x86, percpu: Collect hot percpu variables into one cacheline

On x86_64, percpu variables current_task and kernel_stack are used for
get_current() and current_thread_info() respectively and thus are
often used close to each other.  Move definition of current_task to
kernel/cpu/common.c right above kernel_stack definition and align it
to cacheline so that they always fall into the same cacheline.  Two
percpu variables defined there together - irq_stack_ptr and irq_count
- are also pretty hot and will benefit from sharing the cacheline.

For consistency, current_task definition for x86_32 is also moved to
kernel/cpu/common.c.

Putting current_task and kernel_stack into the same cacheline was
suggested by Linus Torvalds.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

arch/x86/kernel/cpu/common.c

@@ -987,13 +987,21 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE);
 
-DEFINE_PER_CPU(char *, irq_stack_ptr) =
-	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
+/*
+ * The following four percpu variables are hot.  Align current_task to
+ * cacheline size such that all four 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(unsigned long, kernel_stack) =
 	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
 EXPORT_PER_CPU_SYMBOL(kernel_stack);
 
+DEFINE_PER_CPU(char *, irq_stack_ptr) =
+	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
+
 DEFINE_PER_CPU(unsigned int, irq_count) = -1;
 
 /*
@@ -1041,6 +1049,9 @@ DEFINE_PER_CPU(struct orig_ist, orig_ist);
 
 #else	/* CONFIG_X86_64 */
 
+DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
+EXPORT_PER_CPU_SYMBOL(current_task);
+
 #ifdef CONFIG_CC_STACKPROTECTOR
 DEFINE_PER_CPU(unsigned long, stack_canary);
 #endif

arch/x86/kernel/process_32.c

@@ -61,9 +61,6 @@
 
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-
 /*
  * Return saved PC of a blocked thread.
  */

arch/x86/kernel/process_64.c

@@ -55,9 +55,6 @@
 
 asmlinkage extern void ret_from_fork(void);
 
-DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
-EXPORT_PER_CPU_SYMBOL(current_task);
-
 DEFINE_PER_CPU(unsigned long, old_rsp);
 static DEFINE_PER_CPU(unsigned char, is_idle);