Merge tag 'nvme-5.10-2020-09-27' of git://git.infradead.org/nvme into for-5.10/drivers

Pull NVMe updates from Christoph:

"nvme updates for 5.10

 - fix keep alive timer modification (Amit Engel)
 - order the PCI ID list more sensibly (Andy Shevchenko)
 - cleanup the open by controller helper (Chaitanya Kulkarni)
 - use an xarray for th CSE log lookup (Chaitanya Kulkarni)
 - support ZNS in nvmet passthrough mode (Chaitanya Kulkarni)
 - fix nvme_ns_report_zones (me)
 - add a sanity check to nvmet-fc (James Smart)
 - fix interrupt allocation when too many polled queues are specified
   (Jeffle Xu)
 - small nvmet-tcp optimization (Mark Wunderlich)"

* tag 'nvme-5.10-2020-09-27' of git://git.infradead.org/nvme:
  nvme-pci: allocate separate interrupt for the reserved non-polled I/O queue
  nvme: fix error handling in nvme_ns_report_zones
  nvmet-fc: fix missing check for no hostport struct
  nvmet: add passthru ZNS support
  nvmet: handle keep-alive timer when kato is modified by a set features cmd
  nvmet-tcp: have queue io_work context run on sock incoming cpu
  nvme-pci: Move enumeration by class to be last in the table
  nvme: use an xarray to lookup the Commands Supported and Effects log
  nvme: lift the file open code from nvme_ctrl_get_by_path

drivers/nvme/host/core.c

@@ -3025,26 +3025,10 @@ int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, u8 csi,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static struct nvme_cel *nvme_find_cel(struct nvme_ctrl *ctrl, u8 csi)
-{
-	struct nvme_cel *cel, *ret = NULL;
-
-	spin_lock_irq(&ctrl->lock);
-	list_for_each_entry(cel, &ctrl->cels, entry) {
-		if (cel->csi == csi) {
-			ret = cel;
-			break;
-		}
-	}
-	spin_unlock_irq(&ctrl->lock);
-
-	return ret;
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 				struct nvme_effects_log **log)
 {
-	struct nvme_cel *cel = nvme_find_cel(ctrl, csi);
+	struct nvme_cel *cel = xa_load(&ctrl->cels, csi);
 	int ret;
 
 	if (cel)
@@ -3062,10 +3046,7 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl, u8 csi,
 	}
 
 	cel->csi = csi;
-
-	spin_lock_irq(&ctrl->lock);
-	list_add_tail(&cel->entry, &ctrl->cels);
-	spin_unlock_irq(&ctrl->lock);
+	xa_store(&ctrl->cels, cel->csi, cel, GFP_KERNEL);
 out:
 	*log = &cel->log;
 	return 0;
@@ -4448,15 +4429,11 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_ctrl *ctrl =
 		container_of(dev, struct nvme_ctrl, ctrl_device);
 	struct nvme_subsystem *subsys = ctrl->subsys;
-	struct nvme_cel *cel, *next;
 
 	if (!subsys || ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
-	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
-		list_del(&cel->entry);
-		kfree(cel);
-	}
+	xa_destroy(&ctrl->cels);
 
 	nvme_mpath_uninit(ctrl);
 	__free_page(ctrl->discard_page);
@@ -4488,7 +4465,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
 	INIT_LIST_HEAD(&ctrl->namespaces);
-	INIT_LIST_HEAD(&ctrl->cels);
+	xa_init(&ctrl->cels);
 	init_rwsem(&ctrl->namespaces_rwsem);
 	ctrl->dev = dev;
 	ctrl->ops = ops;
@@ -4668,28 +4645,13 @@ void nvme_sync_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_sync_queues);
 
-struct nvme_ctrl *nvme_ctrl_get_by_path(const char *path)
+struct nvme_ctrl *nvme_ctrl_from_file(struct file *file)
 {
-	struct nvme_ctrl *ctrl;
-	struct file *f;
-
-	f = filp_open(path, O_RDWR, 0);
-	if (IS_ERR(f))
-		return ERR_CAST(f);
-
-	if (f->f_op != &nvme_dev_fops) {
-		ctrl = ERR_PTR(-EINVAL);
-		goto out_close;
-	}
-
-	ctrl = f->private_data;
-	nvme_get_ctrl(ctrl);
-
-out_close:
-	filp_close(f, NULL);
-	return ctrl;
+	if (file->f_op != &nvme_dev_fops)
+		return NULL;
+	return file->private_data;
 }
-EXPORT_SYMBOL_NS_GPL(nvme_ctrl_get_by_path, NVME_TARGET_PASSTHRU);
+EXPORT_SYMBOL_NS_GPL(nvme_ctrl_from_file, NVME_TARGET_PASSTHRU);
 
