Merge branch 'for-4.7/dax' into libnvdimm-for-next

block/ioctl.c

···
 		ret == -ENOIOCTLCMD;
 }
 
-#ifdef CONFIG_FS_DAX
-bool blkdev_dax_capable(struct block_device *bdev)
-{
-	struct gendisk *disk = bdev->bd_disk;
-
-	if (!disk->fops->direct_access)
-		return false;
-
-	/*
-	 * If the partition is not aligned on a page boundary, we can't
-	 * do dax I/O to it.
-	 */
-	if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
-			|| (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
-		return false;
-
-	/*
-	 * If the device has known bad blocks, force all I/O through the
-	 * driver / page cache.
-	 *
-	 * TODO: support finer grained dax error handling
-	 */
-	if (disk->bb && disk->bb->count)
-		return false;
-
-	return true;
-}
-#endif
-
 static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode,
 		unsigned cmd, unsigned long arg)
 {
···
 	case BLKTRACESETUP:
 	case BLKTRACETEARDOWN:
 		return blk_trace_ioctl(bdev, cmd, argp);
-	case BLKDAXGET:
-		return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX));
-		break;
 	case IOC_PR_REGISTER:
 		return blkdev_pr_register(bdev, argp);
 	case IOC_PR_RESERVE:

drivers/Kconfig

···
 
 source "drivers/nvdimm/Kconfig"
 
+source "drivers/dax/Kconfig"
+
 source "drivers/nvmem/Kconfig"
 
 source "drivers/hwtracing/stm/Kconfig"

drivers/Makefile

···
 obj-$(CONFIG_NVM)		+= lightnvm/
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
+obj-$(CONFIG_DEV_DAX)		+= dax/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/

drivers/dax/Kconfig

···
+menuconfig DEV_DAX
+	tristate "DAX: direct access to differentiated memory"
+	default m if NVDIMM_DAX
+	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.
+
+if DEV_DAX
+
+config DEV_DAX_PMEM
+	tristate "PMEM DAX: direct access to persistent memory"
+	depends on NVDIMM_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

drivers/dax/Makefile

···
+obj-$(CONFIG_DEV_DAX) += dax.o
+obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
+
+dax_pmem-y := pmem.o

