* (C) 1997 Linus Torvalds
*/
-#include <linux/config.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/dcache.h>
*/
struct inodes_stat_t inodes_stat;
-static kmem_cache_t * inode_cachep __read_mostly;
+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);
+}
static struct inode *alloc_inode(struct super_block *sb)
{
- static struct address_space_operations empty_aops;
+ static const struct address_space_operations empty_aops;
static struct inode_operations empty_iops;
static const struct file_operations empty_fops;
struct inode *inode;
if (sb->s_op->alloc_inode)
inode = sb->s_op->alloc_inode(sb);
else
- inode = (struct inode *) kmem_cache_alloc(inode_cachep, SLAB_KERNEL);
+ inode = (struct inode *) kmem_cache_alloc(inode_cachep, GFP_KERNEL);
if (inode) {
struct address_space * const mapping = &inode->i_data;
inode->i_bdev = NULL;
inode->i_cdev = NULL;
inode->i_rdev = 0;
- inode->i_security = NULL;
inode->dirtied_when = 0;
if (security_inode_alloc(inode)) {
if (inode->i_sb->s_op->destroy_inode)
return NULL;
}
+ 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);
+ mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE);
mapping->assoc_mapping = NULL;
mapping->backing_dev_info = &default_backing_dev_info;
bdi = sb->s_bdev->bd_inode->i_mapping->backing_dev_info;
mapping->backing_dev_info = bdi;
}
- memset(&inode->u, 0, sizeof(inode->u));
+ inode->i_private = NULL;
inode->i_mapping = mapping;
}
return inode;
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_dentry);
INIT_LIST_HEAD(&inode->i_devices);
- mutex_init(&inode->i_mutex);
- init_rwsem(&inode->i_alloc_sem);
INIT_RADIX_TREE(&inode->i_data.page_tree, GFP_ATOMIC);
rwlock_init(&inode->i_data.tree_lock);
spin_lock_init(&inode->i_data.i_mmap_lock);
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);
- spin_lock_init(&inode->i_lock);
i_size_ordered_init(inode);
#ifdef CONFIG_INOTIFY
INIT_LIST_HEAD(&inode->inotify_watches);
EXPORT_SYMBOL(inode_init_once);
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void init_once(struct kmem_cache * cachep, void *foo)
{
struct inode * inode = (struct inode *) foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR)
- inode_init_once(inode);
+ inode_init_once(inode);
}
/*
return;
}
atomic_inc(&inode->i_count);
- if (!(inode->i_state & (I_DIRTY|I_LOCK)))
+ if (!(inode->i_state & (I_DIRTY|I_SYNC)))
list_move(&inode->i_list, &inode_in_use);
inodes_stat.nr_unused--;
}
BUG_ON(inode->i_data.nrpages);
BUG_ON(!(inode->i_state & I_FREEING));
BUG_ON(inode->i_state & I_CLEAR);
- wait_on_inode(inode);
+ inode_sync_wait(inode);
DQUOT_DROP(inode);
- if (inode->i_sb && inode->i_sb->s_op->clear_inode)
+ if (inode->i_sb->s_op->clear_inode)
inode->i_sb->s_op->clear_inode(inode);
- if (inode->i_bdev)
+ if (S_ISBLK(inode->i_mode) && inode->i_bdev)
bd_forget(inode);
- if (inode->i_cdev)
+ if (S_ISCHR(inode->i_mode) && inode->i_cdev)
cd_forget(inode);
inode->i_state = I_CLEAR;
}
while (!list_empty(head)) {
struct inode *inode;
- inode = list_entry(head->next, struct inode, i_list);
+ inode = list_first_entry(head, struct inode, i_list);
list_del(&inode->i_list);
if (inode->i_data.nrpages)
}
EXPORT_SYMBOL(invalidate_inodes);
-
-int __invalidate_device(struct block_device *bdev)
-{
- struct super_block *sb = get_super(bdev);
- int res = 0;
-
- if (sb) {
- /*
- * no need to lock the super, get_super holds the
- * read mutex so the filesystem cannot go away
- * under us (->put_super runs with the write lock
- * hold).
