Merge branch 'nvme-4.18' of git://git.infradead.org/nvme into for-4.18/block

Pull NVMe changes from Christoph:

"Below is another set of NVMe updates for 4.18.  Besides the usual bug
 fixes this includes more feature completness in terms of AEN and log
 page handling on the target."

* 'nvme-4.18' of git://git.infradead.org/nvme:
  nvme: use the changed namespaces list log to clear ns data changed AENs
  nvme: mark nvme_queue_scan static
  nvme: submit AEN event configuration on startup
  nvmet: mask pending AENs
  nvmet: add AEN configuration support
  nvmet: implement the changed namespaces log
  nvmet: split log page implementation
  nvmet: add a new nvmet_zero_sgl helper
  nvme.h: add AEN configuration symbols
  nvme.h: add the changed namespace list log
  nvme.h: untangle AEN notice definitions
  nvmet: fix error return code in nvmet_file_ns_enable()
  nvmet: fix a typo in nvmet_file_ns_enable()
  nvme-fabrics: allow internal passthrough command on deleting controllers
  nvme-loop: add support for multiple ports
  nvme-pci: simplify __nvme_submit_cmd
  nvme-pci: Rate limit the nvme timeout warnings
  nvme: allow duplicate controller if prior controller being deleted

drivers/nvme/host/core.c

@@ -100,6 +100,15 @@ static struct class *nvme_subsys_class;
 static void nvme_ns_remove(struct nvme_ns *ns);
 static int nvme_revalidate_disk(struct gendisk *disk);
 
+static void nvme_queue_scan(struct nvme_ctrl *ctrl)
+{
+	/*
+	 * Only new queue scan work when admin and IO queues are both alive
+	 */
+	if (ctrl->state == NVME_CTRL_LIVE)
+		queue_work(nvme_wq, &ctrl->scan_work);
+}
+
 int nvme_reset_ctrl(struct nvme_ctrl *ctrl)
 {
 	if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING))
@@ -1027,6 +1036,21 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 }
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
+#define NVME_AEN_SUPPORTED \
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+
+static void nvme_enable_aen(struct nvme_ctrl *ctrl)
+{
+	u32 result;
+	int status;
+
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
+			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	if (status)
+		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
+			 ctrl->oaes & NVME_AEN_SUPPORTED);
+}
+
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
 {
 	struct nvme_user_io io;
@@ -2344,6 +2368,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 
 	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->oncs = le16_to_cpup(&id->oncs);
+	ctrl->oaes = le32_to_cpu(id->oaes);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
 	ctrl->cntlid = le16_to_cpup(&id->cntlid);
@@ -3166,6 +3191,42 @@ static void nvme_scan_ns_sequential(struct nvme_ctrl *ctrl, unsigned nn)
 	nvme_remove_invalid_namespaces(ctrl, nn);
 }
 
+static bool nvme_scan_changed_ns_log(struct nvme_ctrl *ctrl)
+{
+	size_t log_size = NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32);
+	__le32 *log;
+	int error, i;
+	bool ret = false;
+
+	log = kzalloc(log_size, GFP_KERNEL);
+	if (!log)
+		return false;
+
+	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	if (error) {
+		dev_warn(ctrl->device,
+			"reading changed ns log failed: %d\n", error);
+		goto out_free_log;
+	}
+
+	if (log[0] == cpu_to_le32(0xffffffff))
+		goto out_free_log;
+
+	for (i = 0; i < NVME_MAX_CHANGED_NAMESPACES; i++) {
+		u32 nsid = le32_to_cpu(log[i]);
+
+		if (nsid == 0)
+			break;
+		dev_info(ctrl->device, "rescanning namespace %d.\n", nsid);
+		nvme_validate_ns(ctrl, nsid);
+	}
+	ret = true;
+
+out_free_log:
+	kfree(log);
+	return ret;
+}
+
 static void nvme_scan_work(struct work_struct *work)
 {
 	struct nvme_ctrl *ctrl =
@@ -3178,6 +3239,12 @@ static void nvme_scan_work(struct work_struct *work)
 
 	WARN_ON_ONCE(!ctrl->tagset);
 
+	if (test_and_clear_bit(EVENT_NS_CHANGED, &ctrl->events)) {
+		if (nvme_scan_changed_ns_log(ctrl))
+			goto out_sort_namespaces;
+		dev_info(ctrl->device, "rescanning namespaces.\n");
+	}
+
 	if (nvme_identify_ctrl(ctrl, &id))
 		return;
 
