Merge branch 'for-linus' of git://git.kernel.dk/linux-block

Pull block layer fixes from Jens Axboe:
 "A final set of fixes for 4.3.

  It is (again) bigger than I would have liked, but it's all been
  through the testing mill and has been carefully reviewed by multiple
  parties.  Each fix is either a regression fix for this cycle, or is
  marked stable.  You can scold me at KS.  The pull request contains:

   - Three simple fixes for NVMe, fixing regressions since 4.3.  From
     Arnd, Christoph, and Keith.

   - A single xen-blkfront fix from Cathy, fixing a NULL dereference if
     an error is returned through the staste change callback.

   - Fixup for some bad/sloppy code in nbd that got introduced earlier
     in this cycle.  From Markus Pargmann.

   - A blk-mq tagset use-after-free fix from Junichi.

   - A backing device lifetime fix from Tejun, fixing a crash.

   - And finally, a set of regression/stable fixes for cgroup writeback
     from Tejun"

* 'for-linus' of git://git.kernel.dk/linux-block:
  writeback: remove broken rbtree_postorder_for_each_entry_safe() usage in cgwb_bdi_destroy()
  NVMe: Fix memory leak on retried commands
  block: don't release bdi while request_queue has live references
  nvme: use an integer value to Linux errno values
  blk-mq: fix use-after-free in blk_mq_free_tag_set()
  nvme: fix 32-bit build warning
  writeback: fix incorrect calculation of available memory for memcg domains
  writeback: memcg dirty_throttle_control should be initialized with wb->memcg_completions
  writeback: bdi_writeback iteration must not skip dying ones
  writeback: fix bdi_writeback iteration in wakeup_dirtytime_writeback()
  writeback: laptop_mode_timer_fn() needs rcu_read_lock() around bdi_writeback iteration
  nbd: Add locking for tasks
  xen-blkfront: check for null drvdata in blkback_changed (XenbusStateClosing)

block/blk-core.c

@@ -576,7 +576,7 @@ void blk_cleanup_queue(struct request_queue *q)
 		q->queue_lock = &q->__queue_lock;
 	spin_unlock_irq(lock);
 
-	bdi_destroy(&q->backing_dev_info);
+	bdi_unregister(&q->backing_dev_info);
 
 	/* @q is and will stay empty, shutdown and put */
 	blk_put_queue(q);

block/blk-mq-tag.c

@@ -641,6 +641,7 @@ void blk_mq_free_tags(struct blk_mq_tags *tags)
 {
 	bt_free(&tags->bitmap_tags);
 	bt_free(&tags->breserved_tags);
+	free_cpumask_var(tags->cpumask);
 	kfree(tags);
 }
 

block/blk-mq.c

@@ -2296,10 +2296,8 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set)
 	int i;
 
 	for (i = 0; i < set->nr_hw_queues; i++) {
-		if (set->tags[i]) {
+		if (set->tags[i])
 			blk_mq_free_rq_map(set, set->tags[i], i);
-			free_cpumask_var(set->tags[i]->cpumask);
-		}
 	}
 
 	kfree(set->tags);

block/blk-sysfs.c

@@ -540,6 +540,7 @@ static void blk_release_queue(struct kobject *kobj)
 	struct request_queue *q =
 		container_of(kobj, struct request_queue, kobj);
 
+	bdi_exit(&q->backing_dev_info);
 	blkcg_exit_queue(q);
 
 	if (q->elevator) {

drivers/block/nbd.c

@@ -60,6 +60,7 @@ struct nbd_device {
 	bool disconnect; /* a disconnect has been requested by user */
 
 	struct timer_list timeout_timer;
+	spinlock_t tasks_lock;
 	struct task_struct *task_recv;
 	struct task_struct *task_send;
 
@@ -140,21 +141,23 @@ static void sock_shutdown(struct nbd_device *nbd)
 static void nbd_xmit_timeout(unsigned long arg)
 {
 	struct nbd_device *nbd = (struct nbd_device *)arg;
-	struct task_struct *task;
+	unsigned long flags;
 
 	if (list_empty(&nbd->queue_head))
 		return;
 
 	nbd->disconnect = true;
 
