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
  ...

10 files changed, 128 insertions, 19 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index eb284f45fc44..838b5e2058be 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -203,7 +203,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl)
 {
 	dev_info(ctrl->device,
-		 "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn);
+		 "Removing ctrl: NQN \"%s\"\n", nvmf_ctrl_subsysnqn(ctrl));
 
 	flush_work(&ctrl->reset_work);
 	nvme_stop_ctrl(ctrl);
@@ -815,6 +815,7 @@ static void nvme_assign_write_stream(struct nvme_ctrl *ctrl,
 static inline void nvme_setup_flush(struct nvme_ns *ns,
 		struct nvme_command *cmnd)
 {
+	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->common.opcode = nvme_cmd_flush;
 	cmnd->common.nsid = cpu_to_le32(ns->head->ns_id);
 }
@@ -866,6 +867,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 		return BLK_STS_IOERR;
 	}
 
+	memset(cmnd, 0, sizeof(*cmnd));
 	cmnd->dsm.opcode = nvme_cmd_dsm;
 	cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id);
 	cmnd->dsm.nr = cpu_to_le32(segments - 1);
@@ -882,6 +884,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req,
 static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns,
 		struct request *req, struct nvme_command *cmnd)
 {
+	memset(cmnd, 0, sizeof(*cmnd));
+
 	if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
 		return nvme_setup_discard(ns, req, cmnd);
 
@@ -915,9 +919,15 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
 
 	cmnd->rw.opcode = op;
+	cmnd->rw.flags = 0;
 	cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id);
+	cmnd->rw.rsvd2 = 0;
+	cmnd->rw.metadata = 0;
 	cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));
 	cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
+	cmnd->rw.reftag = 0;
+	cmnd->rw.apptag = 0;
+	cmnd->rw.appmask = 0;
 
 	if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams)
 		nvme_assign_write_stream(ctrl, req, &control, &dsmgmt);
@@ -974,10 +984,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req)
 	struct nvme_ctrl *ctrl = nvme_req(req)->ctrl;
 	blk_status_t ret = BLK_STS_OK;
 
-	if (!(req->rq_flags & RQF_DONTPREP)) {
+	if (!(req->rq_flags & RQF_DONTPREP))
 		nvme_clear_nvme_request(req);
-		memset(cmd, 0, sizeof(*cmd));
-	}
 
 	switch (req_op(req)) {
 	case REQ_OP_DRV_IN:
@@ -2593,6 +2601,24 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev,
 }
 static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn);
 
+static ssize_t nvme_subsys_show_type(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct nvme_subsystem *subsys =
+		container_of(dev, struct nvme_subsystem, dev);
+
+	switch (subsys->subtype) {
+	case NVME_NQN_DISC:
+		return sysfs_emit(buf, "discovery\n");
+	case NVME_NQN_NVME:
+		return sysfs_emit(buf, "nvm\n");
+	default:
+		return sysfs_emit(buf, "reserved\n");
+	}
+}
+static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type);
+
 #define nvme_subsys_show_str_function(field)				\
 static ssize_t subsys_##field##_show(struct device *dev,		\
 			    struct device_attribute *attr, char *buf)	\
@@ -2613,6 +2639,7 @@ static struct attribute *nvme_subsys_attrs[] = {
 	&subsys_attr_serial.attr,
 	&subsys_attr_firmware_rev.attr,
 	&subsys_attr_subsysnqn.attr,
+	&subsys_attr_subsystype.attr,
 #ifdef CONFIG_NVME_MULTIPATH
 	&subsys_attr_iopolicy.attr,
 #endif
@@ -2683,6 +2710,21 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev));
 	subsys->vendor_id = le16_to_cpu(id->vid);
 	subsys->cmic = id->cmic;
+
+	/* Versions prior to 1.4 don't necessarily report a valid type */
+	if (id->cntrltype == NVME_CTRL_DISC ||
+	    !strcmp(subsys->subnqn, NVME_DISC_SUBSYS_NAME))
+		subsys->subtype = NVME_NQN_DISC;
+	else
+		subsys->subtype = NVME_NQN_NVME;
+
+	if (nvme_discovery_ctrl(ctrl) && subsys->subtype != NVME_NQN_DISC) {
+		dev_err(ctrl->device,
+			"Subsystem %s is not a discovery controller",
+			subsys->subnqn);
+		kfree(subsys);
+		return -EINVAL;
+	}
 	subsys->awupf = le16_to_cpu(id->awupf);
 #ifdef CONFIG_NVME_MULTIPATH
 	subsys->iopolicy = NVME_IOPOLICY_NUMA;
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 668c6bb7a567..c5a2b71c5268 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -548,6 +548,7 @@ static const match_table_t opt_tokens = {
 	{ NVMF_OPT_NR_POLL_QUEUES,	"nr_poll_queues=%d"	},
 	{ NVMF_OPT_TOS,			"tos=%d"		},
 	{ NVMF_OPT_FAIL_FAST_TMO,	"fast_io_fail_tmo=%d"	},
+	{ NVMF_OPT_DISCOVERY,		"discovery"		},
 	{ NVMF_OPT_ERR,			NULL			}
 };
 
