blob: 5a77acf6ac6a621dc7b5e7b46402b2b714b45bea [file] [log] [blame]
/*
* Resizable virtual memory filesystem for Linux.
*
* Copyright (C) 2000 Linus Torvalds.
* 2000 Transmeta Corp.
* 2000-2001 Christoph Rohland
* 2000-2001 SAP AG
* 2002 Red Hat Inc.
* Copyright (C) 2002-2011 Hugh Dickins.
* Copyright (C) 2011 Google Inc.
* Copyright (C) 2002-2005 VERITAS Software Corporation.
* Copyright (C) 2004 Andi Kleen, SuSE Labs
*
* Extended attribute support for tmpfs:
* Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
* Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
*
* tiny-shmem:
* Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com>
*
* This file is released under the GPL.
*/
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/vfs.h>
#include <linux/mount.h>
#include <linux/ramfs.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/fileattr.h>
#include <linux/mm.h>
#include <linux/random.h>
#include <linux/sched/signal.h>
#include <linux/export.h>
#include <linux/shmem_fs.h>
#include <linux/swap.h>
#include <linux/uio.h>
#include <linux/hugetlb.h>
#include <linux/fs_parser.h>
#include <linux/swapfile.h>
#include <linux/iversion.h>
#include "swap.h"
static struct vfsmount *shm_mnt __ro_after_init;
#ifdef CONFIG_SHMEM
/*
* This virtual memory filesystem is heavily based on the ramfs. It
* extends ramfs by the ability to use swap and honor resource limits
* which makes it a completely usable filesystem.
*/
#include <linux/xattr.h>
#include <linux/exportfs.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/mman.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/pagevec.h>
#include <linux/percpu_counter.h>
#include <linux/falloc.h>
#include <linux/splice.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
#include <linux/seq_file.h>
#include <linux/magic.h>
#include <linux/syscalls.h>
#include <linux/fcntl.h>
#include <uapi/linux/memfd.h>
#include <linux/rmap.h>
#include <linux/uuid.h>
#include <linux/quotaops.h>
#include <linux/rcupdate_wait.h>
#include <linux/uaccess.h>
#include "internal.h"
#define BLOCKS_PER_PAGE (PAGE_SIZE/512)
#define VM_ACCT(size) (PAGE_ALIGN(size) >> PAGE_SHIFT)
/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20
/* Pretend that one inode + its dentry occupy this much memory */
#define BOGO_INODE_SIZE 1024
/* Symlink up to this size is kmalloc'ed instead of using a swappable page */
#define SHORT_SYMLINK_LEN 128
/*
* shmem_fallocate communicates with shmem_fault or shmem_writepage via
* inode->i_private (with i_rwsem making sure that it has only one user at
* a time): we would prefer not to enlarge the shmem inode just for that.
*/
struct shmem_falloc {
wait_queue_head_t *waitq; /* faults into hole wait for punch to end */
pgoff_t start; /* start of range currently being fallocated */
pgoff_t next; /* the next page offset to be fallocated */
pgoff_t nr_falloced; /* how many new pages have been fallocated */
pgoff_t nr_unswapped; /* how often writepage refused to swap out */
};
struct shmem_options {
unsigned long long blocks;
unsigned long long inodes;
struct mempolicy *mpol;
kuid_t uid;
kgid_t gid;
umode_t mode;
bool full_inums;
int huge;
int seen;
bool noswap;
unsigned short quota_types;
struct shmem_quota_limits qlimits;
#define SHMEM_SEEN_BLOCKS 1
#define SHMEM_SEEN_INODES 2
#define SHMEM_SEEN_HUGE 4
#define SHMEM_SEEN_INUMS 8
#define SHMEM_SEEN_NOSWAP 16
#define SHMEM_SEEN_QUOTA 32
};
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static unsigned long huge_shmem_orders_always __read_mostly;
static unsigned long huge_shmem_orders_madvise __read_mostly;
static unsigned long huge_shmem_orders_inherit __read_mostly;
static unsigned long huge_shmem_orders_within_size __read_mostly;
#endif
#ifdef CONFIG_TMPFS
static unsigned long shmem_default_max_blocks(void)
{
return totalram_pages() / 2;
}
static unsigned long shmem_default_max_inodes(void)
{
unsigned long nr_pages = totalram_pages();
return min3(nr_pages - totalhigh_pages(), nr_pages / 2,
ULONG_MAX / BOGO_INODE_SIZE);
}
#endif
static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
struct folio **foliop, enum sgp_type sgp, gfp_t gfp,
struct mm_struct *fault_mm, vm_fault_t *fault_type);
static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
{
return sb->s_fs_info;
}
/*
* shmem_file_setup pre-accounts the whole fixed size of a VM object,
* for shared memory and for shared anonymous (/dev/zero) mappings
* (unless MAP_NORESERVE and sysctl_overcommit_memory <= 1),
* consistent with the pre-accounting of private mappings ...
*/
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
return (flags & VM_NORESERVE) ?
0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size));
}
static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
if (!(flags & VM_NORESERVE))
vm_unacct_memory(VM_ACCT(size));
}
static inline int shmem_reacct_size(unsigned long flags,
loff_t oldsize, loff_t newsize)
{
if (!(flags & VM_NORESERVE)) {
if (VM_ACCT(newsize) > VM_ACCT(oldsize))
return security_vm_enough_memory_mm(current->mm,
VM_ACCT(newsize) - VM_ACCT(oldsize));
else if (VM_ACCT(newsize) < VM_ACCT(oldsize))
vm_unacct_memory(VM_ACCT(oldsize) - VM_ACCT(newsize));
}
return 0;
}
/*
* ... whereas tmpfs objects are accounted incrementally as
* pages are allocated, in order to allow large sparse files.
* shmem_get_folio reports shmem_acct_blocks failure as -ENOSPC not -ENOMEM,
* so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
*/
static inline int shmem_acct_blocks(unsigned long flags, long pages)
{
if (!(flags & VM_NORESERVE))
return 0;
return security_vm_enough_memory_mm(current->mm,
pages * VM_ACCT(PAGE_SIZE));
}
static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
if (flags & VM_NORESERVE)
vm_unacct_memory(pages * VM_ACCT(PAGE_SIZE));
}
static int shmem_inode_acct_blocks(struct inode *inode, long pages)
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int err = -ENOSPC;
if (shmem_acct_blocks(info->flags, pages))
return err;
might_sleep(); /* when quotas */
if (sbinfo->max_blocks) {
if (!percpu_counter_limited_add(&sbinfo->used_blocks,
sbinfo->max_blocks, pages))
goto unacct;
err = dquot_alloc_block_nodirty(inode, pages);
if (err) {
percpu_counter_sub(&sbinfo->used_blocks, pages);
goto unacct;
}
} else {
err = dquot_alloc_block_nodirty(inode, pages);
if (err)
goto unacct;
}
return 0;
unacct:
shmem_unacct_blocks(info->flags, pages);
return err;
}
static void shmem_inode_unacct_blocks(struct inode *inode, long pages)
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
might_sleep(); /* when quotas */
dquot_free_block_nodirty(inode, pages);
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks, pages);
shmem_unacct_blocks(info->flags, pages);
}
static const struct super_operations shmem_ops;
static const struct address_space_operations shmem_aops;
static const struct file_operations shmem_file_operations;
static const struct inode_operations shmem_inode_operations;
static const struct inode_operations shmem_dir_inode_operations;
static const struct inode_operations shmem_special_inode_operations;
static const struct vm_operations_struct shmem_vm_ops;
static const struct vm_operations_struct shmem_anon_vm_ops;
static struct file_system_type shmem_fs_type;
bool shmem_mapping(struct address_space *mapping)
{
return mapping->a_ops == &shmem_aops;
}
EXPORT_SYMBOL_GPL(shmem_mapping);
bool vma_is_anon_shmem(struct vm_area_struct *vma)
{
return vma->vm_ops == &shmem_anon_vm_ops;
}
bool vma_is_shmem(struct vm_area_struct *vma)
{
return vma_is_anon_shmem(vma) || vma->vm_ops == &shmem_vm_ops;
}
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
#ifdef CONFIG_TMPFS_QUOTA
static int shmem_enable_quotas(struct super_block *sb,
unsigned short quota_types)
{
int type, err = 0;
sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NOLIST_DIRTY;
for (type = 0; type < SHMEM_MAXQUOTAS; type++) {
if (!(quota_types & (1 << type)))
continue;
err = dquot_load_quota_sb(sb, type, QFMT_SHMEM,
DQUOT_USAGE_ENABLED |
DQUOT_LIMITS_ENABLED);
if (err)
goto out_err;
}
return 0;
out_err:
pr_warn("tmpfs: failed to enable quota tracking (type=%d, err=%d)\n",
type, err);
for (type--; type >= 0; type--)
dquot_quota_off(sb, type);
return err;
}
static void shmem_disable_quotas(struct super_block *sb)
{
int type;
for (type = 0; type < SHMEM_MAXQUOTAS; type++)
dquot_quota_off(sb, type);
}
static struct dquot __rcu **shmem_get_dquots(struct inode *inode)
{
return SHMEM_I(inode)->i_dquot;
}
#endif /* CONFIG_TMPFS_QUOTA */
/*
* shmem_reserve_inode() performs bookkeeping to reserve a shmem inode, and
* produces a novel ino for the newly allocated inode.
*
* It may also be called when making a hard link to permit the space needed by
* each dentry. However, in that case, no new inode number is needed since that
* internally draws from another pool of inode numbers (currently global
* get_next_ino()). This case is indicated by passing NULL as inop.
*/
#define SHMEM_INO_BATCH 1024
static int shmem_reserve_inode(struct super_block *sb, ino_t *inop)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
ino_t ino;
if (!(sb->s_flags & SB_KERNMOUNT)) {
raw_spin_lock(&sbinfo->stat_lock);
if (sbinfo->max_inodes) {
if (sbinfo->free_ispace < BOGO_INODE_SIZE) {
raw_spin_unlock(&sbinfo->stat_lock);
return -ENOSPC;
}
sbinfo->free_ispace -= BOGO_INODE_SIZE;
}
if (inop) {
ino = sbinfo->next_ino++;
if (unlikely(is_zero_ino(ino)))
ino = sbinfo->next_ino++;
if (unlikely(!sbinfo->full_inums &&
ino > UINT_MAX)) {
/*
* Emulate get_next_ino uint wraparound for
* compatibility
*/
if (IS_ENABLED(CONFIG_64BIT))
pr_warn("%s: inode number overflow on device %d, consider using inode64 mount option\n",
__func__, MINOR(sb->s_dev));
sbinfo->next_ino = 1;
ino = sbinfo->next_ino++;
}
*inop = ino;
}
raw_spin_unlock(&sbinfo->stat_lock);
} else if (inop) {
/*
* __shmem_file_setup, one of our callers, is lock-free: it
* doesn't hold stat_lock in shmem_reserve_inode since
* max_inodes is always 0, and is called from potentially
* unknown contexts. As such, use a per-cpu batched allocator
* which doesn't require the per-sb stat_lock unless we are at
* the batch boundary.
