Merge tag 'block-5.15-2021-09-17' of git://git.kernel.dk/linux-block

Pull block fixes from Jens Axboe:

 - NVMe pull request via Christoph:
       - fix ANA state updates when a namespace is not present (Anton
         Eidelman)
       - nvmet: fix a width vs precision bug in
         nvmet_subsys_attr_serial_show (Dan Carpenter)
       - avoid race in shutdown namespace removal (Daniel Wagner)
       - fix io_work priority inversion in nvme-tcp (Keith Busch)
       - destroy cm id before destroy qp to avoid use after free (Ruozhu
         Li)

 - blk-integrity profile registration fixes (Christoph, Lihong)

 - blk-cgroup UAF fix (Li)

 - blk-mq tag iterator fix (Ming)

 - blkcg memory leak fix (Yanfei)

* tag 'block-5.15-2021-09-17' of git://git.kernel.dk/linux-block:
  blk-cgroup: fix UAF by grabbing blkcg lock before destroying blkg pd
  blkcg: fix memory leak in blk_iolatency_init
  nvme: remove the call to nvme_update_disk_info in nvme_ns_remove
  block: flush the integrity workqueue in blk_integrity_unregister
  block: check if a profile is actually registered in blk_integrity_unregister
  nvme-tcp: fix io_work priority inversion
  nvme-rdma: destroy cm id before destroy qp to avoid use after free
  nvme-multipath: fix ANA state updates when a namespace is not present
  nvme: avoid race in shutdown namespace removal
  nvmet: fix a width vs precision bug in nvmet_subsys_attr_serial_show()
  blk-mq: avoid to iterate over stale request

block/blk-cgroup.c

@@ -1182,10 +1182,6 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
-	ret = blk_iolatency_init(q);
-	if (ret)
-		goto err_destroy_all;
-
 	ret = blk_ioprio_init(q);
 	if (ret)
 		goto err_destroy_all;
@@ -1194,6 +1190,12 @@ int blkcg_init_queue(struct request_queue *q)
 	if (ret)
 		goto err_destroy_all;
 
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		blk_throtl_exit(q);
+		goto err_destroy_all;
+	}
+
 	return 0;
 
 err_destroy_all:
@@ -1364,10 +1366,14 @@ int blkcg_activate_policy(struct request_queue *q,
 	/* alloc failed, nothing's initialized yet, free everything */
 	spin_lock_irq(&q->queue_lock);
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		struct blkcg *blkcg = blkg->blkcg;
+
+		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
+		spin_unlock(&blkcg->lock);
 	}
 	spin_unlock_irq(&q->queue_lock);
 	ret = -ENOMEM;
@@ -1399,12 +1405,16 @@ void blkcg_deactivate_policy(struct request_queue *q,
 	__clear_bit(pol->plid, q->blkcg_pols);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
+		struct blkcg *blkcg = blkg->blkcg;
+
+		spin_lock(&blkcg->lock);
 		if (blkg->pd[pol->plid]) {
 			if (pol->pd_offline_fn)
 				pol->pd_offline_fn(blkg->pd[pol->plid]);
 			pol->pd_free_fn(blkg->pd[pol->plid]);
 			blkg->pd[pol->plid] = NULL;
 		}
+		spin_unlock(&blkcg->lock);
 	}
 
 	spin_unlock_irq(&q->queue_lock);

block/blk-integrity.c

@@ -426,8 +426,15 @@ EXPORT_SYMBOL(blk_integrity_register);
  */
 void blk_integrity_unregister(struct gendisk *disk)
 {
+	struct blk_integrity *bi = &disk->queue->integrity;
+
+	if (!bi->profile)
+		return;
+
+	/* ensure all bios are off the integrity workqueue */
+	blk_flush_integrity();
 	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	memset(&disk->queue->integrity, 0, sizeof(struct blk_integrity));
+	memset(bi, 0, sizeof(*bi));
 }
 EXPORT_SYMBOL(blk_integrity_unregister);
 

block/blk-mq-tag.c

@@ -208,7 +208,7 @@ static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags,
 
 	spin_lock_irqsave(&tags->lock, flags);
 	rq = tags->rqs[bitnr];
-	if (!rq || !refcount_inc_not_zero(&rq->ref))
+	if (!rq || rq->tag != bitnr || !refcount_inc_not_zero(&rq->ref))
 		rq = NULL;
 	spin_unlock_irqrestore(&tags->lock, flags);
 	return rq;

drivers/nvme/host/core.c

@@ -3524,7 +3524,9 @@ static struct nvme_ns_head *nvme_find_ns_head(struct nvme_subsystem *subsys,
 	lockdep_assert_held(&subsys->lock);
 
 	list_for_each_entry(h, &subsys->nsheads, entry) {
-		if (h->ns_id == nsid && nvme_tryget_ns_head(h))
+		if (h->ns_id != nsid)
+			continue;
+		if (!list_empty(&h->list) && nvme_tryget_ns_head(h))
 			return h;
 	}
 
@@ -3843,6 +3845,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 
 	mutex_lock(&ns->ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
+	if (list_empty(&ns->head->list)) {
+		list_del_init(&ns->head->entry);
+		last_path = true;
+	}
 	mutex_unlock(&ns->ctrl->subsys->lock);
 
