mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-06-04 08:34:01 -04:00
Pull more MM updates from Andrew Morton: - "Eliminate Dying Memory Cgroup" (Qi Zheng and Muchun Song) Address the longstanding "dying memcg problem". A situation wherein a no-longer-used memory control group will hang around for an extended period pointlessly consuming memory - "fix unexpected type conversions and potential overflows" (Qi Zheng) Fix a couple of potential 32-bit/64-bit issues which were identified during review of the "Eliminate Dying Memory Cgroup" series - "kho: history: track previous kernel version and kexec boot count" (Breno Leitao) Use Kexec Handover (KHO) to pass the previous kernel's version string and the number of kexec reboots since the last cold boot to the next kernel, and print it at boot time - "liveupdate: prevent double preservation" (Pasha Tatashin) Teach LUO to avoid managing the same file across different active sessions - "liveupdate: Fix module unloading and unregister API" (Pasha Tatashin) Address an issue with how LUO handles module reference counting and unregistration during module unloading - "zswap pool per-CPU acomp_ctx simplifications" (Kanchana Sridhar) Simplify and clean up the zswap crypto compression handling and improve the lifecycle management of zswap pool's per-CPU acomp_ctx resources - "mm/damon/core: fix damon_call()/damos_walk() vs kdmond exit race" (SeongJae Park) Address unlikely but possible leaks and deadlocks in damon_call() and damon_walk() - "mm/damon/core: validate damos_quota_goal->nid" (SeongJae Park) Fix a couple of root-only wild pointer dereferences - "Docs/admin-guide/mm/damon: warn commit_inputs vs other params race" (SeongJae Park) Update the DAMON documentation to warn operators about potential races which can occur if the commit_inputs parameter is altered at the wrong time - "Minor hmm_test fixes and cleanups" (Alistair Popple) Bugfixes and a cleanup for the HMM kernel selftests - "Modify memfd_luo code" (Chenghao Duan) Cleanups, simplifications and speedups to the memfd_lou code - "mm, kvm: allow uffd support in guest_memfd" (Mike Rapoport) Support for userfaultfd in guest_memfd - "selftests/mm: skip several tests when thp is not available" (Chunyu Hu) Fix several issues in the selftests code which were causing breakage when the tests were run on CONFIG_THP=n kernels - "mm/mprotect: micro-optimization work" (Pedro Falcato) A couple of nice speedups for mprotect() - "MAINTAINERS: update KHO and LIVE UPDATE entries" (Pratyush Yadav) Document upcoming changes in the maintenance of KHO, LUO, memfd_luo, kexec, crash, kdump and probably other kexec-based things - they are being moved out of mm.git and into a new git tree * tag 'mm-stable-2026-04-18-02-14' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (121 commits) MAINTAINERS: add page cache reviewer mm/vmscan: avoid false-positive -Wuninitialized warning MAINTAINERS: update Dave's kdump reviewer email address MAINTAINERS: drop include/linux/liveupdate from LIVE UPDATE MAINTAINERS: drop include/linux/kho/abi/ from KHO MAINTAINERS: update KHO and LIVE UPDATE maintainers MAINTAINERS: update kexec/kdump maintainers entries mm/migrate_device: remove dead migration entry check in migrate_vma_collect_huge_pmd() selftests: mm: skip charge_reserved_hugetlb without killall userfaultfd: allow registration of ranges below mmap_min_addr mm/vmstat: fix vmstat_shepherd double-scheduling vmstat_update mm/hugetlb: fix early boot crash on parameters without '=' separator zram: reject unrecognized type= values in recompress_store() docs: proc: document ProtectionKey in smaps mm/mprotect: special-case small folios when applying permissions mm/mprotect: move softleaf code out of the main function mm: remove '!root_reclaim' checking in should_abort_scan() mm/sparse: fix comment for section map alignment mm/page_io: use sio->len for PSWPIN accounting in sio_read_complete() selftests/mm: transhuge_stress: skip the test when thp not available ...
