Commit d5406bd4 authored by John Groves's avatar John Groves Committed by Ira Weiny
Browse files

dax: add fsdev.c driver for fs-dax on character dax



The new fsdev driver provides pages/folios initialized compatibly with
fsdax - normal rather than devdax-style refcounting, and starting out
with order-0 folios.

When fsdev binds to a daxdev, it is usually (always?) switching from the
devdax mode (device.c), which pre-initializes compound folios according
to its alignment. Fsdev uses fsdev_clear_folio_state() to switch the
folios into a fsdax-compatible state.

A side effect of this is that raw mmap doesn't (can't?) work on an fsdev
dax instance. Accordingly, The fsdev driver does not provide raw mmap -
devices must be put in 'devdax' mode (drivers/dax/device.c) to get raw
mmap capability.

In this commit is just the framework, which remaps pages/folios compatibly
with fsdax.

Enabling dax changes:

- bus.h: add DAXDRV_FSDEV_TYPE driver type
- bus.c: allow DAXDRV_FSDEV_TYPE drivers to bind to daxdevs
- dax.h: prototype inode_dax(), which fsdev needs

Suggested-by: default avatarDan Williams <dan.j.williams@intel.com>
Suggested-by: default avatarGregory Price <gourry@gourry.net>
Reviewed-by: default avatarJonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: default avatarJohn Groves <john@groves.net>
Link: https://patch.msgid.link/0100019d311cf904-419e9526-bdaf-4daa-97f1-5060b31a5c9f-000000@email.amazonses.com


Signed-off-by: default avatarIra Weiny <ira.weiny@intel.com>
parent 59eb73b9
Loading
Loading
Loading
Loading
+8 −0
Original line number Diff line number Diff line
@@ -7298,6 +7298,14 @@ L: linux-cxl@vger.kernel.org
S:	Supported
F:	drivers/dax/
DEVICE DIRECT ACCESS (DAX) [fsdev_dax]
M:	John Groves <jgroves@micron.com>
M:	John Groves <John@Groves.net>
L:	nvdimm@lists.linux.dev
L:	linux-cxl@vger.kernel.org
S:	Supported
F:	drivers/dax/fsdev.c
DEVICE FREQUENCY (DEVFREQ)
M:	MyungJoo Ham <myungjoo.ham@samsung.com>
M:	Kyungmin Park <kyungmin.park@samsung.com>
+5 −0
Original line number Diff line number Diff line
@@ -61,6 +61,11 @@ config DEV_DAX_HMEM_DEVICES
	depends on DEV_DAX_HMEM && DAX
	def_bool y

config DEV_DAX_FSDEV
	tristate
	depends on DEV_DAX && FS_DAX
	default DEV_DAX

config DEV_DAX_KMEM
	tristate "KMEM DAX: map dax-devices as System-RAM"
	default DEV_DAX
+2 −0
Original line number Diff line number Diff line
@@ -4,11 +4,13 @@ obj-$(CONFIG_DEV_DAX) += device_dax.o
obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
obj-$(CONFIG_DEV_DAX_CXL) += dax_cxl.o
obj-$(CONFIG_DEV_DAX_FSDEV) += fsdev_dax.o

dax-y := super.o
dax-y += bus.o
device_dax-y := device.o
dax_pmem-y := pmem.o
dax_cxl-y := cxl.o
fsdev_dax-y := fsdev.o

obj-y += hmem/
+1 −0
Original line number Diff line number Diff line
@@ -31,6 +31,7 @@ struct dev_dax *devm_create_dev_dax(struct dev_dax_data *data);
enum dax_driver_type {
	DAXDRV_KMEM_TYPE,
	DAXDRV_DEVICE_TYPE,
	DAXDRV_FSDEV_TYPE,
};

struct dax_device_driver {

drivers/dax/fsdev.c

0 → 100644
+245 −0
Original line number Diff line number Diff line
// SPDX-License-Identifier: GPL-2.0
/* Copyright(c) 2026 Micron Technology, Inc. */
#include <linux/memremap.h>
#include <linux/pagemap.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/slab.h>
#include <linux/dax.h>
#include <linux/uio.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include "dax-private.h"
#include "bus.h"

