Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "The largest set of changes here come from Miao Xie.  He's cleaning up
  and improving read recovery/repair for raid, and has a number of
  related fixes.

  I've merged another set of fsync fixes from Filipe, and he's also
  improved the way we handle metadata write errors to make sure we force
  the FS readonly if things go wrong.

  Otherwise we have a collection of fixes and cleanups.  Dave Sterba
  gets a cookie for removing the most lines (thanks Dave)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (139 commits)
  btrfs: Fix compile error when CONFIG_SECURITY is not set.
  Btrfs: fix compiles when CONFIG_BTRFS_FS_RUN_SANITY_TESTS is off
  btrfs: Make btrfs handle security mount options internally to avoid losing security label.
  Btrfs: send, don't delay dir move if there's a new parent inode
  btrfs: add more superblock checks
  Btrfs: fix race in WAIT_SYNC ioctl
  Btrfs: be aware of btree inode write errors to avoid fs corruption
  Btrfs: remove redundant btrfs_verify_qgroup_counts declaration.
  btrfs: fix shadow warning on cmp
  Btrfs: fix compilation errors under DEBUG
  Btrfs: fix crash of btrfs_release_extent_buffer_page
  Btrfs: add missing end_page_writeback on submit_extent_page failure
  btrfs: Fix the wrong condition judgment about subset extent map
  Btrfs: fix build_backref_tree issue with multiple shared blocks
  Btrfs: cleanup error handling in build_backref_tree
  btrfs: move checks for DUMMY_ROOT into a helper
  btrfs: new define for the inline extent data start
  btrfs: kill extent_buffer_page helper
  btrfs: drop constant param from btrfs_release_extent_buffer_page
  btrfs: hide typecast to definition of BTRFS_SEND_TRANS_STUB
  ...

1 files changed, 173 insertions, 111 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d0d78dc0779..fa45e3cae40 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -72,21 +72,41 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root);
 static void btrfs_error_commit_super(struct btrfs_root *root);
 
 /*
- * end_io_wq structs are used to do processing in task context when an IO is
- * complete.  This is used during reads to verify checksums, and it is used
+ * btrfs_end_io_wq structs are used to do processing in task context when an IO
+ * is complete.  This is used during reads to verify checksums, and it is used
  * by writes to insert metadata for new file extents after IO is complete.
  */
-struct end_io_wq {
+struct btrfs_end_io_wq {
 	struct bio *bio;
 	bio_end_io_t *end_io;
 	void *private;
 	struct btrfs_fs_info *info;
 	int error;
-	int metadata;
+	enum btrfs_wq_endio_type metadata;
 	struct list_head list;
 	struct btrfs_work work;
 };
 
+static struct kmem_cache *btrfs_end_io_wq_cache;
+
+int __init btrfs_end_io_wq_init(void)
+{
+	btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
+					sizeof(struct btrfs_end_io_wq),
+					0,
+					SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+					NULL);
+	if (!btrfs_end_io_wq_cache)
+		return -ENOMEM;
+	return 0;
+}
+
+void btrfs_end_io_wq_exit(void)
+{
+	if (btrfs_end_io_wq_cache)
+		kmem_cache_destroy(btrfs_end_io_wq_cache);
+}
+
 /*
  * async submit bios are used to offload expensive checksumming
  * onto the worker threads.  They checksum file and metadata bios
@@ -327,8 +347,7 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 {
 	struct extent_state *cached_state = NULL;
 	int ret;
-	bool need_lock = (current->journal_info ==
-			  (void *)BTRFS_SEND_TRANS_STUB);
+	bool need_lock = (current->journal_info == BTRFS_SEND_TRANS_STUB);
 
 	if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
 		return 0;
@@ -348,9 +367,9 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 		ret = 0;
 		goto out;
 	}
-	printk_ratelimited("parent transid verify failed on %llu wanted %llu "
-		       "found %llu\n",
-		       eb->start, parent_transid, btrfs_header_generation(eb));
+	printk_ratelimited(KERN_INFO "BTRFS (device %s): parent transid verify failed on %llu wanted %llu found %llu\n",
+			eb->fs_info->sb->s_id, eb->start,
+			parent_transid, btrfs_header_generation(eb));
 	ret = 1;
 
