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
  ...

4 files changed, 362 insertions, 232 deletions

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 +437,257 @@ static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	return rc;
 }
 
-static void dax_dev_vm_open(struct vm_area_struct *vma)
-{
-	struct file *filp = vma->vm_file;
-	struct dax_dev *dax_dev = filp->private_data;
-
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	kref_get(&dax_dev->kref);
-}
-
-static void dax_dev_vm_close(struct vm_area_struct *vma)
-{
-	struct file *filp = vma->vm_file;
-	struct dax_dev *dax_dev = filp->private_data;
-
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
-	dax_dev_put(dax_dev);
-}
-
 static const struct vm_operations_struct dax_dev_vm_ops = {
 	.fault = dax_dev_fault,
 	.pmd_fault = dax_dev_pmd_fault,
-	.open = dax_dev_vm_open,
-	.close = dax_dev_vm_close,
 };
 
-static int dax_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
 {
 	struct dax_dev *dax_dev = filp->private_data;
 	int rc;
 
-	dev_dbg(dax_dev->dev, "%s\n", __func__);
+	dev_dbg(&dax_dev->dev, "%s\n", __func__);
 
 	rc = check_vma(dax_dev, vma, __func__);
 	if (rc)
 		return rc;
 
-	kref_get(&dax_dev->kref);
 	vma->vm_ops = &dax_dev_vm_ops;
 	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	return 0;
+}
+
+/* return an unmapped area aligned to the dax region specified alignment */
+static unsigned long dax_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 dax_open(struct inode *inode, struct file *filp)
+{
+	struct dax_dev *dax_dev;
+
+	dax_dev = container_of(inode->i_cdev, struct dax_dev, cdev);
+	dev_dbg(&dax_dev->dev, "%s\n", __func__);
+	inode->i_mapping = dax_dev->inode->i_mapping;
+	inode->i_mapping->host = dax_dev->inode;
+	filp->f_mapping = inode->i_mapping;
+	filp->private_data = dax_dev;
+	inode->i_flags = S_DAX;
+
+	return 0;
+}
+
+static int dax_release(struct inode *inode, struct file *filp)
+{
+	struct dax_dev *dax_dev = filp->private_data;
+
+	dev_dbg(&dax_dev->dev, "%s\n", __func__);
+	return 0;
 }
 
 static const struct file_operations dax_fops = {
 	.llseek = noop_llseek,
 	.owner = THIS_MODULE,
-	.open = dax_dev_open,
-	.release = dax_dev_release,
-	.get_unmapped_area = dax_dev_get_unmapped_area,
-	.mmap = dax_dev_mmap,
+	.open = dax_open,
+	.release = dax_release,
+	.get_unmapped_area = dax_get_unmapped_area,
+	.mmap = dax_mmap,
 };
 
+static void dax_dev_release(struct device *dev)
+{
+	struct dax_dev *dax_dev = to_dax_dev(dev);
+	struct dax_region *dax_region = dax_dev->region;
+
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
+	dax_region_put(dax_region);
+	iput(dax_dev->inode);
+	kfree(dax_dev);
+}
+
+static void unregister_dax_dev(void *dev)
+{
+	struct dax_dev *dax_dev = to_dax_dev(dev);
+	struct cdev *cdev = &dax_dev->cdev;
+
+	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();
+	unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
+	cdev_del(cdev);
+	device_unregister(dev);
+}
+
+struct dax_dev *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;
+	int rc = 0, minor, i;
+	struct device *dev;
+	struct cdev *cdev;
+	dev_t dev_t;
+
+	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
+	if (!dax_dev)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < count; i++) {
+		if (!IS_ALIGNED(res[i].start, dax_region->align)
+				|| !IS_ALIGNED(resource_size(&res[i]),
+					dax_region->align)) {
+			rc = -EINVAL;
+			break;
+		}
+		dax_dev->res[i].start = res[i].start;
+		dax_dev->res[i].end = res[i].end;
+	}
+
+	if (i < count)
+		goto err_id;
+
+	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(MAJOR(dax_devt), minor);
+	dev = &dax_dev->dev;
+	dax_dev->inode = dax_inode_get(&dax_dev->cdev, dev_t);
+	if (!dax_dev->inode) {
+		rc = -ENOMEM;
+		goto err_inode;
+	}
+
+	/* device_initialize() so cdev can reference kobj parent */
+	device_initialize(dev);
+
+	cdev = &dax_dev->cdev;
+	cdev_init(cdev, &dax_fops);
+	cdev->owner = parent->driver->owner;
+	cdev->kobj.parent = &dev->kobj;
+	rc = cdev_add(&dax_dev->cdev, dev_t, 1);
+	if (rc)
+		goto err_cdev;
+
+	/* from here on we're committed to teardown via dax_dev_release() */
+	dax_dev->num_resources = count;
+	dax_dev->alive = true;
+	dax_dev->region = dax_region;
+	kref_get(&dax_region->kref);
+
+	dev->devt = dev_t;
+	dev->class = dax_class;
+	dev->parent = parent;
+	dev->groups = dax_attribute_groups;
+	dev->release = dax_dev_release;
+	dev_set_name(dev, "dax%d.%d", dax_region->id, dax_dev->id);
+	rc = device_add(dev);
+	if (rc) {
+		put_device(dev);
+		return ERR_PTR(rc);
+	}
+
+	rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
+	if (rc)
+		return ERR_PTR(rc);
+
+	return dax_dev;
+
+ err_cdev:
+	iput(dax_dev->inode);
+ err_inode:
+	ida_simple_remove(&dax_minor_ida, minor);
+ err_minor:
+	ida_simple_remove(&dax_region->ida, dax_dev->id);
+ err_id:
+	kfree(dax_dev);
+
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_GPL(devm_create_dax_dev);
+
 static int __init dax_init(void)
 {
 	int rc;
 
-	rc = register_chrdev(0, "dax", &dax_fops);
-	if (rc < 0)
+	rc = dax_inode_init();
+	if (rc)
 		return rc;
-	dax_major = rc;
+
+	nr_dax = max(nr_dax, 256);
+	rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax");
+	if (rc)
+		goto err_chrdev;
 
 	dax_class = class_create(THIS_MODULE, "dax");
 	if (IS_ERR(dax_class)) {
-		unregister_chrdev(dax_major, "dax");
-		return PTR_ERR(dax_class);
+		rc = PTR_ERR(dax_class);
+		goto err_class;
 	}
 
 	return 0;
+
+ err_class:
+	unregister_chrdev_region(dax_devt, nr_dax);
+ err_chrdev:
+	dax_inode_exit();
+	return rc;
 }
 
 static void __exit dax_exit(void)
 {
 	class_destroy(dax_class);
-	unregister_chrdev(dax_major, "dax");
+	unregister_chrdev_region(dax_devt, nr_dax);
 	ida_destroy(&dax_minor_ida);
+	dax_inode_exit();
 }
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/dax/dax.h b/drivers/dax/dax.h
index d8b8f1f25054..ddd829ab58c0 100644
--- a/drivers/dax/dax.h
+++ b/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__ */
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index 1f01e98c83c7..9630d8837ba9 100644
--- a/drivers/dax/pmem.c
+++ b/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 = {