From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/fs/btrfs/qgroup.c | 1422 +++++++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 1,190 insertions(+), 232 deletions(-)
diff --git a/kernel/fs/btrfs/qgroup.c b/kernel/fs/btrfs/qgroup.c
index 7bda558..a67323c 100644
--- a/kernel/fs/btrfs/qgroup.c
+++ b/kernel/fs/btrfs/qgroup.c
@@ -11,7 +11,7 @@
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/btrfs.h>
-#include <linux/sizes.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "transaction.h"
@@ -21,7 +21,8 @@
#include "backref.h"
#include "extent_io.h"
#include "qgroup.h"
-
+#include "block-group.h"
+#include "sysfs.h"
/* TODO XXX FIXME
* - subvol delete -> delete when ref goes to 0? delete limits also?
@@ -30,7 +31,7 @@
* - sync
* - copy also limits on subvol creation
* - limit
- * - caches fuer ulists
+ * - caches for ulists
* - performance benchmarks
* - check all ioctl parameters
*/
@@ -220,7 +221,8 @@
return qgroup;
}
-static void __del_qgroup_rb(struct btrfs_qgroup *qgroup)
+static void __del_qgroup_rb(struct btrfs_fs_info *fs_info,
+ struct btrfs_qgroup *qgroup)
{
struct btrfs_qgroup_list *list;
@@ -240,7 +242,6 @@
list_del(&list->next_member);
kfree(list);
}
- kfree(qgroup);
}
/* must be called with qgroup_lock held */
@@ -252,7 +253,7 @@
return -ENOENT;
rb_erase(&qgroup->node, &fs_info->qgroup_tree);
- __del_qgroup_rb(qgroup);
+ __del_qgroup_rb(fs_info, qgroup);
return 0;
}
@@ -351,6 +352,9 @@
goto out;
}
+ ret = btrfs_sysfs_add_qgroups(fs_info);
+ if (ret < 0)
+ goto out;
/* default this to quota off, in case no status key is found */
fs_info->qgroup_flags = 0;
@@ -412,6 +416,10 @@
goto out;
}
}
+ ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
+ if (ret < 0)
+ goto out;
+
switch (found_key.type) {
case BTRFS_QGROUP_INFO_KEY: {
struct btrfs_qgroup_info_item *ptr;
@@ -500,9 +508,48 @@
ulist_free(fs_info->qgroup_ulist);
fs_info->qgroup_ulist = NULL;
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+ btrfs_sysfs_del_qgroups(fs_info);
}
return ret < 0 ? ret : 0;
+}
+
+/*
+ * Called in close_ctree() when quota is still enabled. This verifies we don't
+ * leak some reserved space.
+ *
+ * Return false if no reserved space is left.
+ * Return true if some reserved space is leaked.
+ */
+bool btrfs_check_quota_leak(struct btrfs_fs_info *fs_info)
+{
+ struct rb_node *node;
+ bool ret = false;
+
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ return ret;
+ /*
+ * Since we're unmounting, there is no race and no need to grab qgroup
+ * lock. And here we don't go post-order to provide a more user
+ * friendly sorted result.
+ */
+ for (node = rb_first(&fs_info->qgroup_tree); node; node = rb_next(node)) {
+ struct btrfs_qgroup *qgroup;
+ int i;
+
+ qgroup = rb_entry(node, struct btrfs_qgroup, node);
+ for (i = 0; i < BTRFS_QGROUP_RSV_LAST; i++) {
+ if (qgroup->rsv.values[i]) {
+ ret = true;
+ btrfs_warn(fs_info,
+ "qgroup %hu/%llu has unreleased space, type %d rsv %llu",
+ btrfs_qgroup_level(qgroup->qgroupid),
+ btrfs_qgroup_subvolid(qgroup->qgroupid),
+ i, qgroup->rsv.values[i]);
+ }
+ }
+ }
+ return ret;
}
/*
@@ -519,15 +566,18 @@
while ((n = rb_first(&fs_info->qgroup_tree))) {
qgroup = rb_entry(n, struct btrfs_qgroup, node);
rb_erase(n, &fs_info->qgroup_tree);
- __del_qgroup_rb(qgroup);
+ __del_qgroup_rb(fs_info, qgroup);
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
}
/*
- * we call btrfs_free_qgroup_config() when umounting
+ * We call btrfs_free_qgroup_config() when unmounting
* filesystem and disabling quota, so we set qgroup_ulist
* to be null here to avoid double free.
*/
ulist_free(fs_info->qgroup_ulist);
fs_info->qgroup_ulist = NULL;
+ btrfs_sysfs_del_qgroups(fs_info);
}
static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
@@ -887,12 +937,46 @@
struct btrfs_key found_key;
struct btrfs_qgroup *qgroup = NULL;
struct btrfs_trans_handle *trans = NULL;
+ struct ulist *ulist = NULL;
int ret = 0;
int slot;
+
+ /*
+ * We need to have subvol_sem write locked, to prevent races between
+ * concurrent tasks trying to enable quotas, because we will unlock
+ * and relock qgroup_ioctl_lock before setting fs_info->quota_root
+ * and before setting BTRFS_FS_QUOTA_ENABLED.
+ */
+ lockdep_assert_held_write(&fs_info->subvol_sem);
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (fs_info->quota_root)
goto out;
+
+ ulist = ulist_alloc(GFP_KERNEL);
+ if (!ulist) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = btrfs_sysfs_add_qgroups(fs_info);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Unlock qgroup_ioctl_lock before starting the transaction. This is to
+ * avoid lock acquisition inversion problems (reported by lockdep) between
+ * qgroup_ioctl_lock and the vfs freeze semaphores, acquired when we
+ * start a transaction.
+ * After we started the transaction lock qgroup_ioctl_lock again and
+ * check if someone else created the quota root in the meanwhile. If so,
+ * just return success and release the transaction handle.
+ *
+ * Also we don't need to worry about someone else calling
+ * btrfs_sysfs_add_qgroups() after we unlock and getting an error because
+ * that function returns 0 (success) when the sysfs entries already exist.
+ */
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
/*
* 1 for quota root item
@@ -903,24 +987,24 @@
* would be a lot of overkill.
*/
trans = btrfs_start_transaction(tree_root, 2);
+
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
goto out;
}
- fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
- if (!fs_info->qgroup_ulist) {
- ret = -ENOMEM;
- btrfs_abort_transaction(trans, ret);
+ if (fs_info->quota_root)
goto out;
- }
+
+ fs_info->qgroup_ulist = ulist;
+ ulist = NULL;
/*
* initially create the quota tree
*/
- quota_root = btrfs_create_tree(trans, fs_info,
- BTRFS_QUOTA_TREE_OBJECTID);
+ quota_root = btrfs_create_tree(trans, BTRFS_QUOTA_TREE_OBJECTID);
if (IS_ERR(quota_root)) {
ret = PTR_ERR(quota_root);
btrfs_abort_transaction(trans, ret);
@@ -976,6 +1060,10 @@
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.type == BTRFS_ROOT_REF_KEY) {
+
+ /* Release locks on tree_root before we access quota_root */
+ btrfs_release_path(path);
+
ret = add_qgroup_item(trans, quota_root,
found_key.offset);
if (ret) {
@@ -988,6 +1076,25 @@
ret = PTR_ERR(qgroup);
btrfs_abort_transaction(trans, ret);
goto out_free_path;
+ }
+ ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_free_path;
+ }
+ ret = btrfs_search_slot_for_read(tree_root, &found_key,
+ path, 1, 0);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_free_path;
+ }
+ if (ret > 0) {
+ /*
+ * Shouldn't happen, but in case it does we
+ * don't need to do the btrfs_next_item, just
+ * continue.
+ */
+ continue;
}
}
ret = btrfs_next_item(tree_root, path);
@@ -1013,9 +1120,25 @@
btrfs_abort_transaction(trans, ret);
goto out_free_path;
}
+ ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
+ if (ret < 0) {
+ btrfs_abort_transaction(trans, ret);
+ goto out_free_path;
+ }
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ /*
+ * Commit the transaction while not holding qgroup_ioctl_lock, to avoid
+ * a deadlock with tasks concurrently doing other qgroup operations, such
+ * adding/removing qgroups or adding/deleting qgroup relations for example,
+ * because all qgroup operations first start or join a transaction and then
+ * lock the qgroup_ioctl_lock mutex.
+ * We are safe from a concurrent task trying to enable quotas, by calling
+ * this function, since we are serialized by fs_info->subvol_sem.
