The grp->bb_largest_free_order is updated regardless of whether
mb_optimize_scan is enabled. This can lead to inconsistencies between
grp->bb_largest_free_order and the actual s_mb_largest_free_orders list
index when mb_optimize_scan is repeatedly enabled and disabled via remount.
For example, if mb_optimize_scan is initially enabled, largest free
order is 3, and the group is in s_mb_largest_free_orders[3]. Then,
mb_optimize_scan is disabled via remount, block allocations occur,
updating largest free order to 2. Finally, mb_optimize_scan is re-enabled
via remount, more block allocations update largest free order to 1.
At this point, the group would be removed from s_mb_largest_free_orders[3]
under the protection of s_mb_largest_free_orders_locks[2]. This lock
mismatch can lead to list corruption.
To fix this, whenever grp->bb_largest_free_order changes, we now always
attempt to remove the group from its old order list. However, we only
insert the group into the new order list if `mb_optimize_scan` is enabled.
This approach helps prevent lock inconsistencies and ensures the data in
the order lists remains reliable.
Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning")
CC: stable@xxxxxxxxxxxxxxx
Suggested-by: Jan Kara <jack@xxxxxxx>
Signed-off-by: Baokun Li <libaokun1@xxxxxxxxxx>
---
fs/ext4/mballoc.c | 33 ++++++++++++++-------------------
1 file changed, 14 insertions(+), 19 deletions(-)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 72b20fc52bbf..fada0d1b3fdb 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1152,33 +1152,28 @@ static void
mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
- int i;
+ int new, old = grp->bb_largest_free_order;
- for (i = MB_NUM_ORDERS(sb) - 1; i >= 0; i--)
- if (grp->bb_counters[i] > 0)
+ for (new = MB_NUM_ORDERS(sb) - 1; new >= 0; new--)
+ if (grp->bb_counters[new] > 0)
break;
+
/* No need to move between order lists? */
- if (!test_opt2(sb, MB_OPTIMIZE_SCAN) ||
- i == grp->bb_largest_free_order) {
- grp->bb_largest_free_order = i;
+ if (new == old)
return;
- }
- if (grp->bb_largest_free_order >= 0) {
- write_lock(&sbi->s_mb_largest_free_orders_locks[
- grp->bb_largest_free_order]);
+ if (old >= 0 && !list_empty(&grp->bb_largest_free_order_node)) {
+ write_lock(&sbi->s_mb_largest_free_orders_locks[old]);
list_del_init(&grp->bb_largest_free_order_node);
- write_unlock(&sbi->s_mb_largest_free_orders_locks[
- grp->bb_largest_free_order]);
+ write_unlock(&sbi->s_mb_largest_free_orders_locks[old]);
}
- grp->bb_largest_free_order = i;
- if (grp->bb_largest_free_order >= 0 && grp->bb_free) {
- write_lock(&sbi->s_mb_largest_free_orders_locks[
- grp->bb_largest_free_order]);
+
+ grp->bb_largest_free_order = new;
+ if (test_opt2(sb, MB_OPTIMIZE_SCAN) && new >= 0 && grp->bb_free) {
+ write_lock(&sbi->s_mb_largest_free_orders_locks[new]);
list_add_tail(&grp->bb_largest_free_order_node,
- &sbi->s_mb_largest_free_orders[grp->bb_largest_free_order]);
- write_unlock(&sbi->s_mb_largest_free_orders_locks[
- grp->bb_largest_free_order]);
+ &sbi->s_mb_largest_free_orders[new]);
+ write_unlock(&sbi->s_mb_largest_free_orders_locks[new]);
}
}
--
2.46.1
