linux-kernel - Re: [GIT PULL] perf/urgent fixes

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] [day] [month] [year] [list]

Message-ID: <20191107070229.GA30739@gmail.com>
Date:   Thu, 7 Nov 2019 08:02:29 +0100
From:   Ingo Molnar <mingo@...nel.org>
To:     Arnaldo Carvalho de Melo <acme@...nel.org>
Cc:     Thomas Gleixner <tglx@...utronix.de>, Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Clark Williams <williams@...hat.com>,
        linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
        Adrian Hunter <adrian.hunter@...el.com>,
        Andi Kleen <ak@...ux.intel.com>,
        "Gustavo A . R . Silva" <gustavo@...eddedor.com>,
        Thomas Richter <tmricht@...ux.ibm.com>,
        Yunfeng Ye <yeyunfeng@...wei.com>,
        Arnaldo Carvalho de Melo <acme@...hat.com>
Subject: Re: [GIT PULL] perf/urgent fixes


* Arnaldo Carvalho de Melo <acme@...nel.org> wrote:

> Em Mon, Oct 21, 2019 at 08:23:54AM +0200, Ingo Molnar escreveu:
> > Secondly, there also appears to be a TUI weirdness when the annotated 
> > kernel functions are small (or weird): the blue cursor is stuck at the 
> > top and I cannot move between the annotated instructions with the down/up 
> > arrow:
> > 
> > Samples: 13M of event 'cycles', 4000 Hz, Event count (approx.): 1272420588851
> > clear_page_rep  /usr/lib/debug/boot/vmlinux-5.4.0-rc3-custom-00557-gb6c81ae120e0 [Percent: local period]
> >   0.01 │     mov  $0x200,%ecx                                                                                                                                                                      ▒
> >        │   xorl %eax,%eax                                                                                                                                                                          ▒
> >   0.01 │     xor  %eax,%eax                                                                                                                                                                        ▒
> >        │   rep stosq                                                                                                                                                                               ▒
> >  99.27 │     rep  stos %rax,%es:(%rdi)                                                                                                                                                             ▒
> >        │   ret                                                                                                                                                                                     ▒
> >   0.71 │   ← retq                         
> > 
> > I can still exit the screen with 'q', and can move around in larger 
> > annotated kernel functions. Not sure whether it's related to function 
> > size, or perhaps to the 'hottest' instruction that the cursor is normally 
> > placed at.
> 
> I couldn't reproduce this one so far, with another small function,
> clear_page_erms, what happens is that the cursor seems to be hidden at the
> bottom, if you press the "magic" 'D' hotkey it will tell (at the bottom of the
> screen) that the idx is at 18, which  for a function with just 8 output lines
> doesn't make sense:
> 
> Samples: 12K of event 'cycles', 4000 Hz, Event count (approx.): 2219443843
> clear_page_erms  /proc/kcore [Percent: local period]
> Percent│                                                                 ◆
>        │                                                                 ▒
>        │                                                                 ▒
>        │    Disassembly of section load0:                                ▒
>        │                                                                 ▒
>        │    ffffffffab9d17c0 <load0>:                                    ▒
>        │      mov  $0x1000,%ecx                                          ▒
>        │      xor  %eax,%eax                                             ▒
> 100.00 │      rep  stos %al,%es:(%rdi)                                   ▒
>        │    ← retq                                                       ▒
>                                                                          ▒
> 1: nr_ent=20, height=35, idx=18, top_idx=1, nr_asm_entries=8
> 
> Doesn't make sense, there aren't 20 entries nor the idx is 18, the
> nr_asm_entries is right, I'll try to follow up on this one...
> 
> But you can in these cases try to go on pressin the up arrow till the cursor
> appears, etc.

Yeah, I can reproduce this too - and don't see the original weirdness 
anymore. :-/

Will re-report if it happens again.

Thanks,

	Ingo