Merge tag 'block-5.13-2021-05-22' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - Fix BLKRRPART and deletion race (Gulam, Christoph)

 - NVMe pull request (Christoph):
      - nvme-tcp corruption and timeout fixes (Sagi Grimberg, Keith
        Busch)
      - nvme-fc teardown fix (James Smart)
      - nvmet/nvme-loop memory leak fixes (Wu Bo)"

* tag 'block-5.13-2021-05-22' of git://git.kernel.dk/linux-block:
  block: fix a race between del_gendisk and BLKRRPART
  block: prevent block device lookups at the beginning of del_gendisk
  nvme-fc: clear q_live at beginning of association teardown
  nvme-tcp: rerun io_work if req_list is not empty
  nvme-tcp: fix possible use-after-completion
  nvme-loop: fix memory leak in nvme_loop_create_ctrl()
  nvmet: fix memory leak in nvmet_alloc_ctrl()

Author: torvalds

block/genhd.c

@@ -29,8 +29,6 @@
 
 static struct kobject *block_depr;
 
-DECLARE_RWSEM(bdev_lookup_sem);
-
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
 static DEFINE_IDA(ext_devt_ida);
@@ -609,13 +607,8 @@ void del_gendisk(struct gendisk *disk)
 	blk_integrity_del(disk);
 	disk_del_events(disk);
 
-	/*
-	 * Block lookups of the disk until all bdevs are unhashed and the
-	 * disk is marked as dead (GENHD_FL_UP cleared).
-	 */
-	down_write(&bdev_lookup_sem);
-
 	mutex_lock(&disk->part0->bd_mutex);
+	disk->flags &= ~GENHD_FL_UP;
 	blk_drop_partitions(disk);
 	mutex_unlock(&disk->part0->bd_mutex);
 
@@ -629,8 +622,6 @@ void del_gendisk(struct gendisk *disk)
 	remove_inode_hash(disk->part0->bd_inode);
 
 	set_capacity(disk, 0);
-	disk->flags &= ~GENHD_FL_UP;
-	up_write(&bdev_lookup_sem);
 
 	if (!(disk->flags & GENHD_FL_HIDDEN)) {
 		sysfs_remove_link(&disk_to_dev(disk)->kobj, "bdi");

drivers/nvme/host/fc.c

@@ -2461,6 +2461,18 @@ nvme_fc_terminate_exchange(struct request *req, void *data, bool reserved)
 static void
 __nvme_fc_abort_outstanding_ios(struct nvme_fc_ctrl *ctrl, bool start_queues)
 {
+	int q;
+
+	/*
+	 * if aborting io, the queues are no longer good, mark them
+	 * all as not live.
+	 */
+	if (ctrl->ctrl.queue_count > 1) {
+		for (q = 1; q < ctrl->ctrl.queue_count; q++)
+			clear_bit(NVME_FC_Q_LIVE, &ctrl->queues[q].flags);
+	}
+	clear_bit(NVME_FC_Q_LIVE, &ctrl->queues[0].flags);
+
 	/*
 	 * If io queues are present, stop them and terminate all outstanding
 	 * ios on them. As FC allocates FC exchange for each io, the

drivers/nvme/host/tcp.c

@@ -943,7 +943,6 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 		if (ret <= 0)
 			return ret;
 
-		nvme_tcp_advance_req(req, ret);
 		if (queue->data_digest)
 			nvme_tcp_ddgst_update(queue->snd_hash, page,
 					offset, ret);
@@ -960,6 +959,7 @@ static int nvme_tcp_try_send_data(struct nvme_tcp_request *req)
 			}
 			return 1;
 		}
+		nvme_tcp_advance_req(req, ret);
 	}
 	return -EAGAIN;
 }
@@ -1140,7 +1140,8 @@ static void nvme_tcp_io_work(struct work_struct *w)
 				pending = true;
 			else if (unlikely(result < 0))
 				break;
-		}
+		} else
+			pending = !llist_empty(&queue->req_list);
 
 		result = nvme_tcp_try_recv(queue);
 		if (result > 0)

drivers/nvme/target/core.c

@@ -1372,7 +1372,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 		goto out_free_changed_ns_list;
 
 	if (subsys->cntlid_min > subsys->cntlid_max)
-		goto out_free_changed_ns_list;
+		goto out_free_sqs;
 
 	ret = ida_simple_get(&cntlid_ida,
 			     subsys->cntlid_min, subsys->cntlid_max,

drivers/nvme/target/loop.c

@@ -590,8 +590,10 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 
 	ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_loop_ctrl_ops,
 				0 /* no quirks, we're perfect! */);
-	if (ret)
+	if (ret) {
+		kfree(ctrl);
 		goto out;
+	}
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING))
 		WARN_ON_ONCE(1);

fs/block_dev.c

@@ -1244,6 +1244,9 @@ int bdev_disk_changed(struct block_device *bdev, bool invalidate)
 
 	lockdep_assert_held(&bdev->bd_mutex);
 
+	if (!(disk->flags & GENHD_FL_UP))
+		return -ENXIO;
+
 rescan:
 	if (bdev->bd_part_count)
 		return -EBUSY;
@@ -1298,6 +1301,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 	struct gendisk *disk = bdev->bd_disk;
 	int ret = 0;
 
+	if (!(disk->flags & GENHD_FL_UP))
+		return -ENXIO;
+
 	if (!bdev->bd_openers) {
 		if (!bdev_is_partition(bdev)) {
 			ret = 0;
@@ -1332,8 +1338,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode)
 			whole->bd_part_count++;
 			mutex_unlock(&whole->bd_mutex);
 
-			if (!(disk->flags & GENHD_FL_UP) ||
-			    !bdev_nr_sectors(bdev)) {
+			if (!bdev_nr_sectors(bdev)) {
 				__blkdev_put(whole, mode, 1);
 				bdput(whole);
 				return -ENXIO;
@@ -1364,16 +1369,12 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 	struct block_device *bdev;
 	struct gendisk *disk;
 
-	down_read(&bdev_lookup_sem);
 	bdev = bdget(dev);
 	if (!bdev) {
-		up_read(&bdev_lookup_sem);
 		blk_request_module(dev);
-		down_read(&bdev_lookup_sem);
-
 		bdev = bdget(dev);
 		if (!bdev)
-			goto unlock;
+			return NULL;
 	}
 
 	disk = bdev->bd_disk;
@@ -1383,14 +1384,11 @@ struct block_device *blkdev_get_no_open(dev_t dev)
 		goto put_disk;
 	if (!try_module_get(bdev->bd_disk->fops->owner))
 		goto put_disk;
-	up_read(&bdev_lookup_sem);
 	return bdev;
 put_disk:
 	put_disk(disk);
 bdput:
 	bdput(bdev);
-unlock:
-	up_read(&bdev_lookup_sem);
 	return NULL;
 }
 

include/linux/genhd.h

@@ -306,8 +306,6 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 }
 #endif /* CONFIG_SYSFS */
 
-extern struct rw_semaphore bdev_lookup_sem;
-
 dev_t blk_lookup_devt(const char *name, int partno);
 void blk_request_module(dev_t devt);
 #ifdef CONFIG_BLOCK