drivers/dax/dax.c

···
+/*
+ * 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/pagemap.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/pfn_t.h>
+#include <linux/slab.h>
+#include <linux/dax.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+
+static int dax_major;
+static struct class *dax_class;
+static DEFINE_IDA(dax_minor_ida);
+
+/**
+ * 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
+ * @kref - enable this data to be tracked in filp->private_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
+ * @res - array of physical address ranges
+ */
+struct dax_dev {
+	struct dax_region *region;
+	struct device *dev;
+	struct kref kref;
+	bool alive;
+	int id;
+	int num_resources;
+	struct resource res[0];
+};
+
+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_dev_free(struct kref *kref)
+{
+	struct dax_dev *dax_dev;
+
+	dax_dev = container_of(kref, struct dax_dev, kref);
+	dax_region_put(dax_dev->region);
+	kfree(dax_dev);
+}
+
+static void dax_dev_put(struct dax_dev *dax_dev)
+{
+	kref_put(&dax_dev->kref, dax_dev_free);
+}
+
+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;
+
+	dax_region = kzalloc(sizeof(*dax_region), GFP_KERNEL);
+
+	if (!dax_region)
+		return NULL;
+
+	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;
+
+	return dax_region;
+}
+EXPORT_SYMBOL_GPL(alloc_dax_region);
+
+static ssize_t size_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct dax_dev *dax_dev = dev_get_drvdata(dev);
+	unsigned long long size = 0;
+	int i;
+
+	for (i = 0; i < dax_dev->num_resources; i++)
+		size += resource_size(&dax_dev->res[i]);
+
+	return sprintf(buf, "%llu\n", size);
+}
+static DEVICE_ATTR_RO(size);
+
+static struct attribute *dax_device_attributes[] = {
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct attribute_group dax_device_attribute_group = {
+	.attrs = dax_device_attributes,
+};
+
+static const struct attribute_group *dax_attribute_groups[] = {
+	&dax_device_attribute_group,
+	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(dax_region->dev, unregister_dax_dev, dev);
+	if (rc) {
+		unregister_dax_dev(dev);
+		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;
+	unsigned long mask;
+
+	if (!dax_dev->alive)
+		return -ENXIO;
+
+	/* prevent private / writable mappings from being established */
+	if ((vma->vm_flags & (VM_NORESERVE|VM_SHARED|VM_WRITE)) == VM_WRITE) {
+		dev_info(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(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(dev, "%s: %s: fail, dax range requires MADV_DONTFORK\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	if (!vma_is_dax(vma)) {
+		dev_info(dev, "%s: %s: fail, vma is not DAX capable\n",
+				current->comm, func);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static phys_addr_t pgoff_to_phys(struct dax_dev *dax_dev, 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];
+		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 (phys + size - 1 <= res->end)
+			return phys;
+	}
+
+	return -1;
+}
+
+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 dax_region *dax_region;
+	int rc = VM_FAULT_SIGBUS;
+	phys_addr_t phys;
+	pfn_t pfn;
+
+	if (check_vma(dax_dev, vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dax_dev->region;
+	if (dax_region->align > PAGE_SIZE) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	phys = pgoff_to_phys(dax_dev, vmf->pgoff, PAGE_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+				vmf->pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	rc = vm_insert_mixed(vma, vaddr, pfn);
+
+	if (rc == -ENOMEM)
+		return VM_FAULT_OOM;
+	if (rc < 0 && rc != -EBUSY)
+		return VM_FAULT_SIGBUS;
+
+	return VM_FAULT_NOPAGE;
+}
+
+static int dax_dev_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	int rc;
+	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__,
+			current->comm, (vmf->flags & FAULT_FLAG_WRITE)
+			? "write" : "read", vma->vm_start, vma->vm_end);
+	rcu_read_lock();
+	rc = __dax_dev_fault(dax_dev, vma, vmf);
+	rcu_read_unlock();
+
+	return rc;
+}
+
+static int __dax_dev_pmd_fault(struct dax_dev *dax_dev,
+		struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd,
+		unsigned int flags)
+{
+	unsigned long pmd_addr = addr & PMD_MASK;
+	struct device *dev = dax_dev->dev;
+	struct dax_region *dax_region;
+	phys_addr_t phys;
+	pgoff_t pgoff;
+	pfn_t pfn;
+
+	if (check_vma(dax_dev, vma, __func__))
+		return VM_FAULT_SIGBUS;
+
+	dax_region = dax_dev->region;
+	if (dax_region->align > PMD_SIZE) {
+		dev_dbg(dev, "%s: alignment > fault size\n", __func__);
+		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__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pgoff = linear_page_index(vma, pmd_addr);
+	phys = pgoff_to_phys(dax_dev, pgoff, PAGE_SIZE);
+	if (phys == -1) {
+		dev_dbg(dev, "%s: phys_to_pgoff(%#lx) failed\n", __func__,
+				pgoff);
+		return VM_FAULT_SIGBUS;
+	}
+
+	pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
+
+	return vmf_insert_pfn_pmd(vma, addr, pmd, pfn,
+			flags & FAULT_FLAG_WRITE);
+}
+
+static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
+		pmd_t *pmd, unsigned int flags)
+{
+	int rc;
+	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__,
+			current->comm, (flags & FAULT_FLAG_WRITE)
+			? "write" : "read", vma->vm_start, vma->vm_end);
+
+	rcu_read_lock();
+	rc = __dax_dev_pmd_fault(dax_dev, vma, addr, pmd, flags);
+	rcu_read_unlock();
+
+	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)
+{
+	struct dax_dev *dax_dev = filp->private_data;
+	int rc;
+
+	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;
+
+}
+
+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,
+};
+
+static int __init dax_init(void)
+{
+	int rc;
+
+	rc = register_chrdev(0, "dax", &dax_fops);
+	if (rc < 0)
+		return rc;
+	dax_major = rc;
+
+	dax_class = class_create(THIS_MODULE, "dax");
+	if (IS_ERR(dax_class)) {
+		unregister_chrdev(dax_major, "dax");
+		return PTR_ERR(dax_class);
+	}
+
+	return 0;
+}
+
+static void __exit dax_exit(void)
+{
+	class_destroy(dax_class);
+	unregister_chrdev(dax_major, "dax");
+	ida_destroy(&dax_minor_ida);
+}
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL v2");
+subsys_initcall(dax_init);
+module_exit(dax_exit);

