dax + libnvdimm for v5.17

- Simplify the dax_operations API
   - Eliminate bdev_dax_pgoff() in favor of the filesystem maintaining
     and applying a partition offset to all its DAX iomap operations.
   - Remove wrappers and device-mapper stacked callbacks for
     ->copy_from_iter() and ->copy_to_iter() in favor of moving
     block_device relative offset responsibility to the
     dax_direct_access() caller.
   - Remove the need for an @bdev in filesystem-DAX infrastructure
   - Remove unused uio helpers copy_from_iter_flushcache() and
     copy_mc_to_iter() as only the non-check_copy_size() versions are
     used for DAX.
 - Prepare XFS for the pending (next merge window) DAX+reflink support
 - Remove deprecated DEV_DAX_PMEM_COMPAT support
 - Cleanup a straggling misuse of the GUID api
 
 Tags offered after the branch was cut:
 Reviewed-by: Mike Snitzer <snitzer@redhat.com>
 Link: https://lore.kernel.org/r/Ydb/3P+8nvjCjYfO@redhat.com
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSbo+XnGs+rwLz9XGXfioYZHlFsZwUCYd3dTAAKCRDfioYZHlFs
 Z//UAP9zetoTE+O7zJG7CXja4jSopSadbdbh6QKSXaqfKBPvQQD+N4US3wA2bGv8
 f/qCY62j2Hj3hUTGHs9RvTyw3JsSYAA=
 =QvDs
 -----END PGP SIGNATURE-----

Merge tag 'libnvdimm-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm

Pull dax and libnvdimm updates from Dan Williams:
 "The bulk of this is a rework of the dax_operations API after
  discovering the obstacles it posed to the work-in-progress DAX+reflink
  support for XFS and other copy-on-write filesystem mechanics.

  Primarily the need to plumb a block_device through the API to handle
  partition offsets was a sticking point and Christoph untangled that
  dependency in addition to other cleanups to make landing the
  DAX+reflink support easier.

  The DAX_PMEM_COMPAT option has been around for 4 years and not only
  are distributions shipping userspace that understand the current
  configuration API, but some are not even bothering to turn this option
  on anymore, so it seems a good time to remove it per the deprecation
  schedule. Recall that this was added after the device-dax subsystem
  moved from /sys/class/dax to /sys/bus/dax for its sysfs organization.
  All recent functionality depends on /sys/bus/dax.

  Some other miscellaneous cleanups and reflink prep patches are
  included as well.

  Summary:

   - Simplify the dax_operations API:

      - Eliminate bdev_dax_pgoff() in favor of the filesystem
        maintaining and applying a partition offset to all its DAX iomap
        operations.

      - Remove wrappers and device-mapper stacked callbacks for
        ->copy_from_iter() and ->copy_to_iter() in favor of moving
        block_device relative offset responsibility to the
        dax_direct_access() caller.

      - Remove the need for an @bdev in filesystem-DAX infrastructure

      - Remove unused uio helpers copy_from_iter_flushcache() and
        copy_mc_to_iter() as only the non-check_copy_size() versions are
        used for DAX.

   - Prepare XFS for the pending (next merge window) DAX+reflink support

   - Remove deprecated DEV_DAX_PMEM_COMPAT support

   - Cleanup a straggling misuse of the GUID api"

* tag 'libnvdimm-for-5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (38 commits)
  iomap: Fix error handling in iomap_zero_iter()
  ACPI: NFIT: Import GUID before use
  dax: remove the copy_from_iter and copy_to_iter methods
  dax: remove the DAXDEV_F_SYNC flag
  dax: simplify dax_synchronous and set_dax_synchronous
  uio: remove copy_from_iter_flushcache() and copy_mc_to_iter()
  iomap: turn the byte variable in iomap_zero_iter into a ssize_t
  memremap: remove support for external pgmap refcounts
  fsdax: don't require CONFIG_BLOCK
  iomap: build the block based code conditionally
  dax: fix up some of the block device related ifdefs
  fsdax: shift partition offset handling into the file systems
  dax: return the partition offset from fs_dax_get_by_bdev
  iomap: add a IOMAP_DAX flag
  xfs: pass the mapping flags to xfs_bmbt_to_iomap
  xfs: use xfs_direct_write_iomap_ops for DAX zeroing
  xfs: move dax device handling into xfs_{alloc,free}_buftarg
  ext4: cleanup the dax handling in ext4_fill_super
  ext2: cleanup the dax handling in ext2_fill_super
  fsdax: decouple zeroing from the iomap buffered I/O code
  ...

Documentation/ABI/obsolete/sysfs-class-dax

@@ -1,22 +0,0 @@
-What:           /sys/class/dax/
-Date:           May, 2016
-KernelVersion:  v4.7
-Contact:        nvdimm@lists.linux.dev
-Description:	Device DAX is the device-centric analogue of Filesystem
-		DAX (CONFIG_FS_DAX).  It allows memory ranges to be
-		allocated and mapped without need of an intervening file
-		system.  Device DAX is strict, precise and predictable.
-		Specifically this interface:
-
-		1. Guarantees fault granularity with respect to a given
-		   page size (pte, pmd, or pud) set at configuration time.
-
-		2. Enforces deterministic behavior by being strict about
-		   what fault scenarios are supported.
-
-		The /sys/class/dax/ interface enumerates all the
-		device-dax instances in the system. The ABI is
-		deprecated and will be removed after 2020. It is
-		replaced with the DAX bus interface /sys/bus/dax/ where
-		device-dax instances can be found under
-		/sys/bus/dax/devices/

drivers/acpi/nfit/core.c

@@ -678,10 +678,12 @@ static const char *spa_type_name(u16 type)
 
 int nfit_spa_type(struct acpi_nfit_system_address *spa)
 {
+	guid_t guid;
 	int i;
 
+	import_guid(&guid, spa->range_guid);
 	for (i = 0; i < NFIT_UUID_MAX; i++)
-		if (guid_equal(to_nfit_uuid(i), (guid_t *)&spa->range_guid))
+		if (guid_equal(to_nfit_uuid(i), &guid))
 			return i;
 	return -1;
 }

drivers/dax/Kconfig

@@ -1,8 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config DAX_DRIVER
-	select DAX
-	bool
-
 menuconfig DAX
 	tristate "DAX: direct access to differentiated memory"
 	select SRCU
@@ -70,13 +66,4 @@ config DEV_DAX_KMEM
 
 	  Say N if unsure.
 
-config DEV_DAX_PMEM_COMPAT
-	tristate "PMEM DAX: support the deprecated /sys/class/dax interface"
-	depends on m && DEV_DAX_PMEM=m
-	default DEV_DAX_PMEM
-	help
-	  Older versions of the libdaxctl library expect to find all
-	  device-dax instances under /sys/class/dax. If libdaxctl in
-	  your distribution is older than v58 say M, otherwise say N.
-
 endif

drivers/dax/Makefile

@@ -2,10 +2,11 @@
 obj-$(CONFIG_DAX) += dax.o
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
+obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
 
 dax-y := super.o
 dax-y += bus.o
 device_dax-y := device.o
+dax_pmem-y := pmem.o
 
-obj-y += pmem/
 obj-y += hmem/

drivers/dax/bus.c

@@ -10,8 +10,6 @@
 #include "dax-private.h"
 #include "bus.h"
 
-static struct class *dax_class;
-
 static DEFINE_MUTEX(dax_bus_lock);
 
 #define DAX_NAME_LEN 30
@@ -1323,14 +1321,17 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 	}
 
 	/*
-	 * No 'host' or dax_operations since there is no access to this
+	 * No dax_operations since there is no access to this device outside of
-	 * device outside of mmap of the resulting character device.
+	 * mmap of the resulting character device.
 	 */
-	dax_dev = alloc_dax(dev_dax, NULL, NULL, DAXDEV_F_SYNC);
+	dax_dev = alloc_dax(dev_dax, NULL);
 	if (IS_ERR(dax_dev)) {
 		rc = PTR_ERR(dax_dev);
 		goto err_alloc_dax;
 	}
+	set_dax_synchronous(dax_dev);
+	set_dax_nocache(dax_dev);
+	set_dax_nomc(dax_dev);
 
 	/* a device_dax instance is dead while the driver is not attached */
 	kill_dax(dax_dev);
@@ -1343,10 +1344,7 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data)
 
 	inode = dax_inode(dax_dev);
 	dev->devt = inode->i_rdev;
-	if (data->subsys == DEV_DAX_BUS)
+	dev->bus = &dax_bus_type;
-		dev->bus = &dax_bus_type;
-	else
-		dev->class = dax_class;
 	dev->parent = parent;
 	dev->type = &dev_dax_type;
 
@@ -1445,22 +1443,10 @@ EXPORT_SYMBOL_GPL(dax_driver_unregister);
 
 int __init dax_bus_init(void)
 {
-	int rc;
+	return bus_register(&dax_bus_type);
-
-	if (IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT)) {
-		dax_class = class_create(THIS_MODULE, "dax");
-		if (IS_ERR(dax_class))
-			return PTR_ERR(dax_class);
-	}
-
-	rc = bus_register(&dax_bus_type);
-	if (rc)
-		class_destroy(dax_class);
-	return rc;
 }
 
 void __exit dax_bus_exit(void)
 {
 	bus_unregister(&dax_bus_type);
-	class_destroy(dax_class);
 }

drivers/dax/bus.h

@@ -16,24 +16,15 @@ struct dax_region *alloc_dax_region(struct device *parent, int region_id,
 		struct range *range, int target_node, unsigned int align,
 		unsigned long flags);
 
-enum dev_dax_subsys {
-	DEV_DAX_BUS = 0, /* zeroed dev_dax_data picks this by default */
-	DEV_DAX_CLASS,
-};
-
 struct dev_dax_data {
 	struct dax_region *dax_region;
 	struct dev_pagemap *pgmap;
-	enum dev_dax_subsys subsys;
 	resource_size_t size;
 	int id;
 };
 
 struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
 
-/* to be deleted when DEV_DAX_CLASS is removed */
-struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys);
-
 struct dax_device_driver {
 	struct device_driver drv;
 	struct list_head ids;
@@ -49,10 +40,6 @@ int __dax_driver_register(struct dax_device_driver *dax_drv,
 void dax_driver_unregister(struct dax_device_driver *dax_drv);
 void kill_dev_dax(struct dev_dax *dev_dax);
 
-#if IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT)
-int dev_dax_probe(struct dev_dax *dev_dax);
-#endif
-
 /*
  * While run_dax() is potentially a generic operation that could be
  * defined in include/linux/dax.h we don't want to grow any users

drivers/dax/device.c

@@ -433,11 +433,7 @@ int dev_dax_probe(struct dev_dax *dev_dax)
 	inode = dax_inode(dax_dev);
 	cdev = inode->i_cdev;
 	cdev_init(cdev, &dax_fops);
-	if (dev->class) {
+	cdev->owner = dev->driver->owner;
-		/* for the CONFIG_DEV_DAX_PMEM_COMPAT case */
-		cdev->owner = dev->parent->driver->owner;
-	} else
-		cdev->owner = dev->driver->owner;
 	cdev_set_parent(cdev, &dev->kobj);
 	rc = cdev_add(cdev, dev->devt, 1);
 	if (rc)

drivers/dax/pmem.c

@@ -3,11 +3,11 @@
 #include <linux/memremap.h>
 #include <linux/module.h>
 #include <linux/pfn_t.h>
-#include "../../nvdimm/pfn.h"
+#include "../nvdimm/pfn.h"
-#include "../../nvdimm/nd.h"
+#include "../nvdimm/nd.h"
-#include "../bus.h"
+#include "bus.h"
 
-struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
+static struct dev_dax *__dax_pmem_probe(struct device *dev)
 {
 	struct range range;
 	int rc, id, region_id;
@@ -63,7 +63,6 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 		.dax_region = dax_region,
 		.id = id,
 		.pgmap = &pgmap,
-		.subsys = subsys,
 		.size = range_len(&range),
 	};
 	dev_dax = devm_create_dev_dax(&data);
@@ -73,7 +72,32 @@ struct dev_dax *__dax_pmem_probe(struct device *dev, enum dev_dax_subsys subsys)
 
 	return dev_dax;
 }
-EXPORT_SYMBOL_GPL(__dax_pmem_probe);
+
+static int dax_pmem_probe(struct device *dev)
+{
+	return PTR_ERR_OR_ZERO(__dax_pmem_probe(dev));
+}
+
+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/dax/pmem/Makefile

@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
 obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o
-obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o
 
 dax_pmem-y := pmem.o
 dax_pmem_core-y := core.o

drivers/dax/pmem/compat.c

@@ -1,72 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
-#include <linux/percpu-refcount.h>
-#include <linux/memremap.h>
-#include <linux/module.h>
-#include <linux/pfn_t.h>
-#include <linux/nd.h>
-#include "../bus.h"
-
-/* we need the private definitions to implement compat suport */
-#include "../dax-private.h"
-
-static int dax_pmem_compat_probe(struct device *dev)
-{
-	struct dev_dax *dev_dax = __dax_pmem_probe(dev, DEV_DAX_CLASS);
-	int rc;
-
-	if (IS_ERR(dev_dax))
-		return PTR_ERR(dev_dax);
-
-        if (!devres_open_group(&dev_dax->dev, dev_dax, GFP_KERNEL))
-		return -ENOMEM;
-
-	device_lock(&dev_dax->dev);
-	rc = dev_dax_probe(dev_dax);
-	device_unlock(&dev_dax->dev);
-
-	devres_close_group(&dev_dax->dev, dev_dax);
-	if (rc)
-		devres_release_group(&dev_dax->dev, dev_dax);
-
-	return rc;
-}
-
-static int dax_pmem_compat_release(struct device *dev, void *data)
-{
-	device_lock(dev);
-	devres_release_group(dev, to_dev_dax(dev));
-	device_unlock(dev);
-
-	return 0;
-}
-
-static void dax_pmem_compat_remove(struct device *dev)
-{
-	device_for_each_child(dev, NULL, dax_pmem_compat_release);
-}
-
-static struct nd_device_driver dax_pmem_compat_driver = {
-	.probe = dax_pmem_compat_probe,
-	.remove = dax_pmem_compat_remove,
-	.drv = {
-		.name = "dax_pmem_compat",
-	},
-	.type = ND_DRIVER_DAX_PMEM,
-};
-
-static int __init dax_pmem_compat_init(void)
-{
-	return nd_driver_register(&dax_pmem_compat_driver);
-}
-module_init(dax_pmem_compat_init);
-
-static void __exit dax_pmem_compat_exit(void)
-{
-	driver_unregister(&dax_pmem_compat_driver.drv);
-}
-module_exit(dax_pmem_compat_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Intel Corporation");
-MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);

drivers/dax/pmem/pmem.c

@@ -7,34 +7,4 @@
 #include <linux/nd.h>
 #include "../bus.h"
 
