1 files changed, 74 insertions, 33 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 88b54cdcbd68..8ebdfd623e0f 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -131,7 +131,7 @@ 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 && ctrl->tagset)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE && ctrl->tagset)
 		queue_work(nvme_wq, &ctrl->scan_work);
 }
 
@@ -143,7 +143,7 @@ void nvme_queue_scan(struct nvme_ctrl *ctrl)
  */
 int nvme_try_sched_reset(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->state != NVME_CTRL_RESETTING)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_RESETTING)
 		return -EBUSY;
 	if (!queue_work(nvme_reset_wq, &ctrl->reset_work))
 		return -EBUSY;
@@ -156,7 +156,7 @@ static void nvme_failfast_work(struct work_struct *work)
 	struct nvme_ctrl *ctrl = container_of(to_delayed_work(work),
 			struct nvme_ctrl, failfast_work);
 
-	if (ctrl->state != NVME_CTRL_CONNECTING)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_CONNECTING)
 		return;
 
 	set_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
@@ -200,7 +200,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl)
 	ret = nvme_reset_ctrl(ctrl);
 	if (!ret) {
 		flush_work(&ctrl->reset_work);
-		if (ctrl->state != NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE)
 			ret = -ENETRESET;
 	}
 
@@ -482,7 +482,6 @@ EXPORT_SYMBOL_GPL(nvme_cancel_tagset);
 
 void nvme_cancel_admin_tagset(struct nvme_ctrl *ctrl)
 {
-	nvme_stop_keep_alive(ctrl);
 	if (ctrl->admin_tagset) {
 		blk_mq_tagset_busy_iter(ctrl->admin_tagset,
 				nvme_cancel_request, ctrl);
@@ -500,7 +499,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 
 	spin_lock_irqsave(&ctrl->lock, flags);
 
-	old_state = ctrl->state;
+	old_state = nvme_ctrl_state(ctrl);
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
@@ -568,7 +567,7 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	}
 
 	if (changed) {
-		ctrl->state = new_state;
+		WRITE_ONCE(ctrl->state, new_state);
 		wake_up_all(&ctrl->state_wq);
 	}
 
@@ -576,11 +575,11 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	if (!changed)
 		return false;
 
-	if (ctrl->state == NVME_CTRL_LIVE) {
+	if (new_state == NVME_CTRL_LIVE) {
 		if (old_state == NVME_CTRL_CONNECTING)
 			nvme_stop_failfast_work(ctrl);
 		nvme_kick_requeue_lists(ctrl);
-	} else if (ctrl->state == NVME_CTRL_CONNECTING &&
+	} else if (new_state == NVME_CTRL_CONNECTING &&
 		old_state == NVME_CTRL_RESETTING) {
 		nvme_start_failfast_work(ctrl);
 	}
@@ -593,7 +592,7 @@ EXPORT_SYMBOL_GPL(nvme_change_ctrl_state);
  */
 static bool nvme_state_terminal(struct nvme_ctrl *ctrl)
 {
-	switch (ctrl->state) {
+	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_NEW:
 	case NVME_CTRL_LIVE:
 	case NVME_CTRL_RESETTING:
@@ -618,7 +617,7 @@ bool nvme_wait_reset(struct nvme_ctrl *ctrl)
 	wait_event(ctrl->state_wq,
 		   nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING) ||
 		   nvme_state_terminal(ctrl));
-	return ctrl->state == NVME_CTRL_RESETTING;
+	return nvme_ctrl_state(ctrl) == NVME_CTRL_RESETTING;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_reset);
 
@@ -705,9 +704,11 @@ EXPORT_SYMBOL_GPL(nvme_init_request);
 blk_status_t nvme_fail_nonready_command(struct nvme_ctrl *ctrl,
 		struct request *rq)
 {
-	if (ctrl->state != NVME_CTRL_DELETING_NOIO &&
-	    ctrl->state != NVME_CTRL_DELETING &&
-	    ctrl->state != NVME_CTRL_DEAD &&
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
+
+	if (state != NVME_CTRL_DELETING_NOIO &&
+	    state != NVME_CTRL_DELETING &&
+	    state != NVME_CTRL_DEAD &&
 	    !test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags) &&
 	    !blk_noretry_request(rq) && !(rq->cmd_flags & REQ_NVME_MPATH))
 		return BLK_STS_RESOURCE;
@@ -737,7 +738,7 @@ bool __nvme_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 		 * command, which is require to set the queue live in the
 		 * appropinquate states.
 		 */
-		switch (ctrl->state) {
+		switch (nvme_ctrl_state(ctrl)) {
 		case NVME_CTRL_CONNECTING:
 			if (blk_rq_is_passthrough(rq) && nvme_is_fabrics(req->cmd) &&
 			    (req->cmd->fabrics.fctype == nvme_fabrics_type_connect ||
@@ -1193,8 +1194,16 @@ static unsigned long nvme_keep_alive_work_period(struct nvme_ctrl *ctrl)
 
