/*
* linux/fs/inode.c
*
* (C) 1997 Linus Torvalds
*/
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/dcache.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/writeback.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/hash.h>
#include <linux/swap.h>
#include <linux/security.h>
#include <linux/ima.h>
#include <linux/pagemap.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/inotify.h>
#include <linux/fsnotify.h>
#include <linux/mount.h>
#include <linux/async.h>
#include <linux/posix_acl.h>
/*
* This is needed for the following functions:
* - inode_has_buffers
* - invalidate_inode_buffers
* - invalidate_bdev
*
* FIXME: remove all knowledge of the buffer layer from this file
*/
#include <linux/buffer_head.h>
/*
* New inode.c implementation.
*
* This implementation has the basic premise of trying
* to be extremely low-overhead and SMP-safe, yet be
* simple enough to be "obviously correct".
*
* Famous last words.
*/
/* inode dynamic allocation 1999, Andrea Arcangeli <andrea@suse.de> */
/* #define INODE_PARANOIA 1 */
/* #define INODE_DEBUG 1 */
/*
* Inode lookup is no longer as critical as it used to be:
* most of the lookups are going to be through the dcache.
*/
#define I_HASHBITS i_hash_shift
#define I_HASHMASK i_hash_mask
static unsigned int i_hash_mask __read_mostly;
static unsigned int i_hash_shift __read_mostly;
/*
* Each inode can be on two separate lists. One is
* the hash list of the inode, used for lookups. The
* other linked list is the "type" list:
* "in_use" - valid inode, i_count > 0, i_nlink > 0
* "dirty" - as "in_use" but also dirty
* "unused" - valid inode, i_count = 0
*
* A "dirty" list is maintained for each super block,
* allowing for low-overhead inode sync() operations.
*/
LIST_HEAD(inode_in_use);
LIST_HEAD(inode_unused);
static struct hlist_head *inode_hashtable __read_mostly;
/*
* A simple spinlock to protect the list manipulations.
*
* NOTE! You also have to own the lock if you change
* the i_state of an inode while it is in use..
*/
DEFINE_SPINLOCK(inode_lock);
/*
* iprune_mutex provides exclusion between the kswapd or try_to_free_pages
* icache shrinking path, and the umount path. Without this exclusion,
* by the time prune_icache calls iput for the inode whose pages it has
* been invalidating, or by the time it calls clear_inode & destroy_inode
* from its final dispose_list, the struct super_block they refer to
* (for inode->i_sb->s_op) may already have been freed and reused.
*/
static DEFINE_MUTEX(iprune_mutex);
/*
* Statistics gathering..
*/
struct inodes_stat_t inodes_stat;
static struct kmem_cache *inode_cachep __read_mostly;
static void wake_up_inode(struct inode *inode)
{
/*
* Prevent speculative execution through spin_unlock(&inode_lock);
*/
smp_mb();
wake_up_bit(&inode->i_state, __I_LOCK);
}
/**
* inode_init_always - perform inode structure intialisation
* @sb: superblock inode belongs to
* @inode: inode to initialise
*
* These are initializations that need to be done on every inode
* allocation as the fields are not initialised by slab allocation.
*/
int inode_init_always(struct super_block *sb, struct inode *inode)
{
static const struct address_space_operations empty_aops;
static struct inode_operations empty_iops;
static const struct file_operations empty_fops;
struct address_space *const mapping = &inode->i_data;
inode->i_sb = sb;
inode->i_blkbits = sb->s_blocksize_bits;
inode->i_flags = 0;
atomic_set(&inode->i_count, 1);
inode->i_op = &empty_iops;
inode->i_fop = &empty_fops;
inode->i_nlink = 1;
inode->i_uid = 0;
inode->i_gid = 0;
atomic_set(&inode->i_writecount, 0);
inode->i_size = 0;
inode->i_blocks = 0;
inode->i_bytes = 0;
inode->i_generation = 0;
#ifdef CONFIG_QUOTA
memset(&inode->i_dquot, 0, sizeof(inode->i_dquot));
#endif
inode->i_pipe = NULL;
inode->i_bdev = NULL;
inode->i_cdev = NULL;
inode->i_rdev = 0;
inode->dirtied_when = 0;
if (security_inode_alloc(inode))
goto out;
/* allocate and initialize an i_integrity */
if (ima_inode_alloc(inode))
goto out_free_security;
spin_lock_init(&inode->i_lock);
lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key);
mutex_init(&inode->i_mutex);
lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
init_rwsem(&inode->i_alloc_sem);
lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key);
mapping->a_ops = &empty_aops;
mapping->host = inode;
mapping->flags = 0;
mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
mapping->assoc_mapping = NULL;
mapping->backing_dev_info = &default_backing_dev_info;
mapping->writeback_index = 0;
/*
* If the block_device provides a backing_dev_info for client
* inodes then use that. Otherwise the inode share the bdev's
* backing_dev_info.
*/
if (sb->s_bdev) {
struct backing_dev_info *bdi;
bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
mapping->backing_dev_info = bdi;
}
inode->i_private = NULL;
inode->i_mapping = mapping;
#ifdef CONFIG_FS_POSIX_ACL
inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
#endif
#ifdef CONFIG_FSNOTIFY
inode->i_fsnotify_mask = 0;
#endif
return 0;
out_free_security:
security_inode_free(inode);
out:
return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);
static struct inode *alloc_inode(struct super_block *sb)
{
struct inode *inode;
if (sb->s_op->alloc_inode)
inode = sb->s_op->alloc_inode(sb);
else
inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
if (!inode)
return NULL;
if (unlikely(inode_init_always(sb, inode))) {
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, inode);
return NULL;
}
return inode;
}
void __destroy_inode(struct inode *inode)
{
BUG_ON(inode_has_buffers(inode));
ima_inode_free(inode);
security_inode_free(inode);
fsnotify_inode_delete(inode);
#ifdef CONFIG_FS_POSIX_ACL
if (inode->i_acl && inode->i_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_acl);
if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_default_acl);
#endif
}
EXPORT_SYMBOL(__destroy_inode);
void destroy_inode(struct inode *inode)
{
__destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, (inode));
}
/*
* These are initializations that only need to be done
* once, because the fields are idempotent across use
* of the inode, so let the slab aware of that.
*/
void inode_init_once(struct inode *inode)
{
memset(inode, 0, sizeof(*inode));
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_dentry);
INIT_LIST_HEAD(&inode->i_devices);
INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
spin_lock_init(&inode->i_data.tree_lock);
spin_lock_init(&inode->i_data.i_mmap_lock);
INIT_LIST_HEAD(&inode->i_data.private_list);
spin_lock_init(&inode->i_data.private_lock);
INIT_RAW_PRIO_TREE_ROOT(&inode->i_data.i_mmap);
INIT_LIST_HEAD(&inode->i_data.i_mmap_nonlinear);
i_size_ordered_init(inode);
#ifdef CONFIG_INOTIFY
INIT_LIST_HEAD(&inode->inotify_watches);
mutex_init(&inode->inotify_mutex);
#endif
#ifdef CONFIG_FSNOTIFY
INIT_HLIST_HEAD(&inode->i_fsnotify_mark_entries);
#endif
}
EXPORT_SYMBOL(inode_init_once);
static void init_once(void *foo)
{
struct inode *inode = (struct inode *) foo;
inode_init_once(inode);
}
/*
* inode_lock must be held
*/
void __iget(struct inode *inode)
{
|