*
* We don't need to worry about inode{32,64} since SB_KERNMOUNT
* shmem mounts are not exposed to userspace, so we don't need
* to worry about things like glibc compatibility.
*/
ino_t *next_ino;
next_ino = per_cpu_ptr(sbinfo->ino_batch, get_cpu());
ino = *next_ino;
if (unlikely(ino % SHMEM_INO_BATCH == 0)) {
raw_spin_lock(&sbinfo->stat_lock);
ino = sbinfo->next_ino;
sbinfo->next_ino += SHMEM_INO_BATCH;
raw_spin_unlock(&sbinfo->stat_lock);
if (unlikely(is_zero_ino(ino)))
ino++;
}
*inop = ino;
*next_ino = ++ino;
put_cpu();
}
return 0;
}
static void shmem_free_inode(struct super_block *sb, size_t freed_ispace)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (sbinfo->max_inodes) {
raw_spin_lock(&sbinfo->stat_lock);
sbinfo->free_ispace += BOGO_INODE_SIZE + freed_ispace;
raw_spin_unlock(&sbinfo->stat_lock);
}
}
/**
* shmem_recalc_inode - recalculate the block usage of an inode
* @inode: inode to recalc
* @alloced: the change in number of pages allocated to inode
* @swapped: the change in number of pages swapped from inode
*
* We have to calculate the free blocks since the mm can drop
* undirtied hole pages behind our back.
*
* But normally info->alloced == inode->i_mapping->nrpages + info->swapped
* So mm freed is info->alloced - (inode->i_mapping->nrpages + info->swapped)
*/
static void shmem_recalc_inode(struct inode *inode, long alloced, long swapped)
{
struct shmem_inode_info *info = SHMEM_I(inode);
long freed;
spin_lock(&info->lock);
info->alloced += alloced;
info->swapped += swapped;
freed = info->alloced - info->swapped -
READ_ONCE(inode->i_mapping->nrpages);
/*
* Special case: whereas normally shmem_recalc_inode() is called
* after i_mapping->nrpages has already been adjusted (up or down),
* shmem_writepage() has to raise swapped before nrpages is lowered -
* to stop a racing shmem_recalc_inode() from thinking that a page has
* been freed. Compensate here, to avoid the need for a followup call.
*/
if (swapped > 0)
freed += swapped;
if (freed > 0)
info->alloced -= freed;
spin_unlock(&info->lock);
/* The quota case may block */
if (freed > 0)
shmem_inode_unacct_blocks(inode, freed);
}
bool shmem_charge(struct inode *inode, long pages)
{
struct address_space *mapping = inode->i_mapping;
if (shmem_inode_acct_blocks(inode, pages))
return false;
/* nrpages adjustment first, then shmem_recalc_inode() when balanced */
xa_lock_irq(&mapping->i_pages);
mapping->nrpages += pages;
xa_unlock_irq(&mapping->i_pages);
shmem_recalc_inode(inode, pages, 0);
return true;
}
void shmem_uncharge(struct inode *inode, long pages)
{
/* pages argument is currently unused: keep it to help debugging */
/* nrpages adjustment done by __filemap_remove_folio() or caller */
shmem_recalc_inode(inode, 0, 0);
}
/*
* Replace item expected in xarray by a new item, while holding xa_lock.
*/
static int shmem_replace_entry(struct address_space *mapping,
pgoff_t index, void *expected, void *replacement)
{
XA_STATE(xas, &mapping->i_pages, index);
void *item;
VM_BUG_ON(!expected);
VM_BUG_ON(!replacement);
item = xas_load(&xas);
if (item != expected)
return -ENOENT;
xas_store(&xas, replacement);
return 0;
}
/*
* Sometimes, before we decide whether to proceed or to fail, we must check
* that an entry was not already brought back from swap by a racing thread.
*
* Checking page is not enough: by the time a SwapCache page is locked, it
* might be reused, and again be SwapCache, using the same swap as before.
*/
static bool shmem_confirm_swap(struct address_space *mapping,
pgoff_t index, swp_entry_t swap)
{
return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap);
}
/*
* Definitions for "huge tmpfs": tmpfs mounted with the huge= option
*
* SHMEM_HUGE_NEVER:
* disables huge pages for the mount;
* SHMEM_HUGE_ALWAYS:
* enables huge pages for the mount;
* SHMEM_HUGE_WITHIN_SIZE:
* only allocate huge pages if the page will be fully within i_size,
* also respect fadvise()/madvise() hints;
* SHMEM_HUGE_ADVISE:
* only allocate huge pages if requested with fadvise()/madvise();
*/
#define SHMEM_HUGE_NEVER 0
#define SHMEM_HUGE_ALWAYS 1
#define SHMEM_HUGE_WITHIN_SIZE 2
#define SHMEM_HUGE_ADVISE 3
/*
* Special values.
* Only can be set via /sys/kernel/mm/transparent_hugepage/shmem_enabled:
*
* SHMEM_HUGE_DENY:
* disables huge on shm_mnt and all mounts, for emergency use;
* SHMEM_HUGE_FORCE:
* enables huge on shm_mnt and all mounts, w/o needing option, for testing;
*
*/
#define SHMEM_HUGE_DENY (-1)
#define SHMEM_HUGE_FORCE (-2)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
/* ifdef here to avoid bloating shmem.o when not necessary */
static int shmem_huge __read_mostly = SHMEM_HUGE_NEVER;
static bool __shmem_is_huge(struct inode *inode, pgoff_t index,
bool shmem_huge_force, struct mm_struct *mm,
unsigned long vm_flags)
{
loff_t i_size;
if (!S_ISREG(inode->i_mode))
return false;
if (mm && ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &mm->flags)))
return false;
if (shmem_huge == SHMEM_HUGE_DENY)
return false;
if (shmem_huge_force || shmem_huge == SHMEM_HUGE_FORCE)
return true;
switch (SHMEM_SB(inode->i_sb)->huge) {
case SHMEM_HUGE_ALWAYS:
return true;
case SHMEM_HUGE_WITHIN_SIZE:
index = round_up(index + 1, HPAGE_PMD_NR);
i_size = round_up(i_size_read(inode), PAGE_SIZE);
if (i_size >> PAGE_SHIFT >= index)
return true;
fallthrough;
case SHMEM_HUGE_ADVISE:
if (mm && (vm_flags & VM_HUGEPAGE))
return true;
fallthrough;
default:
return false;
}
}
bool shmem_is_huge(struct inode *inode, pgoff_t index,
bool shmem_huge_force, struct mm_struct *mm,
unsigned long vm_flags)
{
if (HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER)
return false;
return __shmem_is_huge(inode, index, shmem_huge_force, mm, vm_flags);
}
#if defined(CONFIG_SYSFS)
static int shmem_parse_huge(const char *str)
{
if (!strcmp(str, "never"))
return SHMEM_HUGE_NEVER;
if (!strcmp(str, "always"))
return SHMEM_HUGE_ALWAYS;
if (!strcmp(str, "within_size"))
return SHMEM_HUGE_WITHIN_SIZE;
if (!strcmp(str, "advise"))
return SHMEM_HUGE_ADVISE;
if (!strcmp(str, "deny"))
return SHMEM_HUGE_DENY;
if (!strcmp(str, "force"))
return SHMEM_HUGE_FORCE;
return -EINVAL;
}
#endif
#if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS)
static const char *shmem_format_huge(int huge)
{
switch (huge) {
case SHMEM_HUGE_NEVER:
return "never";
case SHMEM_HUGE_ALWAYS:
return "always";
case SHMEM_HUGE_WITHIN_SIZE:
return "within_size";
case SHMEM_HUGE_ADVISE:
return "advise";
case SHMEM_HUGE_DENY:
return "deny";
case SHMEM_HUGE_FORCE:
return "force";
default:
VM_BUG_ON(1);
return "bad_val";
}
}
#endif
static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shrink_control *sc, unsigned long nr_to_split)
{
LIST_HEAD(list), *pos, *next;
LIST_HEAD(to_remove);
struct inode *inode;
struct shmem_inode_info *info;
struct folio *folio;
unsigned long batch = sc ? sc->nr_to_scan : 128;
int split = 0;
if (list_empty(&sbinfo->shrinklist))
return SHRINK_STOP;
spin_lock(&sbinfo->shrinklist_lock);
list_for_each_safe(pos, next, &sbinfo->shrinklist) {
info = list_entry(pos, struct shmem_inode_info, shrinklist);
/* pin the inode */
inode = igrab(&info->vfs_inode);
/* inode is about to be evicted */
if (!inode) {
list_del_init(&info->shrinklist);
goto next;
}
/* Check if there's anything to gain */
if (round_up(inode->i_size, PAGE_SIZE) ==
round_up(inode->i_size, HPAGE_PMD_SIZE)) {
list_move(&info->shrinklist, &to_remove);
goto next;
}
list_move(&info->shrinklist, &list);
next:
sbinfo->shrinklist_len--;
if (!--batch)
break;
}
spin_unlock(&sbinfo->shrinklist_lock);
list_for_each_safe(pos, next, &to_remove) {
info = list_entry(pos, struct shmem_inode_info, shrinklist);
inode = &info->vfs_inode;
list_del_init(&info->shrinklist);
iput(inode);
}
list_for_each_safe(pos, next, &list) {
int ret;
pgoff_t index;
info = list_entry(pos, struct shmem_inode_info, shrinklist);
inode = &info->vfs_inode;
if (nr_to_split && split >= nr_to_split)
goto move_back;
index = (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT;
folio = filemap_get_folio(inode->i_mapping, index);
if (IS_ERR(folio))
goto drop;
/* No huge page at the end of the file: nothing to split */
if (!folio_test_large(folio)) {
folio_put(folio);
goto drop;
}
/*
* Move the inode on the list back to shrinklist if we failed
* to lock the page at this time.
*
* Waiting for the lock may lead to deadlock in the
* reclaim path.
*/
if (!folio_trylock(folio)) {
folio_put(folio);
goto move_back;
}
ret = split_folio(folio);
folio_unlock(folio);
folio_put(folio);
/* If split failed move the inode on the list back to shrinklist */
if (ret)
goto move_back;
split++;
drop:
list_del_init(&info->shrinklist);
goto put;
move_back:
/*
* Make sure the inode is either on the global list or deleted
* from any local list before iput() since it could be deleted
* in another thread once we put the inode (then the local list
* is corrupted).
*/
spin_lock(&sbinfo->shrinklist_lock);
list_move(&info->shrinklist, &sbinfo->shrinklist);
sbinfo->shrinklist_len++;
spin_unlock(&sbinfo->shrinklist_lock);
put:
iput(inode);
}
return split;
}
static long shmem_unused_huge_scan(struct super_block *sb,
struct shrink_control *sc)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (!READ_ONCE(sbinfo->shrinklist_len))
return SHRINK_STOP;
return shmem_unused_huge_shrink(sbinfo, sc, 0);
}
static long shmem_unused_huge_count(struct super_block *sb,
struct shrink_control *sc)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
return READ_ONCE(sbinfo->shrinklist_len);
}
#else /* !CONFIG_TRANSPARENT_HUGEPAGE */
#define shmem_huge SHMEM_HUGE_DENY
static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
struct shrink_control *sc, unsigned long nr_to_split)
{
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
* Somewhat like filemap_add_folio, but error if expected item has gone.
*/
static int shmem_add_to_page_cache(struct folio *folio,
struct address_space *mapping,
pgoff_t index, void *expected, gfp_t gfp)
{
XA_STATE_ORDER(xas, &mapping->i_pages, index, folio_order(folio));
long nr = folio_nr_pages(folio);
VM_BUG_ON_FOLIO(index != round_down(index, nr), folio);
VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
VM_BUG_ON_FOLIO(!folio_test_swapbacked(folio), folio);
VM_BUG_ON(expected && folio_test_large(folio));
folio_ref_add(folio, nr);
folio->mapping = mapping;
folio->index = index;
gfp &= GFP_RECLAIM_MASK;
folio_throttle_swaprate(folio, gfp);
do {
xas_lock_irq(&xas);
if (expected != xas_find_conflict(&xas)) {
xas_set_err(&xas, -EEXIST);
goto unlock;
}
if (expected && xas_find_conflict(&xas)) {
xas_set_err(&xas, -EEXIST);
goto unlock;
}
xas_store(&xas, folio);
if (xas_error(&xas))
goto unlock;
if (folio_test_pmd_mappable(folio))
__lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, nr);
__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, nr);
__lruvec_stat_mod_folio(folio, NR_SHMEM, nr);
mapping->nrpages += nr;
unlock:
xas_unlock_irq(&xas);
} while (xas_nomem(&xas, gfp));
if (xas_error(&xas)) {
folio->mapping = NULL;
folio_ref_sub(folio, nr);
return xas_error(&xas);
}
return 0;
}
/*
* Somewhat like filemap_remove_folio, but substitutes swap for @folio.
*/
static void shmem_delete_from_page_cache(struct folio *folio, void *radswap)
{
struct address_space *mapping = folio->mapping;
long nr = folio_nr_pages(folio);
int error;
xa_lock_irq(&mapping->i_pages);
error = shmem_replace_entry(mapping, folio->index, folio, radswap);
folio->mapping = NULL;
mapping->nrpages -= nr;
__lruvec_stat_mod_folio(folio, NR_FILE_PAGES, -nr);
__lruvec_stat_mod_folio(folio, NR_SHMEM, -nr);
xa_unlock_irq(&mapping->i_pages);
folio_put(folio);
BUG_ON(error);
}
/*
* Remove swap entry from page cache, free the swap and its page cache.
*/
static int shmem_free_swap(struct address_space *mapping,
pgoff_t index, void *radswap)
{
void *old;
old = xa_cmpxchg_irq(&mapping->i_pages, index, radswap, NULL, 0);
if (old != radswap)
return -ENOENT;
free_swap_and_cache(radix_to_swp_entry(radswap));
return 0;
}
/*
* Determine (in bytes) how many of the shmem object's pages mapped by the
* given offsets are swapped out.
*
* This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
* as long as the inode doesn't go away and racy results are not a problem.
*/
unsigned long shmem_partial_swap_usage(struct address_space *mapping,
pgoff_t start, pgoff_t end)
{
XA_STATE(xas, &mapping->i_pages, start);
struct page *page;
unsigned long swapped = 0;
unsigned long max = end - 1;
rcu_read_lock();
xas_for_each(&xas, page, max) {
if (xas_retry(&xas, page))
continue;
if (xa_is_value(page))
swapped++;
if (xas.xa_index == max)
break;
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
}
rcu_read_unlock();
return swapped << PAGE_SHIFT;
}
/*
* Determine (in bytes) how many of the shmem object's pages mapped by the
* given vma is swapped out.
*
* This is safe to call without i_rwsem or the i_pages lock thanks to RCU,
* as long as the inode doesn't go away and racy results are not a problem.
*/
unsigned long shmem_swap_usage(struct vm_area_struct *vma)
{
struct inode *inode = file_inode(vma->vm_file);
struct shmem_inode_info *info = SHMEM_I(inode);
struct address_space *mapping = inode->i_mapping;
unsigned long swapped;
/* Be careful as we don't hold info->lock */
swapped = READ_ONCE(info->swapped);
/*
* The easier cases are when the shmem object has nothing in swap, or
* the vma maps it whole. Then we can simply use the stats that we
* already track.
*/
if (!swapped)
return 0;
if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size)
return swapped << PAGE_SHIFT;
/* Here comes the more involved part */
return shmem_partial_swap_usage(mapping, vma->vm_pgoff,
vma->vm_pgoff + vma_pages(vma));
}
/*
* SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
*/
void shmem_unlock_mapping(struct address_space *mapping)
{
struct folio_batch fbatch;
pgoff_t index = 0;
folio_batch_init(&fbatch);
/*
* Minor point, but we might as well stop if someone else SHM_LOCKs it.
*/
while (!mapping_unevictable(mapping) &&
filemap_get_folios(mapping, &index, ~0UL, &fbatch)) {
check_move_unevictable_folios(&fbatch);
folio_batch_release(&fbatch);
cond_resched();
}
}
static struct folio *shmem_get_partial_folio(struct inode *inode, pgoff_t index)
{
struct folio *folio;
/*
* At first avoid shmem_get_folio(,,,SGP_READ): that fails
* beyond i_size, and reports fallocated folios as holes.
*/
folio = filemap_get_entry(inode->i_mapping, index);
if (!folio)
return folio;
if (!xa_is_value(folio)) {
folio_lock(folio);
if (folio->mapping == inode->i_mapping)
return folio;
/* The folio has been swapped out */
folio_unlock(folio);
folio_put(folio);
}
/*
* But read a folio back from swap if any of it is within i_size
* (although in some cases this is just a waste of time).
*/
folio = NULL;
shmem_get_folio(inode, index, &folio, SGP_READ);
return folio;
}
/*
* Remove range of pages and swap entries from page cache, and free them.
* If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
*/
static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
bool unfalloc)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT;
pgoff_t end = (lend + 1) >> PAGE_SHIFT;
struct folio_batch fbatch;
pgoff_t indices[PAGEVEC_SIZE];
struct folio *folio;
bool same_folio;
long nr_swaps_freed = 0;
pgoff_t index;
int i;
if (lend == -1)
end = -1; /* unsigned, so actually very big */
if (info->fallocend > start && info->fallocend <= end && !unfalloc)
info->fallocend = start;
folio_batch_init(&fbatch);
index = start;
while (index < end && find_lock_entries(mapping, &index, end - 1,
&fbatch, indices)) {
for (i = 0; i < folio_batch_count(&fbatch); i++) {
folio = fbatch.folios[i];
if (xa_is_value(folio)) {
if (unfalloc)
continue;
nr_swaps_freed += !shmem_free_swap(mapping,
indices[i], folio);
continue;
}
if (!unfalloc || !folio_test_uptodate(folio))
truncate_inode_folio(mapping, folio);
folio_unlock(folio);
}
folio_batch_remove_exceptionals(&fbatch);
folio_batch_release(&fbatch);
cond_resched();
}
/*
* When undoing a failed fallocate, we want none of the partial folio
* zeroing and splitting below, but shall want to truncate the whole
* folio when !uptodate indicates that it was added by this fallocate,
* even when [lstart, lend] covers only a part of the folio.
*/
if (unfalloc)
goto whole_folios;
same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT);
if (folio) {
same_folio = lend < folio_pos(folio) + folio_size(folio);
folio_mark_dirty(folio);
if (!truncate_inode_partial_folio(folio, lstart, lend)) {
start = folio_next_index(folio);
if (same_folio)
end = folio->index;
}
folio_unlock(folio);
folio_put(folio);
folio = NULL;
}
if (!same_folio)
folio = shmem_get_partial_folio(inode, lend >> PAGE_SHIFT);
if (folio) {
folio_mark_dirty(folio);
if (!truncate_inode_partial_folio(folio, lstart, lend))
end = folio->index;
folio_unlock(folio);
folio_put(folio);
}
whole_folios:
index = start;
while (index < end) {
cond_resched();
if (!find_get_entries(mapping, &index, end - 1, &fbatch,
indices)) {
/* If all gone or hole-punch or unfalloc, we're done */
if (index == start || end != -1)
break;
/* But if truncating, restart to make sure all gone */
index = start;
continue;
}
for (i = 0; i < folio_batch_count(&fbatch); i++) {
folio = fbatch.folios[i];
if (xa_is_value(folio)) {
if (unfalloc)
continue;
if (shmem_free_swap(mapping, indices[i], folio)) {
/* Swap was replaced by page: retry */
index = indices[i];
break;
}
nr_swaps_freed++;
continue;
}
folio_lock(folio);
if (!unfalloc || !folio_test_uptodate(folio)) {
if (folio_mapping(folio) != mapping) {
/* Page was replaced by swap: retry */
folio_unlock(folio);
index = indices[i];
break;
}
VM_BUG_ON_FOLIO(folio_test_writeback(folio),
folio);
if (!folio_test_large(folio)) {
truncate_inode_folio(mapping, folio);
} else if (truncate_inode_partial_folio(folio, lstart, lend)) {
/*
* If we split a page, reset the loop so
* that we pick up the new sub pages.
* Otherwise the THP was entirely
* dropped or the target range was
* zeroed, so just continue the loop as
* is.