 	/*
@@ -607,22 +626,22 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 		goto err;
 
 	eb->read_mirror = mirror;
-	if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
+	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
 		ret = -EIO;
 		goto err;
 	}
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
+		printk_ratelimited(KERN_INFO "BTRFS (device %s): bad tree block start "
 			       "%llu %llu\n",
-			       found_start, eb->start);
+			       eb->fs_info->sb->s_id, found_start, eb->start);
 		ret = -EIO;
 		goto err;
 	}
 	if (check_tree_block_fsid(root, eb)) {
-		printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
-			       eb->start);
+		printk_ratelimited(KERN_INFO "BTRFS (device %s): bad fsid on block %llu\n",
+			       eb->fs_info->sb->s_id, eb->start);
 		ret = -EIO;
 		goto err;
 	}
@@ -680,7 +699,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 	struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
 
 	eb = (struct extent_buffer *)page->private;
-	set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
+	set_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags);
 	eb->read_mirror = failed_mirror;
 	atomic_dec(&eb->io_pages);
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
@@ -690,7 +709,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 
 static void end_workqueue_bio(struct bio *bio, int err)
 {
-	struct end_io_wq *end_io_wq = bio->bi_private;
+	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
 	struct btrfs_fs_info *fs_info;
 	struct btrfs_workqueue *wq;
 	btrfs_work_func_t func;
@@ -713,7 +732,11 @@ static void end_workqueue_bio(struct bio *bio, int err)
 			func = btrfs_endio_write_helper;
 		}
 	} else {
-		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
+		if (unlikely(end_io_wq->metadata ==
+			     BTRFS_WQ_ENDIO_DIO_REPAIR)) {
+			wq = fs_info->endio_repair_workers;
+			func = btrfs_endio_repair_helper;
+		} else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56) {
 			wq = fs_info->endio_raid56_workers;
 			func = btrfs_endio_raid56_helper;
 		} else if (end_io_wq->metadata) {
@@ -729,19 +752,12 @@ static void end_workqueue_bio(struct bio *bio, int err)
 	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
-/*
- * For the metadata arg you want
- *
- * 0 - if data
- * 1 - if normal metadta
- * 2 - if writing to the free space cache area
- * 3 - raid parity work
- */
 int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
-			int metadata)
+			enum btrfs_wq_endio_type metadata)
 {
-	struct end_io_wq *end_io_wq;
-	end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS);
+	struct btrfs_end_io_wq *end_io_wq;
+
+	end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
 	if (!end_io_wq)
 		return -ENOMEM;
 
@@ -925,7 +941,7 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
 		 * can happen in the async kernel threads
 		 */
 		ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
-					  bio, 1);
+					  bio, BTRFS_WQ_ENDIO_METADATA);
 		if (ret)
 			goto out_w_error;
 		ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
@@ -1057,20 +1073,17 @@ static const struct address_space_operations btree_aops = {
 	.set_page_dirty = btree_set_page_dirty,
 };
 
-int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
-			 u64 parent_transid)
+void readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize)
 {
 	struct extent_buffer *buf = NULL;
 	struct inode *btree_inode = root->fs_info->btree_inode;
-	int ret = 0;
 
 	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
 	if (!buf)
-		return 0;
+		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
 				 buf, 0, WAIT_NONE, btree_get_extent, 0);
 	free_extent_buffer(buf);
-	return ret;
 }
 
 int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
@@ -1106,7 +1119,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
 }
 
 struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
-					    u64 bytenr, u32 blocksize)
+					    u64 bytenr)
 {
 	return find_extent_buffer(root->fs_info, bytenr);
 }
@@ -1114,11 +1127,9 @@ struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
 struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr, u32 blocksize)
 {
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-	if (unlikely(test_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state)))
+	if (btrfs_test_is_dummy_root(root))
 		return alloc_test_extent_buffer(root->fs_info, bytenr,
 						blocksize);
-#endif
 	return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
 }
 
@@ -1136,12 +1147,12 @@ int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
 }
 
 struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
-				      u32 blocksize, u64 parent_transid)
+				      u64 parent_transid)
 {
 	struct extent_buffer *buf = NULL;
 	int ret;
 
-	buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
+	buf = btrfs_find_create_tree_block(root, bytenr, root->nodesize);
 	if (!buf)
 		return NULL;
 
@@ -1200,16 +1211,14 @@ btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
 	kfree(writers);
 }
 
