Re: [PATCH 2/3] perf: script: use capstone disasm engine to show assembly instructions

[Thomas Richter]

On 1/16/24 12:34, Changbin Du wrote:
> Currently, the instructions of samples are shown as raw hex strings
> which are hard to read. x86 has a special option '--xed' to disassemble
> the hex string via intel XED tool.
> 
> Here we use capstone as our disassembler engine to give more friendly
> instructions. We select libcapstone because capstone can provide more
> insn details. Perf will fallback to raw instructions if libcapstone is
> not available.
> 
> The advantages compared to XED tool:
>  * Support arm, arm64, x86-32, x86_64 (more could be supported),
>    xed only for x86_64.
>  * Immediate address operands are shown as symbol+offs.
> 
> Before:
> $ sudo perf record --event intel_pt//u -- ls
> $ sudo perf script --insn-trace
>             perf 17423 [000] 423271.557970005:      7f2d95f16217 __GI___ioctl+0x7 (/lib/x86_64-linux-gnu/libc-2.27.so) insn: 48 3d 01 f0 ff ff
>             perf 17423 [000] 423271.557970005:      7f2d95f1621d __GI___ioctl+0xd (/lib/x86_64-linux-gnu/libc-2.27.so) insn: 73 01
>             perf 17423 [000] 423271.557970338:      7f2d95f1621f __GI___ioctl+0xf (/lib/x86_64-linux-gnu/libc-2.27.so) insn: c3
>             perf 17423 [000] 423271.557970338:      5593ad3346d7 perf_evsel__enable_cpu+0x97 (/work/linux/tools/perf/perf) insn: 85 c0
>             perf 17423 [000] 423271.557970338:      5593ad3346d9 perf_evsel__enable_cpu+0x99 (/work/linux/tools/perf/perf) insn: 75 12
>             perf 17423 [000] 423271.557970338:      5593ad3346db perf_evsel__enable_cpu+0x9b (/work/linux/tools/perf/perf) insn: 49 8b 84 24 a8 00 00 00
>             perf 17423 [000] 423271.557970338:      5593ad3346e3 perf_evsel__enable_cpu+0xa3 (/work/linux/tools/perf/perf) insn: 48 8b 50 20
> 
> After:
> $ sudo perf script --insn-trace
>             perf 17423 [000] 423271.557970005:      7f2d95f16217 __GI___ioctl+0x7 (/lib/x86_64-linux-gnu/libc-2.27.so) insn: cmpq $-0xfff, %rax
>             perf 17423 [000] 423271.557970005:      7f2d95f1621d __GI___ioctl+0xd (/lib/x86_64-linux-gnu/libc-2.27.so) insn: jae __GI___ioctl+0x10
>             perf 17423 [000] 423271.557970338:      7f2d95f1621f __GI___ioctl+0xf (/lib/x86_64-linux-gnu/libc-2.27.so) insn: retq
>             perf 17423 [000] 423271.557970338:      5593ad3346d7 perf_evsel__enable_cpu+0x97 (/work/linux/tools/perf/perf) insn: testl %eax, %eax
>             perf 17423 [000] 423271.557970338:      5593ad3346d9 perf_evsel__enable_cpu+0x99 (/work/linux/tools/perf/perf) insn: jne perf_evsel__enable_cpu+0xad
>             perf 17423 [000] 423271.557970338:      5593ad3346db perf_evsel__enable_cpu+0x9b (/work/linux/tools/perf/perf) insn: movq 0xa8(%r12), %rax
>             perf 17423 [000] 423271.557970338:      5593ad3346e3 perf_evsel__enable_cpu+0xa3 (/work/linux/tools/perf/perf) insn: movq 0x20(%rax), %rdx
>             perf 17423 [000] 423271.557970338:      5593ad3346e7 perf_evsel__enable_cpu+0xa7 (/work/linux/tools/perf/perf) insn: cmpl %edx, %ebx
>             perf 17423 [000] 423271.557970338:      5593ad3346e9 perf_evsel__enable_cpu+0xa9 (/work/linux/tools/perf/perf) insn: jl perf_evsel__enable_cpu+0x60
>             perf 17423 [000] 423271.557970338:      5593ad3346eb perf_evsel__enable_cpu+0xab (/work/linux/tools/perf/perf) insn: xorl %eax, %eax
> 
> Signed-off-by: Changbin Du <changbin.du@xxxxxxxxxx>
> ---

...

> diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
> new file mode 100644
> index 000000000000..c8d9741748cd
> --- /dev/null
> +++ b/tools/perf/util/print_insn.c
> @@ -0,0 +1,118 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Instruction binary disassembler based on capstone.
> + *
> + * Author(s): Changbin Du <changbin.du@xxxxxxxxxx>
> + */
> +#include "print_insn.h"
> +#include <stdlib.h>
> +#include <string.h>
> +#include <stdbool.h>
> +#include "util/debug.h"
> +#include "util/symbol.h"
> +#include "machine.h"
> +
> +size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
> +{
> +	int printed = 0;
> +
> +	for (int i = 0; i < sample->insn_len; i++)
> +		printed += fprintf(fp, "%02x ", (unsigned char)sample->insn[i]);
> +	return printed;
> +}
> +
> +#ifdef HAVE_LIBCAPSTONE_SUPPORT
> +#include <capstone/capstone.h>
> +
> +static int capstone_init(struct machine *machine, csh *cs_handle)
> +{
> +	cs_arch arch;
> +	cs_mode mode;
> +
> +	if (machine__is(machine, "x86_64")) {
> +		arch = CS_ARCH_X86;
> +		mode = CS_MODE_64;
> +	} else if (machine__normalized_is(machine, "x86")) {
> +		arch = CS_ARCH_X86;
> +		mode = CS_MODE_32;
> +	} else if (machine__normalized_is(machine, "arm64")) {
> +		arch = CS_ARCH_ARM64;
> +		mode = CS_MODE_ARM;
> +	} else if (machine__normalized_is(machine, "arm")) {
> +		arch = CS_ARCH_ARM;
> +		mode = CS_MODE_ARM + CS_MODE_V8;
> +	} else {
> +		return -1;
> +	}
> ...

Did you forgot to support s390? Or was it omitted on intention?
Something along the lines will support s390:

 # git diff util/print_insn.c
diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
index c8d9741748cd..c5127910c75b 100644
--- a/tools/perf/util/print_insn.c
+++ b/tools/perf/util/print_insn.c
@@ -41,6 +41,9 @@ static int capstone_init(struct machine *machine, csh *cs_handle)
        } else if (machine__normalized_is(machine, "arm")) {
                arch = CS_ARCH_ARM;
                mode = CS_MODE_ARM + CS_MODE_V8;
+       } else if (machine__normalized_is(machine, "s390x")) {
+               arch = CS_ARCH_SYSZ;
+               mode = CS_MODE_BIG_ENDIAN;
        } else {
                return -1;
        }
  #

Thanks a lot for including these line in your next version.

-- 
Thomas Richter, Dept 3303, IBM s390 Linux Development, Boeblingen, Germany
--
IBM Deutschland Research & Development GmbH

Vorsitzender des Aufsichtsrats: Wolfgang Wendt

Geschäftsführung: David Faller

Sitz der Gesellschaft: Böblingen / Registergericht: Amtsgericht Stuttgart, HRB 243294