From: Jason Gunthorpe <jgg@nvidia.com>
To: Xiaoyao Li <xiaoyao.li@intel.com>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>,
"linux-coco@lists.linux.dev" <linux-coco@lists.linux.dev>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"Duan, Zhenzhong" <zhenzhong.duan@intel.com>,
"x86@kernel.org" <x86@kernel.org>,
"Hansen, Dave" <dave.hansen@intel.com>,
"dave.hansen@linux.intel.com" <dave.hansen@linux.intel.com>,
"kas@kernel.org" <kas@kernel.org>,
"mingo@redhat.com" <mingo@redhat.com>,
"seanjc@google.com" <seanjc@google.com>,
"pbonzini@redhat.com" <pbonzini@redhat.com>,
"Peng, Chao P" <chao.p.peng@intel.com>,
"Verma, Vishal L" <vishal.l.verma@intel.com>,
"aneesh.kumar@kernel.org" <aneesh.kumar@kernel.org>,
"Tian, Kevin" <kevin.tian@intel.com>,
"hpa@zytor.com" <hpa@zytor.com>,
"tglx@kernel.org" <tglx@kernel.org>,
"nicolinc@nvidia.com" <nicolinc@nvidia.com>,
"bp@alien8.de" <bp@alien8.de>, "Gao, Chao" <chao.gao@intel.com>,
"aik@amd.com" <aik@amd.com>,
"yilun.xu@linux.intel.com" <yilun.xu@linux.intel.com>
Subject: Re: [RFC PATCH 10/15] virt: tdx-guest: Set up and accept private MMIO ranges
Date: Thu, 19 Nov 2026 09:59:08 -0400 [thread overview]
Message-ID: <20261119135908.GR2245175@nvidia.com> (raw)
In-Reply-To: <eb3a3d57-fd98-4167-b6fb-27025e737097@intel.com>
On Thu, Nov 19, 2026 at 07:24:13PM +0800, Xiaoyao Li wrote:
> On 11/3/2026 6:38 AM, Edgecombe, Rick P wrote:
> > On Thu, 2026-10-29 at 09:56 +0000, Duan, Zhenzhong wrote:
> >> After thinking about this further, a second .run() attempt cannot recover
> >> from partial MMIO acceptance with the current implementation. It starts
> >> accepting ranges from the beginning, so it will encounter a re-acceptance
> >> error on the first range successfully accepted by the previous attempt,
> >> before reaching the range that originally failed.
> >
> > How does MMIO acceptance fail? Whose fault is it?
>
> According to the Completion Status Codes defined for TDG.TDI.MMIO.ACCEPT in TDX
> Connect ABI spec, it can fail due to various reason. I think most of them are
> the fault of the host, and a few are guest fault.
>
> The most interesting one is the TDX_OPERAND_BUSY due to contention on some
> locks. E.g., when host is operating on the TDI, it fails to acquire the TDIMT lock.
The host should having locking to prevent this kind of return code
right?
> >> When .run() fails, the device is not accepted for driver attachment, so
> >> there should be no driver MMIO accesses. Therefore, removing the
> >> guest-side MMIO resource entries and freeing the descriptors in
> >> tdx_tdi_mmio_teardown() should be safe. However, this cleanup does not
> >> undo the MMIO acceptance already performed by the TDX module.
> >>
> >> There is no TDG.MMIO.UNACCEPT ABI to roll back those successful
> >> acceptances. Recovery therefore requires unlocking the device through
> >> the UNBIND hypercall, which asks the host to tear down the associated
> >> MMIO mappings, before locking and accepting the device again.
>
> The UNBIND is invoked by userspace. What if userspace doesn't do it? Do we need
> to harden it that driver attachment will always fail when the TDI is locked but
> not accepted?
Yes, Leon's trust level series should be part of this, ultimately you
can't change to lock unless the trist level is disabled/isolated and
you shouldn't be able to change away from that while the device is not
in unlocked or run.