- */
- shrink_dcache_sb(sb);
- res = invalidate_inodes(sb);
- drop_super(sb);
- }
- invalidate_bdev(bdev, 0);
- return res;
-}
-EXPORT_SYMBOL(__invalidate_device);
static int can_unuse(struct inode *inode)
{
__iget(inode);
spin_unlock(&inode_lock);
if (remove_inode_buffers(inode))
- reap += invalidate_inode_pages(&inode->i_data);
+ reap += invalidate_mapping_pages(&inode->i_data,
+ 0, -1);
iput(inode);
spin_lock(&inode_lock);
nr_pruned++;
}
inodes_stat.nr_unused -= nr_pruned;
+ if (current_is_kswapd())
+ __count_vm_events(KSWAPD_INODESTEAL, reap);
+ else
+ __count_vm_events(PGINODESTEAL, reap);
spin_unlock(&inode_lock);
dispose_list(&freeable);
mutex_unlock(&iprune_mutex);
-
- if (current_is_kswapd())
- mod_page_state(kswapd_inodesteal, reap);
- else
- mod_page_state(pginodesteal, reap);
}
/*
return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
}
+static struct shrinker icache_shrinker = {
+ .shrink = shrink_icache_memory,
+ .seeks = DEFAULT_SEEKS,
+};
+
static void __wait_on_freeing_inode(struct inode *inode);
/*
* Called with the inode lock held.
* new_inode - obtain an inode
* @sb: superblock
*
- * Allocates a new inode for given superblock.
+ * Allocates a new inode for given superblock. The default gfp_mask
+ * for allocations related to inode->i_mapping is GFP_HIGHUSER_PAGECACHE.
+ * If HIGHMEM pages are unsuitable or it is known that pages allocated
+ * for the page cache are not reclaimable or migratable,
+ * mapping_set_gfp_mask() must be called with suitable flags on the
+ * newly created inode's mapping
+ *
*/
struct inode *new_inode(struct super_block *sb)
{
- static unsigned long last_ino;
+ /*
+ * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
+ * error if st_ino won't fit in target struct field. Use 32bit counter
+ * here to attempt to avoid that.
+ */
+ static unsigned int last_ino;
struct inode * inode;
spin_lock_prefetch(&inode_lock);
void unlock_new_inode(struct inode *inode)
{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ if (inode->i_mode & S_IFDIR) {
+ struct file_system_type *type = inode->i_sb->s_type;
+
+ /*
+ * ensure nobody is actually holding i_mutex
+ */
+ mutex_destroy(&inode->i_mutex);
+ mutex_init(&inode->i_mutex);
+ lockdep_set_class(&inode->i_mutex, &type->i_mutex_dir_key);
+ }
+#endif
/*
* This is special! We do not need the spinlock
* when clearing I_LOCK, because we're guaranteed
return inode;
}
-static inline unsigned long hash(struct super_block *sb, unsigned long hashval)
+static unsigned long hash(struct super_block *sb, unsigned long hashval)
{
unsigned long tmp;
*/
ino_t iunique(struct super_block *sb, ino_t max_reserved)
{
- static ino_t counter;
+ /*
+ * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
+ * error if st_ino won't fit in target struct field. Use 32bit counter
+ * here to attempt to avoid that.
+ */
+ static unsigned int counter;
struct inode *inode;
- struct hlist_head * head;
+ struct hlist_head *head;
ino_t res;
+
spin_lock(&inode_lock);
-retry:
- if (counter > max_reserved) {
- head = inode_hashtable + hash(sb,counter);
+ do {
+ if (counter <= max_reserved)
+ counter = max_reserved + 1;
res = counter++;
+ head = inode_hashtable + hash(sb, res);
inode = find_inode_fast(sb, head, res);
- if (!inode) {
- spin_unlock(&inode_lock);
- return res;
- }
- } else {
- counter = max_reserved + 1;
- }
- goto retry;
-
-}
+ } while (inode != NULL);
+ spin_unlock(&inode_lock);
+ return res;
+}
EXPORT_SYMBOL(iunique);
struct inode *igrab(struct inode *inode)
{
spin_lock(&inode_lock);
- if (!(inode->i_state & (I_FREEING|I_WILL_FREE)))
+ if (!(inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)))
__iget(inode);
else
/*
* @set: callback used to initialize a new struct inode
* @data: opaque data pointer to pass to @test and @set
*
- * This is iget() without the read_inode() portion of get_new_inode().
