diff -up ./arch/x86/include/asm/processor.h.gsi ./arch/x86/include/asm/processor.h
--- ./arch/x86/include/asm/processor.h.gsi	2018-03-22 06:40:12.000000000 +0900
+++ ./arch/x86/include/asm/processor.h	2018-04-16 21:12:06.000000000 +0900
@@ -527,6 +527,15 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
+/*
+ * per-CPU IRQ handling stacks
+ */
+struct irq_stack {
+	u32                     stack[THREAD_SIZE/sizeof(u32)];
+} __aligned(THREAD_SIZE);
+
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
+DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
 extern unsigned int xstate_size;
diff -up ./arch/x86/include/asm/thread_info.h.gsi ./arch/x86/include/asm/thread_info.h
--- ./arch/x86/include/asm/thread_info.h.gsi	2018-03-22 06:40:12.000000000 +0900
+++ ./arch/x86/include/asm/thread_info.h	2018-04-16 23:01:00.000000000 +0900
@@ -9,6 +9,7 @@
 
 #include <linux/compiler.h>
 #include <asm/page.h>
+#include <asm/percpu.h>
 #include <asm/types.h>
 
 /*
@@ -34,9 +35,6 @@ struct thread_info {
 	struct restart_block    restart_block;
 	void __user		*sysenter_return;
 #ifdef CONFIG_X86_32
-	unsigned long           previous_esp;   /* ESP of the previous stack in
-						   case of nested (IRQ) stacks
-						*/
 	__u8			supervisor_stack[0];
 #endif
 	unsigned int		sig_on_uaccess_error:1;
@@ -159,9 +157,9 @@ struct thread_info {
 
 #define PREEMPT_ACTIVE		0x10000000
 
-#ifdef CONFIG_X86_32
+#define STACK_WARN		(THREAD_SIZE/8)
+#define KERNEL_STACK_OFFSET	(5*(BITS_PER_LONG/8))
 
-#define STACK_WARN	(THREAD_SIZE/8)
 /*
  * macros/functions for gaining access to the thread information structure
  *
@@ -173,30 +171,9 @@ struct thread_info {
 /* how to get the current stack pointer from C */
 register unsigned long current_stack_pointer asm("esp") __used;
 
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)	 \
-	movl $-THREAD_SIZE, reg; \
-	andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-	andl $-THREAD_SIZE, reg
-
 #endif
 
-#else /* X86_32 */
-
 #include <asm/percpu.h>
-#define KERNEL_STACK_OFFSET (5*8)
 
 /*
  * macros/functions for gaining access to the thread information structure
@@ -220,8 +197,8 @@ static inline struct thread_info *curren
 
 /* how to get the thread information struct from ASM */
 #define GET_THREAD_INFO(reg) \
-	movq PER_CPU_VAR(kernel_stack),reg ; \
-	subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
+	_ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+	_ASM_SUB $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg ;
 
 /*
  * Same if PER_CPU_VAR(kernel_stack) is, perhaps with some offset, already in
@@ -231,8 +208,6 @@ static inline struct thread_info *curren
 
 #endif
 
-#endif /* !X86_32 */
-
 /*
  * Thread-synchronous status.
  *
diff -up ./arch/x86/kernel/cpu/common.c.gsi ./arch/x86/kernel/cpu/common.c
--- ./arch/x86/kernel/cpu/common.c.gsi	2018-04-15 20:28:45.000000000 +0900
+++ ./arch/x86/kernel/cpu/common.c	2018-04-16 23:48:12.000000000 +0900
@@ -1286,6 +1286,13 @@ static __init int setup_clearcpuid(char
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+DEFINE_PER_CPU(unsigned long, __kernel_stack_70__) =
+	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE - 8192;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
+EXPORT_PER_CPU_SYMBOL(__kernel_stack_70__);
+
 #ifdef CONFIG_X86_64
 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
 struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1302,12 +1309,6 @@ DEFINE_PER_CPU(struct task_struct *, cur
 	&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;
-DEFINE_PER_CPU(unsigned long, __kernel_stack_70__) =
-	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE - 8192;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-EXPORT_PER_CPU_SYMBOL(__kernel_stack_70__);
 
 DEFINE_PER_CPU(char *, irq_stack_ptr) =
 	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE;
diff -up ./arch/x86/kernel/dumpstack_32.c.gsi ./arch/x86/kernel/dumpstack_32.c
--- ./arch/x86/kernel/dumpstack_32.c.gsi	2018-04-16 21:12:06.000000000 +0900
+++ ./arch/x86/kernel/dumpstack_32.c	2018-04-17 19:43:45.000000000 +0900
@@ -17,6 +17,95 @@
 #include <asm/stacktrace.h>
 
