Merge tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull libnvdimm updates from Dan Williams:
 "The bulk of this has been in multiple -next releases. There were a few
  late breaking fixes and small features that got added in the last
  couple days, but the whole set has received a build success
  notification from the kbuild robot.

  Change summary:

   - Region media error reporting: A libnvdimm region device is the
     parent to one or more namespaces. To date, media errors have been
     reported via the "badblocks" attribute attached to pmem block
     devices for namespaces in "raw" or "memory" mode. Given that
     namespaces can be in "device-dax" or "btt-sector" mode this new
     interface reports media errors generically, i.e. independent of
     namespace modes or state.

     This subsequently allows userspace tooling to craft "ACPI 6.1
     Section 9.20.7.6 Function Index 4 - Clear Uncorrectable Error"
     requests and submit them via the ioctl path for NVDIMM root bus
     devices.

   - Introduce 'struct dax_device' and 'struct dax_operations': Prompted
     by a request from Linus and feedback from Christoph this allows for
     dax capable drivers to publish their own custom dax operations.
     This fixes the broken assumption that all dax operations are
     related to a persistent memory device, and makes it easier for
     other architectures and platforms to add customized persistent
     memory support.

   - 'libnvdimm' core updates: A new "deep_flush" sysfs attribute is
     available for storage appliance applications to manually trigger
     memory controllers to drain write-pending buffers that would
     otherwise be flushed automatically by the platform ADR
     (asynchronous-DRAM-refresh) mechanism at a power loss event.
     Support for "locked" DIMMs is included to prevent namespaces from
     surfacing when the namespace label data area is locked. Finally,
     fixes for various reported deadlocks and crashes, also tagged for
     -stable.

   - ACPI / nfit driver updates: General updates of the nfit driver to
     add DSM command overrides, ACPI 6.1 health state flags support, DSM
     payload debug available by default, and various fixes.

  Acknowledgements that came after the branch was pushed:

   - commmit 565851c972b5 "device-dax: fix sysfs attribute deadlock":
     Tested-by: Yi Zhang <yizhan@redhat.com>

   - commit 23f498448362 "libnvdimm: rework region badblocks clearing"
     Tested-by: Toshi Kani <toshi.kani@hpe.com>"

* tag 'libnvdimm-for-4.12' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (52 commits)
  libnvdimm, pfn: fix 'npfns' vs section alignment
  libnvdimm: handle locked label storage areas
  libnvdimm: convert NDD_ flags to use bitops, introduce NDD_LOCKED
  brd: fix uninitialized use of brd->dax_dev
  block, dax: use correct format string in bdev_dax_supported
  device-dax: fix sysfs attribute deadlock
  libnvdimm: restore "libnvdimm: band aid btt vs clear poison locking"
  libnvdimm: fix nvdimm_bus_lock() vs device_lock() ordering
  libnvdimm: rework region badblocks clearing
  acpi, nfit: kill ACPI_NFIT_DEBUG
  libnvdimm: fix clear length of nvdimm_forget_poison()
  libnvdimm, pmem: fix a NULL pointer BUG in nd_pmem_notify
  libnvdimm, region: sysfs trigger for nvdimm_flush()
  libnvdimm: fix phys_addr for nvdimm_clear_poison
  x86, dax, pmem: remove indirection around memcpy_from_pmem()
  block: remove block_device_operations ->direct_access()
  block, dax: convert bdev_dax_supported() to dax_direct_access()
  filesystem-dax: convert to dax_direct_access()
  Revert "block: use DAX for partition table reads"
  ext2, ext4, xfs: retrieve dax_device for iomap operations
  ...

8 files changed, 677 insertions, 371 deletions

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 9e95bf94eb13..b7053eafd88e 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig
@@ -1,8 +1,13 @@
-menuconfig DEV_DAX
+menuconfig DAX
 	tristate "DAX: direct access to differentiated memory"
+	select SRCU
 	default m if NVDIMM_DAX
+
+if DAX
+
+config DEV_DAX
+	tristate "Device DAX: direct access mapping device"
 	depends on TRANSPARENT_HUGEPAGE
-	select SRCU
 	help
 	  Support raw access to differentiated (persistence, bandwidth,
 	  latency...) memory via an mmap(2) capable character
@@ -11,7 +16,6 @@ menuconfig DEV_DAX
 	  baseline memory pool.  Mappings of a /dev/daxX.Y device impose
 	  restrictions that make the mapping behavior deterministic.
 
-if DEV_DAX
 
 config DEV_DAX_PMEM
 	tristate "PMEM DAX: direct access to persistent memory"
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 27c54e38478a..dc7422530462 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -1,4 +1,7 @@
-obj-$(CONFIG_DEV_DAX) += dax.o
+obj-$(CONFIG_DAX) += dax.o
+obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
 
