From: Auger Eric <eric.auger@redhat.com>
To: Jean-Philippe Brucker <jean-philippe.brucker@arm.com>,
Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: "kevin.tian@intel.com" <kevin.tian@intel.com>,
Vincent Stehle <Vincent.Stehle@arm.com>,
"ashok.raj@intel.com" <ashok.raj@intel.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Marc Zyngier <Marc.Zyngier@arm.com>,
Will Deacon <Will.Deacon@arm.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"iommu@lists.linux-foundation.org"
<iommu@lists.linux-foundation.org>,
Alex Williamson <alex.williamson@redhat.com>,
Robin Murphy <Robin.Murphy@arm.com>,
"kvmarm@lists.cs.columbia.edu" <kvmarm@lists.cs.columbia.edu>,
"eric.auger.pro@gmail.com" <eric.auger.pro@gmail.com>
Subject: Re: [PATCH v8 26/29] vfio-pci: Register an iommu fault handler
Date: Thu, 11 Jul 2019 15:07:19 +0200 [thread overview]
Message-ID: <b441c7aa-7aab-d816-f87f-7981dfeebc48@redhat.com> (raw)
In-Reply-To: <77405d39-81a4-d9a8-5d35-27602199867a@arm.com>
Hi Jean, Jacob,
On 6/18/19 4:04 PM, Jean-Philippe Brucker wrote:
> On 12/06/2019 19:53, Jacob Pan wrote:
>>>> You are right, the worst case of the spurious PS is to terminate the
>>>> group prematurely. Need to know the scope of the HW damage in case
>>>> of mdev where group IDs can be shared among mdevs belong to the
>>>> same PF.
>>>
>>> But from the IOMMU fault API point of view, the full page request is
>>> identified by both PRGI and PASID. Given that each mdev has its own
>>> set of PASIDs, it should be easy to isolate page responses per mdev.
>>>
>> On Intel platform, devices sending page request with private data must
>> receive page response with matching private data. If we solely depend
>> on PRGI and PASID, we may send stale private data to the device in
>> those incorrect page response. Since private data may represent PF
>> device wide contexts, the consequence of sending page response with
>> wrong private data may affect other mdev/PASID.
>>
>> One solution we are thinking to do is to inject the sequence #(e.g.
>> ktime raw mono clock) as vIOMMU private data into to the guest. Guest
>> would return this fake private data in page response, then host will
>> send page response back to the device that matches PRG1 and PASID and
>> private_data.
>>
>> This solution does not expose HW context related private data to the
>> guest but need to extend page response in iommu uapi.
>>
>> /**
>> * struct iommu_page_response - Generic page response information
>> * @version: API version of this structure
>> * @flags: encodes whether the corresponding fields are valid
>> * (IOMMU_FAULT_PAGE_RESPONSE_* values)
>> * @pasid: Process Address Space ID
>> * @grpid: Page Request Group Index
>> * @code: response code from &enum iommu_page_response_code
>> * @private_data: private data for the matching page request
>> */
>> struct iommu_page_response {
>> #define IOMMU_PAGE_RESP_VERSION_1 1
>> __u32 version;
>> #define IOMMU_PAGE_RESP_PASID_VALID (1 << 0)
>> #define IOMMU_PAGE_RESP_PRIVATE_DATA (1 << 1)
>> __u32 flags;
>> __u32 pasid;
>> __u32 grpid;
>> __u32 code;
>> __u32 padding;
>> __u64 private_data[2];
>> };
>>
>> There is also the change needed for separating storage for the real and
>> fake private data.
>>
>> Sorry for the last minute change, did not realize the HW implications.
>>
>> I see this as a future extension due to limited testing,
>
> I'm wondering how we deal with:
> (1) old userspace that won't fill the new private_data field in
> page_response. A new kernel still has to support it.
> (2) old kernel that won't recognize the new PRIVATE_DATA flag. Currently
> iommu_page_response() rejects page responses with unknown flags.
>
> I guess we'll need a two-way negotiation, where userspace queries
> whether the kernel supports the flag (2), and the kernel learns whether
> it should expect the private data to come back (1).
