* - check all ioctl parameters
*/
+/*
+ * Helpers to access qgroup reservation
+ *
+ * Callers should ensure the lock context and type are valid
+ */
+
+static u64 qgroup_rsv_total(const struct btrfs_qgroup *qgroup)
+{
+ u64 ret = 0;
+ int i;
+
+ for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++)
+ ret += qgroup->rsv.values[i];
+
+ return ret;
+}
+
+#ifdef CONFIG_BTRFS_DEBUG
+static const char *qgroup_rsv_type_str(enum btrfs_qgroup_rsv_type type)
+{
+ if (type == BTRFS_QGROUP_RSV_DATA)
+ return "data";
+ if (type == BTRFS_QGROUP_RSV_META_PERTRANS)
+ return "meta_pertrans";
+ if (type == BTRFS_QGROUP_RSV_META_PREALLOC)
+ return "meta_prealloc";
+ return NULL;
+}
+#endif
+
+static void qgroup_rsv_add(struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup *qgroup, u64 num_bytes,
+ enum btrfs_qgroup_rsv_type type)
+{
+ trace_qgroup_update_reserve(fs_info, qgroup, num_bytes, type);
+ qgroup->rsv.values[type] += num_bytes;
+}
+
+static void qgroup_rsv_release(struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup *qgroup, u64 num_bytes,
+ enum btrfs_qgroup_rsv_type type)
+{
+ trace_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes, type);
+ if (qgroup->rsv.values[type] >= num_bytes) {
+ qgroup->rsv.values[type] -= num_bytes;
+ return;
+ }
+#ifdef CONFIG_BTRFS_DEBUG
+ WARN_RATELIMIT(1,
+ "qgroup %llu %s reserved space underflow, have %llu to free %llu",
+ qgroup->qgroupid, qgroup_rsv_type_str(type),
+ qgroup->rsv.values[type], num_bytes);
+#endif
+ qgroup->rsv.values[type] = 0;
+}
+
+static void qgroup_rsv_add_by_qgroup(struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup *dest,
+ struct btrfs_qgroup *src)
+{
+ int i;
+
+ for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++)
+ qgroup_rsv_add(fs_info, dest, src->rsv.values[i], i);
+}
+
+static void qgroup_rsv_release_by_qgroup(struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup *dest,
+ struct btrfs_qgroup *src)
+{
+ int i;
+
+ for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++)
+ qgroup_rsv_release(fs_info, dest, src->rsv.values[i], i);
+}
+
static void btrfs_qgroup_update_old_refcnt(struct btrfs_qgroup *qg, u64 seq,
int mod)
{
int slot;
mutex_lock(&fs_info->qgroup_ioctl_lock);
- if (fs_info->quota_root) {
- set_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags);
+ if (fs_info->quota_root)
goto out;
- }
fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
if (!fs_info->qgroup_ulist) {
}
spin_lock(&fs_info->qgroup_lock);
fs_info->quota_root = quota_root;
- set_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags);
+ set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
spin_unlock(&fs_info->qgroup_lock);
+ ret = qgroup_rescan_init(fs_info, 0, 1);
+ if (!ret) {
+ qgroup_rescan_zero_tracking(fs_info);
+ btrfs_queue_work(fs_info->qgroup_rescan_workers,
+ &fs_info->qgroup_rescan_work);
+ }
+
out_free_path:
btrfs_free_path(path);
out_free_root:
list_add(&qgroup->dirty, &fs_info->dirty_qgroups);
}
-static void report_reserved_underflow(struct btrfs_fs_info *fs_info,
- struct btrfs_qgroup *qgroup,
- u64 num_bytes)
-{
-#ifdef CONFIG_BTRFS_DEBUG
- WARN_ON(qgroup->reserved < num_bytes);
- btrfs_debug(fs_info,
- "qgroup %llu reserved space underflow, have: %llu, to free: %llu",
- qgroup->qgroupid, qgroup->reserved, num_bytes);
-#endif
- qgroup->reserved = 0;
-}
/*
- * The easy accounting, if we are adding/removing the only ref for an extent
- * then this qgroup and all of the parent qgroups get their reference and
- * exclusive counts adjusted.
