[PATCH] lib: memcmp optimization

[Jack Wang]

From: Florian-Ewald Mueller <florian-ewald.mueller@xxxxxxxxxxxxxxxx>

During testing, I have configured 128 md/raid1's and, while under
heavy IO, I started a check on each of them
(echo check > /sys/block/mdx/md/sync_action).

The CPU utilization went through the ceiling and when looking for
the cause (with 'perf top'). I've discovered that ~50% of the time
was spend in memcmp() called from process_checks().

With this patch applied, it drops to 4% - 10%.

Signed-off-by: Florian-Ewald Mueller <florian-ewald.mueller@xxxxxxxxxxxxxxxx>
[jwang: reformat the commit message]
Signed-off-by: Jack Wang <jinpu.wang@xxxxxxxxxxxxxxxx>
---
 lib/string.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/lib/string.c b/lib/string.c
index 2c0900a5d51a..932ef9af2baa 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -852,7 +852,7 @@ EXPORT_SYMBOL(memmove);
  * @count: The size of the area.
  */
 #undef memcmp
-__visible int memcmp(const void *cs, const void *ct, size_t count)
+static inline int __memcmp(const void *cs, const void *ct, size_t count)
 {
 	const unsigned char *su1, *su2;
 	int res = 0;
@@ -862,6 +862,20 @@ __visible int memcmp(const void *cs, const void *ct, size_t count)
 			break;
 	return res;
 }
+__visible int memcmp(const void *cs, const void *ct, size_t count)
+{
+	const uint64_t *l1p = cs;
+	const uint64_t *l2p = ct;
+
+	while (count >= sizeof(*l1p)) {
+		if (*l1p != *l2p)
+			return __memcmp(l1p, l2p, sizeof(*l1p));
+		count -= sizeof(*l1p);
+		++l1p;
+		++l2p;
+	}
+	return __memcmp(l1p, l2p, count);
+}
 EXPORT_SYMBOL(memcmp);
 #endif
 
-- 
2.7.4