1 files changed, 132 insertions, 79 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d10c7be10f3b..abf86b202b43 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -358,16 +358,14 @@ static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
 	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
 
 	shash->tfm = fs_info->csum_shash;
-	crypto_shash_init(shash);
 
 	/*
 	 * The super_block structure does not span the whole
 	 * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is
 	 * filled with zeros and is included in the checksum.
 	 */
-	crypto_shash_update(shash, raw_disk_sb + BTRFS_CSUM_SIZE,
-			    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
-	crypto_shash_final(shash, result);
+	crypto_shash_digest(shash, raw_disk_sb + BTRFS_CSUM_SIZE,
+			    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result);
 
 	if (memcmp(disk_sb->csum, result, btrfs_super_csum_size(disk_sb)))
 		return 1;
@@ -709,9 +707,7 @@ static void end_workqueue_bio(struct bio *bio)
 		else
 			wq = fs_info->endio_write_workers;
 	} else {
-		if (unlikely(end_io_wq->metadata == BTRFS_WQ_ENDIO_DIO_REPAIR))
-			wq = fs_info->endio_repair_workers;
-		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
+		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
 			wq = fs_info->endio_raid56_workers;
 		else if (end_io_wq->metadata)
 			wq = fs_info->endio_meta_workers;
@@ -980,9 +976,7 @@ static void btree_invalidatepage(struct page *page, unsigned int offset,
 		btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
 			   "page private not zero on page %llu",
 			   (unsigned long long)page_offset(page));
-		ClearPagePrivate(page);
-		set_page_private(page, 0);
-		put_page(page);
+		detach_page_private(page);
 	}
 }
 
@@ -1122,6 +1116,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	mutex_init(&root->log_mutex);
 	mutex_init(&root->ordered_extent_mutex);
 	mutex_init(&root->delalloc_mutex);
+	init_waitqueue_head(&root->qgroup_flush_wait);
 	init_waitqueue_head(&root->log_writer_wait);
 	init_waitqueue_head(&root->log_commit_wait[0]);
 	init_waitqueue_head(&root->log_commit_wait[1]);
@@ -1137,17 +1132,16 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->log_transid = 0;
 	root->log_transid_committed = -1;
 	root->last_log_commit = 0;
-	if (!dummy)
+	if (!dummy) {
 		extent_io_tree_init(fs_info, &root->dirty_log_pages,
 				    IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL);
+		extent_io_tree_init(fs_info, &root->log_csum_range,
+				    IO_TREE_LOG_CSUM_RANGE, NULL);
+	}
 
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
 	memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
-	if (!dummy)
-		root->defrag_trans_start = fs_info->generation;
-	else
-		root->defrag_trans_start = 0;
 	root->root_key.objectid = objectid;
 	root->anon_dev = 0;
 
@@ -1277,12 +1271,13 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 	root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
 
 	/*
-	 * DON'T set REF_COWS for log trees
+	 * DON'T set SHAREABLE bit for log trees.
 	 *
-	 * log trees do not get reference counted because they go away
-	 * before a real commit is actually done.  They do store pointers
-	 * to file data extents, and those reference counts still get
-	 * updated (along with back refs to the log tree).
+	 * Log trees are not exposed to user space thus can't be snapshotted,
+	 * and they go away before a real commit is actually done.
+	 *
+	 * They do store pointers to file data extents, and those reference
+	 * counts still get updated (along with back refs to the log tree).
 	 */
 
 	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
@@ -1397,7 +1392,12 @@ alloc_fail:
 	goto out;
 }
 
-static int btrfs_init_fs_root(struct btrfs_root *root)
+/*
+ * Initialize subvolume root in-memory structure
+ *
+ * @anon_dev:	anonymous device to attach to the root, if zero, allocate new
+ */
+static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
 {
 	int ret;
 	unsigned int nofs_flag;
@@ -1420,8 +1420,9 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
 	if (ret)
 		goto fail;
 
