arm64: percpu: implement optimised pcpu access using tpidr_el1

This patch implements optimised percpu variable accesses using the
el1 r/w thread register (tpidr_el1) along the same lines as arch/arm/.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index bd9bbd0..97d9084 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -108,6 +108,16 @@
 	printk("%s", buf);
 }
 
+void __init smp_setup_processor_id(void)
+{
+	/*
+	 * clear __my_cpu_offset on boot CPU to avoid hang caused by
+	 * using percpu variable early, for example, lockdep will
+	 * access percpu variable inside lock_release
+	 */
+	set_my_cpu_offset(0);
+}
+
 bool arch_match_cpu_phys_id(int cpu, u64 phys_id)
 {
 	return phys_id == cpu_logical_map(cpu);