dax: Add fs_dax_get() func to prepare dax for fs-dax usage

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.

Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: John Groves <john@groves.net>
Link: https://patch.msgid.link/0100019d311d8750-75395c22-031b-4d5f-aebe-790dca656b87-000000@email.amazonses.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

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)
 {

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) \

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 +124,66 @@ 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) {
+		iput(&dax_dev->inode);
+		return -ENODEV;
+	}
+
+	device_lock(&dev_dax->dev);
+	if (!dev_dax->dev.driver) {
+		device_unlock(&dev_dax->dev);
+		iput(&dax_dev->inode);
+		return -ENODEV;
+	}
+	dax_drv = to_dax_drv(dev_dax->dev.driver);
+	if (dax_drv->type != DAXDRV_FSDEV_TYPE) {
+		device_unlock(&dev_dax->dev);
+		iput(&dax_dev->inode);
+		return -EOPNOTSUPP;
+	}
+	device_unlock(&dev_dax->dev);
+
+	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 */

include/linux/dax.h

@@ -130,7 +130,6 @@ 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)
 {
@@ -145,12 +144,12 @@ 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);
 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);
@@ -164,6 +163,15 @@ 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;