Merge branch 'd_real' of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs into work.misc

70 files changed, 1260 insertions, 957 deletions

diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 0146d911f468..631f1554c87b 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -66,11 +66,12 @@ static int autofs4_write(struct autofs_sb_info *sbi,
 	set_fs(KERNEL_DS);
 
 	mutex_lock(&sbi->pipe_mutex);
-	wr = __vfs_write(file, data, bytes, &file->f_pos);
-	while (bytes && wr) {
+	while (bytes) {
+		wr = __vfs_write(file, data, bytes, &file->f_pos);
+		if (wr <= 0)
+			break;
 		data += wr;
 		bytes -= wr;
-		wr = __vfs_write(file, data, bytes, &file->f_pos);
 	}
 	mutex_unlock(&sbi->pipe_mutex);
 
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index b677a6ea6001..7706c8dc5fa6 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -2645,7 +2645,7 @@ static void btrfsic_dump_tree_sub(const struct btrfsic_state *state,
 	 * This algorithm is recursive because the amount of used stack space
 	 * is very small and the max recursion depth is limited.
 	 */
-	indent_add = sprintf(buf, "%c-%llu(%s/%llu/%d)",
+	indent_add = sprintf(buf, "%c-%llu(%s/%llu/%u)",
 			     btrfsic_get_block_type(state, block),
 			     block->logical_bytenr, block->dev_state->name,
 			     block->dev_bytenr, block->mirror_num);
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 427c36b430a6..a85cf7d23309 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1373,7 +1373,8 @@ tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 
 	if (tm->op == MOD_LOG_KEY_REMOVE_WHILE_FREEING) {
 		BUG_ON(tm->slot != 0);
-		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start);
+		eb_rewin = alloc_dummy_extent_buffer(fs_info, eb->start,
+						eb->len);
 		if (!eb_rewin) {
 			btrfs_tree_read_unlock_blocking(eb);
 			free_extent_buffer(eb);
@@ -1454,7 +1455,8 @@ get_old_root(struct btrfs_root *root, u64 time_seq)
 	} else if (old_root) {
 		btrfs_tree_read_unlock(eb_root);
 		free_extent_buffer(eb_root);
-		eb = alloc_dummy_extent_buffer(root->fs_info, logical);
+		eb = alloc_dummy_extent_buffer(root->fs_info, logical,
+					root->nodesize);
 	} else {
 		btrfs_set_lock_blocking_rw(eb_root, BTRFS_READ_LOCK);
 		eb = btrfs_clone_extent_buffer(eb_root);
@@ -1552,6 +1554,7 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		       trans->transid, root->fs_info->generation);
 
 	if (!should_cow_block(trans, root, buf)) {
+		trans->dirty = true;
 		*cow_ret = buf;
 		return 0;
 	}
@@ -1783,10 +1786,12 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
 			if (!err) {
 				tmp = (struct btrfs_disk_key *)(kaddr + offset -
 							map_start);
-			} else {
+			} else if (err == 1) {
 				read_extent_buffer(eb, &unaligned,
 						   offset, sizeof(unaligned));
 				tmp = &unaligned;
+			} else {
+				return err;
 			}
 
 		} else {
@@ -2510,6 +2515,8 @@ read_block_for_search(struct btrfs_trans_handle *trans,
 		if (!btrfs_buffer_uptodate(tmp, 0, 0))
 			ret = -EIO;
 		free_extent_buffer(tmp);
+	} else {
+		ret = PTR_ERR(tmp);
 	}
 	return ret;
 }
@@ -2773,8 +2780,10 @@ again:
 			 * then we don't want to set the path blocking,
 			 * so we test it here
 			 */
-			if (!should_cow_block(trans, root, b))
+			if (!should_cow_block(trans, root, b)) {
+				trans->dirty = true;
 				goto cow_done;
+			}
 
 			/*
 			 * must have write locks on this node and the
@@ -2823,6 +2832,8 @@ cow_done:
 		}
 
 		ret = key_search(b, key, level, &prev_cmp, &slot);
+		if (ret < 0)
+			goto done;
 
 		if (level != 0) {
 			int dec = 0;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 101c3cfd3f7c..4274a7bfdaed 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2518,7 +2518,7 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
-				 unsigned long count, int wait);
+				 unsigned long count, u64 transid, int wait);
 int btrfs_lookup_data_extent(struct btrfs_root *root, u64 start, u64 len);
 int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root, u64 bytenr,
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 61561c2a3f96..d3aaabbfada0 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1606,15 +1606,23 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode)
 	return 0;
 }
 
