[PATCH 3/3] lib/string: optimized memset

[Matteo Croce <mcroce@linux.microsoft.com>]

From: Matteo Croce <mcroce@microsoft.com>

The generic memset is defined as a byte at time write. This is always
safe, but it's slower than a 4 byte or even 8 byte write.

Write a generic memset which fills the data one byte at time until the
destination is aligned, then fills using the largest size allowed,
and finally fills the remaining data one byte at time.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>
---
 lib/string.c | 30 ++++++++++++++++++++++++++++--
 1 file changed, 28 insertions(+), 2 deletions(-)

diff --git a/lib/string.c b/lib/string.c
index 69adec252597..598ece5434e9 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -811,10 +811,36 @@ EXPORT_SYMBOL(__sysfs_match_string);
  */
 void *memset(void *s, int c, size_t count)
 {
-	char *xs = s;
+	union types dest = { .as_u8 = s };
 
+	if (count >= MIN_THRESHOLD) {
+		unsigned long cu = (unsigned long)c;
+
+		/* Compose an ulong with 'c' repeated 4/8 times */
+		cu |= cu << 8;
+		cu |= cu << 16;
+#if BITS_PER_LONG == 64
+		cu |= cu << 32;
+#endif
+
+		if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			/*
+			 * Fill the buffer one byte at time until
+			 * the destination is word aligned.
+			 */
+			for (; count && dest.as_uptr & word_mask; count--)
+				*dest.as_u8++ = c;
+		}
+
+		/* Copy using the largest size allowed */
+		for (; count >= bytes_long; count -= bytes_long)
+			*dest.as_ulong++ = cu;
+	}
+
+	/* copy the remainder */
 	while (count--)
-		*xs++ = c;
+		*dest.as_u8++ = c;
+
 	return s;
 }
 EXPORT_SYMBOL(memset);
-- 
2.31.1