1 files changed, 253 insertions, 305 deletions

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 6e928f37d084..c00b9dff4a06 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -1,27 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * 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/pseudo_fs.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>
+#include <linux/cacheinfo.h>
+#include "dax-private.h"
+
+/**
+ * struct dax_device - anchor object for dax services
+ * @inode: core vfs
+ * @cdev: optional character interface for "device dax"
+ * @private: dax driver private data
+ * @flags: state and boolean properties
+ * @ops: operations for this device
+ * @holder_data: holder of a dax_device: could be filesystem or mapped device
+ * @holder_ops: operations for the inner holder
+ */
+struct dax_device {
+	struct inode inode;
+	struct cdev cdev;
+	void *private;
+	unsigned long flags;
+	const struct dax_operations *ops;
+	void *holder_data;
+	const struct dax_holder_operations *holder_ops;
+};
 
 static dev_t dax_devt;
 DEFINE_STATIC_SRCU(dax_srcu);
@@ -30,10 +42,6 @@ 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);
@@ -46,216 +54,92 @@ void dax_read_unlock(int id)
 }
 EXPORT_SYMBOL_GPL(dax_read_unlock);
 
-#ifdef CONFIG_BLOCK
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
 #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;
+static DEFINE_XARRAY(dax_hosts);
 
-	if (pgoff)
-		*pgoff = PHYS_PFN(phys_off);
-	if (phys_off % PAGE_SIZE || size % PAGE_SIZE)
-		return -EINVAL;
-	return 0;
+int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
+{
+	return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL);
 }
-EXPORT_SYMBOL(bdev_dax_pgoff);
+EXPORT_SYMBOL_GPL(dax_add_host);
 
-#if IS_ENABLED(CONFIG_FS_DAX)
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
+void dax_remove_host(struct gendisk *disk)
 {
-	if (!blk_queue_dax(bdev->bd_queue))
-		return NULL;
-	return fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	xa_erase(&dax_hosts, (unsigned long)disk);
 }
-EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
-#endif
+EXPORT_SYMBOL_GPL(dax_remove_host);
 
 /**
- * __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
+ * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
+ * @bdev: block device to find a dax_device for
+ * @start_off: returns the byte offset into the dax_device that @bdev starts
+ * @holder: filesystem or mapped device inside the dax_device
+ * @ops: operations for the inner holder
  */
-bool __bdev_dax_supported(struct block_device *bdev, int blocksize)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
+		void *holder, const struct dax_holder_operations *ops)
 {
 	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;
-	}
+	u64 part_size;
+	int id;
 
-	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;
-	}
+	if (!blk_queue_dax(bdev->bd_disk->queue))
+		return NULL;
 
-	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;
+	*start_off = get_start_sect(bdev) * SECTOR_SIZE;
+	part_size = bdev_nr_sectors(bdev) * SECTOR_SIZE;
+	if (*start_off % PAGE_SIZE || part_size % PAGE_SIZE) {
+		pr_info("%pg: error: unaligned partition for dax\n", bdev);
+		return NULL;
 	}
 
 	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;
+	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
+	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
+		dax_dev = NULL;
+	else if (holder) {
+		if (!cmpxchg(&dax_dev->holder_data, NULL, holder))
+			dax_dev->holder_ops = ops;
+		else
+			dax_dev = NULL;
 	}
+	dax_read_unlock(id);
 
-	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);
-	}
+	return dax_dev;
+}
+EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 
-	if (!dax_enabled) {
-		pr_debug("%s: error: dax support not enabled\n",
-				bdevname(bdev, buf));
-		return false;
-	}
-	return true;
+void fs_put_dax(struct dax_device *dax_dev, void *holder)
+{
+	if (dax_dev && holder &&
+	    cmpxchg(&dax_dev->holder_data, holder, NULL) == holder)
+		dax_dev->holder_ops = NULL;
+	put_dax(dax_dev);
 }
-EXPORT_SYMBOL_GPL(__bdev_dax_supported);
-#endif
+EXPORT_SYMBOL_GPL(fs_put_dax);
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
 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,
+	/* flag to check if device supports synchronous flush */
+	DAXDEV_SYNC,
+	/* do not leave the caches dirty after writes */
+	DAXDEV_NOCACHE,
+	/* handle CPU fetch exceptions during reads */
+	DAXDEV_NOMC,
 };
 
 /**
- * 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
+ * @mode: indicator on normal access or recovery write
  * @kaddr: output parameter that returns a virtual address mapping of pfn
  * @pfn: output parameter that returns an absolute pfn translation of @pgoff
  *
@@ -263,7 +147,7 @@ EXPORT_SYMBOL_GPL(dax_attribute_group);
  * 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)
+		enum dax_access_mode mode, void **kaddr, unsigned long *pfn)
 {
 	long avail;
 
