From d9850d9b0ebd8f027e01a22273b7e915248ade53 Mon Sep 17 00:00:00 2001
From: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Date: Tue, 9 Nov 2021 16:52:14 +0530
Subject: [PATCH] rcu-tasks: Inspect stalled task's trc state in locked state

References: bnc#1189998 (PREEMPT_RT prerequisite backports)
Patch-mainline: v5.17-rc0
Git-commit: 65b629e70489b810a108fe1155da4e41a5010534

On RCU tasks trace stall, inspect the RCU-tasks-trace specific
states of stalled task in locked down state, using try_invoke_
on_locked_down_task(), to get reliable trc state of a non-running
stalled task.

This was tested using the following command:

tools/testing/selftests/rcutorture/bin/kvm.sh --cpus 8 --configs TRACE01 \
--bootargs "rcutorture.torture_type=tasks-tracing rcutorture.stall_cpu=10 \
rcutorture.stall_cpu_block=1 rcupdate.rcu_task_stall_timeout=100" --trust-make

As expected, this produced the following console output for running and
sleeping tasks.

[   21.520291] INFO: rcu_tasks_trace detected stalls on tasks:
[   21.521292] P85: ... nesting: 1N cpu: 2
[   21.521966] task:rcu_torture_sta state:D stack:15080 pid:   85 ppid:     2
flags:0x00004000
[   21.523384] Call Trace:
[   21.523808]  __schedule+0x273/0x6e0
[   21.524428]  schedule+0x35/0xa0
[   21.524971]  schedule_timeout+0x1ed/0x270
[   21.525690]  ? del_timer_sync+0x30/0x30
[   21.526371]  ? rcu_torture_writer+0x720/0x720
[   21.527106]  rcu_torture_stall+0x24a/0x270
[   21.527816]  kthread+0x115/0x140
[   21.528401]  ? set_kthread_struct+0x40/0x40
[   21.529136]  ret_from_fork+0x22/0x30
[   21.529766]  1 holdouts
[   21.632300] INFO: rcu_tasks_trace detected stalls on tasks:
[   21.632345] rcu_torture_stall end.
[   21.633293] P85: .
[   21.633294] task:rcu_torture_sta state:R  running task stack:15080 pid:
85 ppid:     2 flags:0x00004000
[   21.633299] Call Trace:
[   21.633301]  ? vprintk_emit+0xab/0x180
[   21.633306]  ? vprintk_emit+0x11a/0x180
[   21.633308]  ? _printk+0x4d/0x69
[   21.633311]  ? __default_send_IPI_shortcut+0x1f/0x40

[ paulmck: Update to new v5.16 task_call_func() name. ]

Signed-off-by: Neeraj Upadhyay <quic_neeraju@quicinc.com>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
 kernel/rcu/tasks.h | 43 ++++++++++++++++++++++++++++++++++---------
 1 file changed, 34 insertions(+), 9 deletions(-)

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index c785dc17652e..0f672042151e 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -1132,25 +1132,50 @@ static void rcu_tasks_trace_postscan(struct list_head *hop)
 	// Any tasks that exit after this point will set ->trc_reader_checked.
 }
 
+/* Communicate task state back to the RCU tasks trace stall warning request. */
+struct trc_stall_chk_rdr {
+	int nesting;
+	int ipi_to_cpu;
+	u8 needqs;
+};
+
+static int trc_check_slow_task(struct task_struct *t, void *arg)
+{
+	struct trc_stall_chk_rdr *trc_rdrp = arg;
+
+	if (task_curr(t))
+		return false; // It is running, so decline to inspect it.
+	trc_rdrp->nesting = READ_ONCE(t->trc_reader_nesting);
+	trc_rdrp->ipi_to_cpu = READ_ONCE(t->trc_ipi_to_cpu);
+	trc_rdrp->needqs = READ_ONCE(t->trc_reader_special.b.need_qs);
+	return true;
+}
+
 /* Show the state of a task stalling the current RCU tasks trace GP. */
 static void show_stalled_task_trace(struct task_struct *t, bool *firstreport)
 {
 	int cpu;
+	struct trc_stall_chk_rdr trc_rdr;
+	bool is_idle_tsk = is_idle_task(t);
 
 	if (*firstreport) {
 		pr_err("INFO: rcu_tasks_trace detected stalls on tasks:\n");
 		*firstreport = false;
 	}
-	// FIXME: This should attempt to use try_invoke_on_nonrunning_task().
 	cpu = task_cpu(t);
-	pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
-		 t->pid,
-		 ".I"[READ_ONCE(t->trc_ipi_to_cpu) >= 0],
-		 ".i"[is_idle_task(t)],
-		 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
-		 READ_ONCE(t->trc_reader_nesting),
-		 " N"[!!READ_ONCE(t->trc_reader_special.b.need_qs)],
-		 cpu);
+	if (!task_call_func(t, trc_check_slow_task, &trc_rdr))
+		pr_alert("P%d: %c\n",
+			 t->pid,
+			 ".i"[is_idle_tsk]);
+	else
+		pr_alert("P%d: %c%c%c nesting: %d%c cpu: %d\n",
+			 t->pid,
+			 ".I"[trc_rdr.ipi_to_cpu >= 0],
+			 ".i"[is_idle_tsk],
+			 ".N"[cpu >= 0 && tick_nohz_full_cpu(cpu)],
+			 trc_rdr.nesting,
+			 " N"[!!trc_rdr.needqs],
+			 cpu);
 	sched_show_task(t);
 }