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)

Author: torvalds

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 */