sched_ext: Bound per-task reenqueues and eject the owning scheduler

Unlike local reenqueues, cap rejections have no repeat limit. A
malfunctioning scheduler can keep re-inserting a task to a cid it lacks caps
on, cycling the task through reject and reenqueue. This was assumed safe
because a task that never runs trips the stall watchdog. However, the
reenqueue irq_work re-arms itself and outranks the timer vector, blocking
everything else on the CPU including stall detection and recovery, until the
NMI hardlockup detector fires.

Local reenqueues already have a repeat cap, SCX_REENQ_LOCAL_MAX_REPEAT,
which needs generalizing to cover all reenqueues. It also has an attribution
problem. Counted per-cpu on root, it tears down the whole hierarchy even
when a sub-scheduler caused the repeated reenqueues.

Generalize by bounding every reenqueue with one per-task counter. reenq_cnt
is bumped in scx_do_enqueue_task() on each SCX_ENQ_REENQ, the single path
every reenqueue producer passes through, and cleared in clr_task_runnable()
when the task is picked to run and in scx_disable_task() when it leaves the
scheduler's control. Past SCX_REENQ_MAX_REPEAT the task's owning scheduler
is ejected with a new SCX_EXIT_ERROR_REENQ and the task is left stranded to
be picked up during sched exit.

The SCX_EV_REENQ_LOCAL_REPEAT event becomes SCX_EV_REENQ_REPEAT, counting
repeat reenqueues from all sources.

v2: Count SCX_EV_REENQ_REPEAT only when a reenqueue leads to another
    reenqueue, not on every reenqueue.

v3: - Also clear reenq_cnt in scx_disable_task() so that the count doesn't
      carry over to the next owner across sched class switches, scheduler
      replacement or sub-scheduler rehoming (Andrea Righi).

    - Update the stale SCX_EV_REENQ_LOCAL_REPEAT references in sched-ext.rst
      (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

Documentation/scheduler/sched-ext.rst

@@ -106,7 +106,7 @@ counters. Each counter occupies one ``name value`` line:
     SCX_EV_ENQ_SKIP_EXITING 0
     SCX_EV_ENQ_SKIP_MIGRATION_DISABLED 0
     SCX_EV_REENQ_IMMED 0
-    SCX_EV_REENQ_LOCAL_REPEAT 0
+    SCX_EV_REENQ_REPEAT 0
     SCX_EV_REFILL_SLICE_DFL 456789
     SCX_EV_BYPASS_DURATION 0
     SCX_EV_BYPASS_DISPATCH 0
@@ -129,9 +129,9 @@ The counters are described in ``kernel/sched/ext/internal.h``; briefly:
   ``SCX_OPS_ENQ_MIGRATION_DISABLED`` is not set).
 * ``SCX_EV_REENQ_IMMED``: a task dispatched with ``SCX_ENQ_IMMED`` was
   re-enqueued because the target CPU was not available for immediate execution.
-* ``SCX_EV_REENQ_LOCAL_REPEAT``: a reenqueue of the local DSQ triggered
-  another reenqueue; recurring counts indicate incorrect ``SCX_ENQ_REENQ``
-  handling in the BPF scheduler.
+* ``SCX_EV_REENQ_REPEAT``: a reenqueue led to another reenqueue without the
+  task running in between; recurring counts indicate that the BPF scheduler
+  keeps re-deciding placements it can't honor.
 * ``SCX_EV_REFILL_SLICE_DFL``: a task's time slice was refilled with the
   default value (``SCX_SLICE_DFL``).
 * ``SCX_EV_BYPASS_DURATION``: total nanoseconds spent in bypass mode.

include/linux/sched/ext.h

@@ -198,6 +198,7 @@ struct sched_ext_entity {
 	u32			dsq_flags;	/* protected by DSQ lock */
 	u32			flags;		/* protected by rq lock */
 	u32			weight;
+	u32			reenq_cnt;	/* reenqueues since last run */
 	s32			sticky_cpu;
 	s32			holding_cpu;
 	s32			selected_cpu;

kernel/sched/ext/ext.c

@@ -1903,6 +1903,24 @@ void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	 */
 	p->scx.flags &= ~SCX_TASK_IMMED;
 
