Merge 'Linux v3.0' into Litmus

Some notes:
* Litmus^RT scheduling class is the topmost scheduling class
  (above stop_sched_class).
* scheduler_ipi() function (e.g., in smp_reschedule_interrupt())
  may increase IPI latencies.
* Added path into schedule() to quickly re-evaluate scheduling
  decision without becoming preemptive again. This used to be
  a standard path before the removal of BKL.

Conflicts:
	Makefile
	arch/arm/kernel/calls.S
	arch/arm/kernel/smp.c
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/smp.c
	arch/x86/kernel/syscall_table_32.S
	include/linux/hrtimer.h
	kernel/printk.c
	kernel/sched.c
	kernel/sched_fair.c

1 files changed, 653 insertions, 519 deletions

diff --git a/fs/inode.c b/fs/inode.c
index d4fe9c031864..dbf0e760c0a9 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1,9 +1,7 @@
 /*
- * linux/fs/inode.c
- *
  * (C) 1997 Linus Torvalds
+ * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation)
  */
-
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/dcache.h>
@@ -24,95 +22,114 @@
 #include <linux/mount.h>
 #include <linux/async.h>
 #include <linux/posix_acl.h>
+#include <linux/prefetch.h>
+#include <linux/ima.h>
+#include <linux/cred.h>
+#include <linux/buffer_head.h> /* for inode_has_buffers */
+#include "internal.h"
 
 /*
- * This is needed for the following functions:
- *  - inode_has_buffers
- *  - invalidate_inode_buffers
- *  - invalidate_bdev
+ * Inode locking rules:
  *
- * FIXME: remove all knowledge of the buffer layer from this file
- */
-#include <linux/buffer_head.h>
-
-/*
- * New inode.c implementation.
+ * inode->i_lock protects:
+ *   inode->i_state, inode->i_hash, __iget()
+ * inode_lru_lock protects:
+ *   inode_lru, inode->i_lru
+ * inode_sb_list_lock protects:
+ *   sb->s_inodes, inode->i_sb_list
+ * inode_wb_list_lock protects:
+ *   bdi->wb.b_{dirty,io,more_io}, inode->i_wb_list
+ * inode_hash_lock protects:
+ *   inode_hashtable, inode->i_hash
  *
- * This implementation has the basic premise of trying
- * to be extremely low-overhead and SMP-safe, yet be
- * simple enough to be "obviously correct".
+ * Lock ordering:
  *
- * 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.
+ * inode_sb_list_lock
+ *   inode->i_lock
+ *     inode_lru_lock
+ *
+ * inode_wb_list_lock
+ *   inode->i_lock
+ *
+ * inode_hash_lock
+ *   inode_sb_list_lock
+ *   inode->i_lock
+ *
+ * iunique_lock
+ *   inode_hash_lock
  */
-#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;
+static struct hlist_head *inode_hashtable __read_mostly;
+static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock);
 
-/*
- * 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.
- */
+static LIST_HEAD(inode_lru);
+static DEFINE_SPINLOCK(inode_lru_lock);
 
-LIST_HEAD(inode_in_use);
-LIST_HEAD(inode_unused);
-static struct hlist_head *inode_hashtable __read_mostly;
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
+__cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_wb_list_lock);
 
 /*
- * A simple spinlock to protect the list manipulations.
+ * iprune_sem provides exclusion between the icache shrinking and the
+ * umount path.
  *
- * NOTE! You also have to own the lock if you change
- * the i_state of an inode while it is in use..
+ * We don't actually need it to protect anything in the umount path,
+ * but only need to cycle through it to make sure any inode that
+ * prune_icache took off the LRU list has been fully torn down by the
+ * time we are past evict_inodes.
  */
-DEFINE_SPINLOCK(inode_lock);
+static DECLARE_RWSEM(iprune_sem);
 
 /*
- * iprune_sem 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.
- *
- * We make this an rwsem because the fastpath is icache shrinking. In
- * some cases a filesystem may be doing a significant amount of work in
- * its inode reclaim code, so this should improve parallelism.
+ * Empty aops. Can be used for the cases where the user does not
+ * define any of the address_space operations.
  */
-static DECLARE_RWSEM(iprune_sem);
+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 struct kmem_cache *inode_cachep __read_mostly;
 
-static void wake_up_inode(struct inode *inode)
+static int get_nr_inodes(void)
 {
-        /*
-         * Prevent speculative execution through spin_unlock(&inode_lock);
-         */
-        smp_mb();
-        wake_up_bit(&inode->i_state, __I_NEW);
+        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)
+{
+        return inodes_stat.nr_unused;
+}
+
+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();
+        return proc_dointvec(table, write, buffer, lenp, ppos);
 }
+#endif
 
