3 files changed, 39 insertions, 3 deletions

diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 421118bc56ff..8686f84497db 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -34,6 +34,7 @@ void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flag
 u32 scx_bpf_dispatch_nr_slots(void) __ksym;
 void scx_bpf_dispatch_cancel(void) __ksym;
 bool scx_bpf_consume(u64 dsq_id) __ksym;
+u32 scx_bpf_reenqueue_local(void) __ksym;
 void scx_bpf_kick_cpu(s32 cpu, u64 flags) __ksym;
 s32 scx_bpf_dsq_nr_queued(u64 dsq_id) __ksym;
 void scx_bpf_destroy_dsq(u64 dsq_id) __ksym;
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index 879fc9c788e5..4a87377558c8 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -11,6 +11,8 @@
  *
  * - BPF-side queueing using PIDs.
  * - Sleepable per-task storage allocation using ops.prep_enable().
+ * - Using ops.cpu_release() to handle a higher priority scheduling class taking
+ *   the CPU away.
  *
  * This scheduler is primarily for demonstration and testing of sched_ext
  * features and unlikely to be useful for actual workloads.
@@ -90,7 +92,7 @@ struct {
 } cpu_ctx_stor SEC(".maps");
 
 /* Statistics */
-u64 nr_enqueued, nr_dispatched, nr_dequeued;
+u64 nr_enqueued, nr_dispatched, nr_reenqueued, nr_dequeued;
 
 s32 BPF_STRUCT_OPS(qmap_select_cpu, struct task_struct *p,
 		   s32 prev_cpu, u64 wake_flags)
@@ -164,6 +166,22 @@ void BPF_STRUCT_OPS(qmap_enqueue, struct task_struct *p, u64 enq_flags)
 		return;
 	}
 
+	/*
+	 * If the task was re-enqueued due to the CPU being preempted by a
+	 * higher priority scheduling class, just re-enqueue the task directly
+	 * on the global DSQ. As we want another CPU to pick it up, find and
+	 * kick an idle CPU.
+	 */
+	if (enq_flags & SCX_ENQ_REENQ) {
+		s32 cpu;
+
+		scx_bpf_dispatch(p, SHARED_DSQ, 0, enq_flags);
+		cpu = scx_bpf_pick_idle_cpu(p->cpus_ptr, 0);
+		if (cpu >= 0)
+			scx_bpf_kick_cpu(cpu, SCX_KICK_IDLE);
+		return;
+	}
+
 	ring = bpf_map_lookup_elem(&queue_arr, &idx);
 	if (!ring) {
 		scx_bpf_error("failed to find ring %d", idx);
@@ -257,6 +275,22 @@ void BPF_STRUCT_OPS(qmap_dispatch, s32 cpu, struct task_struct *prev)
 	}
 }
 
+void BPF_STRUCT_OPS(qmap_cpu_release, s32 cpu, struct scx_cpu_release_args *args)
+{
+	u32 cnt;
+
+	/*
+	 * Called when @cpu is taken by a higher priority scheduling class. This
+	 * makes @cpu no longer available for executing sched_ext tasks. As we
+	 * don't want the tasks in @cpu's local dsq to sit there until @cpu
+	 * becomes available again, re-enqueue them into the global dsq. See
+	 * %SCX_ENQ_REENQ handling in qmap_enqueue().
+	 */
+	cnt = scx_bpf_reenqueue_local();
+	if (cnt)
+		__sync_fetch_and_add(&nr_reenqueued, cnt);
+}
+
 s32 BPF_STRUCT_OPS(qmap_init_task, struct task_struct *p,
 		   struct scx_init_task_args *args)
 {
@@ -339,6 +373,7 @@ SCX_OPS_DEFINE(qmap_ops,
 	       .enqueue			= (void *)qmap_enqueue,
 	       .dequeue			= (void *)qmap_dequeue,
 	       .dispatch		= (void *)qmap_dispatch,
+	       .cpu_release		= (void *)qmap_cpu_release,
 	       .init_task		= (void *)qmap_init_task,
 	       .dump			= (void *)qmap_dump,
 	       .dump_cpu		= (void *)qmap_dump_cpu,
diff --git a/tools/sched_ext/scx_qmap.c b/tools/sched_ext/scx_qmap.c
index 594147a710a8..2a97421afe9a 100644
--- a/tools/sched_ext/scx_qmap.c
+++ b/tools/sched_ext/scx_qmap.c
@@ -112,9 +112,9 @@ int main(int argc, char **argv)
 		long nr_enqueued = skel->bss->nr_enqueued;
 		long nr_dispatched = skel->bss->nr_dispatched;
 
-		printf("stats  : enq=%lu dsp=%lu delta=%ld deq=%"PRIu64"\n",
+		printf("stats  : enq=%lu dsp=%lu delta=%ld reenq=%"PRIu64" deq=%"PRIu64"\n",
 		       nr_enqueued, nr_dispatched, nr_enqueued - nr_dispatched,
-		       skel->bss->nr_dequeued);
+		       skel->bss->nr_reenqueued, skel->bss->nr_dequeued);
 		fflush(stdout);
 		sleep(1);
 	}