x86, setup: Use string copy operation to optimze copy in kernel compression

The kernel decompression code parses the ELF header and then copies
the segment to the corresponding destination.  Currently it uses slow
byte-copy code.  This patch makes it use the string copy operations
instead.

In the test the copy performance can be improved very significantly after using
the string copy operation mechanism.
        1. The copy time can be reduced from 150ms to 20ms on one Atom machine
	2. The copy time can be reduced about 80% on another machine
		The time is reduced from 7ms to 1.5ms when using 32-bit kernel.
		The time is reduced from 10ms to 2ms when using 64-bit kernel.

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
LKML-Reference: <1286502453-7043-1-git-send-email-yakui.zhao@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

arch/x86/boot/compressed/misc.c

@@ -229,18 +229,35 @@ void *memset(void *s, int c, size_t n)
 		ss[i] = c;
 	return s;
 }
-
+#ifdef CONFIG_X86_32
 void *memcpy(void *dest, const void *src, size_t n)
 {
-	int i;
-	const char *s = src;
-	char *d = dest;
+	int d0, d1, d2;
+	asm volatile(
+		"rep ; movsl\n\t"
+		"movl %4,%%ecx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
+		: "memory");
 
-	for (i = 0; i < n; i++)
-		d[i] = s[i];
 	return dest;
 }
+#else
+void *memcpy(void *dest, const void *src, size_t n)
+{
+	long d0, d1, d2;
+	asm volatile(
+		"rep ; movsq\n\t"
+		"movq %4,%%rcx\n\t"
+		"rep ; movsb\n\t"
+		: "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
+		: "memory");
 
+	return dest;
+}
+#endif
 
 static void error(char *x)
 {