@@ -3185,26 +3252,17 @@ static void nvme_scan_work(struct work_struct *work)
 	if (ctrl->vs >= NVME_VS(1, 1, 0) &&
 	    !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) {
 		if (!nvme_scan_ns_list(ctrl, nn))
-			goto done;
+			goto out_free_id;
 	}
 	nvme_scan_ns_sequential(ctrl, nn);
- done:
+out_free_id:
+	kfree(id);
+out_sort_namespaces:
 	down_write(&ctrl->namespaces_rwsem);
 	list_sort(NULL, &ctrl->namespaces, ns_cmp);
 	up_write(&ctrl->namespaces_rwsem);
-	kfree(id);
 }
 
-void nvme_queue_scan(struct nvme_ctrl *ctrl)
-{
-	/*
-	 * Only new queue scan work when admin and IO queues are both alive
-	 */
-	if (ctrl->state == NVME_CTRL_LIVE)
-		queue_work(nvme_wq, &ctrl->scan_work);
-}
-EXPORT_SYMBOL_GPL(nvme_queue_scan);
-
 /*
  * This function iterates the namespace list unlocked to allow recovery from
  * controller failure. It is up to the caller to ensure the namespace list is
@@ -3318,6 +3376,21 @@ static void nvme_fw_act_work(struct work_struct *work)
 	nvme_get_fw_slot_info(ctrl);
 }
 
+static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
+{
+	switch ((result & 0xff00) >> 8) {
+	case NVME_AER_NOTICE_NS_CHANGED:
+		set_bit(EVENT_NS_CHANGED, &ctrl->events);
+		nvme_queue_scan(ctrl);
+		break;
+	case NVME_AER_NOTICE_FW_ACT_STARTING:
+		queue_work(nvme_wq, &ctrl->fw_act_work);
+		break;
+	default:
+		dev_warn(ctrl->device, "async event result %08x\n", result);
+	}
+}
+
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		volatile union nvme_result *res)
 {
@@ -3327,6 +3400,9 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		return;
 
 	switch (result & 0x7) {
+	case NVME_AER_NOTICE:
+		nvme_handle_aen_notice(ctrl, result);
+		break;
 	case NVME_AER_ERROR:
 	case NVME_AER_SMART:
 	case NVME_AER_CSS:
@@ -3336,18 +3412,6 @@ void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 	default:
 		break;
 	}
-
-	switch (result & 0xff07) {
-	case NVME_AER_NOTICE_NS_CHANGED:
-		dev_info(ctrl->device, "rescanning\n");
-		nvme_queue_scan(ctrl);
-		break;
-	case NVME_AER_NOTICE_FW_ACT_STARTING:
-		queue_work(nvme_wq, &ctrl->fw_act_work);
-		break;
-	default:
-		dev_warn(ctrl->device, "async event result %08x\n", result);
-	}
 	queue_work(nvme_wq, &ctrl->async_event_work);
 }
 EXPORT_SYMBOL_GPL(nvme_complete_async_event);
@@ -3370,6 +3434,7 @@ void nvme_start_ctrl(struct nvme_ctrl *ctrl)
 
 	if (ctrl->queue_count > 1) {
 		nvme_queue_scan(ctrl);
+		nvme_enable_aen(ctrl);
 		queue_work(nvme_wq, &ctrl->async_event_work);
 		nvme_start_queues(ctrl);
 	}

drivers/nvme/host/fabrics.c

@@ -545,71 +545,54 @@ blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		return BLK_STS_OK;
 