>
>> perhaps for
>> now, can you add paddings similar to page request? Make it 64B as well.
>
> I don't think padding is necessary, because iommu_page_response is sent
> by userspace to the kernel, unlike iommu_fault which is allocated by
> userspace and filled by the kernel.
>
> Page response looks a lot more like existing VFIO mechanisms, so I
> suppose we'll wrap the iommu_page_response structure and include an
> argsz parameter at the top:
>
> struct vfio_iommu_page_response {
> u32 argsz;
> struct iommu_page_response pr;
> };
>
> struct vfio_iommu_page_response vpr = {
> .argsz = sizeof(vpr),
> .pr = ...
> ...
> };
>
> ioctl(devfd, VFIO_IOMMU_PAGE_RESPONSE, &vpr);
>
> In that case supporting private data can be done by simply appending a
> field at the end (plus the negotiation above).
Sorry I did not quite follow the spurious response discussion but I just
noticed we still do have, upstream, in
iommu_unregister_device_fault_handler:
/* we cannot unregister handler if there are pending faults */
if (!list_empty(¶m->fault_param->faults)) {
ret = -EBUSY;
goto unlock;
}
So did you eventually decide to let
iommu_unregister_device_fault_handler fail or is an oversight?
Thanks
Eric
>
> Thanks,
> Jean
> _______________________________________________
> iommu mailing list
> iommu@lists.linux-foundation.org
> https://lists.linuxfoundation.org/mailman/listinfo/iommu
>
_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
next prev parent reply other threads:[~2019-07-11 13:07 UTC|newest]
Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-26 16:09 [PATCH v8 00/29] SMMUv3 Nested Stage Setup Eric Auger
2019-05-26 16:09 ` [PATCH v8 01/29] driver core: Add per device iommu param Eric Auger
2019-05-26 16:09 ` [PATCH v8 02/29] iommu: Introduce device fault data Eric Auger
2019-05-26 16:09 ` [PATCH v8 03/29] iommu: Introduce device fault report API Eric Auger
2019-05-26 16:09 ` [PATCH v8 04/29] iommu: Add recoverable fault reporting Eric Auger
2019-06-03 22:31 ` Alex Williamson
2019-06-04 15:48 ` Jacob Pan
2019-05-26 16:09 ` [PATCH v8 05/29] iommu: Add a timeout parameter for PRQ response Eric Auger
2019-06-03 22:32 ` Alex Williamson
2019-06-04 10:52 ` Jean-Philippe Brucker
2019-06-04 15:50 ` Jacob Pan
2019-05-26 16:09 ` [PATCH v8 06/29] trace/iommu: Add sva trace events Eric Auger
2019-05-26 16:09 ` [PATCH v8 07/29] iommu: Use device fault trace event Eric Auger
2019-05-26 16:09 ` [PATCH v8 08/29] iommu: Introduce attach/detach_pasid_table API Eric Auger
2019-05-26 16:09 ` [PATCH v8 09/29] iommu: Introduce cache_invalidate API Eric Auger
2019-05-26 16:09 ` [PATCH v8 10/29] iommu: Introduce bind/unbind_guest_msi Eric Auger
2019-05-26 16:09 ` [PATCH v8 11/29] iommu/arm-smmu-v3: Maintain a SID->device structure Eric Auger
2019-05-26 16:09 ` [PATCH v8 12/29] iommu/smmuv3: Dynamically allocate s1_cfg and s2_cfg Eric Auger
2019-05-26 16:09 ` [PATCH v8 13/29] iommu/smmuv3: Get prepared for nested stage support Eric Auger
2019-05-26 16:09 ` [PATCH v8 14/29] iommu/smmuv3: Implement attach/detach_pasid_table Eric Auger
