27 files changed, 1940 insertions, 751 deletions

diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index e1d5ea6d5e40..71a7d07c28c9 100644
--- a/drivers/acpi/nfit/core.c
+++ b/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[] = {
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index 161f91539ae6..e5ce81c38eed 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/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);
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index e894ded24d99..14296f5267c8 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/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__ */
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index cedab7572de3..daadd20aa936 100644
--- a/drivers/dax/Kconfig
+++ b/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
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 29f600f2c447..0e499bfca41c 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -13,15 +13,25 @@
 #include <linux/pagemap.h>
 #include <linux/module.h>
 #include <linux/device.h>
+#include <linux/mount.h>
 #include <linux/pfn_t.h>
+#include <linux/hash.h>
+#include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include "dax.h"
 
-static int dax_major;
+static dev_t dax_devt;
 static struct class *dax_class;
 static DEFINE_IDA(dax_minor_ida);
+static int nr_dax = CONFIG_NR_DEV_DAX;
+module_param(nr_dax, int, S_IRUGO);
+static struct vfsmount *dax_mnt;
+static struct kmem_cache *dax_cache __read_mostly;
+static struct super_block *dax_superblock __read_mostly;
+MODULE_PARM_DESC(nr_dax, "max number of device-dax instances");
 
 /**
  * struct dax_region - mapping infrastructure for dax devices
@@ -48,7 +58,7 @@ struct dax_region {
  * struct dax_dev - subdivision of a dax region
  * @region - parent region
  * @dev - device backing the character device
- * @kref - enable this data to be tracked in filp->private_data
+ * @cdev - core chardev data
  * @alive - !alive + rcu grace period == no new mappings can be established
  * @id - child id in the region
  * @num_resources - number of physical address extents in this device
@@ -56,41 +66,139 @@ struct dax_region {
  */
 struct dax_dev {
 	struct dax_region *region;
-	struct device *dev;
-	struct kref kref;
+	struct inode *inode;
+	struct device dev;
+	struct cdev cdev;
 	bool alive;
 	int id;
 	int num_resources;
 	struct resource res[0];
 };
 
-static void dax_region_free(struct kref *kref)
+static struct inode *dax_alloc_inode(struct super_block *sb)
 {
-	struct dax_region *dax_region;
+	return kmem_cache_alloc(dax_cache, GFP_KERNEL);
+}
 
-	dax_region = container_of(kref, struct dax_region, kref);
-	kfree(dax_region);
+static void dax_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+
+	kmem_cache_free(dax_cache, inode);
 }
 
-void dax_region_put(struct dax_region *dax_region)
+static void dax_destroy_inode(struct inode *inode)
 {
-	kref_put(&dax_region->kref, dax_region_free);
+	call_rcu(&inode->i_rcu, dax_i_callback);
 }
-EXPORT_SYMBOL_GPL(dax_region_put);
 
-static void dax_dev_free(struct kref *kref)
+static const struct super_operations dax_sops = {
+	.statfs = simple_statfs,
+	.alloc_inode = dax_alloc_inode,
+	.destroy_inode = dax_destroy_inode,
+	.drop_inode = generic_delete_inode,
+};
+
+static struct dentry *dax_mount(struct file_system_type *fs_type,
+		int flags, const char *dev_name, void *data)
 {
-	struct dax_dev *dax_dev;
+	return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC);
+}
 
-	dax_dev = container_of(kref, struct dax_dev, kref);
-	dax_region_put(dax_dev->region);
-	kfree(dax_dev);
+static struct file_system_type dax_type = {
+	.name = "dax",
+	.mount = dax_mount,
+	.kill_sb = kill_anon_super,
+};
+
+static int dax_test(struct inode *inode, void *data)
+{
+	return inode->i_cdev == data;
+}
+
+static int dax_set(struct inode *inode, void *data)
+{
+	inode->i_cdev = data;
+	return 0;
+}
+
+static struct inode *dax_inode_get(struct cdev *cdev, dev_t devt)
+{
+	struct inode *inode;
+
+	inode = iget5_locked(dax_superblock, hash_32(devt + DAXFS_MAGIC, 31),
+			dax_test, dax_set, cdev);
+
+	if (!inode)
+		return NULL;
+
+	if (inode->i_state & I_NEW) {
+		inode->i_mode = S_IFCHR;
+		inode->i_flags = S_DAX;
+		inode->i_rdev = devt;
+		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
+		unlock_new_inode(inode);
+	}
+	return inode;
+}
+
+static void init_once(void *inode)
+{
+	inode_init_once(inode);
+}
+
+static int dax_inode_init(void)
+{
+	int rc;
+
+	dax_cache = kmem_cache_create("dax_cache", sizeof(struct inode), 0,
+			(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
+			 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+			init_once);
+	if (!dax_cache)
+		return -ENOMEM;
+
+	rc = register_filesystem(&dax_type);
+	if (rc)
+		goto err_register_fs;
+
+	dax_mnt = kern_mount(&dax_type);
+	if (IS_ERR(dax_mnt)) {
+		rc = PTR_ERR(dax_mnt);
+		goto err_mount;
+	}
+	dax_superblock = dax_mnt->mnt_sb;
+
+	return 0;
+
+ err_mount:
+	unregister_filesystem(&dax_type);
+ err_register_fs:
+	kmem_cache_destroy(dax_cache);
+
+	return rc;
 }
 
