From: Paolo Bonzini <pbonzini@redhat.com>
To: David Matlack <dmatlack@google.com>,
Ignat Korchagin <ignat@cloudflare.com>
Cc: kvm@vger.kernel.org, Sean Christopherson <seanjc@google.com>,
stevensd@chromium.org, kernel-team <kernel-team@cloudflare.com>
Subject: Re: Potential bug in TDP MMU
Date: Sat, 11 Dec 2021 02:49:02 +0100 [thread overview]
Message-ID: <e995aceb-40cc-e4cc-f3c8-2e8c2877a896@redhat.com> (raw)
In-Reply-To: <CALzav=fyaXAn4CLRW2qKTrROGUh6+F4bphhfoMZ13Qp5Njx3gw@mail.gmail.com>
On 12/11/21 02:34, David Matlack wrote:
> The stacks help, thanks for including them. It seems like a race
> during do_exit teardown. One thing I notice is that
> do_exit->mmput->kvm_mmu_zap_all can interleave with
> kvm_vcpu_release->kvm_tdp_mmu_put_root (full call chains omitted),
> since the former path allows yielding. But I don't yet see that could
> lead to any issues, let alone cause us to encounter a PFN in the EPT
> with a zero refcount.
Can it? The call chains are
zap_gfn_range+2229
kvm_tdp_mmu_put_root+465
kvm_mmu_free_roots+629
kvm_mmu_unload+28
kvm_arch_destroy_vm+510
kvm_put_kvm+1017
kvm_vcpu_release+78
__fput+516
task_work_run+206
do_exit+2615
do_group_exit+236
and
zap_gfn_range+2229
__kvm_tdp_mmu_zap_gfn_range+162
kvm_tdp_mmu_zap_all+34
kvm_mmu_zap_all+518
kvm_mmu_notifier_release+83
__mmu_notifier_release+420
exit_mmap+965
mmput+167
do_exit+2482
do_group_exit+236
but there can be no parallelism or interleaving here, because the call
to kvm_vcpu_release() is scheduled in exit_files() (and performed in
exit_task_work()). That comes after exit_mm(), where mmput() is called.
Even if the two could interleave, they go through the same zap_gfn_range
path. That path takes the lock for write and only yields on the 512
top-level page structures. Anything below is handled by
tdp_mmu_set_spte's (with mutual recursion between handle_changed_spte
and handle_removed_tdp_mmu_page), and there are no yields on that path.
Paolo
next prev parent reply other threads:[~2021-12-11 1:49 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-29 21:44 Potential bug in TDP MMU Ignat Korchagin
2021-11-30 9:29 ` Paolo Bonzini
2021-11-30 10:58 ` Ignat Korchagin
2021-11-30 10:59 ` Ignat Korchagin
2021-11-30 11:11 ` Paolo Bonzini
2021-11-30 11:19 ` Ignat Korchagin
2021-11-30 11:43 ` Ignat Korchagin
2021-11-30 11:49 ` Paolo Bonzini
2021-11-30 12:13 ` Paolo Bonzini
2021-11-30 20:23 ` Sean Christopherson
2021-12-01 23:44 ` Ignat Korchagin
2021-12-10 23:04 ` Ignat Korchagin
2021-12-11 1:34 ` David Matlack
2021-12-11 1:49 ` Paolo Bonzini [this message]
2021-12-11 17:46 ` David Matlack
2021-12-11 1:37 ` Paolo Bonzini
2021-12-11 2:39 ` Sean Christopherson
2021-12-11 9:38 ` Ignat Korchagin
2021-12-11 20:49 ` Paolo Bonzini
2021-12-13 16:14 ` Sean Christopherson
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=e995aceb-40cc-e4cc-f3c8-2e8c2877a896@redhat.com \
--to=pbonzini@redhat.com \
--cc=dmatlack@google.com \
--cc=ignat@cloudflare.com \
--cc=kernel-team@cloudflare.com \
--cc=kvm@vger.kernel.org \
--cc=seanjc@google.com \
--cc=stevensd@chromium.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.