[RFC PATCH v3 12/16] sched: A quick and dirty cgroup tagging interface

[Vineeth Remanan Pillai]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Marks all tasks in a cgroup as matching for core-scheduling.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Julien Desfossez <jdesfossez@xxxxxxxxxxxxxxxx>
Signed-off-by: Vineeth Remanan Pillai <vpillai@xxxxxxxxxxxxxxxx>
---

Changes in v3
-------------
- Fixes the refcount management when deleting a tagged cgroup.
  - Julien Desfossez

---
 kernel/sched/core.c  | 78 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/sched.h |  4 +++
 2 files changed, 82 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 112d70f2b1e5..3164c6b33553 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6658,6 +6658,15 @@ static void sched_change_group(struct task_struct *tsk, int type)
 	tg = container_of(task_css_check(tsk, cpu_cgrp_id, true),
 			  struct task_group, css);
 	tg = autogroup_task_group(tsk, tg);
+
+#ifdef CONFIG_SCHED_CORE
+	if ((unsigned long)tsk->sched_task_group == tsk->core_cookie)
+		tsk->core_cookie = 0UL;
+
+	if (tg->tagged /* && !tsk->core_cookie ? */)
+		tsk->core_cookie = (unsigned long)tg;
+#endif
+
 	tsk->sched_task_group = tg;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6737,6 +6746,18 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 	return 0;
 }
 
+static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css)
+{
+#ifdef CONFIG_SCHED_CORE
+	struct task_group *tg = css_tg(css);
+
+	if (tg->tagged) {
+		sched_core_put();
+		tg->tagged = 0;
+	}
+#endif
+}
+
 static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
 {
 	struct task_group *tg = css_tg(css);
@@ -7117,6 +7138,46 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_SCHED_CORE
+static u64 cpu_core_tag_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	struct task_group *tg = css_tg(css);
+
+	return !!tg->tagged;
+}
+
+static int cpu_core_tag_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val)
+{
+	struct task_group *tg = css_tg(css);
+	struct css_task_iter it;
+	struct task_struct *p;
+
+	if (val > 1)
+		return -ERANGE;
+
+	if (!static_branch_likely(&sched_smt_present))
+		return -EINVAL;
+
+	if (tg->tagged == !!val)
+		return 0;
+
+	tg->tagged = !!val;
+
+	if (!!val)
+		sched_core_get();
+
+	css_task_iter_start(css, 0, &it);
+	while ((p = css_task_iter_next(&it)))
+		p->core_cookie = !!val ? (unsigned long)tg : 0UL;
+	css_task_iter_end(&it);
+
+	if (!val)
+		sched_core_put();
+
+	return 0;
+}
+#endif
+
 static struct cftype cpu_legacy_files[] = {
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	{
@@ -7152,6 +7213,14 @@ static struct cftype cpu_legacy_files[] = {
 		.read_u64 = cpu_rt_period_read_uint,
 		.write_u64 = cpu_rt_period_write_uint,
 	},
+#endif
+#ifdef CONFIG_SCHED_CORE
+	{
+		.name = "tag",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = cpu_core_tag_read_u64,
+		.write_u64 = cpu_core_tag_write_u64,
+	},
 #endif
 	{ }	/* Terminate */
 };
@@ -7319,6 +7388,14 @@ static struct cftype cpu_files[] = {
 		.seq_show = cpu_max_show,
 		.write = cpu_max_write,
 	},
+#endif
+#ifdef CONFIG_SCHED_CORE
+	{
+		.name = "tag",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.read_u64 = cpu_core_tag_read_u64,
+		.write_u64 = cpu_core_tag_write_u64,
+	},
 #endif
 	{ }	/* terminate */
 };
@@ -7326,6 +7403,7 @@ static struct cftype cpu_files[] = {
 struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_alloc	= cpu_cgroup_css_alloc,
 	.css_online	= cpu_cgroup_css_online,
+	.css_offline	= cpu_cgroup_css_offline,
 	.css_released	= cpu_cgroup_css_released,
 	.css_free	= cpu_cgroup_css_free,
 	.css_extra_stat_show = cpu_extra_stat_show,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0cbcfb6c8ee4..bd9b473ebde2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -363,6 +363,10 @@ struct cfs_bandwidth {
 struct task_group {
 	struct cgroup_subsys_state css;
 
+#ifdef CONFIG_SCHED_CORE
+	int			tagged;
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/* schedulable entities of this group on each CPU */
 	struct sched_entity	**se;
-- 
2.17.1