sched: Introduce smart grid scheduling strategy for cfs

hulk inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I7BQZ0
CVE: NA

----------------------------------------

We want to dynamically expand or shrink the affinity range of tasks
based on the CPU topology level while meeting the minimum resource
requirements of tasks.

We divide several level of affinity domains according to sched domains:

level4   * SOCKET  [                                                  ]
level3   * DIE     [                             ]
level2   * MC      [             ] [             ]
level1   * SMT     [     ] [     ] [     ] [     ]
level0   * CPU      0   1   2   3   4   5   6   7

Whether users tend to choose power saving or performance will affect
strategy of adjusting affinity, when selecting the power saving mode,
we will choose a more appropriate affinity based on the energy model
to reduce power consumption, while considering the QOS of resources
such as CPU and memory consumption, for instance, if the current task
CPU load is less than required, smart grid will judge whether to aggregate
tasks together into a smaller range or not according to energy model.

The main difference from EAS is that we pay more attention to the impact
of power consumption brought by such as cpuidle and DVFS, and classify
tasks to reduce interference and ensure resource QOS in each divided unit,
which are more suitable for general-purpose on non-heterogeneous CPUs.

        --------        --------        --------
       | group0 |      | group1 |      | group2 |
        --------        --------        --------
	   |                |              |
	   v                |              v
       ---------------------+-----     -----------------
      |                  ---v--   |   |
      |       DIE0      |  MC1 |  |   |   DIE1
      |                  ------   |   |
       ---------------------------     -----------------

We regularly count the resource satisfaction of groups, and adjust the
affinity, scheduling balance and migrating memory will be considered
based on memory location for better meetting resource requirements.
Signed-off-by: NHui Tang <tanghui20@huawei.com>
Signed-off-by: NWang ShaoBo <bobo.shaobowang@huawei.com>
Reviewed-by: NChen Hui <judy.chenhui@huawei.com>
Reviewed-by: NZhang Qiao <zhangqiao22@huawei.com>
Signed-off-by: NZhang Changzhong <zhangchangzhong@huawei.com>

fs/proc/array.c

@@ -386,6 +386,16 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
 		   cpumask_pr_args(&task->cpus_allowed));
 }
 
+#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY
+static void task_cpus_preferred(struct seq_file *m, struct task_struct *task)
+{
+	seq_printf(m, "Cpus_preferred:\t%*pb\n",
+		   cpumask_pr_args(task->prefer_cpus));
+	seq_printf(m, "Cpus_preferred_list:\t%*pbl\n",
+		   cpumask_pr_args(task->prefer_cpus));
+}
+#endif
+
 static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
 {
 	seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state);
@@ -414,6 +424,9 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
 	task_cpus_allowed(m, task);
 	cpuset_task_status_allowed(m, task);
 	task_context_switch_counts(m, task);
+#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY
+	task_cpus_preferred(m, task);
+#endif
 	return 0;
 }
 

include/linux/sched.h

@@ -2000,4 +2000,17 @@ int sched_prefer_cpus_fork(struct task_struct *p, struct task_struct *orig);
 void sched_prefer_cpus_free(struct task_struct *p);
 #endif
 
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+extern struct static_key __smart_grid_used;
+static inline bool smart_grid_used(void)
+{
+	return static_key_false(&__smart_grid_used);
+}
+#else
+static inline bool smart_grid_used(void)
+{
+	return false;
+}
+#endif
+
 #endif

include/linux/sched/sysctl.h

@@ -36,6 +36,10 @@ extern unsigned int sysctl_sched_child_runs_first;
 extern int sysctl_sched_util_low_pct;
 #endif
 
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+extern int sysctl_affinity_adjust_delay_ms;
+#endif
+
 enum sched_tunable_scaling {
 	SCHED_TUNABLESCALING_NONE,
 	SCHED_TUNABLESCALING_LOG,

init/Kconfig

@@ -834,6 +834,19 @@ config QOS_SCHED_DYNAMIC_AFFINITY
 	 of taskgroup is below threshold setted, otherwise make taskgroup to use
 	 cpus allowed.
 
