Merge tag 'nvme-6.12-2024-10-18' of git://git.infradead.org/nvme into block-6.12

Pull NVMe fixes from Keith:

"nvme fixes for Linux 6.12

 - Fix target passthrough identifier (Nilay)
 - Fix tcp locking (Hannes)
 - Replace list with sbitmap for tracking RDMA rsp tags (Guixen)
 - Remove unnecessary fallthrough statements (Tokunori)
 - Remove ready-without-media support (Greg)
 - Fix multipath partition scan deadlock (Keith)
 - Fix concurrent PCI reset and remove queue mapping (Maurizio)
 - Fabrics shutdown fixes (Nilay)"

* tag 'nvme-6.12-2024-10-18' of git://git.infradead.org/nvme:
  nvme: use helper nvme_ctrl_state in nvme_keep_alive_finish function
  nvme: make keep-alive synchronous operation
  nvme-loop: flush off pending I/O while shutting down loop controller
  nvme-pci: fix race condition between reset and nvme_dev_disable()
  nvme-multipath: defer partition scanning
  nvme: disable CC.CRIME (NVME_CC_CRIME)
  nvme: delete unnecessary fallthru comment
  nvmet-rdma: use sbitmap to replace rsp free list
  nvme: tcp: avoid race between queue_lock lock and destroy
  nvmet-passthru: clear EUID/NGUID/UUID while using loop target
  block: fix blk_rq_map_integrity_sg kernel-doc

drivers/nvme/host/core.c

@@ -1292,14 +1292,12 @@ static void nvme_queue_keep_alive_work(struct nvme_ctrl *ctrl)
 	queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
 }
 
-static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
-						 blk_status_t status)
+static void nvme_keep_alive_finish(struct request *rq,
+		blk_status_t status, struct nvme_ctrl *ctrl)
 {
-	struct nvme_ctrl *ctrl = rq->end_io_data;
-	unsigned long flags;
-	bool startka = false;
 	unsigned long rtt = jiffies - (rq->deadline - rq->timeout);
 	unsigned long delay = nvme_keep_alive_work_period(ctrl);
+	enum nvme_ctrl_state state = nvme_ctrl_state(ctrl);
 
 	/*
 	 * Subtract off the keepalive RTT so nvme_keep_alive_work runs
@@ -1313,25 +1311,17 @@ static enum rq_end_io_ret nvme_keep_alive_end_io(struct request *rq,
 		delay = 0;
 	}
 
-	blk_mq_free_request(rq);
-
 	if (status) {
 		dev_err(ctrl->device,
 			"failed nvme_keep_alive_end_io error=%d\n",
 				status);
-		return RQ_END_IO_NONE;
+		return;
 	}
 
 	ctrl->ka_last_check_time = jiffies;
 	ctrl->comp_seen = false;
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (ctrl->state == NVME_CTRL_LIVE ||
-	    ctrl->state == NVME_CTRL_CONNECTING)
-		startka = true;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-	if (startka)
+	if (state == NVME_CTRL_LIVE || state == NVME_CTRL_CONNECTING)
 		queue_delayed_work(nvme_wq, &ctrl->ka_work, delay);
-	return RQ_END_IO_NONE;
 }
 
 static void nvme_keep_alive_work(struct work_struct *work)
@@ -1340,6 +1330,7 @@ static void nvme_keep_alive_work(struct work_struct *work)
 			struct nvme_ctrl, ka_work);
 	bool comp_seen = ctrl->comp_seen;
 	struct request *rq;
+	blk_status_t status;
 
 	ctrl->ka_last_check_time = jiffies;
 
@@ -1362,9 +1353,9 @@ static void nvme_keep_alive_work(struct work_struct *work)
 	nvme_init_request(rq, &ctrl->ka_cmd);
 
 	rq->timeout = ctrl->kato * HZ;
-	rq->end_io = nvme_keep_alive_end_io;
-	rq->end_io_data = ctrl;
-	blk_execute_rq_nowait(rq, false);
+	status = blk_execute_rq(rq, false);
+	nvme_keep_alive_finish(rq, status, ctrl);
+	blk_mq_free_request(rq);
 }
 
 static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
@@ -2458,8 +2449,13 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 	else
 		ctrl->ctrl_config = NVME_CC_CSS_NVM;
 