 /*
  * Check we didn't inadvertently grow the command structure sizes:

drivers/nvme/host/nvme.h

@@ -300,7 +300,7 @@ struct nvme_ctrl {
 	unsigned long quirks;
 	struct nvme_id_power_state psd[32];
 	struct nvme_effects_log *effects;
-	struct list_head cels;
+	struct xarray cels;
 	struct work_struct scan_work;
 	struct work_struct async_event_work;
 	struct delayed_work ka_work;
@@ -822,7 +822,7 @@ static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { }
 u32 nvme_command_effects(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 			 u8 opcode);
 void nvme_execute_passthru_rq(struct request *rq);
-struct nvme_ctrl *nvme_ctrl_get_by_path(const char *path);
+struct nvme_ctrl *nvme_ctrl_from_file(struct file *file);
 struct nvme_ns *nvme_find_get_ns(struct nvme_ctrl *ctrl, unsigned nsid);
 void nvme_put_ns(struct nvme_ns *ns);
 

drivers/nvme/host/pci.c

@@ -2038,32 +2038,30 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.calc_sets	= nvme_calc_irq_sets,
 		.priv		= dev,
 	};
-	unsigned int irq_queues, this_p_queues;
+	unsigned int irq_queues, poll_queues;
 
 	/*
-	 * Poll queues don't need interrupts, but we need at least one IO
-	 * queue left over for non-polled IO.
+	 * Poll queues don't need interrupts, but we need at least one I/O queue
+	 * left over for non-polled I/O.
 	 */
-	this_p_queues = dev->nr_poll_queues;
-	if (this_p_queues >= nr_io_queues) {
-		this_p_queues = nr_io_queues - 1;
-		irq_queues = 1;
-	} else {
-		irq_queues = nr_io_queues - this_p_queues + 1;
-	}
-	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
+	poll_queues = min(dev->nr_poll_queues, nr_io_queues - 1);
+	dev->io_queues[HCTX_TYPE_POLL] = poll_queues;
 
-	/* Initialize for the single interrupt case */
+	/*
+	 * Initialize for the single interrupt case, will be updated in
+	 * nvme_calc_irq_sets().
+	 */
 	dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
 	dev->io_queues[HCTX_TYPE_READ] = 0;
 
 	/*
-	 * Some Apple controllers require all queues to use the
-	 * first vector.
+	 * We need interrupts for the admin queue and each non-polled I/O queue,
+	 * but some Apple controllers require all queues to use the first
+	 * vector.
 	 */
-	if (dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR)
-		irq_queues = 1;
-
+	irq_queues = 1;
+	if (!(dev->ctrl.quirks & NVME_QUIRK_SINGLE_VECTOR))
+		irq_queues += (nr_io_queues - poll_queues);
 	return pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
 			      PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
 }
@@ -3187,7 +3185,6 @@ static const struct pci_device_id nvme_id_table[] = {
 				NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE(0x1c5c, 0x1504),   /* SK Hynix PC400 */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
-	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
@@ -3195,6 +3192,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_SINGLE_VECTOR |
 				NVME_QUIRK_128_BYTES_SQES |
 				NVME_QUIRK_SHARED_TAGS },
+
+	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, nvme_id_table);

drivers/nvme/host/zns.c

@@ -133,28 +133,6 @@ static void *nvme_zns_alloc_report_buffer(struct nvme_ns *ns,
 	return NULL;
 }
 
-static int __nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
-				  struct nvme_zone_report *report,
-				  size_t buflen)
-{
-	struct nvme_command c = { };
-	int ret;
-
-	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
-	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
-	c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
-	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
-	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
-	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
-	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
-
-	ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
-	if (ret)
-		return ret;
-
-	return le64_to_cpu(report->nr_zones);
-}
-
 static int nvme_zone_parse_entry(struct nvme_ns *ns,
 				 struct nvme_zone_descriptor *entry,
 				 unsigned int idx, report_zones_cb cb,
@@ -182,6 +160,7 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 			unsigned int nr_zones, report_zones_cb cb, void *data)
 {
 	struct nvme_zone_report *report;
+	struct nvme_command c = { };
 	int ret, zone_idx = 0;
 	unsigned int nz, i;
 	size_t buflen;
@@ -190,14 +169,26 @@ static int nvme_ns_report_zones(struct nvme_ns *ns, sector_t sector,
 	if (!report)
 		return -ENOMEM;
 
