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

5 files changed, 142 insertions, 99 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 70c3961676e7..ef2a0af41fde 100644
--- a/drivers/nvme/host/core.c
+++ b/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);
 	}
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index aa318136460e..5f5f7067c41d 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/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;
 }
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index ef46c915b7b5..0cf0460a5c92 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/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;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ec6e4acc4d48..07e8bfe705c6 100644
--- a/drivers/nvme/host/nvme.h
+++ b/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,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index bca8f521f887..4d0bb0e45401 100644
--- a/drivers/nvme/host/pci.c
+++ b/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);