watchdog/core: Create new thread handling infrastructure

The lockup detector reconfiguration tears down all watchdog threads when
the watchdog is disabled and sets them up again when its enabled.

That's a pointless exercise. The watchdog threads are not consuming an
insane amount of resources, so it's enough to set them up at init time and
keep them in parked position when the watchdog is disabled and unpark them
when it is reenabled. The smpboot thread infrastructure takes care of
keeping the force parked threads in place even across cpu hotplug.

Another horrible mechanism are the open coded park/unpark loops which are
used for reconfiguration of the watchdog. The smpboot infrastructure allows
exactly the same via smpboot_update_cpumask_thread_percpu(), which is cpu
hotplug safe. Using that instead of the open coded loops allows to get rid
of the hotplug locking mess in the watchdog code.

Implement a clean infrastructure which allows to replace the open coded
nonsense.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194147.377182587@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 75 insertions, 0 deletions

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 8935a3a4c2fb..b35518375fb7 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -139,6 +139,9 @@ unsigned int __read_mostly softlockup_panic =
                         CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 int __read_mostly soft_watchdog_enabled;
 
+struct cpumask watchdog_allowed_mask __read_mostly;
+static bool softlockup_threads_initialized __read_mostly;
+
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -584,12 +587,84 @@ static void watchdog_disable_all_cpus(void)
         }
 }
 
+static void softlockup_update_smpboot_threads(void)
+{
+        lockdep_assert_held(&watchdog_mutex);
+
+        if (!softlockup_threads_initialized)
+                return;
+
+        smpboot_update_cpumask_percpu_thread(&watchdog_threads,
+                                             &watchdog_allowed_mask);
+        __lockup_detector_cleanup();
+}
+
+/* Temporarily park all watchdog threads */
+static void softlockup_park_all_threads(void)
+{
+        cpumask_clear(&watchdog_allowed_mask);
+        softlockup_update_smpboot_threads();
+}
+
+/*
+ * Park threads which are not longer enabled and unpark threads which have
+ * been newly enabled.
+ */
+static void softlockup_update_threads(void)
+{
+        cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+        softlockup_update_smpboot_threads();
+}
+
+static void softlockup_reconfigure_threads(bool enabled)
+{
+        softlockup_park_all_threads();
+        set_sample_period();
+        if (enabled)
+                softlockup_update_threads();
+}
+
+/*
+ * Create the watchdog thread infrastructure.
+ *
+ * The threads are not unparked as watchdog_allowed_mask is empty.  When
+ * the threads are sucessfully initialized, take the proper locks and
+ * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
+ */
+static __init void softlockup_init_threads(void)
+{
+        int ret;
+
+        /*
+         * If sysctl is off and watchdog got disabled on the command line,
+         * nothing to do here.
+         */
+        if (!IS_ENABLED(CONFIG_SYSCTL) &&
+            !(watchdog_enabled && watchdog_thresh))
+                return;
+
+        ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
+                                                     &watchdog_allowed_mask);
+        if (ret) {
+                pr_err("Failed to initialize soft lockup detector threads\n");
+                return;
+        }
+
+        mutex_lock(&watchdog_mutex);
+        softlockup_threads_initialized = true;
+        softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh);
+        mutex_unlock(&watchdog_mutex);
+}
+
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline int watchdog_park_threads(void) { return 0; }
 static inline void watchdog_unpark_threads(void) { }
 static inline int watchdog_enable_all_cpus(void) { return 0; }
 static inline void watchdog_disable_all_cpus(void) { }
 static inline void set_sample_period(void) { }
+static inline void softlockup_init_threads(void) { }
+static inline void softlockup_update_threads(void) { }
+static inline void softlockup_reconfigure_threads(bool enabled) { }
 #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
 static void __lockup_detector_cleanup(void)