sh: move xchg_cmpxchg to a header by itself

Looks like future sh variants will support a 4-byte cas which will be
used to implement 1 and 2 byte xchg.

This is exactly what we do for llsc now, move the portable part of the
code into a separate header so it's easy to reuse.
Suggested-by: NRich Felker <dalias@libc.org>
Signed-off-by: NMichael S. Tsirkin <mst@redhat.com>
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>

arch/sh/include/asm/cmpxchg-llsc.h

 #ifndef __ASM_SH_CMPXCHG_LLSC_H
 #define __ASM_SH_CMPXCHG_LLSC_H
 
-#include <linux/bitops.h>
-#include <asm/byteorder.h>
-
 static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 {
 	unsigned long retval;
@@ -50,36 +47,6 @@ __cmpxchg_u32(volatile u32 *m, unsigned long old, unsigned long new)
 	return retval;
 }
 
-static inline u32 __xchg_cmpxchg(volatile void *ptr, u32 x, int size)
-{
-	int off = (unsigned long)ptr % sizeof(u32);
-	volatile u32 *p = ptr - off;
-#ifdef __BIG_ENDIAN
-	int bitoff = (sizeof(u32) - 1 - off) * BITS_PER_BYTE;
-#else
-	int bitoff = off * BITS_PER_BYTE;
-#endif
-	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
-	u32 oldv, newv;
-	u32 ret;
-
-	do {
-		oldv = READ_ONCE(*p);
-		ret = (oldv & bitmask) >> bitoff;
-		newv = (oldv & ~bitmask) | (x << bitoff);
-	} while (__cmpxchg_u32(p, oldv, newv) != oldv);
-
-	return ret;
-}
-
-static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
-{
-	return __xchg_cmpxchg(m, val, sizeof *m);
-}
-
-static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
-{
-	return __xchg_cmpxchg(m, val, sizeof *m);
-}
+#include <asm/cmpxchg-xchg.h>
 
 #endif /* __ASM_SH_CMPXCHG_LLSC_H */

arch/sh/include/asm/cmpxchg-xchg.h

+#ifndef __ASM_SH_CMPXCHG_XCHG_H
+#define __ASM_SH_CMPXCHG_XCHG_H
+
+/*
+ * Copyright (C) 2016 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See the
+ * file "COPYING" in the main directory of this archive for more details.
+ */
+#include <linux/bitops.h>
+#include <asm/byteorder.h>
+
+/*
+ * Portable implementations of 1 and 2 byte xchg using a 4 byte cmpxchg.
+ * Note: this header isn't self-contained: before including it, __cmpxchg_u32
+ * must be defined first.
+ */
+static inline u32 __xchg_cmpxchg(volatile void *ptr, u32 x, int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - 1 - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 oldv, newv;
+	u32 ret;
+
+	do {
+		oldv = READ_ONCE(*p);
+		ret = (oldv & bitmask) >> bitoff;
+		newv = (oldv & ~bitmask) | (x << bitoff);
+	} while (__cmpxchg_u32(p, oldv, newv) != oldv);
+
+	return ret;
+}
+
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+	return __xchg_cmpxchg(m, val, sizeof *m);
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	return __xchg_cmpxchg(m, val, sizeof *m);
+}
+
+#endif /* __ASM_SH_CMPXCHG_XCHG_H */