 /**
  * inode_init_always - perform inode structure intialisation
@@ -124,7 +141,6 @@ static void wake_up_inode(struct inode *inode)
  */
 int inode_init_always(struct super_block *sb, struct inode *inode)
 {
-        static const struct address_space_operations empty_aops;
         static const struct inode_operations empty_iops;
         static const struct file_operations empty_fops;
         struct address_space *const mapping = &inode->i_data;
@@ -192,6 +208,8 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
         inode->i_fsnotify_mask = 0;
 #endif
 
+        this_cpu_inc(nr_inodes);
+
         return 0;
 out:
         return -ENOMEM;
@@ -221,6 +239,12 @@ static struct inode *alloc_inode(struct super_block *sb)
         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));
@@ -232,18 +256,40 @@ void __destroy_inode(struct inode *inode)
         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);
 
-void destroy_inode(struct inode *inode)
+static void 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(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
-                kmem_cache_free(inode_cachep, (inode));
+                call_rcu(&inode->i_rcu, i_callback);
 }
 
+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
@@ -255,13 +301,9 @@ void inode_init_once(struct inode *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);
+        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);
@@ -279,34 +321,150 @@ static void init_once(void *foo)
 }
 
 /*
- * inode_lock must be held
+ * inode->i_lock must be held
  */
 void __iget(struct inode *inode)
 {
-        if (atomic_inc_return(&inode->i_count) != 1)
-                return;
+        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_lru_lock);
+        if (list_empty(&inode->i_lru)) {
+                list_add(&inode->i_lru, &inode_lru);
+                inodes_stat.nr_unused++;
+        }
+        spin_unlock(&inode_lru_lock);
+}
+
+static void inode_lru_list_del(struct inode *inode)
+{
+        spin_lock(&inode_lru_lock);
+        if (!list_empty(&inode->i_lru)) {
+                list_del_init(&inode->i_lru);
+                inodes_stat.nr_unused--;
+        }
+        spin_unlock(&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)
+{
+        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);
 
-        if (!(inode->i_state & (I_DIRTY|I_SYNC)))
-                list_move(&inode->i_list, &inode_in_use);
-        inodes_stat.nr_unused--;
+        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));
+
+        inode_wb_list_del(inode);
+        inode_sb_list_del(inode);
+
         if (op->evict_inode) {
                 op->evict_inode(inode);
         } else {
@@ -318,6 +476,15 @@ static void evict(struct inode *inode)
                 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);
 }
 
 /*
@@ -329,101 +496,108 @@ static void evict(struct inode *inode)
  */
 static void dispose_list(struct list_head *head)
 {
-        int nr_disposed = 0;
-
         while (!list_empty(head)) {
                 struct inode *inode;
 
-                inode = list_first_entry(head, struct inode, i_list);
-                list_del(&inode->i_list);
+                inode = list_first_entry(head, struct inode, i_lru);
+                list_del_init(&inode->i_lru);
 
                 evict(inode);
-
-                spin_lock(&inode_lock);
-                hlist_del_init(&inode->i_hash);
-                list_del_init(&inode->i_sb_list);
-                spin_unlock(&inode_lock);
-
-                wake_up_inode(inode);
-                destroy_inode(inode);
-                nr_disposed++;
         }
-        spin_lock(&inode_lock);
-        inodes_stat.nr_inodes -= nr_disposed;
-        spin_unlock(&inode_lock);
 }
 
-/*
- * Invalidate all inodes for a device.
+/**
+ * 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.
  */
-static int invalidate_list(struct list_head *head, struct list_head *dispose)
+void evict_inodes(struct super_block *sb)
 {
-        struct list_head *next;
-        int busy = 0, count = 0;
+        struct inode *inode, *next;
+        LIST_HEAD(dispose);
 