 	switch (ctrl->state) {
-	case NVME_CTRL_DELETING:
-		goto reject_io;
-
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
+	case NVME_CTRL_DELETING:
+		/*
+		 * This is the case of starting a new or deleting an association
+		 * but connectivity was lost before it was fully created or torn
+		 * down. We need to error the commands used to initialize the
+		 * controller so the reconnect can go into a retry attempt.  The
+		 * commands should all be marked REQ_FAILFAST_DRIVER, which will
+		 * hit the reject path below. Anything else will be queued while
+		 * the state settles.
+		 */
 		if (!is_connected)
-			/*
-			 * This is the case of starting a new
-			 * association but connectivity was lost
-			 * before it was fully created. We need to
-			 * error the commands used to initialize the
-			 * controller so the reconnect can go into a
-			 * retry attempt. The commands should all be
-			 * marked REQ_FAILFAST_DRIVER, which will hit
-			 * the reject path below. Anything else will
-			 * be queued while the state settles.
-			 */
-			goto reject_or_queue_io;
-
-		if ((queue_live &&
-		     !(nvme_req(rq)->flags & NVME_REQ_USERCMD)) ||
-		    (!queue_live && blk_rq_is_passthrough(rq) &&
-		     cmd->common.opcode == nvme_fabrics_command &&
-		     cmd->fabrics.fctype == nvme_fabrics_type_connect))
-			/*
-			 * If queue is live, allow only commands that
-			 * are internally generated pass through. These
-			 * are commands on the admin queue to initialize
-			 * the controller. This will reject any ioctl
-			 * admin cmds received while initializing.
-			 *
-			 * If the queue is not live, allow only a
-			 * connect command. This will reject any ioctl
-			 * admin cmd as well as initialization commands
-			 * if the controller reverted the queue to non-live.
-			 */
+			break;
+
+		/*
+		 * If queue is live, allow only commands that are internally
+		 * generated pass through.  These are commands on the admin
+		 * queue to initialize the controller. This will reject any
+		 * ioctl admin cmds received while initializing.
+		 */
+		if (queue_live && !(nvme_req(rq)->flags & NVME_REQ_USERCMD))
 			return BLK_STS_OK;
 
 		/*
-		 * fall-thru to the reject_or_queue_io clause
+		 * If the queue is not live, allow only a connect command.  This
+		 * will reject any ioctl admin cmd as well as initialization
+		 * commands if the controller reverted the queue to non-live.
 		 */
+		if (!queue_live && blk_rq_is_passthrough(rq) &&
+		     cmd->common.opcode == nvme_fabrics_command &&
+		     cmd->fabrics.fctype == nvme_fabrics_type_connect)
+			return BLK_STS_OK;
 		break;
-
-	/* these cases fall-thru
-	 * case NVME_CTRL_LIVE:
-	 * case NVME_CTRL_RESETTING:
-	 */
 	default:
 		break;
 	}
 
-reject_or_queue_io:
 	/*
-	 * Any other new io is something we're not in a state to send
-	 * to the device. Default action is to busy it and retry it
-	 * after the controller state is recovered. However, anything
-	 * marked for failfast or nvme multipath is immediately failed.
-	 * Note: commands used to initialize the controller will be
-	 *  marked for failfast.
+	 * Any other new io is something we're not in a state to send to the
+	 * device.  Default action is to busy it and retry it after the
+	 * controller state is recovered. However, anything marked for failfast
+	 * or nvme multipath is immediately failed.  Note: commands used to
+	 * initialize the controller will be marked for failfast.
 	 * Note: nvme cli/ioctl commands are marked for failfast.
 	 */
 	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
-
-reject_io:
 	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
 	return BLK_STS_IOERR;
 }

drivers/nvme/host/fabrics.h

@@ -139,7 +139,9 @@ static inline bool
 nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl,
 			struct nvmf_ctrl_options *opts)
 {
-	if (strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
+	if (ctrl->state == NVME_CTRL_DELETING ||
+	    ctrl->state == NVME_CTRL_DEAD ||
+	    strcmp(opts->subsysnqn, ctrl->opts->subsysnqn) ||
 	    strcmp(opts->host->nqn, ctrl->opts->host->nqn) ||
 	    memcmp(&opts->host->id, &ctrl->opts->host->id, sizeof(uuid_t)))
 		return false;

drivers/nvme/host/nvme.h

@@ -176,6 +176,7 @@ struct nvme_ctrl {
 	u16 kas;
 	u8 npss;
 	u8 apsta;
+	u32 oaes;
 	u32 aen_result;
 	unsigned int shutdown_timeout;
 	unsigned int kato;
@@ -188,6 +189,8 @@ struct nvme_ctrl {
 	struct delayed_work ka_work;
 	struct nvme_command ka_cmd;
 	struct work_struct fw_act_work;
+#define EVENT_NS_CHANGED		(1 << 0)
+	unsigned long events;
 
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
@@ -394,7 +397,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl);
 void nvme_put_ctrl(struct nvme_ctrl *ctrl);
 int nvme_init_identify(struct nvme_ctrl *ctrl);
 
