[PATCH v2 4/5] kernel/watchdog: Adapt the watchdog_hld interface for async model

[Lecopzer Chen]

When lockup_detector_init()->watchdog_nmi_probe(), PMU may be not ready
yet. E.g. on arm64, PMU is not ready until
device_initcall(armv8_pmu_driver_init).  And it is deeply integrated
with the driver model and cpuhp. Hence it is hard to push this
initialization before smp_init().

But it is easy to take an opposite approach by enabling watchdog_hld to
get the capability of PMU async.

The async model is achieved by expanding watchdog_nmi_probe() with
-EBUSY, and a re-initializing work_struct which waits on a wait_queue_head.

Co-developed-by: Pingfan Liu <kernelfans@xxxxxxxxx>
Signed-off-by: Pingfan Liu <kernelfans@xxxxxxxxx>
Signed-off-by: Lecopzer Chen <lecopzer.chen@xxxxxxxxxxxx>
Suggested-by: Petr Mladek <pmladek@xxxxxxxx>
---
 include/linux/nmi.h |  3 +++
 kernel/watchdog.c   | 62 +++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 63 insertions(+), 2 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index b7bcd63c36b4..cc7df31be9db 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -118,6 +118,9 @@ static inline int hardlockup_detector_perf_init(void) { return 0; }
 
 void watchdog_nmi_stop(void);
 void watchdog_nmi_start(void);
+
+extern bool lockup_detector_pending_init;
+extern struct wait_queue_head hld_detector_wait;
 int watchdog_nmi_probe(void);
 void watchdog_nmi_enable(unsigned int cpu);
 void watchdog_nmi_disable(unsigned int cpu);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b71d434cf648..49bdcaf5bd8f 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -103,7 +103,11 @@ void __weak watchdog_nmi_disable(unsigned int cpu)
 	hardlockup_detector_perf_disable();
 }
 
-/* Return 0, if a NMI watchdog is available. Error code otherwise */
+/*
+ * Arch specific API. Return 0, if a NMI watchdog is available. -EBUSY if not
+ * ready, and arch code should wake up hld_detector_wait when ready. Other
+ * negative value if not support.
+ */
 int __weak __init watchdog_nmi_probe(void)
 {
 	return hardlockup_detector_perf_init();
@@ -839,16 +843,70 @@ static void __init watchdog_sysctl_init(void)
 #define watchdog_sysctl_init() do { } while (0)
 #endif /* CONFIG_SYSCTL */
 
+static void lockup_detector_delay_init(struct work_struct *work);
+bool lockup_detector_pending_init __initdata;
+
+struct wait_queue_head hld_detector_wait __initdata =
+		__WAIT_QUEUE_HEAD_INITIALIZER(hld_detector_wait);
+
+static struct work_struct detector_work __initdata =
+		__WORK_INITIALIZER(detector_work, lockup_detector_delay_init);
+
+static void __init lockup_detector_delay_init(struct work_struct *work)
+{
+	int ret;
+
+	wait_event(hld_detector_wait,
+			lockup_detector_pending_init == false);
+
+	/*
+	 * Here, we know the PMU should be ready, so set pending to true to
+	 * inform watchdog_nmi_probe() that it shouldn't return -EBUSY again.
+	 */
+	lockup_detector_pending_init = true;
+	ret = watchdog_nmi_probe();
+	if (ret) {
+		pr_info("Delayed init of the lockup detector failed: %d\n", ret);
+		pr_info("Perf NMI watchdog permanently disabled\n");
+		return;
+	}
+
+	nmi_watchdog_available = true;
+	lockup_detector_setup();
+	lockup_detector_pending_init = false;
+}
+
+/* Ensure the check is called after the initialization of PMU driver */
+static int __init lockup_detector_check(void)
+{
+	if (!lockup_detector_pending_init)
+		return 0;
+
+	pr_info("Delayed init checking failed, retry for once.\n");
+	lockup_detector_pending_init = false;
+	wake_up(&hld_detector_wait);
+	return 0;
+}
+late_initcall_sync(lockup_detector_check);
+
 void __init lockup_detector_init(void)
 {
+	int ret;
+
 	if (tick_nohz_full_enabled())
 		pr_info("Disabling watchdog on nohz_full cores by default\n");
 
 	cpumask_copy(&watchdog_cpumask,
 		     housekeeping_cpumask(HK_FLAG_TIMER));
 
-	if (!watchdog_nmi_probe())
+	ret = watchdog_nmi_probe();
+	if (!ret)
 		nmi_watchdog_available = true;
+	else if (ret == -EBUSY) {
+		lockup_detector_pending_init = true;
+		queue_work_on(smp_processor_id(), system_wq, &detector_work);
+	}
+
 	lockup_detector_setup();
 	watchdog_sysctl_init();
 }
-- 
2.25.1