+dax-y := super.o
 dax_pmem-y := pmem.o
+device_dax-y := device.o
diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
new file mode 100644
index 000000000000..b6fc4f04636d
--- /dev/null
+++ b/drivers/dax/dax-private.h
@@ -0,0 +1,57 @@
+/*
+ * Copyright(c) 2016 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef __DAX_PRIVATE_H__
+#define __DAX_PRIVATE_H__
+
+#include <linux/device.h>
+#include <linux/cdev.h>
+
+/**
+ * struct dax_region - mapping infrastructure for dax devices
+ * @id: kernel-wide unique region for a memory range
+ * @base: linear address corresponding to @res
+ * @kref: to pin while other agents have a need to do lookups
+ * @dev: parent device backing this region
+ * @align: allocation and mapping alignment for child dax devices
+ * @res: physical address range of the region
+ * @pfn_flags: identify whether the pfns are paged back or not
+ */
+struct dax_region {
+	int id;
+	struct ida ida;
+	void *base;
+	struct kref kref;
+	struct device *dev;
+	unsigned int align;
+	struct resource res;
+	unsigned long pfn_flags;
+};
+
+/**
+ * struct dev_dax - instance data for a subdivision of a dax region
+ * @region - parent region
+ * @dax_dev - core dax functionality
+ * @dev - device core
+ * @id - child id in the region
+ * @num_resources - number of physical address extents in this device
+ * @res - array of physical address ranges
+ */
+struct dev_dax {
+	struct dax_region *region;
+	struct dax_device *dax_dev;
+	struct device dev;
+	int id;
+	int num_resources;
+	struct resource res[0];
+};
+#endif
diff --git a/drivers/dax/dax.h b/drivers/dax/dax.h
index ddd829ab58c0..f9e5feea742c 100644
--- a/drivers/dax/dax.h
+++ b/drivers/dax/dax.h
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation. All rights reserved.
+ * Copyright(c) 2016 - 2017 Intel Corporation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -12,14 +12,7 @@
  */
 #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);
-struct dax_dev *devm_create_dax_dev(struct dax_region *dax_region,
-		struct resource *res, int count);
+struct dax_device;
+struct dax_device *inode_dax(struct inode *inode);
+struct inode *dax_inode(struct dax_device *dax_dev);
 #endif /* __DAX_H__ */
diff --git a/drivers/dax/device-dax.h b/drivers/dax/device-dax.h
new file mode 100644
index 000000000000..fdcd9769ffde
--- /dev/null
+++ b/drivers/dax/device-dax.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright(c) 2016 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#ifndef __DEVICE_DAX_H__
+#define __DEVICE_DAX_H__
+struct device;
+struct dev_dax;
+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);
+struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region,
+		struct resource *res, int count);
+#endif /* __DEVICE_DAX_H__ */
diff --git a/drivers/dax/dax.c b/drivers/dax/device.c
index 19795eb35579..006e657dfcb9 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/device.c
@@ -1,5 +1,5 @@
 /*
- * Copyright(c) 2016 Intel Corporation. All rights reserved.
+ * Copyright(c) 2016 - 2017 Intel Corporation. All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -13,100 +13,38 @@
 #include <linux/pagemap.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/magic.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-private.h"
 #include "dax.h"
 
-static dev_t dax_devt;
-DEFINE_STATIC_SRCU(dax_srcu);
 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
- * @id: kernel-wide unique region for a memory range
- * @base: linear address corresponding to @res
- * @kref: to pin while other agents have a need to do lookups
- * @dev: parent device backing this region
- * @align: allocation and mapping alignment for child dax devices
- * @res: physical address range of the region
- * @pfn_flags: identify whether the pfns are paged back or not
- */
-struct dax_region {
-	int id;
-	struct ida ida;
-	void *base;
-	struct kref kref;
-	struct device *dev;
-	unsigned int align;
-	struct resource res;
-	unsigned long pfn_flags;
-};
 
-/**
- * struct dax_dev - subdivision of a dax region
- * @region - parent region
- * @dev - device backing the character device
- * @cdev - core chardev data
- * @alive - !alive + srcu grace period == no new mappings can be established
- * @id - child id in the region
- * @num_resources - number of physical address extents in this device
- * @res - array of physical address ranges
+/*
+ * Rely on the fact that drvdata is set before the attributes are
+ * registered, and that the attributes are unregistered before drvdata
+ * is cleared to assume that drvdata is always valid.
  */
-struct dax_dev {
-	struct dax_region *region;
-	struct inode *inode;
-	struct device dev;
-	struct cdev cdev;
-	bool alive;
-	int id;
-	int num_resources;
-	struct resource res[0];
-};
-
 static ssize_t id_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct dax_region *dax_region;
-	ssize_t rc = -ENXIO;
-
-	device_lock(dev);
-	dax_region = dev_get_drvdata(dev);
-	if (dax_region)
-		rc = sprintf(buf, "%d\n", dax_region->id);
-	device_unlock(dev);
+	struct dax_region *dax_region = dev_get_drvdata(dev);
 
-	return rc;
+	return sprintf(buf, "%d\n", dax_region->id);
 }
 static DEVICE_ATTR_RO(id);
 
 static ssize_t region_size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct dax_region *dax_region;
-	ssize_t rc = -ENXIO;
-
-	device_lock(dev);
-	dax_region = dev_get_drvdata(dev);
-	if (dax_region)
-		rc = sprintf(buf, "%llu\n", (unsigned long long)
-				resource_size(&dax_region->res));
-	device_unlock(dev);
+	struct dax_region *dax_region = dev_get_drvdata(dev);
 
-	return rc;
+	return sprintf(buf, "%llu\n", (unsigned long long)
+			resource_size(&dax_region->res));
 }
 static struct device_attribute dev_attr_region_size = __ATTR(size, 0444,
 		region_size_show, NULL);
@@ -114,16 +52,9 @@ static struct device_attribute dev_attr_region_size = __ATTR(size, 0444,
 static ssize_t align_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct dax_region *dax_region;
-	ssize_t rc = -ENXIO;
-
-	device_lock(dev);
-	dax_region = dev_get_drvdata(dev);
-	if (dax_region)
-		rc = sprintf(buf, "%u\n", dax_region->align);
-	device_unlock(dev);
+	struct dax_region *dax_region = dev_get_drvdata(dev);
 