-	task = READ_ONCE(nbd->task_recv);
-	if (task)
-		force_sig(SIGKILL, task);
+	spin_lock_irqsave(&nbd->tasks_lock, flags);
+
+	if (nbd->task_recv)
+		force_sig(SIGKILL, nbd->task_recv);
 
-	task = READ_ONCE(nbd->task_send);
-	if (task)
+	if (nbd->task_send)
 		force_sig(SIGKILL, nbd->task_send);
 
+	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
 	dev_err(nbd_to_dev(nbd), "Connection timed out, killed receiver and sender, shutting down connection\n");
 }
 
@@ -403,17 +406,24 @@ static int nbd_thread_recv(struct nbd_device *nbd)
 {
 	struct request *req;
 	int ret;
+	unsigned long flags;
 
 	BUG_ON(nbd->magic != NBD_MAGIC);
 
 	sk_set_memalloc(nbd->sock->sk);
 
+	spin_lock_irqsave(&nbd->tasks_lock, flags);
 	nbd->task_recv = current;
+	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
 
 	ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
 	if (ret) {
 		dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
+
+		spin_lock_irqsave(&nbd->tasks_lock, flags);
 		nbd->task_recv = NULL;
+		spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
 		return ret;
 	}
 
@@ -429,7 +439,9 @@ static int nbd_thread_recv(struct nbd_device *nbd)
 
 	device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
 
+	spin_lock_irqsave(&nbd->tasks_lock, flags);
 	nbd->task_recv = NULL;
+	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
 
 	if (signal_pending(current)) {
 		siginfo_t info;
@@ -534,8 +546,11 @@ static int nbd_thread_send(void *data)
 {
 	struct nbd_device *nbd = data;
 	struct request *req;
+	unsigned long flags;
 
+	spin_lock_irqsave(&nbd->tasks_lock, flags);
 	nbd->task_send = current;
+	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
 
 	set_user_nice(current, MIN_NICE);
 	while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
@@ -572,7 +587,15 @@ static int nbd_thread_send(void *data)
 		nbd_handle_req(nbd, req);
 	}
 
+	spin_lock_irqsave(&nbd->tasks_lock, flags);
 	nbd->task_send = NULL;
+	spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
+	/* Clear maybe pending signals */
+	if (signal_pending(current)) {
+		siginfo_t info;
+		dequeue_signal_lock(current, &current->blocked, &info);
+	}
 
 	return 0;
 }
@@ -1052,6 +1075,7 @@ static int __init nbd_init(void)
 		nbd_dev[i].magic = NBD_MAGIC;
 		INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
 		spin_lock_init(&nbd_dev[i].queue_lock);
+		spin_lock_init(&nbd_dev[i].tasks_lock);
 		INIT_LIST_HEAD(&nbd_dev[i].queue_head);
 		mutex_init(&nbd_dev[i].tx_lock);
 		init_timer(&nbd_dev[i].timeout_timer);

drivers/block/nvme-core.c

@@ -603,27 +603,31 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	struct nvme_iod *iod = ctx;
 	struct request *req = iod_get_private(iod);
 	struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
-
 	u16 status = le16_to_cpup(&cqe->status) >> 1;
+	bool requeue = false;
+	int error = 0;
 
 	if (unlikely(status)) {
 		if (!(status & NVME_SC_DNR || blk_noretry_request(req))
 		    && (jiffies - req->start_time) < req->timeout) {
 			unsigned long flags;
 
+			requeue = true;
 			blk_mq_requeue_request(req);
 			spin_lock_irqsave(req->q->queue_lock, flags);
 			if (!blk_queue_stopped(req->q))
 				blk_mq_kick_requeue_list(req->q);
 			spin_unlock_irqrestore(req->q->queue_lock, flags);
-			return;
+			goto release_iod;
 		}
 
 		if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
 			if (cmd_rq->ctx == CMD_CTX_CANCELLED)
-				status = -EINTR;
+				error = -EINTR;
+			else
+				error = status;
 		} else {
-			status = nvme_error_status(status);
+			error = nvme_error_status(status);
 		}
 	}
 
@@ -635,8 +639,9 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	if (cmd_rq->aborted)
 		dev_warn(nvmeq->dev->dev,
 			"completing aborted command with status:%04x\n",
-			status);
+			error);
 
