#include "root-tree.h"
#include "tree-checker.h"
+enum btrfs_qgroup_mode btrfs_qgroup_mode(struct btrfs_fs_info *fs_info)
+{
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ return BTRFS_QGROUP_MODE_DISABLED;
+ if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE)
+ return BTRFS_QGROUP_MODE_SIMPLE;
+ return BTRFS_QGROUP_MODE_FULL;
+}
+
+bool btrfs_qgroup_enabled(struct btrfs_fs_info *fs_info)
+{
+ return btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_DISABLED;
+}
+
+bool btrfs_qgroup_full_accounting(struct btrfs_fs_info *fs_info)
+{
+ return btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL;
+}
+
/*
* Helpers to access qgroup reservation
*
static void qgroup_mark_inconsistent(struct btrfs_fs_info *fs_info)
{
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+ return;
fs_info->qgroup_flags |= (BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT |
BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN |
BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING);
}
+static void qgroup_read_enable_gen(struct btrfs_fs_info *fs_info,
+ struct extent_buffer *leaf, int slot,
+ struct btrfs_qgroup_status_item *ptr)
+{
+ ASSERT(btrfs_fs_incompat(fs_info, SIMPLE_QUOTA));
+ ASSERT(btrfs_item_size(leaf, slot) >= sizeof(*ptr));
+ fs_info->qgroup_enable_gen = btrfs_qgroup_status_enable_gen(leaf, ptr);
+}
+
/*
* The full config is read in one go, only called from open_ctree()
* It doesn't use any locking, as at this point we're still single-threaded
u64 flags = 0;
u64 rescan_progress = 0;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!fs_info->quota_root)
return 0;
fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
"old qgroup version, quota disabled");
goto out;
}
- if (btrfs_qgroup_status_generation(l, ptr) !=
- fs_info->generation) {
+ fs_info->qgroup_flags = btrfs_qgroup_status_flags(l, ptr);
+ if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE) {
+ qgroup_read_enable_gen(fs_info, l, slot, ptr);
+ } else if (btrfs_qgroup_status_generation(l, ptr) != fs_info->generation) {
qgroup_mark_inconsistent(fs_info);
btrfs_err(fs_info,
"qgroup generation mismatch, marked as inconsistent");
}
- fs_info->qgroup_flags = btrfs_qgroup_status_flags(l,
- ptr);
rescan_progress = btrfs_qgroup_status_rescan(l, ptr);
goto next1;
}
out:
btrfs_free_path(path);
fs_info->qgroup_flags |= flags;
- if (!(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON))
- clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
- else if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN &&
- ret >= 0)
- ret = qgroup_rescan_init(fs_info, rescan_progress, 0);
-
- if (ret < 0) {
+ if (ret >= 0) {
+ if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_ON)
+ set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+ if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
+ ret = qgroup_rescan_init(fs_info, rescan_progress, 0);
+ } else {
ulist_free(fs_info->qgroup_ulist);
fs_info->qgroup_ulist = NULL;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
struct rb_node *node;
bool ret = false;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED)
return ret;
/*
* Since we're unmounting, there is no race and no need to grab qgroup
return ret;
}
-int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info,
+ struct btrfs_ioctl_quota_ctl_args *quota_ctl_args)
{
struct btrfs_root *quota_root;
struct btrfs_root *tree_root = fs_info->tree_root;
struct btrfs_qgroup *prealloc = NULL;
struct btrfs_trans_handle *trans = NULL;
struct ulist *ulist = NULL;
+ const bool simple = (quota_ctl_args->cmd == BTRFS_QUOTA_CTL_ENABLE_SIMPLE_QUOTA);
int ret = 0;
int slot;
struct btrfs_qgroup_status_item);
btrfs_set_qgroup_status_generation(leaf, ptr, trans->transid);
btrfs_set_qgroup_status_version(leaf, ptr, BTRFS_QGROUP_STATUS_VERSION);
- fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON |
- BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ fs_info->qgroup_flags = BTRFS_QGROUP_STATUS_FLAG_ON;
+ if (simple) {
+ fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
+ btrfs_set_qgroup_status_enable_gen(leaf, ptr, trans->transid);
+ } else {
+ fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ }
btrfs_set_qgroup_status_flags(leaf, ptr, fs_info->qgroup_flags &
BTRFS_QGROUP_STATUS_FLAGS_MASK);
btrfs_set_qgroup_status_rescan(leaf, ptr, 0);
goto out_free_path;
}
+ fs_info->qgroup_enable_gen = trans->transid;
+
mutex_unlock(&fs_info->qgroup_ioctl_lock);
/*
* Commit the transaction while not holding qgroup_ioctl_lock, to avoid
spin_lock(&fs_info->qgroup_lock);
fs_info->quota_root = quota_root;
set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+ if (simple)
+ btrfs_set_fs_incompat(fs_info, SIMPLE_QUOTA);
spin_unlock(&fs_info->qgroup_lock);
+ /* Skip rescan for simple qgroups. */
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+ goto out_free_path;
+
ret = qgroup_rescan_init(fs_info, 0, 1);
if (!ret) {
qgroup_rescan_zero_tracking(fs_info);
return ret;
}
+/*
+ * It is possible to have outstanding ordered extents which reserved bytes
+ * before we disabled. We need to fully flush delalloc, ordered extents, and a
+ * commit to ensure that we don't leak such reservations, only to have them
+ * come back if we re-enable.
