From: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
To: "seanjc@google.com" <seanjc@google.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"sagis@google.com" <sagis@google.com>,
"isaku.yamahata@gmail.com" <isaku.yamahata@gmail.com>,
"Aktas, Erdem" <erdemaktas@google.com>,
"Zhao, Yan Y" <yan.y.zhao@intel.com>,
"pbonzini@redhat.com" <pbonzini@redhat.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"dmatlack@google.com" <dmatlack@google.com>
Subject: Re: [PATCH 08/16] KVM: x86/mmu: Bug the VM if kvm_zap_gfn_range() is called for TDX
Date: Wed, 15 May 2024 16:12:37 +0000 [thread overview]
Message-ID: <de3cb02ae9e639f423ae47ef2fad1e89aa9dd3d8.camel@intel.com> (raw)
In-Reply-To: <ZkTcbPowDSLVgGft@google.com>
On Wed, 2024-05-15 at 09:02 -0700, Sean Christopherson wrote:
> > Or most specifically, we only need this zapping if we *try* to have
> > consistent
> > cache attributes between private and shared. In the non-coherent DMA case we
> > can't have them be consistent because TDX doesn't support changing the
> > private
> > memory in this way.
>
> Huh? That makes no sense. A physical page can't be simultaneously mapped
> SHARED
> and PRIVATE, so there can't be meaningful cache attribute aliasing between
> private
> and shared EPT entries.
>
> Trying to provide consistency for the GPA is like worrying about having
> matching
> PAT entires for the virtual address in two different processes.
No, not matching between the private and shared mappings of the same page. The
whole private memory will be WB, and the whole shared half will honor PAT.
next prev parent reply other threads:[~2024-05-15 16:12 UTC|newest]
Thread overview: 152+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-15 0:59 [PATCH 00/16] TDX MMU prep series part 1 Rick Edgecombe
2024-05-15 0:59 ` [PATCH 01/16] KVM: x86: Add a VM type define for TDX Rick Edgecombe
2024-05-15 0:59 ` [PATCH 02/16] KVM: x86/mmu: Introduce a slot flag to zap only slot leafs on slot deletion Rick Edgecombe
2024-05-15 13:24 ` Huang, Kai
2024-05-15 19:09 ` Sean Christopherson
2024-05-15 19:23 ` Edgecombe, Rick P
2024-05-15 20:05 ` Sean Christopherson
2024-05-15 20:53 ` Edgecombe, Rick P
2024-05-15 22:47 ` Sean Christopherson
2024-05-15 23:06 ` Huang, Kai
2024-05-15 23:20 ` Sean Christopherson
2024-05-15 23:36 ` Huang, Kai
2024-05-16 1:12 ` Xiaoyao Li
2024-05-17 15:30 ` Paolo Bonzini
2024-05-22 1:29 ` Yan Zhao
2024-05-22 2:31 ` Sean Christopherson
2024-05-22 6:48 ` Yan Zhao
2024-05-22 15:45 ` Paolo Bonzini
2024-05-24 1:50 ` Yan Zhao
2024-05-15 23:56 ` Edgecombe, Rick P
2024-05-16 2:21 ` Edgecombe, Rick P
2024-05-16 3:56 ` Yan Zhao
2024-05-17 15:27 ` Paolo Bonzini
2024-05-17 15:25 ` Paolo Bonzini
2024-05-15 18:03 ` Isaku Yamahata
2024-05-15 0:59 ` [PATCH 03/16] KVM: x86/tdp_mmu: Add a helper function to walk down the TDP MMU Rick Edgecombe
