riscv: optimized memmove

When the destination buffer is before the source one, or when the
buffers doesn't overlap, it's safe to use memcpy() instead, which is
optimized to use a bigger data size possible.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>

arch/riscv/include/asm/string.h

@@ -17,11 +17,11 @@ extern asmlinkage void *__memset(void *, int, size_t);
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *dest, const void *src, size_t count);
 extern void *__memcpy(void *dest, const void *src, size_t count);
+#define __HAVE_ARCH_MEMMOVE
+extern void *memmove(void *dest, const void *src, size_t count);
+extern void *__memmove(void *dest, const void *src, size_t count);
 #endif
 
-#define __HAVE_ARCH_MEMMOVE
-extern asmlinkage void *memmove(void *, const void *, size_t);
-extern asmlinkage void *__memmove(void *, const void *, size_t);
 /* For those files which don't want to check by kasan. */
 #if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__)
 #define memcpy(dst, src, len) __memcpy(dst, src, len)

arch/riscv/kernel/riscv_ksyms.c

@@ -10,6 +10,4 @@
  * Assembly functions that may be used (directly or indirectly) by modules
  */
 EXPORT_SYMBOL(memset);
-EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__memset);
-EXPORT_SYMBOL(__memmove);

arch/riscv/lib/Makefile

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 lib-y			+= delay.o
 lib-y			+= memset.o
-lib-y			+= memmove.o
 lib-$(CONFIG_MMU)	+= uaccess.o
 lib-$(CONFIG_64BIT)	+= tishift.o
 lib-$(CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE) += string.o

arch/riscv/lib/string.c

@@ -89,3 +89,26 @@ EXPORT_SYMBOL(__memcpy);
 
 void *memcpy(void *dest, const void *src, size_t count) __weak __alias(__memcpy);
 EXPORT_SYMBOL(memcpy);
+
+/*
+ * Simply check if the buffer overlaps an call memcpy() in case,
+ * otherwise do a simple one byte at time backward copy.
+ */
+void *__memmove(void *dest, const void *src, size_t count)
+{
+	if (dest < src || src + count <= dest)
+		return memcpy(dest, src, count);
+
+	if (dest > src) {
+		const char *s = src + count;
+		char *tmp = dest + count;
+
+		while (count--)
+			*--tmp = *--s;
+	}
+	return dest;
+}
+EXPORT_SYMBOL(__memmove);
+
+void *memmove(void *dest, const void *src, size_t count) __weak __alias(__memmove);
+EXPORT_SYMBOL(memmove);