Merge tag 'libnvdimm-for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "Aside from the recently added pmem sub-division support these have
  been in -next for several releases with no reported issues. The sub-
  division support was included in next-20161010 with no reported
  issues. It passes all unit tests including new tests for all the new
  functionality below.

  Summary:

   - PMEM sub-division support: Allow a single PMEM region to be divided
     into multiple namespaces. Originally, ~2 years ago, it was thought
     that partitions of a /dev/pmemX block device could handle
     sub-allocations of persistent memory for different use cases. With
     the decision to not support DAX mappings of raw block-devices, and
     the genesis of device-dax, the need for having multiple
     pmem-namespace per region has grown.

   - Device-DAX unified inode: In support of dynamic-resizing of a
     device-dax instance the kernel arranges for all mappings of a
     device-dax node to share the same inode. This allows unmap /
     truncate / invalidation events to affect all instances of the
     device similar to the behavior of mmap on block devices.

   - Hardware error scrubbing reworks: The original address-range-scrub
     and badblocks tracking solution allowed clearing entries at the
     individual namespace level, but it failed to clear the internal
     list of media errors maintained at the bus level. The result was
     that the next scrub or namespace disable/re-enable event would
     restore the cleared badblocks, but now that is fixed. The v4.8
     kernel introduced an auto-scrub-on-machine-check behavior to
     repopulate the badblocks list. Now, in v4.9, the auto-scrub
     behavior can be disabled and simply arrange for the error reported
     in the machine-check to be added to the list.

   - DIMM health-event notification support: ACPI 6.1 defines a
     notification event code that can be send to ACPI NVDIMM devices. A
     poll(2) capable file descriptor for these events can be obtained
     from the nmemX/nfit/flags sysfs-attribute of a libnvdimm memory
     device.

   - Miscellaneous fixes: NVDIMM-N probe error, device-dax build error,
     and a change to dedup the flush hint list to not flush the memory
     controller more than necessary"

* tag 'libnvdimm-for-4.9' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (39 commits)
  /dev/dax: fix Kconfig dependency build breakage
  dax: use correct dev_t value
  dax: convert devm_create_dax_dev to PTR_ERR
  libnvdimm, namespace: allow creation of multiple pmem-namespaces per region
  libnvdimm, namespace: lift single pmem limit in scan_labels()
  libnvdimm, namespace: filter out of range labels in scan_labels()
  libnvdimm, namespace: enable allocation of multiple pmem namespaces
  libnvdimm, namespace: update label implementation for multi-pmem
  libnvdimm, namespace: expand pmem device naming scheme for multi-pmem
  libnvdimm, region: update nd_region_available_dpa() for multi-pmem support
  libnvdimm, namespace: sort namespaces by dpa at init
  libnvdimm, namespace: allow multiple pmem-namespaces per region at scan time
  tools/testing/nvdimm: support for sub-dividing a pmem region
  libnvdimm, namespace: unify blk and pmem label scanning
  libnvdimm, namespace: refactor uuid_show() into a namespace_to_uuid() helper
  libnvdimm, label: convert label tracking to a linked list
  libnvdimm, region: move region-mapping input-paramters to nd_mapping_desc
  nvdimm: reduce duplicated wpq flushes
  libnvdimm: clear the internal poison_list when clearing badblocks
  pmem: reduce kmap_atomic sections to the memcpys only
  ...

drivers/acpi/nfit/core.c

@@ -886,6 +886,58 @@ static ssize_t revision_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(revision);
 
+static ssize_t hw_error_scrub_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+	return sprintf(buf, "%d\n", acpi_desc->scrub_mode);
+}
+
+/*
+ * The 'hw_error_scrub' attribute can have the following values written to it:
+ * '0': Switch to the default mode where an exception will only insert
+ *      the address of the memory error into the poison and badblocks lists.
+ * '1': Enable a full scrub to happen if an exception for a memory error is
+ *      received.
+ */
+static ssize_t hw_error_scrub_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t size)
+{
+	struct nvdimm_bus_descriptor *nd_desc;
+	ssize_t rc;
+	long val;
+
+	rc = kstrtol(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	device_lock(dev);
+	nd_desc = dev_get_drvdata(dev);
+	if (nd_desc) {
+		struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
+
+		switch (val) {
+		case HW_ERROR_SCRUB_ON:
+			acpi_desc->scrub_mode = HW_ERROR_SCRUB_ON;
+			break;
+		case HW_ERROR_SCRUB_OFF:
+			acpi_desc->scrub_mode = HW_ERROR_SCRUB_OFF;
+			break;
+		default:
+			rc = -EINVAL;
+			break;
+		}
+	}
+	device_unlock(dev);
+	if (rc)
+		return rc;
+	return size;
+}
+static DEVICE_ATTR_RW(hw_error_scrub);
+
 /*
  * This shows the number of full Address Range Scrubs that have been
  * completed since driver load time. Userspace can wait on this using
@@ -958,6 +1010,7 @@ static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n)
 static struct attribute *acpi_nfit_attributes[] = {
 	&dev_attr_revision.attr,
 	&dev_attr_scrub.attr,
+	&dev_attr_hw_error_scrub.attr,
 	NULL,
 };
 
@@ -1256,6 +1309,44 @@ static struct nvdimm *acpi_nfit_dimm_by_handle(struct acpi_nfit_desc *acpi_desc,
 	return NULL;
 }
 
+void __acpi_nvdimm_notify(struct device *dev, u32 event)
+{
+	struct nfit_mem *nfit_mem;
+	struct acpi_nfit_desc *acpi_desc;
+
+	dev_dbg(dev->parent, "%s: %s: event: %d\n", dev_name(dev), __func__,
+			event);
+
+	if (event != NFIT_NOTIFY_DIMM_HEALTH) {
+		dev_dbg(dev->parent, "%s: unknown event: %d\n", dev_name(dev),
+				event);
+		return;
+	}
+
+	acpi_desc = dev_get_drvdata(dev->parent);
+	if (!acpi_desc)
+		return;
+
+	/*
+	 * If we successfully retrieved acpi_desc, then we know nfit_mem data
+	 * is still valid.
+	 */
+	nfit_mem = dev_get_drvdata(dev);
+	if (nfit_mem && nfit_mem->flags_attr)
+		sysfs_notify_dirent(nfit_mem->flags_attr);
+}
+EXPORT_SYMBOL_GPL(__acpi_nvdimm_notify);
+
+static void acpi_nvdimm_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct acpi_device *adev = data;
+	struct device *dev = &adev->dev;
+
+	device_lock(dev->parent);
+	__acpi_nvdimm_notify(dev, event);
+	device_unlock(dev->parent);
+}
+
 static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_mem *nfit_mem, u32 device_handle)
 {
@@ -1280,6 +1371,13 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 		return force_enable_dimms ? 0 : -ENODEV;
 	}
 
+	if (ACPI_FAILURE(acpi_install_notify_handler(adev_dimm->handle,
+		ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify, adev_dimm))) {
+		dev_err(dev, "%s: notification registration failed\n",
+				dev_name(&adev_dimm->dev));
+		return -ENXIO;
+	}
+
 	/*
 	 * Until standardization materializes we need to consider 4
 	 * different command sets.  Note, that checking for function0 (bit0)
@@ -1318,18 +1416,41 @@ static int acpi_nfit_add_dimm(struct acpi_nfit_desc *acpi_desc,
 	return 0;
 }
 
+static void shutdown_dimm_notify(void *data)
+{
+	struct acpi_nfit_desc *acpi_desc = data;
+	struct nfit_mem *nfit_mem;
+
+	mutex_lock(&acpi_desc->init_mutex);
+	/*
+	 * Clear out the nfit_mem->flags_attr and shut down dimm event
+	 * notifications.
+	 */
+	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+		struct acpi_device *adev_dimm = nfit_mem->adev;
+
+		if (nfit_mem->flags_attr) {
+			sysfs_put(nfit_mem->flags_attr);
+			nfit_mem->flags_attr = NULL;
+		}
+		if (adev_dimm)
+			acpi_remove_notify_handler(adev_dimm->handle,
+					ACPI_DEVICE_NOTIFY, acpi_nvdimm_notify);
+	}
+	mutex_unlock(&acpi_desc->init_mutex);
+}
+
 static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 {
 	struct nfit_mem *nfit_mem;
-	int dimm_count = 0;
+	int dimm_count = 0, rc;
+	struct nvdimm *nvdimm;
 
