Merge branch 'odp_fixes' into hmm.git

From rdma.git

Jason Gunthorpe says:

====================
This is a collection of general cleanups for ODP to clarify some of the
flows around umem creation and use of the interval tree.
====================

The branch is based on v5.3-rc5 due to dependencies, and is being taken
into hmm.git due to dependencies in the next patches.

* odp_fixes:
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  RDMA/core: Make invalidate_range a device operation
  RDMA/odp: Use kvcalloc for the dma_list and page_list
  RDMA/odp: Check for overflow when computing the umem_odp end
  RDMA/odp: Provide ib_umem_odp_release() to undo the allocs
  RDMA/odp: Split creating a umem_odp from ib_umem_get
  RDMA/odp: Make the three ways to create a umem_odp clear
  RMDA/odp: Consolidate umem_odp initialization
  RDMA/odp: Make it clearer when a umem is an implicit ODP umem
  RDMA/odp: Iterate over the whole rbtree directly
  RDMA/odp: Use the common interval tree library instead of generic
  RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

5 files changed, 138 insertions, 32 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index cc09b81fc7f4..c258a1ce4b28 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1286,6 +1286,9 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	 */
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
 		mutex_lock(&ctrl->scan_lock);
+		mutex_lock(&ctrl->subsys->lock);
+		nvme_mpath_start_freeze(ctrl->subsys);
+		nvme_mpath_wait_freeze(ctrl->subsys);
 		nvme_start_freeze(ctrl);
 		nvme_wait_freeze(ctrl);
 	}
@@ -1316,6 +1319,8 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects)
 		nvme_update_formats(ctrl);
 	if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) {
 		nvme_unfreeze(ctrl);
+		nvme_mpath_unfreeze(ctrl->subsys);
+		mutex_unlock(&ctrl->subsys->lock);
 		mutex_unlock(&ctrl->scan_lock);
 	}
 	if (effects & NVME_CMD_EFFECTS_CCC)
@@ -1715,6 +1720,7 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
+		revalidate_disk(ns->head->disk);
 	}
 #endif
 }
@@ -2311,17 +2317,15 @@ static void nvme_init_subnqn(struct nvme_subsystem *subsys, struct nvme_ctrl *ct
 	memset(subsys->subnqn + off, 0, sizeof(subsys->subnqn) - off);
 }
 
-static void __nvme_release_subsystem(struct nvme_subsystem *subsys)
+static void nvme_release_subsystem(struct device *dev)
 {
+	struct nvme_subsystem *subsys =
+		container_of(dev, struct nvme_subsystem, dev);
+
 	ida_simple_remove(&nvme_subsystems_ida, subsys->instance);
 	kfree(subsys);
 }
 
-static void nvme_release_subsystem(struct device *dev)
-{
-	__nvme_release_subsystem(container_of(dev, struct nvme_subsystem, dev));
-}
-
 static void nvme_destroy_subsystem(struct kref *ref)
 {
 	struct nvme_subsystem *subsys =
@@ -2477,7 +2481,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	mutex_lock(&nvme_subsystems_lock);
 	found = __nvme_find_get_subsystem(subsys->subnqn);
 	if (found) {
-		__nvme_release_subsystem(subsys);
+		put_device(&subsys->dev);
 		subsys = found;
 
 		if (!nvme_validate_cntlid(subsys, ctrl, id)) {
@@ -2489,6 +2493,7 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 		if (ret) {
 			dev_err(ctrl->device,
 				"failed to register subsystem device.\n");
+			put_device(&subsys->dev);
 			goto out_unlock;
 		}
 		ida_init(&subsys->ns_ida);
@@ -2511,7 +2516,6 @@ out_put_subsystem:
 	nvme_put_subsystem(subsys);
 out_unlock:
 	mutex_unlock(&nvme_subsystems_lock);
-	put_device(&subsys->dev);
 	return ret;
 }
 
@@ -3573,6 +3577,13 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 	struct nvme_ns *ns, *next;
 	LIST_HEAD(ns_list);
 
+	/*
+	 * make sure to requeue I/O to all namespaces as these
+	 * might result from the scan itself and must complete
+	 * for the scan_work to make progress
+	 */
+	nvme_mpath_clear_ctrl_paths(ctrl);
+
 	/* prevent racing with ns scanning */
 	flush_work(&ctrl->scan_work);
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index a9a927677970..888d4543894e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -12,9 +12,34 @@ module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
 
-inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
 {
-	return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
+	struct nvme_ns_head *h;
+
+	lockdep_assert_held(&subsys->lock);
+	list_for_each_entry(h, &subsys->nsheads, entry)
+		if (h->disk)
+			blk_mq_unfreeze_queue(h->disk->queue);
+}
+
+void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
+{
+	struct nvme_ns_head *h;
+
+	lockdep_assert_held(&subsys->lock);
+	list_for_each_entry(h, &subsys->nsheads, entry)
+		if (h->disk)
+			blk_mq_freeze_queue_wait(h->disk->queue);
+}
+
+void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
+{
+	struct nvme_ns_head *h;
+
+	lockdep_assert_held(&subsys->lock);
+	list_for_each_entry(h, &subsys->nsheads, entry)
+		if (h->disk)
+			blk_freeze_queue_start(h->disk->queue);
 }
 
 /*
@@ -109,18 +134,34 @@ static const char *nvme_ana_state_names[] = {
 	[NVME_ANA_CHANGE]		= "change",
 };
 
-void nvme_mpath_clear_current_path(struct nvme_ns *ns)
+bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
 	struct nvme_ns_head *head = ns->head;
+	bool changed = false;
 	int node;
 
 	if (!head)
-		return;
+		goto out;
 
 	for_each_node(node) {
-		if (ns == rcu_access_pointer(head->current_path[node]))
+		if (ns == rcu_access_pointer(head->current_path[node])) {
 			rcu_assign_pointer(head->current_path[node], NULL);
+			changed = true;
+		}
 	}
+out:
+	return changed;
+}
+
+void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
+{
+	struct nvme_ns *ns;
+
+	mutex_lock(&ctrl->scan_lock);
+	list_for_each_entry(ns, &ctrl->namespaces, list)
+		if (nvme_mpath_clear_current_path(ns))
+			kblockd_schedule_work(&ns->head->requeue_work);
+	mutex_unlock(&ctrl->scan_lock);
 }
 
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
@@ -231,6 +272,24 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	return ns;
 }
 
+static bool nvme_available_path(struct nvme_ns_head *head)
+{
+	struct nvme_ns *ns;
+
+	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		switch (ns->ctrl->state) {
+		case NVME_CTRL_LIVE:
+		case NVME_CTRL_RESETTING:
+		case NVME_CTRL_CONNECTING:
+			/* fallthru */
+			return true;
+		default:
+			break;
+		}
+	}
+	return false;
+}
+
 static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 		struct bio *bio)
 {
@@ -257,14 +316,14 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q,
 				      disk_devt(ns->head->disk),
 				      bio->bi_iter.bi_sector);
 		ret = direct_make_request(bio);
-	} else if (!list_empty_careful(&head->list)) {
-		dev_warn_ratelimited(dev, "no path available - requeuing I/O\n");
+	} else if (nvme_available_path(head)) {
+		dev_warn_ratelimited(dev, "no usable path - requeuing I/O\n");
 
 		spin_lock_irq(&head->requeue_lock);
 		bio_list_add(&head->requeue_list, bio);
 		spin_unlock_irq(&head->requeue_lock);
 	} else {
-		dev_warn_ratelimited(dev, "no path - failing I/O\n");
+		dev_warn_ratelimited(dev, "no available path - failing I/O\n");
 
 		bio->bi_status = BLK_STS_IOERR;
 		bio_endio(bio);
@@ -622,7 +681,8 @@ int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 {
 	int error;
 
-	if (!nvme_ctrl_use_ana(ctrl))
+	/* check if multipath is enabled and we have the capability */
+	if (!multipath || !ctrl->subsys || !(ctrl->subsys->cmic & (1 << 3)))
 		return 0;
 
 	ctrl->anacap = id->anacap;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 716a876119c8..778b3a0b6adb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -485,7 +485,14 @@ extern const struct attribute_group *nvme_ns_id_attr_groups[];
 extern const struct block_device_operations nvme_ns_head_ops;
 
 #ifdef CONFIG_NVME_MULTIPATH
-bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return ctrl->ana_log_buf != NULL;
+}
+
+void nvme_mpath_unfreeze(struct nvme_subsystem *subsys);
+void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys);
+void nvme_mpath_start_freeze(struct nvme_subsystem *subsys);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
@@ -496,7 +503,8 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head);
 int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
-void nvme_mpath_clear_current_path(struct nvme_ns *ns);
+bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
+void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
@@ -544,7 +552,11 @@ static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 }
-static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
+static inline bool nvme_mpath_clear_current_path(struct nvme_ns *ns)
+{
+	return false;
+}
+static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 }
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
@@ -564,6 +576,15 @@ static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
 {
 }
+static inline void nvme_mpath_unfreeze(struct nvme_subsystem *subsys)
+{
+}
+static inline void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys)
+{
+}
+static inline void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index bb970ca82517..6bd9b1033965 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2254,9 +2254,7 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	if (!dev->ctrl.tagset) {
 		dev->tagset.ops = &nvme_mq_ops;
 		dev->tagset.nr_hw_queues = dev->online_queues - 1;
-		dev->tagset.nr_maps = 1; /* default */
-		if (dev->io_queues[HCTX_TYPE_READ])
-			dev->tagset.nr_maps++;
+		dev->tagset.nr_maps = 2; /* default + read */
 		if (dev->io_queues[HCTX_TYPE_POLL])
 			dev->tagset.nr_maps++;
 		dev->tagset.timeout = NVME_IO_TIMEOUT;
@@ -2697,7 +2695,7 @@ static void nvme_async_probe(void *data, async_cookie_t cookie)
 {
 	struct nvme_dev *dev = data;
 
