[31/32] rcu-tasks: Be more patient for RCU Tasks boot-time testing

Commit Message

Paul E. McKenney June 20, 2022, 10:54 p.m. UTC

The RCU-Tasks family of grace-period primitives can take some time to
complete, and the amount of time can depend on the exact hardware and
software configuration.  Some configurations boot up fast enough that the
RCU-Tasks verification process gets false-positive failures.  This commit
therefore allows up to 30 seconds for the grace periods to complete, with
this value adjustable downwards using the rcupdate.rcu_task_stall_timeout
kernel boot parameter.

Reported-by: Matthew Wilcox <[e-mail]>
Reported-by: Zhouyi Zhou <[e-mail]>
Signed-off-by: Paul E. McKenney <[e-mail]>
Tested-by: Zhouyi Zhou <[e-mail]>
Tested-by: Mark Rutland <[e-mail]>
---
 kernel/rcu/tasks.h | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

Patch

diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index df6b2cb2f205d..fcbd0ec33c866 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -145,6 +145,7 @@  static int rcu_task_ipi_delay __read_mostly = RCU_TASK_IPI_DELAY;
 module_param(rcu_task_ipi_delay, int, 0644);
 
 /* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */
+#define RCU_TASK_BOOT_STALL_TIMEOUT (HZ * 30)
 #define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)
 static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
 module_param(rcu_task_stall_timeout, int, 0644);
@@ -1776,23 +1777,24 @@  struct rcu_tasks_test_desc {
 	struct rcu_head rh;
 	const char *name;
 	bool notrun;
+	unsigned long runstart;
 };
 
 static struct rcu_tasks_test_desc tests[] = {
 	{
 		.name = "call_rcu_tasks()",
 		/* If not defined, the test is skipped. */
-		.notrun = !IS_ENABLED(CONFIG_TASKS_RCU),
+		.notrun = IS_ENABLED(CONFIG_TASKS_RCU),
 	},
 	{
 		.name = "call_rcu_tasks_rude()",
 		/* If not defined, the test is skipped. */
-		.notrun = !IS_ENABLED(CONFIG_TASKS_RUDE_RCU),
+		.notrun = IS_ENABLED(CONFIG_TASKS_RUDE_RCU),
 	},
 	{
 		.name = "call_rcu_tasks_trace()",
 		/* If not defined, the test is skipped. */
-		.notrun = !IS_ENABLED(CONFIG_TASKS_TRACE_RCU)
+		.notrun = IS_ENABLED(CONFIG_TASKS_TRACE_RCU)
 	}
 };
 
@@ -1803,23 +1805,28 @@  static void test_rcu_tasks_callback(struct rcu_head *rhp)
 
 	pr_info("Callback from %s invoked.\n", rttd->name);
 
-	rttd->notrun = true;
+	rttd->notrun = false;
 }
 
 static void rcu_tasks_initiate_self_tests(void)
 {
+	unsigned long j = jiffies;
+
 	pr_info("Running RCU-tasks wait API self tests\n");
 #ifdef CONFIG_TASKS_RCU
+	tests[0].runstart = j;
 	synchronize_rcu_tasks();
 	call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback);
 #endif
 
 #ifdef CONFIG_TASKS_RUDE_RCU
+	tests[1].runstart = j;
 	synchronize_rcu_tasks_rude();
 	call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback);
 #endif
 
 #ifdef CONFIG_TASKS_TRACE_RCU
+	tests[2].runstart = j;
 	synchronize_rcu_tasks_trace();
 	call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback);
 #endif
@@ -1829,11 +1836,18 @@  static int rcu_tasks_verify_self_tests(void)
 {
 	int ret = 0;
 	int i;
+	unsigned long bst = rcu_task_stall_timeout;
 
+	if (bst <= 0 || bst > RCU_TASK_BOOT_STALL_TIMEOUT)
+		bst = RCU_TASK_BOOT_STALL_TIMEOUT;
 	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		if (!tests[i].notrun) {		// still hanging.
-			pr_err("%s has been failed.\n", tests[i].name);
-			ret = -1;
+		while (tests[i].notrun) {		// still hanging.
+			if (time_after(jiffies, tests[i].runstart + bst)) {
+				pr_err("%s has failed boot-time tests.\n", tests[i].name);
+				ret = -1;
+				break;
+			}
+			schedule_timeout_uninterruptible(1);
 		}
 	}