#include <linux/init.h>
#include <linux/vfs.h>
#include <linux/mount.h>
+#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/mm.h>
#include <linux/module.h>
+#include <linux/percpu_counter.h>
#include <linux/swap.h>
static struct vfsmount *shm_mnt;
#include <linux/xattr.h>
#include <linux/exportfs.h>
+#include <linux/posix_acl.h>
#include <linux/generic_acl.h>
#include <linux/mman.h>
-#include <linux/pagemap.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/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <asm/div64.h>
#include <asm/pgtable.h>
+/*
+ * The maximum size of a shmem/tmpfs file is limited by the maximum size of
+ * its triple-indirect swap vector - see illustration at shmem_swp_entry().
+ *
+ * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel,
+ * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum
+ * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel,
+ * MAX_LFS_FILESIZE being then more restrictive than swap vector layout.
+ *
+ * We use / and * instead of shifts in the definitions below, so that the swap
+ * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE.
+ */
#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
-#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
-#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
+#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
+
+#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
+#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT)
-#define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
-#define SHMEM_MAX_BYTES ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)
+#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE)
+#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT))
+#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
#define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)
/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
*/
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
- return (flags & VM_ACCOUNT) ?
- security_vm_enough_memory_kern(VM_ACCT(size)) : 0;
+ return (flags & VM_NORESERVE) ?
+ 0 : security_vm_enough_memory_kern(VM_ACCT(size));
}
static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
- if (flags & VM_ACCOUNT)
+ if (!(flags & VM_NORESERVE))
vm_unacct_memory(VM_ACCT(size));
}
*/
static inline int shmem_acct_block(unsigned long flags)
{
- return (flags & VM_ACCOUNT) ?
- 0 : security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE));
+ return (flags & VM_NORESERVE) ?
+ security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0;
}
static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
- if (!(flags & VM_ACCOUNT))
+ if (flags & VM_NORESERVE)
vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}
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 struct vm_operations_struct shmem_vm_ops;
+static const struct vm_operations_struct shmem_vm_ops;
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
{
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += pages;
+ percpu_counter_add(&sbinfo->used_blocks, -pages);
+ spin_lock(&inode->i_lock);
inode->i_blocks -= pages*BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
+ spin_unlock(&inode->i_lock);
}
}
if (sgp == SGP_READ)
return shmem_swp_map(ZERO_PAGE(0));
/*
- * Test free_blocks against 1 not 0, since we have 1 data
+ * Test used_blocks against 1 less max_blocks, since we have 1 data
* page (and perhaps indirect index pages) yet to allocate:
* a waste to allocate index if we cannot allocate data.
*/
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks <= 1) {
- spin_unlock(&sbinfo->stat_lock);
+ if (percpu_counter_compare(&sbinfo->used_blocks,
+ sbinfo->max_blocks - 1) >= 0)
return ERR_PTR(-ENOSPC);
- }
- sbinfo->free_blocks--;
+ percpu_counter_inc(&sbinfo->used_blocks);
+ spin_lock(&inode->i_lock);
inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
+ spin_unlock(&inode->i_lock);
}
spin_unlock(&info->lock);
page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
- if (page)
- set_page_private(page, 0);
spin_lock(&info->lock);
if (!page) {
if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
/*
* Call truncate_inode_pages again: racing shmem_unuse_inode
- * may have swizzled a page in from swap since vmtruncate or
- * generic_delete_inode did it, before we lowered next_index.
- * Also, though shmem_getpage checks i_size before adding to
- * cache, no recheck after: so fix the narrow window there too.
+ * may have swizzled a page in from swap since
+ * truncate_pagecache or generic_delete_inode did it, before we
+ * lowered next_index. Also, though shmem_getpage checks
+ * i_size before adding to cache, no recheck after: so fix the
+ * narrow window there too.
