[PATCH V4 01/19] dax: move dax_pgoff_to_phys from [drivers/dax/] device.c to bus.c

[PATCH V4 01/19] dax: move dax_pgoff_to_phys from [drivers/dax/] device.c to bus.c

[John Groves]

This function will be used by both device.c and fsdev.c, but both are
loadable modules. Moving to bus.c puts it in core and makes it available
to both.

No code changes - just relocated.

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/bus.c    | 24 ++++++++++++++++++++++++
 drivers/dax/device.c | 23 -----------------------
 2 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index fde29e0ad68b..a73f54eac567 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -1417,6 +1417,30 @@ static const struct device_type dev_dax_type = {
 	.groups = dax_attribute_groups,
 };
 
+/* see "strong" declaration in tools/testing/nvdimm/dax-dev.c */
+__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
+			      unsigned long size)
+{
+	int i;
+
+	for (i = 0; i < dev_dax->nr_range; i++) {
+		struct dev_dax_range *dax_range = &dev_dax->ranges[i];
+		struct range *range = &dax_range->range;
+		unsigned long long pgoff_end;
+		phys_addr_t phys;
+
+		pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
+		if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
+			continue;
+		phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
+		if (phys + size - 1 <= range->end)
+			return phys;
+		break;
+	}
+	return -1;
+}
+EXPORT_SYMBOL_GPL(dax_pgoff_to_phys);
+
 static struct dev_dax *__devm_create_dev_dax(struct dev_dax_data *data)
 {
 	struct dax_region *dax_region = data->dax_region;
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 22999a402e02..132c1d03fd07 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -57,29 +57,6 @@ static int check_vma(struct dev_dax *dev_dax, struct vm_area_struct *vma,
 			   vma->vm_file, func);
 }
 
-/* see "strong" declaration in tools/testing/nvdimm/dax-dev.c */
-__weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
-		unsigned long size)
-{
-	int i;
-
-	for (i = 0; i < dev_dax->nr_range; i++) {
-		struct dev_dax_range *dax_range = &dev_dax->ranges[i];
-		struct range *range = &dax_range->range;
-		unsigned long long pgoff_end;
-		phys_addr_t phys;
-
-		pgoff_end = dax_range->pgoff + PHYS_PFN(range_len(range)) - 1;
-		if (pgoff < dax_range->pgoff || pgoff > pgoff_end)
-			continue;
-		phys = PFN_PHYS(pgoff - dax_range->pgoff) + range->start;
-		if (phys + size - 1 <= range->end)
-			return phys;
-		break;
-	}
-	return -1;
-}
-
 static void dax_set_mapping(struct vm_fault *vmf, unsigned long pfn,
 			      unsigned long fault_size)
 {
-- 
2.52.0

[PATCH V4 02/19] dax: Factor out dax_folio_reset_order() helper

[John Groves]

From: John Groves <John@Groves.net>

Both fs/dax.c:dax_folio_put() and drivers/dax/fsdev.c:
fsdev_clear_folio_state() (the latter coming in the next commit after this
one) contain nearly identical code to reset a compound DAX folio back to
order-0 pages. Factor this out into a shared helper function.

The new dax_folio_reset_order() function:
- Clears the folio's mapping and share count
- Resets compound folio state via folio_reset_order()
- Clears PageHead and compound_head for each sub-page
- Restores the pgmap pointer for each resulting order-0 folio
- Returns the original folio order (for callers that need to advance by
  that many pages)

This simplifies fsdev_clear_folio_state() from ~50 lines to ~15 lines while
maintaining the same functionality in both call sites.

Suggested-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: John Groves <john@groves.net>
---
 fs/dax.c | 60 +++++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 18 deletions(-)

diff --git a/fs/dax.c b/fs/dax.c
index 289e6254aa30..7d7bbfb32c41 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -378,6 +378,45 @@ static void dax_folio_make_shared(struct folio *folio)
 	folio->share = 1;
 }
 
+/**
+ * dax_folio_reset_order - Reset a compound DAX folio to order-0 pages
+ * @folio: The folio to reset
+ *
+ * Splits a compound folio back into individual order-0 pages,
+ * clearing compound state and restoring pgmap pointers.
+ *
+ * Returns: the original folio order (0 if already order-0)
+ */
+int dax_folio_reset_order(struct folio *folio)
+{
+	struct dev_pagemap *pgmap = page_pgmap(&folio->page);
+	int order = folio_order(folio);
+	int i;
+
+	folio->mapping = NULL;
+	folio->share = 0;
+
+	if (!order) {
+		folio->pgmap = pgmap;
+		return 0;
+	}
+
+	folio_reset_order(folio);
+
+	for (i = 0; i < (1UL << order); i++) {
+		struct page *page = folio_page(folio, i);
+		struct folio *f = (struct folio *)page;
+
+		ClearPageHead(page);
+		clear_compound_head(page);
+		f->mapping = NULL;
+		f->share = 0;
+		f->pgmap = pgmap;
+	}
+
+	return order;
+}
+
 static inline unsigned long dax_folio_put(struct folio *folio)
 {
 	unsigned long ref;
@@ -391,28 +430,13 @@ static inline unsigned long dax_folio_put(struct folio *folio)
 	if (ref)
 		return ref;
 
-	folio->mapping = NULL;
-	order = folio_order(folio);
-	if (!order)
-		return 0;
-	folio_reset_order(folio);
+	order = dax_folio_reset_order(folio);
 
+	/* Debug check: verify refcounts are zero for all sub-folios */
 	for (i = 0; i < (1UL << order); i++) {
-		struct dev_pagemap *pgmap = page_pgmap(&folio->page);
 		struct page *page = folio_page(folio, i);
-		struct folio *new_folio = (struct folio *)page;
 
-		ClearPageHead(page);
-		clear_compound_head(page);
-
-		new_folio->mapping = NULL;
-		/*
-		 * Reset pgmap which was over-written by
-		 * prep_compound_page().
-		 */
-		new_folio->pgmap = pgmap;
-		new_folio->share = 0;
-		WARN_ON_ONCE(folio_ref_count(new_folio));
+		WARN_ON_ONCE(folio_ref_count((struct folio *)page));
 	}
 
 	return ref;
-- 
2.52.0

[PATCH V4 03/19] dax: add fsdev.c driver for fs-dax on character dax

[John Groves]

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: Dan Williams <dan.j.williams@intel.com>
Suggested-by: Gregory Price <gourry@gourry.net>
Signed-off-by: John Groves <john@groves.net>
---
 MAINTAINERS          |   8 ++
 drivers/dax/Makefile |   6 ++
 drivers/dax/bus.c    |   4 +
 drivers/dax/bus.h    |   1 +
 drivers/dax/fsdev.c  | 242 +++++++++++++++++++++++++++++++++++++++++++
 fs/dax.c             |   1 +
 include/linux/dax.h  |   5 +
 7 files changed, 267 insertions(+)
 create mode 100644 drivers/dax/fsdev.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 0d044a58cbfe..10aa5120d93f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7188,6 +7188,14 @@ 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>
diff --git a/drivers/dax/Makefile b/drivers/dax/Makefile
index 5ed5c39857c8..3bae252fd1bf 100644
--- a/drivers/dax/Makefile
+++ b/drivers/dax/Makefile
@@ -5,10 +5,16 @@ obj-$(CONFIG_DEV_DAX_KMEM) += kmem.o
 obj-$(CONFIG_DEV_DAX_PMEM) += dax_pmem.o
 obj-$(CONFIG_DEV_DAX_CXL) += dax_cxl.o
 
+# fsdev_dax: fs-dax compatible devdax driver (needs DEV_DAX and FS_DAX)
+ifeq ($(CONFIG_FS_DAX),y)
+obj-$(CONFIG_DEV_DAX) += fsdev_dax.o
+endif
+
 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/
diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index a73f54eac567..e79daf825b52 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -81,6 +81,10 @@ static int dax_match_type(const struct dax_device_driver *dax_drv, struct device
 	    !IS_ENABLED(CONFIG_DEV_DAX_KMEM))
 		return 1;
 
+	/* fsdev driver can also bind to device-type dax devices */
+	if (dax_drv->type == DAXDRV_FSDEV_TYPE && type == DAXDRV_DEVICE_TYPE)
+		return 1;
+
 	return 0;
 }
 
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index cbbf64443098..880bdf7e72d7 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -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 {
diff --git a/drivers/dax/fsdev.c b/drivers/dax/fsdev.c
new file mode 100644
index 000000000000..29b7345f65b1
--- /dev/null
+++ b/drivers/dax/fsdev.c
@@ -0,0 +1,242 @@
+// 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 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;
+	u64 data_offset = 0;
+	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;
+		}
+	}
+
+	/*
+	 * FS-DAX compatible mode: Use MEMORY_DEVICE_FS_DAX type and
+	 * do NOT set vmemmap_shift. This leaves folios at order-0,
+	 * allowing fs-dax to dynamically create compound folios as needed
+	 * (similar to pmem behavior).
+	 */
+	pgmap->type = MEMORY_DEVICE_FS_DAX;
+	pgmap->ops = &fsdev_pagemap_ops;
+	pgmap->owner = dev_dax;
+
+	/*
+	 * CRITICAL DIFFERENCE from device.c:
+	 * We do NOT set vmemmap_shift here, even if align > PAGE_SIZE.
+	 * This ensures folios remain order-0 and are compatible with
+	 * fs-dax's folio management.
+	 */
+
+	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).
+	 */
+	fsdev_clear_folio_state(dev_dax);
+
+	/* 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;
+
+		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);
diff --git a/fs/dax.c b/fs/dax.c
index 7d7bbfb32c41..85a4b428e72b 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -416,6 +416,7 @@ int dax_folio_reset_order(struct folio *folio)
 
 	return order;
 }
+EXPORT_SYMBOL_GPL(dax_folio_reset_order);
 
 static inline unsigned long dax_folio_put(struct folio *folio)
 {
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 9d624f4d9df6..fe1315135fdd 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -51,6 +51,10 @@ struct dax_holder_operations {
 
 #if IS_ENABLED(CONFIG_DAX)
 struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
+
+#if IS_ENABLED(CONFIG_DEV_DAX_FS)
+struct dax_device *inode_dax(struct inode *inode);
+#endif
 void *dax_holder(struct dax_device *dax_dev);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
@@ -153,6 +157,7 @@ static inline void fs_put_dax(struct dax_device *dax_dev, void *holder)
 #if IS_ENABLED(CONFIG_FS_DAX)
 int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc);
+int dax_folio_reset_order(struct folio *folio);
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
 struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
-- 
2.52.0

[PATCH V4 04/19] dax: Save the kva from memremap

[John Groves]

Save the kva from memremap because we need it for iomap rw support.

Prior to famfs, there were no iomap users of /dev/dax - so the virtual
address from memremap was not needed.

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/dax-private.h | 9 +++++++--
 drivers/dax/fsdev.c       | 1 +
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index 0867115aeef2..f3cf0a664f1b 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -67,8 +67,12 @@ struct dev_dax_range {
 /**
  * struct dev_dax - instance data for a subdivision of a dax region, and
  * data while the device is activated in the driver.
- * @region - parent region
- * @dax_dev - core dax functionality
+<<<<<<< Conflict 1 of 1
++++++++ Contents of side #1
+ * @region: parent region
+ * @dax_dev: core dax functionality
+ * @virt_addr: kva from memremap; used by fsdev_dax
+ * @align: alignment of this instance
  * @target_node: effective numa node if dev_dax memory range is onlined
  * @dyn_id: is this a dynamic or statically created instance
  * @id: ida allocated id when the dax_region is not static
@@ -81,6 +85,7 @@ struct dev_dax_range {
 struct dev_dax {
 	struct dax_region *region;
 	struct dax_device *dax_dev;
+	void *virt_addr;
 	unsigned int align;
 	int target_node;
 	bool dyn_id;
diff --git a/drivers/dax/fsdev.c b/drivers/dax/fsdev.c
index 29b7345f65b1..72f78f606e06 100644
--- a/drivers/dax/fsdev.c
+++ b/drivers/dax/fsdev.c
@@ -201,6 +201,7 @@ static int fsdev_dax_probe(struct dev_dax *dev_dax)
 		pr_debug("%s: offset detected phys=%llx pgmap_phys=%llx offset=%llx\n",
 		       __func__, phys, pgmap_phys, data_offset);
 	}
+	dev_dax->virt_addr = addr + data_offset;
 
 	inode = dax_inode(dax_dev);
 	cdev = inode->i_cdev;
-- 
2.52.0

[PATCH V4 05/19] dax: Add dax_operations for use by fs-dax on fsdev dax

[John Groves]

From: John Groves <John@Groves.net>

fsdev: Add dax_operations for use by famfs

- These methods are based on pmem_dax_ops from drivers/nvdimm/pmem.c
- fsdev_dax_direct_access() returns the hpa, pfn and kva. The kva was
  newly stored as dev_dax->virt_addr by dev_dax_probe().
- The hpa/pfn are used for mmap (dax_iomap_fault()), and the kva is used
  for read/write (dax_iomap_rw())
- fsdev_dax_recovery_write() and dev_dax_zero_page_range() have not been
  tested yet. I'm looking for suggestions as to how to test those.
- dax-private.h: add dev_dax->cached_size, which fsdev needs to
  remember. The dev_dax size cannot change while a driver is bound
  (dev_dax_resize returns -EBUSY if dev->driver is set). Caching the size
  at probe time allows fsdev's direct_access path can use it without
  acquiring dax_dev_rwsem (which isn't exported anyway).

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/dax-private.h |  1 +
 drivers/dax/fsdev.c       | 80 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)

diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
index f3cf0a664f1b..164dd5b9d933 100644
--- a/drivers/dax/dax-private.h
+++ b/drivers/dax/dax-private.h
@@ -86,6 +86,7 @@ struct dev_dax {
 	struct dax_region *region;
 	struct dax_device *dax_dev;
 	void *virt_addr;
+	u64 cached_size;
 	unsigned int align;
 	int target_node;
 	bool dyn_id;
diff --git a/drivers/dax/fsdev.c b/drivers/dax/fsdev.c
index 72f78f606e06..f58c88de7a4d 100644
--- a/drivers/dax/fsdev.c
+++ b/drivers/dax/fsdev.c
@@ -28,6 +28,81 @@
  * - No mmap support - all access is through fs-dax/iomap
  */
 
+static void fsdev_write_dax(void *pmem_addr, struct page *page,
+		unsigned int off, unsigned int len)
+{
+	while (len) {
+		void *mem = kmap_local_page(page);
+		unsigned int chunk = min_t(unsigned int, len, PAGE_SIZE - off);
+
+		memcpy_flushcache(pmem_addr, mem + off, chunk);
+		kunmap_local(mem);
+		len -= chunk;
+		off = 0;
+		page++;
+		pmem_addr += chunk;
+	}
+}
+
+static long __fsdev_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
+			long nr_pages, enum dax_access_mode mode, void **kaddr,
+			unsigned long *pfn)
+{
+	struct dev_dax *dev_dax = dax_get_private(dax_dev);
+	size_t size = nr_pages << PAGE_SHIFT;
+	size_t offset = pgoff << PAGE_SHIFT;
+	void *virt_addr = dev_dax->virt_addr + offset;
+	phys_addr_t phys;
+	unsigned long local_pfn;
+
+	WARN_ON(!dev_dax->virt_addr);
+
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, nr_pages << PAGE_SHIFT);
+
+	if (kaddr)
+		*kaddr = virt_addr;
+
+	local_pfn = PHYS_PFN(phys);
+	if (pfn)
+		*pfn = local_pfn;
+
+	/*
+	 * Use cached_size which was computed at probe time. The size cannot
+	 * change while the driver is bound (resize returns -EBUSY).
+	 */
+	return PHYS_PFN(min(size, dev_dax->cached_size - offset));
+}
+
+static int fsdev_dax_zero_page_range(struct dax_device *dax_dev,
+			pgoff_t pgoff, size_t nr_pages)
+{
+	void *kaddr;
+
+	WARN_ONCE(nr_pages > 1, "%s: nr_pages > 1\n", __func__);
+	__fsdev_dax_direct_access(dax_dev, pgoff, 1, DAX_ACCESS, &kaddr, NULL);
+	fsdev_write_dax(kaddr, ZERO_PAGE(0), 0, PAGE_SIZE);
+	return 0;
+}
+
+static long fsdev_dax_direct_access(struct dax_device *dax_dev,
+		  pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
+		  void **kaddr, unsigned long *pfn)
+{
+	return __fsdev_dax_direct_access(dax_dev, pgoff, nr_pages, mode,
+					 kaddr, pfn);
+}
+
+static size_t fsdev_dax_recovery_write(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 const struct dax_operations dev_dax_ops = {
+	.direct_access = fsdev_dax_direct_access,
+	.zero_page_range = fsdev_dax_zero_page_range,
+	.recovery_write = fsdev_dax_recovery_write,
+};
 
 static void fsdev_cdev_del(void *cdev)
 {
@@ -163,6 +238,11 @@ static int fsdev_dax_probe(struct dev_dax *dev_dax)
 		}
 	}
 
+	/* Cache size now; it cannot change while driver is bound */
+	dev_dax->cached_size = 0;
+	for (i = 0; i < dev_dax->nr_range; i++)
+		dev_dax->cached_size += range_len(&dev_dax->ranges[i].range);
+
 	/*
 	 * FS-DAX compatible mode: Use MEMORY_DEVICE_FS_DAX type and
 	 * do NOT set vmemmap_shift. This leaves folios at order-0,
-- 
2.52.0

[PATCH V4 06/19] dax: Add dax_set_ops() for setting dax_operations at bind time

[John Groves]

From: John Groves <John@Groves.net>

Add a new dax_set_ops() function that allows drivers to set the
dax_operations after the dax_device has been allocated. This is needed
for fsdev_dax where the operations need to be set during probe and
cleared during unbind.

The fsdev driver uses devm_add_action_or_reset() for cleanup consistency,
avoiding the complexity of mixing devm-managed resources with manual
cleanup in a remove() callback. This ensures cleanup happens automatically
in the correct reverse order when the device is unbound.