 	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
 		struct acpi_nfit_flush_address *flush;
 		unsigned long flags = 0, cmd_mask;
-		struct nvdimm *nvdimm;
 		u32 device_handle;
 		u16 mem_flags;
-		int rc;
 
 		device_handle = __to_nfit_memdev(nfit_mem)->device_handle;
 		nvdimm = acpi_nfit_dimm_by_handle(acpi_desc, device_handle);
@@ -1382,7 +1503,30 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc)
 
 	}
 
-	return nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count);
+	rc = nvdimm_bus_check_dimm_count(acpi_desc->nvdimm_bus, dimm_count);
+	if (rc)
+		return rc;
+
+	/*
+	 * Now that dimms are successfully registered, and async registration
+	 * is flushed, attempt to enable event notification.
+	 */
+	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+		struct kernfs_node *nfit_kernfs;
+
+		nvdimm = nfit_mem->nvdimm;
+		nfit_kernfs = sysfs_get_dirent(nvdimm_kobj(nvdimm)->sd, "nfit");
+		if (nfit_kernfs)
+			nfit_mem->flags_attr = sysfs_get_dirent(nfit_kernfs,
+					"flags");
+		sysfs_put(nfit_kernfs);
+		if (!nfit_mem->flags_attr)
+			dev_warn(acpi_desc->dev, "%s: notifications disabled\n",
+					nvdimm_name(nvdimm));
+	}
+
+	return devm_add_action_or_reset(acpi_desc->dev, shutdown_dimm_notify,
+			acpi_desc);
 }
 
 static void acpi_nfit_init_dsms(struct acpi_nfit_desc *acpi_desc)
@@ -1491,9 +1635,9 @@ static int acpi_nfit_init_interleave_set(struct acpi_nfit_desc *acpi_desc,
 	if (!info)
 		return -ENOMEM;
 	for (i = 0; i < nr; i++) {
-		struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
+		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
 		struct nfit_set_info_map *map = &info->mapping[i];
-		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+		struct nvdimm *nvdimm = mapping->nvdimm;
 		struct nfit_mem *nfit_mem = nvdimm_provider_data(nvdimm);
 		struct acpi_nfit_memory_map *memdev = memdev_from_spa(acpi_desc,
 				spa->range_index, i);
@@ -1917,7 +2061,7 @@ static int acpi_nfit_insert_resource(struct acpi_nfit_desc *acpi_desc,
 }
 
 static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
-		struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc,
+		struct nd_mapping_desc *mapping, struct nd_region_desc *ndr_desc,
 		struct acpi_nfit_memory_map *memdev,
 		struct nfit_spa *nfit_spa)
 {
@@ -1934,12 +2078,12 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 		return -ENODEV;
 	}
 
-	nd_mapping->nvdimm = nvdimm;
+	mapping->nvdimm = nvdimm;
 	switch (nfit_spa_type(spa)) {
 	case NFIT_SPA_PM:
 	case NFIT_SPA_VOLATILE:
-		nd_mapping->start = memdev->address;
-		nd_mapping->size = memdev->region_size;
+		mapping->start = memdev->address;
+		mapping->size = memdev->region_size;
 		break;
 	case NFIT_SPA_DCR:
 		nfit_mem = nvdimm_provider_data(nvdimm);
@@ -1947,13 +2091,13 @@ static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc,
 			dev_dbg(acpi_desc->dev, "spa%d %s missing bdw\n",
 					spa->range_index, nvdimm_name(nvdimm));
 		} else {
-			nd_mapping->size = nfit_mem->bdw->capacity;
-			nd_mapping->start = nfit_mem->bdw->start_address;
+			mapping->size = nfit_mem->bdw->capacity;
+			mapping->start = nfit_mem->bdw->start_address;
 			ndr_desc->num_lanes = nfit_mem->bdw->windows;
 			blk_valid = 1;
 		}
 
-		ndr_desc->nd_mapping = nd_mapping;
+		ndr_desc->mapping = mapping;
 		ndr_desc->num_mappings = blk_valid;
 		ndbr_desc = to_blk_region_desc(ndr_desc);
 		ndbr_desc->enable = acpi_nfit_blk_region_enable;
@@ -1979,7 +2123,7 @@ static bool nfit_spa_is_virtual(struct acpi_nfit_system_address *spa)
 static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 		struct nfit_spa *nfit_spa)
 {
-	static struct nd_mapping nd_mappings[ND_MAX_MAPPINGS];
+	static struct nd_mapping_desc mappings[ND_MAX_MAPPINGS];
 	struct acpi_nfit_system_address *spa = nfit_spa->spa;
 	struct nd_blk_region_desc ndbr_desc;
 	struct nd_region_desc *ndr_desc;
@@ -1998,7 +2142,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 	}
 
 	memset(&res, 0, sizeof(res));
-	memset(&nd_mappings, 0, sizeof(nd_mappings));
+	memset(&mappings, 0, sizeof(mappings));
 	memset(&ndbr_desc, 0, sizeof(ndbr_desc));
 	res.start = spa->address;
 	res.end = res.start + spa->length - 1;
@@ -2014,7 +2158,7 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 
 	list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) {
 		struct acpi_nfit_memory_map *memdev = nfit_memdev->memdev;
-		struct nd_mapping *nd_mapping;
+		struct nd_mapping_desc *mapping;
 
 		if (memdev->range_index != spa->range_index)
 			continue;
@@ -2023,14 +2167,14 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc,
 					spa->range_index, ND_MAX_MAPPINGS);
 			return -ENXIO;
 		}
-		nd_mapping = &nd_mappings[count++];
-		rc = acpi_nfit_init_mapping(acpi_desc, nd_mapping, ndr_desc,
+		mapping = &mappings[count++];
+		rc = acpi_nfit_init_mapping(acpi_desc, mapping, ndr_desc,
 				memdev, nfit_spa);
 		if (rc)
 			goto out;
 	}
 
-	ndr_desc->nd_mapping = nd_mappings;
+	ndr_desc->mapping = mappings;
 	ndr_desc->num_mappings = count;
 	rc = acpi_nfit_init_interleave_set(acpi_desc, ndr_desc, spa);
 	if (rc)
@@ -2678,29 +2822,30 @@ static int acpi_nfit_remove(struct acpi_device *adev)
 	return 0;
 }
 
-static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
+void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event)
 {
-	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(&adev->dev);
+	struct acpi_nfit_desc *acpi_desc = dev_get_drvdata(dev);
 	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
-	struct device *dev = &adev->dev;
 	union acpi_object *obj;
 	acpi_status status;
 	int ret;
 
 	dev_dbg(dev, "%s: event: %d\n", __func__, event);
 
-	device_lock(dev);
+	if (event != NFIT_NOTIFY_UPDATE)
+		return;
+
 	if (!dev->driver) {
 		/* dev->driver may be null if we're being removed */
 		dev_dbg(dev, "%s: no driver found for dev\n", __func__);
-		goto out_unlock;
+		return;
 	}
 
 	if (!acpi_desc) {
 		acpi_desc = devm_kzalloc(dev, sizeof(*acpi_desc), GFP_KERNEL);
 		if (!acpi_desc)
-			goto out_unlock;
-		acpi_nfit_desc_init(acpi_desc, &adev->dev);
+			return;
+		acpi_nfit_desc_init(acpi_desc, dev);
 	} else {
 		/*
 		 * Finish previous registration before considering new
@@ -2710,10 +2855,10 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 	}
 
