[T106][ZXW-22]7520V3SCV2.01.01.02P42U09_VEC_V0.8_AP_VEC origin source commit
Change-Id: Ic6e05d89ecd62fc34f82b23dcf306c93764aec4b
diff --git a/ap/os/linux/linux-3.4.x/fs/inode.c b/ap/os/linux/linux-3.4.x/fs/inode.c
new file mode 100644
index 0000000..8de457e
--- /dev/null
+++ b/ap/os/linux/linux-3.4.x/fs/inode.c
@@ -0,0 +1,1743 @@
+/*
+ * (C) 1997 Linus Torvalds
+ * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
+ */
+#include <linux/export.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/backing-dev.h>
+#include <linux/hash.h>
+#include <linux/swap.h>
+#include <linux/security.h>
+#include <linux/cdev.h>
+#include <linux/bootmem.h>
+#include <linux/fsnotify.h>
+#include <linux/mount.h>
+#include <linux/posix_acl.h>
+#include <linux/prefetch.h>
+#include <linux/buffer_head.h> /* for inode_has_buffers */
+#include <linux/ratelimit.h>
+#include "internal.h"
+
+/*
+ * Inode locking rules:
+ *
+ * inode->i_lock protects:
+ * inode->i_state, inode->i_hash, __iget()
+ * inode->i_sb->s_inode_lru_lock protects:
+ * inode->i_sb->s_inode_lru, inode->i_lru
+ * inode_sb_list_lock protects:
+ * sb->s_inodes, inode->i_sb_list
+ * bdi->wb.list_lock protects:
+ * bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
+ * inode_hash_lock protects:
+ * inode_hashtable, inode->i_hash
+ *
+ * Lock ordering:
+ *
+ * inode_sb_list_lock
+ * inode->i_lock
+ * inode->i_sb->s_inode_lru_lock
+ *
+ * bdi->wb.list_lock
+ * inode->i_lock
+ *
+ * inode_hash_lock
+ * inode_sb_list_lock
+ * inode->i_lock
+ *
+ * iunique_lock
+ * inode_hash_lock
+ */
+
+static unsigned int i_hash_mask __read_mostly;
+static unsigned int i_hash_shift __read_mostly;
+static struct hlist_head *inode_hashtable __read_mostly;
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
+
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
+
+/*
+ * Empty aops. Can be used for the cases where the user does not
+ * define any of the address_space operations.
+ */
+const struct address_space_operations empty_aops = {
+};
+EXPORT_SYMBOL(empty_aops);
+
+/*
+ * Statistics gathering..
+ */
+struct inodes_stat_t inodes_stat;
+
+static DEFINE_PER_CPU(unsigned int, nr_inodes);
+static DEFINE_PER_CPU(unsigned int, nr_unused);
+
+static struct kmem_cache *inode_cachep __read_mostly;
+
+static int get_nr_inodes(void)
+{
+ int i;
+ int sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_inodes, i);
+ return sum < 0 ? 0 : sum;
+}
+
+static inline int get_nr_inodes_unused(void)
+{
+ int i;
+ int sum = 0;
+ for_each_possible_cpu(i)
+ sum += per_cpu(nr_unused, i);
+ return sum < 0 ? 0 : sum;
+}
+
+int get_nr_dirty_inodes(void)
+{
+ /* not actually dirty inodes, but a wild approximation */
+ int nr_dirty = get_nr_inodes() - get_nr_inodes_unused();
+ return nr_dirty > 0 ? nr_dirty : 0;
+}
+
+/*
+ * Handle nr_inode sysctl
+ */
+#ifdef CONFIG_SYSCTL
+int proc_nr_inodes(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ inodes_stat.nr_inodes = get_nr_inodes();
+ inodes_stat.nr_unused = get_nr_inodes_unused();
+ return proc_dointvec(table, write, buffer, lenp, ppos);
+}
+#endif
+
+/**
+ * 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 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_opflags = 0;
+ 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;
+ 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);
+
+ atomic_set(&inode->i_dio_count, 0);
+
+ 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;
+ INIT_LIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */
+#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
+
+ this_cpu_inc(nr_inodes);
+
+ return 0;
+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 free_inode_nonrcu(struct inode *inode)
+{
+ kmem_cache_free(inode_cachep, inode);
+}
+EXPORT_SYMBOL(free_inode_nonrcu);
+
+void __destroy_inode(struct inode *inode)
+{
+ BUG_ON(inode_has_buffers(inode));
+ security_inode_free(inode);
+ fsnotify_inode_delete(inode);
+ if (!inode->i_nlink) {
+ WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0);
+ atomic_long_dec(&inode->i_sb->s_remove_count);
+ }
+
+#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
+ this_cpu_dec(nr_inodes);
+}
+EXPORT_SYMBOL(__destroy_inode);
+
+static void i_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ kmem_cache_free(inode_cachep, inode);
+}
+
+static void destroy_inode(struct inode *inode)
+{
+ BUG_ON(!list_empty(&inode->i_lru));
+ __destroy_inode(inode);
+ if (inode->i_sb->s_op->destroy_inode)
+ inode->i_sb->s_op->destroy_inode(inode);
+ else
+ call_rcu(&inode->i_rcu, i_callback);
+}
+
+/**
+ * drop_nlink - directly drop an inode's link count
+ * @inode: inode
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink. In cases
+ * where we are attempting to track writes to the
+ * filesystem, a decrement to zero means an imminent
+ * write when the file is truncated and actually unlinked
+ * on the filesystem.
+ */
+void drop_nlink(struct inode *inode)
+{
+ WARN_ON(inode->i_nlink == 0);
+ inode->__i_nlink--;
+ if (!inode->i_nlink)
+ atomic_long_inc(&inode->i_sb->s_remove_count);
+}
+EXPORT_SYMBOL(drop_nlink);
+
+/**
+ * clear_nlink - directly zero an inode's link count
+ * @inode: inode
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink. See
+ * drop_nlink() for why we care about i_nlink hitting zero.
+ */
+void clear_nlink(struct inode *inode)
+{
+ if (inode->i_nlink) {
+ inode->__i_nlink = 0;
+ atomic_long_inc(&inode->i_sb->s_remove_count);
+ }
+}
+EXPORT_SYMBOL(clear_nlink);
+
+/**
+ * set_nlink - directly set an inode's link count
+ * @inode: inode
+ * @nlink: new nlink (should be non-zero)
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink.