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/fsdev.c | 16 ++++++++++++++++
 drivers/dax/super.c | 38 +++++++++++++++++++++++++++++++++++++-
 include/linux/dax.h |  1 +
 3 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/drivers/dax/fsdev.c b/drivers/dax/fsdev.c
index f58c88de7a4d..d658942b7143 100644
--- a/drivers/dax/fsdev.c
+++ b/drivers/dax/fsdev.c
@@ -114,6 +114,13 @@ static void fsdev_kill(void *dev_dax)
 	kill_dev_dax(dev_dax);
 }
 
+static void fsdev_clear_ops(void *data)
+{
+	struct dev_dax *dev_dax = data;
+
+	dax_set_ops(dev_dax->dax_dev, NULL);
+}
+
 /*
  * Page map operations for FS-DAX mode
  * Similar to fsdax_pagemap_ops in drivers/nvdimm/pmem.c
@@ -296,6 +303,15 @@ static int fsdev_dax_probe(struct dev_dax *dev_dax)
 	if (rc)
 		return rc;
 
+	/* Set the dax operations for fs-dax access path */
+	rc = dax_set_ops(dax_dev, &dev_dax_ops);
+	if (rc)
+		return rc;
+
+	rc = devm_add_action_or_reset(dev, fsdev_clear_ops, dev_dax);
+	if (rc)
+		return rc;
+
 	run_dax(dax_dev);
 	return devm_add_action_or_reset(dev, fsdev_kill, dev_dax);
 }
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index c00b9dff4a06..ba0b4cd18a77 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -157,6 +157,9 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 	if (!dax_alive(dax_dev))
 		return -ENXIO;
 
+	if (!dax_dev->ops)
+		return -EOPNOTSUPP;
+
 	if (nr_pages < 0)
 		return -EINVAL;
 
@@ -207,6 +210,10 @@ int dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 
 	if (!dax_alive(dax_dev))
 		return -ENXIO;
+
+	if (!dax_dev->ops)
+		return -EOPNOTSUPP;
+
 	/*
 	 * There are no callers that want to zero more than one page as of now.
 	 * Once users are there, this check can be removed after the
@@ -223,7 +230,7 @@ EXPORT_SYMBOL_GPL(dax_zero_page_range);
 size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *iter)
 {
-	if (!dax_dev->ops->recovery_write)
+	if (!dax_dev->ops || !dax_dev->ops->recovery_write)
 		return 0;
 	return dax_dev->ops->recovery_write(dax_dev, pgoff, addr, bytes, iter);
 }
@@ -307,6 +314,35 @@ void set_dax_nomc(struct dax_device *dax_dev)
 }
 EXPORT_SYMBOL_GPL(set_dax_nomc);
 
+/**
+ * dax_set_ops - set the dax_operations for a dax_device
+ * @dax_dev: the dax_device to configure
+ * @ops: the operations to set (may be NULL to clear)
+ *
+ * This allows drivers to set the dax_operations after the dax_device
+ * has been allocated. This is needed when the device is created before
+ * the driver that needs specific ops is bound (e.g., fsdev_dax binding
+ * to a dev_dax created by hmem).
+ *
+ * When setting non-NULL ops, fails if ops are already set (returns -EBUSY).
+ * When clearing ops (NULL), always succeeds.
+ *
+ * Return: 0 on success, -EBUSY if ops already set
+ */
+int dax_set_ops(struct dax_device *dax_dev, const struct dax_operations *ops)
+{
+	if (ops) {
+		/* Setting ops: fail if already set */
+		if (cmpxchg(&dax_dev->ops, NULL, ops) != NULL)
+			return -EBUSY;
+	} else {
+		/* Clearing ops: always allowed */
+		dax_dev->ops = NULL;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dax_set_ops);
+
 bool dax_alive(struct dax_device *dax_dev)
 {
 	lockdep_assert_held(&dax_srcu);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index fe1315135fdd..5aaaca135737 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -247,6 +247,7 @@ static inline void dax_break_layout_final(struct inode *inode)
 
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
+int dax_set_ops(struct dax_device *dax_dev, const struct dax_operations *ops);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
 		enum dax_access_mode mode, void **kaddr, unsigned long *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
-- 
2.52.0

[PATCH V4 07/19] dax: Add fs_dax_get() func to prepare dax for fs-dax usage

[John Groves]

The fs_dax_get() function should be called by fs-dax file systems after
opening a fsdev dax device. This adds holder_operations, which provides
a memory failure callback path and effects exclusivity between callers
of fs_dax_get().

fs_dax_get() is specific to fsdev_dax, so it checks the driver type
(which required touching bus.[ch]). fs_dax_get() fails if fsdev_dax is
not bound to the memory.

This function serves the same role as fs_dax_get_by_bdev(), which dax
file systems call after opening the pmem block device.

This can't be located in fsdev.c because struct dax_device is opaque
there.

This will be called by fs/fuse/famfs.c in a subsequent commit.

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/bus.c   |  2 --
 drivers/dax/bus.h   |  2 ++
 drivers/dax/super.c | 58 ++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/dax.h | 20 ++++++++++------
 4 files changed, 72 insertions(+), 10 deletions(-)

diff --git a/drivers/dax/bus.c b/drivers/dax/bus.c
index e79daf825b52..01402d5103ef 100644
--- a/drivers/dax/bus.c
+++ b/drivers/dax/bus.c
@@ -39,8 +39,6 @@ static int dax_bus_uevent(const struct device *dev, struct kobj_uevent_env *env)
 	return add_uevent_var(env, "MODALIAS=" DAX_DEVICE_MODALIAS_FMT, 0);
 }
 
-#define to_dax_drv(__drv)	container_of_const(__drv, struct dax_device_driver, drv)
-
 static struct dax_id *__dax_match_id(const struct dax_device_driver *dax_drv,
 		const char *dev_name)
 {
diff --git a/drivers/dax/bus.h b/drivers/dax/bus.h
index 880bdf7e72d7..dc6f112ac4a4 100644
--- a/drivers/dax/bus.h
+++ b/drivers/dax/bus.h
@@ -42,6 +42,8 @@ struct dax_device_driver {
 	void (*remove)(struct dev_dax *dev);
 };
 
+#define to_dax_drv(__drv) container_of_const(__drv, struct dax_device_driver, drv)
+
 int __dax_driver_register(struct dax_device_driver *dax_drv,
 		struct module *module, const char *mod_name);
 #define dax_driver_register(driver) \
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index ba0b4cd18a77..00c330ef437c 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/cacheinfo.h>
 #include "dax-private.h"
+#include "bus.h"
 
 /**
  * struct dax_device - anchor object for dax services
@@ -111,6 +112,10 @@ struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
 }
 EXPORT_SYMBOL_GPL(fs_dax_get_by_bdev);
 
+#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
+
+#if IS_ENABLED(CONFIG_FS_DAX)
+
 void fs_put_dax(struct dax_device *dax_dev, void *holder)
 {
 	if (dax_dev && holder &&
@@ -119,7 +124,58 @@ void fs_put_dax(struct dax_device *dax_dev, void *holder)
 	put_dax(dax_dev);
 }
 EXPORT_SYMBOL_GPL(fs_put_dax);
-#endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
+
+/**
+ * fs_dax_get() - get ownership of a devdax via holder/holder_ops
+ *
+ * fs-dax file systems call this function to prepare to use a devdax device for
+ * fsdax. This is like fs_dax_get_by_bdev(), but the caller already has struct
+ * dev_dax (and there is no bdev). The holder makes this exclusive.
+ *
+ * @dax_dev: dev to be prepared for fs-dax usage
+ * @holder: filesystem or mapped device inside the dax_device
+ * @hops: operations for the inner holder
+ *
+ * Returns: 0 on success, <0 on failure
+ */
+int fs_dax_get(struct dax_device *dax_dev, void *holder,
+	const struct dax_holder_operations *hops)
+{
+	struct dev_dax *dev_dax;
+	struct dax_device_driver *dax_drv;
+	int id;
+
+	id = dax_read_lock();
+	if (!dax_dev || !dax_alive(dax_dev) || !igrab(&dax_dev->inode)) {
+		dax_read_unlock(id);
+		return -ENODEV;
+	}
+	dax_read_unlock(id);
+
+	/* Verify the device is bound to fsdev_dax driver */
+	dev_dax = dax_get_private(dax_dev);
+	if (!dev_dax || !dev_dax->dev.driver) {
+		iput(&dax_dev->inode);
+		return -ENODEV;
+	}
+
+	dax_drv = to_dax_drv(dev_dax->dev.driver);
+	if (dax_drv->type != DAXDRV_FSDEV_TYPE) {
+		iput(&dax_dev->inode);
+		return -EOPNOTSUPP;
+	}
+
+	if (cmpxchg(&dax_dev->holder_data, NULL, holder)) {
+		iput(&dax_dev->inode);
+		return -EBUSY;
+	}
+
+	dax_dev->holder_ops = hops;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(fs_dax_get);
+#endif /* CONFIG_FS_DAX */
 
 enum dax_device_flags {
 	/* !alive + rcu grace period == no new operations / mappings */
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 5aaaca135737..6897c5736543 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -52,9 +52,6 @@ struct dax_holder_operations {
 #if IS_ENABLED(CONFIG_DAX)
 struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
 
-#if IS_ENABLED(CONFIG_DEV_DAX_FS)
-struct dax_device *inode_dax(struct inode *inode);
-#endif
 void *dax_holder(struct dax_device *dax_dev);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
@@ -134,7 +131,6 @@ int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
 void dax_remove_host(struct gendisk *disk);
 struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev, u64 *start_off,
 		void *holder, const struct dax_holder_operations *ops);
-void fs_put_dax(struct dax_device *dax_dev, void *holder);
 #else
 static inline int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk)
 {
@@ -149,12 +145,13 @@ static inline struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev,
 {
 	return NULL;
 }
-static inline void fs_put_dax(struct dax_device *dax_dev, void *holder)
-{
-}
 #endif /* CONFIG_BLOCK && CONFIG_FS_DAX */
 
 #if IS_ENABLED(CONFIG_FS_DAX)
+void fs_put_dax(struct dax_device *dax_dev, void *holder);
+int fs_dax_get(struct dax_device *dax_dev, void *holder,
+	       const struct dax_holder_operations *hops);
+struct dax_device *inode_dax(struct inode *inode);
 int dax_writeback_mapping_range(struct address_space *mapping,
 		struct dax_device *dax_dev, struct writeback_control *wbc);
 int dax_folio_reset_order(struct folio *folio);
@@ -168,6 +165,15 @@ dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
 void dax_unlock_mapping_entry(struct address_space *mapping,
 		unsigned long index, dax_entry_t cookie);
 #else
+static inline void fs_put_dax(struct dax_device *dax_dev, void *holder)
+{
+}
+
+static inline int fs_dax_get(struct dax_device *dax_dev, void *holder,
+			     const struct dax_holder_operations *hops)
+{
+	return -EOPNOTSUPP;
+}
 static inline struct page *dax_layout_busy_page(struct address_space *mapping)
 {
 	return NULL;
-- 
2.52.0

[PATCH V4 08/19] dax: export dax_dev_get()

[John Groves]

famfs needs to look up a dax_device by dev_t when resolving fmap
entries that reference character dax devices.

Signed-off-by: John Groves <john@groves.net>
---
 drivers/dax/super.c | 3 ++-
 include/linux/dax.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 00c330ef437c..d097561d78db 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -513,7 +513,7 @@ static int dax_set(struct inode *inode, void *data)
 	return 0;
 }
 
-static struct dax_device *dax_dev_get(dev_t devt)
+struct dax_device *dax_dev_get(dev_t devt)
 {
 	struct dax_device *dax_dev;
 	struct inode *inode;
@@ -536,6 +536,7 @@ static struct dax_device *dax_dev_get(dev_t devt)
 
 	return dax_dev;
 }
+EXPORT_SYMBOL_GPL(dax_dev_get);
 
 struct dax_device *alloc_dax(void *private, const struct dax_operations *ops)
 {
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 6897c5736543..1ef9b03f9671 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -55,6 +55,7 @@ struct dax_device *alloc_dax(void *private, const struct dax_operations *ops);
 void *dax_holder(struct dax_device *dax_dev);
 void put_dax(struct dax_device *dax_dev);
 void kill_dax(struct dax_device *dax_dev);
+struct dax_device *dax_dev_get(dev_t devt);
 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);
-- 
2.52.0

[PATCH V4 09/19] famfs_fuse: magic.h: Add famfs magic numbers

[John Groves]

Famfs distinguishes between its on-media and in-memory superblocks. This
reserves the numbers, but they are only used by the user space
components of famfs.

Signed-off-by: John Groves <john@groves.net>
---
 include/uapi/linux/magic.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index 638ca21b7a90..712b097bf2a5 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -38,6 +38,8 @@
 #define OVERLAYFS_SUPER_MAGIC	0x794c7630
 #define FUSE_SUPER_MAGIC	0x65735546
 #define BCACHEFS_SUPER_MAGIC	0xca451a4e
+#define FAMFS_SUPER_MAGIC	0x87b282ff
+#define FAMFS_STATFS_MAGIC      0x87b282fd
 
 #define MINIX_SUPER_MAGIC	0x137F		/* minix v1 fs, 14 char names */
 #define MINIX_SUPER_MAGIC2	0x138F		/* minix v1 fs, 30 char names */
-- 
2.52.0

[PATCH V4 10/19] famfs_fuse: Update macro s/FUSE_IS_DAX/FUSE_IS_VIRTIO_DAX/

[John Groves]

Virtio_fs now needs to determine if an inode is DAX && not famfs.
This relaces the FUSE_IS_DAX() macro with FUSE_IS_VIRTIO_DAX(),
in preparation for famfs in later commits. The dummy
fuse_file_famfs() macro will be replaced with a working
function.

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: John Groves <john@groves.net>
---
 fs/fuse/dir.c    |  2 +-
 fs/fuse/file.c   | 13 ++++++++-----
 fs/fuse/fuse_i.h |  9 ++++++++-
 fs/fuse/inode.c  |  4 ++--
 fs/fuse/iomode.c |  2 +-
 5 files changed, 20 insertions(+), 10 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 4b6b3d2758ff..1400c9d733ba 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -2153,7 +2153,7 @@ int fuse_do_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
 		is_truncate = true;
 	}
 
-	if (FUSE_IS_DAX(inode) && is_truncate) {
+	if (FUSE_IS_VIRTIO_DAX(fi) && is_truncate) {
 		filemap_invalidate_lock(mapping);
 		fault_blocked = true;
 		err = fuse_dax_break_layouts(inode, 0, -1);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 01bc894e9c2b..093569033ed1 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -252,7 +252,7 @@ static int fuse_open(struct inode *inode, struct file *file)
 	int err;
 	bool is_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc;
 	bool is_wb_truncate = is_truncate && fc->writeback_cache;
-	bool dax_truncate = is_truncate && FUSE_IS_DAX(inode);
+	bool dax_truncate = is_truncate && FUSE_IS_VIRTIO_DAX(fi);
 
 	if (fuse_is_bad(inode))
 		return -EIO;
@@ -1812,11 +1812,12 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
 	struct inode *inode = file_inode(file);
+	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	if (fuse_is_bad(inode))
 		return -EIO;
 
-	if (FUSE_IS_DAX(inode))
+	if (FUSE_IS_VIRTIO_DAX(fi))
 		return fuse_dax_read_iter(iocb, to);
 
 	/* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
@@ -1833,11 +1834,12 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct fuse_file *ff = file->private_data;
 	struct inode *inode = file_inode(file);
+	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	if (fuse_is_bad(inode))
 		return -EIO;
 
-	if (FUSE_IS_DAX(inode))
+	if (FUSE_IS_VIRTIO_DAX(fi))
 		return fuse_dax_write_iter(iocb, from);
 
 	/* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
@@ -2370,10 +2372,11 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 	struct fuse_file *ff = file->private_data;
 	struct fuse_conn *fc = ff->fm->fc;
 	struct inode *inode = file_inode(file);
+	struct fuse_inode *fi = get_fuse_inode(inode);
 	int rc;
 
 	/* DAX mmap is superior to direct_io mmap */
-	if (FUSE_IS_DAX(inode))
+	if (FUSE_IS_VIRTIO_DAX(fi))
 		return fuse_dax_mmap(file, vma);
 
 	/*
@@ -2934,7 +2937,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 		.mode = mode
 	};
 	int err;
-	bool block_faults = FUSE_IS_DAX(inode) &&
+	bool block_faults = FUSE_IS_VIRTIO_DAX(fi) &&
 		(!(mode & FALLOC_FL_KEEP_SIZE) ||
 		 (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)));
 
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 7f16049387d1..45e108dec771 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1508,7 +1508,14 @@ void fuse_free_conn(struct fuse_conn *fc);
 
 /* dax.c */
 
-#define FUSE_IS_DAX(inode) (IS_ENABLED(CONFIG_FUSE_DAX) && IS_DAX(inode))
+static inline bool fuse_file_famfs(struct fuse_inode *fuse_inode) /* Will be superseded */
+{
+	(void)fuse_inode;
+	return false;
+}
+#define FUSE_IS_VIRTIO_DAX(fuse_inode) (IS_ENABLED(CONFIG_FUSE_DAX)	\
+					&& IS_DAX(&fuse_inode->inode)  \
+					&& !fuse_file_famfs(fuse_inode))
 
 ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to);
 ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 819e50d66622..ed667920997f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -162,7 +162,7 @@ static void fuse_evict_inode(struct inode *inode)
 	/* Will write inode on close/munmap and in all other dirtiers */
 	WARN_ON(inode_state_read_once(inode) & I_DIRTY_INODE);
 
-	if (FUSE_IS_DAX(inode))
+	if (FUSE_IS_VIRTIO_DAX(fi))
 		dax_break_layout_final(inode);
 
 	truncate_inode_pages_final(&inode->i_data);
@@ -170,7 +170,7 @@ static void fuse_evict_inode(struct inode *inode)
 	if (inode->i_sb->s_flags & SB_ACTIVE) {
 		struct fuse_conn *fc = get_fuse_conn(inode);
 
-		if (FUSE_IS_DAX(inode))
+		if (FUSE_IS_VIRTIO_DAX(fi))
 			fuse_dax_inode_cleanup(inode);
 		if (fi->nlookup) {
 			fuse_queue_forget(fc, fi->forget, fi->nodeid,
diff --git a/fs/fuse/iomode.c b/fs/fuse/iomode.c
index 3728933188f3..31ee7f3304c6 100644
--- a/fs/fuse/iomode.c
+++ b/fs/fuse/iomode.c
@@ -203,7 +203,7 @@ int fuse_file_io_open(struct file *file, struct inode *inode)
 	 * io modes are not relevant with DAX and with server that does not
 	 * implement open.
 	 */
-	if (FUSE_IS_DAX(inode) || !ff->args)
+	if (FUSE_IS_VIRTIO_DAX(fi) || !ff->args)
 		return 0;
 
 	/*
-- 
2.52.0

[PATCH V4 11/19] famfs_fuse: Basic fuse kernel ABI enablement for famfs

[John Groves]

This patch starts the kernel ABI enablement of famfs in fuse.

- Kconfig: Add FUSE_FAMFS_DAX config parameter, to control
  compilation of famfs within fuse.
- FUSE_DAX_FMAP flag in INIT request/reply
- fuse_conn->famfs_iomap (enable famfs-mapped files) to denote a
  famfs-enabled connection

Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: John Groves <john@groves.net>
---
 fs/fuse/Kconfig           | 14 ++++++++++++++
 fs/fuse/fuse_i.h          |  3 +++
 fs/fuse/inode.c           |  6 ++++++
 include/uapi/linux/fuse.h |  5 +++++
 4 files changed, 28 insertions(+)

diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 3a4ae632c94a..5ca9fae62c7b 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -76,3 +76,17 @@ config FUSE_IO_URING
 
 	  If you want to allow fuse server/client communication through io-uring,
 	  answer Y
+
+config FUSE_FAMFS_DAX
+	bool "FUSE support for fs-dax filesystems backed by devdax"
+	depends on FUSE_FS
+	depends on DEV_DAX
+	depends on FS_DAX
+	default FUSE_FS
+	help
+	  This enables the fabric-attached memory file system (famfs),
+	  which enables formatting devdax memory as a file system. Famfs
+	  is primarily intended for scale-out shared access to
+	  disaggregated memory.
+
+	  To enable famfs or other fuse/fs-dax file systems, answer Y
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 45e108dec771..2839efb219a9 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -921,6 +921,9 @@ struct fuse_conn {
 	/* Is synchronous FUSE_INIT allowed? */
 	unsigned int sync_init:1;
 
+	/* dev_dax_iomap support for famfs */
+	unsigned int famfs_iomap:1;
+
 	/* Use io_uring for communication */
 	unsigned int io_uring;
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index ed667920997f..acabf92a11f8 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1456,6 +1456,10 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 
 			if (flags & FUSE_REQUEST_TIMEOUT)
 				timeout = arg->request_timeout;
+
+			if (IS_ENABLED(CONFIG_FUSE_FAMFS_DAX) &&
+			    flags & FUSE_DAX_FMAP)
+				fc->famfs_iomap = 1;
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1517,6 +1521,8 @@ static struct fuse_init_args *fuse_new_init(struct fuse_mount *fm)
 		flags |= FUSE_SUBMOUNTS;
 	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
 		flags |= FUSE_PASSTHROUGH;
+	if (IS_ENABLED(CONFIG_FUSE_FAMFS_DAX))
+		flags |= FUSE_DAX_FMAP;
 
 	/*
 	 * This is just an information flag for fuse server. No need to check
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index c13e1f9a2f12..25686f088e6a 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -240,6 +240,9 @@
  *  - add FUSE_COPY_FILE_RANGE_64
  *  - add struct fuse_copy_file_range_out
  *  - add FUSE_NOTIFY_PRUNE
+ *
+ *  7.46
+ *  - Add FUSE_DAX_FMAP capability - ability to handle in-kernel fsdax maps
  */
 
 #ifndef _LINUX_FUSE_H
@@ -448,6 +451,7 @@ struct fuse_file_lock {
  * FUSE_OVER_IO_URING: Indicate that client supports io-uring
  * FUSE_REQUEST_TIMEOUT: kernel supports timing out requests.
  *			 init_out.request_timeout contains the timeout (in secs)
+ * FUSE_DAX_FMAP: kernel supports dev_dax_iomap (aka famfs) fmaps
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -495,6 +499,7 @@ struct fuse_file_lock {
 #define FUSE_ALLOW_IDMAP	(1ULL << 40)
 #define FUSE_OVER_IO_URING	(1ULL << 41)
 #define FUSE_REQUEST_TIMEOUT	(1ULL << 42)
+#define FUSE_DAX_FMAP		(1ULL << 43)
 
 /**
  * CUSE INIT request/reply flags
-- 
2.52.0

[PATCH V4 12/19] famfs_fuse: Plumb the GET_FMAP message/response

[John Groves]

Upon completion of an OPEN, if we're in famfs-mode we do a GET_FMAP to
retrieve and cache up the file-to-dax map in the kernel. If this
succeeds, read/write/mmap are resolved direct-to-dax with no upcalls.

