12 files changed, 224 insertions, 134 deletions

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index dd6ec08651..25ecc1a005 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1388,7 +1388,7 @@ static void devm_apple_nvme_mempool_destroy(void *data)
 	mempool_destroy(data);
 }
 
-static int apple_nvme_probe(struct platform_device *pdev)
+static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct apple_nvme *anv;
@@ -1396,7 +1396,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
 
 	anv = devm_kzalloc(dev, sizeof(*anv), GFP_KERNEL);
 	if (!anv)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	anv->dev = get_device(dev);
 	anv->adminq.is_adminq = true;
@@ -1516,10 +1516,26 @@ static int apple_nvme_probe(struct platform_device *pdev)
 		goto put_dev;
 	}
 
+	return anv;
+put_dev:
+	put_device(anv->dev);
+	return ERR_PTR(ret);
+}
+
+static int apple_nvme_probe(struct platform_device *pdev)
+{
+	struct apple_nvme *anv;
+	int ret;
+
+	anv = apple_nvme_alloc(pdev);
+	if (IS_ERR(anv))
+		return PTR_ERR(anv);
+
 	anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
 	if (IS_ERR(anv->ctrl.admin_q)) {
 		ret = -ENOMEM;
-		goto put_dev;
+		anv->ctrl.admin_q = NULL;
+		goto out_uninit_ctrl;
 	}
 
 	nvme_reset_ctrl(&anv->ctrl);
@@ -1527,8 +1543,9 @@ static int apple_nvme_probe(struct platform_device *pdev)
 
 	return 0;
 
-put_dev:
-	put_device(anv->dev);
+out_uninit_ctrl:
+	nvme_uninit_ctrl(&anv->ctrl);
+	nvme_put_ctrl(&anv->ctrl);
 	return ret;
 }
 
@@ -1602,4 +1619,5 @@ static struct platform_driver apple_nvme_driver = {
 module_platform_driver(apple_nvme_driver);
 
 MODULE_AUTHOR("Sven Peter <sven@svenpeter.dev>");
+MODULE_DESCRIPTION("Apple ANS NVM Express device driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c
index a264b3ae07..371e14f0a2 100644
--- a/drivers/nvme/host/auth.c
+++ b/drivers/nvme/host/auth.c
@@ -730,7 +730,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
 					 NVME_AUTH_DHCHAP_MESSAGE_CHALLENGE);
 	if (ret) {
 		chap->status = ret;
-		chap->error = -ECONNREFUSED;
+		chap->error = -EKEYREJECTED;
 		return;
 	}
 
@@ -797,7 +797,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
 					 NVME_AUTH_DHCHAP_MESSAGE_SUCCESS1);
 	if (ret) {
 		chap->status = ret;
-		chap->error = -ECONNREFUSED;
+		chap->error = -EKEYREJECTED;
 		return;
 	}
 
@@ -818,7 +818,7 @@ static void nvme_queue_auth_work(struct work_struct *work)
 	ret = nvme_auth_process_dhchap_success1(ctrl, chap);
 	if (ret) {
 		/* Controller authentication failed */
-		chap->error = -ECONNREFUSED;
+		chap->error = -EKEYREJECTED;
 		goto fail2;
 	}
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d513fd2758..782090ce0b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -383,14 +383,14 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
 	if (likely(nvme_req(req)->status == 0))
 		return COMPLETE;
 
-	if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
-		return AUTHENTICATE;
-
 	if (blk_noretry_request(req) ||
 	    (nvme_req(req)->status & NVME_SC_DNR) ||
 	    nvme_req(req)->retries >= nvme_max_retries)
 		return COMPLETE;
 
+	if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
+		return AUTHENTICATE;
+
 	if (req->cmd_flags & REQ_NVME_MPATH) {
 		if (nvme_is_path_error(nvme_req(req)->status) ||
 		    blk_queue_dying(req->q))
@@ -678,7 +678,7 @@ static void nvme_free_ns(struct kref *kref)
 	kfree(ns);
 }
 
