linux-kernel - Re: dynamic function tracing

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 for Android: free password hash cracker in your pocket

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

Message-Id: <1228096730.4886.3.camel@localhost.localdomain>
Date:	Sun, 30 Nov 2008 20:58:50 -0500
From:	Steven Rostedt <srostedt@...hat.com>
To:	Arjan van de Ven <arjan@...radead.org>
Cc:	linux-kernel@...r.kernel.org, Steven Rostedt <rostedt@...dmis.org>,
	Frederic Weisbecker <fweisbec@...il.com>
Subject: Re: dynamic function tracing


On Fri, 2008-11-28 at 10:19 -0800, Arjan van de Ven wrote:
> Hi,
> 
> I like the new function trace format with the {}'s a lot.. but I would
> like to use it in a way I don't think would work with dynamic tracing.
> 
> What I would like to do (read: usecase) is mark a function as
> interesting (because it has some performance issue or whatever),
> and then I want to get all functions it calls (recursive) traced
> automatically for the duration of that function.
> 
> This might be implementable by, on hitting the function to trace,
> patching all trace points with a function that checks if it's this
> thread (eg this "current"), and if so, traces the call. 
> I realize it's not going to be super cheap, so it needs to be one-shot,
> but it'll form a really strong usecase in practice...

It would not be wise to enable the function pointer at that moment. But
what we could do is have a function trace enabled that will flag when a
function is hit. Then it could start tracing all functions until it
returns. This would be possible.

What we need is a better way to attach the function tracer with the
function graph.

-- Steve


--
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/