1 files changed, 334 insertions, 173 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index eae96dfe0261..c5740c6d37a2 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/blkdev.h>
 #include <linux/wait.h>
 #include <linux/rbtree.h>
 #include <linux/kthread.h>
@@ -15,11 +16,11 @@
 #include <linux/writeback.h>
 #include <linux/device.h>
 #include <trace/events/writeback.h>
+#include "internal.h"
 
 struct backing_dev_info noop_backing_dev_info;
 EXPORT_SYMBOL_GPL(noop_backing_dev_info);
 
-static struct class *bdi_class;
 static const char *bdi_unknown_name = "(unknown)";
 
 /*
@@ -34,12 +35,23 @@ LIST_HEAD(bdi_list);
 /* bdi_wq serves all asynchronous writeback tasks */
 struct workqueue_struct *bdi_wq;
 
-#define K(x) ((x) << (PAGE_SHIFT - 10))
-
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 
+struct wb_stats {
+	unsigned long nr_dirty;
+	unsigned long nr_io;
+	unsigned long nr_more_io;
+	unsigned long nr_dirty_time;
+	unsigned long nr_writeback;
+	unsigned long nr_reclaimable;
+	unsigned long nr_dirtied;
+	unsigned long nr_written;
+	unsigned long dirty_thresh;
+	unsigned long wb_thresh;
+};
+
 static struct dentry *bdi_debug_root;
 
 static void bdi_debug_init(void)
@@ -47,31 +59,68 @@ static void bdi_debug_init(void)
 	bdi_debug_root = debugfs_create_dir("bdi", NULL);
 }
 
-static int bdi_debug_stats_show(struct seq_file *m, void *v)
+static void collect_wb_stats(struct wb_stats *stats,
+			     struct bdi_writeback *wb)
 {
-	struct backing_dev_info *bdi = m->private;
-	struct bdi_writeback *wb = &bdi->wb;
-	unsigned long background_thresh;
-	unsigned long dirty_thresh;
-	unsigned long wb_thresh;
-	unsigned long nr_dirty, nr_io, nr_more_io, nr_dirty_time;
 	struct inode *inode;
 
-	nr_dirty = nr_io = nr_more_io = nr_dirty_time = 0;
 	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_io_list)
-		nr_dirty++;
+		stats->nr_dirty++;
 	list_for_each_entry(inode, &wb->b_io, i_io_list)
-		nr_io++;
+		stats->nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_io_list)
-		nr_more_io++;
+		stats->nr_more_io++;
 	list_for_each_entry(inode, &wb->b_dirty_time, i_io_list)
-		if (inode->i_state & I_DIRTY_TIME)
-			nr_dirty_time++;
+		if (inode_state_read_once(inode) & I_DIRTY_TIME)
+			stats->nr_dirty_time++;
 	spin_unlock(&wb->list_lock);
 
+	stats->nr_writeback += wb_stat(wb, WB_WRITEBACK);
+	stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE);
+	stats->nr_dirtied += wb_stat(wb, WB_DIRTIED);
+	stats->nr_written += wb_stat(wb, WB_WRITTEN);
+	stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh);
+}
+
+#ifdef CONFIG_CGROUP_WRITEBACK
+static void bdi_collect_stats(struct backing_dev_info *bdi,
+			      struct wb_stats *stats)
+{
+	struct bdi_writeback *wb;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) {
+		if (!wb_tryget(wb))
+			continue;
+
+		collect_wb_stats(stats, wb);
+		wb_put(wb);
+	}
+	rcu_read_unlock();
+}
+#else
+static void bdi_collect_stats(struct backing_dev_info *bdi,
+			      struct wb_stats *stats)
+{
+	collect_wb_stats(stats, &bdi->wb);
+}
+#endif
+
+static int bdi_debug_stats_show(struct seq_file *m, void *v)
+{
+	struct backing_dev_info *bdi = m->private;
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+	struct wb_stats stats;
+	unsigned long tot_bw;
+
 	global_dirty_limits(&background_thresh, &dirty_thresh);
-	wb_thresh = wb_calc_thresh(wb, dirty_thresh);
+
+	memset(&stats, 0, sizeof(stats));
+	stats.dirty_thresh = dirty_thresh;
+	bdi_collect_stats(bdi, &stats);
+	tot_bw = atomic_long_read(&bdi->tot_write_bandwidth);
 
