![David Rientjes](/assets/img/avatar_default.png)
When a transparent hugepage is mapped and it is included in an mlock() range, follow_page() incorrectly avoids setting the page's mlock bit and moving it to the unevictable lru. This is evident if you try to mlock(), munlock(), and then mlock() a range again. Currently: #define MAP_SIZE (4 << 30) /* 4GB */ void *ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, 0, 0); mlock(ptr, MAP_SIZE); $ grep -E "Unevictable|Inactive\(anon" /proc/meminfo Inactive(anon): 6304 kB Unevictable: 4213924 kB munlock(ptr, MAP_SIZE); Inactive(anon): 4186252 kB Unevictable: 19652 kB mlock(ptr, MAP_SIZE); Inactive(anon): 4198556 kB Unevictable: 21684 kB Notice that less than 2MB was added to the unevictable list; this is because these pages in the range are not transparent hugepages since the 4GB range was allocated with mmap() and has no specific alignment. If posix_memalign() were used instead, unevictable would not have grown at all on the second mlock(). The fix is to call mlock_vma_page() so that the mlock bit is set and the page is added to the unevictable list. With this patch: mlock(ptr, MAP_SIZE); Inactive(anon): 4056 kB Unevictable: 4213940 kB munlock(ptr, MAP_SIZE); Inactive(anon): 4198268 kB Unevictable: 19636 kB mlock(ptr, MAP_SIZE); Inactive(anon): 4008 kB Unevictable: 4213940 kB Signed-off-by: David Rientjes <rientjes@google.com> Acked-by: Hugh Dickins <hughd@google.com> Reviewed-by: Andrea Arcangeli <aarcange@redhat.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
201 lines
6.4 KiB
C
201 lines
6.4 KiB
C
#ifndef _LINUX_HUGE_MM_H
|
|
#define _LINUX_HUGE_MM_H
|
|
|
|
extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
unsigned long address, pmd_t *pmd,
|
|
unsigned int flags);
|
|
extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
|
|
pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
|
|
struct vm_area_struct *vma);
|
|
extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long address, pmd_t *pmd,
|
|
pmd_t orig_pmd);
|
|
extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
|
|
unsigned long addr,
|
|
pmd_t *pmd,
|
|
unsigned int flags);
|
|
extern int zap_huge_pmd(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, unsigned long addr);
|
|
extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, unsigned long end,
|
|
unsigned char *vec);
|
|
extern int move_huge_pmd(struct vm_area_struct *vma,
|
|
struct vm_area_struct *new_vma,
|
|
unsigned long old_addr,
|
|
unsigned long new_addr, unsigned long old_end,
|
|
pmd_t *old_pmd, pmd_t *new_pmd);
|
|
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, pgprot_t newprot);
|
|
|
|
enum transparent_hugepage_flag {
|
|
TRANSPARENT_HUGEPAGE_FLAG,
|
|
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
|
|
#ifdef CONFIG_DEBUG_VM
|
|
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
|
|
#endif
|
|
};
|
|
|
|
enum page_check_address_pmd_flag {
|
|
PAGE_CHECK_ADDRESS_PMD_FLAG,
|
|
PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG,
|
|
PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG,
|
|
};
|
|
extern pmd_t *page_check_address_pmd(struct page *page,
|
|
struct mm_struct *mm,
|
|
unsigned long address,
|
|
enum page_check_address_pmd_flag flag);
|
|
|
|
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
|
|
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
#define HPAGE_PMD_SHIFT HPAGE_SHIFT
|
|
#define HPAGE_PMD_MASK HPAGE_MASK
|
|
#define HPAGE_PMD_SIZE HPAGE_SIZE
|
|
|
|
extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
|
|
|
|
#define transparent_hugepage_enabled(__vma) \
|
|
((transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_FLAG) || \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) && \
|
|