/*
 * FS-DAX compatible devdax driver
 *
 * Unlike drivers/dax/device.c which pre-initializes compound folios based
 * on device alignment (via vmemmap_shift), this driver leaves folios
 * uninitialized similar to pmem. This allows fs-dax filesystems like famfs
 * to work without needing special handling for pre-initialized folios.
 *
 * Key differences from device.c:
 * - pgmap type is MEMORY_DEVICE_FS_DAX (not MEMORY_DEVICE_GENERIC)
 * - vmemmap_shift is NOT set (folios remain order-0)
 * - fs-dax can dynamically create compound folios as needed
 * - No mmap support - all access is through fs-dax/iomap
 */

static void fsdev_cdev_del(void *cdev)
{
	cdev_del(cdev);
}

static void fsdev_kill(void *dev_dax)
{
	kill_dev_dax(dev_dax);
}

/*
 * Page map operations for FS-DAX mode
 * Similar to fsdax_pagemap_ops in drivers/nvdimm/pmem.c
 *
 * Note: folio_free callback is not needed for MEMORY_DEVICE_FS_DAX.
 * The core mm code in free_zone_device_folio() handles the wake_up_var()
 * directly for this memory type.
 */
static int fsdev_pagemap_memory_failure(struct dev_pagemap *pgmap,
		unsigned long pfn, unsigned long nr_pages, int mf_flags)
{
	struct dev_dax *dev_dax = pgmap->owner;
	u64 offset = PFN_PHYS(pfn) - dev_dax->ranges[0].range.start;
	u64 len = nr_pages << PAGE_SHIFT;

	return dax_holder_notify_failure(dev_dax->dax_dev, offset,
					 len, mf_flags);
}

static const struct dev_pagemap_ops fsdev_pagemap_ops = {
	.memory_failure		= fsdev_pagemap_memory_failure,
};

/*
 * Clear any stale folio state from pages in the given range.
 * This is necessary because device_dax pre-initializes compound folios
 * based on vmemmap_shift, and that state may persist after driver unbind.
 * Since fsdev_dax uses MEMORY_DEVICE_FS_DAX without vmemmap_shift, fs-dax
 * expects to find clean order-0 folios that it can build into compound
 * folios on demand.
 *
 * At probe time, no filesystem should be mounted yet, so all mappings
 * are stale and must be cleared along with compound state.
 */
static void fsdev_clear_folio_state(struct dev_dax *dev_dax)
{
	for (int i = 0; i < dev_dax->nr_range; i++) {
		struct range *range = &dev_dax->ranges[i].range;
		unsigned long pfn = PHYS_PFN(range->start);
		unsigned long end_pfn = PHYS_PFN(range->end) + 1;

		while (pfn < end_pfn) {
			struct folio *folio = pfn_folio(pfn);
			int order = dax_folio_reset_order(folio);

			pfn += 1UL << order;
		}
	}
}

static void fsdev_clear_folio_state_action(void *data)
{
	fsdev_clear_folio_state(data);
}

static int fsdev_open(struct inode *inode, struct file *filp)
{
	struct dax_device *dax_dev = inode_dax(inode);
	struct dev_dax *dev_dax = dax_get_private(dax_dev);

	filp->private_data = dev_dax;

	return 0;
}

static int fsdev_release(struct inode *inode, struct file *filp)
{
	return 0;
}

static const struct file_operations fsdev_fops = {
	.llseek = noop_llseek,
	.owner = THIS_MODULE,
	.open = fsdev_open,
	.release = fsdev_release,
};

static int fsdev_dax_probe(struct dev_dax *dev_dax)
{
	struct dax_device *dax_dev = dev_dax->dax_dev;
	struct device *dev = &dev_dax->dev;
	struct dev_pagemap *pgmap;
	struct inode *inode;
	struct cdev *cdev;
	void *addr;
	int rc, i;

	if (static_dev_dax(dev_dax)) {
		if (dev_dax->nr_range > 1) {
			dev_warn(dev, "static pgmap / multi-range device conflict\n");
			return -EINVAL;
		}

