Adding upstream version 4.19.249.upstream/4.19.249

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

8 files changed, 1683 insertions, 0 deletions

diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
new file mode 100644
index 000000000..e0700bf48
--- /dev/null
+++ b/drivers/dax/Kconfig
@@ -0,0 +1,34 @@
+config DAX_DRIVER
+	select DAX
+	bool
+
+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
+	help
+	  Support raw access to differentiated (persistence, bandwidth,
+	  latency...) memory via an mmap(2) capable character
+	  device.  Platform firmware or a device driver may identify a
+	  platform memory resource that is differentiated from the
+	  baseline memory pool.  Mappings of a /dev/daxX.Y device impose
+	  restrictions that make the mapping behavior deterministic.
+
+config DEV_DAX_PMEM
+	tristate "PMEM DAX: direct access to persistent memory"
+	depends on LIBNVDIMM && NVDIMM_DAX && DEV_DAX
+	default DEV_DAX
+	help
+	  Support raw access to persistent memory.  Note that this
+	  driver consumes memory ranges allocated and exported by the
+	  libnvdimm sub-system.
+
+	  Say Y if unsure
+
+endif
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
new file mode 100644
index 000000000..574286fac
--- /dev/null
+++ b/drivers/dax/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+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 000000000..b6fc4f046
--- /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
new file mode 100644
index 000000000..f9e5feea7
--- /dev/null
+++ b/drivers/dax/dax.h
@@ -0,0 +1,18 @@
+/*
+ * 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
+ * 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_H__
+#define __DAX_H__
+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 000000000..688b05175
--- /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,
+		int id, struct resource *res, int count);
+#endif /* __DEVICE_DAX_H__ */
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
new file mode 100644
index 000000000..a89ebd94c
--- /dev/null
+++ b/drivers/dax/device.c
@@ -0,0 +1,725 @@
+/*
+ * 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
+ * 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/device.h>
+#include <linux/pfn_t.h>
+#include <linux/cdev.h>
+#include <linux/slab.h>
+#include <linux/dax.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include "dax-private.h"
+#include "dax.h"
+
+static struct class *dax_class;
+
+/*
+ * 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.
+ */
+static ssize_t id_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_region *dax_region = dev_get_drvdata(dev);
+
+	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 = dev_get_drvdata(dev);
+
+	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);
+
+static ssize_t align_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_region *dax_region = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%u\n", dax_region->align);
+}
+static DEVICE_ATTR_RO(align);
+
+static struct attribute *dax_region_attributes[] = {
+	&dev_attr_region_size.attr,
+	&dev_attr_align.attr,
+	&dev_attr_id.attr,
+	NULL,
+};
+
+static const struct attribute_group dax_region_attribute_group = {
+	.name = "dax_region",
+	.attrs = dax_region_attributes,
+};
+
+static const struct attribute_group *dax_region_attribute_groups[] = {
+	&dax_region_attribute_group,
+	NULL,
+};
+
+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_region->kref, dax_region_free);
+}
+EXPORT_SYMBOL_GPL(dax_region_put);
+
+static void dax_region_unregister(void *region)
+{
+	struct dax_region *dax_region = region;
+
+	sysfs_remove_groups(&dax_region->dev->kobj,
+			dax_region_attribute_groups);
+	dax_region_put(dax_region);
+}
+
+struct dax_region *alloc_dax_region(struct device *parent, int region_id,
+		struct resource *res, unsigned int align, void *addr,
+		unsigned long pfn_flags)
+{
+	struct dax_region *dax_region;
+
+	/*
+	 * The DAX core assumes that it can store its private data in
+	 * parent->driver_data. This WARN is a reminder / safeguard for
+	 * developers of device-dax drivers.
