Merge branch 'nvme-5.9-rc' of git://git.infradead.org/nvme into block…

…-5.9

Pull NVMe fixes from Sagi:

"- instance leak and io boundary fixes from Keith
 - fc locking fix from Christophe
 - various tcp/rdma reset during traffic fixes from Me
 - pci use-after-free fix from Tong
 - tcp target null deref fix from Ziye"

* 'nvme-5.9-rc' of git://git.infradead.org/nvme:
  nvme-pci: cancel nvme device request before disabling
  nvme: only use power of two io boundaries
  nvme: fix controller instance leak
  nvmet-fc: Fix a missed _irqsave version of spin_lock in 'nvmet_fc_fod_op_done()'
  nvme: Fix NULL dereference for pci nvme controllers
  nvme-rdma: fix reset hang if controller died in the middle of a reset
  nvme-rdma: fix timeout handler
  nvme-rdma: serialize controller teardown sequences
  nvme-tcp: fix reset hang if controller died in the middle of a reset
  nvme-tcp: fix timeout handler
  nvme-tcp: serialize controller teardown sequences
  nvme: have nvme_wait_freeze_timeout return if it timed out
  nvme-fabrics: don't check state NVME_CTRL_NEW for request acceptance
  nvmet-tcp: Fix NULL dereference when a connect data comes in h2cdata pdu

drivers/nvme/host/core.c

@@ -2026,13 +2026,49 @@ static void nvme_update_disk_info(struct gendisk *disk,
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
+static inline bool nvme_first_scan(struct gendisk *disk)
+{
+	/* nvme_alloc_ns() scans the disk prior to adding it */
+	return !(disk->flags & GENHD_FL_UP);
+}
+
+static void nvme_set_chunk_sectors(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	struct nvme_ctrl *ctrl = ns->ctrl;
+	u32 iob;
+
+	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
+	    is_power_of_2(ctrl->max_hw_sectors))
+		iob = ctrl->max_hw_sectors;
+	else
+		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
+
+	if (!iob)
+		return;
+
+	if (!is_power_of_2(iob)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring unaligned IO boundary:%u\n",
+				ns->disk->disk_name, iob);
+		return;
+	}
+
+	if (blk_queue_is_zoned(ns->disk->queue)) {
+		if (nvme_first_scan(ns->disk))
+			pr_warn("%s: ignoring zoned namespace IO boundary\n",
+				ns->disk->disk_name);
+		return;
+	}
+
+	blk_queue_chunk_sectors(ns->queue, iob);
+}
+
 static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 {
 	unsigned lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
 	struct nvme_ns *ns = disk->private_data;
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	int ret;
-	u32 iob;
 
 	/*
 	 * If identify namespace failed, use default 512 byte block size so
@@ -2060,12 +2096,6 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		return -ENODEV;
 	}
 
-	if ((ctrl->quirks & NVME_QUIRK_STRIPE_SIZE) &&
-	    is_power_of_2(ctrl->max_hw_sectors))
-		iob = ctrl->max_hw_sectors;
-	else
-		iob = nvme_lba_to_sect(ns, le16_to_cpu(id->noiob));
-
 	ns->features = 0;
 	ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
 	/* the PI implementation requires metadata equal t10 pi tuple size */
@@ -2097,8 +2127,7 @@ static int __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 		}
 	}
 
-	if (iob && !blk_queue_is_zoned(ns->queue))
-		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
+	nvme_set_chunk_sectors(ns, id);
 	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
 	if (ns->head->disk) {
@@ -3676,6 +3705,10 @@ static umode_t nvme_dev_attrs_are_visible(struct kobject *kobj,
 		return 0;
 	if (a == &dev_attr_hostid.attr && !ctrl->opts)
 		return 0;
+	if (a == &dev_attr_ctrl_loss_tmo.attr && !ctrl->opts)
+		return 0;
+	if (a == &dev_attr_reconnect_delay.attr && !ctrl->opts)
+		return 0;
 
 	return a->mode;
 }
@@ -4390,7 +4423,7 @@ static void nvme_free_ctrl(struct device *dev)
 	struct nvme_subsystem *subsys = ctrl->subsys;
 	struct nvme_cel *cel, *next;
 
