Merge tag 'for-6.7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs updates from David Sterba:
 "New features:

   - raid-stripe-tree

     New tree for logical file extent mapping where the physical mapping
     may not match on multiple devices. This is now used in zoned mode
     to implement RAID0/RAID1* profiles, but can be used in non-zoned
     mode as well. The support for RAID56 is in development and will
     eventually fix the problems with the current implementation. This
     is a backward incompatible feature and has to be enabled at mkfs
     time.

   - simple quota accounting (squota)

     A simplified mode of qgroup that accounts all space on the initial
     extent owners (a subvolume), the snapshots are then cheap to create
     and delete. The deletion of snapshots in fully accounting qgroups
     is a known CPU/IO performance bottleneck.

     The squota is not suitable for the general use case but works well
     for containers where the original subvolume exists for the whole
     time. This is a backward incompatible feature as it needs extending
     some structures, but can be enabled on an existing filesystem.

   - temporary filesystem fsid (temp_fsid)

     The fsid identifies a filesystem and is hard coded in the
     structures, which disallows mounting the same fsid found on
     different devices.

     For a single device filesystem this is not strictly necessary, a
     new temporary fsid can be generated on mount e.g. after a device is
     cloned. This will be used by Steam Deck for root partition A/B
     testing, or can be used for VM root images.

  Other user visible changes:

   - filesystems with partially finished metadata_uuid conversion cannot
     be mounted anymore and the uuid fixup has to be done by btrfs-progs
     (btrfstune).

  Performance improvements:

   - reduce reservations for checksum deletions (with enabled free space
     tree by factor of 4), on a sample workload on file with many
     extents the deletion time decreased by 12%

   - make extent state merges more efficient during insertions, reduce
     rb-tree iterations (run time of critical functions reduced by 5%)

  Core changes:

   - the integrity check functionality has been removed, this was a
     debugging feature and removal does not affect other integrity
     checks like checksums or tree-checker

   - space reservation changes:

      - more efficient delayed ref reservations, this avoids building up
        too much work or overusing or exhausting the global block
        reserve in some situations

      - move delayed refs reservation to the transaction start time,
        this prevents some ENOSPC corner cases related to exhaustion of
        global reserve

      - improvements in reducing excessive reservations for block group
        items

      - adjust overcommit logic in near full situations, account for one
        more chunk to eventually allocate metadata chunk, this is mostly
        relevant for small filesystems (<10GiB)

   - single device filesystems are scanned but not registered (except
     seed devices), this allows temp_fsid to work

   - qgroup iterations do not need GFP_ATOMIC allocations anymore

   - cleanups, refactoring, reduced data structure size, function
     parameter simplifications, error handling fixes"

* tag 'for-6.7-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (156 commits)
  btrfs: open code timespec64 in struct btrfs_inode
  btrfs: remove redundant log root tree index assignment during log sync
  btrfs: remove redundant initialization of variable dirty in btrfs_update_time()
  btrfs: sysfs: show temp_fsid feature
  btrfs: disable the device add feature for temp-fsid
  btrfs: disable the seed feature for temp-fsid
  btrfs: update comment for temp-fsid, fsid, and metadata_uuid
  btrfs: remove pointless empty log context list check when syncing log
  btrfs: update comment for struct btrfs_inode::lock
  btrfs: remove pointless barrier from btrfs_sync_file()
  btrfs: add and use helpers for reading and writing last_trans_committed
  btrfs: add and use helpers for reading and writing fs_info->generation
  btrfs: add and use helpers for reading and writing log_transid
  btrfs: add and use helpers for reading and writing last_log_commit
  btrfs: support cloned-device mount capability
  btrfs: add helper function find_fsid_by_disk
  btrfs: stop reserving excessive space for block group item insertions
  btrfs: stop reserving excessive space for block group item updates
  btrfs: reorder btrfs_inode to fill gaps
  btrfs: open code btrfs_ordered_inode_tree in btrfs_inode
  ...

1 files changed, 36 insertions, 45 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index bfee3ebb422f..7d6729d9fd2f 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -347,8 +347,7 @@ static int process_one_buffer(struct btrfs_root *log,
 	}
 
 	if (wc->pin) {
-		ret = btrfs_pin_extent_for_log_replay(wc->trans, eb->start,
-						      eb->len);
+		ret = btrfs_pin_extent_for_log_replay(wc->trans, eb);
 		if (ret)
 			return ret;
 
