linux-kernel - Re: [PATCH] KVM: arm/arm64: vgic: Use a single IO device per redistributor

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: <ccb49856-f958-8bea-4b27-9a808415c43d@redhat.com>
Date:   Tue, 27 Aug 2019 09:53:23 +0200
From:   Auger Eric <eric.auger@...hat.com>
To:     Zenghui Yu <yuzenghui@...wei.com>, eric.auger.pro@...il.com,
        maz@...nel.org, linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
        kvmarm@...ts.cs.columbia.edu
Cc:     zhang.zhanghailiang@...wei.com, wanghaibin.wang@...wei.com,
        james.morse@....com, qemu-arm@...gnu.org,
        julien.thierry.kdev@...il.com, suzuki.poulose@....com,
        peter.maydell@...aro.org, andre.przywara@....com
Subject: Re: [PATCH] KVM: arm/arm64: vgic: Use a single IO device per
 redistributor

Hi Zenghui,
On 8/27/19 9:49 AM, Zenghui Yu wrote:
> Hi Eric,
> 
> Thanks for this patch!
> 
> On 2019/8/24 1:52, Auger Eric wrote:
>> Hi Zenghui, Marc,
>>
>> On 8/23/19 7:33 PM, Eric Auger wrote:
>>> At the moment we use 2 IO devices per GICv3 redistributor: one
>                                                              ^^^
>>> one for the RD_base frame and one for the SGI_base frame.
>   ^^^
>>>
>>> Instead we can use a single IO device per redistributor (the 2
>>> frames are contiguous). This saves slots on the KVM_MMIO_BUS
>>> which is currently limited to NR_IOBUS_DEVS (1000).
>>>
>>> This change allows to instantiate up to 512 redistributors and may
>>> speed the guest boot with a large number of VCPUs.
>>>
>>> Signed-off-by: Eric Auger <eric.auger@...hat.com>
>>
>> I tested this patch with below kernel and QEMU branches:
>> kernel: https://github.com/eauger/linux/tree/256fix-v1
>> (Marc's patch + this patch)
>> https://github.com/eauger/qemu/tree/v4.1.0-256fix-rfc1-rc0
>> (header update + kvm_arm_gic_set_irq modification)
> 
> I also tested these three changes on HiSi D05 (with 64 pcpus), and yes,
> I can get a 512U guest to boot properly now.

Many thanks for the testing (and the bug report). I will formally post
the QEMU changes asap.

Thanks

Eric
> 
> Tested-by: Zenghui Yu <yuzenghui@...wei.com>
> 
>> On a machine with 224 pcpus, I was able to boot a 512 vcpu guest.
>>
>> As expected, qemu outputs warnings:
>>
>> qemu-system-aarch64: warning: Number of SMP cpus requested (512) exceeds
>> the recommended cpus supported by KVM (224)
>> qemu-system-aarch64: warning: Number of hotpluggable cpus requested
>> (512) exceeds the recommended cpus supported by KVM (224)
>>
>> on the guest: getconf _NPROCESSORS_ONLN returns 512
>>
>> Then I have no clue about what can be expected of such overcommit config
>> and I have not further exercised the guest at the moment. But at least
>> it seems to boot properly. I also tested without overcommit and it seems
>> to behave as before (boot, migration).
>>
>> I still need to look at the migration of > 256vcpu guest at qemu level.
> 
> Let us know if further tests are needed.
> 
> 
> Thanks,
> zenghui
>