rcutorture: Add test_nmis module parameter

This commit adds a test_nmis module parameter to generate the specified
number of NMI stack backtraces 15 seconds apart.  This module parameter
can be used to test NMI delivery and accompanying diagnostics.

It also forces NMI backtraces in the case where the destination CPU is
idle, thus avoiding the occasional annoying failure to actually send
an NMI.

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

kernel/rcu/rcutorture.c

@@ -119,6 +119,7 @@ torture_param(int, stutter, 5, "Number of seconds to run/halt test");
 torture_param(int, test_boost, 1, "Test RCU prio boost: 0=no, 1=maybe, 2=yes.");
 torture_param(int, test_boost_duration, 4, "Duration of each boost test, seconds.");
 torture_param(int, test_boost_interval, 7, "Interval between boost tests, seconds.");
+torture_param(int, test_nmis, 0, "End-test NMI tests, 0 to disable.");
 torture_param(bool, test_no_idle_hz, true, "Test support for tickless idle CPUs");
 torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 
@@ -2358,7 +2359,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 "n_barrier_cbs=%d "
 		 "onoff_interval=%d onoff_holdoff=%d "
 		 "read_exit_delay=%d read_exit_burst=%d "
-		 "nocbs_nthreads=%d nocbs_toggle=%d\n",
+		 "nocbs_nthreads=%d nocbs_toggle=%d "
+		 "test_nmis=%d\n",
 		 torture_type, tag, nrealreaders, nfakewriters,
 		 stat_interval, verbose, test_no_idle_hz, shuffle_interval,
 		 stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter,
@@ -2369,7 +2371,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 		 n_barrier_cbs,
 		 onoff_interval, onoff_holdoff,
 		 read_exit_delay, read_exit_burst,
-		 nocbs_nthreads, nocbs_toggle);
+		 nocbs_nthreads, nocbs_toggle,
+		 test_nmis);
 }
 
 static int rcutorture_booster_cleanup(unsigned int cpu)
@@ -3273,6 +3276,25 @@ static void rcu_torture_read_exit_cleanup(void)
 	torture_stop_kthread(rcutorture_read_exit, read_exit_task);
 }
 
+static void rcutorture_test_nmis(int n)
+{
+	int cpu;
+	int dumpcpu;
+	int i;
+
+	for (i = 0; i < n; i++) {
+		preempt_disable();
+		cpu = smp_processor_id();
+		dumpcpu = cpu + 1;
+		if (dumpcpu >= nr_cpu_ids)
+			dumpcpu = 0;
+		pr_alert("%s: CPU %d invoking dump_cpu_task(%d)\n", __func__, cpu, dumpcpu);
+		dump_cpu_task(dumpcpu);
+		preempt_enable();
+		schedule_timeout_uninterruptible(15 * HZ);
+	}
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
@@ -3297,6 +3319,8 @@ rcu_torture_cleanup(void)
 		return;
 	}
 
+	rcutorture_test_nmis(test_nmis);
+
 	if (cur_ops->gp_kthread_dbg)
 		cur_ops->gp_kthread_dbg();
 	rcu_torture_read_exit_cleanup();

lib/nmi_backtrace.c

@@ -102,16 +102,11 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 		 * against other CPUs.
 		 */
 		printk_cpu_sync_get_irqsave(flags);
-		if (!READ_ONCE(backtrace_idle) && regs && cpu_in_idle(instruction_pointer(regs))) {
-			pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
-				cpu, (void *)instruction_pointer(regs));
-		} else {
-			pr_warn("NMI backtrace for cpu %d\n", cpu);
-			if (regs)
-				show_regs(regs);
-			else
-				dump_stack();
-		}
+		pr_warn("NMI backtrace for cpu %d\n", cpu);
+		if (regs)
+			show_regs(regs);
+		else
+			dump_stack();
 		printk_cpu_sync_put_irqrestore(flags);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;