sh: Split out atomic ops logically.

We have a few different ways to do the atomic operations, so split
them out in to different headers rather than bloating atomic.h.
Kernelspace gUSA will take this up to a third implementation.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>

include/asm-sh/atomic-irq.h

+#ifndef __ASM_SH_ATOMIC_IRQ_H
+#define __ASM_SH_ATOMIC_IRQ_H
+
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v += i;
+	local_irq_restore(flags);
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v -= i;
+	local_irq_restore(flags);
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long temp, flags;
+
+	local_irq_save(flags);
+	temp = *(long *)v;
+	temp += i;
+	*(long *)v = temp;
+	local_irq_restore(flags);
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long temp, flags;
+
+	local_irq_save(flags);
+	temp = *(long *)v;
+	temp -= i;
+	*(long *)v = temp;
+	local_irq_restore(flags);
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v &= ~mask;
+	local_irq_restore(flags);
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	*(long *)v |= mask;
+	local_irq_restore(flags);
+}
+
+#endif /* __ASM_SH_ATOMIC_IRQ_H */

include/asm-sh/atomic-llsc.h

+#ifndef __ASM_SH_ATOMIC_LLSC_H
+#define __ASM_SH_ATOMIC_LLSC_H
+
+/*
+ * To get proper branch prediction for the main line, we must branch
+ * forward to code at the end of this object's .text section, then
+ * branch back to restart the operation.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_add	\n"
+"	add	%1, %0				\n"
+"	movco.l	%0, @%2				\n"
+"	bf	1b				\n"
+	: "=&z" (tmp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_sub	\n"
+"	sub	%1, %0				\n"
+"	movco.l	%0, @%2				\n"
+"	bf	1b				\n"
+	: "=&z" (tmp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+}
+
+/*
+ * SH-4A note:
+ *
+ * We basically get atomic_xxx_return() for free compared with
+ * atomic_xxx(). movli.l/movco.l require r0 due to the instruction
+ * encoding, so the retval is automatically set without having to
+ * do any special work.
+ */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_add_return	\n"
+"	add	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+"	synco						\n"
+	: "=&z" (temp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+
+	return temp;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long temp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_sub_return	\n"
+"	sub	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+"	synco						\n"
+	: "=&z" (temp)
+	: "r" (i), "r" (&v->counter)
+	: "t");
+
+	return temp;
+}
+
+static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
+"	and	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+	: "=&z" (tmp)
+	: "r" (~mask), "r" (&v->counter)
+	: "t");
+}
+
+static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
+{
+	unsigned long tmp;
+
+	__asm__ __volatile__ (
+"1:	movli.l @%2, %0		! atomic_set_mask	\n"
+"	or	%1, %0					\n"
+"	movco.l	%0, @%2					\n"
+"	bf	1b					\n"
+	: "=&z" (tmp)
+	: "r" (mask), "r" (&v->counter)
+	: "t");
+}
+
+#endif /* __ASM_SH_ATOMIC_LLSC_H */

include/asm-sh/atomic.h

@@ -17,119 +17,14 @@ typedef struct { volatile int counter; } atomic_t;
 #include <linux/compiler.h>
 #include <asm/system.h>
 
-/*
- * To get proper branch prediction for the main line, we must branch
- * forward to code at the end of this object's .text section, then
- * branch back to restart the operation.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
 #ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_add	\n"
-"	add	%1, %0				\n"
-"	movco.l	%0, @%2				\n"
-"	bf	1b				\n"
-	: "=&z" (tmp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
+#include <asm/atomic-llsc.h>
 #else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v += i;
-	local_irq_restore(flags);
-#endif
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-#ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_sub	\n"
-"	sub	%1, %0				\n"
-"	movco.l	%0, @%2				\n"
-"	bf	1b				\n"
-	: "=&z" (tmp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v -= i;
-	local_irq_restore(flags);
+#include <asm/atomic-irq.h>
 #endif
-}
-
-/*
- * SH-4A note:
- *
- * We basically get atomic_xxx_return() for free compared with
- * atomic_xxx(). movli.l/movco.l require r0 due to the instruction
- * encoding, so the retval is automatically set without having to
- * do any special work.
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long temp;
-
-#ifdef CONFIG_CPU_SH4A
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_add_return	\n"
-"	add	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-"	synco						\n"
-	: "=&z" (temp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	temp = *(long *)v;
-	temp += i;
-	*(long *)v = temp;
-	local_irq_restore(flags);
-#endif
-
-	return temp;
-}
 
 #define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long temp;
-
-#ifdef CONFIG_CPU_SH4A
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_sub_return	\n"
-"	sub	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-"	synco						\n"
-	: "=&z" (temp)
-	: "r" (i), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	temp = *(long *)v;
-	temp -= i;
-	*(long *)v = temp;
-	local_irq_restore(flags);
-#endif
-
-	return temp;
-}
-
 #define atomic_dec_return(v) atomic_sub_return(1,(v))
 #define atomic_inc_return(v) atomic_add_return(1,(v))
 
@@ -180,50 +75,6 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 }
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-static inline void atomic_clear_mask(unsigned int mask, atomic_t *v)
-{
-#ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_clear_mask	\n"
-"	and	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (~mask), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v &= ~mask;
-	local_irq_restore(flags);
-#endif
-}
-
-static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
-{
-#ifdef CONFIG_CPU_SH4A
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-"1:	movli.l @%2, %0		! atomic_set_mask	\n"
-"	or	%1, %0					\n"
-"	movco.l	%0, @%2					\n"
-"	bf	1b					\n"
-	: "=&z" (tmp)
-	: "r" (mask), "r" (&v->counter)
-	: "t");
-#else
-	unsigned long flags;
-
-	local_irq_save(flags);
-	*(long *)v |= mask;
-	local_irq_restore(flags);
-#endif
-}
-
 /* Atomic operations are already serializing on SH */
 #define smp_mb__before_atomic_dec()	barrier()
 #define smp_mb__after_atomic_dec()	barrier()