 	/* Evaluate _FIT */
-	status = acpi_evaluate_object(adev->handle, "_FIT", NULL, &buf);
+	status = acpi_evaluate_object(handle, "_FIT", NULL, &buf);
 	if (ACPI_FAILURE(status)) {
 		dev_err(dev, "failed to evaluate _FIT\n");
-		goto out_unlock;
+		return;
 	}
 
 	obj = buf.pointer;
@@ -2725,9 +2870,14 @@ static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
 	} else
 		dev_err(dev, "Invalid _FIT\n");
 	kfree(buf.pointer);
+}
+EXPORT_SYMBOL_GPL(__acpi_nfit_notify);
 
- out_unlock:
-	device_unlock(dev);
+static void acpi_nfit_notify(struct acpi_device *adev, u32 event)
+{
+	device_lock(&adev->dev);
+	__acpi_nfit_notify(&adev->dev, adev->handle, event);
+	device_unlock(&adev->dev);
 }
 
 static const struct acpi_device_id acpi_nfit_ids[] = {

drivers/acpi/nfit/mce.c

@@ -14,6 +14,7 @@
  */
 #include <linux/notifier.h>
 #include <linux/acpi.h>
+#include <linux/nd.h>
 #include <asm/mce.h>
 #include "nfit.h"
 
@@ -62,12 +63,25 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
 		}
 		mutex_unlock(&acpi_desc->init_mutex);
 
-		/*
-		 * We can ignore an -EBUSY here because if an ARS is already
-		 * in progress, just let that be the last authoritative one
-		 */
-		if (found_match)
+		if (!found_match)
+			continue;
+
+		/* If this fails due to an -ENOMEM, there is little we can do */
+		nvdimm_bus_add_poison(acpi_desc->nvdimm_bus,
+				ALIGN(mce->addr, L1_CACHE_BYTES),
+				L1_CACHE_BYTES);
+		nvdimm_region_notify(nfit_spa->nd_region,
+				NVDIMM_REVALIDATE_POISON);
+
+		if (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) {
+			/*
+			 * We can ignore an -EBUSY here because if an ARS is
+			 * already in progress, just let that be the last
+			 * authoritative one
+			 */
 			acpi_nfit_ars_rescan(acpi_desc);
+		}
+		break;
 	}
 
 	mutex_unlock(&acpi_desc_lock);

drivers/acpi/nfit/nfit.h

@@ -78,6 +78,14 @@ enum {
 	NFIT_ARS_TIMEOUT = 90,
 };
 
+enum nfit_root_notifiers {
+	NFIT_NOTIFY_UPDATE = 0x80,
+};
+
+enum nfit_dimm_notifiers {
+	NFIT_NOTIFY_DIMM_HEALTH = 0x81,
+};
+
 struct nfit_spa {
 	struct list_head list;
 	struct nd_region *nd_region;
@@ -124,6 +132,7 @@ struct nfit_mem {
 	struct acpi_nfit_system_address *spa_bdw;
 	struct acpi_nfit_interleave *idt_dcr;
 	struct acpi_nfit_interleave *idt_bdw;
+	struct kernfs_node *flags_attr;
 	struct nfit_flush *nfit_flush;
 	struct list_head list;
 	struct acpi_device *adev;
@@ -152,6 +161,7 @@ struct acpi_nfit_desc {
 	struct list_head list;
 	struct kernfs_node *scrub_count_state;
 	unsigned int scrub_count;
+	unsigned int scrub_mode;
 	unsigned int cancel:1;
 	unsigned long dimm_cmd_force_en;
 	unsigned long bus_cmd_force_en;
@@ -159,6 +169,11 @@ struct acpi_nfit_desc {
 			void *iobuf, u64 len, int rw);
 };
 
+enum scrub_mode {
+	HW_ERROR_SCRUB_OFF,
+	HW_ERROR_SCRUB_ON,
+};
+
 enum nd_blk_mmio_selector {
 	BDW,
 	DCR,
@@ -223,5 +238,7 @@ static inline struct acpi_nfit_desc *to_acpi_desc(
 
 const u8 *to_nfit_uuid(enum nfit_uuids id);
 int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *nfit, acpi_size sz);
+void __acpi_nfit_notify(struct device *dev, acpi_handle handle, u32 event);
+void __acpi_nvdimm_notify(struct device *dev, u32 event);
 void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev);
 #endif /* __NFIT_H__ */

drivers/dax/Kconfig

@@ -23,4 +23,9 @@ config DEV_DAX_PMEM
 
 	  Say Y if unsure
 
+config NR_DEV_DAX
+	int "Maximum number of Device-DAX instances"
+	default 32768
+	range 256 2147483647
+
 endif

drivers/dax/dax.h

@@ -13,12 +13,13 @@
 #ifndef __DAX_H__
 #define __DAX_H__
 struct device;
+struct dax_dev;
 struct resource;
 struct dax_region;
 void dax_region_put(struct dax_region *dax_region);
 struct dax_region *alloc_dax_region(struct device *parent,
 		int region_id, struct resource *res, unsigned int align,
 		void *addr, unsigned long flags);
-int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
-		int count);
+struct dax_dev *devm_create_dax_dev(struct dax_region *dax_region,
+		struct resource *res, int count);
 #endif /* __DAX_H__ */

drivers/dax/pmem.c

@@ -24,7 +24,7 @@ struct dax_pmem {
 	struct completion cmp;
 };
 
-struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
+static struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
 {
 	return container_of(ref, struct dax_pmem, ref);
 }
@@ -61,6 +61,7 @@ static int dax_pmem_probe(struct device *dev)
 	int rc;
 	void *addr;
 	struct resource res;
+	struct dax_dev *dax_dev;
 	struct nd_pfn_sb *pfn_sb;
 	struct dax_pmem *dax_pmem;
 	struct nd_region *nd_region;
@@ -126,12 +127,12 @@ static int dax_pmem_probe(struct device *dev)
 		return -ENOMEM;
 
 	/* TODO: support for subdividing a dax region... */
-	rc = devm_create_dax_dev(dax_region, &res, 1);
+	dax_dev = devm_create_dax_dev(dax_region, &res, 1);
 
 	/* child dax_dev instances now own the lifetime of the dax_region */
 	dax_region_put(dax_region);
 
-	return rc;
+	return PTR_ERR_OR_ZERO(dax_dev);
 }
 
 static struct nd_device_driver dax_pmem_driver = {

drivers/nvdimm/Kconfig

@@ -89,7 +89,7 @@ config NVDIMM_PFN
 	  Select Y if unsure
 
 config NVDIMM_DAX
-	bool "NVDIMM DAX: Raw access to persistent memory"
+	tristate "NVDIMM DAX: Raw access to persistent memory"
 	default LIBNVDIMM
 	depends on NVDIMM_PFN
 	help

drivers/nvdimm/bus.c

@@ -217,6 +217,8 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
 		return rc;
 	if (cmd_rc < 0)
 		return cmd_rc;
+
+	nvdimm_clear_from_poison_list(nvdimm_bus, phys, len);
 	return clear_err.cleared;
 }
 EXPORT_SYMBOL_GPL(nvdimm_clear_poison);

drivers/nvdimm/core.c

@@ -547,11 +547,12 @@ void nvdimm_badblocks_populate(struct nd_region *nd_region,
 }
 EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);
 
-static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length,
+			gfp_t flags)
 {
 	struct nd_poison *pl;
 
-	pl = kzalloc(sizeof(*pl), GFP_KERNEL);
+	pl = kzalloc(sizeof(*pl), flags);
 	if (!pl)
 		return -ENOMEM;
 
@@ -567,7 +568,7 @@ static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 	struct nd_poison *pl;
 
 	if (list_empty(&nvdimm_bus->poison_list))
-		return add_poison(nvdimm_bus, addr, length);
+		return add_poison(nvdimm_bus, addr, length, GFP_KERNEL);
 
