[IA64] implement csum_ipv6_magic for ia64.

The asm version is 4.4 times faster than the generic C version and
10X smaller in code size.
Signed-off-by: NKen Chen <kenneth.w.chen@intel.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>

arch/ia64/lib/ip_fast_csum.S

@@ -8,8 +8,8 @@
  *      in0: address of buffer to checksum (char *)
  *      in1: length of the buffer (int)
  *
- * Copyright (C) 2002 Intel Corp.
- * Copyright (C) 2002 Ken Chen <kenneth.w.chen@intel.com>
+ * Copyright (C) 2002, 2006 Intel Corp.
+ * Copyright (C) 2002, 2006 Ken Chen <kenneth.w.chen@intel.com>
  */
 
 #include <asm/asmmacro.h>
@@ -25,6 +25,9 @@
 
 #define in0	r32
 #define in1	r33
+#define in2	r34
+#define in3	r35
+#define in4	r36
 #define ret0	r8
 
 GLOBAL_ENTRY(ip_fast_csum)
@@ -88,3 +91,51 @@ GLOBAL_ENTRY(ip_fast_csum)
 	mov	b0=r34
 	br.ret.sptk.many b0
 END(ip_fast_csum)
+
+GLOBAL_ENTRY(csum_ipv6_magic)
+	ld4	r20=[in0],4
+	ld4	r21=[in1],4
+	dep	r15=in3,in2,32,16
+	;;
+	ld4	r22=[in0],4
+	ld4	r23=[in1],4
+	mux1	r15=r15,@rev
+	;;
+	ld4	r24=[in0],4
+	ld4	r25=[in1],4
+	shr.u	r15=r15,16
+	add	r16=r20,r21
+	add	r17=r22,r23
+	;;
+	ld4	r26=[in0],4
+	ld4	r27=[in1],4
+	add	r18=r24,r25
+	add	r8=r16,r17
+	;;
+	add	r19=r26,r27
+	add	r8=r8,r18
+	;;
+	add	r8=r8,r19
+	add	r15=r15,in4
+	;;
+	add	r8=r8,r15
+	;;
+	shr.u	r10=r8,32	// now fold sum into short
+	zxt4	r11=r8
+	;;
+	add	r8=r10,r11
+	;;
+	shr.u	r10=r8,16	// yeah, keep it rolling
+	zxt2	r11=r8
+	;;
+	add	r8=r10,r11
+	;;
+	shr.u	r10=r8,16	// three times lucky
+	zxt2	r11=r8
+	;;
+	add	r8=r10,r11
+	mov	r9=0xffff
+	;;
+	andcm	r8=r9,r8
+	br.ret.sptk.many b0
+END(csum_ipv6_magic)

include/asm-ia64/checksum.h

@@ -70,4 +70,10 @@ static inline __sum16 csum_fold(__wsum csum)
 	return (__force __sum16)~sum;
 }
 
+#define _HAVE_ARCH_IPV6_CSUM	1
+struct in6_addr;
+extern unsigned short int csum_ipv6_magic(struct in6_addr *saddr,
+	struct in6_addr *daddr, __u32 len, unsigned short proto,
+	unsigned int csum);
+
 #endif /* _ASM_IA64_CHECKSUM_H */