@@ -274,10 +158,10 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		return -ENXIO;
 
 	if (nr_pages < 0)
-		return nr_pages;
+		return -EINVAL;
 
 	avail = dax_dev->ops->direct_access(dax_dev, pgoff, nr_pages,
-			kaddr, pfn);
+			mode, kaddr, pfn);
 	if (!avail)
 		return -ERANGE;
 	return min(avail, nr_pages);
@@ -290,9 +174,15 @@ size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 	if (!dax_alive(dax_dev))
 		return 0;
 
-	return dax_dev->ops->copy_from_iter(dax_dev, pgoff, addr, bytes, i);
+	/*
+	 * The userspace address for the memory copy has already been validated
+	 * via access_ok() in vfs_write, so use the 'no check' version to bypass
+	 * the HARDENED_USERCOPY overhead.
+	 */
+	if (test_bit(DAXDEV_NOCACHE, &dax_dev->flags))
+		return _copy_from_iter_flushcache(addr, bytes, i);
+	return _copy_from_iter(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)
@@ -300,9 +190,67 @@ size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 	if (!dax_alive(dax_dev))
 		return 0;
 
-	return dax_dev->ops->copy_to_iter(dax_dev, pgoff, addr, bytes, i);
+	/*
+	 * The userspace address for the memory copy has already been validated
+	 * via access_ok() in vfs_red, so use the 'no check' version to bypass
+	 * the HARDENED_USERCOPY overhead.
+	 */
+	if (test_bit(DAXDEV_NOMC, &dax_dev->flags))
+		return _copy_mc_to_iter(addr, bytes, i);
+	return _copy_to_iter(addr, bytes, i);
 }
-EXPORT_SYMBOL_GPL(dax_copy_to_iter);
+
+int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
+			size_t nr_pages)
+{
+	int ret;
+
+	if (!dax_alive(dax_dev))
+		return -ENXIO;
+	/*
+	 * There are no callers that want to zero more than one page as of now.
+	 * Once users are there, this check can be removed after the
+	 * device mapper code has been updated to split ranges across targets.
+	 */
+	if (nr_pages != 1)
+		return -EIO;
+
+	ret = dax_dev->ops->zero_page_range(dax_dev, pgoff, nr_pages);
+	return dax_mem2blk_err(ret);
+}
+EXPORT_SYMBOL_GPL(dax_zero_page_range);
+
+size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
+		void *addr, size_t bytes, struct iov_iter *iter)
+{
+	if (!dax_dev->ops->recovery_write)
+		return 0;
+	return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter);
+}
+EXPORT_SYMBOL_GPL(dax_recovery_write);
+
+int dax_holder_notify_failure(struct dax_device *dax_dev, u64 off,
+			      u64 len, int mf_flags)
+{
+	int rc, id;
+
+	id = dax_read_lock();
+	if (!dax_alive(dax_dev)) {
+		rc = -ENXIO;
+		goto out;
+	}
+
+	if (!dax_dev->holder_ops) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	rc = dax_dev->holder_ops->notify_failure(dax_dev, off, len, mf_flags);
+out:
+	dax_read_unlock(id);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(dax_holder_notify_failure);
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size);
@@ -335,6 +283,30 @@ bool dax_write_cache_enabled(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(dax_write_cache_enabled);
 
+bool dax_synchronous(struct dax_device *dax_dev)
+{
+	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(dax_synchronous);
+
+void set_dax_synchronous(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_SYNC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(set_dax_synchronous);
+
+void set_dax_nocache(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_NOCACHE, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(set_dax_nocache);
+
+void set_dax_nomc(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_NOMC, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(set_dax_nomc);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);
@@ -342,40 +314,47 @@ bool dax_alive(struct dax_device *dax_dev)
 }
 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().
+ *
+ * Note, because alloc_dax() returns an ERR_PTR() on error, callers
+ * typically store its result into a local variable in order to check
+ * the result. Therefore, care must be taken to populate the struct
+ * device dax_dev field make sure the dax_dev is not leaked.
  */
 void kill_dax(struct dax_device *dax_dev)
 {
 	if (!dax_dev)
 		return;
 
-	clear_bit(DAXDEV_ALIVE, &dax_dev->flags);
+	if (dax_dev->holder_data != NULL)
+		dax_holder_notify_failure(dax_dev, 0, U64_MAX,
+				MF_MEM_PRE_REMOVE);
 
+	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;
+	/* clear holder data */
+	dax_dev->holder_ops = NULL;
+	dax_dev->holder_data = NULL;
 }
 EXPORT_SYMBOL_GPL(kill_dax);
 
+void run_dax(struct dax_device *dax_dev)
+{
+	set_bit(DAXDEV_ALIVE, &dax_dev->flags);
+}
+EXPORT_SYMBOL_GPL(run_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);
+	dax_dev = alloc_inode_sb(sb, dax_cache, GFP_KERNEL);
 	if (!dax_dev)
 		return NULL;
 
@@ -389,44 +368,42 @@ 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)
+static void dax_free_inode(struct inode *inode)
 {
-	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));
+		ida_free(&dax_minor_ida, iminor(inode));
 	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,
+	.free_inode = dax_free_inode,
+	.drop_inode = inode_just_drop,
 };
 
