From: Sean Christopherson <seanjc@google.com>
To: Yan Zhao <yan.y.zhao@intel.com>
Cc: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
pbonzini@redhat.com, chao.gao@intel.com, kai.huang@intel.com,
robert.hoo.linux@gmail.com, yuan.yao@linux.intel.com
Subject: Re: [PATCH v4 07/12] KVM: VMX: drop IPAT in memtype when CD=1 for KVM_X86_QUIRK_CD_NW_CLEARED
Date: Fri, 25 Aug 2023 14:43:45 -0700 [thread overview]
Message-ID: <ZOkgka+DX4KNm5Mp@google.com> (raw)
In-Reply-To: <20230714065326.20557-1-yan.y.zhao@intel.com>
On Fri, Jul 14, 2023, Yan Zhao wrote:
> For KVM_X86_QUIRK_CD_NW_CLEARED is on, remove the IPAT (ignore PAT) bit in
> EPT memory types when cache is disabled and non-coherent DMA are present.
>
> To correctly emulate CR0.CD=1, UC + IPAT are required as memtype in EPT.
> However, as with commit
> fb279950ba02 ("KVM: vmx: obey KVM_QUIRK_CD_NW_CLEARED"), WB + IPAT are
> now returned to workaround a BIOS issue that guest MTRRs are enabled too
> late. Without this workaround, a super slow guest boot-up is expected
> during the pre-guest-MTRR-enabled period due to UC as the effective memory
> type for all guest memory.
>
> Absent emulating CR0.CD=1 with UC, it makes no sense to set IPAT when KVM
> is honoring the guest memtype.
> Removing the IPAT bit in this patch allows effective memory type to honor
> PAT values as well, as WB is the weakest memtype. It means if a guest
> explicitly claims UC as the memtype in PAT, the effective memory is UC
> instead of previous WB. If, for some unknown reason, a guest meets a slow
> boot-up issue with the removal of IPAT, it's desired to fix the blamed PAT
> in the guest.
>
> Besides, this patch is also a preparation patch for later fine-grained gfn
> zap when guest MTRRs are honored, because it allows zapping only non-WB
> ranges when CR0.CD toggles.
>
> BTW, returning guest MTRR type as if CR0.CD=0 is also not preferred because
> it still has to hardcode the MTRR type to WB during the
Please use full names instead of prononous, I found the "it still has to hardcode"
part really hard to grok. I think this is what you're saying?
BTW, returning guest MTRR type as if CR0.CD=0 is also not preferred because
KVMs ABI for the quirk also requires KVM to force WB memtype regardless of
guest MTRRs to workaround the slow guest boot-up issue.
> pre-guest-MTRR-enabled period to workaround the slow guest boot-up issue
> (guest MTRR type when guest MTRRs are disabled is UC).
> In addition, it will make the quirk unnecessarily complexer .
next prev parent reply other threads:[~2023-08-25 21:44 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-07-14 6:46 [PATCH v4 00/12] KVM: x86/mmu: refine memtype related mmu zap Yan Zhao
2023-07-14 6:50 ` [PATCH v4 01/12] KVM: x86/mmu: helpers to return if KVM honors guest MTRRs Yan Zhao
2023-10-07 7:00 ` Like Xu
2023-10-09 19:52 ` Sean Christopherson
2023-10-09 21:27 ` Sean Christopherson
2023-10-09 21:36 ` Sean Christopherson
2023-10-10 3:46 ` Yan Zhao
2023-10-11 0:08 ` Sean Christopherson
2023-10-11 1:47 ` Yan Zhao
2023-07-14 6:50 ` [PATCH v4 02/12] KVM: x86/mmu: Use KVM honors guest MTRRs helper in kvm_tdp_page_fault() Yan Zhao
2023-07-14 6:51 ` [PATCH v4 03/12] KVM: x86/mmu: Use KVM honors guest MTRRs helper when CR0.CD toggles Yan Zhao
2023-07-14 6:51 ` [PATCH v4 04/12] KVM: x86/mmu: Use KVM honors guest MTRRs helper when update mtrr Yan Zhao
2023-07-14 6:52 ` [PATCH v4 05/12] KVM: x86/mmu: zap KVM TDP when noncoherent DMA assignment starts/stops Yan Zhao
2023-07-14 6:52 ` [PATCH v4 06/12] KVM: x86/mmu: move TDP zaps from guest MTRRs update to CR0.CD toggling Yan Zhao
2023-07-14 6:53 ` [PATCH v4 07/12] KVM: VMX: drop IPAT in memtype when CD=1 for KVM_X86_QUIRK_CD_NW_CLEARED Yan Zhao
2023-08-25 21:43 ` Sean Christopherson [this message]
2023-09-04 7:41 ` Yan Zhao
2023-07-14 6:53 ` [PATCH v4 08/12] KVM: x86: centralize code to get CD=1 memtype when guest MTRRs are honored Yan Zhao
2023-08-25 21:46 ` Sean Christopherson
2023-09-04 7:46 ` Yan Zhao
2023-07-14 6:54 ` [PATCH v4 09/12] KVM: x86/mmu: serialize vCPUs to zap gfn " Yan Zhao
2023-08-25 22:47 ` Sean Christopherson
2023-09-04 8:24 ` Yan Zhao
2023-07-14 6:55 ` [PATCH v4 10/12] KVM: x86/mmu: fine-grained gfn zap " Yan Zhao
2023-08-25 23:13 ` Sean Christopherson
2023-09-04 8:37 ` Yan Zhao
2023-07-14 6:56 ` [PATCH v4 11/12] KVM: x86/mmu: split a single gfn zap range " Yan Zhao
2023-08-25 23:15 ` Sean Christopherson
2023-09-04 8:39 ` Yan Zhao
2023-07-14 6:56 ` [PATCH v4 12/12] KVM: x86/mmu: convert kvm_zap_gfn_range() to use shared mmu_lock in TDP MMU Yan Zhao
2023-08-25 21:34 ` Sean Christopherson
2023-09-04 7:31 ` Yan Zhao
2023-09-05 22:31 ` Sean Christopherson
2023-09-06 0:50 ` Yan Zhao
2023-08-25 23:17 ` [PATCH v4 00/12] KVM: x86/mmu: refine memtype related mmu zap Sean Christopherson
2023-09-04 8:48 ` Yan Zhao
2023-10-05 1:29 ` Sean Christopherson
2023-10-05 2:19 ` Huang, Kai
2023-10-05 2:28 ` Sean Christopherson
2023-10-06 0:50 ` 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=ZOkgka+DX4KNm5Mp@google.com \
--to=seanjc@google.com \
--cc=chao.gao@intel.com \
--cc=kai.huang@intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=robert.hoo.linux@gmail.com \
--cc=yan.y.zhao@intel.com \
--cc=yuan.yao@linux.intel.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 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.