+ */
ret = btrfs_commit_transaction(trans);
trans = NULL;
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
if (ret)
goto out_free_path;
@@ -1035,24 +1158,40 @@
fs_info->qgroup_rescan_running = true;
btrfs_queue_work(fs_info->qgroup_rescan_workers,
&fs_info->qgroup_rescan_work);
+ } else {
+ /*
+ * We have set both BTRFS_FS_QUOTA_ENABLED and
+ * BTRFS_QGROUP_STATUS_FLAG_ON, so we can only fail with
+ * -EINPROGRESS. That can happen because someone started the
+ * rescan worker by calling quota rescan ioctl before we
+ * attempted to initialize the rescan worker. Failure due to
+ * quotas disabled in the meanwhile is not possible, because
+ * we are holding a write lock on fs_info->subvol_sem, which
+ * is also acquired when disabling quotas.
+ * Ignore such error, and any other error would need to undo
+ * everything we did in the transaction we just committed.
+ */
+ ASSERT(ret == -EINPROGRESS);
+ ret = 0;
}
out_free_path:
btrfs_free_path(path);
out_free_root:
- if (ret) {
- free_extent_buffer(quota_root->node);
- free_extent_buffer(quota_root->commit_root);
- kfree(quota_root);
- }
+ if (ret)
+ btrfs_put_root(quota_root);
out:
if (ret) {
ulist_free(fs_info->qgroup_ulist);
fs_info->qgroup_ulist = NULL;
- if (trans)
- btrfs_end_transaction(trans);
+ btrfs_sysfs_del_qgroups(fs_info);
}
mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ if (ret && trans)
+ btrfs_end_transaction(trans);
+ else if (trans)
+ ret = btrfs_end_transaction(trans);
+ ulist_free(ulist);
return ret;
}
@@ -1062,24 +1201,66 @@
struct btrfs_trans_handle *trans = NULL;
int ret = 0;
+ /*
+ * We need to have subvol_sem write locked to prevent races with
+ * snapshot creation.
+ */
+ lockdep_assert_held_write(&fs_info->subvol_sem);
+
+ /*
+ * Lock the cleaner mutex to prevent races with concurrent relocation,
+ * because relocation may be building backrefs for blocks of the quota
+ * root while we are deleting the root. This is like dropping fs roots
+ * of deleted snapshots/subvolumes, we need the same protection.
+ *
+ * This also prevents races between concurrent tasks trying to disable
+ * quotas, because we will unlock and relock qgroup_ioctl_lock across
+ * BTRFS_FS_QUOTA_ENABLED changes.
+ */
+ mutex_lock(&fs_info->cleaner_mutex);
+
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
goto out;
+
+ /*
+ * Unlock the qgroup_ioctl_lock mutex before waiting for the rescan worker to
+ * complete. Otherwise we can deadlock because btrfs_remove_qgroup() needs
+ * to lock that mutex while holding a transaction handle and the rescan
+ * worker needs to commit a transaction.
+ */
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
+ /*
+ * Request qgroup rescan worker to complete and wait for it. This wait
+ * must be done before transaction start for quota disable since it may
+ * deadlock with transaction by the qgroup rescan worker.
+ */
+ clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
+ btrfs_qgroup_wait_for_completion(fs_info, false);
/*
* 1 For the root item
*
* We should also reserve enough items for the quota tree deletion in
* btrfs_clean_quota_tree but this is not done.
+ *
+ * Also, we must always start a transaction without holding the mutex
+ * qgroup_ioctl_lock, see btrfs_quota_enable().
*/
trans = btrfs_start_transaction(fs_info->tree_root, 1);
+
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
+ trans = NULL;
+ set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
goto out;
}
- clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
- btrfs_qgroup_wait_for_completion(fs_info, false);
+ if (!fs_info->quota_root)
+ goto out;
+
spin_lock(&fs_info->qgroup_lock);
quota_root = fs_info->quota_root;
fs_info->quota_root = NULL;
@@ -1091,30 +1272,34 @@
ret = btrfs_clean_quota_tree(trans, quota_root);
if (ret) {
btrfs_abort_transaction(trans, ret);
- goto end_trans;
+ goto out;
}
ret = btrfs_del_root(trans, "a_root->root_key);
if (ret) {
btrfs_abort_transaction(trans, ret);
- goto end_trans;
+ goto out;
}
+ spin_lock(&fs_info->trans_lock);
list_del("a_root->dirty_list);
+ spin_unlock(&fs_info->trans_lock);
btrfs_tree_lock(quota_root->node);
- clean_tree_block(fs_info, quota_root->node);
+ btrfs_clean_tree_block(quota_root->node);
btrfs_tree_unlock(quota_root->node);
btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1);
- free_extent_buffer(quota_root->node);
- free_extent_buffer(quota_root->commit_root);
- kfree(quota_root);
+ btrfs_put_root(quota_root);
-end_trans:
- ret = btrfs_end_transaction(trans);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ if (ret && trans)
+ btrfs_end_transaction(trans);
+ else if (trans)
+ ret = btrfs_end_transaction(trans);
+ mutex_unlock(&fs_info->cleaner_mutex);
+
return ret;
}
@@ -1129,7 +1314,7 @@
* 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
+ * In this case, all exclusive extents will also be exclusive for parent, so
* excl/rfer just get added/removed.
*
* So is qgroup reservation space, which should also be added/removed to
@@ -1246,25 +1431,27 @@
u64 dst)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *quota_root;
struct btrfs_qgroup *parent;
struct btrfs_qgroup *member;
struct btrfs_qgroup_list *list;
struct ulist *tmp;
+ unsigned int nofs_flag;
int ret = 0;
/* Check the level of src and dst first */
if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst))
return -EINVAL;
+ /* We hold a transaction handle open, must do a NOFS allocation. */
+ nofs_flag = memalloc_nofs_save();
tmp = ulist_alloc(GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
if (!tmp)
return -ENOMEM;
mutex_lock(&fs_info->qgroup_ioctl_lock);
- quota_root = fs_info->quota_root;
- if (!quota_root) {
- ret = -EINVAL;
+ if (!fs_info->quota_root) {
+ ret = -ENOTCONN;
goto out;
}
member = find_qgroup_rb(fs_info, src);
@@ -1310,48 +1497,62 @@
u64 dst)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *quota_root;
struct btrfs_qgroup *parent;
struct btrfs_qgroup *member;
struct btrfs_qgroup_list *list;
struct ulist *tmp;
+ bool found = false;
+ unsigned int nofs_flag;
int ret = 0;
- int err;
+ int ret2;
+ /* We hold a transaction handle open, must do a NOFS allocation. */
+ nofs_flag = memalloc_nofs_save();
tmp = ulist_alloc(GFP_KERNEL);
+ memalloc_nofs_restore(nofs_flag);
if (!tmp)
return -ENOMEM;
- quota_root = fs_info->quota_root;
- if (!quota_root) {
- ret = -EINVAL;
+ if (!fs_info->quota_root) {
+ ret = -ENOTCONN;
goto out;
}
member = find_qgroup_rb(fs_info, src);
parent = find_qgroup_rb(fs_info, dst);
- if (!member || !parent) {
- ret = -EINVAL;
- goto out;
- }
+ /*
+ * The parent/member pair doesn't exist, then try to delete the dead
+ * relation items only.
