On Fri, Feb 02, 2024 at 03:56:52PM +0000, Jon Hunter wrote: > > On 02/02/2024 14:35, Jason Gunthorpe wrote: > > On Fri, Feb 02, 2024 at 10:40:36AM +0000, Jon Hunter wrote: > > > > > > But, what is the actual log output you see, is it -EEXIST? > > > > > > I see ... > > > > > > ERR KERN host1x drm: iommu configuration for device failed with -ENOENT > > > > So that shouldn't happen in you case as far as I can tell, the device > > is properly added, link->kobj should be fine and ENOENT shouldn't > > happen. > > > > > > If it is coming and going is it a race of some kind? > > > > > > It is consistent without the above. However, I did not think that the > > > above change would change the returning on -ENOENT? I will add more > > > debug. > > > > I do not think it can either > > > > Still wonder if there is some odd race.. > > > > Let me know when you figure out what is happening - I think there is > > some bug here it is not just a harmless warning. > > > Yes looks like a race of some sort. Adding a bit of debug also makes the > issue go away so difficult to see what is happening. I'm wondering if it is racing with iommu driver probing? I looked but didn't notice anything obviously wrong there that would cause this though. Though, it shouldn't be racing with self-removal of the device it just added, that would be crazy??? Jason
