Re: [PATCH] perf test: Fix dwarf unwind for optimized builds.

[Jiri Olsa]

On Fri, Nov 13, 2020 at 04:08:03PM -0800, Ian Rogers wrote:
> To ensure the stack frames are on the stack tail calls optimizations
> need to be inhibited. If your compiler supports an attribute use it,
> otherwise use an asm volatile barrier.
> 
> The barrier fix was suggested here:
> https://lore.kernel.org/lkml/20201028081123.GT2628@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/
> 
> Fixes: 9ae1e990f1ab ("perf tools: Remove broken __no_tail_call
>        attribute")

missing SOB

LGTM and test is passing for me ;-)

Tested-by: Jiri Olsa <jolsa@xxxxxxxxxx>

jirka

> ---
>  tools/perf/tests/dwarf-unwind.c | 39 +++++++++++++++++++++++++++------
>  1 file changed, 32 insertions(+), 7 deletions(-)
> 
> diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
> index 83638097c3bc..c8ce86bceea8 100644
> --- a/tools/perf/tests/dwarf-unwind.c
> +++ b/tools/perf/tests/dwarf-unwind.c
> @@ -24,6 +24,23 @@
>  /* For bsearch. We try to unwind functions in shared object. */
>  #include <stdlib.h>
>  
> +/*
> + * The test will assert frames are on the stack but tail call optimizations lose
> + * the frame of the caller. Clang can disable this optimization on a called
> + * function but GCC currently (11/2020) lacks this attribute. The barrier is
> + * used to inhibit tail calls in these cases.
> + */
> +#ifdef __has_attribute
> +#if __has_attribute(disable_tail_calls)
> +#define NO_TAIL_CALL_ATTRIBUTE __attribute__((disable_tail_calls))
> +#define NO_TAIL_CALL_BARRIER
> +#endif
> +#endif
> +#ifndef NO_TAIL_CALL_ATTRIBUTE
> +#define NO_TAIL_CALL_ATTRIBUTE
> +#define NO_TAIL_CALL_BARRIER __asm__ __volatile__("" : : : "memory");
> +#endif
> +
>  static int mmap_handler(struct perf_tool *tool __maybe_unused,
>  			union perf_event *event,
>  			struct perf_sample *sample,
> @@ -95,7 +112,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
>  	return strcmp((const char *) symbol, funcs[idx]);
>  }
>  
> -noinline int test_dwarf_unwind__thread(struct thread *thread)
> +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thread)
>  {
>  	struct perf_sample sample;
>  	unsigned long cnt = 0;
> @@ -126,7 +143,7 @@ noinline int test_dwarf_unwind__thread(struct thread *thread)
>  
>  static int global_unwind_retval = -INT_MAX;
>  
> -noinline int test_dwarf_unwind__compare(void *p1, void *p2)
> +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__compare(void *p1, void *p2)
>  {
>  	/* Any possible value should be 'thread' */
>  	struct thread *thread = *(struct thread **)p1;
> @@ -145,7 +162,7 @@ noinline int test_dwarf_unwind__compare(void *p1, void *p2)
>  	return p1 - p2;
>  }
>  
> -noinline int test_dwarf_unwind__krava_3(struct thread *thread)
> +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_3(struct thread *thread)
>  {
>  	struct thread *array[2] = {thread, thread};
>  	void *fp = &bsearch;
> @@ -164,14 +181,22 @@ noinline int test_dwarf_unwind__krava_3(struct thread *thread)
>  	return global_unwind_retval;
>  }
>  
> -noinline int test_dwarf_unwind__krava_2(struct thread *thread)
> +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_2(struct thread *thread)
>  {
> -	return test_dwarf_unwind__krava_3(thread);
> +	int ret;
> +
> +	ret =  test_dwarf_unwind__krava_3(thread);
> +	NO_TAIL_CALL_BARRIER;
> +	return ret;
>  }
>  
> -noinline int test_dwarf_unwind__krava_1(struct thread *thread)
> +NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__krava_1(struct thread *thread)
>  {
> -	return test_dwarf_unwind__krava_2(thread);
> +	int ret;
> +
> +	ret =  test_dwarf_unwind__krava_2(thread);
> +	NO_TAIL_CALL_BARRIER;
> +	return ret;
>  }
>  
>  int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
> -- 
> 2.29.2.299.gdc1121823c-goog
>