-static int dax_pmem_probe(struct device *dev)
-{
-	return PTR_ERR_OR_ZERO(__dax_pmem_probe(dev, DEV_DAX_BUS));
-}
 
-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");
-#if !IS_ENABLED(CONFIG_DEV_DAX_PMEM_COMPAT)
-/* For compat builds, don't load this module by default */
-MODULE_ALIAS_ND_DEVICE(ND_DEVICE_DAX_PMEM);
-#endif

drivers/dax/super.c

@@ -7,10 +7,8 @@
 #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>
@@ -21,15 +19,12 @@
  * 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;
@@ -42,10 +37,6 @@ 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);
@@ -58,169 +49,54 @@ void dax_read_unlock(int id)
 }
 EXPORT_SYMBOL_GPL(dax_read_unlock);
 
-static int dax_host_hash(const char *host)
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
-{
-	return hashlen_hash(hashlen_string("DAX", host)) % DAX_HASH_SIZE;
-}
-
-#ifdef CONFIG_BLOCK
 #include <linux/blkdev.h>
 
-int bdev_dax_pgoff(struct block_device *bdev, sector_t sector, size_t size,
+static DEFINE_XARRAY(dax_hosts);
-		pgoff_t *pgoff)
+
+int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 {
-	sector_t start_sect = bdev ? get_start_sect(bdev) : 0;
+	return xa_insert(&dax_hosts, (unsigned long)disk, dax_dev, GFP_KERNEL);
-	phys_addr_t phys_off = (start_sect + 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);
+EXPORT_SYMBOL_GPL(dax_add_host);
+
+void dax_remove_host(struct gendisk *disk)
+{
+	xa_erase(&dax_hosts, (unsigned long)disk);
+}
+EXPORT_SYMBOL_GPL(dax_remove_host);
 
-#if IS_ENABLED(CONFIG_FS_DAX)
 /**
- * dax_get_by_host() - temporary lookup mechanism for filesystem-dax
+ * fs_dax_get_by_bdev() - temporary lookup mechanism for filesystem-dax
- * @host: alternate name for the device registered by a dax driver
+ * @bdev: block device to find a dax_device for
+ * @start_off: returns the byte offset into the dax_device that @bdev starts
  */
-static struct dax_device *dax_get_by_host(const char *host)
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off)
 {
-	struct dax_device *dax_dev, *found = NULL;
+	struct dax_device *dax_dev;
-	int hash, id;
+	u64 part_size;
-
-	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;
-}
-
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
-{
-	if (!blk_queue_dax(bdev->bd_disk->queue))
-		return NULL;
-	return dax_get_by_host(bdev->bd_disk->disk_name);
-}
-EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
-
-bool generic_fsdax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t sectors)
-{
-	bool dax_enabled = false;
-	pgoff_t pgoff, pgoff_end;
-	void *kaddr, *end_kaddr;
-	pfn_t pfn, end_pfn;
-	sector_t last_page;
-	long len, len2;
-	int err, id;
-
-	if (blocksize != PAGE_SIZE) {
-		pr_info("%pg: error: unsupported blocksize for dax\n", bdev);
-		return false;
-	}
-
-	if (!dax_dev) {
-		pr_debug("%pg: error: dax unsupported by block device\n", bdev);
-		return false;
-	}
-
-	err = bdev_dax_pgoff(bdev, start, PAGE_SIZE, &pgoff);
-	if (err) {
-		pr_info("%pg: error: unaligned partition for dax\n", bdev);
-		return false;
-	}
-
-	last_page = PFN_DOWN((start + sectors - 1) * 512) * PAGE_SIZE / 512;
-	err = bdev_dax_pgoff(bdev, last_page, PAGE_SIZE, &pgoff_end);
-	if (err) {
-		pr_info("%pg: error: unaligned partition for dax\n", bdev);
-		return false;
-	}
-
-	id = dax_read_lock();
-	len = dax_direct_access(dax_dev, pgoff, 1, &kaddr, &pfn);
-	len2 = dax_direct_access(dax_dev, pgoff_end, 1, &end_kaddr, &end_pfn);
-
-	if (len < 1 || len2 < 1) {
-		pr_info("%pg: error: dax access failed (%ld)\n",
-				bdev, len < 1 ? len : len2);
-		dax_read_unlock(id);
-		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) && pfn_t_devmap(end_pfn)) {
-		struct dev_pagemap *pgmap, *end_pgmap;
-
-		pgmap = get_dev_pagemap(pfn_t_to_pfn(pfn), NULL);
-		end_pgmap = get_dev_pagemap(pfn_t_to_pfn(end_pfn), NULL);
-		if (pgmap && pgmap == end_pgmap && pgmap->type == MEMORY_DEVICE_FS_DAX
-				&& pfn_t_to_page(pfn)->pgmap == pgmap
-				&& pfn_t_to_page(end_pfn)->pgmap == pgmap
-				&& pfn_t_to_pfn(pfn) == PHYS_PFN(__pa(kaddr))
-				&& pfn_t_to_pfn(end_pfn) == PHYS_PFN(__pa(end_kaddr)))
-			dax_enabled = true;
-		put_dev_pagemap(pgmap);
-		put_dev_pagemap(end_pgmap);
-
-	}
-	dax_read_unlock(id);
-
-	if (!dax_enabled) {
-		pr_info("%pg: error: dax support not enabled\n", bdev);
-		return false;
-	}
-	return true;
-}
-EXPORT_SYMBOL_GPL(generic_fsdax_supported);
-
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len)
-{
-	bool ret = false;
 	int id;
 
-	if (!dax_dev)
+	if (!blk_queue_dax(bdev->bd_disk->queue))
-		return false;
+		return NULL;
+
+	*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();
-	if (dax_alive(dax_dev) && dax_dev->ops->dax_supported)
+	dax_dev = xa_load(&dax_hosts, (unsigned long)bdev->bd_disk);
-		ret = dax_dev->ops->dax_supported(dax_dev, bdev, blocksize,
+	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode))
-						  start, len);
+		dax_dev = NULL;
 	dax_read_unlock(id);
-	return ret;
+
+	return dax_dev;
 }
-EXPORT_SYMBOL_GPL(dax_supported);
+EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
-#endif /* CONFIG_FS_DAX */
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
-#endif /* CONFIG_BLOCK */
 
 enum dax_device_flags {
 	/* !alive + rcu grace period == no new operations / mappings */
@@ -229,6 +105,10 @@ enum dax_device_flags {
 	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,
 };
 
 /**
@@ -270,9 +150,15 @@ 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)
@@ -280,9 +166,15 @@ 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)
@@ -332,17 +224,29 @@ 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)
+bool dax_synchronous(struct dax_device *dax_dev)
 {
 	return test_bit(DAXDEV_SYNC, &dax_dev->flags);
 }
-EXPORT_SYMBOL_GPL(__dax_synchronous);
+EXPORT_SYMBOL_GPL(dax_synchronous);
 
-void __set_dax_synchronous(struct dax_device *dax_dev)
+void set_dax_synchronous(struct dax_device *dax_dev)
 {
 	set_bit(DAXDEV_SYNC, &dax_dev->flags);
 }
-EXPORT_SYMBOL_GPL(__set_dax_synchronous);
+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)
 {
@@ -363,12 +267,7 @@ void kill_dax(struct dax_device *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);
 }
 EXPORT_SYMBOL_GPL(kill_dax);
 
@@ -400,8 +299,6 @@ static struct dax_device *to_dax_dev(struct inode *inode)
 static void dax_free_inode(struct inode *inode)
 {
 	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, iminor(inode));
 	kmem_cache_free(dax_cache, dax_dev);
@@ -476,65 +373,30 @@ 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)
+struct dax_device *alloc_dax(void *private, const struct dax_operations *ops)
-{
-	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, unsigned long flags)
 {
 	struct dax_device *dax_dev;
-	const char *host;
 	dev_t devt;
 	int minor;
 
-	if (ops && !ops->zero_page_range) {
+	if (WARN_ON_ONCE(ops && !ops->zero_page_range))
-		pr_debug("%s: error: device does not provide dax"
-			 " operation zero_page_range()\n",
-			 __host ? __host : "Unknown");
 		return ERR_PTR(-EINVAL);
-	}
-
-	host = kstrdup(__host, GFP_KERNEL);
-	if (__host && !host)
-		return ERR_PTR(-ENOMEM);
 
 	minor = ida_simple_get(&dax_minor_ida, 0, MINORMASK+1, 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;
-	if (flags & DAXDEV_F_SYNC)
-		set_dax_synchronous(dax_dev);
-
 	return dax_dev;
 
  err_dev:
 	ida_simple_remove(&dax_minor_ida, minor);
- err_minor:
-	kfree(host);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL_GPL(alloc_dax);

drivers/md/dm-linear.c

@@ -162,71 +162,34 @@ static int linear_iterate_devices(struct dm_target *ti,
 	return fn(ti, lc->dev, lc->start, ti->len, data);
 }
 
-#if IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_FS_DAX)
+static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
+{
+	struct linear_c *lc = ti->private;
+	sector_t sector = linear_map_sector(ti, *pgoff << PAGE_SECTORS_SHIFT);
+
+	*pgoff = (get_start_sect(lc->dev->bdev) + sector) >> PAGE_SECTORS_SHIFT;
+	return lc->dev->dax_dev;
+}
+
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn)
 {
-	long ret;
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
 
-	dev_sector = linear_map_sector(ti, sector);
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
-	if (ret)
-		return ret;
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
-static size_t linear_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-
-	dev_sector = linear_map_sector(ti, sector);
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
-}
-
-static size_t linear_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-
-	dev_sector = linear_map_sector(ti, sector);
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
-}
-
 static int linear_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 				      size_t nr_pages)
 {
-	int ret;
+	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
-	struct linear_c *lc = ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct dax_device *dax_dev = lc->dev->dax_dev;
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
 
-	dev_sector = linear_map_sector(ti, sector);
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
-	if (ret)
-		return ret;
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
 #else
 #define linear_dax_direct_access NULL
-#define linear_dax_copy_from_iter NULL
-#define linear_dax_copy_to_iter NULL
 #define linear_dax_zero_page_range NULL
 #endif
 
@@ -244,8 +207,6 @@ static struct target_type linear_target = {
 	.prepare_ioctl = linear_prepare_ioctl,
 	.iterate_devices = linear_iterate_devices,
 	.direct_access = linear_dax_direct_access,
-	.dax_copy_from_iter = linear_dax_copy_from_iter,
-	.dax_copy_to_iter = linear_dax_copy_to_iter,
 	.dax_zero_page_range = linear_dax_zero_page_range,
 };
 

drivers/md/dm-log-writes.c

@@ -901,120 +901,34 @@ static void log_writes_io_hints(struct dm_target *ti, struct queue_limits *limit
 	limits->io_min = limits->physical_block_size;
 }
 
-#if IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_FS_DAX)
-static int log_dax(struct log_writes_c *lc, sector_t sector, size_t bytes,
+static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
-		   struct iov_iter *i)
+		pgoff_t *pgoff)
 {
-	struct pending_block *block;
+	struct log_writes_c *lc = ti->private;
 
-	if (!bytes)
+	*pgoff += (get_start_sect(lc->dev->bdev) >> PAGE_SECTORS_SHIFT);
-		return 0;
+	return lc->dev->dax_dev;
-
-	block = kzalloc(sizeof(struct pending_block), GFP_KERNEL);
-	if (!block) {
-		DMERR("Error allocating dax pending block");
-		return -ENOMEM;
-	}
-
-	block->data = kzalloc(bytes, GFP_KERNEL);
-	if (!block->data) {
-		DMERR("Error allocating dax data space");
-		kfree(block);
-		return -ENOMEM;
-	}
-
-	/* write data provided via the iterator */
-	if (!copy_from_iter(block->data, bytes, i)) {
-		DMERR("Error copying dax data");
-		kfree(block->data);
-		kfree(block);
-		return -EIO;
-	}
-
-	/* rewind the iterator so that the block driver can use it */
-	iov_iter_revert(i, bytes);
-
-	block->datalen = bytes;
-	block->sector = bio_to_dev_sectors(lc, sector);
-	block->nr_sectors = ALIGN(bytes, lc->sectorsize) >> lc->sectorshift;
-
-	atomic_inc(&lc->pending_blocks);
-	spin_lock_irq(&lc->blocks_lock);
-	list_add_tail(&block->list, &lc->unflushed_blocks);
-	spin_unlock_irq(&lc->blocks_lock);
-	wake_up_process(lc->log_kthread);
-
-	return 0;
 }
 
