[RFC PATCH v2] perf/x86: make perf callchain work without CONFIG_FRAME_POINTER

[Kairui Song]

Currently perf callchain is not working properly with ORC unwinder,
and sampling event from trace point. We'll get useless in kernel
callchain like this:

perf  6429 [000]    22.498450:             kmem:mm_page_alloc: page=0x176a17 pfn=1534487 order=0 migratetype=0 gfp_flags=GFP_KERNEL
    ffffffffbe23e32e __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux)
	7efdf7f7d3e8 __poll+0x18 (/usr/lib64/libc-2.28.so)
	5651468729c1 [unknown] (/usr/bin/perf)
	5651467ee82a main+0x69a (/usr/bin/perf)
	7efdf7eaf413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so)
    5541f689495641d7 [unknown] ([unknown])

The root cause is within a trace point perf will try to dump the
caller's register, but without CONFIG_FRAME_POINTER we can't get
caller's BP as the frame pointer, so current frame pointer is returned
instead. We get a register combination of caller IP and current BP,
which confuse the unwinder and end the stacktrace early.

So in such case don't dump BP, and just let the unwinder start directly
and skip until we reached the stack we wanted.

This make the callchain get the full kernel space stacktrace again:

perf  6503 [000]  1567.570191:             kmem:mm_page_alloc: page=0x16c904 pfn=1493252 order=0 migratetype=0 gfp_flags=GFP_KERNEL
    ffffffffb523e2ae __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb52383bd __get_free_pages+0xd (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb52fd28a __pollwait+0x8a (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb521426f perf_poll+0x2f (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb52fe3e2 do_sys_poll+0x252 (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb52ff027 __x64_sys_poll+0x37 (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb500418b do_syscall_64+0x5b (/lib/modules/5.1.0-rc3+/build/vmlinux)
    ffffffffb5a0008c entry_SYSCALL_64_after_hwframe+0x44 (/lib/modules/5.1.0-rc3+/build/vmlinux)
	7f71e92d03e8 __poll+0x18 (/usr/lib64/libc-2.28.so)
	55a22960d9c1 [unknown] (/usr/bin/perf)
	55a22958982a main+0x69a (/usr/bin/perf)
	7f71e9202413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so)
    5541f689495641d7 [unknown] ([unknown])

Signed-off-by: Kairui Song <kasong@xxxxxxxxxx>
---

Update from V1:
  Get rid of a lot of unneccessary code and just don't dump a inaccurate
  BP, and use SP as the marker for target frame.

 arch/x86/events/core.c            | 18 +++++++++++++++---
 arch/x86/include/asm/stacktrace.h |  9 +++++++--
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..6075a4f94376 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2355,6 +2355,12 @@ void arch_perf_update_userpage(struct perf_event *event,
 	cyc2ns_read_end();
 }
 
+static inline int
+valid_perf_registers(struct pt_regs *regs)
+{
+	return (regs->ip && regs->bp && regs->sp);
+}
+
 void
 perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
@@ -2366,11 +2372,17 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 		return;
 	}
 
-	if (perf_callchain_store(entry, regs->ip))
+	if (valid_perf_registers(regs)) {
+		if (perf_callchain_store(entry, regs->ip))
+			return;
+		unwind_start(&state, current, regs, NULL);
+	} else if (regs->sp) {
+		unwind_start(&state, current, NULL, (unsigned long *)regs->sp);
+	} else {
 		return;
+	}
 
-	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/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f335aad404a4..226077e20412 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -98,18 +98,23 @@ struct stack_frame_ia32 {
     u32 return_address;
 };
 
+#ifdef CONFIG_FRAME_POINTER
 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;
 }
+#else
+static inline unsigned long caller_frame_pointer(void)
+{
+	return 0;
+}
+#endif
 
 void show_opcodes(struct pt_regs *regs, const char *loglvl);
 void show_ip(struct pt_regs *regs, const char *loglvl);
-- 
2.20.1