-	nvme_reset_ctrl_sync(&dev->ctrl);
+	flush_work(&dev->ctrl.reset_work);
 	flush_work(&dev->ctrl.scan_work);
 	nvme_put_ctrl(&dev->ctrl);
 }
@@ -2763,6 +2761,7 @@ static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
+	nvme_reset_ctrl(&dev->ctrl);
 	nvme_get_ctrl(&dev->ctrl);
 	async_schedule(nvme_async_probe, dev);
 
@@ -2848,7 +2847,7 @@ static int nvme_resume(struct device *dev)
 	struct nvme_dev *ndev = pci_get_drvdata(to_pci_dev(dev));
 	struct nvme_ctrl *ctrl = &ndev->ctrl;
 
-	if (pm_resume_via_firmware() || !ctrl->npss ||
+	if (ndev->last_ps == U32_MAX ||
 	    nvme_set_power_state(ctrl, ndev->last_ps) != 0)
 		nvme_reset_ctrl(ctrl);
 	return 0;
@@ -2861,6 +2860,8 @@ static int nvme_suspend(struct device *dev)
 	struct nvme_ctrl *ctrl = &ndev->ctrl;
 	int ret = -EBUSY;
 
+	ndev->last_ps = U32_MAX;
+
 	/*
 	 * The platform does not remove power for a kernel managed suspend so
 	 * use host managed nvme power settings for lowest idle power if
@@ -2868,8 +2869,14 @@ static int nvme_suspend(struct device *dev)
 	 * shutdown.  But if the firmware is involved after the suspend or the
 	 * device does not support any non-default power states, shut down the
 	 * device fully.
+	 *
+	 * If ASPM is not enabled for the device, shut down the device and allow
+	 * the PCI bus layer to put it into D3 in order to take the PCIe link
+	 * down, so as to allow the platform to achieve its minimum low-power
+	 * state (which may not be possible if the link is up).
 	 */
-	if (pm_suspend_via_firmware() || !ctrl->npss) {
+	if (pm_suspend_via_firmware() || !ctrl->npss ||
+	    !pcie_aspm_enabled(pdev)) {
 		nvme_dev_disable(ndev, true);
 		return 0;
 	}
@@ -2882,7 +2889,6 @@ static int nvme_suspend(struct device *dev)
 	    ctrl->state != NVME_CTRL_ADMIN_ONLY)
 		goto unfreeze;
 
-	ndev->last_ps = 0;
 	ret = nvme_get_power_state(ctrl, &ndev->last_ps);
 	if (ret < 0)
 		goto unfreeze;
@@ -3029,6 +3035,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
 	{ PCI_DEVICE(0x1d1d, 0x2601),	/* CNEX Granby */
 		.driver_data = NVME_QUIRK_LIGHTNVM, },
+	{ PCI_DEVICE(0x10ec, 0x5762),   /* ADATA SX6000LNP */
+		.driver_data = NVME_QUIRK_IGNORE_DEV_SUBNQN, },
 	{ PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index a249db528d54..1a6449bc547b 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -562,13 +562,17 @@ out_destroy_cm_id:
 	return ret;
 }
 
+static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
+{
+	rdma_disconnect(queue->cm_id);
+	ib_drain_qp(queue->qp);
+}
+
 static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue)
 {
 	if (!test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags))
 		return;
-
-	rdma_disconnect(queue->cm_id);
-	ib_drain_qp(queue->qp);
+	__nvme_rdma_stop_queue(queue);
 }
 
 static void nvme_rdma_free_queue(struct nvme_rdma_queue *queue)
@@ -607,11 +611,13 @@ static int nvme_rdma_start_queue(struct nvme_rdma_ctrl *ctrl, int idx)
 	else
 		ret = nvmf_connect_admin_queue(&ctrl->ctrl);
 
-	if (!ret)
+	if (!ret) {
 		set_bit(NVME_RDMA_Q_LIVE, &queue->flags);
-	else
+	} else {
+		__nvme_rdma_stop_queue(queue);
 		dev_info(ctrl->ctrl.device,
 			"failed to connect queue: %d ret=%d\n", idx, ret);
+	}
 	return ret;
 }