 	/*
 	 * There is a chance this is a duplicate, check for those first.
@@ -587,7 +588,7 @@ static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 	 * as any overlapping ranges will get resolved when the list is consumed
 	 * and converted to badblocks
 	 */
-	return add_poison(nvdimm_bus, addr, length);
+	return add_poison(nvdimm_bus, addr, length, GFP_KERNEL);
 }
 
 int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
@@ -602,6 +603,70 @@ int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
 }
 EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);
 
+void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
+		phys_addr_t start, unsigned int len)
+{
+	struct list_head *poison_list = &nvdimm_bus->poison_list;
+	u64 clr_end = start + len - 1;
+	struct nd_poison *pl, *next;
+
+	nvdimm_bus_lock(&nvdimm_bus->dev);
+	WARN_ON_ONCE(list_empty(poison_list));
+
+	/*
+	 * [start, clr_end] is the poison interval being cleared.
+	 * [pl->start, pl_end] is the poison_list entry we're comparing
+	 * the above interval against. The poison list entry may need
+	 * to be modified (update either start or length), deleted, or
+	 * split into two based on the overlap characteristics
+	 */
+
+	list_for_each_entry_safe(pl, next, poison_list, list) {
+		u64 pl_end = pl->start + pl->length - 1;
+
+		/* Skip intervals with no intersection */
+		if (pl_end < start)
+			continue;
+		if (pl->start >  clr_end)
+			continue;
+		/* Delete completely overlapped poison entries */
+		if ((pl->start >= start) && (pl_end <= clr_end)) {
+			list_del(&pl->list);
+			kfree(pl);
+			continue;
+		}
+		/* Adjust start point of partially cleared entries */
+		if ((start <= pl->start) && (clr_end > pl->start)) {
+			pl->length -= clr_end - pl->start + 1;
+			pl->start = clr_end + 1;
+			continue;
+		}
+		/* Adjust pl->length for partial clearing at the tail end */
+		if ((pl->start < start) && (pl_end <= clr_end)) {
+			/* pl->start remains the same */
+			pl->length = start - pl->start;
+			continue;
+		}
+		/*
+		 * If clearing in the middle of an entry, we split it into
+		 * two by modifying the current entry to represent one half of
+		 * the split, and adding a new entry for the second half.
+		 */
+		if ((pl->start < start) && (pl_end > clr_end)) {
+			u64 new_start = clr_end + 1;
+			u64 new_len = pl_end - new_start + 1;
+
+			/* Add new entry covering the right half */
+			add_poison(nvdimm_bus, new_start, new_len, GFP_NOIO);
+			/* Adjust this entry to cover the left half */
+			pl->length = start - pl->start;
+			continue;
+		}
+	}
+	nvdimm_bus_unlock(&nvdimm_bus->dev);
+}
+EXPORT_SYMBOL_GPL(nvdimm_clear_from_poison_list);
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
 {

drivers/nvdimm/dimm.c

@@ -26,6 +26,14 @@ static int nvdimm_probe(struct device *dev)
 	struct nvdimm_drvdata *ndd;
 	int rc;
 
+	rc = nvdimm_check_config_data(dev);
+	if (rc) {
+		/* not required for non-aliased nvdimm, ex. NVDIMM-N */
+		if (rc == -ENOTTY)
+			rc = 0;
+		return rc;
+	}
+
 	ndd = kzalloc(sizeof(*ndd), GFP_KERNEL);
 	if (!ndd)
 		return -ENOMEM;
@@ -72,6 +80,9 @@ static int nvdimm_remove(struct device *dev)
 {
 	struct nvdimm_drvdata *ndd = dev_get_drvdata(dev);
 
+	if (!ndd)
+		return 0;
+
 	nvdimm_bus_lock(dev);
 	dev_set_drvdata(dev, NULL);
 	nvdimm_bus_unlock(dev);

drivers/nvdimm/dimm_devs.c

@@ -28,28 +28,30 @@ static DEFINE_IDA(dimm_ida);
  * Retrieve bus and dimm handle and return if this bus supports
  * get_config_data commands
  */
-static int __validate_dimm(struct nvdimm_drvdata *ndd)
+int nvdimm_check_config_data(struct device *dev)
 {
-	struct nvdimm *nvdimm;
+	struct nvdimm *nvdimm = to_nvdimm(dev);
 
-	if (!ndd)
-		return -EINVAL;
-
-	nvdimm = to_nvdimm(ndd->dev);
-
-	if (!nvdimm->cmd_mask)
-		return -ENXIO;
-	if (!test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask))
-		return -ENXIO;
+	if (!nvdimm->cmd_mask ||
+	    !test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask)) {
+		if (nvdimm->flags & NDD_ALIASING)
+			return -ENXIO;
+		else
+			return -ENOTTY;
+	}
 
 	return 0;
 }
 
 static int validate_dimm(struct nvdimm_drvdata *ndd)
 {
-	int rc = __validate_dimm(ndd);
+	int rc;
 
-	if (rc && ndd)
+	if (!ndd)
+		return -EINVAL;
+
+	rc = nvdimm_check_config_data(ndd->dev);
+	if (rc)
 		dev_dbg(ndd->dev, "%pf: %s error: %d\n",
 				__builtin_return_address(0), __func__, rc);
 	return rc;
@@ -263,6 +265,12 @@ const char *nvdimm_name(struct nvdimm *nvdimm)
 }
 EXPORT_SYMBOL_GPL(nvdimm_name);
 
+struct kobject *nvdimm_kobj(struct nvdimm *nvdimm)
+{
+	return &nvdimm->dev.kobj;
+}
+EXPORT_SYMBOL_GPL(nvdimm_kobj);
+
 unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm)
 {
 	return nvdimm->cmd_mask;
@@ -378,40 +386,166 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
 }
 EXPORT_SYMBOL_GPL(nvdimm_create);
 
+int alias_dpa_busy(struct device *dev, void *data)
+{
+	resource_size_t map_end, blk_start, new, busy;
+	struct blk_alloc_info *info = data;
+	struct nd_mapping *nd_mapping;
+	struct nd_region *nd_region;
+	struct nvdimm_drvdata *ndd;
+	struct resource *res;
+	int i;
+
+	if (!is_nd_pmem(dev))
+		return 0;
+
+	nd_region = to_nd_region(dev);
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		nd_mapping  = &nd_region->mapping[i];
+		if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
+			break;
+	}
+
+	if (i >= nd_region->ndr_mappings)
+		return 0;
+
+	ndd = to_ndd(nd_mapping);
+	map_end = nd_mapping->start + nd_mapping->size - 1;
+	blk_start = nd_mapping->start;
+
+	/*
+	 * In the allocation case ->res is set to free space that we are
+	 * looking to validate against PMEM aliasing collision rules
+	 * (i.e. BLK is allocated after all aliased PMEM).
+	 */
+	if (info->res) {
+		if (info->res->start >= nd_mapping->start
+				&& info->res->start < map_end)
+			/* pass */;
+		else
+			return 0;
+	}
+
+ retry:
+	/*
+	 * Find the free dpa from the end of the last pmem allocation to
+	 * the end of the interleave-set mapping that is not already
+	 * covered by a blk allocation.
+	 */
+	busy = 0;
+	for_each_dpa_resource(ndd, res) {
+		if ((res->start >= blk_start && res->start < map_end)
+				|| (res->end >= blk_start
+					&& res->end <= map_end)) {
+			if (strncmp(res->name, "pmem", 4) == 0) {
+				new = max(blk_start, min(map_end + 1,
+							res->end + 1));
+				if (new != blk_start) {
+					blk_start = new;
+					goto retry;
+				}
+			} else
+				busy += min(map_end, res->end)
+					- max(nd_mapping->start, res->start) + 1;
+		} else if (nd_mapping->start > res->start
+				&& map_end < res->end) {
+			/* total eclipse of the PMEM region mapping */
+			busy += nd_mapping->size;
+			break;
+		}
+	}
+
+	/* update the free space range with the probed blk_start */
+	if (info->res && blk_start > info->res->start) {
+		info->res->start = max(info->res->start, blk_start);
+		if (info->res->start > info->res->end)
+			info->res->end = info->res->start - 1;
+		return 1;
+	}
+
+	info->available -= blk_start - nd_mapping->start + busy;
+
+	return 0;
+}
+
+static int blk_dpa_busy(struct device *dev, void *data)
+{
+	struct blk_alloc_info *info = data;
+	struct nd_mapping *nd_mapping;
+	struct nd_region *nd_region;
+	resource_size_t map_end;
+	int i;
+
+	if (!is_nd_pmem(dev))
+		return 0;
+
+	nd_region = to_nd_region(dev);
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		nd_mapping  = &nd_region->mapping[i];
+		if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
+			break;
+	}
+
+	if (i >= nd_region->ndr_mappings)
+		return 0;
+
+	map_end = nd_mapping->start + nd_mapping->size - 1;
+	if (info->res->start >= nd_mapping->start
+			&& info->res->start < map_end) {
+		if (info->res->end <= map_end) {
+			info->busy = 0;
+			return 1;
+		} else {
+			info->busy -= info->res->end - map_end;
+			return 0;
+		}
+	} else if (info->res->end >= nd_mapping->start
+			&& info->res->end <= map_end) {
+		info->busy -= nd_mapping->start - info->res->start;
+		return 0;
+	} else {
+		info->busy -= nd_mapping->size;
+		return 0;
+	}
+}
+
 /**
  * nd_blk_available_dpa - account the unused dpa of BLK region
  * @nd_mapping: container of dpa-resource-root + labels
  *
- * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges.
+ * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges, but
+ * we arrange for them to never start at an lower dpa than the last
+ * PMEM allocation in an aliased region.
  */
-resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping)
+resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 {
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+	struct nd_mapping *nd_mapping = &nd_region->mapping[0];
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	resource_size_t map_end, busy = 0, available;
+	struct blk_alloc_info info = {
+		.nd_mapping = nd_mapping,
+		.available = nd_mapping->size,
+		.res = NULL,
+	};
 	struct resource *res;
 