Signed-off-by: John Groves <john@groves.net>
---
 MAINTAINERS               |  8 +++++
 fs/fuse/Makefile          |  1 +
 fs/fuse/famfs.c           | 74 +++++++++++++++++++++++++++++++++++++++
 fs/fuse/file.c            | 14 +++++++-
 fs/fuse/fuse_i.h          | 70 +++++++++++++++++++++++++++++++++---
 fs/fuse/inode.c           |  8 ++++-
 fs/fuse/iomode.c          |  2 +-
 include/uapi/linux/fuse.h |  7 ++++
 8 files changed, 176 insertions(+), 8 deletions(-)
 create mode 100644 fs/fuse/famfs.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 10aa5120d93f..e3d0aa5eb361 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10379,6 +10379,14 @@ F:	fs/fuse/
 F:	include/uapi/linux/fuse.h
 F:	tools/testing/selftests/filesystems/fuse/
 
+FUSE [FAMFS Fabric-Attached Memory File System]
+M:	John Groves <jgroves@micron.com>
+M:	John Groves <John@Groves.net>
+L:	linux-cxl@vger.kernel.org
+L:	linux-fsdevel@vger.kernel.org
+S:	Supported
+F:	fs/fuse/famfs.c
+
 FUTEX SUBSYSTEM
 M:	Thomas Gleixner <tglx@kernel.org>
 M:	Ingo Molnar <mingo@redhat.com>
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 22ad9538dfc4..3f8dcc8cbbd0 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -17,5 +17,6 @@ fuse-$(CONFIG_FUSE_DAX) += dax.o
 fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o backing.o
 fuse-$(CONFIG_SYSCTL) += sysctl.o
 fuse-$(CONFIG_FUSE_IO_URING) += dev_uring.o
+fuse-$(CONFIG_FUSE_FAMFS_DAX) += famfs.o
 
 virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
new file mode 100644
index 000000000000..615819cc922d
--- /dev/null
+++ b/fs/fuse/famfs.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * famfs - dax file system for shared fabric-attached memory
+ *
+ * Copyright 2023-2026 Micron Technology, Inc.
+ *
+ * This file system, originally based on ramfs the dax support from xfs,
+ * is intended to allow multiple host systems to mount a common file system
+ * view of dax files that map to shared memory.
+ */
+
+#include <linux/cleanup.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/dax.h>
+#include <linux/iomap.h>
+#include <linux/path.h>
+#include <linux/namei.h>
+#include <linux/string.h>
+
+#include "fuse_i.h"
+
+
+#define FMAP_BUFSIZE PAGE_SIZE
+
+int
+fuse_get_fmap(struct fuse_mount *fm, struct inode *inode)
+{
+	void *fmap_buf __free(kfree) = NULL;
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	size_t fmap_bufsize = FMAP_BUFSIZE;
+	u64 nodeid = get_node_id(inode);
+	ssize_t fmap_size;
+	int rc;
+
+	FUSE_ARGS(args);
+
+	/* Don't retrieve if we already have the famfs metadata */
+	if (fi->famfs_meta)
+		return 0;
+
+	fmap_buf = kzalloc(FMAP_BUFSIZE, GFP_KERNEL);
+	if (!fmap_buf)
+		return -EIO;
+
+	args.opcode = FUSE_GET_FMAP;
+	args.nodeid = nodeid;
+
+	/* Variable-sized output buffer
+	 * this causes fuse_simple_request() to return the size of the
+	 * output payload
+	 */
+	args.out_argvar = true;
+	args.out_numargs = 1;
+	args.out_args[0].size = fmap_bufsize;
+	args.out_args[0].value = fmap_buf;
+
+	/* Send GET_FMAP command */
+	rc = fuse_simple_request(fm, &args);
+	if (rc < 0) {
+		pr_err("%s: err=%d from fuse_simple_request()\n",
+		       __func__, rc);
+		return rc;
+	}
+	fmap_size = rc;
+
+	/* We retrieved the "fmap" (the file's map to memory), but
+	 * we haven't used it yet. A call to famfs_file_init_dax() will be added
+	 * here in a subsequent patch, when we add the ability to attach
+	 * fmaps to files.
+	 */
+
+	return 0;
+}
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 093569033ed1..1f64bf68b5ee 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -277,6 +277,16 @@ static int fuse_open(struct inode *inode, struct file *file)
 	err = fuse_do_open(fm, get_node_id(inode), file, false);
 	if (!err) {
 		ff = file->private_data;
+
+		if ((fm->fc->famfs_iomap) && (S_ISREG(inode->i_mode))) {
+			/* Get the famfs fmap - failure is fatal */
+			err = fuse_get_fmap(fm, inode);
+			if (err) {
+				fuse_sync_release(fi, ff, file->f_flags);
+				goto out_nowrite;
+			}
+		}
+
 		err = fuse_finish_open(inode, file);
 		if (err)
 			fuse_sync_release(fi, ff, file->f_flags);
@@ -284,12 +294,14 @@ static int fuse_open(struct inode *inode, struct file *file)
 			fuse_truncate_update_attr(inode, file);
 	}
 
+out_nowrite:
 	if (is_wb_truncate || dax_truncate)
 		fuse_release_nowrite(inode);
 	if (!err) {
 		if (is_truncate)
 			truncate_pagecache(inode, 0);
-		else if (!(ff->open_flags & FOPEN_KEEP_CACHE))
+		else if (!(ff->open_flags & FOPEN_KEEP_CACHE) &&
+			 !fuse_file_famfs(fi))
 			invalidate_inode_pages2(inode->i_mapping);
 	}
 	if (dax_truncate)
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 2839efb219a9..b66b5ca0bc11 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -223,6 +223,14 @@ struct fuse_inode {
 	 * so preserve the blocksize specified by the server.
 	 */
 	u8 cached_i_blkbits;
+
+#if IS_ENABLED(CONFIG_FUSE_FAMFS_DAX)
+	/* Pointer to the file's famfs metadata. Primary content is the
+	 * in-memory version of the fmap - the map from file's offset range
+	 * to DAX memory
+	 */
+	void *famfs_meta;
+#endif
 };
 
 /** FUSE inode state bits */
@@ -1511,11 +1519,8 @@ void fuse_free_conn(struct fuse_conn *fc);
 
 /* dax.c */
 
-static inline bool fuse_file_famfs(struct fuse_inode *fuse_inode) /* Will be superseded */
-{
-	(void)fuse_inode;
-	return false;
-}
+static inline int fuse_file_famfs(struct fuse_inode *fi); /* forward */
+
 #define FUSE_IS_VIRTIO_DAX(fuse_inode) (IS_ENABLED(CONFIG_FUSE_DAX)	\
 					&& IS_DAX(&fuse_inode->inode)  \
 					&& !fuse_file_famfs(fuse_inode))
@@ -1634,4 +1639,59 @@ extern void fuse_sysctl_unregister(void);
 #define fuse_sysctl_unregister()	do { } while (0)
 #endif /* CONFIG_SYSCTL */
 
+/* famfs.c */
+
+#if IS_ENABLED(CONFIG_FUSE_FAMFS_DAX)
+void __famfs_meta_free(void *map);
+
+/* Set fi->famfs_meta = NULL regardless of prior value */
+static inline void famfs_meta_init(struct fuse_inode *fi)
+{
+	fi->famfs_meta = NULL;
+}
+
+/* Set fi->famfs_meta iff the current value is NULL */
+static inline struct fuse_backing *famfs_meta_set(struct fuse_inode *fi,
+						  void *meta)
+{
+	return cmpxchg(&fi->famfs_meta, NULL, meta);
+}
+
+static inline void famfs_meta_free(struct fuse_inode *fi)
+{
+	famfs_meta_set(fi, NULL);
+}
+
+static inline int fuse_file_famfs(struct fuse_inode *fi)
+{
+	return (READ_ONCE(fi->famfs_meta) != NULL);
+}
+
+int fuse_get_fmap(struct fuse_mount *fm, struct inode *inode);
+
+#else /* !CONFIG_FUSE_FAMFS_DAX */
+
+static inline struct fuse_backing *famfs_meta_set(struct fuse_inode *fi,
+						  void *meta)
+{
+	return NULL;
+}
+
+static inline void famfs_meta_free(struct fuse_inode *fi)
+{
+}
+
+static inline int fuse_file_famfs(struct fuse_inode *fi)
+{
+	return 0;
+}
+
+static inline int
+fuse_get_fmap(struct fuse_mount *fm, struct inode *inode)
+{
+	return 0;
+}
+
+#endif /* CONFIG_FUSE_FAMFS_DAX */
+
 #endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index acabf92a11f8..f2d742d723dc 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -120,6 +120,9 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
 	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
 		fuse_inode_backing_set(fi, NULL);
 
+	if (IS_ENABLED(CONFIG_FUSE_FAMFS_DAX))
+		famfs_meta_set(fi, NULL);
+
 	return &fi->inode;
 
 out_free_forget:
@@ -141,6 +144,9 @@ static void fuse_free_inode(struct inode *inode)
 	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
 		fuse_backing_put(fuse_inode_backing(fi));
 
+	if (S_ISREG(inode->i_mode) && fuse_file_famfs(fi))
+		famfs_meta_free(fi);
+
 	kmem_cache_free(fuse_inode_cachep, fi);
 }
 
@@ -162,7 +168,7 @@ static void fuse_evict_inode(struct inode *inode)
 	/* Will write inode on close/munmap and in all other dirtiers */
 	WARN_ON(inode_state_read_once(inode) & I_DIRTY_INODE);
 
-	if (FUSE_IS_VIRTIO_DAX(fi))
+	if (FUSE_IS_VIRTIO_DAX(fi) || fuse_file_famfs(fi))
 		dax_break_layout_final(inode);
 
 	truncate_inode_pages_final(&inode->i_data);
diff --git a/fs/fuse/iomode.c b/fs/fuse/iomode.c
index 31ee7f3304c6..948148316ef0 100644
--- a/fs/fuse/iomode.c
+++ b/fs/fuse/iomode.c
@@ -203,7 +203,7 @@ int fuse_file_io_open(struct file *file, struct inode *inode)
 	 * io modes are not relevant with DAX and with server that does not
 	 * implement open.
 	 */
-	if (FUSE_IS_VIRTIO_DAX(fi) || !ff->args)
+	if (FUSE_IS_VIRTIO_DAX(fi) || fuse_file_famfs(fi) || !ff->args)
 		return 0;
 
 	/*
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 25686f088e6a..9eff9083d3b5 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -669,6 +669,9 @@ enum fuse_opcode {
 	FUSE_STATX		= 52,
 	FUSE_COPY_FILE_RANGE_64	= 53,
 
+	/* Famfs / devdax opcodes */
+	FUSE_GET_FMAP           = 54,
+
 	/* CUSE specific operations */
 	CUSE_INIT		= 4096,
 
@@ -1313,4 +1316,8 @@ struct fuse_uring_cmd_req {
 	uint8_t padding[6];
 };
 
+/* Famfs fmap message components */
+
+#define FAMFS_FMAP_MAX 32768 /* Largest supported fmap message */
+
 #endif /* _LINUX_FUSE_H */
-- 
2.52.0

[PATCH V4 13/19] famfs_fuse: Create files with famfs fmaps

[John Groves]

On completion of GET_FMAP message/response, setup the full famfs
metadata such that it's possible to handle read/write/mmap directly to
dax. Note that the devdax_iomap plumbing is not in yet...

* Add famfs_kfmap.h: in-memory structures for resolving famfs file maps
  (fmaps) to dax.
* famfs.c: allocate, initialize and free fmaps
* inode.c: only allow famfs mode if the fuse server has CAP_SYS_RAWIO
* Update MAINTAINERS for the new file.

Signed-off-by: John Groves <john@groves.net>
---
 MAINTAINERS               |   1 +
 fs/fuse/famfs.c           | 336 +++++++++++++++++++++++++++++++++++++-
 fs/fuse/famfs_kfmap.h     |  67 ++++++++
 fs/fuse/fuse_i.h          |   8 +-
 fs/fuse/inode.c           |  19 ++-
 include/uapi/linux/fuse.h |  56 +++++++
 6 files changed, 477 insertions(+), 10 deletions(-)
 create mode 100644 fs/fuse/famfs_kfmap.h

diff --git a/MAINTAINERS b/MAINTAINERS
index e3d0aa5eb361..6f8a7c813c2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10386,6 +10386,7 @@ L:	linux-cxl@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
 F:	fs/fuse/famfs.c
+F:	fs/fuse/famfs_kfmap.h
 
 FUTEX SUBSYSTEM
 M:	Thomas Gleixner <tglx@kernel.org>
diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
index 615819cc922d..e3b5f204de82 100644
--- a/fs/fuse/famfs.c
+++ b/fs/fuse/famfs.c
@@ -18,9 +18,336 @@
 #include <linux/namei.h>
 #include <linux/string.h>
 
+#include "famfs_kfmap.h"
 #include "fuse_i.h"
 