-void nvme_queue_scan(struct nvme_ctrl *ctrl);
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
 int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,

drivers/nvme/host/pci.c

@@ -421,28 +421,25 @@ static int nvme_pci_map_queues(struct blk_mq_tag_set *set)
 }
 
 /**
- * __nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
+ * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
  * @nvmeq: The queue to use
  * @cmd: The command to send
- *
- * Safe to use from interrupt context
  */
-static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
-						struct nvme_command *cmd)
+static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
 {
-	u16 tail = nvmeq->sq_tail;
-
+	spin_lock(&nvmeq->sq_lock);
 	if (nvmeq->sq_cmds_io)
-		memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
+		memcpy_toio(&nvmeq->sq_cmds_io[nvmeq->sq_tail], cmd,
+				sizeof(*cmd));
 	else
-		memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
+		memcpy(&nvmeq->sq_cmds[nvmeq->sq_tail], cmd, sizeof(*cmd));
 
-	if (++tail == nvmeq->q_depth)
-		tail = 0;
-	if (nvme_dbbuf_update_and_check_event(tail, nvmeq->dbbuf_sq_db,
-					      nvmeq->dbbuf_sq_ei))
-		writel(tail, nvmeq->q_db);
-	nvmeq->sq_tail = tail;
+	if (++nvmeq->sq_tail == nvmeq->q_depth)
+		nvmeq->sq_tail = 0;
+	if (nvme_dbbuf_update_and_check_event(nvmeq->sq_tail,
+			nvmeq->dbbuf_sq_db, nvmeq->dbbuf_sq_ei))
+		writel(nvmeq->sq_tail, nvmeq->q_db);
+	spin_unlock(&nvmeq->sq_lock);
 }
 
 static void **nvme_pci_iod_list(struct request *req)
@@ -895,10 +892,7 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
 	}
 
 	blk_mq_start_request(req);
-
-	spin_lock(&nvmeq->sq_lock);
-	__nvme_submit_cmd(nvmeq, &cmnd);
-	spin_unlock(&nvmeq->sq_lock);
+	nvme_submit_cmd(nvmeq, &cmnd);
 	return BLK_STS_OK;
 out_cleanup_iod:
 	nvme_free_iod(dev, req);
@@ -1058,10 +1052,7 @@ static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl)
 	memset(&c, 0, sizeof(c));
 	c.common.opcode = nvme_admin_async_event;
 	c.common.command_id = NVME_AQ_BLK_MQ_DEPTH;
-
-	spin_lock(&nvmeq->sq_lock);
-	__nvme_submit_cmd(nvmeq, &c);
-	spin_unlock(&nvmeq->sq_lock);
+	nvme_submit_cmd(nvmeq, &c);
 }
 
 static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
@@ -1227,7 +1218,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 	switch (dev->ctrl.state) {
 	case NVME_CTRL_CONNECTING:
 	case NVME_CTRL_RESETTING:
-		dev_warn(dev->ctrl.device,
+		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
 		nvme_dev_disable(dev, false);

drivers/nvme/target/admin-cmd.c

@@ -32,6 +32,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 	return len;
 }
 
+static void nvmet_execute_get_log_page_noop(struct nvmet_req *req)
+{
+	nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len));
+}
+
 static u16 nvmet_get_smart_log_nsid(struct nvmet_req *req,
 		struct nvme_smart_log *slog)
 {
@@ -97,74 +102,50 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 	return NVME_SC_SUCCESS;
 }
 
-static u16 nvmet_get_smart_log(struct nvmet_req *req,
-		struct nvme_smart_log *slog)
+static void nvmet_execute_get_log_page_smart(struct nvmet_req *req)
 {
-	u16 status;
+	struct nvme_smart_log *log;
+	u16 status = NVME_SC_INTERNAL;
+
+	if (req->data_len != sizeof(*log))
+		goto out;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		goto out;
 
-	WARN_ON(req == NULL || slog == NULL);
 	if (req->cmd->get_log_page.nsid == cpu_to_le32(NVME_NSID_ALL))
-		status = nvmet_get_smart_log_all(req, slog);
+		status = nvmet_get_smart_log_all(req, log);
 	else
-		status = nvmet_get_smart_log_nsid(req, slog);
-	return status;
+		status = nvmet_get_smart_log_nsid(req, log);
+	if (status)
+		goto out;
+
+	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+out:
+	nvmet_req_complete(req, status);
 }
 
