#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;
{
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);
loff_t newsize = attr->ia_size;
int error;
+ 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;
}
}
- error = simple_setsize(inode, newsize);
+ /* XXX(truncate): truncate_setsize should be called last */
+ truncate_setsize(inode, newsize);
if (page)
page_cache_release(page);
- if (error)
- return error;
shmem_truncate_range(inode, newsize, (loff_t)-1);
}
- error = inode_change_ok(inode, attr);
- if (!error)
- generic_setattr(inode, attr);
+ setattr_copy(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
- if (!error && (attr->ia_valid & ATTR_MODE))
+ if (attr->ia_valid & ATTR_MODE)
error = generic_acl_chmod(inode);
#endif
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);
}
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);
- /*
- * Can some race bring us here? We've been holding page lock,
- * so I think not; but would rather try again later than BUG()
- */
+
+uncharge:
+ if (!found)
+ mem_cgroup_uncharge_cache_page(page);
+ if (found < 0)
+ error = found;
+out:
unlock_page(page);
page_cache_release(page);
-out:
- return (found < 0) ? found : 0;
+ return error;
}
/*
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;
- spin_unlock(&info->lock);
swap_shmem_alloc(swap);
+ spin_unlock(&info->lock);
BUG_ON(page_mapped(page));
page_cache_release(page); /* pagecache ref */
swap_writepage(page, wbc);
- 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);
- }
return 0;
}
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);
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;
}
inode = new_inode(sb);
if (inode) {
+ 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;
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;
}
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 < 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;
}
#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;
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);
}
- kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
+ call_rcu(&inode->i_rcu, shmem_i_callback);
}
static void init_once(void *foo)
.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 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 struct file_system_type tmpfs_fs_type = {
.name = "tmpfs",
- .get_sb = ramfs_get_sb,
+ .mount = ramfs_mount,
.kill_sb = kill_litter_super,
};
fput(vma->vm_file);
vma->vm_file = file;
vma->vm_ops = &shmem_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}