-static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
-			 u32 stripesize, struct btrfs_root *root,
-			 struct btrfs_fs_info *fs_info,
+static void __setup_root(u32 nodesize, u32 sectorsize, u32 stripesize,
+			 struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 			 u64 objectid)
 {
 	root->node = NULL;
 	root->commit_root = NULL;
 	root->sectorsize = sectorsize;
 	root->nodesize = nodesize;
-	root->leafsize = leafsize;
 	root->stripesize = stripesize;
 	root->state = 0;
 	root->orphan_cleanup_state = 0;
@@ -1295,7 +1304,7 @@ struct btrfs_root *btrfs_alloc_dummy_root(void)
 	root = btrfs_alloc_root(NULL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
-	__setup_root(4096, 4096, 4096, 4096, root, NULL, 1);
+	__setup_root(4096, 4096, 4096, root, NULL, 1);
 	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
 	root->alloc_bytenr = 0;
 
@@ -1318,15 +1327,13 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, objectid);
+	__setup_root(tree_root->nodesize, tree_root->sectorsize,
+		tree_root->stripesize, root, fs_info, objectid);
 	root->root_key.objectid = objectid;
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
 	root->root_key.offset = 0;
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
-				      0, objectid, NULL, 0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		ret = PTR_ERR(leaf);
 		leaf = NULL;
@@ -1396,9 +1403,9 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	if (!root)
 		return ERR_PTR(-ENOMEM);
 
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, BTRFS_TREE_LOG_OBJECTID);
+	__setup_root(tree_root->nodesize, tree_root->sectorsize,
+		     tree_root->stripesize, root, fs_info,
+		     BTRFS_TREE_LOG_OBJECTID);
 
 	root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
 	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
@@ -1413,9 +1420,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	 * updated (along with back refs to the log tree).
 	 */
 
-	leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
-				      BTRFS_TREE_LOG_OBJECTID, NULL,
-				      0, 0, 0);
+	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
+			NULL, 0, 0, 0);
 	if (IS_ERR(leaf)) {
 		kfree(root);
 		return ERR_CAST(leaf);
@@ -1465,7 +1471,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
 	btrfs_set_stack_inode_generation(inode_item, 1);
 	btrfs_set_stack_inode_size(inode_item, 3);
 	btrfs_set_stack_inode_nlink(inode_item, 1);
-	btrfs_set_stack_inode_nbytes(inode_item, root->leafsize);
+	btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
 	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
 
 	btrfs_set_root_node(&log_root->root_item, log_root->node);
@@ -1485,7 +1491,6 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	struct btrfs_fs_info *fs_info = tree_root->fs_info;
 	struct btrfs_path *path;
 	u64 generation;
-	u32 blocksize;
 	int ret;
 
 	path = btrfs_alloc_path();
@@ -1498,9 +1503,8 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 		goto alloc_fail;
 	}
 
-	__setup_root(tree_root->nodesize, tree_root->leafsize,
-		     tree_root->sectorsize, tree_root->stripesize,
-		     root, fs_info, key->objectid);
+	__setup_root(tree_root->nodesize, tree_root->sectorsize,
+		tree_root->stripesize, root, fs_info, key->objectid);
 
 	ret = btrfs_find_root(tree_root, key, path,
 			      &root->root_item, &root->root_key);
@@ -1511,9 +1515,8 @@ static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
 	}
 
 	generation = btrfs_root_generation(&root->root_item);
-	blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
 	root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
-				     blocksize, generation);
+				     generation);
 	if (!root->node) {
 		ret = -ENOMEM;
 		goto find_fail;
@@ -1573,8 +1576,8 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 	root->subv_writers = writers;
 
 	btrfs_init_free_ino_ctl(root);
-	spin_lock_init(&root->cache_lock);
-	init_waitqueue_head(&root->cache_wait);
+	spin_lock_init(&root->ino_cache_lock);
+	init_waitqueue_head(&root->ino_cache_wait);
 
 	ret = get_anon_bdev(&root->anon_dev);
 	if (ret)
@@ -1708,10 +1711,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	return ret;
 }
 
-/*
- * If this fails, caller must call bdi_destroy() to get rid of the
- * bdi again.
- */
 static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
 	int err;
@@ -1734,16 +1733,16 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 static void end_workqueue_fn(struct btrfs_work *work)
 {
 	struct bio *bio;
-	struct end_io_wq *end_io_wq;
+	struct btrfs_end_io_wq *end_io_wq;
 	int error;
 
