Merge tag 'for-5.18-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "This contains feature updates, performance improvements, preparatory
  and core work and some related VFS updates:

  Features:

   - encoded read/write ioctls, allows user space to read or write raw
     data directly to extents (now compressed, encrypted in the future),
     will be used by send/receive v2 where it saves processing time

   - zoned mode now works with metadata DUP (the mkfs.btrfs default)

   - error message header updates:
      - print error state: transaction abort, other error, log tree
        errors
      - print transient filesystem state: remount, device replace,
        ignored checksum verifications

   - tree-checker: verify the transaction id of the to-be-written dirty
     extent buffer

  Performance improvements for fsync:

   - directory logging speedups (up to -90% run time)

   - avoid logging all directory changes during renames (up to -60% run
     time)

   - avoid inode logging during rename and link when possible (up to
     -60% run time)

   - prepare extents to be logged before locking a log tree path
     (throughput +7%)

   - stop copying old file extents when doing a full fsync()

   - improved logging of old extents after truncate

  Core, fixes:

   - improved stale device identification by dev_t and not just path
     (for devices that are behind other layers like device mapper)

   - continued extent tree v2 preparatory work
      - disable features that won't work yet
      - add wrappers and abstractions for new tree roots

   - improved error handling

   - add super block write annotations around background block group
     reclaim

   - fix device scanning messages potentially accessing stale pointer

   - cleanups and refactoring

  VFS:

   - allow reflinks/deduplication from two different mounts of the same
     filesystem

   - export and add helpers for read/write range verification, for the
     encoded ioctls"

* tag 'for-5.18-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (98 commits)
  btrfs: zoned: put block group after final usage
  btrfs: don't access possibly stale fs_info data in device_list_add
  btrfs: add lockdep_assert_held to need_preemptive_reclaim
  btrfs: verify the tranisd of the to-be-written dirty extent buffer
  btrfs: unify the error handling of btrfs_read_buffer()
  btrfs: unify the error handling pattern for read_tree_block()
  btrfs: factor out do_free_extent_accounting helper
  btrfs: remove last_ref from the extent freeing code
  btrfs: add a alloc_reserved_extent helper
  btrfs: remove BUG_ON(ret) in alloc_reserved_tree_block
  btrfs: add and use helper for unlinking inode during log replay
  btrfs: extend locking to all space_info members accesses
  btrfs: zoned: mark relocation as writing
  fs: allow cross-vfsmount reflink/dedupe
  btrfs: remove the cross file system checks from remap
  btrfs: pass btrfs_fs_info to btrfs_recover_relocation
  btrfs: pass btrfs_fs_info for deleting snapshots and cleaner
  btrfs: add filesystems state details to error messages
  btrfs: deal with unexpected extent type during reflinking
  btrfs: fix unexpected error path when reflinking an inline extent
  ...

1 files changed, 156 insertions, 63 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index b3e9cf3fd1dd..62565ee00b97 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -441,17 +441,31 @@ static int csum_one_extent_buffer(struct extent_buffer *eb)
 	else
 		ret = btrfs_check_leaf_full(eb);
 
-	if (ret < 0) {
-		btrfs_print_tree(eb, 0);
+	if (ret < 0)
+		goto error;
+
+	/*
+	 * Also check the generation, the eb reached here must be newer than
+	 * last committed. Or something seriously wrong happened.
+	 */
+	if (unlikely(btrfs_header_generation(eb) <= fs_info->last_trans_committed)) {
+		ret = -EUCLEAN;
 		btrfs_err(fs_info,
-			"block=%llu write time tree block corruption detected",
-			eb->start);
-		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
-		return ret;
+			"block=%llu bad generation, have %llu expect > %llu",
+			  eb->start, btrfs_header_generation(eb),
+			  fs_info->last_trans_committed);
+		goto error;
 	}
 	write_extent_buffer(eb, result, 0, fs_info->csum_size);
 
 	return 0;
+
+error:
+	btrfs_print_tree(eb, 0);
+	btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
+		  eb->start);
+	WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+	return ret;
 }
 
 /* Checksum all dirty extent buffers in one bio_vec */
@@ -1289,12 +1303,33 @@ struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info,
 	return root;
 }
 
