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

Pull btrfs fixes from Chris Mason:
 "We've queued up a few fixes in my for-linus branch"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: fix crash when starting transaction
  Btrfs: fix btrfs_print_leaf for skinny metadata
  Btrfs: fix race of using total_bytes_pinned
  btrfs: use E2BIG instead of EIO if compression does not help
  btrfs: remove stale comment from btrfs_flush_all_pending_stuffs
  Btrfs: fix use-after-free when cloning a trailing file hole
  btrfs: fix null pointer dereference in btrfs_show_devname when name is null
  btrfs: fix null pointer dereference in clone_fs_devices when name is null
  btrfs: fix nossd and ssd_spread mount option regression
  Btrfs: fix race between balance recovery and root deletion
  Btrfs: atomically set inode->i_flags in btrfs_update_iflags
  btrfs: only unlock block in verify_parent_transid if we locked it
  Btrfs: assert send doesn't attempt to start transactions
  btrfs compression: reuse recently used workspace
  Btrfs: fix crash when mounting raid5 btrfs with missing disks
  btrfs: create sprout should rename fsid on the sysfs as well
  btrfs: dev replace should replace the sysfs entry
  btrfs: dev add should add its sysfs entry
  btrfs: dev delete should remove sysfs entry
  btrfs: rename add_device_membership to btrfs_kobj_add_device

13 files changed, 108 insertions, 47 deletions

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 92371c4..1daea0b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -821,7 +821,7 @@ static void free_workspace(int type, struct list_head *workspace)
 
 	spin_lock(workspace_lock);
 	if (*num_workspace < num_online_cpus()) {
-		list_add_tail(workspace, idle_workspace);
+		list_add(workspace, idle_workspace);
 		(*num_workspace)++;
 		spin_unlock(workspace_lock);
 		goto wake;
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 2af6e66..eea26e1 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -36,6 +36,7 @@
 #include "check-integrity.h"
 #include "rcu-string.h"
 #include "dev-replace.h"
+#include "sysfs.h"
 
 static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 				       int scrub_ret);
@@ -562,6 +563,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 
+	/* replace the sysfs entry */
+	btrfs_kobj_rm_device(fs_info, src_device);
+	btrfs_kobj_add_device(fs_info, tgt_device);
+
 	btrfs_rm_dev_replace_blocked(fs_info);
 
 	btrfs_rm_dev_replace_srcdev(fs_info, src_device);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8bb4aa1..08e65e9 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -369,7 +369,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree,
 out:
 	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
 			     &cached_state, GFP_NOFS);
-	btrfs_tree_read_unlock_blocking(eb);
+	if (need_lock)
+		btrfs_tree_read_unlock_blocking(eb);
 	return ret;
 }
 
@@ -2904,7 +2905,9 @@ retry_root_backup:
 		if (ret)
 			goto fail_qgroup;
 
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(tree_root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret < 0) {
 			printk(KERN_WARNING
 			       "BTRFS: failed to recover relocation\n");
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 99c2539..813537f 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5678,7 +5678,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 	struct btrfs_caching_control *next;
 	struct btrfs_caching_control *caching_ctl;
 	struct btrfs_block_group_cache *cache;
-	struct btrfs_space_info *space_info;
 
 	down_write(&fs_info->commit_root_sem);
 
@@ -5701,9 +5700,6 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
 
 	up_write(&fs_info->commit_root_sem);
 
-	list_for_each_entry_rcu(space_info, &fs_info->space_info, list)
-		percpu_counter_set(&space_info->total_bytes_pinned, 0);
-
 	update_global_block_rsv(fs_info);
 }
 
@@ -5741,6 +5737,7 @@ static int unpin_extent_range(struct btrfs_root *root, u64 start, u64 end)
 		spin_lock(&cache->lock);
 		cache->pinned -= len;
 		space_info->bytes_pinned -= len;
+		percpu_counter_add(&space_info->total_bytes_pinned, -len);
 		if (cache->ro) {
 			space_info->bytes_readonly += len;
 			readonly = true;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0d321c2..47aceb4 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -136,19 +136,22 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
 void btrfs_update_iflags(struct inode *inode)
 {
 	struct btrfs_inode *ip = BTRFS_I(inode);
-
-	inode->i_flags &= ~(S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
+	unsigned int new_fl = 0;
 