 
+/***************************************************************************/
+
+void __famfs_meta_free(void *famfs_meta)
+{
+	struct famfs_file_meta *fmap = famfs_meta;
+
+	if (!fmap)
+		return;
+
+	switch (fmap->fm_extent_type) {
+	case SIMPLE_DAX_EXTENT:
+		kfree(fmap->se);
+		break;
+	case INTERLEAVED_EXTENT:
+		if (fmap->ie)
+			kfree(fmap->ie->ie_strips);
+
+		kfree(fmap->ie);
+		break;
+	default:
+		pr_err("%s: invalid fmap type\n", __func__);
+		break;
+	}
+
+	kfree(fmap);
+}
+DEFINE_FREE(__famfs_meta_free, void *, if (_T) __famfs_meta_free(_T))
+
+static int
+famfs_check_ext_alignment(struct famfs_meta_simple_ext *se)
+{
+	int errs = 0;
+
+	if (se->dev_index != 0)
+		errs++;
+
+	/* TODO: pass in alignment so we can support the other page sizes */
+	if (!IS_ALIGNED(se->ext_offset, PMD_SIZE))
+		errs++;
+
+	if (!IS_ALIGNED(se->ext_len, PMD_SIZE))
+		errs++;
+
+	return errs;
+}
+
+/**
+ * famfs_fuse_meta_alloc() - Allocate famfs file metadata
+ * @fmap_buf:  fmap buffer from fuse server
+ * @fmap_buf_size: size of fmap buffer
+ * @metap:         pointer where 'struct famfs_file_meta' is returned
+ *
+ * Returns: 0=success
+ *          -errno=failure
+ */
+static int
+famfs_fuse_meta_alloc(
+	void *fmap_buf,
+	size_t fmap_buf_size,
+	struct famfs_file_meta **metap)
+{
+	struct famfs_file_meta *meta __free(__famfs_meta_free) = NULL;
+	struct fuse_famfs_fmap_header *fmh;
+	size_t extent_total = 0;
+	size_t next_offset = 0;
+	int errs = 0;
+	int i, j;
+
+	fmh = fmap_buf;
+
+	/* Move past fmh in fmap_buf */
+	next_offset += sizeof(*fmh);
+	if (next_offset > fmap_buf_size) {
+		pr_err("%s:%d: fmap_buf underflow offset/size %ld/%ld\n",
+		       __func__, __LINE__, next_offset, fmap_buf_size);
+		return -EINVAL;
+	}
+
+	if (fmh->nextents < 1) {
+		pr_err("%s: nextents %d < 1\n", __func__, fmh->nextents);
+		return -EINVAL;
+	}
+
+	if (fmh->nextents > FUSE_FAMFS_MAX_EXTENTS) {
+		pr_err("%s: nextents %d > max (%d) 1\n",
+		       __func__, fmh->nextents, FUSE_FAMFS_MAX_EXTENTS);
+		return -E2BIG;
+	}
+
+	meta = kzalloc(sizeof(*meta), GFP_KERNEL);
+	if (!meta)
+		return -ENOMEM;
+
+	meta->error = false;
+	meta->file_type = fmh->file_type;
+	meta->file_size = fmh->file_size;
+	meta->fm_extent_type = fmh->ext_type;
+
+	switch (fmh->ext_type) {
+	case FUSE_FAMFS_EXT_SIMPLE: {
+		struct fuse_famfs_simple_ext *se_in;
+
+		se_in = fmap_buf + next_offset;
+
+		/* Move past simple extents */
+		next_offset += fmh->nextents * sizeof(*se_in);
+		if (next_offset > fmap_buf_size) {
+			pr_err("%s:%d: fmap_buf underflow offset/size %ld/%ld\n",
+			       __func__, __LINE__, next_offset, fmap_buf_size);
+			return -EINVAL;
+		}
+
+		meta->fm_nextents = fmh->nextents;
+
+		meta->se = kcalloc(meta->fm_nextents, sizeof(*(meta->se)),
+				   GFP_KERNEL);
+		if (!meta->se)
+			return -ENOMEM;
+
+		if ((meta->fm_nextents > FUSE_FAMFS_MAX_EXTENTS) ||
+		    (meta->fm_nextents < 1))
+			return -EINVAL;
+
+		for (i = 0; i < fmh->nextents; i++) {
+			meta->se[i].dev_index  = se_in[i].se_devindex;
+			meta->se[i].ext_offset = se_in[i].se_offset;
+			meta->se[i].ext_len    = se_in[i].se_len;
+
+			/* Record bitmap of referenced daxdev indices */
+			meta->dev_bitmap |= (1 << meta->se[i].dev_index);
+
+			errs += famfs_check_ext_alignment(&meta->se[i]);
+
+			extent_total += meta->se[i].ext_len;
+		}
+		break;
+	}
+
+	case FUSE_FAMFS_EXT_INTERLEAVE: {
+		s64 size_remainder = meta->file_size;
+		struct fuse_famfs_iext *ie_in;
+		int niext = fmh->nextents;
+
+		meta->fm_niext = niext;
+
+		/* Allocate interleaved extent */
+		meta->ie = kcalloc(niext, sizeof(*(meta->ie)), GFP_KERNEL);
+		if (!meta->ie)
+			return -ENOMEM;
+
+		/*
+		 * Each interleaved extent has a simple extent list of strips.
+		 * Outer loop is over separate interleaved extents
+		 */
+		for (i = 0; i < niext; i++) {
+			u64 nstrips;
+			struct fuse_famfs_simple_ext *sie_in;
+
+			/* ie_in = one interleaved extent in fmap_buf */
+			ie_in = fmap_buf + next_offset;
+
+			/* Move past one interleaved extent header in fmap_buf */
+			next_offset += sizeof(*ie_in);
+			if (next_offset > fmap_buf_size) {
+				pr_err("%s:%d: fmap_buf underflow offset/size %ld/%ld\n",
+				       __func__, __LINE__, next_offset,
+				       fmap_buf_size);
+				return -EINVAL;
+			}
+
+			nstrips = ie_in->ie_nstrips;
+			meta->ie[i].fie_chunk_size = ie_in->ie_chunk_size;
+			meta->ie[i].fie_nstrips    = ie_in->ie_nstrips;
+			meta->ie[i].fie_nbytes     = ie_in->ie_nbytes;
+
+			if (!meta->ie[i].fie_nbytes) {
+				pr_err("%s: zero-length interleave!\n",
+				       __func__);
+				return -EINVAL;
+			}
+
+			/* sie_in = the strip extents in fmap_buf */
+			sie_in = fmap_buf + next_offset;
+
+			/* Move past strip extents in fmap_buf */
+			next_offset += nstrips * sizeof(*sie_in);
+			if (next_offset > fmap_buf_size) {
+				pr_err("%s:%d: fmap_buf underflow offset/size %ld/%ld\n",
+				       __func__, __LINE__, next_offset,
+				       fmap_buf_size);
+				return -EINVAL;
+			}
+
+			if ((nstrips > FUSE_FAMFS_MAX_STRIPS) || (nstrips < 1)) {
+				pr_err("%s: invalid nstrips=%lld (max=%d)\n",
+				       __func__, nstrips,
+				       FUSE_FAMFS_MAX_STRIPS);
+				errs++;
+			}
+
+			/* Allocate strip extent array */
+			meta->ie[i].ie_strips =
+				kcalloc(ie_in->ie_nstrips,
+					sizeof(meta->ie[i].ie_strips[0]),
+					GFP_KERNEL);
+			if (!meta->ie[i].ie_strips)
+				return -ENOMEM;
+
+			/* Inner loop is over strips */
+			for (j = 0; j < nstrips; j++) {
+				struct famfs_meta_simple_ext *strips_out;
+				u64 devindex = sie_in[j].se_devindex;
+				u64 offset   = sie_in[j].se_offset;
+				u64 len      = sie_in[j].se_len;
+
+				strips_out = meta->ie[i].ie_strips;
+				strips_out[j].dev_index  = devindex;
+				strips_out[j].ext_offset = offset;
+				strips_out[j].ext_len    = len;
+
+				/* Record bitmap of referenced daxdev indices */
+				meta->dev_bitmap |= (1 << devindex);
+
+				extent_total += len;
+				errs += famfs_check_ext_alignment(&strips_out[j]);
+				size_remainder -= len;
+			}
+		}
+
+		if (size_remainder > 0) {
+			/* Sum of interleaved extent sizes is less than file size! */
+			pr_err("%s: size_remainder %lld (0x%llx)\n",
+			       __func__, size_remainder, size_remainder);
+			return -EINVAL;
+		}
+		break;
+	}
+
+	default:
+		pr_err("%s: invalid ext_type %d\n", __func__, fmh->ext_type);
+		return -EINVAL;
+	}
+
+	if (errs > 0) {
+		pr_err("%s: %d alignment errors found\n", __func__, errs);
+		return -EINVAL;
+	}
+
+	/* More sanity checks */
+	if (extent_total < meta->file_size) {
+		pr_err("%s: file size %ld larger than map size %ld\n",
+		       __func__, meta->file_size, extent_total);
+		return -EINVAL;
+	}
+
+	if (cmpxchg(metap, NULL, meta) != NULL) {
+		pr_debug("%s: fmap race detected\n", __func__);
+		return 0; /* fmap already installed */
+	}
+	meta = NULL; /* disarm __free() - the meta struct was consumed */
+
+	return 0;
+}
+
+/**
+ * famfs_file_init_dax() - init famfs dax file metadata
+ *
+ * @fm:        fuse_mount
+ * @inode:     the inode
+ * @fmap_buf:  fmap response message
+ * @fmap_size: Size of the fmap message
+ *
+ * Initialize famfs metadata for a file, based on the contents of the GET_FMAP
+ * response
+ *
+ * Return: 0=success
+ *          -errno=failure
+ */
+int
+famfs_file_init_dax(
+	struct fuse_mount *fm,
+	struct inode *inode,
+	void *fmap_buf,
+	size_t fmap_size)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct famfs_file_meta *meta = NULL;
+	int rc;
+
+	if (fi->famfs_meta) {
+		pr_notice("%s: i_no=%ld fmap_size=%ld ALREADY INITIALIZED\n",
+			  __func__,
+			  inode->i_ino, fmap_size);
+		return 0;
+	}
+
+	rc = famfs_fuse_meta_alloc(fmap_buf, fmap_size, &meta);
+	if (rc)
+		goto errout;
+
+	/* Publish the famfs metadata on fi->famfs_meta */
+	inode_lock(inode);
+	if (fi->famfs_meta) {
+		rc = -EEXIST; /* file already has famfs metadata */
+	} else {
+		if (famfs_meta_set(fi, meta) != NULL) {
+			pr_debug("%s: file already had metadata\n", __func__);
+			__famfs_meta_free(meta);
+			/* rc is 0 - the file is valid */
+			goto unlock_out;
+		}
+		i_size_write(inode, meta->file_size);
+		inode->i_flags |= S_DAX;
+	}
+ unlock_out:
+	inode_unlock(inode);
+	return 0;
+
+errout:
+	inode_unlock(inode);
+	if (rc)
+		__famfs_meta_free(meta);
+
+	return rc;
+}
+
 #define FMAP_BUFSIZE PAGE_SIZE
 
 int
@@ -64,11 +391,8 @@ fuse_get_fmap(struct fuse_mount *fm, struct inode *inode)
 	}
 	fmap_size = rc;
 
-	/* We retrieved the "fmap" (the file's map to memory), but
-	 * we haven't used it yet. A call to famfs_file_init_dax() will be added
-	 * here in a subsequent patch, when we add the ability to attach
-	 * fmaps to files.
-	 */
+	/* Convert fmap into in-memory format and hang from inode */
+	rc = famfs_file_init_dax(fm, inode, fmap_buf, fmap_size);
 
-	return 0;
+	return rc;
 }
diff --git a/fs/fuse/famfs_kfmap.h b/fs/fuse/famfs_kfmap.h
new file mode 100644
index 000000000000..18ab22bcc5a1
--- /dev/null
+++ b/fs/fuse/famfs_kfmap.h
@@ -0,0 +1,67 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * famfs - dax file system for shared fabric-attached memory
+ *
+ * Copyright 2023-2026 Micron Technology, Inc.
+ */
+#ifndef FAMFS_KFMAP_H
+#define FAMFS_KFMAP_H
+
+/*
+ * The structures below are the in-memory metadata format for famfs files.
+ * Metadata retrieved via the GET_FMAP response is converted to this format
+ * for use in resolving file mapping faults.
+ *
+ * The GET_FMAP response contains the same information, but in a more
+ * message-and-versioning-friendly format. Those structs can be found in the
+ * famfs section of include/uapi/linux/fuse.h (aka fuse_kernel.h in libfuse)
+ */
+
+enum famfs_file_type {
+	FAMFS_REG,
+	FAMFS_SUPERBLOCK,
+	FAMFS_LOG,
+};
+
+/* We anticipate the possibility of supporting additional types of extents */
+enum famfs_extent_type {
+	SIMPLE_DAX_EXTENT,
+	INTERLEAVED_EXTENT,
+	INVALID_EXTENT_TYPE,
+};
+
+struct famfs_meta_simple_ext {
+	u64 dev_index;
+	u64 ext_offset;
+	u64 ext_len;
+};
+
+struct famfs_meta_interleaved_ext {
+	u64 fie_nstrips;
+	u64 fie_chunk_size;
+	u64 fie_nbytes;
+	struct famfs_meta_simple_ext *ie_strips;
+};
+
+/*
+ * Each famfs dax file has this hanging from its fuse_inode->famfs_meta
+ */
+struct famfs_file_meta {
+	bool                   error;
+	enum famfs_file_type   file_type;
+	size_t                 file_size;
+	enum famfs_extent_type fm_extent_type;
+	u64 dev_bitmap; /* bitmap of referenced daxdevs by index */
+	union {
+		struct {
+			size_t         fm_nextents;
+			struct famfs_meta_simple_ext  *se;
+		};
+		struct {
+			size_t         fm_niext;
+			struct famfs_meta_interleaved_ext *ie;
+		};
+	};
+};
+
+#endif /* FAMFS_KFMAP_H */
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index b66b5ca0bc11..dbfec5b9c6e1 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1642,6 +1642,9 @@ extern void fuse_sysctl_unregister(void);
 /* famfs.c */
 
 #if IS_ENABLED(CONFIG_FUSE_FAMFS_DAX)
+int famfs_file_init_dax(struct fuse_mount *fm,
+			struct inode *inode, void *fmap_buf,
+			size_t fmap_size);
 void __famfs_meta_free(void *map);
 
 /* Set fi->famfs_meta = NULL regardless of prior value */
@@ -1659,7 +1662,10 @@ static inline struct fuse_backing *famfs_meta_set(struct fuse_inode *fi,
 
 static inline void famfs_meta_free(struct fuse_inode *fi)
 {
-	famfs_meta_set(fi, NULL);
+	if (fi->famfs_meta != NULL) {
+		__famfs_meta_free(fi->famfs_meta);
+		famfs_meta_set(fi, NULL);
+	}
 }
 
 static inline int fuse_file_famfs(struct fuse_inode *fi)
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f2d742d723dc..b9933d0fbb9f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1464,8 +1464,21 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
 				timeout = arg->request_timeout;
 
 			if (IS_ENABLED(CONFIG_FUSE_FAMFS_DAX) &&
-			    flags & FUSE_DAX_FMAP)
-				fc->famfs_iomap = 1;
+			    flags & FUSE_DAX_FMAP) {
+				/* famfs_iomap is only allowed if the fuse
+				 * server has CAP_SYS_RAWIO. This was checked
+				 * in fuse_send_init, and FUSE_DAX_IOMAP was
+				 * set in in_flags if so. Only allow enablement
+				 * if we find it there. This function is
+				 * normally not running in fuse server context,
+				 * so we can't do the capability check here...
+				 */
+				u64 in_flags = ((u64)ia->in.flags2 << 32)
+						| ia->in.flags;
+
+				if (in_flags & FUSE_DAX_FMAP)
+					fc->famfs_iomap = 1;
+			}
 		} else {
 			ra_pages = fc->max_read / PAGE_SIZE;
 			fc->no_lock = 1;
@@ -1527,7 +1540,7 @@ static struct fuse_init_args *fuse_new_init(struct fuse_mount *fm)
 		flags |= FUSE_SUBMOUNTS;
 	if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
 		flags |= FUSE_PASSTHROUGH;
-	if (IS_ENABLED(CONFIG_FUSE_FAMFS_DAX))
+	if (IS_ENABLED(CONFIG_FUSE_FAMFS_DAX) && capable(CAP_SYS_RAWIO))
 		flags |= FUSE_DAX_FMAP;
 
 	/*
diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h
index 9eff9083d3b5..cf678bebbfe0 100644
--- a/include/uapi/linux/fuse.h
+++ b/include/uapi/linux/fuse.h
@@ -243,6 +243,13 @@
  *
  *  7.46
  *  - Add FUSE_DAX_FMAP capability - ability to handle in-kernel fsdax maps
+ *  - Add the following structures for the GET_FMAP message reply components:
+ *    - struct fuse_famfs_simple_ext
+ *    - struct fuse_famfs_iext
+ *    - struct fuse_famfs_fmap_header
+ *  - Add the following enumerated types
+ *    - enum fuse_famfs_file_type
+ *    - enum famfs_ext_type
  */
 
 #ifndef _LINUX_FUSE_H
@@ -1318,6 +1325,55 @@ struct fuse_uring_cmd_req {
 
 /* Famfs fmap message components */
 
+#define FAMFS_FMAP_VERSION 1
+
 #define FAMFS_FMAP_MAX 32768 /* Largest supported fmap message */
+#define FUSE_FAMFS_MAX_EXTENTS 32
+#define FUSE_FAMFS_MAX_STRIPS 32
+
+enum fuse_famfs_file_type {
+	FUSE_FAMFS_FILE_REG,
+	FUSE_FAMFS_FILE_SUPERBLOCK,
+	FUSE_FAMFS_FILE_LOG,
+};
+
+enum famfs_ext_type {
+	FUSE_FAMFS_EXT_SIMPLE = 0,
+	FUSE_FAMFS_EXT_INTERLEAVE = 1,
+};
+
+struct fuse_famfs_simple_ext {
+	uint32_t se_devindex;
+	uint32_t reserved;
+	uint64_t se_offset;
+	uint64_t se_len;
+};
+
+struct fuse_famfs_iext { /* Interleaved extent */
+	uint32_t ie_nstrips;
+	uint32_t ie_chunk_size;
+	uint64_t ie_nbytes; /* Total bytes for this interleaved_ext;
+			     * sum of strips may be more
+			     */
+	uint64_t reserved;
+};
+
+struct fuse_famfs_fmap_header {
+	uint8_t file_type; /* enum famfs_file_type */
+	uint8_t reserved;
+	uint16_t fmap_version;
+	uint32_t ext_type; /* enum famfs_log_ext_type */
+	uint32_t nextents;
+	uint32_t reserved0;
+	uint64_t file_size;
+	uint64_t reserved1;
+};
+
+static inline int32_t fmap_msg_min_size(void)
+{
+	/* Smallest fmap message is a header plus one simple extent */
+	return (sizeof(struct fuse_famfs_fmap_header)
+		+ sizeof(struct fuse_famfs_simple_ext));
+}
 
 #endif /* _LINUX_FUSE_H */
-- 
2.52.0

[PATCH V4 15/19] famfs_fuse: Plumb dax iomap and fuse read/write/mmap

[John Groves]

This commit fills in read/write/mmap handling for famfs files. The
dev_dax_iomap interface is used - just like xfs in fs-dax mode.

- Read/write are handled by famfs_fuse_[read|write]_iter() via
  dax_iomap_rw() to fsdev_dax.
- Mmap is handled by famfs_fuse_mmap()
- Faults are handled by famfs_filemap_fault(), using dax_iomap_fault()
  to fsdev_dax.
- File offset to dax offset resolution is handled via
  famfs_fuse_iomap_begin(), which uses famfs "fmaps" to resolve the
  the requested (file, offset) to an offset on a dax device (by way of
  famfs_fileofs_to_daxofs() and famfs_interleave_fileofs_to_daxofs())

Signed-off-by: John Groves <john@groves.net>
---
 fs/fuse/famfs.c  | 443 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/fuse/file.c   |  18 +-
 fs/fuse/fuse_i.h |  19 ++
 3 files changed, 478 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
index 438fc286d1a6..2de70aef1df8 100644
--- a/fs/fuse/famfs.c
+++ b/fs/fuse/famfs.c
@@ -574,6 +574,449 @@ famfs_file_init_dax(
 	return rc;
 }
 