drivers/dax/dax.h

···
+/*
+ * 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_H__
+#define __DAX_H__
+struct device;
+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);
+#endif /* __DAX_H__ */

drivers/dax/pmem.c

···
+/*
+ * 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 "dax.h"
+
+struct dax_pmem {
+	struct device *dev;
+	struct percpu_ref ref;
+	struct completion cmp;
+};
+
+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, "%s\n", __func__);
+	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, "%s\n", __func__);
+	percpu_ref_exit(ref);
+	wait_for_completion(&dax_pmem->cmp);
+}
+
+static void dax_pmem_percpu_kill(void *data)
+{
+	struct percpu_ref *ref = data;
+	struct dax_pmem *dax_pmem = to_dax_pmem(ref);
+
+	dev_dbg(dax_pmem->dev, "%s\n", __func__);
+	percpu_ref_kill(ref);
+}
+
+static int dax_pmem_probe(struct device *dev)
+{
+	int rc;
+	void *addr;
+	struct resource res;
+	struct nd_pfn_sb *pfn_sb;
+	struct dax_pmem *dax_pmem;
+	struct nd_region *nd_region;
+	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;
+	struct vmem_altmap __altmap, *altmap = NULL;
+
+	ndns = nvdimm_namespace_common_probe(dev);
+	if (IS_ERR(ndns))
+		return PTR_ERR(ndns);
+	nsio = to_nd_namespace_io(&ndns->dev);
+
+	/* parse the 'pfn' info block via ->rw_bytes */
+	devm_nsio_enable(dev, nsio);
+	altmap = nvdimm_setup_pfn(nd_pfn, &res, &__altmap);
+	if (IS_ERR(altmap))
+		return PTR_ERR(altmap);
+	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(dev))) {
+		dev_warn(dev, "could not reserve region %pR\n", &nsio->res);
+		return -EBUSY;
+	}
+
+	dax_pmem = devm_kzalloc(dev, sizeof(*dax_pmem), GFP_KERNEL);
+	if (!dax_pmem)
+		return -ENOMEM;
+
+	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) {
+		dax_pmem_percpu_exit(&dax_pmem->ref);
+		return rc;
+	}
+
+	addr = devm_memremap_pages(dev, &res, &dax_pmem->ref, altmap);
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
+
+	rc = devm_add_action(dev, dax_pmem_percpu_kill, &dax_pmem->ref);
+	if (rc) {
+		dax_pmem_percpu_kill(&dax_pmem->ref);
+		return rc;
+	}
+
+	nd_region = to_nd_region(dev->parent);
+	dax_region = alloc_dax_region(dev, nd_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... */
+	rc = 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;
+}
+
+static struct nd_device_driver dax_pmem_driver = {
+	.probe = dax_pmem_probe,
+	.drv = {
+		.name = "dax_pmem",
+	},
+	.type = ND_DRIVER_DAX_PMEM,
+};
+
+static int __init dax_pmem_init(void)
+{
+	return nd_driver_register(&dax_pmem_driver);
+}
+module_init(dax_pmem_init);
+
+static void __exit dax_pmem_exit(void)
+{
+	driver_unregister(&dax_pmem_driver.drv);
+}
+module_exit(dax_pmem_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);

drivers/nvdimm/bus.c

···
 	struct nd_device_driver *nd_drv = to_nd_device_driver(dev->driver);
 	struct module *provider = to_bus_provider(dev);
 	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
-	int rc;
+	int rc = 0;
 