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
-			     struct list_head *del_list)
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list)
 {
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_delayed_item *item;
 
 	delayed_node = btrfs_get_delayed_node(inode);
 	if (!delayed_node)
-		return;
+		return false;
+
+	/*
+	 * We can only do one readdir with delayed items at a time because of
+	 * item->readdir_list.
+	 */
+	inode_unlock_shared(inode);
+	inode_lock(inode);
 
 	mutex_lock(&delayed_node->mutex);
 	item = __btrfs_first_delayed_insertion_item(delayed_node);
@@ -1641,10 +1649,13 @@ void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
 	 * requeue or dequeue this delayed node.
 	 */
 	atomic_dec(&delayed_node->refs);
+
+	return true;
 }
 
-void btrfs_put_delayed_items(struct list_head *ins_list,
-			     struct list_head *del_list)
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list)
 {
 	struct btrfs_delayed_item *curr, *next;
 
@@ -1659,6 +1670,12 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
 		if (atomic_dec_and_test(&curr->refs))
 			kfree(curr);
 	}
+
+	/*
+	 * The VFS is going to do up_read(), so we need to downgrade back to a
+	 * read lock.
+	 */
+	downgrade_write(&inode->i_rwsem);
 }
 
 int btrfs_should_delete_dir_index(struct list_head *del_list,
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 0167853c84ae..2495b3d4075f 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -137,10 +137,12 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
 void btrfs_destroy_delayed_inodes(struct btrfs_root *root);
 
 /* Used for readdir() */
-void btrfs_get_delayed_items(struct inode *inode, struct list_head *ins_list,
-			     struct list_head *del_list);
-void btrfs_put_delayed_items(struct list_head *ins_list,
-			     struct list_head *del_list);
+bool btrfs_readdir_get_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list);
+void btrfs_readdir_put_delayed_items(struct inode *inode,
+				     struct list_head *ins_list,
+				     struct list_head *del_list);
 int btrfs_should_delete_dir_index(struct list_head *del_list,
 				  u64 index);
 int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6628fca9f4ed..60ce1190307b 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1098,7 +1098,7 @@ void readahead_tree_block(struct btrfs_root *root, u64 bytenr)
 	struct inode *btree_inode = root->fs_info->btree_inode;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return;
 	read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
 				 buf, 0, WAIT_NONE, btree_get_extent, 0);
@@ -1114,7 +1114,7 @@ int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
+	if (IS_ERR(buf))
 		return 0;
 
 	set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);
@@ -1147,7 +1147,8 @@ struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
 						 u64 bytenr)
 {
 	if (btrfs_test_is_dummy_root(root))
-		return alloc_test_extent_buffer(root->fs_info, bytenr);
+		return alloc_test_extent_buffer(root->fs_info, bytenr,
+				root->nodesize);
 	return alloc_extent_buffer(root->fs_info, bytenr);
 }
 
@@ -1171,8 +1172,8 @@ struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
 	int ret;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
 
 	ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
 	if (ret) {
@@ -1314,14 +1315,16 @@ static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 /* Should only be used by the testing infrastructure */
-struct btrfs_root *btrfs_alloc_dummy_root(void)
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize)
 {
 	struct btrfs_root *root;
 
 	root = btrfs_alloc_root(NULL, GFP_KERNEL);
 	if (!root)
 		return ERR_PTR(-ENOMEM);
-	__setup_root(4096, 4096, 4096, root, NULL, 1);
+	/* We don't use the stripesize in selftest, set it as sectorsize */
+	__setup_root(nodesize, sectorsize, sectorsize, root, NULL,
+			BTRFS_ROOT_TREE_OBJECTID);
 	set_bit(BTRFS_ROOT_DUMMY_ROOT, &root->state);
 	root->alloc_bytenr = 0;
 