+ * The easy accounting, we're updating qgroup relationship whose child qgroup
+ * only has exclusive extents.
+ *
+ * In this case, all exclsuive extents will also be exlusive for parent, so
+ * excl/rfer just get added/removed.
+ *
+ * So is qgroup reservation space, which should also be added/removed to
+ * parent.
+ * Or when child tries to release reservation space, parent will underflow its
+ * reservation (for relationship adding case).
*
* Caller should hold fs_info->qgroup_lock.
*/
static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
struct ulist *tmp, u64 ref_root,
- u64 num_bytes, int sign)
+ struct btrfs_qgroup *src, int sign)
{
struct btrfs_qgroup *qgroup;
struct btrfs_qgroup_list *glist;
struct ulist_node *unode;
struct ulist_iterator uiter;
+ u64 num_bytes = src->excl;
int ret = 0;
qgroup = find_qgroup_rb(fs_info, ref_root);
WARN_ON(sign < 0 && qgroup->excl < num_bytes);
qgroup->excl += sign * num_bytes;
qgroup->excl_cmpr += sign * num_bytes;
- if (sign > 0) {
- trace_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes);
- if (qgroup->reserved < num_bytes)
- report_reserved_underflow(fs_info, qgroup, num_bytes);
- else
- qgroup->reserved -= num_bytes;
- }
+
+ if (sign > 0)
+ qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);
+ else
+ qgroup_rsv_release_by_qgroup(fs_info, qgroup, src);
qgroup_dirty(fs_info, qgroup);
qgroup->rfer_cmpr += sign * num_bytes;
WARN_ON(sign < 0 && qgroup->excl < num_bytes);
qgroup->excl += sign * num_bytes;
- if (sign > 0) {
- trace_qgroup_update_reserve(fs_info, qgroup,
- -(s64)num_bytes);
- if (qgroup->reserved < num_bytes)
- report_reserved_underflow(fs_info, qgroup,
- num_bytes);
- else
- qgroup->reserved -= num_bytes;
- }
+ if (sign > 0)
+ qgroup_rsv_add_by_qgroup(fs_info, qgroup, src);
+ else
+ qgroup_rsv_release_by_qgroup(fs_info, qgroup, src);
qgroup->excl_cmpr += sign * num_bytes;
qgroup_dirty(fs_info, qgroup);
if (qgroup->excl == qgroup->rfer) {
ret = 0;
err = __qgroup_excl_accounting(fs_info, tmp, dst,
- qgroup->excl, sign);
+ qgroup, sign);
if (err < 0) {
ret = err;
goto out;
return ret;
}
-int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info)
+int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_qgroup_extent_record *record;
struct btrfs_delayed_ref_root *delayed_refs;
struct ulist *new_roots = NULL;
{
struct btrfs_root *quota_root = fs_info->quota_root;
int ret = 0;
- int start_rescan_worker = 0;
if (!quota_root)
- goto out;
-
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
- test_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags))
- start_rescan_worker = 1;
-
- if (test_and_clear_bit(BTRFS_FS_QUOTA_ENABLING, &fs_info->flags))
- set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+ return ret;
spin_lock(&fs_info->qgroup_lock);
while (!list_empty(&fs_info->dirty_qgroups)) {
if (ret)
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- if (!ret && start_rescan_worker) {
- ret = qgroup_rescan_init(fs_info, 0, 1);
- if (!ret) {
- qgroup_rescan_zero_tracking(fs_info);
- btrfs_queue_work(fs_info->qgroup_rescan_workers,
- &fs_info->qgroup_rescan_work);
- }
- ret = 0;
- }
-
-out:
-
return ret;
}
static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
{
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
- qg->reserved + (s64)qg->rfer + num_bytes > qg->max_rfer)
+ qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer)
return false;
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
- qg->reserved + (s64)qg->excl + num_bytes > qg->max_excl)
+ qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl)
return false;
return true;
}
-static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
+static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce,
+ enum btrfs_qgroup_rsv_type type)
{
struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
* Commit the tree and retry, since we may have
* deletions which would free up space.
