From 5d10d4e19e6daa487f0cd0ea6cba472325de92f9 Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Mon, 15 Jun 2026 10:49:06 -0700 Subject: [PATCH] mm/kmemleak: avoid soft lockup when scanning task stacks Patch series "mm/kmemleak: avoid soft lockup when scanning task", v3. kmemleak_scan() scans every task stack under one rcu_read_lock() with no reschedule point, which can trip the soft lockup watchdog on hosts with very many threads. That prints the following message, depending on the workload+host configuration: watchdog: BUG: soft lockup - CPU#35 stuck for 22s! [kmemleak:537] scan_block kmemleak_scan kmemleak_scan_thread kthread Patch 1 walks the tasks with find_ge_pid() so the scan reschedules between tasks Patches 2-3 let the scan loops stop early once a scan is interrupted. This patch (of 3): kmemleak_scan() walks every thread and scans its kernel stack under a single rcu_read_lock() with no reschedule point. On a host with very many threads -- amplified by KASAN/lockdep in debug builds -- this loop can hog a CPU long enough to trip the soft lockup watchdog: watchdog: BUG: soft lockup - CPU#35 stuck for 22s! [kmemleak:537] scan_block kmemleak_scan kmemleak_scan_thread kthread A cond_resched() cannot be added directly: the loop runs inside an RCU read-side critical section. Walk the tasks one PID at a time with find_ge_pid(), taking the RCU read lock only to look up and pin each task. The stack is then scanned with no lock held, so cond_resched() runs between tasks and the scan stops early on scan_should_stop(). This follows the next_tgid()/task_seq_get_next() iteration pattern and keeps each RCU critical section short. Link: https://lore.kernel.org/20260615-kmemleak-stack-resched-v3-0-acecd7d7fd92@debian.org Link: https://lore.kernel.org/20260615-kmemleak-stack-resched-v3-1-acecd7d7fd92@debian.org Fixes: c4b28963fd79 ("mm/kmemleak: rely on rcu for task stack scanning") Signed-off-by: Breno Leitao Reviewed-by: Catalin Marinas Reviewed-by: Davidlohr Bueso Reviewed-by: Lance Yang Reviewed-by: Oleg Nesterov Cc: Qian Cai Cc: SeongJae Park Cc: Signed-off-by: Andrew Morton --- mm/kmemleak.c | 51 ++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 38 insertions(+), 13 deletions(-) diff --git a/mm/kmemleak.c b/mm/kmemleak.c index e196f53f9b46..16b72cead07d 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1696,6 +1696,42 @@ static void kmemleak_cond_resched(struct kmemleak_object *object) put_object(object); } +/* + * Scan all task kernel stacks, rescheduling between tasks. Each task is looked + * up and pinned within its own RCU read-side section, so no lock is held across + * the scan and the walk cannot trip the soft lockup watchdog. + */ +static void kmemleak_scan_task_stacks(void) +{ + struct pid *pid; + int nr = 1; + + do { + struct task_struct *p = NULL; + + rcu_read_lock(); + pid = find_ge_pid(nr, &init_pid_ns); + if (pid) { + nr = pid_nr(pid) + 1; + p = pid_task(pid, PIDTYPE_PID); + if (p) + get_task_struct(p); + } + rcu_read_unlock(); + + if (p) { + void *stack = try_get_task_stack(p); + + if (stack) { + scan_block(stack, stack + THREAD_SIZE, NULL); + put_task_stack(p); + } + put_task_struct(p); + } + cond_resched(); + } while (pid && !scan_should_stop()); +} + /* * Print one leak inline. The hex dump is gated on OBJECT_ALLOCATED so it * does not touch user memory that was freed concurrently; the rest of the @@ -1885,19 +1921,8 @@ static void kmemleak_scan(void) /* * Scanning the task stacks (may introduce false negatives). */ - if (kmemleak_stack_scan) { - struct task_struct *p, *g; - - rcu_read_lock(); - for_each_process_thread(g, p) { - void *stack = try_get_task_stack(p); - if (stack) { - scan_block(stack, stack + THREAD_SIZE, NULL); - put_task_stack(p); - } - } - rcu_read_unlock(); - } + if (kmemleak_stack_scan) + kmemleak_scan_task_stacks(); /* * Scan the objects already referenced from the sections scanned