writeback: move dirty inodes from super_block to backing_dev_info

This is a first step at introducing per-bdi flusher threads. We should
have no change in behaviour, although sb_has_dirty_inodes() is now
ridiculously expensive, as there's no easy way to answer that question.
Not a huge problem, since it'll be deleted in subsequent patches.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>

fs/super.c

@@ -62,9 +62,6 @@ static struct super_block *alloc_super(struct file_system_type *type)
 			s = NULL;
 			goto out;
 		}
-		INIT_LIST_HEAD(&s->s_dirty);
-		INIT_LIST_HEAD(&s->s_io);
-		INIT_LIST_HEAD(&s->s_more_io);
 		INIT_LIST_HEAD(&s->s_files);
 		INIT_LIST_HEAD(&s->s_instances);
 		INIT_HLIST_HEAD(&s->s_anon);

include/linux/backing-dev.h

@@ -40,6 +40,8 @@ enum bdi_stat_item {
 #define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids)))
 
 struct backing_dev_info {
+	struct list_head bdi_list;
+
 	unsigned long ra_pages;	/* max readahead in PAGE_CACHE_SIZE units */
 	unsigned long state;	/* Always use atomic bitops on this */
 	unsigned int capabilities; /* Device capabilities */
@@ -58,6 +60,10 @@ struct backing_dev_info {
 
 	struct device *dev;
 
+	struct list_head	b_dirty;	/* dirty inodes */
+	struct list_head	b_io;		/* parked for writeback */
+	struct list_head	b_more_io;	/* parked for more writeback */
+
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debug_dir;
 	struct dentry *debug_stats;
@@ -72,6 +78,9 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
 void bdi_unregister(struct backing_dev_info *bdi);
 
+extern struct mutex bdi_lock;
+extern struct list_head bdi_list;
+
 static inline void __add_bdi_stat(struct backing_dev_info *bdi,
 		enum bdi_stat_item item, s64 amount)
 {

include/linux/fs.h

@@ -715,7 +715,7 @@ struct posix_acl;
 
 struct inode {
 	struct hlist_node	i_hash;
-	struct list_head	i_list;
+	struct list_head	i_list;		/* backing dev IO list */
 	struct list_head	i_sb_list;
 	struct list_head	i_dentry;
 	unsigned long		i_ino;
@@ -1336,9 +1336,6 @@ struct super_block {
 	struct xattr_handler	**s_xattr;
 
 	struct list_head	s_inodes;	/* all inodes */
-	struct list_head	s_dirty;	/* dirty inodes */
-	struct list_head	s_io;		/* parked for writeback */
-	struct list_head	s_more_io;	/* parked for more writeback */
 	struct hlist_head	s_anon;		/* anonymous dentries for (nfs) exporting */
 	struct list_head	s_files;
 	/* s_dentry_lru and s_nr_dentry_unused are protected by dcache_lock */

mm/backing-dev.c

@@ -22,6 +22,8 @@ struct backing_dev_info default_backing_dev_info = {
 EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
 static struct class *bdi_class;
+DEFINE_MUTEX(bdi_lock);
+LIST_HEAD(bdi_list);
 
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
@@ -211,6 +213,10 @@ int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		goto exit;
 	}
 
+	mutex_lock(&bdi_lock);
+	list_add_tail(&bdi->bdi_list, &bdi_list);
+	mutex_unlock(&bdi_lock);
+
 	bdi->dev = dev;
 	bdi_debug_register(bdi, dev_name(dev));
 
@@ -225,9 +231,17 @@ int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev)
 }
 EXPORT_SYMBOL(bdi_register_dev);
 
+static void bdi_remove_from_list(struct backing_dev_info *bdi)
+{
+	mutex_lock(&bdi_lock);
+	list_del(&bdi->bdi_list);
+	mutex_unlock(&bdi_lock);
+}
+
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_remove_from_list(bdi);
 		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
@@ -245,6 +259,10 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
 	bdi->max_prop_frac = PROP_FRAC_BASE;
+	INIT_LIST_HEAD(&bdi->bdi_list);
+	INIT_LIST_HEAD(&bdi->b_io);
+	INIT_LIST_HEAD(&bdi->b_dirty);
+	INIT_LIST_HEAD(&bdi->b_more_io);
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
@@ -259,6 +277,8 @@ int bdi_init(struct backing_dev_info *bdi)
 err:
 		while (i--)
 			percpu_counter_destroy(&bdi->bdi_stat[i]);
+
+		bdi_remove_from_list(bdi);
 	}
 
 	return err;
@@ -269,6 +289,10 @@ void bdi_destroy(struct backing_dev_info *bdi)
 {
 	int i;
 
+	WARN_ON(!list_empty(&bdi->b_dirty));
+	WARN_ON(!list_empty(&bdi->b_io));
+	WARN_ON(!list_empty(&bdi->b_more_io));
+
 	bdi_unregister(bdi);
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)

mm/page-writeback.c

@@ -320,15 +320,13 @@ static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
 /*
  *
  */
-static DEFINE_SPINLOCK(bdi_lock);
 static unsigned int bdi_min_ratio;
 
 int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
 {
 	int ret = 0;
-	unsigned long flags;
 
-	spin_lock_irqsave(&bdi_lock, flags);
+	mutex_lock(&bdi_lock);
 	if (min_ratio > bdi->max_ratio) {
 		ret = -EINVAL;
 	} else {
@@ -340,27 +338,26 @@ int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
 			ret = -EINVAL;
 		}
 	}
-	spin_unlock_irqrestore(&bdi_lock, flags);
+	mutex_unlock(&bdi_lock);
 
 	return ret;
 }
 
 int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
 {
-	unsigned long flags;
 	int ret = 0;
 
 	if (max_ratio > 100)
 		return -EINVAL;
 
-	spin_lock_irqsave(&bdi_lock, flags);
+	mutex_lock(&bdi_lock);
 	if (bdi->min_ratio > max_ratio) {
 		ret = -EINVAL;
 	} else {
 		bdi->max_ratio = max_ratio;
 		bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
 	}
-	spin_unlock_irqrestore(&bdi_lock, flags);
+	mutex_unlock(&bdi_lock);
 
 	return ret;
 }