diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index d9d4dae305f6991efa446ec0ef4e7fad8054bdc3..094fb30817abb8ea9fb6ce475a87e1c886df90b9 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -152,6 +152,11 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 	(regs)->bp = caller_frame_pointer();			\
 	(regs)->cs = __KERNEL_CS;				\
 	regs->flags = 0;					\
+	asm volatile(						\
+		_ASM_MOV "%%"_ASM_SP ", %0\n"			\
+		: "=m" ((regs)->sp)				\
+		:: "memory"					\
+	);							\
 }
 
 #else
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index e71c98d3c0d2d7ff4fc2085d646d31b56bc6a476..19853ad8afc5ff940cbf6806b6ae283695296cd7 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -104,34 +104,6 @@ in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
 	return (stack >= irq_stack && stack < irq_stack_end);
 }
 
-/*
- * We are returning from the irq stack and go to the previous one.
- * If the previous stack is also in the irq stack, then bp in the first
- * frame of the irq stack points to the previous, interrupted one.
- * Otherwise we have another level of indirection: We first save
- * the bp of the previous stack, then we switch the stack to the irq one
- * and save a new bp that links to the previous one.
- * (See save_args())
- */
-static inline unsigned long
-fixup_bp_irq_link(unsigned long bp, unsigned long *stack,
-		  unsigned long *irq_stack, unsigned long *irq_stack_end)
-{
-#ifdef CONFIG_FRAME_POINTER
-	struct stack_frame *frame = (struct stack_frame *)bp;
-	unsigned long next;
-
-	if (!in_irq_stack(stack, irq_stack, irq_stack_end)) {
-		if (!probe_kernel_address(&frame->next_frame, next))
-			return next;
-		else
-			WARN_ONCE(1, "Perf: bad frame pointer = %p in "
-				  "callchain\n", &frame->next_frame);
-	}
-#endif
-	return bp;
-}
-
 /*
  * x86-64 can have up to three kernel stacks:
  * process stack
@@ -155,9 +127,12 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		task = current;
 
 	if (!stack) {
-		stack = &dummy;
-		if (task && task != current)
+		if (regs)
+			stack = (unsigned long *)regs->sp;
+		else if (task && task != current)
 			stack = (unsigned long *)task->thread.sp;
+		else
+			stack = &dummy;
 	}
 
 	if (!bp)
@@ -205,8 +180,6 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 				 * pointer (index -1 to end) in the IRQ stack:
 				 */
 				stack = (unsigned long *) (irq_stack_end[-1]);
-				bp = fixup_bp_irq_link(bp, stack, irq_stack,
-						       irq_stack_end);
 				irq_stack_end = NULL;
 				ops->stack(data, "EOI");
 				continue;
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 8a445a0c989e095bc84557861d4a4e73e09e3e90..d656f68371a4afdac2cd98b7a06cfac88f4f5769 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -297,27 +297,26 @@ ENDPROC(native_usergs_sysret64)
 	.endm
 
 /* save partial stack frame */
-	.pushsection .kprobes.text, "ax"
-ENTRY(save_args)
-	XCPT_FRAME
+	.macro SAVE_ARGS_IRQ
 	cld
-	/*
-	 * start from rbp in pt_regs and jump over
-	 * return address.
-	 */
-	movq_cfi rdi, RDI+8-RBP
-	movq_cfi rsi, RSI+8-RBP
-	movq_cfi rdx, RDX+8-RBP
-	movq_cfi rcx, RCX+8-RBP
-	movq_cfi rax, RAX+8-RBP
-	movq_cfi  r8,  R8+8-RBP
-	movq_cfi  r9,  R9+8-RBP
-	movq_cfi r10, R10+8-RBP
-	movq_cfi r11, R11+8-RBP
-
-	leaq -RBP+8(%rsp),%rdi	/* arg1 for handler */
-	movq_cfi rbp, 8		/* push %rbp */
-	leaq 8(%rsp), %rbp		/* mov %rsp, %ebp */
+	/* start from rbp in pt_regs and jump over */
+	movq_cfi rdi, RDI-RBP
+	movq_cfi rsi, RSI-RBP
+	movq_cfi rdx, RDX-RBP
+	movq_cfi rcx, RCX-RBP
+	movq_cfi rax, RAX-RBP
+	movq_cfi  r8,  R8-RBP
+	movq_cfi  r9,  R9-RBP
+	movq_cfi r10, R10-RBP
+	movq_cfi r11, R11-RBP
+
+	/* Save rbp so that we can unwind from get_irq_regs() */
+	movq_cfi rbp, 0
+
+	/* Save previous stack value */
+	movq %rsp, %rsi
+
+	leaq -RBP(%rsp),%rdi	/* arg1 for handler */
 	testl $3, CS(%rdi)
 	je 1f
 	SWAPGS
@@ -329,19 +328,14 @@ ENTRY(save_args)
 	 */
 1:	incl PER_CPU_VAR(irq_count)
 	jne 2f
-	popq_cfi %rax			/* move return address... */
 	mov PER_CPU_VAR(irq_stack_ptr),%rsp
 	EMPTY_FRAME 0
-	pushq_cfi %rbp			/* backlink for unwinder */
-	pushq_cfi %rax			/* ... to the new stack */
-	/*
-	 * We entered an interrupt context - irqs are off:
-	 */
-2:	TRACE_IRQS_OFF
-	ret
-	CFI_ENDPROC
-END(save_args)
-	.popsection
+
+2:	/* Store previous stack value */
+	pushq %rsi
+	/* We entered an interrupt context - irqs are off: */
+	TRACE_IRQS_OFF
+	.endm
 
 ENTRY(save_rest)
 	PARTIAL_FRAME 1 REST_SKIP+8
@@ -791,7 +785,7 @@ END(interrupt)
 	/* reserve pt_regs for scratch regs and rbp */
 	subq $ORIG_RAX-RBP, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
-	call save_args
+	SAVE_ARGS_IRQ
 	PARTIAL_FRAME 0
 	call \func
 	.endm
@@ -814,15 +808,14 @@ ret_from_intr:
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	decl PER_CPU_VAR(irq_count)
-	leaveq
 
-	CFI_RESTORE		rbp
+	/* Restore saved previous stack */
+	popq %rsi
+	leaq 16(%rsi), %rsp
+
 	CFI_DEF_CFA_REGISTER	rsp
-	CFI_ADJUST_CFA_OFFSET	-8
+	CFI_ADJUST_CFA_OFFSET	-16
 
-	/* we did not save rbx, restore only from ARGOFFSET */
-	addq $8, %rsp
-	CFI_ADJUST_CFA_OFFSET	-8
 exit_intr:
 	GET_THREAD_INFO(%rcx)
 	testl $3,CS-ARGOFFSET(%rsp)