2024-05-17 7:44 ` Chao Gao
2024-05-17 9:08 ` Isaku Yamahata
2024-05-15 0:59 ` [PATCH 04/16] KVM: x86/mmu: Add address conversion functions for TDX shared bit of GPA Rick Edgecombe
2024-05-15 22:34 ` Huang, Kai
2024-05-15 23:21 ` Edgecombe, Rick P
2024-05-15 23:31 ` Huang, Kai
2024-05-15 23:38 ` Edgecombe, Rick P
2024-05-15 23:44 ` Huang, Kai
2024-05-15 23:59 ` Edgecombe, Rick P
2024-05-16 0:12 ` Huang, Kai
2024-05-16 0:19 ` Edgecombe, Rick P
2024-05-16 0:25 ` Huang, Kai
2024-05-16 0:35 ` Edgecombe, Rick P
2024-05-16 1:04 ` Huang, Kai
2024-05-16 1:20 ` Edgecombe, Rick P
2024-05-16 1:40 ` Huang, Kai
2024-05-16 5:52 ` Yan Zhao
2024-05-18 0:25 ` Edgecombe, Rick P
2024-05-16 23:08 ` Edgecombe, Rick P
2024-05-17 0:37 ` Huang, Kai
2024-05-17 1:51 ` Edgecombe, Rick P
2024-05-17 4:26 ` Huang, Kai
2024-05-17 21:12 ` Edgecombe, Rick P
2024-05-15 0:59 ` [PATCH 05/16] KVM: Add member to struct kvm_gfn_range for target alias Rick Edgecombe
2024-05-17 20:58 ` Edgecombe, Rick P
2024-05-15 0:59 ` [PATCH 06/16] KVM: x86/mmu: Add a new is_private member for union kvm_mmu_page_role Rick Edgecombe
2024-05-15 0:59 ` [PATCH 07/16] KVM: x86/mmu: Add a private pointer to struct kvm_mmu_page Rick Edgecombe
2024-05-15 0:59 ` [PATCH 08/16] KVM: x86/mmu: Bug the VM if kvm_zap_gfn_range() is called for TDX Rick Edgecombe
2024-05-15 13:27 ` Huang, Kai
2024-05-15 15:22 ` Edgecombe, Rick P
2024-05-15 23:14 ` Huang, Kai
2024-05-15 15:34 ` Sean Christopherson
2024-05-15 15:49 ` Edgecombe, Rick P
2024-05-15 15:56 ` Edgecombe, Rick P
2024-05-15 16:02 ` Sean Christopherson
2024-05-15 16:12 ` Edgecombe, Rick P [this message]
2024-05-15 18:09 ` Sean Christopherson
2024-05-15 18:22 ` Edgecombe, Rick P
2024-05-15 19:48 ` Sean Christopherson
2024-05-15 20:32 ` Edgecombe, Rick P
2024-05-15 23:26 ` Sean Christopherson
2024-05-15 16:22 ` Isaku Yamahata
2024-05-15 22:17 ` Huang, Kai
2024-05-15 23:14 ` Edgecombe, Rick P
2024-05-15 23:38 ` Huang, Kai
2024-05-16 0:13 ` Edgecombe, Rick P
2024-05-16 0:27 ` Isaku Yamahata
2024-05-16 1:11 ` Huang, Kai
2024-05-16 0:15 ` Isaku Yamahata
2024-05-16 0:52 ` Edgecombe, Rick P
2024-05-16 1:21 ` Huang, Kai
2024-05-16 17:27 ` Isaku Yamahata
2024-05-16 21:46 ` Edgecombe, Rick P
2024-05-16 22:23 ` Huang, Kai
2024-05-16 22:38 ` Edgecombe, Rick P
2024-05-16 23:16 ` Huang, Kai
2024-05-15 0:59 ` [PATCH 09/16] KVM: x86/mmu: Make kvm_tdp_mmu_alloc_root() return void Rick Edgecombe
2024-05-15 0:59 ` [PATCH 10/16] KVM: x86/tdp_mmu: Support TDX private mapping for TDP MMU Rick Edgecombe
2024-05-15 17:35 ` Isaku Yamahata
2024-05-15 18:00 ` Edgecombe, Rick P
2024-05-16 0:52 ` Huang, Kai
2024-05-16 1:27 ` Edgecombe, Rick P
2024-05-16 2:07 ` Huang, Kai
2024-05-16 2:57 ` Edgecombe, Rick P
2024-05-16 13:04 ` Huang, Kai
2024-05-16 16:36 ` Edgecombe, Rick P
2024-05-16 19:42 ` Isaku Yamahata
2024-05-17 2:35 ` Edgecombe, Rick P