*/
- if (!retried && qg->reserved > 0) {
+ if (!retried && qgroup_rsv_total(qg) > 0) {
struct btrfs_trans_handle *trans;
spin_unlock(&fs_info->qgroup_lock);
qg = unode_aux_to_qgroup(unode);
- trace_qgroup_update_reserve(fs_info, qg, num_bytes);
- qg->reserved += num_bytes;
+ trace_qgroup_update_reserve(fs_info, qg, num_bytes, type);
+ qgroup_rsv_add(fs_info, qg, num_bytes, type);
}
out:
return ret;
}
+/*
+ * Free @num_bytes of reserved space with @type for qgroup. (Normally level 0
+ * qgroup).
+ *
+ * Will handle all higher level qgroup too.
+ *
+ * NOTE: If @num_bytes is (u64)-1, this means to free all bytes of this qgroup.
+ * This special case is only used for META_PERTRANS type.
+ */
void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
- u64 ref_root, u64 num_bytes)
+ u64 ref_root, u64 num_bytes,
+ enum btrfs_qgroup_rsv_type type)
{
struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
if (num_bytes == 0)
return;
+ if (num_bytes == (u64)-1 && type != BTRFS_QGROUP_RSV_META_PERTRANS) {
+ WARN(1, "%s: Invalid type to free", __func__);
+ return;
+ }
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
if (!qgroup)
goto out;
+ if (num_bytes == (u64)-1)
+ /*
+ * We're freeing all pertrans rsv, get reserved value from
+ * level 0 qgroup as real num_bytes to free.
+ */
+ num_bytes = qgroup->rsv.values[type];
+
ulist_reinit(fs_info->qgroup_ulist);
ret = ulist_add(fs_info->qgroup_ulist, qgroup->qgroupid,
(uintptr_t)qgroup, GFP_ATOMIC);
qg = unode_aux_to_qgroup(unode);
- trace_qgroup_update_reserve(fs_info, qg, -(s64)num_bytes);
- if (qg->reserved < num_bytes)
- report_reserved_underflow(fs_info, qg, num_bytes);
- else
- qg->reserved -= num_bytes;
+ trace_qgroup_update_reserve(fs_info, qg, -(s64)num_bytes, type);
+ qgroup_rsv_release(fs_info, qg, num_bytes, type);
list_for_each_entry(glist, &qg->groups, next_group) {
ret = ulist_add(fs_info->qgroup_ulist,
to_reserve, QGROUP_RESERVE);
if (ret < 0)
goto cleanup;
- ret = qgroup_reserve(root, to_reserve, true);
+ ret = qgroup_reserve(root, to_reserve, true, BTRFS_QGROUP_RSV_DATA);
if (ret < 0)
goto cleanup;
goto out;
freed += changeset.bytes_changed;
}
- btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed);
+ btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed,
+ BTRFS_QGROUP_RSV_DATA);
ret = freed;
out:
extent_changeset_release(&changeset);
if (free)
btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
BTRFS_I(inode)->root->objectid,
- changeset.bytes_changed);
+ changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
ret = changeset.bytes_changed;
out:
extent_changeset_release(&changeset);
return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
}
-int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
- bool enforce)
+static void add_root_meta_rsv(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type)
+{
+ if (type != BTRFS_QGROUP_RSV_META_PREALLOC &&
+ type != BTRFS_QGROUP_RSV_META_PERTRANS)
+ return;
+ if (num_bytes == 0)
+ return;
+
+ spin_lock(&root->qgroup_meta_rsv_lock);
+ if (type == BTRFS_QGROUP_RSV_META_PREALLOC)
+ root->qgroup_meta_rsv_prealloc += num_bytes;
+ else
+ root->qgroup_meta_rsv_pertrans += num_bytes;
+ spin_unlock(&root->qgroup_meta_rsv_lock);
+}
+
+static int sub_root_meta_rsv(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type)
+{
+ if (type != BTRFS_QGROUP_RSV_META_PREALLOC &&
+ type != BTRFS_QGROUP_RSV_META_PERTRANS)
+ return 0;
+ if (num_bytes == 0)
+ return 0;
+
+ spin_lock(&root->qgroup_meta_rsv_lock);
+ if (type == BTRFS_QGROUP_RSV_META_PREALLOC) {
+ num_bytes = min_t(u64, root->qgroup_meta_rsv_prealloc,
+ num_bytes);
+ root->qgroup_meta_rsv_prealloc -= num_bytes;
+ } else {
+ num_bytes = min_t(u64, root->qgroup_meta_rsv_pertrans,
+ num_bytes);
+ root->qgroup_meta_rsv_pertrans -= num_bytes;
+ }
+ spin_unlock(&root->qgroup_meta_rsv_lock);
+ return num_bytes;
+}
+
+int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type, bool enforce)
{
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
return 0;
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- trace_qgroup_meta_reserve(root, (s64)num_bytes);
- ret = qgroup_reserve(root, num_bytes, enforce);
+ trace_qgroup_meta_reserve(root, type, (s64)num_bytes);
+ ret = qgroup_reserve(root, num_bytes, enforce, type);
if (ret < 0)
return ret;
- atomic64_add(num_bytes, &root->qgroup_meta_rsv);
+ /*
+ * Record what we have reserved into root.