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 					 long nr_pages, void **kaddr, pfn_t *pfn)
 {
-	struct log_writes_c *lc = ti->private;
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
-	sector_t sector = pgoff * PAGE_SECTORS;
-	int ret;
 
-	ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages * PAGE_SIZE, &pgoff);
+	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
-	if (ret)
-		return ret;
-	return dax_direct_access(lc->dev->dax_dev, pgoff, nr_pages, kaddr, pfn);
-}
-
-static size_t log_writes_dax_copy_from_iter(struct dm_target *ti,
-					    pgoff_t pgoff, void *addr, size_t bytes,
-					    struct iov_iter *i)
-{
-	struct log_writes_c *lc = ti->private;
-	sector_t sector = pgoff * PAGE_SECTORS;
-	int err;
-
-	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-
-	/* Don't bother doing anything if logging has been disabled */
-	if (!lc->logging_enabled)
-		goto dax_copy;
-
-	err = log_dax(lc, sector, bytes, i);
-	if (err) {
-		DMWARN("Error %d logging DAX write", err);
-		return 0;
-	}
-dax_copy:
-	return dax_copy_from_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
-}
-
-static size_t log_writes_dax_copy_to_iter(struct dm_target *ti,
-					  pgoff_t pgoff, void *addr, size_t bytes,
-					  struct iov_iter *i)
-{
-	struct log_writes_c *lc = ti->private;
-	sector_t sector = pgoff * PAGE_SECTORS;
-
-	if (bdev_dax_pgoff(lc->dev->bdev, sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-	return dax_copy_to_iter(lc->dev->dax_dev, pgoff, addr, bytes, i);
 }
 
 static int log_writes_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 					  size_t nr_pages)
 {
-	int ret;
+	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
-	struct log_writes_c *lc = ti->private;
-	sector_t sector = pgoff * PAGE_SECTORS;
 
-	ret = bdev_dax_pgoff(lc->dev->bdev, sector, nr_pages << PAGE_SHIFT,
+	return dax_zero_page_range(dax_dev, pgoff, nr_pages << PAGE_SHIFT);
-			     &pgoff);
-	if (ret)
-		return ret;
-	return dax_zero_page_range(lc->dev->dax_dev, pgoff,
-				   nr_pages << PAGE_SHIFT);
 }
 
 #else
 #define log_writes_dax_direct_access NULL
-#define log_writes_dax_copy_from_iter NULL
-#define log_writes_dax_copy_to_iter NULL
 #define log_writes_dax_zero_page_range NULL
 #endif
 
@@ -1032,8 +946,6 @@ static struct target_type log_writes_target = {
 	.iterate_devices = log_writes_iterate_devices,
 	.io_hints = log_writes_io_hints,
 	.direct_access = log_writes_dax_direct_access,
-	.dax_copy_from_iter = log_writes_dax_copy_from_iter,
-	.dax_copy_to_iter = log_writes_dax_copy_to_iter,
 	.dax_zero_page_range = log_writes_dax_zero_page_range,
 };
 

drivers/md/dm-stripe.c

@@ -300,91 +300,40 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
 	return DM_MAPIO_REMAPPED;
 }
 
-#if IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_FS_DAX)
+static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
+{
+	struct stripe_c *sc = ti->private;
+	struct block_device *bdev;
+	sector_t dev_sector;
+	uint32_t stripe;
+
+	stripe_map_sector(sc, *pgoff * PAGE_SECTORS, &stripe, &dev_sector);
+	dev_sector += sc->stripe[stripe].physical_start;
+	bdev = sc->stripe[stripe].dev->bdev;
+
+	*pgoff = (get_start_sect(bdev) + dev_sector) >> PAGE_SECTORS_SHIFT;
+	return sc->stripe[stripe].dev->dax_dev;
+}
+
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn)
 {
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
-	long ret;
 
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
-
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages * PAGE_SIZE, &pgoff);
-	if (ret)
-		return ret;
 	return dax_direct_access(dax_dev, pgoff, nr_pages, kaddr, pfn);
 }
 
-static size_t stripe_dax_copy_from_iter(struct dm_target *ti, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
-
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
-
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-	return dax_copy_from_iter(dax_dev, pgoff, addr, bytes, i);
-}
-
-static size_t stripe_dax_copy_to_iter(struct dm_target *ti, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
-
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
-
-	if (bdev_dax_pgoff(bdev, dev_sector, ALIGN(bytes, PAGE_SIZE), &pgoff))
-		return 0;
-	return dax_copy_to_iter(dax_dev, pgoff, addr, bytes, i);
-}
-
 static int stripe_dax_zero_page_range(struct dm_target *ti, pgoff_t pgoff,
 				      size_t nr_pages)
 {
-	int ret;
+	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
-	sector_t dev_sector, sector = pgoff * PAGE_SECTORS;
-	struct stripe_c *sc = ti->private;
-	struct dax_device *dax_dev;
-	struct block_device *bdev;
-	uint32_t stripe;
 
-	stripe_map_sector(sc, sector, &stripe, &dev_sector);
-	dev_sector += sc->stripe[stripe].physical_start;
-	dax_dev = sc->stripe[stripe].dev->dax_dev;
-	bdev = sc->stripe[stripe].dev->bdev;
-
-	ret = bdev_dax_pgoff(bdev, dev_sector, nr_pages << PAGE_SHIFT, &pgoff);
-	if (ret)
-		return ret;
 	return dax_zero_page_range(dax_dev, pgoff, nr_pages);
 }
 
 #else
 #define stripe_dax_direct_access NULL
-#define stripe_dax_copy_from_iter NULL
-#define stripe_dax_copy_to_iter NULL
 #define stripe_dax_zero_page_range NULL
 #endif
 
@@ -521,8 +470,6 @@ static struct target_type stripe_target = {
 	.iterate_devices = stripe_iterate_devices,
 	.io_hints = stripe_io_hints,
 	.direct_access = stripe_dax_direct_access,
-	.dax_copy_from_iter = stripe_dax_copy_from_iter,
-	.dax_copy_to_iter = stripe_dax_copy_to_iter,
 	.dax_zero_page_range = stripe_dax_zero_page_range,
 };
 

drivers/md/dm-table.c

@@ -806,12 +806,14 @@ void dm_table_set_type(struct dm_table *t, enum dm_queue_mode type)
 EXPORT_SYMBOL_GPL(dm_table_set_type);
 
 /* validate the dax capability of the target device span */
-int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
+static int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
 			sector_t start, sector_t len, void *data)
 {
-	int blocksize = *(int *) data;
+	if (dev->dax_dev)
+		return false;
 
-	return !dax_supported(dev->dax_dev, dev->bdev, blocksize, start, len);
+	DMDEBUG("%pg: error: dax unsupported by block device", dev->bdev);
+	return true;
 }
 
 /* Check devices support synchronous DAX */
@@ -821,8 +823,8 @@ static int device_not_dax_synchronous_capable(struct dm_target *ti, struct dm_de
 	return !dev->dax_dev || !dax_synchronous(dev->dax_dev);
 }
 
-bool dm_table_supports_dax(struct dm_table *t,
+static bool dm_table_supports_dax(struct dm_table *t,
-			   iterate_devices_callout_fn iterate_fn, int *blocksize)
+			   iterate_devices_callout_fn iterate_fn)
 {
 	struct dm_target *ti;
 	unsigned i;
@@ -835,7 +837,7 @@ bool dm_table_supports_dax(struct dm_table *t,
 			return false;
 
 		if (!ti->type->iterate_devices ||
-		    ti->type->iterate_devices(ti, iterate_fn, blocksize))
+		    ti->type->iterate_devices(ti, iterate_fn, NULL))
 			return false;
 	}
 
@@ -862,7 +864,6 @@ static int dm_table_determine_type(struct dm_table *t)
 	struct dm_target *tgt;
 	struct list_head *devices = dm_table_get_devices(t);
 	enum dm_queue_mode live_md_type = dm_get_md_type(t->md);
-	int page_size = PAGE_SIZE;
 
 	if (t->type != DM_TYPE_NONE) {
 		/* target already set the table's type */
@@ -906,7 +907,7 @@ static int dm_table_determine_type(struct dm_table *t)
 verify_bio_based:
 		/* We must use this table as bio-based */
 		t->type = DM_TYPE_BIO_BASED;
-		if (dm_table_supports_dax(t, device_not_dax_capable, &page_size) ||
+		if (dm_table_supports_dax(t, device_not_dax_capable) ||
 		    (list_empty(devices) && live_md_type == DM_TYPE_DAX_BIO_BASED)) {
 			t->type = DM_TYPE_DAX_BIO_BASED;
 		}
@@ -1976,7 +1977,6 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 			      struct queue_limits *limits)
 {
 	bool wc = false, fua = false;
-	int page_size = PAGE_SIZE;
 	int r;
 
 	/*
@@ -2010,9 +2010,9 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	}
 	blk_queue_write_cache(q, wc, fua);
 
-	if (dm_table_supports_dax(t, device_not_dax_capable, &page_size)) {
+	if (dm_table_supports_dax(t, device_not_dax_capable)) {
 		blk_queue_flag_set(QUEUE_FLAG_DAX, q);
-		if (dm_table_supports_dax(t, device_not_dax_synchronous_capable, NULL))
+		if (dm_table_supports_dax(t, device_not_dax_synchronous_capable))
 			set_dax_synchronous(t->md->dax_dev);
 	}
 	else

drivers/md/dm-writecache.c

@@ -38,7 +38,7 @@
 #define BITMAP_GRANULARITY	PAGE_SIZE
 #endif
 
-#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_DAX_DRIVER)
+#if IS_ENABLED(CONFIG_ARCH_HAS_PMEM_API) && IS_ENABLED(CONFIG_FS_DAX)
 #define DM_WRITECACHE_HAS_PMEM
 #endif
 

drivers/md/dm.c

@@ -637,7 +637,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
 			     struct mapped_device *md)
 {
 	struct block_device *bdev;
-
+	u64 part_off;
 	int r;
 
 	BUG_ON(td->dm_dev.bdev);
@@ -653,7 +653,7 @@ static int open_table_device(struct table_device *td, dev_t dev,
 	}
 
 	td->dm_dev.bdev = bdev;
-	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev);
+	td->dm_dev.dax_dev = fs_dax_get_by_bdev(bdev, &part_off);
 	return 0;
 }
 
@@ -1027,74 +1027,6 @@ static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	return ret;
 }
 
-static bool dm_dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len)
-{
-	struct mapped_device *md = dax_get_private(dax_dev);
-	struct dm_table *map;
-	bool ret = false;
-	int srcu_idx;
-
-	map = dm_get_live_table(md, &srcu_idx);
-	if (!map)
-		goto out;
-
-	ret = dm_table_supports_dax(map, device_not_dax_capable, &blocksize);
-
-out:
-	dm_put_live_table(md, srcu_idx);
-
-	return ret;
-}
-
-static size_t dm_dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-				    void *addr, size_t bytes, struct iov_iter *i)
-{
-	struct mapped_device *md = dax_get_private(dax_dev);
-	sector_t sector = pgoff * PAGE_SECTORS;
-	struct dm_target *ti;
-	long ret = 0;
-	int srcu_idx;
-
-	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
-
-	if (!ti)
-		goto out;
-	if (!ti->type->dax_copy_from_iter) {
-		ret = copy_from_iter(addr, bytes, i);
-		goto out;
-	}
-	ret = ti->type->dax_copy_from_iter(ti, pgoff, addr, bytes, i);
- out:
-	dm_put_live_table(md, srcu_idx);
-
-	return ret;
-}
-
-static size_t dm_dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	struct mapped_device *md = dax_get_private(dax_dev);
-	sector_t sector = pgoff * PAGE_SECTORS;
-	struct dm_target *ti;
-	long ret = 0;
-	int srcu_idx;
-
-	ti = dm_dax_get_live_target(md, sector, &srcu_idx);
-
-	if (!ti)
-		goto out;
-	if (!ti->type->dax_copy_to_iter) {
-		ret = copy_to_iter(addr, bytes, i);
-		goto out;
-	}
-	ret = ti->type->dax_copy_to_iter(ti, pgoff, addr, bytes, i);
- out:
-	dm_put_live_table(md, srcu_idx);
-
-	return ret;
-}
-
 static int dm_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 				  size_t nr_pages)
 {
@@ -1683,6 +1615,7 @@ static void cleanup_mapped_device(struct mapped_device *md)
 	bioset_exit(&md->io_bs);
 
 	if (md->dax_dev) {
+		dax_remove_host(md->disk);
 		kill_dax(md->dax_dev);
 		put_dax(md->dax_dev);
 		md->dax_dev = NULL;
@@ -1784,10 +1717,15 @@ static struct mapped_device *alloc_dev(int minor)
 	md->disk->private_data = md;
 	sprintf(md->disk->disk_name, "dm-%d", minor);
 
-	if (IS_ENABLED(CONFIG_DAX_DRIVER)) {
+	if (IS_ENABLED(CONFIG_FS_DAX)) {
-		md->dax_dev = alloc_dax(md, md->disk->disk_name,
+		md->dax_dev = alloc_dax(md, &dm_dax_ops);
-					&dm_dax_ops, 0);
+		if (IS_ERR(md->dax_dev)) {
-		if (IS_ERR(md->dax_dev))
+			md->dax_dev = NULL;
+			goto bad;
+		}
+		set_dax_nocache(md->dax_dev);
+		set_dax_nomc(md->dax_dev);
+		if (dax_add_host(md->dax_dev, md->disk))
 			goto bad;
 	}
 
