alistair23-linux/include/linux/hugetlb.h
Linus Torvalds 3d59eebc5e Automatic NUMA Balancing V11
-----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.18 (GNU/Linux)
 
 iQIcBAABAgAGBQJQx0kQAAoJEHzG/DNEskfi4fQP/R5PRovayroZALBMLnVJDaLD
 Ttr9p40VNXbiJ+MfRgatJjSSJZ4Jl+fC3NEqBhcwVZhckZZb9R2s0WtrSQo5+ZbB
 vdRfiuKoCaKM4cSZ08C12uTvsF6xjhjd27CTUlMkyOcDoKxMEFKelv0hocSxe4Wo
 xqlv3eF+VsY7kE1BNbgBP06SX4tDpIHRxXfqJPMHaSKQmre+cU0xG2GcEu3QGbHT
 DEDTI788YSaWLmBfMC+kWoaQl1+bV/FYvavIAS8/o4K9IKvgR42VzrXmaFaqrbgb
 72ksa6xfAi57yTmZHqyGmts06qYeBbPpKI+yIhCMInxA9CY3lPbvHppRf0RQOyzj
 YOi4hovGEMJKE+BCILukhJcZ9jCTtS3zut6v1rdvR88f4y7uhR9RfmRfsxuW7PNj
 3Rmh191+n0lVWDmhOs2psXuCLJr3LEiA0dFffN1z8REUTtTAZMsj8Rz+SvBNAZDR
 hsJhERVeXB6X5uQ5rkLDzbn1Zic60LjVw7LIp6SF2OYf/YKaF8vhyWOA8dyCEu8W
 CGo7AoG0BO8tIIr8+LvFe8CweypysZImx4AjCfIs4u9pu/v11zmBvO9NO5yfuObF
 BreEERYgTes/UITxn1qdIW4/q+Nr0iKO3CTqsmu6L1GfCz3/XzPGs3U26fUhllqi
 Ka0JKgnWvsa6ez6FSzKI
 =ivQa
 -----END PGP SIGNATURE-----

Merge tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma

Pull Automatic NUMA Balancing bare-bones from Mel Gorman:
 "There are three implementations for NUMA balancing, this tree
  (balancenuma), numacore which has been developed in tip/master and
  autonuma which is in aa.git.

  In almost all respects balancenuma is the dumbest of the three because
  its main impact is on the VM side with no attempt to be smart about
  scheduling.  In the interest of getting the ball rolling, it would be
  desirable to see this much merged for 3.8 with the view to building
  scheduler smarts on top and adapting the VM where required for 3.9.

  The most recent set of comparisons available from different people are

    mel:    https://lkml.org/lkml/2012/12/9/108
    mingo:  https://lkml.org/lkml/2012/12/7/331
    tglx:   https://lkml.org/lkml/2012/12/10/437
    srikar: https://lkml.org/lkml/2012/12/10/397

  The results are a mixed bag.  In my own tests, balancenuma does
  reasonably well.  It's dumb as rocks and does not regress against
  mainline.  On the other hand, Ingo's tests shows that balancenuma is
  incapable of converging for this workloads driven by perf which is bad
  but is potentially explained by the lack of scheduler smarts.  Thomas'
  results show balancenuma improves on mainline but falls far short of
  numacore or autonuma.  Srikar's results indicate we all suffer on a
  large machine with imbalanced node sizes.

  My own testing showed that recent numacore results have improved
  dramatically, particularly in the last week but not universally.
  We've butted heads heavily on system CPU usage and high levels of
  migration even when it shows that overall performance is better.
  There are also cases where it regresses.  Of interest is that for
  specjbb in some configurations it will regress for lower numbers of
  warehouses and show gains for higher numbers which is not reported by
  the tool by default and sometimes missed in treports.  Recently I
  reported for numacore that the JVM was crashing with
  NullPointerExceptions but currently it's unclear what the source of
  this problem is.  Initially I thought it was in how numacore batch
  handles PTEs but I'm no longer think this is the case.  It's possible
  numacore is just able to trigger it due to higher rates of migration.

  These reports were quite late in the cycle so I/we would like to start
  with this tree as it contains much of the code we can agree on and has
  not changed significantly over the last 2-3 weeks."

* tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma: (50 commits)
  mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable
  mm/rmap: Convert the struct anon_vma::mutex to an rwsem
  mm: migrate: Account a transhuge page properly when rate limiting
  mm: numa: Account for failed allocations and isolations as migration failures
  mm: numa: Add THP migration for the NUMA working set scanning fault case build fix
  mm: numa: Add THP migration for the NUMA working set scanning fault case.
  mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node
  mm: sched: numa: Control enabling and disabling of NUMA balancing if !SCHED_DEBUG
  mm: sched: numa: Control enabling and disabling of NUMA balancing
  mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
  mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
  mm: numa: migrate: Set last_nid on newly allocated page
  mm: numa: split_huge_page: Transfer last_nid on tail page
  mm: numa: Introduce last_nid to the page frame
  sched: numa: Slowly increase the scanning period as NUMA faults are handled
  mm: numa: Rate limit setting of pte_numa if node is saturated
  mm: numa: Rate limit the amount of memory that is migrated between nodes
  mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting
  mm: numa: Migrate pages handled during a pmd_numa hinting fault
  mm: numa: Migrate on reference policy
  ...
2012-12-16 15:18:08 -08:00

373 lines
10 KiB
C

#ifndef _LINUX_HUGETLB_H
#define _LINUX_HUGETLB_H
#include <linux/mm_types.h>
#include <linux/fs.h>
#include <linux/hugetlb_inline.h>
#include <linux/cgroup.h>
struct ctl_table;
struct user_struct;
struct mmu_gather;
#ifdef CONFIG_HUGETLB_PAGE
#include <linux/mempolicy.h>
#include <linux/shm.h>
#include <asm/tlbflush.h>
struct hugepage_subpool {
spinlock_t lock;
long count;
long max_hpages, used_hpages;
};
extern spinlock_t hugetlb_lock;
extern int hugetlb_max_hstate __read_mostly;
#define for_each_hstate(h) \
for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
void hugepage_put_subpool(struct hugepage_subpool *spool);
int PageHuge(struct page *page);
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
int hugetlb_treat_movable_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
#ifdef CONFIG_NUMA
int hugetlb_mempolicy_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
#endif
int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *);
int follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
unsigned long *, int *, int, unsigned int flags);
void unmap_hugepage_range(struct vm_area_struct *,
unsigned long, unsigned long, struct page *);
void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page);
void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page);
int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(int, char *);
unsigned long hugetlb_total_pages(void);
int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags);
int hugetlb_reserve_pages(struct inode *inode, long from, long to,
struct vm_area_struct *vma,
vm_flags_t vm_flags);
void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
int dequeue_hwpoisoned_huge_page(struct page *page);
void copy_huge_page(struct page *dst, struct page *src);
extern unsigned long hugepages_treat_as_movable;
extern const unsigned long hugetlb_zero, hugetlb_infinity;
extern int sysctl_hugetlb_shm_group;
extern struct list_head huge_boot_pages;
/* arch callbacks */
pte_t *huge_pte_alloc(struct mm_struct *mm,
unsigned long addr, unsigned long sz);
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
int write);
struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write);
struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
pud_t *pud, int write);
int pmd_huge(pmd_t pmd);
int pud_huge(pud_t pmd);
unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot);
#else /* !CONFIG_HUGETLB_PAGE */
static inline int PageHuge(struct page *page)
{
return 0;
}
static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
static inline unsigned long hugetlb_total_pages(void)
{
return 0;
}
#define follow_hugetlb_page(m,v,p,vs,a,b,i,w) ({ BUG(); 0; })
#define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL)
#define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; })
#define hugetlb_prefault(mapping, vma) ({ BUG(); 0; })
static inline void hugetlb_report_meminfo(struct seq_file *m)
{
}
#define hugetlb_report_node_meminfo(n, buf) 0
#define follow_huge_pmd(mm, addr, pmd, write) NULL
#define follow_huge_pud(mm, addr, pud, write) NULL
#define prepare_hugepage_range(file, addr, len) (-EINVAL)
#define pmd_huge(x) 0
#define pud_huge(x) 0
#define is_hugepage_only_range(mm, addr, len) 0
#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
#define hugetlb_fault(mm, vma, addr, flags) ({ BUG(); 0; })
#define huge_pte_offset(mm, address) 0
static inline int dequeue_hwpoisoned_huge_page(struct page *page)
{
return 0;
}
static inline void copy_huge_page(struct page *dst, struct page *src)
{
}
static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
unsigned long address, unsigned long end, pgprot_t newprot)
{
return 0;
}
