Merge tag 'sched_ext-for-7.0-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_extHEADmaster

Pull sched_ext fixes from Tejun Heo:

 - Fix SCX_KICK_WAIT deadlock where multiple CPUs waiting for each other
   in hardirq context form a cycle. Move the wait to a balance callback
   which can drop the rq lock and process IPIs.

 - Fix inconsistent NUMA node lookup in scx_select_cpu_dfl() where
   the waker_node used cpu_to_node() while prev_cpu used
   scx_cpu_node_if_enabled(), leading to undefined behavior when
   per-node idle tracking is disabled.

* tag 'sched_ext-for-7.0-rc6-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
  selftests/sched_ext: Add cyclic SCX_KICK_WAIT stress test
  sched_ext: Fix SCX_KICK_WAIT deadlock by deferring wait to balance callback
  sched_ext: Fix inconsistent NUMA node lookup in scx_select_cpu_dfl()

1 files changed, 68 insertions, 0 deletions

diff --git a/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
new file mode 100644
index 000000000000..cb34d3335917
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/cyclic_kick_wait.bpf.c
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Stress concurrent SCX_KICK_WAIT calls to reproduce wait-cycle deadlock.
+ *
+ * Three CPUs are designated from userspace. Every enqueue from one of the
+ * three CPUs kicks the next CPU in the ring with SCX_KICK_WAIT, creating a
+ * persistent A -> B -> C -> A wait cycle pressure.
+ */
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+const volatile s32 test_cpu_a;
+const volatile s32 test_cpu_b;
+const volatile s32 test_cpu_c;
+
+u64 nr_enqueues;
+u64 nr_wait_kicks;
+
+UEI_DEFINE(uei);
+
+static s32 target_cpu(s32 cpu)
+{
+	if (cpu == test_cpu_a)
+		return test_cpu_b;
+	if (cpu == test_cpu_b)
+		return test_cpu_c;
+	if (cpu == test_cpu_c)
+		return test_cpu_a;
+	return -1;
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_enqueue, struct task_struct *p,
+		    u64 enq_flags)
+{
+	s32 this_cpu = bpf_get_smp_processor_id();
+	s32 tgt;
+
+	__sync_fetch_and_add(&nr_enqueues, 1);
+
+	if (p->flags & PF_KTHREAD) {
+		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_INF,
+				   enq_flags | SCX_ENQ_PREEMPT);
+		return;
+	}
+
+	scx_bpf_dsq_insert(p, SCX_DSQ_GLOBAL, SCX_SLICE_DFL, enq_flags);
+
+	tgt = target_cpu(this_cpu);
+	if (tgt < 0 || tgt == this_cpu)
+		return;
+
+	__sync_fetch_and_add(&nr_wait_kicks, 1);
+	scx_bpf_kick_cpu(tgt, SCX_KICK_WAIT);
+}
+
+void BPF_STRUCT_OPS(cyclic_kick_wait_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops cyclic_kick_wait_ops = {
+	.enqueue		= cyclic_kick_wait_enqueue,
+	.exit			= cyclic_kick_wait_exit,
+	.name			= "cyclic_kick_wait",
+	.timeout_ms		= 1000U,
+};