Merge tag 'for-5.16/drivers-2021-10-29' of git://git.kernel.dk/linux-block

Pull block driver updates from Jens Axboe:

 - paride driver cleanups (Christoph)

 - Remove cryptoloop support (Christoph)

 - null_blk poll support (me)

 - Now that add_disk() supports proper error handling, add it to various
   drivers (Luis)

 - Make ataflop actually work again (Michael)

 - s390 dasd fixes (Stefan, Heiko)

 - nbd fixes (Yu, Ye)

 - Remove redundant wq flush in mtip32xx (Christophe)

 - NVMe updates
      - fix a multipath partition scanning deadlock (Hannes Reinecke)
      - generate uevent once a multipath namespace is operational again
        (Hannes Reinecke)
      - support unique discovery controller NQNs (Hannes Reinecke)
      - fix use-after-free when a port is removed (Israel Rukshin)
      - clear shadow doorbell memory on resets (Keith Busch)
      - use struct_size (Len Baker)
      - add error handling support for add_disk (Luis Chamberlain)
      - limit the maximal queue size for RDMA controllers (Max Gurtovoy)
      - use a few more symbolic names (Max Gurtovoy)
      - fix error code in nvme_rdma_setup_ctrl (Max Gurtovoy)
      - add support for ->map_queues on FC (Saurav Kashyap)
      - support the current discovery subsystem entry (Hannes Reinecke)
      - use flex_array_size and struct_size (Len Baker)

 - bcache fixes (Christoph, Coly, Chao, Lin, Qing)

 - MD updates (Christoph, Guoqing, Xiao)

 - Misc fixes (Dan, Ding, Jiapeng, Shin'ichiro, Ye)

* tag 'for-5.16/drivers-2021-10-29' of git://git.kernel.dk/linux-block: (117 commits)
  null_blk: Fix handling of submit_queues and poll_queues attributes
  block: ataflop: Fix warning comparing pointer to 0
  bcache: replace snprintf in show functions with sysfs_emit
  bcache: move uapi header bcache.h to bcache code directory
  nvmet: use flex_array_size and struct_size
  nvmet: register discovery subsystem as 'current'
  nvmet: switch check for subsystem type
  nvme: add new discovery log page entry definitions
  block: ataflop: more blk-mq refactoring fixes
  block: remove support for cryptoloop and the xor transfer
  mtd: add add_disk() error handling
  rnbd: add error handling support for add_disk()
  um/drivers/ubd_kern: add error handling support for add_disk()
  m68k/emu/nfblock: add error handling support for add_disk()
  xen-blkfront: add error handling support for add_disk()
  bcache: add error handling support for add_disk()
  dm: add add_disk() error handling
  block: aoe: fixup coccinelle warnings
  nvmet: use struct_size over open coded arithmetic
  nvme: drop scan_lock and always kick requeue list when removing namespaces
  ...

8 files changed, 131 insertions, 20 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index aa6d84d8848e..6fb24746de06 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -264,7 +264,7 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
 	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
 	desc->state = req->port->ana_state[grpid];
 	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
-	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+	return struct_size(desc, nsids, count);
 }
 
 static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
@@ -278,8 +278,8 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
 	u16 status;
 
 	status = NVME_SC_INTERNAL;
-	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
-			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+	desc = kmalloc(struct_size(desc, nsids, NVMET_MAX_NAMESPACES),
+		       GFP_KERNEL);
 	if (!desc)
 		goto out;
 
@@ -374,13 +374,19 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	id->rab = 6;
 
+	if (nvmet_is_disc_subsys(ctrl->subsys))
+		id->cntrltype = NVME_CTRL_DISC;
+	else
+		id->cntrltype = NVME_CTRL_IO;
+
 	/*
 	 * XXX: figure out how we can assign a IEEE OUI, but until then
 	 * the safest is to leave it as zeroes.
 	 */
 
 	/* we support multiple ports, multiples hosts and ANA: */
-	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
+	id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL |
+		NVME_CTRL_CMIC_ANA;
 
