[PATCH v2 3/3] lib/string: optimized memset

[Matteo Croce]

From: Matteo Croce <mcroce@xxxxxxxxxxxxx>

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.

On a RISC-V machine the speed goes from 140 Mb/s to 241 Mb/s,
and this the binary size increase according to bloat-o-meter:

Function     old     new   delta
memset        32     148    +116

Signed-off-by: Matteo Croce <mcroce@xxxxxxxxxxxxx>
---
 lib/string.c | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/lib/string.c b/lib/string.c
index 108b83c34cec..264821f0e795 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -810,10 +810,38 @@ 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 */
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+		cu *= 0x0101010101010101UL;
+#else
+		cu |= cu << 8;
+		cu |= cu << 16;
+		/* Suppress warning on 32 bit machines */
+		cu |= (cu << 16) << 16;
+#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