+	 */
+	if (dev_get_drvdata(parent)) {
+		dev_WARN(parent, "dax core failed to setup private data\n");
+		return NULL;
+	}
+
+	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;
+
+	dev_set_drvdata(parent, dax_region);
+	memcpy(&dax_region->res, res, sizeof(*res));
+	dax_region->pfn_flags = pfn_flags;
+	kref_init(&dax_region->kref);
+	dax_region->id = region_id;
+	ida_init(&dax_region->ida);
+	dax_region->align = align;
+	dax_region->dev = parent;
+	dax_region->base = addr;
+	if (sysfs_create_groups(&parent->kobj, dax_region_attribute_groups)) {
+		kfree(dax_region);
+		return NULL;
+	}
+
+	kref_get(&dax_region->kref);
+	if (devm_add_action_or_reset(parent, dax_region_unregister, dax_region))
+		return NULL;
+	return dax_region;
+}
+EXPORT_SYMBOL_GPL(alloc_dax_region);
+
+static struct dev_dax *to_dev_dax(struct device *dev)
+{
+	return container_of(dev, struct dev_dax, dev);
+}
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dev_dax *dev_dax = to_dev_dax(dev);
+	unsigned long long size = 0;
+	int 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 *dev_dax_attributes[] = {
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct attribute_group dev_dax_attribute_group = {
+	.attrs = dev_dax_attributes,
+};
+
+static const struct attribute_group *dax_attribute_groups[] = {
+	&dev_dax_attribute_group,
+	NULL,
+};
+
+static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
+		const char *func)
+{
+	struct dax_region *dax_region = dev_dax->region;
+	struct device *dev = &dev_dax->dev;
+	unsigned long mask;
+
+	if (!dax_alive(dev_dax->dax_dev))
+		return -ENXIO;
+
+	/* prevent private mappings from being established */
+	if ((vma->vm_flags & VM_MAYSHARE) != VM_MAYSHARE) {
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, attempted private mapping\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	mask = dax_region->align - 1;
+	if (vma->vm_start & mask || vma->vm_end & mask) {
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, unaligned vma (%#lx - %#lx, %#lx)\n",
+				current->comm, func, vma->vm_start, vma->vm_end,
+				mask);
+		return -EINVAL;
+	}
+
+	if ((dax_region->pfn_flags & (PFN_DEV|PFN_MAP)) == PFN_DEV
+			&& (vma->vm_flags & VM_DONTCOPY) == 0) {
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, dax range requires MADV_DONTFORK\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	if (!vma_is_dax(vma)) {
+		dev_info_ratelimited(dev,
+				"%s: %s: fail, vma is not DAX capable\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* 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;
+	/* gcc-4.6.3-nolibc for i386 complains that this is uninitialized */
+	phys_addr_t uninitialized_var(phys);
+	int 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 < dev_dax->num_resources) {
+		res = &dev_dax->res[i];
+		if (phys + size - 1 <= res->end)
+			return phys;
+	}
+
+	return -1;
+}
+
+static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
+				struct vm_fault *vmf, pfn_t *pfn)
+{
+	struct device *dev = &dev_dax->dev;
+	struct dax_region *dax_region;
+	phys_addr_t phys;
+	unsigned int fault_size = PAGE_SIZE;
+
+	if (check_vma(dev_dax, vmf->vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dev_dax->region;
+	if (dax_region->align > PAGE_SIZE) {
+		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
+			dax_region->align, fault_size);
+		return VM_FAULT_SIGBUS;
+	}
+
+	if (fault_size != dax_region->align)
+		return VM_FAULT_SIGBUS;
+
+	phys = dax_pgoff_to_phys(dev_dax, vmf->pgoff, PAGE_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", vmf->pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	return vmf_insert_mixed(vmf->vma, vmf->address, *pfn);
