Merge branch 'bug-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/josef/btrfs-work

Conflicts:
	fs/btrfs/extent-tree.c

Signed-off-by: Chris Mason <chris.mason@oracle.com>

fs/btrfs/ctree.h

@@ -698,7 +698,8 @@ struct btrfs_block_group_item {
 struct btrfs_space_info {
 	u64 flags;
 
-	u64 total_bytes;	/* total bytes in the space */
+	u64 total_bytes;	/* total bytes in the space,
+				   this doesn't take mirrors into account */
 	u64 bytes_used;		/* total bytes used,
 				   this does't take mirrors into account */
 	u64 bytes_pinned;	/* total bytes pinned, will be freed when the
@@ -710,6 +711,8 @@ struct btrfs_space_info {
 	u64 bytes_may_use;	/* number of bytes that may be used for
 				   delalloc/allocations */
 	u64 disk_used;		/* total bytes used on disk */
+	u64 disk_total;		/* total bytes on disk, takes mirrors into
+				   account */
 
 	int full;		/* indicates that we cannot allocate any more
 				   chunks for this space */
@@ -2146,7 +2149,7 @@ int btrfs_check_data_free_space(struct inode *inode, u64 bytes);
 void btrfs_free_reserved_data_space(struct inode *inode, u64 bytes);
 int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
-				int num_items, int *retries);
+				int num_items);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
@@ -2167,7 +2170,7 @@ void btrfs_add_durable_block_rsv(struct btrfs_fs_info *fs_info,
 int btrfs_block_rsv_add(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv,
-			u64 num_bytes, int *retries);
+			u64 num_bytes);
 int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root,
 			  struct btrfs_block_rsv *block_rsv,
@@ -2441,7 +2444,8 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 			       u32 min_type);
 
 int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput);
-int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput);
+int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput,
+				   int sync);
 int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 			      struct extent_state **cached_state);
 int btrfs_writepages(struct address_space *mapping,

fs/btrfs/extent-tree.c

@@ -2976,6 +2976,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 	if (found) {
 		spin_lock(&found->lock);
 		found->total_bytes += total_bytes;
+		found->disk_total += total_bytes * factor;
 		found->bytes_used += bytes_used;
 		found->disk_used += bytes_used * factor;
 		found->full = 0;
@@ -2995,6 +2996,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags,
 				BTRFS_BLOCK_GROUP_SYSTEM |
 				BTRFS_BLOCK_GROUP_METADATA);
 	found->total_bytes = total_bytes;
+	found->disk_total = total_bytes * factor;
 	found->bytes_used = bytes_used;
 	found->disk_used = bytes_used * factor;
 	found->bytes_pinned = 0;
@@ -3216,8 +3218,7 @@ static void force_metadata_allocation(struct btrfs_fs_info *info)
 	rcu_read_unlock();
 }
 
-static int should_alloc_chunk(struct btrfs_space_info *sinfo,
-			      u64 alloc_bytes)
+static int should_alloc_chunk(struct btrfs_space_info *sinfo, u64 alloc_bytes)
 {
 	u64 num_bytes = sinfo->total_bytes - sinfo->bytes_readonly;
 
@@ -3229,6 +3230,10 @@ static int should_alloc_chunk(struct btrfs_space_info *sinfo,
 	    alloc_bytes < div_factor(num_bytes, 8))
 		return 0;
 
+	if (num_bytes > 256 * 1024 * 1024 &&
+	    sinfo->bytes_used < div_factor(num_bytes, 3))
+		return 0;
+
 	return 1;
 }
 