 	seq_printf(m,
 		   "BdiWriteback:       %10lu kB\n"
@@ -88,37 +137,114 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 		   "b_dirty_time:       %10lu\n"
 		   "bdi_list:           %10u\n"
 		   "state:              %10lx\n",
-		   (unsigned long) K(wb_stat(wb, WB_WRITEBACK)),
-		   (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)),
-		   K(wb_thresh),
+		   K(stats.nr_writeback),
+		   K(stats.nr_reclaimable),
+		   K(stats.wb_thresh),
 		   K(dirty_thresh),
 		   K(background_thresh),
-		   (unsigned long) K(wb_stat(wb, WB_DIRTIED)),
-		   (unsigned long) K(wb_stat(wb, WB_WRITTEN)),
-		   (unsigned long) K(wb->write_bandwidth),
-		   nr_dirty,
-		   nr_io,
-		   nr_more_io,
-		   nr_dirty_time,
+		   K(stats.nr_dirtied),
+		   K(stats.nr_written),
+		   K(tot_bw),
+		   stats.nr_dirty,
+		   stats.nr_io,
+		   stats.nr_more_io,
+		   stats.nr_dirty_time,
 		   !list_empty(&bdi->bdi_list), bdi->wb.state);
 
 	return 0;
 }
 DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats);
 
+static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb,
+			  struct wb_stats *stats)
+{
+
+	seq_printf(m,
+		   "WbCgIno:           %10lu\n"
+		   "WbWriteback:       %10lu kB\n"
+		   "WbReclaimable:     %10lu kB\n"
+		   "WbDirtyThresh:     %10lu kB\n"
+		   "WbDirtied:         %10lu kB\n"
+		   "WbWritten:         %10lu kB\n"
+		   "WbWriteBandwidth:  %10lu kBps\n"
+		   "b_dirty:           %10lu\n"
+		   "b_io:              %10lu\n"
+		   "b_more_io:         %10lu\n"
+		   "b_dirty_time:      %10lu\n"
+		   "state:             %10lx\n\n",
+#ifdef CONFIG_CGROUP_WRITEBACK
+		   cgroup_ino(wb->memcg_css->cgroup),
+#else
+		   1ul,
+#endif
+		   K(stats->nr_writeback),
+		   K(stats->nr_reclaimable),
+		   K(stats->wb_thresh),
+		   K(stats->nr_dirtied),
+		   K(stats->nr_written),
+		   K(wb->avg_write_bandwidth),
+		   stats->nr_dirty,
+		   stats->nr_io,
+		   stats->nr_more_io,
+		   stats->nr_dirty_time,
+		   wb->state);
+}
+
+static int cgwb_debug_stats_show(struct seq_file *m, void *v)
+{
+	struct backing_dev_info *bdi = m->private;
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+	struct bdi_writeback *wb;
+
+	global_dirty_limits(&background_thresh, &dirty_thresh);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) {
+		struct wb_stats stats = { .dirty_thresh = dirty_thresh };
+
+		if (!wb_tryget(wb))
+			continue;
+
+		collect_wb_stats(&stats, wb);
+
+		/*
+		 * Calculate thresh of wb in writeback cgroup which is min of
+		 * thresh in global domain and thresh in cgroup domain. Drop
+		 * rcu lock because cgwb_calc_thresh may sleep in
+		 * cgroup_rstat_flush. We can do so here because we have a ref.
+		 */
+		if (mem_cgroup_wb_domain(wb)) {
+			rcu_read_unlock();
+			stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb));
+			rcu_read_lock();
+		}
+
+		wb_stats_show(m, wb, &stats);
+
+		wb_put(wb);
+	}
+	rcu_read_unlock();
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats);
+
 static void bdi_debug_register(struct backing_dev_info *bdi, const char *name)
 {
 	bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root);
 
 	debugfs_create_file("stats", 0444, bdi->debug_dir, bdi,
 			    &bdi_debug_stats_fops);
+	debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi,
+			    &cgwb_debug_stats_fops);
 }
 