 
+void stack_type_str(enum stack_type type, const char **begin, const char **end)
+{
+	switch (type) {
+	case STACK_TYPE_IRQ:
+		*begin = "IRQ";
+		*end   = "EOI";
+		break;
+	case STACK_TYPE_SOFTIRQ:
+		*begin = "SOFTIRQ";
+		*end   = "EOI";
+		break;
+#if 0 /*{*/
+	case STACK_TYPE_ENTRY:
+		*begin = "ENTRY_TRAMPOLINE";
+		*end   = "EOE";
+#endif /*}*/
+	default:
+		*begin = NULL;
+		*end   = NULL;
+	}
+}
+
+static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
+{
+	unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack);
+	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
+
+	if (stack < begin || stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_IRQ;
+	info->begin	= begin;
+	info->end	= end;
+
+	/*
+	 * See irq_32.c -- the next stack pointer is stored at the beginning of
+	 * the stack.
+	 */
+	info->next_sp	= (unsigned long *)*begin;
+
+	return true;
+}
+
+static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
+{
+	unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack);
+	unsigned long *end   = begin + (THREAD_SIZE / sizeof(long));
+
+	if (stack < begin || stack >= end)
+		return false;
+
+	info->type	= STACK_TYPE_SOFTIRQ;
+	info->begin	= begin;
+	info->end	= end;
+
+	/*
+	 * The next stack pointer is stored at the beginning of the stack.
+	 * See irq_32.c.
+	 */
+	info->next_sp	= (unsigned long *)*begin;
+
+	return true;
+}
+
+int get_stack_info(unsigned long *stack, struct task_struct *task,
+		   struct stack_info *info, unsigned long *visit_mask)
+{
+	if (!stack)
+		goto unknown;
+
+	task = task ? : current;
+
+	if (in_task_stack(stack, task, info))
+		return 0;
+
+	if (task != current)
+		goto unknown;
+
+	if (in_hardirq_stack(stack, info))
+		return 0;
+
+	if (in_softirq_stack(stack, info))
+		return 0;
+
+unknown:
+	info->type = STACK_TYPE_UNKNOWN;
+	return -EINVAL;
+}
+
 void show_regs(struct pt_regs *regs)
 {
 	int i;
diff -up ./arch/x86/kernel/irq_32.c.gsi ./arch/x86/kernel/irq_32.c
--- ./arch/x86/kernel/irq_32.c.gsi	2018-04-15 20:28:44.000000000 +0900
+++ ./arch/x86/kernel/irq_32.c	2018-04-16 23:09:01.000000000 +0900
@@ -58,16 +58,8 @@ static inline int check_stack_overflow(v
 static inline void print_stack_overflow(void) { }
 #endif
 
-/*
- * per-CPU IRQ handling contexts (thread information and stack)
- */
-union irq_ctx {
-	struct thread_info      tinfo;
-	u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(THREAD_SIZE)));
-
-static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
-static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -80,14 +72,22 @@ static void call_on_stack(void *func, vo
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("esp") __used;
+
+static inline void *current_stack(void)
+{
+	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
 static inline int
 execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 {
-	union irq_ctx *curctx, *irqctx;
-	u32 *isp, arg1, arg2;
+	struct irq_stack *curstk, *irqstk;
+ 	u32 *isp, *prev_esp, arg1, arg2;
 
-	curctx = (union irq_ctx *) current_thread_info();
-	irqctx = __this_cpu_read(hardirq_ctx);
+	curstk = (struct irq_stack *) current_stack();
+	irqstk = __this_cpu_read(hardirq_stack);
 
 	/*
 	 * this is where we switch to the IRQ stack. However, if we are
@@ -95,16 +95,14 @@ execute_on_irq_stack(int overflow, struc
 	 * handler) we can't do that and just have to keep using the
 	 * current stack (which is the irq stack already after all)
 	 */
-	if (unlikely(curctx == irqctx))
+	if (unlikely(curstk == irqstk))
 		return 0;
 
-	/* build the stack frame on the IRQ stack */
-	isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
-	irqctx->tinfo.task = curctx->tinfo.task;
-	irqctx->tinfo.previous_esp = current_stack_pointer;
+	isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
 
-	/* Copy the preempt_count so that the [soft]irq checks work. */
-	irqctx->tinfo.preempt_count = curctx->tinfo.preempt_count;
+	/* Save the next esp at the bottom of the stack */
+	prev_esp = (u32 *)irqstk;
+ 	*prev_esp = current_stack_pointer;
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -124,40 +122,31 @@ execute_on_irq_stack(int overflow, struc
  */
 void irq_ctx_init(int cpu)
 {
-	union irq_ctx *irqctx;
+	struct irq_stack *irqstk;
 
