x86/percpu: Move cpu_number next to current_task

Also add cpu_number to the pcpu_hot structure, it is often referenced
and this cacheline is there.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111145.387678283@infradead.org

arch/x86/include/asm/current.h

@@ -16,6 +16,7 @@ struct pcpu_hot {
 		struct {
 			struct task_struct	*current_task;
 			int			preempt_count;
+			int			cpu_number;
 		};
 		u8	pad[64];
 	};

arch/x86/include/asm/smp.h

@@ -3,10 +3,10 @@
 #define _ASM_X86_SMP_H
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
-#include <asm/percpu.h>
 
-#include <asm/thread_info.h>
 #include <asm/cpumask.h>
+#include <asm/current.h>
+#include <asm/thread_info.h>
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
@@ -19,7 +19,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
 DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id);
-DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid);
@@ -150,11 +149,10 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
 
 /*
  * This function is needed by all SMP systems. It must _always_ be valid
- * from the initial startup. We map APIC_BASE very early in page_setup(),
- * so this is correct in the x86 case.
+ * from the initial startup.
  */
-#define raw_smp_processor_id()  this_cpu_read(cpu_number)
-#define __smp_processor_id() __this_cpu_read(cpu_number)
+#define raw_smp_processor_id()  this_cpu_read(pcpu_hot.cpu_number)
+#define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number)
 
 #ifdef CONFIG_X86_32
 extern int safe_smp_processor_id(void);

arch/x86/kernel/setup_percpu.c

@@ -23,9 +23,6 @@
 #include <asm/cpu.h>
 #include <asm/stackprotector.h>
 
-DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
-EXPORT_PER_CPU_SYMBOL(cpu_number);
-
 #ifdef CONFIG_X86_64
 #define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
 #else
@@ -172,7 +169,7 @@ void __init setup_per_cpu_areas(void)
 	for_each_possible_cpu(cpu) {
 		per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu];
 		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
-		per_cpu(cpu_number, cpu) = cpu;
+		per_cpu(pcpu_hot.cpu_number, cpu) = cpu;
 		setup_percpu_segment(cpu);
 		/*
 		 * Copy data used in early init routines from the