*
* Recalling truncate_inode_pages_range and unmap_mapping_range
* every time for punch_hole (which never got a chance to clear
}
}
-static void shmem_truncate(struct inode *inode)
-{
- shmem_truncate_range(inode, inode->i_size, (loff_t)-1);
-}
-
static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
- struct page *page = NULL;
+ loff_t newsize = attr->ia_size;
int error;
- if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
- if (attr->ia_size < inode->i_size) {
+ error = inode_change_ok(inode, attr);
+ if (error)
+ return error;
+
+ if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
+ && newsize != inode->i_size) {
+ struct page *page = NULL;
+
+ if (newsize < inode->i_size) {
/*
* If truncating down to a partial page, then
* if that page is already allocated, hold it
* truncate_partial_page cannnot miss it were
* it assigned to swap.
*/
- if (attr->ia_size & (PAGE_CACHE_SIZE-1)) {
+ if (newsize & (PAGE_CACHE_SIZE-1)) {
(void) shmem_getpage(inode,
- attr->ia_size>>PAGE_CACHE_SHIFT,
+ newsize >> PAGE_CACHE_SHIFT,
&page, SGP_READ, NULL);
if (page)
unlock_page(page);
* if it's being fully truncated to zero-length: the
* nrpages check is efficient enough in that case.
*/
- if (attr->ia_size) {
+ if (newsize) {
struct shmem_inode_info *info = SHMEM_I(inode);
spin_lock(&info->lock);
info->flags &= ~SHMEM_PAGEIN;
spin_unlock(&info->lock);
}
}
+
+ /* XXX(truncate): truncate_setsize should be called last */
+ truncate_setsize(inode, newsize);
+ if (page)
+ page_cache_release(page);
+ shmem_truncate_range(inode, newsize, (loff_t)-1);
}
- error = inode_change_ok(inode, attr);
- if (!error)
- error = inode_setattr(inode, attr);
+ setattr_copy(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
- if (!error && (attr->ia_valid & ATTR_MODE))
- error = generic_acl_chmod(inode, &shmem_acl_ops);
+ if (attr->ia_valid & ATTR_MODE)
+ error = generic_acl_chmod(inode);
#endif
- if (page)
- page_cache_release(page);
return error;
}
-static void shmem_delete_inode(struct inode *inode)
+static void shmem_evict_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
- if (inode->i_op->truncate == shmem_truncate) {
+ if (inode->i_mapping->a_ops == &shmem_aops) {
truncate_inode_pages(inode->i_mapping, 0);
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
- shmem_truncate(inode);
+ shmem_truncate_range(inode, 0, (loff_t)-1);
if (!list_empty(&info->swaplist)) {
mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
}
BUG_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
- clear_inode(inode);
+ end_writeback(inode);
}
static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
{
- struct inode *inode;
+ struct address_space *mapping;
unsigned long idx;
unsigned long size;
unsigned long limit;
if (size > SHMEM_NR_DIRECT)
size = SHMEM_NR_DIRECT;
offset = shmem_find_swp(entry, ptr, ptr+size);
- if (offset >= 0)
+ if (offset >= 0) {
+ shmem_swp_balance_unmap();
goto found;
+ }
if (!info->i_indirect)
goto lost2;
shmem_swp_unmap(ptr);
if (offset >= 0) {
shmem_dir_unmap(dir);
+ ptr = shmem_swp_map(subdir);
goto found;
}
}
return 0;
found:
idx += offset;
- inode = igrab(&info->vfs_inode);
- spin_unlock(&info->lock);
+ ptr += offset;
/*
* Move _head_ to start search for next from here.
- * But be careful: shmem_delete_inode checks list_empty without taking
+ * 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. We
* could avoid doing it if inode NULL; or use this minor optimization.
*/
if (shmem_swaplist.next != &info->swaplist)
list_move_tail(&shmem_swaplist, &info->swaplist);
- mutex_unlock(&shmem_swaplist_mutex);
- error = 1;
- if (!inode)
- goto out;
/*
- * Charge page using GFP_KERNEL while we can wait.
- * Charged back to the user(not to caller) when swap account is used.
- * add_to_page_cache() will be called with GFP_NOWAIT.
+ * 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).