 static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 {
-	queue_delayed_work(nvme_wq, &ctrl->ka_work,
-			   nvme_keep_alive_work_period(ctrl));
+	unsigned long now = jiffies;
+	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+	unsigned long ka_next_check_tm = ctrl->ka_last_check_time + delay;
+
+	if (time_after(now, ka_next_check_tm))
+		delay = 0;
+	else
+		delay = ka_next_check_tm - now;
+
+	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
 static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
@@ -1480,7 +1489,8 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 	if (id->ncap == 0) {
 		/* namespace not allocated or attached */
 		info->is_removed = true;
-		return -ENODEV;
+		ret = -ENODEV;
+		goto error;
 	}
 
 	info->anagrpid = id->anagrpid;
@@ -1498,8 +1508,10 @@ static int nvme_ns_info_from_identify(struct nvme_ctrl *ctrl,
 		    !memchr_inv(ids->nguid, 0, sizeof(ids->nguid)))
 			memcpy(ids->nguid, id->nguid, sizeof(ids->nguid));
 	}
+
+error:
 	kfree(id);
-	return 0;
+	return ret;
 }
 
 static int nvme_ns_info_from_id_cs_indep(struct nvme_ctrl *ctrl,
@@ -1814,16 +1826,18 @@ set_pi:
 	return ret;
 }
 
-static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
+static int nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 {
 	struct nvme_ctrl *ctrl = ns->ctrl;
+	int ret;
 
-	if (nvme_init_ms(ns, id))
-		return;
+	ret = nvme_init_ms(ns, id);
+	if (ret)
+		return ret;
 
 	ns->features &= ~(NVME_NS_METADATA_SUPPORTED | NVME_NS_EXT_LBAS);
 	if (!ns->ms || !(ctrl->ops->flags & NVME_F_METADATA_SUPPORTED))
-		return;
+		return 0;
 
 	if (ctrl->ops->flags & NVME_F_FABRICS) {
 		/*
@@ -1832,7 +1846,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		 * remap the separate metadata buffer from the block layer.
 		 */
 		if (WARN_ON_ONCE(!(id->flbas & NVME_NS_FLBAS_META_EXT)))
-			return;
+			return 0;
 
 		ns->features |= NVME_NS_EXT_LBAS;
 
@@ -1859,6 +1873,7 @@ static void nvme_configure_metadata(struct nvme_ns *ns, struct nvme_id_ns *id)
 		else
 			ns->features |= NVME_NS_METADATA_SUPPORTED;
 	}
+	return 0;
 }
 
 static void nvme_set_queue_limits(struct nvme_ctrl *ctrl,
@@ -1888,9 +1903,10 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	/*
 	 * The block layer can't support LBA sizes larger than the page size
-	 * yet, so catch this early and don't allow block I/O.
+	 * or smaller than a sector size yet, so catch this early and don't
+	 * allow block I/O.
 	 */
-	if (ns->lba_shift > PAGE_SHIFT) {
+	if (ns->lba_shift > PAGE_SHIFT || ns->lba_shift < SECTOR_SHIFT) {
 		capacity = 0;
 		bs = (1 << 9);
 	}
@@ -2027,12 +2043,23 @@ static int nvme_update_ns_info_block(struct nvme_ns *ns,
 	if (ret)
 		return ret;
 
+	if (id->ncap == 0) {
+		/* namespace not allocated or attached */
+		info->is_removed = true;
+		ret = -ENODEV;
+		goto error;
+	}
+
 	blk_mq_freeze_queue(ns->disk->queue);
 	lbaf = nvme_lbaf_index(id->flbas);
 	ns->lba_shift = id->lbaf[lbaf].ds;
 	nvme_set_queue_limits(ns->ctrl, ns->queue);
 
-	nvme_configure_metadata(ns, id);
+	ret = nvme_configure_metadata(ns, id);
+	if (ret < 0) {
+		blk_mq_unfreeze_queue(ns->disk->queue);
+		goto out;
+	}
 	nvme_set_chunk_sectors(ns, id);
 	nvme_update_disk_info(ns->disk, ns, id);
 