@@ -3041,9 +2979,6 @@ static const struct block_device_operations dm_rq_blk_dops = {
 
 static const struct dax_operations dm_dax_ops = {
 	.direct_access = dm_dax_direct_access,
-	.dax_supported = dm_dax_supported,
-	.copy_from_iter = dm_dax_copy_from_iter,
-	.copy_to_iter = dm_dax_copy_to_iter,
 	.zero_page_range = dm_dax_zero_page_range,
 };
 

drivers/md/dm.h

@@ -73,10 +73,6 @@ bool dm_table_bio_based(struct dm_table *t);
 bool dm_table_request_based(struct dm_table *t);
 void dm_table_free_md_mempools(struct dm_table *t);
 struct dm_md_mempools *dm_table_get_md_mempools(struct dm_table *t);
-bool dm_table_supports_dax(struct dm_table *t, iterate_devices_callout_fn fn,
-			   int *blocksize);
-int device_not_dax_capable(struct dm_target *ti, struct dm_dev *dev,
-			   sector_t start, sector_t len, void *data);
 
 void dm_lock_md_type(struct mapped_device *md);
 void dm_unlock_md_type(struct mapped_device *md);

drivers/nvdimm/Kconfig

@@ -22,7 +22,7 @@ if LIBNVDIMM
 config BLK_DEV_PMEM
 	tristate "PMEM: Persistent memory block device support"
 	default LIBNVDIMM
-	select DAX_DRIVER
+	select DAX
 	select ND_BTT if BTT
 	select ND_PFN if NVDIMM_PFN
 	help

drivers/nvdimm/pmem.c

@@ -301,29 +301,8 @@ static long pmem_dax_direct_access(struct dax_device *dax_dev,
 	return __pmem_direct_access(pmem, pgoff, nr_pages, kaddr, pfn);
 }
 
-/*
- * Use the 'no check' versions of copy_from_iter_flushcache() and
- * copy_mc_to_iter() to bypass HARDENED_USERCOPY overhead. Bounds
- * checking, both file offset and device offset, is handled by
- * dax_iomap_actor()
- */
-static size_t pmem_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	return _copy_from_iter_flushcache(addr, bytes, i);
-}
-
-static size_t pmem_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i)
-{
-	return _copy_mc_to_iter(addr, bytes, i);
-}
-
 static const struct dax_operations pmem_dax_ops = {
 	.direct_access = pmem_dax_direct_access,
-	.dax_supported = generic_fsdax_supported,
-	.copy_from_iter = pmem_copy_from_iter,
-	.copy_to_iter = pmem_copy_to_iter,
 	.zero_page_range = pmem_dax_zero_page_range,
 };
 
@@ -379,6 +358,7 @@ static void pmem_release_disk(void *__pmem)
 {
 	struct pmem_device *pmem = __pmem;
 
+	dax_remove_host(pmem->disk);
 	kill_dax(pmem->dax_dev);
 	put_dax(pmem->dax_dev);
 	del_gendisk(pmem->disk);
@@ -402,7 +382,6 @@ static int pmem_attach_disk(struct device *dev,
 	struct gendisk *disk;
 	void *addr;
 	int rc;
-	unsigned long flags = 0UL;
 
 	pmem = devm_kzalloc(dev, sizeof(*pmem), GFP_KERNEL);
 	if (!pmem)
@@ -495,19 +474,24 @@ static int pmem_attach_disk(struct device *dev,
 	nvdimm_badblocks_populate(nd_region, &pmem->bb, &bb_range);
 	disk->bb = &pmem->bb;
 
-	if (is_nvdimm_sync(nd_region))
+	dax_dev = alloc_dax(pmem, &pmem_dax_ops);
-		flags = DAXDEV_F_SYNC;
-	dax_dev = alloc_dax(pmem, disk->disk_name, &pmem_dax_ops, flags);
 	if (IS_ERR(dax_dev)) {
 		rc = PTR_ERR(dax_dev);
 		goto out;
 	}
+	set_dax_nocache(dax_dev);
+	set_dax_nomc(dax_dev);
+	if (is_nvdimm_sync(nd_region))
+		set_dax_synchronous(dax_dev);
+	rc = dax_add_host(dax_dev, disk);
+	if (rc)
+		goto out_cleanup_dax;
 	dax_write_cache(dax_dev, nvdimm_has_cache(nd_region));
 	pmem->dax_dev = dax_dev;
 
 	rc = device_add_disk(dev, disk, pmem_attribute_groups);
 	if (rc)
-		goto out_cleanup_dax;
+		goto out_remove_host;
 	if (devm_add_action_or_reset(dev, pmem_release_disk, pmem))
 		return -ENOMEM;
 
@@ -519,6 +503,8 @@ static int pmem_attach_disk(struct device *dev,
 		dev_warn(dev, "'badblocks' notification disabled\n");
 	return 0;
 
+out_remove_host:
+	dax_remove_host(pmem->disk);
 out_cleanup_dax:
 	kill_dax(pmem->dax_dev);
 	put_dax(pmem->dax_dev);

drivers/pci/p2pdma.c

@@ -219,7 +219,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 	error = gen_pool_add_owner(p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,
 			range_len(&pgmap->range), dev_to_node(&pdev->dev),
-			pgmap->ref);
+			&pgmap->ref);
 	if (error)
 		goto pages_free;
 

drivers/s390/block/Kconfig

@@ -5,7 +5,7 @@ comment "S/390 block device drivers"
 config DCSSBLK
 	def_tristate m
 	select FS_DAX_LIMITED
-	select DAX_DRIVER
+	select DAX
 	prompt "DCSSBLK support"
 	depends on S390 && BLOCK
 	help

drivers/s390/block/dcssblk.c

@@ -44,18 +44,6 @@ static const struct block_device_operations dcssblk_devops = {
 	.release 	= dcssblk_release,
 };
 
-static size_t dcssblk_dax_copy_from_iter(struct dax_device *dax_dev,
-		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter(addr, bytes, i);
-}
-
-static size_t dcssblk_dax_copy_to_iter(struct dax_device *dax_dev,
-		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
-{
-	return copy_to_iter(addr, bytes, i);
-}
-
 static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 				       pgoff_t pgoff, size_t nr_pages)
 {
@@ -72,9 +60,6 @@ static int dcssblk_dax_zero_page_range(struct dax_device *dax_dev,
 
 static const struct dax_operations dcssblk_dax_ops = {
 	.direct_access = dcssblk_dax_direct_access,
-	.dax_supported = generic_fsdax_supported,
-	.copy_from_iter = dcssblk_dax_copy_from_iter,
-	.copy_to_iter = dcssblk_dax_copy_to_iter,
 	.zero_page_range = dcssblk_dax_zero_page_range,
 };
 
@@ -687,18 +672,21 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	if (rc)
 		goto put_dev;
 
-	dev_info->dax_dev = alloc_dax(dev_info, dev_info->gd->disk_name,
+	dev_info->dax_dev = alloc_dax(dev_info, &dcssblk_dax_ops);
-			&dcssblk_dax_ops, DAXDEV_F_SYNC);
 	if (IS_ERR(dev_info->dax_dev)) {
 		rc = PTR_ERR(dev_info->dax_dev);
 		dev_info->dax_dev = NULL;
 		goto put_dev;
 	}
+	set_dax_synchronous(dev_info->dax_dev);
+	rc = dax_add_host(dev_info->dax_dev, dev_info->gd);
+	if (rc)
+		goto out_dax;
 
 	get_device(&dev_info->dev);
 	rc = device_add_disk(&dev_info->dev, dev_info->gd, NULL);
 	if (rc)
-		goto out_dax;
+		goto out_dax_host;
 
 	switch (dev_info->segment_type) {
 		case SEG_TYPE_SR:
@@ -714,6 +702,8 @@ dcssblk_add_store(struct device *dev, struct device_attribute *attr, const char
 	rc = count;
 	goto out;
 
+out_dax_host:
+	dax_remove_host(dev_info->gd);
 out_dax:
 	put_device(&dev_info->dev);
 	kill_dax(dev_info->dax_dev);

fs/Kconfig

@@ -15,11 +15,11 @@ config VALIDATE_FS_PARSER
 	  Enable this to perform validation of the parameter description for a
 	  filesystem when it is registered.
 
-if BLOCK
-
 config FS_IOMAP
 	bool
 
+if BLOCK
+
 source "fs/ext2/Kconfig"
 source "fs/ext4/Kconfig"
 source "fs/jbd2/Kconfig"
@@ -42,6 +42,8 @@ source "fs/nilfs2/Kconfig"
 source "fs/f2fs/Kconfig"
 source "fs/zonefs/Kconfig"
 
+endif # BLOCK
+
 config FS_DAX
 	bool "File system based Direct Access (DAX) support"
 	depends on MMU
@@ -89,8 +91,6 @@ config FS_DAX_PMD
 config FS_DAX_LIMITED
 	bool
 
-endif # BLOCK
-
 # Posix ACL utility routines
 #
 # Note: Posix ACLs can be implemented without these helpers.  Never use

fs/dax.c

@@ -709,26 +709,26 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 	return __dax_invalidate_entry(mapping, index, false);
 }
 
-static int copy_cow_page_dax(struct block_device *bdev, struct dax_device *dax_dev,
+static pgoff_t dax_iomap_pgoff(const struct iomap *iomap, loff_t pos)
-			     sector_t sector, struct page *to, unsigned long vaddr)
 {
+	return PHYS_PFN(iomap->addr + (pos & PAGE_MASK) - iomap->offset);
+}
+
+static int copy_cow_page_dax(struct vm_fault *vmf, const struct iomap_iter *iter)
+{
+	pgoff_t pgoff = dax_iomap_pgoff(&iter->iomap, iter->pos);
 	void *vto, *kaddr;
-	pgoff_t pgoff;
 	long rc;
 	int id;
 
-	rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
-	if (rc)
-		return rc;
-
 	id = dax_read_lock();
-	rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
+	rc = dax_direct_access(iter->iomap.dax_dev, pgoff, 1, &kaddr, NULL);
 	if (rc < 0) {
 		dax_read_unlock(id);
 		return rc;
 	}
-	vto = kmap_atomic(to);
+	vto = kmap_atomic(vmf->cow_page);
-	copy_user_page(vto, (void __force *)kaddr, vaddr, to);
+	copy_user_page(vto, kaddr, vmf->address, vmf->cow_page);
 	kunmap_atomic(vto);
 	dax_read_unlock(id);
 	return 0;
@@ -1005,22 +1005,13 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
-static sector_t dax_iomap_sector(const struct iomap *iomap, loff_t pos)
-{
-	return (iomap->addr + (pos & PAGE_MASK) - iomap->offset) >> 9;
-}
-
 static int dax_iomap_pfn(const struct iomap *iomap, loff_t pos, size_t size,
 			 pfn_t *pfnp)
 {
-	const sector_t sector = dax_iomap_sector(iomap, pos);
+	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
-	pgoff_t pgoff;
 	int id, rc;
 	long length;
 
-	rc = bdev_dax_pgoff(iomap->bdev, sector, size, &pgoff);
-	if (rc)
-		return rc;
 	id = dax_read_lock();
 	length = dax_direct_access(iomap->dax_dev, pgoff, PHYS_PFN(size),
 				   NULL, pfnp);
@@ -1126,50 +1117,94 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 }
 #endif /* CONFIG_FS_DAX_PMD */
 
-s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap)
+static int dax_memzero(struct dax_device *dax_dev, pgoff_t pgoff,
+		unsigned int offset, size_t size)
 {
-	sector_t sector = iomap_sector(iomap, pos & PAGE_MASK);
-	pgoff_t pgoff;
-	long rc, id;
 	void *kaddr;
-	bool page_aligned = false;
+	long ret;
-	unsigned offset = offset_in_page(pos);
-	unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 
-	if (IS_ALIGNED(sector << SECTOR_SHIFT, PAGE_SIZE) &&
+	ret = dax_direct_access(dax_dev, pgoff, 1, &kaddr, NULL);
-	    (size == PAGE_SIZE))
+	if (ret > 0) {
-		page_aligned = true;
-
-	rc = bdev_dax_pgoff(iomap->bdev, sector, PAGE_SIZE, &pgoff);
-	if (rc)
-		return rc;
-
-	id = dax_read_lock();
-
-	if (page_aligned)
-		rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
-	else
-		rc = dax_direct_access(iomap->dax_dev, pgoff, 1, &kaddr, NULL);
-	if (rc < 0) {
-		dax_read_unlock(id);
-		return rc;
-	}
-
-	if (!page_aligned) {
 		memset(kaddr + offset, 0, size);
-		dax_flush(iomap->dax_dev, kaddr + offset, size);
+		dax_flush(dax_dev, kaddr + offset, size);
 	}
-	dax_read_unlock(id);
+	return ret;
-	return size;
 }
 
