On 2022-02-03 11:09:57 [+0100], Michal Hocko wrote: > Thanks for this test. I do assume that both have been run inside a > non-root memcg. I did run after a regular login on a Debian unstable installation. I did confirm via trace_printk() that get_obj_stock() was invoked from process and interrupt context and the caller was cc1 and so on. > Weiman, what was the original motivation for 559271146efc0? Because as > this RT patch shows it makes future changes much more complex and I > would prefer a simpler and easier to maintain code than some micro > optimizations that do not have any visible effect on real workloads. Sebastian
