[PATCH v2 0/4] btrfs: rst: updates for RAID stripe tree

[PATCH v2 0/4] btrfs: rst: updates for RAID stripe tree

[Johannes Thumshirn]

Three independent updates for RAID stripe tree.
The 1st one removes pointless space from the on-disk format. As the
feature itself is still experimental I'd like to get rid of that as early
as possible.

Patch 2 replaces stripe extents in case we hit a EEXIST when inserting a
stripe extent on a write. This can happen i.e. on device-replace.

Patch 3 splits a stripe extent on partial delete of a stripe.

Patch 4 adds selftests for the stripe-tree delete code, these selftests
can and will be extended to cover insert and get as well

---
Changes in v2:
- Added selftests for delete code
- Link to v1: https://lore.kernel.org/r/20240610-b4-rst-updates-v1-0-179c1eec08f2@kernel.org

---
Johannes Thumshirn (4):
      btrfs: rst: remove encoding field from stripe_extent
      btrfs: replace stripe extents
      btrfs: split RAID stripes on deletion
      btrfs: stripe-tree: add selftests

 fs/btrfs/Makefile                       |   3 +-
 fs/btrfs/accessors.h                    |   3 -
 fs/btrfs/ctree.c                        |   1 +
 fs/btrfs/print-tree.c                   |   5 -
 fs/btrfs/raid-stripe-tree.c             | 150 ++++++++++++++-----
 fs/btrfs/raid-stripe-tree.h             |   8 +-
 fs/btrfs/tests/btrfs-tests.c            |   3 +
 fs/btrfs/tests/btrfs-tests.h            |   1 +
 fs/btrfs/tests/raid-stripe-tree-tests.c | 258 ++++++++++++++++++++++++++++++++
 fs/btrfs/tree-checker.c                 |  19 ---
 include/uapi/linux/btrfs_tree.h         |  14 +-
 11 files changed, 384 insertions(+), 81 deletions(-)
---
base-commit: 7f5983607be0823e94c20f565915faf9074a370d
change-id: 20240610-b4-rst-updates-d0aa696b9d5a

Best regards,
-- 
Johannes Thumshirn <jth@kernel.org>

[PATCH v2 1/4] btrfs: rst: remove encoding field from stripe_extent

[Johannes Thumshirn]

From: Johannes Thumshirn <johannes.thumshirn@wdc.com>

Remove the encoding field from 'struct btrfs_stripe_extent'. It was
originally intended to encode the RAID type as well as if we're a data
or a parity stripe.

But the RAID type can be inferred form the block-group and the data vs.
parity differentiation can be done easier with adding a new key type
for parity stripes in the RAID stripe tree.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/accessors.h            |  3 ---
 fs/btrfs/print-tree.c           |  5 -----
 fs/btrfs/raid-stripe-tree.c     | 13 -------------
 fs/btrfs/raid-stripe-tree.h     |  3 +--
 fs/btrfs/tree-checker.c         | 19 -------------------
 include/uapi/linux/btrfs_tree.h | 14 +-------------
 6 files changed, 2 insertions(+), 55 deletions(-)

diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h
index 6c3deaa3e878..b2eb9cde2c5d 100644
--- a/fs/btrfs/accessors.h
+++ b/fs/btrfs/accessors.h
@@ -315,11 +315,8 @@ BTRFS_SETGET_FUNCS(timespec_nsec, struct btrfs_timespec, nsec, 32);
 BTRFS_SETGET_STACK_FUNCS(stack_timespec_sec, struct btrfs_timespec, sec, 64);
 BTRFS_SETGET_STACK_FUNCS(stack_timespec_nsec, struct btrfs_timespec, nsec, 32);
 
-BTRFS_SETGET_FUNCS(stripe_extent_encoding, struct btrfs_stripe_extent, encoding, 8);
 BTRFS_SETGET_FUNCS(raid_stride_devid, struct btrfs_raid_stride, devid, 64);
 BTRFS_SETGET_FUNCS(raid_stride_physical, struct btrfs_raid_stride, physical, 64);
-BTRFS_SETGET_STACK_FUNCS(stack_stripe_extent_encoding,
-			 struct btrfs_stripe_extent, encoding, 8);
 BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_devid, struct btrfs_raid_stride, devid, 64);
 BTRFS_SETGET_STACK_FUNCS(stack_raid_stride_physical, struct btrfs_raid_stride, physical, 64);
 
