optimize malloc0

Implementation of __malloc0 in malloc.c takes care to preserve zero
pages by overwriting only non-zero data. However, malloc must have
already modified auxiliary heap data just before and beyond the
allocated region, so we know that edge pages need not be preserved.

For allocations smaller than one page, pass them immediately to memset.
Otherwise, use memset to handle partial pages at the head and tail of
the allocation, and scan complete pages in the interior. Optimize the
scanning loop by processing 16 bytes per iteration and handling rest of
page via memset as soon as a non-zero byte is found.

1 files changed, 23 insertions, 6 deletions

diff --git a/src/malloc/malloc.c b/src/malloc/malloc.c
index 9e05e1d6..0a7d5d85 100644
--- a/src/malloc/malloc.c
+++ b/src/malloc/malloc.c
@@ -366,15 +366,32 @@ void *malloc(size_t n)
 	return CHUNK_TO_MEM(c);
 }
 
+static size_t mal0_clear(char *p, size_t pagesz, size_t n)
+{
+#ifdef __GNUC__
+	typedef uint64_t __attribute__((__may_alias__)) T;
+#else
+	typedef unsigned char T;
+#endif
+	char *pp = p + n;
+	size_t i = (uintptr_t)pp & (pagesz - 1);
+	for (;;) {
+		pp = memset(pp - i, 0, i);
+		if (pp - p < pagesz) return pp - p;
+		for (i = pagesz; i; i -= 2*sizeof(T), pp -= 2*sizeof(T))
+		        if (((T *)pp)[-1] | ((T *)pp)[-2])
+				break;
+	}
+}
+
 void *__malloc0(size_t n)
 {
 	void *p = malloc(n);
-	if (p && !IS_MMAPPED(MEM_TO_CHUNK(p))) {
-		size_t *z;
-		n = (n + sizeof *z - 1)/sizeof *z;
-		for (z=p; n; n--, z++) if (*z) *z=0;
-	}
-	return p;
+	if (!p || IS_MMAPPED(MEM_TO_CHUNK(p)))
+		return p;
+	if (n >= PAGE_SIZE)
+		n = mal0_clear(p, PAGE_SIZE, n);
+	return memset(p, 0, n);
 }
 
 void *realloc(void *p, size_t n)