Merge tag 'for-5.1-part2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "Correctness and a deadlock fixes"

* tag 'for-5.1-part2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: zstd: ensure reclaim timer is properly cleaned up
  btrfs: move ulist allocation out of transaction in quota enable
  btrfs: save drop_progress if we drop refs at all
  btrfs: check for refs on snapshot delete resume
  Btrfs: fix deadlock between clone/dedupe and rename
  Btrfs: fix corruption reading shared and compressed extents after hole punching

fs/btrfs/ctree.h

@@ -1210,6 +1210,8 @@ enum {
 	 * Set for the subvolume tree owning the reloc tree.
 	 */
 	BTRFS_ROOT_DEAD_RELOC_TREE,
+	/* Mark dead root stored on device whose cleanup needs to be resumed */
+	BTRFS_ROOT_DEAD_TREE,
 };
 
 /*

fs/btrfs/extent-tree.c

@@ -8764,6 +8764,8 @@ struct walk_control {
 	u64 refs[BTRFS_MAX_LEVEL];
 	u64 flags[BTRFS_MAX_LEVEL];
 	struct btrfs_key update_progress;
+	struct btrfs_key drop_progress;
+	int drop_level;
 	int stage;
 	int level;
 	int shared_level;
@@ -8771,6 +8773,7 @@ struct walk_control {
 	int keep_locks;
 	int reada_slot;
 	int reada_count;
+	int restarted;
 };
 
 #define DROP_REFERENCE	1
@@ -8933,6 +8936,33 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+/*
+ * This is used to verify a ref exists for this root to deal with a bug where we
+ * would have a drop_progress key that hadn't been updated properly.
+ */
+static int check_ref_exists(struct btrfs_trans_handle *trans,
+			    struct btrfs_root *root, u64 bytenr, u64 parent,
+			    int level)
+{
+	struct btrfs_path *path;
+	struct btrfs_extent_inline_ref *iref;
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = lookup_extent_backref(trans, path, &iref, bytenr,
+				    root->fs_info->nodesize, parent,
+				    root->root_key.objectid, level, 0);
+	btrfs_free_path(path);
+	if (ret == -ENOENT)
+		return 0;
+	if (ret < 0)
+		return ret;
+	return 1;
+}
+
 /*
  * helper to process tree block pointer.
  *
@@ -9087,6 +9117,23 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 			parent = 0;
 		}
 
+		/*
+		 * If we had a drop_progress we need to verify the refs are set
+		 * as expected.  If we find our ref then we know that from here
+		 * on out everything should be correct, and we can clear the
+		 * ->restarted flag.
+		 */
+		if (wc->restarted) {
+			ret = check_ref_exists(trans, root, bytenr, parent,
+					       level - 1);
+			if (ret < 0)
+				goto out_unlock;
+			if (ret == 0)
+				goto no_delete;
+			ret = 0;
+			wc->restarted = 0;
+		}
+
 		/*
 		 * Reloc tree doesn't contribute to qgroup numbers, and we have
 		 * already accounted them at merge time (replace_path),
@@ -9102,13 +9149,23 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 					     ret);
 			}
 		}
+
+		/*
+		 * We need to update the next key in our walk control so we can
+		 * update the drop_progress key accordingly.  We don't care if
+		 * find_next_key doesn't find a key because that means we're at
+		 * the end and are going to clean up now.
+		 */
+		wc->drop_level = level;
+		find_next_key(path, level, &wc->drop_progress);
+
 		ret = btrfs_free_extent(trans, root, bytenr, fs_info->nodesize,
 					parent, root->root_key.objectid,
 					level - 1, 0);
 		if (ret)
 			goto out_unlock;
 	}
-
+no_delete:
 	*lookup_info = 1;
 	ret = 1;
 
@@ -9425,6 +9482,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		}
 	}
 
+	wc->restarted = test_bit(BTRFS_ROOT_DEAD_TREE, &root->state);
 	wc->level = level;
 	wc->shared_level = -1;
 	wc->stage = DROP_REFERENCE;
@@ -9452,12 +9510,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 		}
 
 		if (wc->stage == DROP_REFERENCE) {
-			level = wc->level;
-			btrfs_node_key(path->nodes[level],
-				       &root_item->drop_progress,
-				       path->slots[level]);
-			root_item->drop_level = level;
-		}
+			wc->drop_level = wc->level;
+			btrfs_node_key_to_cpu(path->nodes[wc->drop_level],
+					      &wc->drop_progress,
+					      path->slots[wc->drop_level]);
+		}
+		btrfs_cpu_key_to_disk(&root_item->drop_progress,
+				      &wc->drop_progress);
+		root_item->drop_level = wc->drop_level;
 
