diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1cb7f5d..d297804 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -22,12 +22,48 @@
 #include "dev-replace.h"
 #include "sysfs.h"
 
+/*
+ * Device replace overview
+ *
+ * [Objective]
+ * To copy all extents (both new and on-disk) from source device to target
+ * device, while still keeping the filesystem read-write.
+ *
+ * [Method]
+ * There are two main methods involved:
+ *
+ * - Write duplication
+ *
+ *   All new writes will be written to both target and source devices, so even
+ *   if replace gets canceled, sources device still contans up-to-date data.
+ *
+ *   Location:		handle_ops_on_dev_replace() from __btrfs_map_block()
+ *   Start:		btrfs_dev_replace_start()
+ *   End:		btrfs_dev_replace_finishing()
+ *   Content:		Latest data/metadata
+ *
+ * - Copy existing extents
+ *
+ *   This happens by re-using scrub facility, as scrub also iterates through
+ *   existing extents from commit root.
+ *
+ *   Location:		scrub_write_block_to_dev_replace() from
+ *   			scrub_block_complete()
+ *   Content:		Data/meta from commit root.
+ *
+ * Due to the content difference, we need to avoid nocow write when dev-replace
+ * is happening.  This is done by marking the block group read-only and waiting
+ * for NOCOW writes.
+ *
+ * After replace is done, the finishing part is done by swapping the target and
+ * source devices.
+ *
+ *   Location:		btrfs_dev_replace_update_device_in_mapping_tree() from
+ *   			btrfs_dev_replace_finishing()
+ */
+
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 				       int scrub_ret);
-static void btrfs_dev_replace_update_device_in_mapping_tree(
-						struct btrfs_fs_info *fs_info,
-						struct btrfs_device *srcdev,
-						struct btrfs_device *tgtdev);
 static int btrfs_dev_replace_kthread(void *data);
 
 int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
@@ -206,7 +242,6 @@
 {
 	struct btrfs_device *device;
 	struct block_device *bdev;
-	struct list_head *devices;
 	struct rcu_string *name;
 	u64 devid = BTRFS_DEV_REPLACE_DEVID;
 	int ret = 0;
@@ -226,8 +261,7 @@
 
 	sync_blockdev(bdev);
 
-	devices = &fs_info->fs_devices->devices;
-	list_for_each_entry(device, devices, dev_list) {
+	list_for_each_entry(device, &fs_info->fs_devices->devices, dev_list) {
 		if (device->bdev == bdev) {
 			btrfs_err(fs_info,
 				  "target device is in the filesystem!");
@@ -494,7 +528,7 @@
 	atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
 	up_write(&dev_replace->rwsem);
 
-	ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
+	ret = btrfs_sysfs_add_device(tgt_device);
 	if (ret)
 		btrfs_err(fs_info, "kobj add dev failed %d", ret);
 
@@ -522,11 +556,8 @@
 			      &dev_replace->scrub_progress, 0, 1);
 
 	ret = btrfs_dev_replace_finishing(fs_info, ret);
-	if (ret == -EINPROGRESS) {
+	if (ret == -EINPROGRESS)
 		ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
-	} else if (ret != -ECANCELED) {
-		WARN_ON(ret);
-	}
 
 	return ret;
 
@@ -615,6 +646,32 @@
 	return ret;
 }
 
+static void btrfs_dev_replace_update_device_in_mapping_tree(
+						struct btrfs_fs_info *fs_info,
+						struct btrfs_device *srcdev,
+						struct btrfs_device *tgtdev)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 start = 0;
+	int i;
+
+	write_lock(&em_tree->lock);
+	do {
+		em = lookup_extent_mapping(em_tree, start, (u64)-1);
+		if (!em)
+			break;
+		map = em->map_lookup;
+		for (i = 0; i < map->num_stripes; i++)
+			if (srcdev == map->stripes[i].dev)
+				map->stripes[i].dev = tgtdev;
+		start = em->start + em->len;
+		free_extent_map(em);
+	} while (start);
+	write_unlock(&em_tree->lock);
+}
+
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 				       int scrub_ret)
 {
@@ -646,7 +703,7 @@
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, -1);
+	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
@@ -771,8 +828,11 @@
 	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 
 	/* replace the sysfs entry */
-	btrfs_sysfs_rm_device_link(fs_info->fs_devices, src_device);
-	btrfs_rm_dev_replace_free_srcdev(src_device);
+	btrfs_sysfs_remove_device(src_device);
+	btrfs_sysfs_update_devid(tgt_device);
+	if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &src_device->dev_state))
+		btrfs_scratch_superblocks(fs_info, src_device->bdev,
+					  src_device->name->str);
 
 	/* write back the superblocks */
 	trans = btrfs_start_transaction(root, 0);
@@ -781,35 +841,11 @@
 
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
+	btrfs_rm_dev_replace_free_srcdev(src_device);
+
 	return 0;
 }
 
-static void btrfs_dev_replace_update_device_in_mapping_tree(
-						struct btrfs_fs_info *fs_info,
-						struct btrfs_device *srcdev,
-						struct btrfs_device *tgtdev)
-{
-	struct extent_map_tree *em_tree = &fs_info->mapping_tree;
-	struct extent_map *em;
-	struct map_lookup *map;
-	u64 start = 0;
-	int i;
-
-	write_lock(&em_tree->lock);
-	do {
-		em = lookup_extent_mapping(em_tree, start, (u64)-1);
-		if (!em)
-			break;
-		map = em->map_lookup;
-		for (i = 0; i < map->num_stripes; i++)
-			if (srcdev == map->stripes[i].dev)
-				map->stripes[i].dev = tgtdev;
-		start = em->start + em->len;
-		free_extent_map(em);
-	} while (start);
-	write_unlock(&em_tree->lock);
-}
-
 /*
  * Read progress of device replace status according to the state and last
  * stored position. The value format is the same as for
@@ -1010,7 +1046,7 @@
 	 * should never allow both to start and pause. We don't want to allow
 	 * dev-replace to start anyway.
 	 */
-	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
+	if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_DEV_REPLACE)) {
 		down_write(&dev_replace->rwsem);
 		dev_replace->replace_state =
 					BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
@@ -1047,11 +1083,11 @@
 	ret = btrfs_dev_replace_finishing(fs_info, ret);
 	WARN_ON(ret && ret != -ECANCELED);
 
-	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
+	btrfs_exclop_finish(fs_info);
 	return 0;
 }
 
-int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
+int __pure btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
 {
 	if (!dev_replace->is_valid)
 		return 0;