[PATCH v4 1/2] sched/debug: Try trigger_single_cpu_backtrace(cpu) in dump_cpu_task()

[Zhen Lei <thunder.leizhen@huawei.com>]

Function trigger_all_cpu_backtrace() uses NMI to dump the stack traces
of other CPU, it should actually be one of the ways to implement
dump_cpu_task(). So try it first in dump_cpu_task(). At the same time,
unnecessary duplicate code of upper-layer functions is eliminated.

There is also a call to dump_cpu_task() in
synchronize_rcu_expedited_wait(), which should also try to use NMI to
dump the stack traces first. It is currently the result of this
adjustment, so leave it unchanged.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
---
 kernel/rcu/tree_stall.h | 8 +++-----
 kernel/sched/core.c     | 3 +++
 kernel/smp.c            | 3 +--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index a001e1e7a99269c..80749d257ac2f78 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -368,7 +368,7 @@ static void rcu_dump_cpu_stacks(void)
 			if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) {
 				if (cpu_is_offline(cpu))
 					pr_err("Offline CPU %d blocking current GP.\n", cpu);
-				else if (!trigger_single_cpu_backtrace(cpu))
+				else
 					dump_cpu_task(cpu);
 			}
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -486,8 +486,7 @@ static void rcuc_kthread_dump(struct rcu_data *rdp)
 
 	pr_err("%s kthread starved for %ld jiffies\n", rcuc->comm, j);
 	sched_show_task(rcuc);
-	if (!trigger_single_cpu_backtrace(cpu))
-		dump_cpu_task(cpu);
+	dump_cpu_task(cpu);
 }
 
 /* Complain about starvation of grace-period kthread.  */
@@ -515,8 +514,7 @@ static void rcu_check_gp_kthread_starvation(void)
 					pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu);
 				} else  {
 					pr_err("Stack dump where RCU GP kthread last ran:\n");
-					if (!trigger_single_cpu_backtrace(cpu))
-						dump_cpu_task(cpu);
+					dump_cpu_task(cpu);
 				}
 			}
 			wake_up_process(gpk);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index df8fe433642fa30..0e82073020bf0d1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -11145,6 +11145,9 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 
 void dump_cpu_task(int cpu)
 {
+	if (trigger_single_cpu_backtrace(cpu))
+		return;
+
 	pr_info("Task dump for CPU %d:\n", cpu);
 	sched_show_task(cpu_curr(cpu));
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index dd215f439426449..56ca958364aebeb 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -370,8 +370,7 @@ static bool csd_lock_wait_toolong(struct __call_single_data *csd, u64 ts0, u64 *
 	if (cpu >= 0) {
 		if (static_branch_unlikely(&csdlock_debug_extended))
 			csd_lock_print_extended(csd, cpu);
-		if (!trigger_single_cpu_backtrace(cpu))
-			dump_cpu_task(cpu);
+		dump_cpu_task(cpu);
 		if (!cpu_cur_csd) {
 			pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu);
 			arch_send_call_function_single_ipi(cpu);
-- 
2.25.1