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

Pull btrfs fixes from Chris Mason:
 "It turns out that we had two crc bugs when running fsx-linux in a
  loop.  Many thanks to Josef, Miao Xie, and Dave Sterba for nailing it
  all down.  Miao also has a new OOM fix in this v2 pull as well.

  Ilya fixed a regression Liu Bo found in the balance ioctls for pausing
  and resuming a running balance across drives.

  Josef's orphan truncate patch fixes an obscure corruption we'd see
  during xfstests.

  Arne's patches address problems with subvolume quotas.  If the user
  destroys quota groups incorrectly the FS will refuse to mount.

  The rest are smaller fixes and plugs for memory leaks."

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (30 commits)
  Btrfs: fix repeated delalloc work allocation
  Btrfs: fix wrong max device number for single profile
  Btrfs: fix missed transaction->aborted check
  Btrfs: Add ACCESS_ONCE() to transaction->abort accesses
  Btrfs: put csums on the right ordered extent
  Btrfs: use right range to find checksum for compressed extents
  Btrfs: fix panic when recovering tree log
  Btrfs: do not allow logged extents to be merged or removed
  Btrfs: fix a regression in balance usage filter
  Btrfs: prevent qgroup destroy when there are still relations
  Btrfs: ignore orphan qgroup relations
  Btrfs: reorder locks and sanity checks in btrfs_ioctl_defrag
  Btrfs: fix unlock order in btrfs_ioctl_rm_dev
  Btrfs: fix unlock order in btrfs_ioctl_resize
  Btrfs: fix "mutually exclusive op is running" error code
  Btrfs: bring back balance pause/resume logic
  btrfs: update timestamps on truncate()
  btrfs: fix btrfs_cont_expand() freeing IS_ERR em
  Btrfs: fix a bug when llseek for delalloc bytes behind prealloc extents
  Btrfs: fix off-by-one in lseek
  ...

1 files changed, 102 insertions, 35 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 16d9e8e191e..cc93b23ca35 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -88,7 +88,7 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFLNK >> S_SHIFT]	= BTRFS_FT_SYMLINK,
 };
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_setsize(struct inode *inode, struct iattr *attr);
 static int btrfs_truncate(struct inode *inode);
 static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
 static noinline int cow_file_range(struct inode *inode,
@@ -2478,6 +2478,18 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				continue;
 			}
 			nr_truncate++;
+
+			/* 1 for the orphan item deletion. */
+			trans = btrfs_start_transaction(root, 1);
+			if (IS_ERR(trans)) {
+				ret = PTR_ERR(trans);
+				goto out;
+			}
+			ret = btrfs_orphan_add(trans, inode);
+			btrfs_end_transaction(trans, root);
+			if (ret)
+				goto out;
+
 			ret = btrfs_truncate(inode);
 		} else {
 			nr_unlink++;
@@ -3665,6 +3677,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				block_end - cur_offset, 0);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
+			em = NULL;
 			break;
 		}
 		last_byte = min(extent_map_end(em), block_end);
@@ -3748,16 +3761,27 @@ next:
 	return err;
 }
 
-static int btrfs_setsize(struct inode *inode, loff_t newsize)
+static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	loff_t oldsize = i_size_read(inode);
+	loff_t newsize = attr->ia_size;
+	int mask = attr->ia_valid;
 	int ret;
 
 	if (newsize == oldsize)
 		return 0;
 
+	/*
+	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+	 * special case where we need to update the times despite not having
+	 * these flags set.  For all other operations the VFS set these flags
+	 * explicitly if it wants a timestamp update.
+	 */
+	if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
+		inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+
 	if (newsize > oldsize) {
 		truncate_pagecache(inode, oldsize, newsize);
 		ret = btrfs_cont_expand(inode, oldsize, newsize);
@@ -3783,9 +3807,34 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
 			set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
 				&BTRFS_I(inode)->runtime_flags);
 
+		/*
+		 * 1 for the orphan item we're going to add
+		 * 1 for the orphan item deletion.
+		 */
+		trans = btrfs_start_transaction(root, 2);
+		if (IS_ERR(trans))
+			return PTR_ERR(trans);
+
+		/*
+		 * We need to do this in case we fail at _any_ point during the
+		 * actual truncate.  Once we do the truncate_setsize we could
+		 * invalidate pages which forces any outstanding ordered io to
+		 * be instantly completed which will give us extents that need
+		 * to be truncated.  If we fail to get an orphan inode down we
+		 * could have left over extents that were never meant to live,
+		 * so we need to garuntee from this point on that everything
+		 * will be consistent.
+		 */
+		ret = btrfs_orphan_add(trans, inode);
+		btrfs_end_transaction(trans, root);
+		if (ret)
+			return ret;
+
 		/* we don't support swapfiles, so vmtruncate shouldn't fail */
 		truncate_setsize(inode, newsize);
 		ret = btrfs_truncate(inode);
+		if (ret && inode->i_nlink)
+			btrfs_orphan_del(NULL, inode);
 	}
 
 	return ret;
@@ -3805,7 +3854,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
 		return err;
 
