On Tue, Feb 18, 2025 at 03:08:46PM -0400, Jason Gunthorpe wrote:

On Tue, Feb 18, 2025 at 11:02:23AM -0800, Nicolin Chen wrote:

quoted

quoted

quoted

quoted

This already holds the streams_mutex across all of this, do you think
we should get rid of the vmaster_rwsem and hold the streams_mutex on
write instead?

They are per master v.s. per smmu. The latter one would make master
commits/attaches exclusive, which feels unnecessary to me, although
it would make the code here slightly cleaner..

I'd pay the cost on the attach side to have a single lock on the fault
side..

OK. Maybe a small patch to turn the streams_mutex to streams_rwsem?

I don't think the interrupt path is multithreaded, is it? So only 1
reader anyhow?

Right, it's IRQF_ONESHOT. I will keep that unchanged.

Thanks
Nicolin