@@ -1803,6 +1806,13 @@ static int cleaner_kthread(void *arg)
 		if (btrfs_need_cleaner_sleep(root))
 			goto sleep;
 
+		/*
+		 * Do not do anything if we might cause open_ctree() to block
+		 * before we have finished mounting the filesystem.
+		 */
+		if (!root->fs_info->open)
+			goto sleep;
+
 		if (!mutex_trylock(&root->fs_info->cleaner_mutex))
 			goto sleep;
 
@@ -2517,7 +2527,6 @@ int open_ctree(struct super_block *sb,
 	int num_backups_tried = 0;
 	int backup_index = 0;
 	int max_active;
-	bool cleaner_mutex_locked = false;
 
 	tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
 	chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info, GFP_KERNEL);
@@ -2797,7 +2806,7 @@ int open_ctree(struct super_block *sb,
 
 	nodesize = btrfs_super_nodesize(disk_super);
 	sectorsize = btrfs_super_sectorsize(disk_super);
-	stripesize = btrfs_super_stripesize(disk_super);
+	stripesize = sectorsize;
 	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
 	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));
 
@@ -2996,13 +3005,6 @@ retry_root_backup:
 		goto fail_sysfs;
 	}
 
-	/*
-	 * Hold the cleaner_mutex thread here so that we don't block
-	 * for a long time on btrfs_recover_relocation.  cleaner_kthread
-	 * will wait for us to finish mounting the filesystem.
-	 */
-	mutex_lock(&fs_info->cleaner_mutex);
-	cleaner_mutex_locked = true;
 	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
 					       "btrfs-cleaner");
 	if (IS_ERR(fs_info->cleaner_kthread))
@@ -3062,8 +3064,10 @@ retry_root_backup:
 		ret = btrfs_cleanup_fs_roots(fs_info);
 		if (ret)
 			goto fail_qgroup;
-		/* We locked cleaner_mutex before creating cleaner_kthread. */
+
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			btrfs_warn(fs_info, "failed to recover relocation: %d",
 					ret);
@@ -3071,8 +3075,6 @@ retry_root_backup:
 			goto fail_qgroup;
 		}
 	}
-	mutex_unlock(&fs_info->cleaner_mutex);
-	cleaner_mutex_locked = false;
 
 	location.objectid = BTRFS_FS_TREE_OBJECTID;
 	location.type = BTRFS_ROOT_ITEM_KEY;
@@ -3186,10 +3188,6 @@ fail_cleaner:
 	filemap_write_and_wait(fs_info->btree_inode->i_mapping);
 
 fail_sysfs:
-	if (cleaner_mutex_locked) {
-		mutex_unlock(&fs_info->cleaner_mutex);
-		cleaner_mutex_locked = false;
-	}
 	btrfs_sysfs_remove_mounted(fs_info);
 
 fail_fsdev_sysfs:
@@ -4130,6 +4128,16 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
 	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
 	 * done later
 	 */
+	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
+		btrfs_err(fs_info, "bytes_used is too small %llu",
+		       btrfs_super_bytes_used(sb));
+		ret = -EINVAL;
+	}
+	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
+		btrfs_err(fs_info, "invalid stripesize %u",
+		       btrfs_super_stripesize(sb));
+		ret = -EINVAL;
+	}
 	if (btrfs_super_num_devices(sb) > (1UL << 31))
 		printk(KERN_WARNING "BTRFS: suspicious number of devices: %llu\n",
 				btrfs_super_num_devices(sb));
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 8e79d0070bcf..acba821499a9 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -90,7 +90,7 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 void btrfs_free_fs_root(struct btrfs_root *root);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-struct btrfs_root *btrfs_alloc_dummy_root(void);
+struct btrfs_root *btrfs_alloc_dummy_root(u32 sectorsize, u32 nodesize);
 #endif
 
 /*
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a400951e8678..82b912a293ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2042,6 +2042,11 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 	struct btrfs_bio *bbio = NULL;
 
