dax: Add dax_operations for use by fs-dax on fsdev dax

fsdev: Add dax_operations for use by famfs.

This replicates the functionality from drivers/nvdimm/pmem.c that
conventional fs-dax file systems (e.g. xfs) use to support dax
read/write/mmap to a daxdev - without which famfs can't sit atop a
daxdev.

- 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>
Link: https://patch.msgid.link/0100019d311d415a-bd6af0fe-5445-484c-9d39-210b8170b686-000000@email.amazonses.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

drivers/dax/dax-private.h

@@ -70,6 +70,7 @@ struct dev_dax_range {
  * @region: parent region
  * @dax_dev: core dax functionality
  * @virt_addr: kva from memremap; used by fsdev_dax
+ * @cached_size: size of daxdev cached 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
@@ -85,6 +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;

drivers/dax/fsdev.c

@@ -28,6 +28,85 @@
  * - No mmap support - all access is through fs-dax/iomap
  */
 
+static void fsdev_write_dax(void *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(addr, mem + off, chunk);
+		kunmap_local(mem);
+		len -= chunk;
+		off = 0;
+		page++;
+		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;
+
+	phys = dax_pgoff_to_phys(dev_dax, pgoff, size);
+	if (phys == -1) {
+		dev_dbg(&dev_dax->dev,
+			"pgoff (%#lx) out of range\n", pgoff);
+		return -EFAULT;
+	}
+
+	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)
 {
 	cdev_del(cdev);
@@ -167,6 +246,11 @@ 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);
+
 	/*
 	 * Use MEMORY_DEVICE_FS_DAX without setting vmemmap_shift, leaving
 	 * folios at order-0. Unlike device.c (MEMORY_DEVICE_GENERIC), this