tools/nolibc/string: slightly simplify memmove()

The direction test inside the loop was not always completely optimized,
resulting in a larger than necessary function. This change adds a
direction variable that is set out of the loop. Now the function is down
to 48 bytes on x86, 32 on ARM and 68 on mips. It's worth noting that other
approaches were attempted (including relying on the up and down functions)
but they were only slightly beneficial on x86 and cost more on others.

Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

1 files changed, 14 insertions, 6 deletions

diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
index 6d8fad7a92e6..b831a02de83f 100644
--- a/tools/include/nolibc/string.h
+++ b/tools/include/nolibc/string.h
@@ -50,14 +50,22 @@ void *_nolibc_memcpy_down(void *dst, const void *src, size_t len)
 static __attribute__((unused))
 void *memmove(void *dst, const void *src, size_t len)
 {
-	ssize_t pos = (dst <= src) ? -1 : (long)len;
-	void *ret = dst;
+	size_t dir, pos;
 
-	while (len--) {
-		pos += (dst <= src) ? 1 : -1;
-		((char *)dst)[pos] = ((char *)src)[pos];
+	pos = len;
+	dir = -1;
+
+	if (dst < src) {
+		pos = -1;
+		dir = 1;
 	}
-	return ret;
+
+	while (len) {
+		pos += dir;
+		((char *)dst)[pos] = ((const char *)src)[pos];
+		len--;
+	}
+	return dst;
 }
 
 /* must be exported, as it's used by libgcc on ARM */