-        next = head->next;
-        for (;;) {
-                struct list_head *tmp = next;
-                struct inode *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
-                 * shrink_icache_memory() away.
-                 */
-                cond_resched_lock(&inode_lock);
-
-                next = next->next;
-                if (tmp == head)
-                        break;
-                inode = list_entry(tmp, struct inode, i_sb_list);
-                if (inode->i_state & I_NEW)
+        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;
-                invalidate_inode_buffers(inode);
-                if (!atomic_read(&inode->i_count)) {
-                        list_move(&inode->i_list, dispose);
-                        WARN_ON(inode->i_state & I_NEW);
-                        inode->i_state |= I_FREEING;
-                        count++;
+
+                spin_lock(&inode->i_lock);
+                if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+                        spin_unlock(&inode->i_lock);
                         continue;
                 }
-                busy = 1;
+
+                inode->i_state |= I_FREEING;
+                inode_lru_list_del(inode);
+                spin_unlock(&inode->i_lock);
+                list_add(&inode->i_lru, &dispose);
         }
-        /* only unused inodes may be cached with i_count zero */
-        inodes_stat.nr_unused -= count;
-        return busy;
+        spin_unlock(&inode_sb_list_lock);
+
+        dispose_list(&dispose);
+
+        /*
+         * Cycle through iprune_sem to make sure any inode that prune_icache
+         * moved off the list before we took the lock has been fully torn
+         * down.
+         */
+        down_write(&iprune_sem);
+        up_write(&iprune_sem);
 }
 
 /**
- *      invalidate_inodes       - discard the inodes on a device
- *      @sb: superblock
+ * invalidate_inodes    - attempt to free all inodes on a superblock
+ * @sb:         superblock to operate on
+ * @kill_dirty: flag to guide handling of dirty inodes
  *
- *      Discard all of the inodes for a given superblock. If the discard
- *      fails because there are busy inodes then a non zero value is returned.
- *      If the discard is successful all the inodes have been discarded.
+ * 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)
+int invalidate_inodes(struct super_block *sb, bool kill_dirty)
 {
-        int busy;
-        LIST_HEAD(throw_away);
+        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;
+                }
 
-        down_write(&iprune_sem);
-        spin_lock(&inode_lock);
-        fsnotify_unmount_inodes(&sb->s_inodes);
-        busy = invalidate_list(&sb->s_inodes, &throw_away);
-        spin_unlock(&inode_lock);
+                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(&throw_away);
-        up_write(&iprune_sem);
+        dispose_list(&dispose);
 
         return busy;
 }
-EXPORT_SYMBOL(invalidate_inodes);
 
 static int can_unuse(struct inode *inode)
 {
-        if (inode->i_state)
+        if (inode->i_state & ~I_REFERENCED)
                 return 0;
         if (inode_has_buffers(inode))
                 return 0;
@@ -435,65 +609,99 @@ static int can_unuse(struct inode *inode)
 }
 
 /*
- * Scan `goal' inodes on the unused list for freeable ones. They are moved to
- * a temporary list and then are freed outside inode_lock by dispose_list().
+ * Scan `goal' inodes on the unused list for freeable ones. They are moved to a
+ * temporary list and then are freed outside inode_lru_lock by dispose_list().
  *
  * Any inodes which are pinned purely because of attached pagecache have their
- * pagecache removed.  We expect the final iput() on that inode to add it to
- * the front of the inode_unused list.  So look for it there and if the
- * inode is still freeable, proceed.  The right inode is found 99.9% of the
- * time in testing on a 4-way.
+ * pagecache removed.  If the inode has metadata buffers attached to
+ * mapping->private_list then try to remove them.
  *
- * 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.
  */
 static void prune_icache(int nr_to_scan)
 {
         LIST_HEAD(freeable);
-        int nr_pruned = 0;
         int nr_scanned;
         unsigned long reap = 0;
 
         down_read(&iprune_sem);
-        spin_lock(&inode_lock);
+        spin_lock(&inode_lru_lock);
         for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
                 struct inode *inode;
 
-                if (list_empty(&inode_unused))
+                if (list_empty(&inode_lru))
                         break;
 
-                inode = list_entry(inode_unused.prev, struct inode, i_list);
+                inode = list_entry(inode_lru.prev, struct inode, i_lru);
+
+                /*
+                 * we are inverting the 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, &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);
+                        inodes_stat.nr_unused--;
+                        continue;
+                }
 
-                if (inode->i_state || atomic_read(&inode->i_count)) {
-                        list_move(&inode->i_list, &inode_unused);
+                /* recently referenced inodes get one more pass */
+                if (inode->i_state & I_REFERENCED) {
+                        inode->i_state &= ~I_REFERENCED;
+                        list_move(&inode->i_lru, &inode_lru);
+                        spin_unlock(&inode->i_lock);
                         continue;
                 }
                 if (inode_has_buffers(inode) || inode->i_data.nrpages) {
                         __iget(inode);
-                        spin_unlock(&inode_lock);
+                        spin_unlock(&inode->i_lock);
+                        spin_unlock(&inode_lru_lock);
                         if (remove_inode_buffers(inode))
                                 reap += invalidate_mapping_pages(&inode->i_data,
                                                                 0, -1);
                         iput(inode);
-                        spin_lock(&inode_lock);
+                        spin_lock(&inode_lru_lock);
 
