[PATCH 10/14] sched_ext: Fix bypassed tasks stalling when the host lacks SCX_CAP_BASE

[Tejun Heo <tj@kernel.org>]

A bypassed task stalls on a cpu where its host lacks SCX_CAP_BASE. The host,
the nearest ancestor that is not bypassing, runs a bypassing sub-scheduler's
tasks through its per-cpu bypass DSQs. A cpu's dispatch only descends into
schedulers holding BASE on it, so the host's bypass DSQ on such a cpu is
never consumed until the host regains the cap.

Resolve a bypassed task against its host at enqueue time. If the host lacks
BASE on the cpu, send the task to rescue on that cpu, which runs it at
bounded bandwidth without the host's dispatch having to reach it.

The enqueue does not look above the host for an ancestor that holds BASE.
That ancestor would run the task on cpus it never granted the host. With
rescue disabled the task goes to the host's bypass DSQ as before and stalls
there until the host regains BASE or the bypass window ends.

Bypass also used to end a rescue, sending a preempted rescuee to the bypass
DSQ with every other preempted task. Now that rescue is how a bypassed task
runs while its host lacks BASE, keep a preempted rescuee on the local DSQ
under bypass too. The grant stays bounded by served time.

While at it, the rescue test in __scx_resolve_local_dsq() goes through the
new scx_rescue_enabled() helper.

Fixes: 147d1885f390 ("sched_ext: Add the SCX_CAP_ENQ_IMMED cap")
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext/ext.c | 34 +++++++++++++++++++++++++++++-----
 kernel/sched/ext/sub.c | 25 +++++++++++++------------
 kernel/sched/ext/sub.h |  9 +++++++++
 3 files changed, 51 insertions(+), 17 deletions(-)

diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index f462d84c9b72..348c63901b51 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -388,8 +388,12 @@ static const struct sched_class *scx_setscheduler_class(struct task_struct *p)
 	return __setscheduler_class(p->policy, p->prio);
 }
 
-static struct scx_dispatch_q *bypass_enq_target_dsq(struct scx_sched *sch, s32 cpu)
+static struct scx_dispatch_q *bypass_enq_target_dsq(struct scx_sched *sch, struct rq *rq,
+						    struct task_struct *p, u64 *enq_flags)
 {
+	struct scx_sched *host = scx_exec_sched(sch, cpu_of(rq));
+	struct scx_dispatch_q *dsq;
+
 	/*
 	 * If @sch is a sub-sched which is bypassing, its tasks should go into
 	 * the bypass DSQs of the nearest ancestor which is not bypassing. The
@@ -400,8 +404,23 @@ static struct scx_dispatch_q *bypass_enq_target_dsq(struct scx_sched *sch, s32 c
 	 * Whenever a sched starts bypassing, all runnable tasks in its subtree
 	 * are re-enqueued after scx_bypassing() is turned on, guaranteeing that
 	 * all tasks are transferred to the right DSQs.
-	 */
-	return scx_bypass_dsq(scx_exec_sched(sch, cpu), cpu);
+	 *
+	 * A cpu's dispatch only descends into a host holding %SCX_CAP_BASE on
+	 * it, so the bypass DSQ of a host without BASE here is never consumed.
+	 * Send @p to rescue on this cpu instead, resolving against @host.
+	 * scx_dispatch_enqueue() resolves a local DSQ again, against the
+	 * bypassing @sch. %SCX_ENQ_IGNORE_CAPS makes that second resolution
+	 * admit @p.
+	 */
+	if (scx_rescue_enabled() &&
+	    unlikely(scx_missing_caps(host, cpu_of(rq), SCX_CAP_BASE))) {
+		*enq_flags |= SCX_ENQ_RESCUE;
+		dsq = scx_resolve_local_dsq(host, rq, p, enq_flags);
+		*enq_flags |= SCX_ENQ_IGNORE_CAPS;
+	} else {
+		dsq = scx_bypass_dsq(host, cpu_of(rq));
+	}
+	return dsq;
 }
 
 /**
@@ -2315,7 +2334,7 @@ void scx_do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags,
 	dsq = find_global_dsq(sch, task_cpu(p));
 	goto enqueue;
 bypass:
-	dsq = bypass_enq_target_dsq(sch, task_cpu(p));
+	dsq = bypass_enq_target_dsq(sch, rq, p, &enq_flags);
 	goto enqueue;
 
 enqueue:
@@ -3653,8 +3672,13 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
 		 * The exception is an IMMED donor put by proxy_resched_idle():
 		 * the CPU isn't busy, proxy resolution is only retrying through
 		 * idle, so keep the donor where it can be picked again.
+		 *
+		 * A task with a kernel slice stays on the local DSQ even while
+		 * @sch bypasses. Under bypass, rescue runs @p when the host
+		 * lacks %SCX_CAP_BASE, see bypass_enq_target_dsq().
 		 */
-		if (p->scx.slice && !scx_bypassing(sch, cpu_of(rq))) {
+		if (p->scx.slice && (!scx_bypassing(sch, cpu_of(rq)) ||
+				     scx_task_has_kernel_slice(p))) {
 			if ((p->scx.flags & SCX_TASK_IMMED) && !proxy_put) {
 				p->scx.flags |= SCX_TASK_REENQ_PREEMPTED;
 				scx_do_enqueue_task(rq, p, SCX_ENQ_REENQ, -1);
diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c
index 4dff3183d33f..e8008d26ece2 100644
--- a/kernel/sched/ext/sub.c
+++ b/kernel/sched/ext/sub.c
@@ -36,7 +36,7 @@ static DEFINE_STATIC_KEY_FALSE(__scx_ops_cid_sched_updated_enabled);
 static s32 scx_nr_ops_cid_sched_updated;	/* such scheds, under scx_enable_mutex */
 