+ */
+void set_nlink(struct inode *inode, unsigned int nlink)
+{
+ if (!nlink) {
+ clear_nlink(inode);
+ } else {
+ /* Yes, some filesystems do change nlink from zero to one */
+ if (inode->i_nlink == 0)
+ atomic_long_dec(&inode->i_sb->s_remove_count);
+
+ inode->__i_nlink = nlink;
+ }
+}
+EXPORT_SYMBOL(set_nlink);
+
+/**
+ * inc_nlink - directly increment an inode's link count
+ * @inode: inode
+ *
+ * This is a low-level filesystem helper to replace any
+ * direct filesystem manipulation of i_nlink. Currently,
+ * it is only here for parity with dec_nlink().
+ */
+void inc_nlink(struct inode *inode)
+{
+ if (WARN_ON(inode->i_nlink == 0))
+ atomic_long_dec(&inode->i_sb->s_remove_count);
+
+ inode->__i_nlink++;
+}
+EXPORT_SYMBOL(inc_nlink);
+
+void address_space_init_once(struct address_space *mapping)
+{
+ memset(mapping, 0, sizeof(*mapping));
+ INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
+ spin_lock_init(&mapping->tree_lock);
+ mutex_init(&mapping->i_mmap_mutex);
+ INIT_LIST_HEAD(&mapping->private_list);
+ spin_lock_init(&mapping->private_lock);
+ INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
+ INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+}
+EXPORT_SYMBOL(address_space_init_once);
+
+/*
+ * 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_devices);
+ INIT_LIST_HEAD(&inode->i_wb_list);
+ INIT_LIST_HEAD(&inode->i_lru);
+ address_space_init_once(&inode->i_data);
+ i_size_ordered_init(inode);
+#ifdef CONFIG_FSNOTIFY
+ INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
+#endif
+}
+EXPORT_SYMBOL(inode_init_once);
+
+static void init_once(void *foo)
+{
+ struct inode *inode = (struct inode *) foo;
+
+ inode_init_once(inode);
+}
+
+/*
+ * inode->i_lock must be held
+ */
+void __iget(struct inode *inode)
+{
+ atomic_inc(&inode->i_count);
+}
+
+/*
+ * get additional reference to inode; caller must already hold one.
+ */
+void ihold(struct inode *inode)
+{
+ WARN_ON(atomic_inc_return(&inode->i_count) < 2);
+}
+EXPORT_SYMBOL(ihold);
+
+static void inode_lru_list_add(struct inode *inode)
+{
+ spin_lock(&inode->i_sb->s_inode_lru_lock);
+ if (list_empty(&inode->i_lru)) {
+ list_add(&inode->i_lru, &inode->i_sb->s_inode_lru);
+ inode->i_sb->s_nr_inodes_unused++;
+ this_cpu_inc(nr_unused);
+ }
+ spin_unlock(&inode->i_sb->s_inode_lru_lock);
+}
+
+static void inode_lru_list_del(struct inode *inode)
+{
+ spin_lock(&inode->i_sb->s_inode_lru_lock);
+ if (!list_empty(&inode->i_lru)) {
+ list_del_init(&inode->i_lru);
+ inode->i_sb->s_nr_inodes_unused--;
+ this_cpu_dec(nr_unused);
+ }
+ spin_unlock(&inode->i_sb->s_inode_lru_lock);
+}
+
+/**
+ * inode_sb_list_add - add inode to the superblock list of inodes
+ * @inode: inode to add
+ */
+void inode_sb_list_add(struct inode *inode)
+{
+ spin_lock(&inode_sb_list_lock);
+ list_add(&inode->i_sb_list, &inode->i_sb->s_inodes);
+ spin_unlock(&inode_sb_list_lock);
+}
+EXPORT_SYMBOL_GPL(inode_sb_list_add);
+
+static inline void inode_sb_list_del(struct inode *inode)
+{
+ if (!list_empty(&inode->i_sb_list)) {
+ spin_lock(&inode_sb_list_lock);
+ list_del_init(&inode->i_sb_list);
+ spin_unlock(&inode_sb_list_lock);
+ }
+}
+
+static unsigned long hash(struct super_block *sb, unsigned long hashval)
+{
+ unsigned long tmp;
+
+ tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) /
+ L1_CACHE_BYTES;
+ tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift);
+ return tmp & i_hash_mask;
+}
+
+/**
+ * __insert_inode_hash - hash an inode
+ * @inode: unhashed inode
+ * @hashval: unsigned long value used to locate this object in the
+ * inode_hashtable.
+ *
+ * Add an inode to the inode hash for this superblock.
+ */
+void __insert_inode_hash(struct inode *inode, unsigned long hashval)
+{
+ struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval);
+
+ spin_lock(&inode_hash_lock);
+ spin_lock(&inode->i_lock);
+ hlist_add_head(&inode->i_hash, b);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&inode_hash_lock);
+}
+EXPORT_SYMBOL(__insert_inode_hash);
+
+/**
+ * __remove_inode_hash - remove an inode from the hash
+ * @inode: inode to unhash
+ *
+ * Remove an inode from the superblock.
+ */
+void __remove_inode_hash(struct inode *inode)
+{
+ spin_lock(&inode_hash_lock);
+ spin_lock(&inode->i_lock);
+ hlist_del_init(&inode->i_hash);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&inode_hash_lock);
+}
+EXPORT_SYMBOL(__remove_inode_hash);
+
+void end_writeback(struct inode *inode)
+{
+ might_sleep();
+ /*
+ * We have to cycle tree_lock here because reclaim can be still in the
+ * process of removing the last page (in __delete_from_page_cache())
+ * and we must not free mapping under it.