-	end_io_wq = container_of(work, struct end_io_wq, work);
+	end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
 	bio = end_io_wq->bio;
 
 	error = end_io_wq->error;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
-	kfree(end_io_wq);
+	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
 	bio_endio_nodec(bio, error);
 }
 
@@ -1772,6 +1771,7 @@ static int cleaner_kthread(void *arg)
 		}
 
 		btrfs_run_delayed_iputs(root);
+		btrfs_delete_unused_bgs(root->fs_info);
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -2063,6 +2063,7 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->endio_workers);
 	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
 	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
+	btrfs_destroy_workqueue(fs_info->endio_repair_workers);
 	btrfs_destroy_workqueue(fs_info->rmw_workers);
 	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
@@ -2143,8 +2144,6 @@ int open_ctree(struct super_block *sb,
 {
 	u32 sectorsize;
 	u32 nodesize;
-	u32 leafsize;
-	u32 blocksize;
 	u32 stripesize;
 	u64 generation;
 	u64 features;
@@ -2233,6 +2232,7 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->qgroup_op_lock);
 	spin_lock_init(&fs_info->buffer_lock);
+	spin_lock_init(&fs_info->unused_bgs_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
@@ -2242,6 +2242,7 @@ int open_ctree(struct super_block *sb,
 	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
 	INIT_LIST_HEAD(&fs_info->space_info);
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
+	INIT_LIST_HEAD(&fs_info->unused_bgs);
 	btrfs_mapping_init(&fs_info->mapping_tree);
 	btrfs_init_block_rsv(&fs_info->global_block_rsv,
 			     BTRFS_BLOCK_RSV_GLOBAL);
@@ -2260,7 +2261,7 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->qgroup_op_seq, 0);
 	atomic64_set(&fs_info->tree_mod_seq, 0);
 	fs_info->sb = sb;
-	fs_info->max_inline = 8192 * 1024;
+	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
 	fs_info->free_chunk_space = 0;
@@ -2389,7 +2390,7 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	__setup_root(4096, 4096, 4096, 4096, tree_root,
+	__setup_root(4096, 4096, 4096, tree_root,
 		     fs_info, BTRFS_ROOT_TREE_OBJECTID);
 
 	invalidate_bdev(fs_devices->latest_bdev);
@@ -2469,19 +2470,22 @@ int open_ctree(struct super_block *sb,
 		goto fail_alloc;
 	}
 
-	if (btrfs_super_leafsize(disk_super) !=
+	/*
+	 * Leafsize and nodesize were always equal, this is only a sanity check.
+	 */
+	if (le32_to_cpu(disk_super->__unused_leafsize) !=
 	    btrfs_super_nodesize(disk_super)) {
 		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
 		       "blocksizes don't match.  node %d leaf %d\n",
 		       btrfs_super_nodesize(disk_super),
-		       btrfs_super_leafsize(disk_super));
+		       le32_to_cpu(disk_super->__unused_leafsize));
 		err = -EINVAL;
 		goto fail_alloc;
 	}
-	if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
+	if (btrfs_super_nodesize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
 		printk(KERN_ERR "BTRFS: couldn't mount because metadata "
 		       "blocksize (%d) was too large\n",
-		       btrfs_super_leafsize(disk_super));
+		       btrfs_super_nodesize(disk_super));
 		err = -EINVAL;
 		goto fail_alloc;
 	}
@@ -2498,17 +2502,16 @@ int open_ctree(struct super_block *sb,
 	 * flag our filesystem as having big metadata blocks if
 	 * they are bigger than the page size
 	 */
-	if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
+	if (btrfs_super_nodesize(disk_super) > PAGE_CACHE_SIZE) {
 		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
 			printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
 		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
 	}
 
 	nodesize = btrfs_super_nodesize(disk_super);
-	leafsize = btrfs_super_leafsize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
 	stripesize = btrfs_super_stripesize(disk_super);
-	fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids));
+	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
 	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
 