-static void dax_dev_put(struct dax_dev *dax_dev)
+static void dax_inode_exit(void)
+{
+	kern_unmount(dax_mnt);
+	unregister_filesystem(&dax_type);
+	kmem_cache_destroy(dax_cache);
+}
+
+static void dax_region_free(struct kref *kref)
+{
+	struct dax_region *dax_region;
+
+	dax_region = container_of(kref, struct dax_region, kref);
+	kfree(dax_region);
+}
+
+void dax_region_put(struct dax_region *dax_region)
 {
-	kref_put(&dax_dev->kref, dax_dev_free);
+	kref_put(&dax_region->kref, dax_region_free);
 }
+EXPORT_SYMBOL_GPL(dax_region_put);
 
 struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct resource *res, unsigned int align, void *addr,
@@ -98,8 +206,11 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 {
 	struct dax_region *dax_region;
 
-	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
+	if (!IS_ALIGNED(res->start, align)
+			|| !IS_ALIGNED(resource_size(res), align))
+		return NULL;
 
+	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
 	if (!dax_region)
 		return NULL;
 
@@ -116,10 +227,15 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 }
 EXPORT_SYMBOL_GPL(alloc_dax_region);
 
+static struct dax_dev *to_dax_dev(struct device *dev)
+{
+	return container_of(dev, struct dax_dev, dev);
+}
+
 static ssize_t size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	struct dax_dev *dax_dev = to_dax_dev(dev);
 	unsigned long long size = 0;
 	int i;
 
@@ -144,180 +260,11 @@ static const struct attribute_group *dax_attribute_groups[] = {
 	NULL,
 };
 
