diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 4487bb989cea9c7ec456ceee7106e379e2f44c6d..554f84bca1c3226318097e9e2917fd458f826e3b 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -23,7 +23,7 @@ static __always_inline void __run_on_irqstack(void (*func)(void))
 	void *tos = __this_cpu_read(hardirq_stack_ptr);
 
 	__this_cpu_write(hardirq_stack_inuse, true);
-	asm_call_on_stack(tos - 8, func, NULL);
+	asm_call_on_stack(tos, func, NULL);
 	__this_cpu_write(hardirq_stack_inuse, false);
 }
 
@@ -34,7 +34,7 @@ __run_sysvec_on_irqstack(void (*func)(struct pt_regs *regs),
 	void *tos = __this_cpu_read(hardirq_stack_ptr);
 
 	__this_cpu_write(hardirq_stack_inuse, true);
-	asm_call_sysvec_on_stack(tos - 8, func, regs);
+	asm_call_sysvec_on_stack(tos, func, regs);
 	__this_cpu_write(hardirq_stack_inuse, false);
 }
 
@@ -45,7 +45,7 @@ __run_irq_on_irqstack(void (*func)(struct irq_desc *desc),
 	void *tos = __this_cpu_read(hardirq_stack_ptr);
 
 	__this_cpu_write(hardirq_stack_inuse, true);
-	asm_call_irq_on_stack(tos - 8, func, desc);
+	asm_call_irq_on_stack(tos, func, desc);
 	__this_cpu_write(hardirq_stack_inuse, false);
 }
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 11d10f4f3059cf3deb6c3b8e4a4321512d5449c9..dc6d149bf851fa911c7c7915fbe68e39f1016b4c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -426,8 +426,6 @@ struct irq_stack {
 	char		stack[IRQ_STACK_SIZE];
 } __aligned(IRQ_STACK_SIZE);
 
-DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
-
 #ifdef CONFIG_X86_32
 DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack);
 #else
@@ -454,6 +452,7 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu)
 	return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
 }
 
+DECLARE_PER_CPU(void *, hardirq_stack_ptr);
 DECLARE_PER_CPU(bool, hardirq_stack_inuse);
 extern asmlinkage void ignore_sysret(void);
 
@@ -473,9 +472,9 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
-/* Per CPU softirq stack pointer */
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
 DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
-#endif	/* X86_64 */
+#endif	/* !X86_64 */
 
 extern unsigned int fpu_kernel_xstate_size;
 extern unsigned int fpu_user_xstate_size;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 845c8a46cf7b291c138ce1fdf060afe7e4e6fd33..c5e23f351f676d7134c9798b3ca00b883a11313b 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1739,7 +1739,7 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
 	&init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr);
+DEFINE_PER_CPU(void *, hardirq_stack_ptr);
 DEFINE_PER_CPU(bool, hardirq_stack_inuse);
 
 DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 1dd851397bd909a915447d75975d2ab6db52413b..5601b95944faedef320f6fb980df21f4fbe58cd6 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -128,12 +128,21 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac
 
 static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 {
-	unsigned long *end   = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
-	unsigned long *begin = end - (IRQ_STACK_SIZE / sizeof(long));
+	unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr);
+	unsigned long *begin;
 
 	/*
-	 * This is a software stack, so 'end' can be a valid stack pointer.
-	 * It just means the stack is empty.
+	 * @end points directly to the top most stack entry to avoid a -8
+	 * adjustment in the stack switch hotpath. Adjust it back before
+	 * calculating @begin.
+	 */
+	end++;
+	begin = end - (IRQ_STACK_SIZE / sizeof(long));
+
+	/*
+	 * Due to the switching logic RSP can never be == @end because the
+	 * final operation is 'popq %rsp' which means after that RSP points
+	 * to the original stack and not to @end.
 	 */
 	if (stack < begin || stack >= end)
 		return false;
@@ -143,8 +152,9 @@ static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info
 	info->end	= end;
 
 	/*
-	 * The next stack pointer is the first thing pushed by the entry code
-	 * after switching to the irq stack.
+	 * The next stack pointer is stored at the top of the irq stack
+	 * before switching to the irq stack. Actual stack entries are all
+	 * below that.
 	 */
 	info->next_sp = (unsigned long *)*(end - 1);
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 440eed558558d9891547ee1bd09a4570bc398156..7103f98899304bc61e8f08838f1ec02aab5612a6 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -48,7 +48,8 @@ static int map_irq_stack(unsigned int cpu)
 	if (!va)
 		return -ENOMEM;
 
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	/* Store actual TOS to avoid adjustment in the hotpath */
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #else
@@ -60,7 +61,8 @@ static int map_irq_stack(unsigned int cpu)
 {
 	void *va = per_cpu_ptr(&irq_stack_backing_store, cpu);
 
-	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE;
+	/* Store actual TOS to avoid adjustment in the hotpath */
+	per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8;
 	return 0;
 }
 #endif