@@ -3298,55 +3303,26 @@ out:
 	return ret;
 }
 
-static int maybe_allocate_chunk(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root,
-				struct btrfs_space_info *sinfo, u64 num_bytes)
-{
-	int ret;
-	int end_trans = 0;
-
-	if (sinfo->full)
-		return 0;
-
-	spin_lock(&sinfo->lock);
-	ret = should_alloc_chunk(sinfo, num_bytes + 2 * 1024 * 1024);
-	spin_unlock(&sinfo->lock);
-	if (!ret)
-		return 0;
-
-	if (!trans) {
-		trans = btrfs_join_transaction(root, 1);
-		BUG_ON(IS_ERR(trans));
-		end_trans = 1;
-	}
-
-	ret = do_chunk_alloc(trans, root->fs_info->extent_root,
-			     num_bytes + 2 * 1024 * 1024,
-			     get_alloc_profile(root, sinfo->flags), 0);
-
-	if (end_trans)
-		btrfs_end_transaction(trans, root);
-
-	return ret == 1 ? 1 : 0;
-}
-
 /*
  * shrink metadata reservation for delalloc
  */
 static int shrink_delalloc(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, u64 to_reclaim)
+			   struct btrfs_root *root, u64 to_reclaim, int sync)
 {
 	struct btrfs_block_rsv *block_rsv;
+	struct btrfs_space_info *space_info;
 	u64 reserved;
 	u64 max_reclaim;
 	u64 reclaimed = 0;
+	int no_reclaim = 0;
 	int pause = 1;
 	int ret;
 
 	block_rsv = &root->fs_info->delalloc_block_rsv;
-	spin_lock(&block_rsv->lock);
-	reserved = block_rsv->reserved;
-	spin_unlock(&block_rsv->lock);
+	space_info = block_rsv->space_info;
+	spin_lock(&space_info->lock);
+	reserved = space_info->bytes_reserved;
+	spin_unlock(&space_info->lock);
 
 	if (reserved == 0)
 		return 0;
@@ -3354,22 +3330,26 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 	max_reclaim = min(reserved, to_reclaim);
 
 	while (1) {
-		ret = btrfs_start_one_delalloc_inode(root, trans ? 1 : 0);
+		ret = btrfs_start_one_delalloc_inode(root, trans ? 1 : 0, sync);
 		if (!ret) {
+			if (no_reclaim > 2)
+				break;
+			no_reclaim++;
 			__set_current_state(TASK_INTERRUPTIBLE);
 			schedule_timeout(pause);
 			pause <<= 1;
 			if (pause > HZ / 10)
 				pause = HZ / 10;
 		} else {
+			no_reclaim = 0;
 			pause = 1;
 		}
 
-		spin_lock(&block_rsv->lock);
-		if (reserved > block_rsv->reserved)
-			reclaimed = reserved - block_rsv->reserved;
-		reserved = block_rsv->reserved;
-		spin_unlock(&block_rsv->lock);
+		spin_lock(&space_info->lock);
+		if (reserved > space_info->bytes_reserved)
+			reclaimed += reserved - space_info->bytes_reserved;
+		reserved = space_info->bytes_reserved;
+		spin_unlock(&space_info->lock);
 
 		if (reserved == 0 || reclaimed >= max_reclaim)
 			break;
@@ -3380,78 +3360,141 @@ static int shrink_delalloc(struct btrfs_trans_handle *trans,
 	return reclaimed >= to_reclaim;
 }
 
-static int should_retry_reserve(struct btrfs_trans_handle *trans,
-				struct btrfs_root *root,
-				struct btrfs_block_rsv *block_rsv,
-				u64 num_bytes, int *retries)
+/*
+ * Retries tells us how many times we've called reserve_metadata_bytes.  The
+ * idea is if this is the first call (retries == 0) then we will add to our
+ * reserved count if we can't make the allocation in order to hold our place
+ * while we go and try and free up space.  That way for retries > 1 we don't try
+ * and add space, we just check to see if the amount of unused space is >= the
+ * total space, meaning that our reservation is valid.
+ *
+ * However if we don't intend to retry this reservation, pass -1 as retries so
+ * that it short circuits this logic.
+ */
+static int reserve_metadata_bytes(struct btrfs_trans_handle *trans,
+				  struct btrfs_root *root,
+				  struct btrfs_block_rsv *block_rsv,
+				  u64 orig_bytes, int flush)
 {
 	struct btrfs_space_info *space_info = block_rsv->space_info;
-	int ret;
+	u64 unused;
+	u64 num_bytes = orig_bytes;
+	int retries = 0;
+	int ret = 0;
+	bool reserved = false;
+	bool committed = false;
 