 	if (!ndd)
 		return 0;
 
-	map_end = nd_mapping->start + nd_mapping->size - 1;
-	for_each_dpa_resource(ndd, res)
-		if (res->start >= nd_mapping->start && res->start < map_end) {
-			resource_size_t end = min(map_end, res->end);
+	device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy);
 
-			busy += end - res->start + 1;
-		} else if (res->end >= nd_mapping->start
-				&& res->end <= map_end) {
-			busy += res->end - nd_mapping->start;
-		} else if (nd_mapping->start > res->start
-				&& nd_mapping->start < res->end) {
-			/* total eclipse of the BLK region mapping */
-			busy += nd_mapping->size;
-		}
+	/* now account for busy blk allocations in unaliased dpa */
+	for_each_dpa_resource(ndd, res) {
+		if (strncmp(res->name, "blk", 3) != 0)
+			continue;
 
-	available = map_end - nd_mapping->start + 1;
-	if (busy < available)
-		return available - busy;
-	return 0;
+		info.res = res;
+		info.busy = resource_size(res);
+		device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy);
+		info.available -= info.busy;
+	}
+
+	return info.available;
 }
 
 /**
@@ -443,21 +577,16 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 	map_start = nd_mapping->start;
 	map_end = map_start + nd_mapping->size - 1;
 	blk_start = max(map_start, map_end + 1 - *overlap);
-	for_each_dpa_resource(ndd, res)
+	for_each_dpa_resource(ndd, res) {
 		if (res->start >= map_start && res->start < map_end) {
 			if (strncmp(res->name, "blk", 3) == 0)
-				blk_start = min(blk_start, res->start);
-			else if (res->start != map_start) {
+				blk_start = min(blk_start,
+						max(map_start, res->start));
+			else if (res->end > map_end) {
 				reason = "misaligned to iset";
 				goto err;
-			} else {
-				if (busy) {
-					reason = "duplicate overlapping PMEM reservations?";
-					goto err;
-				}
+			} else
 				busy += resource_size(res);
-				continue;
-			}
 		} else if (res->end >= map_start && res->end <= map_end) {
 			if (strncmp(res->name, "blk", 3) == 0) {
 				/*
@@ -466,15 +595,14 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 				 * be used for BLK.
 				 */
 				blk_start = map_start;
-			} else {
-				reason = "misaligned to iset";
-				goto err;
-			}
+			} else
+				busy += resource_size(res);
 		} else if (map_start > res->start && map_start < res->end) {
 			/* total eclipse of the mapping */
 			busy += nd_mapping->size;
 			blk_start = map_start;
 		}
+	}
 
 	*overlap = map_end + 1 - blk_start;
 	available = blk_start - map_start;
@@ -483,10 +611,6 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 	return 0;
 
  err:
-	/*
-	 * Something is wrong, PMEM must align with the start of the
-	 * interleave set, and there can only be one allocation per set.
-	 */
 	nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason);
 	return 0;
 }

drivers/nvdimm/label.c

@@ -494,11 +494,13 @@ static int __pmem_label_update(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, struct nd_namespace_pmem *nspm,
 		int pos)
 {
-	u64 cookie = nd_region_interleave_set_cookie(nd_region), rawsize;
+	u64 cookie = nd_region_interleave_set_cookie(nd_region);
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	struct nd_namespace_label *victim_label;
+	struct nd_label_ent *label_ent, *victim = NULL;
 	struct nd_namespace_label *nd_label;
 	struct nd_namespace_index *nsindex;
+	struct nd_label_id label_id;
+	struct resource *res;
 	unsigned long *free;
 	u32 nslot, slot;
 	size_t offset;
@@ -507,6 +509,16 @@ static int __pmem_label_update(struct nd_region *nd_region,
 	if (!preamble_next(ndd, &nsindex, &free, &nslot))
 		return -ENXIO;
 
+	nd_label_gen_id(&label_id, nspm->uuid, 0);
+	for_each_dpa_resource(ndd, res)
+		if (strcmp(res->name, label_id.id) == 0)
+			break;
+
+	if (!res) {
+		WARN_ON_ONCE(1);
+		return -ENXIO;
+	}
+
 	/* allocate and write the label to the staging (next) index */
 	slot = nd_label_alloc_slot(ndd);
 	if (slot == UINT_MAX)
@@ -522,11 +534,10 @@ static int __pmem_label_update(struct nd_region *nd_region,
 	nd_label->nlabel = __cpu_to_le16(nd_region->ndr_mappings);
 	nd_label->position = __cpu_to_le16(pos);
 	nd_label->isetcookie = __cpu_to_le64(cookie);
-	rawsize = div_u64(resource_size(&nspm->nsio.res),
-			nd_region->ndr_mappings);
-	nd_label->rawsize = __cpu_to_le64(rawsize);
-	nd_label->dpa = __cpu_to_le64(nd_mapping->start);
+	nd_label->rawsize = __cpu_to_le64(resource_size(res));
+	nd_label->dpa = __cpu_to_le64(res->start);
 	nd_label->slot = __cpu_to_le32(slot);
+	nd_dbg_dpa(nd_region, ndd, res, "%s\n", __func__);
 
 	/* update label */
 	offset = nd_label_offset(ndd, nd_label);
@@ -536,38 +547,43 @@ static int __pmem_label_update(struct nd_region *nd_region,
 		return rc;
 
 	/* Garbage collect the previous label */
-	victim_label = nd_mapping->labels[0];
-	if (victim_label) {
-		slot = to_slot(ndd, victim_label);
-		nd_label_free_slot(ndd, slot);
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry(label_ent, &nd_mapping->labels, list) {
+		if (!label_ent->label)
+			continue;
+		if (memcmp(nspm->uuid, label_ent->label->uuid,
+					NSLABEL_UUID_LEN) != 0)
+			continue;
+		victim = label_ent;
+		list_move_tail(&victim->list, &nd_mapping->labels);
+		break;
+	}
+	if (victim) {
 		dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
+		slot = to_slot(ndd, victim->label);
+		nd_label_free_slot(ndd, slot);
+		victim->label = NULL;
 	}
 