@@ -2084,6 +2111,8 @@ out:
 		set_bit(NVME_NS_READY, &ns->flags);
 		ret = 0;
 	}
+
+error:
 	kfree(id);
 	return ret;
 }
@@ -2523,7 +2552,7 @@ static void nvme_set_latency_tolerance(struct device *dev, s32 val)
 
 	if (ctrl->ps_max_latency_us != latency) {
 		ctrl->ps_max_latency_us = latency;
-		if (ctrl->state == NVME_CTRL_LIVE)
+		if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE)
 			nvme_configure_apst(ctrl);
 	}
 }
@@ -3211,7 +3240,7 @@ static int nvme_dev_open(struct inode *inode, struct file *file)
 	struct nvme_ctrl *ctrl =
 		container_of(inode->i_cdev, struct nvme_ctrl, cdev);
 
-	switch (ctrl->state) {
+	switch (nvme_ctrl_state(ctrl)) {
 	case NVME_CTRL_LIVE:
 		break;
 	default:
@@ -3633,6 +3662,14 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, struct nvme_ns_info *info)
 		goto out_unlink_ns;
 
 	down_write(&ctrl->namespaces_rwsem);
+	/*
+	 * Ensure that no namespaces are added to the ctrl list after the queues
+	 * are frozen, thereby avoiding a deadlock between scan and reset.
+	 */
+	if (test_bit(NVME_CTRL_FROZEN, &ctrl->flags)) {
+		up_write(&ctrl->namespaces_rwsem);
+		goto out_unlink_ns;
+	}
 	nvme_ns_add_to_ctrl_list(ns);
 	up_write(&ctrl->namespaces_rwsem);
 	nvme_get_ctrl(ctrl);
@@ -3897,7 +3934,7 @@ static void nvme_scan_work(struct work_struct *work)
 	int ret;
 
 	/* No tagset on a live ctrl means IO queues could not created */
-	if (ctrl->state != NVME_CTRL_LIVE || !ctrl->tagset)
+	if (nvme_ctrl_state(ctrl) != NVME_CTRL_LIVE || !ctrl->tagset)
 		return;
 
 	/*
@@ -3967,7 +4004,7 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	 * removing the namespaces' disks; fail all the queues now to avoid
 	 * potentially having to clean up the failed sync later.
 	 */
-	if (ctrl->state == NVME_CTRL_DEAD)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_DEAD)
 		nvme_mark_namespaces_dead(ctrl);
 
 	/* this is a no-op when called from the controller reset handler */
@@ -4049,7 +4086,7 @@ static void nvme_async_event_work(struct work_struct *work)
 	 * flushing ctrl async_event_work after changing the controller state
 	 * from LIVE and before freeing the admin queue.
 	*/
-	if (ctrl->state == NVME_CTRL_LIVE)
+	if (nvme_ctrl_state(ctrl) == NVME_CTRL_LIVE)
 		ctrl->ops->submit_async_event(ctrl);
 }
 
@@ -4348,6 +4385,7 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
 	nvme_mpath_stop(ctrl);
 	nvme_auth_stop(ctrl);
+	nvme_stop_keep_alive(ctrl);
 	nvme_stop_failfast_work(ctrl);
 	flush_work(&ctrl->async_event_work);
 	cancel_work_sync(&ctrl->fw_act_work);
@@ -4443,7 +4481,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 {
 	int ret;
 
-	ctrl->state = NVME_CTRL_NEW;
+	WRITE_ONCE(ctrl->state, NVME_CTRL_NEW);
 	clear_bit(NVME_CTRL_FAILFAST_EXPIRED, &ctrl->flags);
 	spin_lock_init(&ctrl->lock);
 	mutex_init(&ctrl->scan_lock);
@@ -4464,6 +4502,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_DELAYED_WORK(&ctrl->failfast_work, nvme_failfast_work);
 	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
 	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+	ctrl->ka_last_check_time = jiffies;
 
 	BUILD_BUG_ON(NVME_DSM_MAX_RANGES * sizeof(struct nvme_dsm_range) >
 			PAGE_SIZE);
@@ -4552,6 +4591,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_mq_unfreeze_queue(ns->queue);
 	up_read(&ctrl->namespaces_rwsem);
+	clear_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
@@ -4585,6 +4625,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
 
+	set_bit(NVME_CTRL_FROZEN, &ctrl->flags);
 	down_read(&ctrl->namespaces_rwsem);
 	list_for_each_entry(ns, &ctrl->namespaces, list)
 		blk_freeze_queue_start(ns->queue);