+release_iod:
 	if (iod->nents) {
 		dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
 			rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
@@ -649,7 +654,8 @@ static void req_completion(struct nvme_queue *nvmeq, void *ctx,
 	}
 	nvme_free_iod(nvmeq->dev, iod);
 
-	blk_mq_complete_request(req, status);
+	if (likely(!requeue))
+		blk_mq_complete_request(req, error);
 }
 
 /* length is in bytes.  gfp flags indicates whether we may sleep. */
@@ -1804,7 +1810,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 
 	length = (io.nblocks + 1) << ns->lba_shift;
 	meta_len = (io.nblocks + 1) * ns->ms;
-	metadata = (void __user *)(unsigned long)io.metadata;
+	metadata = (void __user *)(uintptr_t)io.metadata;
 	write = io.opcode & 1;
 
 	if (ns->ext) {
@@ -1844,7 +1850,7 @@ static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 	c.rw.metadata = cpu_to_le64(meta_dma);
 
 	status = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
-			(void __user *)io.addr, length, NULL, 0);
+			(void __user *)(uintptr_t)io.addr, length, NULL, 0);
  unmap:
 	if (meta) {
 		if (status == NVME_SC_SUCCESS && !write) {
@@ -1886,7 +1892,7 @@ static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
 		timeout = msecs_to_jiffies(cmd.timeout_ms);
 
 	status = __nvme_submit_sync_cmd(ns ? ns->queue : dev->admin_q, &c,
-			NULL, (void __user *)cmd.addr, cmd.data_len,
+			NULL, (void __user *)(uintptr_t)cmd.addr, cmd.data_len,
 			&cmd.result, timeout);
 	if (status >= 0) {
 		if (put_user(cmd.result, &ucmd->result))

drivers/block/xen-blkfront.c

@@ -1956,7 +1956,8 @@ static void blkback_changed(struct xenbus_device *dev,
 			break;
 		/* Missed the backend's Closing state -- fallthrough */
 	case XenbusStateClosing:
-		blkfront_closing(info);
+		if (info)
+			blkfront_closing(info);
 		break;
 	}
 }

fs/fs-writeback.c

@@ -778,19 +778,24 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 				  struct wb_writeback_work *base_work,
 				  bool skip_if_busy)
 {
-	int next_memcg_id = 0;
-	struct bdi_writeback *wb;
-	struct wb_iter iter;
+	struct bdi_writeback *last_wb = NULL;
+	struct bdi_writeback *wb = list_entry_rcu(&bdi->wb_list,
+						struct bdi_writeback, bdi_node);
 
 	might_sleep();
 restart:
 	rcu_read_lock();
-	bdi_for_each_wb(wb, bdi, &iter, next_memcg_id) {
+	list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) {
 		DEFINE_WB_COMPLETION_ONSTACK(fallback_work_done);
 		struct wb_writeback_work fallback_work;
 		struct wb_writeback_work *work;
 		long nr_pages;
 
+		if (last_wb) {
+			wb_put(last_wb);
+			last_wb = NULL;
+		}
+
 		/* SYNC_ALL writes out I_DIRTY_TIME too */
 		if (!wb_has_dirty_io(wb) &&
 		    (base_work->sync_mode == WB_SYNC_NONE ||
@@ -819,12 +824,22 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 
 		wb_queue_work(wb, work);
 
-		next_memcg_id = wb->memcg_css->id + 1;
+		/*
+		 * Pin @wb so that it stays on @bdi->wb_list.  This allows
+		 * continuing iteration from @wb after dropping and
+		 * regrabbing rcu read lock.
+		 */
+		wb_get(wb);
+		last_wb = wb;
+
 		rcu_read_unlock();
 		wb_wait_for_completion(bdi, &fallback_work_done);
 		goto restart;
 	}
 	rcu_read_unlock();
+
+	if (last_wb)
+		wb_put(last_wb);
 }
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
@@ -1857,12 +1872,11 @@ void wakeup_flusher_threads(long nr_pages, enum wb_reason reason)
 	rcu_read_lock();
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		struct bdi_writeback *wb;
-		struct wb_iter iter;
 
 		if (!bdi_has_dirty_io(bdi))
 			continue;
 
