Merge tag 'for-4.17-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux

Pull btrfs fixes from David Sterba:
 "We've accumulated some fixes during the last week, some of them were
  in the works for a longer time but there are some newer ones too.

  Most of the fixes have a reproducer and fix user visible problems,
  also candidates for stable kernels. They IMHO qualify for a late rc,
  though I did not expect that many"

* tag 'for-4.17-rc5-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  btrfs: fix crash when trying to resume balance without the resume flag
  btrfs: Fix delalloc inodes invalidation during transaction abort
  btrfs: Split btrfs_del_delalloc_inode into 2 functions
  btrfs: fix reading stale metadata blocks after degraded raid1 mounts
  btrfs: property: Set incompat flag if lzo/zstd compression is set
  Btrfs: fix duplicate extents after fsync of file with prealloc extents
  Btrfs: fix xattr loss after power failure
  Btrfs: send, fix invalid access to commit roots due to concurrent snapshotting

7 files changed, 180 insertions, 48 deletions

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 3fd44835b3869..8c68961925b14 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2436,10 +2436,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	if (p->reada != READA_NONE)
 		reada_for_search(fs_info, p, level, slot, key->objectid);
 
-	btrfs_release_path(p);
-
 	ret = -EAGAIN;
-	tmp = read_tree_block(fs_info, blocknr, 0, parent_level - 1,
+	tmp = read_tree_block(fs_info, blocknr, gen, parent_level - 1,
 			      &first_key);
 	if (!IS_ERR(tmp)) {
 		/*
@@ -2454,6 +2452,8 @@ read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
 	} else {
 		ret = PTR_ERR(tmp);
 	}
+
+	btrfs_release_path(p);
 	return ret;
 }
 
@@ -5414,12 +5414,24 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 	down_read(&fs_info->commit_root_sem);
 	left_level = btrfs_header_level(left_root->commit_root);
 	left_root_level = left_level;
-	left_path->nodes[left_level] = left_root->commit_root;
+	left_path->nodes[left_level] =
+			btrfs_clone_extent_buffer(left_root->commit_root);
+	if (!left_path->nodes[left_level]) {
+		up_read(&fs_info->commit_root_sem);
+		ret = -ENOMEM;
+		goto out;
+	}
 	extent_buffer_get(left_path->nodes[left_level]);
 
 	right_level = btrfs_header_level(right_root->commit_root);
 	right_root_level = right_level;
-	right_path->nodes[right_level] = right_root->commit_root;
+	right_path->nodes[right_level] =
+			btrfs_clone_extent_buffer(right_root->commit_root);
+	if (!right_path->nodes[right_level]) {
+		up_read(&fs_info->commit_root_sem);
+		ret = -ENOMEM;
+		goto out;
+	}
 	extent_buffer_get(right_path->nodes[right_level]);
 	up_read(&fs_info->commit_root_sem);
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2771cc56a622f..0d422c9908b80 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3182,6 +3182,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes);
 
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+				struct btrfs_inode *inode);
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
 int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 60caa68c3618d..c3504b4d281b5 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3818,6 +3818,7 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
 
 	btrfs_free_qgroup_config(fs_info);
+	ASSERT(list_empty(&fs_info->delalloc_roots));
 
 	if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
 		btrfs_info(fs_info, "at unmount delalloc count %lld",
@@ -4125,15 +4126,15 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
 
 static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
 {
+	/* cleanup FS via transaction */
+	btrfs_cleanup_transaction(fs_info);
+
 	mutex_lock(&fs_info->cleaner_mutex);
 	btrfs_run_delayed_iputs(fs_info);
 	mutex_unlock(&fs_info->cleaner_mutex);
 
 	down_write(&fs_info->cleanup_work_sem);
 	up_write(&fs_info->cleanup_work_sem);
-
-	/* cleanup FS via transaction */
-	btrfs_cleanup_transaction(fs_info);
 }
 
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
@@ -4258,19 +4259,23 @@ static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
 	list_splice_init(&root->delalloc_inodes, &splice);
 
 	while (!list_empty(&splice)) {
+		struct inode *inode = NULL;
 		btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
 					       delalloc_inodes);
-
-		list_del_init(&btrfs_inode->delalloc_inodes);
-		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			  &btrfs_inode->runtime_flags);
+		__btrfs_del_delalloc_inode(root, btrfs_inode);
 		spin_unlock(&root->delalloc_lock);
 
