On Fri 17-11-17 09:35:21, Christoph Hellwig wrote: > On Tue, Nov 14, 2017 at 06:37:42AM +0900, Tetsuo Handa wrote: > > Since do_shrink_slab() can reschedule, we cannot protect shrinker_list > > using one RCU section. But using atomic_inc()/atomic_dec() for each > > do_shrink_slab() call will not impact so much. > > But you could use SRCU..
Davidlohr has tried that already http://lkml.kernel.org/r/1434398602.1903.15.ca...@stgolabs.net and failed. Doing SRCU inside core kernel is not seen with a great support... -- Michal Hocko SUSE Labs
