blob: e67d6ba4e98e73210c8046e82612180fca220e89 [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/mm.h>
#include <linux/sched/signal.h>
#include <linux/export.h>
#include <linux/swap.h>
#include <linux/uio.h>
#include <linux/khugepaged.h>
#include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
static struct vfsmount *shm_mnt;
#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/shmem_fs.h>
#include <linux/writeback.h>
#include <linux/blkdev.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/userfaultfd_k.h>
#include <linux/rmap.h>
#include <linux/uaccess.h>
#include <asm/pgtable.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
/* 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_mutex 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 */
};
#ifdef CONFIG_TMPFS
static unsigned long shmem_default_max_blocks(void)
{
return totalram_pages / 2;
}
static unsigned long shmem_default_max_inodes(void)
{
return min(totalram_pages - totalhigh_pages, totalram_pages / 2);
}
#endif
static bool shmem_should_replace_page(struct page *page, gfp_t gfp);
static int shmem_replace_page(struct page **pagep, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index);
static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp,
gfp_t gfp, struct vm_area_struct *vma,
struct vm_fault *vmf, int *fault_type);
int shmem_getpage(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp)
{
return shmem_getpage_gfp(inode, index, pagep, sgp,
mapping_gfp_mask(inode->i_mapping), NULL, NULL, NULL);
}
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_getpage reports shmem_acct_block failure as -ENOSPC not -ENOMEM,
* so that a failure on a sparse tmpfs mapping will give SIGBUS not OOM.
*/
static inline int shmem_acct_block(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 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 struct file_system_type shmem_fs_type;
bool vma_is_shmem(struct vm_area_struct *vma)
{
return vma->vm_ops == &shmem_vm_ops;
}
static LIST_HEAD(shmem_swaplist);
static DEFINE_MUTEX(shmem_swaplist_mutex);
static int shmem_reserve_inode(struct super_block *sb)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (sbinfo->max_inodes) {
spin_lock(&sbinfo->stat_lock);
if (!sbinfo->free_inodes) {
spin_unlock(&sbinfo->stat_lock);
return -ENOSPC;
}
sbinfo->free_inodes--;
spin_unlock(&sbinfo->stat_lock);
}
return 0;
}
static void shmem_free_inode(struct super_block *sb)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (sbinfo->max_inodes) {
spin_lock(&sbinfo->stat_lock);
sbinfo->free_inodes++;
spin_unlock(&sbinfo->stat_lock);
}
}
/**
* shmem_recalc_inode - recalculate the block usage of an inode
* @inode: inode to recalc
*
* 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)
*
* It has to be called with the spinlock held.
*/
static void shmem_recalc_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
long freed;
freed = info->alloced - info->swapped - inode->i_mapping->nrpages;
if (freed > 0) {
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -freed);
info->alloced -= freed;
inode->i_blocks -= freed * BLOCKS_PER_PAGE;
shmem_unacct_blocks(info->flags, freed);
}
}
bool shmem_charge(struct inode *inode, long pages)
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
unsigned long flags;
if (shmem_acct_block(info->flags, pages))
return false;
spin_lock_irqsave(&info->lock, flags);
info->alloced += pages;
inode->i_blocks += pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
inode->i_mapping->nrpages += pages;
if (!sbinfo->max_blocks)
return true;
if (percpu_counter_compare(&sbinfo->used_blocks,
sbinfo->max_blocks - pages) > 0) {
inode->i_mapping->nrpages -= pages;
spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
shmem_unacct_blocks(info->flags, pages);
return false;
}
percpu_counter_add(&sbinfo->used_blocks, pages);
return true;
}
void shmem_uncharge(struct inode *inode, long pages)
{
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
unsigned long flags;
spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
inode->i_blocks -= pages * BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock_irqrestore(&info->lock, flags);
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks, pages);
shmem_unacct_blocks(info->flags, pages);
}
/*
* Replace item expected in radix tree by a new item, while holding tree lock.
*/
static int shmem_radix_tree_replace(struct address_space *mapping,
pgoff_t index, void *expected, void *replacement)
{
struct radix_tree_node *node;
void **pslot;
void *item;
VM_BUG_ON(!expected);
VM_BUG_ON(!replacement);
item = __radix_tree_lookup(&mapping->page_tree, index, &node, &pslot);
if (!item)
return -ENOENT;
if (item != expected)
return -ENOENT;
__radix_tree_replace(&mapping->page_tree, node, pslot,
replacement, NULL, NULL);
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)
{
void *item;
rcu_read_lock();
item = radix_tree_lookup(&mapping->page_tree, index);
rcu_read_unlock();
return item == 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_HUGE_PAGECACHE
/* ifdef here to avoid bloating shmem.o when not necessary */
int shmem_huge __read_mostly;
#if defined(CONFIG_SYSFS) || defined(CONFIG_TMPFS)
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;
}
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 page *page;
unsigned long batch = sc ? sc->nr_to_scan : 128;
int removed = 0, 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);
removed++;
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);
removed++;
goto next;
}
list_move(&info->shrinklist, &list);
next:
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;
info = list_entry(pos, struct shmem_inode_info, shrinklist);
inode = &info->vfs_inode;
if (nr_to_split && split >= nr_to_split) {
iput(inode);
continue;
}
page = find_lock_page(inode->i_mapping,
(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
if (!page)
goto drop;
if (!PageTransHuge(page)) {
unlock_page(page);
put_page(page);
goto drop;
}
ret = split_huge_page(page);
unlock_page(page);
put_page(page);
if (ret) {
/* split failed: leave it on the list */
iput(inode);
continue;
}
split++;
drop:
list_del_init(&info->shrinklist);
removed++;
iput(inode);
}
spin_lock(&sbinfo->shrinklist_lock);
list_splice_tail(&list, &sbinfo->shrinklist);
sbinfo->shrinklist_len -= removed;
spin_unlock(&sbinfo->shrinklist_lock);
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_HUGE_PAGECACHE */
#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_HUGE_PAGECACHE */
/*
* Like add_to_page_cache_locked, but error if expected item has gone.