-	return rc;
+	return sprintf(buf, "%u\n", dax_region->align);
 }
 static DEVICE_ATTR_RO(align);
 
@@ -144,117 +75,6 @@ static const struct attribute_group *dax_region_attribute_groups[] = {
 	NULL,
 };
 
-static struct inode *dax_alloc_inode(struct super_block *sb)
-{
-	return kmem_cache_alloc(dax_cache, GFP_KERNEL);
-}
-
-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);
-}
-
-static void dax_destroy_inode(struct inode *inode)
-{
-	call_rcu(&inode->i_rcu, dax_i_callback);
-}
-
-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)
-{
-	return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC);
-}
-
-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_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;
@@ -323,47 +143,47 @@ 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)
+static struct dev_dax *to_dev_dax(struct device *dev)
 {
-	return container_of(dev, struct dax_dev, dev);
+	return container_of(dev, struct dev_dax, dev);
 }
 
 static ssize_t size_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct dax_dev *dax_dev = to_dax_dev(dev);
+	struct dev_dax *dev_dax = to_dev_dax(dev);
 	unsigned long long size = 0;
 	int i;
 
-	for (i = 0; i < dax_dev->num_resources; i++)
-		size += resource_size(&dax_dev->res[i]);
+	for (i = 0; i < dev_dax->num_resources; i++)
+		size += resource_size(&dev_dax->res[i]);
 
 	return sprintf(buf, "%llu\n", size);
 }
 static DEVICE_ATTR_RO(size);
 
-static struct attribute *dax_device_attributes[] = {
+static struct attribute *dev_dax_attributes[] = {
 	&dev_attr_size.attr,
 	NULL,
 };
 
-static const struct attribute_group dax_device_attribute_group = {
-	.attrs = dax_device_attributes,
+static const struct attribute_group dev_dax_attribute_group = {
+	.attrs = dev_dax_attributes,
 };
 
 static const struct attribute_group *dax_attribute_groups[] = {
-	&dax_device_attribute_group,
+	&dev_dax_attribute_group,
 	NULL,
 };
 
-static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
+static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 		const char *func)
 {
-	struct dax_region *dax_region = dax_dev->region;
-	struct device *dev = &dax_dev->dev;
+	struct dax_region *dax_region = dev_dax->region;
+	struct device *dev = &dev_dax->dev;
 	unsigned long mask;
 
-	if (!dax_dev->alive)
+	if (!dax_alive(dev_dax->dax_dev))
 		return -ENXIO;
 
 	/* prevent private mappings from being established */
@@ -397,23 +217,24 @@ static int check_vma(struct dax_dev *dax_dev, struct vm_area_struct *vma,
 	return 0;
 }
 
-static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, pgoff_t pgoff,
+/* see "strong" declaration in tools/testing/nvdimm/dax-dev.c */
+__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 		unsigned long size)
 {
 	struct resource *res;
 	phys_addr_t phys;
 	int i;
 
-	for (i = 0; i < dax_dev->num_resources; i++) {
-		res = &dax_dev->res[i];
+	for (i = 0; i < dev_dax->num_resources; i++) {
+		res = &dev_dax->res[i];
 		phys = pgoff * PAGE_SIZE + res->start;
 		if (phys >= res->start && phys <= res->end)
 			break;
 		pgoff -= PHYS_PFN(resource_size(res));
 	}
 
-	if (i < dax_dev->num_resources) {
-		res = &dax_dev->res[i];
+	if (i < dev_dax->num_resources) {
+		res = &dev_dax->res[i];
 		if (phys + size - 1 <= res->end)
 			return phys;
 	}
@@ -421,28 +242,29 @@ static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, pgoff_t pgoff,
 	return -1;
 }
 
-static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
+static int __dev_dax_pte_fault(struct dev_dax *dev_dax, struct vm_fault *vmf)
 {
-	struct device *dev = &dax_dev->dev;
+	struct device *dev = &dev_dax->dev;
 	struct dax_region *dax_region;
 	int rc = VM_FAULT_SIGBUS;
 	phys_addr_t phys;
 	pfn_t pfn;
 	unsigned int fault_size = PAGE_SIZE;
 
-	if (check_vma(dax_dev, vmf->vma, __func__))
+	if (check_vma(dev_dax, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
-	dax_region = dax_dev->region;
+	dax_region = dev_dax->region;
 	if (dax_region->align > PAGE_SIZE) {
-		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n",
+			__func__, dax_region->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
 	if (fault_size != dax_region->align)
 		return VM_FAULT_SIGBUS;
 
-	phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
+	phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE);
 	if (phys == -1) {
 		dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
 				vmf->pgoff);
@@ -461,28 +283,29 @@ static int __dax_dev_pte_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 	return VM_FAULT_NOPAGE;
 }
 
-static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
+static int __dev_dax_pmd_fault(struct dev_dax *dev_dax, struct vm_fault *vmf)
 {
 	unsigned long pmd_addr = vmf->address & PMD_MASK;
-	struct device *dev = &dax_dev->dev;
+	struct device *dev = &dev_dax->dev;
 	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
 	pfn_t pfn;
 	unsigned int fault_size = PMD_SIZE;
 