+ */
+ spin_lock_irq(&inode->i_data.tree_lock);
+ BUG_ON(inode->i_data.nrpages);
+ spin_unlock_irq(&inode->i_data.tree_lock);
+ BUG_ON(!list_empty(&inode->i_data.private_list));
+ BUG_ON(!(inode->i_state & I_FREEING));
+ BUG_ON(inode->i_state & I_CLEAR);
+ inode_sync_wait(inode);
+ /* don't need i_lock here, no concurrent mods to i_state */
+ inode->i_state = I_FREEING | I_CLEAR;
+}
+EXPORT_SYMBOL(end_writeback);
+
+/*
+ * Free the inode passed in, removing it from the lists it is still connected
+ * to. We remove any pages still attached to the inode and wait for any IO that
+ * is still in progress before finally destroying the inode.
+ *
+ * An inode must already be marked I_FREEING so that we avoid the inode being
+ * moved back onto lists if we race with other code that manipulates the lists
+ * (e.g. writeback_single_inode). The caller is responsible for setting this.
+ *
+ * An inode must already be removed from the LRU list before being evicted from
+ * the cache. This should occur atomically with setting the I_FREEING state
+ * flag, so no inodes here should ever be on the LRU when being evicted.
+ */
+static void evict(struct inode *inode)
+{
+ const struct super_operations *op = inode->i_sb->s_op;
+
+ BUG_ON(!(inode->i_state & I_FREEING));
+ BUG_ON(!list_empty(&inode->i_lru));
+
+ if (!list_empty(&inode->i_wb_list))
+ inode_wb_list_del(inode);
+
+ inode_sb_list_del(inode);
+
+ if (op->evict_inode) {
+ op->evict_inode(inode);
+ } else {
+ if (inode->i_data.nrpages)
+ truncate_inode_pages(&inode->i_data, 0);
+ end_writeback(inode);
+ }
+ if (S_ISBLK(inode->i_mode) && inode->i_bdev)
+ bd_forget(inode);
+ if (S_ISCHR(inode->i_mode) && inode->i_cdev)
+ cd_forget(inode);
+
+ remove_inode_hash(inode);
+
+ spin_lock(&inode->i_lock);
+ wake_up_bit(&inode->i_state, __I_NEW);
+ BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
+ spin_unlock(&inode->i_lock);
+
+ destroy_inode(inode);
+}
+
+/*
+ * dispose_list - dispose of the contents of a local list
+ * @head: the head of the list to free
+ *
+ * Dispose-list gets a local list with local inodes in it, so it doesn't
+ * need to worry about list corruption and SMP locks.
+ */
+static void dispose_list(struct list_head *head)
+{
+ while (!list_empty(head)) {
+ struct inode *inode;
+
+ inode = list_first_entry(head, struct inode, i_lru);
+ list_del_init(&inode->i_lru);
+
+ evict(inode);
+ }
+}
+
+/**
+ * evict_inodes - evict all evictable inodes for a superblock
+ * @sb: superblock to operate on
+ *
+ * Make sure that no inodes with zero refcount are retained. This is
+ * called by superblock shutdown after having MS_ACTIVE flag removed,
+ * so any inode reaching zero refcount during or after that call will
+ * be immediately evicted.
+ */
+void evict_inodes(struct super_block *sb)
+{
+ struct inode *inode, *next;
+ LIST_HEAD(dispose);
+
+ spin_lock(&inode_sb_list_lock);
+ list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+ if (atomic_read(&inode->i_count))
+ continue;
+
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+
+ inode->i_state |= I_FREEING;
+ inode_lru_list_del(inode);
+ spin_unlock(&inode->i_lock);
+ list_add(&inode->i_lru, &dispose);
+ }
+ spin_unlock(&inode_sb_list_lock);
+
+ dispose_list(&dispose);
+}
+
+/**
+ * invalidate_inodes - attempt to free all inodes on a superblock
+ * @sb: superblock to operate on
+ * @kill_dirty: flag to guide handling of dirty inodes
+ *
+ * Attempts to free all inodes for a given superblock. If there were any
+ * busy inodes return a non-zero value, else zero.
+ * If @kill_dirty is set, discard dirty inodes too, otherwise treat
+ * them as busy.
+ */
+int invalidate_inodes(struct super_block *sb, bool kill_dirty)
+{
+ int busy = 0;
+ struct inode *inode, *next;
+ LIST_HEAD(dispose);
+
+ spin_lock(&inode_sb_list_lock);
+ list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) {
+ spin_lock(&inode->i_lock);
+ if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (inode->i_state & I_DIRTY && !kill_dirty) {
+ spin_unlock(&inode->i_lock);
+ busy = 1;
+ continue;
+ }
+ if (atomic_read(&inode->i_count)) {
+ spin_unlock(&inode->i_lock);
+ busy = 1;
+ continue;
+ }
+
+ inode->i_state |= I_FREEING;
+ inode_lru_list_del(inode);
+ spin_unlock(&inode->i_lock);
+ list_add(&inode->i_lru, &dispose);
+ }
+ spin_unlock(&inode_sb_list_lock);
+
+ dispose_list(&dispose);
+
+ return busy;
+}
+
+static int can_unuse(struct inode *inode)
+{
+ if (inode->i_state & ~I_REFERENCED)
+ return 0;
+ if (inode_has_buffers(inode))
+ return 0;
+ if (atomic_read(&inode->i_count))
+ return 0;
+ if (inode->i_data.nrpages)
+ return 0;
+ return 1;
+}
+
+/*
+ * Walk the superblock inode LRU for freeable inodes and attempt to free them.
+ * This is called from the superblock shrinker function with a number of inodes
+ * to trim from the LRU. Inodes to be freed are moved to a temporary list and
+ * then are freed outside inode_lock by dispose_list().
+ *
+ * Any inodes which are pinned purely because of attached pagecache have their
+ * pagecache removed. If the inode has metadata buffers attached to
+ * mapping->private_list then try to remove them.
+ *
+ * If the inode has the I_REFERENCED flag set, then it means that it has been
+ * used recently - the flag is set in iput_final(). When we encounter such an
+ * inode, clear the flag and move it to the back of the LRU so it gets another
+ * pass through the LRU before it gets reclaimed. This is necessary because of
+ * the fact we are doing lazy LRU updates to minimise lock contention so the
+ * LRU does not have strict ordering. Hence we don't want to reclaim inodes
+ * with this flag set because they are the inodes that are out of order.