-static inline bool nvme_get_ns(struct nvme_ns *ns)
+bool nvme_get_ns(struct nvme_ns *ns)
 {
 	return kref_get_unless_zero(&ns->kref);
 }
@@ -998,6 +998,7 @@ void nvme_cleanup_cmd(struct request *req)
 			clear_bit_unlock(0, &ctrl->discard_page_busy);
 		else
 			kfree(bvec_virt(&req->special_vec));
+		req->rq_flags &= ~RQF_SPECIAL_PAYLOAD;
 	}
 }
 EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
@@ -2137,7 +2138,7 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	blk_mq_unfreeze_queue(ns->disk->queue);
 
 	if (blk_queue_is_zoned(ns->queue)) {
-		ret = blk_revalidate_disk_zones(ns->disk, NULL);
+		ret = blk_revalidate_disk_zones(ns->disk);
 		if (ret && !nvme_first_scan(ns->disk))
 			goto out;
 	}
@@ -3684,9 +3685,10 @@ out_unlock:
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 {
 	struct nvme_ns *ns, *ret = NULL;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		if (ns->head->ns_id == nsid) {
 			if (!nvme_get_ns(ns))
 				continue;
@@ -3696,7 +3698,7 @@ struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		if (ns->head->ns_id > nsid)
 			break;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return ret;
 }
 EXPORT_SYMBOL_NS_GPL(nvme_find_get_ns, NVME_TARGET_PASSTHRU);
@@ -3710,7 +3712,7 @@ static void nvme_ns_add_to_ctrl_list(struct nvme_ns *ns)
 
 	list_for_each_entry_reverse(tmp, &ns->ctrl->namespaces, list) {
 		if (tmp->head->ns_id < ns->head->ns_id) {
-			list_add(&ns->list, &tmp->list);
+			list_add_rcu(&ns->list, &tmp->list);
 			return;
 		}
 	}
@@ -3776,17 +3778,18 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 	if (nvme_update_ns_info(ns, info))
 		goto out_unlink_ns;
 
-	down_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
 	/*
 	 * Ensure that no namespaces are added to the ctrl list after the queues
 	 * are frozen, thereby avoiding a deadlock between scan and reset.
 	 */
 	if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
-		up_write(&ctrl->namespaces_rwsem);
+		mutex_unlock(&ctrl->namespaces_lock);
 		goto out_unlink_ns;
 	}
 	nvme_ns_add_to_ctrl_list(ns);
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
 	nvme_get_ctrl(ctrl);
 
 	if (device_add_disk(ctrl->device, ns->disk, nvme_ns_attr_groups))
@@ -3809,9 +3812,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 
  out_cleanup_ns_from_list:
 	nvme_put_ctrl(ctrl);
-	down_write(&ctrl->namespaces_rwsem);
-	list_del_init(&ns->list);
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
+	list_del_rcu(&ns->list);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
 	list_del_rcu(&ns->siblings);
@@ -3861,9 +3865,10 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 		nvme_cdev_del(&ns->cdev, &ns->cdev_device);
 	del_gendisk(ns->disk);
 
-	down_write(&ns->ctrl->namespaces_rwsem);
-	list_del_init(&ns->list);
-	up_write(&ns->ctrl->namespaces_rwsem);
+	mutex_lock(&ns->ctrl->namespaces_lock);
+	list_del_rcu(&ns->list);
+	mutex_unlock(&ns->ctrl->namespaces_lock);
+	synchronize_srcu(&ns->ctrl->srcu);
 
 	if (last_path)
 		nvme_mpath_shutdown_disk(ns->head);
@@ -3953,16 +3958,18 @@ static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 	struct nvme_ns *ns, *next;
 	LIST_HEAD(rm_list);
 
