linux-kernel - Re: [PATCH 4/7] x86/intel_rdt: Implement scheduling support for Intel RDT

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] [day] [month] [year] [list]

Message-ID: <alpine.DEB.2.10.1505081342090.6658@vshiva-Udesk>
Date:	Fri, 8 May 2015 13:55:57 -0700 (PDT)
From:	Vikas Shivappa <vikas.shivappa@...el.com>
To:	Peter Zijlstra <peterz@...radead.org>
cc:	Vikas Shivappa <vikas.shivappa@...el.com>,
	Vikas Shivappa <vikas.shivappa@...ux.intel.com>,
	linux-kernel@...r.kernel.org, x86@...nel.org, hpa@...or.com,
	tglx@...utronix.de, mingo@...nel.org, tj@...nel.org,
	Matt Fleming <matt.fleming@...el.com>,
	"Auld, Will" <will.auld@...el.com>, peter.zijlstra@...el.com,
	h.peter.anvin@...el.com,
	"Juvva, Kanaka D" <kanaka.d.juvva@...el.com>
Subject: Re: [PATCH 4/7] x86/intel_rdt: Implement scheduling support for
 Intel RDT



On Fri, 8 May 2015, Peter Zijlstra wrote:

> On Thu, May 07, 2015 at 04:15:41PM -0700, Vikas Shivappa wrote:
>>> No.
>>>
>>> 1) two arch hooks right after one another is FAIL
>>> 1a) just 'fix' the existing hook
>>> 2) current is cheap and easily obtainable without passing it as
>>>   an argument
>>
>> will fix to just use an existing hook in finish_task_switch and
>> current(get_current) since the stack would already be changed ..
>>
>> Thanks,
>> Vikas
>>
>>> 3) why do you need the hook in the first place?
>>> 3a) why can't you put this in __switch_to()? This is very much x86 only
>>>    code.
>
> ^ please also answer 3, why can't this go in __swtich_to()?

perf uses similar(#1a) hook to update its MSRs (including for cache 
monitoring ).
Also since switch_to is for registers state and stack , may be a 
safer option to use it in the finish_arch_switch? Thats kind of why we had it 
there at first but had a seperate hook.

#define finish_arch_switch(prev)					\
do {									\
 	intel_rdt_sched_in();						\
} while (0)


Hpa , any comments ?

>
--
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/