locking/atomic: arm: fix sync ops

The sync_*() ops on arch/arm are defined in terms of the regular bitops
with no special handling. This is not correct, as UP kernels elide
barriers for the fully-ordered operations, and so the required ordering
is lost when such UP kernels are run under a hypervsior on an SMP
system.

Fix this by defining sync ops with the required barriers.

Note: On 32-bit arm, the sync_*() ops are currently only used by Xen,
which requires ARMv7, but the semantics can be implemented for ARMv6+.

Fixes: e54d2f6152 ("xen/arm: sync_bitops")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20230605070124.3741859-2-mark.rutland@arm.com

arch/arm/include/asm/assembler.h

@@ -394,6 +394,23 @@ ALT_UP_B(.L0_\@)
 #endif
 	.endm
 
+/*
+ * Raw SMP data memory barrier
+ */
+	.macro	__smp_dmb mode
+#if __LINUX_ARM_ARCH__ >= 7
+	.ifeqs "\mode","arm"
+	dmb	ish
+	.else
+	W(dmb)	ish
+	.endif
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+#else
+	.error "Incompatible SMP platform"
+#endif
+	.endm
+
 #if defined(CONFIG_CPU_V7M)
 	/*
 	 * setmode is used to assert to be in svc mode during boot. For v7-M