-	down_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
 	list_for_each_entry_safe(ns, next, &ctrl->namespaces, list) {
-		if (ns->head->ns_id > nsid)
-			list_move_tail(&ns->list, &rm_list);
+		if (ns->head->ns_id > nsid) {
+			list_del_rcu(&ns->list);
+			synchronize_srcu(&ctrl->srcu);
+			list_add_tail_rcu(&ns->list, &rm_list);
+		}
 	}
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_unlock(&ctrl->namespaces_lock);
 
 	list_for_each_entry_safe(ns, next, &rm_list, list)
 		nvme_ns_remove(ns);
-
 }
 
 static int nvme_scan_ns_list(struct nvme_ctrl *ctrl)
@@ -4132,9 +4139,10 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	/* this is a no-op when called from the controller reset handler */
 	nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING_NOIO);
 
-	down_write(&ctrl->namespaces_rwsem);
-	list_splice_init(&ctrl->namespaces, &ns_list);
-	up_write(&ctrl->namespaces_rwsem);
+	mutex_lock(&ctrl->namespaces_lock);
+	list_splice_init_rcu(&ctrl->namespaces, &ns_list, synchronize_rcu);
+	mutex_unlock(&ctrl->namespaces_lock);
+	synchronize_srcu(&ctrl->srcu);
 
 	list_for_each_entry_safe(ns, next, &ns_list, list)
 		nvme_ns_remove(ns);
@@ -4582,6 +4590,7 @@ static void nvme_free_ctrl(struct device *dev)
 	key_put(ctrl->tls_key);
 	nvme_free_cels(ctrl);
 	nvme_mpath_uninit(ctrl);
+	cleanup_srcu_struct(&ctrl->srcu);
 	nvme_auth_stop(ctrl);
 	nvme_auth_free(ctrl);
 	__free_page(ctrl->discard_page);
@@ -4614,10 +4623,15 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	ctrl->passthru_err_log_enabled = false;
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
+	mutex_init(&ctrl->namespaces_lock);
+
+	ret = init_srcu_struct(&ctrl->srcu);
+	if (ret)
+		return ret;
+
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
 	xa_init(&ctrl->cels);
-	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
 	ctrl->quirks = quirks;
@@ -4697,6 +4711,7 @@ out_release_instance:
 out:
 	if (ctrl->discard_page)
 		__free_page(ctrl->discard_page);
+	cleanup_srcu_struct(&ctrl->srcu);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_init_ctrl);
@@ -4705,22 +4720,24 @@ EXPORT_SYMBOL_GPL(nvme_init_ctrl);
 void nvme_mark_namespaces_dead(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_mark_disk_dead(ns->disk);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_mark_namespaces_dead);
 
 void nvme_unfreeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_mq_unfreeze_queue(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
@@ -4728,14 +4745,15 @@ EXPORT_SYMBOL_GPL(nvme_unfreeze);
 int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		timeout = blk_mq_freeze_queue_wait_timeout(ns->queue, timeout);
 		if (timeout <= 0)
 			break;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return timeout;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
@@ -4743,23 +4761,25 @@ EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_mq_freeze_queue_wait(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze);
 
 void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
 	set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_freeze_queue_start(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_start_freeze);
 
@@ -4802,11 +4822,12 @@ EXPORT_SYMBOL_GPL(nvme_unquiesce_admin_queue);
 void nvme_sync_io_queues(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list)
 		blk_sync_queue(ns->queue);
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 EXPORT_SYMBOL_GPL(nvme_sync_io_queues);
 
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 1f0ea1f32d..ceb9c0ed31 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -180,7 +180,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0);
+			NVME_QID_ANY, NVME_SUBMIT_RESERVED);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -226,7 +226,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
 	cmd.prop_get.offset = cpu_to_le32(off);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, &res, NULL, 0,
-			NVME_QID_ANY, 0);
+			NVME_QID_ANY, NVME_SUBMIT_RESERVED);
 
 	if (ret >= 0)
 		*val = le64_to_cpu(res.u64);
@@ -271,7 +271,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
 	cmd.prop_set.value = cpu_to_le64(val);
 