I haven't seen anyone work on this detail yet though
Jason
next prev parent reply other threads:[~2026-11-19 13:59 UTC|newest]
Thread overview: 135+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-24 4:10 [RFC PATCH 00/15] PCI/TSM: coco/tdx-guest: Implement TDX-Connect PCIe TDISP (phase2) Zhenzhong Duan
2026-09-24 4:10 ` [RFC PATCH 01/15] x86/tdx: Export tdg_vm_rd() for tdx-guest module Zhenzhong Duan
2026-09-30 22:13 ` Peter Fang
2026-10-01 12:38 ` Xu Yilun
2026-10-08 6:45 ` Duan, Zhenzhong
2026-10-08 16:30 ` Edgecombe, Rick P
2026-09-24 4:10 ` [RFC PATCH 02/15] x86/tdx: Add TDCM hypercall wrapper for TDX Connect Zhenzhong Duan
2026-10-13 14:34 ` Nikolay Borisov
2026-10-14 6:19 ` Duan, Zhenzhong
2026-10-14 6:27 ` Nikolay Borisov
2026-10-14 7:22 ` Duan, Zhenzhong
2026-10-26 0:33 ` Xiaoyao Li
2026-10-27 3:28 ` Duan, Zhenzhong
2026-10-27 5:49 ` Xiaoyao Li
2026-10-27 6:08 ` Duan, Zhenzhong
2026-10-29 2:15 ` Xiaoyao Li
2026-10-29 7:34 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 03/15] x86/tdx: Add TDG.TDI.RD module call " Zhenzhong Duan
2026-09-25 0:06 ` Edgecombe, Rick P
2026-10-08 6:27 ` Duan, Zhenzhong
2026-10-08 16:42 ` Edgecombe, Rick P
2026-10-09 2:28 ` Duan, Zhenzhong
2026-10-26 0:51 ` Xiaoyao Li
2026-10-27 6:22 ` Duan, Zhenzhong
2026-11-02 21:07 ` Edgecombe, Rick P
2026-11-03 13:11 ` Duan, Zhenzhong
2026-11-03 21:04 ` Edgecombe, Rick P
2026-11-04 10:16 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 04/15] virt: tdx-guest: Support devsec TSM for secure devices Zhenzhong Duan
2026-10-15 13:42 ` Xu Yilun
2026-10-16 6:42 ` Duan, Zhenzhong
2026-10-26 1:12 ` Xiaoyao Li
2026-10-27 7:20 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 05/15] virt: tdx-guest: Add TDCM helpers and TEE-IO support check Zhenzhong Duan
2026-10-13 14:31 ` Nikolay Borisov
2026-10-14 6:11 ` Duan, Zhenzhong
2026-10-26 1:26 ` Xiaoyao Li
2026-10-26 7:13 ` Nikolay Borisov
2026-10-28 5:42 ` Duan, Zhenzhong
2026-10-28 6:51 ` Nikolay Borisov
2026-10-14 12:52 ` Nikolay Borisov
2026-10-15 6:24 ` Duan, Zhenzhong
2026-10-26 2:06 ` Xiaoyao Li
2026-10-27 8:32 ` Duan, Zhenzhong
2026-10-29 2:27 ` Xiaoyao Li
2026-09-24 4:10 ` [RFC PATCH 06/15] virt: tdx-guest: Support TDI bind and unbind operations Zhenzhong Duan
2026-10-13 12:10 ` Nikolay Borisov
2026-10-14 3:06 ` Duan, Zhenzhong
2026-10-14 6:32 ` Nikolay Borisov
2026-10-14 7:33 ` Duan, Zhenzhong
2026-11-04 8:20 ` Xu Yilun
2026-11-04 9:03 ` Duan, Zhenzhong
2026-10-17 18:38 ` Nikolay Borisov
2026-10-19 2:16 ` Duan, Zhenzhong
2026-10-26 2:32 ` Xiaoyao Li
2026-10-27 8:58 ` Duan, Zhenzhong
2026-10-29 2:38 ` Xiaoyao Li
2026-10-29 7:42 ` Duan, Zhenzhong
2026-10-29 3:26 ` Duan, Zhenzhong
2026-11-02 21:11 ` Edgecombe, Rick P
2026-11-03 8:49 ` Duan, Zhenzhong
2026-11-03 21:07 ` Edgecombe, Rick P
2026-11-04 8:59 ` Duan, Zhenzhong
2026-11-04 14:39 ` Edgecombe, Rick P
2026-11-05 4:37 ` Duan, Zhenzhong
2026-11-05 19:06 ` Edgecombe, Rick P
2026-11-06 3:03 ` Duan, Zhenzhong
2026-11-09 23:38 ` Edgecombe, Rick P
2026-11-10 9:40 ` Duan, Zhenzhong
2026-11-10 18:55 ` Edgecombe, Rick P
2026-11-10 19:57 ` Jason Gunthorpe
2026-11-10 22:25 ` Edgecombe, Rick P
2026-11-11 0:16 ` Jason Gunthorpe
2026-11-11 0:19 ` Edgecombe, Rick P
2026-11-11 9:44 ` Tian, Kevin
2026-11-11 15:00 ` Jason Gunthorpe
2026-11-11 23:05 ` Tian, Kevin
2026-11-12 10:50 ` Alexey Kardashevskiy
2026-11-12 14:54 ` Jason Gunthorpe