+config QOS_SCHED_SMART_GRID
+	bool "qos smart grid scheduler"
+	depends on FAIR_GROUP_SCHED && QOS_SCHED_DYNAMIC_AFFINITY
+	default n
+	help
+	 This feature is used for power consumption tuning in server scenario.
+	 This can be divided into the following aspects:
+	  1. User interface, manage user needs.
+	  2. Collect tasks' features to ensure key tasks' QOS.
+	  3. Weaken the influence the impact of CPU frequency and cpuidle
+	     adjustment on tasks.
+	  4. Docking EAS (Energy Aware Scheduling) model.
+
 config CGROUP_PIDS
 	bool "PIDs controller"
 	help

kernel/sched/core.c

@@ -5842,6 +5842,7 @@ int sched_cpu_activate(unsigned int cpu)
 		static_branch_inc_cpuslocked(&sched_smt_present);
 #endif
 	set_cpu_active(cpu, true);
+	tg_update_affinity_domains(cpu, 1);
 
 	if (sched_smp_initialized) {
 		sched_domains_numa_masks_set(cpu);
@@ -5900,6 +5901,7 @@ int sched_cpu_deactivate(unsigned int cpu)
 		return ret;
 	}
 	sched_domains_numa_masks_clear(cpu);
+	tg_update_affinity_domains(cpu, 0);
 	return 0;
 }
 
@@ -5970,6 +5972,8 @@ void __init sched_init_smp(void)
 	init_sched_dl_class();
 
 	sched_smp_initialized = true;
+
+	init_auto_affinity(&root_task_group);
 }
 
 static int __init migration_init(void)
@@ -6530,6 +6534,9 @@ void sched_move_task(struct task_struct *tsk)
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq_flags rf;
 	struct rq *rq;
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+	struct affinity_domain *ad;
+#endif
 
 	rq = task_rq_lock(tsk, &rf);
 	update_rq_clock(rq);
@@ -6550,6 +6557,14 @@ void sched_move_task(struct task_struct *tsk)
 		set_curr_task(rq, tsk);
 