 	ret = __nvme_submit_sync_cmd(ctrl->fabrics_q, &cmd, NULL, NULL, 0,
-			NVME_QID_ANY, 0);
+			NVME_QID_ANY, NVME_SUBMIT_RESERVED);
 	if (unlikely(ret))
 		dev_err(ctrl->device,
 			"Property Set error: %d, offset %#x\n",
@@ -428,12 +428,6 @@ static void nvmf_connect_cmd_prep(struct nvme_ctrl *ctrl, u16 qid,
  * fabrics-protocol connection of the NVMe Admin queue between the
  * host system device and the allocated NVMe controller on the
  * target system via a NVMe Fabrics "Connect" command.
- *
- * Return:
- *	0: success
- *	> 0: NVMe error status code
- *	< 0: Linux errno error code
- *
  */
 int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 {
@@ -467,7 +461,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 		if (result & NVME_CONNECT_AUTHREQ_ASCR) {
 			dev_warn(ctrl->device,
 				 "qid 0: secure concatenation is not supported\n");
-			ret = NVME_SC_AUTH_REQUIRED;
+			ret = -EOPNOTSUPP;
 			goto out_free_data;
 		}
 		/* Authentication required */
@@ -475,14 +469,14 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl)
 		if (ret) {
 			dev_warn(ctrl->device,
 				 "qid 0: authentication setup failed\n");
-			ret = NVME_SC_AUTH_REQUIRED;
 			goto out_free_data;
 		}
 		ret = nvme_auth_wait(ctrl, 0);
-		if (ret)
+		if (ret) {
 			dev_warn(ctrl->device,
-				 "qid 0: authentication failed\n");
-		else
+				 "qid 0: authentication failed, error %d\n",
+				 ret);
+		} else
 			dev_info(ctrl->device,
 				 "qid 0: authenticated\n");
 	}
@@ -542,7 +536,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 		if (result & NVME_CONNECT_AUTHREQ_ASCR) {
 			dev_warn(ctrl->device,
 				 "qid 0: secure concatenation is not supported\n");
-			ret = NVME_SC_AUTH_REQUIRED;
+			ret = -EOPNOTSUPP;
 			goto out_free_data;
 		}
 		/* Authentication required */
@@ -550,12 +544,13 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
 		if (ret) {
 			dev_warn(ctrl->device,
 				 "qid %d: authentication setup failed\n", qid);
-			ret = NVME_SC_AUTH_REQUIRED;
-		} else {
-			ret = nvme_auth_wait(ctrl, qid);
-			if (ret)
-				dev_warn(ctrl->device,
-					 "qid %u: authentication failed\n", qid);
+			goto out_free_data;
+		}
+		ret = nvme_auth_wait(ctrl, qid);
+		if (ret) {
+			dev_warn(ctrl->device,
+				 "qid %u: authentication failed, error %d\n",
+				 qid, ret);
 		}
 	}
 out_free_data:
@@ -564,8 +559,26 @@ out_free_data:
 }
 EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
 
-bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
+/*
+ * Evaluate the status information returned by the transport in order to decided
+ * if a reconnect attempt should be scheduled.
+ *
+ * Do not retry when:
+ *
+ * - the DNR bit is set and the specification states no further connect
+ *   attempts with the same set of paramenters should be attempted.
+ *
+ * - when the authentication attempt fails, because the key was invalid.
+ *   This error code is set on the host side.
+ */
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status)
 {
+	if (status > 0 && (status & NVME_SC_DNR))
+		return false;
+
+	if (status == -EKEYREJECTED)
+		return false;
+
 	if (ctrl->opts->max_reconnects == -1 ||
 	    ctrl->nr_reconnects < ctrl->opts->max_reconnects)
 		return true;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 37c974c38d..602135910a 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -223,7 +223,7 @@ int nvmf_register_transport(struct nvmf_transport_ops *ops);
 void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
-bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status);
 bool nvmf_ip_options_match(struct nvme_ctrl *ctrl,
 		struct nvmf_ctrl_options *opts);
 void nvmf_set_io_queues(struct nvmf_ctrl_options *opts, u32 nr_io_queues,
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index a5b29e9ad3..f0b0813327 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -3310,12 +3310,10 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
 		dev_info(ctrl->ctrl.device,
 			"NVME-FC{%d}: reset: Reconnect attempt failed (%d)\n",
 			ctrl->cnum, status);
-		if (status > 0 && (status & NVME_SC_DNR))
-			recon = false;
 	} else if (time_after_eq(jiffies, rport->dev_loss_end))
 		recon = false;
 
