[PATCH 13/39] sched_ext: Add boilerplate for extensible scheduler class

From: Tejun Heo
Date: Wed May 01 2024 - 11:16:37 EST

Next message: Tejun Heo: "[PATCH 16/39] sched_ext: Add sysrq-S which disables the BPF scheduler"
Previous message: Nathan Chancellor: "Re: [PATCH] selftests/harness: fix many "format string is empty" warnings"
In reply to: Tejun Heo: "[PATCH 12/39] sched: Add normal_policy()"
Next in thread: Tejun Heo: "[PATCH 16/39] sched_ext: Add sysrq-S which disables the BPF scheduler"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

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@xxxxxxxxxx>
Reviewed-by: David Vernet <dvernet@xxxxxxxx>
Acked-by: Josh Don <joshdon@xxxxxxxxxx>
Acked-by: Hao Luo <haoluo@xxxxxxxxxx>
Acked-by: Barret Rhoden <brho@xxxxxxxxxx>
---
include/linux/sched/ext.h | 12 ++++++++++++
kernel/fork.c | 2 ++
kernel/sched/core.c | 32 ++++++++++++++++++++++++--------
kernel/sched/cpufreq_schedutil.c | 4 +++-
kernel/sched/ext.h | 25 +++++++++++++++++++++++++
kernel/sched/idle.c | 2 ++
kernel/sched/sched.h | 2 ++
7 files changed, 70 insertions(+), 9 deletions(-)
create mode 100644 include/linux/sched/ext.h
create mode 100644 kernel/sched/ext.h

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
new file mode 100644
index 000000000000..a05dfcf533b0
--- /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 02f12033db9c..6238b1ae3306 100644
--- 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>
@@ -970,6 +971,7 @@ 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 7542a39f1fde..0231905ec827 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4767,6 +4767,8 @@ 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
@@ -4803,12 +4805,16 @@ 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);

@@ -4826,6 +4832,10 @@ 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)
@@ -4856,16 +4866,18 @@ 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)
@@ -6017,7 +6029,7 @@ 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;
}
@@ -6035,6 +6047,9 @@ __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
@@ -6075,7 +6090,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
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;
@@ -6108,7 +6123,7 @@ 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;
@@ -10135,6 +10150,7 @@ 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/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 972b7dd65af2..0827864c35ff 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -197,7 +197,9 @@ unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,

static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
{
- unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+ unsigned long min, max;
+ unsigned long util = cpu_util_cfs_boost(sg_cpu->cpu) +
+ scx_cpuperf_target(sg_cpu->cpu);

util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
util = max(util, boost);
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
new file mode 100644
index 000000000000..42bd1e47b304
--- /dev/null
+++ b/kernel/sched/ext.h
@@ -0,0 +1,25 @@
+/* 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) {}
+static inline u32 scx_cpuperf_target(s32 cpu) { return 0; }
+
+#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 6135fbe83d68..3b6540cc436a 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -458,11 +458,13 @@ 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 11b4345d2638..fbd1e9ea8b18 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3540,4 +3540,6 @@ enum cpu_cftype_id {
extern struct cftype cpu_cftypes[CPU_CFTYPE_CNT + 1];
#endif /* CONFIG_CGROUP_SCHED */

+#include "ext.h"
+
#endif /* _KERNEL_SCHED_SCHED_H */
--
2.44.0

Next message: Tejun Heo: "[PATCH 16/39] sched_ext: Add sysrq-S which disables the BPF scheduler"
Previous message: Nathan Chancellor: "Re: [PATCH] selftests/harness: fix many "format string is empty" warnings"
In reply to: Tejun Heo: "[PATCH 12/39] sched: Add normal_policy()"
Next in thread: Tejun Heo: "[PATCH 16/39] sched_ext: Add sysrq-S which disables the BPF scheduler"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]