*/
if (!folio_test_large(folio)) {
folio_unlock(folio);
index = start;
break;
}
}
}
folio_unlock(folio);
}
folio_batch_remove_exceptionals(&fbatch);
folio_batch_release(&fbatch);
}
shmem_recalc_inode(inode, 0, -nr_swaps_freed);
}
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
shmem_undo_range(inode, lstart, lend, false);
inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
inode_inc_iversion(inode);
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
static int shmem_getattr(struct mnt_idmap *idmap,
const struct path *path, struct kstat *stat,
u32 request_mask, unsigned int query_flags)
{
struct inode *inode = path->dentry->d_inode;
struct shmem_inode_info *info = SHMEM_I(inode);
if (info->alloced - info->swapped != inode->i_mapping->nrpages)
shmem_recalc_inode(inode, 0, 0);
if (info->fsflags & FS_APPEND_FL)
stat->attributes |= STATX_ATTR_APPEND;
if (info->fsflags & FS_IMMUTABLE_FL)
stat->attributes |= STATX_ATTR_IMMUTABLE;
if (info->fsflags & FS_NODUMP_FL)
stat->attributes |= STATX_ATTR_NODUMP;
stat->attributes_mask |= (STATX_ATTR_APPEND |
STATX_ATTR_IMMUTABLE |
STATX_ATTR_NODUMP);
generic_fillattr(idmap, request_mask, inode, stat);
if (shmem_is_huge(inode, 0, false, NULL, 0))
stat->blksize = HPAGE_PMD_SIZE;
if (request_mask & STATX_BTIME) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = info->i_crtime.tv_sec;
stat->btime.tv_nsec = info->i_crtime.tv_nsec;
}
return 0;
}
static int shmem_setattr(struct mnt_idmap *idmap,
struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
int error;
bool update_mtime = false;
bool update_ctime = true;
error = setattr_prepare(idmap, dentry, attr);
if (error)
return error;
if ((info->seals & F_SEAL_EXEC) && (attr->ia_valid & ATTR_MODE)) {
if ((inode->i_mode ^ attr->ia_mode) & 0111) {
return -EPERM;
}
}
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
loff_t oldsize = inode->i_size;
loff_t newsize = attr->ia_size;
/* protected by i_rwsem */
if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
(newsize > oldsize && (info->seals & F_SEAL_GROW)))
return -EPERM;
if (newsize != oldsize) {
error = shmem_reacct_size(SHMEM_I(inode)->flags,
oldsize, newsize);
if (error)
return error;
i_size_write(inode, newsize);
update_mtime = true;
} else {
update_ctime = false;
}
if (newsize <= oldsize) {
loff_t holebegin = round_up(newsize, PAGE_SIZE);
if (oldsize > holebegin)
unmap_mapping_range(inode->i_mapping,
holebegin, 0, 1);
if (info->alloced)
shmem_truncate_range(inode,
newsize, (loff_t)-1);
/* unmap again to remove racily COWed private pages */
if (oldsize > holebegin)
unmap_mapping_range(inode->i_mapping,
holebegin, 0, 1);
}
}
if (is_quota_modification(idmap, inode, attr)) {
error = dquot_initialize(inode);
if (error)
return error;
}
/* Transfer quota accounting */
if (i_uid_needs_update(idmap, attr, inode) ||
i_gid_needs_update(idmap, attr, inode)) {
error = dquot_transfer(idmap, inode, attr);
if (error)
return error;
}
setattr_copy(idmap, inode, attr);
if (attr->ia_valid & ATTR_MODE)
error = posix_acl_chmod(idmap, dentry, inode->i_mode);
if (!error && update_ctime) {
inode_set_ctime_current(inode);
if (update_mtime)
inode_set_mtime_to_ts(inode, inode_get_ctime(inode));
inode_inc_iversion(inode);
}
return error;
}
static void shmem_evict_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
size_t freed = 0;
if (shmem_mapping(inode->i_mapping)) {
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
mapping_set_exiting(inode->i_mapping);
shmem_truncate_range(inode, 0, (loff_t)-1);
if (!list_empty(&info->shrinklist)) {
spin_lock(&sbinfo->shrinklist_lock);
if (!list_empty(&info->shrinklist)) {
list_del_init(&info->shrinklist);
sbinfo->shrinklist_len--;
}
spin_unlock(&sbinfo->shrinklist_lock);
}
while (!list_empty(&info->swaplist)) {
/* Wait while shmem_unuse() is scanning this inode... */
wait_var_event(&info->stop_eviction,
!atomic_read(&info->stop_eviction));
mutex_lock(&shmem_swaplist_mutex);
/* ...but beware of the race if we peeked too early */
if (!atomic_read(&info->stop_eviction))
list_del_init(&info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
}
}
simple_xattrs_free(&info->xattrs, sbinfo->max_inodes ? &freed : NULL);
shmem_free_inode(inode->i_sb, freed);
WARN_ON(inode->i_blocks);
clear_inode(inode);
#ifdef CONFIG_TMPFS_QUOTA
dquot_free_inode(inode);
dquot_drop(inode);
#endif
}
static int shmem_find_swap_entries(struct address_space *mapping,
pgoff_t start, struct folio_batch *fbatch,
pgoff_t *indices, unsigned int type)
{
XA_STATE(xas, &mapping->i_pages, start);
struct folio *folio;
swp_entry_t entry;
rcu_read_lock();
xas_for_each(&xas, folio, ULONG_MAX) {
if (xas_retry(&xas, folio))
continue;
if (!xa_is_value(folio))
continue;
entry = radix_to_swp_entry(folio);
/*
* swapin error entries can be found in the mapping. But they're
* deliberately ignored here as we've done everything we can do.
*/
if (swp_type(entry) != type)
continue;
indices[folio_batch_count(fbatch)] = xas.xa_index;
if (!folio_batch_add(fbatch, folio))
break;
if (need_resched()) {
xas_pause(&xas);
cond_resched_rcu();
}
}
rcu_read_unlock();
return xas.xa_index;
}
/*
* Move the swapped pages for an inode to page cache. Returns the count
* of pages swapped in, or the error in case of failure.
*/
static int shmem_unuse_swap_entries(struct inode *inode,
struct folio_batch *fbatch, pgoff_t *indices)
{
int i = 0;
int ret = 0;
int error = 0;
struct address_space *mapping = inode->i_mapping;
for (i = 0; i < folio_batch_count(fbatch); i++) {
struct folio *folio = fbatch->folios[i];
if (!xa_is_value(folio))
continue;
error = shmem_swapin_folio(inode, indices[i], &folio, SGP_CACHE,
mapping_gfp_mask(mapping), NULL, NULL);
if (error == 0) {
folio_unlock(folio);
folio_put(folio);
ret++;
}
if (error == -ENOMEM)
break;
error = 0;
}
return error ? error : ret;
}
/*
* If swap found in inode, free it and move page from swapcache to filecache.
*/
static int shmem_unuse_inode(struct inode *inode, unsigned int type)
{
struct address_space *mapping = inode->i_mapping;
pgoff_t start = 0;
struct folio_batch fbatch;
pgoff_t indices[PAGEVEC_SIZE];
int ret = 0;
do {
folio_batch_init(&fbatch);
shmem_find_swap_entries(mapping, start, &fbatch, indices, type);
if (folio_batch_count(&fbatch) == 0) {
ret = 0;
break;
}
ret = shmem_unuse_swap_entries(inode, &fbatch, indices);
if (ret < 0)
break;
start = indices[folio_batch_count(&fbatch) - 1];
} while (true);
return ret;
}
/*
* Read all the shared memory data that resides in the swap
* device 'type' back into memory, so the swap device can be
* unused.
*/
int shmem_unuse(unsigned int type)
{
struct shmem_inode_info *info, *next;
int error = 0;
if (list_empty(&shmem_swaplist))
return 0;
mutex_lock(&shmem_swaplist_mutex);
list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) {
if (!info->swapped) {
list_del_init(&info->swaplist);
continue;
}
/*
* Drop the swaplist mutex while searching the inode for swap;
* but before doing so, make sure shmem_evict_inode() will not
* remove placeholder inode from swaplist, nor let it be freed
* (igrab() would protect from unlink, but not from unmount).
*/
atomic_inc(&info->stop_eviction);
mutex_unlock(&shmem_swaplist_mutex);
error = shmem_unuse_inode(&info->vfs_inode, type);
cond_resched();
mutex_lock(&shmem_swaplist_mutex);
next = list_next_entry(info, swaplist);
if (!info->swapped)
list_del_init(&info->swaplist);
if (atomic_dec_and_test(&info->stop_eviction))
wake_up_var(&info->stop_eviction);
if (error)
break;
}
mutex_unlock(&shmem_swaplist_mutex);
return error;
}
/*
* Move the page from the page cache to the swap cache.
*/
static int shmem_writepage(struct page *page, struct writeback_control *wbc)
{
struct folio *folio = page_folio(page);
struct address_space *mapping = folio->mapping;
struct inode *inode = mapping->host;
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
swp_entry_t swap;
pgoff_t index;
/*
* Our capabilities prevent regular writeback or sync from ever calling
* shmem_writepage; but a stacking filesystem might use ->writepage of
* its underlying filesystem, in which case tmpfs should write out to
* swap only in response to memory pressure, and not for the writeback
* threads or sync.
*/
if (WARN_ON_ONCE(!wbc->for_reclaim))
goto redirty;
if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap))
goto redirty;
if (!total_swap_pages)
goto redirty;
/*
* If /sys/kernel/mm/transparent_hugepage/shmem_enabled is "always" or
* "force", drivers/gpu/drm/i915/gem/i915_gem_shmem.c gets huge pages,
* and its shmem_writeback() needs them to be split when swapping.
*/
if (folio_test_large(folio)) {
/* Ensure the subpages are still dirty */
folio_test_set_dirty(folio);
if (split_huge_page(page) < 0)
goto redirty;
folio = page_folio(page);
folio_clear_dirty(folio);
}
index = folio->index;
/*
* This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC
* value into swapfile.c, the only way we can correctly account for a
* fallocated folio arriving here is now to initialize it and write it.
*
* That's okay for a folio already fallocated earlier, but if we have
* not yet completed the fallocation, then (a) we want to keep track
* of this folio in case we have to undo it, and (b) it may not be a
* good idea to continue anyway, once we're pushing into swap. So
* reactivate the folio, and let shmem_fallocate() quit when too many.
*/
if (!folio_test_uptodate(folio)) {
if (inode->i_private) {
struct shmem_falloc *shmem_falloc;
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
!shmem_falloc->waitq &&
index >= shmem_falloc->start &&
index < shmem_falloc->next)
shmem_falloc->nr_unswapped++;
else
shmem_falloc = NULL;
spin_unlock(&inode->i_lock);
if (shmem_falloc)
goto redirty;
}
folio_zero_range(folio, 0, folio_size(folio));
flush_dcache_folio(folio);
folio_mark_uptodate(folio);
}
swap = folio_alloc_swap(folio);
if (!swap.val)
goto redirty;
/*
* Add inode to shmem_unuse()'s list of swapped-out inodes,
* if it's not already there. Do it now before the folio is
* moved to swap cache, when its pagelock no longer protects
* the inode from eviction. But don't unlock the mutex until
* we've incremented swapped, because shmem_unuse_inode() will
* prune a !swapped inode from the swaplist under this mutex.
