fs: inode split IO and LRU lists

The use of the same inode list structure (inode->i_list) for two
different list constructs with different lifecycles and purposes
makes it impossible to separate the locking of the different
operations. Therefore, to enable the separation of the locking of
the writeback and reclaim lists, split the inode->i_list into two
separate lists dedicated to their specific tracking functions.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/block_dev.c

@@ -59,7 +59,7 @@ static void bdev_inode_switch_bdi(struct inode *inode,
 	spin_lock(&inode_lock);
 	inode->i_data.backing_dev_info = dst;
 	if (inode->i_state & I_DIRTY)
-		list_move(&inode->i_list, &dst->wb.b_dirty);
+		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
 	spin_unlock(&inode_lock);
 }
 

fs/fs-writeback.c

@@ -79,6 +79,11 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode)
 	return sb->s_bdi;
 }
 
+static inline struct inode *wb_inode(struct list_head *head)
+{
+	return list_entry(head, struct inode, i_wb_list);
+}
+
 static void bdi_queue_work(struct backing_dev_info *bdi,
 		struct wb_writeback_work *work)
 {
@@ -172,11 +177,11 @@ static void redirty_tail(struct inode *inode)
 	if (!list_empty(&wb->b_dirty)) {
 		struct inode *tail;
 
-		tail = list_entry(wb->b_dirty.next, struct inode, i_list);
+		tail = wb_inode(wb->b_dirty.next);
 		if (time_before(inode->dirtied_when, tail->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
-	list_move(&inode->i_list, &wb->b_dirty);
+	list_move(&inode->i_wb_list, &wb->b_dirty);
 }
 
 /*
@@ -186,7 +191,7 @@ static void requeue_io(struct inode *inode)
 {
 	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
 
-	list_move(&inode->i_list, &wb->b_more_io);
+	list_move(&inode->i_wb_list, &wb->b_more_io);
 }
 
 static void inode_sync_complete(struct inode *inode)
@@ -227,14 +232,14 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 	int do_sb_sort = 0;
 
 	while (!list_empty(delaying_queue)) {
-		inode = list_entry(delaying_queue->prev, struct inode, i_list);
+		inode = wb_inode(delaying_queue->prev);
 		if (older_than_this &&
 		    inode_dirtied_after(inode, *older_than_this))
 			break;
 		if (sb && sb != inode->i_sb)
 			do_sb_sort = 1;
 		sb = inode->i_sb;
-		list_move(&inode->i_list, &tmp);
+		list_move(&inode->i_wb_list, &tmp);
 	}
 
 	/* just one sb in list, splice to dispatch_queue and we're done */
@@ -245,12 +250,11 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 
 	/* Move inodes from one superblock together */
 	while (!list_empty(&tmp)) {
-		inode = list_entry(tmp.prev, struct inode, i_list);
-		sb = inode->i_sb;
+		sb = wb_inode(tmp.prev)->i_sb;
 		list_for_each_prev_safe(pos, node, &tmp) {
-			inode = list_entry(pos, struct inode, i_list);
+			inode = wb_inode(pos);
 			if (inode->i_sb == sb)
-				list_move(&inode->i_list, dispatch_queue);
+				list_move(&inode->i_wb_list, dispatch_queue);
 		}
 	}
 }
@@ -414,7 +418,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 			 * a reference to the inode or it's on it's way out.
 			 * No need to add it back to the LRU.
 			 */
-			list_del_init(&inode->i_list);
+			list_del_init(&inode->i_wb_list);
 		}
 	}
 	inode_sync_complete(inode);
@@ -462,8 +466,7 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 {
 	while (!list_empty(&wb->b_io)) {
 		long pages_skipped;
-		struct inode *inode = list_entry(wb->b_io.prev,
-						 struct inode, i_list);
+		struct inode *inode = wb_inode(wb->b_io.prev);
 
 		if (inode->i_sb != sb) {
 			if (only_this_sb) {
@@ -533,8 +536,7 @@ void writeback_inodes_wb(struct bdi_writeback *wb,
 		queue_io(wb, wbc->older_than_this);
 
 	while (!list_empty(&wb->b_io)) {
-		struct inode *inode = list_entry(wb->b_io.prev,
-						 struct inode, i_list);
+		struct inode *inode = wb_inode(wb->b_io.prev);
 		struct super_block *sb = inode->i_sb;
 
 		if (!pin_sb_for_writeback(sb)) {
@@ -672,8 +674,7 @@ static long wb_writeback(struct bdi_writeback *wb,
 		 */
 		spin_lock(&inode_lock);
 		if (!list_empty(&wb->b_more_io))  {
-			inode = list_entry(wb->b_more_io.prev,
-						struct inode, i_list);
+			inode = wb_inode(wb->b_more_io.prev);
 			trace_wbc_writeback_wait(&wbc, wb->bdi);
 			inode_wait_for_writeback(inode);
 		}
@@ -987,7 +988,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			}
 
 			inode->dirtied_when = jiffies;
-			list_move(&inode->i_list, &bdi->wb.b_dirty);
+			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
 		}
 	}
 out:

fs/inode.c

@@ -71,7 +71,7 @@ static unsigned int i_hash_shift __read_mostly;
  * allowing for low-overhead inode sync() operations.
  */
 
-static LIST_HEAD(inode_unused);
+static LIST_HEAD(inode_lru);
 static struct hlist_head *inode_hashtable __read_mostly;
 