((__vma)->vm_flags & VM_HUGEPAGE))) && \
|
|
!((__vma)->vm_flags & VM_NOHUGEPAGE) && \
|
|
!is_vma_temporary_stack(__vma))
|
|
#define transparent_hugepage_defrag(__vma) \
|
|
((transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) || \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) && \
|
|
(__vma)->vm_flags & VM_HUGEPAGE))
|
|
#ifdef CONFIG_DEBUG_VM
|
|
#define transparent_hugepage_debug_cow() \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
|
|
#else /* CONFIG_DEBUG_VM */
|
|
#define transparent_hugepage_debug_cow() 0
|
|
#endif /* CONFIG_DEBUG_VM */
|
|
|
|
extern unsigned long transparent_hugepage_flags;
|
|
extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
|
|
pmd_t *dst_pmd, pmd_t *src_pmd,
|
|
struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end);
|
|
extern int handle_pte_fault(struct mm_struct *mm,
|
|
struct vm_area_struct *vma, unsigned long address,
|
|
pte_t *pte, pmd_t *pmd, unsigned int flags);
|
|
extern int split_huge_page(struct page *page);
|
|
extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
|
|
#define split_huge_page_pmd(__mm, __pmd) \
|
|
do { \
|
|
pmd_t *____pmd = (__pmd); \
|
|
if (unlikely(pmd_trans_huge(*____pmd))) \
|
|
__split_huge_page_pmd(__mm, ____pmd); \
|
|
} while (0)
|
|
#define wait_split_huge_page(__anon_vma, __pmd) \
|
|
do { \
|
|
pmd_t *____pmd = (__pmd); \
|
|
anon_vma_lock(__anon_vma); \
|
|
anon_vma_unlock(__anon_vma); \
|
|
BUG_ON(pmd_trans_splitting(*____pmd) || \
|
|
pmd_trans_huge(*____pmd)); \
|
|
} while (0)
|
|
#if HPAGE_PMD_ORDER > MAX_ORDER
|
|
#error "hugepages can't be allocated by the buddy allocator"
|
|
#endif
|
|
extern int hugepage_madvise(struct vm_area_struct *vma,
|
|
unsigned long *vm_flags, int advice);
|
|
extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next);
|
|
extern int __pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma);
|
|
/* mmap_sem must be held on entry */
|
|
static inline int pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
|
|
if (pmd_trans_huge(*pmd))
|
|
return __pmd_trans_huge_lock(pmd, vma);
|
|
else
|
|
return 0;
|
|
}
|
|
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next)
|
|
{
|
|
if (!vma->anon_vma || vma->vm_ops)
|
|
return;
|
|
__vma_adjust_trans_huge(vma, start, end, adjust_next);
|
|
}
|
|
static inline int hpage_nr_pages(struct page *page)
|
|
{
|
|
if (unlikely(PageTransHuge(page)))
|
|
return HPAGE_PMD_NR;
|
|
return 1;
|
|
}
|
|
static inline struct page *compound_trans_head(struct page *page)
|
|
{
|
|
if (PageTail(page)) {
|
|
struct page *head;
|
|
head = page->first_page;
|
|
smp_rmb();
|
|
/*
|
|
* head may be a dangling pointer.
|
|
* __split_huge_page_refcount clears PageTail before
|
|
* overwriting first_page, so if PageTail is still
|
|
* there it means the head pointer isn't dangling.
|
|
*/
|
|
if (PageTail(page))
|
|
return head;
|
|
}
|
|
return page;
|
|
}
|
|
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
|
|
|
|
#define hpage_nr_pages(x) 1
|
|
|
|
#define transparent_hugepage_enabled(__vma) 0
|
|
|
|
#define transparent_hugepage_flags 0UL
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
#define split_huge_page_pmd(__mm, __pmd) \
|
|
do { } while (0)
|
|
#define wait_split_huge_page(__anon_vma, __pmd) \
|
|
do { } while (0)
|
|
#define compound_trans_head(page) compound_head(page)
|
|
static inline int hugepage_madvise(struct vm_area_struct *vma,
|
|
unsigned long *vm_flags, int advice)
|
|
{
|
|
BUG();
|
|
return 0;
|
|
}
|
|
static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
|
|
unsigned long start,
|
|
unsigned long end,
|
|
long adjust_next)
|
|
{
|
|
}
|
|
static inline int pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
#endif /* _LINUX_HUGE_MM_H */
|