037c8f59217a06e6e6ea1c429594d51073 100644
--- a/arch/sh/include/asm/sections.h
+++ b/arch/sh/include/asm/sections.h
@@ -3,7 +3,7 @@
 
 #include <asm-generic/sections.h>
 
-extern void __nosave_begin, __nosave_end;
+extern long __nosave_begin, __nosave_end;
 extern long __machvec_start, __machvec_end;
 extern char __uncached_start, __uncached_end;
 extern char _ebss[];
diff --git a/arch/sh/kernel/cpu/sh4/setup-sh7750.c b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
index 672944f5b19c63031f128232345360869ff6a558..e53b4b38bd11f954fd3d23b9e72e74d1540ea78e 100644
--- a/arch/sh/kernel/cpu/sh4/setup-sh7750.c
+++ b/arch/sh/kernel/cpu/sh4/setup-sh7750.c
@@ -14,7 +14,7 @@
 #include <linux/io.h>
 #include <linux/sh_timer.h>
 #include <linux/serial_sci.h>
-#include <asm/machtypes.h>
+#include <generated/machtypes.h>
 
 static struct resource rtc_resources[] = {
 	[0] = {
@@ -255,12 +255,17 @@ static struct platform_device *sh7750_early_devices[] __initdata = {
 
 void __init plat_early_device_setup(void)
 {
+	struct platform_device *dev[1];
+
 	if (mach_is_rts7751r2d()) {
 		scif_platform_data.scscr |= SCSCR_CKE1;
-		early_platform_add_devices(&scif_device, 1);
+		dev[0] = &scif_device;
+		early_platform_add_devices(dev, 1);
 	} else {
-		early_platform_add_devices(&sci_device, 1);
-		early_platform_add_devices(&scif_device, 1);
+		dev[0] = &sci_device;
+		early_platform_add_devices(dev, 1);
+		dev[0] = &scif_device;
+		early_platform_add_devices(dev, 1);
 	}
 
 	early_platform_add_devices(sh7750_early_devices,
diff --git a/arch/sh/lib/delay.c b/arch/sh/lib/delay.c
index faa8f86c0db490718d5dbb2c6948f11d3fff28d1..0901b2f14e15e9b2b396e923641de5c2a28eb90d 100644
--- a/arch/sh/lib/delay.c
+++ b/arch/sh/lib/delay.c
@@ -10,6 +10,16 @@
 void __delay(unsigned long loops)
 {
 	__asm__ __volatile__(
+		/*
+		 * ST40-300 appears to have an issue with this code,
+		 * normally taking two cycles each loop, as with all
+		 * other SH variants. If however the branch and the
+		 * delay slot straddle an 8 byte boundary, this increases
+		 * to 3 cycles.
+		 * This align directive ensures this doesn't occur.
+		 */
+		".balign 8\n\t"
+
 		"tst	%0, %0\n\t"
 		"1:\t"
 		"bf/s	1b\n\t"
diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c
index 88d3dc3d30d50aabcbdfcff04ac197cf19470bb7..5a580ea04429801eef9bda7d3301c8311492989e 100644
--- a/arch/sh/mm/cache.c
+++ b/arch/sh/mm/cache.c
@@ -108,7 +108,8 @@ void copy_user_highpage(struct page *to, struct page *from,
 		kunmap_atomic(vfrom, KM_USER0);
 	}
 
-	if (pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK))
+	if (pages_do_alias((unsigned long)vto, vaddr & PAGE_MASK) ||
+	    (vma->vm_flags & VM_EXEC))
 		__flush_purge_region(vto, PAGE_SIZE);
 
 	kunmap_atomic(vto, KM_USER1);