-		btrfs_invalidate_inodes(btrfs_inode->root);
-
+		/*
+		 * Make sure we get a live inode and that it'll not disappear
+		 * meanwhile.
+		 */
+		inode = igrab(&btrfs_inode->vfs_inode);
+		if (inode) {
+			invalidate_inode_pages2(inode->i_mapping);
+			iput(inode);
+		}
 		spin_lock(&root->delalloc_lock);
 	}
-
 	spin_unlock(&root->delalloc_lock);
 }
 
@@ -4286,7 +4291,6 @@ static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info)
 	while (!list_empty(&splice)) {
 		root = list_first_entry(&splice, struct btrfs_root,
 					 delalloc_root);
-		list_del_init(&root->delalloc_root);
 		root = btrfs_grab_fs_root(root);
 		BUG_ON(!root);
 		spin_unlock(&fs_info->delalloc_root_lock);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index d241285a0d2a8..8e604e7071f14 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1742,12 +1742,12 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 	spin_unlock(&root->delalloc_lock);
 }
 
-static void btrfs_del_delalloc_inode(struct btrfs_root *root,
-				     struct btrfs_inode *inode)
+
+void __btrfs_del_delalloc_inode(struct btrfs_root *root,
+				struct btrfs_inode *inode)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 
-	spin_lock(&root->delalloc_lock);
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
 		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
@@ -1760,6 +1760,13 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
 			spin_unlock(&fs_info->delalloc_root_lock);
 		}
 	}
+}
+
+static void btrfs_del_delalloc_inode(struct btrfs_root *root,
+				     struct btrfs_inode *inode)
+{
+	spin_lock(&root->delalloc_lock);
+	__btrfs_del_delalloc_inode(root, inode);
 	spin_unlock(&root->delalloc_lock);
 }
 
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index 53a8c95828e33..dc6140013ae81 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -380,6 +380,7 @@ static int prop_compression_apply(struct inode *inode,
 				  const char *value,
 				  size_t len)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int type;
 
 	if (len == 0) {
@@ -390,14 +391,17 @@ static int prop_compression_apply(struct inode *inode,
 		return 0;
 	}
 
-	if (!strncmp("lzo", value, 3))
+	if (!strncmp("lzo", value, 3)) {
 		type = BTRFS_COMPRESS_LZO;
-	else if (!strncmp("zlib", value, 4))
+		btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
+	} else if (!strncmp("zlib", value, 4)) {
 		type = BTRFS_COMPRESS_ZLIB;
-	else if (!strncmp("zstd", value, len))
+	} else if (!strncmp("zstd", value, len)) {
 		type = BTRFS_COMPRESS_ZSTD;
-	else
+		btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
+	} else {
 		return -EINVAL;
+	}
 
 	BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
 	BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 43758e30aa7a9..8f23a94dab770 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4320,6 +4320,110 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * Log all prealloc extents beyond the inode's i_size to make sure we do not
+ * lose them after doing a fast fsync and replaying the log. We scan the
+ * subvolume's root instead of iterating the inode's extent map tree because
+ * otherwise we can log incorrect extent items based on extent map conversion.
+ * That can happen due to the fact that extent maps are merged when they
+ * are not in the extent map tree's list of modified extents.
+ */
+static int btrfs_log_prealloc_extents(struct btrfs_trans_handle *trans,
+				      struct btrfs_inode *inode,
+				      struct btrfs_path *path)
+{
+	struct btrfs_root *root = inode->root;
+	struct btrfs_key key;
+	const u64 i_size = i_size_read(&inode->vfs_inode);
+	const u64 ino = btrfs_ino(inode);
+	struct btrfs_path *dst_path = NULL;
+	u64 last_extent = (u64)-1;
+	int ins_nr = 0;
+	int start_slot;
+	int ret;
+
+	if (!(inode->flags & BTRFS_INODE_PREALLOC))
+		return 0;
+
+	key.objectid = ino;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = i_size;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	while (true) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+
+		if (slot >= btrfs_header_nritems(leaf)) {
+			if (ins_nr > 0) {
+				ret = copy_items(trans, inode, dst_path, path,
+						 &last_extent, start_slot,
+						 ins_nr, 1, 0);
+				if (ret < 0)
+					goto out;
+				ins_nr = 0;
+			}
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			if (ret > 0) {
+				ret = 0;
+				break;
+			}
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid > ino)
+			break;
+		if (WARN_ON_ONCE(key.objectid < ino) ||
+		    key.type < BTRFS_EXTENT_DATA_KEY ||
+		    key.offset < i_size) {
+			path->slots[0]++;
+			continue;
+		}
+		if (last_extent == (u64)-1) {
+			last_extent = key.offset;
+			/*
+			 * Avoid logging extent items logged in past fsync calls
+			 * and leading to duplicate keys in the log tree.
+			 */
+			do {
+				ret = btrfs_truncate_inode_items(trans,
+							 root->log_root,
+							 &inode->vfs_inode,
+							 i_size,
+							 BTRFS_EXTENT_DATA_KEY);
+			} while (ret == -EAGAIN);
+			if (ret)
+				goto out;
+		}
+		if (ins_nr == 0)
+			start_slot = slot;
+		ins_nr++;
+		path->slots[0]++;
+		if (!dst_path) {
+			dst_path = btrfs_alloc_path();
+			if (!dst_path) {
+				ret = -ENOMEM;
+				goto out;
+			}
+		}
+	}
+	if (ins_nr > 0) {
+		ret = copy_items(trans, inode, dst_path, path, &last_extent,
+				 start_slot, ins_nr, 1, 0);
+		if (ret > 0)
+			ret = 0;
+	}
+out:
+	btrfs_release_path(path);
+	btrfs_free_path(dst_path);
+	return ret;
+}
+
 static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct btrfs_inode *inode,
@@ -4362,6 +4466,11 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		if (em->generation <= test_gen)
 			continue;
 
