linux-kernel - Re: [PATCH v3] perf annotate: Add itrace options support

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <5b0e6138-854a-2996-3551-7e10ba0ce2b7@huawei.com>
Date:   Tue, 15 Jun 2021 17:28:43 +0800
From:   Yang Jihong <yangjihong1@...wei.com>
To:     Adrian Hunter <adrian.hunter@...el.com>, <acme@...nel.org>,
        Leo Yan <leo.yan@...aro.org>
CC:     <peterz@...radead.org>, <mingo@...hat.com>, <mark.rutland@....com>,
        <alexander.shishkin@...ux.intel.com>, <jolsa@...hat.com>,
        <namhyung@...nel.org>, <linux-perf-users@...r.kernel.org>,
        <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v3] perf annotate: Add itrace options support

Hello, Adrain,

On 2021/6/15 16:22, Adrian Hunter wrote:
> On 15/06/21 5:40 am, Yang Jihong wrote:
>> The "auxtrace_info" and "auxtrace" functions are not set in "tool" member of
>> "annotate". As a result, perf annotate does not support parsing itrace data.
>>
>> Before:
>>
>>    # perf record -e arm_spe_0/branch_filter=1/ -a sleep 1
>>    [ perf record: Woken up 9 times to write data ]
>>    [ perf record: Captured and wrote 20.874 MB perf.data ]
>>    # perf annotate --stdio
>>    Error:
>>    The perf.data data has no samples!
>>
>> Solution:
>> 1.Add itrace options in help,
>> 2.Set hook functions of "auxtrace_info" and "auxtrace" in perf_tool.
>>
>> After:
>>
>>    # perf record --all-user -e arm_spe_0/branch_filter=1/ ls
>>    Couldn't synthesize bpf events.
>>    perf.data
>>    [ perf record: Woken up 1 times to write data ]
>>    [ perf record: Captured and wrote 0.010 MB perf.data ]
>>    # perf annotate --stdio
>>     Percent |      Source code & Disassembly of libc-2.28.so for branch-miss (1 samples, percent: local period)
>>    ------------------------------------------------------------------------------------------------------------
>>             :
>>             :
>>             :
>>             :           Disassembly of section .text:
>>             :
>>             :           0000000000066180 <__getdelim@@GLIBC_2.17>:
>>        0.00 :   66180:  stp     x29, x30, [sp, #-96]!
>>        0.00 :   66184:  cmp     x0, #0x0
>>        0.00 :   66188:  ccmp    x1, #0x0, #0x4, ne  // ne = any
>>        0.00 :   6618c:  mov     x29, sp
>>        0.00 :   66190:  stp     x24, x25, [sp, #56]
>>
>> Signed-off-by: Yang Jihong <yangjihong1@...wei.com>
>> ---
>>
>> Changes since v2:
>>   - Updating tools/perf/Documentation/perf-annotate.txt.
>>   - Add test result to commit message.
>>
>> Changes since v1:
>>   - Adjust spaces to maintain alignment in "tool".
>>
>>   tools/perf/Documentation/perf-annotate.txt |  7 +++++++
>>   tools/perf/builtin-annotate.c              | 10 ++++++++++
>>   2 files changed, 17 insertions(+)
>>
>> diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
>> index 80c1be5d566c..33c2521cba4a 100644
>> --- a/tools/perf/Documentation/perf-annotate.txt
>> +++ b/tools/perf/Documentation/perf-annotate.txt
>> @@ -58,6 +58,13 @@ OPTIONS
>>   --ignore-vmlinux::
>>   	Ignore vmlinux files.
>>   
>> +--itrace::
>> +	Options for decoding instruction tracing data. The options are:
>> +
>> +include::itrace.txt[]
>> +
>> +	To disable decoding entirely, use --no-itrace.
>> +
>>   -m::
>>   --modules::
>>           Load module symbols. WARNING: use only with -k and LIVE kernel.
>> diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
>> index 49627a7bed7c..8f87658eff31 100644
>> --- a/tools/perf/builtin-annotate.c
>> +++ b/tools/perf/builtin-annotate.c
>> @@ -474,6 +474,8 @@ int cmd_annotate(int argc, const char **argv)
>>   			.attr	= perf_event__process_attr,
>>   			.build_id = perf_event__process_build_id,
>>   			.tracing_data   = perf_event__process_tracing_data,
>> +			.auxtrace_info	= perf_event__process_auxtrace_info,
>> +			.auxtrace	= perf_event__process_auxtrace,
> 
> For sample mode, Intel PT also needs:
> 
> 			.id_index	 = perf_event__process_id_index,
> 
Thanks for testing this patch in the Intel PT environment.
OK, I add the id_index processing function to the v4 patch:
https://lore.kernel.org/patchwork/patch/1446727/

Thanks,
Jihong