 	task_rq_unlock(rq, tsk, &rf);
+
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+	if (smart_grid_used()) {
+		ad = &task_group(tsk)->auto_affinity->ad;
+		set_prefer_cpus_ptr(tsk, ad->domains[ad->curr_level]);
+	}
+#endif
+
 }
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -6969,6 +6984,117 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
 }
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+int tg_set_dynamic_affinity_mode(struct task_group *tg, u64 mode)
+{
+	struct auto_affinity *auto_affi = tg->auto_affinity;
+	int ret = 0;
+
+	raw_spin_lock_irq(&auto_affi->lock);
+
+	/* auto mode*/
+	if (mode == 1) {
+		start_auto_affinity(auto_affi);
+	} else if (mode == 0) {
+		stop_auto_affinity(auto_affi);
+	} else {
+		raw_spin_unlock_irq(&auto_affi->lock);
+		return -EINVAL;
+	}
+
+	auto_affi->mode = mode;
+	raw_spin_unlock_irq(&auto_affi->lock);
+
+	return ret;
+}
+
+static u64 cpu_affinity_mode_read_u64(struct cgroup_subsys_state *css,
+					      struct cftype *cft)
+{
+	struct task_group *tg = css_tg(css);
+
+	return tg->auto_affinity->mode;
+}
+
+static int cpu_affinity_mode_write_u64(struct cgroup_subsys_state *css,
+				   struct cftype *cftype, u64 mode)
+{
+	return tg_set_dynamic_affinity_mode(css_tg(css), mode);
+}
+
+int tg_set_affinity_period(struct task_group *tg, u64 period_ms)
+{
+	if (period_ms > U64_MAX / NSEC_PER_MSEC)
+		return -EINVAL;
+
+	raw_spin_lock_irq(&tg->auto_affinity->lock);
+	tg->auto_affinity->period = ms_to_ktime(period_ms);
+	raw_spin_unlock_irq(&tg->auto_affinity->lock);
+	return 0;
+}
+
+u64 tg_get_affinity_period(struct task_group *tg)
+{
+	return ktime_to_ms(tg->auto_affinity->period);
+}
+
+static int cpu_affinity_period_write_uint(struct cgroup_subsys_state *css,
+					  struct cftype *cftype, u64 period)
+{
+	return tg_set_affinity_period(css_tg(css), period);
+}
+
+static u64 cpu_affinity_period_read_uint(struct cgroup_subsys_state *css,
+					 struct cftype *cft)
+{
+	return tg_get_affinity_period(css_tg(css));
+}
+
+static int cpu_affinity_domain_mask_write_u64(struct cgroup_subsys_state *css,
+					      struct cftype *cftype,
+					      u64 mask)
+{
+	struct task_group *tg = css_tg(css);
+	struct affinity_domain *ad = &tg->auto_affinity->ad;
+	u16 full = (1 << ad->dcount) - 1;
+
+	if (mask > full)
+		return -EINVAL;
+
+	raw_spin_lock_irq(&tg->auto_affinity->lock);
+	ad->domain_mask = mask;
+	raw_spin_unlock_irq(&tg->auto_affinity->lock);
+	return 0;
+}
+
+static u64 cpu_affinity_domain_mask_read_u64(struct cgroup_subsys_state *css,
+					     struct cftype *cft)
+{
+	struct task_group *tg = css_tg(css);
+
+	return tg->auto_affinity->ad.domain_mask;
+}
+
+static int cpu_affinity_stat_show(struct seq_file *sf, void *v)
+{
+	struct task_group *tg = css_tg(seq_css(sf));
+	struct auto_affinity *auto_affi = tg->auto_affinity;
+	struct affinity_domain *ad = &auto_affi->ad;
+	int i;
+
+	seq_printf(sf, "period_active %d\n", auto_affi->period_active);
+	seq_printf(sf, "dcount %d\n", ad->dcount);
+	seq_printf(sf, "domain_mask 0x%x\n", ad->domain_mask);
+	seq_printf(sf, "curr_level %d\n", ad->curr_level);
+	for (i = 0; i < ad->dcount; i++)
+		seq_printf(sf, "sd_level %d, cpu list %*pbl, stay_cnt %llu\n",
+			i, cpumask_pr_args(ad->domains[i]),
+			schedstat_val(ad->stay_cnt[i]));
+
+	return 0;
+}
+#endif /* CONFIG_QOS_SCHED_SMART_GRID */
+
 #ifdef CONFIG_QOS_SCHED
 static int tg_change_scheduler(struct task_group *tg, void *data)
 {
@@ -7073,6 +7199,27 @@ static struct cftype cpu_legacy_files[] = {
 		.read_s64 = cpu_qos_read,
 		.write_s64 = cpu_qos_write,
 	},
+#endif
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+	{
+		.name = "dynamic_affinity_mode",
+		.read_u64 = cpu_affinity_mode_read_u64,
+		.write_u64 = cpu_affinity_mode_write_u64,
+	},
+	{
+		.name = "affinity_period_ms",
+		.read_u64 = cpu_affinity_period_read_uint,
+		.write_u64 = cpu_affinity_period_write_uint,
+	},
+	{
+		.name = "affinity_domain_mask",
+		.read_u64 = cpu_affinity_domain_mask_read_u64,
+		.write_u64 = cpu_affinity_domain_mask_write_u64,
+	},
+	{
+		.name = "affinity_stat",
+		.seq_show = cpu_affinity_stat_show,
+	},
 #endif
 	{ }	/* Terminate */
 };

kernel/sched/fair.c

@@ -5281,6 +5281,417 @@ static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {}
 