-	if (ctrl->cap & NVME_CAP_CRMS_CRWMS && ctrl->cap & NVME_CAP_CRMS_CRIMS)
-		ctrl->ctrl_config |= NVME_CC_CRIME;
+	/*
+	 * Setting CRIME results in CSTS.RDY before the media is ready. This
+	 * makes it possible for media related commands to return the error
+	 * NVME_SC_ADMIN_COMMAND_MEDIA_NOT_READY. Until the driver is
+	 * restructured to handle retries, disable CC.CRIME.
+	 */
+	ctrl->ctrl_config &= ~NVME_CC_CRIME;
 
 	ctrl->ctrl_config |= (NVME_CTRL_PAGE_SHIFT - 12) << NVME_CC_MPS_SHIFT;
 	ctrl->ctrl_config |= NVME_CC_AMS_RR | NVME_CC_SHN_NONE;
@@ -2489,9 +2485,6 @@ int nvme_enable_ctrl(struct nvme_ctrl *ctrl)
 		 * devices are known to get this wrong. Use the larger of the
 		 * two values.
 		 */
-		if (ctrl->ctrl_config & NVME_CC_CRIME)
-			ready_timeout = NVME_CRTO_CRIMT(crto);
-		else
 		ready_timeout = NVME_CRTO_CRWMT(crto);
 
 		if (ready_timeout < timeout)

drivers/nvme/host/multipath.c

@@ -431,7 +431,6 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 		case NVME_CTRL_LIVE:
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
-			/* fallthru */
 			return true;
 		default:
 			break;
@@ -580,6 +579,20 @@ static int nvme_add_ns_head_cdev(struct nvme_ns_head *head)
 	return ret;
 }
 
+static void nvme_partition_scan_work(struct work_struct *work)
+{
+	struct nvme_ns_head *head =
+		container_of(work, struct nvme_ns_head, partition_scan_work);
+
+	if (WARN_ON_ONCE(!test_and_clear_bit(GD_SUPPRESS_PART_SCAN,
+					     &head->disk->state)))
+		return;
+
+	mutex_lock(&head->disk->open_mutex);
+	bdev_disk_changed(head->disk, false);
+	mutex_unlock(&head->disk->open_mutex);
+}
+
 static void nvme_requeue_work(struct work_struct *work)
 {
 	struct nvme_ns_head *head =
@@ -606,6 +619,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	bio_list_init(&head->requeue_list);
 	spin_lock_init(&head->requeue_lock);
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
+	INIT_WORK(&head->partition_scan_work, nvme_partition_scan_work);
 
 	/*
 	 * Add a multipath node if the subsystems supports multiple controllers.
@@ -629,6 +643,16 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 		return PTR_ERR(head->disk);
 	head->disk->fops = &nvme_ns_head_ops;
 	head->disk->private_data = head;
+
+	/*
+	 * We need to suppress the partition scan from occuring within the
+	 * controller's scan_work context. If a path error occurs here, the IO
+	 * will wait until a path becomes available or all paths are torn down,
+	 * but that action also occurs within scan_work, so it would deadlock.
+	 * Defer the partion scan to a different context that does not block
+	 * scan_work.
+	 */
+	set_bit(GD_SUPPRESS_PART_SCAN, &head->disk->state);
 	sprintf(head->disk->disk_name, "nvme%dn%d",
 			ctrl->subsys->instance, head->instance);
 	return 0;
@@ -655,6 +679,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			return;
 		}
 		nvme_add_ns_head_cdev(head);
+		kblockd_schedule_work(&head->partition_scan_work);
 	}
 
