diff mbox series

[05/34] sched: Add sched_class->switching_to() and expose check_class_changing/changed()

Message ID 20230711011412.100319-6-tj@kernel.org (mailing list archive)
State Not Applicable
Headers show
Series [01/34] cgroup: Implement cgroup_show_cftypes() | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch, async
bpf/vmtest-bpf-PR success PR summary
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-3 success Logs for build for s390x with gcc
bpf/vmtest-bpf-VM_Test-4 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-5 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-6 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-7 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-8 pending Logs for test_maps on s390x with gcc
bpf/vmtest-bpf-VM_Test-9 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-10 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-11 success Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-12 pending Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-VM_Test-13 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-14 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-15 success Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-16 pending Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-VM_Test-17 fail Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-18 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-19 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-20 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-21 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-22 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-23 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-24 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-25 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-26 pending Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-27 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-28 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-VM_Test-29 success Logs for veristat

Commit Message

Tejun Heo July 11, 2023, 1:13 a.m. UTC 
When a task switches to a new sched_class, the prev and new classes are
notified through ->switched_from() and ->switched_to(), respectively, after
the switching is done.

A new BPF extensible sched_class will have callbacks that allow the BPF
scheduler to keep track of relevant task states (like priority and cpumask).
Those callbacks aren't called while a task is on a different sched_class.
When a task comes back, we wanna tell the BPF progs the up-to-date state
before the task gets enqueued, so we need a hook which is called before the
switching is committed.

This patch adds ->switching_to() which is called during sched_class switch
through check_class_changing() before the task is restored. Also, this patch
exposes check_class_changing/changed() in kernel/sched/sched.h. They will be
used by the new BPF extensible sched_class to implement implicit sched_class
switching which is used e.g. when falling back to CFS when the BPF scheduler
fails or unloads.

This is a prep patch and doesn't cause any behavior changes. The new
operation and exposed functions aren't used yet.

v2: Improve patch description w/ details on planned use.

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>
---
 kernel/sched/core.c  | 19 ++++++++++++++++---
 kernel/sched/sched.h |  7 +++++++
 2 files changed, 23 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a205d00f0669..29f75a31b414 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2178,6 +2178,17 @@  inline int task_curr(const struct task_struct *p)
 	return cpu_curr(task_cpu(p)) == p;
 }
 
+/*
+ * ->switching_to() is called with the pi_lock and rq_lock held and must not
+ * mess with locking.
+ */
+void check_class_changing(struct rq *rq, struct task_struct *p,
+			  const struct sched_class *prev_class)
+{
+	if (prev_class != p->sched_class && p->sched_class->switching_to)
+		p->sched_class->switching_to(rq, p);
+}
+
 /*
  * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock,
  * use the balance_callback list if you want balancing.
@@ -2185,9 +2196,9 @@  inline int task_curr(const struct task_struct *p)
  * this means any call to check_class_changed() must be followed by a call to
  * balance_callback().
  */
-static inline void check_class_changed(struct rq *rq, struct task_struct *p,
-				       const struct sched_class *prev_class,
-				       int oldprio)
+void check_class_changed(struct rq *rq, struct task_struct *p,
+			 const struct sched_class *prev_class,
+			 int oldprio)
 {
 	if (prev_class != p->sched_class) {
 		if (prev_class->switched_from)
@@ -7140,6 +7151,7 @@  void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	}
 
 	__setscheduler_prio(p, prio);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
@@ -7768,6 +7780,7 @@  static int __sched_setscheduler(struct task_struct *p,
 		__setscheduler_prio(p, newprio);
 	}
 	__setscheduler_uclamp(p, attr);
+	check_class_changing(rq, p, prev_class);
 
 	if (queued) {
 		/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1a12a0d9ea40..0a25bcd8d9d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2211,6 +2211,7 @@  struct sched_class {
 	 * cannot assume the switched_from/switched_to pair is serialized by
 	 * rq->lock. They are however serialized by p->pi_lock.
 	 */
+	void (*switching_to) (struct rq *this_rq, struct task_struct *task);
 	void (*switched_from)(struct rq *this_rq, struct task_struct *task);
 	void (*switched_to)  (struct rq *this_rq, struct task_struct *task);
 	void (*reweight_task)(struct rq *this_rq, struct task_struct *task,
@@ -2451,6 +2452,12 @@  static inline void sub_nr_running(struct rq *rq, unsigned count)
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
+extern void check_class_changing(struct rq *rq, struct task_struct *p,
+				 const struct sched_class *prev_class);
+extern void check_class_changed(struct rq *rq, struct task_struct *p,
+				const struct sched_class *prev_class,
+				int oldprio);
+
 extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
 #ifdef CONFIG_PREEMPT_RT