 #endif /* CONFIG_CFS_BANDWIDTH */
 
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+#define AUTO_AFFINITY_DEFAULT_PERIOD_MS 2000
+#define IS_DOMAIN_SET(level, mask)	((1 << (level)) & (mask))
+
+static inline unsigned long cpu_util(int cpu);
+static unsigned long target_load(int cpu, int type);
+static unsigned long capacity_of(int cpu);
+static int sched_idle_cpu(int cpu);
+static unsigned long weighted_cpuload(struct rq *rq);
+
+int sysctl_affinity_adjust_delay_ms = 5000;
+
+struct static_key __smart_grid_used;
+
+static void smart_grid_usage_inc(void)
+{
+	static_key_slow_inc_cpuslocked(&__smart_grid_used);
+}
+
+static void smart_grid_usage_dec(void)
+{
+	static_key_slow_dec_cpuslocked(&__smart_grid_used);
+}
+
+static void tg_update_task_prefer_cpus(struct task_group *tg)
+{
+	struct affinity_domain *ad = &tg->auto_affinity->ad;
+	struct task_struct *task;
+	struct css_task_iter it;
+
+	css_task_iter_start(&tg->css, 0, &it);
+	while ((task = css_task_iter_next(&it))) {
+		if (tg == &root_task_group && !task->mm)
+			continue;
+
+		set_prefer_cpus_ptr(task, ad->domains[ad->curr_level]);
+	}
+	css_task_iter_end(&it);
+}
+
+static void affinity_domain_up(struct task_group *tg)
+{
+	struct affinity_domain *ad = &tg->auto_affinity->ad;
+	u16 level = ad->curr_level;
+
+	if (ad->curr_level >= ad->dcount - 1)
+		return;
+
+	while (level < ad->dcount) {
+		if (IS_DOMAIN_SET(level + 1, ad->domain_mask)) {
+			ad->curr_level = level + 1;
+			break;
+		}
+		level++;
+	}
+
+	if (level == ad->dcount)
+		return;
+
+	tg_update_task_prefer_cpus(tg);
+}
+
+static void affinity_domain_down(struct task_group *tg)
+{
+	struct affinity_domain *ad = &tg->auto_affinity->ad;
+	u16 level = ad->curr_level;
+
+	if (ad->curr_level <= 0)
+		return;
+
+	while (level > 0) {
+		if (IS_DOMAIN_SET(level - 1, ad->domain_mask)) {
+			ad->curr_level = level - 1;
+			break;
+		}
+		level--;
+	}
+
+	if (!level)
+		return;
+
+	tg_update_task_prefer_cpus(tg);
+}
+
+static enum hrtimer_restart sched_auto_affi_period_timer(struct hrtimer *timer)
+{
+	struct auto_affinity *auto_affi =
+		container_of(timer, struct auto_affinity, period_timer);
+	struct task_group *tg = auto_affi->tg;
+	struct affinity_domain *ad = &auto_affi->ad;
+	struct cpumask *span = ad->domains[ad->curr_level];
+	unsigned long util_avg_sum = 0;
+	unsigned long tg_capacity = 0;
+	unsigned long flags;
+	int cpu;
+
+	for_each_cpu(cpu, span) {
+		util_avg_sum += cpu_util(cpu);
+		tg_capacity += capacity_of(cpu);
+	}
+
+	if (unlikely(!tg_capacity))
+		return HRTIMER_RESTART;
+
+	raw_spin_lock_irqsave(&auto_affi->lock, flags);
+	if (util_avg_sum * 100 > tg_capacity * sysctl_sched_util_low_pct) {
+		affinity_domain_up(tg);
+	} else if (util_avg_sum * 100 < tg_capacity *
+		   sysctl_sched_util_low_pct / 2) {
+		affinity_domain_down(tg);
+	}
+
+	schedstat_inc(ad->stay_cnt[ad->curr_level]);
+	hrtimer_forward_now(timer, auto_affi->period);
+	raw_spin_unlock_irqrestore(&auto_affi->lock, flags);
+	return HRTIMER_RESTART;
+}
+
+static int tg_update_affinity_domain_down(struct task_group *tg, void *data)
+{
+	struct auto_affinity *auto_affi = tg->auto_affinity;
+	struct affinity_domain *ad;
+	int *cpu_state = data;
+	unsigned long flags;
+	int i;
+
+	if (!auto_affi)
+		return 0;
+
+	ad = &tg->auto_affinity->ad;
+	raw_spin_lock_irqsave(&auto_affi->lock, flags);
+
+	for (i = 0; i < ad->dcount; i++) {
+		if (!cpumask_test_cpu(cpu_state[0], ad->domains_orig[i]))
+			continue;
+
+		/* online */
+		if (cpu_state[1])
+			cpumask_set_cpu(cpu_state[0], ad->domains[i]);
+		else
+			cpumask_clear_cpu(cpu_state[0], ad->domains[i]);
+	}
