linux-kernel - Re: [PATCH v7 8/8] x86/tlb: just do tlb flush on one of siblings of SMT

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]

Date:	Thu, 24 May 2012 11:42:49 +0200
From:	Peter Zijlstra <a.p.zijlstra@...llo.nl>
To:	Alex Shi <alex.shi@...el.com>
Cc:	Jan Beulich <JBeulich@...e.com>, borislav.petkov@....com,
	arnd@...db.de, akinobu.mita@...il.com, eric.dumazet@...il.com,
	fweisbec@...il.com, rostedt@...dmis.org, hughd@...gle.com,
	jeremy@...p.org, len.brown@...el.com, tony.luck@...el.com,
	yongjie.ren@...el.com, kamezawa.hiroyu@...fujitsu.com,
	seto.hidetoshi@...fujitsu.com, penberg@...nel.org,
	yinghai@...nel.org, tglx@...utronix.de, akpm@...ux-foundation.org,
	ak@...ux.intel.com, luto@....edu, avi@...hat.com,
	dhowells@...hat.com, mingo@...hat.com, riel@...hat.com,
	cpw@....com, steiner@....com, linux-kernel@...r.kernel.org,
	viro@...iv.linux.org.uk, hpa@...or.com,
	Rusty Russell <rusty@...tcorp.com.au>
Subject: Re: [PATCH v7 8/8] x86/tlb: just do tlb flush on one of siblings
 of SMT

On Thu, 2012-05-24 at 17:27 +0800, Alex Shi wrote:

> I just want to know why it is too big on stack? Since if it causes
> trouble in using, that mean current kernel will fail to run on 4096 CPU
> system.

Because the stack is only 8k or so. If you add functions with 512+ bytes
of footprint you're done very very quickly indeed.

Now if you were able to build a call-graph using a static analysis tool
and were able to weight each edge with the stack usage of every
function, finding the actual max stack would be doable. Lacking this its
a matter of policy and 'luck'.

Our policy is to use as little stack as possible and 512 bytes is
definitely out.

Our 'luck' is that every so often people over-run their stack and we get
to spend time on figuring out wtf happened.

--
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/