On Thu, Feb 20, 2025 at 07:24:07PM -0400, Jason Gunthorpe wrote:

On Thu, Feb 20, 2025 at 12:45:46PM -0800, Nicolin Chen wrote:

quoted

------------------------------------------------------------

diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index fd2f13a63f27..be9746ecdc65 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h

@@ -1067,7 +1067,16 @@ enum iommu_veventq_type {
  * struct iommu_vevent_arm_smmuv3 - ARM SMMUv3 Virtual Event
  *                                  (IOMMU_VEVENTQ_TYPE_ARM_SMMUV3)
  * @evt: 256-bit ARM SMMUv3 Event record, little-endian.
- *       (Refer to "7.3 Event records" in SMMUv3 HW Spec)
+ *       Reported event records: (Refer to "7.3 Event records" in SMMUv3 HW Spec)
+ *       - 0x02 C_BAD_STREAMID

This is documented as 'Transaction StreamID out of range.' so it would
by a hypervisor kernel bug to hit it

I see. Dropping it.

quoted

+ *       - 0x04 C_BAD_STE

I'm not sure we do enough validation to reject all bad STE fragments
so it makes sense this could happen.

quoted

+ *       - 0x06 F_STREAM_DISABLED

This looked guest triggerable to me.. so it makes sense

Keeping these two.

quoted

+ *       - 0x08 C_BAD_SUBSTREAMID
+ *       - 0x0a C_BAD_STE

Typo, this is C_BAD_CD

Fixed.

quoted

But F_CD_FETCH and F_STE_FETCH seem to be complicated here, as both

F_STE_FETCH would indicate a hypervisor failure managing the stream
table so no need to forward it.

quoted

report PA in their FetchAddr fields, although the spec does mention
both might be injected to a guest VM:
 - "Note: This event might be injected into a guest VM, as though
    from a virtual SMMU, when a hypervisor receives a stage 2
    Translation-related fault indicating CD fetch as a cause (with
    CLASS == CD)."

That sounds like the VMM should be catching the
F_TRANSLATION and convert it for the CLASS=CD

quoted

For F_CD_FETCH, at least the CD table pointer in the nested STE is
an IPA, and all the entries in the CD table that can be 2-level are
IPAs as well. So, we need some kinda reverse translation from a PA
to IPA using its stage-2 mapping. I am not sure what's the best way
to do that...

And if the F_TRANSLATION covers the case then maybe this just stays in
the hypervisor?

quoted

Otherwise, perhaps not-supporting them in this series might be a
safer bet?

Yeah, I would consider skipping F_CD_FETCH. May also just try it out
and see what events come out on a CD fetch failure..

I will skip these two for now. Meanwhile, will try some hack to
trigger a FETCH fault.

Thanks
Nicolin