 	if (ip->flags & BTRFS_INODE_SYNC)
-		inode->i_flags |= S_SYNC;
+		new_fl |= S_SYNC;
 	if (ip->flags & BTRFS_INODE_IMMUTABLE)
-		inode->i_flags |= S_IMMUTABLE;
+		new_fl |= S_IMMUTABLE;
 	if (ip->flags & BTRFS_INODE_APPEND)
-		inode->i_flags |= S_APPEND;
+		new_fl |= S_APPEND;
 	if (ip->flags & BTRFS_INODE_NOATIME)
-		inode->i_flags |= S_NOATIME;
+		new_fl |= S_NOATIME;
 	if (ip->flags & BTRFS_INODE_DIRSYNC)
-		inode->i_flags |= S_DIRSYNC;
+		new_fl |= S_DIRSYNC;
+
+	set_mask_bits(&inode->i_flags,
+		      S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC,
+		      new_fl);
 }
 
 /*
@@ -3139,7 +3142,6 @@ out:
 static void clone_update_extent_map(struct inode *inode,
 				    const struct btrfs_trans_handle *trans,
 				    const struct btrfs_path *path,
-				    struct btrfs_file_extent_item *fi,
 				    const u64 hole_offset,
 				    const u64 hole_len)
 {
@@ -3154,7 +3156,11 @@ static void clone_update_extent_map(struct inode *inode,
 		return;
 	}
 
-	if (fi) {
+	if (path) {
+		struct btrfs_file_extent_item *fi;
+
+		fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
+				    struct btrfs_file_extent_item);
 		btrfs_extent_item_to_extent_map(inode, path, fi, false, em);
 		em->generation = -1;
 		if (btrfs_file_extent_type(path->nodes[0], fi) ==
@@ -3508,18 +3514,15 @@ process_slot:
 					    btrfs_item_ptr_offset(leaf, slot),
 					    size);
 				inode_add_bytes(inode, datal);
-				extent = btrfs_item_ptr(leaf, slot,
-						struct btrfs_file_extent_item);
 			}
 
 			/* If we have an implicit hole (NO_HOLES feature). */
 			if (drop_start < new_key.offset)
 				clone_update_extent_map(inode, trans,
-						path, NULL, drop_start,
+						NULL, drop_start,
 						new_key.offset - drop_start);
 
-			clone_update_extent_map(inode, trans, path,
-						extent, 0, 0);
+			clone_update_extent_map(inode, trans, path, 0, 0);
 
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
@@ -3562,12 +3565,10 @@ process_slot:
 			btrfs_end_transaction(trans, root);
 			goto out;
 		}
+		clone_update_extent_map(inode, trans, NULL, last_dest_end,
+					destoff + len - last_dest_end);
 		ret = clone_finish_inode_update(trans, inode, destoff + len,
 						destoff, olen);
-		if (ret)
-			goto out;
-		clone_update_extent_map(inode, trans, path, NULL, last_dest_end,
-					destoff + len - last_dest_end);
 	}
 
 out:
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 6efd70d..9626b4a 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -54,7 +54,7 @@ static void print_extent_data_ref(struct extent_buffer *eb,
 	       btrfs_extent_data_ref_count(eb, ref));
 }
 
-static void print_extent_item(struct extent_buffer *eb, int slot)
+static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 {
 	struct btrfs_extent_item *ei;
 	struct btrfs_extent_inline_ref *iref;
@@ -63,7 +63,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot)
 	struct btrfs_disk_key key;
 	unsigned long end;
 	unsigned long ptr;
-	int type;
 	u32 item_size = btrfs_item_size_nr(eb, slot);
 	u64 flags;
 	u64 offset;
@@ -88,7 +87,8 @@ static void print_extent_item(struct extent_buffer *eb, int slot)
 	       btrfs_extent_refs(eb, ei), btrfs_extent_generation(eb, ei),
 	       flags);
 