-	if (subsys && ctrl->instance != subsys->instance)
+	if (!subsys || ctrl->instance != subsys->instance)
 		ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 
 	list_for_each_entry_safe(cel, next, &ctrl->cels, entry) {
@@ -4534,7 +4567,7 @@ void nvme_unfreeze(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_unfreeze);
 
-void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 {
 	struct nvme_ns *ns;
 
@@ -4545,6 +4578,7 @@ void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout)
 			break;
 	}
 	up_read(&ctrl->namespaces_rwsem);
+	return timeout;
 }
 EXPORT_SYMBOL_GPL(nvme_wait_freeze_timeout);
 

drivers/nvme/host/fabrics.c

@@ -576,7 +576,6 @@ bool __nvmf_check_ready(struct nvme_ctrl *ctrl, struct request *rq,
 	 * which is require to set the queue live in the appropinquate states.
 	 */
 	switch (ctrl->state) {
-	case NVME_CTRL_NEW:
 	case NVME_CTRL_CONNECTING:
 		if (nvme_is_fabrics(req->cmd) &&
 		    req->cmd->fabrics.fctype == nvme_fabrics_type_connect)

drivers/nvme/host/nvme.h

@@ -605,7 +605,7 @@ void nvme_kill_queues(struct nvme_ctrl *ctrl);
 void nvme_sync_queues(struct nvme_ctrl *ctrl);
 void nvme_unfreeze(struct nvme_ctrl *ctrl);
 void nvme_wait_freeze(struct nvme_ctrl *ctrl);
-void nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
+int nvme_wait_freeze_timeout(struct nvme_ctrl *ctrl, long timeout);
 void nvme_start_freeze(struct nvme_ctrl *ctrl);
 
 #define NVME_QID_ANY -1

drivers/nvme/host/pci.c

@@ -1249,8 +1249,8 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		dev_warn_ratelimited(dev->ctrl.device,
 			 "I/O %d QID %d timeout, disable controller\n",
 			 req->tag, nvmeq->qid);
-		nvme_dev_disable(dev, true);
 		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
+		nvme_dev_disable(dev, true);
 		return BLK_EH_DONE;
 	case NVME_CTRL_RESETTING:
 		return BLK_EH_RESET_TIMER;
@@ -1267,10 +1267,10 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		dev_warn(dev->ctrl.device,
 			 "I/O %d QID %d timeout, reset controller\n",
 			 req->tag, nvmeq->qid);
+		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		nvme_dev_disable(dev, false);
 		nvme_reset_ctrl(&dev->ctrl);
 
-		nvme_req(req)->flags |= NVME_REQ_CANCELLED;
 		return BLK_EH_DONE;
 	}
 

drivers/nvme/host/rdma.c

@@ -122,6 +122,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	struct mutex		teardown_lock;
 	bool			use_inline_data;
 	u32			io_queues[HCTX_MAX_TYPES];
 };
@@ -975,14 +976,25 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 
 	if (!new) {
 		nvme_start_queues(&ctrl->ctrl);
-		nvme_wait_freeze(&ctrl->ctrl);
+		if (!nvme_wait_freeze_timeout(&ctrl->ctrl, NVME_IO_TIMEOUT)) {
+			/*
+			 * If we timed out waiting for freeze we are likely to
+			 * be stuck.  Fail the controller initialization just
+			 * to be safe.
+			 */
+			ret = -ENODEV;
+			goto out_wait_freeze_timed_out;
+		}
 		blk_mq_update_nr_hw_queues(ctrl->ctrl.tagset,
 			ctrl->ctrl.queue_count - 1);
 		nvme_unfreeze(&ctrl->ctrl);
 	}
 
 	return 0;
 