+/*********************************************************************
+ * iomap_operations
+ *
+ * This stuff uses the iomap (dax-related) helpers to resolve file offsets to
+ * offsets within a dax device.
+ */
+
+static int famfs_file_bad(struct inode *inode);
+
+static int
+famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
+			 loff_t file_offset, off_t len, unsigned int flags)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct famfs_file_meta *meta = fi->famfs_meta;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	loff_t local_offset = file_offset;
+
+	/* This function is only for extent_type INTERLEAVED_EXTENT */
+	if (meta->fm_extent_type != INTERLEAVED_EXTENT) {
+		pr_err("%s: bad extent type\n", __func__);
+		goto err_out;
+	}
+
+	if (famfs_file_bad(inode))
+		goto err_out;
+
+	iomap->offset = file_offset;
+
+	for (int i = 0; i < meta->fm_niext; i++) {
+		struct famfs_meta_interleaved_ext *fei = &meta->ie[i];
+		u64 chunk_size = fei->fie_chunk_size;
+		u64 nstrips = fei->fie_nstrips;
+		u64 ext_size = min(ext_size, meta->file_size);
+
+		if (ext_size == 0) {
+			pr_err("%s: ext_size=%lld file_size=%ld\n",
+			       __func__, fei->fie_nbytes, meta->file_size);
+			goto err_out;
+		}
+
+		/* Is the data is in this striped extent? */
+		if (local_offset < ext_size) {
+			u64 chunk_num       = local_offset / chunk_size;
+			u64 chunk_offset    = local_offset % chunk_size;
+			u64 chunk_remainder = chunk_size - chunk_offset;
+			u64 stripe_num      = chunk_num / nstrips;
+			u64 strip_num       = chunk_num % nstrips;
+			u64 strip_offset    = chunk_offset + (stripe_num * chunk_size);
+			u64 strip_dax_ofs = fei->ie_strips[strip_num].ext_offset;
+			u64 strip_devidx = fei->ie_strips[strip_num].dev_index;
+
+			if (strip_devidx >= fc->dax_devlist->nslots) {
+				pr_err("%s: strip_devidx %llu >= nslots %d\n",
+				       __func__, strip_devidx,
+				       fc->dax_devlist->nslots);
+				goto err_out;
+			}
+
+			if (!fc->dax_devlist->devlist[strip_devidx].valid) {
+				pr_err("%s: daxdev=%lld invalid\n", __func__,
+					strip_devidx);
+				goto err_out;
+			}
+
+			iomap->addr    = strip_dax_ofs + strip_offset;
+			iomap->offset  = file_offset;
+			iomap->length  = min_t(loff_t, len, chunk_remainder);
+
+			iomap->dax_dev = fc->dax_devlist->devlist[strip_devidx].devp;
+
+			iomap->type    = IOMAP_MAPPED;
+			iomap->flags   = flags;
+
+			return 0;
+		}
+		local_offset -= ext_size; /* offset is beyond this striped extent */
+	}
+
+ err_out:
+	pr_err("%s: err_out\n", __func__);
+
+	/* We fell out the end of the extent list.
+	 * Set iomap to zero length in this case, and return 0
+	 * This just means that the r/w is past EOF
+	 */
+	iomap->addr    = 0; /* there is no valid dax device offset */
+	iomap->offset  = file_offset; /* file offset */
+	iomap->length  = 0; /* this had better result in no access to dax mem */
+	iomap->dax_dev = NULL;
+	iomap->type    = IOMAP_MAPPED;
+	iomap->flags   = flags;
+
+	return -EIO;
+}
+
+/**
+ * famfs_fileofs_to_daxofs() - Resolve (file, offset, len) to (daxdev, offset, len)
+ *
+ * This function is called by famfs_fuse_iomap_begin() to resolve an offset in a
+ * file to an offset in a dax device. This is upcalled from dax from calls to
+ * both  * dax_iomap_fault() and dax_iomap_rw(). Dax finishes the job resolving
+ * a fault to a specific physical page (the fault case) or doing a memcpy
+ * variant (the rw case)
+ *
+ * Pages can be PTE (4k), PMD (2MiB) or (theoretically) PuD (1GiB)
+ * (these sizes are for X86; may vary on other cpu architectures
+ *
+ * @inode:  The file where the fault occurred
+ * @iomap:       To be filled in to indicate where to find the right memory,
+ *               relative  to a dax device.
+ * @file_offset: Within the file where the fault occurred (will be page boundary)
+ * @len:         The length of the faulted mapping (will be a page multiple)
+ *               (will be trimmed in *iomap if it's disjoint in the extent list)
+ * @flags:       flags passed to famfs_fuse_iomap_begin(), and sent back via
+ *               struct iomap
+ *
+ * Return values: 0. (info is returned in a modified @iomap struct)
+ */
+static int
+famfs_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
+			loff_t file_offset, off_t len, unsigned int flags)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct famfs_file_meta *meta = fi->famfs_meta;
+	struct fuse_conn *fc = get_fuse_conn(inode);
+	loff_t local_offset = file_offset;
+
+	if (!fc->dax_devlist) {
+		pr_err("%s: null dax_devlist\n", __func__);
+		goto err_out;
+	}
+
+	if (famfs_file_bad(inode))
+		goto err_out;
+
+	if (meta->fm_extent_type == INTERLEAVED_EXTENT)
+		return famfs_interleave_fileofs_to_daxofs(inode, iomap,
+							  file_offset,
+							  len, flags);
+
+	iomap->offset = file_offset;
+
+	for (int i = 0; i < meta->fm_nextents; i++) {
+		/* TODO: check devindex too */
+		loff_t dax_ext_offset = meta->se[i].ext_offset;
+		loff_t dax_ext_len    = meta->se[i].ext_len;
+		u64 daxdev_idx = meta->se[i].dev_index;
+
+
+		/* TODO: test that superblock and log offsets only happen
+		 * with superblock and log files. Requires instrumentaiton
+		 * from user space...
+		 */
+
+		/* local_offset is the offset minus the size of extents skipped
+		 * so far; If local_offset < dax_ext_len, the data of interest
+		 * starts in this extent
+		 */
+		if (local_offset < dax_ext_len) {
+			loff_t ext_len_remainder = dax_ext_len - local_offset;
+			struct famfs_daxdev *dd;
+
+			if (daxdev_idx >= fc->dax_devlist->nslots) {
+				pr_err("%s: daxdev_idx %llu >= nslots %d\n",
+				       __func__, daxdev_idx,
+				       fc->dax_devlist->nslots);
+				goto err_out;
+			}
+
+			dd = &fc->dax_devlist->devlist[daxdev_idx];
+
+			if (!dd->valid || dd->error) {
+				pr_err("%s: daxdev=%lld %s\n", __func__,
+				       daxdev_idx,
+				       dd->valid ? "error" : "invalid");
+				goto err_out;
+			}
+
+			/*
+			 * OK, we found the file metadata extent where this
+			 * data begins
+			 * @local_offset      - The offset within the current
+			 *                      extent
+			 * @ext_len_remainder - Remaining length of ext after
+			 *                      skipping local_offset
+			 * Outputs:
+			 * iomap->addr:   the offset within the dax device where
+			 *                the  data starts
+			 * iomap->offset: the file offset
+			 * iomap->length: the valid length resolved here
+			 */
+			iomap->addr    = dax_ext_offset + local_offset;
+			iomap->offset  = file_offset;
+			iomap->length  = min_t(loff_t, len, ext_len_remainder);
+
+			iomap->dax_dev = fc->dax_devlist->devlist[daxdev_idx].devp;
+
+			iomap->type    = IOMAP_MAPPED;
+			iomap->flags   = flags;
+			return 0;
+		}
+		local_offset -= dax_ext_len; /* Get ready for the next extent */
+	}
+
+ err_out:
+	pr_err("%s: err_out\n", __func__);
+
+	/* We fell out the end of the extent list.
+	 * Set iomap to zero length in this case, and return 0
+	 * This just means that the r/w is past EOF
+	 */
+	iomap->addr    = 0; /* there is no valid dax device offset */
+	iomap->offset  = file_offset; /* file offset */
+	iomap->length  = 0; /* this had better result in no access to dax mem */
+	iomap->dax_dev = NULL;
+	iomap->type    = IOMAP_MAPPED;
+	iomap->flags   = flags;
+
+	return -EIO;
+}
+
+/**
+ * famfs_fuse_iomap_begin() - Handler for iomap_begin upcall from dax
+ *
+ * This function is pretty simple because files are
+ * * never partially allocated
+ * * never have holes (never sparse)
+ * * never "allocate on write"
+ *
+ * @inode:  inode for the file being accessed
+ * @offset: offset within the file
+ * @length: Length being accessed at offset
+ * @flags:  flags to be retured via struct iomap
+ * @iomap:  iomap struct to be filled in, resolving (offset, length) to
+ *          (daxdev, offset, len)
+ * @srcmap: source mapping if it is a COW operation (which it is not here)
+ */
+static int
+famfs_fuse_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+		  unsigned int flags, struct iomap *iomap, struct iomap *srcmap)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct famfs_file_meta *meta = fi->famfs_meta;
+	size_t size;
+
+	size = i_size_read(inode);
+
+	WARN_ON(size != meta->file_size);
+
+	return famfs_fileofs_to_daxofs(inode, iomap, offset, length, flags);
+}
+
+/* Note: We never need a special set of write_iomap_ops because famfs never
+ * performs allocation on write.
+ */
+const struct iomap_ops famfs_iomap_ops = {
+	.iomap_begin		= famfs_fuse_iomap_begin,
+};
+
+/*********************************************************************
+ * vm_operations
+ */
+static vm_fault_t
+__famfs_fuse_filemap_fault(struct vm_fault *vmf, unsigned int pe_size,
+		      bool write_fault)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	vm_fault_t ret;
+	unsigned long pfn;
+
+	if (!IS_DAX(file_inode(vmf->vma->vm_file))) {
+		pr_err("%s: file not marked IS_DAX!!\n", __func__);
+		return VM_FAULT_SIGBUS;
+	}
+
+	if (write_fault) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vmf->vma->vm_file);
+	}
+
+	ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL, &famfs_iomap_ops);
+	if (ret & VM_FAULT_NEEDDSYNC)
+		ret = dax_finish_sync_fault(vmf, pe_size, pfn);
+
+	if (write_fault)
+		sb_end_pagefault(inode->i_sb);
+
+	return ret;
+}
+
+static inline bool
+famfs_is_write_fault(struct vm_fault *vmf)
+{
+	return (vmf->flags & FAULT_FLAG_WRITE) &&
+	       (vmf->vma->vm_flags & VM_SHARED);
+}
+
+static vm_fault_t
+famfs_filemap_fault(struct vm_fault *vmf)
+{
+	return __famfs_fuse_filemap_fault(vmf, 0, famfs_is_write_fault(vmf));
+}
+
+static vm_fault_t
+famfs_filemap_huge_fault(struct vm_fault *vmf, unsigned int pe_size)
+{
+	return __famfs_fuse_filemap_fault(vmf, pe_size,
+					  famfs_is_write_fault(vmf));
+}
+
+static vm_fault_t
+famfs_filemap_mkwrite(struct vm_fault *vmf)
+{
+	return __famfs_fuse_filemap_fault(vmf, 0, true);
+}
+
+const struct vm_operations_struct famfs_file_vm_ops = {
+	.fault		= famfs_filemap_fault,
+	.huge_fault	= famfs_filemap_huge_fault,
+	.map_pages	= filemap_map_pages,
+	.page_mkwrite	= famfs_filemap_mkwrite,
+	.pfn_mkwrite	= famfs_filemap_mkwrite,
+};
+
+/*********************************************************************
+ * file_operations
+ */
+
+/**
+ * famfs_file_bad() - Check for files that aren't in a valid state
+ *
+ * @inode: inode
+ *
+ * Returns: 0=success
+ *          -errno=failure
+ */
+static int
+famfs_file_bad(struct inode *inode)
+{
+	struct fuse_inode *fi = get_fuse_inode(inode);
+	struct famfs_file_meta *meta = fi->famfs_meta;
+	size_t i_size = i_size_read(inode);
+
+	if (!meta) {
+		pr_err("%s: un-initialized famfs file\n", __func__);
+		return -EIO;
+	}
+	if (meta->error) {
+		pr_debug("%s: previously detected metadata errors\n", __func__);
+		return -EIO;
+	}
+	if (i_size != meta->file_size) {
+		pr_warn("%s: i_size overwritten from %ld to %ld\n",
+		       __func__, meta->file_size, i_size);
+		meta->error = true;
+		return -ENXIO;
+	}
+	if (!IS_DAX(inode)) {
+		pr_debug("%s: inode %llx IS_DAX is false\n",
+			 __func__, (u64)inode);
+		return -ENXIO;
+	}
+	return 0;
+}
+
+static ssize_t
+famfs_fuse_rw_prep(struct kiocb *iocb, struct iov_iter *ubuf)
+{
+	struct inode *inode = iocb->ki_filp->f_mapping->host;
+	size_t i_size = i_size_read(inode);
+	size_t count = iov_iter_count(ubuf);
+	size_t max_count;
+	ssize_t rc;
+
+	rc = famfs_file_bad(inode);
+	if (rc)
+		return (ssize_t)rc;
+
+	/* Avoid unsigned underflow if position is past EOF */
+	if (iocb->ki_pos >= i_size)
+		max_count = 0;
+	else
+		max_count = i_size - iocb->ki_pos;
+
+	if (count > max_count)
+		iov_iter_truncate(ubuf, max_count);
+
+	if (!iov_iter_count(ubuf))
+		return 0;
+
+	return rc;
+}
+
+ssize_t
+famfs_fuse_read_iter(struct kiocb *iocb, struct iov_iter	*to)
+{
+	ssize_t rc;
+
+	rc = famfs_fuse_rw_prep(iocb, to);
+	if (rc)
+		return rc;
+
+	if (!iov_iter_count(to))
+		return 0;
+
+	rc = dax_iomap_rw(iocb, to, &famfs_iomap_ops);
+
+	file_accessed(iocb->ki_filp);
+	return rc;
+}
+
+ssize_t
+famfs_fuse_write_iter(struct kiocb *iocb, struct iov_iter *from)
+{
+	ssize_t rc;
+
+	rc = famfs_fuse_rw_prep(iocb, from);
+	if (rc)
+		return rc;
+
+	if (!iov_iter_count(from))
+		return 0;
+
+	return dax_iomap_rw(iocb, from, &famfs_iomap_ops);
+}
+
+int
+famfs_fuse_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct inode *inode = file_inode(file);
+	ssize_t rc;
+
+	rc = famfs_file_bad(inode);
+	if (rc)
+		return rc;
+
+	file_accessed(file);
+	vma->vm_ops = &famfs_file_vm_ops;
+	vm_flags_set(vma, VM_HUGEPAGE);
+	return 0;
+}
+
 #define FMAP_BUFSIZE PAGE_SIZE
 
 int
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 1f64bf68b5ee..45a09a7f0012 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1831,6 +1831,8 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 	if (FUSE_IS_VIRTIO_DAX(fi))
 		return fuse_dax_read_iter(iocb, to);
+	if (fuse_file_famfs(fi))
+		return famfs_fuse_read_iter(iocb, to);
 
 	/* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
 	if (ff->open_flags & FOPEN_DIRECT_IO)
@@ -1853,6 +1855,8 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	if (FUSE_IS_VIRTIO_DAX(fi))
 		return fuse_dax_write_iter(iocb, from);
+	if (fuse_file_famfs(fi))
+		return famfs_fuse_write_iter(iocb, from);
 
 	/* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
 	if (ff->open_flags & FOPEN_DIRECT_IO)
@@ -1868,9 +1872,13 @@ static ssize_t fuse_splice_read(struct file *in, loff_t *ppos,
 				unsigned int flags)
 {
 	struct fuse_file *ff = in->private_data;
+	struct inode *inode = file_inode(in);
+	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	/* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
-	if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO))
+	if (fuse_file_famfs(fi))
+		return -EIO; /* famfs does not use the page cache... */
+	else if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO))
 		return fuse_passthrough_splice_read(in, ppos, pipe, len, flags);
 	else
 		return filemap_splice_read(in, ppos, pipe, len, flags);
@@ -1880,9 +1888,13 @@ static ssize_t fuse_splice_write(struct pipe_inode_info *pipe, struct file *out,
 				 loff_t *ppos, size_t len, unsigned int flags)
 {
 	struct fuse_file *ff = out->private_data;
+	struct inode *inode = file_inode(out);
+	struct fuse_inode *fi = get_fuse_inode(inode);
 
 	/* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
-	if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO))
+	if (fuse_file_famfs(fi))
+		return -EIO; /* famfs does not use the page cache... */
+	else if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO))
 		return fuse_passthrough_splice_write(pipe, out, ppos, len, flags);
 	else
 		return iter_file_splice_write(pipe, out, ppos, len, flags);
@@ -2390,6 +2402,8 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 	/* DAX mmap is superior to direct_io mmap */
 	if (FUSE_IS_VIRTIO_DAX(fi))
 		return fuse_dax_mmap(file, vma);
+	if (fuse_file_famfs(fi))
+		return famfs_fuse_mmap(file, vma);
 
 	/*
 	 * If inode is in passthrough io mode, because it has some file open
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 83e24cee994b..f5548466c2b2 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1650,6 +1650,9 @@ extern void fuse_sysctl_unregister(void);
 int famfs_file_init_dax(struct fuse_mount *fm,
 			struct inode *inode, void *fmap_buf,
 			size_t fmap_size);
+ssize_t famfs_fuse_write_iter(struct kiocb *iocb, struct iov_iter *from);
+ssize_t famfs_fuse_read_iter(struct kiocb *iocb, struct iov_iter	*to);
+int famfs_fuse_mmap(struct file *file, struct vm_area_struct *vma);
 void __famfs_meta_free(void *map);
 
 void famfs_teardown(struct fuse_conn *fc);
@@ -1692,6 +1695,22 @@ int fuse_get_fmap(struct fuse_mount *fm, struct inode *inode);
 static inline void famfs_teardown(struct fuse_conn *fc)
 {
 }
+static inline ssize_t famfs_fuse_write_iter(struct kiocb *iocb,
+					    struct iov_iter *to)
+{
+	return -ENODEV;
+}
+static inline ssize_t famfs_fuse_read_iter(struct kiocb *iocb,
+					   struct iov_iter *to)
+{
+	return -ENODEV;
+}
+static inline int famfs_fuse_mmap(struct file *file,
+				  struct vm_area_struct *vma)
+{
+	return -ENODEV;
+}
+
 static inline struct fuse_backing *famfs_meta_set(struct fuse_inode *fi,
 						  void *meta)
 {
-- 
2.52.0

[PATCH V4 16/19] famfs_fuse: Add holder_operations for dax notify_failure()

[John Groves]

Memory errors are at least somewhat more likely on disaggregated memory
than on-board memory. This commit registers to be notified by fsdev_dax
in the event that a memory failure is detected.

When a file access resolves to a daxdev with memory errors, it will fail
with an appropriate error.

If a daxdev failed fs_dax_get(), we set dd->dax_err. If a daxdev called
our notify_failure(), set dd->error. When any of the above happens, set
(file)->error and stop allowing access.

In general, the recovery from memory errors is to unmount the file
system and re-initialize the memory, but there may be usable degraded
modes of operation - particularly in the future when famfs supports
file systems backed by more than one daxdev. In those cases,
accessing data that is on a working daxdev can still work.

For now, return errors for any file that has encountered a memory or dax
error.

Signed-off-by: John Groves <john@groves.net>
---
 fs/fuse/famfs.c       | 110 +++++++++++++++++++++++++++++++++++++++---
 fs/fuse/famfs_kfmap.h |   3 +-
 2 files changed, 105 insertions(+), 8 deletions(-)

diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
index 2de70aef1df8..ee3526175b6b 100644
--- a/fs/fuse/famfs.c
+++ b/fs/fuse/famfs.c
@@ -21,6 +21,26 @@
 #include "famfs_kfmap.h"
 #include "fuse_i.h"
 
+static void famfs_set_daxdev_err(
+	struct fuse_conn *fc, struct dax_device *dax_devp);
+
+static int
+famfs_dax_notify_failure(struct dax_device *dax_devp, u64 offset,
+			u64 len, int mf_flags)
+{
+	struct fuse_conn *fc = dax_holder(dax_devp);
+
+	famfs_set_daxdev_err(fc, dax_devp);
+
+	return 0;
+}
+
+static const struct dax_holder_operations famfs_fuse_dax_holder_ops = {
+	.notify_failure		= famfs_dax_notify_failure,
+};
+
+/*****************************************************************************/
+
 /*
  * famfs_teardown()
  *
@@ -47,9 +67,12 @@ famfs_teardown(struct fuse_conn *fc)
 		if (!dd->valid)
 			continue;
 
-		/* Release reference from dax_dev_get() */
-		if (dd->devp)
+		/* Only call fs_put_dax if fs_dax_get succeeded */
+		if (dd->devp) {
+			if (!dd->dax_err)
+				fs_put_dax(dd->devp, fc);
 			put_dax(dd->devp);
+		}
 
 		kfree(dd->name);
 	}
@@ -170,6 +193,17 @@ famfs_fuse_get_daxdev(struct fuse_mount *fm, const u64 index)
 		if (!daxdev->name)
 			return -ENOMEM;
 
+		rc = fs_dax_get(daxdev->devp, fc, &famfs_fuse_dax_holder_ops);
+		if (rc) {
+			/* If fs_dax_get() fails, we don't attempt recovery;
+			 * We mark the daxdev valid with dax_err
+			 */
+			daxdev->dax_err = 1;
+			pr_err("%s: fs_dax_get(%lld) failed\n",
+			       __func__, (u64)daxdev->devno);
+			return -EBUSY;
+		}
+
 		wmb(); /* All other fields must be visible before valid */
 		daxdev->valid = 1;
 	}
@@ -245,6 +279,36 @@ famfs_update_daxdev_table(
 	return 0;
 }
 
+static void
+famfs_set_daxdev_err(
+	struct fuse_conn *fc,
+	struct dax_device *dax_devp)
+{
+	int i;
+
+	/* Gotta search the list by dax_devp;
+	 * read lock because we're not adding or removing daxdev entries
+	 */
+	scoped_guard(rwsem_write, &fc->famfs_devlist_sem) {
+		for (i = 0; i < fc->dax_devlist->nslots; i++) {
+			if (fc->dax_devlist->devlist[i].valid) {
+				struct famfs_daxdev *dd;
+
+				dd = &fc->dax_devlist->devlist[i];
+				if (dd->devp != dax_devp)
+					continue;
+
+				dd->error = true;
+
+				pr_err("%s: memory error on daxdev %s (%d)\n",
+				       __func__, dd->name, i);
+				return;
+			}
+		}
+	}
+	pr_err("%s: memory err on unrecognized daxdev\n", __func__);
+}
+
 /***************************************************************************/
 
 void __famfs_meta_free(void *famfs_meta)
@@ -583,6 +647,26 @@ famfs_file_init_dax(
 
 static int famfs_file_bad(struct inode *inode);
 
+static int famfs_dax_err(struct famfs_daxdev *dd)
+{
+	if (!dd->valid) {
+		pr_err("%s: daxdev=%s invalid\n",
+		       __func__, dd->name);
+		return -EIO;
+	}
+	if (dd->dax_err) {
+		pr_err("%s: daxdev=%s dax_err\n",
+		       __func__, dd->name);
+		return -EIO;
+	}
+	if (dd->error) {
+		pr_err("%s: daxdev=%s memory error\n",
+		       __func__, dd->name);
+		return -EHWPOISON;
+	}
+	return 0;
+}
+
 static int
 famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
 			 loff_t file_offset, off_t len, unsigned int flags)
@@ -617,6 +701,7 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
 
