Merge tag 'for-5.11-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "A few more fixes that arrived before the end of the year:

   - a bunch of fixes related to transaction handle lifetime wrt various
     operations (umount, remount, qgroup scan, orphan cleanup)

   - async discard scheduling fixes

   - fix item size calculation when item keys collide for extend refs
     (hardlinks)

   - fix qgroup flushing from running transaction

   - fix send, wrong file path when there is an inode with a pending
     rmdir

   - fix deadlock when cloning inline extent and low on free metadata
     space"

* tag 'for-5.11-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: run delayed iputs when remounting RO to avoid leaking them
  btrfs: add assertion for empty list of transactions at late stage of umount
  btrfs: fix race between RO remount and the cleaner task
  btrfs: fix transaction leak and crash after cleaning up orphans on RO mount
  btrfs: fix transaction leak and crash after RO remount caused by qgroup rescan
  btrfs: merge critical sections of discard lock in workfn
  btrfs: fix racy access to discard_ctl data
  btrfs: fix async discard stall
  btrfs: tests: initialize test inodes location
  btrfs: send: fix wrong file path when there is an inode with a pending rmdir
  btrfs: qgroup: don't try to wait flushing if we're already holding a transaction
  btrfs: correctly calculate item size used when item key collision happens
  btrfs: fix deadlock when cloning inline extent and low on free metadata space

Author: torvalds

fs/btrfs/btrfs_inode.h

@@ -42,6 +42,15 @@ enum {
 	 * to an inode.
 	 */
 	BTRFS_INODE_NO_XATTRS,
+	/*
+	 * Set when we are in a context where we need to start a transaction and
+	 * have dirty pages with the respective file range locked. This is to
+	 * ensure that when reserving space for the transaction, if we are low
+	 * on available space and need to flush delalloc, we will not flush
+	 * delalloc for this inode, because that could result in a deadlock (on
+	 * the file range, inode's io_tree).
+	 */
+	BTRFS_INODE_NO_DELALLOC_FLUSH,
 };
 
 /* in memory btrfs inode */

fs/btrfs/ctree.c

@@ -2555,8 +2555,14 @@ static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
  * @p:		Holds all btree nodes along the search path
  * @root:	The root node of the tree
  * @key:	The key we are looking for
- * @ins_len:	Indicates purpose of search, for inserts it is 1, for
- *		deletions it's -1. 0 for plain searches
+ * @ins_len:	Indicates purpose of search:
+ *              >0  for inserts it's size of item inserted (*)
+ *              <0  for deletions
+ *               0  for plain searches, not modifying the tree
+ *
+ *              (*) If size of item inserted doesn't include
+ *              sizeof(struct btrfs_item), then p->search_for_extension must
+ *              be set.
  * @cow:	boolean should CoW operations be performed. Must always be 1
  *		when modifying the tree.
  *
@@ -2717,6 +2723,20 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 
 		if (level == 0) {
 			p->slots[level] = slot;
+			/*
+			 * Item key already exists. In this case, if we are
+			 * allowed to insert the item (for example, in dir_item
+			 * case, item key collision is allowed), it will be
+			 * merged with the original item. Only the item size
+			 * grows, no new btrfs item will be added. If
+			 * search_for_extension is not set, ins_len already
+			 * accounts the size btrfs_item, deduct it here so leaf
+			 * space check will be correct.
+			 */
+			if (ret == 0 && ins_len > 0 && !p->search_for_extension) {
+				ASSERT(ins_len >= sizeof(struct btrfs_item));
+				ins_len -= sizeof(struct btrfs_item);
+			}
 			if (ins_len > 0 &&
 			    btrfs_leaf_free_space(b) < ins_len) {
 				if (write_lock_level < 1) {