+}
+
+static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
+				struct vm_fault *vmf, pfn_t *pfn)
+{
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	struct device *dev = &dev_dax->dev;
+	struct dax_region *dax_region;
+	phys_addr_t phys;
+	pgoff_t pgoff;
+	unsigned int fault_size = PMD_SIZE;
+
+	if (check_vma(dev_dax, vmf->vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dev_dax->region;
+	if (dax_region->align > PMD_SIZE) {
+		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
+			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, "region lacks devmap flags\n");
+		return VM_FAULT_SIGBUS;
+	}
+
+	if (fault_size < dax_region->align)
+		return VM_FAULT_SIGBUS;
+	else if (fault_size > dax_region->align)
+		return VM_FAULT_FALLBACK;
+
+	/* if we are outside of the VMA */
+	if (pmd_addr < vmf->vma->vm_start ||
+			(pmd_addr + PMD_SIZE) > vmf->vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	pgoff = linear_page_index(vmf->vma, pmd_addr);
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, PMD_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
+}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
+				struct vm_fault *vmf, pfn_t *pfn)
+{
+	unsigned long pud_addr = vmf->address & PUD_MASK;
+	struct device *dev = &dev_dax->dev;
+	struct dax_region *dax_region;
+	phys_addr_t phys;
+	pgoff_t pgoff;
+	unsigned int fault_size = PUD_SIZE;
+
+
+	if (check_vma(dev_dax, vmf->vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dev_dax->region;
+	if (dax_region->align > PUD_SIZE) {
+		dev_dbg(dev, "alignment (%#x) > fault size (%#x)\n",
+			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, "region lacks devmap flags\n");
+		return VM_FAULT_SIGBUS;
+	}
+
+	if (fault_size < dax_region->align)
+		return VM_FAULT_SIGBUS;
+	else if (fault_size > dax_region->align)
+		return VM_FAULT_FALLBACK;
+
+	/* if we are outside of the VMA */
+	if (pud_addr < vmf->vma->vm_start ||
+			(pud_addr + PUD_SIZE) > vmf->vma->vm_end)
+		return VM_FAULT_SIGBUS;
+
+	pgoff = linear_page_index(vmf->vma, pud_addr);
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, PUD_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "pgoff_to_phys(%#lx) failed\n", pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
+}
+#else
+static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
+				struct vm_fault *vmf, pfn_t *pfn)
+{
+	return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
+static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf,
+		enum page_entry_size pe_size)
+{
+	struct file *filp = vmf->vma->vm_file;
+	unsigned long fault_size;
+	vm_fault_t rc = VM_FAULT_SIGBUS;
+	int id;
+	pfn_t pfn;
+	struct dev_dax *dev_dax = filp->private_data;
+
+	dev_dbg(&dev_dax->dev, "%s: %s (%#lx - %#lx) size = %d\n", current->comm,
+			(vmf->flags & FAULT_FLAG_WRITE) ? "write" : "read",
+			vmf->vma->vm_start, vmf->vma->vm_end, pe_size);
+
+	id = dax_read_lock();
+	switch (pe_size) {
+	case PE_SIZE_PTE:
+		fault_size = PAGE_SIZE;
+		rc = __dev_dax_pte_fault(dev_dax, vmf, &pfn);
+		break;
+	case PE_SIZE_PMD:
+		fault_size = PMD_SIZE;
+		rc = __dev_dax_pmd_fault(dev_dax, vmf, &pfn);
+		break;
+	case PE_SIZE_PUD:
+		fault_size = PUD_SIZE;
+		rc = __dev_dax_pud_fault(dev_dax, vmf, &pfn);
+		break;
+	default:
+		rc = VM_FAULT_SIGBUS;
+	}
+
+	if (rc == VM_FAULT_NOPAGE) {
+		unsigned long i;
+		pgoff_t pgoff;
+
+		/*
+		 * In the device-dax case the only possibility for a
+		 * VM_FAULT_NOPAGE result is when device-dax capacity is
+		 * mapped. No need to consider the zero page, or racing
+		 * conflicting mappings.