+ *
+ * - enable simple quotas
+ * - reserve space
+ * - release it, store rsv_bytes in OE
+ * - disable quotas
+ * - enable simple quotas (qgroup rsv are all 0)
+ * - OE finishes
+ * - run delayed refs
+ * - free rsv_bytes, resulting in miscounting or even underflow
+ */
+static int flush_reservations(struct btrfs_fs_info *fs_info)
+{
+ struct btrfs_trans_handle *trans;
+ int ret;
+
+ ret = btrfs_start_delalloc_roots(fs_info, LONG_MAX, false);
+ if (ret)
+ return ret;
+ btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
+ trans = btrfs_join_transaction(fs_info->tree_root);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+ btrfs_commit_transaction(trans);
+
+ return ret;
+}
+
int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
{
struct btrfs_root *quota_root;
clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
btrfs_qgroup_wait_for_completion(fs_info, false);
+ ret = flush_reservations(fs_info);
+ if (ret)
+ goto out_unlock_cleaner;
+
/*
* 1 For the root item
*
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
+ fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
fs_info->qgroup_drop_subtree_thres = BTRFS_MAX_LEVEL;
spin_unlock(&fs_info->qgroup_lock);
if (ret && trans)
btrfs_end_transaction(trans);
else if (trans)
- ret = btrfs_end_transaction(trans);
+ ret = btrfs_commit_transaction(trans);
+out_unlock_cleaner:
mutex_unlock(&fs_info->cleaner_mutex);
return ret;
return ret;
}
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
- u64 dst)
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_qgroup *parent;
struct btrfs_qgroup *prealloc = NULL;
int ret = 0;
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED)
+ return 0;
+
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root) {
ret = -ENOTCONN;
struct btrfs_qgroup_extent_record *entry;
u64 bytenr = record->bytenr;
+ if (!btrfs_qgroup_full_accounting(fs_info))
+ return 0;
+
lockdep_assert_held(&delayed_refs->lock);
trace_btrfs_qgroup_trace_extent(fs_info, record);
struct btrfs_backref_walk_ctx ctx = { 0 };
int ret;
+ if (!btrfs_qgroup_full_accounting(trans->fs_info))
+ return 0;
/*
* We are always called in a context where we are already holding a
* transaction handle. Often we are called when adding a data delayed
struct btrfs_delayed_ref_root *delayed_refs;
int ret;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
- || bytenr == 0 || num_bytes == 0)
+ if (!btrfs_qgroup_full_accounting(fs_info) || bytenr == 0 || num_bytes == 0)
return 0;
record = kzalloc(sizeof(*record), GFP_NOFS);
if (!record)
u64 bytenr, num_bytes;
/* We can be called directly from walk_up_proc() */
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!btrfs_qgroup_full_accounting(fs_info))
return 0;
for (i = 0; i < nr; i++) {
int level;
int ret;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!btrfs_qgroup_full_accounting(fs_info))
return 0;
/* Wrong parameter order */
BUG_ON(root_level < 0 || root_level >= BTRFS_MAX_LEVEL);
BUG_ON(root_eb == NULL);
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!btrfs_qgroup_full_accounting(fs_info))
return 0;
spin_lock(&fs_info->qgroup_lock);
* If quotas get disabled meanwhile, the resources need to be freed and
* we can't just exit here.