 /* latched at root enable before any rescue runs */
-static s32 scx_rescue_bw_1024;
+s32 scx_rescue_bw_1024;			/* 0 if disabled, see scx_rescue_enabled() */
 static s64 scx_rescue_quantum_ns;
 static s64 scx_rescue_sat_delta_ns;
 static unsigned long scx_rescue_decay_halflife;
@@ -482,12 +482,14 @@ void scx_rescue_end(struct rq *rq)
  * this when nothing else is runnable and put_prev_task_scx() when another task
  * won the pick. scx_rescue_charge() ends the rescue the moment the admitted
  * slice is fully served, so arriving here with the rescue still open means @p
- * was preempted. Restore the unserved remainder and return %true. @p stays the
- * rescuee. dispatch_one() keeps it running and put_prev_task_scx() reinserts it
- * at the tail of the local DSQ, behind whatever preempted the rescuee.
+ * was preempted or, under bypass, that dispatch_one() declined to keep it
+ * running although it had slice left. Restore the unserved remainder and return
+ * %true. @p stays the rescuee. dispatch_one() keeps it running and
+ * put_prev_task_scx() reinserts it at the tail of the local DSQ, behind
+ * whatever preempted the rescuee.
  *
- * Return %false to end the rescue instead - the slice is already fully served,
- * @p is leaving the rq or bypass is dismantling rescues.
+ * Return %false to end the rescue instead - the slice is already fully served
+ * or @p is leaving the rq.
  */
 bool scx_rescue_keep(struct rq *rq, struct task_struct *p)
 {
@@ -495,8 +497,7 @@ bool scx_rescue_keep(struct rq *rq, struct task_struct *p)
 
 	lockdep_assert_rq_held(rq);
 
-	if (!remaining || !(p->scx.flags & SCX_TASK_QUEUED) ||
-	    scx_bypassing(scx_task_sched(p), cpu_of(rq)))
+	if (!remaining || !(p->scx.flags & SCX_TASK_QUEUED))
 		return false;
 
 	scx_set_task_slice(p, remaining);
@@ -852,9 +853,9 @@ void scx_rescue_init(struct rq *rq)
  * %SCX_ENQ_PREEMPT_LAZY are also cleared on a fallback migration-disabled
  * admission.
  *
- * Bypass doesn't need special-casing as a bypassing sched's tasks are enqueued
- * to and run by its nearest non-bypassing ancestor. If root is bypassing, it
- * always holds all caps.
+ * bypass_enq_target_dsq() also calls this with the host as @sch when the host
+ * lacks %SCX_CAP_BASE on @rq's cid and rescue is enabled. The bypassed task
+ * then diverts like a capless %SCX_ENQ_RESCUE insert by the host itself.
  */
 struct scx_dispatch_q *__scx_resolve_local_dsq(struct scx_sched *sch, struct rq *rq,
 					       struct task_struct *p, u64 *enq_flags)
@@ -897,7 +898,7 @@ struct scx_dispatch_q *__scx_resolve_local_dsq(struct scx_sched *sch, struct rq
 	scx_divert_strip_flags(p, enq_flags);
 
 	/* the enqueuer opted for rescue instead of rejection and reenqueue */
-	if ((*enq_flags & SCX_ENQ_RESCUE) && likely(scx_rescue_bw_1024)) {
+	if (scx_rescue_enabled() && (*enq_flags & SCX_ENQ_RESCUE)) {
 		__scx_add_event(sch, SCX_EV_SUB_RESCUE, 1);
 		if (scx_rescue_try_admit(rq, p))
 			return &rq->scx.local_dsq;
diff --git a/kernel/sched/ext/sub.h b/kernel/sched/ext/sub.h
index 223c34309b5a..acd7b4210906 100644
--- a/kernel/sched/ext/sub.h
+++ b/kernel/sched/ext/sub.h
@@ -14,6 +14,8 @@
 
 #ifdef CONFIG_EXT_SUB_SCHED
 
+extern s32 scx_rescue_bw_1024;
+
 struct scx_sched *scx_skip_subtree_pre(struct scx_sched *pos, struct scx_sched *root);
 struct scx_sched *scx_next_descendant_pre(struct scx_sched *pos, struct scx_sched *root);
 void scx_cid_sched_update(struct rq *rq, struct scx_sched *sch);
@@ -48,6 +50,12 @@ void scx_rescue_dump(struct seq_buf *s, struct rq *rq);
 void scx_rescue_set_knobs(struct scx_sched *sch);
 void scx_rescue_init(struct rq *rq);
 
+/* false only when the root disabled rescue, see scx_rescue_set_knobs() */
+static inline bool scx_rescue_enabled(void)
+{
+	return likely(scx_rescue_bw_1024);
+}
+
 /*
  * cgrp->scx_sched is written by root/sub enable/disable under all of
  * scx_enable_mutex, scx_fork_rwsem and cgroup_mutex. A new cgroup inherits the
@@ -122,6 +130,7 @@ static inline void scx_rescue_end(struct rq *rq) {}
 static inline bool scx_rescue_keep(struct rq *rq, struct task_struct *p) { return false; }
 static inline void scx_rescue_flush(struct rq *rq) {}
 static inline void scx_rescue_dump(struct seq_buf *s, struct rq *rq) {}
+static inline bool scx_rescue_enabled(void) { return false; }
 static inline void scx_rescue_set_knobs(struct scx_sched *sch) {}
 static inline void scx_rescue_init(struct rq *rq) {}
 static inline void scx_dec_has_subs(struct scx_sched *sch) {}
-- 
2.56.0