*/
- error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
- if (error)
- goto out;
- error = radix_tree_preload(GFP_KERNEL);
- if (error) {
- mem_cgroup_uncharge_cache_page(page);
- goto out;
- }
- error = 1;
-
- spin_lock(&info->lock);
- ptr = shmem_swp_entry(info, idx, NULL);
- if (ptr && ptr->val == entry.val) {
- error = add_to_page_cache_locked(page, inode->i_mapping,
- idx, GFP_NOWAIT);
- /* does mem_cgroup_uncharge_cache_page on error */
- } else /* we must compensate for our precharge above */
- mem_cgroup_uncharge_cache_page(page);
+ mapping = info->vfs_inode.i_mapping;
+ error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT);
+ /* which does mem_cgroup_uncharge_cache_page on error */
if (error == -EEXIST) {
- struct page *filepage = find_get_page(inode->i_mapping, idx);
+ struct page *filepage = find_get_page(mapping, idx);
error = 1;
if (filepage) {
/*
swap_free(entry);
error = 1; /* not an error, but entry was found */
}
- if (ptr)
- shmem_swp_unmap(ptr);
+ shmem_swp_unmap(ptr);
spin_unlock(&info->lock);
- radix_tree_preload_end();
-out:
- unlock_page(page);
- page_cache_release(page);
- iput(inode); /* allows for NULL */
return error;
}
struct list_head *p, *next;
struct shmem_inode_info *info;
int found = 0;
+ int error;
+
+ /*
+ * 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.
+ * add_to_page_cache() will be called with GFP_NOWAIT.
+ */
+ error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
+ if (error)
+ goto out;
+ /*
+ * Try to preload while we can wait, to not make a habit of
+ * draining atomic reserves; but don't latch on to this cpu,
+ * it's okay if sometimes we get rescheduled after this.
+ */
+ error = radix_tree_preload(GFP_KERNEL);
+ if (error)
+ goto uncharge;
+ radix_tree_preload_end();
mutex_lock(&shmem_swaplist_mutex);
list_for_each_safe(p, next, &shmem_swaplist) {
found = shmem_unuse_inode(info, entry, page);
cond_resched();
if (found)
- goto out;
+ break;
}
mutex_unlock(&shmem_swaplist_mutex);
-out: return found; /* 0 or 1 or -ENOMEM */
+
+uncharge:
+ if (!found)
+ mem_cgroup_uncharge_cache_page(page);
+ if (found < 0)
+ error = found;
+out:
+ unlock_page(page);
+ page_cache_release(page);
+ return error;
}
/*
* sync from ever calling shmem_writepage; but a stacking filesystem
* may use the ->writepage of its underlying filesystem, in which case
* tmpfs should write out to swap only in response to memory pressure,
- * and not for pdflush or sync. However, in those cases, we do still
- * want to check if there's a redundant swappage to be discarded.
+ * and not for the writeback threads or sync. However, in those cases,
+ * we do still want to check if there's a redundant swappage to be
+ * discarded.
*/
if (wbc->for_reclaim)
swap = get_swap_page();
else
swap.val = 0;
+ /*
+ * Add inode to shmem_unuse()'s list of swapped-out inodes,
+ * if it's not already there. Do it now because we cannot take
+ * mutex while holding spinlock, and must do so 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 taken the spinlock, because shmem_unuse_inode() will
+ * prune a !swapped inode from the swaplist under both locks.
+ */
+ if (swap.val) {
+ mutex_lock(&shmem_swaplist_mutex);
+ if (list_empty(&info->swaplist))
+ list_add_tail(&info->swaplist, &shmem_swaplist);
+ }
+
spin_lock(&info->lock);
+ if (swap.val)
+ mutex_unlock(&shmem_swaplist_mutex);
+
if (index >= info->next_index) {
BUG_ON(!(info->flags & SHMEM_TRUNCATE));
goto unlock;
remove_from_page_cache(page);
shmem_swp_set(info, entry, swap.val);
shmem_swp_unmap(entry);
- if (list_empty(&info->swaplist))
- inode = igrab(inode);
- else
- inode = NULL;
+ swap_shmem_alloc(swap);
spin_unlock(&info->lock);
- swap_duplicate(swap);
BUG_ON(page_mapped(page));
page_cache_release(page); /* pagecache ref */
- set_page_dirty(page);
- unlock_page(page);
- if (inode) {
- mutex_lock(&shmem_swaplist_mutex);
- /* move instead of add in case we're racing */
- list_move_tail(&info->swaplist, &shmem_swaplist);
- mutex_unlock(&shmem_swaplist_mutex);
- iput(inode);
- }
+ swap_writepage(page, wbc);
return 0;
}
shmem_swp_unmap(entry);
unlock:
spin_unlock(&info->lock);
- swap_free(swap);
+ /*
+ * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+ * clear SWAP_HAS_CACHE flag.