-	if (recon && nvmf_should_reconnect(&ctrl->ctrl)) {
+	if (recon && nvmf_should_reconnect(&ctrl->ctrl, status)) {
 		if (portptr->port_state == FC_OBJSTATE_ONLINE)
 			dev_info(ctrl->ctrl.device,
 				"NVME-FC{%d}: Reconnect attempt in %ld "
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 3dfd5ae99a..8b69427a44 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -111,6 +111,13 @@ static struct request *nvme_alloc_user_request(struct request_queue *q,
 	return req;
 }
 
+static void nvme_unmap_bio(struct bio *bio)
+{
+	if (bio_integrity(bio))
+		bio_integrity_unmap_free_user(bio);
+	blk_rq_unmap_user(bio);
+}
+
 static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		unsigned bufflen, void __user *meta_buffer, unsigned meta_len,
 		u32 meta_seed, struct io_uring_cmd *ioucmd, unsigned int flags)
@@ -157,7 +164,7 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 
 out_unmap:
 	if (bio)
-		blk_rq_unmap_user(bio);
+		nvme_unmap_bio(bio);
 out:
 	blk_mq_free_request(req);
 	return ret;
@@ -195,7 +202,7 @@ static int nvme_submit_user_cmd(struct request_queue *q,
 	if (result)
 		*result = le64_to_cpu(nvme_req(req)->result.u64);
 	if (bio)
-		blk_rq_unmap_user(bio);
+		nvme_unmap_bio(bio);
 	blk_mq_free_request(req);
 
 	if (effects)
@@ -406,7 +413,7 @@ static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
 	if (pdu->bio)
-		blk_rq_unmap_user(pdu->bio);
+		nvme_unmap_bio(pdu->bio);
 	io_uring_cmd_done(ioucmd, pdu->status, pdu->result, issue_flags);
 }
 
@@ -423,13 +430,20 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,
 	pdu->result = le64_to_cpu(nvme_req(req)->result.u64);
 
 	/*
-	 * For iopoll, complete it directly.
+	 * For iopoll, complete it directly. Note that using the uring_cmd
+	 * helper for this is safe only because we check blk_rq_is_poll().
+	 * As that returns false if we're NOT on a polled queue, then it's
+	 * safe to use the polled completion helper.
+	 *
 	 * Otherwise, move the completion to task work.
 	 */
-	if (blk_rq_is_poll(req))
-		nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED);
-	else
+	if (blk_rq_is_poll(req)) {
+		if (pdu->bio)
+			nvme_unmap_bio(pdu->bio);
+		io_uring_cmd_iopoll_done(ioucmd, pdu->result, pdu->status);
+	} else {
 		io_uring_cmd_do_in_task_lazy(ioucmd, nvme_uring_task_cb);
+	}
 
 	return RQ_END_IO_FREE;
 }
@@ -782,15 +796,15 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 		bool open_for_write)
 {
 	struct nvme_ns *ns;
-	int ret;
+	int ret, srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
 	if (list_empty(&ctrl->namespaces)) {
 		ret = -ENOTTY;
 		goto out_unlock;
 	}
 
-	ns = list_first_entry(&ctrl->namespaces, struct nvme_ns, list);
+	ns = list_first_or_null_rcu(&ctrl->namespaces, struct nvme_ns, list);
 	if (ns != list_last_entry(&ctrl->namespaces, struct nvme_ns, list)) {
 		dev_warn(ctrl->device,
 			"NVME_IOCTL_IO_CMD not supported when multiple namespaces present!\n");
@@ -800,15 +814,18 @@ static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp,
 
 	dev_warn(ctrl->device,
 		"using deprecated NVME_IOCTL_IO_CMD ioctl on the char device!\n");
-	kref_get(&ns->kref);
-	up_read(&ctrl->namespaces_rwsem);
+	if (!nvme_get_ns(ns)) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 
 	ret = nvme_user_cmd(ctrl, ns, argp, 0, open_for_write);
 	nvme_put_ns(ns);
 	return ret;
 