-		bdi_for_each_wb(wb, bdi, &iter, 0)
+		list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node)
 			wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages),
 					   false, reason);
 	}
@@ -1894,11 +1908,10 @@ static void wakeup_dirtytime_writeback(struct work_struct *w)
 	rcu_read_lock();
 	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
 		struct bdi_writeback *wb;
-		struct wb_iter iter;
 
-		bdi_for_each_wb(wb, bdi, &iter, 0)
-			if (!list_empty(&bdi->wb.b_dirty_time))
-				wb_wakeup(&bdi->wb);
+		list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node)
+			if (!list_empty(&wb->b_dirty_time))
+				wb_wakeup(wb);
 	}
 	rcu_read_unlock();
 	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);

include/linux/backing-dev-defs.h

@@ -116,6 +116,8 @@ struct bdi_writeback {
 	struct list_head work_list;
 	struct delayed_work dwork;	/* work item used for writeback */
 
+	struct list_head bdi_node;	/* anchored at bdi->wb_list */
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct percpu_ref refcnt;	/* used only for !root wb's */
 	struct fprop_local_percpu memcg_completions;
@@ -150,6 +152,7 @@ struct backing_dev_info {
 	atomic_long_t tot_write_bandwidth;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
+	struct list_head wb_list; /* list of all wbs */
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */
 	struct rb_root cgwb_congested_tree; /* their congested states */

include/linux/backing-dev.h

@@ -19,13 +19,17 @@
 #include <linux/slab.h>
 
 int __must_check bdi_init(struct backing_dev_info *bdi);
-void bdi_destroy(struct backing_dev_info *bdi);
+void bdi_exit(struct backing_dev_info *bdi);
 
 __printf(3, 4)
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...);
 int bdi_register_dev(struct backing_dev_info *bdi, dev_t dev);
+void bdi_unregister(struct backing_dev_info *bdi);
+
 int __must_check bdi_setup_and_register(struct backing_dev_info *, char *);
+void bdi_destroy(struct backing_dev_info *bdi);
+
 void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
 			bool range_cyclic, enum wb_reason reason);
 void wb_start_background_writeback(struct bdi_writeback *wb);
@@ -408,61 +412,6 @@ static inline void unlocked_inode_to_wb_end(struct inode *inode, bool locked)
 	rcu_read_unlock();
 }
 
-struct wb_iter {
-	int			start_memcg_id;
-	struct radix_tree_iter	tree_iter;
-	void			**slot;
-};
-
-static inline struct bdi_writeback *__wb_iter_next(struct wb_iter *iter,
-						   struct backing_dev_info *bdi)
-{
-	struct radix_tree_iter *titer = &iter->tree_iter;
-
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	if (iter->start_memcg_id >= 0) {
-		iter->slot = radix_tree_iter_init(titer, iter->start_memcg_id);
-		iter->start_memcg_id = -1;
-	} else {
-		iter->slot = radix_tree_next_slot(iter->slot, titer, 0);
-	}
-
-	if (!iter->slot)
-		iter->slot = radix_tree_next_chunk(&bdi->cgwb_tree, titer, 0);
-	if (iter->slot)
-		return *iter->slot;
-	return NULL;
-}
-
-static inline struct bdi_writeback *__wb_iter_init(struct wb_iter *iter,
-						   struct backing_dev_info *bdi,
-						   int start_memcg_id)
-{
-	iter->start_memcg_id = start_memcg_id;
-
-	if (start_memcg_id)
-		return __wb_iter_next(iter, bdi);
-	else
-		return &bdi->wb;
-}
-
-/**
- * bdi_for_each_wb - walk all wb's of a bdi in ascending memcg ID order
- * @wb_cur: cursor struct bdi_writeback pointer
- * @bdi: bdi to walk wb's of
- * @iter: pointer to struct wb_iter to be used as iteration buffer
- * @start_memcg_id: memcg ID to start iteration from
- *
- * Iterate @wb_cur through the wb's (bdi_writeback's) of @bdi in ascending
- * memcg ID order starting from @start_memcg_id.  @iter is struct wb_iter
- * to be used as temp storage during iteration.  rcu_read_lock() must be
- * held throughout iteration.
- */
-#define bdi_for_each_wb(wb_cur, bdi, iter, start_memcg_id)		\
-	for ((wb_cur) = __wb_iter_init(iter, bdi, start_memcg_id);	\
-	     (wb_cur); (wb_cur) = __wb_iter_next(iter, bdi))
-
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static inline bool inode_cgwb_enabled(struct inode *inode)
@@ -522,14 +471,6 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg)
 {
 }
 
