sched_ext: Allow BPF schedulers to disallow specific tasks from joining SCHED_EXT

BPF schedulers might not want to schedule certain tasks - e.g. kernel
threads. This patch adds p->scx.disallow which can be set by BPF schedulers
in such cases. The field can be changed anytime and setting it in
ops.prep_enable() guarantees that the task can never be scheduled by
sched_ext.

scx_qmap is updated with the -d option to disallow a specific PID:

  # echo $$
  1092
  # grep -E '(policy)|(ext\.enabled)' /proc/self/sched
  policy                                       :                    0
  ext.enabled                                  :                    0
  # ./set-scx 1092
  # grep -E '(policy)|(ext\.enabled)' /proc/self/sched
  policy                                       :                    7
  ext.enabled                                  :                    0

Run "scx_qmap -p -d 1092" in another terminal.

  # cat /sys/kernel/sched_ext/nr_rejected
  1
  # grep -E '(policy)|(ext\.enabled)' /proc/self/sched
  policy                                       :                    0
  ext.enabled                                  :                    0
  # ./set-scx 1092
  setparam failed for 1092 (Permission denied)

- v4: Refreshed on top of tip:sched/core.

- v3: Update description to reflect /sys/kernel/sched_ext interface change.

- v2: Use atomic_long_t instead of atomic64_t for scx_kick_cpus_pnt_seqs to
      accommodate 32bit archs.

Signed-off-by: Tejun Heo <[email protected]>
Suggested-by: Barret Rhoden <[email protected]>
Reviewed-by: David Vernet <[email protected]>
Acked-by: Josh Don <[email protected]>
Acked-by: Hao Luo <[email protected]>
Acked-by: Barret Rhoden <[email protected]>

3 files changed, 56 insertions, 0 deletions

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 3dc515b3351f..8ff30b80e862 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -483,6 +483,8 @@ struct static_key_false scx_has_op[SCX_OPI_END] =
 static atomic_t scx_exit_kind = ATOMIC_INIT(SCX_EXIT_DONE);
 static struct scx_exit_info *scx_exit_info;
 
+static atomic_long_t scx_nr_rejected = ATOMIC_LONG_INIT(0);
+
 /*
  * The maximum amount of time in jiffies that a task may be runnable without
  * being scheduled on a CPU. If this timeout is exceeded, it will trigger
@@ -2332,6 +2334,8 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
 {
 	int ret;
 
+	p->scx.disallow = false;
+
 	if (SCX_HAS_OP(init_task)) {
 		struct scx_init_task_args args = {
 			.fork = fork,
@@ -2346,6 +2350,27 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool
 
 	scx_set_task_state(p, SCX_TASK_INIT);
 
+	if (p->scx.disallow) {
+		struct rq *rq;
+		struct rq_flags rf;
+
+		rq = task_rq_lock(p, &rf);
+
+		/*
+		 * We're either in fork or load path and @p->policy will be
+		 * applied right after. Reverting @p->policy here and rejecting
+		 * %SCHED_EXT transitions from scx_check_setscheduler()
+		 * guarantees that if ops.init_task() sets @p->disallow, @p can
+		 * never be in SCX.
+		 */
+		if (p->policy == SCHED_EXT) {
+			p->policy = SCHED_NORMAL;
+			atomic_long_inc(&scx_nr_rejected);
+		}
+
+		task_rq_unlock(rq, p, &rf);
+	}
+
 	p->scx.flags |= SCX_TASK_RESET_RUNNABLE_AT;
 	return 0;
 }
@@ -2549,6 +2574,18 @@ static void switched_from_scx(struct rq *rq, struct task_struct *p)
 static void wakeup_preempt_scx(struct rq *rq, struct task_struct *p,int wake_flags) {}
 static void switched_to_scx(struct rq *rq, struct task_struct *p) {}
 
+int scx_check_setscheduler(struct task_struct *p, int policy)
+{
+	lockdep_assert_rq_held(task_rq(p));
+
+	/* if disallow, reject transitioning into SCX */
+	if (scx_enabled() && READ_ONCE(p->scx.disallow) &&
+	    p->policy != policy && policy == SCHED_EXT)
+		return -EACCES;
+
+	return 0;
+}
+
 /*
  * Omitted operations:
  *
@@ -2703,9 +2740,17 @@ static ssize_t scx_attr_switch_all_show(struct kobject *kobj,
 }
 SCX_ATTR(switch_all);
 
+static ssize_t scx_attr_nr_rejected_show(struct kobject *kobj,
+					 struct kobj_attribute *ka, char *buf)
+{
+	return sysfs_emit(buf, "%ld\n", atomic_long_read(&scx_nr_rejected));
+}
+SCX_ATTR(nr_rejected);
+
 static struct attribute *scx_global_attrs[] = {
 	&scx_attr_state.attr,
 	&scx_attr_switch_all.attr,
+	&scx_attr_nr_rejected.attr,
 	NULL,
 };
 
@@ -3178,6 +3223,8 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 	atomic_set(&scx_exit_kind, SCX_EXIT_NONE);
 	scx_warned_zero_slice = false;
 
+	atomic_long_set(&scx_nr_rejected, 0);
+
 	/*
 	 * Keep CPUs stable during enable so that the BPF scheduler can track
 	 * online CPUs by watching ->on/offline_cpu() after ->init().
@@ -3476,6 +3523,9 @@ static int bpf_scx_btf_struct_access(struct bpf_verifier_log *log,
 		if (off >= offsetof(struct task_struct, scx.slice) &&
 		    off + size <= offsetofend(struct task_struct, scx.slice))
 			return SCALAR_VALUE;
+		if (off >= offsetof(struct task_struct, scx.disallow) &&
+		    off + size <= offsetofend(struct task_struct, scx.disallow))
+			return SCALAR_VALUE;
 	}
 
 	return -EACCES;
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index 56fcdb0b2c05..33a9f7fe5832 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -35,6 +35,7 @@ void scx_pre_fork(struct task_struct *p);
 int scx_fork(struct task_struct *p);
 void scx_post_fork(struct task_struct *p);
 void scx_cancel_fork(struct task_struct *p);
+int scx_check_setscheduler(struct task_struct *p, int policy);
 bool task_should_scx(struct task_struct *p);
 void init_sched_ext_class(void);
 
@@ -72,6 +73,7 @@ static inline void scx_pre_fork(struct task_struct *p) {}
 static inline int scx_fork(struct task_struct *p) { return 0; }
 static inline void scx_post_fork(struct task_struct *p) {}
 static inline void scx_cancel_fork(struct task_struct *p) {}
+static inline int scx_check_setscheduler(struct task_struct *p, int policy) { return 0; }
 static inline bool task_on_scx(const struct task_struct *p) { return false; }
 static inline void init_sched_ext_class(void) {}
 
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 18d44d180db1..4fa59c9f69ac 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -714,6 +714,10 @@ recheck:
 		goto unlock;
 	}
 
+	retval = scx_check_setscheduler(p, policy);
+	if (retval)
+		goto unlock;
+
 	/*
 	 * If not changing anything there's no need to proceed further,
 	 * but store a possible modification of reset_on_fork.