Merge tag 'for-5.1-rc2-tag' of git://git.kernel.org/pub/scm/linux/ker…

…nel/git/kdave/linux

Pull btrfs fixes from David Sterba:

 - fsync fixes: i_size for truncate vs fsync, dio vs buffered during
   snapshotting, remove complicated but incomplete assertion

 - removed excessive warnigs, misreported device stats updates

 - fix raid56 page mapping for 32bit arch

 - fixes reported by static analyzer

* tag 'for-5.1-rc2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux:
  Btrfs: fix assertion failure on fsync with NO_HOLES enabled
  btrfs: Avoid possible qgroup_rsv_size overflow in btrfs_calculate_inode_block_rsv_size
  btrfs: Fix bound checking in qgroup_trace_new_subtree_blocks
  btrfs: raid56: properly unmap parity page in finish_parity_scrub()
  btrfs: don't report readahead errors and don't update statistics
  Btrfs: fix file corruption after snapshotting due to mix of buffered/DIO writes
  btrfs: remove WARN_ON in log_dir_items
  Btrfs: fix incorrect file size after shrinking truncate and fsync

fs/btrfs/extent-tree.c

@@ -6174,7 +6174,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 	 *
 	 * This is overestimating in most cases.
 	 */
-	qgroup_rsv_size = outstanding_extents * fs_info->nodesize;
+	qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize;
 
 	spin_lock(&block_rsv->lock);
 	block_rsv->size = reserve_size;

fs/btrfs/qgroup.c

@@ -1922,8 +1922,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
 	int i;
 
 	/* Level sanity check */
-	if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL ||
-	    root_level < 0 || root_level >= BTRFS_MAX_LEVEL ||
+	if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 ||
+	    root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 ||
 	    root_level < cur_level) {
 		btrfs_err_rl(fs_info,
 			"%s: bad levels, cur_level=%d root_level=%d",

fs/btrfs/raid56.c

@@ -2430,8 +2430,9 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 			bitmap_clear(rbio->dbitmap, pagenr, 1);
 		kunmap(p);
 
-		for (stripe = 0; stripe < rbio->real_stripes; stripe++)
+		for (stripe = 0; stripe < nr_data; stripe++)
 			kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
+		kunmap(p_page);
 	}
 
 	__free_page(p_page);

fs/btrfs/transaction.c

@@ -1886,8 +1886,10 @@ static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
        }
 }
 
-static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+
 	/*
 	 * We use writeback_inodes_sb here because if we used
 	 * btrfs_start_delalloc_roots we would deadlock with fs freeze.
@@ -1897,15 +1899,50 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 	 * from already being in a transaction and our join_transaction doesn't
 	 * have to re-take the fs freeze lock.
 	 */
-	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
 		writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
+	} else {
+		struct btrfs_pending_snapshot *pending;
+		struct list_head *head = &trans->transaction->pending_snapshots;
+
+		/*
+		 * Flush dellaloc for any root that is going to be snapshotted.
+		 * This is done to avoid a corrupted version of files, in the
+		 * snapshots, that had both buffered and direct IO writes (even
+		 * if they were done sequentially) due to an unordered update of
+		 * the inode's size on disk.
+		 */
+		list_for_each_entry(pending, head, list) {
+			int ret;
+
+			ret = btrfs_start_delalloc_snapshot(pending->root);
+			if (ret)
+				return ret;
+		}
+	}
 	return 0;
 }
 
-static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
+static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans)
 {
-	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+
+	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
 		btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+	} else {
+		struct btrfs_pending_snapshot *pending;
+		struct list_head *head = &trans->transaction->pending_snapshots;
+
+		/*
+		 * Wait for any dellaloc that we started previously for the roots
+		 * that are going to be snapshotted. This is to avoid a corrupted
+		 * version of files in the snapshots that had both buffered and
+		 * direct IO writes (even if they were done sequentially).
+		 */
+		list_for_each_entry(pending, head, list)
+			btrfs_wait_ordered_extents(pending->root,
+						   U64_MAX, 0, U64_MAX);
+	}
 }
 
 int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
@@ -2023,7 +2060,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	extwriter_counter_dec(cur_trans, trans->type);
 
-	ret = btrfs_start_delalloc_flush(fs_info);
+	ret = btrfs_start_delalloc_flush(trans);
 	if (ret)
 		goto cleanup_transaction;
 
@@ -2039,7 +2076,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	if (ret)
 		goto cleanup_transaction;
 
-	btrfs_wait_delalloc_flush(fs_info);
+	btrfs_wait_delalloc_flush(trans);
 
 	btrfs_scrub_pause(fs_info);
 	/*

fs/btrfs/tree-log.c

@@ -3578,9 +3578,16 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	/* find the first key from this transaction again */
+	/*
+	 * Find the first key from this transaction again.  See the note for
+	 * log_new_dir_dentries, if we're logging a directory recursively we
+	 * won't be holding its i_mutex, which means we can modify the directory
+	 * while we're logging it.  If we remove an entry between our first
+	 * search and this search we'll not find the key again and can just
+	 * bail.
+	 */
 	ret = btrfs_search_slot(NULL, root, &min_key, path, 0, 0);
-	if (WARN_ON(ret != 0))
+	if (ret != 0)
 		goto done;
 
 	/*
@@ -4544,6 +4551,19 @@ static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
 		item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				      struct btrfs_inode_item);
 		*size_ret = btrfs_inode_size(path->nodes[0], item);
+		/*
+		 * If the in-memory inode's i_size is smaller then the inode
+		 * size stored in the btree, return the inode's i_size, so
+		 * that we get a correct inode size after replaying the log
+		 * when before a power failure we had a shrinking truncate
+		 * followed by addition of a new name (rename / new hard link).
+		 * Otherwise return the inode size from the btree, to avoid
+		 * data loss when replaying a log due to previously doing a
+		 * write that expands the inode's size and logging a new name
+		 * immediately after.
+		 */
+		if (*size_ret > inode->vfs_inode.i_size)
+			*size_ret = inode->vfs_inode.i_size;
 	}
 
 	btrfs_release_path(path);
@@ -4705,15 +4725,8 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 					struct btrfs_file_extent_item);
 
 		if (btrfs_file_extent_type(leaf, extent) ==
-		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_ram_bytes(leaf, extent);
-			ASSERT(len == i_size ||
-			       (len == fs_info->sectorsize &&
-				btrfs_file_extent_compression(leaf, extent) !=
-				BTRFS_COMPRESS_NONE) ||
-			       (len < i_size && i_size < fs_info->sectorsize));
+		    BTRFS_FILE_EXTENT_INLINE)
 			return 0;
-		}
 
 		len = btrfs_file_extent_num_bytes(leaf, extent);
 		/* Last extent goes beyond i_size, no need to log a hole. */

fs/btrfs/volumes.c

@@ -6407,7 +6407,7 @@ static void btrfs_end_bio(struct bio *bio)
 				if (bio_op(bio) == REQ_OP_WRITE)
 					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_WRITE_ERRS);
-				else
+				else if (!(bio->bi_opf & REQ_RAHEAD))
 					btrfs_dev_stat_inc_and_print(dev,
 						BTRFS_DEV_STAT_READ_ERRS);
 				if (bio->bi_opf & REQ_PREFLUSH)