Re: [PATCHv5 16/28] mm, thp: remove compound_lock

2015-05-18 Thread Vlastimil Babka
On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: We are going to use migration entries to stabilize page counts. It means we don't need compound_lock() for that. git grep says you didn't clean up enough :) mm/memcontrol.c: * zone->lru_lock, 'splitting on pmd' and compound_lock.

Re: [PATCHv5 16/28] mm, thp: remove compound_lock

2015-05-18 Thread Vlastimil Babka
On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: We are going to use migration entries to stabilize page counts. It means we don't need compound_lock() for that. git grep says you didn't clean up enough :) mm/memcontrol.c: * zone-lru_lock, 'splitting on pmd' and compound_lock.

Re: [PATCHv5 16/28] mm, thp: remove compound_lock

2015-04-30 Thread Kirill A. Shutemov
On Wed, Apr 29, 2015 at 06:11:08PM +0200, Jerome Marchand wrote: > On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: > > We are going to use migration entries to stabilize page counts. It means > > By "stabilize" do you mean "protect" from concurrent access? I've seen > that you use the same term

Re: [PATCHv5 16/28] mm, thp: remove compound_lock

2015-04-30 Thread Kirill A. Shutemov
On Wed, Apr 29, 2015 at 06:11:08PM +0200, Jerome Marchand wrote: On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: We are going to use migration entries to stabilize page counts. It means By stabilize do you mean protect from concurrent access? I've seen that you use the same term in

Re: [PATCHv5 16/28] mm, thp: remove compound_lock

2015-04-29 Thread Jerome Marchand
On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: > We are going to use migration entries to stabilize page counts. It means By "stabilize" do you mean "protect" from concurrent access? I've seen that you use the same term in seemingly the same sense several times (at least in patches 15, 16, 23,

Re: [PATCHv5 16/28] mm, thp: remove compound_lock

2015-04-29 Thread Jerome Marchand
On 04/23/2015 11:03 PM, Kirill A. Shutemov wrote: We are going to use migration entries to stabilize page counts. It means By stabilize do you mean protect from concurrent access? I've seen that you use the same term in seemingly the same sense several times (at least in patches 15, 16, 23, 24

[PATCHv5 16/28] mm, thp: remove compound_lock

2015-04-23 Thread Kirill A. Shutemov
We are going to use migration entries to stabilize page counts. It means we don't need compound_lock() for that. Signed-off-by: Kirill A. Shutemov Tested-by: Sasha Levin --- include/linux/mm.h | 35 --- include/linux/page-flags.h | 12 +---

[PATCHv5 16/28] mm, thp: remove compound_lock

2015-04-23 Thread Kirill A. Shutemov
We are going to use migration entries to stabilize page counts. It means we don't need compound_lock() for that. Signed-off-by: Kirill A. Shutemov kirill.shute...@linux.intel.com Tested-by: Sasha Levin sasha.le...@oracle.com --- include/linux/mm.h | 35 ---