238 lines
8.2 KiB
C
238 lines
8.2 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>
|
|
#include <linux/fs_parser.h>
|
|
#include <linux/userfaultfd_k.h>
|
|
#include <linux/bits.h>
|
|
|
|
struct swap_iocb;
|
|
|
|
/* inode in-kernel data */
|
|
|
|
#ifdef CONFIG_TMPFS_QUOTA
|
|
#define SHMEM_MAXQUOTAS 2
|
|
#endif
|
|
|
|
/* Suppress pre-accounting of the entire object size. */
|
|
#define SHMEM_F_NORESERVE BIT(0)
|
|
/* Disallow swapping. */
|
|
#define SHMEM_F_LOCKED BIT(1)
|
|
/*
|
|
* Disallow growing, shrinking, or hole punching in the inode. Combined with
|
|
* folio pinning, makes sure the inode's mapping stays fixed.
|
|
*
|
|
* In some ways similar to F_SEAL_GROW | F_SEAL_SHRINK, but can be removed and
|
|
* isn't directly visible to userspace.
|
|
*/
|
|
#define SHMEM_F_MAPPING_FROZEN BIT(2)
|
|
|
|
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 */
|
|
union {
|
|
struct offset_ctx dir_offsets; /* stable directory offsets */
|
|
struct {
|
|
struct list_head shrinklist; /* shrinkable hpage inodes */
|
|
struct list_head swaplist; /* chain of maybes on swap */
|
|
};
|
|
};
|
|
struct timespec64 i_crtime; /* file creation time */
|
|
struct shared_policy policy; /* NUMA memory alloc policy */
|
|
struct simple_xattrs *xattrs; /* list of xattrs */
|
|
pgoff_t fallocend; /* highest fallocate endindex */
|
|
unsigned int fsflags; /* for FS_IOC_[SG]ETFLAGS */
|
|
atomic_t stop_eviction; /* hold when working on inode */
|
|
#ifdef CONFIG_TMPFS_QUOTA
|
|
struct dquot __rcu *i_dquot[MAXQUOTAS];
|
|
#endif
|
|
struct inode vfs_inode;
|
|
};
|
|
|
|
#define SHMEM_FL_USER_VISIBLE (FS_FL_USER_VISIBLE | FS_CASEFOLD_FL)
|
|
#define SHMEM_FL_USER_MODIFIABLE \
|
|
(FS_IMMUTABLE_FL | FS_APPEND_FL | FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL)
|
|
#define SHMEM_FL_INHERITED (FS_NODUMP_FL | FS_NOATIME_FL | FS_CASEFOLD_FL)
|
|
|
|
struct shmem_quota_limits {
|
|
qsize_t usrquota_bhardlimit; /* Default user quota block hard limit */
|
|
qsize_t usrquota_ihardlimit; /* Default user quota inode hard limit */
|
|
qsize_t grpquota_bhardlimit; /* Default group quota block hard limit */
|
|
qsize_t grpquota_ihardlimit; /* Default group quota inode hard limit */
|
|
};
|
|
|
|
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_ispace; /* How much ispace left for allocation */
|
|
raw_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 */
|
|
bool full_inums; /* If i_ino should be uint or ino_t */
|
|
bool noswap; /* ignores VM reclaim / swap requests */
|
|
ino_t next_ino; /* The next per-sb inode number to use */
|
|
ino_t __percpu *ino_batch; /* The next per-cpu inode number to use */
|
|
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 */
|
|
struct shmem_quota_limits qlimits; /* Default quota limits */
|
|
};
|
|
|
|
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 const struct fs_parameter_spec shmem_fs_parameters[];
|
|
extern void shmem_init(void);
|
|
extern int shmem_init_fs_context(struct fs_context *fc);
|
|
struct file *shmem_file_setup(const char *name, loff_t size, vma_flags_t flags);
|
|
struct file *shmem_kernel_file_setup(const char *name, loff_t size, vma_flags_t vma_flags);
|
|
extern struct file *shmem_file_setup_with_mnt(struct vfsmount *mnt,
|
|
const char *name, loff_t size, vma_flags_t flags);
|
|
int shmem_zero_setup(struct vm_area_struct *vma);
|
|
int shmem_zero_setup_desc(struct vm_area_desc *desc);
|
|
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 ucounts *ucounts);
|
|
#ifdef CONFIG_SHMEM
|
|
bool shmem_mapping(const struct address_space *mapping);
|
|
#else
|
|
static inline bool shmem_mapping(const struct address_space *mapping)
|
|
{
|
|
return false;
|
|
}
|
|
