From: David Matlack <dmatlack@google.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Cc: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
seanjc@google.com, vkuznets@redhat.com
Subject: Re: [PATCH 00/23] KVM: MMU: MMU role refactoring
Date: Mon, 7 Feb 2022 23:08:48 +0000 [thread overview]
Message-ID: <YgGmgMMR0dBmjW86@google.com> (raw)
In-Reply-To: <20220204115718.14934-1-pbonzini@redhat.com>
On Fri, Feb 04, 2022 at 06:56:55AM -0500, Paolo Bonzini wrote:
> The TDP MMU has a performance regression compared to the legacy
> MMU when CR0 changes often. This was reported for the grsecurity
> kernel, which uses CR0.WP to implement kernel W^X. In that case,
> each change to CR0.WP unloads the MMU and causes a lot of unnecessary
> work. When running nested, this can even cause the L1 to hardly
> make progress, as the L0 hypervisor it is overwhelmed by the amount
> of MMU work that is needed.
>
> The root cause of the issue is that the "MMU role" in KVM is a mess
> that mixes the CPU setup (CR0/CR4/EFER, SMM, guest mode, etc.)
> and the shadow page table format. Whenever something is different
> between the MMU and the CPU, it is stored as an extra field in struct
> kvm_mmu---and for extra bonus complication, sometimes the same thing
> is stored in both the role and an extra field.
>
> So, this is the "no functional change intended" part of the changes
> required to fix the performance regression. It separates neatly
> the shadow page table format ("MMU role") from the guest page table
> format ("CPU role"), and removes the duplicate fields.
What do you think about calling this the guest_role instead of cpu_role?
There is a bit of a precedent for using "guest" instead of "cpu" already
for this type of concept (e.g. guest_walker), and I find it more
intuitive.
> The next
> step then is to avoid unloading the MMU as long as the MMU role
> stays the same.
>
> Please review!
>
> Paolo
>
> Paolo Bonzini (23):
> KVM: MMU: pass uses_nx directly to reset_shadow_zero_bits_mask
> KVM: MMU: nested EPT cannot be used in SMM
> KVM: MMU: remove valid from extended role
> KVM: MMU: constify uses of struct kvm_mmu_role_regs
> KVM: MMU: pull computation of kvm_mmu_role_regs to kvm_init_mmu
> KVM: MMU: load new PGD once nested two-dimensional paging is
> initialized
> KVM: MMU: remove kvm_mmu_calc_root_page_role
> KVM: MMU: rephrase unclear comment
> KVM: MMU: remove "bool base_only" arguments
> KVM: MMU: split cpu_role from mmu_role
> KVM: MMU: do not recompute root level from kvm_mmu_role_regs
> KVM: MMU: remove ept_ad field
> KVM: MMU: remove kvm_calc_shadow_root_page_role_common
> KVM: MMU: cleanup computation of MMU roles for two-dimensional paging
> KVM: MMU: cleanup computation of MMU roles for shadow paging
> KVM: MMU: remove extended bits from mmu_role
> KVM: MMU: remove redundant bits from extended role
> KVM: MMU: fetch shadow EFER.NX from MMU role
> KVM: MMU: simplify and/or inline computation of shadow MMU roles
> KVM: MMU: pull CPU role computation to kvm_init_mmu
> KVM: MMU: store shadow_root_level into mmu_role
> KVM: MMU: use cpu_role for root_level
> KVM: MMU: replace direct_map with mmu_role.direct
>
> arch/x86/include/asm/kvm_host.h | 13 +-
> arch/x86/kvm/mmu.h | 2 +-
> arch/x86/kvm/mmu/mmu.c | 408 ++++++++++++--------------------
> arch/x86/kvm/mmu/mmu_audit.c | 6 +-
> arch/x86/kvm/mmu/paging_tmpl.h | 12 +-
> arch/86/kvm/mmu/tdp_mmu.c | 4 +-
> arch/x86/kvm/svm/svm.c | 2 +-
> arch/x86/kvm/vmx/vmx.c | 2 +-
> arch/x86/kvm/x86.c | 12 +-
> 10 files changed, 178 insertions(+), 284 deletions(-)
>
> --
> 2.31.1
>
next prev parent reply other threads:[~2022-02-08 1:05 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-04 11:56 [PATCH 00/23] KVM: MMU: MMU role refactoring Paolo Bonzini
2022-02-04 11:56 ` [PATCH 01/23] KVM: MMU: pass uses_nx directly to reset_shadow_zero_bits_mask Paolo Bonzini
2022-02-04 17:59 ` David Matlack
2022-02-05 14:52 ` Paolo Bonzini
2022-02-07 16:09 ` Sean Christopherson
2022-02-07 21:50 ` David Matlack
