dax: Add dax_set_ops() for setting dax_operations at bind time

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.

Reviewed-by: Dave Jiang <[email protected]>
Reviewed-by: Jonathan Cameron <[email protected]>
Signed-off-by: John Groves <[email protected]>
Link: https://patch.msgid.link/0100019d311d65a0-b9c1419e-f3a0-4afd-b0bd-848f18ff5950-000000@email.amazonses.com
Signed-off-by: Ira Weiny <[email protected]>

Author: jagalactic

drivers/dax/fsdev.c

@@ -117,6 +117,13 @@ 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
@@ -303,6 +310,15 @@ 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);
 }

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);

include/linux/dax.h

@@ -243,6 +243,7 @@ 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,