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 7e46aa8a0444..9f1e5e11bf71 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -208,11 +208,6 @@ static void print_raid_stripe_key(const struct extent_buffer *eb, u32 item_size,
 				  struct btrfs_stripe_extent *stripe)
 {
 	const int num_stripes = btrfs_num_raid_stripes(item_size);
-	const u8 encoding = btrfs_stripe_extent_encoding(eb, stripe);
-
-	pr_info("\t\t\tencoding: %s\n",
-		(encoding && encoding < BTRFS_NR_RAID_TYPES) ?
-		btrfs_raid_array[encoding].raid_name : "unknown");
 
 	for (int i = 0; i < num_stripes; i++)
 		pr_info("\t\t\tstride %d devid %llu physical %llu\n",
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 6af6b4b9a32e..e6f7a234b8f6 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -80,7 +80,6 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_key stripe_key;
 	struct btrfs_root *stripe_root = fs_info->stripe_root;
 	const int num_stripes = btrfs_bg_type_to_factor(bioc->map_type);
-	u8 encoding = btrfs_bg_flags_to_raid_index(bioc->map_type);
 	struct btrfs_stripe_extent *stripe_extent;
 	const size_t item_size = struct_size(stripe_extent, strides, num_stripes);
 	int ret;
@@ -94,7 +93,6 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
 
 	trace_btrfs_insert_one_raid_extent(fs_info, bioc->logical, bioc->size,
 					   num_stripes);
-	btrfs_set_stack_stripe_extent_encoding(stripe_extent, encoding);
 	for (int i = 0; i < num_stripes; i++) {
 		u64 devid = bioc->stripes[i].dev->devid;
 		u64 physical = bioc->stripes[i].physical;
@@ -159,7 +157,6 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *leaf;
 	const u64 end = logical + *length;
 	int num_stripes;
-	u8 encoding;
 	u64 offset;
 	u64 found_logical;
 	u64 found_length;
@@ -222,16 +219,6 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
 
 	num_stripes = btrfs_num_raid_stripes(btrfs_item_size(leaf, slot));
 	stripe_extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent);
-	encoding = btrfs_stripe_extent_encoding(leaf, stripe_extent);
-
-	if (encoding != btrfs_bg_flags_to_raid_index(map_type)) {
-		ret = -EUCLEAN;
-		btrfs_handle_fs_error(fs_info, ret,
-				      "on-disk stripe encoding %d doesn't match RAID index %d",
-				      encoding,
-				      btrfs_bg_flags_to_raid_index(map_type));
-		goto out;
-	}
 
 	for (int i = 0; i < num_stripes; i++) {
 		struct btrfs_raid_stride *stride = &stripe_extent->strides[i];
diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h
index c9c258f84903..1ac1c21aac2f 100644
--- a/fs/btrfs/raid-stripe-tree.h
+++ b/fs/btrfs/raid-stripe-tree.h
@@ -48,8 +48,7 @@ static inline bool btrfs_need_stripe_tree_update(struct btrfs_fs_info *fs_info,
 
 static inline int btrfs_num_raid_stripes(u32 item_size)
 {
-	return (item_size - offsetof(struct btrfs_stripe_extent, strides)) /
-		sizeof(struct btrfs_raid_stride);
+	return item_size / sizeof(struct btrfs_raid_stride);
 }
 
 #endif
diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index a2c3651a3d8f..1e140f6dabc6 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -1682,9 +1682,6 @@ static int check_inode_ref(struct extent_buffer *leaf,
 static int check_raid_stripe_extent(const struct extent_buffer *leaf,
 				    const struct btrfs_key *key, int slot)
 {
-	struct btrfs_stripe_extent *stripe_extent =
-		btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent);
-
 	if (unlikely(!IS_ALIGNED(key->objectid, leaf->fs_info->sectorsize))) {
 		generic_err(leaf, slot,
 "invalid key objectid for raid stripe extent, have %llu expect aligned to %u",
@@ -1698,22 +1695,6 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf,
 		return -EUCLEAN;
 	}
 
