1 files changed, 110 insertions, 61 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 576220acd686..eae96dfe0261 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -2,8 +2,9 @@
 
 #include <linux/wait.h>
 #include <linux/rbtree.h>
-#include <linux/backing-dev.h>
 #include <linux/kthread.h>
+#include <linux/backing-dev.h>
+#include <linux/blk-cgroup.h>
 #include <linux/freezer.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -271,6 +272,14 @@ void wb_wakeup_delayed(struct bdi_writeback *wb)
 	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),
+						struct bdi_writeback, bw_dwork);
+
+	wb_update_bandwidth(wb);
+}
+
 /*
  * Initial write bandwidth: 100 MB/s
  */
@@ -283,8 +292,6 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 
 	memset(wb, 0, sizeof(*wb));
 
-	if (wb != &bdi->wb)
-		bdi_get(bdi);
 	wb->bdi = bdi;
 	wb->last_old_flush = jiffies;
 	INIT_LIST_HEAD(&wb->b_dirty);
@@ -293,6 +300,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	INIT_LIST_HEAD(&wb->b_dirty_time);
 	spin_lock_init(&wb->list_lock);
 
+	atomic_set(&wb->writeback_inodes, 0);
 	wb->bw_time_stamp = jiffies;
 	wb->balanced_dirty_ratelimit = INIT_BW;
 	wb->dirty_ratelimit = INIT_BW;
@@ -302,11 +310,12 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi,
 	spin_lock_init(&wb->work_lock);
 	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)
-		goto out_put_bdi;
+		return err;
 
 	for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
 		err = percpu_counter_init(&wb->stat[i], 0, gfp);
@@ -320,9 +329,6 @@ out_destroy_stat:
 	while (i--)
 		percpu_counter_destroy(&wb->stat[i]);
 	fprop_local_destroy_percpu(&wb->completions);
-out_put_bdi:
-	if (wb != &bdi->wb)
-		bdi_put(bdi);
 	return err;
 }
 
@@ -350,6 +356,7 @@ static void wb_shutdown(struct bdi_writeback *wb)
 	mod_delayed_work(bdi_wq, &wb->dwork, 0);
 	flush_delayed_work(&wb->dwork);
 	WARN_ON(!list_empty(&wb->work_list));
+	flush_delayed_work(&wb->bw_dwork);
 }
 
 static void wb_exit(struct bdi_writeback *wb)
@@ -362,8 +369,6 @@ static void wb_exit(struct bdi_writeback *wb)
 		percpu_counter_destroy(&wb->stat[i]);
 
 	fprop_local_destroy_percpu(&wb->completions);
-	if (wb != &wb->bdi->wb)
-		bdi_put(wb->bdi);
 }
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -371,17 +376,22 @@ static void wb_exit(struct bdi_writeback *wb)
 #include <linux/memcontrol.h>
 
 /*
- * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, and memcg->cgwb_list.
- * bdi->cgwb_tree is also RCU protected.
+ * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and
+ * memcg->cgwb_list.  bdi->cgwb_tree is also RCU protected.
  */
 static DEFINE_SPINLOCK(cgwb_lock);
 static struct workqueue_struct *cgwb_release_wq;
 
+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_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);
 	wb_shutdown(wb);
@@ -394,8 +404,15 @@ static void cgwb_release_workfn(struct work_struct *work)
 	blkcg_unpin_online(blkcg);
 
 	fprop_local_destroy_percpu(&wb->memcg_completions);
+
+	spin_lock_irq(&cgwb_lock);
+	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);
 }
 
@@ -413,6 +430,7 @@ static void cgwb_kill(struct bdi_writeback *wb)
 	WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id));
 	list_del(&wb->memcg_node);
 	list_del(&wb->blkcg_node);
+	list_add(&wb->offline_node, &offline_cgwbs);
 	percpu_ref_kill(&wb->refcnt);
 }
 
@@ -472,8 +490,10 @@ 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->release_work, cgwb_release_workfn);
 	set_bit(WB_registered, &wb->state);
+	bdi_get(bdi);
 
 	/*
 	 * The root wb determines the registered state of the whole bdi and
@@ -505,6 +525,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 	goto out_put;
 
 err_fprop_exit:
+	bdi_put(bdi);
 	fprop_local_destroy_percpu(&wb->memcg_completions);
 err_ref_exit:
 	percpu_ref_exit(&wb->refcnt);
@@ -633,6 +654,54 @@ static void cgwb_bdi_unregister(struct backing_dev_info *bdi)
 	mutex_unlock(&bdi->cgwb_release_mutex);
 }
 