*/
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+ if (!btrfs_qgroup_full_accounting(fs_info) ||
fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_NO_ACCOUNTING)
goto out_free;
u64 qgroup_to_skip;
int ret = 0;
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+ return 0;
+
delayed_refs = &trans->transaction->delayed_refs;
qgroup_to_skip = delayed_refs->qgroup_to_skip;
while ((node = rb_first(&delayed_refs->dirty_extent_root))) {
qgroup_mark_inconsistent(fs_info);
spin_lock(&fs_info->qgroup_lock);
}
- if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (btrfs_qgroup_enabled(fs_info))
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_ON;
else
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
return ret;
}
+static int qgroup_auto_inherit(struct btrfs_fs_info *fs_info,
+ u64 inode_rootid,
+ struct btrfs_qgroup_inherit **inherit)
+{
+ int i = 0;
+ u64 num_qgroups = 0;
+ struct btrfs_qgroup *inode_qg;
+ struct btrfs_qgroup_list *qg_list;
+ struct btrfs_qgroup_inherit *res;
+ size_t struct_sz;
+ u64 *qgids;
+
+ if (*inherit)
+ return -EEXIST;
+
+ inode_qg = find_qgroup_rb(fs_info, inode_rootid);
+ if (!inode_qg)
+ return -ENOENT;
+
+ num_qgroups = list_count_nodes(&inode_qg->groups);
+
+ if (!num_qgroups)
+ return 0;
+
+ struct_sz = struct_size(res, qgroups, num_qgroups);
+ if (struct_sz == SIZE_MAX)
+ return -ERANGE;
+
+ res = kzalloc(struct_sz, GFP_NOFS);
+ if (!res)
+ return -ENOMEM;
+ res->num_qgroups = num_qgroups;
+ qgids = res->qgroups;
+
+ list_for_each_entry(qg_list, &inode_qg->groups, next_group)
+ qgids[i] = qg_list->group->qgroupid;
+
+ *inherit = res;
+ return 0;
+}
+
/*
* Copy the accounting information between qgroups. This is necessary
* when a snapshot or a subvolume is created. Throwing an error will
* when a readonly fs is a reasonable outcome.
*/
int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
- u64 objectid, struct btrfs_qgroup_inherit *inherit)
+ u64 objectid, u64 inode_rootid,
+ struct btrfs_qgroup_inherit *inherit)
{
int ret = 0;
int i;
struct btrfs_qgroup *dstgroup;
struct btrfs_qgroup *prealloc;
struct btrfs_qgroup_list **qlist_prealloc = NULL;
+ bool free_inherit = false;
bool need_rescan = false;
u32 level_size = 0;
u64 nums;
if (!committing)
mutex_lock(&fs_info->qgroup_ioctl_lock);
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!btrfs_qgroup_enabled(fs_info))
goto out;
quota_root = fs_info->quota_root;
goto out;
}
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE && !inherit) {
+ ret = qgroup_auto_inherit(fs_info, inode_rootid, &inherit);
+ if (ret)
+ goto out;
+ free_inherit = true;
+ }
+
if (inherit) {
i_qgroups = (u64 *)(inherit + 1);
nums = inherit->num_qgroups + 2 * inherit->num_ref_copies +
qgroup_dirty(fs_info, dstgroup);
}
- if (srcid) {
+ if (srcid && btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL) {
srcgroup = find_qgroup_rb(fs_info, srcid);
if (!srcgroup)
goto unlock;
kfree(qlist_prealloc[i]);
kfree(qlist_prealloc);
}
+ if (free_inherit)
+ kfree(inherit);
kfree(prealloc);
return ret;
}
int slot;
int ret;
+ if (!btrfs_qgroup_full_accounting(fs_info))
+ return 1;
+
mutex_lock(&fs_info->qgroup_rescan_lock);
extent_root = btrfs_extent_root(fs_info,
fs_info->qgroup_rescan_progress.objectid);
static bool rescan_should_stop(struct btrfs_fs_info *fs_info)
{
- return btrfs_fs_closing(fs_info) ||
- test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state) ||
- !test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
- fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN;
+ if (btrfs_fs_closing(fs_info))
+ return true;
+ if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state))
+ return true;
+ if (!btrfs_qgroup_enabled(fs_info))
+ return true;
+ if (fs_info->qgroup_flags & BTRFS_QGROUP_RUNTIME_FLAG_CANCEL_RESCAN)
+ return true;
+ return false;
}