@@ -504,9 +503,9 @@ insert:
 		found_size = btrfs_item_size(path->nodes[0],
 						path->slots[0]);
 		if (found_size > item_size)
-			btrfs_truncate_item(path, item_size, 1);
+			btrfs_truncate_item(trans, path, item_size, 1);
 		else if (found_size < item_size)
-			btrfs_extend_item(path, item_size - found_size);
+			btrfs_extend_item(trans, path, item_size - found_size);
 	} else if (ret) {
 		return ret;
 	}
@@ -574,7 +573,7 @@ insert:
 		}
 	}
 no_copy:
-	btrfs_mark_buffer_dirty(path->nodes[0]);
+	btrfs_mark_buffer_dirty(trans, path->nodes[0]);
 	btrfs_release_path(path);
 	return 0;
 }
@@ -767,7 +766,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 			} else if (ret == 0) {
 				btrfs_init_generic_ref(&ref,
 						BTRFS_ADD_DELAYED_REF,
-						ins.objectid, ins.offset, 0);
+						ins.objectid, ins.offset, 0,
+						root->root_key.objectid);
 				btrfs_init_data_ref(&ref,
 						root->root_key.objectid,
 						key->objectid, offset, 0, false);
@@ -890,7 +890,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 
 update_inode:
 	btrfs_update_inode_bytes(BTRFS_I(inode), nbytes, drop_args.bytes_found);
-	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+	ret = btrfs_update_inode(trans, BTRFS_I(inode));
 out:
 	iput(inode);
 	return ret;
@@ -1445,7 +1445,7 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 			if (ret)
 				goto out;
 
-			ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+			ret = btrfs_update_inode(trans, BTRFS_I(inode));
 			if (ret)
 				goto out;
 		}
@@ -1483,8 +1483,7 @@ out:
 	return ret;
 }
 
-static int count_inode_extrefs(struct btrfs_root *root,
-		struct btrfs_inode *inode, struct btrfs_path *path)
+static int count_inode_extrefs(struct btrfs_inode *inode, struct btrfs_path *path)
 {
 	int ret = 0;
 	int name_len;
@@ -1498,8 +1497,8 @@ static int count_inode_extrefs(struct btrfs_root *root,
 	struct extent_buffer *leaf;
 
 	while (1) {
-		ret = btrfs_find_one_extref(root, inode_objectid, offset, path,
-					    &extref, &offset);
+		ret = btrfs_find_one_extref(inode->root, inode_objectid, offset,
+					    path, &extref, &offset);
 		if (ret)
 			break;
 
@@ -1527,8 +1526,7 @@ static int count_inode_extrefs(struct btrfs_root *root,
 	return nlink;
 }
 
-static int count_inode_refs(struct btrfs_root *root,
-			struct btrfs_inode *inode, struct btrfs_path *path)
+static int count_inode_refs(struct btrfs_inode *inode, struct btrfs_path *path)
 {
 	int ret;
 	struct btrfs_key key;
@@ -1543,7 +1541,7 @@ static int count_inode_refs(struct btrfs_root *root,
 	key.offset = (u64)-1;
 
 	while (1) {
-		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+		ret = btrfs_search_slot(NULL, inode->root, &key, path, 0, 0);
 		if (ret < 0)
 			break;
 		if (ret > 0) {
@@ -1595,9 +1593,9 @@ process_slot:
  * will free the inode.
  */
 static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
-					   struct btrfs_root *root,
 					   struct inode *inode)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
 	int ret;
 	u64 nlink = 0;
@@ -1607,13 +1605,13 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = count_inode_refs(root, BTRFS_I(inode), path);
+	ret = count_inode_refs(BTRFS_I(inode), path);
 	if (ret < 0)
 		goto out;
 
 	nlink = ret;
 
-	ret = count_inode_extrefs(root, BTRFS_I(inode), path);
+	ret = count_inode_extrefs(BTRFS_I(inode), path);
 	if (ret < 0)
 		goto out;
 
@@ -1623,7 +1621,7 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 
 	if (nlink != inode->i_nlink) {
 		set_nlink(inode, nlink);
-		ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+		ret = btrfs_update_inode(trans, BTRFS_I(inode));
 		if (ret)
 			goto out;
 	}
@@ -1685,7 +1683,7 @@ static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
 			break;
 		}
 
-		ret = fixup_inode_link_count(trans, root, inode);
+		ret = fixup_inode_link_count(trans, inode);
 		iput(inode);
 		if (ret)
 			break;
@@ -1732,7 +1730,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
 			set_nlink(inode, 1);
 		else
 			inc_nlink(inode);
-		ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
+		ret = btrfs_update_inode(trans, BTRFS_I(inode));
 	} else if (ret == -EEXIST) {
 		ret = 0;
 	}
@@ -1939,7 +1937,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 out:
 	if (!ret && update_size) {
 		btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name.len * 2);
-		ret = btrfs_update_inode(trans, root, BTRFS_I(dir));
+		ret = btrfs_update_inode(trans, BTRFS_I(dir));
 	}
 	kfree(name.name);
 	iput(dir);
@@ -2483,7 +2481,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 							drop_args.bytes_found);
 					/* Update the inode's nbytes. */
 					ret = btrfs_update_inode(wc->trans,
-							root, BTRFS_I(inode));
+								 BTRFS_I(inode));
 				}
 				iput(inode);
 				if (ret)
@@ -2574,7 +2572,7 @@ static int clean_log_buffer(struct btrfs_trans_handle *trans,
 	btrfs_tree_unlock(eb);
 
 	if (trans) {
-		ret = btrfs_pin_reserved_extent(trans, eb->start, eb->len);
+		ret = btrfs_pin_reserved_extent(trans, eb);
 		if (ret)
 			return ret;
 		btrfs_redirty_list_add(trans->transaction, eb);
@@ -2848,10 +2846,9 @@ static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
 }
 
