Re: [PATCH bpf-next v3 2/6] x86/ftrace: implement DYNAMIC_FTRACE_WITH_JMP

[Jiri Olsa <olsajiri@gmail.com>]

On Tue, Nov 18, 2025 at 08:36:30PM +0800, Menglong Dong wrote:
> Implement the DYNAMIC_FTRACE_WITH_JMP for x86_64. In ftrace_call_replace,
> we will use JMP32_INSN_OPCODE instead of CALL_INSN_OPCODE if the address
> should use "jmp".
> 
> Meanwhile, adjust the direct call in the ftrace_regs_caller. The RSB is
> balanced in the "jmp" mode. Take the function "foo" for example:
> 
>  original_caller:
>  call foo -> foo:
>          call fentry -> fentry:
>                  [do ftrace callbacks ]
>                  move tramp_addr to stack
>                  RET -> tramp_addr
>                          tramp_addr:
>                          [..]
>                          call foo_body -> foo_body:
>                                  [..]
>                                  RET -> back to tramp_addr
>                          [..]
>                          RET -> back to original_caller
> 
> Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
> ---
>  arch/x86/Kconfig            |  1 +
>  arch/x86/kernel/ftrace.c    |  7 ++++++-
>  arch/x86/kernel/ftrace_64.S | 12 +++++++++++-
>  3 files changed, 18 insertions(+), 2 deletions(-)
> 
> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
> index fa3b616af03a..462250a20311 100644
> --- a/arch/x86/Kconfig
> +++ b/arch/x86/Kconfig
> @@ -230,6 +230,7 @@ config X86
>  	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if X86_64
>  	select HAVE_FTRACE_REGS_HAVING_PT_REGS	if X86_64
>  	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
> +	select HAVE_DYNAMIC_FTRACE_WITH_JMP	if X86_64
>  	select HAVE_SAMPLE_FTRACE_DIRECT	if X86_64
>  	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
>  	select HAVE_EBPF_JIT
> diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
> index 4450acec9390..0543b57f54ee 100644
> --- a/arch/x86/kernel/ftrace.c
> +++ b/arch/x86/kernel/ftrace.c
> @@ -74,7 +74,12 @@ static const char *ftrace_call_replace(unsigned long ip, unsigned long addr)
>  	 * No need to translate into a callthunk. The trampoline does
>  	 * the depth accounting itself.
>  	 */
> -	return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
> +	if (ftrace_is_jmp(addr)) {
> +		addr = ftrace_jmp_get(addr);
> +		return text_gen_insn(JMP32_INSN_OPCODE, (void *)ip, (void *)addr);
> +	} else {
> +		return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr);
> +	}
>  }
>  
>  static int ftrace_verify_code(unsigned long ip, const char *old_code)
> diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
> index 823dbdd0eb41..a132608265f6 100644
> --- a/arch/x86/kernel/ftrace_64.S
> +++ b/arch/x86/kernel/ftrace_64.S
> @@ -285,8 +285,18 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
>  	ANNOTATE_NOENDBR
>  	RET
>  
> +1:
> +	testb	$1, %al
> +	jz	2f
> +	andq $0xfffffffffffffffe, %rax
> +	movq %rax, MCOUNT_REG_SIZE+8(%rsp)
> +	restore_mcount_regs
> +	/* Restore flags */
> +	popfq
> +	RET

is this hunk the reason for the 0x1 jmp-bit you set in the address?

I wonder if we introduced new flag in dyn_ftrace::flags for this,
then we'd need to have extra ftrace trampoline for jmp ftrace_ops

jirka