-	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
-		set_bit(BTRFS_ROOT_REF_COWS, &root->state);
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
+	    root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) {
+		set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
 		btrfs_check_and_init_root_item(&root->root_item);
 	}
 
@@ -1429,9 +1430,20 @@ static int btrfs_init_fs_root(struct btrfs_root *root)
 	spin_lock_init(&root->ino_cache_lock);
 	init_waitqueue_head(&root->ino_cache_wait);
 
-	ret = get_anon_bdev(&root->anon_dev);
-	if (ret)
-		goto fail;
+	/*
+	 * Don't assign anonymous block device to roots that are not exposed to
+	 * userspace, the id pool is limited to 1M
+	 */
+	if (is_fstree(root->root_key.objectid) &&
+	    btrfs_root_refs(&root->root_item) > 0) {
+		if (!anon_dev) {
+			ret = get_anon_bdev(&root->anon_dev);
+			if (ret)
+				goto fail;
+		} else {
+			root->anon_dev = anon_dev;
+		}
+	}
 
 	mutex_lock(&root->objectid_mutex);
 	ret = btrfs_find_highest_objectid(root,
@@ -1526,6 +1538,7 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 	btrfs_put_root(fs_info->uuid_root);
 	btrfs_put_root(fs_info->free_space_root);
 	btrfs_put_root(fs_info->fs_root);
+	btrfs_put_root(fs_info->data_reloc_root);
 	btrfs_check_leaked_roots(fs_info);
 	btrfs_extent_buffer_leak_debug_check(fs_info);
 	kfree(fs_info->super_copy);
@@ -1534,37 +1547,57 @@ void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
 }
 
 
-struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
-				     struct btrfs_key *location,
-				     bool check_ref)
+/*
+ * Get an in-memory reference of a root structure.
+ *
+ * For essential trees like root/extent tree, we grab it from fs_info directly.
+ * For subvolume trees, we check the cached filesystem roots first. If not
+ * found, then read it from disk and add it to cached fs roots.
+ *
+ * Caller should release the root by calling btrfs_put_root() after the usage.
+ *
+ * NOTE: Reloc and log trees can't be read by this function as they share the
+ *	 same root objectid.
+ *
+ * @objectid:	root id
+ * @anon_dev:	preallocated anonymous block device number for new roots,
+ * 		pass 0 for new allocation.
+ * @check_ref:	whether to check root item references, If true, return -ENOENT
+ *		for orphan roots
+ */
+static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
+					     u64 objectid, dev_t anon_dev,
+					     bool check_ref)
 {
 	struct btrfs_root *root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	int ret;
 
-	if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
+	if (objectid == BTRFS_ROOT_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->tree_root);
-	if (location->objectid == BTRFS_EXTENT_TREE_OBJECTID)
+	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->extent_root);
-	if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID)
+	if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->chunk_root);
-	if (location->objectid == BTRFS_DEV_TREE_OBJECTID)
+	if (objectid == BTRFS_DEV_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->dev_root);
-	if (location->objectid == BTRFS_CSUM_TREE_OBJECTID)
+	if (objectid == BTRFS_CSUM_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->csum_root);
-	if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID)
+	if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->quota_root) ?
 			fs_info->quota_root : ERR_PTR(-ENOENT);
-	if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
+	if (objectid == BTRFS_UUID_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->uuid_root) ?
 			fs_info->uuid_root : ERR_PTR(-ENOENT);
-	if (location->objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
+	if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID)
 		return btrfs_grab_root(fs_info->free_space_root) ?
 			fs_info->free_space_root : ERR_PTR(-ENOENT);
 again:
-	root = btrfs_lookup_fs_root(fs_info, location->objectid);
+	root = btrfs_lookup_fs_root(fs_info, objectid);
 	if (root) {
+		/* Shouldn't get preallocated anon_dev for cached roots */
+		ASSERT(!anon_dev);
 		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
 			btrfs_put_root(root);
 			return ERR_PTR(-ENOENT);
@@ -1572,7 +1605,10 @@ again:
 		return root;
 	}
 
