x86/asm/entry: Unify and fix initial thread_struct::sp0 values

x86_32 and x86_64 need slightly different thread_struct::sp0 values, and
x86_32's was incorrect for init.

This never mattered -- the init thread never runs user code, so we never
used thread_struct::sp0 for anything.

Fix it and mostly unify them.
Signed-off-by: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1b810c1d2e797e27bb4a7708c426101161edd1f6.1426009661.git.luto@amacapital.netSigned-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/include/asm/processor.h

@@ -811,6 +811,9 @@ static inline void spin_lock_prefetch(const void *x)
 	prefetchw(x);
 }
 
+#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \
+			   TOP_OF_KERNEL_STACK_PADDING)
+
 #ifdef CONFIG_X86_32
 /*
  * User space process size: 3GB (default).
@@ -821,7 +824,7 @@ static inline void spin_lock_prefetch(const void *x)
 #define STACK_TOP_MAX		STACK_TOP
 
 #define INIT_THREAD  {							  \
-	.sp0			= sizeof(init_stack) + (long)&init_stack, \
+	.sp0			= TOP_OF_INIT_STACK,			  \
 	.vm86_info		= NULL,					  \
 	.sysenter_cs		= __KERNEL_CS,				  \
 	.io_bitmap_ptr		= NULL,					  \
@@ -883,7 +886,7 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
 #define INIT_THREAD  { \
-	.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
+	.sp0 = TOP_OF_INIT_STACK \
 }
 
 /*

arch/x86/kernel/process.c

@@ -39,7 +39,7 @@
  */
 __visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, cpu_tss) = {
 	.x86_tss = {
-		.sp0 = (unsigned long)&init_stack + sizeof(init_stack),
+		.sp0 = TOP_OF_INIT_STACK,
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
 		.ss1 = __KERNEL_CS,