mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 01:10:04 +00:00
![Hugh Dickins](/assets/img/avatar_default.png)
The igrab() in shmem_unuse() looks good, but we forgot that it gives no protection against concurrent unmounting: a point made by Konstantin Khlebnikov eight years ago, and then fixed in 2.6.39 by778dd893ae
("tmpfs: fix race between umount and swapoff"). The current 5.1-rc swapoff is liable to hit "VFS: Busy inodes after unmount of tmpfs. Self-destruct in 5 seconds. Have a nice day..." followed by GPF. Once again, give up on using igrab(); but don't go back to making such heavy-handed use of shmem_swaplist_mutex as last time: that would spoil the new design, and I expect could deadlock inside shmem_swapin_page(). Instead, shmem_unuse() just raise a "stop_eviction" count in the shmem- specific inode, and shmem_evict_inode() wait for that to go down to 0. Call it "stop_eviction" rather than "swapoff_busy" because it can be put to use for others later (huge tmpfs patches expect to use it). That simplifies shmem_unuse(), protecting it from both unlink and unmount; and in practice lets it locate all the swap in its first try. But do not rely on that: there's still a theoretical case, when shmem_writepage() might have been preempted after its get_swap_page(), before making the swap entry visible to swapoff. [hughd@google.com: remove incorrect list_del()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904091133570.1898@eggly.anvils Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081259400.1523@eggly.anvils Fixes:b56a2d8af9
("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins <hughd@google.com> Cc: "Alex Xu (Hello71)" <alex_y_xu@yahoo.ca> Cc: Huang Ying <ying.huang@intel.com> Cc: Kelley Nielsen <kelleynnn@gmail.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Cc: Rik van Riel <riel@surriel.com> Cc: Vineeth Pillai <vpillai@digitalocean.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
141 lines
5 KiB
C
141 lines
5 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#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 list_head shrinklist; /* shrinkable hpage inodes */
|
|
struct list_head swaplist; /* chain of maybes on swap */
|
|
struct shared_policy policy; /* NUMA memory alloc policy */
|
|
struct simple_xattrs xattrs; /* list of xattrs */
|
|
atomic_t stop_eviction; /* hold when working on inode */
|
|
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 */
|
|
spinlock_t shrinklist_lock; /* Protects shrinklist */
|
|
struct list_head shrinklist; /* List of shinkable inodes */
|
|
unsigned long shrinklist_len; /* Length of shrinklist */
|
|
};
|
|
|
|
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 struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt,
|
|
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);
|
|
#ifdef CONFIG_SHMEM
|
|
extern bool shmem_mapping(struct address_space *mapping);
|
|
#else
|
|
static inline bool shmem_mapping(struct address_space *mapping)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* CONFIG_SHMEM */
|
|
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(unsigned int type, bool frontswap,
|
|
unsigned long *fs_pages_to_unuse);
|
|
|
|
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_TRANSPARENT_HUGE_PAGECACHE
|
|
extern bool shmem_huge_enabled(struct vm_area_struct *vma);
|
|
#else
|
|
static inline bool shmem_huge_enabled(struct vm_area_struct *vma)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SHMEM
|
|
extern int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm, pmd_t *dst_pmd,
|
|
struct vm_area_struct *dst_vma,
|
|
unsigned long dst_addr,
|
|
unsigned long src_addr,
|
|
struct page **pagep);
|
|
extern int shmem_mfill_zeropage_pte(struct mm_struct *dst_mm,
|
|
pmd_t *dst_pmd,
|
|
struct vm_area_struct *dst_vma,
|
|
unsigned long dst_addr);
|
|
#else
|
|
#define shmem_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
|
|
src_addr, pagep) ({ BUG(); 0; })
|
|
#define shmem_mfill_zeropage_pte(dst_mm, dst_pmd, dst_vma, \
|
|
dst_addr) ({ BUG(); 0; })
|
|
#endif
|
|
|
|
#endif
|