+ */
+ if (!member || !parent)
+ goto delete_item;
/* check if such qgroup relation exist firstly */
list_for_each_entry(list, &member->groups, next_group) {
- if (list->group == parent)
- goto exist;
+ if (list->group == parent) {
+ found = true;
+ break;
+ }
}
- ret = -ENOENT;
- goto out;
-exist:
- ret = del_qgroup_relation_item(trans, src, dst);
- err = del_qgroup_relation_item(trans, dst, src);
- if (err && !ret)
- ret = err;
- spin_lock(&fs_info->qgroup_lock);
- del_relation_rb(fs_info, src, dst);
- ret = quick_update_accounting(fs_info, tmp, src, dst, -1);
- spin_unlock(&fs_info->qgroup_lock);
+delete_item:
+ ret = del_qgroup_relation_item(trans, src, dst);
+ if (ret < 0 && ret != -ENOENT)
+ goto out;
+ ret2 = del_qgroup_relation_item(trans, dst, src);
+ if (ret2 < 0 && ret2 != -ENOENT)
+ goto out;
+
+ /* At least one deletion succeeded, return 0 */
+ if (!ret || !ret2)
+ ret = 0;
+
+ if (found) {
+ spin_lock(&fs_info->qgroup_lock);
+ del_relation_rb(fs_info, src, dst);
+ ret = quick_update_accounting(fs_info, tmp, src, dst, -1);
+ spin_unlock(&fs_info->qgroup_lock);
+ }
out:
ulist_free(tmp);
return ret;
@@ -1378,11 +1579,11 @@
int ret = 0;
mutex_lock(&fs_info->qgroup_ioctl_lock);
- quota_root = fs_info->quota_root;
- if (!quota_root) {
- ret = -EINVAL;
+ if (!fs_info->quota_root) {
+ ret = -ENOTCONN;
goto out;
}
+ quota_root = fs_info->quota_root;
qgroup = find_qgroup_rb(fs_info, qgroupid);
if (qgroup) {
ret = -EEXIST;
@@ -1397,8 +1598,11 @@
qgroup = add_qgroup_rb(fs_info, qgroupid);
spin_unlock(&fs_info->qgroup_lock);
- if (IS_ERR(qgroup))
+ if (IS_ERR(qgroup)) {
ret = PTR_ERR(qgroup);
+ goto out;
+ }
+ ret = btrfs_sysfs_add_one_qgroup(fs_info, qgroup);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
return ret;
@@ -1407,15 +1611,13 @@
int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
struct btrfs_qgroup_list *list;
int ret = 0;
mutex_lock(&fs_info->qgroup_ioctl_lock);
- quota_root = fs_info->quota_root;
- if (!quota_root) {
- ret = -EINVAL;
+ if (!fs_info->quota_root) {
+ ret = -ENOTCONN;
goto out;
}
@@ -1423,13 +1625,14 @@
if (!qgroup) {
ret = -ENOENT;
goto out;
- } else {
- /* check if there are no children of this qgroup */
- if (!list_empty(&qgroup->members)) {
- ret = -EBUSY;
- goto out;
- }
}
+
+ /* Check if there are no children of this qgroup */
+ if (!list_empty(&qgroup->members)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
ret = del_qgroup_item(trans, qgroupid);
if (ret && ret != -ENOENT)
goto out;
@@ -1446,6 +1649,14 @@
spin_lock(&fs_info->qgroup_lock);
del_qgroup_rb(fs_info, qgroupid);
spin_unlock(&fs_info->qgroup_lock);
+
+ /*
+ * Remove the qgroup from sysfs now without holding the qgroup_lock
+ * spinlock, since the sysfs_remove_group() function needs to take
+ * the mutex kernfs_mutex through kernfs_remove_by_name_ns().
+ */
+ btrfs_sysfs_del_one_qgroup(fs_info, qgroup);
+ kfree(qgroup);
out:
mutex_unlock(&fs_info->qgroup_ioctl_lock);
return ret;
@@ -1455,7 +1666,6 @@
struct btrfs_qgroup_limit *limit)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
int ret = 0;
/* Sometimes we would want to clear the limit on this qgroup.
@@ -1465,9 +1675,8 @@
const u64 CLEAR_VALUE = -1;
mutex_lock(&fs_info->qgroup_ioctl_lock);
- quota_root = fs_info->quota_root;
- if (!quota_root) {
- ret = -EINVAL;
+ if (!fs_info->quota_root) {
+ ret = -ENOTCONN;
goto out;
}
@@ -1546,12 +1755,18 @@
parent_node = *p;
entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
node);
- if (bytenr < entry->bytenr)
+ if (bytenr < entry->bytenr) {
p = &(*p)->rb_left;
- else if (bytenr > entry->bytenr)
+ } else if (bytenr > entry->bytenr) {
p = &(*p)->rb_right;
- else
+ } else {
+ if (record->data_rsv && !entry->data_rsv) {
+ entry->data_rsv = record->data_rsv;
+ entry->data_rsv_refroot =
+ record->data_rsv_refroot;
+ }
return 1;
+ }
}
rb_link_node(&record->node, parent_node, p);
@@ -1597,7 +1812,7 @@
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
|| bytenr == 0 || num_bytes == 0)
return 0;
- record = kmalloc(sizeof(*record), gfp_flag);
+ record = kzalloc(sizeof(*record), gfp_flag);
if (!record)
return -ENOMEM;
@@ -1719,6 +1934,357 @@
return 0;
}
+/*
+ * Helper function to trace a subtree tree block swap.
+ *
+ * The swap will happen in highest tree block, but there may be a lot of
+ * tree blocks involved.
+ *
+ * For example:
+ * OO = Old tree blocks
+ * NN = New tree blocks allocated during balance
+ *
+ * File tree (257) Reloc tree for 257
+ * L2 OO NN
+ * / \ / \
+ * L1 OO OO (a) OO NN (a)
+ * / \ / \ / \ / \
+ * L0 OO OO OO OO OO OO NN NN
+ * (b) (c) (b) (c)
+ *
+ * When calling qgroup_trace_extent_swap(), we will pass:
+ * @src_eb = OO(a)
+ * @dst_path = [ nodes[1] = NN(a), nodes[0] = NN(c) ]
+ * @dst_level = 0
+ * @root_level = 1
+ *
+ * In that case, qgroup_trace_extent_swap() will search from OO(a) to
+ * reach OO(c), then mark both OO(c) and NN(c) as qgroup dirty.
+ *
+ * The main work of qgroup_trace_extent_swap() can be split into 3 parts:
+ *
+ * 1) Tree search from @src_eb
+ * It should acts as a simplified btrfs_search_slot().
+ * The key for search can be extracted from @dst_path->nodes[dst_level]
+ * (first key).
+ *
+ * 2) Mark the final tree blocks in @src_path and @dst_path qgroup dirty
+ * NOTE: In above case, OO(a) and NN(a) won't be marked qgroup dirty.
+ * They should be marked during previous (@dst_level = 1) iteration.
+ *
+ * 3) Mark file extents in leaves dirty
+ * We don't have good way to pick out new file extents only.
+ * So we still follow the old method by scanning all file extents in
+ * the leave.
+ *
+ * This function can free us from keeping two paths, thus later we only need
+ * to care about how to iterate all new tree blocks in reloc tree.
+ */
+static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans,
+ struct extent_buffer *src_eb,
+ struct btrfs_path *dst_path,
+ int dst_level, int root_level,
+ bool trace_leaf)
+{
+ struct btrfs_key key;
+ struct btrfs_path *src_path;
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ u32 nodesize = fs_info->nodesize;
+ int cur_level = root_level;
+ int ret;
+
+ BUG_ON(dst_level > root_level);
+ /* Level mismatch */
+ if (btrfs_header_level(src_eb) != root_level)
+ return -EINVAL;
+
+ src_path = btrfs_alloc_path();
+ if (!src_path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ if (dst_level)
+ btrfs_node_key_to_cpu(dst_path->nodes[dst_level], &key, 0);
+ else
+ btrfs_item_key_to_cpu(dst_path->nodes[dst_level], &key, 0);
+
+ /* For src_path */
+ atomic_inc(&src_eb->refs);
+ src_path->nodes[root_level] = src_eb;
+ src_path->slots[root_level] = dst_path->slots[root_level];
+ src_path->locks[root_level] = 0;
+
+ /* A simplified version of btrfs_search_slot() */
+ while (cur_level >= dst_level) {
+ struct btrfs_key src_key;
+ struct btrfs_key dst_key;
+
+ if (src_path->nodes[cur_level] == NULL) {
+ struct btrfs_key first_key;
+ struct extent_buffer *eb;
+ int parent_slot;
+ u64 child_gen;
+ u64 child_bytenr;
+
+ eb = src_path->nodes[cur_level + 1];
+ parent_slot = src_path->slots[cur_level + 1];
+ child_bytenr = btrfs_node_blockptr(eb, parent_slot);
+ child_gen = btrfs_node_ptr_generation(eb, parent_slot);
+ btrfs_node_key_to_cpu(eb, &first_key, parent_slot);
+
+ eb = read_tree_block(fs_info, child_bytenr, child_gen,
+ cur_level, &first_key);
+ if (IS_ERR(eb)) {
+ ret = PTR_ERR(eb);
+ goto out;
+ } else if (!extent_buffer_uptodate(eb)) {
+ free_extent_buffer(eb);
+ ret = -EIO;
+ goto out;
+ }
+
+ src_path->nodes[cur_level] = eb;
+
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_read(eb);
+ src_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING;
+ }
+
+ src_path->slots[cur_level] = dst_path->slots[cur_level];
+ if (cur_level) {
+ btrfs_node_key_to_cpu(dst_path->nodes[cur_level],
+ &dst_key, dst_path->slots[cur_level]);
+ btrfs_node_key_to_cpu(src_path->nodes[cur_level],
+ &src_key, src_path->slots[cur_level]);
+ } else {
+ btrfs_item_key_to_cpu(dst_path->nodes[cur_level],
+ &dst_key, dst_path->slots[cur_level]);
+ btrfs_item_key_to_cpu(src_path->nodes[cur_level],
+ &src_key, src_path->slots[cur_level]);
+ }
+ /* Content mismatch, something went wrong */
+ if (btrfs_comp_cpu_keys(&dst_key, &src_key)) {
+ ret = -ENOENT;
+ goto out;
+ }
+ cur_level--;
+ }
+
+ /*
+ * Now both @dst_path and @src_path have been populated, record the tree
+ * blocks for qgroup accounting.