+static u64 btrfs_global_root_id(struct btrfs_fs_info *fs_info, u64 bytenr)
+{
+	struct btrfs_block_group *block_group;
+	u64 ret;
+
+	if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
+		return 0;
+
+	if (bytenr)
+		block_group = btrfs_lookup_block_group(fs_info, bytenr);
+	else
+		block_group = btrfs_lookup_first_block_group(fs_info, bytenr);
+	ASSERT(block_group);
+	if (!block_group)
+		return 0;
+	ret = block_group->global_root_id;
+	btrfs_put_block_group(block_group);
+
+	return ret;
+}
+
 struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info, u64 bytenr)
 {
 	struct btrfs_key key = {
 		.objectid = BTRFS_CSUM_TREE_OBJECTID,
 		.type = BTRFS_ROOT_ITEM_KEY,
-		.offset = 0,
+		.offset = btrfs_global_root_id(fs_info, bytenr),
 	};
 
 	return btrfs_global_root(fs_info, &key);
@@ -1305,7 +1340,7 @@ struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr)
 	struct btrfs_key key = {
 		.objectid = BTRFS_EXTENT_TREE_OBJECTID,
 		.type = BTRFS_ROOT_ITEM_KEY,
-		.offset = 0,
+		.offset = btrfs_global_root_id(fs_info, bytenr),
 	};
 
 	return btrfs_global_root(fs_info, &key);
@@ -1522,7 +1557,8 @@ static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
 		ret = PTR_ERR(root->node);
 		root->node = NULL;
 		goto fail;
-	} else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
+	}
+	if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
 		ret = -EIO;
 		goto fail;
 	}
@@ -1727,6 +1763,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 	btrfs_put_root(fs_info->uuid_root);
 	btrfs_put_root(fs_info->fs_root);
 	btrfs_put_root(fs_info->data_reloc_root);
+	btrfs_put_root(fs_info->block_group_root);
 	btrfs_check_leaked_roots(fs_info);
 	btrfs_extent_buffer_leak_debug_check(fs_info);
 	kfree(fs_info->super_copy);
@@ -1925,8 +1962,7 @@ static void end_workqueue_fn(struct btrfs_work *work)
 
 static int cleaner_kthread(void *arg)
 {
-	struct btrfs_root *root = arg;
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_fs_info *fs_info = (struct btrfs_fs_info *)arg;
 	int again;
 
 	while (1) {
@@ -1959,7 +1995,7 @@ static int cleaner_kthread(void *arg)
 
 		btrfs_run_delayed_iputs(fs_info);
 
-		again = btrfs_clean_one_deleted_snapshot(root);
+		again = btrfs_clean_one_deleted_snapshot(fs_info);
 		mutex_unlock(&fs_info->cleaner_mutex);
 
 		/*
@@ -2095,8 +2131,6 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 {
 	const int next_backup = info->backup_root_index;
 	struct btrfs_root_backup *root_backup;
-	struct btrfs_root *extent_root = btrfs_extent_root(info, 0);
-	struct btrfs_root *csum_root = btrfs_csum_root(info, 0);
 
 	root_backup = info->super_for_commit->super_roots + next_backup;
 
@@ -2121,11 +2155,30 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 	btrfs_set_backup_chunk_root_level(root_backup,
 			       btrfs_header_level(info->chunk_root->node));
 
-	btrfs_set_backup_extent_root(root_backup, extent_root->node->start);
-	btrfs_set_backup_extent_root_gen(root_backup,
-			       btrfs_header_generation(extent_root->node));
-	btrfs_set_backup_extent_root_level(root_backup,
-			       btrfs_header_level(extent_root->node));
+	if (btrfs_fs_incompat(info, EXTENT_TREE_V2)) {
+		btrfs_set_backup_block_group_root(root_backup,
+					info->block_group_root->node->start);
+		btrfs_set_backup_block_group_root_gen(root_backup,
+			btrfs_header_generation(info->block_group_root->node));
+		btrfs_set_backup_block_group_root_level(root_backup,
+			btrfs_header_level(info->block_group_root->node));
+	} else {
+		struct btrfs_root *extent_root = btrfs_extent_root(info, 0);
+		struct btrfs_root *csum_root = btrfs_csum_root(info, 0);
+
+		btrfs_set_backup_extent_root(root_backup,
+					     extent_root->node->start);
+		btrfs_set_backup_extent_root_gen(root_backup,
+				btrfs_header_generation(extent_root->node));
+		btrfs_set_backup_extent_root_level(root_backup,
+					btrfs_header_level(extent_root->node));
+
+		btrfs_set_backup_csum_root(root_backup, csum_root->node->start);
+		btrfs_set_backup_csum_root_gen(root_backup,
+					       btrfs_header_generation(csum_root->node));
+		btrfs_set_backup_csum_root_level(root_backup,
+						 btrfs_header_level(csum_root->node));
+	}
 
