From: Chen Wandun <chenwandun@lixiang.com>

Cgroup v2 doesn't have the concept of memory hardwall, only top_cpuset
has CS_MEM_EXCLUSIVE/CS_MEM_HARDWALL flags, nearest_hardwall_ancestor
always returns top_cpuset with all nodes set, so no need to acquire
callback_lock and scan up cpuset.

Suggested-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Chen Wandun <chenwandun@lixiang.com>

---
v1 --> v2:
use cpuset_v2 instead of is_in_v2_mode, suggested by Tejun.
---
 kernel/cgroup/cpuset.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index a48901a0416a..cbd9e7fc800e 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -4231,6 +4231,9 @@ bool cpuset_current_node_allowed(int node, gfp_t gfp_mask)
 	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
 		return false;
 
+	if (cpuset_v2())
+		return true;
+
 	/* Not hardwall and node outside mems_allowed: scan up cpusets */
 	spin_lock_irqsave(&callback_lock, flags);
 
-- 
2.43.0

Hello,

Applied to cgroup/for-7.2 after back-merging for-7.1-fixes to pick up
dde2f938d02f ("cgroup/cpuset: move PF_EXITING check before
__GFP_HARDWALL in cpuset_current_node_allowed()"), which was needed
as a dependency.

Thanks.

--
tejun