+ */
+ ret = btrfs_qgroup_trace_extent(trans, src_path->nodes[dst_level]->start,
+ nodesize, GFP_NOFS);
+ if (ret < 0)
+ goto out;
+ ret = btrfs_qgroup_trace_extent(trans,
+ dst_path->nodes[dst_level]->start,
+ nodesize, GFP_NOFS);
+ if (ret < 0)
+ goto out;
+
+ /* Record leaf file extents */
+ if (dst_level == 0 && trace_leaf) {
+ ret = btrfs_qgroup_trace_leaf_items(trans, src_path->nodes[0]);
+ if (ret < 0)
+ goto out;
+ ret = btrfs_qgroup_trace_leaf_items(trans, dst_path->nodes[0]);
+ }
+out:
+ btrfs_free_path(src_path);
+ return ret;
+}
+
+/*
+ * Helper function to do recursive generation-aware depth-first search, to
+ * locate all new tree blocks in a subtree of reloc tree.
+ *
+ * E.g. (OO = Old tree blocks, NN = New tree blocks, whose gen == last_snapshot)
+ * reloc tree
+ * L2 NN (a)
+ * / \
+ * L1 OO NN (b)
+ * / \ / \
+ * L0 OO OO OO NN
+ * (c) (d)
+ * If we pass:
+ * @dst_path = [ nodes[1] = NN(b), nodes[0] = NULL ],
+ * @cur_level = 1
+ * @root_level = 1
+ *
+ * We will iterate through tree blocks NN(b), NN(d) and info qgroup to trace
+ * above tree blocks along with their counter parts in file tree.
+ * While during search, old tree blocks OO(c) will be skipped as tree block swap
+ * won't affect OO(c).
+ */
+static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
+ struct extent_buffer *src_eb,
+ struct btrfs_path *dst_path,
+ int cur_level, int root_level,
+ u64 last_snapshot, bool trace_leaf)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct extent_buffer *eb;
+ bool need_cleanup = false;
+ int ret = 0;
+ int i;
+
+ /* Level sanity check */
+ if (cur_level < 0 || cur_level >= BTRFS_MAX_LEVEL - 1 ||
+ root_level < 0 || root_level >= BTRFS_MAX_LEVEL - 1 ||
+ root_level < cur_level) {
+ btrfs_err_rl(fs_info,
+ "%s: bad levels, cur_level=%d root_level=%d",
+ __func__, cur_level, root_level);
+ return -EUCLEAN;
+ }
+
+ /* Read the tree block if needed */
+ if (dst_path->nodes[cur_level] == NULL) {
+ struct btrfs_key first_key;
+ int parent_slot;
+ u64 child_gen;
+ u64 child_bytenr;
+
+ /*
+ * dst_path->nodes[root_level] must be initialized before
+ * calling this function.
+ */
+ if (cur_level == root_level) {
+ btrfs_err_rl(fs_info,
+ "%s: dst_path->nodes[%d] not initialized, root_level=%d cur_level=%d",
+ __func__, root_level, root_level, cur_level);
+ return -EUCLEAN;
+ }
+
+ /*
+ * We need to get child blockptr/gen from parent before we can
+ * read it.
+ */
+ eb = dst_path->nodes[cur_level + 1];
+ parent_slot = dst_path->slots[cur_level + 1];
+ child_bytenr = btrfs_node_blockptr(eb, parent_slot);
+ child_gen = btrfs_node_ptr_generation(eb, parent_slot);
+ btrfs_node_key_to_cpu(eb, &first_key, parent_slot);
+
+ /* This node is old, no need to trace */
+ if (child_gen < last_snapshot)
+ goto out;
+
+ eb = read_tree_block(fs_info, child_bytenr, child_gen,
+ cur_level, &first_key);
+ if (IS_ERR(eb)) {
+ ret = PTR_ERR(eb);
+ goto out;
+ } else if (!extent_buffer_uptodate(eb)) {
+ free_extent_buffer(eb);
+ ret = -EIO;
+ goto out;
+ }
+
+ dst_path->nodes[cur_level] = eb;
+ dst_path->slots[cur_level] = 0;
+
+ btrfs_tree_read_lock(eb);
+ btrfs_set_lock_blocking_read(eb);
+ dst_path->locks[cur_level] = BTRFS_READ_LOCK_BLOCKING;
+ need_cleanup = true;
+ }
+
+ /* Now record this tree block and its counter part for qgroups */
+ ret = qgroup_trace_extent_swap(trans, src_eb, dst_path, cur_level,
+ root_level, trace_leaf);
+ if (ret < 0)
+ goto cleanup;
+
+ eb = dst_path->nodes[cur_level];
+
+ if (cur_level > 0) {
+ /* Iterate all child tree blocks */
+ for (i = 0; i < btrfs_header_nritems(eb); i++) {
+ /* Skip old tree blocks as they won't be swapped */
+ if (btrfs_node_ptr_generation(eb, i) < last_snapshot)
+ continue;
+ dst_path->slots[cur_level] = i;
+
+ /* Recursive call (at most 7 times) */
+ ret = qgroup_trace_new_subtree_blocks(trans, src_eb,
+ dst_path, cur_level - 1, root_level,
+ last_snapshot, trace_leaf);
+ if (ret < 0)
+ goto cleanup;
+ }
+ }
+
+cleanup:
+ if (need_cleanup) {
+ /* Clean up */
+ btrfs_tree_unlock_rw(dst_path->nodes[cur_level],
+ dst_path->locks[cur_level]);
+ free_extent_buffer(dst_path->nodes[cur_level]);
+ dst_path->nodes[cur_level] = NULL;
+ dst_path->slots[cur_level] = 0;
+ dst_path->locks[cur_level] = 0;
+ }
+out:
+ return ret;
+}
+
+static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
+ struct extent_buffer *src_eb,
+ struct extent_buffer *dst_eb,
+ u64 last_snapshot, bool trace_leaf)
+{
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_path *dst_path = NULL;
+ int level;
+ int ret;
+
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ return 0;
+
+ /* Wrong parameter order */
+ if (btrfs_header_generation(src_eb) > btrfs_header_generation(dst_eb)) {
+ btrfs_err_rl(fs_info,
+ "%s: bad parameter order, src_gen=%llu dst_gen=%llu", __func__,
+ btrfs_header_generation(src_eb),
+ btrfs_header_generation(dst_eb));
+ return -EUCLEAN;
+ }
+
+ if (!extent_buffer_uptodate(src_eb) || !extent_buffer_uptodate(dst_eb)) {
+ ret = -EIO;
+ goto out;
+ }
+
+ level = btrfs_header_level(dst_eb);
+ dst_path = btrfs_alloc_path();
+ if (!dst_path) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ /* For dst_path */
+ atomic_inc(&dst_eb->refs);
+ dst_path->nodes[level] = dst_eb;
+ dst_path->slots[level] = 0;
+ dst_path->locks[level] = 0;
+
+ /* Do the generation aware breadth-first search */
+ ret = qgroup_trace_new_subtree_blocks(trans, src_eb, dst_path, level,
+ level, last_snapshot, trace_leaf);
+ if (ret < 0)
+ goto out;
+ ret = 0;
+
+out:
+ btrfs_free_path(dst_path);
+ if (ret < 0)
+ fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ return ret;
+}
+
int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
struct extent_buffer *root_eb,
u64 root_gen, int root_level)
@@ -1759,7 +2325,7 @@
* walk back up the tree (adjusting slot pointers as we go)
* and restart the search process.
*/
- extent_buffer_get(root_eb); /* For path */
+ atomic_inc(&root_eb->refs); /* For path */
path->nodes[root_level] = root_eb;
path->slots[root_level] = 0;
path->locks[root_level] = 0; /* so release_path doesn't try to unlock */
@@ -1797,7 +2363,7 @@
path->slots[level] = 0;
btrfs_tree_read_lock(eb);
- btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ btrfs_set_lock_blocking_read(eb);
path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
ret = btrfs_qgroup_trace_extent(trans, child_bytenr,
@@ -1894,7 +2460,7 @@
* Update qgroup rfer/excl counters.