+		 */
+		pgoff = linear_page_index(vmf->vma, vmf->address
+				& ~(fault_size - 1));
+		for (i = 0; i < fault_size / PAGE_SIZE; i++) {
+			struct page *page;
+
+			page = pfn_to_page(pfn_t_to_pfn(pfn) + i);
+			if (page->mapping)
+				continue;
+			page->mapping = filp->f_mapping;
+			page->index = pgoff + i;
+		}
+	}
+	dax_read_unlock(id);
+
+	return rc;
+}
+
+static vm_fault_t dev_dax_fault(struct vm_fault *vmf)
+{
+	return dev_dax_huge_fault(vmf, PE_SIZE_PTE);
+}
+
+static int dev_dax_split(struct vm_area_struct *vma, unsigned long addr)
+{
+	struct file *filp = vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	struct dax_region *dax_region = dev_dax->region;
+
+	if (!IS_ALIGNED(addr, dax_region->align))
+		return -EINVAL;
+	return 0;
+}
+
+static unsigned long dev_dax_pagesize(struct vm_area_struct *vma)
+{
+	struct file *filp = vma->vm_file;
+	struct dev_dax *dev_dax = filp->private_data;
+	struct dax_region *dax_region = dev_dax->region;
+
+	return dax_region->align;
+}
+
+static const struct vm_operations_struct dax_vm_ops = {
+	.fault = dev_dax_fault,
+	.huge_fault = dev_dax_huge_fault,
+	.split = dev_dax_split,
+	.pagesize = dev_dax_pagesize,
+};
+
+static int dax_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct dev_dax *dev_dax = filp->private_data;
+	int rc, id;
+
+	dev_dbg(&dev_dax->dev, "trace\n");
+
+	/*
+	 * 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_vm_ops;
+	vma->vm_flags |= 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 dev_dax *dev_dax = filp ? filp->private_data : NULL;
+	struct dax_region *dax_region;
+
+	if (!dev_dax || addr)
+		goto out;
+
+	dax_region = dev_dax->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 const struct address_space_operations dev_dax_aops = {
+	.set_page_dirty		= noop_set_page_dirty,
+	.invalidatepage		= noop_invalidatepage,
+};
+
+static int dax_open(struct inode *inode, struct file *filp)
+{
+	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);
+
+	dev_dbg(&dev_dax->dev, "trace\n");
+	inode->i_mapping = __dax_inode->i_mapping;
+	inode->i_mapping->host = __dax_inode;
+	inode->i_mapping->a_ops = &dev_dax_aops;
+	filp->f_mapping = inode->i_mapping;
+	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
+	filp->private_data = dev_dax;
+	inode->i_flags = S_DAX;
+
+	return 0;
+}
+
+static int dax_release(struct inode *inode, struct file *filp)
+{
+	struct dev_dax *dev_dax = filp->private_data;
+
+	dev_dbg(&dev_dax->dev, "trace\n");
+	return 0;
+}
+
+static const struct file_operations dax_fops = {
+	.llseek = noop_llseek,
+	.owner = THIS_MODULE,
+	.open = dax_open,
+	.release = dax_release,
+	.get_unmapped_area = dax_get_unmapped_area,
+	.mmap = dax_mmap,
+	.mmap_supported_flags = MAP_SYNC,
+};
+
+static void dev_dax_release(struct device *dev)
+{
+	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;
+
+	if (dev_dax->id >= 0)
