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>

1 files changed, 4 insertions, 2 deletions

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a0c2ca602cf8..b5d2031c12c6 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -122,8 +122,6 @@ asmlinkage void secondary_start_kernel(void)
 	struct mm_struct *mm = &init_mm;
 	unsigned int cpu = smp_processor_id();
 
-	printk("CPU%u: Booted secondary processor\n", cpu);
-
 	/*
 	 * All kernel threads share the same mm context; grab a
 	 * reference and switch to it.
@@ -132,6 +130,9 @@ asmlinkage void secondary_start_kernel(void)
 	current->active_mm = mm;
 	cpumask_set_cpu(cpu, mm_cpumask(mm));
 
+	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	printk("CPU%u: Booted secondary processor\n", cpu);
+
 	/*
 	 * TTBR0 is only used for the identity mapping at this stage. Make it
 	 * point to zero page to avoid speculatively fetching new entries.
@@ -271,6 +272,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 
 void __init smp_prepare_boot_cpu(void)
 {
+	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
 }
 
 static void (*smp_cross_call)(const struct cpumask *, unsigned int);