 	mutex_lock(&head->lock);
@@ -974,14 +999,14 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 		return;
 	if (test_and_clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
-		del_gendisk(head->disk);
-	}
 		/*
 		 * requeue I/O after NVME_NSHEAD_DISK_LIVE has been cleared
 		 * to allow multipath to fail all I/O.
 		 */
 		synchronize_srcu(&head->srcu);
 		kblockd_schedule_work(&head->requeue_work);
+		del_gendisk(head->disk);
+	}
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -991,6 +1016,7 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
 	flush_work(&head->requeue_work);
+	flush_work(&head->partition_scan_work);
 	put_disk(head->disk);
 }
 

drivers/nvme/host/nvme.h

@@ -494,6 +494,7 @@ struct nvme_ns_head {
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
+	struct work_struct	partition_scan_work;
 	struct mutex		lock;
 	unsigned long		flags;
 #define NVME_NSHEAD_DISK_LIVE	0

drivers/nvme/host/pci.c

@@ -2506,17 +2506,29 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev)
 	return 1;
 }
 
-static void nvme_pci_update_nr_queues(struct nvme_dev *dev)
+static bool nvme_pci_update_nr_queues(struct nvme_dev *dev)
 {
 	if (!dev->ctrl.tagset) {
 		nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops,
 				nvme_pci_nr_maps(dev), sizeof(struct nvme_iod));
-		return;
+		return true;
+	}
+
+	/* Give up if we are racing with nvme_dev_disable() */
+	if (!mutex_trylock(&dev->shutdown_lock))
+		return false;
+
+	/* Check if nvme_dev_disable() has been executed already */
+	if (!dev->online_queues) {
+		mutex_unlock(&dev->shutdown_lock);
+		return false;
 	}
 
 	blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
 	/* free previously allocated queues that are no longer usable */
 	nvme_free_queues(dev, dev->online_queues);
+	mutex_unlock(&dev->shutdown_lock);
+	return true;
 }
 
 static int nvme_pci_enable(struct nvme_dev *dev)
@@ -2797,7 +2809,8 @@ static void nvme_reset_work(struct work_struct *work)
 		nvme_dbbuf_set(dev);
 		nvme_unquiesce_io_queues(&dev->ctrl);
 		nvme_wait_freeze(&dev->ctrl);
-		nvme_pci_update_nr_queues(dev);
+		if (!nvme_pci_update_nr_queues(dev))
+			goto out;
 		nvme_unfreeze(&dev->ctrl);
 	} else {
 		dev_warn(dev->ctrl.device, "IO queues lost\n");

drivers/nvme/host/tcp.c

@@ -2644,10 +2644,11 @@ static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 
 	len = nvmf_get_address(ctrl, buf, size);
 
+	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
+		return len;
+
 	mutex_lock(&queue->queue_lock);
 
-	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
-		goto done;
 	ret = kernel_getsockname(queue->sock, (struct sockaddr *)&src_addr);
 	if (ret > 0) {
 		if (len > 0)
@@ -2655,7 +2656,7 @@ static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)
 		len += scnprintf(buf + len, size - len, "%ssrc_addr=%pISc\n",
 				(len) ? "," : "", &src_addr);
 	}
-done:
+
 	mutex_unlock(&queue->queue_lock);
 
 	return len;

drivers/nvme/target/loop.c

@@ -265,6 +265,13 @@ static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl)
 {
 	if (!test_and_clear_bit(NVME_LOOP_Q_LIVE, &ctrl->queues[0].flags))
 		return;
+	/*
+	 * It's possible that some requests might have been added
+	 * after admin queue is stopped/quiesced. So now start the
+	 * queue to flush these requests to the completion.
+	 */
+	nvme_unquiesce_admin_queue(&ctrl->ctrl);
+
 	nvmet_sq_destroy(&ctrl->queues[0].nvme_sq);
 	nvme_remove_admin_tag_set(&ctrl->ctrl);
 }
@@ -297,6 +304,12 @@ static void nvme_loop_destroy_io_queues(struct nvme_loop_ctrl *ctrl)
 		nvmet_sq_destroy(&ctrl->queues[i].nvme_sq);
 	}
 	ctrl->ctrl.queue_count = 1;
+	/*
+	 * It's possible that some requests might have been added
+	 * after io queue is stopped/quiesced. So now start the
+	 * queue to flush these requests to the completion.
+	 */
+	nvme_unquiesce_io_queues(&ctrl->ctrl);
 }
 