-static void unregister_dax_dev(void *_dev)
-{
-	struct device *dev = _dev;
-	struct dax_dev *dax_dev = dev_get_drvdata(dev);
-	struct dax_region *dax_region = dax_dev->region;
-
-	dev_dbg(dev, "%s\n", __func__);
-
-	/*
-	 * Note, rcu is not protecting the liveness of dax_dev, rcu is
-	 * ensuring that any fault handlers that might have seen
-	 * dax_dev->alive == true, have completed.  Any fault handlers
-	 * that start after synchronize_rcu() has started will abort
-	 * upon seeing dax_dev->alive == false.
-	 */
-	dax_dev->alive = false;
-	synchronize_rcu();
-
-	get_device(dev);
-	device_unregister(dev);
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
-	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
-	put_device(dev);
-	dax_dev_put(dax_dev);
-}
-
-int devm_create_dax_dev(struct dax_region *dax_region, struct resource *res,
-		int count)
-{
-	struct device *parent = dax_region->dev;
-	struct dax_dev *dax_dev;
-	struct device *dev;
-	int rc, minor;
-	dev_t dev_t;
-
-	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
-	if (!dax_dev)
-		return -ENOMEM;
-	memcpy(dax_dev->res, res, sizeof(*res) * count);
-	dax_dev->num_resources = count;
-	kref_init(&dax_dev->kref);
-	dax_dev->alive = true;
-	dax_dev->region = dax_region;
-	kref_get(&dax_region->kref);
-
-	dax_dev->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
-	if (dax_dev->id < 0) {
-		rc = dax_dev->id;
-		goto err_id;
-	}
-
-	minor = ida_simple_get(&dax_minor_ida, 0, 0, GFP_KERNEL);
-	if (minor < 0) {
-		rc = minor;
-		goto err_minor;
-	}
-
-	dev_t = MKDEV(dax_major, minor);
-	dev = device_create_with_groups(dax_class, parent, dev_t, dax_dev,
-			dax_attribute_groups, "dax%d.%d", dax_region->id,
-			dax_dev->id);
-	if (IS_ERR(dev)) {
-		rc = PTR_ERR(dev);
-		goto err_create;
-	}
-	dax_dev->dev = dev;
-
-	rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
-	if (rc)
-		return rc;
-
-	return 0;
-
- err_create:
-	ida_simple_remove(&dax_minor_ida, minor);
- err_minor:
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
- err_id:
-	dax_dev_put(dax_dev);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(devm_create_dax_dev);
-
-/* return an unmapped area aligned to the dax region specified alignment */
-static unsigned long dax_dev_get_unmapped_area(struct file *filp,
-		unsigned long addr, unsigned long len, unsigned long pgoff,
-		unsigned long flags)
-{
-	unsigned long off, off_end, off_align, len_align, addr_align, align;
-	struct dax_dev *dax_dev = filp ? filp->private_data : NULL;
-	struct dax_region *dax_region;
-
-	if (!dax_dev || addr)
-		goto out;
-
-	dax_region = dax_dev->region;
-	align = dax_region->align;
-	off = pgoff << PAGE_SHIFT;
-	off_end = off + len;
-	off_align = round_up(off, align);
-
-	if ((off_end <= off_align) || ((off_end - off_align) < align))
-		goto out;
-
-	len_align = len + align;
-	if ((off + len_align) < off)
-		goto out;
-
-	addr_align = current->mm->get_unmapped_area(filp, addr, len_align,
-			pgoff, flags);
-	if (!IS_ERR_VALUE(addr_align)) {
-		addr_align += (off - addr_align) & (align - 1);
-		return addr_align;
-	}
- out:
-	return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
-}
-
-static int __match_devt(struct device *dev, const void *data)
-{
-	const dev_t *devt = data;
-
-	return dev->devt == *devt;
-}
-
-static struct device *dax_dev_find(dev_t dev_t)
-{
-	return class_find_device(dax_class, NULL, &dev_t, __match_devt);
-}
-
-static int dax_dev_open(struct inode *inode, struct file *filp)
-{
-	struct dax_dev *dax_dev = NULL;
-	struct device *dev;
-
-	dev = dax_dev_find(inode->i_rdev);
-	if (!dev)
-		return -ENXIO;
-
-	device_lock(dev);
-	dax_dev = dev_get_drvdata(dev);
-	if (dax_dev) {
-		dev_dbg(dev, "%s\n", __func__);
-		filp->private_data = dax_dev;
-		kref_get(&dax_dev->kref);
-		inode->i_flags = S_DAX;
-	}
-	device_unlock(dev);
-
-	if (!dax_dev) {
-		put_device(dev);
-		return -ENXIO;
-	}
-	return 0;
-}
-
-static int dax_dev_release(struct inode *inode, struct file *filp)
-{
-	struct dax_dev *dax_dev = filp->private_data;
-	struct device *dev = dax_dev->dev;
-
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	dax_dev_put(dax_dev);
-	put_device(dev);
-
-	return 0;
-}
-
 static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		const char *func)
 {
 	struct dax_region *dax_region = dax_dev->region;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 	unsigned long mask;
 
 	if (!dax_dev->alive)
@@ -382,7 +329,7 @@ static int __dax_dev_fault(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 		struct vm_fault *vmf)
 {
 	unsigned long vaddr = (unsigned long) vmf->virtual_address;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	int rc = VM_FAULT_SIGBUS;
 	phys_addr_t phys;
@@ -422,7 +369,7 @@ static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	struct file *filp = vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
-	dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
 			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
 			? "write" : "read", vma->vm_start, vma->vm_end);
 	rcu_read_lock();
@@ -437,7 +384,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
 		unsigned int flags)
 {
 	unsigned long pmd_addr = addr & PMD_MASK;
-	struct device *dev = dax_dev->dev;
+	struct device *dev = &dax_dev->dev;
 	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
@@ -479,7 +426,7 @@ static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	struct file *filp = vma->vm_file;
 	struct dax_dev *dax_dev = filp->private_data;
 
-	dev_dbg(dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
 			current->comm, (flags & FAULT_FLAG_WRITE)
 			? "write" : "read", vma->vm_start, vma->vm_end);
 
@@ -490,81 +437,2