+	raw_spin_unlock_irqrestore(&auto_affi->lock, flags);
+
+	if (!smart_grid_used())
+		return 0;
+
+	if (auto_affi->mode)
+		tg_update_task_prefer_cpus(tg);
+	return 0;
+}
+
+void tg_update_affinity_domains(int cpu, int online)
+{
+	int cpu_state[2];
+
+	cpu_state[0] = cpu;
+	cpu_state[1] = online;
+
+	rcu_read_lock();
+	walk_tg_tree(tg_update_affinity_domain_down, tg_nop, cpu_state);
+	rcu_read_unlock();
+}
+
+void start_auto_affinity(struct auto_affinity *auto_affi)
+{
+	struct task_group *tg = auto_affi->tg;
+	ktime_t delay_ms;
+
+	if (auto_affi->period_active == 1)
+		return;
+
+	tg_update_task_prefer_cpus(tg);
+
+	auto_affi->period_active = 1;
+	delay_ms = ms_to_ktime(sysctl_affinity_adjust_delay_ms);
+	hrtimer_forward_now(&auto_affi->period_timer, delay_ms);
+	hrtimer_start_expires(&auto_affi->period_timer,
+				HRTIMER_MODE_ABS_PINNED);
+	smart_grid_usage_inc();
+}
+
+void stop_auto_affinity(struct auto_affinity *auto_affi)
+{
+	struct task_group *tg = auto_affi->tg;
+	struct affinity_domain *ad = &auto_affi->ad;
+
+	if (auto_affi->period_active == 0)
+		return;
+
+	hrtimer_cancel(&auto_affi->period_timer);
+	auto_affi->period_active = 0;
+	ad->curr_level = ad->dcount > 0 ? ad->dcount - 1 : 0;
+
+	tg_update_task_prefer_cpus(tg);
+	smart_grid_usage_dec();
+}
+
+static struct sched_group *sd_find_idlest_group(struct sched_domain *sd)
+{
+	struct sched_group *idlest = NULL, *group = sd->groups;
+	unsigned long min_runnable_load = ULONG_MAX;
+	unsigned long min_avg_load = ULONG_MAX;
+	int imbalance_scale = 100 + (sd->imbalance_pct-100)/2;
+	unsigned long imbalance = scale_load_down(NICE_0_LOAD) *
+				(sd->imbalance_pct-100) / 100;
+
+	do {
+		unsigned long load, avg_load, runnable_load;
+		int i;
+
+		avg_load = 0;
+		runnable_load = 0;
+
+		for_each_cpu(i, sched_group_span(group)) {
+			load = target_load(i, 0);
+			runnable_load += load;
+			avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs);
+		}
+
+		avg_load = (avg_load * SCHED_CAPACITY_SCALE) /
+					group->sgc->capacity;
+		runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) /
+					group->sgc->capacity;
+
+		if (min_runnable_load > (runnable_load + imbalance)) {
+			min_runnable_load = runnable_load;
+			min_avg_load = avg_load;
+			idlest = group;
+		} else if ((runnable_load < (min_runnable_load + imbalance)) &&
+			   (100*min_avg_load > imbalance_scale*avg_load)) {
+			min_avg_load = avg_load;
+			idlest = group;
+		}
+	} while (group = group->next, group != sd->groups);
+
+	return idlest ? idlest : group;
+}
+
+static int group_find_idlest_cpu(struct sched_group *group)
+{
+	int least_loaded_cpu = cpumask_first(sched_group_span(group));
+	unsigned long load, min_load = ULONG_MAX;
+	unsigned int min_exit_latency = UINT_MAX;
+	u64 latest_idle_timestamp = 0;
+	int shallowest_idle_cpu = -1;
+	int i;
+
+	if (group->group_weight == 1)
+		return least_loaded_cpu;
+
+	for_each_cpu(i, sched_group_span(group)) {
+		if (sched_idle_cpu(i))
+			return i;
+
+		if (available_idle_cpu(i)) {
+			struct rq *rq = cpu_rq(i);
+			struct cpuidle_state *idle = idle_get_state(rq);
+
+			if (idle && idle->exit_latency < min_exit_latency) {
+				min_exit_latency = idle->exit_latency;
+				latest_idle_timestamp = rq->idle_stamp;
+				shallowest_idle_cpu = i;
+			} else if ((!idle ||
+				   idle->exit_latency == min_exit_latency) &&
+				   rq->idle_stamp > latest_idle_timestamp) {
+				latest_idle_timestamp = rq->idle_stamp;
+				shallowest_idle_cpu = i;
+			}
+		} else if (shallowest_idle_cpu == -1) {
+			load = weighted_cpuload(cpu_rq(i));
+			if (load < min_load) {
+				min_load = load;
+				least_loaded_cpu = i;