 	/* update index */
 	rc = nd_label_write_index(ndd, ndd->ns_next,
 			nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);
-	if (rc < 0)
-		return rc;
+	if (rc == 0) {
+		list_for_each_entry(label_ent, &nd_mapping->labels, list)
+			if (!label_ent->label) {
+				label_ent->label = nd_label;
+				nd_label = NULL;
+				break;
+			}
+		dev_WARN_ONCE(&nspm->nsio.common.dev, nd_label,
+				"failed to track label: %d\n",
+				to_slot(ndd, nd_label));
+		if (nd_label)
+			rc = -ENXIO;
+	}
+	mutex_unlock(&nd_mapping->lock);
 
-	nd_mapping->labels[0] = nd_label;
-
-	return 0;
-}
-
-static void del_label(struct nd_mapping *nd_mapping, int l)
-{
-	struct nd_namespace_label *next_label, *nd_label;
-	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	unsigned int slot;
-	int j;
-
-	nd_label = nd_mapping->labels[l];
-	slot = to_slot(ndd, nd_label);
-	dev_vdbg(ndd->dev, "%s: clear: %d\n", __func__, slot);
-
-	for (j = l; (next_label = nd_mapping->labels[j + 1]); j++)
-		nd_mapping->labels[j] = next_label;
-	nd_mapping->labels[j] = NULL;
+	return rc;
 }
 
 static bool is_old_resource(struct resource *res, struct resource **list, int n)
@@ -607,14 +623,16 @@ static int __blk_label_update(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, struct nd_namespace_blk *nsblk,
 		int num_labels)
 {
-	int i, l, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO;
+	int i, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO;
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
 	struct nd_namespace_label *nd_label;
+	struct nd_label_ent *label_ent, *e;
 	struct nd_namespace_index *nsindex;
 	unsigned long *free, *victim_map = NULL;
 	struct resource *res, **old_res_list;
 	struct nd_label_id label_id;
 	u8 uuid[NSLABEL_UUID_LEN];
+	LIST_HEAD(list);
 	u32 nslot, slot;
 
 	if (!preamble_next(ndd, &nsindex, &free, &nslot))
@@ -736,15 +754,22 @@ static int __blk_label_update(struct nd_region *nd_region,
 	 * entries in nd_mapping->labels
 	 */
 	nlabel = 0;
-	for_each_label(l, nd_label, nd_mapping->labels) {
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		nd_label = label_ent->label;
+		if (!nd_label)
+			continue;
 		nlabel++;
 		memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN);
 		if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0)
 			continue;
 		nlabel--;
-		del_label(nd_mapping, l);
-		l--; /* retry with the new label at this index */
+		list_move(&label_ent->list, &list);
+		label_ent->label = NULL;
 	}
+	list_splice_tail_init(&list, &nd_mapping->labels);
+	mutex_unlock(&nd_mapping->lock);
+
 	if (nlabel + nsblk->num_resources > num_labels) {
 		/*
 		 * Bug, we can't end up with more resources than
@@ -755,6 +780,15 @@ static int __blk_label_update(struct nd_region *nd_region,
 		goto out;
 	}
 
+	mutex_lock(&nd_mapping->lock);
+	label_ent = list_first_entry_or_null(&nd_mapping->labels,
+			typeof(*label_ent), list);
+	if (!label_ent) {
+		WARN_ON(1);
+		mutex_unlock(&nd_mapping->lock);
+		rc = -ENXIO;
+		goto out;
+	}
 	for_each_clear_bit_le(slot, free, nslot) {
 		nd_label = nd_label_base(ndd) + slot;
 		memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN);
@@ -762,11 +796,19 @@ static int __blk_label_update(struct nd_region *nd_region,
 			continue;
 		res = to_resource(ndd, nd_label);
 		res->flags &= ~DPA_RESOURCE_ADJUSTED;
-		dev_vdbg(&nsblk->common.dev, "assign label[%d] slot: %d\n",
-				l, slot);
-		nd_mapping->labels[l++] = nd_label;
+		dev_vdbg(&nsblk->common.dev, "assign label slot: %d\n", slot);
+		list_for_each_entry_from(label_ent, &nd_mapping->labels, list) {
+			if (label_ent->label)
+				continue;
+			label_ent->label = nd_label;
+			nd_label = NULL;
+			break;
+		}
+		if (nd_label)
+			dev_WARN(&nsblk->common.dev,
+					"failed to track label slot%d\n", slot);
 	}
-	nd_mapping->labels[l] = NULL;
+	mutex_unlock(&nd_mapping->lock);
 
  out:
 	kfree(old_res_list);
@@ -788,32 +830,28 @@ static int __blk_label_update(struct nd_region *nd_region,
 
 static int init_labels(struct nd_mapping *nd_mapping, int num_labels)
 {
-	int i, l, old_num_labels = 0;
+	int i, old_num_labels = 0;
+	struct nd_label_ent *label_ent;
 	struct nd_namespace_index *nsindex;
-	struct nd_namespace_label *nd_label;
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	size_t size = (num_labels + 1) * sizeof(struct nd_namespace_label *);
 
-	for_each_label(l, nd_label, nd_mapping->labels)
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry(label_ent, &nd_mapping->labels, list)
 		old_num_labels++;
+	mutex_unlock(&nd_mapping->lock);
 
 	/*
 	 * We need to preserve all the old labels for the mapping so
 	 * they can be garbage collected after writing the new labels.
 	 */
-	if (num_labels > old_num_labels) {
-		struct nd_namespace_label **labels;
-
-		labels = krealloc(nd_mapping->labels, size, GFP_KERNEL);
-		if (!labels)
+	for (i = old_num_labels; i < num_labels; i++) {
+		label_ent = kzalloc(sizeof(*label_ent), GFP_KERNEL);
+		if (!label_ent)
 			return -ENOMEM;
-		nd_mapping->labels = labels;
+		mutex_lock(&nd_mapping->lock);
+		list_add_tail(&label_ent->list, &nd_mapping->labels);
+		mutex_unlock(&nd_mapping->lock);
 	}
-	if (!nd_mapping->labels)
-		return -ENOMEM;
-
-	for (i = old_num_labels; i <= num_labels; i++)
-		nd_mapping->labels[i] = NULL;
 
 	if (ndd->ns_current == -1 || ndd->ns_next == -1)
 		/* pass */;
@@ -837,42 +875,45 @@ static int init_labels(struct nd_mapping *nd_mapping, int num_labels)
 static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid)
 {
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
-	struct nd_namespace_label *nd_label;
+	struct nd_label_ent *label_ent, *e;
 	struct nd_namespace_index *nsindex;
 	u8 label_uuid[NSLABEL_UUID_LEN];
-	int l, num_freed = 0;
 	unsigned long *free;
+	LIST_HEAD(list);
 	u32 nslot, slot;
+	int active = 0;
 
 	if (!uuid)
 		return 0;
 
 	/* no index || no labels == nothing to delete */
-	if (!preamble_next(ndd, &nsindex, &free, &nslot)
-			|| !nd_mapping->labels)
+	if (!preamble_next(ndd, &nsindex, &free, &nslot))
 		return 0;
 
-	for_each_label(l, nd_label, nd_mapping->labels) {
+	mutex_lock(&nd_mapping->lock);
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		struct nd_namespace_label *nd_label = label_ent->label;
+
+		if (!nd_label)
+			continue;
+		active++;
 		memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN);
 		if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0)
 			continue;
+		active--;
 		slot = to_slot(ndd, nd_label);
 		nd_label_free_slot(ndd, slot);
 		dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
-		del_label(nd_mapping, l);
-		num_freed++;
-		l--; /* retry with new label at this index */
+		list_move_tail(&label_ent->list, &list);
+		label_ent->label = NULL;
 	}
+	list_splice_tail_init(&list, &nd_mapping->labels);
 