2024-05-17 9:03 ` Isaku Yamahata
2024-05-17 18:16 ` Edgecombe, Rick P
2024-05-17 19:16 ` Isaku Yamahata
2024-05-20 23:32 ` Isaku Yamahata
2024-05-21 15:07 ` Edgecombe, Rick P
2024-05-21 16:15 ` Isaku Yamahata
2024-05-22 22:34 ` Isaku Yamahata
2024-05-22 23:09 ` Edgecombe, Rick P
2024-05-22 23:47 ` Isaku Yamahata
2024-05-22 23:50 ` Edgecombe, Rick P
2024-05-23 0:01 ` Isaku Yamahata
2024-05-23 18:27 ` Edgecombe, Rick P
2024-05-24 7:55 ` Isaku Yamahata
2024-05-28 16:27 ` Edgecombe, Rick P
2024-05-28 17:47 ` Paolo Bonzini
2024-05-29 2:13 ` Edgecombe, Rick P
2024-05-29 7:25 ` Paolo Bonzini
2024-05-31 14:11 ` Isaku Yamahata
2024-05-28 17:43 ` Paolo Bonzini
2024-05-28 17:16 ` Paolo Bonzini
2024-05-28 18:29 ` Edgecombe, Rick P
2024-05-29 1:06 ` Isaku Yamahata
2024-05-29 1:51 ` Edgecombe, Rick P
2024-05-17 2:36 ` Huang, Kai
2024-05-17 8:14 ` Isaku Yamahata
2024-05-18 5:42 ` Huang, Kai
2024-05-18 15:41 ` Edgecombe, Rick P
2024-05-20 10:38 ` Huang, Kai
2024-05-20 18:58 ` Isaku Yamahata
2024-05-20 19:02 ` Edgecombe, Rick P
2024-05-20 23:39 ` Edgecombe, Rick P
2024-05-21 2:25 ` Isaku Yamahata
2024-05-21 2:57 ` Edgecombe, Rick P
2024-05-20 22:34 ` Huang, Kai
2024-05-16 1:48 ` Isaku Yamahata
2024-05-16 2:00 ` Edgecombe, Rick P
2024-05-16 2:10 ` Huang, Kai
2024-05-28 16:59 ` Paolo Bonzini
2024-05-16 17:10 ` Isaku Yamahata
2024-05-23 23:14 ` Edgecombe, Rick P
2024-05-24 8:20 ` Isaku Yamahata
2024-05-28 21:48 ` Edgecombe, Rick P
2024-05-29 1:16 ` Isaku Yamahata
2024-05-29 1:50 ` Edgecombe, Rick P
2024-05-29 2:20 ` Isaku Yamahata
2024-05-29 2:29 ` Edgecombe, Rick P
2024-05-28 20:54 ` Edgecombe, Rick P
2024-05-29 1:24 ` Isaku Yamahata
2024-05-28 23:06 ` Edgecombe, Rick P
2024-05-29 1:57 ` Isaku Yamahata
2024-05-29 2:13 ` Edgecombe, Rick P
2024-05-29 16:55 ` Isaku Yamahata
2024-05-15 0:59 ` [PATCH 11/16] KVM: x86/tdp_mmu: Extract root invalid check from tdx_mmu_next_root() Rick Edgecombe
2024-05-15 0:59 ` [PATCH 12/16] KVM: x86/tdp_mmu: Introduce KVM MMU root types to specify page table type Rick Edgecombe
2024-05-15 0:59 ` [PATCH 13/16] KVM: x86/tdp_mmu: Introduce shared, private KVM MMU root types Rick Edgecombe
2024-05-15 0:59 ` [PATCH 14/16] KVM: x86/tdp_mmu: Take root types for kvm_tdp_mmu_invalidate_all_roots() Rick Edgecombe
2024-05-15 0:59 ` [PATCH 15/16] KVM: x86/tdp_mmu: Make mmu notifier callbacks to check kvm_process Rick Edgecombe
2024-05-15 0:59 ` [PATCH 16/16] KVM: x86/tdp_mmu: Invalidate correct roots Rick Edgecombe
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=de3cb02ae9e639f423ae47ef2fad1e89aa9dd3d8.camel@intel.com \
--to=rick.p.edgecombe@intel.com \
--cc=dmatlack@google.com \
--cc=erdemaktas@google.com \
--cc=isaku.yamahata@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=sagis@google.com \
--cc=seanjc@google.com \
--cc=yan.y.zhao@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox