[pve-devel] [RFC kernel] revert problematic TSC multiplier commit

[Eneko Lacunza]

Hi Fiona,

Does this patch correspond to kernels linked in this forum thread?

https://forum.proxmox.com/threads/proxmox-7-2-3-ceph-16-2-7-migrating-vms-hangs-them-kernel-panic-on-linux-freeze-on-windows.109645/page-2#post-488479

If so I can test them and see if that helps with bugzilla entry #4073:
https://bugzilla.proxmox.com/show_bug.cgi?id=4073

Thanks

El 1/9/22 a las 8:25, Fiona Ebner escribió:
> Am 31.08.22 um 15:28 schrieb Fiona Ebner:
>> which might be responsible for several issues reported in the
>> community forum[0][1].
>>
>> In my case, loading a VM snapshot that originally was taken on
>> a CPU from a different vendor often caused problems in other VMs(!).
>> In particular, it often led to RCU stalls (with similar messages as in
>> [1]) or slowdowns, and sometimes clock jumps far into the future (like
>> in [0]). With this revert applied, everything seems to run smoothly
>> even after loading the "bad" snapshot 10 times.
>>
>> [0]https://forum.proxmox.com/threads/112756/
>> [1]https://forum.proxmox.com/threads/111494/
>>
>> Signed-off-by: Fiona Ebner<f.ebner at proxmox.com>
>> ---
>>
>> Needed to build with an ABI bump, AFAICT because of the removed
>> KVM_X86_OP(write_tsc_multiplier), but it's even an ABI break I guess?
>> If this is not ok, we can either
>> A) try to revert while keeping the ABI intact
>> B) try to backport d1021a1bc47668aa715b7f2121086c9598bffcbf instead
> Sorry, that's the hash in
> git://git.launchpad.net/~ubuntu-kernel-test/ubuntu/+source/linux/+git/mainline-crack
>
> Upstream it's 11d39e8cc43e1c6737af19ca9372e590061b5ad2
>
>> That's the one reason it's RFC. The other is that I haven't had much
>> time to look at the actual code yet.
>>
>>   ...dd-vendor-callbacks-for-writing-the-.patch | 247 ++++++++++++++++++
>>   1 file changed, 247 insertions(+)
>>   create mode 100644 patches/kernel/0032-Revert-KVM-X86-Add-vendor-callbacks-for-writing-the-.patch
>>
>> diff --git a/patches/kernel/0032-Revert-KVM-X86-Add-vendor-callbacks-for-writing-the-.patch b/patches/kernel/0032-Revert-KVM-X86-Add-vendor-callbacks-for-writing-the-.patch
>> new file mode 100644
>> index 0000000..d2f7796
>> --- /dev/null
>> +++ b/patches/kernel/0032-Revert-KVM-X86-Add-vendor-callbacks-for-writing-the-.patch
>> @@ -0,0 +1,247 @@
>> +From 0747f18be1da2033a20c2a355678b9c278ce4603 Mon Sep 17 00:00:00 2001
>> +From: Fiona Ebner<f.ebner at proxmox.com>
>> +Date: Wed, 31 Aug 2022 13:49:55 +0200
>> +Subject: [PATCH] Revert "KVM: X86: Add vendor callbacks for writing the TSC
>> + multiplier"
>> +
>> +This reverts commit 1ab9287add5e265352d18517551abf6d01d004fd until commit
>> +d1021a1bc47668aa715b7f2121086c9598bffcbf which fixes it can be cleanly
> Same here
>
>> +applied.
>> +
>> +Signed-off-by: Fiona Ebner<f.ebner at proxmox.com>
>
> _______________________________________________
> pve-devel mailing list
> pve-devel at lists.proxmox.com
> https://lists.proxmox.com/cgi-bin/mailman/listinfo/pve-devel
>

Eneko Lacunza
Zuzendari teknikoa | Director técnico
Binovo IT Human Project

Tel. +34 943 569 206 |https://www.binovo.es
Astigarragako Bidea, 2 - 2º izda. Oficina 10-11, 20180 Oiartzun

https://www.youtube.com/user/CANALBINOVO
https://www.linkedin.com/company/37269706/