smp_call_function_map() was not safe against preemption to another
cpu: its test for removing self from map was outside the spinlock.
Rearrange it a little to fix that.

smp_call_function_single() was also wrong: now get_cpu() before
excluding self, as other architectures do.
Signed-off-by: NHugh Dickins <hugh@veritas.com>
Signed-off-by: NPaul Mackerras <paulus@samba.org>