Re: [PATCHv2 2/4] x86/fgraph,bpf: Fix stack ORC unwind from kprobe_multi return probe

[Peter Zijlstra <peterz@infradead.org>]

On Mon, Nov 03, 2025 at 11:09:22PM +0100, Jiri Olsa wrote:
> Currently we don't get stack trace via ORC unwinder on top of fgraph exit
> handler. We can see that when generating stacktrace from kretprobe_multi
> bpf program which is based on fprobe/fgraph.
> 
> The reason is that the ORC unwind code won't get pass the return_to_handler
> callback installed by fgraph return probe machinery.
> 
> Solving this by creating stack frame in return_to_handler expected by
> ftrace_graph_ret_addr function to recover original return address and
> continue with the unwind.
> 
> Also updating the pt_regs data with cs/flags/rsp which are needed for
> successful stack retrieval from ebpf bpf_get_stackid helper.
>  - in get_perf_callchain we check user_mode(regs) so CS has to be set
>  - in perf_callchain_kernel we call perf_hw_regs(regs), so EFLAGS/FIXED
>     has to be unset
> 
> Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> Signed-off-by: Jiri Olsa <jolsa@kernel.org>
> ---
>  arch/x86/include/asm/ftrace.h |  5 +++++
>  arch/x86/kernel/ftrace_64.S   |  8 +++++++-
>  include/linux/ftrace.h        | 10 +++++++++-
>  3 files changed, 21 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
> index 93156ac4ffe0..b08c95872eed 100644
> --- a/arch/x86/include/asm/ftrace.h
> +++ b/arch/x86/include/asm/ftrace.h
> @@ -56,6 +56,11 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
>  	return &arch_ftrace_regs(fregs)->regs;
>  }
>  
> +#define arch_ftrace_partial_regs(regs) do {	\
> +	regs->flags &= ~X86_EFLAGS_FIXED;	\
> +	regs->cs = __KERNEL_CS;			\
> +} while (0)

I lost the plot. Why here and not in asm below?

>  #define arch_ftrace_fill_perf_regs(fregs, _regs) do {	\
>  		(_regs)->ip = arch_ftrace_regs(fregs)->regs.ip;		\
>  		(_regs)->sp = arch_ftrace_regs(fregs)->regs.sp;		\
> diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
> index 367da3638167..823dbdd0eb41 100644
> --- a/arch/x86/kernel/ftrace_64.S
> +++ b/arch/x86/kernel/ftrace_64.S
> @@ -354,12 +354,17 @@ SYM_CODE_START(return_to_handler)
>  	UNWIND_HINT_UNDEFINED
>  	ANNOTATE_NOENDBR
>  
> +	/* Restore return_to_handler value that got eaten by previous ret instruction. */
> +	subq $8, %rsp
> +	UNWIND_HINT_FUNC
> +
>  	/* Save ftrace_regs for function exit context  */
>  	subq $(FRAME_SIZE), %rsp
>  
>  	movq %rax, RAX(%rsp)
>  	movq %rdx, RDX(%rsp)
>  	movq %rbp, RBP(%rsp)
> +	movq %rsp, RSP(%rsp)
>  	movq %rsp, %rdi
>  
>  	call ftrace_return_to_handler
> @@ -368,7 +373,8 @@ SYM_CODE_START(return_to_handler)
>  	movq RDX(%rsp), %rdx
>  	movq RAX(%rsp), %rax
>  
> -	addq $(FRAME_SIZE), %rsp
> +	addq $(FRAME_SIZE) + 8, %rsp
> +
>  	/*
>  	 * Jump back to the old return address. This cannot be JMP_NOSPEC rdi
>  	 * since IBT would demand that contain ENDBR, which simply isn't so for