- *
* iget5_locked() uses ifind() to search for the inode specified by @hashval
* and @data in the inode cache and if present it is returned with an increased
* reference count. This is a generalized version of iget_locked() for file
* @sb: super block of file system
* @ino: inode number to get
*
- * This is iget() without the read_inode() portion of get_new_inode_fast().
- *
* iget_locked() uses ifind_fast() to search for the inode specified by @ino in
* the inode cache and if present it is returned with an increased reference
* count. This is for file systems where the inode number is sufficient for
*/
void generic_delete_inode(struct inode *inode)
{
- struct super_operations *op = inode->i_sb->s_op;
+ const struct super_operations *op = inode->i_sb->s_op;
list_del_init(&inode->i_list);
list_del_init(&inode->i_sb_list);
- inode->i_state|=I_FREEING;
+ inode->i_state |= I_FREEING;
inodes_stat.nr_inodes--;
spin_unlock(&inode_lock);
struct super_block *sb = inode->i_sb;
if (!hlist_unhashed(&inode->i_hash)) {
- if (!(inode->i_state & (I_DIRTY|I_LOCK)))
+ if (!(inode->i_state & (I_DIRTY|I_SYNC)))
list_move(&inode->i_list, &inode_unused);
inodes_stat.nr_unused++;
- if (!sb || (sb->s_flags & MS_ACTIVE)) {
+ if (sb->s_flags & MS_ACTIVE) {
spin_unlock(&inode_lock);
return;
}
*/
static inline void iput_final(struct inode *inode)
{
- struct super_operations *op = inode->i_sb->s_op;
+ const struct super_operations *op = inode->i_sb->s_op;
void (*drop)(struct inode *) = generic_drop_inode;
if (op && op->drop_inode)
void iput(struct inode *inode)
{
if (inode) {
- struct super_operations *op = inode->i_sb->s_op;
+ const struct super_operations *op = inode->i_sb->s_op;
BUG_ON(inode->i_state == I_CLEAR);
res = inode->i_mapping->a_ops->bmap(inode->i_mapping, block);
return res;
}
-
EXPORT_SYMBOL(bmap);
/**
struct inode *inode = dentry->d_inode;
struct timespec now;
- if (IS_RDONLY(inode))
- return;
-
- if ((inode->i_flags & S_NOATIME) ||
- (inode->i_sb->s_flags & MS_NOATIME) ||
- ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode)))
- return;
-
- /*
- * We may have a NULL vfsmount when coming from NFSD
- */
- if (mnt &&
- ((mnt->mnt_flags & MNT_NOATIME) ||
- ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))))
+ if (mnt_want_write(mnt))
return;
+ if (inode->i_flags & S_NOATIME)
+ goto out;
+ if (IS_NOATIME(inode))
+ goto out;
+ if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
+ goto out;
+
+ if (mnt->mnt_flags & MNT_NOATIME)
+ goto out;
+ if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
+ goto out;
+ if (mnt->mnt_flags & MNT_RELATIME) {
+ /*
+ * With relative atime, only update atime if the previous
+ * atime is earlier than either the ctime or mtime.
