Merge branch 'next' into for-linus

Prepare input updates for 6.3 merge window.

1 files changed, 34 insertions, 53 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index cd2d36580f1a..72ba13b027a9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -36,6 +36,13 @@
 #include "rcu-string.h"
 #include "zoned.h"
 #include "dev-replace.h"
+#include "fs.h"
+#include "accessors.h"
+#include "extent-tree.h"
+#include "root-tree.h"
+#include "file-item.h"
+#include "orphan.h"
+#include "tree-checker.h"
 
 #undef SCRAMBLE_DELAYED_REFS
 
@@ -1706,6 +1713,11 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 		BUG();
 	if (ret && insert_reserved)
 		btrfs_pin_extent(trans, node->bytenr, node->num_bytes, 1);
+	if (ret < 0)
+		btrfs_err(trans->fs_info,
+"failed to run delayed ref for logical %llu num_bytes %llu type %u action %u ref_mod %d: %d",
+			  node->bytenr, node->num_bytes, node->type,
+			  node->action, node->ref_mod, ret);
 	return ret;
 }
 
@@ -1947,8 +1959,6 @@ static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
 		if (ret) {
 			unselect_delayed_ref_head(delayed_refs, locked_ref);
 			btrfs_put_delayed_ref(ref);
-			btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
-				    ret);
 			return ret;
 		}
 
@@ -3295,21 +3305,22 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		}
 
 		/*
-		 * If this is a leaf and there are tree mod log users, we may
-		 * have recorded mod log operations that point to this leaf.
-		 * So we must make sure no one reuses this leaf's extent before
-		 * mod log operations are applied to a node, otherwise after
-		 * rewinding a node using the mod log operations we get an
-		 * inconsistent btree, as the leaf's extent may now be used as
-		 * a node or leaf for another different btree.
+		 * If there are tree mod log users we may have recorded mod log
+		 * operations for this node.  If we re-allocate this node we
+		 * could replay operations on this node that happened when it
+		 * existed in a completely different root.  For example if it
+		 * was part of root A, then was reallocated to root B, and we
+		 * are doing a btrfs_old_search_slot(root b), we could replay
+		 * operations that happened when the block was part of root A,
+		 * giving us an inconsistent view of the btree.
+		 *
 		 * We are safe from races here because at this point no other
 		 * node or root points to this extent buffer, so if after this
-		 * check a new tree mod log user joins, it will not be able to
-		 * find a node pointing to this leaf and record operations that
-		 * point to this leaf.
+		 * check a new tree mod log user joins we will not have an
+		 * existing log of operations on this node that we have to
+		 * contend with.
 		 */
-		if (btrfs_header_level(buf) == 0 &&
-		    test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
+		if (test_bit(BTRFS_FS_TREE_MOD_LOG_USERS, &fs_info->flags))
 			must_pin = true;
 
 		if (must_pin || btrfs_is_zoned(fs_info)) {
@@ -5254,8 +5265,8 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	u64 bytenr;
 	u64 generation;
 	u64 parent;
+	struct btrfs_tree_parent_check check = { 0 };
 	struct btrfs_key key;
-	struct btrfs_key first_key;
 	struct btrfs_ref ref = { 0 };
 	struct extent_buffer *next;
 	int level = wc->level;
@@ -5277,7 +5288,12 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	}
 
 	bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]);
-	btrfs_node_key_to_cpu(path->nodes[level], &first_key,
+
+	check.level = level - 1;
+	check.transid = generation;
+	check.owner_root = root->root_key.objectid;
+	check.has_first_key = true;
+	btrfs_node_key_to_cpu(path->nodes[level], &check.first_key,
 			      path->slots[level]);
 
 	next = find_extent_buffer(fs_info, bytenr);
@@ -5339,8 +5355,7 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	if (!next) {
 		if (reada && level == 1)
 			reada_walk_down(trans, root, wc, path);
-		next = read_tree_block(fs_info, bytenr, root->root_key.objectid,
-				       generation, level - 1, &first_key);
+		next = read_tree_block(fs_info, bytenr, &check);
 		if (IS_ERR(next)) {
 			return PTR_ERR(next);
 		} else if (!extent_buffer_uptodate(next)) {
@@ -5972,40 +5987,6 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-/*
- * helper to account the unused space of all the readonly block group in the
- * space_info. takes mirrors into account.
- */
-u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
-{
-	struct btrfs_block_group *block_group;
-	u64 free_bytes = 0;
-	int factor;
-
-	/* It's df, we don't care if it's racy */
-	if (list_empty(&sinfo->ro_bgs))
-		return 0;
-
-	spin_lock(&sinfo->lock);
-	list_for_each_entry(block_group, &sinfo->ro_bgs, ro_list) {
-		spin_lock(&block_group->lock);
-
-		if (!block_group->ro) {
-			spin_unlock(&block_group->lock);
-			continue;
-		}
-
-		factor = btrfs_bg_type_to_factor(block_group->flags);
-		free_bytes += (block_group->length -
-			       block_group->used) * factor;
-
-		spin_unlock(&block_group->lock);
-	}
-	spin_unlock(&sinfo->lock);
-
-	return free_bytes;
-}
-
 int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end)
 {
@@ -6071,7 +6052,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device, u64 *trimmed)
 			btrfs_warn_in_rcu(fs_info,
 "ignoring attempt to trim beyond device size: offset %llu length %llu device %s device size %llu",
 					  start, end - start + 1,
-					  rcu_str_deref(device->name),
+					  btrfs_dev_name(device),
 					  device->total_bytes);
 			mutex_unlock(&fs_info->chunk_mutex);
 			ret = 0;