+ */
+ swapcache_free(swap, NULL);
redirty:
set_page_dirty(page);
if (wbc->for_reclaim)
struct shmem_sb_info *sbinfo;
struct page *filepage = *pagep;
struct page *swappage;
+ struct page *prealloc_page = NULL;
swp_entry_t *entry;
swp_entry_t swap;
gfp_t gfp;
filepage = find_lock_page(mapping, idx);
if (filepage && PageUptodate(filepage))
goto done;
- error = 0;
gfp = mapping_gfp_mask(mapping);
if (!filepage) {
/*
if (error)
goto failed;
radix_tree_preload_end();
+ if (sgp != SGP_READ && !prealloc_page) {
+ /* We don't care if this fails */
+ prealloc_page = shmem_alloc_page(gfp, info, idx);
+ if (prealloc_page) {
+ if (mem_cgroup_cache_charge(prealloc_page,
+ current->mm, GFP_KERNEL)) {
+ page_cache_release(prealloc_page);
+ prealloc_page = NULL;
+ }
+ }
+ }
}
+ error = 0;
spin_lock(&info->lock);
shmem_recalc_inode(inode);
shmem_swp_unmap(entry);
spin_unlock(&info->lock);
if (error == -ENOMEM) {
- /* allow reclaim from this memory cgroup */
- error = mem_cgroup_shrink_usage(swappage,
+ /*
+ * reclaim from proper memory cgroup and
+ * call memcg's OOM if needed.
+ */
+ error = mem_cgroup_shmem_charge_fallback(
+ swappage,
current->mm,
gfp);
if (error) {
shmem_swp_unmap(entry);
sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks == 0 ||
- shmem_acct_block(info->flags)) {
- spin_unlock(&sbinfo->stat_lock);
- spin_unlock(&info->lock);
- error = -ENOSPC;
- goto failed;
- }
- sbinfo->free_blocks--;
+ if (percpu_counter_compare(&sbinfo->used_blocks,
+ sbinfo->max_blocks) >= 0 ||
+ shmem_acct_block(info->flags))
+ goto nospace;
+ percpu_counter_inc(&sbinfo->used_blocks);
+ spin_lock(&inode->i_lock);
inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
- } else if (shmem_acct_block(info->flags)) {
- spin_unlock(&info->lock);
- error = -ENOSPC;
- goto failed;
- }
+ spin_unlock(&inode->i_lock);
+ } else if (shmem_acct_block(info->flags))
+ goto nospace;
if (!filepage) {
int ret;
- spin_unlock(&info->lock);
- filepage = shmem_alloc_page(gfp, info, idx);
- if (!filepage) {
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- error = -ENOMEM;
- goto failed;
- }
- SetPageSwapBacked(filepage);
+ if (!prealloc_page) {
+ spin_unlock(&info->lock);
+ filepage = shmem_alloc_page(gfp, info, idx);
+ if (!filepage) {
+ shmem_unacct_blocks(info->flags, 1);
+ shmem_free_blocks(inode, 1);
+ error = -ENOMEM;
+ goto failed;
+ }
+ SetPageSwapBacked(filepage);
+
+ /*
+ * Precharge page while we can wait, compensate
+ * after
+ */
+ error = mem_cgroup_cache_charge(filepage,
+ current->mm, GFP_KERNEL);
+ if (error) {
+ page_cache_release(filepage);
+ shmem_unacct_blocks(info->flags, 1);
+ shmem_free_blocks(inode, 1);
+ filepage = NULL;
+ goto failed;
+ }
- /* Precharge page while we can wait, compensate after */
- error = mem_cgroup_cache_charge(filepage, current->mm,
- GFP_KERNEL);
- if (error) {
- page_cache_release(filepage);
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- filepage = NULL;
- goto failed;
+ spin_lock(&info->lock);
+ } else {
+ filepage = prealloc_page;
+ prealloc_page = NULL;
+ SetPageSwapBacked(filepage);
}
- spin_lock(&info->lock);
entry = shmem_swp_alloc(info, idx, sgp);
if (IS_ERR(entry))
error = PTR_ERR(entry);
}
done:
*pagep = filepage;
- return 0;
+ error = 0;
+ goto out;
+nospace:
+ /*
+ * Perhaps the page was brought in from swap between find_lock_page
+ * and taking info->lock? We allow for that at add_to_page_cache_lru,
+ * but must also avoid reporting a spurious ENOSPC while working on a
+ * full tmpfs. (When filepage has been passed in to shmem_getpage, it
+ * is already in page cache, which prevents this race from occurring.)