-static void nvmet_execute_get_log_page(struct nvmet_req *req)
+static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 {
-	struct nvme_smart_log *smart_log;
-	size_t data_len = nvmet_get_log_page_len(req->cmd);
-	void *buf;
-	u16 status = 0;
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	u16 status = NVME_SC_INTERNAL;
+	size_t len;
 
-	buf = kzalloc(data_len, GFP_KERNEL);
-	if (!buf) {
-		status = NVME_SC_INTERNAL;
+	if (req->data_len != NVME_MAX_CHANGED_NAMESPACES * sizeof(__le32))
 		goto out;
-	}
-
-	switch (req->cmd->get_log_page.lid) {
-	case NVME_LOG_ERROR:
-		/*
-		 * We currently never set the More bit in the status field,
-		 * so all error log entries are invalid and can be zeroed out.
-		 * This is called a minum viable implementation (TM) of this
-		 * mandatory log page.
-		 */
-		break;
-	case NVME_LOG_SMART:
-		/*
-		 * XXX: fill out actual smart log
-		 *
-		 * We might have a hard time coming up with useful values for
-		 * many of the fields, and even when we have useful data
-		 * available (e.g. units or commands read/written) those aren't
-		 * persistent over power loss.
-		 */
-		if (data_len != sizeof(*smart_log)) {
-			status = NVME_SC_INTERNAL;
-			goto err;
-		}
-		smart_log = buf;
-		status = nvmet_get_smart_log(req, smart_log);
-		if (status)
-			goto err;
-		break;
-	case NVME_LOG_FW_SLOT:
-		/*
-		 * We only support a single firmware slot which always is
-		 * active, so we can zero out the whole firmware slot log and
-		 * still claim to fully implement this mandatory log page.
-		 */
-		break;
-	default:
-		BUG();
-	}
-
-	status = nvmet_copy_to_sgl(req, 0, buf, data_len);
 
-err:
-	kfree(buf);
+	mutex_lock(&ctrl->lock);
+	if (ctrl->nr_changed_ns == U32_MAX)
+		len = sizeof(__le32);
+	else
+		len = ctrl->nr_changed_ns * sizeof(__le32);
+	status = nvmet_copy_to_sgl(req, 0, ctrl->changed_ns_list, len);
+	if (!status)
+		status = nvmet_zero_sgl(req, len, req->data_len - len);
+	ctrl->nr_changed_ns = 0;
+	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
 }
@@ -209,7 +190,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->ver = cpu_to_le32(ctrl->subsys->ver);
 
 	/* XXX: figure out what to do about RTD3R/RTD3 */
-	id->oaes = cpu_to_le32(1 << 8);
+	id->oaes = cpu_to_le32(NVMET_AEN_CFG_OPTIONAL);
 	id->ctratt = cpu_to_le32(1 << 0);
 
 	id->oacs = 0;
@@ -455,6 +436,16 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 		req->sq->ctrl->kato = DIV_ROUND_UP(val32, 1000);
 		nvmet_set_result(req, req->sq->ctrl->kato);
 		break;
+	case NVME_FEAT_ASYNC_EVENT:
+		val32 = le32_to_cpu(req->cmd->common.cdw10[1]);
+		if (val32 & ~NVMET_AEN_CFG_ALL) {
+			status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
+			break;
+		}
+
+		WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
+		nvmet_set_result(req, val32);
+		break;
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 		break;
@@ -493,9 +484,10 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		break;
 	case NVME_FEAT_WRITE_ATOMIC:
 		break;
+#endif
 	case NVME_FEAT_ASYNC_EVENT:
+		nvmet_set_result(req, READ_ONCE(req->sq->ctrl->aen_enabled));
 		break;
-#endif
 	case NVME_FEAT_VOLATILE_WC:
 		nvmet_set_result(req, 1);
 		break;
@@ -566,9 +558,28 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 
 		switch (cmd->get_log_page.lid) {
 		case NVME_LOG_ERROR:
+			/*
+			 * We currently never set the More bit in the status
+			 * field, so all error log entries are invalid and can
+			 * be zeroed out.  This is called a minum viable
+			 * implementation (TM) of this mandatory log page.
+			 */
+			req->execute = nvmet_execute_get_log_page_noop;
+			return 0;
 		case NVME_LOG_SMART:
+			req->execute = nvmet_execute_get_log_page_smart;
+			return 0;
 		case NVME_LOG_FW_SLOT:
-			req->execute = nvmet_execute_get_log_page;
+			/*
+			 * We only support a single firmware slot which always
+			 * is active, so we can zero out the whole firmware slot
+			 * log and still claim to fully implement this mandatory
+			 * log page.
+			 */
+			req->execute = nvmet_execute_get_log_page_noop;
+			return 0;
+		case NVME_LOG_CHANGED_NS:
+			req->execute = nvmet_execute_get_log_changed_ns;
 			return 0;
 		}
 		break;