-	rc = nd_drv->remove(dev);
+	if (nd_drv->remove)
+		rc = nd_drv->remove(dev);
 	nd_region_disable(nvdimm_bus, dev);
 
 	dev_dbg(&nvdimm_bus->dev, "%s.remove(%s) = %d\n", dev->driver->name,
···
 		return -EINVAL;
 	}
 
-	if (!nd_drv->probe || !nd_drv->remove) {
-		pr_debug("->probe() and ->remove() must be specified\n");
+	if (!nd_drv->probe) {
+		pr_debug("%s ->probe() must be specified\n", mod_name);
 		return -EINVAL;
 	}
 

drivers/nvdimm/claim.c

···
 	return true;
 }
 
+struct nd_pfn *to_nd_pfn_safe(struct device *dev)
+{
+	/*
+	 * pfn device attributes are re-used by dax device instances, so we
+	 * need to be careful to correct device-to-nd_pfn conversion.
+	 */
+	if (is_nd_pfn(dev))
+		return to_nd_pfn(dev);
+
+	if (is_nd_dax(dev)) {
+		struct nd_dax *nd_dax = to_nd_dax(dev);
+
+		return &nd_dax->nd_pfn;
+	}
+
+	WARN_ON(1);
+	return NULL;
+}
+
 static void nd_detach_and_reset(struct device *dev,
 		struct nd_namespace_common **_ndns)
 {
···
 		nd_btt->lbasize = 0;
 		kfree(nd_btt->uuid);
 		nd_btt->uuid = NULL;
-	} else if (is_nd_pfn(dev)) {
-		struct nd_pfn *nd_pfn = to_nd_pfn(dev);
+	} else if (is_nd_pfn(dev) || is_nd_dax(dev)) {
+		struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
 
 		kfree(nd_pfn->uuid);
 		nd_pfn->uuid = NULL;

drivers/nvdimm/core.c

···
 	nd_region_exit();
 	nvdimm_exit();
 	nvdimm_bus_exit();
+	nd_region_devs_exit();
+	nvdimm_devs_exit();
+	ida_destroy(&nd_ida);
 }
 
 MODULE_LICENSE("GPL v2");

drivers/nvdimm/dax_devs.c

···
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include "nd-core.h"
+#include "pfn.h"
 #include "nd.h"
 
 static void nd_dax_release(struct device *dev)
···
 	__nd_device_register(dev);
 	return dev;
 }
+
+int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns)
+{
+	int rc;
+	struct nd_dax *nd_dax;
+	struct device *dax_dev;
+	struct nd_pfn *nd_pfn;
+	struct nd_pfn_sb *pfn_sb;
+	struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
+
+	if (ndns->force_raw)
+		return -ENODEV;
+
+	nvdimm_bus_lock(&ndns->dev);
+	nd_dax = nd_dax_alloc(nd_region);
+	nd_pfn = &nd_dax->nd_pfn;
+	dax_dev = nd_pfn_devinit(nd_pfn, ndns);
+	nvdimm_bus_unlock(&ndns->dev);
+	if (!dax_dev)
+		return -ENOMEM;
+	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
+	nd_pfn->pfn_sb = pfn_sb;
+	rc = nd_pfn_validate(nd_pfn, DAX_SIG);
+	dev_dbg(dev, "%s: dax: %s\n", __func__,
+			rc == 0 ? dev_name(dax_dev) : "<none>");
+	if (rc < 0) {
+		__nd_detach_ndns(dax_dev, &nd_pfn->ndns);
+		put_device(dax_dev);
+	} else
+		__nd_device_register(dax_dev);
+
+	return rc;
+}
+EXPORT_SYMBOL(nd_dax_probe);

drivers/nvdimm/dimm_devs.c

···
 	return 0;
 }
 EXPORT_SYMBOL_GPL(nvdimm_bus_check_dimm_count);
+
+void __exit nvdimm_devs_exit(void)
+{
+	ida_destroy(&dimm_ida);
+}

