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

From: Peter Zijlstra
Date: Mon Apr 15 2019 - 11:36:37 EST



I'll mostly defer to Josh on unwinding, but a few comments below.

On Tue, Apr 09, 2019 at 12:59:42AM +0800, Kairui Song wrote:
> 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);
> +}

I'm unconvinced by this, with both guess and orc having !bp is perfectly
valid.

> 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;
> + }

AFAICT if we, by pure accident, end up with !bp for ORC, then we
initialize the unwind wrong.

Note that @regs is mostly trivially correct, except for that tracepoint
case. So I don't think we should magic here.

> - 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

OK, that makes sense I guess.