+ */
+ if (!filepage) {
+ struct page *page = find_get_page(mapping, idx);
+ if (page) {
+ spin_unlock(&info->lock);
+ page_cache_release(page);
+ goto repeat;
+ }
+ }
+ spin_unlock(&info->lock);
+ error = -ENOSPC;
failed:
if (*pagep != filepage) {
unlock_page(filepage);
page_cache_release(filepage);
}
+out:
+ if (prealloc_page) {
+ mem_cgroup_uncharge_cache_page(prealloc_page);
+ page_cache_release(prealloc_page);
+ }
return error;
}
return 0;
}
-static struct inode *
-shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
+static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir,
+ int mode, dev_t dev, unsigned long flags)
{
struct inode *inode;
struct shmem_inode_info *info;
inode = new_inode(sb);
if (inode) {
- inode->i_mode = mode;
- inode->i_uid = current_fsuid();
- inode->i_gid = current_fsgid();
+ inode->i_ino = get_next_ino();
+ inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
+ info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->swaplist);
+ cache_no_acl(inode);
switch (mode & S_IFMT) {
default:
if (pos + copied > inode->i_size)
i_size_write(inode, pos + copied);
- unlock_page(page);
set_page_dirty(page);
+ unlock_page(page);
page_cache_release(page);
return copied;
buf->f_type = TMPFS_MAGIC;
buf->f_bsize = PAGE_CACHE_SIZE;
buf->f_namelen = NAME_MAX;
- spin_lock(&sbinfo->stat_lock);
if (sbinfo->max_blocks) {
buf->f_blocks = sbinfo->max_blocks;
- buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+ buf->f_bavail = buf->f_bfree =
+ sbinfo->max_blocks - percpu_counter_sum(&sbinfo->used_blocks);
}
if (sbinfo->max_inodes) {
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
/* else leave those fields 0 like simple_statfs */
- spin_unlock(&sbinfo->stat_lock);
return 0;
}
static int
shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
- struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev);
+ struct inode *inode;
int error = -ENOSPC;
+ inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);
if (inode) {
error = security_inode_init_security(inode, dir, NULL, NULL,
NULL);
return error;
}
}
- error = shmem_acl_init(inode, dir);
+#ifdef CONFIG_TMPFS_POSIX_ACL
+ error = generic_acl_init(inode, dir);
if (error) {
iput(inode);
return error;
}
- if (dir->i_mode & S_ISGID) {
- inode->i_gid = dir->i_gid;
- if (S_ISDIR(mode))
- inode->i_mode |= S_ISGID;
- }
+#else
+ error = 0;
+#endif
dir->i_size += BOGO_DIRENT_SIZE;
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
dir->i_size += BOGO_DIRENT_SIZE;
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
inc_nlink(inode);
- atomic_inc(&inode->i_count); /* New dentry reference */
+ ihold(inode); /* New dentry reference */
dget(dentry); /* Extra pinning count for the created dentry */
d_instantiate(dentry, inode);
out:
if (len > PAGE_CACHE_SIZE)
return -ENAMETOOLONG;
- inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
+ inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE);
if (!inode)
return -ENOSPC;
iput(inode);
return error;
}
- unlock_page(page);
inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_symlink_inode_operations;
kaddr = kmap_atomic(page, KM_USER0);
memcpy(kaddr, symname, len);
kunmap_atomic(kaddr, KM_USER0);
set_page_dirty(page);
+ unlock_page(page);
page_cache_release(page);
}
- if (dir->i_mode & S_ISGID)
- inode->i_gid = dir->i_gid;
dir->i_size += BOGO_DIRENT_SIZE;
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
};
static const struct inode_operations shmem_symlink_inode_operations = {
- .truncate = shmem_truncate,
.readlink = generic_readlink,
.follow_link = shmem_follow_link,
.put_link = shmem_put_link,
* filesystem level, though.
