linux-kernel - Re: [PATCH v3 0/3] genirq/vfio: Introduce update_irq

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: <4b2c76e3-91da-09b6-65f4-535828373c04@linux.alibaba.com>
Date:   Tue, 20 Aug 2019 23:51:23 +0800
From:   luoben <luoben@...ux.alibaba.com>
To:     Alex Williamson <alex.williamson@...hat.com>
Cc:     tglx@...utronix.de, linux-kernel@...r.kernel.org,
        tao.ma@...ux.alibaba.com, gerry@...ux.alibaba.com,
        nanhai.zou@...ux.alibaba.com, linyunsheng@...wei.com
Subject: Re: [PATCH v3 0/3] genirq/vfio: Introduce update_irq_devid and
 optimize VFIO irq ops


在 2019/8/20 下午11:22, Alex Williamson 写道:
> On Tue, 20 Aug 2019 12:03:50 +0800
> luoben <luoben@...ux.alibaba.com> wrote:
>
>> 在 2019/8/20 上午4:51, Alex Williamson 写道:
>>> On Thu, 15 Aug 2019 21:02:58 +0800
>>> Ben Luo <luoben@...ux.alibaba.com> wrote:
>>>   
>>>> Currently, VFIO takes a lot of free-then-request-irq actions whenever
>>>> a VM (with device passthru via VFIO) sets irq affinity or mask/unmask
>>>> irq. Those actions only change the cookie data of irqaction or even
>>>> change nothing. The free-then-request-irq not only adds more latency,
>>>> but also increases the risk of losing interrupt, which may lead to a
>>>> VM hung forever in waiting for IO completion
>>> What guest environment is generating this?  Typically I don't see that
>>> Windows or Linux guests bounce the interrupt configuration much.
>>> Thanks,
>>>
>>> Alex
>> By tracing centos5u8 on host, I found it keep masking and unmasking
>> interrupt like this:
>>
>> [1566032533709879] index:28 irte_hi:000000010004a601
>> irte_lo:adb54bc000b98001
>> [1566032533711242] index:28 irte_hi:0000000000000000
>> irte_lo:0000000000000000
>> [1566032533711258] index:28 irte_hi:000000000004a601
>> irte_lo:00003fff00ac002d
>> [1566032533711269] index:28 irte_hi:000000000004a601
>> irte_lo:00003fff00ac002d
> [snip]
>> "[1566032533720007]" is timestamp in μs, so centos5u8 tiggers 30+ irte
>> modification within 10ms
> Ok, that matches my understanding that only very old guests behave in
> this manner.  It's a curious case to optimize as RHEL5 is in extended
> life-cycle support, with regular maintenance releases ending 2+ years
> ago.  Thanks,
>
> Alex

But repeatedly set interrupt affinity in a new version guest can also 
cause the problem.


Thanks,

     Ben