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/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;
-
-	if (!ndd)
-		return -EINVAL;
-
-	nvdimm = to_nvdimm(ndd->dev);
+	struct nvdimm *nvdimm = to_nvdimm(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/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,

include/linux/nd.h

@@ -77,11 +77,13 @@ struct nd_namespace_io {
  * @nsio: device and system physical address range to drive
  * @alt_name: namespace name supplied in the dimm label
  * @uuid: namespace name supplied in the dimm label
+ * @id: ida allocated id
  */
 struct nd_namespace_pmem {
 	struct nd_namespace_io nsio;
 	char *alt_name;
 	u8 *uuid;
+	int id;
 };
 
 /**
@@ -105,19 +107,19 @@ struct nd_namespace_blk {
 	struct resource **res;
 };
 
-static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev)
+static inline struct nd_namespace_io *to_nd_namespace_io(const struct device *dev)
 {
 	return container_of(dev, struct nd_namespace_io, common.dev);
 }
 
-static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev)
+static inline struct nd_namespace_pmem *to_nd_namespace_pmem(const struct device *dev)
 {
 	struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
 
 	return container_of(nsio, struct nd_namespace_pmem, nsio);
 }
 
-static inline struct nd_namespace_blk *to_nd_namespace_blk(struct device *dev)
+static inline struct nd_namespace_blk *to_nd_namespace_blk(const struct device *dev)
 {
 	return container_of(dev, struct nd_namespace_blk, common.dev);
 }

include/uapi/linux/magic.h

@@ -65,6 +65,7 @@
 #define V9FS_MAGIC		0x01021997
 
 #define BDEVFS_MAGIC            0x62646576
+#define DAXFS_MAGIC             0x64646178
 #define BINFMTFS_MAGIC          0x42494e4d
 #define DEVPTS_SUPER_MAGIC	0x1cd1
 #define FUTEXFS_SUPER_MAGIC	0xBAD1DEA

include/uapi/linux/ndctl.h

@@ -21,14 +21,16 @@ struct nd_cmd_smart {
 } __packed;
 
 #define ND_SMART_HEALTH_VALID	(1 << 0)
-#define ND_SMART_TEMP_VALID 	(1 << 1)
-#define ND_SMART_SPARES_VALID	(1 << 2)
-#define ND_SMART_ALARM_VALID	(1 << 3)
-#define ND_SMART_USED_VALID	(1 << 4)
-#define ND_SMART_SHUTDOWN_VALID	(1 << 5)
-#define ND_SMART_VENDOR_VALID	(1 << 6)
-#define ND_SMART_TEMP_TRIP	(1 << 0)
-#define ND_SMART_SPARE_TRIP	(1 << 1)
+#define ND_SMART_SPARES_VALID	(1 << 1)
+#define ND_SMART_USED_VALID	(1 << 2)
+#define ND_SMART_TEMP_VALID 	(1 << 3)
+#define ND_SMART_CTEMP_VALID 	(1 << 4)
+#define ND_SMART_ALARM_VALID	(1 << 9)
+#define ND_SMART_SHUTDOWN_VALID	(1 << 10)
+#define ND_SMART_VENDOR_VALID	(1 << 11)
+#define ND_SMART_SPARE_TRIP	(1 << 0)
+#define ND_SMART_TEMP_TRIP	(1 << 1)
+#define ND_SMART_CTEMP_TRIP	(1 << 2)
 #define ND_SMART_NON_CRITICAL_HEALTH	(1 << 0)
 #define ND_SMART_CRITICAL_HEALTH	(1 << 1)
 #define ND_SMART_FATAL_HEALTH		(1 << 2)
@@ -37,14 +39,15 @@ struct nd_smart_payload {
 	__u32 flags;
 	__u8 reserved0[4];
 	__u8 health;
-	__u16 temperature;
 	__u8 spares;
-	__u8 alarm_flags;
 	__u8 life_used;
+	__u8 alarm_flags;
+	__u16 temperature;
+	__u16 ctrl_temperature;
+	__u8 reserved1[15];
 	__u8 shutdown_state;
-	__u8 reserved1;
 	__u32 vendor_size;
-	__u8 vendor_data[108];
+	__u8 vendor_data[92];
 } __packed;
 