*/
mutex_lock(&shmem_swaplist_mutex);
if (list_empty(&info->swaplist))
list_add(&info->swaplist, &shmem_swaplist);
if (add_to_swap_cache(folio, swap,
__GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN,
NULL) == 0) {
shmem_recalc_inode(inode, 0, 1);
swap_shmem_alloc(swap);
shmem_delete_from_page_cache(folio, swp_to_radix_entry(swap));
mutex_unlock(&shmem_swaplist_mutex);
BUG_ON(folio_mapped(folio));
return swap_writepage(&folio->page, wbc);
}
mutex_unlock(&shmem_swaplist_mutex);
put_swap_folio(folio, swap);
redirty:
folio_mark_dirty(folio);
if (wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE; /* Return with folio locked */
folio_unlock(folio);
return 0;
}
#if defined(CONFIG_NUMA) && defined(CONFIG_TMPFS)
static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
{
char buffer[64];
if (!mpol || mpol->mode == MPOL_DEFAULT)
return; /* show nothing */
mpol_to_str(buffer, sizeof(buffer), mpol);
seq_printf(seq, ",mpol=%s", buffer);
}
static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
{
struct mempolicy *mpol = NULL;
if (sbinfo->mpol) {
raw_spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */
mpol = sbinfo->mpol;
mpol_get(mpol);
raw_spin_unlock(&sbinfo->stat_lock);
}
return mpol;
}
#else /* !CONFIG_NUMA || !CONFIG_TMPFS */
static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
{
}
static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
{
return NULL;
}
#endif /* CONFIG_NUMA && CONFIG_TMPFS */
static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info,
pgoff_t index, unsigned int order, pgoff_t *ilx);
static struct folio *shmem_swapin_cluster(swp_entry_t swap, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct mempolicy *mpol;
pgoff_t ilx;
struct folio *folio;
mpol = shmem_get_pgoff_policy(info, index, 0, &ilx);
folio = swap_cluster_readahead(swap, gfp, mpol, ilx);
mpol_cond_put(mpol);
return folio;
}
/*
* Make sure huge_gfp is always more limited than limit_gfp.
* Some of the flags set permissions, while others set limitations.
*/
static gfp_t limit_gfp_mask(gfp_t huge_gfp, gfp_t limit_gfp)
{
gfp_t allowflags = __GFP_IO | __GFP_FS | __GFP_RECLAIM;
gfp_t denyflags = __GFP_NOWARN | __GFP_NORETRY;
gfp_t zoneflags = limit_gfp & GFP_ZONEMASK;
gfp_t result = huge_gfp & ~(allowflags | GFP_ZONEMASK);
/* Allow allocations only from the originally specified zones. */
result |= zoneflags;
/*
* Minimize the result gfp by taking the union with the deny flags,
* and the intersection of the allow flags.
*/
result |= (limit_gfp & denyflags);
result |= (huge_gfp & limit_gfp) & allowflags;
return result;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
unsigned long shmem_allowable_huge_orders(struct inode *inode,
struct vm_area_struct *vma, pgoff_t index,
bool global_huge)
{
unsigned long mask = READ_ONCE(huge_shmem_orders_always);
unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size);
unsigned long vm_flags = vma->vm_flags;
loff_t i_size;
int order;
if ((vm_flags & VM_NOHUGEPAGE) ||
test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
return 0;
/* If the hardware/firmware marked hugepage support disabled. */
if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED))
return 0;
/*
* Following the 'deny' semantics of the top level, force the huge
* option off from all mounts.
*/
if (shmem_huge == SHMEM_HUGE_DENY)
return 0;
/*
* Only allow inherit orders if the top-level value is 'force', which
* means non-PMD sized THP can not override 'huge' mount option now.
*/
if (shmem_huge == SHMEM_HUGE_FORCE)
return READ_ONCE(huge_shmem_orders_inherit);
/* Allow mTHP that will be fully within i_size. */
order = highest_order(within_size_orders);
while (within_size_orders) {
index = round_up(index + 1, order);
i_size = round_up(i_size_read(inode), PAGE_SIZE);
if (i_size >> PAGE_SHIFT >= index) {
mask |= within_size_orders;
break;
}
order = next_order(&within_size_orders, order);
}
if (vm_flags & VM_HUGEPAGE)
mask |= READ_ONCE(huge_shmem_orders_madvise);
if (global_huge)
mask |= READ_ONCE(huge_shmem_orders_inherit);
return THP_ORDERS_ALL_FILE_DEFAULT & mask;
}
static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf,
struct address_space *mapping, pgoff_t index,
unsigned long orders)
{
struct vm_area_struct *vma = vmf->vma;
pgoff_t aligned_index;
unsigned long pages;
int order;
orders = thp_vma_suitable_orders(vma, vmf->address, orders);
if (!orders)
return 0;
/* Find the highest order that can add into the page cache */
order = highest_order(orders);
while (orders) {
pages = 1UL << order;
aligned_index = round_down(index, pages);
if (!xa_find(&mapping->i_pages, &aligned_index,
aligned_index + pages - 1, XA_PRESENT))
break;
order = next_order(&orders, order);
}
return orders;
}
#else
static unsigned long shmem_suitable_orders(struct inode *inode, struct vm_fault *vmf,
struct address_space *mapping, pgoff_t index,
unsigned long orders)
{
return 0;
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static struct folio *shmem_alloc_folio(gfp_t gfp, int order,
struct shmem_inode_info *info, pgoff_t index)
{
struct mempolicy *mpol;
pgoff_t ilx;
struct folio *folio;
mpol = shmem_get_pgoff_policy(info, index, order, &ilx);
folio = folio_alloc_mpol(gfp, order, mpol, ilx, numa_node_id());
mpol_cond_put(mpol);
return folio;
}
static struct folio *shmem_alloc_and_add_folio(struct vm_fault *vmf,
gfp_t gfp, struct inode *inode, pgoff_t index,
struct mm_struct *fault_mm, unsigned long orders)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
unsigned long suitable_orders = 0;
struct folio *folio = NULL;
long pages;
int error, order;
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
orders = 0;
if (orders > 0) {
if (vma && vma_is_anon_shmem(vma)) {
suitable_orders = shmem_suitable_orders(inode, vmf,
mapping, index, orders);
} else if (orders & BIT(HPAGE_PMD_ORDER)) {
pages = HPAGE_PMD_NR;
suitable_orders = BIT(HPAGE_PMD_ORDER);
index = round_down(index, HPAGE_PMD_NR);
/*
* Check for conflict before waiting on a huge allocation.
* Conflict might be that a huge page has just been allocated
* and added to page cache by a racing thread, or that there
* is already at least one small page in the huge extent.
* Be careful to retry when appropriate, but not forever!
* Elsewhere -EEXIST would be the right code, but not here.
*/
if (xa_find(&mapping->i_pages, &index,
index + HPAGE_PMD_NR - 1, XA_PRESENT))
return ERR_PTR(-E2BIG);
}
order = highest_order(suitable_orders);
while (suitable_orders) {
pages = 1UL << order;
index = round_down(index, pages);
folio = shmem_alloc_folio(gfp, order, info, index);
if (folio)
goto allocated;
if (pages == HPAGE_PMD_NR)
count_vm_event(THP_FILE_FALLBACK);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_mthp_stat(order, MTHP_STAT_SHMEM_FALLBACK);
#endif
order = next_order(&suitable_orders, order);
}
} else {
pages = 1;
folio = shmem_alloc_folio(gfp, 0, info, index);
}
if (!folio)
return ERR_PTR(-ENOMEM);
allocated:
__folio_set_locked(folio);
__folio_set_swapbacked(folio);
gfp &= GFP_RECLAIM_MASK;
error = mem_cgroup_charge(folio, fault_mm, gfp);
if (error) {
if (xa_find(&mapping->i_pages, &index,
index + pages - 1, XA_PRESENT)) {
error = -EEXIST;
} else if (pages > 1) {
if (pages == HPAGE_PMD_NR) {
count_vm_event(THP_FILE_FALLBACK);
count_vm_event(THP_FILE_FALLBACK_CHARGE);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK);
count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_FALLBACK_CHARGE);
#endif
}
goto unlock;
}
error = shmem_add_to_page_cache(folio, mapping, index, NULL, gfp);
if (error)
goto unlock;
error = shmem_inode_acct_blocks(inode, pages);
if (error) {
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
long freed;
/*
* Try to reclaim some space by splitting a few
* large folios beyond i_size on the filesystem.
*/
shmem_unused_huge_shrink(sbinfo, NULL, 2);
/*
* And do a shmem_recalc_inode() to account for freed pages:
* except our folio is there in cache, so not quite balanced.
*/
spin_lock(&info->lock);
freed = pages + info->alloced - info->swapped -
READ_ONCE(mapping->nrpages);
if (freed > 0)
info->alloced -= freed;
spin_unlock(&info->lock);
if (freed > 0)
shmem_inode_unacct_blocks(inode, freed);
error = shmem_inode_acct_blocks(inode, pages);
if (error) {
filemap_remove_folio(folio);
goto unlock;
}
}
shmem_recalc_inode(inode, pages, 0);
folio_add_lru(folio);
return folio;
unlock:
folio_unlock(folio);
folio_put(folio);
return ERR_PTR(error);
}
/*
* When a page is moved from swapcache to shmem filecache (either by the
* usual swapin of shmem_get_folio_gfp(), or by the less common swapoff of
* shmem_unuse_inode()), it may have been read in earlier from swap, in
* ignorance of the mapping it belongs to. If that mapping has special
* constraints (like the gma500 GEM driver, which requires RAM below 4GB),
* we may need to copy to a suitable page before moving to filecache.
*
* In a future release, this may well be extended to respect cpuset and
* NUMA mempolicy, and applied also to anonymous pages in do_swap_page();
* but for now it is a simple matter of zone.
*/
static bool shmem_should_replace_folio(struct folio *folio, gfp_t gfp)
{
return folio_zonenum(folio) > gfp_zone(gfp);
}
static int shmem_replace_folio(struct folio **foliop, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct folio *old, *new;
struct address_space *swap_mapping;
swp_entry_t entry;
pgoff_t swap_index;
int error;
old = *foliop;
entry = old->swap;
swap_index = swap_cache_index(entry);
swap_mapping = swap_address_space(entry);
/*
* We have arrived here because our zones are constrained, so don't
* limit chance of success by further cpuset and node constraints.
*/
gfp &= ~GFP_CONSTRAINT_MASK;
VM_BUG_ON_FOLIO(folio_test_large(old), old);
new = shmem_alloc_folio(gfp, 0, info, index);
if (!new)
return -ENOMEM;
folio_get(new);
folio_copy(new, old);
flush_dcache_folio(new);
__folio_set_locked(new);
__folio_set_swapbacked(new);
folio_mark_uptodate(new);
new->swap = entry;
folio_set_swapcache(new);
/*
* Our caller will very soon move newpage out of swapcache, but it's
* a nice clean interface for us to replace oldpage by newpage there.