* Rfer update is easy, codes can explain themselves.
*
- * Excl update is tricky, the update is split into 2 part.
+ * Excl update is tricky, the update is split into 2 parts.
* Part 1: Possible exclusive <-> sharing detect:
* | A | !A |
* -------------------------------------
@@ -2143,6 +2709,7 @@
struct btrfs_delayed_ref_root *delayed_refs;
struct ulist *new_roots = NULL;
struct rb_node *node;
+ u64 num_dirty_extents = 0;
u64 qgroup_to_skip;
int ret = 0;
@@ -2152,6 +2719,7 @@
record = rb_entry(node, struct btrfs_qgroup_extent_record,
node);
+ num_dirty_extents++;
trace_btrfs_qgroup_account_extents(fs_info, record);
if (!ret) {
@@ -2168,6 +2736,11 @@
goto cleanup;
}
+ /* Free the reserved data space */
+ btrfs_qgroup_free_refroot(fs_info,
+ record->data_rsv_refroot,
+ record->data_rsv,
+ BTRFS_QGROUP_RSV_DATA);
/*
* Use SEQ_LAST as time_seq to do special search, which
* doesn't lock tree or delayed_refs and search current
@@ -2197,19 +2770,29 @@
kfree(record);
}
+ trace_qgroup_num_dirty_extents(fs_info, trans->transid,
+ num_dirty_extents);
return ret;
}
/*
- * called from commit_transaction. Writes all changed qgroups to disk.
+ * Writes all changed qgroups to disk.
+ * Called by the transaction commit path and the qgroup assign ioctl.
*/
int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
- struct btrfs_root *quota_root = fs_info->quota_root;
int ret = 0;
- if (!quota_root)
+ /*
+ * In case we are called from the qgroup assign ioctl, assert that we
+ * are holding the qgroup_ioctl_lock, otherwise we can race with a quota
+ * disable operation (ioctl) and access a freed quota root.
+ */
+ if (trans->transaction->state != TRANS_STATE_COMMIT_DOING)
+ lockdep_assert_held(&fs_info->qgroup_ioctl_lock);
+
+ if (!fs_info->quota_root)
return ret;
spin_lock(&fs_info->qgroup_lock);
@@ -2353,14 +2936,7 @@
dstgroup->rsv_rfer = inherit->lim.rsv_rfer;
dstgroup->rsv_excl = inherit->lim.rsv_excl;
- ret = update_qgroup_limit_item(trans, dstgroup);
- if (ret) {
- fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- btrfs_info(fs_info,
- "unable to update quota limit for %llu",
- dstgroup->qgroupid);
- goto unlock;
- }
+ qgroup_dirty(fs_info, dstgroup);
}
if (srcid) {
@@ -2455,6 +3031,8 @@
unlock:
spin_unlock(&fs_info->qgroup_lock);
+ if (!ret)
+ ret = btrfs_sysfs_add_one_qgroup(fs_info, dstgroup);
out:
if (!committing)
mutex_unlock(&fs_info->qgroup_ioctl_lock);
@@ -2463,20 +3041,8 @@
return ret;
}
-/*
- * Two limits to commit transaction in advance.
- *
- * For RATIO, it will be 1/RATIO of the remaining limit as threshold.
- * For SIZE, it will be in byte unit as threshold.
- */
-#define QGROUP_FREE_RATIO 32
-#define QGROUP_FREE_SIZE SZ_32M
-static bool qgroup_check_limits(struct btrfs_fs_info *fs_info,
- const struct btrfs_qgroup *qg, u64 num_bytes)
+static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
{
- u64 free;
- u64 threshold;
-
if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
qgroup_rsv_total(qg) + (s64)qg->rfer + num_bytes > qg->max_rfer)
return false;
@@ -2485,39 +3051,12 @@
qgroup_rsv_total(qg) + (s64)qg->excl + num_bytes > qg->max_excl)
return false;
- /*
- * Even if we passed the check, it's better to check if reservation
- * for meta_pertrans is pushing us near limit.
- * If there is too much pertrans reservation or it's near the limit,
- * let's try commit transaction to free some, using transaction_kthread
- */
- if ((qg->lim_flags & (BTRFS_QGROUP_LIMIT_MAX_RFER |
- BTRFS_QGROUP_LIMIT_MAX_EXCL))) {
- if (qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) {
- free = qg->max_excl - qgroup_rsv_total(qg) - qg->excl;
- threshold = min_t(u64, qg->max_excl / QGROUP_FREE_RATIO,
- QGROUP_FREE_SIZE);
- } else {
- free = qg->max_rfer - qgroup_rsv_total(qg) - qg->rfer;
- threshold = min_t(u64, qg->max_rfer / QGROUP_FREE_RATIO,
- QGROUP_FREE_SIZE);
- }
-
- /*
- * Use transaction_kthread to commit transaction, so we no
- * longer need to bother nested transaction nor lock context.
- */
- if (free < threshold)
- btrfs_commit_transaction_locksafe(fs_info);
- }
-
return true;
}
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;
struct btrfs_fs_info *fs_info = root->fs_info;
u64 ref_root = root->root_key.objectid;
@@ -2536,8 +3075,7 @@
enforce = false;
spin_lock(&fs_info->qgroup_lock);
- quota_root = fs_info->quota_root;
- if (!quota_root)
+ if (!fs_info->quota_root)
goto out;
qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -2560,7 +3098,7 @@
qg = unode_aux_to_qgroup(unode);
- if (enforce && !qgroup_check_limits(fs_info, qg, num_bytes)) {
+ if (enforce && !qgroup_check_limits(qg, num_bytes)) {
ret = -EDQUOT;
goto out;
}
@@ -2583,7 +3121,6 @@
qg = unode_aux_to_qgroup(unode);
- trace_qgroup_update_reserve(fs_info, qg, num_bytes, type);
qgroup_rsv_add(fs_info, qg, num_bytes, type);
}
@@ -2605,7 +3142,6 @@
u64 ref_root, u64 num_bytes,
enum btrfs_qgroup_rsv_type type)
{
- struct btrfs_root *quota_root;
struct btrfs_qgroup *qgroup;
struct ulist_node *unode;
struct ulist_iterator uiter;
@@ -2623,8 +3159,7 @@
}
spin_lock(&fs_info->qgroup_lock);
- quota_root = fs_info->quota_root;
- if (!quota_root)
+ if (!fs_info->quota_root)
goto out;
qgroup = find_qgroup_rb(fs_info, ref_root);
@@ -2650,7 +3185,6 @@
qg = unode_aux_to_qgroup(unode);
- 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) {
@@ -2734,9 +3268,6 @@
mutex_unlock(&fs_info->qgroup_rescan_lock);
goto out;
}
- extent_buffer_get(scratch_leaf);
- btrfs_tree_read_lock(scratch_leaf);
- btrfs_set_lock_blocking_rw(scratch_leaf, BTRFS_READ_LOCK);
slot = path->slots[0];
btrfs_release_path(path);
mutex_unlock(&fs_info->qgroup_rescan_lock);
@@ -2762,10 +3293,8 @@
goto out;
}
out:
- if (scratch_leaf) {
- btrfs_tree_read_unlock_blocking(scratch_leaf);
+ if (scratch_leaf)
free_extent_buffer(scratch_leaf);
- }
if (done && !ret) {
ret = 1;
@@ -2777,7 +3306,8 @@
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_STATE_REMOUNTING, &fs_info->fs_state) ||
+ !test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
}
static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
@@ -2789,6 +3319,7 @@
int err = -ENOMEM;
int ret = 0;
bool stopped = false;
+ bool did_leaf_rescans = false;
path = btrfs_alloc_path();
if (!path)
@@ -2807,11 +3338,10 @@
err = PTR_ERR(trans);
break;
}
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
- err = -EINTR;
- } else {
- err = qgroup_rescan_leaf(trans, path);
- }
+
+ err = qgroup_rescan_leaf(trans, path);
+ did_leaf_rescans = true;
+
if (err > 0)
btrfs_commit_transaction(trans);
else
@@ -2825,22 +3355,29 @@
if (err > 0 &&
fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT) {
fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
- } else if (err < 0) {
+ } else if (err < 0 || stopped) {
fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
}
mutex_unlock(&fs_info->qgroup_rescan_lock);
/*
- * only update status, since the previous part has already updated the
- * qgroup info.
+ * Only update status, since the previous part has already updated the
+ * qgroup info, and only if we did any actual work. This also prevents
+ * race with a concurrent quota disable, which has already set
+ * fs_info->quota_root to NULL and cleared BTRFS_FS_QUOTA_ENABLED at
+ * btrfs_quota_disable().
*/
- trans = btrfs_start_transaction(fs_info->quota_root, 1);
- if (IS_ERR(trans)) {
- err = PTR_ERR(trans);
+ if (did_leaf_rescans) {
+ trans = btrfs_start_transaction(fs_info->quota_root, 1);
+ if (IS_ERR(trans)) {
+ err = PTR_ERR(trans);
+ trans = NULL;
+ btrfs_err(fs_info,
+ "fail to start transaction for status update: %d",
+ err);
+ }
+ } else {
trans = NULL;
- btrfs_err(fs_info,
- "fail to start transaction for status update: %d",
- err);
}
mutex_lock(&fs_info->qgroup_rescan_lock);
@@ -2902,7 +3439,6 @@
}
mutex_lock(&fs_info->qgroup_rescan_lock);
- spin_lock(&fs_info->qgroup_lock);
if (init_flags) {
if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN) {
@@ -2914,10 +3450,12 @@
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)) {
+ /* Quota disable is in progress */
+ ret = -EBUSY;
}
if (ret) {
- spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
return ret;
}
@@ -2928,14 +3466,9 @@
sizeof(fs_info->qgroup_rescan_progress));
fs_info->qgroup_rescan_progress.objectid = progress_objectid;
init_completion(&fs_info->qgroup_rescan_completion);
-
- spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
- memset(&fs_info->qgroup_rescan_work, 0,
- sizeof(fs_info->qgroup_rescan_work));
btrfs_init_work(&fs_info->qgroup_rescan_work,
- btrfs_qgroup_rescan_helper,
btrfs_qgroup_rescan_worker, NULL, NULL);
return 0;
}
@@ -3009,9 +3542,7 @@
int ret = 0;
mutex_lock(&fs_info->qgroup_rescan_lock);
- spin_lock(&fs_info->qgroup_lock);
running = fs_info->qgroup_rescan_running;
- spin_unlock(&fs_info->qgroup_lock);
mutex_unlock(&fs_info->qgroup_rescan_lock);
if (!running)
@@ -3042,40 +3573,169 @@
}
}
+#define rbtree_iterate_from_safe(node, next, start) \
+ for (node = start; node && ({ next = rb_next(node); 1;}); node = next)
+
+static int qgroup_unreserve_range(struct btrfs_inode *inode,
+ struct extent_changeset *reserved, u64 start,
+ u64 len)
+{
+ struct rb_node *node;
+ struct rb_node *next;
+ struct ulist_node *entry;
+ int ret = 0;
+
+ node = reserved->range_changed.root.rb_node;
+ if (!node)
+ return 0;
+ while (node) {
+ entry = rb_entry(node, struct ulist_node, rb_node);
+ if (entry->val < start)
+ node = node->rb_right;
+ else
+ node = node->rb_left;
+ }
+
+ if (entry->val > start && rb_prev(&entry->rb_node))
+ entry = rb_entry(rb_prev(&entry->rb_node), struct ulist_node,
+ rb_node);
+
+ rbtree_iterate_from_safe(node, next, &entry->rb_node) {
+ u64 entry_start;
+ u64 entry_end;
+ u64 entry_len;
+ int clear_ret;
+
+ entry = rb_entry(node, struct ulist_node, rb_node);
+ entry_start = entry->val;
+ entry_end = entry->aux;
+ entry_len = entry_end - entry_start + 1;
+
+ if (entry_start >= start + len)
+ break;
+ if (entry_start + entry_len <= start)
+ continue;
+ /*
+ * Now the entry is in [start, start + len), revert the
+ * EXTENT_QGROUP_RESERVED bit.
+ */
+ clear_ret = clear_extent_bits(&inode->io_tree, entry_start,
+ entry_end, EXTENT_QGROUP_RESERVED);
+ if (!ret && clear_ret < 0)
+ ret = clear_ret;
+
+ ulist_del(&reserved->range_changed, entry->val, entry->aux);
+ if (likely(reserved->bytes_changed >= entry_len)) {
+ reserved->bytes_changed -= entry_len;
+ } else {
+ WARN_ON(1);
+ reserved->bytes_changed = 0;
+ }
+ }
+
+ return ret;
+}
+
/*
- * Reserve qgroup space for range [start, start + len).
+ * Try to free some space for qgroup.
*
- * This function will either reserve space from related qgroups or doing
- * nothing if the range is already reserved.
+ * For qgroup, there are only 3 ways to free qgroup space:
+ * - Flush nodatacow write
+ * Any nodatacow write will free its reserved data space at run_delalloc_range().
+ * In theory, we should only flush nodatacow inodes, but it's not yet
+ * possible, so we need to flush the whole root.
*
- * Return 0 for successful reserve
- * Return <0 for error (including -EQUOT)
+ * - Wait for ordered extents
+ * When ordered extents are finished, their reserved metadata is finally
+ * converted to per_trans status, which can be freed by later commit
+ * transaction.
*
- * NOTE: this function may sleep for memory allocation.
- * if btrfs_qgroup_reserve_data() is called multiple times with
- * same @reserved, caller must ensure when error happens it's OK
- * to free *ALL* reserved space.
+ * - Commit transaction
+ * This would free the meta_per_trans space.
+ * In theory this shouldn't provide much space, but any more qgroup space
+ * is needed.
*/
-int btrfs_qgroup_reserve_data(struct inode *inode,
+static int try_flush_qgroup(struct btrfs_root *root)
+{
+ struct btrfs_trans_handle *trans;
+ int ret;
+ bool can_commit = true;
+
+ /*
+ * If current process holds a transaction, we shouldn't flush, as we
+ * assume all space reservation happens before a transaction handle is
+ * held.
+ *
+ * But there are cases like btrfs_delayed_item_reserve_metadata() where
+ * we try to reserve space with one transction handle already held.
+ * In that case we can't commit transaction, but at least try to end it
+ * and hope the started data writes can free some space.
+ */
+ if (current->journal_info &&
+ current->journal_info != BTRFS_SEND_TRANS_STUB)
+ can_commit = false;
+
+ /*
+ * We don't want to run flush again and again, so if there is a running
+ * one, we won't try to start a new flush, but exit directly.
+ */
+ if (test_and_set_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state)) {
+ /*
+ * We are already holding a transaction, thus we can block other
+ * threads from flushing. So exit right now. This increases
+ * the chance of EDQUOT for heavy load and near limit cases.
+ * But we can argue that if we're already near limit, EDQUOT is
+ * unavoidable anyway.
+ */
+ if (!can_commit)
+ return 0;
+
+ wait_event(root->qgroup_flush_wait,
+ !test_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state));
+ return 0;
+ }
+
+ ret = btrfs_start_delalloc_snapshot(root);
+ if (ret < 0)
+ goto out;
+ btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
+
+ trans = btrfs_join_transaction(root);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+
+ if (can_commit)
+ ret = btrfs_commit_transaction(trans);
+ else
+ ret = btrfs_end_transaction(trans);
+out:
+ clear_bit(BTRFS_ROOT_QGROUP_FLUSHING, &root->state);
+ wake_up(&root->qgroup_flush_wait);
+ return ret;
+}
+
+static int qgroup_reserve_data(struct btrfs_inode *inode,
struct extent_changeset **reserved_ret, u64 start,
u64 len)
{
- struct btrfs_root *root = BTRFS_I(inode)->root;
- struct ulist_node *unode;
- struct ulist_iterator uiter;
+ struct btrfs_root *root = inode->root;
struct extent_changeset *reserved;
+ bool new_reserved = false;
u64 orig_reserved;
u64 to_reserve;
int ret;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) ||
- !is_fstree(root->objectid) || len == 0)
+ !is_fstree(root->root_key.objectid) || len == 0)
return 0;
/* @reserved parameter is mandatory for qgroup */
if (WARN_ON(!reserved_ret))
return -EINVAL;
if (!*reserved_ret) {
+ new_reserved = true;
*reserved_ret = extent_changeset_alloc();
if (!*reserved_ret)
return -ENOMEM;
@@ -3083,15 +3743,15 @@
reserved = *reserved_ret;
/* Record already reserved space */
orig_reserved = reserved->bytes_changed;
- ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
+ ret = set_record_extent_bits(&inode->io_tree, start,
start + len -1, EXTENT_QGROUP_RESERVED, reserved);
/* Newly reserved space */
to_reserve = reserved->bytes_changed - orig_reserved;
- trace_btrfs_qgroup_reserve_data(inode, start, len,
+ trace_btrfs_qgroup_reserve_data(&inode->vfs_inode, start, len,
to_reserve, QGROUP_RESERVE);
if (ret < 0)
- goto cleanup;
+ goto out;
ret = qgroup_reserve(root, to_reserve, true, BTRFS_QGROUP_RSV_DATA);
if (ret < 0)
goto cleanup;
@@ -3099,23 +3759,49 @@
return ret;
cleanup:
- /* cleanup *ALL* already reserved ranges */
- ULIST_ITER_INIT(&uiter);
- while ((unode = ulist_next(&reserved->range_changed, &uiter)))
- clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
- unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL);
- /* Also free data bytes of already reserved one */
- btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid,
- orig_reserved, BTRFS_QGROUP_RSV_DATA);
- extent_changeset_release(reserved);
+ qgroup_unreserve_range(inode, reserved, start, len);
+out:
+ if (new_reserved) {
+ extent_changeset_release(reserved);
+ kfree(reserved);
+ *reserved_ret = NULL;
+ }
return ret;
}
+/*
+ * Reserve qgroup space for range [start, start + len).
+ *
+ * This function will either reserve space from related qgroups or do nothing
+ * if the range is already reserved.
+ *
+ * Return 0 for successful reservation
+ * Return <0 for error (including -EQUOT)
+ *
+ * NOTE: This function may sleep for memory allocation, dirty page flushing and
+ * commit transaction. So caller should not hold any dirty page locked.
+ */
+int btrfs_qgroup_reserve_data(struct btrfs_inode *inode,
+ struct extent_changeset **reserved_ret, u64 start,
+ u64 len)
+{
+ int ret;
+
+ ret = qgroup_reserve_data(inode, reserved_ret, start, len);
+ if (ret <= 0 && ret != -EDQUOT)
+ return ret;
+
+ ret = try_flush_qgroup(inode->root);
+ if (ret < 0)
+ return ret;
+ return qgroup_reserve_data(inode, reserved_ret, start, len);
+}
+
/* Free ranges specified by @reserved, normally in error path */
-static int qgroup_free_reserved_data(struct inode *inode,
+static int qgroup_free_reserved_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start, u64 len)
{
- struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_root *root = inode->root;
struct ulist_node *unode;
struct ulist_iterator uiter;
struct extent_changeset changeset;
@@ -3151,14 +3837,14 @@
* EXTENT_QGROUP_RESERVED, we won't double free.
* So not need to rush.
*/
- ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree,
- free_start, free_start + free_len - 1,
+ ret = clear_record_extent_bits(&inode->io_tree, free_start,
+ free_start + free_len - 1,
EXTENT_QGROUP_RESERVED, &changeset);
if (ret < 0)
goto out;
freed += changeset.bytes_changed;
}
- btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed,
+ btrfs_qgroup_free_refroot(root->fs_info, root->root_key.objectid, freed,
BTRFS_QGROUP_RSV_DATA);
ret = freed;
out:
@@ -3166,7 +3852,7 @@
return ret;
}
-static int __btrfs_qgroup_release_data(struct inode *inode,
+static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start, u64 len,
int free)
{
@@ -3174,8 +3860,7 @@
int trace_op = QGROUP_RELEASE;
int ret;
- if (!test_bit(BTRFS_FS_QUOTA_ENABLED,
- &BTRFS_I(inode)->root->fs_info->flags))
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &inode->root->fs_info->flags))
return 0;
/* In release case, we shouldn't have @reserved */
@@ -3183,18 +3868,18 @@
if (free && reserved)
return qgroup_free_reserved_data(inode, reserved, start, len);
extent_changeset_init(&changeset);
- ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
- start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
+ ret = clear_record_extent_bits(&inode->io_tree, start, start + len -1,
+ EXTENT_QGROUP_RESERVED, &changeset);
if (ret < 0)
goto out;
if (free)
trace_op = QGROUP_FREE;
- trace_btrfs_qgroup_release_data(inode, start, len,
+ trace_btrfs_qgroup_release_data(&inode->vfs_inode, start, len,
changeset.bytes_changed, trace_op);
if (free)
- btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
- BTRFS_I(inode)->root->objectid,
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid,
changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
ret = changeset.bytes_changed;
out:
@@ -3214,7 +3899,7 @@
*
* NOTE: This function may sleep for memory allocation.
*/
-int btrfs_qgroup_free_data(struct inode *inode,
+int btrfs_qgroup_free_data(struct btrfs_inode *inode,
struct extent_changeset *reserved, u64 start, u64 len)
{
return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
@@ -3235,7 +3920,7 @@
*
* NOTE: This function may sleep for memory allocation.
*/
-int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len)
+int btrfs_qgroup_release_data(struct btrfs_inode *inode, u64 start, u64 len)
{
return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
}
@@ -3280,14 +3965,14 @@
return num_bytes;
}
-int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
- enum btrfs_qgroup_rsv_type type, bool enforce)
+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;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
- !is_fstree(root->objectid) || num_bytes == 0)
+ !is_fstree(root->root_key.objectid) || num_bytes == 0)
return 0;
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
@@ -3307,18 +3992,33 @@
return ret;
}
+int __btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+ enum btrfs_qgroup_rsv_type type, bool enforce)
+{
+ int ret;
+
+ ret = btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce);
+ if (ret <= 0 && ret != -EDQUOT)
+ return ret;
+
+ ret = try_flush_qgroup(root);
+ if (ret < 0)
+ return ret;
+ return btrfs_qgroup_reserve_meta(root, num_bytes, type, enforce);
+}
+
void btrfs_qgroup_free_meta_all_pertrans(struct btrfs_root *root)
{
struct btrfs_fs_info *fs_info = root->fs_info;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
- !is_fstree(root->objectid))
+ !is_fstree(root->root_key.objectid))
return;
/* 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_free_refroot(fs_info, root->root_key.objectid, (u64)-1,
BTRFS_QGROUP_RSV_META_PERTRANS);
}
@@ -3328,7 +4028,7 @@
struct btrfs_fs_info *fs_info = root->fs_info;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
- !is_fstree(root->objectid))
+ !is_fstree(root->root_key.objectid))
return;
/*
@@ -3339,13 +4039,13 @@
num_bytes = sub_root_meta_rsv(root, num_bytes, type);
BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
trace_qgroup_meta_reserve(root, -(s64)num_bytes, type);
- btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes, type);
+ btrfs_qgroup_free_refroot(fs_info, root->root_key.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;
@@ -3353,7 +4053,7 @@
if (num_bytes == 0)
return;
- if (!quota_root)
+ if (!fs_info->quota_root)
return;
spin_lock(&fs_info->qgroup_lock);
@@ -3393,20 +4093,20 @@
struct btrfs_fs_info *fs_info = root->fs_info;
if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
- !is_fstree(root->objectid))
+ !is_fstree(root->root_key.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);
+ qgroup_convert_meta(fs_info, root->root_key.objectid, num_bytes);
}
/*
* Check qgroup reserved space leaking, normally at destroy inode
* time
*/
-void btrfs_qgroup_check_reserved_leak(struct inode *inode)
+void btrfs_qgroup_check_reserved_leak(struct btrfs_inode *inode)
{
struct extent_changeset changeset;
struct ulist_node *unode;
@@ -3414,21 +4114,279 @@
int ret;
extent_changeset_init(&changeset);
- ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
+ ret = clear_record_extent_bits(&inode->io_tree, 0, (u64)-1,
EXTENT_QGROUP_RESERVED, &changeset);
WARN_ON(ret < 0);
if (WARN_ON(changeset.bytes_changed)) {
ULIST_ITER_INIT(&iter);
while ((unode = ulist_next(&changeset.range_changed, &iter))) {
- btrfs_warn(BTRFS_I(inode)->root->fs_info,
- "leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu",
- inode->i_ino, unode->val, unode->aux);
+ btrfs_warn(inode->root->fs_info,
+ "leaking qgroup reserved space, ino: %llu, start: %llu, end: %llu",
+ btrfs_ino(inode), unode->val, unode->aux);
}
- btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
- BTRFS_I(inode)->root->objectid,
+ btrfs_qgroup_free_refroot(inode->root->fs_info,
+ inode->root->root_key.objectid,
changeset.bytes_changed, BTRFS_QGROUP_RSV_DATA);
}
extent_changeset_release(&changeset);
}
+
+void btrfs_qgroup_init_swapped_blocks(
+ struct btrfs_qgroup_swapped_blocks *swapped_blocks)
+{
+ int i;
+
+ spin_lock_init(&swapped_blocks->lock);
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++)
+ swapped_blocks->blocks[i] = RB_ROOT;
+ swapped_blocks->swapped = false;
+}
+
+/*
+ * Delete all swapped blocks record of @root.
+ * Every record here means we skipped a full subtree scan for qgroup.
+ *
+ * Gets called when committing one transaction.
+ */
+void btrfs_qgroup_clean_swapped_blocks(struct btrfs_root *root)
+{
+ struct btrfs_qgroup_swapped_blocks *swapped_blocks;
+ int i;
+
+ swapped_blocks = &root->swapped_blocks;
+
+ spin_lock(&swapped_blocks->lock);
+ if (!swapped_blocks->swapped)
+ goto out;
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+ struct rb_root *cur_root = &swapped_blocks->blocks[i];
+ struct btrfs_qgroup_swapped_block *entry;
+ struct btrfs_qgroup_swapped_block *next;
+
+ rbtree_postorder_for_each_entry_safe(entry, next, cur_root,
+ node)
+ kfree(entry);
+ swapped_blocks->blocks[i] = RB_ROOT;
+ }
+ swapped_blocks->swapped = false;
+out:
+ spin_unlock(&swapped_blocks->lock);
+}
+
+/*
+ * Add subtree roots record into @subvol_root.
+ *
+ * @subvol_root: tree root of the subvolume tree get swapped
+ * @bg: block group under balance
+ * @subvol_parent/slot: pointer to the subtree root in subvolume tree
+ * @reloc_parent/slot: pointer to the subtree root in reloc tree
+ * BOTH POINTERS ARE BEFORE TREE SWAP
+ * @last_snapshot: last snapshot generation of the subvolume tree
+ */
+int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
+ struct btrfs_root *subvol_root,
+ struct btrfs_block_group *bg,
+ struct extent_buffer *subvol_parent, int subvol_slot,
+ struct extent_buffer *reloc_parent, int reloc_slot,
+ u64 last_snapshot)
+{
+ struct btrfs_fs_info *fs_info = subvol_root->fs_info;
+ struct btrfs_qgroup_swapped_blocks *blocks = &subvol_root->swapped_blocks;
+ struct btrfs_qgroup_swapped_block *block;
+ struct rb_node **cur;
+ struct rb_node *parent = NULL;
+ int level = btrfs_header_level(subvol_parent) - 1;
+ int ret = 0;
+
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ return 0;
+
+ if (btrfs_node_ptr_generation(subvol_parent, subvol_slot) >
+ btrfs_node_ptr_generation(reloc_parent, reloc_slot)) {
+ btrfs_err_rl(fs_info,
+ "%s: bad parameter order, subvol_gen=%llu reloc_gen=%llu",
+ __func__,
+ btrfs_node_ptr_generation(subvol_parent, subvol_slot),
+ btrfs_node_ptr_generation(reloc_parent, reloc_slot));
+ return -EUCLEAN;
+ }
+
+ block = kmalloc(sizeof(*block), GFP_NOFS);
+ if (!block) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ /*
+ * @reloc_parent/slot is still before swap, while @block is going to
+ * record the bytenr after swap, so we do the swap here.
+ */
+ block->subvol_bytenr = btrfs_node_blockptr(reloc_parent, reloc_slot);
+ block->subvol_generation = btrfs_node_ptr_generation(reloc_parent,
+ reloc_slot);
+ block->reloc_bytenr = btrfs_node_blockptr(subvol_parent, subvol_slot);
+ block->reloc_generation = btrfs_node_ptr_generation(subvol_parent,
+ subvol_slot);
+ block->last_snapshot = last_snapshot;
+ block->level = level;
+
+ /*
+ * If we have bg == NULL, we're called from btrfs_recover_relocation(),
+ * no one else can modify tree blocks thus we qgroup will not change
+ * no matter the value of trace_leaf.
+ */
+ if (bg && bg->flags & BTRFS_BLOCK_GROUP_DATA)
+ block->trace_leaf = true;
+ else
+ block->trace_leaf = false;
+ btrfs_node_key_to_cpu(reloc_parent, &block->first_key, reloc_slot);
+
+ /* Insert @block into @blocks */
+ spin_lock(&blocks->lock);
+ cur = &blocks->blocks[level].rb_node;
+ while (*cur) {
+ struct btrfs_qgroup_swapped_block *entry;
+
+ parent = *cur;
+ entry = rb_entry(parent, struct btrfs_qgroup_swapped_block,
+ node);
+
+ if (entry->subvol_bytenr < block->subvol_bytenr) {
+ cur = &(*cur)->rb_left;
+ } else if (entry->subvol_bytenr > block->subvol_bytenr) {
+ cur = &(*cur)->rb_right;
+ } else {
+ if (entry->subvol_generation !=
+ block->subvol_generation ||
+ entry->reloc_bytenr != block->reloc_bytenr ||
+ entry->reloc_generation !=
+ block->reloc_generation) {
+ /*
+ * Duplicated but mismatch entry found.
+ * Shouldn't happen.
+ *
+ * Marking qgroup inconsistent should be enough
+ * for end users.
+ */
+ WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
+ ret = -EEXIST;
+ }
+ kfree(block);
+ goto out_unlock;
+ }
+ }
+ rb_link_node(&block->node, parent, cur);
+ rb_insert_color(&block->node, &blocks->blocks[level]);
+ blocks->swapped = true;
+out_unlock:
+ spin_unlock(&blocks->lock);
+out:
+ if (ret < 0)
+ fs_info->qgroup_flags |=
+ BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ return ret;
+}
+
+/*
+ * Check if the tree block is a subtree root, and if so do the needed
+ * delayed subtree trace for qgroup.
+ *
+ * This is called during btrfs_cow_block().
+ */
+int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct extent_buffer *subvol_eb)
+{
+ struct btrfs_fs_info *fs_info = root->fs_info;
+ struct btrfs_qgroup_swapped_blocks *blocks = &root->swapped_blocks;
+ struct btrfs_qgroup_swapped_block *block;
+ struct extent_buffer *reloc_eb = NULL;
+ struct rb_node *node;
+ bool found = false;
+ bool swapped = false;
+ int level = btrfs_header_level(subvol_eb);
+ int ret = 0;
+ int i;
+
+ if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+ return 0;
+ if (!is_fstree(root->root_key.objectid) || !root->reloc_root)
+ return 0;
+
+ spin_lock(&blocks->lock);
+ if (!blocks->swapped) {
+ spin_unlock(&blocks->lock);
+ return 0;
+ }
+ node = blocks->blocks[level].rb_node;
+
+ while (node) {
+ block = rb_entry(node, struct btrfs_qgroup_swapped_block, node);
+ if (block->subvol_bytenr < subvol_eb->start) {
+ node = node->rb_left;
+ } else if (block->subvol_bytenr > subvol_eb->start) {
+ node = node->rb_right;
+ } else {
+ found = true;
+ break;
+ }
+ }
+ if (!found) {
+ spin_unlock(&blocks->lock);
+ goto out;
+ }
+ /* Found one, remove it from @blocks first and update blocks->swapped */
+ rb_erase(&block->node, &blocks->blocks[level]);
+ for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
+ if (RB_EMPTY_ROOT(&blocks->blocks[i])) {
+ swapped = true;
+ break;
+ }
+ }
+ blocks->swapped = swapped;
+ spin_unlock(&blocks->lock);
+
+ /* Read out reloc subtree root */
+ reloc_eb = read_tree_block(fs_info, block->reloc_bytenr,
+ block->reloc_generation, block->level,
+ &block->first_key);
+ if (IS_ERR(reloc_eb)) {
+ ret = PTR_ERR(reloc_eb);
+ reloc_eb = NULL;
+ goto free_out;
+ }
+ if (!extent_buffer_uptodate(reloc_eb)) {
+ ret = -EIO;
+ goto free_out;
+ }
+
+ ret = qgroup_trace_subtree_swap(trans, reloc_eb, subvol_eb,
+ block->last_snapshot, block->trace_leaf);
+free_out:
+ kfree(block);
+ free_extent_buffer(reloc_eb);
+out:
+ if (ret < 0) {
+ btrfs_err_rl(fs_info,
+ "failed to account subtree at bytenr %llu: %d",
+ subvol_eb->start, ret);
+ fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+ }
+ return ret;
+}
+
+void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans)
+{
+ struct btrfs_qgroup_extent_record *entry;
+ struct btrfs_qgroup_extent_record *next;
+ struct rb_root *root;
+
+ root = &trans->delayed_refs.dirty_extent_root;
+ rbtree_postorder_for_each_entry_safe(entry, next, root, node) {
+ ulist_free(entry->old_roots);
+ kfree(entry);
+ }
+ *root = RB_ROOT;
+}
--
Gitblit v1.6.2