+			}
+		}
+	}
+
+	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu :
+			least_loaded_cpu;
+}
+
+void free_affinity_domains(struct affinity_domain *ad)
+{
+	int i;
+
+	for (i = 0; i < ad->dcount; i++) {
+		kfree(ad->domains[i]);
+		ad->domains[i] = NULL;
+	}
+	ad->dcount = 0;
+}
+
+static int init_affinity_domains_orig(struct affinity_domain *ad)
+{
+	int i, j;
+
+	for (i = 0; i < ad->dcount; i++) {
+		ad->domains_orig[i] = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		if (!ad->domains_orig[i])
+			goto err;
+
+		cpumask_copy(ad->domains_orig[i], ad->domains[i]);
+	}
+
+	return 0;
+err:
+	for (j = 0; j < i; j++) {
+		kfree(ad->domains_orig[j]);
+		ad->domains_orig[i] = NULL;
+	}
+	return -ENOMEM;
+}
+
+static int init_affinity_domains(struct affinity_domain *ad)
+{
+	struct sched_domain *sd = NULL, *tmp;
+	struct sched_group *idlest = NULL;
+	int ret = -ENOMEM;
+	int dcount = 0;
+	int i = 0;
+	int cpu;
+
+	rcu_read_lock();
+	cpu = cpumask_first_and(cpu_active_mask,
+				housekeeping_cpumask(HK_FLAG_DOMAIN));
+	for_each_domain(cpu, tmp) {
+		sd = tmp;
+		dcount++;
+	}
+
+	if (!sd) {
+		ad->dcount = 0;
+		rcu_read_unlock();
+		return -EINVAL;
+	}
+	rcu_read_unlock();
+
+	for (i = 0; i < dcount; i++) {
+		ad->domains[i] = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
+		if (!ad->domains[i])
+			goto err;
+	}
+
+	rcu_read_lock();
+	idlest = sd_find_idlest_group(sd);
+	cpu = group_find_idlest_cpu(idlest);
+	i = 0;
+	for_each_domain(cpu, tmp) {
+		cpumask_copy(ad->domains[i], sched_domain_span(tmp));
+		__schedstat_set(ad->stay_cnt[i], 0);
+		i++;
+	}
+	rcu_read_unlock();
+
+	ad->dcount = dcount;
+	ad->curr_level = ad->dcount > 0 ? ad->dcount - 1 : 0;
+	ad->domain_mask = (1 << ad->dcount) - 1;
+
+	ret = init_affinity_domains_orig(ad);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	free_affinity_domains(ad);
+	return ret;
+}
+
+int init_auto_affinity(struct task_group *tg)
+{
+	struct auto_affinity *auto_affi;
+	int ret;
+
+	auto_affi = kmalloc(sizeof(*auto_affi), GFP_KERNEL);
+	if (!auto_affi)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&auto_affi->lock);
+	auto_affi->mode = 0;
+	auto_affi->period_active = 0;
+	auto_affi->period = ms_to_ktime(AUTO_AFFINITY_DEFAULT_PERIOD_MS);
+	hrtimer_init(&auto_affi->period_timer, CLOCK_MONOTONIC,
+		HRTIMER_MODE_ABS_PINNED);
+	auto_affi->period_timer.function = sched_auto_affi_period_timer;
+
+	ret = init_affinity_domains(&auto_affi->ad);
+	if (ret) {
+		kfree(auto_affi);
+		return ret;
+	}
+
+	auto_affi->tg = tg;
+	tg->auto_affinity = auto_affi;
+	return 0;
+}
+
+static void destroy_auto_affinity(struct task_group *tg)
+{
+	struct auto_affinity *auto_affi = tg->auto_affinity;
+
+	hrtimer_cancel(&auto_affi->period_timer);
+	free_affinity_domains(&auto_affi->ad);
+
+	kfree(tg->auto_affinity);
+	tg->auto_affinity = NULL;
+}
+#else
+static void destroy_auto_affinity(struct task_group *tg) {}
+#endif
+
 /**************************************************
  * CFS operations on tasks:
  */
@@ -6733,7 +7144,7 @@ static inline bool prefer_cpus_valid(struct task_struct *p)
 /*
  * set_task_select_cpus: select the cpu range for task
  * @p: the task whose available cpu range will to set
- * @idlest_cpu: the cpu which is the idlest in prefer cpus
+ *uto_affinity_used @idlest_cpu: the cpu which is the idlest in prefer cpus
  *
  * If sum of 'util_avg' among 'preferred_cpus' lower than the percentage
  * 'sysctl_sched_util_low_pct' of 'preferred_cpus' capacity, select
@@ -6757,6 +7168,13 @@ static void set_task_select_cpus(struct task_struct *p, int *idlest_cpu,
 	if (!prefer_cpus_valid(p))
 		return;
 