-	if ((*retries) > 2)
-		return -ENOSPC;
+again:
+	ret = -ENOSPC;
+	if (reserved)
+		num_bytes = 0;
 
-	ret = maybe_allocate_chunk(trans, root, space_info, num_bytes);
-	if (ret)
-		return 1;
+	spin_lock(&space_info->lock);
+	unused = space_info->bytes_used + space_info->bytes_reserved +
+		 space_info->bytes_pinned + space_info->bytes_readonly +
+		 space_info->bytes_may_use;
 
-	if (trans && trans->transaction->in_commit)
-		return -ENOSPC;
+	/*
+	 * The idea here is that we've not already over-reserved the block group
+	 * then we can go ahead and save our reservation first and then start
+	 * flushing if we need to.  Otherwise if we've already overcommitted
+	 * lets start flushing stuff first and then come back and try to make
+	 * our reservation.
+	 */
+	if (unused <= space_info->total_bytes) {
+		unused -= space_info->total_bytes;
+		if (unused >= num_bytes) {
+			if (!reserved)
+				space_info->bytes_reserved += orig_bytes;
+			ret = 0;
+		} else {
+			/*
+			 * Ok set num_bytes to orig_bytes since we aren't
+			 * overocmmitted, this way we only try and reclaim what
+			 * we need.
+			 */
+			num_bytes = orig_bytes;
+		}
+	} else {
+		/*
+		 * Ok we're over committed, set num_bytes to the overcommitted
+		 * amount plus the amount of bytes that we need for this
+		 * reservation.
+		 */
+		num_bytes = unused - space_info->total_bytes +
+			(orig_bytes * (retries + 1));
+	}
 
-	ret = shrink_delalloc(trans, root, num_bytes);
-	if (ret)
-		return ret;
+	/*
+	 * Couldn't make our reservation, save our place so while we're trying
+	 * to reclaim space we can actually use it instead of somebody else
+	 * stealing it from us.
+	 */
+	if (ret && !reserved) {
+		space_info->bytes_reserved += orig_bytes;
+		reserved = true;
+	}
 
-	spin_lock(&space_info->lock);
-	if (space_info->bytes_pinned < num_bytes)
-		ret = 1;
 	spin_unlock(&space_info->lock);
-	if (ret)
-		return -ENOSPC;
 
-	(*retries)++;
-
-	if (trans)
-		return -EAGAIN;
+	if (!ret)
+		return 0;
 
-	trans = btrfs_join_transaction(root, 1);
-	BUG_ON(IS_ERR(trans));
-	ret = btrfs_commit_transaction(trans, root);
-	BUG_ON(ret);
+	if (!flush)
+		goto out;
 
-	return 1;
-}
+	/*
+	 * We do synchronous shrinking since we don't actually unreserve
+	 * metadata until after the IO is completed.
+	 */
+	ret = shrink_delalloc(trans, root, num_bytes, 1);
+	if (ret > 0)
+		return 0;
+	else if (ret < 0)
+		goto out;
 
-static int reserve_metadata_bytes(struct btrfs_block_rsv *block_rsv,
-				  u64 num_bytes)
-{
-	struct btrfs_space_info *space_info = block_rsv->space_info;
-	u64 unused;
-	int ret = -ENOSPC;
+	/*
+	 * So if we were overcommitted it's possible that somebody else flushed
+	 * out enough space and we simply didn't have enough space to reclaim,
+	 * so go back around and try again.
+	 */
+	if (retries < 2) {
+		retries++;
+		goto again;
+	}
 
 	spin_lock(&space_info->lock);
-	unused = space_info->bytes_used + space_info->bytes_reserved +
-		 space_info->bytes_pinned + space_info->bytes_readonly;
+	/*
+	 * Not enough space to be reclaimed, don't bother committing the
+	 * transaction.
+	 */
+	if (space_info->bytes_pinned < orig_bytes)
+		ret = -ENOSPC;
+	spin_unlock(&space_info->lock);
+	if (ret)
+		goto out;
 