+ */
+void prune_icache_sb(struct super_block *sb, int nr_to_scan)
+{
+ LIST_HEAD(freeable);
+ int nr_scanned;
+ unsigned long reap = 0;
+
+ spin_lock(&sb->s_inode_lru_lock);
+ for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
+ struct inode *inode;
+
+ if (list_empty(&sb->s_inode_lru))
+ break;
+
+ inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
+
+ /*
+ * we are inverting the sb->s_inode_lru_lock/inode->i_lock here,
+ * so use a trylock. If we fail to get the lock, just move the
+ * inode to the back of the list so we don't spin on it.
+ */
+ if (!spin_trylock(&inode->i_lock)) {
+ list_move(&inode->i_lru, &sb->s_inode_lru);
+ continue;
+ }
+
+ /*
+ * Referenced or dirty inodes are still in use. Give them
+ * another pass through the LRU as we canot reclaim them now.
+ */
+ if (atomic_read(&inode->i_count) ||
+ (inode->i_state & ~I_REFERENCED)) {
+ list_del_init(&inode->i_lru);
+ spin_unlock(&inode->i_lock);
+ sb->s_nr_inodes_unused--;
+ this_cpu_dec(nr_unused);
+ continue;
+ }
+
+ /* recently referenced inodes get one more pass */
+ if (inode->i_state & I_REFERENCED) {
+ inode->i_state &= ~I_REFERENCED;
+ list_move(&inode->i_lru, &sb->s_inode_lru);
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (inode_has_buffers(inode) || inode->i_data.nrpages) {
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&sb->s_inode_lru_lock);
+ if (remove_inode_buffers(inode))
+ reap += invalidate_mapping_pages(&inode->i_data,
+ 0, -1);
+ iput(inode);
+ spin_lock(&sb->s_inode_lru_lock);
+
+ if (inode != list_entry(sb->s_inode_lru.next,
+ struct inode, i_lru))
+ continue; /* wrong inode or list_empty */
+ /* avoid lock inversions with trylock */
+ if (!spin_trylock(&inode->i_lock))
+ continue;
+ if (!can_unuse(inode)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ }
+ WARN_ON(inode->i_state & I_NEW);
+ inode->i_state |= I_FREEING;
+ spin_unlock(&inode->i_lock);
+
+ list_move(&inode->i_lru, &freeable);
+ sb->s_nr_inodes_unused--;
+ this_cpu_dec(nr_unused);
+ }
+ if (current_is_kswapd())
+ __count_vm_events(KSWAPD_INODESTEAL, reap);
+ else
+ __count_vm_events(PGINODESTEAL, reap);
+ spin_unlock(&sb->s_inode_lru_lock);
+ if (current->reclaim_state)
+ current->reclaim_state->reclaimed_slab += reap;
+
+ dispose_list(&freeable);
+}
+
+static void __wait_on_freeing_inode(struct inode *inode);
+/*
+ * Called with the inode lock held.
+ */
+static struct inode *find_inode(struct super_block *sb,
+ struct hlist_head *head,
+ int (*test)(struct inode *, void *),
+ void *data)
+{
+ struct hlist_node *node;
+ struct inode *inode = NULL;
+
+repeat:
+ hlist_for_each_entry(inode, node, head, i_hash) {
+ spin_lock(&inode->i_lock);
+ if (inode->i_sb != sb) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (!test(inode, data)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
+ __wait_on_freeing_inode(inode);
+ goto repeat;
+ }
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ return inode;
+ }
+ return NULL;
+}
+
+/*
+ * find_inode_fast is the fast path version of find_inode, see the comment at
+ * iget_locked for details.
+ */
+static struct inode *find_inode_fast(struct super_block *sb,
+ struct hlist_head *head, unsigned long ino)
+{
+ struct hlist_node *node;
+ struct inode *inode = NULL;
+
+repeat:
+ hlist_for_each_entry(inode, node, head, i_hash) {
+ spin_lock(&inode->i_lock);
+ if (inode->i_ino != ino) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (inode->i_sb != sb) {
+ spin_unlock(&inode->i_lock);
+ continue;
+ }
+ if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
+ __wait_on_freeing_inode(inode);
+ goto repeat;
+ }
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ return inode;
+ }
+ return NULL;
+}
+
+/*
+ * Each cpu owns a range of LAST_INO_BATCH numbers.
+ * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations,
+ * to renew the exhausted range.
+ *
+ * This does not significantly increase overflow rate because every CPU can
+ * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is
+ * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the
+ * 2^32 range, and is a worst-case. Even a 50% wastage would only increase
+ * overflow rate by 2x, which does not seem too significant.
+ *
+ * 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.
+ */
+#define LAST_INO_BATCH 1024
+static DEFINE_PER_CPU(unsigned int, last_ino);
+
+unsigned int get_next_ino(void)
+{
+ unsigned int *p = &get_cpu_var(last_ino);
+ unsigned int res = *p;
+
+#ifdef CONFIG_SMP
+ if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) {
+ static atomic_t shared_last_ino;
+ int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino);
+
+ res = next - LAST_INO_BATCH;
+ }
+#endif
+
+ *p = ++res;
+ put_cpu_var(last_ino);
+ return res;
+}
+EXPORT_SYMBOL(get_next_ino);
+
+/**
+ * new_inode_pseudo - obtain an inode
+ * @sb: superblock
+ *
+ * Allocates a new inode for given superblock.
+ * Inode wont be chained in superblock s_inodes list
+ * This means :
+ * - fs can't be unmount
+ * - quotas, fsnotify, writeback can't work
+ */
+struct inode *new_inode_pseudo(struct super_block *sb)
+{
+ struct inode *inode = alloc_inode(sb);
+
+ if (inode) {
+ spin_lock(&inode->i_lock);
+ inode->i_state = 0;
+ spin_unlock(&inode->i_lock);
+ INIT_LIST_HEAD(&inode->i_sb_list);
+ }
+ return inode;
+}
+
+/**
+ * new_inode - obtain an inode
+ * @sb: superblock
+ *
+ * Allocates a new inode for given superblock. The default gfp_mask
+ * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE.