+	c.zmr.opcode = nvme_cmd_zone_mgmt_recv;
+	c.zmr.nsid = cpu_to_le32(ns->head->ns_id);
+	c.zmr.numd = cpu_to_le32(nvme_bytes_to_numd(buflen));
+	c.zmr.zra = NVME_ZRA_ZONE_REPORT;
+	c.zmr.zrasf = NVME_ZRASF_ZONE_REPORT_ALL;
+	c.zmr.pr = NVME_REPORT_ZONE_PARTIAL;
+
 	sector &= ~(ns->zsze - 1);
 	while (zone_idx < nr_zones && sector < get_capacity(ns->disk)) {
 		memset(report, 0, buflen);
-		ret = __nvme_ns_report_zones(ns, sector, report, buflen);
-		if (ret < 0)
+
+		c.zmr.slba = cpu_to_le64(nvme_sect_to_lba(ns, sector));
+		ret = nvme_submit_sync_cmd(ns->queue, &c, report, buflen);
+		if (ret) {
+			if (ret > 0)
+				ret = -EIO;
 			goto out_free;
+		}
 
-		nz = min_t(unsigned int, ret, nr_zones);
+		nz = min((unsigned int)le64_to_cpu(report->nr_zones), nr_zones);
 		if (!nz)
 			break;
 

drivers/nvme/target/admin-cmd.c

@@ -727,7 +727,9 @@ u16 nvmet_set_feat_kato(struct nvmet_req *req)
 {
 	u32 val32 = le32_to_cpu(req->cmd->common.cdw11);
 
+	nvmet_stop_keep_alive_timer(req->sq->ctrl);
 	req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
+	nvmet_start_keep_alive_timer(req->sq->ctrl);
 
 	nvmet_set_result(req, req->sq->ctrl->kato);
 

drivers/nvme/target/core.c

@@ -395,7 +395,7 @@ static void nvmet_keep_alive_timer(struct work_struct *work)
 	nvmet_ctrl_fatal_error(ctrl);
 }
 
-static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
+void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
 	if (unlikely(ctrl->kato == 0))
 		return;
@@ -407,7 +407,7 @@ static void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl)
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
-static void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
+void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl)
 {
 	if (unlikely(ctrl->kato == 0))
 		return;

drivers/nvme/target/fc.c

@@ -1019,7 +1019,7 @@ static void
 nvmet_fc_free_hostport(struct nvmet_fc_hostport *hostport)
 {
 	/* if LLDD not implemented, leave as NULL */
-	if (!hostport->hosthandle)
+	if (!hostport || !hostport->hosthandle)
 		return;
 
 	nvmet_fc_hostport_put(hostport);

drivers/nvme/target/nvmet.h

@@ -395,6 +395,8 @@ void nvmet_get_feat_async_event(struct nvmet_req *req);
 u16 nvmet_set_feat_kato(struct nvmet_req *req);
 u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask);
 void nvmet_execute_async_event(struct nvmet_req *req);
+void nvmet_start_keep_alive_timer(struct nvmet_ctrl *ctrl);
+void nvmet_stop_keep_alive_timer(struct nvmet_ctrl *ctrl);
 
 u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
 void nvmet_bdev_set_limits(struct block_device *bdev, struct nvme_id_ns *id);

drivers/nvme/target/passthru.c

@@ -456,10 +456,26 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 			req->execute = nvmet_passthru_execute_cmd;
 			req->p.use_workqueue = true;
 			return NVME_SC_SUCCESS;
+		case NVME_ID_CNS_CS_CTRL:
+			switch (req->cmd->identify.csi) {
+			case NVME_CSI_ZNS:
+				req->execute = nvmet_passthru_execute_cmd;
+				req->p.use_workqueue = true;
+				return NVME_SC_SUCCESS;
+			}
+			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		case NVME_ID_CNS_NS:
 			req->execute = nvmet_passthru_execute_cmd;
 			req->p.use_workqueue = true;
 			return NVME_SC_SUCCESS;
+		case NVME_ID_CNS_CS_NS:
+			switch (req->cmd->identify.csi) {
+			case NVME_CSI_ZNS:
+				req->execute = nvmet_passthru_execute_cmd;
+				req->p.use_workqueue = true;
+				return NVME_SC_SUCCESS;
+			}
+			return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
 		default:
 			return nvmet_setup_passthru_command(req);
 		}
@@ -474,6 +490,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 {
 	struct nvme_ctrl *ctrl;
+	struct file *file;
 	int ret = -EINVAL;
 	void *old;
 
@@ -488,24 +505,29 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 		goto out_unlock;
 	}
 
-	ctrl = nvme_ctrl_get_by_path(subsys->passthru_ctrl_path);
-	if (IS_ERR(ctrl)) {
-		ret = PTR_ERR(ctrl);
+	file = filp_open(subsys->passthru_ctrl_path, O_RDWR, 0);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto out_unlock;
+	}
+
+	ctrl = nvme_ctrl_from_file(file);
+	if (!ctrl) {
 		pr_err("failed to open nvme controller %s\n",
 		       subsys->passthru_ctrl_path);
 