 static void bdi_debug_unregister(struct backing_dev_info *bdi)
 {
 	debugfs_remove_recursive(bdi->debug_dir);
 }
-#else
+#else /* CONFIG_DEBUG_FS */
 static inline void bdi_debug_init(void)
 {
 }
@@ -129,7 +255,7 @@ static inline void bdi_debug_register(struct backing_dev_info *bdi,
 static inline void bdi_debug_unregister(struct backing_dev_info *bdi)
 {
 }
-#endif
+#endif /* CONFIG_DEBUG_FS */
 
 static ssize_t read_ahead_kb_store(struct device *dev,
 				  struct device_attribute *attr,
@@ -177,7 +303,26 @@ static ssize_t min_ratio_store(struct device *dev,
 
 	return ret;
 }
-BDI_SHOW(min_ratio, bdi->min_ratio)
+BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE)
+
+static ssize_t min_ratio_fine_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int ratio;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_min_ratio_no_scale(bdi, ratio);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+BDI_SHOW(min_ratio_fine, bdi->min_ratio)
 
 static ssize_t max_ratio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
@@ -196,7 +341,82 @@ static ssize_t max_ratio_store(struct device *dev,
 
 	return ret;
 }
-BDI_SHOW(max_ratio, bdi->max_ratio)
+BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE)
+
+static ssize_t max_ratio_fine_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int ratio;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &ratio);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_max_ratio_no_scale(bdi, ratio);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+BDI_SHOW(max_ratio_fine, bdi->max_ratio)
+
+static ssize_t min_bytes_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi));
+}
+
+static ssize_t min_bytes_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	u64 bytes;
+	ssize_t ret;
+
+	ret = kstrtoull(buf, 10, &bytes);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_min_bytes(bdi, bytes);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+static DEVICE_ATTR_RW(min_bytes);
+
+static ssize_t max_bytes_show(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi));
+}
+
+static ssize_t max_bytes_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	u64 bytes;
+	ssize_t ret;
+
+	ret = kstrtoull(buf, 10, &bytes);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_max_bytes(bdi, bytes);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+static DEVICE_ATTR_RW(max_bytes);
 
 static ssize_t stable_pages_required_show(struct device *dev,
 					  struct device_attribute *attr,
@@ -208,70 +428,77 @@ static ssize_t stable_pages_required_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(stable_pages_required);
 
+static ssize_t strict_limit_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+	unsigned int strict_limit;
+	ssize_t ret;
+
+	ret = kstrtouint(buf, 10, &strict_limit);
+	if (ret < 0)
+		return ret;
+
+	ret = bdi_set_strict_limit(bdi, strict_limit);
+	if (!ret)
+		ret = count;
+
+	return ret;
+}
+
+static ssize_t strict_limit_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct backing_dev_info *bdi = dev_get_drvdata(dev);
+
+	return sysfs_emit(buf, "%d\n",
+			!!(bdi->capabilities & BDI_CAP_STRICTLIMIT));
+}
+static DEVICE_ATTR_RW(strict_limit);
+
 static struct attribute *bdi_dev_attrs[] = {
 	&dev_attr_read_ahead_kb.attr,
 	&dev_attr_min_ratio.attr,
+	&dev_attr_min_ratio_fine.attr,
 	&dev_attr_max_ratio.attr,
+	&dev_attr_max_ratio_fine.attr,
+	&dev_attr_min_bytes.attr,
+	&dev_attr_max_bytes.attr,
 	&dev_attr_stable_pages_required.attr,
+	&dev_attr_strict_limit.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(bdi_dev);
 
+static const struct class bdi_class = {
+	.name		= "bdi",
+	.dev_groups	= bdi_dev_groups,
+};
+
 static __init int bdi_class_init(void)
 {
-	bdi_class = class_create(THIS_MODULE, "bdi");
-	if (IS_ERR(bdi_class))
-		return PTR_ERR(bdi_class);
+	int ret;
+
+	ret = class_register(&bdi_class);
+	if (ret)
+		return ret;
 
-	bdi_class->dev_groups = bdi_dev_groups;
 	bdi_debug_init();
 
 	return 0;
 }
 postcore_initcall(bdi_class_init);
 