+		ida_simple_remove(&dax_region->ida, dev_dax->id);
+	dax_region_put(dax_region);
+	put_dax(dax_dev);
+	kfree(dev_dax);
+}
+
+static void kill_dev_dax(struct dev_dax *dev_dax)
+{
+	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_dev_dax(void *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, "trace\n");
+
+	kill_dev_dax(dev_dax);
+	cdev_device_del(cdev, dev);
+	put_device(dev);
+}
+
+struct dev_dax *devm_create_dev_dax(struct dax_region *dax_region,
+		int id, struct resource *res, int count)
+{
+	struct device *parent = dax_region->dev;
+	struct dax_device *dax_dev;
+	struct dev_dax *dev_dax;
+	struct inode *inode;
+	struct device *dev;
+	struct cdev *cdev;
+	int rc, i;
+
+	if (!count)
+		return ERR_PTR(-EINVAL);
+
+	dev_dax = kzalloc(struct_size(dev_dax, res, count), GFP_KERNEL);
+	if (!dev_dax)
+		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;
+		}
+		dev_dax->res[i].start = res[i].start;
+		dev_dax->res[i].end = res[i].end;
+	}
+
+	if (i < count)
+		goto err_id;
+
+	if (id < 0) {
+		id = ida_simple_get(&dax_region->ida, 0, 0, GFP_KERNEL);
+		dev_dax->id = id;
+		if (id < 0) {
+			rc = id;
+			goto err_id;
+		}
+	} else {
+		/* region provider owns @id lifetime */
+		dev_dax->id = -1;
+	}
+
+	/*
+	 * 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) {
+		rc = -ENOMEM;
+		goto err_dax;
+	}
+
+	/* from here on we're committed to teardown via dax_dev_release() */
+	dev = &dev_dax->dev;
+	device_initialize(dev);
+
+	inode = dax_inode(dax_dev);
+	cdev = inode->i_cdev;
+	cdev_init(cdev, &dax_fops);
+	cdev->owner = parent->driver->owner;
+
+	dev_dax->num_resources = count;
+	dev_dax->dax_dev = dax_dev;
+	dev_dax->region = dax_region;
+	kref_get(&dax_region->kref);
+
+	dev->devt = inode->i_rdev;
+	dev->class = dax_class;
+	dev->parent = parent;
+	dev->groups = dax_attribute_groups;
+	dev->release = dev_dax_release;
+	dev_set_name(dev, "dax%d.%d", dax_region->id, id);
+
+	rc = cdev_device_add(cdev, dev);
+	if (rc) {
+		kill_dev_dax(dev_dax);
+		put_device(dev);
+		return ERR_PTR(rc);
+	}
+
+	rc = devm_add_action_or_reset(dax_region->dev, unregister_dev_dax, dev);
+	if (rc)
+		return ERR_PTR(rc);
+
+	return dev_dax;
+
+ err_dax:
+	if (dev_dax->id >= 0)
+		ida_simple_remove(&dax_region->ida, dev_dax->id);
+ err_id:
+	kfree(dev_dax);
+
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_GPL(devm_create_dev_dax);
+
+static int __init dax_init(void)
+{
+	dax_class = class_create(THIS_MODULE, "dax");
+	return PTR_ERR_OR_ZERO(dax_class);
+}
+
+static void __exit dax_exit(void)
+{
+	class_destroy(dax_class);
+}
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL v2");
+subsys_initcall(dax_init);
+module_exit(dax_exit);
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
new file mode 100644
index 000000000..2c1f459c0
--- /dev/null
+++ b/drivers/dax/pmem.c
@@ -0,0 +1,153 @@
+/*
+ * 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.
