1 files changed, 130 insertions, 16 deletions

diff --git a/fs/btrfs/raid-stripe-tree.c b/fs/btrfs/raid-stripe-tree.c
index 9ffc79f250fb..1834011ccc49 100644
--- a/fs/btrfs/raid-stripe-tree.c
+++ b/fs/btrfs/raid-stripe-tree.c
@@ -13,12 +13,13 @@
 #include "volumes.h"
 #include "print-tree.h"
 
-static void btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans,
+static int btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans,
 					       struct btrfs_path *path,
 					       const struct btrfs_key *oldkey,
 					       u64 newlen, u64 frontpad)
 {
-	struct btrfs_stripe_extent *extent;
+	struct btrfs_root *stripe_root = trans->fs_info->stripe_root;
+	struct btrfs_stripe_extent *extent, *newitem;
 	struct extent_buffer *leaf;
 	int slot;
 	size_t item_size;
@@ -27,23 +28,39 @@ static void btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans,
 		.type = BTRFS_RAID_STRIPE_KEY,
 		.offset = newlen,
 	};
+	int ret;
 
+	ASSERT(newlen > 0);
 	ASSERT(oldkey->type == BTRFS_RAID_STRIPE_KEY);
 
 	leaf = path->nodes[0];
 	slot = path->slots[0];
 	item_size = btrfs_item_size(leaf, slot);
+
+	newitem = kzalloc(item_size, GFP_NOFS);
+	if (!newitem)
+		return -ENOMEM;
+
 	extent = btrfs_item_ptr(leaf, slot, struct btrfs_stripe_extent);
 
 	for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) {
 		struct btrfs_raid_stride *stride = &extent->strides[i];
 		u64 phys;
 
-		phys = btrfs_raid_stride_physical(leaf, stride);
-		btrfs_set_raid_stride_physical(leaf, stride, phys + frontpad);
+		phys = btrfs_raid_stride_physical(leaf, stride) + frontpad;
+		btrfs_set_stack_raid_stride_physical(&newitem->strides[i], phys);
 	}
 
-	btrfs_set_item_key_safe(trans, path, &newkey);
+	ret = btrfs_del_item(trans, stripe_root, path);
+	if (ret)
+		goto out;
+
+	btrfs_release_path(path);
+	ret = btrfs_insert_item(trans, stripe_root, &newkey, newitem, item_size);
+
+out:
+	kfree(newitem);
+	return ret;
 }
 
 int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 length)
@@ -59,9 +76,22 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 	int slot;
 	int ret;
 
-	if (!stripe_root)
+	if (!btrfs_fs_incompat(fs_info, RAID_STRIPE_TREE) || !stripe_root)
 		return 0;
 
+	if (!btrfs_is_testing(fs_info)) {
+		struct btrfs_chunk_map *map;
+		bool use_rst;
+
+		map = btrfs_find_chunk_map(fs_info, start, length);
+		if (!map)
+			return -EINVAL;
+		use_rst = btrfs_need_stripe_tree_update(fs_info, map->type);
+		btrfs_free_chunk_map(map);
+		if (!use_rst)
+			return 0;
+	}
+
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
@@ -85,6 +115,37 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 		found_end = found_start + key.offset;
 		ret = 0;
 
+		/*
+		 * The stripe extent starts before the range we want to delete,
+		 * but the range spans more than one stripe extent:
+		 *
+		 * |--- RAID Stripe Extent ---||--- RAID Stripe Extent ---|
+		 *        |--- keep  ---|--- drop ---|
+		 *
+		 * This means we have to get the previous item, truncate its
+		 * length and then restart the search.
+		 */
+		if (found_start > start) {
+			if (slot == 0) {
+				ret = btrfs_previous_item(stripe_root, path, start,
+							  BTRFS_RAID_STRIPE_KEY);
+				if (ret) {
+					if (ret > 0)
+						ret = -ENOENT;
+					break;
+				}
+			} else {
+				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;
+			ASSERT(found_start <= start);
+		}
+
 		if (key.type != BTRFS_RAID_STRIPE_KEY)
 			break;
 
@@ -96,6 +157,54 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 					       found_start, found_end);
 
 		/*
+		 * The stripe extent starts before the range we want to delete
+		 * and ends after the range we want to delete, i.e. we're
+		 * punching a hole in the stripe extent:
+		 *
+		 *  |--- RAID Stripe Extent ---|
+		 *  | keep |--- drop ---| keep |
+		 *
+		 * This means we need to a) truncate the existing item and b)
+		 * create a second item for the remaining range.
+		 */
+		if (found_start < start && found_end > end) {
+			size_t item_size;
+			u64 diff_start = start - found_start;
+			u64 diff_end = found_end - end;
+			struct btrfs_stripe_extent *extent;
+			struct btrfs_key newkey = {
+				.objectid = end,
+				.type = BTRFS_RAID_STRIPE_KEY,
+				.offset = diff_end,
+			};
+
+			/* The "right" item. */
+			ret = btrfs_duplicate_item(trans, stripe_root, path, &newkey);
+			if (ret)
+				break;
+
+			item_size = btrfs_item_size(leaf, path->slots[0]);
+			extent = btrfs_item_ptr(leaf, path->slots[0],
+						struct btrfs_stripe_extent);
+
+			for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) {
+				struct btrfs_raid_stride *stride = &extent->strides[i];
+				u64 phys;
+
+				phys = btrfs_raid_stride_physical(leaf, stride);
+				phys += diff_start + length;
+				btrfs_set_raid_stride_physical(leaf, stride, phys);
+			}
+
+			/* The "left" item. */
+			path->slots[0]--;
+			btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+			btrfs_partially_delete_raid_extent(trans, path, &key,
+							   diff_start, 0);
+			break;
+		}
+
+		/*
 		 * The stripe extent starts before the range we want to delete:
 		 *
 		 * |--- RAID Stripe Extent ---|
@@ -105,11 +214,18 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 		 * length to the new size and then re-insert the item.
 		 */
 		if (found_start < start) {
-			u64 diff = start - found_start;
+			u64 diff_start = start - found_start;
 
 			btrfs_partially_delete_raid_extent(trans, path, &key,
-							   diff, 0);
-			break;
+							   diff_start, 0);
+
+			start += (key.offset - diff_start);
+			length -= (key.offset - diff_start);
+			if (length == 0)
+				break;
+
+			btrfs_release_path(path);
+			continue;
 		}
 
 		/*
@@ -122,13 +238,16 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 		 * length to the new size and then re-insert the item.
 		 */
 		if (found_end > end) {
-			u64 diff = found_end - end;
+			u64 diff_end = found_end - end;
 
 			btrfs_partially_delete_raid_extent(trans, path, &key,
-							   diff, diff);
+							   key.offset - length,
+							   length);
+			ASSERT(key.offset - diff_end == length);
 			break;
 		}
 
+		/* Finally we can delete the whole item, no more special cases. */
 		ret = btrfs_del_item(trans, stripe_root, path);
 		if (ret)
 			break;
@@ -169,7 +288,6 @@ static int update_raid_extent_item(struct btrfs_trans_handle *trans,
 
 	write_extent_buffer(leaf, stripe_extent, btrfs_item_ptr_offset(leaf, slot),
 			    item_size);
-	btrfs_mark_buffer_dirty(trans, leaf);
 	btrfs_free_path(path);
 
 	return ret;
@@ -199,12 +317,8 @@ int btrfs_insert_one_raid_extent(struct btrfs_trans_handle *trans,
 	for (int i = 0; i < num_stripes; i++) {
 		u64 devid = bioc->stripes[i].dev->devid;
 		u64 physical = bioc->stripes[i].physical;
-		u64 length = bioc->stripes[i].length;
 		struct btrfs_raid_stride *raid_stride = &stripe_extent->strides[i];
 
-		if (length == 0)
-			length = bioc->size;
-
 		btrfs_set_stack_raid_stride_devid(raid_stride, devid);
 		btrfs_set_stack_raid_stride_physical(raid_stride, physical);
 	}