-                        if (inode != list_entry(inode_unused.next,
-                                                struct inode, i_list))
+                        if (inode != list_entry(inode_lru.next,
+                                                struct inode, i_lru))
                                 continue;       /* wrong inode or list_empty */
-                        if (!can_unuse(inode))
+                        /* avoid lock inversions with trylock */
+                        if (!spin_trylock(&inode->i_lock))
                                 continue;
+                        if (!can_unuse(inode)) {
+                                spin_unlock(&inode->i_lock);
+                                continue;
+                        }
                 }
-                list_move(&inode->i_list, &freeable);
                 WARN_ON(inode->i_state & I_NEW);
                 inode->i_state |= I_FREEING;
-                nr_pruned++;
+                spin_unlock(&inode->i_lock);
+
+                list_move(&inode->i_lru, &freeable);
+                inodes_stat.nr_unused--;
         }
-        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);
+        spin_unlock(&inode_lru_lock);
 
         dispose_list(&freeable);
         up_read(&iprune_sem);
@@ -508,8 +716,12 @@ static void prune_icache(int nr_to_scan)
  * This function is passed the number of inodes to scan, and it returns the
  * total number of remaining possibly-reclaimable inodes.
  */
-static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int shrink_icache_memory(struct shrinker *shrink,
+                                struct shrink_control *sc)
 {
+        int nr = sc->nr_to_scan;
+        gfp_t gfp_mask = sc->gfp_mask;
+
         if (nr) {
                 /*
                  * Nasty deadlock avoidance.  We may hold various FS locks,
@@ -520,7 +732,7 @@ static int shrink_icache_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
                         return -1;
                 prune_icache(nr);
         }
-        return (inodes_stat.nr_unused / 100) * sysctl_vfs_cache_pressure;
+        return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure;
 }
 
 static struct shrinker icache_shrinker = {
@@ -531,9 +743,6 @@ static struct shrinker icache_shrinker = {
 static void __wait_on_freeing_inode(struct inode *inode);
 /*
  * Called with the inode lock held.
- * NOTE: we are not increasing the inode-refcount, you must call __iget()
- * by hand after calling find_inode now! This simplifies iunique and won't
- * add any additional branch in the common code.
  */
 static struct inode *find_inode(struct super_block *sb,
                                 struct hlist_head *head,
@@ -545,17 +754,24 @@ static struct inode *find_inode(struct super_block *sb,
 
 repeat:
         hlist_for_each_entry(inode, node, head, i_hash) {
-                if (inode->i_sb != sb)
+                spin_lock(&inode->i_lock);
+                if (inode->i_sb != sb) {
+                        spin_unlock(&inode->i_lock);
                         continue;
-                if (!test(inode, data))
+                }
+                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;
                 }
-                break;
+                __iget(inode);
+                spin_unlock(&inode->i_lock);
+                return inode;
         }
-        return node ? inode : NULL;
+        return NULL;
 }
 
 /*
@@ -570,61 +786,63 @@ static struct inode *find_inode_fast(struct super_block *sb,
 
 repeat:
         hlist_for_each_entry(inode, node, head, i_hash) {
-                if (inode->i_ino != ino)
+                spin_lock(&inode->i_lock);
+                if (inode->i_ino != ino) {
+                        spin_unlock(&inode->i_lock);
                         continue;
-                if (inode->i_sb != sb)
+                }
+                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;
                 }
-                break;
+                __iget(inode);
+                spin_unlock(&inode->i_lock);
+                return inode;
         }
-        return node ? inode : NULL;
-}
-
-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_HASHBITS);
-        return tmp & I_HASHMASK;
-}
-
-static inline void
-__inode_add_to_lists(struct super_block *sb, struct hlist_head *head,
-                        struct inode *inode)
-{
-        inodes_stat.nr_inodes++;
-        list_add(&inode->i_list, &inode_in_use);
-        list_add(&inode->i_sb_list, &sb->s_inodes);
-        if (head)
-                hlist_add_head(&inode->i_hash, head);
+        return NULL;
 }
 