-	root = btrfs_read_tree_root(fs_info->tree_root, location);
+	key.objectid = objectid;
+	key.type = BTRFS_ROOT_ITEM_KEY;
+	key.offset = (u64)-1;
+	root = btrfs_read_tree_root(fs_info->tree_root, &key);
 	if (IS_ERR(root))
 		return root;
 
@@ -1581,7 +1617,7 @@ again:
 		goto fail;
 	}
 
-	ret = btrfs_init_fs_root(root);
+	ret = btrfs_init_fs_root(root, anon_dev);
 	if (ret)
 		goto fail;
 
@@ -1592,7 +1628,7 @@ again:
 	}
 	key.objectid = BTRFS_ORPHAN_OBJECTID;
 	key.type = BTRFS_ORPHAN_ITEM_KEY;
-	key.offset = location->objectid;
+	key.offset = objectid;
 
 	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
 	btrfs_free_path(path);
@@ -1614,25 +1650,31 @@ fail:
 	return ERR_PTR(ret);
 }
 
-static int btrfs_congested_fn(void *congested_data, int bdi_bits)
+/*
+ * Get in-memory reference of a root structure
+ *
+ * @objectid:	tree objectid
+ * @check_ref:	if set, verify that the tree exists and the item has at least
+ *		one reference
+ */
+struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
+				     u64 objectid, bool check_ref)
 {
-	struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
-	int ret = 0;
-	struct btrfs_device *device;
-	struct backing_dev_info *bdi;
+	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
+}
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
-		if (!device->bdev)
-			continue;
-		bdi = device->bdev->bd_bdi;
-		if (bdi_congested(bdi, bdi_bits)) {
-			ret = 1;
-			break;
-		}
-	}
-	rcu_read_unlock();
-	return ret;
+/*
+ * Get in-memory reference of a root structure, created as new, optionally pass
+ * the anonymous block device id
+ *
+ * @objectid:	tree objectid
+ * @anon_dev:	if zero, allocate a new anonymous block device or use the
+ *		parameter value
+ */
+struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
+					 u64 objectid, dev_t anon_dev)
+{
+	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
 }
 
 /*
@@ -1747,7 +1789,6 @@ static int transaction_kthread(void *arg)
 
 		now = ktime_get_seconds();
 		if (cur->state < TRANS_STATE_COMMIT_START &&
-		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
 		     now - cur->start_time < fs_info->commit_interval)) {
 			spin_unlock(&fs_info->trans_lock);
@@ -1942,7 +1983,6 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->workers);
 	btrfs_destroy_workqueue(fs_info->endio_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_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
@@ -1983,6 +2023,7 @@ static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
 	free_root_extent_buffers(info->quota_root);
 	free_root_extent_buffers(info->uuid_root);
 	free_root_extent_buffers(info->fs_root);
+	free_root_extent_buffers(info->data_reloc_root);
 	if (free_chunk_root)
 		free_root_extent_buffers(info->chunk_root);
 	free_root_extent_buffers(info->free_space_root);
@@ -1995,11 +2036,11 @@ void btrfs_put_root(struct btrfs_root *root)
 
 	if (refcount_dec_and_test(&root->refs)) {
 		WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
+		WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
 		if (root->anon_dev)
 			free_anon_bdev(root->anon_dev);
 		btrfs_drew_lock_destroy(&root->snapshot_lock);
-		free_extent_buffer(root->node);
-		free_extent_buffer(root->commit_root);
+		free_root_extent_buffers(root);
 		kfree(root->free_ino_ctl);
 		kfree(root->free_ino_pinned);
 #ifdef CONFIG_BTRFS_DEBUG
@@ -2145,8 +2186,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 	fs_info->endio_raid56_workers =
 		btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
 				      max_active, 4);
-	fs_info->endio_repair_workers =
-		btrfs_alloc_workqueue(fs_info, "endio-repair", flags, 1, 0);
 	fs_info->rmw_workers =
 		btrfs_alloc_workqueue(fs_info, "rmw", flags, max_active, 2);
 	fs_info->endio_write_workers =
@@ -2170,7 +2209,6 @@ static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info,
 	      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 &&
@@ -2292,6 +2330,19 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
 	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
 	fs_info->csum_root = root;
 