+		/* We log prealloc extents beyond eof later. */
+		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) &&
+		    em->start >= i_size_read(&inode->vfs_inode))
+			continue;
+
 		if (em->start < logged_start)
 			logged_start = em->start;
 		if ((em->start + em->len - 1) > logged_end)
@@ -4374,31 +4483,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		num++;
 	}
 
-	/*
-	 * Add all prealloc extents beyond the inode's i_size to make sure we
-	 * don't lose them after doing a fast fsync and replaying the log.
-	 */
-	if (inode->flags & BTRFS_INODE_PREALLOC) {
-		struct rb_node *node;
-
-		for (node = rb_last(&tree->map); node; node = rb_prev(node)) {
-			em = rb_entry(node, struct extent_map, rb_node);
-			if (em->start < i_size_read(&inode->vfs_inode))
-				break;
-			if (!list_empty(&em->list))
-				continue;
-			/* Same as above loop. */
-			if (++num > 32768) {
-				list_del_init(&tree->modified_extents);
-				ret = -EFBIG;
-				goto process;
-			}
-			refcount_inc(&em->refs);
-			set_bit(EXTENT_FLAG_LOGGING, &em->flags);
-			list_add_tail(&em->list, &extents);
-		}
-	}
-
 	list_sort(NULL, &extents, extent_cmp);
 	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
 	/*
@@ -4443,6 +4527,9 @@ process:
 	up_write(&inode->dio_sem);
 
 	btrfs_release_path(path);
+	if (!ret)
+		ret = btrfs_log_prealloc_extents(trans, inode, path);
+
 	return ret;
 }
 
@@ -4827,6 +4914,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 logged_isize = 0;
 	bool need_log_inode_item = true;
+	bool xattrs_logged = false;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -5128,6 +5216,7 @@ next_key:
 	err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
 	if (err)
 		goto out_unlock;
+	xattrs_logged = true;
 	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
 		btrfs_release_path(path);
 		btrfs_release_path(dst_path);
@@ -5140,6 +5229,11 @@ log_extents:
 	btrfs_release_path(dst_path);
 	if (need_log_inode_item) {
 		err = log_inode_item(trans, log, dst_path, inode);
+		if (!err && !xattrs_logged) {
+			err = btrfs_log_all_xattrs(trans, root, inode, path,
+						   dst_path);
+			btrfs_release_path(path);
+		}
 		if (err)
 			goto out_unlock;
 	}
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 292266f6ab9c9..be3fc701f3894 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4052,6 +4052,15 @@ int btrfs_resume_balance_async(struct btrfs_fs_info *fs_info)
 		return 0;
 	}
 
+	/*
+	 * A ro->rw remount sequence should continue with the paused balance
+	 * regardless of who pauses it, system or the user as of now, so set
+	 * the resume flag.
+	 */
+	spin_lock(&fs_info->balance_lock);
+	fs_info->balance_ctl->flags |= BTRFS_BALANCE_RESUME;
+	spin_unlock(&fs_info->balance_lock);
+
 	tsk = kthread_run(balance_kthread, fs_info, "btrfs-balance");
 	return PTR_ERR_OR_ZERO(tsk);
 }