+ */
+ if (timespec_compare(&inode->i_mtime, &inode->i_atime) < 0 &&
+ timespec_compare(&inode->i_ctime, &inode->i_atime) < 0)
+ goto out;
+ }
now = current_fs_time(inode->i_sb);
- if (!timespec_equal(&inode->i_atime, &now)) {
- inode->i_atime = now;
- mark_inode_dirty_sync(inode);
- }
-}
+ if (timespec_equal(&inode->i_atime, &now))
+ goto out;
+ inode->i_atime = now;
+ mark_inode_dirty_sync(inode);
+out:
+ mnt_drop_write(mnt);
+}
EXPORT_SYMBOL(touch_atime);
/**
void file_update_time(struct file *file)
{
- struct inode *inode = file->f_dentry->d_inode;
+ struct inode *inode = file->f_path.dentry->d_inode;
struct timespec now;
int sync_it = 0;
+ int err;
if (IS_NOCMTIME(inode))
return;
- if (IS_RDONLY(inode))
+
+ err = mnt_want_write(file->f_path.mnt);
+ if (err)
return;
now = current_fs_time(inode->i_sb);
- if (!timespec_equal(&inode->i_mtime, &now))
+ if (!timespec_equal(&inode->i_mtime, &now)) {
+ inode->i_mtime = now;
sync_it = 1;
- inode->i_mtime = now;
+ }
- if (!timespec_equal(&inode->i_ctime, &now))
+ if (!timespec_equal(&inode->i_ctime, &now)) {
+ inode->i_ctime = now;
sync_it = 1;
- inode->i_ctime = now;
+ }
+
+ if (IS_I_VERSION(inode)) {
+ inode_inc_iversion(inode);
+ sync_it = 1;
+ }
if (sync_it)
mark_inode_dirty_sync(inode);
+ mnt_drop_write(file->f_path.mnt);
}
EXPORT_SYMBOL(file_update_time);
EXPORT_SYMBOL(inode_needs_sync);
-/*
- * Quota functions that want to walk the inode lists..
- */
-#ifdef CONFIG_QUOTA
-
-/* Function back in dquot.c */
-int remove_inode_dquot_ref(struct inode *, int, struct list_head *);
-
-void remove_dquot_ref(struct super_block *sb, int type,
- struct list_head *tofree_head)
-{
- struct inode *inode;
-
- if (!sb->dq_op)
- return; /* nothing to do */
- spin_lock(&inode_lock); /* This lock is for inodes code */
-
- /*
- * We don't have to lock against quota code - test IS_QUOTAINIT is
- * just for speedup...
- */
- list_for_each_entry(inode, &sb->s_inodes, i_sb_list)
- if (!IS_NOQUOTA(inode))
- remove_inode_dquot_ref(inode, type, tofree_head);
-
- spin_unlock(&inode_lock);
-}
-
-#endif
-
int inode_wait(void *word)
{
schedule();
spin_lock(&inode_lock);
}
-void wake_up_inode(struct inode *inode)
+/*
+ * We rarely want to lock two inodes that do not have a parent/child
+ * relationship (such as directory, child inode) simultaneously. The
+ * vast majority of file systems should be able to get along fine
+ * without this. Do not use these functions except as a last resort.
+ */
+void inode_double_lock(struct inode *inode1, struct inode *inode2)
{
- /*
- * Prevent speculative execution through spin_unlock(&inode_lock);
- */
- smp_mb();
- wake_up_bit(&inode->i_state, __I_LOCK);
+ if (inode1 == NULL || inode2 == NULL || inode1 == inode2) {
+ if (inode1)
+ mutex_lock(&inode1->i_mutex);
+ else if (inode2)
+ mutex_lock(&inode2->i_mutex);
+ return;
+ }
+
+ if (inode1 < inode2) {
+ mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+ } else {
+ mutex_lock_nested(&inode2->i_mutex, I_MUTEX_PARENT);
+ mutex_lock_nested(&inode1->i_mutex, I_MUTEX_CHILD);
+ }
+}
+EXPORT_SYMBOL(inode_double_lock);
+
+void inode_double_unlock(struct inode *inode1, struct inode *inode2)
+{
+ if (inode1)
+ mutex_unlock(&inode1->i_mutex);
+
+ if (inode2 && inode2 != inode1)
+ mutex_unlock(&inode2->i_mutex);
}
+EXPORT_SYMBOL(inode_double_unlock);
static __initdata unsigned long ihash_entries;
static int __init set_ihash_entries(char *str)
INIT_HLIST_HEAD(&inode_hashtable[loop]);
}
-void __init inode_init(unsigned long mempages)
+void __init inode_init(void)
{
int loop;
0,
(SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
SLAB_MEM_SPREAD),
- init_once,
- NULL);
- set_shrinker(DEFAULT_SEEKS, shrink_icache_memory);
+ init_once);
+ register_shrinker(&icache_shrinker);
/* Hash may have been set up in inode_init_early */
if (!hashdist)
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff