diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index de1a924a49145127b8cde57dca2070e736d69ce6..f315425d8468f473bf11e95c6039b59ac6b318a4 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2382,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event,
 	cyc2ns_read_end();
 }
 
+/*
+ * Determine whether the regs were taken from an irq/exception handler rather
+ * than from perf_arch_fetch_caller_regs().
+ */
+static bool perf_hw_regs(struct pt_regs *regs)
+{
+	return regs->flags & X86_EFLAGS_FIXED;
+}
+
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
@@ -2393,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_callchain_store(entry, regs->ip))
-		return;
+	if (perf_hw_regs(regs)) {
+		if (perf_callchain_store(entry, regs->ip))
+			return;
+		unwind_start(&state, current, regs, NULL);
+	} else {
+		unwind_start(&state, current, NULL, (void *)regs->sp);
+	}
 
-	for (unwind_start(&state, current, regs, NULL); !unwind_done(&state);
-	     unwind_next_frame(&state)) {
+	for (; !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
 		if (!addr || perf_callchain_store(entry, addr))
 			return;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 04768a3a5454823d3693efcf62d9bbc93d5c83d6..1392d5e6e8d671fe7d503646399c193dfce2dafa 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -308,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
  */
 #define perf_arch_fetch_caller_regs(regs, __ip)		{	\
 	(regs)->ip = (__ip);					\
-	(regs)->bp = caller_frame_pointer();			\
+	(regs)->sp = (unsigned long)__builtin_frame_address(0);	\
 	(regs)->cs = __KERNEL_CS;				\
 	regs->flags = 0;					\
-	asm volatile(						\
-		_ASM_MOV "%%"_ASM_SP ", %0\n"			\
-		: "=m" ((regs)->sp)				\
-		:: "memory"					\
-	);							\
 }
 
 struct perf_guest_switch_msr {
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f335aad404a479e98e4a5d38dc41ee5e5aa419ec..beef7ad9e43a4a7391aad3db4231de806f4799d6 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -98,19 +98,6 @@ struct stack_frame_ia32 {
     u32 return_address;
 };
 
-static inline unsigned long caller_frame_pointer(void)
-{
-	struct stack_frame *frame;
-
-	frame = __builtin_frame_address(0);
-
-#ifdef CONFIG_FRAME_POINTER
-	frame = frame->next_frame;
-#endif
-
-	return (unsigned long)frame;
-}
-
 void show_opcodes(struct pt_regs *regs, const char *loglvl);
 void show_ip(struct pt_regs *regs, const char *loglvl);
 #endif /* _ASM_X86_STACKTRACE_H */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f3864e1c55695bc7c0bd86951f6d08a7ab48e1bc..cf023db0e8a2fd411d5e53d306c4ce981a9027f6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1058,12 +1058,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo
 #endif
 
 /*
- * Take a snapshot of the regs. Skip ip and frame pointer to
- * the nth caller. We only need a few of the regs:
+ * When generating a perf sample in-line, instead of from an interrupt /
+ * exception, we lack a pt_regs. This is typically used from software events
+ * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints.
+ *
+ * We typically don't need a full set, but (for x86) do require:
  * - ip for PERF_SAMPLE_IP
  * - cs for user_mode() tests
- * - bp for callchains
- * - eflags, for future purposes, just in case
+ * - sp for PERF_SAMPLE_CALLCHAIN
+ * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs())
+ *
+ * NOTE: assumes @regs is otherwise already 0 filled; this is important for
+ * things like PERF_SAMPLE_REGS_INTR.
  */
 static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 {