x86/entry/64: Remove thread_struct::sp0

On x86_64, we can easily calculate sp0 when needed instead of
storing it in thread_struct.

On x86_32, a similar cleanup would be possible, but it would require
cleaning up the vm86 code first, and that can wait for a later
cleanup series.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bpetkov@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/719cd9c66c548c4350d98a90f050aee8b17f8919.1509609304.git.luto@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 16 insertions, 20 deletions

diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 5343c19814b3..948b6d8ec46f 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -6,6 +6,7 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <asm/processor.h>
 #include <asm/user32.h>
 #include <asm/unistd.h>
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ad59cec14239..ae2ae6d80674 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -430,7 +430,9 @@ typedef struct {
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
+#ifdef CONFIG_X86_32
 	unsigned long		sp0;
+#endif
 	unsigned long		sp;
 #ifdef CONFIG_X86_32
 	unsigned long		sysenter_cs;
@@ -797,6 +799,13 @@ static inline void spin_lock_prefetch(const void *x)
 
 #define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1))
 
+#define task_pt_regs(task) \
+({									\
+	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
+	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
+	((struct pt_regs *)__ptr) - 1;					\
+})
+
 #ifdef CONFIG_X86_32
 /*
  * User space process size: 3GB (default).
@@ -816,23 +825,6 @@ static inline void spin_lock_prefetch(const void *x)
 	.addr_limit		= KERNEL_DS,				  \
 }
 
-/*
- * TOP_OF_KERNEL_STACK_PADDING reserves 8 bytes on top of the ring0 stack.
- * This is necessary to guarantee that the entire "struct pt_regs"
- * is accessible even if the CPU haven't stored the SS/ESP registers
- * on the stack (interrupt gate does not save these registers
- * when switching to the same priv ring).
- * Therefore beware: accessing the ss/esp fields of the
- * "struct pt_regs" is possible, but they may contain the
- * completely wrong values.
- */
-#define task_pt_regs(task) \
-({									\
-	unsigned long __ptr = (unsigned long)task_stack_page(task);	\
-	__ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;		\
-	((struct pt_regs *)__ptr) - 1;					\
-})
-
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
 #else
@@ -866,11 +858,9 @@ static inline void spin_lock_prefetch(const void *x)
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
 #define INIT_THREAD  {						\
-	.sp0			= TOP_OF_INIT_STACK,		\
 	.addr_limit		= KERNEL_DS,			\
 }
 
-#define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
 
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 54e64d909725..010cd6e4eafc 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_X86_SWITCH_TO_H
 #define _ASM_X86_SWITCH_TO_H
 
+#include <linux/sched/task_stack.h>
+
 struct task_struct; /* one of the stranger aspects of C forward declarations */
 
 struct task_struct *__switch_to_asm(struct task_struct *prev,
@@ -87,7 +89,11 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 /* This is used when switching tasks or entering/exiting vm86 mode. */
 static inline void update_sp0(struct task_struct *task)
 {
+#ifdef CONFIG_X86_32
 	load_sp0(task->thread.sp0);
+#else
+	load_sp0(task_top_of_stack(task));
+#endif
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 45e380958392..eeeb34f85c25 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -274,7 +274,6 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct inactive_task_frame *frame;
 	struct task_struct *me = current;
 
-	p->thread.sp0 = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;