*/
static int shmem_add_to_page_cache(struct page *page,
struct address_space *mapping,
pgoff_t index, void *expected)
{
int error, nr = hpage_nr_pages(page);
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page);
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
VM_BUG_ON(expected && PageTransHuge(page));
page_ref_add(page, nr);
page->mapping = mapping;
page->index = index;
spin_lock_irq(&mapping->tree_lock);
if (PageTransHuge(page)) {
void __rcu **results;
pgoff_t idx;
int i;
error = 0;
if (radix_tree_gang_lookup_slot(&mapping->page_tree,
&results, &idx, index, 1) &&
idx < index + HPAGE_PMD_NR) {
error = -EEXIST;
}
if (!error) {
for (i = 0; i < HPAGE_PMD_NR; i++) {
error = radix_tree_insert(&mapping->page_tree,
index + i, page + i);
VM_BUG_ON(error);
}
count_vm_event(THP_FILE_ALLOC);
}
} else if (!expected) {
error = radix_tree_insert(&mapping->page_tree, index, page);
} else {
error = shmem_radix_tree_replace(mapping, index, expected,
page);
}
if (!error) {
mapping->nrpages += nr;
if (PageTransHuge(page))
__inc_node_page_state(page, NR_SHMEM_THPS);
__mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr);
__mod_node_page_state(page_pgdat(page), NR_SHMEM, nr);
spin_unlock_irq(&mapping->tree_lock);
} else {
page->mapping = NULL;
spin_unlock_irq(&mapping->tree_lock);
page_ref_sub(page, nr);
}
return error;
}
/*
* Like delete_from_page_cache, but substitutes swap for page.
*/
static void shmem_delete_from_page_cache(struct page *page, void *radswap)
{
struct address_space *mapping = page->mapping;
int error;
VM_BUG_ON_PAGE(PageCompound(page), page);
spin_lock_irq(&mapping->tree_lock);
error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
page->mapping = NULL;
mapping->nrpages--;
__dec_node_page_state(page, NR_FILE_PAGES);
__dec_node_page_state(page, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
put_page(page);
BUG_ON(error);
}
/*
* Remove swap entry from radix tree, free the swap and its page cache.
*/
static int shmem_free_swap(struct address_space *mapping,
pgoff_t index, void *radswap)
{
void *old;
spin_lock_irq(&mapping->tree_lock);
old = radix_tree_delete_item(&mapping->page_tree, index, radswap);
spin_unlock_irq(&mapping->tree_lock);
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_mutex or mapping->tree_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)
{
struct radix_tree_iter iter;
void **slot;
struct page *page;
unsigned long swapped = 0;
rcu_read_lock();
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
if (iter.index >= end)
break;
page = radix_tree_deref_slot(slot);
if (radix_tree_deref_retry(page)) {
slot = radix_tree_iter_retry(&iter);
continue;
}
if (radix_tree_exceptional_entry(page))
swapped++;
if (need_resched()) {
slot = radix_tree_iter_resume(slot, &iter);
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_mutex or mapping->tree_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,
linear_page_index(vma, vma->vm_start),
linear_page_index(vma, vma->vm_end));
}
/*
* SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
*/
void shmem_unlock_mapping(struct address_space *mapping)
{
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
pgoff_t index = 0;
pagevec_init(&pvec, 0);
/*
* Minor point, but we might as well stop if someone else SHM_LOCKs it.
*/
while (!mapping_unevictable(mapping)) {
/*
* Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
* has finished, if it hits a row of PAGEVEC_SIZE swap entries.
*/
pvec.nr = find_get_entries(mapping, index,
PAGEVEC_SIZE, pvec.pages, indices);
if (!pvec.nr)
break;
index = indices[pvec.nr - 1] + 1;
pagevec_remove_exceptionals(&pvec);
check_move_unevictable_pages(pvec.pages, pvec.nr);
pagevec_release(&pvec);
cond_resched();
}
}
/*
* Remove range of pages and swap entries from radix tree, 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;
unsigned int partial_start = lstart & (PAGE_SIZE - 1);
unsigned int partial_end = (lend + 1) & (PAGE_SIZE - 1);
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
long nr_swaps_freed = 0;
pgoff_t index;
int i;
if (lend == -1)
end = -1; /* unsigned, so actually very big */
pagevec_init(&pvec, 0);
index = start;
while (index < end) {
pvec.nr = find_get_entries(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr)
break;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
index = indices[i];
if (index >= end)
break;
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
nr_swaps_freed += !shmem_free_swap(mapping,
index, page);
continue;
}
VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page);
if (!trylock_page(page))
continue;
if (PageTransTail(page)) {
/* Middle of THP: zero out the page */
clear_highpage(page);
unlock_page(page);
continue;
} else if (PageTransHuge(page)) {
if (index == round_down(end, HPAGE_PMD_NR)) {
/*
* Range ends in the middle of THP:
* zero out the page
*/
clear_highpage(page);
unlock_page(page);
continue;
}
index += HPAGE_PMD_NR - 1;
i += HPAGE_PMD_NR - 1;
}
if (!unfalloc || !PageUptodate(page)) {
VM_BUG_ON_PAGE(PageTail(page), page);
if (page_mapping(page) == mapping) {
VM_BUG_ON_PAGE(PageWriteback(page), page);
truncate_inode_page(mapping, page);
}
}
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
cond_resched();
index++;
}
if (partial_start) {
struct page *page = NULL;
shmem_getpage(inode, start - 1, &page, SGP_READ);
if (page) {
unsigned int top = PAGE_SIZE;
if (start > end) {
top = partial_end;
partial_end = 0;
}
zero_user_segment(page, partial_start, top);
set_page_dirty(page);
unlock_page(page);
put_page(page);
}
}
if (partial_end) {
struct page *page = NULL;
shmem_getpage(inode, end, &page, SGP_READ);
if (page) {
zero_user_segment(page, 0, partial_end);
set_page_dirty(page);
unlock_page(page);
put_page(page);
}
}
if (start >= end)
return;
index = start;
while (index < end) {
cond_resched();
pvec.nr = find_get_entries(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr) {
/* 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 < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
index = indices[i];
if (index >= end)
break;
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
if (shmem_free_swap(mapping, index, page)) {
/* Swap was replaced by page: retry */
index--;
break;
}
nr_swaps_freed++;
continue;
}
lock_page(page);
if (PageTransTail(page)) {
/* Middle of THP: zero out the page */
clear_highpage(page);
unlock_page(page);
/*
* Partial thp truncate due 'start' in middle
* of THP: don't need to look on these pages
* again on !pvec.nr restart.