-	if (num_freed > l) {
-		/*
-		 * num_freed will only ever be > l when we delete the last
-		 * label
-		 */
-		kfree(nd_mapping->labels);
-		nd_mapping->labels = NULL;
-		dev_dbg(ndd->dev, "%s: no more labels\n", __func__);
+	if (active == 0) {
+		nd_mapping_free_labels(nd_mapping);
+		dev_dbg(ndd->dev, "%s: no more active labels\n", __func__);
 	}
+	mutex_unlock(&nd_mapping->lock);
 
 	return nd_label_write_index(ndd, ndd->ns_next,
 			nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);
@@ -885,7 +926,9 @@ int nd_pmem_namespace_label_update(struct nd_region *nd_region,
 
 	for (i = 0; i < nd_region->ndr_mappings; i++) {
 		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
-		int rc;
+		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+		struct resource *res;
+		int rc, count = 0;
 
 		if (size == 0) {
 			rc = del_labels(nd_mapping, nspm->uuid);
@@ -894,7 +937,12 @@ int nd_pmem_namespace_label_update(struct nd_region *nd_region,
 			continue;
 		}
 
-		rc = init_labels(nd_mapping, 1);
+		for_each_dpa_resource(ndd, res)
+			if (strncmp(res->name, "pmem", 3) == 0)
+				count++;
+		WARN_ON_ONCE(!count);
+
+		rc = init_labels(nd_mapping, count);
 		if (rc < 0)
 			return rc;
 

drivers/nvdimm/nd-core.h

@@ -44,6 +44,23 @@ struct nvdimm {
 	struct resource *flush_wpq;
 };
 
+/**
+ * struct blk_alloc_info - tracking info for BLK dpa scanning
+ * @nd_mapping: blk region mapping boundaries
+ * @available: decremented in alias_dpa_busy as aliased PMEM is scanned
+ * @busy: decremented in blk_dpa_busy to account for ranges already
+ * 	  handled by alias_dpa_busy
+ * @res: alias_dpa_busy interprets this a free space range that needs to
+ * 	 be truncated to the valid BLK allocation starting DPA, blk_dpa_busy
+ * 	 treats it as a busy range that needs the aliased PMEM ranges
+ * 	 truncated.
+ */
+struct blk_alloc_info {
+	struct nd_mapping *nd_mapping;
+	resource_size_t available, busy;
+	struct resource *res;
+};
+
 bool is_nvdimm(struct device *dev);
 bool is_nd_pmem(struct device *dev);
 bool is_nd_blk(struct device *dev);
@@ -54,7 +71,7 @@ void nvdimm_devs_exit(void);
 void nd_region_devs_exit(void);
 void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 struct nd_region;
-void nd_region_create_blk_seed(struct nd_region *nd_region);
+void nd_region_create_ns_seed(struct nd_region *nd_region);
 void nd_region_create_btt_seed(struct nd_region *nd_region);
 void nd_region_create_pfn_seed(struct nd_region *nd_region);
 void nd_region_create_dax_seed(struct nd_region *nd_region);
@@ -73,13 +90,14 @@ bool nd_is_uuid_unique(struct device *dev, u8 *uuid);
 struct nd_region;
 struct nvdimm_drvdata;
 struct nd_mapping;
+void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
 resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, resource_size_t *overlap);
-resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping);
+resource_size_t nd_blk_available_dpa(struct nd_region *nd_region);
 resource_size_t nd_region_available_dpa(struct nd_region *nd_region);
 resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
 		struct nd_label_id *label_id);
-struct nd_mapping;
+int alias_dpa_busy(struct device *dev, void *data);
 struct resource *nsblk_add_resource(struct nd_region *nd_region,
 		struct nvdimm_drvdata *ndd, struct nd_namespace_blk *nsblk,
 		resource_size_t start);

drivers/nvdimm/nd.h

@@ -101,9 +101,6 @@ static inline struct nd_namespace_index *to_next_namespace_index(
 		(unsigned long long) (res ? resource_size(res) : 0), \
 		(unsigned long long) (res ? res->start : 0), ##arg)
 
-#define for_each_label(l, label, labels) \
-	for (l = 0; (label = labels ? labels[l] : NULL); l++)
-
 #define for_each_dpa_resource(ndd, res) \
 	for (res = (ndd)->dpa.child; res; res = res->sibling)
 
@@ -116,6 +113,31 @@ struct nd_percpu_lane {
 	spinlock_t lock;
 };
 
+struct nd_label_ent {
+	struct list_head list;
+	struct nd_namespace_label *label;
+};
+
+enum nd_mapping_lock_class {
+	ND_MAPPING_CLASS0,
+	ND_MAPPING_UUID_SCAN,
+};
+
+struct nd_mapping {
+	struct nvdimm *nvdimm;
+	u64 start;
+	u64 size;
+	struct list_head labels;
+	struct mutex lock;
+	/*
+	 * @ndd is for private use at region enable / disable time for
+	 * get_ndd() + put_ndd(), all other nd_mapping to ndd
+	 * conversions use to_ndd() which respects enabled state of the
+	 * nvdimm.
+	 */
+	struct nvdimm_drvdata *ndd;
+};
+
 struct nd_region {
 	struct device dev;
 	struct ida ns_ida;
@@ -209,6 +231,7 @@ void nvdimm_exit(void);
 void nd_region_exit(void);
 struct nvdimm;
 struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping);
+int nvdimm_check_config_data(struct device *dev);
 int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd);
 int nvdimm_init_config_data(struct nvdimm_drvdata *ndd);
 int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,

drivers/nvdimm/pmem.c

@@ -66,13 +66,32 @@ static void pmem_clear_poison(struct pmem_device *pmem, phys_addr_t offset,
 	invalidate_pmem(pmem->virt_addr + offset, len);
 }
 
+static void write_pmem(void *pmem_addr, struct page *page,
+		unsigned int off, unsigned int len)
+{
+	void *mem = kmap_atomic(page);
+
+	memcpy_to_pmem(pmem_addr, mem + off, len);
+	kunmap_atomic(mem);
+}
+
+static int read_pmem(struct page *page, unsigned int off,
+		void *pmem_addr, unsigned int len)
+{
+	int rc;
+	void *mem = kmap_atomic(page);
+
+	rc = memcpy_from_pmem(mem + off, pmem_addr, len);
+	kunmap_atomic(mem);
+	return rc;
+}
+
 static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 			unsigned int len, unsigned int off, bool is_write,
 			sector_t sector)
 {
 	int rc = 0;
 	bool bad_pmem = false;
-	void *mem = kmap_atomic(page);
 	phys_addr_t pmem_off = sector * 512 + pmem->data_offset;
 	void *pmem_addr = pmem->virt_addr + pmem_off;
 
@@ -83,7 +102,7 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 		if (unlikely(bad_pmem))
 			rc = -EIO;
 		else {
-			rc = memcpy_from_pmem(mem + off, pmem_addr, len);
+			rc = read_pmem(page, off, pmem_addr, len);
 			flush_dcache_page(page);
 		}
 	} else {
@@ -102,14 +121,13 @@ static int pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 		 * after clear poison.
 		 */
 		flush_dcache_page(page);
-		memcpy_to_pmem(pmem_addr, mem + off, len);
+		write_pmem(pmem_addr, page, off, len);
 		if (unlikely(bad_pmem)) {
 			pmem_clear_poison(pmem, pmem_off, len);
-			memcpy_to_pmem(pmem_addr, mem + off, len);
+			write_pmem(pmem_addr, page, off, len);
 		}
 	}
 
-	kunmap_atomic(mem);
 	return rc;
 }
 

drivers/nvdimm/region_devs.c

@@ -70,7 +70,7 @@ static int nvdimm_map_flush(struct device *dev, struct nvdimm *nvdimm, int dimm,
 
 int nd_region_activate(struct nd_region *nd_region)
 {
-	int i, num_flush = 0;
+	int i, j, num_flush = 0;
 	struct nd_region_data *ndrd;
 	struct device *dev = &nd_region->dev;
 	size_t flush_data_size = sizeof(void *);
@@ -107,6 +107,21 @@ int nd_region_activate(struct nd_region *nd_region)
 			return rc;
 	}
 