+out_wait_freeze_timed_out:
+	nvme_stop_queues(&ctrl->ctrl);
+	nvme_rdma_stop_io_queues(ctrl);
 out_cleanup_connect_q:
 	if (new)
 		blk_cleanup_queue(ctrl->ctrl.connect_q);
@@ -997,6 +1009,7 @@ static int nvme_rdma_configure_io_queues(struct nvme_rdma_ctrl *ctrl, bool new)
 static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_stop_queue(&ctrl->queues[0]);
 	if (ctrl->ctrl.admin_tagset) {
@@ -1007,11 +1020,13 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
 	if (remove)
 		blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
 	nvme_rdma_destroy_admin_queue(ctrl, remove);
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 		bool remove)
 {
+	mutex_lock(&ctrl->teardown_lock);
 	if (ctrl->ctrl.queue_count > 1) {
 		nvme_start_freeze(&ctrl->ctrl);
 		nvme_stop_queues(&ctrl->ctrl);
@@ -1025,6 +1040,7 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
 			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, remove);
 	}
+	mutex_unlock(&ctrl->teardown_lock);
 }
 
 static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl)
@@ -1180,6 +1196,7 @@ static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_RESETTING))
 		return;
 
+	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
 	queue_work(nvme_reset_wq, &ctrl->err_work);
 }
 
@@ -1946,6 +1963,22 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	return 0;
 }
 
+static void nvme_rdma_complete_timed_out(struct request *rq)
+{
+	struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
+	struct nvme_rdma_queue *queue = req->queue;
+	struct nvme_rdma_ctrl *ctrl = queue->ctrl;
+
+	/* fence other contexts that may complete the command */
+	mutex_lock(&ctrl->teardown_lock);
+	nvme_rdma_stop_queue(queue);
+	if (!blk_mq_request_completed(rq)) {
+		nvme_req(rq)->status = NVME_SC_HOST_ABORTED_CMD;
+		blk_mq_complete_request(rq);
+	}
+	mutex_unlock(&ctrl->teardown_lock);
+}
+
 static enum blk_eh_timer_return
 nvme_rdma_timeout(struct request *rq, bool reserved)
 {
@@ -1956,29 +1989,29 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
 	dev_warn(ctrl->ctrl.device, "I/O %d QID %d timeout\n",
 		 rq->tag, nvme_rdma_queue_idx(queue));
 
-	/*
-	 * Restart the timer if a controller reset is already scheduled. Any
-	 * timed out commands would be handled before entering the connecting
-	 * state.
-	 */
-	if (ctrl->ctrl.state == NVME_CTRL_RESETTING)
-		return BLK_EH_RESET_TIMER;
-
 	if (ctrl->ctrl.state != NVME_CTRL_LIVE) {
 		/*
-		 * Teardown immediately if controller times out while starting
-		 * or we are already started error recovery. all outstanding
-		 * requests are completed on shutdown, so we return BLK_EH_DONE.
+		 * If we are resetting, connecting or deleting we should
+		 * complete immediately because we may block controller
+		 * teardown or setup sequence
+		 * - ctrl disable/shutdown fabrics requests
+		 * - connect requests
+		 * - initialization admin requests
+		 * - I/O requests that entered after unquiescing and
+		 *   the controller stopped responding
+		 *
+		 * All other requests should be cancelled by the error
+		 * recovery work, so it's fine that we fail it here.
 		 */
-		flush_work(&ctrl->err_work);
-		nvme_rdma_teardown_io_queues(ctrl, false);
-		nvme_rdma_teardown_admin_queue(ctrl, false);
+		nvme_rdma_complete_timed_out(rq);
 		return BLK_EH_DONE;
 	}
 
-	dev_warn(ctrl->ctrl.device, "starting error recovery\n");
+	/*
+	 * LIVE state should trigger the normal error recovery which will
+	 * handle completing this request.
+	 */
 	nvme_rdma_error_recovery(ctrl);
-
 	return BLK_EH_RESET_TIMER;
 }
 
@@ -2278,6 +2311,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 		return ERR_PTR(-ENOMEM);
 	ctrl->ctrl.opts = opts;
 	INIT_LIST_HEAD(&ctrl->list);
+	mutex_init(&ctrl->teardown_lock);
 
 	if (!(opts->mask & NVMF_OPT_TRSVCID)) {
 		opts->trsvcid =