linuxppc-dev.lists.ozlabs.org archive mirror
 help / color / mirror / Atom feed
From: christophe leroy <christophe.leroy@c-s.fr>
To: Joakim Tjernlund <joakim.tjernlund@transmode.se>,
	"linuxppc-dev@lists.ozlabs.org" <linuxppc-dev@lists.ozlabs.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Paul Mackerras <paulus@samba.org>,
	Anton Blanchard <anton@samba.org>,
	"sukadev@linux.vnet.ibm.com" <sukadev@linux.vnet.ibm.com>
Subject: Re: Strange reports of perf events on powerpc 83xx
Date: Wed, 2 Sep 2015 20:48:56 +0200	[thread overview]
Message-ID: <55E74498.10904@c-s.fr> (raw)
In-Reply-To: <1441203638.3349.203.camel@transmode.se>



Le 02/09/2015 16:20, Joakim Tjernlund a écrit :
> On Thu, 2015-08-27 at 15:58 +0200, leroy christophe wrote:
>> Hi,
>>
>> Has anybody already used 'perf' tool on powerpc MPC83xx ?
>>
>> I have been succesfully using perf on MPC8xx, but on MPC83xx I get
>> something strange.
>>
>> perf record/report reports addresses on user stack, as if it was mixing
>> up D accesses and I accesses.
>>
>> Any idea of what the problem can be ?
> We are also experiencing strange addresses on 83xx, did find the cause
> of this problem?
>
> We are using Linux 4.1.0
I identified this afternoon that the issue comes from 
perf_instruction_pointer()
which reads SPRN_SIAR instead of using the NIP register from the pt_regs 
struct
According to the MPC8323 reference manual, there is no such register.

I'm looking at the history in order to fully understand the reason.
Looks like PPC_HAVE_PMU_SUPPORT is selected for all PPC_BOOK3S_32 allthought
mpc832x has no PMU.

Christophe
>
>> # Samples: 8K of event 'cpu-clock'
>> # Event count (approx.): 2196000000
>> #
>> # Overhead  Command       Shared Object       Symbol
>> # ........  ............  ..................
>> ............................................
>> #
>>        2.62%  perf_reseau4  libpthread-2.18.so  [.] __libc_send
>>        2.56%  perf_reseau4  [kernel.kallsyms]   [k] __ip_make_skb
>>        1.62%  perf_reseau4  [kernel.kallsyms]   [k] __ip_append_data.isra.39
>>        1.55%  perf_reseau4  [kernel.kallsyms]   [k] ip_finish_output
>>        1.33%  perf_reseau4  [unknown]           [k] 0x7ffffd94
>>        1.33%  perf_reseau4  [unknown]           [k] 0x7ffffd95
>>        1.28%  perf_reseau4  [unknown]           [k] 0x7ffffd97
>>        1.26%  perf_reseau4  [unknown]           [k] 0x7ffffda3
>>        1.24%  perf_reseau4  [unknown]           [k] 0x7ffffd98
>>        1.22%  perf_reseau4  [unknown]           [k] 0x7ffffd92
>>        1.22%  perf_reseau4  [unknown]           [k] 0x7ffffd9b
>>        1.22%  perf_reseau4  [unknown]           [k] 0x7ffffdaa
>>        1.21%  perf_reseau4  [unknown]           [k] 0x7ffffd96
>>        1.18%  perf_reseau4  [unknown]           [k] 0x7ffffda7
>>        1.17%  perf_reseau4  [unknown]           [k] 0x7ffffd8d
>>        1.17%  perf_reseau4  [unknown]           [k] 0x7ffffd99
>>        1.13%  perf_reseau4  [unknown]           [k] 0x7ffffd90
>>        1.13%  perf_reseau4  [unknown]           [k] 0x7ffffda2
>>        1.12%  perf_reseau4  [kernel.kallsyms]   [k] __local_bh_enable_ip
>>        1.12%  perf_reseau4  [unknown]           [k] 0x7ffffd9c
>>        1.12%  perf_reseau4  [unknown]           [k] 0x7ffffd9e
>>        1.10%  perf_reseau4  [unknown]           [k] 0x7ffffda0
>>        1.08%  perf_reseau4  [unknown]           [k] 0x7ffffd9f
>>        1.08%  perf_reseau4  [unknown]           [k] 0x7ffffda6
>>        1.05%  perf_reseau4  [unknown]           [k] 0x7ffffda8
>>        1.02%  perf_reseau4  [unknown]           [k] 0x7ffffd9a
>>        1.01%  perf_reseau4  [unknown]           [k] 0x7ffffdb0
>>        1.00%  perf_reseau4  [unknown]           [k] 0x7ffffd89
>>        1.00%  perf_reseau4  [unknown]           [k] 0x7ffffd8b
>>        1.00%  perf_reseau4  [unknown]           [k] 0x7ffffdac


---
L'absence de virus dans ce courrier électronique a été vérifiée par le logiciel antivirus Avast.
https://www.avast.com/antivirus

      reply	other threads:[~2015-09-02 18:49 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-08-27 13:58 Strange reports of perf events on powerpc 83xx leroy christophe
2015-09-02 14:20 ` Joakim Tjernlund
2015-09-02 18:48   ` christophe leroy [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=55E74498.10904@c-s.fr \
    --to=christophe.leroy@c-s.fr \
    --cc=anton@samba.org \
    --cc=joakim.tjernlund@transmode.se \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=paulus@samba.org \
    --cc=sukadev@linux.vnet.ibm.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).