Re: [PATCH v5 3/5] perf: script: add field 'disasm' to display mnemonic instructions

[Adrian Hunter]

On 22/01/24 13:20, Changbin Du wrote:
> In addition to the 'insn' field, this adds a new field 'disasm' to
> display mnemonic instructions instead of the raw code.
> 
> $ sudo perf script -F +disasm
>        perf-exec 1443864 [006] 2275506.209848:          psb:  psb offs: 0                                      0 [unknown] ([unknown])
>        perf-exec 1443864 [006] 2275506.209848:          cbr:  cbr: 41 freq: 4100 MHz (114%)                    0 [unknown] ([unknown])
>               ls 1443864 [006] 2275506.209905:          1  branches:uH:      7f216b426100 _start+0x0 (/usr/lib/x86_64-linux-gnu/ld-2.31.so)	movq %rsp, %rdi
>               ls 1443864 [006] 2275506.209908:          1  branches:uH:      7f216b426103 _start+0x3 (/usr/lib/x86_64-linux-gnu/ld-2.31.so)	callq _dl_start+0x0
> 
> Signed-off-by: Changbin Du <changbin.du@xxxxxxxxxx>
> 
> ---
> v2:
>   - update Documentation.
> ---
>  tools/perf/Documentation/perf-script.txt | 13 +++++++------
>  tools/perf/builtin-script.c              |  8 +++++++-
>  2 files changed, 14 insertions(+), 7 deletions(-)
> 
> diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
> index ff9a52e44688..578fa59f51a5 100644
> --- a/tools/perf/Documentation/perf-script.txt
> +++ b/tools/perf/Documentation/perf-script.txt
> @@ -132,9 +132,10 @@ OPTIONS
>          Comma separated list of fields to print. Options are:
>          comm, tid, pid, time, cpu, event, trace, ip, sym, dso, dsoff, addr, symoff,
>          srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
> -        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, insnlen, synth,
> -        phys_addr, metric, misc, srccode, ipc, data_page_size, code_page_size, ins_lat,
> -        machine_pid, vcpu, cgroup, retire_lat.
> +        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, disasm,
> +        insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size,
> +        code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat.
> +
>          Field list can be prepended with the type, trace, sw or hw,
>          to indicate to which event type the field list applies.
>          e.g., -F sw:comm,tid,time,ip,sym  and -F trace:time,cpu,trace
> @@ -217,9 +218,9 @@ OPTIONS
>  	Instruction Trace decoding. For calls and returns, it will display the
>  	name of the symbol indented with spaces to reflect the stack depth.
>  
> -	When doing instruction trace decoding insn and insnlen give the
> -	instruction bytes and the instruction length of the current
> -	instruction.
> +	When doing instruction trace decoding, insn, disasm and insnlen give the
> +	instruction bytes, disassembled instructions (requires libcapstone support)
> +	and the instruction length of the current instruction respectively.
>  
>  	The synth field is used by synthesized events which may be created when
>  	Instruction Trace decoding.
> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
> index 4817a37f16e2..4ac9670704ff 100644
> --- a/tools/perf/builtin-script.c
> +++ b/tools/perf/builtin-script.c
> @@ -135,6 +135,7 @@ enum perf_output_field {
>  	PERF_OUTPUT_CGROUP          = 1ULL << 39,
>  	PERF_OUTPUT_RETIRE_LAT      = 1ULL << 40,
>  	PERF_OUTPUT_DSOFF           = 1ULL << 41,
> +	PERF_OUTPUT_DISASM          = 1ULL << 42,
>  };
>  
>  struct perf_script {
> @@ -190,6 +191,7 @@ struct output_option {
>  	{.str = "bpf-output",   .field = PERF_OUTPUT_BPF_OUTPUT},
>  	{.str = "callindent", .field = PERF_OUTPUT_CALLINDENT},
>  	{.str = "insn", .field = PERF_OUTPUT_INSN},
> +	{.str = "disasm", .field = PERF_OUTPUT_DISASM},
>  	{.str = "insnlen", .field = PERF_OUTPUT_INSNLEN},
>  	{.str = "brstackinsn", .field = PERF_OUTPUT_BRSTACKINSN},
>  	{.str = "brstackoff", .field = PERF_OUTPUT_BRSTACKOFF},
> @@ -1515,6 +1517,10 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
>  		printed += fprintf(fp, " insn: ");
>  		printed += sample__fprintf_insn_raw(sample, fp);
>  	}
> +	if (PRINT_FIELD(DISASM) && sample->insn_len) {
> +		printed += fprintf(fp, "\t\t");

This is good, except if both 'insn' and 'disasm' are used together.
It either:
 a) without libcapstone, prints insn bytes twice

	Probably simpler to make 'disasm' without libcapstone
	a fatal error explaining that perf needs to be built
	with libcapstone support for 'disasm' to work.

 b) with libcapstone, disassembly does not line up nicely

> +		printed += sample__fprintf_insn(sample, thread, machine, fp);
> +	}
>  	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
>  		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
>  
> @@ -3900,7 +3906,7 @@ int cmd_script(int argc, const char **argv)
>  		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff,"
>  		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
>  		     "brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
> -		     "brstackinsnlen,brstackoff,callindent,insn,insnlen,synth,"
> +		     "brstackinsnlen,brstackoff,callindent,insn,disasm,insnlen,synth,"
>  		     "phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
>  		     "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat",
>  		     parse_output_fields),