@@ -823,6 +824,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
 			}
 			opts->tos = token;
 			break;
+		case NVMF_OPT_DISCOVERY:
+			opts->discovery_nqn = true;
+			break;
 		default:
 			pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n",
 				p);
@@ -949,7 +953,7 @@ EXPORT_SYMBOL_GPL(nvmf_free_options);
 #define NVMF_ALLOWED_OPTS	(NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \
 				 NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \
 				 NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\
-				 NVMF_OPT_DISABLE_SQFLOW |\
+				 NVMF_OPT_DISABLE_SQFLOW | NVMF_OPT_DISCOVERY |\
 				 NVMF_OPT_FAIL_FAST_TMO)
 
 static struct nvme_ctrl *
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index a146cb903869..c3203ff1c654 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -67,6 +67,7 @@ enum {
 	NVMF_OPT_TOS		= 1 << 19,
 	NVMF_OPT_FAIL_FAST_TMO	= 1 << 20,
 	NVMF_OPT_HOST_IFACE	= 1 << 21,
+	NVMF_OPT_DISCOVERY	= 1 << 22,
 };
 
 /**
@@ -178,6 +179,13 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 	return true;
 }
 
+static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl)
+{
+	if (!ctrl->subsys)
+		return ctrl->opts->subsysnqn;
+	return ctrl->subsys->subnqn;
+}
+
 int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val);
 int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val);
 int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val);
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 580a216da619..71b3108c22f0 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -16,6 +16,7 @@
 #include <linux/nvme-fc.h>
 #include "fc.h"
 #include <scsi/scsi_transport_fc.h>
+#include <linux/blk-mq-pci.h>
 
 /* *************************** Data Structures/Defines ****************** */
 
@@ -2841,6 +2842,28 @@ nvme_fc_complete_rq(struct request *rq)
 	nvme_fc_ctrl_put(ctrl);
 }
 
+static int nvme_fc_map_queues(struct blk_mq_tag_set *set)
+{
+	struct nvme_fc_ctrl *ctrl = set->driver_data;
+	int i;
+
+	for (i = 0; i < set->nr_maps; i++) {
+		struct blk_mq_queue_map *map = &set->map[i];
+
+		if (!map->nr_queues) {
+			WARN_ON(i == HCTX_TYPE_DEFAULT);
+			continue;
+		}
+
+		/* Call LLDD map queue functionality if defined */
+		if (ctrl->lport->ops->map_queues)
+			ctrl->lport->ops->map_queues(&ctrl->lport->localport,
+						     map);
+		else
+			blk_mq_map_queues(map);
+	}
+	return 0;
+}
 
 static const struct blk_mq_ops nvme_fc_mq_ops = {
 	.queue_rq	= nvme_fc_queue_rq,
@@ -2849,6 +2872,7 @@ static const struct blk_mq_ops nvme_fc_mq_ops = {
 	.exit_request	= nvme_fc_exit_request,
 	.init_hctx	= nvme_fc_init_hctx,
 	.timeout	= nvme_fc_timeout,
+	.map_queues	= nvme_fc_map_queues,
 };
 
 static int
@@ -3572,7 +3596,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
 