+ * 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)
+{
+ struct inode *inode;
+
+ spin_lock_prefetch(&inode_sb_list_lock);
+
+ inode = new_inode_pseudo(sb);
+ if (inode)
+ inode_sb_list_add(inode);
+ return inode;
+}
+EXPORT_SYMBOL(new_inode);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void lockdep_annotate_inode_mutex_key(struct inode *inode)
+{
+ if (S_ISDIR(inode->i_mode)) {
+ struct file_system_type *type = inode->i_sb->s_type;
+
+ /* Set new key only if filesystem hasn't already changed it */
+ if (lockdep_match_class(&inode->i_mutex, &type->i_mutex_key)) {
+ /*
+ * 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);
+ }
+ }
+}
+EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key);
+#endif
+
+/**
+ * unlock_new_inode - clear the I_NEW state and wake up any waiters
+ * @inode: new inode to unlock
+ *
+ * Called when the inode is fully initialised to clear the new state of the
+ * inode and wake up anyone waiting for the inode to finish initialisation.
+ */
+void unlock_new_inode(struct inode *inode)
+{
+ lockdep_annotate_inode_mutex_key(inode);
+ spin_lock(&inode->i_lock);
+ WARN_ON(!(inode->i_state & I_NEW));
+ inode->i_state &= ~I_NEW;
+ smp_mb();
+ wake_up_bit(&inode->i_state, __I_NEW);
+ spin_unlock(&inode->i_lock);
+}
+EXPORT_SYMBOL(unlock_new_inode);
+
+/**
+ * iget5_locked - obtain an inode from a mounted file system
+ * @sb: super block of file system
+ * @hashval: hash value (usually inode number) to get
+ * @test: callback used for comparisons between inodes
+ * @set: callback used to initialize a new struct inode
+ * @data: opaque data pointer to pass to @test and @set
+ *
+ * Search for the inode specified by @hashval and @data in the inode cache,
+ * and if present it is return it with an increased reference count. This is
+ * a generalized version of iget_locked() for file systems where the inode
+ * number is not sufficient for unique identification of an inode.
+ *
+ * If the inode is not in cache, allocate a new inode and return it locked,
+ * hashed, and with the I_NEW flag set. The file system gets to fill it in
+ * before unlocking it via unlock_new_inode().
+ *
+ * Note both @test and @set are called with the inode_hash_lock held, so can't
+ * sleep.
+ */
+struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
+ int (*test)(struct inode *, void *),
+ int (*set)(struct inode *, void *), void *data)
+{
+ struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+ struct inode *inode;
+
+ spin_lock(&inode_hash_lock);
+ inode = find_inode(sb, head, test, data);
+ spin_unlock(&inode_hash_lock);
+
+ if (inode) {
+ wait_on_inode(inode);
+ return inode;
+ }
+
+ inode = alloc_inode(sb);
+ if (inode) {
+ struct inode *old;
+
+ spin_lock(&inode_hash_lock);
+ /* We released the lock, so.. */
+ old = find_inode(sb, head, test, data);
+ if (!old) {
+ if (set(inode, data))
+ goto set_failed;
+
+ spin_lock(&inode->i_lock);
+ inode->i_state = I_NEW;
+ hlist_add_head(&inode->i_hash, head);
+ spin_unlock(&inode->i_lock);
+ inode_sb_list_add(inode);
+ spin_unlock(&inode_hash_lock);
+
+ /* Return the locked inode with I_NEW set, the
+ * caller is responsible for filling in the contents
+ */
+ return inode;
+ }
+
+ /*
+ * Uhhuh, somebody else created the same inode under
+ * us. Use the old inode instead of the one we just
+ * allocated.
+ */
+ spin_unlock(&inode_hash_lock);
+ destroy_inode(inode);
+ inode = old;
+ wait_on_inode(inode);
+ }
+ return inode;
+
+set_failed:
+ spin_unlock(&inode_hash_lock);
+ destroy_inode(inode);
+ return NULL;
+}
+EXPORT_SYMBOL(iget5_locked);
+
+/**
+ * iget_locked - obtain an inode from a mounted file system
+ * @sb: super block of file system
+ * @ino: inode number to get
+ *
+ * Search for the inode specified by @ino in the inode cache and if present
+ * return it with an increased reference count. This is for file systems
+ * where the inode number is sufficient for unique identification of an inode.
+ *
+ * If the inode is not in cache, allocate a new inode and return it locked,
+ * hashed, and with the I_NEW flag set. The file system gets to fill it in
+ * before unlocking it via unlock_new_inode().
+ */
+struct inode *iget_locked(struct super_block *sb, unsigned long ino)
+{
+ struct hlist_head *head = inode_hashtable + hash(sb, ino);
+ struct inode *inode;
+
+ spin_lock(&inode_hash_lock);
+ inode = find_inode_fast(sb, head, ino);
+ spin_unlock(&inode_hash_lock);
+ if (inode) {
+ wait_on_inode(inode);
+ return inode;
+ }
+
+ inode = alloc_inode(sb);
+ if (inode) {
+ struct inode *old;
+
+ spin_lock(&inode_hash_lock);
+ /* We released the lock, so.. */
+ old = find_inode_fast(sb, head, ino);
+ if (!old) {
+ inode->i_ino = ino;
+ spin_lock(&inode->i_lock);
+ inode->i_state = I_NEW;
+ hlist_add_head(&inode->i_hash, head);
+ spin_unlock(&inode->i_lock);
+ inode_sb_list_add(inode);
+ spin_unlock(&inode_hash_lock);
+
+ /* Return the locked inode with I_NEW set, the
+ * caller is responsible for filling in the contents
+ */
+ return inode;
+ }
+
+ /*
+ * Uhhuh, somebody else created the same inode under
+ * us. Use the old inode instead of the one we just
+ * allocated.
+ */
+ spin_unlock(&inode_hash_lock);
+ destroy_inode(inode);
+ inode = old;
+ wait_on_inode(inode);
+ }
+ return inode;
+}
+EXPORT_SYMBOL(iget_locked);
+
+/*
+ * search the inode cache for a matching inode number.
+ * If we find one, then the inode number we are trying to
+ * allocate is not unique and so we should not use it.
+ *
+ * Returns 1 if the inode number is unique, 0 if it is not.