 		BUG_ON(wc->level == 0);
 		if (btrfs_should_end_transaction(trans) ||

fs/btrfs/extent_io.c

@@ -2995,11 +2995,11 @@ static int __do_readpage(struct extent_io_tree *tree,
 		 */
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
 		    prev_em_start && *prev_em_start != (u64)-1 &&
-		    *prev_em_start != em->orig_start)
+		    *prev_em_start != em->start)
 			force_bio_submit = true;
 
 		if (prev_em_start)
-			*prev_em_start = em->orig_start;
+			*prev_em_start = em->start;
 
 		free_extent_map(em);
 		em = NULL;

fs/btrfs/ioctl.c

@@ -3207,21 +3207,6 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
-{
-	inode_unlock(inode1);
-	inode_unlock(inode2);
-}
-
-static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
-{
-	if (inode1 < inode2)
-		swap(inode1, inode2);
-
-	inode_lock_nested(inode1, I_MUTEX_PARENT);
-	inode_lock_nested(inode2, I_MUTEX_CHILD);
-}
-
 static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
 				       struct inode *inode2, u64 loff2, u64 len)
 {
@@ -3956,7 +3941,7 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	if (same_inode)
 		inode_lock(inode_in);
 	else
-		btrfs_double_inode_lock(inode_in, inode_out);
+		lock_two_nondirectories(inode_in, inode_out);
 
 	/* don't make the dst file partly checksummed */
 	if ((BTRFS_I(inode_in)->flags & BTRFS_INODE_NODATASUM) !=
@@ -4013,7 +3998,7 @@ static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 	if (same_inode)
 		inode_unlock(inode_in);
 	else
-		btrfs_double_inode_unlock(inode_in, inode_out);
+		unlock_two_nondirectories(inode_in, inode_out);
 
 	return ret;
 }
@@ -4043,7 +4028,7 @@ loff_t btrfs_remap_file_range(struct file *src_file, loff_t off,
 	if (same_inode)
 		inode_unlock(src_inode);
 	else
-		btrfs_double_inode_unlock(src_inode, dst_inode);
+		unlock_two_nondirectories(src_inode, dst_inode);
 
 	return ret < 0 ? ret : len;
 }

fs/btrfs/qgroup.c

@@ -894,6 +894,12 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 	if (fs_info->quota_root)
 		goto out;
 
+	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
+	if (!fs_info->qgroup_ulist) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
 	/*
 	 * 1 for quota root item
 	 * 1 for BTRFS_QGROUP_STATUS item
@@ -909,13 +915,6 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 		goto out;
 	}
 
-	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
-	if (!fs_info->qgroup_ulist) {
-		ret = -ENOMEM;
-		btrfs_abort_transaction(trans, ret);
-		goto out;
-	}
-
 	/*
 	 * initially create the quota tree
 	 */

fs/btrfs/root-tree.c

@@ -263,8 +263,10 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 		if (root) {
 			WARN_ON(!test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
 					  &root->state));
-			if (btrfs_root_refs(&root->root_item) == 0)
+			if (btrfs_root_refs(&root->root_item) == 0) {
+				set_bit(BTRFS_ROOT_DEAD_TREE, &root->state);
 				btrfs_add_dead_root(root);
+			}
 			continue;
 		}
 
@@ -310,8 +312,10 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 			break;
 		}
 
-		if (btrfs_root_refs(&root->root_item) == 0)
+		if (btrfs_root_refs(&root->root_item) == 0) {
+			set_bit(BTRFS_ROOT_DEAD_TREE, &root->state);
 			btrfs_add_dead_root(root);
+		}
 	}
 
 	btrfs_free_path(path);

fs/btrfs/zstd.c

@@ -195,8 +195,7 @@ static void zstd_cleanup_workspace_manager(void)
 	struct workspace *workspace;
 	int i;
 
-	del_timer(&wsm.timer);
-
+	spin_lock(&wsm.lock);
 	for (i = 0; i < ZSTD_BTRFS_MAX_LEVEL; i++) {
 		while (!list_empty(&wsm.idle_ws[i])) {
 			workspace = container_of(wsm.idle_ws[i].next,
@@ -206,6 +205,9 @@ static void zstd_cleanup_workspace_manager(void)
 			wsm.ops->free_workspace(&workspace->list);
 		}
 	}
+	spin_unlock(&wsm.lock);
+
+	del_timer_sync(&wsm.timer);
 }
 
 /*