a1e78772d7
This patch reserves huge pages at mmap() time for MAP_PRIVATE mappings in a similar manner to the reservations taken for MAP_SHARED mappings. The reserve count is accounted both globally and on a per-VMA basis for private mappings. This guarantees that a process that successfully calls mmap() will successfully fault all pages in the future unless fork() is called. The characteristics of private mappings of hugetlbfs files behaviour after this patch are; 1. The process calling mmap() is guaranteed to succeed all future faults until it forks(). 2. On fork(), the parent may die due to SIGKILL on writes to the private mapping if enough pages are not available for the COW. For reasonably reliable behaviour in the face of a small huge page pool, children of hugepage-aware processes should not reference the mappings; such as might occur when fork()ing to exec(). 3. On fork(), the child VMAs inherit no reserves. Reads on pages already faulted by the parent will succeed. Successful writes will depend on enough huge pages being free in the pool. 4. Quotas of the hugetlbfs mount are checked at reserve time for the mapper and at fault time otherwise. Before this patch, all reads or writes in the child potentially needs page allocations that can later lead to the death of the parent. This applies to reads and writes of uninstantiated pages as well as COW. After the patch it is only a write to an instantiated page that causes problems. Signed-off-by: Mel Gorman <mel@csn.ul.ie> Acked-by: Adam Litke <agl@us.ibm.com> Cc: Andy Whitcroft <apw@shadowen.org> Cc: William Lee Irwin III <wli@holomorphy.com> Cc: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
166 lines
5.2 KiB
C
166 lines
5.2 KiB
C
#ifndef _LINUX_HUGETLB_H
|
|
#define _LINUX_HUGETLB_H
|
|
|
|
#include <linux/fs.h>
|
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/shm.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/hugetlb.h>
|
|
|
|
struct ctl_table;
|
|
|
|
static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
|
|
{
|
|
return vma->vm_flags & VM_HUGETLB;
|
|
}
|
|
|
|
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
|
|
int hugetlb_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
|
|
int hugetlb_overcommit_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
|
|
int hugetlb_treat_movable_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *);
|
|
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, int);
|
|
void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
|
|
void __unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long);
|
|
int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
|
|
int hugetlb_report_meminfo(char *);
|
|
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, int write_access);
|
|
int hugetlb_reserve_pages(struct inode *inode, long from, long to,
|
|
struct vm_area_struct *vma);
|
|
void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
|
|
|
|
extern unsigned long max_huge_pages;
|
|
extern unsigned long sysctl_overcommit_huge_pages;
|
|
extern unsigned long hugepages_treat_as_movable;
|
|
extern const unsigned long hugetlb_zero, hugetlb_infinity;
|
|
extern int sysctl_hugetlb_shm_group;
|
|
|
|
/* arch callbacks */
|
|
|
|
pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr);
|
|
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);
|
|
int pmd_huge(pmd_t pmd);
|
|
void hugetlb_change_protection(struct vm_area_struct *vma,
|
|
unsigned long address, unsigned long end, pgprot_t newprot);
|
|
|
|
#else /* !CONFIG_HUGETLB_PAGE */
|
|
|
|
static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
|
|
{
|
|
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; })
|
|
#define unmap_hugepage_range(vma, start, end) BUG()
|
|
#define hugetlb_report_meminfo(buf) 0
|
|
#define hugetlb_report_node_meminfo(n, buf) 0
|
|
#define follow_huge_pmd(mm, addr, pmd, write) NULL
|
|
#define prepare_hugepage_range(addr,len) (-EINVAL)
|
|
#define pmd_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, write) ({ BUG(); 0; })
|
|
|
|
#define hugetlb_change_protection(vma, address, end, newprot)
|
|
|
|
#ifndef HPAGE_MASK
|
|
#define HPAGE_MASK PAGE_MASK /* Keep the compiler happy */
|
|
#define HPAGE_SIZE PAGE_SIZE
|
|
#endif
|
|
|
|
#endif /* !CONFIG_HUGETLB_PAGE */
|
|
|
|
#ifdef CONFIG_HUGETLBFS
|
|
struct hugetlbfs_config {
|
|
uid_t uid;
|
|
gid_t gid;
|
|
umode_t mode;
|
|
long nr_blocks;
|
|
long nr_inodes;
|
|
};
|
|
|
|
struct hugetlbfs_sb_info {
|
|
long max_blocks; /* blocks allowed */
|
|
long free_blocks; /* blocks free */
|
|
long max_inodes; /* inodes allowed */
|
|
long free_inodes; /* inodes free */
|
|
spinlock_t stat_lock;
|
|
};
|
|
|
|
|
|
struct hugetlbfs_inode_info {
|
|
struct shared_policy policy;
|
|
struct inode vfs_inode;
|
|
};
|
|
|
|
static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
|
|
{
|
|
return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
|
|
}
|
|
|
|
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 struct vm_operations_struct hugetlb_vm_ops;
|
|
struct file *hugetlb_file_setup(const char *name, size_t);
|
|
int hugetlb_get_quota(struct address_space *mapping, long delta);
|
|
void hugetlb_put_quota(struct address_space *mapping, long delta);
|
|
|
|
#define BLOCKS_PER_HUGEPAGE (HPAGE_SIZE / 512)
|
|
|
|
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;
|
|
}
|
|
|
|
static inline void set_file_hugepages(struct file *file)
|
|
{
|
|
file->f_op = &hugetlbfs_file_operations;
|
|
}
|
|
#else /* !CONFIG_HUGETLBFS */
|
|
|
|
#define is_file_hugepages(file) 0
|
|
#define set_file_hugepages(file) BUG()
|
|
#define hugetlb_file_setup(name,size) 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 */
|
|
|
|
#endif /* _LINUX_HUGETLB_H */
|