 	/*
@@ -2516,7 +2519,7 @@ int open_ctree(struct super_block *sb,
 	 * extent buffers for the same range.  It leads to corruptions
 	 */
 	if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
-	    (sectorsize != leafsize)) {
+	    (sectorsize != nodesize)) {
 		printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
 				"are not allowed for mixed block groups on %s\n",
 				sb->s_id);
@@ -2579,6 +2582,8 @@ int open_ctree(struct super_block *sb,
 		btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
 	fs_info->endio_raid56_workers =
 		btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
+	fs_info->endio_repair_workers =
+		btrfs_alloc_workqueue("endio-repair", flags, 1, 0);
 	fs_info->rmw_workers =
 		btrfs_alloc_workqueue("rmw", flags, max_active, 2);
 	fs_info->endio_write_workers =
@@ -2600,11 +2605,12 @@ int open_ctree(struct super_block *sb,
 	      fs_info->submit_workers && fs_info->flush_workers &&
 	      fs_info->endio_workers && fs_info->endio_meta_workers &&
 	      fs_info->endio_meta_write_workers &&
+	      fs_info->endio_repair_workers &&
 	      fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
 	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
 	      fs_info->caching_workers && fs_info->readahead_workers &&
 	      fs_info->fixup_workers && fs_info->delayed_workers &&
-	      fs_info->fixup_workers && fs_info->extent_workers &&
+	      fs_info->extent_workers &&
 	      fs_info->qgroup_rescan_workers)) {
 		err = -ENOMEM;
 		goto fail_sb_buffer;
@@ -2615,7 +2621,6 @@ int open_ctree(struct super_block *sb,
 				    4 * 1024 * 1024 / PAGE_CACHE_SIZE);
 
 	tree_root->nodesize = nodesize;
-	tree_root->leafsize = leafsize;
 	tree_root->sectorsize = sectorsize;
 	tree_root->stripesize = stripesize;
 
@@ -2642,16 +2647,14 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
-	blocksize = btrfs_level_size(tree_root,
-				     btrfs_super_chunk_root_level(disk_super));
 	generation = btrfs_super_chunk_root_generation(disk_super);
 
-	__setup_root(nodesize, leafsize, sectorsize, stripesize,
-		     chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID);
+	__setup_root(nodesize, sectorsize, stripesize, chunk_root,
+		     fs_info, BTRFS_CHUNK_TREE_OBJECTID);
 
 	chunk_root->node = read_tree_block(chunk_root,
 					   btrfs_super_chunk_root(disk_super),
-					   blocksize, generation);
+					   generation);
 	if (!chunk_root->node ||
 	    !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
 		printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
@@ -2684,13 +2687,11 @@ int open_ctree(struct super_block *sb,
 	}
 
 retry_root_backup:
-	blocksize = btrfs_level_size(tree_root,
-				     btrfs_super_root_level(disk_super));
 	generation = btrfs_super_generation(disk_super);
 
 	tree_root->node = read_tree_block(tree_root,
 					  btrfs_super_root(disk_super),
-					  blocksize, generation);
+					  generation);
 	if (!tree_root->node ||
 	    !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
@@ -2859,9 +2860,6 @@ retry_root_backup:
 			err = -EIO;
 			goto fail_qgroup;
 		}
-		blocksize =
-		     btrfs_level_size(tree_root,
-				      btrfs_super_log_root_level(disk_super));
 
 		log_tree_root = btrfs_alloc_root(fs_info);
 		if (!log_tree_root) {
@@ -2869,11 +2867,10 @@ retry_root_backup:
 			goto fail_qgroup;
 		}
 
-		__setup_root(nodesize, leafsize, sectorsize, stripesize,
+		__setup_root(nodesize, sectorsize, stripesize,
 			     log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);
 
 		log_tree_root->node = read_tree_block(tree_root, bytenr,
-						      blocksize,
 						      generation + 1);
 		if (!log_tree_root->node ||
 		    !extent_buffer_uptodate(log_tree_root->node)) {
@@ -2980,6 +2977,8 @@ retry_root_backup:
 		fs_info->update_uuid_tree_gen = 1;
 	}
 
+	fs_info->open = 1;
+
 	return 0;
 
 fail_qgroup:
@@ -3139,7 +3138,8 @@ static int write_dev_supers(struct btrfs_device *device,
 
 	for (i = 0; i < max_mirrors; i++) {
 		bytenr = btrfs_sb_offset(i);
-		if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
+		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
+		    device->commit_total_bytes)
 			break;
 
