From 3541a2b06ecd78ba333188df04368dcf97273d6a Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 20 Jul 2026 06:23:45 -0700 Subject: [PATCH] mm/kmemleak: report RCU-tasks quiescent states during the scan kmemleak_scan() can run for ages on large debug kernels. It was causing some soft-lockups which I got fixed with commit 3175fcfec8b16baeb ("mm/kmemleak: avoid soft lockup when scanning task stacks") with our beloved cond_resched(). I've got the fix above deployed in the Meta fleet, and now I am seeing: INFO: rcu_tasks detected stalls on tasks: task:kmemleak state:R ... nvcsw: 274/274 holdout: 1 idle_cpu: -1/3 scan_block scan_gray_list kmemleak_scan and, worse, blocks the callers waiting on that grace period. Here a BPF struct_ops map free, which waits via synchronize_rcu_mult(call_rcu, call_rcu_tasks), is stuck long enough to also trip the hung task check: INFO: task kworker/...:bpf_map_free_deferred blocked for 122 seconds __wait_rcu_gp bpf_struct_ops_map_free Then I've learned that cond_resched() is not an RCU-tasks quiescent state, so, we need to use stronger primitives. Use cond_resched_tasks_rcu_qs() at the scan reschedule points so the scan reports an RCU-tasks quiescent state as it proceeds. Inspired by commit b96285e10aad ("tracing: Have osnoise_main() add a quiescent state for task rcu"). Link: https://lore.kernel.org/20260720-kmemleak_rcu_task-v1-1-5b460ade777d@debian.org Fixes: c4b28963fd79 ("mm/kmemleak: rely on rcu for task stack scanning") Signed-off-by: Breno Leitao Reviewed-by: Paul E. McKenney Reviewed-by: SJ Park Reviewed-by: Catalin Marinas Cc: Breno Leitao Cc: Puranjay Mohan Cc: Signed-off-by: Andrew Morton --- mm/kmemleak.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index e96e9efd19b0..0a6045c857d6 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1571,7 +1571,7 @@ static int scan_large_block(void *start, void *end) if (scan_block(start, next, NULL)) return 1; start = next; - cond_resched(); + cond_resched_tasks_rcu_qs(); } return 0; @@ -1608,7 +1608,7 @@ static void scan_object(struct kmemleak_object *object) scan_block(start, end, object); raw_spin_unlock_irqrestore(&object->lock, flags); - cond_resched(); + cond_resched_tasks_rcu_qs(); raw_spin_lock_irqsave(&object->lock, flags); if (!(object->flags & OBJECT_ALLOCATED)) break; @@ -1630,7 +1630,7 @@ static void scan_object(struct kmemleak_object *object) break; raw_spin_unlock_irqrestore(&object->lock, flags); - cond_resched(); + cond_resched_tasks_rcu_qs(); raw_spin_lock_irqsave(&object->lock, flags); } while (object->flags & OBJECT_ALLOCATED); } else { @@ -1658,7 +1658,7 @@ static void scan_gray_list(void) */ object = list_entry(gray_list.next, typeof(*object), gray_list); while (&object->gray_list != &gray_list) { - cond_resched(); + cond_resched_tasks_rcu_qs(); /* may add new objects to the list */ if (!scan_should_stop()) @@ -1693,7 +1693,7 @@ static void kmemleak_cond_resched(struct kmemleak_object *object) raw_spin_unlock_irq(&kmemleak_lock); rcu_read_unlock(); - cond_resched(); + cond_resched_tasks_rcu_qs(); rcu_read_lock(); raw_spin_lock_irq(&kmemleak_lock); @@ -1738,7 +1738,7 @@ static void kmemleak_scan_task_stacks(void) } put_task_struct(p); } - cond_resched(); + cond_resched_tasks_rcu_qs(); } while (pid && !stop); } @@ -1915,7 +1915,7 @@ static void kmemleak_scan(void) struct page *page = pfn_to_online_page(pfn); if (!(pfn & 63)) - cond_resched(); + cond_resched_tasks_rcu_qs(); if (!page) continue;