 static int nvme_loop_init_io_queues(struct nvme_loop_ctrl *ctrl)

drivers/nvme/target/passthru.c

@@ -535,10 +535,6 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 		break;
 	case nvme_admin_identify:
 		switch (req->cmd->identify.cns) {
-		case NVME_ID_CNS_CTRL:
-			req->execute = nvmet_passthru_execute_cmd;
-			req->p.use_workqueue = true;
-			return NVME_SC_SUCCESS;
 		case NVME_ID_CNS_CS_CTRL:
 			switch (req->cmd->identify.csi) {
 			case NVME_CSI_ZNS:
@@ -547,7 +543,9 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
 				return NVME_SC_SUCCESS;
 			}
 			return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+		case NVME_ID_CNS_CTRL:
 		case NVME_ID_CNS_NS:
+		case NVME_ID_CNS_NS_DESC_LIST:
 			req->execute = nvmet_passthru_execute_cmd;
 			req->p.use_workqueue = true;
 			return NVME_SC_SUCCESS;

drivers/nvme/target/rdma.c

@@ -39,6 +39,8 @@
 
 #define NVMET_RDMA_BACKLOG 128
 
+#define NVMET_RDMA_DISCRETE_RSP_TAG		-1
+
 struct nvmet_rdma_srq;
 
 struct nvmet_rdma_cmd {
@@ -75,7 +77,7 @@ struct nvmet_rdma_rsp {
 	u32			invalidate_rkey;
 
 	struct list_head	wait_list;
-	struct list_head	free_list;
+	int			tag;
 };
 
 enum nvmet_rdma_queue_state {
@@ -98,8 +100,7 @@ struct nvmet_rdma_queue {
 	struct nvmet_sq		nvme_sq;
 
 	struct nvmet_rdma_rsp	*rsps;
-	struct list_head	free_rsps;
-	spinlock_t		rsps_lock;
+	struct sbitmap		rsp_tags;
 	struct nvmet_rdma_cmd	*cmds;
 
 	struct work_struct	release_work;
@@ -172,7 +173,8 @@ static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
 static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev,
 				struct nvmet_rdma_rsp *r);
 static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
-				struct nvmet_rdma_rsp *r);
+				struct nvmet_rdma_rsp *r,
+				int tag);
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops;
 
@@ -210,15 +212,12 @@ static inline bool nvmet_rdma_need_data_out(struct nvmet_rdma_rsp *rsp)
 static inline struct nvmet_rdma_rsp *
 nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
 {
-	struct nvmet_rdma_rsp *rsp;
-	unsigned long flags;
+	struct nvmet_rdma_rsp *rsp = NULL;
+	int tag;
 
-	spin_lock_irqsave(&queue->rsps_lock, flags);
-	rsp = list_first_entry_or_null(&queue->free_rsps,
-				struct nvmet_rdma_rsp, free_list);
-	if (likely(rsp))
-		list_del(&rsp->free_list);
-	spin_unlock_irqrestore(&queue->rsps_lock, flags);
+	tag = sbitmap_get(&queue->rsp_tags);
+	if (tag >= 0)
+		rsp = &queue->rsps[tag];
 
 	if (unlikely(!rsp)) {
 		int ret;
@@ -226,13 +225,12 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
 		rsp = kzalloc(sizeof(*rsp), GFP_KERNEL);
 		if (unlikely(!rsp))
 			return NULL;
-		ret = nvmet_rdma_alloc_rsp(queue->dev, rsp);
+		ret = nvmet_rdma_alloc_rsp(queue->dev, rsp,
+				NVMET_RDMA_DISCRETE_RSP_TAG);
 		if (unlikely(ret)) {
 			kfree(rsp);
 			return NULL;
 		}
-
-		rsp->allocated = true;
 	}
 
 	return rsp;
@@ -241,17 +239,13 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue)
 static inline void
 nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 {
-	unsigned long flags;
-
-	if (unlikely(rsp->allocated)) {
+	if (unlikely(rsp->tag == NVMET_RDMA_DISCRETE_RSP_TAG)) {
 		nvmet_rdma_free_rsp(rsp->queue->dev, rsp);
 		kfree(rsp);
 		return;
 	}
 