-struct wb_iter {
-	int		next_id;
-};
-
-#define bdi_for_each_wb(wb_cur, bdi, iter, start_blkcg_id)		\
-	for ((iter)->next_id = (start_blkcg_id);			\
-	     ({	(wb_cur) = !(iter)->next_id++ ? &(bdi)->wb : NULL; }); )
-
 static inline int inode_congested(struct inode *inode, int cong_bits)
 {
 	return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);

include/linux/memcontrol.h

@@ -676,8 +676,9 @@ enum {
 
 struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
 struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb);
-void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail,
-			 unsigned long *pdirty, unsigned long *pwriteback);
+void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
+			 unsigned long *pheadroom, unsigned long *pdirty,
+			 unsigned long *pwriteback);
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
@@ -687,7 +688,8 @@ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
 }
 
 static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
-				       unsigned long *pavail,
+				       unsigned long *pfilepages,
+				       unsigned long *pheadroom,
 				       unsigned long *pdirty,
 				       unsigned long *pwriteback)
 {

mm/backing-dev.c

@@ -480,6 +480,10 @@ static void cgwb_release_workfn(struct work_struct *work)
 						release_work);
 	struct backing_dev_info *bdi = wb->bdi;
 
+	spin_lock_irq(&cgwb_lock);
+	list_del_rcu(&wb->bdi_node);
+	spin_unlock_irq(&cgwb_lock);
+
 	wb_shutdown(wb);
 
 	css_put(wb->memcg_css);
@@ -575,6 +579,7 @@ static int cgwb_create(struct backing_dev_info *bdi,
 		ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb);
 		if (!ret) {
 			atomic_inc(&bdi->usage_cnt);
+			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);
 			css_get(memcg_css);
@@ -676,7 +681,7 @@ static int cgwb_bdi_init(struct backing_dev_info *bdi)
 static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 {
 	struct radix_tree_iter iter;
-	struct bdi_writeback_congested *congested, *congested_n;
+	struct rb_node *rbn;
 	void **slot;
 
 	WARN_ON(test_bit(WB_registered, &bdi->wb.state));
@@ -686,9 +691,11 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi)
 	radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0)
 		cgwb_kill(*slot);
 
-	rbtree_postorder_for_each_entry_safe(congested, congested_n,
-					&bdi->cgwb_congested_tree, rb_node) {
-		rb_erase(&congested->rb_node, &bdi->cgwb_congested_tree);
+	while ((rbn = rb_first(&bdi->cgwb_congested_tree))) {
+		struct bdi_writeback_congested *congested =
+			rb_entry(rbn, struct bdi_writeback_congested, rb_node);
+
+		rb_erase(rbn, &bdi->cgwb_congested_tree);
 		congested->bdi = NULL;	/* mark @congested unlinked */
 	}
 
@@ -764,15 +771,22 @@ static void cgwb_bdi_destroy(struct backing_dev_info *bdi) { }
 
 int bdi_init(struct backing_dev_info *bdi)
 {
+	int ret;
+
 	bdi->dev = NULL;
 
 	bdi->min_ratio = 0;
 	bdi->max_ratio = 100;
 	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);
 
-	return cgwb_bdi_init(bdi);
+	ret = cgwb_bdi_init(bdi);
+
+	list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list);
+
+	return ret;
 }
 EXPORT_SYMBOL(bdi_init);
 
@@ -823,7 +837,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	synchronize_rcu_expedited();
 }
 
-void bdi_destroy(struct backing_dev_info *bdi)
+void bdi_unregister(struct backing_dev_info *bdi)
 {
 	/* make sure nobody finds us on the bdi_list anymore */
 	bdi_remove_from_list(bdi);
@@ -835,9 +849,19 @@ void bdi_destroy(struct backing_dev_info *bdi)
 		device_unregister(bdi->dev);
 		bdi->dev = NULL;
 	}
+}
 
