tracing/timerlat: Drop interface_lock in stop_kthread()

stop_kthread() is the offline callback for "trace/osnoise:online", since
commit 5bfbcd1ee57b ("tracing/timerlat: Add interface_lock around clearing
of kthread in stop_kthread()"), the following ABBA deadlock scenario is
introduced:

T1                            | T2 [BP]               | T3 [AP]
osnoise_hotplug_workfn()      | work_for_cpu_fn()     | cpuhp_thread_fun()
                              |   _cpu_down()         |   osnoise_cpu_die()
  mutex_lock(&interface_lock) |                       |     stop_kthread()
                              |     cpus_write_lock() |       mutex_lock(&interface_lock)
  cpus_read_lock()            |     cpuhp_kick_ap()   |

As the interface_lock here in just for protecting the "kthread" field of
the osn_var, use xchg() instead to fix this issue. Also use
for_each_online_cpu() back in stop_per_cpu_kthreads() as it can take
cpu_read_lock() again.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20240924094515.3561410-3-liwei391@huawei.com
Fixes: 5bfbcd1ee57b ("tracing/timerlat: Add interface_lock around clearing of kthread in stop_kthread()")
Signed-off-by: Wei Li <liwei391@huawei.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
index d1a539913a5f5cd193394a4ee04ee701a0a87d12..e22567174dd31de9363185d46e302d371df42d59 100644 (file)
--- a/kernel/trace/trace_osnoise.c
+++ b/kernel/trace/trace_osnoise.c
@@ -1953,12 +1953,8 @@ static void stop_kthread(unsigned int cpu)
 {
        struct task_struct *kthread;
 
-       mutex_lock(&interface_lock);
-       kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+       kthread = xchg_relaxed(&(per_cpu(per_cpu_osnoise_var, cpu).kthread), NULL);
        if (kthread) {
-               per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
-               mutex_unlock(&interface_lock);
-
                if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) &&
                    !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) {
                        kthread_stop(kthread);
@@ -1972,7 +1968,6 @@ static void stop_kthread(unsigned int cpu)
                        put_task_struct(kthread);
                }
        } else {
-               mutex_unlock(&interface_lock);
                /* if no workload, just return */
                if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
                        /*
@@ -1994,8 +1989,12 @@ static void stop_per_cpu_kthreads(void)
 {
        int cpu;
 
-       for_each_possible_cpu(cpu)
+       cpus_read_lock();
+
+       for_each_online_cpu(cpu)
                stop_kthread(cpu);
+
+       cpus_read_unlock();
 }
 
 /*