+static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
+{
+	const struct iomap *iomap = &iter->iomap;
+	const struct iomap *srcmap = iomap_iter_srcmap(iter);
+	loff_t pos = iter->pos;
+	u64 length = iomap_length(iter);
+	s64 written = 0;
+
+	/* already zeroed?  we're done. */
+	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
+		return length;
+
+	do {
+		unsigned offset = offset_in_page(pos);
+		unsigned size = min_t(u64, PAGE_SIZE - offset, length);
+		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
+		long rc;
+		int id;
+
+		id = dax_read_lock();
+		if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
+			rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
+		else
+			rc = dax_memzero(iomap->dax_dev, pgoff, offset, size);
+		dax_read_unlock(id);
+
+		if (rc < 0)
+			return rc;
+		pos += size;
+		length -= size;
+		written += size;
+		if (did_zero)
+			*did_zero = true;
+	} while (length > 0);
+
+	return written;
+}
+
+int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		const struct iomap_ops *ops)
+{
+	struct iomap_iter iter = {
+		.inode		= inode,
+		.pos		= pos,
+		.len		= len,
+		.flags		= IOMAP_DAX | IOMAP_ZERO,
+	};
+	int ret;
+
+	while ((ret = iomap_iter(&iter, ops)) > 0)
+		iter.processed = dax_zero_iter(&iter, did_zero);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dax_zero_range);
+
+int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		const struct iomap_ops *ops)
+{
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int off = pos & (blocksize - 1);
+
+	/* Block boundary? Nothing to do */
+	if (!off)
+		return 0;
+	return dax_zero_range(inode, pos, blocksize - off, did_zero, ops);
+}
+EXPORT_SYMBOL_GPL(dax_truncate_page);
+
 static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		struct iov_iter *iter)
 {
 	const struct iomap *iomap = &iomi->iomap;
 	loff_t length = iomap_length(iomi);
 	loff_t pos = iomi->pos;
-	struct block_device *bdev = iomap->bdev;
 	struct dax_device *dax_dev = iomap->dax_dev;
 	loff_t end = pos + length, done = 0;
 	ssize_t ret = 0;
@@ -1203,9 +1238,8 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		const size_t size = ALIGN(length + offset, PAGE_SIZE);
-		const sector_t sector = dax_iomap_sector(iomap, pos);
+		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 		ssize_t map_len;
-		pgoff_t pgoff;
 		void *kaddr;
 
 		if (fatal_signal_pending(current)) {
@@ -1213,10 +1247,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 			break;
 		}
 
-		ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
-		if (ret)
-			break;
-
 		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
 				&kaddr, NULL);
 		if (map_len < 0) {
@@ -1230,11 +1260,6 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		if (map_len > end - pos)
 			map_len = end - pos;
 
-		/*
-		 * The userspace address for the memory copy has already been
-		 * validated via access_ok() in either vfs_read() or
-		 * vfs_write(), depending on which operation we are doing.
-		 */
 		if (iov_iter_rw(iter) == WRITE)
 			xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
@@ -1274,6 +1299,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		.inode		= iocb->ki_filp->f_mapping->host,
 		.pos		= iocb->ki_pos,
 		.len		= iov_iter_count(iter),
+		.flags		= IOMAP_DAX,
 	};
 	loff_t done = 0;
 	int ret;
@@ -1332,19 +1358,16 @@ static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
 static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf,
 		const struct iomap_iter *iter)
 {
-	sector_t sector = dax_iomap_sector(&iter->iomap, iter->pos);
-	unsigned long vaddr = vmf->address;
 	vm_fault_t ret;
 	int error = 0;
 
 	switch (iter->iomap.type) {
 	case IOMAP_HOLE:
 	case IOMAP_UNWRITTEN:
-		clear_user_highpage(vmf->cow_page, vaddr);
+		clear_user_highpage(vmf->cow_page, vmf->address);
 		break;
 	case IOMAP_MAPPED:
-		error = copy_cow_page_dax(iter->iomap.bdev, iter->iomap.dax_dev,
+		error = copy_cow_page_dax(vmf, iter);
-					  sector, vmf->cow_page, vaddr);
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -1430,7 +1453,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 		.inode		= mapping->host,
 		.pos		= (loff_t)vmf->pgoff << PAGE_SHIFT,
 		.len		= PAGE_SIZE,
-		.flags		= IOMAP_FAULT,
+		.flags		= IOMAP_DAX | IOMAP_FAULT,
 	};
 	vm_fault_t ret = 0;
 	void *entry;
@@ -1539,7 +1562,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	struct iomap_iter iter = {
 		.inode		= mapping->host,
 		.len		= PMD_SIZE,
-		.flags		= IOMAP_FAULT,
+		.flags		= IOMAP_DAX | IOMAP_FAULT,
 	};
 	vm_fault_t ret = VM_FAULT_FALLBACK;
 	pgoff_t max_pgoff;

fs/erofs/data.c

@@ -192,6 +192,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 	/* primary device by default */
 	map->m_bdev = sb->s_bdev;
 	map->m_daxdev = EROFS_SB(sb)->dax_dev;
+	map->m_dax_part_off = EROFS_SB(sb)->dax_part_off;
 
 	if (map->m_deviceid) {
 		down_read(&devs->rwsem);
@@ -202,6 +203,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 		}
 		map->m_bdev = dif->bdev;
 		map->m_daxdev = dif->dax_dev;
+		map->m_dax_part_off = dif->dax_part_off;
 		up_read(&devs->rwsem);
 	} else if (devs->extra_devices) {
 		down_read(&devs->rwsem);
@@ -218,6 +220,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map)
 				map->m_pa -= startoff;
 				map->m_bdev = dif->bdev;
 				map->m_daxdev = dif->dax_dev;
+				map->m_dax_part_off = dif->dax_part_off;
 				break;
 			}
 		}
@@ -248,9 +251,13 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret)
 		return ret;
 
-	iomap->bdev = mdev.m_bdev;
-	iomap->dax_dev = mdev.m_daxdev;
 	iomap->offset = map.m_la;
+	if (flags & IOMAP_DAX) {
+		iomap->dax_dev = mdev.m_daxdev;
+		iomap->offset += mdev.m_dax_part_off;
+	} else {
+		iomap->bdev = mdev.m_bdev;
+	}
 	iomap->length = map.m_llen;
 	iomap->flags = 0;
 	iomap->private = NULL;

fs/erofs/internal.h

@@ -51,6 +51,7 @@ struct erofs_device_info {
 	char *path;
 	struct block_device *bdev;
 	struct dax_device *dax_dev;
+	u64 dax_part_off;
 
 	u32 blocks;
 	u32 mapped_blkaddr;
@@ -115,6 +116,7 @@ struct erofs_sb_info {
 #endif	/* CONFIG_EROFS_FS_ZIP */
 	struct erofs_dev_context *devs;
 	struct dax_device *dax_dev;
+	u64 dax_part_off;
 	u64 total_blocks;
 	u32 primarydevice_blocks;
 
@@ -467,6 +469,7 @@ static inline int z_erofs_map_blocks_iter(struct inode *inode,
 struct erofs_map_dev {
 	struct block_device *m_bdev;
 	struct dax_device *m_daxdev;
+	u64 m_dax_part_off;
 
 	erofs_off_t m_pa;
 	unsigned int m_deviceid;

fs/erofs/super.c

@@ -267,7 +267,7 @@ static int erofs_init_devices(struct super_block *sb,
 			break;
 		}
 		dif->bdev = bdev;
-		dif->dax_dev = fs_dax_get_by_bdev(bdev);
+		dif->dax_dev = fs_dax_get_by_bdev(bdev, &dif->dax_part_off);
 		dif->blocks = le32_to_cpu(dis->blocks);
 		dif->mapped_blkaddr = le32_to_cpu(dis->mapped_blkaddr);
 		sbi->total_blocks += dif->blocks;
@@ -597,7 +597,7 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	sb->s_fs_info = sbi;
 	sbi->opt = ctx->opt;
-	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
+	sbi->dax_dev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->dax_part_off);
 	sbi->devs = ctx->devs;
 	ctx->devs = NULL;
 
@@ -605,10 +605,13 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
-	if (test_opt(&sbi->opt, DAX_ALWAYS) &&
+	if (test_opt(&sbi->opt, DAX_ALWAYS)) {
-	    !dax_supported(sbi->dax_dev, sb->s_bdev, EROFS_BLKSIZ, 0, bdev_nr_sectors(sb->s_bdev))) {
+		BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE);
-		errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
+
-		clear_opt(&sbi->opt, DAX_ALWAYS);
+		if (!sbi->dax_dev) {
+			errorfc(fc, "DAX unsupported by block device. Turning off DAX.");
+			clear_opt(&sbi->opt, DAX_ALWAYS);
+		}
 	}
 	sb->s_flags |= SB_RDONLY | SB_NOATIME;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;

fs/ext2/ext2.h

@@ -118,6 +118,7 @@ struct ext2_sb_info {
 	spinlock_t s_lock;
 	struct mb_cache *s_ea_block_cache;
 	struct dax_device *s_daxdev;
+	u64 s_dax_part_off;
 };
 
 static inline spinlock_t *

fs/ext2/inode.c

@@ -36,6 +36,7 @@
 #include <linux/iomap.h>
 #include <linux/namei.h>
 #include <linux/uio.h>
+#include <linux/dax.h>
 #include "ext2.h"
 #include "acl.h"
 #include "xattr.h"
@@ -816,9 +817,11 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		return ret;
 
 	iomap->flags = 0;
-	iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64)first_block << blkbits;
-	iomap->dax_dev = sbi->s_daxdev;
+	if (flags & IOMAP_DAX)
+		iomap->dax_dev = sbi->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 
 	if (ret == 0) {
 		iomap->type = IOMAP_HOLE;
@@ -827,6 +830,8 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	} else {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64)bno << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += sbi->s_dax_part_off;
 		iomap->length = (u64)ret << blkbits;
 		iomap->flags |= IOMAP_F_MERGED;
 	}
@@ -1297,9 +1302,9 @@ static int ext2_setsize(struct inode *inode, loff_t newsize)
 	inode_dio_wait(inode);
 
 	if (IS_DAX(inode)) {
-		error = iomap_zero_range(inode, newsize,
+		error = dax_zero_range(inode, newsize,
-					 PAGE_ALIGN(newsize) - newsize, NULL,
+				       PAGE_ALIGN(newsize) - newsize, NULL,
-					 &ext2_iomap_ops);
+				       &ext2_iomap_ops);
 	} else if (test_opt(inode->i_sb, NOBH))
 		error = nobh_truncate_page(inode->i_mapping,
 				newsize, ext2_get_block);

fs/ext2/super.c

@@ -802,7 +802,6 @@ static unsigned long descriptor_loc(struct super_block *sb,
 
 static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
 	struct buffer_head * bh;
 	struct ext2_sb_info * sbi;
 	struct ext2_super_block * es;
@@ -822,17 +821,17 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
-		goto failed;
+		return -ENOMEM;
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
 	if (!sbi->s_blockgroup_lock) {
 		kfree(sbi);
-		goto failed;
+		return -ENOMEM;
 	}
 	sb->s_fs_info = sbi;
 	sbi->s_sb_block = sb_block;
-	sbi->s_daxdev = dax_dev;
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
 
 	spin_lock_init(&sbi->s_lock);
 	ret = -EINVAL;
@@ -946,11 +945,13 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
 
 	if (test_opt(sb, DAX)) {
-		if (!dax_supported(dax_dev, sb->s_bdev, blocksize, 0,
+		if (!sbi->s_daxdev) {
-				bdev_nr_sectors(sb->s_bdev))) {
 			ext2_msg(sb, KERN_ERR,
 				"DAX unsupported by block device. Turning off DAX.");
 			clear_opt(sbi->s_mount_opt, DAX);
+		} else if (blocksize != PAGE_SIZE) {
+			ext2_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+			clear_opt(sbi->s_mount_opt, DAX);
 		}
 	}
 
@@ -1199,11 +1200,10 @@ failed_mount_group_desc:
 failed_mount:
 	brelse(bh);
 failed_sbi:
+	fs_put_dax(sbi->s_daxdev);
 	sb->s_fs_info = NULL;
 	kfree(sbi->s_blockgroup_lock);
 	kfree(sbi);
-failed:
-	fs_put_dax(dax_dev);
 	return ret;
 }
 

fs/ext4/ext4.h

@@ -1699,6 +1699,7 @@ struct ext4_sb_info {
 	 */
 	struct percpu_rw_semaphore s_writepages_rwsem;
 	struct dax_device *s_daxdev;
+	u64 s_dax_part_off;
 #ifdef CONFIG_EXT4_DEBUG
 	unsigned long s_simulate_fail;
 #endif

fs/ext4/inode.c

@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/iomap.h>
 #include <linux/iversion.h>
+#include <linux/dax.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -3253,7 +3254,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
 
 static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 			   struct ext4_map_blocks *map, loff_t offset,
-			   loff_t length)
+			   loff_t length, unsigned int flags)
 {
 	u8 blkbits = inode->i_blkbits;
 
@@ -3270,8 +3271,10 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_NEW)
 		iomap->flags |= IOMAP_F_NEW;
 
-	iomap->bdev = inode->i_sb->s_bdev;
+	if (flags & IOMAP_DAX)
-	iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+		iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+	else
+		iomap->bdev = inode->i_sb->s_bdev;
 	iomap->offset = (u64) map->m_lblk << blkbits;
 	iomap->length = (u64) map->m_len << blkbits;
 
@@ -3291,9 +3294,13 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
 	if (map->m_flags & EXT4_MAP_UNWRITTEN) {
 		iomap->type = IOMAP_UNWRITTEN;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else if (map->m_flags & EXT4_MAP_MAPPED) {
 		iomap->type = IOMAP_MAPPED;
 		iomap->addr = (u64) map->m_pblk << blkbits;
+		if (flags & IOMAP_DAX)
+			iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
 	} else {
 		iomap->type = IOMAP_HOLE;
 		iomap->addr = IOMAP_NULL_ADDR;
@@ -3330,8 +3337,8 @@ retry:
 	 * DAX and direct I/O are the only two operations that are currently
 	 * supported with IOMAP_WRITE.
 	 */
-	WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
+	WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT)));
-	if (IS_DAX(inode))
+	if (flags & IOMAP_DAX)
 		m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
 	/*
 	 * We use i_size instead of i_disksize here because delalloc writeback
@@ -3402,7 +3409,7 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	if (ret < 0)
 		return ret;
 out:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 
 	return 0;
 }
@@ -3522,7 +3529,7 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
 		delalloc = ext4_iomap_is_delalloc(inode, &map);
 
 set_iomap:
-	ext4_set_iomap(inode, iomap, &map, offset, length);
+	ext4_set_iomap(inode, iomap, &map, offset, length, flags);
 	if (delalloc && iomap->type == IOMAP_HOLE)
 		iomap->type = IOMAP_DELALLOC;
 