-		goto out_unlock;
+		goto out_put_file;
 	}
 
 	old = xa_cmpxchg(&passthru_subsystems, ctrl->cntlid, NULL,
 			 subsys, GFP_KERNEL);
 	if (xa_is_err(old)) {
 		ret = xa_err(old);
-		goto out_put_ctrl;
+		goto out_put_file;
 	}
 
 	if (old)
-		goto out_put_ctrl;
+		goto out_put_file;
 
 	subsys->passthru_ctrl = ctrl;
 	subsys->ver = ctrl->vs;
@@ -516,13 +538,12 @@ int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys)
 			NVME_TERTIARY(subsys->ver));
 		subsys->ver = NVME_VS(1, 2, 1);
 	}
-
+	nvme_get_ctrl(ctrl);
 	__module_get(subsys->passthru_ctrl->ops->module);
-	mutex_unlock(&subsys->lock);
-	return 0;
+	ret = 0;
 
-out_put_ctrl:
-	nvme_put_ctrl(ctrl);
+out_put_file:
+	filp_close(file, NULL);
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;

drivers/nvme/target/tcp.c

@@ -94,7 +94,6 @@ struct nvmet_tcp_queue {
 	struct socket		*sock;
 	struct nvmet_tcp_port	*port;
 	struct work_struct	io_work;
-	int			cpu;
 	struct nvmet_cq		nvme_cq;
 	struct nvmet_sq		nvme_sq;
 
@@ -144,7 +143,6 @@ struct nvmet_tcp_port {
 	struct work_struct	accept_work;
 	struct nvmet_port	*nport;
 	struct sockaddr_storage addr;
-	int			last_cpu;
 	void (*data_ready)(struct sock *);
 };
 
@@ -219,6 +217,11 @@ static inline void nvmet_tcp_put_cmd(struct nvmet_tcp_cmd *cmd)
 	list_add_tail(&cmd->entry, &cmd->queue->free_list);
 }
 
+static inline int queue_cpu(struct nvmet_tcp_queue *queue)
+{
+	return queue->sock->sk->sk_incoming_cpu;
+}
+
 static inline u8 nvmet_tcp_hdgst_len(struct nvmet_tcp_queue *queue)
 {
 	return queue->hdr_digest ? NVME_TCP_DIGEST_LENGTH : 0;
@@ -506,7 +509,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 	struct nvmet_tcp_queue	*queue = cmd->queue;
 
 	llist_add(&cmd->lentry, &queue->resp_list);
-	queue_work_on(cmd->queue->cpu, nvmet_tcp_wq, &cmd->queue->io_work);
+	queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &cmd->queue->io_work);
 }
 
 static int nvmet_try_send_data_pdu(struct nvmet_tcp_cmd *cmd)
@@ -1223,7 +1226,7 @@ static void nvmet_tcp_io_work(struct work_struct *w)
 	 * We exahusted our budget, requeue our selves
 	 */
 	if (pending)
-		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 }
 
 static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
@@ -1383,7 +1386,7 @@ static void nvmet_tcp_data_ready(struct sock *sk)
 	read_lock_bh(&sk->sk_callback_lock);
 	queue = sk->sk_user_data;
 	if (likely(queue))
-		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
@@ -1403,7 +1406,7 @@ static void nvmet_tcp_write_space(struct sock *sk)
 
 	if (sk_stream_is_writeable(sk)) {
 		clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-		queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+		queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 	}
 out:
 	read_unlock_bh(&sk->sk_callback_lock);
@@ -1512,9 +1515,6 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	if (ret)
 		goto out_free_connect;
 
-	port->last_cpu = cpumask_next_wrap(port->last_cpu,
-				cpu_online_mask, -1, false);
-	queue->cpu = port->last_cpu;
 	nvmet_prepare_receive_pdu(queue);
 
 	mutex_lock(&nvmet_tcp_queue_mutex);
@@ -1525,7 +1525,7 @@ static int nvmet_tcp_alloc_queue(struct nvmet_tcp_port *port,
 	if (ret)
 		goto out_destroy_sq;
 
-	queue_work_on(queue->cpu, nvmet_tcp_wq, &queue->io_work);
+	queue_work_on(queue_cpu(queue), nvmet_tcp_wq, &queue->io_work);
 
 	return 0;
 out_destroy_sq:
@@ -1612,7 +1612,6 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport)
 	}
 
 	port->nport = nport;
-	port->last_cpu = -1;
 	INIT_WORK(&port->accept_work, nvmet_tcp_accept_work);
 	if (port->nport->inline_data_size < 0)
 		port->nport->inline_data_size = NVMET_TCP_DEF_INLINE_DATA_SIZE;