 /*
- * btrfs_sync_log does sends a given tree log down to the disk and
- * updates the super blocks to record it.  When this call is done,
- * you know that any inodes previously logged are safely on disk only
- * if it returns 0.
+ * Sends a given tree log down to the disk and updates the super blocks to
+ * record it.  When this call is done, you know that any inodes previously
+ * logged are safely on disk only if it returns 0.
  *
  * Any other return value means you need to call btrfs_commit_transaction.
  * Some of the edge cases for fsyncing directories that have had unlinks
@@ -2961,7 +2958,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	btrfs_set_root_node(&log->root_item, log->node);
 	memcpy(&new_root_item, &log->root_item, sizeof(new_root_item));
 
-	root->log_transid++;
+	btrfs_set_root_log_transid(root, root->log_transid + 1);
 	log->log_transid = root->log_transid;
 	root->log_start_pid = 0;
 	/*
@@ -2999,9 +2996,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 */
 	ret = update_log_root(trans, log, &new_root_item);
 	if (ret) {
-		if (!list_empty(&root_log_ctx.list))
-			list_del_init(&root_log_ctx.list);
-
+		list_del_init(&root_log_ctx.list);
 		blk_finish_plug(&plug);
 		btrfs_set_log_full_commit(trans);
 		if (ret != -ENOSPC)
@@ -3021,7 +3016,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	index2 = root_log_ctx.log_transid % 2;
 	if (atomic_read(&log_root_tree->log_commit[index2])) {
 		blk_finish_plug(&plug);
 		ret = btrfs_wait_tree_log_extents(log, mark);
@@ -3136,8 +3130,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 * someone else already started it. We use <= and not < because the
 	 * first log transaction has an ID of 0.
 	 */
-	ASSERT(root->last_log_commit <= log_transid);
-	root->last_log_commit = log_transid;
+	ASSERT(btrfs_get_root_last_log_commit(root) <= log_transid);
+	btrfs_set_root_last_log_commit(root, log_transid);
 
 out_wake_log_root:
 	mutex_lock(&log_root_tree->log_mutex);
@@ -3211,8 +3205,7 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	clear_extent_bits(&log->dirty_log_pages, 0, (u64)-1,
-			  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
+	extent_io_tree_release(&log->dirty_log_pages);
 	extent_io_tree_release(&log->log_csum_range);
 
 	btrfs_put_root(log);
@@ -3530,7 +3523,7 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
 		last_offset = max(last_offset, curr_end);
 	}
 	btrfs_set_dir_log_end(path->nodes[0], item, last_offset);
-	btrfs_mark_buffer_dirty(path->nodes[0]);
+	btrfs_mark_buffer_dirty(trans, path->nodes[0]);
 	btrfs_release_path(path);
 	return 0;
 }
@@ -4488,7 +4481,7 @@ copy_item:
 		dst_index++;
 	}
 
-	btrfs_mark_buffer_dirty(dst_path->nodes[0]);
+	btrfs_mark_buffer_dirty(trans, dst_path->nodes[0]);
 	btrfs_release_path(dst_path);
 out:
 	kfree(ins_data);
@@ -4693,7 +4686,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	write_extent_buffer(leaf, &fi,
 			    btrfs_item_ptr_offset(leaf, path->slots[0]),
 			    sizeof(fi));
-	btrfs_mark_buffer_dirty(leaf);
+	btrfs_mark_buffer_dirty(trans, leaf);
 
 	btrfs_release_path(path);
 
@@ -4921,12 +4914,12 @@ process:
 		set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags);
 
 		if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-			spin_lock_irq(&inode->ordered_tree.lock);
+			spin_lock_irq(&inode->ordered_tree_lock);
 			if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
 				set_bit(BTRFS_ORDERED_PENDING, &ordered->flags);
 				atomic_inc(&trans->transaction->pending_ordered);
 			}
-			spin_unlock_irq(&inode->ordered_tree.lock);
+			spin_unlock_irq(&inode->ordered_tree_lock);
 		}
 		btrfs_put_ordered_extent(ordered);
 	}
@@ -7204,9 +7197,7 @@ again:
 			 * each subsequent pass.
 			 */
 			if (ret == -ENOENT)
-				ret = btrfs_pin_extent_for_log_replay(trans,
-							log->node->start,
-							log->node->len);
+				ret = btrfs_pin_extent_for_log_replay(trans, log->node);
 			btrfs_put_root(log);
 
 			if (!ret)