drivers/nvdimm/nd-core.h

···
 struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev);
 int __init nvdimm_bus_init(void);
 void nvdimm_bus_exit(void);
+void nvdimm_devs_exit(void);
+void nd_region_devs_exit(void);
 void nd_region_probe_success(struct nvdimm_bus *nvdimm_bus, struct device *dev);
 struct nd_region;
 void nd_region_create_blk_seed(struct nd_region *nd_region);
···
 ssize_t nd_namespace_store(struct device *dev,
 		struct nd_namespace_common **_ndns, const char *buf,
 		size_t len);
+struct nd_pfn *to_nd_pfn_safe(struct device *dev);
 #endif /* __ND_CORE_H__ */

drivers/nvdimm/nd.h

···
 struct device *nd_pfn_create(struct nd_region *nd_region);
 struct device *nd_pfn_devinit(struct nd_pfn *nd_pfn,
 		struct nd_namespace_common *ndns);
-int nd_pfn_validate(struct nd_pfn *nd_pfn);
+int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig);
 extern struct attribute_group nd_pfn_attribute_group;
 #else
 static inline int nd_pfn_probe(struct device *dev,
···
 	return NULL;
 }
 
-static inline int nd_pfn_validate(struct nd_pfn *nd_pfn)
+static inline int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	return -ENODEV;
 }
···
 
 struct nd_dax *to_nd_dax(struct device *dev);
 #if IS_ENABLED(CONFIG_NVDIMM_DAX)
+int nd_dax_probe(struct device *dev, struct nd_namespace_common *ndns);
 bool is_nd_dax(struct device *dev);
 struct device *nd_dax_create(struct nd_region *nd_region);
 #else
+static inline int nd_dax_probe(struct device *dev,
+		struct nd_namespace_common *ndns)
+{
+	return -ENODEV;
+}
+
 static inline bool is_nd_dax(struct device *dev)
 {
 	return false;

drivers/nvdimm/pfn.h

···
 
 #define PFN_SIG_LEN 16
 #define PFN_SIG "NVDIMM_PFN_INFO\0"
+#define DAX_SIG "NVDIMM_DAX_INFO\0"
 
 struct nd_pfn_sb {
 	u8 signature[PFN_SIG_LEN];

drivers/nvdimm/pfn_devs.c

···
 }
 EXPORT_SYMBOL(to_nd_pfn);
 
-static struct nd_pfn *to_nd_pfn_safe(struct device *dev)
-{
-	/*
-	 * pfn device attributes are re-used by dax device instances, so we
-	 * need to be careful to correct device-to-nd_pfn conversion.
-	 */
-	if (is_nd_pfn(dev))
-		return to_nd_pfn(dev);
-
-	if (is_nd_dax(dev)) {
-		struct nd_dax *nd_dax = to_nd_dax(dev);
-
-		return &nd_dax->nd_pfn;
-	}
-
-	WARN_ON(1);
-	return NULL;
-}
-
 static ssize_t mode_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
···
 	return dev;
 }
 
-int nd_pfn_validate(struct nd_pfn *nd_pfn)
+int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
 {
 	u64 checksum, offset;
 	struct nd_namespace_io *nsio;
···
 	if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
 		return -ENXIO;
 
-	if (memcmp(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN) != 0)
+	if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
 		return -ENODEV;
 
 	checksum = le64_to_cpu(pfn_sb->checksum);
···
 			return -ENODEV;
 	}
 
+	if (nd_pfn->align == 0)
+		nd_pfn->align = le32_to_cpu(pfn_sb->align);
 	if (nd_pfn->align > nvdimm_namespace_capacity(ndns)) {
 		dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
 				nd_pfn->align, nvdimm_namespace_capacity(ndns));
···
 		return -EBUSY;
 	}
 