 out_unlock:
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return ret;
 }
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index a4e46eb20b..d8b6b4648e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -151,16 +151,17 @@ void nvme_mpath_end_request(struct request *rq)
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		if (!ns->head->disk)
 			continue;
 		kblockd_schedule_work(&ns->head->requeue_work);
 		if (nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 
 static const char *nvme_ana_state_names[] = {
@@ -194,13 +195,14 @@ out:
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
+	int srcu_idx;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		nvme_mpath_clear_current_path(ns);
 		kblockd_schedule_work(&ns->head->requeue_work);
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 }
 
 void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -596,7 +598,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 		int node, srcu_idx;
 
 		srcu_idx = srcu_read_lock(&head->srcu);
-		for_each_node(node)
+		for_each_online_node(node)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
@@ -681,6 +683,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
 	unsigned *nr_change_groups = data;
 	struct nvme_ns *ns;
+	int srcu_idx;
 
 	dev_dbg(ctrl->device, "ANA group %d: %s.\n",
 			le32_to_cpu(desc->grpid),
@@ -692,8 +695,8 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	if (!nr_nsids)
 		return 0;
 
-	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list) {
+	srcu_idx = srcu_read_lock(&ctrl->srcu);
+	list_for_each_entry_rcu(ns, &ctrl->namespaces, list) {
 		unsigned nsid;
 again:
 		nsid = le32_to_cpu(desc->nsids[n]);
@@ -706,7 +709,7 @@ again:
 		if (ns->head->ns_id > nsid)
 			goto again;
 	}
-	up_read(&ctrl->namespaces_rwsem);
+	srcu_read_unlock(&ctrl->srcu, srcu_idx);
 	return 0;
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index d7bcc6d51e..68b400f9c4 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -282,7 +282,8 @@ struct nvme_ctrl {
 	struct blk_mq_tag_set *tagset;
 	struct blk_mq_tag_set *admin_tagset;
 	struct list_head namespaces;
-	struct rw_semaphore namespaces_rwsem;
+	struct mutex namespaces_lock;
+	struct srcu_struct srcu;
 	struct device ctrl_device;
 	struct device *device;	/* char device */
 #ifdef CONFIG_NVME_HWMON
@@ -471,8 +472,6 @@ struct nvme_ns_head {
 	u8			pi_type;
 	u8			pi_offset;
 	u8			guard_type;
-	u16			sgs;
-	u32			sws;
 #ifdef CONFIG_BLK_DEV_ZONED
 	u64			zsze;
 #endif
@@ -503,7 +502,7 @@ static inline bool nvme_ns_head_multipath(struct nvme_ns_head *head)
 enum nvme_ns_features {
 	NVME_NS_EXT_LBAS = 1 << 0, /* support extended LBA format */
 	NVME_NS_METADATA_SUPPORTED = 1 << 1, /* support getting generated md */
-	NVME_NS_DEAC,		/* DEAC bit in Write Zeores supported */
+	NVME_NS_DEAC = 1 << 2,		/* DEAC bit in Write Zeores supported */
 };
 
 struct nvme_ns {
@@ -1149,7 +1148,7 @@ static inline int nvme_auth_negotiate(struct nvme_ctrl *ctrl, int qid)
 }
 static inline int nvme_auth_wait(struct nvme_ctrl *ctrl, int qid)
 {
-	return NVME_SC_AUTH_REQUIRED;
+	return -EPROTONOSUPPORT;
 }
 static inline void nvme_auth_free(struct nvme_ctrl *ctrl) {};
 #endif
@@ -1162,6 +1161,7 @@ void nvme_passthru_end(struct nvme_ctrl *ctrl, struct nvme_ns *ns, u32 effects,
 		       struct nvme_command *cmd, int status);
 struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
+bool nvme_get_ns(struct nvme_ns *ns);
 void nvme_put_ns(struct nvme_ns *ns);
 
 static inline bool nvme_multi_css(struct nvme_ctrl *ctrl)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 710043086d..a823330567 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -778,7 +778,8 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		struct bio_vec bv = req_bvec(req);
 
 		if (!is_pci_p2pdma_page(bv.bv_page)) {
-			if (bv.bv_offset + bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
+			if ((bv.bv_offset & (NVME_CTRL_PAGE_SIZE - 1)) +
+			     bv.bv_len <= NVME_CTRL_PAGE_SIZE * 2)
 				return nvme_setup_prp_simple(dev, req,
 							     &cmnd->rw, &bv);
 
