alistair23-linux/include/linux/hugetlb.h
Andrea Arcangeli 27c73ae759 mm: hugetlbfs: fix hugetlbfs optimization
Commit 7cb2ef56e6 ("mm: fix aio performance regression for database
caused by THP") can cause dereference of a dangling pointer if
split_huge_page runs during PageHuge() if there are updates to the
tail_page->private field.

Also it is repeating compound_head twice for hugetlbfs and it is running
compound_head+compound_trans_head for THP when a single one is needed in
both cases.

The new code within the PageSlab() check doesn't need to verify that the
THP page size is never bigger than the smallest hugetlbfs page size, to
avoid memory corruption.

A longstanding theoretical race condition was found while fixing the
above (see the change right after the skip_unlock label, that is
relevant for the compound_lock path too).

By re-establishing the _mapcount tail refcounting for all compound
pages, this also fixes the below problem:

  echo 0 >/sys/kernel/mm/hugepages/hugepages-2048kB/nr_hugepages

  BUG: Bad page state in process bash  pfn:59a01
  page:ffffea000139b038 count:0 mapcount:10 mapping:          (null) index:0x0
  page flags: 0x1c00000000008000(tail)
  Modules linked in:
  CPU: 6 PID: 2018 Comm: bash Not tainted 3.12.0+ #25
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  Call Trace:
    dump_stack+0x55/0x76
    bad_page+0xd5/0x130
    free_pages_prepare+0x213/0x280
    __free_pages+0x36/0x80
    update_and_free_page+0xc1/0xd0
    free_pool_huge_page+0xc2/0xe0
    set_max_huge_pages.part.58+0x14c/0x220
    nr_hugepages_store_common.isra.60+0xd0/0xf0
    nr_hugepages_store+0x13/0x20
    kobj_attr_store+0xf/0x20
    sysfs_write_file+0x189/0x1e0
    vfs_write+0xc5/0x1f0
    SyS_write+0x55/0xb0
    system_call_fastpath+0x16/0x1b

Signed-off-by: Khalid Aziz <khalid.aziz@oracle.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Tested-by: Khalid Aziz <khalid.aziz@oracle.com>
Cc: Pravin Shelar <pshelar@nicira.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Ben Hutchings <bhutchings@solarflare.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-21 16:42:27 -08:00

455 lines
12 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);
int PageHeadHuge(struct page *page_head);
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 *);
long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
struct page **, struct vm_area_struct **,
unsigned long *, unsigned long *, long, unsigned int);
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);
void hugetlb_report_meminfo(struct seq_file *);
int hugetlb_report_node_meminfo(int, char *);
void hugetlb_show_meminfo(void);
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);
bool isolate_huge_page(struct page *page, struct list_head *list);
void putback_active_hugepage(struct page *page);
bool is_hugepage_active(struct page *page);
#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud);
#endif
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 int PageHeadHuge(struct page *page_head)
{
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; })
static inline void hugetlb_report_meminfo(struct seq_file *m)
{
}
#define hugetlb_report_node_meminfo(n, buf) 0
static inline void hugetlb_show_meminfo(void)
{
}
#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;
}
#define isolate_huge_page(p, l) false
#define putback_active_hugepage(p) do {} while (0)
#define is_hugepage_active(x) false
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, 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, 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);
struct page *alloc_huge_page_noerr(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve);
/* 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(file_inode(f));
}
static inline struct hstate *hstate_sizelog(int page_size_log)
{
if (!page_size_log)
return &default_hstate;
return size_to_hstate(1 << page_size_log);
}
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;
}
pgoff_t __basepage_index(struct page *page);
/* Return page->index in PAGE_SIZE units */
static inline pgoff_t basepage_index(struct page *page)
{
if (!PageCompound(page))
return page->index;
return __basepage_index(page);
}
extern void dissolve_free_huge_pages(unsigned long start_pfn,
unsigned long end_pfn);
int pmd_huge_support(void);
/*
* Currently hugepage migration is enabled only for pmd-based hugepage.
* This function will be updated when hugepage migration is more widely
* supported.
*/
static inline int hugepage_migration_support(struct hstate *h)
{
return pmd_huge_support() && (huge_page_shift(h) == PMD_SHIFT);
}
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
if (huge_page_size(h) == PMD_SIZE)
return pmd_lockptr(mm, (pmd_t *) pte);
VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
return &mm->page_table_lock;
}
#else /* CONFIG_HUGETLB_PAGE */
struct hstate {};
#define alloc_huge_page_node(h, nid) NULL
#define alloc_huge_page_noerr(v, a, r) NULL
#define alloc_bootmem_huge_page(h) NULL
#define hstate_file(f) NULL
#define hstate_sizelog(s) NULL
#define hstate_vma(v) NULL
#define hstate_inode(i) NULL
#define page_hstate(page) 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
static inline pgoff_t basepage_index(struct page *page)
{
return page->index;
}
#define dissolve_free_huge_pages(s, e) do {} while (0)
#define pmd_huge_support() 0
#define hugepage_migration_support(h) 0
static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
return &mm->page_table_lock;
}
#endif /* CONFIG_HUGETLB_PAGE */
static inline spinlock_t *huge_pte_lock(struct hstate *h,
struct mm_struct *mm, pte_t *pte)
{
spinlock_t *ptl;
ptl = huge_pte_lockptr(h, mm, pte);
spin_lock(ptl);
return ptl;
}
#endif /* _LINUX_HUGETLB_H */