On Wed, Apr 15, 2015 at 03:08:56PM +0100, Tvrtko Ursulin wrote: > > On 04/14/2015 05:31 PM, Chris Wilson wrote: > >In order to use userptr, the kernel tracks the owner's mm with a > >mmu_notifier. Setting that is very expensive - it involves taking all > >mm_locks and a stop_machine(). This tracking lives only for as long as > >the client is using userptr objects - so if the client allocates then > >frees a userptr in a loop, we will be executing that heavyweight setup > >everytime. To ammoritize this cost, just leak the test bo and the single > > Spellcheck on this line. > > Also, if drm_intel_bufmgr_destroy is what I think it is, I think for > correctness we would need to release that stuff there. What do you > think? I could respin it with that if you are too busy? I contemplated it, then decided I was too lazy to store a couple of pointers. If you want to respin with that and push, please do. -Chris -- Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx http://lists.freedesktop.org/mailman/listinfo/intel-gfx