@@ -825,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
 		struct nvme_command *cmnd)
 {
 	struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+	struct bio_vec bv = rq_integrity_vec(req);
 
-	iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
-			rq_dma_dir(req), 0);
+	iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
 	if (dma_mapping_error(dev->dev, iod->meta_dma))
 		return BLK_STS_IOERR;
 	cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
@@ -862,7 +863,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
 	nvme_start_request(req);
 	return BLK_STS_OK;
 out_unmap_data:
-	nvme_unmap_data(dev, req);
+	if (blk_rq_nr_phys_segments(req))
+		nvme_unmap_data(dev, req);
 out_free_cmd:
 	nvme_cleanup_cmd(req);
 	return ret;
@@ -966,7 +968,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
 	        struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
 		dma_unmap_page(dev->dev, iod->meta_dma,
-			       rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
+			       rq_integrity_vec(req).bv_len, rq_dma_dir(req));
 	}
 
 	if (blk_rq_nr_phys_segments(req))
@@ -1273,7 +1275,7 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
 	dev_warn(dev->ctrl.device,
 		 "Does your device have a faulty power saving mode enabled?\n");
 	dev_warn(dev->ctrl.device,
-		 "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
+		 "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off\" and report a bug\n");
 }
 
 static enum blk_eh_timer_return nvme_timeout(struct request *req)
@@ -2931,6 +2933,13 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
 			return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
 	}
 
+	/*
+	 * NVMe SSD drops off the PCIe bus after system idle
+	 * for 10 hours on a Lenovo N60z board.
+	 */
+	if (dmi_match(DMI_BOARD_NAME, "LXKT-ZXEG-N6"))
+		return NVME_QUIRK_NO_APST;
+
 	return 0;
 }
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 366f0bb4eb..51a62b0c64 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -982,7 +982,8 @@ free_ctrl:
 	kfree(ctrl);
 }
 
-static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl,
+					  int status)
 {
 	enum nvme_ctrl_state state = nvme_ctrl_state(&ctrl->ctrl);
 
@@ -992,7 +993,7 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 		return;
 	}
 
-	if (nvmf_should_reconnect(&ctrl->ctrl)) {
+	if (nvmf_should_reconnect(&ctrl->ctrl, status)) {
 		dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
 			ctrl->ctrl.opts->reconnect_delay);
 		queue_delayed_work(nvme_wq, &ctrl->reconnect_work,
@@ -1104,10 +1105,12 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_rdma_ctrl, reconnect_work);
+	int ret;
 
 	++ctrl->ctrl.nr_reconnects;
 
-	if (nvme_rdma_setup_ctrl(ctrl, false))
+	ret = nvme_rdma_setup_ctrl(ctrl, false);
+	if (ret)
 		goto requeue;
 
 	dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
@@ -1118,9 +1121,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	return;
 
 requeue:
-	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
-			ctrl->ctrl.nr_reconnects);
-	nvme_rdma_reconnect_or_remove(ctrl);
+	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d/%d\n",
+		 ctrl->ctrl.nr_reconnects, ctrl->ctrl.opts->max_reconnects);
+	nvme_rdma_reconnect_or_remove(ctrl, ret);
 }
 
 static void nvme_rdma_error_recovery_work(struct work_struct *work)
@@ -1145,7 +1148,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 		return;
 	}
 
-	nvme_rdma_reconnect_or_remove(ctrl);
+	nvme_rdma_reconnect_or_remove(ctrl, 0);
 }
 
 static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
@@ -2169,6 +2172,7 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl =
 		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
+	int ret;
 
