x86-64: Move oldrsp from PDA to per-cpu.

tj: * in asm-offsets_64.c, pda.h inclusion shouldn't be removed as pda
      is still referenced in the file
    * s/oldrsp/old_rsp/

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 6c5f576..4801289 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -60,6 +60,8 @@
 DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
+DEFINE_PER_CPU(unsigned long, old_rsp);
+
 unsigned long kernel_thread_flags = CLONE_VM | CLONE_UNTRACED;
 
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
@@ -395,7 +397,7 @@
 	load_gs_index(0);
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
-	write_pda(oldrsp, new_sp);
+	percpu_write(old_rsp, new_sp);
 	regs->cs		= __USER_CS;
 	regs->ss		= __USER_DS;
 	regs->flags		= 0x200;
@@ -616,8 +618,8 @@
 	/*
 	 * Switch the PDA and FPU contexts.
 	 */
-	prev->usersp = read_pda(oldrsp);
-	write_pda(oldrsp, next->usersp);
+	prev->usersp = percpu_read(old_rsp);
+	percpu_write(old_rsp, next->usersp);
 	percpu_write(current_task, next_p);
 
 	percpu_write(kernel_stack,