Re: [PATCH v2 02/16] perf capstone: Fix arm64 jump/adrp disassembly mismatch with objdump

[Namhyung Kim]

On Fri, Apr 03, 2026 at 09:47:46AM +0000, Tengda Wu wrote:
> The jump and adrp instructions parsed by libcapstone currently lack
> symbolic representation and use a '#' prefix for addresses. This
> format is inconsistent with objdump's output, which causes subsequent
> parsing in jump__parse() and arm64_mov__parse() to fail.
> 
> Example mismatch:
>   Current: b #0xffff8000800114c8
>   Fix:     b ffff8000800114c8 <el0t_64_sync+0x108>
> 
>   Current: adrp x18, #0xffff800081f5f000
>   Fix:     adrp x18, ffff800081f5f000 <this_cpu_vector>
> 
> Fix this by implementing extended formatting for these arm64
> instructions during symbol__disassemble_capstone(). This ensures
> the output matches objdump's expected style, including the raw
> address and the associated <symbol+offset> suffix.
> 
> Signed-off-by: Tengda Wu <wutengda@xxxxxxxxxxxxxxx>
> ---
>  tools/perf/util/capstone.c | 107 ++++++++++++++++++++++++++++++++-----
>  tools/perf/util/disasm.c   |   5 ++
>  tools/perf/util/disasm.h   |   1 +
>  3 files changed, 101 insertions(+), 12 deletions(-)
> 
> diff --git a/tools/perf/util/capstone.c b/tools/perf/util/capstone.c
> index 25cf6e15ec27..1d8421d2d98c 100644
> --- a/tools/perf/util/capstone.c
> +++ b/tools/perf/util/capstone.c
> @@ -255,10 +255,6 @@ static void print_capstone_detail(struct cs_insn *insn, char *buf, size_t len,
>  	struct map *map = args->ms->map;
>  	struct symbol *sym;
>  
> -	/* TODO: support more architectures */
> -	if (!arch__is_x86(args->arch))
> -		return;
> -
>  	if (insn->detail == NULL)
>  		return;
>  
> @@ -305,6 +301,98 @@ static void print_capstone_detail(struct cs_insn *insn, char *buf, size_t len,
>  	}
>  }
>  
> +static void format_capstone_insn_x86(struct cs_insn *insn, char *buf,
> +				     size_t len, struct annotate_args *args,
> +				     u64 addr)
> +{
> +	int printed;
> +
> +	printed = scnprintf(buf, len, "       %-7s %s",
> +			    insn->mnemonic, insn->op_str);
> +	buf += printed;
> +	len -= printed;
> +
> +	print_capstone_detail(insn, buf, len, args, addr);
> +}
> +
> +static void format_capstone_insn_arm64(struct cs_insn *insn, char *buf,
> +				       size_t len, struct annotate_args *args,
> +				       u64 addr)
> +{
> +	struct map *map = args->ms->map;
> +	struct symbol *sym;
> +	char *last_imm, *endptr;
> +	u64 orig_addr;
> +
> +	scnprintf(buf, len, "       %-7s %s",
> +		  insn->mnemonic, insn->op_str);
> +	/*
> +	 * Adjust instructions to keep the existing behavior with objdump.
> +	 *
> +	 * Example conversion:
> +	 * From: b #0xffff8000800114c8
> +	 * To:   b ffff8000800114c8 <el0t_64_sync+0x108>
> +	 */
> +	switch (insn->id) {
> +	case ARM64_INS_B:
> +	case ARM64_INS_BL:
> +	case ARM64_INS_CBNZ:
> +	case ARM64_INS_CBZ:
> +	case ARM64_INS_TBNZ:
> +	case ARM64_INS_TBZ:
> +	case ARM64_INS_ADRP:
> +		/* Extract last immediate value as address */
> +		last_imm = strrchr(buf, '#');
> +		if (!last_imm)
> +			return;
> +
> +		orig_addr = strtoull(last_imm + 1, &endptr, 16);
> +		if (endptr == last_imm + 1)
> +			return;
> +
> +		/* Relocate map that contains the address */
> +		if (dso__kernel(map__dso(map))) {
> +			map = maps__find(map__kmaps(map), orig_addr);
> +			if (map == NULL)
> +				return;

I know you copied the logic from x86, but I've realized that it leaks a
refcount for the new kernel map returned from maps__find().  This needs
to be fixed separately.