-	if (check_vma(dax_dev, vmf->vma, __func__))
+	if (check_vma(dev_dax, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
-	dax_region = dax_dev->region;
+	dax_region = dev_dax->region;
 	if (dax_region->align > PMD_SIZE) {
-		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n",
+			__func__, dax_region->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
 	/* dax pmd mappings require pfn_t_devmap() */
 	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
-		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		dev_dbg(dev, "%s: region lacks devmap flags\n", __func__);
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -497,7 +320,7 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	pgoff = linear_page_index(vmf->vma, pmd_addr);
-	phys = pgoff_to_phys(dax_dev, pgoff, PMD_SIZE);
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, PMD_SIZE);
 	if (phys == -1) {
 		dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
 				pgoff);
@@ -511,10 +334,10 @@ static int __dax_dev_pmd_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
+static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf)
 {
 	unsigned long pud_addr = vmf->address & PUD_MASK;
-	struct device *dev = &dax_dev->dev;
+	struct device *dev = &dev_dax->dev;
 	struct dax_region *dax_region;
 	phys_addr_t phys;
 	pgoff_t pgoff;
@@ -522,18 +345,19 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 	unsigned int fault_size = PUD_SIZE;
 
 
-	if (check_vma(dax_dev, vmf->vma, __func__))
+	if (check_vma(dev_dax, vmf->vma, __func__))
 		return VM_FAULT_SIGBUS;
 
-	dax_region = dax_dev->region;
+	dax_region = dev_dax->region;
 	if (dax_region->align > PUD_SIZE) {
-		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		dev_dbg(dev, "%s: alignment (%#x) > fault size (%#x)\n",
+			__func__, dax_region->align, fault_size);
 		return VM_FAULT_SIGBUS;
 	}
 
 	/* dax pud mappings require pfn_t_devmap() */
 	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) != (PFN_DEV|PFN_MAP)) {
-		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		dev_dbg(dev, "%s: region lacks devmap flags\n", __func__);
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -548,7 +372,7 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	pgoff = linear_page_index(vmf->vma, pud_addr);
-	phys = pgoff_to_phys(dax_dev, pgoff, PUD_SIZE);
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, PUD_SIZE);
 	if (phys == -1) {
 		dev_dbg(dev, "%s: pgoff_to_phys(%#lx) failed\n", __func__,
 				pgoff);
@@ -561,65 +385,71 @@ static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
 			vmf->flags & FAULT_FLAG_WRITE);
 }
 #else
-static int __dax_dev_pud_fault(struct dax_dev *dax_dev, struct vm_fault *vmf)
+static int __dev_dax_pud_fault(struct dev_dax *dev_dax, struct vm_fault *vmf)
 {
 	return VM_FAULT_FALLBACK;
 }
 #endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
 
-static int dax_dev_huge_fault(struct vm_fault *vmf,
+static int dev_dax_huge_fault(struct vm_fault *vmf,
 		enum page_entry_size pe_size)
 {
 	int rc, id;
 	struct file *filp = vmf->vma->vm_file;
-	struct dax_dev *dax_dev = filp->private_data;
+	struct dev_dax *dev_dax = filp->private_data;
 
-	dev_dbg(&dax_dev->dev, "%s: %s: %s (%#lx - %#lx)\n", __func__,
+	dev_dbg(&dev_dax->dev, "%s: %s: %s (%#lx - %#lx) size = %d\n", __func__,
 			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
 			? "write" : "read",
-			vmf->vma->vm_start, vmf->vma->vm_end);
+			vmf->vma->vm_start, vmf->vma->vm_end, pe_size);
 
-	id = srcu_read_lock(&dax_srcu);
+	id = dax_read_lock();
 	switch (pe_size) {
 	case PE_SIZE_PTE:
-		rc = __dax_dev_pte_fault(dax_dev, vmf);
+		rc = __dev_dax_pte_fault(dev_dax, vmf);
 		break;
 	case PE_SIZE_PMD:
-		rc = __dax_dev_pmd_fault(dax_dev, vmf);
+		rc = __dev_dax_pmd_fault(dev_dax, vmf);
 		break;
 	case PE_SIZE_PUD:
-		rc = __dax_dev_pud_fault(dax_dev, vmf);
+		rc = __dev_dax_pud_fault(dev_dax, vmf);
 		break;
 	default:
-		return VM_FAULT_FALLBACK;
+		rc = VM_FAULT_SIGBUS;
 	}
-	srcu_read_unlock(&dax_srcu, id);
+	dax_read_unlock(id);
 
 	return rc;
 }
 
-static int dax_dev_fault(struct vm_fault *vmf)
+static int dev_dax_fault(struct vm_fault *vmf)
 {
-	return dax_dev_huge_fault(vmf, PE_SIZE_PTE);
+	return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
-static const struct vm_operations_struct dax_dev_vm_ops = {
-	.fault = dax_dev_fault,
-	.huge_fault = dax_dev_huge_fault,
+static const struct vm_operations_struct dax_vm_ops = {
+	.fault = dev_dax_fault,
+	.huge_fault = dev_dax_huge_fault,
 };
 
 static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
 {
-	struct dax_dev *dax_dev = filp->private_data;
-	int rc;
+	struct dev_dax *dev_dax = filp->private_data;
+	int rc, id;
 