drivers/nvme/target/core.c

@@ -57,6 +57,13 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
 	return 0;
 }
 
+u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
+{
+	if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len)
+		return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
+	return 0;
+}
+
 static unsigned int nvmet_max_nsid(struct nvmet_subsys *subsys)
 {
 	struct nvmet_ns *ns;
@@ -137,6 +144,51 @@ static void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 	schedule_work(&ctrl->async_event_work);
 }
 
+static bool nvmet_aen_disabled(struct nvmet_ctrl *ctrl, u32 aen)
+{
+	if (!(READ_ONCE(ctrl->aen_enabled) & aen))
+		return true;
+	return test_and_set_bit(aen, &ctrl->aen_masked);
+}
+
+static void nvmet_add_to_changed_ns_log(struct nvmet_ctrl *ctrl, __le32 nsid)
+{
+	u32 i;
+
+	mutex_lock(&ctrl->lock);
+	if (ctrl->nr_changed_ns > NVME_MAX_CHANGED_NAMESPACES)
+		goto out_unlock;
+
+	for (i = 0; i < ctrl->nr_changed_ns; i++) {
+		if (ctrl->changed_ns_list[i] == nsid)
+			goto out_unlock;
+	}
+
+	if (ctrl->nr_changed_ns == NVME_MAX_CHANGED_NAMESPACES) {
+		ctrl->changed_ns_list[0] = cpu_to_le32(0xffffffff);
+		ctrl->nr_changed_ns = U32_MAX;
+		goto out_unlock;
+	}
+
+	ctrl->changed_ns_list[ctrl->nr_changed_ns++] = nsid;
+out_unlock:
+	mutex_unlock(&ctrl->lock);
+}
+
+static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+{
+	struct nvmet_ctrl *ctrl;
+
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid));
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_NS_ATTR))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_NS_CHANGED,
+				NVME_LOG_CHANGED_NS);
+	}
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
@@ -280,7 +332,6 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	struct nvmet_ctrl *ctrl;
 	int ret = 0;
 
 	mutex_lock(&subsys->lock);
@@ -319,9 +370,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
 
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
-
+	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
 	ret = 0;
 out_unlock:
@@ -335,7 +384,6 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 void nvmet_ns_disable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	struct nvmet_ctrl *ctrl;
 
 	mutex_lock(&subsys->lock);
 	if (!ns->enabled)
@@ -361,9 +409,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
-	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
-		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE, 0, 0);
-
+	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
 out_unlock:
 	mutex_unlock(&subsys->lock);
@@ -824,12 +870,18 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	kref_init(&ctrl->ref);
 	ctrl->subsys = subsys;
+	WRITE_ONCE(ctrl->aen_enabled, NVMET_AEN_CFG_OPTIONAL);
+
+	ctrl->changed_ns_list = kmalloc_array(NVME_MAX_CHANGED_NAMESPACES,
+			sizeof(__le32), GFP_KERNEL);
+	if (!ctrl->changed_ns_list)
+		goto out_free_ctrl;
 
 	ctrl->cqs = kcalloc(subsys->max_qid + 1,
 			sizeof(struct nvmet_cq *),
 			GFP_KERNEL);
 	if (!ctrl->cqs)
-		goto out_free_ctrl;
+		goto out_free_changed_ns_list;
 
 	ctrl->sqs = kcalloc(subsys->max_qid + 1,
 			sizeof(struct nvmet_sq *),
@@ -887,6 +939,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 	kfree(ctrl->sqs);
 out_free_cqs:
 	kfree(ctrl->cqs);
+out_free_changed_ns_list:
+	kfree(ctrl->changed_ns_list);
 out_free_ctrl:
 	kfree(ctrl);
 out_put_subsystem:
@@ -913,6 +967,7 @@ static void nvmet_ctrl_free(struct kref *ref)
 