-	if (unused < space_info->total_bytes)
-		unused = space_info->total_bytes - unused;
-	else
-		unused = 0;
+	ret = -EAGAIN;
+	if (trans || committed)
+		goto out;
 
-	if (unused >= num_bytes) {
-		if (block_rsv->priority >= 10) {
-			space_info->bytes_reserved += num_bytes;
-			ret = 0;
-		} else {
-			if ((unused + block_rsv->reserved) *
-			    block_rsv->priority >=
-			    (num_bytes + block_rsv->reserved) * 10) {
-				space_info->bytes_reserved += num_bytes;
-				ret = 0;
-			}
-		}
+	ret = -ENOSPC;
+	trans = btrfs_join_transaction(root, 1);
+	if (IS_ERR(trans))
+		goto out;
+	ret = btrfs_commit_transaction(trans, root);
+	if (!ret) {
+		trans = NULL;
+		committed = true;
+		goto again;
+	}
+
+out:
+	if (reserved) {
+		spin_lock(&space_info->lock);
+		space_info->bytes_reserved -= orig_bytes;
+		spin_unlock(&space_info->lock);
 	}
-	spin_unlock(&space_info->lock);
 
 	return ret;
 }
@@ -3595,23 +3638,19 @@ void btrfs_add_durable_block_rsv(struct btrfs_fs_info *fs_info,
 int btrfs_block_rsv_add(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv,
-			u64 num_bytes, int *retries)
+			u64 num_bytes)
 {
 	int ret;
 
 	if (num_bytes == 0)
 		return 0;
-again:
-	ret = reserve_metadata_bytes(block_rsv, num_bytes);
+
+	ret = reserve_metadata_bytes(trans, root, block_rsv, num_bytes, 1);
 	if (!ret) {
 		block_rsv_add_bytes(block_rsv, num_bytes, 1);
 		return 0;
 	}
 
-	ret = should_retry_reserve(trans, root, block_rsv, num_bytes, retries);
-	if (ret > 0)
-		goto again;
-
 	return ret;
 }
 
@@ -3646,7 +3685,8 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
 		return 0;
 
 	if (block_rsv->refill_used) {
-		ret = reserve_metadata_bytes(block_rsv, num_bytes);
+		ret = reserve_metadata_bytes(trans, root, block_rsv,
+					     num_bytes, 0);
 		if (!ret) {
 			block_rsv_add_bytes(block_rsv, num_bytes, 0);
 			return 0;
@@ -3725,6 +3765,8 @@ static u64 calc_global_metadata_size(struct btrfs_fs_info *fs_info)
 
 	sinfo = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
 	spin_lock(&sinfo->lock);
+	if (sinfo->flags & BTRFS_BLOCK_GROUP_DATA)
+		data_used = 0;
 	meta_used = sinfo->bytes_used;
 	spin_unlock(&sinfo->lock);
 
@@ -3752,7 +3794,8 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	block_rsv->size = num_bytes;
 
 	num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
-		    sinfo->bytes_reserved + sinfo->bytes_readonly;
+		    sinfo->bytes_reserved + sinfo->bytes_readonly +
+		    sinfo->bytes_may_use;
 
 	if (sinfo->total_bytes > num_bytes) {
 		num_bytes = sinfo->total_bytes - num_bytes;
@@ -3823,7 +3866,7 @@ static u64 calc_trans_metadata_size(struct btrfs_root *root, int num_items)
 
 int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
-				 int num_items, int *retries)
+				 int num_items)
 {
 	u64 num_bytes;
 	int ret;
@@ -3833,7 +3876,7 @@ int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
 
 	num_bytes = calc_trans_metadata_size(root, num_items);
 	ret = btrfs_block_rsv_add(trans, root, &root->fs_info->trans_block_rsv,
-				  num_bytes, retries);
+				  num_bytes);
 	if (!ret) {
 		trans->bytes_reserved += num_bytes;
 		trans->block_rsv = &root->fs_info->trans_block_rsv;
@@ -3907,14 +3950,13 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv;
 	u64 to_reserve;
 	int nr_extents;
-	int retries = 0;
 	int ret;
 