 struct nd_cmd_smart_threshold {
@@ -53,7 +56,8 @@ struct nd_cmd_smart_threshold {
 } __packed;
 
 struct nd_smart_threshold_payload {
-	__u16 alarm_control;
+	__u8 alarm_control;
+	__u8 reserved0;
 	__u16 temperature;
 	__u8 spares;
 	__u8 reserved[3];

tools/testing/nvdimm/Kbuild

@@ -13,6 +13,7 @@ ldflags-y += --wrap=__release_region
 ldflags-y += --wrap=devm_memremap_pages
 ldflags-y += --wrap=insert_resource
 ldflags-y += --wrap=remove_resource
+ldflags-y += --wrap=acpi_evaluate_object
 
 DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm

tools/testing/nvdimm/test/iomap.c

@@ -17,6 +17,7 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/pfn_t.h>
+#include <linux/acpi.h>
 #include <linux/io.h>
 #include <linux/mm.h>
 #include "nfit_test.h"
@@ -73,7 +74,7 @@ void __iomem *__nfit_test_ioremap(resource_size_t offset, unsigned long size,
 
 	if (nfit_res)
 		return (void __iomem *) nfit_res->buf + offset
-			- nfit_res->res->start;
+			- nfit_res->res.start;
 	return fallback_fn(offset, size);
 }
 
@@ -84,7 +85,7 @@ void __iomem *__wrap_devm_ioremap_nocache(struct device *dev,
 
 	if (nfit_res)
 		return (void __iomem *) nfit_res->buf + offset
-			- nfit_res->res->start;
+			- nfit_res->res.start;
 	return devm_ioremap_nocache(dev, offset, size);
 }
 EXPORT_SYMBOL(__wrap_devm_ioremap_nocache);
@@ -95,7 +96,7 @@ void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
 	if (nfit_res)
-		return nfit_res->buf + offset - nfit_res->res->start;
+		return nfit_res->buf + offset - nfit_res->res.start;
 	return devm_memremap(dev, offset, size, flags);
 }
 EXPORT_SYMBOL(__wrap_devm_memremap);
@@ -107,7 +108,7 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct resource *res,
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
 	if (nfit_res)
-		return nfit_res->buf + offset - nfit_res->res->start;
+		return nfit_res->buf + offset - nfit_res->res.start;
 	return devm_memremap_pages(dev, res, ref, altmap);
 }
 EXPORT_SYMBOL(__wrap_devm_memremap_pages);
@@ -128,7 +129,7 @@ void *__wrap_memremap(resource_size_t offset, size_t size,
 	struct nfit_test_resource *nfit_res = get_nfit_res(offset);
 
 	if (nfit_res)
-		return nfit_res->buf + offset - nfit_res->res->start;
+		return nfit_res->buf + offset - nfit_res->res.start;
 	return memremap(offset, size, flags);
 }
 EXPORT_SYMBOL(__wrap_memremap);
@@ -174,6 +175,63 @@ void __wrap_memunmap(void *addr)
 }
 EXPORT_SYMBOL(__wrap_memunmap);
 