+ */
+static int test_inode_iunique(struct super_block *sb, unsigned long ino)
+{
+ struct hlist_head *b = inode_hashtable + hash(sb, ino);
+ struct hlist_node *node;
+ struct inode *inode;
+
+ spin_lock(&inode_hash_lock);
+ hlist_for_each_entry(inode, node, b, i_hash) {
+ if (inode->i_ino == ino && inode->i_sb == sb) {
+ spin_unlock(&inode_hash_lock);
+ return 0;
+ }
+ }
+ spin_unlock(&inode_hash_lock);
+
+ return 1;
+}
+
+/**
+ * iunique - get a unique inode number
+ * @sb: superblock
+ * @max_reserved: highest reserved inode number
+ *
+ * Obtain an inode number that is unique on the system for a given
+ * superblock. This is used by file systems that have no natural
+ * permanent inode numbering system. An inode number is returned that
+ * is higher than the reserved limit but unique.
+ *
+ * BUGS:
+ * With a large number of inodes live on the file system this function
+ * currently becomes quite slow.
+ */
+ino_t iunique(struct super_block *sb, ino_t max_reserved)
+{
+ /*
+ * 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 DEFINE_SPINLOCK(iunique_lock);
+ static unsigned int counter;
+ ino_t res;
+
+ spin_lock(&iunique_lock);
+ do {
+ if (counter <= max_reserved)
+ counter = max_reserved + 1;
+ res = counter++;
+ } while (!test_inode_iunique(sb, res));
+ spin_unlock(&iunique_lock);
+
+ return res;
+}
+EXPORT_SYMBOL(iunique);
+
+struct inode *igrab(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) {
+ __iget(inode);
+ spin_unlock(&inode->i_lock);
+ } else {
+ spin_unlock(&inode->i_lock);
+ /*
+ * Handle the case where s_op->clear_inode is not been
+ * called yet, and somebody is calling igrab
+ * while the inode is getting freed.
+ */
+ inode = NULL;
+ }
+ return inode;
+}
+EXPORT_SYMBOL(igrab);
+
+/**
+ * ilookup5_nowait - search for an inode in the inode cache
+ * @sb: super block of file system to search
+ * @hashval: hash value (usually inode number) to search for
+ * @test: callback used for comparisons between inodes
+ * @data: opaque data pointer to pass to @test
+ *
+ * Search for the inode specified by @hashval and @data in the inode cache.
+ * If the inode is in the cache, the inode is returned with an incremented
+ * reference count.
+ *
+ * Note: I_NEW is not waited upon so you have to be very careful what you do
+ * with the returned inode. You probably should be using ilookup5() instead.
+ *
+ * Note2: @test is called with the inode_hash_lock held, so can't sleep.
+ */
+struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
+ int (*test)(struct inode *, void *), void *data)
+{
+ struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+ struct inode *inode;
+
+ spin_lock(&inode_hash_lock);
+ inode = find_inode(sb, head, test, data);
+ spin_unlock(&inode_hash_lock);
+
+ return inode;
+}
+EXPORT_SYMBOL(ilookup5_nowait);
+
+/**
+ * ilookup5 - search for an inode in the inode cache
+ * @sb: super block of file system to search
+ * @hashval: hash value (usually inode number) to search for
+ * @test: callback used for comparisons between inodes
+ * @data: opaque data pointer to pass to @test
+ *
+ * Search for the inode specified by @hashval and @data in the inode cache,
+ * and if the inode is in the cache, return the inode with an incremented
+ * reference count. Waits on I_NEW before returning the inode.
+ * returned with an incremented reference count.
+ *
+ * This is a generalized version of ilookup() for file systems where the
+ * inode number is not sufficient for unique identification of an inode.
+ *
+ * Note: @test is called with the inode_hash_lock held, so can't sleep.
+ */
+struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
+ int (*test)(struct inode *, void *), void *data)
+{
+ struct inode *inode = ilookup5_nowait(sb, hashval, test, data);
+
+ if (inode)
+ wait_on_inode(inode);
+ return inode;
+}
+EXPORT_SYMBOL(ilookup5);
+
+/**
+ * ilookup - search for an inode in the inode cache
+ * @sb: super block of file system to search
+ * @ino: inode number to search for
+ *
+ * Search for the inode @ino in the inode cache, and if the inode is in the
+ * cache, the inode is returned with an incremented reference count.
+ */
+struct inode *ilookup(struct super_block *sb, unsigned long ino)
+{
+ struct hlist_head *head = inode_hashtable + hash(sb, ino);
+ struct inode *inode;
+
+ spin_lock(&inode_hash_lock);
+ inode = find_inode_fast(sb, head, ino);
+ spin_unlock(&inode_hash_lock);
+
+ if (inode)
+ wait_on_inode(inode);
+ return inode;
+}
+EXPORT_SYMBOL(ilookup);
+
+int insert_inode_locked(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+ ino_t ino = inode->i_ino;
+ struct hlist_head *head = inode_hashtable + hash(sb, ino);
+
+ while (1) {
+ struct hlist_node *node;
+ struct inode *old = NULL;
+ spin_lock(&inode_hash_lock);
+ hlist_for_each_entry(old, node, head, i_hash) {
+ if (old->i_ino != ino)
+ continue;
+ if (old->i_sb != sb)
+ continue;
+ spin_lock(&old->i_lock);
+ if (old->i_state & (I_FREEING|I_WILL_FREE)) {
+ spin_unlock(&old->i_lock);
+ continue;
+ }
+ break;
+ }
+ if (likely(!node)) {
+ spin_lock(&inode->i_lock);
+ inode->i_state |= I_NEW;
+ hlist_add_head(&inode->i_hash, head);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&inode_hash_lock);
+ return 0;
+ }
+ __iget(old);
+ spin_unlock(&old->i_lock);
+ spin_unlock(&inode_hash_lock);
+ wait_on_inode(old);
+ if (unlikely(!inode_unhashed(old))) {
+ iput(old);
+ return -EBUSY;
+ }
+ iput(old);
+ }
+}
+EXPORT_SYMBOL(insert_inode_locked);
+
+int insert_inode_locked4(struct inode *inode, unsigned long hashval,
+ int (*test)(struct inode *, void *), void *data)
+{
+ struct super_block *sb = inode->i_sb;
+ struct hlist_head *head = inode_hashtable + hash(sb, hashval);
+
+ while (1) {
+ struct hlist_node *node;
+ struct inode *old = NULL;
+
+ spin_lock(&inode_hash_lock);
+ hlist_for_each_entry(old, node, head, i_hash) {
+ if (old->i_sb != sb)
+ continue;
+ if (!test(old, data))
+ continue;
+ spin_lock(&old->i_lock);
+ if (old->i_state & (I_FREEING|I_WILL_FREE)) {
+ spin_unlock(&old->i_lock);
+ continue;
+ }
+ break;
+ }
+ if (likely(!node)) {
+ spin_lock(&inode->i_lock);
+ inode->i_state |= I_NEW;
+ hlist_add_head(&inode->i_hash, head);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&inode_hash_lock);
+ return 0;
+ }
+ __iget(old);
+ spin_unlock(&old->i_lock);
+ spin_unlock(&inode_hash_lock);
+ wait_on_inode(old);
+ if (unlikely(!inode_unhashed(old))) {
+ iput(old);
+ return -EBUSY;
+ }
+ iput(old);
+ }
+}
+EXPORT_SYMBOL(insert_inode_locked4);
+
+
+int generic_delete_inode(struct inode *inode)
+{
+ return 1;
+}
+EXPORT_SYMBOL(generic_delete_inode);
+
+/*
+ * Called when we're dropping the last reference
+ * to an inode.