 	kfree(ctrl->sqs);
 	kfree(ctrl->cqs);
+	kfree(ctrl->changed_ns_list);
 	kfree(ctrl);
 
 	nvmet_subsys_put(subsys);

drivers/nvme/target/io-cmd-file.c

@@ -34,7 +34,7 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns)
 			O_RDWR | O_LARGEFILE | O_DIRECT, 0);
 	if (IS_ERR(ns->file)) {
 		pr_err("failed to open file %s: (%ld)\n",
-				ns->device_path, PTR_ERR(ns->bdev));
+				ns->device_path, PTR_ERR(ns->file));
 		return PTR_ERR(ns->file);
 	}
 
@@ -49,14 +49,18 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns)
 	ns->bvec_cache = kmem_cache_create("nvmet-bvec",
 			NVMET_MAX_MPOOL_BVEC * sizeof(struct bio_vec),
 			0, SLAB_HWCACHE_ALIGN, NULL);
-	if (!ns->bvec_cache)
+	if (!ns->bvec_cache) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	ns->bvec_pool = mempool_create(NVMET_MIN_MPOOL_OBJ, mempool_alloc_slab,
 			mempool_free_slab, ns->bvec_cache);
 
-	if (!ns->bvec_pool)
+	if (!ns->bvec_pool) {
+		ret = -ENOMEM;
 		goto err;
+	}
 
 	return ret;
 err:

drivers/nvme/target/loop.c

@@ -45,6 +45,7 @@ struct nvme_loop_ctrl {
 	struct nvme_ctrl	ctrl;
 
 	struct nvmet_ctrl	*target_ctrl;
+	struct nvmet_port	*port;
 };
 
 static inline struct nvme_loop_ctrl *to_loop_ctrl(struct nvme_ctrl *ctrl)
@@ -63,7 +64,8 @@ struct nvme_loop_queue {
 	unsigned long		flags;
 };
 
-static struct nvmet_port *nvmet_loop_port;
+static LIST_HEAD(nvme_loop_ports);
+static DEFINE_MUTEX(nvme_loop_ports_mutex);
 
 static LIST_HEAD(nvme_loop_ctrl_list);
 static DEFINE_MUTEX(nvme_loop_ctrl_mutex);
@@ -169,7 +171,7 @@ static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx,
 
 	blk_mq_start_request(req);
 	iod->cmd.common.flags |= NVME_CMD_SGL_METABUF;
-	iod->req.port = nvmet_loop_port;
+	iod->req.port = queue->ctrl->port;
 	if (!nvmet_req_init(&iod->req, &queue->nvme_cq,
 			&queue->nvme_sq, &nvme_loop_ops))
 		return BLK_STS_OK;
@@ -517,6 +519,7 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
 	.free_ctrl		= nvme_loop_free_ctrl,
 	.submit_async_event	= nvme_loop_submit_async_event,
 	.delete_ctrl		= nvme_loop_delete_ctrl_host,
+	.get_address		= nvmf_get_address,
 };
 
 static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
@@ -565,6 +568,23 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
 	return ret;
 }
 
+static struct nvmet_port *nvme_loop_find_port(struct nvme_ctrl *ctrl)
+{
+	struct nvmet_port *p, *found = NULL;
+
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_for_each_entry(p, &nvme_loop_ports, entry) {
+		/* if no transport address is specified use the first port */
+		if ((ctrl->opts->mask & NVMF_OPT_TRADDR) &&
+		    strcmp(ctrl->opts->traddr, p->disc_addr.traddr))
+			continue;
+		found = p;
+		break;
+	}
+	mutex_unlock(&nvme_loop_ports_mutex);
+	return found;
+}
+
 static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 		struct nvmf_ctrl_options *opts)
 {
@@ -589,6 +609,7 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 
 	ctrl->ctrl.sqsize = opts->queue_size - 1;
 	ctrl->ctrl.kato = opts->kato;
+	ctrl->port = nvme_loop_find_port(&ctrl->ctrl);
 
 	ctrl->queues = kcalloc(opts->nr_io_queues + 1, sizeof(*ctrl->queues),
 			GFP_KERNEL);
@@ -646,27 +667,17 @@ static struct nvme_ctrl *nvme_loop_create_ctrl(struct device *dev,
 
