linux-kernel - Re: [PATCH] adjust root-domain->online span in response to hotplug event

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: <47D4F455.BA47.005A.0@novell.com>
Date:	Mon, 10 Mar 2008 06:41:57 -0600
From:	"Gregory Haskins" <ghaskins@...ell.com>
To:	"Suresh Siddha" <suresh.b.siddha@...el.com>
Cc:	<mingo@...e.hu>, <dmitry.adamushko@...il.com>, <ego@...ibm.com>,
	<yi.y.yang@...el.com>, <tglx@...utronix.de>,
	<akpm@...ux-foundation.org>, <rjw@...k.pl>, <oleg@...sign.ru>,
	<linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] adjust root-domain->online span in response to
	hotplug event

>>> On Sat, Mar 8, 2008 at  9:35 PM, in message
<20080309023515.GC15909@...ux-os.sc.intel.com>, Suresh Siddha
<suresh.b.siddha@...el.com> wrote: 
> On Sat, Mar 08, 2008 at 12:10:15AM -0500, Gregory Haskins wrote:
>> Suresh Siddha wrote:
>>  >
>>  > -	cpus_and(*lowest_mask, task_rq(task)->rd->online, task->cpus_allowed);
>>  > +	cpus_and(*lowest_mask, task->cpus_allowed, cpu_online_map);
>> 
>> Hi Suresh,
>>    Unfortunately, this patch will introduce its own set of bugs. 
> 
> Is that because of the missing get/put_online_cpus() ?

Actually, I was referring to the problem of potentially including "out of domain" CPUs in the search, but that is a good point too.  Ill have to think about whether a get/put is needed here.


> 
>> However, your analysis was spot-on.  I think I see the problem now.  It 
>> was introduced when I put a hack in to "fix" s2ram problems in -mm as a 
>> result of the new root-domain logic.  I think the following patch will 
>> fix both issues:
> 
> BTW, what is use of per root domains online map, when we have global
> cpu_online_map() ? Each domains span & cpu_online_map should give
> domain_online_map anyhow.


Thats exactly right.  rd->online is a cached version of "rd->span & cpu_online_map".  It simply saves us from having to do an extra cpu_and() at run-time (which can be expensive as the NR_CPUS grows large).

> 
> And is n't it buggy if someone accesses rd->online with out 
> get/put_online_map()

See above: I'm not sure, but you may be right about that.

Regards,
-Greg

--
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/