-static int bdi_init(struct backing_dev_info *bdi);
-
 static int __init default_bdi_init(void)
 {
-	int err;
-
 	bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND |
 				 WQ_SYSFS, 0);
 	if (!bdi_wq)
 		return -ENOMEM;
-
-	err = bdi_init(&noop_backing_dev_info);
-
-	return err;
+	return 0;
 }
 subsys_initcall(default_bdi_init);
 
-/*
- * This function is used when the first inode for this wb is marked dirty. It
- * wakes-up the corresponding bdi thread which should then take care of the
- * periodic background write-out of dirty inodes. Since the write-out would
- * starts only 'dirty_writeback_interval' centisecs from now anyway, we just
- * set up a timer which wakes the bdi thread up later.
- *
- * Note, we wouldn't bother setting up the timer, but this function is on the
- * fast-path (used by '__mark_inode_dirty()'), so we save few context switches
- * by delaying the wake-up.
- *
- * We have to be careful not to postpone flush work if it is scheduled for
- * earlier. Thus we use queue_delayed_work().
- */
-void wb_wakeup_delayed(struct bdi_writeback *wb)
-{
-	unsigned long timeout;
-
-	timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
-	spin_lock_bh(&wb->work_lock);
-	if (test_bit(WB_registered, &wb->state))
-		queue_delayed_work(bdi_wq, &wb->dwork, timeout);
-	spin_unlock_bh(&wb->work_lock);
-}
-
 static void wb_update_bandwidth_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(to_delayed_work(work),
@@ -283,12 +510,12 @@ static void wb_update_bandwidth_workfn(struct work_struct *work)
 /*
  * Initial write bandwidth: 100 MB/s
  */
-#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+#define INIT_BW		MB_TO_PAGES(100)
 
 static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 		   gfp_t gfp)
 {
-	int i, err;
+	int err;
 
 	memset(wb, 0, sizeof(*wb));
 
@@ -311,24 +538,15 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->work_list);
 	INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
 	INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn);
-	wb->dirty_sleep = jiffies;
 
 	err = fprop_local_init_percpu(&wb->completions, gfp);
 	if (err)
 		return err;
 
-	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
-		err = percpu_counter_init(&wb->stat[i], 0, gfp);
-		if (err)
-			goto out_destroy_stat;
-	}
-
-	return 0;
+	err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS);
+	if (err)
+		fprop_local_destroy_percpu(&wb->completions);
 
-out_destroy_stat:
-	while (i--)
-		percpu_counter_destroy(&wb->stat[i]);
-	fprop_local_destroy_percpu(&wb->completions);
 	return err;
 }
 
@@ -340,12 +558,12 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb);
 static void wb_shutdown(struct bdi_writeback *wb)
 {
 	/* Make sure nobody queues further work */
-	spin_lock_bh(&wb->work_lock);
+	spin_lock_irq(&wb->work_lock);
 	if (!test_and_clear_bit(WB_registered, &wb->state)) {
-		spin_unlock_bh(&wb->work_lock);
+		spin_unlock_irq(&wb->work_lock);
 		return;
 	}
-	spin_unlock_bh(&wb->work_lock);
+	spin_unlock_irq(&wb->work_lock);
 
 	cgwb_remove_from_bdi_list(wb);
 	/*
@@ -361,13 +579,8 @@ static void wb_shutdown(struct bdi_writeback *wb)
 
 static void wb_exit(struct bdi_writeback *wb)
 {
-	int i;
-
 	WARN_ON(delayed_work_pending(&wb->dwork));
-
-	for (i = 0; i < NR_WB_STAT_ITEMS; i++)
-		percpu_counter_destroy(&wb->stat[i]);
-
+	percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS);
 	fprop_local_destroy_percpu(&wb->completions);
 }
 
@@ -386,11 +599,19 @@ static LIST_HEAD(offline_cgwbs);
 static void cleanup_offline_cgwbs_workfn(struct work_struct *work);
 static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn);
 
+static void cgwb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct bdi_writeback *wb = container_of(rcu_head,
+			struct bdi_writeback, rcu);
+
+	percpu_ref_exit(&wb->refcnt);
+	kfree(wb);
+}
+
 static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
 						release_work);
-	struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css);
 	struct backing_dev_info *bdi = wb->bdi;
 
 	mutex_lock(&wb->bdi->cgwb_release_mutex);
@@ -401,7 +622,7 @@ static void cgwb_release_workfn(struct work_struct *work)
 	mutex_unlock(&wb->bdi->cgwb_release_mutex);
 