static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
bool stopped = false;
bool did_leaf_rescans = false;
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE)
+ return;
+
path = btrfs_alloc_path();
if (!path)
goto out;
{
int ret = 0;
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE) {
+ btrfs_warn(fs_info, "qgroup rescan init failed, running in simple mode");
+ return -EINVAL;
+ }
+
if (!init_flags) {
/* we're resuming qgroup rescan at mount time */
if (!(fs_info->qgroup_flags &
btrfs_warn(fs_info,
"qgroup rescan init failed, qgroup is not enabled");
ret = -EINVAL;
- } else if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
+ } else if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
/* Quota disable is in progress */
ret = -EBUSY;
}
u64 to_reserve;
int ret;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) ||
+ if (btrfs_qgroup_mode(root->fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
!is_fstree(root->root_key.objectid) || len == 0)
return 0;
int trace_op = QGROUP_RELEASE;
int ret;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &inode->root->fs_info->flags))
- return 0;
+ if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
+ extent_changeset_init(&changeset);
+ return clear_record_extent_bits(&inode->io_tree, start,
+ start + len - 1,
+ EXTENT_QGROUP_RESERVED, &changeset);
+ }
/* In release case, we shouldn't have @reserved */
WARN_ON(!free && reserved);
struct btrfs_fs_info *fs_info = root->fs_info;
int ret;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
!is_fstree(root->root_key.objectid) || num_bytes == 0)
return 0;
{
struct btrfs_fs_info *fs_info = root->fs_info;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
!is_fstree(root->root_key.objectid))
return;
{
struct btrfs_fs_info *fs_info = root->fs_info;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
!is_fstree(root->root_key.objectid))
return;
{
struct btrfs_fs_info *fs_info = root->fs_info;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
+ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_DISABLED ||
!is_fstree(root->root_key.objectid))
return;
/* Same as btrfs_qgroup_free_meta_prealloc() */
int level = btrfs_header_level(subvol_parent) - 1;
int ret = 0;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!btrfs_qgroup_full_accounting(fs_info))
return 0;
if (btrfs_node_ptr_generation(subvol_parent, subvol_slot) >
int ret = 0;
int i;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ if (!btrfs_qgroup_full_accounting(fs_info))
return 0;
if (!is_fstree(root->root_key.objectid) || !root->reloc_root)
return 0;
}
*root = RB_ROOT;
}
+
+int btrfs_record_squota_delta(struct btrfs_fs_info *fs_info,
+ struct btrfs_squota_delta *delta)
+{
+ int ret;
+ struct btrfs_qgroup *qgroup;
+ struct btrfs_qgroup *qg;
+ LIST_HEAD(qgroup_list);
+ u64 root = delta->root;
+ u64 num_bytes = delta->num_bytes;
+ const int sign = (delta->is_inc ? 1 : -1);
+
+ if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_SIMPLE)
+ return 0;
+
+ if (!is_fstree(root))
+ return 0;
+
+ /* If the extent predates enabling quotas, don't count it. */
+ if (delta->generation < fs_info->qgroup_enable_gen)
+ return 0;
+
+ spin_lock(&fs_info->qgroup_lock);
+ qgroup = find_qgroup_rb(fs_info, root);
+ if (!qgroup) {
+ ret = -ENOENT;
+ goto out;
+ }
+
+ ret = 0;
+ qgroup_iterator_add(&qgroup_list, qgroup);
+ list_for_each_entry(qg, &qgroup_list, iterator) {
+ struct btrfs_qgroup_list *glist;
+
+ qg->excl += num_bytes * sign;
+ qg->rfer += num_bytes * sign;
+ qgroup_dirty(fs_info, qg);
+
+ list_for_each_entry(glist, &qg->groups, next_group)
+ qgroup_iterator_add(&qgroup_list, glist->group);
+ }
+ qgroup_iterator_clean(&qgroup_list);
+
+out:
+ spin_unlock(&fs_info->qgroup_lock);
+ if (!ret && delta->rsv_bytes)
+ btrfs_qgroup_free_refroot(fs_info, root, delta->rsv_bytes,
+ BTRFS_QGROUP_RSV_DATA);
+ return ret;
+}