-	spin_lock_irqsave(&rsp->queue->rsps_lock, flags);
-	list_add_tail(&rsp->free_list, &rsp->queue->free_rsps);
-	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
+	sbitmap_clear_bit(&rsp->queue->rsp_tags, rsp->tag);
 }
 
 static void nvmet_rdma_free_inline_pages(struct nvmet_rdma_device *ndev,
@@ -404,7 +398,7 @@ static void nvmet_rdma_free_cmds(struct nvmet_rdma_device *ndev,
 }
 
 static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
-		struct nvmet_rdma_rsp *r)
+		struct nvmet_rdma_rsp *r, int tag)
 {
 	/* NVMe CQE / RDMA SEND */
 	r->req.cqe = kmalloc(sizeof(*r->req.cqe), GFP_KERNEL);
@@ -432,6 +426,7 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev,
 	r->read_cqe.done = nvmet_rdma_read_data_done;
 	/* Data Out / RDMA WRITE */
 	r->write_cqe.done = nvmet_rdma_write_data_done;
+	r->tag = tag;
 
 	return 0;
 
@@ -454,21 +449,23 @@ nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue)
 {
 	struct nvmet_rdma_device *ndev = queue->dev;
 	int nr_rsps = queue->recv_queue_size * 2;
-	int ret = -EINVAL, i;
+	int ret = -ENOMEM, i;
+
+	if (sbitmap_init_node(&queue->rsp_tags, nr_rsps, -1, GFP_KERNEL,
+			NUMA_NO_NODE, false, true))
+		goto out;
 
 	queue->rsps = kcalloc(nr_rsps, sizeof(struct nvmet_rdma_rsp),
 			GFP_KERNEL);
 	if (!queue->rsps)
-		goto out;
+		goto out_free_sbitmap;
 
 	for (i = 0; i < nr_rsps; i++) {
 		struct nvmet_rdma_rsp *rsp = &queue->rsps[i];
 
-		ret = nvmet_rdma_alloc_rsp(ndev, rsp);
+		ret = nvmet_rdma_alloc_rsp(ndev, rsp, i);
 		if (ret)
 			goto out_free;
-
-		list_add_tail(&rsp->free_list, &queue->free_rsps);
 	}
 
 	return 0;
@@ -477,6 +474,8 @@ nvmet_rdma_alloc_rsps(struct nvmet_rdma_queue *queue)
 	while (--i >= 0)
 		nvmet_rdma_free_rsp(ndev, &queue->rsps[i]);
 	kfree(queue->rsps);
+out_free_sbitmap:
+	sbitmap_free(&queue->rsp_tags);
 out:
 	return ret;
 }
@@ -489,6 +488,7 @@ static void nvmet_rdma_free_rsps(struct nvmet_rdma_queue *queue)
 	for (i = 0; i < nr_rsps; i++)
 		nvmet_rdma_free_rsp(ndev, &queue->rsps[i]);
 	kfree(queue->rsps);
+	sbitmap_free(&queue->rsp_tags);
 }
 
 static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
@@ -1447,8 +1447,6 @@ nvmet_rdma_alloc_queue(struct nvmet_rdma_device *ndev,
 	INIT_LIST_HEAD(&queue->rsp_wait_list);
 	INIT_LIST_HEAD(&queue->rsp_wr_wait_list);
 	spin_lock_init(&queue->rsp_wr_wait_lock);
-	INIT_LIST_HEAD(&queue->free_rsps);
-	spin_lock_init(&queue->rsps_lock);
 	INIT_LIST_HEAD(&queue->queue_list);
 
 	queue->idx = ida_alloc(&nvmet_rdma_queue_ida, GFP_KERNEL);