+	/*
+	 * Clear out entries that are duplicates. This should prevent the
+	 * extra flushings.
+	 */
+	for (i = 0; i < nd_region->ndr_mappings - 1; i++) {
+		/* ignore if NULL already */
+		if (!ndrd_get_flush_wpq(ndrd, i, 0))
+			continue;
+
+		for (j = i + 1; j < nd_region->ndr_mappings; j++)
+			if (ndrd_get_flush_wpq(ndrd, i, 0) ==
+			    ndrd_get_flush_wpq(ndrd, j, 0))
+				ndrd_set_flush_wpq(ndrd, j, 0, NULL);
+	}
+
 	return 0;
 }
 
@@ -298,9 +313,8 @@ resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
 				blk_max_overlap = overlap;
 				goto retry;
 			}
-		} else if (is_nd_blk(&nd_region->dev)) {
-			available += nd_blk_available_dpa(nd_mapping);
-		}
+		} else if (is_nd_blk(&nd_region->dev))
+			available += nd_blk_available_dpa(nd_region);
 	}
 
 	return available;
@@ -491,6 +505,17 @@ u64 nd_region_interleave_set_cookie(struct nd_region *nd_region)
 	return 0;
 }
 
+void nd_mapping_free_labels(struct nd_mapping *nd_mapping)
+{
+	struct nd_label_ent *label_ent, *e;
+
+	WARN_ON(!mutex_is_locked(&nd_mapping->lock));
+	list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+		list_del(&label_ent->list);
+		kfree(label_ent);
+	}
+}
+
 /*
  * Upon successful probe/remove, take/release a reference on the
  * associated interleave set (if present), and plant new btt + namespace
@@ -511,8 +536,10 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 			struct nvdimm_drvdata *ndd = nd_mapping->ndd;
 			struct nvdimm *nvdimm = nd_mapping->nvdimm;
 
-			kfree(nd_mapping->labels);
-			nd_mapping->labels = NULL;
+			mutex_lock(&nd_mapping->lock);
+			nd_mapping_free_labels(nd_mapping);
+			mutex_unlock(&nd_mapping->lock);
+
 			put_ndd(ndd);
 			nd_mapping->ndd = NULL;
 			if (ndd)
@@ -522,11 +549,12 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 		if (is_nd_pmem(dev))
 			return;
 	}
-	if (dev->parent && is_nd_blk(dev->parent) && probe) {
+	if (dev->parent && (is_nd_blk(dev->parent) || is_nd_pmem(dev->parent))
+			&& probe) {
 		nd_region = to_nd_region(dev->parent);
 		nvdimm_bus_lock(dev);
 		if (nd_region->ns_seed == dev)
-			nd_region_create_blk_seed(nd_region);
+			nd_region_create_ns_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
 	if (is_nd_btt(dev) && probe) {
@@ -536,23 +564,30 @@ static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
 		nvdimm_bus_lock(dev);
 		if (nd_region->btt_seed == dev)
 			nd_region_create_btt_seed(nd_region);
-		if (nd_region->ns_seed == &nd_btt->ndns->dev &&
-				is_nd_blk(dev->parent))
-			nd_region_create_blk_seed(nd_region);
+		if (nd_region->ns_seed == &nd_btt->ndns->dev)
+			nd_region_create_ns_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
 	if (is_nd_pfn(dev) && probe) {
+		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+
 		nd_region = to_nd_region(dev->parent);
 		nvdimm_bus_lock(dev);
 		if (nd_region->pfn_seed == dev)
 			nd_region_create_pfn_seed(nd_region);
+		if (nd_region->ns_seed == &nd_pfn->ndns->dev)
+			nd_region_create_ns_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
 	if (is_nd_dax(dev) && probe) {
+		struct nd_dax *nd_dax = to_nd_dax(dev);
+
 		nd_region = to_nd_region(dev->parent);
 		nvdimm_bus_lock(dev);
 		if (nd_region->dax_seed == dev)
 			nd_region_create_dax_seed(nd_region);
+		if (nd_region->ns_seed == &nd_dax->nd_pfn.ndns->dev)
+			nd_region_create_ns_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
 }
@@ -759,10 +794,10 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 	int ro = 0;
 
 	for (i = 0; i < ndr_desc->num_mappings; i++) {
-		struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
-		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
+		struct nvdimm *nvdimm = mapping->nvdimm;
 
-		if ((nd_mapping->start | nd_mapping->size) % SZ_4K) {
+		if ((mapping->start | mapping->size) % SZ_4K) {
 			dev_err(&nvdimm_bus->dev, "%s: %s mapping%d is not 4K aligned\n",
 					caller, dev_name(&nvdimm->dev), i);
 
@@ -813,11 +848,15 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
 		ndl->count = 0;
 	}
 
-	memcpy(nd_region->mapping, ndr_desc->nd_mapping,
-			sizeof(struct nd_mapping) * ndr_desc->num_mappings);
 	for (i = 0; i < ndr_desc->num_mappings; i++) {
-		struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
-		struct nvdimm *nvdimm = nd_mapping->nvdimm;
+		struct nd_mapping_desc *mapping = &ndr_desc->mapping[i];
+		struct nvdimm *nvdimm = mapping->nvdimm;
+
+		nd_region->mapping[i].nvdimm = nvdimm;
+		nd_region->mapping[i].start = mapping->start;
+		nd_region->mapping[i].size = mapping->size;
+		INIT_LIST_HEAD(&nd_region->mapping[i].labels);
+		mutex_init(&nd_region->mapping[i].lock);
 
 		get_device(&nvdimm->dev);
 	}

fs/char_dev.c

@@ -406,6 +406,7 @@ void cd_forget(struct inode *inode)
 	spin_lock(&cdev_lock);
 	list_del_init(&inode->i_devices);
 	inode->i_cdev = NULL;
+	inode->i_mapping = &inode->i_data;
 	spin_unlock(&cdev_lock);
 }
 

include/linux/libnvdimm.h

@@ -50,23 +50,6 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc);
 
-struct nd_namespace_label;
-struct nvdimm_drvdata;
-
-struct nd_mapping {
-	struct nvdimm *nvdimm;
-	struct nd_namespace_label **labels;
-	u64 start;
-	u64 size;
-	/*
-	 * @ndd is for private use at region enable / disable time for
-	 * get_ndd() + put_ndd(), all other nd_mapping to ndd
-	 * conversions use to_ndd() which respects enabled state of the
-	 * nvdimm.
-	 */
-	struct nvdimm_drvdata *ndd;
-};
-
 struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
 	unsigned long cmd_mask;
@@ -89,9 +72,15 @@ struct nd_interleave_set {
 	u64 cookie;
 };
 
+struct nd_mapping_desc {
+	struct nvdimm *nvdimm;
+	u64 start;
+	u64 size;
+};
+
 struct nd_region_desc {
 	struct resource *res;
-	struct nd_mapping *nd_mapping;
+	struct nd_mapping_desc *mapping;
 	u16 num_mappings;
 	const struct attribute_group **attr_groups;
 	struct nd_interleave_set *nd_set;
@@ -129,6 +118,8 @@ static inline struct nd_blk_region_desc *to_blk_region_desc(
 }
 
 int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length);
+void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
+		phys_addr_t start, unsigned int len);
 struct nvdimm_bus *nvdimm_bus_register(struct device *parent,
 		struct nvdimm_bus_descriptor *nfit_desc);
 void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus);
@@ -139,6 +130,7 @@ struct nd_blk_region *to_nd_blk_region(struct device *dev);
 struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
 struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus);
 const char *nvdimm_name(struct nvdimm *nvdimm);
+struct kobject *nvdimm_kobj(struct nvdimm *nvdimm);
 unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm);
 void *nvdimm_provider_data(struct nvdimm *nvdimm);
 struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,