Merge tag 'sched_ext-for-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

Pull sched_ext updates from Tejun Heo:

 - Add mechanism to count and report internal events. This significantly
   improves visibility on subtle corner conditions.

 - The default idle CPU selection logic is revamped and improved in
   multiple ways including being made topology aware.

 - sched_ext was disabling ttwu_queue for simplicity, which can be
   costly when hardware topology is more complex. Implement
   SCX_OPS_ALLOWED_QUEUED_WAKEUP so that BPF schedulers can selectively
   enable ttwu_queue.

 - tools/sched_ext updates to improve compatibility among others.

 - Other misc updates and fixes.

 - sched_ext/for-6.14-fixes were pulled a few times to receive
   prerequisite fixes and resolve conflicts.

* tag 'sched_ext-for-6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext: (42 commits)
  sched_ext: idle: Refactor scx_select_cpu_dfl()
  sched_ext: idle: Honor idle flags in the built-in idle selection policy
  sched_ext: Skip per-CPU tasks in scx_bpf_reenqueue_local()
  sched_ext: Add trace point to track sched_ext core events
  sched_ext: Change the event type from u64 to s64
  sched_ext: Documentation: add task lifecycle summary
  tools/sched_ext: Provide a compatible helper for scx_bpf_events()
  selftests/sched_ext: Add NUMA-aware scheduler test
  tools/sched_ext: Provide consistent access to scx flags
  sched_ext: idle: Fix scx_bpf_pick_any_cpu_node() behavior
  sched_ext: idle: Introduce scx_bpf_nr_node_ids()
  sched_ext: idle: Introduce node-aware idle cpu kfunc helpers
  sched_ext: idle: Per-node idle cpumasks
  sched_ext: idle: Introduce SCX_OPS_BUILTIN_IDLE_PER_NODE
  sched_ext: idle: Make idle static keys private
  sched/topology: Introduce for_each_node_numadist() iterator
  mm/numa: Introduce nearest_node_nodemask()
  nodemask: numa: reorganize inclusion path
  nodemask: add nodes_copy()
  tools/sched_ext: Sync with scx repo
  ...

