We don't need to split THP page when MADV_FREE syscall is called if [start, len] is aligned with THP size. The split could be done when VM decide to free it in reclaim path if memory pressure is heavy. With that, we could avoid unnecessary THP split. For the feature, this patch changes pte dirtness marking logic of THP. Now, it marks every ptes of pages dirty unconditionally in splitting, which makes MADV_FREE void. So, instead, this patch propagates pmd dirtiness to all pages via PG_dirty and restores pte dirtiness from PG_dirty. With this, if pmd is clean(ie, MADV_FREEed) when split happens(e,g, shrink_page_list), all of pages are clean too so we could discard them. Signed-off-by: Minchan Kim <minchan@kernel.org> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Shaohua Li <shli@kernel.org> Cc: <yalin.wang2010@gmail.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chen Gang <gang.chen.5i5j@gmail.com> Cc: Chris Zankel <chris@zankel.net> Cc: Daniel Micay <danielmicay@gmail.com> Cc: Darrick J. Wong <darrick.wong@oracle.com> Cc: David S. Miller <davem@davemloft.net> Cc: Helge Deller <deller@gmx.de> Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru> Cc: Jason Evans <je@fb.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mika Penttil <mika.penttila@nextfour.com> Cc: Ralf Baechle <ralf@linux-mips.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Rik van Riel <riel@redhat.com> Cc: Roland Dreier <roland@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Shaohua Li <shli@kernel.org> Cc: Will Deacon <will.deacon@arm.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
210 lines
6.4 KiB
C
210 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 void huge_pmd_set_accessed(struct mm_struct *mm,
|
|
struct vm_area_struct *vma,
|
|
unsigned long address, pmd_t *pmd,
|
|
pmd_t orig_pmd, int dirty);
|
|
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 madvise_free_huge_pmd(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pmd_t *pmd, unsigned long addr, unsigned long next);
|
|
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 bool 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,
|
|
int prot_numa);
|
|
int vmf_insert_pfn_pmd(struct vm_area_struct *, unsigned long addr, pmd_t *,
|
|
unsigned long pfn, bool write);
|
|
|
|
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,
|
|
TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG,
|
|
#ifdef CONFIG_DEBUG_VM
|
|
TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
|
|
#endif
|
|
};
|
|
|
|
#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 PMD_SHIFT
|
|
#define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT)
|
|
#define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1))
|
|
|
|
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))
|
|
#define transparent_hugepage_use_zero_page() \
|
|
(transparent_hugepage_flags & \
|
|
(1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
|
|
#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 void prep_transhuge_page(struct page *page);
|
|
extern void free_transhuge_page(struct page *page);
|
|
|
|
int split_huge_page_to_list(struct page *page, struct list_head *list);
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return split_huge_page_to_list(page, NULL);
|
|
}
|
|
void deferred_split_huge_page(struct page *page);
|
|
|
|
void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long address);
|
|
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { \
|
|
pmd_t *____pmd = (__pmd); \
|
|
if (pmd_trans_huge(*____pmd)) \
|
|
__split_huge_pmd(__vma, __pmd, __address); \
|
|
} 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 bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
|
|
spinlock_t **ptl);
|
|
/* mmap_sem must be held on entry */
|
|
static inline bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
|
|
spinlock_t **ptl)
|
|
{
|
|
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
|
|
if (pmd_trans_huge(*pmd))
|
|
return __pmd_trans_huge_lock(pmd, vma, ptl);
|
|
else
|
|
return false;
|
|
}
|
|
static inline int hpage_nr_pages(struct page *page)
|
|
{
|
|
if (unlikely(PageTransHuge(page)))
|
|
return HPAGE_PMD_NR;
|
|
return 1;
|
|
}
|
|
|
|
extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long addr, pmd_t pmd, pmd_t *pmdp);
|
|
|
|
extern struct page *huge_zero_page;
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return ACCESS_ONCE(huge_zero_page) == page;
|
|
}
|
|
|
|
static inline bool is_huge_zero_pmd(pmd_t pmd)
|
|
{
|
|
return is_huge_zero_page(pmd_page(pmd));
|
|
}
|
|
|
|
struct page *get_huge_zero_page(void);
|
|
|
|
#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_to_list(struct page *page, struct list_head *list)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int split_huge_page(struct page *page)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline void deferred_split_huge_page(struct page *page) {}
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { } while (0)
|
|
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 bool pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma,
|
|
spinlock_t **ptl)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long addr, pmd_t pmd, pmd_t *pmdp)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
#endif /* _LINUX_HUGE_MM_H */
|