 	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
-		err = btrfs_setsize(inode, attr->ia_size);
+		err = btrfs_setsize(inode, attr);
 		if (err)
 			return err;
 	}
@@ -5572,10 +5621,13 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 		return em;
 	if (em) {
 		/*
-		 * if our em maps to a hole, there might
-		 * actually be delalloc bytes behind it
+		 * if our em maps to
+		 * -  a hole or
+		 * -  a pre-alloc extent,
+		 * there might actually be delalloc bytes behind it.
 		 */
-		if (em->block_start != EXTENT_MAP_HOLE)
+		if (em->block_start != EXTENT_MAP_HOLE &&
+		    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			return em;
 		else
 			hole_em = em;
@@ -5657,6 +5709,8 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 			 */
 			em->block_start = hole_em->block_start;
 			em->block_len = hole_len;
+			if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
+				set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		} else {
 			em->start = range_start;
 			em->len = found;
@@ -6915,11 +6969,9 @@ static int btrfs_truncate(struct inode *inode)
 
 	/*
 	 * 1 for the truncate slack space
-	 * 1 for the orphan item we're going to add
-	 * 1 for the orphan item deletion
 	 * 1 for updating the inode.
 	 */
-	trans = btrfs_start_transaction(root, 4);
+	trans = btrfs_start_transaction(root, 2);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
 		goto out;
@@ -6930,12 +6982,6 @@ static int btrfs_truncate(struct inode *inode)
 				      min_size);
 	BUG_ON(ret);
 
-	ret = btrfs_orphan_add(trans, inode);
-	if (ret) {
-		btrfs_end_transaction(trans, root);
-		goto out;
-	}
-
 	/*
 	 * setattr is responsible for setting the ordered_data_close flag,
 	 * but that is only tested during the last file release.  That
@@ -7004,12 +7050,6 @@ static int btrfs_truncate(struct inode *inode)
 		ret = btrfs_orphan_del(trans, inode);
 		if (ret)
 			err = ret;
-	} else if (ret && inode->i_nlink > 0) {
-		/*
-		 * Failed to do the truncate, remove us from the in memory
-		 * orphan list.
-		 */
-		ret = btrfs_orphan_del(NULL, inode);
 	}
 
 	if (trans) {
@@ -7531,41 +7571,61 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
  */
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 {
-	struct list_head *head = &root->fs_info->delalloc_inodes;
 	struct btrfs_inode *binode;
 	struct inode *inode;
 	struct btrfs_delalloc_work *work, *next;
 	struct list_head works;
+	struct list_head splice;
 	int ret = 0;
 
 	if (root->fs_info->sb->s_flags & MS_RDONLY)
 		return -EROFS;
 
 	INIT_LIST_HEAD(&works);
-
+	INIT_LIST_HEAD(&splice);
+again:
 	spin_lock(&root->fs_info->delalloc_lock);
-	while (!list_empty(head)) {
-		binode = list_entry(head->next, struct btrfs_inode,
+	list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+	while (!list_empty(&splice)) {
+		binode = list_entry(splice.next, struct btrfs_inode,
 				    delalloc_inodes);
+
+		list_del_init(&binode->delalloc_inodes);
+
 		inode = igrab(&binode->vfs_inode);
 		if (!inode)
-			list_del_init(&binode->delalloc_inodes);
+			continue;
+
+		list_add_tail(&binode->delalloc_inodes,
+			      &root->fs_info->delalloc_inodes);
 		spin_unlock(&root->fs_info->delalloc_lock);
-		if (inode) {
-			work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
-			if (!work) {
-				ret = -ENOMEM;
-				goto out;
-			}
-			list_add_tail(&work->list, &works);
-			btrfs_queue_worker(&root->fs_info->flush_workers,
-					   &work->work);
+
+		work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
+		if (unlikely(!work)) {
+			ret = -ENOMEM;
+			goto out;
 		}
+		list_add_tail(&work->list, &works);
+		btrfs_queue_worker(&root->fs_info->flush_workers,
+				   &work->work);
+
 		cond_resched();
 		spin_lock(&root->fs_info->delalloc_lock);
 	}
 	spin_unlock(&root->fs_info->delalloc_lock);
 
+	list_for_each_entry_safe(work, next, &works, list) {
+		list_del_init(&work->list);
+		btrfs_wait_and_free_delalloc_work(work);
+	}
+
+	spin_lock(&root->fs_info->delalloc_lock);
+	if (!list_empty(&root->fs_info->delalloc_inodes)) {
+		spin_unlock(&root->fs_info->delalloc_lock);
+		goto again;
+	}
+	spin_unlock(&root->fs_info->delalloc_lock);
+
 	/* the filemap_flush will queue IO into the worker threads, but
 	 * we have to make sure the IO is actually started and that
 	 * ordered extents get created before we return
@@ -7578,11 +7638,18 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 		    atomic_read(&root->fs_info->async_delalloc_pages) == 0));
 	}
 	atomic_dec(&root->fs_info->async_submit_draining);
+	return 0;
 out:
 	list_for_each_entry_safe(work, next, &works, list) {
 		list_del_init(&work->list);
 		btrfs_wait_and_free_delalloc_work(work);
 	}
+
+	if (!list_empty_careful(&splice)) {
+		spin_lock(&root->fs_info->delalloc_lock);
+		list_splice_tail(&splice, &root->fs_info->delalloc_inodes);
+		spin_unlock(&root->fs_info->delalloc_lock);
+	}
 	return ret;
 }