-/**
- * inode_add_to_lists - add a new inode to relevant lists
- * @sb: superblock inode belongs to
- * @inode: inode to mark in use
+/*
+ * 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.
  *
- * When an inode is allocated it needs to be accounted for, added to the in use
- * list, the owning superblock and the inode hash. This needs to be done under
- * the inode_lock, so export a function to do this rather than the inode lock
- * itself. We calculate the hash list to add to here so it is all internal
- * which requires the caller to have already set up the inode number in the
- * inode to add.
+ * 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.
  */
-void inode_add_to_lists(struct super_block *sb, struct inode *inode)
+#define LAST_INO_BATCH 1024
+static DEFINE_PER_CPU(unsigned int, last_ino);
+
+unsigned int get_next_ino(void)
 {
-        struct hlist_head *head = inode_hashtable + hash(sb, inode->i_ino);
+        unsigned int *p = &get_cpu_var(last_ino);
+        unsigned int res = *p;
 
-        spin_lock(&inode_lock);
-        __inode_add_to_lists(sb, head, inode);
-        spin_unlock(&inode_lock);
+#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_GPL(inode_add_to_lists);
+EXPORT_SYMBOL(get_next_ino);
 
 /**
  *      new_inode       - obtain an inode
@@ -640,32 +858,32 @@ EXPORT_SYMBOL_GPL(inode_add_to_lists);
  */
 struct inode *new_inode(struct super_block *sb)
 {
-        /*
-         * 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);
+        spin_lock_prefetch(&inode_sb_list_lock);
 
         inode = alloc_inode(sb);
         if (inode) {
-                spin_lock(&inode_lock);
-                __inode_add_to_lists(sb, NULL, inode);
-                inode->i_ino = ++last_ino;
+                spin_lock(&inode->i_lock);
                 inode->i_state = 0;
-                spin_unlock(&inode_lock);
+                spin_unlock(&inode->i_lock);
+                inode_sb_list_add(inode);
         }
         return inode;
 }
 EXPORT_SYMBOL(new_inode);
 
+/**
+ * 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)
 {
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
-        if (inode->i_mode & S_IFDIR) {
+        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 */
@@ -681,50 +899,67 @@ void unlock_new_inode(struct inode *inode)
                 }
         }
 #endif
-        /*
-         * This is special!  We do not need the spinlock when clearing I_NEW,
-         * because we're guaranteed that nobody else tries to do anything about
-         * the state of the inode when it is locked, as we just created it (so
-         * there can be no old holders that haven't tested I_NEW).
-         * However we must emit the memory barrier so that other CPUs reliably
-         * see the clearing of I_NEW after the other inode initialisation has
-         * completed.
-         */
-        smp_mb();
+        spin_lock(&inode->i_lock);
         WARN_ON(!(inode->i_state & I_NEW));
         inode->i_state &= ~I_NEW;
-        wake_up_inode(inode);
+        wake_up_bit(&inode->i_state, __I_NEW);
+        spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(unlock_new_inode);
 
-/*
- * This is called without the inode lock held.. Be careful.
+/**
+ * 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
  *
- * We no longer cache the sb_flags in i_flags - see fs.h
- *      -- rmk@arm.uk.linux.org
+ * 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.
  */
-static struct inode *get_new_inode(struct super_block *sb,
-                                struct hlist_head *head,
-                                int (*test)(struct inode *, void *),
-                                int (*set)(struct inode *, void *),
-                                void *data)
+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_lock);
+                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;
 
-                        __inode_add_to_lists(sb, head, inode);
+                        spin_lock(&inode->i_lock);
                         inode->i_state = I_NEW;
-                        spin_unlock(&inode_lock);
+                        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
@@ -737,8 +972,7 @@ static struct inode *get_new_inode(struct super_block *sb,
                  * us. Use the old inode instead of the one we just
                  * allocated.
                  */
-                __iget(old);
-                spin_unlock(&inode_lock);
+                spin_unlock(&inode_hash_lock);
                 destroy_inode(inode);
                 inode = old;
                 wait_on_inode(inode);
@@ -746,32 +980,53 @@ static struct inode *get_new_inode(struct super_block *sb,
         return inode;
 
 set_failed:
-        spin_unlock(&inode_lock);
+        spin_unlock(&inode_hash_lock);
         destroy_inode(inode);
         return NULL;
 }
+EXPORT_SYMBOL(iget5_locked);
 