+static bool nfit_test_release_region(struct device *dev,
+		struct resource *parent, resource_size_t start,
+		resource_size_t n);
+
+static void nfit_devres_release(struct device *dev, void *data)
+{
+	struct resource *res = *((struct resource **) data);
+
+	WARN_ON(!nfit_test_release_region(NULL, &iomem_resource, res->start,
+			resource_size(res)));
+}
+
+static int match(struct device *dev, void *__res, void *match_data)
+{
+	struct resource *res = *((struct resource **) __res);
+	resource_size_t start = *((resource_size_t *) match_data);
+
+	return res->start == start;
+}
+
+static bool nfit_test_release_region(struct device *dev,
+		struct resource *parent, resource_size_t start,
+		resource_size_t n)
+{
+	if (parent == &iomem_resource) {
+		struct nfit_test_resource *nfit_res = get_nfit_res(start);
+
+		if (nfit_res) {
+			struct nfit_test_request *req;
+			struct resource *res = NULL;
+
+			if (dev) {
+				devres_release(dev, nfit_devres_release, match,
+						&start);
+				return true;
+			}
+
+			spin_lock(&nfit_res->lock);
+			list_for_each_entry(req, &nfit_res->requests, list)
+				if (req->res.start == start) {
+					res = &req->res;
+					list_del(&req->list);
+					break;
+				}
+			spin_unlock(&nfit_res->lock);
+
+			WARN(!res || resource_size(res) != n,
+					"%s: start: %llx n: %llx mismatch: %pr\n",
+						__func__, start, n, res);
+			if (res)
+				kfree(req);
+			return true;
+		}
+	}
+	return false;
+}
+
 static struct resource *nfit_test_request_region(struct device *dev,
 		struct resource *parent, resource_size_t start,
 		resource_size_t n, const char *name, int flags)
@@ -183,21 +241,57 @@ static struct resource *nfit_test_request_region(struct device *dev,
 	if (parent == &iomem_resource) {
 		nfit_res = get_nfit_res(start);
 		if (nfit_res) {
-			struct resource *res = nfit_res->res + 1;
+			struct nfit_test_request *req;
+			struct resource *res = NULL;
 
-			if (start + n > nfit_res->res->start
-					+ resource_size(nfit_res->res)) {
+			if (start + n > nfit_res->res.start
+					+ resource_size(&nfit_res->res)) {
 				pr_debug("%s: start: %llx n: %llx overflow: %pr\n",
 						__func__, start, n,
-						nfit_res->res);
+						&nfit_res->res);
 				return NULL;
 			}
 
+			spin_lock(&nfit_res->lock);
+			list_for_each_entry(req, &nfit_res->requests, list)
+				if (start == req->res.start) {
+					res = &req->res;
+					break;
+				}
+			spin_unlock(&nfit_res->lock);
+
+			if (res) {
+				WARN(1, "%pr already busy\n", res);
+				return NULL;
+			}
+
+			req = kzalloc(sizeof(*req), GFP_KERNEL);
+			if (!req)
+				return NULL;
+			INIT_LIST_HEAD(&req->list);
+			res = &req->res;
+
 			res->start = start;
 			res->end = start + n - 1;
 			res->name = name;
 			res->flags = resource_type(parent);
 			res->flags |= IORESOURCE_BUSY | flags;
+			spin_lock(&nfit_res->lock);
+			list_add(&req->list, &nfit_res->requests);
+			spin_unlock(&nfit_res->lock);
+
+			if (dev) {
+				struct resource **d;
+
+				d = devres_alloc(nfit_devres_release,
+						sizeof(struct resource *),
+						GFP_KERNEL);
+				if (!d)
+					return NULL;
+				*d = res;
+				devres_add(dev, d);
+			}
+
 			pr_debug("%s: %pr\n", __func__, res);
 			return res;
 		}
@@ -241,29 +335,10 @@ struct resource *__wrap___devm_request_region(struct device *dev,
 }
 EXPORT_SYMBOL(__wrap___devm_request_region);
 
-static bool nfit_test_release_region(struct resource *parent,
-		resource_size_t start, resource_size_t n)
-{
-	if (parent == &iomem_resource) {
-		struct nfit_test_resource *nfit_res = get_nfit_res(start);
-		if (nfit_res) {
-			struct resource *res = nfit_res->res + 1;
-
-			if (start != res->start || resource_size(res) != n)
-				pr_info("%s: start: %llx n: %llx mismatch: %pr\n",
-						__func__, start, n, res);
-			else
-				memset(res, 0, sizeof(*res));
-			return true;
-		}
-	}
-	return false;
-}
-
 void __wrap___release_region(struct resource *parent, resource_size_t start,
 		resource_size_t n)
 {
-	if (!nfit_test_release_region(parent, start, n))
+	if (!nfit_test_release_region(NULL, parent, start, n))
 		__release_region(parent, start, n);
 }
 EXPORT_SYMBOL(__wrap___release_region);
@@ -271,9 +346,25 @@ EXPORT_SYMBOL(__wrap___release_region);
 void __wrap___devm_release_region(struct device *dev, struct resource *parent,
 		resource_size_t start, resource_size_t n)
 {
-	if (!nfit_test_release_region(parent, start, n))
+	if (!nfit_test_release_region(dev, parent, start, n))
 		__devm_release_region(dev, parent, start, n);
 }
 EXPORT_SYMBOL(__wrap___devm_release_region);
 
