Merge branch 'nvme-5.2' of git://git.infradead.org/nvme into for-5.2/block

Pull NVMe updates from Christoph.

* 'nvme-5.2' of git://git.infradead.org/nvme:
  nvmet: protect discovery change log event list iteration
  nvme: mark nvme_core_init and nvme_core_exit static
  nvme: move command size checks to the core
  nvme-fabrics: check more command sizes
  nvme-pci: check more command sizes
  nvme-pci: remove an unneeded variable initialization
  nvme-pci: unquiesce admin queue on shutdown
  nvme-pci: shutdown on timeout during deletion
  nvme-pci: fix psdt field for single segment sgls
  nvme-multipath: don't print ANA group state by default
  nvme-multipath: split bios with the ns_head bio_set before submitting
  nvme-tcp: fix possible null deref on a timed out io queue connect

drivers/nvme/host/core.c

@@ -3879,10 +3879,37 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-int __init nvme_core_init(void)
+/*
+ * Check we didn't inadvertently grow the command structure sizes:
+ */
+static inline void _nvme_check_size(void)
+{
+	BUILD_BUG_ON(sizeof(struct nvme_common_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_identify) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_download_firmware) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_dsm_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_write_zeroes_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_get_log_page_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
+	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
+	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64);
+}
+
+
+static int __init nvme_core_init(void)
 {
 	int result = -ENOMEM;
 
+	_nvme_check_size();
+
 	nvme_wq = alloc_workqueue("nvme-wq",
 			WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0);
 	if (!nvme_wq)
@@ -3929,7 +3956,7 @@ int __init nvme_core_init(void)
 	return result;
 }
 
-void __exit nvme_core_exit(void)
+static void __exit nvme_core_exit(void)
 {
 	ida_destroy(&nvme_subsystems_ida);
 	class_destroy(nvme_subsys_class);

drivers/nvme/host/fabrics.c

@@ -1188,6 +1188,7 @@ static void __exit nvmf_exit(void)
 	class_destroy(nvmf_class);
 	nvmf_host_put(nvmf_default_host);
 
+	BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64);
 	BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64);

drivers/nvme/host/multipath.c

@@ -232,6 +232,14 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 	blk_qc_t ret = BLK_QC_T_NONE;
 	int srcu_idx;
 
+	/*
+	 * The namespace might be going away and the bio might
+	 * be moved to a different queue via blk_steal_bios(),
+	 * so we need to use the bio_split pool from the original
+	 * queue to allocate the bvecs from.
+	 */
+	blk_queue_split(q, &bio);
+
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = nvme_find_path(head);
 	if (likely(ns)) {
@@ -421,7 +429,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
 	unsigned *nr_change_groups = data;
 	struct nvme_ns *ns;
 
-	dev_info(ctrl->device, "ANA group %d: %s.\n",
+	dev_dbg(ctrl->device, "ANA group %d: %s.\n",
 			le32_to_cpu(desc->grpid),
 			nvme_ana_state_names[desc->state]);
 

drivers/nvme/host/nvme.h

@@ -577,7 +577,4 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 	return dev_to_disk(dev)->private_data;
 }
 
-int __init nvme_core_init(void);
-void __exit nvme_core_exit(void);
-
 #endif /* _NVME_H */

drivers/nvme/host/pci.c

@@ -146,7 +146,7 @@ static int io_queue_depth_set(const char *val, const struct kernel_param *kp)
 
 static int queue_count_set(const char *val, const struct kernel_param *kp)
 {
-	int n = 0, ret;
+	int n, ret;
 
 	ret = kstrtoint(val, 10, &n);
 	if (ret)
@@ -226,26 +226,6 @@ struct nvme_iod {
 	struct scatterlist *sg;
 };
 
-/*
- * Check we didin't inadvertently grow the command struct
- */
-static inline void _nvme_check_size(void)
-{
-	BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE);
-	BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE);
-	BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
-	BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
-	BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
-}
-
 static unsigned int max_io_queues(void)
 {
 	return num_possible_cpus() + write_queues + poll_queues;
@@ -830,6 +810,7 @@ static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev,
 		return BLK_STS_RESOURCE;
 	iod->dma_len = bv->bv_len;
 
+	cmnd->flags = NVME_CMD_SGL_METABUF;
 	cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma);
 	cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len);
 	cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4;
@@ -1276,6 +1257,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
 	struct nvme_command cmd;
+	bool shutdown = false;
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 
 	/* If PCI error recovery process is happening, we cannot reset or
@@ -1312,12 +1294,14 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	 * shutdown, so we return BLK_EH_DONE.
 	 */
 	switch (dev->ctrl.state) {
+	case NVME_CTRL_DELETING:
+		shutdown = true;
 	case NVME_CTRL_CONNECTING:
 	case NVME_CTRL_RESETTING:
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, false);
+		nvme_dev_disable(dev, shutdown);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
 	default:
@@ -2433,8 +2417,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown)
 	 * must flush all entered requests to their failed completion to avoid
 	 * deadlocking blk-mq hot-cpu notifier.
 	 */
-	if (shutdown)
+	if (shutdown) {
 		nvme_start_queues(&dev->ctrl);
+		if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q))
+			blk_mq_unquiesce_queue(dev->ctrl.admin_q);
+	}
 	mutex_unlock(&dev->shutdown_lock);
 }
 
@@ -2974,6 +2961,9 @@ static struct pci_driver nvme_driver = {
 
 static int __init nvme_init(void)
 {
+	BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
+	BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
 	BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2);
 	return pci_register_driver(&nvme_driver);
 }
@@ -2982,7 +2972,6 @@ static void __exit nvme_exit(void)
 {
 	pci_unregister_driver(&nvme_driver);
 	flush_workqueue(nvme_wq);
-	_nvme_check_size();
 }
 
 MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");

drivers/nvme/host/tcp.c

@@ -1423,6 +1423,7 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx)
 	if (!ret) {
 		set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags);
 	} else {
+		if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags))
 			__nvme_tcp_stop_queue(&ctrl->queues[idx]);
 		dev_err(nctrl->device,
 			"failed to connect queue: %d ret=%d\n", idx, ret);

drivers/nvme/target/discovery.c

@@ -30,14 +30,17 @@ void nvmet_port_disc_changed(struct nvmet_port *port,
 {
 	struct nvmet_ctrl *ctrl;
 
+	lockdep_assert_held(&nvmet_config_sem);
 	nvmet_genctr++;
 
+	mutex_lock(&nvmet_disc_subsys->lock);
 	list_for_each_entry(ctrl, &nvmet_disc_subsys->ctrls, subsys_entry) {
 		if (subsys && !nvmet_host_allowed(subsys, ctrl->hostnqn))
 			continue;
 
 		__nvmet_disc_changed(port, ctrl);
 	}
+	mutex_unlock(&nvmet_disc_subsys->lock);
 }
 
 static void __nvmet_subsys_disc_changed(struct nvmet_port *port,
@@ -46,12 +49,14 @@ static void __nvmet_subsys_disc_changed(struct nvmet_port *port,
 {
 	struct nvmet_ctrl *ctrl;
 
+	mutex_lock(&nvmet_disc_subsys->lock);
 	list_for_each_entry(ctrl, &nvmet_disc_subsys->ctrls, subsys_entry) {
 		if (host && strcmp(nvmet_host_name(host), ctrl->hostnqn))
 			continue;
 
 		__nvmet_disc_changed(port, ctrl);
 	}
+	mutex_unlock(&nvmet_disc_subsys->lock);
 }
 
 void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,