-static struct dentry *dax_mount(struct file_system_type *fs_type,
-		int flags, const char *dev_name, void *data)
+static int dax_init_fs_context(struct fs_context *fc)
 {
-	return mount_pseudo(fs_type, "dax:", &dax_sops, NULL, DAXFS_MAGIC);
+	struct pseudo_fs_context *ctx = init_pseudo(fc, DAXFS_MAGIC);
+	if (!ctx)
+		return -ENOMEM;
+	ctx->ops = &dax_sops;
+	return 0;
 }
 
 static struct file_system_type dax_fs_type = {
-	.name = "dax",
-	.mount = dax_mount,
-	.kill_sb = kill_anon_super,
+	.name		= "dax",
+	.init_fs_context = dax_init_fs_context,
+	.kill_sb	= kill_anon_super,
 };
 
 static int dax_test(struct inode *inode, void *data)
@@ -456,7 +433,7 @@ static struct dax_device *dax_dev_get(dev_t devt)
 		return NULL;
 
 	dax_dev = to_dax_dev(inode);
-	if (inode->i_state & I_NEW) {
+	if (inode_state_read_once(inode) & I_NEW) {
 		set_bit(DAXDEV_ALIVE, &dax_dev->flags);
 		inode->i_cdev = &dax_dev->cdev;
 		inode->i_mode = S_IFCHR;
@@ -468,56 +445,39 @@ static struct dax_device *dax_dev_get(dev_t devt)
 	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 *alloc_dax(void *private, 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;
+	/*
+	 * Unavailable on architectures with virtually aliased data caches,
+	 * except for device-dax (NULL operations pointer), which does
+	 * not use aliased mappings from the kernel.
+	 */
+	if (ops && cpu_dcache_is_aliasing())
+		return ERR_PTR(-EOPNOTSUPP);
+
+	if (WARN_ON_ONCE(ops && !ops->zero_page_range))
+		return ERR_PTR(-EINVAL);
 
-	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, GFP_KERNEL);
+	minor = ida_alloc_max(&dax_minor_ida, MINORMASK, GFP_KERNEL);
 	if (minor < 0)
-		goto err_minor;
+		return ERR_PTR(-ENOMEM);
 
 	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;
+	ida_free(&dax_minor_ida, minor);
+	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(alloc_dax);
 
@@ -530,36 +490,17 @@ void put_dax(struct dax_device *dax_dev)
 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
+ * dax_holder() - obtain the holder of a dax device
+ * @dax_dev: a dax_device instance
+ *
+ * Return: the holder's data which represents the holder if registered,
+ * otherwize NULL.
  */
-struct dax_device *dax_get_by_host(const char *host)
+void *dax_holder(struct dax_device *dax_dev)
 {
-	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;
+	return dax_dev->holder_data;
 }
-EXPORT_SYMBOL_GPL(dax_get_by_host);
+EXPORT_SYMBOL_GPL(dax_holder);
 
 /**
  * inode_dax: convert a public inode into its dax_dev
@@ -584,6 +525,8 @@ EXPORT_SYMBOL_GPL(dax_inode);
 
 void *dax_get_private(struct dax_device *dax_dev)
 {
+	if (!test_bit(DAXDEV_ALIVE, &dax_dev->flags))
+		return NULL;
 	return dax_dev->private;
 }
 EXPORT_SYMBOL_GPL(dax_get_private);
@@ -597,21 +540,16 @@ static void init_once(void *_dax_dev)
 	inode_init_once(inode);
 }
 
-static int __dax_fs_init(void)
+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),
+			SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | 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);
@@ -622,42 +560,52 @@ static int __dax_fs_init(void)
 	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)
+static void dax_fs_exit(void)
 {
 	kern_unmount(dax_mnt);
-	unregister_filesystem(&dax_fs_type);
+	rcu_barrier();
 	kmem_cache_destroy(dax_cache);
 }
 
-static int __init dax_fs_init(void)
+static int __init dax_core_init(void)
 {
 	int rc;
 
-	rc = __dax_fs_init();
+	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;
+		goto err_chrdev;
+
+	rc = dax_bus_init();
+	if (rc)
+		goto err_bus;
+	return 0;
+
+err_bus:
+	unregister_chrdev_region(dax_devt, MINORMASK+1);
+err_chrdev:
+	dax_fs_exit();
+	return 0;
 }
 
-static void __exit dax_fs_exit(void)
+static void __exit dax_core_exit(void)
 {
+	dax_bus_exit();
 	unregister_chrdev_region(dax_devt, MINORMASK+1);
 	ida_destroy(&dax_minor_ida);
-	__dax_fs_exit();
+	dax_fs_exit();
 }
 
 MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("DAX: direct access to differentiated memory");
 MODULE_LICENSE("GPL v2");
-subsys_initcall(dax_fs_init);
-module_exit(dax_fs_exit);
+subsys_initcall(dax_core_init);
+module_exit(dax_core_exit);