UPSTREAM: arm64: make cpu number a percpu variable

In the absence of CONFIG_THREAD_INFO_IN_TASK, core code maintains
thread_info::cpu, and low-level architecture code can access this to
build raw_smp_processor_id(). With CONFIG_THREAD_INFO_IN_TASK, core code
maintains task_struct::cpu, which for reasons of hte header soup is not
accessible to low-level arch code.

Instead, we can maintain a percpu variable containing the cpu number.

For both the old and new implementation of raw_smp_processor_id(), we
read a syreg into a GPR, add an offset, and load the result. As the
offset is now larger, it may not be folded into the load, but otherwise
the assembly shouldn't change much.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Cc: James Morse <james.morse@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Bug: 38331309
Change-Id: I154927b0f9fc0ebbbed88c9958408bbb19cf09de
(cherry picked from commit 57c82954e77fa12c1023e87210d2ede77aaa0058)
Signed-off-by: Zubin Mithra <zsm@google.com>

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;
 

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;