#endif /* CONFIG_SHMEM */
|
|
void shmem_unlock_mapping(struct address_space *mapping);
|
|
struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp_mask);
|
|
int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
|
|
struct list_head *folio_list);
|
|
void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end);
|
|
int shmem_unuse(unsigned int type);
|
|
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
unsigned long shmem_allowable_huge_orders(struct inode *inode,
|
|
struct vm_area_struct *vma, pgoff_t index,
|
|
loff_t write_end, bool shmem_huge_force);
|
|
bool shmem_hpage_pmd_enabled(void);
|
|
#else
|
|
static inline unsigned long shmem_allowable_huge_orders(struct inode *inode,
|
|
struct vm_area_struct *vma, pgoff_t index,
|
|
loff_t write_end, bool shmem_huge_force)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline bool shmem_hpage_pmd_enabled(void)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SHMEM
|
|
extern unsigned long shmem_swap_usage(struct vm_area_struct *vma);
|
|
extern void shmem_uncharge(struct inode *inode, long pages);
|
|
#else
|
|
static inline unsigned long shmem_swap_usage(struct vm_area_struct *vma)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static inline void shmem_uncharge(struct inode *inode, long pages)
|
|
{
|
|
}
|
|
#endif
|
|
extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
|
|
pgoff_t start, pgoff_t end);
|
|
|
|
/* Flag allocation requirements to shmem_get_folio */
|
|
enum sgp_type {
|
|
SGP_READ, /* don't exceed i_size, don't allocate page */
|
|
SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */
|
|
SGP_CACHE, /* don't exceed i_size, may allocate page */
|
|
SGP_WRITE, /* may exceed i_size, may allocate !Uptodate page */
|
|
SGP_FALLOC, /* like SGP_WRITE, but make existing page Uptodate */
|
|
};
|
|
|
|
int shmem_get_folio(struct inode *inode, pgoff_t index, loff_t write_end,
|
|
struct folio **foliop, enum sgp_type sgp);
|
|
struct folio *shmem_read_folio_gfp(struct address_space *mapping,
|
|
pgoff_t index, gfp_t gfp);
|
|
|
|
static inline struct folio *shmem_read_folio(struct address_space *mapping,
|
|
pgoff_t index)
|
|
{
|
|
return shmem_read_folio_gfp(mapping, index, mapping_gfp_mask(mapping));
|
|
}
|
|
|
|
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);
|
|
}
|
|
|
|
/* Must be called with inode lock taken exclusive. */
|
|
static inline void shmem_freeze(struct inode *inode, bool freeze)
|
|
{
|
|
if (freeze)
|
|
SHMEM_I(inode)->flags |= SHMEM_F_MAPPING_FROZEN;
|
|
else
|
|
SHMEM_I(inode)->flags &= ~SHMEM_F_MAPPING_FROZEN;
|
|
}
|
|
|
|
/*
|
|
* If fallocate(FALLOC_FL_KEEP_SIZE) has been used, there may be pages
|
|
* beyond i_size's notion of EOF, which fallocate has committed to reserving:
|
|
* which split_huge_page() must therefore not delete. This use of a single
|
|
* "fallocend" per inode errs on the side of not deleting a reservation when
|
|
* in doubt: there are plenty of cases when it preserves unreserved pages.
|
|
*/
|
|
static inline pgoff_t shmem_fallocend(struct inode *inode, pgoff_t eof)
|
|
{
|
|
return max(eof, SHMEM_I(inode)->fallocend);
|
|
}
|
|
|
|
extern bool shmem_charge(struct inode *inode, long pages);
|
|
|
|
/*
|
|
* Used space is stored as unsigned 64-bit value in bytes but
|
|
* quota core supports only signed 64-bit values so use that
|
|
* as a limit
|
|
*/
|
|
#define SHMEM_QUOTA_MAX_SPC_LIMIT 0x7fffffffffffffffLL /* 2^63-1 */
|
|
#define SHMEM_QUOTA_MAX_INO_LIMIT 0x7fffffffffffffffLL
|
|
|
|
#ifdef CONFIG_TMPFS_QUOTA
|
|
extern const struct dquot_operations shmem_quota_operations;
|
|
extern struct quota_format_type shmem_quota_format;
|
|
#endif /* CONFIG_TMPFS_QUOTA */
|
|
|
|
#endif
|