*/
if (index != round_down(end, HPAGE_PMD_NR))
start++;
continue;
} else if (PageTransHuge(page)) {
if (index == round_down(end, HPAGE_PMD_NR)) {
/*
* Range ends in the middle of THP:
* zero out the page
*/
clear_highpage(page);
unlock_page(page);
continue;
}
index += HPAGE_PMD_NR - 1;
i += HPAGE_PMD_NR - 1;
}
if (!unfalloc || !PageUptodate(page)) {
VM_BUG_ON_PAGE(PageTail(page), page);
if (page_mapping(page) == mapping) {
VM_BUG_ON_PAGE(PageWriteback(page), page);
truncate_inode_page(mapping, page);
} else {
/* Page was replaced by swap: retry */
unlock_page(page);
index--;
break;
}
}
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
index++;
}
spin_lock_irq(&info->lock);
info->swapped -= nr_swaps_freed;
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
}
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
shmem_undo_range(inode, lstart, lend, false);
inode->i_ctime = inode->i_mtime = current_time(inode);
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
static int shmem_getattr(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) {
spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
}
generic_fillattr(inode, stat);
return 0;
}
static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
int error;
error = setattr_prepare(dentry, attr);
if (error)
return error;
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_mutex */
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);
inode->i_ctime = inode->i_mtime = current_time(inode);
}
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);
/*
* Part of the huge page can be beyond i_size: subject
* to shrink under memory pressure.
*/
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) {
spin_lock(&sbinfo->shrinklist_lock);
if (list_empty(&info->shrinklist)) {
list_add_tail(&info->shrinklist,
&sbinfo->shrinklist);
sbinfo->shrinklist_len++;
}
spin_unlock(&sbinfo->shrinklist_lock);
}
}
}
setattr_copy(inode, attr);
if (attr->ia_valid & ATTR_MODE)
error = posix_acl_chmod(inode, inode->i_mode);
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);
if (inode->i_mapping->a_ops == &shmem_aops) {
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
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);
}
if (!list_empty(&info->swaplist)) {
mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
}
}
simple_xattrs_free(&info->xattrs);
WARN_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
clear_inode(inode);
}
static unsigned long find_swap_entry(struct radix_tree_root *root, void *item)
{
struct radix_tree_iter iter;
void **slot;
unsigned long found = -1;
unsigned int checked = 0;
rcu_read_lock();
radix_tree_for_each_slot(slot, root, &iter, 0) {
if (*slot == item) {
found = iter.index;
break;
}
checked++;
if ((checked % 4096) != 0)
continue;
slot = radix_tree_iter_resume(slot, &iter);
cond_resched_rcu();
}
rcu_read_unlock();
return found;
}
/*
* If swap found in inode, free it and move page from swapcache to filecache.
*/
static int shmem_unuse_inode(struct shmem_inode_info *info,
swp_entry_t swap, struct page **pagep)
{
struct address_space *mapping = info->vfs_inode.i_mapping;
void *radswap;
pgoff_t index;
gfp_t gfp;
int error = 0;
radswap = swp_to_radix_entry(swap);
index = find_swap_entry(&mapping->page_tree, radswap);
if (index == -1)
return -EAGAIN; /* tell shmem_unuse we found nothing */
/*
* Move _head_ to start search for next from here.
* But be careful: shmem_evict_inode checks list_empty without taking
* mutex, and there's an instant in list_move_tail when info->swaplist
* would appear empty, if it were the only one on shmem_swaplist.
*/
if (shmem_swaplist.next != &info->swaplist)
list_move_tail(&shmem_swaplist, &info->swaplist);
gfp = mapping_gfp_mask(mapping);
if (shmem_should_replace_page(*pagep, gfp)) {
mutex_unlock(&shmem_swaplist_mutex);
error = shmem_replace_page(pagep, gfp, info, index);
mutex_lock(&shmem_swaplist_mutex);
/*
* We needed to drop mutex to make that restrictive page
* allocation, but the inode might have been freed while we
* dropped it: although a racing shmem_evict_inode() cannot
* complete without emptying the radix_tree, our page lock
* on this swapcache page is not enough to prevent that -
* free_swap_and_cache() of our swap entry will only
* trylock_page(), removing swap from radix_tree whatever.
*
* We must not proceed to shmem_add_to_page_cache() if the
* inode has been freed, but of course we cannot rely on
* inode or mapping or info to check that. However, we can
* safely check if our swap entry is still in use (and here
* it can't have got reused for another page): if it's still
* in use, then the inode cannot have been freed yet, and we
* can safely proceed (if it's no longer in use, that tells
* nothing about the inode, but we don't need to unuse swap).
*/
if (!page_swapcount(*pagep))
error = -ENOENT;
}
/*
* We rely on shmem_swaplist_mutex, not only to protect the swaplist,
* but also to hold up shmem_evict_inode(): so inode cannot be freed
* beneath us (pagelock doesn't help until the page is in pagecache).
*/
if (!error)
error = shmem_add_to_page_cache(*pagep, mapping, index,
radswap);
if (error != -ENOMEM) {
/*
* Truncation and eviction use free_swap_and_cache(), which
* only does trylock page: if we raced, best clean up here.
*/
delete_from_swap_cache(*pagep);
set_page_dirty(*pagep);
if (!error) {
spin_lock_irq(&info->lock);
info->swapped--;
spin_unlock_irq(&info->lock);
swap_free(swap);
}
}
return error;
}
/*
* Search through swapped inodes to find and replace swap by page.
*/
int shmem_unuse(swp_entry_t swap, struct page *page)
{
struct list_head *this, *next;
struct shmem_inode_info *info;
struct mem_cgroup *memcg;
int error = 0;
/*
* There's a faint possibility that swap page was replaced before
* caller locked it: caller will come back later with the right page.
*/
if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val))
goto out;
/*
* Charge page using GFP_KERNEL while we can wait, before taking
* the shmem_swaplist_mutex which might hold up shmem_writepage().
* Charged back to the user (not to caller) when swap account is used.