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are discarding.
+	 */
+	btrfs_bio_counter_inc_blocked(root->fs_info);
 	/* Tell the block device(s) that the sectors can be discarded */
 	ret = btrfs_map_block(root->fs_info, REQ_DISCARD,
 			      bytenr, &num_bytes, &bbio, 0);
@@ -2074,6 +2079,7 @@ int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr,
 		}
 		btrfs_put_bbio(bbio);
 	}
+	btrfs_bio_counter_dec(root->fs_info);
 
 	if (actual_bytes)
 		*actual_bytes = discarded_bytes;
@@ -2829,6 +2835,7 @@ int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
 
 struct async_delayed_refs {
 	struct btrfs_root *root;
+	u64 transid;
 	int count;
 	int error;
 	int sync;
@@ -2844,6 +2851,10 @@ static void delayed_ref_async_start(struct btrfs_work *work)
 
 	async = container_of(work, struct async_delayed_refs, work);
 
+	/* if the commit is already started, we don't need to wait here */
+	if (btrfs_transaction_blocked(async->root->fs_info))
+		goto done;
+
 	trans = btrfs_join_transaction(async->root);
 	if (IS_ERR(trans)) {
 		async->error = PTR_ERR(trans);
@@ -2855,10 +2866,15 @@ static void delayed_ref_async_start(struct btrfs_work *work)
 	 * wait on delayed refs
 	 */
 	trans->sync = true;
+
+	/* Don't bother flushing if we got into a different transaction */
+	if (trans->transid > async->transid)
+		goto end;
+
 	ret = btrfs_run_delayed_refs(trans, async->root, async->count);
 	if (ret)
 		async->error = ret;
-
+end:
 	ret = btrfs_end_transaction(trans, async->root);
 	if (ret && !async->error)
 		async->error = ret;
@@ -2870,7 +2886,7 @@ done:
 }
 
 int btrfs_async_run_delayed_refs(struct btrfs_root *root,
-				 unsigned long count, int wait)
+				 unsigned long count, u64 transid, int wait)
 {
 	struct async_delayed_refs *async;
 	int ret;
@@ -2882,6 +2898,7 @@ int btrfs_async_run_delayed_refs(struct btrfs_root *root,
 	async->root = root->fs_info->tree_root;
 	async->count = count;
 	async->error = 0;
+	async->transid = transid;
 	if (wait)
 		async->sync = 1;
 	else
@@ -8010,8 +8027,9 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	struct extent_buffer *buf;
 
 	buf = btrfs_find_create_tree_block(root, bytenr);
-	if (!buf)
-		return ERR_PTR(-ENOMEM);
+	if (IS_ERR(buf))
+		return buf;
+
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
@@ -8038,7 +8056,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
 			 buf->start + buf->len - 1, GFP_NOFS);
 	}
-	trans->blocks_used++;
+	trans->dirty = true;
 	/* this returns a buffer locked for blocking */
 	return buf;
 }
@@ -8653,8 +8671,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
 	next = btrfs_find_tree_block(root->fs_info, bytenr);
 	if (!next) {
 		next = btrfs_find_create_tree_block(root, bytenr);
-		if (!next)
-			return -ENOMEM;
+		if (IS_ERR(next))
+			return PTR_ERR(next);
+
 		btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
 					       level - 1);
 		reada = 1;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3cd57825c75f..75533adef998 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2025,9 +2025,16 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
+	/*
+	 * Avoid races with device replace and make sure our bbio has devices
+	 * associated to its stripes that don't go away while we are doing the
+	 * read repair operation.
+	 */
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_block(fs_info, WRITE, logical,
 			      &map_length, &bbio, mirror_num);
 	if (ret) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2037,6 +2044,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	dev = bbio->stripes[mirror_num-1].dev;
 	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		return -EIO;
 	}
@@ -2045,6 +2053,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 
 	if (btrfsic_submit_bio_wait(WRITE_SYNC, bio)) {
 		/* try to remap that extent elsewhere? */
+		btrfs_bio_counter_dec(fs_info);
 		bio_put(bio);
 		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
 		return -EIO;
@@ -2054,6 +2063,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
 				  btrfs_ino(inode), start,
 				  rcu_str_deref(dev->name), sector);
+	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
 	return 0;
 }
@@ -4718,16 +4728,16 @@ err:
 }
 
 struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
-						u64 start)
+						u64 start, u32 nodesize)
 {
 	unsigned long len;
 
 	if (!fs_info) {
 		/*
 		 * Calle