+ */
+#include <linux/percpu-refcount.h>
+#include <linux/memremap.h>
+#include <linux/module.h>
+#include <linux/pfn_t.h>
+#include "../nvdimm/pfn.h"
+#include "../nvdimm/nd.h"
+#include "device-dax.h"
+
+struct dax_pmem {
+	struct device *dev;
+	struct percpu_ref ref;
+	struct dev_pagemap pgmap;
+	struct completion cmp;
+};
+
+static struct dax_pmem *to_dax_pmem(struct percpu_ref *ref)
+{
+	return container_of(ref, struct dax_pmem, ref);
+}
+
+static void dax_pmem_percpu_release(struct percpu_ref *ref)
+{
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "trace\n");
+	complete(&dax_pmem->cmp);
+}
+
+static void dax_pmem_percpu_exit(void *data)
+{
+	struct percpu_ref *ref = data;
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "trace\n");
+	wait_for_completion(&dax_pmem->cmp);
+	percpu_ref_exit(ref);
+}
+
+static void dax_pmem_percpu_kill(struct percpu_ref *ref)
+{
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "trace\n");
+	percpu_ref_kill(ref);
+}
+
+static int dax_pmem_probe(struct device *dev)
+{
+	void *addr;
+	struct resource res;
+	int rc, id, region_id;
+	struct nd_pfn_sb *pfn_sb;
+	struct dev_dax *dev_dax;
+	struct dax_pmem *dax_pmem;
+	struct nd_namespace_io *nsio;
+	struct dax_region *dax_region;
+	struct nd_namespace_common *ndns;
+	struct nd_dax *nd_dax = to_nd_dax(dev);
+	struct nd_pfn *nd_pfn = &nd_dax->nd_pfn;
+
+	ndns = nvdimm_namespace_common_probe(dev);
+	if (IS_ERR(ndns))
+		return PTR_ERR(ndns);
+	nsio = to_nd_namespace_io(&ndns->dev);
+
+	dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
+	if (!dax_pmem)
+		return -ENOMEM;
+
+	/* parse the 'pfn' info block via ->rw_bytes */
+	rc = devm_nsio_enable(dev, nsio);
+	if (rc)
+		return rc;
+	rc = nvdimm_setup_pfn(nd_pfn, &dax_pmem->pgmap);
+	if (rc)
+		return rc;
+	devm_nsio_disable(dev, nsio);
+
+	pfn_sb = nd_pfn->pfn_sb;
+
+	if (!devm_request_mem_region(dev, nsio->res.start,
+				resource_size(&nsio->res),
+				dev_name(&ndns->dev))) {
+		dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
+		return -EBUSY;
+	}
+
+	dax_pmem->dev = dev;
+	init_completion(&dax_pmem->cmp);
+	rc = percpu_ref_init(&dax_pmem->ref, dax_pmem_percpu_release, 0,
+			GFP_KERNEL);
+	if (rc)
+		return rc;
+
+	rc = devm_add_action(dev, dax_pmem_percpu_exit, &dax_pmem->ref);
+	if (rc) {
+		percpu_ref_exit(&dax_pmem->ref);
+		return rc;
+	}
+
+	dax_pmem->pgmap.ref = &dax_pmem->ref;
+	dax_pmem->pgmap.kill = dax_pmem_percpu_kill;
+	addr = devm_memremap_pages(dev, &dax_pmem->pgmap);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
+	/* adjust the dax_region resource to the start of data */
+	memcpy(&res, &dax_pmem->pgmap.res, sizeof(res));
+	res.start += le64_to_cpu(pfn_sb->dataoff);
+
+	rc = sscanf(dev_name(&ndns->dev), "namespace%d.%d", &region_id, &id);
+	if (rc != 2)
+		return -EINVAL;
+
+	dax_region = alloc_dax_region(dev, region_id, &res,
+			le32_to_cpu(pfn_sb->align), addr, PFN_DEV|PFN_MAP);
+	if (!dax_region)
+		return -ENOMEM;
+
+	/* TODO: support for subdividing a dax region... */
+	dev_dax = devm_create_dev_dax(dax_region, id, &res, 1);
+
+	/* child dev_dax instances now own the lifetime of the dax_region */
+	dax_region_put(dax_region);
