linux_dsm_epyc7002/include/linux/khugepaged.h
Michal Hocko 1860033237 mm: make PR_SET_THP_DISABLE immediately active
PR_SET_THP_DISABLE has a rather subtle semantic.  It doesn't affect any
existing mapping because it only updated mm->def_flags which is a
template for new mappings.

The mappings created after prctl(PR_SET_THP_DISABLE) have VM_NOHUGEPAGE
flag set.  This can be quite surprising for all those applications which
do not do prctl(); fork() & exec() and want to control their own THP
behavior.

Another usecase when the immediate semantic of the prctl might be useful
is a combination of pre- and post-copy migration of containers with
CRIU.  In this case CRIU populates a part of a memory region with data
that was saved during the pre-copy stage.  Afterwards, the region is
registered with userfaultfd and CRIU expects to get page faults for the
parts of the region that were not yet populated.  However, khugepaged
collapses the pages and the expected page faults do not occur.

In more general case, the prctl(PR_SET_THP_DISABLE) could be used as a
temporary mechanism for enabling/disabling THP process wide.

Implementation wise, a new MMF_DISABLE_THP flag is added.  This flag is
tested when decision whether to use huge pages is taken either during
page fault of at the time of THP collapse.

It should be noted, that the new implementation makes PR_SET_THP_DISABLE
master override to any per-VMA setting, which was not the case
previously.

Fixes: a0715cc226 ("mm, thp: add VM_INIT_DEF_MASK and PRCTL_THP_DISABLE")
Link: http://lkml.kernel.org/r/1496415802-30944-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-07-10 16:32:31 -07:00

78 lines
2.2 KiB
C

#ifndef _LINUX_KHUGEPAGED_H
#define _LINUX_KHUGEPAGED_H
#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern struct attribute_group khugepaged_attr_group;
extern int khugepaged_init(void);
extern void khugepaged_destroy(void);
extern int start_stop_khugepaged(void);
extern int __khugepaged_enter(struct mm_struct *mm);
extern void __khugepaged_exit(struct mm_struct *mm);
extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
unsigned long vm_flags);
#define khugepaged_enabled() \
(transparent_hugepage_flags & \
((1<<TRANSPARENT_HUGEPAGE_FLAG) | \
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
#define khugepaged_always() \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_FLAG))
#define khugepaged_req_madv() \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
#define khugepaged_defrag() \
(transparent_hugepage_flags & \
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG))
static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags))
return __khugepaged_enter(mm);
return 0;
}
static inline void khugepaged_exit(struct mm_struct *mm)
{
if (test_bit(MMF_VM_HUGEPAGE, &mm->flags))
__khugepaged_exit(mm);
}
static inline int khugepaged_enter(struct vm_area_struct *vma,
unsigned long vm_flags)
{
if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
if ((khugepaged_always() ||
(khugepaged_req_madv() && (vm_flags & VM_HUGEPAGE))) &&
!(vm_flags & VM_NOHUGEPAGE) &&
!test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
if (__khugepaged_enter(vma->vm_mm))
return -ENOMEM;
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
{
return 0;
}
static inline void khugepaged_exit(struct mm_struct *mm)
{
}
static inline int khugepaged_enter(struct vm_area_struct *vma,
unsigned long vm_flags)
{
return 0;
}
static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma,
unsigned long vm_flags)
{
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_KHUGEPAGED_H */