linux-kernel - perf report broken for branch stack samples

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-next>] [day] [month] [year] [list]

Date:	Wed, 01 Apr 2015 14:32:54 +0530
From:	Anshuman Khandual <khandual@...ux.vnet.ibm.com>
To:	Linux PPC dev <linuxppc-dev@...abs.org>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
CC:	Sukadev Bhattiprolu <sukadev@...ux.vnet.ibm.com>,
	Michael Ellerman <michaele@....ibm.com>,
	Arnaldo Carvalho de Melo <acme@...nel.org>,
	"ak@...ux.intel.com" <ak@...ux.intel.com>
Subject: perf report broken for branch stack samples

Hello,

perf report is not showing up the branch stack sample results in the
from_symbol ---> to_symbol format even if the perf.data file has got
the samples (through 'perf record -b <workload>' session). Perf report
still displays the generic event based relative symbol classification
as usual. This problem can also be seen on X86. I wonder whether there
is any semantics change in the way perf report auto detects branch stack
samples in the perf.data file and reports in the intended format. After
doing a git bisect session, this following commit seems to have changed
the  perf report behavior.

commit fa94c36c29ed8bb4749b5fd7ea51a593f673dcef
Author: Andi Kleen <ak@...ux.intel.com>
Date:   Wed Nov 12 18:05:22 2014 -0800

    perf report: Add --branch-history option

    Add a --branch-history option to perf report that changes all the
    settings necessary for using the branches in callstacks.

    This is just a short cut to make this nicer to use, it does not enable
    any functionality by itself.

    v2: Change sort order. Rename option to --branch-history to
        be less confusing.
    v3: Updates
    v4: Fix conflict with newer perf base
    v5: Port to latest tip
    v6: Add more comments. Remove CCKEY_ADDRESS setting. Remove
        unnecessary branch_mode setting. Use a boolean.

    Signed-off-by: Andi Kleen <ak@...ux.intel.com>
    Cc: Jiri Olsa <jolsa@...hat.com>
    Cc: Namhyung Kim <namhyung@...nel.org>
    Link: http://lkml.kernel.org/r/1415844328-4884-5-git-send-email-andi@firstfloor.org
    Signed-off-by: Arnaldo Carvalho de Melo <acme@...hat.com>

I dont have much context of this change but it seems to be using branch
records along with call chain data (provided you have used both -b/-j
and -g option during perf record) to display better control flow graph ?
But then if we have just used -b and not -g then it should still give us
the previous output what we used to get.

Regards
Anshuman

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/