 	/* triggers blkg destruction if no online users left */
-	blkcg_unpin_online(blkcg);
+	blkcg_unpin_online(wb->blkcg_css);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 
@@ -409,11 +630,11 @@ static void cgwb_release_workfn(struct work_struct *work)
 	list_del(&wb->offline_node);
 	spin_unlock_irq(&cgwb_lock);
 
-	percpu_ref_exit(&wb->refcnt);
 	wb_exit(wb);
 	bdi_put(bdi);
 	WARN_ON_ONCE(!list_empty(&wb->b_attached));
-	kfree_rcu(wb, rcu);
+	WARN_ON_ONCE(work_pending(&wb->switch_work));
+	call_rcu(&wb->rcu, cgwb_free_rcu);
 }
 
 static void cgwb_release(struct percpu_ref *refcnt)
@@ -446,7 +667,6 @@ static int cgwb_create(struct backing_dev_info *bdi,
 {
 	struct mem_cgroup *memcg;
 	struct cgroup_subsys_state *blkcg_css;
-	struct blkcg *blkcg;
 	struct list_head *memcg_cgwb_list, *blkcg_cgwb_list;
 	struct bdi_writeback *wb;
 	unsigned long flags;
@@ -454,9 +674,8 @@ static int cgwb_create(struct backing_dev_info *bdi,
 
 	memcg = mem_cgroup_from_css(memcg_css);
 	blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys);
-	blkcg = css_to_blkcg(blkcg_css);
 	memcg_cgwb_list = &memcg->cgwb_list;
-	blkcg_cgwb_list = &blkcg->cgwb_list;
+	blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css);
 
 	/* look up again under lock and discard on blkcg mismatch */
 	spin_lock_irqsave(&cgwb_lock, flags);
@@ -491,6 +710,8 @@ static int cgwb_create(struct backing_dev_info *bdi,
 	wb->memcg_css = memcg_css;
 	wb->blkcg_css = blkcg_css;
 	INIT_LIST_HEAD(&wb->b_attached);
+	INIT_WORK(&wb->switch_work, inode_switch_wbs_work_fn);
+	init_llist_head(&wb->switch_wbs_ctxs);
 	INIT_WORK(&wb->release_work, cgwb_release_workfn);
 	set_bit(WB_registered, &wb->state);
 	bdi_get(bdi);
@@ -511,7 +732,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 			list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list);
 			list_add(&wb->memcg_node, memcg_cgwb_list);
 			list_add(&wb->blkcg_node, blkcg_cgwb_list);
-			blkcg_pin_online(blkcg);
+			blkcg_pin_online(blkcg_css);
 			css_get(memcg_css);
 			css_get(blkcg_css);
 		}
@@ -602,9 +823,6 @@ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi,
 
 	might_alloc(gfp);
 
-	if (!memcg_css->parent)
-		return &bdi->wb;
-
 	do {
 		wb = wb_get_lookup(bdi, memcg_css);
 	} while (!wb && !cgwb_create(bdi, memcg_css, gfp));
@@ -624,6 +842,8 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 	if (!ret) {
 		bdi->wb.memcg_css = &root_mem_cgroup->css;
 		bdi->wb.blkcg_css = blkcg_root_css;
+		INIT_WORK(&bdi->wb.switch_work, inode_switch_wbs_work_fn);
+		init_llist_head(&bdi->wb.switch_wbs_ctxs);
 	}
 	return ret;
 }
@@ -724,18 +944,19 @@ void wb_memcg_offline(struct mem_cgroup *memcg)
 
 /**
  * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined
- * @blkcg: blkcg being offlined
+ * @css: blkcg being offlined
  *
  * Also prevents creation of any new wb's associated with @blkcg.
  */
-void wb_blkcg_offline(struct blkcg *blkcg)
+void wb_blkcg_offline(struct cgroup_subsys_state *css)
 {
 	struct bdi_writeback *wb, *next;
+	struct list_head *list = blkcg_get_cgwb_list(css);
 
 	spin_lock_irq(&cgwb_lock);
-	list_for_each_entry_safe(wb, next, &blkcg->cgwb_list, blkcg_node)
+	list_for_each_entry_safe(wb, next, list, blkcg_node)
 		cgwb_kill(wb);
-	blkcg->cgwb_list.next = NULL;	/* prevent new wb's */
+	list->next = NULL;	/* prevent new wb's */
 	spin_unlock_irq(&cgwb_lock);
 }
 