 	/* Limit MDTS according to transport capability */
 	if (ctrl->ops->get_mdts)
@@ -536,7 +542,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * Our namespace might always be shared.  Not just with other
 	 * controllers, but also with any other user of the block device.
 	 */
-	id->nmic = (1 << 0);
+	id->nmic = NVME_NS_NMIC_SHARED;
 	id->anagrpid = cpu_to_le32(req->ns->anagrpid);
 
 	memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid));
@@ -1008,7 +1014,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 	if (nvme_is_fabrics(cmd))
 		return nvmet_parse_fabrics_cmd(req);
-	if (nvmet_req_subsys(req)->type == NVME_NQN_DISC)
+	if (nvmet_is_disc_subsys(nvmet_req_subsys(req)))
 		return nvmet_parse_discovery_cmd(req);
 
 	ret = nvmet_check_ctrl_status(req);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index be5d82421e3a..091a0ca16361 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -1233,6 +1233,44 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item,
 }
 CONFIGFS_ATTR(nvmet_subsys_, attr_model);
 
+static ssize_t nvmet_subsys_attr_discovery_nqn_show(struct config_item *item,
+			char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%s\n",
+			nvmet_disc_subsys->subsysnqn);
+}
+
+static ssize_t nvmet_subsys_attr_discovery_nqn_store(struct config_item *item,
+			const char *page, size_t count)
+{
+	struct nvmet_subsys *subsys = to_subsys(item);
+	char *subsysnqn;
+	int len;
+
+	len = strcspn(page, "\n");
+	if (!len)
+		return -EINVAL;
+
+	subsysnqn = kmemdup_nul(page, len, GFP_KERNEL);
+	if (!subsysnqn)
+		return -ENOMEM;
+
+	/*
+	 * The discovery NQN must be different from subsystem NQN.
+	 */
+	if (!strcmp(subsysnqn, subsys->subsysnqn)) {
+		kfree(subsysnqn);
+		return -EBUSY;
+	}
+	down_write(&nvmet_config_sem);
+	kfree(nvmet_disc_subsys->subsysnqn);
+	nvmet_disc_subsys->subsysnqn = subsysnqn;
+	up_write(&nvmet_config_sem);
+
+	return count;
+}
+CONFIGFS_ATTR(nvmet_subsys_, attr_discovery_nqn);
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 static ssize_t nvmet_subsys_attr_pi_enable_show(struct config_item *item,
 						char *page)
@@ -1262,6 +1300,7 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = {
 	&nvmet_subsys_attr_attr_cntlid_min,
 	&nvmet_subsys_attr_attr_cntlid_max,
 	&nvmet_subsys_attr_attr_model,
+	&nvmet_subsys_attr_attr_discovery_nqn,
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	&nvmet_subsys_attr_attr_pi_enable,
 #endif
@@ -1553,6 +1592,8 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	/* Let inflight controllers teardown complete */
+	flush_scheduled_work();
 	list_del(&port->global_entry);
 
 	kfree(port->ana_state);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index b8425fa34300..5119c687de68 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -1140,7 +1140,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl)
 	 * should verify iosqes,iocqes are zeroed, however that
 	 * would break backwards compatibility, so don't enforce it.
 	 */
-	if (ctrl->subsys->type != NVME_NQN_DISC &&
+	if (!nvmet_is_disc_subsys(ctrl->subsys) &&
 	    (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES ||
 	     nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) {
 		ctrl->csts = NVME_CSTS_CFS;
@@ -1205,7 +1205,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl)
 	/* CC.EN timeout in 500msec units: */
 	ctrl->cap |= (15ULL << 24);
 	/* maximum queue entries supported: */
-	ctrl->cap |= NVMET_QUEUE_SIZE - 1;
+	if (ctrl->ops->get_max_queue_size)
+		ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1;
+	else
+		ctrl->cap |= NVMET_QUEUE_SIZE - 1;
 
 	if (nvmet_is_passthru_subsys(ctrl->subsys))
 		nvmet_passthrough_override_cap(ctrl);
@@ -1278,7 +1281,7 @@ bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn)
 	if (subsys->allow_any_host)
 		return true;
 
