[PATCH V4 6/6] x86/entry/32: Introduce cpu_current_thread_sp0 to replace cpu_tss_rw.x86_tss.sp1

[Lai Jiangshan]

From: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>

TSS sp1 is not used by hardware and is used as a copy of thread.sp0.

It should just use a percpu variable instead, so we introduce
cpu_current_thread_sp0 for it.

And we remove the unneeded TSS_sp1.

Signed-off-by: Lai Jiangshan <laijs@xxxxxxxxxxxxxxxxx>
---
 arch/x86/entry/entry_32.S        | 6 +++---
 arch/x86/include/asm/processor.h | 2 ++
 arch/x86/include/asm/switch_to.h | 2 +-
 arch/x86/kernel/asm-offsets.c    | 1 -
 arch/x86/kernel/cpu/common.c     | 9 ++++++++-
 arch/x86/kernel/process.c        | 2 --
 6 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index d5b5b43fd0c0..55dcf5c35141 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -472,7 +472,7 @@
 	movl	%esp, %esi
 
 	/* Load top of task-stack into %edi */
-	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %edi
+	movl	PER_CPU_VAR(cpu_current_thread_sp0), %edi
 
 	/* Special case - entry from kernel mode via entry stack */
 #ifdef CONFIG_VM86
@@ -658,7 +658,7 @@
 	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
 
 	/* Bytes on the task-stack to ecx */
-	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
+	movl	PER_CPU_VAR(cpu_current_thread_sp0), %ecx
 	subl	%esi, %ecx
 
 	/* Allocate stack-frame on entry-stack */
@@ -916,7 +916,7 @@ SYM_FUNC_START(entry_SYSENTER_32)
 
 	/* Switch to task stack */
 	movl	%esp, %eax
-	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %esp
+	movl	PER_CPU_VAR(cpu_current_thread_sp0), %esp
 
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index e197de05d0aa..a40bade32105 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -776,6 +776,8 @@ static inline void spin_lock_prefetch(const void *x)
 
 #define KSTK_ESP(task)		(task_pt_regs(task)->sp)
 
+DECLARE_PER_CPU(unsigned long, cpu_current_thread_sp0);
+
 #else
 #define INIT_THREAD { }
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index f0ba06bcba0b..eb0d3ae8a54d 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -69,7 +69,7 @@ static inline void update_task_stack(struct task_struct *task)
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task->thread.sp0);
 	else
-		this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
+		this_cpu_write(cpu_current_thread_sp0, task->thread.sp0);
 #else
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task_top_of_stack(task));
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 60b9f42ce3c1..3b63b6062792 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -98,6 +98,5 @@ static void __used common(void)
 
 	/* Offset for fields in tss_struct */
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
-	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
 }
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9c531ec73f5c..86485d55949e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1792,12 +1792,19 @@ EXPORT_PER_CPU_SYMBOL(__preempt_count);
 /*
  * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
  * the top of the kernel stack.  Use an extra percpu variable to track the
- * top of the kernel stack directly.
+ * top of the kernel stack directly and an percpu variable to track the
+ * thread.sp0 for using in entry code.  cpu_current_top_of_stack and
+ * cpu_current_thread_sp0 are different value because of the non-zero
+ * stack-padding on 32bit.  See more comment at TOP_OF_KERNEL_STACK_PADDING
+ * and vm86.
  */
 DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) =
 	(unsigned long)&init_thread_union + THREAD_SIZE;
 EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack);
 
+DEFINE_PER_CPU(unsigned long, cpu_current_thread_sp0) = TOP_OF_INIT_STACK;
+EXPORT_PER_CPU_SYMBOL_GPL(cpu_current_thread_sp0);
+
 #ifdef CONFIG_STACKPROTECTOR
 DEFINE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 296de77da4b2..e6d4b5399a81 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -64,8 +64,6 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
 
 #ifdef CONFIG_X86_32
-		.sp1 = TOP_OF_INIT_STACK,
-
 		.ss0 = __KERNEL_DS,
 		.ss1 = __KERNEL_CS,
 #endif
-- 
2.19.1.6.gb485710b