summaryrefslogtreecommitdiff
path: root/fs/btrfs/qgroup.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/qgroup.c')
-rw-r--r--fs/btrfs/qgroup.c140
1 files changed, 87 insertions, 53 deletions
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 77c54749f432..fe3046007f52 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -11,6 +11,7 @@
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/btrfs.h>
+#include <linux/sched/mm.h>
#include "ctree.h"
#include "transaction.h"
@@ -497,13 +498,13 @@ next2:
break;
}
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);
- btrfs_free_path(path);
if (ret < 0) {
ulist_free(fs_info->qgroup_ulist);
@@ -893,8 +894,6 @@ static int btrfs_clean_quota_tree(struct btrfs_trans_handle *trans,
if (!path)
return -ENOMEM;
- path->leave_spinning = 1;
-
key.objectid = 0;
key.offset = 0;
key.type = 0;
@@ -936,6 +935,7 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
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;
@@ -943,8 +943,8 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
if (fs_info->quota_root)
goto out;
- fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
- if (!fs_info->qgroup_ulist) {
+ ulist = ulist_alloc(GFP_KERNEL);
+ if (!ulist) {
ret = -ENOMEM;
goto out;
}
@@ -952,6 +952,22 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
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
* 1 for BTRFS_QGROUP_STATUS item
@@ -961,12 +977,20 @@ int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
* 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;
}
+ if (fs_info->quota_root)
+ goto out;
+
+ fs_info->qgroup_ulist = ulist;
+ ulist = NULL;
+
/*
* initially create the quota tree
*/
@@ -1124,11 +1148,14 @@ 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;
}
@@ -1141,19 +1168,29 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
mutex_lock(&fs_info->qgroup_ioctl_lock);
if (!fs_info->quota_root)
goto out;
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
/*
* 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;
goto out;
}
+ if (!fs_info->quota_root)
+ goto out;
+
clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
btrfs_qgroup_wait_for_completion(fs_info, false);
spin_lock(&fs_info->qgroup_lock);
@@ -1167,13 +1204,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
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, &quota_root->root_key);
if (ret) {
btrfs_abort_transaction(trans, ret);
- goto end_trans;
+ goto out;
}
list_del(&quota_root->dirty_list);
@@ -1185,10 +1222,13 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
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);
+
return ret;
}
@@ -1324,13 +1364,17 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
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;
@@ -1387,10 +1431,14 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
struct btrfs_qgroup_list *list;
struct ulist *tmp;
bool found = false;
+ unsigned int nofs_flag;
int ret = 0;
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;
@@ -1894,34 +1942,22 @@ static int qgroup_trace_extent_swap(struct btrfs_trans_handle* trans,
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);
+ eb = btrfs_read_node_slot(eb, parent_slot);
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->locks[cur_level] = BTRFS_READ_LOCK;
}
src_path->slots[cur_level] = dst_path->slots[cur_level];
@@ -2016,10 +2052,8 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
/* 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
@@ -2038,31 +2072,23 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
*/
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);
+ eb = btrfs_read_node_slot(eb, parent_slot);
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;
+ dst_path->locks[cur_level] = BTRFS_READ_LOCK;
need_cleanup = true;
}
@@ -2206,38 +2232,28 @@ walk_down:
level = root_level;
while (level >= 0) {
if (path->nodes[level] == NULL) {
- struct btrfs_key first_key;
int parent_slot;
- u64 child_gen;
u64 child_bytenr;
/*
- * We need to get child blockptr/gen from parent before
- * we can read it.
+ * We need to get child blockptr from parent before we
+ * can read it.
*/
eb = path->nodes[level + 1];
parent_slot = path->slots[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,
- level, &first_key);
+ eb = btrfs_read_node_slot(eb, parent_slot);
if (IS_ERR(eb)) {
ret = PTR_ERR(eb);
goto out;
- } else if (!extent_buffer_uptodate(eb)) {
- free_extent_buffer(eb);
- ret = -EIO;
- goto out;
}
path->nodes[level] = eb;
path->slots[level] = 0;
btrfs_tree_read_lock(eb);
- btrfs_set_lock_blocking_read(eb);
- path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
+ path->locks[level] = BTRFS_READ_LOCK;
ret = btrfs_qgroup_trace_extent(trans, child_bytenr,
fs_info->nodesize,
@@ -3512,6 +3528,7 @@ static int try_flush_qgroup(struct btrfs_root *root)
{
struct btrfs_trans_handle *trans;
int ret;
+ bool can_commit = true;
/*
* We don't want to run flush again and again, so if there is a running
@@ -3523,6 +3540,20 @@ static int try_flush_qgroup(struct btrfs_root *root)
return 0;
}
+ /*
+ * 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;
+
ret = btrfs_start_delalloc_snapshot(root);
if (ret < 0)
goto out;
@@ -3534,7 +3565,10 @@ static int try_flush_qgroup(struct btrfs_root *root)
goto out;
}
- ret = btrfs_commit_transaction(trans);
+ 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);
@@ -4174,7 +4208,7 @@ int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
spin_unlock(&blocks->lock);
/* Read out reloc subtree root */
- reloc_eb = read_tree_block(fs_info, block->reloc_bytenr,
+ reloc_eb = read_tree_block(fs_info, block->reloc_bytenr, 0,
block->reloc_generation, block->level,
&block->first_key);
if (IS_ERR(reloc_eb)) {
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-26 14:13:36 +0300