fs/btrfs/ctree.h

@@ -131,6 +131,8 @@ enum {
 	 * defrag
 	 */
 	BTRFS_FS_STATE_REMOUNTING,
+	/* Filesystem in RO mode */
+	BTRFS_FS_STATE_RO,
 	/* Track if a transaction abort has been reported on this filesystem */
 	BTRFS_FS_STATE_TRANS_ABORTED,
 	/*
@@ -367,6 +369,12 @@ struct btrfs_path {
 	unsigned int search_commit_root:1;
 	unsigned int need_commit_sem:1;
 	unsigned int skip_release_on_error:1;
+	/*
+	 * Indicate that new item (btrfs_search_slot) is extending already
+	 * existing item and ins_len contains only the data size and not item
+	 * header (ie. sizeof(struct btrfs_item) is not included).
+	 */
+	unsigned int search_for_extension:1;
 };
 #define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
 					sizeof(struct btrfs_item))
@@ -2885,10 +2893,26 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
  * If we remount the fs to be R/O or umount the fs, the cleaner needn't do
  * anything except sleeping. This function is used to check the status of
  * the fs.
+ * We check for BTRFS_FS_STATE_RO to avoid races with a concurrent remount,
+ * since setting and checking for SB_RDONLY in the superblock's flags is not
+ * atomic.
  */
 static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
 {
-	return fs_info->sb->s_flags & SB_RDONLY || btrfs_fs_closing(fs_info);
+	return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) ||
+		btrfs_fs_closing(fs_info);
+}
+
+static inline void btrfs_set_sb_rdonly(struct super_block *sb)
+{
+	sb->s_flags |= SB_RDONLY;
+	set_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
+}
+
+static inline void btrfs_clear_sb_rdonly(struct super_block *sb)
+{
+	sb->s_flags &= ~SB_RDONLY;
+	clear_bit(BTRFS_FS_STATE_RO, &btrfs_sb(sb)->fs_state);
 }
 
 /* tree mod log functions from ctree.c */
@@ -3073,7 +3097,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       u32 min_type);
 
 int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr);
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			       bool in_reclaim_context);
 int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
 			      unsigned int extra_bits,
 			      struct extent_state **cached_state);

fs/btrfs/dev-replace.c

@@ -715,7 +715,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	 * flush all outstanding I/O and inode extent mappings before the
 	 * copy operation is declared as being finished
 	 */
-	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+	ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 	if (ret) {
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;

fs/btrfs/discard.c

@@ -199,16 +199,15 @@ static struct btrfs_block_group *find_next_block_group(
 static struct btrfs_block_group *peek_discard_list(
 					struct btrfs_discard_ctl *discard_ctl,
 					enum btrfs_discard_state *discard_state,
-					int *discard_index)
+					int *discard_index, u64 now)
 {
 	struct btrfs_block_group *block_group;
-	const u64 now = ktime_get_ns();
 
 	spin_lock(&discard_ctl->lock);
 again:
 	block_group = find_next_block_group(discard_ctl, now);
 
-	if (block_group && now > block_group->discard_eligible_time) {
+	if (block_group && now >= block_group->discard_eligible_time) {
 		if (block_group->discard_index == BTRFS_DISCARD_INDEX_UNUSED &&
 		    block_group->used != 0) {
 			if (btrfs_is_block_group_data_only(block_group))
@@ -222,12 +221,11 @@ static struct btrfs_block_group *peek_discard_list(
 			block_group->discard_state = BTRFS_DISCARD_EXTENTS;
 		}
 		discard_ctl->block_group = block_group;
+	}
+	if (block_group) {
 		*discard_state = block_group->discard_state;
 		*discard_index = block_group->discard_index;
-	} else {
-		block_group = NULL;
 	}
-
 	spin_unlock(&discard_ctl->lock);
 
 	return block_group;
@@ -330,28 +328,15 @@ void btrfs_discard_queue_work(struct btrfs_discard_ctl *discard_ctl,
 		btrfs_discard_schedule_work(discard_ctl, false);
 }
 