+/*
+ * cleanup_offline_cgwbs_workfn - try to release dying cgwbs
+ *
+ * Try to release dying cgwbs by switching attached inodes to the nearest
+ * living ancestor's writeback. Processed wbs are placed at the end
+ * of the list to guarantee the forward progress.
+ */
+static void cleanup_offline_cgwbs_workfn(struct work_struct *work)
+{
+	struct bdi_writeback *wb;
+	LIST_HEAD(processed);
+
+	spin_lock_irq(&cgwb_lock);
+
+	while (!list_empty(&offline_cgwbs)) {
+		wb = list_first_entry(&offline_cgwbs, struct bdi_writeback,
+				      offline_node);
+		list_move(&wb->offline_node, &processed);
+
+		/*
+		 * If wb is dirty, cleaning up the writeback by switching
+		 * attached inodes will result in an effective removal of any
+		 * bandwidth restrictions, which isn't the goal.  Instead,
+		 * it can be postponed until the next time, when all io
+		 * will be likely completed.  If in the meantime some inodes
+		 * will get re-dirtied, they should be eventually switched to
+		 * a new cgwb.
+		 */
+		if (wb_has_dirty_io(wb))
+			continue;
+
+		if (!wb_tryget(wb))
+			continue;
+
+		spin_unlock_irq(&cgwb_lock);
+		while (cleanup_offline_cgwb(wb))
+			cond_resched();
+		spin_lock_irq(&cgwb_lock);
+
+		wb_put(wb);
+	}
+
+	if (!list_empty(&processed))
+		list_splice_tail(&processed, &offline_cgwbs);
+
+	spin_unlock_irq(&cgwb_lock);
+}
+
 /**
  * wb_memcg_offline - kill all wb's associated with a memcg being offlined
  * @memcg: memcg being offlined
@@ -649,6 +718,8 @@ void wb_memcg_offline(struct mem_cgroup *memcg)
 		cgwb_kill(wb);
 	memcg_cgwb_list->next = NULL;	/* prevent new wb's */
 	spin_unlock_irq(&cgwb_lock);
+
+	queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work);
 }
 
 /**
@@ -745,6 +816,7 @@ struct backing_dev_info *bdi_alloc(int node_id)
 	bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT;
 	bdi->ra_pages = VM_READAHEAD_PAGES;
 	bdi->io_pages = VM_READAHEAD_PAGES;
+	timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0);
 	return bdi;
 }
 EXPORT_SYMBOL(bdi_alloc);
@@ -866,11 +938,20 @@ 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);
+
 	/* make sure nobody finds us on the bdi_list anymore */
 	bdi_remove_from_list(bdi);
 	wb_shutdown(&bdi->wb);
 	cgwb_bdi_unregister(bdi);
 
+	/*
+	 * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+	 * update the global bdi_min_ratio.
+	 */
+	if (bdi->min_ratio)
+		bdi_set_min_ratio(bdi, 0);
+
 	if (bdi->dev) {
 		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);
@@ -882,14 +963,14 @@ void bdi_unregister(struct backing_dev_info *bdi)
 		bdi->owner = NULL;
 	}
 }
+EXPORT_SYMBOL(bdi_unregister);
 
 static void release_bdi(struct kref *ref)
 {
 	struct backing_dev_info *bdi =
 			container_of(ref, struct backing_dev_info, refcnt);
 
-	if (test_bit(WB_registered, &bdi->wb.state))
-		bdi_unregister(bdi);
+	WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state));
 	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
 	kfree(bdi);
@@ -901,6 +982,22 @@ void bdi_put(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL(bdi_put);
 
+struct backing_dev_info *inode_to_bdi(struct inode *inode)
+{
+	struct super_block *sb;
+
+	if (!inode)
+		return &noop_backing_dev_info;
+
+	sb = inode->i_sb;
+#ifdef CONFIG_BLOCK
+	if (sb_is_blkdev_sb(sb))
+		return I_BDEV(inode)->bd_disk->bdi;
+#endif
+	return sb->s_bdi;
+}
+EXPORT_SYMBOL(inode_to_bdi);
+
 const char *bdi_dev_name(struct backing_dev_info *bdi)
 {
 	if (!bdi || !bdi->dev)
@@ -965,51 +1062,3 @@ long congestion_wait(int sync, long timeout)
 	return ret;
 }
 EXPORT_SYMBOL(congestion_wait);
-
-/**
- * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a pgdat to complete writes
- * @sync: SYNC or ASYNC IO
- * @timeout: timeout in jiffies
- *
- * In the event of a congested backing_dev (any backing_dev) this waits
- * for up to @timeout jiffies for either a BDI to exit congestion of the
- * given @sync queue or a write to complete.
- *
- * The return value is 0 if the sleep is for the full timeout. Otherwise,
- * it is the number of jiffies that were still remaining when the function
- * returned. return_value == timeout implies the function did not sleep.
- */
-long wait_iff_congested(int sync, long timeout)
-{
-	long ret;
-	unsigned long start = jiffies;
-	DEFINE_WAIT(wait);
-	wait_queue_head_t *wqh = &congestion_wqh[sync];
-
-	/*
-	 * If there is no congestion, yield if necessary instead
-	 * of sleeping on the congestion queue
-	 */
-	if (atomic_read(&nr_wb_congested[sync]) == 0) {
-		cond_resched();
-
-		/* In case we scheduled, work out time remaining */
-		ret = timeout - (jiffies - start);
-		if (ret < 0)
-			ret = 0;
-
-		goto out;
-	}
-
-	/* Sleep until uncongested or a write happens */
-	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
-	ret = io_schedule_timeout(timeout);
-	finish_wait(wqh, &wait);
-
-out:
-	trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
-					jiffies_to_usecs(jiffies - start));
-
-	return ret;
-}
-EXPORT_SYMBOL(wait_iff_congested);