+acpi_status __wrap_acpi_evaluate_object(acpi_handle handle, acpi_string path,
+		struct acpi_object_list *p, struct acpi_buffer *buf)
+{
+	struct nfit_test_resource *nfit_res = get_nfit_res((long) handle);
+	union acpi_object **obj;
+
+	if (!nfit_res || strcmp(path, "_FIT") || !buf)
+		return acpi_evaluate_object(handle, path, p, buf);
+
+	obj = nfit_res->buf;
+	buf->length = sizeof(union acpi_object);
+	buf->pointer = *obj;
+	return AE_OK;
+}
+EXPORT_SYMBOL(__wrap_acpi_evaluate_object);
+
 MODULE_LICENSE("GPL v2");

tools/testing/nvdimm/test/nfit.c

@@ -132,6 +132,8 @@ static u32 handle[NUM_DCR] = {
 	[4] = NFIT_DIMM_HANDLE(0, 1, 0, 0, 0),
 };
 
+static unsigned long dimm_fail_cmd_flags[NUM_DCR];
+
 struct nfit_test {
 	struct acpi_nfit_desc acpi_desc;
 	struct platform_device pdev;
@@ -154,11 +156,14 @@ struct nfit_test {
 	int (*alloc)(struct nfit_test *t);
 	void (*setup)(struct nfit_test *t);
 	int setup_hotplug;
+	union acpi_object **_fit;
+	dma_addr_t _fit_dma;
 	struct ars_state {
 		struct nd_cmd_ars_status *ars_status;
 		unsigned long deadline;
 		spinlock_t lock;
 	} ars_state;
+	struct device *dimm_dev[NUM_DCR];
 };
 
 static struct nfit_test *to_nfit_test(struct device *dev)
@@ -411,6 +416,9 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 		if (i >= ARRAY_SIZE(handle))
 			return -ENXIO;
 
+		if ((1 << func) & dimm_fail_cmd_flags[i])
+			return -EIO;
+
 		switch (func) {
 		case ND_CMD_GET_CONFIG_SIZE:
 			rc = nfit_test_cmd_get_config_size(buf, buf_len);
@@ -428,6 +436,9 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
 			break;
 		case ND_CMD_SMART_THRESHOLD:
 			rc = nfit_test_cmd_smart_threshold(buf, buf_len);
+			device_lock(&t->pdev.dev);
+			__acpi_nvdimm_notify(t->dimm_dev[i], 0x81);
+			device_unlock(&t->pdev.dev);
 			break;
 		default:
 			return -ENOTTY;
@@ -467,14 +478,12 @@ static struct nfit_test *instances[NUM_NFITS];
 static void release_nfit_res(void *data)
 {
 	struct nfit_test_resource *nfit_res = data;
-	struct resource *res = nfit_res->res;
 
 	spin_lock(&nfit_test_lock);
 	list_del(&nfit_res->list);
 	spin_unlock(&nfit_test_lock);
 
 	vfree(nfit_res->buf);
-	kfree(res);
 	kfree(nfit_res);
 }
 
@@ -482,12 +491,11 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma,
 		void *buf)
 {
 	struct device *dev = &t->pdev.dev;
-	struct resource *res = kzalloc(sizeof(*res) * 2, GFP_KERNEL);
 	struct nfit_test_resource *nfit_res = kzalloc(sizeof(*nfit_res),
 			GFP_KERNEL);
 	int rc;
 
