Merge tag 'sched_ext-for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

Pull sched_ext updates from Tejun Heo:

 - Improve recovery from misbehaving BPF schedulers.

   When a scheduler puts many tasks with varying affinity restrictions
   on a shared DSQ, CPUs scanning through tasks they cannot run can
   overwhelm the system, causing lockups.

   Bypass mode now uses per-CPU DSQs with a load balancer to avoid this,
   and hooks into the hardlockup detector to attempt recovery.

   Add scx_cpu0 example scheduler to demonstrate this scenario.

 - Add lockless peek operation for DSQs to reduce lock contention for
   schedulers that need to query queue state during load balancing.

 - Allow scx_bpf_reenqueue_local() to be called from anywhere in
   preparation for deprecating cpu_acquire/release() callbacks in favor
   of generic BPF hooks.

 - Prepare for hierarchical scheduler support: add
   scx_bpf_task_set_slice() and scx_bpf_task_set_dsq_vtime() kfuncs,
   make scx_bpf_dsq_insert*() return bool, and wrap kfunc args in
   structs for future aux__prog parameter.

 - Implement cgroup_set_idle() callback to notify BPF schedulers when a
   cgroup's idle state changes.

 - Fix migration tasks being incorrectly downgraded from
   stop_sched_class to rt_sched_class across sched_ext enable/disable.
   Applied late as the fix is low risk and the bug subtle but needs
   stable backporting.

 - Various fixes and cleanups including cgroup exit ordering,
   SCX_KICK_WAIT reliability, and backward compatibility improvements.

* tag 'sched_ext-for-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext: (44 commits)
  sched_ext: Fix incorrect sched_class settings for per-cpu migration tasks
  sched_ext: tools: Removing duplicate targets during non-cross compilation
  sched_ext: Use kvfree_rcu() to release per-cpu ksyncs object
  sched_ext: Pass locked CPU parameter to scx_hardlockup() and add docs
  sched_ext: Update comments replacing breather with aborting mechanism
  sched_ext: Implement load balancer for bypass mode
  sched_ext: Factor out abbreviated dispatch dequeue into dispatch_dequeue_locked()
  sched_ext: Factor out scx_dsq_list_node cursor initialization into INIT_DSQ_LIST_CURSOR
  sched_ext: Add scx_cpu0 example scheduler
  sched_ext: Hook up hardlockup detector
  sched_ext: Make handle_lockup() propagate scx_verror() result
  sched_ext: Refactor lockup handlers into handle_lockup()
  sched_ext: Make scx_exit() and scx_vexit() return bool
  sched_ext: Exit dispatch and move operations immediately when aborting
  sched_ext: Simplify breather mechanism with scx_aborting flag
  sched_ext: Use per-CPU DSQs instead of per-node global DSQs in bypass mode
  sched_ext: Refactor do_enqueue_task() local and global DSQ paths
  sched_ext: Use shorter slice in bypass mode
  sched_ext: Mark racy bitfields to prevent adding fields that can't tolerate races
  sched_ext: Minor cleanups to scx_task_iter
  ...

1 files changed, 88 insertions, 0 deletions

diff --git a/tools/sched_ext/scx_cpu0.bpf.c b/tools/sched_ext/scx_cpu0.bpf.c
new file mode 100644
index 000000000000..6326ce598c8e
--- /dev/null
+++ b/tools/sched_ext/scx_cpu0.bpf.c
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A CPU0 scheduler.
+ *
+ * This scheduler queues all tasks to a shared DSQ and only dispatches them on
+ * CPU0 in FIFO order. This is useful for testing bypass behavior when many
+ * tasks are concentrated on a single CPU. If the load balancer doesn't work,
+ * bypass mode can trigger task hangs or RCU stalls as the queue is long and
+ * there's only one CPU working on it.
+ *
+ * - Statistics tracking how many tasks are queued to local and CPU0 DSQs.
+ * - Termination notification for userspace.
+ *
+ * Copyright (c) 2025 Meta Platforms, Inc. and affiliates.
+ * Copyright (c) 2025 Tejun Heo <tj@kernel.org>
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile u32 nr_cpus = 32;	/* !0 for veristat, set during init */
+
+UEI_DEFINE(uei);
+
+/*
+ * We create a custom DSQ with ID 0 that we dispatch to and consume from on
+ * CPU0.
+ */
+#define DSQ_CPU0 0
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(key_size, sizeof(u32));
+	__uint(value_size, sizeof(u64));
+	__uint(max_entries, 2);			/* [local, cpu0] */
+} stats SEC(".maps");
+
+static void stat_inc(u32 idx)
+{
+	u64 *cnt_p = bpf_map_lookup_elem(&stats, &idx);
+	if (cnt_p)
+		(*cnt_p)++;
+}
+
+s32 BPF_STRUCT_OPS(cpu0_select_cpu, struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	return 0;
+}
+
+void BPF_STRUCT_OPS(cpu0_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	/*
+	 * select_cpu() always picks CPU0. If @p is not on CPU0, it can't run on
+	 * CPU 0. Queue on whichever CPU it's currently only.
+	 */
+	if (scx_bpf_task_cpu(p) != 0) {
+		stat_inc(0);	/* count local queueing */
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
+		return;
+	}
+
+	stat_inc(1);	/* count cpu0 queueing */
+	scx_bpf_dsq_insert(p, DSQ_CPU0, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(cpu0_dispatch, s32 cpu, struct task_struct *prev)
+{
+	if (cpu == 0)
+		scx_bpf_dsq_move_to_local(DSQ_CPU0);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(cpu0_init)
+{
+	return scx_bpf_create_dsq(DSQ_CPU0, -1);
+}
+
+void BPF_STRUCT_OPS(cpu0_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SCX_OPS_DEFINE(cpu0_ops,
+	       .select_cpu		= (void *)cpu0_select_cpu,
+	       .enqueue			= (void *)cpu0_enqueue,
+	       .dispatch		= (void *)cpu0_dispatch,
+	       .init			= (void *)cpu0_init,
+	       .exit			= (void *)cpu0_exit,
+	       .name			= "cpu0");