-	if (per_cpu(hardirq_ctx, cpu))
+	if (per_cpu(hardirq_stack, cpu))
 		return;
 
-	irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
 					       THREADINFO_GFP,
 					       THREAD_SIZE_ORDER));
-	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
-	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
-	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
-
-	per_cpu(hardirq_ctx, cpu) = irqctx;
+	per_cpu(hardirq_stack, cpu) = irqstk;
 
-	irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+	irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
 					       THREADINFO_GFP,
 					       THREAD_SIZE_ORDER));
-	memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
-	irqctx->tinfo.cpu		= cpu;
-	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
-
-	per_cpu(softirq_ctx, cpu) = irqctx;
+	per_cpu(softirq_stack, cpu) = irqstk;
 
 	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-	       cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
+	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags;
-	struct thread_info *curctx;
-	union irq_ctx *irqctx;
-	u32 *isp;
+	struct thread_info *curstk;
+	struct irq_stack *irqstk;
+ 	u32 *isp, *prev_esp;
 
 	if (in_interrupt())
 		return;
@@ -165,13 +154,14 @@ asmlinkage void do_softirq(void)
 	local_irq_save(flags);
 
 	if (local_softirq_pending()) {
-		curctx = current_thread_info();
-		irqctx = __this_cpu_read(softirq_ctx);
-		irqctx->tinfo.task = curctx->task;
-		irqctx->tinfo.previous_esp = current_stack_pointer;
+		curstk = current_stack();
+		irqstk = __this_cpu_read(softirq_stack);
 
 		/* build the stack frame on the softirq stack */
-		isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
+		isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+		prev_esp = (u32 *)irqstk;
+		*prev_esp = current_stack_pointer;
 
 		call_on_stack(__do_softirq, isp);
 		/*
diff -up ./arch/x86/kernel/process_32.c.gsi ./arch/x86/kernel/process_32.c
--- ./arch/x86/kernel/process_32.c.gsi	2018-03-22 06:40:12.000000000 +0900
+++ ./arch/x86/kernel/process_32.c	2018-04-16 21:12:06.000000000 +0900
@@ -307,6 +307,10 @@ __switch_to(struct task_struct *prev_p,
 	 */
 	arch_end_context_switch(next_p);
 
+	this_cpu_write(kernel_stack,
+		  (unsigned long)task_stack_page(next_p) +
+		  THREAD_SIZE - KERNEL_STACK_OFFSET);
+
 	/*
 	 * Restore %gs if needed (which is common)
 	 */
diff -up ./arch/x86/kernel/ptrace.c.gsi ./arch/x86/kernel/ptrace.c
--- ./arch/x86/kernel/ptrace.c.gsi	2018-04-16 21:12:06.000000000 +0900
+++ ./arch/x86/kernel/ptrace.c	2018-04-16 23:39:44.000000000 +0900
@@ -184,14 +184,15 @@ unsigned long kernel_stack_pointer(struc
 {
 	unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
 	unsigned long sp = (unsigned long)&regs->sp;
-	struct thread_info *tinfo;
+	u32 *prev_esp;
 
 	if (context == (sp & ~(THREAD_SIZE - 1)))
 		return sp;
 
-	tinfo = (struct thread_info *)context;
-	if (tinfo->previous_esp)
-		return tinfo->previous_esp;
+	prev_esp = (u32 *)(context);
+	if (*prev_esp)
+		return (unsigned long)*prev_esp;
+
 
 	return (unsigned long)regs;
 }
diff -up ./arch/x86/kernel/smpboot.c.gsi ./arch/x86/kernel/smpboot.c
--- ./arch/x86/kernel/smpboot.c.gsi	2018-04-16 21:12:06.000000000 +0900
+++ ./arch/x86/kernel/smpboot.c	2018-04-16 21:46:54.000000000 +0900
@@ -898,13 +898,13 @@ static int do_boot_cpu(int apicid, int c
 #else
 	clear_tsk_thread_flag(idle, TIF_FORK);
 	initial_gs = per_cpu_offset(cpu);
+#endif
 	per_cpu(kernel_stack, cpu) =
 		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE;
 	per_cpu(__kernel_stack_70__, cpu) =
 		(unsigned long)task_stack_page(idle) -
 		KERNEL_STACK_OFFSET + THREAD_SIZE - 8192;
-#endif
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;
 	initial_stack  = idle->thread.sp;