-	if (!res || !buf || !nfit_res)
+	if (!buf || !nfit_res)
 		goto err;
 	rc = devm_add_action(dev, release_nfit_res, nfit_res);
 	if (rc)
@@ -496,10 +504,11 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma,
 	memset(buf, 0, size);
 	nfit_res->dev = dev;
 	nfit_res->buf = buf;
-	nfit_res->res = res;
-	res->start = *dma;
-	res->end = *dma + size - 1;
-	res->name = "NFIT";
+	nfit_res->res.start = *dma;
+	nfit_res->res.end = *dma + size - 1;
+	nfit_res->res.name = "NFIT";
+	spin_lock_init(&nfit_res->lock);
+	INIT_LIST_HEAD(&nfit_res->requests);
 	spin_lock(&nfit_test_lock);
 	list_add(&nfit_res->list, &t->resources);
 	spin_unlock(&nfit_test_lock);
@@ -508,7 +517,6 @@ static void *__test_alloc(struct nfit_test *t, size_t size, dma_addr_t *dma,
  err:
 	if (buf)
 		vfree(buf);
-	kfree(res);
 	kfree(nfit_res);
 	return NULL;
 }
@@ -533,13 +541,13 @@ static struct nfit_test_resource *nfit_test_lookup(resource_size_t addr)
 			continue;
 		spin_lock(&nfit_test_lock);
 		list_for_each_entry(n, &t->resources, list) {
-			if (addr >= n->res->start && (addr < n->res->start
-						+ resource_size(n->res))) {
+			if (addr >= n->res.start && (addr < n->res.start
+						+ resource_size(&n->res))) {
 				nfit_res = n;
 				break;
 			} else if (addr >= (unsigned long) n->buf
 					&& (addr < (unsigned long) n->buf
-						+ resource_size(n->res))) {
+						+ resource_size(&n->res))) {
 				nfit_res = n;
 				break;
 			}
@@ -564,6 +572,86 @@ static int ars_state_init(struct device *dev, struct ars_state *ars_state)
 	return 0;
 }
 
+static void put_dimms(void *data)
+{
+	struct device **dimm_dev = data;
+	int i;
+
+	for (i = 0; i < NUM_DCR; i++)
+		if (dimm_dev[i])
+			device_unregister(dimm_dev[i]);
+}
+
+static struct class *nfit_test_dimm;
+
+static int dimm_name_to_id(struct device *dev)
+{
+	int dimm;
+
+	if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1
+			|| dimm >= NUM_DCR || dimm < 0)
+		return -ENXIO;
+	return dimm;
+}
+
+
+static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	int dimm = dimm_name_to_id(dev);
+
+	if (dimm < 0)
+		return dimm;
+
+	return sprintf(buf, "%#x", handle[dimm]);
+}
+DEVICE_ATTR_RO(handle);
+
+static ssize_t fail_cmd_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	int dimm = dimm_name_to_id(dev);
+
+	if (dimm < 0)
+		return dimm;
+
+	return sprintf(buf, "%#lx\n", dimm_fail_cmd_flags[dimm]);
+}
+
+static ssize_t fail_cmd_store(struct device *dev, struct device_attribute *attr,
+		const char *buf, size_t size)
+{
+	int dimm = dimm_name_to_id(dev);
+	unsigned long val;
+	ssize_t rc;
+
+	if (dimm < 0)
+		return dimm;
+
+	rc = kstrtol(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	dimm_fail_cmd_flags[dimm] = val;
+	return size;
+}
+static DEVICE_ATTR_RW(fail_cmd);
+
+static struct attribute *nfit_test_dimm_attributes[] = {
+	&dev_attr_fail_cmd.attr,
+	&dev_attr_handle.attr,
+	NULL,
+};
+
+static struct attribute_group nfit_test_dimm_attribute_group = {
+	.attrs = nfit_test_dimm_attributes,
+};
+
+static const struct attribute_group *nfit_test_dimm_attribute_groups[] = {
+	&nfit_test_dimm_attribute_group,
+	NULL,
+};
+
 static int nfit_test0_alloc(struct nfit_test *t)
 {
 	size_t nfit_size = sizeof(struct acpi_nfit_system_address) * NUM_SPA
@@ -616,6 +704,21 @@ static int nfit_test0_alloc(struct nfit_test *t)
 			return -ENOMEM;
 	}
 
