On Fri 17-01-20 15:43:58, David Hildenbrand wrote: > On 17.01.20 15:42, Michal Hocko wrote: > > On Fri 17-01-20 07:40:15, Qian Cai wrote: > >> > >> > >>> On Jan 17, 2020, at 3:51 AM, David Hildenbrand <david@xxxxxxxxxx> wrote: > >>> > >>> -> you are accessing the pageblock without the zone lock. It could > >>> change to "isolate" again in the meantime if I am not wrong! > >> > >> Since we are just dumping the state for debugging, it should be fine > >> to accept a bit inaccuracy here due to racing. I could put a bit > >> comments over there. > > > > Sorry, I could have been more specific. The race I was talking about is > > not about accuracy. The current code is racy in that sense already > > because you are looking at a struct page you do not own so its state can > > change at any time. Please note that the zone->lock doesn't really > > The pageblock state cannot change with the zone->lock. That's what I was > referring to here. (this specific check) CMA pages tend to have a stable pageblock state. More importantly this is not the most important information from my experience. It is usually reference count and page flags that are of interest. Or details about what kind of filesystem is owning the page and it doesn't want to release it. -- Michal Hocko SUSE Labs