2022-02-10 0:30 ` Sean Christopherson
2022-02-10 16:38 ` Paolo Bonzini
2022-02-04 11:56 ` [PATCH 02/23] KVM: MMU: nested EPT cannot be used in SMM Paolo Bonzini
2022-02-04 18:16 ` David Matlack
2022-02-09 22:43 ` Sean Christopherson
2022-02-04 11:56 ` [PATCH 03/23] KVM: MMU: remove valid from extended role Paolo Bonzini
2022-02-04 18:32 ` David Matlack
2022-02-05 14:50 ` Paolo Bonzini
2022-02-09 22:54 ` Sean Christopherson
2022-02-10 9:53 ` Paolo Bonzini
2022-02-04 11:56 ` [PATCH 04/23] KVM: MMU: constify uses of struct kvm_mmu_role_regs Paolo Bonzini
2022-02-04 18:41 ` David Matlack
2022-02-09 22:57 ` Sean Christopherson
2022-02-04 11:57 ` [PATCH 05/23] KVM: MMU: pull computation of kvm_mmu_role_regs to kvm_init_mmu Paolo Bonzini
2022-02-04 18:45 ` David Matlack
2022-02-04 11:57 ` [PATCH 06/23] KVM: MMU: load new PGD once nested two-dimensional paging is initialized Paolo Bonzini
2022-02-04 19:18 ` David Matlack
2022-02-07 13:50 ` Paolo Bonzini
2022-02-07 14:35 ` Paolo Bonzini
2022-02-09 12:34 ` Paolo Bonzini
2022-02-04 11:57 ` [PATCH 07/23] KVM: MMU: remove kvm_mmu_calc_root_page_role Paolo Bonzini
2022-02-04 19:32 ` David Matlack
2022-02-05 14:46 ` Paolo Bonzini
2022-02-10 0:47 ` Sean Christopherson
2022-02-10 9:52 ` Paolo Bonzini
2022-02-10 17:29 ` Sean Christopherson
2022-02-10 17:43 ` Paolo Bonzini
2022-02-04 11:57 ` [PATCH 08/23] KVM: MMU: rephrase unclear comment Paolo Bonzini
2022-02-04 19:38 ` David Matlack
2022-02-04 11:57 ` [PATCH 09/23] KVM: MMU: remove "bool base_only" arguments Paolo Bonzini
2022-02-04 19:41 ` David Matlack
2022-02-04 11:57 ` [PATCH 10/23] KVM: MMU: split cpu_role from mmu_role Paolo Bonzini
2022-02-04 21:57 ` David Matlack
2022-02-05 14:49 ` Paolo Bonzini
2022-02-07 21:38 ` David Matlack
2022-02-04 11:57 ` [PATCH 11/23] KVM: MMU: do not recompute root level from kvm_mmu_role_regs Paolo Bonzini
2022-02-07 22:10 ` David Matlack
2022-02-07 22:17 ` David Matlack
2022-02-04 11:57 ` [PATCH 12/23] KVM: MMU: remove ept_ad field Paolo Bonzini
2022-02-04 11:57 ` [PATCH 13/23] KVM: MMU: remove kvm_calc_shadow_root_page_role_common Paolo Bonzini
2022-02-07 22:25 ` David Matlack
2022-02-04 11:57 ` [PATCH 14/23] KVM: MMU: cleanup computation of MMU roles for two-dimensional paging Paolo Bonzini
2022-02-04 11:57 ` [PATCH 15/23] KVM: MMU: cleanup computation of MMU roles for shadow paging Paolo Bonzini
2022-02-04 11:57 ` [PATCH 16/23] KVM: MMU: remove extended bits from mmu_role Paolo Bonzini
2022-02-04 11:57 ` [PATCH 17/23] KVM: MMU: remove redundant bits from extended role Paolo Bonzini
2022-02-04 11:57 ` [PATCH 18/23] KVM: MMU: fetch shadow EFER.NX from MMU role Paolo Bonzini
2022-02-04 11:57 ` [PATCH 19/23] KVM: MMU: simplify and/or inline computation of shadow MMU roles Paolo Bonzini
2022-02-04 11:57 ` [PATCH 20/23] KVM: MMU: pull CPU role computation to kvm_init_mmu Paolo Bonzini
2022-02-07 22:42 ` David Matlack
2022-02-04 11:57 ` [PATCH 21/23] KVM: MMU: store shadow_root_level into mmu_role Paolo Bonzini
2022-02-07 23:00 ` David Matlack
2022-02-04 11:57 ` [PATCH 22/23] KVM: MMU: use cpu_role for root_level Paolo Bonzini
2022-02-07 23:01 ` David Matlack
2022-02-04 11:57 ` [PATCH 23/23] KVM: MMU: replace direct_map with mmu_role.direct Paolo Bonzini
2022-02-07 23:02 ` David Matlack
2022-02-07 23:08 ` David Matlack [this message]
2022-02-07 23:27 ` [PATCH 00/23] KVM: MMU: MMU role refactoring Sean Christopherson
2022-02-07 23:53 ` David Matlack
2022-02-10 1:11 ` Sean Christopherson
2022-02-10 11:58 ` Paolo Bonzini
2022-02-10 16:55 ` Sean Christopherson
2022-02-10 17:30 ` Paolo Bonzini
2022-02-10 19:28 ` Sean Christopherson
2022-02-09 22:31 ` Sean Christopherson
2022-02-10 9:54 ` Paolo Bonzini
2022-02-14 18:14 ` David Matlack
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=YgGmgMMR0dBmjW86@google.com \
--to=dmatlack@google.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=seanjc@google.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;
as well as URLs for NNTP newsgroup(s).