On Mon, 4 May 2020 22:25:40 +0200 Peter Zijlstra <pet...@infradead.org> wrote:
> I'm only following this with half an eye atm, but one solution is to > pull the vmalloc fault out of the trace path entirely. > > With the current code that is 'interesting', but with the pile of > patches Thomas is sitting on that would be quite feasible. As I assume that's not something that would be backported to the stable kernels, I'm still going to add the workaround. But getting rid of vmalloc_sync_mappings() altogether is still a good idea IMO. -- Steve