-	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
+	if ((type == BTRFS_EXTENT_ITEM_KEY) &&
+	    flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
 		struct btrfs_tree_block_info *info;
 		info = (struct btrfs_tree_block_info *)(ei + 1);
 		btrfs_tree_block_key(eb, info, &key);
@@ -223,7 +223,8 @@ void btrfs_print_leaf(struct btrfs_root *root, struct extent_buffer *l)
 				btrfs_disk_root_refs(l, ri));
 			break;
 		case BTRFS_EXTENT_ITEM_KEY:
-			print_extent_item(l, i);
+		case BTRFS_METADATA_ITEM_KEY:
+			print_extent_item(l, i, type);
 			break;
 		case BTRFS_TREE_BLOCK_REF_KEY:
 			printk(KERN_INFO "\t\ttree block backref\n");
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 4055291..4a88f07 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1956,9 +1956,10 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 	 * pages are going to be uptodate.
 	 */
 	for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
-		if (rbio->faila == stripe ||
-		    rbio->failb == stripe)
+		if (rbio->faila == stripe || rbio->failb == stripe) {
+			atomic_inc(&rbio->bbio->error);
 			continue;
+		}
 
 		for (pagenr = 0; pagenr < nr_pages; pagenr++) {
 			struct page *p;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 4662d92..8e16bca 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -522,9 +522,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_ssd_spread:
 			btrfs_set_and_info(root, SSD_SPREAD,
 					   "use spread ssd allocation scheme");
+			btrfs_set_opt(info->mount_opt, SSD);
 			break;
 		case Opt_nossd:
-			btrfs_clear_and_info(root, NOSSD,
+			btrfs_set_and_info(root, NOSSD,
 					     "not using ssd allocation scheme");
 			btrfs_clear_opt(info->mount_opt, SSD);
 			break;
@@ -1467,7 +1468,9 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 			goto restore;
 
 		/* recover relocation */
+		mutex_lock(&fs_info->cleaner_mutex);
 		ret = btrfs_recover_relocation(root);
+		mutex_unlock(&fs_info->cleaner_mutex);
 		if (ret)
 			goto restore;
 
@@ -1808,6 +1811,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 		list_for_each_entry(dev, head, dev_list) {
 			if (dev->missing)
 				continue;
+			if (!dev->name)
+				continue;
 			if (!first_dev || dev->devid < first_dev->devid)
 				first_dev = dev;
 		}
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index df39458..7869936 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -605,14 +605,37 @@ static void init_feature_attrs(void)
 	}
 }
 
-static int add_device_membership(struct btrfs_fs_info *fs_info)
+int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device)
+{
+	struct hd_struct *disk;
+	struct kobject *disk_kobj;
+
+	if (!fs_info->device_dir_kobj)
+		return -EINVAL;
+
+	if (one_device) {
+		disk = one_device->bdev->bd_part;
+		disk_kobj = &part_to_dev(disk)->kobj;
+
+		sysfs_remove_link(fs_info->device_dir_kobj,
+						disk_kobj->name);
+	}
+
+	return 0;
+}
+
+int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device)
 {
 	int error = 0;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *dev;
 
-	fs_info->device_dir_kobj = kobject_create_and_add("devices",
+	if (!fs_info->device_dir_kobj)
+		fs_info->device_dir_kobj = kobject_create_and_add("devices",
 						&fs_info->super_kobj);
+
 	if (!fs_info->device_dir_kobj)
 		return -ENOMEM;
 
@@ -623,6 +646,9 @@ static int add_device_membership(struct btrfs_fs_info *fs_info)
 		if (!dev->bdev)
 			continue;
 
+		if (one_device && one_device != dev)
+			continue;
+
 		disk = dev->bdev->bd_part;
 		disk_kobj = &part_to_dev(disk)->kobj;
 
@@ -666,7 +692,7 @@ int btrfs_sysfs_add_one(struct btrfs_fs_info *fs_info)
 	if (error)
 		goto failure;
 
-	error = add_device_membership(fs_info);
+	error = btrfs_kobj_add_device(fs_info, NULL);
 	if (error)
 		goto failure;
 
diff --git a/fs/btrfs/sysfs.h b/fs/btrfs/sysfs.h
index 9ab5763..ac46df3 100644
--- a/fs/btrfs/sysfs.h
+++ b/fs/btrfs/sysfs.h
@@ -66,4 +66,8 @@ char *btrfs_printable_features(enum btrfs_feature_set set, u64 flags);
 extern const char * const btrfs_feature_set_names[3];
 extern struct kobj_type space_info_ktype;
 extern struct kobj_type btrfs_raid_ktype;
+int btrfs_kobj_add_device(struct btrfs_fs_info *fs_info,
+		struct btrfs_device *one_device);
+int btrfs_kobj_rm_device(struct btrfs_fs_info *fs_info,
+                struct btrfs_device *one_device);
 #endif /* _BTRFS_SYSFS_H_ */
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 511839c..5f379af 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -386,11 +386,13 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type,
 	bool reloc_reserved = false;
 	int ret;
 
