sh/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()

The mmiowb() macro is horribly difficult to use and drivers will continue
to work most of the time if they omit a call when it is required.

Rather than rely on driver authors getting this right, push mmiowb() into
arch_spin_unlock() for sh. If this is deemed to be a performance issue,
a subsequent optimisation could make use of ARCH_HAS_MMIOWB to elide
the barrier in cases where no I/O writes were performed inside the
critical section.

Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/sh/include/asm/Kbuild

@@ -14,7 +14,6 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mmiowb.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h

arch/sh/include/asm/io.h

@@ -229,9 +229,6 @@ __BUILD_IOPORT_STRING(q, u64)
 
 #define IO_SPACE_LIMIT 0xffffffff
 
-/* synco on SH-4A, otherwise a nop */
-#define mmiowb()		wmb()
-
 /* We really want to try and get these to memcpy etc */
 void memcpy_fromio(void *, const volatile void __iomem *, unsigned long);
 void memcpy_toio(volatile void __iomem *, const void *, unsigned long);

arch/sh/include/asm/mmiowb.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_SH_MMIOWB_H
+#define __ASM_SH_MMIOWB_H
+
+#include <asm/barrier.h>
+
+/* synco on SH-4A, otherwise a nop */
+#define mmiowb()			wmb()
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* __ASM_SH_MMIOWB_H */

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

@@ -47,6 +47,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
 
+	/* This could be optimised with ARCH_HAS_MMIOWB */
+	mmiowb();
 	__asm__ __volatile__ (
 		"mov		#1, %0 ! arch_spin_unlock	\n\t"
 		"mov.l		%0, @%1				\n\t"