-	dev_dbg(&dax_dev->dev, "%s\n", __func__);
+	dev_dbg(&dev_dax->dev, "%s\n", __func__);
 
-	rc = check_vma(dax_dev, vma, __func__);
+	/*
+	 * We lock to check dax_dev liveness and will re-check at
+	 * fault time.
+	 */
+	id = dax_read_lock();
+	rc = check_vma(dev_dax, vma, __func__);
+	dax_read_unlock(id);
 	if (rc)
 		return rc;
 
-	vma->vm_ops = &dax_dev_vm_ops;
+	vma->vm_ops = &dax_vm_ops;
 	vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
 	return 0;
 }
@@ -630,13 +460,13 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 		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 dev_dax *dev_dax = filp ? filp->private_data : NULL;
 	struct dax_region *dax_region;
 
-	if (!dax_dev || addr)
+	if (!dev_dax || addr)
 		goto out;
 
-	dax_region = dax_dev->region;
+	dax_region = dev_dax->region;
 	align = dax_region->align;
 	off = pgoff << PAGE_SHIFT;
 	off_end = off + len;
@@ -661,14 +491,15 @@ static unsigned long dax_get_unmapped_area(struct file *filp,
 
 static int dax_open(struct inode *inode, struct file *filp)
 {
-	struct dax_dev *dax_dev;
+	struct dax_device *dax_dev = inode_dax(inode);
+	struct inode *__dax_inode = dax_inode(dax_dev);
+	struct dev_dax *dev_dax = dax_get_private(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;
+	dev_dbg(&dev_dax->dev, "%s\n", __func__);
+	inode->i_mapping = __dax_inode->i_mapping;
+	inode->i_mapping->host = __dax_inode;
 	filp->f_mapping = inode->i_mapping;
-	filp->private_data = dax_dev;
+	filp->private_data = dev_dax;
 	inode->i_flags = S_DAX;
 
 	return 0;
@@ -676,9 +507,9 @@ static int dax_open(struct inode *inode, struct file *filp)
 
 static int dax_release(struct inode *inode, struct file *filp)
 {
-	struct dax_dev *dax_dev = filp->private_data;
+	struct dev_dax *dev_dax = filp->private_data;
 
-	dev_dbg(&dax_dev->dev, "%s\n", __func__);
+	dev_dbg(&dev_dax->dev, "%s\n", __func__);
 	return 0;
 }
 
@@ -691,55 +522,54 @@ static const struct file_operations dax_fops = {
 	.mmap = dax_mmap,
 };
 
-static void dax_dev_release(struct device *dev)
+static void dev_dax_release(struct device *dev)
 {
-	struct dax_dev *dax_dev = to_dax_dev(dev);
-	struct dax_region *dax_region = dax_dev->region;
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct dax_region *dax_region = dev_dax->region;
+	struct dax_device *dax_dev = dev_dax->dax_dev;
 
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
-	ida_simple_remove(&dax_minor_ida, MINOR(dev->devt));
+	ida_simple_remove(&dax_region->ida, dev_dax->id);
 	dax_region_put(dax_region);
-	iput(dax_dev->inode);
-	kfree(dax_dev);
+	put_dax(dax_dev);
+	kfree(dev_dax);
 }
 
-static void kill_dax_dev(struct dax_dev *dax_dev)
+static void kill_dev_dax(struct dev_dax *dev_dax)
 {
-	/*
-	 * 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_srcu() has started will abort
-	 * upon seeing dax_dev->alive == false.
-	 */
-	dax_dev->alive = false;
-	synchronize_srcu(&dax_srcu);
-	unmap_mapping_range(dax_dev->inode->i_mapping, 0, 0, 1);
+	struct dax_device *dax_dev = dev_dax->dax_dev;
+	struct inode *inode = dax_inode(dax_dev);
+
+	kill_dax(dax_dev);
+	unmap_mapping_range(inode->i_mapping, 0, 0, 1);
 }
 
-static void unregister_dax_dev(void *dev)
+static void unregister_dev_dax(void *dev)
 {
-	struct dax_dev *dax_dev = to_dax_dev(dev);
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	struct dax_device *dax_dev = dev_dax->dax_dev;
+	struct inode *inode = dax_inode(dax_dev);
+	struct cdev *cdev = inode->i_cdev;
 
 	dev_dbg(dev, "%s\n", __func__);
 
-	kill_dax_dev(dax_dev);
-	cdev_device_del(&dax_dev->cdev, dev);
+	kill_dev_dax(dev_dax);
+	cdev_device_del(cdev, dev);
 	put_device(dev);
 }
 
-struct dax_dev *devm_create_dax_dev(struct dax_region *dax_region,
+struct dev_dax *devm_create_dev_dax(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 dax_device *dax_dev;
+	struct dev_dax *dev_dax;
+	struct inode *inode;
 	struct device *dev;
 	struct cdev *cdev;
-	dev_t dev_t;
+	int rc = 0, i;
 
