watchdog/perf: adapt the watchdog_perf interface for async model

When lockup_detector_init()->watchdog_hardlockup_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 and try to initialize the
watchdog once again later.  The delayed probe is called using workqueues. 
It need to allocate memory and must be proceed in a normal context.  The
delayed probe is able to use if watchdog_hardlockup_probe() returns
non-zero which means the return code returned when PMU is not ready yet.

Provide an API - lockup_detector_retry_init() for anyone who needs to
delayed init lockup detector if they had ever failed at
lockup_detector_init().

The original assumption is: nobody should use delayed probe after
lockup_detector_check() which has __init attribute.  That is, anyone uses
this API must call between lockup_detector_init() and
lockup_detector_check(), and the caller must have __init attribute

Link: https://lkml.kernel.org/r/20230519101840.v5.16.If4ad5dd5d09fb1309cebf8bcead4b6a5a7758ca7@changeid
Reviewed-by: Petr Mladek <[email protected]>
Co-developed-by: Pingfan Liu <[email protected]>
Signed-off-by: Pingfan Liu <[email protected]>
Signed-off-by: Lecopzer Chen <[email protected]>
Signed-off-by: Douglas Anderson <[email protected]>
Suggested-by: Petr Mladek <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Chen-Yu Tsai <[email protected]>
Cc: Christophe Leroy <[email protected]>
Cc: Colin Cross <[email protected]>
Cc: Daniel Thompson <[email protected]>
Cc: "David S. Miller" <[email protected]>
Cc: Guenter Roeck <[email protected]>
Cc: Ian Rogers <[email protected]>
Cc: Marc Zyngier <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Masayoshi Mizuma <[email protected]>
Cc: Matthias Kaehlcke <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: "Ravi V. Shankar" <[email protected]>
Cc: Ricardo Neri <[email protected]>
Cc: Stephane Eranian <[email protected]>
Cc: Stephen Boyd <[email protected]>
Cc: Sumit Garg <[email protected]>
Cc: Tzung-Bi Shih <[email protected]>
Cc: Will Deacon <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

2 files changed, 68 insertions, 1 deletions

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 28e65fd1de13..83577ae736cc 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -13,6 +13,7 @@
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 void lockup_detector_init(void);
+void lockup_detector_retry_init(void);
 void lockup_detector_soft_poweroff(void);
 void lockup_detector_cleanup(void);
 
@@ -32,6 +33,7 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 
 #else /* CONFIG_LOCKUP_DETECTOR */
 static inline void lockup_detector_init(void) { }
+static inline void lockup_detector_retry_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
 static inline void lockup_detector_cleanup(void) { }
 #endif /* !CONFIG_LOCKUP_DETECTOR */
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 10947c835079..237990e8d345 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -208,7 +208,13 @@ void __weak watchdog_hardlockup_enable(unsigned int cpu) { }
 
 void __weak watchdog_hardlockup_disable(unsigned int cpu) { }
 
-/* Return 0, if a hardlockup watchdog is available. Error code otherwise */
+/*
+ * Watchdog-detector specific API.
+ *
+ * Return 0 when hardlockup watchdog is available, negative value otherwise.
+ * Note that the negative value means that a delayed probe might
+ * succeed later.
+ */
 int __weak __init watchdog_hardlockup_probe(void)
 {
 	/*
@@ -954,6 +960,62 @@ static void __init watchdog_sysctl_init(void)
 #define watchdog_sysctl_init() do { } while (0)
 #endif /* CONFIG_SYSCTL */
 
+static void __init lockup_detector_delay_init(struct work_struct *work);
+static bool allow_lockup_detector_init_retry __initdata;
+
+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;
+
+	ret = watchdog_hardlockup_probe();
+	if (ret) {
+		pr_info("Delayed init of the lockup detector failed: %d\n", ret);
+		pr_info("Hard watchdog permanently disabled\n");
+		return;
+	}
+
+	allow_lockup_detector_init_retry = false;
+
+	watchdog_hardlockup_available = true;
+	lockup_detector_setup();
+}
+
+/*
+ * lockup_detector_retry_init - retry init lockup detector if possible.
+ *
+ * Retry hardlockup detector init. It is useful when it requires some
+ * functionality that has to be initialized later on a particular
+ * platform.
+ */
+void __init lockup_detector_retry_init(void)
+{
+	/* Must be called before late init calls */
+	if (!allow_lockup_detector_init_retry)
+		return;
+
+	schedule_work(&detector_work);
+}
+
+/*
+ * Ensure that optional delayed hardlockup init is proceed before
+ * the init code and memory is freed.
+ */
+static int __init lockup_detector_check(void)
+{
+	/* Prevent any later retry. */
+	allow_lockup_detector_init_retry = false;
+
+	/* Make sure no work is pending. */
+	flush_work(&detector_work);
+
+	return 0;
+
+}
+late_initcall_sync(lockup_detector_check);
+
 void __init lockup_detector_init(void)
 {
 	if (tick_nohz_full_enabled())
@@ -964,6 +1026,9 @@ void __init lockup_detector_init(void)
 
 	if (!watchdog_hardlockup_probe())
 		watchdog_hardlockup_available = true;
+	else
+		allow_lockup_detector_init_retry = true;
+
 	lockup_detector_setup();
 	watchdog_sysctl_init();
 }