 	if (btrfs_transaction_in_commit(root->fs_info))
 		schedule_timeout(1);
 
 	num_bytes = ALIGN(num_bytes, root->sectorsize);
-again:
+
 	spin_lock(&BTRFS_I(inode)->accounting_lock);
 	nr_extents = atomic_read(&BTRFS_I(inode)->outstanding_extents) + 1;
 	if (nr_extents > BTRFS_I(inode)->reserved_extents) {
@@ -3924,18 +3966,14 @@ again:
 		nr_extents = 0;
 		to_reserve = 0;
 	}
+	spin_unlock(&BTRFS_I(inode)->accounting_lock);
 
 	to_reserve += calc_csum_metadata_size(inode, num_bytes);
-	ret = reserve_metadata_bytes(block_rsv, to_reserve);
-	if (ret) {
-		spin_unlock(&BTRFS_I(inode)->accounting_lock);
-		ret = should_retry_reserve(NULL, root, block_rsv, to_reserve,
-					   &retries);
-		if (ret > 0)
-			goto again;
+	ret = reserve_metadata_bytes(NULL, root, block_rsv, to_reserve, 1);
+	if (ret)
 		return ret;
-	}
 
+	spin_lock(&BTRFS_I(inode)->accounting_lock);
 	BTRFS_I(inode)->reserved_extents += nr_extents;
 	atomic_inc(&BTRFS_I(inode)->outstanding_extents);
 	spin_unlock(&BTRFS_I(inode)->accounting_lock);
@@ -3943,7 +3981,7 @@ again:
 	block_rsv_add_bytes(block_rsv, to_reserve, 1);
 
 	if (block_rsv->size > 512 * 1024 * 1024)
-		shrink_delalloc(NULL, root, to_reserve);
+		shrink_delalloc(NULL, root, to_reserve, 0);
 
 	return 0;
 }
@@ -5561,7 +5599,8 @@ use_block_rsv(struct btrfs_trans_handle *trans,
 	block_rsv = get_block_rsv(trans, root);
 
 	if (block_rsv->size == 0) {
-		ret = reserve_metadata_bytes(block_rsv, blocksize);
+		ret = reserve_metadata_bytes(trans, root, block_rsv,
+					     blocksize, 0);
 		if (ret)
 			return ERR_PTR(ret);
 		return block_rsv;
@@ -5571,11 +5610,6 @@ use_block_rsv(struct btrfs_trans_handle *trans,
 	if (!ret)
 		return block_rsv;
 
-	WARN_ON(1);
-	printk(KERN_INFO"block_rsv size %llu reserved %llu freed %llu %llu\n",
-		block_rsv->size, block_rsv->reserved,
-		block_rsv->freed[0], block_rsv->freed[1]);
-
 	return ERR_PTR(-ENOSPC);
 }
 
@@ -8393,6 +8427,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct inode *inode;
 	int ret;
+	int factor;
 
 	root = root->fs_info->extent_root;
 
@@ -8400,6 +8435,14 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	BUG_ON(!block_group);
 	BUG_ON(!block_group->ro);
 
+	memcpy(&key, &block_group->key, sizeof(key));
+	if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
+				  BTRFS_BLOCK_GROUP_RAID1 |
+				  BTRFS_BLOCK_GROUP_RAID10))
+		factor = 2;
+	else
+		factor = 1;
+
 	/* make sure this block group isn't part of an allocation cluster */
 	cluster = &root->fs_info->data_alloc_cluster;
 	spin_lock(&cluster->refill_lock);
@@ -8473,6 +8516,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_lock(&block_group->space_info->lock);
 	block_group->space_info->total_bytes -= block_group->key.offset;
 	block_group->space_info->bytes_readonly -= block_group->key.offset;
+	block_group->space_info->disk_total -= block_group->key.offset * factor;
 	spin_unlock(&block_group->space_info->lock);
 
 	memcpy(&key, &block_group->key, sizeof(key));

fs/btrfs/inode.c

@@ -6681,7 +6681,8 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
 	return 0;
 }
 