-	dax_dev = kzalloc(sizeof(*dax_dev) + sizeof(*res) * count, GFP_KERNEL);
-	if (!dax_dev)
+	dev_dax = kzalloc(sizeof(*dev_dax) + sizeof(*res) * count, GFP_KERNEL);
+	if (!dev_dax)
 		return ERR_PTR(-ENOMEM);
 
 	for (i = 0; i < count; i++) {
@@ -749,110 +579,79 @@ struct dax_dev *devm_create_dax_dev(struct dax_region *dax_region,
 			rc = -EINVAL;
 			break;
 		}
-		dax_dev->res[i].start = res[i].start;
-		dax_dev->res[i].end = res[i].end;
+		dev_dax->res[i].start = res[i].start;
+		dev_dax->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;
+	dev_dax->id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
+	if (dev_dax->id < 0) {
+		rc = dev_dax->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;
-	}
+	/*
+	 * No 'host' or dax_operations since there is no access to this
+	 * device outside of mmap of the resulting character device.
+	 */
+	dax_dev = alloc_dax(dev_dax, NULL, NULL);
+	if (!dax_dev)
+		goto err_dax;
 
 	/* from here on we're committed to teardown via dax_dev_release() */
+	dev = &dev_dax->dev;
 	device_initialize(dev);
 
-	cdev = &dax_dev->cdev;
+	inode = dax_inode(dax_dev);
+	cdev = inode->i_cdev;
 	cdev_init(cdev, &dax_fops);
 	cdev->owner = parent->driver->owner;
 
-	dax_dev->num_resources = count;
-	dax_dev->alive = true;
-	dax_dev->region = dax_region;
+	dev_dax->num_resources = count;
+	dev_dax->dax_dev = dax_dev;
+	dev_dax->region = dax_region;
 	kref_get(&dax_region->kref);
 
-	dev->devt = dev_t;
+	dev->devt = inode->i_rdev;
 	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);
+	dev->release = dev_dax_release;
+	dev_set_name(dev, "dax%d.%d", dax_region->id, dev_dax->id);
 
 	rc = cdev_device_add(cdev, dev);
 	if (rc) {
-		kill_dax_dev(dax_dev);
+		kill_dev_dax(dev_dax);
 		put_device(dev);
 		return ERR_PTR(rc);
 	}
 
-	rc = devm_add_action_or_reset(dax_region->dev, unregister_dax_dev, dev);
+	rc = devm_add_action_or_reset(dax_region->dev, unregister_dev_dax, dev);
 	if (rc)
 		return ERR_PTR(rc);
 
-	return dax_dev;
+	return dev_dax;
 
- err_inode:
-	ida_simple_remove(&dax_minor_ida, minor);
- err_minor:
-	ida_simple_remove(&dax_region->ida, dax_dev->id);
+ err_dax:
+	ida_simple_remove(&dax_region->ida, dev_dax->id);
  err_id:
-	kfree(dax_dev);
+	kfree(dev_dax);
 
 	return ERR_PTR(rc);
 }
-EXPORT_SYMBOL_GPL(devm_create_dax_dev);
+EXPORT_SYMBOL_GPL(devm_create_dev_dax);
 
 static int __init dax_init(void)
 {
-	int rc;
-
-	rc = dax_inode_init();
-	if (rc)
-		return 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)) {
-		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;
+	return PTR_ERR_OR_ZERO(dax_class);
 }
 
 static void __exit dax_exit(void)
 {
 	class_destroy(dax_class);
-	unregister_chrdev_region(dax_devt, nr_dax);
-	ida_destroy(&dax_minor_ida);
-	dax_inode_exit();
 }
 
 MODULE_AUTHOR("Intel Corporation");
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index cb0d742fa23f..9f2a0b4fd801 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -16,7 +16,7 @@
 #include <linux/pfn_t.h>
 #include "../nvdimm/pfn.h"
 #include "../nvdimm/nd.h"
-#include "dax.h"
+#include "device-dax.h"
 
 struct dax_pmem {
 	struct device *dev;
@@ -61,8 +61,8 @@ 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 dev_dax *dev_dax;
 	struct dax_pmem *dax_pmem;
 	struct nd_region *nd_region;
 	struct nd_namespace_io *nsio;
@@ -130,12 +130,12 @@ static int dax_pmem_probe(struct device *dev)
 		return -ENOMEM;
 
 	/* TODO: support for subdividing a dax region... */
-	dax_dev = devm_create_dax_dev(dax_region, &res, 1);
+	dev_dax = devm_create_dev_dax(dax_region, &res, 1);
 
-	/* child dax_dev instances now own the lifetime of the dax_region */
+	/* child dev_dax instances now own the lifetime of the dax_region */
 	dax_region_put(dax_region);
 