2026-11-17 11:16 ` Alexey Kardashevskiy
2026-11-17 14:24 ` Jason Gunthorpe
2026-11-18 11:12 ` Alexey Kardashevskiy
2026-11-12 12:56 ` Xu Yilun
2026-11-16 23:57 ` Edgecombe, Rick P
2026-11-17 10:36 ` Xu Yilun
2026-11-17 22:00 ` Edgecombe, Rick P
2026-11-11 8:04 ` Nikolay Borisov
2026-10-26 2:38 ` Xiaoyao Li
2026-10-27 10:14 ` Duan, Zhenzhong
2026-11-02 21:15 ` Edgecombe, Rick P
2026-11-03 6:02 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 07/15] PCI/TSM: Track Device Interface Report MMIO range index Zhenzhong Duan
2026-10-26 2:45 ` Xiaoyao Li
2026-10-27 9:11 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 08/15] x86/tdx: Add TDG.MMIO.ACCEPT module call wrapper for TDX Connect Zhenzhong Duan
2026-09-24 23:41 ` Edgecombe, Rick P
2026-09-25 0:02 ` Edgecombe, Rick P
2026-10-08 6:01 ` Duan, Zhenzhong
2026-10-08 16:47 ` Edgecombe, Rick P
2026-10-08 5:49 ` Duan, Zhenzhong
2026-10-08 16:44 ` Edgecombe, Rick P
2026-10-09 2:16 ` Duan, Zhenzhong
2026-11-03 7:48 ` Xiaoyao Li
2026-09-24 4:10 ` [RFC PATCH 09/15] virt: tdx-guest: Capture the TDI report during device lock Zhenzhong Duan
2026-10-26 5:04 ` Xiaoyao Li
2026-10-28 3:23 ` Duan, Zhenzhong
2026-11-02 21:19 ` Edgecombe, Rick P
2026-11-03 0:36 ` Jason Gunthorpe
2026-11-03 0:48 ` Edgecombe, Rick P
2026-11-03 1:26 ` Jason Gunthorpe
2026-11-03 21:11 ` Edgecombe, Rick P
2026-11-04 8:08 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 10/15] virt: tdx-guest: Set up and accept private MMIO ranges Zhenzhong Duan
2026-10-26 5:22 ` Xiaoyao Li
2026-10-28 3:32 ` Duan, Zhenzhong
2026-10-29 2:44 ` Xiaoyao Li
2026-10-29 9:56 ` Duan, Zhenzhong
2026-11-02 22:38 ` Edgecombe, Rick P
2026-11-19 11:24 ` Xiaoyao Li
2026-11-19 13:59 ` Jason Gunthorpe [this message]
2026-09-24 4:10 ` [RFC PATCH 11/15] x86/tdx: Add TDG.TDI.START module call wrapper for TDX Connect Zhenzhong Duan
2026-09-24 4:10 ` [RFC PATCH 12/15] virt: tdx-guest: Support Trust Device Interface (TDI) activation Zhenzhong Duan
2026-10-26 7:19 ` Xiaoyao Li
2026-10-28 6:44 ` Duan, Zhenzhong
2026-10-28 12:41 ` Jason Gunthorpe
2026-10-29 2:24 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 13/15] x86/tdx: Add __tdcall_saved() helper Zhenzhong Duan
2026-10-26 7:35 ` Xiaoyao Li
2026-09-24 4:10 ` [RFC PATCH 14/15] x86/tdx: Add TDG.DMAR.ACCEPT module call wrapper for TDX Connect Zhenzhong Duan
2026-10-26 7:39 ` Xiaoyao Li
2026-10-28 5:57 ` Duan, Zhenzhong
2026-09-24 4:10 ` [RFC PATCH 15/15] virt: tdx-guest: Accept default DMAR entry during PCI driver attach Zhenzhong Duan
2026-10-26 7:49 ` Xiaoyao Li
2026-10-26 12:02 ` Jason Gunthorpe
2026-10-28 9:39 ` Xu Yilun
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=20261119135908.GR2245175@nvidia.com \
--to=jgg@nvidia.com \
--cc=aik@amd.com \
--cc=aneesh.kumar@kernel.org \
--cc=bp@alien8.de \
--cc=chao.gao@intel.com \
--cc=chao.p.peng@intel.com \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=kas@kernel.org \
--cc=kevin.tian@intel.com \
--cc=linux-coco@lists.linux.dev \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nicolinc@nvidia.com \
--cc=pbonzini@redhat.com \
--cc=rick.p.edgecombe@intel.com \
--cc=seanjc@google.com \
--cc=tglx@kernel.org \
--cc=vishal.l.verma@intel.com \
--cc=x86@kernel.org \
--cc=xiaoyao.li@intel.com \
--cc=yilun.xu@linux.intel.com \
--cc=zhenzhong.duan@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
all inboxes | Powered by JetHome®