*/
error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg,
false);
if (error)
goto out;
/* No radix_tree_preload: swap entry keeps a place for page in tree */
error = -EAGAIN;
mutex_lock(&shmem_swaplist_mutex);
list_for_each_safe(this, next, &shmem_swaplist) {
info = list_entry(this, struct shmem_inode_info, swaplist);
if (info->swapped)
error = shmem_unuse_inode(info, swap, &page);
else
list_del_init(&info->swaplist);
cond_resched();
if (error != -EAGAIN)
break;
/* found nothing in this: move on to search the next */
}
mutex_unlock(&shmem_swaplist_mutex);
if (error) {
if (error != -ENOMEM)
error = 0;
mem_cgroup_cancel_charge(page, memcg, false);
} else
mem_cgroup_commit_charge(page, memcg, true, false);
out:
unlock_page(page);
put_page(page);
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 shmem_inode_info *info;
struct address_space *mapping;
struct inode *inode;
swp_entry_t swap;
pgoff_t index;
VM_BUG_ON_PAGE(PageCompound(page), page);
BUG_ON(!PageLocked(page));
mapping = page->mapping;
index = page->index;
inode = mapping->host;
info = SHMEM_I(inode);
if (info->flags & VM_LOCKED)
goto redirty;
if (!total_swap_pages)
goto redirty;
/*
* 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 (!wbc->for_reclaim) {
WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
goto redirty;
}
/*
* 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 page arriving here is now to initialize it and write it.
*
* That's okay for a page already fallocated earlier, but if we have
* not yet completed the fallocation, then (a) we want to keep track
* of this page 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 page, and let shmem_fallocate() quit when too many.
*/
if (!PageUptodate(page)) {
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;
}
clear_highpage(page);
flush_dcache_page(page);
SetPageUptodate(page);
}
swap = get_swap_page();
if (!swap.val)
goto redirty;
if (mem_cgroup_try_charge_swap(page, swap))
goto free_swap;
/*
* Add inode to shmem_unuse()'s list of swapped-out inodes,
* if it's not already there. Do it now before the page 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_tail(&info->swaplist, &shmem_swaplist);
if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
info->swapped++;
spin_unlock_irq(&info->lock);
swap_shmem_alloc(swap);
shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
mutex_unlock(&shmem_swaplist_mutex);
BUG_ON(page_mapped(page));
swap_writepage(page, wbc);
return 0;
}
mutex_unlock(&shmem_swaplist_mutex);
free_swap:
swapcache_free(swap);
redirty:
set_page_dirty(page);
if (wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */
unlock_page(page);
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) {
spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */
mpol = sbinfo->mpol;
mpol_get(mpol);
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 */
#ifndef CONFIG_NUMA
#define vm_policy vm_private_data
#endif
static void shmem_pseudo_vma_init(struct vm_area_struct *vma,
struct shmem_inode_info *info, pgoff_t index)
{
/* Create a pseudo vma that just contains the policy */
vma->vm_start = 0;
/* Bias interleave by inode number to distribute better across nodes */
vma->vm_pgoff = index + info->vfs_inode.i_ino;
vma->vm_ops = NULL;
vma->vm_policy = mpol_shared_policy_lookup(&info->policy, index);
}
static void shmem_pseudo_vma_destroy(struct vm_area_struct *vma)
{
/* Drop reference taken by mpol_shared_policy_lookup() */
mpol_cond_put(vma->vm_policy);
}
static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
struct page *page;
shmem_pseudo_vma_init(&pvma, info, index);
page = swapin_readahead(swap, gfp, &pvma, 0);
shmem_pseudo_vma_destroy(&pvma);
return page;
}
static struct page *shmem_alloc_hugepage(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
struct inode *inode = &info->vfs_inode;
struct address_space *mapping = inode->i_mapping;
pgoff_t idx, hindex;
void __rcu **results;
struct page *page;
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
return NULL;
hindex = round_down(index, HPAGE_PMD_NR);
rcu_read_lock();
if (radix_tree_gang_lookup_slot(&mapping->page_tree, &results, &idx,
hindex, 1) && idx < hindex + HPAGE_PMD_NR) {
rcu_read_unlock();
return NULL;
}
rcu_read_unlock();
shmem_pseudo_vma_init(&pvma, info, hindex);
page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
shmem_pseudo_vma_destroy(&pvma);
if (page)
prep_transhuge_page(page);
return page;
}
static struct page *shmem_alloc_page(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
struct page *page;
shmem_pseudo_vma_init(&pvma, info, index);
page = alloc_page_vma(gfp, &pvma, 0);
shmem_pseudo_vma_destroy(&pvma);
return page;
}
static struct page *shmem_alloc_and_acct_page(gfp_t gfp,
struct shmem_inode_info *info, struct shmem_sb_info *sbinfo,
pgoff_t index, bool huge)
{
struct page *page;
int nr;
int err = -ENOSPC;
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
huge = false;
nr = huge ? HPAGE_PMD_NR : 1;
if (shmem_acct_block(info->flags, nr))
goto failed;
if (sbinfo->max_blocks) {
if (percpu_counter_compare(&sbinfo->used_blocks,
sbinfo->max_blocks - nr) > 0)
goto unacct;
percpu_counter_add(&sbinfo->used_blocks, nr);
}
if (huge)
page = shmem_alloc_hugepage(gfp, info, index);
else
page = shmem_alloc_page(gfp, info, index);
if (page) {
__SetPageLocked(page);
__SetPageSwapBacked(page);
return page;
}
err = -ENOMEM;
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -nr);
unacct:
shmem_unacct_blocks(info->flags, nr);
failed:
return ERR_PTR(err);
}
/*
* When a page is moved from swapcache to shmem filecache (either by the
* usual swapin of shmem_getpage_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_page(struct page *page, gfp_t gfp)
{
return page_zonenum(page) > gfp_zone(gfp);
}
static int shmem_replace_page(struct page **pagep, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct page *oldpage, *newpage;
struct address_space *swap_mapping;
pgoff_t swap_index;
int error;
oldpage = *pagep;
swap_index = page_private(oldpage);
swap_mapping = page_mapping(oldpage);
/*
* 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;
newpage = shmem_alloc_page(gfp, info, index);
if (!newpage)
return -ENOMEM;
get_page(newpage);
copy_highpage(newpage, oldpage);
flush_dcache_page(newpage);
__SetPageLocked(newpage);
__SetPageSwapBacked(newpage);
SetPageUptodate(newpage);
set_page_private(newpage, swap_index);
SetPageSwapCache(newpage);
/*
* 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.
*/
spin_lock_irq(&swap_mapping->tree_lock);
error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
newpage);
if (!error) {
__inc_node_page_state(newpage, NR_FILE_PAGES);
__dec_node_page_state(oldpage, NR_FILE_PAGES);
}
spin_unlock_irq(&swap_mapping->tree_lock);
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.
