linux-kernel - Re: [PATCH] perf report: Fix no libunwind compiled warning break s390 issue

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <7b88fdcc-9603-d3e1-d43b-b8fb8b394f70@linux.intel.com>
Date:   Wed, 8 Jan 2020 21:02:02 +0800
From:   "Jin, Yao" <yao.jin@...ux.intel.com>
To:     Jiri Olsa <jolsa@...hat.com>
Cc:     acme@...nel.org, jolsa@...nel.org, peterz@...radead.org,
        mingo@...hat.com, alexander.shishkin@...ux.intel.com,
        Linux-kernel@...r.kernel.org, ak@...ux.intel.com,
        kan.liang@...el.com, yao.jin@...el.com, tmricht@...ux.ibm.com
Subject: Re: [PATCH] perf report: Fix no libunwind compiled warning break s390
 issue



On 1/8/2020 6:27 PM, Jiri Olsa wrote:
> On Wed, Jan 08, 2020 at 03:17:45AM +0800, Jin Yao wrote:
>> Commit 800d3f561659 ("perf report: Add warning when libunwind not compiled in")
>> breaks the s390 platform. S390 uses libdw-dwarf-unwind for call chain
>> unwinding and had no support for libunwind.
>>
>> So the warning "Please install libunwind development packages during the perf build."
>> caused the confusion even if the call-graph is displayed correctly.
>>
>> This patch adds checking for HAVE_DWARF_SUPPORT, which is set when
>> libdw-dwarf-unwind is compiled in.
>>
>> Fixes: 800d3f561659 ("perf report: Add warning when libunwind not compiled in")
>>
>> Reviewed-by: Thomas Richter <tmricht@...ux.ibm.com>
>> Tested-by: Thomas Richter <tmricht@...ux.ibm.com>
>> Signed-off-by: Jin Yao <yao.jin@...ux.intel.com>
> 
> perfect, I have the same change prepared for sending, but it's
> together with making libdw default dwarf unwinder, which I'm still
> not sure we want to do, so it all got posponed ;-)
>  > would you guys be ok with that? with having libdw picked up as 
default dwarf unwinder..
> 

I've roughly compared the performance between libunwind-dev and 
libdw-dev. While in my test (on KBL desktop), for the same perf report 
command-line, it looks the perf built with libunwind-dev is much faster 
than the perf built with libdw-dev.

The command line is as following:

perf record --call-graph dwarf ./div
perf report -g graph --stdio

Maybe you give it a try. :)

> for the patch:
> 
> Acked-by: Jiri Olsa <jolsa@...hat.com>
> 
Thanks for reviewing the patch.

Thanks
Jin Yao

> thanks,
> jirka
> 
>> ---
>>   tools/perf/builtin-report.c | 6 +++---
>>   1 file changed, 3 insertions(+), 3 deletions(-)
>>
>> diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
>> index de988589d99b..66cd97cc8b92 100644
>> --- a/tools/perf/builtin-report.c
>> +++ b/tools/perf/builtin-report.c
>> @@ -412,10 +412,10 @@ static int report__setup_sample_type(struct report *rep)
>>   				PERF_SAMPLE_BRANCH_ANY))
>>   		rep->nonany_branch_mode = true;
>>   
>> -#ifndef HAVE_LIBUNWIND_SUPPORT
>> +#if !defined(HAVE_LIBUNWIND_SUPPORT) && !defined(HAVE_DWARF_SUPPORT)
>>   	if (dwarf_callchain_users) {
>> -		ui__warning("Please install libunwind development packages "
>> -			    "during the perf build.\n");
>> +		ui__warning("Please install libunwind or libdw "
>> +			    "development packages during the perf build.\n");
>>   	}
>>   #endif
>>   
>> -- 
>> 2.17.1
>>
>