 static int nvme_loop_add_port(struct nvmet_port *port)
 {
-	/*
-	 * XXX: disalow adding more than one port so
-	 * there is no connection rejections when a
-	 * a subsystem is assigned to a port for which
-	 * loop doesn't have a pointer.
-	 * This scenario would be possible if we allowed
-	 * more than one port to be added and a subsystem
-	 * was assigned to a port other than nvmet_loop_port.
-	 */
-
-	if (nvmet_loop_port)
-		return -EPERM;
-
-	nvmet_loop_port = port;
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_add_tail(&port->entry, &nvme_loop_ports);
+	mutex_unlock(&nvme_loop_ports_mutex);
 	return 0;
 }
 
 static void nvme_loop_remove_port(struct nvmet_port *port)
 {
-	if (port == nvmet_loop_port)
-		nvmet_loop_port = NULL;
+	mutex_lock(&nvme_loop_ports_mutex);
+	list_del_init(&port->entry);
+	mutex_unlock(&nvme_loop_ports_mutex);
 }
 
 static const struct nvmet_fabrics_ops nvme_loop_ops = {
@@ -682,6 +693,7 @@ static struct nvmf_transport_ops nvme_loop_transport = {
 	.name		= "loop",
 	.module		= THIS_MODULE,
 	.create_ctrl	= nvme_loop_create_ctrl,
+	.allowed_opts	= NVMF_OPT_TRADDR,
 };
 
 static int __init nvme_loop_init_module(void)

drivers/nvme/target/nvmet.h

@@ -30,6 +30,21 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
+
+/*
+ * Supported optional AENs:
+ */
+#define NVMET_AEN_CFG_OPTIONAL \
+	NVME_AEN_CFG_NS_ATTR
+
+/*
+ * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
+ */
+#define NVMET_AEN_CFG_ALL \
+	(NVME_SMART_CRIT_SPARE | NVME_SMART_CRIT_TEMPERATURE | \
+	 NVME_SMART_CRIT_RELIABILITY | NVME_SMART_CRIT_MEDIA | \
+	 NVME_SMART_CRIT_VOLATILE_MEMORY | NVMET_AEN_CFG_OPTIONAL)
+
 /* Helper Macros when NVMe error is NVME_SC_CONNECT_INVALID_PARAM
  * The 16 bit shift is to set IATTR bit to 1, which means offending
  * offset starts in the data section of connect()
@@ -85,7 +100,7 @@ struct nvmet_sq {
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
- * @entry:		List head for holding a list of these elements.
+ * @entry:		Entry into referrals or transport list.
  * @disc_addr:		Address information is stored in a format defined
  *				for a discovery log page entry.
  * @group:		ConfigFS group for this element's folder.
@@ -123,6 +138,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	u32			aen_enabled;
+	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
 	unsigned int		nr_async_event_cmds;
 	struct list_head	async_events;
@@ -135,6 +152,9 @@ struct nvmet_ctrl {
 
 	const struct nvmet_fabrics_ops *ops;
 
+	__le32			*changed_ns_list;
+	u32			nr_changed_ns;
+
 	char			subsysnqn[NVMF_NQN_FIELD_LEN];
 	char			hostnqn[NVMF_NQN_FIELD_LEN];
 };
@@ -330,6 +350,7 @@ u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
 		size_t len);
 u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf,
 		size_t len);
+u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len);
 
 u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 

include/linux/nvme.h

@@ -436,10 +436,19 @@ enum {
 enum {
 	NVME_AER_ERROR			= 0,
 	NVME_AER_SMART			= 1,
+	NVME_AER_NOTICE			= 2,
 	NVME_AER_CSS			= 6,
 	NVME_AER_VS			= 7,
-	NVME_AER_NOTICE_NS_CHANGED	= 0x0002,
-	NVME_AER_NOTICE_FW_ACT_STARTING = 0x0102,
+};
+
+enum {
+	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
+	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+};
+
+enum {
+	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
+	NVME_AEN_CFG_FW_ACT		= 1 << 9,
 };
 
 struct nvme_lba_range_type {
@@ -747,6 +756,7 @@ enum {
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
+	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
@@ -755,6 +765,8 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+#define NVME_MAX_CHANGED_NAMESPACES	1024
+
 struct nvme_identify {
 	__u8			opcode;
 	__u8			flags;