 		/* Is the data is in this striped extent? */
 		if (local_offset < ext_size) {
+			struct famfs_daxdev *dd;
 			u64 chunk_num       = local_offset / chunk_size;
 			u64 chunk_offset    = local_offset % chunk_size;
 			u64 chunk_remainder = chunk_size - chunk_offset;
@@ -625,6 +710,7 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
 			u64 strip_offset    = chunk_offset + (stripe_num * chunk_size);
 			u64 strip_dax_ofs = fei->ie_strips[strip_num].ext_offset;
 			u64 strip_devidx = fei->ie_strips[strip_num].dev_index;
+			int rc;
 
 			if (strip_devidx >= fc->dax_devlist->nslots) {
 				pr_err("%s: strip_devidx %llu >= nslots %d\n",
@@ -639,6 +725,15 @@ famfs_interleave_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
 				goto err_out;
 			}
 
+			dd = &fc->dax_devlist->devlist[strip_devidx];
+
+			rc = famfs_dax_err(dd);
+			if (rc) {
+				/* Shut down access to this file */
+				meta->error = true;
+				return rc;
+			}
+
 			iomap->addr    = strip_dax_ofs + strip_offset;
 			iomap->offset  = file_offset;
 			iomap->length  = min_t(loff_t, len, chunk_remainder);
@@ -736,6 +831,7 @@ famfs_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
 		if (local_offset < dax_ext_len) {
 			loff_t ext_len_remainder = dax_ext_len - local_offset;
 			struct famfs_daxdev *dd;
+			int rc;
 
 			if (daxdev_idx >= fc->dax_devlist->nslots) {
 				pr_err("%s: daxdev_idx %llu >= nslots %d\n",
@@ -746,11 +842,11 @@ famfs_fileofs_to_daxofs(struct inode *inode, struct iomap *iomap,
 
 			dd = &fc->dax_devlist->devlist[daxdev_idx];
 
-			if (!dd->valid || dd->error) {
-				pr_err("%s: daxdev=%lld %s\n", __func__,
-				       daxdev_idx,
-				       dd->valid ? "error" : "invalid");
-				goto err_out;
+			rc = famfs_dax_err(dd);
+			if (rc) {
+				/* Shut down access to this file */
+				meta->error = true;
+				return rc;
 			}
 
 			/*
diff --git a/fs/fuse/famfs_kfmap.h b/fs/fuse/famfs_kfmap.h
index eb9f70b5cb81..0fff841f5a9e 100644
--- a/fs/fuse/famfs_kfmap.h
+++ b/fs/fuse/famfs_kfmap.h
@@ -73,7 +73,8 @@ struct famfs_file_meta {
 struct famfs_daxdev {
 	/* Include dev uuid? */
 	bool valid;
-	bool error;
+	bool error; /* Dax has reported a memory error (probably poison) */
+	bool dax_err; /* fs_dax_get() failed */
 	dev_t devno;
 	struct dax_device *devp;
 	char *name;
-- 
2.52.0

[PATCH V4 17/19] famfs_fuse: Add DAX address_space_operations with noop_dirty_folio

[John Groves]

From: John Groves <John@Groves.net>

Famfs is memory-backed; there is no place to write back to, and no
reason to mark pages dirty at all.

Signed-off-by: John Groves <john@groves.net>
---
 fs/fuse/famfs.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/fs/fuse/famfs.c b/fs/fuse/famfs.c
index ee3526175b6b..f98e358ea489 100644
--- a/fs/fuse/famfs.c
+++ b/fs/fuse/famfs.c
@@ -14,6 +14,7 @@
 #include <linux/mm.h>
 #include <linux/dax.h>
 #include <linux/iomap.h>
+#include <linux/pagemap.h>
 #include <linux/path.h>
 #include <linux/namei.h>
 #include <linux/string.h>
@@ -39,6 +40,15 @@ static const struct dax_holder_operations famfs_fuse_dax_holder_ops = {
 	.notify_failure		= famfs_dax_notify_failure,
 };
 
+/*
+ * DAX address_space_operations for famfs.
+ * famfs doesn't need dirty tracking - writes go directly to
+ * memory with no writeback required.
+ */
+static const struct address_space_operations famfs_dax_aops = {
+	.dirty_folio	= noop_dirty_folio,
+};
+
 /*****************************************************************************/
 
 /*
@@ -625,6 +635,7 @@ famfs_file_init_dax(
 		}
 		i_size_write(inode, meta->file_size);
 		inode->i_flags |= S_DAX;
+		inode->i_data.a_ops = &famfs_dax_aops;
 	}
  unlock_out:
 	inode_unlock(inode);
-- 
2.52.0

[PATCH V4 18/19] famfs_fuse: Add famfs fmap metadata documentation

[John Groves]

From: John Groves <John@Groves.net>

This describes the fmap metadata - both simple and interleaved

Signed-off-by: John Groves <john@groves.net>
---
 fs/fuse/famfs_kfmap.h | 73 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/fs/fuse/famfs_kfmap.h b/fs/fuse/famfs_kfmap.h
index 0fff841f5a9e..970ad802b492 100644
--- a/fs/fuse/famfs_kfmap.h
+++ b/fs/fuse/famfs_kfmap.h
@@ -7,6 +7,79 @@
 #ifndef FAMFS_KFMAP_H
 #define FAMFS_KFMAP_H
 
+/* KABI version 43 (aka v2) fmap structures
+ *
+ * The location of the memory backing for a famfs file is described by
+ * the response to the GET_FMAP fuse message (defined in
+ * include/uapi/linux/fuse.h
+ *
+ * There are currently two extent formats: Simple and Interleaved.
+ *
+ * Simple extents are just (devindex, offset, length) tuples, where devindex
+ * references a devdax device that must be retrievable via the GET_DAXDEV
+ * message/response.
+ *
+ * The extent list size must be >= file_size.
+ *
+ * Interleaved extents merit some additional explanation. Interleaved
+ * extents stripe data across a collection of strips. Each strip is a
+ * contiguous allocation from a single devdax device - and is described by
+ * a simple_extent structure.
+ *
+ * Interleaved_extent example:
+ *   ie_nstrips = 4
+ *   ie_chunk_size = 2MiB
+ *   ie_nbytes = 24MiB
+ *
+ * ┌────────────┐────────────┐────────────┐────────────┐
+ * │Chunk = 0   │Chunk = 1   │Chunk = 2   │Chunk = 3   │
+ * │Strip = 0   │Strip = 1   │Strip = 2   │Strip = 3   │
+ * │Stripe = 0  │Stripe = 0  │Stripe = 0  │Stripe = 0  │
+ * │            │            │            │            │
+ * └────────────┘────────────┘────────────┘────────────┘
+ * │Chunk = 4   │Chunk = 5   │Chunk = 6   │Chunk = 7   │
+ * │Strip = 0   │Strip = 1   │Strip = 2   │Strip = 3   │
+ * │Stripe = 1  │Stripe = 1  │Stripe = 1  │Stripe = 1  │
+ * │            │            │            │            │
+ * └────────────┘────────────┘────────────┘────────────┘
+ * │Chunk = 8   │Chunk = 9   │Chunk = 10  │Chunk = 11  │
+ * │Strip = 0   │Strip = 1   │Strip = 2   │Strip = 3   │
+ * │Stripe = 2  │Stripe = 2  │Stripe = 2  │Stripe = 2  │
+ * │            │            │            │            │
+ * └────────────┘────────────┘────────────┘────────────┘
+ *
+ * * Data is laid out across chunks in chunk # order
+ * * Columns are strips
+ * * Strips are contiguous devdax extents, normally each coming from a
+ *   different memory device
+ * * Rows are stripes
+ * * The number of chunks is (int)((file_size + chunk_size - 1) / chunk_size)
+ *   (and obviously the last chunk could be partial)
+ * * The stripe_size = (nstrips * chunk_size)
+ * * chunk_num(offset) = offset / chunk_size    //integer division
+ * * strip_num(offset) = chunk_num(offset) % nchunks
+ * * stripe_num(offset) = offset / stripe_size  //integer division
+ * * ...You get the idea - see the code for more details...
+ *
+ * Some concrete examples from the layout above:
+ * * Offset 0 in the file is offset 0 in chunk 0, which is offset 0 in
+ *   strip 0
+ * * Offset 4MiB in the file is offset 0 in chunk 2, which is offset 0 in
+ *   strip 2
+ * * Offset 15MiB in the file is offset 1MiB in chunk 7, which is offset
+ *   3MiB in strip 3
+ *
+ * Notes about this metadata format:
+ *
+ * * For various reasons, chunk_size must be a multiple of the applicable
+ *   PAGE_SIZE
+ * * Since chunk_size and nstrips are constant within an interleaved_extent,
+ *   resolving a file offset to a strip offset within a single
+ *   interleaved_ext is order 1.
+ * * If nstrips==1, a list of interleaved_ext structures degenerates to a
+ *   regular extent list (albeit with some wasted struct space).
+ */
+
 /*
  * The structures below are the in-memory metadata format for famfs files.
  * Metadata retrieved via the GET_FMAP response is converted to this format
-- 
2.52.0

[PATCH V4 19/19] famfs_fuse: Add documentation

[John Groves]

Add Documentation/filesystems/famfs.rst and update MAINTAINERS

Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Signed-off-by: John Groves <john@groves.net>
---
 Documentation/filesystems/famfs.rst | 142 ++++++++++++++++++++++++++++
 Documentation/filesystems/index.rst |   1 +
 MAINTAINERS                         |   1 +
 3 files changed, 144 insertions(+)
 create mode 100644 Documentation/filesystems/famfs.rst

diff --git a/Documentation/filesystems/famfs.rst b/Documentation/filesystems/famfs.rst
new file mode 100644
index 000000000000..bf0c0e6574bb
--- /dev/null
+++ b/Documentation/filesystems/famfs.rst
@@ -0,0 +1,142 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. _famfs_index:
+
+==================================================================
+famfs: The fabric-attached memory file system
+==================================================================
+
+- Copyright (C) 2024-2026 Micron Technology, Inc.
+
+Introduction
+============
+Compute Express Link (CXL) provides a mechanism for disaggregated or
+fabric-attached memory (FAM). This creates opportunities for data sharing;
+clustered apps that would otherwise have to shard or replicate data can
+share one copy in disaggregated memory.
+
+Famfs, which is not CXL-specific in any way, provides a mechanism for
+multiple hosts to concurrently access data in shared memory, by giving it
+a file system interface. With famfs, any app that understands files can
+access data sets in shared memory. Although famfs supports read and write,
+the real point is to support mmap, which provides direct (dax) access to
+the memory - either writable or read-only.
+
+Shared memory can pose complex coherency and synchronization issues, but
+there are also simple cases. Two simple and eminently useful patterns that
+occur frequently in data analytics and AI are:
+
+* Serial Sharing - Only one host or process at a time has access to a file
+* Read-only Sharing - Multiple hosts or processes share read-only access
+  to a file
+
+The famfs fuse file system is part of the famfs framework; user space
+components [1] handle metadata allocation and distribution, and provide a
+low-level fuse server to expose files that map directly to [presumably
+shared] memory.
+
+The famfs framework manages coherency of its own metadata and structures,
+but does not attempt to manage coherency for applications.
+
+Famfs also provides data isolation between files. That is, even though
+the host has access to an entire memory "device" (as a devdax device), apps
+cannot write to memory for which the file is read-only, and mapping one
+file provides isolation from the memory of all other files. This is pretty
+basic, but some experimental shared memory usage patterns provide no such
+isolation.
+
+Principles of Operation
+=======================
+
+Famfs is a file system with one or more devdax devices as a first-class
+backing device(s). Metadata maintenance and query operations happen
+entirely in user space.
+
+The famfs low-level fuse server daemon provides file maps (fmaps) and
+devdax device info to the fuse/famfs kernel component so that
+read/write/mapping faults can be handled without up-calls for all active
+files.
+
+The famfs user space is responsible for maintaining and distributing
+consistent metadata. This is currently handled via an append-only
+metadata log within the memory, but this is orthogonal to the fuse/famfs
+kernel code.
+
+Once instantiated, "the same file" on each host points to the same shared
+memory, but in-memory metadata (inodes, etc.) is ephemeral on each host
+that has a famfs instance mounted. Use cases are free to allow or not
+allow mutations to data on a file-by-file basis.
+
+When an app accesses a data object in a famfs file, there is no page cache
+involvement. The CPU cache is loaded directly from the shared memory. In
+some use cases, this is an enormous reduction read amplification compared
+to loading an entire page into the page cache.
+
+
+Famfs is Not a Conventional File System
+---------------------------------------
+
+Famfs files can be accessed by conventional means, but there are
+limitations. The kernel component of fuse/famfs is not involved in the
+allocation of backing memory for files at all; the famfs user space
+creates files and responds as a low-level fuse server with fmaps and
+devdax device info upon request.
+
+Famfs differs in some important ways from conventional file systems:
+
+* Files must be pre-allocated by the famfs framework; allocation is never
+  performed on (or after) write.
+* Any operation that changes a file's size is considered to put the file
+  in an invalid state, disabling access to the data. It may be possible to
+  revisit this in the future. (Typically the famfs user space can restore
+  files to a valid state by replaying the famfs metadata log.)
+
+Famfs exists to apply the existing file system abstractions to shared
+memory so applications and workflows can more easily adapt to an
+environment with disaggregated shared memory.
+
+Memory Error Handling
+=====================
+
+Possible memory errors include timeouts, poison and unexpected
+reconfiguration of an underlying dax device. In all of these cases, famfs
+receives a call from the devdax layer via its iomap_ops->notify_failure()
+function. If any memory errors have been detected, access to the affected
+daxdev is disabled to avoid further errors or corruption.
+
+In all known cases, famfs can be unmounted cleanly. In most cases errors
+can be cleared by re-initializing the memory - at which point a new famfs
+file system can be created.
+
+Key Requirements
+================
+
+The primary requirements for famfs are:
+
+1. Must support a file system abstraction backed by sharable devdax memory
+2. Files must efficiently handle VMA faults
+3. Must support metadata distribution in a sharable way
+4. Must handle clients with a stale copy of metadata
+
+The famfs kernel component takes care of 1-2 above by caching each file's
+mapping metadata in the kernel.
+
+Requirements 3 and 4 are handled by the user space components, and are
+largely orthogonal to the functionality of the famfs kernel module.
+
+Requirements 3 and 4 cannot be met by conventional fs-dax file systems
+(e.g. xfs) because they use write-back metadata; it is not valid to mount
+such a file system on two hosts from the same in-memory image.
+
+
+Famfs Usage
+===========
+
+Famfs usage is documented at [1].
+
+
+References
+==========
+
+- [1] Famfs user space repository and documentation
+      https://github.com/cxl-micron-reskit/famfs
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index f4873197587d..e6fb467c1680 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -89,6 +89,7 @@ Documentation for filesystem implementations.
    ext3
    ext4/index
    f2fs
+   famfs
    gfs2/index
    hfs
    hfsplus
diff --git a/MAINTAINERS b/MAINTAINERS
index 6f8a7c813c2f..43141ee4fd4e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10385,6 +10385,7 @@ M:	John Groves <John@Groves.net>
 L:	linux-cxl@vger.kernel.org
 L:	linux-fsdevel@vger.kernel.org
 S:	Supported
+F:	Documentation/filesystems/famfs.rst
 F:	fs/fuse/famfs.c
 F:	fs/fuse/famfs_kfmap.h
 
-- 
2.52.0

[PATCH V4 0/3]

[John Groves]

This short series adds adds the necessary support for famfs to libfuse.

This series is also a pull request at [1].

Changes since V3:
- The patch "add API to set kernel mount options" has been dropped. I found
  a way to accomplish the same thing via getxattr.

References

[1] - https://github.com/libfuse/libfuse/pull/1414


John Groves (3):
  fuse_kernel.h: bring up to baseline 6.19
  fuse_kernel.h: add famfs DAX fmap protocol definitions
  fuse: add famfs DAX fmap support

 include/fuse_common.h   |  5 +++
 include/fuse_kernel.h   | 98 ++++++++++++++++++++++++++++++++++++++++-
 include/fuse_lowlevel.h | 37 ++++++++++++++++
 lib/fuse_lowlevel.c     | 31 ++++++++++++-
 patch/maintainers.txt   |  0
 5 files changed, 169 insertions(+), 2 deletions(-)
 create mode 100644 patch/maintainers.txt


base-commit: 6278995cca991978abd25ebb2c20ebd3fc9e8a13
-- 
2.52.0

[PATCH V4 1/3] fuse_kernel.h: bring up to baseline 6.19

[John Groves]

This is copied from include/uapi/linux/fuse.h in 6.19 with no changes.