-/*
- * get_new_inode_fast is the fast path version of get_new_inode, see the
- * comment at iget_locked for details.
+/**
+ * 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().
  */
-static struct inode *get_new_inode_fast(struct super_block *sb,
-                                struct hlist_head *head, unsigned long ino)
+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_lock);
+                spin_lock(&inode_hash_lock);
                 /* We released the lock, so.. */
                 old = find_inode_fast(sb, head, ino);
                 if (!old) {
                         inode->i_ino = ino;
-                        __inode_add_to_lists(sb, head, inode);
+                        spin_lock(&inode->i_lock);
                         inode->i_state = I_NEW;
-                        spin_unlock(&inode_lock);
+                        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
@@ -784,14 +1039,39 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
                  * us. Use the old inode instead of the one we just
                  * allocated.
                  */
-                __iget(old);
-                spin_unlock(&inode_lock);
+                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
@@ -814,20 +1094,17 @@ ino_t iunique(struct super_block *sb, ino_t max_reserved)
          * 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;
-        struct inode *inode;
-        struct hlist_head *head;
         ino_t res;
 
-        spin_lock(&inode_lock);
+        spin_lock(&iunique_lock);
         do {
                 if (counter <= max_reserved)
                         counter = max_reserved + 1;
                 res = counter++;
-                head = inode_hashtable + hash(sb, res);
-                inode = find_inode_fast(sb, head, res);
-        } while (inode != NULL);
-        spin_unlock(&inode_lock);
+        } while (!test_inode_iunique(sb, res));
+        spin_unlock(&iunique_lock);
 
         return res;
 }
@@ -835,118 +1112,50 @@ EXPORT_SYMBOL(iunique);
 
 struct inode *igrab(struct inode *inode)
 {
-        spin_lock(&inode_lock);
-        if (!(inode->i_state & (I_FREEING|I_WILL_FREE)))
+        spin_lock(&inode->i_lock);
+        if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) {
                 __iget(inode);
-        else
+                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;
-        spin_unlock(&inode_lock);
+        }
         return inode;
 }
 EXPORT_SYMBOL(igrab);
 
 /**
- * ifind - internal function, you want ilookup5() or iget5().
- * @sb:         super block of file system to search
- * @head:       the head of the list to search
- * @test:       callback used for comparisons between inodes
- * @data:       opaque data pointer to pass to @test
- * @wait:       if true wait for the inode to be unlocked, if false do not
- *
- * ifind() searches for the inode specified by @data in the inode
- * cache. This is a generalized version of ifind_fast() for file systems where
- * the inode number is not sufficient for unique identification of an inode.
- *
- * If the inode is in the cache, the inode is returned with an incremented
- * reference count.
- *
- * Otherwise NULL is returned.
- *
- * Note, @test is called with the inode_lock held, so can't sleep.
- */
-static struct inode *ifind(struct super_block *sb,
-                struct hlist_head *head, int (*test)(struct inode *, void *),
-                void *data, const int wait)
-{
-        struct inode *inode;
-
-        spin_lock(&inode_lock);
-        inode = find_inode(sb, head, test, data);
-        if (inode) {
-                __iget(inode);
-                spin_unlock(&inode_lock);
-                if (likely(wait))
-                        wait_on_inode(inode);
-                return inode;
-        }
-        spin_unlock(&inode_lock);
-        return NULL;
-}
-
-/**
- * ifind_fast - internal function, you want ilookup() or iget().
- * @sb:         super block of file system to search
- * @head:       head of the list to search
- * @ino:        inode number to search for
- *
- * ifind_fast() searches for the inode @ino in the inode cache. This is for
- * file systems where the inode number is sufficient for unique identification
- * of an inode.
- *
- * If the inode is in the cache, the inode is returned with an incremented
- * reference count.
- *
- * Otherwise NULL is returned.
- */
-static struct inode *ifind_fast(struct super_block *sb,
-                struct hlist_head *head, unsigned long ino)
-{
-        struct inode *inode;
-
-        spin_lock(&inode_lock);
-        inode = find_inode_fast(sb, head, ino);
-        if (inode) {
-                __iget(inode);
-                spin_unlock(&inode_lock);
-                wait_on_inode(inode);
-                return inode;
-        }
-        spin_unlock(&inode_lock);
-        return NULL;
-}
-
-/**
  * 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
  *
- * ilookup5() uses ifind() to search for the inode specified by @hashval and
- * @data in the inode cache. This is a generalized version of ilookup() for
- * file systems where the inode number is not sufficient for unique
- * identification of an inode.
- *
+ * 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, the inode lock 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.
+ * reference count.
  *
- * Otherwise NULL is returned.
+ * 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.
  *
- * Note, @test is called with the inode_lock held, so can't sleep.
+ * 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 ifind(sb, head, test, data, 0);
+        return inode;
 }
 EXPORT_SYMBOL(ilookup5_nowait);
 