*/
xa_lock_irq(&swap_mapping->i_pages);
error = shmem_replace_entry(swap_mapping, swap_index, old, new);
if (!error) {
mem_cgroup_replace_folio(old, new);
__lruvec_stat_mod_folio(new, NR_FILE_PAGES, 1);
__lruvec_stat_mod_folio(new, NR_SHMEM, 1);
__lruvec_stat_mod_folio(old, NR_FILE_PAGES, -1);
__lruvec_stat_mod_folio(old, NR_SHMEM, -1);
}
xa_unlock_irq(&swap_mapping->i_pages);
if (unlikely(error)) {
/*
* Is this possible? I think not, now that our callers check
* both PageSwapCache and page_private after getting page lock;
* but be defensive. Reverse old to newpage for clear and free.
*/
old = new;
} else {
folio_add_lru(new);
*foliop = new;
}
folio_clear_swapcache(old);
old->private = NULL;
folio_unlock(old);
folio_put_refs(old, 2);
return error;
}
static void shmem_set_folio_swapin_error(struct inode *inode, pgoff_t index,
struct folio *folio, swp_entry_t swap)
{
struct address_space *mapping = inode->i_mapping;
swp_entry_t swapin_error;
void *old;
swapin_error = make_poisoned_swp_entry();
old = xa_cmpxchg_irq(&mapping->i_pages, index,
swp_to_radix_entry(swap),
swp_to_radix_entry(swapin_error), 0);
if (old != swp_to_radix_entry(swap))
return;
folio_wait_writeback(folio);
delete_from_swap_cache(folio);
/*
* Don't treat swapin error folio as alloced. Otherwise inode->i_blocks
* won't be 0 when inode is released and thus trigger WARN_ON(i_blocks)
* in shmem_evict_inode().
*/
shmem_recalc_inode(inode, -1, -1);
swap_free(swap);
}
/*
* Swap in the folio pointed to by *foliop.
* Caller has to make sure that *foliop contains a valid swapped folio.
* Returns 0 and the folio in foliop if success. On failure, returns the
* error code and NULL in *foliop.
*/
static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
struct folio **foliop, enum sgp_type sgp,
gfp_t gfp, struct mm_struct *fault_mm,
vm_fault_t *fault_type)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
struct swap_info_struct *si;
struct folio *folio = NULL;
swp_entry_t swap;
int error;
VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
swap = radix_to_swp_entry(*foliop);
*foliop = NULL;
if (is_poisoned_swp_entry(swap))
return -EIO;
si = get_swap_device(swap);
if (!si) {
if (!shmem_confirm_swap(mapping, index, swap))
return -EEXIST;
else
return -EINVAL;
}
/* Look it up and read it in.. */
folio = swap_cache_get_folio(swap, NULL, 0);
if (!folio) {
/* Or update major stats only when swapin succeeds?? */
if (fault_type) {
*fault_type |= VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
count_memcg_event_mm(fault_mm, PGMAJFAULT);
}
/* Here we actually start the io */
folio = shmem_swapin_cluster(swap, gfp, info, index);
if (!folio) {
error = -ENOMEM;
goto failed;
}
}
/* We have to do this with folio locked to prevent races */
folio_lock(folio);
if (!folio_test_swapcache(folio) ||
folio->swap.val != swap.val ||
!shmem_confirm_swap(mapping, index, swap)) {
error = -EEXIST;
goto unlock;
}
if (!folio_test_uptodate(folio)) {
error = -EIO;
goto failed;
}
folio_wait_writeback(folio);
/*
* Some architectures may have to restore extra metadata to the
* folio after reading from swap.
*/
arch_swap_restore(folio_swap(swap, folio), folio);
if (shmem_should_replace_folio(folio, gfp)) {
error = shmem_replace_folio(&folio, gfp, info, index);
if (error)
goto failed;
}
error = shmem_add_to_page_cache(folio, mapping, index,
swp_to_radix_entry(swap), gfp);
if (error)
goto failed;
shmem_recalc_inode(inode, 0, -1);
if (sgp == SGP_WRITE)
folio_mark_accessed(folio);
delete_from_swap_cache(folio);
folio_mark_dirty(folio);
swap_free(swap);
put_swap_device(si);
*foliop = folio;
return 0;
failed:
if (!shmem_confirm_swap(mapping, index, swap))
error = -EEXIST;
if (error == -EIO)
shmem_set_folio_swapin_error(inode, index, folio, swap);
unlock:
if (folio) {
folio_unlock(folio);
folio_put(folio);
}
put_swap_device(si);
return error;
}
/*
* shmem_get_folio_gfp - find page in cache, or get from swap, or allocate
*
* If we allocate a new one we do not mark it dirty. That's up to the
* vm. If we swap it in we mark it dirty since we also free the swap
* entry since a page cannot live in both the swap and page cache.
*
* vmf and fault_type are only supplied by shmem_fault: otherwise they are NULL.
*/
static int shmem_get_folio_gfp(struct inode *inode, pgoff_t index,
struct folio **foliop, enum sgp_type sgp, gfp_t gfp,
struct vm_fault *vmf, vm_fault_t *fault_type)
{
struct vm_area_struct *vma = vmf ? vmf->vma : NULL;
struct mm_struct *fault_mm;
struct folio *folio;
int error;
bool alloced, huge;
unsigned long orders = 0;
if (WARN_ON_ONCE(!shmem_mapping(inode->i_mapping)))
return -EINVAL;
if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
return -EFBIG;
repeat:
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode))
return -EINVAL;
alloced = false;
fault_mm = vma ? vma->vm_mm : NULL;
folio = filemap_get_entry(inode->i_mapping, index);
if (folio && vma && userfaultfd_minor(vma)) {
if (!xa_is_value(folio))
folio_put(folio);
*fault_type = handle_userfault(vmf, VM_UFFD_MINOR);
return 0;
}
if (xa_is_value(folio)) {
error = shmem_swapin_folio(inode, index, &folio,
sgp, gfp, fault_mm, fault_type);
if (error == -EEXIST)
goto repeat;
*foliop = folio;
return error;
}
if (folio) {
folio_lock(folio);
/* Has the folio been truncated or swapped out? */
if (unlikely(folio->mapping != inode->i_mapping)) {
folio_unlock(folio);
folio_put(folio);
goto repeat;
}
if (sgp == SGP_WRITE)
folio_mark_accessed(folio);
if (folio_test_uptodate(folio))
goto out;
/* fallocated folio */
if (sgp != SGP_READ)
goto clear;
folio_unlock(folio);
folio_put(folio);
}
/*
* SGP_READ: succeed on hole, with NULL folio, letting caller zero.
* SGP_NOALLOC: fail on hole, with NULL folio, letting caller fail.
*/
*foliop = NULL;
if (sgp == SGP_READ)
return 0;
if (sgp == SGP_NOALLOC)
return -ENOENT;
/*
* Fast cache lookup and swap lookup did not find it: allocate.
*/
if (vma && userfaultfd_missing(vma)) {
*fault_type = handle_userfault(vmf, VM_UFFD_MISSING);
return 0;
}
huge = shmem_is_huge(inode, index, false, fault_mm,
vma ? vma->vm_flags : 0);
/* Find hugepage orders that are allowed for anonymous shmem. */
if (vma && vma_is_anon_shmem(vma))
orders = shmem_allowable_huge_orders(inode, vma, index, huge);
else if (huge)
orders = BIT(HPAGE_PMD_ORDER);
if (orders > 0) {
gfp_t huge_gfp;
huge_gfp = vma_thp_gfp_mask(vma);
huge_gfp = limit_gfp_mask(huge_gfp, gfp);
folio = shmem_alloc_and_add_folio(vmf, huge_gfp,
inode, index, fault_mm, orders);
if (!IS_ERR(folio)) {
if (folio_test_pmd_mappable(folio))
count_vm_event(THP_FILE_ALLOC);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
count_mthp_stat(folio_order(folio), MTHP_STAT_SHMEM_ALLOC);
#endif
goto alloced;
}
if (PTR_ERR(folio) == -EEXIST)
goto repeat;
}
folio = shmem_alloc_and_add_folio(vmf, gfp, inode, index, fault_mm, 0);
if (IS_ERR(folio)) {
error = PTR_ERR(folio);
if (error == -EEXIST)
goto repeat;
folio = NULL;
goto unlock;
}
alloced:
alloced = true;
if (folio_test_large(folio) &&
DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) <
folio_next_index(folio) - 1) {
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct shmem_inode_info *info = SHMEM_I(inode);
/*
* Part of the large folio is beyond i_size: subject
* to shrink under memory pressure.
*/
spin_lock(&sbinfo->shrinklist_lock);
/*
* _careful to defend against unlocked access to
* ->shrink_list in shmem_unused_huge_shrink()
*/
if (list_empty_careful(&info->shrinklist)) {
list_add_tail(&info->shrinklist,
&sbinfo->shrinklist);
sbinfo->shrinklist_len++;
}
spin_unlock(&sbinfo->shrinklist_lock);
}
if (sgp == SGP_WRITE)
folio_set_referenced(folio);
/*
* Let SGP_FALLOC use the SGP_WRITE optimization on a new folio.
*/
if (sgp == SGP_FALLOC)
sgp = SGP_WRITE;
clear:
/*
* Let SGP_WRITE caller clear ends if write does not fill folio;
* but SGP_FALLOC on a folio fallocated earlier must initialize
* it now, lest undo on failure cancel our earlier guarantee.
*/
if (sgp != SGP_WRITE && !folio_test_uptodate(folio)) {
long i, n = folio_nr_pages(folio);
for (i = 0; i < n; i++)
clear_highpage(folio_page(folio, i));
flush_dcache_folio(folio);
folio_mark_uptodate(folio);
}
/* Perhaps the file has been truncated since we checked */
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
goto unlock;
}
out:
*foliop = folio;
return 0;
/*
* Error recovery.
*/
unlock:
if (alloced)
filemap_remove_folio(folio);
shmem_recalc_inode(inode, 0, 0);
if (folio) {
folio_unlock(folio);
folio_put(folio);
}
return error;
}
/**
* shmem_get_folio - find, and lock a shmem folio.
* @inode: inode to search
* @index: the page index.
* @foliop: pointer to the folio if found
* @sgp: SGP_* flags to control behavior
*
* Looks up the page cache entry at @inode & @index. If a folio is
* present, it is returned locked with an increased refcount.
*
* If the caller modifies data in the folio, it must call folio_mark_dirty()
* before unlocking the folio to ensure that the folio is not reclaimed.
* There is no need to reserve space before calling folio_mark_dirty().
*
* When no folio is found, the behavior depends on @sgp:
* - for SGP_READ, *@foliop is %NULL and 0 is returned
* - for SGP_NOALLOC, *@foliop is %NULL and -ENOENT is returned
* - for all other flags a new folio is allocated, inserted into the
* page cache and returned locked in @foliop.
*
* Context: May sleep.
* Return: 0 if successful, else a negative error code.