-	nd_pfn->align = le32_to_cpu(pfn_sb->align);
-	if (!is_power_of_2(offset) || offset < PAGE_SIZE) {
+	if ((nd_pfn->align && !IS_ALIGNED(offset, nd_pfn->align))
+			|| !IS_ALIGNED(offset, PAGE_SIZE)) {
 		dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled\n",
 				offset);
 		return -ENXIO;
···
 	pfn_sb = devm_kzalloc(dev, sizeof(*pfn_sb), GFP_KERNEL);
 	nd_pfn = to_nd_pfn(pfn_dev);
 	nd_pfn->pfn_sb = pfn_sb;
-	rc = nd_pfn_validate(nd_pfn);
+	rc = nd_pfn_validate(nd_pfn, PFN_SIG);
 	dev_dbg(dev, "%s: pfn: %s\n", __func__,
 			rc == 0 ? dev_name(pfn_dev) : "<none>");
 	if (rc < 0) {
···
 	struct nd_pfn_sb *pfn_sb;
 	unsigned long npfns;
 	phys_addr_t offset;
+	const char *sig;
 	u64 checksum;
 	int rc;
 
···
 		return -ENOMEM;
 
 	nd_pfn->pfn_sb = pfn_sb;
-	rc = nd_pfn_validate(nd_pfn);
+	if (is_nd_dax(&nd_pfn->dev))
+		sig = DAX_SIG;
+	else
+		sig = PFN_SIG;
+	rc = nd_pfn_validate(nd_pfn, sig);
 	if (rc != -ENODEV)
 		return rc;
 
···
 	pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
 	pfn_sb->dataoff = cpu_to_le64(offset);
 	pfn_sb->npfns = cpu_to_le64(npfns);
-	memcpy(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN);
+	memcpy(pfn_sb->signature, sig, PFN_SIG_LEN);
 	memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
 	memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
 	pfn_sb->version_major = cpu_to_le16(1);

drivers/nvdimm/pmem.c

···
 		return pmem_attach_disk(dev, ndns);
 
 	/* if we find a valid info-block we'll come back as that personality */
-	if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0)
+	if (nd_btt_probe(dev, ndns) == 0 || nd_pfn_probe(dev, ndns) == 0
+			|| nd_dax_probe(dev, ndns) == 0)
 		return -ENXIO;
 
 	/* ...otherwise we're just a raw pmem device */

drivers/nvdimm/region_devs.c

···
 			__func__);
 }
 EXPORT_SYMBOL_GPL(nvdimm_volatile_region_create);
+
+void __exit nd_region_devs_exit(void)
+{
+	ida_destroy(&region_ida);
+}

fs/block_dev.c

···
 #include <linux/log2.h>
 #include <linux/cleancache.h>
 #include <linux/dax.h>
+#include <linux/badblocks.h>
 #include <asm/uaccess.h>
 #include "internal.h"
 
···
 }
 EXPORT_SYMBOL(bd_set_size);
 
+static bool blkdev_dax_capable(struct block_device *bdev)
+{
+	struct gendisk *disk = bdev->bd_disk;
+
+	if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX))
+		return false;
+
+	/*
+	 * If the partition is not aligned on a page boundary, we can't
+	 * do dax I/O to it.
+	 */
+	if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512))
+			|| (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+		return false;
+
+	/*
+	 * If the device has known bad blocks, force all I/O through the
+	 * driver / page cache.
+	 *
+	 * TODO: support finer grained dax error handling
+	 */
+	if (disk->bb && disk->bb->count)
+		return false;
+
+	return true;
+}
+
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
···
 	.is_dirty_writeback = buffer_check_dirty_writeback,
 };
 
