1 files changed, 48 insertions, 88 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 4be128cbc754..a48fa5355fb4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -33,8 +33,8 @@
  *
  * inode->i_lock protects:
  *   inode->i_state, inode->i_hash, __iget()
- * inode_lru_lock protects:
- *   inode_lru, inode->i_lru
+ * 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:
@@ -46,7 +46,7 @@
  *
  * inode_sb_list_lock
  *   inode->i_lock
- *     inode_lru_lock
+ *     inode->i_sb->s_inode_lru_lock
  *
  * bdi->wb.list_lock
  *   inode->i_lock
@@ -64,23 +64,9 @@ 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);
 
-static LIST_HEAD(inode_lru);
-static DEFINE_SPINLOCK(inode_lru_lock);
-
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_sb_list_lock);
 
 /*
- * iprune_sem provides exclusion between the icache shrinking and the
- * umount path.
- *
- * 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.
- */
-static DECLARE_RWSEM(iprune_sem);
-
-/*
  * Empty aops. Can be used for the cases where the user does not
  * define any of the address_space operations.
  */
@@ -94,6 +80,7 @@ EXPORT_SYMBOL(empty_aops);
 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;
 
@@ -108,7 +95,11 @@ static int get_nr_inodes(void)
 
 static inline int get_nr_inodes_unused(void)
 {
-	return inodes_stat.nr_unused;
+	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)
@@ -126,6 +117,7 @@ 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
@@ -175,8 +167,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	mutex_init(&inode->i_mutex);
 	lockdep_set_class(&inode->i_mutex, &sb->s_type->i_mutex_key);
 
-	init_rwsem(&inode->i_alloc_sem);
-	lockdep_set_class(&inode->i_alloc_sem, &sb->s_type->i_alloc_sem_key);
+	atomic_set(&inode->i_dio_count, 0);
 
 	mapping->a_ops = &empty_aops;
 	mapping->host = inode;
@@ -336,22 +327,24 @@ EXPORT_SYMBOL(ihold);
 
 static void inode_lru_list_add(struct inode *inode)
 {
-	spin_lock(&inode_lru_lock);
+	spin_lock(&inode->i_sb->s_inode_lru_lock);
 	if (list_empty(&inode->i_lru)) {
-		list_add(&inode->i_lru, &inode_lru);
-		inodes_stat.nr_unused++;
+		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_lru_lock);
+	spin_unlock(&inode->i_sb->s_inode_lru_lock);
 }
 
 static void inode_lru_list_del(struct inode *inode)
 {
-	spin_lock(&inode_lru_lock);
+	spin_lock(&inode->i_sb->s_inode_lru_lock);
 	if (!list_empty(&inode->i_lru)) {
 		list_del_init(&inode->i_lru);
-		inodes_stat.nr_unused--;
+		inode->i_sb->s_nr_inodes_unused--;
+		this_cpu_dec(nr_unused);
 	}
-	spin_unlock(&inode_lru_lock);
+	spin_unlock(&inode->i_sb->s_inode_lru_lock);
 }
 
 /**
@@ -422,7 +415,14 @@ 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);
@@ -529,14 +529,6 @@ void evict_inodes(struct super_block *sb)
 	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);
 }
 
 /**
@@ -599,8 +591,10 @@ 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_lru_lock by dispose_list().
+ * 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
@@ -614,29 +608,28 @@ static int can_unuse(struct inode *inode)
  * 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)
+void prune_icache_sb(struct super_block *sb, int nr_to_scan)
 {
 	LIST_HEAD(freeable);
 	int nr_scanned;
 	unsigned long reap = 0;
 
-	down_read(&iprune_sem);
-	spin_lock(&inode_lru_lock);
-	for (nr_scanned = 0; nr_scanned < nr_to_scan; nr_scanned++) {
+	spin_lock(&sb->s_inode_lru_lock);
+	for (nr_scanned = nr_to_scan; nr_scanned >= 0; nr_scanned--) {
 		struct inode *inode;
 
-		if (list_empty(&inode_lru))
+		if (list_empty(&sb->s_inode_lru))
 			break;
 
-		inode = list_entry(inode_lru.prev, struct inode, i_lru);
+		inode = list_entry(sb->s_inode_lru.prev, struct inode, i_lru);
 
 		/*
-		 * we are inverting the inode_lru_lock/inode->i_lock here,
+		 * 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, &inode_lru);
+			list_move(&inode->i_lru, &sb->s_inode_lru);
 			continue;
 		}
 
@@ -648,28 +641,29 @@ static void prune_icache(int nr_to_scan)
 		    (inode->i_state & ~I_REFERENCED)) {
 			list_del_init(&inode->i_lru);
 			spin_unlock(&inode->i_lock);
-			inodes_stat.nr_unused--;
+			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, &inode_lru);
+			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(&inode_lru_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(&inode_lru_lock);
+			spin_lock(&sb->s_inode_lru_lock);
 
-			if (inode != list_entry(inode_lru.next,
+			if (inode != list_entry(sb->s_inode_lru.next,
 						struct inode, i_lru))
 				continue;	/* wrong inode or list_empty */
 			/* avoid lock inversions with trylock */
@@ -685,51 +679,18 @@ static void prune_icache(int nr_to_scan)
 		spin_unlock(&inode->i_lock);
 
 		list_move(&inode->i_lru, &freeable);
-		inodes_stat.nr_unused--;
+		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(&inode_lru_lock);
+	spin_unlock(&sb->s_inode_lru_lock);
 
 	dispose_list(&freeable);
-	up_read(&iprune_sem);
 }
 
-/*
- * shrink_icache_memory() will attempt to reclaim some unused inodes.  Here,
- * "unused" means that no dentries are referring to the inodes: the files are
- * not open and the dcache references to those inodes have already been
- * reclaimed.
- *
- * 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,
-				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,
-		 * and we don't want to recurse into the FS that called us
-		 * in clear_inode() and friends..
-		 */
-		if (!(gfp_mask & __GFP_FS))
-			return -1;
-		prune_icache(nr);
-	}
-	return (get_nr_inodes_unused() / 100) * sysctl_vfs_cache_pressure;
-}
-
-static struct shrinker icache_shrinker = {
-	.shrink = shrink_icache_memory,
-	.seeks = DEFAULT_SEEKS,
-};
-
 static void __wait_on_freeing_inode(struct inode *inode);
 /*
  * Called with the inode lock held.
@@ -1323,7 +1284,7 @@ static void iput_final(struct inode *inode)
 
 	WARN_ON(inode->i_state & I_NEW);
 
-	if (op && op->drop_inode)
+	if (op->drop_inode)
 		drop = op->drop_inode(inode);
 	else
 		drop = generic_drop_inode(inode);
@@ -1609,7 +1570,6 @@ void __init inode_init(void)
 					 (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|
 					 SLAB_MEM_SPREAD),
 					 init_once);
-	register_shrinker(&icache_shrinker);
 
 	/* Hash may have been set up in inode_init_early */
 	if (!hashdist)