+
+	return PTR_ERR_OR_ZERO(dev_dax);
+}
+
+static struct nd_device_driver dax_pmem_driver = {
+	.probe = dax_pmem_probe,
+	.drv = {
+		.name = "dax_pmem",
+	},
+	.type = ND_DRIVER_DAX_PMEM,
+};
+
+module_nd_driver(dax_pmem_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
new file mode 100644
index 000000000..6e928f37d
--- /dev/null
+++ b/drivers/dax/super.c
@@ -0,0 +1,663 @@
+/*
+ * 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/genhd.h>
+#include <linux/pfn_t.h>
+#include <linux/cdev.h>
+#include <linux/hash.h>
+#include <linux/slab.h>
+#include <linux/uio.h>
+#include <linux/dax.h>
+#include <linux/fs.h>
+
+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);
+
+#ifdef CONFIG_BLOCK
+#include <linux/blkdev.h>
+
+int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
+		pgoff_t *pgoff)
+{
+	phys_addr_t phys_off = (get_start_sect(bdev) + sector) * 512;
+
+	if (pgoff)
+		*pgoff = PHYS_PFN(phys_off);
+	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
+		return -EINVAL;
+	return 0;
+}
+EXPORT_SYMBOL(bdev_dax_pgoff);
+
+#if IS_ENABLED(CONFIG_FS_DAX)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+{
+	if (!blk_queue_dax(bdev->bd_queue))
+		return NULL;
+	return fs_dax_get_by_host(bdev->bd_disk->disk_name);
+}
+EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
+#endif
+
+/**
+ * __bdev_dax_supported() - Check if the device supports dax for filesystem
+ * @bdev: block device to check
+ * @blocksize: The block size of the device
+ *
+ * This is a library function for filesystems to check if the block device
+ * can be mounted with dax option.
+ *
+ * Return: true if supported, false if unsupported
+ */
+bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+{
+	struct dax_device *dax_dev;
+	bool dax_enabled = false;
+	struct request_queue *q;
+	pgoff_t pgoff;
+	int err, id;
+	pfn_t pfn;
+	long len;
+	char buf[BDEVNAME_SIZE];
+
+	if (blocksize != PAGE_SIZE) {
+		pr_debug("%s: error: unsupported blocksize for dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
+	q = bdev_get_queue(bdev);
+	if (!q || !blk_queue_dax(q)) {
+		pr_debug("%s: error: request queue doesn't support dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
+	err = bdev_dax_pgoff(bdev, 0, PAGE_SIZE, &pgoff);
+	if (err) {
+		pr_debug("%s: error: unaligned partition for dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
+	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+	if (!dax_dev) {
+		pr_debug("%s: error: device does not support dax\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+
+	id = dax_read_lock();
+	len = dax_direct_access(dax_dev, pgoff, 1, NULL, &pfn);
+	dax_read_unlock(id);
+
+	put_dax(dax_dev);
+
+	if (len < 1) {
+		pr_debug("%s: error: dax access failed (%ld)\n",
+				bdevname(bdev, buf), len);
+		return false;
+	}
+
+	if (IS_ENABLED(CONFIG_FS_DAX_LIMITED) && pfn_t_special(pfn)) {
+		/*
+		 * An arch that has enabled the pmem api should also
+		 * have its drivers support pfn_t_devmap()
+		 *
+		 * This is a developer warning and should not trigger in
+		 * production. dax_flush() will crash since it depends
+		 * on being able to do (page_address(pfn_to_page())).