Signed-off-by: John Groves <john@groves.net>
---
 include/fuse_kernel.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/fuse_kernel.h b/include/fuse_kernel.h
index 94621f6..c13e1f9 100644
--- a/include/fuse_kernel.h
+++ b/include/fuse_kernel.h
@@ -239,6 +239,7 @@
  *  7.45
  *  - add FUSE_COPY_FILE_RANGE_64
  *  - add struct fuse_copy_file_range_out
+ *  - add FUSE_NOTIFY_PRUNE
  */
 
 #ifndef _LINUX_FUSE_H
@@ -680,7 +681,7 @@ enum fuse_notify_code {
 	FUSE_NOTIFY_DELETE = 6,
 	FUSE_NOTIFY_RESEND = 7,
 	FUSE_NOTIFY_INC_EPOCH = 8,
-	FUSE_NOTIFY_CODE_MAX,
+	FUSE_NOTIFY_PRUNE = 9,
 };
 
 /* The read buffer is required to be at least 8k, but may be much larger */
@@ -1119,6 +1120,12 @@ struct fuse_notify_retrieve_in {
 	uint64_t	dummy4;
 };
 
+struct fuse_notify_prune_out {
+	uint32_t	count;
+	uint32_t	padding;
+	uint64_t	spare;
+};
+
 struct fuse_backing_map {
 	int32_t		fd;
 	uint32_t	flags;
@@ -1131,6 +1138,7 @@ struct fuse_backing_map {
 #define FUSE_DEV_IOC_BACKING_OPEN	_IOW(FUSE_DEV_IOC_MAGIC, 1, \
 					     struct fuse_backing_map)
 #define FUSE_DEV_IOC_BACKING_CLOSE	_IOW(FUSE_DEV_IOC_MAGIC, 2, uint32_t)
+#define FUSE_DEV_IOC_SYNC_INIT		_IO(FUSE_DEV_IOC_MAGIC, 3)
 
 struct fuse_lseek_in {
 	uint64_t	fh;
-- 
2.52.0

[PATCH V4 2/3] fuse_kernel.h: add famfs DAX fmap protocol definitions

[John Groves]

Add FUSE protocol version 7.46 definitions for famfs DAX file mapping:

Capability flag:
  - FUSE_DAX_FMAP (bit 43): kernel supports DAX fmap operations

New opcodes:
  - FUSE_GET_FMAP (54): retrieve file extent map for DAX mapping
  - FUSE_GET_DAXDEV (55): retrieve DAX device info by index

New structures for GET_FMAP reply:
  - struct fuse_famfs_fmap_header: file map header with type and extent info
  - struct fuse_famfs_simple_ext: simple extent (device, offset, length)
  - struct fuse_famfs_iext: interleaved extent for striped allocations

New structures for GET_DAXDEV:
  - struct fuse_get_daxdev_in: request DAX device by index
  - struct fuse_daxdev_out: DAX device name response

Supporting definitions:
  - enum fuse_famfs_file_type: regular, superblock, or log file
  - enum famfs_ext_type: simple or interleaved extent type

Signed-off-by: John Groves <john@groves.net>
---
 include/fuse_kernel.h | 88 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 88 insertions(+)

diff --git a/include/fuse_kernel.h b/include/fuse_kernel.h
index c13e1f9..7fdfc30 100644
--- a/include/fuse_kernel.h
+++ b/include/fuse_kernel.h
@@ -240,6 +240,19 @@
  *  - add FUSE_COPY_FILE_RANGE_64
  *  - add struct fuse_copy_file_range_out
  *  - add FUSE_NOTIFY_PRUNE
+ *
+ *  7.46
+ *    - Add FUSE_DAX_FMAP capability - ability to handle in-kernel fsdax maps
+ *    - Add the following structures for the GET_FMAP message reply components:
+ *      - struct fuse_famfs_simple_ext
+ *      - struct fuse_famfs_iext
+ *      - struct fuse_famfs_fmap_header
+ *    - Add the following structs for the GET_DAXDEV message and reply
+ *      - struct fuse_get_daxdev_in
+ *      - struct fuse_get_daxdev_out
+ *    - Add the following enumerated types
+ *      - enum fuse_famfs_file_type
+ *      - enum famfs_ext_type
  */
 
 #ifndef _LINUX_FUSE_H
@@ -448,6 +461,7 @@ struct fuse_file_lock {
  * FUSE_OVER_IO_URING: Indicate that client supports io-uring
  * FUSE_REQUEST_TIMEOUT: kernel supports timing out requests.
  *			 init_out.request_timeout contains the timeout (in secs)
+ * FUSE_DAX_FMAP:        kernel supports dev_dax_iomap (aka famfs) fmaps
  */
 #define FUSE_ASYNC_READ		(1 << 0)
 #define FUSE_POSIX_LOCKS	(1 << 1)
@@ -495,6 +509,7 @@ struct fuse_file_lock {
 #define FUSE_ALLOW_IDMAP	(1ULL << 40)
 #define FUSE_OVER_IO_URING	(1ULL << 41)
 #define FUSE_REQUEST_TIMEOUT	(1ULL << 42)
+#define FUSE_DAX_FMAP		(1ULL << 43)
 
 /**
  * CUSE INIT request/reply flags
@@ -664,6 +679,10 @@ enum fuse_opcode {
 	FUSE_STATX		= 52,
 	FUSE_COPY_FILE_RANGE_64	= 53,
 
+	/* Famfs / devdax opcodes */
+	FUSE_GET_FMAP           = 54,
+	FUSE_GET_DAXDEV         = 55,
+
 	/* CUSE specific operations */
 	CUSE_INIT		= 4096,
 
@@ -1308,4 +1327,73 @@ struct fuse_uring_cmd_req {
 	uint8_t padding[6];
 };
 
+/* Famfs fmap message components */
+
+#define FAMFS_FMAP_VERSION 1
+
+#define FAMFS_FMAP_MAX 32768 /* Largest supported fmap message */
+#define FUSE_FAMFS_MAX_EXTENTS 32
+#define FUSE_FAMFS_MAX_STRIPS 32
+
+enum fuse_famfs_file_type {
+	FUSE_FAMFS_FILE_REG,
+	FUSE_FAMFS_FILE_SUPERBLOCK,
+	FUSE_FAMFS_FILE_LOG,
+};
+
+enum famfs_ext_type {
+	FUSE_FAMFS_EXT_SIMPLE = 0,
+	FUSE_FAMFS_EXT_INTERLEAVE = 1,
+};
+
+struct fuse_famfs_simple_ext {
+	uint32_t se_devindex;
+	uint32_t reserved;
+	uint64_t se_offset;
+	uint64_t se_len;
+};
+
+struct fuse_famfs_iext { /* Interleaved extent */
+	uint32_t ie_nstrips;
+	uint32_t ie_chunk_size;
+	uint64_t ie_nbytes; /* Total bytes for this interleaved_ext;
+			     * sum of strips may be more
+			     */
+	uint64_t reserved;
+};
+
+struct fuse_famfs_fmap_header {
+	uint8_t file_type; /* enum famfs_file_type */
+	uint8_t reserved;
+	uint16_t fmap_version;
+	uint32_t ext_type; /* enum famfs_log_ext_type */
+	uint32_t nextents;
+	uint32_t reserved0;
+	uint64_t file_size;
+	uint64_t reserved1;
+};
+
+struct fuse_get_daxdev_in {
+	uint32_t        daxdev_num;
+};
+
+#define DAXDEV_NAME_MAX 256
+
+/* fuse_daxdev_out has enough space for a uuid if we need it */
+struct fuse_daxdev_out {
+	uint16_t index;
+	uint16_t reserved;
+	uint32_t reserved2;
+	uint64_t reserved3;
+	uint64_t reserved4;
+	char name[DAXDEV_NAME_MAX];
+};
+
+static __inline__ int32_t fmap_msg_min_size(void)
+{
+	/* Smallest fmap message is a header plus one simple extent */
+	return (sizeof(struct fuse_famfs_fmap_header)
+		+ sizeof(struct fuse_famfs_simple_ext));
+}
+
 #endif /* _LINUX_FUSE_H */
-- 
2.52.0

[PATCH V4 3/3] fuse: add famfs DAX fmap support

[John Groves]

Add new FUSE operations and capability for famfs DAX file mapping:

- FUSE_CAP_DAX_FMAP: New capability flag at bit 32 (using want_ext/capable_ext
  fields) to indicate kernel and userspace support for DAX fmaps

- GET_FMAP: New operation to retrieve a file map for DAX-mapped files.
  Returns a fuse_famfs_fmap_header followed by simple or interleaved
  extent descriptors. The kernel passes the file size as an argument.

- GET_DAXDEV: New operation to retrieve DAX device info by index.
  Called when GET_FMAP returns an fmap referencing a previously
  unknown DAX device.

These operations enable FUSE filesystems to provide direct access
mappings to persistent memory, allowing the kernel to map files
directly to DAX devices without page cache intermediation.

Signed-off-by: John Groves <john@groves.net>
---
 include/fuse_common.h   |  5 +++++
 include/fuse_lowlevel.h | 37 +++++++++++++++++++++++++++++++++++++
 lib/fuse_lowlevel.c     | 31 ++++++++++++++++++++++++++++++-
 patch/maintainers.txt   |  0
 4 files changed, 72 insertions(+), 1 deletion(-)
 create mode 100644 patch/maintainers.txt

diff --git a/include/fuse_common.h b/include/fuse_common.h
index 041188e..23b24e8 100644
--- a/include/fuse_common.h
+++ b/include/fuse_common.h
@@ -512,6 +512,11 @@ struct fuse_loop_config_v1 {
  */
 #define FUSE_CAP_OVER_IO_URING (1UL << 31)
 
+/**
+ * handle files that use famfs dax fmaps
+ */
+#define FUSE_CAP_DAX_FMAP (1UL << 32)
+
 /**
  * Ioctl flags
  *
diff --git a/include/fuse_lowlevel.h b/include/fuse_lowlevel.h
index 016f831..a94436a 100644
--- a/include/fuse_lowlevel.h
+++ b/include/fuse_lowlevel.h
@@ -1341,6 +1341,43 @@ struct fuse_lowlevel_ops {
 	 */
 	void (*statx)(fuse_req_t req, fuse_ino_t ino, int flags, int mask,
 		      struct fuse_file_info *fi);
+
+	/**
+	 * Get a famfs/devdax/fsdax fmap
+	 *
+	 * Retrieve a file map (aka fmap) for a previously looked-up file.
+	 * The fmap is serialized into the buffer, anchored by
+	 * struct fuse_famfs_fmap_header, followed by one or more
+	 * structs fuse_famfs_simple_ext, or fuse_famfs_iext (which itself
+	 * is followed by one or more fuse_famfs_simple_ext...
+	 *
+	 * Valid replies:
+	 *    fuse_reply_buf  (TODO: variable-size reply)
+	 *    fuse_reply_err
+	 *
+	 * @param req request handle
+	 * @param ino the inode number
+	 */
+	void (*get_fmap) (fuse_req_t req, fuse_ino_t ino, size_t size);
+
+	/**
+	 * Get a daxdev by index
+	 *
+	 * Retrieve info on a daxdev by index. This will be called any time
+	 * GET_FMAP has returned a file map that references a previously
+	 * unused daxdev. struct famfs_simple_ext, which is used for all
+	 * resolutions to daxdev offsets, references daxdevs by index.
+	 * In user space we maintain a master list of all referenced daxdevs
+	 * by index, which is queried by get_daxdev.
+	 *
+	 * Valid replies:
+	 *    fuse_reply_buf
+	 *    fuse_reply_err
+	 *
+	 * @param req request handle
+	 * @param ino the index of the daxdev
+	 */
+	void (*get_daxdev) (fuse_req_t req, int daxdev_index);
 };
 
 /**
diff --git a/lib/fuse_lowlevel.c b/lib/fuse_lowlevel.c
index 0cde3d4..ac78233 100644
--- a/lib/fuse_lowlevel.c
+++ b/lib/fuse_lowlevel.c
@@ -2769,7 +2769,8 @@ _do_init(fuse_req_t req, const fuse_ino_t nodeid, const void *op_in,
 			se->conn.capable_ext |= FUSE_CAP_NO_EXPORT_SUPPORT;
 		if (inargflags & FUSE_OVER_IO_URING)
 			se->conn.capable_ext |= FUSE_CAP_OVER_IO_URING;
-
+		if (inargflags & FUSE_DAX_FMAP)
+			se->conn.capable_ext |= FUSE_CAP_DAX_FMAP;
 	} else {
 		se->conn.max_readahead = 0;
 	}
@@ -2932,6 +2933,8 @@ _do_init(fuse_req_t req, const fuse_ino_t nodeid, const void *op_in,
 		outargflags |= FUSE_REQUEST_TIMEOUT;
 		outarg.request_timeout = se->conn.request_timeout;
 	}
+	if (se->conn.want_ext & FUSE_CAP_DAX_FMAP)
+		outargflags |= FUSE_DAX_FMAP;
 
 	outarg.max_readahead = se->conn.max_readahead;
 	outarg.max_write = se->conn.max_write;
@@ -3035,6 +3038,30 @@ static void do_destroy(fuse_req_t req, fuse_ino_t nodeid, const void *inarg)
 	_do_destroy(req, nodeid, inarg, NULL);
 }
 
+static void
+do_get_fmap(fuse_req_t req, fuse_ino_t nodeid, const void *inarg)
+{
+	struct fuse_session *se = req->se;
+	struct fuse_getxattr_in *arg = (struct fuse_getxattr_in *) inarg;
+
+	if (se->op.get_fmap)
+		se->op.get_fmap(req, nodeid, arg->size);
+	else
+		fuse_reply_err(req, -EOPNOTSUPP);
+}
+
+static void
+do_get_daxdev(fuse_req_t req, fuse_ino_t nodeid, const void *inarg)
+{
+	struct fuse_session *se = req->se;
+	(void)inarg;
+
+	if (se->op.get_daxdev)
+		se->op.get_daxdev(req, nodeid); /* Use nodeid as daxdev_index */
+	else
+		fuse_reply_err(req, -EOPNOTSUPP);
+}
+
 static void list_del_nreq(struct fuse_notify_req *nreq)
 {
 	struct fuse_notify_req *prev = nreq->prev;
@@ -3470,6 +3497,8 @@ static struct {
 	[FUSE_LSEEK]	   = { do_lseek,       "LSEEK"	     },
 	[FUSE_STATX]	   = { do_statx,       "STATX"	     },
 	[CUSE_INIT]	   = { cuse_lowlevel_init, "CUSE_INIT"   },
+	[FUSE_GET_FMAP]	   = { do_get_fmap, "GET_FMAP"       },
+	[FUSE_GET_DAXDEV]  = { do_get_daxdev, "GET_DAXDEV"   },
 };
 
 static struct {
diff --git a/patch/maintainers.txt b/patch/maintainers.txt
new file mode 100644
index 0000000..e69de29
-- 
2.52.0

[PATCH V2 0/2] ndctl: Add daxctl support for the new "famfs" mode of devdax

[John Groves]

No change since V1 - reposting as v2 to keep this with the related
kernel (dax and fuse) patches and libfuse patches.

This short series adds support and tests to daxctl for famfs[1]. The
famfs kernel patch series, under the same "compound cover" as this
series, adds a new 'fsdev_dax' driver for devdax. When that driver
is bound (instead of device_dax), the device is in 'famfs' mode rather
than 'devdax' mode.

References

[1] - https://famfs.org


John Groves (2):
  daxctl: Add support for famfs mode
  Add test/daxctl-famfs.sh to test famfs mode transitions:

 daxctl/device.c                | 126 ++++++++++++++--
 daxctl/json.c                  |   6 +-
 daxctl/lib/libdaxctl-private.h |   2 +
 daxctl/lib/libdaxctl.c         |  77 ++++++++++
 daxctl/lib/libdaxctl.sym       |   7 +
 daxctl/libdaxctl.h             |   3 +
 test/daxctl-famfs.sh           | 253 +++++++++++++++++++++++++++++++++
 test/meson.build               |   2 +
 8 files changed, 465 insertions(+), 11 deletions(-)
 create mode 100755 test/daxctl-famfs.sh


base-commit: 4f7a1c63b3305c97013d3c46daa6c0f76feff10d
-- 
2.49.0

[PATCH V2 1/2] daxctl: Add support for famfs mode

[John Groves]

From: John Groves <John@Groves.net>

Putting a daxdev in famfs mode means binding it to fsdev_dax.ko
(drivers/dax/fsdev.c). Finding a daxdev bound to fsdev_dax means
it is in famfs mode.

The test is added to the destructive test suite since it
modifies device modes.

With devdax, famfs, and system-ram modes, the previous logic that assumed
'not in mode X means in mode Y' needed to get slightly more complicated

Add explicit mode detection functions:
- daxctl_dev_is_famfs_mode(): check if bound to fsdev_dax driver
- daxctl_dev_is_devdax_mode(): check if bound to device_dax driver

Fix mode transition logic in device.c:
- disable_devdax_device(): verify device is actually in devdax mode
- disable_famfs_device(): verify device is actually in famfs mode
- All reconfig_mode_*() functions now explicitly check each mode
- Handle unknown mode with error instead of wrong assumption

Modify json.c to show 'unknown' if device is not in a recognized mode.

Signed-off-by: John Groves <john@groves.net>
---
 daxctl/device.c                | 126 ++++++++++++++++++++++++++++++---
 daxctl/json.c                  |   6 +-
 daxctl/lib/libdaxctl-private.h |   2 +
 daxctl/lib/libdaxctl.c         |  77 ++++++++++++++++++++
 daxctl/lib/libdaxctl.sym       |   7 ++
 daxctl/libdaxctl.h             |   3 +
 6 files changed, 210 insertions(+), 11 deletions(-)

diff --git a/daxctl/device.c b/daxctl/device.c
index e3993b1..14e1796 100644
--- a/daxctl/device.c
+++ b/daxctl/device.c
@@ -42,6 +42,7 @@ enum dev_mode {
 	DAXCTL_DEV_MODE_UNKNOWN,
 	DAXCTL_DEV_MODE_DEVDAX,
 	DAXCTL_DEV_MODE_RAM,
+	DAXCTL_DEV_MODE_FAMFS,
 };
 
 struct mapping {
@@ -471,6 +472,13 @@ static const char *parse_device_options(int argc, const char **argv,
 					"--no-online is incompatible with --mode=devdax\n");
 				rc =  -EINVAL;
 			}
+		} else if (strcmp(param.mode, "famfs") == 0) {
+			reconfig_mode = DAXCTL_DEV_MODE_FAMFS;
+			if (param.no_online) {
+				fprintf(stderr,
+					"--no-online is incompatible with --mode=famfs\n");
+				rc =  -EINVAL;
+			}
 		}
 		break;
 	case ACTION_CREATE:
@@ -696,8 +704,42 @@ static int disable_devdax_device(struct daxctl_dev *dev)
 	int rc;
 
 	if (mem) {
-		fprintf(stderr, "%s was already in system-ram mode\n",
-			devname);
+		fprintf(stderr, "%s is in system-ram mode\n", devname);
+		return 1;
+	}
+	if (daxctl_dev_is_famfs_mode(dev)) {
+		fprintf(stderr, "%s is in famfs mode\n", devname);
+		return 1;
+	}
+	if (!daxctl_dev_is_devdax_mode(dev)) {
+		fprintf(stderr, "%s is not in devdax mode\n", devname);
+		return 1;
+	}
+	rc = daxctl_dev_disable(dev);
+	if (rc) {
+		fprintf(stderr, "%s: disable failed: %s\n",
+			daxctl_dev_get_devname(dev), strerror(-rc));
+		return rc;
+	}
+	return 0;
+}
+
+static int disable_famfs_device(struct daxctl_dev *dev)
+{
+	struct daxctl_memory *mem = daxctl_dev_get_memory(dev);
+	const char *devname = daxctl_dev_get_devname(dev);
+	int rc;
+
+	if (mem) {
+		fprintf(stderr, "%s is in system-ram mode\n", devname);
+		return 1;
+	}
+	if (daxctl_dev_is_devdax_mode(dev)) {
+		fprintf(stderr, "%s is in devdax mode\n", devname);
+		return 1;
+	}
+	if (!daxctl_dev_is_famfs_mode(dev)) {
+		fprintf(stderr, "%s is not in famfs mode\n", devname);
 		return 1;
 	}
 	rc = daxctl_dev_disable(dev);
@@ -711,6 +753,7 @@ static int disable_devdax_device(struct daxctl_dev *dev)
 
 static int reconfig_mode_system_ram(struct daxctl_dev *dev)
 {
+	struct daxctl_memory *mem = daxctl_dev_get_memory(dev);
 	const char *devname = daxctl_dev_get_devname(dev);
 	int rc, skip_enable = 0;
 
@@ -724,11 +767,21 @@ static int reconfig_mode_system_ram(struct daxctl_dev *dev)
 	}
 
 	if (daxctl_dev_is_enabled(dev)) {
-		rc = disable_devdax_device(dev);
-		if (rc < 0)
-			return rc;
-		if (rc > 0)
+		if (mem) {
+			/* already in system-ram mode */
 			skip_enable = 1;
+		} else if (daxctl_dev_is_famfs_mode(dev)) {
+			rc = disable_famfs_device(dev);
+			if (rc)
+				return rc;
+		} else if (daxctl_dev_is_devdax_mode(dev)) {
+			rc = disable_devdax_device(dev);
+			if (rc)
+				return rc;
+		} else {
+			fprintf(stderr, "%s: unknown mode\n", devname);
+			return -EINVAL;
+		}
 	}
 
 	if (!skip_enable) {
@@ -750,7 +803,7 @@ static int disable_system_ram_device(struct daxctl_dev *dev)
 	int rc;
 
 	if (!mem) {
-		fprintf(stderr, "%s was already in devdax mode\n", devname);
+		fprintf(stderr, "%s is not in system-ram mode\n", devname);
 		return 1;
 	}
 
@@ -786,12 +839,28 @@ static int disable_system_ram_device(struct daxctl_dev *dev)
 
 static int reconfig_mode_devdax(struct daxctl_dev *dev)
 {
+	struct daxctl_memory *mem = daxctl_dev_get_memory(dev);
+	const char *devname = daxctl_dev_get_devname(dev);
 	int rc;
 
 	if (daxctl_dev_is_enabled(dev)) {
-		rc = disable_system_ram_device(dev);
-		if (rc)
-			return rc;
+		if (mem) {
+			rc = disable_system_ram_device(dev);
+			if (rc)
+				return rc;
+		} else if (daxctl_dev_is_famfs_mode(dev)) {
+			rc = disable_famfs_device(dev);
+			if (rc)
+				return rc;
+		} else if (daxctl_dev_is_devdax_mode(dev)) {
+			/* already in devdax mode, just re-enable */
+			rc = daxctl_dev_disable(dev);
+			if (rc)
+				return rc;
+		} else {
+			fprintf(stderr, "%s: unknown mode\n", devname);
+			return -EINVAL;
+		}
 	}
 
 	rc = daxctl_dev_enable_devdax(dev);
@@ -801,6 +870,40 @@ static int reconfig_mode_devdax(struct daxctl_dev *dev)
 	return 0;
 }
 