@@ -3762,8 +3769,8 @@ static int ext4_block_zero_page_range(handle_t *handle,
 		length = max;
 
 	if (IS_DAX(inode)) {
-		return iomap_zero_range(inode, from, length, NULL,
+		return dax_zero_range(inode, from, length, NULL,
-					&ext4_iomap_ops);
+				      &ext4_iomap_ops);
 	}
 	return __ext4_block_zero_page_range(handle, mapping, from, length);
 }

fs/ext4/super.c

@@ -4338,7 +4338,7 @@ static struct ext4_sb_info *ext4_alloc_sbi(struct super_block *sb)
 	if (!sbi)
 		return NULL;
 
-	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev);
+	sbi->s_daxdev = fs_dax_get_by_bdev(sb->s_bdev, &sbi->s_dax_part_off);
 
 	sbi->s_blockgroup_lock =
 		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
@@ -4756,9 +4756,12 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
 		goto failed_mount;
 	}
 
-	if (dax_supported(sbi->s_daxdev, sb->s_bdev, blocksize, 0,
+	if (sbi->s_daxdev) {
-			bdev_nr_sectors(sb->s_bdev)))
+		if (blocksize == PAGE_SIZE)
-		set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+			set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+		else
+			ext4_msg(sb, KERN_ERR, "unsupported blocksize for DAX\n");
+	}
 
 	if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
 		if (ext4_has_feature_inline_data(sb)) {

fs/fuse/Kconfig

@@ -45,7 +45,7 @@ config FUSE_DAX
 	select INTERVAL_TREE
 	depends on VIRTIO_FS
 	depends on FS_DAX
-	depends on DAX_DRIVER
+	depends on DAX
 	help
 	  This allows bypassing guest page cache and allows mapping host page
 	  cache directly in guest address space.

fs/fuse/virtio_fs.c

@@ -765,20 +765,6 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
 }
 
-static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev,
-				       pgoff_t pgoff, void *addr,
-				       size_t bytes, struct iov_iter *i)
-{
-	return copy_from_iter(addr, bytes, i);
-}
-
-static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev,
-				       pgoff_t pgoff, void *addr,
-				       size_t bytes, struct iov_iter *i)
-{
-	return copy_to_iter(addr, bytes, i);
-}
-
 static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
 				     pgoff_t pgoff, size_t nr_pages)
 {
@@ -795,8 +781,6 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
 
 static const struct dax_operations virtio_fs_dax_ops = {
 	.direct_access = virtio_fs_direct_access,
-	.copy_from_iter = virtio_fs_copy_from_iter,
-	.copy_to_iter = virtio_fs_copy_to_iter,
 	.zero_page_range = virtio_fs_zero_page_range,
 };
 
@@ -862,7 +846,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
 	dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
 		__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);
 
-	fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0);
+	fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops);
 	if (IS_ERR(fs->dax_dev))
 		return PTR_ERR(fs->dax_dev);
 

fs/iomap/Makefile

@@ -9,9 +9,9 @@ ccflags-y += -I $(srctree)/$(src)		# needed for trace events
 obj-$(CONFIG_FS_IOMAP)		+= iomap.o
 
 iomap-y				+= trace.o \
-				   buffered-io.o \
+				   iter.o
+iomap-$(CONFIG_BLOCK)		+= buffered-io.o \
 				   direct-io.o \
 				   fiemap.o \
-				   iter.o \
 				   seek.o
 iomap-$(CONFIG_SWAP)		+= swapfile.o

fs/iomap/buffered-io.c

@@ -897,7 +897,6 @@ EXPORT_SYMBOL_GPL(iomap_file_unshare);
 
 static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 {
-	struct iomap *iomap = &iter->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	loff_t length = iomap_length(iter);
@@ -913,14 +912,6 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		size_t offset;
 		size_t bytes = min_t(u64, SIZE_MAX, length);
 
-		if (IS_DAX(iter->inode)) {
-			s64 tmp = dax_iomap_zero(pos, bytes, iomap);
-			if (tmp < 0)
-				return tmp;
-			bytes = tmp;
-			goto good;
-		}
-
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (status)
 			return status;
@@ -933,7 +924,6 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		folio_mark_accessed(folio);
 
 		bytes = iomap_write_end(iter, pos, bytes, bytes, folio);
-good:
 		if (WARN_ON_ONCE(bytes == 0))
 			return -EIO;
 

fs/xfs/libxfs/xfs_bmap.c

@@ -4551,7 +4551,7 @@ xfs_bmapi_convert_delalloc(
 	 * the extent.  Just return the real extent at this offset.
 	 */
 	if (!isnullstartblock(bma.got.br_startblock)) {
-		xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
+		xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
 		*seq = READ_ONCE(ifp->if_seq);
 		goto out_trans_cancel;
 	}
@@ -4598,7 +4598,7 @@ xfs_bmapi_convert_delalloc(
 	XFS_STATS_INC(mp, xs_xstrat_quick);
 
 	ASSERT(!isnullstartblock(bma.got.br_startblock));
-	xfs_bmbt_to_iomap(ip, iomap, &bma.got, flags);
+	xfs_bmbt_to_iomap(ip, iomap, &bma.got, 0, flags);
 	*seq = READ_ONCE(ifp->if_seq);
 
 	if (whichfork == XFS_COW_FORK)

fs/xfs/xfs_aops.c

@@ -359,7 +359,7 @@ retry:
 	    isnullstartblock(imap.br_startblock))
 		goto allocate_blocks;
 
-	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0);
+	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0);
 	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:

fs/xfs/xfs_bmap_util.c

@@ -1001,7 +1001,7 @@ xfs_free_file_space(
 
 	/*
 	 * Now that we've unmap all full blocks we'll have to zero out any
-	 * partial block at the beginning and/or end.  iomap_zero_range is smart
+	 * partial block at the beginning and/or end.  xfs_zero_range is smart
 	 * enough to skip any holes, including those we just created, but we
 	 * must take care not to zero beyond EOF and enlarge i_size.
 	 */
@@ -1009,15 +1009,14 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = iomap_zero_range(VFS_I(ip), offset, len, NULL,
+	error = xfs_zero_range(ip, offset, len, NULL);
-			&xfs_buffered_write_iomap_ops);
 	if (error)
 		return error;
 
 	/*
 	 * If we zeroed right up to EOF and EOF straddles a page boundary we
 	 * must make sure that the post-EOF area is also zeroed because the
-	 * page could be mmap'd and iomap_zero_range doesn't do that for us.
+	 * page could be mmap'd and xfs_zero_range doesn't do that for us.
 	 * Writeback of the eof page will do this, albeit clumsily.
 	 */
 	if (offset + len >= XFS_ISIZE(ip) && offset_in_page(offset + len) > 0) {

fs/xfs/xfs_buf.c

@@ -1892,6 +1892,7 @@ xfs_free_buftarg(
 	list_lru_destroy(&btp->bt_lru);
 
 	blkdev_issue_flush(btp->bt_bdev);
+	fs_put_dax(btp->bt_daxdev);
 
 	kmem_free(btp);
 }
@@ -1932,11 +1933,10 @@ xfs_setsize_buftarg_early(
 	return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev));
 }
 
-xfs_buftarg_t *
+struct xfs_buftarg *
 xfs_alloc_buftarg(
 	struct xfs_mount	*mp,
-	struct block_device	*bdev,
+	struct block_device	*bdev)
-	struct dax_device	*dax_dev)
 {
 	xfs_buftarg_t		*btp;
 
@@ -1945,7 +1945,7 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_daxdev = dax_dev;
+	btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
 
 	/*
 	 * Buffer IO error rate limiting. Limit it to no more than 10 messages

fs/xfs/xfs_buf.h

@@ -89,6 +89,7 @@ typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
 	struct dax_device	*bt_daxdev;
+	u64			bt_dax_part_off;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;
@@ -338,8 +339,8 @@ xfs_buf_update_cksum(struct xfs_buf *bp, unsigned long cksum_offset)
 /*
  *	Handling of buftargs.
  */
-extern struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *,
+struct xfs_buftarg *xfs_alloc_buftarg(struct xfs_mount *mp,
-		struct block_device *, struct dax_device *);
+		struct block_device *bdev);
 extern void xfs_free_buftarg(struct xfs_buftarg *);
 extern void xfs_buftarg_wait(struct xfs_buftarg *);
 extern void xfs_buftarg_drain(struct xfs_buftarg *);

fs/xfs/xfs_file.c

@@ -437,8 +437,7 @@ restart:
 		}
 
 		trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
-		error = iomap_zero_range(inode, isize, iocb->ki_pos - isize,
+		error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, NULL);
-				NULL, &xfs_buffered_write_iomap_ops);
 		if (error)
 			return error;
 	} else

fs/xfs/xfs_iomap.c

@@ -28,7 +28,6 @@
 #include "xfs_dquot.h"
 #include "xfs_reflink.h"
 
-
 #define XFS_ALLOC_ALIGN(mp, off) \
 	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
 
@@ -54,7 +53,8 @@ xfs_bmbt_to_iomap(
 	struct xfs_inode	*ip,
 	struct iomap		*iomap,
 	struct xfs_bmbt_irec	*imap,
-	u16			flags)
+	unsigned int		mapping_flags,
+	u16			iomap_flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
@@ -71,16 +71,22 @@ xfs_bmbt_to_iomap(
 		iomap->type = IOMAP_DELALLOC;
 	} else {
 		iomap->addr = BBTOB(xfs_fsb_to_db(ip, imap->br_startblock));
+		if (mapping_flags & IOMAP_DAX)
+			iomap->addr += target->bt_dax_part_off;
+
 		if (imap->br_state == XFS_EXT_UNWRITTEN)
 			iomap->type = IOMAP_UNWRITTEN;
 		else
 			iomap->type = IOMAP_MAPPED;
+
 	}
 	iomap->offset = XFS_FSB_TO_B(mp, imap->br_startoff);
 	iomap->length = XFS_FSB_TO_B(mp, imap->br_blockcount);
-	iomap->bdev = target->bt_bdev;
+	if (mapping_flags & IOMAP_DAX)
-	iomap->dax_dev = target->bt_daxdev;
+		iomap->dax_dev = target->bt_daxdev;
-	iomap->flags = flags;
+	else
+		iomap->bdev = target->bt_bdev;
+	iomap->flags = iomap_flags;
 
 	if (xfs_ipincount(ip) &&
 	    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
@@ -188,6 +194,7 @@ xfs_iomap_write_direct(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		offset_fsb,
 	xfs_fileoff_t		count_fsb,
+	unsigned int		flags,
 	struct xfs_bmbt_irec	*imap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
@@ -229,7 +236,7 @@ xfs_iomap_write_direct(
 	 * the reserve block pool for bmbt block allocation if there is no space
 	 * left but we need to do unwritten extent conversion.
 	 */
-	if (IS_DAX(VFS_I(ip))) {
+	if (flags & IOMAP_DAX) {
 		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
 		if (imap->br_state == XFS_EXT_UNWRITTEN) {
 			force = true;
@@ -620,7 +627,7 @@ imap_needs_alloc(
 	    imap->br_startblock == DELAYSTARTBLOCK)
 		return true;
 	/* we convert unwritten extents before copying the data for DAX */
-	if (IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN)
+	if ((flags & IOMAP_DAX) && imap->br_state == XFS_EXT_UNWRITTEN)
 		return true;
 	return false;
 }
@@ -800,7 +807,7 @@ xfs_direct_write_iomap_begin(
 
 	xfs_iunlock(ip, lockmode);
 	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, iomap_flags);
 
 allocate_blocks:
 	error = -EAGAIN;
@@ -826,23 +833,24 @@ allocate_blocks:
 	xfs_iunlock(ip, lockmode);
 
 	error = xfs_iomap_write_direct(ip, offset_fsb, end_fsb - offset_fsb,
-			&imap);
+			flags, &imap);
 	if (error)
 		return error;
 
 	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, iomap_flags | IOMAP_F_NEW);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
+				 iomap_flags | IOMAP_F_NEW);
 
 out_found_cow:
 	xfs_iunlock(ip, lockmode);
 	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
 	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
 	if (imap.br_startblock != HOLESTARTBLOCK) {
-		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
+		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0);
 		if (error)
 			return error;
 	}
-	return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED);
 
 out_unlock:
 	if (lockmode)
@@ -1052,23 +1060,24 @@ retry:
 	 */
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	trace_xfs_iomap_alloc(ip, offset, count, allocfork, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, IOMAP_F_NEW);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, IOMAP_F_NEW);
 
 found_imap:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
 
 found_cow:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	if (imap.br_startoff <= offset_fsb) {
-		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, 0);
+		error = xfs_bmbt_to_iomap(ip, srcmap, &imap, flags, 0);
 		if (error)
 			return error;
-		return xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+		return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
+					 IOMAP_F_SHARED);
 	}
 
 	xfs_trim_extent(&cmap, offset_fsb, imap.br_startoff - offset_fsb);
-	return xfs_bmbt_to_iomap(ip, iomap, &cmap, 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, 0);
 
