linux_dsm_epyc7002/include/linux/huge_mm.h
David Rientjes 21440d7eb9 mm, thp: add new defer+madvise defrag option
There is no thp defrag option that currently allows MADV_HUGEPAGE
regions to do direct compaction and reclaim while all other thp
allocations simply trigger kswapd and kcompactd in the background and
fail immediately.

The "defer" setting simply triggers background reclaim and compaction
for all regions, regardless of MADV_HUGEPAGE, which makes it unusable
for our userspace where MADV_HUGEPAGE is being used to indicate the
application is willing to wait for work for thp memory to be available.

The "madvise" setting will do direct compaction and reclaim for these
MADV_HUGEPAGE regions, but does not trigger kswapd and kcompactd in the
background for anybody else.

For reasonable usage, there needs to be a mesh between the two options.
This patch introduces a fifth mode, "defer+madvise", that will do direct
reclaim and compaction for MADV_HUGEPAGE regions and trigger background
reclaim and compaction for everybody else so that hugepages may be
available in the near future.

A proposal to allow direct reclaim and compaction for MADV_HUGEPAGE
regions as part of the "defer" mode, making it a very powerful setting
and avoids breaking userspace, was offered:
     http://marc.info/?t=148236612700003
This additional mode is a compromise.

A second proposal to allow both "defer" and "madvise" to be selected at
the same time was also offered:
     http://marc.info/?t=148357345300001.
This is possible, but there was a concern that it might break existing
userspaces the parse the output of the defrag mode, so the fifth option
was introduced instead.

This patch also cleans up the helper function for storing to "enabled"
and "defrag" since the former supports three modes while the latter
supports five and triple_flag_store() was getting unnecessarily messy.

Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1701101614330.41805@chino.kir.corp.google.com
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-02-22 16:41:30 -08:00

239 lines
7.3 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 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 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 *, unsigned long addr, pmd_t *,
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
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
pmd_t *pmd, int flags);
#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_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);
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);
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);
/* 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 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 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));
}
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_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 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) {}
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 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 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;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#endif /* _LINUX_HUGE_MM_H */