-	if (subsys->type == NVME_NQN_DISC) /* allow all access to disc subsys */
+	if (nvmet_is_disc_subsys(subsys)) /* allow all access to disc subsys */
 		return true;
 
 	list_for_each_entry(p, &subsys->hosts, entry) {
@@ -1367,6 +1370,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	mutex_init(&ctrl->lock);
 
 	ctrl->port = req->port;
+	ctrl->ops = req->ops;
 
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
@@ -1405,13 +1409,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	}
 	ctrl->cntlid = ret;
 
-	ctrl->ops = req->ops;
-
 	/*
 	 * Discovery controllers may use some arbitrary high value
 	 * in order to cleanup stale discovery sessions
 	 */
-	if ((ctrl->subsys->type == NVME_NQN_DISC) && !kato)
+	if (nvmet_is_disc_subsys(ctrl->subsys) && !kato)
 		kato = NVMET_DISC_KATO_MS;
 
 	/* keep-alive timeout in seconds */
@@ -1491,7 +1493,8 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 	if (!port)
 		return NULL;
 
-	if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn)) {
+	if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn) ||
+	    !strcmp(nvmet_disc_subsys->subsysnqn, subsysnqn)) {
 		if (!kref_get_unless_zero(&nvmet_disc_subsys->ref))
 			return NULL;
 		return nvmet_disc_subsys;
@@ -1538,6 +1541,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
 		subsys->max_qid = NVMET_NR_QUEUES;
 		break;
 	case NVME_NQN_DISC:
+	case NVME_NQN_CURR:
 		subsys->max_qid = 0;
 		break;
 	default:
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 7aa62bc6ae84..c2162eef8ce1 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -146,7 +146,7 @@ static size_t discovery_log_entries(struct nvmet_req *req)
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvmet_subsys_link *p;
 	struct nvmet_port *r;
-	size_t entries = 0;
+	size_t entries = 1;
 
 	list_for_each_entry(p, &req->port->subsystems, entry) {
 		if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
@@ -171,6 +171,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
 	u32 numrec = 0;
 	u16 status = 0;
 	void *buffer;
+	char traddr[NVMF_TRADDR_SIZE];
 
 	if (!nvmet_check_transfer_len(req, data_len))
 		return;
@@ -203,15 +204,19 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
 		status = NVME_SC_INTERNAL;
 		goto out;
 	}
-
 	hdr = buffer;
-	list_for_each_entry(p, &req->port->subsystems, entry) {
-		char traddr[NVMF_TRADDR_SIZE];
 
+	nvmet_set_disc_traddr(req, req->port, traddr);
+
+	nvmet_format_discovery_entry(hdr, req->port,
+				     nvmet_disc_subsys->subsysnqn,
+				     traddr, NVME_NQN_CURR, numrec);
+	numrec++;
+
+	list_for_each_entry(p, &req->port->subsystems, entry) {
 		if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn))
 			continue;
 
-		nvmet_set_disc_traddr(req, req->port, traddr);
 		nvmet_format_discovery_entry(hdr, req->port,
 				p->subsys->subsysnqn, traddr,
 				NVME_NQN_NVME, numrec);
@@ -268,6 +273,8 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
 	memcpy_and_pad(id->fr, sizeof(id->fr),
 		       UTS_RELEASE, strlen(UTS_RELEASE), ' ');
 
+	id->cntrltype = NVME_CTRL_DISC;
+
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
 	id->cntlid = cpu_to_le16(ctrl->cntlid);
@@ -387,7 +394,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
 int __init nvmet_init_discovery(void)
 {
 	nvmet_disc_subsys =
-		nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC);
+		nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_CURR);
 	return PTR_ERR_OR_ZERO(nvmet_disc_subsys);
 }
 
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 7d0454cee920..70fb587e9413 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -221,7 +221,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
 		goto out;
 	}
 