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1177,7 +1186,8 @@ xfs_read_iomap_begin(
 	if (error)
 		return error;
 	trace_xfs_iomap_found(ip, offset, length, XFS_DATA_FORK, &imap);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared ? IOMAP_F_SHARED : 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags,
+				 shared ? IOMAP_F_SHARED : 0);
 }
 
 const struct iomap_ops xfs_read_iomap_ops = {
@@ -1236,7 +1246,8 @@ xfs_seek_iomap_begin(
 		if (data_fsb < cow_fsb + cmap.br_blockcount)
 			end_fsb = min(end_fsb, data_fsb);
 		xfs_trim_extent(&cmap, offset_fsb, end_fsb);
-		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, IOMAP_F_SHARED);
+		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, flags,
+					  IOMAP_F_SHARED);
 		/*
 		 * This is a COW extent, so we must probe the page cache
 		 * because there could be dirty page cache being backed
@@ -1258,7 +1269,7 @@ xfs_seek_iomap_begin(
 	imap.br_state = XFS_EXT_NORM;
 done:
 	xfs_trim_extent(&imap, offset_fsb, end_fsb);
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
 out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
@@ -1305,9 +1316,40 @@ out_unlock:
 	if (error)
 		return error;
 	ASSERT(nimaps);
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	return xfs_bmbt_to_iomap(ip, iomap, &imap, flags, 0);
 }
 
 const struct iomap_ops xfs_xattr_iomap_ops = {
 	.iomap_begin		= xfs_xattr_iomap_begin,
 };
+
+int
+xfs_zero_range(
+	struct xfs_inode	*ip,
+	loff_t			pos,
+	loff_t			len,
+	bool			*did_zero)
+{
+	struct inode		*inode = VFS_I(ip);
+
+	if (IS_DAX(inode))
+		return dax_zero_range(inode, pos, len, did_zero,
+				      &xfs_direct_write_iomap_ops);
+	return iomap_zero_range(inode, pos, len, did_zero,
+				&xfs_buffered_write_iomap_ops);
+}
+
+int
+xfs_truncate_page(
+	struct xfs_inode	*ip,
+	loff_t			pos,
+	bool			*did_zero)
+{
+	struct inode		*inode = VFS_I(ip);
+
+	if (IS_DAX(inode))
+		return dax_truncate_page(inode, pos, did_zero,
+					&xfs_direct_write_iomap_ops);
+	return iomap_truncate_page(inode, pos, did_zero,
+				   &xfs_buffered_write_iomap_ops);
+}

fs/xfs/xfs_iomap.h

@@ -12,13 +12,19 @@ struct xfs_inode;
 struct xfs_bmbt_irec;
 
 int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb,
-		xfs_fileoff_t count_fsb, struct xfs_bmbt_irec *imap);
+		xfs_fileoff_t count_fsb, unsigned int flags,
+		struct xfs_bmbt_irec *imap);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
 		xfs_fileoff_t end_fsb);
 
-int xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
+int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap,
-		struct xfs_bmbt_irec *, u16);
+		struct xfs_bmbt_irec *imap, unsigned int mapping_flags,
+		u16 iomap_flags);
+
+int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len,
+		bool *did_zero);
+int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, bool *did_zero);
 
 static inline xfs_filblks_t
 xfs_aligned_fsb_count(

fs/xfs/xfs_iops.c

@@ -890,8 +890,8 @@ xfs_setattr_size(
 	 */
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
-		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
+		error = xfs_zero_range(ip, oldsize, newsize - oldsize,
-				&did_zeroing, &xfs_buffered_write_iomap_ops);
+				&did_zeroing);
 	} else {
 		/*
 		 * iomap won't detect a dirty page over an unwritten block (or a
@@ -903,8 +903,7 @@ xfs_setattr_size(
 						     newsize);
 		if (error)
 			return error;
-		error = iomap_truncate_page(inode, newsize, &did_zeroing,
+		error = xfs_truncate_page(ip, newsize, &did_zeroing);
-				&xfs_buffered_write_iomap_ops);
 	}
 
 	if (error)

fs/xfs/xfs_pnfs.c

@@ -155,7 +155,7 @@ xfs_fs_map_blocks(
 		xfs_iunlock(ip, lock_flags);
 
 		error = xfs_iomap_write_direct(ip, offset_fsb,
-				end_fsb - offset_fsb, &imap);
+				end_fsb - offset_fsb, 0, &imap);
 		if (error)
 			goto out_unlock;
 
@@ -173,7 +173,7 @@ xfs_fs_map_blocks(
 	}
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
-	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0);
+	error = xfs_bmbt_to_iomap(ip, iomap, &imap, 0, 0);
 	*device_generation = mp->m_generation;
 	return error;
 out_unlock:

fs/xfs/xfs_reflink.c

@@ -1272,8 +1272,7 @@ xfs_reflink_zero_posteof(
 		return 0;
 
 	trace_xfs_zero_eof(ip, isize, pos - isize);
-	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
+	return xfs_zero_range(ip, isize, pos - isize, NULL);
-			&xfs_buffered_write_iomap_ops);
 }
 
 /*

fs/xfs/xfs_super.c

@@ -331,13 +331,34 @@ xfs_set_inode_alloc(
 	return xfs_is_inode32(mp) ? maxagi : agcount;
 }
 
-static bool
+static int
-xfs_buftarg_is_dax(
+xfs_setup_dax_always(
-	struct super_block	*sb,
+	struct xfs_mount	*mp)
-	struct xfs_buftarg	*bt)
 {
-	return dax_supported(bt->bt_daxdev, bt->bt_bdev, sb->s_blocksize, 0,
+	if (!mp->m_ddev_targp->bt_daxdev &&
-			bdev_nr_sectors(bt->bt_bdev));
+	    (!mp->m_rtdev_targp || !mp->m_rtdev_targp->bt_daxdev)) {
+		xfs_alert(mp,
+			"DAX unsupported by block device. Turning off DAX.");
+		goto disable_dax;
+	}
+
+	if (mp->m_super->s_blocksize != PAGE_SIZE) {
+		xfs_alert(mp,
+			"DAX not supported for blocksize. Turning off DAX.");
+		goto disable_dax;
+	}
+
+	if (xfs_has_reflink(mp)) {
+		xfs_alert(mp, "DAX and reflink cannot be used together!");
+		return -EINVAL;
+	}
+
+	xfs_warn(mp, "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+	return 0;
+
+disable_dax:
+	xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
+	return 0;
 }
 
 STATIC int
@@ -370,26 +391,19 @@ STATIC void
 xfs_close_devices(
 	struct xfs_mount	*mp)
 {
-	struct dax_device *dax_ddev = mp->m_ddev_targp->bt_daxdev;
-
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
 		struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
-		struct dax_device *dax_logdev = mp->m_logdev_targp->bt_daxdev;
 
 		xfs_free_buftarg(mp->m_logdev_targp);
 		xfs_blkdev_put(logdev);
-		fs_put_dax(dax_logdev);
 	}
 	if (mp->m_rtdev_targp) {
 		struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
-		struct dax_device *dax_rtdev = mp->m_rtdev_targp->bt_daxdev;
 
 		xfs_free_buftarg(mp->m_rtdev_targp);
 		xfs_blkdev_put(rtdev);
-		fs_put_dax(dax_rtdev);
 	}
 	xfs_free_buftarg(mp->m_ddev_targp);
-	fs_put_dax(dax_ddev);
 }
 
 /*
@@ -407,8 +421,6 @@ xfs_open_devices(
 	struct xfs_mount	*mp)
 {
 	struct block_device	*ddev = mp->m_super->s_bdev;
-	struct dax_device	*dax_ddev = fs_dax_get_by_bdev(ddev);
-	struct dax_device	*dax_logdev = NULL, *dax_rtdev = NULL;
 	struct block_device	*logdev = NULL, *rtdev = NULL;
 	int			error;
 
@@ -418,8 +430,7 @@ xfs_open_devices(
 	if (mp->m_logname) {
 		error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
 		if (error)
-			goto out;
+			return error;
-		dax_logdev = fs_dax_get_by_bdev(logdev);
 	}
 
 	if (mp->m_rtname) {
@@ -433,25 +444,24 @@ xfs_open_devices(
 			error = -EINVAL;
 			goto out_close_rtdev;
 		}
-		dax_rtdev = fs_dax_get_by_bdev(rtdev);
 	}
 
 	/*
 	 * Setup xfs_mount buffer target pointers
 	 */
 	error = -ENOMEM;
-	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev, dax_ddev);
+	mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
 	if (!mp->m_ddev_targp)
 		goto out_close_rtdev;
 
 	if (rtdev) {
-		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev, dax_rtdev);
+		mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
 		if (!mp->m_rtdev_targp)
 			goto out_free_ddev_targ;
 	}
 
 	if (logdev && logdev != ddev) {
-		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev, dax_logdev);
+		mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
 		if (!mp->m_logdev_targp)
 			goto out_free_rtdev_targ;
 	} else {
@@ -467,14 +477,9 @@ xfs_open_devices(
 	xfs_free_buftarg(mp->m_ddev_targp);
  out_close_rtdev:
 	xfs_blkdev_put(rtdev);
-	fs_put_dax(dax_rtdev);
  out_close_logdev:
-	if (logdev && logdev != ddev) {
+	if (logdev && logdev != ddev)
 		xfs_blkdev_put(logdev);
-		fs_put_dax(dax_logdev);
-	}
- out:
-	fs_put_dax(dax_ddev);
 	return error;
 }
 
@@ -1593,26 +1598,9 @@ xfs_fs_fill_super(
 		sb->s_flags |= SB_I_VERSION;
 
 	if (xfs_has_dax_always(mp)) {
-		bool rtdev_is_dax = false, datadev_is_dax;
+		error = xfs_setup_dax_always(mp);
-
+		if (error)
-		xfs_warn(mp,
-		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
-
-		datadev_is_dax = xfs_buftarg_is_dax(sb, mp->m_ddev_targp);
-		if (mp->m_rtdev_targp)
-			rtdev_is_dax = xfs_buftarg_is_dax(sb,
-						mp->m_rtdev_targp);
-		if (!rtdev_is_dax && !datadev_is_dax) {
-			xfs_alert(mp,
-			"DAX unsupported by block device. Turning off DAX.");
-			xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER);
-		}
-		if (xfs_has_reflink(mp)) {
-			xfs_alert(mp,
-		"DAX and reflink cannot be used together!");
-			error = -EINVAL;
 			goto out_filestream_unmount;
-		}
 	}
 
 	if (xfs_has_discard(mp)) {

include/linux/dax.h

@@ -6,14 +6,14 @@
 #include <linux/mm.h>
 #include <linux/radix-tree.h>
 
-/* Flag for synchronous flush */
-#define DAXDEV_F_SYNC (1UL << 0)
-
 typedef unsigned long dax_entry_t;
 
-struct iomap_ops;
-struct iomap;
 struct dax_device;
+struct gendisk;
+struct iomap_ops;
+struct iomap_iter;
+struct iomap;
+
 struct dax_operations {
 	/*
 	 * direct_access: translate a device-relative
@@ -28,33 +28,18 @@ struct dax_operations {
 	 */
 	bool (*dax_supported)(struct dax_device *, struct block_device *, int,
 			sector_t, sector_t);
-	/* copy_from_iter: required operation for fs-dax direct-i/o */
-	size_t (*copy_from_iter)(struct dax_device *, pgoff_t, void *, size_t,
-			struct iov_iter *);
-	/* copy_to_iter: required operation for fs-dax direct-i/o */
-	size_t (*copy_to_iter)(struct dax_device *, pgoff_t, void *, size_t,
-			struct iov_iter *);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 };
 
 #if IS_ENABLED(CONFIG_DAX)
-struct dax_device *alloc_dax(void *private, const char *host,
+struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
-		const struct dax_operations *ops, unsigned long flags);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
-bool __dax_synchronous(struct dax_device *dax_dev);
+bool dax_synchronous(struct dax_device *dax_dev);
-static inline bool dax_synchronous(struct dax_device *dax_dev)
+void set_dax_synchronous(struct dax_device *dax_dev);
-{
-	return  __dax_synchronous(dax_dev);
-}
-void __set_dax_synchronous(struct dax_device *dax_dev);
-static inline void set_dax_synchronous(struct dax_device *dax_dev)
-{
-	__set_dax_synchronous(dax_dev);
-}
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
@@ -68,8 +53,8 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 	return dax_synchronous(dax_dev);
 }
 #else
-static inline struct dax_device *alloc_dax(void *private, const char *host,
+static inline struct dax_device *alloc_dax(void *private,
-		const struct dax_operations *ops, unsigned long flags)
+		const struct dax_operations *ops)
 {
 	/*
 	 * Callers should check IS_ENABLED(CONFIG_DAX) to know if this
@@ -104,22 +89,38 @@ static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
 }
 #endif
 
+void set_dax_nocache(struct dax_device *dax_dev);
+void set_dax_nomc(struct dax_device *dax_dev);
+
 struct writeback_control;
-int bdev_dax_pgoff(struct block_device *, sector_t, size_t, pgoff_t *pgoff);
+#if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
-#if IS_ENABLED(CONFIG_FS_DAX)
+int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
-bool generic_fsdax_supported(struct dax_device *dax_dev,
+void dax_remove_host(struct gendisk *disk);
-		struct block_device *bdev, int blocksize, sector_t start,
+struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
-		sector_t sectors);
+		u64 *start_off);
-
-bool dax_supported(struct dax_device *dax_dev, struct block_device *bdev,
-		int blocksize, sector_t start, sector_t len);
-
 static inline void fs_put_dax(struct dax_device *dax_dev)
 {
 	put_dax(dax_dev);
 }
+#else
+static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
+{
+	return 0;
+}
+static inline void dax_remove_host(struct gendisk *disk)
+{
+}
+static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
+		u64 *start_off)
+{
+	return NULL;
+}
+static inline void fs_put_dax(struct dax_device *dax_dev)
+{
+}
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
-struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev);
+#if IS_ENABLED(CONFIG_FS_DAX)
 int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc);
 