*/
-static size_t shmem_xattr_security_list(struct inode *inode, char *list,
+static size_t shmem_xattr_security_list(struct dentry *dentry, char *list,
size_t list_len, const char *name,
- size_t name_len)
+ size_t name_len, int handler_flags)
{
- return security_inode_listsecurity(inode, list, list_len);
+ return security_inode_listsecurity(dentry->d_inode, list, list_len);
}
-static int shmem_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int shmem_xattr_security_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size, int handler_flags)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return xattr_getsecurity(inode, name, buffer, size);
+ return xattr_getsecurity(dentry->d_inode, name, buffer, size);
}
-static int shmem_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static int shmem_xattr_security_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags, int handler_flags)
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return security_inode_setsecurity(inode, name, value, size, flags);
+ return security_inode_setsecurity(dentry->d_inode, name, value,
+ size, flags);
}
-static struct xattr_handler shmem_xattr_security_handler = {
+static const struct xattr_handler shmem_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.list = shmem_xattr_security_list,
.get = shmem_xattr_security_get,
.set = shmem_xattr_security_set,
};
-static struct xattr_handler *shmem_xattr_handlers[] = {
- &shmem_xattr_acl_access_handler,
- &shmem_xattr_acl_default_handler,
+static const struct xattr_handler *shmem_xattr_handlers[] = {
+ &generic_acl_access_handler,
+ &generic_acl_default_handler,
&shmem_xattr_security_handler,
NULL
};
if (*len < 3)
return 255;
- if (hlist_unhashed(&inode->i_hash)) {
+ if (inode_unhashed(inode)) {
/* Unfortunately insert_inode_hash is not idempotent,
* so as we hash inodes here rather than at creation
* time, we need a lock to ensure we only try
*/
static DEFINE_SPINLOCK(lock);
spin_lock(&lock);
- if (hlist_unhashed(&inode->i_hash))
+ if (inode_unhashed(inode))
__insert_inode_hash(inode,
inode->i_ino + inode->i_generation);
spin_unlock(&lock);
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
struct shmem_sb_info config = *sbinfo;
- unsigned long blocks;
unsigned long inodes;
int error = -EINVAL;
return error;
spin_lock(&sbinfo->stat_lock);
- blocks = sbinfo->max_blocks - sbinfo->free_blocks;
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (config.max_blocks < blocks)
+ if (percpu_counter_compare(&sbinfo->used_blocks, config.max_blocks) > 0)
goto out;
if (config.max_inodes < inodes)
goto out;
error = 0;
sbinfo->max_blocks = config.max_blocks;
- sbinfo->free_blocks = config.max_blocks - blocks;
sbinfo->max_inodes = config.max_inodes;
sbinfo->free_inodes = config.max_inodes - inodes;
static void shmem_put_super(struct super_block *sb)
{
- kfree(sb->s_fs_info);
+ struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+
+ percpu_counter_destroy(&sbinfo->used_blocks);
+ kfree(sbinfo);
sb->s_fs_info = NULL;
}
-static int shmem_fill_super(struct super_block *sb,
- void *data, int silent)
+int shmem_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
struct dentry *root;
int err = -ENOMEM;
/* Round up to L1_CACHE_BYTES to resist false sharing */
- sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info),
+ sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
L1_CACHE_BYTES), GFP_KERNEL);
if (!sbinfo)
return -ENOMEM;
- sbinfo->max_blocks = 0;
- sbinfo->max_inodes = 0;
sbinfo->mode = S_IRWXUGO | S_ISVTX;
sbinfo->uid = current_fsuid();
sbinfo->gid = current_fsgid();
- sbinfo->mpol = NULL;
