Merge tag 'nvme-for-4.18' of git://git.infradead.org/nvme

Pull NVMe fixes from Christoph Hellwig:

 - fix a regression in 4.18 that causes a memory leak on probe failure
   (Keith Bush)

 - fix a deadlock in the passthrough ioctl code (Scott Bauer)

 - don't enable AENs if not supported (Weiping Zhang)

 - fix an old regression in metadata handling in the passthrough ioctl
   code (Roland Dreier)

* tag 'nvme-for-4.18' of git://git.infradead.org/nvme:
  nvme: fix handling of metadata_len for NVME_IOCTL_IO_CMD
  nvme: don't enable AEN if not supported
  nvme: ensure forward progress during Admin passthru
  nvme-pci: fix memory leak on probe failure

Author: torvalds

drivers/nvme/host/core.c

@@ -100,6 +100,22 @@ static struct class *nvme_subsys_class;
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
+static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
+					   unsigned nsid);
+
+static void nvme_set_queue_dying(struct nvme_ns *ns)
+{
+	/*
+	 * Revalidating a dead namespace sets capacity to 0. This will end
+	 * buffered writers dirtying pages that can't be synced.
+	 */
+	if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
+		return;
+	revalidate_disk(ns->disk);
+	blk_set_queue_dying(ns->queue);
+	/* Forcibly unquiesce queues to avoid blocking dispatch */
+	blk_mq_unquiesce_queue(ns->queue);
+}
 
 static void nvme_queue_scan(struct nvme_ctrl *ctrl)
 {
@@ -1044,14 +1060,17 @@ EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
-	u32 result;
+	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
 	int status;
 
-	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
-			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	if (!supported_aens)
+		return;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported_aens,
+			NULL, 0, &result);
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
-			 ctrl->oaes & NVME_AEN_SUPPORTED);
+			 supported_aens);
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -1151,19 +1170,15 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 
 static void nvme_update_formats(struct nvme_ctrl *ctrl)
 {
-	struct nvme_ns *ns, *next;
-	LIST_HEAD(rm_list);
+	struct nvme_ns *ns;
 
-	down_write(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->disk && nvme_revalidate_disk(ns->disk)) {
-			list_move_tail(&ns->list, &rm_list);
-		}
-	}
-	up_write(&ctrl->namespaces_rwsem);
+	down_read(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		if (ns->disk && nvme_revalidate_disk(ns->disk))
+			nvme_set_queue_dying(ns);
+	up_read(&ctrl->namespaces_rwsem);
 
-	list_for_each_entry_safe(ns, next, &rm_list, list)
-		nvme_ns_remove(ns);
+	nvme_remove_invalid_namespaces(ctrl, NVME_NSID_ALL);
 }
 
 static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
@@ -1218,7 +1233,7 @@ static int nvme_user_cmd(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	effects = nvme_passthru_start(ctrl, ns, cmd.opcode);
 	status = nvme_submit_user_cmd(ns ? ns->queue : ctrl->admin_q, &c,
 			(void __user *)(uintptr_t)cmd.addr, cmd.data_len,
-			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata,
+			(void __user *)(uintptr_t)cmd.metadata, cmd.metadata_len,
 			0, &cmd.result, timeout);
 	nvme_passthru_end(ctrl, effects);
 
@@ -3138,7 +3153,7 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 
 	down_write(&ctrl->namespaces_rwsem);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
+		if (ns->head->ns_id > nsid || test_bit(NVME_NS_DEAD, &ns->flags))
 			list_move_tail(&ns->list, &rm_list);
 	}
 	up_write(&ctrl->namespaces_rwsem);
@@ -3542,19 +3557,9 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl)
 	if (ctrl->admin_q)
 		blk_mq_unquiesce_queue(ctrl->admin_q);
 
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		/*
-		 * Revalidating a dead namespace sets capacity to 0. This will
-		 * end buffered writers dirtying pages that can't be synced.
-		 */
-		if (!ns->disk || test_and_set_bit(NVME_NS_DEAD, &ns->flags))
-			continue;
-		revalidate_disk(ns->disk);
-		blk_set_queue_dying(ns->queue);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		nvme_set_queue_dying(ns);
 
-		/* Forcibly unquiesce queues to avoid blocking dispatch */
-		blk_mq_unquiesce_queue(ns->queue);
-	}
 	up_read(&ctrl->namespaces_rwsem);
 }
 EXPORT_SYMBOL_GPL(nvme_kill_queues);

drivers/nvme/host/pci.c

@@ -2556,11 +2556,6 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	quirks |= check_vendor_combination_bug(pdev);
 
-	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
-			quirks);
-	if (result)
-		goto release_pools;
-
 	/*
 	 * Double check that our mempool alloc size will cover the biggest
 	 * command we support.
@@ -2578,13 +2573,20 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto release_pools;
 	}
 
+	result = nvme_init_ctrl(&dev->ctrl, &pdev->dev, &nvme_pci_ctrl_ops,
+			quirks);
+	if (result)
+		goto release_mempool;
+
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	nvme_get_ctrl(&dev->ctrl);
 	async_schedule(nvme_async_probe, dev);
 
 	return 0;
 
+ release_mempool:
+	mempool_destroy(dev->iod_mempool);
  release_pools:
 	nvme_release_prp_pools(dev);
  unmap: