Merge tag 'nvme-6.5-2023-07-13' of git://git.infradead.org/nvme into block-6.5

Pull NVMe fixes from Keith:

"nvme fixes for Linux 6.5

 - Don't require quirk to use duplicate namespace identifiers
   (Christoph, Sagi)
 - One more BOGUS_NID quirk (Pankaj)
 - IO timeout and error hanlding fixes for PCI (Keith)
 - Enhanced metadata format mask fix (Ankit)
 - Association race condition fix for fibre channel (Michael)
 - Correct debugfs error checks (Minjie)
 - Use PAGE_SECTORS_SHIFT where needed (Damien)
 - Reduce kernel logs for legacy nguid attribute (Keith)
 - Use correct dma direction when unmapping metadata (Ming)"

* tag 'nvme-6.5-2023-07-13' of git://git.infradead.org/nvme:
  nvme-pci: fix DMA direction of unmapping integrity data
  nvme: don't reject probe due to duplicate IDs for single-ported PCIe devices
  nvme: ensure disabling pairs with unquiesce
  nvme-fc: fix race between error recovery and creating association
  nvme-fc: return non-zero status code when fails to create association
  nvme: fix parameter check in nvme_fault_inject_init()
  nvme: warn only once for legacy uuid attribute
  nvme: fix the NVME_ID_NS_NVM_STS_MASK definition
  nvmet: use PAGE_SECTORS_SHIFT
  nvme: add BOGUS_NID quirk for Samsung SM953

Author: axboe

drivers/nvme/host/core.c

@@ -3431,10 +3431,40 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 
 	ret = nvme_global_check_duplicate_ids(ctrl->subsys, &info->ids);
 	if (ret) {
-		dev_err(ctrl->device,
-			"globally duplicate IDs for nsid %d\n", info->nsid);
+		/*
+		 * We've found two different namespaces on two different
+		 * subsystems that report the same ID.  This is pretty nasty
+		 * for anything that actually requires unique device
+		 * identification.  In the kernel we need this for multipathing,
+		 * and in user space the /dev/disk/by-id/ links rely on it.
+		 *
+		 * If the device also claims to be multi-path capable back off
+		 * here now and refuse the probe the second device as this is a
+		 * recipe for data corruption.  If not this is probably a
+		 * cheap consumer device if on the PCIe bus, so let the user
+		 * proceed and use the shiny toy, but warn that with changing
+		 * probing order (which due to our async probing could just be
+		 * device taking longer to startup) the other device could show
+		 * up at any time.
+		 */
 		nvme_print_device_info(ctrl);
-		return ret;
+		if ((ns->ctrl->ops->flags & NVME_F_FABRICS) || /* !PCIe */
+		    ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) &&
+		     info->is_shared)) {
+			dev_err(ctrl->device,
+				"ignoring nsid %d because of duplicate IDs\n",
+				info->nsid);
+			return ret;
+		}
+
+		dev_err(ctrl->device,
+			"clearing duplicate IDs for nsid %d\n", info->nsid);
+		dev_err(ctrl->device,
+			"use of /dev/disk/by-id/ may cause data corruption\n");
+		memset(&info->ids.nguid, 0, sizeof(info->ids.nguid));
+		memset(&info->ids.uuid, 0, sizeof(info->ids.uuid));
+		memset(&info->ids.eui64, 0, sizeof(info->ids.eui64));
+		ctrl->quirks |= NVME_QUIRK_BOGUS_NID;
 	}
 
 	mutex_lock(&ctrl->subsys->lock);

drivers/nvme/host/fault_inject.c

@@ -27,7 +27,7 @@ void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj,
 
 	/* create debugfs directory and attribute */
 	parent = debugfs_create_dir(dev_name, NULL);
-	if (!parent) {
+	if (IS_ERR(parent)) {
 		pr_warn("%s: failed to create debugfs directory\n", dev_name);
 		return;
 	}

drivers/nvme/host/fc.c

@@ -2548,14 +2548,24 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg)
 	 * the controller.  Abort any ios on the association and let the
 	 * create_association error path resolve things.
 	 */
-	if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) {
-		__nvme_fc_abort_outstanding_ios(ctrl, true);
+	enum nvme_ctrl_state state;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrl->lock, flags);
+	state = ctrl->ctrl.state;
+	if (state == NVME_CTRL_CONNECTING) {
 		set_bit(ASSOC_FAILED, &ctrl->flags);
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+		__nvme_fc_abort_outstanding_ios(ctrl, true);
+		dev_warn(ctrl->ctrl.device,
+			"NVME-FC{%d}: transport error during (re)connect\n",
+			ctrl->cnum);
 		return;
 	}
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	/* Otherwise, only proceed if in LIVE state - e.g. on first error */
-	if (ctrl->ctrl.state != NVME_CTRL_LIVE)
+	if (state != NVME_CTRL_LIVE)
 		return;
 
 	dev_warn(ctrl->ctrl.device,
@@ -3110,7 +3120,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	 */
 
 	ret = nvme_enable_ctrl(&ctrl->ctrl);
-	if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
+	if (ret)
 		goto out_disconnect_admin_queue;
 
 	ctrl->ctrl.max_segments = ctrl->lport->ops->max_sgl_segments;
@@ -3120,7 +3132,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	nvme_unquiesce_admin_queue(&ctrl->ctrl);
 
 	ret = nvme_init_ctrl_finish(&ctrl->ctrl, false);
-	if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
+	if (ret)
 		goto out_disconnect_admin_queue;
 
 	/* sanity checks */
@@ -3165,10 +3179,16 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
-	if (ret || test_bit(ASSOC_FAILED, &ctrl->flags))
-		goto out_term_aen_ops;
 
+	spin_lock_irqsave(&ctrl->lock, flags);
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
+	if (ret) {
+		spin_unlock_irqrestore(&ctrl->lock, flags);
+		goto out_term_aen_ops;
+	}
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
+	spin_unlock_irqrestore(&ctrl->lock, flags);
 
 	ctrl->ctrl.nr_reconnects = 0;
 
@@ -3180,6 +3200,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 out_term_aen_ops:
 	nvme_fc_term_aen_ops(ctrl);
 out_disconnect_admin_queue:
+	dev_warn(ctrl->ctrl.device,
+		"NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n",
+		ctrl->cnum, ctrl->association_id, ret);
 	/* send a Disconnect(association) LS to fc-nvme target */
 	nvme_fc_xmt_disconnect_assoc(ctrl);
 	spin_lock_irqsave(&ctrl->lock, flags);

drivers/nvme/host/pci.c

@@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
 	        struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
 
 		dma_unmap_page(dev->dev, iod->meta_dma,
-			       rq_integrity_vec(req)->bv_len, rq_data_dir(req));
+			       rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
 	}
 
 	if (blk_rq_nr_phys_segments(req))
@@ -1298,9 +1298,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 */
 	if (nvme_should_reset(dev, csts)) {
 		nvme_warn_reset(dev, csts);
-		nvme_dev_disable(dev, false);
-		nvme_reset_ctrl(&dev->ctrl);
-		return BLK_EH_DONE;
+		goto disable;
 	}
 
 	/*
@@ -1351,10 +1349,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 			 "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);
-
-		return BLK_EH_DONE;
+		goto disable;
 	}
 
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
@@ -1391,6 +1386,15 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * as the device then is in a faulty state.
 	 */
 	return BLK_EH_RESET_TIMER;
+
+disable:
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+		return BLK_EH_DONE;
+
+	nvme_dev_disable(dev, false);
+	if (nvme_try_sched_reset(&dev->ctrl))
+		nvme_unquiesce_io_queues(&dev->ctrl);
+	return BLK_EH_DONE;
 }
 
 static void nvme_free_queue(struct nvme_queue *nvmeq)
@@ -3278,6 +3282,10 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev,
 	case pci_channel_io_frozen:
 		dev_warn(dev->ctrl.device,
 			"frozen state error detected, reset controller\n");
+		if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) {
+			nvme_dev_disable(dev, true);
+			return PCI_ERS_RESULT_DISCONNECT;
+		}
 		nvme_dev_disable(dev, false);
 		return PCI_ERS_RESULT_NEED_RESET;
 	case pci_channel_io_perm_failure:
@@ -3294,7 +3302,8 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev)
 
 	dev_info(dev->ctrl.device, "restart after slot reset\n");
 	pci_restore_state(pdev);
-	nvme_reset_ctrl(&dev->ctrl);
+	if (!nvme_try_sched_reset(&dev->ctrl))
+		nvme_unquiesce_io_queues(&dev->ctrl);
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
@@ -3396,6 +3405,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x144d, 0xa809),   /* Samsung MZALQ256HBJD 256G */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
+	{ PCI_DEVICE(0x144d, 0xa802),   /* Samsung SM953 */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc4, 0x6303),   /* UMIS RPJTJ512MGE1QDY 512G */
 		.driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, },
 	{ PCI_DEVICE(0x1cc4, 0x6302),   /* UMIS RPJTJ256MGE1QDY 256G */

drivers/nvme/host/sysfs.c

@@ -92,7 +92,7 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	 * we have no UUID set
 	 */
 	if (uuid_is_null(&ids->uuid)) {
-		dev_warn_ratelimited(dev,
+		dev_warn_once(dev,
 			"No UUID available providing old NGUID\n");
 		return sysfs_emit(buf, "%pU\n", ids->nguid);
 	}

drivers/nvme/target/loop.c

@@ -373,7 +373,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
 		goto out_cleanup_tagset;
 
 	ctrl->ctrl.max_hw_sectors =
-		(NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9);
+		(NVME_LOOP_MAX_SEGMENTS - 1) << PAGE_SECTORS_SHIFT;
 
 	nvme_unquiesce_admin_queue(&ctrl->ctrl);
 

drivers/nvme/target/passthru.c

@@ -102,14 +102,14 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req)
 	 * which depends on the host's memory fragementation. To solve this,
 	 * ensure mdts is limited to the pages equal to the number of segments.
 	 */
-	max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9),
+	max_hw_sectors = min_not_zero(pctrl->max_segments << PAGE_SECTORS_SHIFT,
 				      pctrl->max_hw_sectors);
 
 	/*
 	 * nvmet_passthru_map_sg is limitted to using a single bio so limit
 	 * the mdts based on BIO_MAX_VECS as well
 	 */
-	max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9),
+	max_hw_sectors = min_not_zero(BIO_MAX_VECS << PAGE_SECTORS_SHIFT,
 				      max_hw_sectors);
 
 	page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12;

include/linux/nvme.h

@@ -473,7 +473,7 @@ struct nvme_id_ns_nvm {
 };
 
 enum {
-	NVME_ID_NS_NVM_STS_MASK		= 0x3f,
+	NVME_ID_NS_NVM_STS_MASK		= 0x7f,
 	NVME_ID_NS_NVM_GUARD_SHIFT	= 7,
 	NVME_ID_NS_NVM_GUARD_MASK	= 0x3,
 };