perf/x86: Always store regs->ip in perf_callchain_kernel()

The stacktrace_map_raw_tp BPF selftest is failing because the RIP saved by
perf_arch_fetch_caller_regs() isn't getting saved by perf_callchain_kernel().

This was broken by the following commit:

  d15d356887e7 ("perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER")

With that change, when starting with non-HW regs, the unwinder starts
with the current stack frame and unwinds until it passes up the frame
which called perf_arch_fetch_caller_regs().  So regs->ip needs to be
saved deliberately.

Fixes: d15d356887e7 ("perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER")
Signed-off-by: Song Liu <[email protected]>
Signed-off-by: Josh Poimboeuf <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Cc: Kairui Song <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Borislav Petkov <[email protected]>
Link: https://lkml.kernel.org/r/3975a298fa52b506fea32666d8ff6a13467eee6d.1561595111.git.jpoimboe@redhat.com

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index f315425d8468f473bf11e95c6039b59ac6b318a4..4fb3ca1e699dddd194262b14036eb6b702aa87b6 100644 (file)
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2402,13 +2402,13 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
                return;
        }
 
-       if (perf_hw_regs(regs)) {
-               if (perf_callchain_store(entry, regs->ip))
-                       return;
+       if (perf_callchain_store(entry, regs->ip))
+               return;
+
+       if (perf_hw_regs(regs))
                unwind_start(&state, current, regs, NULL);
-       } else {
+       else
                unwind_start(&state, current, NULL, (void *)regs->sp);
-       }
 
        for (; !unwind_done(&state); unwind_next_frame(&state)) {
                addr = unwind_get_return_address(&state);