*/
oldpage = newpage;
} else {
mem_cgroup_migrate(oldpage, newpage);
lru_cache_add_anon(newpage);
*pagep = newpage;
}
ClearPageSwapCache(oldpage);
set_page_private(oldpage, 0);
unlock_page(oldpage);
put_page(oldpage);
put_page(oldpage);
return error;
}
/*
* shmem_getpage_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.
*
* fault_mm and fault_type are only supplied by shmem_fault:
* otherwise they are NULL.
*/
static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp, gfp_t gfp,
struct vm_area_struct *vma, struct vm_fault *vmf, int *fault_type)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo;
struct mm_struct *charge_mm;
struct mem_cgroup *memcg;
struct page *page;
swp_entry_t swap;
enum sgp_type sgp_huge = sgp;
pgoff_t hindex = index;
int error;
int once = 0;
int alloced = 0;
if (index > (MAX_LFS_FILESIZE >> PAGE_SHIFT))
return -EFBIG;
if (sgp == SGP_NOHUGE || sgp == SGP_HUGE)
sgp = SGP_CACHE;
repeat:
swap.val = 0;
page = find_lock_entry(mapping, index);
if (radix_tree_exceptional_entry(page)) {
swap = radix_to_swp_entry(page);
page = NULL;
}
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
goto unlock;
}
if (page && sgp == SGP_WRITE)
mark_page_accessed(page);
/* fallocated page? */
if (page && !PageUptodate(page)) {
if (sgp != SGP_READ)
goto clear;
unlock_page(page);
put_page(page);
page = NULL;
}
if (page || (sgp == SGP_READ && !swap.val)) {
*pagep = page;
return 0;
}
/*
* Fast cache lookup did not find it:
* bring it back from swap or allocate.
*/
sbinfo = SHMEM_SB(inode->i_sb);
charge_mm = vma ? vma->vm_mm : current->mm;
if (swap.val) {
/* Look it up and read it in.. */
page = lookup_swap_cache(swap);
if (!page) {
/* Or update major stats only when swapin succeeds?? */
if (fault_type) {
*fault_type |= VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(charge_mm,
PGMAJFAULT);
}
/* Here we actually start the io */
page = shmem_swapin(swap, gfp, info, index);
if (!page) {
error = -ENOMEM;
goto failed;
}
}
/* We have to do this with page locked to prevent races */
lock_page(page);
if (!PageSwapCache(page) || page_private(page) != swap.val ||
!shmem_confirm_swap(mapping, index, swap)) {
error = -EEXIST; /* try again */
goto unlock;
}
if (!PageUptodate(page)) {
error = -EIO;
goto failed;
}
wait_on_page_writeback(page);
if (shmem_should_replace_page(page, gfp)) {
error = shmem_replace_page(&page, gfp, info, index);
if (error)
goto failed;
}
error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
false);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
swp_to_radix_entry(swap));
/*
* We already confirmed swap under page lock, and make
* no memory allocation here, so usually no possibility
* of error; but free_swap_and_cache() only trylocks a
* page, so it is just possible that the entry has been
* truncated or holepunched since swap was confirmed.
* shmem_undo_range() will have done some of the
* unaccounting, now delete_from_swap_cache() will do
* the rest.
* Reset swap.val? No, leave it so "failed" goes back to
* "repeat": reading a hole and writing should succeed.
*/
if (error) {
mem_cgroup_cancel_charge(page, memcg, false);
delete_from_swap_cache(page);
}
}
if (error)
goto failed;
mem_cgroup_commit_charge(page, memcg, true, false);
spin_lock_irq(&info->lock);
info->swapped--;
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
if (sgp == SGP_WRITE)
mark_page_accessed(page);
delete_from_swap_cache(page);
set_page_dirty(page);
swap_free(swap);
} else {
if (vma && userfaultfd_missing(vma)) {
*fault_type = handle_userfault(vmf, VM_UFFD_MISSING);
return 0;
}
/* shmem_symlink() */
if (mapping->a_ops != &shmem_aops)
goto alloc_nohuge;
if (shmem_huge == SHMEM_HUGE_DENY || sgp_huge == SGP_NOHUGE)
goto alloc_nohuge;
if (shmem_huge == SHMEM_HUGE_FORCE)
goto alloc_huge;
switch (sbinfo->huge) {
loff_t i_size;
pgoff_t off;
case SHMEM_HUGE_NEVER:
goto alloc_nohuge;
case SHMEM_HUGE_WITHIN_SIZE:
off = round_up(index, HPAGE_PMD_NR);
i_size = round_up(i_size_read(inode), PAGE_SIZE);
if (i_size >= HPAGE_PMD_SIZE &&
i_size >> PAGE_SHIFT >= off)
goto alloc_huge;
/* fallthrough */
case SHMEM_HUGE_ADVISE:
if (sgp_huge == SGP_HUGE)
goto alloc_huge;
/* TODO: implement fadvise() hints */
goto alloc_nohuge;
}
alloc_huge:
page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
index, true);
if (IS_ERR(page)) {
alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, info, sbinfo,
index, false);
}
if (IS_ERR(page)) {
int retry = 5;
error = PTR_ERR(page);
page = NULL;
if (error != -ENOSPC)
goto failed;
/*
* Try to reclaim some spece by splitting a huge page
* beyond i_size on the filesystem.
*/
while (retry--) {
int ret;
ret = shmem_unused_huge_shrink(sbinfo, NULL, 1);
if (ret == SHRINK_STOP)
break;
if (ret)
goto alloc_nohuge;
}
goto failed;
}
if (PageTransHuge(page))
hindex = round_down(index, HPAGE_PMD_NR);
else
hindex = index;
if (sgp == SGP_WRITE)
__SetPageReferenced(page);
error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
PageTransHuge(page));
if (error)
goto unacct;
error = radix_tree_maybe_preload_order(gfp & GFP_RECLAIM_MASK,
compound_order(page));
if (!error) {
error = shmem_add_to_page_cache(page, mapping, hindex,
NULL);
radix_tree_preload_end();
}
if (error) {
mem_cgroup_cancel_charge(page, memcg,
PageTransHuge(page));
goto unacct;
}
mem_cgroup_commit_charge(page, memcg, false,
PageTransHuge(page));
lru_cache_add_anon(page);
spin_lock_irq(&info->lock);
info->alloced += 1 << compound_order(page);
inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
alloced = true;
if (PageTransHuge(page) &&
DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE) <
hindex + HPAGE_PMD_NR - 1) {
/*
* Part of the huge page is beyond i_size: subject
* to shrink under memory pressure.
*/
spin_lock(&sbinfo->shrinklist_lock);
if (list_empty(&info->shrinklist)) {
list_add_tail(&info->shrinklist,
&sbinfo->shrinklist);
sbinfo->shrinklist_len++;
}
spin_unlock(&sbinfo->shrinklist_lock);
}
/*
* Let SGP_FALLOC use the SGP_WRITE optimization on a new page.
*/
if (sgp == SGP_FALLOC)
sgp = SGP_WRITE;
clear:
/*
* Let SGP_WRITE caller clear ends if write does not fill page;
* but SGP_FALLOC on a page fallocated earlier must initialize
* it now, lest undo on failure cancel our earlier guarantee.
*/
if (sgp != SGP_WRITE && !PageUptodate(page)) {
struct page *head = compound_head(page);
int i;
for (i = 0; i < (1 << compound_order(head)); i++) {
clear_highpage(head + i);
flush_dcache_page(head + i);
}
SetPageUptodate(head);
}
}
/* Perhaps the file has been truncated since we checked */
if (sgp <= SGP_CACHE &&
((loff_t)index << PAGE_SHIFT) >= i_size_read(inode)) {
if (alloced) {
ClearPageDirty(page);
delete_from_page_cache(page);
spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
}
error = -EINVAL;
goto unlock;
}
*pagep = page + index - hindex;
return 0;
/*
* Error recovery.
*/
unacct:
if (sbinfo->max_blocks)
percpu_counter_sub(&sbinfo->used_blocks,
1 << compound_order(page));
shmem_unacct_blocks(info->flags, 1 << compound_order(page));
if (PageTransHuge(page)) {
unlock_page(page);
put_page(page);
goto alloc_nohuge;
}
failed:
if (swap.val && !shmem_confirm_swap(mapping, index, swap))
error = -EEXIST;
unlock:
if (page) {
unlock_page(page);
put_page(page);
}
if (error == -ENOSPC && !once++) {
spin_lock_irq(&info->lock);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
goto repeat;
}
if (error == -EEXIST) /* from above or from radix_tree_insert */
goto repeat;
return error;
}
/*
* 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_t *wait, unsigned mode, int sync, void *key)
{
int ret = default_wake_function(wait, mode, sync, key);
list_del_init(&wait->task_list);
return ret;
}
static int shmem_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct inode *inode = file_inode(vma->vm_file);
gfp_t gfp = mapping_gfp_mask(inode->i_mapping);
enum sgp_type sgp;
int error;
int ret = VM_FAULT_LOCKED;
/*
* 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_mutex. 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_mutex in fault,
* and bloating every shmem inode for this unlikely case would be sad.
*/
if (unlikely(inode->i_private)) {
struct shmem_falloc *shmem_falloc;
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;
if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
/* It's polite to up mmap_sem if we can */
up_read(&vma->vm_mm->mmap_sem);
ret = VM_FAULT_RETRY;
}
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);
return ret;
}
spin_unlock(&inode->i_lock);
}
sgp = SGP_CACHE;
if (vma->vm_flags & VM_HUGEPAGE)
sgp = SGP_HUGE;
else if (vma->vm_flags & VM_NOHUGEPAGE)
sgp = SGP_NOHUGE;
error = shmem_getpage_gfp(inode, vmf->pgoff, &vmf->page, sgp,
gfp, vma, vmf, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
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 (*get_area)(struct file *,
unsigned long, unsigned long, unsigned long, unsigned long);
unsigned long addr;
unsigned long offset;
unsigned long inflated_len;
unsigned long inflated_addr;
unsigned long inflated_offset;
if (len > TASK_SIZE)
return -ENOMEM;
get_area = current->mm->get_unmapped_area;
addr = get_area(file, uaddr, len, pgoff, flags);
if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE))
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 (len < HPAGE_PMD_SIZE)
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, respect that as before.
*/
if (uaddr)
return addr;
if (shmem_huge != SHMEM_HUGE_FORCE) {
struct super_block *sb;
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;
}
if (SHMEM_SB(sb)->huge == SHMEM_HUGE_NEVER)
return addr;
}
offset = (pgoff << PAGE_SHIFT) & (HPAGE_PMD_SIZE-1);
if (offset && offset + len < 2 * HPAGE_PMD_SIZE)
return addr;
if ((addr & (HPAGE_PMD_SIZE-1)) == offset)
return addr;
inflated_len = len + HPAGE_PMD_SIZE - PAGE_SIZE;
if (inflated_len > TASK_SIZE)
return addr;
if (inflated_len < len)
return addr;
inflated_addr = get_area(NULL, 0, inflated_len, 0, flags);
if (IS_ERR_VALUE(inflated_addr))
return addr;
if (inflated_addr & ~PAGE_MASK)
return addr;
inflated_offset = inflated_addr & (HPAGE_PMD_SIZE-1);
inflated_addr += offset - inflated_offset;
if (inflated_offset > offset)
inflated_addr += HPAGE_PMD_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)
{
struct inode *inode = file_inode(vma->vm_file);
pgoff_t index;
index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index);
}
#endif
int shmem_lock(struct file *file, int lock, struct user_struct *user)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
spin_lock_irq(&info->lock);
if (lock && !(info->flags & VM_LOCKED)) {
if (!user_shm_lock(inode->i_size, user))
goto out_nomem;
info->flags |= VM_LOCKED;
mapping_set_unevictable(file->f_mapping);
}
if (!lock && (info->flags & VM_LOCKED) && user) {
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
}
retval = 0;
out_nomem:
spin_unlock_irq(&info->lock);
return retval;
}
static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
vma->vm_ops = &shmem_vm_ops;
if (IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
((vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK) <
(vma->vm_end & HPAGE_PMD_MASK)) {
khugepaged_enter(vma, vma->vm_flags);
}
return 0;
}
static struct inode *shmem_get_inode(struct super_block *sb, const 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);
if (shmem_reserve_inode(sb))
return NULL;
inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
inode->i_generation = get_seconds();
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
info->seals = F_SEAL_SEAL;
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->shrinklist);
INIT_LIST_HEAD(&info->swaplist);
simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
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_dir_operations;
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;
}
} else
shmem_free_inode(sb);
return inode;
}
bool shmem_mapping(struct address_space *mapping)
{
return mapping->a_ops == &shmem_aops;
}
int shmem_mcopy_atomic_pte(struct mm_struct *dst_mm,
pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
struct page **pagep)
{
struct inode *inode = file_inode(dst_vma->vm_file);
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct address_space *mapping = inode->i_mapping;
gfp_t gfp = mapping_gfp_mask(mapping);
pgoff_t pgoff = linear_page_index(dst_vma, dst_addr);
struct mem_cgroup *memcg;
spinlock_t *ptl;
void *page_kaddr;
struct page *page;
pte_t _dst_pte, *dst_pte;
int ret;
