linux_dsm_epyc7002/include/linux/huge_mm.h
Yang Shi 87eaceb3fa mm: thp: make deferred split shrinker memcg aware
Currently THP deferred split shrinker is not memcg aware, this may cause
premature OOM with some configuration.  For example the below test would
run into premature OOM easily:

$ cgcreate -g memory:thp
$ echo 4G > /sys/fs/cgroup/memory/thp/memory/limit_in_bytes
$ cgexec -g memory:thp transhuge-stress 4000

transhuge-stress comes from kernel selftest.

It is easy to hit OOM, but there are still a lot THP on the deferred split
queue, memcg direct reclaim can't touch them since the deferred split
shrinker is not memcg aware.

Convert deferred split shrinker memcg aware by introducing per memcg
deferred split queue.  The THP should be on either per node or per memcg
deferred split queue if it belongs to a memcg.  When the page is
immigrated to the other memcg, it will be immigrated to the target memcg's
deferred split queue too.

Reuse the second tail page's deferred_list for per memcg list since the
same THP can't be on multiple deferred split queues.

[yang.shi@linux.alibaba.com: simplify deferred split queue dereference per Kirill Tkhai]
  Link: http://lkml.kernel.org/r/1566496227-84952-5-git-send-email-yang.shi@linux.alibaba.com
Link: http://lkml.kernel.org/r/1565144277-36240-5-git-send-email-yang.shi@linux.alibaba.com
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reviewed-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Qian Cai <cai@lca.pw>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-09-24 15:54:11 -07:00

406 lines
11 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_HUGE_MM_H
#define _LINUX_HUGE_MM_H
#include <linux/sched/coredump.h>
#include <linux/mm_types.h>
#include <linux/fs.h> /* only for vma_is_dax() */
extern vm_fault_t 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 vm_fault_t 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);
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, pgprot_t newprot,
int prot_numa);
vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, 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);
extern unsigned long transparent_hugepage_flags;
/*
* to be used on vmas which are known to support THP.
* Use transparent_hugepage_enabled otherwise
*/
static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
{
if (vma->vm_flags & VM_NOHUGEPAGE)
return false;
if (is_vma_temporary_stack(vma))
return false;
if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
return false;
if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG))
return true;
if (vma_is_dax(vma))
return true;
if (transparent_hugepage_flags &
(1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
return !!(vma->vm_flags & VM_HUGEPAGE);
return false;
}
bool transparent_hugepage_enabled(struct vm_area_struct *vma);
#define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1)
static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
unsigned long haddr)
{
/* Don't have to check pgoff for anonymous vma */
if (!vma_is_anonymous(vma)) {
if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) !=
(vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK))
return false;
}
if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
return false;
return true;
}
#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 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 (is_swap_pmd(*____pmd) || 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);
static inline int is_swap_pmd(pmd_t pmd)
{
return !pmd_none(pmd) && !pmd_present(pmd);
}
/* 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 (is_swap_pmd(*pmd) || 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 dev_pagemap **pgmap);
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
pud_t *pud, int flags, struct dev_pagemap **pgmap);
extern vm_fault_t 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 READ_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))
static inline bool thp_migration_supported(void)
{
return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
}
static inline struct list_head *page_deferred_list(struct page *page)
{
/*
* Global or memcg deferred list in the second tail pages is
* occupied by compound_head.
*/
return &page[2].deferred_list;
}
#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
static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma)
{
return false;
}
static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma)
{
return false;
}
static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
unsigned long haddr)
{
return false;
}
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 int is_swap_pmd(pmd_t pmd)
{
return 0;
}
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 vm_fault_t 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, struct dev_pagemap **pgmap)
{
return NULL;
}
static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap)
{
return NULL;
}
static inline bool thp_migration_supported(void)
{
return false;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_HUGE_MM_H */