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

Pull NVMe fixes from Christoph:

"Fix various little regressions introduced in this merge window, plus
 a rework of the fibre channel connect and reconnect path to share the
 code instead of having separate sets of bugs. Last but not least a
 trivial trace point addition from Hannes."

* 'nvme-4.18' of git://git.infradead.org/nvme:
  nvme-fabrics: fix and refine state checks in __nvmf_check_ready
  nvme-fabrics: handle the admin-only case properly in nvmf_check_ready
  nvme-fabrics: refactor queue ready check
  blk-mq: remove blk_mq_tagset_iter
  nvme: remove nvme_reinit_tagset
  nvme-fc: fix nulling of queue data on reconnect
  nvme-fc: remove reinit_request routine
  nvme-fc: change controllers first connect to use reconnect path
  nvme: don't rely on the changed namespace list log
  nvmet: free smart-log buffer after use
  nvme-rdma: fix error flow during mapping request data
  nvme: add bio remapping tracepoint
  nvme: fix NULL pointer dereference in nvme_init_subsystem

Author: axboe

block/blk-mq-tag.c

@@ -311,35 +311,6 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 }
 EXPORT_SYMBOL(blk_mq_tagset_busy_iter);
 
-int blk_mq_tagset_iter(struct blk_mq_tag_set *set, void *data,
-			 int (fn)(void *, struct request *))
-{
-	int i, j, ret = 0;
-
-	if (WARN_ON_ONCE(!fn))
-		goto out;
-
-	for (i = 0; i < set->nr_hw_queues; i++) {
-		struct blk_mq_tags *tags = set->tags[i];
-
-		if (!tags)
-			continue;
-
-		for (j = 0; j < tags->nr_tags; j++) {
-			if (!tags->static_rqs[j])
-				continue;
-
-			ret = fn(data, tags->static_rqs[j]);
-			if (ret)
-				goto out;
-		}
-	}
-
-out:
-	return ret;
-}
-EXPORT_SYMBOL_GPL(blk_mq_tagset_iter);
-
 void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn,
 		void *priv)
 {

drivers/nvme/host/core.c

@@ -2208,7 +2208,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		 * Verify that the subsystem actually supports multiple
 		 * controllers, else bail out.
 		 */
-		if (!ctrl->opts->discovery_nqn &&
+		if (!(ctrl->opts && ctrl->opts->discovery_nqn) &&
 		    nvme_active_ctrls(found) && !(id->cmic & (1 << 1))) {
 			dev_err(ctrl->device,
 				"ignoring ctrl due to duplicate subnqn (%s).\n",
@@ -3197,40 +3197,28 @@ 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)
+static void nvme_clear_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;
+	int error;
 
 	log = kzalloc(log_size, GFP_KERNEL);
 	if (!log)
-		return false;
+		return;
 
+	/*
+	 * We need to read the log to clear the AEN, but we don't want to rely
+	 * on it for the changed namespace information as userspace could have
+	 * raced with us in reading the log page, which could cause us to miss
+	 * updates.
+	 */
 	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
-	if (error) {
+	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)
@@ -3246,9 +3234,8 @@ static void nvme_scan_work(struct work_struct *work)
 	WARN_ON_ONCE(!ctrl->tagset);
 
 	if (test_and_clear_bit(NVME_AER_NOTICE_NS_CHANGED, &ctrl->events)) {
-		if (nvme_scan_changed_ns_log(ctrl))
-			goto out_sort_namespaces;
 		dev_info(ctrl->device, "rescanning namespaces.\n");
+		nvme_clear_changed_ns_log(ctrl);
 	}
 
 	if (nvme_identify_ctrl(ctrl, &id))
@@ -3263,7 +3250,6 @@ static void nvme_scan_work(struct work_struct *work)
 	nvme_scan_ns_sequential(ctrl, nn);
 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);
@@ -3641,16 +3627,6 @@ void nvme_start_queues(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_start_queues);
 
-int nvme_reinit_tagset(struct nvme_ctrl *ctrl, struct blk_mq_tag_set *set)
-{
-	if (!ctrl->ops->reinit_request)
-		return 0;
-
-	return blk_mq_tagset_iter(set, set->driver_data,
-			ctrl->ops->reinit_request);
-}
-EXPORT_SYMBOL_GPL(nvme_reinit_tagset);
-
 int __init nvme_core_init(void)
 {
 	int result = -ENOMEM;

drivers/nvme/host/fabrics.c

@@ -536,67 +536,55 @@ static struct nvmf_transport_ops *nvmf_lookup_transport(
 	return NULL;
 }
 
-blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl, struct request *rq,
-		bool queue_live, bool is_connected)
+/*
+ * For something we're not in a state to send to the device the 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.
+ */
+blk_status_t nvmf_fail_nonready_command(struct request *rq)
 {
-	struct nvme_command *cmd = nvme_req(rq)->cmd;
+	if (!blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
+		return BLK_STS_RESOURCE;
+	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
+	return BLK_STS_IOERR;
+}
+EXPORT_SYMBOL_GPL(nvmf_fail_nonready_command);
 
-	if (likely(ctrl->state == NVME_CTRL_LIVE && is_connected))
-		return BLK_STS_OK;
+bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	struct nvme_request *req = nvme_req(rq);
+
+	/*
+	 * If we are in some state of setup or teardown only allow
+	 * internally generated commands.
+	 */
+	if (!blk_rq_is_passthrough(rq) || (req->flags & NVME_REQ_USERCMD))
+		return false;
 
+	/*
+	 * Only allow commands on a live queue, except for the connect command,
+	 * which is require to set the queue live in the appropinquate states.
+	 */
 	switch (ctrl->state) {
 	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)
-			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;
-
-		/*
-		 * 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;
+		if (req->cmd->common.opcode == nvme_fabrics_command &&
+		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)
+			return true;
 		break;
 	default:
 		break;
+	case NVME_CTRL_DEAD:
+		return false;
 	}
 
-	/*
-	 * 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;
-	nvme_req(rq)->status = NVME_SC_ABORT_REQ;
-	return BLK_STS_IOERR;
+	return queue_live;
 }
-EXPORT_SYMBOL_GPL(nvmf_check_if_ready);
+EXPORT_SYMBOL_GPL(__nvmf_check_ready);
 
 static const match_table_t opt_tokens = {
 	{ NVMF_OPT_TRANSPORT,		"transport=%s"		},

drivers/nvme/host/fabrics.h

@@ -162,7 +162,17 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
 void nvmf_free_options(struct nvmf_ctrl_options *opts);
 int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
-blk_status_t nvmf_check_if_ready(struct nvme_ctrl *ctrl,
-	struct request *rq, bool queue_live, bool is_connected);
+blk_status_t nvmf_fail_nonready_command(struct request *rq);
+bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live);
+
+static inline bool nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
+		bool queue_live)
+{
+	if (likely(ctrl->state == NVME_CTRL_LIVE ||
+		   ctrl->state == NVME_CTRL_ADMIN_ONLY))
+		return true;
+	return __nvmf_check_ready(ctrl, rq, queue_live);
+}
 
 #endif /* _NVME_FABRICS_H */