@@ -128,24 +129,6 @@ struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t st
 dax_entry_t dax_lock_page(struct page *page);
 void dax_unlock_page(struct page *page, dax_entry_t cookie);
 #else
-#define generic_fsdax_supported		NULL
-
-static inline bool dax_supported(struct dax_device *dax_dev,
-		struct block_device *bdev, int blocksize, sector_t start,
-		sector_t len)
-{
-	return false;
-}
-
-static inline void fs_put_dax(struct dax_device *dax_dev)
-{
-}
-
-static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev)
-{
-	return NULL;
-}
-
 static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 {
 	return NULL;
@@ -174,6 +157,11 @@ static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
 }
 #endif
 
+int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
+		const struct iomap_ops *ops);
+int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
+		const struct iomap_ops *ops);
+
 #if IS_ENABLED(CONFIG_DAX)
 int dax_read_lock(void);
 void dax_read_unlock(int id);
@@ -208,7 +196,6 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
-s64 dax_iomap_zero(loff_t pos, u64 length, struct iomap *iomap);
 static inline bool dax_mapping(struct address_space *mapping)
 {
 	return mapping->host && IS_DAX(mapping->host);

include/linux/device-mapper.h

@@ -147,8 +147,6 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, void **kaddr, pfn_t *pfn);
-typedef size_t (*dm_dax_copy_iter_fn)(struct dm_target *ti, pgoff_t pgoff,
-		void *addr, size_t bytes, struct iov_iter *i);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
@@ -200,8 +198,6 @@ struct target_type {
 	dm_iterate_devices_fn iterate_devices;
 	dm_io_hints_fn io_hints;
 	dm_dax_direct_access_fn direct_access;
-	dm_dax_copy_iter_fn dax_copy_from_iter;
-	dm_dax_copy_iter_fn dax_copy_to_iter;
 	dm_dax_zero_page_range_fn dax_zero_page_range;
 
 	/* For internal device-mapper use. */

include/linux/iomap.h

@@ -141,6 +141,11 @@ struct iomap_page_ops {
 #define IOMAP_NOWAIT		(1 << 5) /* do not block */
 #define IOMAP_OVERWRITE_ONLY	(1 << 6) /* only pure overwrites allowed */
 #define IOMAP_UNSHARE		(1 << 7) /* unshare_file_range */
+#ifdef CONFIG_FS_DAX
+#define IOMAP_DAX		(1 << 8) /* DAX mapping */
+#else
+#define IOMAP_DAX		0
+#endif /* CONFIG_FS_DAX */
 
 struct iomap_ops {
 	/*

include/linux/memremap.h

@@ -72,16 +72,6 @@ struct dev_pagemap_ops {
 	 */
 	void (*page_free)(struct page *page);
 
-	/*
-	 * Transition the refcount in struct dev_pagemap to the dead state.
-	 */
-	void (*kill)(struct dev_pagemap *pgmap);
-
-	/*
-	 * Wait for refcount in struct dev_pagemap to be idle and reap it.
-	 */
-	void (*cleanup)(struct dev_pagemap *pgmap);
-
 	/*
 	 * Used for private (un-addressable) device memory only.  Must migrate
 	 * the page back to a CPU accessible page.
@@ -95,8 +85,7 @@ struct dev_pagemap_ops {
  * struct dev_pagemap - metadata for ZONE_DEVICE mappings
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @ref: reference count that pins the devm_memremap_pages() mapping
- * @internal_ref: internal reference if @ref is not provided by the caller
+ * @done: completion for @ref
- * @done: completion for @internal_ref
  * @type: memory type: see MEMORY_* in memory_hotplug.h
  * @flags: PGMAP_* flags to specify defailed behavior
  * @ops: method table
@@ -109,8 +98,7 @@ struct dev_pagemap_ops {
  */
 struct dev_pagemap {
 	struct vmem_altmap altmap;
-	struct percpu_ref *ref;
+	struct percpu_ref ref;
-	struct percpu_ref internal_ref;
 	struct completion done;
 	enum memory_type type;
 	unsigned int flags;
@@ -191,7 +179,7 @@ static inline unsigned long memremap_compat_align(void)
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
 {
 	if (pgmap)
-		percpu_ref_put(pgmap->ref);
+		percpu_ref_put(&pgmap->ref);
 }
 
 #endif /* _LINUX_MEMREMAP_H_ */

include/linux/uio.h

@@ -203,7 +203,7 @@ bool copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i)
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 /*
  * Note, users like pmem that depend on the stricter semantics of
- * copy_from_iter_flushcache() than copy_from_iter_nocache() must check for
+ * _copy_from_iter_flushcache() than _copy_from_iter_nocache() must check for
  * IS_ENABLED(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) before assuming that the
  * destination is flushed from the cache on return.
  */
@@ -218,24 +218,6 @@ size_t _copy_mc_to_iter(const void *addr, size_t bytes, struct iov_iter *i);
 #define _copy_mc_to_iter _copy_to_iter
 #endif
 
-static __always_inline __must_check
-size_t copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i)
-{
-	if (unlikely(!check_copy_size(addr, bytes, false)))
-		return 0;
-	else
-		return _copy_from_iter_flushcache(addr, bytes, i);
-}
-
-static __always_inline __must_check
-size_t copy_mc_to_iter(void *addr, size_t bytes, struct iov_iter *i)
-{
-	if (unlikely(!check_copy_size(addr, bytes, true)))
-		return 0;
-	else
-		return _copy_mc_to_iter(addr, bytes, i);
-}
-
 size_t iov_iter_zero(size_t bytes, struct iov_iter *);
 unsigned long iov_iter_alignment(const struct iov_iter *i);
 unsigned long iov_iter_gap_alignment(const struct iov_iter *i);

mm/memremap.c

@@ -112,30 +112,6 @@ static unsigned long pfn_next(unsigned long pfn)
 #define for_each_device_pfn(pfn, map, i) \
 	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
 
-static void dev_pagemap_kill(struct dev_pagemap *pgmap)
-{
-	if (pgmap->ops && pgmap->ops->kill)
-		pgmap->ops->kill(pgmap);
-	else
-		percpu_ref_kill(pgmap->ref);
-}
-
-static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
-{
-	if (pgmap->ops && pgmap->ops->cleanup) {
-		pgmap->ops->cleanup(pgmap);
-	} else {
-		wait_for_completion(&pgmap->done);
-		percpu_ref_exit(pgmap->ref);
-	}
-	/*
-	 * Undo the pgmap ref assignment for the internal case as the
-	 * caller may re-enable the same pgmap.
-	 */
-	if (pgmap->ref == &pgmap->internal_ref)
-		pgmap->ref = NULL;
-}
-
 static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 {
 	struct range *range = &pgmap->ranges[range_id];
@@ -167,11 +143,12 @@ void memunmap_pages(struct dev_pagemap *pgmap)
 	unsigned long pfn;
 	int i;
 
-	dev_pagemap_kill(pgmap);
+	percpu_ref_kill(&pgmap->ref);
 	for (i = 0; i < pgmap->nr_range; i++)
 		for_each_device_pfn(pfn, pgmap, i)
 			put_page(pfn_to_page(pfn));
-	dev_pagemap_cleanup(pgmap);
+	wait_for_completion(&pgmap->done);
+	percpu_ref_exit(&pgmap->ref);
 
 	for (i = 0; i < pgmap->nr_range; i++)
 		pageunmap_range(pgmap, i);
@@ -188,8 +165,7 @@ static void devm_memremap_pages_release(void *data)
 
 static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 {
-	struct dev_pagemap *pgmap =
+	struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
-		container_of(ref, struct dev_pagemap, internal_ref);
 
 	complete(&pgmap->done);
 }
@@ -295,8 +271,8 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
 				PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), pgmap);
-	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap, range_id)
+	percpu_ref_get_many(&pgmap->ref,
-			- pfn_first(pgmap, range_id));
+		pfn_end(pgmap, range_id) - pfn_first(pgmap, range_id));
 	return 0;
 
 err_add_memory:
@@ -362,22 +338,11 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		break;
 	}
 
-	if (!pgmap->ref) {
+	init_completion(&pgmap->done);
-		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+	error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
-			return ERR_PTR(-EINVAL);
+				GFP_KERNEL);
-
+	if (error)
-		init_completion(&pgmap->done);
+		return ERR_PTR(error);
-		error = percpu_ref_init(&pgmap->internal_ref,
-				dev_pagemap_percpu_release, 0, GFP_KERNEL);
-		if (error)
-			return ERR_PTR(error);
-		pgmap->ref = &pgmap->internal_ref;
-	} else {
-		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
-			WARN(1, "Missing reference count teardown definition\n");
-			return ERR_PTR(-EINVAL);
-		}
-	}
 
 	devmap_managed_enable_get(pgmap);
 
@@ -486,7 +451,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 	/* fall back to slow path lookup */
 	rcu_read_lock();
 	pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
-	if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
+	if (pgmap && !percpu_ref_tryget_live(&pgmap->ref))
 		pgmap = NULL;
 	rcu_read_unlock();
 

tools/testing/nvdimm/Kbuild

@@ -35,8 +35,6 @@ obj-$(CONFIG_DAX) += dax.o
 endif
 obj-$(CONFIG_DEV_DAX) += device_dax.o
 obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
-obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem_core.o
-obj-$(CONFIG_DEV_DAX_PMEM_COMPAT) += dax_pmem_compat.o
 
 nfit-y := $(ACPI_SRC)/core.o
 nfit-y += $(ACPI_SRC)/intel.o
@@ -67,12 +65,8 @@ device_dax-y += dax-dev.o
 device_dax-y += device_dax_test.o
 device_dax-y += config_check.o
 
-dax_pmem-y := $(DAX_SRC)/pmem/pmem.o
+dax_pmem-y := $(DAX_SRC)/pmem.o
 dax_pmem-y += dax_pmem_test.o
-dax_pmem_core-y := $(DAX_SRC)/pmem/core.o
-dax_pmem_core-y += dax_pmem_core_test.o
-dax_pmem_compat-y := $(DAX_SRC)/pmem/compat.o
-dax_pmem_compat-y += dax_pmem_compat_test.o
 dax_pmem-y += config_check.o
 
 libnvdimm-y := $(NVDIMM_SRC)/core.o

tools/testing/nvdimm/dax_pmem_compat_test.c

@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright(c) 2019 Intel Corporation. All rights reserved.
-
-#include <linux/module.h>
-#include <linux/printk.h>
-#include "watermark.h"
-
-nfit_test_watermark(dax_pmem_compat);

tools/testing/nvdimm/dax_pmem_core_test.c

@@ -1,8 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright(c) 2019 Intel Corporation. All rights reserved.
-
-#include <linux/module.h>
-#include <linux/printk.h>
-#include "watermark.h"
-
-nfit_test_watermark(dax_pmem_core);

tools/testing/nvdimm/test/iomap.c

@@ -100,25 +100,17 @@ static void nfit_test_kill(void *_pgmap)
 {
 	struct dev_pagemap *pgmap = _pgmap;
 
-	WARN_ON(!pgmap || !pgmap->ref);
+	WARN_ON(!pgmap);
 
-	if (pgmap->ops && pgmap->ops->kill)
+	percpu_ref_kill(&pgmap->ref);
-		pgmap->ops->kill(pgmap);
-	else
-		percpu_ref_kill(pgmap->ref);
 
-	if (pgmap->ops && pgmap->ops->cleanup) {
+	wait_for_completion(&pgmap->done);
-		pgmap->ops->cleanup(pgmap);
+	percpu_ref_exit(&pgmap->ref);
-	} else {
-		wait_for_completion(&pgmap->done);
-		percpu_ref_exit(pgmap->ref);
-	}
 }
 
 static void dev_pagemap_percpu_release(struct percpu_ref *ref)
 {
-	struct dev_pagemap *pgmap =
+	struct dev_pagemap *pgmap = container_of(ref, struct dev_pagemap, ref);
-		container_of(ref, struct dev_pagemap, internal_ref);
 
 	complete(&pgmap->done);
 }
@@ -132,22 +124,11 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	if (!nfit_res)
 		return devm_memremap_pages(dev, pgmap);
 
-	if (!pgmap->ref) {
+	init_completion(&pgmap->done);
-		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+	error = percpu_ref_init(&pgmap->ref, dev_pagemap_percpu_release, 0,
-			return ERR_PTR(-EINVAL);
+				GFP_KERNEL);
-
+	if (error)
-		init_completion(&pgmap->done);
+		return ERR_PTR(error);
-		error = percpu_ref_init(&pgmap->internal_ref,
-				dev_pagemap_percpu_release, 0, GFP_KERNEL);
-		if (error)
-			return ERR_PTR(error);
-		pgmap->ref = &pgmap->internal_ref;
-	} else {
-		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
-			WARN(1, "Missing reference count teardown definition\n");
-			return ERR_PTR(-EINVAL);
-		}
-	}
 
 	error = devm_add_action_or_reset(dev, nfit_test_kill, pgmap);
 	if (error)

tools/testing/nvdimm/test/ndtest.c

@@ -1054,10 +1054,6 @@ static __init int ndtest_init(void)
 	libnvdimm_test();
 	device_dax_test();
 	dax_pmem_test();
-	dax_pmem_core_test();
-#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
-	dax_pmem_compat_test();
-#endif
 
 	nfit_test_setup(ndtest_resource_lookup, NULL);
 

tools/testing/nvdimm/test/nfit.c

@@ -3300,10 +3300,6 @@ static __init int nfit_test_init(void)
 	acpi_nfit_test();
 	device_dax_test();
 	dax_pmem_test();
-	dax_pmem_core_test();
-#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
-	dax_pmem_compat_test();
-#endif
 
 	nfit_test_setup(nfit_test_lookup, nfit_test_evaluate_dsm);