+	/*
+	 * A task reenqueued too many times without running means the scheduler
+	 * keeps re-deciding a placement it can't honor, e.g. re-inserting to a
+	 * cid it lacks caps on. Eject the owning scheduler and strand the task
+	 * to be picked up during sched exit.
+	 */
+	if (enq_flags & SCX_ENQ_REENQ) {
+		if (++p->scx.reenq_cnt > 1)
+			__scx_add_event(sch, SCX_EV_REENQ_REPEAT, 1);
+
+		if (unlikely(p->scx.reenq_cnt > SCX_REENQ_MAX_REPEAT)) {
+			__scx_exit(sch, SCX_EXIT_ERROR_REENQ, 0, cpu_of(rq),
+				   "%s[%d] reenqueued %u times without running",
+				   p->comm, p->pid, p->scx.reenq_cnt);
+			return;
+		}
+	}
+
 	/*
 	 * If !scx_rq_online(), we already told the BPF scheduler that the CPU
 	 * is offline and are just running the hotplug path. Don't bother the
@@ -2025,8 +2043,10 @@ static void clr_task_runnable(struct task_struct *p, bool reset_runnable_at)
 {
 	list_del_init(&p->scx.runnable_node);
 	WRITE_ONCE(p->scx.runnable_cpu, -1);
-	if (reset_runnable_at)
+	if (reset_runnable_at) {
 		p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
+		p->scx.reenq_cnt = 0;
+	}
 }
 
 static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_flags)
@@ -3669,6 +3689,7 @@ static void scx_disable_task(struct scx_sched *sch, struct task_struct *p)
 	 */
 	p->scx.dsq_vtime = 0;
 	set_task_slice(p, 0);
+	p->scx.reenq_cnt = 0;
 
 	/*
 	 * Verify the task is not in BPF scheduler's custody. If flag
@@ -4066,8 +4087,8 @@ static void process_ddsp_deferred_locals(struct rq *rq)
  * Reenqueued tasks go through ops.enqueue() with %SCX_ENQ_REENQ |
  * %SCX_TASK_REENQ_IMMED. If the BPF scheduler dispatches back to the same local
  * DSQ with %SCX_ENQ_IMMED while the CPU is still unavailable, this triggers
- * another reenq cycle. Repetitions are bounded by %SCX_REENQ_LOCAL_MAX_REPEAT
- * in process_deferred_reenq_locals().
+ * another reenq cycle. Repetitions are bounded by %SCX_REENQ_MAX_REPEAT in
+ * scx_do_enqueue_task(), which ejects the task's owning scheduler.
  */
 static bool local_task_should_reenq(struct rq *rq, struct task_struct *p,
 				    u64 *reenq_flags, u32 *reason)
@@ -4175,14 +4196,16 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags)
 
 static void process_deferred_reenq_locals(struct rq *rq)
 {
-	u64 seq = ++rq->scx.deferred_reenq_locals_seq;
-
 	lockdep_assert_rq_held(rq);
 
+	/*
+	 * A task can be re-queued within this loop when a reenqueued task
+	 * bounces straight back to the local DSQ. That recursion is bounded by
+	 * the per-task reenqueue cap in scx_do_enqueue_task().
+	 */
 	while (true) {
 		struct scx_sched *sch;
 		u64 reenq_flags;
-		bool skip = false;
 
 		scoped_guard (raw_spinlock, &rq->scx.deferred_reenq_lock) {
 			struct scx_deferred_reenq_local *drl =
@@ -4201,27 +4224,12 @@ static void process_deferred_reenq_locals(struct rq *rq)
 			reenq_flags = drl->flags;
 			WRITE_ONCE(drl->flags, 0);
 			list_del_init(&drl->node);
-
-			if (likely(drl->seq != seq)) {
-				drl->seq = seq;
-				drl->cnt = 0;
-			} else {
-				if (unlikely(++drl->cnt > SCX_REENQ_LOCAL_MAX_REPEAT)) {
-					scx_error(sch, "SCX_ENQ_REENQ on SCX_DSQ_LOCAL repeated %u times",
-						  drl->cnt);
-					skip = true;
-				}
-
-				__scx_add_event(sch, SCX_EV_REENQ_LOCAL_REPEAT, 1);
-			}
 		}
 
-		if (!skip) {
-			/* see schedule_dsq_reenq() */
-			smp_mb();
+		/* see schedule_dsq_reenq() */
+		smp_mb();
 
-			reenq_local(sch, rq, reenq_flags);
-		}
+		reenq_local(sch, rq, reenq_flags);
 	}
 }
 