+ *
+ * To avoid quota disabled->enabled underflow.
+ * In that case, we may try to free space we haven't reserved
+ * (since quota was disabled), so record what we reserved into root.
+ * And ensure later release won't underflow this number.
+ */
+ add_root_meta_rsv(root, num_bytes, type);
return ret;
}
-void btrfs_qgroup_free_meta_all(struct btrfs_root *root)
+void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
- u64 reserved;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
!is_fstree(root->objectid))
return;
- reserved = atomic64_xchg(&root->qgroup_meta_rsv, 0);
- if (reserved == 0)
- return;
- trace_qgroup_meta_reserve(root, -(s64)reserved);
- btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved);
+ /* TODO: Update trace point to handle such free */
+ trace_qgroup_meta_free_all_pertrans(root);
+ /* Special value -1 means to free all reserved space */
+ btrfs_qgroup_free_refroot(fs_info, root->objectid, (u64)-1,
+ BTRFS_QGROUP_RSV_META_PERTRANS);
}
-void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
+void __btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type)
{
struct btrfs_fs_info *fs_info = root->fs_info;
!is_fstree(root->objectid))
return;
+ /*
+ * reservation for META_PREALLOC can happen before quota is enabled,
+ * which can lead to underflow.
+ * Here ensure we will only free what we really have reserved.
+ */
+ num_bytes = sub_root_meta_rsv(root, num_bytes, type);
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
- WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes);
- atomic64_sub(num_bytes, &root->qgroup_meta_rsv);
- trace_qgroup_meta_reserve(root, -(s64)num_bytes);
- btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes);
+ trace_qgroup_meta_reserve(root, type, -(s64)num_bytes);
+ btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes, type);
+}
+
+static void qgroup_convert_meta(struct btrfs_fs_info *fs_info, u64 ref_root,
+ int num_bytes)
+{
+ struct btrfs_root *quota_root = fs_info->quota_root;
+ struct btrfs_qgroup *qgroup;
+ struct ulist_node *unode;
+ struct ulist_iterator uiter;
+ int ret = 0;
+
+ if (num_bytes == 0)
+ return;
+ if (!quota_root)
+ return;
+
+ spin_lock(&fs_info->qgroup_lock);
+ 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 = unode_aux_to_qgroup(unode);
+
+ qgroup_rsv_release(fs_info, qg, num_bytes,
+ BTRFS_QGROUP_RSV_META_PREALLOC);
+ qgroup_rsv_add(fs_info, qg, num_bytes,
+ BTRFS_QGROUP_RSV_META_PERTRANS);
+ 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);
+}
+
+void btrfs_qgroup_convert_reserved_meta(struct btrfs_root *root, int num_bytes)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+ !is_fstree(root->objectid))
+ return;
+ /* Same as btrfs_qgroup_free_meta_prealloc() */
+ num_bytes = sub_root_meta_rsv(root, num_bytes,
+ BTRFS_QGROUP_RSV_META_PREALLOC);
+ trace_qgroup_meta_convert(root, num_bytes);
+ qgroup_convert_meta(fs_info, root->objectid, num_bytes);
}
/*
}
btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
BTRFS_I(inode)->root->objectid,
- changeset.bytes_changed);
+ changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
}
extent_changeset_release(&changeset);
git.samba.org / sfrench / cifs-2.6.git / blobdiff