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: new ctrl: NQN \"%s\"\n",
-		ctrl->cnum, ctrl->ctrl.opts->subsysnqn);
+		ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl));
 
 	return &ctrl->ctrl;
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 11440c86881e..7f2071f2460c 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -105,8 +105,11 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
-		if (ns->head->disk)
-			kblockd_schedule_work(&ns->head->requeue_work);
+		if (!ns->head->disk)
+			continue;
+		kblockd_schedule_work(&ns->head->requeue_work);
+		if (ctrl->state == NVME_CTRL_LIVE)
+			disk_uevent(ns->head->disk, KOBJ_CHANGE);
 	}
 	up_read(&ctrl->namespaces_rwsem);
 }
@@ -143,13 +146,12 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
-	mutex_lock(&ctrl->scan_lock);
 	down_read(&ctrl->namespaces_rwsem);
-	list_for_each_entry(ns, &ctrl->namespaces, list)
-		if (nvme_mpath_clear_current_path(ns))
-			kblockd_schedule_work(&ns->head->requeue_work);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		nvme_mpath_clear_current_path(ns);
+		kblockd_schedule_work(&ns->head->requeue_work);
+	}
 	up_read(&ctrl->namespaces_rwsem);
-	mutex_unlock(&ctrl->scan_lock);
 }
 
 void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
@@ -506,13 +508,23 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
 	struct nvme_ns_head *head = ns->head;
+	int rc;
 
 	if (!head->disk)
 		return;
 
+	/*
+	 * test_and_set_bit() is used because it is protecting against two nvme
+	 * paths simultaneously calling device_add_disk() on the same namespace
+	 * head.
+	 */
 	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
-		device_add_disk(&head->subsys->dev, head->disk,
-				nvme_ns_id_attr_groups);
+		rc = device_add_disk(&head->subsys->dev, head->disk,
+				     nvme_ns_id_attr_groups);
+		if (rc) {
+			clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
+			return;
+		}
 		nvme_add_ns_head_cdev(head);
 	}
 
@@ -550,7 +562,7 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
 			return -EINVAL;
 
 		nr_nsids = le32_to_cpu(desc->nnsids);
-		nsid_buf_size = nr_nsids * sizeof(__le32);
+		nsid_buf_size = flex_array_size(desc, nsids, nr_nsids);
 
 		if (WARN_ON_ONCE(desc->grpid == 0))
 			return -EINVAL;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 3652439a7458..b334af8aa264 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -373,6 +373,7 @@ struct nvme_subsystem {
 	char			model[40];
 	char			firmware_rev[8];
 	u8			cmic;
+	enum nvme_subsys_type	subtype;
 	u16			vendor_id;
 	u16			awupf;	/* 0's based awupf value. */
 	struct ida		ns_ida;
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index fde36c137900..ca2ee806d74b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -245,8 +245,15 @@ static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
 {
 	unsigned int mem_size = nvme_dbbuf_size(dev);
 
-	if (dev->dbbuf_dbs)
+	if (dev->dbbuf_dbs) {
+		/*
+		 * Clear the dbbuf memory so the driver doesn't observe stale
+		 * values from the previous instantiation.
+		 */
+		memset(dev->dbbuf_dbs, 0, mem_size);
+		memset(dev->dbbuf_eis, 0, mem_size);
 		return 0;
+	}
 
 	dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
 					    &dev->dbbuf_dbs_dma_addr,
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 7d9ac544db37..850f84d204d0 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1096,11 +1096,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 		return ret;
 
 	if (ctrl->ctrl.icdoff) {
+		ret = -EOPNOTSUPP;
 		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
 		goto destroy_admin;
 	}
 
 	if (!(ctrl->ctrl.sgls & (1 << 2))) {
+		ret = -EOPNOTSUPP;
 		dev_err(ctrl->ctrl.device,
 			"Mandatory keyed sgls are not supported!\n");
 		goto destroy_admin;
@@ -1112,6 +1114,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
 	}
 
+	if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) {
+		dev_warn(ctrl->ctrl.device,
+			"ctrl sqsize %u > max queue size %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE);
+		ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1;
+	}
+
 	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
 		dev_warn(ctrl->ctrl.device,
 			"sqsize %u > ctrl maxcmd %u, clamping down\n",
@@ -2386,7 +2395,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		goto out_uninit_ctrl;
 
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
-		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
 
 	mutex_lock(&nvme_rdma_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 19dcb9279a24..33bc83d8d992 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2585,7 +2585,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev,
 		goto out_uninit_ctrl;
 
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
-		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
+		nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr);
 
 	mutex_lock(&nvme_tcp_ctrl_mutex);
 	list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list);
diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c
index d95010481fce..bfc259e0d7b8 100644
--- a/drivers/nvme/host/zns.c
+++ b/drivers/nvme/host/zns.c
@@ -233,6 +233,8 @@ out_free:
 blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *c, enum nvme_zone_mgmt_action action)
 {
+	memset(c, 0, sizeof(*c));
+
 	c->zms.opcode = nvme_cmd_zone_mgmt_send;
 	c->zms.nsid = cpu_to_le32(ns->head->ns_id);
 	c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req)));