sched_ext: Add boilerplate for extensible scheduler class

This adds dummy implementations of sched_ext interfaces which interact with
the scheduler core and hook them in the correct places. As they're all
dummies, this doesn't cause any behavior changes. This is split out to help
reviewing.

v2: balance_scx_on_up() dropped. This will be handled in sched_ext proper.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
new file mode 100644 (file)
index 0000000..a05dfcf
--- /dev/null
+++ b/include/linux/sched/ext.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SCHED_EXT_H
+#define _LINUX_SCHED_EXT_H
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+#error "NOT IMPLEMENTED YET"
+#else  /* !CONFIG_SCHED_CLASS_EXT */
+
+static inline void sched_ext_free(struct task_struct *p) {}
+
+#endif /* CONFIG_SCHED_CLASS_EXT */
+#endif /* _LINUX_SCHED_EXT_H */

diff --git a/kernel/fork.c b/kernel/fork.c
index e601fdf787c3fe501676bdc39404a3c40db098ef..741d962db0d958eadb988b85572aa71997df4a68 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -23,6 +23,7 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/sched/cputime.h>
+#include <linux/sched/ext.h>
 #include <linux/seq_file.h>
 #include <linux/rtmutex.h>
 #include <linux/init.h>
@@ -971,6 +972,7 @@ void __put_task_struct(struct task_struct *tsk)
        WARN_ON(refcount_read(&tsk->usage));
        WARN_ON(tsk == current);
 
+       sched_ext_free(tsk);
        io_uring_free(tsk);
        cgroup_free(tsk);
        task_numa_free(tsk, true);

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0bfbceebc4e924dc0bd361992a135aaec776e3f6..d8c963fea9eb412e78ba682fa78459d83a0d95f2 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4559,6 +4559,8 @@ late_initcall(sched_core_sysctl_init);
  */
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
+       int ret;
+
        __sched_fork(clone_flags, p);
        /*
         * We mark the process as NEW here. This guarantees that
@@ -4595,12 +4597,16 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
                p->sched_reset_on_fork = 0;
        }
 
-       if (dl_prio(p->prio))
-               return -EAGAIN;
-       else if (rt_prio(p->prio))
+       scx_pre_fork(p);
+
+       if (dl_prio(p->prio)) {
+               ret = -EAGAIN;
+               goto out_cancel;
+       } else if (rt_prio(p->prio)) {
                p->sched_class = &rt_sched_class;
-       else
+       } else {
                p->sched_class = &fair_sched_class;
+       }
 
        init_entity_runnable_average(&p->se);
 
@@ -4618,6 +4624,10 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
        RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
        return 0;
+
+out_cancel:
+       scx_cancel_fork(p);
+       return ret;
 }
 
 int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
@@ -4648,16 +4658,18 @@ int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
                p->sched_class->task_fork(p);
        raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
-       return 0;
+       return scx_fork(p);
 }
 
 void sched_cancel_fork(struct task_struct *p)
 {
+       scx_cancel_fork(p);
 }
 
 void sched_post_fork(struct task_struct *p)
 {
        uclamp_post_fork(p);
+       scx_post_fork(p);
 }
 
 unsigned long to_ratio(u64 period, u64 runtime)
@@ -5800,7 +5812,7 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
         * We can terminate the balance pass as soon as we know there is
         * a runnable task of @class priority or higher.
         */
-       for_class_range(class, prev->sched_class, &idle_sched_class) {
+       for_balance_class_range(class, prev->sched_class, &idle_sched_class) {
                if (class->balance(rq, prev, rf))
                        break;
        }
@@ -5818,6 +5830,9 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
        const struct sched_class *class;
        struct task_struct *p;
 
+       if (scx_enabled())
+               goto restart;
+
        /*
         * Optimization: we know that if all tasks are in the fair class we can
         * call that function directly, but only if the @prev task wasn't of a
@@ -5858,7 +5873,7 @@ restart:
        if (prev->dl_server)
                prev->dl_server = NULL;
 
-       for_each_class(class) {
+       for_each_active_class(class) {
                p = class->pick_next_task(rq);
                if (p)
                        return p;
@@ -5891,7 +5906,7 @@ static inline struct task_struct *pick_task(struct rq *rq)
        const struct sched_class *class;
        struct task_struct *p;
 
-       for_each_class(class) {
+       for_each_active_class(class) {
                p = class->pick_task(rq);
                if (p)
                        return p;
@@ -8355,6 +8370,7 @@ void __init sched_init(void)
        balance_push_set(smp_processor_id(), false);
 #endif
        init_sched_fair_class();
+       init_sched_ext_class();
 
        psi_init();
 

diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
new file mode 100644 (file)
index 0000000..6a93c48
--- /dev/null
+++ b/kernel/sched/ext.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+#error "NOT IMPLEMENTED YET"
+#else  /* CONFIG_SCHED_CLASS_EXT */
+
+#define scx_enabled()          false
+
+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 void init_sched_ext_class(void) {}
+
+#define for_each_active_class          for_each_class
+#define for_balance_class_range                for_class_range
+
+#endif /* CONFIG_SCHED_CLASS_EXT */
+
+#if defined(CONFIG_SCHED_CLASS_EXT) && defined(CONFIG_SMP)
+#error "NOT IMPLEMENTED YET"
+#else
+static inline void scx_update_idle(struct rq *rq, bool idle) {}
+#endif

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6e78d071beb58ad26665be2c87e46bc7bab061b4..c7a218123b7ac6c7b62ec54acd7403f7b2feb058 100644 (file)
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -452,11 +452,13 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
 
 static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
 {
+       scx_update_idle(rq, false);
 }
 
 static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
 {
        update_idle_core(rq);
+       scx_update_idle(rq, true);
        schedstat_inc(rq->sched_goidle);
 }
 

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 25660dc9f639d1e67de5802b5266705e952b0812..c52ad5fdd096001cf222a867478ba38a78ef0806 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3658,4 +3658,6 @@ static inline void balance_callbacks(struct rq *rq, struct balance_callback *hea
 
 #endif
 
+#include "ext.h"
+
 #endif /* _KERNEL_SCHED_SCHED_H */