 	/*
 	 * we might commit during log recovery, which happens before we set
@@ -2146,12 +2199,6 @@ static void backup_super_roots(struct btrfs_fs_info *info)
 	btrfs_set_backup_dev_root_level(root_backup,
 				       btrfs_header_level(info->dev_root->node));
 
-	btrfs_set_backup_csum_root(root_backup, csum_root->node->start);
-	btrfs_set_backup_csum_root_gen(root_backup,
-				       btrfs_header_generation(csum_root->node));
-	btrfs_set_backup_csum_root_level(root_backup,
-					 btrfs_header_level(csum_root->node));
-
 	btrfs_set_backup_total_bytes(root_backup,
 			     btrfs_super_total_bytes(info->super_copy));
 	btrfs_set_backup_bytes_used(root_backup,
@@ -2269,6 +2316,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 	free_root_extent_buffers(info->uuid_root);
 	free_root_extent_buffers(info->fs_root);
 	free_root_extent_buffers(info->data_reloc_root);
+	free_root_extent_buffers(info->block_group_root);
 	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 }
@@ -2504,11 +2552,13 @@ static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
 		log_tree_root->node = NULL;
 		btrfs_put_root(log_tree_root);
 		return ret;
-	} else if (!extent_buffer_uptodate(log_tree_root->node)) {
+	}
+	if (!extent_buffer_uptodate(log_tree_root->node)) {
 		btrfs_err(fs_info, "failed to read log tree");
 		btrfs_put_root(log_tree_root);
 		return -EIO;
 	}
+
 	/* returns with log_tree_root freed on success */
 	ret = btrfs_recover_log_trees(log_tree_root);
 	if (ret) {
@@ -2533,6 +2583,7 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 {
 	struct btrfs_fs_info *fs_info = tree_root->fs_info;
 	struct btrfs_root *root;
+	u64 max_global_id = 0;
 	int ret;
 	struct btrfs_key key = {
 		.objectid = objectid,
@@ -2568,6 +2619,13 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 			break;
 		btrfs_release_path(path);
 
+		/*
+		 * Just worry about this for extent tree, it'll be the same for
+		 * everybody.
+		 */
+		if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
+			max_global_id = max(max_global_id, key.offset);
+
 		found = true;
 		root = read_tree_root_path(tree_root, path, &key);
 		if (IS_ERR(root)) {
@@ -2585,6 +2643,9 @@ static int load_global_roots_objectid(struct btrfs_root *tree_root,
 	}
 	btrfs_release_path(path);
 
+	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
+		fs_info->nr_global_roots = max_global_id + 1;
+
 	if (!found || ret) {
 		if (objectid == BTRFS_CSUM_TREE_OBJECTID)
 			set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
@@ -2930,6 +2991,56 @@ out:
 	return ret;
 }
 
+static int load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int level)
+{
+	int ret = 0;
+
+	root->node = read_tree_block(root->fs_info, bytenr,
+				     root->root_key.objectid, gen, level, NULL);
+	if (IS_ERR(root->node)) {
+		ret = PTR_ERR(root->node);
+		root->node = NULL;
+		return ret;
+	}
+	if (!extent_buffer_uptodate(root->node)) {
+		free_extent_buffer(root->node);
+		root->node = NULL;
+		return -EIO;
+	}
+
+	btrfs_set_root_node(&root->root_item, root->node);
+	root->commit_root = btrfs_root_node(root);
+	btrfs_set_root_refs(&root->root_item, 1);
+	return ret;
+}
+
+static int load_important_roots(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_super_block *sb = fs_info->super_copy;
+	u64 gen, bytenr;
+	int level, ret;
+
+	bytenr = btrfs_super_root(sb);
+	gen = btrfs_super_generation(sb);
+	level = btrfs_super_root_level(sb);
+	ret = load_super_root(fs_info->tree_root, bytenr, gen, level);
+	if (ret) {
+		btrfs_warn(fs_info, "couldn't read tree root");
+		return ret;
+	}
+
+	if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
+		return 0;
+
+	bytenr = btrfs_super_block_group_root(sb);
+	gen = btrfs_super_block_group_root_generation(sb);
+	level = btrfs_super_block_group_root_level(sb);
+	ret = load_super_root(fs_info->block_group_root, bytenr, gen, level);
+	if (ret)
+		btrfs_warn(fs_info, "couldn't read block group root");
+	return ret;
+}
+
 static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 {
 	int backup_index = find_newest_super_backup(fs_info);
@@ -2939,10 +3050,17 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 	int ret = 0;
 	int i;
 
