f3f0e1d215
This patch extends khugepaged to support collapse of tmpfs/shmem pages.
We share fair amount of infrastructure with anon-THP collapse.
Few design points:
- First we are looking for VMA which can be suitable for mapping huge
page;
- If the VMA maps shmem file, the rest scan/collapse operations
operates on page cache, not on page tables as in anon VMA case.
- khugepaged_scan_shmem() finds a range which is suitable for huge
page. The scan is lockless and shouldn't disturb system too much.
- once the candidate for collapse is found, collapse_shmem() attempts
to create a huge page:
+ scan over radix tree, making the range point to new huge page;
+ new huge page is not-uptodate, locked and freezed (refcount
is 0), so nobody can touch them until we say so.
+ we swap in pages during the scan. khugepaged_scan_shmem()
filters out ranges with more than khugepaged_max_ptes_swap
swapped out pages. It's HPAGE_PMD_NR/8 by default.
+ old pages are isolated, unmapped and put to local list in case
to be restored back if collapse failed.
- if collapse succeed, we retract pte page tables from VMAs where huge
pages mapping is possible. The huge page will be mapped as PMD on
next minor fault into the range.
Link: http://lkml.kernel.org/r/1466021202-61880-35-git-send-email-kirill.shutemov@linux.intel.com
Signed-off-by: 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>
116 lines
4.0 KiB
C
116 lines
4.0 KiB
C
#ifndef __SHMEM_FS_H
|
|
#define __SHMEM_FS_H
|
|
|
|
#include <linux/file.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/percpu_counter.h>
|
|
#include <linux/xattr.h>
|
|
|
|
/* inode in-kernel data */
|
|
|
|
struct shmem_inode_info {
|
|
spinlock_t lock;
|
|
unsigned int seals; /* shmem seals */
|
|
unsigned long flags;
|
|
unsigned long alloced; /* data pages alloced to file */
|
|
unsigned long swapped; /* subtotal assigned to swap */
|
|
struct shared_policy policy; /* NUMA memory alloc policy */
|
|
struct list_head swaplist; /* chain of maybes on swap */
|
|
struct simple_xattrs xattrs; /* list of xattrs */
|
|
struct inode vfs_inode;
|
|
};
|
|
|
|
struct shmem_sb_info {
|
|
unsigned long max_blocks; /* How many blocks are allowed */
|
|
struct percpu_counter used_blocks; /* How many are allocated */
|
|
unsigned long max_inodes; /* How many inodes are allowed */
|
|
unsigned long free_inodes; /* How many are left for allocation */
|
|
spinlock_t stat_lock; /* Serialize shmem_sb_info changes */
|
|
umode_t mode; /* Mount mode for root directory */
|
|
unsigned char huge; /* Whether to try for hugepages */
|
|
kuid_t uid; /* Mount uid for root directory */
|
|
kgid_t gid; /* Mount gid for root directory */
|
|
struct mempolicy *mpol; /* default memory policy for mappings */
|
|
};
|
|
|
|
static inline struct shmem_inode_info *SHMEM_I(struct inode *inode)
|
|
{
|
|
return container_of(inode, struct shmem_inode_info, vfs_inode);
|
|
}
|
|
|
|
/*
|
|
* Functions in mm/shmem.c called directly from elsewhere:
|
|
*/
|
|
extern int shmem_init(void);
|
|
extern int shmem_fill_super(struct super_block *sb, void *data, int silent);
|
|
extern struct file *shmem_file_setup(const char *name,
|
|
loff_t size, unsigned long flags);
|
|
extern struct file *shmem_kernel_file_setup(const char *name, loff_t size,
|
|
unsigned long flags);
|
|
extern int shmem_zero_setup(struct vm_area_struct *);
|
|
extern unsigned long shmem_get_unmapped_area(struct file *, unsigned long addr,
|
|
unsigned long len, unsigned long pgoff, unsigned long flags);
|
|
extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
|
|
extern bool shmem_mapping(struct address_space *mapping);
|
|
extern bool shmem_huge_enabled(struct vm_area_struct *vma);
|
|
extern void shmem_unlock_mapping(struct address_space *mapping);
|
|
extern struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp_mask);
|
|
extern void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
|
|
extern int shmem_unuse(swp_entry_t entry, struct page *page);
|
|
|
|
extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
|
|
extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
|
|
pgoff_t start, pgoff_t end);
|
|
|
|
/* Flag allocation requirements to shmem_getpage */
|
|
enum sgp_type {
|
|
SGP_READ, /* don't exceed i_size, don't allocate page */
|
|
SGP_CACHE, /* don't exceed i_size, may allocate page */
|
|
SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */
|
|
SGP_HUGE, /* like SGP_CACHE, huge pages preferred */
|
|
SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
|
|
SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
|
|
};
|
|
|
|
extern int shmem_getpage(struct inode *inode, pgoff_t index,
|
|
struct page **pagep, enum sgp_type sgp);
|
|
|
|
static inline struct page *shmem_read_mapping_page(
|
|
struct address_space *mapping, pgoff_t index)
|
|
{
|
|
return shmem_read_mapping_page_gfp(mapping, index,
|
|
mapping_gfp_mask(mapping));
|
|
}
|
|
|
|
static inline bool shmem_file(struct file *file)
|
|
{
|
|
if (!IS_ENABLED(CONFIG_SHMEM))
|
|
return false;
|
|
if (!file || !file->f_mapping)
|
|
return false;
|
|
return shmem_mapping(file->f_mapping);
|
|
}
|
|
|
|
extern bool shmem_charge(struct inode *inode, long pages);
|
|
extern void shmem_uncharge(struct inode *inode, long pages);
|
|
|
|
#ifdef CONFIG_TMPFS
|
|
|
|
extern int shmem_add_seals(struct file *file, unsigned int seals);
|
|
extern int shmem_get_seals(struct file *file);
|
|
extern long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg);
|
|
|
|
#else
|
|
|
|
static inline long shmem_fcntl(struct file *f, unsigned int c, unsigned long a)
|
|
{
|
|
return -EINVAL;
|
|
}
|
|
|
|
#endif
|
|
|
|
#endif
|