@@ -957,24 +1166,24 @@ EXPORT_SYMBOL(ilookup5_nowait);
  * @test:       callback used for comparisons between inodes
  * @data:       opaque data pointer to pass to @test
  *
- * ilookup5() uses ifind() to search for the inode specified by @hashval and
- * @data in the inode cache. This is a generalized version of ilookup() for
- * file systems where the inode number is not sufficient for unique
- * identification of an inode.
- *
- * If the inode is in the cache, the inode lock is waited upon and the inode is
+ * 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.
  *
- * Otherwise NULL is returned.
+ * 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_lock held, so can't sleep.
+ * 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 hlist_head *head = inode_hashtable + hash(sb, hashval);
+        struct inode *inode = ilookup5_nowait(sb, hashval, test, data);
 
-        return ifind(sb, head, test, data, 1);
+        if (inode)
+                wait_on_inode(inode);
+        return inode;
 }
 EXPORT_SYMBOL(ilookup5);
 
@@ -983,91 +1192,23 @@ EXPORT_SYMBOL(ilookup5);
  * @sb:         super block of file system to search
  * @ino:        inode number to search for
  *
- * ilookup() uses ifind_fast() to search for the inode @ino in the inode cache.
- * This is for file systems where the inode number is sufficient for unique
- * identification of an inode.
- *
- * If the inode is in the cache, the inode is returned with an incremented
- * reference count.
- *
- * Otherwise NULL is returned.
+ * 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);
-
-        return ifind_fast(sb, head, ino);
-}
-EXPORT_SYMBOL(ilookup);
-
-/**
- * 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
- *
- * 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
- * systems where the inode number is not sufficient for unique identification
- * of an inode.
- *
- * If the inode is not in cache, get_new_inode() is called to allocate a new
- * inode and this is returned 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_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;
 
-        inode = ifind(sb, head, test, data, 1);
-        if (inode)
-                return inode;
-        /*
-         * get_new_inode() will do the right thing, re-trying the search
-         * in case it had to block at any point.
-         */
-        return get_new_inode(sb, head, test, set, data);
-}
-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
- *
- * 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
- * unique identification of an inode.
- *
- * If the inode is not in cache, get_new_inode_fast() is called to allocate a
- * new inode and this is returned 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);
 
-        inode = ifind_fast(sb, head, ino);
         if (inode)
-                return inode;
-        /*
-         * get_new_inode_fast() will do the right thing, re-trying the search
-         * in case it had to block at any point.
-         */
-        return get_new_inode_fast(sb, head, ino);
+                wait_on_inode(inode);
+        return inode;
 }
-EXPORT_SYMBOL(iget_locked);
+EXPORT_SYMBOL(ilookup);
 
 int insert_inode_locked(struct inode *inode)
 {
@@ -1075,29 +1216,35 @@ int insert_inode_locked(struct inode *inode)
         ino_t ino = inode->i_ino;
         struct hlist_head *head = inode_hashtable + hash(sb, ino);
 
-        inode->i_state |= I_NEW;
         while (1) {
                 struct hlist_node *node;
                 struct inode *old = NULL;
-                spin_lock(&inode_lock);
+                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;
-                        if (old->i_state & (I_FREEING|I_WILL_FREE))
+                        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_lock);
+                        spin_unlock(&inode->i_lock);
+                        spin_unlock(&inode_hash_lock);
                         return 0;
                 }
                 __iget(old);
-                spin_unlock(&inode_lock);
+                spin_unlock(&old->i_lock);
+                spin_unlock(&inode_hash_lock);
                 wait_on_inode(old);
-                if (unlikely(!hlist_unhashed(&old->i_hash))) {
+                if (unlikely(!inode_unhashed(old))) {
                         iput(old);
                         return -EBUSY;
                 }
@@ -1112,31 +1259,36 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
         struct super_block *sb = inode->i_sb;
         struct hlist_head *head = inode_hashtable + hash(sb, hashval);
 
-        inode->i_state |= I_NEW;
-
         while (1) {
                 struct hlist_node *node;
                 struct inode *old = NULL;
 
-                spin_lock(&inode_lock);
+                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;
-                        if (old->i_state & (I_FREEING|I_WILL_FREE))
+                        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_lock);
+                        spin_unlock(&inode->i_lock);
+                        spin_unlock(&inode_hash_lock);
                         return 0;
                 }
                 __iget(old);
-                spin_unlock(&inode_lock);
+                spin_unlock(&old->i_lock);
+                spin_unlock(&inode_hash_lock);
                 wait_on_inode(old);
-                if (unlikely(!hlist_unhashed(&old->i_hash))) {
+                if (unlikely(!inode_unhashed(old))) {
                         iput(old);
                         return -EBUSY;
                 }
@@ -1145,36 +1297,6 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 }
 EXPORT_SYMBOL(insert_inode_locked4);
 
