sched_ext: Hook up hardlockup detector

A poorly behaving BPF scheduler can trigger hard lockup. For example, on a
large system with many tasks pinned to different subsets of CPUs, if the BPF
scheduler puts all tasks in a single DSQ and lets all CPUs at it, the DSQ lock
can be contended to the point where hardlockup triggers. Unfortunately,
hardlockup can be the first signal out of such situations, thus requiring
hardlockup handling.

Hook scx_hardlockup() into the hardlockup detector to try kicking out the
current scheduler in an attempt to recover the system to a good state. The
handling strategy can delay watchdog taking its own action by one polling
period; however, given that the only remediation for hardlockup is crash, this
is likely an acceptable trade-off.

v2: Add missing dummy scx_hardlockup() definition for
    !CONFIG_SCHED_CLASS_EXT (kernel test bot).

Reported-by: Dan Schatzberg <schatzberg.dan@gmail.com>
Cc: Emil Tsalapatis <etsal@meta.com>
Cc: Douglas Anderson <dianders@chromium.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

Author: htejun

include/linux/sched/ext.h

@@ -223,13 +223,15 @@ struct sched_ext_entity {
 void sched_ext_dead(struct task_struct *p);
 void print_scx_info(const char *log_lvl, struct task_struct *p);
 void scx_softlockup(u32 dur_s);
+bool scx_hardlockup(void);
 bool scx_rcu_cpu_stall(void);
 
 #else	/* !CONFIG_SCHED_CLASS_EXT */
 
 static inline void sched_ext_dead(struct task_struct *p) {}
 static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
 static inline void scx_softlockup(u32 dur_s) {}
+static inline bool scx_hardlockup(void) { return false; }
 static inline bool scx_rcu_cpu_stall(void) { return false; }
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */

kernel/sched/ext.c

@@ -3711,6 +3711,24 @@ void scx_softlockup(u32 dur_s)
 			smp_processor_id(), dur_s);
 }
 
+/**
+ * scx_hardlockup - sched_ext hardlockup handler
+ *
+ * A poorly behaving BPF scheduler can trigger hard lockup by e.g. putting
+ * numerous affinitized tasks in a single queue and directing all CPUs at it.
+ * Try kicking out the current scheduler in an attempt to recover the system to
+ * a good state before taking more drastic actions.
+ */
+bool scx_hardlockup(void)
+{
+	if (!handle_lockup("hard lockup - CPU %d", smp_processor_id()))
+		return false;
+
+	printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n",
+			smp_processor_id());
+	return true;
+}
+
 /**
  * scx_bypass - [Un]bypass scx_ops and guarantee forward progress
  * @bypass: true for bypass, false for unbypass

kernel/watchdog.c

@@ -196,6 +196,15 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
 #ifdef CONFIG_SYSFS
 		++hardlockup_count;
 #endif
+		/*
+		 * A poorly behaving BPF scheduler can trigger hard lockup by
+		 * e.g. putting numerous affinitized tasks in a single queue and
+		 * directing all CPUs at it. The following call can return true
+		 * only once when sched_ext is enabled and will immediately
+		 * abort the BPF scheduler and print out a warning message.
+		 */
+		if (scx_hardlockup())
+			return;
 
 		/* Only print hardlockups once. */
 		if (per_cpu(watchdog_hardlockup_warned, cpu))