linux-kernel - Re: [for-next][PATCH 2/2] tracing: Use temp buffer when filtering events

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

Date:	Thu, 5 May 2016 11:32:51 -0400
From:	Steven Rostedt <rostedt@...dmis.org>
To:	Alexei Starovoitov <alexei.starovoitov@...il.com>
Cc:	linux-kernel@...r.kernel.org, Ingo Molnar <mingo@...nel.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Alexei Starovoitov <ast@...nel.org>
Subject: Re: [for-next][PATCH 2/2] tracing: Use temp buffer when filtering
 events

On Thu, 5 May 2016 08:20:57 -0700
Alexei Starovoitov <alexei.starovoitov@...il.com> wrote:


> tricky :)

Thanks ;-)

> so the buffer is used only for non-recursive events.
> If the 2nd event on the same cpu also needs filtering it will
> be going through normal trace_buffer_lock_reserve() path,
> but then it means such events will be out of order if both
> are accepted, right?
> Is that a concern or not?

Well, what is the order?

Think about it, what's the difference if the interrupt came in just
before the trace or just after? It still came in the same location with
respect to the normal flow of the code. The only difference is, where
we recorded it.

-- Steve