Re: [PATCHv4 18/24] thp, mm: split_huge_page(): caller need to lock page

2015-03-30 Thread Kirill A. Shutemov
On Mon, Mar 30, 2015 at 07:40:29PM +0530, Aneesh Kumar K.V wrote: > "Kirill A. Shutemov" writes: > > > We're going to use migration entries instead of compound_lock() to > > stabilize page refcounts. Setup and remove migration entries require > > page to be locked. > > > > Some of

Re: [PATCHv4 18/24] thp, mm: split_huge_page(): caller need to lock page

2015-03-30 Thread Aneesh Kumar K.V
"Kirill A. Shutemov" writes: > We're going to use migration entries instead of compound_lock() to > stabilize page refcounts. Setup and remove migration entries require > page to be locked. > > Some of split_huge_page() callers already have the page locked. Let's > require everybody to lock the

Re: [PATCHv4 18/24] thp, mm: split_huge_page(): caller need to lock page

2015-03-30 Thread Aneesh Kumar K.V
Kirill A. Shutemov kirill.shute...@linux.intel.com writes: We're going to use migration entries instead of compound_lock() to stabilize page refcounts. Setup and remove migration entries require page to be locked. Some of split_huge_page() callers already have the page locked. Let's require

Re: [PATCHv4 18/24] thp, mm: split_huge_page(): caller need to lock page

2015-03-30 Thread Kirill A. Shutemov
On Mon, Mar 30, 2015 at 07:40:29PM +0530, Aneesh Kumar K.V wrote: Kirill A. Shutemov kirill.shute...@linux.intel.com writes: We're going to use migration entries instead of compound_lock() to stabilize page refcounts. Setup and remove migration entries require page to be locked. Some

[PATCHv4 18/24] thp, mm: split_huge_page(): caller need to lock page

2015-03-04 Thread Kirill A. Shutemov
We're going to use migration entries instead of compound_lock() to stabilize page refcounts. Setup and remove migration entries require page to be locked. Some of split_huge_page() callers already have the page locked. Let's require everybody to lock the page before calling split_huge_page().

[PATCHv4 18/24] thp, mm: split_huge_page(): caller need to lock page

2015-03-04 Thread Kirill A. Shutemov
We're going to use migration entries instead of compound_lock() to stabilize page refcounts. Setup and remove migration entries require page to be locked. Some of split_huge_page() callers already have the page locked. Let's require everybody to lock the page before calling split_huge_page().