-/**
- *      __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 *head = inode_hashtable + hash(inode->i_sb, hashval);
-        spin_lock(&inode_lock);
-        hlist_add_head(&inode->i_hash, head);
-        spin_unlock(&inode_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_lock);
-        hlist_del_init(&inode->i_hash);
-        spin_unlock(&inode_lock);
-}
-EXPORT_SYMBOL(remove_inode_hash);
 
 int generic_delete_inode(struct inode *inode)
 {
@@ -1189,7 +1311,7 @@ EXPORT_SYMBOL(generic_delete_inode);
  */
 int generic_drop_inode(struct inode *inode)
 {
-        return !inode->i_nlink || hlist_unhashed(&inode->i_hash);
+        return !inode->i_nlink || inode_unhashed(inode);
 }
 EXPORT_SYMBOL_GPL(generic_drop_inode);
 
@@ -1209,42 +1331,35 @@ static void iput_final(struct inode *inode)
         const struct super_operations *op = inode->i_sb->s_op;
         int drop;
 
+        WARN_ON(inode->i_state & I_NEW);
+
         if (op && op->drop_inode)
                 drop = op->drop_inode(inode);
         else
                 drop = generic_drop_inode(inode);
 
-        if (!drop) {
+        if (!drop && (sb->s_flags & MS_ACTIVE)) {
+                inode->i_state |= I_REFERENCED;
                 if (!(inode->i_state & (I_DIRTY|I_SYNC)))
-                        list_move(&inode->i_list, &inode_unused);
-                inodes_stat.nr_unused++;
-                if (sb->s_flags & MS_ACTIVE) {
-                        spin_unlock(&inode_lock);
-                        return;
-                }
-                WARN_ON(inode->i_state & I_NEW);
+                        inode_lru_list_add(inode);
+                spin_unlock(&inode->i_lock);
+                return;
+        }
+
+        if (!drop) {
                 inode->i_state |= I_WILL_FREE;
-                spin_unlock(&inode_lock);
+                spin_unlock(&inode->i_lock);
                 write_inode_now(inode, 1);
-                spin_lock(&inode_lock);
+                spin_lock(&inode->i_lock);
                 WARN_ON(inode->i_state & I_NEW);
                 inode->i_state &= ~I_WILL_FREE;
-                inodes_stat.nr_unused--;
-                hlist_del_init(&inode->i_hash);
         }
-        list_del_init(&inode->i_list);
-        list_del_init(&inode->i_sb_list);
-        WARN_ON(inode->i_state & I_NEW);
+
         inode->i_state |= I_FREEING;
-        inodes_stat.nr_inodes--;
-        spin_unlock(&inode_lock);
+        inode_lru_list_del(inode);
+        spin_unlock(&inode->i_lock);
+
         evict(inode);
-        spin_lock(&inode_lock);
-        hlist_del_init(&inode->i_hash);
-        spin_unlock(&inode_lock);
-        wake_up_inode(inode);
-        BUG_ON(inode->i_state != (I_FREEING | I_CLEAR));
-        destroy_inode(inode);
 }
 
 /**
@@ -1261,7 +1376,7 @@ void iput(struct inode *inode)
         if (inode) {
                 BUG_ON(inode->i_state & I_CLEAR);
 
-                if (atomic_dec_and_lock(&inode->i_count, &inode_lock))
+                if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock))
                         iput_final(inode);
         }
 }
@@ -1440,9 +1555,8 @@ EXPORT_SYMBOL(inode_wait);
  * to recheck inode state.
  *
  * It doesn't matter if I_NEW is not set initially, a call to
- * wake_up_inode() after removing from the hash list will DTRT.
- *
- * This is called with inode_lock held.
+ * 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)
 {
@@ -1450,10 +1564,11 @@ static void __wait_on_freeing_inode(struct inode *inode)
         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_lock);
+        spin_unlock(&inode->i_lock);
+        spin_unlock(&inode_hash_lock);
         schedule();
         finish_wait(wq, &wait.wait);
-        spin_lock(&inode_lock);
+        spin_lock(&inode_hash_lock);
 }
 
 static __initdata unsigned long ihash_entries;
@@ -1545,7 +1660,7 @@ void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
 EXPORT_SYMBOL(init_special_inode);
 
 /**
- * Init uid,gid,mode for new inode according to posix standards
+ * 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
@@ -1563,3 +1678,22 @@ void inode_init_owner(struct inode *inode, const struct inode *dir,
         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);