-	return PTR_ERR_OR_ZERO(dax_dev);
+	return PTR_ERR_OR_ZERO(dev_dax);
 }
 
 static struct nd_device_driver dax_pmem_driver = {
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
new file mode 100644
index 000000000000..465dcd7317d5
--- /dev/null
+++ b/drivers/dax/super.c
@@ -0,0 +1,425 @@
+/*
+ * Copyright(c) 2017 Intel Corporation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+#include <linux/pagemap.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/magic.h>
+#include <linux/cdev.h>
+#include <linux/hash.h>
+#include <linux/slab.h>
+#include <linux/dax.h>
+#include <linux/fs.h>
+
+static int nr_dax = CONFIG_NR_DEV_DAX;
+module_param(nr_dax, int, S_IRUGO);
+MODULE_PARM_DESC(nr_dax, "max number of dax device instances");
+
+static dev_t dax_devt;
+DEFINE_STATIC_SRCU(dax_srcu);
+static struct vfsmount *dax_mnt;
+static DEFINE_IDA(dax_minor_ida);
+static struct kmem_cache *dax_cache __read_mostly;
+static struct super_block *dax_superblock __read_mostly;
+
+#define DAX_HASH_SIZE (PAGE_SIZE / sizeof(struct hlist_head))
+static struct hlist_head dax_host_list[DAX_HASH_SIZE];
+static DEFINE_SPINLOCK(dax_host_lock);
+
+int dax_read_lock(void)
+{
+	return srcu_read_lock(&dax_srcu);
+}
+EXPORT_SYMBOL_GPL(dax_read_lock);
+
+void dax_read_unlock(int id)
+{
+	srcu_read_unlock(&dax_srcu, id);
+}
+EXPORT_SYMBOL_GPL(dax_read_unlock);
+
+/**
+ * struct dax_device - anchor object for dax services
+ * @inode: core vfs
+ * @cdev: optional character interface for "device dax"
+ * @host: optional name for lookups where the device path is not available
+ * @private: dax driver private data
+ * @alive: !alive + rcu grace period == no new operations / mappings
+ */
+struct dax_device {
+	struct hlist_node list;
+	struct inode inode;
+	struct cdev cdev;
+	const char *host;
+	void *private;
+	bool alive;
+	const struct dax_operations *ops;
+};
+
+/**
+ * dax_direct_access() - translate a device pgoff to an absolute pfn
+ * @dax_dev: a dax_device instance representing the logical memory range
+ * @pgoff: offset in pages from the start of the device to translate
+ * @nr_pages: number of consecutive pages caller can handle relative to @pfn
+ * @kaddr: output parameter that returns a virtual address mapping of pfn
+ * @pfn: output parameter that returns an absolute pfn translation of @pgoff
+ *
+ * Return: negative errno if an error occurs, otherwise the number of
+ * pages accessible at the device relative @pgoff.
+ */
+long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
+		void **kaddr, pfn_t *pfn)
+{
+	long avail;
+
+	/*
+	 * The device driver is allowed to sleep, in order to make the
+	 * memory directly accessible.
+	 */
+	might_sleep();
+
+	if (!dax_dev)
+		return -EOPNOTSUPP;
+
+	if (!dax_alive(dax_dev))
+		return -ENXIO;
+
+	if (nr_pages < 0)
+		return nr_pages;
+
+	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
+			kaddr, pfn);
+	if (!avail)
+		return -ERANGE;
+	return min(avail, nr_pages);
+}
+EXPORT_SYMBOL_GPL(dax_direct_access);
+
+bool dax_alive(struct dax_device *dax_dev)
+{
+	lockdep_assert_held(&dax_srcu);
+	return dax_dev->alive;
+}
+EXPORT_SYMBOL_GPL(dax_alive);
+
+static int dax_host_hash(const char *host)
+{
+	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
+}
+
+/*
+ * Note, rcu is not protecting the liveness of dax_dev, rcu is ensuring
+ * that any fault handlers or operations that might have seen
+ * dax_alive(), have completed.  Any operations that start after
+ * synchronize_srcu() has run will abort upon seeing !dax_alive().
+ */
+void kill_dax(struct dax_device *dax_dev)
+{
+	if (!dax_dev)
+		return;
+
+	dax_dev->alive = false;
+
+	synchronize_srcu(&dax_srcu);
+
+	spin_lock(&dax_host_lock);
+	hlist_del_init(&dax_dev->list);
+	spin_unlock(&dax_host_lock);
+
+	dax_dev->private = NULL;
+}
+EXPORT_SYMBOL_GPL(kill_dax);
+
+static struct inode *dax_alloc_inode(struct super_block *sb)
+{
+	struct dax_device *dax_dev;
+
+	dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
+	return &dax_dev->inode;
+}
+
+static struct dax_device *to_dax_dev(struct inode *inode)
+{
+	return container_of(inode, struct dax_device, inode);
+}
+
+static void dax_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct dax_device *dax_dev = to_dax_dev(inode);
+
+	kfree(dax_dev->host);
+	dax_dev->host = NULL;
+	ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
+	kmem_cache_free(dax_cache, dax_dev);
+}
+
+static void dax_destroy_inode(struct inode *inode)
+{
+	struct dax_device *dax_dev = to_dax_dev(inode);
+
+	WARN_ONCE(dax_dev->alive,
+			"kill_dax() must be called before final iput()\n");
+	call_rcu(&inode->i_rcu, dax_i_callback);
+}
+
+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)
+{
+	return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC);
+}
+
+static struct file_system_type dax_fs_type = {
+	.name = "dax",
+	.mount = dax_mount,
