On Mon, Jan 20, 2014 at 09:15:25PM +0100, Oleg Nesterov wrote:
> On 01/20, Alex Thorlton wrote:
> >
> > No, definitely not. Upon review, khugepaged_test_exit is the wrong
> > place to do this check. I think I need to move it up to
> > khugepaged_scan_mm_slot for this to work correctly.
>
> Why?
On 01/20, Alex Thorlton wrote:
>
> No, definitely not. Upon review, khugepaged_test_exit is the wrong
> place to do this check. I think I need to move it up to
> khugepaged_scan_mm_slot for this to work correctly.
Why? unless a MMF_THP_DISABLE task does madvise(MADV_HUGEPAGE)
khugepaged_scan_mm_
On Sun, Jan 19, 2014 at 01:49:57AM +0200, Kirill A. Shutemov wrote:
> __khugepaged_enter() has VM_BUG_ON(khugepaged_test_exit(mm)).
> Do we really want to crash there if MMF_THP_DISABLE is set?
No, definitely not. Upon review, khugepaged_test_exit is the wrong
place to do this check. I think I n
On Thu, Jan 16, 2014 at 03:01:44PM -0600, Alex Thorlton wrote:
> This just adds a simple check to get khugepaged to behave
> appropriately when MMF_THP_DISABLE is set.
>
> Signed-off-by: Alex Thorlton
> Cc: Ingo Molnar
> Cc: Peter Zijlstra
> Cc: Andrew Morton
> Cc: "Kirill A. Shutemov"
> Cc:
On Fri, Jan 17, 2014 at 09:34:44PM +0100, Oleg Nesterov wrote:
> On 01/16, Alex Thorlton wrote:
> >
> > static inline int khugepaged_test_exit(struct mm_struct *mm)
> > {
> > - return atomic_read(&mm->mm_users) == 0;
> > + return atomic_read(&mm->mm_users) == 0 ||
> > + (mm->flags &
On 01/16, Alex Thorlton wrote:
>
> static inline int khugepaged_test_exit(struct mm_struct *mm)
> {
> - return atomic_read(&mm->mm_users) == 0;
> + return atomic_read(&mm->mm_users) == 0 ||
> +(mm->flags & MMF_THP_DISABLE_MASK);
^
6 matches
Mail list logo