@@ -782,23 +1003,20 @@ static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb)
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
-static int bdi_init(struct backing_dev_info *bdi)
+int bdi_init(struct backing_dev_info *bdi)
 {
-	int ret;
-
 	bdi->dev = NULL;
 
 	kref_init(&bdi->refcnt);
 	bdi->min_ratio = 0;
-	bdi->max_ratio = 100;
+	bdi->max_ratio = 100 * BDI_RATIO_SCALE;
 	bdi->max_prop_frac = FPROP_FRAC_BASE;
 	INIT_LIST_HEAD(&bdi->bdi_list);
 	INIT_LIST_HEAD(&bdi->wb_list);
 	init_waitqueue_head(&bdi->wb_waitq);
+	bdi->last_bdp_sleep = jiffies;
 
-	ret = cgwb_bdi_init(bdi);
-
-	return ret;
+	return cgwb_bdi_init(bdi);
 }
 
 struct backing_dev_info *bdi_alloc(int node_id)
@@ -813,7 +1031,7 @@ struct backing_dev_info *bdi_alloc(int node_id)
 		kfree(bdi);
 		return NULL;
 	}
-	bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT;
+	bdi->capabilities = BDI_CAP_WRITEBACK;
 	bdi->ra_pages = VM_READAHEAD_PAGES;
 	bdi->io_pages = VM_READAHEAD_PAGES;
 	timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0);
@@ -878,7 +1096,7 @@ int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args)
 		return 0;
 
 	vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args);
-	dev = device_create(bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name);
+	dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name);
 	if (IS_ERR(dev))
 		return PTR_ERR(dev);
 
@@ -938,7 +1156,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 
 void bdi_unregister(struct backing_dev_info *bdi)
 {
-	del_timer_sync(&bdi->laptop_mode_wb_timer);
+	timer_delete_sync(&bdi->laptop_mode_wb_timer);
 
 	/* make sure nobody finds us on the bdi_list anymore */
 	bdi_remove_from_list(bdi);
@@ -1005,60 +1223,3 @@ const char *bdi_dev_name(struct backing_dev_info *bdi)
 	return bdi->dev_name;
 }
 EXPORT_SYMBOL_GPL(bdi_dev_name);
-
-static wait_queue_head_t congestion_wqh[2] = {
-		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
-		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
-	};
-static atomic_t nr_wb_congested[2];
-
-void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
-{
-	wait_queue_head_t *wqh = &congestion_wqh[sync];
-	enum wb_congested_state bit;
-
-	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (test_and_clear_bit(bit, &bdi->wb.congested))
-		atomic_dec(&nr_wb_congested[sync]);
-	smp_mb__after_atomic();
-	if (waitqueue_active(wqh))
-		wake_up(wqh);
-}
-EXPORT_SYMBOL(clear_bdi_congested);
-
-void set_bdi_congested(struct backing_dev_info *bdi, int sync)
-{
-	enum wb_congested_state bit;
-
-	bit = sync ? WB_sync_congested : WB_async_congested;
-	if (!test_and_set_bit(bit, &bdi->wb.congested))
-		atomic_inc(&nr_wb_congested[sync]);
-}
-EXPORT_SYMBOL(set_bdi_congested);
-
-/**
- * congestion_wait - wait for a backing_dev to become uncongested
- * @sync: SYNC or ASYNC IO
- * @timeout: timeout in jiffies
- *
- * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit
- * write congestion.  If no backing_devs are congested then just wait for the
- * next write to be completed.
- */
-long congestion_wait(int sync, long timeout)
-{
-	long ret;
-	unsigned long start = jiffies;
-	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = &congestion_wqh[sync];
-
-	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
-	ret = io_schedule_timeout(timeout);
-	finish_wait(wqh, &wait);
-
-	trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
-					jiffies_to_usecs(jiffies - start));
-
-	return ret;
-}
-EXPORT_SYMBOL(congestion_wait);