-	switch (btrfs_stripe_extent_encoding(leaf, stripe_extent)) {
-	case BTRFS_STRIPE_RAID0:
-	case BTRFS_STRIPE_RAID1:
-	case BTRFS_STRIPE_DUP:
-	case BTRFS_STRIPE_RAID10:
-	case BTRFS_STRIPE_RAID5:
-	case BTRFS_STRIPE_RAID6:
-	case BTRFS_STRIPE_RAID1C3:
-	case BTRFS_STRIPE_RAID1C4:
-		break;
-	default:
-		generic_err(leaf, slot, "invalid raid stripe encoding %u",
-			    btrfs_stripe_extent_encoding(leaf, stripe_extent));
-		return -EUCLEAN;
-	}
-
 	return 0;
 }
 
diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h
index c7636331e566..fc29d273845d 100644
--- a/include/uapi/linux/btrfs_tree.h
+++ b/include/uapi/linux/btrfs_tree.h
@@ -747,21 +747,9 @@ struct btrfs_raid_stride {
 	__le64 physical;
 } __attribute__ ((__packed__));
 
-/* The stripe_extent::encoding, 1:1 mapping of enum btrfs_raid_types. */
-#define BTRFS_STRIPE_RAID0	1
-#define BTRFS_STRIPE_RAID1	2
-#define BTRFS_STRIPE_DUP	3
-#define BTRFS_STRIPE_RAID10	4
-#define BTRFS_STRIPE_RAID5	5
-#define BTRFS_STRIPE_RAID6	6
-#define BTRFS_STRIPE_RAID1C3	7
-#define BTRFS_STRIPE_RAID1C4	8
-
 struct btrfs_stripe_extent {
-	__u8 encoding;
-	__u8 reserved[7];
 	/* An array of raid strides this stripe is composed of. */
-	struct btrfs_raid_stride strides[];
+	__DECLARE_FLEX_ARRAY(struct btrfs_raid_stride, strides);
 } __attribute__ ((__packed__));
 
 #define BTRFS_HEADER_FLAG_WRITTEN	(1ULL << 0)

-- 
2.43.0

[PATCH v2 2/4] btrfs: replace stripe extents

[Johannes Thumshirn]

From: Johannes Thumshirn <johannes.thumshirn@wdc.com>

If we can't insert a stripe extent in the RAID stripe tree, because
the key that points to the specific position in the stripe tree is
already existing, we have to remove the item and then replace it by a
new item.

This can happen for example on device replace operations.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/raid-stripe-tree.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index e6f7a234b8f6..3020820dd6e2 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -73,6 +73,37 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 	return ret;
 }
 
+static int replace_raid_extent_item(struct btrfs_trans_handle *trans,
+				    struct btrfs_key *key,
+				    struct btrfs_stripe_extent *stripe_extent,
+				    const size_t item_size)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *stripe_root = fs_info->stripe_root;
+	struct btrfs_path *path;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = btrfs_search_slot(trans, stripe_root, key, path, -1, 1);
+	if (ret)
+		goto err;
+
+	ret = btrfs_del_item(trans, stripe_root, path);
+	if (ret)
+		goto err;
+
+	btrfs_free_path(path);
+
+	return btrfs_insert_item(trans, stripe_root, key, stripe_extent,
+				 item_size);
+ err:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
 					struct btrfs_io_context *bioc)
 {
@@ -112,6 +143,9 @@ static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_item(trans, stripe_root, &stripe_key, stripe_extent,
 				item_size);
+	if (ret == -EEXIST)
+		ret = replace_raid_extent_item(trans, &stripe_key,
+					       stripe_extent, item_size);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 

-- 
2.43.0

[PATCH v2 3/4] btrfs: split RAID stripes on deletion

[Johannes Thumshirn]

From: Johannes Thumshirn <johannes.thumshirn@wdc.com>

The current RAID stripe code assumes, that we will always remove a
whole stripe entry.

But if we're only removing a part of a RAID stripe we're hitting the
ASSERT()ion checking for this condition.

