On Wed, 18 Mar 2026 20:28:37 -0500 John Groves <[email protected]> wrote:
> 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 <[email protected]> > Suggested-by: Gregory Price <[email protected]> > Signed-off-by: John Groves <[email protected]> A few comments inline. I think some of the code here could be moved to a helper library used by both this and device.c > --- > MAINTAINERS | 8 ++ > drivers/dax/Makefile | 6 + > drivers/dax/bus.c | 4 + > drivers/dax/bus.h | 1 + > drivers/dax/fsdev.c | 253 +++++++++++++++++++++++++++++++++++++++++++ > fs/dax.c | 1 + > include/linux/dax.h | 3 + > 7 files changed, 276 insertions(+) > create mode 100644 drivers/dax/fsdev.c > > diff --git a/MAINTAINERS b/MAINTAINERS > index 96ea84948d76..e83cfcf7e932 100644 > --- a/MAINTAINERS > +++ b/MAINTAINERS > @@ -7298,6 +7298,14 @@ L: [email protected] > S: Supported > F: drivers/dax/ > > +DEVICE DIRECT ACCESS (DAX) [fsdev_dax] > +M: John Groves <[email protected]> > +M: John Groves <[email protected]> > +L: [email protected] > +L: [email protected] > +S: Supported > +F: drivers/dax/fsdev.c > + > DEVICE FREQUENCY (DEVFREQ) > M: MyungJoo Ham <[email protected]> > M: Kyungmin Park <[email protected]> > 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 Why not throw in a new CONFIG_FSDAX_DEV and handle the dependencies in Kconfig? > + > 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/fsdev.c b/drivers/dax/fsdev.c > new file mode 100644 > index 000000000000..e5b4396ce401 > --- /dev/null > +++ b/drivers/dax/fsdev.c > +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; See below. I think you can useful reduce scope of this one. > + struct inode *inode; > + struct cdev *cdev; > + void *addr; > + int rc, i; > + There is a lot of duplication in here with dax/device.c Is any of it suitable for shared helpers? > + 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); Bonus space before 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; > + } > + } Everything above here is shared. Some sort of _init() or similar library function seems in order. > + > + /* > + * 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). Also register this > + * as a devm action so folio state is cleared on unbind, ensuring > + * clean pages for subsequent drivers (e.g., kmem for system-ram). > + */ > + fsdev_clear_folio_state(dev_dax); > + rc = devm_add_action_or_reset(dev, fsdev_clear_folio_state_action, > + dev_dax); > + if (rc) > + return rc; > + > + /* Detect whether the data is at a non-zero offset into the memory */ > + if (pgmap->range.start != dev_dax->ranges[0].range.start) { > + u64 phys = dev_dax->ranges[0].range.start; > + u64 pgmap_phys = dev_dax->pgmap[0].range.start; > + > + 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); Might change later, but at least at this point you could pull declaration of data_offset into this scope. > + } > + > + 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); > +} > diff --git a/include/linux/dax.h b/include/linux/dax.h > index bf103f317cac..996493f5c538 100644 > --- a/include/linux/dax.h > +++ b/include/linux/dax.h > @@ -51,6 +51,7 @@ struct dax_holder_operations { > > #if IS_ENABLED(CONFIG_DAX) > struct dax_device *alloc_dax(void *private, const struct dax_operations > *ops); > + Unrelated change. Tidy this up for v9. > void *dax_holder(struct dax_device *dax_dev); > void put_dax(struct dax_device *dax_dev); > void kill_dax(struct dax_device *dax_dev); > @@ -151,8 +152,10 @@ 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) > +struct dax_device *inode_dax(struct inode *inode); Already in dax_private.h so why does it want to be here? > 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);