-#ifdef CONFIG_FS_DAX
-/*
- * In the raw block case we do not need to contend with truncation nor
- * unwritten file extents.  Without those concerns there is no need for
- * additional locking beyond the mmap_sem context that these routines
- * are already executing under.
- *
- * Note, there is no protection if the block device is dynamically
- * resized (partition grow/shrink) during a fault. A stable block device
- * size is already not enforced in the blkdev_direct_IO path.
- *
- * For DAX, it is the responsibility of the block device driver to
- * ensure the whole-disk device size is stable while requests are in
- * flight.
- *
- * Finally, unlike the filemap_page_mkwrite() case there is no
- * filesystem superblock to sync against freezing.  We still include a
- * pfn_mkwrite callback for dax drivers to receive write fault
- * notifications.
- */
-static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
-{
-	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
-}
-
-static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
-		struct vm_fault *vmf)
-{
-	return dax_pfn_mkwrite(vma, vmf);
-}
-
-static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, unsigned int flags)
-{
-	return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL);
-}
-
-static const struct vm_operations_struct blkdev_dax_vm_ops = {
-	.fault		= blkdev_dax_fault,
-	.pmd_fault	= blkdev_dax_pmd_fault,
-	.pfn_mkwrite	= blkdev_dax_pfn_mkwrite,
-};
-
-static const struct vm_operations_struct blkdev_default_vm_ops = {
-	.fault		= filemap_fault,
-	.map_pages	= filemap_map_pages,
-};
-
-static int blkdev_mmap(struct file *file, struct vm_area_struct *vma)
-{
-	struct inode *bd_inode = bdev_file_inode(file);
-
-	file_accessed(file);
-	if (IS_DAX(bd_inode)) {
-		vma->vm_ops = &blkdev_dax_vm_ops;
-		vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE;
-	} else {
-		vma->vm_ops = &blkdev_default_vm_ops;
-	}
-
-	return 0;
-}
-#else
-#define blkdev_mmap generic_file_mmap
-#endif
-
 const struct file_operations def_blk_fops = {
 	.open		= blkdev_open,
 	.release	= blkdev_close,
 	.llseek		= block_llseek,
 	.read_iter	= blkdev_read_iter,
 	.write_iter	= blkdev_write_iter,
-	.mmap		= blkdev_mmap,
+	.mmap		= generic_file_mmap,
 	.fsync		= blkdev_fsync,
 	.unlocked_ioctl	= block_ioctl,
 #ifdef CONFIG_COMPAT

include/linux/fs.h

···
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
-#ifdef CONFIG_FS_DAX
-extern bool blkdev_dax_capable(struct block_device *bdev);
-#else
-static inline bool blkdev_dax_capable(struct block_device *bdev)
-{
-	return false;
-}
-#endif
 
 extern struct super_block *blockdev_superblock;
 

include/uapi/linux/fs.h

···
 #define BLKSECDISCARD _IO(0x12,125)
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
-#define BLKDAXGET _IO(0x12,129)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */

mm/huge_memory.c

···
 	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write);
 	return VM_FAULT_NOPAGE;
 }
+EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
 
 static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd)

mm/hugetlb.c

···
 {
 	return vma_hugecache_offset(hstate_vma(vma), vma, address);
 }
+EXPORT_SYMBOL_GPL(linear_hugepage_index);
 
 /*
  * Return the size of the pages allocated when backing a VMA. In the majority

tools/testing/nvdimm/Kbuild

···
 DRIVERS := ../../../drivers
 NVDIMM_SRC := $(DRIVERS)/nvdimm
 ACPI_SRC := $(DRIVERS)/acpi
+DAX_SRC := $(DRIVERS)/dax
 
 obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
···
 obj-$(CONFIG_ND_BLK) += nd_blk.o
 obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_ACPI_NFIT) += nfit.o
+obj-$(CONFIG_DEV_DAX) += dax.o
+obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
 
 nfit-y := $(ACPI_SRC)/nfit.o
 nfit-y += config_check.o
···
 
 nd_e820-y := $(NVDIMM_SRC)/e820.o
 nd_e820-y += config_check.o
+
+dax-y := $(DAX_SRC)/dax.o
+dax-y += config_check.o
+
+dax_pmem-y := $(DAX_SRC)/pmem.o
+dax_pmem-y += config_check.o
 
 libnvdimm-y := $(NVDIMM_SRC)/core.o
 libnvdimm-y += $(NVDIMM_SRC)/bus.o

tools/testing/nvdimm/config_check.c

···
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BTT));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ND_BLK));
 	BUILD_BUG_ON(!IS_MODULE(CONFIG_ACPI_NFIT));
+	BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX));
+	BUILD_BUG_ON(!IS_MODULE(CONFIG_DEV_DAX_PMEM));
 }