		pgmap = dev_dax->pgmap;
	} else {
		size_t pgmap_size;

		if (dev_dax->pgmap) {
			dev_warn(dev, "dynamic-dax with pre-populated page map\n");
			return -EINVAL;
		}

		pgmap_size = struct_size(pgmap, ranges, dev_dax->nr_range - 1);
		pgmap = devm_kzalloc(dev, pgmap_size, GFP_KERNEL);
		if (!pgmap)
			return -ENOMEM;

		pgmap->nr_range = dev_dax->nr_range;
		dev_dax->pgmap = pgmap;

		for (i = 0; i < dev_dax->nr_range; i++) {
			struct range *range = &dev_dax->ranges[i].range;

			pgmap->ranges[i] = *range;
		}
	}

	for (i = 0; i < dev_dax->nr_range; i++) {
		struct range *range = &dev_dax->ranges[i].range;

		if (!devm_request_mem_region(dev, range->start,
					range_len(range), dev_name(dev))) {
			dev_warn(dev, "mapping%d: %#llx-%#llx could not reserve range\n",
				 i, range->start, range->end);
			return -EBUSY;
		}
	}

	/*
	 * Use MEMORY_DEVICE_FS_DAX without setting vmemmap_shift, leaving
	 * folios at order-0. Unlike device.c (MEMORY_DEVICE_GENERIC), this
	 * lets fs-dax dynamically build compound folios as needed, similar
	 * to pmem behavior.
	 */
	pgmap->type = MEMORY_DEVICE_FS_DAX;
	pgmap->ops = &fsdev_pagemap_ops;
	pgmap->owner = dev_dax;

	addr = devm_memremap_pages(dev, pgmap);
	if (IS_ERR(addr))
		return PTR_ERR(addr);

	/*
	 * Clear any stale compound folio state left over from a previous
	 * driver (e.g., device_dax with vmemmap_shift). Also register this
	 * as a devm action so folio state is cleared on unbind, ensuring
	 * clean pages for subsequent drivers (e.g., kmem for system-ram).
	 */
	fsdev_clear_folio_state(dev_dax);
	rc = devm_add_action_or_reset(dev, fsdev_clear_folio_state_action,
				      dev_dax);
	if (rc)
		return rc;

	/* Detect whether the data is at a non-zero offset into the memory */
	if (pgmap->range.start != dev_dax->ranges[0].range.start) {
		u64 phys = dev_dax->ranges[0].range.start;
		u64 pgmap_phys = dev_dax->pgmap[0].range.start;
		u64 data_offset = 0;

		if (!WARN_ON(pgmap_phys > phys))
			data_offset = phys - pgmap_phys;

		pr_debug("%s: offset detected phys=%llx pgmap_phys=%llx offset=%llx\n",
		       __func__, phys, pgmap_phys, data_offset);
	}

	inode = dax_inode(dax_dev);
	cdev = inode->i_cdev;
	cdev_init(cdev, &fsdev_fops);
	cdev->owner = dev->driver->owner;
	cdev_set_parent(cdev, &dev->kobj);
	rc = cdev_add(cdev, dev->devt, 1);
	if (rc)
		return rc;

	rc = devm_add_action_or_reset(dev, fsdev_cdev_del, cdev);
	if (rc)
		return rc;

	run_dax(dax_dev);
	return devm_add_action_or_reset(dev, fsdev_kill, dev_dax);
}

static struct dax_device_driver fsdev_dax_driver = {
	.probe = fsdev_dax_probe,
	.type = DAXDRV_FSDEV_TYPE,
};

static int __init dax_init(void)
{
	return dax_driver_register(&fsdev_dax_driver);
}

static void __exit dax_exit(void)
{
	dax_driver_unregister(&fsdev_dax_driver);
}

MODULE_AUTHOR("John Groves");
MODULE_DESCRIPTION("FS-DAX Device: fs-dax compatible devdax driver");
MODULE_LICENSE("GPL");
module_init(dax_init);
module_exit(dax_exit);
MODULE_ALIAS_DAX_DEVICE(0);
Loading