linux-kernel - Re: perf top using /proc/kcore

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: <525CDD11.40803@intel.com>
Date:	Tue, 15 Oct 2013 09:13:37 +0300
From:	Adrian Hunter <adrian.hunter@...el.com>
To:	Arnaldo Carvalho de Melo <acme@...stprotocols.net>
CC:	David Ahern <dsahern@...il.com>, Jiri Olsa <jolsa@...hat.com>,
	Namhyung Kim <namhyung@...il.com>,
	Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: perf top using /proc/kcore

On 15/10/13 05:09, Arnaldo Carvalho de Melo wrote:
> Hi Adrian,
> 
> 	While testing 'perf top -U' to reply a message in another thread
> I noticed that ksm symbols appeared as '[kernel]', and only when I tried
> 'perf top -U -v' to look at the DSO long name I noticed that it was...
> /proc/kcore.
> 
> 	Question is: since we have access to /proc/modules, can't we
> parse that, as when we have access to vmlinux, and recreate the mmaps,
> etc, and see:
> 
> 	[module]  symbol
> 
> 	Instead of grouping everything into a single [kernel] bucket?

I would suggest just splitting the maps and giving them names, rather than
splitting the dso as well.  That would mean changing places that have:

	map->dso->short_name

to

	map->name ? map->name : map->dso->short_name


--
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/