+	/* Send isn't supposed to start transactions. */
+	ASSERT(current->journal_info != (void *)BTRFS_SEND_TRANS_STUB);
+
 	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state))
 		return ERR_PTR(-EROFS);
 
-	if (current->journal_info &&
-	    current->journal_info != (void *)BTRFS_SEND_TRANS_STUB) {
+	if (current->journal_info) {
 		WARN_ON(type & TRANS_EXTWRITERS);
 		h = current->journal_info;
 		h->use_count++;
@@ -491,6 +493,7 @@ again:
 	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_BLOCKED &&
 	    may_wait_transaction(root, type)) {
+		current->journal_info = h;
 		btrfs_commit_transaction(h, root);
 		goto again;
 	}
@@ -1615,11 +1618,6 @@ static int btrfs_flush_all_pending_stuffs(struct btrfs_trans_handle *trans,
 	int ret;
 
 	ret = btrfs_run_delayed_items(trans, root);
-	/*
-	 * running the delayed items may have added new refs. account
-	 * them now so that they hinder processing of more delayed refs
-	 * as little as possible.
-	 */
 	if (ret)
 		return ret;
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c83b242..6104676 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -40,6 +40,7 @@
 #include "rcu-string.h"
 #include "math.h"
 #include "dev-replace.h"
+#include "sysfs.h"
 
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
@@ -554,12 +555,14 @@ static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
 		 * This is ok to do without rcu read locked because we hold the
 		 * uuid mutex so nothing we touch in here is going to disappear.
 		 */
-		name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
-		if (!name) {
-			kfree(device);
-			goto error;
+		if (orig_dev->name) {
+			name = rcu_string_strdup(orig_dev->name->str, GFP_NOFS);
+			if (!name) {
+				kfree(device);
+				goto error;
+			}
+			rcu_assign_pointer(device->name, name);
 		}
-		rcu_assign_pointer(device->name, name);
 
 		list_add(&device->dev_list, &fs_devices->devices);
 		device->fs_devices = fs_devices;
@@ -1680,6 +1683,9 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path)
 	if (device->bdev)
 		device->fs_devices->open_devices--;
 
+	/* remove sysfs entry */
+	btrfs_kobj_rm_device(root->fs_info, device);
+
 	call_rcu(&device->rcu, free_device);
 
 	num_devices = btrfs_super_num_devices(root->fs_info->super_copy) - 1;
@@ -2143,9 +2149,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 	total_bytes = btrfs_super_num_devices(root->fs_info->super_copy);
 	btrfs_set_super_num_devices(root->fs_info->super_copy,
 				    total_bytes + 1);
+
+	/* add sysfs device entry */
+	btrfs_kobj_add_device(root->fs_info, device);
+
 	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
+		char fsid_buf[BTRFS_UUID_UNPARSED_SIZE];
 		ret = init_first_rw_device(trans, root, device);
 		if (ret) {
 			btrfs_abort_transaction(trans, root, ret);
@@ -2156,6 +2167,14 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path)
 			btrfs_abort_transaction(trans, root, ret);
 			goto error_trans;
 		}
+
+		/* Sprouting would change fsid of the mounted root,
+		 * so rename the fsid on the sysfs
+		 */
+		snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
+						root->fs_info->fsid);
+		if (kobject_rename(&root->fs_info->super_kobj, fsid_buf))
+			goto error_trans;
 	} else {
 		ret = btrfs_add_device(trans, root, device);
 		if (ret) {
@@ -2205,6 +2224,7 @@ error_trans:
 	unlock_chunks(root);
 	btrfs_end_transaction(trans, root);
 	rcu_string_free(device->name);
+	btrfs_kobj_rm_device(root->fs_info, device);
 	kfree(device);
 error:
 	blkdev_put(bdev, FMODE_EXCL);
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index 4f19631..b67d8fc 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -136,7 +136,7 @@ static int zlib_compress_pages(struct list_head *ws,
 		if (workspace->def_strm.total_in > 8192 &&
 		    workspace->def_strm.total_in <
 		    workspace->def_strm.total_out) {
-			ret = -EIO;
+			ret = -E2BIG;
 			goto out;
 		}
 		/* we need another page for writing out.  Test this