 /*
@@ -271,6 +271,7 @@ EXPORT_SYMBOL(__destroy_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);
@@ -289,7 +290,8 @@ 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_LIST_HEAD(&inode->i_list);
+	INIT_LIST_HEAD(&inode->i_wb_list);
+	INIT_LIST_HEAD(&inode->i_lru);
 	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);
@@ -330,16 +332,16 @@ EXPORT_SYMBOL(ihold);
 
 static void inode_lru_list_add(struct inode *inode)
 {
-	if (list_empty(&inode->i_list)) {
-		list_add(&inode->i_list, &inode_unused);
+	if (list_empty(&inode->i_lru)) {
+		list_add(&inode->i_lru, &inode_lru);
 		percpu_counter_inc(&nr_inodes_unused);
 	}
 }
 
 static void inode_lru_list_del(struct inode *inode)
 {
-	if (!list_empty(&inode->i_list)) {
-		list_del_init(&inode->i_list);
+	if (!list_empty(&inode->i_lru)) {
+		list_del_init(&inode->i_lru);
 		percpu_counter_dec(&nr_inodes_unused);
 	}
 }
@@ -460,8 +462,8 @@ static void dispose_list(struct list_head *head)
 	while (!list_empty(head)) {
 		struct inode *inode;
 
-		inode = list_first_entry(head, struct inode, i_list);
-		list_del_init(&inode->i_list);
+		inode = list_first_entry(head, struct inode, i_lru);
+		list_del_init(&inode->i_lru);
 
 		evict(inode);
 
@@ -507,8 +509,14 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
 			continue;
 		}
 
-		list_move(&inode->i_list, dispose);
 		inode->i_state |= I_FREEING;
+
+		/*
+		 * Move the inode off the IO lists and LRU once I_FREEING is
+		 * set so that it won't get moved back on there if it is dirty.
+		 */
+		list_move(&inode->i_lru, dispose);
+		list_del_init(&inode->i_wb_list);
 		if (!(inode->i_state & (I_DIRTY | I_SYNC)))
 			percpu_counter_dec(&nr_inodes_unused);
 	}
@@ -580,10 +588,10 @@ static void prune_icache(int nr_to_scan)
 	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);
 
 		/*
 		 * Referenced or dirty inodes are still in use. Give them
@@ -591,14 +599,14 @@ static void prune_icache(int nr_to_scan)
 		 */
 		if (atomic_read(&inode->i_count) ||
 		    (inode->i_state & ~I_REFERENCED)) {
-			list_del_init(&inode->i_list);
+			list_del_init(&inode->i_lru);
 			percpu_counter_dec(&nr_inodes_unused);
 			continue;
 		}
 
 		/* recently referenced inodes get one more pass */
 		if (inode->i_state & I_REFERENCED) {
-			list_move(&inode->i_list, &inode_unused);
+			list_move(&inode->i_lru, &inode_lru);
 			inode->i_state &= ~I_REFERENCED;
 			continue;
 		}
@@ -611,15 +619,21 @@ static void prune_icache(int nr_to_scan)
 			iput(inode);
 			spin_lock(&inode_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))
 				continue;
 		}
-		list_move(&inode->i_list, &freeable);
 		WARN_ON(inode->i_state & I_NEW);
 		inode->i_state |= I_FREEING;
+
+		/*
+		 * Move the inode off the IO lists and LRU once I_FREEING is
+		 * set so that it won't get moved back on there if it is dirty.
+		 */
+		list_move(&inode->i_lru, &freeable);
+		list_del_init(&inode->i_wb_list);
 		percpu_counter_dec(&nr_inodes_unused);
 	}
 	if (current_is_kswapd())
@@ -1340,15 +1354,16 @@ static void iput_final(struct inode *inode)
 		inode->i_state &= ~I_WILL_FREE;
 		__remove_inode_hash(inode);
 	}
+
 	WARN_ON(inode->i_state & I_NEW);
 	inode->i_state |= I_FREEING;
 
 	/*
-	 * After we delete the inode from the LRU here, we avoid moving dirty
-	 * inodes back onto the LRU now because I_FREEING is set and hence
-	 * writeback_single_inode() won't move the inode around.
+	 * Move the inode off the IO lists and LRU once I_FREEING is
+	 * set so that it won't get moved back on there if it is dirty.
 	 */
 	inode_lru_list_del(inode);
+	list_del_init(&inode->i_wb_list);
 
 	__inode_sb_list_del(inode);
 	spin_unlock(&inode_lock);

include/linux/fs.h

@@ -723,7 +723,8 @@ struct posix_acl;
 
 struct inode {
 	struct hlist_node	i_hash;
-	struct list_head	i_list;		/* backing dev IO list */
+	struct list_head	i_wb_list;	/* backing dev IO list */
+	struct list_head	i_lru;		/* inode LRU list */
 	struct list_head	i_sb_list;
 	struct list_head	i_dentry;
 	unsigned long		i_ino;

mm/backing-dev.c

@@ -74,11 +74,11 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 
 	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
 	spin_lock(&inode_lock);
-	list_for_each_entry(inode, &wb->b_dirty, i_list)
+	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
-	list_for_each_entry(inode, &wb->b_io, i_list)
+	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
-	list_for_each_entry(inode, &wb->b_more_io, i_list)
+	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
 	spin_unlock(&inode_lock);