Btrfs: qgroup: Introduce a may_use to account space_info->bytes_may_use.

Currently, for pre_alloc or delay_alloc, the bytes will be accounted
in space_info by the three guys.
space_info->bytes_may_use --- space_info->reserved --- space_info->used.
But on the other hand, in qgroup, there are only two counters to account the
bytes, qgroup->reserved and qgroup->excl. And qg->reserved accounts
bytes in space_info->bytes_may_use and qg->excl accounts bytes in
space_info->used. So the bytes in space_info->reserved is not accounted
in qgroup. If so, there is a window we can exceed the quota limit when
bytes is in space_info->reserved.

Example:
	# btrfs quota enable /mnt
	# btrfs qgroup limit -e 10M /mnt
	# for((i=0;i<20;i++));do fallocate -l 1M /mnt/data$i; done
	# sync
	# btrfs qgroup show -pcre /mnt
qgroupid rfer     excl     max_rfer max_excl parent  child
-------- ----     ----     -------- -------- ------  -----
0/5      20987904 20987904 0        10485760 ---     ---

qg->excl is 20987904 larger than max_excl 10485760.

This patch introduce a new counter named may_use to qgroup, then
there are three counters in qgroup to account bytes in space_info
as below.
space_info->bytes_may_use --- space_info->reserved --- space_info->used.
qgroup->may_use           --- qgroup->reserved     --- qgroup->excl

With this patch applied:
	# btrfs quota enable /mnt
	# btrfs qgroup limit -e 10M /mnt
	# for((i=0;i<20;i++));do fallocate -l 1M /mnt/data$i; done
fallocate: /mnt/data9: fallocate failed: Disk quota exceeded
fallocate: /mnt/data10: fallocate failed: Disk quota exceeded
fallocate: /mnt/data11: fallocate failed: Disk quota exceeded
fallocate: /mnt/data12: fallocate failed: Disk quota exceeded
fallocate: /mnt/data13: fallocate failed: Disk quota exceeded
fallocate: /mnt/data14: fallocate failed: Disk quota exceeded
fallocate: /mnt/data15: fallocate failed: Disk quota exceeded
fallocate: /mnt/data16: fallocate failed: Disk quota exceeded
fallocate: /mnt/data17: fallocate failed: Disk quota exceeded
fallocate: /mnt/data18: fallocate failed: Disk quota exceeded
fallocate: /mnt/data19: fallocate failed: Disk quota exceeded
	# sync
	# btrfs qgroup show -pcre /mnt
qgroupid rfer    excl    max_rfer max_excl parent  child
-------- ----    ----    -------- -------- ------  -----
0/5      9453568 9453568 0        10485760 ---     ---

Reported-by: Cyril SCETBON <cyril.scetbon@free.fr>
Signed-off-by: Dongsheng Yang <yangds.fnst@cn.fujitsu.com>
Signed-off-by: Chris Mason <clm@fb.com>

1 files changed, 64 insertions, 4 deletions

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index de321c9..cd29173 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -72,6 +72,7 @@ struct btrfs_qgroup {
 	/*
 	 * reservation tracking
 	 */
+	u64 may_use;
 	u64 reserved;
 
 	/*
@@ -1417,6 +1418,8 @@ static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 	WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes);
 	qgroup->excl += sign * oper->num_bytes;
 	qgroup->excl_cmpr += sign * oper->num_bytes;
+	if (sign > 0)
+		qgroup->reserved -= oper->num_bytes;
 
 	qgroup_dirty(fs_info, qgroup);
 
@@ -1436,6 +1439,8 @@ static int qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 		qgroup->rfer_cmpr += sign * oper->num_bytes;
 		WARN_ON(sign < 0 && qgroup->excl < oper->num_bytes);
 		qgroup->excl += sign * oper->num_bytes;
+		if (sign > 0)
+			qgroup->reserved -= oper->num_bytes;
 		qgroup->excl_cmpr += sign * oper->num_bytes;
 		qgroup_dirty(fs_info, qgroup);
 
@@ -2378,6 +2383,61 @@ out:
 	return ret;
 }
 
+int btrfs_qgroup_update_reserved_bytes(struct btrfs_fs_info *fs_info,
+					    u64 ref_root,
+					    u64 num_bytes,
+					    int sign)
+{
+	struct btrfs_root *quota_root;
+	struct btrfs_qgroup *qgroup;
+	int ret = 0;
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
+
+	if (!is_fstree(ref_root) || !fs_info->quota_enabled)
+		return 0;
+
+	if (num_bytes == 0)
+		return 0;
+
+	spin_lock(&fs_info->qgroup_lock);
+	quota_root = fs_info->quota_root;
+	if (!quota_root)
+		goto out;
+
+	qgroup = find_qgroup_rb(fs_info, ref_root);
+	if (!qgroup)
+		goto out;
+
+	ulist_reinit(fs_info->qgroup_ulist);
+	ret = ulist_add(fs_info->qgroup_ulist, qgroup->qgroupid,
+			(uintptr_t)qgroup, GFP_ATOMIC);
+	if (ret < 0)
+		goto out;
+
+	ULIST_ITER_INIT(&uiter);
+	while ((unode = ulist_next(fs_info->qgroup_ulist, &uiter))) {
+		struct btrfs_qgroup *qg;
+		struct btrfs_qgroup_list *glist;
+
+		qg = u64_to_ptr(unode->aux);
+
+		qg->reserved += sign * num_bytes;
+
+		list_for_each_entry(glist, &qg->groups, next_group) {
+			ret = ulist_add(fs_info->qgroup_ulist,
+					glist->group->qgroupid,
+					(uintptr_t)glist->group, GFP_ATOMIC);
+			if (ret < 0)
+				goto out;
+		}
+	}
+
+out:
+	spin_unlock(&fs_info->qgroup_lock);
+	return ret;
+}
+
 /*
  * reserve some space for a qgroup and all its parents. The reservation takes
  * place with start_transaction or dealloc_reserve, similar to ENOSPC
@@ -2426,14 +2486,14 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 		qg = u64_to_ptr(unode->aux);
 
 		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
-		    qg->reserved + (s64)qg->rfer + num_bytes >
+		    qg->reserved + qg->may_use + (s64)qg->rfer + num_bytes >
 		    qg->max_rfer) {
 			ret = -EDQUOT;
 			goto out;
 		}
 
 		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
-		    qg->reserved + (s64)qg->excl + num_bytes >
+		    qg->reserved + qg->may_use + (s64)qg->excl + num_bytes >
 		    qg->max_excl) {
 			ret = -EDQUOT;
 			goto out;
@@ -2457,7 +2517,7 @@ int btrfs_qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 
 		qg = u64_to_ptr(unode->aux);
 
-		qg->reserved += num_bytes;
+		qg->may_use += num_bytes;
 	}
 
 out:
@@ -2503,7 +2563,7 @@ void btrfs_qgroup_free(struct btrfs_root *root, u64 num_bytes)
 
 		qg = u64_to_ptr(unode->aux);
 
-		qg->reserved -= num_bytes;
+		qg->may_use -= num_bytes;
 
 		list_for_each_entry(glist, &qg->groups, next_group) {
 			ret = ulist_add(fs_info->qgroup_ulist,