mm-lock-pgdat_reclaim_locked-with-acquire-memory-ordering.patch removed from -mm tree
The quilt patch titled
Subject: mm: lock PGDAT_RECLAIM_LOCKED with acquire memory ordering
has been removed from the -mm tree. Its filename was
mm-lock-pgdat_reclaim_locked-with-acquire-memory-ordering.patch
This patch was dropped because it was merged into the mm-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
------------------------------------------------------
From: Mathieu Desnoyers <[email protected]>
Subject: mm: lock PGDAT_RECLAIM_LOCKED with acquire memory ordering
Date: Wed, 12 Mar 2025 10:10:14 -0400
The PGDAT_RECLAIM_LOCKED bit is used to provide mutual exclusion of node reclaim for struct pglist_data using a single bit.
Use test_and_set_bit_lock rather than test_and_set_bit to test-and-set PGDAT_RECLAIM_LOCKED with an acquire memory ordering semantic.
This changes the "lock" acquisition from a full barrier to an acquire memory ordering, which is weaker. The acquire semi-permeable barrier paired with the release on unlock is sufficient for this mutual exclusion use-case.
No behavior change intended other than to reduce overhead by using the appropriate barrier.
---
mm/vmscan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
mm/vmscan.c renamed from mm/vmscan.c~mm-lock-pgdat_reclaim_locked-with-acquire-memory-ordering +1 -1
@@ -7577,7 +7577,7 @@ int node_reclaim(struct pglist_data *pgdif (node_state (pgdat->node_id,N_CPU ) && pgdat->node_id !=numa_node_id ())return NODE_RECLAIM_NOSCAN ; -if (test_and_set_bit (PGDAT_RECLAIM_LOCKED , &pgdat->flags)) +if (test_and_set_bit_lock (PGDAT_RECLAIM_LOCKED , &pgdat->flags))return NODE_RECLAIM_NOSCAN ; ret =__node_reclaim (pgdat, gfp_mask, order);
_
Patches currently in -mm which might be from [email protected] are