*/
int shmem_get_folio(struct inode *inode, pgoff_t index, struct folio **foliop,
enum sgp_type sgp)
{
return shmem_get_folio_gfp(inode, index, foliop, sgp,
mapping_gfp_mask(inode->i_mapping), NULL, NULL);
}
EXPORT_SYMBOL_GPL(shmem_get_folio);
/*
* This is like autoremove_wake_function, but it removes the wait queue
* entry unconditionally - even if something else had already woken the
* target.
*/
static int synchronous_wake_function(wait_queue_entry_t *wait,
unsigned int mode, int sync, void *key)
{
int ret = default_wake_function(wait, mode, sync, key);
list_del_init(&wait->entry);
return ret;
}
/*
* Trinity finds that probing a hole which tmpfs is punching can
* prevent the hole-punch from ever completing: which in turn
* locks writers out with its hold on i_rwsem. So refrain from
* faulting pages into the hole while it's being punched. Although
* shmem_undo_range() does remove the additions, it may be unable to
* keep up, as each new page needs its own unmap_mapping_range() call,
* and the i_mmap tree grows ever slower to scan if new vmas are added.
*
* It does not matter if we sometimes reach this check just before the
* hole-punch begins, so that one fault then races with the punch:
* we just need to make racing faults a rare case.
*
* The implementation below would be much simpler if we just used a
* standard mutex or completion: but we cannot take i_rwsem in fault,
* and bloating every shmem inode for this unlikely case would be sad.
*/
static vm_fault_t shmem_falloc_wait(struct vm_fault *vmf, struct inode *inode)
{
struct shmem_falloc *shmem_falloc;
struct file *fpin = NULL;
vm_fault_t ret = 0;
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
shmem_falloc->waitq &&
vmf->pgoff >= shmem_falloc->start &&
vmf->pgoff < shmem_falloc->next) {
wait_queue_head_t *shmem_falloc_waitq;
DEFINE_WAIT_FUNC(shmem_fault_wait, synchronous_wake_function);
ret = VM_FAULT_NOPAGE;
fpin = maybe_unlock_mmap_for_io(vmf, NULL);
shmem_falloc_waitq = shmem_falloc->waitq;
prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
TASK_UNINTERRUPTIBLE);
spin_unlock(&inode->i_lock);
schedule();
/*
* shmem_falloc_waitq points into the shmem_fallocate()
* stack of the hole-punching task: shmem_falloc_waitq
* is usually invalid by the time we reach here, but
* finish_wait() does not dereference it in that case;
* though i_lock needed lest racing with wake_up_all().
*/
spin_lock(&inode->i_lock);
finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
}
spin_unlock(&inode->i_lock);
if (fpin) {
fput(fpin);
ret = VM_FAULT_RETRY;
}
return ret;
}
static vm_fault_t shmem_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
struct folio *folio = NULL;
vm_fault_t ret = 0;
int err;
/*
* Trinity finds that probing a hole which tmpfs is punching can
* prevent the hole-punch from ever completing: noted in i_private.
*/
if (unlikely(inode->i_private)) {
ret = shmem_falloc_wait(vmf, inode);
if (ret)
return ret;
}
WARN_ON_ONCE(vmf->page != NULL);
err = shmem_get_folio_gfp(inode, vmf->pgoff, &folio, SGP_CACHE,
gfp, vmf, &ret);
if (err)
return vmf_error(err);
if (folio) {
vmf->page = folio_file_page(folio, vmf->pgoff);
ret |= VM_FAULT_LOCKED;
}
return ret;
}
unsigned long shmem_get_unmapped_area(struct file *file,
unsigned long uaddr, unsigned long len,
unsigned long pgoff, unsigned long flags)
{
unsigned long addr;
unsigned long offset;
unsigned long inflated_len;
unsigned long inflated_addr;
unsigned long inflated_offset;
unsigned long hpage_size;
if (len > TASK_SIZE)
return -ENOMEM;
addr = mm_get_unmapped_area(current->mm, file, uaddr, len, pgoff,
flags);
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
return addr;
if (IS_ERR_VALUE(addr))
return addr;
if (addr & ~PAGE_MASK)
return addr;
if (addr > TASK_SIZE - len)
return addr;
if (shmem_huge == SHMEM_HUGE_DENY)
return addr;
if (flags & MAP_FIXED)
return addr;
/*
* Our priority is to support MAP_SHARED mapped hugely;
* and support MAP_PRIVATE mapped hugely too, until it is COWed.
* But if caller specified an address hint and we allocated area there
* successfully, respect that as before.
*/
if (uaddr == addr)
return addr;
hpage_size = HPAGE_PMD_SIZE;
if (shmem_huge != SHMEM_HUGE_FORCE) {
struct super_block *sb;
unsigned long __maybe_unused hpage_orders;
int order = 0;
if (file) {
VM_BUG_ON(file->f_op != &shmem_file_operations);
sb = file_inode(file)->i_sb;
} else {
/*
* Called directly from mm/mmap.c, or drivers/char/mem.c
* for "/dev/zero", to create a shared anonymous object.
*/
if (IS_ERR(shm_mnt))
return addr;
sb = shm_mnt->mnt_sb;
/*
* Find the highest mTHP order used for anonymous shmem to
* provide a suitable alignment address.
*/
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
hpage_orders = READ_ONCE(huge_shmem_orders_always);
hpage_orders |= READ_ONCE(huge_shmem_orders_within_size);
hpage_orders |= READ_ONCE(huge_shmem_orders_madvise);
if (SHMEM_SB(sb)->huge != SHMEM_HUGE_NEVER)
hpage_orders |= READ_ONCE(huge_shmem_orders_inherit);
if (hpage_orders > 0) {
order = highest_order(hpage_orders);
hpage_size = PAGE_SIZE << order;
}
#endif
}
if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER && !order)
return addr;
}
if (len < hpage_size)
return addr;
offset = (pgoff << PAGE_SHIFT) & (hpage_size - 1);
if (offset && offset + len < 2 * hpage_size)
return addr;
if ((addr & (hpage_size - 1)) == offset)
return addr;
inflated_len = len + hpage_size - PAGE_SIZE;
if (inflated_len > TASK_SIZE)
return addr;
if (inflated_len < len)
return addr;
inflated_addr = mm_get_unmapped_area(current->mm, NULL, uaddr,
inflated_len, 0, flags);
if (IS_ERR_VALUE(inflated_addr))
return addr;
if (inflated_addr & ~PAGE_MASK)
return addr;
inflated_offset = inflated_addr & (hpage_size - 1);
inflated_addr += offset - inflated_offset;
if (inflated_offset > offset)
inflated_addr += hpage_size;
if (inflated_addr > TASK_SIZE - len)
return addr;
return inflated_addr;
}
#ifdef CONFIG_NUMA
static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
{
struct inode *inode = file_inode(vma->vm_file);
return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol);
}
static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
unsigned long addr, pgoff_t *ilx)
{
struct inode *inode = file_inode(vma->vm_file);
pgoff_t index;
/*
* Bias interleave by inode number to distribute better across nodes;
* but this interface is independent of which page order is used, so
* supplies only that bias, letting caller apply the offset (adjusted
* by page order, as in shmem_get_pgoff_policy() and get_vma_policy()).
*/
*ilx = inode->i_ino;
index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index);
}
static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info,
pgoff_t index, unsigned int order, pgoff_t *ilx)
{
struct mempolicy *mpol;
/* Bias interleave by inode number to distribute better across nodes */
*ilx = info->vfs_inode.i_ino + (index >> order);
mpol = mpol_shared_policy_lookup(&info->policy, index);
return mpol ? mpol : get_task_policy(current);
}
#else
static struct mempolicy *shmem_get_pgoff_policy(struct shmem_inode_info *info,
pgoff_t index, unsigned int order, pgoff_t *ilx)
{
*ilx = 0;
return NULL;
}
#endif /* CONFIG_NUMA */
int shmem_lock(struct file *file, int lock, struct ucounts *ucounts)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
/*
* What serializes the accesses to info->flags?
* ipc_lock_object() when called from shmctl_do_lock(),
* no serialization needed when called from shm_destroy().
*/
if (lock && !(info->flags & VM_LOCKED)) {
if (!user_shm_lock(inode->i_size, ucounts))
goto out_nomem;
info->flags |= VM_LOCKED;
mapping_set_unevictable(file->f_mapping);
}
if (!lock && (info->flags & VM_LOCKED) && ucounts) {
user_shm_unlock(inode->i_size, ucounts);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
}
retval = 0;
out_nomem:
return retval;
}
static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
int ret;
ret = seal_check_write(info->seals, vma);
if (ret)
return ret;
/* arm64 - allow memory tagging on RAM-based files */
vm_flags_set(vma, VM_MTE_ALLOWED);
file_accessed(file);
/* This is anonymous shared memory if it is unlinked at the time of mmap */
if (inode->i_nlink)
vma->vm_ops = &shmem_vm_ops;
else
vma->vm_ops = &shmem_anon_vm_ops;
return 0;
}
static int shmem_file_open(struct inode *inode, struct file *file)
{
file->f_mode |= FMODE_CAN_ODIRECT;
return generic_file_open(inode, file);
}
#ifdef CONFIG_TMPFS_XATTR
static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
/*
* chattr's fsflags are unrelated to extended attributes,
* but tmpfs has chosen to enable them under the same config option.
*/
static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags)
{
unsigned int i_flags = 0;
if (fsflags & FS_NOATIME_FL)
i_flags |= S_NOATIME;
if (fsflags & FS_APPEND_FL)
i_flags |= S_APPEND;
if (fsflags & FS_IMMUTABLE_FL)
i_flags |= S_IMMUTABLE;
/*
* But FS_NODUMP_FL does not require any action in i_flags.
