diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1d665a0b202c..c6bde7d7afdc 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1707,3 +1707,15 @@ struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 
 	return entry;
 }
+
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
+{
+	regs->ip = ip;
+	/*
+	 * perf_arch_fetch_caller_regs adds another call, we need to increment
+	 * the skip level
+	 */
+	regs->bp = rewind_frame_pointer(skip + 1);
+	regs->cs = __KERNEL_CS;
+	local_save_flags(regs->flags);
+}
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index 4fd1420faffa..29e5f7c845b2 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -29,4 +29,19 @@ struct stack_frame {
 	struct stack_frame *next_frame;
 	unsigned long return_address;
 };
+
+static inline unsigned long rewind_frame_pointer(int n)
+{
+	struct stack_frame *frame;
+
+	get_bp(frame);
+
+#ifdef CONFIG_FRAME_POINTER
+	while (n--)
+		frame = frame->next_frame;
 #endif
+
+	return (unsigned long)frame;
+}
+
+#endif /* DUMPSTACK_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 80acbf3d5de1..70cffd052c04 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -452,6 +452,7 @@ enum perf_callchain_context {
 #include <linux/fs.h>
 #include <linux/pid_namespace.h>
 #include <linux/workqueue.h>
+#include <linux/ftrace.h>
 #include <asm/atomic.h>
 
 #define PERF_MAX_STACK_DEPTH		255
@@ -847,6 +848,44 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 		__perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
+extern void
+perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip);
+
+/*
+ * Take a snapshot of the regs. Skip ip and frame pointer to
+ * the nth caller. We only need a few of the regs:
+ * - ip for PERF_SAMPLE_IP
+ * - cs for user_mode() tests
+ * - bp for callchains
+ * - eflags, for future purposes, just in case
+ */
+static inline void perf_fetch_caller_regs(struct pt_regs *regs, int skip)
+{
+	unsigned long ip;
+
+	memset(regs, 0, sizeof(*regs));
+
+	switch (skip) {
+	case 1 :
+		ip = CALLER_ADDR0;
+		break;
+	case 2 :
+		ip = CALLER_ADDR1;
+		break;
+	case 3 :
+		ip = CALLER_ADDR2;
+		break;
+	case 4:
+		ip = CALLER_ADDR3;
+		break;
+	/* No need to support further for now */
+	default:
+		ip = 0;
+	}
+
+	return perf_arch_fetch_caller_regs(regs, ip, skip);
+}
+
 extern void __perf_event_mmap(struct vm_area_struct *vma);
 
 static inline void perf_event_mmap(struct vm_area_struct *vma)
@@ -880,7 +919,8 @@ static inline bool perf_paranoid_kernel(void)
 }
 
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record,
+			  int entry_size, struct pt_regs *regs);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 52c69a34d697..359d7f690c2b 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -2786,6 +2786,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
+__weak
+void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
+{
+}
+
 /*
  * Output
  */