diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index 2013a4dc5124..d7e851c5bc42 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -16,11 +16,20 @@
 #ifndef __ASM_SMP_H
 #define __ASM_SMP_H
 
+#include <asm/percpu.h>
+
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
 
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
+
+/*
+ * We don't use this_cpu_read(cpu_number) as that has implicit writes to
+ * preempt_count, and associated (compiler) barriers, that we'd like to avoid
+ * the expense of. If we're preemptible, the value can be stale at use anyway.
+ */
+#define raw_smp_processor_id() (*this_cpu_ptr(&cpu_number))
 
 struct seq_file;
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 8526ff64e4b2..0b66134345f7 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -57,6 +57,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
+
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
  * so we need some other way of telling a new secondary core
@@ -608,6 +611,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 		if (max_cpus == 0)
 			break;
 
+		per_cpu(cpu_number, cpu) = cpu;
+
 		if (cpu == smp_processor_id())
 			continue;