*/
inode_set_flags(inode, i_flags, S_NOATIME | S_APPEND | S_IMMUTABLE);
}
#else
static void shmem_set_inode_flags(struct inode *inode, unsigned int fsflags)
{
}
#define shmem_initxattrs NULL
#endif
static struct offset_ctx *shmem_get_offset_ctx(struct inode *inode)
{
return &SHMEM_I(inode)->dir_offsets;
}
static struct inode *__shmem_get_inode(struct mnt_idmap *idmap,
struct super_block *sb,
struct inode *dir, umode_t mode,
dev_t dev, unsigned long flags)
{
struct inode *inode;
struct shmem_inode_info *info;
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
ino_t ino;
int err;
err = shmem_reserve_inode(sb, &ino);
if (err)
return ERR_PTR(err);
inode = new_inode(sb);
if (!inode) {
shmem_free_inode(sb, 0);
return ERR_PTR(-ENOSPC);
}
inode->i_ino = ino;
inode_init_owner(idmap, inode, dir, mode);
inode->i_blocks = 0;
simple_inode_init_ts(inode);
inode->i_generation = get_random_u32();
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
atomic_set(&info->stop_eviction, 0);
info->seals = F_SEAL_SEAL;
info->flags = flags & VM_NORESERVE;
info->i_crtime = inode_get_mtime(inode);
info->fsflags = (dir == NULL) ? 0 :
SHMEM_I(dir)->fsflags & SHMEM_FL_INHERITED;
if (info->fsflags)
shmem_set_inode_flags(inode, info->fsflags);
INIT_LIST_HEAD(&info->shrinklist);
INIT_LIST_HEAD(&info->swaplist);
simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
if (sbinfo->noswap)
mapping_set_unevictable(inode->i_mapping);
mapping_set_large_folios(inode->i_mapping);
switch (mode & S_IFMT) {
default:
inode->i_op = &shmem_special_inode_operations;
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_inode_operations;
inode->i_fop = &shmem_file_operations;
mpol_shared_policy_init(&info->policy,
shmem_get_sbmpol(sbinfo));
break;
case S_IFDIR:
inc_nlink(inode);
/* Some things misbehave if size == 0 on a directory */
inode->i_size = 2 * BOGO_DIRENT_SIZE;
inode->i_op = &shmem_dir_inode_operations;
inode->i_fop = &simple_offset_dir_operations;
simple_offset_init(shmem_get_offset_ctx(inode));
break;
case S_IFLNK:
/*
* Must not load anything in the rbtree,
* mpol_free_shared_policy will not be called.
*/
mpol_shared_policy_init(&info->policy, NULL);
break;
}
lockdep_annotate_inode_mutex_key(inode);
return inode;
}
#ifdef CONFIG_TMPFS_QUOTA
static struct inode *shmem_get_inode(struct mnt_idmap *idmap,
struct super_block *sb, struct inode *dir,
umode_t mode, dev_t dev, unsigned long flags)
{
int err;
struct inode *inode;
inode = __shmem_get_inode(idmap, sb, dir, mode, dev, flags);
if (IS_ERR(inode))
return inode;
err = dquot_initialize(inode);
if (err)
goto errout;
err = dquot_alloc_inode(inode);
if (err) {
dquot_drop(inode);
goto errout;
}
return inode;
errout:
inode->i_flags |= S_NOQUOTA;
iput(inode);
return ERR_PTR(err);
}
#else
static inline struct inode *shmem_get_inode(struct mnt_idmap *idmap,
struct super_block *sb, struct inode *dir,
umode_t mode, dev_t dev, unsigned long flags)
{
return __shmem_get_inode(idmap, sb, dir, mode, dev, flags);
}
#endif /* CONFIG_TMPFS_QUOTA */
#ifdef CONFIG_USERFAULTFD
int shmem_mfill_atomic_pte(pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
uffd_flags_t flags,
struct folio **foliop)
{
struct inode *inode = file_inode(dst_vma->vm_file);
struct shmem_inode_info *info = SHMEM_I(inode);
struct address_space *mapping = inode->i_mapping;
gfp_t gfp = mapping_gfp_mask(mapping);
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
void *page_kaddr;
struct folio *folio;
int ret;
pgoff_t max_off;
if (shmem_inode_acct_blocks(inode, 1)) {
/*
* We may have got a page, returned -ENOENT triggering a retry,
* and now we find ourselves with -ENOMEM. Release the page, to
* avoid a BUG_ON in our caller.
*/
if (unlikely(*foliop)) {
folio_put(*foliop);
*foliop = NULL;
}
return -ENOMEM;
}
if (!*foliop) {
ret = -ENOMEM;
folio = shmem_alloc_folio(gfp, 0, info, pgoff);
if (!folio)
goto out_unacct_blocks;
if (uffd_flags_mode_is(flags, MFILL_ATOMIC_COPY)) {
page_kaddr = kmap_local_folio(folio, 0);
/*
* The read mmap_lock is held here. Despite the
* mmap_lock being read recursive a deadlock is still
* possible if a writer has taken a lock. For example:
*
* process A thread 1 takes read lock on own mmap_lock
* process A thread 2 calls mmap, blocks taking write lock
* process B thread 1 takes page fault, read lock on own mmap lock
* process B thread 2 calls mmap, blocks taking write lock
* process A thread 1 blocks taking read lock on process B
* process B thread 1 blocks taking read lock on process A
*
* Disable page faults to prevent potential deadlock
* and retry the copy outside the mmap_lock.
*/
pagefault_disable();
ret = copy_from_user(page_kaddr,
(const void __user *)src_addr,
PAGE_SIZE);
pagefault_enable();
kunmap_local(page_kaddr);
/* fallback to copy_from_user outside mmap_lock */
if (unlikely(ret)) {
*foliop = folio;
ret = -ENOENT;
/* don't free the page */
goto out_unacct_blocks;
}
flush_dcache_folio(folio);
} else { /* ZEROPAGE */
clear_user_highpage(&folio->page, dst_addr);
}
} else {
folio = *foliop;
VM_BUG_ON_FOLIO(folio_test_large(folio), folio);
*foliop = NULL;
}
VM_BUG_ON(folio_test_locked(folio));
VM_BUG_ON(folio_test_swapbacked(folio));
__folio_set_locked(folio);
__folio_set_swapbacked(folio);
__folio_mark_uptodate(folio);
ret = -EFAULT;
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
if (unlikely(pgoff >= max_off))
goto out_release;
ret = mem_cgroup_charge(folio, dst_vma->vm_mm, gfp);
if (ret)
goto out_release;
ret = shmem_add_to_page_cache(folio, mapping, pgoff, NULL, gfp);
if (ret)
goto out_release;
ret = mfill_atomic_install_pte(dst_pmd, dst_vma, dst_addr,
&folio->page, true, flags);
if (ret)
goto out_delete_from_cache;
shmem_recalc_inode(inode, 1, 0);
folio_unlock(folio);
return 0;
out_delete_from_cache:
filemap_remove_folio(folio);
out_release:
folio_unlock(folio);
folio_put(folio);
out_unacct_blocks:
shmem_inode_unacct_blocks(inode, 1);
return ret;
}
#endif /* CONFIG_USERFAULTFD */
#ifdef CONFIG_TMPFS
static const struct inode_operations shmem_symlink_inode_operations;
static const struct inode_operations shmem_short_symlink_operations;
static int
shmem_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t index = pos >> PAGE_SHIFT;
struct folio *folio;
int ret = 0;
/* i_rwsem is held by caller */
if (unlikely(info->seals & (F_SEAL_GROW |
F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))) {
if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE))
return -EPERM;
if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
return -EPERM;
}
ret = shmem_get_folio(inode, index, &folio, SGP_WRITE);
if (ret)
return ret;
*pagep = folio_file_page(folio, index);
if (PageHWPoison(*pagep)) {
folio_unlock(folio);
folio_put(folio);
*pagep = NULL;
return -EIO;
}
return 0;
}
static int
shmem_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct folio *folio = page_folio(page);
struct inode *inode = mapping->host;
if (pos + copied > inode->i_size)
i_size_write(inode, pos + copied);
if (!folio_test_uptodate(folio)) {
if (copied < folio_size(folio)) {
size_t from = offset_in_folio(folio, pos);
folio_zero_segments(folio, 0, from,
from + copied, folio_size(folio));
}
folio_mark_uptodate(folio);
}
folio_mark_dirty(folio);
folio_unlock(folio);
folio_put(folio);
return copied;
}
static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
pgoff_t index;
unsigned long offset;
int error = 0;
ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
index = *ppos >> PAGE_SHIFT;
offset = *ppos & ~PAGE_MASK;
for (;;) {
struct folio *folio = NULL;
struct page *page = NULL;
pgoff_t end_index;
unsigned long nr, ret;
loff_t i_size = i_size_read(inode);
end_index = i_size >> PAGE_SHIFT;
if (index > end_index)
break;
if (index == end_index) {
nr = i_size & ~PAGE_MASK;
if (nr <= offset)
break;
}
error = shmem_get_folio(inode, index, &folio, SGP_READ);
if (error) {
if (error == -EINVAL)
error = 0;
break;
}
if (folio) {
folio_unlock(folio);
page = folio_file_page(folio, index);
if (PageHWPoison(page)) {
folio_put(folio);
error = -EIO;
break;
}
}
/*
* We must evaluate after, since reads (unlike writes)
* are called without i_rwsem protection against truncate
*/
nr = PAGE_SIZE;
i_size = i_size_read(inode);
end_index = i_size >> PAGE_SHIFT;
if (index == end_index) {
nr = i_size & ~PAGE_MASK;
if (nr <= offset) {
if (folio)
folio_put(folio);
break;
}
}
nr -= offset;
if (folio) {
/*
* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
/*
* Mark the page accessed if we read the beginning.
*/
if (!offset)
folio_mark_accessed(folio);
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*/
ret = copy_page_to_iter(page, offset, nr, to);
folio_put(folio);
} else if (user_backed_iter(to)) {
/*
* Copy to user tends to be so well optimized, but
* clear_user() not so much, that it is noticeably
* faster to copy the zero page instead of clearing.
*/
ret = copy_page_to_iter(ZERO_PAGE(0), offset, nr, to);
} else {
/*
* But submitting the same page twice in a row to
* splice() - or others? - can result in confusion:
* so don't attempt that optimization on pipes etc.
*/
ret = iov_iter_zero(nr, to);
}
retval += ret;
offset += ret;
index += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
if (!iov_iter_count(to))
break;
if (ret < nr) {
error = -EFAULT;
break;
}
cond_resched();
}
*ppos = ((loff_t) index << PAGE_SHIFT) + offset;
file_accessed(file);
return retval ? retval : error;
}
static ssize_t shmem_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
ssize_t ret;
inode_lock(inode);
ret = generic_write_checks(iocb, from);
if (ret <= 0)
goto unlock;
ret = file_remove_privs(file);
if (ret)
goto unlock;
ret = file_update_time(file);
if (ret)
goto unlock;
ret = generic_perform_write(iocb, from);
unlock:
inode_unlock(inode);
return ret;
}
static bool zero_pipe_buf_get(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
return true;
}
static void zero_pipe_buf_release(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
}
static bool zero_pipe_buf_try_steal(struct pipe_inode_info *pipe,
struct pipe_buffer *buf)
{
return false;
}
static const struct pipe_buf_operations zero_pipe_buf_ops = {
.release = zero_pipe_buf_release,
.try_steal = zero_pipe_buf_try_steal,
.get = zero_pipe_buf_get,
};
static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe,
loff_t fpos, size_t size)
{
size_t offset = fpos & ~PAGE_MASK;
size = min_t(size_t, size, PAGE_SIZE - offset);
if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
struct pipe_buffer *buf = pipe_head_buf(pipe);
*buf = (struct pipe_buffer) {
.ops = &zero_pipe_buf_ops,
.page = ZERO_PAGE(0),
.offset = offset,
.len = size,
};
pipe->head++;
}
return size;
}
static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe,
size_t len, unsigned int flags)