+	.kill_sb = kill_anon_super,
+};
+
+static int dax_test(struct inode *inode, void *data)
+{
+	dev_t devt = *(dev_t *) data;
+
+	return inode->i_rdev == devt;
+}
+
+static int dax_set(struct inode *inode, void *data)
+{
+	dev_t devt = *(dev_t *) data;
+
+	inode->i_rdev = devt;
+	return 0;
+}
+
+static struct dax_device *dax_dev_get(dev_t devt)
+{
+	struct dax_device *dax_dev;
+	struct inode *inode;
+
+	inode = iget5_locked(dax_superblock, hash_32(devt + DAXFS_MAGIC, 31),
+			dax_test, dax_set, &devt);
+
+	if (!inode)
+		return NULL;
+
+	dax_dev = to_dax_dev(inode);
+	if (inode->i_state & I_NEW) {
+		dax_dev->alive = true;
+		inode->i_cdev = &dax_dev->cdev;
+		inode->i_mode = S_IFCHR;
+		inode->i_flags = S_DAX;
+		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
+		unlock_new_inode(inode);
+	}
+
+	return dax_dev;
+}
+
+static void dax_add_host(struct dax_device *dax_dev, const char *host)
+{
+	int hash;
+
+	/*
+	 * Unconditionally init dax_dev since it's coming from a
+	 * non-zeroed slab cache
+	 */
+	INIT_HLIST_NODE(&dax_dev->list);
+	dax_dev->host = host;
+	if (!host)
+		return;
+
+	hash = dax_host_hash(host);
+	spin_lock(&dax_host_lock);
+	hlist_add_head(&dax_dev->list, &dax_host_list[hash]);
+	spin_unlock(&dax_host_lock);
+}
+
+struct dax_device *alloc_dax(void *private, const char *__host,
+		const struct dax_operations *ops)
+{
+	struct dax_device *dax_dev;
+	const char *host;
+	dev_t devt;
+	int minor;
+
+	host = kstrdup(__host, GFP_KERNEL);
+	if (__host && !host)
+		return NULL;
+
+	minor = ida_simple_get(&dax_minor_ida, 0, nr_dax, GFP_KERNEL);
+	if (minor < 0)
+		goto err_minor;
+
+	devt = MKDEV(MAJOR(dax_devt), minor);
+	dax_dev = dax_dev_get(devt);
+	if (!dax_dev)
+		goto err_dev;
+
+	dax_add_host(dax_dev, host);
+	dax_dev->ops = ops;
+	dax_dev->private = private;
+	return dax_dev;
+
+ err_dev:
+	ida_simple_remove(&dax_minor_ida, minor);
+ err_minor:
+	kfree(host);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(alloc_dax);
+
+void put_dax(struct dax_device *dax_dev)
+{
+	if (!dax_dev)
+		return;
+	iput(&dax_dev->inode);
+}
+EXPORT_SYMBOL_GPL(put_dax);
+
+/**
+ * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
+ * @host: alternate name for the device registered by a dax driver
+ */
+struct dax_device *dax_get_by_host(const char *host)
+{
+	struct dax_device *dax_dev, *found = NULL;
+	int hash, id;
+
+	if (!host)
+		return NULL;
+
+	hash = dax_host_hash(host);
+
+	id = dax_read_lock();
+	spin_lock(&dax_host_lock);
+	hlist_for_each_entry(dax_dev, &dax_host_list[hash], list) {
+		if (!dax_alive(dax_dev)
+				|| strcmp(host, dax_dev->host) != 0)
+			continue;
+
+		if (igrab(&dax_dev->inode))
+			found = dax_dev;
+		break;
+	}
+	spin_unlock(&dax_host_lock);
+	dax_read_unlock(id);
+
+	return found;
+}
+EXPORT_SYMBOL_GPL(dax_get_by_host);
+
+/**
+ * inode_dax: convert a public inode into its dax_dev
+ * @inode: An inode with i_cdev pointing to a dax_dev
+ *
+ * Note this is not equivalent to to_dax_dev() which is for private
+ * internal use where we know the inode filesystem type == dax_fs_type.
+ */
+struct dax_device *inode_dax(struct inode *inode)
+{
+	struct cdev *cdev = inode->i_cdev;
+
+	return container_of(cdev, struct dax_device, cdev);
+}
+EXPORT_SYMBOL_GPL(inode_dax);
+
+struct inode *dax_inode(struct dax_device *dax_dev)
+{
+	return &dax_dev->inode;
+}
+EXPORT_SYMBOL_GPL(dax_inode);
+
+void *dax_get_private(struct dax_device *dax_dev)
+{
+	return dax_dev->private;
+}
+EXPORT_SYMBOL_GPL(dax_get_private);
+
+static void init_once(void *_dax_dev)
+{
+	struct dax_device *dax_dev = _dax_dev;
+	struct inode *inode = &dax_dev->inode;
+
+	inode_init_once(inode);
+}
+
+static int __dax_fs_init(void)
+{
+	int rc;
+
+	dax_cache = kmem_cache_create("dax_cache", sizeof(struct dax_device), 0,
+			(SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
+			 SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+			init_once);
+	if (!dax_cache)
+		return -ENOMEM;
+
+	rc = register_filesystem(&dax_fs_type);
+	if (rc)
+		goto err_register_fs;
+
+	dax_mnt = kern_mount(&dax_fs_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_fs_type);
+ err_register_fs:
+	kmem_cache_destroy(dax_cache);
+
+	return rc;
+}
+
+static void __dax_fs_exit(void)
+{
+	kern_unmount(dax_mnt);
+	unregister_filesystem(&dax_fs_type);
+	kmem_cache_destroy(dax_cache);
+}
+
+static int __init dax_fs_init(void)
+{
+	int rc;
+
+	rc = __dax_fs_init();
+	if (rc)
+		return rc;
+
+	nr_dax = max(nr_dax, 256);
+	rc = alloc_chrdev_region(&dax_devt, 0, nr_dax, "dax");
+	if (rc)
+		__dax_fs_exit();
+	return rc;
+}
+
+static void __exit dax_fs_exit(void)
+{
+	unregister_chrdev_region(dax_devt, nr_dax);
+	ida_destroy(&dax_minor_ida);
+	__dax_fs_exit();
+}
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL v2");
+subsys_initcall(dax_fs_init);
+module_exit(dax_fs_exit);