-int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput)
+int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput,
+				   int sync)
 {
 	struct btrfs_inode *binode;
 	struct inode *inode = NULL;
@@ -6703,7 +6704,26 @@ int btrfs_start_one_delalloc_inode(struct btrfs_root *root, int delay_iput)
 	spin_unlock(&root->fs_info->delalloc_lock);
 
 	if (inode) {
-		write_inode_now(inode, 0);
+		if (sync) {
+			filemap_write_and_wait(inode->i_mapping);
+			/*
+			 * We have to do this because compression doesn't
+			 * actually set PG_writeback until it submits the pages
+			 * for IO, which happens in an async thread, so we could
+			 * race and not actually wait for any writeback pages
+			 * because they've not been submitted yet.  Technically
+			 * this could still be the case for the ordered stuff
+			 * since the async thread may not have started to do its
+			 * work yet.  If this becomes the case then we need to
+			 * figure out a way to make sure that in writepage we
+			 * wait for any async pages to be submitted before
+			 * returning so that fdatawait does what its supposed to
+			 * do.
+			 */
+			btrfs_wait_ordered_range(inode, 0, (u64)-1);
+		} else {
+			filemap_flush(inode->i_mapping);
+		}
 		if (delay_iput)
 			btrfs_add_delayed_iput(inode);
 		else

fs/btrfs/ioctl.c

@@ -1879,6 +1879,22 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp)
 	return 0;
 }
 
+static void get_block_group_info(struct list_head *groups_list,
+				 struct btrfs_ioctl_space_info *space)
+{
+	struct btrfs_block_group_cache *block_group;
+
+	space->total_bytes = 0;
+	space->used_bytes = 0;
+	space->flags = 0;
+	list_for_each_entry(block_group, groups_list, list) {
+		space->flags = block_group->flags;
+		space->total_bytes += block_group->key.offset;
+		space->used_bytes +=
+			btrfs_block_group_used(&block_group->item);
+	}
+}
+
 long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 {
 	struct btrfs_ioctl_space_args space_args;
@@ -1887,27 +1903,56 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 	struct btrfs_ioctl_space_info *dest_orig;
 	struct btrfs_ioctl_space_info *user_dest;
 	struct btrfs_space_info *info;
+	u64 types[] = {BTRFS_BLOCK_GROUP_DATA,
+		       BTRFS_BLOCK_GROUP_SYSTEM,
+		       BTRFS_BLOCK_GROUP_METADATA,
+		       BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA};
+	int num_types = 4;
 	int alloc_size;
 	int ret = 0;
 	int slot_count = 0;
+	int i, c;
 
 	if (copy_from_user(&space_args,
 			   (struct btrfs_ioctl_space_args __user *)arg,
 			   sizeof(space_args)))
 		return -EFAULT;
 
-	/* first we count slots */
-	rcu_read_lock();
-	list_for_each_entry_rcu(info, &root->fs_info->space_info, list)
-		slot_count++;
-	rcu_read_unlock();
+	for (i = 0; i < num_types; i++) {
+		struct btrfs_space_info *tmp;
+
+		info = NULL;
+		rcu_read_lock();
+		list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
+					list) {
+			if (tmp->flags == types[i]) {
+				info = tmp;
+				break;
+			}
+		}
+		rcu_read_unlock();
+
+		if (!info)
+			continue;
+
+		down_read(&info->groups_sem);
+		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
+			if (!list_empty(&info->block_groups[c]))
+				slot_count++;
+		}
+		up_read(&info->groups_sem);
+	}
 
 	/* space_slots == 0 means they are asking for a count */
 	if (space_args.space_slots == 0) {
 		space_args.total_spaces = slot_count;
 		goto out;
 	}
+
+	slot_count = min_t(int, space_args.space_slots, slot_count);
+
 	alloc_size = sizeof(*dest) * slot_count;
+
 	/* we generally have at most 6 or so space infos, one for each raid
 	 * level.  So, a whole page should be more than enough for everyone
 	 */
@@ -1921,27 +1966,34 @@ long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg)
 	dest_orig = dest;
 
