x86: Put hot per CPU variables into a struct

The layout of per-cpu variables is at the mercy of the compiler. This
can lead to random performance fluctuations from build to build.

Create a structure to hold some of the hottest per-cpu variables,
starting with current_task.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111145.179707194@infradead.org

arch/x86/include/asm/current.h

@@ -3,16 +3,29 @@
 #define _ASM_X86_CURRENT_H
 
 #include <linux/compiler.h>
-#include <asm/percpu.h>
 
 #ifndef __ASSEMBLY__
+
+#include <linux/cache.h>
+#include <asm/percpu.h>
+
 struct task_struct;
 
-DECLARE_PER_CPU(struct task_struct *, current_task);
+struct pcpu_hot {
+	union {
+		struct {
+			struct task_struct	*current_task;
+		};
+		u8	pad[64];
+	};
+};
+static_assert(sizeof(struct pcpu_hot) == 64);
+
+DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return this_cpu_read_stable(current_task);
+	return this_cpu_read_stable(pcpu_hot.current_task);
 }
 
 #define current get_current()

arch/x86/kernel/cpu/common.c

@@ -2012,18 +2012,16 @@ static __init int setup_clearcpuid(char *arg)
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
+DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
+	.current_task	= &init_task,
+};
+EXPORT_PER_CPU_SYMBOL(pcpu_hot);
+
 #ifdef CONFIG_X86_64
 DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
 		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
 EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
-/*
- * The following percpu variables are hot.  Align current_task to
- * cacheline size such that they fall in the same cacheline.
- */
-DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
-	&init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
 
 DEFINE_PER_CPU(void *, hardirq_stack_ptr);
 DEFINE_PER_CPU(bool, hardirq_stack_inuse);
@@ -2083,8 +2081,6 @@ void syscall_init(void)
 
 #else	/* CONFIG_X86_64 */
 
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 

arch/x86/kernel/process_32.c

@@ -207,7 +207,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (prev->gs | next->gs)
 		loadsegment(gs, next->gs);
 
-	this_cpu_write(current_task, next_p);
+	raw_cpu_write(pcpu_hot.current_task, next_p);
 
 	switch_fpu_finish();
 

arch/x86/kernel/process_64.c

@@ -617,7 +617,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	this_cpu_write(current_task, next_p);
+	raw_cpu_write(pcpu_hot.current_task, next_p);
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	switch_fpu_finish();

arch/x86/kernel/smpboot.c

@@ -1046,7 +1046,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 	/* Just in case we booted with a single CPU. */
 	alternatives_enable_smp();
 
-	per_cpu(current_task, cpu) = idle;
+	per_cpu(pcpu_hot.current_task, cpu) = idle;
 	cpu_init_stack_canary(cpu, idle);
 
 	/* Initialize the interrupt stack(s) */