[PATCH 1/3] lib/string: optimized memcpy

[Matteo Croce]

From: Matteo Croce <mcroce at microsoft.com>

Rewrite the generic memcpy() to copy a word at time, without generating
unaligned accesses.

The procedure is made of three steps:
First copy data one byte at time until the destination buffer is aligned
to a long boundary.
Then copy the data one long at time shifting the current and the next long
to compose a long at every cycle.
Finally, copy the remainder one byte at time.

Signed-off-by: Matteo Croce <mcroce at microsoft.com>
---
 lib/string.c | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 78 insertions(+), 3 deletions(-)

diff --git a/lib/string.c b/lib/string.c
index 546d59711a12..15e906f97d9e 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -33,6 +33,24 @@
 #include <asm/word-at-a-time.h>
 #include <asm/page.h>
 
+#define MIN_THRESHOLD (sizeof(long) * 2)
+
+/* convenience union to avoid cast between different pointer types */
+union types {
+	u8 *as_u8;
+	unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+union const_types {
+	const u8 *as_u8;
+	const unsigned long *as_ulong;
+	uintptr_t as_uptr;
+};
+
+static const unsigned int bytes_long = sizeof(long);
+static const unsigned int word_mask = bytes_long - 1;
+
 #ifndef __HAVE_ARCH_STRNCASECMP
 /**
  * strncasecmp - Case insensitive, length-limited string comparison
@@ -878,16 +896,73 @@ EXPORT_SYMBOL(memset64);
  * You should not use this function to access IO space, use memcpy_toio()
  * or memcpy_fromio() instead.
  */
+
+#ifdef __BIG_ENDIAN
+#define MERGE_UL(h, l, d) ((h) << ((d) * 8) | (l) >> ((bytes_long - (d)) * 8))
+#else
+#define MERGE_UL(h, l, d) ((h) >> ((d) * 8) | (l) << ((bytes_long - (d)) * 8))
+#endif
+
 void *memcpy(void *dest, const void *src, size_t count)
 {
-	char *tmp = dest;
-	const char *s = src;
+	union const_types s = { .as_u8 = src };
+	union types d = { .as_u8 = dest };
+	int distance = 0;
+
+	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+		if (count < MIN_THRESHOLD)
+			goto copy_remainder;
+
+		/* Copy a byte at time until destination is aligned. */
+		for (; d.as_uptr & word_mask; count--)
+			*d.as_u8++ = *s.as_u8++;
+
+		distance = s.as_uptr & word_mask;
+	}
 
+	if (distance) {
+		unsigned long last, next;
+
+		/*
+		 * s is distance bytes ahead of d, and d just reached
+		 * the alignment boundary. Move s backward to word align it
+		 * and shift data to compensate for distance, in order to do
+		 * word-by-word copy.
+		 */
+		s.as_u8 -= distance;
+
+		next = s.as_ulong[0];
+		for (; count >= bytes_long + word_mask; count -= bytes_long) {
+			last = next;
+			next = s.as_ulong[1];
+
+			d.as_ulong[0] = MERGE_UL(last, next, distance);
+
+			d.as_ulong++;
+			s.as_ulong++;
+		}
+
+		/* Restore s with the original offset. */
+		s.as_u8 += distance;
+	} else {
+		/*
+		 * If the source and dest lower bits are the same, do a simple
+		 * 32/64 bit wide copy.
+		 */
+		for (; count >= bytes_long; count -= bytes_long)
+			*d.as_ulong++ = *s.as_ulong++;
+	}
+
+copy_remainder:
 	while (count--)
-		*tmp++ = *s++;
+		*d.as_u8++ = *s.as_u8++;
+
 	return dest;
 }
 EXPORT_SYMBOL(memcpy);
+
+#undef MERGE_UL
+
 #endif
 
 #ifndef __HAVE_ARCH_MEMMOVE
-- 
2.31.1