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -2179,14 +2183,15 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	if (nvme_rdma_setup_ctrl(ctrl, false))
+	ret = nvme_rdma_setup_ctrl(ctrl, false);
+	if (ret)
 		goto out_fail;
 
 	return;
 
 out_fail:
 	++ctrl->ctrl.nr_reconnects;
-	nvme_rdma_reconnect_or_remove(ctrl);
+	nvme_rdma_reconnect_or_remove(ctrl, ret);
 }
 
 static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = {
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 28bc2f373c..8b5e4327fe 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2161,7 +2161,8 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl,
 	nvme_tcp_destroy_io_queues(ctrl, remove);
 }
 
-static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
+static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl,
+		int status)
 {
 	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
 
@@ -2171,13 +2172,14 @@ static void nvme_tcp_reconnect_or_remove(struct nvme_ctrl *ctrl)
 		return;
 	}
 
-	if (nvmf_should_reconnect(ctrl)) {
+	if (nvmf_should_reconnect(ctrl, status)) {
 		dev_info(ctrl->device, "Reconnecting in %d seconds...\n",
 			ctrl->opts->reconnect_delay);
 		queue_delayed_work(nvme_wq, &to_tcp_ctrl(ctrl)->connect_work,
 				ctrl->opts->reconnect_delay * HZ);
 	} else {
-		dev_info(ctrl->device, "Removing controller...\n");
+		dev_info(ctrl->device, "Removing controller (%d)...\n",
+			 status);
 		nvme_delete_ctrl(ctrl);
 	}
 }
@@ -2258,23 +2260,25 @@ static void nvme_tcp_reconnect_ctrl_work(struct work_struct *work)
 	struct nvme_tcp_ctrl *tcp_ctrl = container_of(to_delayed_work(work),
 			struct nvme_tcp_ctrl, connect_work);
 	struct nvme_ctrl *ctrl = &tcp_ctrl->ctrl;
+	int ret;
 
 	++ctrl->nr_reconnects;
 
-	if (nvme_tcp_setup_ctrl(ctrl, false))
+	ret = nvme_tcp_setup_ctrl(ctrl, false);
+	if (ret)
 		goto requeue;
 
-	dev_info(ctrl->device, "Successfully reconnected (%d attempt)\n",
-			ctrl->nr_reconnects);
+	dev_info(ctrl->device, "Successfully reconnected (attempt %d/%d)\n",
+		 ctrl->nr_reconnects, ctrl->opts->max_reconnects);
 
 	ctrl->nr_reconnects = 0;
 
 	return;
 
 requeue:
-	dev_info(ctrl->device, "Failed reconnect attempt %d\n",
-			ctrl->nr_reconnects);
-	nvme_tcp_reconnect_or_remove(ctrl);
+	dev_info(ctrl->device, "Failed reconnect attempt %d/%d\n",
+		 ctrl->nr_reconnects, ctrl->opts->max_reconnects);
+	nvme_tcp_reconnect_or_remove(ctrl, ret);
 }
 
 static void nvme_tcp_error_recovery_work(struct work_struct *work)
@@ -2301,7 +2305,7 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work)
 		return;
 	}
 
-	nvme_tcp_reconnect_or_remove(ctrl);
+	nvme_tcp_reconnect_or_remove(ctrl, 0);
 }
 
 static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown)
@@ -2321,6 +2325,7 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl =
 		container_of(work, struct nvme_ctrl, reset_work);
+	int ret;
 
 	nvme_stop_ctrl(ctrl);
 	nvme_tcp_teardown_ctrl(ctrl, false);
@@ -2334,14 +2339,15 @@ static void nvme_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	if (nvme_tcp_setup_ctrl(ctrl, false))
+	ret = nvme_tcp_setup_ctrl(ctrl, false);
+	if (ret)
 		goto out_fail;
 
 	return;
 
 out_fail:
 	++ctrl->nr_reconnects;
-	nvme_tcp_reconnect_or_remove(ctrl);
+	nvme_tcp_reconnect_or_remove(ctrl, ret);
 }
 
 static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl)