diff mbox series

[08/30] sched: Expose css_tg(), __setscheduler_prio() and SCHED_CHANGE_BLOCK()

Message ID 20230128001639.3510083-9-tj@kernel.org (mailing list archive)
State Not Applicable
Headers show
Series [01/30] cgroup: Implement cgroup_show_cftypes() | expand

Commit Message

Tejun Heo Jan. 28, 2023, 12:16 a.m. UTC 
These will be used by a new BPF extensible sched_class.

css_tg() will be used in the init and exit paths to visit all task_groups by
walking cgroups.

__setscheduler_prio() is used to pick the sched_class matching the current
prio of the task. For the new BPF extensible sched_class, the mapping from
the task configuration to sched_class isn't static and depends on a few
factors - e.g. whether the BPF progs implementing the scheduler are loaded
and in a serviceable state. That mapping logic will be added to
__setscheduler_prio().

When the BPF scheduler progs get loaded and unloaded, the mapping changes
and the new sched_class will walk the tasks applying the new mapping using
SCHED_CHANGE_BLOCK() and __setscheduler_prio().

v2: Expose SCHED_CHANGE_BLOCK() too and update the description.

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  | 47 +++----------------------------------------
 kernel/sched/sched.h | 48 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 44 deletions(-)

Comments

kernel test robot Jan. 28, 2023, 5:24 p.m. UTC | #1 
Hi Tejun,

I love your patch! Perhaps something to improve:

[auto build test WARNING on linux/master]
[also build test WARNING on linus/master v6.2-rc5 next-20230127]
[cannot apply to tip/sched/core tj-cgroup/for-next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Tejun-Heo/sched-Encapsulate-task-attribute-change-sequence-into-a-helper-macro/20230128-123001
patch link:    https://lore.kernel.org/r/20230128001639.3510083-9-tj%40kernel.org
patch subject: [PATCH 08/30] sched: Expose css_tg(), __setscheduler_prio() and SCHED_CHANGE_BLOCK()
config: arc-defconfig (https://download.01.org/0day-ci/archive/20230129/202301290130.A9xDBZbR-lkp@intel.com/config)
compiler: arc-elf-gcc (GCC) 12.1.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/intel-lab-lkp/linux/commit/49fe6fbf20db85f7bd19f55cdcd7e957ae0f0983
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Tejun-Heo/sched-Encapsulate-task-attribute-change-sequence-into-a-helper-macro/20230128-123001
        git checkout 49fe6fbf20db85f7bd19f55cdcd7e957ae0f0983
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=arc olddefconfig
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-12.1.0 make.cross W=1 O=build_dir ARCH=arc SHELL=/bin/bash kernel/

If you fix the issue, kindly add following tag where applicable
| Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

>> kernel/sched/core.c:6967:6: warning: no previous prototype for '__setscheduler_prio' [-Wmissing-prototypes]
    6967 | void __setscheduler_prio(struct task_struct *p, int prio)
         |      ^~~~~~~~~~~~~~~~~~~


vim +/__setscheduler_prio +6967 kernel/sched/core.c

  6966	
> 6967	void __setscheduler_prio(struct task_struct *p, int prio)
  6968	{
  6969		if (dl_prio(prio))
  6970			p->sched_class = &dl_sched_class;
  6971		else if (rt_prio(prio))
  6972			p->sched_class = &rt_sched_class;
  6973		else
  6974			p->sched_class = &fair_sched_class;
  6975	
  6976		p->prio = prio;
  6977	}
  6978
diff mbox series

Patch

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 70698725f6de..1fd4e2cde35c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2094,15 +2094,7 @@  void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-struct sched_change_guard {
-	struct task_struct	*p;
-	struct rq		*rq;
-	bool			queued;
-	bool			running;
-	bool			done;
-};
-
-static struct sched_change_guard
+struct sched_change_guard
 sched_change_guard_init(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_change_guard cg = {
@@ -2127,7 +2119,7 @@  sched_change_guard_init(struct rq *rq, struct task_struct *p, int flags)
 	return cg;
 }
 
-static void sched_change_guard_fini(struct sched_change_guard *cg, int flags)
+void sched_change_guard_fini(struct sched_change_guard *cg, int flags)
 {
 	if (cg->queued)
 		enqueue_task(cg->rq, cg->p, flags | ENQUEUE_NOCLOCK);
@@ -2136,34 +2128,6 @@  static void sched_change_guard_fini(struct sched_change_guard *cg, int flags)
 	cg->done = true;
 }
 
-/**
- * SCHED_CHANGE_BLOCK - Nested block for task attribute updates
- * @__rq: Runqueue the target task belongs to
- * @__p: Target task
- * @__flags: DEQUEUE/ENQUEUE_* flags
- *
- * A task may need to be dequeued and put_prev_task'd for attribute updates and
- * set_next_task'd and re-enqueued afterwards. This helper defines a nested
- * block which automatically handles these preparation and cleanup operations.
- *
- *  SCHED_CHANGE_BLOCK(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK) {
- *	  update_attribute(p);
- *        ...
- *  }
- *
- * If @__flags is a variable, the variable may be updated in the block body and
- * the updated value will be used when re-enqueueing @p.
- *
- * If %DEQUEUE_NOCLOCK is specified, the caller is responsible for calling
- * update_rq_clock() beforehand. Otherwise, the rq clock is automatically
- * updated iff the task needs to be dequeued and re-enqueued. Only the former
- * case guarantees that the rq clock is up-to-date inside and after the block.
- */
-#define SCHED_CHANGE_BLOCK(__rq, __p, __flags)					\
-	for (struct sched_change_guard __cg =					\
-			sched_change_guard_init(__rq, __p, __flags);		\
-	     !__cg.done; sched_change_guard_fini(&__cg, __flags))
-
 static inline int __normal_prio(int policy, int rt_prio, int nice)
 {
 	int prio;
@@ -6949,7 +6913,7 @@  int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag
 }
 EXPORT_SYMBOL(default_wake_function);
 
-static void __setscheduler_prio(struct task_struct *p, int prio)
+void __setscheduler_prio(struct task_struct *p, int prio)
 {
 	if (dl_prio(prio))
 		p->sched_class = &dl_sched_class;
@@ -10340,11 +10304,6 @@  void sched_move_task(struct task_struct *tsk)
 	task_rq_unlock(rq, tsk, &rf);
 }
 
-static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
-{
-	return css ? container_of(css, struct task_group, css) : NULL;
-}
-
 static struct cgroup_subsys_state *
 cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 946fdb51b6e6..1927adc6c4bb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -469,6 +469,11 @@  static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
 	return walk_tg_tree_from(&root_task_group, down, up, data);
 }
 
+static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct task_group, css) : NULL;
+}
+
 extern int tg_nop(struct task_group *tg, void *data);
 
 extern void free_fair_sched_group(struct task_group *tg);
@@ -493,6 +498,8 @@  extern long sched_group_rt_runtime(struct task_group *tg);
 extern long sched_group_rt_period(struct task_group *tg);
 extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 
+extern void __setscheduler_prio(struct task_struct *p, int prio);
+
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_online_group(struct task_group *tg,
 			       struct task_group *parent);
@@ -2461,6 +2468,47 @@  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);
 
+struct sched_change_guard {
+	struct task_struct	*p;
+	struct rq		*rq;
+	bool			queued;
+	bool			running;
+	bool			done;
+};
+
+extern struct sched_change_guard
+sched_change_guard_init(struct rq *rq, struct task_struct *p, int flags);
+
+extern void sched_change_guard_fini(struct sched_change_guard *cg, int flags);
+
+/**
+ * SCHED_CHANGE_BLOCK - Nested block for task attribute updates
+ * @__rq: Runqueue the target task belongs to
+ * @__p: Target task
+ * @__flags: DEQUEUE/ENQUEUE_* flags
+ *
+ * A task may need to be dequeued and put_prev_task'd for attribute updates and
+ * set_next_task'd and re-enqueued afterwards. This helper defines a nested
+ * block which automatically handles these preparation and cleanup operations.
+ *
+ *  SCHED_CHANGE_BLOCK(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK) {
+ *	  update_attribute(p);
+ *        ...
+ *  }
+ *
+ * If @__flags is a variable, the variable may be updated in the block body and
+ * the updated value will be used when re-enqueueing @p.
+ *
+ * If %DEQUEUE_NOCLOCK is specified, the caller is responsible for calling
+ * update_rq_clock() beforehand. Otherwise, the rq clock is automatically
+ * updated iff the task needs to be dequeued and re-enqueued. Only the former
+ * case guarantees that the rq clock is up-to-date inside and after the block.
+ */
+#define SCHED_CHANGE_BLOCK(__rq, __p, __flags)					\
+	for (struct sched_change_guard __cg =					\
+			sched_change_guard_init(__rq, __p, __flags);		\
+	     !__cg.done; sched_change_guard_fini(&__cg, __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,