Bringing a secondary CPU online is a special case in which, accessing
the cpu_online_mask is safe, even though that task (which running on the
CPU coming online) is not the hotplug writer.

It is a little hard to teach this to the debugging checks under
CONFIG_DEBUG_HOTPLUG_CPU. But luckily powerpc is one of the few places
where the CPU coming online traverses the cpu_online_mask before fully
coming online. So wrap that part under get/put_online_cpus_atomic(), to
avoid false-positive warnings from the CPU hotplug debug code.

Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <redacted>
Cc: Kumar Gala <redacted>
Cc: Zhao Chenhui <redacted>
Cc: Thomas Gleixner <redacted>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Srivatsa S. Bhat <redacted>
---

 arch/powerpc/kernel/smp.c |    2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 2123bec..59c9a09 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c

@@ -657,6 +657,7 @@ __cpuinit void start_secondary(void *unused)
 		cpumask_set_cpu(base + i, cpu_core_mask(cpu));
 	}
 	l2_cache = cpu_to_l2cache(cpu);
+	get_online_cpus_atomic();
 	for_each_online_cpu(i) {
 		struct device_node *np = cpu_to_l2cache(i);
 		if (!np)

@@ -667,6 +668,7 @@ __cpuinit void start_secondary(void *unused)
 		}
 		of_node_put(np);
 	}
+	put_online_cpus_atomic();
 	of_node_put(l2_cache);
 
 	local_irq_enable();