On 2016/10/14 8:24, Tejun Heo wrote: > Hello, > > On Fri, Oct 14, 2016 at 08:06:10AM +0800, zijun_hu wrote: >>> I really can't decode what the actual issue is here. Can you please >>> give an example of a concrete case? >>> >> the right relationship between the number of CPUs @nr_cpus within a percpu group >> and the number of unites @nr_units within the same group is that >> @nr_units == roundup(@nr_cpus, @upa); > > My question was whether there can be actual hardware configurations > where this code can fail and if so what they look like and how they > would fail. > > Thanks. > this answer is difficult to answer since there are so many hardware configurations moreover, besides hardware configuration, reserved size can contribute to this issue as we known, this interface is developed for various ARCHs to setups percpu areas, so we should not assume more detailed aspects about ARCH. neither hardware config nor reserved size. i am learning memory management code and find the inconsistency between here and there. the log is similar with a panic triggered by BUG_ON() if the numbers of CPUs isn't aligned to @upa are you agree the relationship of between CPU and units? what bad effects do this changes results in? are you sure all hardware configurations and reserved size always make number of CPUs are equal to units? if ture， is it redundant for the consideration in there place. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>