cpuidle, ACPI: Make noinstr clean

objtool found cases where ACPI methods called out into instrumentation code:

vmlinux.o: warning: objtool: io_idle+0xc: call to __inb.isra.0() leaves .noinstr.text section
vmlinux.o: warning: objtool: acpi_idle_enter+0xfe: call to num_online_cpus() leaves .noinstr.text section
vmlinux.o: warning: objtool: acpi_idle_enter+0x115: call to acpi_idle_fallback_to_c1.isra.0() leaves .noinstr.text section

Fix this by: marking the IO in/out, acpi_idle_fallback_to_c1() and
num_online_cpus() methods as __always_inline.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>
Tested-by: Tony Lindgren <[e-mail]>
Tested-by: Ulf Hansson <[e-mail]>
Acked-by: Rafael J. Wysocki <[e-mail]>
Acked-by: Frederic Weisbecker <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/x86/include/asm/shared/io.h

···
 #include <linux/types.h>
 
 #define BUILDIO(bwl, bw, type)						\
-static inline void __out##bwl(type value, u16 port)			\
+static __always_inline void __out##bwl(type value, u16 port)		\
 {									\
 	asm volatile("out" #bwl " %" #bw "0, %w1"			\
 		     : : "a"(value), "Nd"(port));			\
 }									\
 									\
-static inline type __in##bwl(u16 port)					\
+static __always_inline type __in##bwl(u16 port)				\
 {									\
 	type value;							\
 	asm volatile("in" #bwl " %w1, %" #bw "0"			\

drivers/acpi/processor_idle.c

···
 	return 0;
 }
 
-static bool acpi_idle_fallback_to_c1(struct acpi_processor *pr)
+static __always_inline bool acpi_idle_fallback_to_c1(struct acpi_processor *pr)
 {
 	return IS_ENABLED(CONFIG_HOTPLUG_CPU) && !pr->flags.has_cst &&
 		!(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED);

include/linux/cpumask.h

···
  * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
  * region.
  */
-static inline unsigned int num_online_cpus(void)
+static __always_inline unsigned int num_online_cpus(void)
 {
-	return atomic_read(&__num_online_cpus);
+	return arch_atomic_read(&__num_online_cpus);
 }
 #define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)