-	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
-		u64 generation;
-		int level;
+	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
+		struct btrfs_root *root;
+
+		root = btrfs_alloc_root(fs_info, BTRFS_BLOCK_GROUP_TREE_OBJECTID,
+					GFP_KERNEL);
+		if (!root)
+			return -ENOMEM;
+		fs_info->block_group_root = root;
+	}
 
+	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
 		if (handle_error) {
 			if (!IS_ERR(tree_root->node))
 				free_extent_buffer(tree_root->node);
@@ -2967,29 +3085,13 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 			if (ret < 0)
 				return ret;
 		}
-		generation = btrfs_super_generation(sb);
-		level = btrfs_super_root_level(sb);
-		tree_root->node = read_tree_block(fs_info, btrfs_super_root(sb),
-						  BTRFS_ROOT_TREE_OBJECTID,
-						  generation, level, NULL);
-		if (IS_ERR(tree_root->node)) {
-			handle_error = true;
-			ret = PTR_ERR(tree_root->node);
-			tree_root->node = NULL;
-			btrfs_warn(fs_info, "couldn't read tree root");
-			continue;
 
-		} else if (!extent_buffer_uptodate(tree_root->node)) {
+		ret = load_important_roots(fs_info);
+		if (ret) {
 			handle_error = true;
-			ret = -EIO;
-			btrfs_warn(fs_info, "error while reading tree root");
 			continue;
 		}
 
-		btrfs_set_root_node(&tree_root->root_item, tree_root->node);
-		tree_root->commit_root = btrfs_root_node(tree_root);
-		btrfs_set_root_refs(&tree_root->root_item, 1);
-
 		/*
 		 * No need to hold btrfs_root::objectid_mutex since the fs
 		 * hasn't been fully initialised and we are the only user
@@ -3009,8 +3111,8 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 		}
 
 		/* All successful */
-		fs_info->generation = generation;
-		fs_info->last_trans_committed = generation;
+		fs_info->generation = btrfs_header_generation(tree_root->node);
+		fs_info->last_trans_committed = fs_info->generation;
 		fs_info->last_reloc_trans = 0;
 
 		/* Always begin writing backup roots after the one being used */
@@ -3293,7 +3395,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 	up_read(&fs_info->cleanup_work_sem);
 
 	mutex_lock(&fs_info->cleaner_mutex);
-	ret = btrfs_recover_relocation(fs_info->tree_root);
+	ret = btrfs_recover_relocation(fs_info);
 	mutex_unlock(&fs_info->cleaner_mutex);
 	if (ret < 0) {
 		btrfs_warn(fs_info, "failed to recover relocation: %d", ret);
@@ -3594,21 +3696,12 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 
 	generation = btrfs_super_chunk_root_generation(disk_super);
 	level = btrfs_super_chunk_root_level(disk_super);
-
-	chunk_root->node = read_tree_block(fs_info,
-					   btrfs_super_chunk_root(disk_super),
-					   BTRFS_CHUNK_TREE_OBJECTID,
-					   generation, level, NULL);
-	if (IS_ERR(chunk_root->node) ||
-	    !extent_buffer_uptodate(chunk_root->node)) {
+	ret = load_super_root(chunk_root, btrfs_super_chunk_root(disk_super),
+			      generation, level);
+	if (ret) {
 		btrfs_err(fs_info, "failed to read chunk root");
-		if (!IS_ERR(chunk_root->node))
-			free_extent_buffer(chunk_root->node);
-		chunk_root->node = NULL;
 		goto fail_tree_roots;
 	}
-	btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
-	chunk_root->commit_root = btrfs_root_node(chunk_root);
 
 	read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid,
 			   offsetof(struct btrfs_header, chunk_tree_uuid),
@@ -3728,7 +3821,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sysfs;
 	}
 
-	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
+	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, fs_info,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
 		goto fail_sysfs;