b8f593cd08
To swap out THP (Transparent Huage Page), before splitting the THP, the swap cluster will be allocated and the THP will be added into the swap cache. But it is possible that the THP cannot be split, so that we must delete the THP from the swap cache and free the swap cluster. To avoid that, in this patch, whether the THP can be split is checked firstly. The check can only be done racy, but it is good enough for most cases. With the patch, the swap out throughput improves 3.6% (from about 4.16GB/s to about 4.31GB/s) in the vm-scalability swap-w-seq test case with 8 processes. The test is done on a Xeon E5 v3 system. The swap device used is a RAM simulated PMEM (persistent memory) device. To test the sequential swapping out, the test case creates 8 processes, which sequentially allocate and write to the anonymous pages until the RAM and part of the swap device is used up. Link: http://lkml.kernel.org/r/20170515112522.32457-5-ying.huang@intel.com Signed-off-by: "Huang, Ying" <ying.huang@intel.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> [for can_split_huge_page()] Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Ebru Akagunduz <ebru.akagunduz@gmail.com> Cc: Hugh Dickins <hughd@google.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Shaohua Li <shli@kernel.org> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
319 lines
9.5 KiB
C
319 lines
9.5 KiB
C
#ifndef _LINUX_HUGE_MM_H
|
|
#define _LINUX_HUGE_MM_H
|
|
|
|
extern int do_huge_pmd_anonymous_page(struct vm_fault *vmf);
|
|
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 vm_fault *vmf, pmd_t orig_pmd);
|
|
extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
|
|
pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
|
|
struct vm_area_struct *vma);
|
|
|
|
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
|
|
extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
|
|
#else
|
|
static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
extern int do_huge_pmd_wp_page(struct vm_fault *vmf, 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 bool 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 zap_huge_pud(struct mmu_gather *tlb,
|
|
struct vm_area_struct *vma,
|
|
pud_t *pud, 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, unsigned long old_addr,
|
|
unsigned long new_addr, unsigned long old_end,
|
|
pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush);
|
|
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 *vma, unsigned long addr,
|
|
pmd_t *pmd, pfn_t pfn, bool write);
|
|
int vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
|
|
pud_t *pud, pfn_t pfn, bool write);
|
|
enum transparent_hugepage_flag {
|
|
TRANSPARENT_HUGEPAGE_FLAG,
|
|
TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG,
|
|
TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_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
|
|
};
|
|
|
|
struct kobject;
|
|
struct kobj_attribute;
|
|
|
|
extern ssize_t single_hugepage_flag_store(struct kobject *kobj,
|
|
struct kobj_attribute *attr,
|
|
const char *buf, size_t count,
|
|
enum transparent_hugepage_flag flag);
|
|
extern ssize_t single_hugepage_flag_show(struct kobject *kobj,
|
|
struct kobj_attribute *attr, char *buf,
|
|
enum transparent_hugepage_flag flag);
|
|
extern struct kobj_attribute shmem_enabled_attr;
|
|
|
|
#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))
|
|
|
|
#define HPAGE_PUD_SHIFT PUD_SHIFT
|
|
#define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT)
|
|
#define HPAGE_PUD_MASK (~(HPAGE_PUD_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_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 unsigned long thp_get_unmapped_area(struct file *filp,
|
|
unsigned long addr, unsigned long len, unsigned long pgoff,
|
|
unsigned long flags);
|
|
|
|
extern void prep_transhuge_page(struct page *page);
|
|
extern void free_transhuge_page(struct page *page);
|
|
|
|
bool can_split_huge_page(struct page *page, int *pextra_pins);
|
|
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, bool freeze, struct page *page);
|
|
|
|
#define split_huge_pmd(__vma, __pmd, __address) \
|
|
do { \
|
|
pmd_t *____pmd = (__pmd); \
|
|
if (pmd_trans_huge(*____pmd) \
|
|
|| pmd_devmap(*____pmd)) \
|
|
__split_huge_pmd(__vma, __pmd, __address, \
|
|
false, NULL); \
|
|
} while (0)
|
|
|
|
|
|
void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
|
|
bool freeze, struct page *page);
|
|
|
|
void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
|
|
unsigned long address);
|
|
|
|
#define split_huge_pud(__vma, __pud, __address) \
|
|
do { \
|
|
pud_t *____pud = (__pud); \
|
|
if (pud_trans_huge(*____pud) \
|
|
|| pud_devmap(*____pud)) \
|
|
__split_huge_pud(__vma, __pud, __address); \
|
|
} while (0)
|
|
|
|
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 spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma);
|
|
extern spinlock_t *__pud_trans_huge_lock(pud_t *pud,
|
|
struct vm_area_struct *vma);
|
|
/* mmap_sem must be held on entry */
|
|
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
|
|
if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
|
|
return __pmd_trans_huge_lock(pmd, vma);
|
|
else
|
|
return NULL;
|
|
}
|
|
static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
|
|
if (pud_trans_huge(*pud) || pud_devmap(*pud))
|
|
return __pud_trans_huge_lock(pud, vma);
|
|
else
|
|
return NULL;
|
|
}
|
|
static inline int hpage_nr_pages(struct page *page)
|
|
{
|
|
if (unlikely(PageTransHuge(page)))
|
|
return HPAGE_PMD_NR;
|
|
return 1;
|
|
}
|
|
|
|
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
|
|
pmd_t *pmd, int flags);
|
|
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
|
|
pud_t *pud, int flags);
|
|
|
|
extern int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
|
|
|
|
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));
|
|
}
|
|
|
|
static inline bool is_huge_zero_pud(pud_t pud)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
struct page *mm_get_huge_zero_page(struct mm_struct *mm);
|
|
void mm_put_huge_zero_page(struct mm_struct *mm);
|
|
|
|
#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
|
|
|
|
#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_PUD_SHIFT ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
|
|
#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
|
|
|
|
#define hpage_nr_pages(x) 1
|
|
|
|
#define transparent_hugepage_enabled(__vma) 0
|
|
|
|
static inline void prep_transhuge_page(struct page *page) {}
|
|
|
|
#define transparent_hugepage_flags 0UL
|
|
|
|
#define thp_get_unmapped_area NULL
|
|
|
|
static inline bool
|
|
can_split_huge_page(struct page *page, int *pextra_pins)
|
|
{
|
|
BUILD_BUG();
|
|
return false;
|
|
}
|
|
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 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long address, bool freeze, struct page *page) {}
|
|
static inline void split_huge_pmd_address(struct vm_area_struct *vma,
|
|
unsigned long address, bool freeze, struct page *page) {}
|
|
|
|
#define split_huge_pud(__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 spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return NULL;
|
|
}
|
|
static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool is_huge_zero_page(struct page *page)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline bool is_huge_zero_pud(pud_t pud)
|
|
{
|
|
return false;
|
|
}
|
|
|
|
static inline void mm_put_huge_zero_page(struct mm_struct *mm)
|
|
{
|
|
return;
|
|
}
|
|
|
|
static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
|
|
unsigned long addr, pmd_t *pmd, int flags)
|
|
{
|
|
return NULL;
|
|
}
|
|
|
|
static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
|
|
unsigned long addr, pud_t *pud, int flags)
|
|
{
|
|
return NULL;
|
|
}
|
|
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
|
|
|
|
#endif /* _LINUX_HUGE_MM_H */
|