+void bdi_exit(struct backing_dev_info *bdi)
+{
+	WARN_ON_ONCE(bdi->dev);
 	wb_exit(&bdi->wb);
 }
+
+void bdi_destroy(struct backing_dev_info *bdi)
+{
+	bdi_unregister(bdi);
+	bdi_exit(bdi);
+}
 EXPORT_SYMBOL(bdi_destroy);
 
 /*

mm/memcontrol.c

@@ -3741,44 +3741,43 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
 /**
  * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg
  * @wb: bdi_writeback in question
- * @pavail: out parameter for number of available pages
+ * @pfilepages: out parameter for number of file pages
+ * @pheadroom: out parameter for number of allocatable pages according to memcg
  * @pdirty: out parameter for number of dirty pages
  * @pwriteback: out parameter for number of pages under writeback
  *
- * Determine the numbers of available, dirty, and writeback pages in @wb's
- * memcg.  Dirty and writeback are self-explanatory.  Available is a bit
- * more involved.
+ * Determine the numbers of file, headroom, dirty, and writeback pages in
+ * @wb's memcg.  File, dirty and writeback are self-explanatory.  Headroom
+ * is a bit more involved.
  *
- * A memcg's headroom is "min(max, high) - used".  The available memory is
- * calculated as the lowest headroom of itself and the ancestors plus the
- * number of pages already being used for file pages.  Note that this
- * doesn't consider the actual amount of available memory in the system.
- * The caller should further cap *@pavail accordingly.
+ * A memcg's headroom is "min(max, high) - used".  In the hierarchy, the
+ * headroom is calculated as the lowest headroom of itself and the
+ * ancestors.  Note that this doesn't consider the actual amount of
+ * available memory in the system.  The caller should further cap
+ * *@pheadroom accordingly.
  */
-void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pavail,
-			 unsigned long *pdirty, unsigned long *pwriteback)
+void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
+			 unsigned long *pheadroom, unsigned long *pdirty,
+			 unsigned long *pwriteback)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
 	struct mem_cgroup *parent;
-	unsigned long head_room = PAGE_COUNTER_MAX;
-	unsigned long file_pages;
 
 	*pdirty = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_DIRTY);
 
 	/* this should eventually include NR_UNSTABLE_NFS */
 	*pwriteback = mem_cgroup_read_stat(memcg, MEM_CGROUP_STAT_WRITEBACK);
+	*pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
+						     (1 << LRU_ACTIVE_FILE));
+	*pheadroom = PAGE_COUNTER_MAX;
 
-	file_pages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) |
-						    (1 << LRU_ACTIVE_FILE));
 	while ((parent = parent_mem_cgroup(memcg))) {
 		unsigned long ceiling = min(memcg->memory.limit, memcg->high);
 		unsigned long used = page_counter_read(&memcg->memory);
 
-		head_room = min(head_room, ceiling - min(ceiling, used));
+		*pheadroom = min(*pheadroom, ceiling - min(ceiling, used));
 		memcg = parent;
 	}
-
-	*pavail = file_pages + head_room;
 }
 
 #else	/* CONFIG_CGROUP_WRITEBACK */

mm/page-writeback.c

@@ -145,9 +145,6 @@ struct dirty_throttle_control {
 	unsigned long		pos_ratio;
 };
 
-#define DTC_INIT_COMMON(__wb)	.wb = (__wb),				\
-				.wb_completions = &(__wb)->completions
-
 /*
  * Length of period for aging writeout fractions of bdis. This is an
  * arbitrarily chosen number. The longer the period, the slower fractions will
@@ -157,12 +154,16 @@ struct dirty_throttle_control {
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-#define GDTC_INIT(__wb)		.dom = &global_wb_domain,		\
-				DTC_INIT_COMMON(__wb)
+#define GDTC_INIT(__wb)		.wb = (__wb),				\
+				.dom = &global_wb_domain,		\
+				.wb_completions = &(__wb)->completions
+
 #define GDTC_INIT_NO_WB		.dom = &global_wb_domain
-#define MDTC_INIT(__wb, __gdtc)	.dom = mem_cgroup_wb_domain(__wb),	\
-				.gdtc = __gdtc,				\
-				DTC_INIT_COMMON(__wb)
+
+#define MDTC_INIT(__wb, __gdtc)	.wb = (__wb),				\
+				.dom = mem_cgroup_wb_domain(__wb),	\
+				.wb_completions = &(__wb)->memcg_completions, \
+				.gdtc = __gdtc
 
 static bool mdtc_valid(struct dirty_throttle_control *dtc)
 {
@@ -213,7 +214,8 @@ static void wb_min_max_ratio(struct bdi_writeback *wb,
 
