x86/apic: Use non-atomic operations when possible

Using __clear_bit() and __cpumask_clear_cpu() is more efficient than using
their atomic counterparts.

Use them when atomicity is not needed, such as when manipulating bitmasks
that are on the stack.

Signed-off-by: Nadav Amit <[e-mail]>
Signed-off-by: Thomas Gleixner <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Andy Lutomirski <[e-mail]>
Cc: Borislav Petkov <[e-mail]>
Cc: Dave Hansen <[e-mail]>
Link: https://lkml.kernel.org/r/[e-mail]

arch/x86/kernel/apic/apic_flat_64.c

···
 	int cpu = smp_processor_id();
 
 	if (cpu < BITS_PER_LONG)
-		clear_bit(cpu, &mask);
+		__clear_bit(cpu, &mask);
 
 	_flat_send_IPI_mask(mask, vector);
 }
···
 			unsigned long mask = cpumask_bits(cpu_online_mask)[0];
 
 			if (cpu < BITS_PER_LONG)
-				clear_bit(cpu, &mask);
+				__clear_bit(cpu, &mask);
 
 			_flat_send_IPI_mask(mask, vector);
 		}

arch/x86/kernel/apic/x2apic_cluster.c

···
 	cpumask_copy(tmpmsk, mask);
 	/* If IPI should not be sent to self, clear current CPU */
 	if (apic_dest != APIC_DEST_ALLINC)
-		cpumask_clear_cpu(smp_processor_id(), tmpmsk);
+		__cpumask_clear_cpu(smp_processor_id(), tmpmsk);
 
 	/* Collapse cpus in a cluster so a single IPI per cluster is sent */
 	for_each_cpu(cpu, tmpmsk) {

arch/x86/kernel/smp.c

···
 	}
 
 	cpumask_copy(allbutself, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), allbutself);
+	__cpumask_clear_cpu(smp_processor_id(), allbutself);
 
 	if (cpumask_equal(mask, allbutself) &&
 	    cpumask_equal(cpu_online_mask, cpu_callout_mask))