* (C) 1997 Linus Torvalds
*/
-#include <linux/config.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/dcache.h>
#include <linux/cdev.h>
#include <linux/bootmem.h>
#include <linux/inotify.h>
+#include <linux/mount.h>
/*
* This is needed for the following functions:
#define I_HASHBITS i_hash_shift
#define I_HASHMASK i_hash_mask
-static unsigned int i_hash_mask;
-static unsigned int i_hash_shift;
+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
LIST_HEAD(inode_in_use);
LIST_HEAD(inode_unused);
-static struct hlist_head *inode_hashtable;
+static struct hlist_head *inode_hashtable __read_mostly;
/*
* A simple spinlock to protect the list manipulations.
DEFINE_SPINLOCK(inode_lock);
/*
- * iprune_sem provides exclusion between the kswapd or try_to_free_pages
+ * 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.
*/
-DECLARE_MUTEX(iprune_sem);
+static DEFINE_MUTEX(iprune_mutex);
/*
* Statistics gathering..
*/
struct inodes_stat_t inodes_stat;
-static kmem_cache_t * inode_cachep;
+static kmem_cache_t * inode_cachep __read_mostly;
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 struct file_operations empty_fops;
+ static const struct file_operations empty_fops;
struct inode *inode;
if (sb->s_op->alloc_inode)
void destroy_inode(struct inode *inode)
{
- if (inode_has_buffers(inode))
- BUG();
+ BUG_ON(inode_has_buffers(inode));
security_inode_free(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
INIT_HLIST_NODE(&inode->i_hash);
INIT_LIST_HEAD(&inode->i_dentry);
INIT_LIST_HEAD(&inode->i_devices);
- sema_init(&inode->i_sem, 1);
+ 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);
i_size_ordered_init(inode);
#ifdef CONFIG_INOTIFY
INIT_LIST_HEAD(&inode->inotify_watches);
- sema_init(&inode->inotify_sem, 1);
+ mutex_init(&inode->inotify_mutex);
#endif
}
might_sleep();
invalidate_inode_buffers(inode);
- if (inode->i_data.nrpages)
- BUG();
- if (!(inode->i_state & I_FREEING))
- BUG();
- if (inode->i_state & I_CLEAR)
- BUG();
+ BUG_ON(inode->i_data.nrpages);
+ BUG_ON(!(inode->i_state & I_FREEING));
+ BUG_ON(inode->i_state & I_CLEAR);
wait_on_inode(inode);
DQUOT_DROP(inode);
if (inode->i_sb && inode->i_sb->s_op->clear_inode)
/*
* We can reschedule here without worrying about the list's
* consistency because the per-sb list of inodes must not
- * change during umount anymore, and because iprune_sem keeps
+ * change during umount anymore, and because iprune_mutex keeps
* shrink_icache_memory() away.
*/
cond_resched_lock(&inode_lock);
int busy;
LIST_HEAD(throw_away);
- down(&iprune_sem);
+ mutex_lock(&iprune_mutex);
spin_lock(&inode_lock);
inotify_unmount_inodes(&sb->s_inodes);
busy = invalidate_list(&sb->s_inodes, &throw_away);
spin_unlock(&inode_lock);
dispose_list(&throw_away);
- up(&iprune_sem);
+ mutex_unlock(&iprune_mutex);
return busy;
}
if (sb) {
/*
* no need to lock the super, get_super holds the
- * read semaphore so the filesystem cannot go away
+ * read mutex so the filesystem cannot go away
* under us (->put_super runs with the write lock
* hold).
*/
int nr_scanned;
unsigned long reap = 0;
- down(&iprune_sem);
+ mutex_lock(&iprune_mutex);
spin_lock(&inode_lock);
for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
struct inode *inode;
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);
- up(&iprune_sem);
-
- if (current_is_kswapd())
- mod_page_state(kswapd_inodesteal, reap);
- else
- mod_page_state(pginodesteal, reap);
+ mutex_unlock(&iprune_mutex);
}
/*
hlist_del_init(&inode->i_hash);
spin_unlock(&inode_lock);
wake_up_inode(inode);
- if (inode->i_state != I_CLEAR)
- BUG();
+ BUG_ON(inode->i_state != I_CLEAR);
destroy_inode(inode);
}
EXPORT_SYMBOL(bmap);
/**
- * update_atime - update the access time
- * @inode: inode accessed
+ * touch_atime - update the access time
+ * @mnt: mount the inode is accessed on
+ * @dentry: dentry accessed
*
* Update the accessed time on an inode and mark it for writeback.
* This function automatically handles read only file systems and media,
* as well as the "noatime" flag and inode specific "noatime" markers.
*/
-void update_atime(struct inode *inode)
+void touch_atime(struct vfsmount *mnt, struct dentry *dentry)
{
+ struct inode *inode = dentry->d_inode;
struct timespec now;
- if (IS_NOATIME(inode))
+ if (IS_RDONLY(inode))
return;
- if (IS_NODIRATIME(inode) && S_ISDIR(inode->i_mode))
+
+ 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;
- if (IS_RDONLY(inode))
+
+ /*
+ * 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))))
return;
now = current_fs_time(inode->i_sb);
}
}
-EXPORT_SYMBOL(update_atime);
+EXPORT_SYMBOL(touch_atime);
/**
- * inode_update_time - update mtime and ctime time
- * @inode: inode accessed
- * @ctime_too: update ctime too
+ * file_update_time - update mtime and ctime time
+ * @file: file accessed
*
- * Update the mtime time on an inode and mark it for writeback.
- * When ctime_too is specified update the ctime too.
+ * Update the mtime and ctime members of an inode and mark the inode
+ * for writeback. Note that this function is meant exclusively for
+ * usage in the file write path of filesystems, and filesystems may
+ * choose to explicitly ignore update via this function with the
+ * S_NOCTIME inode flag, e.g. for network filesystem where these
+ * timestamps are handled by the server.
*/
-void inode_update_time(struct inode *inode, int ctime_too)
+void file_update_time(struct file *file)
{
+ struct inode *inode = file->f_dentry->d_inode;
struct timespec now;
int sync_it = 0;
sync_it = 1;
inode->i_mtime = now;
- if (ctime_too) {
- if (!timespec_equal(&inode->i_ctime, &now))
- sync_it = 1;
- inode->i_ctime = now;
- }
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it = 1;
+ inode->i_ctime = now;
+
if (sync_it)
mark_inode_dirty_sync(inode);
}
-EXPORT_SYMBOL(inode_update_time);
+EXPORT_SYMBOL(file_update_time);
int inode_needs_sync(struct inode *inode)
{
int loop;
/* inode slab cache */
- inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode),
- 0, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC, init_once, NULL);
+ inode_cachep = kmem_cache_create("inode_cache",
+ sizeof(struct inode),
+ 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
+ SLAB_MEM_SPREAD),
+ init_once,
+ NULL);
set_shrinker(DEFAULT_SEEKS, shrink_icache_memory);
/* Hash may have been set up in inode_init_early */