ret = -ENOMEM;
if (shmem_acct_block(info->flags, 1))
goto out;
if (sbinfo->max_blocks) {
if (percpu_counter_compare(&sbinfo->used_blocks,
sbinfo->max_blocks) >= 0)
goto out_unacct_blocks;
percpu_counter_inc(&sbinfo->used_blocks);
}
if (!*pagep) {
page = shmem_alloc_page(gfp, info, pgoff);
if (!page)
goto out_dec_used_blocks;
page_kaddr = kmap_atomic(page);
ret = copy_from_user(page_kaddr, (const void __user *)src_addr,
PAGE_SIZE);
kunmap_atomic(page_kaddr);
/* fallback to copy_from_user outside mmap_sem */
if (unlikely(ret)) {
*pagep = page;
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -1);
shmem_unacct_blocks(info->flags, 1);
/* don't free the page */
return -EFAULT;
}
} else {
page = *pagep;
*pagep = NULL;
}
VM_BUG_ON(PageLocked(page) || PageSwapBacked(page));
__SetPageLocked(page);
__SetPageSwapBacked(page);
__SetPageUptodate(page);
ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
if (ret)
goto out_release;
ret = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
if (!ret) {
ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL);
radix_tree_preload_end();
}
if (ret)
goto out_release_uncharge;
mem_cgroup_commit_charge(page, memcg, false, false);
_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
if (dst_vma->vm_flags & VM_WRITE)
_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
ret = -EEXIST;
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
if (!pte_none(*dst_pte))
goto out_release_uncharge_unlock;
lru_cache_add_anon(page);
spin_lock(&info->lock);
info->alloced++;
inode->i_blocks += BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
inc_mm_counter(dst_mm, mm_counter_file(page));
page_add_file_rmap(page, false);
set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
unlock_page(page);
pte_unmap_unlock(dst_pte, ptl);
ret = 0;
out:
return ret;
out_release_uncharge_unlock:
pte_unmap_unlock(dst_pte, ptl);
out_release_uncharge:
mem_cgroup_cancel_charge(page, memcg, false);
out_release:
unlock_page(page);
put_page(page);
out_dec_used_blocks:
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -1);
out_unacct_blocks:
shmem_unacct_blocks(info->flags, 1);
goto out;
}
#ifdef CONFIG_TMPFS
static const struct inode_operations shmem_symlink_inode_operations;
static const struct inode_operations shmem_short_symlink_operations;
#ifdef CONFIG_TMPFS_XATTR
static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
#else
#define shmem_initxattrs NULL
#endif
static int
shmem_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t index = pos >> PAGE_SHIFT;
/* i_mutex is held by caller */
if (unlikely(info->seals & (F_SEAL_WRITE | F_SEAL_GROW))) {
if (info->seals & F_SEAL_WRITE)
return -EPERM;
if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
return -EPERM;
}
return shmem_getpage(inode, index, pagep, SGP_WRITE);
}
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 inode *inode = mapping->host;
if (pos + copied > inode->i_size)
i_size_write(inode, pos + copied);
if (!PageUptodate(page)) {
struct page *head = compound_head(page);
if (PageTransCompound(page)) {
int i;
for (i = 0; i < HPAGE_PMD_NR; i++) {
if (head + i == page)
continue;
clear_highpage(head + i);
flush_dcache_page(head + i);
}
}
if (copied < PAGE_SIZE) {
unsigned from = pos & (PAGE_SIZE - 1);
zero_user_segments(page, 0, from,
from + copied, PAGE_SIZE);
}
SetPageUptodate(head);
}
set_page_dirty(page);
unlock_page(page);
put_page(page);
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;
enum sgp_type sgp = SGP_READ;
int error = 0;
ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
/*
* Might this read be for a stacking filesystem? Then when reading
* holes of a sparse file, we actually need to allocate those pages,
* and even mark them dirty, so it cannot exceed the max_blocks limit.
*/
if (!iter_is_iovec(to))
sgp = SGP_CACHE;
index = *ppos >> PAGE_SHIFT;
offset = *ppos & ~PAGE_MASK;
for (;;) {
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_getpage(inode, index, &page, sgp);
if (error) {
if (error == -EINVAL)
error = 0;
break;
}
if (page) {
if (sgp == SGP_CACHE)
set_page_dirty(page);
unlock_page(page);
}
/*
* We must evaluate after, since reads (unlike writes)
* are called without i_mutex 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 (page)
put_page(page);
break;
}
}
nr -= offset;
if (page) {
/*
* 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)
mark_page_accessed(page);
} else {
page = ZERO_PAGE(0);
get_page(page);
}
/*
* 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);
retval += ret;
offset += ret;
index += offset >> PAGE_SHIFT;
offset &= ~PAGE_MASK;
put_page(page);
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;
}
/*
* llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
*/
static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
pgoff_t index, pgoff_t end, int whence)
{
struct page *page;
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
bool done = false;
int i;
pagevec_init(&pvec, 0);
pvec.nr = 1; /* start small: we may be there already */
while (!done) {
pvec.nr = find_get_entries(mapping, index,
pvec.nr, pvec.pages, indices);
if (!pvec.nr) {
if (whence == SEEK_DATA)
index = end;
break;
}
for (i = 0; i < pvec.nr; i++, index++) {
if (index < indices[i]) {
if (whence == SEEK_HOLE) {
done = true;
break;
}
index = indices[i];
}
page = pvec.pages[i];
if (page && !radix_tree_exceptional_entry(page)) {
if (!PageUptodate(page))
page = NULL;
}
if (index >= end ||
(page && whence == SEEK_DATA) ||
(!page && whence == SEEK_HOLE)) {
done = true;
break;
}
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
pvec.nr = PAGEVEC_SIZE;
cond_resched();
}
return index;
}
static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
{
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
pgoff_t start, end;
loff_t new_offset;
if (whence != SEEK_DATA && whence != SEEK_HOLE)
return generic_file_llseek_size(file, offset, whence,
MAX_LFS_FILESIZE, i_size_read(inode));
inode_lock(inode);
/* We're holding i_mutex so we can access i_size directly */
if (offset < 0)
offset = -EINVAL;
else if (offset >= inode->i_size)
offset = -ENXIO;
else {
start = offset >> PAGE_SHIFT;
end = (inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
new_offset = shmem_seek_hole_data(mapping, start, end, whence);
new_offset <<= PAGE_SHIFT;
if (new_offset > offset) {
if (new_offset < inode->i_size)
offset = new_offset;
else if (whence == SEEK_DATA)
offset = -ENXIO;
else
offset = inode->i_size;
}
}
if (offset >= 0)
offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
inode_unlock(inode);
return offset;
}
/*
* We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
* so reuse a tag which we firmly believe is never set or cleared on shmem.
