sched_ext: idle: Introduce scx_bpf_select_cpu_and()

Provide a new kfunc, scx_bpf_select_cpu_and(), that can be used to apply
the built-in idle CPU selection policy to a subset of allowed CPU.

This new helper is basically an extension of scx_bpf_select_cpu_dfl().
However, when an idle CPU can't be found, it returns a negative value
instead of @prev_cpu, aligning its behavior more closely with
scx_bpf_pick_idle_cpu().

It also accepts %SCX_PICK_IDLE_* flags, which can be used to enforce
strict selection to @prev_cpu's node (%SCX_PICK_IDLE_IN_NODE), or to
request only a full-idle SMT core (%SCX_PICK_IDLE_CORE), while applying
the built-in selection logic.

With this helper, BPF schedulers can apply the built-in idle CPU
selection policy restricted to any arbitrary subset of CPUs.

Example usage
=============

Possible usage in ops.select_cpu():

s32 BPF_STRUCT_OPS(foo_select_cpu, struct task_struct *p,
		   s32 prev_cpu, u64 wake_flags)
{
	const struct cpumask *cpus = task_allowed_cpus(p) ?: p->cpus_ptr;
	s32 cpu;

	cpu = scx_bpf_select_cpu_and(p, prev_cpu, wake_flags, cpus, 0);
	if (cpu >= 0) {
		scx_bpf_dsq_insert(p, SCX_DSQ_LOCAL, SCX_SLICE_DFL, 0);
		return cpu;
	}

	return prev_cpu;
}

Results
=======

Load distribution on a 4 sockets, 4 cores per socket system, simulated
using virtme-ng, running a modified version of scx_bpfland that uses
scx_bpf_select_cpu_and() with 0xff00 as the allowed subset of CPUs:

 $ vng --cpu 16,sockets=4,cores=4,threads=1
 ...
 $ stress-ng -c 16
 ...
 $ htop
 ...
   0[                         0.0%]   8[||||||||||||||||||||||||100.0%]
   1[                         0.0%]   9[||||||||||||||||||||||||100.0%]
   2[                         0.0%]  10[||||||||||||||||||||||||100.0%]
   3[                         0.0%]  11[||||||||||||||||||||||||100.0%]
   4[                         0.0%]  12[||||||||||||||||||||||||100.0%]
   5[                         0.0%]  13[||||||||||||||||||||||||100.0%]
   6[                         0.0%]  14[||||||||||||||||||||||||100.0%]
   7[                         0.0%]  15[||||||||||||||||||||||||100.0%]

With scx_bpf_select_cpu_dfl() tasks would be distributed evenly across
all the available CPUs.

Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

3 files changed, 58 insertions, 0 deletions

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index ac3fd7a409e9..eae16108f8d6 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -465,6 +465,7 @@ struct sched_ext_ops {
 	 * idle CPU tracking and the following helpers become unavailable:
 	 *
 	 * - scx_bpf_select_cpu_dfl()
+	 * - scx_bpf_select_cpu_and()
 	 * - scx_bpf_test_and_clear_cpu_idle()
 	 * - scx_bpf_pick_idle_cpu()
 	 *
diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c
index f39b34fbb8a6..023ae6df5e8c 100644
--- a/kernel/sched/ext_idle.c
+++ b/kernel/sched/ext_idle.c
@@ -913,6 +913,60 @@ prev_cpu:
 }
 
 /**
+ * scx_bpf_select_cpu_and - Pick an idle CPU usable by task @p,
+ *			    prioritizing those in @cpus_allowed
+ * @p: task_struct to select a CPU for
+ * @prev_cpu: CPU @p was on previously
+ * @wake_flags: %SCX_WAKE_* flags
+ * @cpus_allowed: cpumask of allowed CPUs
+ * @flags: %SCX_PICK_IDLE* flags
+ *
+ * Can only be called from ops.select_cpu() or ops.enqueue() if the
+ * built-in CPU selection is enabled: ops.update_idle() is missing or
+ * %SCX_OPS_KEEP_BUILTIN_IDLE is set.
+ *
+ * @p, @prev_cpu and @wake_flags match ops.select_cpu().
+ *
+ * Returns the selected idle CPU, which will be automatically awakened upon
+ * returning from ops.select_cpu() and can be used for direct dispatch, or
+ * a negative value if no idle CPU is available.
+ */
+__bpf_kfunc s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+				       const struct cpumask *cpus_allowed, u64 flags)
+{
+	s32 cpu;
+
+	if (!ops_cpu_valid(prev_cpu, NULL))
+		return -EINVAL;
+
+	if (!check_builtin_idle_enabled())
+		return -EBUSY;
+
+	if (!scx_kf_allowed(SCX_KF_SELECT_CPU | SCX_KF_ENQUEUE))
+		return -EPERM;
+
+#ifdef CONFIG_SMP
+	/*
+	 * This may also be called from ops.enqueue(), so we need to handle
+	 * per-CPU tasks as well. For these tasks, we can skip all idle CPU
+	 * selection optimizations and simply check whether the previously
+	 * used CPU is idle and within the allowed cpumask.
+	 */
+	if (p->nr_cpus_allowed == 1) {
+		if (cpumask_test_cpu(prev_cpu, cpus_allowed) &&
+		    scx_idle_test_and_clear_cpu(prev_cpu))
+			return prev_cpu;
+		return -EBUSY;
+	}
+	cpu = scx_select_cpu_dfl(p, prev_cpu, wake_flags, cpus_allowed, flags);
+#else
+	cpu = -EBUSY;
+#endif
+
+	return cpu;
+}
+
+/**
  * scx_bpf_get_idle_cpumask_node - Get a referenced kptr to the
  * idle-tracking per-CPU cpumask of a target NUMA node.
  * @node: target NUMA node
@@ -1220,6 +1274,7 @@ static const struct btf_kfunc_id_set scx_kfunc_set_idle = {
 
 BTF_KFUNCS_START(scx_kfunc_ids_select_cpu)
 BTF_ID_FLAGS(func, scx_bpf_select_cpu_dfl, KF_RCU)
+BTF_ID_FLAGS(func, scx_bpf_select_cpu_and, KF_RCU)
 BTF_KFUNCS_END(scx_kfunc_ids_select_cpu)
 
 static const struct btf_kfunc_id_set scx_kfunc_set_select_cpu = {
diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h
index 8787048c6762..d4e21558e982 100644
--- a/tools/sched_ext/include/scx/common.bpf.h
+++ b/tools/sched_ext/include/scx/common.bpf.h
@@ -48,6 +48,8 @@ static inline void ___vmlinux_h_sanity_check___(void)
 
 s32 scx_bpf_create_dsq(u64 dsq_id, s32 node) __ksym;
 s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu, u64 wake_flags, bool *is_idle) __ksym;
+s32 scx_bpf_select_cpu_and(struct task_struct *p, s32 prev_cpu, u64 wake_flags,
+			   const struct cpumask *cpus_allowed, u64 flags) __ksym __weak;
 void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice, u64 enq_flags) __ksym __weak;
 void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id, u64 slice, u64 vtime, u64 enq_flags) __ksym __weak;
 u32 scx_bpf_dispatch_nr_slots(void) __ksym;