2019-05-26 16:09 ` [PATCH v8 15/29] iommu/smmuv3: Introduce __arm_smmu_tlb_inv_asid/s1_range_nosync Eric Auger
2019-05-26 16:09 ` [PATCH v8 16/29] iommu/smmuv3: Implement cache_invalidate Eric Auger
2019-05-26 16:09 ` [PATCH v8 17/29] dma-iommu: Implement NESTED_MSI cookie Eric Auger
2019-05-26 16:09 ` [PATCH v8 18/29] iommu/smmuv3: Nested mode single MSI doorbell per domain enforcement Eric Auger
2019-05-26 16:09 ` [PATCH v8 19/29] iommu/smmuv3: Enforce incompatibility between nested mode and HW MSI regions Eric Auger
2019-05-26 16:09 ` [PATCH v8 20/29] iommu/smmuv3: Implement bind/unbind_guest_msi Eric Auger
2019-05-26 16:09 ` [PATCH v8 21/29] iommu/smmuv3: Report non recoverable faults Eric Auger
2019-05-26 16:09 ` [PATCH v8 22/29] vfio: VFIO_IOMMU_ATTACH/DETACH_PASID_TABLE Eric Auger
2019-06-03 22:32 ` Alex Williamson
2019-05-26 16:09 ` [PATCH v8 23/29] vfio: VFIO_IOMMU_CACHE_INVALIDATE Eric Auger
2019-06-14 12:38 ` Liu, Yi L
2019-06-14 13:17 ` Auger Eric
2019-05-26 16:09 ` [PATCH v8 24/29] vfio: VFIO_IOMMU_BIND/UNBIND_MSI Eric Auger
2019-06-03 22:32 ` Alex Williamson
2019-06-07 8:30 ` Auger Eric
2019-05-26 16:10 ` [PATCH v8 25/29] vfio-pci: Add a new VFIO_REGION_TYPE_NESTED region type Eric Auger
2019-06-03 22:31 ` Alex Williamson
2019-06-07 8:28 ` Auger Eric
2019-06-07 12:47 ` Jean-Philippe Brucker
2019-06-07 16:29 ` Alex Williamson
2019-05-26 16:10 ` [PATCH v8 26/29] vfio-pci: Register an iommu fault handler Eric Auger
2019-06-03 22:31 ` Alex Williamson
2019-06-04 16:11 ` Auger Eric
2019-06-05 22:45 ` Jacob Pan
2019-06-06 18:54 ` Jean-Philippe Brucker
2019-06-06 20:29 ` Jacob Pan
2019-06-07 7:02 ` Auger Eric
2019-06-07 10:28 ` Jean-Philippe Brucker
2019-06-07 17:43 ` Jacob Pan
2019-06-10 12:45 ` Jean-Philippe Brucker
2019-06-10 21:31 ` Jacob Pan
2019-06-11 13:14 ` Jean-Philippe Brucker
2019-06-12 18:53 ` Jacob Pan
2019-06-18 14:04 ` Jean-Philippe Brucker
2019-06-19 0:19 ` Jacob Pan
2019-06-19 11:44 ` Jean-Philippe Brucker
2019-07-11 13:07 ` Auger Eric [this message]
2019-06-07 12:48 ` Jean-Philippe Brucker
2019-06-07 14:18 ` Auger Eric
2019-05-26 16:10 ` [PATCH v8 27/29] vfio_pci: Allow to mmap the fault queue Eric Auger
2019-05-26 16:10 ` [PATCH v8 28/29] vfio-pci: Add VFIO_PCI_DMA_FAULT_IRQ_INDEX Eric Auger
2019-06-03 22:31 ` Alex Williamson
2019-06-04 16:11 ` Auger Eric
2019-05-26 16:10 ` [PATCH v8 29/29] vfio: Document nested stage control Eric Auger
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=b441c7aa-7aab-d816-f87f-7981dfeebc48@redhat.com \
--to=eric.auger@redhat.com \
--cc=Marc.Zyngier@arm.com \
--cc=Robin.Murphy@arm.com \
--cc=Vincent.Stehle@arm.com \
--cc=Will.Deacon@arm.com \
--cc=alex.williamson@redhat.com \
--cc=ashok.raj@intel.com \
--cc=eric.auger.pro@gmail.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jean-philippe.brucker@arm.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=kvmarm@lists.cs.columbia.edu \
--cc=linux-kernel@vger.kernel.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 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).