linux-kernel - Re: [tip:perf/core] perf/x86: Fix USER/KERNEL tagging of 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-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1341598329.7709.57.camel@twins>
Date:	Fri, 06 Jul 2012 20:12:09 +0200
From:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
To:	Linus Torvalds <torvalds@...ux-foundation.org>
Cc:	mingo@...nel.org, hpa@...or.com, eranian@...gle.com,
	linux-kernel@...r.kernel.org, fweisbec@...il.com,
	akpm@...ux-foundation.org, tglx@...utronix.de,
	linux-tip-commits@...r.kernel.org
Subject: Re: [tip:perf/core] perf/x86: Fix USER/KERNEL tagging of samples

On Fri, 2012-07-06 at 09:29 -0700, Linus Torvalds wrote:
> On Thu, Jul 5, 2012 at 11:20 PM, tip-bot for Peter Zijlstra
> <a.p.zijlstra@...llo.nl> wrote:
> >
> > Several perf interrupt handlers (PEBS,IBS,BTS) re-write regs->ip but
> > do not update the segment registers. So use an regs->ip based test
> > instead of an regs->cs/regs->flags based test.
> 
> Christ, people, YOU CANNOT DO THIS!
> 
> It is never *ever* valid to test the IP to see if you're in kernel
> space or user space. People can do various odd segments etc, the IP is
> totally meaningless.
> 
> If the perf handlers fake the IP information, they had better fake the
> CS/eflags information too. Because it is *wrong* to look at IP. Don't
> do it.

PEBS, BTS, LBR don't have CS. PEBS does have eflags.

If we cannot do this I'm not sure what we can do :/
--
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/