sb->s_fs_info = sbinfo;
#ifdef CONFIG_TMPFS
#endif
spin_lock_init(&sbinfo->stat_lock);
- sbinfo->free_blocks = sbinfo->max_blocks;
+ if (percpu_counter_init(&sbinfo->used_blocks, 0))
+ goto failed;
sbinfo->free_inodes = sbinfo->max_inodes;
sb->s_maxbytes = SHMEM_MAX_BYTES;
sb->s_flags |= MS_POSIXACL;
#endif
- inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0);
+ inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
if (!inode)
goto failed;
inode->i_uid = sbinfo->uid;
return &p->vfs_inode;
}
+static void shmem_i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
+}
+
static void shmem_destroy_inode(struct inode *inode)
{
if ((inode->i_mode & S_IFMT) == S_IFREG) {
/* only struct inode is valid if it's an inline symlink */
mpol_free_shared_policy(&SHMEM_I(inode)->policy);
}
- shmem_acl_destroy_inode(inode);
- kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
+ call_rcu(&inode->i_rcu, shmem_i_callback);
}
static void init_once(void *foo)
struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
inode_init_once(&p->vfs_inode);
-#ifdef CONFIG_TMPFS_POSIX_ACL
- p->i_acl = NULL;
- p->i_default_acl = NULL;
-#endif
}
static int init_inodecache(void)
.write_end = shmem_write_end,
#endif
.migratepage = migrate_page,
+ .error_remove_page = generic_error_remove_page,
};
static const struct file_operations shmem_file_operations = {
.write = do_sync_write,
.aio_read = shmem_file_aio_read,
.aio_write = generic_file_aio_write,
- .fsync = simple_sync_file,
+ .fsync = noop_fsync,
.splice_read = generic_file_splice_read,
.splice_write = generic_file_splice_write,
#endif
};
static const struct inode_operations shmem_inode_operations = {
- .truncate = shmem_truncate,
.setattr = shmem_notify_change,
.truncate_range = shmem_truncate_range,
#ifdef CONFIG_TMPFS_POSIX_ACL
.getxattr = generic_getxattr,
.listxattr = generic_listxattr,
.removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .check_acl = generic_check_acl,
#endif
};
.getxattr = generic_getxattr,
.listxattr = generic_listxattr,
.removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .check_acl = generic_check_acl,
#endif
};
.getxattr = generic_getxattr,
.listxattr = generic_listxattr,
.removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .check_acl = generic_check_acl,
#endif
};
.remount_fs = shmem_remount_fs,
.show_options = shmem_show_options,
#endif
- .delete_inode = shmem_delete_inode,
+ .evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
.put_super = shmem_put_super,
};
-static struct vm_operations_struct shmem_vm_ops = {
+static const struct vm_operations_struct shmem_vm_ops = {
.fault = shmem_fault,
#ifdef CONFIG_NUMA
.set_policy = shmem_set_policy,
};
-static int shmem_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *shmem_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
{
- return get_sb_nodev(fs_type, flags, data, shmem_fill_super, mnt);
+ return mount_nodev(fs_type, flags, data, shmem_fill_super);
}
static struct file_system_type tmpfs_fs_type = {
.owner = THIS_MODULE,
.name = "tmpfs",
- .get_sb = shmem_get_sb,
+ .mount = shmem_mount,
.kill_sb = kill_litter_super,
};
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
{
int error;
return error;
}
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+/**
+ * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
+ * @inode: the inode to be searched
+ * @pgoff: the offset to be searched
+ * @pagep: the pointer for the found page to be stored
+ * @ent: the pointer for the found swap entry to be stored
+ *
+ * If a page is found, refcount of it is incremented. Callers should handle
+ * these refcount.
