summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorBreno Leitao <leitao@debian.org>2026-09-03 13:49:08 -0400
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2026-09-07 17:37:25 +0200
commit59ebe7b0ff646071bbf6ef8e8208db9de209bc56 (patch)
tree67e50f36cdf4df751726ec11dbd28a048f78628e
parent3ee49d4dbd08a919f42016243b1d8bda4122981e (diff)
downloadlinux-stable-59ebe7b0ff646071bbf6ef8e8208db9de209bc56.tar.gz
linux-stable-59ebe7b0ff646071bbf6ef8e8208db9de209bc56.zip
mm/kmemleak: report RCU-tasks quiescent states during the scan
[ Upstream commit 3541a2b06ecd78ba333188df04368dcf97273d6a ] 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 <leitao@debian.org> Reviewed-by: Paul E. McKenney <paulmck@kernel.org> Reviewed-by: SJ Park <sj@kernel.org> Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> Cc: Breno Leitao <leitao@debian.org> Cc: Puranjay Mohan <puranjay@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [ adapted scan_large_block() to the branch’s existing void implementation without interruption propagation. ] Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-rw-r--r--mm/kmemleak.c14
1 files changed, 7 insertions, 7 deletions
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index bc79e293531b..e3c9dbde014b 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1569,7 +1569,7 @@ static void scan_large_block(void *start, void *end)
next = min(start + MAX_SCAN_SIZE, end);
scan_block(start, next, NULL);
start = next;
- cond_resched();
+ cond_resched_tasks_rcu_qs();
}
}
#endif
@@ -1604,7 +1604,7 @@ 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;
@@ -1626,7 +1626,7 @@ 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 {
@@ -1654,7 +1654,7 @@ 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())
@@ -1689,7 +1689,7 @@ 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);
@@ -1734,7 +1734,7 @@ static void kmemleak_scan_task_stacks(void)
}
put_task_struct(p);
}
- cond_resched();
+ cond_resched_tasks_rcu_qs();
} while (pid && !stop);
}
@@ -1908,7 +1908,7 @@ 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;