 	/* now we have a buffer to copy into */
-	rcu_read_lock();
-	list_for_each_entry_rcu(info, &root->fs_info->space_info, list) {
-		/* make sure we don't copy more than we allocated
-		 * in our buffer
-		 */
-		if (slot_count == 0)
-			break;
-		slot_count--;
-
-		/* make sure userland has enough room in their buffer */
-		if (space_args.total_spaces >= space_args.space_slots)
-			break;
+	for (i = 0; i < num_types; i++) {
+		struct btrfs_space_info *tmp;
+
+		info = NULL;
+		rcu_read_lock();
+		list_for_each_entry_rcu(tmp, &root->fs_info->space_info,
+					list) {
+			if (tmp->flags == types[i]) {
+				info = tmp;
+				break;
+			}
+		}
+		rcu_read_unlock();
 
-		space.flags = info->flags;
-		space.total_bytes = info->total_bytes;
-		space.used_bytes = info->bytes_used;
-		memcpy(dest, &space, sizeof(space));
-		dest++;
-		space_args.total_spaces++;
+		if (!info)
+			continue;
+		down_read(&info->groups_sem);
+		for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) {
+			if (!list_empty(&info->block_groups[c])) {
+				get_block_group_info(&info->block_groups[c],
+						     &space);
+				memcpy(dest, &space, sizeof(space));
+				dest++;
+				space_args.total_spaces++;
+			}
+		}
+		up_read(&info->groups_sem);
 	}
-	rcu_read_unlock();
 
 	user_dest = (struct btrfs_ioctl_space_info *)
 		(arg + sizeof(struct btrfs_ioctl_space_args));

fs/btrfs/relocation.c

@@ -179,8 +179,6 @@ struct reloc_control {
 	u64 search_start;
 	u64 extents_found;
 
-	int block_rsv_retries;
-
 	unsigned int stage:8;
 	unsigned int create_reloc_tree:1;
 	unsigned int merge_reloc_tree:1;
@@ -2134,7 +2132,6 @@ int prepare_to_merge(struct reloc_control *rc, int err)
 	LIST_HEAD(reloc_roots);
 	u64 num_bytes = 0;
 	int ret;
-	int retries = 0;
 
 	mutex_lock(&root->fs_info->trans_mutex);
 	rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
@@ -2144,7 +2141,7 @@ again:
 	if (!err) {
 		num_bytes = rc->merging_rsv_size;
 		ret = btrfs_block_rsv_add(NULL, root, rc->block_rsv,
-					  num_bytes, &retries);
+					  num_bytes);
 		if (ret)
 			err = ret;
 	}
@@ -2156,7 +2153,6 @@ again:
 			btrfs_end_transaction(trans, rc->extent_root);
 			btrfs_block_rsv_release(rc->extent_root,
 						rc->block_rsv, num_bytes);
-			retries = 0;
 			goto again;
 		}
 	}
@@ -2406,15 +2402,13 @@ static int reserve_metadata_space(struct btrfs_trans_handle *trans,
 	num_bytes = calcu_metadata_size(rc, node, 1) * 2;
 
 	trans->block_rsv = rc->block_rsv;
-	ret = btrfs_block_rsv_add(trans, root, rc->block_rsv, num_bytes,
-				  &rc->block_rsv_retries);
+	ret = btrfs_block_rsv_add(trans, root, rc->block_rsv, num_bytes);
 	if (ret) {
 		if (ret == -EAGAIN)
 			rc->commit_transaction = 1;
 		return ret;
 	}
 
-	rc->block_rsv_retries = 0;
 	return 0;
 }
 
@@ -3615,8 +3609,7 @@ int prepare_to_relocate(struct reloc_control *rc)
 	 * is no reservation in transaction handle.
 	 */
 	ret = btrfs_block_rsv_add(NULL, rc->extent_root, rc->block_rsv,
-				  rc->extent_root->nodesize * 256,
-				  &rc->block_rsv_retries);
+				  rc->extent_root->nodesize * 256);
 	if (ret)
 		return ret;
 