 	/* guarantee not available in head->list */
@@ -3856,20 +3862,11 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
 	blk_cleanup_queue(ns->queue);
-	if (blk_get_integrity(ns->disk))
-		blk_integrity_unregister(ns->disk);
 
 	down_write(&ns->ctrl->namespaces_rwsem);
 	list_del_init(&ns->list);
 	up_write(&ns->ctrl->namespaces_rwsem);
 
-	/* Synchronize with nvme_init_ns_head() */
-	mutex_lock(&ns->head->subsys->lock);
-	if (list_empty(&ns->head->list)) {
-		list_del_init(&ns->head->entry);
-		last_path = true;
-	}
-	mutex_unlock(&ns->head->subsys->lock);
 	if (last_path)
 		nvme_mpath_shutdown_disk(ns->head);
 	nvme_put_ns(ns);

drivers/nvme/host/multipath.c

@@ -600,14 +600,17 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		unsigned nsid = le32_to_cpu(desc->nsids[n]);
-
+		unsigned nsid;
+again:
+		nsid = le32_to_cpu(desc->nsids[n]);
 		if (ns->head->ns_id < nsid)
 			continue;
 		if (ns->head->ns_id == nsid)
 			nvme_update_ns_ana_state(desc, ns);
 		if (++n == nr_nsids)
 			break;
+		if (ns->head->ns_id > nsid)
+			goto again;
 	}
 	up_read(&ctrl->namespaces_rwsem);
 	return 0;

drivers/nvme/host/rdma.c

@@ -656,8 +656,8 @@ static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
 	if (!test_and_clear_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags))
 		return;
 
-	nvme_rdma_destroy_queue_ib(queue);
 	rdma_destroy_id(queue->cm_id);
+	nvme_rdma_destroy_queue_ib(queue);
 	mutex_destroy(&queue->queue_lock);
 }
 
@@ -1815,14 +1815,10 @@ static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue)
 	for (i = 0; i < queue->queue_size; i++) {
 		ret = nvme_rdma_post_recv(queue, &queue->rsp_ring[i]);
 		if (ret)
-			goto out_destroy_queue_ib;
+			return ret;
 	}
 
 	return 0;
-
-out_destroy_queue_ib:
-	nvme_rdma_destroy_queue_ib(queue);
-	return ret;
 }
 
 static int nvme_rdma_conn_rejected(struct nvme_rdma_queue *queue,
@@ -1916,14 +1912,10 @@ static int nvme_rdma_route_resolved(struct nvme_rdma_queue *queue)
 	if (ret) {
 		dev_err(ctrl->ctrl.device,
 			"rdma_connect_locked failed (%d).\n", ret);
-		goto out_destroy_queue_ib;
+		return ret;
 	}
 
 	return 0;
-
-out_destroy_queue_ib:
-	nvme_rdma_destroy_queue_ib(queue);
-	return ret;
 }
 
 static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
@@ -1954,8 +1946,6 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_ROUTE_ERROR:
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
-		nvme_rdma_destroy_queue_ib(queue);
-		fallthrough;
 	case RDMA_CM_EVENT_ADDR_ERROR:
 		dev_dbg(queue->ctrl->ctrl.device,
 			"CM error event %d\n", ev->event);

drivers/nvme/host/tcp.c

@@ -274,6 +274,12 @@ static inline void nvme_tcp_send_all(struct nvme_tcp_queue *queue)
 	} while (ret > 0);
 }
 
+static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
+{
+	return !list_empty(&queue->send_list) ||
+		!llist_empty(&queue->req_list) || queue->more_requests;
+}
+
 static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		bool sync, bool last)
 {
@@ -294,9 +300,10 @@ static inline void nvme_tcp_queue_request(struct nvme_tcp_request *req,
 		nvme_tcp_send_all(queue);
 		queue->more_requests = false;
 		mutex_unlock(&queue->send_mutex);
-	} else if (last) {
-		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 	}
+
+	if (last && nvme_tcp_queue_more(queue))
+		queue_work_on(queue->io_cpu, nvme_tcp_wq, &queue->io_work);
 }
 
 static void nvme_tcp_process_req_list(struct nvme_tcp_queue *queue)
@@ -906,12 +913,6 @@ static void nvme_tcp_state_change(struct sock *sk)
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
-static inline bool nvme_tcp_queue_more(struct nvme_tcp_queue *queue)
-{
-	return !list_empty(&queue->send_list) ||
-		!llist_empty(&queue->req_list) || queue->more_requests;
-}
-
 static inline void nvme_tcp_done_send_req(struct nvme_tcp_queue *queue)
 {
 	queue->request = NULL;
@@ -1145,8 +1146,7 @@ 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/configfs.c

@@ -1067,7 +1067,7 @@ static ssize_t nvmet_subsys_attr_serial_show(struct config_item *item,
 {
 	struct nvmet_subsys *subsys = to_subsys(item);
 
-	return snprintf(page, PAGE_SIZE, "%*s\n",
+	return snprintf(page, PAGE_SIZE, "%.*s\n",
 			NVMET_SN_MAX_SIZE, subsys->serial);
 }