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
-#define GDTC_INIT(__wb)		DTC_INIT_COMMON(__wb)
+#define GDTC_INIT(__wb)		.wb = (__wb),                           \
+				.wb_completions = &(__wb)->completions
 #define GDTC_INIT_NO_WB
 #define MDTC_INIT(__wb, __gdtc)
 
@@ -682,13 +684,19 @@ static unsigned long hard_dirty_limit(struct wb_domain *dom,
 	return max(thresh, dom->dirty_limit);
 }
 
-/* memory available to a memcg domain is capped by system-wide clean memory */
-static void mdtc_cap_avail(struct dirty_throttle_control *mdtc)
+/*
+ * Memory which can be further allocated to a memcg domain is capped by
+ * system-wide clean memory excluding the amount being used in the domain.
+ */
+static void mdtc_calc_avail(struct dirty_throttle_control *mdtc,
+			    unsigned long filepages, unsigned long headroom)
 {
 	struct dirty_throttle_control *gdtc = mdtc_gdtc(mdtc);
-	unsigned long clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
+	unsigned long clean = filepages - min(filepages, mdtc->dirty);
+	unsigned long global_clean = gdtc->avail - min(gdtc->avail, gdtc->dirty);
+	unsigned long other_clean = global_clean - min(global_clean, clean);
 
-	mdtc->avail = min(mdtc->avail, clean);
+	mdtc->avail = filepages + min(headroom, other_clean);
 }
 
 /**
@@ -1562,16 +1570,16 @@ static void balance_dirty_pages(struct address_space *mapping,
 		}
 
 		if (mdtc) {
-			unsigned long writeback;
+			unsigned long filepages, headroom, writeback;
 
 			/*
 			 * If @wb belongs to !root memcg, repeat the same
 			 * basic calculations for the memcg domain.
 			 */
-			mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty,
-					    &writeback);
-			mdtc_cap_avail(mdtc);
+			mem_cgroup_wb_stats(wb, &filepages, &headroom,
+					    &mdtc->dirty, &writeback);
 			mdtc->dirty += writeback;
+			mdtc_calc_avail(mdtc, filepages, headroom);
 
 			domain_dirty_limits(mdtc);
 
@@ -1893,10 +1901,11 @@ bool wb_over_bg_thresh(struct bdi_writeback *wb)
 		return true;
 
 	if (mdtc) {
-		unsigned long writeback;
+		unsigned long filepages, headroom, writeback;
 
-		mem_cgroup_wb_stats(wb, &mdtc->avail, &mdtc->dirty, &writeback);
-		mdtc_cap_avail(mdtc);
+		mem_cgroup_wb_stats(wb, &filepages, &headroom, &mdtc->dirty,
+				    &writeback);
+		mdtc_calc_avail(mdtc, filepages, headroom);
 		domain_dirty_limits(mdtc);	/* ditto, ignore writeback */
 
 		if (mdtc->dirty > mdtc->bg_thresh)
@@ -1956,7 +1965,6 @@ void laptop_mode_timer_fn(unsigned long data)
 	int nr_pages = global_page_state(NR_FILE_DIRTY) +
 		global_page_state(NR_UNSTABLE_NFS);
 	struct bdi_writeback *wb;
-	struct wb_iter iter;
 
 	/*
 	 * We want to write everything out, not just down to the dirty
@@ -1965,10 +1973,12 @@ void laptop_mode_timer_fn(unsigned long data)
 	if (!bdi_has_dirty_io(&q->backing_dev_info))
 		return;
 
-	bdi_for_each_wb(wb, &q->backing_dev_info, &iter, 0)
+	rcu_read_lock();
+	list_for_each_entry_rcu(wb, &q->backing_dev_info.wb_list, bdi_node)
 		if (wb_has_dirty_io(wb))
 			wb_start_writeback(wb, nr_pages, true,
 					   WB_REASON_LAPTOP_TIMER);
+	rcu_read_unlock();
 }
 
 /*