@@ -3628,7 +3621,6 @@ int prepare_to_relocate(struct reloc_control *rc)
 	rc->extents_found = 0;
 	rc->nodes_relocated = 0;
 	rc->merging_rsv_size = 0;
-	rc->block_rsv_retries = 0;
 
 	rc->create_reloc_tree = 1;
 	set_reloc_control(rc);

fs/btrfs/super.c

@@ -638,7 +638,7 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags,
 	if (IS_ERR(root)) {
 		error = PTR_ERR(root);
 		deactivate_locked_super(s);
-		goto error;
+		goto error_free_subvol_name;
 	}
 	/* if they gave us a subvolume name bind mount into that */
 	if (strcmp(subvol_name, ".")) {
@@ -652,14 +652,14 @@ static int btrfs_get_sb(struct file_system_type *fs_type, int flags,
 			deactivate_locked_super(s);
 			error = PTR_ERR(new_root);
 			dput(root);
-			goto error_close_devices;
+			goto error_free_subvol_name;
 		}
 		if (!new_root->d_inode) {
 			dput(root);
 			dput(new_root);
 			deactivate_locked_super(s);
 			error = -ENXIO;
-			goto error_close_devices;
+			goto error_free_subvol_name;
 		}
 		dput(root);
 		root = new_root;
@@ -677,7 +677,6 @@ error_close_devices:
 	btrfs_close_devices(fs_devices);
 error_free_subvol_name:
 	kfree(subvol_name);
-error:
 	return error;
 }
 
@@ -725,18 +724,25 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct list_head *head = &root->fs_info->space_info;
 	struct btrfs_space_info *found;
 	u64 total_used = 0;
+	u64 total_used_data = 0;
 	int bits = dentry->d_sb->s_blocksize_bits;
 	__be32 *fsid = (__be32 *)root->fs_info->fsid;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(found, head, list)
+	list_for_each_entry_rcu(found, head, list) {
+		if (found->flags & (BTRFS_BLOCK_GROUP_METADATA |
+				    BTRFS_BLOCK_GROUP_SYSTEM))
+			total_used_data += found->disk_total;
+		else
+			total_used_data += found->disk_used;
 		total_used += found->disk_used;
+	}
 	rcu_read_unlock();
 
 	buf->f_namelen = BTRFS_NAME_LEN;
 	buf->f_blocks = btrfs_super_total_bytes(disk_super) >> bits;
 	buf->f_bfree = buf->f_blocks - (total_used >> bits);
-	buf->f_bavail = buf->f_bfree;
+	buf->f_bavail = buf->f_blocks - (total_used_data >> bits);
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	buf->f_type = BTRFS_SUPER_MAGIC;
 

fs/btrfs/transaction.c

@@ -180,7 +180,6 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 {
 	struct btrfs_trans_handle *h;
 	struct btrfs_transaction *cur_trans;
-	int retries = 0;
 	int ret;
 again:
 	h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
@@ -215,8 +214,7 @@ again:
 	}
 
 	if (num_items > 0) {
-		ret = btrfs_trans_reserve_metadata(h, root, num_items,
-						   &retries);
+		ret = btrfs_trans_reserve_metadata(h, root, num_items);
 		if (ret == -EAGAIN) {
 			btrfs_commit_transaction(h, root);
 			goto again;
@@ -855,7 +853,6 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	struct extent_buffer *tmp;
 	struct extent_buffer *old;
 	int ret;
-	int retries = 0;
 	u64 to_reserve = 0;
 	u64 index = 0;
 	u64 objectid;
@@ -877,7 +874,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	if (to_reserve > 0) {
 		ret = btrfs_block_rsv_add(trans, root, &pending->block_rsv,
-					  to_reserve, &retries);
+					  to_reserve);
 		if (ret) {
 			pending->error = ret;
 			goto fail;