+ *
+ * Call the FS "drop_inode()" function, defaulting to
+ * the legacy UNIX filesystem behaviour. If it tells
+ * us to evict inode, do so. Otherwise, retain inode
+ * in cache if fs is alive, sync and evict if fs is
+ * shutting down.
+ */
+static void iput_final(struct inode *inode)
+{
+ struct super_block *sb = inode->i_sb;
+ const struct super_operations *op = inode->i_sb->s_op;
+ int drop;
+
+ WARN_ON(inode->i_state & I_NEW);
+
+ if (op->drop_inode)
+ drop = op->drop_inode(inode);
+ else
+ drop = generic_drop_inode(inode);
+
+ if (!drop && (sb->s_flags & MS_ACTIVE)) {
+ inode->i_state |= I_REFERENCED;
+ if (!(inode->i_state & (I_DIRTY|I_SYNC)))
+ inode_lru_list_add(inode);
+ spin_unlock(&inode->i_lock);
+ return;
+ }
+
+ if (!drop) {
+ inode->i_state |= I_WILL_FREE;
+ spin_unlock(&inode->i_lock);
+ write_inode_now(inode, 1);
+ spin_lock(&inode->i_lock);
+ WARN_ON(inode->i_state & I_NEW);
+ inode->i_state &= ~I_WILL_FREE;
+ }
+
+ inode->i_state |= I_FREEING;
+ if (!list_empty(&inode->i_lru))
+ inode_lru_list_del(inode);
+ spin_unlock(&inode->i_lock);
+
+ evict(inode);
+}
+
+/**
+ * iput - put an inode
+ * @inode: inode to put
+ *
+ * Puts an inode, dropping its usage count. If the inode use count hits
+ * zero, the inode is then freed and may also be destroyed.
+ *
+ * Consequently, iput() can sleep.
+ */
+void iput(struct inode *inode)
+{
+ if (inode) {
+ BUG_ON(inode->i_state & I_CLEAR);
+
+ if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
+ iput_final(inode);
+ }
+}
+EXPORT_SYMBOL(iput);
+
+/**
+ * bmap - find a block number in a file
+ * @inode: inode of file
+ * @block: block to find
+ *
+ * Returns the block number on the device holding the inode that
+ * is the disk block number for the block of the file requested.
+ * That is, asked for block 4 of inode 1 the function will return the
+ * disk block relative to the disk start that holds that block of the
+ * file.
+ */
+sector_t bmap(struct inode *inode, sector_t block)
+{
+ sector_t res = 0;
+ if (inode->i_mapping->a_ops->bmap)
+ res = inode->i_mapping->a_ops->bmap(inode->i_mapping, block);
+ return res;
+}
+EXPORT_SYMBOL(bmap);
+
+/*
+ * With relative atime, only update atime if the previous atime is
+ * earlier than either the ctime or mtime or if at least a day has
+ * passed since the last atime update.
+ */
+static int relatime_need_update(struct vfsmount *mnt, struct inode *inode,
+ struct timespec now)
+{
+
+ if (!(mnt->mnt_flags & MNT_RELATIME))
+ return 1;
+ /*
+ * Is mtime younger than atime? If yes, update atime:
+ */
+ if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0)
+ return 1;
+ /*
+ * Is ctime younger than atime? If yes, update atime:
+ */
+ if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0)
+ return 1;
+
+ /*
+ * Is the previous atime value older than a day? If yes,
+ * update atime:
+ */
+ if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60)
+ return 1;
+ /*
+ * Good, we can skip the atime update:
+ */
+ return 0;
+}
+
+/**
+ * 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 touch_atime(struct path *path)
+{
+ struct vfsmount *mnt = path->mnt;
+ struct inode *inode = path->dentry->d_inode;
+ struct timespec now;
+
+ if (inode->i_flags & S_NOATIME)
+ return;
+ if (IS_NOATIME(inode))
+ return;
+ if ((inode->i_sb->s_flags & MS_NODIRATIME) && S_ISDIR(inode->i_mode))
+ return;
+
+ if (mnt->mnt_flags & MNT_NOATIME)
+ return;
+ if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode))
+ return;
+
+ now = current_fs_time(inode->i_sb);
+
+ if (!relatime_need_update(mnt, inode, now))
+ return;
+
+ if (timespec_equal(&inode->i_atime, &now))
+ return;
+
+ if (mnt_want_write(mnt))
+ return;
+
+ inode->i_atime = now;
+ mark_inode_dirty_sync(inode);
+ mnt_drop_write(mnt);
+}
+EXPORT_SYMBOL(touch_atime);
+
+/**
+ * file_update_time - update mtime and ctime time
+ * @file: file accessed
+ *
+ * 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_NOCMTIME inode flag, e.g. for network filesystem where these
+ * timestamps are handled by the server.