 		if (wait) {
@@ -3456,8 +3456,9 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors)
 		btrfs_set_stack_device_type(dev_item, dev->type);
 		btrfs_set_stack_device_id(dev_item, dev->devid);
 		btrfs_set_stack_device_total_bytes(dev_item,
-						   dev->disk_total_bytes);
-		btrfs_set_stack_device_bytes_used(dev_item, dev->bytes_used);
+						   dev->commit_total_bytes);
+		btrfs_set_stack_device_bytes_used(dev_item,
+						  dev->commit_bytes_used);
 		btrfs_set_stack_device_io_align(dev_item, dev->io_align);
 		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
 		btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
@@ -3532,7 +3533,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 
 static void free_fs_root(struct btrfs_root *root)
 {
-	iput(root->cache_inode);
+	iput(root->ino_cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
 	btrfs_free_block_rsv(root, root->orphan_block_rsv);
 	root->orphan_block_rsv = NULL;
@@ -3623,7 +3624,7 @@ int btrfs_commit_super(struct btrfs_root *root)
 	return btrfs_commit_transaction(trans, root);
 }
 
-int close_ctree(struct btrfs_root *root)
+void close_ctree(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
@@ -3689,6 +3690,7 @@ int close_ctree(struct btrfs_root *root)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	fs_info->open = 0;
 	free_root_pointers(fs_info, 1);
 
 	iput(fs_info->btree_inode);
@@ -3711,8 +3713,6 @@ int close_ctree(struct btrfs_root *root)
 
 	btrfs_free_block_rsv(root, root->orphan_block_rsv);
 	root->orphan_block_rsv = NULL;
-
-	return 0;
 }
 
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
@@ -3814,10 +3814,73 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
 static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 			      int read_only)
 {
+	struct btrfs_super_block *sb = fs_info->super_copy;
+	int ret = 0;
+
+	if (sb->root_level > BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: tree_root level too big: %d > %d\n",
+				sb->root_level, BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+	if (sb->chunk_root_level > BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: chunk_root level too big: %d > %d\n",
+				sb->chunk_root_level, BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+	if (sb->log_root_level > BTRFS_MAX_LEVEL) {
+		printk(KERN_ERR "BTRFS: log_root level too big: %d > %d\n",
+				sb->log_root_level, BTRFS_MAX_LEVEL);
+		ret = -EINVAL;
+	}
+
 	/*
-	 * Placeholder for checks
+	 * The common minimum, we don't know if we can trust the nodesize/sectorsize
+	 * items yet, they'll be verified later. Issue just a warning.
 	 */
-	return 0;
+	if (!IS_ALIGNED(sb->root, 4096))
+		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+				sb->root);
+	if (!IS_ALIGNED(sb->chunk_root, 4096))
+		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+				sb->chunk_root);
+	if (!IS_ALIGNED(sb->log_root, 4096))
+		printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n",
+				sb->log_root);
+
+	if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) {
+		printk(KERN_ERR "BTRFS: dev_item UUID does not match fsid: %pU != %pU\n",
+				fs_info->fsid, sb->dev_item.fsid);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
+	 * done later
+	 */
+	if (sb->num_devices > (1UL << 31))
+		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
+				sb->num_devices);
+
+	if (sb->bytenr != BTRFS_SUPER_INFO_OFFSET) {
+		printk(KERN_ERR "BTRFS: super offset mismatch %llu != %u\n",
+				sb->bytenr, BTRFS_SUPER_INFO_OFFSET);
+		ret = -EINVAL;
+	}
+
+	/*
+	 * The generation is a global counter, we'll trust it more than the others
+	 * but it's still possible that it's the one that's wrong.
+	 */
+	if (sb->generation < sb->chunk_root_generation)
+		printk(KERN_WARNING
+			"BTRFS: suspicious: generation < chunk_root_generation: %llu < %llu\n",
+			sb->generation, sb->chunk_root_generation);
+	if (sb->generation < sb->cache_generation && sb->cache_generation != (u64)-1)
+		printk(KERN_WARNING
+			"BTRFS: suspicious: generation < cache_generation: %llu < %llu\n",
+			sb->generation, sb->cache_generation);
+
+	return ret;
 }
 
 static void btrfs_error_commit_super(struct btrfs_root *root)
@@ -4009,9 +4072,8 @@ static int btrfs_destroy_marked_extents(struct btrfs_root *root,
 
 		clear_extent_bits(dirty_pages, start, end, mark, GFP_NOFS);
 		while (start <= end) {
-			eb = btrfs_find_tree_block(root, start,
-						   root->leafsize);
-			start += root->leafsize;
+			eb = btrfs_find_tree_block(root, start);
+			start += root->nodesize;
 			if (!eb)
 				continue;
 			wait_on_extent_buffer_writeback(eb);