-/**
- * btrfs_discard_schedule_work - responsible for scheduling the discard work
- * @discard_ctl: discard control
- * @override: override the current timer
- *
- * Discards are issued by a delayed workqueue item.  @override is used to
- * update the current delay as the baseline delay interval is reevaluated on
- * transaction commit.  This is also maxed with any other rate limit.
- */
-void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
-				 bool override)
+static void __btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+					  u64 now, bool override)
 {
 	struct btrfs_block_group *block_group;
-	const u64 now = ktime_get_ns();
-
-	spin_lock(&discard_ctl->lock);
 
 	if (!btrfs_run_discard_work(discard_ctl))
-		goto out;
-
+		return;
 	if (!override && delayed_work_pending(&discard_ctl->work))
-		goto out;
+		return;
 
 	block_group = find_next_block_group(discard_ctl, now);
 	if (block_group) {
@@ -393,7 +378,24 @@ void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
 		mod_delayed_work(discard_ctl->discard_workers,
 				 &discard_ctl->work, nsecs_to_jiffies(delay));
 	}
-out:
+}
+
+/*
+ * btrfs_discard_schedule_work - responsible for scheduling the discard work
+ * @discard_ctl:  discard control
+ * @override:     override the current timer
+ *
+ * Discards are issued by a delayed workqueue item.  @override is used to
+ * update the current delay as the baseline delay interval is reevaluated on
+ * transaction commit.  This is also maxed with any other rate limit.
+ */
+void btrfs_discard_schedule_work(struct btrfs_discard_ctl *discard_ctl,
+				 bool override)
+{
+	const u64 now = ktime_get_ns();
+
+	spin_lock(&discard_ctl->lock);
+	__btrfs_discard_schedule_work(discard_ctl, now, override);
 	spin_unlock(&discard_ctl->lock);
 }
 
@@ -438,13 +440,18 @@ static void btrfs_discard_workfn(struct work_struct *work)
 	int discard_index = 0;
 	u64 trimmed = 0;
 	u64 minlen = 0;
+	u64 now = ktime_get_ns();
 
 	discard_ctl = container_of(work, struct btrfs_discard_ctl, work.work);
 
 	block_group = peek_discard_list(discard_ctl, &discard_state,
-					&discard_index);
+					&discard_index, now);
 	if (!block_group || !btrfs_run_discard_work(discard_ctl))
 		return;
+	if (now < block_group->discard_eligible_time) {
+		btrfs_discard_schedule_work(discard_ctl, false);
+		return;
+	}
 
 	/* Perform discarding */
 	minlen = discard_minlen[discard_index];
@@ -474,13 +481,6 @@ static void btrfs_discard_workfn(struct work_struct *work)
 		discard_ctl->discard_extent_bytes += trimmed;
 	}
 
-	/*
-	 * Updated without locks as this is inside the workfn and nothing else
-	 * is reading the values
-	 */
-	discard_ctl->prev_discard = trimmed;
-	discard_ctl->prev_discard_time = ktime_get_ns();
-
 	/* Determine next steps for a block_group */
 	if (block_group->discard_cursor >= btrfs_block_group_end(block_group)) {
 		if (discard_state == BTRFS_DISCARD_BITMAPS) {
@@ -496,11 +496,13 @@ static void btrfs_discard_workfn(struct work_struct *work)
 		}
 	}
 
+	now = ktime_get_ns();
 	spin_lock(&discard_ctl->lock);
+	discard_ctl->prev_discard = trimmed;
+	discard_ctl->prev_discard_time = now;
 	discard_ctl->block_group = NULL;
+	__btrfs_discard_schedule_work(discard_ctl, now, false);
 	spin_unlock(&discard_ctl->lock);
-
-	btrfs_discard_schedule_work(discard_ctl, false);
 }
 
 /**

fs/btrfs/disk-io.c

@@ -1729,7 +1729,7 @@ static int cleaner_kthread(void *arg)
 		 */
 		btrfs_delete_unused_bgs(fs_info);
 sleep:
-		clear_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
+		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
 		if (kthread_should_park())
 			kthread_parkme();
 		if (kthread_should_stop())
@@ -2830,6 +2830,9 @@ static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block
 		return -ENOMEM;
 	btrfs_init_delayed_root(fs_info->delayed_root);
 