+ */
+
+void file_update_time(struct file *file)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct timespec now;
+ enum { S_MTIME = 1, S_CTIME = 2, S_VERSION = 4 } sync_it = 0;
+
+ /* First try to exhaust all avenues to not sync */
+ if (IS_NOCMTIME(inode))
+ return;
+
+ now = current_fs_time(inode->i_sb);
+ if (!timespec_equal(&inode->i_mtime, &now))
+ sync_it = S_MTIME;
+
+ if (!timespec_equal(&inode->i_ctime, &now))
+ sync_it |= S_CTIME;
+
+ if (IS_I_VERSION(inode))
+ sync_it |= S_VERSION;
+
+ if (!sync_it)
+ return;
+
+ /* Finally allowed to write? Takes lock. */
+ if (mnt_want_write_file(file))
+ return;
+
+ /* Only change inode inside the lock region */
+ if (sync_it & S_VERSION)
+ inode_inc_iversion(inode);
+ if (sync_it & S_CTIME)
+ inode->i_ctime = now;
+ if (sync_it & S_MTIME)
+ inode->i_mtime = now;
+ mark_inode_dirty_sync(inode);
+ mnt_drop_write_file(file);
+}
+EXPORT_SYMBOL(file_update_time);
+
+int inode_needs_sync(struct inode *inode)
+{
+ if (IS_SYNC(inode))
+ return 1;
+ if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode))
+ return 1;
+ return 0;
+}
+EXPORT_SYMBOL(inode_needs_sync);
+
+int inode_wait(void *word)
+{
+ schedule();
+ return 0;
+}
+EXPORT_SYMBOL(inode_wait);
+
+/*
+ * If we try to find an inode in the inode hash while it is being
+ * deleted, we have to wait until the filesystem completes its
+ * deletion before reporting that it isn't found. This function waits
+ * until the deletion _might_ have completed. Callers are responsible
+ * to recheck inode state.
+ *
+ * It doesn't matter if I_NEW is not set initially, a call to
+ * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list
+ * will DTRT.
+ */
+static void __wait_on_freeing_inode(struct inode *inode)
+{
+ wait_queue_head_t *wq;
+ DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
+ wq = bit_waitqueue(&inode->i_state, __I_NEW);
+ prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(&inode_hash_lock);
+ schedule();
+ finish_wait(wq, &wait.wait);
+ spin_lock(&inode_hash_lock);
+}
+
+static __initdata unsigned long ihash_entries;
+static int __init set_ihash_entries(char *str)
+{
+ if (!str)
+ return 0;
+ ihash_entries = simple_strtoul(str, &str, 0);
+ return 1;
+}
+__setup("ihash_entries=", set_ihash_entries);
+
+/*
+ * Initialize the waitqueues and inode hash table.
+ */
+void __init inode_init_early(void)
+{
+ unsigned int loop;
+
+ /* If hashes are distributed across NUMA nodes, defer
+ * hash allocation until vmalloc space is available.
+ */
+ if (hashdist)
+ return;
+
+ inode_hashtable =
+ alloc_large_system_hash("Inode-cache",
+ sizeof(struct hlist_head),
+ ihash_entries,
+ 14,
+ HASH_EARLY,
+ &i_hash_shift,
+ &i_hash_mask,
+ 0);
+
+ for (loop = 0; loop < (1U << i_hash_shift); loop++)
+ INIT_HLIST_HEAD(&inode_hashtable[loop]);
+}
+
+void __init inode_init(void)
+{
+ unsigned int loop;
+
+ /* inode slab cache */
+ inode_cachep = kmem_cache_create("inode_cache",
+ sizeof(struct inode),
+ 0,
+ (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
+ SLAB_MEM_SPREAD),
+ init_once);
+
+ /* Hash may have been set up in inode_init_early */
+ if (!hashdist)
+ return;
+
+ inode_hashtable =
+ alloc_large_system_hash("Inode-cache",
+ sizeof(struct hlist_head),
+ ihash_entries,
+ 14,
+ 0,
+ &i_hash_shift,
+ &i_hash_mask,
+ 0);
+
+ for (loop = 0; loop < (1U << i_hash_shift); loop++)
+ INIT_HLIST_HEAD(&inode_hashtable[loop]);
+}
+
+void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
+{
+ inode->i_mode = mode;
+ if (S_ISCHR(mode)) {
+ inode->i_fop = &def_chr_fops;
+ inode->i_rdev = rdev;
+ } else if (S_ISBLK(mode)) {
+ inode->i_fop = &def_blk_fops;
+ inode->i_rdev = rdev;
+ } else if (S_ISFIFO(mode))
+ inode->i_fop = &def_fifo_fops;
+ else if (S_ISSOCK(mode))
+ inode->i_fop = &bad_sock_fops;
+ else
+ printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for"
+ " inode %s:%lu\n", mode, inode->i_sb->s_id,
+ inode->i_ino);
+}
+EXPORT_SYMBOL(init_special_inode);
+
+/**
+ * inode_init_owner - Init uid,gid,mode for new inode according to posix standards
+ * @inode: New inode
+ * @dir: Directory inode
+ * @mode: mode of the new inode
+ */
+void inode_init_owner(struct inode *inode, const struct inode *dir,
+ umode_t mode)
+{
+ inode->i_uid = current_fsuid();
+ if (dir && dir->i_mode & S_ISGID) {
+ inode->i_gid = dir->i_gid;
+ if (S_ISDIR(mode))
+ mode |= S_ISGID;
+ } else
+ inode->i_gid = current_fsgid();
+ inode->i_mode = mode;
+}
+EXPORT_SYMBOL(inode_init_owner);
+
+/**
+ * inode_owner_or_capable - check current task permissions to inode
+ * @inode: inode being checked
+ *
+ * Return true if current either has CAP_FOWNER to the inode, or
+ * owns the file.
+ */
+bool inode_owner_or_capable(const struct inode *inode)
+{
+ struct user_namespace *ns = inode_userns(inode);
+
+ if (current_user_ns() == ns && current_fsuid() == inode->i_uid)
+ return true;
+ if (ns_capable(ns, CAP_FOWNER))
+ return true;
+ return false;
+}
+EXPORT_SYMBOL(inode_owner_or_capable);