> > I wonder, is that a win? I guess you don't even have to pin it, just do > > copy_to_user() to update the counter, but mmap doesn't seem so bad. > > Not sure you can call copy_to_user from a mmu_notifier callback? What > if it faults?
Good point... we could defer it to a context where we could block but... > I think the idea would be that by letting user space select the > counter location it could place it in a sensible cachline/etc and > probably avoid a pointer indirection. OK, I have to look at the perf stuff. That makes sense but OTOH userspace could (unknowingly) pick a highmen page and then we end up having to do kmap_atomic or something from an mmu notifier callback. -- Roland Dreier <rola...@cisco.com> For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/index.html -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html