Thanks,
Namhyung


> +		}
> +
> +		/* Convert it to map-relative address for search */
> +		addr = map__map_ip(map, orig_addr);
> +
> +		sym = map__find_symbol(map, addr);
> +		if (sym == NULL)
> +			return;
> +
> +		/* Symbolize the resolved address */
> +		len = len - (last_imm - buf);
> +		if (addr == sym->start) {
> +			scnprintf(last_imm, len, "%"PRIx64" <%s>",
> +				  orig_addr, sym->name);
> +		} else {
> +			scnprintf(last_imm, len, "%"PRIx64" <%s+%#"PRIx64">",
> +				  orig_addr, sym->name, addr - sym->start);
> +		}
> +		break;
> +	default:
> +		break;
> +	}
> +}
> +
> +static void format_capstone_insn(struct cs_insn *insn, char *buf, size_t len,
> +				 struct annotate_args *args, u64 addr)
> +{
> +	/* TODO: support more architectures */
> +	if (arch__is_x86(args->arch))
> +		format_capstone_insn_x86(insn, buf, len, args, addr);
> +	else if (arch__is_arm64(args->arch))
> +		format_capstone_insn_arm64(insn, buf, len, args, addr);
> +	else {
> +		scnprintf(buf, len, "       %-7s %s",
> +			  insn->mnemonic, insn->op_str);
> +	}
> +}
> +
>  struct find_file_offset_data {
>  	u64 ip;
>  	u64 offset;
> @@ -381,14 +469,9 @@ int symbol__disassemble_capstone(const char *filename __maybe_unused,
>  
>  	free_count = count = perf_cs_disasm(handle, buf, buf_len, start, buf_len, &insn);
>  	for (i = 0, offset = 0; i < count; i++) {
> -		int printed;
> -
> -		printed = scnprintf(disasm_buf, sizeof(disasm_buf),
> -				    "       %-7s %s",
> -				    insn[i].mnemonic, insn[i].op_str);
> -		print_capstone_detail(&insn[i], disasm_buf + printed,
> -				      sizeof(disasm_buf) - printed, args,
> -				      start + offset);
> +		format_capstone_insn(&insn[i], disasm_buf,
> +				     sizeof(disasm_buf), args,
> +				     start + offset);
>  
>  		args->offset = offset;
>  		args->line = disasm_buf;
> diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
> index 40fcaed5d0b1..988b2b748e11 100644
> --- a/tools/perf/util/disasm.c
> +++ b/tools/perf/util/disasm.c
> @@ -202,6 +202,11 @@ bool arch__is_powerpc(const struct arch *arch)
>  	return arch->id.e_machine == EM_PPC || arch->id.e_machine == EM_PPC64;
>  }
>  
> +bool arch__is_arm64(const struct arch *arch)
> +{
> +	return arch->id.e_machine == EM_AARCH64;
> +}
> +
>  static void ins_ops__delete(struct ins_operands *ops)
>  {
>  	if (ops == NULL)
> diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h
> index a6e478caf61a..d3730ed86dba 100644
> --- a/tools/perf/util/disasm.h
> +++ b/tools/perf/util/disasm.h
> @@ -111,6 +111,7 @@ struct annotate_args {
>  const struct arch *arch__find(uint16_t e_machine, uint32_t e_flags, const char *cpuid);
>  bool arch__is_x86(const struct arch *arch);
>  bool arch__is_powerpc(const struct arch *arch);
> +bool arch__is_arm64(const struct arch *arch);
>  
>  extern const struct ins_ops call_ops;
>  extern const struct ins_ops dec_ops;
> -- 
> 2.34.1
>