-	pr_info("creating controller %d for subsystem %s for NQN %s%s.\n",
+	pr_info("creating %s controller %d for subsystem %s for NQN %s%s.\n",
+		nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm",
 		ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn,
 		ctrl->pi_support ? " T10-PI is enabled" : "");
 	req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 7143c7fa7464..af193423c10b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -309,6 +309,7 @@ struct nvmet_fabrics_ops {
 	u16 (*install_queue)(struct nvmet_sq *nvme_sq);
 	void (*discovery_chg)(struct nvmet_port *port);
 	u8 (*get_mdts)(const struct nvmet_ctrl *ctrl);
+	u16 (*get_max_queue_size)(const struct nvmet_ctrl *ctrl);
 };
 
 #define NVMET_MAX_INLINE_BIOVEC	8
@@ -576,6 +577,11 @@ static inline struct nvmet_subsys *nvmet_req_subsys(struct nvmet_req *req)
 	return req->sq->ctrl->subsys;
 }
 
+static inline bool nvmet_is_disc_subsys(struct nvmet_subsys *subsys)
+{
+    return subsys->type != NVME_NQN_NVME;
+}
+
 #ifdef CONFIG_NVME_TARGET_PASSTHRU
 void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys);
 int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 38d1f292ecc2..1deb4043e242 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1819,12 +1819,36 @@ restart:
 	mutex_unlock(&nvmet_rdma_queue_mutex);
 }
 
+static void nvmet_rdma_destroy_port_queues(struct nvmet_rdma_port *port)
+{
+	struct nvmet_rdma_queue *queue, *tmp;
+	struct nvmet_port *nport = port->nport;
+
+	mutex_lock(&nvmet_rdma_queue_mutex);
+	list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list,
+				 queue_list) {
+		if (queue->port != nport)
+			continue;
+
+		list_del_init(&queue->queue_list);
+		__nvmet_rdma_queue_disconnect(queue);
+	}
+	mutex_unlock(&nvmet_rdma_queue_mutex);
+}
+
 static void nvmet_rdma_disable_port(struct nvmet_rdma_port *port)
 {
 	struct rdma_cm_id *cm_id = xchg(&port->cm_id, NULL);
 
 	if (cm_id)
 		rdma_destroy_id(cm_id);
+
+	/*
+	 * Destroy the remaining queues, which are not belong to any
+	 * controller yet. Do it here after the RDMA-CM was destroyed
+	 * guarantees that no new queue will be created.
+	 */
+	nvmet_rdma_destroy_port_queues(port);
 }
 
 static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port)
@@ -1976,6 +2000,11 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl)
 	return NVMET_RDMA_MAX_MDTS;
 }
 
+static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl)
+{
+	return NVME_RDMA_MAX_QUEUE_SIZE;
+}
+
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
@@ -1987,6 +2016,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.delete_ctrl		= nvmet_rdma_delete_ctrl,
 	.disc_traddr		= nvmet_rdma_disc_port_addr,
 	.get_mdts		= nvmet_rdma_get_mdts,
+	.get_max_queue_size	= nvmet_rdma_get_max_queue_size,
 };
 
 static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 46c3b3be7e03..84c387e4bf43 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1740,6 +1740,17 @@ err_port:
 	return ret;
 }
 
+static void nvmet_tcp_destroy_port_queues(struct nvmet_tcp_port *port)
+{
+	struct nvmet_tcp_queue *queue;
+
+	mutex_lock(&nvmet_tcp_queue_mutex);
+	list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list)
+		if (queue->port == port)
+			kernel_sock_shutdown(queue->sock, SHUT_RDWR);
+	mutex_unlock(&nvmet_tcp_queue_mutex);
+}
+
 static void nvmet_tcp_remove_port(struct nvmet_port *nport)
 {
 	struct nvmet_tcp_port *port = nport->priv;
@@ -1749,6 +1760,11 @@ static void nvmet_tcp_remove_port(struct nvmet_port *nport)
 	port->sock->sk->sk_user_data = NULL;
 	write_unlock_bh(&port->sock->sk->sk_callback_lock);
 	cancel_work_sync(&port->accept_work);
+	/*
+	 * Destroy the remaining queues, which are not belong to any
+	 * controller yet.
+	 */
+	nvmet_tcp_destroy_port_queues(port);
 
 	sock_release(port->sock);
 	kfree(port);