+	if (smart_grid_used()) {
+		p->select_cpus = p->prefer_cpus;
+		if (idlest_cpu)
+			*idlest_cpu = cpumask_first(p->select_cpus);
+		return;
+	}
+
 	rcu_read_lock();
 	tg = task_group(p);
 	for_each_cpu(cpu, p->prefer_cpus) {
@@ -10928,6 +11346,7 @@ void free_fair_sched_group(struct task_group *tg)
 	int i;
 
 	destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
+	destroy_auto_affinity(tg);
 
 	for_each_possible_cpu(i) {
 #ifdef CONFIG_QOS_SCHED
@@ -10948,7 +11367,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 {
 	struct sched_entity *se;
 	struct cfs_rq *cfs_rq;
-	int i;
+	int i, ret;
 
 	tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL);
 	if (!tg->cfs_rq)
@@ -10960,6 +11379,9 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	tg->shares = NICE_0_LOAD;
 
 	init_cfs_bandwidth(tg_cfs_bandwidth(tg));
+	ret = init_auto_affinity(tg);
+	if (ret)
+		goto err;
 
 	for_each_possible_cpu(i) {
 		cfs_rq = kzalloc_node(sizeof(struct cfs_rq),
@@ -10982,6 +11404,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 err_free_rq:
 	kfree(cfs_rq);
 err:
+	destroy_auto_affinity(tg);
 	return 0;
 }
 

kernel/sched/sched.h

@@ -361,6 +361,34 @@ struct cfs_bandwidth {
 #endif
 };
 
+
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+#define AD_LEVEL_MAX		8
+
+struct affinity_domain {
+	int			dcount;
+	int			curr_level;
+	u32			domain_mask;
+#ifdef CONFIG_SCHEDSTATS
+	u64			stay_cnt[AD_LEVEL_MAX];
+#endif
+	struct cpumask		*domains[AD_LEVEL_MAX];
+	struct cpumask		*domains_orig[AD_LEVEL_MAX];
+};
+#endif
+
+struct auto_affinity {
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+	raw_spinlock_t		lock;
+	u64			mode;
+	ktime_t			period;
+	struct hrtimer		period_timer;
+	int			period_active;
+	struct affinity_domain	ad;
+	struct task_group	*tg;
+#endif
+};
+
 /* Task group related information */
 struct task_group {
 	struct cgroup_subsys_state css;
@@ -407,7 +435,12 @@ struct task_group {
 #else
 	KABI_RESERVE(1)
 #endif
+
+#if defined(CONFIG_QOS_SCHED_SMART_GRID) && !defined(__GENKSYMS__)
+	struct auto_affinity	*auto_affinity;
+#else
 	KABI_RESERVE(2)
+#endif
 };
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -475,6 +508,21 @@ extern void sched_offline_group(struct task_group *tg);
 
 extern void sched_move_task(struct task_struct *tsk);
 
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+extern void start_auto_affinity(struct auto_affinity *auto_affi);
+extern void stop_auto_affinity(struct auto_affinity *auto_affi);
+extern int init_auto_affinity(struct task_group *tg);
+extern void tg_update_affinity_domains(int cpu, int online);
+
+#else
+static inline int init_auto_affinity(struct task_group *tg)
+{
+	return 0;
+}
+
+static inline void tg_update_affinity_domains(int cpu, int online) {}
+#endif
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 

kernel/sysctl.c

@@ -1336,6 +1336,15 @@ static struct ctl_table kern_table[] = {
 		.extra1         = &zero,
 		.extra2		= &one_hundred,
 	},
+#endif
+#ifdef CONFIG_QOS_SCHED_SMART_GRID
+	{
+		.procname	= "affinity_adjust_delay_ms",
+		.data		= &sysctl_affinity_adjust_delay_ms,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
 #endif
 	{ }
 };