*/
#define SHMEM_TAG_PINNED PAGECACHE_TAG_TOWRITE
#define LAST_SCAN 4 /* about 150ms max */
static void shmem_tag_pins(struct address_space *mapping)
{
struct radix_tree_iter iter;
void **slot;
pgoff_t start;
struct page *page;
lru_add_drain();
start = 0;
rcu_read_lock();
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
page = radix_tree_deref_slot(slot);
if (!page || radix_tree_exception(page)) {
if (radix_tree_deref_retry(page)) {
slot = radix_tree_iter_retry(&iter);
continue;
}
} else if (page_count(page) - page_mapcount(page) > 1) {
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_set(&mapping->page_tree, iter.index,
SHMEM_TAG_PINNED);
spin_unlock_irq(&mapping->tree_lock);
}
if (need_resched()) {
slot = radix_tree_iter_resume(slot, &iter);
cond_resched_rcu();
}
}
rcu_read_unlock();
}
/*
* Setting SEAL_WRITE requires us to verify there's no pending writer. However,
* via get_user_pages(), drivers might have some pending I/O without any active
* user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
* and see whether it has an elevated ref-count. If so, we tag them and wait for
* them to be dropped.
* The caller must guarantee that no new user will acquire writable references
* to those pages to avoid races.
*/
static int shmem_wait_for_pins(struct address_space *mapping)
{
struct radix_tree_iter iter;
void **slot;
pgoff_t start;
struct page *page;
int error, scan;
shmem_tag_pins(mapping);
error = 0;
for (scan = 0; scan <= LAST_SCAN; scan++) {
if (!radix_tree_tagged(&mapping->page_tree, SHMEM_TAG_PINNED))
break;
if (!scan)
lru_add_drain_all();
else if (schedule_timeout_killable((HZ << scan) / 200))
scan = LAST_SCAN;
start = 0;
rcu_read_lock();
radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter,
start, SHMEM_TAG_PINNED) {
page = radix_tree_deref_slot(slot);
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page)) {
slot = radix_tree_iter_retry(&iter);
continue;
}
page = NULL;
}
if (page &&
page_count(page) - page_mapcount(page) != 1) {
if (scan < LAST_SCAN)
goto continue_resched;
/*
* On the last scan, we clean up all those tags
* we inserted; but make a note that we still
* found pages pinned.
*/
error = -EBUSY;
}
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_clear(&mapping->page_tree,
iter.index, SHMEM_TAG_PINNED);
spin_unlock_irq(&mapping->tree_lock);
continue_resched:
if (need_resched()) {
slot = radix_tree_iter_resume(slot, &iter);
cond_resched_rcu();
}
}
rcu_read_unlock();
}
return error;
}
#define F_ALL_SEALS (F_SEAL_SEAL | \
F_SEAL_SHRINK | \
F_SEAL_GROW | \
F_SEAL_WRITE)
int shmem_add_seals(struct file *file, unsigned int seals)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
int error;
/*
* SEALING
* Sealing allows multiple parties to share a shmem-file but restrict
* access to a specific subset of file operations. Seals can only be
* added, but never removed. This way, mutually untrusted parties can
* share common memory regions with a well-defined policy. A malicious
* peer can thus never perform unwanted operations on a shared object.
*
* Seals are only supported on special shmem-files and always affect
* the whole underlying inode. Once a seal is set, it may prevent some
* kinds of access to the file. Currently, the following seals are
* defined:
* SEAL_SEAL: Prevent further seals from being set on this file
* SEAL_SHRINK: Prevent the file from shrinking
* SEAL_GROW: Prevent the file from growing
* SEAL_WRITE: Prevent write access to the file
*
* As we don't require any trust relationship between two parties, we
* must prevent seals from being removed. Therefore, sealing a file
* only adds a given set of seals to the file, it never touches
* existing seals. Furthermore, the "setting seals"-operation can be
* sealed itself, which basically prevents any further seal from being
* added.
*
* Semantics of sealing are only defined on volatile files. Only
* anonymous shmem files support sealing. More importantly, seals are
* never written to disk. Therefore, there's no plan to support it on
* other file types.
*/
if (file->f_op != &shmem_file_operations)
return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EPERM;
if (seals & ~(unsigned int)F_ALL_SEALS)
return -EINVAL;
inode_lock(inode);
if (info->seals & F_SEAL_SEAL) {
error = -EPERM;
goto unlock;
}
if ((seals & F_SEAL_WRITE) && !(info->seals & F_SEAL_WRITE)) {
error = mapping_deny_writable(file->f_mapping);
if (error)
goto unlock;
error = shmem_wait_for_pins(file->f_mapping);
if (error) {
mapping_allow_writable(file->f_mapping);
goto unlock;
}
}
info->seals |= seals;
error = 0;
unlock:
inode_unlock(inode);
return error;
}
EXPORT_SYMBOL_GPL(shmem_add_seals);
int shmem_get_seals(struct file *file)
{
if (file->f_op != &shmem_file_operations)
return -EINVAL;
return SHMEM_I(file_inode(file))->seals;
}
EXPORT_SYMBOL_GPL(shmem_get_seals);
long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
{
long error;
switch (cmd) {
case F_ADD_SEALS:
/* disallow upper 32bit */
if (arg > UINT_MAX)
return -EINVAL;
error = shmem_add_seals(file, arg);
break;
case F_GET_SEALS:
error = shmem_get_seals(file);
break;
default: