[PATCH v2 10/16] ext4: fix largest free orders lists corruption on mb_optimize_scan switch

[Baokun Li <libaokun1@huawei.com>]

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, a new field bb_largest_free_order_idx is added to struct
ext4_group_info to explicitly track the list index. Then still update
bb_largest_free_order unconditionally, but only update
bb_largest_free_order_idx when mb_optimize_scan is enabled. so that there
is no inconsistency between the lock and the data to be protected.

Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning")
CC: stable@vger.kernel.org
Signed-off-by: Baokun Li <libaokun1@huawei.com>
---
 fs/ext4/ext4.h    |  1 +
 fs/ext4/mballoc.c | 35 ++++++++++++++++-------------------
 2 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 003b8d3726e8..0e574378c6a3 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3476,6 +3476,7 @@ struct ext4_group_info {
 	int		bb_avg_fragment_size_order;	/* order of average
 							   fragment in BG */
 	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
+	ext4_grpblk_t	bb_largest_free_order_idx; /* index of largest frag */
 	ext4_group_t	bb_group;	/* Group number */
 	struct          list_head bb_prealloc_list;
 #ifdef DOUBLE_CHECK
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index e6d6c2da3c6e..dc82124f0905 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1152,33 +1152,29 @@ 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_idx;
 
-	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;
+
+	grp->bb_largest_free_order = new;
 	/* 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 (!test_opt2(sb, MB_OPTIMIZE_SCAN) || 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) {
+		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_idx = new;
+	if (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]);
 	}
 }
 
@@ -3391,6 +3387,7 @@ int ext4_mb_add_groupinfo(struct super_block *sb, ext4_group_t group,
 	INIT_LIST_HEAD(&meta_group_info[i]->bb_avg_fragment_size_node);
 	meta_group_info[i]->bb_largest_free_order = -1;  /* uninit */
 	meta_group_info[i]->bb_avg_fragment_size_order = -1;  /* uninit */
+	meta_group_info[i]->bb_largest_free_order_idx = -1;  /* uninit */
 	meta_group_info[i]->bb_group = group;
 
 	mb_group_bb_bitmap_alloc(sb, meta_group_info[i], group);
-- 
2.46.1