linux-kernel - Re: [PATCH v7 2/8] x86/flush_tlb: try flush_tlb_single one by one in flush_tlb

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 22:36:15 +0800
From:	Alex Shi <alex.shi@...el.com>
To:	Jan Beulich <JBeulich@...e.com>
CC:	borislav.petkov@....com, arnd@...db.de, a.p.zijlstra@...llo.nl,
	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
Subject: Re: [PATCH v7 2/8] x86/flush_tlb: try flush_tlb_single one by one
 in flush_tlb_range

On 05/24/2012 05:44 PM, Jan Beulich wrote:

>>>> On 24.05.12 at 10:55, Alex Shi <alex.shi@...el.com> wrote:
>> On 05/24/2012 04:12 PM, Jan Beulich wrote:
>>
>>>>>> On 24.05.12 at 08:41, Alex Shi <alex.shi@...el.com> wrote:
>>>> So, the following change should be more safe for PV?
>>>>
>>>> -       if (va == TLB_FLUSH_ALL) {
>>>> -               args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
>>>> -       } else {
>>>> -               args->op.cmd = MMUEXT_INVLPG_MULTI;
>>>> -               args->op.arg1.linear_addr = va;
>>>> -       }
>>>> +       args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
>>>
>>> This would be safe ...
>>>
>>>> +       if (start != TLB_FLUSH_ALL)
>>>> +               args->op.arg1.linear_addr = start;
>>>
>>> ... and then this superfluous, but it'd result in an unconditional
>>> full TLB flush. When start and end (or perhaps end-1, assuming
>>> end is not inclusive) are on the same page, MMUEXT_INVLPG_MULTI
>>> should be used; MMUEXT_TLB_FLUSH_MULTI might need to be
>>> used in all other cases, unless you want to split multi-page, non-
>>> global invalidations into multiple MMUEXT_INVLPG_MULTI-s (which
>>> would appear to be what the whole patch aims at).
>>
>>
>>         args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
>> -       if (start != TLB_FLUSH_ALL)
>> +       if (start != TLB_FLUSH_ALL && (end - start) < PAGE_SIZE) {
> 
> Assuming 'end' is not inclusive (you didn't clarify that),
> 
>        if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
> 
> (and only if 'start' is guaranteed to be page aligned).


I still a idiot for xen and a newbie for kernel. :)
AFAIK, if system just flush one page, it won't set end there. But anyway
using '<=' has no problem.

> 
>> +               args->op.cmd = MMUEXT_INVLPG_MULTI;
>>                 args->op.arg1.linear_addr = start;
>> +       }
>>
>> So, above it correct code for xen?
>> As to the xen optimisation of flush range, it is may better to be done
>> in a separate patch.
> 
> Agreed.


Thanks for all comments!

> 
> Jan
> 


--
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/