ARM: avoid unwanted GCC memset()/memcpy() optimisations for IO variants

We don't want GCC optimising our memset_io(), memcpy_fromio() or
memcpy_toio() variants, so we must not call one of the standard
functions.  Provide a separate name for our assembly memcpy() and
memset() functions, and use that instead, thereby bypassing GCC's
ability to optimise these operations.

GCCs optimisation may introduce unaligned accesses which are invalid
for device mappings.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

arch/arm/include/asm/io.h

@@ -316,21 +316,24 @@ extern void _memset_io(volatile void __iomem *, int, size_t);
 static inline void memset_io(volatile void __iomem *dst, unsigned c,
 	size_t count)
 {
-	memset((void __force *)dst, c, count);
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
 }
 #define memset_io(dst,c,count) memset_io(dst,c,count)
 
 static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
 	size_t count)
 {
-	memcpy(to, (const void __force *)from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
 }
 #define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
 
 static inline void memcpy_toio(volatile void __iomem *to, const void *from,
 	size_t count)
 {
-	memcpy((void __force *)to, from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
 }
 #define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
 

arch/arm/kernel/armksyms.c

@@ -50,6 +50,9 @@ extern void __aeabi_ulcmp(void);
 
 extern void fpundefinstr(void);
 
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
 	/* platform dependent support */
 EXPORT_SYMBOL(arm_delay_ops);
 
@@ -88,6 +91,9 @@ EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
+
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 

arch/arm/lib/memcpy.S

@@ -61,8 +61,10 @@
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
 
+ENTRY(mmiocpy)
 ENTRY(memcpy)
 
 #include "copy_template.S"
 
 ENDPROC(memcpy)
+ENDPROC(mmiocpy)

arch/arm/lib/memset.S

@@ -16,6 +16,7 @@
 	.text
 	.align	5
 
+ENTRY(mmioset)
 ENTRY(memset)
 UNWIND( .fnstart         )
 	ands	r3, r0, #3		@ 1 unaligned?
@@ -133,3 +134,4 @@ UNWIND( .fnstart            )
 	b	1b
 UNWIND( .fnend   )
 ENDPROC(memset)
+ENDPROC(mmioset)