static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
BUG();
}
static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
struct vm_area_struct *vma, unsigned long start,
unsigned long end, struct page *ref_page)
{
BUG();
}
#endif /* !CONFIG_HUGETLB_PAGE */
#define HUGETLB_ANON_FILE "anon_hugepage"
enum {
/*
* The file will be used as an shm file so shmfs accounting rules
* apply
*/
HUGETLB_SHMFS_INODE = 1,
/*
* The file is being created on the internal vfs mount and shmfs
* accounting rules do not apply
*/
HUGETLB_ANONHUGE_INODE = 2,
};
#ifdef CONFIG_HUGETLBFS
struct hugetlbfs_sb_info {
long max_inodes; /* inodes allowed */
long free_inodes; /* inodes free */
spinlock_t stat_lock;
struct hstate *hstate;
struct hugepage_subpool *spool;
};
static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
extern const struct file_operations hugetlbfs_file_operations;
extern const struct vm_operations_struct hugetlb_vm_ops;
struct file *hugetlb_file_setup(const char *name, unsigned long addr,
size_t size, vm_flags_t acct,
struct user_struct **user, int creat_flags,
int page_size_log);
static inline int is_file_hugepages(struct file *file)
{
if (file->f_op == &hugetlbfs_file_operations)
return 1;
if (is_file_shm_hugepages(file))
return 1;
return 0;
}
#else /* !CONFIG_HUGETLBFS */
#define is_file_hugepages(file) 0
static inline struct file *
hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
vm_flags_t acctflag, struct user_struct **user, int creat_flags,
int page_size_log)
{
return ERR_PTR(-ENOSYS);
}
#endif /* !CONFIG_HUGETLBFS */
#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
unsigned long flags);
#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
#ifdef CONFIG_HUGETLB_PAGE
#define HSTATE_NAME_LEN 32
/* Defines one hugetlb page size */
struct hstate {
int next_nid_to_alloc;
int next_nid_to_free;
unsigned int order;
unsigned long mask;
unsigned long max_huge_pages;
unsigned long nr_huge_pages;
unsigned long free_huge_pages;
unsigned long resv_huge_pages;
unsigned long surplus_huge_pages;
unsigned long nr_overcommit_huge_pages;
struct list_head hugepage_activelist;
struct list_head hugepage_freelists[MAX_NUMNODES];
unsigned int nr_huge_pages_node[MAX_NUMNODES];
unsigned int free_huge_pages_node[MAX_NUMNODES];
unsigned int surplus_huge_pages_node[MAX_NUMNODES];
#ifdef CONFIG_CGROUP_HUGETLB
/* cgroup control files */
struct cftype cgroup_files[5];
#endif
char name[HSTATE_NAME_LEN];
};
struct huge_bootmem_page {
struct list_head list;
struct hstate *hstate;
#ifdef CONFIG_HIGHMEM
phys_addr_t phys;
#endif
};
struct page *alloc_huge_page_node(struct hstate *h, int nid);
/* arch callback */
int __init alloc_bootmem_huge_page(struct hstate *h);
void __init hugetlb_add_hstate(unsigned order);
struct hstate *size_to_hstate(unsigned long size);
#ifndef HUGE_MAX_HSTATE
#define HUGE_MAX_HSTATE 1
#endif
extern struct hstate hstates[HUGE_MAX_HSTATE];
extern unsigned int default_hstate_idx;
#define default_hstate (hstates[default_hstate_idx])
static inline struct hstate *hstate_inode(struct inode *i)
{
struct hugetlbfs_sb_info *hsb;
hsb = HUGETLBFS_SB(i->i_sb);
return hsb->hstate;
}
static inline struct hstate *hstate_file(struct file *f)
{
return hstate_inode(f->f_dentry->d_inode);
}
static inline struct hstate *hstate_vma(struct vm_area_struct *vma)
{
return hstate_file(vma->vm_file);
}
static inline unsigned long huge_page_size(struct hstate *h)
{
return (unsigned long)PAGE_SIZE << h->order;
}
extern unsigned long vma_kernel_pagesize(struct vm_area_struct *vma);
extern unsigned long vma_mmu_pagesize(struct vm_area_struct *vma);
static inline unsigned long huge_page_mask(struct hstate *h)
{
return h->mask;
}
static inline unsigned int huge_page_order(struct hstate *h)
{
return h->order;
}
static inline unsigned huge_page_shift(struct hstate *h)
{
return h->order + PAGE_SHIFT;
}
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1 << h->order;
}
static inline unsigned int blocks_per_huge_page(struct hstate *h)
{
return huge_page_size(h) / 512;
}
#include <asm/hugetlb.h>
#ifndef arch_make_huge_pte
static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
struct page *page, int writable)
{
return entry;
}
#endif
static inline struct hstate *page_hstate(struct page *page)
{
return size_to_hstate(PAGE_SIZE << compound_order(page));
}
static inline unsigned hstate_index_to_shift(unsigned index)
{
return hstates[index].order + PAGE_SHIFT;
}
static inline int hstate_index(struct hstate *h)
{
return h - hstates;
}
#else
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
#define alloc_bootmem_huge_page(h) NULL
#define hstate_file(f) NULL
#define hstate_vma(v) NULL
#define hstate_inode(i) NULL
#define huge_page_size(h) PAGE_SIZE
#define huge_page_mask(h) PAGE_MASK
#define vma_kernel_pagesize(v) PAGE_SIZE
#define vma_mmu_pagesize(v) PAGE_SIZE
#define huge_page_order(h) 0
#define huge_page_shift(h) PAGE_SHIFT
static inline unsigned int pages_per_huge_page(struct hstate *h)
{
return 1;
}
#define hstate_index_to_shift(index) 0
#define hstate_index(h) 0
#endif
#endif /* _LINUX_HUGETLB_H */