+	t->_fit = test_alloc(t, sizeof(union acpi_object **), &t->_fit_dma);
+	if (!t->_fit)
+		return -ENOMEM;
+
+	if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t->dimm_dev))
+		return -ENOMEM;
+	for (i = 0; i < NUM_DCR; i++) {
+		t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
+				&t->pdev.dev, 0, NULL,
+				nfit_test_dimm_attribute_groups,
+				"test_dimm%d", i);
+		if (!t->dimm_dev[i])
+			return -ENOMEM;
+	}
+
 	return ars_state_init(&t->pdev.dev, &t->ars_state);
 }
 
@@ -1409,6 +1512,8 @@ static int nfit_test_probe(struct platform_device *pdev)
 	struct acpi_nfit_desc *acpi_desc;
 	struct device *dev = &pdev->dev;
 	struct nfit_test *nfit_test;
+	struct nfit_mem *nfit_mem;
+	union acpi_object *obj;
 	int rc;
 
 	nfit_test = to_nfit_test(&pdev->dev);
@@ -1476,14 +1581,30 @@ static int nfit_test_probe(struct platform_device *pdev)
 	if (nfit_test->setup != nfit_test0_setup)
 		return 0;
 
-	flush_work(&acpi_desc->work);
 	nfit_test->setup_hotplug = 1;
 	nfit_test->setup(nfit_test);
 
-	rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf,
-			nfit_test->nfit_size);
-	if (rc)
-		return rc;
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+	obj->type = ACPI_TYPE_BUFFER;
+	obj->buffer.length = nfit_test->nfit_size;
+	obj->buffer.pointer = nfit_test->nfit_buf;
+	*(nfit_test->_fit) = obj;
+	__acpi_nfit_notify(&pdev->dev, nfit_test, 0x80);
+
+	/* associate dimm devices with nfit_mem data for notification testing */
+	mutex_lock(&acpi_desc->init_mutex);
+	list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) {
+		u32 nfit_handle = __to_nfit_memdev(nfit_mem)->device_handle;
+		int i;
+
+		for (i = 0; i < NUM_DCR; i++)
+			if (nfit_handle == handle[i])
+				dev_set_drvdata(nfit_test->dimm_dev[i],
+						nfit_mem);
+	}
+	mutex_unlock(&acpi_desc->init_mutex);
 
 	return 0;
 }
@@ -1518,6 +1639,10 @@ static __init int nfit_test_init(void)
 {
 	int rc, i;
 
+	nfit_test_dimm = class_create(THIS_MODULE, "nfit_test_dimm");
+	if (IS_ERR(nfit_test_dimm))
+		return PTR_ERR(nfit_test_dimm);
+
 	nfit_test_setup(nfit_test_lookup);
 
 	for (i = 0; i < NUM_NFITS; i++) {
@@ -1584,6 +1709,7 @@ static __exit void nfit_test_exit(void)
 	for (i = 0; i < NUM_NFITS; i++)
 		platform_device_unregister(&instances[i]->pdev);
 	nfit_test_teardown();
+	class_destroy(nfit_test_dimm);
 }
 
 module_init(nfit_test_init);

tools/testing/nvdimm/test/nfit_test.h

@@ -13,11 +13,21 @@
 #ifndef __NFIT_TEST_H__
 #define __NFIT_TEST_H__
 #include <linux/list.h>
+#include <linux/ioport.h>
+#include <linux/spinlock_types.h>
+
+struct nfit_test_request {
+	struct list_head list;
+	struct resource res;
+};
 
 struct nfit_test_resource {
+	struct list_head requests;
 	struct list_head list;
-	struct resource *res;
+	struct resource res;
 	struct device *dev;
+	spinlock_t lock;
+	int req_count;
 	void *buf;
 };