+	if (sb_rdonly(sb))
+		set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);
+
 	return btrfs_alloc_stripe_hash_table(fs_info);
 }
 
@@ -2969,6 +2972,7 @@ int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
 		}
 	}
 
+	ret = btrfs_find_orphan_roots(fs_info);
 out:
 	return ret;
 }
@@ -3383,10 +3387,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		}
 	}
 
-	ret = btrfs_find_orphan_roots(fs_info);
-	if (ret)
-		goto fail_qgroup;
-
 	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
 	if (IS_ERR(fs_info->fs_root)) {
 		err = PTR_ERR(fs_info->fs_root);
@@ -4181,6 +4181,9 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	/* We shouldn't have any transaction open at this point */
+	ASSERT(list_empty(&fs_info->trans_list));
+
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, true);
 	btrfs_free_fs_roots(fs_info);

fs/btrfs/extent-tree.c

@@ -844,6 +844,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 	want = extent_ref_type(parent, owner);
 	if (insert) {
 		extra_size = btrfs_extent_inline_ref_size(want);
+		path->search_for_extension = 1;
 		path->keep_locks = 1;
 	} else
 		extra_size = -1;
@@ -996,6 +997,7 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 out:
 	if (insert) {
 		path->keep_locks = 0;
+		path->search_for_extension = 0;
 		btrfs_unlock_up_safe(path, 1);
 	}
 	return err;

fs/btrfs/file-item.c

@@ -1016,8 +1016,10 @@ int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 	}
 
 	btrfs_release_path(path);
+	path->search_for_extension = 1;
 	ret = btrfs_search_slot(trans, root, &file_key, path,
 				csum_size, 1);
+	path->search_for_extension = 0;
 	if (ret < 0)
 		goto out;
 

fs/btrfs/inode.c

@@ -9390,7 +9390,8 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
  * some fairly slow code that needs optimization. This walks the list
  * of all the inodes with pending delalloc and forces them to disk.
  */
-static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot)
+static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot,
+				 bool in_reclaim_context)
 {
 	struct btrfs_inode *binode;
 	struct inode *inode;
@@ -9411,6 +9412,11 @@ static int start_delalloc_inodes(struct btrfs_root *root, u64 *nr, bool snapshot
 
 		list_move_tail(&binode->delalloc_inodes,
 			       &root->delalloc_inodes);
+
+		if (in_reclaim_context &&
+		    test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags))
+			continue;
+
 		inode = igrab(&binode->vfs_inode);
 		if (!inode) {
 			cond_resched_lock(&root->delalloc_lock);
@@ -9464,10 +9470,11 @@ int btrfs_start_delalloc_snapshot(struct btrfs_root *root)
 	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
 		return -EROFS;
 
-	return start_delalloc_inodes(root, &nr, true);
+	return start_delalloc_inodes(root, &nr, true, false);
 }
 
-int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
+int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			       bool in_reclaim_context)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
@@ -9490,7 +9497,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr)
 			       &fs_info->delalloc_roots);
 		spin_unlock(&fs_info->delalloc_root_lock);
 
-		ret = start_delalloc_inodes(root, &nr, false);
+		ret = start_delalloc_inodes(root, &nr, false, in_reclaim_context);
 		btrfs_put_root(root);
 		if (ret < 0)
 			goto out;

fs/btrfs/ioctl.c

@@ -4951,7 +4951,7 @@ long btrfs_ioctl(struct file *file, unsigned int
 	case BTRFS_IOC_SYNC: {
 		int ret;
 
-		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX);
+		ret = btrfs_start_delalloc_roots(fs_info, U64_MAX, false);
 		if (ret)
 			return ret;
 		ret = btrfs_sync_fs(inode->i_sb, 1);