3 files changed, 160 insertions, 0 deletions

diff --git a/tools/testing/selftests/sched_ext/Makefile b/tools/testing/selftests/sched_ext/Makefile
index 011762224600..f4531327b8e7 100644
--- a/tools/testing/selftests/sched_ext/Makefile
+++ b/tools/testing/selftests/sched_ext/Makefile
@@ -172,6 +172,7 @@ auto-test-targets :=			\
 	maximal				\
 	maybe_null			\
 	minimal				\
+	numa				\
 	prog_run			\
 	reload_loop			\
 	select_cpu_dfl			\
diff --git a/tools/testing/selftests/sched_ext/numa.bpf.c b/tools/testing/selftests/sched_ext/numa.bpf.c
new file mode 100644
index 000000000000..a79d86ed54a1
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/numa.bpf.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A scheduler that validates the behavior of the NUMA-aware
+ * functionalities.
+ *
+ * The scheduler creates a separate DSQ for each NUMA node, ensuring tasks
+ * are exclusively processed by CPUs within their respective nodes. Idle
+ * CPUs are selected only within the same node, so task migration can only
+ * occurs between CPUs belonging to the same node.
+ *
+ * Copyright (c) 2025 Andrea Righi <arighi@nvidia.com>
+ */
+
+#include <scx/common.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+UEI_DEFINE(uei);
+
+const volatile unsigned int __COMPAT_SCX_PICK_IDLE_IN_NODE;
+
+static bool is_cpu_idle(s32 cpu, int node)
+{
+	const struct cpumask *idle_cpumask;
+	bool idle;
+
+	idle_cpumask = __COMPAT_scx_bpf_get_idle_cpumask_node(node);
+	idle = bpf_cpumask_test_cpu(cpu, idle_cpumask);
+	scx_bpf_put_cpumask(idle_cpumask);
+
+	return idle;
+}
+
+s32 BPF_STRUCT_OPS(numa_select_cpu,
+		   struct task_struct *p, s32 prev_cpu, u64 wake_flags)
+{
+	int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p));
+	s32 cpu;
+
+	/*
+	 * We could just use __COMPAT_scx_bpf_pick_any_cpu_node() here,
+	 * since it already tries to pick an idle CPU within the node
+	 * first, but let's use both functions for better testing coverage.
+	 */
+	cpu = __COMPAT_scx_bpf_pick_idle_cpu_node(p->cpus_ptr, node,
+					__COMPAT_SCX_PICK_IDLE_IN_NODE);
+	if (cpu < 0)
+		cpu = __COMPAT_scx_bpf_pick_any_cpu_node(p->cpus_ptr, node,
+						__COMPAT_SCX_PICK_IDLE_IN_NODE);
+
+	if (is_cpu_idle(cpu, node))
+		scx_bpf_error("CPU %d should be marked as busy", cpu);
+
+	if (__COMPAT_scx_bpf_cpu_node(cpu) != node)
+		scx_bpf_error("CPU %d should be in node %d", cpu, node);
+
+	return cpu;
+}
+
+void BPF_STRUCT_OPS(numa_enqueue, struct task_struct *p, u64 enq_flags)
+{
+	int node = __COMPAT_scx_bpf_cpu_node(scx_bpf_task_cpu(p));
+
+	scx_bpf_dsq_insert(p, node, SCX_SLICE_DFL, enq_flags);
+}
+
+void BPF_STRUCT_OPS(numa_dispatch, s32 cpu, struct task_struct *prev)
+{
+	int node = __COMPAT_scx_bpf_cpu_node(cpu);
+
+	scx_bpf_dsq_move_to_local(node);
+}
+
+s32 BPF_STRUCT_OPS_SLEEPABLE(numa_init)
+{
+	int node, err;
+
+	bpf_for(node, 0, __COMPAT_scx_bpf_nr_node_ids()) {
+		err = scx_bpf_create_dsq(node, node);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void BPF_STRUCT_OPS(numa_exit, struct scx_exit_info *ei)
+{
+	UEI_RECORD(uei, ei);
+}
+
+SEC(".struct_ops.link")
+struct sched_ext_ops numa_ops = {
+	.select_cpu		= (void *)numa_select_cpu,
+	.enqueue		= (void *)numa_enqueue,
+	.dispatch		= (void *)numa_dispatch,
+	.init			= (void *)numa_init,
+	.exit			= (void *)numa_exit,
+	.name			= "numa",
+};
diff --git a/tools/testing/selftests/sched_ext/numa.c b/tools/testing/selftests/sched_ext/numa.c
new file mode 100644
index 000000000000..b060c3b65c82
--- /dev/null
+++ b/tools/testing/selftests/sched_ext/numa.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025 Andrea Righi <arighi@nvidia.com>
+ */
+#include <bpf/bpf.h>
+#include <scx/common.h>
+#include <sys/wait.h>
+#include <unistd.h>
+#include "numa.bpf.skel.h"
+#include "scx_test.h"
+
+static enum scx_test_status setup(void **ctx)
+{
+	struct numa *skel;
+
+	skel = numa__open();
+	SCX_FAIL_IF(!skel, "Failed to open");
+	SCX_ENUM_INIT(skel);
+	skel->rodata->__COMPAT_SCX_PICK_IDLE_IN_NODE = SCX_PICK_IDLE_IN_NODE;
+	skel->struct_ops.numa_ops->flags = SCX_OPS_BUILTIN_IDLE_PER_NODE;
+	SCX_FAIL_IF(numa__load(skel), "Failed to load skel");
+
+	*ctx = skel;
+
+	return SCX_TEST_PASS;
+}
+
+static enum scx_test_status run(void *ctx)
+{
+	struct numa *skel = ctx;
+	struct bpf_link *link;
+
+	link = bpf_map__attach_struct_ops(skel->maps.numa_ops);
+	SCX_FAIL_IF(!link, "Failed to attach scheduler");
+
+	/* Just sleeping is fine, plenty of scheduling events happening */
+	sleep(1);
+
+	SCX_EQ(skel->data->uei.kind, EXIT_KIND(SCX_EXIT_NONE));
+	bpf_link__destroy(link);
+
+	return SCX_TEST_PASS;
+}
+
+static void cleanup(void *ctx)
+{
+	struct numa *skel = ctx;
+
+	numa__destroy(skel);
+}
+
+struct scx_test numa = {
+	.name = "numa",
+	.description = "Verify NUMA-aware functionalities",
+	.setup = setup,
+	.run = run,
+	.cleanup = cleanup,
+};
+REGISTER_SCX_TEST(&numa)