Re: [v2 PATCH 6/7] mm: migrate: check mapcount for THP instead of ref count

2021-04-15 Thread Zi Yan
On 15 Apr 2021, at 2:45, Huang, Ying wrote: > "Zi Yan" writes: > >> On 13 Apr 2021, at 23:00, Huang, Ying wrote: >> >>> Yang Shi writes: >>> The generic migration path will check refcount, so no need check refcount here. But the old code actually prevents from migrating shared TH

Re: [v2 PATCH 6/7] mm: migrate: check mapcount for THP instead of ref count

2021-04-14 Thread Huang, Ying
"Zi Yan" writes: > On 13 Apr 2021, at 23:00, Huang, Ying wrote: > >> Yang Shi writes: >> >>> The generic migration path will check refcount, so no need check refcount >>> here. >>> But the old code actually prevents from migrating shared THP (mapped by >>> multiple >>> processes), so bail out

Re: [v2 PATCH 6/7] mm: migrate: check mapcount for THP instead of ref count

2021-04-14 Thread Yang Shi
On Tue, Apr 13, 2021 at 8:00 PM Huang, Ying wrote: > > Yang Shi writes: > > > The generic migration path will check refcount, so no need check refcount > > here. > > But the old code actually prevents from migrating shared THP (mapped by > > multiple > > processes), so bail out early if mapcoun

Re: [v2 PATCH 6/7] mm: migrate: check mapcount for THP instead of ref count

2021-04-14 Thread Zi Yan
On 13 Apr 2021, at 23:00, Huang, Ying wrote: > Yang Shi writes: > >> The generic migration path will check refcount, so no need check refcount >> here. >> But the old code actually prevents from migrating shared THP (mapped by >> multiple >> processes), so bail out early if mapcount is > 1 to k

Re: [v2 PATCH 6/7] mm: migrate: check mapcount for THP instead of ref count

2021-04-13 Thread Huang, Ying
Yang Shi writes: > The generic migration path will check refcount, so no need check refcount > here. > But the old code actually prevents from migrating shared THP (mapped by > multiple > processes), so bail out early if mapcount is > 1 to keep the behavior. What prevents us from migrating sha