Merge v6.18.6linux-rolling-stable

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

7 files changed, 85 insertions, 43 deletions

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 3df7b9d7fbe8..59b489d7e4b5 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -152,37 +152,39 @@ again:
 		return ERR_PTR(-ENOMEM);
 	btrfs_init_delayed_node(node, root, ino);
 
+	/* Cached in the inode and can be accessed. */
+	refcount_set(&node->refs, 2);
+	btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_NOFS);
+	btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_NOFS);
+
 	/* Allocate and reserve the slot, from now it can return a NULL from xa_load(). */
 	ret = xa_reserve(&root->delayed_nodes, ino, GFP_NOFS);
-	if (ret == -ENOMEM) {
-		btrfs_delayed_node_ref_tracker_dir_exit(node);
-		kmem_cache_free(delayed_node_cache, node);
-		return ERR_PTR(-ENOMEM);
-	}
+	if (ret == -ENOMEM)
+		goto cleanup;
+
 	xa_lock(&root->delayed_nodes);
 	ptr = xa_load(&root->delayed_nodes, ino);
 	if (ptr) {
 		/* Somebody inserted it, go back and read it. */
 		xa_unlock(&root->delayed_nodes);
-		btrfs_delayed_node_ref_tracker_dir_exit(node);
-		kmem_cache_free(delayed_node_cache, node);
-		node = NULL;
-		goto again;
+		goto cleanup;
 	}
 	ptr = __xa_store(&root->delayed_nodes, ino, node, GFP_ATOMIC);
 	ASSERT(xa_err(ptr) != -EINVAL);
 	ASSERT(xa_err(ptr) != -ENOMEM);
 	ASSERT(ptr == NULL);
-
-	/* Cached in the inode and can be accessed. */
-	refcount_set(&node->refs, 2);
-	btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_ATOMIC);
-	btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_ATOMIC);
-
 	btrfs_inode->delayed_node = node;
 	xa_unlock(&root->delayed_nodes);
 
 	return node;
+cleanup:
+	btrfs_delayed_node_ref_tracker_free(node, tracker);
+	btrfs_delayed_node_ref_tracker_free(node, &node->inode_cache_tracker);
+	btrfs_delayed_node_ref_tracker_dir_exit(node);
+	kmem_cache_free(delayed_node_cache, node);
+	if (ret)
+		return ERR_PTR(ret);
+	goto again;
 }
 
 /*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 23273d0e6f22..1a07edaefaa0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1691,14 +1691,15 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 	unsigned long range_bitmap = 0;
 	bool submitted_io = false;
 	int found_error = 0;
+	const u64 end = start + len;
 	const u64 folio_start = folio_pos(folio);
+	const u64 folio_end = folio_start + folio_size(folio);
 	const unsigned int blocks_per_folio = btrfs_blocks_per_folio(fs_info, folio);
 	u64 cur;
 	int bit;
 	int ret = 0;
 
-	ASSERT(start >= folio_start &&
-	       start + len <= folio_start + folio_size(folio));
+	ASSERT(start >= folio_start && end <= folio_end);
 
 	ret = btrfs_writepage_cow_fixup(folio);
 	if (ret == -EAGAIN) {
@@ -1714,7 +1715,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 		return ret;
 	}
 
-	for (cur = start; cur < start + len; cur += fs_info->sectorsize)
+	for (cur = start; cur < end; cur += fs_info->sectorsize)
 		set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap);
 	bitmap_and(&bio_ctrl->submit_bitmap, &bio_ctrl->submit_bitmap, &range_bitmap,
 		   blocks_per_folio);
@@ -1725,8 +1726,25 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 		cur = folio_pos(folio) + (bit << fs_info->sectorsize_bits);
 
 		if (cur >= i_size) {
+			struct btrfs_ordered_extent *ordered;
+			unsigned long flags;
+
+			ordered = btrfs_lookup_first_ordered_range(inode, cur,
+								   fs_info->sectorsize);
+			/*
+			 * We have just run delalloc before getting here, so
+			 * there must be an ordered extent.
+			 */
+			ASSERT(ordered != NULL);
+			spin_lock_irqsave(&inode->ordered_tree_lock, flags);
+			set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
+			ordered->truncated_len = min(ordered->truncated_len,
+						     cur - ordered->file_offset);
+			spin_unlock_irqrestore(&inode->ordered_tree_lock, flags);
+			btrfs_put_ordered_extent(ordered);
+
 			btrfs_mark_ordered_io_finished(inode, folio, cur,
-						       start + len - cur, true);
+						       fs_info->sectorsize, true);
 			/*
 			 * This range is beyond i_size, thus we don't need to
 			 * bother writing back.
@@ -1735,9 +1753,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode,
 			 * writeback the sectors with subpage dirty bits,
 			 * causing writeback without ordered extent.
 			 */
-			btrfs_folio_clear_dirty(fs_info, folio, cur,
-						start + len - cur);
-			break;
+			btrfs_folio_clear_dirty(fs_info, folio, cur, fs_info->sectorsize);
+			continue;
 		}
 		ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size);
 		if (unlikely(ret < 0)) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 51401d586a7b..27a562bad6e8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3976,11 +3976,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	btrfs_set_inode_mapping_order(inode);
 
 cache_index:
-	ret = btrfs_init_file_extent_tree(inode);
-	if (ret)
-		goto out;
-	btrfs_inode_set_file_extent_range(inode, 0,
-			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 	/*
 	 * If we were modified in the current generation and evicted from memory
 	 * and then re-read we need to do a full sync since we don't have any
@@ -4067,6 +4062,20 @@ cache_acl:
 				  btrfs_ino(inode), btrfs_root_id(root), ret);
 	}
 
+	/*
+	 * We don't need the path anymore, so release it to avoid holding a read
+	 * lock on a leaf while calling btrfs_init_file_extent_tree(), which can
+	 * allocate memory that triggers reclaim (GFP_KERNEL) and cause a locking
+	 * dependency.
+	 */
+	btrfs_release_path(path);
+
+	ret = btrfs_init_file_extent_tree(inode);
+	if (ret)
+		goto out;
+	btrfs_inode_set_file_extent_range(inode, 0,
+			  round_up(i_size_read(vfs_inode), fs_info->sectorsize));
+
 	if (!maybe_acls)
 		cache_no_acl(vfs_inode);
 
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2829f20d7bb5..8a8aa6ed405b 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -1098,8 +1098,9 @@ struct btrfs_ordered_extent *btrfs_lookup_first_ordered_range(
 	struct rb_node *prev;
 	struct rb_node *next;
 	struct btrfs_ordered_extent *entry = NULL;
+	unsigned long flags;
 
-	spin_lock_irq(&inode->ordered_tree_lock);
+	spin_lock_irqsave(&inode->ordered_tree_lock, flags);
 	node = inode->ordered_tree.rb_node;
 	/*
 	 * Here we don't want to use tree_search() which will use tree->last
@@ -1154,7 +1155,7 @@ out:
 		trace_btrfs_ordered_extent_lookup_first_range(inode, entry);
 	}
 
-	spin_unlock_irq(&inode->ordered_tree_lock);
+	spin_unlock_irqrestore(&inode->ordered_tree_lock, flags);
 	return entry;
 }
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 31ad8580322a..febc22d1b648 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -3244,9 +3244,15 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info,
 {
 	struct btrfs_qgroup *src;
 	struct btrfs_qgroup *parent;
+	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup_list *list;
+	LIST_HEAD(qgroup_list);
+	const u32 nodesize = fs_info->nodesize;
 	int nr_parents = 0;
 
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_FULL)
+		return 0;
+
 	src = find_qgroup_rb(fs_info, srcid);
 	if (!src)
 		return -ENOENT;
@@ -3281,8 +3287,19 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info,
 	if (parent->excl != parent->rfer)
 		return 1;
 
-	parent->excl += fs_info->nodesize;
-	parent->rfer += fs_info->nodesize;
+	qgroup_iterator_add(&qgroup_list, parent);
+	list_for_each_entry(qgroup, &qgroup_list, iterator) {
+		qgroup->rfer += nodesize;
+		qgroup->rfer_cmpr += nodesize;
+		qgroup->excl += nodesize;
+		qgroup->excl_cmpr += nodesize;
+		qgroup_dirty(fs_info, qgroup);
+
+		/* Append parent qgroups to @qgroup_list. */
+		list_for_each_entry(list, &qgroup->groups, next_group)
+			qgroup_iterator_add(&qgroup_list, list->group);
+	}
+	qgroup_iterator_clean(&qgroup_list);
 	return 0;
 }
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 430e7419349c..c40944ca7b94 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -736,14 +736,12 @@ bool btrfs_check_options(const struct btrfs_fs_info *info,
  */
 void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info)
 {
-	if (fs_info->sectorsize < PAGE_SIZE) {
+	if (fs_info->sectorsize < PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) {
+		btrfs_info(fs_info,
+			   "forcing free space tree for sector size %u with page size %lu",
+			   fs_info->sectorsize, PAGE_SIZE);
 		btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
-		if (!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) {
-			btrfs_info(fs_info,
-				   "forcing free space tree for sector size %u with page size %lu",
-				   fs_info->sectorsize, PAGE_SIZE);
-			btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
-		}
+		btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE);
 	}
 
 	/*
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index e0b0750696a1..1444857de9fe 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -189,7 +189,7 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function,
 
 	btrfs_abort_transaction(wc->trans, error);
 
-	if (wc->subvol_path->nodes[0]) {
+	if (wc->subvol_path && wc->subvol_path->nodes[0]) {
 		btrfs_crit(fs_info,
 			   "subvolume (root %llu) leaf currently being processed:",
 			   btrfs_root_id(wc->root));
@@ -6348,10 +6348,8 @@ again:
 			 * and no keys greater than that, so bail out.
 			 */
 			break;
-		} else if ((min_key->type == BTRFS_INODE_REF_KEY ||
-			    min_key->type == BTRFS_INODE_EXTREF_KEY) &&
-			   (inode->generation == trans->transid ||
-			    ctx->logging_conflict_inodes)) {
+		} else if (min_key->type == BTRFS_INODE_REF_KEY ||
+			   min_key->type == BTRFS_INODE_EXTREF_KEY) {
 			u64 other_ino = 0;
 			u64 other_parent = 0;