+	/*
+	 * This tree can share blocks with some other fs tree during relocation
+	 * and we need a proper setup by btrfs_get_fs_root
+	 */
+	root = btrfs_get_fs_root(tree_root->fs_info,
+				 BTRFS_DATA_RELOC_TREE_OBJECTID, true);
+	if (IS_ERR(root)) {
+		ret = PTR_ERR(root);
+		goto out;
+	}
+	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
+	fs_info->data_reloc_root = root;
+
 	location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
 	root = btrfs_read_tree_root(tree_root, &location);
 	if (!IS_ERR(root)) {
@@ -2580,10 +2631,12 @@ static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
 		    !extent_buffer_uptodate(tree_root->node)) {
 			handle_error = true;
 
-			if (IS_ERR(tree_root->node))
+			if (IS_ERR(tree_root->node)) {
 				ret = PTR_ERR(tree_root->node);
-			else if (!extent_buffer_uptodate(tree_root->node))
+				tree_root->node = NULL;
+			} else if (!extent_buffer_uptodate(tree_root->node)) {
 				ret = -EUCLEAN;
+			}
 
 			btrfs_warn(fs_info, "failed to read tree root");
 			continue;
@@ -2829,7 +2882,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 	u64 generation;
 	u64 features;
 	u16 csum_type;
-	struct btrfs_key location;
 	struct btrfs_super_block *disk_super;
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_root *tree_root;
@@ -3039,8 +3091,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		goto fail_sb_buffer;
 	}
 
-	sb->s_bdi->congested_fn = btrfs_congested_fn;
-	sb->s_bdi->congested_data = fs_info;
 	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
 	sb->s_bdi->ra_pages = VM_READAHEAD_PAGES;
 	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
@@ -3243,11 +3293,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device
 		}
 	}
 
-	location.objectid = BTRFS_FS_TREE_OBJECTID;
-	location.type = BTRFS_ROOT_ITEM_KEY;
-	location.offset = 0;
-
-	fs_info->fs_root = btrfs_get_fs_root(fs_info, &location, true);
+	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);
 		btrfs_warn(fs_info, "failed to read fs tree: %d", err);
@@ -3372,6 +3418,8 @@ fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
 
 fail_tree_roots:
+	if (fs_info->data_reloc_root)
+		btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root);
 	free_root_pointers(fs_info, true);
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 
@@ -3510,10 +3558,9 @@ static int write_dev_supers(struct btrfs_device *device,
 
 		btrfs_set_super_bytenr(sb, bytenr);
 
-		crypto_shash_init(shash);
-		crypto_shash_update(shash, (const char *)sb + BTRFS_CSUM_SIZE,
-				    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
-		crypto_shash_final(shash, sb->csum);
+		crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE,
+				    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE,
+				    sb->csum);
 
 		page = find_or_create_page(mapping, bytenr >> PAGE_SHIFT,
 					   GFP_NOFS);
@@ -4049,6 +4096,11 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	ASSERT(list_empty(&fs_info->delayed_iputs));
 	set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);
 
+	if (btrfs_check_quota_leak(fs_info)) {
+		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+		btrfs_err(fs_info, "qgroup reserved space leaked");
+	}
+
 	btrfs_free_qgroup_config(fs_info);
 	ASSERT(list_empty(&fs_info->delalloc_roots));
 
@@ -4501,6 +4553,7 @@ static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
 		cache->io_ctl.inode = NULL;
 		iput(inode);
 	}
+	ASSERT(cache->io_ctl.pages == NULL);
 	btrfs_put_block_group(cache);
 }