+static int reconfig_mode_famfs(struct daxctl_dev *dev)
+{
+	struct daxctl_memory *mem = daxctl_dev_get_memory(dev);
+	const char *devname = daxctl_dev_get_devname(dev);
+	int rc;
+
+	if (daxctl_dev_is_enabled(dev)) {
+		if (mem) {
+			fprintf(stderr,
+				"%s is in system-ram mode, must be in devdax mode to convert to famfs\n",
+				devname);
+			return -EINVAL;
+		} else if (daxctl_dev_is_famfs_mode(dev)) {
+			/* already in famfs mode, just re-enable */
+			rc = daxctl_dev_disable(dev);
+			if (rc)
+				return rc;
+		} else if (daxctl_dev_is_devdax_mode(dev)) {
+			rc = disable_devdax_device(dev);
+			if (rc)
+				return rc;
+		} else {
+			fprintf(stderr, "%s: unknown mode\n", devname);
+			return -EINVAL;
+		}
+	}
+
+	rc = daxctl_dev_enable_famfs(dev);
+	if (rc)
+		return rc;
+
+	return 0;
+}
+
 static int do_create(struct daxctl_region *region, long long val,
 		     struct json_object **jdevs)
 {
@@ -887,6 +990,9 @@ static int do_reconfig(struct daxctl_dev *dev, enum dev_mode mode,
 	case DAXCTL_DEV_MODE_DEVDAX:
 		rc = reconfig_mode_devdax(dev);
 		break;
+	case DAXCTL_DEV_MODE_FAMFS:
+		rc = reconfig_mode_famfs(dev);
+		break;
 	default:
 		fprintf(stderr, "%s: unknown mode requested: %d\n",
 			devname, mode);
diff --git a/daxctl/json.c b/daxctl/json.c
index 3cbce9d..01f139b 100644
--- a/daxctl/json.c
+++ b/daxctl/json.c
@@ -48,8 +48,12 @@ struct json_object *util_daxctl_dev_to_json(struct daxctl_dev *dev,
 
 	if (mem)
 		jobj = json_object_new_string("system-ram");
-	else
+	else if (daxctl_dev_is_famfs_mode(dev))
+		jobj = json_object_new_string("famfs");
+	else if (daxctl_dev_is_devdax_mode(dev))
 		jobj = json_object_new_string("devdax");
+	else
+		jobj = json_object_new_string("unknown");
 	if (jobj)
 		json_object_object_add(jdev, "mode", jobj);
 
diff --git a/daxctl/lib/libdaxctl-private.h b/daxctl/lib/libdaxctl-private.h
index ae45311..0bb73e8 100644
--- a/daxctl/lib/libdaxctl-private.h
+++ b/daxctl/lib/libdaxctl-private.h
@@ -21,12 +21,14 @@ static const char *dax_subsystems[] = {
 enum daxctl_dev_mode {
 	DAXCTL_DEV_MODE_DEVDAX = 0,
 	DAXCTL_DEV_MODE_RAM,
+	DAXCTL_DEV_MODE_FAMFS,
 	DAXCTL_DEV_MODE_END,
 };
 
 static const char *dax_modules[] = {
 	[DAXCTL_DEV_MODE_DEVDAX] = "device_dax",
 	[DAXCTL_DEV_MODE_RAM] = "kmem",
+	[DAXCTL_DEV_MODE_FAMFS] = "fsdev_dax",
 };
 
 enum memory_op {
diff --git a/daxctl/lib/libdaxctl.c b/daxctl/lib/libdaxctl.c
index b7fa0de..0a6cbfe 100644
--- a/daxctl/lib/libdaxctl.c
+++ b/daxctl/lib/libdaxctl.c
@@ -418,6 +418,78 @@ DAXCTL_EXPORT int daxctl_dev_is_system_ram_capable(struct daxctl_dev *dev)
 	return false;
 }
 
+/*
+ * Check if device is currently in famfs mode (bound to fsdev_dax driver)
+ */
+DAXCTL_EXPORT int daxctl_dev_is_famfs_mode(struct daxctl_dev *dev)
+{
+	const char *devname = daxctl_dev_get_devname(dev);
+	struct daxctl_ctx *ctx = daxctl_dev_get_ctx(dev);
+	char *mod_path, *mod_base;
+	char path[200];
+	const int len = sizeof(path);
+
+	if (!device_model_is_dax_bus(dev))
+		return false;
+
+	if (!daxctl_dev_is_enabled(dev))
+		return false;
+
+	if (snprintf(path, len, "%s/driver", dev->dev_path) >= len) {
+		err(ctx, "%s: buffer too small!\n", devname);
+		return false;
+	}
+
+	mod_path = realpath(path, NULL);
+	if (!mod_path)
+		return false;
+
+	mod_base = basename(mod_path);
+	if (strcmp(mod_base, dax_modules[DAXCTL_DEV_MODE_FAMFS]) == 0) {
+		free(mod_path);
+		return true;
+	}
+
+	free(mod_path);
+	return false;
+}
+
+/*
+ * Check if device is currently in devdax mode (bound to device_dax driver)
+ */
+DAXCTL_EXPORT int daxctl_dev_is_devdax_mode(struct daxctl_dev *dev)
+{
+	const char *devname = daxctl_dev_get_devname(dev);
+	struct daxctl_ctx *ctx = daxctl_dev_get_ctx(dev);
+	char *mod_path, *mod_base;
+	char path[200];
+	const int len = sizeof(path);
+
+	if (!device_model_is_dax_bus(dev))
+		return false;
+
+	if (!daxctl_dev_is_enabled(dev))
+		return false;
+
+	if (snprintf(path, len, "%s/driver", dev->dev_path) >= len) {
+		err(ctx, "%s: buffer too small!\n", devname);
+		return false;
+	}
+
+	mod_path = realpath(path, NULL);
+	if (!mod_path)
+		return false;
+
+	mod_base = basename(mod_path);
+	if (strcmp(mod_base, dax_modules[DAXCTL_DEV_MODE_DEVDAX]) == 0) {
+		free(mod_path);
+		return true;
+	}
+
+	free(mod_path);
+	return false;
+}
+
 /*
  * This checks for the device to be in system-ram mode, so calling
  * daxctl_dev_get_memory() on a devdax mode device will always return NULL.
@@ -982,6 +1054,11 @@ DAXCTL_EXPORT int daxctl_dev_enable_ram(struct daxctl_dev *dev)
 	return daxctl_dev_enable(dev, DAXCTL_DEV_MODE_RAM);
 }
 
+DAXCTL_EXPORT int daxctl_dev_enable_famfs(struct daxctl_dev *dev)
+{
+	return daxctl_dev_enable(dev, DAXCTL_DEV_MODE_FAMFS);
+}
+
 DAXCTL_EXPORT int daxctl_dev_disable(struct daxctl_dev *dev)
 {
 	const char *devname = daxctl_dev_get_devname(dev);
diff --git a/daxctl/lib/libdaxctl.sym b/daxctl/lib/libdaxctl.sym
index 3098811..2a812c6 100644
--- a/daxctl/lib/libdaxctl.sym
+++ b/daxctl/lib/libdaxctl.sym
@@ -104,3 +104,10 @@ LIBDAXCTL_10 {
 global:
 	daxctl_dev_is_system_ram_capable;
 } LIBDAXCTL_9;
+
+LIBDAXCTL_11 {
+global:
+	daxctl_dev_enable_famfs;
+	daxctl_dev_is_famfs_mode;
+	daxctl_dev_is_devdax_mode;
+} LIBDAXCTL_10;
diff --git a/daxctl/libdaxctl.h b/daxctl/libdaxctl.h
index 53c6bbd..84fcdb4 100644
--- a/daxctl/libdaxctl.h
+++ b/daxctl/libdaxctl.h
@@ -72,12 +72,15 @@ int daxctl_dev_is_enabled(struct daxctl_dev *dev);
 int daxctl_dev_disable(struct daxctl_dev *dev);
 int daxctl_dev_enable_devdax(struct daxctl_dev *dev);
 int daxctl_dev_enable_ram(struct daxctl_dev *dev);
+int daxctl_dev_enable_famfs(struct daxctl_dev *dev);
 int daxctl_dev_get_target_node(struct daxctl_dev *dev);
 int daxctl_dev_will_auto_online_memory(struct daxctl_dev *dev);
 int daxctl_dev_has_online_memory(struct daxctl_dev *dev);
 
 struct daxctl_memory;
 int daxctl_dev_is_system_ram_capable(struct daxctl_dev *dev);
+int daxctl_dev_is_famfs_mode(struct daxctl_dev *dev);
+int daxctl_dev_is_devdax_mode(struct daxctl_dev *dev);
 struct daxctl_memory *daxctl_dev_get_memory(struct daxctl_dev *dev);
 struct daxctl_dev *daxctl_memory_get_dev(struct daxctl_memory *mem);
 const char *daxctl_memory_get_node_path(struct daxctl_memory *mem);
-- 
2.49.0

[PATCH V2 2/2] Add test/daxctl-famfs.sh to test famfs mode transitions:

[John Groves]

From: John Groves <John@Groves.net>

- devdax <-> famfs mode switches
- Verify famfs -> system-ram is rejected (must go via devdax)
- Test JSON output shows correct mode
- Test error handling for invalid modes

The test is added to the destructive test suite since it
modifies device modes.

Signed-off-by: John Groves <john@groves.net>
---
 test/daxctl-famfs.sh | 253 +++++++++++++++++++++++++++++++++++++++++++
 test/meson.build     |   2 +
 2 files changed, 255 insertions(+)
 create mode 100755 test/daxctl-famfs.sh

diff --git a/test/daxctl-famfs.sh b/test/daxctl-famfs.sh
new file mode 100755
index 0000000..12fbfef
--- /dev/null
+++ b/test/daxctl-famfs.sh
@@ -0,0 +1,253 @@
+#!/bin/bash -Ex
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 Micron Technology, Inc. All rights reserved.
+#
+# Test daxctl famfs mode transitions and mode detection
+
+rc=77
+. $(dirname $0)/common
+
+trap 'cleanup $LINENO' ERR
+
+daxdev=""
+original_mode=""
+
+cleanup()
+{
+	printf "Error at line %d\n" "$1"
+	# Try to restore to original mode if we know it
+	if [[ $daxdev && $original_mode ]]; then
+		"$DAXCTL" reconfigure-device -f -m "$original_mode" "$daxdev" 2>/dev/null || true
+	fi
+	exit $rc
+}
+
+# Check if fsdev_dax module is available
+check_fsdev_dax()
+{
+	if modinfo fsdev_dax &>/dev/null; then
+		return 0
+	fi
+	if grep -qF "fsdev_dax" "/lib/modules/$(uname -r)/modules.builtin" 2>/dev/null; then
+		return 0
+	fi
+	printf "fsdev_dax module not available, skipping\n"
+	exit 77
+}
+
+# Check if kmem module is available (needed for system-ram mode tests)
+check_kmem()
+{
+	if modinfo kmem &>/dev/null; then
+		return 0
+	fi
+	if grep -qF "kmem" "/lib/modules/$(uname -r)/modules.builtin" 2>/dev/null; then
+		return 0
+	fi
+	printf "kmem module not available, skipping system-ram tests\n"
+	return 1
+}
+
+# Find an existing dax device to test with
+find_daxdev()
+{
+	# Look for any available dax device
+	daxdev=$("$DAXCTL" list | jq -er '.[0].chardev // empty' 2>/dev/null) || true
+
+	if [[ ! $daxdev ]]; then
+		printf "No dax device found, skipping\n"
+		exit 77
+	fi
+
+	# Save the original mode so we can restore it
+	original_mode=$("$DAXCTL" list -d "$daxdev" | jq -er '.[].mode')
+
+	printf "Found dax device: %s (current mode: %s)\n" "$daxdev" "$original_mode"
+}
+
+daxctl_get_mode()
+{
+	"$DAXCTL" list -d "$1" | jq -er '.[].mode'
+}
+
+# Ensure device is in devdax mode for testing
+ensure_devdax_mode()
+{
+	local mode
+	mode=$(daxctl_get_mode "$daxdev")
+
+	if [[ "$mode" == "devdax" ]]; then
+		return 0
+	fi
+
+	if [[ "$mode" == "system-ram" ]]; then
+		printf "Device is in system-ram mode, attempting to convert to devdax...\n"
+		"$DAXCTL" reconfigure-device -f -m devdax "$daxdev"
+	elif [[ "$mode" == "famfs" ]]; then
+		printf "Device is in famfs mode, converting to devdax...\n"
+		"$DAXCTL" reconfigure-device -m devdax "$daxdev"
+	else
+		printf "Device is in unknown mode: %s\n" "$mode"
+		return 1
+	fi
+
+	[[ $(daxctl_get_mode "$daxdev") == "devdax" ]]
+}
+
+#
+# Test basic mode transitions involving famfs
+#
+test_famfs_mode_transitions()
+{
+	printf "\n=== Testing famfs mode transitions ===\n"
+
+	# Ensure starting in devdax mode
+	ensure_devdax_mode
+	[[ $(daxctl_get_mode "$daxdev") == "devdax" ]]
+	printf "Initial mode: devdax - OK\n"
+
+	# Test: devdax -> famfs
+	printf "Testing devdax -> famfs... "
+	"$DAXCTL" reconfigure-device -m famfs "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "famfs" ]]
+	printf "OK\n"
+
+	# Test: famfs -> famfs (re-enable in same mode)
+	printf "Testing famfs -> famfs (re-enable)... "
+	"$DAXCTL" reconfigure-device -m famfs "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "famfs" ]]
+	printf "OK\n"
+
+	# Test: famfs -> devdax
+	printf "Testing famfs -> devdax... "
+	"$DAXCTL" reconfigure-device -m devdax "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "devdax" ]]
+	printf "OK\n"
+
+	# Test: devdax -> devdax (re-enable in same mode)
+	printf "Testing devdax -> devdax (re-enable)... "
+	"$DAXCTL" reconfigure-device -m devdax "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "devdax" ]]
+	printf "OK\n"
+}
+
+#
+# Test mode transitions with system-ram (requires kmem)
+#
+test_system_ram_transitions()
+{
+	printf "\n=== Testing system-ram transitions with famfs ===\n"
+
+	# Ensure we start in devdax mode
+	ensure_devdax_mode
+	[[ $(daxctl_get_mode "$daxdev") == "devdax" ]]
+
+	# Test: devdax -> system-ram
+	printf "Testing devdax -> system-ram... "
+	"$DAXCTL" reconfigure-device -N -m system-ram "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "system-ram" ]]
+	printf "OK\n"
+
+	# Test: system-ram -> famfs should fail
+	printf "Testing system-ram -> famfs (should fail)... "
+	if "$DAXCTL" reconfigure-device -m famfs "$daxdev" 2>/dev/null; then
+		printf "FAILED - should have been rejected\n"
+		return 1
+	fi
+	printf "OK (correctly rejected)\n"
+
+	# Test: system-ram -> devdax -> famfs (proper path)
+	printf "Testing system-ram -> devdax -> famfs... "
+	"$DAXCTL" reconfigure-device -f -m devdax "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "devdax" ]]
+	"$DAXCTL" reconfigure-device -m famfs "$daxdev"
+	[[ $(daxctl_get_mode "$daxdev") == "famfs" ]]
+	printf "OK\n"
+
+	# Restore to devdax for subsequent tests
+	"$DAXCTL" reconfigure-device -m devdax "$daxdev"
+}
+
+#
+# Test JSON output shows correct mode
+#
+test_json_output()
+{
+	printf "\n=== Testing JSON output for mode field ===\n"
+
+	# Test devdax mode in JSON
+	ensure_devdax_mode
+	printf "Testing JSON output for devdax mode... "
+	mode=$("$DAXCTL" list -d "$daxdev" | jq -er '.[].mode')
+	[[ "$mode" == "devdax" ]]
+	printf "OK\n"
+
+	# Test famfs mode in JSON
+	"$DAXCTL" reconfigure-device -m famfs "$daxdev"
+	printf "Testing JSON output for famfs mode... "
+	mode=$("$DAXCTL" list -d "$daxdev" | jq -er '.[].mode')
+	[[ "$mode" == "famfs" ]]
+	printf "OK\n"
+
+	# Restore to devdax
+	"$DAXCTL" reconfigure-device -m devdax "$daxdev"
+}
+
+#
+# Test error messages for invalid transitions
+#
+test_error_handling()
+{
+	printf "\n=== Testing error handling ===\n"
+
+	# Ensure we're in famfs mode
+	"$DAXCTL" reconfigure-device -m famfs "$daxdev"
+
+	# Test that invalid mode is rejected
+	printf "Testing invalid mode rejection... "
+	if "$DAXCTL" reconfigure-device -m invalidmode "$daxdev" 2>/dev/null; then
+		printf "FAILED - invalid mode should be rejected\n"
+		return 1
+	fi
+	printf "OK (correctly rejected)\n"
+
+	# Restore to devdax
+	"$DAXCTL" reconfigure-device -m devdax "$daxdev"
+}
+
+#
+# Main test sequence
+#
+main()
+{
+	check_fsdev_dax
+	find_daxdev
+
+	rc=1  # From here on, failures are real failures
+
+	test_famfs_mode_transitions
+	test_json_output
+	test_error_handling
+
+	# System-ram tests require kmem module
+	if check_kmem; then
+		# Save and disable online policy for system-ram tests
+		saved_policy="$(cat /sys/devices/system/memory/auto_online_blocks)"
+		echo "offline" > /sys/devices/system/memory/auto_online_blocks
+
+		test_system_ram_transitions
+
+		# Restore online policy
+		echo "$saved_policy" > /sys/devices/system/memory/auto_online_blocks
+	fi
+
+	# Restore original mode
+	printf "\nRestoring device to original mode: %s\n" "$original_mode"
+	"$DAXCTL" reconfigure-device -f -m "$original_mode" "$daxdev"
+
+	printf "\n=== All famfs tests passed ===\n"
+
+	exit 0
+}
+
+main
diff --git a/test/meson.build b/test/meson.build
index 615376e..ad1d393 100644
--- a/test/meson.build
+++ b/test/meson.build
@@ -209,6 +209,7 @@ if get_option('destructive').enabled()
   device_dax_fio = find_program('device-dax-fio.sh')
   daxctl_devices = find_program('daxctl-devices.sh')
   daxctl_create = find_program('daxctl-create.sh')
+  daxctl_famfs = find_program('daxctl-famfs.sh')
   dm = find_program('dm.sh')
   mmap_test = find_program('mmap.sh')
 
@@ -226,6 +227,7 @@ if get_option('destructive').enabled()
     [ 'device-dax-fio.sh', device_dax_fio, 'dax'   ],
     [ 'daxctl-devices.sh', daxctl_devices, 'dax'   ],
     [ 'daxctl-create.sh',  daxctl_create,  'dax'   ],
+    [ 'daxctl-famfs.sh',   daxctl_famfs,   'dax'   ],
     [ 'dm.sh',             dm,		   'dax'   ],
     [ 'mmap.sh',           mmap_test,	   'dax'   ],
   ]
-- 
2.49.0