+ */
+void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
+ struct page **pagep, swp_entry_t *ent)
+{
+ swp_entry_t entry = { .val = 0 }, *ptr;
+ struct page *page = NULL;
+ struct shmem_inode_info *info = SHMEM_I(inode);
+
+ if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ goto out;
+
+ spin_lock(&info->lock);
+ ptr = shmem_swp_entry(info, pgoff, NULL);
+#ifdef CONFIG_SWAP
+ if (ptr && ptr->val) {
+ entry.val = ptr->val;
+ page = find_get_page(&swapper_space, entry.val);
+ } else
+#endif
+ page = find_get_page(inode->i_mapping, pgoff);
+ if (ptr)
+ shmem_swp_unmap(ptr);
+ spin_unlock(&info->lock);
+out:
+ *pagep = page;
+ *ent = entry;
+}
+#endif
+
#else /* !CONFIG_SHMEM */
/*
static struct file_system_type tmpfs_fs_type = {
.name = "tmpfs",
- .get_sb = ramfs_get_sb,
+ .mount = ramfs_mount,
.kill_sb = kill_litter_super,
};
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
{
BUG_ON(register_filesystem(&tmpfs_fs_type) != 0);
return 0;
}
-#define shmem_file_operations ramfs_file_operations
-#define shmem_vm_ops generic_file_vm_ops
-#define shmem_get_inode ramfs_get_inode
-#define shmem_acct_size(a, b) 0
-#define shmem_unacct_size(a, b) do {} while (0)
-#define SHMEM_MAX_BYTES LLONG_MAX
+int shmem_lock(struct file *file, int lock, struct user_struct *user)
+{
+ return 0;
+}
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+/**
+ * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
+ * @inode: the inode to be searched
+ * @pgoff: the offset to be searched
+ * @pagep: the pointer for the found page to be stored
+ * @ent: the pointer for the found swap entry to be stored
+ *
+ * If a page is found, refcount of it is incremented. Callers should handle
+ * these refcount.
+ */
+void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
+ struct page **pagep, swp_entry_t *ent)
+{
+ struct page *page = NULL;
+
+ if ((pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ goto out;
+ page = find_get_page(inode->i_mapping, pgoff);
+out:
+ *pagep = page;
+ *ent = (swp_entry_t){ .val = 0 };
+}
+#endif
+
+#define shmem_vm_ops generic_file_vm_ops
+#define shmem_file_operations ramfs_file_operations
+#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
+#define shmem_acct_size(flags, size) 0
+#define shmem_unacct_size(flags, size) do {} while (0)
+#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE
#endif /* CONFIG_SHMEM */
* shmem_file_setup - get an unlinked file living in tmpfs
* @name: name for dentry (to be seen in /proc/<pid>/maps
* @size: size to be set for the file
- * @flags: vm_flags
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
*/
-struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
{
int error;
struct file *file;
struct inode *inode;
- struct dentry *dentry, *root;
+ struct path path;
+ struct dentry *root;
struct qstr this;
if (IS_ERR(shm_mnt))
this.len = strlen(name);
this.hash = 0; /* will go */
root = shm_mnt->mnt_root;
- dentry = d_alloc(root, &this);
- if (!dentry)
+ path.dentry = d_alloc(root, &this);
+ if (!path.dentry)
goto put_memory;
-
- error = -ENFILE;
- file = get_empty_filp();
- if (!file)
- goto put_dentry;
+ path.mnt = mntget(shm_mnt);
error = -ENOSPC;
- inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
+ inode = shmem_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
if (!inode)
- goto close_file;
+ goto put_dentry;
-#ifdef CONFIG_SHMEM
- SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
-#endif
- d_instantiate(dentry, inode);
+ d_instantiate(path.dentry, inode);
inode->i_size = size;
inode->i_nlink = 0; /* It is unlinked */
- init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
- &shmem_file_operations);
-
#ifndef CONFIG_MMU
error = ramfs_nommu_expand_for_mapping(inode, size);
if (error)
- goto close_file;
+ goto put_dentry;
#endif
+
+ error = -ENFILE;
+ file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
+ &shmem_file_operations);
+ if (!file)
+ goto put_dentry;
+
return file;
-close_file:
- put_filp(file);
put_dentry:
- dput(dentry);
+ path_put(&path);
put_memory:
shmem_unacct_size(flags, size);
return ERR_PTR(error);
fput(vma->vm_file);
vma->vm_file = file;
vma->vm_ops = &shmem_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
-
-module_init(init_tmpfs)