Instead of assuming the complete deletion of a RAID stripe, split the
stripe if we need to.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/ctree.c            |   1 +
 fs/btrfs/raid-stripe-tree.c | 100 +++++++++++++++++++++++++++++++++-----------
 2 files changed, 77 insertions(+), 24 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 763b9a1da428..a5c841da0357 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -3858,6 +3858,7 @@ static noinline int setup_leaf_for_split(struct btrfs_trans_handle *trans,
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
 
 	BUG_ON(key.type != BTRFS_EXTENT_DATA_KEY &&
+	       key.type != BTRFS_RAID_STRIPE_KEY &&
 	       key.type != BTRFS_EXTENT_CSUM_KEY);
 
 	if (btrfs_leaf_free_space(leaf) >= ins_len)
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 3020820dd6e2..64e36b46cbab 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -33,42 +33,94 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 	if (!path)
 		return -ENOMEM;
 
-	while (1) {
-		key.objectid = start;
-		key.type = BTRFS_RAID_STRIPE_KEY;
-		key.offset = length;
+again:
+	key.objectid = start;
+	key.type = BTRFS_RAID_STRIPE_KEY;
+	key.offset = length;
 
-		ret = btrfs_search_slot(trans, stripe_root, &key, path, -1, 1);
-		if (ret < 0)
-			break;
-		if (ret > 0) {
-			ret = 0;
-			if (path->slots[0] == 0)
-				break;
-			path->slots[0]--;
-		}
+	ret = btrfs_search_slot(trans, stripe_root, &key, path, -1, 1);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = 0;
+		if (path->slots[0] == 0)
+			goto out;
+		path->slots[0]--;
+	}
+
+	leaf = path->nodes[0];
+	slot = path->slots[0];
+	btrfs_item_key_to_cpu(leaf, &key, slot);
+	found_start = key.objectid;
+	found_end = found_start + key.offset;
+
+	/* That stripe ends before we start, we're done. */
+	if (found_end <= start)
+		goto out;
+
+	trace_btrfs_raid_extent_delete(fs_info, start, end,
+				       found_start, found_end);
+
+	if (found_start < start) {
+		u64 diff = start - found_start;
+		struct btrfs_key new_key;
+		int num_stripes;
+		struct btrfs_stripe_extent *stripe_extent;
+
+		new_key.objectid = start;
+		new_key.type = BTRFS_RAID_STRIPE_KEY;
+		new_key.offset = length - diff;
+
+		ret = btrfs_duplicate_item(trans, stripe_root, path,
+					   &new_key);
+		if (ret)
+			goto out;
 
 		leaf = path->nodes[0];
 		slot = path->slots[0];
-		btrfs_item_key_to_cpu(leaf, &key, slot);
-		found_start = key.objectid;
-		found_end = found_start + key.offset;
 
-		/* That stripe ends before we start, we're done. */
-		if (found_end <= start)
-			break;
+		num_stripes =
+			btrfs_num_raid_stripes(btrfs_item_size(leaf, slot));
+		stripe_extent =
+			btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent);
+
+		for (int i = 0; i < num_stripes; i++) {
+			struct btrfs_raid_stride *raid_stride =
+				&stripe_extent->strides[i];
+			u64 physical =
+				btrfs_raid_stride_physical(leaf, raid_stride);
+
+			btrfs_set_raid_stride_physical(leaf, raid_stride,
+							     physical + diff);
+		}
+
+		btrfs_mark_buffer_dirty(trans, leaf);
+		btrfs_release_path(path);
+		goto again;
+	}
+
+	if (found_end > end) {
+		u64 diff = found_end - end;
+		struct btrfs_key new_key;
 
-		trace_btrfs_raid_extent_delete(fs_info, start, end,
-					       found_start, found_end);
+		new_key.objectid = found_start;
+		new_key.type = BTRFS_RAID_STRIPE_KEY;
+		new_key.offset = length - diff;
 
-		ASSERT(found_start >= start && found_end <= end);
-		ret = btrfs_del_item(trans, stripe_root, path);
+		ret = btrfs_duplicate_item(trans, stripe_root, path,
+					   &new_key);
 		if (ret)
-			break;
+			goto out;
 
+		btrfs_mark_buffer_dirty(trans, leaf);
 		btrfs_release_path(path);
+		goto again;
+
 	}
 
+	ret = btrfs_del_item(trans, stripe_root, path);
+
+ out:
 	btrfs_free_path(path);
 	return ret;
 }

-- 
2.43.0

[PATCH v2 4/4] btrfs: stripe-tree: add selftests

[Johannes Thumshirn]

From: Johannes Thumshirn <johannes.thumshirn@wdc.com>

Add self-tests for the RAID stripe tree code.

Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
---
 fs/btrfs/Makefile                       |   3 +-
 fs/btrfs/raid-stripe-tree.c             |   3 +-
 fs/btrfs/raid-stripe-tree.h             |   5 +
 fs/btrfs/tests/btrfs-tests.c            |   3 +
 fs/btrfs/tests/btrfs-tests.h            |   1 +
 fs/btrfs/tests/raid-stripe-tree-tests.c | 258 ++++++++++++++++++++++++++++++++
 6 files changed, 271 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
index 50b19d15e956..79690d746781 100644
--- a/fs/btrfs/Makefile
+++ b/fs/btrfs/Makefile
@@ -43,4 +43,5 @@ btrfs-$(CONFIG_FS_VERITY) += verity.o
 btrfs-$(CONFIG_BTRFS_FS_RUN_SANITY_TESTS) += tests/free-space-tests.o \
 	tests/extent-buffer-tests.o tests/btrfs-tests.o \
 	tests/extent-io-tests.o tests/inode-tests.o tests/qgroup-tests.o \
-	tests/free-space-tree-tests.o tests/extent-map-tests.o
+	tests/free-space-tree-tests.o tests/extent-map-tests.o \
+	tests/raid-stripe-tree-tests.o
diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 64e36b46cbab..c5c2f19387ff 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -156,7 +156,8 @@ static int replace_raid_extent_item(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
+EXPORT_FOR_TESTS
+int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
 					struct btrfs_io_context *bioc)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
diff --git a/fs/btrfs/raid-stripe-tree.h b/fs/btrfs/raid-stripe-tree.h
index 1ac1c21aac2f..541836421778 100644
--- a/fs/btrfs/raid-stripe-tree.h
+++ b/fs/btrfs/raid-stripe-tree.h
@@ -28,6 +28,11 @@ int btrfs_get_raid_extent_offset(struct btrfs_fs_info *fs_info,
 int btrfs_insert_raid_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_ordered_extent *ordered_extent);
 
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
+				 struct btrfs_io_context *bioc);
+#endif
+
 static inline bool btrfs_need_stripe_tree_update(struct btrfs_fs_info *fs_info,
 						 u64 map_type)
 {
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index ce50847e1e01..18e1ab4a0914 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -291,6 +291,9 @@ int btrfs_run_sanity_tests(void)
 			ret = btrfs_test_free_space_tree(sectorsize, nodesize);
 			if (ret)
 				goto out;
+			ret = btrfs_test_raid_stripe_tree(sectorsize, nodesize);
+			if (ret)
+				goto out;
 		}
 	}
 	ret = btrfs_test_extent_map();
diff --git a/fs/btrfs/tests/btrfs-tests.h b/fs/btrfs/tests/btrfs-tests.h
index dc2f2ab15fa5..61bcadaf2036 100644
--- a/fs/btrfs/tests/btrfs-tests.h
+++ b/fs/btrfs/tests/btrfs-tests.h
@@ -37,6 +37,7 @@ int btrfs_test_extent_io(u32 sectorsize, u32 nodesize);
 int btrfs_test_inodes(u32 sectorsize, u32 nodesize);
 int btrfs_test_qgroups(u32 sectorsize, u32 nodesize);
 int btrfs_test_free_space_tree(u32 sectorsize, u32 nodesize);
+int btrfs_test_raid_stripe_tree(u32 sectorsize, u32 nodesize);
 int btrfs_test_extent_map(void);
 struct inode *btrfs_new_test_inode(void);
 struct btrfs_fs_info *btrfs_alloc_dummy_fs_info(u32 nodesize, u32 sectorsize);
diff --git a/fs/btrfs/tests/raid-stripe-tree-tests.c b/fs/btrfs/tests/raid-stripe-tree-tests.c
new file mode 100644
index 000000000000..9a5848c4a1c4
--- /dev/null
+++ b/fs/btrfs/tests/raid-stripe-tree-tests.c
@@ -0,0 +1,258 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Western Digital Corporation.  All rights reserved.
+ */
+#include <linux/array_size.h>
+#include <linux/sizes.h>
+#include <linux/btrfs.h>
+#include <linux/btrfs_tree.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include "btrfs-tests.h"
+#include "../disk-io.h"
+#include "../transaction.h"
+#include "../volumes.h"
+#include "../raid-stripe-tree.h"
+#include "../block-group.h"
+
+static struct btrfs_io_context *alloc_dummy_bioc(struct btrfs_fs_info *fs_info,
+						 u64 logical, u16 total_stripes)
+{
+	struct btrfs_io_context *bioc;
+
+	bioc = kzalloc(sizeof(struct btrfs_io_context) +
+		       sizeof(struct btrfs_io_stripe) * total_stripes,
+		       GFP_KERNEL);
+
+	if (!bioc)
+		return NULL;
+
+	refcount_set(&bioc->refs, 1);
+
+	bioc->fs_info = fs_info;
+	bioc->replace_stripe_src = -1;
+	bioc->full_stripe_logical = (u64)-1;
+	bioc->logical = logical;
+
+	return bioc;
+}
+
+typedef int (*test_func_t)(struct btrfs_fs_info *);
+
+static int test_stripe_tree_delete_tail(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_io_context *bioc;
+	const u64 map_type = BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_RAID1;
+	const int total_stripes = btrfs_bg_type_to_factor(map_type);
+	u64 logical = SZ_8K;
+	u64 length = SZ_64K;
+	int i;
+	int ret;
+
+	btrfs_init_dummy_trans(&trans, fs_info);
+
+	bioc = alloc_dummy_bioc(fs_info, logical, total_stripes);
+	if (!bioc)
+		return -ENOMEM;
+
+	bioc->size = length;
+	bioc->map_type = map_type;
+	for (i = 0; i < total_stripes; ++i) {
+		struct btrfs_device *dev;
+
+		dev = kzalloc(sizeof(struct btrfs_device), GFP_KERNEL);
+		if (!dev) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		dev->devid = i;
+		bioc->stripes[i].dev = dev;
+		bioc->stripes[i].length = length;
+		bioc->stripes[i].physical = i * SZ_8K;
+	}
+
+	ret = btrfs_insert_one_raid_extent(&trans, bioc);
+	if (ret)
+		goto out;
+
+	ret = btrfs_delete_raid_extent(&trans, logical, SZ_16K);
+
+out:
+	for (i = 0; i < total_stripes; i++)
+		kfree(bioc->stripes[i].dev);
+
+	kfree(bioc);
+	return ret;
+}
+
+static int test_stripe_tree_delete_front(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_io_context *bioc;
+	const u64 map_type = BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_RAID1;
+	const int total_stripes = btrfs_bg_type_to_factor(map_type);
+	u64 logical = SZ_8K;
+	u64 length = SZ_64K;
+	int i;
+	int ret;
+
+	btrfs_init_dummy_trans(&trans, fs_info);
+
+	bioc = alloc_dummy_bioc(fs_info, logical, total_stripes);
+	if (!bioc)
+		return -ENOMEM;
+
+	bioc->size = length;
+	bioc->map_type = map_type;
+	for (i = 0; i < total_stripes; i++) {
+		struct btrfs_device *dev;
+
+		dev = kzalloc(sizeof(struct btrfs_device), GFP_KERNEL);
+		if (!dev) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		dev->devid = i;
+		bioc->stripes[i].dev = dev;
+		bioc->stripes[i].length = length;
+		bioc->stripes[i].physical = i * SZ_8K;
+	}
+
+	ret = btrfs_insert_one_raid_extent(&trans, bioc);
+	if (ret)
+		goto out;
+	ret = btrfs_delete_raid_extent(&trans, logical, SZ_8K);
+out:
+	for (i = 0; i < total_stripes; i++)
+		kfree(bioc->stripes[i].dev);
+
+	kfree(bioc);
+	return ret;
+
+}
+
+static int test_stripe_tree_delete_whole(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_trans_handle trans;
+	struct btrfs_io_context *bioc;
+	const u64 map_type = BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_RAID1;
+	const int total_stripes = btrfs_bg_type_to_factor(map_type);
+	u64 logical = SZ_8K;
+	u64 length = SZ_64K;
+	int i;
+	int ret;
+
+	btrfs_init_dummy_trans(&trans, fs_info);
+
+	bioc = alloc_dummy_bioc(fs_info, logical, total_stripes);
+	if (!bioc)
+		return -ENOMEM;
+
+	bioc->size = length;
+	bioc->map_type = map_type;
+	for (i = 0; i < total_stripes; ++i) {
+		struct btrfs_device *dev;
+
+		dev = kzalloc(sizeof(struct btrfs_device), GFP_KERNEL);
+		if (!dev) {
+			ret = -ENOMEM;
+			goto out;
+		}
+		dev->devid = i;
+		bioc->stripes[i].dev = dev;
+		bioc->stripes[i].length = length;
+		bioc->stripes[i].physical = i * SZ_8K;
+	}
+
+	ret = btrfs_insert_one_raid_extent(&trans, bioc);
+	if (ret)
+		goto out;
+
+	ret = btrfs_delete_raid_extent(&trans, logical, length);
+
+out:
+	for (i = 0; i < total_stripes; i++)
+		kfree(bioc->stripes[i].dev);
+
+	kfree(bioc);
+	return ret;
+}
+
+static int test_stripe_tree_delete(struct btrfs_fs_info *fs_info)
+{
+	test_func_t delete_tests[] = {
+		test_stripe_tree_delete_whole,
+		test_stripe_tree_delete_front,
+		test_stripe_tree_delete_tail,
+	};
+	int ret;
+
+	for (int i = 0; i < ARRAY_SIZE(delete_tests); i++) {
+		test_func_t test = delete_tests[i];
+
+		ret = test(fs_info);
+		if (ret)
+			goto out;
+	}
+
+out:
+	return ret;
+}
+
+int btrfs_test_raid_stripe_tree(u32 sectorsize, u32 nodesize)
+{
+	test_func_t tests[] = {
+		test_stripe_tree_delete,
+	};
+	struct btrfs_fs_info *fs_info;
+	struct btrfs_root *root = NULL;
+	int ret = 0;
+
+	test_msg("running raid-stripe-tree tests");
+
+	fs_info = btrfs_alloc_dummy_fs_info(nodesize, sectorsize);
+	if (!fs_info) {
+		test_std_err(TEST_ALLOC_FS_INFO);
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	root = btrfs_alloc_dummy_root(fs_info);
+	if (IS_ERR(root)) {
+		test_std_err(TEST_ALLOC_ROOT);
+		ret = PTR_ERR(root);
+		goto out;
+	}
+
+	btrfs_set_super_incompat_flags(fs_info->super_copy,
+				       BTRFS_FEATURE_INCOMPAT_RAID_STRIPE_TREE);
+	root->root_key.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID;
+	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
+	root->root_key.offset = 0;
+	btrfs_global_root_insert(root);
+	fs_info->stripe_root = root;
+
+	root->node = alloc_test_extent_buffer(fs_info, nodesize);
+	if (IS_ERR(root->node)) {
+		test_std_err(TEST_ALLOC_EXTENT_BUFFER);
+		ret = PTR_ERR(root->node);
+		goto out;
+	}
+	btrfs_set_header_level(root->node, 0);
+	btrfs_set_header_nritems(root->node, 0);
+	root->alloc_bytenr += 2 * nodesize;
+
+	for (int i = 0; i < ARRAY_SIZE(tests); i++) {
+		test_func_t test = tests[i];
+
+		ret = test(fs_info);
+		if (ret)
+			goto out;
+	}
+out:
+	btrfs_free_dummy_root(root);
+	btrfs_free_dummy_fs_info(fs_info);
+	return ret;
+}

-- 
2.43.0