[PATCH sched_ext/for-6.14-fixes 1/2] sched_ext: Implement auto local dispatching of migration disabled tasks

[Tejun Heo <tj@kernel.org>]

Migration disabled tasks are special and pinned to their previous CPUs. They
tripped up some unsuspecting BPF schedulers as their ->nr_cpus_allowed may
not agree with the bits set in ->cpus_ptr. Make it easier for BPF schedulers
by automatically dispatching them to the pinned local DSQs by default. If a
BPF scheduler wants to handle migration disabled tasks explicitly, it can
set SCX_OPS_ENQ_MIGRATION_DISABLED.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c |   23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -123,6 +123,19 @@ enum scx_ops_flags {
 	SCX_OPS_SWITCH_PARTIAL	= 1LLU << 3,
 
 	/*
+	 * A migration disabled task can only execute on its current CPU. By
+	 * default, such tasks are automatically put on the CPU's local DSQ with
+	 * the default slice on enqueue. If this ops flag is set, they also go
+	 * through ops.enqueue().
+	 *
+	 * A migration disabled task never invokes ops.select_cpu() as it can
+	 * only select the current CPU. Also, p->cpus_ptr will only contain its
+	 * current CPU while p->nr_cpus_allowed keeps tracking p->user_cpus_ptr
+	 * and thus may disagree with cpumask_weight(p->cpus_ptr).
+	 */
+	SCX_OPS_ENQ_MIGRATION_DISABLED = 1LLU << 4,
+
+	/*
 	 * CPU cgroup support flags
 	 */
 	SCX_OPS_HAS_CGROUP_WEIGHT = 1LLU << 16,	/* cpu.weight */
@@ -130,6 +143,7 @@ enum scx_ops_flags {
 	SCX_OPS_ALL_FLAGS	= SCX_OPS_KEEP_BUILTIN_IDLE |
 				  SCX_OPS_ENQ_LAST |
 				  SCX_OPS_ENQ_EXITING |
+				  SCX_OPS_ENQ_MIGRATION_DISABLED |
 				  SCX_OPS_SWITCH_PARTIAL |
 				  SCX_OPS_HAS_CGROUP_WEIGHT,
 };
@@ -882,6 +896,7 @@ static bool scx_warned_zero_slice;
 
 static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_last);
 static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_exiting);
+static DEFINE_STATIC_KEY_FALSE(scx_ops_enq_migration_disabled);
 static DEFINE_STATIC_KEY_FALSE(scx_ops_cpu_preempt);
 static DEFINE_STATIC_KEY_FALSE(scx_builtin_idle_enabled);
 
@@ -2014,6 +2029,11 @@ static void do_enqueue_task(struct rq *r
 	    unlikely(p->flags & PF_EXITING))
 		goto local;
 
+	/* see %SCX_OPS_ENQ_MIGRATION_DISABLED */
+	if (!static_branch_unlikely(&scx_ops_enq_migration_disabled) &&
+	    is_migration_disabled(p))
+		goto local;
+
 	if (!SCX_HAS_OP(enqueue))
 		goto global;
 
@@ -5052,6 +5072,7 @@ static void scx_ops_disable_workfn(struc
 		static_branch_disable(&scx_has_op[i]);
 	static_branch_disable(&scx_ops_enq_last);
 	static_branch_disable(&scx_ops_enq_exiting);
+	static_branch_disable(&scx_ops_enq_migration_disabled);
 	static_branch_disable(&scx_ops_cpu_preempt);
 	static_branch_disable(&scx_builtin_idle_enabled);
 	synchronize_rcu();
@@ -5661,6 +5682,8 @@ static int scx_ops_enable(struct sched_e
 
 	if (ops->flags & SCX_OPS_ENQ_EXITING)
 		static_branch_enable(&scx_ops_enq_exiting);
+	if (ops->flags & SCX_OPS_ENQ_MIGRATION_DISABLED)
+		static_branch_enable(&scx_ops_enq_migration_disabled);
 	if (scx_ops.cpu_acquire || scx_ops.cpu_release)
 		static_branch_enable(&scx_ops_cpu_preempt);