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>

2 files changed, 28 insertions, 7 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index c86edd244294..6f163e0f0509 100644
--- a/mm/backing-dev.c
+++ b/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++)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 81627ebcd313..f8341b6019bf 100644
--- a/mm/page-writeback.c
+++ b/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;
 }