On Thu 17-09-20 15:48:57, Ira Weiny wrote: > On Thu, Sep 17, 2020 at 07:09:00PM -0300, Jason Gunthorpe wrote: > > On Thu, Sep 17, 2020 at 05:40:59PM -0400, Peter Xu wrote: > > > On Thu, Sep 17, 2020 at 01:35:56PM -0700, Linus Torvalds wrote: > > > > For that to happen, we'd need to have the vma flag so that we wouldn't > > > > have any worry about non-pinners, but as you suggested, I think even > > > > just a mm-wide counter - or flag - to deal with the fast-bup case is > > > > likely perfectly sufficient. > > > > > > Would mm_struct.pinned_vm suffice? > > > > I think that could be a good long term goal > > > > IIRC last time we dug into the locked_vm vs pinned_vm mess it didn't > > get fixed. There is a mix of both kinds, as you saw, and some > > resistance I don't clearly remember to changing it. > > > > My advice for this -rc fix is to go with a single bit in the mm_struct > > set on any call to pin_user_pages* > > > > Then only users using pin_user_pages and forking are the only ones who > > would ever do extra COW on fork. I think that is OK for -rc, this > > workload should be rare due to the various historical issues. Anyhow, > > a slow down regression is better than a it is broken regression. > > > > This can be improved into a counter later. Due to the pinned_vm > > accounting all call sites should have the mm_struct at unpin, but I > > have a feeling it will take a alot of driver patches to sort it all > > out. > > Agreed. The HFI1 driver for example increments/decrements pinned_vm on it's > own. I've kind of always felt dirty for that... > > I think long term it would be better to move this accounting to > pin_user_pages() but Jason is correct that I think that is going to be too > complex for an rc. Moving accounting to pin_user_pages() won't be simple because you need to unaccount on unpin. And that can happen from a different task context (e.g. IRQ handler for direct IO) so we won't have proper mm_struct available. > Could we move pinned_vm out of the drivers/rdma subsystem? I'd love to because IMO it's a mess... Honza -- Jan Kara <jack@xxxxxxxx> SUSE Labs, CR
