RE: [PATCH v3] iommu/vt-d: Disable IOMMU by default on Lenovo ThinkPad P50s

"Tian, Kevin" <[email protected]> Mon, 27 Jul 2026 04:03:12 +0000
Newsgroups dev.linux.lists.iommu,org.kernel.vger.linux-kernel
Message-ID <CO1PR11MB4835CB1B5633DD1E4F1011428CCC2@CO1PR11MB4835.namprd11.prod.outlook.com>
> From: Oliver Lin <[email protected]>
> Sent: Monday, July 27, 2026 11:22 AM
> 
> On 27/7/2026 09:31, Tian, Kevin wrote:
> > This needs an official erratum disclosure from the vendor...
> Thanks for the clarification.
> 
> Could you please advise whether this issue should be treated as an Intel
> VT-d erratum or a Lenovo firmware issue?
> 
> The symptom is:
> - ThinkPad P50s with VT-d enabled cannot fully power off.
> - Adding intel_iommu=off resolves the issue.
> - The issue is reproducible on this platform.
> 
> If Intel erratum is not applicable, would a Lenovo firmware confirmation
> be sufficient for adding a platform quirk?

If it's confirmed to be a hardware issue, it should be (or will be) documented
as an VT-d erratum. Then a quirk could be added accordingly.

If Lenovo confirms to be a firmware issue, then they should release a new
firmware version to fix it. It doesn't justify a quirk in iommu driver.

and it is not about a policy "whether this issue should be *treated* as...".
It needs a root cause first.