+		 */
+		WARN_ON(IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API));
+		dax_enabled = true;
+	} else if (pfn_t_devmap(pfn)) {
+		struct dev_pagemap *pgmap;
+
+		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
+		if (pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX)
+			dax_enabled = true;
+		put_dev_pagemap(pgmap);
+	}
+
+	if (!dax_enabled) {
+		pr_debug("%s: error: dax support not enabled\n",
+				bdevname(bdev, buf));
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(__bdev_dax_supported);
+#endif
+
+enum dax_device_flags {
+	/* !alive + rcu grace period == no new operations / mappings */
+	DAXDEV_ALIVE,
+	/* gate whether dax_flush() calls the low level flush routine */
+	DAXDEV_WRITE_CACHE,
+};
+
+/**
+ * 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
+ * @flags: state and boolean properties
+ */
+struct dax_device {
+	struct hlist_node list;
+	struct inode inode;
+	struct cdev cdev;
+	const char *host;
+	void *private;
+	unsigned long flags;
+	const struct dax_operations *ops;
+};
+
+static ssize_t write_cache_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+	ssize_t rc;
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return -ENXIO;
+
+	rc = sprintf(buf, "%d\n", !!dax_write_cache_enabled(dax_dev));
+	put_dax(dax_dev);
+	return rc;
+}
+
+static ssize_t write_cache_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	bool write_cache;
+	int rc = strtobool(buf, &write_cache);
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return -ENXIO;
+
+	if (rc)
+		len = rc;
+	else
+		dax_write_cache(dax_dev, write_cache);
+
+	put_dax(dax_dev);
+	return len;
+}
+static DEVICE_ATTR_RW(write_cache);
+
+static umode_t dax_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	struct device *dev = container_of(kobj, typeof(*dev), kobj);
+	struct dax_device *dax_dev = dax_get_by_host(dev_name(dev));
+
+	WARN_ON_ONCE(!dax_dev);
+	if (!dax_dev)
+		return 0;
+
+#ifndef CONFIG_ARCH_HAS_PMEM_API
+	if (a == &dev_attr_write_cache.attr)
+		return 0;
+#endif
+	return a->mode;
+}
+
+static struct attribute *dax_attributes[] = {
+	&dev_attr_write_cache.attr,
+	NULL,
+};
+
+struct attribute_group dax_attribute_group = {
+	.name = "dax",
+	.attrs = dax_attributes,
+	.is_visible = dax_visible,
+};
+EXPORT_SYMBOL_GPL(dax_attribute_group);
+
+/**
+ * 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;
+
+	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);
+
+size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	if (!dax_alive(dax_dev))
+		return 0;
+
+	return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_from_iter);
+
+size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
+		size_t bytes, struct iov_iter *i)
+{
+	if (!dax_alive(dax_dev))
+		return 0;
+
+	return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+}
+EXPORT_SYMBOL_GPL(dax_copy_to_iter);
+
+#ifdef CONFIG_ARCH_HAS_PMEM_API
+void arch_wb_cache_pmem(void *addr, size_t size);
+void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
+{
+	if (unlikely(!dax_write_cache_enabled(dax_dev)))
+		return;
+
+	arch_wb_cache_pmem(addr, size);
+}
+#else
+void dax_flush(struct dax_device *dax_dev, void *addr, size_t size)
+{
+}
+#endif
+EXPORT_SYMBOL_GPL(dax_flush);
+
+void dax_write_cache(struct dax_device *dax_dev, bool wc)
+{
+	if (wc)
+		set_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+	else
+		clear_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(dax_write_cache);
+
+bool dax_write_cache_enabled(struct dax_device *dax_dev)
+{
+	return test_bit(DAXDEV_WRITE_CACHE, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
+
+bool dax_alive(struct dax_device *dax_dev)
+{
+	lockdep_assert_held(&dax_srcu);
+	return test_bit(DAXDEV_ALIVE, &dax_dev->flags);
+}
+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;
+
+	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
+
+	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;
+	struct inode *inode;
+
+	dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
+	if (!dax_dev)
+		return NULL;
+
+	inode = &dax_dev->inode;
+	inode->i_rdev = 0;
+	return 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;
+	if (inode->i_rdev)
+		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(test_bit(DAXDEV_ALIVE, &dax_dev->flags),
+			"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) {
+		set_bit(DAXDEV_ALIVE, &dax_dev->flags);
+		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, MINORMASK+1, 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;
+
+	memset(dax_dev, 0, sizeof(*dax_dev));
+	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;
+
+	rc = alloc_chrdev_region(&dax_devt, 0, MINORMASK+1, "dax");
+	if (rc)
+		__dax_fs_exit();
+	return rc;
+}
+
+static void __exit dax_fs_exit(void)
+{
+	unregister_chrdev_region(dax_devt, MINORMASK+1);
+	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);