public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: "Mancini, Riccardo" <mancio@amazon.com>
To: "pbonzini@redhat.com" <pbonzini@redhat.com>,
	"vkuznets@redhat.com" <vkuznets@redhat.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>, "Graf (AWS),
	Alexander" <graf@amazon.de>,
	"Teragni, Matias" <mteragni@amazon.com>,
	"Batalov, Eugene" <bataloe@amazon.com>
Subject: Bug? Incompatible APF for 4.14 guest on 5.10 and later host
Date: Thu, 5 Oct 2023 15:08:20 +0000	[thread overview]
Message-ID: <9d5ddfbe407940afa02567262a22fa4c@amazon.com> (raw)

Hi,

when a 4.14 guest runs on a 5.10 host (and later), it cannot use APF (despite
CPUID advertising KVM_FEATURE_ASYNC_PF) due to the new interrupt-based
mechanism 2635b5c4a0 (KVM: x86: interrupt based APF 'page ready' event delivery).
Kernels after 5.9 won't satisfy the guest request to enable APF through
KVM_ASYNC_PF_ENABLED, requiring also KVM_ASYNC_PF_DELIVERY_AS_INT to be set.
Furthermore, the patch set seems to be dropping parts of the legacy #PF handling
as well.
I consider this as a bug as it breaks APF compatibility for older guests running
on newer kernels, by breaking the underlying ABI.
What do you think? Was this a deliberate decision?
Was this already reported in the past (I couldn't find anything in the mailing list
but I might have missed it!)?
Would it be much effort to support the legacy #PF based mechanism for older
guests that choose to only set KVM_ASYNC_PF_ENABLED?

The reason this is an issue for us now is that not having APF for older guests
introduces a significant performance regression on 4.14 guests when paired to
uffd handling of "remote" page-faults (similar to a live migration scenario)
when we update from a 4.14 host kernel to a 5.10 host kernel.

Thanks,
Riccardo

             reply	other threads:[~2023-10-05 15:50 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-05 15:08 Mancini, Riccardo [this message]
2023-10-05 15:38 ` Bug? Incompatible APF for 4.14 guest on 5.10 and later host Vitaly Kuznetsov
2023-10-13 16:36   ` [RFC PATCH 4.14] KVM: x86: Backport support for interrupt-based APF page-ready delivery in guest Riccardo Mancini
2023-10-16 14:18     ` Vitaly Kuznetsov
2023-10-16 21:57       ` Paolo Bonzini
2023-10-17 11:22         ` Vitaly Kuznetsov
2023-10-05 16:15 ` Bug? Incompatible APF for 4.14 guest on 5.10 and later host Paolo Bonzini
  -- strict thread matches above, loose matches on Subject: below --
2023-10-05 17:24 Mancini, Riccardo
2023-10-06  1:39 ` Gavin Shan
2023-10-13 15:40 Mancini, Riccardo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=9d5ddfbe407940afa02567262a22fa4c@amazon.com \
    --to=mancio@amazon.com \
    --cc=bataloe@amazon.com \
    --cc=graf@amazon.de \
    --cc=kvm@vger.kernel.org \
    --cc=mteragni@amazon.com \
    --cc=pbonzini@redhat.com \
    --cc=vkuznets@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox