for-7.1-rc1-tag

-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE8rQSAMVO+zA4DBdWxWXV+ddtWDsFAmnvdO8ACgkQxWXV+ddt
 WDuLqA//fcHDOnClWHRRUaIWhhkMYm7gNZkXf2d+qyYLMtAP2Cv2sZ+aV+OkHp5D
 /Gq1W1mUXZLabu0EV0xKICn01nwzWtbZwDO8Bo3+QEdLoAi2gITODsYyY8yeW9KO
 GfSBPsom+d7ktVrjaYE7Ppcm6YifBjWNDDcC+MX7Kpy+OUqhyOtsJIaEeTwii9+P
 eiyAAC1zqrHZtaQfLsY3WvM0baNaqlm1xURMjJPyRCAtjGpjZy1hK/iFsGcHRlfc
 SR//WT/MRnUAFn8zlIBG0wNrk1IEIgPPiA7hAXMRGXFKo0C6ICYLl5MJQh/o/MUs
 tFBdkBhtcX/Kynvwb059SyalXZzVhQvzaRN89ZGuDyalNiejRzb8F2oVCfKAVKIU
 MdkKOjnR5b7BUzCcZ1cJf1LgX4SngYKTnXrNGHpW0fuUzX6moJEd4wbrgmHjk9ke
 +TVdl2vcpAduvBU9idkpDAcUW998tcYmX/LyQhGYpR6k/4n2UdFZJPINqco3pOAO
 RIFbIgEAq9rUi+GMSJdEDMO6xLmUYoI6vaw7uZSU6E04zJPiVIcixfRDCBKGPV5Q
 Yl9PC3ViLSlgKWaG7UVl8PVaSkCQ7esbfPAnNI/+RBCUeehhSFygePcY+kH1k4LA
 0qMne1abDysUVwolb/1de/fqkznLlB3SlA447HwdvwMI0mCSb7w=
 =ajKs
 -----END PGP SIGNATURE-----

Merge tag 'for-7.1-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - space reservation fixes:
     - correctly undo 'may_use' accounting for remap tree
     - avoid double decrement of 'may_use' when submitting async io

 - actually enable the shutdown ioctl callback (not just the superblock
   ops)

 - raid stripe tree fixes when deleting extents
     - add missing error handling
     - fix various incorrect values set

 - fix transaction state when removing a directory, possibly leading to
   EIO during log replay

 - additional b-tree node key checks during metadata readahead

 - error handling and transaction abort updates

* tag 'for-7.1-rc1-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix double-decrement of bytes_may_use in submit_one_async_extent()
  btrfs: check return value of btrfs_partially_delete_raid_extent()
  btrfs: handle -EAGAIN from btrfs_duplicate_item and refresh stale leaf pointer
  btrfs: replace ASSERT with proper error handling in stripe lookup fallback
  btrfs: fix wrong min_objectid in btrfs_previous_item() call
  btrfs: fix raid stripe search missing entries at leaf boundaries
  btrfs: copy devid in btrfs_partially_delete_raid_extent()
  btrfs: handle unexpected free-space-tree key types
  btrfs: fix missing last_unlink_trans update when removing a directory
  btrfs: don't clobber errors in add_remap_tree_entries()
  btrfs: enable shutdown ioctl for non-experimental builds
  btrfs: apply first key check for readahead when possible
  btrfs: abort transaction in do_remap_reloc_trans() on failure
  btrfs: fix bytes_may_use leak in do_remap_reloc_trans()
  btrfs: fix bytes_may_use leak in move_existing_remap()

fs/btrfs/extent_io.c

@@ -4641,7 +4641,8 @@ int try_release_extent_buffer(struct folio *folio)
  * to read the block we will not block on anything.
  */
 void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
-				u64 bytenr, u64 owner_root, u64 gen, int level)
+				u64 bytenr, u64 owner_root, u64 gen, int level,
+				const struct btrfs_key *first_key)
 {
 	struct btrfs_tree_parent_check check = {
 		.level = level,
@@ -4650,6 +4651,11 @@ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
 	struct extent_buffer *eb;
 	int ret;
 
+	if (first_key) {
+		memcpy(&check.first_key, first_key, sizeof(struct btrfs_key));
+		check.has_first_key = true;
+	}
+
 	eb = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level);
 	if (IS_ERR(eb))
 		return;
@@ -4677,9 +4683,13 @@ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
  */
 void btrfs_readahead_node_child(struct extent_buffer *node, int slot)
 {
+	struct btrfs_key node_key;
+
+	btrfs_node_key_to_cpu(node, &node_key, slot);
 	btrfs_readahead_tree_block(node->fs_info,
 				   btrfs_node_blockptr(node, slot),
 				   btrfs_header_owner(node),
 				   btrfs_node_ptr_generation(node, slot),
-				   btrfs_header_level(node) - 1);
+				   btrfs_header_level(node) - 1,
+				   &node_key);
 }

fs/btrfs/extent_io.h

@@ -287,7 +287,8 @@ static inline void wait_on_extent_buffer_writeback(struct extent_buffer *eb)
 }
 
 void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info,
-				u64 bytenr, u64 owner_root, u64 gen, int level);
+				u64 bytenr, u64 owner_root, u64 gen, int level,
+				const struct btrfs_key *first_key);
 void btrfs_readahead_node_child(struct extent_buffer *node, int slot);
 
 /* Note: this can be used in for loops without caching the value in a variable. */

fs/btrfs/free-space-tree.c

@@ -259,7 +259,11 @@ int btrfs_convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
 				nr++;
 				path->slots[0]--;
 			} else {
-				ASSERT(0);
+				btrfs_err(fs_info, "unexpected free space tree key type %u",
+					  found_key.type);
+				ret = -EUCLEAN;
+				btrfs_abort_transaction(trans, ret);
+				goto out;
 			}
 		}
 
@@ -405,7 +409,11 @@ int btrfs_convert_free_space_to_extents(struct btrfs_trans_handle *trans,
 
 				nr++;
 			} else {
-				ASSERT(0);
+				btrfs_err(fs_info, "unexpected free space tree key type %u",
+					  found_key.type);
+				ret = -EUCLEAN;
+				btrfs_abort_transaction(trans, ret);
+				goto out;
 			}
 		}
 
@@ -1518,7 +1526,11 @@ int btrfs_remove_block_group_free_space(struct btrfs_trans_handle *trans,
 				nr++;
 				path->slots[0]--;
 			} else {
-				ASSERT(0);
+				btrfs_err(trans->fs_info, "unexpected free space tree key type %u",
+					  found_key.type);
+				ret = -EUCLEAN;
+				btrfs_abort_transaction(trans, ret);
+				return ret;
 			}
 		}
 

fs/btrfs/inode.c

@@ -1153,7 +1153,7 @@ static void submit_one_async_extent(struct async_chunk *async_chunk,
 				     NULL, &cached,
 				     EXTENT_LOCKED | EXTENT_DELALLOC |
 				     EXTENT_DELALLOC_NEW |
-				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
+				     EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV,
 				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
 				     PAGE_END_WRITEBACK);
 	if (async_extent->cb)
@@ -4959,6 +4959,8 @@ static int btrfs_rmdir(struct inode *vfs_dir, struct dentry *dentry)
 	if (ret)
 		goto out;
 
+	btrfs_record_unlink_dir(trans, dir, inode, false);
+
 	/* now the directory is empty */
 	ret = btrfs_unlink_inode(trans, dir, inode, &fname.disk_name);
 	if (!ret)

fs/btrfs/ioctl.c

@@ -5102,7 +5102,6 @@ static int btrfs_ioctl_subvol_sync(struct btrfs_fs_info *fs_info, void __user *a
 	return 0;
 }
 
-#ifdef CONFIG_BTRFS_EXPERIMENTAL
 static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg)
 {
 	int ret = 0;
@@ -5134,10 +5133,12 @@ static int btrfs_ioctl_shutdown(struct btrfs_fs_info *fs_info, unsigned long arg
 	case BTRFS_SHUTDOWN_FLAGS_NOLOGFLUSH:
 		btrfs_force_shutdown(fs_info);
 		break;
+	default:
+		ret = -EINVAL;
+		break;
 	}
 	return ret;
 }
-#endif
 
 long btrfs_ioctl(struct file *file, unsigned int
 		cmd, unsigned long arg)
@@ -5294,10 +5295,8 @@ long btrfs_ioctl(struct file *file, unsigned int
 #endif
 	case BTRFS_IOC_SUBVOL_SYNC_WAIT:
 		return btrfs_ioctl_subvol_sync(fs_info, argp);
-#ifdef CONFIG_BTRFS_EXPERIMENTAL
 	case BTRFS_IOC_SHUTDOWN:
 		return btrfs_ioctl_shutdown(fs_info, arg);
-#endif
 	}
 
 	return -ENOTTY;

fs/btrfs/raid-stripe-tree.c

@@ -45,8 +45,11 @@ static int btrfs_partially_delete_raid_extent(struct btrfs_trans_handle *trans,
 
 	for (int i = 0; i < btrfs_num_raid_stripes(item_size); i++) {
 		struct btrfs_raid_stride *stride = &extent->strides[i];
+		u64 devid;
 		u64 phys;
 
+		devid = btrfs_raid_stride_devid(leaf, stride);
+		btrfs_set_stack_raid_stride_devid(&newitem->strides[i], devid);
 		phys = btrfs_raid_stride_physical(leaf, stride) + frontpad;
 		btrfs_set_stack_raid_stride_physical(&newitem->strides[i], phys);
 	}
@@ -95,14 +98,26 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 	while (1) {
 		key.objectid = start;
 		key.type = BTRFS_RAID_STRIPE_KEY;
-		key.offset = 0;
+		key.offset = (u64)-1;
 
 		ret = btrfs_search_slot(trans, stripe_root, &key, path, -1, 1);
 		if (ret < 0)
 			break;
 
-		if (path->slots[0] == btrfs_header_nritems(path->nodes[0]))
-			path->slots[0]--;
+		/*
+		 * Search with offset=(u64)-1 ensures we land on the correct
+		 * leaf even when the target entry is the first item on a leaf.
+		 * Since no real entry has offset=(u64)-1, ret is always 1 and
+		 * slot points past the last entry with objectid==start (or
+		 * past the end of the leaf if that entry is the last item).
+		 * Back up one slot to find the actual entry.
+		 */
+		if (path->slots[0] == 0) {
+			/* No entry with objectid <= start exists. */
+			ret = 0;
+			break;
+		}
+		path->slots[0]--;
 
 		leaf = path->nodes[0];
 		slot = path->slots[0];
@@ -123,7 +138,7 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 		 */
 		if (found_start > start) {
 			if (slot == 0) {
-				ret = btrfs_previous_item(stripe_root, path, start,
+				ret = btrfs_previous_item(stripe_root, path, 0,
 							  BTRFS_RAID_STRIPE_KEY);
 				if (ret) {
 					if (ret > 0)
@@ -139,7 +154,10 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 			btrfs_item_key_to_cpu(leaf, &key, slot);
 			found_start = key.objectid;
 			found_end = found_start + key.offset;
-			ASSERT(found_start <= start);
+			if (found_start > start || found_end <= start) {
+				ret = -ENOENT;
+				break;
+			}
 		}
 
 		if (key.type != BTRFS_RAID_STRIPE_KEY)
@@ -176,9 +194,19 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 
 			/* The "right" item. */
 			ret = btrfs_duplicate_item(trans, stripe_root, path, &newkey);
+			if (ret == -EAGAIN) {
+				btrfs_release_path(path);
+				continue;
+			}
 			if (ret)
 				break;
 
+			/*
+			 * btrfs_duplicate_item() may have triggered a leaf
+			 * split via setup_leaf_for_split(), so we must refresh
+			 * our leaf pointer from the path.
+			 */
+			leaf = path->nodes[0];
 			item_size = btrfs_item_size(leaf, path->slots[0]);
 			extent = btrfs_item_ptr(leaf, path->slots[0],
 						struct btrfs_stripe_extent);
@@ -195,8 +223,9 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 			/* 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);
+			ret = btrfs_partially_delete_raid_extent(trans, path,
+								 &key,
+								 diff_start, 0);
 			break;
 		}
 
@@ -212,8 +241,11 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 		if (found_start < start) {
 			u64 diff_start = start - found_start;
 
-			btrfs_partially_delete_raid_extent(trans, path, &key,
-							   diff_start, 0);
+			ret = btrfs_partially_delete_raid_extent(trans, path,
+								 &key,
+								 diff_start, 0);
+			if (ret)
+				break;
 
 			start += (key.offset - diff_start);
 			length -= (key.offset - diff_start);
@@ -236,9 +268,10 @@ int btrfs_delete_raid_extent(struct btrfs_trans_handle *trans, u64 start, u64 le
 		if (found_end > end) {
 			u64 diff_end = found_end - end;
 
-			btrfs_partially_delete_raid_extent(trans, path, &key,
-							   key.offset - length,
-							   length);
+			ret = btrfs_partially_delete_raid_extent(trans, path,
+								 &key,
+								 key.offset - length,
+								 length);
 			ASSERT(key.offset - diff_end == length);
 			break;
 		}

fs/btrfs/relocation.c

@@ -2607,7 +2607,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans,
 		if (!block->key_ready)
 			btrfs_readahead_tree_block(fs_info, block->bytenr,
 						   block->owner, 0,
-						   block->level);
+						   block->level, NULL);
 	}
 
 	/* Get first keys */
@@ -3876,7 +3876,7 @@ static int add_remap_tree_entries(struct btrfs_trans_handle *trans, struct btrfs
 		ret = btrfs_insert_empty_items(trans, fs_info->remap_root, path, &batch);
 		btrfs_release_path(path);
 
-		if (num_entries <= max_items)
+		if (ret || num_entries <= max_items)
 			break;
 
 		num_entries -= max_items;
@@ -4174,6 +4174,12 @@ static int move_existing_remap(struct btrfs_fs_info *fs_info,
 		return ret;
 	}
 
+	if (ins.offset < length) {
+		spin_lock(&sinfo->lock);
+		btrfs_space_info_update_bytes_may_use(sinfo, ins.offset - length);
+		spin_unlock(&sinfo->lock);
+	}
+
 	dest_addr = ins.objectid;
 	dest_length = ins.offset;
 
@@ -5000,6 +5006,12 @@ static int do_remap_reloc_trans(struct btrfs_fs_info *fs_info,
 		return ret;
 	}
 
+	if (ins.offset < remap_length) {
+		spin_lock(&sinfo->lock);
+		btrfs_space_info_update_bytes_may_use(sinfo, ins.offset - remap_length);
+		spin_unlock(&sinfo->lock);
+	}
+
 	made_reservation = true;
 
 	new_addr = ins.objectid;
@@ -5023,21 +5035,27 @@ static int do_remap_reloc_trans(struct btrfs_fs_info *fs_info,
 
 	if (bg_needs_free_space) {
 		ret = btrfs_add_block_group_free_space(trans, dest_bg);
-		if (ret)
+		if (ret) {
+			btrfs_abort_transaction(trans, ret);
 			goto fail;
+		}
 	}
 
 	ret = copy_remapped_data(fs_info, start, new_addr, length);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
+	}
 
 	ret = btrfs_remove_from_free_space_tree(trans, new_addr, length);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
+	}
 
 	ret = add_remap_entry(trans, path, src_bg, start, new_addr, length);
 	if (ret) {
-		btrfs_add_to_free_space_tree(trans, new_addr, length);
+		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}