@@ -5941,6 +5949,8 @@ static const char *scx_exit_reason(enum scx_exit_kind kind)
 		return "scx_bpf_error";
 	case SCX_EXIT_ERROR_STALL:
 		return "runnable task stall";
+	case SCX_EXIT_ERROR_REENQ:
+		return "reenqueue limit";
 	default:
 		return "<UNKNOWN>";
 	}

kernel/sched/ext/internal.h

@@ -56,6 +56,7 @@ enum scx_exit_kind {
 	SCX_EXIT_ERROR = 1024,	/* runtime error, error msg contains details */
 	SCX_EXIT_ERROR_BPF,	/* ERROR but triggered through scx_bpf_error() */
 	SCX_EXIT_ERROR_STALL,	/* watchdog detected stalled runnable tasks */
+	SCX_EXIT_ERROR_REENQ,	/* task hit reenqueue limit without running */
 };
 
 /*
@@ -1119,15 +1120,13 @@ struct scx_event_stats {
 	s64		SCX_EV_REENQ_IMMED;
 
 	/*
-	 * The number of times a reenq of local DSQ caused another reenq of
-	 * local DSQ. This can happen when %SCX_ENQ_IMMED races against a higher
-	 * priority class task even if the BPF scheduler always satisfies the
-	 * prerequisites for %SCX_ENQ_IMMED at the time of enqueue. However,
-	 * that scenario is very unlikely and this count going up regularly
-	 * indicates that the BPF scheduler is handling %SCX_ENQ_REENQ
-	 * incorrectly causing recursive reenqueues.
+	 * The number of times a reenqueue (%SCX_ENQ_REENQ) led to another
+	 * reenqueue without the task running in between. This count climbing
+	 * rapidly indicates that the BPF scheduler keeps re-deciding placements
+	 * it can't honor. A single task reenqueued more than
+	 * %SCX_REENQ_MAX_REPEAT times gets its owning scheduler ejected.
 	 */
-	s64		SCX_EV_REENQ_LOCAL_REPEAT;
+	s64		SCX_EV_REENQ_REPEAT;
 
 	/*
 	 * Total number of times a task's time slice was refilled with the
@@ -1221,7 +1220,7 @@ struct scx_event_stats {
 	SCX_EVENT(SCX_EV_ENQ_SKIP_EXITING);				\
 	SCX_EVENT(SCX_EV_ENQ_SKIP_MIGRATION_DISABLED);			\
 	SCX_EVENT(SCX_EV_REENQ_IMMED);					\
-	SCX_EVENT(SCX_EV_REENQ_LOCAL_REPEAT);				\
+	SCX_EVENT(SCX_EV_REENQ_REPEAT);					\
 	SCX_EVENT(SCX_EV_REFILL_SLICE_DFL);				\
 	SCX_EVENT(SCX_EV_SLICE_CLAMPED);				\
 	SCX_EVENT(SCX_EV_SLICE_DENIED);					\
@@ -1260,8 +1259,6 @@ struct scx_dsp_ctx {
 struct scx_deferred_reenq_local {
 	struct list_head	node;
 	u64			flags;
-	u64			seq;
-	u32			cnt;
 };
 
 struct scx_sched_pcpu {

kernel/sched/ext/sub.c

@@ -319,9 +319,9 @@ bool scx_task_reenq_on_cap_revoke(struct rq *rq, struct task_struct *p)
  * Drain @rq->scx.reject_dsq, reenqueueing each task so the BPF re-decides
  * from p->scx.reenq_reason_*.
  *
- * A task can be re-rejected repeatedly, and there's no repeat limit here.
- * Rejection can't happen for root, and sub-scheds can be safely ejected after
- * triggering the stall watchdog.
+ * A task can be re-rejected repeatedly. The reenqueue is bounded per task in
+ * scx_do_enqueue_task(), which ejects the owning sub past SCX_REENQ_MAX_REPEAT.
+ * Rejection can't happen for root.
  */
 void scx_reenq_reject(struct rq *rq)
 {

kernel/sched/ext/types.h

@@ -41,7 +41,7 @@ enum scx_consts {
 	SCX_BYPASS_LB_MIN_DELTA_DIV	= 4,
 	SCX_BYPASS_LB_BATCH		= 256,
 
-	SCX_REENQ_LOCAL_MAX_REPEAT	= 256,
+	SCX_REENQ_MAX_REPEAT		= 256,
 
 	SCX_SUB_MAX_DEPTH		= 4,
 };

kernel/sched/sched.h

@@ -823,7 +823,6 @@ struct scx_rq {
 	struct list_head	sched_pcpus_to_kick;	/* see kick_cpus_irq_workfn() */
 
 	raw_spinlock_t		deferred_reenq_lock;
-	u64			deferred_reenq_locals_seq;
 	struct list_head	deferred_reenq_locals;	/* scheds requesting reenq of local DSQ */
 	struct list_head	deferred_reenq_users;	/* user DSQs requesting reenq */
 	struct balance_callback	deferred_bal_cb;